Perf events fixes left over from the v6.11 cycle:

- Fix energy-pkg event enumeration on certain AMD CPUs
  - Set up the LBR branch stack for BPF counting events too
 
 Signed-off-by: Ingo Molnar <mingo@kernel.org>
 -----BEGIN PGP SIGNATURE-----
 
 iQJFBAABCgAvFiEEBpT5eoXrXCwVQwEKEnMQ0APhK1gFAmbquN0RHG1pbmdvQGtl
 cm5lbC5vcmcACgkQEnMQ0APhK1gE7A//QEpiJJ+I979t+cJNcleXZ97fKYRn59z6
 Vkal94GTUDsaB09sgYo2RnjUWcIO8tSeeAIBjtCKgSwPwvXT1MxWVmQd/11vIpoo
 gLGKmUwuphtOMBvsWSof8j7QLGioUA/4AAnvVr3N6IS059c03NquCKONwoSShNII
 OOBENo/+AYywHkIhPSZw50bnNjLCQJ2gtcYFgsYwVKzbRHQqi3uNT42zwIIYAO14
 f4cWuRqG/ZTvGXUMZCQhvuFPQehK4sTTFxs3rRMfKA2+wwDf5f8rhduzzIjGF8cE
 zcoAXJbTBmCeQLyHfUMwuTLCIK4SAsTICJQVIm+ZmwuFZbxeH3PlLYJZ3YZjrR06
 uZi6+Lg2fXWOn/IQ3nWceE+qO7AdJOkWjOOQIh2GmXUR3UgVlHlS2BgZICssvFue
 qB5dvHYO6kJgWF4c5uKCF4A6YRlPLv5pUegnKojXrnL6CJ/JUh7qkhfKEYhxUKNE
 IOwUXci5XnGO4E/l9xZ+yW/I2F8sfjp49mvS+Myqb/fDJrb4p5AGopLPW+LuRcsy
 G5ByYNcjFpgHZ/xDsiE/N6+FbRwSzQ6/VizAu0aW3XpLQ5amOcXD0H+NjZvucof9
 OoxOaQrmwfQxmFF72cbkNOtiiDT49GP2C80wuDBa0meGfrR0s8VasEdFEF1pfJx4
 2UptHzXzzTQ=
 =BxbU
 -----END PGP SIGNATURE-----

Merge tag 'perf-urgent-2024-09-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull perf event fixes from Ingo Molnar:
 "Left over from the v6.11 cycle:

   - Fix energy-pkg event enumeration on certain AMD CPUs

   - Set up the LBR branch stack for BPF counting events too"

* tag 'perf-urgent-2024-09-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  perf/x86/intel: Allow to setup LBR for counting event for BPF
  perf/x86/rapl: Fix the energy-pkg event for AMD CPUs

arch/x86/events/intel/core.c

@@ -3972,8 +3972,12 @@ static int intel_pmu_hw_config(struct perf_event *event)
 			x86_pmu.pebs_aliases(event);
 	}
 
-	if (needs_branch_stack(event) && is_sampling_event(event))
+	if (needs_branch_stack(event)) {
-		event->hw.flags  |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+		/* Avoid branch stack setup for counting events in SAMPLE READ */
+		if (is_sampling_event(event) ||
+		    !(event->attr.sample_type & PERF_SAMPLE_READ))
+			event->hw.flags |= PERF_X86_EVENT_NEEDS_BRANCH_STACK;
+	}
 
 	if (branch_sample_counters(event)) {
 		struct perf_event *leader, *sibling;

arch/x86/events/rapl.c

@@ -103,6 +103,19 @@ static struct perf_pmu_events_attr event_attr_##v = {				\
 	.event_str	= str,							\
 };
 
