Merge tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma

Pull rdma updates from Jason Gunthorpe:

 - Usual minor updates and fixes for bnxt_re, hfi1, rxe, mana, iser,
   mlx5, vmw_pvrdma, hns

 - Make rxe work on tun devices

 - mana gains more standard verbs as it moves toward supporting
   in-kernel verbs

 - DMABUF support for mana

 - Fix page size calculations when memory registration exceeds 4G

 - On Demand Paging support for rxe

 - mlx5 support for RDMA TRANSPORT flow tables and a new ucap mechanism
   to access control use of them

 - Optional RDMA_TX/RX counters per QP in mlx5

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (73 commits)
  IB/mad: Check available slots before posting receive WRs
  RDMA/mana_ib: Fix integer overflow during queue creation
  RDMA/mlx5: Fix calculation of total invalidated pages
  RDMA/mlx5: Fix mlx5_poll_one() cur_qp update flow
  RDMA/mlx5: Fix page_size variable overflow
  RDMA/mlx5: Drop access_flags from _mlx5_mr_cache_alloc()
  RDMA/mlx5: Fix cache entry update on dereg error
  RDMA/mlx5: Fix MR cache initialization error flow
  RDMA/mlx5: Support optional-counters binding for QPs
  RDMA/mlx5: Compile fs.c regardless of INFINIBAND_USER_ACCESS config
  RDMA/core: Pass port to counter bind/unbind operations
  RDMA/core: Add support to optional-counters binding configuration
  RDMA/core: Create and destroy rdma_counter using rdma_zalloc_drv_obj()
  RDMA/mlx5: Add optional counters for RDMA_TX/RX_packets/bytes
  RDMA/core: Fix use-after-free when rename device name
  RDMA/bnxt_re: Support perf management counters
  RDMA/rxe: Fix incorrect return value of rxe_odp_atomic_op()
  RDMA/uverbs: Propagate errors from rdma_lookup_get_uobject()
  RDMA/mana_ib: Handle net event for pointing to the current netdev
  net: mana: Change the function signature of mana_get_primary_netdev_rcu
  ...

1 files changed, 105 insertions, 0 deletions

diff --git a/drivers/infiniband/hw/mana/mr.c b/drivers/infiniband/hw/mana/mr.c
index 887b09dd86e7..f99557ec7767 100644
--- a/drivers/infiniband/hw/mana/mr.c
+++ b/drivers/infiniband/hw/mana/mr.c
@@ -8,6 +8,8 @@
 #define VALID_MR_FLAGS                                                         \
 	(IB_ACCESS_LOCAL_WRITE | IB_ACCESS_REMOTE_WRITE | IB_ACCESS_REMOTE_READ)
 
+#define VALID_DMA_MR_FLAGS (IB_ACCESS_LOCAL_WRITE)
+
 static enum gdma_mr_access_flags
 mana_ib_verbs_to_gdma_access_flags(int access_flags)
 {
@@ -39,6 +41,8 @@ static int mana_ib_gd_create_mr(struct mana_ib_dev *dev, struct mana_ib_mr *mr,
 	req.mr_type = mr_params->mr_type;
 
 	switch (mr_params->mr_type) {
+	case GDMA_MR_TYPE_GPA:
+		break;
 	case GDMA_MR_TYPE_GVA:
 		req.gva.dma_region_handle = mr_params->gva.dma_region_handle;
 		req.gva.virtual_address = mr_params->gva.virtual_address;
@@ -169,6 +173,107 @@ err_free:
 	return ERR_PTR(err);
 }
 
+struct ib_mr *mana_ib_reg_user_mr_dmabuf(struct ib_pd *ibpd, u64 start, u64 length,
+					 u64 iova, int fd, int access_flags,
+					 struct uverbs_attr_bundle *attrs)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct gdma_create_mr_params mr_params = {};
+	struct ib_device *ibdev = ibpd->device;
+	struct ib_umem_dmabuf *umem_dmabuf;
+	struct mana_ib_dev *dev;
+	struct mana_ib_mr *mr;
+	u64 dma_region_handle;
+	int err;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	access_flags &= ~IB_ACCESS_OPTIONAL;
+	if (access_flags & ~VALID_MR_FLAGS)
+		return ERR_PTR(-EOPNOTSUPP);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	umem_dmabuf = ib_umem_dmabuf_get_pinned(ibdev, start, length, fd, access_flags);
+	if (IS_ERR(umem_dmabuf)) {
+		err = PTR_ERR(umem_dmabuf);
+		ibdev_dbg(ibdev, "Failed to get dmabuf umem, %d\n", err);
+		goto err_free;
+	}
+
+	mr->umem = &umem_dmabuf->umem;
+
+	err = mana_ib_create_dma_region(dev, mr->umem, &dma_region_handle, iova);
+	if (err) {
+		ibdev_dbg(ibdev, "Failed create dma region for user-mr, %d\n",
+			  err);
+		goto err_umem;
+	}
+
+	mr_params.pd_handle = pd->pd_handle;
+	mr_params.mr_type = GDMA_MR_TYPE_GVA;
+	mr_params.gva.dma_region_handle = dma_region_handle;
+	mr_params.gva.virtual_address = iova;
+	mr_params.gva.access_flags =
+		mana_ib_verbs_to_gdma_access_flags(access_flags);
+
+	err = mana_ib_gd_create_mr(dev, mr, &mr_params);
+	if (err)
+		goto err_dma_region;
+
+	/*
+	 * There is no need to keep track of dma_region_handle after MR is
+	 * successfully created. The dma_region_handle is tracked in the PF
+	 * as part of the lifecycle of this MR.
+	 */
+
+	return &mr->ibmr;
+
+err_dma_region:
+	mana_gd_destroy_dma_region(mdev_to_gc(dev), dma_region_handle);
+
+err_umem:
+	ib_umem_release(mr->umem);
+
+err_free:
+	kfree(mr);
+	return ERR_PTR(err);
+}
+
+struct ib_mr *mana_ib_get_dma_mr(struct ib_pd *ibpd, int access_flags)
+{
+	struct mana_ib_pd *pd = container_of(ibpd, struct mana_ib_pd, ibpd);
+	struct gdma_create_mr_params mr_params = {};
+	struct ib_device *ibdev = ibpd->device;
+	struct mana_ib_dev *dev;
+	struct mana_ib_mr *mr;
+	int err;
+
+	dev = container_of(ibdev, struct mana_ib_dev, ib_dev);
+
+	if (access_flags & ~VALID_DMA_MR_FLAGS)
+		return ERR_PTR(-EINVAL);
+
+	mr = kzalloc(sizeof(*mr), GFP_KERNEL);
+	if (!mr)
+		return ERR_PTR(-ENOMEM);
+
+	mr_params.pd_handle = pd->pd_handle;
+	mr_params.mr_type = GDMA_MR_TYPE_GPA;
+
+	err = mana_ib_gd_create_mr(dev, mr, &mr_params);
+	if (err)
+		goto err_free;
+
+	return &mr->ibmr;
+
+err_free:
+	kfree(mr);
+	return ERR_PTR(err);
+}
+
 int mana_ib_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata)
 {
 	struct mana_ib_mr *mr = container_of(ibmr, struct mana_ib_mr, ibmr);