Merge branch 'mlx4-next'

Or Gerlitz says:

====================
mlx4 driver update

This series from Matan, Jenny, Dotan and myself is mostly about adding
support to a new performance optimized flow steering mode (patches 4-10).

The 1st two patches are small fixes (one for VXLAN and one for SRIOV),
and the third patch is a fix to avoid hard-lockup situation when many
(hunderds) processes holding user-space QPs/CQs get events.

Matan and Or.
====================
Signed-off-by: David S. Miller <davem@davemloft.net>

drivers/infiniband/hw/mlx4/cq.c

@@ -233,7 +233,10 @@ struct ib_cq *mlx4_ib_create_cq(struct ib_device *ibdev, int entries, int vector
 	if (err)
 		goto err_dbmap;
 
-	cq->mcq.comp  = mlx4_ib_cq_comp;
+	if (context)
+		cq->mcq.tasklet_ctx.comp = mlx4_ib_cq_comp;
+	else
+		cq->mcq.comp = mlx4_ib_cq_comp;
 	cq->mcq.event = mlx4_ib_cq_event;
 
 	if (context)

drivers/infiniband/hw/mlx4/main.c

@@ -2227,7 +2227,7 @@ static void *mlx4_ib_add(struct mlx4_dev *dev)
 		ibdev->steer_qpn_count = MLX4_IB_UC_MAX_NUM_QPS;
 		err = mlx4_qp_reserve_range(dev, ibdev->steer_qpn_count,
 					    MLX4_IB_UC_STEER_QPN_ALIGN,
-					    &ibdev->steer_qpn_base);
+					    &ibdev->steer_qpn_base, 0);
 		if (err)
 			goto err_counter;
 

drivers/infiniband/hw/mlx4/qp.c

@@ -802,16 +802,21 @@ static int create_qp_common(struct mlx4_ib_dev *dev, struct ib_pd *pd,
 			}
 		}
 	} else {
-		/* Raw packet QPNs must be aligned to 8 bits. If not, the WQE
-		 * BlueFlame setup flow wrongly causes VLAN insertion. */
+		/* Raw packet QPNs may not have bits 6,7 set in their qp_num;
+		 * otherwise, the WQE BlueFlame setup flow wrongly causes
+		 * VLAN insertion. */
 		if (init_attr->qp_type == IB_QPT_RAW_PACKET)
-			err = mlx4_qp_reserve_range(dev->dev, 1, 1 << 8, &qpn);
+			err = mlx4_qp_reserve_range(dev->dev, 1, 1, &qpn,
+						    (init_attr->cap.max_send_wr ?
+						     MLX4_RESERVE_ETH_BF_QP : 0) |
+						    (init_attr->cap.max_recv_wr ?
+						     MLX4_RESERVE_A0_QP : 0));
 		else
 			if (qp->flags & MLX4_IB_QP_NETIF)
 				err = mlx4_ib_steer_qp_alloc(dev, 1, &qpn);
 			else
 				err = mlx4_qp_reserve_range(dev->dev, 1, 1,
-							    &qpn);
+							    &qpn, 0);
 		if (err)
 			goto err_proxy;
 	}

drivers/net/ethernet/mellanox/mlx4/cq.c

@@ -52,6 +52,51 @@
 #define MLX4_CQ_STATE_ARMED_SOL		( 6 <<  8)
 #define MLX4_EQ_STATE_FIRED		(10 <<  8)
 
