summaryrefslogtreecommitdiff
path: root/drivers/infiniband
diff options
context:
space:
mode:
authorJoao Martins <joao.m.martins@oracle.com>2021-04-29 22:55:53 -0700
committerLinus Torvalds <torvalds@linux-foundation.org>2021-04-30 11:20:37 -0700
commit1d4b0166e36334c3f32686a336bb25dd904fce2b (patch)
tree84b6fb8f6b815e2661b099bbcf3091cbc43d35c9 /drivers/infiniband
parent458a4f788f8602e5701b3d8c2fb6b021310a7301 (diff)
RDMA/umem: batch page unpin in __ib_umem_release()
Use the newly added unpin_user_page_range_dirty_lock() for more quickly unpinning a consecutive range of pages represented as compound pages. This will also calculate number of pages to unpin (for the tail pages which matching head page) and thus batch the refcount update. Running a test program which calls memory range reg/unreg on a region 1G in size and measures cost of both operations together (in a guest using rxe) with THP and hugetlbfs: Before: 590 rounds in 5.003 sec: 8480.335 usec / round 6898 rounds in 60.001 sec: 8698.367 usec / round After: 2688 rounds in 5.002 sec: 1860.786 usec / round 32517 rounds in 60.001 sec: 1845.225 usec / round Link: https://lkml.kernel.org/r/20210212130843.13865-5-joao.m.martins@oracle.com Signed-off-by: Joao Martins <joao.m.martins@oracle.com> Acked-by: Jason Gunthorpe <jgg@nvidia.com> Cc: Christoph Hellwig <hch@infradead.org> Cc: Doug Ledford <dledford@redhat.com> Cc: John Hubbard <jhubbard@nvidia.com> Cc: Matthew Wilcox <willy@infradead.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'drivers/infiniband')
-rw-r--r--drivers/infiniband/core/umem.c12
1 files changed, 6 insertions, 6 deletions
diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index 2dde99a9ba07..9b607013e2a2 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -47,17 +47,17 @@
static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int dirty)
{
- struct sg_page_iter sg_iter;
- struct page *page;
+ bool make_dirty = umem->writable && dirty;
+ struct scatterlist *sg;
+ unsigned int i;
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);
- }
+ for_each_sg(umem->sg_head.sgl, sg, umem->sg_nents, i)
+ unpin_user_page_range_dirty_lock(sg_page(sg),
+ DIV_ROUND_UP(sg->length, PAGE_SIZE), make_dirty);
sg_free_table(&umem->sg_head);
}