[PATCH v4 0/3] perf annotate: Enable cross arch annotate

[PATCH v4 0/3] perf annotate: Enable cross arch annotate

[Ravi Bangoria]

Perf can currently only support code navigation (branches and calls) in
annotate when run on the same architecture where perf.data was recorded.
But cross arch annotate is not supported.

This patchset enables cross arch annotate. Currently I've used x86
and arm instructions which are already available and adding support
for powerpc as well. Adding support for other arch will be easy.

I've created this patch on top of acme/perf/core. And tested it with
x86 and powerpc only.

Note for arm:
Few instructions were defined under #if __arm__ which I've used as a
table for arm. But I'm not sure whether instruction defined outside of
that also contains arm instructions. Apart from that, 'call__parse()'
and 'move__parse()' contains #ifdef __arm__ directive. I've changed it
to  if (!strcmp(norm_arch, arm)). I don't have a arm machine to test
these changes.

Example:

  Record on powerpc:
  $ ./perf record -a

  Report -> Annotate on x86:
  $ ./perf report -i perf.data.powerpc --vmlinux vmlinux.powerpc

Changes in v4:
  - powerpc: Added support for branch instructions that includes 'ctr'
  - __maybe_unused was misplaced at few location. Corrected it.
  - Moved position of v3 last patch that define macro for each arch name

v3 link: https://lkml.org/lkml/2016/6/30/99

Naveen N. Rao (1):
  perf annotate: add powerpc support

Ravi Bangoria (2):
  perf: Define macro for normalized arch names
  perf annotate: Enable cross arch annotate

 tools/perf/arch/common.c           |  36 ++---
 tools/perf/arch/common.h           |  11 ++
 tools/perf/builtin-top.c           |   2 +-
 tools/perf/ui/browsers/annotate.c  |   3 +-
 tools/perf/ui/gtk/annotate.c       |   2 +-
 tools/perf/util/annotate.c         | 273 ++++++++++++++++++++++++++++++-------
 tools/perf/util/annotate.h         |   6 +-
 tools/perf/util/unwind-libunwind.c |   4 +-
 8 files changed, 265 insertions(+), 72 deletions(-)

--
2.5.5

[PATCH v4 1/3] perf: Define macro for normalized arch names

[Ravi Bangoria]

Define macro for each normalized arch name and use them instead
of using arch name as string

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
---
Changes in v4:
  - Moved position of patch

 tools/perf/arch/common.c           | 36 ++++++++++++++++++------------------
 tools/perf/arch/common.h           | 11 +++++++++++
 tools/perf/util/unwind-libunwind.c |  4 ++--
 3 files changed, 31 insertions(+), 20 deletions(-)

diff --git a/tools/perf/arch/common.c b/tools/perf/arch/common.c
index ee69668..feb2113 100644
--- a/tools/perf/arch/common.c
+++ b/tools/perf/arch/common.c
@@ -122,25 +122,25 @@ static int lookup_triplets(const char *const *triplets, const char *name)
 const char *normalize_arch(char *arch)
 {
 	if (!strcmp(arch, "x86_64"))
-		return "x86";
+		return NORM_X86;
 	if (arch[0] == 'i' && arch[2] == '8' && arch[3] == '6')
-		return "x86";
+		return NORM_X86;
 	if (!strcmp(arch, "sun4u") || !strncmp(arch, "sparc", 5))
-		return "sparc";
+		return NORM_SPARC;
 	if (!strcmp(arch, "aarch64") || !strcmp(arch, "arm64"))
-		return "arm64";
+		return NORM_ARM64;
 	if (!strncmp(arch, "arm", 3) || !strcmp(arch, "sa110"))
-		return "arm";
+		return NORM_ARM;
 	if (!strncmp(arch, "s390", 4))
-		return "s390";
+		return NORM_S390;
 	if (!strncmp(arch, "parisc", 6))
-		return "parisc";
+		return NORM_PARISC;
 	if (!strncmp(arch, "powerpc", 7) || !strncmp(arch, "ppc", 3))
-		return "powerpc";
+		return NORM_POWERPC;
 	if (!strncmp(arch, "mips", 4))
-		return "mips";
+		return NORM_MIPS;
 	if (!strncmp(arch, "sh", 2) && isdigit(arch[2]))
-		return "sh";
+		return NORM_SH;
 
 	return arch;
 }
@@ -180,21 +180,21 @@ static int perf_env__lookup_binutils_path(struct perf_env *env,
 		zfree(&buf);
 	}
 
