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

Pull rdma updates from Jason Gunthorpe:
 "This has been a smaller cycle than normal. One new driver was
  accepted, which is unusual, and at least one more driver remains in
  review on the list.

  Summary:

   - Driver fixes for hns, hfi1, nes, rxe, i40iw, mlx5, cxgb4,
     vmw_pvrdma

   - Many patches from MatthewW converting radix tree and IDR users to
     use xarray

   - Introduction of tracepoints to the MAD layer

   - Build large SGLs at the start for DMA mapping and get the driver to
     split them

   - Generally clean SGL handling code throughout the subsystem

   - Support for restricting RDMA devices to net namespaces for
     containers

   - Progress to remove object allocation boilerplate code from drivers

   - Change in how the mlx5 driver shows representor ports linked to VFs

   - mlx5 uapi feature to access the on chip SW ICM memory

   - Add a new driver for 'EFA'. This is HW that supports user space
     packet processing through QPs in Amazon's cloud"

* tag 'for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/rdma/rdma: (186 commits)
  RDMA/ipoib: Allow user space differentiate between valid dev_port
  IB/core, ipoib: Do not overreact to SM LID change event
  RDMA/device: Don't fire uevent before device is fully initialized
  lib/scatterlist: Remove leftover from sg_page_iter comment
  RDMA/efa: Add driver to Kconfig/Makefile
  RDMA/efa: Add the efa module
  RDMA/efa: Add EFA verbs implementation
  RDMA/efa: Add common command handlers
  RDMA/efa: Implement functions that submit and complete admin commands
  RDMA/efa: Add the ABI definitions
  RDMA/efa: Add the com service API definitions
  RDMA/efa: Add the efa_com.h file
  RDMA/efa: Add the efa.h header file
  RDMA/efa: Add EFA device definitions
  RDMA: Add EFA related definitions
  RDMA/umem: Remove hugetlb flag
  RDMA/bnxt_re: Use core helpers to get aligned DMA address
  RDMA/i40iw: Use core helpers to get aligned DMA address within a supported page size
  RDMA/verbs: Add a DMA iterator to return aligned contiguous memory blocks
  RDMA/umem: Add API to find best driver supported page size in an MR
  ...

1 files changed, 26 insertions, 20 deletions

diff --git a/drivers/infiniband/sw/rxe/rxe_net.c b/drivers/infiniband/sw/rxe/rxe_net.c
index 753cabcd441c..5a3474f9351b 100644
--- a/drivers/infiniband/sw/rxe/rxe_net.c
+++ b/drivers/infiniband/sw/rxe/rxe_net.c
@@ -338,13 +338,13 @@ static void prepare_ipv6_hdr(struct dst_entry *dst, struct sk_buff *skb,
 	ip6h->payload_len = htons(skb->len - sizeof(*ip6h));
 }
 
-static int prepare4(struct rxe_pkt_info *pkt, struct sk_buff *skb,
-		    struct rxe_av *av)
+static int prepare4(struct rxe_pkt_info *pkt, struct sk_buff *skb)
 {
 	struct rxe_qp *qp = pkt->qp;
 	struct dst_entry *dst;
 	bool xnet = false;
 	__be16 df = htons(IP_DF);
+	struct rxe_av *av = rxe_get_av(pkt);
 	struct in_addr *saddr = &av->sgid_addr._sockaddr_in.sin_addr;
 	struct in_addr *daddr = &av->dgid_addr._sockaddr_in.sin_addr;
 
@@ -364,11 +364,11 @@ static int prepare4(struct rxe_pkt_info *pkt, struct sk_buff *skb,
 	return 0;
 }
 
-static int prepare6(struct rxe_pkt_info *pkt, struct sk_buff *skb,
-		    struct rxe_av *av)
+static int prepare6(struct rxe_pkt_info *pkt, struct sk_buff *skb)
 {
 	struct rxe_qp *qp = pkt->qp;
 	struct dst_entry *dst;
+	struct rxe_av *av = rxe_get_av(pkt);
 	struct in6_addr *saddr = &av->sgid_addr._sockaddr_in6.sin6_addr;
 	struct in6_addr *daddr = &av->dgid_addr._sockaddr_in6.sin6_addr;
 
