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

Pull rdma updates from Jason Gunthorpe:
 "A smaller set of patches, nothing stands out as being particularly
  major this cycle. The biggest item would be the new HIP09 HW support
  from HNS, otherwise it was pretty quiet for new work here:

   - Driver bug fixes and updates: bnxt_re, cxgb4, rxe, hns, i40iw,
     cxgb4, mlx4 and mlx5

   - Bug fixes and polishing for the new rts ULP

   - Cleanup of uverbs checking for allowed driver operations

   - Use sysfs_emit all over the place

   - Lots of bug fixes and clarity improvements for hns

   - hip09 support for hns

   - NDR and 50/100Gb signaling rates

   - Remove dma_virt_ops and go back to using the IB DMA wrappers

   - mlx5 optimizations for contiguous DMA regions"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (147 commits)
  RDMA/cma: Don't overwrite sgid_attr after device is released
  RDMA/mlx5: Fix MR cache memory leak
  RDMA/rxe: Use acquire/release for memory ordering
  RDMA/hns: Simplify AEQE process for different types of queue
  RDMA/hns: Fix inaccurate prints
  RDMA/hns: Fix incorrect symbol types
  RDMA/hns: Clear redundant variable initialization
  RDMA/hns: Fix coding style issues
  RDMA/hns: Remove unnecessary access right set during INIT2INIT
  RDMA/hns: WARN_ON if get a reserved sl from users
  RDMA/hns: Avoid filling sl in high 3 bits of vlan_id
  RDMA/hns: Do shift on traffic class when using RoCEv2
  RDMA/hns: Normalization the judgment of some features
  RDMA/hns: Limit the length of data copied between kernel and userspace
  RDMA/mlx4: Remove bogus dev_base_lock usage
  RDMA/uverbs: Fix incorrect variable type
  RDMA/core: Do not indicate device ready when device enablement fails
  RDMA/core: Clean up cq pool mechanism
  RDMA/core: Update kernel documentation for ib_create_named_qp()
  MAINTAINERS: SOFT-ROCE: Change Zhu Yanjun's email address
  ...

1 files changed, 43 insertions, 47 deletions

diff --git a/drivers/infiniband/hw/mlx5/devx.c b/drivers/infiniband/hw/mlx5/devx.c
index 9e3d8b826498..819c142857d6 100644
--- a/drivers/infiniband/hw/mlx5/devx.c
+++ b/drivers/infiniband/hw/mlx5/devx.c
@@ -93,9 +93,6 @@ struct devx_async_event_file {
 struct devx_umem {
 	struct mlx5_core_dev		*mdev;
 	struct ib_umem			*umem;
-	u32				page_offset;
-	int				page_shift;
-	int				ncont;
 	u32				dinlen;
 	u32				dinbox[MLX5_ST_SZ_DW(general_obj_in_cmd_hdr)];
 };
@@ -1311,7 +1308,7 @@ static int devx_obj_cleanup(struct ib_uobject *uobject,
 	else
 		ret = mlx5_cmd_exec(obj->ib_dev->mdev, obj->dinbox,
 				    obj->dinlen, out, sizeof(out));
-	if (ib_is_destroy_retryable(ret, why, uobject))
+	if (ret)
 		return ret;
 
 	devx_event_table = &dev->devx_event_table;
@@ -2057,9 +2054,7 @@ static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext,
 	u64 addr;
 	size_t size;
 	u32 access;
-	int npages;
 	int err;
-	u32 page_mask;
 
 	if (uverbs_copy_from(&addr, attrs, MLX5_IB_ATTR_DEVX_UMEM_REG_ADDR) ||
 	    uverbs_copy_from(&size, attrs, MLX5_IB_ATTR_DEVX_UMEM_REG_LEN))
@@ -2073,57 +2068,62 @@ static int devx_umem_get(struct mlx5_ib_dev *dev, struct ib_ucontext *ucontext,
 	if (err)
 		return err;
 
-	err = ib_check_mr_access(access);
+	err = ib_check_mr_access(&dev->ib_dev, access);
 	if (err)
 		return err;
 
 	obj->umem = ib_umem_get(&dev->ib_dev, addr, size, access);
 	if (IS_ERR(obj->umem))
 		return PTR_ERR(obj->umem);
-
-	mlx5_ib_cont_pages(obj->umem, obj->umem->address,
-			   MLX5_MKEY_PAGE_SHIFT_MASK, &npages,
-			   &obj->page_shift, &obj->ncont, NULL);
-
-	if (!npages) {
-		ib_umem_release(obj->umem);
-		return -EINVAL;
-	}
-
-	page_mask = (1 << obj->page_shift) - 1;
-	obj->page_offset = obj->umem->address & page_mask;
-
 	return 0;
 }
 
