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

Pull arm64 updates from Will Deacon:
 "I think we have a bit less than usual on the architecture side, but
  that's somewhat balanced out by a large crop of perf/PMU driver
  updates and extensions to our selftests.

  CPU features and system registers:

   - Advertise hinted conditional branch support (FEAT_HBC) to userspace

   - Avoid false positive "SANITY CHECK" warning when xCR registers
     differ outside of the length field

  Documentation:

   - Fix macro name typo in SME documentation

  Entry code:

   - Unmask exceptions earlier on the system call entry path

  Memory management:

   - Don't bother clearing PTE_RDONLY for dirty ptes in pte_wrprotect()
     and pte_modify()

  Perf and PMU drivers:

   - Initial support for Coresight TRBE devices on ACPI systems (the
     coresight driver changes will come later)

   - Fix hw_breakpoint single-stepping when called from bpf

   - Fixes for DDR PMU on i.MX8MP SoC

   - Add NUMA-awareness to Hisilicon PCIe PMU driver

   - Fix locking dependency issue in Arm DMC620 PMU driver

   - Workaround Hisilicon erratum 162001900 in the SMMUv3 PMU driver

   - Add support for Arm CMN-700 r3 parts to the CMN PMU driver

   - Add support for recent Arm Cortex CPU PMUs

   - Update Hisilicon PMU maintainers

  Selftests:

   - Add a bunch of new features to the hwcap test (JSCVT, PMULL, AES,
     SHA1, etc)

   - Fix SSVE test to leave streaming-mode after grabbing the signal
     context

   - Add new test for SVE vector-length changes with SME enabled

  Miscellaneous:

   - Allow compiler to warn on suspicious looking system register
     expressions

   - Work around SDEI firmware bug by aborting any running handlers on a
     kernel crash

   - Fix some harmless warnings when building with W=1

   - Remove some unused function declarations

   - Other minor fixes and cleanup"

* tag 'arm64-upstream' of git://git.kernel.org/pub/scm/linux/kernel/git/arm64/linux: (62 commits)
  drivers/perf: hisi: Update HiSilicon PMU maintainers
  arm_pmu: acpi: Add a representative platform device for TRBE
  arm_pmu: acpi: Refactor arm_spe_acpi_register_device()
  kselftest/arm64: Fix hwcaps selftest build
  hw_breakpoint: fix single-stepping when using bpf_overflow_handler
  arm64/sysreg: refactor deprecated strncpy
  kselftest/arm64: add jscvt feature to hwcap test
  kselftest/arm64: add pmull feature to hwcap test
  kselftest/arm64: add AES feature check to hwcap test
  kselftest/arm64: add SHA1 and related features to hwcap test
  arm64: sysreg: Generate C compiler warnings on {read,write}_sysreg_s arguments
  kselftest/arm64: build BTI tests in output directory
  perf/imx_ddr: don't enable counter0 if none of 4 counters are used
  perf/imx_ddr: speed up overflow frequency of cycle
  drivers/perf: hisi: Schedule perf session according to locality
  kselftest/arm64: fix a memleak in zt_regs_run()
  perf/arm-dmc620: Fix dmc620_pmu_irqs_lock/cpu_hotplug_lock circular lock dependency
  perf/smmuv3: Add MODULE_ALIAS for module auto loading
  perf/smmuv3: Enable HiSilicon Erratum 162001900 quirk for HIP08/09
  kselftest/arm64: Size sycall-abi buffers for the actual maximum VL
  ...

18 files changed, 383 insertions, 135 deletions

diff --git a/drivers/perf/Kconfig b/drivers/perf/Kconfig
index f4572a5cca72..273d67ecf6d2 100644
--- a/drivers/perf/Kconfig
+++ b/drivers/perf/Kconfig
@@ -92,7 +92,7 @@ config ARM_PMU_ACPI
 
 config ARM_SMMU_V3_PMU
 	 tristate "ARM SMMUv3 Performance Monitors Extension"
-	 depends on (ARM64 && ACPI) || (COMPILE_TEST && 64BIT)
+	 depends on ARM64 || (COMPILE_TEST && 64BIT)
 	 depends on GENERIC_MSI_IRQ
 	   help
 	   Provides support for the ARM SMMUv3 Performance Monitor Counter
diff --git a/drivers/perf/alibaba_uncore_drw_pmu.c b/drivers/perf/alibaba_uncore_drw_pmu.c
index 5c5be9fc1b15..19d459a36be5 100644
--- a/drivers/perf/alibaba_uncore_drw_pmu.c
+++ b/drivers/perf/alibaba_uncore_drw_pmu.c
@@ -236,10 +236,37 @@ static const struct attribute_group ali_drw_pmu_cpumask_attr_group = {
 	.attrs = ali_drw_pmu_cpumask_attrs,
 };
 
+static ssize_t ali_drw_pmu_identifier_show(struct device *dev,
+					struct device_attribute *attr,
+					char *page)
+{
+	return sysfs_emit(page, "%s\n", "ali_drw_pmu");
+}
+
+static umode_t ali_drw_pmu_identifier_attr_visible(struct kobject *kobj,
+						struct attribute *attr, int n)
+{
+	return attr->mode;
+}
+
+static struct device_attribute ali_drw_pmu_identifier_attr =
+	__ATTR(identifier, 0444, ali_drw_pmu_identifier_show, NULL);
+
+static struct attribute *ali_drw_pmu_identifier_attrs[] = {
+	&ali_drw_pmu_identifier_attr.attr,
+	NULL
+};
+
+static const struct attribute_group ali_drw_pmu_identifier_attr_group = {
+	.attrs = ali_drw_pmu_identifier_attrs,
+	.is_visible = ali_drw_pmu_identifier_attr_visible
+};
+
 static const struct attribute_group *ali_drw_pmu_attr_groups[] = {
 	&ali_drw_pmu_events_attr_group,
 	&ali_drw_pmu_cpumask_attr_group,
 	&ali_drw_pmu_format_group,
+	&ali_drw_pmu_identifier_attr_group,
 	NULL,
 };
 
