mm: rmap: move the cache flushing to the correct place for hugetlb PMD sharing

The cache level flush will always be first when changing an existing
virtual–>physical mapping to a new value, since this allows us to
properly handle systems whose caches are strict and require a
virtual–>physical translation to exist for a virtual address.  So we
should move the cache flushing before huge_pmd_unshare().

As Muchun pointed out[1], now the architectures whose supporting hugetlb
PMD sharing have no cache flush issues in practice.  But I think we should
still follow the cache/TLB flushing rules when changing a valid virtual
address mapping in case of potential issues in future.

[1] https://lore.kernel.org/all/YmT%2F%2FhuUbFX+KHcy@FVFYT0MHHV2J.usts.net/

Link: https://lkml.kernel.org/r/4f7ae6dfdc838ab71e1655188b657c032ff1f28f.1651056365.git.baolin.wang@linux.alibaba.comSigned-off-by: Baolin Wang <baolin.wang@linux.alibaba.com>
Reviewed-by: Mike Kravetz <mike.kravetz@oracle.com>
Cc: Mina Almasry <almasrymina@google.com>
Cc: Muchun Song <songmuchun@bytedance.com>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

mm/rmap.c

@@ -1532,15 +1532,16 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 			 * do this outside rmap routines.
 			 */
 			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+			/*
+			 * huge_pmd_unshare may unmap an entire PMD page.
+			 * There is no way of knowing exactly which PMDs may
+			 * be cached for this mm, so we must flush them all.
+			 * start/end were already adjusted above to cover this
+			 * range.
+			 */
+			flush_cache_range(vma, range.start, range.end);
+
 			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
-				/*
-				 * huge_pmd_unshare unmapped an entire PMD
-				 * page.  There is no way of knowing exactly
-				 * which PMDs may be cached for this mm, so
-				 * we must flush them all.  start/end were
-				 * already adjusted above to cover this range.
-				 */
-				flush_cache_range(vma, range.start, range.end);
 				flush_tlb_range(vma, range.start, range.end);
 				mmu_notifier_invalidate_range(mm, range.start,
 							      range.end);
@@ -1557,13 +1558,14 @@ static bool try_to_unmap_one(struct folio *folio, struct vm_area_struct *vma,
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
+		} else {
+			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
 		}
 
 		/*
 		 * Nuke the page table entry. When having to clear
 		 * PageAnonExclusive(), we always have to flush.
 		 */
-		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
 		if (should_defer_flush(mm, flags) && !anon_exclusive) {
 			/*
 			 * We clear the PTE but do not flush so potentially
@@ -1884,15 +1886,16 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 			 * do this outside rmap routines.
 			 */
 			VM_BUG_ON(!(flags & TTU_RMAP_LOCKED));
+			/*
+			 * huge_pmd_unshare may unmap an entire PMD page.
+			 * There is no way of knowing exactly which PMDs may
+			 * be cached for this mm, so we must flush them all.
+			 * start/end were already adjusted above to cover this
+			 * range.
+			 */
+			flush_cache_range(vma, range.start, range.end);
+
 			if (huge_pmd_unshare(mm, vma, &address, pvmw.pte)) {
-				/*
-				 * huge_pmd_unshare unmapped an entire PMD
-				 * page.  There is no way of knowing exactly
-				 * which PMDs may be cached for this mm, so
-				 * we must flush them all.  start/end were
-				 * already adjusted above to cover this range.
-				 */
-				flush_cache_range(vma, range.start, range.end);
 				flush_tlb_range(vma, range.start, range.end);
 				mmu_notifier_invalidate_range(mm, range.start,
 							      range.end);
@@ -1909,10 +1912,11 @@ static bool try_to_migrate_one(struct folio *folio, struct vm_area_struct *vma,
 				page_vma_mapped_walk_done(&pvmw);
 				break;
 			}
+		} else {
+			flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
 		}
 
 		/* Nuke the page table entry. */
-		flush_cache_page(vma, address, pte_pfn(*pvmw.pte));
 		pteval = ptep_clear_flush(vma, address, pvmw.pte);
 
 		/* Set the dirty flag on the folio now the pte is gone. */