arm64: perf: Add support caps under sysfs

ARMv8.4-PMU introduces the PMMIR_EL1 registers and some new PMU events,
like STALL_SLOT etc, are related to it. Let's add a caps directory to
/sys/bus/event_source/devices/armv8_pmuv3_0/ and support slots from
PMMIR_EL1 registers in this entry. The user programs can get the slots
from sysfs directly.

/sys/bus/event_source/devices/armv8_pmuv3_0/caps/slots is exposed
under sysfs. Both ARMv8.4-PMU and STALL_SLOT event are implemented,
it returns the slots from PMMIR_EL1, otherwise it will return 0.
Signed-off-by: Shaokun Zhang <zhangshaokun@hisilicon.com>
Cc: Will Deacon <will@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Link: https://lore.kernel.org/r/1600754025-53535-1-git-send-email-zhangshaokun@hisilicon.comSigned-off-by: Will Deacon <will@kernel.org>

arch/arm64/include/asm/perf_event.h

@@ -236,6 +236,9 @@
 #define ARMV8_PMU_USERENR_CR	(1 << 2) /* Cycle counter can be read at EL0 */
 #define ARMV8_PMU_USERENR_ER	(1 << 3) /* Event counter can be read at EL0 */
 
+/* PMMIR_EL1.SLOTS mask */
+#define ARMV8_PMU_SLOTS_MASK	0xff
+
 #ifdef CONFIG_PERF_EVENTS
 struct pt_regs;
 extern unsigned long perf_instruction_pointer(struct pt_regs *regs);

arch/arm64/include/asm/sysreg.h

@@ -321,6 +321,8 @@
 #define SYS_PMINTENSET_EL1		sys_reg(3, 0, 9, 14, 1)
 #define SYS_PMINTENCLR_EL1		sys_reg(3, 0, 9, 14, 2)
 
+#define SYS_PMMIR_EL1			sys_reg(3, 0, 9, 14, 6)
+
 #define SYS_MAIR_EL1			sys_reg(3, 0, 10, 2, 0)
 #define SYS_AMAIR_EL1			sys_reg(3, 0, 10, 3, 0)
 

arch/arm64/kernel/perf_event.c

@@ -305,6 +305,28 @@ static struct attribute_group armv8_pmuv3_format_attr_group = {
 	.attrs = armv8_pmuv3_format_attrs,
 };
 
+static ssize_t slots_show(struct device *dev, struct device_attribute *attr,
+			  char *page)
+{
+	struct pmu *pmu = dev_get_drvdata(dev);
+	struct arm_pmu *cpu_pmu = container_of(pmu, struct arm_pmu, pmu);
+	u32 slots = cpu_pmu->reg_pmmir & ARMV8_PMU_SLOTS_MASK;
+
+	return snprintf(page, PAGE_SIZE, "0x%08x\n", slots);
+}
+
+static DEVICE_ATTR_RO(slots);
+
+static struct attribute *armv8_pmuv3_caps_attrs[] = {
+	&dev_attr_slots.attr,
+	NULL,
+};
+
+static struct attribute_group armv8_pmuv3_caps_attr_group = {
+	.name = "caps",
+	.attrs = armv8_pmuv3_caps_attrs,
+};
+
 /*
  * Perf Events' indices
  */
@@ -984,6 +1006,12 @@ static void __armv8pmu_probe_pmu(void *info)
 
 	bitmap_from_arr32(cpu_pmu->pmceid_ext_bitmap,
 			     pmceid, ARMV8_PMUV3_MAX_COMMON_EVENTS);
+
+	/* store PMMIR_EL1 register for sysfs */
+	if (pmuver >= ID_AA64DFR0_PMUVER_8_4 && (pmceid_raw[1] & BIT(31)))
+		cpu_pmu->reg_pmmir = read_cpuid(PMMIR_EL1);
+	else
+		cpu_pmu->reg_pmmir = 0;
 }
 
 static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
@@ -1006,7 +1034,8 @@ static int armv8pmu_probe_pmu(struct arm_pmu *cpu_pmu)
 static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			  int (*map_event)(struct perf_event *event),
 			  const struct attribute_group *events,
-			  const struct attribute_group *format)
+			  const struct attribute_group *format,
+			  const struct attribute_group *caps)
 {
 	int ret = armv8pmu_probe_pmu(cpu_pmu);
 	if (ret)
@@ -1031,104 +1060,112 @@ static int armv8_pmu_init(struct arm_pmu *cpu_pmu, char *name,
 			events : &armv8_pmuv3_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = format ?
 			format : &armv8_pmuv3_format_attr_group;
+	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_CAPS] = caps ?
+			caps : &armv8_pmuv3_caps_attr_group;
 
 	return 0;
 }
 
+static int armv8_pmu_init_nogroups(struct arm_pmu *cpu_pmu, char *name,
+				   int (*map_event)(struct perf_event *event))
+{
+	return armv8_pmu_init(cpu_pmu, name, map_event, NULL, NULL, NULL);
+}
+
 static int armv8_pmuv3_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_pmuv3",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_pmuv3",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a34_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a34",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a34",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a35_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a35",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a35",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a53_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a53",
-			      armv8_a53_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a53",
+				       armv8_a53_map_event);
 }
 
 static int armv8_a55_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a55",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a55",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a57_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a57",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a57",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a65_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a65",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a65",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a72_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a72",
-			      armv8_a57_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a72",
+				       armv8_a57_map_event);
 }
 
 static int armv8_a73_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a73",
-			      armv8_a73_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a73",
+				       armv8_a73_map_event);
 }
 
 static int armv8_a75_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a75",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a75",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a76_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a76",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a76",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_a77_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cortex_a77",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cortex_a77",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_e1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_e1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_e1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_n1_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_neoverse_n1",
-			      armv8_pmuv3_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_neoverse_n1",
+				       armv8_pmuv3_map_event);
 }
 
 static int armv8_thunder_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_cavium_thunder",
-			      armv8_thunder_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_cavium_thunder",
+				       armv8_thunder_map_event);
 }
 
 static int armv8_vulcan_pmu_init(struct arm_pmu *cpu_pmu)
 {
-	return armv8_pmu_init(cpu_pmu, "armv8_brcm_vulcan",
-			      armv8_vulcan_map_event, NULL, NULL);
+	return armv8_pmu_init_nogroups(cpu_pmu, "armv8_brcm_vulcan",
+				       armv8_vulcan_map_event);
 }
 
 static const struct of_device_id armv8_pmu_of_device_ids[] = {

include/linux/perf/arm_pmu.h

@@ -73,6 +73,7 @@ enum armpmu_attr_groups {
 	ARMPMU_ATTR_GROUP_COMMON,
 	ARMPMU_ATTR_GROUP_EVENTS,
 	ARMPMU_ATTR_GROUP_FORMATS,
+	ARMPMU_ATTR_GROUP_CAPS,
 	ARMPMU_NR_ATTR_GROUPS
 };
 
@@ -109,6 +110,8 @@ struct arm_pmu {
 	struct notifier_block	cpu_pm_nb;
 	/* the attr_groups array must be NULL-terminated */
 	const struct attribute_group *attr_groups[ARMPMU_NR_ATTR_GROUPS + 1];
+	/* store the PMMIR_EL1 to expose slots */
+	u64		reg_pmmir;
 
 	/* Only to be used by ACPI probing code */
 	unsigned long acpi_cpuid;