net/mlx4_core: Dynamic VST to VST vlan/qos changes

Within VST mode, enable modifying the vlan and/or qos
for a VF without requiring unbind/rebind.

This requires firmware which supports the UPDATE_QP command.
(If the command is not available, we fall back to requiring
unbind/bind to activate these changes).

To avoid race conditions with modify-qp on QPs that are affected
by update-qp, this operation is performed on the comm_wq.

If the update operation succeeds for all the necessary QPs, a
vlan_unregister is performed for the abandoned vlan id.

Signed-off-by: Jack Morgenstein <jackm@dev.mellanox.co.il>
Signed-off-by: Or Gerlitz <ogerlitz@mellanox.com>
Signed-off-by: David S. Miller <davem@davemloft.net>

4 files changed, 282 insertions, 10 deletions

diff --git a/drivers/net/ethernet/mellanox/mlx4/cmd.c b/drivers/net/ethernet/mellanox/mlx4/cmd.c
index df04c82..7b92789 100644
--- a/drivers/net/ethernet/mellanox/mlx4/cmd.c
+++ b/drivers/net/ethernet/mellanox/mlx4/cmd.c
@@ -112,6 +112,14 @@ enum {
 	GO_BIT_TIMEOUT_MSECS	= 10000
 };
 
+enum mlx4_vlan_transition {
+	MLX4_VLAN_TRANSITION_VST_VST = 0,
+	MLX4_VLAN_TRANSITION_VST_VGT = 1,
+	MLX4_VLAN_TRANSITION_VGT_VST = 2,
+	MLX4_VLAN_TRANSITION_VGT_VGT = 3,
+};
+
+
 struct mlx4_cmd_context {
 	struct completion	done;
 	int			result;
@@ -792,6 +800,15 @@ static int mlx4_MAD_IFC_wrapper(struct mlx4_dev *dev, int slave,
 				    vhcr->op, MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
 }
 
+int MLX4_CMD_UPDATE_QP_wrapper(struct mlx4_dev *dev, int slave,
+		     struct mlx4_vhcr *vhcr,
+		     struct mlx4_cmd_mailbox *inbox,
+		     struct mlx4_cmd_mailbox *outbox,
+		     struct mlx4_cmd_info *cmd)
+{
+	return -EPERM;
+}
+
 int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
 		     struct mlx4_vhcr *vhcr,
 		     struct mlx4_cmd_mailbox *inbox,
@@ -1226,6 +1243,15 @@ static struct mlx4_cmd_info cmd_info[] = {
 		.wrapper = mlx4_GEN_QP_wrapper
 	},
 	{
+		.opcode = MLX4_CMD_UPDATE_QP,
+		.has_inbox = false,
+		.has_outbox = false,
+		.out_is_imm = false,
+		.encode_slave_id = false,
+		.verify = NULL,
+		.wrapper = MLX4_CMD_UPDATE_QP_wrapper
+	},
+	{
 		.opcode = MLX4_CMD_CONF_SPECIAL_QP,
 		.has_inbox = false,
 		.has_outbox = false,
@@ -1495,6 +1521,72 @@ out:
 	return ret;
 }
 
+
+int mlx4_master_immediate_activate_vlan_qos(struct mlx4_priv *priv,
+					    int slave, int port)
+{
+	struct mlx4_vport_oper_state *vp_oper;
+	struct mlx4_vport_state *vp_admin;
+	struct mlx4_vf_immed_vlan_work *work;
+	int err;
+	int admin_vlan_ix = NO_INDX;
+
+	vp_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+	vp_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
+
+	if (vp_oper->state.default_vlan == vp_admin->default_vlan &&
+	    vp_oper->state.default_qos == vp_admin->default_qos)
+		return 0;
+
+	work = kzalloc(sizeof(*work), GFP_KERNEL);
+	if (!work)
+		return -ENOMEM;
+
+	if (vp_oper->state.default_vlan != vp_admin->default_vlan) {
+		err = __mlx4_register_vlan(&priv->dev, port,
+					   vp_admin->default_vlan,
+					   &admin_vlan_ix);
+		if (err) {
+			mlx4_warn((&priv->dev),
+				  "No vlan resources slave %d, port %d\n",
+				  slave, port);
+			return err;
+		}
+		work->flags |= MLX4_VF_IMMED_VLAN_FLAG_VLAN;
+		mlx4_dbg((&(priv->dev)),
+			 "alloc vlan %d idx  %d slave %d port %d\n",
+			 (int)(vp_admin->default_vlan),
+			 admin_vlan_ix, slave, port);
+	}
+
+	/* save original vlan ix and vlan id */
+	work->orig_vlan_id = vp_oper->state.default_vlan;
+	work->orig_vlan_ix = vp_oper->vlan_idx;
+
+	/* handle new qos */
+	if (vp_oper->state.default_qos != vp_admin->default_qos)
+		work->flags |= MLX4_VF_IMMED_VLAN_FLAG_QOS;
+
+	if (work->flags & MLX4_VF_IMMED_VLAN_FLAG_VLAN)
+		vp_oper->vlan_idx = admin_vlan_ix;
+
+	vp_oper->state.default_vlan = vp_admin->default_vlan;
+	vp_oper->state.default_qos = vp_admin->default_qos;
+
+	/* iterate over QPs owned by this slave, using UPDATE_QP */
+	work->port = port;
+	work->slave = slave;
+	work->qos = vp_oper->state.default_qos;
+	work->vlan_id = vp_oper->state.default_vlan;
+	work->vlan_ix = vp_oper->vlan_idx;
+	work->priv = priv;
+	INIT_WORK(&work->work, mlx4_vf_immed_vlan_work_handler);
+	queue_work(priv->mfunc.master.comm_wq, &work->work);
+
+	return 0;
+}
+
+
 static int mlx4_master_activate_admin_state(struct mlx4_priv *priv, int slave)
 {
 	int port, err;
@@ -2109,11 +2201,18 @@ int mlx4_set_vf_mac(struct mlx4_dev *dev, int port, int vf, u64 mac)
 }
 EXPORT_SYMBOL_GPL(mlx4_set_vf_mac);
 
