Andrew Murray (1): arm64: HWCAP: add support for AT_HWCAP2
Dave Martin (1): arm64: Expose SVE2 features for userspace
Documentation/arm64/cpu-feature-registers.txt | 16 ++++ Documentation/arm64/elf_hwcaps.txt | 37 ++++++++- Documentation/arm64/sve.txt | 17 ++++ arch/arm64/Kconfig | 3 + arch/arm64/crypto/aes-ce-ccm-glue.c | 2 +- arch/arm64/crypto/aes-neonbs-glue.c | 2 +- arch/arm64/crypto/chacha20-neon-glue.c | 2 +- arch/arm64/crypto/ghash-ce-glue.c | 6 +- arch/arm64/crypto/sha256-glue.c | 4 +- arch/arm64/include/asm/cpufeature.h | 22 +++--- arch/arm64/include/asm/hwcap.h | 55 ++++++++++++- arch/arm64/include/asm/sysreg.h | 14 ++++ arch/arm64/include/uapi/asm/hwcap.h | 12 ++- arch/arm64/kernel/cpufeature.c | 77 +++++++++++-------- arch/arm64/kernel/cpuinfo.c | 12 ++- arch/arm64/kernel/fpsimd.c | 4 +- drivers/clocksource/arm_arch_timer.c | 8 ++ 17 files changed, 236 insertions(+), 57 deletions(-)
反馈： 您发送到kernel@openeuler.org的补丁/补丁集，已成功转换为PR！ PR链接地址： https://gitee.com/openeuler/kernel/pulls/2610 邮件列表地址：https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/M...
FeedBack: The patch(es) which you have sent to kernel@openeuler.org mailing list has been converted to a pull request successfully! Pull request link: https://gitee.com/openeuler/kernel/pulls/2610 Mailing list address: https://mailweb.openeuler.org/hyperkitty/list/kernel@openeuler.org/message/M...
From: Andrew Murray andrew.murray@arm.com
mainline inclusion from mainline-v5.2-rc1 commit 06a916feca2b262ab0c1a2aeb68882f4b1108a07 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8B82O CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
As we will exhaust the first 32 bits of AT_HWCAP let's start exposing AT_HWCAP2 to userspace to give us up to 64 caps.
Whilst it's possible to use the remaining 32 bits of AT_HWCAP, we prefer to expand into AT_HWCAP2 in order to provide a consistent view to userspace between ILP32 and LP64. However internal to the kernel we prefer to continue to use the full space of elf_hwcap.
To reduce complexity and allow for future expansion, we now represent hwcaps in the kernel as ordinals and use a KERNEL_HWCAP_ prefix. This allows us to support automatic feature based module loading for all our hwcaps.
We introduce cpu_set_feature to set hwcaps which complements the existing cpu_have_feature helper. These helpers allow us to clean up existing direct uses of elf_hwcap and reduce any future effort required to move beyond 64 caps.
For convenience we also introduce cpu_{have,set}_named_feature which makes use of the cpu_feature macro to allow providing a hwcap name without a {KERNEL_}HWCAP_ prefix.
Signed-off-by: Andrew Murray andrew.murray@arm.com [will: use const_ilog2() and tweak documentation] Signed-off-by: Will Deacon will.deacon@arm.com
Conflicts: Documentation/arm64/elf_hwcaps.txt arch/arm64/crypto/chacha-neon-glue.c arch/arm64/crypto/crct10dif-ce-glue.c arch/arm64/crypto/ghash-ce-glue.c arch/arm64/crypto/nhpoly1305-neon-glue.c arch/arm64/kernel/cpufeature.c drivers/clocksource/arm_arch_timer.c
Signed-off-by: Yu Liao liaoyu15@huawei.com --- Documentation/arm64/elf_hwcaps.txt | 13 ++++-- arch/arm64/crypto/aes-ce-ccm-glue.c | 2 +- arch/arm64/crypto/aes-neonbs-glue.c | 2 +- arch/arm64/crypto/chacha20-neon-glue.c | 2 +- arch/arm64/crypto/ghash-ce-glue.c | 6 +-- arch/arm64/crypto/sha256-glue.c | 4 +- arch/arm64/include/asm/cpufeature.h | 22 +++++----- arch/arm64/include/asm/hwcap.h | 49 ++++++++++++++++++++- arch/arm64/include/uapi/asm/hwcap.h | 2 +- arch/arm64/kernel/cpufeature.c | 60 +++++++++++++------------- arch/arm64/kernel/cpuinfo.c | 2 +- arch/arm64/kernel/fpsimd.c | 4 +- drivers/clocksource/arm_arch_timer.c | 8 ++++ 13 files changed, 120 insertions(+), 56 deletions(-)
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt index 6feaffe90e22..186feb16e2f2 100644 --- a/Documentation/arm64/elf_hwcaps.txt +++ b/Documentation/arm64/elf_hwcaps.txt @@ -13,9 +13,9 @@ architected discovery mechanism available to userspace code at EL0. The kernel exposes the presence of these features to userspace through a set of flags called hwcaps, exposed in the auxilliary vector.
