[PATCH v2 08/21] arm64/sme: Add basic enumeration for SME2

[Mark Brown]

Add basic feature detection for SME2, detecting that the feature is present
and disabling traps for ZT0.

Signed-off-by: Mark Brown <broonie at kernel.org>
---
 arch/arm64/include/asm/cpufeature.h |  6 ++++++
 arch/arm64/include/asm/fpsimd.h     |  1 +
 arch/arm64/kernel/cpufeature.c      | 14 ++++++++++++++
 arch/arm64/kernel/fpsimd.c          | 11 +++++++++++
 arch/arm64/tools/cpucaps            |  1 +
 5 files changed, 33 insertions(+)

diff --git a/arch/arm64/include/asm/cpufeature.h b/arch/arm64/include/asm/cpufeature.h
index f73f11b55042..3ad41c26c9e7 100644
--- a/arch/arm64/include/asm/cpufeature.h
+++ b/arch/arm64/include/asm/cpufeature.h
@@ -769,6 +769,12 @@ static __always_inline bool system_supports_sme(void)
 		cpus_have_const_cap(ARM64_SME);
 }
 
+static __always_inline bool system_supports_sme2(void)
+{
+	return IS_ENABLED(CONFIG_ARM64_SME) &&
+		cpus_have_const_cap(ARM64_SME2);
+}
+
 static __always_inline bool system_supports_fa64(void)
 {
 	return IS_ENABLED(CONFIG_ARM64_SME) &&
diff --git a/arch/arm64/include/asm/fpsimd.h b/arch/arm64/include/asm/fpsimd.h
index a18a86ccfd82..f2bda963cfe5 100644
--- a/arch/arm64/include/asm/fpsimd.h
+++ b/arch/arm64/include/asm/fpsimd.h
@@ -109,6 +109,7 @@ extern void za_load_state(void const *state);
 struct arm64_cpu_capabilities;
 extern void sve_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 extern void sme_kernel_enable(const struct arm64_cpu_capabilities *__unused);
+extern void sme2_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 extern void fa64_kernel_enable(const struct arm64_cpu_capabilities *__unused);
 
 extern u64 read_zcr_features(void);
diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index bb1ef8cf7d04..416785eeb512 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -282,6 +282,8 @@ 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_SMEver_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
 		       FTR_STRICT, FTR_EXACT, ID_AA64SMFR0_EL1_I16I64_SHIFT, 4, 0),
 	ARM64_FTR_BITS(FTR_VISIBLE_IF_IS_ENABLED(CONFIG_ARM64_SME),
@@ -2618,6 +2620,18 @@ static const struct arm64_cpu_capabilities arm64_features[] = {
 		.matches = has_cpuid_feature,
 		.cpu_enable = fa64_kernel_enable,
 	},
+	{
+		.desc = "SME2",
+		.type = ARM64_CPUCAP_SYSTEM_FEATURE,
+		.capability = ARM64_SME2,
+		.sys_reg = SYS_ID_AA64SMFR0_EL1,
+		.sign = FTR_UNSIGNED,
+		.field_pos = ID_AA64SMFR0_EL1_SMEver_SHIFT,
+		.field_width = ID_AA64SMFR0_EL1_SMEver_WIDTH,
+		.min_field_value = ID_AA64SMFR0_EL1_SMEver_SME2,
+		.matches = has_cpuid_feature,
+		.cpu_enable = sme2_kernel_enable,
+	},
 #endif /* CONFIG_ARM64_SME */
 	{
 		.desc = "WFx with timeout",
diff --git a/arch/arm64/kernel/fpsimd.c b/arch/arm64/kernel/fpsimd.c
index b677b5a3e0f6..73ec8850a402 100644
--- a/arch/arm64/kernel/fpsimd.c
+++ b/arch/arm64/kernel/fpsimd.c
@@ -1254,6 +1254,17 @@ void sme_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
 	isb();
 }
 
+/*
+ * This must be called after sme_kernel_enable(), we rely on the
+ * feature table being sorted to ensure this.
+ */
+void sme2_kernel_enable(const struct arm64_cpu_capabilities *__always_unused p)
+{
+	/* Allow use of ZT0 */
+	write_sysreg_s(read_sysreg_s(SYS_SMCR_EL1) | SMCR_ELx_EZT0_MASK,
+		       SYS_SMCR_EL1);
+}
+
 /*
  * This must be called after sme_kernel_enable(), we rely on the
  * feature table being sorted to ensure this.
diff --git a/arch/arm64/tools/cpucaps b/arch/arm64/tools/cpucaps
index f1c0347ec31a..79f511ef3195 100644
--- a/arch/arm64/tools/cpucaps
+++ b/arch/arm64/tools/cpucaps
@@ -49,6 +49,7 @@ MTE
 MTE_ASYMM
 SME
 SME_FA64
+SME2
 SPECTRE_V2
 SPECTRE_V3A
 SPECTRE_V4
-- 
2.30.2