10 files changed, 766 insertions, 52 deletions

diff --git a/tools/perf/arch/arm/util/pmu.c b/tools/perf/arch/arm/util/pmu.c
index 1c9541d01722..57dc94a6e38c 100644
--- a/tools/perf/arch/arm/util/pmu.c
+++ b/tools/perf/arch/arm/util/pmu.c
@@ -23,16 +23,19 @@ void perf_pmu__arch_init(struct perf_pmu *pmu)
 #ifdef HAVE_AUXTRACE_SUPPORT
 	if (!strcmp(pmu->name, CORESIGHT_ETM_PMU_NAME)) {
 		/* add ETM default config here */
+		pmu->auxtrace = true;
 		pmu->selectable = true;
 		pmu->perf_event_attr_init_default = cs_etm_get_default_config;
 #if defined(__aarch64__)
 	} else if (strstarts(pmu->name, ARM_SPE_PMU_NAME)) {
+		pmu->auxtrace = true;
 		pmu->selectable = true;
 		pmu->is_uncore = false;
 		pmu->perf_event_attr_init_default = arm_spe_pmu_default_config;
 		if (strstarts(pmu->name, "arm_spe_"))
 			pmu->mem_events = perf_mem_events_arm;
 	} else if (strstarts(pmu->name, HISI_PTT_PMU_NAME)) {
+		pmu->auxtrace = true;
 		pmu->selectable = true;
 #endif
 	}
diff --git a/tools/perf/arch/arm64/annotate/instructions.c b/tools/perf/arch/arm64/annotate/instructions.c
index 4af0c3a0f86e..f86d9f4798bd 100644
--- a/tools/perf/arch/arm64/annotate/instructions.c
+++ b/tools/perf/arch/arm64/annotate/instructions.c
@@ -11,7 +11,8 @@ struct arm64_annotate {
 
 static int arm64_mov__parse(struct arch *arch __maybe_unused,
 			    struct ins_operands *ops,
-			    struct map_symbol *ms __maybe_unused)
+			    struct map_symbol *ms __maybe_unused,
+			    struct disasm_line *dl __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *endptr;
 
diff --git a/tools/perf/arch/arm64/util/arm-spe.c b/tools/perf/arch/arm64/util/arm-spe.c
index 0b52e67edb3b..d59f6ca499f2 100644
--- a/tools/perf/arch/arm64/util/arm-spe.c
+++ b/tools/perf/arch/arm64/util/arm-spe.c
@@ -8,6 +8,7 @@
 #include <linux/types.h>
 #include <linux/bitops.h>
 #include <linux/log2.h>
+#include <linux/string.h>
 #include <linux/zalloc.h>
 #include <time.h>
 
@@ -132,32 +133,66 @@ static __u64 arm_spe_pmu__sample_period(const struct perf_pmu *arm_spe_pmu)
 	return sample_period;
 }
 
+static void arm_spe_setup_evsel(struct evsel *evsel, struct perf_cpu_map *cpus)
+{
+	u64 bit;
+
+	evsel->core.attr.freq = 0;
+	evsel->core.attr.sample_period = arm_spe_pmu__sample_period(evsel->pmu);
+	evsel->needs_auxtrace_mmap = true;
+
+	/*
+	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
+	 * must come first.
+	 */
+	evlist__to_front(evsel->evlist, evsel);
+
+	/*
+	 * In the case of per-cpu mmaps, sample CPU for AUX event;
+	 * also enable the timestamp tracing for samples correlation.
+	 */
+	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
+		evsel__set_sample_bit(evsel, CPU);
+		evsel__set_config_if_unset(evsel->pmu, evsel, "ts_enable", 1);
+	}
+
+	/*
+	 * Set this only so that perf report knows that SPE generates memory info. It has no effect
+	 * on the opening of the event or the SPE data produced.
+	 */
+	evsel__set_sample_bit(evsel, DATA_SRC);
+
+	/*
+	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
+	 * inform that the resulting output's SPE samples contain physical addresses
+	 * where applicable.
+	 */
+	bit = perf_pmu__format_bits(evsel->pmu, "pa_enable");
+	if (evsel->core.attr.config & bit)
+		evsel__set_sample_bit(evsel, PHYS_ADDR);
+}
+
 static int arm_spe_recording_options(struct auxtrace_record *itr,
 				     struct evlist *evlist,
 				     struct record_opts *opts)
 {
 	struct arm_spe_recording *sper =
 			container_of(itr, struct arm_spe_recording, itr);
-	struct perf_pmu *arm_spe_pmu = sper->arm_spe_pmu;
-	struct evsel *evsel, *arm_spe_evsel = NULL;
+	struct evsel *evsel, *tmp;
 	struct perf_cpu_map *cpus = evlist->core.user_requested_cpus;
 	bool privileged = perf_event_paranoid_check(-1);
 	struct evsel *tracking_evsel;
 	int err;
-	u64 bit;
 
 	sper->evlist = evlist;
 
