[PATCH 12/73] perf tools x86: Add support for recording and printing XMM registers
From: Arnaldo Carvalho de Melo
Date: Fri May 17 2019 - 15:39:29 EST
From: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Icelake and later platforms support collecting XMM registers with PEBS
event.
Add support for 'perf script' to dump them, and support for the register
parser in 'perf record -I=' ... to configure them.
For now they are just printed in hex, we could potentially later add
other formats too.
Committer testing:
Before:
# perf record -IXMM0
Warning:
unknown register XMM0, check man page or run 'perf record -I?'
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
#
# perf record -I?
available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
#
After:
# perf record -IXMM0
Error:
The sys_perf_event_open() syscall returned with 22 (Invalid argument) for event (cycles).
/bin/dmesg | grep -i perf may provide additional information.
#
# perf record -I?
available registers: AX BX CX DX SI DI BP SP IP FLAGS CS SS R8 R9 R10 R11 R12 R13 R14 R15 XMM0 XMM1 XMM2 XMM3 XMM4 XMM5 XMM6 XMM7 XMM8 XMM9 XMM10 XMM11 XMM12 XMM13 XMM14 XMM15
Usage: perf record [<options>] [<command>]
or: perf record [<options>] -- <command> [<options>]
-I, --intr-regs[=<any register>]
sample selected machine registers on interrupt, use -I ? to list register names
#
More work is needed to, when faced with such error, warn the user that
that register is not available on the running platform.
Signed-off-by: Andi Kleen <ak@xxxxxxxxxxxxxxx>
Tested-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
Cc: Alexander Shishkin <alexander.shishkin@xxxxxxxxxxxxxxx>
Cc: Jiri Olsa <jolsa@xxxxxxxxxx>
Cc: Peter Zijlstra <peterz@xxxxxxxxxxxxx>
Link: http://lkml.kernel.org/r/20190506141926.13659-1-kan.liang@xxxxxxxxxxxxxxx
Signed-off-by: Kan Liang <kan.liang@xxxxxxxxxxxxxxx>
Signed-off-by: Arnaldo Carvalho de Melo <acme@xxxxxxxxxx>
---
tools/perf/arch/x86/include/perf_regs.h | 25 +++++++++++++++++++++++--
tools/perf/arch/x86/util/perf_regs.c | 16 ++++++++++++++++
tools/perf/util/perf_regs.h | 1 +
3 files changed, 40 insertions(+), 2 deletions(-)
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 7f6d538f8a89..b7321337d100 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -8,9 +8,9 @@
void perf_regs_load(u64 *regs);
+#define PERF_REGS_MAX PERF_REG_X86_XMM_MAX
#ifndef HAVE_ARCH_X86_64_SUPPORT
#define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
-#define PERF_REGS_MAX PERF_REG_X86_32_MAX
#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
#else
#define REG_NOSUPPORT ((1ULL << PERF_REG_X86_DS) | \
@@ -18,7 +18,6 @@ void perf_regs_load(u64 *regs);
(1ULL << PERF_REG_X86_FS) | \
(1ULL << PERF_REG_X86_GS))
#define PERF_REGS_MASK (((1ULL << PERF_REG_X86_64_MAX) - 1) & ~REG_NOSUPPORT)
-#define PERF_REGS_MAX PERF_REG_X86_64_MAX
#define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_64
#endif
#define PERF_REG_IP PERF_REG_X86_IP
@@ -77,6 +76,28 @@ static inline const char *perf_reg_name(int id)
case PERF_REG_X86_R15:
return "R15";
#endif /* HAVE_ARCH_X86_64_SUPPORT */
+
+#define XMM(x) \
+ case PERF_REG_X86_XMM ## x: \
+ case PERF_REG_X86_XMM ## x + 1: \
+ return "XMM" #x;
+ XMM(0)
+ XMM(1)
+ XMM(2)
+ XMM(3)
+ XMM(4)
+ XMM(5)
+ XMM(6)
+ XMM(7)
+ XMM(8)
+ XMM(9)
+ XMM(10)
+ XMM(11)
+ XMM(12)
+ XMM(13)
+ XMM(14)
+ XMM(15)
+#undef XMM
default:
return NULL;
}
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index fead6b3b4206..71d7604dbf0b 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -31,6 +31,22 @@ const struct sample_reg sample_reg_masks[] = {
SMPL_REG(R14, PERF_REG_X86_R14),
SMPL_REG(R15, PERF_REG_X86_R15),
#endif
+ SMPL_REG2(XMM0, PERF_REG_X86_XMM0),
+ SMPL_REG2(XMM1, PERF_REG_X86_XMM1),
+ SMPL_REG2(XMM2, PERF_REG_X86_XMM2),
+ SMPL_REG2(XMM3, PERF_REG_X86_XMM3),
+ SMPL_REG2(XMM4, PERF_REG_X86_XMM4),
+ SMPL_REG2(XMM5, PERF_REG_X86_XMM5),
+ SMPL_REG2(XMM6, PERF_REG_X86_XMM6),
+ SMPL_REG2(XMM7, PERF_REG_X86_XMM7),
+ SMPL_REG2(XMM8, PERF_REG_X86_XMM8),
+ SMPL_REG2(XMM9, PERF_REG_X86_XMM9),
+ SMPL_REG2(XMM10, PERF_REG_X86_XMM10),
+ SMPL_REG2(XMM11, PERF_REG_X86_XMM11),
+ SMPL_REG2(XMM12, PERF_REG_X86_XMM12),
+ SMPL_REG2(XMM13, PERF_REG_X86_XMM13),
+ SMPL_REG2(XMM14, PERF_REG_X86_XMM14),
+ SMPL_REG2(XMM15, PERF_REG_X86_XMM15),
SMPL_REG_END
};
diff --git a/tools/perf/util/perf_regs.h b/tools/perf/util/perf_regs.h
index c9319f8d17a6..1a15a4bfc28d 100644
--- a/tools/perf/util/perf_regs.h
+++ b/tools/perf/util/perf_regs.h
@@ -12,6 +12,7 @@ struct sample_reg {
uint64_t mask;
};
#define SMPL_REG(n, b) { .name = #n, .mask = 1ULL << (b) }
+#define SMPL_REG2(n, b) { .name = #n, .mask = 3ULL << (b) }
#define SMPL_REG_END { .name = NULL }
extern const struct sample_reg sample_reg_masks[];
--
2.20.1