perf: arm_pmuv3: Add support for Armv9.4 PMU instruction counter

Armv9.4/8.9 PMU adds optional support for a fixed instruction counter
similar to the fixed cycle counter. Support for the feature is indicated
in the ID_AA64DFR1_EL1 register PMICNTR field. The counter is not
accessible in AArch32.

Existing userspace using direct counter access won't know how to handle
the fixed instruction counter, so we have to avoid using the counter
when user access is requested.

Acked-by: Mark Rutland <mark.rutland@arm.com>
Signed-off-by: Rob Herring (Arm) <robh@kernel.org>
Tested-by: James Clark <james.clark@linaro.org>
Link: https://lore.kernel.org/r/20240731-arm-pmu-3-9-icntr-v3-7-280a8d7ff465@kernel.org
Signed-off-by: Will Deacon <will@kernel.org>

include/linux/perf/arm_pmu.h

@@ -17,10 +17,14 @@
 #ifdef CONFIG_ARM_PMU
 
 /*
- * The ARMv7 CPU PMU supports up to 32 event counters.
+ * The Armv7 and Armv8.8 or less CPU PMU supports up to 32 event counters.
+ * The Armv8.9/9.4 CPU PMU supports up to 33 event counters.
  */
+#ifdef CONFIG_ARM
 #define ARMPMU_MAX_HWEVENTS		32
-
+#else
+#define ARMPMU_MAX_HWEVENTS		33
+#endif
 /*
  * ARM PMU hw_event flags
  */

include/linux/perf/arm_pmuv3.h

@@ -8,7 +8,7 @@
 
 #define ARMV8_PMU_MAX_GENERAL_COUNTERS	31
 #define ARMV8_PMU_CYCLE_IDX		31
-
+#define ARMV8_PMU_INSTR_IDX		32 /* Not accessible from AArch32 */
 
 /*
  * Common architectural and microarchitectural event numbers.
@@ -228,8 +228,10 @@
  */
 #define ARMV8_PMU_OVSR_P		GENMASK(30, 0)
 #define ARMV8_PMU_OVSR_C		BIT(31)
+#define ARMV8_PMU_OVSR_F		BIT_ULL(32) /* arm64 only */
 /* Mask for writable bits is both P and C fields */
-#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C)
+#define ARMV8_PMU_OVERFLOWED_MASK	(ARMV8_PMU_OVSR_P | ARMV8_PMU_OVSR_C | \
+					ARMV8_PMU_OVSR_F)
 
 /*
  * PMXEVTYPER: Event selection reg