Merge tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Uprobes:
    - Add BPF session support (Jiri Olsa)
    - Switch to RCU Tasks Trace flavor for better performance (Andrii
      Nakryiko)
    - Massively increase uretprobe SMP scalability by SRCU-protecting
      the uretprobe lifetime (Andrii Nakryiko)
    - Kill xol_area->slot_count (Oleg Nesterov)

  Core facilities:
    - Implement targeted high-frequency profiling by adding the ability
      for an event to "pause" or "resume" AUX area tracing (Adrian
      Hunter)

  VM profiling/sampling:
    - Correct perf sampling with guest VMs (Colton Lewis)

  New hardware support:
    - x86/intel: Add PMU support for Intel ArrowLake-H CPUs (Dapeng Mi)

  Misc fixes and enhancements:
    - x86/intel/pt: Fix buffer full but size is 0 case (Adrian Hunter)
    - x86/amd: Warn only on new bits set (Breno Leitao)
    - x86/amd/uncore: Avoid a false positive warning about snprintf
      truncation in amd_uncore_umc_ctx_init (Jean Delvare)
    - uprobes: Re-order struct uprobe_task to save some space
      (Christophe JAILLET)
    - x86/rapl: Move the pmu allocation out of CPU hotplug (Kan Liang)
    - x86/rapl: Clean up cpumask and hotplug (Kan Liang)
    - uprobes: Deuglify xol_get_insn_slot/xol_free_insn_slot paths (Oleg
      Nesterov)"

* tag 'perf-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (32 commits)
  perf/core: Correct perf sampling with guest VMs
  perf/x86: Refactor misc flag assignments
  perf/powerpc: Use perf_arch_instruction_pointer()
  perf/core: Hoist perf_instruction_pointer() and perf_misc_flags()
  perf/arm: Drop unused functions
  uprobes: Re-order struct uprobe_task to save some space
  perf/x86/amd/uncore: Avoid a false positive warning about snprintf truncation in amd_uncore_umc_ctx_init
  perf/x86/intel: Do not enable large PEBS for events with aux actions or aux sampling
  perf/x86/intel/pt: Add support for pause / resume
  perf/core: Add aux_pause, aux_resume, aux_start_paused
  perf/x86/intel/pt: Fix buffer full but size is 0 case
  uprobes: SRCU-protect uretprobe lifetime (with timeout)
  uprobes: allow put_uprobe() from non-sleepable softirq context
  perf/x86/rapl: Clean up cpumask and hotplug
  perf/x86/rapl: Move the pmu allocation out of CPU hotplug
  uprobe: Add support for session consumer
  uprobe: Add data pointer to consumer handlers
  perf/x86/amd: Warn only on new bits set
  uprobes: fold xol_take_insn_slot() into xol_get_insn_slot()
  uprobes: kill xol_area->slot_count
  ...

4 files changed, 137 insertions, 12 deletions

diff --git a/include/linux/cpuhotplug.h b/include/linux/cpuhotplug.h
index 61d9a66d1807..f1d151c03164 100644
--- a/include/linux/cpuhotplug.h
+++ b/include/linux/cpuhotplug.h
@@ -208,7 +208,6 @@ enum cpuhp_state {
 	CPUHP_AP_PERF_X86_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_UNCORE_ONLINE,
 	CPUHP_AP_PERF_X86_AMD_POWER_ONLINE,
-	CPUHP_AP_PERF_X86_RAPL_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 fb908843f209..cb99ec8c9e96 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -170,6 +170,12 @@ struct hw_perf_event {
 		};
 		struct { /* aux / Intel-PT */
 			u64		aux_config;
+			/*
+			 * For AUX area events, aux_paused cannot be a state
+			 * flag because it can be updated asynchronously to
+			 * state.
+			 */
+			unsigned int	aux_paused;
 		};
 		struct { /* software */
 			struct hrtimer	hrtimer;
@@ -294,6 +300,7 @@ struct perf_event_pmu_context;
 #define PERF_PMU_CAP_NO_EXCLUDE			0x0040
 #define PERF_PMU_CAP_AUX_OUTPUT			0x0080
 #define PERF_PMU_CAP_EXTENDED_HW_TYPE		0x0100
+#define PERF_PMU_CAP_AUX_PAUSE			0x0200
 
 /**
  * pmu::scope
@@ -384,6 +391,8 @@ struct pmu {
 #define PERF_EF_START	0x01		/* start the counter when adding    */
 #define PERF_EF_RELOAD	0x02		/* reload the counter when starting */
 #define PERF_EF_UPDATE	0x04		/* update the counter when stopping */
+#define PERF_EF_PAUSE	0x08		/* AUX area event, pause tracing */
+#define PERF_EF_RESUME	0x10		/* AUX area event, resume tracing */
 
