1 files changed, 644 insertions, 208 deletions

diff --git a/tools/perf/util/disasm.c b/tools/perf/util/disasm.c
index e10558b79504..f05ba7739c1e 100644
--- a/tools/perf/util/disasm.c
+++ b/tools/perf/util/disasm.c
@@ -12,9 +12,11 @@
 #include <subcmd/run-command.h>
 
 #include "annotate.h"
+#include "annotate-data.h"
 #include "build-id.h"
 #include "debug.h"
 #include "disasm.h"
+#include "disasm_bpf.h"
 #include "dso.h"
 #include "env.h"
 #include "evsel.h"
@@ -35,6 +37,8 @@ static struct ins_ops mov_ops;
 static struct ins_ops nop_ops;
 static struct ins_ops lock_ops;
 static struct ins_ops ret_ops;
+static struct ins_ops load_store_ops;
+static struct ins_ops arithmetic_ops;
 
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops, int max_ins_name);
@@ -43,6 +47,8 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 
 static void ins__sort(struct arch *arch);
 static int disasm_line__parse(char *line, const char **namep, char **rawp);
+static int disasm_line__parse_powerpc(struct disasm_line *dl);
+static char *expand_tabs(char *line, char **storage, size_t *storage_len);
 
 static __attribute__((constructor)) void symbol__init_regexpr(void)
 {
@@ -145,10 +151,16 @@ static struct arch architectures[] = {
 			.memory_ref_char = '(',
 			.imm_char = '$',
 		},
+#ifdef HAVE_DWARF_SUPPORT
+		.update_insn_state = update_insn_state_x86,
+#endif
 	},
 	{
 		.name = "powerpc",
 		.init = powerpc__annotate_init,
+#ifdef HAVE_DWARF_SUPPORT
+		.update_insn_state = update_insn_state_powerpc,
+#endif
 	},
 	{
 		.name = "riscv64",
@@ -250,7 +262,8 @@ bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
 	return arch->ins_is_fused(arch, ins1, ins2);
 }
 
-static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+static int call__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms,
+		struct disasm_line *dl __maybe_unused)
 {
 	char *endptr, *tok, *name;
 	struct map *map = ms->map;
@@ -345,7 +358,8 @@ static inline const char *validate_comma(const char *c, struct ins_operands *ops
 	return c;
 }
 
-static int jump__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+static int 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;
@@ -504,7 +518,8 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
 	return 0;
 }
 
-static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms)
+static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms,
+		struct disasm_line *dl __maybe_unused)
 {
 	ops->locked.ops = zalloc(sizeof(*ops->locked.ops));
 	if (ops->locked.ops == NULL)
@@ -513,13 +528,13 @@ static int lock__parse(struct arch *arch, struct ins_operands *ops, struct map_s
 	if (disasm_line__parse(ops->raw, &ops->locked.ins.name, &ops->locked.ops->raw) < 0)
 		goto out_free_ops;
 
-	ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name);
+	ops->locked.ins.ops = ins__find(arch, ops->locked.ins.name, 0);
 
 	if (ops->locked.ins.ops == NULL)
 		goto out_free_ops;
 
 	if (ops->locked.ins.ops->parse &&
-	    ops->locked.ins.ops->parse(arch, ops->locked.ops, ms) < 0)
+	    ops->locked.ins.ops->parse(arch, ops->locked.ops, ms, NULL) < 0)
 		goto out_free_ops;
 
 	return 0;
@@ -552,6 +567,7 @@ static void lock__delete(struct ins_operands *ops)
 		ins_ops__delete(ops->locked.ops);
 
 	zfree(&ops->locked.ops);
+	zfree(&ops->locked.ins.name);
 	zfree(&ops->target.raw);
 	zfree(&ops->target.name);
 }
@@ -590,7 +606,8 @@ static bool check_multi_regs(struct arch *arch, const char *op)
 	return count > 1;
 }
 
-static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+static int mov__parse(struct arch *arch, struct ins_operands *ops, struct map_symbol *ms __maybe_unused,
+		struct disasm_line *dl __maybe_unused)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
 
@@ -668,7 +685,92 @@ static struct ins_ops mov_ops = {
 	.scnprintf = mov__scnprintf,
 };
 