 	evlist__for_each_entry(evlist, evsel) {
-		if (evsel->core.attr.type == arm_spe_pmu->type) {
-			if (arm_spe_evsel) {
-				pr_err("There may be only one " ARM_SPE_PMU_NAME "x event\n");
+		if (evsel__is_aux_event(evsel)) {
+			if (!strstarts(evsel->pmu_name, ARM_SPE_PMU_NAME)) {
+				pr_err("Found unexpected auxtrace event: %s\n",
+				       evsel->pmu_name);
 				return -EINVAL;
 			}
-			evsel->core.attr.freq = 0;
-			evsel->core.attr.sample_period = arm_spe_pmu__sample_period(arm_spe_pmu);
-			evsel->needs_auxtrace_mmap = true;
-			arm_spe_evsel = evsel;
 			opts->full_auxtrace = true;
 		}
 	}
@@ -222,37 +257,11 @@ static int arm_spe_recording_options(struct auxtrace_record *itr,
 		pr_debug2("%sx snapshot size: %zu\n", ARM_SPE_PMU_NAME,
 			  opts->auxtrace_snapshot_size);
 
-	/*
-	 * To obtain the auxtrace buffer file descriptor, the auxtrace event
-	 * must come first.
-	 */
-	evlist__to_front(evlist, arm_spe_evsel);
-
-	/*
-	 * In the case of per-cpu mmaps, sample CPU for AUX event;
-	 * also enable the timestamp tracing for samples correlation.
-	 */
-	if (!perf_cpu_map__is_any_cpu_or_is_empty(cpus)) {
-		evsel__set_sample_bit(arm_spe_evsel, CPU);
-		evsel__set_config_if_unset(arm_spe_pmu, arm_spe_evsel,
-					   "ts_enable", 1);
+	evlist__for_each_entry_safe(evlist, tmp, evsel) {
+		if (evsel__is_aux_event(evsel))
+			arm_spe_setup_evsel(evsel, cpus);
 	}
 
-	/*
-	 * Set this only so that perf report knows that SPE generates memory info. It has no effect
-	 * on the opening of the event or the SPE data produced.
-	 */
-	evsel__set_sample_bit(arm_spe_evsel, DATA_SRC);
-
-	/*
-	 * The PHYS_ADDR flag does not affect the driver behaviour, it is used to
-	 * inform that the resulting output's SPE samples contain physical addresses
-	 * where applicable.
-	 */
-	bit = perf_pmu__format_bits(arm_spe_pmu, "pa_enable");
-	if (arm_spe_evsel->core.attr.config & bit)
-		evsel__set_sample_bit(arm_spe_evsel, PHYS_ADDR);
-
 	/* Add dummy event to keep tracking */
 	err = parse_event(evlist, "dummy:u");
 	if (err)
@@ -301,12 +310,16 @@ static int arm_spe_snapshot_start(struct auxtrace_record *itr)
 	struct arm_spe_recording *ptr =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct evsel *evsel;
+	int ret = -EINVAL;
 
 	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
-			return evsel__disable(evsel);
+		if (evsel__is_aux_event(evsel)) {
+			ret = evsel__disable(evsel);
+			if (ret < 0)
+				return ret;
+		}
 	}
-	return -EINVAL;
+	return ret;
 }
 
 static int arm_spe_snapshot_finish(struct auxtrace_record *itr)
@@ -314,12 +327,16 @@ static int arm_spe_snapshot_finish(struct auxtrace_record *itr)
 	struct arm_spe_recording *ptr =
 			container_of(itr, struct arm_spe_recording, itr);
 	struct evsel *evsel;
+	int ret = -EINVAL;
 
 	evlist__for_each_entry(ptr->evlist, evsel) {
-		if (evsel->core.attr.type == ptr->arm_spe_pmu->type)
-			return evsel__enable(evsel);
+		if (evsel__is_aux_event(evsel)) {
+			ret = evsel__enable(evsel);
+			if (ret < 0)
+				return ret;
+		}
 	}
-	return -EINVAL;
+	return ret;
 }
 
 static int arm_spe_alloc_wrapped_array(struct arm_spe_recording *ptr, int idx)
diff --git a/tools/perf/arch/loongarch/annotate/instructions.c b/tools/perf/arch/loongarch/annotate/instructions.c
index 21cc7e4149f7..ab43b1ab51e3 100644
--- a/tools/perf/arch/loongarch/annotate/instructions.c
+++ b/tools/perf/arch/loongarch/annotate/instructions.c
@@ -5,7 +5,8 @@
  * Copyright (C) 2020-2023 Loongson Technology Corporation Limited
  */
 
-static int loongarch_call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+static int loongarch_call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms,
+		struct disasm_line *dl __maybe_unused)
 {
 	char *c, *endptr, *tok, *name;
 	struct map *map = ms->map;
@@ -51,7 +52,8 @@ static struct ins_ops loongarch_call_ops = {
 	.scnprintf = call__scnprintf,
 };
 
-static int loongarch_jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+static int loongarch_jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms,
+		struct disasm_line *dl __maybe_unused)
 {
 	struct map *map = ms->map;
 	struct symbol *sym = ms->sym;
diff --git a/tools/perf/arch/powerpc/annotate/instructions.c b/tools/perf/arch/powerpc/annotate/instructions.c
index a3f423c27cae..ede9eeade0ab 100644
--- a/tools/perf/arch/powerpc/annotate/instructions.c
+++ b/tools/perf/arch/powerpc/annotate/instructions.c
@@ -49,12 +49,266 @@ static struct ins_ops *powerpc__associate_instruction_ops(struct arch *arch, con
 	return ops;
 }
 
