Merge tag 'iommu-updates-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu

Pull iommu updates from Joerg Roedel:

 - batched unmap support for the IOMMU-API

 - support for unlocked command queueing in the ARM-SMMU driver

 - rework the ATS support in the ARM-SMMU driver

 - more refactoring in the ARM-SMMU driver to support hardware
   implemention specific quirks and errata

 - bounce buffering DMA-API implementatation in the Intel VT-d driver
   for untrusted devices (like Thunderbolt devices)

 - fixes for runtime PM support in the OMAP iommu driver

 - MT8183 IOMMU support in the Mediatek IOMMU driver

 - rework of the way the IOMMU core sets the default domain type for
   groups. Changing the default domain type on x86 does not require two
   kernel parameters anymore.

 - more smaller fixes and cleanups

* tag 'iommu-updates-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/joro/iommu: (113 commits)
  iommu/vt-d: Declare Broadwell igfx dmar support snafu
  iommu/vt-d: Add Scalable Mode fault information
  iommu/vt-d: Use bounce buffer for untrusted devices
  iommu/vt-d: Add trace events for device dma map/unmap
  iommu/vt-d: Don't switch off swiotlb if bounce page is used
  iommu/vt-d: Check whether device requires bounce buffer
  swiotlb: Split size parameter to map/unmap APIs
  iommu/omap: Mark pm functions __maybe_unused
  iommu/ipmmu-vmsa: Disable cache snoop transactions on R-Car Gen3
  iommu/ipmmu-vmsa: Move IMTTBCR_SL0_TWOBIT_* to restore sort order
  iommu: Don't use sme_active() in generic code
  iommu/arm-smmu-v3: Fix build error without CONFIG_PCI_ATS
  iommu/qcom: Use struct_size() helper
  iommu: Remove wrong default domain comments
  iommu/dma: Fix for dereferencing before null checking
  iommu/mediatek: Clean up struct mtk_smi_iommu
  memory: mtk-smi: Get rid of need_larbid
  iommu/mediatek: Fix VLD_PA_RNG register backup when suspend
  memory: mtk-smi: Add bus_sel for mt8183
  memory: mtk-smi: Invoke pm runtime_callback to enable clocks
  ...

2 files changed, 22 insertions, 14 deletions

diff --git a/kernel/dma/direct.c b/kernel/dma/direct.c
index 706113c6bebc..8402b29c280f 100644
--- a/kernel/dma/direct.c
+++ b/kernel/dma/direct.c
@@ -305,7 +305,7 @@ void dma_direct_unmap_page(struct device *dev, dma_addr_t addr,
 		dma_direct_sync_single_for_cpu(dev, addr, size, dir);
 
 	if (unlikely(is_swiotlb_buffer(phys)))
-		swiotlb_tbl_unmap_single(dev, phys, size, dir, attrs);
+		swiotlb_tbl_unmap_single(dev, phys, size, size, dir, attrs);
 }
 EXPORT_SYMBOL(dma_direct_unmap_page);
 
diff --git a/kernel/dma/swiotlb.c b/kernel/dma/swiotlb.c
index 9de232229063..796a44f8ef5a 100644
--- a/kernel/dma/swiotlb.c
+++ b/kernel/dma/swiotlb.c
@@ -444,7 +444,9 @@ static void swiotlb_bounce(phys_addr_t orig_addr, phys_addr_t tlb_addr,
 
 phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 				   dma_addr_t tbl_dma_addr,
-				   phys_addr_t orig_addr, size_t size,
+				   phys_addr_t orig_addr,
+				   size_t mapping_size,
+				   size_t alloc_size,
 				   enum dma_data_direction dir,
 				   unsigned long attrs)
 {
@@ -464,6 +466,12 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 		pr_warn_once("%s is active and system is using DMA bounce buffers\n",
 			     sme_active() ? "SME" : "SEV");
 
