Merge tag 'perf-core-2021-02-17' of git://git.kernel.org/pub/scm/linu…

…x/kernel/git/tip/tip

Pull performance event updates from Ingo Molnar:

 - Add CPU-PMU support for Intel Sapphire Rapids CPUs

 - Extend the perf ABI with PERF_SAMPLE_WEIGHT_STRUCT, to offer
   two-parameter sampling event feedback. Not used yet, but is intended
   for Golden Cove CPU-PMU, which can provide both the instruction
   latency and the cache latency information for memory profiling
   events.

 - Remove experimental, default-disabled perfmon-v4 counter_freezing
   support that could only be enabled via a boot option. The hardware is
   hopelessly broken, we'd like to make sure nobody starts relying on
   this, as it would only end in tears.

 - Fix energy/power events on Intel SPR platforms

 - Simplify the uprobes resume_execution() logic

 - Misc smaller fixes.

* tag 'perf-core-2021-02-17' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/rapl: Fix psys-energy event on Intel SPR platform
  perf/x86/rapl: Only check lower 32bits for RAPL energy counters
  perf/x86/rapl: Add msr mask support
  perf/x86/kvm: Add Cascade Lake Xeon steppings to isolation_ucodes[]
  perf/x86/intel: Support CPUID 10.ECX to disable fixed counters
  perf/x86/intel: Add perf core PMU support for Sapphire Rapids
  perf/x86/intel: Filter unsupported Topdown metrics event
  perf/x86/intel: Factor out intel_update_topdown_event()
  perf/core: Add PERF_SAMPLE_WEIGHT_STRUCT
  perf/intel: Remove Perfmon-v4 counter_freezing support
  x86/perf: Use static_call for x86_pmu.guest_get_msrs
  perf/x86/intel/uncore: With > 8 nodes, get pci bus die id from NUMA info
  perf/x86/intel/uncore: Store the logical die id instead of the physical die id.
  x86/kprobes: Do not decode opcode in resume_execution()

Documentation/admin-guide/kernel-parameters.txt

@@ -945,12 +945,6 @@
 			causing system reset or hang due to sending
 			INIT from AP to BSP.
 
-	perf_v4_pmi=	[X86,INTEL]
-			Format: <bool>
-			Disable Intel PMU counter freezing feature.
-			The feature only exists starting from
-			Arch Perfmon v4 (Skylake and newer).
-
 	disable_ddw	[PPC/PSERIES]
 			Disable Dynamic DMA Window support. Use this
 			to workaround buggy firmware.

arch/powerpc/perf/core-book3s.c

@@ -2195,7 +2195,7 @@ static void record_and_restart(struct perf_event *event, unsigned long val,
 
 		if (event->attr.sample_type & PERF_SAMPLE_WEIGHT &&
 						ppmu->get_mem_weight)
-			ppmu->get_mem_weight(&data.weight);
+			ppmu->get_mem_weight(&data.weight.full);
 
 		if (perf_event_overflow(event, &data, regs))
 			power_pmu_stop(event, 0);

arch/x86/events/core.c

@@ -81,6 +81,8 @@ DEFINE_STATIC_CALL_NULL(x86_pmu_swap_task_ctx, *x86_pmu.swap_task_ctx);
 DEFINE_STATIC_CALL_NULL(x86_pmu_drain_pebs,   *x86_pmu.drain_pebs);
 DEFINE_STATIC_CALL_NULL(x86_pmu_pebs_aliases, *x86_pmu.pebs_aliases);
 
+DEFINE_STATIC_CALL_NULL(x86_pmu_guest_get_msrs,  *x86_pmu.guest_get_msrs);
+
 u64 __read_mostly hw_cache_event_ids
 				[PERF_COUNT_HW_CACHE_MAX]
 				[PERF_COUNT_HW_CACHE_OP_MAX]
@@ -253,6 +255,8 @@ static bool check_hw_exists(void)
 		if (ret)
 			goto msr_fail;
 		for (i = 0; i < x86_pmu.num_counters_fixed; i++) {
+			if (fixed_counter_disabled(i))
+				continue;
 			if (val & (0x03 << i*4)) {
 				bios_fail = 1;
 				val_fail = val;
@@ -665,6 +669,12 @@ void x86_pmu_disable_all(void)
 	}
 }
 
+struct perf_guest_switch_msr *perf_guest_get_msrs(int *nr)
+{
+	return static_call(x86_pmu_guest_get_msrs)(nr);
+}
+EXPORT_SYMBOL_GPL(perf_guest_get_msrs);
+
 /*
  * There may be PMI landing after enabled=0. The PMI hitting could be before or
  * after disable_all.
@@ -1523,6 +1533,8 @@ void perf_event_print_debug(void)
 			cpu, idx, prev_left);
 	}
 	for (idx = 0; idx < x86_pmu.num_counters_fixed; idx++) {
+		if (fixed_counter_disabled(idx))
+			continue;
 		rdmsrl(MSR_ARCH_PERFMON_FIXED_CTR0 + idx, pmc_count);
 
 		pr_info("CPU#%d: fixed-PMC%d count: %016llx\n",
@@ -1923,13 +1935,22 @@ static void x86_pmu_static_call_update(void)
 
 	static_call_update(x86_pmu_drain_pebs, x86_pmu.drain_pebs);
 	static_call_update(x86_pmu_pebs_aliases, x86_pmu.pebs_aliases);
+
+	static_call_update(x86_pmu_guest_get_msrs, x86_pmu.guest_get_msrs);
 }
 
 static void _x86_pmu_read(struct perf_event *event)
 {
 	x86_perf_event_update(event);
 }
 
+static inline struct perf_guest_switch_msr *
+perf_guest_get_msrs_nop(int *nr)
+{
+	*nr = 0;
+	return NULL;
+}
+
 static int __init init_hw_perf_events(void)
 {
 	struct x86_pmu_quirk *quirk;
@@ -1995,12 +2016,17 @@ static int __init init_hw_perf_events(void)
 	pr_info("... generic registers:      %d\n",     x86_pmu.num_counters);
 	pr_info("... value mask:             %016Lx\n", x86_pmu.cntval_mask);
 	pr_info("... max period:             %016Lx\n", x86_pmu.max_period);
-	pr_info("... fixed-purpose events:   %d\n",     x86_pmu.num_counters_fixed);
+	pr_info("... fixed-purpose events:   %lu\n",
+			hweight64((((1ULL << x86_pmu.num_counters_fixed) - 1)
+					<< INTEL_PMC_IDX_FIXED) & x86_pmu.intel_ctrl));
 	pr_info("... event mask:             %016Lx\n", x86_pmu.intel_ctrl);
 
 	if (!x86_pmu.read)
 		x86_pmu.read = _x86_pmu_read;
 
+	if (!x86_pmu.guest_get_msrs)
+		x86_pmu.guest_get_msrs = perf_guest_get_msrs_nop;
+
 	x86_pmu_static_call_update();
 
 	/*