[PATCH] mm/vmalloc: try alloc_pages_bulk first to get order 0 pages fast

[Yang Huan]

Vmalloc may offen get pages by loop invoke alloc_pags, this is
cost too much time in count watermark/cpuset or something.
Let's just try alloc by alloc_pages_bulk, if failed, fullback in
original path.

With my own test, simulate loop alloc_page and alloc_pages_bulk_array,
get this:
size		1M	10M	20M	30
normal		44	1278	3665	5581
test		34	889	2167	3300
optimize	22%	30%	40%	40%
And in my vmalloc top sort, zram/f2fs may alloc more than 20MB, so,
It's worth to use alloc_pages_bulk.

Signed-off-by: Yang Huan <link@xxxxxxxx>
---
 mm/vmalloc.c | 14 +++++++++++---
 1 file changed, 11 insertions(+), 3 deletions(-)

diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index a13ac524f6ff..b5af7b4e30bc 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -2791,17 +2791,23 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 	}
 
 	area->pages = pages;
-	area->nr_pages = nr_small_pages;
+	area->nr_pages = 0;
 	set_vm_area_page_order(area, page_shift - PAGE_SHIFT);
 
 	page_order = vm_area_page_order(area);
-
+	/* first try alloc in alloc bulk when order is 0*/
+	if (!page_order) {
+		area->nr_pages = alloc_pages_bulk_array(
+			gfp_mask, nr_small_pages, area->pages);
+		if (likely(area->nr_pages == nr_small_pages))
+			goto success;
+	}
 	/*
 	 * Careful, we allocate and map page_order pages, but tracking is done
 	 * per PAGE_SIZE page so as to keep the vm_struct APIs independent of
 	 * the physical/mapped size.
 	 */
-	for (i = 0; i < area->nr_pages; i += 1U << page_order) {
+	for (i = area->nr_pages; i < nr_small_pages; i += 1U << page_order) {
 		struct page *page;
 		int p;
 
@@ -2824,6 +2830,8 @@ static void *__vmalloc_area_node(struct vm_struct *area, gfp_t gfp_mask,
 		if (gfpflags_allow_blocking(gfp_mask))
 			cond_resched();
 	}
+	area->nr_pages = nr_small_pages;
+success:
 	atomic_long_add(area->nr_pages, &nr_vmalloc_pages);
 
 	if (vmap_pages_range(addr, addr + size, prot, pages, page_shift) < 0) {
-- 
2.32.0