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, 89 insertions, 3 deletions

diff --git a/kernel/events/callchain.c b/kernel/events/callchain.c
index 808c0d7a31fa..b9c7e00725d6 100644
--- a/kernel/events/callchain.c
+++ b/kernel/events/callchain.c
@@ -218,7 +218,7 @@ static void fixup_uretprobe_trampoline_entries(struct perf_callchain_entry *entr
 
 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)
 {
 	struct perf_callchain_entry *entry;
 	struct perf_callchain_entry_ctx ctx;
@@ -251,6 +251,18 @@ get_perf_callchain(struct pt_regs *regs, bool kernel, bool user,
 			regs = task_pt_regs(current);
 		}
 
+		if (defer_cookie) {
+			/*
+			 * Foretell the coming of PERF_RECORD_CALLCHAIN_DEFERRED
+			 * which can be stitched to this one, and add
+			 * the cookie after it (it will be cut off when the
+			 * user stack is copied to the callchain).
+			 */
+			perf_callchain_store_context(&ctx, PERF_CONTEXT_USER_DEFERRED);
+			perf_callchain_store_context(&ctx, defer_cookie);
+			goto exit_put;
+		}
+
 		if (add_mark)
 			perf_callchain_store_context(&ctx, PERF_CONTEXT_USER);
 
diff --git a/kernel/events/core.c b/kernel/events/core.c
index 2c35acc2722b..ece716879cbc 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -56,6 +56,7 @@
 #include <linux/buildid.h>
 #include <linux/task_work.h>
 #include <linux/percpu-rwsem.h>
+#include <linux/unwind_deferred.h>
 
 #include "internal.h"
 
@@ -8200,6 +8201,8 @@ static u64 perf_get_page_size(unsigned long addr)
 
 static struct perf_callchain_entry __empty_callchain = { .nr = 0, };
 
+static struct unwind_work perf_unwind_work;
+
 struct perf_callchain_entry *
 perf_callchain(struct perf_event *event, struct pt_regs *regs)
 {
@@ -8208,8 +8211,11 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 		!(current->flags & (PF_KTHREAD | PF_USER_WORKER));
 	/* Disallow cross-task user callchains. */
 	bool crosstask = event->ctx->task && event->ctx->task != current;
+	bool defer_user = IS_ENABLED(CONFIG_UNWIND_USER) && user &&
+			  event->attr.defer_callchain;
 	const u32 max_stack = event->attr.sample_max_stack;
 	struct perf_callchain_entry *callchain;
+	u64 defer_cookie;
 
 	if (!current->mm)
 		user = false;
@@ -8217,8 +8223,13 @@ perf_callchain(struct perf_event *event, struct pt_regs *regs)
 	if (!kernel && !user)
 		return &__empty_callchain;
 
-	callchain = get_perf_callchain(regs, kernel, user,
-				       max_stack, crosstask, true);
+	if (!(user && defer_user && !crosstask &&
+	      unwind_deferred_request(&perf_unwind_work, &defer_cookie) >= 0))
+		defer_cookie = 0;
+
+	callchain = get_perf_callchain(regs, kernel, user, max_stack,
+				       crosstask, true, defer_cookie);
+
 	return callchain ?: &__empty_callchain;
 }
 
@@ -10003,6 +10014,66 @@ void perf_event_bpf_event(struct bpf_prog *prog,
 	perf_iterate_sb(perf_event_bpf_output, &bpf_event, NULL);
 }
 
+struct perf_callchain_deferred_event {
+	struct unwind_stacktrace *trace;
+	struct {
+		struct perf_event_header	header;
+		u64				cookie;
+		u64				nr;
+		u64				ips[];
+	} event;
+};
+
+static void perf_callchain_deferred_output(struct perf_event *event, void *data)
+{
+	struct perf_callchain_deferred_event *deferred_event = data;
+	struct perf_output_handle handle;
+	struct perf_sample_data sample;
+	int ret, size = deferred_event->event.header.size;
+
+	if (!event->attr.defer_output)
+		return;
+
+	/* XXX do we really need sample_id_all for this ??? */
+	perf_event_header__init_id(&deferred_event->event.header, &sample, event);
+
+	ret = perf_output_begin(&handle, &sample, event,
+				deferred_event->event.header.size);
+	if (ret)
+		goto out;
+
+	perf_output_put(&handle, deferred_event->event);
+	for (int i = 0; i < deferred_event->trace->nr; i++) {
+		u64 entry = deferred_event->trace->entries[i];
+		perf_output_put(&handle, entry);
+	}
+	perf_event__output_id_sample(event, &handle, &sample);
+
+	perf_output_end(&handle);
+out:
+	deferred_event->event.header.size = size;
+}
+
+static void perf_unwind_deferred_callback(struct unwind_work *work,
+					 struct unwind_stacktrace *trace, u64 cookie)
+{
+	struct perf_callchain_deferred_event deferred_event = {
+		.trace = trace,
+		.event = {
+			.header = {
+				.type = PERF_RECORD_CALLCHAIN_DEFERRED,
+				.misc = PERF_RECORD_MISC_USER,
+				.size = sizeof(deferred_event.event) +
+					(trace->nr * sizeof(u64)),
+			},
+			.cookie = cookie,
+			.nr = trace->nr,
+		},
+	};
+
+	perf_iterate_sb(perf_callchain_deferred_output, &deferred_event, NULL);
+}
+
 struct perf_text_poke_event {
 	const void		*old_bytes;
 	const void		*new_bytes;
@@ -14809,6 +14880,9 @@ void __init perf_event_init(void)
 
 	idr_init(&pmu_idr);
 
+	unwind_deferred_init(&perf_unwind_work,
+			     perf_unwind_deferred_callback);
+
 	perf_event_init_all_cpus();
 	init_srcu_struct(&pmus_srcu);
 	perf_pmu_register(&perf_swevent, "software", PERF_TYPE_SOFTWARE);