diff --git a/drivers/perf/amlogic/meson_ddr_pmu_core.c b/drivers/perf/amlogic/meson_ddr_pmu_core.c
index 0b24dee1ed3c..bbc7285fd934 100644
--- a/drivers/perf/amlogic/meson_ddr_pmu_core.c
+++ b/drivers/perf/amlogic/meson_ddr_pmu_core.c
@@ -9,8 +9,6 @@
 #include <linux/kernel.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 #include <linux/printk.h>
diff --git a/drivers/perf/arm-cci.c b/drivers/perf/arm-cci.c
index 998259f1d973..61de861eaf91 100644
--- a/drivers/perf/arm-cci.c
+++ b/drivers/perf/arm-cci.c
@@ -7,10 +7,7 @@
 #include <linux/io.h>
 #include <linux/interrupt.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
-#include <linux/of_platform.h>
+#include <linux/of.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 #include <linux/slab.h>
diff --git a/drivers/perf/arm-cmn.c b/drivers/perf/arm-cmn.c
index b8c15878bc86..913dc04b3a40 100644
--- a/drivers/perf/arm-cmn.c
+++ b/drivers/perf/arm-cmn.c
@@ -72,6 +72,8 @@
 /* For most nodes, this is all there is */
 #define CMN_PMU_EVENT_SEL		0x000
 #define CMN__PMU_CBUSY_SNTHROTTLE_SEL	GENMASK_ULL(44, 42)
+#define CMN__PMU_SN_HOME_SEL		GENMASK_ULL(40, 39)
+#define CMN__PMU_HBT_LBT_SEL		GENMASK_ULL(38, 37)
 #define CMN__PMU_CLASS_OCCUP_ID		GENMASK_ULL(36, 35)
 /* Technically this is 4 bits wide on DNs, but we only use 2 there anyway */
 #define CMN__PMU_OCCUP1_ID		GENMASK_ULL(34, 32)
@@ -226,6 +228,7 @@ enum cmn_revision {
 	REV_CMN700_R0P0 = 0,
 	REV_CMN700_R1P0,
 	REV_CMN700_R2P0,
+	REV_CMN700_R3P0,
 	REV_CI700_R0P0 = 0,
 	REV_CI700_R1P0,
 	REV_CI700_R2P0,
@@ -254,6 +257,9 @@ enum cmn_node_type {
 	CMN_TYPE_CCHA,
 	CMN_TYPE_CCLA,
 	CMN_TYPE_CCLA_RNI,
+	CMN_TYPE_HNS = 0x200,
+	CMN_TYPE_HNS_MPAM_S,
+	CMN_TYPE_HNS_MPAM_NS,
 	/* Not a real node type */
 	CMN_TYPE_WP = 0x7770
 };
@@ -263,6 +269,8 @@ enum cmn_filter_select {
 	SEL_OCCUP1ID,
 	SEL_CLASS_OCCUP_ID,
 	SEL_CBUSY_SNTHROTTLE_SEL,
+	SEL_HBT_LBT_SEL,
+	SEL_SN_HOME_SEL,
 	SEL_MAX
 };
 
@@ -742,8 +750,8 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 	_CMN_EVENT_ATTR(_model, dn_##_name, CMN_TYPE_DVM, _event, _occup, _fsel)
 #define CMN_EVENT_DTC(_name)					\
 	CMN_EVENT_ATTR(CMN_ANY, dtc_##_name, CMN_TYPE_DTC, 0)
-#define _CMN_EVENT_HNF(_model, _name, _event, _occup, _fsel)		\
-	_CMN_EVENT_ATTR(_model, hnf_##_name, CMN_TYPE_HNF, _event, _occup, _fsel)
+#define CMN_EVENT_HNF(_model, _name, _event)			\
+	CMN_EVENT_ATTR(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 #define CMN_EVENT_HNI(_name, _event)				\
 	CMN_EVENT_ATTR(CMN_ANY, hni_##_name, CMN_TYPE_HNI, _event)
 #define CMN_EVENT_HNP(_name, _event)				\
@@ -768,6 +776,8 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 	CMN_EVENT_ATTR(CMN_ANY, ccla_##_name, CMN_TYPE_CCLA, _event)
 #define CMN_EVENT_CCLA_RNI(_name, _event)				\
 	CMN_EVENT_ATTR(CMN_ANY, ccla_rni_##_name, CMN_TYPE_CCLA_RNI, _event)
+#define CMN_EVENT_HNS(_name, _event)				\
+	CMN_EVENT_ATTR(CMN_ANY, hns_##_name, CMN_TYPE_HNS, _event)
 
 #define CMN_EVENT_DVM(_model, _name, _event)			\
 	_CMN_EVENT_DVM(_model, _name, _event, 0, SEL_NONE)
@@ -775,32 +785,68 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 	_CMN_EVENT_DVM(_model, _name##_all, _event, 0, SEL_OCCUP1ID),	\
 	_CMN_EVENT_DVM(_model, _name##_dvmop, _event, 1, SEL_OCCUP1ID),	\
 	_CMN_EVENT_DVM(_model, _name##_dvmsync, _event, 2, SEL_OCCUP1ID)
-#define CMN_EVENT_HNF(_model, _name, _event)			\
-	_CMN_EVENT_HNF(_model, _name, _event, 0, SEL_NONE)
+
+#define CMN_EVENT_HN_OCC(_model, _name, _type, _event)		\
+	_CMN_EVENT_ATTR(_model, _name##_all, _type, _event, 0, SEL_OCCUP1ID), \
+	_CMN_EVENT_ATTR(_model, _name##_read, _type, _event, 1, SEL_OCCUP1ID), \
+	_CMN_EVENT_ATTR(_model, _name##_write, _type, _event, 2, SEL_OCCUP1ID), \
+	_CMN_EVENT_ATTR(_model, _name##_atomic, _type, _event, 3, SEL_OCCUP1ID), \
+	_CMN_EVENT_ATTR(_model, _name##_stash, _type, _event, 4, SEL_OCCUP1ID)
+#define CMN_EVENT_HN_CLS(_model, _name, _type, _event)			\
+	_CMN_EVENT_ATTR(_model, _name##_class0, _type, _event, 0, SEL_CLASS_OCCUP_ID), \
+	_CMN_EVENT_ATTR(_model, _name##_class1, _type, _event, 1, SEL_CLASS_OCCUP_ID), \
+	_CMN_EVENT_ATTR(_model, _name##_class2, _type, _event, 2, SEL_CLASS_OCCUP_ID), \
+	_CMN_EVENT_ATTR(_model, _name##_class3, _type, _event, 3, SEL_CLASS_OCCUP_ID)
+#define CMN_EVENT_HN_SNT(_model, _name, _type, _event)			\
+	_CMN_EVENT_ATTR(_model, _name##_all, _type, _event, 0, SEL_CBUSY_SNTHROTTLE_SEL), \
+	_CMN_EVENT_ATTR(_model, _name##_group0_read, _type, _event, 1, SEL_CBUSY_SNTHROTTLE_SEL), \
+	_CMN_EVENT_ATTR(_model, _name##_group0_write, _type, _event, 2, SEL_CBUSY_SNTHROTTLE_SEL), \
+	_CMN_EVENT_ATTR(_model, _name##_group1_read, _type, _event, 3, SEL_CBUSY_SNTHROTTLE_SEL), \
+	_CMN_EVENT_ATTR(_model, _name##_group1_write, _type, _event, 4, SEL_CBUSY_SNTHROTTLE_SEL), \
+	_CMN_EVENT_ATTR(_model, _name##_read, _type, _event, 5, SEL_CBUSY_SNTHROTTLE_SEL), \
+	_CMN_EVENT_ATTR(_model, _name##_write, _type, _event, 6, SEL_CBUSY_SNTHROTTLE_SEL)
+
+#define CMN_EVENT_HNF_OCC(_model, _name, _event)			\
+	CMN_EVENT_HN_OCC(_model, hnf_##_name, CMN_TYPE_HNF, _event)
 #define CMN_EVENT_HNF_CLS(_model, _name, _event)			\
-	_CMN_EVENT_HNF(_model, _name##_class0, _event, 0, SEL_CLASS_OCCUP_ID), \
-	_CMN_EVENT_HNF(_model, _name##_class1, _event, 1, SEL_CLASS_OCCUP_ID), \
-	_CMN_EVENT_HNF(_model, _name##_class2, _event, 2, SEL_CLASS_OCCUP_ID), \
-	_CMN_EVENT_HNF(_model, _name##_class3, _event, 3, SEL_CLASS_OCCUP_ID)
+	CMN_EVENT_HN_CLS(_model, hnf_##_name, CMN_TYPE_HNS, _event)
 #define CMN_EVENT_HNF_SNT(_model, _name, _event)			\
-	_CMN_EVENT_HNF(_model, _name##_all, _event, 0, SEL_CBUSY_SNTHROTTLE_SEL), \
-	_CMN_EVENT_HNF(_model, _name##_group0_read, _event, 1, SEL_CBUSY_SNTHROTTLE_SEL), \
-	_CMN_EVENT_HNF(_model, _name##_group0_write, _event, 2, SEL_CBUSY_SNTHROTTLE_SEL), \
-	_CMN_EVENT_HNF(_model, _name##_group1_read, _event, 3, SEL_CBUSY_SNTHROTTLE_SEL), \
-	_CMN_EVENT_HNF(_model, _name##_group1_write, _event, 4, SEL_CBUSY_SNTHROTTLE_SEL), \
-	_CMN_EVENT_HNF(_model, _name##_read, _event, 5, SEL_CBUSY_SNTHROTTLE_SEL), \
-	_CMN_EVENT_HNF(_model, _name##_write, _event, 6, SEL_CBUSY_SNTHROTTLE_SEL)
-
-#define _CMN_EVENT_XP(_name, _event)				\
+	CMN_EVENT_HN_SNT(_model, hnf_##_name, CMN_TYPE_HNF, _event)
+
+#define CMN_EVENT_HNS_OCC(_name, _event)				\
+	CMN_EVENT_HN_OCC(CMN_ANY, hns_##_name, CMN_TYPE_HNS, _event),	\
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_rxsnp, CMN_TYPE_HNS, _event, 5, SEL_OCCUP1ID), \
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_lbt, CMN_TYPE_HNS, _event, 6, SEL_OCCUP1ID), \
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_hbt, CMN_TYPE_HNS, _event, 7, SEL_OCCUP1ID)
+#define CMN_EVENT_HNS_CLS( _name, _event)				\
+	CMN_EVENT_HN_CLS(CMN_ANY, hns_##_name, CMN_TYPE_HNS, _event)
+#define CMN_EVENT_HNS_SNT(_name, _event)				\
+	CMN_EVENT_HN_SNT(CMN_ANY, hns_##_name, CMN_TYPE_HNS, _event)
+#define CMN_EVENT_HNS_HBT(_name, _event)				\
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_all, CMN_TYPE_HNS, _event, 0, SEL_HBT_LBT_SEL), \
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_hbt, CMN_TYPE_HNS, _event, 1, SEL_HBT_LBT_SEL), \
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_lbt, CMN_TYPE_HNS, _event, 2, SEL_HBT_LBT_SEL)
+#define CMN_EVENT_HNS_SNH(_name, _event)				\
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_all, CMN_TYPE_HNS, _event, 0, SEL_SN_HOME_SEL), \
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_sn, CMN_TYPE_HNS, _event, 1, SEL_SN_HOME_SEL), \
+	_CMN_EVENT_ATTR(CMN_ANY, hns_##_name##_home, CMN_TYPE_HNS, _event, 2, SEL_SN_HOME_SEL)
+
+#define _CMN_EVENT_XP_MESH(_name, _event)			\
 	__CMN_EVENT_XP(e_##_name, (_event) | (0 << 2)),		\
 	__CMN_EVENT_XP(w_##_name, (_event) | (1 << 2)),		\
 	__CMN_EVENT_XP(n_##_name, (_event) | (2 << 2)),		\
-	__CMN_EVENT_XP(s_##_name, (_event) | (3 << 2)),		\
+	__CMN_EVENT_XP(s_##_name, (_event) | (3 << 2))
+
+#define _CMN_EVENT_XP_PORT(_name, _event)			\
 	__CMN_EVENT_XP(p0_##_name, (_event) | (4 << 2)),	\
 	__CMN_EVENT_XP(p1_##_name, (_event) | (5 << 2)),	\
 	__CMN_EVENT_XP(p2_##_name, (_event) | (6 << 2)),	\
 	__CMN_EVENT_XP(p3_##_name, (_event) | (7 << 2))
 