+#define PPC_OP(op)	(((op) >> 26) & 0x3F)
+#define PPC_21_30(R)	(((R) >> 1) & 0x3ff)
+#define PPC_22_30(R)	(((R) >> 1) & 0x1ff)
+
+struct insn_offset {
+	const char	*name;
+	int		value;
+};
+
+/*
+ * There are memory instructions with opcode 31 which are
+ * of X Form, Example:
+ * ldx RT,RA,RB
+ * ______________________________________
+ * | 31 |  RT  |  RA |  RB |   21     |/|
+ * --------------------------------------
+ * 0    6     11    16    21         30 31
+ *
+ * But all instructions with opcode 31 are not memory.
+ * Example: add RT,RA,RB
+ *
+ * Use bits 21 to 30 to check memory insns with 31 as opcode.
+ * In ins_array below, for ldx instruction:
+ * name => OP_31_XOP_LDX
+ * value => 21
+ */
+
+static struct insn_offset ins_array[] = {
+	{ .name = "OP_31_XOP_LXSIWZX",  .value = 12, },
+	{ .name = "OP_31_XOP_LWARX",	.value = 20, },
+	{ .name = "OP_31_XOP_LDX",	.value = 21, },
+	{ .name = "OP_31_XOP_LWZX",	.value = 23, },
+	{ .name = "OP_31_XOP_LDUX",	.value = 53, },
+	{ .name = "OP_31_XOP_LWZUX",	.value = 55, },
+	{ .name = "OP_31_XOP_LXSIWAX",  .value = 76, },
+	{ .name = "OP_31_XOP_LDARX",    .value = 84, },
+	{ .name = "OP_31_XOP_LBZX",	.value = 87, },
+	{ .name = "OP_31_XOP_LVX",      .value = 103, },
+	{ .name = "OP_31_XOP_LBZUX",    .value = 119, },
+	{ .name = "OP_31_XOP_STXSIWX",  .value = 140, },
+	{ .name = "OP_31_XOP_STDX",	.value = 149, },
+	{ .name = "OP_31_XOP_STWX",	.value = 151, },
+	{ .name = "OP_31_XOP_STDUX",	.value = 181, },
+	{ .name = "OP_31_XOP_STWUX",	.value = 183, },
+	{ .name = "OP_31_XOP_STBX",	.value = 215, },
+	{ .name = "OP_31_XOP_STVX",     .value = 231, },
+	{ .name = "OP_31_XOP_STBUX",	.value = 247, },
+	{ .name = "OP_31_XOP_LHZX",	.value = 279, },
+	{ .name = "OP_31_XOP_LHZUX",	.value = 311, },
+	{ .name = "OP_31_XOP_LXVDSX",   .value = 332, },
+	{ .name = "OP_31_XOP_LWAX",	.value = 341, },
+	{ .name = "OP_31_XOP_LHAX",	.value = 343, },
+	{ .name = "OP_31_XOP_LWAUX",	.value = 373, },
+	{ .name = "OP_31_XOP_LHAUX",	.value = 375, },
+	{ .name = "OP_31_XOP_STHX",	.value = 407, },
+	{ .name = "OP_31_XOP_STHUX",	.value = 439, },
+	{ .name = "OP_31_XOP_LXSSPX",   .value = 524, },
+	{ .name = "OP_31_XOP_LDBRX",	.value = 532, },
+	{ .name = "OP_31_XOP_LSWX",	.value = 533, },
+	{ .name = "OP_31_XOP_LWBRX",	.value = 534, },
+	{ .name = "OP_31_XOP_LFSUX",    .value = 567, },
+	{ .name = "OP_31_XOP_LXSDX",    .value = 588, },
+	{ .name = "OP_31_XOP_LSWI",	.value = 597, },
+	{ .name = "OP_31_XOP_LFDX",     .value = 599, },
+	{ .name = "OP_31_XOP_LFDUX",    .value = 631, },
+	{ .name = "OP_31_XOP_STXSSPX",  .value = 652, },
+	{ .name = "OP_31_XOP_STDBRX",	.value = 660, },
+	{ .name = "OP_31_XOP_STXWX",	.value = 661, },
+	{ .name = "OP_31_XOP_STWBRX",	.value = 662, },
+	{ .name = "OP_31_XOP_STFSX",	.value = 663, },
+	{ .name = "OP_31_XOP_STFSUX",	.value = 695, },
+	{ .name = "OP_31_XOP_STXSDX",   .value = 716, },
+	{ .name = "OP_31_XOP_STSWI",	.value = 725, },
+	{ .name = "OP_31_XOP_STFDX",	.value = 727, },
+	{ .name = "OP_31_XOP_STFDUX",	.value = 759, },
+	{ .name = "OP_31_XOP_LXVW4X",   .value = 780, },
+	{ .name = "OP_31_XOP_LHBRX",	.value = 790, },
+	{ .name = "OP_31_XOP_LXVD2X",   .value = 844, },
+	{ .name = "OP_31_XOP_LFIWAX",	.value = 855, },
+	{ .name = "OP_31_XOP_LFIWZX",	.value = 887, },
+	{ .name = "OP_31_XOP_STXVW4X",  .value = 908, },
+	{ .name = "OP_31_XOP_STHBRX",	.value = 918, },
+	{ .name = "OP_31_XOP_STXVD2X",  .value = 972, },
+	{ .name = "OP_31_XOP_STFIWX",	.value = 983, },
+};
+
+/*
+ * Arithmetic instructions which are having opcode as 31.
+ * These instructions are tracked to save the register state
+ * changes. Example:
+ *
+ * lwz	r10,264(r3)
+ * add	r31, r3, r3
+ * lwz	r9, 0(r31)
+ *
+ * Here instruction tracking needs to identify the "add"
+ * instruction and save data type of r3 to r31. If a sample
+ * is hit at next "lwz r9, 0(r31)", by this instruction tracking,
+ * data type of r31 can be resolved.
+ */
+static struct insn_offset arithmetic_ins_op_31[] = {
+	{ .name = "SUB_CARRY_XO_FORM",  .value = 8, },
+	{ .name = "MUL_HDW_XO_FORM1",   .value = 9, },
+	{ .name = "ADD_CARRY_XO_FORM",  .value = 10, },
+	{ .name = "MUL_HW_XO_FORM1",    .value = 11, },
+	{ .name = "SUB_XO_FORM",        .value = 40, },
+	{ .name = "MUL_HDW_XO_FORM",    .value = 73, },
+	{ .name = "MUL_HW_XO_FORM",     .value = 75, },
+	{ .name = "SUB_EXT_XO_FORM",    .value = 136, },
+	{ .name = "ADD_EXT_XO_FORM",    .value = 138, },
+	{ .name = "SUB_ZERO_EXT_XO_FORM",       .value = 200, },
