Merge tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux

Pull arm64 updates from Will Deacon:
 "The highlights are support for Arm's "Permission Overlay Extension"
  using memory protection keys, support for running as a protected guest
  on Android as well as perf support for a bunch of new interconnect
  PMUs.

  Summary:

  ACPI:
   - Enable PMCG erratum workaround for HiSilicon HIP10 and 11
     platforms.
   - Ensure arm64-specific IORT header is covered by MAINTAINERS.

  CPU Errata:
   - Enable workaround for hardware access/dirty issue on Ampere-1A
     cores.

  Memory management:
   - Define PHYSMEM_END to fix a crash in the amdgpu driver.
   - Avoid tripping over invalid kernel mappings on the kexec() path.
   - Userspace support for the Permission Overlay Extension (POE) using
     protection keys.

  Perf and PMUs:
   - Add support for the "fixed instruction counter" extension in the
     CPU PMU architecture.
   - Extend and fix the event encodings for Apple's M1 CPU PMU.
   - Allow LSM hooks to decide on SPE permissions for physical
     profiling.
   - Add support for the CMN S3 and NI-700 PMUs.

  Confidential Computing:
   - Add support for booting an arm64 kernel as a protected guest under
     Android's "Protected KVM" (pKVM) hypervisor.

  Selftests:
   - Fix vector length issues in the SVE/SME sigreturn tests
   - Fix build warning in the ptrace tests.

  Timers:
   - Add support for PR_{G,S}ET_TSC so that 'rr' can deal with
     non-determinism arising from the architected counter.

  Miscellaneous:
   - Rework our IPI-based CPU stopping code to try NMIs if regular IPIs
     don't succeed.
   - Minor fixes and cleanups"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (94 commits)
  perf: arm-ni: Fix an NULL vs IS_ERR() bug
  arm64: hibernate: Fix warning for cast from restricted gfp_t
  arm64: esr: Define ESR_ELx_EC_* constants as UL
  arm64: pkeys: remove redundant WARN
  perf: arm_pmuv3: Use BR_RETIRED for HW branch event if enabled
  MAINTAINERS: List Arm interconnect PMUs as supported
  perf: Add driver for Arm NI-700 interconnect PMU
  dt-bindings/perf: Add Arm NI-700 PMU
  perf/arm-cmn: Improve format attr printing
  perf/arm-cmn: Clean up unnecessary NUMA_NO_NODE check
  arm64/mm: use lm_alias() with addresses passed to memblock_free()
  mm: arm64: document why pte is not advanced in contpte_ptep_set_access_flags()
  arm64: Expose the end of the linear map in PHYSMEM_END
  arm64: trans_pgd: mark PTEs entries as valid to avoid dead kexec()
  arm64/mm: Delete __init region from memblock.reserved
  perf/arm-cmn: Support CMN S3
  dt-bindings: perf: arm-cmn: Add CMN S3
  perf/arm-cmn: Refactor DTC PMU register access
  perf/arm-cmn: Make cycle counts less surprising
  perf/arm-cmn: Improve build-time assertion
  ...

15 files changed, 1243 insertions, 369 deletions

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index aa9530b4064f..bab8ba64162f 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -48,6 +48,13 @@ config ARM_CMN
 	  Support for PMU events monitoring on the Arm CMN-600 Coherent Mesh
 	  Network interconnect.
 
+config ARM_NI
+	tristate "Arm NI-700 PMU support"
+	depends on ARM64 || COMPILE_TEST
+	help
+	  Support for PMU events monitoring on the Arm NI-700 Network-on-Chip
+	  interconnect and family.
+
 config ARM_PMU
 	depends on ARM || ARM64
 	bool "ARM PMU framework"
diff --git a/drivers/perf/Makefile b/drivers/perf/Makefile
index d43df81d52f7..8268f38e42c5 100644
--- a/drivers/perf/Makefile
+++ b/drivers/perf/Makefile
@@ -3,6 +3,7 @@ obj-$(CONFIG_ARM_CCI_PMU) += arm-cci.o
 obj-$(CONFIG_ARM_CCN) += arm-ccn.o
 obj-$(CONFIG_ARM_CMN) += arm-cmn.o
 obj-$(CONFIG_ARM_DSU_PMU) += arm_dsu_pmu.o
+obj-$(CONFIG_ARM_NI) += arm-ni.o
 obj-$(CONFIG_ARM_PMU) += arm_pmu.o arm_pmu_platform.o
 obj-$(CONFIG_ARM_PMU_ACPI) += arm_pmu_acpi.o
 obj-$(CONFIG_ARM_PMUV3) += arm_pmuv3.o
diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index 38a2947ae813..c6ff1bc7d336 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -400,7 +400,7 @@ static irqreturn_t ali_drw_pmu_isr(int irq_num, void *data)
 			}
 
