Merge tag 'iommu-v4.15-rc1' of git://github.com/awilliam/linux-vfio

Pull IOMMU updates from Alex Williamson:
 "As Joerg mentioned[1], he's out on paternity leave through the end of
  the year and I'm filling in for him in the interim:

   - Enforce MSI multiple IRQ alignment in AMD IOMMU

   - VT-d PASID error handling fixes

   - Add r8a7795 IPMMU support

   - Manage runtime PM links on exynos at {add,remove}_device callbacks

   - Fix Mediatek driver name to avoid conflict

   - Add terminate support to qcom fault handler

   - 64-bit IOVA optimizations

   - Simplfy IOVA domain destruction, better use of rcache, and skip
     anchor nodes on copy

   - Convert to IOMMU TLB sync API in io-pgtable-arm{-v7s}

   - Drop command queue lock when waiting for CMD_SYNC completion on ARM
     SMMU implementations supporting MSI to cacheable memory

   - iomu-vmsa cleanup inspired by missed IOTLB sync callbacks

   - Fix sleeping lock with preemption disabled for RT

   - Dual MMU support for TI DRA7xx DSPs

   - Optional flush option on IOVA allocation avoiding overhead when
     caller can try other options

  [1] https://lkml.org/lkml/2017/10/22/72"

* tag 'iommu-v4.15-rc1' of git://github.com/awilliam/linux-vfio: (54 commits)
  iommu/iova: Use raw_cpu_ptr() instead of get_cpu_ptr() for ->fq
  iommu/mediatek: Fix driver name
  iommu/ipmmu-vmsa: Hook up r8a7795 DT matching code
  iommu/ipmmu-vmsa: Allow two bit SL0
  iommu/ipmmu-vmsa: Make IMBUSCTR setup optional
  iommu/ipmmu-vmsa: Write IMCTR twice
  iommu/ipmmu-vmsa: IPMMU device is 40-bit bus master
  iommu/ipmmu-vmsa: Make use of IOMMU_OF_DECLARE()
  iommu/ipmmu-vmsa: Enable multi context support
  iommu/ipmmu-vmsa: Add optional root device feature
  iommu/ipmmu-vmsa: Introduce features, break out alias
  iommu/ipmmu-vmsa: Unify ipmmu_ops
  iommu/ipmmu-vmsa: Clean up struct ipmmu_vmsa_iommu_priv
  iommu/ipmmu-vmsa: Simplify group allocation
  iommu/ipmmu-vmsa: Unify domain alloc/free
  iommu/ipmmu-vmsa: Fix return value check in ipmmu_find_group_dma()
  iommu/vt-d: Clear pasid table entry when memory unbound
  iommu/vt-d: Clear Page Request Overflow fault bit
  iommu/vt-d: Missing checks for pasid tables if allocation fails
  iommu/amd: Limit the IOVA page range to the specified addresses
  ...

23 files changed, 983 insertions, 627 deletions

diff --git a/drivers/gpu/drm/tegra/drm.c b/drivers/gpu/drm/tegra/drm.c
index 597d563d636a..b822e484b7e5 100644
--- a/drivers/gpu/drm/tegra/drm.c
+++ b/drivers/gpu/drm/tegra/drm.c
@@ -155,8 +155,7 @@ static int tegra_drm_load(struct drm_device *drm, unsigned long flags)
 
                 order = __ffs(tegra->domain->pgsize_bitmap);
                 init_iova_domain(&tegra->carveout.domain, 1UL << order,
-                                 carveout_start >> order,
-                                 carveout_end >> order);
+                                 carveout_start >> order);
 
                 tegra->carveout.shift = iova_shift(&tegra->carveout.domain);
                 tegra->carveout.limit = carveout_end >> tegra->carveout.shift;
diff --git a/drivers/gpu/host1x/dev.c b/drivers/gpu/host1x/dev.c
index 7f22c5c37660..5267c62e8896 100644
--- a/drivers/gpu/host1x/dev.c
+++ b/drivers/gpu/host1x/dev.c
@@ -198,8 +198,7 @@ static int host1x_probe(struct platform_device *pdev)
 
                 order = __ffs(host->domain->pgsize_bitmap);
                 init_iova_domain(&host->iova, 1UL << order,
-                                 geometry->aperture_start >> order,
-                                 geometry->aperture_end >> order);
+                                 geometry->aperture_start >> order);
                 host->iova_end = geometry->aperture_end;
         }
 
diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c
index 9c848e36f209..7d5eb004091d 100644
--- a/drivers/iommu/amd_iommu.c
+++ b/drivers/iommu/amd_iommu.c
@@ -63,7 +63,6 @@
 /* IO virtual address start page frame number */
 #define IOVA_START_PFN          (1)
 #define IOVA_PFN(addr)          ((addr) >> PAGE_SHIFT)
-#define DMA_32BIT_PFN           IOVA_PFN(DMA_BIT_MASK(32))
 