@@ -392,16 +392,15 @@ static int prepare6(struct rxe_pkt_info *pkt, struct sk_buff *skb,
 int rxe_prepare(struct rxe_pkt_info *pkt, struct sk_buff *skb, u32 *crc)
 {
 	int err = 0;
-	struct rxe_av *av = rxe_get_av(pkt);
 
-	if (av->network_type == RDMA_NETWORK_IPV4)
-		err = prepare4(pkt, skb, av);
-	else if (av->network_type == RDMA_NETWORK_IPV6)
-		err = prepare6(pkt, skb, av);
+	if (skb->protocol == htons(ETH_P_IP))
+		err = prepare4(pkt, skb);
+	else if (skb->protocol == htons(ETH_P_IPV6))
+		err = prepare6(pkt, skb);
 
 	*crc = rxe_icrc_hdr(pkt, skb);
 
-	if (ether_addr_equal(skb->dev->dev_addr, av->dmac))
+	if (ether_addr_equal(skb->dev->dev_addr, rxe_get_av(pkt)->dmac))
 		pkt->mask |= RXE_LOOPBACK_MASK;
 
 	return err;
@@ -422,23 +421,20 @@ static void rxe_skb_tx_dtor(struct sk_buff *skb)
 
 int rxe_send(struct rxe_pkt_info *pkt, struct sk_buff *skb)
 {
-	struct rxe_av *av;
 	int err;
 
-	av = rxe_get_av(pkt);
-
 	skb->destructor = rxe_skb_tx_dtor;
 	skb->sk = pkt->qp->sk->sk;
 
 	rxe_add_ref(pkt->qp);
 	atomic_inc(&pkt->qp->skb_out);
 
-	if (av->network_type == RDMA_NETWORK_IPV4) {
+	if (skb->protocol == htons(ETH_P_IP)) {
 		err = ip_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
-	} else if (av->network_type == RDMA_NETWORK_IPV6) {
+	} else if (skb->protocol == htons(ETH_P_IPV6)) {
 		err = ip6_local_out(dev_net(skb_dst(skb)->dev), skb->sk, skb);
 	} else {
-		pr_err("Unknown layer 3 protocol: %d\n", av->network_type);
+		pr_err("Unknown layer 3 protocol: %d\n", skb->protocol);
 		atomic_dec(&pkt->qp->skb_out);
 		rxe_drop_ref(pkt->qp);
 		kfree_skb(skb);
@@ -462,7 +458,7 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 				int paylen, struct rxe_pkt_info *pkt)
 {
 	unsigned int hdr_len;
-	struct sk_buff *skb;
+	struct sk_buff *skb = NULL;
 	struct net_device *ndev;
 	const struct ib_gid_attr *attr;
 	const int port_num = 1;
@@ -470,7 +466,6 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 	attr = rdma_get_gid_attr(&rxe->ib_dev, port_num, av->grh.sgid_index);
 	if (IS_ERR(attr))
 		return NULL;
-	ndev = attr->ndev;
 
 	if (av->network_type == RDMA_NETWORK_IPV4)
 		hdr_len = ETH_HLEN + sizeof(struct udphdr) +
@@ -479,15 +474,26 @@ struct sk_buff *rxe_init_packet(struct rxe_dev *rxe, struct rxe_av *av,
 		hdr_len = ETH_HLEN + sizeof(struct udphdr) +
 			sizeof(struct ipv6hdr);
 
+	rcu_read_lock();
+	ndev = rdma_read_gid_attr_ndev_rcu(attr);
+	if (IS_ERR(ndev)) {
+		rcu_read_unlock();
+		goto out;
+	}
 	skb = alloc_skb(paylen + hdr_len + LL_RESERVED_SPACE(ndev),
 			GFP_ATOMIC);
 
-	if (unlikely(!skb))
+	if (unlikely(!skb)) {
+		rcu_read_unlock();
 		goto out;
+	}
 
-	skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(rxe->ndev));
+	skb_reserve(skb, hdr_len + LL_RESERVED_SPACE(ndev));
 
+	/* FIXME: hold reference to this netdev until life of this skb. */
 	skb->dev	= ndev;
+	rcu_read_unlock();
+
 	if (av->network_type == RDMA_NETWORK_IPV4)
 		skb->protocol = htons(ETH_P_IP);
 	else