-	if (!strcmp(arch, "arm"))
+	if (!strcmp(arch, NORM_ARM))
 		path_list = arm_triplets;
-	else if (!strcmp(arch, "arm64"))
+	else if (!strcmp(arch, NORM_ARM64))
 		path_list = arm64_triplets;
-	else if (!strcmp(arch, "powerpc"))
+	else if (!strcmp(arch, NORM_POWERPC))
 		path_list = powerpc_triplets;
-	else if (!strcmp(arch, "sh"))
+	else if (!strcmp(arch, NORM_SH))
 		path_list = sh_triplets;
-	else if (!strcmp(arch, "s390"))
+	else if (!strcmp(arch, NORM_S390))
 		path_list = s390_triplets;
-	else if (!strcmp(arch, "sparc"))
+	else if (!strcmp(arch, NORM_SPARC))
 		path_list = sparc_triplets;
-	else if (!strcmp(arch, "x86"))
+	else if (!strcmp(arch, NORM_X86))
 		path_list = x86_triplets;
-	else if (!strcmp(arch, "mips"))
+	else if (!strcmp(arch, NORM_MIPS))
 		path_list = mips_triplets;
 	else {
 		ui__error("binutils for %s not supported.\n", arch);
diff --git a/tools/perf/arch/common.h b/tools/perf/arch/common.h
index 6b01c73..14ca8ca 100644
--- a/tools/perf/arch/common.h
+++ b/tools/perf/arch/common.h
@@ -5,6 +5,17 @@
 
 extern const char *objdump_path;
 
+/* Macro for normalized arch names */
+#define NORM_X86	"x86"
+#define NORM_SPARC	"sparc"
+#define NORM_ARM64	"arm64"
+#define NORM_ARM	"arm"
+#define NORM_S390	"s390"
+#define NORM_PARISC	"parisc"
+#define NORM_POWERPC	"powerpc"
+#define NORM_MIPS	"mips"
+#define NORM_SH		"sh"
+
 int perf_env__lookup_objdump(struct perf_env *env);
 const char *normalize_arch(char *arch);
 
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 6d542a4..6199102 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -40,10 +40,10 @@ int unwind__prepare_access(struct thread *thread, struct map *map,
 
 	arch = normalize_arch(thread->mg->machine->env->arch);
 
-	if (!strcmp(arch, "x86")) {
+	if (!strcmp(arch, NORM_X86)) {
 		if (dso_type != DSO__TYPE_64BIT)
 			ops = x86_32_unwind_libunwind_ops;
-	} else if (!strcmp(arch, "arm64") || !strcmp(arch, "arm")) {
+	} else if (!strcmp(arch, NORM_ARM64) || !strcmp(arch, NORM_ARM)) {
 		if (dso_type == DSO__TYPE_64BIT)
 			ops = arm64_unwind_libunwind_ops;
 	}
-- 
2.5.5

[PATCH v4 2/3] perf annotate: Enable cross arch annotate

[Ravi Bangoria]

Change current data structures and function to enable cross arch
annotate.

Current implementation does not contain logic of record on one arch
and annotating on other. This remote annotate is partially possible
with current implementation for x86 (or may be arm as well) only.
But, to make remote annotation work properly, all architecture
instruction tables need to be included in the perf binary. And while
annotating, look for instruction table where perf.data was recorded.

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
---
Changes in v4:
  - __maybe_unused was misplaced at few location. Corrected it

 tools/perf/builtin-top.c          |   2 +-
 tools/perf/ui/browsers/annotate.c |   3 +-
 tools/perf/ui/gtk/annotate.c      |   2 +-
 tools/perf/util/annotate.c        | 134 ++++++++++++++++++++++++--------------
 tools/perf/util/annotate.h        |   5 +-
 5 files changed, 93 insertions(+), 53 deletions(-)

diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 07fc792..d4fd947 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -128,7 +128,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__annotate(sym, map, 0);
+	err = symbol__annotate(sym, map, 0, NULL);
 	if (err == 0) {
 out_assign:
 		top->sym_filter_entry = he;
diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 29dc6d2..3a652a6f 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -1050,7 +1050,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 		  (nr_pcnt - 1);
 	}
 
-	if (symbol__annotate(sym, map, sizeof_bdl) < 0) {
+	if (symbol__annotate(sym, map, sizeof_bdl,
+			     perf_evsel__env_arch(evsel)) < 0) {
 		ui__error("%s", ui_helpline__last_msg);
 		goto out_free_offsets;
 	}
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index 9c7ff8d..d7150b3 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -166,7 +166,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 	if (map->dso->annotate_warned)
 		return -1;
 
