[PATCH 1/2] perf annotate: generalize handling of ret instructions

[PATCH 1/2] perf annotate: generalize handling of ret instructions

[Naveen N. Rao]

Introduce helper to detect ret instructions and use the same in the tui.

Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
---
 tools/perf/ui/browsers/annotate.c | 20 +++++++++-----------
 tools/perf/util/annotate.c        | 10 ++++++++++
 tools/perf/util/annotate.h        |  1 +
 3 files changed, 20 insertions(+), 11 deletions(-)

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4fc208e..dcfaf7a 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -222,16 +222,14 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 			} else if (ins__is_call(dl->ins)) {
 				ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
 				SLsmg_write_char(' ');
+			} else if (ins__is_ret(dl->ins)) {
+				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
+				SLsmg_write_char(' ');
 			} else {
 				ui_browser__write_nstring(browser, " ", 2);
 			}
 		} else {
-			if (strcmp(dl->name, "retq")) {
-				ui_browser__write_nstring(browser, " ", 2);
-			} else {
-				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
-				SLsmg_write_char(' ');
-			}
+			ui_browser__write_nstring(browser, " ", 2);
 		}
 
 		disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
@@ -842,14 +840,14 @@ show_help:
 				ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
 			else if (browser->selection->offset == -1)
 				ui_helpline__puts("Actions are only available for assembly lines.");
-			else if (!browser->selection->ins) {
-				if (strcmp(browser->selection->name, "retq"))
-					goto show_sup_ins;
+			else if (!browser->selection->ins)
+				goto show_sup_ins;
+			else if (ins__is_ret(browser->selection->ins))
 				goto out;
-			} else if (!(annotate_browser__jump(browser) ||
+			else if (!(annotate_browser__jump(browser) ||
 				     annotate_browser__callq(browser, evsel, hbt))) {
 show_sup_ins:
-				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
+				ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
 			}
 			continue;
 		case 't':
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 7e5a1e8..e871b4e 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -354,6 +354,15 @@ static struct ins_ops nop_ops = {
 	.scnprintf = nop__scnprintf,
 };
 
+static struct ins_ops ret_ops = {
+	.scnprintf = ins__raw_scnprintf,
+};
+
+bool ins__is_ret(const struct ins *ins)
+{
+	return ins->ops == &ret_ops;
+}
+
 static struct ins instructions[] = {
 	{ .name = "add",   .ops  = &mov_ops, },
 	{ .name = "addl",  .ops  = &mov_ops, },
@@ -444,6 +453,7 @@ static struct ins instructions[] = {
 	{ .name = "xadd",  .ops  = &mov_ops, },
 	{ .name = "xbeginl", .ops  = &jump_ops, },
 	{ .name = "xbeginq", .ops  = &jump_ops, },
+	{ .name = "retq",  .ops  = &ret_ops, },
 };
 
 static int ins__key_cmp(const void *name, const void *insp)
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 9241f8c..720a4c0 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -48,6 +48,7 @@ struct ins {
 
 bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
+bool ins__is_ret(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
 
 struct annotation;
-- 
2.8.2

[PATCH 2/2] perf annotate: add powerpc support

[Naveen N. Rao]

Convert ins__find() to a __weak function for generic functionality,
while adding a powerpc-specific variant. We look at the function name
for branch instructions and classify the instructions to one among a
branch, a function call (branch with LR update) or a function return
(branch to LR).

Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Anton Blanchard <anton@ozlabs.org>
Cc: Michael Ellerman <mpe@ellerman.id.au>
Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
Reported-by: Anton Blanchard <anton@ozlabs.org>
Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
---
 tools/perf/arch/powerpc/util/Build      |  1 +
 tools/perf/arch/powerpc/util/annotate.c | 58 +++++++++++++++++++++++++++++++++
 tools/perf/util/annotate.c              | 17 +++++-----
 tools/perf/util/annotate.h              |  9 +++++
 4 files changed, 76 insertions(+), 9 deletions(-)
 create mode 100644 tools/perf/arch/powerpc/util/annotate.c

diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
index 90ad64b..d9e91d6 100644
--- a/tools/perf/arch/powerpc/util/Build
+++ b/tools/perf/arch/powerpc/util/Build
@@ -2,6 +2,7 @@ libperf-y += header.o
 libperf-y += sym-handling.o
 libperf-y += kvm-stat.o
 libperf-y += perf_regs.o
+libperf-y += annotate.o
 
 libperf-$(CONFIG_DWARF) += dwarf-regs.o
 libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
diff --git a/tools/perf/arch/powerpc/util/annotate.c b/tools/perf/arch/powerpc/util/annotate.c
new file mode 100644
index 0000000..f069bd7
--- /dev/null
+++ b/tools/perf/arch/powerpc/util/annotate.c
@@ -0,0 +1,58 @@
+#include "perf.h"
+#include "annotate.h"
+
+struct ins *ins__find(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;
+
+		/* these start with 'b', but aren't branch instructions */
+		if (!strncmp(name, "bcd", 3) ||
+				!strncmp(name, "brinc", 5) ||
+				!strncmp(name, "bper", 4))
+			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;
+}
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index e871b4e..0fa4fc5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -25,7 +25,6 @@ const char 	*disassembler_style;
 const char	*objdump_path;
 static regex_t	 file_lineno;
 
-static struct ins *ins__find(const char *name);
 static int disasm_line__parse(char *line, char **namep, char **rawp);
 
 static void ins__delete(struct ins_operands *ops)
@@ -107,7 +106,7 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
 	return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
 }
 
-static struct ins_ops call_ops = {
+struct ins_ops call_ops = {
 	.parse	   = call__parse,
 	.scnprintf = call__scnprintf,
 };
@@ -137,7 +136,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
 	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
 }
 
-static struct ins_ops jump_ops = {
+struct ins_ops jump_ops = {
 	.parse	   = jump__parse,
 	.scnprintf = jump__scnprintf,
 };
@@ -230,7 +229,7 @@ static void lock__delete(struct ins_operands *ops)
 	zfree(&ops->target.name);
 }
 
-static struct ins_ops lock_ops = {
+struct ins_ops lock_ops = {
 	.free	   = lock__delete,
 	.parse	   = lock__parse,
 	.scnprintf = lock__scnprintf,
@@ -298,7 +297,7 @@ static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
 			 ops->target.name ?: ops->target.raw);
 }
 
-static struct ins_ops mov_ops = {
+struct ins_ops mov_ops = {
 	.parse	   = mov__parse,
 	.scnprintf = mov__scnprintf,
 };
@@ -339,7 +338,7 @@ static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
 			 ops->target.name ?: ops->target.raw);
 }
 
-static struct ins_ops dec_ops = {
+struct ins_ops dec_ops = {
 	.parse	   = dec__parse,
 	.scnprintf = dec__scnprintf,
 };
@@ -350,11 +349,11 @@ static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
 	return scnprintf(bf, size, "%-6.6s", "nop");
 }
 
-static struct ins_ops nop_ops = {
+struct ins_ops nop_ops = {
 	.scnprintf = nop__scnprintf,
 };
 
-static struct ins_ops ret_ops = {
+struct ins_ops ret_ops = {
 	.scnprintf = ins__raw_scnprintf,
 };
 
@@ -478,7 +477,7 @@ static void ins__sort(void)
 	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
 }
 
-static struct ins *ins__find(const char *name)
+__weak struct ins *ins__find(const char *name)
 {
 	const int nmemb = ARRAY_SIZE(instructions);
 	static bool sorted;
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 720a4c0..6d89c1d 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -50,6 +50,15 @@ bool ins__is_jump(const struct ins *ins);
 bool ins__is_call(const struct ins *ins);
 bool ins__is_ret(const struct ins *ins);
 int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
+struct ins *ins__find(const char *name);
+
+extern struct ins_ops call_ops;
+extern struct ins_ops jump_ops;
+extern struct ins_ops ret_ops;
+extern struct ins_ops mov_ops;
+extern struct ins_ops lock_ops;
+extern struct ins_ops dec_ops;
+extern struct ins_ops nop_ops;
 
 struct annotation;
 
-- 
2.8.2

Re: [PATCH 2/2] perf annotate: add powerpc support

[Arnaldo Carvalho de Melo]

Em Fri, Jun 10, 2016 at 06:32:51PM +0530, Naveen N. Rao escreveu:
> Convert ins__find() to a __weak function for generic functionality,
> while adding a powerpc-specific variant. We look at the function name
> for branch instructions and classify the instructions to one among a
> branch, a function call (branch with LR update) or a function return
> (branch to LR).