+#define TASKLET_MAX_TIME 2
+#define TASKLET_MAX_TIME_JIFFIES msecs_to_jiffies(TASKLET_MAX_TIME)
+
+void mlx4_cq_tasklet_cb(unsigned long data)
+{
+	unsigned long flags;
+	unsigned long end = jiffies + TASKLET_MAX_TIME_JIFFIES;
+	struct mlx4_eq_tasklet *ctx = (struct mlx4_eq_tasklet *)data;
+	struct mlx4_cq *mcq, *temp;
+
+	spin_lock_irqsave(&ctx->lock, flags);
+	list_splice_tail_init(&ctx->list, &ctx->process_list);
+	spin_unlock_irqrestore(&ctx->lock, flags);
+
+	list_for_each_entry_safe(mcq, temp, &ctx->process_list, tasklet_ctx.list) {
+		list_del_init(&mcq->tasklet_ctx.list);
+		mcq->tasklet_ctx.comp(mcq);
+		if (atomic_dec_and_test(&mcq->refcount))
+			complete(&mcq->free);
+		if (time_after(jiffies, end))
+			break;
+	}
+
+	if (!list_empty(&ctx->process_list))
+		tasklet_schedule(&ctx->task);
+}
+
+static void mlx4_add_cq_to_tasklet(struct mlx4_cq *cq)
+{
+	unsigned long flags;
+	struct mlx4_eq_tasklet *tasklet_ctx = cq->tasklet_ctx.priv;
+
+	spin_lock_irqsave(&tasklet_ctx->lock, flags);
+	/* When migrating CQs between EQs will be implemented, please note
+	 * that you need to sync this point. It is possible that
+	 * while migrating a CQ, completions on the old EQs could
+	 * still arrive.
+	 */
+	if (list_empty_careful(&cq->tasklet_ctx.list)) {
+		atomic_inc(&cq->refcount);
+		list_add_tail(&cq->tasklet_ctx.list, &tasklet_ctx->list);
+	}
+	spin_unlock_irqrestore(&tasklet_ctx->lock, flags);
+}
+
 void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn)
 {
 	struct mlx4_cq *cq;
@@ -292,6 +337,11 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent,
 	cq->uar        = uar;
 	atomic_set(&cq->refcount, 1);
 	init_completion(&cq->free);
+	cq->comp = mlx4_add_cq_to_tasklet;
+	cq->tasklet_ctx.priv =
+		&priv->eq_table.eq[cq->vector].tasklet_ctx;
+	INIT_LIST_HEAD(&cq->tasklet_ctx.list);
+
 
 	cq->irq = priv->eq_table.eq[cq->vector].irq;
 	return 0;

drivers/net/ethernet/mellanox/mlx4/en_netdev.c

@@ -595,7 +595,7 @@ static int mlx4_en_get_qp(struct mlx4_en_priv *priv)
 		return 0;
 	}
 
-	err = mlx4_qp_reserve_range(dev, 1, 1, qpn);
+	err = mlx4_qp_reserve_range(dev, 1, 1, qpn, MLX4_RESERVE_A0_QP);
 	en_dbg(DRV, priv, "Reserved qp %d\n", *qpn);
 	if (err) {
 		en_err(priv, "Failed to reserve qp for mac registration\n");
@@ -1974,15 +1974,8 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 {
 	struct mlx4_en_port_profile *prof = priv->prof;
 	int i;
-	int err;
 	int node;
 
-	err = mlx4_qp_reserve_range(priv->mdev->dev, priv->tx_ring_num, 256, &priv->base_tx_qpn);
-	if (err) {
-		en_err(priv, "failed reserving range for TX rings\n");
-		return err;
-	}
-
 	/* Create tx Rings */
 	for (i = 0; i < priv->tx_ring_num; i++) {
 		node = cpu_to_node(i % num_online_cpus());
@@ -1991,7 +1984,6 @@ int mlx4_en_alloc_resources(struct mlx4_en_priv *priv)
 			goto err;
 
 		if (mlx4_en_create_tx_ring(priv, &priv->tx_ring[i],
-					   priv->base_tx_qpn + i,
 					   prof->tx_ring_size, TXBB_SIZE,
 					   node, i))
 			goto err;
@@ -2602,7 +2594,8 @@ int mlx4_en_init_netdev(struct mlx4_en_dev *mdev, int port,
 			NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX;
 
 	if (mdev->dev->caps.steering_mode ==
-	    MLX4_STEERING_MODE_DEVICE_MANAGED)
+	    MLX4_STEERING_MODE_DEVICE_MANAGED &&
+	    mdev->dev->caps.dmfs_high_steer_mode != MLX4_STEERING_DMFS_A0_STATIC)
 		dev->hw_features |= NETIF_F_NTUPLE;
 