+	{ .name = "ADD_ZERO_EXT_XO_FORM",       .value = 202, },
+	{ .name = "SUB_EXT_XO_FORM2",   .value = 232, },
+	{ .name = "MUL_DW_XO_FORM",     .value = 233, },
+	{ .name = "ADD_EXT_XO_FORM2",   .value = 234, },
+	{ .name = "MUL_W_XO_FORM",      .value = 235, },
+	{ .name = "ADD_XO_FORM",	.value = 266, },
+	{ .name = "DIV_DW_XO_FORM1",    .value = 457, },
+	{ .name = "DIV_W_XO_FORM1",     .value = 459, },
+	{ .name = "DIV_DW_XO_FORM",	.value = 489, },
+	{ .name = "DIV_W_XO_FORM",	.value = 491, },
+};
+
+static struct insn_offset arithmetic_two_ops[] = {
+	{ .name = "mulli",      .value = 7, },
+	{ .name = "subfic",     .value = 8, },
+	{ .name = "addic",      .value = 12, },
+	{ .name = "addic.",     .value = 13, },
+	{ .name = "addi",       .value = 14, },
+	{ .name = "addis",      .value = 15, },
+};
+
+static int cmp_offset(const void *a, const void *b)
+{
+	const struct insn_offset *val1 = a;
+	const struct insn_offset *val2 = b;
+
+	return (val1->value - val2->value);
+}
+
+static struct ins_ops *check_ppc_insn(struct disasm_line *dl)
+{
+	int raw_insn = dl->raw.raw_insn;
+	int opcode = PPC_OP(raw_insn);
+	int mem_insn_31 = PPC_21_30(raw_insn);
+	struct insn_offset *ret;
+	struct insn_offset mem_insns_31_opcode = {
+		"OP_31_INSN",
+		mem_insn_31
+	};
+	char name_insn[32];
+
+	/*
+	 * Instructions with opcode 32 to 63 are memory
+	 * instructions in powerpc
+	 */
+	if ((opcode & 0x20)) {
+		/*
+		 * Set name in case of raw instruction to
+		 * opcode to be used in insn-stat
+		 */
+		if (!strlen(dl->ins.name)) {
+			sprintf(name_insn, "%d", opcode);
+			dl->ins.name = strdup(name_insn);
+		}
+		return &load_store_ops;
+	} else if (opcode == 31) {
+		/* Check for memory instructions with opcode 31 */
+		ret = bsearch(&mem_insns_31_opcode, ins_array, ARRAY_SIZE(ins_array), sizeof(ins_array[0]), cmp_offset);
+		if (ret) {
+			if (!strlen(dl->ins.name))
+				dl->ins.name = strdup(ret->name);
+			return &load_store_ops;
+		} else {
+			mem_insns_31_opcode.value = PPC_22_30(raw_insn);
+			ret = bsearch(&mem_insns_31_opcode, arithmetic_ins_op_31, ARRAY_SIZE(arithmetic_ins_op_31),
+					sizeof(arithmetic_ins_op_31[0]), cmp_offset);
+			if (ret != NULL)
+				return &arithmetic_ops;
+			/* Bits 21 to 30 has value 444 for "mr" insn ie, OR X form */
+			if (PPC_21_30(raw_insn) == 444)
+				return &arithmetic_ops;
+		}
+	} else {
+		mem_insns_31_opcode.value = opcode;
+		ret = bsearch(&mem_insns_31_opcode, arithmetic_two_ops, ARRAY_SIZE(arithmetic_two_ops),
+				sizeof(arithmetic_two_ops[0]), cmp_offset);
+		if (ret != NULL)
+			return &arithmetic_ops;
+	}
+
+	return NULL;
+}
+
+/*
+ * Instruction tracking function to track register state moves.
+ * Example sequence:
+ *    ld      r10,264(r3)
+ *    mr      r31,r3
+ *    <<after some sequence>
+ *    ld      r9,312(r31)
+ *
+ * Previous instruction sequence shows that register state of r3
+ * is moved to r31. update_insn_state_powerpc tracks these state
+ * changes
+ */
+#ifdef HAVE_DWARF_SUPPORT
+static void update_insn_state_powerpc(struct type_state *state,
+		struct data_loc_info *dloc, Dwarf_Die * cu_die __maybe_unused,
+		struct disasm_line *dl)
+{
+	struct annotated_insn_loc loc;
+	struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE];
+	struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET];
+	struct type_state_reg *tsr;
+	u32 insn_offset = dl->al.offset;
+
+	if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0)
+		return;
+
+	/*
+	 * Value 444 for bits 21:30 is for "mr"
+	 * instruction. "mr" is extended OR. So set the
+	 * source and destination reg correctly
+	 */
+	if (PPC_21_30(dl->raw.raw_insn) == 444) {
+		int src_reg = src->reg1;
+
+		src->reg1 = dst->reg1;
+		dst->reg1 = src_reg;
+	}
+
+	if (!has_reg_type(state, dst->reg1))
+		return;
+
+	tsr = &state->regs[dst->reg1];
+
+	if (!has_reg_type(state, src->reg1) ||
+			!state->regs[src->reg1].ok) {
+		tsr->ok = false;
+		return;
+	}
+
+	tsr->type = state->regs[src->reg1].type;
+	tsr->kind = state->regs[src->reg1].kind;
+	tsr->ok = true;
+
+	pr_debug_dtp("mov [%x] reg%d -> reg%d",
+			insn_offset, src->reg1, dst->reg1);
+	pr_debug_type_name(&tsr->type, tsr->kind);
+}
+#endif /* HAVE_DWARF_SUPPORT */
+
 static int powerpc__annotate_init(struct arch *arch, char *cpuid __maybe_unused)
 {
 	if (!arch->initialized) {
 		arch->initialized = true;
 		arch->associate_instruction_ops = powerpc__associate_instruction_ops;
 		arch->objdump.comment_char      = '#';
+		annotate_opts.show_asm_raw = true;
 	}
 
