17 files changed, 726 insertions, 23 deletions

diff --git a/arch/parisc/kernel/perf.c b/arch/parisc/kernel/perf.c
index e1a8fee3ad49..d46b6709ec56 100644
--- a/arch/parisc/kernel/perf.c
+++ b/arch/parisc/kernel/perf.c
@@ -300,7 +300,7 @@ static ssize_t perf_write(struct file *file, const char __user *buf,
 	else
 		return -EFAULT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	if (count != sizeof(uint32_t))
diff --git a/arch/powerpc/perf/imc-pmu.c b/arch/powerpc/perf/imc-pmu.c
index eb82dda884e5..0edcfd0b491d 100644
--- a/arch/powerpc/perf/imc-pmu.c
+++ b/arch/powerpc/perf/imc-pmu.c
@@ -976,7 +976,7 @@ static int thread_imc_event_init(struct perf_event *event)
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/* Sampling not supported */
@@ -1412,7 +1412,7 @@ static int trace_imc_event_init(struct perf_event *event)
 	if (event->attr.type != event->pmu->type)
 		return -ENOENT;
 
-	if (!capable(CAP_SYS_ADMIN))
+	if (!perfmon_capable())
 		return -EACCES;
 
 	/* Return if this is a couting event */
diff --git a/arch/x86/events/Kconfig b/arch/x86/events/Kconfig
index 9a7a1446cb3a..4a809c6cbd2f 100644
--- a/arch/x86/events/Kconfig
+++ b/arch/x86/events/Kconfig
@@ -10,11 +10,11 @@ config PERF_EVENTS_INTEL_UNCORE
 	available on NehalemEX and more modern processors.
 
 config PERF_EVENTS_INTEL_RAPL
-	tristate "Intel rapl performance events"
-	depends on PERF_EVENTS && CPU_SUP_INTEL && PCI
+	tristate "Intel/AMD rapl performance events"
+	depends on PERF_EVENTS && (CPU_SUP_INTEL || CPU_SUP_AMD) && PCI
 	default y
 	---help---
-	Include support for Intel rapl performance events for power
+	Include support for Intel and AMD rapl performance events for power
 	monitoring on modern processors.
 
 config PERF_EVENTS_INTEL_CSTATE
diff --git a/arch/x86/events/Makefile b/arch/x86/events/Makefile
index 9e07f554333f..12c42eba77ec 100644
--- a/arch/x86/events/Makefile
+++ b/arch/x86/events/Makefile
@@ -1,5 +1,8 @@
 # SPDX-License-Identifier: GPL-2.0-only
 obj-y					+= core.o probe.o
+obj-$(PERF_EVENTS_INTEL_RAPL)		+= rapl.o
 obj-y					+= amd/
 obj-$(CONFIG_X86_LOCAL_APIC)            += msr.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= intel/
+obj-$(CONFIG_CPU_SUP_CENTAUR)		+= zhaoxin/
+obj-$(CONFIG_CPU_SUP_ZHAOXIN)		+= zhaoxin/
diff --git a/arch/x86/events/core.c b/arch/x86/events/core.c
index a619763e96e1..9e63ee50b19a 100644
--- a/arch/x86/events/core.c
+++ b/arch/x86/events/core.c
@@ -1839,6 +1839,10 @@ static int __init init_hw_perf_events(void)
 		err = amd_pmu_init();
 		x86_pmu.name = "HYGON";
 		break;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		err = zhaoxin_pmu_init();
+		break;
 	default:
 		err = -ENOTSUPP;
 	}
diff --git a/arch/x86/events/intel/Makefile b/arch/x86/events/intel/Makefile
index 3468b0c1dc7c..e67a5886336c 100644
--- a/arch/x86/events/intel/Makefile
+++ b/arch/x86/events/intel/Makefile
@@ -2,8 +2,6 @@
 obj-$(CONFIG_CPU_SUP_INTEL)		+= core.o bts.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= ds.o knc.o
 obj-$(CONFIG_CPU_SUP_INTEL)		+= lbr.o p4.o p6.o pt.o
-obj-$(CONFIG_PERF_EVENTS_INTEL_RAPL)	+= intel-rapl-perf.o
-intel-rapl-perf-objs			:= rapl.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_UNCORE)	+= intel-uncore.o
 intel-uncore-objs			:= uncore.o uncore_nhmex.o uncore_snb.o uncore_snbep.o
 obj-$(CONFIG_PERF_EVENTS_INTEL_CSTATE)	+= intel-cstate.o
diff --git a/arch/x86/events/intel/bts.c b/arch/x86/events/intel/bts.c
index 6a3b599ee0fe..731dd8d0dbb1 100644
--- a/arch/x86/events/intel/bts.c
+++ b/arch/x86/events/intel/bts.c
@@ -58,7 +58,7 @@ struct bts_buffer {
 	local_t		head;
 	unsigned long	end;
 	void		**data_pages;
-	struct bts_phys	buf[0];
+	struct bts_phys	buf[];
 };
 