-static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused)
+#define PPC_22_30(R)    (((R) >> 1) & 0x1ff)
+#define MINUS_EXT_XO_FORM	234
+#define SUB_EXT_XO_FORM		232
+#define	ADD_ZERO_EXT_XO_FORM	202
+#define	SUB_ZERO_EXT_XO_FORM	200
+
+static int arithmetic__scnprintf(struct ins *ins, char *bf, size_t size,
+		struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
+			ops->raw);
+}
+
+/*
+ * Sets the fields: multi_regs and "mem_ref".
+ * "mem_ref" is set for ops->source which is later used to
+ * fill the objdump->memory_ref-char field. This ops is currently
+ * used by powerpc and since binary instruction code is used to
+ * extract opcode, regs and offset, no other parsing is needed here.
+ *
+ * Dont set multi regs for 4 cases since it has only one operand
+ * for source:
+ * - Add to Minus One Extended XO-form ( Ex: addme, addmeo )
+ * - Subtract From Minus One Extended XO-form ( Ex: subfme )
+ * - Add to Zero Extended XO-form ( Ex: addze, addzeo )
+ * - Subtract From Zero Extended XO-form ( Ex: subfze )
+ */
+static int arithmetic__parse(struct arch *arch __maybe_unused, struct ins_operands *ops,
+		struct map_symbol *ms __maybe_unused, struct disasm_line *dl)
+{
+	int opcode = PPC_OP(dl->raw.raw_insn);
+
+	ops->source.mem_ref = false;
+	if (opcode == 31) {
+		if ((opcode != MINUS_EXT_XO_FORM) && (opcode != SUB_EXT_XO_FORM) \
+				&& (opcode != ADD_ZERO_EXT_XO_FORM) && (opcode != SUB_ZERO_EXT_XO_FORM))
+			ops->source.multi_regs = true;
+	}
+
+	ops->target.mem_ref = false;
+	ops->target.multi_regs = false;
+
+	return 0;
+}
+
+static struct ins_ops arithmetic_ops = {
+	.parse     = arithmetic__parse,
+	.scnprintf = arithmetic__scnprintf,
+};
+
+static int load_store__scnprintf(struct ins *ins, char *bf, size_t size,
+		struct ins_operands *ops, int max_ins_name)
+{
+	return scnprintf(bf, size, "%-*s %s", max_ins_name, ins->name,
+			ops->raw);
+}
+
+/*
+ * Sets the fields: multi_regs and "mem_ref".
+ * "mem_ref" is set for ops->source which is later used to
+ * fill the objdump->memory_ref-char field. This ops is currently
+ * used by powerpc and since binary instruction code is used to
+ * extract opcode, regs and offset, no other parsing is needed here
+ */
+static int load_store__parse(struct arch *arch __maybe_unused, struct ins_operands *ops,
+		struct map_symbol *ms __maybe_unused, struct disasm_line *dl __maybe_unused)
+{
+	ops->source.mem_ref = true;
+	ops->source.multi_regs = false;
+	/* opcode 31 is of X form */
+	if (PPC_OP(dl->raw.raw_insn) == 31)
+		ops->source.multi_regs = true;
+
+	ops->target.mem_ref = false;
+	ops->target.multi_regs = false;
+
+	return 0;
+}
+
+static struct ins_ops load_store_ops = {
+	.parse     = load_store__parse,
+	.scnprintf = load_store__scnprintf,
+};
+
+static int dec__parse(struct arch *arch __maybe_unused, struct ins_operands *ops, struct map_symbol *ms __maybe_unused,
+		struct disasm_line *dl __maybe_unused)
 {
 	char *target, *comment, *s, prev;
 
@@ -758,11 +860,23 @@ static void ins__sort(struct arch *arch)
 	qsort(arch->instructions, nmemb, sizeof(struct ins), ins__cmp);
 }
 
-static struct ins_ops *__ins__find(struct arch *arch, const char *name)
+static struct ins_ops *__ins__find(struct arch *arch, const char *name, struct disasm_line *dl)
 {
 	struct ins *ins;
 	const int nmemb = arch->nr_instructions;
 
+	if (arch__is(arch, "powerpc")) {
+		/*
+		 * For powerpc, identify the instruction ops
+		 * from the opcode using raw_insn.
+		 */
+		struct ins_ops *ops;
+
+		ops = check_ppc_insn(dl);
+		if (ops)
+			return ops;
+	}
+
 	if (!arch->sorted_instructions) {
 		ins__sort(arch);
 		arch->sorted_instructions = true;
@@ -792,9 +906,9 @@ static struct ins_ops *__ins__find(struct arch *arch, const char *name)
 	return ins ? ins->ops : NULL;
 }
 
