[PATCH 2/2] perf annotate: Add fusion logic for AMD microarchs
From: Ravi Bangoria <hidden>
Date: 2021-09-06 10:57:43
Also in:
lkml
Subsystem:
performance events subsystem, the rest · Maintainers:
Peter Zijlstra, Ingo Molnar, Arnaldo Carvalho de Melo, Namhyung Kim, Linus Torvalds
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
Reported-by: Kim Phillips <redacted>
Signed-off-by: Ravi Bangoria <redacted>
---
tools/perf/arch/x86/annotate/instructions.c | 37 ++++++++++++++++++++-
tools/perf/util/annotate.c | 1 +
2 files changed, 37 insertions(+), 1 deletion(-)
diff --git a/tools/perf/arch/x86/annotate/instructions.c b/tools/perf/arch/x86/annotate/instructions.c
index 24ea12ec7e02..46d7124cc4e1 100644
--- a/tools/perf/arch/x86/annotate/instructions.c
+++ b/tools/perf/arch/x86/annotate/instructions.c@@ -144,8 +144,31 @@ 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;
@@ -172,6 +195,15 @@ static bool x86__ins_is_fused(struct arch *arch, const char *ins1, return false; } +static bool x86__ins_is_fused(struct arch *arch, const char *ins1, + const char *ins2) +{ + if (strstarts(arch->vendor, "AuthenticAMD")) + return amd__ins_is_fused(arch, ins1, ins2); + + return intel__ins_is_fused(arch, ins1, ins2); +} + static int x86__cpuid_parse(struct arch *arch, char *cpuid) { unsigned int family, model, stepping;
@@ -184,6 +216,9 @@ static int x86__cpuid_parse(struct arch *arch, char *cpuid) if (ret == 3) { arch->family = family; arch->model = model; + arch->vendor = strndup(cpuid, 12); + if (!arch->vendor) + return -1; return 0; }
diff --git a/tools/perf/util/annotate.c b/tools/perf/util/annotate.c
index 0bae061b2d6d..88326bb990b5 100644
--- a/tools/perf/util/annotate.c
+++ b/tools/perf/util/annotate.c@@ -77,6 +77,7 @@ struct arch { bool sorted_instructions; bool initialized; void *priv; + char *vendor; unsigned int model; unsigned int family; int (*init)(struct arch *arch, char *cpuid);
--
2.27.0