perf, x86: Implement initial P4 PMU driver

The netburst PMU is way different from the "architectural
perfomance monitoring" specification that current CPUs use.
P4 uses a tuple of ESCR+CCCR+COUNTER MSR registers to handle
perfomance monitoring events.

A few implementational details:

1) We need a separate x86_pmu::hw_config helper in struct
   x86_pmu since register bit-fields are quite different from P6,
   Core and later cpu series.

2) For the same reason is a x86_pmu::schedule_events helper
   introduced.

3) hw_perf_event::config consists of packed ESCR+CCCR values.
   It's allowed since in reality both registers only use a half
   of their size. Of course before making a real write into a
   particular MSR we need to unpack the value and extend it to
   a proper size.

4) The tuple of packed ESCR+CCCR in hw_perf_event::config
   doesn't describe the memory address of ESCR MSR register
   so that we need to keep a mapping between these tuples
   used and available ESCR (various P4 events may use same
   ESCRs but not simultaneously), for this sake every active
   event has a per-cpu map of hw_perf_event::idx <--> ESCR
   addresses.

5) Since hw_perf_event::idx is an offset to counter/control register
   we need to lift X86_PMC_MAX_GENERIC up, otherwise kernel
   strips it down to 8 registers and event armed may never be turned
   off (ie the bit in active_mask is set but the loop never reaches
   this index to check), thanks to Peter Zijlstra

Restrictions:

 - No cascaded counters support (do we ever need them?)
 - No dependent events support (so PERF_COUNT_HW_INSTRUCTIONS
   doesn't work for now)
 - There are events with same counters which can't work simultaneously
   (need to use intersected ones due to broken counter 1)
 - No PERF_COUNT_HW_CACHE_ events yet

Todo:

 - Implement dependent events
 - Need proper hashing for event opcodes (no linear search, good for
   debugging stage but not in real loads)
 - Some events counted during a clock cycle -- need to set threshold
   for them and count every clock cycle just to get summary statistics
   (ie to behave the same way as other PMUs do)
 - Need to swicth to use event_constraints
 - To support RAW events we need to encode a global list of P4 events
   into p4_templates
 - Cache events need to be added

Event support status matrix:

 Event			status
 -----------------------------
 cycles			works
 cache-references	works
 cache-misses		works
 branch-misses		works
 bus-cycles		partially (does not work on 64bit cpu with HT enabled)
 instruction		doesnt work (needs dependent event [mop tagging])
 branches		doesnt work

Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org>
Signed-off-by: Lin Ming <ming.m.lin@intel.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Arnaldo Carvalho de Melo <acme@redhat.com>
Cc: Stephane Eranian <eranian@google.com>
Cc: Robert Richter <robert.richter@amd.com>
Cc: Frederic Weisbecker <fweisbec@gmail.com>
LKML-Reference: <20100311165439.GB5129@lenovo>
Signed-off-by: Ingo Molnar <mingo@elte.hu>

1 files changed, 29 insertions, 17 deletions

diff --git a/arch/x86/kernel/cpu/perf_event.c b/arch/x86/kernel/cpu/perf_event.c
index e24f6374f9f5..e6a3f5f81c96 100644
--- a/arch/x86/kernel/cpu/perf_event.c
+++ b/arch/x86/kernel/cpu/perf_event.c
@@ -190,6 +190,8 @@ struct x86_pmu {
 	void		(*enable_all)(void);
 	void		(*enable)(struct perf_event *);
 	void		(*disable)(struct perf_event *);
+	int		(*hw_config)(struct perf_event_attr *attr, struct hw_perf_event *hwc);
+	int		(*schedule_events)(struct cpu_hw_events *cpuc, int n, int *assign);
 	unsigned	eventsel;
 	unsigned	perfctr;
 	u64		(*event_map)(int);
@@ -415,6 +417,25 @@ set_ext_hw_attr(struct hw_perf_event *hwc, struct perf_event_attr *attr)
 	return 0;
 }
 
+static int x86_hw_config(struct perf_event_attr *attr, struct hw_perf_event *hwc)
+{
+	/*
+	 * Generate PMC IRQs:
+	 * (keep 'enabled' bit clear for now)
+	 */
+	hwc->config = ARCH_PERFMON_EVENTSEL_INT;
+
+	/*
+	 * Count user and OS events unless requested not to
+	 */
+	if (!attr->exclude_user)
+		hwc->config |= ARCH_PERFMON_EVENTSEL_USR;
+	if (!attr->exclude_kernel)
+		hwc->config |= ARCH_PERFMON_EVENTSEL_OS;
+
+	return 0;
+}
+
 /*
  * Setup the hardware configuration for a given attr_type
  */
@@ -446,23 +467,13 @@ static int __hw_perf_event_init(struct perf_event *event)
 
 	event->destroy = hw_perf_event_destroy;
 
-	/*
-	 * Generate PMC IRQs:
-	 * (keep 'enabled' bit clear for now)
-	 */
-	hwc->config = ARCH_PERFMON_EVENTSEL_INT;
-
 	hwc->idx = -1;
 	hwc->last_cpu = -1;
 	hwc->last_tag = ~0ULL;
 
-	/*
-	 * Count user and OS events unless requested not to.
-	 */
-	if (!attr->exclude_user)
-		hwc->config |= ARCH_PERFMON_EVENTSEL_USR;
-	if (!attr->exclude_kernel)
-		hwc->config |= ARCH_PERFMON_EVENTSEL_OS;
+	/* Processor specifics */
+	if (x86_pmu.hw_config(attr, hwc))
+		return -EOPNOTSUPP;
 
 	if (!hwc->sample_period) {
 		hwc->sample_period = x86_pmu.max_period;
@@ -517,7 +528,7 @@ static int __hw_perf_event_init(struct perf_event *event)
 			return -EOPNOTSUPP;
 
 		/* BTS is currently only allowed for user-mode. */
-		if (hwc->config & ARCH_PERFMON_EVENTSEL_OS)
+		if (!attr->exclude_kernel)
 			return -EOPNOTSUPP;
 	}
 
@@ -931,7 +942,7 @@ static int x86_pmu_enable(struct perf_event *event)
 	if (n < 0)
 		return n;
 
-	ret = x86_schedule_events(cpuc, n, assign);
+	ret = x86_pmu.schedule_events(cpuc, n, assign);
 	if (ret)
 		return ret;
 	/*
@@ -1263,7 +1274,7 @@ int hw_perf_group_sched_in(struct perf_event *leader,
 	if (n0 < 0)
 		return n0;
 
-	ret = x86_schedule_events(cpuc, n0, assign);
+	ret = x86_pmu.schedule_events(cpuc, n0, assign);
 	if (ret)
 		return ret;
 
@@ -1313,6 +1324,7 @@ undo:
 
 #include "perf_event_amd.c"
 #include "perf_event_p6.c"
+#include "perf_event_p4.c"
 #include "perf_event_intel_lbr.c"
 #include "perf_event_intel_ds.c"
 #include "perf_event_intel.c"
@@ -1515,7 +1527,7 @@ static int validate_group(struct perf_event *event)
 
 	fake_cpuc->n_events = n;
 
-	ret = x86_schedule_events(fake_cpuc, n, NULL);
+	ret = x86_pmu.schedule_events(fake_cpuc, n, NULL);
 
 out_free:
 	kfree(fake_cpuc);