 	return 0;
diff --git a/tools/perf/arch/powerpc/util/dwarf-regs.c b/tools/perf/arch/powerpc/util/dwarf-regs.c
index 0c4f4caf53ac..104c7ae5c433 100644
--- a/tools/perf/arch/powerpc/util/dwarf-regs.c
+++ b/tools/perf/arch/powerpc/util/dwarf-regs.c
@@ -98,3 +98,56 @@ int regs_query_register_offset(const char *name)
 			return roff->ptregs_offset;
 	return -EINVAL;
 }
+
+#define PPC_OP(op)	(((op) >> 26) & 0x3F)
+#define PPC_RA(a)	(((a) >> 16) & 0x1f)
+#define PPC_RT(t)	(((t) >> 21) & 0x1f)
+#define PPC_RB(b)	(((b) >> 11) & 0x1f)
+#define PPC_D(D)	((D) & 0xfffe)
+#define PPC_DS(DS)	((DS) & 0xfffc)
+#define OP_LD	58
+#define OP_STD	62
+
+static int get_source_reg(u32 raw_insn)
+{
+	return PPC_RA(raw_insn);
+}
+
+static int get_target_reg(u32 raw_insn)
+{
+	return PPC_RT(raw_insn);
+}
+
+static int get_offset_opcode(u32 raw_insn)
+{
+	int opcode = PPC_OP(raw_insn);
+
+	/* DS- form */
+	if ((opcode == OP_LD) || (opcode == OP_STD))
+		return PPC_DS(raw_insn);
+	else
+		return PPC_D(raw_insn);
+}
+
+/*
+ * Fills the required fields for op_loc depending on if it
+ * is a source or target.
+ * D form: ins RT,D(RA) -> src_reg1 = RA, offset = D, dst_reg1 = RT
+ * DS form: ins RT,DS(RA) -> src_reg1 = RA, offset = DS, dst_reg1 = RT
+ * X form: ins RT,RA,RB -> src_reg1 = RA, src_reg2 = RB, dst_reg1 = RT
+ */
+void get_powerpc_regs(u32 raw_insn, int is_source,
+		struct annotated_op_loc *op_loc)
+{
+	if (is_source)
+		op_loc->reg1 = get_source_reg(raw_insn);
+	else
+		op_loc->reg1 = get_target_reg(raw_insn);
+
+	if (op_loc->multi_regs)
+		op_loc->reg2 = PPC_RB(raw_insn);
+
+	/* TODO: Implement offset handling for X Form */
+	if ((op_loc->mem_ref) && (PPC_OP(raw_insn) != 31))
+		op_loc->offset = get_offset_opcode(raw_insn);
+}
diff --git a/tools/perf/arch/s390/annotate/instructions.c b/tools/perf/arch/s390/annotate/instructions.c
index da5aa3e1f04c..eeac25cca699 100644
--- a/tools/perf/arch/s390/annotate/instructions.c
+++ b/tools/perf/arch/s390/annotate/instructions.c
@@ -2,7 +2,7 @@
 #include <linux/compiler.h>
 