 /* Reserved IOVA ranges */
 #define MSI_RANGE_START         (0xfee00000)
@@ -1547,10 +1546,11 @@ static unsigned long dma_ops_alloc_iova(struct device *dev,
 
         if (dma_mask > DMA_BIT_MASK(32))
                 pfn = alloc_iova_fast(&dma_dom->iovad, pages,
-                                      IOVA_PFN(DMA_BIT_MASK(32)));
+                                      IOVA_PFN(DMA_BIT_MASK(32)), false);
 
         if (!pfn)
-                pfn = alloc_iova_fast(&dma_dom->iovad, pages, IOVA_PFN(dma_mask));
+                pfn = alloc_iova_fast(&dma_dom->iovad, pages,
+                                      IOVA_PFN(dma_mask), true);
 
         return (pfn << PAGE_SHIFT);
 }
@@ -1788,8 +1788,7 @@ static struct dma_ops_domain *dma_ops_domain_alloc(void)
         if (!dma_dom->domain.pt_root)
                 goto free_dma_dom;
 
-        init_iova_domain(&dma_dom->iovad, PAGE_SIZE,
-                         IOVA_START_PFN, DMA_32BIT_PFN);
+        init_iova_domain(&dma_dom->iovad, PAGE_SIZE, IOVA_START_PFN);
 
         if (init_iova_flush_queue(&dma_dom->iovad, iova_domain_flush_tlb, NULL))
                 goto free_dma_dom;
@@ -2383,11 +2382,9 @@ static void __unmap_single(struct dma_ops_domain *dma_dom,
                            size_t size,
                            int dir)
 {
-        dma_addr_t flush_addr;
         dma_addr_t i, start;
         unsigned int pages;
 
-        flush_addr = dma_addr;
         pages = iommu_num_pages(dma_addr, size, PAGE_SIZE);
         dma_addr &= PAGE_MASK;
         start = dma_addr;
@@ -2696,8 +2693,7 @@ static int init_reserved_iova_ranges(void)
         struct pci_dev *pdev = NULL;
         struct iova *val;
 
-        init_iova_domain(&reserved_iova_ranges, PAGE_SIZE,
-                         IOVA_START_PFN, DMA_32BIT_PFN);
+        init_iova_domain(&reserved_iova_ranges, PAGE_SIZE, IOVA_START_PFN);
 
         lockdep_set_class(&reserved_iova_ranges.iova_rbtree_lock,
                           &reserved_rbtree_key);
@@ -3155,7 +3151,7 @@ static void amd_iommu_apply_resv_region(struct device *dev,
         unsigned long start, end;
 
         start = IOVA_PFN(region->start);
-        end   = IOVA_PFN(region->start + region->length);
+        end   = IOVA_PFN(region->start + region->length - 1);
 
         WARN_ON_ONCE(reserve_iova(&dma_dom->iovad, start, end) == NULL);
 }
@@ -3663,11 +3659,11 @@ out_unlock:
         return table;
 }
 
-static int alloc_irq_index(u16 devid, int count)
+static int alloc_irq_index(u16 devid, int count, bool align)
 {
         struct irq_remap_table *table;
+        int index, c, alignment = 1;
         unsigned long flags;
-        int index, c;
         struct amd_iommu *iommu = amd_iommu_rlookup_table[devid];
 
         if (!iommu)
@@ -3677,16 +3673,21 @@ static int alloc_irq_index(u16 devid, int count)
         if (!table)
                 return -ENODEV;
 
+        if (align)
+                alignment = roundup_pow_of_two(count);
+
         spin_lock_irqsave(&table->lock, flags);
 
         /* Scan table for free entries */
-        for (c = 0, index = table->min_index;
-             index < MAX_IRQS_PER_TABLE;
-             ++index) {
-                if (!iommu->irte_ops->is_allocated(table, index))
+        for (index = ALIGN(table->min_index, alignment), c = 0;
+             index < MAX_IRQS_PER_TABLE;) {
+                if (!iommu->irte_ops->is_allocated(table, index)) {
                         c += 1;
-                else
-                        c = 0;
+                } else {
+                        c     = 0;
+                        index = ALIGN(index + 1, alignment);
+                        continue;
+                }
 
                 if (c == count) {
                         for (; c != 0; --c)
@@ -3695,6 +3696,8 @@ static int alloc_irq_index(u16 devid, int count)
                         index -= count - 1;
                         goto out;