+#define _CMN_EVENT_XP(_name, _event)				\
+	_CMN_EVENT_XP_MESH(_name, _event),			\
+	_CMN_EVENT_XP_PORT(_name, _event)
+
 /* Good thing there are only 3 fundamental XP events... */
 #define CMN_EVENT_XP(_name, _event)				\
 	_CMN_EVENT_XP(req_##_name, (_event) | (0 << 5)),	\
@@ -813,6 +859,10 @@ static umode_t arm_cmn_event_attr_is_visible(struct kobject *kobj,
 	_CMN_EVENT_XP(snp2_##_name, (_event) | (7 << 5)),	\
 	_CMN_EVENT_XP(req2_##_name, (_event) | (8 << 5))
 
+#define CMN_EVENT_XP_DAT(_name, _event)				\
+	_CMN_EVENT_XP_PORT(dat_##_name, (_event) | (3 << 5)),	\
+	_CMN_EVENT_XP_PORT(dat2_##_name, (_event) | (6 << 5))
+
 
 static struct attribute *arm_cmn_event_attrs[] = {
 	CMN_EVENT_DTC(cycles),
@@ -862,11 +912,7 @@ static struct attribute *arm_cmn_event_attrs[] = {
 	CMN_EVENT_HNF(CMN_ANY, mc_retries,		0x0c),
 	CMN_EVENT_HNF(CMN_ANY, mc_reqs,			0x0d),
 	CMN_EVENT_HNF(CMN_ANY, qos_hh_retry,		0x0e),
-	_CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_all,	0x0f, 0, SEL_OCCUP1ID),
-	_CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_read, 0x0f, 1, SEL_OCCUP1ID),
-	_CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_write, 0x0f, 2, SEL_OCCUP1ID),
-	_CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_atomic, 0x0f, 3, SEL_OCCUP1ID),
-	_CMN_EVENT_HNF(CMN_ANY, qos_pocq_occupancy_stash, 0x0f, 4, SEL_OCCUP1ID),
+	CMN_EVENT_HNF_OCC(CMN_ANY, qos_pocq_occupancy,	0x0f),
 	CMN_EVENT_HNF(CMN_ANY, pocq_addrhaz,		0x10),
 	CMN_EVENT_HNF(CMN_ANY, pocq_atomic_addrhaz,	0x11),
 	CMN_EVENT_HNF(CMN_ANY, ld_st_swp_adq_full,	0x12),
@@ -943,7 +989,7 @@ static struct attribute *arm_cmn_event_attrs[] = {
 
 	CMN_EVENT_XP(txflit_valid,			0x01),
 	CMN_EVENT_XP(txflit_stall,			0x02),
-	CMN_EVENT_XP(partial_dat_flit,			0x03),
+	CMN_EVENT_XP_DAT(partial_dat_flit,		0x03),
 	/* We treat watchpoints as a special made-up class of XP events */
 	CMN_EVENT_ATTR(CMN_ANY, watchpoint_up, CMN_TYPE_WP, CMN_WP_UP),
 	CMN_EVENT_ATTR(CMN_ANY, watchpoint_down, CMN_TYPE_WP, CMN_WP_DOWN),
@@ -1132,6 +1178,66 @@ static struct attribute *arm_cmn_event_attrs[] = {
 	CMN_EVENT_CCLA(pfwd_sndr_stalls_static_crd,	0x2a),
 	CMN_EVENT_CCLA(pfwd_sndr_stalls_dynmaic_crd,	0x2b),
 
