summaryrefslogtreecommitdiff
path: root/drivers/iommu/intel-iommu.c
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/iommu/intel-iommu.c')
-rw-r--r--drivers/iommu/intel-iommu.c94
1 files changed, 76 insertions, 18 deletions
diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c
index 14e4b3722428..115ff26e9ced 100644
--- a/drivers/iommu/intel-iommu.c
+++ b/drivers/iommu/intel-iommu.c
@@ -31,7 +31,6 @@
#include <linux/pci.h>
#include <linux/dmar.h>
#include <linux/dma-mapping.h>
-#include <linux/dma-direct.h>
#include <linux/mempool.h>
#include <linux/memory.h>
#include <linux/cpu.h>
@@ -485,14 +484,37 @@ static int dmar_forcedac;
static int intel_iommu_strict;
static int intel_iommu_superpage = 1;
static int intel_iommu_ecs = 1;
+static int intel_iommu_pasid28;
static int iommu_identity_mapping;
#define IDENTMAP_ALL 1
#define IDENTMAP_GFX 2
#define IDENTMAP_AZALIA 4
-#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap))
-#define pasid_enabled(iommu) (ecs_enabled(iommu) && ecap_pasid(iommu->ecap))
+/* Broadwell and Skylake have broken ECS support — normal so-called "second
+ * level" translation of DMA requests-without-PASID doesn't actually happen
+ * unless you also set the NESTE bit in an extended context-entry. Which of
+ * course means that SVM doesn't work because it's trying to do nested
+ * translation of the physical addresses it finds in the process page tables,
+ * through the IOVA->phys mapping found in the "second level" page tables.
+ *
+ * The VT-d specification was retroactively changed to change the definition
+ * of the capability bits and pretend that Broadwell/Skylake never happened...
+ * but unfortunately the wrong bit was changed. It's ECS which is broken, but
+ * for some reason it was the PASID capability bit which was redefined (from
+ * bit 28 on BDW/SKL to bit 40 in future).
+ *
+ * So our test for ECS needs to eschew those implementations which set the old
+ * PASID capabiity bit 28, since those are the ones on which ECS is broken.
+ * Unless we are working around the 'pasid28' limitations, that is, by putting
+ * the device into passthrough mode for normal DMA and thus masking the bug.
+ */
+#define ecs_enabled(iommu) (intel_iommu_ecs && ecap_ecs(iommu->ecap) && \
+ (intel_iommu_pasid28 || !ecap_broken_pasid(iommu->ecap)))
+/* PASID support is thus enabled if ECS is enabled and *either* of the old
+ * or new capability bits are set. */
+#define pasid_enabled(iommu) (ecs_enabled(iommu) && \
+ (ecap_pasid(iommu->ecap) || ecap_broken_pasid(iommu->ecap)))
int intel_iommu_gfx_mapped;
EXPORT_SYMBOL_GPL(intel_iommu_gfx_mapped);
@@ -555,6 +577,11 @@ static int __init intel_iommu_setup(char *str)
printk(KERN_INFO
"Intel-IOMMU: disable extended context table support\n");
intel_iommu_ecs = 0;
+ } else if (!strncmp(str, "pasid28", 7)) {
+ printk(KERN_INFO
+ "Intel-IOMMU: enable pre-production PASID support\n");
+ intel_iommu_pasid28 = 1;
+ iommu_identity_mapping |= IDENTMAP_GFX;
} else if (!strncmp(str, "tboot_noforce", 13)) {
printk(KERN_INFO
"Intel-IOMMU: not forcing on after tboot. This could expose security risk for tboot\n");
@@ -3713,30 +3740,61 @@ static void *intel_alloc_coherent(struct device *dev, size_t size,
dma_addr_t *dma_handle, gfp_t flags,
unsigned long attrs)
{
- void *vaddr;
+ struct page *page = NULL;
+ int order;
- vaddr = dma_direct_alloc(dev, size, dma_handle, flags, attrs);
- if (iommu_no_mapping(dev) || !vaddr)
- return vaddr;
+ size = PAGE_ALIGN(size);
+ order = get_order(size);
- *dma_handle = __intel_map_single(dev, virt_to_phys(vaddr),
- PAGE_ALIGN(size), DMA_BIDIRECTIONAL,
- dev->coherent_dma_mask);
- if (!*dma_handle)
- goto out_free_pages;
- return vaddr;
+ if (!iommu_no_mapping(dev))
+ flags &= ~(GFP_DMA | GFP_DMA32);
+ else if (dev->coherent_dma_mask < dma_get_required_mask(dev)) {
+ if (dev->coherent_dma_mask < DMA_BIT_MASK(32))
+ flags |= GFP_DMA;
+ else
+ flags |= GFP_DMA32;
+ }
+
+ if (gfpflags_allow_blocking(flags)) {
+ unsigned int count = size >> PAGE_SHIFT;
+
+ page = dma_alloc_from_contiguous(dev, count, order, flags);
+ if (page && iommu_no_mapping(dev) &&
+ page_to_phys(page) + size > dev->coherent_dma_mask) {
+ dma_release_from_contiguous(dev, page, count);
+ page = NULL;
+ }
+ }
+
+ if (!page)
+ page = alloc_pages(flags, order);
+ if (!page)
+ return NULL;
+ memset(page_address(page), 0, size);
+
+ *dma_handle = __intel_map_single(dev, page_to_phys(page), size,
+ DMA_BIDIRECTIONAL,
+ dev->coherent_dma_mask);
+ if (*dma_handle)
+ return page_address(page);
+ if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+ __free_pages(page, order);
-out_free_pages:
- dma_direct_free(dev, size, vaddr, *dma_handle, attrs);
return NULL;
}
static void intel_free_coherent(struct device *dev, size_t size, void *vaddr,
dma_addr_t dma_handle, unsigned long attrs)
{
- if (!iommu_no_mapping(dev))
- intel_unmap(dev, dma_handle, PAGE_ALIGN(size));
- dma_direct_free(dev, size, vaddr, dma_handle, attrs);
+ int order;
+ struct page *page = virt_to_page(vaddr);
+
+ size = PAGE_ALIGN(size);
+ order = get_order(size);
+
+ intel_unmap(dev, dma_handle, size);
+ if (!dma_release_from_contiguous(dev, page, size >> PAGE_SHIFT))
+ __free_pages(page, order);
}
static void intel_unmap_sg(struct device *dev, struct scatterlist *sglist,