+static int calculate_transition(u16 oper_vlan, u16 admin_vlan)
+{
+	return (2 * (oper_vlan == MLX4_VGT) + (admin_vlan == MLX4_VGT));
+}
+
 int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
-	struct mlx4_vport_state *s_info;
+	struct mlx4_vport_oper_state *vf_oper;
+	struct mlx4_vport_state *vf_admin;
 	int slave;
+	enum mlx4_vlan_transition vlan_trans;
 
 	if ((!mlx4_is_master(dev)) ||
 	    !(dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_VLAN_CONTROL))
@@ -2126,12 +2225,25 @@ int mlx4_set_vf_vlan(struct mlx4_dev *dev, int port, int vf, u16 vlan, u8 qos)
 	if (slave < 0)
 		return -EINVAL;
 
-	s_info = &priv->mfunc.master.vf_admin[slave].vport[port];
+	vf_admin = &priv->mfunc.master.vf_admin[slave].vport[port];
+	vf_oper = &priv->mfunc.master.vf_oper[slave].vport[port];
+
 	if ((0 == vlan) && (0 == qos))
-		s_info->default_vlan = MLX4_VGT;
+		vf_admin->default_vlan = MLX4_VGT;
 	else
-		s_info->default_vlan = vlan;
-	s_info->default_qos = qos;
+		vf_admin->default_vlan = vlan;
+	vf_admin->default_qos = qos;
+
+	vlan_trans = calculate_transition(vf_oper->state.default_vlan,
+					  vf_admin->default_vlan);
+
+	if (priv->mfunc.master.slave_state[slave].active &&
+	    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_UPDATE_QP &&
+	    vlan_trans == MLX4_VLAN_TRANSITION_VST_VST) {
+		mlx4_info(dev, "updating vf %d port %d config params immediately\n",
+			  vf, port);
+		mlx4_master_immediate_activate_vlan_qos(priv, slave, port);
+	}
 	return 0;
 }
 EXPORT_SYMBOL_GPL(mlx4_set_vf_vlan);
diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c
index 569bbe3..8873d68 100644
--- a/drivers/net/ethernet/mellanox/mlx4/fw.c
+++ b/drivers/net/ethernet/mellanox/mlx4/fw.c
@@ -133,7 +133,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[4] = "Automatic MAC reassignment support",
 		[5] = "Time stamping support",
 		[6] = "VST (control vlan insertion/stripping) support",
-		[7] = "FSM (MAC anti-spoofing) support"
+		[7] = "FSM (MAC anti-spoofing) support",
+		[8] = "Dynamic QP updates support"
 	};
 	int i;
 
@@ -659,6 +660,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			 QUERY_DEV_CAP_MAX_COUNTERS_OFFSET);
 
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
+	if (field32 & (1 << 16))
+		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
 	if (field32 & (1 << 26))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_VLAN_CONTROL;
 	if (field32 & (1 << 20))
diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
index 7527293..5abcb65 100644
--- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h
+++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h
@@ -571,6 +571,24 @@ struct mlx4_cmd {
 	u8			comm_toggle;
 };
 
