Merge branch 'ttm-prot-fix' of git://people.freedesktop.org/~thomash/linux into drm-nextdrm-next-2020-02-04

A small fix for the long-standing ttm vm page protection hack.

Sent as a separate PR as it touches mm, has all acks in place.

Signed-off-by: Dave Airlie <airlied@redhat.com>
From: Thomas Hellström (VMware) <thellstrom@vmware.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200116102411.3056-1-thomas_os@shipmail.org

4 files changed, 63 insertions, 12 deletions

diff --git a/drivers/gpu/drm/ttm/ttm_bo_vm.c b/drivers/gpu/drm/ttm/ttm_bo_vm.c
index eebb4c06c04d..389128b8c4dd 100644
--- a/drivers/gpu/drm/ttm/ttm_bo_vm.c
+++ b/drivers/gpu/drm/ttm/ttm_bo_vm.c
@@ -179,7 +179,6 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 				    pgoff_t num_prefault)
 {
 	struct vm_area_struct *vma = vmf->vma;
-	struct vm_area_struct cvma = *vma;
 	struct ttm_buffer_object *bo = vma->vm_private_data;
 	struct ttm_bo_device *bdev = bo->bdev;
 	unsigned long page_offset;
@@ -250,7 +249,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		goto out_io_unlock;
 	}
 
-	cvma.vm_page_prot = ttm_io_prot(bo->mem.placement, prot);
+	prot = ttm_io_prot(bo->mem.placement, prot);
 	if (!bo->mem.bus.is_iomem) {
 		struct ttm_operation_ctx ctx = {
 			.interruptible = false,
@@ -266,7 +265,7 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 		}
 	} else {
 		/* Iomem should not be marked encrypted */
-		cvma.vm_page_prot = pgprot_decrypted(cvma.vm_page_prot);
+		prot = pgprot_decrypted(prot);
 	}
 
 	/*
@@ -289,11 +288,20 @@ vm_fault_t ttm_bo_vm_fault_reserved(struct vm_fault *vmf,
 			pfn = page_to_pfn(page);
 		}
 
+		/*
+		 * Note that the value of @prot at this point may differ from
+		 * the value of @vma->vm_page_prot in the caching- and
+		 * encryption bits. This is because the exact location of the
+		 * data may not be known at mmap() time and may also change
+		 * at arbitrary times while the data is mmap'ed.
+		 * See vmf_insert_mixed_prot() for a discussion.
+		 */
 		if (vma->vm_flags & VM_MIXEDMAP)
-			ret = vmf_insert_mixed(&cvma, address,
-					__pfn_to_pfn_t(pfn, PFN_DEV));
+			ret = vmf_insert_mixed_prot(vma, address,
+						    __pfn_to_pfn_t(pfn, PFN_DEV),
+						    prot);
 		else
-			ret = vmf_insert_pfn(&cvma, address, pfn);
+			ret = vmf_insert_pfn_prot(vma, address, pfn, prot);
 
 		/* Never error on prefaulted PTEs */
 		if (unlikely((ret & VM_FAULT_ERROR))) {
@@ -325,7 +333,7 @@ vm_fault_t ttm_bo_vm_fault(struct vm_fault *vmf)
 	if (ret)
 		return ret;
 
-	prot = vm_get_page_prot(vma->vm_flags);
+	prot = vma->vm_page_prot;
 	ret = ttm_bo_vm_fault_reserved(vmf, prot, TTM_BO_VM_NUM_PREFAULT);
 	if (ret == VM_FAULT_RETRY && !(vmf->flags & FAULT_FLAG_RETRY_NOWAIT))
 		return ret;
diff --git a/include/linux/mm.h b/include/linux/mm.h
index cfaa8feecfe8..5adb8141d271 100644
--- a/include/linux/mm.h
+++ b/include/linux/mm.h
@@ -2533,6 +2533,8 @@ vm_fault_t vmf_insert_pfn_prot(struct vm_area_struct *vma, unsigned long addr,
 			unsigned long pfn, pgprot_t pgprot);
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 			pfn_t pfn);
+vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
+			pfn_t pfn, pgprot_t pgprot);
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn);
 int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 270aa8fd2800..e5f0080b4e15 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -312,7 +312,12 @@ struct vm_area_struct {
 	/* Second cache line starts here. */
 
 	struct mm_struct *vm_mm;	/* The address space we belong to. */
-	pgprot_t vm_page_prot;		/* Access permissions of this VMA. */
+
+	/*
+	 * Access permissions of this VMA.
+	 * See vmf_insert_mixed_prot() for discussion.
+	 */
+	pgprot_t vm_page_prot;
 	unsigned long vm_flags;		/* Flags, see mm.h. */
 