+	CMN_EVENT_HNS_HBT(cache_miss,			0x01),
+	CMN_EVENT_HNS_HBT(slc_sf_cache_access,		0x02),
+	CMN_EVENT_HNS_HBT(cache_fill,			0x03),
+	CMN_EVENT_HNS_HBT(pocq_retry,			0x04),
+	CMN_EVENT_HNS_HBT(pocq_reqs_recvd,		0x05),
+	CMN_EVENT_HNS_HBT(sf_hit,			0x06),
+	CMN_EVENT_HNS_HBT(sf_evictions,			0x07),
+	CMN_EVENT_HNS(dir_snoops_sent,			0x08),
+	CMN_EVENT_HNS(brd_snoops_sent,			0x09),
+	CMN_EVENT_HNS_HBT(slc_eviction,			0x0a),
+	CMN_EVENT_HNS_HBT(slc_fill_invalid_way,		0x0b),
+	CMN_EVENT_HNS(mc_retries_local,			0x0c),
+	CMN_EVENT_HNS_SNH(mc_reqs_local,		0x0d),
+	CMN_EVENT_HNS(qos_hh_retry,			0x0e),
+	CMN_EVENT_HNS_OCC(qos_pocq_occupancy,		0x0f),
+	CMN_EVENT_HNS(pocq_addrhaz,			0x10),
+	CMN_EVENT_HNS(pocq_atomic_addrhaz,		0x11),
+	CMN_EVENT_HNS(ld_st_swp_adq_full,		0x12),
+	CMN_EVENT_HNS(cmp_adq_full,			0x13),
+	CMN_EVENT_HNS(txdat_stall,			0x14),
+	CMN_EVENT_HNS(txrsp_stall,			0x15),
+	CMN_EVENT_HNS(seq_full,				0x16),
+	CMN_EVENT_HNS(seq_hit,				0x17),
+	CMN_EVENT_HNS(snp_sent,				0x18),
+	CMN_EVENT_HNS(sfbi_dir_snp_sent,		0x19),
+	CMN_EVENT_HNS(sfbi_brd_snp_sent,		0x1a),
+	CMN_EVENT_HNS(intv_dirty,			0x1c),
+	CMN_EVENT_HNS(stash_snp_sent,			0x1d),
+	CMN_EVENT_HNS(stash_data_pull,			0x1e),
+	CMN_EVENT_HNS(snp_fwded,			0x1f),
+	CMN_EVENT_HNS(atomic_fwd,			0x20),
+	CMN_EVENT_HNS(mpam_hardlim,			0x21),
+	CMN_EVENT_HNS(mpam_softlim,			0x22),
+	CMN_EVENT_HNS(snp_sent_cluster,			0x23),
+	CMN_EVENT_HNS(sf_imprecise_evict,		0x24),
+	CMN_EVENT_HNS(sf_evict_shared_line,		0x25),
+	CMN_EVENT_HNS_CLS(pocq_class_occup,		0x26),
+	CMN_EVENT_HNS_CLS(pocq_class_retry,		0x27),
+	CMN_EVENT_HNS_CLS(class_mc_reqs_local,		0x28),
+	CMN_EVENT_HNS_CLS(class_cgnt_cmin,		0x29),
+	CMN_EVENT_HNS_SNT(sn_throttle,			0x2a),
+	CMN_EVENT_HNS_SNT(sn_throttle_min,		0x2b),
+	CMN_EVENT_HNS(sf_precise_to_imprecise,		0x2c),
+	CMN_EVENT_HNS(snp_intv_cln,			0x2d),
+	CMN_EVENT_HNS(nc_excl,				0x2e),
+	CMN_EVENT_HNS(excl_mon_ovfl,			0x2f),
+	CMN_EVENT_HNS(snp_req_recvd,			0x30),
+	CMN_EVENT_HNS(snp_req_byp_pocq,			0x31),
+	CMN_EVENT_HNS(dir_ccgha_snp_sent,		0x32),
+	CMN_EVENT_HNS(brd_ccgha_snp_sent,		0x33),
+	CMN_EVENT_HNS(ccgha_snp_stall,			0x34),
+	CMN_EVENT_HNS(lbt_req_hardlim,			0x35),
+	CMN_EVENT_HNS(hbt_req_hardlim,			0x36),
+	CMN_EVENT_HNS(sf_reupdate,			0x37),
+	CMN_EVENT_HNS(excl_sf_imprecise,		0x38),
+	CMN_EVENT_HNS(snp_pocq_addrhaz,			0x39),
+	CMN_EVENT_HNS(mc_retries_remote,		0x3a),
+	CMN_EVENT_HNS_SNH(mc_reqs_remote,		0x3b),
+	CMN_EVENT_HNS_CLS(class_mc_reqs_remote,		0x3c),
+
 	NULL
 };
 
@@ -1373,6 +1479,10 @@ static int arm_cmn_set_event_sel_hi(struct arm_cmn_node *dn,
 		dn->occupid[fsel].val = occupid;
 		reg = FIELD_PREP(CMN__PMU_CBUSY_SNTHROTTLE_SEL,
 				 dn->occupid[SEL_CBUSY_SNTHROTTLE_SEL].val) |
+		      FIELD_PREP(CMN__PMU_SN_HOME_SEL,
+				 dn->occupid[SEL_SN_HOME_SEL].val) |
+		      FIELD_PREP(CMN__PMU_HBT_LBT_SEL,
+				 dn->occupid[SEL_HBT_LBT_SEL].val) |
 		      FIELD_PREP(CMN__PMU_CLASS_OCCUP_ID,
 				 dn->occupid[SEL_CLASS_OCCUP_ID].val) |
 		      FIELD_PREP(CMN__PMU_OCCUP1_ID,
@@ -2200,6 +2310,7 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
 			case CMN_TYPE_CCRA:
 			case CMN_TYPE_CCHA:
 			case CMN_TYPE_CCLA:
+			case CMN_TYPE_HNS:
 				dn++;
 				break;
 			/* Nothing to see here */
@@ -2207,6 +2318,8 @@ static int arm_cmn_discover(struct arm_cmn *cmn, unsigned int rgn_offset)
 			case CMN_TYPE_MPAM_NS:
 			case CMN_TYPE_RNSAM:
 			case CMN_TYPE_CXLA:
+			case CMN_TYPE_HNS_MPAM_S:
+			case CMN_TYPE_HNS_MPAM_NS:
 				break;
 			/*
 			 * Split "optimised" combination nodes into separate
diff --git a/drivers/perf/arm_dmc620_pmu.c b/drivers/perf/arm_dmc620_pmu.c
index 9d0f01c4455a..30cea6859574 100644
--- a/drivers/perf/arm_dmc620_pmu.c
+++ b/drivers/perf/arm_dmc620_pmu.c
@@ -66,8 +66,13 @@
 #define DMC620_PMU_COUNTERn_OFFSET(n) \
 	(DMC620_PMU_COUNTERS_BASE + 0x28 * (n))
 