 static struct pmu bts_pmu;
diff --git a/arch/x86/events/intel/core.c b/arch/x86/events/intel/core.c
index 332954cccece..ca35c8b5ee10 100644
--- a/arch/x86/events/intel/core.c
+++ b/arch/x86/events/intel/core.c
@@ -1892,8 +1892,8 @@ static __initconst const u64 tnt_hw_cache_extra_regs
 
 static struct extra_reg intel_tnt_extra_regs[] __read_mostly = {
 	/* must define OFFCORE_RSP_X first, see intel_fixup_er() */
-	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0xffffff9fffull, RSP_0),
-	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xffffff9fffull, RSP_1),
+	INTEL_UEVENT_EXTRA_REG(0x01b7, MSR_OFFCORE_RSP_0, 0x800ff0ffffff9fffull, RSP_0),
+	INTEL_UEVENT_EXTRA_REG(0x02b7, MSR_OFFCORE_RSP_1, 0xff0ffffff9fffull, RSP_1),
 	EVENT_EXTRA_END
 };
 
diff --git a/arch/x86/events/intel/pt.c b/arch/x86/events/intel/pt.c
index 1db7a51d9792..e94af4a54d0d 100644
--- a/arch/x86/events/intel/pt.c
+++ b/arch/x86/events/intel/pt.c
@@ -226,8 +226,6 @@ static int __init pt_pmu_hw_init(void)
 			pt_pmu.vmx = true;
 	}
 
-	attrs = NULL;
-
 	for (i = 0; i < PT_CPUID_LEAVES; i++) {
 		cpuid_count(20, i,
 			    &pt_pmu.caps[CPUID_EAX + i*PT_CPUID_REGS_NUM],
diff --git a/arch/x86/events/intel/uncore.h b/arch/x86/events/intel/uncore.h
index 0da4a4605536..b469ddd45515 100644
--- a/arch/x86/events/intel/uncore.h
+++ b/arch/x86/events/intel/uncore.h
@@ -130,7 +130,7 @@ struct intel_uncore_box {
 	struct list_head list;
 	struct list_head active_list;
 	void __iomem *io_addr;
-	struct intel_uncore_extra_reg shared_regs[0];
+	struct intel_uncore_extra_reg shared_regs[];
 };
 
 /* CFL uncore 8th cbox MSRs */
diff --git a/arch/x86/events/perf_event.h b/arch/x86/events/perf_event.h
index f1cd1ca1a77b..e17a3d8a47ed 100644
--- a/arch/x86/events/perf_event.h
+++ b/arch/x86/events/perf_event.h
@@ -618,6 +618,7 @@ struct x86_pmu {
 
 	/* PMI handler bits */
 	unsigned int	late_ack		:1,
+			enabled_ack		:1,
 			counter_freezing	:1;
 	/*
 	 * sysfs attrs
@@ -1133,3 +1134,12 @@ static inline int is_ht_workaround_enabled(void)
 	return 0;
 }
 #endif /* CONFIG_CPU_SUP_INTEL */
+
+#if ((defined CONFIG_CPU_SUP_CENTAUR) || (defined CONFIG_CPU_SUP_ZHAOXIN))
+int zhaoxin_pmu_init(void);
+#else
+static inline int zhaoxin_pmu_init(void)
+{
+	return 0;
+}
+#endif /*CONFIG_CPU_SUP_CENTAUR or CONFIG_CPU_SUP_ZHAOXIN*/
diff --git a/arch/x86/events/probe.c b/arch/x86/events/probe.c
index c2ede2f3b277..136a1e847254 100644
--- a/arch/x86/events/probe.c
+++ b/arch/x86/events/probe.c
@@ -10,6 +10,11 @@ not_visible(struct kobject *kobj, struct attribute *attr, int i)
 	return 0;
 }
 
+/*
+ * Accepts msr[] array with non populated entries as long as either
+ * msr[i].msr is 0 or msr[i].grp is NULL. Note that the default sysfs
+ * visibility is visible when group->is_visible callback is set.
+ */
 unsigned long
 perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
 {
@@ -24,8 +29,16 @@ perf_msr_probe(struct perf_msr *msr, int cnt, bool zero, void *data)
 		if (!msr[bit].no_check) {
 			struct attribute_group *grp = msr[bit].grp;
 
