x86/mm/pat: clear VM_PAT if copy_p4d_range failed

Syzbot reports a warning in untrack_pfn().  Digging into the root we found
that this is due to memory allocation failure in pmd_alloc_one.  And this
failure is produced due to failslab.

In copy_page_range(), memory alloaction for pmd failed.  During the error
handling process in copy_page_range(), mmput() is called to remove all
vmas.  While untrack_pfn this empty pfn, warning happens.

Here's a simplified flow:

dup_mm
  dup_mmap
    copy_page_range
      copy_p4d_range
        copy_pud_range
          copy_pmd_range
            pmd_alloc
              __pmd_alloc
                pmd_alloc_one
                  page = alloc_pages(gfp, 0);
                    if (!page)
                      return NULL;
    mmput
        exit_mmap
          unmap_vmas
            unmap_single_vma
              untrack_pfn
                follow_phys
                  WARN_ON_ONCE(1);

Since this vma is not generate successfully, we can clear flag VM_PAT.  In
this case, untrack_pfn() will not be called while cleaning this vma.

Function untrack_pfn_moved() has also been renamed to fit the new logic.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Ma Wupeng <[email protected]>
Reported-by: <[email protected]>
Cc: Andy Lutomirski <[email protected]>
Cc: Borislav Petkov <[email protected]>
Cc: Dave Hansen <[email protected]>
Cc: Peter Zijlstra <[email protected]>
Cc: Suresh Siddha <[email protected]>
Cc: Toshi Kani <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: Ma Wupeng

arch/x86/mm/pat/memtype.c

@@ -1073,11 +1073,15 @@ void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 }
 
 /*
- * untrack_pfn_moved is called, while mremapping a pfnmap for a new region,
- * with the old vma after its pfnmap page table has been removed.  The new
- * vma has a new pfnmap to the same pfn & cache type with VM_PAT set.
+ * untrack_pfn_clear is called if the following situation fits:
+ *
+ * 1) while mremapping a pfnmap for a new region,  with the old vma after
+ * its pfnmap page table has been removed.  The new vma has a new pfnmap
+ * to the same pfn & cache type with VM_PAT set.
+ * 2) while duplicating vm area, the new vma fails to copy the pgtable from
+ * old vma.
  */
-void untrack_pfn_moved(struct vm_area_struct *vma)
+void untrack_pfn_clear(struct vm_area_struct *vma)
 {
 	vm_flags_clear(vma, VM_PAT);
 }

include/linux/pgtable.h

@@ -1191,9 +1191,10 @@ static inline void untrack_pfn(struct vm_area_struct *vma,
 }
 
 /*
- * untrack_pfn_moved is called while mremapping a pfnmap for a new region.
+ * untrack_pfn_clear is called while mremapping a pfnmap for a new region
+ * or fails to copy pgtable during duplicate vm area.
  */
-static inline void untrack_pfn_moved(struct vm_area_struct *vma)
+static inline void untrack_pfn_clear(struct vm_area_struct *vma)
 {
 }
 #else
@@ -1205,7 +1206,7 @@ extern void track_pfn_insert(struct vm_area_struct *vma, pgprot_t *prot,
 extern int track_pfn_copy(struct vm_area_struct *vma);
 extern void untrack_pfn(struct vm_area_struct *vma, unsigned long pfn,
 			unsigned long size, bool mm_wr_locked);
-extern void untrack_pfn_moved(struct vm_area_struct *vma);
+extern void untrack_pfn_clear(struct vm_area_struct *vma);
 #endif
 
 #ifdef CONFIG_MMU

mm/memory.c

@@ -1290,6 +1290,7 @@ copy_page_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma)
 			continue;
 		if (unlikely(copy_p4d_range(dst_vma, src_vma, dst_pgd, src_pgd,
 					    addr, next))) {
+			untrack_pfn_clear(dst_vma);
 			ret = -ENOMEM;
 			break;
 		}

mm/mremap.c

@@ -683,7 +683,7 @@ static unsigned long move_vma(struct vm_area_struct *vma,
 
 	/* Tell pfnmap has moved from this vma */
 	if (unlikely(vma->vm_flags & VM_PFNMAP))
-		untrack_pfn_moved(vma);
+		untrack_pfn_clear(vma);
 
 	if (unlikely(!err && (flags & MREMAP_DONTUNMAP))) {
 		/* We always clear VM_LOCKED[ONFAULT] on the old vma */