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
  ...

7 files changed, 195 insertions, 8 deletions

diff --git a/arch/x86/include/asm/insn-eval.h b/arch/x86/include/asm/insn-eval.h
index 54368a43abf6..4733e9064ee5 100644
--- a/arch/x86/include/asm/insn-eval.h
+++ b/arch/x86/include/asm/insn-eval.h
@@ -44,4 +44,6 @@ enum insn_mmio_type {
 
 enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes);
 
+bool insn_is_nop(struct insn *insn);
+
 #endif /* _ASM_X86_INSN_EVAL_H */
diff --git a/arch/x86/include/asm/insn.h b/arch/x86/include/asm/insn.h
index 091f88c8254d..846d21c1a7f8 100644
--- a/arch/x86/include/asm/insn.h
+++ b/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/arch/x86/include/asm/intel_ds.h b/arch/x86/include/asm/intel_ds.h
index 5dbeac48a5b9..695f87efbeb8 100644
--- a/arch/x86/include/asm/intel_ds.h
+++ b/arch/x86/include/asm/intel_ds.h
@@ -4,7 +4,15 @@
 #include <linux/percpu-defs.h>
 
 #define BTS_BUFFER_SIZE		(PAGE_SIZE << 4)
-#define PEBS_BUFFER_SIZE	(PAGE_SIZE << 4)
+#define PEBS_BUFFER_SHIFT	4
+#define PEBS_BUFFER_SIZE	(PAGE_SIZE << PEBS_BUFFER_SHIFT)
+
+/*
+ * The largest PEBS record could consume a page, ensure
+ * a record at least can be written after triggering PMI.
+ */
+#define ARCH_PEBS_THRESH_MULTI	((PEBS_BUFFER_SIZE - PAGE_SIZE) >> PEBS_BUFFER_SHIFT)
+#define ARCH_PEBS_THRESH_SINGLE	1
 
 /* The maximal number of PEBS events: */
 #define MAX_PEBS_EVENTS_FMT4	8
diff --git a/arch/x86/include/asm/msr-index.h b/arch/x86/include/asm/msr-index.h
index 9e1720d73244..65cc528fbad8 100644
--- a/arch/x86/include/asm/msr-index.h
+++ b/arch/x86/include/asm/msr-index.h
@@ -327,6 +327,26 @@
 					 PERF_CAP_PEBS_FORMAT | PERF_CAP_PEBS_BASELINE | \
 					 PERF_CAP_PEBS_TIMING_INFO)
 
+/* Arch PEBS */
+#define MSR_IA32_PEBS_BASE		0x000003f4
+#define MSR_IA32_PEBS_INDEX		0x000003f5
+#define ARCH_PEBS_OFFSET_MASK		0x7fffff
+#define ARCH_PEBS_INDEX_WR_SHIFT	4
+
+#define ARCH_PEBS_RELOAD		0xffffffff
+#define ARCH_PEBS_CNTR_ALLOW		BIT_ULL(35)
+#define ARCH_PEBS_CNTR_GP		BIT_ULL(36)
+#define ARCH_PEBS_CNTR_FIXED		BIT_ULL(37)
+#define ARCH_PEBS_CNTR_METRICS		BIT_ULL(38)
+#define ARCH_PEBS_LBR_SHIFT		40
+#define ARCH_PEBS_LBR			(0x3ull << ARCH_PEBS_LBR_SHIFT)
+#define ARCH_PEBS_VECR_XMM		BIT_ULL(49)
+#define ARCH_PEBS_GPR			BIT_ULL(61)
+#define ARCH_PEBS_AUX			BIT_ULL(62)
+#define ARCH_PEBS_EN			BIT_ULL(63)
+#define ARCH_PEBS_CNTR_MASK		(ARCH_PEBS_CNTR_GP | ARCH_PEBS_CNTR_FIXED | \
+					 ARCH_PEBS_CNTR_METRICS)
+
 #define MSR_IA32_RTIT_CTL		0x00000570
 #define RTIT_CTL_TRACEEN		BIT(0)
 #define RTIT_CTL_CYCLEACC		BIT(1)
diff --git a/arch/x86/include/asm/perf_event.h b/arch/x86/include/asm/perf_event.h
index 49a4d442f3fc..7276ba70c88a 100644
--- a/arch/x86/include/asm/perf_event.h
+++ b/arch/x86/include/asm/perf_event.h
@@ -141,16 +141,16 @@
 #define ARCH_PERFMON_EVENTS_COUNT			7
 
