Merge tag 'perf-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Core:
   - Move perf_event sysctls into kernel/events/ (Joel Granados)
   - Use POLLHUP for pinned events in error (Namhyung Kim)
   - Avoid the read if the count is already updated (Peter Zijlstra)
   - Allow the EPOLLRDNORM flag for poll (Tao Chen)
   - locking/percpu-rwsem: Add guard support [ NOTE: this got
     (mis-)merged into the perf tree due to related work ] (Peter
     Zijlstra)

  perf_pmu_unregister() related improvements: (Peter Zijlstra)
   - Simplify the perf_event_alloc() error path
   - Simplify the perf_pmu_register() error path
   - Simplify perf_pmu_register()
   - Simplify perf_init_event()
   - Simplify perf_event_alloc()
   - Merge struct pmu::pmu_disable_count into struct
     perf_cpu_pmu_context::pmu_disable_count
   - Add this_cpc() helper
   - Introduce perf_free_addr_filters()
   - Robustify perf_event_free_bpf_prog()
   - Simplify the perf_mmap() control flow
   - Further simplify perf_mmap()
   - Remove retry loop from perf_mmap()
   - Lift event->mmap_mutex in perf_mmap()
   - Detach 'struct perf_cpu_pmu_context' and 'struct pmu' lifetimes
   - Fix perf_mmap() failure path

  Uprobes:
   - Harden x86 uretprobe syscall trampoline check (Jiri Olsa)
   - Remove redundant spinlock in uprobe_deny_signal() (Liao Chang)
   - Remove the spinlock within handle_singlestep() (Liao Chang)

  x86 Intel PMU enhancements:
   - Support PEBS counters snapshotting (Kan Liang)
   - Fix intel_pmu_read_event() (Kan Liang)
   - Extend per event callchain limit to branch stack (Kan Liang)
   - Fix system-wide LBR profiling (Kan Liang)
   - Allocate bts_ctx only if necessary (Li RongQing)
   - Apply static call for drain_pebs (Peter Zijlstra)

  x86 AMD PMU enhancements: (Ravi Bangoria)
   - Remove pointless sample period check
   - Fix ->config to sample period calculation for OP PMU
   - Fix perf_ibs_op.cnt_mask for CurCnt
   - Don't allow freq mode event creation through ->config interface
   - Add PMU specific minimum period
   - Add ->check_period() callback
   - Ceil sample_period to min_period
   - Add support for OP Load Latency Filtering
   - Update DTLB/PageSize decode logic

  Hardware breakpoints:
   - Return EOPNOTSUPP for unsupported breakpoint type (Saket Kumar
     Bhaskar)

  Hardlockup detector improvements: (Li Huafei)
   - perf_event memory leak
   - Warn if watchdog_ev is leaked

  Fixes and cleanups:
   - Misc fixes and cleanups (Andy Shevchenko, Kan Liang, Peter
     Zijlstra, Ravi Bangoria, Thorsten Blum, XieLudan)"

* tag 'perf-core-2025-03-22' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (55 commits)
  perf: Fix __percpu annotation
  perf: Clean up pmu specific data
  perf/x86: Remove swap_task_ctx()
  perf/x86/lbr: Fix shorter LBRs call stacks for the system-wide mode
  perf: Supply task information to sched_task()
  perf: attach/detach PMU specific data
  locking/percpu-rwsem: Add guard support
  perf: Save PMU specific data in task_struct
  perf: Extend per event callchain limit to branch stack
  perf/ring_buffer: Allow the EPOLLRDNORM flag for poll
  perf/core: Use POLLHUP for pinned events in error
  perf/core: Use sysfs_emit() instead of scnprintf()
  perf/core: Remove optional 'size' arguments from strscpy() calls
  perf/x86/intel/bts: Check if bts_ctx is allocated when calling BTS functions
  uprobes/x86: Harden uretprobe syscall trampoline check
  watchdog/hardlockup/perf: Warn if watchdog_ev is leaked
  watchdog/hardlockup/perf: Fix perf_event memory leak
  perf/x86: Annotate struct bts_buffer::buf with __counted_by()
  perf/core: Clean up perf_try_init_event()
  perf/core: Fix perf_mmap() failure path
  ...