How would this allow one to get a perf.data collected on a powerpc
system, transfer it to a x86-64 (or aarch64, to mention another
workstation wannabe chip) system and then try annotating it?

There was a previous discussion about this, and it involved having all
yout ppc tables available as well as other arches tables, and then
choosing which one to use based on:

	normalize_arch(thread->mg->machine->env->arch)

just like was done for support cross unwinding, see recent patch kit by
He Kuang, CCed.

- Arnaldo
 
> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> Cc: Anton Blanchard <anton@ozlabs.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
> Reported-by: Anton Blanchard <anton@ozlabs.org>
> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
> ---
>  tools/perf/arch/powerpc/util/Build      |  1 +
>  tools/perf/arch/powerpc/util/annotate.c | 58 +++++++++++++++++++++++++++++++++
>  tools/perf/util/annotate.c              | 17 +++++-----
>  tools/perf/util/annotate.h              |  9 +++++
>  4 files changed, 76 insertions(+), 9 deletions(-)
>  create mode 100644 tools/perf/arch/powerpc/util/annotate.c
> 
> diff --git a/tools/perf/arch/powerpc/util/Build b/tools/perf/arch/powerpc/util/Build
> index 90ad64b..d9e91d6 100644
> --- a/tools/perf/arch/powerpc/util/Build
> +++ b/tools/perf/arch/powerpc/util/Build
> @@ -2,6 +2,7 @@ libperf-y += header.o
>  libperf-y += sym-handling.o
>  libperf-y += kvm-stat.o
>  libperf-y += perf_regs.o
> +libperf-y += annotate.o
>  
>  libperf-$(CONFIG_DWARF) += dwarf-regs.o
>  libperf-$(CONFIG_DWARF) += skip-callchain-idx.o
> diff --git a/tools/perf/arch/powerpc/util/annotate.c b/tools/perf/arch/powerpc/util/annotate.c
> new file mode 100644
> index 0000000..f069bd7
> --- /dev/null
> +++ b/tools/perf/arch/powerpc/util/annotate.c
> @@ -0,0 +1,58 @@
> +#include "perf.h"
> +#include "annotate.h"
> +
> +struct ins *ins__find(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;
> +
> +		/* these start with 'b', but aren't branch instructions */
> +		if (!strncmp(name, "bcd", 3) ||
> +				!strncmp(name, "brinc", 5) ||
> +				!strncmp(name, "bper", 4))
> +			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;
> +}
> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
> index e871b4e..0fa4fc5 100644
> --- a/tools/perf/util/annotate.c
> +++ b/tools/perf/util/annotate.c
> @@ -25,7 +25,6 @@ const char 	*disassembler_style;
>  const char	*objdump_path;
>  static regex_t	 file_lineno;
>  
> -static struct ins *ins__find(const char *name);
>  static int disasm_line__parse(char *line, char **namep, char **rawp);
>  
>  static void ins__delete(struct ins_operands *ops)
> @@ -107,7 +106,7 @@ static int call__scnprintf(struct ins *ins, char *bf, size_t size,
>  	return scnprintf(bf, size, "%-6.6s *%" PRIx64, ins->name, ops->target.addr);
>  }
>  
> -static struct ins_ops call_ops = {
> +struct ins_ops call_ops = {
>  	.parse	   = call__parse,
>  	.scnprintf = call__scnprintf,
>  };
> @@ -137,7 +136,7 @@ static int jump__scnprintf(struct ins *ins, char *bf, size_t size,
>  	return scnprintf(bf, size, "%-6.6s %" PRIx64, ins->name, ops->target.offset);
>  }
>  
> -static struct ins_ops jump_ops = {
> +struct ins_ops jump_ops = {
>  	.parse	   = jump__parse,
>  	.scnprintf = jump__scnprintf,
>  };
> @@ -230,7 +229,7 @@ static void lock__delete(struct ins_operands *ops)
>  	zfree(&ops->target.name);
>  }
>  
> -static struct ins_ops lock_ops = {
> +struct ins_ops lock_ops = {
>  	.free	   = lock__delete,
>  	.parse	   = lock__parse,
>  	.scnprintf = lock__scnprintf,
> @@ -298,7 +297,7 @@ static int mov__scnprintf(struct ins *ins, char *bf, size_t size,
>  			 ops->target.name ?: ops->target.raw);
>  }
>  
> -static struct ins_ops mov_ops = {
> +struct ins_ops mov_ops = {
>  	.parse	   = mov__parse,
>  	.scnprintf = mov__scnprintf,
>  };
> @@ -339,7 +338,7 @@ static int dec__scnprintf(struct ins *ins, char *bf, size_t size,
>  			 ops->target.name ?: ops->target.raw);
>  }
>  
> -static struct ins_ops dec_ops = {
> +struct ins_ops dec_ops = {
>  	.parse	   = dec__parse,
>  	.scnprintf = dec__scnprintf,
>  };
> @@ -350,11 +349,11 @@ static int nop__scnprintf(struct ins *ins __maybe_unused, char *bf, size_t size,
>  	return scnprintf(bf, size, "%-6.6s", "nop");
>  }
>  
> -static struct ins_ops nop_ops = {
> +struct ins_ops nop_ops = {
>  	.scnprintf = nop__scnprintf,
>  };
>  
> -static struct ins_ops ret_ops = {
> +struct ins_ops ret_ops = {
>  	.scnprintf = ins__raw_scnprintf,
>  };
>  
> @@ -478,7 +477,7 @@ static void ins__sort(void)
>  	qsort(instructions, nmemb, sizeof(struct ins), ins__cmp);
>  }
>  
> -static struct ins *ins__find(const char *name)
> +__weak struct ins *ins__find(const char *name)
>  {
>  	const int nmemb = ARRAY_SIZE(instructions);
>  	static bool sorted;
> diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
> index 720a4c0..6d89c1d 100644
> --- a/tools/perf/util/annotate.h
> +++ b/tools/perf/util/annotate.h
> @@ -50,6 +50,15 @@ bool ins__is_jump(const struct ins *ins);
>  bool ins__is_call(const struct ins *ins);
>  bool ins__is_ret(const struct ins *ins);
>  int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
> +struct ins *ins__find(const char *name);
> +
> +extern struct ins_ops call_ops;
> +extern struct ins_ops jump_ops;
> +extern struct ins_ops ret_ops;
> +extern struct ins_ops mov_ops;
> +extern struct ins_ops lock_ops;
> +extern struct ins_ops dec_ops;
> +extern struct ins_ops nop_ops;
>  
>  struct annotation;
>  
> -- 
> 2.8.2