-struct ins_ops *ins__find(struct arch *arch, const char *name)
+struct ins_ops *ins__find(struct arch *arch, const char *name, struct disasm_line *dl)
 {
-	struct ins_ops *ops = __ins__find(arch, name);
+	struct ins_ops *ops = __ins__find(arch, name, dl);
 
 	if (!ops && arch->associate_instruction_ops)
 		ops = arch->associate_instruction_ops(arch, name);
@@ -804,12 +918,12 @@ struct ins_ops *ins__find(struct arch *arch, const char *name)
 
 static void disasm_line__init_ins(struct disasm_line *dl, struct arch *arch, struct map_symbol *ms)
 {
-	dl->ins.ops = ins__find(arch, dl->ins.name);
+	dl->ins.ops = ins__find(arch, dl->ins.name, dl);
 
 	if (!dl->ins.ops)
 		return;
 
-	if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms) < 0)
+	if (dl->ins.ops->parse && dl->ins.ops->parse(arch, &dl->ops, ms, dl) < 0)
 		dl->ins.ops = NULL;
 }
 
@@ -841,6 +955,51 @@ out:
 	return -1;
 }
 
+/*
+ * Parses the result captured from symbol__disassemble_*
+ * Example, line read from DSO file in powerpc:
+ * line:    38 01 81 e8
+ * opcode: fetched from arch specific get_opcode_insn
+ * rawp_insn: e8810138
+ *
+ * rawp_insn is used later to extract the reg/offset fields
+ */
+#define	PPC_OP(op)	(((op) >> 26) & 0x3F)
+#define	RAW_BYTES	11
+
+static int disasm_line__parse_powerpc(struct disasm_line *dl)
+{
+	char *line = dl->al.line;
+	const char **namep = &dl->ins.name;
+	char **rawp = &dl->ops.raw;
+	char *tmp_raw_insn, *name_raw_insn = skip_spaces(line);
+	char *name = skip_spaces(name_raw_insn + RAW_BYTES);
+	int objdump = 0;
+
+	if (strlen(line) > RAW_BYTES)
+		objdump = 1;
+
+	if (name_raw_insn[0] == '\0')
+		return -1;
+
+	if (objdump) {
+		disasm_line__parse(name, namep, rawp);
+	} else
+		*namep = "";
+
+	tmp_raw_insn = strndup(name_raw_insn, 11);
+	if (tmp_raw_insn == NULL)
+		return -1;
+
+	remove_spaces(tmp_raw_insn);
+
+	sscanf(tmp_raw_insn, "%x", &dl->raw.raw_insn);
+	if (objdump)
+		dl->raw.raw_insn = be32_to_cpu(dl->raw.raw_insn);
+
+	return 0;
+}
+
 static void annotation_line__init(struct annotation_line *al,
 				  struct annotate_args *args,
 				  int nr)
@@ -857,6 +1016,7 @@ static void annotation_line__exit(struct annotation_line *al)
 	zfree_srcline(&al->path);
 	zfree(&al->line);
 	zfree(&al->cycles);
+	zfree(&al->br_cntr);
 }
 
 static size_t disasm_line_size(int nr)
@@ -880,10 +1040,8 @@ static size_t disasm_line_size(int nr)
 struct disasm_line *disasm_line__new(struct annotate_args *args)
 {
 	struct disasm_line *dl = NULL;
-	int nr = 1;
-
-	if (evsel__is_group_event(args->evsel))
-		nr = args->evsel->core.nr_members;
+	struct annotation *notes = symbol__annotation(args->ms.sym);
+	int nr = notes->src->nr_events;
 
 	dl = zalloc(disasm_line_size(nr));
 	if (!dl)
@@ -894,7 +1052,10 @@ struct disasm_line *disasm_line__new(struct annotate_args *args)
 		goto out_delete;
 
 	if (args->offset != -1) {
-		if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
+		if (arch__is(args->arch, "powerpc")) {
+			if (disasm_line__parse_powerpc(dl) < 0)
+				goto out_free_line;
+		} else if (disasm_line__parse(dl->al.line, &dl->ins.name, &dl->ops.raw) < 0)
 			goto out_free_line;
 
 		disasm_line__init_ins(dl, args->arch, &args->ms);
@@ -1164,195 +1325,11 @@ fallback:
 	return 0;
 }
 