 static int s390_call__parse(struct arch *arch, struct ins_operands *ops,
-			    struct map_symbol *ms)
+			    struct map_symbol *ms, struct disasm_line *dl __maybe_unused)
 {
 	char *endptr, *tok, *name;
 	struct map *map = ms->map;
@@ -52,7 +52,8 @@ static struct ins_ops s390_call_ops = {
 
 static int s390_mov__parse(struct arch *arch __maybe_unused,
 			   struct ins_operands *ops,
-			   struct map_symbol *ms __maybe_unused)
+			   struct map_symbol *ms __maybe_unused,
+			   struct disasm_line *dl __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *endptr;
 
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 5cdf457f5cbe..7b7d462c6c6b 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -206,3 +206,380 @@ static int x86__annotate_init(struct arch *arch, char *cpuid)
 	arch->initialized = true;
 	return err;
 }
+
+#ifdef HAVE_DWARF_SUPPORT
+static void update_insn_state_x86(struct type_state *state,
+				  struct data_loc_info *dloc, Dwarf_Die *cu_die,
+				  struct disasm_line *dl)
+{
+	struct annotated_insn_loc loc;
+	struct annotated_op_loc *src = &loc.ops[INSN_OP_SOURCE];
+	struct annotated_op_loc *dst = &loc.ops[INSN_OP_TARGET];
+	struct type_state_reg *tsr;
+	Dwarf_Die type_die;
+	u32 insn_offset = dl->al.offset;
+	int fbreg = dloc->fbreg;
+	int fboff = 0;
+
+	if (annotate_get_insn_location(dloc->arch, dl, &loc) < 0)
+		return;
+
+	if (ins__is_call(&dl->ins)) {
+		struct symbol *func = dl->ops.target.sym;
+
+		if (func == NULL)
+			return;
+
+		/* __fentry__ will preserve all registers */
+		if (!strcmp(func->name, "__fentry__"))
+			return;
+
+		pr_debug_dtp("call [%x] %s\n", insn_offset, func->name);
+
+		/* Otherwise invalidate caller-saved registers after call */
+		for (unsigned i = 0; i < ARRAY_SIZE(state->regs); i++) {
+			if (state->regs[i].caller_saved)
+				state->regs[i].ok = false;
+		}
+
+		/* Update register with the return type (if any) */
+		if (die_find_func_rettype(cu_die, func->name, &type_die)) {
+			tsr = &state->regs[state->ret_reg];
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("call [%x] return -> reg%d",
+				     insn_offset, state->ret_reg);
+			pr_debug_type_name(&type_die, tsr->kind);
+		}
+		return;
+	}
+
+	if (!strncmp(dl->ins.name, "add", 3)) {
+		u64 imm_value = -1ULL;
+		int offset;
+		const char *var_name = NULL;
+		struct map_symbol *ms = dloc->ms;
+		u64 ip = ms->sym->start + dl->al.offset;
+
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+
+		if (src->imm)
+			imm_value = src->offset;
+		else if (has_reg_type(state, src->reg1) &&
+			 state->regs[src->reg1].kind == TSR_KIND_CONST)
+			imm_value = state->regs[src->reg1].imm_value;
+		else if (src->reg1 == DWARF_REG_PC) {
+			u64 var_addr = annotate_calc_pcrel(dloc->ms, ip,
+							   src->offset, dl);
+
+			if (get_global_var_info(dloc, var_addr,
+						&var_name, &offset) &&
+			    !strcmp(var_name, "this_cpu_off") &&
+			    tsr->kind == TSR_KIND_CONST) {
+				tsr->kind = TSR_KIND_PERCPU_BASE;
+				imm_value = tsr->imm_value;
+			}
+		}
+		else
+			return;
+
+		if (tsr->kind != TSR_KIND_PERCPU_BASE)
+			return;
+
+		if (get_global_var_type(cu_die, dloc, ip, imm_value, &offset,
+					&type_die) && offset == 0) {
+			/*
+			 * This is not a pointer type, but it should be treated
+			 * as a pointer.
+			 */
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_POINTER;
+			tsr->ok = true;
+
+			pr_debug_dtp("add [%x] percpu %#"PRIx64" -> reg%d",
+				     insn_offset, imm_value, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		return;
+	}
+
+	if (strncmp(dl->ins.name, "mov", 3))
+		return;
+
+	if (dloc->fb_cfa) {
+		u64 ip = dloc->ms->sym->start + dl->al.offset;
+		u64 pc = map__rip_2objdump(dloc->ms->map, ip);
+
+		if (die_get_cfa(dloc->di->dbg, pc, &fbreg, &fboff) < 0)
+			fbreg = -1;
+	}
+
+	/* Case 1. register to register or segment:offset to register transfers */
+	if (!src->mem_ref && !dst->mem_ref) {
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+		if (dso__kernel(map__dso(dloc->ms->map)) &&
+		    src->segment == INSN_SEG_X86_GS && src->imm) {
+			u64 ip = dloc->ms->sym->start + dl->al.offset;
+			u64 var_addr;
+			int offset;
+
+			/*
+			 * In kernel, %gs points to a per-cpu region for the
+			 * current CPU.  Access with a constant offset should
+			 * be treated as a global variable access.
+			 */
+			var_addr = src->offset;
+
+			if (var_addr == 40) {
+				tsr->kind = TSR_KIND_CANARY;
+				tsr->ok = true;
+
+				pr_debug_dtp("mov [%x] stack canary -> reg%d\n",
+					     insn_offset, dst->reg1);
+				return;
+			}
+
+			if (!get_global_var_type(cu_die, dloc, ip, var_addr,
+						 &offset, &type_die) ||
+			    !die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->ok = false;
+				return;
+			}
+
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] this-cpu addr=%#"PRIx64" -> reg%d",
+				     insn_offset, var_addr, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+			return;
+		}
+
+		if (src->imm) {
+			tsr->kind = TSR_KIND_CONST;
+			tsr->imm_value = src->offset;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] imm=%#x -> reg%d\n",
+				     insn_offset, tsr->imm_value, dst->reg1);
+			return;
+		}
+
+		if (!has_reg_type(state, src->reg1) ||
+		    !state->regs[src->reg1].ok) {
+			tsr->ok = false;
+			return;
+		}
+
+		tsr->type = state->regs[src->reg1].type;
+		tsr->kind = state->regs[src->reg1].kind;
+		tsr->ok = true;
+
+		pr_debug_dtp("mov [%x] reg%d -> reg%d",
+			     insn_offset, src->reg1, dst->reg1);
+		pr_debug_type_name(&tsr->type, tsr->kind);
+	}
+	/* Case 2. memory to register transers */
+	if (src->mem_ref && !dst->mem_ref) {
+		int sreg = src->reg1;
+
+		if (!has_reg_type(state, dst->reg1))
+			return;
+