+enum {
+	MLX4_VF_IMMED_VLAN_FLAG_VLAN = 1 << 0,
+	MLX4_VF_IMMED_VLAN_FLAG_QOS = 1 << 1,
+};
+struct mlx4_vf_immed_vlan_work {
+	struct work_struct	work;
+	struct mlx4_priv	*priv;
+	int			flags;
+	int			slave;
+	int			vlan_ix;
+	int			orig_vlan_ix;
+	u8			port;
+	u8			qos;
+	u16			vlan_id;
+	u16			orig_vlan_id;
+};
+
+
 struct mlx4_uar_table {
 	struct mlx4_bitmap	bitmap;
 };
@@ -1218,4 +1236,6 @@ static inline spinlock_t *mlx4_tlock(struct mlx4_dev *dev)
 
 #define NOT_MASKED_PD_BITS 17
 
+void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work);
+
 #endif /* MLX4_H */
diff --git a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
index 1157f02..46323a2 100644
--- a/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
+++ b/drivers/net/ethernet/mellanox/mlx4/resource_tracker.c
@@ -101,6 +101,8 @@ struct res_qp {
 	spinlock_t		mcg_spl;
 	int			local_qpn;
 	atomic_t		ref_count;
+	u32			qpc_flags;
+	u8			sched_queue;
 };
 
 enum res_mtt_states {
@@ -355,7 +357,7 @@ static void update_gid(struct mlx4_dev *dev, struct mlx4_cmd_mailbox *inbox,
 
 static int update_vport_qp_param(struct mlx4_dev *dev,
 				 struct mlx4_cmd_mailbox *inbox,
-				 u8 slave)
+				 u8 slave, u32 qpn)
 {
 	struct mlx4_qp_context	*qpc = inbox->buf + 8;
 	struct mlx4_vport_oper_state *vp_oper;
@@ -369,9 +371,17 @@ static int update_vport_qp_param(struct mlx4_dev *dev,
 
 	if (MLX4_VGT != vp_oper->state.default_vlan) {
 		qp_type	= (be32_to_cpu(qpc->flags) >> 16) & 0xff;
-		if (MLX4_QP_ST_RC == qp_type)
+		if (MLX4_QP_ST_RC == qp_type ||
+		    (MLX4_QP_ST_UD == qp_type &&
+		     !mlx4_is_qp_reserved(dev, qpn)))
 			return -EINVAL;
 
+		/* the reserved QPs (special, proxy, tunnel)
+		 * do not operate over vlans
+		 */
+		if (mlx4_is_qp_reserved(dev, qpn))
+			return 0;
+
 		/* force strip vlan by clear vsd */
 		qpc->param3 &= ~cpu_to_be32(MLX4_STRIP_VLAN);
 		if (0 != vp_oper->state.default_vlan) {
@@ -2114,6 +2124,8 @@ int mlx4_RST2INIT_QP_wrapper(struct mlx4_dev *dev, int slave,
 	if (err)
 		return err;
 	qp->local_qpn = local_qpn;
+	qp->sched_queue = 0;
+	qp->qpc_flags = be32_to_cpu(qpc->flags);
 
 	err = get_res(dev, slave, mtt_base, RES_MTT, &mtt);
 	if (err)
@@ -2836,6 +2848,9 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
 {
 	int err;
 	struct mlx4_qp_context *qpc = inbox->buf + 8;
+	int qpn = vhcr->in_modifier & 0x7fffff;
+	struct res_qp *qp;
+	u8 orig_sched_queue;
 
 	err = verify_qp_parameters(dev, inbox, QP_TRANS_INIT2RTR, slave);
 	if (err)
@@ -2844,11 +2859,30 @@ int mlx4_INIT2RTR_QP_wrapper(struct mlx4_dev *dev, int slave,
 	update_pkey_index(dev, slave, inbox);
 	update_gid(dev, inbox, (u8)slave);
 	adjust_proxy_tun_qkey(dev, vhcr, qpc);
-	err = update_vport_qp_param(dev, inbox, slave);
+	orig_sched_queue = qpc->pri_path.sched_queue;
+	err = update_vport_qp_param(dev, inbox, slave, qpn);
 	if (err)
 		return err;
 
-	return mlx4_GEN_QP_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+	err = get_res(dev, slave, qpn, RES_QP, &qp);
+	if (err)
+		return err;
+	if (qp->com.from_state != RES_QP_HW) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	err = mlx4_DMA_wrapper(dev, slave, vhcr, inbox, outbox, cmd);
+out:
+	/* if no error, save sched queue value passed in by VF. This is
+	 * essentially the QOS value provided by the VF. This will be useful
+	 * if we allow dynamic changes from VST back to VGT
+	 */
+	if (!err)
+		qp->sched_queue = orig_sched_queue;
+
+	put_res(dev, slave, qpn, RES_QP);
+	return err;
 }
 