 			/* clear common counter intr status */
-			clr_status = FIELD_PREP(ALI_DRW_PMCOM_CNT_OV_INTR_MASK, 1);
+			clr_status = FIELD_PREP(ALI_DRW_PMCOM_CNT_OV_INTR_MASK, status);
 			writel(clr_status,
 			       drw_pmu->cfg_base + ALI_DRW_PMU_OV_INTR_CLR);
 		}
diff --git a/drivers/perf/apple_m1_cpu_pmu.c b/drivers/perf/apple_m1_cpu_pmu.c
index f322e5ca1114..1d4d01e1275e 100644
--- a/drivers/perf/apple_m1_cpu_pmu.c
+++ b/drivers/perf/apple_m1_cpu_pmu.c
@@ -47,46 +47,79 @@
  * implementations, we'll have to introduce per cpu-type tables.
  */
 enum m1_pmu_events {
-	M1_PMU_PERFCTR_UNKNOWN_01	= 0x01,
-	M1_PMU_PERFCTR_CPU_CYCLES	= 0x02,
-	M1_PMU_PERFCTR_INSTRUCTIONS	= 0x8c,
-	M1_PMU_PERFCTR_UNKNOWN_8d	= 0x8d,
-	M1_PMU_PERFCTR_UNKNOWN_8e	= 0x8e,
-	M1_PMU_PERFCTR_UNKNOWN_8f	= 0x8f,
-	M1_PMU_PERFCTR_UNKNOWN_90	= 0x90,
-	M1_PMU_PERFCTR_UNKNOWN_93	= 0x93,
-	M1_PMU_PERFCTR_UNKNOWN_94	= 0x94,
-	M1_PMU_PERFCTR_UNKNOWN_95	= 0x95,
-	M1_PMU_PERFCTR_UNKNOWN_96	= 0x96,
-	M1_PMU_PERFCTR_UNKNOWN_97	= 0x97,
-	M1_PMU_PERFCTR_UNKNOWN_98	= 0x98,
-	M1_PMU_PERFCTR_UNKNOWN_99	= 0x99,
-	M1_PMU_PERFCTR_UNKNOWN_9a	= 0x9a,
-	M1_PMU_PERFCTR_UNKNOWN_9b	= 0x9b,
-	M1_PMU_PERFCTR_UNKNOWN_9c	= 0x9c,
-	M1_PMU_PERFCTR_UNKNOWN_9f	= 0x9f,
-	M1_PMU_PERFCTR_UNKNOWN_bf	= 0xbf,
-	M1_PMU_PERFCTR_UNKNOWN_c0	= 0xc0,
-	M1_PMU_PERFCTR_UNKNOWN_c1	= 0xc1,
-	M1_PMU_PERFCTR_UNKNOWN_c4	= 0xc4,
-	M1_PMU_PERFCTR_UNKNOWN_c5	= 0xc5,
-	M1_PMU_PERFCTR_UNKNOWN_c6	= 0xc6,
-	M1_PMU_PERFCTR_UNKNOWN_c8	= 0xc8,
-	M1_PMU_PERFCTR_UNKNOWN_ca	= 0xca,
-	M1_PMU_PERFCTR_UNKNOWN_cb	= 0xcb,
-	M1_PMU_PERFCTR_UNKNOWN_f5	= 0xf5,
-	M1_PMU_PERFCTR_UNKNOWN_f6	= 0xf6,
-	M1_PMU_PERFCTR_UNKNOWN_f7	= 0xf7,
-	M1_PMU_PERFCTR_UNKNOWN_f8	= 0xf8,
-	M1_PMU_PERFCTR_UNKNOWN_fd	= 0xfd,
-	M1_PMU_PERFCTR_LAST		= M1_PMU_CFG_EVENT,
+	M1_PMU_PERFCTR_RETIRE_UOP				= 0x1,
+	M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE			= 0x2,
+	M1_PMU_PERFCTR_L1I_TLB_FILL				= 0x4,
+	M1_PMU_PERFCTR_L1D_TLB_FILL				= 0x5,
+	M1_PMU_PERFCTR_MMU_TABLE_WALK_INSTRUCTION		= 0x7,
+	M1_PMU_PERFCTR_MMU_TABLE_WALK_DATA			= 0x8,
+	M1_PMU_PERFCTR_L2_TLB_MISS_INSTRUCTION			= 0xa,
+	M1_PMU_PERFCTR_L2_TLB_MISS_DATA				= 0xb,
+	M1_PMU_PERFCTR_MMU_VIRTUAL_MEMORY_FAULT_NONSPEC		= 0xd,
+	M1_PMU_PERFCTR_SCHEDULE_UOP				= 0x52,
+	M1_PMU_PERFCTR_INTERRUPT_PENDING			= 0x6c,
+	M1_PMU_PERFCTR_MAP_STALL_DISPATCH			= 0x70,
+	M1_PMU_PERFCTR_MAP_REWIND				= 0x75,
+	M1_PMU_PERFCTR_MAP_STALL				= 0x76,
+	M1_PMU_PERFCTR_MAP_INT_UOP				= 0x7c,
+	M1_PMU_PERFCTR_MAP_LDST_UOP				= 0x7d,
+	M1_PMU_PERFCTR_MAP_SIMD_UOP				= 0x7e,
+	M1_PMU_PERFCTR_FLUSH_RESTART_OTHER_NONSPEC		= 0x84,
+	M1_PMU_PERFCTR_INST_ALL					= 0x8c,
+	M1_PMU_PERFCTR_INST_BRANCH				= 0x8d,
+	M1_PMU_PERFCTR_INST_BRANCH_CALL				= 0x8e,
+	M1_PMU_PERFCTR_INST_BRANCH_RET				= 0x8f,
+	M1_PMU_PERFCTR_INST_BRANCH_TAKEN			= 0x90,
+	M1_PMU_PERFCTR_INST_BRANCH_INDIR			= 0x93,
+	M1_PMU_PERFCTR_INST_BRANCH_COND				= 0x94,
+	M1_PMU_PERFCTR_INST_INT_LD				= 0x95,
+	M1_PMU_PERFCTR_INST_INT_ST				= 0x96,
+	M1_PMU_PERFCTR_INST_INT_ALU				= 0x97,
+	M1_PMU_PERFCTR_INST_SIMD_LD				= 0x98,
+	M1_PMU_PERFCTR_INST_SIMD_ST				= 0x99,
+	M1_PMU_PERFCTR_INST_SIMD_ALU				= 0x9a,
+	M1_PMU_PERFCTR_INST_LDST				= 0x9b,
+	M1_PMU_PERFCTR_INST_BARRIER				= 0x9c,
+	M1_PMU_PERFCTR_UNKNOWN_9f				= 0x9f,
+	M1_PMU_PERFCTR_L1D_TLB_ACCESS				= 0xa0,
+	M1_PMU_PERFCTR_L1D_TLB_MISS				= 0xa1,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_ST			= 0xa2,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_LD			= 0xa3,
+	M1_PMU_PERFCTR_LD_UNIT_UOP				= 0xa6,
+	M1_PMU_PERFCTR_ST_UNIT_UOP				= 0xa7,
+	M1_PMU_PERFCTR_L1D_CACHE_WRITEBACK			= 0xa8,
+	M1_PMU_PERFCTR_LDST_X64_UOP				= 0xb1,
+	M1_PMU_PERFCTR_LDST_XPG_UOP				= 0xb2,
+	M1_PMU_PERFCTR_ATOMIC_OR_EXCLUSIVE_SUCC			= 0xb3,
+	M1_PMU_PERFCTR_ATOMIC_OR_EXCLUSIVE_FAIL			= 0xb4,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_LD_NONSPEC		= 0xbf,
+	M1_PMU_PERFCTR_L1D_CACHE_MISS_ST_NONSPEC		= 0xc0,
+	M1_PMU_PERFCTR_L1D_TLB_MISS_NONSPEC			= 0xc1,
+	M1_PMU_PERFCTR_ST_MEMORY_ORDER_VIOLATION_NONSPEC	= 0xc4,
+	M1_PMU_PERFCTR_BRANCH_COND_MISPRED_NONSPEC		= 0xc5,
+	M1_PMU_PERFCTR_BRANCH_INDIR_MISPRED_NONSPEC		= 0xc6,
+	M1_PMU_PERFCTR_BRANCH_RET_INDIR_MISPRED_NONSPEC		= 0xc8,
+	M1_PMU_PERFCTR_BRANCH_CALL_INDIR_MISPRED_NONSPEC	= 0xca,
+	M1_PMU_PERFCTR_BRANCH_MISPRED_NONSPEC			= 0xcb,
+	M1_PMU_PERFCTR_L1I_TLB_MISS_DEMAND			= 0xd4,
+	M1_PMU_PERFCTR_MAP_DISPATCH_BUBBLE			= 0xd6,
+	M1_PMU_PERFCTR_L1I_CACHE_MISS_DEMAND			= 0xdb,
+	M1_PMU_PERFCTR_FETCH_RESTART				= 0xde,
+	M1_PMU_PERFCTR_ST_NT_UOP				= 0xe5,
+	M1_PMU_PERFCTR_LD_NT_UOP				= 0xe6,
+	M1_PMU_PERFCTR_UNKNOWN_f5				= 0xf5,
+	M1_PMU_PERFCTR_UNKNOWN_f6				= 0xf6,
+	M1_PMU_PERFCTR_UNKNOWN_f7				= 0xf7,
+	M1_PMU_PERFCTR_UNKNOWN_f8				= 0xf8,
+	M1_PMU_PERFCTR_UNKNOWN_fd				= 0xfd,
+	M1_PMU_PERFCTR_LAST					= M1_PMU_CFG_EVENT,
 
