mm: fix finish_fault() handling for large folios

When handling faults for anon shmem finish_fault() will attempt to install
ptes for the entire folio.  Unfortunately if it encounters a single
non-pte_none entry in that range it will bail, even if the pte that
triggered the fault is still pte_none.  When this situation happens the
fault will be retried endlessly never making forward progress.

This patch fixes this behavior and if it detects that a pte in the range
is not pte_none it will fall back to setting a single pte.

[[email protected]: tweak whitespace]
  Link: https://lkml.kernel.org/r/[email protected]
Link: https://lkml.kernel.org/r/[email protected]
Fixes: 43e027e ("mm: memory: extend finish_fault() to support large folio")
Signed-off-by: Brian Geffon <[email protected]>
Suggested-by: Baolin Wang <[email protected]>
Reported-by: Marek Maslanka <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: David Hildenbrand <[email protected]>
Cc: Hugh Dickens <[email protected]>
Cc: Kefeng Wang <[email protected]>
Cc: Matthew Wilcow (Oracle) <[email protected]>
Cc: Suren Baghdasaryan <[email protected]>
Cc: Zi Yan <[email protected]>
Cc: <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>

Author: bgaff

mm/memory.c

@@ -5185,7 +5185,11 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	bool is_cow = (vmf->flags & FAULT_FLAG_WRITE) &&
 		      !(vma->vm_flags & VM_SHARED);
 	int type, nr_pages;
-	unsigned long addr = vmf->address;
+	unsigned long addr;
+	bool needs_fallback = false;
+
+fallback:
+	addr = vmf->address;
 
 	/* Did we COW the page? */
 	if (is_cow)
@@ -5224,7 +5228,8 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 	 * approach also applies to non-anonymous-shmem faults to avoid
 	 * inflating the RSS of the process.
 	 */
-	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma))) {
+	if (!vma_is_anon_shmem(vma) || unlikely(userfaultfd_armed(vma)) ||
+	    unlikely(needs_fallback)) {
 		nr_pages = 1;
 	} else if (nr_pages > 1) {
 		pgoff_t idx = folio_page_idx(folio, page);
@@ -5260,9 +5265,9 @@ vm_fault_t finish_fault(struct vm_fault *vmf)
 		ret = VM_FAULT_NOPAGE;
 		goto unlock;
 	} else if (nr_pages > 1 && !pte_range_none(vmf->pte, nr_pages)) {
-		update_mmu_tlb_range(vma, addr, vmf->pte, nr_pages);
-		ret = VM_FAULT_NOPAGE;
-		goto unlock;
+		needs_fallback = true;
+		pte_unmap_unlock(vmf->pte, vmf->ptl);
+		goto fallback;
 	}
 
 	folio_ref_add(folio, nr_pages - 1);