Skip to contentSkip to conversation

infiniband/mm: convert put_page() to put_user_page*()

PATCH Superseded [email protected] 5 participants 6 messages May 25, 2019 – May 27, 2019

Subsystems (5)
lore
Share & tools
lore
#0 lore raw

v2 cover infiniband/mm: convert put_page() to put_user_page*()

From: John Hubbard <[email protected]>

Hi Jason and all,

I've added Jerome's and Ira's Reviewed-by tags. Other than that, this patch is the same as v1.

==========================================================================
Earlier cover letter:

IIUC, now that we have the put_user_pages() merged in to linux.git, we can start sending up the callsite conversions via different subsystem maintainer trees. Here's one for linux-rdma.

I've left the various Reviewed-by: and Tested-by: tags on here, even though it's been through a few rebases.

If anyone has hardware, it would be good to get a real test of this.

thanks,
--
John Hubbard
NVIDIA

Cc Doug Ledford <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Mike Marciniszyn <[email protected]>
Cc Dennis Dalessandro <[email protected]>
Cc Christian Benvenuti <[email protected]>
Cc Jan Kara <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Ira Weiny <[email protected]>
Cc Jérôme Glisse <[email protected]>

John Hubbard (1):
infiniband/mm: convert put_page() to put_user_page*()

 drivers/infiniband/core/umem.c              |  7 ++++---
 drivers/infiniband/core/umem_odp.c          | 10 +++++-----
 drivers/infiniband/hw/hfi1/user_pages.c     | 11 ++++-------
 drivers/infiniband/hw/mthca/mthca_memfree.c |  6 +++---
 drivers/infiniband/hw/qib/qib_user_pages.c  | 11 ++++-------
 drivers/infiniband/hw/qib/qib_user_sdma.c   |  6 +++---
 drivers/infiniband/hw/usnic/usnic_uiom.c    |  7 ++++---
 7 files changed, 27 insertions(+), 31 deletions(-)
Signature · 1 line
2.21.0
#1 lore raw

PATCH v2 1/1 infiniband/mm: convert put_page() to put_user_page*()

From: John Hubbard <[email protected]>

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()"

Cc Doug Ledford <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Mike Marciniszyn <[email protected]>
Cc Dennis Dalessandro <[email protected]>
Cc Christian Benvenuti <[email protected]>
---
 drivers/infiniband/core/umem.c              |  7 ++++---
 drivers/infiniband/core/umem_odp.c          | 10 +++++-----
 drivers/infiniband/hw/hfi1/user_pages.c     | 11 ++++-------
 drivers/infiniband/hw/mthca/mthca_memfree.c |  6 +++---
 drivers/infiniband/hw/qib/qib_user_pages.c  | 11 ++++-------
 drivers/infiniband/hw/qib/qib_user_sdma.c   |  6 +++---
 drivers/infiniband/hw/usnic/usnic_uiom.c    |  7 ++++---
 7 files changed, 27 insertions(+), 31 deletions(-)
drivers/infiniband/core/umem.c +4 -3
index e7ea819fcb11..673f0d240b3e 100644
@@ -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
index f962b5bbfa40..17e46df3990a 100644
@@ -487,7 +487,7 @@ 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.
  */
@@ -536,7 +536,7 @@ 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);
@@ -659,7 +659,7 @@ 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;
 			}
 
@@ -686,8 +686,8 @@ 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],
-					      npages - (j + 1));
+				put_user_pages(&local_page_list[j+1],
+					       npages - (j + 1));
 			break;
 		}
 	}
drivers/infiniband/hw/hfi1/user_pages.c +4 -7
index 02eee8eff1db..b89a9b9aef7a 100644
@@ -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]);
-	}
+	if (dirty)
+		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
index 8ff0e90d7564..edccfd6e178f 100644
@@ -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
index f712fb7fa82f..bfbfbb7e0ff4 100644
@@ -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]);
-	}
+	if (dirty)
+		put_user_pages_dirty_lock(p, num_pages);
+	else
+		put_user_pages(p, num_pages);
 }
 
