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
  ...

1 files changed, 147 insertions, 4 deletions

diff --git a/arch/x86/lib/insn-eval.c b/arch/x86/lib/insn-eval.c
index 4e385cbfd444..e03eeec55cfe 100644
--- a/arch/x86/lib/insn-eval.c
+++ b/arch/x86/lib/insn-eval.c
@@ -63,11 +63,10 @@ static bool is_string_insn(struct insn *insn)
 bool insn_has_rep_prefix(struct insn *insn)
 {
 	insn_byte_t p;
-	int i;
 
 	insn_get_prefixes(insn);
 
-	for_each_insn_prefix(insn, i, p) {
+	for_each_insn_prefix(insn, p) {
 		if (p == 0xf2 || p == 0xf3)
 			return true;
 	}
@@ -92,13 +91,13 @@ bool insn_has_rep_prefix(struct insn *insn)
 static int get_seg_reg_override_idx(struct insn *insn)
 {
 	int idx = INAT_SEG_REG_DEFAULT;
-	int num_overrides = 0, i;
+	int num_overrides = 0;
 	insn_byte_t p;
 
 	insn_get_prefixes(insn);
 
 	/* Look for any segment override prefixes. */
-	for_each_insn_prefix(insn, i, p) {
+	for_each_insn_prefix(insn, p) {
 		insn_attr_t attr;
 
 		attr = inat_get_opcode_attribute(p);
@@ -1676,3 +1675,147 @@ enum insn_mmio_type insn_decode_mmio(struct insn *insn, int *bytes)
 
 	return type;
 }
+
+/*
+ * Recognise typical NOP patterns for both 32bit and 64bit.
+ *
+ * Notably:
+ *  - NOP, but not: REP NOP aka PAUSE
+ *  - NOPL
+ *  - MOV %reg, %reg
+ *  - LEA 0(%reg),%reg
+ *  - JMP +0
+ *
+ * Must not have false-positives; instructions identified as a NOP might be
+ * emulated as a NOP (uprobe) or Run Length Encoded in a larger NOP
+ * (alternatives).
+ *
+ * False-negatives are fine; need not be exhaustive.
+ */
+bool insn_is_nop(struct insn *insn)
+{
+	u8 b3 = 0, x3 = 0, r3 = 0;
+	u8 b4 = 0, x4 = 0, r4 = 0, m = 0;
+	u8 modrm, modrm_mod, modrm_reg, modrm_rm;
+	u8 sib = 0, sib_scale, sib_index, sib_base;
+	u8 nrex, rex;
+	u8 p, rep = 0;
+
+	if ((nrex = insn->rex_prefix.nbytes)) {
+		rex = insn->rex_prefix.bytes[nrex-1];
+
+		r3 = !!X86_REX_R(rex);
+		x3 = !!X86_REX_X(rex);
+		b3 = !!X86_REX_B(rex);
+		if (nrex > 1) {
+			r4 = !!X86_REX2_R(rex);
+			x4 = !!X86_REX2_X(rex);
+			b4 = !!X86_REX2_B(rex);
+			m  = !!X86_REX2_M(rex);
+		}
+
+	} else if (insn->vex_prefix.nbytes) {
+		/*
+		 * Ignore VEX encoded NOPs
+		 */
+		return false;
+	}
+
+	if (insn->modrm.nbytes) {
+		modrm = insn->modrm.bytes[0];
+		modrm_mod = X86_MODRM_MOD(modrm);
+		modrm_reg = X86_MODRM_REG(modrm) + 8*r3 + 16*r4;
+		modrm_rm  = X86_MODRM_RM(modrm)  + 8*b3 + 16*b4;
+		modrm = 1;
+	}
+
+	if (insn->sib.nbytes) {
+		sib = insn->sib.bytes[0];
+		sib_scale = X86_SIB_SCALE(sib);
+		sib_index = X86_SIB_INDEX(sib) + 8*x3 + 16*x4;
+		sib_base  = X86_SIB_BASE(sib)  + 8*b3 + 16*b4;
+		sib = 1;
+
+		modrm_rm = sib_base;
+	}
+
+	for_each_insn_prefix(insn, p) {
+		if (p == 0xf3) /* REPE */
+			rep = 1;
+	}
+
+	/*
+	 * Opcode map munging:
+	 *
+	 * REX2: 0 - single byte opcode
+	 *       1 - 0f second byte opcode
+	 */
+	switch (m) {
+	case 0: break;
+	case 1: insn->opcode.value <<= 8;
+		insn->opcode.value |= 0x0f;
+		break;
+	default:
+		return false;
+	}
+
+	switch (insn->opcode.bytes[0]) {
+	case 0x0f: /* 2nd byte */
+		break;
+
+	case 0x89: /* MOV */
+		if (modrm_mod != 3) /* register-direct */
+			return false;
+
+		/* native size */
+		if (insn->opnd_bytes != 4 * (1 + insn->x86_64))
+			return false;
+
+		return modrm_reg == modrm_rm; /* MOV %reg, %reg */
+
+	case 0x8d: /* LEA */
+		if (modrm_mod == 0 || modrm_mod == 3) /* register-indirect with disp */
+			return false;
+
+		/* native size */
+		if (insn->opnd_bytes != 4 * (1 + insn->x86_64))
+			return false;
+
+		if (insn->displacement.value != 0)
+			return false;
+
+		if (sib && (sib_scale != 0 || sib_index != 4)) /* (%reg, %eiz, 1) */
+			return false;
+
+		for_each_insn_prefix(insn, p) {
+			if (p != 0x3e) /* DS */
+				return false;
+		}
+
+		return modrm_reg == modrm_rm; /* LEA 0(%reg), %reg */
+
+	case 0x90: /* NOP */
+		if (b3 || b4) /* XCHG %r{8,16,24},%rax */
+			return false;
+
+		if (rep) /* REP NOP := PAUSE */
+			return false;
+
+		return true;
+
+	case 0xe9: /* JMP.d32 */
+	case 0xeb: /* JMP.d8 */
+		return insn->immediate.value == 0; /* JMP +0 */
+
+	default:
+		return false;
+	}
+
+	switch (insn->opcode.bytes[1]) {
+	case 0x1f:
+		return modrm_reg == 0; /* 0f 1f /0 -- NOPL */
+
+	default:
+		return false;
+	}
+}