mm/memory.c: allow different return codes for copy_nonpresent_pte()

Currently if copy_nonpresent_pte() returns a non-zero value it is assumed
to be a swap entry which requires further processing outside the loop in
copy_pte_range() after dropping locks.  This prevents other values being
returned to signal conditions such as failure which a subsequent change
requires.

Instead make copy_nonpresent_pte() return an error code if further
processing is required and read the value for the swap entry in the main
loop under the ptl.

Link: https://lkml.kernel.org/r/[email protected]
Signed-off-by: Alistair Popple <[email protected]>
Reviewed-by: Peter Xu <[email protected]>
Cc: Ben Skeggs <[email protected]>
Cc: Christoph Hellwig <[email protected]>
Cc: Hugh Dickins <[email protected]>
Cc: Jason Gunthorpe <[email protected]>
Cc: John Hubbard <[email protected]>
Cc: "Matthew Wilcox (Oracle)" <[email protected]>
Cc: Ralph Campbell <[email protected]>
Cc: Shakeel Butt <[email protected]>
Signed-off-by: Andrew Morton <[email protected]>
Signed-off-by: Linus Torvalds <[email protected]>

Author: apopple-nvidia

mm/memory.c

@@ -717,7 +717,7 @@ copy_nonpresent_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm,
 
 	if (likely(!non_swap_entry(entry))) {
 		if (swap_duplicate(entry) < 0)
-			return entry.val;
+			return -EIO;
 
 		/* make sure dst_mm is on swapoff's mmlist. */
 		if (unlikely(list_empty(&dst_mm->mmlist))) {
@@ -973,12 +973,14 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 			continue;
 		}
 		if (unlikely(!pte_present(*src_pte))) {
-			entry.val = copy_nonpresent_pte(dst_mm, src_mm,
-							dst_pte, src_pte,
-							dst_vma, src_vma,
-							addr, rss);
-			if (entry.val)
+			ret = copy_nonpresent_pte(dst_mm, src_mm,
+						  dst_pte, src_pte,
+						  dst_vma, src_vma,
+						  addr, rss);
+			if (ret == -EIO) {
+				entry = pte_to_swp_entry(*src_pte);
 				break;
+			}
 			progress += 8;
 			continue;
 		}
@@ -1011,20 +1013,24 @@ copy_pte_range(struct vm_area_struct *dst_vma, struct vm_area_struct *src_vma,
 	pte_unmap_unlock(orig_dst_pte, dst_ptl);
 	cond_resched();
 
-	if (entry.val) {
+	if (ret == -EIO) {
+		VM_WARN_ON_ONCE(!entry.val);
 		if (add_swap_count_continuation(entry, GFP_KERNEL) < 0) {
 			ret = -ENOMEM;
 			goto out;
 		}
 		entry.val = 0;
-	} else if (ret) {
-		WARN_ON_ONCE(ret != -EAGAIN);
+	} else if (ret ==  -EAGAIN) {
 		prealloc = page_copy_prealloc(src_mm, src_vma, addr);
 		if (!prealloc)
 			return -ENOMEM;
-		/* We've captured and resolved the error. Reset, try again. */
-		ret = 0;
+	} else if (ret) {
+		VM_WARN_ON_ONCE(1);
 	}
+
+	/* We've captured and resolved the error. Reset, try again. */
+	ret = 0;
+
 	if (addr != end)
 		goto again;
 out: