Merge tag 'perf-core-2025-01-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Seqlock optimizations that arose in a perf context and were merged
  into the perf tree:

   - seqlock: Add raw_seqcount_try_begin (Suren Baghdasaryan)
   - mm: Convert mm_lock_seq to a proper seqcount (Suren Baghdasaryan)
   - mm: Introduce mmap_lock_speculate_{try_begin|retry} (Suren
     Baghdasaryan)
   - mm/gup: Use raw_seqcount_try_begin() (Peter Zijlstra)

  Core perf enhancements:

   - Reduce 'struct page' footprint of perf by mapping pages in advance
     (Lorenzo Stoakes)
   - Save raw sample data conditionally based on sample type (Yabin Cui)
   - Reduce sampling overhead by checking sample_type in
     perf_sample_save_callchain() and perf_sample_save_brstack() (Yabin
     Cui)
   - Export perf_exclude_event() (Namhyung Kim)

  Uprobes scalability enhancements: (Andrii Nakryiko)

   - Simplify find_active_uprobe_rcu() VMA checks
   - Add speculative lockless VMA-to-inode-to-uprobe resolution
   - Simplify session consumer tracking
   - Decouple return_instance list traversal and freeing
   - Ensure return_instance is detached from the list before freeing
   - Reuse return_instances between multiple uretprobes within task
   - Guard against kmemdup() failing in dup_return_instance()

  AMD core PMU driver enhancements:

   - Relax privilege filter restriction on AMD IBS (Namhyung Kim)

  AMD RAPL energy counters support: (Dhananjay Ugwekar)

   - Introduce topology_logical_core_id() (K Prateek Nayak)
   - Remove the unused get_rapl_pmu_cpumask() function
   - Remove the cpu_to_rapl_pmu() function
   - Rename rapl_pmu variables
   - Make rapl_model struct global
   - Add arguments to the init and cleanup functions
   - Modify the generic variable names to *_pkg*
   - Remove the global variable rapl_msrs
   - Move the cntr_mask to rapl_pmus struct
   - Add core energy counter support for AMD CPUs

  Intel core PMU driver enhancements:

   - Support RDPMC 'metrics clear mode' feature (Kan Liang)
   - Clarify adaptive PEBS processing (Kan Liang)
   - Factor out functions for PEBS records processing (Kan Liang)
   - Simplify the PEBS records processing for adaptive PEBS (Kan Liang)

  Intel uncore driver enhancements: (Kan Liang)

   - Convert buggy pmu->func_id use to pmu->registered
   - Support more units on Granite Rapids"

* tag 'perf-core-2025-01-20' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (33 commits)
  perf: map pages in advance
  perf/x86/intel/uncore: Support more units on Granite Rapids
  perf/x86/intel/uncore: Clean up func_id
  perf/x86/intel: Support RDPMC metrics clear mode
  uprobes: Guard against kmemdup() failing in dup_return_instance()
  perf/x86: Relax privilege filter restriction on AMD IBS
  perf/core: Export perf_exclude_event()
  uprobes: Reuse return_instances between multiple uretprobes within task
  uprobes: Ensure return_instance is detached from the list before freeing
  uprobes: Decouple return_instance list traversal and freeing
  uprobes: Simplify session consumer tracking
  uprobes: add speculative lockless VMA-to-inode-to-uprobe resolution
  uprobes: simplify find_active_uprobe_rcu() VMA checks
  mm: introduce mmap_lock_speculate_{try_begin|retry}
  mm: convert mm_lock_seq to a proper seqcount
  mm/gup: Use raw_seqcount_try_begin()
  seqlock: add raw_seqcount_try_begin
  perf/x86/rapl: Add core energy counter support for AMD CPUs
  perf/x86/rapl: Move the cntr_mask to rapl_pmus struct
  perf/x86/rapl: Remove the global variable rapl_msrs
  ...

3 files changed, 20 insertions, 2 deletions

diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index d95f902acc52..1ac79f361645 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -41,6 +41,7 @@
 #define INTEL_FIXED_0_USER				(1ULL << 1)
 #define INTEL_FIXED_0_ANYTHREAD			(1ULL << 2)
 #define INTEL_FIXED_0_ENABLE_PMI			(1ULL << 3)
+#define INTEL_FIXED_3_METRICS_CLEAR			(1ULL << 2)
 
 #define HSW_IN_TX					(1ULL << 32)
 #define HSW_IN_TX_CHECKPOINTED				(1ULL << 33)
@@ -372,6 +373,9 @@ static inline bool use_fixed_pseudo_encoding(u64 code)
 #define INTEL_TD_METRIC_MAX			INTEL_TD_METRIC_MEM_BOUND
 #define INTEL_TD_METRIC_NUM			8
 
+#define INTEL_TD_CFG_METRIC_CLEAR_BIT		0
+#define INTEL_TD_CFG_METRIC_CLEAR		BIT_ULL(INTEL_TD_CFG_METRIC_CLEAR_BIT)
+
 static inline bool is_metric_idx(int idx)
 {
 	return (unsigned)(idx - INTEL_PMC_IDX_METRIC_BASE) < INTEL_TD_METRIC_NUM;
@@ -422,7 +426,9 @@ static inline bool is_topdown_idx(int idx)
  */
 
 struct pebs_basic {
-	u64 format_size;
+	u64 format_group:32,
+	    retire_latency:16,
+	    format_size:16;
 	u64 ip;
 	u64 applicable_counters;
 	u64 tsc;
@@ -431,7 +437,17 @@ struct pebs_basic {
 struct pebs_meminfo {
 	u64 address;
 	u64 aux;
-	u64 latency;
+	union {
+		/* pre Alder Lake */
+		u64 mem_latency;
+		/* Alder Lake and later */
+		struct {
+			u64 instr_latency:16;
+			u64 pad2:16;
+			u64 cache_latency:16;
+			u64 pad3:16;
+		};
+	};
 	u64 tsx_tuning;
 };
 
diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 20e6009381ed..c0cd10182e90 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -98,6 +98,7 @@ struct cpuinfo_topology {
 	// Logical ID mappings
 	u32			logical_pkg_id;
 	u32			logical_die_id;
+	u32			logical_core_id;
 
 	// AMD Node ID and Nodes per Package info
 	u32			amd_node_id;
diff --git a/arch/x86/include/asm/topology.h b/arch/x86/include/asm/topology.h
index fd41103ad342..3973cb9bb2e6 100644
--- a/arch/x86/include/asm/topology.h
+++ b/arch/x86/include/asm/topology.h
@@ -143,6 +143,7 @@ extern const struct cpumask *cpu_clustergroup_mask(int cpu);
 #define topology_logical_package_id(cpu)	(cpu_data(cpu).topo.logical_pkg_id)
 #define topology_physical_package_id(cpu)	(cpu_data(cpu).topo.pkg_id)
 #define topology_logical_die_id(cpu)		(cpu_data(cpu).topo.logical_die_id)
+#define topology_logical_core_id(cpu)		(cpu_data(cpu).topo.logical_core_id)
 #define topology_die_id(cpu)			(cpu_data(cpu).topo.die_id)
 #define topology_core_id(cpu)			(cpu_data(cpu).topo.core_id)
 #define topology_ppin(cpu)			(cpu_data(cpu).ppin)