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

Pull perf events updates from Ingo Molnar:

 - Implement per-PMU context rescheduling to significantly improve
   single-PMU performance, and related cleanups/fixes (Peter Zijlstra
   and Namhyung Kim)

 - Fix ancient bug resulting in a lot of events being dropped
   erroneously at higher sampling frequencies (Luo Gengkun)

 - uprobes enhancements:

     - Implement RCU-protected hot path optimizations for better
       performance:

         "For baseline vs SRCU, peak througput increased from 3.7 M/s
          (million uprobe triggerings per second) up to about 8 M/s. For
          uretprobes it's a bit more modest with bump from 2.4 M/s to
          5 M/s.

          For SRCU vs RCU Tasks Trace, peak throughput for uprobes
          increases further from 8 M/s to 10.3 M/s (+28%!), and for
          uretprobes from 5.3 M/s to 5.8 M/s (+11%), as we have more
          work to do on uretprobes side.

          Even single-thread (no contention) performance is slightly
          better: 3.276 M/s to 3.396 M/s (+3.5%) for uprobes, and 2.055
          M/s to 2.174 M/s (+5.8%) for uretprobes."

          (Andrii Nakryiko et al)

     - Document mmap_lock, don't abuse get_user_pages_remote() (Oleg
       Nesterov)

     - Cleanups & fixes to prepare for future work:
        - Remove uprobe_register_refctr()
	- Simplify error handling for alloc_uprobe()
        - Make uprobe_register() return struct uprobe *
        - Fold __uprobe_unregister() into uprobe_unregister()
        - Shift put_uprobe() from delete_uprobe() to uprobe_unregister()
        - BPF: Fix use-after-free in bpf_uprobe_multi_link_attach()
          (Oleg Nesterov)

 - New feature & ABI extension: allow events to use PERF_SAMPLE READ
   with inheritance, enabling sample based profiling of a group of
   counters over a hierarchy of processes or threads (Ben Gainey)

 - Intel uncore & power events updates:

      - Add Arrow Lake and Lunar Lake support
      - Add PERF_EV_CAP_READ_SCOPE
      - Clean up and enhance cpumask and hotplug support
        (Kan Liang)

      - Add LNL uncore iMC freerunning support
      - Use D0:F0 as a default device
        (Zhenyu Wang)

 - Intel PT: fix AUX snapshot handling race (Adrian Hunter)

 - Misc fixes and cleanups (James Clark, Jiri Olsa, Oleg Nesterov and
   Peter Zijlstra)

* tag 'perf-core-2024-09-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (40 commits)
  dmaengine: idxd: Clean up cpumask and hotplug for perfmon
  iommu/vt-d: Clean up cpumask and hotplug for perfmon
  perf/x86/intel/cstate: Clean up cpumask and hotplug
  perf: Add PERF_EV_CAP_READ_SCOPE
  perf: Generic hotplug support for a PMU with a scope
  uprobes: perform lockless SRCU-protected uprobes_tree lookup
  rbtree: provide rb_find_rcu() / rb_find_add_rcu()
  perf/uprobe: split uprobe_unregister()
  uprobes: travers uprobe's consumer list locklessly under SRCU protection
  uprobes: get rid of enum uprobe_filter_ctx in uprobe filter callbacks
  uprobes: protected uprobe lifetime with SRCU
  uprobes: revamp uprobe refcounting and lifetime management
  bpf: Fix use-after-free in bpf_uprobe_multi_link_attach()
  perf/core: Fix small negative period being ignored
  perf: Really fix event_function_call() locking
  perf: Optimize __pmu_ctx_sched_out()
  perf: Add context time freeze
  perf: Fix event_function_call() locking
  perf: Extract a few helpers
  perf: Optimize context reschedule for single PMU cases
  ...

1 files changed, 30 insertions, 2 deletions

diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e336306b8c08..fb908843f209 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -168,6 +168,9 @@ struct hw_perf_event {
 			struct hw_perf_event_extra extra_reg;
 			struct hw_perf_event_extra branch_reg;
 		};
+		struct { /* aux / Intel-PT */
+			u64		aux_config;
+		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
 		};
@@ -292,6 +295,19 @@ struct perf_event_pmu_context;
 #define PERF_PMU_CAP_AUX_OUTPUT			0x0080
 #define PERF_PMU_CAP_EXTENDED_HW_TYPE		0x0100
 
+/**
+ * pmu::scope
+ */
+enum perf_pmu_scope {
+	PERF_PMU_SCOPE_NONE	= 0,
+	PERF_PMU_SCOPE_CORE,
+	PERF_PMU_SCOPE_DIE,
+	PERF_PMU_SCOPE_CLUSTER,
+	PERF_PMU_SCOPE_PKG,
+	PERF_PMU_SCOPE_SYS_WIDE,
+	PERF_PMU_MAX_SCOPE,
+};
+
 struct perf_output_handle;
 
 #define PMU_NULL_DEV	((void *)(~0UL))
@@ -315,6 +331,11 @@ struct pmu {
 	 */
 	int				capabilities;
 
+	/*
+	 * PMU scope
+	 */
+	unsigned int			scope;
+
 	int __percpu			*pmu_disable_count;
 	struct perf_cpu_pmu_context __percpu *cpu_pmu_context;
 	atomic_t			exclusive_cnt; /* < 0: cpu; > 0: tsk */
@@ -615,10 +636,13 @@ typedef void (*perf_overflow_handler_t)(struct perf_event *,
  * PERF_EV_CAP_SIBLING: An event with this flag must be a group sibling and
  * cannot be a group leader. If an event with this flag is detached from the
  * group it is scheduled out and moved into an unrecoverable ERROR state.
+ * PERF_EV_CAP_READ_SCOPE: A CPU event that can be read from any CPU of the
+ * PMU scope where it is active.
  */
 #define PERF_EV_CAP_SOFTWARE		BIT(0)
 #define PERF_EV_CAP_READ_ACTIVE_PKG	BIT(1)
 #define PERF_EV_CAP_SIBLING		BIT(2)
+#define PERF_EV_CAP_READ_SCOPE		BIT(3)
 
 #define SWEVENT_HLIST_BITS		8
 #define SWEVENT_HLIST_SIZE		(1 << SWEVENT_HLIST_BITS)
@@ -963,12 +987,16 @@ struct perf_event_context {
 	struct rcu_head			rcu_head;
 
 	/*
-	 * Sum (event->pending_work + event->pending_work)
+	 * The count of events for which using the switch-out fast path
+	 * should be avoided.
+	 *
+	 * Sum (event->pending_work + events with
+	 *    (attr->inherit && (attr->sample_type & PERF_SAMPLE_READ)))
 	 *
 	 * The SIGTRAP is targeted at ctx->task, as such it won't do changing
 	 * that until the signal is delivered.
 	 */
-	local_t				nr_pending;
+	local_t				nr_no_switch_fast;
 };
 
 struct perf_cpu_pmu_context {