-#if defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-#define PACKAGE "perf"
-#include <bfd.h>
-#include <dis-asm.h>
-#include <bpf/bpf.h>
-#include <bpf/btf.h>
-#include <bpf/libbpf.h>
-#include <linux/btf.h>
-#include <tools/dis-asm-compat.h>
-
-#include "bpf-event.h"
-#include "bpf-utils.h"
-
-static int symbol__disassemble_bpf(struct symbol *sym,
-				   struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct bpf_prog_linfo *prog_linfo = NULL;
-	struct bpf_prog_info_node *info_node;
-	int len = sym->end - sym->start;
-	disassembler_ftype disassemble;
-	struct map *map = args->ms.map;
-	struct perf_bpil *info_linear;
-	struct disassemble_info info;
-	struct dso *dso = map__dso(map);
-	int pc = 0, count, sub_id;
-	struct btf *btf = NULL;
-	char tpath[PATH_MAX];
-	size_t buf_size;
-	int nr_skip = 0;
-	char *buf;
-	bfd *bfdf;
-	int ret;
-	FILE *s;
-
-	if (dso__binary_type(dso) != DSO_BINARY_TYPE__BPF_PROG_INFO)
-		return SYMBOL_ANNOTATE_ERRNO__BPF_INVALID_FILE;
-
-	pr_debug("%s: handling sym %s addr %" PRIx64 " len %" PRIx64 "\n", __func__,
-		  sym->name, sym->start, sym->end - sym->start);
-
-	memset(tpath, 0, sizeof(tpath));
-	perf_exe(tpath, sizeof(tpath));
-
-	bfdf = bfd_openr(tpath, NULL);
-	if (bfdf == NULL)
-		abort();
-
-	if (!bfd_check_format(bfdf, bfd_object))
-		abort();
-
-	s = open_memstream(&buf, &buf_size);
-	if (!s) {
-		ret = errno;
-		goto out;
-	}
-	init_disassemble_info_compat(&info, s,
-				     (fprintf_ftype) fprintf,
-				     fprintf_styled);
-	info.arch = bfd_get_arch(bfdf);
-	info.mach = bfd_get_mach(bfdf);
-
-	info_node = perf_env__find_bpf_prog_info(dso__bpf_prog(dso)->env,
-						 dso__bpf_prog(dso)->id);
-	if (!info_node) {
-		ret = SYMBOL_ANNOTATE_ERRNO__BPF_MISSING_BTF;
-		goto out;
-	}
-	info_linear = info_node->info_linear;
-	sub_id = dso__bpf_prog(dso)->sub_id;
-
-	info.buffer = (void *)(uintptr_t)(info_linear->info.jited_prog_insns);
-	info.buffer_length = info_linear->info.jited_prog_len;
-
-	if (info_linear->info.nr_line_info)
-		prog_linfo = bpf_prog_linfo__new(&info_linear->info);
-
-	if (info_linear->info.btf_id) {
-		struct btf_node *node;
-
-		node = perf_env__find_btf(dso__bpf_prog(dso)->env,
-					  info_linear->info.btf_id);
-		if (node)
-			btf = btf__new((__u8 *)(node->data),
-				       node->data_size);
-	}
-
-	disassemble_init_for_target(&info);
-
-#ifdef DISASM_FOUR_ARGS_SIGNATURE
-	disassemble = disassembler(info.arch,
-				   bfd_big_endian(bfdf),
-				   info.mach,
-				   bfdf);
-#else
-	disassemble = disassembler(bfdf);
-#endif
-	if (disassemble == NULL)
-		abort();
-
-	fflush(s);
-	do {
-		const struct bpf_line_info *linfo = NULL;
-		struct disasm_line *dl;
-		size_t prev_buf_size;
-		const char *srcline;
-		u64 addr;
-
-		addr = pc + ((u64 *)(uintptr_t)(info_linear->info.jited_ksyms))[sub_id];
-		count = disassemble(pc, &info);
-
-		if (prog_linfo)
-			linfo = bpf_prog_linfo__lfind_addr_func(prog_linfo,
-								addr, sub_id,
-								nr_skip);
-
-		if (linfo && btf) {
-			srcline = btf__name_by_offset(btf, linfo->line_off);
-			nr_skip++;
-		} else
-			srcline = NULL;
-
-		fprintf(s, "\n");
-		prev_buf_size = buf_size;
-		fflush(s);
-
-		if (!annotate_opts.hide_src_code && srcline) {
-			args->offset = -1;
-			args->line = strdup(srcline);
-			args->line_nr = 0;
-			args->fileloc = NULL;
-			args->ms.sym  = sym;
-			dl = disasm_line__new(args);
-			if (dl) {
-				annotation_line__add(&dl->al,
-						     &notes->src->source);
-			}
-		}
-
-		args->offset = pc;
-		args->line = buf + prev_buf_size;
-		args->line_nr = 0;
-		args->fileloc = NULL;
-		args->ms.sym  = sym;
-		dl = disasm_line__new(args);
-		if (dl)
-			annotation_line__add(&dl->al, &notes->src->source);
-
-		pc += count;
-	} while (count > 0 && pc < len);
-
-	ret = 0;
-out:
-	free(prog_linfo);
-	btf__free(btf);
-	fclose(s);
-	bfd_close(bfdf);
-	return ret;
-}
-#else // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-static int symbol__disassemble_bpf(struct symbol *sym __maybe_unused,
-				   struct annotate_args *args __maybe_unused)
-{
-	return SYMBOL_ANNOTATE_ERRNO__NO_LIBOPCODES_FOR_BPF;
-}
-#endif // defined(HAVE_LIBBFD_SUPPORT) && defined(HAVE_LIBBPF_SUPPORT)
-
-static int
-symbol__disassemble_bpf_image(struct symbol *sym,
-			      struct annotate_args *args)
-{
-	struct annotation *notes = symbol__annotation(sym);
-	struct disasm_line *dl;
-
-	args->offset = -1;
-	args->line = strdup("to be implemented");
-	args->line_nr = 0;
-	args->fileloc = NULL;
-	dl = disasm_line__new(args);
-	if (dl)
-		annotation_line__add(&dl->al, &notes->src->source);
-
-	zfree(&args->line);
-	return 0;
-}
-
 #ifdef HAVE_LIBCAPSTONE_SUPPORT
 #include <capstone/capstone.h>
 
