linux-kernel - [PATCH 10/11] iommu/vt-d: Add cache invalidation latency sampling

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Date:   Thu, 20 May 2021 11:15:30 +0800
From:   Lu Baolu <baolu.lu@...ux.intel.com>
To:     Joerg Roedel <joro@...tes.org>
Cc:     ashok.raj@...el.com, kevin.tian@...el.com, jacob.jun.pan@...el.com,
        Jean-Philippe Brucker <jean-philippe@...aro.org>,
        iommu@...ts.linux-foundation.org, linux-kernel@...r.kernel.org,
        Lu Baolu <baolu.lu@...ux.intel.com>
Subject: [PATCH 10/11] 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: Lu Baolu <baolu.lu@...ux.intel.com>
---
 drivers/iommu/intel/dmar.c | 31 +++++++++++++++++++++++++++++++
 1 file changed, 31 insertions(+)

diff --git a/drivers/iommu/intel/dmar.c b/drivers/iommu/intel/dmar.c
index 1e31e6799d5c..59ea07d5d70a 100644
--- a/drivers/iommu/intel/dmar.c
+++ b/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 {
@@ -1340,15 +1341,33 @@ 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;
 
@@ -1423,6 +1442,18 @@ 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;
 }
 
-- 
2.25.1