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
  ...

2 files changed, 22 insertions, 4 deletions

diff --git a/tools/arch/x86/include/asm/insn.h b/tools/arch/x86/include/asm/insn.h
index c683d609934b..8f10f2943370 100644
--- a/tools/arch/x86/include/asm/insn.h
+++ b/tools/arch/x86/include/asm/insn.h
@@ -312,7 +312,6 @@ static inline int insn_offset_immediate(struct insn *insn)
 /**
  * for_each_insn_prefix() -- Iterate prefixes in the instruction
  * @insn: Pointer to struct insn.
- * @idx:  Index storage.
  * @prefix: Prefix byte.
  *
  * Iterate prefix bytes of given @insn. Each prefix byte is stored in @prefix
@@ -321,8 +320,8 @@ static inline int insn_offset_immediate(struct insn *insn)
  * Since prefixes.nbytes can be bigger than 4 if some prefixes
  * are repeated, it cannot be used for looping over the prefixes.
  */
-#define for_each_insn_prefix(insn, idx, prefix)	\
-	for (idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
+#define for_each_insn_prefix(insn, prefix)	\
+	for (int idx = 0; idx < ARRAY_SIZE(insn->prefixes.bytes) && (prefix = insn->prefixes.bytes[idx]) != 0; idx++)
 
 #define POP_SS_OPCODE 0x1f
 #define MOV_SREG_OPCODE 0x8e
diff --git a/tools/include/uapi/linux/perf_event.h b/tools/include/uapi/linux/perf_event.h
index 78a362b80027..d292f96bc06f 100644
--- a/tools/include/uapi/linux/perf_event.h
+++ b/tools/include/uapi/linux/perf_event.h
@@ -463,7 +463,9 @@ struct perf_event_attr {
 				inherit_thread :  1, /* children only inherit if cloned with CLONE_THREAD */
 				remove_on_exec :  1, /* event is removed from task on exec */
 				sigtrap        :  1, /* send synchronous SIGTRAP on event */
-				__reserved_1   : 26;
+				defer_callchain:  1, /* request PERF_RECORD_CALLCHAIN_DEFERRED records */
+				defer_output   :  1, /* output PERF_RECORD_CALLCHAIN_DEFERRED records */
+				__reserved_1   : 24;
 
 	union {
 		__u32		wakeup_events;	  /* wake up every n events */
@@ -1239,6 +1241,22 @@ enum perf_event_type {
 	 */
 	PERF_RECORD_AUX_OUTPUT_HW_ID		= 21,
 
+	/*
+	 * This user callchain capture was deferred until shortly before
+	 * returning to user space.  Previous samples would have kernel
+	 * callchains only and they need to be stitched with this to make full
+	 * callchains.
+	 *
+	 * struct {
+	 *	struct perf_event_header	header;
+	 *	u64				cookie;
+	 *	u64				nr;
+	 *	u64				ips[nr];
+	 *	struct sample_id		sample_id;
+	 * };
+	 */
+	PERF_RECORD_CALLCHAIN_DEFERRED		= 22,
+
 	PERF_RECORD_MAX,			/* non-ABI */
 };
 
@@ -1269,6 +1287,7 @@ enum perf_callchain_context {
 	PERF_CONTEXT_HV				= (__u64)-32,
 	PERF_CONTEXT_KERNEL			= (__u64)-128,
 	PERF_CONTEXT_USER			= (__u64)-512,
+	PERF_CONTEXT_USER_DEFERRED		= (__u64)-640,
 
 	PERF_CONTEXT_GUEST			= (__u64)-2048,
 	PERF_CONTEXT_GUEST_KERNEL		= (__u64)-2176,