 #define PEBS_DATACFG_MEMINFO	BIT_ULL(0)
-#define PEBS_DATACFG_GP	BIT_ULL(1)
+#define PEBS_DATACFG_GP		BIT_ULL(1)
 #define PEBS_DATACFG_XMMS	BIT_ULL(2)
 #define PEBS_DATACFG_LBRS	BIT_ULL(3)
-#define PEBS_DATACFG_LBR_SHIFT	24
 #define PEBS_DATACFG_CNTR	BIT_ULL(4)
+#define PEBS_DATACFG_METRICS	BIT_ULL(5)
+#define PEBS_DATACFG_LBR_SHIFT	24
 #define PEBS_DATACFG_CNTR_SHIFT	32
 #define PEBS_DATACFG_CNTR_MASK	GENMASK_ULL(15, 0)
 #define PEBS_DATACFG_FIX_SHIFT	48
 #define PEBS_DATACFG_FIX_MASK	GENMASK_ULL(7, 0)
-#define PEBS_DATACFG_METRICS	BIT_ULL(5)
 
 /* Steal the highest bit of pebs_data_cfg for SW usage */
 #define PEBS_UPDATE_DS_SW	BIT_ULL(63)
@@ -200,6 +200,8 @@ union cpuid10_edx {
 #define ARCH_PERFMON_EXT_LEAF			0x00000023
 #define ARCH_PERFMON_NUM_COUNTER_LEAF		0x1
 #define ARCH_PERFMON_ACR_LEAF			0x2
+#define ARCH_PERFMON_PEBS_CAP_LEAF		0x4
+#define ARCH_PERFMON_PEBS_COUNTER_LEAF		0x5
 
 union cpuid35_eax {
 	struct {
@@ -210,7 +212,10 @@ union cpuid35_eax {
 		unsigned int    acr_subleaf:1;
 		/* Events Sub-Leaf */
 		unsigned int    events_subleaf:1;
-		unsigned int	reserved:28;
+		/* arch-PEBS Sub-Leaves */
+		unsigned int	pebs_caps_subleaf:1;
+		unsigned int	pebs_cnts_subleaf:1;
+		unsigned int	reserved:26;
 	} split;
 	unsigned int            full;
 };
@@ -432,6 +437,8 @@ static inline bool is_topdown_idx(int idx)
 #define GLOBAL_STATUS_LBRS_FROZEN		BIT_ULL(GLOBAL_STATUS_LBRS_FROZEN_BIT)
 #define GLOBAL_STATUS_TRACE_TOPAPMI_BIT		55
 #define GLOBAL_STATUS_TRACE_TOPAPMI		BIT_ULL(GLOBAL_STATUS_TRACE_TOPAPMI_BIT)
+#define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT	54
+#define GLOBAL_STATUS_ARCH_PEBS_THRESHOLD	BIT_ULL(GLOBAL_STATUS_ARCH_PEBS_THRESHOLD_BIT)
 #define GLOBAL_STATUS_PERF_METRICS_OVF_BIT	48
 
 #define GLOBAL_CTRL_EN_PERF_METRICS		BIT_ULL(48)
@@ -503,6 +510,107 @@ struct pebs_cntr_header {
 #define INTEL_CNTR_METRICS		0x3
 