Re: [PATCH 2/2] perf annotate: add powerpc support

[Naveen N. Rao]

On 2016/06/10 10:36AM, Arnaldo Carvalho de Melo wrote:
> Em Fri, Jun 10, 2016 at 06:32:51PM +0530, Naveen N. Rao escreveu:
> > Convert ins__find() to a __weak function for generic functionality,
> > while adding a powerpc-specific variant. We look at the function name
> > for branch instructions and classify the instructions to one among a
> > branch, a function call (branch with LR update) or a function return
> > (branch to LR).
> 
> How would this allow one to get a perf.data collected on a powerpc
> system, transfer it to a x86-64 (or aarch64, to mention another
> workstation wannabe chip) system and then try annotating it?
> 
> There was a previous discussion about this, and it involved having all
> yout ppc tables available as well as other arches tables, and then
> choosing which one to use based on:
> 
> 	normalize_arch(thread->mg->machine->env->arch)
> 
> just like was done for support cross unwinding, see recent patch kit by
> He Kuang, CCed.

Nice. This would be good to have. I will look at adding powerpc support 
for cross-architecture unwind.

However, for cross-architecture annotation, I think there will be a lot 
more dependencies since perf currently uses objdump to obtain the 
disassembly. In addition, the actual binaries will also be needed.


