[V4,20/23] perf, tools: Add support for recording and printing XMM registers
diff mbox series

Message ID 20190326160901.4887-21-kan.liang@linux.intel.com
State New
Headers show
Series
  • perf: Add Icelake support
Related show

Commit Message

Liang, Kan March 26, 2019, 4:08 p.m. UTC
From: Andi Kleen <ak@linux.intel.com>

Newer kernel code can collect XMM registers in some cases.
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, could potentially add
other formats too.

Signed-off-by: Andi Kleen <ak@linux.intel.com>
Signed-off-by: Kan Liang <kan.liang@linux.intel.com>
---

Changes since V3:
- Update perf_regs.h accordingly

 tools/arch/x86/include/uapi/asm/perf_regs.h | 23 ++++++++++++++++++-
 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 +
 4 files changed, 62 insertions(+), 3 deletions(-)

Patch
diff mbox series

diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..ac67bbea10ca 100644
--- a/tools/arch/x86/include/uapi/asm/perf_regs.h
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -27,8 +27,29 @@  enum perf_event_x86_regs {
 	PERF_REG_X86_R13,
 	PERF_REG_X86_R14,
 	PERF_REG_X86_R15,
-
+	/* These are the limits for the GPRs. */
 	PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
 	PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
+
+	/* These all need two bits set because they are 128bit */
+	PERF_REG_X86_XMM0  = 32,
+	PERF_REG_X86_XMM1  = 34,
+	PERF_REG_X86_XMM2  = 36,
+	PERF_REG_X86_XMM3  = 38,
+	PERF_REG_X86_XMM4  = 40,
+	PERF_REG_X86_XMM5  = 42,
+	PERF_REG_X86_XMM6  = 44,
+	PERF_REG_X86_XMM7  = 46,
+	PERF_REG_X86_XMM8  = 48,
+	PERF_REG_X86_XMM9  = 50,
+	PERF_REG_X86_XMM10 = 52,
+	PERF_REG_X86_XMM11 = 54,
+	PERF_REG_X86_XMM12 = 56,
+	PERF_REG_X86_XMM13 = 58,
+	PERF_REG_X86_XMM14 = 60,
+	PERF_REG_X86_XMM15 = 62,
+
+	/* These include both GPRs and XMMX registers */
+	PERF_REG_X86_XMM_MAX = PERF_REG_X86_XMM15 + 2,
 };
 #endif /* _ASM_X86_PERF_REGS_H */
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[];