+int capstone_init(struct machine *machine, csh *cs_handle, bool is64, bool disassembler_style);
+
 static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
 				csh *handle)
 {
@@ -1378,7 +1355,9 @@ static int open_capstone_handle(struct annotate_args *args, bool is_64bit,
 
 	return 0;
 }
+#endif
 
+#if defined(HAVE_LIBCAPSTONE_SUPPORT) || defined(HAVE_LIBLLVM_SUPPORT)
 struct find_file_offset_data {
 	u64 ip;
 	u64 offset;
@@ -1396,6 +1375,55 @@ static int find_file_offset(u64 start, u64 len, u64 pgoff, void *arg)
 	return 0;
 }
 
+static u8 *
+read_symbol(const char *filename, struct map *map, struct symbol *sym,
+	    u64 *len, bool *is_64bit)
+{
+	struct dso *dso = map__dso(map);
+	struct nscookie nsc;
+	u64 start = map__rip_2objdump(map, sym->start);
+	u64 end = map__rip_2objdump(map, sym->end);
+	int fd, count;
+	u8 *buf = NULL;
+	struct find_file_offset_data data = {
+		.ip = start,
+	};
+
+	*is_64bit = false;
+
+	nsinfo__mountns_enter(dso__nsinfo(dso), &nsc);
+	fd = open(filename, O_RDONLY);
+	nsinfo__mountns_exit(&nsc);
+	if (fd < 0)
+		return NULL;
+
+	if (file__read_maps(fd, /*exe=*/true, find_file_offset, &data,
+			    is_64bit) == 0)
+		goto err;
+
+	*len = end - start;
+	buf = malloc(*len);
+	if (buf == NULL)
+		goto err;
+
+	count = pread(fd, buf, *len, data.offset);
+	close(fd);
+	fd = -1;
+
+	if ((u64)count != *len)
+		goto err;
+
+	return buf;
+
+err:
+	if (fd >= 0)
+		close(fd);
+	free(buf);
+	return NULL;
+}
+#endif
+
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
 static void print_capstone_detail(cs_insn *insn, char *buf, size_t len,
 				  struct annotate_args *args, u64 addr)
 {
@@ -1453,7 +1481,7 @@ static void print_capstone_detail(cs_insn *insn, char *buf, size_t len,
 	}
 }
 
-static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
+static int symbol__disassemble_capstone_powerpc(char *filename, struct symbol *sym,
 					struct annotate_args *args)
 {
 	struct annotation *notes = symbol__annotation(sym);
@@ -1472,9 +1500,10 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 		.ip = start,
 	};
 	csh handle;
-	cs_insn *insn;
 	char disasm_buf[512];
 	struct disasm_line *dl;
+	u32 *line;
+	bool disassembler_style = false;
 
 	if (args->options->objdump_path)
 		return -1;
@@ -1489,7 +1518,11 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 			    &is_64bit) == 0)
 		goto err;
 
-	if (open_capstone_handle(args, is_64bit, &handle) < 0)
+	if (!args->options->disassembler_style ||
+			!strcmp(args->options->disassembler_style, "att"))
+		disassembler_style = true;
+
+	if (capstone_init(maps__machine(args->ms.maps), &handle, is_64bit, disassembler_style) < 0)
 		goto err;
 
 	needs_cs_close = true;
@@ -1505,6 +1538,8 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 	if ((u64)count != len)
 		goto err;
 
