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

Pull infiniband/rdma fixes from Roland Dreier:
 - Fixes for the newly merged mlx5 hardware driver
 - Stack info leak fixes from Dan Carpenter
 - Fixes for pkey table handling with SR-IOV
 - A few other small things

* tag 'rdma-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/roland/infiniband:
  IPoIB: Fix pkey change flow for virtualization environments
  IPoIB: Make sure child devices use valid/proper pkeys
  IB/core: Create QP1 using the pkey index which contains the default pkey
  mlx5_core: Variable may be used uninitialized
  mlx5_core: Implement new initialization sequence
  mlx5_core: Fix use after free in mlx5_cmd_comp_handler()
  IB/mlx5: Fix stack info leak in mlx5_ib_alloc_ucontext()
  IB/mlx5: Fix error return code in init_one()
  IB/mlx4: Use default pkey when creating tunnel QPs
  RDMA/cma: Only call cma_save_ib_info() for CM REQs
  RDMA/cma: Fix accessing invalid private data for UD
  RDMA/cma: Fix gcc warning
  Revert "RDMA/nes: Fix compilation error when nes_debug is enabled"
  IB/qib: Add err_decode() call for ring dump
  RDMA/cxgb3: Fix stack info leak in iwch_create_cq()
  RDMA/nes: Fix info leaks in nes_create_qp() and nes_create_cq()
  RDMA/ocrdma: Fix several stack info leaks
  RDMA/cxgb4: Fix stack info leak in c4iw_create_qp()
  RDMA/ocrdma: Remove unused include

drivers/infiniband/core/cma.c

@@ -423,7 +423,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 	struct sockaddr_ib *addr;
 	union ib_gid gid, sgid, *dgid;
 	u16 pkey, index;
-	u8 port, p;
+	u8 p;
 	int i;
 
 	cma_dev = NULL;
@@ -443,7 +443,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 				if (!memcmp(&gid, dgid, sizeof(gid))) {
 					cma_dev = cur_dev;
 					sgid = gid;
-					port = p;
+					id_priv->id.port_num = p;
 					goto found;
 				}
 
@@ -451,7 +451,7 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 						 dgid->global.subnet_prefix)) {
 					cma_dev = cur_dev;
 					sgid = gid;
-					port = p;
+					id_priv->id.port_num = p;
 				}
 			}
 		}
@@ -462,7 +462,6 @@ static int cma_resolve_ib_dev(struct rdma_id_private *id_priv)
 
 found:
 	cma_attach_to_dev(id_priv, cma_dev);
-	id_priv->id.port_num = port;
 	addr = (struct sockaddr_ib *) cma_src_addr(id_priv);
 	memcpy(&addr->sib_addr, &sgid, sizeof sgid);
 	cma_translate_ib(addr, &id_priv->id.route.addr.dev_addr);
@@ -880,7 +879,8 @@ static int cma_save_net_info(struct rdma_cm_id *id, struct rdma_cm_id *listen_id
 {
 	struct cma_hdr *hdr;
 
-	if (listen_id->route.addr.src_addr.ss_family == AF_IB) {
+	if ((listen_id->route.addr.src_addr.ss_family == AF_IB) &&
+	    (ib_event->event == IB_CM_REQ_RECEIVED)) {
 		cma_save_ib_info(id, listen_id, ib_event->param.req_rcvd.primary_path);
 		return 0;
 	}
@@ -2677,29 +2677,32 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
 {
 	struct ib_cm_sidr_req_param req;
 	struct ib_cm_id	*id;
+	void *private_data;
 	int offset, ret;
 
