Re: [REGRESSION][BISECTED] Performance Regression in IOMMU/VT-d Since Kernel 6.10

[Baolu Lu]

On 7/2/2025 1:14 PM, Baolu Lu wrote:
> On 7/2/25 01:11, Ioanna Alifieraki wrote:
> > #regzbot introduced: 129dab6e1286
> >
> > Hello everyone,
> >
> > We've identified a performance regression that starts with linux
> > kernel 6.10 and persists through 6.16(tested at commit e540341508ce).
> > Bisection pointed to commit:
> > 129dab6e1286 ("iommu/vt-d: Use cache_tag_flush_range_np() in 
> > iotlb_sync_map").
> >
> > The issue occurs when running fio against two NVMe devices located
> > under the same PCIe bridge (dual-port NVMe configuration). Performance
> > drops compared to configurations where the devices are on different
> > bridges.
> >
> > Observed Performance:
> > - Before the commit: ~6150 MiB/s, regardless of NVMe device placement.
> > - After the commit:
> >    -- Same PCIe bridge: ~4985 MiB/s
> >    -- Different PCIe bridges: ~6150 MiB/s
> >
> >
> > Currently we can only reproduce the issue on a Z3 metal instance on
> > gcp. I suspect the issue can be reproducible if you have a dual port
> > nvme on any machine.
> > At [1] there's a more detailed description of the issue and details
> > on the reproducer.
>
> This test was running on bare metal hardware instead of any
> virtualization guest, right? If that's the case,
> cache_tag_flush_range_np() is almost a no-op.
>
> Can you please show me the capability register of the IOMMU by:
>
> #cat /sys/bus/pci/devices/[pci_dev_name]/iommu/intel-iommu/cap

Also, can you please try whether the below changes make any difference?
I've also attached a patch file to this email so you can apply the
change more easily.

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7aa3932251b2..f60201ee4be0 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1796,6 +1796,18 @@ static int domain_setup_first_level(struct 
intel_iommu *iommu,
 					  (pgd_t *)pgd, flags, old);
 }

+static bool domain_need_iotlb_sync_map(struct dmar_domain *domain,
+				       struct intel_iommu *iommu)
+{
+	if (cap_caching_mode(iommu->cap) && !domain->use_first_level)
+		return true;
+
+	if (rwbf_quirk || cap_rwbf(iommu->cap))
+		return true;
+
+	return false;
+}
+
 static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
@@ -1833,6 +1845,8 @@ static int dmar_domain_attach_device(struct 
dmar_domain *domain,
 	if (ret)
 		goto out_block_translation;

+	domain->iotlb_sync_map |= domain_need_iotlb_sync_map(domain, iommu);
+
 	return 0;

 out_block_translation:
@@ -3945,7 +3959,10 @@ static bool risky_device(struct pci_dev *pdev)
 static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				      unsigned long iova, size_t size)
 {
-	cache_tag_flush_range_np(to_dmar_domain(domain), iova, iova + size - 1);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (dmar_domain->iotlb_sync_map)
+		cache_tag_flush_range_np(dmar_domain, iova, iova + size - 1);

 	return 0;
 }
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 3ddbcc603de2..7ab2c34a5ecc 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -614,6 +614,9 @@ struct dmar_domain {
 	u8 has_mappings:1;		/* Has mappings configured through
 					 * iommu_map() interface.
 					 */
+	u8 iotlb_sync_map:1;		/* Need to flush IOTLB cache or write
+					 * buffer when creating mappings.
+					 */

 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
--
2.43.0

Thanks,
baoluFrom ddc4210a3365147df978bd0bf45d824b9c869877 Mon Sep 17 00:00:00 2001
From: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
Date: Wed, 2 Jul 2025 16:51:48 +0800
Subject: [PATCH 1/1] iommu/vt-d: Avoid unnecessary cache_tag_flush_range_np()

For test purpose only!

Signed-off-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
---
 drivers/iommu/intel/iommu.c | 19 ++++++++++++++++++-
 drivers/iommu/intel/iommu.h |  3 +++
 2 files changed, 21 insertions(+), 1 deletion(-)

diff --git a/drivers/iommu/intel/iommu.c b/drivers/iommu/intel/iommu.c
index 7aa3932251b2..f60201ee4be0 100644
--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -1796,6 +1796,18 @@ static int domain_setup_first_level(struct intel_iommu *iommu,
 					  (pgd_t *)pgd, flags, old);
 }
 
+static bool domain_need_iotlb_sync_map(struct dmar_domain *domain,
+				       struct intel_iommu *iommu)
+{
+	if (cap_caching_mode(iommu->cap) && !domain->use_first_level)
+		return true;
+
+	if (rwbf_quirk || cap_rwbf(iommu->cap))
+		return true;
+
+	return false;
+}
+
 static int dmar_domain_attach_device(struct dmar_domain *domain,
 				     struct device *dev)
 {
@@ -1833,6 +1845,8 @@ static int dmar_domain_attach_device(struct dmar_domain *domain,
 	if (ret)
 		goto out_block_translation;
 
+	domain->iotlb_sync_map |= domain_need_iotlb_sync_map(domain, iommu);
+
 	return 0;
 
 out_block_translation:
@@ -3945,7 +3959,10 @@ static bool risky_device(struct pci_dev *pdev)
 static int intel_iommu_iotlb_sync_map(struct iommu_domain *domain,
 				      unsigned long iova, size_t size)
 {
-	cache_tag_flush_range_np(to_dmar_domain(domain), iova, iova + size - 1);
+	struct dmar_domain *dmar_domain = to_dmar_domain(domain);
+
+	if (dmar_domain->iotlb_sync_map)
+		cache_tag_flush_range_np(dmar_domain, iova, iova + size - 1);
 
 	return 0;
 }
diff --git a/drivers/iommu/intel/iommu.h b/drivers/iommu/intel/iommu.h
index 3ddbcc603de2..7ab2c34a5ecc 100644
--- a/drivers/iommu/intel/iommu.h
+++ b/drivers/iommu/intel/iommu.h
@@ -614,6 +614,9 @@ struct dmar_domain {
 	u8 has_mappings:1;		/* Has mappings configured through
 					 * iommu_map() interface.
 					 */
+	u8 iotlb_sync_map:1;		/* Need to flush IOTLB cache or write
+					 * buffer when creating mappings.
+					 */
 
 	spinlock_t lock;		/* Protect device tracking lists */
 	struct list_head devices;	/* all devices' list */
-- 
2.43.0