Merge branch 'stable/for-linus-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb

Pull swiotlb fixes from Konrad Rzeszutek Wilk:
 "This has one fix to make i915 work when using Xen SWIOTLB, and a
  feature from Geert to aid in debugging of devices that can't do DMA
  outside the 32-bit address space.

  The feature from Geert is on top of v4.10 merge window commit
  (specifically you pulling my previous branch), as his changes were
  dependent on the Documentation/ movement patches.

  I figured it would just easier than me trying than to cherry-pick the
  Documentation patches to satisfy git.

  The patches have been soaking since 12/20, albeit I updated the last
  patch due to linux-next catching an compiler error and adding an
  Tested-and-Reported-by tag"

* 'stable/for-linus-4.10' of git://git.kernel.org/pub/scm/linux/kernel/git/konrad/swiotlb:
  swiotlb: Export swiotlb_max_segment to users
  swiotlb: Add swiotlb=noforce debug option
  swiotlb: Convert swiotlb_force from int to enum
  x86, swiotlb: Simplify pci_swiotlb_detect_override()

lib/swiotlb.c

@@ -53,7 +53,7 @@
  */
 #define IO_TLB_MIN_SLABS ((1<<20) >> IO_TLB_SHIFT)
 
-int swiotlb_force;
+enum swiotlb_force swiotlb_force;
 
 /*
  * Used to do a quick range check in swiotlb_tbl_unmap_single and
@@ -82,6 +82,12 @@ static phys_addr_t io_tlb_overflow_buffer;
 static unsigned int *io_tlb_list;
 static unsigned int io_tlb_index;
 
+/*
+ * Max segment that we can provide which (if pages are contingous) will
+ * not be bounced (unless SWIOTLB_FORCE is set).
+ */
+unsigned int max_segment;
+
 /*
  * We need to save away the original address corresponding to a mapped entry
  * for the sync operations.
@@ -106,8 +112,12 @@ setup_io_tlb_npages(char *str)
 	}
 	if (*str == ',')
 		++str;
-	if (!strcmp(str, "force"))
-		swiotlb_force = 1;
+	if (!strcmp(str, "force")) {
+		swiotlb_force = SWIOTLB_FORCE;
+	} else if (!strcmp(str, "noforce")) {
+		swiotlb_force = SWIOTLB_NO_FORCE;
+		io_tlb_nslabs = 1;
+	}
 
 	return 0;
 }
@@ -120,6 +130,20 @@ unsigned long swiotlb_nr_tbl(void)
 }
 EXPORT_SYMBOL_GPL(swiotlb_nr_tbl);
 
+unsigned int swiotlb_max_segment(void)
+{
+	return max_segment;
+}
+EXPORT_SYMBOL_GPL(swiotlb_max_segment);
+
+void swiotlb_set_max_segment(unsigned int val)
+{
+	if (swiotlb_force == SWIOTLB_FORCE)
+		max_segment = 1;
+	else
+		max_segment = rounddown(val, PAGE_SIZE);
+}
+
 /* default to 64MB */
 #define IO_TLB_DEFAULT_SIZE (64UL<<20)
 unsigned long swiotlb_size_or_default(void)
@@ -201,6 +225,7 @@ int __init swiotlb_init_with_tbl(char *tlb, unsigned long nslabs, int verbose)
 	if (verbose)
 		swiotlb_print_info();
 
+	swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
 	return 0;
 }
 
@@ -279,6 +304,7 @@ swiotlb_late_init_with_default_size(size_t default_size)
 	rc = swiotlb_late_init_with_tbl(vstart, io_tlb_nslabs);
 	if (rc)
 		free_pages((unsigned long)vstart, order);
+
 	return rc;
 }
 
@@ -333,6 +359,8 @@ swiotlb_late_init_with_tbl(char *tlb, unsigned long nslabs)
 
 	late_alloc = 1;
 
+	swiotlb_set_max_segment(io_tlb_nslabs << IO_TLB_SHIFT);
+
 	return 0;
 
 cleanup4:
@@ -347,6 +375,7 @@ cleanup2:
 	io_tlb_end = 0;
 	io_tlb_start = 0;
 	io_tlb_nslabs = 0;
+	max_segment = 0;
 	return -ENOMEM;
 }
 
@@ -375,6 +404,7 @@ void __init swiotlb_free(void)
 				   PAGE_ALIGN(io_tlb_nslabs << IO_TLB_SHIFT));
 	}
 	io_tlb_nslabs = 0;
+	max_segment = 0;
 }
 
 int is_swiotlb_buffer(phys_addr_t paddr)
@@ -543,8 +573,15 @@ static phys_addr_t
 map_single(struct device *hwdev, phys_addr_t phys, size_t size,
 	   enum dma_data_direction dir, unsigned long attrs)
 {
-	dma_addr_t start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
+	dma_addr_t start_dma_addr;
 
+	if (swiotlb_force == SWIOTLB_NO_FORCE) {
+		dev_warn_ratelimited(hwdev, "Cannot do DMA to address %pa\n",
+				     &phys);
+		return SWIOTLB_MAP_ERROR;
+	}
+
+	start_dma_addr = phys_to_dma(hwdev, io_tlb_start);
 	return swiotlb_tbl_map_single(hwdev, start_dma_addr, phys, size,
 				      dir, attrs);
 }
@@ -721,6 +758,9 @@ static void
 swiotlb_full(struct device *dev, size_t size, enum dma_data_direction dir,
 	     int do_panic)
 {
+	if (swiotlb_force == SWIOTLB_NO_FORCE)
+		return;
+
 	/*
 	 * Ran out of IOMMU space for this operation. This is very bad.
 	 * Unfortunately the drivers cannot handle this operation properly.
@@ -763,7 +803,7 @@ dma_addr_t swiotlb_map_page(struct device *dev, struct page *page,
 	 * we can safely return the device addr and not worry about bounce
 	 * buffering it.
 	 */
-	if (dma_capable(dev, dev_addr, size) && !swiotlb_force)
+	if (dma_capable(dev, dev_addr, size) && swiotlb_force != SWIOTLB_FORCE)
 		return dev_addr;
 
 	trace_swiotlb_bounced(dev, dev_addr, size, swiotlb_force);
@@ -904,7 +944,7 @@ swiotlb_map_sg_attrs(struct device *hwdev, struct scatterlist *sgl, int nelems,
 		phys_addr_t paddr = sg_phys(sg);
 		dma_addr_t dev_addr = phys_to_dma(hwdev, paddr);
 
-		if (swiotlb_force ||
+		if (swiotlb_force == SWIOTLB_FORCE ||
 		    !dma_capable(hwdev, dev_addr, sg->length)) {
 			phys_addr_t map = map_single(hwdev, sg_phys(sg),
 						     sg->length, dir, attrs);