 /*
+ * Arch PEBS
+ */
+union arch_pebs_index {
+	struct {
+		u64 rsvd:4,
+		    wr:23,
+		    rsvd2:4,
+		    full:1,
+		    en:1,
+		    rsvd3:3,
+		    thresh:23,
+		    rsvd4:5;
+	};
+	u64 whole;
+};
+
+struct arch_pebs_header {
+	union {
+		u64 format;
+		struct {
+			u64 size:16,	/* Record size */
+			    rsvd:14,
+			    mode:1,	/* 64BIT_MODE */
+			    cont:1,
+			    rsvd2:3,
+			    cntr:5,
+			    lbr:2,
+			    rsvd3:7,
+			    xmm:1,
+			    ymmh:1,
+			    rsvd4:2,
+			    opmask:1,
+			    zmmh:1,
+			    h16zmm:1,
+			    rsvd5:5,
+			    gpr:1,
+			    aux:1,
+			    basic:1;
+		};
+	};
+	u64 rsvd6;
+};
+
+struct arch_pebs_basic {
+	u64 ip;
+	u64 applicable_counters;
+	u64 tsc;
+	u64 retire	:16,	/* Retire Latency */
+	    valid	:1,
+	    rsvd	:47;
+	u64 rsvd2;
+	u64 rsvd3;
+};
+
+struct arch_pebs_aux {
+	u64 address;
+	u64 rsvd;
+	u64 rsvd2;
+	u64 rsvd3;
+	u64 rsvd4;
+	u64 aux;
+	u64 instr_latency	:16,
+	    pad2		:16,
+	    cache_latency	:16,
+	    pad3		:16;
+	u64 tsx_tuning;
+};
+
+struct arch_pebs_gprs {
+	u64 flags, ip, ax, cx, dx, bx, sp, bp, si, di;
+	u64 r8, r9, r10, r11, r12, r13, r14, r15, ssp;
+	u64 rsvd;
+};
+
+struct arch_pebs_xer_header {
+	u64 xstate;
+	u64 rsvd;
+};
+
+#define ARCH_PEBS_LBR_NAN		0x0
+#define ARCH_PEBS_LBR_NUM_8		0x1
+#define ARCH_PEBS_LBR_NUM_16		0x2
+#define ARCH_PEBS_LBR_NUM_VAR		0x3
+#define ARCH_PEBS_BASE_LBR_ENTRIES	8
+struct arch_pebs_lbr_header {
+	u64 rsvd;
+	u64 ctl;
+	u64 depth;
+	u64 ler_from;
+	u64 ler_to;
+	u64 ler_info;
+};
+
+struct arch_pebs_cntr_header {
+	u32 cntr;
+	u32 fixed;
+	u32 metrics;
+	u32 reserved;
+};
+
+/*
  * AMD Extended Performance Monitoring and Debug cpuid feature detection
  */
 #define EXT_PERFMON_DEBUG_FEATURES		0x80000022
diff --git a/arch/x86/include/asm/unwind_user.h b/arch/x86/include/asm/unwind_user.h
new file mode 100644
index 000000000000..12064284bc4e
--- /dev/null
+++ b/arch/x86/include/asm/unwind_user.h
@@ -0,0 +1,41 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _ASM_X86_UNWIND_USER_H
+#define _ASM_X86_UNWIND_USER_H
+
+#ifdef CONFIG_HAVE_UNWIND_USER_FP
+
+#include <asm/ptrace.h>
+#include <asm/uprobes.h>
+
+#define ARCH_INIT_USER_FP_FRAME(ws)			\
+	.cfa_off	=  2*(ws),			\
+	.ra_off		= -1*(ws),			\
+	.fp_off		= -2*(ws),			\
+	.use_fp		= true,
+
+#define ARCH_INIT_USER_FP_ENTRY_FRAME(ws)		\
+	.cfa_off	=  1*(ws),			\
+	.ra_off		= -1*(ws),			\
+	.fp_off		= 0,				\
+	.use_fp		= false,
+
+static inline int unwind_user_word_size(struct pt_regs *regs)
+{
+	/* We can't unwind VM86 stacks */
+	if (regs->flags & X86_VM_MASK)
+		return 0;
+#ifdef CONFIG_X86_64
+	if (!user_64bit_mode(regs))
+		return sizeof(int);
+#endif
+	return sizeof(long);
+}
+
+static inline bool unwind_user_at_function_start(struct pt_regs *regs)
+{
+	return is_uprobe_at_func_entry(regs);
+}
+
+#endif /* CONFIG_HAVE_UNWIND_USER_FP */
+
+#endif /* _ASM_X86_UNWIND_USER_H */
diff --git a/arch/x86/include/asm/uprobes.h b/arch/x86/include/asm/uprobes.h
index 1ee2e5115955..362210c79998 100644
--- a/arch/x86/include/asm/uprobes.h
+++ b/arch/x86/include/asm/uprobes.h
@@ -62,4 +62,13 @@ struct arch_uprobe_task {
 	unsigned int			saved_tf;
 };
 
+#ifdef CONFIG_UPROBES
+extern bool is_uprobe_at_func_entry(struct pt_regs *regs);
+#else
+static bool is_uprobe_at_func_entry(struct pt_regs *regs)
+{
+	return false;
+}
+#endif /* CONFIG_UPROBES */
+
 #endif	/* _ASM_UPROBES_H */