IB/core: dma map/unmap locking optimizations

Currently, while mapping or unmapping pages for ODP, the umem mutex is locked
and unlocked once for each page. Such lock/unlock operation take few tens to
hundreds of nsecs. This makes a significant impact when mapping or unmapping few
MBs of memory.

To avoid this, the mutex should be locked only once per operation, and not per
page.

Signed-off-by: Guy Shapiro <guysh@mellanox.com>
Acked-by: Shachar Raindel <raindel@mellanox.com>
Reviewed-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Doug Ledford <dledford@redhat.com>

diff --git a/drivers/infiniband/core/umem_odp.c b/drivers/infiniband/core/umem_odp.c
index 8b8cc6fa0ab0c1ebf966b2ace4932807d9181bf1..aba47398880ddc5cb932b5935556844274f9c841 100644 (file)
--- a/drivers/infiniband/core/umem_odp.c
+++ b/drivers/infiniband/core/umem_odp.c
@@ -446,7 +446,6 @@ static int ib_umem_odp_map_dma_single_page(
        int remove_existing_mapping = 0;
        int ret = 0;
 
-       mutex_lock(&umem->odp_data->umem_mutex);
        /*
         * Note: we avoid writing if seq is different from the initial seq, to
         * handle case of a racing notifier. This check also allows us to bail
@@ -479,8 +478,6 @@ static int ib_umem_odp_map_dma_single_page(
        }
 
 out:
-       mutex_unlock(&umem->odp_data->umem_mutex);
-
        /* On Demand Paging - avoid pinning the page */
        if (umem->context->invalidate_range || !stored_page)
                put_page(page);
@@ -586,6 +583,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
 
                bcnt -= min_t(size_t, npages << PAGE_SHIFT, bcnt);
                user_virt += npages << PAGE_SHIFT;
+               mutex_lock(&umem->odp_data->umem_mutex);
                for (j = 0; j < npages; ++j) {
                        ret = ib_umem_odp_map_dma_single_page(
                                umem, k, base_virt_addr, local_page_list[j],
@@ -594,6 +592,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem *umem, u64 user_virt, u64 bcnt,
                                break;
                        k++;
                }
+               mutex_unlock(&umem->odp_data->umem_mutex);
 
                if (ret < 0) {
                        /* Release left over pages when handling errors. */
@@ -633,9 +632,9 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
         * faults from completion. We might be racing with other
         * invalidations, so we must make sure we free each page only
         * once. */
+       mutex_lock(&umem->odp_data->umem_mutex);
        for (addr = virt; addr < bound; addr += (u64)umem->page_size) {
                idx = (addr - ib_umem_start(umem)) / PAGE_SIZE;
-               mutex_lock(&umem->odp_data->umem_mutex);
                if (umem->odp_data->page_list[idx]) {
                        struct page *page = umem->odp_data->page_list[idx];
                        struct page *head_page = compound_head(page);
@@ -663,7 +662,7 @@ void ib_umem_odp_unmap_dma_pages(struct ib_umem *umem, u64 virt,
                        umem->odp_data->page_list[idx] = NULL;
                        umem->odp_data->dma_list[idx] = 0;
                }
-               mutex_unlock(&umem->odp_data->umem_mutex);
        }
+       mutex_unlock(&umem->odp_data->umem_mutex);
 }
 EXPORT_SYMBOL(ib_umem_odp_unmap_dma_pages);