diff options
Diffstat (limited to 'arch/x86')
72 files changed, 2072 insertions, 1093 deletions
diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index 4fff6ed46e90..928820e61cb5 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -62,6 +62,7 @@ config X86 select ACPI_HOTPLUG_CPU if ACPI_PROCESSOR && HOTPLUG_CPU select ARCH_32BIT_OFF_T if X86_32 select ARCH_CLOCKSOURCE_INIT + select ARCH_CONFIGURES_CPU_MITIGATIONS select ARCH_CORRECT_STACKTRACE_ON_KRETPROBE select ARCH_ENABLE_HUGEPAGE_MIGRATION if X86_64 && HUGETLB_PAGE && MIGRATION select ARCH_ENABLE_MEMORY_HOTPLUG if X86_64 @@ -2488,17 +2489,21 @@ config PREFIX_SYMBOLS def_bool y depends on CALL_PADDING && !CFI_CLANG -menuconfig SPECULATION_MITIGATIONS - bool "Mitigations for speculative execution vulnerabilities" +menuconfig CPU_MITIGATIONS + bool "Mitigations for CPU vulnerabilities" default y help - Say Y here to enable options which enable mitigations for - speculative execution hardware vulnerabilities. + Say Y here to enable options which enable mitigations for hardware + vulnerabilities (usually related to speculative execution). + Mitigations can be disabled or restricted to SMT systems at runtime + via the "mitigations" kernel parameter. - If you say N, all mitigations will be disabled. You really - should know what you are doing to say so. + If you say N, all mitigations will be disabled. This CANNOT be + overridden at runtime. -if SPECULATION_MITIGATIONS + Say 'Y', unless you really know what you are doing. + +if CPU_MITIGATIONS config MITIGATION_PAGE_TABLE_ISOLATION bool "Remove the kernel mapping in user mode" @@ -2633,6 +2638,16 @@ config MITIGATION_RFDS stored in floating point, vector and integer registers. See also <file:Documentation/admin-guide/hw-vuln/reg-file-data-sampling.rst> +config MITIGATION_SPECTRE_BHI + bool "Mitigate Spectre-BHB (Branch History Injection)" + depends on CPU_SUP_INTEL + default y + help + Enable BHI mitigations. BHI attacks are a form of Spectre V2 attacks + where the branch history buffer is poisoned to speculatively steer + indirect branches. + See <file:Documentation/admin-guide/hw-vuln/spectre.rst> + endif config ARCH_HAS_ADD_PAGES diff --git a/arch/x86/Kconfig.assembler b/arch/x86/Kconfig.assembler index 8ad41da301e5..59aedf32c4ea 100644 --- a/arch/x86/Kconfig.assembler +++ b/arch/x86/Kconfig.assembler @@ -25,6 +25,16 @@ config AS_GFNI help Supported by binutils >= 2.30 and LLVM integrated assembler +config AS_VAES + def_bool $(as-instr,vaesenc %ymm0$(comma)%ymm1$(comma)%ymm2) + help + Supported by binutils >= 2.30 and LLVM integrated assembler + +config AS_VPCLMULQDQ + def_bool $(as-instr,vpclmulqdq \$0x10$(comma)%ymm0$(comma)%ymm1$(comma)%ymm2) + help + Supported by binutils >= 2.30 and LLVM integrated assembler + config AS_WRUSS def_bool $(as-instr,wrussq %rax$(comma)(%rbx)) help diff --git a/arch/x86/configs/hardening.config b/arch/x86/configs/hardening.config index 7b497f3b7bc3..de319852a1e9 100644 --- a/arch/x86/configs/hardening.config +++ b/arch/x86/configs/hardening.config @@ -10,5 +10,8 @@ CONFIG_INTEL_IOMMU_DEFAULT_ON=y CONFIG_INTEL_IOMMU_SVM=y CONFIG_AMD_IOMMU=y +# Enforce CET Indirect Branch Tracking in the kernel. +CONFIG_X86_KERNEL_IBT=y + # Enable CET Shadow Stack for userspace. CONFIG_X86_USER_SHADOW_STACK=y diff --git a/arch/x86/crypto/Makefile b/arch/x86/crypto/Makefile index 9aa46093c91b..9c5ce5613738 100644 --- a/arch/x86/crypto/Makefile +++ b/arch/x86/crypto/Makefile @@ -48,7 +48,8 @@ chacha-x86_64-$(CONFIG_AS_AVX512) += chacha-avx512vl-x86_64.o obj-$(CONFIG_CRYPTO_AES_NI_INTEL) += aesni-intel.o aesni-intel-y := aesni-intel_asm.o aesni-intel_glue.o -aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o aes_ctrby8_avx-x86_64.o +aesni-intel-$(CONFIG_64BIT) += aesni-intel_avx-x86_64.o \ + aes_ctrby8_avx-x86_64.o aes-xts-avx-x86_64.o obj-$(CONFIG_CRYPTO_SHA1_SSSE3) += sha1-ssse3.o sha1-ssse3-y := sha1_avx2_x86_64_asm.o sha1_ssse3_asm.o sha1_ssse3_glue.o diff --git a/arch/x86/crypto/aes-xts-avx-x86_64.S b/arch/x86/crypto/aes-xts-avx-x86_64.S new file mode 100644 index 000000000000..48f97b79f7a9 --- /dev/null +++ b/arch/x86/crypto/aes-xts-avx-x86_64.S @@ -0,0 +1,845 @@ +/* SPDX-License-Identifier: GPL-2.0-or-later */ +/* + * AES-XTS for modern x86_64 CPUs + * + * Copyright 2024 Google LLC + * + * Author: Eric Biggers <ebiggers@google.com> + */ + +/* + * This file implements AES-XTS for modern x86_64 CPUs. To handle the + * complexities of coding for x86 SIMD, e.g. where every vector length needs + * different code, it uses a macro to generate several implementations that + * share similar source code but are targeted at different CPUs, listed below: + * + * AES-NI + AVX + * - 128-bit vectors (1 AES block per vector) + * - VEX-coded instructions + * - xmm0-xmm15 + * - This is for older CPUs that lack VAES but do have AVX. + * + * VAES + VPCLMULQDQ + AVX2 + * - 256-bit vectors (2 AES blocks per vector) + * - VEX-coded instructions + * - ymm0-ymm15 + * - This is for CPUs that have VAES but lack AVX512 or AVX10, + * e.g. Intel's Alder Lake and AMD's Zen 3. + * + * VAES + VPCLMULQDQ + AVX10/256 + BMI2 + * - 256-bit vectors (2 AES blocks per vector) + * - EVEX-coded instructions + * - ymm0-ymm31 + * - This is for CPUs that have AVX512 but where using zmm registers causes + * downclocking, and for CPUs that have AVX10/256 but not AVX10/512. + * - By "AVX10/256" we really mean (AVX512BW + AVX512VL) || AVX10/256. + * To avoid confusion with 512-bit, we just write AVX10/256. + * + * VAES + VPCLMULQDQ + AVX10/512 + BMI2 + * - Same as the previous one, but upgrades to 512-bit vectors + * (4 AES blocks per vector) in zmm0-zmm31. + * - This is for CPUs that have good AVX512 or AVX10/512 support. + * + * This file doesn't have an implementation for AES-NI alone (without AVX), as + * the lack of VEX would make all the assembly code different. + * + * When we use VAES, we also use VPCLMULQDQ to parallelize the computation of + * the XTS tweaks. This avoids a bottleneck. Currently there don't seem to be + * any CPUs that support VAES but not VPCLMULQDQ. If that changes, we might + * need to start also providing an implementation using VAES alone. + * + * The AES-XTS implementations in this file support everything required by the + * crypto API, including support for arbitrary input lengths and multi-part + * processing. However, they are most heavily optimized for the common case of + * power-of-2 length inputs that are processed in a single part (disk sectors). + */ + +#include <linux/linkage.h> +#include <linux/cfi_types.h> + +.section .rodata +.p2align 4 +.Lgf_poly: + // The low 64 bits of this value represent the polynomial x^7 + x^2 + x + // + 1. It is the value that must be XOR'd into the low 64 bits of the + // tweak each time a 1 is carried out of the high 64 bits. + // + // The high 64 bits of this value is just the internal carry bit that + // exists when there's a carry out of the low 64 bits of the tweak. + .quad 0x87, 1 + + // This table contains constants for vpshufb and vpblendvb, used to + // handle variable byte shifts and blending during ciphertext stealing + // on CPUs that don't support AVX10-style masking. +.Lcts_permute_table: + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 + .byte 0x00, 0x01, 0x02, 0x03, 0x04, 0x05, 0x06, 0x07 + .byte 0x08, 0x09, 0x0a, 0x0b, 0x0c, 0x0d, 0x0e, 0x0f + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 + .byte 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80, 0x80 +.text + +// Function parameters +.set KEY, %rdi // Initially points to crypto_aes_ctx, then is + // advanced to point to 7th-from-last round key +.set SRC, %rsi // Pointer to next source data +.set DST, %rdx // Pointer to next destination data +.set LEN, %ecx // Remaining length in bytes +.set LEN8, %cl +.set LEN64, %rcx +.set TWEAK, %r8 // Pointer to next tweak + +// %rax holds the AES key length in bytes. +.set KEYLEN, %eax +.set KEYLEN64, %rax + +// %r9-r11 are available as temporaries. + +.macro _define_Vi i +.if VL == 16 + .set V\i, %xmm\i +.elseif VL == 32 + .set V\i, %ymm\i +.elseif VL == 64 + .set V\i, %zmm\i +.else + .error "Unsupported Vector Length (VL)" +.endif +.endm + +.macro _define_aliases + // Define register aliases V0-V15, or V0-V31 if all 32 SIMD registers + // are available, that map to the xmm, ymm, or zmm registers according + // to the selected Vector Length (VL). + _define_Vi 0 + _define_Vi 1 + _define_Vi 2 + _define_Vi 3 + _define_Vi 4 + _define_Vi 5 + _define_Vi 6 + _define_Vi 7 + _define_Vi 8 + _define_Vi 9 + _define_Vi 10 + _define_Vi 11 + _define_Vi 12 + _define_Vi 13 + _define_Vi 14 + _define_Vi 15 +.if USE_AVX10 + _define_Vi 16 + _define_Vi 17 + _define_Vi 18 + _define_Vi 19 + _define_Vi 20 + _define_Vi 21 + _define_Vi 22 + _define_Vi 23 + _define_Vi 24 + _define_Vi 25 + _define_Vi 26 + _define_Vi 27 + _define_Vi 28 + _define_Vi 29 + _define_Vi 30 + _define_Vi 31 +.endif + + // V0-V3 hold the data blocks during the main loop, or temporary values + // otherwise. V4-V5 hold temporary values. + + // V6-V9 hold XTS tweaks. Each 128-bit lane holds one tweak. + .set TWEAK0_XMM, %xmm6 + .set TWEAK0, V6 + .set TWEAK1_XMM, %xmm7 + .set TWEAK1, V7 + .set TWEAK2, V8 + .set TWEAK3, V9 + + // V10-V13 are used for computing the next values of TWEAK[0-3]. + .set NEXT_TWEAK0, V10 + .set NEXT_TWEAK1, V11 + .set NEXT_TWEAK2, V12 + .set NEXT_TWEAK3, V13 + + // V14 holds the constant from .Lgf_poly, copied to all 128-bit lanes. + .set GF_POLY_XMM, %xmm14 + .set GF_POLY, V14 + + // V15 holds the key for AES "round 0", copied to all 128-bit lanes. + .set KEY0_XMM, %xmm15 + .set KEY0, V15 + + // If 32 SIMD registers are available, then V16-V29 hold the remaining + // AES round keys, copied to all 128-bit lanes. + // + // AES-128, AES-192, and AES-256 use different numbers of round keys. + // To allow handling all three variants efficiently, we align the round + // keys to the *end* of this register range. I.e., AES-128 uses + // KEY5-KEY14, AES-192 uses KEY3-KEY14, and AES-256 uses KEY1-KEY14. + // (All also use KEY0 for the XOR-only "round" at the beginning.) +.if USE_AVX10 + .set KEY1_XMM, %xmm16 + .set KEY1, V16 + .set KEY2_XMM, %xmm17 + .set KEY2, V17 + .set KEY3_XMM, %xmm18 + .set KEY3, V18 + .set KEY4_XMM, %xmm19 + .set KEY4, V19 + .set KEY5_XMM, %xmm20 + .set KEY5, V20 + .set KEY6_XMM, %xmm21 + .set KEY6, V21 + .set KEY7_XMM, %xmm22 + .set KEY7, V22 + .set KEY8_XMM, %xmm23 + .set KEY8, V23 + .set KEY9_XMM, %xmm24 + .set KEY9, V24 + .set KEY10_XMM, %xmm25 + .set KEY10, V25 + .set KEY11_XMM, %xmm26 + .set KEY11, V26 + .set KEY12_XMM, %xmm27 + .set KEY12, V27 + .set KEY13_XMM, %xmm28 + .set KEY13, V28 + .set KEY14_XMM, %xmm29 + .set KEY14, V29 +.endif + // V30-V31 are currently unused. +.endm + +// Move a vector between memory and a register. +.macro _vmovdqu src, dst +.if VL < 64 + vmovdqu \src, \dst +.else + vmovdqu8 \src, \dst +.endif +.endm + +// Broadcast a 128-bit value into a vector. +.macro _vbroadcast128 src, dst +.if VL == 16 && !USE_AVX10 + vmovdqu \src, \dst +.elseif VL == 32 && !USE_AVX10 + vbroadcasti128 \src, \dst +.else + vbroadcasti32x4 \src, \dst +.endif +.endm + +// XOR two vectors together. +.macro _vpxor src1, src2, dst +.if USE_AVX10 + vpxord \src1, \src2, \dst +.else + vpxor \src1, \src2, \dst +.endif +.endm + +// XOR three vectors together. +.macro _xor3 src1, src2, src3_and_dst +.if USE_AVX10 + // vpternlogd with immediate 0x96 is a three-argument XOR. + vpternlogd $0x96, \src1, \src2, \src3_and_dst +.else + vpxor \src1, \src3_and_dst, \src3_and_dst + vpxor \src2, \src3_and_dst, \src3_and_dst +.endif +.endm + +// Given a 128-bit XTS tweak in the xmm register \src, compute the next tweak +// (by multiplying by the polynomial 'x') and write it to \dst. +.macro _next_tweak src, tmp, dst + vpshufd $0x13, \src, \tmp + vpaddq \src, \src, \dst + vpsrad $31, \tmp, \tmp + vpand GF_POLY_XMM, \tmp, \tmp + vpxor \tmp, \dst, \dst +.endm + +// Given the XTS tweak(s) in the vector \src, compute the next vector of +// tweak(s) (by multiplying by the polynomial 'x^(VL/16)') and write it to \dst. +// +// If VL > 16, then there are multiple tweaks, and we use vpclmulqdq to compute +// all tweaks in the vector in parallel. If VL=16, we just do the regular +// computation without vpclmulqdq, as it's the faster method for a single tweak. +.macro _next_tweakvec src, tmp1, tmp2, dst +.if VL == 16 + _next_tweak \src, \tmp1, \dst +.else + vpsrlq $64 - VL/16, \src, \tmp1 + vpclmulqdq $0x01, GF_POLY, \tmp1, \tmp2 + vpslldq $8, \tmp1, \tmp1 + vpsllq $VL/16, \src, \dst + _xor3 \tmp1, \tmp2, \dst +.endif +.endm + +// Given the first XTS tweak at (TWEAK), compute the first set of tweaks and +// store them in the vector registers TWEAK0-TWEAK3. Clobbers V0-V5. +.macro _compute_first_set_of_tweaks + vmovdqu (TWEAK), TWEAK0_XMM + _vbroadcast128 .Lgf_poly(%rip), GF_POLY +.if VL == 16 + // With VL=16, multiplying by x serially is fastest. + _next_tweak TWEAK0, %xmm0, TWEAK1 + _next_tweak TWEAK1, %xmm0, TWEAK2 + _next_tweak TWEAK2, %xmm0, TWEAK3 +.else +.if VL == 32 + // Compute the second block of TWEAK0. + _next_tweak TWEAK0_XMM, %xmm0, %xmm1 + vinserti128 $1, %xmm1, TWEAK0, TWEAK0 +.elseif VL == 64 + // Compute the remaining blocks of TWEAK0. + _next_tweak TWEAK0_XMM, %xmm0, %xmm1 + _next_tweak %xmm1, %xmm0, %xmm2 + _next_tweak %xmm2, %xmm0, %xmm3 + vinserti32x4 $1, %xmm1, TWEAK0, TWEAK0 + vinserti32x4 $2, %xmm2, TWEAK0, TWEAK0 + vinserti32x4 $3, %xmm3, TWEAK0, TWEAK0 +.endif + // Compute TWEAK[1-3] from TWEAK0. + vpsrlq $64 - 1*VL/16, TWEAK0, V0 + vpsrlq $64 - 2*VL/16, TWEAK0, V2 + vpsrlq $64 - 3*VL/16, TWEAK0, V4 + vpclmulqdq $0x01, GF_POLY, V0, V1 + vpclmulqdq $0x01, GF_POLY, V2, V3 + vpclmulqdq $0x01, GF_POLY, V4, V5 + vpslldq $8, V0, V0 + vpslldq $8, V2, V2 + vpslldq $8, V4, V4 + vpsllq $1*VL/16, TWEAK0, TWEAK1 + vpsllq $2*VL/16, TWEAK0, TWEAK2 + vpsllq $3*VL/16, TWEAK0, TWEAK3 +.if USE_AVX10 + vpternlogd $0x96, V0, V1, TWEAK1 + vpternlogd $0x96, V2, V3, TWEAK2 + vpternlogd $0x96, V4, V5, TWEAK3 +.else + vpxor V0, TWEAK1, TWEAK1 + vpxor V2, TWEAK2, TWEAK2 + vpxor V4, TWEAK3, TWEAK3 + vpxor V1, TWEAK1, TWEAK1 + vpxor V3, TWEAK2, TWEAK2 + vpxor V5, TWEAK3, TWEAK3 +.endif +.endif +.endm + +// Do one step in computing the next set of tweaks using the method of just +// multiplying by x repeatedly (the same method _next_tweak uses). +.macro _tweak_step_mulx i +.if \i == 0 + .set PREV_TWEAK, TWEAK3 + .set NEXT_TWEAK, NEXT_TWEAK0 +.elseif \i == 5 + .set PREV_TWEAK, NEXT_TWEAK0 + .set NEXT_TWEAK, NEXT_TWEAK1 +.elseif \i == 10 + .set PREV_TWEAK, NEXT_TWEAK1 + .set NEXT_TWEAK, NEXT_TWEAK2 +.elseif \i == 15 + .set PREV_TWEAK, NEXT_TWEAK2 + .set NEXT_TWEAK, NEXT_TWEAK3 +.endif +.if \i >= 0 && \i < 20 && \i % 5 == 0 + vpshufd $0x13, PREV_TWEAK, V5 +.elseif \i >= 0 && \i < 20 && \i % 5 == 1 + vpaddq PREV_TWEAK, PREV_TWEAK, NEXT_TWEAK +.elseif \i >= 0 && \i < 20 && \i % 5 == 2 + vpsrad $31, V5, V5 +.elseif \i >= 0 && \i < 20 && \i % 5 == 3 + vpand GF_POLY, V5, V5 +.elseif \i >= 0 && \i < 20 && \i % 5 == 4 + vpxor V5, NEXT_TWEAK, NEXT_TWEAK +.elseif \i == 1000 + vmovdqa NEXT_TWEAK0, TWEAK0 + vmovdqa NEXT_TWEAK1, TWEAK1 + vmovdqa NEXT_TWEAK2, TWEAK2 + vmovdqa NEXT_TWEAK3, TWEAK3 +.endif +.endm + +// Do one step in computing the next set of tweaks using the VPCLMULQDQ method +// (the same method _next_tweakvec uses for VL > 16). This means multiplying +// each tweak by x^(4*VL/16) independently. Since 4*VL/16 is a multiple of 8 +// when VL > 16 (which it is here), the needed shift amounts are byte-aligned, +// which allows the use of vpsrldq and vpslldq to do 128-bit wide shifts. +.macro _tweak_step_pclmul i +.if \i == 0 + vpsrldq $(128 - 4*VL/16) / 8, TWEAK0, NEXT_TWEAK0 +.elseif \i == 2 + vpsrldq $(128 - 4*VL/16) / 8, TWEAK1, NEXT_TWEAK1 +.elseif \i == 4 + vpsrldq $(128 - 4*VL/16) / 8, TWEAK2, NEXT_TWEAK2 +.elseif \i == 6 + vpsrldq $(128 - 4*VL/16) / 8, TWEAK3, NEXT_TWEAK3 +.elseif \i == 8 + vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK0, NEXT_TWEAK0 +.elseif \i == 10 + vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK1, NEXT_TWEAK1 +.elseif \i == 12 + vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK2, NEXT_TWEAK2 +.elseif \i == 14 + vpclmulqdq $0x00, GF_POLY, NEXT_TWEAK3, NEXT_TWEAK3 +.elseif \i == 1000 + vpslldq $(4*VL/16) / 8, TWEAK0, TWEAK0 + vpslldq $(4*VL/16) / 8, TWEAK1, TWEAK1 + vpslldq $(4*VL/16) / 8, TWEAK2, TWEAK2 + vpslldq $(4*VL/16) / 8, TWEAK3, TWEAK3 + _vpxor NEXT_TWEAK0, TWEAK0, TWEAK0 + _vpxor NEXT_TWEAK1, TWEAK1, TWEAK1 + _vpxor NEXT_TWEAK2, TWEAK2, TWEAK2 + _vpxor NEXT_TWEAK3, TWEAK3, TWEAK3 +.endif +.endm + +// _tweak_step does one step of the computation of the next set of tweaks from +// TWEAK[0-3]. To complete all steps, this is invoked with increasing values of +// \i that include at least 0 through 19, then 1000 which signals the last step. +// +// This is used to interleave the computation of the next set of tweaks with the +// AES en/decryptions, which increases performance in some cases. +.macro _tweak_step i +.if VL == 16 + _tweak_step_mulx \i +.else + _tweak_step_pclmul \i +.endif +.endm + +.macro _setup_round_keys enc + + // Select either the encryption round keys or the decryption round keys. +.if \enc + .set OFFS, 0 +.else + .set OFFS, 240 +.endif + + // Load the round key for "round 0". + _vbroadcast128 OFFS(KEY), KEY0 + + // Increment KEY to make it so that 7*16(KEY) is the last round key. + // For AES-128, increment by 3*16, resulting in the 10 round keys (not + // counting the zero-th round key which was just loaded into KEY0) being + // -2*16(KEY) through 7*16(KEY). For AES-192, increment by 5*16 and use + // 12 round keys -4*16(KEY) through 7*16(KEY). For AES-256, increment + // by 7*16 and use 14 round keys -6*16(KEY) through 7*16(KEY). + // + // This rebasing provides two benefits. First, it makes the offset to + // any round key be in the range [-96, 112], fitting in a signed byte. + // This shortens VEX-encoded instructions that access the later round + // keys which otherwise would need 4-byte offsets. Second, it makes it + // easy to do AES-128 and AES-192 by skipping irrelevant rounds at the + // beginning. Skipping rounds at the end doesn't work as well because + // the last round needs different instructions. + // + // An alternative approach would be to roll up all the round loops. We + // don't do that because it isn't compatible with caching the round keys + // in registers which we do when possible (see below), and also because + // it seems unwise to rely *too* heavily on the CPU's branch predictor. + lea OFFS-16(KEY, KEYLEN64, 4), KEY + + // If all 32 SIMD registers are available, cache all the round keys. +.if USE_AVX10 + cmp $24, KEYLEN + jl .Laes128\@ + je .Laes192\@ + _vbroadcast128 -6*16(KEY), KEY1 + _vbroadcast128 -5*16(KEY), KEY2 +.Laes192\@: + _vbroadcast128 -4*16(KEY), KEY3 + _vbroadcast128 -3*16(KEY), KEY4 +.Laes128\@: + _vbroadcast128 -2*16(KEY), KEY5 + _vbroadcast128 -1*16(KEY), KEY6 + _vbroadcast128 0*16(KEY), KEY7 + _vbroadcast128 1*16(KEY), KEY8 + _vbroadcast128 2*16(KEY), KEY9 + _vbroadcast128 3*16(KEY), KEY10 + _vbroadcast128 4*16(KEY), KEY11 + _vbroadcast128 5*16(KEY), KEY12 + _vbroadcast128 6*16(KEY), KEY13 + _vbroadcast128 7*16(KEY), KEY14 +.endif +.endm + +// Do a single round of AES encryption (if \enc==1) or decryption (if \enc==0) +// on the block(s) in \data using the round key(s) in \key. The register length +// determines the number of AES blocks en/decrypted. +.macro _vaes enc, last, key, data +.if \enc +.if \last + vaesenclast \key, \data, \data +.else + vaesenc \key, \data, \data +.endif +.else +.if \last + vaesdeclast \key, \data, \data +.else + vaesdec \key, \data, \data +.endif +.endif +.endm + +// Do a single round of AES en/decryption on the block(s) in \data, using the +// same key for all block(s). The round key is loaded from the appropriate +// register or memory location for round \i. May clobber V4. +.macro _vaes_1x enc, last, i, xmm_suffix, data +.if USE_AVX10 + _vaes \enc, \last, KEY\i\xmm_suffix, \data +.else +.ifnb \xmm_suffix + _vaes \enc, \last, (\i-7)*16(KEY), \data +.else + _vbroadcast128 (\i-7)*16(KEY), V4 + _vaes \enc, \last, V4, \data +.endif +.endif +.endm + +// Do a single round of AES en/decryption on the blocks in registers V0-V3, +// using the same key for all blocks. The round key is loaded from the +// appropriate register or memory location for round \i. In addition, does two +// steps of the computation of the next set of tweaks. May clobber V4. +.macro _vaes_4x enc, last, i +.if USE_AVX10 + _tweak_step (2*(\i-5)) + _vaes \enc, \last, KEY\i, V0 + _vaes \enc, \last, KEY\i, V1 + _tweak_step (2*(\i-5) + 1) + _vaes \enc, \last, KEY\i, V2 + _vaes \enc, \last, KEY\i, V3 +.else + _vbroadcast128 (\i-7)*16(KEY), V4 + _tweak_step (2*(\i-5)) + _vaes \enc, \last, V4, V0 + _vaes \enc, \last, V4, V1 + _tweak_step (2*(\i-5) + 1) + _vaes \enc, \last, V4, V2 + _vaes \enc, \last, V4, V3 +.endif +.endm + +// Do tweaked AES en/decryption (i.e., XOR with \tweak, then AES en/decrypt, +// then XOR with \tweak again) of the block(s) in \data. To process a single +// block, use xmm registers and set \xmm_suffix=_XMM. To process a vector of +// length VL, use V* registers and leave \xmm_suffix empty. May clobber V4. +.macro _aes_crypt enc, xmm_suffix, tweak, data + _xor3 KEY0\xmm_suffix, \tweak, \data + cmp $24, KEYLEN + jl .Laes128\@ + je .Laes192\@ + _vaes_1x \enc, 0, 1, \xmm_suffix, \data + _vaes_1x \enc, 0, 2, \xmm_suffix, \data +.Laes192\@: + _vaes_1x \enc, 0, 3, \xmm_suffix, \data + _vaes_1x \enc, 0, 4, \xmm_suffix, \data +.Laes128\@: + _vaes_1x \enc, 0, 5, \xmm_suffix, \data + _vaes_1x \enc, 0, 6, \xmm_suffix, \data + _vaes_1x \enc, 0, 7, \xmm_suffix, \data + _vaes_1x \enc, 0, 8, \xmm_suffix, \data + _vaes_1x \enc, 0, 9, \xmm_suffix, \data + _vaes_1x \enc, 0, 10, \xmm_suffix, \data + _vaes_1x \enc, 0, 11, \xmm_suffix, \data + _vaes_1x \enc, 0, 12, \xmm_suffix, \data + _vaes_1x \enc, 0, 13, \xmm_suffix, \data + _vaes_1x \enc, 1, 14, \xmm_suffix, \data + _vpxor \tweak, \data, \data +.endm + +.macro _aes_xts_crypt enc + _define_aliases + +.if !