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
  ...

drivers/infiniband/sw/rdmavt/mr.c

@@ -329,12 +329,14 @@ bail:
  * @length: length of region to register
  * @virt_addr: associated virtual address
  * @mr_access_flags: access flags for this memory region
+ * @dmah: dma handle
  * @udata: unused by the driver
  *
  * Return: the memory region on success, otherwise returns an errno.
  */
 struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			      u64 virt_addr, int mr_access_flags,
+			      struct ib_dmah *dmah,
 			      struct ib_udata *udata)
 {
 	struct rvt_mr *mr;
@@ -343,6 +345,9 @@ struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 	int n, m;
 	struct ib_mr *ret;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (length == 0)
 		return ERR_PTR(-EINVAL);
 

drivers/infiniband/sw/rdmavt/mr.h

@@ -26,6 +26,7 @@ void rvt_mr_exit(struct rvt_dev_info *rdi);
 struct ib_mr *rvt_get_dma_mr(struct ib_pd *pd, int acc);
 struct ib_mr *rvt_reg_user_mr(struct ib_pd *pd, u64 start, u64 length,
 			      u64 virt_addr, int mr_access_flags,
+			      struct ib_dmah *dmah,
 			      struct ib_udata *udata);
 int rvt_dereg_mr(struct ib_mr *ibmr, struct ib_udata *udata);
 struct ib_mr *rvt_alloc_mr(struct ib_pd *pd, enum ib_mr_type mr_type,

drivers/infiniband/sw/rdmavt/vt.c

@@ -49,7 +49,7 @@ struct rvt_dev_info *rvt_alloc_device(size_t size, int nports)
 {
 	struct rvt_dev_info *rdi;
 
-	rdi = container_of(_ib_alloc_device(size), struct rvt_dev_info, ibdev);
+	rdi = container_of(_ib_alloc_device(size, &init_net), struct rvt_dev_info, ibdev);
 	if (!rdi)
 		return rdi;
 

drivers/infiniband/sw/rxe/rxe.c

@@ -34,6 +34,10 @@ void rxe_dealloc(struct ib_device *ib_dev)
 	mutex_destroy(&rxe->usdev_lock);
 }
 
+static const struct ib_device_ops rxe_ib_dev_odp_ops = {
+	.advise_mr = rxe_ib_advise_mr,
+};
+
 /* initialize rxe device parameters */
 static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
 {
@@ -103,6 +107,9 @@ static void rxe_init_device_param(struct rxe_dev *rxe, struct net_device *ndev)
 		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_SRQ_RECV;
 		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_FLUSH;
 		rxe->attr.odp_caps.per_transport_caps.rc_odp_caps |= IB_ODP_SUPPORT_ATOMIC_WRITE;
+
+		/* set handler for ODP prefetching API - ibv_advise_mr(3) */
+		ib_set_device_ops(&rxe->ib_dev, &rxe_ib_dev_odp_ops);
 	}
 }
 

drivers/infiniband/sw/rxe/rxe_loc.h

@@ -203,6 +203,9 @@ enum resp_states rxe_odp_atomic_op(struct rxe_mr *mr, u64 iova, int opcode,
 int rxe_odp_flush_pmem_iova(struct rxe_mr *mr, u64 iova,
 			    unsigned int length);
 enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value);
+int rxe_ib_advise_mr(struct ib_pd *pd, enum ib_uverbs_advise_mr_advice advice,
+		     u32 flags, struct ib_sge *sg_list, u32 num_sge,
+		     struct uverbs_attr_bundle *attrs);
 #else /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 static inline int
 rxe_odp_mr_init_user(struct rxe_dev *rxe, u64 start, u64 length, u64 iova,
@@ -231,6 +234,15 @@ static inline enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr,
 {
 	return RESPST_ERR_UNSUPPORTED_OPCODE;
 }
+static inline int rxe_ib_advise_mr(struct ib_pd *pd,
+				   enum ib_uverbs_advise_mr_advice advice,
+				   u32 flags, struct ib_sge *sg_list,
+				   u32 num_sge,
+				   struct uverbs_attr_bundle *attrs)
+{
+	return -EOPNOTSUPP;
+}
+
 #endif /* CONFIG_INFINIBAND_ON_DEMAND_PAGING */
 
 #endif /* RXE_LOC_H */

drivers/infiniband/sw/rxe/rxe_odp.c

@@ -203,8 +203,6 @@ static int __rxe_odp_mr_copy(struct rxe_mr *mr, u64 iova, void *addr,
 
 		page = hmm_pfn_to_page(umem_odp->map.pfn_list[idx]);
 		user_va = kmap_local_page(page);
-		if (!user_va)
-			return -EFAULT;
 
 		src = (dir == RXE_TO_MR_OBJ) ? addr : user_va;
 		dest = (dir == RXE_TO_MR_OBJ) ? user_va : addr;
@@ -283,17 +281,15 @@ static enum resp_states rxe_odp_do_atomic_op(struct rxe_mr *mr, u64 iova,
 		return RESPST_ERR_RKEY_VIOLATION;
 	}
 
