[PATCH 0/4] perf annotate: Enable cross arch annotate

[PATCH 0/4] 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.

Example:

  Record on powerpc:
  $ ./perf record -a

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

Changes in [PATCH] vs [RFC]
  - Removed global var 'arch__ins' and pass arch info till ins__find

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

Ravi Bangoria (3):
  perf: Utility function to fetch arch
  perf annotate: Enable cross arch annotate
  perf annotate: Define macro for arch names

 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         | 198 ++++++++++++++++++++++++++++---------
 tools/perf/util/annotate.h         |   5 +-
 tools/perf/util/evsel.c            |   7 ++
 tools/perf/util/evsel.h            |   2 +
 tools/perf/util/unwind-libunwind.c |   4 +-
 10 files changed, 198 insertions(+), 72 deletions(-)

--
2.5.5

[PATCH 1/4] perf: Utility function to fetch arch from evsel

[Ravi Bangoria]

Add Utility function to fetch 'arch' from 'evsel'. (evsel->env->arch)

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
---
 tools/perf/util/evsel.c | 7 +++++++
 tools/perf/util/evsel.h | 2 ++
 2 files changed, 9 insertions(+)

diff --git a/tools/perf/util/evsel.c b/tools/perf/util/evsel.c
index 1d8f2bb..0fea724 100644
--- a/tools/perf/util/evsel.c
+++ b/tools/perf/util/evsel.c
@@ -2422,3 +2422,10 @@ int perf_evsel__open_strerror(struct perf_evsel *evsel, struct target *target,
 			 err, strerror_r(err, sbuf, sizeof(sbuf)),
 			 perf_evsel__name(evsel));
 }
+
+char *perf_evsel__env_arch(struct perf_evsel *evsel)
+{
+	if (evsel && evsel->evlist && evsel->evlist->env)
+		return evsel->evlist->env->arch;
+	return NULL;
+}
diff --git a/tools/perf/util/evsel.h b/tools/perf/util/evsel.h
index 828ddd1..86fed7a 100644
--- a/tools/perf/util/evsel.h
+++ b/tools/perf/util/evsel.h
@@ -435,4 +435,6 @@ typedef int (*attr__fprintf_f)(FILE *, const char *, const char *, void *);
 int perf_event_attr__fprintf(FILE *fp, struct perf_event_attr *attr,
 			     attr__fprintf_f attr__fprintf, void *priv);
 
+char *perf_evsel__env_arch(struct perf_evsel *evsel);
+
 #endif /* __PERF_EVSEL_H */
-- 
2.5.5

[PATCH 2/4] 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 annotate 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.

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")). But I've not
tested this as well.

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
---
 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        | 136 ++++++++++++++++++++++++--------------
 tools/perf/util/annotate.h        |   5 +-
 5 files changed, 95 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 c385fec..36a5825 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 +55,8 @@ 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,
+		       __maybe_unused const char *norm_arch)
 {
 	char *endptr, *tok, *name;
 
@@ -65,10 +68,8 @@ static int call__parse(struct ins_operands *ops)
 
 	name++;
 
-#ifdef __arm__
-	if (strchr(name, '+'))
+	if (!strcmp(norm_arch, "arm") && strchr(name, '+'))
 		return -1;
-#endif
 
 	tok = strchr(name, '>');
 	if (tok == NULL)
@@ -117,7 +118,8 @@ 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,
+		       __maybe_unused const char *norm_arch)
 {
 	const char *s = strchr(ops->raw, '+');
 
@@ -172,7 +174,7 @@ 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 +185,7 @@ 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 +195,7 @@ 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 +238,8 @@ 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,
+		      __maybe_unused const char *norm_arch)
 {
 	char *s = strchr(ops->raw, ','), *target, *comment, prev;
 
@@ -251,11 +254,11 @@ 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, "arm"))
+		comment = strchr(s, ';');
+	else
+		comment = strchr(s, '#');
 
 	if (comment != NULL)
 		s = comment - 1;
@@ -303,7 +306,8 @@ 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,
+		      __maybe_unused const char *norm_arch)
 {
 	char *target, *comment, *s, prev;
 
@@ -363,26 +367,12 @@ 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 +446,21 @@ 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 +476,48 @@ 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, "x86")) {
+		instructions = instructions_x86;
+		nmemb = ARRAY_SIZE(instructions_x86);
+	} else if (!strcmp(norm_arch, "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 +744,16 @@ 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 +761,8 @@ 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 +804,8 @@ 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 +820,7 @@ 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 +1043,7 @@ 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 +1104,8 @@ 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 +1162,8 @@ 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 +1311,7 @@ fallback:
 	nline = 0;
 	while (!feof(file)) {
 		if (symbol__parse_objdump_line(sym, map, file, privsize,
-			    &lineno) < 0)
+			    &lineno, arch) < 0)
 			break;
 		nline++;
 	}
@@ -1665,7 +1705,7 @@ 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 3/4] 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.

Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
---
 tools/perf/util/annotate.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 64 insertions(+)

diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 36a5825..96c6610 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -476,6 +476,68 @@ static int ins__cmp(const void *a, const void *b)
 	return strcmp(ia->name, ib->name);
 }
 
+static struct ins *ins__find_powerpc(const char *name)
+{
+	int i;
+	struct ins *ins;
+
+	ins = zalloc(sizeof(struct ins));
+	if (!ins)
+		return NULL;
+
+	ins->name = strdup(name);
+	if (!ins->name)
+		return NULL;
+
+	if (name[0] == 'b') {
+		/* branch instructions */
+		ins->ops = &jump_ops;
+
+		/*
+		 * - Few start with 'b', but aren't branch instructions.
+		 * - Let's also ignore instructions involving 'ctr' and
+		 *   'tar' since target branch addresses for those can't
+		 *   be determined statically.
+		 */
+		if (!strncmp(name, "bcd", 3)   ||
+		    !strncmp(name, "brinc", 5) ||
+		    !strncmp(name, "bper", 4)  ||
+		    strstr(name, "ctr")        ||
+		    strstr(name, "tar"))
+			return NULL;
+
+		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-"))
+				ins->ops = &call_ops;
+		}
+		if (name[i] == 'r' && name[i-1] == 'l')
+			/*
+			 * instructions ending with 'lr' are considered to be
+			 * return instructions
+			 */
+			ins->ops = &ret_ops;
+
+		return ins;
+	}
+	return NULL;
+}
+
 static void ins__sort(struct ins *instructions, int nmemb)
 {
 	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
@@ -511,6 +573,8 @@ static struct ins *ins__find(const char *name, const char *norm_arch)
 	} else if (!strcmp(norm_arch, "arm")) {
 		instructions = instructions_arm;
 		nmemb = ARRAY_SIZE(instructions_arm);
+	} else if (!strcmp(norm_arch, "powerpc")) {
+		return ins__find_powerpc(name);
 	} else {
 		pr_err("perf annotate not supported by %s arch\n", norm_arch);
 		return NULL;
-- 
2.5.5

RE: [PATCH 3/4] perf annotate: add powerpc support

[David Laight]

From: Ravi Bangoria
> Sent: 28 June 2016 12:37
> 
> 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.
> 
> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
> Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
> ---
>  tools/perf/util/annotate.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++
>  1 file changed, 64 insertions(+)
> 
> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
> index 36a5825..96c6610 100644
> --- a/tools/perf/util/annotate.c
> +++ b/tools/perf/util/annotate.c
> @@ -476,6 +476,68 @@ static int ins__cmp(const void *a, const void *b)
>  	return strcmp(ia->name, ib->name);
>  }
> 
> +static struct ins *ins__find_powerpc(const char *name)

It would be better if the function name include 'branch'.

> +{
> +	int i;
> +	struct ins *ins;
> +
> +	ins = zalloc(sizeof(struct ins));
> +	if (!ins)
> +		return NULL;
> +
> +	ins->name = strdup(name);
> +	if (!ins->name)
> +		return NULL;

	You leak 'ins' here.

> +
> +	if (name[0] == 'b') {
> +		/* branch instructions */
> +		ins->ops = &jump_ops;
> +
> +		/*
> +		 * - Few start with 'b', but aren't branch instructions.
> +		 * - Let's also ignore instructions involving 'ctr' and
> +		 *   'tar' since target branch addresses for those can't
> +		 *   be determined statically.
> +		 */
> +		if (!strncmp(name, "bcd", 3)   ||
> +		    !strncmp(name, "brinc", 5) ||
> +		    !strncmp(name, "bper", 4)  ||
> +		    strstr(name, "ctr")        ||
> +		    strstr(name, "tar"))
> +			return NULL;

	More importantly you leak 'ins' and 'ins->name' here.
	And on other paths below.

...

	David

Re: [PATCH 3/4] perf annotate: add powerpc support

[Ravi Bangoria]

Thanks David.

