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

Pull rdma updates from Jason Gunthorpe:

 - Various minor code cleanups and fixes for hns, iser, cxgb4, hfi1,
   rxe, erdma, mana_ib

 - Prefetch supprot for rxe ODP

 - Remove memory window support from hns as new device FW is no longer
   support it

 - Remove qib, it is very old and obsolete now, Cornelis wishes to
   restructure the hfi1/qib shared layer

 - Fix a race in destroying CQs where we can still end up with work
   running because the work is cancled before the driver stops
   triggering it

 - Improve interaction with namespaces:
     * Follow the devlink namespace for newly spawned RDMA devices
     * Create iopoib net devces in the parent IB device's namespace
     * Allow CAP_NET_RAW checks to pass in user namespaces

 - A new flow control scheme for IB MADs to try and avoid queue
   overflows in the network

 - Fix 2G message sizes in bnxt_re

 - Optimize mkey layout for mlx5 DMABUF

 - New "DMA Handle" concept to allow controlling PCI TPH and steering
   tags

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (71 commits)
  RDMA/siw: Change maintainer email address
  RDMA/mana_ib: add support of multiple ports
  RDMA/mlx5: Refactor optional counters steering code
  RDMA/mlx5: Add DMAH support for reg_user_mr/reg_user_dmabuf_mr
  IB: Extend UVERBS_METHOD_REG_MR to get DMAH
  RDMA/mlx5: Add DMAH object support
  RDMA/core: Introduce a DMAH object and its alloc/free APIs
  IB/core: Add UVERBS_METHOD_REG_MR on the MR object
  net/mlx5: Add support for device steering tag
  net/mlx5: Expose IFC bits for TPH
  PCI/TPH: Expose pcie_tph_get_st_table_size()
  RDMA/mlx5: Fix incorrect MKEY masking
  RDMA/mlx5: Fix returned type from _mlx5r_umr_zap_mkey()
  RDMA/mlx5: remove redundant check on err on return expression
  RDMA/mana_ib: add additional port counters
  RDMA/mana_ib: Fix DSCP value in modify QP
  RDMA/efa: Add CQ with external memory support
  RDMA/core: Add umem "is_contiguous" and "start_dma_addr" helpers
  RDMA/uverbs: Add a common way to create CQ with umem
  RDMA/mlx5: Optimize DMABUF mkey page size
  ...

3 files changed, 24 insertions, 8 deletions

diff --git a/drivers/infiniband/sw/siw/siw_qp_tx.c b/drivers/infiniband/sw/siw/siw_qp_tx.c
index 6432bce7d083..3a08f57d2211 100644
--- a/drivers/infiniband/sw/siw/siw_qp_tx.c
+++ b/drivers/infiniband/sw/siw/siw_qp_tx.c
@@ -277,6 +277,15 @@ static int siw_qp_prepare_tx(struct siw_iwarp_tx *c_tx)
 	return PKT_FRAGMENTED;
 }
 
+static noinline_for_stack int
+siw_sendmsg(struct socket *sock, unsigned int msg_flags,
+	    struct kvec *vec, size_t num, size_t len)
+{
+	struct msghdr msg = { .msg_flags = msg_flags };
+
+	return kernel_sendmsg(sock, &msg, vec, num, len);
+}
+
 /*
  * Send out one complete control type FPDU, or header of FPDU carrying
  * data. Used for fixed sized packets like Read.Requests or zero length
@@ -285,12 +294,11 @@ static int siw_qp_prepare_tx(struct siw_iwarp_tx *c_tx)
 static int siw_tx_ctrl(struct siw_iwarp_tx *c_tx, struct socket *s,
 			      int flags)
 {
-	struct msghdr msg = { .msg_flags = flags };
 	struct kvec iov = { .iov_base =
 				    (char *)&c_tx->pkt.ctrl + c_tx->ctrl_sent,
 			    .iov_len = c_tx->ctrl_len - c_tx->ctrl_sent };
 
