arm64/hwcap: Describe 2024 dpISA extensions to userspace

The 2024 dpISA introduces a number of architecture features all of which
only add new instructions so only require the addition of hwcaps and ID
register visibility.

Signed-off-by: Mark Brown <[email protected]>
Link: https://lore.kernel.org/r/[email protected]
Signed-off-by: Will Deacon <[email protected]>

Author: broonie

Documentation/arch/arm64/elf_hwcaps.rst

@@ -174,6 +174,56 @@ HWCAP_GCS
     Functionality implied by ID_AA64PFR1_EL1.GCS == 0b1, as
     described by Documentation/arch/arm64/gcs.rst.
 
+HWCAP_CMPBR
+    Functionality implied by ID_AA64ISAR2_EL1.CSSC == 0b0010.
+
+HWCAP_FPRCVT
+    Functionality implied by ID_AA64ISAR3_EL1.FPRCVT == 0b0001.
+
+HWCAP_F8MM8
+    Functionality implied by ID_AA64FPFR0_EL1.F8MM8 == 0b0001.
+
+HWCAP_F8MM4
+    Functionality implied by ID_AA64FPFR0_EL1.F8MM4 == 0b0001.
+
+HWCAP_SVE_F16MM
+    Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and
+    ID_AA64ZFR0_EL1.F16MM == 0b0001.
+
+HWCAP_SVE_ELTPERM
+    Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and
+    ID_AA64ZFR0_EL1.ELTPERM == 0b0001.
+
+HWCAP_SVE_AES2
+    Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and
+    ID_AA64ZFR0_EL1.AES == 0b0011.
+
+HWCAP_SVE_BFSCALE
+    Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and
+    ID_AA64ZFR0_EL1.B16B16 == 0b0010.
+
+HWCAP_SVE2P2
+    Functionality implied by ID_AA64PFR0_EL1.SVE == 0b0001 and
+    ID_AA64ZFR0_EL1.SVEver == 0b0011.
+
+HWCAP_SME2P2
+    Functionality implied by ID_AA64SMFR0_EL1.SMEver == 0b0011.
+
+HWCAP_SME_SBITPERM
+    Functionality implied by ID_AA64SMFR0_EL1.SBitPerm == 0b1.
+
+HWCAP_SME_AES
+    Functionality implied by ID_AA64SMFR0_EL1.AES == 0b1.
+
+HWCAP_SME_SFEXPA
+    Functionality implied by ID_AA64SMFR0_EL1.SFEXPA == 0b1.
+
+HWCAP_SME_STMOP
+    Functionality implied by ID_AA64SMFR0_EL1.STMOP == 0b1.
+
+HWCAP_SME_SMOP4
+    Functionality implied by ID_AA64SMFR0_EL1.SMOP4 == 0b1.
+
 HWCAP2_DCPODP
     Functionality implied by ID_AA64ISAR1_EL1.DPB == 0b0010.
 

arch/arm64/include/asm/hwcap.h

@@ -93,6 +93,21 @@
 #define KERNEL_HWCAP_PACA		__khwcap_feature(PACA)
 #define KERNEL_HWCAP_PACG		__khwcap_feature(PACG)
 #define KERNEL_HWCAP_GCS		__khwcap_feature(GCS)
+#define KERNEL_HWCAP_CMPBR		__khwcap_feature(CMPBR)
+#define KERNEL_HWCAP_FPRCVT		__khwcap_feature(FPRCVT)
+#define KERNEL_HWCAP_F8MM8		__khwcap_feature(F8MM8)
+#define KERNEL_HWCAP_F8MM4		__khwcap_feature(F8MM4)
+#define KERNEL_HWCAP_SVE_F16MM		__khwcap_feature(SVE_F16MM)
+#define KERNEL_HWCAP_SVE_ELTPERM	__khwcap_feature(SVE_ELTPERM)
+#define KERNEL_HWCAP_SVE_AES2		__khwcap_feature(SVE_AES2)
+#define KERNEL_HWCAP_SVE_BFSCALE	__khwcap_feature(SVE_BFSCALE)
+#define KERNEL_HWCAP_SVE2P2		__khwcap_feature(SVE2P2)
+#define KERNEL_HWCAP_SME2P2		__khwcap_feature(SME2P2)
+#define KERNEL_HWCAP_SME_SBITPERM	__khwcap_feature(SME_SBITPERM)
+#define KERNEL_HWCAP_SME_AES		__khwcap_feature(SME_AES)
+#define KERNEL_HWCAP_SME_SFEXPA		__khwcap_feature(SME_SFEXPA)
+#define KERNEL_HWCAP_SME_STMOP		__khwcap_feature(SME_STMOP)
+#define KERNEL_HWCAP_SME_SMOP4		__khwcap_feature(SME_SMOP4)
 
