perf: arm64: Add SVE vector granule register to user regs

Dwarf based unwinding in a function that pushes SVE registers onto
the stack requires the unwinder to know the length of the SVE register
to calculate the stack offsets correctly. This was added to the Arm
specific Dwarf spec as the VG pseudo register[1].

Add the vector length at position 46 if it's requested by userspace and
SVE is supported. If it's not supported then fail to open the event.

The vector length must be on each sample because it can be changed
at runtime via a prctl or ptrace call. Also by adding it as a register
rather than a separate attribute, minimal changes will be required in an
unwinder that already indexes into the register list.

[1]: https://github.com/ARM-software/abi-aa/blob/main/aadwarf64/aadwarf64.rstReviewed-by: Mark Brown <broonie@kernel.org>
Signed-off-by: James Clark <james.clark@arm.com>
Link: https://lore.kernel.org/r/20220901132658.1024635-2-james.clark@arm.comSigned-off-by: Will Deacon <will@kernel.org>

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

@@ -37,5 +37,12 @@ enum perf_event_arm_regs {
 	PERF_REG_ARM64_SP,
 	PERF_REG_ARM64_PC,
 	PERF_REG_ARM64_MAX,
+
+	/* Extended/pseudo registers */
+	PERF_REG_ARM64_VG = 46, // SVE Vector Granule
+	PERF_REG_ARM64_EXTENDED_MAX
 };
+
+#define PERF_REG_EXTENDED_MASK	(1ULL << PERF_REG_ARM64_VG)
+
 #endif /* _ASM_ARM64_PERF_REGS_H */

arch/arm64/kernel/perf_regs.c

@@ -9,9 +9,27 @@
 #include <asm/perf_regs.h>
 #include <asm/ptrace.h>
 
+static u64 perf_ext_regs_value(int idx)
+{
+	switch (idx) {
+	case PERF_REG_ARM64_VG:
+		if (WARN_ON_ONCE(!system_supports_sve()))
+			return 0;
+
+		/*
+		 * Vector granule is current length in bits of SVE registers
+		 * divided by 64.
+		 */
+		return (task_get_sve_vl(current) * 8) / 64;
+	default:
+		WARN_ON_ONCE(true);
+		return 0;
+	}
+}
+
 u64 perf_reg_value(struct pt_regs *regs, int idx)
 {
-	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_MAX))
+	if (WARN_ON_ONCE((u32)idx >= PERF_REG_ARM64_EXTENDED_MAX))
 		return 0;
 
 	/*
@@ -51,6 +69,9 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 	if ((u32)idx == PERF_REG_ARM64_PC)
 		return regs->pc;
 
+	if ((u32)idx >= PERF_REG_ARM64_MAX)
+		return perf_ext_regs_value(idx);
+
 	return regs->regs[idx];
 }
 
@@ -58,7 +79,12 @@ u64 perf_reg_value(struct pt_regs *regs, int idx)
 
 int perf_reg_validate(u64 mask)
 {
-	if (!mask || mask & REG_RESERVED)
+	u64 reserved_mask = REG_RESERVED;
+
+	if (system_supports_sve())
+		reserved_mask &= ~(1ULL << PERF_REG_ARM64_VG);
+
+	if (!mask || mask & reserved_mask)
 		return -EINVAL;
 
 	return 0;

drivers/perf/arm_pmu.c

@@ -894,7 +894,7 @@ static struct arm_pmu *__armpmu_alloc(gfp_t flags)
 		 * pmu::filter_match callback and pmu::event_init group
 		 * validation).
 		 */
-		.capabilities	= PERF_PMU_CAP_HETEROGENEOUS_CPUS,
+		.capabilities	= PERF_PMU_CAP_HETEROGENEOUS_CPUS | PERF_PMU_CAP_EXTENDED_REGS,
 	};
 
 	pmu->attr_groups[ARMPMU_ATTR_GROUP_COMMON] =