-Userspace software can test for features by acquiring the AT_HWCAP entry -of the auxilliary vector, and testing whether the relevant flags are -set, e.g. +Userspace software can test for features by acquiring the AT_HWCAP or +AT_HWCAP2 entry of the auxiliary vector, and testing whether the relevant +flags are set, e.g.
bool floating_point_is_present(void) { @@ -182,3 +182,10 @@ HWCAP_FLAGM HWCAP_SSBS
Functionality implied by ID_AA64PFR1_EL1.SSBS == 0b0010. + + +4. Unused AT_HWCAP bits +----------------------- + +For interoperation with userspace, the kernel guarantees that bits 62 +and 63 of AT_HWCAP will always be returned as 0. diff --git a/arch/arm64/crypto/aes-ce-ccm-glue.c b/arch/arm64/crypto/aes-ce-ccm-glue.c index 5fc6f51908fd..036ea77f83bc 100644 --- a/arch/arm64/crypto/aes-ce-ccm-glue.c +++ b/arch/arm64/crypto/aes-ce-ccm-glue.c @@ -372,7 +372,7 @@ static struct aead_alg ccm_aes_alg = {
static int __init aes_mod_init(void) { - if (!(elf_hwcap & HWCAP_AES)) + if (!cpu_have_named_feature(AES)) return -ENODEV; return crypto_register_aead(&ccm_aes_alg); } diff --git a/arch/arm64/crypto/aes-neonbs-glue.c b/arch/arm64/crypto/aes-neonbs-glue.c index 5cc248967387..742359801559 100644 --- a/arch/arm64/crypto/aes-neonbs-glue.c +++ b/arch/arm64/crypto/aes-neonbs-glue.c @@ -442,7 +442,7 @@ static int __init aes_init(void) int err; int i;
- if (!(elf_hwcap & HWCAP_ASIMD)) + if (!cpu_have_named_feature(ASIMD)) return -ENODEV;
err = crypto_register_skciphers(aes_algs, ARRAY_SIZE(aes_algs)); diff --git a/arch/arm64/crypto/chacha20-neon-glue.c b/arch/arm64/crypto/chacha20-neon-glue.c index 727579c93ded..bb3314905bee 100644 --- a/arch/arm64/crypto/chacha20-neon-glue.c +++ b/arch/arm64/crypto/chacha20-neon-glue.c @@ -114,7 +114,7 @@ static struct skcipher_alg alg = {
static int __init chacha20_simd_mod_init(void) { - if (!(elf_hwcap & HWCAP_ASIMD)) + if (!cpu_have_named_feature(ASIMD)) return -ENODEV;
return crypto_register_skcipher(&alg); diff --git a/arch/arm64/crypto/ghash-ce-glue.c b/arch/arm64/crypto/ghash-ce-glue.c index 1ed227bf6106..cd9d743cb40f 100644 --- a/arch/arm64/crypto/ghash-ce-glue.c +++ b/arch/arm64/crypto/ghash-ce-glue.c @@ -648,10 +648,10 @@ static int __init ghash_ce_mod_init(void) { int ret;
- if (!(elf_hwcap & HWCAP_ASIMD)) + if (!cpu_have_named_feature(ASIMD)) return -ENODEV;
- if (elf_hwcap & HWCAP_PMULL) + if (cpu_have_named_feature(PMULL)) pmull_ghash_update = pmull_ghash_update_p64;
else @@ -661,7 +661,7 @@ static int __init ghash_ce_mod_init(void) if (ret) return ret;
- if (elf_hwcap & HWCAP_PMULL) { + if (cpu_have_named_feature(PMULL)) { ret = crypto_register_aead(&gcm_aes_alg); if (ret) crypto_unregister_shash(&ghash_alg); diff --git a/arch/arm64/crypto/sha256-glue.c b/arch/arm64/crypto/sha256-glue.c index 4aedeaefd61f..0cccdb9cc2c0 100644 --- a/arch/arm64/crypto/sha256-glue.c +++ b/arch/arm64/crypto/sha256-glue.c @@ -173,7 +173,7 @@ static int __init sha256_mod_init(void) if (ret) return ret;
- if (elf_hwcap & HWCAP_ASIMD) { + if (cpu_have_named_feature(ASIMD)) { ret = crypto_register_shashes(neon_algs, ARRAY_SIZE(neon_algs)); if (ret) crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); @@ -183,7 +183,7 @@ static int __init sha256_mod_init(void)
static void __exit sha256_mod_fini(void) { - if (elf_hwcap & HWCAP_ASIMD) + if (cpu_have_named_feature(ASIMD)) crypto_unregister_shashes(neon_algs, ARRAY_SIZE(neon_algs)); crypto_unregister_shashes(algs, ARRAY_SIZE(algs)); } diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h index ffb0a1ec0088..eef5a9c9b823 100644 --- a/arch/arm64/include/asm/cpufeature.h +++ b/arch/arm64/include/asm/cpufeature.h @@ -14,15 +14,8 @@ #include <asm/hwcap.h> #include <asm/sysreg.h>
