[PATCH v4 1/2] perf util: Check for fused instruction

[Jin Yao]

Macro fusion merges two instructions to a single micro-op. Intel
core platform performs this hardware optimization under limited
circumstances.

For example, CMP + JCC can be "fused" and executed /retired
together. While with sampling this can result in the sample
sometimes being on the JCC and sometimes on the CMP.
So for the fused instruction pair, they could be considered
together.

On Nehalem, fused instruction pairs:
cmp/test + jcc.

On other new CPU:
cmp/test/add/sub/and/inc/dec + jcc.

This patch adds an x86-specific function which checks if 2
instructions are in a "fused" pair. For non-x86 arch, the
function is just NULL.

Change-log:
-----------
v4: Move the CPU model checking to symbol__disassemble and
    save the CPU family/model in arch structure.

    It avoids checking every time when jump arrow printed.

v3: Add checking for Nehalem (CMP, TEST). For other newer
    Intel CPUs just check it by default (CMP, TEST, ADD,
    SUB, AND, INC, DEC).

v2: Remove the origial weak function. Arnaldo points out
    that doing it as a weak function that will be overridden
    by the host arch doesn't work. So now it's implemented
    as an arch-specific function.

v1: Initial post

Signed-off-by: Jin Yao <yao.jin@xxxxxxxxxxxxxxx>
---
 tools/perf/arch/x86/annotate/instructions.c | 46 +++++++++++++++++++++++++++++
 tools/perf/builtin-top.c                    |  2 +-
 tools/perf/ui/browsers/annotate.c           |  4 ++-
 tools/perf/ui/gtk/annotate.c                |  2 +-
 tools/perf/util/annotate.c                  | 22 ++++++++++++--
 tools/perf/util/annotate.h                  |  3 +-
 6 files changed, 73 insertions(+), 6 deletions(-)

diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index c1625f2..d84b720 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -76,3 +76,49 @@ static struct ins x86__instructions[] = {
 	{ .name = "xbeginq",	.ops = &jump_ops, },
 	{ .name = "retq",	.ops = &ret_ops,  },
 };
+
+static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
+			      const char *ins2)
+{
+	if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp"))
+		return false;
+
+	if (arch->model == 0x1e) {
+		/* Nehalem */
+		if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) ||
+		     strstr(ins1, "test")) {
+			return true;
+		}
+	} else {
+		/* Newer platform */
+		if ((strstr(ins1, "cmp") && !strstr(ins1, "xchg")) ||
+		     strstr(ins1, "test") ||
+		     strstr(ins1, "add") ||
+		     strstr(ins1, "sub") ||
+		     strstr(ins1, "and") ||
+		     strstr(ins1, "inc") ||
+		     strstr(ins1, "dec")) {
+			return true;
+		}
+	}
+
+	return false;
+}
+
+static int x86__cpuid_parse(struct arch *arch, char *cpuid)
+{
+	unsigned int family, model, stepping;
+	int ret;
+
+	/*
+	 * cpuid = "GenuineIntel,family,model,stepping"
+	 */
+	ret = sscanf(cpuid, "%*[^,],%u,%u,%u", &family, &model, &stepping);
+	if (ret == 3) {
+		arch->family = family;
+		arch->model = model;
+		return 0;
+	}
+
+	return -1;
+}
diff --git a/tools/perf/builtin-top.c b/tools/perf/builtin-top.c
index 6052376..022486d 100644
--- a/tools/perf/builtin-top.c
+++ b/tools/perf/builtin-top.c
@@ -134,7 +134,7 @@ static int perf_top__parse_source(struct perf_top *top, struct hist_entry *he)
 		return err;
 	}
 
-	err = symbol__disassemble(sym, map, NULL, 0, NULL);
+	err = symbol__disassemble(sym, map, NULL, 0, NULL, 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 27f41f2..ae05ebb 100644
--- a/tools/perf/ui/browsers/annotate.c
+++ b/tools/perf/ui/browsers/annotate.c
@@ -9,6 +9,7 @@
 #include "../../util/symbol.h"
 #include "../../util/evsel.h"
 #include "../../util/config.h"
+#include "../../util/evlist.h"
 #include <inttypes.h>
 #include <pthread.h>
 #include <linux/kernel.h>
@@ -1074,7 +1075,8 @@ int symbol__tui_annotate(struct symbol *sym, struct map *map,
 	}
 