+			/* skip entry with no group */
+			if (!grp)
+				continue;
+
 			grp->is_visible = not_visible;
 
+			/* skip unpopulated entry */
+			if (!msr[bit].msr)
+				continue;
+
 			if (msr[bit].test && !msr[bit].test(bit, data))
 				continue;
 			/* Virt sucks; you cannot tell if a R/O MSR is present :/ */
diff --git a/arch/x86/events/intel/rapl.c b/arch/x86/events/rapl.c
index a5dbd25852cb..0f2bf59f4354 100644
--- a/arch/x86/events/intel/rapl.c
+++ b/arch/x86/events/rapl.c
@@ -1,11 +1,14 @@
 // SPDX-License-Identifier: GPL-2.0-only
 /*
- * Support Intel RAPL energy consumption counters
+ * Support Intel/AMD RAPL energy consumption counters
  * Copyright (C) 2013 Google, Inc., Stephane Eranian
  *
  * Intel RAPL interface is specified in the IA-32 Manual Vol3b
  * section 14.7.1 (September 2013)
  *
+ * AMD RAPL interface for Fam17h is described in the public PPR:
+ * https://bugzilla.kernel.org/show_bug.cgi?id=206537
+ *
  * RAPL provides more controls than just reporting energy consumption
  * however here we only expose the 3 energy consumption free running
  * counters (pp0, pkg, dram).
@@ -58,8 +61,8 @@
 #include <linux/nospec.h>
 #include <asm/cpu_device_id.h>
 #include <asm/intel-family.h>
-#include "../perf_event.h"
-#include "../probe.h"
+#include "perf_event.h"
+#include "probe.h"
 
 MODULE_LICENSE("GPL");
 
@@ -128,7 +131,9 @@ struct rapl_pmus {
 };
 
 struct rapl_model {
+	struct perf_msr *rapl_msrs;
 	unsigned long	events;
+	unsigned int	msr_power_unit;
 	bool		apply_quirk;
 };
 
@@ -138,7 +143,7 @@ static struct rapl_pmus *rapl_pmus;
 static cpumask_t rapl_cpu_mask;
 static unsigned int rapl_cntr_mask;
 static u64 rapl_timer_ms;
-static struct perf_msr rapl_msrs[];
+static struct perf_msr *rapl_msrs;
 
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
@@ -455,9 +460,16 @@ static struct attribute *rapl_events_cores[] = {
 	NULL,
 };
 
+static umode_t
+rapl_not_visible(struct kobject *kobj, struct attribute *attr, int i)
+{
+	return 0;
+}
+
 static struct attribute_group rapl_events_cores_group = {
 	.name  = "events",
 	.attrs = rapl_events_cores,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_pkg[] = {
@@ -470,6 +482,7 @@ static struct attribute *rapl_events_pkg[] = {
 static struct attribute_group rapl_events_pkg_group = {
 	.name  = "events",
 	.attrs = rapl_events_pkg,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_ram[] = {
@@ -482,6 +495,7 @@ static struct attribute *rapl_events_ram[] = {
 static struct attribute_group rapl_events_ram_group = {
 	.name  = "events",
 	.attrs = rapl_events_ram,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_gpu[] = {
@@ -494,6 +508,7 @@ static struct attribute *rapl_events_gpu[] = {
 static struct attribute_group rapl_events_gpu_group = {
 	.name  = "events",
 	.attrs = rapl_events_gpu,
+	.is_visible = rapl_not_visible,
 };
 
 static struct attribute *rapl_events_psys[] = {
@@ -506,6 +521,7 @@ static struct attribute *rapl_events_psys[] = {
 static struct attribute_group rapl_events_psys_group = {
 	.name  = "events",
 	.attrs = rapl_events_psys,
+	.is_visible = rapl_not_visible,
 };
 
 static bool test_msr(int idx, void *data)
@@ -513,7 +529,7 @@ static bool test_msr(int idx, void *data)
 	return test_bit(idx, (unsigned long *) data);
 }
 
-static struct perf_msr rapl_msrs[] = {
+static struct perf_msr intel_rapl_msrs[] = {
 	[PERF_RAPL_PP0]  = { MSR_PP0_ENERGY_STATUS,      &rapl_events_cores_group, test_msr },
 	[PERF_RAPL_PKG]  = { MSR_PKG_ENERGY_STATUS,      &rapl_events_pkg_group,   test_msr },
 	[PERF_RAPL_RAM]  = { MSR_DRAM_ENERGY_STATUS,     &rapl_events_ram_group,   test_msr },
@@ -521,6 +537,16 @@ static struct perf_msr rapl_msrs[] = {
 	[PERF_RAPL_PSYS] = { MSR_PLATFORM_ENERGY_STATUS, &rapl_events_psys_group,  test_msr },
 };
 