-/* - * In the arm64 world (as in the ARM world), elf_hwcap is used both internally - * in the kernel and for user space to keep track of which optional features - * are supported by the current system. So let's map feature 'x' to HWCAP_x. - * Note that HWCAP_x constants are bit fields so we need to take the log. - */ - -#define MAX_CPU_FEATURES (8 * sizeof(elf_hwcap)) -#define cpu_feature(x) ilog2(HWCAP_ ## x) +#define MAX_CPU_FEATURES 64 +#define cpu_feature(x) KERNEL_HWCAP_ ## x
#ifndef __ASSEMBLY__
@@ -372,10 +365,19 @@ extern bool set_cap_spectre_bhb;
bool this_cpu_has_cap(unsigned int cap);
+static inline void cpu_set_feature(unsigned int num) +{ + WARN_ON(num >= MAX_CPU_FEATURES); + elf_hwcap |= BIT(num); +} +#define cpu_set_named_feature(name) cpu_set_feature(cpu_feature(name)) + static inline bool cpu_have_feature(unsigned int num) { - return elf_hwcap & (1UL << num); + WARN_ON(num >= MAX_CPU_FEATURES); + return elf_hwcap & BIT(num); } +#define cpu_have_named_feature(name) cpu_have_feature(cpu_feature(name))
/* System capability check for constant caps */ static __always_inline bool __cpus_have_const_cap(int num) diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 428b745b5386..458ff2d7ece3 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -40,11 +40,58 @@ #define COMPAT_HWCAP2_CRC32 (1 << 4)
#ifndef __ASSEMBLY__ +#include <linux/kernel.h> +#include <linux/log2.h> + +/* + * For userspace we represent hwcaps as a collection of HWCAP{,2}_x bitfields + * as described in uapi/asm/hwcap.h. For the kernel we represent hwcaps as + * natural numbers (in a single range of size MAX_CPU_FEATURES) defined here + * with prefix KERNEL_HWCAP_ mapped to their HWCAP{,2}_x counterpart. + * + * Hwcaps should be set and tested within the kernel via the + * cpu_{set,have}_named_feature(feature) where feature is the unique suffix + * of KERNEL_HWCAP_{feature}. + */ +#define __khwcap_feature(x) const_ilog2(HWCAP_ ## x) +#define KERNEL_HWCAP_FP __khwcap_feature(FP) +#define KERNEL_HWCAP_ASIMD __khwcap_feature(ASIMD) +#define KERNEL_HWCAP_EVTSTRM __khwcap_feature(EVTSTRM) +#define KERNEL_HWCAP_AES __khwcap_feature(AES) +#define KERNEL_HWCAP_PMULL __khwcap_feature(PMULL) +#define KERNEL_HWCAP_SHA1 __khwcap_feature(SHA1) +#define KERNEL_HWCAP_SHA2 __khwcap_feature(SHA2) +#define KERNEL_HWCAP_CRC32 __khwcap_feature(CRC32) +#define KERNEL_HWCAP_ATOMICS __khwcap_feature(ATOMICS) +#define KERNEL_HWCAP_FPHP __khwcap_feature(FPHP) +#define KERNEL_HWCAP_ASIMDHP __khwcap_feature(ASIMDHP) +#define KERNEL_HWCAP_CPUID __khwcap_feature(CPUID) +#define KERNEL_HWCAP_ASIMDRDM __khwcap_feature(ASIMDRDM) +#define KERNEL_HWCAP_JSCVT __khwcap_feature(JSCVT) +#define KERNEL_HWCAP_FCMA __khwcap_feature(FCMA) +#define KERNEL_HWCAP_LRCPC __khwcap_feature(LRCPC) +#define KERNEL_HWCAP_DCPOP __khwcap_feature(DCPOP) +#define KERNEL_HWCAP_SHA3 __khwcap_feature(SHA3) +#define KERNEL_HWCAP_SM3 __khwcap_feature(SM3) +#define KERNEL_HWCAP_SM4 __khwcap_feature(SM4) +#define KERNEL_HWCAP_ASIMDDP __khwcap_feature(ASIMDDP) +#define KERNEL_HWCAP_SHA512 __khwcap_feature(SHA512) +#define KERNEL_HWCAP_SVE __khwcap_feature(SVE) +#define KERNEL_HWCAP_ASIMDFHM __khwcap_feature(ASIMDFHM) +#define KERNEL_HWCAP_DIT __khwcap_feature(DIT) +#define KERNEL_HWCAP_USCAT __khwcap_feature(USCAT) +#define KERNEL_HWCAP_ILRCPC __khwcap_feature(ILRCPC) +#define KERNEL_HWCAP_FLAGM __khwcap_feature(FLAGM) +#define KERNEL_HWCAP_SSBS __khwcap_feature(SSBS) + +#define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 32) + /* * This yields a mask that user programs can use to figure out what * instruction set this cpu supports. */ -#define ELF_HWCAP (elf_hwcap) +#define ELF_HWCAP lower_32_bits(elf_hwcap) +#define ELF_HWCAP2 upper_32_bits(elf_hwcap)