 	if (mdev->dev->caps.steering_mode != MLX4_STEERING_MODE_A0)

drivers/net/ethernet/mellanox/mlx4/en_rx.c

@@ -888,7 +888,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud
 			gro_skb->ip_summed = ip_summed;
 
 			if (l2_tunnel && ip_summed == CHECKSUM_UNNECESSARY)
-				gro_skb->encapsulation = 1;
+				gro_skb->csum_level = 1;
+
 			if ((cqe->vlan_my_qpn &
 			    cpu_to_be32(MLX4_CQE_VLAN_PRESENT_MASK)) &&
 			    (dev->features & NETIF_F_HW_VLAN_CTAG_RX)) {
@@ -1130,7 +1131,8 @@ int mlx4_en_create_drop_qp(struct mlx4_en_priv *priv)
 	int err;
 	u32 qpn;
 
-	err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn);
+	err = mlx4_qp_reserve_range(priv->mdev->dev, 1, 1, &qpn,
+				    MLX4_RESERVE_A0_QP);
 	if (err) {
 		en_err(priv, "Failed reserving drop qpn\n");
 		return err;
@@ -1173,7 +1175,7 @@ int mlx4_en_config_rss_steer(struct mlx4_en_priv *priv)
 	en_dbg(DRV, priv, "Configuring rss steering\n");
 	err = mlx4_qp_reserve_range(mdev->dev, priv->rx_ring_num,
 				    priv->rx_ring_num,
-				    &rss_map->base_qpn);
+				    &rss_map->base_qpn, 0);
 	if (err) {
 		en_err(priv, "Failed reserving %d qps\n", priv->rx_ring_num);
 		return err;

drivers/net/ethernet/mellanox/mlx4/en_tx.c

@@ -46,7 +46,7 @@
 #include "mlx4_en.h"
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
-			   struct mlx4_en_tx_ring **pring, int qpn, u32 size,
+			   struct mlx4_en_tx_ring **pring, u32 size,
 			   u16 stride, int node, int queue_index)
 {
 	struct mlx4_en_dev *mdev = priv->mdev;
@@ -112,11 +112,17 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	       ring, ring->buf, ring->size, ring->buf_size,
 	       (unsigned long long) ring->wqres.buf.direct.map);
 
-	ring->qpn = qpn;
+	err = mlx4_qp_reserve_range(mdev->dev, 1, 1, &ring->qpn,
+				    MLX4_RESERVE_ETH_BF_QP);
+	if (err) {
+		en_err(priv, "failed reserving qp for TX ring\n");
+		goto err_map;
+	}
+
 	err = mlx4_qp_alloc(mdev->dev, ring->qpn, &ring->qp, GFP_KERNEL);
 	if (err) {
 		en_err(priv, "Failed allocating qp %d\n", ring->qpn);
-		goto err_map;
+		goto err_reserve;
 	}
 	ring->qp.event = mlx4_en_sqp_event;
 
@@ -143,6 +149,8 @@ int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 	*pring = ring;
 	return 0;
 
+err_reserve:
+	mlx4_qp_release_range(mdev->dev, ring->qpn, 1);
 err_map:
 	mlx4_en_unmap_buffer(&ring->wqres.buf);
 err_hwq_res:

drivers/net/ethernet/mellanox/mlx4/eq.c

@@ -450,7 +450,7 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 {
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_eqe *eqe;
-	int cqn;
+	int cqn = -1;
 	int eqes_found = 0;
 	int set_ci = 0;
 	int port;
@@ -758,6 +758,13 @@ static int mlx4_eq_int(struct mlx4_dev *dev, struct mlx4_eq *eq)
 
 	eq_set_ci(eq, 1);
 
+	/* cqn is 24bit wide but is initialized such that its higher bits
+	 * are ones too. Thus, if we got any event, cqn's high bits should be off
+	 * and we need to schedule the tasklet.
+	 */
+	if (!(cqn & ~0xffffff))
+		tasklet_schedule(&eq->tasklet_ctx.task);
+
 	return eqes_found;
 }
 