- Naveen

Re: [PATCH 2/2] perf annotate: add powerpc support

[Naveen N. Rao]

On 2016/06/10 08:08PM, Naveen N. Rao wrote:
> On 2016/06/10 10:36AM, Arnaldo Carvalho de Melo wrote:
> > Em Fri, Jun 10, 2016 at 06:32:51PM +0530, Naveen N. Rao escreveu:
> > > Convert ins__find() to a __weak function for generic functionality,
> > > while adding a powerpc-specific variant. We look at the function name
> > > for branch instructions and classify the instructions to one among a
> > > branch, a function call (branch with LR update) or a function return
> > > (branch to LR).
> > 
> > How would this allow one to get a perf.data collected on a powerpc
> > system, transfer it to a x86-64 (or aarch64, to mention another
> > workstation wannabe chip) system and then try annotating it?
> > 
> > There was a previous discussion about this, and it involved having all
> > yout ppc tables available as well as other arches tables, and then
> > choosing which one to use based on:
> > 
> > 	normalize_arch(thread->mg->machine->env->arch)
> > 
> > just like was done for support cross unwinding, see recent patch kit by
> > He Kuang, CCed.
> 
> Nice. This would be good to have. I will look at adding powerpc support 
> for cross-architecture unwind.
> 
> However, for cross-architecture annotation, I think there will be a lot 
> more dependencies since perf currently uses objdump to obtain the 
> disassembly. In addition, the actual binaries will also be needed.

perf report already has a --objdump flag... will look into this later 
next week.

- Naveen

Re: [PATCH 2/2] perf annotate: add powerpc support

[Michael Ellerman]

On Fri, 2016-06-10 at 20:08 +0530, Naveen N. Rao wrote:
> On 2016/06/10 10:36AM, Arnaldo Carvalho de Melo wrote:
> > Em Fri, Jun 10, 2016 at 06:32:51PM +0530, Naveen N. Rao escreveu:
> > > Convert ins__find() to a __weak function for generic functionality,
> > > while adding a powerpc-specific variant. We look at the function name
> > > for branch instructions and classify the instructions to one among a
> > > branch, a function call (branch with LR update) or a function return
> > > (branch to LR).
> > 
> > How would this allow one to get a perf.data collected on a powerpc
> > system, transfer it to a x86-64 (or aarch64, to mention another
> > workstation wannabe chip) system and then try annotating it?
> > 
> > There was a previous discussion about this, and it involved having all
> > yout ppc tables available as well as other arches tables, and then
> > choosing which one to use based on:
> > 
> > 	normalize_arch(thread->mg->machine->env->arch)
> > 
> > just like was done for support cross unwinding, see recent patch kit by
> > He Kuang, CCed.
> 
> Nice. This would be good to have. I will look at adding powerpc support 
> for cross-architecture unwind.
> 
> However, for cross-architecture annotation, I think there will be a lot 
> more dependencies since perf currently uses objdump to obtain the 
> disassembly. In addition, the actual binaries will also be needed.

It's possible to build a multi-arch objdump, I don't know if it's packaged on
all distros, or if perf wants to depend on it.

cheers

Re: [PATCH 2/2] perf annotate: add powerpc support

[Arnaldo Carvalho de Melo]

Em Tue, Jun 14, 2016 at 01:40:47PM +1000, Michael Ellerman escreveu:
> On Fri, 2016-06-10 at 20:08 +0530, Naveen N. Rao wrote:
> > On 2016/06/10 10:36AM, Arnaldo Carvalho de Melo wrote:
> > > Em Fri, Jun 10, 2016 at 06:32:51PM +0530, Naveen N. Rao escreveu:
> > > > Convert ins__find() to a __weak function for generic functionality,
> > > > while adding a powerpc-specific variant. We look at the function name
> > > > for branch instructions and classify the instructions to one among a
> > > > branch, a function call (branch with LR update) or a function return
> > > > (branch to LR).

> > > How would this allow one to get a perf.data collected on a powerpc
> > > system, transfer it to a x86-64 (or aarch64, to mention another
> > > workstation wannabe chip) system and then try annotating it?

> > > There was a previous discussion about this, and it involved having all
> > > yout ppc tables available as well as other arches tables, and then
> > > choosing which one to use based on:

> > > 	normalize_arch(thread->mg->machine->env->arch)

> > > just like was done for support cross unwinding, see recent patch kit by
> > > He Kuang, CCed.