#ifdef CONFIG_AARCH32_EL0 extern unsigned int a32_elf_hwcap, a32_elf_hwcap2; diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 2bcd6e4f3474..602158a55554 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -18,7 +18,7 @@ #define _UAPI__ASM_HWCAP_H
/* - * HWCAP flags - for elf_hwcap (in kernel) and AT_HWCAP + * HWCAP flags - for AT_HWCAP */ #define HWCAP_FP (1 << 0) #define HWCAP_ASIMD (1 << 1) diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 1c93cc3f7692..3a0e7e10f2d7 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -1553,35 +1553,35 @@ static const struct arm64_cpu_capabilities arm64_features[] = { }
static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_PMULL), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_AES), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA1), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA2), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_SHA512), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_CRC32), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ATOMICS), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDRDM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SHA3), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM3), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_SM4), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDDP), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_ASIMDFHM), - HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FLAGM), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_FP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_FPHP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, HWCAP_ASIMD), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_ASIMDHP), - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, HWCAP_DIT), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_DCPOP), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_JSCVT), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_FCMA), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_LRCPC), - HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, HWCAP_ILRCPC), - HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, HWCAP_USCAT), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_PMULL), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_AES_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_AES), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA1_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA1), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA2), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA2_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_SHA512), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_CRC32_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_CRC32), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_ATOMICS_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ATOMICS), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_RDM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDRDM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SHA3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SHA3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM3_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM3), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