+/*
+ * Force to PERF_RAPL_MAX size due to:
+ * - perf_msr_probe(PERF_RAPL_MAX)
+ * - want to use same event codes across both architectures
+ */
+static struct perf_msr amd_rapl_msrs[PERF_RAPL_MAX] = {
+	[PERF_RAPL_PKG]  = { MSR_AMD_PKG_ENERGY_STATUS,  &rapl_events_pkg_group,   test_msr },
+};
+
+
 static int rapl_cpu_offline(unsigned int cpu)
 {
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
@@ -575,13 +601,13 @@ static int rapl_cpu_online(unsigned int cpu)
 	return 0;
 }
 
-static int rapl_check_hw_unit(bool apply_quirk)
+static int rapl_check_hw_unit(struct rapl_model *rm)
 {
 	u64 msr_rapl_power_unit_bits;
 	int i;
 
 	/* protect rdmsrl() to handle virtualization */
-	if (rdmsrl_safe(MSR_RAPL_POWER_UNIT, &msr_rapl_power_unit_bits))
+	if (rdmsrl_safe(rm->msr_power_unit, &msr_rapl_power_unit_bits))
 		return -1;
 	for (i = 0; i < NR_RAPL_DOMAINS; i++)
 		rapl_hw_unit[i] = (msr_rapl_power_unit_bits >> 8) & 0x1FULL;
@@ -592,7 +618,7 @@ static int rapl_check_hw_unit(bool apply_quirk)
 	 * "Intel Xeon Processor E5-1600 and E5-2600 v3 Product Families, V2
 	 * of 2. Datasheet, September 2014, Reference Number: 330784-001 "
 	 */
-	if (apply_quirk)
+	if (rm->apply_quirk)
 		rapl_hw_unit[PERF_RAPL_RAM] = 16;
 
 	/*
@@ -673,6 +699,8 @@ static struct rapl_model model_snb = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_PP1),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_snbep = {
@@ -680,6 +708,8 @@ static struct rapl_model model_snbep = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsw = {
@@ -688,6 +718,8 @@ static struct rapl_model model_hsw = {
 			  BIT(PERF_RAPL_RAM) |
 			  BIT(PERF_RAPL_PP1),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_hsx = {
@@ -695,12 +727,16 @@ static struct rapl_model model_hsx = {
 			  BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.apply_quirk	= true,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_knl = {
 	.events		= BIT(PERF_RAPL_PKG) |
 			  BIT(PERF_RAPL_RAM),
 	.apply_quirk	= true,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
 };
 
 static struct rapl_model model_skl = {
@@ -710,6 +746,15 @@ static struct rapl_model model_skl = {
 			  BIT(PERF_RAPL_PP1) |
 			  BIT(PERF_RAPL_PSYS),
 	.apply_quirk	= false,
+	.msr_power_unit = MSR_RAPL_POWER_UNIT,
+	.rapl_msrs      = intel_rapl_msrs,
+};
+
+static struct rapl_model model_amd_fam17h = {
+	.events		= BIT(PERF_RAPL_PKG),
+	.apply_quirk	= false,
+	.msr_power_unit = MSR_AMD_RAPL_POWER_UNIT,
+	.rapl_msrs      = amd_rapl_msrs,
 };
 
 static const struct x86_cpu_id rapl_model_match[] __initconst = {
@@ -738,8 +783,11 @@ static const struct x86_cpu_id rapl_model_match[] __initconst = {
 	X86_MATCH_INTEL_FAM6_MODEL(ATOM_GOLDMONT_PLUS,	&model_hsw),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE,		&model_skl),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_D,		&model_hsx),
+	X86_MATCH_INTEL_FAM6_MODEL(ICELAKE_X,		&model_hsx),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE_L,		&model_skl),
 	X86_MATCH_INTEL_FAM6_MODEL(COMETLAKE,		&model_skl),
+	X86_MATCH_VENDOR_FAM(AMD, 0x17, &model_amd_fam17h),
 	{},
 };
 MODULE_DEVICE_TABLE(x86cpu, rapl_model_match);
@@ -755,10 +803,13 @@ static int __init rapl_pmu_init(void)
 		return -ENODEV;
 
 	rm = (struct rapl_model *) id->driver_data;
+
+	rapl_msrs = rm->rapl_msrs;
+
 	rapl_cntr_mask = perf_msr_probe(rapl_msrs, PERF_RAPL_MAX,
 					false, (void *) &rm->events);
 