-static int devx_umem_reg_cmd_alloc(struct uverbs_attr_bundle *attrs,
+static int devx_umem_reg_cmd_alloc(struct mlx5_ib_dev *dev,
+				   struct uverbs_attr_bundle *attrs,
 				   struct devx_umem *obj,
 				   struct devx_umem_reg_cmd *cmd)
 {
+	unsigned int page_size;
+	__be64 *mtt;
+	void *umem;
+
+	/*
+	 * We don't know what the user intends to use this umem for, but the HW
+	 * restrictions must be met. MR, doorbell records, QP, WQ and CQ all
+	 * have different requirements. Since we have no idea how to sort this
+	 * out, only support PAGE_SIZE with the expectation that userspace will
+	 * provide the necessary alignments inside the known PAGE_SIZE and that
+	 * FW will check everything.
+	 */
+	page_size = ib_umem_find_best_pgoff(
+		obj->umem, PAGE_SIZE,
+		__mlx5_page_offset_to_bitmask(__mlx5_bit_sz(umem, page_offset),
+					      0));
+	if (!page_size)
+		return -EINVAL;
+
 	cmd->inlen = MLX5_ST_SZ_BYTES(create_umem_in) +
-		    (MLX5_ST_SZ_BYTES(mtt) * obj->ncont);
+		     (MLX5_ST_SZ_BYTES(mtt) *
+		      ib_umem_num_dma_blocks(obj->umem, page_size));
 	cmd->in = uverbs_zalloc(attrs, cmd->inlen);
-	return PTR_ERR_OR_ZERO(cmd->in);
-}
-
-static void devx_umem_reg_cmd_build(struct mlx5_ib_dev *dev,
-				    struct devx_umem *obj,
-				    struct devx_umem_reg_cmd *cmd)
-{
-	void *umem;
-	__be64 *mtt;
+	if (IS_ERR(cmd->in))
+		return PTR_ERR(cmd->in);
 
 	umem = MLX5_ADDR_OF(create_umem_in, cmd->in, umem);
 	mtt = (__be64 *)MLX5_ADDR_OF(umem, umem, mtt);
 
 	MLX5_SET(create_umem_in, cmd->in, opcode, MLX5_CMD_OP_CREATE_UMEM);
-	MLX5_SET64(umem, umem, num_of_mtt, obj->ncont);
-	MLX5_SET(umem, umem, log_page_size, obj->page_shift -
-					    MLX5_ADAPTER_PAGE_SHIFT);
-	MLX5_SET(umem, umem, page_offset, obj->page_offset);
-	mlx5_ib_populate_pas(dev, obj->umem, obj->page_shift, mtt,
+	MLX5_SET64(umem, umem, num_of_mtt,
+		   ib_umem_num_dma_blocks(obj->umem, page_size));
+	MLX5_SET(umem, umem, log_page_size,
+		 order_base_2(page_size) - MLX5_ADAPTER_PAGE_SHIFT);
+	MLX5_SET(umem, umem, page_offset,
+		 ib_umem_dma_offset(obj->umem, page_size));
+
+	mlx5_ib_populate_pas(obj->umem, page_size, mtt,
 			     (obj->umem->writable ? MLX5_IB_MTT_WRITE : 0) |
-			     MLX5_IB_MTT_READ);
+				     MLX5_IB_MTT_READ);
+	return 0;
 }
 
 static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_UMEM_REG)(
@@ -2150,12 +2150,10 @@ static int UVERBS_HANDLER(MLX5_IB_METHOD_DEVX_UMEM_REG)(
 	if (err)
 		goto err_obj_free;
 
-	err = devx_umem_reg_cmd_alloc(attrs, obj, &cmd);
+	err = devx_umem_reg_cmd_alloc(dev, attrs, obj, &cmd);
 	if (err)
 		goto err_umem_release;
 
-	devx_umem_reg_cmd_build(dev, obj, &cmd);
-
 	MLX5_SET(create_umem_in, cmd.in, uid, c->devx_uid);
 	err = mlx5_cmd_exec(dev->mdev, cmd.in, cmd.inlen, cmd.out,
 			    sizeof(cmd.out));
@@ -2187,7 +2185,7 @@ static int devx_umem_cleanup(struct ib_uobject *uobject,
 	int err;
 
 	err = mlx5_cmd_exec(obj->mdev, obj->dinbox, obj->dinlen, out, sizeof(out));
-	if (ib_is_destroy_retryable(err, why, uobject))
+	if (err)
 		return err;
 
 	ib_umem_release(obj->umem);
@@ -2600,8 +2598,8 @@ static const struct file_operations devx_async_event_fops = {
 	.llseek	 = no_llseek,
 };
 
-static int devx_async_cmd_event_destroy_uobj(struct ib_uobject *uobj,
-					     enum rdma_remove_reason why)
+static void devx_async_cmd_event_destroy_uobj(struct ib_uobject *uobj,
+					      enum rdma_remove_reason why)
 {
 	struct devx_async_cmd_event_file *comp_ev_file =
 		container_of(uobj, struct devx_async_cmd_event_file,
@@ -2623,11 +2621,10 @@ static int devx_async_cmd_event_destroy_uobj(struct ib_uobject *uobj,
 		kvfree(entry);
 	}
 	spin_unlock_irq(&comp_ev_file->ev_queue.lock);
-	return 0;
 };
 
-static int devx_async_event_destroy_uobj(struct ib_uobject *uobj,
-					 enum rdma_remove_reason why)
+static void devx_async_event_destroy_uobj(struct ib_uobject *uobj,
+					  enum rdma_remove_reason why)
 {
 	struct devx_async_event_file *ev_file =
 		container_of(uobj, struct devx_async_event_file,
@@ -2671,7 +2668,6 @@ static int devx_async_event_destroy_uobj(struct ib_uobject *uobj,
 	mutex_unlock(&dev->devx_event_table.event_xa_lock);
 
 	put_device(&dev->ib_dev.dev);
-	return 0;
 };
 
 DECLARE_UVERBS_NAMED_METHOD(