6 files changed, 89 insertions, 37 deletions

diff --git a/include/linux/idr.h b/include/linux/idr.h
index da5f5fa4a3a6..cd729be369b3 100644
--- a/include/linux/idr.h
+++ b/include/linux/idr.h
@@ -15,6 +15,7 @@
 #include <linux/radix-tree.h>
 #include <linux/gfp.h>
 #include <linux/percpu.h>
+#include <linux/cleanup.h>
 
 struct idr {
 	struct radix_tree_root	idr_rt;
@@ -124,6 +125,22 @@ void *idr_get_next_ul(struct idr *, unsigned long *nextid);
 void *idr_replace(struct idr *, void *, unsigned long id);
 void idr_destroy(struct idr *);
 
+struct __class_idr {
+	struct idr *idr;
+	int id;
+};
+
+#define idr_null ((struct __class_idr){ NULL, -1 })
+#define take_idr_id(id) __get_and_null(id, idr_null)
+
+DEFINE_CLASS(idr_alloc, struct __class_idr,
+	     if (_T.id >= 0) idr_remove(_T.idr, _T.id),
+	     ((struct __class_idr){
+	     	.idr = idr,
+		.id = idr_alloc(idr, ptr, start, end, gfp),
+	     }),
+	     struct idr *idr, void *ptr, int start, int end, gfp_t gfp);
+
 /**
  * idr_init_base() - Initialise an IDR.
  * @idr: IDR handle.
diff --git a/include/linux/nmi.h b/include/linux/nmi.h
index a8dfb38c9bb6..e78fa535f61d 100644
--- a/include/linux/nmi.h
+++ b/include/linux/nmi.h
@@ -17,7 +17,6 @@
 void lockup_detector_init(void);
 void lockup_detector_retry_init(void);
 void lockup_detector_soft_poweroff(void);
-void lockup_detector_cleanup(void);
 
 extern int watchdog_user_enabled;
 extern int watchdog_thresh;
@@ -37,7 +36,6 @@ extern int sysctl_hardlockup_all_cpu_backtrace;
 static inline void lockup_detector_init(void) { }
 static inline void lockup_detector_retry_init(void) { }
 static inline void lockup_detector_soft_poweroff(void) { }
-static inline void lockup_detector_cleanup(void) { }
 #endif /* !CONFIG_LOCKUP_DETECTOR */
 
 #ifdef CONFIG_SOFTLOCKUP_DETECTOR
@@ -104,12 +102,10 @@ void watchdog_hardlockup_check(unsigned int cpu, struct pt_regs *regs);
 #if defined(CONFIG_HARDLOCKUP_DETECTOR_PERF)
 extern void hardlockup_detector_perf_stop(void);
 extern void hardlockup_detector_perf_restart(void);
-extern void hardlockup_detector_perf_cleanup(void);
 extern void hardlockup_config_perf_event(const char *str);
 #else
 static inline void hardlockup_detector_perf_stop(void) { }
 static inline void hardlockup_detector_perf_restart(void) { }
-static inline void hardlockup_detector_perf_cleanup(void) { }
 static inline void hardlockup_config_perf_event(const char *str) { }
 #endif
 
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index c012df33a9f0..af7d75ede619 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -8,6 +8,7 @@
 #include <linux/wait.h>
 #include <linux/rcu_sync.h>
 #include <linux/lockdep.h>
+#include <linux/cleanup.h>
 
 struct percpu_rw_semaphore {
 	struct rcu_sync		rss;
@@ -125,6 +126,13 @@ extern bool percpu_is_read_locked(struct percpu_rw_semaphore *);
 extern void percpu_down_write(struct percpu_rw_semaphore *);
 extern void percpu_up_write(struct percpu_rw_semaphore *);
 
+DEFINE_GUARD(percpu_read, struct percpu_rw_semaphore *,
+	     percpu_down_read(_T), percpu_up_read(_T))
+DEFINE_GUARD_COND(percpu_read, _try, percpu_down_read_trylock(_T))
+
+DEFINE_GUARD(percpu_write, struct percpu_rw_semaphore *,
+	     percpu_down_write(_T), percpu_up_write(_T))
+
 static inline bool percpu_is_write_locked(struct percpu_rw_semaphore *sem)
 {
 	return atomic_read(&sem->block);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index 8333f132f4a9..63dddb3b54f0 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -343,8 +343,7 @@ struct pmu {
 	 */
 	unsigned int			scope;
 
