iommu/vt-d: Add cache invalidation latency sampling

Queued invalidation execution time is performance critical and needs
to be monitored. This adds code to sample the execution time of IOTLB/
devTLB/ICE cache invalidation.
Signed-off-by: NLu Baolu <baolu.lu@linux.intel.com>
Link: https://lore.kernel.org/r/20210520031531.712333-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20210610020115.1637656-16-baolu.lu@linux.intel.comSigned-off-by: NJoerg Roedel <jroedel@suse.de>

drivers/iommu/intel/dmar.c

@@ -34,6 +34,7 @@
 #include <trace/events/intel_iommu.h>
 
 #include "../irq_remapping.h"
+#include "perf.h"
 
 typedef int (*dmar_res_handler_t)(struct acpi_dmar_header *, void *);
 struct dmar_res_callback {
@@ -1342,15 +1343,33 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
 		   unsigned int count, unsigned long options)
 {
 	struct q_inval *qi = iommu->qi;
+	s64 devtlb_start_ktime = 0;
+	s64 iotlb_start_ktime = 0;
+	s64 iec_start_ktime = 0;
 	struct qi_desc wait_desc;
 	int wait_index, index;
 	unsigned long flags;
 	int offset, shift;
 	int rc, i;
+	u64 type;
 
 	if (!qi)
 		return 0;
 
+	type = desc->qw0 & GENMASK_ULL(3, 0);
+
+	if ((type == QI_IOTLB_TYPE || type == QI_EIOTLB_TYPE) &&
+	    dmar_latency_enabled(iommu, DMAR_LATENCY_INV_IOTLB))
+		iotlb_start_ktime = ktime_to_ns(ktime_get());
+
+	if ((type == QI_DIOTLB_TYPE || type == QI_DEIOTLB_TYPE) &&
+	    dmar_latency_enabled(iommu, DMAR_LATENCY_INV_DEVTLB))
+		devtlb_start_ktime = ktime_to_ns(ktime_get());
+
+	if (type == QI_IEC_TYPE &&
+	    dmar_latency_enabled(iommu, DMAR_LATENCY_INV_IEC))
+		iec_start_ktime = ktime_to_ns(ktime_get());
+
 restart:
 	rc = 0;
 
@@ -1425,6 +1444,18 @@ int qi_submit_sync(struct intel_iommu *iommu, struct qi_desc *desc,
 	if (rc == -EAGAIN)
 		goto restart;
 
+	if (iotlb_start_ktime)
+		dmar_latency_update(iommu, DMAR_LATENCY_INV_IOTLB,
+				ktime_to_ns(ktime_get()) - iotlb_start_ktime);
+
+	if (devtlb_start_ktime)
+		dmar_latency_update(iommu, DMAR_LATENCY_INV_DEVTLB,
+				ktime_to_ns(ktime_get()) - devtlb_start_ktime);
+
+	if (iec_start_ktime)
+		dmar_latency_update(iommu, DMAR_LATENCY_INV_IEC,
+				ktime_to_ns(ktime_get()) - iec_start_ktime);
+
 	return rc;
 }