 	/*
 	 * Adds/Removes a counter to/from the PMU, can be done inside a
@@ -423,6 +432,18 @@ struct pmu {
 	 *
 	 * ->start() with PERF_EF_RELOAD will reprogram the counter
 	 *  value, must be preceded by a ->stop() with PERF_EF_UPDATE.
+	 *
+	 * ->stop() with PERF_EF_PAUSE will stop as simply as possible. Will not
+	 * overlap another ->stop() with PERF_EF_PAUSE nor ->start() with
+	 * PERF_EF_RESUME.
+	 *
+	 * ->start() with PERF_EF_RESUME will start as simply as possible but
+	 * only if the counter is not otherwise stopped. Will not overlap
+	 * another ->start() with PERF_EF_RESUME nor ->stop() with
+	 * PERF_EF_PAUSE.
+	 *
+	 * Notably, PERF_EF_PAUSE/PERF_EF_RESUME *can* be concurrent with other
+	 * ->stop()/->start() invocations, just not itself.
 	 */
 	void (*start)			(struct perf_event *event, int flags);
 	void (*stop)			(struct perf_event *event, int flags);
@@ -1655,15 +1676,35 @@ extern void perf_tp_event(u16 event_type, u64 count, void *record,
 			  struct task_struct *task);
 extern void perf_bp_event(struct perf_event *event, void *data);
 
-#ifndef perf_misc_flags
-# define perf_misc_flags(regs) \
+extern unsigned long perf_misc_flags(struct perf_event *event, struct pt_regs *regs);
+extern unsigned long perf_instruction_pointer(struct perf_event *event,
+					      struct pt_regs *regs);
+
+#ifndef perf_arch_misc_flags
+# define perf_arch_misc_flags(regs) \
 		(user_mode(regs) ? PERF_RECORD_MISC_USER : PERF_RECORD_MISC_KERNEL)
-# define perf_instruction_pointer(regs)	instruction_pointer(regs)
+# define perf_arch_instruction_pointer(regs)	instruction_pointer(regs)
 #endif
 #ifndef perf_arch_bpf_user_pt_regs
 # define perf_arch_bpf_user_pt_regs(regs) regs
 #endif
 
+#ifndef perf_arch_guest_misc_flags
+static inline unsigned long perf_arch_guest_misc_flags(struct pt_regs *regs)
+{
+	unsigned long guest_state = perf_guest_state();
+
+	if (!(guest_state & PERF_GUEST_ACTIVE))
+		return 0;
+
+	if (guest_state & PERF_GUEST_USER)
+		return PERF_RECORD_MISC_GUEST_USER;
+	else
+		return PERF_RECORD_MISC_GUEST_KERNEL;
+}
+# define perf_arch_guest_misc_flags(regs)	perf_arch_guest_misc_flags(regs)
+#endif
+
 static inline bool has_branch_stack(struct perf_event *event)
 {
 	return event->attr.sample_type & PERF_SAMPLE_BRANCH_STACK;
@@ -1679,6 +1720,13 @@ static inline bool has_aux(struct perf_event *event)
 	return event->pmu->setup_aux;
 }
 
+static inline bool has_aux_action(struct perf_event *event)
+{
+	return event->attr.aux_sample_size ||
+	       event->attr.aux_pause ||
+	       event->attr.aux_resume;
+}
+
 static inline bool is_write_backward(struct perf_event *event)
 {
 	return !!event->attr.write_backward;
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index 2b294bf1881f..e0a4c2082245 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -15,6 +15,7 @@
 #include <linux/rbtree.h>
 #include <linux/types.h>
 #include <linux/wait.h>
+#include <linux/timer.h>
 
 struct uprobe;
 struct vm_area_struct;
@@ -23,8 +24,17 @@ struct inode;
 struct notifier_block;
 struct page;
 
+/*
+ * Allowed return values from uprobe consumer's handler callback
+ * with following meaning:
+ *
+ * UPROBE_HANDLER_REMOVE
+ * - Remove the uprobe breakpoint from current->mm.
+ * UPROBE_HANDLER_IGNORE
+ * - Ignore ret_handler callback for this consumer.
+ */
 #define UPROBE_HANDLER_REMOVE		1
-#define UPROBE_HANDLER_MASK		1
+#define UPROBE_HANDLER_IGNORE		2
 
 #define MAX_URETPROBE_DEPTH		64
 
@@ -37,13 +47,15 @@ struct uprobe_consumer {
 	 * 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 (*handler)(struct uprobe_consumer *self, struct pt_regs *regs, __u64 *data);
 	int (*ret_handler)(struct uprobe_consumer *self,
 				unsigned long func,
-				struct pt_regs *regs);
+				struct pt_regs *regs, __u64 *data);
 	bool (*filter)(struct uprobe_consumer *self, struct mm_struct *mm);
 
 	struct list_head cons_node;
+
+	__u64 id;	/* set when uprobe_consumer is registered */
 };
 