+		tsr = &state->regs[dst->reg1];
+
+retry:
+		/* Check stack variables with offset */
+		if (sreg == fbreg) {
+			struct type_state_stack *stack;
+			int offset = src->offset - fboff;
+
+			stack = find_stack_state(state, offset);
+			if (stack == NULL) {
+				tsr->ok = false;
+				return;
+			} else if (!stack->compound) {
+				tsr->type = stack->type;
+				tsr->kind = stack->kind;
+				tsr->ok = true;
+			} else if (die_get_member_type(&stack->type,
+						       offset - stack->offset,
+						       &type_die)) {
+				tsr->type = type_die;
+				tsr->kind = TSR_KIND_TYPE;
+				tsr->ok = true;
+			} else {
+				tsr->ok = false;
+				return;
+			}
+
+			pr_debug_dtp("mov [%x] -%#x(stack) -> reg%d",
+				     insn_offset, -offset, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* And then dereference the pointer if it has one */
+		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
+			 state->regs[sreg].kind == TSR_KIND_TYPE &&
+			 die_deref_ptr_type(&state->regs[sreg].type,
+					    src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] %#x(reg%d) -> reg%d",
+				     insn_offset, src->offset, sreg, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* Or check if it's a global variable */
+		else if (sreg == DWARF_REG_PC) {
+			struct map_symbol *ms = dloc->ms;
+			u64 ip = ms->sym->start + dl->al.offset;
+			u64 addr;
+			int offset;
+
+			addr = annotate_calc_pcrel(ms, ip, src->offset, dl);
+
+			if (!get_global_var_type(cu_die, dloc, ip, addr, &offset,
+						 &type_die) ||
+			    !die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->ok = false;
+				return;
+			}
+
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] global addr=%"PRIx64" -> reg%d",
+				     insn_offset, addr, dst->reg1);
+			pr_debug_type_name(&type_die, tsr->kind);
+		}
+		/* And check percpu access with base register */
+		else if (has_reg_type(state, sreg) &&
+			 state->regs[sreg].kind == TSR_KIND_PERCPU_BASE) {
+			u64 ip = dloc->ms->sym->start + dl->al.offset;
+			u64 var_addr = src->offset;
+			int offset;
+
+			if (src->multi_regs) {
+				int reg2 = (sreg == src->reg1) ? src->reg2 : src->reg1;
+
+				if (has_reg_type(state, reg2) && state->regs[reg2].ok &&
+				    state->regs[reg2].kind == TSR_KIND_CONST)
+					var_addr += state->regs[reg2].imm_value;
+			}
+
+			/*
+			 * In kernel, %gs points to a per-cpu region for the
+			 * current CPU.  Access with a constant offset should
+			 * be treated as a global variable access.
+			 */
+			if (get_global_var_type(cu_die, dloc, ip, var_addr,
+						&offset, &type_die) &&
+			    die_get_member_type(&type_die, offset, &type_die)) {
+				tsr->type = type_die;
+				tsr->kind = TSR_KIND_TYPE;
+				tsr->ok = true;
+
+				if (src->multi_regs) {
+					pr_debug_dtp("mov [%x] percpu %#x(reg%d,reg%d) -> reg%d",
+						     insn_offset, src->offset, src->reg1,
+						     src->reg2, dst->reg1);
+				} else {
+					pr_debug_dtp("mov [%x] percpu %#x(reg%d) -> reg%d",
+						     insn_offset, src->offset, sreg, dst->reg1);
+				}
+				pr_debug_type_name(&tsr->type, tsr->kind);
+			} else {
+				tsr->ok = false;
+			}
+		}
+		/* And then dereference the calculated pointer if it has one */
+		else if (has_reg_type(state, sreg) && state->regs[sreg].ok &&
+			 state->regs[sreg].kind == TSR_KIND_POINTER &&
+			 die_get_member_type(&state->regs[sreg].type,
+					     src->offset, &type_die)) {
+			tsr->type = type_die;
+			tsr->kind = TSR_KIND_TYPE;
+			tsr->ok = true;
+
+			pr_debug_dtp("mov [%x] pointer %#x(reg%d) -> reg%d",
+				     insn_offset, src->offset, sreg, dst->reg1);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/* Or try another register if any */
+		else if (src->multi_regs && sreg == src->reg1 &&
+			 src->reg1 != src->reg2) {
+			sreg = src->reg2;
+			goto retry;
+		}
+		else {
+			int offset;
+			const char *var_name = NULL;
+
+			/* it might be per-cpu variable (in kernel) access */
+			if (src->offset < 0) {
+				if (get_global_var_info(dloc, (s64)src->offset,
+							&var_name, &offset) &&
+				    !strcmp(var_name, "__per_cpu_offset")) {
+					tsr->kind = TSR_KIND_PERCPU_BASE;
+
+					pr_debug_dtp("mov [%x] percpu base reg%d\n",
+						     insn_offset, dst->reg1);
+				}
+			}
+
+			tsr->ok = false;
+		}
+	}
+	/* Case 3. register to memory transfers */
+	if (!src->mem_ref && dst->mem_ref) {
+		if (!has_reg_type(state, src->reg1) ||
+		    !state->regs[src->reg1].ok)
+			return;
+
+		/* Check stack variables with offset */
+		if (dst->reg1 == fbreg) {
+			struct type_state_stack *stack;
+			int offset = dst->offset - fboff;
+
+			tsr = &state->regs[src->reg1];
+
+			stack = find_stack_state(state, offset);
+			if (stack) {
+				/*
+				 * The source register is likely to hold a type
+				 * of member if it's a compound type.  Do not
+				 * update the stack variable type since we can
+				 * get the member type later by using the
+				 * die_get_member_type().
+				 */
+				if (!stack->compound)
+					set_stack_state(stack, offset, tsr->kind,
+							&tsr->type);
+			} else {
+				findnew_stack_state(state, offset, tsr->kind,
+						    &tsr->type);
+			}
+
+			pr_debug_dtp("mov [%x] reg%d -> -%#x(stack)",
+				     insn_offset, src->reg1, -offset);
+			pr_debug_type_name(&tsr->type, tsr->kind);
+		}
+		/*
+		 * Ignore other transfers since it'd set a value in a struct
+		 * and won't change the type.
+		 */
+	}
+	/* Case 4. memory to memory transfers (not handled for now) */
+}
+#endif
diff --git a/tools/perf/arch/x86/util/event.c b/tools/perf/arch/x86/util/event.c
index e65b7dbe27fb..a0400707180c 100644
--- a/tools/perf/arch/x86/util/event.c
+++ b/tools/perf/arch/x86/util/event.c
@@ -15,7 +15,7 @@
 #if defined(__x86_64__)
 