 	/*
 	 * From this point onwards, these are not actual HW events,
 	 * but attributes that get stored in hw->config_base.
 	 */
-	M1_PMU_CFG_COUNT_USER		= BIT(8),
-	M1_PMU_CFG_COUNT_KERNEL		= BIT(9),
+	M1_PMU_CFG_COUNT_USER					= BIT(8),
+	M1_PMU_CFG_COUNT_KERNEL					= BIT(9),
 };
 
 /*
@@ -96,46 +129,45 @@ enum m1_pmu_events {
  * counters had strange affinities.
  */
 static const u16 m1_pmu_event_affinity[M1_PMU_PERFCTR_LAST + 1] = {
-	[0 ... M1_PMU_PERFCTR_LAST]	= ANY_BUT_0_1,
-	[M1_PMU_PERFCTR_UNKNOWN_01]	= BIT(7),
-	[M1_PMU_PERFCTR_CPU_CYCLES]	= ANY_BUT_0_1 | BIT(0),
-	[M1_PMU_PERFCTR_INSTRUCTIONS]	= BIT(7) | BIT(1),
-	[M1_PMU_PERFCTR_UNKNOWN_8d]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_8e]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_8f]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_90]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_93]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_94]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_95]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_96]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_97]	= BIT(7),
-	[M1_PMU_PERFCTR_UNKNOWN_98]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_99]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_9a]	= BIT(7),
-	[M1_PMU_PERFCTR_UNKNOWN_9b]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_9c]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_9f]	= BIT(7),
-	[M1_PMU_PERFCTR_UNKNOWN_bf]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c0]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c1]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c4]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c5]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c6]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_c8]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_ca]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_cb]	= ONLY_5_6_7,
-	[M1_PMU_PERFCTR_UNKNOWN_f5]	= ONLY_2_4_6,
-	[M1_PMU_PERFCTR_UNKNOWN_f6]	= ONLY_2_4_6,
-	[M1_PMU_PERFCTR_UNKNOWN_f7]	= ONLY_2_4_6,
-	[M1_PMU_PERFCTR_UNKNOWN_f8]	= ONLY_2_TO_7,
-	[M1_PMU_PERFCTR_UNKNOWN_fd]	= ONLY_2_4_6,
+	[0 ... M1_PMU_PERFCTR_LAST]				= ANY_BUT_0_1,
+	[M1_PMU_PERFCTR_RETIRE_UOP]				= BIT(7),
+	[M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE]			= ANY_BUT_0_1 | BIT(0),
+	[M1_PMU_PERFCTR_INST_ALL]				= BIT(7) | BIT(1),
+	[M1_PMU_PERFCTR_INST_BRANCH]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_CALL]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_RET]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_TAKEN]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_INDIR]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_BRANCH_COND]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_INT_LD]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_INT_ST]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_INT_ALU]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_SIMD_LD]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_SIMD_ST]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_INST_SIMD_ALU]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_LDST]				= BIT(7),
+	[M1_PMU_PERFCTR_INST_BARRIER]				= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_9f]				= BIT(7),
+	[M1_PMU_PERFCTR_L1D_CACHE_MISS_LD_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_L1D_CACHE_MISS_ST_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_L1D_TLB_MISS_NONSPEC]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_ST_MEMORY_ORDER_VIOLATION_NONSPEC]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_COND_MISPRED_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_INDIR_MISPRED_NONSPEC]		= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_RET_INDIR_MISPRED_NONSPEC]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_CALL_INDIR_MISPRED_NONSPEC]	= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_BRANCH_MISPRED_NONSPEC]			= ONLY_5_6_7,
+	[M1_PMU_PERFCTR_UNKNOWN_f5]				= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f6]				= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f7]				= ONLY_2_4_6,
+	[M1_PMU_PERFCTR_UNKNOWN_f8]				= ONLY_2_TO_7,
+	[M1_PMU_PERFCTR_UNKNOWN_fd]				= ONLY_2_4_6,
 };
 
 static const unsigned m1_pmu_perf_map[PERF_COUNT_HW_MAX] = {
 	PERF_MAP_ALL_UNSUPPORTED,
-	[PERF_COUNT_HW_CPU_CYCLES]	= M1_PMU_PERFCTR_CPU_CYCLES,
-	[PERF_COUNT_HW_INSTRUCTIONS]	= M1_PMU_PERFCTR_INSTRUCTIONS,
-	/* No idea about the rest yet */
+	[PERF_COUNT_HW_CPU_CYCLES]		= M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE,
+	[PERF_COUNT_HW_INSTRUCTIONS]		= M1_PMU_PERFCTR_INST_ALL,
 };
 