+	line = (u32 *)buf;
+
 	/* add the function address and name */
 	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
 		  start, sym->name);
@@ -1521,6 +1556,114 @@ static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
 
 	annotation_line__add(&dl->al, &notes->src->source);
 
+	/*
+	 * TODO: enable disassm for powerpc
+	 * count = cs_disasm(handle, buf, len, start, len, &insn);
+	 *
+	 * For now, only binary code is saved in disassembled line
+	 * to be used in "type" and "typeoff" sort keys. Each raw code
+	 * is 32 bit instruction. So use "len/4" to get the number of
+	 * entries.
+	 */
+	count = len/4;
+
+	for (i = 0, offset = 0; i < count; i++) {
+		args->offset = offset;
+		sprintf(args->line, "%x", line[i]);
+
+		dl = disasm_line__new(args);
+		if (dl == NULL)
+			goto err;
+
+		annotation_line__add(&dl->al, &notes->src->source);
+
+		offset += 4;
+	}
+
+	/* It failed in the middle */
+	if (offset != len) {
+		struct list_head *list = &notes->src->source;
+
+		/* Discard all lines and fallback to objdump */
+		while (!list_empty(list)) {
+			dl = list_first_entry(list, struct disasm_line, al.node);
+
+			list_del_init(&dl->al.node);
+			disasm_line__free(dl);
+		}
+		count = -1;
+	}
+
+out:
+	if (needs_cs_close)
+		cs_close(&handle);
+	free(buf);
+	return count < 0 ? count : 0;
+
+err:
+	if (fd >= 0)
+		close(fd);
+	if (needs_cs_close) {
+		struct disasm_line *tmp;
+
+		/*
+		 * It probably failed in the middle of the above loop.
+		 * Release any resources it might add.
+		 */
+		list_for_each_entry_safe(dl, tmp, &notes->src->source, al.node) {
+			list_del(&dl->al.node);
+			free(dl);
+		}
+	}
+	count = -1;
+	goto out;
+}
+
+static int symbol__disassemble_capstone(char *filename, struct symbol *sym,
+					struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct map *map = args->ms.map;
+	u64 start = map__rip_2objdump(map, sym->start);
+	u64 len;
+	u64 offset;
+	int i, count;
+	bool is_64bit = false;
+	bool needs_cs_close = false;
+	u8 *buf = NULL;
+	csh handle;
+	cs_insn *insn;
+	char disasm_buf[512];
+	struct disasm_line *dl;
+
+	if (args->options->objdump_path)
+		return -1;
+
+	buf = read_symbol(filename, map, sym, &len, &is_64bit);
+	if (buf == NULL)
+		return -1;
+
+	/* add the function address and name */
+	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
+		  start, sym->name);
+
+	args->offset = -1;
+	args->line = disasm_buf;
+	args->line_nr = 0;
+	args->fileloc = NULL;
+	args->ms.sym = sym;
+
+	dl = disasm_line__new(args);
+	if (dl == NULL)
+		goto err;
+
+	annotation_line__add(&dl->al, &notes->src->source);
+
+	if (open_capstone_handle(args, is_64bit, &handle) < 0)
+		goto err;
+
+	needs_cs_close = true;
+
 	count = cs_disasm(handle, buf, len, start, len, &insn);
 	for (i = 0, offset = 0; i < count; i++) {
 		int printed;
@@ -1565,8 +1708,6 @@ out:
 	return count < 0 ? count : 0;
 
 err:
-	if (fd >= 0)
-		close(fd);
 	if (needs_cs_close) {
 		struct disasm_line *tmp;
 
