linux-kernel - [PATCH 3/3] perf regs x86: Add X86 support for non-gprs

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-Id: <1557844753-58223-3-git-send-email-kan.liang@linux.intel.com>
Date:   Tue, 14 May 2019 07:39:13 -0700
From:   kan.liang@...ux.intel.com
To:     acme@...nel.org, jolsa@...nel.org, mingo@...hat.com,
        linux-kernel@...r.kernel.org
Cc:     ak@...ux.intel.com, Kan Liang <kan.liang@...ux.intel.com>
Subject: [PATCH 3/3] perf regs x86: Add X86 support for non-gprs

From: Kan Liang <kan.liang@...ux.intel.com>

XMM registers can be collected on Icelake and later platforms.

Add specific has_non_gprs_support(), which creating an event to check if
the kernel and hardware can collect XMM registers.

Add specific non_gprs_mask() to return the mask of XMM registers.

The XMM registers collection is only supported with --int-regs option.

Test on Skylake which doesn't support XMM registers collection. There is
nothing changed.

   #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>]

    -I, --intr-regs[=<any register>]
                          sample selected machine registers on
   interrupt, use '-I?' to list register names

   #perf record -I
   [ perf record: Woken up 1 times to write data ]
   [ perf record: Captured and wrote 0.905 MB perf.data (2520 samples) ]

   #perf evlist -v
   cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type:
   IP|TID|TIME|CPU|PERIOD|REGS_INTR, read_format: ID, disabled: 1,
   inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3,
   sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol:
   1, bpf_event: 1, sample_regs_intr: 0xff0fff

Test on Icelake which support XMM registers collection.

   #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

   #perf record -I
   [ perf record: Woken up 1 times to write data ]
   [ perf record: Captured and wrote 0.800 MB perf.data (318 samples) ]

   #perf evlist -v
   cycles: size: 112, { sample_period, sample_freq }: 4000, sample_type:
   IP|TID|TIME|CPU|PERIOD|REGS_INTR, read_format: ID, disabled: 1,
   inherit: 1, mmap: 1, comm: 1, freq: 1, task: 1, precise_ip: 3,
   sample_id_all: 1, exclude_guest: 1, mmap2: 1, comm_exec: 1, ksymbol:
   1, bpf_event: 1, sample_regs_intr: 0xffffffff00ff0fff

Signed-off-by: Kan Liang <kan.liang@...ux.intel.com>
---
 tools/perf/arch/x86/include/perf_regs.h |  1 +
 tools/perf/arch/x86/util/perf_regs.c    | 36 +++++++++++++++++++++++++++++++++
 2 files changed, 37 insertions(+)

diff --git a/tools/perf/arch/x86/include/perf_regs.h b/tools/perf/arch/x86/include/perf_regs.h
index b732133..b7cd91a 100644
--- a/tools/perf/arch/x86/include/perf_regs.h
+++ b/tools/perf/arch/x86/include/perf_regs.h
@@ -9,6 +9,7 @@
 void perf_regs_load(u64 *regs);
 
 #define PERF_REGS_MAX PERF_REG_X86_XMM_MAX
+#define PERF_XMM_REGS_MASK	(~((1ULL << PERF_REG_X86_XMM0) - 1))
 #ifndef HAVE_ARCH_X86_64_SUPPORT
 #define PERF_REGS_MASK ((1ULL << PERF_REG_X86_32_MAX) - 1)
 #define PERF_SAMPLE_REGS_ABI PERF_SAMPLE_REGS_ABI_32
diff --git a/tools/perf/arch/x86/util/perf_regs.c b/tools/perf/arch/x86/util/perf_regs.c
index 71d7604..963b126 100644
--- a/tools/perf/arch/x86/util/perf_regs.c
+++ b/tools/perf/arch/x86/util/perf_regs.c
@@ -270,3 +270,39 @@ int arch_sdt_arg_parse_op(char *old_op, char **new_op)
 
 	return SDT_ARG_VALID;
 }
+
+bool has_non_gprs_support(bool intr)
+{
+	struct perf_event_attr attr = {
+		.type			= PERF_TYPE_HARDWARE,
+		.config			= PERF_COUNT_HW_CPU_CYCLES,
+		.sample_period		= 1,
+		.sample_type		= PERF_SAMPLE_REGS_INTR,
+		.sample_regs_intr	= PERF_XMM_REGS_MASK,
+		.precise_ip		= 1,
+		.disabled 		= 1,
+		.exclude_kernel		= 1,
+	};
+	int fd;
+
+	if (!intr)
+		return false;
+
+	event_attr_init(&attr);
+
+	fd = sys_perf_event_open(&attr, 0, -1, -1, 0);
+	if (fd != -1) {
+		close(fd);
+		return true;
+	}
+
+	return false;
+}
+
+u64 non_gprs_mask(bool intr)
+{
+	if (intr)
+		return PERF_XMM_REGS_MASK;
+
+	return 0;
+}
-- 
2.7.4