-	int __percpu			*pmu_disable_count;
-	struct perf_cpu_pmu_context __percpu *cpu_pmu_context;
+	struct perf_cpu_pmu_context * __percpu *cpu_pmu_context;
 	atomic_t			exclusive_cnt; /* < 0: cpu; > 0: tsk */
 	int				task_ctx_nr;
 	int				hrtimer_interval_ms;
@@ -495,7 +494,7 @@ struct pmu {
 	 * context-switches callback
 	 */
 	void (*sched_task)		(struct perf_event_pmu_context *pmu_ctx,
-					bool sched_in);
+					 struct task_struct *task, bool sched_in);
 
 	/*
 	 * Kmem cache of PMU specific data
@@ -503,16 +502,6 @@ struct pmu {
 	struct kmem_cache		*task_ctx_cache;
 
 	/*
-	 * PMU specific parts of task perf event context (i.e. ctx->task_ctx_data)
-	 * can be synchronized using this function. See Intel LBR callstack support
-	 * implementation and Perf core context switch handling callbacks for usage
-	 * examples.
-	 */
-	void (*swap_task_ctx)		(struct perf_event_pmu_context *prev_epc,
-					 struct perf_event_pmu_context *next_epc);
-					/* optional */
-
-	/*
 	 * Set up pmu-private data structures for an AUX area
 	 */
 	void *(*setup_aux)		(struct perf_event *event, void **pages,
@@ -673,13 +662,16 @@ struct swevent_hlist {
 	struct rcu_head			rcu_head;
 };
 
-#define PERF_ATTACH_CONTEXT	0x01
-#define PERF_ATTACH_GROUP	0x02
-#define PERF_ATTACH_TASK	0x04
-#define PERF_ATTACH_TASK_DATA	0x08
-#define PERF_ATTACH_ITRACE	0x10
-#define PERF_ATTACH_SCHED_CB	0x20
-#define PERF_ATTACH_CHILD	0x40
+#define PERF_ATTACH_CONTEXT	0x0001
+#define PERF_ATTACH_GROUP	0x0002
+#define PERF_ATTACH_TASK	0x0004
+#define PERF_ATTACH_TASK_DATA	0x0008
+#define PERF_ATTACH_GLOBAL_DATA	0x0010
+#define PERF_ATTACH_SCHED_CB	0x0020
+#define PERF_ATTACH_CHILD	0x0040
+#define PERF_ATTACH_EXCLUSIVE	0x0080
+#define PERF_ATTACH_CALLCHAIN	0x0100
+#define PERF_ATTACH_ITRACE	0x0200
 
 struct bpf_prog;
 struct perf_cgroup;
@@ -921,7 +913,7 @@ struct perf_event_pmu_context {
 	struct list_head		pinned_active;
 	struct list_head		flexible_active;
 
-	/* Used to avoid freeing per-cpu perf_event_pmu_context */
+	/* Used to identify the per-cpu perf_event_pmu_context */
 	unsigned int			embedded : 1;
 
 	unsigned int			nr_events;
@@ -931,7 +923,6 @@ struct perf_event_pmu_context {
 	atomic_t			refcount; /* event <-> epc */
 	struct rcu_head			rcu_head;
 
-	void				*task_ctx_data; /* pmu specific data */
 	/*
 	 * Set when one or more (plausibly active) event can't be scheduled
 	 * due to pmu overcommit or pmu constraints, except tolerant to
@@ -979,7 +970,6 @@ struct perf_event_context {
 	int				nr_user;
 	int				is_active;
 
-	int				nr_task_data;
 	int				nr_stat;
 	int				nr_freq;
 	int				rotate_disable;
@@ -1020,6 +1010,41 @@ struct perf_event_context {
 	local_t				nr_no_switch_fast;
 };
 