 /* sysfs definitions */
@@ -154,8 +186,8 @@ static ssize_t m1_pmu_events_sysfs_show(struct device *dev,
 	PMU_EVENT_ATTR_ID(name, m1_pmu_events_sysfs_show, config)
 
 static struct attribute *m1_pmu_event_attrs[] = {
-	M1_PMU_EVENT_ATTR(cycles, M1_PMU_PERFCTR_CPU_CYCLES),
-	M1_PMU_EVENT_ATTR(instructions, M1_PMU_PERFCTR_INSTRUCTIONS),
+	M1_PMU_EVENT_ATTR(cycles, M1_PMU_PERFCTR_CORE_ACTIVE_CYCLE),
+	M1_PMU_EVENT_ATTR(instructions, M1_PMU_PERFCTR_INST_ALL),
 	NULL,
 };
 
@@ -400,7 +432,7 @@ static irqreturn_t m1_pmu_handle_irq(struct arm_pmu *cpu_pmu)
 
 	regs = get_irq_regs();
 
-	for (idx = 0; idx < cpu_pmu->num_events; idx++) {
+	for_each_set_bit(idx, cpu_pmu->cntr_mask, M1_PMU_NR_COUNTERS) {
 		struct perf_event *event = cpuc->events[idx];
 		struct perf_sample_data data;
 
@@ -560,7 +592,7 @@ static int m1_pmu_init(struct arm_pmu *cpu_pmu, u32 flags)
 	cpu_pmu->reset		  = m1_pmu_reset;
 	cpu_pmu->set_event_filter = m1_pmu_set_event_filter;
 
-	cpu_pmu->num_events	  = M1_PMU_NR_COUNTERS;
+	bitmap_set(cpu_pmu->cntr_mask, 0, M1_PMU_NR_COUNTERS);
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_EVENTS] = &m1_pmu_events_attr_group;
 	cpu_pmu->attr_groups[ARMPMU_ATTR_GROUP_FORMATS] = &m1_pmu_format_attr_group;
 	return 0;
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index c932d9d355cf..397a46410f7c 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -24,14 +24,6 @@
 #define CMN_NI_NODE_ID			GENMASK_ULL(31, 16)
 #define CMN_NI_LOGICAL_ID		GENMASK_ULL(47, 32)
 
-#define CMN_NODEID_DEVID(reg)		((reg) & 3)
-#define CMN_NODEID_EXT_DEVID(reg)	((reg) & 1)
-#define CMN_NODEID_PID(reg)		(((reg) >> 2) & 1)
-#define CMN_NODEID_EXT_PID(reg)		(((reg) >> 1) & 3)
-#define CMN_NODEID_1x1_PID(reg)		(((reg) >> 2) & 7)
-#define CMN_NODEID_X(reg, bits)		((reg) >> (3 + (bits)))
-#define CMN_NODEID_Y(reg, bits)		(((reg) >> 3) & ((1U << (bits)) - 1))
-
 #define CMN_CHILD_INFO			0x0080
 #define CMN_CI_CHILD_COUNT		GENMASK_ULL(15, 0)
 #define CMN_CI_CHILD_PTR_OFFSET		GENMASK_ULL(31, 16)
@@ -43,6 +35,9 @@
 #define CMN_MAX_XPS			(CMN_MAX_DIMENSION * CMN_MAX_DIMENSION)
 #define CMN_MAX_DTMS			(CMN_MAX_XPS + (CMN_MAX_DIMENSION - 1) * 4)
 
+/* Currently XPs are the node type we can have most of; others top out at 128 */
+#define CMN_MAX_NODES_PER_EVENT		CMN_MAX_XPS
+
 /* The CFG node has various info besides the discovery tree */
 #define CMN_CFGM_PERIPH_ID_01		0x0008
 #define CMN_CFGM_PID0_PART_0		GENMASK_ULL(7, 0)
@@ -50,24 +45,28 @@
 #define CMN_CFGM_PERIPH_ID_23		0x0010
 #define CMN_CFGM_PID2_REVISION		GENMASK_ULL(7, 4)
 
-#define CMN_CFGM_INFO_GLOBAL		0x900
+#define CMN_CFGM_INFO_GLOBAL		0x0900
 #define CMN_INFO_MULTIPLE_DTM_EN	BIT_ULL(63)
 #define CMN_INFO_RSP_VC_NUM		GENMASK_ULL(53, 52)
 #define CMN_INFO_DAT_VC_NUM		GENMASK_ULL(51, 50)
+#define CMN_INFO_DEVICE_ISO_ENABLE	BIT_ULL(44)
 
-#define CMN_CFGM_INFO_GLOBAL_1		0x908
+#define CMN_CFGM_INFO_GLOBAL_1		0x0908
 #define CMN_INFO_SNP_VC_NUM		GENMASK_ULL(3, 2)
 #define CMN_INFO_REQ_VC_NUM		GENMASK_ULL(1, 0)
 
 /* XPs also have some local topology info which has uses too */
 #define CMN_MXP__CONNECT_INFO(p)	(0x0008 + 8 * (p))
-#define CMN__CONNECT_INFO_DEVICE_TYPE	GENMASK_ULL(4, 0)
+#define CMN__CONNECT_INFO_DEVICE_TYPE	GENMASK_ULL(5, 0)
 
 #define CMN_MAX_PORTS			6
 #define CI700_CONNECT_INFO_P2_5_OFFSET	0x10
 
 /* PMU registers occupy the 3rd 4KB page of each node's region */
 #define CMN_PMU_OFFSET			0x2000
+/* ...except when they don't :( */
+#define CMN_S3_DTM_OFFSET		0xa000
+#define CMN_S3_PMU_OFFSET		0xd900
 
 /* For most nodes, this is all there is */
 #define CMN_PMU_EVENT_SEL		0x000
@@ -78,7 +77,8 @@
 /* Technically this is 4 bits wide on DNs, but we only use 2 there anyway */
 #define CMN__PMU_OCCUP1_ID		GENMASK_ULL(34, 32)
 
-/* HN-Ps are weird... */
+/* Some types are designed to coexist with another device in the same node */
+#define CMN_CCLA_PMU_EVENT_SEL		0x008
 #define CMN_HNP_PMU_EVENT_SEL		0x008
 
