powerpc/perf: Adds support for programming of Thresholding in P10

Thresholding, a performance monitoring unit feature, can be
used to identify marked instructions which take more than
expected cycles between start event and end event.
Threshold compare (thresh_cmp) bits are programmed in MMCRA
register. In Power9, thresh_cmp bits were part of the
event code. But in case of P10, thresh_cmp are not part of
event code due to inclusion of MMCR3 bits.

Patch here adds an option to use attr.config1 variable
to be used to pass thresh_cmp value to be programmed in
MMCRA register. A new ppmu flag called PPMU_HAS_ATTR_CONFIG1
has been added and this flag is used to notify the use of
attr.config1 variable.

Patch has extended the parameter list of 'compute_mmcr',
to include power_pmu's 'flags' element and parameter list of
get_constraint to include attr.config1 value. It also extend
parameter list of power_check_constraints inorder to pass
perf_event list.

As stated by commit ef0e3b650f8d ("powerpc/perf: Fix Threshold
Event Counter Multiplier width for P10"), constraint bits for
thresh_cmp is also needed to be increased to 11 bits, which is
handled as part of this patch. We added bit number 53 as part
of constraint bits of thresh_cmp for power10 to make it an
11 bit field.

Updated layout for p10:

/*
 * Layout of constraint bits:
 *
 *        60        56        52        48        44        40        36        32
 * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
 *   [   fab_match   ]         [       thresh_cmp      ] [   thresh_ctl    ] [   ]
 *                                          |                                  |
 *                           [  thresh_cmp bits for p10]           thresh_sel -*
 *
 *        28        24        20        16        12         8         4         0
 * | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - | - - - - |
 *               [ ] |   [ ] |  [  sample ]   [     ]   [6] [5]   [4] [3]   [2] [1]
 *                |  |    |  |                  |
 *      BHRB IFM -*  |    |  |*radix_scope      |      Count of events for each PMC.
 *              EBB -*    |                     |        p1, p2, p3, p4, p5, p6.
 *      L1 I/D qualifier -*                     |
 *                     nc - number of counters -*
 *
 * The PMC fields P1..P6, and NC, are adder fields. As we accumulate constraints
 * we want the low bit of each field to be added to any existing value.
 *
 * Everything else is a value field.
 */

Result:
command#: cat /sys/devices/cpu/format/thresh_cmp
config1:0-17

ex. usage:

command#: perf record -I --weight -d  -e
	 cpu/event=0x67340101EC,thresh_cmp=500/ ./ebizzy -S 2 -t 1 -s 4096
1826636 records/s
real  2.00 s
user  2.00 s
sys   0.00 s
[ perf record: Woken up 1 times to write data ]
[ perf record: Captured and wrote 0.038 MB perf.data (61 samples) ]

Signed-off-by: Kajol Jain <kjain@linux.ibm.com>
Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Link: https://lore.kernel.org/r/20210209095234.837356-1-kjain@linux.ibm.com

1 files changed, 8 insertions, 7 deletions

diff --git a/arch/powerpc/perf/core-book3s.c b/arch/powerpc/perf/core-book3s.c
index 0e31aaa0a0d2..4b4319d84c54 100644
--- a/arch/powerpc/perf/core-book3s.c
+++ b/arch/powerpc/perf/core-book3s.c
@@ -916,7 +916,7 @@ void perf_event_print_debug(void)
  */
 static int power_check_constraints(struct cpu_hw_events *cpuhw,
 				   u64 event_id[], unsigned int cflags[],
-				   int n_ev)
+				   int n_ev, struct perf_event **event)
 {
 	unsigned long mask, value, nv;
 	unsigned long smasks[MAX_HWEVENTS], svalues[MAX_HWEVENTS];
@@ -939,7 +939,7 @@ static int power_check_constraints(struct cpu_hw_events *cpuhw,
 			event_id[i] = cpuhw->alternatives[i][0];
 		}
 		if (ppmu->get_constraint(event_id[i], &cpuhw->amasks[i][0],
-					 &cpuhw->avalues[i][0]))
+					 &cpuhw->avalues[i][0], event[i]->attr.config1))
 			return -1;
 	}
 	value = mask = 0;
@@ -974,7 +974,8 @@ static int power_check_constraints(struct cpu_hw_events *cpuhw,
 		for (j = 1; j < n_alt[i]; ++j)
 			ppmu->get_constraint(cpuhw->alternatives[i][j],
 					     &cpuhw->amasks[i][j],
-					     &cpuhw->avalues[i][j]);
+					     &cpuhw->avalues[i][j],
+					     event[i]->attr.config1);
 	}
 
 	/* enumerate all possibilities and see if any will work */
@@ -1392,7 +1393,7 @@ static void power_pmu_enable(struct pmu *pmu)
 	memset(&cpuhw->mmcr, 0, sizeof(cpuhw->mmcr));
 
 	if (ppmu->compute_mmcr(cpuhw->events, cpuhw->n_events, hwc_index,
-			       &cpuhw->mmcr, cpuhw->event)) {
+			       &cpuhw->mmcr, cpuhw->event, ppmu->flags)) {
 		/* shouldn't ever get here */
 		printk(KERN_ERR "oops compute_mmcr failed\n");
 		goto out;
@@ -1580,7 +1581,7 @@ static int power_pmu_add(struct perf_event *event, int ef_flags)
 
 	if (check_excludes(cpuhw->event, cpuhw->flags, n0, 1))
 		goto out;
-	if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1))
+	if (power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n0 + 1, cpuhw->event))
 		goto out;
 	event->hw.config = cpuhw->events[n0];
 
@@ -1790,7 +1791,7 @@ static int power_pmu_commit_txn(struct pmu *pmu)
 	n = cpuhw->n_events;
 	if (check_excludes(cpuhw->event, cpuhw->flags, 0, n))
 		return -EAGAIN;
-	i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n);
+	i = power_check_constraints(cpuhw, cpuhw->events, cpuhw->flags, n, cpuhw->event);
 	if (i < 0)
 		return -EAGAIN;
 
@@ -2028,7 +2029,7 @@ static int power_pmu_event_init(struct perf_event *event)
 	local_irq_save(irq_flags);
 	cpuhw = this_cpu_ptr(&cpu_hw_events);
 
-	err = power_check_constraints(cpuhw, events, cflags, n + 1);
+	err = power_check_constraints(cpuhw, events, cflags, n + 1, ctrs);
 
 	if (has_branch_stack(event)) {
 		u64 bhrb_filter = -1;