-static LIST_HEAD(dmc620_pmu_irqs);
+/*
+ * dmc620_pmu_irqs_lock: protects dmc620_pmu_irqs list
+ * dmc620_pmu_node_lock: protects pmus_node lists in all dmc620_pmu instances
+ */
 static DEFINE_MUTEX(dmc620_pmu_irqs_lock);
+static DEFINE_MUTEX(dmc620_pmu_node_lock);
+static LIST_HEAD(dmc620_pmu_irqs);
 
 struct dmc620_pmu_irq {
 	struct hlist_node node;
@@ -475,9 +480,9 @@ static int dmc620_pmu_get_irq(struct dmc620_pmu *dmc620_pmu, int irq_num)
 		return PTR_ERR(irq);
 
 	dmc620_pmu->irq = irq;
-	mutex_lock(&dmc620_pmu_irqs_lock);
+	mutex_lock(&dmc620_pmu_node_lock);
 	list_add_rcu(&dmc620_pmu->pmus_node, &irq->pmus_node);
-	mutex_unlock(&dmc620_pmu_irqs_lock);
+	mutex_unlock(&dmc620_pmu_node_lock);
 
 	return 0;
 }
@@ -486,9 +491,11 @@ static void dmc620_pmu_put_irq(struct dmc620_pmu *dmc620_pmu)
 {
 	struct dmc620_pmu_irq *irq = dmc620_pmu->irq;
 
-	mutex_lock(&dmc620_pmu_irqs_lock);
+	mutex_lock(&dmc620_pmu_node_lock);
 	list_del_rcu(&dmc620_pmu->pmus_node);
+	mutex_unlock(&dmc620_pmu_node_lock);
 
+	mutex_lock(&dmc620_pmu_irqs_lock);
 	if (!refcount_dec_and_test(&irq->refcount)) {
 		mutex_unlock(&dmc620_pmu_irqs_lock);
 		return;
@@ -638,10 +645,10 @@ static int dmc620_pmu_cpu_teardown(unsigned int cpu,
 		return 0;
 
 	/* We're only reading, but this isn't the place to be involving RCU */
-	mutex_lock(&dmc620_pmu_irqs_lock);
+	mutex_lock(&dmc620_pmu_node_lock);
 	list_for_each_entry(dmc620_pmu, &irq->pmus_node, pmus_node)
 		perf_pmu_migrate_context(&dmc620_pmu->pmu, irq->cpu, target);
-	mutex_unlock(&dmc620_pmu_irqs_lock);
+	mutex_unlock(&dmc620_pmu_node_lock);
 
 	WARN_ON(irq_set_affinity(irq->irq_num, cpumask_of(target)));
 	irq->cpu = target;
diff --git a/drivers/perf/arm_dsu_pmu.c b/drivers/perf/arm_dsu_pmu.c
index fe2abb412c00..8223c49bd082 100644
--- a/drivers/perf/arm_dsu_pmu.c
+++ b/drivers/perf/arm_dsu_pmu.c
@@ -20,7 +20,7 @@
 #include <linux/interrupt.h>
 #include <linux/kernel.h>
 #include <linux/module.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
 #include <linux/spinlock.h>
diff --git a/drivers/perf/arm_pmu_acpi.c b/drivers/perf/arm_pmu_acpi.c
index 90815ad762eb..05dda19c5359 100644
--- a/drivers/perf/arm_pmu_acpi.c
+++ b/drivers/perf/arm_pmu_acpi.c
@@ -69,6 +69,62 @@ static void arm_pmu_acpi_unregister_irq(int cpu)
 		acpi_unregister_gsi(gsi);
 }
 
+static int __maybe_unused
+arm_acpi_register_pmu_device(struct platform_device *pdev, u8 len,
+			     u16 (*parse_gsi)(struct acpi_madt_generic_interrupt *))
+{
+	int cpu, this_hetid, hetid, irq, ret;
+	u16 this_gsi = 0, gsi = 0;
+
+	/*
+	 * Ensure that platform device must have IORESOURCE_IRQ
+	 * resource to hold gsi interrupt.
+	 */
+	if (pdev->num_resources != 1)
+		return -ENXIO;
+
+	if (pdev->resource[0].flags != IORESOURCE_IRQ)
+		return -ENXIO;
+
+	/*
+	 * Sanity check all the GICC tables for the same interrupt
+	 * number. For now, only support homogeneous ACPI machines.
+	 */
+	for_each_possible_cpu(cpu) {
+		struct acpi_madt_generic_interrupt *gicc;
+
+		gicc = acpi_cpu_get_madt_gicc(cpu);
+		if (gicc->header.length < len)
+			return gsi ? -ENXIO : 0;
+
+		this_gsi = parse_gsi(gicc);
+		this_hetid = find_acpi_cpu_topology_hetero_id(cpu);
+		if (!gsi) {
+			hetid = this_hetid;
+			gsi = this_gsi;
+		} else if (hetid != this_hetid || gsi != this_gsi) {
+			pr_warn("ACPI: %s: must be homogeneous\n", pdev->name);
+			return -ENXIO;
+		}
+	}
+
+	if (!this_gsi)
+		return 0;
+
+	irq = acpi_register_gsi(NULL, gsi, ACPI_LEVEL_SENSITIVE, ACPI_ACTIVE_HIGH);
+	if (irq < 0) {
+		pr_warn("ACPI: %s Unable to register interrupt: %d\n", pdev->name, gsi);
+		return -ENXIO;
+	}
+
+	pdev->resource[0].start = irq;
+	ret = platform_device_register(pdev);
+	if (ret)
+		acpi_unregister_gsi(gsi);
+
+	return ret;
+}
+
 #if IS_ENABLED(CONFIG_ARM_SPE_PMU)
 static struct resource spe_resources[] = {
 	{
@@ -84,6 +140,11 @@ static struct platform_device spe_dev = {
 	.num_resources = ARRAY_SIZE(spe_resources)
 };
 
+static u16 arm_spe_parse_gsi(struct acpi_madt_generic_interrupt *gicc)
+{
+	return gicc->spe_interrupt;
+}
+
 /*
  * For lack of a better place, hook the normal PMU MADT walk
  * and create a SPE device if we detect a recent MADT with
@@ -91,53 +152,50 @@ static struct platform_device spe_dev = {
  */
 static void arm_spe_acpi_register_device(void)
 {
-	int cpu, hetid, irq, ret;
-	bool first = true;
-	u16 gsi = 0;
-
-	/*
-	 * Sanity check all the GICC tables for the same interrupt number.
-	 * For now, we only support homogeneous ACPI/SPE machines.
-	 */
-	for_each_possible_cpu(cpu) {
-		struct acpi_madt_generic_interrupt *gicc;
+	int ret = arm_acpi_register_pmu_device(&spe_dev, ACPI_MADT_GICC_SPE,
+					       arm_spe_parse_gsi);
+	if (ret)
+		pr_warn("ACPI: SPE: Unable to register device\n");
+}
+#else
+static inline void arm_spe_acpi_register_device(void)
+{
+}
+#endif /* CONFIG_ARM_SPE_PMU */
 
-		gicc = acpi_cpu_get_madt_gicc(cpu);
-		if (gicc->header.length < ACPI_MADT_GICC_SPE)
-			return;
-
-		if (first) {
-			gsi = gicc->spe_interrupt;
-			if (!gsi)
-				return;
-			hetid = find_acpi_cpu_topology_hetero_id(cpu);
-			first = false;
-		} else if ((gsi != gicc->spe_interrupt) ||
-			   (hetid != find_acpi_cpu_topology_hetero_id(cpu))) {
-			pr_warn("ACPI: SPE must be homogeneous\n");
-			return;
-		}
+#if IS_ENABLED(CONFIG_CORESIGHT_TRBE)
+static struct resource trbe_resources[] = {
+	{
+		/* irq */
+		.flags          = IORESOURCE_IRQ,
 	}
+};
 