 #define __khwcap2_feature(x)		(const_ilog2(HWCAP2_ ## x) + 64)
 #define KERNEL_HWCAP_DCPODP		__khwcap2_feature(DCPODP)

arch/arm64/include/uapi/asm/hwcap.h

@@ -56,6 +56,21 @@
 #define HWCAP_PACA		(1 << 30)
 #define HWCAP_PACG		(1UL << 31)
 #define HWCAP_GCS		(1UL << 32)
+#define HWCAP_CMPBR		(1UL << 33)
+#define HWCAP_FPRCVT		(1UL << 34)
+#define HWCAP_F8MM8		(1UL << 35)
+#define HWCAP_F8MM4		(1UL << 36)
+#define HWCAP_SVE_F16MM		(1UL << 37)
+#define HWCAP_SVE_ELTPERM	(1UL << 38)
+#define HWCAP_SVE_AES2		(1UL << 39)
+#define HWCAP_SVE_BFSCALE	(1UL << 40)
+#define HWCAP_SVE2P2		(1UL << 41)
+#define HWCAP_SME2P2		(1UL << 42)
+#define HWCAP_SME_SBITPERM	(1UL << 43)
+#define HWCAP_SME_AES		(1UL << 44)
+#define HWCAP_SME_SFEXPA	(1UL << 45)
+#define HWCAP_SME_STMOP		(1UL << 46)
+#define HWCAP_SME_SMOP4		(1UL << 47)
 
 /*
  * HWCAP2 flags - for AT_HWCAP2

arch/arm64/kernel/cpufeature.c

@@ -268,6 +268,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
 };
 
 static const struct arm64_ftr_bits ftr_id_aa64isar3[] = {
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FPRCVT_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR3_EL1_FAMINMAX_SHIFT, 4, 0),
 	ARM64_FTR_END,
 };
@@ -317,6 +318,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F64MM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F32MM_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_F16MM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_I8MM_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
@@ -329,6 +332,8 @@ static const struct arm64_ftr_bits ftr_id_aa64zfr0[] = {
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BF16_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_BitPerm_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
+		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_EltPerm_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
 		       FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ZFR0_EL1_AES_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SVE),
@@ -373,6 +378,16 @@ static const struct arm64_ftr_bits ftr_id_aa64smfr0[] = {
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP4_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SF8DP2_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SBitPerm_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_AES_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SFEXPA_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_STMOP_SHIFT, 1, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
+		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_SMOP4_SHIFT, 1, 0),
 	ARM64_FTR_END,
 };
 
