[Patch v3 0/3] iommu: reduce spinlock contention on fast path

[Cong Wang]

This patchset contains three small optimizations for the global spinlock
contention in IOVA cache. Our memcache perf test shows this reduced its
p999 latency down by 45% on AMD when IOMMU is enabled.

(Resending v3 on Joerg's request.)

Cong Wang (3):
  iommu: avoid unnecessary magazine allocations
  iommu: optimize iova_magazine_free_pfns()
  iommu: avoid taking iova_rbtree_lock twice

---
v3: improve changelog, no code change
v2: fix a memory leak

 drivers/iommu/iova.c | 75 ++++++++++++++++++++++++++------------------
 1 file changed, 45 insertions(+), 30 deletions(-)

-- 
2.21.0