@@ -1584,6 +1725,274 @@ err:
 }
 #endif
 
+static int symbol__disassemble_raw(char *filename, struct symbol *sym,
+					struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
+	u64 start = map__rip_2objdump(map, sym->start);
+	u64 end = map__rip_2objdump(map, sym->end);
+	u64 len = end - start;
+	u64 offset;
+	int i, count;
+	u8 *buf = NULL;
+	char disasm_buf[512];
+	struct disasm_line *dl;
+	u32 *line;
+
+	/* Return if objdump is specified explicitly */
+	if (args->options->objdump_path)
+		return -1;
+
+	pr_debug("Reading raw instruction from : %s using dso__data_read_offset\n", filename);
+
+	buf = malloc(len);
+	if (buf == NULL)
+		goto err;
+
+	count = dso__data_read_offset(dso, NULL, sym->start, buf, len);
+
+	line = (u32 *)buf;
+
+	if ((u64)count != len)
+		goto err;
+
+	/* add the function address and name */
+	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
+		  start, sym->name);
+
+	args->offset = -1;
+	args->line = disasm_buf;
+	args->line_nr = 0;
+	args->fileloc = NULL;
+	args->ms.sym = sym;
+
+	dl = disasm_line__new(args);
+	if (dl == NULL)
+		goto err;
+
+	annotation_line__add(&dl->al, &notes->src->source);
+
+	/* Each raw instruction is 4 byte */
+	count = len/4;
+
+	for (i = 0, offset = 0; i < count; i++) {
+		args->offset = offset;
+		sprintf(args->line, "%x", line[i]);
+		dl = disasm_line__new(args);
+		if (dl == NULL)
+			goto err;
+
+		annotation_line__add(&dl->al, &notes->src->source);
+		offset += 4;
+	}
+
+	/* It failed in the middle */
+	if (offset != len) {
+		struct list_head *list = &notes->src->source;
+
+		/* Discard all lines and fallback to objdump */
+		while (!list_empty(list)) {
+			dl = list_first_entry(list, struct disasm_line, al.node);
+
+			list_del_init(&dl->al.node);
+			disasm_line__free(dl);
+		}
+		count = -1;
+	}
+
+out:
+	free(buf);
+	return count < 0 ? count : 0;
+
+err:
+	count = -1;
+	goto out;
+}
+
+#ifdef HAVE_LIBLLVM_SUPPORT
+#include <llvm-c/Disassembler.h>
+#include <llvm-c/Target.h>
+#include "util/llvm-c-helpers.h"
+
+struct symbol_lookup_storage {
+	u64 branch_addr;
+	u64 pcrel_load_addr;
+};
+
+/*
+ * Whenever LLVM wants to resolve an address into a symbol, it calls this
+ * callback. We don't ever actually _return_ anything (in particular, because
+ * it puts quotation marks around what we return), but we use this as a hint
+ * that there is a branch or PC-relative address in the expression that we
+ * should add some textual annotation for after the instruction. The caller
+ * will use this information to add the actual annotation.
+ */
+static const char *
+symbol_lookup_callback(void *disinfo, uint64_t value,
+		       uint64_t *ref_type,
+		       uint64_t address __maybe_unused,
+		       const char **ref __maybe_unused)
+{
+	struct symbol_lookup_storage *storage = disinfo;
+
+	if (*ref_type == LLVMDisassembler_ReferenceType_In_Branch)
+		storage->branch_addr = value;
+	else if (*ref_type == LLVMDisassembler_ReferenceType_In_PCrel_Load)
+		storage->pcrel_load_addr = value;
+	*ref_type = LLVMDisassembler_ReferenceType_InOut_None;
+	return NULL;
+}
+
+static int symbol__disassemble_llvm(char *filename, struct symbol *sym,
+				    struct annotate_args *args)
+{
+	struct annotation *notes = symbol__annotation(sym);
+	struct map *map = args->ms.map;
+	struct dso *dso = map__dso(map);
+	u64 start = map__rip_2objdump(map, sym->start);
+	u8 *buf;
+	u64 len;
+	u64 pc;
+	bool is_64bit;
+	char triplet[64];
+	char disasm_buf[2048];
+	size_t disasm_len;
+	struct disasm_line *dl;
+	LLVMDisasmContextRef disasm = NULL;
+	struct symbol_lookup_storage storage;
+	char *line_storage = NULL;
+	size_t line_storage_len = 0;
+	int ret = -1;
+
+	if (args->options->objdump_path)
+		return -1;
+
+	LLVMInitializeAllTargetInfos();
+	LLVMInitializeAllTargetMCs();
+	LLVMInitializeAllDisassemblers();
+
+	buf = read_symbol(filename, map, sym, &len, &is_64bit);
+	if (buf == NULL)
+		return -1;
+
+	if (arch__is(args->arch, "x86")) {
+		if (is_64bit)
+			scnprintf(triplet, sizeof(triplet), "x86_64-pc-linux");
+		else
+			scnprintf(triplet, sizeof(triplet), "i686-pc-linux");
