Merge tag 'perf-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull performance events updates from Ingo Molnar:
 "Callchain support:

   - Add support for deferred user-space stack unwinding for perf,
     enabled on x86. (Peter Zijlstra, Steven Rostedt)

   - unwind_user/x86: Enable frame pointer unwinding on x86 (Josh
     Poimboeuf)

  x86 PMU support and infrastructure:

   - x86/insn: Simplify for_each_insn_prefix() (Peter Zijlstra)

   - x86/insn,uprobes,alternative: Unify insn_is_nop() (Peter Zijlstra)

  Intel PMU driver:

   - Large series to prepare for and implement architectural PEBS
     support for Intel platforms such as Clearwater Forest (CWF) and
     Panther Lake (PTL). (Dapeng Mi, Kan Liang)

   - Check dynamic constraints (Kan Liang)

   - Optimize PEBS extended config (Peter Zijlstra)

   - cstates:
      - Remove PC3 support from LunarLake (Zhang Rui)
      - Add Pantherlake support (Zhang Rui)
      - Clearwater Forest support (Zide Chen)

  AMD PMU driver:

   - x86/amd: Check event before enable to avoid GPF (George Kennedy)

  Fixes and cleanups:

   - task_work: Fix NMI race condition (Peter Zijlstra)

   - perf/x86: Fix NULL event access and potential PEBS record loss
     (Dapeng Mi)

   - Misc other fixes and cleanups (Dapeng Mi, Ingo Molnar, Peter
     Zijlstra)"

* tag 'perf-core-2025-12-01' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (38 commits)
  perf/x86/intel: Fix and clean up intel_pmu_drain_arch_pebs() type use
  perf/x86/intel: Optimize PEBS extended config
  perf/x86/intel: Check PEBS dyn_constraints
  perf/x86/intel: Add a check for dynamic constraints
  perf/x86/intel: Add counter group support for arch-PEBS
  perf/x86/intel: Setup PEBS data configuration and enable legacy groups
  perf/x86/intel: Update dyn_constraint base on PEBS event precise level
  perf/x86/intel: Allocate arch-PEBS buffer and initialize PEBS_BASE MSR
  perf/x86/intel: Process arch-PEBS records or record fragments
  perf/x86/intel/ds: Factor out PEBS group processing code to functions
  perf/x86/intel/ds: Factor out PEBS record processing code to functions
  perf/x86/intel: Initialize architectural PEBS
  perf/x86/intel: Correct large PEBS flag check
  perf/x86/intel: Replace x86_pmu.drain_pebs calling with static call
  perf/x86: Fix NULL event access and potential PEBS record loss
  perf/x86: Remove redundant is_x86_event() prototype
  entry,unwind/deferred: Fix unwind_reset_info() placement
  unwind_user/x86: Fix arch=um build
  perf: Support deferred user unwind
  unwind_user/x86: Teach FP unwind about start of function
  ...

5 files changed, 46 insertions, 30 deletions

diff --git a/include/linux/irq-entry-common.h b/include/linux/irq-entry-common.h
index d643c7c87822..ba1ed42f8a1c 100644
--- a/include/linux/irq-entry-common.h
+++ b/include/linux/irq-entry-common.h
@@ -253,11 +253,11 @@ static __always_inline void exit_to_user_mode_prepare(struct pt_regs *regs)
 static __always_inline void exit_to_user_mode(void)
 {
 	instrumentation_begin();
+	unwind_reset_info();
 	trace_hardirqs_on_prepare();
 	lockdep_hardirqs_on_prepare();
 	instrumentation_end();
 
-	unwind_reset_info();
 	user_enter_irqoff();
 	arch_exit_to_user_mode();
 	lockdep_hardirqs_on(CALLER_ADDR0);
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index fd1d91017b99..9870d768db4c 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -1720,7 +1720,7 @@ extern void perf_callchain_user(struct perf_callchain_entry_ctx *entry, struct p
 extern void perf_callchain_kernel(struct perf_callchain_entry_ctx *entry, struct pt_regs *regs);
 extern struct perf_callchain_entry *
 get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
-		   u32 max_stack, bool crosstask, bool add_mark);
+		   u32 max_stack, bool crosstask, bool add_mark, u64 defer_cookie);
 extern int get_callchain_buffers(int max_stack);
 extern void put_callchain_buffers(void);
 extern struct perf_callchain_entry *get_callchain_entry(int *rctx);
diff --git a/include/linux/unwind_deferred.h b/include/linux/unwind_deferred.h
index 26122d00708a..bc7ae7d21900 100644
--- a/include/linux/unwind_deferred.h
+++ b/include/linux/unwind_deferred.h
@@ -6,16 +6,6 @@
 #include <linux/unwind_user.h>
 #include <linux/unwind_deferred_types.h>
 