-	if (symbol__annotate(sym, map, 0) < 0) {
+	if (symbol__annotate(sym, map, 0, perf_evsel__env_arch(evsel)) < 0) {
 		ui__error("%s", ui_helpline__current);
 		return -1;
 	}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e9825fe..32889ce 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -20,12 +20,14 @@
 #include <regex.h>
 #include <pthread.h>
 #include <linux/bitops.h>
+#include <sys/utsname.h>
+#include "../arch/common.h"
 
 const char 	*disassembler_style;
 const char	*objdump_path;
 static regex_t	 file_lineno;
 
-static struct ins *ins__find(const char *name);
+static struct ins *ins__find(const char *name, const char *norm_arch);
 static int disasm_line__parse(char *line, char **namep, char **rawp);
 
 static void ins__delete(struct ins_operands *ops)
@@ -53,7 +55,7 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size,
 	return ins__raw_scnprintf(ins, bf, size, ops);
 }
 
-static int call__parse(struct ins_operands *ops)
+static int call__parse(struct ins_operands *ops, const char *norm_arch)
 {
 	char *endptr, *tok, *name;
 
@@ -65,10 +67,8 @@ static int call__parse(struct ins_operands *ops)
 
 	name++;
 
-#ifdef __arm__
-	if (strchr(name, '+'))
+	if (!strcmp(norm_arch, NORM_ARM) && strchr(name, '+'))
 		return -1;
-#endif
 
 	tok = strchr(name, '>');
 	if (tok == NULL)
@@ -117,7 +117,8 @@ bool ins__is_call(const struct ins *ins)
 	return ins->ops == &call_ops;
 }
 
-static int jump__parse(struct ins_operands *ops)
+static int jump__parse(struct ins_operands *ops,
+		       const char *norm_arch __maybe_unused)
 {
 	const char *s = strchr(ops->raw, '+');
 
@@ -172,7 +173,7 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
 	return 0;
 }
 
-static int lock__parse(struct ins_operands *ops)
+static int lock__parse(struct ins_operands *ops, const char *norm_arch)
 {
 	char *name;
 
@@ -183,7 +184,7 @@ static int lock__parse(struct ins_operands *ops)
 	if (disasm_line__parse(ops->raw, &name, &ops->locked.ops->raw) < 0)
 		goto out_free_ops;
 
-	ops->locked.ins = ins__find(name);
+	ops->locked.ins = ins__find(name, norm_arch);
 	free(name);
 
 	if (ops->locked.ins == NULL)
@@ -193,7 +194,7 @@ static int lock__parse(struct ins_operands *ops)
 		return 0;
 
 	if (ops->locked.ins->ops->parse &&
-	    ops->locked.ins->ops->parse(ops->locked.ops) < 0)
+	    ops->locked.ins->ops->parse(ops->locked.ops, norm_arch) < 0)
 		goto out_free_ops;
 
 	return 0;
@@ -236,7 +237,7 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
-static int mov__parse(struct ins_operands *ops)
+static int mov__parse(struct ins_operands *ops, const char *norm_arch)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
 
@@ -251,11 +252,11 @@ static int mov__parse(struct ins_operands *ops)
 		return -1;
 
 	target = ++s;
-#ifdef __arm__
-	comment = strchr(s, ';');
-#else
-	comment = strchr(s, '#');
-#endif
+
+	if (!strcmp(norm_arch, NORM_ARM))
+		comment = strchr(s, ';');
+	else
+		comment = strchr(s, '#');
 
 	if (comment != NULL)
 		s = comment - 1;
@@ -303,7 +304,8 @@ static struct ins_ops mov_ops = {
 	.scnprintf = mov__scnprintf,
 };
 
-static int dec__parse(struct ins_operands *ops)
+static int dec__parse(struct ins_operands *ops,
+		      const char *norm_arch __maybe_unused)
 {
 	char *target, *comment, *s, prev;
 
@@ -363,26 +365,12 @@ bool ins__is_ret(const struct ins *ins)
 	return ins->ops == &ret_ops;
 }
 
