[GIT PULL] Intel IOMMU improvements for 4.7

[GIT PULL] Intel IOMMU improvements for 4.7

[David Woodhouse]

[-- Attachment #1.1: Type: text/plain, Size: 1464 bytes --]

Linus, please pull from
	git://git.infradead.org/intel-iommu.git

This patchset improves the scalability of the Intel IOMMU code by
resolving two spinlock bottlenecks and eliminating the linearity of
the IOVA allocator, yielding up to ~5x performance improvement and
approaching iommu=off performance.

Omer Peleg (8):
      iommu/vt-d: refactoring of deferred flush entries
      iommu/vt-d: per-cpu deferred invalidation queues
      iommu/vt-d: correct flush_unmaps pfn usage
      iommu/vt-d: only unmap mapped entries
      iommu/vt-d: avoid dev iotlb logic for domains with no dev iotlbs
      iommu/vt-d: change intel-iommu to use IOVA frame numbers
      iommu/iova: introduce per-cpu caching to iova allocation
      iommu/vt-d: Use per-cpu IOVA caching

 drivers/iommu/intel-iommu.c | 318 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++------------------------------------
 drivers/iommu/iova.c        | 417 ++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++++---------
 include/linux/iova.h        |  23 ++++++++-
 3 files changed, 638 insertions(+), 120 deletions(-)

-- 
David Woodhouse                            Open Source Technology Centre
David.Woodhouse-ral2JQCrhuEAvxtiuMwx3w@public.gmane.org                              Intel Corporation

[-- Attachment #1.2: smime.p7s --]
[-- Type: application/x-pkcs7-signature, Size: 5760 bytes --]

[-- Attachment #2: Type: text/plain, Size: 0 bytes --]