[PATCH RFC 8/9] RDMA/umem: batch page unpin in __ib_mem_release()

[Joao Martins <joao.m.martins@oracle.com>]

Take advantage of the newly added unpin_user_pages() batched
refcount update, by calculating a page array from an SGL
(same size as the one used in ib_mem_get()) and call
unpin_user_pages() with that.

unpin_user_pages() will check on consecutive pages that belong
to the same compound page set and batch the refcount update in
a single write.

Running a test program which calls mr reg/unreg on a 1G in size
and measures cost of both operations together (in a guest using rxe)
with device-dax and hugetlbfs:

Before:
159 rounds in 5.027 sec: 31617.923 usec / round (device-dax)
466 rounds in 5.009 sec: 10748.456 usec / round (hugetlbfs)

After:
 305 rounds in 5.010 sec: 16426.047 usec / round (device-dax)
1073 rounds in 5.004 sec: 4663.622 usec / round (hugetlbfs)

We also see similar improvements on a setup with pmem and RDMA hardware.

Signed-off-by: Joao Martins <joao.m.martins@oracle.com>
---
 drivers/infiniband/core/umem.c | 25 ++++++++++++++++++++++---
 1 file changed, 22 insertions(+), 3 deletions(-)

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index e9fecbdf391b..493cfdcf7381 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -44,20 +44,40 @@
 
 #include "uverbs.h"
 
+#define PAGES_PER_LIST (PAGE_SIZE / sizeof(struct page *))
+
 static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)
 {
+	bool make_dirty = umem->writable && dirty;
+	struct page **page_list = NULL;
 	struct sg_page_iter sg_iter;
+	unsigned long nr = 0;
 	struct page *page;
 
+	page_list = (struct page **) __get_free_page(GFP_KERNEL);
+
 	if (umem->nmap > 0)
 		ib_dma_unmap_sg(dev, umem->sg_head.sgl, umem->sg_nents,
 				DMA_BIDIRECTIONAL);
 
 	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {
 		page = sg_page_iter_page(&sg_iter);
-		unpin_user_pages_dirty_lock(&page, 1, umem->writable && dirty);
+		if (page_list)
+			page_list[nr++] = page;
+
+		if (!page_list) {
+			unpin_user_pages_dirty_lock(&page, 1, make_dirty);
+		} else if (nr == PAGES_PER_LIST) {
+			unpin_user_pages_dirty_lock(page_list, nr, make_dirty);
+			nr = 0;
+		}
 	}
 
+	if (nr)
+		unpin_user_pages_dirty_lock(page_list, nr, make_dirty);
+
+	if (page_list)
+		free_page((unsigned long) page_list);
 	sg_free_table(&umem->sg_head);
 }
 
@@ -212,8 +232,7 @@ struct ib_umem *ib_umem_get(struct ib_device *device, unsigned long addr,
 		cond_resched();
 		ret = pin_user_pages_fast(cur_base,
 					  min_t(unsigned long, npages,
-						PAGE_SIZE /
-						sizeof(struct page *)),
+						PAGES_PER_LIST),
 					  gup_flags | FOLL_LONGTERM, page_list);
 		if (ret < 0)
 			goto umem_release;
-- 
2.17.1