_SM4_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_SM4), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_DP_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_FHM_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), + HWCAP_CAP(SYS_ID_AA64ISAR0_EL1, ID_AA64ISAR0_TS_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FLAGM), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_FP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_FP_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FPHP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 0, CAP_HWCAP, KERNEL_HWCAP_ASIMD), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_ASIMD_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_ASIMDHP), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_DIT_SHIFT, FTR_SIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DIT), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_DPB_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_DCPOP), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_JSCVT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_JSCVT), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_FCMA_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_FCMA), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_LRCPC), + HWCAP_CAP(SYS_ID_AA64ISAR1_EL1, ID_AA64ISAR1_LRCPC_SHIFT, FTR_UNSIGNED, 2, CAP_HWCAP, KERNEL_HWCAP_ILRCPC), + HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE - HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, HWCAP_SVE), + HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE), #endif - HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, HWCAP_SSBS), + HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), {}, };
@@ -1627,7 +1627,7 @@ static void __init cap_set_elf_hwcap(const struct arm64_cpu_capabilities *cap) { switch (cap->hwcap_type) { case CAP_HWCAP: - elf_hwcap |= cap->hwcap; + cpu_set_feature(cap->hwcap); break; #ifdef CONFIG_AARCH32_EL0 case CAP_COMPAT_HWCAP: @@ -1650,7 +1650,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap)
switch (cap->hwcap_type) { case CAP_HWCAP: - rc = (elf_hwcap & cap->hwcap) != 0; + rc = cpu_have_feature(cap->hwcap); break; #ifdef CONFIG_AARCH32_EL0 case CAP_COMPAT_HWCAP: @@ -1671,7 +1671,7 @@ static bool cpus_have_elf_hwcap(const struct arm64_cpu_capabilities *cap) static void __init setup_elf_hwcaps(const struct arm64_cpu_capabilities *hwcaps) { /* We support emulation of accesses to CPU ID feature registers */ - elf_hwcap |= HWCAP_CPUID; + cpu_set_named_feature(CPUID); for (; hwcaps->matches; hwcaps++) if (hwcaps->matches(hwcaps, cpucap_default_scope(hwcaps))) cap_set_elf_hwcap(hwcaps); diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 005d88db1082..bfe3bb8f05fe 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -164,7 +164,7 @@ static int c_show(struct seq_file *m, void *v) #endif /* CONFIG_AARCH32_EL0 */ } else { for (j = 0; hwcap_str[j]; j++) - if (elf_hwcap & (1 << j)) + if (cpu_have_feature(j)) seq_printf(m, " %s", hwcap_str[j]); } seq_puts(m, "\n"); diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c index bb048144c3bd..6972de5681ec 100644 --- a/arch/arm64/kernel/fpsimd.c +++ b/arch/arm64/kernel/fpsimd.c @@ -1302,14 +1302,14 @@ static inline void fpsimd_hotplug_init(void) { } */ static int __init fpsimd_init(void) { - if (elf_hwcap & HWCAP_FP) { + if (cpu_have_named_feature(FP)) { fpsimd_pm_init(); fpsimd_hotplug_init(); } else { pr_notice("Floating-point is not implemented\n"); }
- if (!(elf_hwcap & HWCAP_ASIMD)) + if (!cpu_have_named_feature(ASIMD)) pr_notice("Advanced SIMD is not implemented\n");