-static struct ins instructions[] = {
+static struct ins instructions_x86[] = {
 	{ .name = "add",   .ops  = &mov_ops, },
 	{ .name = "addl",  .ops  = &mov_ops, },
 	{ .name = "addq",  .ops  = &mov_ops, },
 	{ .name = "addw",  .ops  = &mov_ops, },
 	{ .name = "and",   .ops  = &mov_ops, },
-#ifdef __arm__
-	{ .name = "b",     .ops  = &jump_ops, }, // might also be a call
-	{ .name = "bcc",   .ops  = &jump_ops, },
-	{ .name = "bcs",   .ops  = &jump_ops, },
-	{ .name = "beq",   .ops  = &jump_ops, },
-	{ .name = "bge",   .ops  = &jump_ops, },
-	{ .name = "bgt",   .ops  = &jump_ops, },
-	{ .name = "bhi",   .ops  = &jump_ops, },
-	{ .name = "bl",    .ops  = &call_ops, },
-	{ .name = "bls",   .ops  = &jump_ops, },
-	{ .name = "blt",   .ops  = &jump_ops, },
-	{ .name = "blx",   .ops  = &call_ops, },
-	{ .name = "bne",   .ops  = &jump_ops, },
-#endif
 	{ .name = "bts",   .ops  = &mov_ops, },
 	{ .name = "call",  .ops  = &call_ops, },
 	{ .name = "callq", .ops  = &call_ops, },
@@ -456,6 +444,21 @@ static struct ins instructions[] = {
 	{ .name = "retq",  .ops  = &ret_ops, },
 };
 
+static struct ins instructions_arm[] = {
+	{ .name = "b",     .ops  = &jump_ops, }, /* might also be a call */
+	{ .name = "bcc",   .ops  = &jump_ops, },
+	{ .name = "bcs",   .ops  = &jump_ops, },
+	{ .name = "beq",   .ops  = &jump_ops, },
+	{ .name = "bge",   .ops  = &jump_ops, },
+	{ .name = "bgt",   .ops  = &jump_ops, },
+	{ .name = "bhi",   .ops  = &jump_ops, },
+	{ .name = "bl",    .ops  = &call_ops, },
+	{ .name = "bls",   .ops  = &jump_ops, },
+	{ .name = "blt",   .ops  = &jump_ops, },
+	{ .name = "blx",   .ops  = &call_ops, },
+	{ .name = "bne",   .ops  = &jump_ops, },
+};
+
 static int ins__key_cmp(const void *name, const void *insp)
 {
 	const struct ins *ins = insp;
@@ -471,24 +474,48 @@ static int ins__cmp(const void *a, const void *b)
 	return strcmp(ia->name, ib->name);
 }
 
-static void ins__sort(void)
+static void ins__sort(struct ins *instructions, int nmemb)
 {
-	const int nmemb = ARRAY_SIZE(instructions);
-
 	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
 }
 
-static struct ins *ins__find(const char *name)
+static const char *annotate__norm_arch(char *arch)
+{
+	struct utsname uts;
+
+	if (!arch) { /* Assume we are annotating locally. */
+		if (uname(&uts) < 0)
+			return NULL;
+		arch = uts.machine;
+	}
+	return normalize_arch(arch);
+}
+
+static struct ins *ins__find(const char *name, const char *norm_arch)
 {
-	const int nmemb = ARRAY_SIZE(instructions);
 	static bool sorted;
+	struct ins *instructions;
+	int nmemb;
 
 	if (!sorted) {
-		ins__sort();
+		ins__sort(instructions_x86, ARRAY_SIZE(instructions_x86));
+		ins__sort(instructions_arm, ARRAY_SIZE(instructions_arm));
 		sorted = true;
 	}
 
-	return bsearch(name, instructions, nmemb, sizeof(struct ins), ins__key_cmp);
+	if (!strcmp(norm_arch, NORM_X86)) {
+		instructions = instructions_x86;
+		nmemb = ARRAY_SIZE(instructions_x86);
+	} else if (!strcmp(norm_arch, NORM_ARM)) {
+		instructions = instructions_arm;
+		nmemb = ARRAY_SIZE(instructions_arm);
+	} else {
+		pr_err("perf annotate not supported by %s arch\n", norm_arch);
+		return NULL;
+	}
+
+	return bsearch(name, instructions, nmemb, sizeof(struct ins),
+			ins__key_cmp);
 }
 
 int symbol__annotate_init(struct map *map __maybe_unused, struct symbol *sym)
@@ -715,9 +742,16 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 ip)
 	return symbol__inc_addr_samples(he->ms.sym, he->ms.map, evidx, ip);
 }
 
-static void disasm_line__init_ins(struct disasm_line *dl)
+static void disasm_line__init_ins(struct disasm_line *dl, char *arch)
 {
-	dl->ins = ins__find(dl->name);
+	const char *norm_arch = annotate__norm_arch(arch);
+
+	if (!norm_arch) {
+		pr_err("Can not annotate. Could not determine architecture.");
+		return;
+	}
+
+	dl->ins = ins__find(dl->name, norm_arch);
 
 	if (dl->ins == NULL)
 		return;
@@ -725,7 +759,8 @@ static void disasm_line__init_ins(struct disasm_line *dl)
 	if (!dl->ins->ops)
 		return;
 