> > Nice. This would be good to have. I will look at adding powerpc support 
> > for cross-architecture unwind.

> > However, for cross-architecture annotation, I think there will be a lot 
> > more dependencies since perf currently uses objdump to obtain the 
> > disassembly. In addition, the actual binaries will also be needed.
 
> It's possible to build a multi-arch objdump, I don't know if it's packaged on
> all distros, or if perf wants to depend on it.

Somebody noticed that we can specify a different objdump binary, from a
cross toolchain package.

We need to at least check if the objdump being used supports the
architecture where the perf.data file was generated, refusing to process
the file for which there is no support, providing a clear message to
users trying to process such files.

I.e. checking if normalize_arch(thread->mg->machine->env->arch) is one of:

[acme@jouet linux]$ objdump -m 2>&1|grep 'objdump: supported' 
objdump: supported targets: elf64-x86-64 elf32-i386 elf32-x86-64 a.out-i386-linux pei-i386 pei-x86-64 elf64-l1om elf64-k1om elf64-little elf64-big elf32-little elf32-big plugin srec symbolsrec verilog tekhex binary ihex
objdump: supported architectures: i386 i386:x86-64 i386:x64-32 i8086 i386:intel i386:x86-64:intel i386:x64-32:intel i386:nacl i386:x86-64:nacl i386:x64-32:nacl l1om l1om:intel k1om k1om:intel plugin
[acme@jouet linux]$

- Arnaldo

Re: [PATCH 1/2] perf annotate: generalize handling of ret instructions

[Arnaldo Carvalho de Melo]

Em Fri, Jun 10, 2016 at 06:32:50PM +0530, Naveen N. Rao escreveu:
> Introduce helper to detect ret instructions and use the same in the tui.

Humm, I think this is simpler and equivalent, since so far we didn't had
any need for special handling of "retq"/"ret" instructions:

diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
index 4fc208e82c6f..29cef599a091 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -226,11 +226,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
 				ui_browser__write_nstring(browser, " ", 2);
 			}
 		} else {
-			if (strcmp(dl->name, "retq")) {
-				ui_browser__write_nstring(browser, " ", 2);
-			} else {
+			if (strcmp(dl->name, "retq") == 0 || strcmp(dl->name, "ret") == 0) {
 				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
 				SLsmg_write_char(' ');
+			} else {
+				ui_browser__write_nstring(browser, " ", 2);
 			}
 		}
 