-	irq = acpi_register_gsi(NULL, gsi, ACPI_LEVEL_SENSITIVE,
-				ACPI_ACTIVE_HIGH);
-	if (irq < 0) {
-		pr_warn("ACPI: SPE Unable to register interrupt: %d\n", gsi);
-		return;
-	}
+static struct platform_device trbe_dev = {
+	.name = ARMV8_TRBE_PDEV_NAME,
+	.id = -1,
+	.resource = trbe_resources,
+	.num_resources = ARRAY_SIZE(trbe_resources)
+};
 
-	spe_resources[0].start = irq;
-	ret = platform_device_register(&spe_dev);
-	if (ret < 0) {
-		pr_warn("ACPI: SPE: Unable to register device\n");
-		acpi_unregister_gsi(gsi);
-	}
+static u16 arm_trbe_parse_gsi(struct acpi_madt_generic_interrupt *gicc)
+{
+	return gicc->trbe_interrupt;
+}
+
+static void arm_trbe_acpi_register_device(void)
+{
+	int ret = arm_acpi_register_pmu_device(&trbe_dev, ACPI_MADT_GICC_TRBE,
+					       arm_trbe_parse_gsi);
+	if (ret)
+		pr_warn("ACPI: TRBE: Unable to register device\n");
 }
 #else
-static inline void arm_spe_acpi_register_device(void)
+static inline void arm_trbe_acpi_register_device(void)
 {
+
 }
-#endif /* CONFIG_ARM_SPE_PMU */
+#endif /* CONFIG_CORESIGHT_TRBE */
 
 static int arm_pmu_acpi_parse_irqs(void)
 {
@@ -374,6 +432,7 @@ static int arm_pmu_acpi_init(void)
 		return 0;
 
 	arm_spe_acpi_register_device();
+	arm_trbe_acpi_register_device();
 
 	return 0;
 }
diff --git a/drivers/perf/arm_pmu_platform.c b/drivers/perf/arm_pmu_platform.c
index 933b96e243b8..3596db36cbff 100644
--- a/drivers/perf/arm_pmu_platform.c
+++ b/drivers/perf/arm_pmu_platform.c
@@ -16,7 +16,6 @@
 #include <linux/irqdesc.h>
 #include <linux/kconfig.h>
 #include <linux/of.h>
-#include <linux/of_device.h>
 #include <linux/percpu.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
diff --git a/drivers/perf/arm_pmuv3.c b/drivers/perf/arm_pmuv3.c
index 08b3a1bf0ef6..e5a2ac4155f6 100644
--- a/drivers/perf/arm_pmuv3.c
+++ b/drivers/perf/arm_pmuv3.c
@@ -721,38 +721,15 @@ static void armv8pmu_enable_event(struct perf_event *event)
 	 * Enable counter and interrupt, and set the counter to count
 	 * the event that we're interested in.
 	 */
-
-	/*
-	 * Disable counter
-	 */
 	armv8pmu_disable_event_counter(event);
-
-	/*
-	 * Set event.
-	 */
 	armv8pmu_write_event_type(event);
-
-	/*
-	 * Enable interrupt for this counter
-	 */
 	armv8pmu_enable_event_irq(event);
-
-	/*
-	 * Enable counter
-	 */
 	armv8pmu_enable_event_counter(event);
 }
 
 static void armv8pmu_disable_event(struct perf_event *event)
 {
-	/*
-	 * Disable counter
-	 */
 	armv8pmu_disable_event_counter(event);
-
-	/*
-	 * Disable interrupt for this counter
-	 */
 	armv8pmu_disable_event_irq(event);
 }
 
@@ -1266,9 +1243,14 @@ PMUV3_INIT_SIMPLE(armv8_cortex_a76)
 PMUV3_INIT_SIMPLE(armv8_cortex_a77)
 PMUV3_INIT_SIMPLE(armv8_cortex_a78)
 PMUV3_INIT_SIMPLE(armv9_cortex_a510)
+PMUV3_INIT_SIMPLE(armv9_cortex_a520)
 PMUV3_INIT_SIMPLE(armv9_cortex_a710)
+PMUV3_INIT_SIMPLE(armv9_cortex_a715)
+PMUV3_INIT_SIMPLE(armv9_cortex_a720)
 PMUV3_INIT_SIMPLE(armv8_cortex_x1)
 PMUV3_INIT_SIMPLE(armv9_cortex_x2)
+PMUV3_INIT_SIMPLE(armv9_cortex_x3)
+PMUV3_INIT_SIMPLE(armv9_cortex_x4)
 PMUV3_INIT_SIMPLE(armv8_neoverse_e1)
 PMUV3_INIT_SIMPLE(armv8_neoverse_n1)
 PMUV3_INIT_SIMPLE(armv9_neoverse_n2)
@@ -1334,9 +1316,14 @@ static const struct of_device_id armv8_pmu_of_device_ids[] = {
 	{.compatible = "arm,cortex-a77-pmu",	.data = armv8_cortex_a77_pmu_init},
 	{.compatible = "arm,cortex-a78-pmu",	.data = armv8_cortex_a78_pmu_init},
 	{.compatible = "arm,cortex-a510-pmu",	.data = armv9_cortex_a510_pmu_init},
+	{.compatible = "arm,cortex-a520-pmu",	.data = armv9_cortex_a520_pmu_init},
 	{.compatible = "arm,cortex-a710-pmu",	.data = armv9_cortex_a710_pmu_init},
+	{.compatible = "arm,cortex-a715-pmu",	.data = armv9_cortex_a715_pmu_init},
+	{.compatible = "arm,cortex-a720-pmu",	.data = armv9_cortex_a720_pmu_init},
 	{.compatible = "arm,cortex-x1-pmu",	.data = armv8_cortex_x1_pmu_init},
 	{.compatible = "arm,cortex-x2-pmu",	.data = armv9_cortex_x2_pmu_init},
+	{.compatible = "arm,cortex-x3-pmu",	.data = armv9_cortex_x3_pmu_init},
+	{.compatible = "arm,cortex-x4-pmu",	.data = armv9_cortex_x4_pmu_init},
 	{.compatible = "arm,neoverse-e1-pmu",	.data = armv8_neoverse_e1_pmu_init},
 	{.compatible = "arm,neoverse-n1-pmu",	.data = armv8_neoverse_n1_pmu_init},
 	{.compatible = "arm,neoverse-n2-pmu",	.data = armv9_neoverse_n2_pmu_init},
diff --git a/drivers/perf/arm_smmuv3_pmu.c b/drivers/perf/arm_smmuv3_pmu.c
index 25a269d431e4..6303b82566f9 100644
--- a/drivers/perf/arm_smmuv3_pmu.c
+++ b/drivers/perf/arm_smmuv3_pmu.c
@@ -115,6 +115,7 @@
 #define SMMU_PMCG_PA_SHIFT              12
 
 #define SMMU_PMCG_EVCNTR_RDONLY         BIT(0)
+#define SMMU_PMCG_HARDEN_DISABLE        BIT(1)
 
 static int cpuhp_state_num;
 
@@ -159,6 +160,20 @@ static inline void smmu_pmu_enable(struct pmu *pmu)
 	writel(SMMU_PMCG_CR_ENABLE, smmu_pmu->reg_base + SMMU_PMCG_CR);
 }
 