\enc + // When decrypting a message whose length isn't a multiple of the AES + // block length, exclude the last full block from the main loop by + // subtracting 16 from LEN. This is needed because ciphertext stealing + // decryption uses the last two tweaks in reverse order. We'll handle + // the last full block and the partial block specially at the end. + lea -16(LEN), %eax + test $15, LEN8 + cmovnz %eax, LEN +.endif + + // Load the AES key length: 16 (AES-128), 24 (AES-192), or 32 (AES-256). + movl 480(KEY), KEYLEN + + // Setup the pointer to the round keys and cache as many as possible. + _setup_round_keys \enc + + // Compute the first set of tweaks TWEAK[0-3]. + _compute_first_set_of_tweaks + + sub $4*VL, LEN + jl .Lhandle_remainder\@ + +.Lmain_loop\@: + // This is the main loop, en/decrypting 4*VL bytes per iteration. + + // XOR each source block with its tweak and the zero-th round key. +.if USE_AVX10 + vmovdqu8 0*VL(SRC), V0 + vmovdqu8 1*VL(SRC), V1 + vmovdqu8 2*VL(SRC), V2 + vmovdqu8 3*VL(SRC), V3 + vpternlogd $0x96, TWEAK0, KEY0, V0 + vpternlogd $0x96, TWEAK1, KEY0, V1 + vpternlogd $0x96, TWEAK2, KEY0, V2 + vpternlogd $0x96, TWEAK3, KEY0, V3 +.else + vpxor 0*VL(SRC), KEY0, V0 + vpxor 1*VL(SRC), KEY0, V1 + vpxor 2*VL(SRC), KEY0, V2 + vpxor 3*VL(SRC), KEY0, V3 + vpxor TWEAK0, V0, V0 + vpxor TWEAK1, V1, V1 + vpxor TWEAK2, V2, V2 + vpxor TWEAK3, V3, V3 +.endif + cmp $24, KEYLEN + jl .Laes128\@ + je .Laes192\@ + // Do all the AES rounds on the data blocks, interleaved with + // the computation of the next set of tweaks. + _vaes_4x \enc, 0, 1 + _vaes_4x \enc, 0, 2 +.Laes192\@: + _vaes_4x \enc, 0, 3 + _vaes_4x \enc, 0, 4 +.Laes128\@: + _vaes_4x \enc, 0, 5 + _vaes_4x \enc, 0, 6 + _vaes_4x \enc, 0, 7 + _vaes_4x \enc, 0, 8 + _vaes_4x \enc, 0, 9 + _vaes_4x \enc, 0, 10 + _vaes_4x \enc, 0, 11 + _vaes_4x \enc, 0, 12 + _vaes_4x \enc, 0, 13 + _vaes_4x \enc, 1, 14 + + // XOR in the tweaks again. + _vpxor TWEAK0, V0, V0 + _vpxor TWEAK1, V1, V1 + _vpxor TWEAK2, V2, V2 + _vpxor TWEAK3, V3, V3 + + // Store the destination blocks. + _vmovdqu V0, 0*VL(DST) + _vmovdqu V1, 1*VL(DST) + _vmovdqu V2, 2*VL(DST) + _vmovdqu V3, 3*VL(DST) + + // Finish computing the next set of tweaks. + _tweak_step 1000 + + add $4*VL, SRC + add $4*VL, DST + sub $4*VL, LEN + jge .Lmain_loop\@ + + // Check for the uncommon case where the data length isn't a multiple of + // 4*VL. Handle it out-of-line in order to optimize for the common + // case. In the common case, just fall through to the ret. + test $4*VL-1, LEN8 + jnz .Lhandle_remainder\@ +.Ldone\@: + // Store the next tweak back to *TWEAK to support continuation calls. + vmovdqu TWEAK0_XMM, (TWEAK) +.if VL > 16 + vzeroupper +.endif + RET + +.Lhandle_remainder\@: + + // En/decrypt any remaining full blocks, one vector at a time. +.if VL > 16 + add $3*VL, LEN // Undo extra sub of 4*VL, then sub VL. + jl .Lvec_at_a_time_done\@ +.Lvec_at_a_time\@: + _vmovdqu (SRC), V0 + _aes_crypt \enc, , TWEAK0, V0 + _vmovdqu V0, (DST) + _next_tweakvec TWEAK0, V0, V1, TWEAK0 + add $VL, SRC + add $VL, DST + sub $VL, LEN + jge .Lvec_at_a_time\@ +.Lvec_at_a_time_done\@: + add $VL-16, LEN // Undo extra sub of VL, then sub 16. +.else + add $4*VL-16, LEN // Undo extra sub of 4*VL, then sub 16. +.endif + + // En/decrypt any remaining full blocks, one at a time. + jl .Lblock_at_a_time_done\@ +.Lblock_at_a_time\@: + vmovdqu (SRC), %xmm0 + _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0 + vmovdqu %xmm0, (DST) + _next_tweak TWEAK0_XMM, %xmm0, TWEAK0_XMM + add $16, SRC + add $16, DST + sub $16, LEN + jge .Lblock_at_a_time\@ +.Lblock_at_a_time_done\@: + add $16, LEN // Undo the extra sub of 16. + // Now 0 <= LEN <= 15. If LEN is zero, we're done. + jz .Ldone\@ + + // Otherwise 1 <= LEN <= 15, but the real remaining length is 16 + LEN. + // Do ciphertext stealing to process the last 16 + LEN bytes. + +.if \enc + // If encrypting, the main loop already encrypted the last full block to + // create the CTS intermediate ciphertext. Prepare for the rest of CTS + // by rewinding the pointers and loading the intermediate ciphertext. + sub $16, SRC + sub $16, DST + vmovdqu (DST), %xmm0 +.else + // If decrypting, the main loop didn't decrypt the last full block + // because CTS decryption uses the last two tweaks in reverse order. + // Do it now by advancing the tweak and decrypting the last full block. + _next_tweak TWEAK0_XMM, %xmm0, TWEAK1_XMM + vmovdqu (SRC), %xmm0 + _aes_crypt \enc, _XMM, TWEAK1_XMM, %xmm0 +.endif + +.if USE_AVX10 + // Create a mask that has the first LEN bits set. + mov $-1, %r9d + bzhi LEN, %r9d, %r9d + kmovd %r9d, %k1 + + // Swap the first LEN bytes of the en/decryption of the last full block + // with the partial block. Note that to support in-place en/decryption, + // the load from the src partial block must happen before the store to + // the dst partial block. + vmovdqa %xmm0, %xmm1 + vmovdqu8 16(SRC), %xmm0{%k1} + vmovdqu8 %xmm1, 16(DST){%k1} +.else + lea .Lcts_permute_table(%rip), %r9 + + // Load the src partial block, left-aligned. Note that to support + // in-place en/decryption, this must happen before the store to the dst + // partial block. + vmovdqu (SRC, LEN64, 1), %xmm1 + + // Shift the first LEN bytes of the en/decryption of the last full block + // to the end of a register, then store it to DST+LEN. This stores the + // dst partial block. It also writes to the second part of the dst last + // full block, but that part is overwritten later. + vpshufb (%r9, LEN64, 1), %xmm0, %xmm2 + vmovdqu %xmm2, (DST, LEN64, 1) + + // Make xmm3 contain [16-LEN,16-LEN+1,...,14,15,0x80,0x80,...]. + sub LEN64, %r9 + vmovdqu 32(%r9), %xmm3 + + // Shift the src partial block to the beginning of its register. + vpshufb %xmm3, %xmm1, %xmm1 + + // Do a blend to generate the src partial block followed by the second + // part of the en/decryption of the last full block. + vpblendvb %xmm3, %xmm0, %xmm1, %xmm0 +.endif + // En/decrypt again and store the last full block. + _aes_crypt \enc, _XMM, TWEAK0_XMM, %xmm0 + vmovdqu %xmm0, (DST) + jmp .Ldone\@ +.endm + +// void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key, +// u8 iv[AES_BLOCK_SIZE]); +SYM_TYPED_FUNC_START(aes_xts_encrypt_iv) + vmovdqu (%rsi), %xmm0 + vpxor (%rdi), %xmm0, %xmm0 + movl 480(%rdi), %eax // AES key length + lea -16(%rdi, %rax, 4), %rdi + cmp $24, %eax + jl .Lencrypt_iv_aes128 + je .Lencrypt_iv_aes192 + vaesenc -6*16(%rdi), %xmm0, %xmm0 + vaesenc -5*16(%rdi), %xmm0, %xmm0 +.Lencrypt_iv_aes192: + vaesenc -4*16(%rdi), %xmm0, %xmm0 + vaesenc -3*16(%rdi), %xmm0, %xmm0 +.Lencrypt_iv_aes128: + vaesenc -2*16(%rdi), %xmm0, %xmm0 + vaesenc -1*16(%rdi), %xmm0, %xmm0 + vaesenc 0*16(%rdi), %xmm0, %xmm0 + vaesenc 1*16(%rdi), %xmm0, %xmm0 + vaesenc 2*16(%rdi), %xmm0, %xmm0 + vaesenc 3*16(%rdi), %xmm0, %xmm0 + vaesenc 4*16(%rdi), %xmm0, %xmm0 + vaesenc 5*16(%rdi), %xmm0, %xmm0 + vaesenc 6*16(%rdi), %xmm0, %xmm0 + vaesenclast 7*16(%rdi), %xmm0, %xmm0 + vmovdqu %xmm0, (%rsi) + RET +SYM_FUNC_END(aes_xts_encrypt_iv) + +// Below are the actual AES-XTS encryption and decryption functions, +// instantiated from the above macro. They all have the following prototype: +// +// void (*xts_asm_func)(const struct crypto_aes_ctx *key, +// const u8 *src, u8 *dst, unsigned int len, +// u8 tweak[AES_BLOCK_SIZE]); +// +// |key| is the data key. |tweak| contains the next tweak; the encryption of +// the original IV with the tweak key was already done. This function supports +// incremental computation, but |len| must always be >= 16 (AES_BLOCK_SIZE), and +// |len| must be a multiple of 16 except on the last call. If |len| is a +// multiple of 16, then this function updates |tweak| to contain the next tweak. + +.set VL, 16 +.set USE_AVX10, 0 +SYM_TYPED_FUNC_START(aes_xts_encrypt_aesni_avx) + _aes_xts_crypt 1 +SYM_FUNC_END(aes_xts_encrypt_aesni_avx) +SYM_TYPED_FUNC_START(aes_xts_decrypt_aesni_avx) + _aes_xts_crypt 0 +SYM_FUNC_END(aes_xts_decrypt_aesni_avx) + +#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) +.set VL, 32 +.set USE_AVX10, 0 +SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx2) + _aes_xts_crypt 1 +SYM_FUNC_END(aes_xts_encrypt_vaes_avx2) +SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx2) + _aes_xts_crypt 0 +SYM_FUNC_END(aes_xts_decrypt_vaes_avx2) + +.set VL, 32 +.set USE_AVX10, 1 +SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_256) + _aes_xts_crypt 1 +SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_256) +SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_256) + _aes_xts_crypt 0 +SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_256) + +.set VL, 64 +.set USE_AVX10, 1 +SYM_TYPED_FUNC_START(aes_xts_encrypt_vaes_avx10_512) + _aes_xts_crypt 1 +SYM_FUNC_END(aes_xts_encrypt_vaes_avx10_512) +SYM_TYPED_FUNC_START(aes_xts_decrypt_vaes_avx10_512) + _aes_xts_crypt 0 +SYM_FUNC_END(aes_xts_decrypt_vaes_avx10_512) +#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */ diff --git a/arch/x86/crypto/aesni-intel_asm.S b/arch/x86/crypto/aesni-intel_asm.S index 411d8c83e88a..39066b57a70e 100644 --- a/arch/x86/crypto/aesni-intel_asm.S +++ b/arch/x86/crypto/aesni-intel_asm.S @@ -83,9 +83,6 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff .text - -#define STACK_OFFSET 8*3 - #define AadHash 16*0 #define AadLen 16*1 #define InLen (16*1)+8 @@ -116,11 +113,6 @@ ALL_F: .octa 0xffffffffffffffffffffffffffffffff #define arg4 rcx #define arg5 r8 #define arg6 r9 -#define arg7 STACK_OFFSET+8(%rsp) -#define arg8 STACK_OFFSET+16(%rsp) -#define arg9 STACK_OFFSET+24(%rsp) -#define arg10 STACK_OFFSET+32(%rsp) -#define arg11 STACK_OFFSET+40(%rsp) #define keysize 2*15*16(%arg1) #endif @@ -1507,184 +1499,6 @@ _esb_loop_\@: MOVADQ (%r10),\TMP1 aesenclast \TMP1,\XMM0 .endm -/***************************************************************************** -* void aesni_gcm_dec(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. -* struct gcm_context_data *data -* // Context data -* u8 *out, // Plaintext output. Encrypt in-place is allowed. -* const u8 *in, // Ciphertext input -* u64 plaintext_len, // Length of data in bytes for decryption. -* u8 *iv, // Pre-counter block j0: 4 byte salt (from Security Association) -* // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload) -* // concatenated with 0x00000001. 16-byte aligned pointer. -* u8 *hash_subkey, // H, the Hash sub key input. Data starts on a 16-byte boundary. -* const u8 *aad, // Additional Authentication Data (AAD) -* u64 aad_len, // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes -* u8 *auth_tag, // Authenticated Tag output. The driver will compare this to the -* // given authentication tag and only return the plaintext if they match. -* u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16 -* // (most likely), 12 or 8. -* -* Assumptions: -* -* keys: -* keys are pre-expanded and aligned to 16 bytes. we are using the first -* set of 11 keys in the data structure void *aes_ctx -* -* iv: -* 0 1 2 3 -* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | Salt (From the SA) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | Initialization Vector | -* | (This is the sequence number from IPSec header) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 0x1 | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* -* -* -* AAD: -* AAD padded to 128 bits with 0 -* for example, assume AAD is a u32 vector -* -* if AAD is 8 bytes: -* AAD[3] = {A0, A1}; -* padded AAD in xmm register = {A1 A0 0 0} -* -* 0 1 2 3 -* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | SPI (A1) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 32-bit Sequence Number (A0) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 0x0 | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* -* AAD Format with 32-bit Sequence Number -* -* if AAD is 12 bytes: -* AAD[3] = {A0, A1, A2}; -* padded AAD in xmm register = {A2 A1 A0 0} -* -* 0 1 2 3 -* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | SPI (A2) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 64-bit Extended Sequence Number {A1,A0} | -* | | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 0x0 | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* -* AAD Format with 64-bit Extended Sequence Number -* -* poly = x^128 + x^127 + x^126 + x^121 + 1 -* -*****************************************************************************/ -SYM_FUNC_START(aesni_gcm_dec) - FUNC_SAVE - - GCM_INIT %arg6, arg7, arg8, arg9 - GCM_ENC_DEC dec - GCM_COMPLETE arg10, arg11 - FUNC_RESTORE - RET -SYM_FUNC_END(aesni_gcm_dec) - - -/***************************************************************************** -* void aesni_gcm_enc(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. -* struct gcm_context_data *data -* // Context data -* u8 *out, // Ciphertext output. Encrypt in-place is allowed. -* const u8 *in, // Plaintext input -* u64 plaintext_len, // Length of data in bytes for encryption. -* u8 *iv, // Pre-counter block j0: 4 byte salt (from Security Association) -* // concatenated with 8 byte Initialisation Vector (from IPSec ESP Payload) -* // concatenated with 0x00000001. 16-byte aligned pointer. -* u8 *hash_subkey, // H, the Hash sub key input. Data starts on a 16-byte boundary. -* const u8 *aad, // Additional Authentication Data (AAD) -* u64 aad_len, // Length of AAD in bytes. With RFC4106 this is going to be 8 or 12 bytes -* u8 *auth_tag, // Authenticated Tag output. -* u64 auth_tag_len); // Authenticated Tag Length in bytes. Valid values are 16 (most likely), -* // 12 or 8. -* -* Assumptions: -* -* keys: -* keys are pre-expanded and aligned to 16 bytes. we are using the -* first set of 11 keys in the data structure void *aes_ctx -* -* -* iv: -* 0 1 2 3 -* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | Salt (From the SA) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | Initialization Vector | -* | (This is the sequence number from IPSec header) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 0x1 | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* -* -* -* AAD: -* AAD padded to 128 bits with 0 -* for example, assume AAD is a u32 vector -* -* if AAD is 8 bytes: -* AAD[3] = {A0, A1}; -* padded AAD in xmm register = {A1 A0 0 0} -* -* 0 1 2 3 -* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | SPI (A1) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 32-bit Sequence Number (A0) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 0x0 | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* -* AAD Format with 32-bit Sequence Number -* -* if AAD is 12 bytes: -* AAD[3] = {A0, A1, A2}; -* padded AAD in xmm register = {A2 A1 A0 0} -* -* 0 1 2 3 -* 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5 6 7 8 9 0 1 -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | SPI (A2) | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 64-bit Extended Sequence Number {A1,A0} | -* | | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* | 0x0 | -* +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+ -* -* AAD Format with 64-bit Extended Sequence Number -* -* poly = x^128 + x^127 + x^126 + x^121 + 1 -***************************************************************************/ -SYM_FUNC_START(aesni_gcm_enc) - FUNC_SAVE - - GCM_INIT %arg6, arg7, arg8, arg9 - GCM_ENC_DEC enc - - GCM_COMPLETE arg10, arg11 - FUNC_RESTORE - RET -SYM_FUNC_END(aesni_gcm_enc) /***************************************************************************** * void aesni_gcm_init(void *aes_ctx, // AES Key schedule. Starts on a 16 byte boundary. @@ -1820,8 +1634,8 @@ SYM_FUNC_START_LOCAL(_key_expansion_256b) SYM_FUNC_END(_key_expansion_256b) /* - * int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, - * unsigned int key_len) + * void aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + * unsigned int key_len) */ SYM_FUNC_START(aesni_set_key) FRAME_BEGIN @@ -1926,7 +1740,6 @@ SYM_FUNC_START(aesni_set_key) sub $0x10, UKEYP cmp TKEYP, KEYP jb .Ldec_key_loop - xor AREG, AREG #ifndef __x86_64__ popl KEYP #endif @@ -2826,28 +2639,24 @@ SYM_FUNC_END(aesni_ctr_enc) .previous /* - * _aesni_gf128mul_x_ble: internal ABI - * Multiply in GF(2^128) for XTS IVs + * _aesni_gf128mul_x_ble: Multiply in GF(2^128) for XTS IVs * input: * IV: current IV * GF128MUL_MASK == mask with 0x87 and 0x01 * output: * IV: next IV * changed: - * CTR: == temporary value + * KEY: == temporary value */ -#define _aesni_gf128mul_x_ble() \ - pshufd $0x13, IV, KEY; \ - paddq IV, IV; \ - psrad $31, KEY; \ - pand GF128MUL_MASK, KEY; \ - pxor KEY, IV; +.macro _aesni_gf128mul_x_ble + pshufd $0x13, IV, KEY + paddq IV, IV + psrad $31, KEY + pand GF128MUL_MASK, KEY + pxor KEY, IV +.endm -/* - * void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *dst, - * const u8 *src, unsigned int len, le128 *iv) - */ -SYM_FUNC_START(aesni_xts_encrypt) +.macro _aesni_xts_crypt enc FRAME_BEGIN #ifndef __x86_64__ pushl IVP @@ -2866,35 +2675,46 @@ SYM_FUNC_START(aesni_xts_encrypt) movups (IVP), IV mov 480(KEYP), KLEN +.if !