linux/drivers/iommu/intel
Lu Baolu fc57475754 iommu/vt-d: Optimize iotlb_sync_map for non-caching/non-RWBF modes
commit 12724ce3fe upstream.

The iotlb_sync_map iommu ops allows drivers to perform necessary cache
flushes when new mappings are established. For the Intel iommu driver,
this callback specifically serves two purposes:

- To flush caches when a second-stage page table is attached to a device
  whose iommu is operating in caching mode (CAP_REG.CM==1).
- To explicitly flush internal write buffers to ensure updates to memory-
  resident remapping structures are visible to hardware (CAP_REG.RWBF==1).

However, in scenarios where neither caching mode nor the RWBF flag is
active, the cache_tag_flush_range_np() helper, which is called in the
iotlb_sync_map path, effectively becomes a no-op.

Despite being a no-op, cache_tag_flush_range_np() involves iterating
through all cache tags of the iommu's attached to the domain, protected
by a spinlock. This unnecessary execution path introduces overhead,
leading to a measurable I/O performance regression. On systems with NVMes
under the same bridge, performance was observed to drop from approximately
~6150 MiB/s down to ~4985 MiB/s.

Introduce a flag in the dmar_domain structure. This flag will only be set
when iotlb_sync_map is required (i.e., when CM or RWBF is set). The
cache_tag_flush_range_np() is called only for domains where this flag is
set. This flag, once set, is immutable, given that there won't be mixed
configurations in real-world scenarios where some IOMMUs in a system
operate in caching mode while others do not. Theoretically, the
immutability of this flag does not impact functionality.

Reported-by: Ioanna Alifieraki <ioanna-maria.alifieraki@canonical.com>
Closes: https://bugs.launchpad.net/ubuntu/+source/linux/+bug/2115738
Link: https://lore.kernel.org/r/20250701171154.52435-1-ioanna-maria.alifieraki@canonical.com
Fixes: 129dab6e12 ("iommu/vt-d: Use cache_tag_flush_range_np() in iotlb_sync_map")
Cc: stable@vger.kernel.org
Signed-off-by: Lu Baolu <baolu.lu@linux.intel.com>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20250703031545.3378602-1-baolu.lu@linux.intel.com
Link: https://lore.kernel.org/r/20250714045028.958850-3-baolu.lu@linux.intel.com
Signed-off-by: Will Deacon <will@kernel.org>
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
History 2025-08-20 18:30:51 +02:00
..
cache.c iommu/vt-d: Fix qi_batch NULL pointer with nested parent domain 2024-12-19 18:13:06 +01:00
cap_audit.c iommu/vt-d: Remove virtual command interface 2023-03-31 10:03:21 +02:00
cap_audit.h iommu/vt-d: Check FL and SL capability sanity in scalable mode 2021-10-18 12:31:48 +02:00
debugfs.c iommu/vt-d: Remove debugfs use of private data field 2024-04-26 11:57:38 +02:00
dmar.c iommu/vt-d: Fix suspicious RCU usage 2025-03-07 18:25:42 +01:00
iommu.c iommu/vt-d: Optimize iotlb_sync_map for non-caching/non-RWBF modes 2025-08-20 18:30:51 +02:00
iommu.h iommu/vt-d: Optimize iotlb_sync_map for non-caching/non-RWBF modes 2025-08-20 18:30:51 +02:00
irq_remapping.c iommu/vt-d: Wire up irq_ack() to irq_move_irq() for posted MSIs 2025-04-20 10:15:48 +02:00
Kconfig dma-mapping: direct calls for dma-iommu 2024-08-22 06:18:11 +02:00
Makefile iommu/vt-d: Add cache tag assignment interface 2024-04-26 11:57:40 +02:00
nested.c iommu/vt-d: Restore context entry setup order for aliased devices 2025-06-27 11:11:21 +01:00
pasid.c Merge branches 'fixes', 'arm/smmu', 'intel/vt-d', 'amd/amd-vi' and 'core' into next 2024-09-13 12:53:05 +02:00
pasid.h iommu/vt-d: Remove control over Execute-Requested requests 2024-07-03 16:39:26 +01:00
perf.c iommu/vt-d: Use kcalloc() instead of kzalloc() 2024-03-01 13:51:18 +01:00
perf.h iommu/vt-d: Remove debugfs use of private data field 2024-04-26 11:57:38 +02:00
perfmon.c iommu/vt-d: Clean up cpumask and hotplug for perfmon 2024-09-10 11:44:13 +02:00
perfmon.h iommu/vt-d: Add IOMMU perfmon support 2023-02-03 11:06:06 +01:00
svm.c iommu/vt-d: Add qi_batch for dmar_domain 2024-09-02 18:15:02 +02:00
trace.c iommu/vt-d: Move trace/events/intel_iommu.h under iommu 2022-07-15 10:21:28 +02:00
trace.h tracing/treewide: Remove second parameter of __assign_str() 2024-05-22 20:14:47 -04:00