 /* DTMs live in the PMU space of XP registers */
@@ -123,27 +123,28 @@
 /* The DTC node is where the magic happens */
 #define CMN_DT_DTC_CTL			0x0a00
 #define CMN_DT_DTC_CTL_DT_EN		BIT(0)
+#define CMN_DT_DTC_CTL_CG_DISABLE	BIT(10)
 
 /* DTC counters are paired in 64-bit registers on a 16-byte stride. Yuck */
 #define _CMN_DT_CNT_REG(n)		((((n) / 2) * 4 + (n) % 2) * 4)
-#define CMN_DT_PMEVCNT(n)		(CMN_PMU_OFFSET + _CMN_DT_CNT_REG(n))
-#define CMN_DT_PMCCNTR			(CMN_PMU_OFFSET + 0x40)
+#define CMN_DT_PMEVCNT(dtc, n)		((dtc)->pmu_base + _CMN_DT_CNT_REG(n))
+#define CMN_DT_PMCCNTR(dtc)		((dtc)->pmu_base + 0x40)
 
-#define CMN_DT_PMEVCNTSR(n)		(CMN_PMU_OFFSET + 0x50 + _CMN_DT_CNT_REG(n))
-#define CMN_DT_PMCCNTRSR		(CMN_PMU_OFFSET + 0x90)
+#define CMN_DT_PMEVCNTSR(dtc, n)	((dtc)->pmu_base + 0x50 + _CMN_DT_CNT_REG(n))
+#define CMN_DT_PMCCNTRSR(dtc)		((dtc)->pmu_base + 0x90)
 
-#define CMN_DT_PMCR			(CMN_PMU_OFFSET + 0x100)
+#define CMN_DT_PMCR(dtc)		((dtc)->pmu_base + 0x100)
 #define CMN_DT_PMCR_PMU_EN		BIT(0)
 #define CMN_DT_PMCR_CNTR_RST		BIT(5)
 #define CMN_DT_PMCR_OVFL_INTR_EN	BIT(6)
 
-#define CMN_DT_PMOVSR			(CMN_PMU_OFFSET + 0x118)
-#define CMN_DT_PMOVSR_CLR		(CMN_PMU_OFFSET + 0x120)
+#define CMN_DT_PMOVSR(dtc)		((dtc)->pmu_base + 0x118)
+#define CMN_DT_PMOVSR_CLR(dtc)		((dtc)->pmu_base + 0x120)
 
-#define CMN_DT_PMSSR			(CMN_PMU_OFFSET + 0x128)
+#define CMN_DT_PMSSR(dtc)		((dtc)->pmu_base + 0x128)
 #define CMN_DT_PMSSR_SS_STATUS(n)	BIT(n)
 
-#define CMN_DT_PMSRR			(CMN_PMU_OFFSET + 0x130)
+#define CMN_DT_PMSRR(dtc)		((dtc)->pmu_base + 0x130)
 #define CMN_DT_PMSRR_SS_REQ		BIT(0)
 
 #define CMN_DT_NUM_COUNTERS		8
@@ -198,10 +199,11 @@ enum cmn_model {
 	CMN650 = 2,
 	CMN700 = 4,
 	CI700 = 8,
+	CMNS3 = 16,
 	/* ...and then we can use bitmap tricks for commonality */
 	CMN_ANY = -1,
 	NOT_CMN600 = -2,
-	CMN_650ON = CMN650 | CMN700,
+	CMN_650ON = CMN650 | CMN700 | CMNS3,
 };
 
 /* Actual part numbers and revision IDs defined by the hardware */
@@ -210,6 +212,7 @@ enum cmn_part {
 	PART_CMN650 = 0x436,
 	PART_CMN700 = 0x43c,
 	PART_CI700 = 0x43a,
+	PART_CMN_S3 = 0x43e,
 };
 
 /* CMN-600 r0px shouldn't exist in silicon, thankfully */
@@ -261,6 +264,7 @@ enum cmn_node_type {
 	CMN_TYPE_HNS = 0x200,
 	CMN_TYPE_HNS_MPAM_S,
 	CMN_TYPE_HNS_MPAM_NS,
+	CMN_TYPE_APB = 0x1000,
 	/* Not a real node type */
 	CMN_TYPE_WP = 0x7770
 };
@@ -280,8 +284,11 @@ struct arm_cmn_node {
 	u16 id, logid;
 	enum cmn_node_type type;
 
+	/* XP properties really, but replicated to children for convenience */
 	u8 dtm;
 	s8 dtc;
+	u8 portid_bits:4;
+	u8 deviceid_bits:4;
 	/* DN/HN-F/CXHA */
 	struct {
 		u8 val : 4;
@@ -307,8 +314,9 @@ struct arm_cmn_dtm {
 
 struct arm_cmn_dtc {
 	void __iomem *base;
+	void __iomem *pmu_base;
 	int irq;
-	int irq_friend;
+	s8 irq_friend;
 	bool cc_active;
 
 	struct perf_event *counters[CMN_DT_NUM_COUNTERS];
@@ -357,49 +365,33 @@ struct arm_cmn {
 static int arm_cmn_hp_state;
 
 struct arm_cmn_nodeid {
-	u8 x;
-	u8 y;
 	u8 port;
 	u8 dev;
 };
 
 static int arm_cmn_xyidbits(const struct arm_cmn *cmn)
 {
-	return fls((cmn->mesh_x - 1) | (cmn->mesh_y - 1) | 2);
+	return fls((cmn->mesh_x - 1) | (cmn->mesh_y - 1));
 }
 
-static struct arm_cmn_nodeid arm_cmn_nid(const struct arm_cmn *cmn, u16 id)
+static struct arm_cmn_nodeid arm_cmn_nid(const struct arm_cmn_node *dn)
 {
 	struct arm_cmn_nodeid nid;
 