\enc + add $240, KEYP -.Lxts_enc_loop4: + test $15, LEN + jz .Lxts_loop4\@ + sub $16, LEN +.endif + +.Lxts_loop4\@: sub $64, LEN - jl .Lxts_enc_1x + jl .Lxts_1x\@ movdqa IV, STATE1 movdqu 0x00(INP), IN pxor IN, STATE1 movdqu IV, 0x00(OUTP) - _aesni_gf128mul_x_ble() + _aesni_gf128mul_x_ble movdqa IV, STATE2 movdqu 0x10(INP), IN pxor IN, STATE2 movdqu IV, 0x10(OUTP) - _aesni_gf128mul_x_ble() + _aesni_gf128mul_x_ble movdqa IV, STATE3 movdqu 0x20(INP), IN pxor IN, STATE3 movdqu IV, 0x20(OUTP) - _aesni_gf128mul_x_ble() + _aesni_gf128mul_x_ble movdqa IV, STATE4 movdqu 0x30(INP), IN pxor IN, STATE4 movdqu IV, 0x30(OUTP) +.if \enc call _aesni_enc4 +.else + call _aesni_dec4 +.endif movdqu 0x00(OUTP), IN pxor IN, STATE1 @@ -2912,17 +2732,17 @@ SYM_FUNC_START(aesni_xts_encrypt) pxor IN, STATE4 movdqu STATE4, 0x30(OUTP) - _aesni_gf128mul_x_ble() + _aesni_gf128mul_x_ble add $64, INP add $64, OUTP test LEN, LEN - jnz .Lxts_enc_loop4 + jnz .Lxts_loop4\@ -.Lxts_enc_ret_iv: +.Lxts_ret_iv\@: movups IV, (IVP) -.Lxts_enc_ret: +.Lxts_ret\@: #ifndef __x86_64__ popl KLEN popl KEYP @@ -2932,201 +2752,60 @@ SYM_FUNC_START(aesni_xts_encrypt) FRAME_END RET -.Lxts_enc_1x: +.Lxts_1x\@: add $64, LEN - jz .Lxts_enc_ret_iv + jz .Lxts_ret_iv\@ +.if \enc sub $16, LEN - jl .Lxts_enc_cts4 + jl .Lxts_cts4\@ +.endif -.Lxts_enc_loop1: +.Lxts_loop1\@: movdqu (INP), STATE +.if \enc pxor IV, STATE call _aesni_enc1 - pxor IV, STATE - _aesni_gf128mul_x_ble() - - test LEN, LEN - jz .Lxts_enc_out - +.else add $16, INP sub $16, LEN - jl .Lxts_enc_cts1 - - movdqu STATE, (OUTP) - add $16, OUTP - jmp .Lxts_enc_loop1 - -.Lxts_enc_out: - movdqu STATE, (OUTP) - jmp .Lxts_enc_ret_iv - -.Lxts_enc_cts4: - movdqa STATE4, STATE - sub $16, OUTP - -.Lxts_enc_cts1: -#ifndef __x86_64__ - lea .Lcts_permute_table, T1 -#else - lea .Lcts_permute_table(%rip), T1 -#endif - add LEN, INP /* rewind input pointer */ - add $16, LEN /* # bytes in final block */ - movups (INP), IN1 - - mov T1, IVP - add $32, IVP - add LEN, T1 - sub LEN, IVP - add OUTP, LEN - - movups (T1), %xmm4 - movaps STATE, IN2 - pshufb %xmm4, STATE - movups STATE, (LEN) - - movups (IVP), %xmm0 - pshufb %xmm0, IN1 - pblendvb IN2, IN1 - movaps IN1, STATE - + jl .Lxts_cts1\@ pxor IV, STATE - call _aesni_enc1 + call _aesni_dec1 +.endif pxor IV, STATE + _aesni_gf128mul_x_ble - movups STATE, (OUTP) - jmp .Lxts_enc_ret -SYM_FUNC_END(aesni_xts_encrypt) - -/* - * void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *dst, - * const u8 *src, unsigned int len, le128 *iv) - */ -SYM_FUNC_START(aesni_xts_decrypt) - FRAME_BEGIN -#ifndef __x86_64__ - pushl IVP - pushl LEN - pushl KEYP - pushl KLEN - movl (FRAME_OFFSET+20)(%esp), KEYP # ctx - movl (FRAME_OFFSET+24)(%esp), OUTP # dst - movl (FRAME_OFFSET+28)(%esp), INP # src - movl (FRAME_OFFSET+32)(%esp), LEN # len - movl (FRAME_OFFSET+36)(%esp), IVP # iv - movdqa .Lgf128mul_x_ble_mask, GF128MUL_MASK -#else - movdqa .Lgf128mul_x_ble_mask(%rip), GF128MUL_MASK -#endif - movups (IVP), IV - - mov 480(KEYP), KLEN - add $240, KEYP - - test $15, LEN - jz .Lxts_dec_loop4 - sub $16, LEN - -.Lxts_dec_loop4: - sub $64, LEN - jl .Lxts_dec_1x - - movdqa IV, STATE1 - movdqu 0x00(INP), IN - pxor IN, STATE1 - movdqu IV, 0x00(OUTP) - - _aesni_gf128mul_x_ble() - movdqa IV, STATE2 - movdqu 0x10(INP), IN - pxor IN, STATE2 - movdqu IV, 0x10(OUTP) - - _aesni_gf128mul_x_ble() - movdqa IV, STATE3 - movdqu 0x20(INP), IN - pxor IN, STATE3 - movdqu IV, 0x20(OUTP) - - _aesni_gf128mul_x_ble() - movdqa IV, STATE4 - movdqu 0x30(INP), IN - pxor IN, STATE4 - movdqu IV, 0x30(OUTP) - - call _aesni_dec4 - - movdqu 0x00(OUTP), IN - pxor IN, STATE1 - movdqu STATE1, 0x00(OUTP) - - movdqu 0x10(OUTP), IN - pxor IN, STATE2 - movdqu STATE2, 0x10(OUTP) - - movdqu 0x20(OUTP), IN - pxor IN, STATE3 - movdqu STATE3, 0x20(OUTP) - - movdqu 0x30(OUTP), IN - pxor IN, STATE4 - movdqu STATE4, 0x30(OUTP) - - _aesni_gf128mul_x_ble() - - add $64, INP - add $64, OUTP test LEN, LEN - jnz .Lxts_dec_loop4 - -.Lxts_dec_ret_iv: - movups IV, (IVP) - -.Lxts_dec_ret: -#ifndef __x86_64__ - popl KLEN - popl KEYP - popl LEN - popl IVP -#endif - FRAME_END - RET - -.Lxts_dec_1x: - add $64, LEN - jz .Lxts_dec_ret_iv - -.Lxts_dec_loop1: - movdqu (INP), STATE + jz .Lxts_out\@ +.if \enc add $16, INP sub $16, LEN - jl .Lxts_dec_cts1 - - pxor IV, STATE - call _aesni_dec1 - pxor IV, STATE - _aesni_gf128mul_x_ble() - - test LEN, LEN - jz .Lxts_dec_out + jl .Lxts_cts1\@ +.endif movdqu STATE, (OUTP) add $16, OUTP - jmp .Lxts_dec_loop1 + jmp .Lxts_loop1\@ -.Lxts_dec_out: +.Lxts_out\@: movdqu STATE, (OUTP) - jmp .Lxts_dec_ret_iv + jmp .Lxts_ret_iv\@ -.Lxts_dec_cts1: +.if \enc +.Lxts_cts4\@: + movdqa STATE4, STATE + sub $16, OUTP +.Lxts_cts1\@: +.else +.Lxts_cts1\@: movdqa IV, STATE4 - _aesni_gf128mul_x_ble() + _aesni_gf128mul_x_ble pxor IV, STATE call _aesni_dec1 pxor IV, STATE - +.endif #ifndef __x86_64__ lea .Lcts_permute_table, T1 #else @@ -3152,10 +2831,32 @@ SYM_FUNC_START(aesni_xts_decrypt) pblendvb IN2, IN1 movaps IN1, STATE +.if \enc + pxor IV, STATE + call _aesni_enc1 + pxor IV, STATE +.else pxor STATE4, STATE call _aesni_dec1 pxor STATE4, STATE +.endif movups STATE, (OUTP) - jmp .Lxts_dec_ret -SYM_FUNC_END(aesni_xts_decrypt) + jmp .Lxts_ret\@ +.endm + +/* + * void aesni_xts_enc(const struct crypto_aes_ctx *ctx, u8 *dst, + * const u8 *src, unsigned int len, le128 *iv) + */ +SYM_FUNC_START(aesni_xts_enc) + _aesni_xts_crypt 1 +SYM_FUNC_END(aesni_xts_enc) + +/* + * void aesni_xts_dec(const struct crypto_aes_ctx *ctx, u8 *dst, + * const u8 *src, unsigned int len, le128 *iv) + */ +SYM_FUNC_START(aesni_xts_dec) + _aesni_xts_crypt 0 +SYM_FUNC_END(aesni_xts_dec) diff --git a/arch/x86/crypto/aesni-intel_glue.c b/arch/x86/crypto/aesni-intel_glue.c index b1d90c25975a..5b25d2a58aeb 100644 --- a/arch/x86/crypto/aesni-intel_glue.c +++ b/arch/x86/crypto/aesni-intel_glue.c @@ -40,7 +40,6 @@ #define AESNI_ALIGN 16 #define AESNI_ALIGN_ATTR __attribute__ ((__aligned__(AESNI_ALIGN))) #define AES_BLOCK_MASK (~(AES_BLOCK_SIZE - 1)) -#define RFC4106_HASH_SUBKEY_SIZE 16 #define AESNI_ALIGN_EXTRA ((AESNI_ALIGN - 1) & ~(CRYPTO_MINALIGN - 1)) #define CRYPTO_AES_CTX_SIZE (sizeof(struct crypto_aes_ctx) + AESNI_ALIGN_EXTRA) #define XTS_AES_CTX_SIZE (sizeof(struct aesni_xts_ctx) + AESNI_ALIGN_EXTRA) @@ -87,8 +86,8 @@ static inline void *aes_align_addr(void *addr) return PTR_ALIGN(addr, AESNI_ALIGN); } -asmlinkage int aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, - unsigned int key_len); +asmlinkage void aesni_set_key(struct crypto_aes_ctx *ctx, const u8 *in_key, + unsigned int key_len); asmlinkage void aesni_enc(const void *ctx, u8 *out, const u8 *in); asmlinkage void aesni_dec(const void *ctx, u8 *out, const u8 *in); asmlinkage void aesni_ecb_enc(struct crypto_aes_ctx *ctx, u8 *out, @@ -107,11 +106,11 @@ asmlinkage void aesni_cts_cbc_dec(struct crypto_aes_ctx *ctx, u8 *out, #define AVX_GEN2_OPTSIZE 640 #define AVX_GEN4_OPTSIZE 4096 -asmlinkage void aesni_xts_encrypt(const struct crypto_aes_ctx *ctx, u8 *out, - const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_xts_enc(const struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); -asmlinkage void aesni_xts_decrypt(const struct crypto_aes_ctx *ctx, u8 *out, - const u8 *in, unsigned int len, u8 *iv); +asmlinkage void aesni_xts_dec(const struct crypto_aes_ctx *ctx, u8 *out, + const u8 *in, unsigned int len, u8 *iv); #ifdef CONFIG_X86_64 @@ -233,19 +232,17 @@ static int aes_set_key_common(struct crypto_aes_ctx *ctx, { int err; - if (key_len != AES_KEYSIZE_128 && key_len != AES_KEYSIZE_192 && - key_len != AES_KEYSIZE_256) - return -EINVAL; - if (!crypto_simd_usable()) - err = aes_expandkey(ctx, in_key, key_len); - else { - kernel_fpu_begin(); - err = aesni_set_key(ctx, in_key, key_len); - kernel_fpu_end(); - } + return aes_expandkey(ctx, in_key, key_len); - return err; + err = aes_check_keylen(key_len); + if (err) + return err; + + kernel_fpu_begin(); + aesni_set_key(ctx, in_key, key_len); + kernel_fpu_end(); + return 0; } static int aes_set_key(struct crypto_tfm *tfm, const u8 *in_key, @@ -592,23 +589,12 @@ static int xctr_crypt(struct skcipher_request *req) return err; } -static int -rfc4106_set_hash_subkey(u8 *hash_subkey, const u8 *key, unsigned int key_len) +static int aes_gcm_derive_hash_subkey(const struct crypto_aes_ctx *aes_key, + u8 hash_subkey[AES_BLOCK_SIZE]) { - struct crypto_aes_ctx ctx; - int ret; - - ret = aes_expandkey(&ctx, key, key_len); - if (ret) - return ret; - - /* Clear the data in the hash sub key container to zero.*/ - /* We want to cipher all zeros to create the hash sub key. */ - memset(hash_subkey, 0, RFC4106_HASH_SUBKEY_SIZE); - - aes_encrypt(&ctx, hash_subkey, hash_subkey); + static const u8 zeroes[AES_BLOCK_SIZE]; - memzero_explicit(&ctx, sizeof(ctx)); + aes_encrypt(aes_key, hash_subkey, zeroes); return 0; } @@ -626,7 +612,8 @@ static int common_rfc4106_set_key(struct crypto_aead *aead, const u8 *key, memcpy(ctx->nonce, key + key_len, sizeof(ctx->nonce)); return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?: - rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); + aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded, + ctx->hash_subkey); } /* This is the Integrity Check Value (aka the authentication tag) length and can @@ -877,7 +864,7 @@ static int helper_rfc4106_decrypt(struct aead_request *req) } #endif -static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key, +static int xts_setkey_aesni(struct crypto_skcipher *tfm, const u8 *key, unsigned int keylen) { struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm); @@ -898,108 +885,149 @@ static int xts_aesni_setkey(struct crypto_skcipher *tfm, const u8 *key, return aes_set_key_common(&ctx->tweak_ctx, key + keylen, keylen); } -static int xts_crypt(struct skcipher_request *req, bool encrypt) +typedef void (*xts_encrypt_iv_func)(const struct crypto_aes_ctx *tweak_key, + u8 iv[AES_BLOCK_SIZE]); +typedef void (*xts_crypt_func)(const struct crypto_aes_ctx *key, + const u8 *src, u8 *dst, unsigned int len, + u8 tweak[AES_BLOCK_SIZE]); + +/* This handles cases where the source and/or destination span pages. */ +static noinline int +xts_crypt_slowpath(struct skcipher_request *req, xts_crypt_func crypt_func) { struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); - struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm); + const struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm); int tail = req->cryptlen % AES_BLOCK_SIZE; + struct scatterlist sg_src[2], sg_dst[2]; struct skcipher_request subreq; struct skcipher_walk walk; + struct scatterlist *src, *dst; int err; - if (req->cryptlen < AES_BLOCK_SIZE) - return -EINVAL; - - err = skcipher_walk_virt(&walk, req, false); - if (!walk.nbytes) - return err; - - if (unlikely(tail > 0 && walk.nbytes < walk.total)) { - int blocks = DIV_ROUND_UP(req->cryptlen, AES_BLOCK_SIZE) - 2; - - skcipher_walk_abort(&walk); - + /* + * If the message length isn't divisible by the AES block size, then + * separate off the last full block and the partial block. This ensures + * that they are processed in the same call to the assembly function, + * which is required for ciphertext stealing. + */ + if (tail) { skcipher_request_set_tfm(&subreq, tfm); skcipher_request_set_callback(&subreq, skcipher_request_flags(req), NULL, NULL); skcipher_request_set_crypt(&subreq, req->src, req->dst, - blocks * AES_BLOCK_SIZE, req->iv); + req->cryptlen - tail - AES_BLOCK_SIZE, + req->iv); req = &subreq; + } - err = skcipher_walk_virt(&walk, req, false); - if (!walk.nbytes) - return err; - } else { - tail = 0; + err = skcipher_walk_virt(&walk, req, false); + + while (walk.nbytes) { + kernel_fpu_begin(); + (*crypt_func)(&ctx->crypt_ctx, + walk.src.virt.addr, walk.dst.virt.addr, + walk.nbytes & ~(AES_BLOCK_SIZE - 1), req->iv); + kernel_fpu_end(); + err = skcipher_walk_done(&walk, + walk.nbytes & (AES_BLOCK_SIZE - 1)); } - kernel_fpu_begin(); + if (err || !tail) + return err; - /* calculate first value of T */ - aesni_enc(&ctx->tweak_ctx, walk.iv, walk.iv); + /* Do ciphertext stealing with the last full block and partial block. */ - while (walk.nbytes > 0) { - int nbytes = walk.nbytes; - - if (nbytes < walk.total) - nbytes &= ~(AES_BLOCK_SIZE - 1); - - if (encrypt) - aesni_xts_encrypt(&ctx->crypt_ctx, - walk.dst.virt.addr, walk.src.virt.addr, - nbytes, walk.iv); - else - aesni_xts_decrypt(&ctx->crypt_ctx, - walk.dst.virt.addr, walk.src.virt.addr, - nbytes, walk.iv); - kernel_fpu_end(); + dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen); + if (req->dst != req->src) + dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen); - err = skcipher_walk_done(&walk, walk.nbytes - nbytes); + skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail, + req->iv); - if (walk.nbytes > 0) - kernel_fpu_begin(); - } + err = skcipher_walk_virt(&walk, req, false); + if (err) + return err; - if (unlikely(tail > 0 && !err)) { - struct scatterlist sg_src[2], sg_dst[2]; - struct scatterlist *src, *dst; + kernel_fpu_begin(); + (*crypt_func)(&ctx->crypt_ctx, walk.src.virt.addr, walk.dst.virt.addr, + walk.nbytes, req->iv); + kernel_fpu_end(); - dst = src = scatterwalk_ffwd(sg_src, req->src, req->cryptlen); - if (req->dst != req->src) - dst = scatterwalk_ffwd(sg_dst, req->dst, req->cryptlen); + return skcipher_walk_done(&walk, 0); +} - skcipher_request_set_crypt(req, src, dst, AES_BLOCK_SIZE + tail, - req->iv); +/* __always_inline to avoid indirect call in fastpath */ +static __always_inline int +xts_crypt(struct skcipher_request *req, xts_encrypt_iv_func encrypt_iv, + xts_crypt_func crypt_func) +{ + struct crypto_skcipher *tfm = crypto_skcipher_reqtfm(req); + const struct aesni_xts_ctx *ctx = aes_xts_ctx(tfm); + const unsigned int cryptlen = req->cryptlen; + struct scatterlist *src = req->src; + struct scatterlist *dst = req->dst; - err = skcipher_walk_virt(&walk, &subreq, false); - if (err) - return err; + if (unlikely(cryptlen < AES_BLOCK_SIZE)) + return -EINVAL; - kernel_fpu_begin(); - if (encrypt) - aesni_xts_encrypt(&ctx->crypt_ctx, - walk.dst.virt.addr, walk.src.virt.addr, - walk.nbytes, walk.iv); - else - aesni_xts_decrypt(&ctx->crypt_ctx, - walk.dst.virt.addr, walk.src.virt.addr, - walk.nbytes, walk.iv); - kernel_fpu_end(); + kernel_fpu_begin(); + (*encrypt_iv)(&ctx->tweak_ctx, req->iv); - err = skcipher_walk_done(&walk, 0); + /* + * In practice, virtually all XTS plaintexts and ciphertexts are either + * 512 or 4096 bytes, aligned such that they don't span page boundaries. + * To optimize the performance of these cases, and also any other case + * where no page boundary is spanned, the below fast-path handles + * single-page sources and destinations as efficiently as possible. + */ + if (likely(src->length >= cryptlen && dst->length >= cryptlen && + src->offset + cryptlen <= PAGE_SIZE && + dst->offset + cryptlen <= PAGE_SIZE)) { + struct page *src_page = sg_page(src); + struct page *dst_page = sg_page(dst); + void *src_virt = kmap_local_page(src_page) + src->offset; + void *dst_virt = kmap_local_page(dst_page) + dst->offset; + + (*crypt_func)(&ctx->crypt_ctx, src_virt, dst_virt, cryptlen, + req->iv); + kunmap_local(dst_virt); + kunmap_local(src_virt); + kernel_fpu_end(); + return 0; } - return err; + kernel_fpu_end(); + return xts_crypt_slowpath(req, crypt_func); +} + +static void aesni_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key, + u8 iv[AES_BLOCK_SIZE]) +{ + aesni_enc(tweak_key, iv, iv); +} + +static void aesni_xts_encrypt(const struct crypto_aes_ctx *key, + const u8 *src, u8 *dst, unsigned int len, + u8 tweak[AES_BLOCK_SIZE]) +{ + aesni_xts_enc(key, dst, src, len, tweak); } -static int xts_encrypt(struct skcipher_request *req) +static void aesni_xts_decrypt(const struct crypto_aes_ctx *key, + const u8 *src, u8 *dst, unsigned int len, + u8 tweak[AES_BLOCK_SIZE]) { - return xts_crypt(req, true); + aesni_xts_dec(key, dst, src, len, tweak); } -static int xts_decrypt(struct skcipher_request *req) +static int xts_encrypt_aesni(struct skcipher_request *req) { - return xts_crypt(req, false); + return xts_crypt(req, aesni_xts_encrypt_iv, aesni_xts_encrypt); +} + +static int xts_decrypt_aesni(struct skcipher_request *req) +{ + return xts_crypt(req, aesni_xts_encrypt_iv, aesni_xts_decrypt); } static struct crypto_alg aesni_cipher_alg = { @@ -1103,9 +1131,9 @@ static struct skcipher_alg aesni_skciphers[] = { .max_keysize = 2 * AES_MAX_KEY_SIZE, .ivsize = AES_BLOCK_SIZE, .walksize = 2 * AES_BLOCK_SIZE, - .setkey = xts_aesni_setkey, - .encrypt = xts_encrypt, - .decrypt = xts_decrypt, + .setkey = xts_setkey_aesni, + .encrypt = xts_encrypt_aesni, + .decrypt = xts_decrypt_aesni, } }; @@ -1137,7 +1165,149 @@ static struct skcipher_alg aesni_xctr = { }; static struct simd_skcipher_alg *aesni_simd_xctr; -#endif /* CONFIG_X86_64 */ + +asmlinkage void aes_xts_encrypt_iv(const struct crypto_aes_ctx *tweak_key, + u8 iv[AES_BLOCK_SIZE]); + +#define DEFINE_XTS_ALG(suffix, driver_name, priority) \ + \ +asmlinkage void \ +aes_xts_encrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src, \ + u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \ +asmlinkage void \ +aes_xts_decrypt_##suffix(const struct crypto_aes_ctx *key, const u8 *src, \ + u8 *dst, unsigned int len, u8 tweak[AES_BLOCK_SIZE]); \ + \ +static int xts_encrypt_##suffix(struct skcipher_request *req) \ +{ \ + return xts_crypt(req, aes_xts_encrypt_iv, aes_xts_encrypt_##suffix); \ +} \ + \ +static int xts_decrypt_##suffix(struct skcipher_request *req) \ +{ \ + return xts_crypt(req, aes_xts_encrypt_iv, aes_xts_decrypt_##suffix); \ +} \ + \ +static struct skcipher_alg aes_xts_alg_##suffix = { \ + .base = { \ + .cra_name = "__xts(aes)", \ + .cra_driver_name = "__" driver_name, \ + .cra_priority = priority, \ + .cra_flags = CRYPTO_ALG_INTERNAL, \ + .cra_blocksize = AES_BLOCK_SIZE, \ + .cra_ctxsize = XTS_AES_CTX_SIZE, \ + .cra_module = THIS_MODULE, \ + }, \ + .min_keysize = 2 * AES_MIN_KEY_SIZE, \ + .max_keysize = 2 * AES_MAX_KEY_SIZE, \ + .ivsize = AES_BLOCK_SIZE, \ + .walksize = 2 * AES_BLOCK_SIZE, \ + .setkey = xts_setkey_aesni, \ + .encrypt = xts_encrypt_##suffix, \ + .decrypt = xts_decrypt_##suffix, \ +}; \ + \ +static struct simd_skcipher_alg *aes_xts_simdalg_##suffix + +DEFINE_XTS_ALG(aesni_avx, "xts-aes-aesni-avx", 500); +#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) +DEFINE_XTS_ALG(vaes_avx2, "xts-aes-vaes-avx2", 600); +DEFINE_XTS_ALG(vaes_avx10_256, "xts-aes-vaes-avx10_256", 700); +DEFINE_XTS_ALG(vaes_avx10_512, "xts-aes-vaes-avx10_512", 800); +#endif + +/* + * This is a list of CPU models that are known to suffer from downclocking when + * zmm registers (512-bit vectors) are used. On these CPUs, the AES-XTS + * implementation with zmm registers won't be used by default. An + * implementation with ymm registers (256-bit vectors) will be used instead. + */ +static const struct x86_cpu_id zmm_exclusion_list[] = { + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_SKYLAKE_X }, + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_X }, + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_D }, + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE }, + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_L }, + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_ICELAKE_NNPI }, + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE_L }, + { .vendor = X86_VENDOR_INTEL, .family = 6, .model = INTEL_FAM6_TIGERLAKE }, + /* Allow Rocket Lake and later, and Sapphire Rapids and later. */ + /* Also allow AMD CPUs (starting with Zen 4, the first with AVX-512). */ + {}, +}; + +static int __init register_xts_algs(void) +{ + int err; + + if (!boot_cpu_has(X86_FEATURE_AVX)) + return 0; + err = simd_register_skciphers_compat(&aes_xts_alg_aesni_avx, 1, + &aes_xts_simdalg_aesni_avx); + if (err) + return err; +#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) + if (!boot_cpu_has(X86_FEATURE_AVX2) || + !boot_cpu_has(X86_FEATURE_VAES) || + !boot_cpu_has(X86_FEATURE_VPCLMULQDQ) || + !boot_cpu_has(X86_FEATURE_PCLMULQDQ) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM, NULL)) + return 0; + err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx2, 1, + &aes_xts_simdalg_vaes_avx2); + if (err) + return err; + + if (!boot_cpu_has(X86_FEATURE_AVX512BW) || + !boot_cpu_has(X86_FEATURE_AVX512VL) || + !boot_cpu_has(X86_FEATURE_BMI2) || + !cpu_has_xfeatures(XFEATURE_MASK_SSE | XFEATURE_MASK_YMM | + XFEATURE_MASK_AVX512, NULL)) + return 0; + + err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_256, 1, + &aes_xts_simdalg_vaes_avx10_256); + if (err) + return err; + + if (x86_match_cpu(zmm_exclusion_list)) + aes_xts_alg_vaes_avx10_512.base.cra_priority = 1; + + err = simd_register_skciphers_compat(&aes_xts_alg_vaes_avx10_512, 1, + &aes_xts_simdalg_vaes_avx10_512); + if (err) + return err; +#endif /* CONFIG_AS_VAES && CONFIG_AS_VPCLMULQDQ */ + return 0; +} + +static void unregister_xts_algs(void) +{ + if (aes_xts_simdalg_aesni_avx) + simd_unregister_skciphers(&aes_xts_alg_aesni_avx, 1, + &aes_xts_simdalg_aesni_avx); +#if defined(CONFIG_AS_VAES) && defined(CONFIG_AS_VPCLMULQDQ) + if (aes_xts_simdalg_vaes_avx2) + simd_unregister_skciphers(&aes_xts_alg_vaes_avx2, 1, + &aes_xts_simdalg_vaes_avx2); + if (aes_xts_simdalg_vaes_avx10_256) + simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_256, 1, + &aes_xts_simdalg_vaes_avx10_256); + if (aes_xts_simdalg_vaes_avx10_512) + simd_unregister_skciphers(&aes_xts_alg_vaes_avx10_512, 1, + &aes_xts_simdalg_vaes_avx10_512); +#endif +} +#else /* CONFIG_X86_64 */ +static int __init register_xts_algs(void) +{ + return 0; +} + +static void unregister_xts_algs(void) +{ +} +#endif /* !CONFIG_X86_64 */ #ifdef CONFIG_X86_64 static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key, @@ -1146,7 +1316,8 @@ static int generic_gcmaes_set_key(struct crypto_aead *aead, const u8 *key, struct generic_gcmaes_ctx *ctx = generic_gcmaes_ctx_get(aead); return aes_set_key_common(&ctx->aes_key_expanded, key, key_len) ?: - rfc4106_set_hash_subkey(ctx->hash_subkey, key, key_len); + aes_gcm_derive_hash_subkey(&ctx->aes_key_expanded, + ctx->hash_subkey); } static int generic_gcmaes_encrypt(struct aead_request *req) @@ -1276,13 +1447,21 @@ static int __init aesni_init(void) goto unregister_aeads; #endif /* CONFIG_X86_64 */ + err = register_xts_algs(); + if (err) + goto unregister_xts; + return 0; +unregister_xts: + unregister_xts_algs(); #ifdef CONFIG_X86_64 + if (aesni_simd_xctr) + simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr); unregister_aeads: +#endif /* CONFIG_X86_64 */ simd_unregister_aeads(aesni_aeads, ARRAY_SIZE(aesni_aeads), aesni_simd_aeads); -#endif /* CONFIG_X86_64 */ unregister_skciphers: simd_unregister_skciphers(aesni_skciphers, ARRAY_SIZE(aesni_skciphers), @@ -1303,6 +1482,7 @@ static void __exit aesni_exit(void) if (boot_cpu_has(X86_FEATURE_AVX)) simd_unregister_skciphers(&aesni_xctr, 1, &aesni_simd_xctr); #endif /* CONFIG_X86_64 */ + unregister_xts_algs(); } late_initcall(aesni_init); diff --git a/arch/x86/crypto/nh-avx2-x86_64.S b/arch/x86/crypto/nh-avx2-x86_64.S index ef73a3ab8726..791386d9a83a 100644 --- a/arch/x86/crypto/nh-avx2-x86_64.S +++ b/arch/x86/crypto/nh-avx2-x86_64.S @@ -154,5 +154,6 @@ SYM_TYPED_FUNC_START(nh_avx2) vpaddq T1, T0, T0 vpaddq T4, T0, T0 vmovdqu T0, (HASH) + vzeroupper RET SYM_FUNC_END(nh_avx2) diff --git a/arch/x86/crypto/sha256-avx2-asm.S b/arch/x86/crypto/sha256-avx2-asm.S index 9918212faf91..0ffb072be956 100644 --- a/arch/x86/crypto/sha256-avx2-asm.S +++ b/arch/x86/crypto/sha256-avx2-asm.S @@ -716,6 +716,7 @@ SYM_TYPED_FUNC_START(sha256_transform_rorx) popq %r13 popq %r12 popq %rbx + vzeroupper RET SYM_FUNC_END(sha256_transform_rorx) diff --git a/arch/x86/crypto/sha256_ni_asm.S b/arch/x86/crypto/sha256_ni_asm.S index 537b6dcd7ed8..d515a55a3bc1 100644 --- a/arch/x86/crypto/sha256_ni_asm.S +++ b/arch/x86/crypto/sha256_ni_asm.S @@ -62,20 +62,41 @@ #define SHA256CONSTANTS %rax -#define MSG %xmm0 +#define MSG %xmm0 /* sha256rnds2 implicit operand */ #define STATE0 %xmm1 #define STATE1 %xmm2 -#define MSGTMP0 %xmm3 -#define MSGTMP1 %xmm4 -#define MSGTMP2 %xmm5 -#define MSGTMP3 %xmm6 -#define MSGTMP4 %xmm7 +#define MSG0 %xmm3 +#define MSG1 %xmm4 +#define MSG2 %xmm5 +#define MSG3 %xmm6 +#define TMP %xmm7 #define SHUF_MASK %xmm8 #define ABEF_SAVE %xmm9 #define CDGH_SAVE %xmm10 +.macro do_4rounds i, m0, m1, m2, m3 +.if \i < 16 + movdqu \i*4(DATA_PTR), \m0 + pshufb SHUF_MASK, \m0 +.endif + movdqa (\i-32)*4(SHA256CONSTANTS), MSG + paddd \m0, MSG + sha256rnds2 STATE0, STATE1 +.if \i >= 12 && \i < 60 + movdqa \m0, TMP + palignr $4, \m3, TMP + paddd TMP, \m1 + sha256msg2 \m0, \m1 +.endif + punpckhqdq MSG, MSG + sha256rnds2 STATE1, STATE0 +.if \i >= 4 && \i < 52 + sha256msg1 \m0, \m3 +.endif +.endm + /* * Intel SHA Extensions optimized implementation of a SHA-256 update function * @@ -86,9 +107,6 @@ * store partial blocks. All message padding and hash value initialization must * be done outside the update function. * - * The indented lines in the loop are instructions related to rounds processing. - * The non-indented lines are instructions related to the message schedule. - * * void sha256_ni_transform(uint32_t *digest, const void *data, uint32_t numBlocks); * digest : pointer to digest @@ -108,202 +126,29 @@ SYM_TYPED_FUNC_START(sha256_ni_transform) * Need to reorder these appropriately * DCBA, HGFE -> ABEF, CDGH */ - movdqu 0*16(DIGEST_PTR), STATE0 - movdqu 1*16(DIGEST_PTR), STATE1 + movdqu 0*16(DIGEST_PTR), STATE0 /* DCBA */ + movdqu 1*16(DIGEST_PTR), STATE1 /* HGFE */ - pshufd $0xB1, STATE0, STATE0 /* CDAB */ - pshufd $0x1B, STATE1, STATE1 /* EFGH */ - movdqa STATE0, MSGTMP4 - palignr $8, STATE1, STATE0 /* ABEF */ - pblendw $0xF0, MSGTMP4, STATE1 /* CDGH */ + movdqa STATE0, TMP + punpcklqdq STATE1, STATE0 /* FEBA */ + punpckhqdq TMP, STATE1 /* DCHG */ + pshufd $0x1B, STATE0, STATE0 /* ABEF */ + pshufd $0xB1, STATE1, STATE1 /* CDGH */ movdqa PSHUFFLE_BYTE_FLIP_MASK(%rip), SHUF_MASK - lea K256(%rip), SHA256CONSTANTS + lea K256+32*4(%rip), SHA256CONSTANTS .Lloop0: /* Save hash values for addition after rounds */ movdqa STATE0, ABEF_SAVE movdqa STATE1, CDGH_SAVE - /* Rounds 0-3 */ - movdqu 0*16(DATA_PTR), MSG - pshufb SHUF_MASK, MSG - movdqa MSG, MSGTMP0 - paddd 0*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - - /* Rounds 4-7 */ - movdqu 1*16(DATA_PTR), MSG - pshufb SHUF_MASK, MSG - movdqa MSG, MSGTMP1 - paddd 1*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP1, MSGTMP0 - - /* Rounds 8-11 */ - movdqu 2*16(DATA_PTR), MSG - pshufb SHUF_MASK, MSG - movdqa MSG, MSGTMP2 - paddd 2*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP2, MSGTMP1 - - /* Rounds 12-15 */ - movdqu 3*16(DATA_PTR), MSG - pshufb SHUF_MASK, MSG - movdqa MSG, MSGTMP3 - paddd 3*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP3, MSGTMP4 - palignr $4, MSGTMP2, MSGTMP4 - paddd MSGTMP4, MSGTMP0 - sha256msg2 MSGTMP3, MSGTMP0 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP3, MSGTMP2 - - /* Rounds 16-19 */ - movdqa MSGTMP0, MSG - paddd 4*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP0, MSGTMP4 - palignr $4, MSGTMP3, MSGTMP4 - paddd MSGTMP4, MSGTMP1 - sha256msg2 MSGTMP0, MSGTMP1 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP0, MSGTMP3 - - /* Rounds 20-23 */ - movdqa MSGTMP1, MSG - paddd 5*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP1, MSGTMP4 - palignr $4, MSGTMP0, MSGTMP4 - paddd MSGTMP4, MSGTMP2 - sha256msg2 MSGTMP1, MSGTMP2 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP1, MSGTMP0 - - /* Rounds 24-27 */ - movdqa MSGTMP2, MSG - paddd 6*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP2, MSGTMP4 - palignr $4, MSGTMP1, MSGTMP4 - paddd MSGTMP4, MSGTMP3 - sha256msg2 MSGTMP2, MSGTMP3 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP2, MSGTMP1 - - /* Rounds 28-31 */ - movdqa MSGTMP3, MSG - paddd 7*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP3, MSGTMP4 - palignr $4, MSGTMP2, MSGTMP4 - paddd MSGTMP4, MSGTMP0 - sha256msg2 MSGTMP3, MSGTMP0 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP3, MSGTMP2 - - /* Rounds 32-35 */ - movdqa MSGTMP0, MSG - paddd 8*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP0, MSGTMP4 - palignr $4, MSGTMP3, MSGTMP4 - paddd MSGTMP4, MSGTMP1 - sha256msg2 MSGTMP0, MSGTMP1 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP0, MSGTMP3 - - /* Rounds 36-39 */ - movdqa MSGTMP1, MSG - paddd 9*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP1, MSGTMP4 - palignr $4, MSGTMP0, MSGTMP4 - paddd MSGTMP4, MSGTMP2 - sha256msg2 MSGTMP1, MSGTMP2 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP1, MSGTMP0 - - /* Rounds 40-43 */ - movdqa MSGTMP2, MSG - paddd 10*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP2, MSGTMP4 - palignr $4, MSGTMP1, MSGTMP4 - paddd MSGTMP4, MSGTMP3 - sha256msg2 MSGTMP2, MSGTMP3 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP2, MSGTMP1 - - /* Rounds 44-47 */ - movdqa MSGTMP3, MSG - paddd 11*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP3, MSGTMP4 - palignr $4, MSGTMP2, MSGTMP4 - paddd MSGTMP4, MSGTMP0 - sha256msg2 MSGTMP3, MSGTMP0 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP3, MSGTMP2 - - /* Rounds 48-51 */ - movdqa MSGTMP0, MSG - paddd 12*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP0, MSGTMP4 - palignr $4, MSGTMP3, MSGTMP4 - paddd MSGTMP4, MSGTMP1 - sha256msg2 MSGTMP0, MSGTMP1 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - sha256msg1 MSGTMP0, MSGTMP3 - - /* Rounds 52-55 */ - movdqa MSGTMP1, MSG - paddd 13*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP1, MSGTMP4 - palignr $4, MSGTMP0, MSGTMP4 - paddd MSGTMP4, MSGTMP2 - sha256msg2 MSGTMP1, MSGTMP2 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - - /* Rounds 56-59 */ - movdqa MSGTMP2, MSG - paddd 14*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - movdqa MSGTMP2, MSGTMP4 - palignr $4, MSGTMP1, MSGTMP4 - paddd MSGTMP4, MSGTMP3 - sha256msg2 MSGTMP2, MSGTMP3 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 - - /* Rounds 60-63 */ - movdqa MSGTMP3, MSG - paddd 15*16(SHA256CONSTANTS), MSG - sha256rnds2 STATE0, STATE1 - pshufd $0x0E, MSG, MSG - sha256rnds2 STATE1, STATE0 +.irp i, 0, 16, 32, 48 + do_4rounds (\i + 0), MSG0, MSG1, MSG2, MSG3 + do_4rounds (\i + 4), MSG1, MSG2, MSG3, MSG0 + do_4rounds (\i + 8), MSG2, MSG3, MSG0, MSG1 + do_4rounds (\i + 12), MSG3, MSG0, MSG1, MSG2 +.endr /* Add current hash values with previously saved */ paddd ABEF_SAVE, STATE0 @@ -315,14 +160,14 @@ SYM_TYPED_FUNC_START(sha256_ni_transform) jne .Lloop0 /* Write hash values back in the correct order */ - pshufd $0x1B, STATE0, STATE0 /* FEBA */ - pshufd $0xB1, STATE1, STATE1 /* DCHG */ - movdqa STATE0, MSGTMP4 - pblendw $0xF0, STATE1, STATE0 /* DCBA */ - palignr $8, MSGTMP4, STATE1 /* HGFE */ - - movdqu STATE0, 0*16(DIGEST_PTR) - movdqu STATE1, 1*16(DIGEST_PTR) + movdqa STATE0, TMP + punpcklqdq STATE1, STATE0 /* GHEF */ + punpckhqdq TMP, STATE1 /* ABCD */ + pshufd $0xB1, STATE0, STATE0 /* HGFE */ + pshufd $0x1B, STATE1, STATE1 /* DCBA */ + + movdqu STATE1, 0*16(DIGEST_PTR) + movdqu STATE0, 1*16(DIGEST_PTR) .Ldone_hash: diff --git a/arch/x86/crypto/sha512-avx2-asm.S b/arch/x86/crypto/sha512-avx2-asm.S index f08496cd6870..24973f42c43f 100644 --- a/arch/x86/crypto/sha512-avx2-asm.S +++ b/arch/x86/crypto/sha512-avx2-asm.S @@ -680,6 +680,7 @@ SYM_TYPED_FUNC_START(sha512_transform_rorx) pop %r12 pop %rbx + vzeroupper RET SYM_FUNC_END(sha512_transform_rorx) diff --git a/arch/x86/entry/common.c b/arch/x86/entry/common.c index 6356060caaf3..51cc9c7cb9bd 100644 --- a/arch/x86/entry/common.c +++ b/arch/x86/entry/common.c @@ -49,7 +49,7 @@ static __always_inline bool do_syscall_x64(struct pt_regs *regs, int nr) if (likely(unr < NR_syscalls)) { unr = array_index_nospec(unr, NR_syscalls); - regs->ax = sys_call_table[unr](regs); + regs->ax = x64_sys_call(regs, unr); return true; } return false; @@ -66,7 +66,7 @@ static __always_inline bool do_syscall_x32(struct pt_regs *regs, int nr) if (IS_ENABLED(CONFIG_X86_X32_ABI) && likely(xnr < X32_NR_syscalls)) { xnr = array_index_nospec(xnr, X32_NR_syscalls); - regs->ax = x32_sys_call_table[xnr](regs); + regs->ax = x32_sys_call(regs, xnr); return true; } return false; @@ -162,7 +162,7 @@ static __always_inline void do_syscall_32_irqs_on(struct pt_regs *regs, int nr) if (likely(unr < IA32_NR_syscalls)) { unr = array_index_nospec(unr, IA32_NR_syscalls); - regs->ax = ia32_sys_call_table[unr](regs); + regs->ax = ia32_sys_call(regs, unr); } else if (nr != -1) { regs->ax = __ia32_sys_ni_syscall(regs); } @@ -189,7 +189,7 @@ static __always_inline bool int80_is_external(void) } /** - * int80_emulation - 32-bit legacy syscall entry + * do_int80_emulation - 32-bit legacy syscall C entry from asm * * This entry point can be used by 32-bit and 64-bit programs to perform * 32-bit system calls. Instances of INT $0x80 can be found inline in @@ -207,7 +207,7 @@ static __always_inline bool int80_is_external(void) * eax: system call number * ebx, ecx, edx, esi, edi, ebp: arg1 - arg 6 */ -DEFINE_IDTENTRY_RAW(int80_emulation) +__visible noinstr void do_int80_emulation(struct pt_regs *regs) { int nr; @@ -255,6 +255,71 @@ DEFINE_IDTENTRY_RAW(int80_emulation) instrumentation_end(); syscall_exit_to_user_mode(regs); } + +#ifdef CONFIG_X86_FRED +/* + * A FRED-specific INT80 handler is warranted for the follwing reasons: + * + * 1) As INT instructions and hardware interrupts are separate event + * types, FRED does not preclude the use of vector 0x80 for external + * interrupts. As a result, the FRED setup code does not reserve + * vector 0x80 and calling int80_is_external() is not merely + * suboptimal but actively incorrect: it could cause a system call + * to be incorrectly ignored. + * + * 2) It is called only for handling vector 0x80 of event type + * EVENT_TYPE_SWINT and will never be called to handle any external + * interrupt (event type EVENT_TYPE_EXTINT). + * + * 3) FRED has separate entry flows depending on if the event came from + * user space or kernel space, and because the kernel does not use + * INT insns, the FRED kernel entry handler fred_entry_from_kernel() + * falls through to fred_bad_type() if the event type is + * EVENT_TYPE_SWINT, i.e., INT insns. So if the kernel is handling + * an INT insn, it can only be from a user level. + * + * 4) int80_emulation() does a CLEAR_BRANCH_HISTORY. While FRED will + * likely take a different approach if it is ever needed: it + * probably belongs in either fred_intx()/ fred_other() or + * asm_fred_entrypoint_user(), depending on if this ought to be done + * for all entries from userspace or only system + * calls. + * + * 5) INT $0x80 is the fast path for 32-bit system calls under FRED. + */ +DEFINE_FREDENTRY_RAW(int80_emulation) +{ + int nr; + + enter_from_user_mode(regs); + + instrumentation_begin(); + add_random_kstack_offset(); + + /* + * FRED pushed 0 into regs::orig_ax and regs::ax contains the + * syscall number. + * + * User tracing code (ptrace or signal handlers) might assume + * that the regs::orig_ax contains a 32-bit number on invoking + * a 32-bit syscall. + * + * Establish the syscall convention by saving the 32bit truncated + * syscall number in regs::orig_ax and by invalidating regs::ax. + */ + regs->orig_ax = regs->ax & GENMASK(31, 0); + regs->ax = -ENOSYS; + + nr = syscall_32_enter(regs); + + local_irq_enable(); + nr = syscall_enter_from_user_mode_work(regs, nr); + do_syscall_32_irqs_on(regs, nr); + + instrumentation_end(); + syscall_exit_to_user_mode(regs); +} +#endif #else /* CONFIG_IA32_EMULATION */ /* Handles int $0x80 on a 32bit kernel */ diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S index 8af2a26b24f6..1b5be07f8669 100644 --- a/arch/x86/entry/entry_64.S +++ b/arch/x86/entry/entry_64.S @@ -116,6 +116,7 @@ SYM_INNER_LABEL(entry_SYSCALL_64_after_hwframe, SYM_L_GLOBAL) /* clobbers %rax, make sure it is after saving the syscall nr */ IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY call do_syscall_64 /* returns with IRQs disabled */ @@ -1491,3 +1492,63 @@ SYM_CODE_START_NOALIGN(rewind_stack_and_make_dead) call make_task_dead SYM_CODE_END(rewind_stack_and_make_dead) .popsection + +/* + * This sequence executes branches in order to remove user branch information + * from the branch history tracker in the Branch Predictor, therefore removing + * user influence on subsequent BTB lookups. + * + * It should be used on parts prior to Alder Lake. Newer parts should use the + * BHI_DIS_S hardware control instead. If a pre-Alder Lake part is being + * virtualized on newer hardware the VMM should protect against BHI attacks by + * setting BHI_DIS_S for the guests. + * + * CALLs/RETs are necessary to prevent Loop Stream Detector(LSD) from engaging + * and not clearing the branch history. The call tree looks like: + * + * call 1 + * call 2 + * call 2 + * call 2 + * call 2 + * call 2 + * ret + * ret + * ret + * ret + * ret + * ret + * + * This means that the stack is non-constant and ORC can't unwind it with %rsp + * alone. Therefore we unconditionally set up the frame pointer, which allows + * ORC to unwind properly. + * + * The alignment is for performance and not for safety, and may be safely + * refactored in the future if needed. + */ +SYM_FUNC_START(clear_bhb_loop) + push %rbp + mov %rsp, %rbp + movl $5, %ecx + ANNOTATE_INTRA_FUNCTION_CALL + call 1f + jmp 5f + .align 64, 0xcc + ANNOTATE_INTRA_FUNCTION_CALL +1: call 2f + RET + .align 64, 0xcc +2: movl $5, %eax +3: jmp 4f + nop +4: sub $1, %eax + jnz 3b + sub $1, %ecx + jnz 1b + RET +5: lfence + pop %rbp + RET +SYM_FUNC_END(clear_bhb_loop) +EXPORT_SYMBOL_GPL(clear_bhb_loop) +STACK_FRAME_NON_STANDARD(clear_bhb_loop) diff --git a/arch/x86/entry/entry_64_compat.S b/arch/x86/entry/entry_64_compat.S index eabf48c4d4b4..c779046cc3fe 100644 --- a/arch/x86/entry/entry_64_compat.S +++ b/arch/x86/entry/entry_64_compat.S @@ -92,6 +92,7 @@ SYM_INNER_LABEL(entry_SYSENTER_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY /* * SYSENTER doesn't filter flags, so we need to clear NT and AC @@ -206,6 +207,7 @@ SYM_INNER_LABEL(entry_SYSCALL_compat_after_hwframe, SYM_L_GLOBAL) IBRS_ENTER UNTRAIN_RET + CLEAR_BRANCH_HISTORY movq %rsp, %rdi call do_fast_syscall_32 @@ -276,3 +278,17 @@ SYM_INNER_LABEL(entry_SYSRETL_compat_end, SYM_L_GLOBAL) ANNOTATE_NOENDBR int3 SYM_CODE_END(entry_SYSCALL_compat) + +/* + * int 0x80 is used by 32 bit mode as a system call entry. Normally idt entries + * point to C routines, however since this is a system call interface the branch + * history needs to be scrubbed to protect against BHI attacks, and that + * scrubbing needs to take place in assembly code prior to entering any C + * routines. + */ +SYM_CODE_START(int80_emulation) + ANNOTATE_NOENDBR + UNWIND_HINT_FUNC + CLEAR_BRANCH_HISTORY + jmp do_int80_emulation +SYM_CODE_END(int80_emulation) diff --git a/arch/x86/entry/entry_fred.c b/arch/x86/entry/entry_fred.c index ac120cbdaaf2..89c1476fcdd9 100644 --- a/arch/x86/entry/entry_fred.c +++ b/arch/x86/entry/entry_fred.c @@ -28,9 +28,9 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code if (regs->fred_cs.sl > 0) { pr_emerg("PANIC: invalid or fatal FRED event; event type %u " "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", - regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + regs->fred_ss.type, regs->fred_ss.vector, error_code, fred_event_data(regs), regs->cs, regs->ip); - die("invalid or fatal FRED event", regs, regs->orig_ax); + die("invalid or fatal FRED event", regs, error_code); panic("invalid or fatal FRED event"); } else { unsigned long flags = oops_begin(); @@ -38,10 +38,10 @@ static noinstr void fred_bad_type(struct pt_regs *regs, unsigned long error_code pr_alert("BUG: invalid or fatal FRED event; event type %u " "vector %u error 0x%lx aux 0x%lx at %04x:%016lx\n", - regs->fred_ss.type, regs->fred_ss.vector, regs->orig_ax, + regs->fred_ss.type, regs->fred_ss.vector, error_code, fred_event_data(regs), regs->cs, regs->ip); - if (__die("Invalid or fatal FRED event", regs, regs->orig_ax)) + if (__die("Invalid or fatal FRED event", regs, error_code)) sig = 0; oops_end(flags, regs, sig); @@ -66,7 +66,7 @@ static noinstr void fred_intx(struct pt_regs *regs) /* INT80 */ case IA32_SYSCALL_VECTOR: if (ia32_enabled()) - return int80_emulation(regs); + return fred_int80_emulation(regs); fallthrough; #endif diff --git a/arch/x86/entry/syscall_32.c b/arch/x86/entry/syscall_32.c index 8cfc9bc73e7f..c2235bae17ef 100644 --- a/arch/x86/entry/syscall_32.c +++ b/arch/x86/entry/syscall_32.c @@ -18,8 +18,25 @@ #include <asm/syscalls_32.