+	memset(&req, 0, sizeof req);
 	offset = cma_user_data_offset(id_priv);
 	req.private_data_len = offset + conn_param->private_data_len;
 	if (req.private_data_len < conn_param->private_data_len)
 		return -EINVAL;
 
 	if (req.private_data_len) {
-		req.private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
-		if (!req.private_data)
+		private_data = kzalloc(req.private_data_len, GFP_ATOMIC);
+		if (!private_data)
 			return -ENOMEM;
 	} else {
-		req.private_data = NULL;
+		private_data = NULL;
 	}
 
 	if (conn_param->private_data && conn_param->private_data_len)
-		memcpy((void *) req.private_data + offset,
-		       conn_param->private_data, conn_param->private_data_len);
+		memcpy(private_data + offset, conn_param->private_data,
+		       conn_param->private_data_len);
 
-	if (req.private_data) {
-		ret = cma_format_hdr((void *) req.private_data, id_priv);
+	if (private_data) {
+		ret = cma_format_hdr(private_data, id_priv);
 		if (ret)
 			goto out;
+		req.private_data = private_data;
 	}
 
 	id = ib_create_cm_id(id_priv->id.device, cma_sidr_rep_handler,
@@ -2721,7 +2724,7 @@ static int cma_resolve_ib_udp(struct rdma_id_private *id_priv,
 		id_priv->cm_id.ib = NULL;
 	}
 out:
-	kfree(req.private_data);
+	kfree(private_data);
 	return ret;
 }
 

drivers/infiniband/core/mad.c

@@ -2663,6 +2663,7 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 	int ret, i;
 	struct ib_qp_attr *attr;
 	struct ib_qp *qp;
+	u16 pkey_index;
 
 	attr = kmalloc(sizeof *attr, GFP_KERNEL);
 	if (!attr) {
@@ -2670,6 +2671,11 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 		return -ENOMEM;
 	}
 
+	ret = ib_find_pkey(port_priv->device, port_priv->port_num,
+			   IB_DEFAULT_PKEY_FULL, &pkey_index);
+	if (ret)
+		pkey_index = 0;
+
 	for (i = 0; i < IB_MAD_QPS_CORE; i++) {
 		qp = port_priv->qp_info[i].qp;
 		if (!qp)
@@ -2680,7 +2686,7 @@ static int ib_mad_port_start(struct ib_mad_port_private *port_priv)
 		 * one is needed for the Reset to Init transition
 		 */
 		attr->qp_state = IB_QPS_INIT;
-		attr->pkey_index = 0;
+		attr->pkey_index = pkey_index;
 		attr->qkey = (qp->qp_num == 0) ? 0 : IB_QP1_QKEY;
 		ret = ib_modify_qp(qp, attr, IB_QP_STATE |
 					     IB_QP_PKEY_INDEX | IB_QP_QKEY);

drivers/infiniband/hw/cxgb3/iwch_provider.c

@@ -226,6 +226,7 @@ static struct ib_cq *iwch_create_cq(struct ib_device *ibdev, int entries, int ve
 			mm->len = PAGE_ALIGN(((1UL << uresp.size_log2) + 1) *
 					     sizeof(struct t3_cqe));
 			uresp.memsize = mm->len;
+			uresp.reserved = 0;
 			resplen = sizeof uresp;
 		}
 		if (ib_copy_to_udata(udata, &uresp, resplen)) {

drivers/infiniband/hw/cxgb4/qp.c

@@ -1657,6 +1657,8 @@ struct ib_qp *c4iw_create_qp(struct ib_pd *pd, struct ib_qp_init_attr *attrs,
 		if (mm5) {
 			uresp.ma_sync_key = ucontext->key;
 			ucontext->key += PAGE_SIZE;
+		} else {
+			uresp.ma_sync_key =  0;
 		}
 		uresp.sq_key = ucontext->key;
 		ucontext->key += PAGE_SIZE;

drivers/infiniband/hw/mlx4/mad.c

@@ -1511,8 +1511,14 @@ static int create_pv_sqp(struct mlx4_ib_demux_pv_ctx *ctx,
 