-	ret = rapl_check_hw_unit(rm->apply_quirk);
+	ret = rapl_check_hw_unit(rm);
 	if (ret)
 		return ret;
 
diff --git a/arch/x86/events/zhaoxin/Makefile b/arch/x86/events/zhaoxin/Makefile
new file mode 100644
index 000000000000..642c1174d662
--- /dev/null
+++ b/arch/x86/events/zhaoxin/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-y	+= core.o
diff --git a/arch/x86/events/zhaoxin/core.c b/arch/x86/events/zhaoxin/core.c
new file mode 100644
index 000000000000..898fa1ae9ceb
--- /dev/null
+++ b/arch/x86/events/zhaoxin/core.c
@@ -0,0 +1,613 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Zhoaxin PMU; like Intel Architectural PerfMon-v2
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/stddef.h>
+#include <linux/types.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/nmi.h>
+
+#include <asm/cpufeature.h>
+#include <asm/hardirq.h>
+#include <asm/apic.h>
+
+#include "../perf_event.h"
+
+/*
+ * Zhaoxin PerfMon, used on zxc and later.
+ */
+static u64 zx_pmon_event_map[PERF_COUNT_HW_MAX] __read_mostly = {
+
+	[PERF_COUNT_HW_CPU_CYCLES]        = 0x0082,
+	[PERF_COUNT_HW_INSTRUCTIONS]      = 0x00c0,
+	[PERF_COUNT_HW_CACHE_REFERENCES]  = 0x0515,
+	[PERF_COUNT_HW_CACHE_MISSES]      = 0x051a,
+	[PERF_COUNT_HW_BUS_CYCLES]        = 0x0083,
+};
+
+static struct event_constraint zxc_event_constraints[] __read_mostly = {
+
+	FIXED_EVENT_CONSTRAINT(0x0082, 1), /* unhalted core clock cycles */
+	EVENT_CONSTRAINT_END
+};
+
+static struct event_constraint zxd_event_constraints[] __read_mostly = {
+
+	FIXED_EVENT_CONSTRAINT(0x00c0, 0), /* retired instructions */
+	FIXED_EVENT_CONSTRAINT(0x0082, 1), /* unhalted core clock cycles */
+	FIXED_EVENT_CONSTRAINT(0x0083, 2), /* unhalted bus clock cycles */
+	EVENT_CONSTRAINT_END
+};
+
+static __initconst const u64 zxd_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0042,
+		[C(RESULT_MISS)] = 0x0538,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0043,
+		[C(RESULT_MISS)] = 0x0562,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0300,
+		[C(RESULT_MISS)] = 0x0301,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x030a,
+		[C(RESULT_MISS)] = 0x030b,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0042,
+		[C(RESULT_MISS)] = 0x052c,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0043,
+		[C(RESULT_MISS)] = 0x0530,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x0564,
+		[C(RESULT_MISS)] = 0x0565,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c0,
+		[C(RESULT_MISS)] = 0x0534,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0700,
+		[C(RESULT_MISS)] = 0x0709,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+};
+
+static __initconst const u64 zxe_hw_cache_event_ids
+				[PERF_COUNT_HW_CACHE_MAX]
+				[PERF_COUNT_HW_CACHE_OP_MAX]
+				[PERF_COUNT_HW_CACHE_RESULT_MAX] = {
+[C(L1D)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0568,
+		[C(RESULT_MISS)] = 0x054b,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0669,
+		[C(RESULT_MISS)] = 0x0562,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(L1I)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0300,
+		[C(RESULT_MISS)] = 0x0301,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x030a,
+		[C(RESULT_MISS)] = 0x030b,
+	},
+},
+[C(LL)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0,
+		[C(RESULT_MISS)] = 0x0,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0,
+		[C(RESULT_MISS)] = 0x0,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x0,
+		[C(RESULT_MISS)] = 0x0,
+	},
+},
+[C(DTLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0568,
+		[C(RESULT_MISS)] = 0x052c,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = 0x0669,
+		[C(RESULT_MISS)] = 0x0530,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = 0x0564,
+		[C(RESULT_MISS)] = 0x0565,
+	},
+},
+[C(ITLB)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x00c0,
+		[C(RESULT_MISS)] = 0x0534,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(BPU)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = 0x0028,
+		[C(RESULT_MISS)] = 0x0029,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+[C(NODE)] = {
+	[C(OP_READ)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_WRITE)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+	[C(OP_PREFETCH)] = {
+		[C(RESULT_ACCESS)] = -1,
+		[C(RESULT_MISS)] = -1,
+	},
+},
+};
+
+static void zhaoxin_pmu_disable_all(void)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, 0);
+}
+
+static void zhaoxin_pmu_enable_all(int added)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_CTRL, x86_pmu.intel_ctrl);
+}
+