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ +#ifdef CONFIG_X86_32 #define __SYSCALL(nr, sym) __ia32_##sym, - -__visible const sys_call_ptr_t ia32_sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_32.h> }; +#undef __SYSCALL +#endif + +#define __SYSCALL(nr, sym) case nr: return __ia32_##sym(regs); + +long ia32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_32.h> + default: return __ia32_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_64.c b/arch/x86/entry/syscall_64.c index be120eec1fc9..33b3f09e6f15 100644 --- a/arch/x86/entry/syscall_64.c +++ b/arch/x86/entry/syscall_64.c @@ -11,8 +11,23 @@ #include <asm/syscalls_64.h> #undef __SYSCALL +/* + * The sys_call_table[] is no longer used for system calls, but + * kernel/trace/trace_syscalls.c still wants to know the system + * call address. + */ #define __SYSCALL(nr, sym) __x64_##sym, - -asmlinkage const sys_call_ptr_t sys_call_table[] = { +const sys_call_ptr_t sys_call_table[] = { #include <asm/syscalls_64.h> }; +#undef __SYSCALL + +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); + +long x64_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_64.h> + default: return __x64_sys_ni_syscall(regs); + } +}; diff --git a/arch/x86/entry/syscall_x32.c b/arch/x86/entry/syscall_x32.c index bdd0e03a1265..03de4a932131 100644 --- a/arch/x86/entry/syscall_x32.c +++ b/arch/x86/entry/syscall_x32.c @@ -11,8 +11,12 @@ #include <asm/syscalls_x32.h> #undef __SYSCALL -#define __SYSCALL(nr, sym) __x64_##sym, +#define __SYSCALL(nr, sym) case nr: return __x64_##sym(regs); -asmlinkage const sys_call_ptr_t x32_sys_call_table[] = { -#include <asm/syscalls_x32.h> +long x32_sys_call(const struct pt_regs *regs, unsigned int nr) +{ + switch (nr) { + #include <asm/syscalls_x32.h> + default: return __x64_sys_ni_syscall(regs); + } }; diff --git a/arch/x86/entry/vsyscall/vsyscall_64.c b/arch/x86/entry/vsyscall/vsyscall_64.c index a3c0df11d0e6..2fb7d53cf333 100644 --- a/arch/x86/entry/vsyscall/vsyscall_64.c +++ b/arch/x86/entry/vsyscall/vsyscall_64.c @@ -98,11 +98,6 @@ static int addr_to_vsyscall_nr(unsigned long addr) static bool write_ok_or_segv(unsigned long ptr, size_t size) { - /* - * XXX: if access_ok, get_user, and put_user handled - * sig_on_uaccess_err, this could go away. - */ - if (!access_ok((void __user *)ptr, size)) { struct thread_struct *thread = ¤t->thread; @@ -120,10 +115,8 @@ static bool write_ok_or_segv(unsigned long ptr, size_t size) bool emulate_vsyscall(unsigned long error_code, struct pt_regs *regs, unsigned long address) { - struct task_struct *tsk; unsigned long caller; int vsyscall_nr, syscall_nr, tmp; - int prev_sig_on_uaccess_err; long ret; unsigned long orig_dx; @@ -172,8 +165,6 @@ bool emulate_vsyscall(unsigned long error_code, goto sigsegv; } - tsk = current; - /* * Check for access_ok violations and find the syscall nr. * @@ -234,12 +225,8 @@ bool emulate_vsyscall(unsigned long error_code, goto do_ret; /* skip requested */ /* - * With a real vsyscall, page faults cause SIGSEGV. We want to - * preserve that behavior to make writing exploits harder. + * With a real vsyscall, page faults cause SIGSEGV. */ - prev_sig_on_uaccess_err = current->thread.sig_on_uaccess_err; - current->thread.sig_on_uaccess_err = 1; - ret = -EFAULT; switch (vsyscall_nr) { case 0: @@ -262,23 +249,12 @@ bool emulate_vsyscall(unsigned long error_code, break; } - current->thread.sig_on_uaccess_err = prev_sig_on_uaccess_err; - check_fault: if (ret == -EFAULT) { /* Bad news -- userspace fed a bad pointer to a vsyscall. */ warn_bad_vsyscall(KERN_INFO, regs, "vsyscall fault (exploit attempt?)"); - - /* - * If we failed to generate a signal for any reason, - * generate one here. (This should be impossible.) - */ - if (WARN_ON_ONCE(!sigismember(&tsk->pending.signal, SIGBUS) && - !sigismember(&tsk->pending.signal, SIGSEGV))) - goto sigsegv; - - return true; /* Don't emulate the ret. */ + goto sigsegv; } regs->ax = ret; diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c index 09050641ce5d..5b0dd07b1ef1 100644 --- a/arch/x86/events/core.c +++ b/arch/x86/events/core.c @@ -1644,6 +1644,7 @@ static void x86_pmu_del(struct perf_event *event, int flags) while (++i < cpuc->n_events) { cpuc->event_list[i-1] = cpuc->event_list[i]; cpuc->event_constraint[i-1] = cpuc->event_constraint[i]; + cpuc->assign[i-1] = cpuc->assign[i]; } cpuc->event_constraint[i-1] = NULL; --cpuc->n_events; diff --git a/arch/x86/events/intel/lbr.c b/arch/x86/events/intel/lbr.c index 78cd5084104e..4367aa77cb8d 100644 --- a/arch/x86/events/intel/lbr.c +++ b/arch/x86/events/intel/lbr.c @@ -1693,6 +1693,7 @@ void x86_perf_get_lbr(struct x86_pmu_lbr *lbr) lbr->from = x86_pmu.lbr_from; lbr->to = x86_pmu.lbr_to; lbr->info = x86_pmu.lbr_info; + lbr->has_callstack = x86_pmu_has_lbr_callstack(); } EXPORT_SYMBOL_GPL(x86_perf_get_lbr); diff --git a/arch/x86/hyperv/hv_apic.c b/arch/x86/hyperv/hv_apic.c index 5fc45543e955..0569f579338b 100644 --- a/arch/x86/hyperv/hv_apic.c +++ b/arch/x86/hyperv/hv_apic.c @@ -105,7 +105,7 @@ static bool cpu_is_self(int cpu) * IPI implementation on Hyper-V. */ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, - bool exclude_self) + bool exclude_self) { struct hv_send_ipi_ex *ipi_arg; unsigned long flags; @@ -132,8 +132,8 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, if (!cpumask_equal(mask, cpu_present_mask) || exclude_self) { ipi_arg->vp_set.format = HV_GENERIC_SET_SPARSE_4K; - nr_bank = cpumask_to_vpset_skip(&(ipi_arg->vp_set), mask, - exclude_self ? cpu_is_self : NULL); + nr_bank = cpumask_to_vpset_skip(&ipi_arg->vp_set, mask, + exclude_self ? cpu_is_self : NULL); /* * 'nr_bank <= 0' means some CPUs in cpumask can't be @@ -147,7 +147,7 @@ static bool __send_ipi_mask_ex(const struct cpumask *mask, int vector, } status = hv_do_rep_hypercall(HVCALL_SEND_IPI_EX, 0, nr_bank, - ipi_arg, NULL); + ipi_arg, NULL); ipi_mask_ex_done: local_irq_restore(flags); @@ -155,7 +155,7 @@ ipi_mask_ex_done: } static bool __send_ipi_mask(const struct cpumask *mask, int vector, - bool exclude_self) + bool exclude_self) { int cur_cpu, vcpu, this_cpu = smp_processor_id(); struct hv_send_ipi ipi_arg; @@ -181,7 +181,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector, return false; } - if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR) return false; /* @@ -218,7 +218,7 @@ static bool __send_ipi_mask(const struct cpumask *mask, int vector, } status = hv_do_fast_hypercall16(HVCALL_SEND_IPI, ipi_arg.vector, - ipi_arg.cpu_mask); + ipi_arg.cpu_mask); return hv_result_success(status); do_ex_hypercall: @@ -241,7 +241,7 @@ static bool __send_ipi_one(int cpu, int vector) return false; } - if ((vector < HV_IPI_LOW_VECTOR) || (vector > HV_IPI_HIGH_VECTOR)) + if (vector < HV_IPI_LOW_VECTOR || vector > HV_IPI_HIGH_VECTOR) return false; if (vp >= 64) diff --git a/arch/x86/hyperv/hv_proc.c b/arch/x86/hyperv/hv_proc.c index 68a0843d4750..3fa1f2ee7b0d 100644 --- a/arch/x86/hyperv/hv_proc.c +++ b/arch/x86/hyperv/hv_proc.c @@ -3,7 +3,6 @@ #include <linux/vmalloc.h> #include <linux/mm.h> #include <linux/clockchips.h> -#include <linux/acpi.h> #include <linux/hyperv.h> #include <linux/slab.h> #include <linux/cpuhotplug.h> @@ -116,12 +115,11 @@ free_buf: int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) { - struct hv_add_logical_processor_in *input; - struct hv_add_logical_processor_out *output; + struct hv_input_add_logical_processor *input; + struct hv_output_add_logical_processor *output; u64 status; unsigned long flags; int ret = HV_STATUS_SUCCESS; - int pxm = node_to_pxm(node); /* * When adding a logical processor, the hypervisor may return @@ -137,11 +135,7 @@ int hv_call_add_logical_proc(int node, u32 lp_index, u32 apic_id) input->lp_index = lp_index; input->apic_id = apic_id; - input->flags = 0; - input->proximity_domain_info.domain_id = pxm; - input->proximity_domain_info.flags.reserved = 0; - input->proximity_domain_info.flags.proximity_info_valid = 1; - input->proximity_domain_info.flags.proximity_preferred = 1; + input->proximity_domain_info = hv_numa_node_to_pxm_info(node); status = hv_do_hypercall(HVCALL_ADD_LOGICAL_PROCESSOR, input, output); local_irq_restore(flags); @@ -166,7 +160,6 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) u64 status; unsigned long irq_flags; int ret = HV_STATUS_SUCCESS; - int pxm = node_to_pxm(node); /* Root VPs don't seem to need pages deposited */ if (partition_id != hv_current_partition_id) { @@ -185,14 +178,7 @@ int hv_call_create_vp(int node, u64 partition_id, u32 vp_index, u32 flags) input->vp_index = vp_index; input->flags = flags; input->subnode_type = HvSubnodeAny; - if (node != NUMA_NO_NODE) { - input->proximity_domain_info.domain_id = pxm; - input->proximity_domain_info.flags.reserved = 0; - input->proximity_domain_info.flags.proximity_info_valid = 1; - input->proximity_domain_info.flags.proximity_preferred = 1; - } else { - input->proximity_domain_info.as_uint64 = 0; - } + input->proximity_domain_info = hv_numa_node_to_pxm_info(node); status = hv_do_hypercall(HVCALL_CREATE_VP, input, NULL); local_irq_restore(irq_flags); diff --git a/arch/x86/include/asm/apic.h b/arch/x86/include/asm/apic.h index 94ce0f7c9d3a..e6ab0cf15ed5 100644 --- a/arch/x86/include/asm/apic.h +++ b/arch/x86/include/asm/apic.h @@ -13,6 +13,7 @@ #include <asm/mpspec.h> #include <asm/msr.h> #include <asm/hardirq.h> +#include <asm/io.h> #define ARCH_APICTIMER_STOPS_ON_C3 1 @@ -98,7 +99,7 @@ static inline void native_apic_mem_write(u32 reg, u32 v) static inline u32 native_apic_mem_read(u32 reg) { - return *((volatile u32 *)(APIC_BASE + reg)); + return readl((void __iomem *)(APIC_BASE + reg)); } static inline void native_apic_mem_eoi(void) diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h index fe1e7e3cc844..63bdc6b85219 100644 --- a/arch/x86/include/asm/barrier.h +++ b/arch/x86/include/asm/barrier.h @@ -79,6 +79,9 @@ do { \ #define __smp_mb__before_atomic() do { } while (0) #define __smp_mb__after_atomic() do { } while (0) +/* Writing to CR3 provides a full memory barrier in switch_mm(). */ +#define smp_mb__after_switch_mm() do { } while (0) + #include <asm-generic/barrier.h> #endif /* _ASM_X86_BARRIER_H */ diff --git a/arch/x86/include/asm/coco.h b/arch/x86/include/asm/coco.h index c086699b0d0c..aa6c8f8ca958 100644 --- a/arch/x86/include/asm/coco.h +++ b/arch/x86/include/asm/coco.h @@ -25,6 +25,7 @@ u64 cc_mkdec(u64 val); void cc_random_init(void); #else #define cc_vendor (CC_VENDOR_NONE) +static const u64 cc_mask = 0; static inline u64 cc_mkenc(u64 val) { diff --git a/arch/x86/include/asm/cpufeatures.h b/arch/x86/include/asm/cpufeatures.h index a38f8f9ba657..3c7434329661 100644 --- a/arch/x86/include/asm/cpufeatures.h +++ b/arch/x86/include/asm/cpufeatures.h @@ -461,11 +461,15 @@ /* * Extended auxiliary flags: Linux defined - for features scattered in various - * CPUID levels like 0x80000022, etc. + * CPUID levels like 0x80000022, etc and Linux defined features. * * Reuse free bits when adding new feature flags! */ #define X86_FEATURE_AMD_LBR_PMC_FREEZE (21*32+ 0) /* AMD LBR and PMC Freeze */ +#define X86_FEATURE_CLEAR_BHB_LOOP (21*32+ 1) /* "" Clear branch history at syscall entry using SW loop */ +#define X86_FEATURE_BHI_CTRL (21*32+ 2) /* "" BHI_DIS_S HW control available */ +#define X86_FEATURE_CLEAR_BHB_HW (21*32+ 3) /* "" BHI_DIS_S HW control enabled */ +#define X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT (21*32+ 4) /* "" Clear branch history at vmexit using SW loop */ /* * BUG word(s) @@ -515,4 +519,5 @@ #define X86_BUG_SRSO X86_BUG(1*32 + 0) /* AMD SRSO bug */ #define X86_BUG_DIV0 X86_BUG(1*32 + 1) /* AMD DIV0 speculation bug */ #define X86_BUG_RFDS X86_BUG(1*32 + 2) /* CPU is vulnerable to Register File Data Sampling */ +#define X86_BUG_BHI X86_BUG(1*32 + 3) /* CPU is affected by Branch History Injection */ #endif /* _ASM_X86_CPUFEATURES_H */ diff --git a/arch/x86/include/asm/e820/api.h b/arch/x86/include/asm/e820/api.h index e8f58ddd06d9..2e74a7f0e935 100644 --- a/arch/x86/include/asm/e820/api.h +++ b/arch/x86/include/asm/e820/api.h @@ -17,6 +17,7 @@ extern bool e820__mapped_all(u64 start, u64 end, enum e820_type type); extern void e820__range_add (u64 start, u64 size, enum e820_type type); extern u64 e820__range_update(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); extern u64 e820__range_remove(u64 start, u64 size, enum e820_type old_type, bool check_type); +extern u64 e820__range_update_table(struct e820_table *t, u64 start, u64 size, enum e820_type old_type, enum e820_type new_type); extern void e820__print_table(char *who); extern int e820__update_table(struct e820_table *table); diff --git a/arch/x86/include/asm/kvm_host.h b/arch/x86/include/asm/kvm_host.h index 16e07a2eee19..6efd1497b026 100644 --- a/arch/x86/include/asm/kvm_host.h +++ b/arch/x86/include/asm/kvm_host.h @@ -855,6 +855,7 @@ struct kvm_vcpu_arch { int cpuid_nent; struct kvm_cpuid_entry2 *cpuid_entries; struct kvm_hypervisor_cpuid kvm_cpuid; + bool is_amd_compatible; /* * FIXME: Drop this macro and use KVM_NR_GOVERNED_FEATURES directly diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h index 05956bd8bacf..e72c2b872957 100644 --- a/arch/x86/include/asm/msr-index.h +++ b/arch/x86/include/asm/msr-index.h @@ -61,10 +61,13 @@ #define SPEC_CTRL_SSBD BIT(SPEC_CTRL_SSBD_SHIFT) /* Speculative Store Bypass Disable */ #define SPEC_CTRL_RRSBA_DIS_S_SHIFT 6 /* Disable RRSBA behavior */ #define SPEC_CTRL_RRSBA_DIS_S BIT(SPEC_CTRL_RRSBA_DIS_S_SHIFT) +#define SPEC_CTRL_BHI_DIS_S_SHIFT 10 /* Disable Branch History Injection behavior */ +#define SPEC_CTRL_BHI_DIS_S BIT(SPEC_CTRL_BHI_DIS_S_SHIFT) /* A mask for bits which the kernel toggles when controlling mitigations */ #define SPEC_CTRL_MITIGATIONS_MASK (SPEC_CTRL_IBRS | SPEC_CTRL_STIBP | SPEC_CTRL_SSBD \ - | SPEC_CTRL_RRSBA_DIS_S) + | SPEC_CTRL_RRSBA_DIS_S \ + | SPEC_CTRL_BHI_DIS_S) #define MSR_IA32_PRED_CMD 0x00000049 /* Prediction Command */ #define PRED_CMD_IBPB BIT(0) /* Indirect Branch Prediction Barrier */ @@ -163,6 +166,10 @@ * are restricted to targets in * kernel. */ +#define ARCH_CAP_BHI_NO BIT(20) /* + * CPU is not affected by Branch + * History Injection. + */ #define ARCH_CAP_PBRSB_NO BIT(24) /* * Not susceptible to Post-Barrier * Return Stack Buffer Predictions. diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index 170c89ed22fc..ff5f1ecc7d1e 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -326,6 +326,19 @@ ALTERNATIVE "", __stringify(verw _ASM_RIP(mds_verw_sel)), X86_FEATURE_CLEAR_CPU_BUF .endm +#ifdef CONFIG_X86_64 +.macro CLEAR_BRANCH_HISTORY + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP +.endm + +.macro CLEAR_BRANCH_HISTORY_VMEXIT + ALTERNATIVE "", "call clear_bhb_loop", X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT +.endm +#else +#define CLEAR_BRANCH_HISTORY +#define CLEAR_BRANCH_HISTORY_VMEXIT +#endif + #else /* __ASSEMBLY__ */ #define ANNOTATE_RETPOLINE_SAFE \ @@ -368,6 +381,10 @@ extern void srso_alias_return_thunk(void); extern void entry_untrain_ret(void); extern void entry_ibpb(void); +#ifdef CONFIG_X86_64 +extern void clear_bhb_loop(void); +#endif + extern void (*x86_return_thunk)(void); extern void __warn_thunk(void); diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h index 3736b8a46c04..7f1e17250546 100644 --- a/arch/x86/include/asm/perf_event.h +++ b/arch/x86/include/asm/perf_event.h @@ -555,6 +555,7 @@ struct x86_pmu_lbr { unsigned int from; unsigned int to; unsigned int info; + bool has_callstack; }; extern void perf_get_x86_pmu_capability(struct x86_pmu_capability *cap); diff --git a/arch/x86/include/asm/pgtable_types.h b/arch/x86/include/asm/pgtable_types.h index 0b748ee16b3d..9abb8cc4cd47 100644 --- a/arch/x86/include/asm/pgtable_types.h +++ b/arch/x86/include/asm/pgtable_types.h @@ -148,7 +148,7 @@ #define _COMMON_PAGE_CHG_MASK (PTE_PFN_MASK | _PAGE_PCD | _PAGE_PWT | \ _PAGE_SPECIAL | _PAGE_ACCESSED | \ _PAGE_DIRTY_BITS | _PAGE_SOFT_DIRTY | \ - _PAGE_DEVMAP | _PAGE_ENC | _PAGE_UFFD_WP) + _PAGE_DEVMAP | _PAGE_CC | _PAGE_UFFD_WP) #define _PAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PAT) #define _HPAGE_CHG_MASK (_COMMON_PAGE_CHG_MASK | _PAGE_PSE | _PAGE_PAT_LARGE) @@ -173,6 +173,7 @@ enum page_cache_mode { }; #endif +#define _PAGE_CC (_AT(pteval_t, cc_mask)) #define _PAGE_ENC (_AT(pteval_t, sme_me_mask)) #define _PAGE_CACHE_MASK (_PAGE_PWT | _PAGE_PCD | _PAGE_PAT) diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h index 811548f131f4..78e51b0d6433 100644 --- a/arch/x86/include/asm/processor.h +++ b/arch/x86/include/asm/processor.h @@ -472,7 +472,6 @@ struct thread_struct { unsigned long iopl_emul; unsigned int iopl_warn:1; - unsigned int sig_on_uaccess_err:1; /* * Protection Keys Register for Userspace. Loaded immediately on diff --git a/arch/x86/include/asm/sev.h b/arch/x86/include/asm/sev.h index 7f57382afee4..93ed60080cfe 100644 --- a/arch/x86/include/asm/sev.h +++ b/arch/x86/include/asm/sev.h @@ -269,6 +269,7 @@ int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 asid, bool immut int rmp_make_shared(u64 pfn, enum pg_level level); void snp_leak_pages(u64 pfn, unsigned int npages); void kdump_sev_callback(void); +void snp_fixup_e820_tables(void); #else static inline bool snp_probe_rmptable_info(void) { return false; } static inline int snp_lookup_rmpentry(u64 pfn, bool *assigned, int *level) { return -ENODEV; } @@ -282,6 +283,7 @@ static inline int rmp_make_private(u64 pfn, u64 gpa, enum pg_level level, u32 as static inline int rmp_make_shared(u64 pfn, enum pg_level level) { return -ENODEV; } static inline void snp_leak_pages(u64 pfn, unsigned int npages) {} static inline void kdump_sev_callback(void) { } +static inline void snp_fixup_e820_tables(void) {} #endif #endif diff --git a/arch/x86/include/asm/syscall.h b/arch/x86/include/asm/syscall.h index f44e2f9ab65d..2fc7bc3863ff 100644 --- a/arch/x86/include/asm/syscall.h +++ b/arch/x86/include/asm/syscall.h @@ -16,19 +16,17 @@ #include <asm/thread_info.h> /* for TS_COMPAT */ #include <asm/unistd.h> +/* This is used purely for kernel/trace/trace_syscalls.c */ typedef long (*sys_call_ptr_t)(const struct pt_regs *); extern const sys_call_ptr_t sys_call_table[]; -#if defined(CONFIG_X86_32) -#define ia32_sys_call_table sys_call_table -#else /* * These may not exist, but still put the prototypes in so we * can use IS_ENABLED(). */ -extern const sys_call_ptr_t ia32_sys_call_table[]; -extern const sys_call_ptr_t x32_sys_call_table[]; -#endif +extern long ia32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x32_sys_call(const struct pt_regs *, unsigned int nr); +extern long x64_sys_call(const struct pt_regs *, unsigned int nr); /* * Only the low 32 bits of orig_ax are meaningful, so we return int. @@ -127,6 +125,7 @@ static inline int syscall_get_arch(struct task_struct *task) } bool do_syscall_64(struct pt_regs *regs, int nr); +void do_int80_emulation(struct pt_regs *regs); #endif /* CONFIG_X86_32 */ diff --git a/arch/x86/kernel/amd_nb.c b/arch/x86/kernel/amd_nb.c index 5bf5f9fc5753..3cf156f70859 100644 --- a/arch/x86/kernel/amd_nb.c +++ b/arch/x86/kernel/amd_nb.c @@ -95,6 +95,7 @@ static const struct pci_device_id amd_nb_misc_ids[] = { { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_19H_M78H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M00H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M20H_DF_F3) }, + { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_1AH_M70H_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI200_DF_F3) }, { PCI_DEVICE(PCI_VENDOR_ID_AMD, PCI_DEVICE_ID_AMD_MI300_DF_F3) }, {} diff --git a/arch/x86/kernel/apic/apic.c b/arch/x86/kernel/apic/apic.c index a42d8a6f7149..803dcfb0e346 100644 --- a/arch/x86/kernel/apic/apic.c +++ b/arch/x86/kernel/apic/apic.c @@ -1687,11 +1687,11 @@ static int x2apic_state; static bool x2apic_hw_locked(void) { - u64 ia32_cap; + u64 x86_arch_cap_msr; u64 msr; - ia32_cap = x86_read_arch_cap_msr(); - if (ia32_cap & ARCH_CAP_XAPIC_DISABLE) { + x86_arch_cap_msr = x86_read_arch_cap_msr(); + if (x86_arch_cap_msr & ARCH_CAP_XAPIC_DISABLE) { rdmsrl(MSR_IA32_XAPIC_DISABLE_STATUS, msr); return (msr & LEGACY_XAPIC_DISABLED); } @@ -1771,7 +1771,7 @@ void x2apic_setup(void) __x2apic_enable(); } -static __init void apic_set_fixmap(void); +static __init void apic_set_fixmap(bool read_apic); static __init void x2apic_disable(void) { @@ -1793,7 +1793,12 @@ static __init void x2apic_disable(void) } __x2apic_disable(); - apic_set_fixmap(); + /* + * Don't reread the APIC ID as it was already done from + * check_x2apic() and the APIC driver still is a x2APIC variant, + * which fails to do the read after x2APIC was disabled. + */ + apic_set_fixmap(false); } static __init void x2apic_enable(void) @@ -2057,13 +2062,14 @@ void __init init_apic_mappings(void) } } -static __init void apic_set_fixmap(void) +static __init void apic_set_fixmap(bool read_apic) { set_fixmap_nocache(FIX_APIC_BASE, mp_lapic_addr); apic_mmio_base = APIC_BASE; apic_printk(APIC_VERBOSE, "mapped APIC to %16lx (%16lx)\n", apic_mmio_base, mp_lapic_addr); - apic_read_boot_cpu_id(false); + if (read_apic) + apic_read_boot_cpu_id(false); } void __init register_lapic_address(unsigned long address) @@ -2073,7 +2079,7 @@ void __init register_lapic_address(unsigned long address) mp_lapic_addr = address; if (!x2apic_mode) - apic_set_fixmap(); + apic_set_fixmap(true); } /* diff --git a/arch/x86/kernel/cpu/amd.c b/arch/x86/kernel/cpu/amd.c index 9bf17c9c29da..307302af0aee 100644 --- a/arch/x86/kernel/cpu/amd.c +++ b/arch/x86/kernel/cpu/amd.c @@ -459,8 +459,7 @@ static void bsp_init_amd(struct cpuinfo_x86 *c) case 0x1a: switch (c->x86_model) { - case 0x00 ... 