-	int rv = kernel_sendmsg(s, &msg, &iov, 1, iov.iov_len);
+	int rv = siw_sendmsg(s, flags, &iov, 1, iov.iov_len);
 
 	if (rv >= 0) {
 		c_tx->ctrl_sent += rv;
@@ -427,13 +435,13 @@ static void siw_unmap_pages(struct kvec *iov, unsigned long kmap_mask, int len)
  * Write out iov referencing hdr, data and trailer of current FPDU.
  * Update transmit state dependent on write return status
  */
-static int siw_tx_hdt(struct siw_iwarp_tx *c_tx, struct socket *s)
+static noinline_for_stack int siw_tx_hdt(struct siw_iwarp_tx *c_tx,
+					 struct socket *s)
 {
 	struct siw_wqe *wqe = &c_tx->wqe_active;
 	struct siw_sge *sge = &wqe->sqe.sge[c_tx->sge_idx];
 	struct kvec iov[MAX_ARRAY];
 	struct page *page_array[MAX_ARRAY];
-	struct msghdr msg = { .msg_flags = MSG_DONTWAIT | MSG_EOR };
 
 	int seg = 0, do_crc = c_tx->do_crc, is_kva = 0, rv;
 	unsigned int data_len = c_tx->bytes_unsent, hdr_len = 0, trl_len = 0,
@@ -586,14 +594,16 @@ sge_done:
 		rv = siw_0copy_tx(s, page_array, &wqe->sqe.sge[c_tx->sge_idx],
 				  c_tx->sge_off, data_len);
 		if (rv == data_len) {
-			rv = kernel_sendmsg(s, &msg, &iov[seg], 1, trl_len);
+
+			rv = siw_sendmsg(s, MSG_DONTWAIT | MSG_EOR, &iov[seg],
+					 1, trl_len);
 			if (rv > 0)
 				rv += data_len;
 			else
 				rv = data_len;
 		}
 	} else {
-		rv = kernel_sendmsg(s, &msg, iov, seg + 1,
+		rv = siw_sendmsg(s, MSG_DONTWAIT | MSG_EOR, iov, seg + 1,
 				    hdr_len + data_len + trl_len);
 		siw_unmap_pages(iov, kmap_mask, seg);
 	}
diff --git a/drivers/infiniband/sw/siw/siw_verbs.c b/drivers/infiniband/sw/siw/siw_verbs.c
index 2b2a7b8e93b0..35c3bde0d00a 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.c
+++ b/drivers/infiniband/sw/siw/siw_verbs.c
@@ -1321,10 +1321,12 @@ int siw_dereg_mr(struct ib_mr *base_mr, struct ib_udata *udata)
  * @len:	len of MR
  * @rnic_va:	not used by siw
  * @rights:	MR access rights
+ * @dmah:	dma handle
  * @udata:	user buffer to communicate STag and Key.
  */
 struct ib_mr *siw_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
-			      u64 rnic_va, int rights, struct ib_udata *udata)
+			      u64 rnic_va, int rights,  struct ib_dmah *dmah,
+			      struct ib_udata *udata)
 {
 	struct siw_mr *mr = NULL;
 	struct siw_umem *umem = NULL;
@@ -1336,6 +1338,9 @@ struct ib_mr *siw_reg_user_mr(struct ib_pd *pd, u64 start, u64 len,
 		   (void *)(uintptr_t)start, (void *)(uintptr_t)rnic_va,
 		   (unsigned long long)len);
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (atomic_inc_return(&sdev->num_mr) > SIW_MAX_MR) {
 		siw_dbg_pd(pd, "too many mr's\n");
 		rv = -ENOMEM;
diff --git a/drivers/infiniband/sw/siw/siw_verbs.h b/drivers/infiniband/sw/siw/siw_verbs.h
index 1f1a305540af..e9f4463aecdc 100644
--- a/drivers/infiniband/sw/siw/siw_verbs.h
+++ b/drivers/infiniband/sw/siw/siw_verbs.h
@@ -65,7 +65,8 @@ int siw_destroy_cq(struct ib_cq *base_cq, struct ib_udata *udata);
 int siw_poll_cq(struct ib_cq *base_cq, int num_entries, struct ib_wc *wc);
 int siw_req_notify_cq(struct ib_cq *base_cq, enum ib_cq_notify_flags flags);
 struct ib_mr *siw_reg_user_mr(struct ib_pd *base_pd, u64 start, u64 len,
-			      u64 rnic_va, int rights, struct ib_udata *udata);
+			      u64 rnic_va, int rights, struct ib_dmah *dmah,
+			      struct ib_udata *udata);
 struct ib_mr *siw_alloc_mr(struct ib_pd *base_pd, enum ib_mr_type mr_type,
 			   u32 max_sge);
 struct ib_mr *siw_get_dma_mr(struct ib_pd *base_pd, int rights);