From abca5e69ab6268cbe1913b19da5a98c3383f8bb3 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Mon, 18 May 2026 16:07:29 +0100 Subject: [PATCH 1/2] arm64/cpufeature: Define hwcaps for 2025 dpISA features The features added by the 2025 dpISA are all straightforward instruction only features so there is no state to manage, we can just expose hwcaps to let userspace know they are available. F16MM is slightly odd in that the feature is FEAT_F16MM but it is discovered via ID_AA64FPFR0_EL1.F16MM2. We follow the feature name. Signed-off-by: Mark Brown Signed-off-by: Will Deacon --- Documentation/arch/arm64/elf_hwcaps.rst | 24 ++++++++++++++++++++++++ arch/arm64/include/uapi/asm/hwcap.h | 8 ++++++++ arch/arm64/kernel/cpufeature.c | 11 +++++++++++ arch/arm64/kernel/cpuinfo.c | 8 ++++++++ 4 files changed, 51 insertions(+) diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 97315ae6c0da..07ff9ea1d605 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -451,6 +451,30 @@ HWCAP3_LS64 of CPU. User should only use ld64b/st64b on supported target (device) memory location, otherwise fallback to the non-atomic alternatives. +HWCAP3_SVE_B16MM + Functionality implied by ID_AA64ZFR0_EL1.B16B16 == 0b0011 + +HWCAP3_SVE2P3 + Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0100 + +HWCAP3_SME_LUT6 + Functionality implied by ID_AA64SMFR0_EL1.LUT6 == 0b1 + +HWCAP3_SME2P3 + Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0100 + +HWCAP3_F16MM + Functionality implied by ID_AA64FPFR0_EL1.F16MM2 == 0b1 + +HWCAP3_F16F32DOT + Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0010 + +HWCAP3_F16F32MM + Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0011 + +HWCAP3_SVE_LUT6 + Functionality implied by ID_AA64ISAR2_EL1.LUT == 0b0010 and + ID_AA64PFR0_EL1.SVE == 0b0001. 4. Unused AT_HWCAP bits ----------------------- diff --git a/arch/arm64/include/uapi/asm/hwcap.h b/arch/arm64/include/uapi/asm/hwcap.h index 06f83ca8de56..10272ddb4d6f 100644 --- a/arch/arm64/include/uapi/asm/hwcap.h +++ b/arch/arm64/include/uapi/asm/hwcap.h @@ -147,5 +147,13 @@ #define HWCAP3_MTE_STORE_ONLY (1UL << 1) #define HWCAP3_LSFE (1UL << 2) #define HWCAP3_LS64 (1UL << 3) +#define HWCAP3_SVE_B16MM (1UL << 4) +#define HWCAP3_SVE2P3 (1UL << 5) +#define HWCAP3_SME_LUT6 (1UL << 6) +#define HWCAP3_SME2P3 (1UL << 7) +#define HWCAP3_F16MM (1UL << 8) +#define HWCAP3_F16F32DOT (1UL << 9) +#define HWCAP3_F16F32MM (1UL << 10) +#define HWCAP3_SVE_LUT6 (1UL << 11) #endif /* _UAPI__ASM_HWCAP_H */ diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c index 6d53bb15cf7b..96de16582fca 100644 --- a/arch/arm64/kernel/cpufeature.c +++ b/arch/arm64/kernel/cpufeature.c @@ -365,6 +365,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = { static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_FA64_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), + FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_LUT6_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_LUTv2_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME), @@ -419,6 +421,7 @@ static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = { ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP2_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM8_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8MM4_SHIFT, 1, 0), + ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F16MM2_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E4M3_SHIFT, 1, 0), ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0), ARM64_FTR_END, @@ -3284,6 +3287,8 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SM4), HWCAP_CAP(ID_AA64ISAR0_EL1, DP, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDDP), HWCAP_CAP(ID_AA64ISAR0_EL1, FHM, IMP, CAP_HWCAP, KERNEL_HWCAP_ASIMDFHM), + HWCAP_CAP(ID_AA64ISAR0_EL1, FHM, F16F32DOT, CAP_HWCAP, KERNEL_HWCAP_F16F32DOT), + HWCAP_CAP(ID_AA64ISAR0_EL1, FHM, F16F32MM, CAP_HWCAP, KERNEL_HWCAP_F16F32MM), HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM, CAP_HWCAP, KERNEL_HWCAP_FLAGM), HWCAP_CAP(ID_AA64ISAR0_EL1, TS, FLAGM2, CAP_HWCAP, KERNEL_HWCAP_FLAGM2), HWCAP_CAP(ID_AA64ISAR0_EL1, RNDR, IMP, CAP_HWCAP, KERNEL_HWCAP_RNG), @@ -3313,7 +3318,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64ISAR3_EL1, LSFE, IMP, CAP_HWCAP, KERNEL_HWCAP_LSFE), HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT), #ifdef CONFIG_ARM64_SVE + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ISAR2_EL1, LUT, LUT6, CAP_HWCAP, KERNEL_HWCAP_SVE_LUT6), HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p3, CAP_HWCAP, KERNEL_HWCAP_SVE2P3), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p2, CAP_HWCAP, KERNEL_HWCAP_SVE2P2), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2p1, CAP_HWCAP, KERNEL_HWCAP_SVE2P1), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SVEver, SVE2, CAP_HWCAP, KERNEL_HWCAP_SVE2), @@ -3323,6 +3330,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBITPERM), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_B16B16), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, BFSCALE, CAP_HWCAP, KERNEL_HWCAP_SVE_BFSCALE), + HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, B16B16, B16MM, CAP_HWCAP, KERNEL_HWCAP_SVE_B16MM), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEBF16), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, BF16, EBF16, CAP_HWCAP, KERNEL_HWCAP_SVE_EBF16), HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SHA3, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESHA3), @@ -3362,7 +3370,9 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { #ifdef CONFIG_ARM64_SME HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME), HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUT6, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUT6), HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2), + HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p3, CAP_HWCAP, KERNEL_HWCAP_SME2P3), HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2), HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1), HWCAP_CAP_MATCH_ID(has_sme_feature, ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2), @@ -3393,6 +3403,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = { HWCAP_CAP(ID_AA64FPFR0_EL1, F8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8DP2), HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM8), HWCAP_CAP(ID_AA64FPFR0_EL1, F8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_F8MM4), + HWCAP_CAP(ID_AA64FPFR0_EL1, F16MM2, IMP, CAP_HWCAP, KERNEL_HWCAP_F16MM), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E4M3, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E4M3), HWCAP_CAP(ID_AA64FPFR0_EL1, F8E5M2, IMP, CAP_HWCAP, KERNEL_HWCAP_F8E5M2), #ifdef CONFIG_ARM64_POE diff --git a/arch/arm64/kernel/cpuinfo.c b/arch/arm64/kernel/cpuinfo.c index 6149bc91251d..d50e2a9b066b 100644 --- a/arch/arm64/kernel/cpuinfo.c +++ b/arch/arm64/kernel/cpuinfo.c @@ -164,6 +164,14 @@ static const char *const hwcap_str[] = { [KERNEL_HWCAP_MTE_FAR] = "mtefar", [KERNEL_HWCAP_MTE_STORE_ONLY] = "mtestoreonly", [KERNEL_HWCAP_LSFE] = "lsfe", + [KERNEL_HWCAP_SVE_B16MM] = "sveb16mm", + [KERNEL_HWCAP_SVE2P3] = "sve2p3", + [KERNEL_HWCAP_SME_LUT6] = "smelut6", + [KERNEL_HWCAP_SME2P3] = "sme2p3", + [KERNEL_HWCAP_F16MM] = "f16mm", + [KERNEL_HWCAP_F16F32DOT] = "f16f32dot", + [KERNEL_HWCAP_F16F32MM] = "f16f32mm", + [KERNEL_HWCAP_SVE_LUT6] = "svelut6", }; #ifdef CONFIG_COMPAT From f20f8fe086b2487ff70562866c4a30b1d9a66a37 Mon Sep 17 00:00:00 2001 From: Mark Brown Date: Fri, 22 May 2026 18:50:28 +0100 Subject: [PATCH 2/2] arm64: Document SVE constraints on new hwcaps Two of the SVE hwcaps added for the SVE features in the 2025 dpISA did not explicitly call out their dependency on SVE in the ABI documentation. Do so. While we're here reorder the SVE and fature specific ID registers for HWCAP3_SVE_LUT6 which did have the SVE dependency but listed it second unlike the other SVE specific ID registers. Fixes: abca5e69ab62 ("arm64/cpufeature: Define hwcaps for 2025 dpISA features") Reported-by: Will Deacon Signed-off-by: Mark Brown Signed-off-by: Will Deacon --- Documentation/arch/arm64/elf_hwcaps.rst | 11 +++++++---- 1 file changed, 7 insertions(+), 4 deletions(-) diff --git a/Documentation/arch/arm64/elf_hwcaps.rst b/Documentation/arch/arm64/elf_hwcaps.rst index 07ff9ea1d605..f60ca5612daa 100644 --- a/Documentation/arch/arm64/elf_hwcaps.rst +++ b/Documentation/arch/arm64/elf_hwcaps.rst @@ -452,10 +452,12 @@ HWCAP3_LS64 memory location, otherwise fallback to the non-atomic alternatives. HWCAP3_SVE_B16MM - Functionality implied by ID_AA64ZFR0_EL1.B16B16 == 0b0011 + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.B16B16 == 0b0011 HWCAP3_SVE2P3 - Functionality implied by ID_AA64ZFR0_EL1.SVEver == 0b0100 + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ZFR0_EL1.SVEver == 0b0100 HWCAP3_SME_LUT6 Functionality implied by ID_AA64SMFR0_EL1.LUT6 == 0b1 @@ -473,8 +475,9 @@ HWCAP3_F16F32MM Functionality implied by ID_AA64ISAR0_EL1.FHM == 0b0011 HWCAP3_SVE_LUT6 - Functionality implied by ID_AA64ISAR2_EL1.LUT == 0b0010 and - ID_AA64PFR0_EL1.SVE == 0b0001. + Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and + ID_AA64ISAR2_EL1.LUT == 0b0010. + 4. Unused AT_HWCAP bits -----------------------