From 3994586f4d7a1e8eb2a152405d0a1c9c8b947c4c Mon Sep 17 00:00:00 2001 From: Parav Pandit Date: Tue, 25 Sep 2018 12:04:04 +0300 Subject: [PATCH] RDMA/core: Acquire and release mmap_sem on page range Currently mmap_sem is read locked while pinning the memory. In a multi-threaded application of a process, holding mmap_sem lock creates contention with other threads who might be either registering memory, creating QPs or simply doing mmap() as such operations also require to hold the mmap_sem write lock. All such operation cannot make forward progress until one memory pin operation is completed. It becomes more worse if the memory is unpinned and/or memory registration is large (in GB range). Therefore, instead of holding mmap_sem for too long (for whole region pinning), acquire and release the lock for every few pages. For example on x86 with 4K page size, acquire and release mmap_sem for every 2Mbytes memory chunk. This allows other competing threads to make progress who might wish to hold mmap_sem for shorter duration. When memory registration latency is measured using [1] for memory sizes ranging from 4K to 48GB, <= 1% or 0.5% degradation is noticed. In many runs no difference is seen other than run-to-run variance. In other targeted tests of users with large memory, desired improvements are seen due to reduced contention of mmap_sem. [1] https://github.com/paravmellanox/rtool $ rdma_resource_lat -c 1 -s 48G -a -u L -i 500 -A It registers pinned memory from 4K to 48GB size with 500 iterations for each memory size. $ rdma_resource_lat -c 1 -s 12G -a -u L -i 500 -t 4 4 competing threads pin memory, each of 12GB size with 500 iterations. Signed-off-by: Parav Pandit Signed-off-by: Leon Romanovsky Signed-off-by: Jason Gunthorpe --- drivers/infiniband/core/umem.c | 7 +++++-- 1 file changed, 5 insertions(+), 2 deletions(-) diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c index 8da1cf29a69f..c6144df47ea4 100644 --- a/drivers/infiniband/core/umem.c +++ b/drivers/infiniband/core/umem.c @@ -181,8 +181,8 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, sg_list_start = umem->sg_head.sgl; - down_read(&mm->mmap_sem); while (npages) { + down_read(&mm->mmap_sem); ret = get_user_pages_longterm(cur_base, min_t(unsigned long, npages, PAGE_SIZE / sizeof (struct page *)), @@ -196,17 +196,20 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr, cur_base += ret * PAGE_SIZE; npages -= ret; + /* Continue to hold the mmap_sem as vma_list access + * needs to be protected. + */ for_each_sg(sg_list_start, sg, ret, i) { if (vma_list && !is_vm_hugetlb_page(vma_list[i])) umem->hugetlb = 0; sg_set_page(sg, page_list[i], PAGE_SIZE, 0); } + up_read(&mm->mmap_sem); /* preparing for next loop */ sg_list_start = sg; } - up_read(&mm->mmap_sem); umem->nmap = ib_dma_map_sg_attrs(context->device, umem->sg_head.sgl, -- 2.45.2