@@ -971,6 +978,12 @@ static int mlx4_create_eq(struct mlx4_dev *dev, int nent,
 
 	eq->cons_index = 0;
 
+	INIT_LIST_HEAD(&eq->tasklet_ctx.list);
+	INIT_LIST_HEAD(&eq->tasklet_ctx.process_list);
+	spin_lock_init(&eq->tasklet_ctx.lock);
+	tasklet_init(&eq->tasklet_ctx.task, mlx4_cq_tasklet_cb,
+		     (unsigned long)&eq->tasklet_ctx);
+
 	return err;
 
 err_out_free_mtt:
@@ -1027,6 +1040,7 @@ static void mlx4_free_eq(struct mlx4_dev *dev,
 		}
 	}
 	synchronize_irq(eq->irq);
+	tasklet_disable(&eq->tasklet_ctx.task);
 
 	mlx4_mtt_cleanup(dev, &eq->mtt);
 	for (i = 0; i < npages; ++i)

drivers/net/ethernet/mellanox/mlx4/fw.h

@@ -43,6 +43,26 @@ struct mlx4_mod_stat_cfg {
 	u8 log_pg_sz_m;
 };
 
+struct mlx4_port_cap {
+	u8  supported_port_types;
+	u8  suggested_type;
+	u8  default_sense;
+	u8  log_max_macs;
+	u8  log_max_vlans;
+	int ib_mtu;
+	int max_port_width;
+	int max_vl;
+	int max_gids;
+	int max_pkeys;
+	u64 def_mac;
+	u16 eth_mtu;
+	int trans_type;
+	int vendor_oui;
+	u16 wavelength;
+	u64 trans_code;
+	u8 dmfs_optimized_state;
+};
+
 struct mlx4_dev_cap {
 	int max_srq_sz;
 	int max_qp_sz;
@@ -67,17 +87,6 @@ struct mlx4_dev_cap {
 	int local_ca_ack_delay;
 	int num_ports;
 	u32 max_msg_sz;
-	int ib_mtu[MLX4_MAX_PORTS + 1];
-	int max_port_width[MLX4_MAX_PORTS + 1];
-	int max_vl[MLX4_MAX_PORTS + 1];
-	int max_gids[MLX4_MAX_PORTS + 1];
-	int max_pkeys[MLX4_MAX_PORTS + 1];
-	u64 def_mac[MLX4_MAX_PORTS + 1];
-	u16 eth_mtu[MLX4_MAX_PORTS + 1];
-	int trans_type[MLX4_MAX_PORTS + 1];
-	int vendor_oui[MLX4_MAX_PORTS + 1];
-	u16 wavelength[MLX4_MAX_PORTS + 1];
-	u64 trans_code[MLX4_MAX_PORTS + 1];
 	u16 stat_rate_support;
 	int fs_log_max_ucast_qp_range_size;
 	int fs_max_num_qp_per_entry;
@@ -115,12 +124,10 @@ struct mlx4_dev_cap {
 	u64 max_icm_sz;
 	int max_gso_sz;
 	int max_rss_tbl_sz;
-	u8  supported_port_types[MLX4_MAX_PORTS + 1];
-	u8  suggested_type[MLX4_MAX_PORTS + 1];
-	u8  default_sense[MLX4_MAX_PORTS + 1];
-	u8  log_max_macs[MLX4_MAX_PORTS + 1];
-	u8  log_max_vlans[MLX4_MAX_PORTS + 1];
 	u32 max_counters;
+	u32 dmfs_high_rate_qpn_base;
+	u32 dmfs_high_rate_qpn_range;
+	struct mlx4_port_cap port_cap[MLX4_MAX_PORTS + 1];
 };
 
 struct mlx4_func_cap {
@@ -144,6 +151,7 @@ struct mlx4_func_cap {
 	u8	port_flags;
 	u8	flags1;
 	u64	phys_port_id;
+	u32	extra_flags;
 };
 