-	if (dl->ins->ops->parse && dl->ins->ops->parse(&dl->ops) < 0)
+	if (dl->ins->ops->parse &&
+	    dl->ins->ops->parse(&dl->ops, norm_arch) < 0)
 		dl->ins = NULL;
 }
 
@@ -767,7 +802,8 @@ out_free_name:
 }
 
 static struct disasm_line *disasm_line__new(s64 offset, char *line,
-					size_t privsize, int line_nr)
+					size_t privsize, int line_nr,
+					char *arch)
 {
 	struct disasm_line *dl = zalloc(sizeof(*dl) + privsize);
 
@@ -782,7 +818,7 @@ static struct disasm_line *disasm_line__new(s64 offset, char *line,
 			if (disasm_line__parse(dl->line, &dl->name, &dl->ops.raw) < 0)
 				goto out_free_line;
 
-			disasm_line__init_ins(dl);
+			disasm_line__init_ins(dl, arch);
 		}
 	}
 
@@ -1005,7 +1041,7 @@ static int disasm_line__print(struct disasm_line *dl, struct symbol *sym, u64 st
  */
 static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 				      FILE *file, size_t privsize,
-				      int *line_nr)
+				      int *line_nr, char *arch)
 {
 	struct annotation *notes = symbol__annotation(sym);
 	struct disasm_line *dl;
@@ -1066,7 +1102,8 @@ static int symbol__parse_objdump_line(struct symbol *sym, struct map *map,
 			parsed_line = tmp2 + 1;
 	}
 
-	dl = disasm_line__new(offset, parsed_line, privsize, *line_nr);
+	dl = disasm_line__new(offset, parsed_line, privsize,
+				*line_nr, arch);
 	free(line);
 	(*line_nr)++;
 
@@ -1123,7 +1160,8 @@ static void delete_last_nop(struct symbol *sym)
 	}
 }
 
-int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize)
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize,
+		     char *arch)
 {
 	struct dso *dso = map->dso;
 	char *filename = dso__build_id_filename(dso, NULL, 0);
@@ -1271,7 +1309,7 @@ fallback:
 	nline = 0;
 	while (!feof(file)) {
 		if (symbol__parse_objdump_line(sym, map, file, privsize,
-			    &lineno) < 0)
+			    &lineno, arch) < 0)
 			break;
 		nline++;
 	}
@@ -1663,7 +1701,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	struct rb_root source_line = RB_ROOT;
 	u64 len;
 
-	if (symbol__annotate(sym, map, 0) < 0)
+	if (symbol__annotate(sym, map, 0, perf_evsel__env_arch(evsel)) < 0)
 		return -1;
 
 	len = symbol__size(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index a23084f..4902138 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -36,7 +36,7 @@ struct ins_operands {
 
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
-	int (*parse)(struct ins_operands *ops);
+	int (*parse)(struct ins_operands *ops, const char *norm_arch);
 	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
 			 struct ins_operands *ops);
 };
@@ -155,7 +155,8 @@ int hist_entry__inc_addr_samples(struct hist_entry *he, int evidx, u64 addr);
 int symbol__alloc_hist(struct symbol *sym);
 void symbol__annotate_zero_histograms(struct symbol *sym);
 
-int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize);
+int symbol__annotate(struct symbol *sym, struct map *map, size_t privsize,
+		     char *arch);
 
 int symbol__annotate_init(struct map *map, struct symbol *sym);
 int symbol__annotate_printf(struct symbol *sym, struct map *map,
-- 
2.5.5

[PATCH v4 3/3] perf annotate: add powerpc support

[Ravi Bangoria]

From: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>

Powerpc has long list of branch instructions and hardcoding them in
table appears to be error-prone. So, add new function to find
instruction instead of creating table. This function dynamically
create table(list of 'struct ins'), and instead of creating object
every time, first check if list already contain object for that
instruction.

Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
---
Chnages in v4:
  - Added support for branch instructions that includes 'ctr'

 tools/perf/util/annotate.c | 155 +++++++++++++++++++++++++++++++++++++++++++--
 tools/perf/util/annotate.h |   3 +-
 2 files changed, 150 insertions(+), 8 deletions(-)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 32889ce..9de1271 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -55,10 +55,15 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size,
 	return ins__raw_scnprintf(ins, bf, size, ops);
 }
 
-static int call__parse(struct ins_operands *ops, const char *norm_arch)
+static int call__parse(char *ins_name, struct ins_operands *ops,
+		       const char *norm_arch)
 {
 	char *endptr, *tok, *name;
 
+	/* Special case for powerpc */
+	if (!strcmp(norm_arch, NORM_POWERPC) && strstr(ins_name, "ctr"))
+		return 0;
+
 	ops->target.addr = strtoull(ops->raw, &endptr, 16);
 
 	name = strchr(endptr, '<');
@@ -117,7 +122,7 @@ bool ins__is_call(const struct ins *ins)
 	return ins->ops == &call_ops;
 }
 
-static int jump__parse(struct ins_operands *ops,
+static int jump__parse(char *ins_name __maybe_unused, struct ins_operands *ops,
 		       const char *norm_arch __maybe_unused)
 {
 	const char *s = strchr(ops->raw, '+');
@@ -135,6 +140,13 @@ static int jump__parse(struct ins_operands *ops,
 static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 			   struct ins_operands *ops)
 {
+	/*
+	 * Instructions that does not include target address in operand
+	 * like 'bctr' for powerpc.
+	 */
+	if (!ops->target.addr)
+		return scnprintf(bf, size, "%-6.6s", ins->name);
+
 	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
 }
 
@@ -173,7 +185,8 @@ static int comment__symbol(char *raw, char *comment, u64 *addrp, char **namep)
 	return 0;
 }
 
-static int lock__parse(struct ins_operands *ops, const char *norm_arch)
+static int lock__parse(char *ins_name, struct ins_operands *ops,
+		       const char *norm_arch)
 {
 	char *name;
 
@@ -194,7 +207,8 @@ static int lock__parse(struct ins_operands *ops, const char *norm_arch)
 		return 0;
 
 	if (ops->locked.ins->ops->parse &&
-	    ops->locked.ins->ops->parse(ops->locked.ops, norm_arch) < 0)
+	    ops->locked.ins->ops->parse(ins_name,
+			ops->locked.ops, norm_arch) < 0)
 		goto out_free_ops;
 
 	return 0;
@@ -237,7 +251,8 @@ static struct ins_ops lock_ops = {
 	.scnprintf = lock__scnprintf,
 };
 
-static int mov__parse(struct ins_operands *ops, const char *norm_arch)
+static int mov__parse(char *ins_name __maybe_unused, struct ins_operands *ops,
+		      const char *norm_arch)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
 
@@ -304,7 +319,7 @@ static struct ins_ops mov_ops = {
 	.scnprintf = mov__scnprintf,
 };
 
-static int dec__parse(struct ins_operands *ops,
+static int dec__parse(char *ins_name __maybe_unused, struct ins_operands *ops,
 		      const char *norm_arch __maybe_unused)
 {
 	char *target, *comment, *s, prev;
@@ -459,6 +474,11 @@ static struct ins instructions_arm[] = {
 	{ .name = "bne",   .ops  = &jump_ops, },
 };
 
+struct instructions_powerpc {
+	struct ins *ins;
+	struct list_head list;
+};
+
 static int ins__key_cmp(const void *name, const void *insp)
 {
 	const struct ins *ins = insp;
@@ -474,6 +494,125 @@ static int ins__cmp(const void *a, const void *b)
 	return strcmp(ia->name, ib->name);
 }
 
