[PATCH 5.11 271/342] iommu/vt-d: Force to flush iotlb before creating superpage

[Greg Kroah-Hartman]

From: Longpeng(Mike) <longpeng2@xxxxxxxxxx>

commit 38c527aeb41926c71902dd42f788a8b093b21416 upstream.

The translation caches may preserve obsolete data when the
mapping size is changed, suppose the following sequence which
can reveal the problem with high probability.

1.mmap(4GB,MAP_HUGETLB)
2.
  while (1) {
   (a)    DMA MAP   0,0xa0000
   (b)    DMA UNMAP 0,0xa0000
   (c)    DMA MAP   0,0xc0000000
             * DMA read IOVA 0 may failure here (Not present)
             * if the problem occurs.
   (d)    DMA UNMAP 0,0xc0000000
  }

The page table(only focus on IOVA 0) after (a) is:
 PML4: 0x19db5c1003   entry:0xffff899bdcd2f000
  PDPE: 0x1a1cacb003  entry:0xffff89b35b5c1000
   PDE: 0x1a30a72003  entry:0xffff89b39cacb000
    PTE: 0x21d200803  entry:0xffff89b3b0a72000

The page table after (b) is:
 PML4: 0x19db5c1003   entry:0xffff899bdcd2f000
  PDPE: 0x1a1cacb003  entry:0xffff89b35b5c1000
   PDE: 0x1a30a72003  entry:0xffff89b39cacb000
    PTE: 0x0          entry:0xffff89b3b0a72000

The page table after (c) is:
 PML4: 0x19db5c1003   entry:0xffff899bdcd2f000
  PDPE: 0x1a1cacb003  entry:0xffff89b35b5c1000
   PDE: 0x21d200883   entry:0xffff89b39cacb000 (*)

Because the PDE entry after (b) is present, it won't be
flushed even if the iommu driver flush cache when unmap,
so the obsolete data may be preserved in cache, which
would cause the wrong translation at end.

However, we can see the PDE entry is finally switch to
2M-superpage mapping, but it does not transform
to 0x21d200883 directly:

1. PDE: 0x1a30a72003
2. __domain_mapping
     dma_pte_free_pagetable
       Set the PDE entry to ZERO
     Set the PDE entry to 0x21d200883

So we must flush the cache after the entry switch to ZERO
to avoid the obsolete info be preserved.

Cc: David Woodhouse <dwmw2@xxxxxxxxxxxxx>
Cc: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
Cc: Nadav Amit <nadav.amit@xxxxxxxxx>
Cc: Alex Williamson <alex.williamson@xxxxxxxxxx>
Cc: Joerg Roedel <joro@xxxxxxxxxx>
Cc: Kevin Tian <kevin.tian@xxxxxxxxx>
Cc: Gonglei (Arei) <arei.gonglei@xxxxxxxxxx>

Fixes: 6491d4d02893 ("intel-iommu: Free old page tables before creating superpage")
Cc: <stable@xxxxxxxxxxxxxxx> # v3.0+
Link: https://lore.kernel.org/linux-iommu/670baaf8-4ff8-4e84-4be3-030b95ab5a5e@xxxxxxxxxx/
Suggested-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
Signed-off-by: Longpeng(Mike) <longpeng2@xxxxxxxxxx>
Acked-by: Lu Baolu <baolu.lu@xxxxxxxxxxxxxxx>
Link: https://lore.kernel.org/r/20210415004628.1779-1-longpeng2@xxxxxxxxxx
Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
Signed-off-by: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
---
 drivers/iommu/intel/iommu.c |   52 ++++++++++++++++++++++++++++++++------------
 1 file changed, 38 insertions(+), 14 deletions(-)

--- a/drivers/iommu/intel/iommu.c
+++ b/drivers/iommu/intel/iommu.c
@@ -2294,6 +2294,41 @@ static inline int hardware_largepage_cap
 	return level;
 }
 
+/*
+ * Ensure that old small page tables are removed to make room for superpage(s).
+ * We're going to add new large pages, so make sure we don't remove their parent
+ * tables. The IOTLB/devTLBs should be flushed if any PDE/PTEs are cleared.
+ */
+static void switch_to_super_page(struct dmar_domain *domain,
+				 unsigned long start_pfn,
+				 unsigned long end_pfn, int level)
+{
+	unsigned long lvl_pages = lvl_to_nr_pages(level);
+	struct dma_pte *pte = NULL;
+	int i;
+
+	while (start_pfn <= end_pfn) {
+		if (!pte)
+			pte = pfn_to_dma_pte(domain, start_pfn, &level);
+
+		if (dma_pte_present(pte)) {
+			dma_pte_free_pagetable(domain, start_pfn,
+					       start_pfn + lvl_pages - 1,
+					       level + 1);
+
+			for_each_domain_iommu(i, domain)
+				iommu_flush_iotlb_psi(g_iommus[i], domain,
+						      start_pfn, lvl_pages,
+						      0, 0);
+		}
+
+		pte++;
+		start_pfn += lvl_pages;
+		if (first_pte_in_page(pte))
+			pte = NULL;
+	}
+}
+
 static int
 __domain_mapping(struct dmar_domain *domain, unsigned long iov_pfn,
 		 unsigned long phys_pfn, unsigned long nr_pages, int prot)
@@ -2327,22 +2362,11 @@ __domain_mapping(struct dmar_domain *dom
 				return -ENOMEM;
 			/* It is large page*/
 			if (largepage_lvl > 1) {
-				unsigned long nr_superpages, end_pfn;
+				unsigned long end_pfn;
 
 				pteval |= DMA_PTE_LARGE_PAGE;
-				lvl_pages = lvl_to_nr_pages(largepage_lvl);
-
-				nr_superpages = nr_pages / lvl_pages;
-				end_pfn = iov_pfn + nr_superpages * lvl_pages - 1;
-
-				/*
-				 * Ensure that old small page tables are
-				 * removed to make room for superpage(s).
-				 * We're adding new large pages, so make sure
-				 * we don't remove their parent tables.
-				 */
-				dma_pte_free_pagetable(domain, iov_pfn, end_pfn,
-						       largepage_lvl + 1);
+				end_pfn = ((iov_pfn + nr_pages) & level_mask(largepage_lvl)) - 1;
+				switch_to_super_page(domain, iov_pfn, end_pfn, largepage_lvl);
 			} else {
 				pteval &= ~(uint64_t)DMA_PTE_LARGE_PAGE;
 			}