 #ifdef CONFIG_UPROBES
@@ -56,12 +68,62 @@ enum uprobe_task_state {
 	UTASK_SSTEP_TRAPPED,
 };
 
+/* The state of hybrid-lifetime uprobe inside struct return_instance */
+enum hprobe_state {
+	HPROBE_LEASED,		/* uretprobes_srcu-protected uprobe */
+	HPROBE_STABLE,		/* refcounted uprobe */
+	HPROBE_GONE,		/* NULL uprobe, SRCU expired, refcount failed */
+	HPROBE_CONSUMED,	/* uprobe "consumed" by uretprobe handler */
+};
+
+/*
+ * Hybrid lifetime uprobe. Represents a uprobe instance that could be either
+ * SRCU protected (with SRCU protection eventually potentially timing out),
+ * refcounted using uprobe->ref, or there could be no valid uprobe (NULL).
+ *
+ * hprobe's internal state is setup such that background timer thread can
+ * atomically "downgrade" temporarily RCU-protected uprobe into refcounted one
+ * (or no uprobe, if refcounting failed).
+ *
+ * *stable* pointer always point to the uprobe (or could be NULL if there is
+ * was no valid underlying uprobe to begin with).
+ *
+ * *leased* pointer is the key to achieving race-free atomic lifetime state
+ * transition and can have three possible states:
+ *   - either the same non-NULL value as *stable*, in which case uprobe is
+ *     SRCU-protected;
+ *   - NULL, in which case uprobe (if there is any) is refcounted;
+ *   - special __UPROBE_DEAD value, which represents an uprobe that was SRCU
+ *     protected initially, but SRCU period timed out and we attempted to
+ *     convert it to refcounted, but refcount_inc_not_zero() failed, because
+ *     uprobe effectively went away (the last consumer unsubscribed). In this
+ *     case it's important to know that *stable* pointer (which still has
+ *     non-NULL uprobe pointer) shouldn't be used, because lifetime of
+ *     underlying uprobe is not guaranteed anymore. __UPROBE_DEAD is just an
+ *     internal marker and is handled transparently by hprobe_fetch() helper.
+ *
+ * When uprobe is SRCU-protected, we also record srcu_idx value, necessary for
+ * SRCU unlocking.
+ *
+ * See hprobe_expire() and hprobe_fetch() for details of race-free uprobe
+ * state transitioning details. It all hinges on atomic xchg() over *leaded*
+ * pointer. *stable* pointer, once initially set, is not modified concurrently.
+ */
+struct hprobe {
+	enum hprobe_state state;
+	int srcu_idx;
+	struct uprobe *uprobe;
+};
+
 /*
  * uprobe_task: Metadata of a task while it singlesteps.
  */
 struct uprobe_task {
 	enum uprobe_task_state		state;
 
+	unsigned int			depth;
+	struct return_instance		*return_instances;
+
 	union {
 		struct {
 			struct arch_uprobe_task	autask;
@@ -75,23 +137,30 @@ struct uprobe_task {
 	};
 
 	struct uprobe			*active_uprobe;
+	struct timer_list		ri_timer;
 	unsigned long			xol_vaddr;
 
 	struct arch_uprobe              *auprobe;
+};
 
-	struct return_instance		*return_instances;
-	unsigned int			depth;
+struct return_consumer {
+	__u64	cookie;
+	__u64	id;
 };
 
 struct return_instance {
-	struct uprobe		*uprobe;
+	struct hprobe		hprobe;
 	unsigned long		func;
 	unsigned long		stack;		/* stack pointer */
 	unsigned long		orig_ret_vaddr; /* original return address */
 	bool			chained;	/* true, if instance is nested */
+	int			consumers_cnt;
 
 	struct return_instance	*next;		/* keep as stack */
-};
+	struct rcu_head		rcu;
+
+	struct return_consumer	consumers[] __counted_by(consumers_cnt);
+} ____cacheline_aligned;
 
 enum rp_check {
 	RP_CHECK_CALL,
diff --git a/include/uapi/linux/perf_event.h b/include/uapi/linux/perf_event.h
index 4842c36fdf80..0524d541d4e3 100644
--- a/include/uapi/linux/perf_event.h
+++ b/include/uapi/linux/perf_event.h
@@ -511,7 +511,16 @@ struct perf_event_attr {
 	__u16	sample_max_stack;
 	__u16	__reserved_2;
 	__u32	aux_sample_size;
-	__u32	__reserved_3;
+
+	union {
+		__u32	aux_action;
+		struct {
+			__u32	aux_start_paused :  1, /* start AUX area tracing paused */
+				aux_pause        :  1, /* on overflow, pause AUX area tracing */
+				aux_resume       :  1, /* on overflow, resume AUX area tracing */
+				__reserved_3     : 29;
+		};
+	};
 
 	/*
 	 * User provided data if sigtrap=1, passed back to user via