On Tuesday 28 June 2016 09:37 PM, David Laight wrote:
> From: Ravi Bangoria
>> Sent: 28 June 2016 12:37
>>
>> 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.
>>
>> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
>> Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
>> ---
>>   tools/perf/util/annotate.c | 64 ++++++++++++++++++++++++++++++++++++++++++++++
>>   1 file changed, 64 insertions(+)
>>
>> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
>> index 36a5825..96c6610 100644
>> --- a/tools/perf/util/annotate.c
>> +++ b/tools/perf/util/annotate.c
>> @@ -476,6 +476,68 @@ static int ins__cmp(const void *a, const void *b)
>>   	return strcmp(ia->name, ib->name);
>>   }
>>
>> +static struct ins *ins__find_powerpc(const char *name)
> It would be better if the function name include 'branch'.
>
>> +{
>> +	int i;
>> +	struct ins *ins;
>> +
>> +	ins = zalloc(sizeof(struct ins));
>> +	if (!ins)
>> +		return NULL;
>> +
>> +	ins->name = strdup(name);
>> +	if (!ins->name)
>> +		return NULL;
> 	You leak 'ins' here.
>
>> +
>> +	if (name[0] == 'b') {
>> +		/* branch instructions */
>> +		ins->ops = &jump_ops;
>> +
>> +		/*
>> +		 * - Few start with 'b', but aren't branch instructions.
>> +		 * - Let's also ignore instructions involving 'ctr' and
>> +		 *   'tar' since target branch addresses for those can't
>> +		 *   be determined statically.
>> +		 */
>> +		if (!strncmp(name, "bcd", 3)   ||
>> +		    !strncmp(name, "brinc", 5) ||
>> +		    !strncmp(name, "bper", 4)  ||
>> +		    strstr(name, "ctr")        ||
>> +		    strstr(name, "tar"))
>> +			return NULL;
> 	More importantly you leak 'ins' and 'ins->name' here.
> 	And on other paths below.

Yes. Fair points.

I can create linked list that maintain allocated instructions and
lookup it every time before allocating memory. But for this,
I need to free memory at the end and it's becoming complicated.

I can go back to normal approach of creating table for powerpc.
This is simplest. But only problem is powerpc has around 400 branch
instructions(which includes call and ret as well). And list them all is
bit error-prone.

Suggestions?

- Ravi

> ...
>
> 	David
>

[PATCH 4/4] perf annotate: Define macro for arch names

[Ravi Bangoria]

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

Signed-off-by: Ravi Bangoria <ravi.bangoria@linux.vnet.ibm.com>
---
 tools/perf/arch/common.c           | 36 ++++++++++++++++++------------------
 tools/perf/arch/common.h           | 11 +++++++++++
 tools/perf/util/annotate.c         | 10 +++++-----
 tools/perf/util/unwind-libunwind.c |  4 ++--
 4 files changed, 36 insertions(+), 25 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/annotate.c b/tools/perf/util/annotate.c
index 96c6610..8146a25 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -68,7 +68,7 @@ static int call__parse(struct ins_operands *ops,
 
 	name++;
 
-	if (!strcmp(norm_arch, "arm") && strchr(name, '+'))
+	if (!strcmp(norm_arch, NORM_ARM) && strchr(name, '+'))
 		return -1;
 
 	tok = strchr(name, '>');
@@ -255,7 +255,7 @@ static int mov__parse(struct ins_operands *ops,
 
 	target = ++s;
 
-	if (!strcmp(norm_arch, "arm"))
+	if (!strcmp(norm_arch, NORM_ARM))
 		comment = strchr(s, ';');
 	else
 		comment = strchr(s, '#');
@@ -567,13 +567,13 @@ static struct ins *ins__find(const char *name, const char *norm_arch)
 		sorted = true;
 	}
 
-	if (!strcmp(norm_arch, "x86")) {
+	if (!strcmp(norm_arch, NORM_X86)) {
 		instructions = instructions_x86;
 		nmemb = ARRAY_SIZE(instructions_x86);
-	} else if (!strcmp(norm_arch, "arm")) {
+	} else if (!strcmp(norm_arch, NORM_ARM)) {
 		instructions = instructions_arm;
 		nmemb = ARRAY_SIZE(instructions_arm);
-	} else if (!strcmp(norm_arch, "powerpc")) {
+	} 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);
diff --git a/tools/perf/util/unwind-libunwind.c b/tools/perf/util/unwind-libunwind.c
index 8547119..8d4a53f 100644
--- a/tools/perf/util/unwind-libunwind.c
+++ b/tools/perf/util/unwind-libunwind.c
@@ -36,10 +36,10 @@ 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