 struct mlx4_func {
@@ -189,6 +197,7 @@ struct mlx4_init_hca_param {
 	u8  mw_enabled;  /* Enable memory windows */
 	u8  uar_page_sz; /* log pg sz in 4k chunks */
 	u8  steering_mode; /* for QUERY_HCA */
+	u8  dmfs_high_steer_mode; /* for QUERY_HCA */
 	u64 dev_cap_enabled;
 	u16 cqe_size; /* For use only when CQE stride feature enabled */
 	u16 eqe_size; /* For use only when EQE stride feature enabled */
@@ -216,6 +225,7 @@ struct mlx4_set_ib_param {
 };
 
 int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap);
+int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_cap);
 int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 			struct mlx4_func_cap *func_cap);
 int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,

drivers/net/ethernet/mellanox/mlx4/mcg.c

@@ -999,12 +999,27 @@ int mlx4_flow_attach(struct mlx4_dev *dev,
 	}
 
 	ret = mlx4_QP_FLOW_STEERING_ATTACH(dev, mailbox, size >> 2, reg_id);
-	if (ret == -ENOMEM)
+	if (ret == -ENOMEM) {
 		mlx4_err_rule(dev,
 			      "mcg table is full. Fail to register network rule\n",
 			      rule);
-	else if (ret)
-		mlx4_err_rule(dev, "Fail to register network rule\n", rule);
+	} else if (ret) {
+		if (ret == -ENXIO) {
+			if (dev->caps.steering_mode != MLX4_STEERING_MODE_DEVICE_MANAGED)
+				mlx4_err_rule(dev,
+					      "DMFS is not enabled, "
+					      "failed to register network rule.\n",
+					      rule);
+			else
+				mlx4_err_rule(dev,
+					      "Rule exceeds the dmfs_high_rate_mode limitations, "
+					      "failed to register network rule.\n",
+					      rule);
+
+		} else {
+			mlx4_err_rule(dev, "Fail to register network rule.\n", rule);
+		}
+	}
 
 	mlx4_free_cmd_mailbox(dev, mailbox);
 

drivers/net/ethernet/mellanox/mlx4/mlx4.h

@@ -43,6 +43,8 @@
 #include <linux/timer.h>
 #include <linux/semaphore.h>
 #include <linux/workqueue.h>
+#include <linux/interrupt.h>
+#include <linux/spinlock.h>
 
 #include <linux/mlx4/device.h>
 #include <linux/mlx4/driver.h>
@@ -243,6 +245,7 @@ struct mlx4_bitmap {
 	u32                     reserved_top;
 	u32			mask;
 	u32			avail;
+	u32			effective_len;
 	spinlock_t		lock;
 	unsigned long	       *table;
 };
@@ -373,6 +376,14 @@ struct mlx4_srq_context {
 	__be64			db_rec_addr;
 };
 
+struct mlx4_eq_tasklet {
+	struct list_head list;
+	struct list_head process_list;
+	struct tasklet_struct task;
+	/* lock on completion tasklet list */
+	spinlock_t lock;
+};
+
 struct mlx4_eq {
 	struct mlx4_dev	       *dev;
 	void __iomem	       *doorbell;
@@ -383,6 +394,7 @@ struct mlx4_eq {
 	int			nent;
 	struct mlx4_buf_list   *page_list;
 	struct mlx4_mtt		mtt;
+	struct mlx4_eq_tasklet	tasklet_ctx;
 };
 
 struct mlx4_slave_eqe {
@@ -670,8 +682,17 @@ struct mlx4_srq_table {
 	struct mlx4_icm_table	cmpt_table;
 };
 
