arm64/sve: Probe SVE capabilities and usable vector lengths

This patch uses the cpufeatures framework to determine common SVE
capabilities and vector lengths, and configures the runtime SVE
support code appropriately.

ZCR_ELx is not really a feature register, but it is convenient to
use it as a template for recording the maximum vector length
supported by a CPU, using the LEN field.  This field is similar to
a feature field in that it is a contiguous bitfield for which we
want to determine the minimum system-wide value.  This patch adds
ZCR as a pseudo-register in cpuinfo/cpufeatures, with appropriate
custom code to populate it.  Finding the minimum supported value of
the LEN field is left to the cpufeatures framework in the usual
way.

The meaning of ID_AA64ZFR0_EL1 is not architecturally defined yet,
so for now we just require it to be zero.

Note that much of this code is dormant and SVE still won't be used
yet, since system_supports_sve() remains hardwired to false.

Signed-off-by: Dave Martin <Dave.Martin@arm.com>
Reviewed-by: Suzuki K Poulose <suzuki.poulose@arm.com>
Reviewed-by: Catalin Marinas <catalin.marinas@arm.com>
Cc: Alex Bennée <alex.bennee@linaro.org>
Signed-off-by: Will Deacon <will.deacon@arm.com>

1 files changed, 52 insertions, 0 deletions

diff --git a/arch/arm64/kernel/cpufeature.c b/arch/arm64/kernel/cpufeature.c
index 0e192cbe4149..036ad9d1b442 100644
--- a/arch/arm64/kernel/cpufeature.c
+++ b/arch/arm64/kernel/cpufeature.c
@@ -27,6 +27,7 @@
 #include <asm/cpu.h>
 #include <asm/cpufeature.h>
 #include <asm/cpu_ops.h>
+#include <asm/fpsimd.h>
 #include <asm/mmu_context.h>
 #include <asm/processor.h>
 #include <asm/sysreg.h>
@@ -287,6 +288,12 @@ static const struct arm64_ftr_bits ftr_id_dfr0[] = {
 	ARM64_FTR_END,
 };
 
+static const struct arm64_ftr_bits ftr_zcr[] = {
+	ARM64_FTR_BITS(FTR_HIDDEN, FTR_NONSTRICT, FTR_LOWER_SAFE,
+		ZCR_ELx_LEN_SHIFT, ZCR_ELx_LEN_SIZE, 0),	/* LEN */
+	ARM64_FTR_END,
+};
+
 /*
  * Common ftr bits for a 32bit register with all hidden, strict
  * attributes, with 4bit feature fields and a default safe value of
@@ -353,6 +360,7 @@ 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_raz),
+	ARM64_FTR_REG(SYS_ID_AA64ZFR0_EL1, ftr_raz),
 
 	/* Op1 = 0, CRn = 0, CRm = 5 */
 	ARM64_FTR_REG(SYS_ID_AA64DFR0_EL1, ftr_id_aa64dfr0),
@@ -367,6 +375,9 @@ static const struct __ftr_reg_entry {
 	ARM64_FTR_REG(SYS_ID_AA64MMFR1_EL1, ftr_id_aa64mmfr1),
 	ARM64_FTR_REG(SYS_ID_AA64MMFR2_EL1, ftr_id_aa64mmfr2),
 
+	/* Op1 = 0, CRn = 1, CRm = 2 */
+	ARM64_FTR_REG(SYS_ZCR_EL1, ftr_zcr),
+
 	/* Op1 = 3, CRn = 0, CRm = 0 */
 	{ SYS_CTR_EL0, &arm64_ftr_reg_ctrel0 },
 	ARM64_FTR_REG(SYS_DCZID_EL0, ftr_dczid),
@@ -504,6 +515,7 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 	init_cpu_ftr_reg(SYS_ID_AA64MMFR2_EL1, info->reg_id_aa64mmfr2);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR0_EL1, info->reg_id_aa64pfr0);
 	init_cpu_ftr_reg(SYS_ID_AA64PFR1_EL1, info->reg_id_aa64pfr1);
+	init_cpu_ftr_reg(SYS_ID_AA64ZFR0_EL1, info->reg_id_aa64zfr0);
 
 	if (id_aa64pfr0_32bit_el0(info->reg_id_aa64pfr0)) {
 		init_cpu_ftr_reg(SYS_ID_DFR0_EL1, info->reg_id_dfr0);
@@ -524,6 +536,10 @@ void __init init_cpu_features(struct cpuinfo_arm64 *info)
 		init_cpu_ftr_reg(SYS_MVFR2_EL1, info->reg_mvfr2);
 	}
 