0x0f: - case 0x20 ... 0x2f: + case 0x00 ... 0x2f: case 0x40 ... 0x4f: case 0x70 ... 0x7f: setup_force_cpu_cap(X86_FEATURE_ZEN5); @@ -535,7 +534,6 @@ clear_sev: static void early_init_amd(struct cpuinfo_x86 *c) { - u64 value; u32 dummy; if (c->x86 >= 0xf) @@ -603,20 +601,6 @@ static void early_init_amd(struct cpuinfo_x86 *c) early_detect_mem_encrypt(c); - /* Re-enable TopologyExtensions if switched off by BIOS */ - if (c->x86 == 0x15 && - (c->x86_model >= 0x10 && c->x86_model <= 0x6f) && - !cpu_has(c, X86_FEATURE_TOPOEXT)) { - - if (msr_set_bit(0xc0011005, 54) > 0) { - rdmsrl(0xc0011005, value); - if (value & BIT_64(54)) { - set_cpu_cap(c, X86_FEATURE_TOPOEXT); - pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); - } - } - } - if (!cpu_has(c, X86_FEATURE_HYPERVISOR) && !cpu_has(c, X86_FEATURE_IBPB_BRTYPE)) { if (c->x86 == 0x17 && boot_cpu_has(X86_FEATURE_AMD_IBPB)) setup_force_cpu_cap(X86_FEATURE_IBPB_BRTYPE); diff --git a/arch/x86/kernel/cpu/bugs.c b/arch/x86/kernel/cpu/bugs.c index e7ba936d798b..ab18185894df 100644 --- a/arch/x86/kernel/cpu/bugs.c +++ b/arch/x86/kernel/cpu/bugs.c @@ -61,6 +61,8 @@ EXPORT_PER_CPU_SYMBOL_GPL(x86_spec_ctrl_current); u64 x86_pred_cmd __ro_after_init = PRED_CMD_IBPB; EXPORT_SYMBOL_GPL(x86_pred_cmd); +static u64 __ro_after_init x86_arch_cap_msr; + static DEFINE_MUTEX(spec_ctrl_mutex); void (*x86_return_thunk)(void) __ro_after_init = __x86_return_thunk; @@ -144,6 +146,8 @@ void __init cpu_select_mitigations(void) x86_spec_ctrl_base &= ~SPEC_CTRL_MITIGATIONS_MASK; } + x86_arch_cap_msr = x86_read_arch_cap_msr(); + /* Select the proper CPU mitigations before patching alternatives: */ spectre_v1_select_mitigation(); spectre_v2_select_mitigation(); @@ -301,8 +305,6 @@ static const char * const taa_strings[] = { static void __init taa_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_TAA)) { taa_mitigation = TAA_MITIGATION_OFF; return; @@ -341,9 +343,8 @@ static void __init taa_select_mitigation(void) * On MDS_NO=1 CPUs if ARCH_CAP_TSX_CTRL_MSR is not set, microcode * update is required. */ - ia32_cap = x86_read_arch_cap_msr(); - if ( (ia32_cap & ARCH_CAP_MDS_NO) && - !(ia32_cap & ARCH_CAP_TSX_CTRL_MSR)) + if ( (x86_arch_cap_msr & ARCH_CAP_MDS_NO) && + !(x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR)) taa_mitigation = TAA_MITIGATION_UCODE_NEEDED; /* @@ -401,8 +402,6 @@ static const char * const mmio_strings[] = { static void __init mmio_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA) || boot_cpu_has_bug(X86_BUG_MMIO_UNKNOWN) || cpu_mitigations_off()) { @@ -413,8 +412,6 @@ static void __init mmio_select_mitigation(void) if (mmio_mitigation == MMIO_MITIGATION_OFF) return; - ia32_cap = x86_read_arch_cap_msr(); - /* * Enable CPU buffer clear mitigation for host and VMM, if also affected * by MDS or TAA. Otherwise, enable mitigation for VMM only. @@ -437,7 +434,7 @@ static void __init mmio_select_mitigation(void) * be propagated to uncore buffers, clearing the Fill buffers on idle * is required irrespective of SMT state. */ - if (!(ia32_cap & ARCH_CAP_FBSDP_NO)) + if (!(x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) static_branch_enable(&mds_idle_clear); /* @@ -447,10 +444,10 @@ static void __init mmio_select_mitigation(void) * FB_CLEAR or by the presence of both MD_CLEAR and L1D_FLUSH on MDS * affected systems. */ - if ((ia32_cap & ARCH_CAP_FB_CLEAR) || + if ((x86_arch_cap_msr & ARCH_CAP_FB_CLEAR) || (boot_cpu_has(X86_FEATURE_MD_CLEAR) && boot_cpu_has(X86_FEATURE_FLUSH_L1D) && - !(ia32_cap & ARCH_CAP_MDS_NO))) + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO))) mmio_mitigation = MMIO_MITIGATION_VERW; else mmio_mitigation = MMIO_MITIGATION_UCODE_NEEDED; @@ -508,7 +505,7 @@ static void __init rfds_select_mitigation(void) if (rfds_mitigation == RFDS_MITIGATION_OFF) return; - if (x86_read_arch_cap_msr() & ARCH_CAP_RFDS_CLEAR) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) setup_force_cpu_cap(X86_FEATURE_CLEAR_CPU_BUF); else rfds_mitigation = RFDS_MITIGATION_UCODE_NEEDED; @@ -659,8 +656,6 @@ void update_srbds_msr(void) static void __init srbds_select_mitigation(void) { - u64 ia32_cap; - if (!boot_cpu_has_bug(X86_BUG_SRBDS)) return; @@ -669,8 +664,7 @@ static void __init srbds_select_mitigation(void) * are only exposed to SRBDS when TSX is enabled or when CPU is affected * by Processor MMIO Stale Data vulnerability. */ - ia32_cap = x86_read_arch_cap_msr(); - if ((ia32_cap & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && + if ((x86_arch_cap_msr & ARCH_CAP_MDS_NO) && !boot_cpu_has(X86_FEATURE_RTM) && !boot_cpu_has_bug(X86_BUG_MMIO_STALE_DATA)) srbds_mitigation = SRBDS_MITIGATION_TSX_OFF; else if (boot_cpu_has(X86_FEATURE_HYPERVISOR)) @@ -813,7 +807,7 @@ static void __init gds_select_mitigation(void) /* Will verify below that mitigation _can_ be disabled */ /* No microcode */ - if (!(x86_read_arch_cap_msr() & ARCH_CAP_GDS_CTRL)) { + if (!(x86_arch_cap_msr & ARCH_CAP_GDS_CTRL)) { if (gds_mitigation == GDS_MITIGATION_FORCE) { /* * This only needs to be done on the boot CPU so do it @@ -1544,20 +1538,25 @@ static enum spectre_v2_mitigation __init spectre_v2_select_retpoline(void) return SPECTRE_V2_RETPOLINE; } +static bool __ro_after_init rrsba_disabled; + /* Disable in-kernel use of non-RSB RET predictors */ static void __init spec_ctrl_disable_kernel_rrsba(void) { - u64 ia32_cap; + if (rrsba_disabled) + return; - if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + if (!(x86_arch_cap_msr & ARCH_CAP_RRSBA)) { + rrsba_disabled = true; return; + } - ia32_cap = x86_read_arch_cap_msr(); + if (!boot_cpu_has(X86_FEATURE_RRSBA_CTRL)) + return; - if (ia32_cap & ARCH_CAP_RRSBA) { - x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; - update_spec_ctrl(x86_spec_ctrl_base); - } + x86_spec_ctrl_base |= SPEC_CTRL_RRSBA_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + rrsba_disabled = true; } static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_mitigation mode) @@ -1607,6 +1606,74 @@ static void __init spectre_v2_determine_rsb_fill_type_at_vmexit(enum spectre_v2_ dump_stack(); } +/* + * Set BHI_DIS_S to prevent indirect branches in kernel to be influenced by + * branch history in userspace. Not needed if BHI_NO is set. + */ +static bool __init spec_ctrl_bhi_dis(void) +{ + if (!boot_cpu_has(X86_FEATURE_BHI_CTRL)) + return false; + + x86_spec_ctrl_base |= SPEC_CTRL_BHI_DIS_S; + update_spec_ctrl(x86_spec_ctrl_base); + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_HW); + + return true; +} + +enum bhi_mitigations { + BHI_MITIGATION_OFF, + BHI_MITIGATION_ON, +}; + +static enum bhi_mitigations bhi_mitigation __ro_after_init = + IS_ENABLED(CONFIG_MITIGATION_SPECTRE_BHI) ? BHI_MITIGATION_ON : BHI_MITIGATION_OFF; + +static int __init spectre_bhi_parse_cmdline(char *str) +{ + if (!str) + return -EINVAL; + + if (!strcmp(str, "off")) + bhi_mitigation = BHI_MITIGATION_OFF; + else if (!strcmp(str, "on")) + bhi_mitigation = BHI_MITIGATION_ON; + else + pr_err("Ignoring unknown spectre_bhi option (%s)", str); + + return 0; +} +early_param("spectre_bhi", spectre_bhi_parse_cmdline); + +static void __init bhi_select_mitigation(void) +{ + if (bhi_mitigation == BHI_MITIGATION_OFF) + return; + + /* Retpoline mitigates against BHI unless the CPU has RRSBA behavior */ + if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE)) { + spec_ctrl_disable_kernel_rrsba(); + if (rrsba_disabled) + return; + } + + if (spec_ctrl_bhi_dis()) + return; + + if (!IS_ENABLED(CONFIG_X86_64)) + return; + + /* Mitigate KVM by default */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT); + pr_info("Spectre BHI mitigation: SW BHB clearing on vm exit\n"); + + /* Mitigate syscalls when the mitigation is forced =on */ + setup_force_cpu_cap(X86_FEATURE_CLEAR_BHB_LOOP); + pr_info("Spectre BHI mitigation: SW BHB clearing on syscall\n"); +} + static void __init spectre_v2_select_mitigation(void) { enum spectre_v2_mitigation_cmd cmd = spectre_v2_parse_cmdline(); @@ -1718,6 +1785,9 @@ static void __init spectre_v2_select_mitigation(void) mode == SPECTRE_V2_RETPOLINE) spec_ctrl_disable_kernel_rrsba(); + if (boot_cpu_has(X86_BUG_BHI)) + bhi_select_mitigation(); + spectre_v2_enabled = mode; pr_info("%s\n", spectre_v2_strings[mode]); @@ -1832,8 +1902,6 @@ static void update_indir_branch_cond(void) /* Update the static key controlling the MDS CPU buffer clear in idle */ static void update_mds_branch_idle(void) { - u64 ia32_cap = x86_read_arch_cap_msr(); - /* * Enable the idle clearing if SMT is active on CPUs which are * affected only by MSBDS and not any other MDS variant. @@ -1848,7 +1916,7 @@ static void update_mds_branch_idle(void) if (sched_smt_active()) { static_branch_enable(&mds_idle_clear); } else if (mmio_mitigation == MMIO_MITIGATION_OFF || - (ia32_cap & ARCH_CAP_FBSDP_NO)) { + (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO)) { static_branch_disable(&mds_idle_clear); } } @@ -2695,15 +2763,15 @@ static char *stibp_state(void) switch (spectre_v2_user_stibp) { case SPECTRE_V2_USER_NONE: - return ", STIBP: disabled"; + return "; STIBP: disabled"; case SPECTRE_V2_USER_STRICT: - return ", STIBP: forced"; + return "; STIBP: forced"; case SPECTRE_V2_USER_STRICT_PREFERRED: - return ", STIBP: always-on"; + return "; STIBP: always-on"; case SPECTRE_V2_USER_PRCTL: case SPECTRE_V2_USER_SECCOMP: if (static_key_enabled(&switch_to_cond_stibp)) - return ", STIBP: conditional"; + return "; STIBP: conditional"; } return ""; } @@ -2712,10 +2780,10 @@ static char *ibpb_state(void) { if (boot_cpu_has(X86_FEATURE_IBPB)) { if (static_key_enabled(&switch_mm_always_ibpb)) - return ", IBPB: always-on"; + return "; IBPB: always-on"; if (static_key_enabled(&switch_mm_cond_ibpb)) - return ", IBPB: conditional"; - return ", IBPB: disabled"; + return "; IBPB: conditional"; + return "; IBPB: disabled"; } return ""; } @@ -2725,14 +2793,32 @@ static char *pbrsb_eibrs_state(void) if (boot_cpu_has_bug(X86_BUG_EIBRS_PBRSB)) { if (boot_cpu_has(X86_FEATURE_RSB_VMEXIT_LITE) || boot_cpu_has(X86_FEATURE_RSB_VMEXIT)) - return ", PBRSB-eIBRS: SW sequence"; + return "; PBRSB-eIBRS: SW sequence"; else - return ", PBRSB-eIBRS: Vulnerable"; + return "; PBRSB-eIBRS: Vulnerable"; } else { - return ", PBRSB-eIBRS: Not affected"; + return "; PBRSB-eIBRS: Not affected"; } } +static const char *spectre_bhi_state(void) +{ + if (!boot_cpu_has_bug(X86_BUG_BHI)) + return "; BHI: Not affected"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_HW)) + return "; BHI: BHI_DIS_S"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP)) + return "; BHI: SW loop, KVM: SW loop"; + else if (boot_cpu_has(X86_FEATURE_RETPOLINE) && + !boot_cpu_has(X86_FEATURE_RETPOLINE_LFENCE) && + rrsba_disabled) + return "; BHI: Retpoline"; + else if (boot_cpu_has(X86_FEATURE_CLEAR_BHB_LOOP_ON_VMEXIT)) + return "; BHI: Vulnerable, KVM: SW loop"; + + return "; BHI: Vulnerable"; +} + static ssize_t spectre_v2_show_state(char *buf) { if (spectre_v2_enabled == SPECTRE_V2_LFENCE) @@ -2745,13 +2831,15 @@ static ssize_t spectre_v2_show_state(char *buf) spectre_v2_enabled == SPECTRE_V2_EIBRS_LFENCE) return sysfs_emit(buf, "Vulnerable: eIBRS+LFENCE with unprivileged eBPF and SMT\n"); - return sysfs_emit(buf, "%s%s%s%s%s%s%s\n", + return sysfs_emit(buf, "%s%s%s%s%s%s%s%s\n", spectre_v2_strings[spectre_v2_enabled], ibpb_state(), - boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? ", IBRS_FW" : "", + boot_cpu_has(X86_FEATURE_USE_IBRS_FW) ? "; IBRS_FW" : "", stibp_state(), - boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? ", RSB filling" : "", + boot_cpu_has(X86_FEATURE_RSB_CTXSW) ? "; RSB filling" : "", pbrsb_eibrs_state(), + spectre_bhi_state(), + /* this should always be at the end */ spectre_v2_module_string()); } diff --git a/arch/x86/kernel/cpu/common.c b/arch/x86/kernel/cpu/common.c index 5c1e6d6be267..605c26c009c8 100644 --- a/arch/x86/kernel/cpu/common.c +++ b/arch/x86/kernel/cpu/common.c @@ -1120,6 +1120,7 @@ static void identify_cpu_without_cpuid(struct cpuinfo_x86 *c) #define NO_SPECTRE_V2 BIT(8) #define NO_MMIO BIT(9) #define NO_EIBRS_PBRSB BIT(10) +#define NO_BHI BIT(11) #define VULNWL(vendor, family, model, whitelist) \ X86_MATCH_VENDOR_FAM_MODEL(vendor, family, model, whitelist) @@ -1182,18 +1183,18 @@ static const __initconst struct x86_cpu_id cpu_vuln_whitelist[] = { VULNWL_INTEL(ATOM_TREMONT_D, NO_ITLB_MULTIHIT | NO_EIBRS_PBRSB), /* AMD Family 0xf - 0x12 */ - VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), - VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO), + VULNWL_AMD(0x0f, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x10, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x11, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), + VULNWL_AMD(0x12, NO_MELTDOWN | NO_SSB | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_BHI), /* FAMILY_ANY must be last, otherwise 0x0f - 0x12 matches won't work */ - VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), - VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB), + VULNWL_AMD(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), + VULNWL_HYGON(X86_FAMILY_ANY, NO_MELTDOWN | NO_L1TF | NO_MDS | NO_SWAPGS | NO_ITLB_MULTIHIT | NO_MMIO | NO_EIBRS_PBRSB | NO_BHI), /* Zhaoxin Family 7 */ - VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), - VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO), + VULNWL(CENTAUR, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), + VULNWL(ZHAOXIN, 7, X86_MODEL_ANY, NO_SPECTRE_V2 | NO_SWAPGS | NO_MMIO | NO_BHI), {} }; @@ -1283,25 +1284,25 @@ static bool __init cpu_matches(const struct x86_cpu_id *table, unsigned long whi u64 x86_read_arch_cap_msr(void) { - u64 ia32_cap = 0; + u64 x86_arch_cap_msr = 0; if (boot_cpu_has(X86_FEATURE_ARCH_CAPABILITIES)) - rdmsrl(MSR_IA32_ARCH_CAPABILITIES, ia32_cap); + rdmsrl(MSR_IA32_ARCH_CAPABILITIES, x86_arch_cap_msr); - return ia32_cap; + return x86_arch_cap_msr; } -static bool arch_cap_mmio_immune(u64 ia32_cap) +static bool arch_cap_mmio_immune(u64 x86_arch_cap_msr) { - return (ia32_cap & ARCH_CAP_FBSDP_NO && - ia32_cap & ARCH_CAP_PSDP_NO && - ia32_cap & ARCH_CAP_SBDR_SSDP_NO); + return (x86_arch_cap_msr & ARCH_CAP_FBSDP_NO && + x86_arch_cap_msr & ARCH_CAP_PSDP_NO && + x86_arch_cap_msr & ARCH_CAP_SBDR_SSDP_NO); } -static bool __init vulnerable_to_rfds(u64 ia32_cap) +static bool __init vulnerable_to_rfds(u64 x86_arch_cap_msr) { /* The "immunity" bit trumps everything else: */ - if (ia32_cap & ARCH_CAP_RFDS_NO) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_NO) return false; /* @@ -1309,7 +1310,7 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap) * indicate that mitigation is needed because guest is running on a * vulnerable hardware or may migrate to such hardware: */ - if (ia32_cap & ARCH_CAP_RFDS_CLEAR) + if (x86_arch_cap_msr & ARCH_CAP_RFDS_CLEAR) return true; /* Only consult the blacklist when there is no enumeration: */ @@ -1318,11 +1319,11 @@ static bool __init vulnerable_to_rfds(u64 ia32_cap) static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) { - u64 ia32_cap = x86_read_arch_cap_msr(); + u64 x86_arch_cap_msr = x86_read_arch_cap_msr(); /* Set ITLB_MULTIHIT bug if cpu is not in the whitelist and not mitigated */ if (!cpu_matches(cpu_vuln_whitelist, NO_ITLB_MULTIHIT) && - !(ia32_cap & ARCH_CAP_PSCHANGE_MC_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PSCHANGE_MC_NO)) setup_force_cpu_bug(X86_BUG_ITLB_MULTIHIT); if (cpu_matches(cpu_vuln_whitelist, NO_SPECULATION)) @@ -1334,7 +1335,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) setup_force_cpu_bug(X86_BUG_SPECTRE_V2); if (!cpu_matches(cpu_vuln_whitelist, NO_SSB) && - !(ia32_cap & ARCH_CAP_SSB_NO) && + !(x86_arch_cap_msr & ARCH_CAP_SSB_NO) && !cpu_has(c, X86_FEATURE_AMD_SSB_NO)) setup_force_cpu_bug(X86_BUG_SPEC_STORE_BYPASS); @@ -1345,17 +1346,17 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Don't use AutoIBRS when SNP is enabled because it degrades host * userspace indirect branch performance. */ - if ((ia32_cap & ARCH_CAP_IBRS_ALL) || + if ((x86_arch_cap_msr & ARCH_CAP_IBRS_ALL) || (cpu_has(c, X86_FEATURE_AUTOIBRS) && !cpu_feature_enabled(X86_FEATURE_SEV_SNP))) { setup_force_cpu_cap(X86_FEATURE_IBRS_ENHANCED); if (!cpu_matches(cpu_vuln_whitelist, NO_EIBRS_PBRSB) && - !(ia32_cap & ARCH_CAP_PBRSB_NO)) + !(x86_arch_cap_msr & ARCH_CAP_PBRSB_NO)) setup_force_cpu_bug(X86_BUG_EIBRS_PBRSB); } if (!cpu_matches(cpu_vuln_whitelist, NO_MDS) && - !(ia32_cap & ARCH_CAP_MDS_NO)) { + !(x86_arch_cap_msr & ARCH_CAP_MDS_NO)) { setup_force_cpu_bug(X86_BUG_MDS); if (cpu_matches(cpu_vuln_whitelist, MSBDS_ONLY)) setup_force_cpu_bug(X86_BUG_MSBDS_ONLY); @@ -1374,9 +1375,9 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * TSX_CTRL check alone is not sufficient for cases when the microcode * update is not present or running as guest that don't get TSX_CTRL. */ - if (!(ia32_cap & ARCH_CAP_TAA_NO) && + if (!(x86_arch_cap_msr & ARCH_CAP_TAA_NO) && (cpu_has(c, X86_FEATURE_RTM) || - (ia32_cap & ARCH_CAP_TSX_CTRL_MSR))) + (x86_arch_cap_msr & ARCH_CAP_TSX_CTRL_MSR))) setup_force_cpu_bug(X86_BUG_TAA); /* @@ -1402,7 +1403,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * Set X86_BUG_MMIO_UNKNOWN for CPUs that are neither in the blacklist, * nor in the whitelist and also don't enumerate MSR ARCH_CAP MMIO bits. */ - if (!arch_cap_mmio_immune(ia32_cap)) { + if (!arch_cap_mmio_immune(x86_arch_cap_msr)) { if (cpu_matches(cpu_vuln_blacklist, MMIO)) setup_force_cpu_bug(X86_BUG_MMIO_STALE_DATA); else if (!cpu_matches(cpu_vuln_whitelist, NO_MMIO)) @@ -1410,7 +1411,7 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) } if (!cpu_has(c, X86_FEATURE_BTC_NO)) { - if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (ia32_cap & ARCH_CAP_RSBA)) + if (cpu_matches(cpu_vuln_blacklist, RETBLEED) || (x86_arch_cap_msr & ARCH_CAP_RSBA)) setup_force_cpu_bug(X86_BUG_RETBLEED); } @@ -1428,18 +1429,25 @@ static void __init cpu_set_bug_bits(struct cpuinfo_x86 *c) * disabling AVX2. The only way to do this in HW is to clear XCR0[2], * which means that AVX will be disabled. */ - if (cpu_matches(cpu_vuln_blacklist, GDS) && !(ia32_cap & ARCH_CAP_GDS_NO) && + if (cpu_matches(cpu_vuln_blacklist, GDS) && !