+static struct ins *list_add__ins_powerpc(struct instructions_powerpc *head,
+					 const char *name, struct ins_ops *ops)
+{
+	struct instructions_powerpc *ins_powerpc;
+	struct ins *ins;
+
+	ins = zalloc(sizeof(struct ins));
+	if (!ins)
+		return NULL;
+
+	ins_powerpc = zalloc(sizeof(struct instructions_powerpc));
+	if (!ins_powerpc)
+		goto out_free_ins;
+
+	ins->name = strdup(name);
+	if (!ins->name)
+		goto out_free_ins_power;
+
+	ins->ops = ops;
+	ins_powerpc->ins = ins;
+	list_add_tail(&(ins_powerpc->list), &(head->list));
+
+	return ins;
+
+out_free_ins_power:
+	zfree(&ins_powerpc);
+out_free_ins:
+	zfree(&ins);
+	return NULL;
+}
+
+static struct ins *list_search__ins_powerpc(struct instructions_powerpc *head,
+					    const char *name)
+{
+	struct instructions_powerpc *pos;
+
+	list_for_each_entry(pos, &head->list, list) {
+		if (!strcmp(pos->ins->name, name))
+			return pos->ins;
+	}
+	return NULL;
+}
+
+static struct ins *ins__find_powerpc(const char *name)
+{
+	int i;
+	struct ins *ins;
+	struct ins_ops *ops;
+	static struct instructions_powerpc head;
+	static bool list_initialized;
+
+	/*
+	 * - Interested only if instruction starts with 'b'.
+	 * - Few start with 'b', but aren't branch instructions.
+	 * - Let's also ignore instructions involving 'tar' since target
+	 *   branch addresses for those can't be determined statically.
+	 *   (same for instruction involving 'ctr'. But they are very
+	 *    common so not filtering them.)
+	 */
+
+	if (name[0] != 'b'             ||
+	    !strncmp(name, "bcd", 3)   ||
+	    !strncmp(name, "brinc", 5) ||
+	    !strncmp(name, "bper", 4)  ||
+	    strstr(name, "tar"))
+		return NULL;
+
+	if (!list_initialized) {
+		INIT_LIST_HEAD(&head.list);
+		list_initialized = true;
+	}
+
+	/*
+	 * Return if we already have object of 'struct ins' for this instruction
+	 */
+	ins = list_search__ins_powerpc(&head, name);
+	if (ins)
+		return ins;
+
+	ops = &jump_ops;
+
+	i = strlen(name) - 1;
+	if (i < 0)
+		return NULL;
+
+	/* ignore optional hints at the end of the instructions */
+	if (name[i] == '+' || name[i] == '-')
+		i--;
+
+	if (name[i] == 'l' || (name[i] == 'a' && name[i-1] == 'l')) {
+		/*
+		 * if the instruction ends up with 'l' or 'la', then
+		 * those are considered 'calls' since they update LR.
+		 * ... except for 'bnl' which is branch if not less than
+		 * and the absolute form of the same.
+		 */
+		if (strcmp(name, "bnl") && strcmp(name, "bnl+") &&
+		    strcmp(name, "bnl-") && strcmp(name, "bnla") &&
+		    strcmp(name, "bnla+") && strcmp(name, "bnla-"))
+			ops = &call_ops;
+	}
+	if (name[i] == 'r' && name[i-1] == 'l')
+		/*
+		 * instructions ending with 'lr' are considered to be
+		 * return instructions
+		 */
+		ops = &ret_ops;
+
+	/*
+	 * Add instruction to list so next time no need to
+	 * allocate memory for it.
+	 */
+	ins = list_add__ins_powerpc(&head, name, ops);
+	if (ins)
+		return ins;
+
+	return NULL;
+}
+
 static void ins__sort(struct ins *instructions, int nmemb)
 {
 	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
@@ -509,6 +648,8 @@ static struct ins *ins__find(const char *name, const char *norm_arch)
 	} else if (!strcmp(norm_arch, NORM_ARM)) {
 		instructions = instructions_arm;
 		nmemb = ARRAY_SIZE(instructions_arm);
+	} else if (!strcmp(norm_arch, NORM_POWERPC)) {
+		return ins__find_powerpc(name);
 	} else {
 		pr_err("perf annotate not supported by %s arch\n", norm_arch);
 		return NULL;
@@ -760,7 +901,7 @@ static void disasm_line__init_ins(struct disasm_line *dl, char *arch)
 		return;
 
 	if (dl->ins->ops->parse &&
-	    dl->ins->ops->parse(&dl->ops, norm_arch) < 0)
+	    dl->ins->ops->parse(dl->name, &dl->ops, norm_arch) < 0)
 		dl->ins = NULL;
 }
 
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 4902138..ce77d35 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -36,7 +36,8 @@ struct ins_operands {
 
 struct ins_ops {
 	void (*free)(struct ins_operands *ops);
-	int (*parse)(struct ins_operands *ops, const char *norm_arch);
+	int (*parse)(char *name, struct ins_operands *ops,
+		     const char *norm_arch);
 	int (*scnprintf)(struct ins *ins, char *bf, size_t size,
 			 struct ins_operands *ops);
 };
-- 
2.5.5

Re: [PATCH v4 0/3] perf annotate: Enable cross arch annotate

[Ravi Bangoria]

Arnaldo, Michael,

I've tested this patchset on ppc64 BE and LE both. Please review this.