 /**
drivers/infiniband/hw/qib/qib_user_sdma.c +3 -3
index 0c204776263f..ac5bdb02144f 100644
@@ -317,7 +317,7 @@ static int qib_user_sdma_page_to_frags(const struct qib_devdata *dd,
 		 * the caller can ignore this page.
 		 */
 		if (put) {
-			put_page(page);
+			put_user_page(page);
 		} else {
 			/* coalesce case */
 			kunmap(page);
@@ -631,7 +631,7 @@ static void qib_user_sdma_free_pkt_frag(struct device *dev,
 			kunmap(pkt->addr[i].page);
 
 		if (pkt->addr[i].put_page)
-			put_page(pkt->addr[i].page);
+			put_user_page(pkt->addr[i].page);
 		else
 			__free_page(pkt->addr[i].page);
 	} else if (pkt->addr[i].kvaddr) {
@@ -706,7 +706,7 @@ static int qib_user_sdma_pin_pages(const struct qib_devdata *dd,
 	/* if error, return all pages not managed by pkt */
 free_pages:
 	while (i < j)
-		put_page(pages[i++]);
+		put_user_page(pages[i++]);
 
 done:
 	return ret;
drivers/infiniband/hw/usnic/usnic_uiom.c +4 -3
index e312f522a66d..0b0237d41613 100644
@@ -75,9 +75,10 @@ static void usnic_uiom_put_pages(struct list_head *chunk_list, int dirty)
 		for_each_sg(chunk->page_list, sg, chunk->nents, i) {
 			page = sg_page(sg);
 			pa = sg_phys(sg);
-			if (!PageDirty(page) && dirty)
-				set_page_dirty_lock(page);
-			put_page(page);
+			if (dirty)
+				put_user_pages_dirty_lock(&page, 1);
+			else
+				put_user_page(page);
 			usnic_dbg("pa: %pa\n", &pa);
 		}
 		kfree(chunk);
Signature · 1 line
2.21.0
#2 lore raw
Quoted 3 lines · On Fri, May 24, 2019 at 06:45:22PM -0700, [email protected] wrote:

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()

I have no objection to this particular patch, but ...

Quoted 10 lines

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.

Quoted 8 lines

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.

I thought we agreed at LSFMM that the future is a new get_user_bvec() / put_user_bvec(). This is largely going to touch the same places as step 2 in your list above. Is it worth doing step 2?

One of the advantages of put_user_bvec() is that it would be quite easy to miss a conversion from put_page() to put_user_page(), but it'll be a type error to miss a conversion from put_page() to put_user_bvec().

#3 lore raw
Quoted 7 lines · Matthew Wilcox

I thought we agreed at LSFMM that the future is a new get_user_bvec() / put_user_bvec(). This is largely going to touch the same places as step 2 in your list above. Is it worth doing step 2?

One of the advantages of put_user_bvec() is that it would be quite easy to miss a conversion from put_page() to put_user_page(), but it'll be a type error to miss a conversion from put_page() to put_user_bvec().

FYI, I've got a prototype for get_user_pages_bvec. I'll post a RFC series in a few days.

#4 lore raw
In reply to Matthew Wilcox
Quoted 21 lines · Matthew Wilcox
Quoted 3 lines · On Fri, May 24, 2019 at 06:45:22PM -0700, [email protected] wrote:

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()

I have no objection to this particular patch, but ...

Quoted 14 lines

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.

Quoted 8 lines
Quoted 4 lines

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.

I thought we agreed at LSFMM that the future is a new get_user_bvec() / put_user_bvec(). This is largely going to touch the same places as step 2 in your list above. Is it worth doing step 2?

I think so, as these two conversions can run in parallel, whichever we finish first, biovec or put_user_pages lets John progress to step #3

Jason

#5 lore raw
In reply to [email protected]
Quoted 40 lines · On Fri, May 24, 2019 at 06:45:22PM -0700, [email protected] wrote:

From: John Hubbard <[email protected]>

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()"

Cc Doug Ledford <[email protected]>
Cc Jason Gunthorpe <[email protected]>
Cc Mike Marciniszyn <[email protected]>
Cc Dennis Dalessandro <[email protected]>
Cc Christian Benvenuti <[email protected]>
Quoted 9 lines
---
 drivers/infiniband/core/umem.c              |  7 ++++---
 drivers/infiniband/core/umem_odp.c          | 10 +++++-----
 drivers/infiniband/hw/hfi1/user_pages.c     | 11 ++++-------
 drivers/infiniband/hw/mthca/mthca_memfree.c |  6 +++---
 drivers/infiniband/hw/qib/qib_user_pages.c  | 11 ++++-------
 drivers/infiniband/hw/qib/qib_user_sdma.c   |  6 +++---
 drivers/infiniband/hw/usnic/usnic_uiom.c    |  7 ++++---
 7 files changed, 27 insertions(+), 31 deletions(-)

Applied to for-next, thanks

Jason