Merge branch 'pci/msi-affinity' into next

Conflicts:
	drivers/nvme/host/pci.c

6 files changed, 46 insertions, 29 deletions

diff --git a/drivers/infiniband/hw/mlx4/ah.c b/drivers/infiniband/hw/mlx4/ah.c
index 105246fba2e7..5fc623362731 100644
--- a/drivers/infiniband/hw/mlx4/ah.c
+++ b/drivers/infiniband/hw/mlx4/ah.c
@@ -47,6 +47,7 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 
 	ah->av.ib.port_pd = cpu_to_be32(to_mpd(pd)->pdn | (ah_attr->port_num << 24));
 	ah->av.ib.g_slid  = ah_attr->src_path_bits;
+	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 	if (ah_attr->ah_flags & IB_AH_GRH) {
 		ah->av.ib.g_slid   |= 0x80;
 		ah->av.ib.gid_index = ah_attr->grh.sgid_index;
@@ -64,7 +65,6 @@ static struct ib_ah *create_ib_ah(struct ib_pd *pd, struct ib_ah_attr *ah_attr,
 		       !(1 << ah->av.ib.stat_rate & dev->caps.stat_rate_support))
 			--ah->av.ib.stat_rate;
 	}
-	ah->av.ib.sl_tclass_flowlabel = cpu_to_be32(ah_attr->sl << 28);
 
 	return &ah->ibah;
 }
diff --git a/drivers/infiniband/hw/mlx4/mad.c b/drivers/infiniband/hw/mlx4/mad.c
index d68f506c1922..9c2e53d28f98 100644
--- a/drivers/infiniband/hw/mlx4/mad.c
+++ b/drivers/infiniband/hw/mlx4/mad.c
@@ -527,7 +527,7 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 		tun_tx_ix = (++tun_qp->tx_ix_head) & (MLX4_NUM_TUNNEL_BUFS - 1);
 	spin_unlock(&tun_qp->tx_lock);
 	if (ret)
-		goto out;
+		goto end;
 
 	tun_mad = (struct mlx4_rcv_tunnel_mad *) (tun_qp->tx_ring[tun_tx_ix].buf.addr);
 	if (tun_qp->tx_ring[tun_tx_ix].ah)
@@ -596,9 +596,15 @@ int mlx4_ib_send_to_slave(struct mlx4_ib_dev *dev, int slave, u8 port,
 	wr.wr.send_flags = IB_SEND_SIGNALED;
 
 	ret = ib_post_send(src_qp, &wr.wr, &bad_wr);
-out:
-	if (ret)
-		ib_destroy_ah(ah);
+	if (!ret)
+		return 0;
+ out:
+	spin_lock(&tun_qp->tx_lock);
+	tun_qp->tx_ix_tail++;
+	spin_unlock(&tun_qp->tx_lock);
+	tun_qp->tx_ring[tun_tx_ix].ah = NULL;
+end:
+	ib_destroy_ah(ah);
 	return ret;
 }
 
@@ -1326,9 +1332,15 @@ int mlx4_ib_send_to_wire(struct mlx4_ib_dev *dev, int slave, u8 port,
 
 
 	ret = ib_post_send(send_qp, &wr.wr, &bad_wr);
+	if (!ret)
+		return 0;
+
+	spin_lock(&sqp->tx_lock);
+	sqp->tx_ix_tail++;
+	spin_unlock(&sqp->tx_lock);
+	sqp->tx_ring[wire_tx_ix].ah = NULL;
 out:
-	if (ret)
-		ib_destroy_ah(ah);
+	ib_destroy_ah(ah);
 	return ret;
 }
 
diff --git a/drivers/infiniband/hw/mlx4/main.c b/drivers/infiniband/hw/mlx4/main.c
index b01ef6eee6e8..42a46078d7d5 100644
--- a/drivers/infiniband/hw/mlx4/main.c
+++ b/drivers/infiniband/hw/mlx4/main.c
@@ -505,9 +505,9 @@ static int mlx4_ib_query_device(struct ib_device *ibdev,
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2B;
 		else
 			props->device_cap_flags |= IB_DEVICE_MEM_WINDOW_TYPE_2A;
-	if (dev->steering_support ==  MLX4_STEERING_MODE_DEVICE_MANAGED)
-		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 	}
+	if (dev->steering_support == MLX4_STEERING_MODE_DEVICE_MANAGED)
+		props->device_cap_flags |= IB_DEVICE_MANAGED_FLOW_STEERING;
 
 	props->device_cap_flags |= IB_DEVICE_RAW_IP_CSUM;
 
@@ -1704,6 +1704,9 @@ static struct ib_flow *mlx4_ib_create_flow(struct ib_qp *qp,
 	struct mlx4_dev *dev = (to_mdev(qp->device))->dev;
 	int is_bonded = mlx4_is_bonded(dev);
 