 	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-				  sizeof_bdl, &browser.arch);
+				  sizeof_bdl, &browser.arch,
+				  evsel->evlist->env->cpuid);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/ui/gtk/annotate.c b/tools/perf/ui/gtk/annotate.c
index d903fd4..87e3760 100644
--- a/tools/perf/ui/gtk/annotate.c
+++ b/tools/perf/ui/gtk/annotate.c
@@ -169,7 +169,7 @@ static int symbol__gtk_annotate(struct symbol *sym, struct map *map,
 		return -1;
 
 	err = symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-				  0, NULL);
+				  0, NULL, NULL);
 	if (err) {
 		char msg[BUFSIZ];
 		symbol__strerror_disassemble(sym, map, err, msg, sizeof(msg));
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index be1caab..8748ebb 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -47,7 +47,12 @@ struct arch {
 	bool		sorted_instructions;
 	bool		initialized;
 	void		*priv;
+	unsigned int	model;
+	unsigned int	family;
 	int		(*init)(struct arch *arch);
+	bool		(*ins_is_fused)(struct arch *arch, const char *ins1,
+					const char *ins2);
+	int		(*cpuid_parse)(struct arch *arch, char *cpuid);
 	struct		{
 		char comment_char;
 		char skip_functions_char;
@@ -129,6 +134,8 @@ static struct arch architectures[] = {
 		.name = "x86",
 		.instructions = x86__instructions,
 		.nr_instructions = ARRAY_SIZE(x86__instructions),
+		.ins_is_fused = x86__ins_is_fused,
+		.cpuid_parse = x86__cpuid_parse,
 		.objdump =  {
 			.comment_char = '#',
 		},
@@ -171,6 +178,14 @@ int ins__scnprintf(struct ins *ins, char *bf, size_t size,
 	return ins__raw_scnprintf(ins, bf, size, ops);
 }
 
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2)
+{
+	if (!arch || !arch->ins_is_fused)
+		return false;
+
+	return arch->ins_is_fused(arch, ins1, ins2);
+}
+
 static int call__parse(struct arch *arch, struct ins_operands *ops, struct map *map)
 {
 	char *endptr, *tok, *name;
@@ -1381,7 +1396,7 @@ static const char *annotate__norm_arch(const char *arch_name)
 
 int symbol__disassemble(struct symbol *sym, struct map *map,
 			const char *arch_name, size_t privsize,
-			struct arch **parch)
+			struct arch **parch, char *cpuid)
 {
 	struct dso *dso = map->dso;
 	char command[PATH_MAX * 2];
@@ -1418,6 +1433,9 @@ int symbol__disassemble(struct symbol *sym, struct map *map,
 		}
 	}
 
+	if (arch->cpuid_parse && cpuid)
+		arch->cpuid_parse(arch, cpuid);
+
 	pr_debug("%s: filename=%s, sym=%s, start=%#" PRIx64 ", end=%#" PRIx64 "\n", __func__,
 		 symfs_filename, sym->name, map->unmap_ip(map, sym->start),
 		 map->unmap_ip(map, sym->end));
@@ -1907,7 +1925,7 @@ int symbol__tty_annotate(struct symbol *sym, struct map *map,
 	u64 len;
 
 	if (symbol__disassemble(sym, map, perf_evsel__env_arch(evsel),
-				0, NULL) < 0)
+				0, NULL, NULL) < 0)
 		return -1;
 
 	len = symbol__size(sym);
diff --git a/tools/perf/util/annotate.h b/tools/perf/util/annotate.h
index 2105503..72d7272 100644
--- a/tools/perf/util/annotate.h
+++ b/tools/perf/util/annotate.h
@@ -53,6 +53,7 @@ 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);
+bool ins__is_fused(struct arch *arch, const char *ins1, const char *ins2);
 
 struct annotation;
 
@@ -160,7 +161,7 @@ void symbol__annotate_zero_histograms(struct symbol *sym);
 
 int symbol__disassemble(struct symbol *sym, struct map *map,
 			const char *arch_name, size_t privsize,
-			struct arch **parch);
+			struct arch **parch, char *cpuid);
 
 enum symbol_disassemble_errno {
 	SYMBOL_ANNOTATE_ERRNO__SUCCESS		= 0,
-- 
2.7.4