linux-kernel - Re: [RFC] perf: need to expose sched_clock to correlate user samples with kernel samples

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: <1365009558.26858.19.camel@hornet>
Date:	Wed, 03 Apr 2013 18:19:18 +0100
From:	Pawel Moll <pawel.moll@....com>
To:	John Stultz <john.stultz@...aro.org>
Cc:	Peter Zijlstra <peterz@...radead.org>,
	David Ahern <dsahern@...il.com>,
	Stephane Eranian <eranian@...gle.com>,
	Thomas Gleixner <tglx@...utronix.de>,
	LKML <linux-kernel@...r.kernel.org>,
	"mingo@...e.hu" <mingo@...e.hu>, Paul Mackerras <paulus@...ba.org>,
	Anton Blanchard <anton@...ba.org>,
	Will Deacon <Will.Deacon@....com>,
	"ak@...ux.intel.com" <ak@...ux.intel.com>,
	Pekka Enberg <penberg@...il.com>,
	Steven Rostedt <rostedt@...dmis.org>,
	Robert Richter <robert.richter@....com>
Subject: Re: [RFC] perf: need to expose sched_clock to correlate user
 samples with kernel samples

On Tue, 2013-04-02 at 17:19 +0100, John Stultz wrote:
> But if we're going to have to do 
> this via a clockid, I'm going to want it to be done via a dynamic posix 
> clockid, so its clear its tightly tied with perf and not considered a 
> generic interface (and I can clearly point folks having problems to the 
> perf maintainers ;).

Ok, so how about the code below?

There are two distinct parts of the "solution":

1. The dynamic posix clock, as you suggested. Then one can get the perf
timestamp by doing:

	clock_fd = open("/dev/perf-clock", O_RDONLY);
	clock_gettime(FD_TO_CLOCKID(clock_fd), &ts) 

2. A sort-of-hack in the get_posix_clock() function making it possible
to do the same using the perf event file descriptor, eg.:

	fd = sys_perf_event_open(&attr, -1, 0, -1, 0);
	clock_gettime(FD_TO_CLOCKID(fd), &ts) 

Any (either strong or not) opinions?

Pawel

8<--------------
diff --git a/include/linux/perf_event.h b/include/linux/perf_event.h
index e47ee46..b2127e3 100644
--- a/include/linux/perf_event.h
+++ b/include/linux/perf_event.h
@@ -52,6 +52,7 @@ struct perf_guest_info_callbacks {
 #include <linux/atomic.h>
 #include <linux/sysfs.h>
 #include <linux/perf_regs.h>
+#include <linux/posix-clock.h>
 #include <asm/local.h>
 
 struct perf_callchain_entry {
@@ -845,4 +846,6 @@ _name##_show(struct device *dev,					\
 									\
 static struct device_attribute format_attr_##_name = __ATTR_RO(_name)
 
+struct posix_clock *perf_get_posix_clock(struct file *fp);
+
 #endif /* _LINUX_PERF_EVENT_H */
diff --git a/kernel/events/core.c b/kernel/events/core.c
index b0cd865..534cb43 100644
--- a/kernel/events/core.c
+++ b/kernel/events/core.c
@@ -7446,6 +7446,49 @@ unlock:
 }
 device_initcall(perf_event_sysfs_init);
 
+static int perf_posix_clock_getres(struct posix_clock *pc, struct timespec *tp)
+{
+	*tp = ns_to_timespec(TICK_NSEC);
+	return 0;
+}
+
+static int perf_posix_clock_gettime(struct posix_clock *pc, struct timespec *tp)
+{
+	*tp = ns_to_timespec(perf_clock());
+	return 0;
+}
+
+static const struct posix_clock_operations perf_posix_clock_ops = {
+	.clock_getres = perf_posix_clock_getres,
+	.clock_gettime = perf_posix_clock_gettime,
+};
+
+static struct posix_clock perf_posix_clock;
+
+struct posix_clock *perf_get_posix_clock(struct file *fp)
+{
+	if (!fp || fp->f_op != &perf_fops)
+		return NULL;
+
+	down_read(&perf_posix_clock.rwsem);
+
+	return &perf_posix_clock;
+}
+
+static int __init perf_posix_clock_init(void)
+{
+	dev_t devt;
+	int ret;
+
+	ret = alloc_chrdev_region(&devt, 0, 1, "perf-clock");
+	if (ret)
+		return ret;
+
+	perf_posix_clock.ops = perf_posix_clock_ops;
+	return posix_clock_register(&perf_posix_clock, devt);
+}
+device_initcall(perf_posix_clock_init);
+
 #ifdef CONFIG_CGROUP_PERF
 static struct cgroup_subsys_state *perf_cgroup_css_alloc(struct cgroup *cont)
 {
diff --git a/kernel/time/posix-clock.c b/kernel/time/posix-clock.c
index ce033c7..e2a40a5 100644
--- a/kernel/time/posix-clock.c
+++ b/kernel/time/posix-clock.c
@@ -20,6 +20,7 @@
 #include <linux/device.h>
 #include <linux/export.h>
 #include <linux/file.h>
+#include <linux/perf_event.h>
 #include <linux/posix-clock.h>
 #include <linux/slab.h>
 #include <linux/syscalls.h>
@@ -249,16 +250,21 @@ struct posix_clock_desc {
 static int get_clock_desc(const clockid_t id, struct posix_clock_desc *cd)
 {
 	struct file *fp = fget(CLOCKID_TO_FD(id));
+	struct posix_clock *perf_clk = NULL;
 	int err = -EINVAL;
 
 	if (!fp)
 		return err;
 
-	if (fp->f_op->open != posix_clock_open || !fp->private_data)
+#if defined(CONFIG_PERF_EVENTS)
+	perf_clk = perf_get_posix_clock(fp);
+#endif
+	if ((fp->f_op->open != posix_clock_open || !fp->private_data) &&
+			!perf_clk)
 		goto out;
 
 	cd->fp = fp;
-	cd->clk = get_posix_clock(fp);
+	cd->clk = perf_clk ? perf_clk : get_posix_clock(fp);
 
 	err = cd->clk ? 0 : -ENODEV;
 out:



--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@...r.kernel.org
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/