 
> Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
> Cc: Anton Blanchard <anton@ozlabs.org>
> Cc: Michael Ellerman <mpe@ellerman.id.au>
> Cc: Ananth N Mavinakayanahalli <ananth@in.ibm.com>
> Signed-off-by: Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com>
> ---
>  tools/perf/ui/browsers/annotate.c | 20 +++++++++-----------
>  tools/perf/util/annotate.c        | 10 ++++++++++
>  tools/perf/util/annotate.h        |  1 +
>  3 files changed, 20 insertions(+), 11 deletions(-)
> 
> diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
> index 4fc208e..dcfaf7a 100644
> --- a/tools/perf/ui/browsers/annotate.c
> +++ b/tools/perf/ui/browsers/annotate.c
> @@ -222,16 +222,14 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
>  			} else if (ins__is_call(dl->ins)) {
>  				ui_browser__write_graph(browser, SLSMG_RARROW_CHAR);
>  				SLsmg_write_char(' ');
> +			} else if (ins__is_ret(dl->ins)) {
> +				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
> +				SLsmg_write_char(' ');
>  			} else {
>  				ui_browser__write_nstring(browser, " ", 2);
>  			}
>  		} else {
> -			if (strcmp(dl->name, "retq")) {
> -				ui_browser__write_nstring(browser, " ", 2);
> -			} else {
> -				ui_browser__write_graph(browser, SLSMG_LARROW_CHAR);
> -				SLsmg_write_char(' ');
> -			}
> +			ui_browser__write_nstring(browser, " ", 2);
>  		}
>  
>  		disasm_line__scnprintf(dl, bf, sizeof(bf), !annotate_browser__opts.use_offset);
> @@ -842,14 +840,14 @@ show_help:
>  				ui_helpline__puts("Huh? No selection. Report to linux-kernel@vger.kernel.org");
>  			else if (browser->selection->offset == -1)
>  				ui_helpline__puts("Actions are only available for assembly lines.");
> -			else if (!browser->selection->ins) {
> -				if (strcmp(browser->selection->name, "retq"))
> -					goto show_sup_ins;
> +			else if (!browser->selection->ins)
> +				goto show_sup_ins;
> +			else if (ins__is_ret(browser->selection->ins))
>  				goto out;
> -			} else if (!(annotate_browser__jump(browser) ||
> +			else if (!(annotate_browser__jump(browser) ||
>  				     annotate_browser__callq(browser, evsel, hbt))) {
>  show_sup_ins:
> -				ui_helpline__puts("Actions are only available for 'callq', 'retq' & jump instructions.");
> +				ui_helpline__puts("Actions are only available for function call/return & jump/branch instructions.");
>  			}
>  			continue;
>  		case 't':
> diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
> index 7e5a1e8..e871b4e 100644
> --- a/tools/perf/util/annotate.c
> +++ b/tools/perf/util/annotate.c
> @@ -354,6 +354,15 @@ static struct ins_ops nop_ops = {
>  	.scnprintf = nop__scnprintf,
>  };
>  
> +static struct ins_ops ret_ops = {
> +	.scnprintf = ins__raw_scnprintf,
> +};
> +
> +bool ins__is_ret(const struct ins *ins)
> +{
> +	return ins->ops == &ret_ops;
> +}
> +
>  static struct ins instructions[] = {
>  	{ .name = "add",   .ops  = &mov_ops, },
>  	{ .name = "addl",  .ops  = &mov_ops, },
> @@ -444,6 +453,7 @@ static struct ins instructions[] = {
>  	{ .name = "xadd",  .ops  = &mov_ops, },
>  	{ .name = "xbeginl", .ops  = &jump_ops, },
>  	{ .name = "xbeginq", .ops  = &jump_ops, },
> +	{ .name = "retq",  .ops  = &ret_ops, },
>  };
>  
>  static int ins__key_cmp(const void *name, const void *insp)
> diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
> index 9241f8c..720a4c0 100644
> --- a/tools/perf/util/annotate.h
> +++ b/tools/perf/util/annotate.h
> @@ -48,6 +48,7 @@ struct ins {
>  
>  bool ins__is_jump(const struct ins *ins);
>  bool ins__is_call(const struct ins *ins);
> +bool ins__is_ret(const struct ins *ins);
>  int ins__scnprintf(struct ins *ins, char *bf, size_t size, struct ins_operands *ops);
>  
>  struct annotation;
> -- 
> 2.8.2

Re: [PATCH 1/2] perf annotate: generalize handling of ret instructions

[Naveen N. Rao]

On 2016/06/10 10:30AM, Arnaldo Carvalho de Melo wrote:
> Em Fri, Jun 10, 2016 at 06:32:50PM +0530, Naveen N. Rao escreveu:
> > Introduce helper to detect ret instructions and use the same in the tui.

Hi Arnaldo,
Thanks for the review.

> 
> Humm, I think this is simpler and equivalent, since so far we didn't had
> any need for special handling of "retq"/"ret" instructions:
> 
> diff --git a/tools/perf/ui/browsers/annotate.c b/tools/perf/ui/browsers/annotate.c
> index 4fc208e82c6f..29cef599a091 100644
> --- a/tools/perf/ui/browsers/annotate.c
> +++ b/tools/perf/ui/browsers/annotate.c
> @@ -226,11 +226,11 @@ static void annotate_browser__write(struct ui_browser *browser, void *entry, int
>  				ui_browser__write_nstring(browser, " ", 2);
>  			}
>  		} else {
> -			if (strcmp(dl->name, "retq")) {
> -				ui_browser__write_nstring(browser, " ", 2);
> -			} else {
> +			if (strcmp(dl->name, "retq") == 0 || strcmp(dl->name, "ret") == 0) {

This won't work on powerpc since we don't have a "ret" instruction.  
Returning from a function is *usually* done through some variant of a 
branch to LR (Link Register) instruction. This logic is encoded in the 
powerpc-specific ins__find() in the next patch.

That was the motivation in introducing a helper for handling return 
instructions in the tui.

- Naveen