perf: starfive: Add StarLink PMU support

This patch adds support for StarFive's StarLink PMU (Performance
Monitor Unit). StarLink PMU integrates one or more CPU cores with
a shared L3 memory system. The PMU supports overflow interrupt,
up to 16 programmable 64bit event counters, and an independent
64bit cycle counter. StarLink PMU is accessed via MMIO.

Example Perf stat output:
[root@user]# perf stat -a -e /starfive_starlink_pmu/cycles/ \
	-e /starfive_starlink_pmu/read_miss/ \
	-e /starfive_starlink_pmu/read_hit/ \
	-e /starfive_starlink_pmu/release_request/  \
	-e /starfive_starlink_pmu/write_hit/ \
	-e /starfive_starlink_pmu/write_miss/ \
	-e /starfive_starlink_pmu/write_request/ \
	-e /starfive_starlink_pmu/writeback/ \
	-e /starfive_starlink_pmu/read_request/ \
	-- openssl speed rsa2048
Doing 2048 bits private rsa's for 10s: 5 2048 bits private RSA's in
2.84s
Doing 2048 bits public rsa's for 10s: 169 2048 bits public RSA's in
2.42s
version: 3.0.11
built on: Tue Sep 19 13:02:31 2023 UTC
options: bn(64,64)
CPUINFO: N/A
                  sign    verify    sign/s verify/s
rsa 2048 bits 0.568000s 0.014320s      1.8     69.8
/////////
 Performance counter stats for 'system wide':

         649991998      starfive_starlink_pmu/cycles/
           1009690      starfive_starlink_pmu/read_miss/
           1079750      starfive_starlink_pmu/read_hit/
           2089405      starfive_starlink_pmu/release_request/
               129      starfive_starlink_pmu/write_hit/
                70      starfive_starlink_pmu/write_miss/
               194      starfive_starlink_pmu/write_request/
            150080      starfive_starlink_pmu/writeback/
           2089423      starfive_starlink_pmu/read_request/

      27.062755678 seconds time elapsed
Signed-off-by: Ji Sheng Teoh <jisheng.teoh@starfivetech.com>
Link: https://lore.kernel.org/r/20240229072720.3987876-2-jisheng.teoh@starfivetech.comSigned-off-by: Will Deacon <will@kernel.org>

drivers/perf/Kconfig

@@ -86,6 +86,15 @@ config RISCV_PMU_SBI
 	  full perf feature support i.e. counter overflow, privilege mode
 	  filtering, counter configuration.
 
+config STARFIVE_STARLINK_PMU
+	depends on ARCH_STARFIVE || COMPILE_TEST
+	bool "StarFive StarLink PMU"
+	help
+	   Provide support for StarLink Performance Monitor Unit.
+	   StarLink Performance Monitor Unit integrates one or more cores with
+	   an L3 memory system. The L3 cache events are added into perf event
+	   subsystem, allowing monitoring of various L3 cache perf events.
+
 config ARM_PMU_ACPI
 	depends on ARM_PMU && ACPI
 	def_bool y

drivers/perf/Makefile

@@ -15,6 +15,7 @@ obj-$(CONFIG_QCOM_L3_PMU) += qcom_l3_pmu.o
 obj-$(CONFIG_RISCV_PMU) += riscv_pmu.o
 obj-$(CONFIG_RISCV_PMU_LEGACY) += riscv_pmu_legacy.o
 obj-$(CONFIG_RISCV_PMU_SBI) += riscv_pmu_sbi.o
+obj-$(CONFIG_STARFIVE_STARLINK_PMU) += starfive_starlink_pmu.o
 obj-$(CONFIG_THUNDERX2_PMU) += thunderx2_pmu.o
 obj-$(CONFIG_XGENE_PMU) += xgene_pmu.o
 obj-$(CONFIG_ARM_SPE_PMU) += arm_spe_pmu.o