+	if (mapping_size > alloc_size) {
+		dev_warn_once(hwdev, "Invalid sizes (mapping: %zd bytes, alloc: %zd bytes)",
+			      mapping_size, alloc_size);
+		return (phys_addr_t)DMA_MAPPING_ERROR;
+	}
+
 	mask = dma_get_seg_boundary(hwdev);
 
 	tbl_dma_addr &= mask;
@@ -471,8 +479,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	offset_slots = ALIGN(tbl_dma_addr, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 
 	/*
- 	 * Carefully handle integer overflow which can occur when mask == ~0UL.
- 	 */
+	 * Carefully handle integer overflow which can occur when mask == ~0UL.
+	 */
 	max_slots = mask + 1
 		    ? ALIGN(mask + 1, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT
 		    : 1UL << (BITS_PER_LONG - IO_TLB_SHIFT);
@@ -481,8 +489,8 @@ phys_addr_t swiotlb_tbl_map_single(struct device *hwdev,
 	 * For mappings greater than or equal to a page, we limit the stride
 	 * (and hence alignment) to a page size.
 	 */
-	nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
-	if (size >= PAGE_SIZE)
+	nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	if (alloc_size >= PAGE_SIZE)
 		stride = (1 << (PAGE_SHIFT - IO_TLB_SHIFT));
 	else
 		stride = 1;
@@ -547,7 +555,7 @@ not_found:
 	spin_unlock_irqrestore(&io_tlb_lock, flags);
 	if (!(attrs & DMA_ATTR_NO_WARN) && printk_ratelimit())
 		dev_warn(hwdev, "swiotlb buffer is full (sz: %zd bytes), total %lu (slots), used %lu (slots)\n",
-			 size, io_tlb_nslabs, tmp_io_tlb_used);
+			 alloc_size, io_tlb_nslabs, tmp_io_tlb_used);
 	return (phys_addr_t)DMA_MAPPING_ERROR;
 found:
 	io_tlb_used += nslots;
@@ -562,7 +570,7 @@ found:
 		io_tlb_orig_addr[index+i] = orig_addr + (i << IO_TLB_SHIFT);
 	if (!(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    (dir == DMA_TO_DEVICE || dir == DMA_BIDIRECTIONAL))
-		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_TO_DEVICE);
+		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_TO_DEVICE);
 
 	return tlb_addr;
 }
@@ -571,11 +579,11 @@ found:
  * tlb_addr is the physical address of the bounce buffer to unmap.
  */
 void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
-			      size_t size, enum dma_data_direction dir,
-			      unsigned long attrs)
+			      size_t mapping_size, size_t alloc_size,
+			      enum dma_data_direction dir, unsigned long attrs)
 {
 	unsigned long flags;
-	int i, count, nslots = ALIGN(size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
+	int i, count, nslots = ALIGN(alloc_size, 1 << IO_TLB_SHIFT) >> IO_TLB_SHIFT;
 	int index = (tlb_addr - io_tlb_start) >> IO_TLB_SHIFT;
 	phys_addr_t orig_addr = io_tlb_orig_addr[index];
 
@@ -585,7 +593,7 @@ void swiotlb_tbl_unmap_single(struct device *hwdev, phys_addr_t tlb_addr,
 	if (orig_addr != INVALID_PHYS_ADDR &&
 	    !(attrs & DMA_ATTR_SKIP_CPU_SYNC) &&
 	    ((dir == DMA_FROM_DEVICE) || (dir == DMA_BIDIRECTIONAL)))
-		swiotlb_bounce(orig_addr, tlb_addr, size, DMA_FROM_DEVICE);
+		swiotlb_bounce(orig_addr, tlb_addr, mapping_size, DMA_FROM_DEVICE);
 
 	/*
 	 * Return the buffer to the free list by setting the corresponding
@@ -665,14 +673,14 @@ bool swiotlb_map(struct device *dev, phys_addr_t *phys, dma_addr_t *dma_addr,
 
 	/* Oh well, have to allocate and map a bounce buffer. */
 	*phys = swiotlb_tbl_map_single(dev, __phys_to_dma(dev, io_tlb_start),
-			*phys, size, dir, attrs);
+			*phys, size, size, dir, attrs);
 	if (*phys == (phys_addr_t)DMA_MAPPING_ERROR)
 		return false;
 
 	/* Ensure that the address returned is DMA'ble */
 	*dma_addr = __phys_to_dma(dev, *phys);
 	if (unlikely(!dma_capable(dev, *dma_addr, size))) {
-		swiotlb_tbl_unmap_single(dev, *phys, size, dir,
+		swiotlb_tbl_unmap_single(dev, *phys, size, size, dir,
 			attrs | DMA_ATTR_SKIP_CPU_SYNC);
 		return false;
 	}