+	} else {
+		scnprintf(triplet, sizeof(triplet), "%s-linux-gnu",
+			  args->arch->name);
+	}
+
+	disasm = LLVMCreateDisasm(triplet, &storage, 0, NULL,
+				  symbol_lookup_callback);
+	if (disasm == NULL)
+		goto err;
+
+	if (args->options->disassembler_style &&
+	    !strcmp(args->options->disassembler_style, "intel"))
+		LLVMSetDisasmOptions(disasm,
+				     LLVMDisassembler_Option_AsmPrinterVariant);
+
+	/*
+	 * This needs to be set after AsmPrinterVariant, due to a bug in LLVM;
+	 * setting AsmPrinterVariant makes a new instruction printer, making it
+	 * forget about the PrintImmHex flag (which is applied before if both
+	 * are given to the same call).
+	 */
+	LLVMSetDisasmOptions(disasm, LLVMDisassembler_Option_PrintImmHex);
+
+	/* add the function address and name */
+	scnprintf(disasm_buf, sizeof(disasm_buf), "%#"PRIx64" <%s>:",
+		  start, sym->name);
+
+	args->offset = -1;
+	args->line = disasm_buf;
+	args->line_nr = 0;
+	args->fileloc = NULL;
+	args->ms.sym = sym;
+
+	dl = disasm_line__new(args);
+	if (dl == NULL)
+		goto err;
+
+	annotation_line__add(&dl->al, &notes->src->source);
+
+	pc = start;
+	for (u64 offset = 0; offset < len; ) {
+		unsigned int ins_len;
+
+		storage.branch_addr = 0;
+		storage.pcrel_load_addr = 0;
+
+		ins_len = LLVMDisasmInstruction(disasm, buf + offset,
+						len - offset, pc,
+						disasm_buf, sizeof(disasm_buf));
+		if (ins_len == 0)
+			goto err;
+		disasm_len = strlen(disasm_buf);
+
+		if (storage.branch_addr != 0) {
+			char *name = llvm_name_for_code(dso, filename,
+							storage.branch_addr);
+			if (name != NULL) {
+				disasm_len += scnprintf(disasm_buf + disasm_len,
+							sizeof(disasm_buf) -
+								disasm_len,
+							" <%s>", name);
+				free(name);
+			}
+		}
+		if (storage.pcrel_load_addr != 0) {
+			char *name = llvm_name_for_data(dso, filename,
+							storage.pcrel_load_addr);
+			disasm_len += scnprintf(disasm_buf + disasm_len,
+						sizeof(disasm_buf) - disasm_len,
+						"  # %#"PRIx64,
+						storage.pcrel_load_addr);
+			if (name) {
+				disasm_len += scnprintf(disasm_buf + disasm_len,
+							sizeof(disasm_buf) -
+							disasm_len,
+							" <%s>", name);
+				free(name);
+			}
+		}
+
+		args->offset = offset;
+		args->line = expand_tabs(disasm_buf, &line_storage,
+					 &line_storage_len);
+		args->line_nr = 0;
+		args->fileloc = NULL;
+		args->ms.sym = sym;
+
+		llvm_addr2line(filename, pc, &args->fileloc,
+			       (unsigned int *)&args->line_nr, false, NULL);
+
+		dl = disasm_line__new(args);
+		if (dl == NULL)
+			goto err;
+
+		annotation_line__add(&dl->al, &notes->src->source);
+
+		free(args->fileloc);
+		pc += ins_len;
+		offset += ins_len;
+	}
+
+	ret = 0;
+
+err:
+	LLVMDisasmDispose(disasm);
+	free(buf);
+	free(line_storage);
+	return ret;
+}
+#endif
+
 /*
  * Possibly create a new version of line with tabs expanded. Returns the
  * existing or new line, storage is updated if a new line is allocated. If
@@ -1708,6 +2117,33 @@ int symbol__disassemble(struct symbol *sym, struct annotate_args *args)
 		strcpy(symfs_filename, tmp);
 	}
 
+	/*
+	 * For powerpc data type profiling, use the dso__data_read_offset
+	 * to read raw instruction directly and interpret the binary code
+	 * to understand instructions and register fields. For sort keys as
+	 * type and typeoff, disassemble to mnemonic notation is
+	 * not required in case of powerpc.
+	 */
+	if (arch__is(args->arch, "powerpc")) {
+		extern const char *sort_order;
+
+		if (sort_order && !strstr(sort_order, "sym")) {
+			err = symbol__disassemble_raw(symfs_filename, sym, args);
+			if (err == 0)
+				goto out_remove_tmp;
+#ifdef HAVE_LIBCAPSTONE_SUPPORT
+			err = symbol__disassemble_capstone_powerpc(symfs_filename, sym, args);
+			if (err == 0)
+				goto out_remove_tmp;
+#endif
+		}
+	}
+
+#ifdef HAVE_LIBLLVM_SUPPORT
+	err = symbol__disassemble_llvm(symfs_filename, sym, args);
+	if (err == 0)
+		goto out_remove_tmp;
+#endif
 #ifdef HAVE_LIBCAPSTONE_SUPPORT
 	err = symbol__disassemble_capstone(symfs_filename, sym, args);
 	if (err == 0)