[PATCH 1/1] alpha/perf: Account for time spent handling PMU interrupts

[Magnus Lindholm <linmag7@gmail.com>]

Alpha does not report PMU interrupt duration to perf, preventing its
adaptive throttling from reducing an excessively costly sampling rate.

Measure handler time with RPCC and report it to perf_sample_event_took().
Convert cycles using the calibrated frequency selected by time_init();
Alpha's tick-based sched_clock() is too coarse for this measurement.
Wrap the existing handler so all return paths are accounted for, without
changing counter programming or event handling.

Signed-off-by: Magnus Lindholm <linmag7@gmail.com>
---
 arch/alpha/kernel/perf_event.c | 26 ++++++++++++++++++++++++--
 1 file changed, 24 insertions(+), 2 deletions(-)

diff --git a/arch/alpha/kernel/perf_event.c b/arch/alpha/kernel/perf_event.c
index a3eaab094ece..dd3bc70b71d7 100644
--- a/arch/alpha/kernel/perf_event.c
+++ b/arch/alpha/kernel/perf_event.c
@@ -16,8 +16,10 @@
 #include <linux/kdebug.h>
 #include <linux/mutex.h>
 #include <linux/init.h>
+#include <linux/math64.h>
 
 #include <asm/hwrpb.h>
+#include <asm/timex.h>
 #include <linux/atomic.h>
 #include <asm/irq.h>
 #include <asm/irq_regs.h>
@@ -26,6 +28,9 @@
 #include <asm/hw_irq.h>
 
 
+extern unsigned long est_cycle_freq;
+static unsigned long pmu_cycle_freq __read_mostly;
+
 /* The maximum number of PMCs on any Alpha CPU whatsoever. */
 #define MAX_HWEVENTS 3
 #define PMC_NO_INDEX -1
@@ -797,8 +802,8 @@ void perf_event_print_debug(void)
  * Performance Monitoring Interrupt Service Routine called when a PMC
  * overflows.  The PMC that overflowed is passed in la_ptr.
  */
-static void alpha_perf_event_irq_handler(unsigned long la_ptr,
-					struct pt_regs *regs)
+static void alpha_perf_event_irq_inner(unsigned long la_ptr,
+				       struct pt_regs *regs)
 {
 	struct cpu_hw_events *cpuc;
 	struct perf_sample_data data;
@@ -862,6 +867,21 @@ static void alpha_perf_event_irq_handler(unsigned long la_ptr,
 
 
 
+/* sched_clock() is tick-based on Alpha; measure a short same-CPU interval. */
+static void alpha_perf_event_irq_handler(unsigned long la_ptr,
+					 struct pt_regs *regs)
+{
+	u32 start = get_cycles();
+	u32 cycles;
+
+	alpha_perf_event_irq_inner(la_ptr, regs);
+	/* Unsigned subtraction handles a wrap of the low 32-bit counter. */
+	cycles = (u32)get_cycles() - start;
+	if (likely(pmu_cycle_freq))
+		perf_sample_event_took(div64_u64((u64)cycles * NSEC_PER_SEC,
+						 pmu_cycle_freq));
+}
+
 /*
  * Init call to initialise performance events at kernel startup.
  */
@@ -878,6 +898,8 @@ static int __init init_hw_perf_events(void)
 
 	/* Override performance counter IRQ vector */
 
+	/* Match the calibrated frequency selected by time_init(). */
+	pmu_cycle_freq = est_cycle_freq ? est_cycle_freq : hwrpb->cycle_freq;
 	perf_irq = alpha_perf_event_irq_handler;
 
 	/* And set up PMU specification */