IB/core: Add support for on demand paging regions

* Extend the umem struct to keep the ODP related data.
* Allocate and initialize the ODP related information in the umem
  (page_list, dma_list) and freeing as needed in the end of the run.
* Store a reference to the process PID struct in the ucontext.  Used to
  safely obtain the task_struct and the mm during fault handling,
  without preventing the task destruction if needed.
* Add 2 helper functions: ib_umem_odp_map_dma_pages and
  ib_umem_odp_unmap_dma_pages. These functions get the DMA addresses
  of specific pages of the umem (and, currently, pin them).
* Support for page faults only - IB core will keep the reference on
  the pages used and call put_page when freeing an ODP umem
  area. Invalidations support will be added in a later patch.

Signed-off-by: Sagi Grimberg <sagig@mellanox.com>
Signed-off-by: Shachar Raindel <raindel@mellanox.com>
Signed-off-by: Haggai Eran <haggaie@mellanox.com>
Signed-off-by: Majd Dibbiny <majd@mellanox.com>
Signed-off-by: Roland Dreier <roland@purestorage.com>

1 files changed, 24 insertions, 0 deletions

diff --git a/drivers/infiniband/core/umem.c b/drivers/infiniband/core/umem.c
index c328e4693d14..5baceb79f21b 100644
--- a/drivers/infiniband/core/umem.c
+++ b/drivers/infiniband/core/umem.c
@@ -39,6 +39,7 @@
 #include <linux/hugetlb.h>
 #include <linux/dma-attrs.h>
 #include <linux/slab.h>
+#include <rdma/ib_umem_odp.h>
 
 #include "uverbs.h"
 
@@ -69,6 +70,10 @@ static void __ib_umem_release(struct ib_device *dev, struct ib_umem *umem, int d
 
 /**
  * ib_umem_get - Pin and DMA map userspace memory.
+ *
+ * If access flags indicate ODP memory, avoid pinning. Instead, stores
+ * the mm for future page fault handling.
+ *
  * @context: userspace context to pin memory for
  * @addr: userspace virtual address to start at
  * @size: length of region to pin
@@ -117,6 +122,17 @@ struct ib_umem *ib_umem_get(struct ib_ucontext *context, unsigned long addr,
 		(IB_ACCESS_LOCAL_WRITE   | IB_ACCESS_REMOTE_WRITE |
 		 IB_ACCESS_REMOTE_ATOMIC | IB_ACCESS_MW_BIND));
 
+	if (access & IB_ACCESS_ON_DEMAND) {
+		ret = ib_umem_odp_get(context, umem);
+		if (ret) {
+			kfree(umem);
+			return ERR_PTR(ret);
+		}
+		return umem;
+	}
+
+	umem->odp_data = NULL;
+
 	/* We assume the memory is from hugetlb until proved otherwise */
 	umem->hugetlb   = 1;
 
@@ -237,6 +253,11 @@ void ib_umem_release(struct ib_umem *umem)
 	struct task_struct *task;
 	unsigned long diff;
 
+	if (umem->odp_data) {
+		ib_umem_odp_release(umem);
+		return;
+	}
+
 	__ib_umem_release(umem->context->device, umem, 1);
 
 	task = get_pid_task(umem->pid, PIDTYPE_PID);
@@ -285,6 +306,9 @@ int ib_umem_page_count(struct ib_umem *umem)
 	int n;
 	struct scatterlist *sg;
 
+	if (umem->odp_data)
+		return ib_umem_num_pages(umem);
+
 	shift = ilog2(umem->page_size);
 
 	n = 0;