Merge branch 'for-next/cpufeature' into for-next/core

* for-next/cpufeature:
  arm64/fpsimd: Only provide the length to cpufeature for xCR registers
  selftests/arm64: add HWCAP2_HBC test
  arm64: add HWCAP for FEAT_HBC (hinted conditional branches)
  arm64/cpufeature: Use ARM64_CPUID_FIELD() to match EVT

Author: willdeacon

arch/arm64/include/asm/hwcap.h

@@ -138,6 +138,7 @@
 #define KERNEL_HWCAP_SME_B16B16		__khwcap2_feature(SME_B16B16)
 #define KERNEL_HWCAP_SME_F16F16		__khwcap2_feature(SME_F16F16)
 #define KERNEL_HWCAP_MOPS		__khwcap2_feature(MOPS)
+#define KERNEL_HWCAP_HBC		__khwcap2_feature(HBC)
 
 /*
  * This yields a mask that user programs can use to figure out what

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

@@ -103,5 +103,6 @@
 #define HWCAP2_SME_B16B16	(1UL << 41)
 #define HWCAP2_SME_F16F16	(1UL << 42)
 #define HWCAP2_MOPS		(1UL << 43)
+#define HWCAP2_HBC		(1UL << 44)
 
 #endif /* _UAPI__ASM_HWCAP_H */

arch/arm64/kernel/cpufeature.c

@@ -222,7 +222,7 @@ static const struct arm64_ftr_bits ftr_id_aa64isar1[] = {
 static const struct arm64_ftr_bits ftr_id_aa64isar2[] = {
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_CSSC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_NONSTRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_RPRFM_SHIFT, 4, 0),
-	ARM64_FTR_BITS(FTR_HIDDEN, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
+	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_HIGHER_SAFE, ID_AA64ISAR2_EL1_BC_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE, FTR_STRICT, FTR_LOWER_SAFE, ID_AA64ISAR2_EL1_MOPS_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_PTR_AUTH),
 		       FTR_STRICT, FTR_EXACT, ID_AA64ISAR2_EL1_APA3_SHIFT, 4, 0),
@@ -2708,12 +2708,8 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.desc = "Enhanced Virtualization Traps",
 		.capability = ARM64_HAS_EVT,
 		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
-		.sys_reg = SYS_ID_AA64MMFR2_EL1,
-		.sign = FTR_UNSIGNED,
-		.field_pos = ID_AA64MMFR2_EL1_EVT_SHIFT,
-		.field_width = 4,
-		.min_field_value = ID_AA64MMFR2_EL1_EVT_IMP,
 		.matches = has_cpuid_feature,
+		ARM64_CPUID_FIELDS(ID_AA64MMFR2_EL1, EVT, IMP)
 	},
 	{},
 };
@@ -2844,6 +2840,7 @@ static const struct arm64_cpu_capabilities arm64_elf_hwcaps[] = {
 	HWCAP_CAP(ID_AA64ISAR2_EL1, RPRES, IMP, CAP_HWCAP, KERNEL_HWCAP_RPRES),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, WFxT, IMP, CAP_HWCAP, KERNEL_HWCAP_WFXT),
 	HWCAP_CAP(ID_AA64ISAR2_EL1, MOPS, IMP, CAP_HWCAP, KERNEL_HWCAP_MOPS),
+	HWCAP_CAP(ID_AA64ISAR2_EL1, BC, IMP, CAP_HWCAP, KERNEL_HWCAP_HBC),
 #ifdef CONFIG_ARM64_SME
 	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),

arch/arm64/kernel/cpuinfo.c

@@ -126,6 +126,7 @@ static const char *const hwcap_str[] = {
 	[KERNEL_HWCAP_SME_B16B16]	= "smeb16b16",
 	[KERNEL_HWCAP_SME_F16F16]	= "smef16f16",
 	[KERNEL_HWCAP_MOPS]		= "mops",
+	[KERNEL_HWCAP_HBC]		= "hbc",
 };
 
 #ifdef CONFIG_COMPAT

arch/arm64/kernel/fpsimd.c

@@ -1178,22 +1178,15 @@ void sve_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  */
 u64 read_zcr_features(void)
 {
-	u64 zcr;
-	unsigned int vq_max;
-
 	/*
 	 * Set the maximum possible VL, and write zeroes to all other
 	 * bits to see if they stick.
 	 */
 	sve_kernel_enable(NULL);
 	write_sysreg_s(ZCR_ELx_LEN_MASK, SYS_ZCR_EL1);
 
-	zcr = read_sysreg_s(SYS_ZCR_EL1);
-	zcr &= ~(u64)ZCR_ELx_LEN_MASK; /* find sticky 1s outside LEN field */
-	vq_max = sve_vq_from_vl(sve_get_vl());
-	zcr |= vq_max - 1; /* set LEN field to maximum effective value */
-
-	return zcr;
+	/* Return LEN value that would be written to get the maximum VL */
+	return sve_vq_from_vl(sve_get_vl()) - 1;
 }
 
 void __init sve_setup(void)
@@ -1348,9 +1341,6 @@ void fa64_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
  */
 u64 read_smcr_features(void)
 {
-	u64 smcr;
-	unsigned int vq_max;
-
 	sme_kernel_enable(NULL);
 
 	/*
@@ -1359,12 +1349,8 @@ u64 read_smcr_features(void)
 	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_LEN_MASK,
 		       SYS_SMCR_EL1);
 
-	smcr = read_sysreg_s(SYS_SMCR_EL1);
-	smcr &= ~(u64)SMCR_ELx_LEN_MASK; /* Only the LEN field */
-	vq_max = sve_vq_from_vl(sme_get_vl());
-	smcr |= vq_max - 1; /* set LEN field to maximum effective value */
-
-	return smcr;
+	/* Return LEN value that would be written to get the maximum VL */
+	return sve_vq_from_vl(sme_get_vl()) - 1;
 }
 
 void __init sme_setup(void)

tools/testing/selftests/arm64/abi/hwcap.c

@@ -208,6 +208,13 @@ static void svebf16_sigill(void)
 	asm volatile(".inst 0x658aa000" : : : "z0");
 }
 
+static void hbc_sigill(void)
+{
+	/* BC.EQ +4 */
+	asm volatile("cmp xzr, xzr\n"
+		     ".inst 0x54000030" : : : "cc");
+}
+
 static const struct hwcap_data {
 	const char *name;
 	unsigned long at_hwcap;
@@ -386,6 +393,14 @@ static const struct hwcap_data {
 		.hwcap_bit = HWCAP2_SVE_EBF16,
 		.cpuinfo = "sveebf16",
 	},
+	{
+		.name = "HBC",
+		.at_hwcap = AT_HWCAP2,
+		.hwcap_bit = HWCAP2_HBC,
+		.cpuinfo = "hbc",
+		.sigill_fn = hbc_sigill,
+		.sigill_reliable = true,
+	},
 };
 
 static bool seen_sigill;