iommu: Remove empty iommu_tlb_range_add() callback from iommu_ops

Commit add02cfdc9bc ("iommu: Introduce Interface for IOMMU TLB Flushing")
added three new TLB flushing operations to the IOMMU API so that the
underlying driver operations can be batched when unmapping large regions
of IO virtual address space.

However, the ->iotlb_range_add() callback has not been implemented by
any IOMMU drivers (amd_iommu.c implements it as an empty function, which
incurs the overhead of an indirect branch). Instead, drivers either flush
the entire IOTLB in the ->iotlb_sync() callback or perform the necessary
invalidation during ->unmap().

Attempting to implement ->iotlb_range_add() for arm-smmu-v3.c revealed
two major issues:

  1. The page size used to map the region in the page-table is not known,
     and so it is not generally possible to issue TLB flushes in the most
     efficient manner.

  2. The only mutable state passed to the callback is a pointer to the
     iommu_domain, which can be accessed concurrently and therefore
     requires expensive synchronisation to keep track of the outstanding
     flushes.

Remove the callback entirely in preparation for extending ->unmap() and
->iotlb_sync() to update a token on the caller's stack.

Signed-off-by: Will Deacon <will@kernel.org>

diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index b607a92791d3f8b48a9c1caeaea48986753ead64..f93b148cf55e78320392d40656b02159d3597e0a 100644 (file)
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -3196,11 +3196,6 @@ static void amd_iommu_flush_iotlb_all(struct iommu_domain *domain)
        domain_flush_complete(dom);
 }
 
-static void amd_iommu_iotlb_range_add(struct iommu_domain *domain,
-                                     unsigned long iova, size_t size)
-{
-}
-
 const struct iommu_ops amd_iommu_ops = {
        .capable = amd_iommu_capable,
        .domain_alloc = amd_iommu_domain_alloc,
@@ -3219,7 +3214,6 @@ const struct iommu_ops amd_iommu_ops = {
        .is_attach_deferred = amd_iommu_is_attach_deferred,
        .pgsize_bitmap  = AMD_IOMMU_PGSIZES,
        .flush_iotlb_all = amd_iommu_flush_iotlb_all,
-       .iotlb_range_add = amd_iommu_iotlb_range_add,
        .iotlb_sync = amd_iommu_flush_iotlb_all,
 };
 

diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c
index 0c674d80c37fd5768fa62296f6be72f97c5dd245..6d7b25fe2474d2110536e9aaab73f31c3ff8b053 100644 (file)
--- a/drivers/iommu/iommu.c
+++ b/drivers/iommu/iommu.c
@@ -1903,9 +1903,6 @@ static size_t __iommu_unmap(struct iommu_domain *domain,
                if (!unmapped_page)
                        break;
 
-               if (sync && ops->iotlb_range_add)
-                       ops->iotlb_range_add(domain, iova, pgsize);
-
                pr_debug("unmapped: iova 0x%lx size 0x%zx\n",
                         iova, unmapped_page);
 

diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 054391f30fa836e013394c0f64917b6fa767ab8b..fad7fd8c167cf1abdb6fc29b093a56f2e0ba29d2 100644 (file)
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -696,7 +696,6 @@ static size_t unmap_unpin_fast(struct vfio_domain *domain,
                if (!unmapped) {
                        kfree(entry);
                } else {
-                       iommu_tlb_range_add(domain->domain, *iova, unmapped);
                        entry->iova = *iova;
                        entry->phys = phys;
                        entry->len  = unmapped;

diff --git a/include/linux/iommu.h b/include/linux/iommu.h
index fdc355ccc5701e59d5894bdd648ccb1c19d26d95..1e21431262d9a5bae84943b5e8e51e95874a6be3 100644 (file)
--- a/include/linux/iommu.h
+++ b/include/linux/iommu.h
@@ -201,7 +201,6 @@ struct iommu_sva_ops {
  * @map: map a physically contiguous memory region to an iommu domain
  * @unmap: unmap a physically contiguous memory region from an iommu domain
  * @flush_iotlb_all: Synchronously flush all hardware TLBs for this domain
- * @iotlb_range_add: Add a given iova range to the flush queue for this domain
  * @iotlb_sync_map: Sync mappings created recently using @map to the hardware
  * @iotlb_sync: Flush all queued ranges from the hardware TLBs and empty flush
  *            queue
@@ -244,8 +243,6 @@ struct iommu_ops {
        size_t (*unmap)(struct iommu_domain *domain, unsigned long iova,
                     size_t size);
        void (*flush_iotlb_all)(struct iommu_domain *domain);
-       void (*iotlb_range_add)(struct iommu_domain *domain,
-                               unsigned long iova, size_t size);
        void (*iotlb_sync_map)(struct iommu_domain *domain);
        void (*iotlb_sync)(struct iommu_domain *domain);
        phys_addr_t (*iova_to_phys)(struct iommu_domain *domain, dma_addr_t iova);
@@ -476,13 +473,6 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
                domain->ops->flush_iotlb_all(domain);
 }
 
-static inline void iommu_tlb_range_add(struct iommu_domain *domain,
-                                      unsigned long iova, size_t size)
-{
-       if (domain->ops->iotlb_range_add)
-               domain->ops->iotlb_range_add(domain, iova, size);
-}
-
 static inline void iommu_tlb_sync(struct iommu_domain *domain)
 {
        if (domain->ops->iotlb_sync)
@@ -637,11 +627,6 @@ static inline void iommu_flush_tlb_all(struct iommu_domain *domain)
 {
 }
 
-static inline void iommu_tlb_range_add(struct iommu_domain *domain,
-                                      unsigned long iova, size_t size)
-{
-}
-
 static inline void iommu_tlb_sync(struct iommu_domain *domain)
 {
 }