mm/vmalloc: huge vmalloc backing pages should be split rather than compound

Huge vmalloc higher-order backing pages were allocated with __GFP_COMP
in order to allow the sub-pages to be refcounted by callers such as
"remap_vmalloc_page [sic]" (remap_vmalloc_range).

However a similar problem exists for other struct page fields callers
use, for example fb_deferred_io_fault() takes a vmalloc'ed page and
not only refcounts it but uses ->lru, ->mapping, ->index.

This is not compatible with compound sub-pages, and can cause bad page
state issues like

  BUG: Bad page state in process swapper/0  pfn:00743
  page:(____ptrval____) refcount:0 mapcount:0 mapping:0000000000000000 index:0x0 pfn:0x743
  flags: 0x7ffff000000000(node=0|zone=0|lastcpupid=0x7ffff)
  raw: 007ffff000000000 c00c00000001d0c8 c00c00000001d0c8 0000000000000000
  raw: 0000000000000000 0000000000000000 00000000ffffffff 0000000000000000
  page dumped because: corrupted mapping in tail page
  Modules linked in:
  CPU: 0 PID: 1 Comm: swapper/0 Not tainted 5.18.0-rc3-00082-gfc6fff4a7ce1-dirty #2810
  Call Trace:
    dump_stack_lvl+0x74/0xa8 (unreliable)
    bad_page+0x12c/0x170
    free_tail_pages_check+0xe8/0x190
    free_pcp_prepare+0x31c/0x4e0
    free_unref_page+0x40/0x1b0
    __vunmap+0x1d8/0x420
    ...

The correct approach is to use split high-order pages for the huge
vmalloc backing. These allow callers to treat them in exactly the same
way as individually-allocated order-0 pages.

Link: https://lore.kernel.org/all/14444103-d51b-0fb3-ee63-c3f182f0b546@molgen.mpg.de/
Signed-off-by: Nicholas Piggin <npiggin@gmail.com>
Cc: Paul Menzel <pmenzel@molgen.mpg.de>
Cc: Song Liu <songliubraving@fb.com>
Cc: Rick Edgecombe <rick.p.edgecombe@intel.com>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 21 insertions, 15 deletions

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 07da85ae825b..cadfbb5155ea 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2653,15 +2653,18 @@ static void __vunmap(const void *addr, int deallocate_pages)
 	vm_remove_mappings(area, deallocate_pages);
 
 	if (deallocate_pages) {
-		unsigned int page_order = vm_area_page_order(area);
-		int i, step = 1U << page_order;
+		int i;
 
-		for (i = 0; i < area->nr_pages; i += step) {
+		for (i = 0; i < area->nr_pages; i++) {
 			struct page *page = area->pages[i];
 
 			BUG_ON(!page);
-			mod_memcg_page_state(page, MEMCG_VMALLOC, -step);
-			__free_pages(page, page_order);
+			mod_memcg_page_state(page, MEMCG_VMALLOC, -1);
+			/*
+			 * High-order allocs for huge vmallocs are split, so
+			 * can be freed as an array of order-0 allocations
+			 */
+			__free_pages(page, 0);
 			cond_resched();
 		}
 		atomic_long_sub(area->nr_pages, &nr_vmalloc_pages);
@@ -2914,12 +2917,7 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			if (nr != nr_pages_request)
 				break;
 		}
-	} else
-		/*
-		 * Compound pages required for remap_vmalloc_page if
-		 * high-order pages.
-		 */
-		gfp |= __GFP_COMP;
+	}
 
 	/* High-order pages or fallback path if "bulk" fails. */
 
@@ -2933,6 +2931,15 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			page = alloc_pages_node(nid, gfp, order);
 		if (unlikely(!page))
 			break;
+		/*
+		 * Higher order allocations must be able to be treated as
+		 * indepdenent small pages by callers (as they can with
+		 * small-page vmallocs). Some drivers do their own refcounting
+		 * on vmalloc_to_page() pages, some use page->mapping,
+		 * page->lru, etc.
+		 */
+		if (order)
+			split_page(page, order);
 
 		/*
 		 * Careful, we allocate and map page-order pages, but
@@ -2992,11 +2999,10 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 	if (gfp_mask & __GFP_ACCOUNT) {
-		int i, step = 1U << page_order;
+		int i;
 
-		for (i = 0; i < area->nr_pages; i += step)
-			mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC,
-					     step);
+		for (i = 0; i < area->nr_pages; i++)
+			mod_memcg_page_state(area->pages[i], MEMCG_VMALLOC, 1);
 	}
 
 	/*