 	memset(&attr, 0, sizeof attr);
 	attr.qp_state = IB_QPS_INIT;
-	attr.pkey_index =
-		to_mdev(ctx->ib_dev)->pkeys.virt2phys_pkey[ctx->slave][ctx->port - 1][0];
+	ret = 0;
+	if (create_tun)
+		ret = find_slave_port_pkey_ix(to_mdev(ctx->ib_dev), ctx->slave,
+					      ctx->port, IB_DEFAULT_PKEY_FULL,
+					      &attr.pkey_index);
+	if (ret || !create_tun)
+		attr.pkey_index =
+			to_mdev(ctx->ib_dev)->pkeys.virt2phys_pkey[ctx->slave][ctx->port - 1][0];
 	attr.qkey = IB_QP1_QKEY;
 	attr.port_num = ctx->port;
 	ret = ib_modify_qp(tun_qp->qp, &attr, qp_attr_mask_INIT);

drivers/infiniband/hw/mlx5/main.c

@@ -619,7 +619,8 @@ static struct ib_ucontext *mlx5_ib_alloc_ucontext(struct ib_device *ibdev,
 
 	resp.tot_uuars = req.total_num_uuars;
 	resp.num_ports = dev->mdev.caps.num_ports;
-	err = ib_copy_to_udata(udata, &resp, sizeof(resp));
+	err = ib_copy_to_udata(udata, &resp,
+			       sizeof(resp) - sizeof(resp.reserved));
 	if (err)
 		goto out_uars;
 
@@ -1426,7 +1427,8 @@ static int init_one(struct pci_dev *pdev,
 	if (err)
 		goto err_eqs;
 
-	if (ib_register_device(&dev->ib_dev, NULL))
+	err = ib_register_device(&dev->ib_dev, NULL);
+	if (err)
 		goto err_rsrc;
 
 	err = create_umr_res(dev);
@@ -1434,8 +1436,9 @@ static int init_one(struct pci_dev *pdev,
 		goto err_dev;
 
 	for (i = 0; i < ARRAY_SIZE(mlx5_class_attributes); i++) {
-		if (device_create_file(&dev->ib_dev.dev,
-				       mlx5_class_attributes[i]))
+		err = device_create_file(&dev->ib_dev.dev,
+					 mlx5_class_attributes[i]);
+		if (err)
 			goto err_umrc;
 	}
 

drivers/infiniband/hw/mlx5/qp.c

@@ -199,7 +199,7 @@ static int set_rq_size(struct mlx5_ib_dev *dev, struct ib_qp_cap *cap,
 
 static int sq_overhead(enum ib_qp_type qp_type)
 {
-	int size;
+	int size = 0;
 
 	switch (qp_type) {
 	case IB_QPT_XRC_INI:

drivers/infiniband/hw/nes/nes_hw.c

@@ -3570,10 +3570,10 @@ static void nes_process_iwarp_aeqe(struct nes_device *nesdev,
 	tcp_state = (aeq_info & NES_AEQE_TCP_STATE_MASK) >> NES_AEQE_TCP_STATE_SHIFT;
 	iwarp_state = (aeq_info & NES_AEQE_IWARP_STATE_MASK) >> NES_AEQE_IWARP_STATE_SHIFT;
 	nes_debug(NES_DBG_AEQ, "aeid = 0x%04X, qp-cq id = %d, aeqe = %p,"
-			" Tcp state = %d, iWARP state = %d\n",
+			" Tcp state = %s, iWARP state = %s\n",
 			async_event_id,
 			le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX]), aeqe,
-			tcp_state, iwarp_state);
+			nes_tcp_state_str[tcp_state], nes_iwarp_state_str[iwarp_state]);
 
 	aeqe_cq_id = le32_to_cpu(aeqe->aeqe_words[NES_AEQE_COMP_QP_CQ_ID_IDX]);
 	if (aeq_info & NES_AEQE_QP) {