return sve_sysctl_init(); diff --git a/drivers/clocksource/arm_arch_timer.c b/drivers/clocksource/arm_arch_timer.c index 58863fd9c91b..fbfc81932dea 100644 --- a/drivers/clocksource/arm_arch_timer.c +++ b/drivers/clocksource/arm_arch_timer.c @@ -825,7 +825,11 @@ static void arch_timer_evtstrm_enable(int divider) cntkctl |= (divider << ARCH_TIMER_EVT_TRIGGER_SHIFT) | ARCH_TIMER_VIRT_EVT_EN; arch_timer_set_cntkctl(cntkctl); +#ifdef CONFIG_ARM64 + cpu_set_named_feature(EVTSTRM); +#else elf_hwcap |= HWCAP_EVTSTRM; +#endif #ifdef CONFIG_AARCH32_EL0 a32_elf_hwcap |= COMPAT_HWCAP_EVTSTRM; #endif @@ -1059,7 +1063,11 @@ static int arch_timer_cpu_pm_notify(struct notifier_block *self, } else if (action == CPU_PM_ENTER_FAILED || action == CPU_PM_EXIT) { arch_timer_set_cntkctl(__this_cpu_read(saved_cntkctl));
+#ifdef CONFIG_ARM64 + if (cpu_have_named_feature(EVTSTRM)) +#else if (elf_hwcap & HWCAP_EVTSTRM) +#endif cpumask_set_cpu(smp_processor_id(), &evtstrm_available); } return NOTIFY_OK;
From: Dave Martin Dave.Martin@arm.com
mainline inclusion from mainline-v5.2-rc1 commit 06a916feca2b262ab0c1a2aeb68882f4b1108a07 category: feature bugzilla: https://gitee.com/openeuler/kernel/issues/I8B82O CVE: NA
Reference: https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?i...
--------------------------------
This patch provides support for reporting the presence of SVE2 and its optional features to userspace.
This will also enable visibility of SVE2 for guests, when KVM support for SVE-enabled guests is available.
Signed-off-by: Dave Martin Dave.Martin@arm.com Signed-off-by: Will Deacon will.deacon@arm.com
Conflicts: arch/arm64/include/asm/hwcap.h arch/arm64/include/uapi/asm/hwcap.h arch/arm64/kernel/cpuinfo.c
Signed-off-by: Yu Liao liaoyu15@huawei.com --- Documentation/arm64/cpu-feature-registers.txt | 16 +++++++++++++ Documentation/arm64/elf_hwcaps.txt | 24 +++++++++++++++++++ Documentation/arm64/sve.txt | 17 +++++++++++++ arch/arm64/Kconfig | 3 +++ arch/arm64/include/asm/hwcap.h | 6 +++++ arch/arm64/include/asm/sysreg.h | 14 +++++++++++ arch/arm64/include/uapi/asm/hwcap.h | 10 ++++++++ arch/arm64/kernel/cpufeature.c | 17 ++++++++++++- arch/arm64/kernel/cpuinfo.c | 10 ++++++++ 9 files changed, 116 insertions(+), 1 deletion(-)
diff --git a/Documentation/arm64/cpu-feature-registers.txt b/Documentation/arm64/cpu-feature-registers.txt index 7964f03846b1..fcd2e1deb886 100644 --- a/Documentation/arm64/cpu-feature-registers.txt +++ b/Documentation/arm64/cpu-feature-registers.txt @@ -201,6 +201,22 @@ infrastructure: | AT | [35-32] | y | x--------------------------------------------------x
+ 6) ID_AA64ZFR0_EL1 - SVE feature ID register 0 + + x--------------------------------------------------x + | Name | bits | visible | + |--------------------------------------------------| + | SM4 | [43-40] | y | + |--------------------------------------------------| + | SHA3 | [35-32] | y | + |--------------------------------------------------| + | BitPerm | [19-16] | y | + |--------------------------------------------------| + | AES | [7-4] | y | + |--------------------------------------------------| + | SVEVer | [3-0] | y | + x--------------------------------------------------x + Appendix I: Example ---------------------------
diff --git a/Documentation/arm64/elf_hwcaps.txt b/Documentation/arm64/elf_hwcaps.txt index 186feb16e2f2..e2ce14dfccf2 100644 --- a/Documentation/arm64/elf_hwcaps.txt +++ b/Documentation/arm64/elf_hwcaps.txt @@ -159,6 +159,30 @@ HWCAP_SVE
Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001.