 int mlx4_RTR2RTS_QP_wrapper(struct mlx4_dev *dev, int slave,
@@ -3932,3 +3966,106 @@ void mlx4_delete_all_resources_for_slave(struct mlx4_dev *dev, int slave)
 	rem_slave_xrcdns(dev, slave);
 	mutex_unlock(&priv->mfunc.master.res_tracker.slave_list[slave].mutex);
 }
+
+void mlx4_vf_immed_vlan_work_handler(struct work_struct *_work)
+{
+	struct mlx4_vf_immed_vlan_work *work =
+		container_of(_work, struct mlx4_vf_immed_vlan_work, work);
+	struct mlx4_cmd_mailbox *mailbox;
+	struct mlx4_update_qp_context *upd_context;
+	struct mlx4_dev *dev = &work->priv->dev;
+	struct mlx4_resource_tracker *tracker =
+		&work->priv->mfunc.master.res_tracker;
+	struct list_head *qp_list =
+		&tracker->slave_list[work->slave].res_list[RES_QP];
+	struct res_qp *qp;
+	struct res_qp *tmp;
+	u64 qp_mask = ((1ULL << MLX4_UPD_QP_PATH_MASK_ETH_TX_BLOCK_UNTAGGED) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_TX_BLOCK_1P) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_TX_BLOCK_TAGGED) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_RX_BLOCK_UNTAGGED) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_RX_BLOCK_1P) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_ETH_RX_BLOCK_TAGGED) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_VLAN_INDEX) |
+		       (1ULL << MLX4_UPD_QP_PATH_MASK_SCHED_QUEUE));
+
+	int err;
+	int port, errors = 0;
+	u8 vlan_control;
+
+	if (mlx4_is_slave(dev)) {
+		mlx4_warn(dev, "Trying to update-qp in slave %d\n",
+			  work->slave);
+		goto out;
+	}
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		goto out;
+
+	if (!work->vlan_id)
+		vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
+			MLX4_VLAN_CTRL_ETH_RX_BLOCK_TAGGED;
+	else
+		vlan_control = MLX4_VLAN_CTRL_ETH_TX_BLOCK_TAGGED |
+			MLX4_VLAN_CTRL_ETH_RX_BLOCK_PRIO_TAGGED |
+			MLX4_VLAN_CTRL_ETH_RX_BLOCK_UNTAGGED;
+
+	upd_context = mailbox->buf;
+	upd_context->primary_addr_path_mask = cpu_to_be64(qp_mask);
+	upd_context->qp_context.pri_path.vlan_control = vlan_control;
+	upd_context->qp_context.pri_path.vlan_index = work->vlan_ix;
+
+	spin_lock_irq(mlx4_tlock(dev));
+	list_for_each_entry_safe(qp, tmp, qp_list, com.list) {
+		spin_unlock_irq(mlx4_tlock(dev));
+		if (qp->com.owner == work->slave) {
+			if (qp->com.from_state != RES_QP_HW ||
+			    !qp->sched_queue ||  /* no INIT2RTR trans yet */
+			    mlx4_is_qp_reserved(dev, qp->local_qpn) ||
+			    qp->qpc_flags & (1 << MLX4_RSS_QPC_FLAG_OFFSET)) {
+				spin_lock_irq(mlx4_tlock(dev));
+				continue;
+			}
+			port = (qp->sched_queue >> 6 & 1) + 1;
+			if (port != work->port) {
+				spin_lock_irq(mlx4_tlock(dev));
+				continue;
+			}
+			upd_context->qp_context.pri_path.sched_queue =
+				qp->sched_queue & 0xC7;
+			upd_context->qp_context.pri_path.sched_queue |=
+				((work->qos & 0x7) << 3);
+
+			err = mlx4_cmd(dev, mailbox->dma,
+				       qp->local_qpn & 0xffffff,
+				       0, MLX4_CMD_UPDATE_QP,
+				       MLX4_CMD_TIME_CLASS_C, MLX4_CMD_NATIVE);
+			if (err) {
+				mlx4_info(dev, "UPDATE_QP failed for slave %d, "
+					  "port %d, qpn %d (%d)\n",
+					  work->slave, port, qp->local_qpn,
+					  err);
+				errors++;
+			}
+		}
+		spin_lock_irq(mlx4_tlock(dev));
+	}
+	spin_unlock_irq(mlx4_tlock(dev));
+	mlx4_free_cmd_mailbox(dev, mailbox);
+
+	if (errors)
+		mlx4_err(dev, "%d UPDATE_QP failures for slave %d, port %d\n",
+			 errors, work->slave, work->port);
+
+	/* unregister previous vlan_id if needed and we had no errors
+	 * while updating the QPs
+	 */
+	if (work->flags & MLX4_VF_IMMED_VLAN_FLAG_VLAN && !errors &&
+	    NO_INDX != work->orig_vlan_ix)
+		__mlx4_unregister_vlan(&work->priv->dev, work->port,
+				       work->orig_vlan_ix);
+out:
+	kfree(work);
+	return;
+}