 struct perf_event__synthesize_extra_kmaps_cb_args {
-	struct perf_tool *tool;
+	const struct perf_tool *tool;
 	perf_event__handler_t process;
 	struct machine *machine;
 	union perf_event *event;
@@ -65,7 +65,7 @@ static int perf_event__synthesize_extra_kmaps_cb(struct map *map, void *data)
 	return 0;
 }
 
-int perf_event__synthesize_extra_kmaps(struct perf_tool *tool,
+int perf_event__synthesize_extra_kmaps(const struct perf_tool *tool,
 				       perf_event__handler_t process,
 				       struct machine *machine)
 {
diff --git a/tools/perf/arch/x86/util/evlist.c b/tools/perf/arch/x86/util/evlist.c
index b1ce0c52d88d..cebdd483149e 100644
--- a/tools/perf/arch/x86/util/evlist.c
+++ b/tools/perf/arch/x86/util/evlist.c
@@ -89,6 +89,12 @@ int arch_evlist__cmp(const struct evsel *lhs, const struct evsel *rhs)
 			return 1;
 	}
 
+	/* Retire latency event should not be group leader*/
+	if (lhs->retire_lat && !rhs->retire_lat)
+		return 1;
+	if (!lhs->retire_lat && rhs->retire_lat)
+		return -1;
+
 	/* Default ordering by insertion index. */
 	return lhs->core.idx - rhs->core.idx;
 }