-	if (cmn->num_xps == 1) {
-		nid.x = 0;
-		nid.y = 0;
-		nid.port = CMN_NODEID_1x1_PID(id);
-		nid.dev = CMN_NODEID_DEVID(id);
-	} else {
-		int bits = arm_cmn_xyidbits(cmn);
-
-		nid.x = CMN_NODEID_X(id, bits);
-		nid.y = CMN_NODEID_Y(id, bits);
-		if (cmn->ports_used & 0xc) {
-			nid.port = CMN_NODEID_EXT_PID(id);
-			nid.dev = CMN_NODEID_EXT_DEVID(id);
-		} else {
-			nid.port = CMN_NODEID_PID(id);
-			nid.dev = CMN_NODEID_DEVID(id);
-		}
-	}
+	nid.dev = dn->id & ((1U << dn->deviceid_bits) - 1);
+	nid.port = (dn->id >> dn->deviceid_bits) & ((1U << dn->portid_bits) - 1);
 	return nid;
 }
 
 static struct arm_cmn_node *arm_cmn_node_to_xp(const struct arm_cmn *cmn,
 					       const struct arm_cmn_node *dn)
 {
-	struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
-	int xp_idx = cmn->mesh_x * nid.y + nid.x;
+	int id = dn->id >> (dn->portid_bits + dn->deviceid_bits);
+	int bits = arm_cmn_xyidbits(cmn);
+	int x = id >> bits;
+	int y = id & ((1U << bits) - 1);
 
-	return cmn->xps + xp_idx;
+	return cmn->xps + cmn->mesh_x * y + x;
 }
 static struct arm_cmn_node *arm_cmn_node(const struct arm_cmn *cmn,
 					 enum cmn_node_type type)
@@ -423,15 +415,27 @@ static enum cmn_model arm_cmn_model(const struct arm_cmn *cmn)
 		return CMN700;
 	case PART_CI700:
 		return CI700;
+	case PART_CMN_S3:
+		return CMNS3;
 	default:
 		return 0;
 	};
 }
 
+static int arm_cmn_pmu_offset(const struct arm_cmn *cmn, const struct arm_cmn_node *dn)
+{
+	if (cmn->part == PART_CMN_S3) {
+		if (dn->type == CMN_TYPE_XP)
+			return CMN_S3_DTM_OFFSET;
+		return CMN_S3_PMU_OFFSET;
+	}
+	return CMN_PMU_OFFSET;
+}
+
 static u32 arm_cmn_device_connect_info(const struct arm_cmn *cmn,
 				       const struct arm_cmn_node *xp, int port)
 {
-	int offset = CMN_MXP__CONNECT_INFO(port);
+	int offset = CMN_MXP__CONNECT_INFO(port) - arm_cmn_pmu_offset(cmn, xp);
 
 	if (port >= 2) {
 		if (cmn->part == PART_CMN600 || cmn->part == PART_CMN650)
@@ -444,7 +448,7 @@ static u32 arm_cmn_device_connect_info(const struct arm_cmn *cmn,
 			offset += CI700_CONNECT_INFO_P2_5_OFFSET;
 	}
 
-	return readl_relaxed(xp->pmu_base - CMN_PMU_OFFSET + offset);
+	return readl_relaxed(xp->pmu_base + offset);
 }
 
 static struct dentry *arm_cmn_debugfs;
@@ -478,20 +482,25 @@ static const char *arm_cmn_device_type(u8 type)
 		case 0x17: return "RN-F_C_E|";
 		case 0x18: return " RN-F_E |";
 		case 0x19: return "RN-F_E_E|";
+		case 0x1a: return "  HN-S  |";
+		case 0x1b: return "  LCN   |";
 		case 0x1c: return "  MTSX  |";
 		case 0x1d: return "  HN-V  |";
 		case 0x1e: return "  CCG   |";
+		case 0x20: return " RN-F_F |";
+		case 0x21: return "RN-F_F_E|";
+		case 0x22: return " SN-F_F |";
 		default:   return "  ????  |";
 	}
 }
 
-static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d)
+static void arm_cmn_show_logid(struct seq_file *s, const struct arm_cmn_node *xp, int p, int d)
 {
 	struct arm_cmn *cmn = s->private;
 	struct arm_cmn_node *dn;
+	u16 id = xp->id | d | (p << xp->deviceid_bits);
 
 	for (dn = cmn->dns; dn->type; dn++) {
-		struct arm_cmn_nodeid nid = arm_cmn_nid(cmn, dn->id);
 		int pad = dn->logid < 10;
 
 		if (dn->type == CMN_TYPE_XP)
@@ -500,7 +509,7 @@ static void arm_cmn_show_logid(struct seq_file *s, int x, int y, int p, int d)
 		if (dn->type < CMN_TYPE_HNI)
 			continue;
 
-		if (nid.x != x || nid.y != y || nid.port != p || nid.dev != d)
+		if (dn->id != id)
 			continue;
 
 		seq_printf(s, " %*c#%-*d  |", pad + 1, ' ', 3 - pad, dn->logid);
@@ -521,6 +530,7 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 	y = cmn->mesh_y;
 	while (y--) {
 		int xp_base = cmn->mesh_x * y;
+		struct arm_cmn_node *xp = cmn->xps + xp_base;
 		u8 port[CMN_MAX_PORTS][CMN_MAX_DIMENSION];
 
 		for (x = 0; x < cmn->mesh_x; x++)
@@ -528,16 +538,14 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 
 		seq_printf(s, "\n%-2d   |", y);
 		for (x = 0; x < cmn->mesh_x; x++) {
-			struct arm_cmn_node *xp = cmn->xps + xp_base + x;
-
 			for (p = 0; p < CMN_MAX_PORTS; p++)
-				port[p][x] = arm_cmn_device_connect_info(cmn, xp, p);
+				port[p][x] = arm_cmn_device_connect_info(cmn, xp + x, p);
 			seq_printf(s, " XP #%-3d|", xp_base + x);
 		}
 
 		seq_puts(s, "\n     |");
 		for (x = 0; x < cmn->mesh_x; x++) {
-			s8 dtc = cmn->xps[xp_base + x].dtc;
+			s8 dtc = xp[x].dtc;
 
 			if (dtc < 0)
 				seq_puts(s, " DTC ?? |");
@@ -554,10 +562,10 @@ static int arm_cmn_map_show(struct seq_file *s, void *data)
 				seq_puts(s, arm_cmn_device_type(port[p][x]));
 			seq_puts(s, "\n    0|");
 			for (x = 0; x < cmn->mesh_x; x++)
-				arm_cmn_show_logid(s, x, y, p, 0);
+				arm_cmn_show_logid(s, xp + x, p, 0);
 			seq_puts(s, "\n    1|");
 			for (x = 0; x < cmn->mesh_x; x++)
-				arm_cmn_show_logid(s, x, y, p, 1);
+				arm_cmn_show_logid(s, xp + x, p, 1);
 		}
 		seq_puts(s, "\n-----+");
 	}
@@ -585,7 +593,7 @@ static void arm_cmn_debugfs_init(struct arm_cmn *cmn, int id) {}
 
 struct arm_cmn_hw_event {
 	struct arm_cmn_node *dn;
-	u64 dtm_idx[4];
+	u64 dtm_idx[DIV_ROUND_UP(CMN_MAX_NODES_PER_EVENT * 2, 64)];
 	s8 dtc_idx[CMN_MAX_DTCS];
 	u8 num_dns;
 	u8 dtm_offset;
@@ -599,6 +607,7 @@ struct arm_cmn_hw_event {
 	bool wide_sel;
 	enum cmn_filter_select filter_sel;
 };
+static_assert(sizeof(struct arm_cmn_hw_event) <= offsetof(struct hw_perf_event, target));
 