drivers/infiniband/hw/nes/nes_verbs.c

@@ -1384,6 +1384,7 @@ static struct ib_qp *nes_create_qp(struct ib_pd *ibpd,
 
 			if (ibpd->uobject) {
 				uresp.mmap_sq_db_index = nesqp->mmap_sq_db_index;
+				uresp.mmap_rq_db_index = 0;
 				uresp.actual_sq_size = sq_size;
 				uresp.actual_rq_size = rq_size;
 				uresp.qp_id = nesqp->hwqp.qp_id;
@@ -1767,7 +1768,7 @@ static struct ib_cq *nes_create_cq(struct ib_device *ibdev, int entries,
 		resp.cq_id = nescq->hw_cq.cq_number;
 		resp.cq_size = nescq->hw_cq.cq_size;
 		resp.mmap_db_index = 0;
-		if (ib_copy_to_udata(udata, &resp, sizeof resp)) {
+		if (ib_copy_to_udata(udata, &resp, sizeof resp - sizeof resp.reserved)) {
 			nes_free_resource(nesadapter, nesadapter->allocated_cqs, cq_num);
 			kfree(nescq);
 			return ERR_PTR(-EFAULT);

drivers/infiniband/hw/ocrdma/ocrdma_ah.c

@@ -29,7 +29,6 @@
 #include <net/netevent.h>
 
 #include <rdma/ib_addr.h>
-#include <rdma/ib_cache.h>
 
 #include "ocrdma.h"
 #include "ocrdma_verbs.h"

drivers/infiniband/hw/ocrdma/ocrdma_verbs.c

@@ -242,6 +242,7 @@ struct ib_ucontext *ocrdma_alloc_ucontext(struct ib_device *ibdev,
 	memset(ctx->ah_tbl.va, 0, map_len);
 	ctx->ah_tbl.len = map_len;
 
+	memset(&resp, 0, sizeof(resp));
 	resp.ah_tbl_len = ctx->ah_tbl.len;
 	resp.ah_tbl_page = ctx->ah_tbl.pa;
 
@@ -253,7 +254,6 @@ struct ib_ucontext *ocrdma_alloc_ucontext(struct ib_device *ibdev,
 	resp.wqe_size = dev->attr.wqe_size;
 	resp.rqe_size = dev->attr.rqe_size;
 	resp.dpp_wqe_size = dev->attr.wqe_size;
-	resp.rsvd = 0;
 
 	memcpy(resp.fw_ver, dev->attr.fw_ver, sizeof(resp.fw_ver));
 	status = ib_copy_to_udata(udata, &resp, sizeof(resp));
@@ -338,6 +338,7 @@ static int ocrdma_copy_pd_uresp(struct ocrdma_pd *pd,
 	struct ocrdma_alloc_pd_uresp rsp;
 	struct ocrdma_ucontext *uctx = get_ocrdma_ucontext(ib_ctx);
 
+	memset(&rsp, 0, sizeof(rsp));
 	rsp.id = pd->id;
 	rsp.dpp_enabled = pd->dpp_enabled;
 	db_page_addr = pd->dev->nic_info.unmapped_db +
@@ -692,6 +693,7 @@ static int ocrdma_copy_cq_uresp(struct ocrdma_cq *cq, struct ib_udata *udata,
 	struct ocrdma_ucontext *uctx;
 	struct ocrdma_create_cq_uresp uresp;
 
+	memset(&uresp, 0, sizeof(uresp));
 	uresp.cq_id = cq->id;
 	uresp.page_size = cq->len;
 	uresp.num_pages = 1;
@@ -1460,6 +1462,7 @@ static int ocrdma_copy_srq_uresp(struct ocrdma_srq *srq, struct ib_udata *udata)
 	int status;
 	struct ocrdma_create_srq_uresp uresp;
 