+static inline u64 zhaoxin_pmu_get_status(void)
+{
+	u64 status;
+
+	rdmsrl(MSR_CORE_PERF_GLOBAL_STATUS, status);
+
+	return status;
+}
+
+static inline void zhaoxin_pmu_ack_status(u64 ack)
+{
+	wrmsrl(MSR_CORE_PERF_GLOBAL_OVF_CTRL, ack);
+}
+
+static inline void zxc_pmu_ack_status(u64 ack)
+{
+	/*
+	 * ZXC needs global control enabled in order to clear status bits.
+	 */
+	zhaoxin_pmu_enable_all(0);
+	zhaoxin_pmu_ack_status(ack);
+	zhaoxin_pmu_disable_all();
+}
+
+static void zhaoxin_pmu_disable_fixed(struct hw_perf_event *hwc)
+{
+	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+	u64 ctrl_val, mask;
+
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void zhaoxin_pmu_disable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		zhaoxin_pmu_disable_fixed(hwc);
+		return;
+	}
+
+	x86_pmu_disable_event(event);
+}
+
+static void zhaoxin_pmu_enable_fixed(struct hw_perf_event *hwc)
+{
+	int idx = hwc->idx - INTEL_PMC_IDX_FIXED;
+	u64 ctrl_val, bits, mask;
+
+	/*
+	 * Enable IRQ generation (0x8),
+	 * and enable ring-3 counting (0x2) and ring-0 counting (0x1)
+	 * if requested:
+	 */
+	bits = 0x8ULL;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_USR)
+		bits |= 0x2;
+	if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+		bits |= 0x1;
+
+	bits <<= (idx * 4);
+	mask = 0xfULL << (idx * 4);
+
+	rdmsrl(hwc->config_base, ctrl_val);
+	ctrl_val &= ~mask;
+	ctrl_val |= bits;
+	wrmsrl(hwc->config_base, ctrl_val);
+}
+
+static void zhaoxin_pmu_enable_event(struct perf_event *event)
+{
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (unlikely(hwc->config_base == MSR_ARCH_PERFMON_FIXED_CTR_CTRL)) {
+		zhaoxin_pmu_enable_fixed(hwc);
+		return;
+	}
+
+	__x86_pmu_enable_event(hwc, ARCH_PERFMON_EVENTSEL_ENABLE);
+}
+
+/*
+ * This handler is triggered by the local APIC, so the APIC IRQ handling
+ * rules apply:
+ */
+static int zhaoxin_pmu_handle_irq(struct pt_regs *regs)
+{
+	struct perf_sample_data data;
+	struct cpu_hw_events *cpuc;
+	int handled = 0;
+	u64 status;
+	int bit;
+
+	cpuc = this_cpu_ptr(&cpu_hw_events);
+	apic_write(APIC_LVTPC, APIC_DM_NMI);
+	zhaoxin_pmu_disable_all();
+	status = zhaoxin_pmu_get_status();
+	if (!status)
+		goto done;
+
+again:
+	if (x86_pmu.enabled_ack)
+		zxc_pmu_ack_status(status);
+	else
+		zhaoxin_pmu_ack_status(status);
+
+	inc_irq_stat(apic_perf_irqs);
+
+	/*
+	 * CondChgd bit 63 doesn't mean any overflow status. Ignore
+	 * and clear the bit.
+	 */
+	if (__test_and_clear_bit(63, (unsigned long *)&status)) {
+		if (!status)
+			goto done;
+	}
+
+	for_each_set_bit(bit, (unsigned long *)&status, X86_PMC_IDX_MAX) {
+		struct perf_event *event = cpuc->events[bit];
+
+		handled++;
+
+		if (!test_bit(bit, cpuc->active_mask))
+			continue;
+
+		x86_perf_event_update(event);
+		perf_sample_data_init(&data, 0, event->hw.last_period);
+
+		if (!x86_perf_event_set_period(event))
+			continue;
+
+		if (perf_event_overflow(event, &data, regs))
+			x86_pmu_stop(event, 0);
+	}
+
+	/*
+	 * Repeat if there is more work to be done:
+	 */
+	status = zhaoxin_pmu_get_status();
+	if (status)
+		goto again;
+
+done:
+	zhaoxin_pmu_enable_all(0);
+	return handled;
+}
+
+static u64 zhaoxin_pmu_event_map(int hw_event)
+{
+	return zx_pmon_event_map[hw_event];
+}
+
+static struct event_constraint *
+zhaoxin_get_event_constraints(struct cpu_hw_events *cpuc, int idx,
+			struct perf_event *event)
+{
+	struct event_constraint *c;
+
+	if (x86_pmu.event_constraints) {
+		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			if ((event->hw.config & c->cmask) == c->code)
+				return c;
+		}
+	}
+
+	return &unconstrained;
+}
+
+PMU_FORMAT_ATTR(event,	"config:0-7");
+PMU_FORMAT_ATTR(umask,	"config:8-15");
+PMU_FORMAT_ATTR(edge,	"config:18");
+PMU_FORMAT_ATTR(inv,	"config:23");
+PMU_FORMAT_ATTR(cmask,	"config:24-31");
+
+static struct attribute *zx_arch_formats_attr[] = {
+	&format_attr_event.attr,
+	&format_attr_umask.attr,
+	&format_attr_edge.attr,
+	&format_attr_inv.attr,
+	&format_attr_cmask.attr,
+	NULL,
+};
+
+static ssize_t zhaoxin_event_sysfs_show(char *page, u64 config)
+{
+	u64 event = (config & ARCH_PERFMON_EVENTSEL_EVENT);
+
+	return x86_event_sysfs_show(page, config, event);
+}
+
+static const struct x86_pmu zhaoxin_pmu __initconst = {
+	.name			= "zhaoxin",
+	.handle_irq		= zhaoxin_pmu_handle_irq,
+	.disable_all		= zhaoxin_pmu_disable_all,
+	.enable_all		= zhaoxin_pmu_enable_all,
+	.enable			= zhaoxin_pmu_enable_event,
+	.disable		= zhaoxin_pmu_disable_event,
+	.hw_config		= x86_pmu_hw_config,
+	.schedule_events	= x86_schedule_events,