(x86_arch_cap_msr & ARCH_CAP_GDS_NO) && boot_cpu_has(X86_FEATURE_AVX)) setup_force_cpu_bug(X86_BUG_GDS); - if (vulnerable_to_rfds(ia32_cap)) + if (vulnerable_to_rfds(x86_arch_cap_msr)) setup_force_cpu_bug(X86_BUG_RFDS); + /* When virtualized, eIBRS could be hidden, assume vulnerable */ + if (!(x86_arch_cap_msr & ARCH_CAP_BHI_NO) && + !cpu_matches(cpu_vuln_whitelist, NO_BHI) && + (boot_cpu_has(X86_FEATURE_IBRS_ENHANCED) || + boot_cpu_has(X86_FEATURE_HYPERVISOR))) + setup_force_cpu_bug(X86_BUG_BHI); + if (cpu_matches(cpu_vuln_whitelist, NO_MELTDOWN)) return; /* Rogue Data Cache Load? No! */ - if (ia32_cap & ARCH_CAP_RDCL_NO) + if (x86_arch_cap_msr & ARCH_CAP_RDCL_NO) return; setup_force_cpu_bug(X86_BUG_CPU_MELTDOWN); diff --git a/arch/x86/kernel/cpu/cpuid-deps.c b/arch/x86/kernel/cpu/cpuid-deps.c index b7174209d855..946813d816bf 100644 --- a/arch/x86/kernel/cpu/cpuid-deps.c +++ b/arch/x86/kernel/cpu/cpuid-deps.c @@ -44,7 +44,10 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_F16C, X86_FEATURE_XMM2, }, { X86_FEATURE_AES, X86_FEATURE_XMM2 }, { X86_FEATURE_SHA_NI, X86_FEATURE_XMM2 }, + { X86_FEATURE_GFNI, X86_FEATURE_XMM2 }, { X86_FEATURE_FMA, X86_FEATURE_AVX }, + { X86_FEATURE_VAES, X86_FEATURE_AVX }, + { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX }, { X86_FEATURE_AVX2, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512F, X86_FEATURE_AVX, }, { X86_FEATURE_AVX512IFMA, X86_FEATURE_AVX512F }, @@ -56,9 +59,6 @@ static const struct cpuid_dep cpuid_deps[] = { { X86_FEATURE_AVX512VL, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512VBMI, X86_FEATURE_AVX512F }, { X86_FEATURE_AVX512_VBMI2, X86_FEATURE_AVX512VL }, - { X86_FEATURE_GFNI, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VAES, X86_FEATURE_AVX512VL }, - { X86_FEATURE_VPCLMULQDQ, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_VNNI, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_BITALG, X86_FEATURE_AVX512VL }, { X86_FEATURE_AVX512_4VNNIW, X86_FEATURE_AVX512F }, diff --git a/arch/x86/kernel/cpu/scattered.c b/arch/x86/kernel/cpu/scattered.c index a515328d9d7d..af5aa2c754c2 100644 --- a/arch/x86/kernel/cpu/scattered.c +++ b/arch/x86/kernel/cpu/scattered.c @@ -28,6 +28,7 @@ static const struct cpuid_bit cpuid_bits[] = { { X86_FEATURE_EPB, CPUID_ECX, 3, 0x00000006, 0 }, { X86_FEATURE_INTEL_PPIN, CPUID_EBX, 0, 0x00000007, 1 }, { X86_FEATURE_RRSBA_CTRL, CPUID_EDX, 2, 0x00000007, 2 }, + { X86_FEATURE_BHI_CTRL, CPUID_EDX, 4, 0x00000007, 2 }, { X86_FEATURE_CQM_LLC, CPUID_EDX, 1, 0x0000000f, 0 }, { X86_FEATURE_CQM_OCCUP_LLC, CPUID_EDX, 0, 0x0000000f, 1 }, { X86_FEATURE_CQM_MBM_TOTAL, CPUID_EDX, 1, 0x0000000f, 1 }, diff --git a/arch/x86/kernel/cpu/topology.c b/arch/x86/kernel/cpu/topology.c index aaca8d235dc2..d17c9b71eb4a 100644 --- a/arch/x86/kernel/cpu/topology.c +++ b/arch/x86/kernel/cpu/topology.c @@ -123,7 +123,6 @@ static void topo_set_cpuids(unsigned int cpu, u32 apic_id, u32 acpi_id) early_per_cpu(x86_cpu_to_apicid, cpu) = apic_id; early_per_cpu(x86_cpu_to_acpiid, cpu) = acpi_id; #endif - set_cpu_possible(cpu, true); set_cpu_present(cpu, true); } @@ -210,7 +209,11 @@ static __init void topo_register_apic(u32 apic_id, u32 acpi_id, bool present) topo_info.nr_disabled_cpus++; } - /* Register present and possible CPUs in the domain maps */ + /* + * Register present and possible CPUs in the domain + * maps. cpu_possible_map will be updated in + * topology_init_possible_cpus() after enumeration is done. + */ for (dom = TOPO_SMT_DOMAIN; dom < TOPO_MAX_DOMAIN; dom++) set_bit(topo_apicid(apic_id, dom), apic_maps[dom].map); } diff --git a/arch/x86/kernel/cpu/topology_amd.c b/arch/x86/kernel/cpu/topology_amd.c index 1a8b3ad493af..ce2d507c3b07 100644 --- a/arch/x86/kernel/cpu/topology_amd.c +++ b/arch/x86/kernel/cpu/topology_amd.c @@ -29,11 +29,21 @@ static bool parse_8000_0008(struct topo_scan *tscan) if (!sft) sft = get_count_order(ecx.cpu_nthreads + 1); - topology_set_dom(tscan, TOPO_SMT_DOMAIN, sft, ecx.cpu_nthreads + 1); + /* + * cpu_nthreads describes the number of threads in the package + * sft is the number of APIC ID bits per package + * + * As the number of actual threads per core is not described in + * this leaf, just set the CORE domain shift and let the later + * parsers set SMT shift. Assume one thread per core by default + * which is correct if there are no other CPUID leafs to parse. + */ + topology_update_dom(tscan, TOPO_SMT_DOMAIN, 0, 1); + topology_set_dom(tscan, TOPO_CORE_DOMAIN, sft, ecx.cpu_nthreads + 1); return true; } -static void store_node(struct topo_scan *tscan, unsigned int nr_nodes, u16 node_id) +static void store_node(struct topo_scan *tscan, u16 nr_nodes, u16 node_id) { /* * Starting with Fam 17h the DIE domain could probably be used to @@ -73,12 +83,14 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb) tscan->c->topo.initial_apicid = leaf.ext_apic_id; /* - * If leaf 0xb is available, then SMT shift is set already. If not - * take it from ecx.threads_per_core and use topo_update_dom() - - * topology_set_dom() would propagate and overwrite the already - * propagated CORE level. + * If leaf 0xb is available, then the domain shifts are set + * already and nothing to do here. */ if (!has_0xb) { + /* + * Leaf 0x80000008 set the CORE domain shift already. + * Update the SMT domain, but do not propagate it. + */ unsigned int nthreads = leaf.core_nthreads + 1; topology_update_dom(tscan, TOPO_SMT_DOMAIN, get_count_order(nthreads), nthreads); @@ -107,32 +119,52 @@ static bool parse_8000_001e(struct topo_scan *tscan, bool has_0xb) return true; } -static bool parse_fam10h_node_id(struct topo_scan *tscan) +static void parse_fam10h_node_id(struct topo_scan *tscan) { - struct { - union { + union { + struct { u64 node_id : 3, nodes_per_pkg : 3, unused : 58; - u64 msr; }; + u64 msr; } nid; if (!boot_cpu_has(X86_FEATURE_NODEID_MSR)) - return false; + return; rdmsrl(MSR_FAM10H_NODE_ID, nid.msr); store_node(tscan, nid.nodes_per_pkg + 1, nid.node_id); tscan->c->topo.llc_id = nid.node_id; - return true; } static void legacy_set_llc(struct topo_scan *tscan) { unsigned int apicid = tscan->c->topo.initial_apicid; - /* parse_8000_0008() set everything up except llc_id */ - tscan->c->topo.llc_id = apicid >> tscan->dom_shifts[TOPO_CORE_DOMAIN]; + /* If none of the parsers set LLC ID then use the die ID for it. */ + if (tscan->c->topo.llc_id == BAD_APICID) + tscan->c->topo.llc_id = apicid >> tscan->dom_shifts[TOPO_CORE_DOMAIN]; +} + +static void topoext_fixup(struct topo_scan *tscan) +{ + struct cpuinfo_x86 *c = tscan->c; + u64 msrval; + + /* Try to re-enable TopologyExtensions if switched off by BIOS */ + if (cpu_has(c, X86_FEATURE_TOPOEXT) || c->x86_vendor != X86_VENDOR_AMD || + c->x86 != 0x15 || c->x86_model < 0x10 || c->x86_model > 0x6f) + return; + + if (msr_set_bit(0xc0011005, 54) <= 0) + return; + + rdmsrl(0xc0011005, msrval); + if (msrval & BIT_64(54)) { + set_cpu_cap(c, X86_FEATURE_TOPOEXT); + pr_info_once(FW_INFO "CPU: Re-enabling disabled Topology Extensions Support.\n"); + } } static void parse_topology_amd(struct topo_scan *tscan) @@ -155,16 +187,15 @@ static void parse_topology_amd(struct topo_scan *tscan) return; /* Try the NODEID MSR */ - if (parse_fam10h_node_id(tscan)) - return; - - legacy_set_llc(tscan); + parse_fam10h_node_id(tscan); } void cpu_parse_topology_amd(struct topo_scan *tscan) { tscan->amd_nodes_per_pkg = 1; + topoext_fixup(tscan); parse_topology_amd(tscan); + legacy_set_llc(tscan); if (tscan->amd_nodes_per_pkg > 1) set_cpu_cap(tscan->c, X86_FEATURE_AMD_DCM); diff --git a/arch/x86/kernel/e820.c b/arch/x86/kernel/e820.c index 6f1b379e3b38..68b09f718f10 100644 --- a/arch/x86/kernel/e820.c +++ b/arch/x86/kernel/e820.c @@ -532,9 +532,10 @@ u64 __init e820__range_update(u64 start, u64 size, enum e820_type old_type, enum return __e820__range_update(e820_table, start, size, old_type, new_type); } -static u64 __init e820__range_update_kexec(u64 start, u64 size, enum e820_type old_type, enum e820_type new_type) +u64 __init e820__range_update_table(struct e820_table *t, u64 start, u64 size, + enum e820_type old_type, enum e820_type new_type) { - return __e820__range_update(e820_table_kexec, start, size, old_type, new_type); + return __e820__range_update(t, start, size, old_type, new_type); } /* Remove a range of memory from the E820 table: */ @@ -806,7 +807,7 @@ u64 __init e820__memblock_alloc_reserved(u64 size, u64 align) addr = memblock_phys_alloc(size, align); if (addr) { - e820__range_update_kexec(addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_kexec, addr, size, E820_TYPE_RAM, E820_TYPE_RESERVED); pr_info("update e820_table_kexec for e820__memblock_alloc_reserved()\n"); e820__update_table_kexec(); } diff --git a/arch/x86/kernel/process_64.c b/arch/x86/kernel/process_64.c index 7062b84dd467..6d3d20e3e43a 100644 --- a/arch/x86/kernel/process_64.c +++ b/arch/x86/kernel/process_64.c @@ -139,7 +139,7 @@ void __show_regs(struct pt_regs *regs, enum show_regs_mode mode, log_lvl, d3, d6, d7); } - if (cpu_feature_enabled(X86_FEATURE_OSPKE)) + if (cr4 & X86_CR4_PKE) printk("%sPKRU: %08x\n", log_lvl, read_pkru()); } diff --git a/arch/x86/kernel/sev-shared.c b/arch/x86/kernel/sev-shared.c index 8b04958da5e7..b4f8fa0f722c 100644 --- a/arch/x86/kernel/sev-shared.c +++ b/arch/x86/kernel/sev-shared.c @@ -1203,12 +1203,14 @@ static enum es_result vc_check_opcode_bytes(struct es_em_ctxt *ctxt, break; case SVM_EXIT_MONITOR: - if (opcode == 0x010f && modrm == 0xc8) + /* MONITOR and MONITORX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc8 || modrm == 0xfa)) return ES_OK; break; case SVM_EXIT_MWAIT: - if (opcode == 0x010f && modrm == 0xc9) + /* MWAIT and MWAITX instructions generate the same error code */ + if (opcode == 0x010f && (modrm == 0xc9 || modrm == 0xfb)) return ES_OK; break; diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index a88bb14266b6..addc44fc7187 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -3,11 +3,6 @@ ccflags-y += -I $(srctree)/arch/x86/kvm ccflags-$(CONFIG_KVM_WERROR) += -Werror -ifeq ($(CONFIG_FRAME_POINTER),y) -OBJECT_FILES_NON_STANDARD_vmx/vmenter.o := y -OBJECT_FILES_NON_STANDARD_svm/vmenter.o := y -endif - include $(srctree)/virt/kvm/Makefile.kvm kvm-y += x86.o emulate.o i8259.o irq.o lapic.o \ diff --git a/arch/x86/kvm/cpuid.c b/arch/x86/kvm/cpuid.c index bfc0bfcb2bc6..77352a4abd87 100644 --- a/arch/x86/kvm/cpuid.c +++ b/arch/x86/kvm/cpuid.c @@ -376,6 +376,7 @@ static void kvm_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) kvm_update_pv_runtime(vcpu); + vcpu->arch.is_amd_compatible = guest_cpuid_is_amd_or_hygon(vcpu); vcpu->arch.maxphyaddr = cpuid_query_maxphyaddr(vcpu); vcpu->arch.reserved_gpa_bits = kvm_vcpu_reserved_gpa_bits_raw(vcpu); diff --git a/arch/x86/kvm/cpuid.h b/arch/x86/kvm/cpuid.h index 856e3037e74f..23dbb9eb277c 100644 --- a/arch/x86/kvm/cpuid.h +++ b/arch/x86/kvm/cpuid.h @@ -120,6 +120,16 @@ static inline bool guest_cpuid_is_intel(struct kvm_vcpu *vcpu) return best && is_guest_vendor_intel(best->ebx, best->ecx, best->edx); } +static inline bool guest_cpuid_is_amd_compatible(struct kvm_vcpu *vcpu) +{ + return vcpu->arch.is_amd_compatible; +} + +static inline bool guest_cpuid_is_intel_compatible(struct kvm_vcpu *vcpu) +{ + return !guest_cpuid_is_amd_compatible(vcpu); +} + static inline int guest_cpuid_family(struct kvm_vcpu *vcpu) { struct kvm_cpuid_entry2 *best; diff --git a/arch/x86/kvm/lapic.c b/arch/x86/kvm/lapic.c index cf37586f0466..ebf41023be38 100644 --- a/arch/x86/kvm/lapic.c +++ b/arch/x86/kvm/lapic.c @@ -2776,7 +2776,8 @@ int kvm_apic_local_deliver(struct kvm_lapic *apic, int lvt_type) trig_mode = reg & APIC_LVT_LEVEL_TRIGGER; r = __apic_accept_irq(apic, mode, vector, 1, trig_mode, NULL); - if (r && lvt_type == APIC_LVTPC) + if (r && lvt_type == APIC_LVTPC && + guest_cpuid_is_intel_compatible(apic->vcpu)) kvm_lapic_set_reg(apic, APIC_LVTPC, reg | APIC_LVT_MASKED); return r; } diff --git a/arch/x86/kvm/mmu/mmu.c b/arch/x86/kvm/mmu/mmu.c index 992e651540e8..db007a4dffa2 100644 --- a/arch/x86/kvm/mmu/mmu.c +++ b/arch/x86/kvm/mmu/mmu.c @@ -4935,7 +4935,7 @@ static void reset_guest_rsvds_bits_mask(struct kvm_vcpu *vcpu, context->cpu_role.base.level, is_efer_nx(context), guest_can_use(vcpu, X86_FEATURE_GBPAGES), is_cr4_pse(context), - guest_cpuid_is_amd_or_hygon(vcpu)); + guest_cpuid_is_amd_compatible(vcpu)); } static void __reset_rsvds_bits_mask_ept(struct rsvd_bits_validate *rsvd_check, @@ -5576,9 +5576,9 @@ void kvm_mmu_after_set_cpuid(struct kvm_vcpu *vcpu) * that problem is swept under the rug; KVM's CPUID API is horrific and * it's all but impossible to solve it without introducing a new API. */ - vcpu->arch.root_mmu.root_role.word = 0; - vcpu->arch.guest_mmu.root_role.word = 0; - vcpu->arch.nested_mmu.root_role.word = 0; + vcpu->arch.root_mmu.root_role.invalid = 1; + vcpu->arch.guest_mmu.root_role.invalid = 1; + vcpu->arch.nested_mmu.root_role.invalid = 1; vcpu->arch.root_mmu.cpu_role.ext.valid = 0; vcpu->arch.guest_mmu.cpu_role.ext.valid = 0; vcpu->arch.nested_mmu.cpu_role.ext.valid = 0; @@ -7399,7 +7399,8 @@ bool kvm_arch_post_set_memory_attributes(struct kvm *kvm, * by the memslot, KVM can't use a hugepage due to the * misaligned address regardless of memory attributes. */ - if (gfn >= slot->base_gfn) { + if (gfn >= slot->base_gfn && + gfn + nr_pages <= slot->base_gfn + slot->npages) { if (hugepage_has_attrs(kvm, slot, gfn, level, attrs)) hugepage_clear_mixed(slot, gfn, level); else diff --git a/arch/x86/kvm/mmu/tdp_mmu.c b/arch/x86/kvm/mmu/tdp_mmu.c index d078157e62aa..04c1f0957fea 100644 --- a/arch/x86/kvm/mmu/tdp_mmu.c +++ b/arch/x86/kvm/mmu/tdp_mmu.c @@ -1548,17 +1548,21 @@ void kvm_tdp_mmu_try_split_huge_pages(struct kvm *kvm, } } -/* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. - */ +static bool tdp_mmu_need_write_protect(struct kvm_mmu_page *sp) +{ + /* + * All TDP MMU shadow pages share the same role as their root, aside + * from level, so it is valid to key off any shadow page to determine if + * write protection is needed for an entire tree. + */ + return kvm_mmu_page_ad_need_write_protect(sp) || !kvm_ad_enabled(); +} + static bool clear_dirty_gfn_range(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t start, gfn_t end) { - u64 dbit = kvm_ad_enabled() ? shadow_dirty_mask : PT_WRITABLE_MASK; + const u64 dbit = tdp_mmu_need_write_protect(root) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; bool spte_set = false; @@ -1573,7 +1577,7 @@ retry: if (tdp_mmu_iter_cond_resched(kvm, &iter, false, true)) continue; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (!(iter.old_spte & dbit)) @@ -1590,11 +1594,9 @@ retry: } /* - * Clear the dirty status of all the SPTEs mapping GFNs in the memslot. If - * AD bits are enabled, this will involve clearing the dirty bit on each SPTE. - * If AD bits are not enabled, this will require clearing the writable bit on - * each SPTE. Returns true if an SPTE has been changed and the TLBs need to - * be flushed. + * Clear the dirty status (D-bit or W-bit) of all the SPTEs mapping GFNs in the + * memslot. Returns true if an SPTE has been changed and the TLBs need to be + * flushed. */ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, const struct kvm_memory_slot *slot) @@ -1610,18 +1612,11 @@ bool kvm_tdp_mmu_clear_dirty_slot(struct kvm *kvm, return spte_set; } -/* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. - */ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, gfn_t gfn, unsigned long mask, bool wrprot) { - u64 dbit = (wrprot || !kvm_ad_enabled()) ? PT_WRITABLE_MASK : - shadow_dirty_mask; + const u64 dbit = (wrprot || tdp_mmu_need_write_protect(root)) ? PT_WRITABLE_MASK : + shadow_dirty_mask; struct tdp_iter iter; lockdep_assert_held_write(&kvm->mmu_lock); @@ -1633,7 +1628,7 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, if (!mask) break; - KVM_MMU_WARN_ON(kvm_ad_enabled() && + KVM_MMU_WARN_ON(dbit == shadow_dirty_mask && spte_ad_need_write_protect(iter.old_spte)); if (iter.level > PG_LEVEL_4K || @@ -1659,11 +1654,9 @@ static void clear_dirty_pt_masked(struct kvm *kvm, struct kvm_mmu_page *root, } /* - * Clears the dirty status of all the 4k SPTEs mapping GFNs for which a bit is - * set in mask, starting at gfn. The given memslot is expected to contain all - * the GFNs represented by set bits in the mask. If AD bits are enabled, - * clearing the dirty status will involve clearing the dirty bit on each SPTE - * or, if AD bits are not enabled, clearing the writable bit on each SPTE. + * Clear the dirty status (D-bit or W-bit) of all the 4k SPTEs mapping GFNs for + * which a bit is set in mask, starting at gfn. The given memslot is expected to + * contain all the GFNs represented by set bits in the mask. */ void kvm_tdp_mmu_clear_dirty_pt_masked(struct kvm *kvm, struct kvm_memory_slot *slot, diff --git a/arch/x86/kvm/pmu.c b/arch/x86/kvm/pmu.c index c397b28e3d1b..a593b03c9aed 100644 --- a/arch/x86/kvm/pmu.c +++ b/arch/x86/kvm/pmu.c @@ -775,8 +775,20 @@ void kvm_pmu_refresh(struct kvm_vcpu *vcpu) pmu->pebs_data_cfg_mask = ~0ull; bitmap_zero(pmu->all_valid_pmc_idx, X86_PMC_IDX_MAX); - if (vcpu->kvm->arch.enable_pmu) - static_call(kvm_x86_pmu_refresh)(vcpu); + if (!vcpu->kvm->arch.enable_pmu) + return; + + static_call(kvm_x86_pmu_refresh)(vcpu); + + /* + * At RESET, both Intel and AMD CPUs set all enable bits for general + * purpose counters in IA32_PERF_GLOBAL_CTRL (so that software that + * was written for v1 PMUs don't unknowingly leave GP counters disabled + * in the global controls). Emulate that behavior when refreshing the + * PMU so that userspace doesn't need to manually set PERF_GLOBAL_CTRL. + */ + if (kvm_pmu_has_perf_global_ctrl(pmu) && pmu->nr_arch_gp_counters) + pmu->global_ctrl = GENMASK_ULL(pmu->nr_arch_gp_counters - 1, 0); } void kvm_pmu_init(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/reverse_cpuid.h b/arch/x86/kvm/reverse_cpuid.h index 58ac8d69c94b..2f4e155080ba 100644 --- a/arch/x86/kvm/reverse_cpuid.h +++ b/arch/x86/kvm/reverse_cpuid.h @@ -52,7 +52,7 @@ enum kvm_only_cpuid_leafs { #define X86_FEATURE_IPRED_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 1) #define KVM_X86_FEATURE_RRSBA_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 2) #define X86_FEATURE_DDPD_U KVM_X86_FEATURE(CPUID_7_2_EDX, 3) -#define X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) +#define KVM_X86_FEATURE_BHI_CTRL KVM_X86_FEATURE(CPUID_7_2_EDX, 4) #define X86_FEATURE_MCDT_NO KVM_X86_FEATURE(CPUID_7_2_EDX, 5) /* CPUID level 0x80000007 (EDX). */ @@ -128,6 +128,7 @@ static __always_inline u32 __feature_translate(int x86_feature) KVM_X86_TRANSLATE_FEATURE(CONSTANT_TSC); KVM_X86_TRANSLATE_FEATURE(PERFMON_V2); KVM_X86_TRANSLATE_FEATURE(RRSBA_CTRL); + KVM_X86_TRANSLATE_FEATURE(BHI_CTRL); default: return x86_feature; } diff --git a/arch/x86/kvm/svm/sev.c b/arch/x86/kvm/svm/sev.c index 61a7531d41b0..759581bb2128 100644 --- a/arch/x86/kvm/svm/sev.c +++ b/arch/x86/kvm/svm/sev.c @@ -434,7 +434,7 @@ static struct page **sev_pin_memory(struct kvm *kvm, unsigned long uaddr, /* Avoid using vmalloc for smaller buffers. */ size = npages * sizeof(struct page *); if (size > PAGE_SIZE) - pages = __vmalloc(size, GFP_KERNEL_ACCOUNT | __GFP_ZERO); + pages = __vmalloc(size, GFP_KERNEL_ACCOUNT); else pages = kmalloc(size, GFP_KERNEL_ACCOUNT); diff --git a/arch/x86/kvm/svm/svm.c b/arch/x86/kvm/svm/svm.c index d1a9f9951635..9aaf83c8d57d 100644 --- a/arch/x86/kvm/svm/svm.c +++ b/arch/x86/kvm/svm/svm.c @@ -1503,6 +1503,11 @@ static void svm_vcpu_free(struct kvm_vcpu *vcpu) __free_pages(virt_to_page(svm->msrpm), get_order(MSRPM_SIZE)); } +static struct sev_es_save_area *sev_es_host_save_area(struct svm_cpu_data *sd) +{ + return page_address(sd->save_area) + 0x400; +} + static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) { struct vcpu_svm *svm = to_svm(vcpu); @@ -1519,12 +1524,8 @@ static void