+static int smmu_pmu_apply_event_filter(struct smmu_pmu *smmu_pmu,
+				       struct perf_event *event, int idx);
+
+static inline void smmu_pmu_enable_quirk_hip08_09(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+	unsigned int idx;
+
+	for_each_set_bit(idx, smmu_pmu->used_counters, smmu_pmu->num_counters)
+		smmu_pmu_apply_event_filter(smmu_pmu, smmu_pmu->events[idx], idx);
+
+	smmu_pmu_enable(pmu);
+}
+
 static inline void smmu_pmu_disable(struct pmu *pmu)
 {
 	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
@@ -167,6 +182,22 @@ static inline void smmu_pmu_disable(struct pmu *pmu)
 	writel(0, smmu_pmu->reg_base + SMMU_PMCG_IRQ_CTRL);
 }
 
+static inline void smmu_pmu_disable_quirk_hip08_09(struct pmu *pmu)
+{
+	struct smmu_pmu *smmu_pmu = to_smmu_pmu(pmu);
+	unsigned int idx;
+
+	/*
+	 * The global disable of PMU sometimes fail to stop the counting.
+	 * Harden this by writing an invalid event type to each used counter
+	 * to forcibly stop counting.
+	 */
+	for_each_set_bit(idx, smmu_pmu->used_counters, smmu_pmu->num_counters)
+		writel(0xffff, smmu_pmu->reg_base + SMMU_PMCG_EVTYPER(idx));
+
+	smmu_pmu_disable(pmu);
+}
+
 static inline void smmu_pmu_counter_set_value(struct smmu_pmu *smmu_pmu,
 					      u32 idx, u64 value)
 {
@@ -765,7 +796,10 @@ static void smmu_pmu_get_acpi_options(struct smmu_pmu *smmu_pmu)
 	switch (model) {
 	case IORT_SMMU_V3_PMCG_HISI_HIP08:
 		/* HiSilicon Erratum 162001800 */
-		smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY;
+		smmu_pmu->options |= SMMU_PMCG_EVCNTR_RDONLY | SMMU_PMCG_HARDEN_DISABLE;
+		break;
+	case IORT_SMMU_V3_PMCG_HISI_HIP09:
+		smmu_pmu->options |= SMMU_PMCG_HARDEN_DISABLE;
 		break;
 	}
 
@@ -890,6 +924,16 @@ static int smmu_pmu_probe(struct platform_device *pdev)
 	if (!dev->of_node)
 		smmu_pmu_get_acpi_options(smmu_pmu);
 
+	/*
+	 * For platforms suffer this quirk, the PMU disable sometimes fails to
+	 * stop the counters. This will leads to inaccurate or error counting.
+	 * Forcibly disable the counters with these quirk handler.
+	 */
+	if (smmu_pmu->options & SMMU_PMCG_HARDEN_DISABLE) {
+		smmu_pmu->pmu.pmu_enable = smmu_pmu_enable_quirk_hip08_09;
+		smmu_pmu->pmu.pmu_disable = smmu_pmu_disable_quirk_hip08_09;
+	}
+
 	/* Pick one CPU to be the preferred one to use */
 	smmu_pmu->on_cpu = raw_smp_processor_id();
 	WARN_ON(irq_set_affinity(smmu_pmu->irq, cpumask_of(smmu_pmu->on_cpu)));
@@ -984,6 +1028,7 @@ static void __exit arm_smmu_pmu_exit(void)
 
 module_exit(arm_smmu_pmu_exit);
 
+MODULE_ALIAS("platform:arm-smmu-v3-pmcg");
 MODULE_DESCRIPTION("PMU driver for ARM SMMUv3 Performance Monitors Extension");
 MODULE_AUTHOR("Neil Leeder <nleeder@codeaurora.org>");
 MODULE_AUTHOR("Shameer Kolothum <shameerali.kolothum.thodi@huawei.com>");
diff --git a/drivers/perf/arm_spe_pmu.c b/drivers/perf/arm_spe_pmu.c
index b9ba4c4fe5a2..d2b0cbf0e0c4 100644
--- a/drivers/perf/arm_spe_pmu.c
+++ b/drivers/perf/arm_spe_pmu.c
@@ -25,8 +25,7 @@
 #include <linux/kernel.h>
 #include <linux/list.h>
 #include <linux/module.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
+#include <linux/of.h>
 #include <linux/perf_event.h>
 #include <linux/perf/arm_pmu.h>
 #include <linux/platform_device.h>
diff --git a/drivers/perf/fsl_imx8_ddr_perf.c b/drivers/perf/fsl_imx8_ddr_perf.c
index 5222ba1e79d0..92611c98120f 100644
--- a/drivers/perf/fsl_imx8_ddr_perf.c
+++ b/drivers/perf/fsl_imx8_ddr_perf.c
@@ -10,10 +10,9 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/of_irq.h>
 #include <linux/perf_event.h>
+#include <linux/platform_device.h>
 #include <linux/slab.h>
 
 #define COUNTER_CNTL		0x0
@@ -28,6 +27,8 @@
 #define CNTL_CLEAR_MASK		0xFFFFFFFD
 #define CNTL_OVER_MASK		0xFFFFFFFE
 
+#define CNTL_CP_SHIFT		16
+#define CNTL_CP_MASK		(0xFF << CNTL_CP_SHIFT)
 #define CNTL_CSV_SHIFT		24
 #define CNTL_CSV_MASK		(0xFFU << CNTL_CSV_SHIFT)
 
@@ -35,6 +36,8 @@
 #define EVENT_CYCLES_COUNTER	0
 #define NUM_COUNTERS		4
 
+/* For removing bias if cycle counter CNTL.CP is set to 0xf0 */
+#define CYCLES_COUNTER_MASK	0x0FFFFFFF
 #define AXI_MASKING_REVERT	0xffff0000	/* AXI_MASKING(MSB 16bits) + AXI_ID(LSB 16bits) */
 
 #define to_ddr_pmu(p)		container_of(p, struct ddr_pmu, pmu)
@@ -101,6 +104,7 @@ struct ddr_pmu {
 	const struct fsl_ddr_devtype_data *devtype_data;
 	int irq;
 	int id;
+	int active_counter;
 };
 
 static ssize_t ddr_perf_identifier_show(struct device *dev,
@@ -427,6 +431,17 @@ static void ddr_perf_counter_enable(struct ddr_pmu *pmu, int config,
 		writel(0, pmu->base + reg);
 		val = CNTL_EN | CNTL_CLEAR;
 		val |= FIELD_PREP(CNTL_CSV_MASK, config);
+
+		/*
+		 * On i.MX8MP we need to bias the cycle counter to overflow more often.
+		 * We do this by initializing bits [23:16] of the counter value via the
+		 * COUNTER_CTRL Counter Parameter (CP) field.
+		 */
+		if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED) {
+			if (counter == EVENT_CYCLES_COUNTER)
+				val |= FIELD_PREP(CNTL_CP_MASK, 0xf0);
+		}
+
 		writel(val, pmu->base + reg);
 	} else {
 		/* Disable counter */
@@ -466,6 +481,12 @@ static void ddr_perf_event_update(struct perf_event *event)
 	int ret;
 
 	new_raw_count = ddr_perf_read_counter(pmu, counter);
+	/* Remove the bias applied in ddr_perf_counter_enable(). */
+	if (pmu->devtype_data->quirks & DDR_CAP_AXI_ID_FILTER_ENHANCED) {
+		if (counter == EVENT_CYCLES_COUNTER)
+			new_raw_count &= CYCLES_COUNTER_MASK;
+	}
+
 	local64_add(new_raw_count, &event->count);
 