+	memset(&uresp, 0, sizeof(uresp));
 	uresp.rq_dbid = srq->rq.dbid;
 	uresp.num_rq_pages = 1;
 	uresp.rq_page_addr[0] = srq->rq.pa;

drivers/infiniband/hw/qib/qib_iba7322.c

@@ -1596,6 +1596,8 @@ static void sdma_7322_p_errors(struct qib_pportdata *ppd, u64 errs)
 	struct qib_devdata *dd = ppd->dd;
 
 	errs &= QIB_E_P_SDMAERRS;
+	err_decode(ppd->cpspec->sdmamsgbuf, sizeof(ppd->cpspec->sdmamsgbuf),
+		   errs, qib_7322p_error_msgs);
 
 	if (errs & QIB_E_P_SDMAUNEXPDATA)
 		qib_dev_err(dd, "IB%u:%u SDmaUnexpData\n", dd->unit,

drivers/infiniband/hw/qib/qib_sdma.c

@@ -717,7 +717,7 @@ void dump_sdma_state(struct qib_pportdata *ppd)
 	struct qib_sdma_txreq *txp, *txpnext;
 	__le64 *descqp;
 	u64 desc[2];
-	dma_addr_t addr;
+	u64 addr;
 	u16 gen, dwlen, dwoffset;
 	u16 head, tail, cnt;
 

drivers/infiniband/ulp/ipoib/ipoib_ib.c

@@ -932,12 +932,47 @@ int ipoib_ib_dev_init(struct net_device *dev, struct ib_device *ca, int port)
 	return 0;
 }
 
+/*
+ * Takes whatever value which is in pkey index 0 and updates priv->pkey
+ * returns 0 if the pkey value was changed.
+ */
+static inline int update_parent_pkey(struct ipoib_dev_priv *priv)
+{
+	int result;
+	u16 prev_pkey;
+
+	prev_pkey = priv->pkey;
+	result = ib_query_pkey(priv->ca, priv->port, 0, &priv->pkey);
+	if (result) {
+		ipoib_warn(priv, "ib_query_pkey port %d failed (ret = %d)\n",
+			   priv->port, result);
+		return result;
+	}
+
+	priv->pkey |= 0x8000;
+
+	if (prev_pkey != priv->pkey) {
+		ipoib_dbg(priv, "pkey changed from 0x%x to 0x%x\n",
+			  prev_pkey, priv->pkey);
+		/*
+		 * Update the pkey in the broadcast address, while making sure to set
+		 * the full membership bit, so that we join the right broadcast group.
+		 */
+		priv->dev->broadcast[8] = priv->pkey >> 8;
+		priv->dev->broadcast[9] = priv->pkey & 0xff;
+		return 0;
+	}
+
+	return 1;
+}
+
 static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 				enum ipoib_flush_level level)
 {
 	struct ipoib_dev_priv *cpriv;
 	struct net_device *dev = priv->dev;
 	u16 new_index;
+	int result;
 
 	mutex_lock(&priv->vlan_mutex);
 
@@ -951,6 +986,10 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 	mutex_unlock(&priv->vlan_mutex);
 
 	if (!test_bit(IPOIB_FLAG_INITIALIZED, &priv->flags)) {
+		/* for non-child devices must check/update the pkey value here */
+		if (level == IPOIB_FLUSH_HEAVY &&
+		    !test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags))
+			update_parent_pkey(priv);
 		ipoib_dbg(priv, "Not flushing - IPOIB_FLAG_INITIALIZED not set.\n");
 		return;
 	}
@@ -961,21 +1000,32 @@ static void __ipoib_ib_dev_flush(struct ipoib_dev_priv *priv,
 	}
 