 	/*
diff --git a/mm/memory.c b/mm/memory.c
index 45442d9a4f52..e24c7d22b117 100644
--- a/mm/memory.c
+++ b/mm/memory.c
@@ -1664,6 +1664,9 @@ out_unlock:
  * vmf_insert_pfn_prot should only be used if using multiple VMAs is
  * impractical.
  *
+ * See vmf_insert_mixed_prot() for a discussion of the implication of using
+ * a value of @pgprot different from that of @vma->vm_page_prot.
+ *
  * Context: Process context.  May allocate using %GFP_KERNEL.
  * Return: vm_fault_t value.
  */
@@ -1737,9 +1740,9 @@ static bool vm_mixed_ok(struct vm_area_struct *vma, pfn_t pfn)
 }
 
 static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
-		unsigned long addr, pfn_t pfn, bool mkwrite)
+		unsigned long addr, pfn_t pfn, pgprot_t pgprot,
+		bool mkwrite)
 {
-	pgprot_t pgprot = vma->vm_page_prot;
 	int err;
 
 	BUG_ON(!vm_mixed_ok(vma, pfn));
@@ -1782,10 +1785,43 @@ static vm_fault_t __vm_insert_mixed(struct vm_area_struct *vma,
 	return VM_FAULT_NOPAGE;
 }
 
+/**
+ * vmf_insert_mixed_prot - insert single pfn into user vma with specified pgprot
+ * @vma: user vma to map to
+ * @addr: target user address of this page
+ * @pfn: source kernel pfn
+ * @pgprot: pgprot flags for the inserted page
+ *
+ * This is exactly like vmf_insert_mixed(), except that it allows drivers to
+ * to override pgprot on a per-page basis.
+ *
+ * Typically this function should be used by drivers to set caching- and
+ * encryption bits different than those of @vma->vm_page_prot, because
+ * the caching- or encryption mode may not be known at mmap() time.
+ * This is ok as long as @vma->vm_page_prot is not used by the core vm
+ * to set caching and encryption bits for those vmas (except for COW pages).
+ * This is ensured by core vm only modifying these page table entries using
+ * functions that don't touch caching- or encryption bits, using pte_modify()
+ * if needed. (See for example mprotect()).
+ * Also when new page-table entries are created, this is only done using the
+ * fault() callback, and never using the value of vma->vm_page_prot,
+ * except for page-table entries that point to anonymous pages as the result
+ * of COW.
+ *
+ * Context: Process context.  May allocate using %GFP_KERNEL.
+ * Return: vm_fault_t value.
+ */
+vm_fault_t vmf_insert_mixed_prot(struct vm_area_struct *vma, unsigned long addr,
+				 pfn_t pfn, pgprot_t pgprot)
+{
+	return __vm_insert_mixed(vma, addr, pfn, pgprot, false);
+}
+EXPORT_SYMBOL(vmf_insert_mixed_prot);
+
 vm_fault_t vmf_insert_mixed(struct vm_area_struct *vma, unsigned long addr,
 		pfn_t pfn)
 {
-	return __vm_insert_mixed(vma, addr, pfn, false);
+	return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, false);
 }
 EXPORT_SYMBOL(vmf_insert_mixed);
 
@@ -1797,7 +1833,7 @@ EXPORT_SYMBOL(vmf_insert_mixed);
 vm_fault_t vmf_insert_mixed_mkwrite(struct vm_area_struct *vma,
 		unsigned long addr, pfn_t pfn)
 {
-	return __vm_insert_mixed(vma, addr, pfn, true);
+	return __vm_insert_mixed(vma, addr, pfn, vma->vm_page_prot, true);
 }
 EXPORT_SYMBOL(vmf_insert_mixed_mkwrite);