-struct unwind_work;
-
-typedef void (*unwind_callback_t)(struct unwind_work *work, struct unwind_stacktrace *trace, u64 cookie);
-
-struct unwind_work {
-	struct list_head		list;
-	unwind_callback_t		func;
-	int				bit;
-};
-
 #ifdef CONFIG_UNWIND_USER
 
 enum {
@@ -44,22 +34,22 @@ void unwind_deferred_task_exit(struct task_struct *task);
 static __always_inline void unwind_reset_info(void)
 {
 	struct unwind_task_info *info = &current->unwind_info;
-	unsigned long bits;
+	unsigned long bits = atomic_long_read(&info->unwind_mask);
 
 	/* Was there any unwinding? */
-	if (unlikely(info->unwind_mask)) {
-		bits = info->unwind_mask;
-		do {
-			/* Is a task_work going to run again before going back */
-			if (bits & UNWIND_PENDING)
-				return;
-		} while (!try_cmpxchg(&info->unwind_mask, &bits, 0UL));
-		current->unwind_info.id.id = 0;
-
-		if (unlikely(info->cache)) {
-			info->cache->nr_entries = 0;
-			info->cache->unwind_completed = 0;
-		}
+	if (likely(!bits))
+		return;
+
+	do {
+		/* Is a task_work going to run again before going back */
+		if (bits & UNWIND_PENDING)
+			return;
+	} while (!atomic_long_try_cmpxchg(&info->unwind_mask, &bits, 0UL));
+	current->unwind_info.id.id = 0;
+
+	if (unlikely(info->cache)) {
+		info->cache->nr_entries = 0;
+		info->cache->unwind_completed = 0;
 	}
 }
 
@@ -68,9 +58,17 @@ static __always_inline void unwind_reset_info(void)
 static inline void unwind_task_init(struct task_struct *task) {}
 static inline void unwind_task_free(struct task_struct *task) {}
 
-static inline int unwind_user_faultable(struct unwind_stacktrace *trace) { return -ENOSYS; }
-static inline int unwind_deferred_init(struct unwind_work *work, unwind_callback_t func) { return -ENOSYS; }
-static inline int unwind_deferred_request(struct unwind_work *work, u64 *timestamp) { return -ENOSYS; }
+static inline int unwind_user_faultable(struct unwind_stacktrace *trace)
+{ return -ENOSYS; }
+
+static inline int
+unwind_deferred_init(struct unwind_work *work, unwind_callback_t func)
+{ return -ENOSYS; }
+
+static inline int
+unwind_deferred_request(struct unwind_work *work, u64 *timestamp)
+{ return -ENOSYS; }
+
 static inline void unwind_deferred_cancel(struct unwind_work *work) {}
 
 static inline void unwind_deferred_task_exit(struct task_struct *task) {}
diff --git a/include/linux/unwind_deferred_types.h b/include/linux/unwind_deferred_types.h
index 33b62ac25c86..18fa3932f61c 100644
--- a/include/linux/unwind_deferred_types.h
+++ b/include/linux/unwind_deferred_types.h
@@ -2,6 +2,9 @@
 #ifndef _LINUX_UNWIND_USER_DEFERRED_TYPES_H
 #define _LINUX_UNWIND_USER_DEFERRED_TYPES_H
 
+#include <linux/types.h>
+#include <linux/atomic.h>
+
 struct unwind_cache {
 	unsigned long		unwind_completed;
 	unsigned int		nr_entries;
@@ -30,10 +33,23 @@ union unwind_task_id {
 };
 
 struct unwind_task_info {
-	unsigned long		unwind_mask;
+	atomic_long_t		unwind_mask;
 	struct unwind_cache	*cache;
 	struct callback_head	work;
 	union unwind_task_id	id;
 };
 
+struct unwind_work;
+struct unwind_stacktrace;
+
+typedef void (*unwind_callback_t)(struct unwind_work *work,
+				  struct unwind_stacktrace *trace,
+				  u64 cookie);
+
+struct unwind_work {
+	struct list_head		list;
+	unwind_callback_t		func;
+	int				bit;
+};
+
 #endif /* _LINUX_UNWIND_USER_DEFERRED_TYPES_H */
diff --git a/include/linux/unwind_user_types.h b/include/linux/unwind_user_types.h
index a449f15be890..412729a269bc 100644
--- a/include/linux/unwind_user_types.h
+++ b/include/linux/unwind_user_types.h
@@ -36,8 +36,10 @@ struct unwind_user_state {
 	unsigned long				ip;
 	unsigned long				sp;
 	unsigned long				fp;
+	unsigned int				ws;
 	enum unwind_user_type			current_type;
 	unsigned int				available_types;
+	bool					topmost;
 	bool					done;
 };