 #define for_each_hw_dn(hw, dn, i) \
 	for (i = 0, dn = hw->dn; i < hw->num_dns; i++, dn++)
@@ -609,7 +618,6 @@ struct arm_cmn_hw_event {
 
 static struct arm_cmn_hw_event *to_cmn_hw(struct perf_event *event)
 {
-	BUILD_BUG_ON(sizeof(struct arm_cmn_hw_event) > offsetof(struct hw_perf_event, target));
 	return (struct arm_cmn_hw_event *)&event->hw;
 }
 
@@ -790,8 +798,8 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 	CMN_EVENT_ATTR(CMN_ANY, cxha_##_name, CMN_TYPE_CXHA, _event)
 #define CMN_EVENT_CCRA(_name, _event)				\
 	CMN_EVENT_ATTR(CMN_ANY, ccra_##_name, CMN_TYPE_CCRA, _event)
-#define CMN_EVENT_CCHA(_name, _event)				\
-	CMN_EVENT_ATTR(CMN_ANY, ccha_##_name, CMN_TYPE_CCHA, _event)
+#define CMN_EVENT_CCHA(_model, _name, _event)				\
+	CMN_EVENT_ATTR(_model, ccha_##_name, CMN_TYPE_CCHA, _event)
 #define CMN_EVENT_CCLA(_name, _event)				\
 	CMN_EVENT_ATTR(CMN_ANY, ccla_##_name, CMN_TYPE_CCLA, _event)
 #define CMN_EVENT_CCLA_RNI(_name, _event)				\
@@ -1149,42 +1157,43 @@ static struct attribute *arm_cmn_event_attrs[] = {
 	CMN_EVENT_CCRA(wdb_alloc,			0x59),
 	CMN_EVENT_CCRA(ssb_alloc,			0x5a),
 
-	CMN_EVENT_CCHA(rddatbyp,			0x61),
-	CMN_EVENT_CCHA(chirsp_up_stall,			0x62),
-	CMN_EVENT_CCHA(chidat_up_stall,			0x63),
-	CMN_EVENT_CCHA(snppcrd_link0_stall,		0x64),
-	CMN_EVENT_CCHA(snppcrd_link1_stall,		0x65),
-	CMN_EVENT_CCHA(snppcrd_link2_stall,		0x66),
-	CMN_EVENT_CCHA(reqtrk_occ,			0x67),
-	CMN_EVENT_CCHA(rdb_occ,				0x68),
-	CMN_EVENT_CCHA(rdbyp_occ,			0x69),
-	CMN_EVENT_CCHA(wdb_occ,				0x6a),
-	CMN_EVENT_CCHA(snptrk_occ,			0x6b),
-	CMN_EVENT_CCHA(sdb_occ,				0x6c),
-	CMN_EVENT_CCHA(snphaz_occ,			0x6d),
-	CMN_EVENT_CCHA(reqtrk_alloc,			0x6e),
-	CMN_EVENT_CCHA(rdb_alloc,			0x6f),
-	CMN_EVENT_CCHA(rdbyp_alloc,			0x70),
-	CMN_EVENT_CCHA(wdb_alloc,			0x71),
-	CMN_EVENT_CCHA(snptrk_alloc,			0x72),
-	CMN_EVENT_CCHA(sdb_alloc,			0x73),
-	CMN_EVENT_CCHA(snphaz_alloc,			0x74),
-	CMN_EVENT_CCHA(pb_rhu_req_occ,			0x75),
-	CMN_EVENT_CCHA(pb_rhu_req_alloc,		0x76),
-	CMN_EVENT_CCHA(pb_rhu_pcie_req_occ,		0x77),
-	CMN_EVENT_CCHA(pb_rhu_pcie_req_alloc,		0x78),
-	CMN_EVENT_CCHA(pb_pcie_wr_req_occ,		0x79),
-	CMN_EVENT_CCHA(pb_pcie_wr_req_alloc,		0x7a),
-	CMN_EVENT_CCHA(pb_pcie_reg_req_occ,		0x7b),
-	CMN_EVENT_CCHA(pb_pcie_reg_req_alloc,		0x7c),
-	CMN_EVENT_CCHA(pb_pcie_rsvd_req_occ,		0x7d),
-	CMN_EVENT_CCHA(pb_pcie_rsvd_req_alloc,		0x7e),
-	CMN_EVENT_CCHA(pb_rhu_dat_occ,			0x7f),
-	CMN_EVENT_CCHA(pb_rhu_dat_alloc,		0x80),
-	CMN_EVENT_CCHA(pb_rhu_pcie_dat_occ,		0x81),
-	CMN_EVENT_CCHA(pb_rhu_pcie_dat_alloc,		0x82),
-	CMN_EVENT_CCHA(pb_pcie_wr_dat_occ,		0x83),
-	CMN_EVENT_CCHA(pb_pcie_wr_dat_alloc,		0x84),
+	CMN_EVENT_CCHA(CMN_ANY, rddatbyp,		0x61),
+	CMN_EVENT_CCHA(CMN_ANY, chirsp_up_stall,	0x62),
+	CMN_EVENT_CCHA(CMN_ANY, chidat_up_stall,	0x63),
+	CMN_EVENT_CCHA(CMN_ANY, snppcrd_link0_stall,	0x64),
+	CMN_EVENT_CCHA(CMN_ANY, snppcrd_link1_stall,	0x65),
+	CMN_EVENT_CCHA(CMN_ANY, snppcrd_link2_stall,	0x66),
+	CMN_EVENT_CCHA(CMN_ANY, reqtrk_occ,		0x67),
+	CMN_EVENT_CCHA(CMN_ANY, rdb_occ,		0x68),
+	CMN_EVENT_CCHA(CMN_ANY, rdbyp_occ,		0x69),
+	CMN_EVENT_CCHA(CMN_ANY, wdb_occ,		0x6a),
+	CMN_EVENT_CCHA(CMN_ANY, snptrk_occ,		0x6b),
+	CMN_EVENT_CCHA(CMN_ANY, sdb_occ,		0x6c),
+	CMN_EVENT_CCHA(CMN_ANY, snphaz_occ,		0x6d),
+	CMN_EVENT_CCHA(CMN_ANY, reqtrk_alloc,		0x6e),
+	CMN_EVENT_CCHA(CMN_ANY, rdb_alloc,		0x6f),
+	CMN_EVENT_CCHA(CMN_ANY, rdbyp_alloc,		0x70),
+	CMN_EVENT_CCHA(CMN_ANY, wdb_alloc,		0x71),
+	CMN_EVENT_CCHA(CMN_ANY, snptrk_alloc,		0x72),
+	CMN_EVENT_CCHA(CMN_ANY, db_alloc,		0x73),
+	CMN_EVENT_CCHA(CMN_ANY, snphaz_alloc,		0x74),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_req_occ,		0x75),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_req_alloc,	0x76),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_req_occ,	0x77),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_req_alloc,	0x78),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_req_occ,	0x79),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_req_alloc,	0x7a),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_reg_req_occ,	0x7b),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_reg_req_alloc,	0x7c),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_rsvd_req_occ,	0x7d),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_rsvd_req_alloc,	0x7e),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_dat_occ,		0x7f),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_dat_alloc,	0x80),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_dat_occ,	0x81),
+	CMN_EVENT_CCHA(CMN_ANY, pb_rhu_pcie_dat_alloc,	0x82),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_dat_occ,	0x83),
+	CMN_EVENT_CCHA(CMN_ANY, pb_pcie_wr_dat_alloc,	0x84),
+	CMN_EVENT_CCHA(CMNS3, chirsp1_up_stall,		0x85),
 