 	if (level == IPOIB_FLUSH_HEAVY) {
-		if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
-			clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
-			ipoib_ib_dev_down(dev, 0);
-			ipoib_ib_dev_stop(dev, 0);
-			if (ipoib_pkey_dev_delay_open(dev))
+		/* child devices chase their origin pkey value, while non-child
+		 * (parent) devices should always takes what present in pkey index 0
+		 */
+		if (test_bit(IPOIB_FLAG_SUBINTERFACE, &priv->flags)) {
+			if (ib_find_pkey(priv->ca, priv->port, priv->pkey, &new_index)) {
+				clear_bit(IPOIB_PKEY_ASSIGNED, &priv->flags);
+				ipoib_ib_dev_down(dev, 0);
+				ipoib_ib_dev_stop(dev, 0);
+				if (ipoib_pkey_dev_delay_open(dev))
+					return;
+			}
+			/* restart QP only if P_Key index is changed */
+			if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
+			    new_index == priv->pkey_index) {
+				ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
 				return;
+			}
+			priv->pkey_index = new_index;
+		} else {
+			result = update_parent_pkey(priv);
+			/* restart QP only if P_Key value changed */
+			if (result) {
+				ipoib_dbg(priv, "Not flushing - P_Key value not changed.\n");
+				return;
+			}
 		}
-
-		/* restart QP only if P_Key index is changed */
-		if (test_and_set_bit(IPOIB_PKEY_ASSIGNED, &priv->flags) &&
-		    new_index == priv->pkey_index) {
-			ipoib_dbg(priv, "Not flushing - P_Key index not changed.\n");
-			return;
-		}
-		priv->pkey_index = new_index;
 	}
 
 	if (level == IPOIB_FLUSH_LIGHT) {

drivers/infiniband/ulp/ipoib/ipoib_main.c

@@ -1461,7 +1461,7 @@ static ssize_t create_child(struct device *dev,
 	if (sscanf(buf, "%i", &pkey) != 1)
 		return -EINVAL;
 
-	if (pkey < 0 || pkey > 0xffff)
+	if (pkey <= 0 || pkey > 0xffff || pkey == 0x8000)
 		return -EINVAL;
 
 	/*

drivers/infiniband/ulp/ipoib/ipoib_netlink.c

@@ -119,6 +119,15 @@ static int ipoib_new_child_link(struct net *src_net, struct net_device *dev,
 	} else
 		child_pkey  = nla_get_u16(data[IFLA_IPOIB_PKEY]);
 
+	if (child_pkey == 0 || child_pkey == 0x8000)
+		return -EINVAL;
+
+	/*
+	 * Set the full membership bit, so that we join the right
+	 * broadcast group, etc.
+	 */
+	child_pkey |= 0x8000;
+
 	err = __ipoib_vlan_add(ppriv, netdev_priv(dev), child_pkey, IPOIB_RTNL_CHILD);
 
 	if (!err && data)

drivers/net/ethernet/mellanox/mlx5/core/cmd.c

@@ -46,7 +46,7 @@
 #include "mlx5_core.h"
 
 enum {
-	CMD_IF_REV = 3,
+	CMD_IF_REV = 4,
 };
 
 enum {
@@ -282,6 +282,12 @@ const char *mlx5_command_str(int command)
 	case MLX5_CMD_OP_TEARDOWN_HCA:
 		return "TEARDOWN_HCA";
 
+	case MLX5_CMD_OP_ENABLE_HCA:
+		return "MLX5_CMD_OP_ENABLE_HCA";
+
+	case MLX5_CMD_OP_DISABLE_HCA:
+		return "MLX5_CMD_OP_DISABLE_HCA";
+
 	case MLX5_CMD_OP_QUERY_PAGES:
 		return "QUERY_PAGES";
 

drivers/net/ethernet/mellanox/mlx5/core/main.c

@@ -249,6 +249,44 @@ static int set_hca_ctrl(struct mlx5_core_dev *dev)
 	return err;
 }
 