+	.eventsel		= MSR_ARCH_PERFMON_EVENTSEL0,
+	.perfctr		= MSR_ARCH_PERFMON_PERFCTR0,
+	.event_map		= zhaoxin_pmu_event_map,
+	.max_events		= ARRAY_SIZE(zx_pmon_event_map),
+	.apic			= 1,
+	/*
+	 * For zxd/zxe, read/write operation for PMCx MSR is 48 bits.
+	 */
+	.max_period		= (1ULL << 47) - 1,
+	.get_event_constraints	= zhaoxin_get_event_constraints,
+
+	.format_attrs		= zx_arch_formats_attr,
+	.events_sysfs_show	= zhaoxin_event_sysfs_show,
+};
+
+static const struct { int id; char *name; } zx_arch_events_map[] __initconst = {
+	{ PERF_COUNT_HW_CPU_CYCLES, "cpu cycles" },
+	{ PERF_COUNT_HW_INSTRUCTIONS, "instructions" },
+	{ PERF_COUNT_HW_BUS_CYCLES, "bus cycles" },
+	{ PERF_COUNT_HW_CACHE_REFERENCES, "cache references" },
+	{ PERF_COUNT_HW_CACHE_MISSES, "cache misses" },
+	{ PERF_COUNT_HW_BRANCH_INSTRUCTIONS, "branch instructions" },
+	{ PERF_COUNT_HW_BRANCH_MISSES, "branch misses" },
+};
+
+static __init void zhaoxin_arch_events_quirk(void)
+{
+	int bit;
+
+	/* disable event that reported as not presend by cpuid */
+	for_each_set_bit(bit, x86_pmu.events_mask, ARRAY_SIZE(zx_arch_events_map)) {
+		zx_pmon_event_map[zx_arch_events_map[bit].id] = 0;
+		pr_warn("CPUID marked event: \'%s\' unavailable\n",
+			zx_arch_events_map[bit].name);
+	}
+}
+
+__init int zhaoxin_pmu_init(void)
+{
+	union cpuid10_edx edx;
+	union cpuid10_eax eax;
+	union cpuid10_ebx ebx;
+	struct event_constraint *c;
+	unsigned int unused;
+	int version;
+
+	pr_info("Welcome to zhaoxin pmu!\n");
+
+	/*
+	 * Check whether the Architectural PerfMon supports
+	 * hw_event or not.
+	 */
+	cpuid(10, &eax.full, &ebx.full, &unused, &edx.full);
+
+	if (eax.split.mask_length < ARCH_PERFMON_EVENTS_COUNT - 1)
+		return -ENODEV;
+
+	version = eax.split.version_id;
+	if (version != 2)
+		return -ENODEV;
+
+	x86_pmu = zhaoxin_pmu;
+	pr_info("Version check pass!\n");
+
+	x86_pmu.version			= version;
+	x86_pmu.num_counters		= eax.split.num_counters;
+	x86_pmu.cntval_bits		= eax.split.bit_width;
+	x86_pmu.cntval_mask		= (1ULL << eax.split.bit_width) - 1;
+	x86_pmu.events_maskl		= ebx.full;
+	x86_pmu.events_mask_len		= eax.split.mask_length;
+
+	x86_pmu.num_counters_fixed = edx.split.num_counters_fixed;
+	x86_add_quirk(zhaoxin_arch_events_quirk);
+
+	switch (boot_cpu_data.x86) {
+	case 0x06:
+		if (boot_cpu_data.x86_model == 0x0f || boot_cpu_data.x86_model == 0x19) {
+
+			x86_pmu.max_period = x86_pmu.cntval_mask >> 1;
+
+			/* Clearing status works only if the global control is enable on zxc. */
+			x86_pmu.enabled_ack = 1;
+
+			x86_pmu.event_constraints = zxc_event_constraints;
+			zx_pmon_event_map[PERF_COUNT_HW_INSTRUCTIONS] = 0;
+			zx_pmon_event_map[PERF_COUNT_HW_CACHE_REFERENCES] = 0;
+			zx_pmon_event_map[PERF_COUNT_HW_CACHE_MISSES] = 0;
+			zx_pmon_event_map[PERF_COUNT_HW_BUS_CYCLES] = 0;
+
+			pr_cont("ZXC events, ");
+			break;
+		}
+		return -ENODEV;
+
+	case 0x07:
+		zx_pmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_FRONTEND] =
+			X86_CONFIG(.event = 0x01, .umask = 0x01, .inv = 0x01, .cmask = 0x01);
+
+		zx_pmon_event_map[PERF_COUNT_HW_STALLED_CYCLES_BACKEND] =
+			X86_CONFIG(.event = 0x0f, .umask = 0x04, .inv = 0, .cmask = 0);
+
+		switch (boot_cpu_data.x86_model) {
+		case 0x1b:
+			memcpy(hw_cache_event_ids, zxd_hw_cache_event_ids,
+			       sizeof(hw_cache_event_ids));
+
+			x86_pmu.event_constraints = zxd_event_constraints;
+
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x0700;
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x0709;
+
+			pr_cont("ZXD events, ");
+			break;
+		case 0x3b:
+			memcpy(hw_cache_event_ids, zxe_hw_cache_event_ids,
+			       sizeof(hw_cache_event_ids));
+
+			x86_pmu.event_constraints = zxd_event_constraints;
+
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_INSTRUCTIONS] = 0x0028;
+			zx_pmon_event_map[PERF_COUNT_HW_BRANCH_MISSES] = 0x0029;
+
+			pr_cont("ZXE events, ");
+			break;
+		default:
+			return -ENODEV;
+		}
+		break;
+
+	default:
+		return -ENODEV;
+	}
+
+	x86_pmu.intel_ctrl = (1 << (x86_pmu.num_counters)) - 1;
+	x86_pmu.intel_ctrl |= ((1LL << x86_pmu.num_counters_fixed)-1) << INTEL_PMC_IDX_FIXED;
+
+	if (x86_pmu.event_constraints) {
+		for_each_event_constraint(c, x86_pmu.event_constraints) {
+			c->idxmsk64 |= (1ULL << x86_pmu.num_counters) - 1;
+			c->weight += x86_pmu.num_counters;
+		}
+	}
+
+	return 0;
+}
+
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 12c9684d59ba..ef452b817f44 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -301,6 +301,9 @@
 #define MSR_PP1_ENERGY_STATUS		0x00000641
 #define MSR_PP1_POLICY			0x00000642
 
