perf_counter: add an mmap method to allow userspace to read hardware counters

Impact: new feature giving performance improvement

This adds the ability for userspace to do an mmap on a hardware counter
fd and get access to a read-only page that contains the information
needed to translate a hardware counter value to the full 64-bit
counter value that would be returned by a read on the fd.  This is
useful on architectures that allow user programs to read the hardware
counters, such as PowerPC.

The mmap will only succeed if the counter is a hardware counter
monitoring the current process.

On my quad 2.5GHz PowerPC 970MP machine, userspace can read a counter
and translate it to the full 64-bit value in about 30ns using the
mmapped page, compared to about 830ns for the read syscall on the
counter, so this does give a significant performance improvement.

Signed-off-by: Paul Mackerras <paulus@samba.org>
Signed-off-by: Peter Zijlstra <a.p.zijlstra@chello.nl>
Orig-LKML-Reference: <20090323172417.297057964@chello.nl>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 15 insertions, 0 deletions

diff --git a/include/linux/perf_counter.h b/include/linux/perf_counter.h
index 18dc17d0a61c..40b324e91bf6 100644
--- a/include/linux/perf_counter.h
+++ b/include/linux/perf_counter.h
@@ -143,6 +143,17 @@ struct perf_counter_hw_event {
 #define PERF_COUNTER_IOC_ENABLE		_IO('$', 0)
 #define PERF_COUNTER_IOC_DISABLE	_IO('$', 1)
 
+/*
+ * Structure of the page that can be mapped via mmap
+ */
+struct perf_counter_mmap_page {
+	__u32	version;		/* version number of this structure */
+	__u32	compat_version;		/* lowest version this is compat with */
+	__u32	lock;			/* seqlock for synchronization */
+	__u32	index;			/* hardware counter identifier */
+	__s64	offset;			/* add to hardware counter value */
+};
+
 #ifdef __KERNEL__
 /*
  * Kernel-internal data types and definitions:
@@ -278,6 +289,9 @@ struct perf_counter {
 	int				oncpu;
 	int				cpu;
 
+	/* pointer to page shared with userspace via mmap */
+	unsigned long			user_page;
+
 	/* read() / irq related data */
 	wait_queue_head_t		waitq;
 	/* optional: for NMIs */
@@ -361,6 +375,7 @@ extern int perf_counter_task_enable(void);
 extern int hw_perf_group_sched_in(struct perf_counter *group_leader,
 	       struct perf_cpu_context *cpuctx,
 	       struct perf_counter_context *ctx, int cpu);
+extern void perf_counter_update_userpage(struct perf_counter *counter);
 
 extern void perf_counter_output(struct perf_counter *counter,
 				int nmi, struct pt_regs *regs);