Re: [RESEND PATCH v1] mm/vmalloc: fix page mapping if vm_area_alloc_pages() with high order fallback to order 0

[Uladzislau Rezki <urezki@gmail.com>]

Hello, Michal.

> 
> Let me clarify what I would like to have clarified:
> 
> diff --git a/mm/vmalloc.c b/mm/vmalloc.c
> index 6b783baf12a1..fea90a39f5c5 100644
> --- a/mm/vmalloc.c
> +++ b/mm/vmalloc.c
> @@ -3510,13 +3510,13 @@ void *vmap_pfn(unsigned long *pfns, unsigned int count, pgprot_t prot)
>  EXPORT_SYMBOL_GPL(vmap_pfn);
>  #endif /* CONFIG_VMAP_PFN */
>  
> +/* GFP_NOFAIL semantic is implemented by __vmalloc_node_range_noprof */
>  static inline unsigned int
>  vm_area_alloc_pages(gfp_t gfp, int nid,
>  		unsigned int order, unsigned int nr_pages, struct page **pages)
>  {
>  	unsigned int nr_allocated = 0;
> -	gfp_t alloc_gfp = gfp;
> -	bool nofail = gfp & __GFP_NOFAIL;
> +	gfp_t alloc_gfp = gfp & ~ __GFP_NOFAIL;
>  	struct page *page;
>  	int i;
>  
> @@ -3527,9 +3527,6 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>  	 * more permissive.
>  	 */
>  	if (!order) {
> -		/* bulk allocator doesn't support nofail req. officially */
> -		gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL;
> -
>  		while (nr_allocated < nr_pages) {
>  			unsigned int nr, nr_pages_request;
>  
> @@ -3547,12 +3544,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>  			 * but mempolicy wants to alloc memory by interleaving.
>  			 */
>  			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
> -				nr = alloc_pages_bulk_array_mempolicy_noprof(bulk_gfp,
> +				nr = alloc_pages_bulk_array_mempolicy_noprof(alloc_gfp,
>  							nr_pages_request,
>  							pages + nr_allocated);
>  
>  			else
> -				nr = alloc_pages_bulk_array_node_noprof(bulk_gfp, nid,
> +				nr = alloc_pages_bulk_array_node_noprof(alloc_gfp, nid,
>  							nr_pages_request,
>  							pages + nr_allocated);
>  
> @@ -3566,13 +3563,6 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
>  			if (nr != nr_pages_request)
>  				break;
>  		}
> -	} else if (gfp & __GFP_NOFAIL) {
> -		/*
> -		 * Higher order nofail allocations are really expensive and
> -		 * potentially dangerous (pre-mature OOM, disruptive reclaim
> -		 * and compaction etc.
> -		 */
> -		alloc_gfp &= ~__GFP_NOFAIL;
>  	}
>  
>  	/* High-order pages or fallback path if "bulk" fails. */
> -- 
>
See below the change. It does not do any functional change and it is rather
a small refactoring, which includes the comment i wanted to add and what you
wanted to be clarified(if i got you correctly):

<snip>
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index 3f9b6bd707d2..24fad2e48799 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3531,8 +3531,6 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 		unsigned int order, unsigned int nr_pages, struct page **pages)
 {
 	unsigned int nr_allocated = 0;
-	gfp_t alloc_gfp = gfp;
-	bool nofail = gfp & __GFP_NOFAIL;
 	struct page *page;
 	int i;
 
@@ -3543,9 +3541,6 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 	 * more permissive.
 	 */
 	if (!order) {
-		/* bulk allocator doesn't support nofail req. officially */
-		gfp_t bulk_gfp = gfp & ~__GFP_NOFAIL;
-
 		while (nr_allocated < nr_pages) {
 			unsigned int nr, nr_pages_request;
 
@@ -3563,12 +3558,12 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			 * but mempolicy wants to alloc memory by interleaving.
 			 */
 			if (IS_ENABLED(CONFIG_NUMA) && nid == NUMA_NO_NODE)
-				nr = alloc_pages_bulk_array_mempolicy_noprof(bulk_gfp,
+				nr = alloc_pages_bulk_array_mempolicy_noprof(gfp & ~__GFP_NOFAIL,
 							nr_pages_request,
 							pages + nr_allocated);
-
 			else
-				nr = alloc_pages_bulk_array_node_noprof(bulk_gfp, nid,
+				/* bulk allocator doesn't support nofail req. officially */
+				nr = alloc_pages_bulk_array_node_noprof(gfp & ~__GFP_NOFAIL, nid,
 							nr_pages_request,
 							pages + nr_allocated);
 
@@ -3582,24 +3577,18 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
 			if (nr != nr_pages_request)
 				break;
 		}
-	} else if (gfp & __GFP_NOFAIL) {
-		/*
-		 * Higher order nofail allocations are really expensive and
-		 * potentially dangerous (pre-mature OOM, disruptive reclaim
-		 * and compaction etc.
-		 */
-		alloc_gfp &= ~__GFP_NOFAIL;
 	}
 
 	/* High-order pages or fallback path if "bulk" fails. */
 	while (nr_allocated < nr_pages) {
-		if (!nofail && fatal_signal_pending(current))
+		if (!(gfp & __GFP_NOFAIL) && fatal_signal_pending(current))
 			break;
 
 		if (nid == NUMA_NO_NODE)
-			page = alloc_pages_noprof(alloc_gfp, order);
+			page = alloc_pages_noprof(gfp, order);
 		else
-			page = alloc_pages_node_noprof(nid, alloc_gfp, order);
+			page = alloc_pages_node_noprof(nid, gfp, order);
+
 		if (unlikely(!page))
 			break;
 
@@ -3666,7 +3655,16 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
 	page_order = vm_area_page_order(area);
 
-	area->nr_pages = vm_area_alloc_pages(gfp_mask | __GFP_NOWARN,
+	/*
+	 * Higher order nofail allocations are really expensive and
+	 * potentially dangerous (pre-mature OOM, disruptive reclaim
+	 * and compaction etc.
+	 *
+	 * Please note, the __vmalloc_node_range_noprof() falls-back
+	 * to order-0 pages if high-order attempt has been unsuccessful.
+	 */
+	area->nr_pages = vm_area_alloc_pages(page_order ?
+		gfp_mask &= ~__GFP_NOFAIL : gfp_mask | __GFP_NOWARN,
 		node, page_order, nr_small_pages, area->pages);
 
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
<snip>

Is that aligned with your wish?

Thanks!

--
Uladzislau Rezki