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
  ...

4 files changed, 122 insertions, 27 deletions

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index f39186738d81..2361ed4d2b15 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -153,7 +153,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_AMD_UNCORE_STARTING,
 	CPUHP_AP_PERF_X86_STARTING,
 	CPUHP_AP_PERF_X86_AMD_IBS_STARTING,
-	CPUHP_AP_PERF_X86_CSTATE_STARTING,
 	CPUHP_AP_PERF_XTENSA_STARTING,
 	CPUHP_AP_ARM_VFP_STARTING,
 	CPUHP_AP_ARM64_DEBUG_MONITORS_STARTING,
@@ -210,7 +209,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
 	CPUHP_AP_PERF_X86_RAPL_ONLINE,
-	CPUHP_AP_PERF_X86_CSTATE_ONLINE,
 	CPUHP_AP_PERF_S390_CF_ONLINE,
 	CPUHP_AP_PERF_S390_SF_ONLINE,
 	CPUHP_AP_PERF_ARM_CCI_ONLINE,
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 {
diff --git a/include/linux/rbtree.h b/include/linux/rbtree.h
index f7edca369eda..7c173aa64e1e 100644
--- a/include/linux/rbtree.h
+++ b/include/linux/rbtree.h
@@ -245,6 +245,42 @@ rb_find_add(struct rb_node *node, struct rb_root *tree,
 }
 
 /**
+ * rb_find_add_rcu() - find equivalent @node in @tree, or add @node
+ * @node: node to look-for / insert
+ * @tree: tree to search / modify
+ * @cmp: operator defining the node order
+ *
+ * Adds a Store-Release for link_node.
+ *
+ * Returns the rb_node matching @node, or NULL when no match is found and @node
+ * is inserted.
+ */
+static __always_inline struct rb_node *
+rb_find_add_rcu(struct rb_node *node, struct rb_root *tree,
+		int (*cmp)(struct rb_node *, const struct rb_node *))
+{
+	struct rb_node **link = &tree->rb_node;
+	struct rb_node *parent = NULL;
+	int c;
+
+	while (*link) {
+		parent = *link;
+		c = cmp(node, parent);
+
+		if (c < 0)
+			link = &parent->rb_left;
+		else if (c > 0)
+			link = &parent->rb_right;
+		else
+			return parent;
+	}
+
+	rb_link_node_rcu(node, parent, link);
+	rb_insert_color(node, tree);
+	return NULL;
+}
+
+/**
  * rb_find() - find @key in tree @tree
  * @key: key to match
  * @tree: tree to search
@@ -273,6 +309,37 @@ rb_find(const void *key, const struct rb_root *tree,
 }
 
 /**
+ * rb_find_rcu() - find @key in tree @tree
+ * @key: key to match
+ * @tree: tree to search
+ * @cmp: operator defining the node order
+ *
+ * Notably, tree descent vs concurrent tree rotations is unsound and can result
+ * in false-negatives.
+ *
+ * Returns the rb_node matching @key or NULL.
+ */
+static __always_inline struct rb_node *
+rb_find_rcu(const void *key, const struct rb_root *tree,
+	    int (*cmp)(const void *key, const struct rb_node *))
+{
+	struct rb_node *node = tree->rb_node;
+
+	while (node) {
+		int c = cmp(key, node);
+
+		if (c < 0)
+			node = rcu_dereference_raw(node->rb_left);
+		else if (c > 0)
+			node = rcu_dereference_raw(node->rb_right);
+		else
+			return node;
+	}
+
+	return NULL;
+}
+
+/**
  * rb_find_first() - find the first @key in @tree
  * @key: key to match
  * @tree: tree to search
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index b503fafb7fb3..2b294bf1881f 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -16,6 +16,7 @@
 #include <linux/types.h>
 #include <linux/wait.h>
 
+struct uprobe;
 struct vm_area_struct;
 struct mm_struct;
 struct inode;
@@ -27,22 +28,22 @@ struct page;
 
 #define MAX_URETPROBE_DEPTH		64
 
-enum uprobe_filter_ctx {
-	UPROBE_FILTER_REGISTER,
-	UPROBE_FILTER_UNREGISTER,
-	UPROBE_FILTER_MMAP,
-};
-
 struct uprobe_consumer {
+	/*
+	 * handler() can return UPROBE_HANDLER_REMOVE to signal the need to
+	 * unregister uprobe for current process. If UPROBE_HANDLER_REMOVE is
+	 * returned, filter() callback has to be implemented as well and it
+	 * should return false to "confirm" the decision to uninstall uprobe
+	 * for the current process. If filter() is omitted or returns true,
+	 * UPROBE_HANDLER_REMOVE is effectively ignored.
+	 */
 	int (*handler)(struct uprobe_consumer *self, struct pt_regs *regs);
 	int (*ret_handler)(struct uprobe_consumer *self,
 				unsigned long func,
 				struct pt_regs *regs);
-	bool (*filter)(struct uprobe_consumer *self,
-				enum uprobe_filter_ctx ctx,
-				struct mm_struct *mm);
+	bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm);
 
-	struct uprobe_consumer *next;
+	struct list_head cons_node;
 };
 
 #ifdef CONFIG_UPROBES
@@ -76,6 +77,8 @@ struct uprobe_task {
 	struct uprobe			*active_uprobe;
 	unsigned long			xol_vaddr;
 
+	struct arch_uprobe              *auprobe;
+
 	struct return_instance		*return_instances;
 	unsigned int			depth;
 };
@@ -110,10 +113,10 @@ extern bool is_trap_insn(uprobe_opcode_t *insn);
 extern unsigned long uprobe_get_swbp_addr(struct pt_regs *regs);
 extern unsigned long uprobe_get_trap_addr(struct pt_regs *regs);
 extern int uprobe_write_opcode(struct arch_uprobe *auprobe, struct mm_struct *mm, unsigned long vaddr, uprobe_opcode_t);
-extern int uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
-extern int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
-extern int uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool);
-extern void uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc);
+extern struct uprobe *uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc);
+extern int uprobe_apply(struct uprobe *uprobe, struct uprobe_consumer *uc, bool);
+extern void uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc);
+extern void uprobe_unregister_sync(void);
 extern int uprobe_mmap(struct vm_area_struct *vma);
 extern void uprobe_munmap(struct vm_area_struct *vma, unsigned long start, unsigned long end);
 extern void uprobe_start_dup_mmap(void);
@@ -151,22 +154,21 @@ static inline void uprobes_init(void)
 
 #define uprobe_get_trap_addr(regs)	instruction_pointer(regs)
 
-static inline int
-uprobe_register(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
-{
-	return -ENOSYS;
-}
-static inline int uprobe_register_refctr(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc)
+static inline struct uprobe *
+uprobe_register(struct inode *inode, loff_t offset, loff_t ref_ctr_offset, struct uprobe_consumer *uc)
 {
-	return -ENOSYS;
+	return ERR_PTR(-ENOSYS);
 }
 static inline int
-uprobe_apply(struct inode *inode, loff_t offset, struct uprobe_consumer *uc, bool add)
+uprobe_apply(struct uprobe* uprobe, struct uprobe_consumer *uc, bool add)
 {
 	return -ENOSYS;
 }
 static inline void
-uprobe_unregister(struct inode *inode, loff_t offset, struct uprobe_consumer *uc)
+uprobe_unregister_nosync(struct uprobe *uprobe, struct uprobe_consumer *uc)
+{
+}
+static inline void uprobe_unregister_sync(void)
 {
 }
 static inline int uprobe_mmap(struct vm_area_struct *vma)