 	/*
@@ -495,6 +516,10 @@ static void ddr_perf_event_start(struct perf_event *event, int flags)
 
 	ddr_perf_counter_enable(pmu, event->attr.config, counter, true);
 
+	if (!pmu->active_counter++)
+		ddr_perf_counter_enable(pmu, EVENT_CYCLES_ID,
+			EVENT_CYCLES_COUNTER, true);
+
 	hwc->state = 0;
 }
 
@@ -548,6 +573,10 @@ static void ddr_perf_event_stop(struct perf_event *event, int flags)
 	ddr_perf_counter_enable(pmu, event->attr.config, counter, false);
 	ddr_perf_event_update(event);
 
+	if (!--pmu->active_counter)
+		ddr_perf_counter_enable(pmu, EVENT_CYCLES_ID,
+			EVENT_CYCLES_COUNTER, false);
+
 	hwc->state |= PERF_HES_STOPPED;
 }
 
@@ -565,25 +594,10 @@ static void ddr_perf_event_del(struct perf_event *event, int flags)
 
 static void ddr_perf_pmu_enable(struct pmu *pmu)
 {
-	struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu);
-
-	/* enable cycle counter if cycle is not active event list */
-	if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL)
-		ddr_perf_counter_enable(ddr_pmu,
-				      EVENT_CYCLES_ID,
-				      EVENT_CYCLES_COUNTER,
-				      true);
 }
 
 static void ddr_perf_pmu_disable(struct pmu *pmu)
 {
-	struct ddr_pmu *ddr_pmu = to_ddr_pmu(pmu);
-
-	if (ddr_pmu->events[EVENT_CYCLES_COUNTER] == NULL)
-		ddr_perf_counter_enable(ddr_pmu,
-				      EVENT_CYCLES_ID,
-				      EVENT_CYCLES_COUNTER,
-				      false);
 }
 
 static int ddr_perf_init(struct ddr_pmu *pmu, void __iomem *base,
diff --git a/drivers/perf/fsl_imx9_ddr_perf.c b/drivers/perf/fsl_imx9_ddr_perf.c
index 71d5b07e3aff..5cf770a1bc31 100644
--- a/drivers/perf/fsl_imx9_ddr_perf.c
+++ b/drivers/perf/fsl_imx9_ddr_perf.c
@@ -7,9 +7,7 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
-#include <linux/of_irq.h>
+#include <linux/platform_device.h>
 #include <linux/perf_event.h>
 
 /* Performance monitor configuration */
diff --git a/drivers/perf/hisilicon/hisi_pcie_pmu.c b/drivers/perf/hisilicon/hisi_pcie_pmu.c
index e10fc7cb9493..5a00adb2de8c 100644
--- a/drivers/perf/hisilicon/hisi_pcie_pmu.c
+++ b/drivers/perf/hisilicon/hisi_pcie_pmu.c
@@ -665,8 +665,8 @@ static int hisi_pcie_pmu_online_cpu(unsigned int cpu, struct hlist_node *node)
 	struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node);
 
 	if (pcie_pmu->on_cpu == -1) {
-		pcie_pmu->on_cpu = cpu;
-		WARN_ON(irq_set_affinity(pcie_pmu->irq, cpumask_of(cpu)));
+		pcie_pmu->on_cpu = cpumask_local_spread(0, dev_to_node(&pcie_pmu->pdev->dev));
+		WARN_ON(irq_set_affinity(pcie_pmu->irq, cpumask_of(pcie_pmu->on_cpu)));
 	}
 
 	return 0;
@@ -676,14 +676,23 @@ static int hisi_pcie_pmu_offline_cpu(unsigned int cpu, struct hlist_node *node)
 {
 	struct hisi_pcie_pmu *pcie_pmu = hlist_entry_safe(node, struct hisi_pcie_pmu, node);
 	unsigned int target;
+	cpumask_t mask;
+	int numa_node;
 
 	/* Nothing to do if this CPU doesn't own the PMU */
 	if (pcie_pmu->on_cpu != cpu)
 		return 0;
 
 	pcie_pmu->on_cpu = -1;
-	/* Choose a new CPU from all online cpus. */
-	target = cpumask_any_but(cpu_online_mask, cpu);
+
+	/* Choose a local CPU from all online cpus. */
+	numa_node = dev_to_node(&pcie_pmu->pdev->dev);
+	if (cpumask_and(&mask, cpumask_of_node(numa_node), cpu_online_mask) &&
+	    cpumask_andnot(&mask, &mask, cpumask_of(cpu)))
+		target = cpumask_any(&mask);
+	else
+		target = cpumask_any_but(cpu_online_mask, cpu);
+
 	if (target >= nr_cpu_ids) {
 		pci_err(pcie_pmu->pdev, "There is no CPU to set\n");
 		return 0;
diff --git a/drivers/perf/marvell_cn10k_ddr_pmu.c b/drivers/perf/marvell_cn10k_ddr_pmu.c
index b94a5f6cc22b..524ba82bfce2 100644
--- a/drivers/perf/marvell_cn10k_ddr_pmu.c
+++ b/drivers/perf/marvell_cn10k_ddr_pmu.c
@@ -8,11 +8,10 @@
 #include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/perf_event.h>
 #include <linux/hrtimer.h>
 #include <linux/acpi.h>
+#include <linux/platform_device.h>
 
 /* Performance Counters Operating Mode Control Registers */
 #define DDRC_PERF_CNT_OP_MODE_CTRL	0x8020
diff --git a/drivers/perf/marvell_cn10k_tad_pmu.c b/drivers/perf/marvell_cn10k_tad_pmu.c
index 3972197e2210..fec8e82edb95 100644
--- a/drivers/perf/marvell_cn10k_tad_pmu.c
+++ b/drivers/perf/marvell_cn10k_tad_pmu.c
@@ -6,10 +6,9 @@
 
 #define pr_fmt(fmt) "tad_pmu: " fmt
 
+#include <linux/io.h>
 #include <linux/module.h>
 #include <linux/of.h>
-#include <linux/of_address.h>
-#include <linux/of_device.h>
 #include <linux/cpuhotplug.h>
 #include <linux/perf_event.h>
 #include <linux/platform_device.h>
diff --git a/drivers/perf/xgene_pmu.c b/drivers/perf/xgene_pmu.c
index 0c32dffc7ede..9972bfc11a5c 100644
--- a/drivers/perf/xgene_pmu.c
+++ b/drivers/perf/xgene_pmu.c
@@ -1833,7 +1833,6 @@ static int xgene_pmu_probe(struct platform_device *pdev)
 	const struct xgene_pmu_data *dev_data;
 	const struct of_device_id *of_id;
 	struct xgene_pmu *xgene_pmu;
-	struct resource *res;
 	int irq, rc;
 	int version;
 
@@ -1883,8 +1882,7 @@ static int xgene_pmu_probe(struct platform_device *pdev)
 	xgene_pmu->version = version;
 	dev_info(&pdev->dev, "X-Gene PMU version %d\n", xgene_pmu->version);
 
-	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
-	xgene_pmu->pcppmu_csr = devm_ioremap_resource(&pdev->dev, res);
+	xgene_pmu->pcppmu_csr = devm_platform_ioremap_resource(pdev, 0);
 	if (IS_ERR(xgene_pmu->pcppmu_csr)) {
 		dev_err(&pdev->dev, "ioremap failed for PCP PMU resource\n");
 		return PTR_ERR(xgene_pmu->pcppmu_csr);