+	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
+		init_cpu_ftr_reg(SYS_ZCR_EL1, info->reg_zcr);
+		sve_init_vq_map();
+	}
 }
 
 static void update_cpu_ftr_reg(struct arm64_ftr_reg *reg, u64 new)
@@ -627,6 +643,9 @@ void update_cpu_features(int cpu,
 	taint |= check_update_ftr_reg(SYS_ID_AA64PFR1_EL1, cpu,
 				      info->reg_id_aa64pfr1, boot->reg_id_aa64pfr1);
 
+	taint |= check_update_ftr_reg(SYS_ID_AA64ZFR0_EL1, cpu,
+				      info->reg_id_aa64zfr0, boot->reg_id_aa64zfr0);
+
 	/*
 	 * If we have AArch32, we care about 32-bit features for compat.
 	 * If the system doesn't support AArch32, don't update them.
@@ -674,6 +693,16 @@ void update_cpu_features(int cpu,
 					info->reg_mvfr2, boot->reg_mvfr2);
 	}
 
+	if (id_aa64pfr0_sve(info->reg_id_aa64pfr0)) {
+		taint |= check_update_ftr_reg(SYS_ZCR_EL1, cpu,
+					info->reg_zcr, boot->reg_zcr);
+
+		/* Probe vector lengths, unless we already gave up on SVE */
+		if (id_aa64pfr0_sve(read_sanitised_ftr_reg(SYS_ID_AA64PFR0_EL1)) &&
+		    !sys_caps_initialised)
+			sve_update_vq_map();
+	}
+
 	/*
 	 * Mismatched CPU features are a recipe for disaster. Don't even
 	 * pretend to support them.
@@ -1106,6 +1135,23 @@ verify_local_cpu_features(const struct arm64_cpu_capabilities *caps)
 	}
 }
 
+static void verify_sve_features(void)
+{
+	u64 safe_zcr = read_sanitised_ftr_reg(SYS_ZCR_EL1);
+	u64 zcr = read_zcr_features();
+
+	unsigned int safe_len = safe_zcr & ZCR_ELx_LEN_MASK;
+	unsigned int len = zcr & ZCR_ELx_LEN_MASK;
+
+	if (len < safe_len || sve_verify_vq_map()) {
+		pr_crit("CPU%d: SVE: required vector length(s) missing\n",
+			smp_processor_id());
+		cpu_die_early();
+	}
+
+	/* Add checks on other ZCR bits here if necessary */
+}
+
 /*
  * Run through the enabled system capabilities and enable() it on this CPU.
  * The capabilities were decided based on the available CPUs at the boot time.
@@ -1119,8 +1165,12 @@ static void verify_local_cpu_capabilities(void)
 	verify_local_cpu_errata_workarounds();
 	verify_local_cpu_features(arm64_features);
 	verify_local_elf_hwcaps(arm64_elf_hwcaps);
+
 	if (system_supports_32bit_el0())
 		verify_local_elf_hwcaps(compat_elf_hwcaps);
+
+	if (system_supports_sve())
+		verify_sve_features();
 }
 
 void check_local_cpu_capabilities(void)
@@ -1198,6 +1248,8 @@ void __init setup_cpu_features(void)
 	if (system_supports_32bit_el0())
 		setup_elf_hwcaps(compat_elf_hwcaps);
 
+	sve_setup();
+
 	/* Advertise that we have computed the system capabilities */
 	set_sys_caps_initialised();