svm_prepare_switch_to_guest(struct kvm_vcpu *vcpu) * or subsequent vmload of host save area. */ vmsave(sd->save_area_pa); - if (sev_es_guest(vcpu->kvm)) { - struct sev_es_save_area *hostsa; - hostsa = (struct sev_es_save_area *)(page_address(sd->save_area) + 0x400); - - sev_es_prepare_switch_to_guest(hostsa); - } + if (sev_es_guest(vcpu->kvm)) + sev_es_prepare_switch_to_guest(sev_es_host_save_area(sd)); if (tsc_scaling) __svm_write_tsc_multiplier(vcpu->arch.tsc_scaling_ratio); @@ -4101,6 +4102,7 @@ static fastpath_t svm_exit_handlers_fastpath(struct kvm_vcpu *vcpu) static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_intercepted) { + struct svm_cpu_data *sd = per_cpu_ptr(&svm_data, vcpu->cpu); struct vcpu_svm *svm = to_svm(vcpu); guest_state_enter_irqoff(); @@ -4108,7 +4110,8 @@ static noinstr void svm_vcpu_enter_exit(struct kvm_vcpu *vcpu, bool spec_ctrl_in amd_clear_divider(); if (sev_es_guest(vcpu->kvm)) - __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted); + __svm_sev_es_vcpu_run(svm, spec_ctrl_intercepted, + sev_es_host_save_area(sd)); else __svm_vcpu_run(svm, spec_ctrl_intercepted); diff --git a/arch/x86/kvm/svm/svm.h b/arch/x86/kvm/svm/svm.h index 7f1fbd874c45..33878efdebc8 100644 --- a/arch/x86/kvm/svm/svm.h +++ b/arch/x86/kvm/svm/svm.h @@ -698,7 +698,8 @@ struct page *snp_safe_alloc_page(struct kvm_vcpu *vcpu); /* vmenter.S */ -void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); +void __svm_sev_es_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted, + struct sev_es_save_area *hostsa); void __svm_vcpu_run(struct vcpu_svm *svm, bool spec_ctrl_intercepted); #define DEFINE_KVM_GHCB_ACCESSORS(field) \ diff --git a/arch/x86/kvm/svm/vmenter.S b/arch/x86/kvm/svm/vmenter.S index 187018c424bf..a0c8eb37d3e1 100644 --- a/arch/x86/kvm/svm/vmenter.S +++ b/arch/x86/kvm/svm/vmenter.S @@ -3,6 +3,7 @@ #include <asm/asm.h> #include <asm/asm-offsets.h> #include <asm/bitsperlong.h> +#include <asm/frame.h> #include <asm/kvm_vcpu_regs.h> #include <asm/nospec-branch.h> #include "kvm-asm-offsets.h" @@ -67,7 +68,7 @@ "", X86_FEATURE_V_SPEC_CTRL 901: .endm -.macro RESTORE_HOST_SPEC_CTRL_BODY +.macro RESTORE_HOST_SPEC_CTRL_BODY spec_ctrl_intercepted:req 900: /* Same for after vmexit. */ mov $MSR_IA32_SPEC_CTRL, %ecx @@ -76,7 +77,7 @@ * Load the value that the guest had written into MSR_IA32_SPEC_CTRL, * if it was not intercepted during guest execution. */ - cmpb $0, (%_ASM_SP) + cmpb $0, \spec_ctrl_intercepted jnz 998f rdmsr movl %eax, SVM_spec_ctrl(%_ASM_DI) @@ -99,6 +100,7 @@ */ SYM_FUNC_START(__svm_vcpu_run) push %_ASM_BP + mov %_ASM_SP, %_ASM_BP #ifdef CONFIG_X86_64 push %r15 push %r14 @@ -268,7 +270,7 @@ SYM_FUNC_START(__svm_vcpu_run) RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY (%_ASM_SP) 10: cmpb $0, _ASM_RIP(kvm_rebooting) jne 2b @@ -290,66 +292,68 @@ SYM_FUNC_START(__svm_vcpu_run) SYM_FUNC_END(__svm_vcpu_run) +#ifdef CONFIG_KVM_AMD_SEV + + +#ifdef CONFIG_X86_64 +#define SEV_ES_GPRS_BASE 0x300 +#define SEV_ES_RBX (SEV_ES_GPRS_BASE + __VCPU_REGS_RBX * WORD_SIZE) +#define SEV_ES_RBP (SEV_ES_GPRS_BASE + __VCPU_REGS_RBP * WORD_SIZE) +#define SEV_ES_RSI (SEV_ES_GPRS_BASE + __VCPU_REGS_RSI * WORD_SIZE) +#define SEV_ES_RDI (SEV_ES_GPRS_BASE + __VCPU_REGS_RDI * WORD_SIZE) +#define SEV_ES_R12 (SEV_ES_GPRS_BASE + __VCPU_REGS_R12 * WORD_SIZE) +#define SEV_ES_R13 (SEV_ES_GPRS_BASE + __VCPU_REGS_R13 * WORD_SIZE) +#define SEV_ES_R14 (SEV_ES_GPRS_BASE + __VCPU_REGS_R14 * WORD_SIZE) +#define SEV_ES_R15 (SEV_ES_GPRS_BASE + __VCPU_REGS_R15 * WORD_SIZE) +#endif + /** * __svm_sev_es_vcpu_run - Run a SEV-ES vCPU via a transition to SVM guest mode * @svm: struct vcpu_svm * * @spec_ctrl_intercepted: bool */ SYM_FUNC_START(__svm_sev_es_vcpu_run) - push %_ASM_BP -#ifdef CONFIG_X86_64 - push %r15 - push %r14 - push %r13 - push %r12 -#else - push %edi - push %esi -#endif - push %_ASM_BX + FRAME_BEGIN /* - * Save variables needed after vmexit on the stack, in inverse - * order compared to when they are needed. + * Save non-volatile (callee-saved) registers to the host save area. + * Except for RAX and RSP, all GPRs are restored on #VMEXIT, but not + * saved on VMRUN. */ + mov %rbp, SEV_ES_RBP (%rdx) + mov %r15, SEV_ES_R15 (%rdx) + mov %r14, SEV_ES_R14 (%rdx) + mov %r13, SEV_ES_R13 (%rdx) + mov %r12, SEV_ES_R12 (%rdx) + mov %rbx, SEV_ES_RBX (%rdx) - /* Accessed directly from the stack in RESTORE_HOST_SPEC_CTRL. */ - push %_ASM_ARG2 - - /* Save @svm. */ - push %_ASM_ARG1 - -.ifnc _ASM_ARG1, _ASM_DI /* - * Stash @svm in RDI early. On 32-bit, arguments are in RAX, RCX - * and RDX which are clobbered by RESTORE_GUEST_SPEC_CTRL. + * Save volatile registers that hold arguments that are needed after + * #VMEXIT (RDI=@svm and RSI=@spec_ctrl_intercepted). */ - mov %_ASM_ARG1, %_ASM_DI -.endif + mov %rdi, SEV_ES_RDI (%rdx) + mov %rsi, SEV_ES_RSI (%rdx) - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX (@hostsa). */ RESTORE_GUEST_SPEC_CTRL /* Get svm->current_vmcb->pa into RAX. */ - mov SVM_current_vmcb(%_ASM_DI), %_ASM_AX - mov KVM_VMCB_pa(%_ASM_AX), %_ASM_AX + mov SVM_current_vmcb(%rdi), %rax + mov KVM_VMCB_pa(%rax), %rax /* Enter guest mode */ sti -1: vmrun %_ASM_AX +1: vmrun %rax 2: cli - /* Pop @svm to RDI, guest registers have been saved already. */ - pop %_ASM_DI - #ifdef CONFIG_MITIGATION_RETPOLINE /* IMPORTANT: Stuff the RSB immediately after VM-Exit, before RET! */ - FILL_RETURN_BUFFER %_ASM_AX, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE + FILL_RETURN_BUFFER %rax, RSB_CLEAR_LOOPS, X86_FEATURE_RETPOLINE #endif - /* Clobbers RAX, RCX, RDX. */ + /* Clobbers RAX, RCX, RDX, consumes RDI (@svm) and RSI (@spec_ctrl_intercepted). */ RESTORE_HOST_SPEC_CTRL /* @@ -361,30 +365,17 @@ SYM_FUNC_START(__svm_sev_es_vcpu_run) */ UNTRAIN_RET_VM - /* "Pop" @spec_ctrl_intercepted. */ - pop %_ASM_BX - - pop %_ASM_BX - -#ifdef CONFIG_X86_64 - pop %r12 - pop %r13 - pop %r14 - pop %r15 -#else - pop %esi - pop %edi -#endif - pop %_ASM_BP + FRAME_END RET RESTORE_GUEST_SPEC_CTRL_BODY - RESTORE_HOST_SPEC_CTRL_BODY + RESTORE_HOST_SPEC_CTRL_BODY %sil -3: cmpb $0, _ASM_RIP(kvm_rebooting) +3: cmpb $0, kvm_rebooting(%rip) jne 2b ud2 _ASM_EXTABLE(1b, 3b) SYM_FUNC_END(__svm_sev_es_vcpu_run) +#endif /* CONFIG_KVM_AMD_SEV */ diff --git a/arch/x86/kvm/vmx/pmu_intel.c b/arch/x86/kvm/vmx/pmu_intel.c index 12ade343a17e..be40474de6e4 100644 --- a/arch/x86/kvm/vmx/pmu_intel.c +++ b/arch/x86/kvm/vmx/pmu_intel.c @@ -535,7 +535,7 @@ static void intel_pmu_refresh(struct kvm_vcpu *vcpu) perf_capabilities = vcpu_get_perf_capabilities(vcpu); if (cpuid_model_is_consistent(vcpu) && (perf_capabilities & PMU_CAP_LBR_FMT)) - x86_perf_get_lbr(&lbr_desc->records); + memcpy(&lbr_desc->records, &vmx_lbr_caps, sizeof(vmx_lbr_caps)); else lbr_desc->records.nr = 0; diff --git a/arch/x86/kvm/vmx/vmenter.S b/arch/x86/kvm/vmx/vmenter.S index 2bfbf758d061..f6986dee6f8c 100644 --- a/arch/x86/kvm/vmx/vmenter.S +++ b/arch/x86/kvm/vmx/vmenter.S @@ -275,6 +275,8 @@ SYM_INNER_LABEL_ALIGN(vmx_vmexit, SYM_L_GLOBAL) call vmx_spec_ctrl_restore_host + CLEAR_BRANCH_HISTORY_VMEXIT + /* Put return value in AX */ mov %_ASM_BX, %_ASM_AX diff --git a/arch/x86/kvm/vmx/vmx.c b/arch/x86/kvm/vmx/vmx.c index c37a89eda90f..22411f4aff53 100644 --- a/arch/x86/kvm/vmx/vmx.c +++ b/arch/x86/kvm/vmx/vmx.c @@ -218,6 +218,8 @@ module_param(ple_window_max, uint, 0444); int __read_mostly pt_mode = PT_MODE_SYSTEM; module_param(pt_mode, int, S_IRUGO); +struct x86_pmu_lbr __ro_after_init vmx_lbr_caps; + static DEFINE_STATIC_KEY_FALSE(vmx_l1d_should_flush); static DEFINE_STATIC_KEY_FALSE(vmx_l1d_flush_cond); static DEFINE_MUTEX(vmx_l1d_flush_mutex); @@ -7862,10 +7864,9 @@ static void vmx_vcpu_after_set_cpuid(struct kvm_vcpu *vcpu) vmx_update_exception_bitmap(vcpu); } -static u64 vmx_get_perf_capabilities(void) +static __init u64 vmx_get_perf_capabilities(void) { u64 perf_cap = PMU_CAP_FW_WRITES; - struct x86_pmu_lbr lbr; u64 host_perf_cap = 0; if (!enable_pmu) @@ -7875,15 +7876,43 @@ static u64 vmx_get_perf_capabilities(void) rdmsrl(MSR_IA32_PERF_CAPABILITIES, host_perf_cap); if (!cpu_feature_enabled(X86_FEATURE_ARCH_LBR)) { - x86_perf_get_lbr(&lbr); - if (lbr.nr) + x86_perf_get_lbr(&vmx_lbr_caps); + + /* + * KVM requires LBR callstack support, as the overhead due to + * context switching LBRs without said support is too high. + * See intel_pmu_create_guest_lbr_event() for more info. + */ + if (!vmx_lbr_caps.has_callstack) + memset(&vmx_lbr_caps, 0, sizeof(vmx_lbr_caps)); + else if (vmx_lbr_caps.nr) perf_cap |= host_perf_cap & PMU_CAP_LBR_FMT; } if (vmx_pebs_supported()) { perf_cap |= host_perf_cap & PERF_CAP_PEBS_MASK; - if ((perf_cap & PERF_CAP_PEBS_FORMAT) < 4) - perf_cap &= ~PERF_CAP_PEBS_BASELINE; + + /* + * Disallow adaptive PEBS as it is functionally broken, can be + * used by the guest to read *host* LBRs, and can be used to + * bypass userspace event filters. To correctly and safely + * support adaptive PEBS, KVM needs to: + * + * 1. Account for the ADAPTIVE flag when (re)programming fixed + * counters. + * + * 2. Gain support from perf (or take direct control of counter + * programming) to support events without adaptive PEBS + * enabled for the hardware counter. + * + * 3. Ensure LBR MSRs cannot hold host data on VM-Entry with + * adaptive PEBS enabled and MSR_PEBS_DATA_CFG.LBRS=1. + * + * 4. Document which PMU events are effectively exposed to the + * guest via adaptive PEBS, and make adaptive PEBS mutually + * exclusive with KVM_SET_PMU_EVENT_FILTER if necessary. + */ + perf_cap &= ~PERF_CAP_PEBS_BASELINE; } return perf_cap; diff --git a/arch/x86/kvm/vmx/vmx.h b/arch/x86/kvm/vmx/vmx.h index 65786dbe7d60..90f9e4434646 100644 --- a/arch/x86/kvm/vmx/vmx.h +++ b/arch/x86/kvm/vmx/vmx.h @@ -15,6 +15,7 @@ #include "vmx_ops.h" #include "../cpuid.h" #include "run_flags.h" +#include "../mmu.h" #define MSR_TYPE_R 1 #define MSR_TYPE_W 2 @@ -109,6 +110,8 @@ struct lbr_desc { bool msr_passthrough; }; +extern struct x86_pmu_lbr vmx_lbr_caps; + /* * The nested_vmx structure is part of vcpu_vmx, and holds information we need * for correct emulation of VMX (i.e., nested VMX) on this vcpu. @@ -719,7 +722,8 @@ static inline bool vmx_need_pf_intercept(struct kvm_vcpu *vcpu) if (!enable_ept) return true; - return allow_smaller_maxphyaddr && cpuid_maxphyaddr(vcpu) < boot_cpu_data.x86_phys_bits; + return allow_smaller_maxphyaddr && + cpuid_maxphyaddr(vcpu) < kvm_get_shadow_phys_bits(); } static inline bool is_unrestricted_guest(struct kvm_vcpu *vcpu) diff --git a/arch/x86/kvm/x86.c b/arch/x86/kvm/x86.c index 47d9f03b7778..91478b769af0 100644 --- a/arch/x86/kvm/x86.c +++ b/arch/x86/kvm/x86.c @@ -1621,7 +1621,7 @@ static bool kvm_is_immutable_feature_msr(u32 msr) ARCH_CAP_PSCHANGE_MC_NO | ARCH_CAP_TSX_CTRL_MSR | ARCH_CAP_TAA_NO | \ ARCH_CAP_SBDR_SSDP_NO | ARCH_CAP_FBSDP_NO | ARCH_CAP_PSDP_NO | \ ARCH_CAP_FB_CLEAR | ARCH_CAP_RRSBA | ARCH_CAP_PBRSB_NO | ARCH_CAP_GDS_NO | \ - ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR) + ARCH_CAP_RFDS_NO | ARCH_CAP_RFDS_CLEAR | ARCH_CAP_BHI_NO) static u64 kvm_get_arch_capabilities(void) { @@ -3470,7 +3470,7 @@ static bool is_mci_status_msr(u32 msr) static bool can_set_mci_status(struct kvm_vcpu *vcpu) { /* McStatusWrEn enabled? */ - if (guest_cpuid_is_amd_or_hygon(vcpu)) + if (guest_cpuid_is_amd_compatible(vcpu)) return !!(vcpu->arch.msr_hwcr & BIT_ULL(18)); return false; diff --git a/arch/x86/lib/retpoline.S b/arch/x86/lib/retpoline.S index e674ccf720b9..391059b2c6fb 100644 --- a/arch/x86/lib/retpoline.S +++ b/arch/x86/lib/retpoline.S @@ -382,8 +382,15 @@ SYM_FUNC_END(call_depth_return_thunk) SYM_CODE_START(__x86_return_thunk) UNWIND_HINT_FUNC ANNOTATE_NOENDBR +#if defined(CONFIG_MITIGATION_UNRET_ENTRY) || \ + defined(CONFIG_MITIGATION_SRSO) || \ + defined(CONFIG_MITIGATION_CALL_DEPTH_TRACKING) ALTERNATIVE __stringify(ANNOTATE_UNRET_SAFE; ret), \ "jmp warn_thunk_thunk", X86_FEATURE_ALWAYS +#else + ANNOTATE_UNRET_SAFE + ret +#endif int3 SYM_CODE_END(__x86_return_thunk) EXPORT_SYMBOL(__x86_return_thunk) diff --git a/arch/x86/mm/fault.c b/arch/x86/mm/fault.c index 622d12ec7f08..bba4e020dd64 100644 --- a/arch/x86/mm/fault.c +++ b/arch/x86/mm/fault.c @@ -723,39 +723,8 @@ kernelmode_fixup_or_oops(struct pt_regs *regs, unsigned long error_code, WARN_ON_ONCE(user_mode(regs)); /* Are we prepared to handle this kernel fault? */ - if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) { - /* - * Any interrupt that takes a fault gets the fixup. This makes - * the below recursive fault logic only apply to a faults from - * task context. - */ - if (in_interrupt()) - return; - - /* - * Per the above we're !in_interrupt(), aka. task context. - * - * In this case we need to make sure we're not recursively - * faulting through the emulate_vsyscall() logic. - */ - if (current->thread.sig_on_uaccess_err && signal) { - sanitize_error_code(address, &error_code); - - set_signal_archinfo(address, error_code); - - if (si_code == SEGV_PKUERR) { - force_sig_pkuerr((void __user *)address, pkey); - } else { - /* XXX: hwpoison faults will set the wrong code. */ - force_sig_fault(signal, si_code, (void __user *)address); - } - } - - /* - * Barring that, we can do the fixup and be happy. - */ + if (fixup_exception(regs, X86_TRAP_PF, error_code, address)) return; - } /* * AMD erratum #91 manifests as a spurious page fault on a PREFETCH diff --git a/arch/x86/mm/mem_encrypt.c b/arch/x86/mm/mem_encrypt.c index 6f3b3e028718..0a120d85d7bb 100644 --- a/arch/x86/mm/mem_encrypt.c +++ b/arch/x86/mm/mem_encrypt.c @@ -102,6 +102,13 @@ void __init mem_encrypt_setup_arch(void) phys_addr_t total_mem = memblock_phys_mem_size(); unsigned long size; + /* + * Do RMP table fixups after the e820 tables have been setup by + * e820__memory_setup(). + */ + if (cc_platform_has(CC_ATTR_HOST_SEV_SNP)) + snp_fixup_e820_tables(); + if (!cc_platform_has(CC_ATTR_GUEST_MEM_ENCRYPT)) return; diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index df5fac428408..59cbc94b6e69 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1807,36 +1807,41 @@ populate_extable: if (BPF_MODE(insn->code) == BPF_PROBE_MEM || BPF_MODE(insn->code) == BPF_PROBE_MEMSX) { /* Conservatively check that src_reg + insn->off is a kernel address: - * src_reg + insn->off >= TASK_SIZE_MAX + PAGE_SIZE - * src_reg is used as scratch for src_reg += insn->off and restored - * after emit_ldx if necessary + * src_reg + insn->off > TASK_SIZE_MAX + PAGE_SIZE + * and + * src_reg + insn->off < VSYSCALL_ADDR */ - u64 limit = TASK_SIZE_MAX + PAGE_SIZE; + u64 limit = TASK_SIZE_MAX + PAGE_SIZE - VSYSCALL_ADDR; u8 *end_of_jmp; - /* At end of these emitted checks, insn->off will have been added - * to src_reg, so no need to do relative load with insn->off offset - */ - insn_off = 0; + /* movabsq r10, VSYSCALL_ADDR */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)VSYSCALL_ADDR >> 32, + (u32)(long)VSYSCALL_ADDR); - /* movabsq r11, limit */ - EMIT2(add_1mod(0x48, AUX_REG), add_1reg(0xB8, AUX_REG)); - EMIT((u32)limit, 4); - EMIT(limit >> 32, 4); + /* mov src_reg, r11 */ + EMIT_mov(AUX_REG, src_reg); if (insn->off) { - /* add src_reg, insn->off */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xC0, src_reg), insn->off); + /* add r11, insn->off */ + maybe_emit_1mod(&prog, AUX_REG, true); + EMIT2_off32(0x81, add_1reg(0xC0, AUX_REG), insn->off); } - /* cmp src_reg, r11 */ - maybe_emit_mod(&prog, src_reg, AUX_REG, true); - EMIT2(0x39, add_2reg(0xC0, src_reg, AUX_REG)); + /* sub r11, r10 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x29, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); + + /* movabsq r10, limit */ + emit_mov_imm64(&prog, BPF_REG_AX, (long)limit >> 32, + (u32)(long)limit); + + /* cmp r10, r11 */ + maybe_emit_mod(&prog, AUX_REG, BPF_REG_AX, true); + EMIT2(0x39, add_2reg(0xC0, AUX_REG, BPF_REG_AX)); - /* if unsigned '>=', goto load */ - EMIT2(X86_JAE, 0); + /* if unsigned '>', goto load */ + EMIT2(X86_JA, 0); end_of_jmp = prog; /* xor dst_reg, dst_reg */ @@ -1862,18 +1867,6 @@ populate_extable: /* populate jmp_offset for JMP above */ start_of_ldx[-1] = prog - start_of_ldx; - if (insn->off && src_reg != dst_reg) { - /* sub src_reg, insn->off - * Restore src_reg after "add src_reg, insn->off" in prev - * if statement. But if src_reg == dst_reg, emit_ldx - * above already clobbered src_reg, so no need to restore. - * If add src_reg, insn->off was unnecessary, no need to - * restore either. - */ - maybe_emit_1mod(&prog, src_reg, true); - EMIT2_off32(0x81, add_1reg(0xE8, src_reg), insn->off); - } - if (!bpf_prog->aux->extable) break; @@ -3473,3 +3466,9 @@ bool bpf_jit_supports_ptr_xchg(void) { return true; } + +/* x86-64 JIT emits its own code to filter user addresses so return 0 here */ +u64 bpf_arch_uaddress_limit(void) +{ + return 0; +} diff --git a/arch/x86/virt/svm/sev.c b/arch/x86/virt/svm/sev.c index ab0e8448bb6e..0ae10535c699 100644 --- a/arch/x86/virt/svm/sev.c +++ b/arch/x86/virt/svm/sev.c @@ -163,6 +163,42 @@ bool snp_probe_rmptable_info(void) return true; } +static void __init __snp_fixup_e820_tables(u64 pa) +{ + if (IS_ALIGNED(pa, PMD_SIZE)) + return; + + /* + * Handle cases where the RMP table placement by the BIOS is not + * 2M aligned and the kexec kernel could try to allocate + * from within that chunk which then causes a fatal RMP fault. + * + * The e820_table needs to be updated as it is converted to + * kernel memory resources and used by KEXEC_FILE_LOAD syscall + * to load kexec segments. + * + * The e820_table_firmware needs to be updated as it is exposed + * to sysfs and used by the KEXEC_LOAD syscall to load kexec + * segments. + * + * The e820_table_kexec needs to be updated as it passed to + * the kexec-ed kernel. + */ + pa = ALIGN_DOWN(pa, PMD_SIZE); + if (e820__mapped_any(pa, pa + PMD_SIZE, E820_TYPE_RAM)) { + pr_info("Reserving start/end of RMP table on a 2MB boundary [0x%016llx]\n", pa); + e820__range_update(pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_kexec, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + e820__range_update_table(e820_table_firmware, pa, PMD_SIZE, E820_TYPE_RAM, E820_TYPE_RESERVED); + } +} + +void __init snp_fixup_e820_tables(void) +{ + __snp_fixup_e820_tables(probed_rmp_base); + __snp_fixup_e820_tables(probed_rmp_base + probed_rmp_size); +} + /* * Do the necessary preparations which are verified by the firmware as * described in the SNP_INIT_EX firmware command description in the SNP diff --git a/arch/x86/xen/enlighten_pv.c b/arch/x86/xen/enlighten_pv.c index ace2eb054053..9ba53814ed6a 100644 --- a/arch/x86/xen/enlighten_pv.c +++ b/arch/x86/xen/enlighten_pv.c @@ -219,13 +219,21 @@ static __read_mostly unsigned int cpuid_leaf5_edx_val; static void xen_cpuid(unsigned int *ax, unsigned int *bx, unsigned int *cx, unsigned int *dx) { - unsigned maskebx = ~0; + unsigned int maskebx = ~0; + unsigned int or_ebx = 0; /* * Mask out inconvenient features, to try and disable as many * unsupported kernel subsystems as possible. */ switch (*ax) { + case 0x1: + /* Replace initial APIC ID in bits 24-31 of EBX. */ + /* See xen_pv_smp_config() for related topology preparations. */ + maskebx = 0x00ffffff; + or_ebx = smp_processor_id() << 24; + break; + case CPUID_MWAIT_LEAF: /* Synthesize the values.. */ *ax = 0; @@ -248,6 +256,7 @@ static void xen_cpuid(unsigned int *ax, unsigned int *bx, : "0" (*ax), "2" (*cx)); *bx &= maskebx; + *bx |= or_ebx; } static bool __init xen_check_mwait(void) diff --git a/arch/x86/xen/smp_pv.c b/arch/x86/xen/smp_pv.c index 27d1a5b7f571..ac41d83b38d3 100644 --- a/arch/x86/xen/smp_pv.c +++ b/arch/x86/xen/smp_pv.c @@ -154,9 +154,9 @@ static void __init xen_pv_smp_config(void) u32 apicid = 0; int i; - topology_register_boot_apic(apicid++); + topology_register_boot_apic(apicid); - for (i = 1; i < nr_cpu_ids; i++) + for (i = 0; i < nr_cpu_ids; i++) topology_register_apic(apicid++, CPU_ACPIID_INVALID, true); /* Pretend to be a proper enumerated system */ |