Commit ea996974 authored by John Hubbard's avatar John Hubbard Committed by Jason Gunthorpe
Browse files

RDMA: Convert put_page() to put_user_page*() 

For infiniband code that retains pages via get_user_pages*(), release
those pages via the new put_user_page(), or put_user_pages*(), instead of
put_page()

This is a tiny part of the second step of fixing the problem described in
[1]. The steps are:

1) Provide put_user_page*() routines, intended to be used for releasing
   pages that were pinned via get_user_pages*().

2) Convert all of the call sites for get_user_pages*(), to invoke
   put_user_page*(), instead of put_page(). This involves dozens of call
   sites, and will take some time.

3) After (2) is complete, use get_user_pages*() and put_user_page*() to
   implement tracking of these pages. This tracking will be separate from
   the existing struct page refcounting.

4) Use the tracking and identification of these pages, to implement
   special handling (especially in writeback paths) when the pages are
   backed by a filesystem. Again, [1] provides details as to why that is
   desirable.

[1] https://lwn.net/Articles/753027/

 : "The Trouble with get_user_pages()"

Reviewed-by: default avatarJan Kara <jack@suse.cz>
Reviewed-by: default avatarDennis Dalessandro <dennis.dalessandro@intel.com>
Reviewed-by: default avatarIra Weiny <ira.weiny@intel.com>
Reviewed-by: default avatarJérôme Glisse <jglisse@redhat.com>
Acked-by: default avatarJason Gunthorpe <jgg@mellanox.com>
Tested-by: default avatarIra Weiny <ira.weiny@intel.com>
Signed-off-by: default avatarJohn Hubbard <jhubbard@nvidia.com>
Signed-off-by: default avatarJason Gunthorpe <jgg@mellanox.com>
parent cfcc048c

drivers/infiniband/core/umem.c

+4 −3
Original line number Diff line number Diff line
@@ -54,9 +54,10 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d 


	for_each_sg_page(umem->sg_head.sgl, &sg_iter, umem->sg_nents, 0) {

		page = sg_page_iter_page(&sg_iter);

		if (!PageDirty(page) && umem->writable && dirty)

			set_page_dirty_lock(page);

		put_page(page);

		if (umem->writable && dirty)

			put_user_pages_dirty_lock(&page, 1);

		else

			put_user_page(page);

	}



	sg_free_table(&umem->sg_head);

drivers/infiniband/core/umem_odp.c

+5 −5
Original line number Diff line number Diff line
@@ -482,7 +482,7 @@ void ib_umem_odp_release(struct ib_umem_odp *umem_odp) 
 * The function returns -EFAULT if the DMA mapping operation fails. It returns

 * -EAGAIN if a concurrent invalidation prevents us from updating the page.

 *

 * The page is released via put_page even if the operation failed. For

 * The page is released via put_user_page even if the operation failed. For

 * on-demand pinning, the page is released whenever it isn't stored in the

 * umem.

 */
@@ -530,7 +530,7 @@ static int ib_umem_odp_map_dma_single_page( 
	}



out:

	put_page(page);

	put_user_page(page);



	if (remove_existing_mapping) {

		ib_umem_notifier_start_account(umem_odp);
@@ -653,7 +653,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt, 
					ret = -EFAULT;

					break;

				}

				put_page(local_page_list[j]);

				put_user_page(local_page_list[j]);

				continue;

			}
@@ -680,7 +680,7 @@ int ib_umem_odp_map_dma_pages(struct ib_umem_odp *umem_odp, u64 user_virt, 
			 * ib_umem_odp_map_dma_single_page().

			 */

			if (npages - (j + 1) > 0)

				release_pages(&local_page_list[j+1],

				put_user_pages(&local_page_list[j+1],

					       npages - (j + 1));

			break;

		}

drivers/infiniband/hw/hfi1/user_pages.c

+4 −7
Original line number Diff line number Diff line
@@ -118,13 +118,10 @@ int hfi1_acquire_user_pages(struct mm_struct *mm, unsigned long vaddr, size_t np 
void hfi1_release_user_pages(struct mm_struct *mm, struct page **p,

			     size_t npages, bool dirty)

{

	size_t i;



	for (i = 0; i < npages; i++) {

	if (dirty)

			set_page_dirty_lock(p[i]);

		put_page(p[i]);

	}

		put_user_pages_dirty_lock(p, npages);

	else

		put_user_pages(p, npages);



	if (mm) { /* during close after signal, mm can be NULL */

		atomic64_sub(npages, &mm->pinned_vm);

drivers/infiniband/hw/mthca/mthca_memfree.c

+3 −3
Original line number Diff line number Diff line
@@ -482,7 +482,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar, 


	ret = pci_map_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);

	if (ret < 0) {

		put_page(pages[0]);

		put_user_page(pages[0]);

		goto out;

	}
@@ -490,7 +490,7 @@ int mthca_map_user_db(struct mthca_dev *dev, struct mthca_uar *uar, 
				 mthca_uarc_virt(dev, uar, i));

	if (ret) {

		pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);

		put_page(sg_page(&db_tab->page[i].mem));

		put_user_page(sg_page(&db_tab->page[i].mem));

		goto out;

	}
@@ -556,7 +556,7 @@ void mthca_cleanup_user_db_tab(struct mthca_dev *dev, struct mthca_uar *uar, 
		if (db_tab->page[i].uvirt) {

			mthca_UNMAP_ICM(dev, mthca_uarc_virt(dev, uar, i), 1);

			pci_unmap_sg(dev->pdev, &db_tab->page[i].mem, 1, PCI_DMA_TODEVICE);

			put_page(sg_page(&db_tab->page[i].mem));

			put_user_page(sg_page(&db_tab->page[i].mem));

		}

	}

drivers/infiniband/hw/qib/qib_user_pages.c

+4 −7
Original line number Diff line number Diff line
@@ -40,13 +40,10 @@ 
static void __qib_release_user_pages(struct page **p, size_t num_pages,

				     int dirty)

{

	size_t i;



	for (i = 0; i < num_pages; i++) {

	if (dirty)

			set_page_dirty_lock(p[i]);

		put_page(p[i]);

	}

		put_user_pages_dirty_lock(p, num_pages);

	else

		put_user_pages(p, num_pages);

}



/**

CRA Git | Maintained and supported by SUSTech CRA and CCSE