+static int mlx5_core_enable_hca(struct mlx5_core_dev *dev)
+{
+	int err;
+	struct mlx5_enable_hca_mbox_in in;
+	struct mlx5_enable_hca_mbox_out out;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_ENABLE_HCA);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err)
+		return err;
+
+	if (out.hdr.status)
+		return mlx5_cmd_status_to_err(&out.hdr);
+
+	return 0;
+}
+
+static int mlx5_core_disable_hca(struct mlx5_core_dev *dev)
+{
+	int err;
+	struct mlx5_disable_hca_mbox_in in;
+	struct mlx5_disable_hca_mbox_out out;
+
+	memset(&in, 0, sizeof(in));
+	memset(&out, 0, sizeof(out));
+	in.hdr.opcode = cpu_to_be16(MLX5_CMD_OP_DISABLE_HCA);
+	err = mlx5_cmd_exec(dev, &in, sizeof(in), &out, sizeof(out));
+	if (err)
+		return err;
+
+	if (out.hdr.status)
+		return mlx5_cmd_status_to_err(&out.hdr);
+
+	return 0;
+}
+
 int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 {
 	struct mlx5_priv *priv = &dev->priv;
@@ -304,28 +342,41 @@ int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 	}
 
 	mlx5_pagealloc_init(dev);
+
+	err = mlx5_core_enable_hca(dev);
+	if (err) {
+		dev_err(&pdev->dev, "enable hca failed\n");
+		goto err_pagealloc_cleanup;
+	}
+
+	err = mlx5_satisfy_startup_pages(dev, 1);
+	if (err) {
+		dev_err(&pdev->dev, "failed to allocate boot pages\n");
+		goto err_disable_hca;
+	}
+
 	err = set_hca_ctrl(dev);
 	if (err) {
 		dev_err(&pdev->dev, "set_hca_ctrl failed\n");
-		goto err_pagealloc_cleanup;
+		goto reclaim_boot_pages;
 	}
 
 	err = handle_hca_cap(dev);
 	if (err) {
 		dev_err(&pdev->dev, "handle_hca_cap failed\n");
-		goto err_pagealloc_cleanup;
+		goto reclaim_boot_pages;
 	}
 
-	err = mlx5_satisfy_startup_pages(dev);
+	err = mlx5_satisfy_startup_pages(dev, 0);
 	if (err) {
-		dev_err(&pdev->dev, "failed to allocate startup pages\n");
-		goto err_pagealloc_cleanup;
+		dev_err(&pdev->dev, "failed to allocate init pages\n");
+		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_pagealloc_start(dev);
 	if (err) {
 		dev_err(&pdev->dev, "mlx5_pagealloc_start failed\n");
-		goto err_reclaim_pages;
+		goto reclaim_boot_pages;
 	}
 
 	err = mlx5_cmd_init_hca(dev);
@@ -396,9 +447,12 @@ int mlx5_dev_init(struct mlx5_core_dev *dev, struct pci_dev *pdev)
 err_pagealloc_stop:
 	mlx5_pagealloc_stop(dev);
 
-err_reclaim_pages:
+reclaim_boot_pages:
 	mlx5_reclaim_startup_pages(dev);
 
+err_disable_hca:
+	mlx5_core_disable_hca(dev);
+
 err_pagealloc_cleanup:
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_cmd_cleanup(dev);
@@ -434,6 +488,7 @@ void mlx5_dev_cleanup(struct mlx5_core_dev *dev)
 	mlx5_cmd_teardown_hca(dev);
 	mlx5_pagealloc_stop(dev);
 	mlx5_reclaim_startup_pages(dev);
+	mlx5_core_disable_hca(dev);
 	mlx5_pagealloc_cleanup(dev);
 	mlx5_cmd_cleanup(dev);
 	iounmap(dev->iseg);

drivers/net/ethernet/mellanox/mlx5/core/pagealloc.c

@@ -64,7 +64,7 @@ struct mlx5_query_pages_inbox {
 
 struct mlx5_query_pages_outbox {
 	struct mlx5_outbox_hdr	hdr;
-	u8			reserved[2];
+	__be16			num_boot_pages;
 	__be16			func_id;
 	__be16			init_pages;
 	__be16			num_pages;
@@ -146,7 +146,7 @@ static struct page *remove_page(struct mlx5_core_dev *dev, u64 addr)
 }
 