@@ -381,6 +396,8 @@ static const struct arm64_ftr_bits ftr_id_aa64fpfr0[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8FMA_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8DP4_SHIFT, 1, 0),
 	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_F8E4M3_SHIFT, 1, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_EXACT, ID_AA64FPFR0_EL1_F8E5M2_SHIFT, 1, 0),
 	ARM64_FTR_END,
@@ -3092,19 +3109,24 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64MMFR2_EL1, AT, IMP, CAP_HWCAP, KERNEL_HWCAP_USCAT),
 #ifdef CONFIG_ARM64_SVE
 	HWCAP_CAP(ID_AA64PFR0_EL1, SVE, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE),
+	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),
 	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEAES),
 	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, PMULL128, CAP_HWCAP, KERNEL_HWCAP_SVEPMULL),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, AES, AES2, CAP_HWCAP, KERNEL_HWCAP_SVE_AES2),
 	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, 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),
 	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, SM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SVESM4),
 	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, I8MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEI8MM),
 	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F32MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF32MM),
 	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F64MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVEF64MM),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, F16MM, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_F16MM),
+	HWCAP_CAP_MATCH_ID(has_sve_feature, ID_AA64ZFR0_EL1, EltPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SVE_ELTPERM),
 #endif
 #ifdef CONFIG_ARM64_GCS
 	HWCAP_CAP(ID_AA64PFR1_EL1, GCS, IMP, CAP_HWCAP, KERNEL_HWCAP_GCS),
@@ -3124,6 +3146,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64MMFR0_EL1, ECV, IMP, CAP_HWCAP, KERNEL_HWCAP_ECV),
 	HWCAP_CAP(ID_AA64MMFR1_EL1, AFP, IMP, CAP_HWCAP, KERNEL_HWCAP_AFP),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, IMP, CAP_HWCAP, KERNEL_HWCAP_CSSC),
+	HWCAP_CAP(ID_AA64ISAR2_EL1, CSSC, CMPBR, CAP_HWCAP, KERNEL_HWCAP_CMPBR),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, RPRFM, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRFM),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
@@ -3133,6 +3156,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64PFR1_EL1, SME, IMP, CAP_HWCAP, KERNEL_HWCAP_SME),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, FA64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_FA64),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, LUTv2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_LUTV2),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p2, CAP_HWCAP, KERNEL_HWCAP_SME2P2),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2p1, CAP_HWCAP, KERNEL_HWCAP_SME2P1),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SMEver, SME2, CAP_HWCAP, KERNEL_HWCAP_SME2),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, I16I64, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_I16I64),
@@ -3150,6 +3174,13 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8FMA),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP4),
 	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8DP2, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8DP2),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM8, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM8),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SF8MM4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SF8MM4),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SBitPerm, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SBITPERM),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, AES, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_AES),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SFEXPA, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SFEXPA),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, STMOP, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_STMOP),
+	HWCAP_CAP(ID_AA64SMFR0_EL1, SMOP4, IMP, CAP_HWCAP, KERNEL_HWCAP_SME_SMOP4),
 #endif /* CONFIG_ARM64_SME */
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8CVT, IMP, CAP_HWCAP, KERNEL_HWCAP_F8CVT),
 	HWCAP_CAP(ID_AA64FPFR0_EL1, F8FMA, IMP, CAP_HWCAP, KERNEL_HWCAP_F8FMA),

arch/arm64/kernel/cpuinfo.c

@@ -145,6 +145,21 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_SME_SF8DP4]	= "smesf8dp4",
 	[KERNEL_HWCAP_SME_SF8DP2]	= "smesf8dp2",
 	[KERNEL_HWCAP_POE]		= "poe",
+	[KERNEL_HWCAP_CMPBR]		= "cmpbr",
+	[KERNEL_HWCAP_FPRCVT]		= "fprcvt",
+	[KERNEL_HWCAP_F8MM8]		= "f8mm8",
+	[KERNEL_HWCAP_F8MM4]		= "f8mm4",
+	[KERNEL_HWCAP_SVE_F16MM]	= "svef16mm",
+	[KERNEL_HWCAP_SVE_ELTPERM]	= "sveeltperm",
+	[KERNEL_HWCAP_SVE_AES2]		= "sveaes2",
+	[KERNEL_HWCAP_SVE_BFSCALE]	= "svebfscale",
+	[KERNEL_HWCAP_SVE2P2]		= "sve2p2",
+	[KERNEL_HWCAP_SME2P2]		= "sme2p2",
+	[KERNEL_HWCAP_SME_SBITPERM]	= "smesbitperm",
+	[KERNEL_HWCAP_SME_AES]		= "smeaes",
+	[KERNEL_HWCAP_SME_SFEXPA]	= "smesfexpa",
+	[KERNEL_HWCAP_SME_STMOP]	= "smestmop",
+	[KERNEL_HWCAP_SME_SMOP4]	= "smesmop4",
 };
 
 #ifdef CONFIG_COMPAT