+#define MSR_AMD_PKG_ENERGY_STATUS	0xc001029b
+#define MSR_AMD_RAPL_POWER_UNIT		0xc0010299
+
 /* Config TDP MSRs */
 #define MSR_CONFIG_TDP_NOMINAL		0x00000648
 #define MSR_CONFIG_TDP_LEVEL_1		0x00000649
diff --git a/arch/x86/kernel/cpu/perfctr-watchdog.c b/arch/x86/kernel/cpu/perfctr-watchdog.c
index 9556930cd8c1..a5ee607a3b89 100644
--- a/arch/x86/kernel/cpu/perfctr-watchdog.c
+++ b/arch/x86/kernel/cpu/perfctr-watchdog.c
@@ -63,6 +63,10 @@ static inline unsigned int nmi_perfctr_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BPU_PERFCTR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_PERFCTR0;
 	}
 	return 0;
 }
@@ -92,6 +96,10 @@ static inline unsigned int nmi_evntsel_msr_to_bit(unsigned int msr)
 		case 15:
 			return msr - MSR_P4_BSU_ESCR0;
 		}
+		fallthrough;
+	case X86_VENDOR_ZHAOXIN:
+	case X86_VENDOR_CENTAUR:
+		return msr - MSR_ARCH_PERFMON_EVENTSEL0;
 	}
 	return 0;