 static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
-				s16 *pages, s16 *init_pages)
+				s16 *pages, s16 *init_pages, u16 *boot_pages)
 {
 	struct mlx5_query_pages_inbox	in;
 	struct mlx5_query_pages_outbox	out;
@@ -164,8 +164,13 @@ static int mlx5_cmd_query_pages(struct mlx5_core_dev *dev, u16 *func_id,
 
 	if (pages)
 		*pages = be16_to_cpu(out.num_pages);
+
 	if (init_pages)
 		*init_pages = be16_to_cpu(out.init_pages);
+
+	if (boot_pages)
+		*boot_pages = be16_to_cpu(out.num_boot_pages);
+
 	*func_id = be16_to_cpu(out.func_id);
 
 	return err;
@@ -357,19 +362,22 @@ void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 	queue_work(dev->priv.pg_wq, &req->work);
 }
 
-int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev)
+int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot)
 {
+	u16 uninitialized_var(boot_pages);
 	s16 uninitialized_var(init_pages);
 	u16 uninitialized_var(func_id);
 	int err;
 
-	err = mlx5_cmd_query_pages(dev, &func_id, NULL, &init_pages);
+	err = mlx5_cmd_query_pages(dev, &func_id, NULL, &init_pages,
+				   &boot_pages);
 	if (err)
 		return err;
 
-	mlx5_core_dbg(dev, "requested %d init pages for func_id 0x%x\n", init_pages, func_id);
 
-	return give_pages(dev, func_id, init_pages, 0);
+	mlx5_core_dbg(dev, "requested %d init pages and %d boot pages for func_id 0x%x\n",
+		      init_pages, boot_pages, func_id);
+	return give_pages(dev, func_id, boot ? boot_pages : init_pages, 0);
 }
 
 static int optimal_reclaimed_pages(void)

include/linux/mlx5/device.h

@@ -690,6 +690,26 @@ struct mlx5_query_cq_mbox_out {
 	__be64			pas[0];
 };
 
+struct mlx5_enable_hca_mbox_in {
+	struct mlx5_inbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct mlx5_enable_hca_mbox_out {
+	struct mlx5_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct mlx5_disable_hca_mbox_in {
+	struct mlx5_inbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
+struct mlx5_disable_hca_mbox_out {
+	struct mlx5_outbox_hdr	hdr;
+	u8			rsvd[8];
+};
+
 struct mlx5_eq_context {
 	u8			status;
 	u8			ec_oi;

include/linux/mlx5/driver.h

@@ -101,6 +101,8 @@ enum {
 	MLX5_CMD_OP_QUERY_ADAPTER		= 0x101,
 	MLX5_CMD_OP_INIT_HCA			= 0x102,
 	MLX5_CMD_OP_TEARDOWN_HCA		= 0x103,
+	MLX5_CMD_OP_ENABLE_HCA			= 0x104,
+	MLX5_CMD_OP_DISABLE_HCA			= 0x105,
 	MLX5_CMD_OP_QUERY_PAGES			= 0x107,
 	MLX5_CMD_OP_MANAGE_PAGES		= 0x108,
 	MLX5_CMD_OP_SET_HCA_CAP			= 0x109,
@@ -690,7 +692,7 @@ int mlx5_pagealloc_start(struct mlx5_core_dev *dev);
 void mlx5_pagealloc_stop(struct mlx5_core_dev *dev);
 void mlx5_core_req_pages_handler(struct mlx5_core_dev *dev, u16 func_id,
 				 s16 npages);
-int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev);
+int mlx5_satisfy_startup_pages(struct mlx5_core_dev *dev, int boot);
 int mlx5_reclaim_startup_pages(struct mlx5_core_dev *dev);
 void mlx5_register_debugfs(void);
 void mlx5_unregister_debugfs(void);