 	CMN_EVENT_CCLA(rx_cxs,				0x21),
 	CMN_EVENT_CCLA(tx_cxs,				0x22),
@@ -1271,15 +1280,11 @@ static ssize_t arm_cmn_format_show(struct device *dev,
 				   struct device_attribute *attr, char *buf)
 {
 	struct arm_cmn_format_attr *fmt = container_of(attr, typeof(*fmt), attr);
-	int lo = __ffs(fmt->field), hi = __fls(fmt->field);
-
-	if (lo == hi)
-		return sysfs_emit(buf, "config:%d\n", lo);
 
 	if (!fmt->config)
-		return sysfs_emit(buf, "config:%d-%d\n", lo, hi);
+		return sysfs_emit(buf, "config:%*pbl\n", 64, &fmt->field);
 
-	return sysfs_emit(buf, "config%d:%d-%d\n", fmt->config, lo, hi);
+	return sysfs_emit(buf, "config%d:%*pbl\n", fmt->config, 64, &fmt->field);
 }
 
 #define _CMN_FORMAT_ATTR(_name, _cfg, _fld)				\
@@ -1415,7 +1420,7 @@ static u32 arm_cmn_wp_config(struct perf_event *event, int wp_idx)
 static void arm_cmn_set_state(struct arm_cmn *cmn, u32 state)
 {
 	if (!cmn->state)
-		writel_relaxed(0, cmn->dtc[0].base + CMN_DT_PMCR);
+		writel_relaxed(0, CMN_DT_PMCR(&cmn->dtc[0]));
 	cmn->state |= state;
 }
 
@@ -1424,7 +1429,7 @@ static void arm_cmn_clear_state(struct arm_cmn *cmn, u32 state)
 	cmn->state &= ~state;
 	if (!cmn->state)
 		writel_relaxed(CMN_DT_PMCR_PMU_EN | CMN_DT_PMCR_OVFL_INTR_EN,
-			       cmn->dtc[0].base + CMN_DT_PMCR);
+			       CMN_DT_PMCR(&cmn->dtc[0]));
 }
 
 static void arm_cmn_pmu_enable(struct pmu *pmu)
@@ -1459,18 +1464,19 @@ static u64 arm_cmn_read_dtm(struct arm_cmn *cmn, struct arm_cmn_hw_event *hw,
 
 static u64 arm_cmn_read_cc(struct arm_cmn_dtc *dtc)
 {
-	u64 val = readq_relaxed(dtc->base + CMN_DT_PMCCNTR);
+	void __iomem *pmccntr = CMN_DT_PMCCNTR(dtc);
+	u64 val = readq_relaxed(pmccntr);
 
-	writeq_relaxed(CMN_CC_INIT, dtc->base + CMN_DT_PMCCNTR);
+	writeq_relaxed(CMN_CC_INIT, pmccntr);
 	return (val - CMN_CC_INIT) & ((CMN_CC_INIT << 1) - 1);
 }
 
 static u32 arm_cmn_read_counter(struct arm_cmn_dtc *dtc, int idx)
 {
-	u32 val, pmevcnt = CMN_DT_PMEVCNT(idx);
+	void __iomem *pmevcnt = CMN_DT_PMEVCNT(dtc, idx);
+	u32 val = readl_relaxed(pmevcnt);
 
-	val = readl_relaxed(dtc->base + pmevcnt);
-	writel_relaxed(CMN_COUNTER_INIT, dtc->base + pmevcnt);
+	writel_relaxed(CMN_COUNTER_INIT, pmevcnt);
 	return val - CMN_COUNTER_INIT;
 }
 
@@ -1481,7 +1487,7 @@ static void arm_cmn_init_counter(struct perf_event *event)
 	u64 count;
 
 	for_each_hw_dtc_idx(hw, i, idx) {
-		writel_relaxed(CMN_COUNTER_INIT, cmn->dtc[i].base + CMN_DT_PMEVCNT(idx));
+		writel_relaxed(CMN_COUNTER_INIT, CMN_DT_PMEVCNT(&cmn->dtc[i], idx));
 		cmn->dtc[i].counters[idx] = event;
 	}
 
@@ -1564,9 +1570,12 @@ s