+/**
+ * struct perf_ctx_data - PMU specific data for a task
+ * @rcu_head:  To avoid the race on free PMU specific data
+ * @refcount:  To track users
+ * @global:    To track system-wide users
+ * @ctx_cache: Kmem cache of PMU specific data
+ * @data:      PMU specific data
+ *
+ * Currently, the struct is only used in Intel LBR call stack mode to
+ * save/restore the call stack of a task on context switches.
+ *
+ * The rcu_head is used to prevent the race on free the data.
+ * The data only be allocated when Intel LBR call stack mode is enabled.
+ * The data will be freed when the mode is disabled.
+ * The content of the data will only be accessed in context switch, which
+ * should be protected by rcu_read_lock().
+ *
+ * Because of the alignment requirement of Intel Arch LBR, the Kmem cache
+ * is used to allocate the PMU specific data. The ctx_cache is to track
+ * the Kmem cache.
+ *
+ * Careful: Struct perf_ctx_data is added as a pointer in struct task_struct.
+ * When system-wide Intel LBR call stack mode is enabled, a buffer with
+ * constant size will be allocated for each task.
+ * Also, system memory consumption can further grow when the size of
+ * struct perf_ctx_data enlarges.
+ */
+struct perf_ctx_data {
+	struct rcu_head			rcu_head;
+	refcount_t			refcount;
+	int				global;
+	struct kmem_cache		*ctx_cache;
+	void				*data;
+};
+
 struct perf_cpu_pmu_context {
 	struct perf_event_pmu_context	epc;
 	struct perf_event_pmu_context	*task_epc;
@@ -1029,6 +1054,7 @@ struct perf_cpu_pmu_context {
 
 	int				active_oncpu;
 	int				exclusive;
+	int				pmu_disable_count;
 
 	raw_spinlock_t			hrtimer_lock;
 	struct hrtimer			hrtimer;
@@ -1062,7 +1088,13 @@ struct perf_output_handle {
 	struct perf_buffer		*rb;
 	unsigned long			wakeup;
 	unsigned long			size;
-	u64				aux_flags;
+	union {
+		u64			flags;		/* perf_output*() */
+		u64			aux_flags;	/* perf_aux_output*() */
+		struct {
+			u64		skip_read : 1;
+		};
+	};
 	union {
 		void			*addr;
 		unsigned long		head;
@@ -1339,6 +1371,9 @@ static inline void perf_sample_save_brstack(struct perf_sample_data *data,
 
 	if (branch_sample_hw_index(event))
 		size += sizeof(u64);
+
+	brs->nr = min_t(u16, event->attr.sample_max_stack, brs->nr);
+
 	size += brs->nr * sizeof(struct perf_branch_entry);
 
 	/*
@@ -1646,19 +1681,10 @@ static inline int perf_callchain_store(struct perf_callchain_entry_ctx *ctx, u64
 }
 
 extern int sysctl_perf_event_paranoid;
-extern int sysctl_perf_event_mlock;
 extern int sysctl_perf_event_sample_rate;
-extern int sysctl_perf_cpu_time_max_percent;
 
 extern void perf_sample_event_took(u64 sample_len_ns);
 
-int perf_event_max_sample_rate_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-int perf_cpu_time_max_percent_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-int perf_event_max_stack_handler(const struct ctl_table *table, int write,
-		void *buffer, size_t *lenp, loff_t *ppos);
-
 /* Access to perf_event_open(2) syscall. */
 #define PERF_SECURITY_OPEN		0
 
diff --git a/include/linux/sched.h b/include/linux/sched.h
index 4659898c0299..6e5c38718ff5 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -65,6 +65,7 @@ struct mempolicy;
 struct nameidata;
 struct nsproxy;
 struct perf_event_context;
+struct perf_ctx_data;
 struct pid_namespace;
 struct pipe_inode_info;
 struct rcu_node;
@@ -1316,6 +1317,7 @@ struct task_struct {
 	struct perf_event_context	*perf_event_ctxp;
 	struct mutex			perf_event_mutex;
 	struct list_head		perf_event_list;
+	struct perf_ctx_data __rcu	*perf_ctx_data;
 #endif
 #ifdef CONFIG_DEBUG_PREEMPT
 	unsigned long			preempt_disable_ip;
diff --git a/include/linux/uprobes.h b/include/linux/uprobes.h
index b1df7d792fa1..2e46b69ff0a6 100644
--- a/include/linux/uprobes.h
+++ b/include/linux/uprobes.h
@@ -39,6 +39,8 @@ struct page;
 
 #define MAX_URETPROBE_DEPTH		64
 
+#define UPROBE_NO_TRAMPOLINE_VADDR	(~0UL)
+
 struct uprobe_consumer {
 	/*
 	 * handler() can return UPROBE_HANDLER_REMOVE to signal the need to
@@ -143,6 +145,7 @@ struct uprobe_task {
 
 	struct uprobe			*active_uprobe;
 	unsigned long			xol_vaddr;
+	bool				signal_denied;
 
 	struct arch_uprobe              *auprobe;
 };