It is needed 4095 pages(1G) or 7 pages(2M) to be allocated once in
alloc_vmemmap_page_list(), so let's add a bulk allocator varietas
alloc_pages_bulk_list_node() and switch alloc_vmemmap_page_list()
to use it to accelerate page allocation.
Simple test on arm64's qemu with 1G Hugetlb, 870,842ns vs 3,845,252ns,
even if there is a certain fluctuation, it is still a nice improvement.
Tested-by: Yuan Can <yuancan@xxxxxxxxxx>
Signed-off-by: Kefeng Wang <wangkefeng.wang@xxxxxxxxxx>
---
resend: fix allocated spell and decrease nr_pages in fallback logical
include/linux/gfp.h | 9 +++++++++
mm/hugetlb_vmemmap.c | 6 ++++++
2 files changed, 15 insertions(+)
diff --git a/include/linux/gfp.h b/include/linux/gfp.h
index 665f06675c83..d6e82f15b61f 100644
--- a/include/linux/gfp.h
+++ b/include/linux/gfp.h
@@ -195,6 +195,15 @@ alloc_pages_bulk_list(gfp_t gfp, unsigned long nr_pages, struct list_head *list)
return __alloc_pages_bulk(gfp, numa_mem_id(), NULL, nr_pages, list, NULL);
}
+static inline unsigned long
+alloc_pages_bulk_list_node(gfp_t gfp, int nid, unsigned long nr_pages, struct list_head *list)
+{
+ if (nid == NUMA_NO_NODE)
+ nid = numa_mem_id();
+
+ return __alloc_pages_bulk(gfp, nid, NULL, nr_pages, list, NULL);
+}
+
static inline unsigned long
alloc_pages_bulk_array(gfp_t gfp, unsigned long nr_pages, struct page **page_array)
{
diff --git a/mm/hugetlb_vmemmap.c b/mm/hugetlb_vmemmap.c
index 4b9734777f69..786e581703c7 100644
--- a/mm/hugetlb_vmemmap.c
+++ b/mm/hugetlb_vmemmap.c
@@ -384,7 +384,13 @@ static int alloc_vmemmap_page_list(unsigned long start, unsigned long end,
unsigned long nr_pages = (end - start) >> PAGE_SHIFT;
int nid = page_to_nid((struct page *)start);
struct page *page, *next;
+ unsigned long nr_allocated;
+ nr_allocated = alloc_pages_bulk_list_node(gfp_mask, nid, nr_pages, list);
+ if (!nr_allocated)
+ return -ENOMEM;
+
+ nr_pages -= nr_allocated;
while (nr_pages--) {
page = alloc_pages_node(nid, gfp_mask, 0);
if (!page)
--
2.27.0