+	if (flow_attr->port < 1 || flow_attr->port > qp->device->phys_port_cnt)
+		return ERR_PTR(-EINVAL);
+
 	if ((flow_attr->flags & IB_FLOW_ATTR_FLAGS_DONT_TRAP) &&
 	    (flow_attr->type != IB_FLOW_ATTR_NORMAL))
 		return ERR_PTR(-EOPNOTSUPP);
diff --git a/drivers/infiniband/hw/mlx4/mlx4_ib.h b/drivers/infiniband/hw/mlx4/mlx4_ib.h
index 6c5ac5d8f32f..29acda249612 100644
--- a/drivers/infiniband/hw/mlx4/mlx4_ib.h
+++ b/drivers/infiniband/hw/mlx4/mlx4_ib.h
@@ -139,7 +139,7 @@ struct mlx4_ib_mr {
 	u32			max_pages;
 	struct mlx4_mr		mmr;
 	struct ib_umem	       *umem;
-	void			*pages_alloc;
+	size_t			page_map_size;
 };
 
 struct mlx4_ib_mw {
diff --git a/drivers/infiniband/hw/mlx4/mr.c b/drivers/infiniband/hw/mlx4/mr.c
index 631272172a0b..5d73989d9771 100644
--- a/drivers/infiniband/hw/mlx4/mr.c
+++ b/drivers/infiniband/hw/mlx4/mr.c
@@ -277,20 +277,23 @@ mlx4_alloc_priv_pages(struct ib_device *device,
 		      struct mlx4_ib_mr *mr,
 		      int max_pages)
 {
-	int size = max_pages * sizeof(u64);
-	int add_size;
 	int ret;
 
-	add_size = max_t(int, MLX4_MR_PAGES_ALIGN - ARCH_KMALLOC_MINALIGN, 0);
+	/* Ensure that size is aligned to DMA cacheline
+	 * requirements.
+	 * max_pages is limited to MLX4_MAX_FAST_REG_PAGES
+	 * so page_map_size will never cross PAGE_SIZE.
+	 */
+	mr->page_map_size = roundup(max_pages * sizeof(u64),
+				    MLX4_MR_PAGES_ALIGN);
 
-	mr->pages_alloc = kzalloc(size + add_size, GFP_KERNEL);
-	if (!mr->pages_alloc)
+	/* Prevent cross page boundary allocation. */
+	mr->pages = (__be64 *)get_zeroed_page(GFP_KERNEL);
+	if (!mr->pages)
 		return -ENOMEM;
 
-	mr->pages = PTR_ALIGN(mr->pages_alloc, MLX4_MR_PAGES_ALIGN);
-
 	mr->page_map = dma_map_single(device->dma_device, mr->pages,
-				      size, DMA_TO_DEVICE);
+				      mr->page_map_size, DMA_TO_DEVICE);
 
 	if (dma_mapping_error(device->dma_device, mr->page_map)) {
 		ret = -ENOMEM;
@@ -298,9 +301,9 @@ mlx4_alloc_priv_pages(struct ib_device *device,
 	}
 
 	return 0;
-err:
-	kfree(mr->pages_alloc);
 
+err:
+	free_page((unsigned long)mr->pages);
 	return ret;
 }
 
@@ -309,11 +312,10 @@ mlx4_free_priv_pages(struct mlx4_ib_mr *mr)
 {
 	if (mr->pages) {
 		struct ib_device *device = mr->ibmr.device;
-		int size = mr->max_pages * sizeof(u64);
 
 		dma_unmap_single(device->dma_device, mr->page_map,
-				 size, DMA_TO_DEVICE);
-		kfree(mr->pages_alloc);
+				 mr->page_map_size, DMA_TO_DEVICE);
+		free_page((unsigned long)mr->pages);
 		mr->pages = NULL;
 	}
 }
@@ -537,14 +539,12 @@ int mlx4_ib_map_mr_sg(struct ib_mr *ibmr, struct scatterlist *sg, int sg_nents,
 	mr->npages = 0;
 
 	ib_dma_sync_single_for_cpu(ibmr->device, mr->page_map,
-				   sizeof(u64) * mr->max_pages,
-				   DMA_TO_DEVICE);
+				   mr->page_map_size, DMA_TO_DEVICE);
 
 	rc = ib_sg_to_pages(ibmr, sg, sg_nents, sg_offset, mlx4_set_page);
 
 	ib_dma_sync_single_for_device(ibmr->device, mr->page_map,
-				      sizeof(u64) * mr->max_pages,
-				      DMA_TO_DEVICE);
+				      mr->page_map_size, DMA_TO_DEVICE);
 
 	return rc;
 }
diff --git a/drivers/infiniband/hw/mlx4/qp.c b/drivers/infiniband/hw/mlx4/qp.c
index 81b0e1fbec1d..8db8405c1e99 100644
--- a/drivers/infiniband/hw/mlx4/qp.c
+++ b/drivers/infiniband/hw/mlx4/qp.c
@@ -362,7 +362,7 @@ static int send_wqe_overhead(enum mlx4_ib_qp_type type, u32 flags)
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_RC:
 		return sizeof (struct mlx4_wqe_ctrl_seg) +
-			sizeof (struct mlx4_wqe_atomic_seg) +
+			sizeof (struct mlx4_wqe_masked_atomic_seg) +
 			sizeof (struct mlx4_wqe_raddr_seg);
 	case MLX4_IB_QPT_SMI:
 	case MLX4_IB_QPT_GSI:
@@ -1191,8 +1191,10 @@ static struct ib_qp *_mlx4_ib_create_qp(struct ib_pd *pd,
 	{
 		err = create_qp_common(to_mdev(pd->device), pd, init_attr,
 				       udata, 0, &qp, gfp);
-		if (err)
+		if (err) {
+			kfree(qp);
 			return ERR_PTR(err);
+		}
 
 		qp->ibqp.qp_num = qp->mqp.qpn;
 		qp->xrcdn = xrcdn;