+HWCAP2_SVE2 + + Functionality implied by ID_AA64ZFR0_EL1.SVEVer == 0b0001. + +HWCAP2_SVEAES + + Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0001. + +HWCAP2_SVEPMULL + + Functionality implied by ID_AA64ZFR0_EL1.AES == 0b0010. + +HWCAP2_SVEBITPERM + + Functionality implied by ID_AA64ZFR0_EL1.BitPerm == 0b0001. + +HWCAP2_SVESHA3 + + Functionality implied by ID_AA64ZFR0_EL1.SHA3 == 0b0001. + +HWCAP2_SVESM4 + + Functionality implied by ID_AA64ZFR0_EL1.SM4 == 0b0001. + HWCAP_ASIMDFHM
Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0001. diff --git a/Documentation/arm64/sve.txt b/Documentation/arm64/sve.txt index 2001d84384ca..5689fc9a976a 100644 --- a/Documentation/arm64/sve.txt +++ b/Documentation/arm64/sve.txt @@ -34,6 +34,23 @@ model features for SVE is included in Appendix A. following sections: software that needs to verify that those interfaces are present must check for HWCAP_SVE instead.
+* On hardware that supports the SVE2 extensions, HWCAP2_SVE2 will also + be reported in the AT_HWCAP2 aux vector entry. In addition to this, + optional extensions to SVE2 may be reported by the presence of: + + HWCAP2_SVE2 + HWCAP2_SVEAES + HWCAP2_SVEPMULL + HWCAP2_SVEBITPERM + HWCAP2_SVESHA3 + HWCAP2_SVESM4 + + This list may be extended over time as the SVE architecture evolves. + + These extensions are also reported via the CPU ID register ID_AA64ZFR0_EL1, + which userspace can read using an MRS instruction. See elf_hwcaps.txt and + cpu-feature-registers.txt for details. + * Debuggers should restrict themselves to interacting with the target via the NT_ARM_SVE regset. The recommended way of detecting support for this regset is to connect to a target process first and then attempt a diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 88b8031a93b2..f7398a1904a2 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -1316,6 +1316,9 @@ config ARM64_SVE
To enable use of this extension on CPUs that implement it, say Y.
+ On CPUs that support the SVE2 extensions, this option will enable + those too. + Note that for architectural reasons, firmware _must_ implement SVE support when running on SVE capable hardware. The required support is present in: diff --git a/arch/arm64/include/asm/hwcap.h b/arch/arm64/include/asm/hwcap.h index 458ff2d7ece3..08315a3bf387 100644 --- a/arch/arm64/include/asm/hwcap.h +++ b/arch/arm64/include/asm/hwcap.h @@ -85,6 +85,12 @@ #define KERNEL_HWCAP_SSBS __khwcap_feature(SSBS)
#define __khwcap2_feature(x) (const_ilog2(HWCAP2_ ## x) + 32) +#define KERNEL_HWCAP_SVE2 __khwcap2_feature(SVE2) +#define KERNEL_HWCAP_SVEAES __khwcap2_feature(SVEAES) +#define KERNEL_HWCAP_SVEPMULL __khwcap2_feature(SVEPMULL) +#define KERNEL_HWCAP_SVEBITPERM __khwcap2_feature(SVEBITPERM) +#define KERNEL_HWCAP_SVESHA3 __khwcap2_feature(SVESHA3) +#define KERNEL_HWCAP_SVESM4 __khwcap2_feature(SVESM4)
/* * This yields a mask that user programs can use to figure out what diff --git a/arch/arm64/include/asm/sysreg.h b/arch/arm64/include/asm/sysreg.h index 0fd51d253648..69618e602ed8 100644 --- a/arch/arm64/include/asm/sysreg.h +++ b/arch/arm64/include/asm/sysreg.h @@ -564,6 +564,20 @@ #define ID_AA64PFR1_SSBS_PSTATE_ONLY 1 #define ID_AA64PFR1_SSBS_PSTATE_INSNS 2