-Ravi

On Friday 08 July 2016 10:10 AM, Ravi Bangoria wrote:
> Perf can currently only support code navigation (branches and calls) in
> annotate when run on the same architecture where perf.data was recorded.
> But cross arch annotate is not supported.
>
> This patchset enables cross arch annotate. Currently I've used x86
> and arm instructions which are already available and adding support
> for powerpc as well. Adding support for other arch will be easy.
>
> I've created this patch on top of acme/perf/core. And tested it with
> x86 and powerpc only.
>
> Note for arm:
> Few instructions were defined under #if __arm__ which I've used as a
> table for arm. But I'm not sure whether instruction defined outside of
> that also contains arm instructions. Apart from that, 'call__parse()'
> and 'move__parse()' contains #ifdef __arm__ directive. I've changed it
> to  if (!strcmp(norm_arch, arm)). I don't have a arm machine to test
> these changes.
>
> Example:
>
>    Record on powerpc:
>    $ ./perf record -a
>
>    Report -> Annotate on x86:
>    $ ./perf report -i perf.data.powerpc --vmlinux vmlinux.powerpc
>
> Changes in v4:
>    - powerpc: Added support for branch instructions that includes 'ctr'
>    - __maybe_unused was misplaced at few location. Corrected it.
>    - Moved position of v3 last patch that define macro for each arch name
>
> v3 link: https://lkml.org/lkml/2016/6/30/99
>
> Naveen N. Rao (1):
>    perf annotate: add powerpc support
>
> Ravi Bangoria (2):
>    perf: Define macro for normalized arch names
>    perf annotate: Enable cross arch annotate
>
>   tools/perf/arch/common.c           |  36 ++---
>   tools/perf/arch/common.h           |  11 ++
>   tools/perf/builtin-top.c           |   2 +-
>   tools/perf/ui/browsers/annotate.c  |   3 +-
>   tools/perf/ui/gtk/annotate.c       |   2 +-
>   tools/perf/util/annotate.c         | 273 ++++++++++++++++++++++++++++++-------
>   tools/perf/util/annotate.h         |   6 +-
>   tools/perf/util/unwind-libunwind.c |   4 +-
>   8 files changed, 265 insertions(+), 72 deletions(-)
>
> --
> 2.5.5
>

Re: [PATCH v4 0/3] perf annotate: Enable cross arch annotate

[Ravi Bangoria]

I've sent v5 series for this. Please review it.

Thanks,
Ravi

On Wednesday 13 July 2016 03:15 PM, Ravi Bangoria wrote:
> Arnaldo, Michael,
>
> I've tested this patchset on ppc64 BE and LE both. Please review this.
>
> -Ravi
>
> On Friday 08 July 2016 10:10 AM, Ravi Bangoria wrote:
>> Perf can currently only support code navigation (branches and calls) in
>> annotate when run on the same architecture where perf.data was recorded.
>> But cross arch annotate is not supported.
>>
>> This patchset enables cross arch annotate. Currently I've used x86
>> and arm instructions which are already available and adding support
>> for powerpc as well. Adding support for other arch will be easy.
>>
>> I've created this patch on top of acme/perf/core. And tested it with
>> x86 and powerpc only.
>>
>> Note for arm:
>> Few instructions were defined under #if __arm__ which I've used as a
>> table for arm. But I'm not sure whether instruction defined outside of
>> that also contains arm instructions. Apart from that, 'call__parse()'
>> and 'move__parse()' contains #ifdef __arm__ directive. I've changed it
>> to  if (!strcmp(norm_arch, arm)). I don't have a arm machine to test
>> these changes.
>>
>> Example:
>>
>>    Record on powerpc:
>>    $ ./perf record -a
>>
>>    Report -> Annotate on x86:
>>    $ ./perf report -i perf.data.powerpc --vmlinux vmlinux.powerpc
>>
>> Changes in v4:
>>    - powerpc: Added support for branch instructions that includes 'ctr'
>>    - __maybe_unused was misplaced at few location. Corrected it.
>>    - Moved position of v3 last patch that define macro for each arch name
>>
>> v3 link: https://lkml.org/lkml/2016/6/30/99
>>
>> Naveen N. Rao (1):
>>    perf annotate: add powerpc support
>>
>> Ravi Bangoria (2):
>>    perf: Define macro for normalized arch names
>>    perf annotate: Enable cross arch annotate
>>
>>   tools/perf/arch/common.c           |  36 ++---
>>   tools/perf/arch/common.h           |  11 ++
>>   tools/perf/builtin-top.c           |   2 +-
>>   tools/perf/ui/browsers/annotate.c  |   3 +-
>>   tools/perf/ui/gtk/annotate.c       |   2 +-
>>   tools/perf/util/annotate.c         | 273 ++++++++++++++++++++++++++++++-------
>>   tools/perf/util/annotate.h         |   6 +-
>>   tools/perf/util/unwind-libunwind.c |   4 +-
>>   8 files changed, 265 insertions(+), 72 deletions(-)
>>
>> -- 
>> 2.5.5
>>
>