summaryrefslogtreecommitdiff
path: root/mm/vmalloc.c
diff options
context:
space:
mode:
authorVishal Moola (Oracle) <vishal.moola@gmail.com>2025-10-21 12:44:56 -0700
committerAndrew Morton <akpm@linux-foundation.org>2025-11-16 17:28:15 -0800
commita0615780439938e8e61343f1f92a4c54a71dc6a5 (patch)
tree52bc877a7737b271bb4316c5b25222440a572dea /mm/vmalloc.c
parent645a3c4243473d5c8b780927d2cc573e3da5a20c (diff)
mm/vmalloc: request large order pages from buddy allocator
Sometimes, vm_area_alloc_pages() will want many pages from the buddy allocator. Rather than making requests to the buddy allocator for at most 100 pages at a time, we can eagerly request large order pages a smaller number of times. We still split the large order pages down to order-0 as the rest of the vmalloc code (and some callers) depend on it. We still defer to the bulk allocator and fallback path in case of order-0 pages or failure. Running 1000 iterations of allocations on a small 4GB system finds: 1000 2mb allocations: [Baseline] [This patch] real 46.310s real 0m34.582 user 0.001s user 0.006s sys 46.058s sys 0m34.365s 10000 200kb allocations: [Baseline] [This patch] real 56.104s real 0m43.696 user 0.001s user 0.003s sys 55.375s sys 0m42.995s Link: https://lkml.kernel.org/r/20251021194455.33351-2-vishal.moola@gmail.com Signed-off-by: Vishal Moola (Oracle) <vishal.moola@gmail.com> Reviewed-by: Uladzislau Rezki (Sony) <urezki@gmail.com> Signed-off-by: Andrew Morton <akpm@linux-foundation.org>
Diffstat (limited to 'mm/vmalloc.c')
-rw-r--r--mm/vmalloc.c36
1 files changed, 36 insertions, 0 deletions
diff --git a/mm/vmalloc.c b/mm/vmalloc.c
index adde450ddf5e..0832f944544c 100644
--- a/mm/vmalloc.c
+++ b/mm/vmalloc.c
@@ -3619,8 +3619,44 @@ vm_area_alloc_pages(gfp_t gfp, int nid,
unsigned int order, unsigned int nr_pages, struct page **pages)
{
unsigned int nr_allocated = 0;
+ unsigned int nr_remaining = nr_pages;
+ unsigned int max_attempt_order = MAX_PAGE_ORDER;
struct page *page;
int i;
+ gfp_t large_gfp = (gfp &
+ ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL | __GFP_COMP))
+ | __GFP_NOWARN;
+ unsigned int large_order = ilog2(nr_remaining);
+
+ large_order = min(max_attempt_order, large_order);
+
+ /*
+ * Initially, attempt to have the page allocator give us large order
+ * pages. Do not attempt allocating smaller than order chunks since
+ * __vmap_pages_range() expects physically contigous pages of exactly
+ * order long chunks.
+ */
+ while (large_order > order && nr_remaining) {
+ if (nid == NUMA_NO_NODE)
+ page = alloc_pages_noprof(large_gfp, large_order);
+ else
+ page = alloc_pages_node_noprof(nid, large_gfp, large_order);
+
+ if (unlikely(!page)) {
+ max_attempt_order = --large_order;
+ continue;
+ }
+
+ split_page(page, large_order);
+ for (i = 0; i < (1U << large_order); i++)
+ pages[nr_allocated + i] = page + i;
+
+ nr_allocated += 1U << large_order;
+ nr_remaining = nr_pages - nr_allocated;
+
+ large_order = ilog2(nr_remaining);
+ large_order = min(max_attempt_order, large_order);
+ }
/*
* For order-0 pages we make use of bulk allocator, if