-	idx = rxe_odp_iova_to_index(umem_odp, iova);
 	page_offset = rxe_odp_iova_to_page_offset(umem_odp, iova);
-	page = hmm_pfn_to_page(umem_odp->map.pfn_list[idx]);
-	if (!page)
-		return RESPST_ERR_RKEY_VIOLATION;
-
 	if (unlikely(page_offset & 0x7)) {
 		rxe_dbg_mr(mr, "iova not aligned\n");
 		return RESPST_ERR_MISALIGNED_ATOMIC;
 	}
 
+	idx = rxe_odp_iova_to_index(umem_odp, iova);
+	page = hmm_pfn_to_page(umem_odp->map.pfn_list[idx]);
+
 	va = kmap_local_page(page);
 
 	spin_lock_bh(&atomic_ops_lock);
@@ -352,10 +348,6 @@ int rxe_odp_flush_pmem_iova(struct rxe_mr *mr, u64 iova,
 		page_offset = rxe_odp_iova_to_page_offset(umem_odp, iova);
 
 		page = hmm_pfn_to_page(umem_odp->map.pfn_list[index]);
-		if (!page) {
-			mutex_unlock(&umem_odp->umem_mutex);
-			return -EFAULT;
-		}
 
 		bytes = min_t(unsigned int, length,
 			      mr_page_size(mr) - page_offset);
@@ -396,12 +388,6 @@ enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 		return RESPST_ERR_RKEY_VIOLATION;
 
 	page_offset = rxe_odp_iova_to_page_offset(umem_odp, iova);
-	index = rxe_odp_iova_to_index(umem_odp, iova);
-	page = hmm_pfn_to_page(umem_odp->map.pfn_list[index]);
-	if (!page) {
-		mutex_unlock(&umem_odp->umem_mutex);
-		return RESPST_ERR_RKEY_VIOLATION;
-	}
 	/* See IBA A19.4.2 */
 	if (unlikely(page_offset & 0x7)) {
 		mutex_unlock(&umem_odp->umem_mutex);
@@ -409,6 +395,9 @@ enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 		return RESPST_ERR_MISALIGNED_ATOMIC;
 	}
 
+	index = rxe_odp_iova_to_index(umem_odp, iova);
+	page = hmm_pfn_to_page(umem_odp->map.pfn_list[index]);
+
 	va = kmap_local_page(page);
 	/* Do atomic write after all prior operations have completed */
 	smp_store_release(&va[page_offset >> 3], value);
@@ -418,3 +407,172 @@ enum resp_states rxe_odp_do_atomic_write(struct rxe_mr *mr, u64 iova, u64 value)
 
 	return RESPST_NONE;
 }
+
+struct prefetch_mr_work {
+	struct work_struct work;
+	u32 pf_flags;
+	u32 num_sge;
+	struct {
+		u64 io_virt;
+		struct rxe_mr *mr;
+		size_t length;
+	} frags[];
+};
+
+static void rxe_ib_prefetch_mr_work(struct work_struct *w)
+{
+	struct prefetch_mr_work *work =
+		container_of(w, struct prefetch_mr_work, work);
+	int ret;
+	u32 i;
+
+	/*
+	 * We rely on IB/core that work is executed
+	 * if we have num_sge != 0 only.
+	 */
+	WARN_ON(!work->num_sge);
+	for (i = 0; i < work->num_sge; ++i) {
+		struct ib_umem_odp *umem_odp;
+
+		ret = rxe_odp_do_pagefault_and_lock(work->frags[i].mr,
+						    work->frags[i].io_virt,
+						    work->frags[i].length,
+						    work->pf_flags);
+		if (ret < 0) {
+			rxe_dbg_mr(work->frags[i].mr,
+				   "failed to prefetch the mr\n");
+			goto deref;
+		}
+
+		umem_odp = to_ib_umem_odp(work->frags[i].mr->umem);
+		mutex_unlock(&umem_odp->umem_mutex);
+
+deref:
+		rxe_put(work->frags[i].mr);
+	}
+
+	kvfree(work);
+}
+
+static int rxe_ib_prefetch_sg_list(struct ib_pd *ibpd,
+				   enum ib_uverbs_advise_mr_advice advice,
+				   u32 pf_flags, struct ib_sge *sg_list,
+				   u32 num_sge)
+{
+	struct rxe_pd *pd = container_of(ibpd, struct rxe_pd, ibpd);
+	int ret = 0;
+	u32 i;
+
+	for (i = 0; i < num_sge; ++i) {
+		struct rxe_mr *mr;
+		struct ib_umem_odp *umem_odp;
+
+		mr = lookup_mr(pd, IB_ACCESS_LOCAL_WRITE,
+			       sg_list[i].lkey, RXE_LOOKUP_LOCAL);
+
+		if (!mr) {
+			rxe_dbg_pd(pd, "mr with lkey %x not found\n",
+				   sg_list[i].lkey);
+			return -EINVAL;
+		}
+
+		if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE &&
+		    !mr->umem->writable) {
+			rxe_dbg_mr(mr, "missing write permission\n");
+			rxe_put(mr);
+			return -EPERM;
+		}
+
+		ret = rxe_odp_do_pagefault_and_lock(
+			mr, sg_list[i].addr, sg_list[i].length, pf_flags);
+		if (ret < 0) {
+			rxe_dbg_mr(mr, "failed to prefetch the mr\n");
+			rxe_put(mr);
+			return ret;
+		}
+
+		umem_odp = to_ib_umem_odp(mr->umem);
+		mutex_unlock(&umem_odp->umem_mutex);
+
+		rxe_put(mr);
+	}
+
+	return 0;
+}
+
+static int rxe_ib_advise_mr_prefetch(struct ib_pd *ibpd,
+				     enum ib_uverbs_advise_mr_advice advice,
+				     u32 flags, struct ib_sge *sg_list,
+				     u32 num_sge)
+{
+	struct rxe_pd *pd = container_of(ibpd, struct rxe_pd, ibpd);
+	u32 pf_flags = RXE_PAGEFAULT_DEFAULT;
+	struct prefetch_mr_work *work;
+	struct rxe_mr *mr;
+	u32 i;
+
+	if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH)
+		pf_flags |= RXE_PAGEFAULT_RDONLY;
+
+	if (advice == IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT)
+		pf_flags |= RXE_PAGEFAULT_SNAPSHOT;
+
+	/* Synchronous call */
+	if (flags & IB_UVERBS_ADVISE_MR_FLAG_FLUSH)
+		return rxe_ib_prefetch_sg_list(ibpd, advice, pf_flags, sg_list,
+					       num_sge);
+
+	/* Asynchronous call is "best-effort" and allowed to fail */
+	work = kvzalloc(struct_size(work, frags, num_sge), GFP_KERNEL);
+	if (!work)
+		return -ENOMEM;
+
+	INIT_WORK(&work->work, rxe_ib_prefetch_mr_work);
+	work->pf_flags = pf_flags;
+	work->num_sge = num_sge;
+
+	for (i = 0; i < num_sge; ++i) {
+		/* Takes a reference, which will be released in the queued work */
+		mr = lookup_mr(pd, IB_ACCESS_LOCAL_WRITE,
+			       sg_list[i].lkey, RXE_LOOKUP_LOCAL);
+		if (!mr) {
+			mr = ERR_PTR(-EINVAL);
+			goto err;
+		}
+
+		work->frags[i].io_virt = sg_list[i].addr;
+		work->frags[i].length = sg_list[i].length;
+		work->frags[i].mr = mr;
+	}
+
+	queue_work(system_unbound_wq, &work->work);
+
+	return 0;
+
+ err:
+	/* rollback reference counts for the invalid request */
+	while (i > 0) {
+		i--;
+		rxe_put(work->frags[i].mr);
+	}
+
+	kvfree(work);
+
+	return PTR_ERR(mr);
+}
+
+int rxe_ib_advise_mr(struct ib_pd *ibpd,
+		     enum ib_uverbs_advise_mr_advice advice,
+		     u32 flags,
+		     struct ib_sge *sg_list,
+		     u32 num_sge,
+		     struct uverbs_attr_bundle *attrs)
+{
+	if (advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH &&
+	    advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_WRITE &&
+	    advice != IB_UVERBS_ADVISE_MR_ADVICE_PREFETCH_NO_FAULT)
+		return -EOPNOTSUPP;
+
+	return rxe_ib_advise_mr_prefetch(ibpd, advice, flags,
+					 sg_list, num_sge);
+}

drivers/infiniband/sw/rxe/rxe_verbs.c

@@ -1271,6 +1271,7 @@ err_free:
 
 static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start,
 				     u64 length, u64 iova, int access,
+				     struct ib_dmah *dmah,
 				     struct ib_udata *udata)
 {
 	struct rxe_dev *rxe = to_rdev(ibpd->device);
@@ -1278,6 +1279,9 @@ static struct ib_mr *rxe_reg_user_mr(struct ib_pd *ibpd, u64 start,
 	struct rxe_mr *mr;
 	int err, cleanup_err;
 
+	if (dmah)
+		return ERR_PTR(-EOPNOTSUPP);
+
 	if (access & ~RXE_ACCESS_SUPPORTED_MR) {
 		rxe_err_pd(pd, "access = %#x not supported (%#x)\n", access,
 				RXE_ACCESS_SUPPORTED_MR);

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);
 	}

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;

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);