From 3149733584c8f0ab828eada539df7aa488c023a9 Mon Sep 17 00:00:00 2001
From: Ravi Bangoria <ravi.bangoria@amd.com>
Date: Sat, 11 Sep 2021 10:08:54 +0530
Subject: [PATCH] perf annotate: Add fusion logic for AMD microarchs
MIME-Version: 1.0
Content-Type: text/plain; charset=utf8
Content-Transfer-Encoding: 8bit

AMD family 15h and above microarchs fuse a subset of cmp/test/ALU
instructions with branch instructions[1][2]. Add perf annotate
fused instruction support for these microarchs.

Before:
         │       testb  $0x80,0x51(%rax)
         │    ┌──jne    5b3
    0.78 │    │  mov    %r13,%rdi
         │    │→ callq  mark_page_accessed
    1.08 │5b3:└─→mov    0x8(%r13),%rax

After:
         │    ┌──testb  $0x80,0x51(%rax)
         │    ├──jne    5b3
    0.78 │    │  mov    %r13,%rdi
         │    │→ callq  mark_page_accessed
    1.08 │5b3:└─→mov    0x8(%r13),%rax

[1] https://bugzilla.kernel.org/attachment.cgi?id=298553
[2] https://bugzilla.kernel.org/attachment.cgi?id=298555

Committer testing:

On a:

  $ grep -m1 "model name" /proc/cpuinfo
  model name	: AMD Ryzen 9 3900X 12-Core Processor
  $

  Samples: 44K of event 'cycles', 4000 Hz, Event count (approx.): 7533249650
  _int_malloc  /usr/lib64/libc-2.33.so [Percent: local period]
  Percent│    ┌──test   %eax,%eax
         │    ├──jne    884
         │    │↓ jmpq   943
         │    │  nop
         │878:│  add    $0x10,%rdx
    0.64 │    │  add    %eax,%eax
    0.57 │    │↓ je     cc9
    0.77 │884:└─→test   %esi,%eax
         │     ↑ je     878
         │       mov    0x18(%rdx),%r15

Reported-by: Kim Phillips <kim.phillips@amd.com>
Signed-off-by: Ravi Bangoria <ravi.bangoria@amd.com>
Tested-by: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jin Yao <yao.jin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Link: https //lore.kernel.org/r/20210911043854.8373-2-ravi.bangoria@amd.com
Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com>
---
 tools/perf/arch/x86/annotate/instructions.c | 28 +++++++++++++++++++++++++++-
 tools/perf/util/annotate.c                  |  1 -
 2 files changed, 27 insertions(+), 2 deletions(-)

diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 24ea12e..3058726 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c
@@ -144,9 +144,32 @@ static struct ins x86__instructions[] = {
 	{ .name = "xorps",	.ops = &mov_ops, },
 };
 
-static bool x86__ins_is_fused(struct arch *arch, const char *ins1,
+static bool amd__ins_is_fused(struct arch *arch, const char *ins1,
 			      const char *ins2)
 {
+	if (strstr(ins2, "jmp"))
+		return false;
+
+	/* Family >= 15h supports cmp/test + branch fusion */
+	if (arch->family >= 0x15 && (strstarts(ins1, "test") ||
+	    (strstarts(ins1, "cmp") && !strstr(ins1, "xchg")))) {
+		return true;
+	}
+
+	/* Family >= 19h supports some ALU + branch fusion */
+	if (arch->family >= 0x19 && (strstarts(ins1, "add") ||
+	    strstarts(ins1, "sub") || strstarts(ins1, "and") ||
+	    strstarts(ins1, "inc") || strstarts(ins1, "dec") ||
+	    strstarts(ins1, "or") || strstarts(ins1, "xor"))) {
+		return true;
+	}
+
+	return false;
+}
+
+static bool intel__ins_is_fused(struct arch *arch, const char *ins1,
+				const char *ins2)
+{
 	if (arch->family != 6 || arch->model < 0x1e || strstr(ins2, "jmp"))
 		return false;
 
@@ -184,6 +207,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid)
 	if (ret == 3) {
 		arch->family = family;
 		arch->model = model;
+		arch->ins_is_fused = strstarts(cpuid, "AuthenticAMD") ?
+					amd__ins_is_fused :
+					intel__ins_is_fused;
 		return 0;
 	}
 
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0bae061..b55f354 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c
@@ -183,7 +183,6 @@ static struct arch architectures[] = {
 		.init = x86__annotate_init,
 		.instructions = x86__instructions,
 		.nr_instructions = ARRAY_SIZE(x86__instructions),
-		.ins_is_fused = x86__ins_is_fused,
 		.objdump =  {
 			.comment_char = '#',
 		},
-- 
2.7.4