+/* id_aa64zfr0 */ +#define ID_AA64ZFR0_SM4_SHIFT 40 +#define ID_AA64ZFR0_SHA3_SHIFT 32 +#define ID_AA64ZFR0_BITPERM_SHIFT 16 +#define ID_AA64ZFR0_AES_SHIFT 4 +#define ID_AA64ZFR0_SVEVER_SHIFT 0 + +#define ID_AA64ZFR0_SM4 0x1 +#define ID_AA64ZFR0_SHA3 0x1 +#define ID_AA64ZFR0_BITPERM 0x1 +#define ID_AA64ZFR0_AES 0x1 +#define ID_AA64ZFR0_AES_PMULL 0x2 +#define ID_AA64ZFR0_SVEVER_SVE2 0x1 + /* id_aa64mmfr0 */ #define ID_AA64MMFR0_TGRAN4_SHIFT 28 #define ID_AA64MMFR0_TGRAN64_SHIFT 24 diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 602158a55554..fea93415b493 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -50,4 +50,14 @@ #define HWCAP_FLAGM (1 << 27) #define HWCAP_SSBS (1 << 28)
+/* + * HWCAP2 flags - for AT_HWCAP2 + */ +#define HWCAP2_SVE2 (1 << 1) +#define HWCAP2_SVEAES (1 << 2) +#define HWCAP2_SVEPMULL (1 << 3) +#define HWCAP2_SVEBITPERM (1 << 4) +#define HWCAP2_SVESHA3 (1 << 5) +#define HWCAP2_SVESM4 (1 << 6) + #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 3a0e7e10f2d7..4f384bbd86c7 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -183,6 +183,15 @@ static const struct arm64_ftr_bits ftr_id_aa64pfr1[] = { ARM64_FTR_END, };
+static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SM4_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SHA3_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_BITPERM_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_AES_SHIFT, 4, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_SVEVER_SHIFT, 4, 0), + ARM64_FTR_END, +}; + static const struct arm64_ftr_bits ftr_id_aa64mmfr0[] = { /* * We already refuse to boot CPUs that don't support our configured @@ -399,7 +408,7 @@ static const struct __ftr_reg_entry { /* Op1 = 0, CRn = 0, CRm = 4 */ ARM64_FTR_REG(SYS_ID_AA64PFR0_EL1, ftr_id_aa64pfr0), ARM64_FTR_REG(SYS_ID_AA64PFR1_EL1, ftr_id_aa64pfr1), - ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz), + ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_id_aa64zfr0),
/* Op1 = 0, CRn = 0, CRm = 5 */ ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0), @@ -1580,6 +1589,12 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(SYS_ID_AA64MMFR2_EL1, ID_AA64MMFR2_AT_SHIFT, FTR_UNSIGNED, 1, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE HWCAP_CAP(SYS_ID_AA64PFR0_EL1, ID_AA64PFR0_SVE_SHIFT, FTR_UNSIGNED, ID_AA64PFR0_SVE, CAP_HWCAP, KERNEL_HWCAP_SVE), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SVEVER_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SVEVER_SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES, CAP_HWCAP, KERNEL_HWCAP_SVEAES), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_AES_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_AES_PMULL, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_BITPERM_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_BITPERM, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SHA3_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SHA3, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), + HWCAP_CAP(SYS_ID_AA64ZFR0_EL1, ID_AA64ZFR0_SM4_SHIFT, FTR_UNSIGNED, ID_AA64ZFR0_SM4, CAP_HWCAP, KERNEL_HWCAP_SVESM4), #endif HWCAP_CAP(SYS_ID_AA64PFR1_EL1, ID_AA64PFR1_SSBS_SHIFT, FTR_UNSIGNED, ID_AA64PFR1_SSBS_PSTATE_INSNS, CAP_HWCAP, KERNEL_HWCAP_SSBS), {}, diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index bfe3bb8f05fe..c8e4ddd23f0c 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -82,6 +82,16 @@ static const char *const hwcap_str[] = { "ilrcpc", "flagm", "ssbs", + "sb", + "paca", + "pacg", + "dcpodp", + "sve2", + "sveaes", + "svepmull", + "svebitperm", + "svesha3", + "svesm4", NULL };
-
patchwork bot -
Yu Liao