iommu/vt-d: Add PRQ handling latency sampling

The execution time for page fault request handling is performance critical
and needs to be monitored. This adds code to sample the execution time of
page fault request handling.

Signed-off-by: Lu 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/20210610020115.1637656-17-baolu.lu@linux.intel.com
Signed-off-by: Joerg Roedel <jroedel@suse.de>

diff --git a/drivers/iommu/intel/svm.c b/drivers/iommu/intel/svm.c
index d3d028c..6bff9a7 100644 (file)
--- a/drivers/iommu/intel/svm.c
+++ b/drivers/iommu/intel/svm.c
@@ -24,6 +24,7 @@
 #include <trace/events/intel_iommu.h>
 
 #include "pasid.h"
+#include "perf.h"
 #include "../iommu-sva-lib.h"
 
 static irqreturn_t prq_event_thread(int irq, void *d);
@@ -838,8 +839,8 @@ static int prq_to_iommu_prot(struct page_req_dsc *req)
        return prot;
 }
 
-static int
-intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc)
+static int intel_svm_prq_report(struct intel_iommu *iommu, struct device *dev,
+                               struct page_req_dsc *desc)
 {
        struct iommu_fault_event event;
 
@@ -871,6 +872,12 @@ intel_svm_prq_report(struct device *dev, struct page_req_dsc *desc)
                event.fault.prm.flags |= IOMMU_FAULT_PAGE_REQUEST_PRIV_DATA;
                memcpy(event.fault.prm.private_data, desc->priv_data,
                       sizeof(desc->priv_data));
+       } else if (dmar_latency_enabled(iommu, DMAR_LATENCY_PRQ)) {
+               /*
+                * If the private data fields are not used by hardware, use it
+                * to monitor the prq handle latency.
+                */
+               event.fault.prm.private_data[0] = ktime_to_ns(ktime_get());
        }
 
        return iommu_report_device_fault(dev, &event);
@@ -983,7 +990,7 @@ bad_req:
                 * If prq is to be handled outside iommu driver via receiver of
                 * the fault notifiers, we skip the page response here.
                 */
-               if (intel_svm_prq_report(sdev->dev, req))
+               if (intel_svm_prq_report(iommu, sdev->dev, req))
                        handle_bad_prq_event(iommu, req, QI_RESP_INVALID);
 
                trace_prq_report(iommu, sdev->dev, req->qw_0, req->qw_1,
@@ -1172,6 +1179,9 @@ int intel_svm_page_response(struct device *dev,
                if (private_present)
                        memcpy(&desc.qw2, prm->private_data,
                               sizeof(prm->private_data));
+               else if (prm->private_data[0])
+                       dmar_latency_update(iommu, DMAR_LATENCY_PRQ,
+                               ktime_to_ns(ktime_get()) - prm->private_data[0]);
 
                qi_submit_sync(iommu, &desc, 1, 0);
        }