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

Pull infiniband updates from Roland Dreier:
 "First batch of InfiniBand/RDMA changes for the 3.7 merge window:
   - mlx4 IB support for SR-IOV
   - A couple of SRP initiator fixes
   - Batch of nes hardware driver fixes
   - Fix for long-standing use-after-free crash in IPoIB
   - Other miscellaneous fixes"

This merge also removes a new use of __cancel_delayed_work(), and
replaces it with the regular cancel_delayed_work() that is now irq-safe
thanks to the workqueue updates.

That said, I suspect the sequence in question should probably use
"mod_delayed_work()".  I just did the minimal "don't use deprecated
functions" fixup, though.

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband: (45 commits)
  IB/qib: Fix local access validation for user MRs
  mlx4_core: Disable SENSE_PORT for multifunction devices
  mlx4_core: Clean up enabling of SENSE_PORT for older (ConnectX-1/-2) HCAs
  mlx4_core: Stash PCI ID driver_data in mlx4_priv structure
  IB/srp: Avoid having aborted requests hang
  IB/srp: Fix use-after-free in srp_reset_req()
  IB/qib: Add a qib driver version
  RDMA/nes: Fix compilation error when nes_debug is enabled
  RDMA/nes: Print hardware resource type
  RDMA/nes: Fix for crash when TX checksum offload is off
  RDMA/nes: Cosmetic changes
  RDMA/nes: Fix for incorrect MSS when TSO is on
  RDMA/nes: Fix incorrect resolving of the loopback MAC address
  mlx4_core: Fix crash on uninitialized priv->cmd.slave_sem
  mlx4_core: Trivial cleanups to driver log messages
  mlx4_core: Trivial readability fix: "0X30" -> "0x30"
  IB/mlx4: Create paravirt contexts for VFs when master IB driver initializes
  mlx4: Modify proxy/tunnel QP mechanism so that guests do no calculations
  mlx4: Paravirtualize Node Guids for slaves
  mlx4: Activate SR-IOV mode for IB
  ...

1 files changed, 30 insertions, 1 deletions

diff --git a/drivers/infiniband/hw/mlx4/cq.c b/drivers/infiniband/hw/mlx4/cq.c
index 6d4ef71cbcdf..c9eb6a6815ce 100644
--- a/drivers/infiniband/hw/mlx4/cq.c
+++ b/drivers/infiniband/hw/mlx4/cq.c
@@ -547,6 +547,26 @@ static int mlx4_ib_ipoib_csum_ok(__be16 status, __be16 checksum)
 		checksum == cpu_to_be16(0xffff);
 }
 
+static int use_tunnel_data(struct mlx4_ib_qp *qp, struct mlx4_ib_cq *cq, struct ib_wc *wc,
+			   unsigned tail, struct mlx4_cqe *cqe)
+{
+	struct mlx4_ib_proxy_sqp_hdr *hdr;
+
+	ib_dma_sync_single_for_cpu(qp->ibqp.device,
+				   qp->sqp_proxy_rcv[tail].map,
+				   sizeof (struct mlx4_ib_proxy_sqp_hdr),
+				   DMA_FROM_DEVICE);
+	hdr = (struct mlx4_ib_proxy_sqp_hdr *) (qp->sqp_proxy_rcv[tail].addr);
+	wc->pkey_index	= be16_to_cpu(hdr->tun.pkey_index);
+	wc->slid	= be16_to_cpu(hdr->tun.slid_mac_47_32);
+	wc->sl		= (u8) (be16_to_cpu(hdr->tun.sl_vid) >> 12);
+	wc->src_qp	= be32_to_cpu(hdr->tun.flags_src_qp) & 0xFFFFFF;
+	wc->wc_flags   |= (hdr->tun.g_ml_path & 0x80) ? (IB_WC_GRH) : 0;
+	wc->dlid_path_bits = 0;
+
+	return 0;
+}
+
 static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
 			    struct mlx4_ib_qp **cur_qp,
 			    struct ib_wc *wc)
@@ -559,6 +579,7 @@ static int mlx4_ib_poll_one(struct mlx4_ib_cq *cq,
 	int is_error;
 	u32 g_mlpath_rqpn;
 	u16 wqe_ctr;
+	unsigned tail = 0;
 
 repoll:
 	cqe = next_cqe_sw(cq);
@@ -634,7 +655,8 @@ repoll:
 		mlx4_ib_free_srq_wqe(srq, wqe_ctr);
 	} else {
 		wq	  = &(*cur_qp)->rq;
-		wc->wr_id = wq->wrid[wq->tail & (wq->wqe_cnt - 1)];
+		tail	  = wq->tail & (wq->wqe_cnt - 1);
+		wc->wr_id = wq->wrid[tail];
 		++wq->tail;
 	}
 
@@ -717,6 +739,13 @@ repoll:
 			break;
 		}
 
+		if (mlx4_is_mfunc(to_mdev(cq->ibcq.device)->dev)) {
+			if ((*cur_qp)->mlx4_ib_qp_type &
+			    (MLX4_IB_QPT_PROXY_SMI_OWNER |
+			     MLX4_IB_QPT_PROXY_SMI | MLX4_IB_QPT_PROXY_GSI))
+				return use_tunnel_data(*cur_qp, cq, wc, tail, cqe);
+		}
+
 		wc->slid	   = be16_to_cpu(cqe->rlid);
 		g_mlpath_rqpn	   = be32_to_cpu(cqe->g_mlpath_rqpn);
 		wc->src_qp	   = g_mlpath_rqpn & 0xffffff;