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, 49 insertions, 28 deletions

diff --git a/drivers/infiniband/hw/mlx5/cq.c b/drivers/infiniband/hw/mlx5/cq.c
index fb62f1d04afa..eb92cefffd77 100644
--- a/drivers/infiniband/hw/mlx5/cq.c
+++ b/drivers/infiniband/hw/mlx5/cq.c
@@ -707,10 +707,10 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 			  int *cqe_size, int *index, int *inlen)
 {
 	struct mlx5_ib_create_cq ucmd = {};
+	unsigned long page_size;
+	unsigned int page_offset_quantized;
 	size_t ucmdlen;
-	int page_shift;
 	__be64 *pas;
-	int npages;
 	int ncont;
 	void *cqc;
 	int err;
@@ -742,14 +742,24 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 		return err;
 	}
 
+	page_size = mlx5_umem_find_best_cq_quantized_pgoff(
+		cq->buf.umem, cqc, log_page_size, MLX5_ADAPTER_PAGE_SHIFT,
+		page_offset, 64, &page_offset_quantized);
+	if (!page_size) {
+		err = -EINVAL;
+		goto err_umem;
+	}
+
 	err = mlx5_ib_db_map_user(context, udata, ucmd.db_addr, &cq->db);
 	if (err)
 		goto err_umem;
 
-	mlx5_ib_cont_pages(cq->buf.umem, ucmd.buf_addr, 0, &npages, &page_shift,
-			   &ncont, NULL);
-	mlx5_ib_dbg(dev, "addr 0x%llx, size %u, npages %d, page_shift %d, ncont %d\n",
-		    ucmd.buf_addr, entries * ucmd.cqe_size, npages, page_shift, ncont);
+	ncont = ib_umem_num_dma_blocks(cq->buf.umem, page_size);
+	mlx5_ib_dbg(
+		dev,
+		"addr 0x%llx, size %u, npages %zu, page_size %lu, ncont %d\n",
+		ucmd.buf_addr, entries * ucmd.cqe_size,
+		ib_umem_num_pages(cq->buf.umem), page_size, ncont);
 
 	*inlen = MLX5_ST_SZ_BYTES(create_cq_in) +
 		 MLX5_FLD_SZ_BYTES(create_cq_in, pas[0]) * ncont;
@@ -760,11 +770,12 @@ static int create_cq_user(struct mlx5_ib_dev *dev, struct ib_udata *udata,
 	}
 
 	pas = (__be64 *)MLX5_ADDR_OF(create_cq_in, *cqb, pas);
-	mlx5_ib_populate_pas(dev, cq->buf.umem, page_shift, pas, 0);
+	mlx5_ib_populate_pas(cq->buf.umem, page_size, pas, 0);
 
 	cqc = MLX5_ADDR_OF(create_cq_in, *cqb, cq_context);
 	MLX5_SET(cqc, cqc, log_page_size,
-		 page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+		 order_base_2(page_size) - MLX5_ADAPTER_PAGE_SHIFT);
+	MLX5_SET(cqc, cqc, page_offset, page_offset_quantized);
 
 	if (ucmd.flags & MLX5_IB_CREATE_CQ_FLAGS_UAR_PAGE_INDEX) {
 		*index = ucmd.uar_page_index;
@@ -1128,13 +1139,12 @@ int mlx5_ib_modify_cq(struct ib_cq *cq, u16 cq_count, u16 cq_period)
 }
 
 static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
-		       int entries, struct ib_udata *udata, int *npas,
-		       int *page_shift, int *cqe_size)
+		       int entries, struct ib_udata *udata,
+		       int *cqe_size)
 {
 	struct mlx5_ib_resize_cq ucmd;
 	struct ib_umem *umem;
 	int err;
-	int npages;
 
 	err = ib_copy_from_udata(&ucmd, udata, sizeof(ucmd));
 	if (err)
@@ -1155,9 +1165,6 @@ static int resize_user(struct mlx5_ib_dev *dev, struct mlx5_ib_cq *cq,
 		return err;
 	}
 
-	mlx5_ib_cont_pages(umem, ucmd.buf_addr, 0, &npages, page_shift,
-			   npas, NULL);
-
 	cq->resize_umem = umem;
 	*cqe_size = ucmd.cqe_size;
 
@@ -1250,7 +1257,8 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 	int err;
 	int npas;
 	__be64 *pas;
-	int page_shift;
+	unsigned int page_offset_quantized = 0;
+	unsigned int page_shift;
 	int inlen;
 	int cqe_size;
 	unsigned long flags;
@@ -1277,22 +1285,34 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 
 	mutex_lock(&cq->resize_mutex);
 	if (udata) {
-		err = resize_user(dev, cq, entries, udata, &npas, &page_shift,
-				  &cqe_size);
+		unsigned long page_size;
+
+		err = resize_user(dev, cq, entries, udata, &cqe_size);
+		if (err)
+			goto ex;
+
+		page_size = mlx5_umem_find_best_cq_quantized_pgoff(
+			cq->resize_umem, cqc, log_page_size,
+			MLX5_ADAPTER_PAGE_SHIFT, page_offset, 64,
+			&page_offset_quantized);
+		if (!page_size) {
+			err = -EINVAL;
+			goto ex_resize;
+		}
+		npas = ib_umem_num_dma_blocks(cq->resize_umem, page_size);
+		page_shift = order_base_2(page_size);
 	} else {
+		struct mlx5_frag_buf *frag_buf;
+
 		cqe_size = 64;
 		err = resize_kernel(dev, cq, entries, cqe_size);
-		if (!err) {
-			struct mlx5_frag_buf *frag_buf = &cq->resize_buf->frag_buf;
-
-			npas = frag_buf->npages;
-			page_shift = frag_buf->page_shift;
-		}
+		if (err)
+			goto ex;
+		frag_buf = &cq->resize_buf->frag_buf;
+		npas = frag_buf->npages;
+		page_shift = frag_buf->page_shift;
 	}
 
-	if (err)
-		goto ex;
-
 	inlen = MLX5_ST_SZ_BYTES(modify_cq_in) +
 		MLX5_FLD_SZ_BYTES(modify_cq_in, pas[0]) * npas;
 
@@ -1304,8 +1324,8 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 
 	pas = (__be64 *)MLX5_ADDR_OF(modify_cq_in, in, pas);
 	if (udata)
-		mlx5_ib_populate_pas(dev, cq->resize_umem, page_shift,
-				     pas, 0);
+		mlx5_ib_populate_pas(cq->resize_umem, 1UL << page_shift, pas,
+				     0);
 	else
 		mlx5_fill_page_frag_array(&cq->resize_buf->frag_buf, pas);
 
@@ -1319,6 +1339,7 @@ int mlx5_ib_resize_cq(struct ib_cq *ibcq, int entries, struct ib_udata *udata)
 
 	MLX5_SET(cqc, cqc, log_page_size,
 		 page_shift - MLX5_ADAPTER_PAGE_SHIFT);
+	MLX5_SET(cqc, cqc, page_offset, page_offset_quantized);
 	MLX5_SET(cqc, cqc, cqe_sz,
 		 cqe_sz_to_mlx_sz(cqe_size,
 				  cq->private_flags &