+/*
+ * RAPL Package energy counter scope:
+ * 1. AMD/HYGON platforms have a per-PKG package energy counter
+ * 2. For Intel platforms
+ *	2.1. CLX-AP is multi-die and its RAPL MSRs are die-scope
+ *	2.2. Other Intel platforms are single die systems so the scope can be
+ *	     considered as either pkg-scope or die-scope, and we are considering
+ *	     them as die-scope.
+ */
+#define rapl_pmu_is_pkg_scope()				\
+	(boot_cpu_data.x86_vendor == X86_VENDOR_AMD ||	\
+	 boot_cpu_data.x86_vendor == X86_VENDOR_HYGON)
+
 struct rapl_pmu {
 	raw_spinlock_t		lock;
 	int			n_active;
@@ -140,9 +153,25 @@ static unsigned int rapl_cntr_mask;
 static u64 rapl_timer_ms;
 static struct perf_msr *rapl_msrs;
 
+/*
+ * Helper functions to get the correct topology macros according to the
+ * RAPL PMU scope.
+ */
+static inline unsigned int get_rapl_pmu_idx(int cpu)
+{
+	return rapl_pmu_is_pkg_scope() ? topology_logical_package_id(cpu) :
+					 topology_logical_die_id(cpu);
+}
+
+static inline const struct cpumask *get_rapl_pmu_cpumask(int cpu)
+{
+	return rapl_pmu_is_pkg_scope() ? topology_core_cpumask(cpu) :
+					 topology_die_cpumask(cpu);
+}
+
 static inline struct rapl_pmu *cpu_to_rapl_pmu(unsigned int cpu)
 {
-	unsigned int rapl_pmu_idx = topology_logical_die_id(cpu);
+	unsigned int rapl_pmu_idx = get_rapl_pmu_idx(cpu);
 
 	/*
 	 * The unsigned check also catches the '-1' return value for non
@@ -552,7 +581,7 @@ static int rapl_cpu_offline(unsigned int cpu)
 
 	pmu->cpu = -1;
 	/* Find a new cpu to collect rapl events */
-	target = cpumask_any_but(topology_die_cpumask(cpu), cpu);
+	target = cpumask_any_but(get_rapl_pmu_cpumask(cpu), cpu);
 
 	/* Migrate rapl events to the new target */
 	if (target < nr_cpu_ids) {
@@ -565,6 +594,11 @@ static int rapl_cpu_offline(unsigned int cpu)
 
 static int rapl_cpu_online(unsigned int cpu)
 {
+	s32 rapl_pmu_idx = get_rapl_pmu_idx(cpu);
+	if (rapl_pmu_idx < 0) {
+		pr_err("topology_logical_(package/die)_id() returned a negative value");
+		return -EINVAL;
+	}
 	struct rapl_pmu *pmu = cpu_to_rapl_pmu(cpu);
 	int target;
 
@@ -579,14 +613,14 @@ static int rapl_cpu_online(unsigned int cpu)
 		pmu->timer_interval = ms_to_ktime(rapl_timer_ms);
 		rapl_hrtimer_init(pmu);
 
-		rapl_pmus->pmus[topology_logical_die_id(cpu)] = pmu;
+		rapl_pmus->pmus[rapl_pmu_idx] = pmu;
 	}
 
 	/*
 	 * Check if there is an online cpu in the package which collects rapl
 	 * events already.
 	 */
-	target = cpumask_any_and(&rapl_cpu_mask, topology_die_cpumask(cpu));
+	target = cpumask_any_and(&rapl_cpu_mask, get_rapl_pmu_cpumask(cpu));
 	if (target < nr_cpu_ids)
 		return 0;
 
@@ -675,7 +709,10 @@ static const struct attribute_group *rapl_attr_update[] = {
 
 static int __init init_rapl_pmus(void)
 {
-	int nr_rapl_pmu = topology_max_packages() * topology_max_dies_per_package();
+	int nr_rapl_pmu = topology_max_packages();
+
+	if (!rapl_pmu_is_pkg_scope())
+		nr_rapl_pmu *= topology_max_dies_per_package();
 
 	rapl_pmus = kzalloc(struct_size(rapl_pmus, pmus, nr_rapl_pmu), GFP_KERNEL);
 	if (!rapl_pmus)