All of lore.kernel.org
 help / color / mirror / Atom feed
From: kan.liang@linux.intel.com
To: peterz@infradead.org, acme@kernel.org, mingo@redhat.com,
	linux-kernel@vger.kernel.org
Cc: tglx@linutronix.de, jolsa@kernel.org, eranian@google.com,
	alexander.shishkin@linux.intel.com, ak@linux.intel.com,
	Kan Liang <kan.liang@linux.intel.com>
Subject: [PATCH 19/22] perf, tools: Add support for recording and printing XMM registers
Date: Mon, 18 Mar 2019 14:41:41 -0700	[thread overview]
Message-ID: <20190318214144.4639-20-kan.liang@linux.intel.com> (raw)
In-Reply-To: <20190318214144.4639-1-kan.liang@linux.intel.com>

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>
---
 tools/arch/x86/include/uapi/asm/perf_regs.h | 19 +++++++++++++++
 tools/perf/arch/x86/include/perf_regs.h     | 27 ++++++++++++++++++---
 tools/perf/arch/x86/util/perf_regs.c        | 16 ++++++++++++
 tools/perf/util/perf_regs.h                 |  1 +
 4 files changed, 60 insertions(+), 3 deletions(-)

diff --git a/tools/arch/x86/include/uapi/asm/perf_regs.h b/tools/arch/x86/include/uapi/asm/perf_regs.h
index f3329cabce5c..29a90e4464b2 100644
--- a/tools/arch/x86/include/uapi/asm/perf_regs.h
+++ b/tools/arch/x86/include/uapi/asm/perf_regs.h
@@ -28,6 +28,25 @@ enum perf_event_x86_regs {
 	PERF_REG_X86_R14,
 	PERF_REG_X86_R15,
 
+	/* 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,
+
+	/* This does not include the XMMX registers */
 	PERF_REG_X86_32_MAX = PERF_REG_X86_GS + 1,
 	PERF_REG_X86_64_MAX = PERF_REG_X86_R15 + 1,
 };
diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index 7f6d538f8a89..c6923eb3a0ce 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 64
 #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_REGS_MASK (((1ULL << PERF_REG_X86_32_MAX) - 1))
 #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[];
-- 
2.17.1


  parent reply	other threads:[~2019-03-18 21:44 UTC|newest]

Thread overview: 39+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2019-03-18 21:41 [PATCH 00/22] perf: Add Icelake support kan.liang
2019-03-18 21:41 ` [PATCH 01/22] perf/core: Support outputting registers from a separate array kan.liang
2019-03-19 13:00   ` Peter Zijlstra
2019-03-19 14:13     ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 02/22] perf/x86/intel: Extract memory code PEBS parser for reuse kan.liang
2019-03-19 13:14   ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 03/22] perf/x86/intel: Support adaptive PEBSv4 kan.liang
2019-03-19 14:47   ` Peter Zijlstra
2019-03-19 16:03     ` Andi Kleen
2019-03-19 16:11       ` Peter Zijlstra
2019-03-19 21:20     ` Liang, Kan
2019-03-19 21:38     ` Andi Kleen
2019-03-20 15:58       ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 04/22] perf/x86/lbr: Avoid reading the LBRs when adaptive PEBS handles them kan.liang
2019-03-18 21:41 ` [PATCH 05/22] perf/x86: Support constraint ranges kan.liang
2019-03-19 14:53   ` Peter Zijlstra
2019-03-19 15:27     ` Peter Zijlstra
2019-03-19 15:57     ` Andi Kleen
2019-03-19 16:09       ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 06/22] perf/x86/intel: Add Icelake support kan.liang
2019-03-20  0:08   ` Stephane Eranian
2019-03-20 14:20     ` Liang, Kan
2019-03-18 21:41 ` [PATCH 07/22] perf/x86/intel/cstate: " kan.liang
2019-03-18 21:41 ` [PATCH 08/22] perf/x86/intel/rapl: " kan.liang
2019-03-18 21:41 ` [PATCH 09/22] perf/x86/msr: " kan.liang
2019-03-18 21:41 ` [PATCH 10/22] perf/x86/intel/uncore: Add Intel Icelake uncore support kan.liang
2019-03-18 21:41 ` [PATCH 11/22] perf/core: Support a REMOVE transaction kan.liang
2019-03-19 15:29   ` Peter Zijlstra
2019-03-18 21:41 ` [PATCH 12/22] perf/x86/intel: Basic support for metrics counters kan.liang
2019-03-18 21:41 ` [PATCH 13/22] perf/x86/intel: Support overflows on SLOTS kan.liang
2019-03-18 21:41 ` [PATCH 14/22] perf/x86/intel: Support hardware TopDown metrics kan.liang
2019-03-18 21:41 ` [PATCH 15/22] perf/x86/intel: Set correct weight for topdown subevent counters kan.liang
2019-03-18 21:41 ` [PATCH 16/22] perf/x86/intel: Export new top down events for Icelake kan.liang
2019-03-18 21:41 ` [PATCH 17/22] perf/x86/intel: Disable sampling read slots and topdown kan.liang
2019-03-18 21:41 ` [PATCH 18/22] perf/x86/intel: Support CPUID 10.ECX to disable fixed counters kan.liang
2019-03-18 21:41 ` kan.liang [this message]
2019-03-18 21:41 ` [PATCH 20/22] perf, tools, stat: Support new per thread TopDown metrics kan.liang
2019-03-18 21:41 ` [PATCH 21/22] perf, tools: Add documentation for topdown metrics kan.liang
2019-03-18 21:41 ` [PATCH 22/22] perf vendor events intel: Add JSON files for Icelake kan.liang

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20190318214144.4639-20-kan.liang@linux.intel.com \
    --to=kan.liang@linux.intel.com \
    --cc=acme@kernel.org \
    --cc=ak@linux.intel.com \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=eranian@google.com \
    --cc=jolsa@kernel.org \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mingo@redhat.com \
    --cc=peterz@infradead.org \
    --cc=tglx@linutronix.de \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.