+enum mlx4_qp_table_zones {
+	MLX4_QP_TABLE_ZONE_GENERAL,
+	MLX4_QP_TABLE_ZONE_RSS,
+	MLX4_QP_TABLE_ZONE_RAW_ETH,
+	MLX4_QP_TABLE_ZONE_NUM
+};
+
 struct mlx4_qp_table {
-	struct mlx4_bitmap	bitmap;
+	struct mlx4_bitmap	*bitmap_gen;
+	struct mlx4_zone_allocator *zones;
+	u32			zones_uids[MLX4_QP_TABLE_ZONE_NUM];
 	u32			rdmarc_base;
 	int			rdmarc_shift;
 	spinlock_t		lock;
@@ -873,7 +894,8 @@ extern struct workqueue_struct *mlx4_wq;
 
 u32 mlx4_bitmap_alloc(struct mlx4_bitmap *bitmap);
 void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr);
-u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align);
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt,
+			    int align, u32 skip_mask);
 void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt,
 			    int use_rr);
 u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap);
@@ -959,7 +981,7 @@ int mlx4_DMA_wrapper(struct mlx4_dev *dev, int slave,
 		     struct mlx4_cmd_mailbox *outbox,
 		     struct mlx4_cmd_info *cmd);
 int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
-			    int *base);
+			    int *base, u8 flags);
 void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 int __mlx4_register_mac(struct mlx4_dev *dev, u8 port, u64 mac);
 void __mlx4_unregister_mac(struct mlx4_dev *dev, u8 port, u64 mac);
@@ -1146,6 +1168,7 @@ void mlx4_cmd_use_polling(struct mlx4_dev *dev);
 int mlx4_comm_cmd(struct mlx4_dev *dev, u8 cmd, u16 param,
 		  unsigned long timeout);
 
+void mlx4_cq_tasklet_cb(unsigned long data);
 void mlx4_cq_completion(struct mlx4_dev *dev, u32 cqn);
 void mlx4_cq_event(struct mlx4_dev *dev, u32 cqn, int event_type);
 
@@ -1332,4 +1355,72 @@ int mlx4_get_slave_num_gids(struct mlx4_dev *dev, int slave, int port);
 int mlx4_get_vf_indx(struct mlx4_dev *dev, int slave);
 int mlx4_config_mad_demux(struct mlx4_dev *dev);
 
+enum mlx4_zone_flags {
+	MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO	= 1UL << 0,
+	MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO	= 1UL << 1,
+	MLX4_ZONE_FALLBACK_TO_HIGHER_PRIO	= 1UL << 2,
+	MLX4_ZONE_USE_RR			= 1UL << 3,
+};
+
+enum mlx4_zone_alloc_flags {
+	/* No two objects could overlap between zones. UID
+	 * could be left unused. If this flag is given and
+	 * two overlapped zones are used, an object will be free'd
+	 * from the smallest possible matching zone.
+	 */
+	MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP	= 1UL << 0,
+};
+
+struct mlx4_zone_allocator;
+
+/* Create a new zone allocator */
+struct mlx4_zone_allocator *mlx4_zone_allocator_create(enum mlx4_zone_alloc_flags flags);
+
+/* Attach a mlx4_bitmap <bitmap> of priority <priority> to the zone allocator
+ * <zone_alloc>. Allocating an object from this zone adds an offset <offset>.
+ * Similarly, when searching for an object to free, this offset it taken into
+ * account. The use_rr mlx4_ib parameter for allocating objects from this <bitmap>
+ * is given through the MLX4_ZONE_USE_RR flag in <flags>.
+ * When an allocation fails, <zone_alloc> tries to allocate from other zones
+ * according to the policy set by <flags>. <puid> is the unique identifier
+ * received to this zone.
+ */
+int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc,
+		      struct mlx4_bitmap *bitmap,
+		      u32 flags,
+		      int priority,
+		      int offset,
+		      u32 *puid);
+
+/* Remove bitmap indicated by <uid> from <zone_alloc> */
+int mlx4_zone_remove_one(struct mlx4_zone_allocator *zone_alloc, u32 uid);
+
+/* Delete the zone allocator <zone_alloc. This function doesn't destroy
+ * the attached bitmaps.
+ */
+void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc);
+
+/* Allocate <count> objects with align <align> and skip_mask <skip_mask>
+ * from the mlx4_bitmap whose uid is <uid>. The bitmap which we actually
+ * allocated from is returned in <puid>. If the allocation fails, a negative
+ * number is returned. Otherwise, the offset of the first object is returned.
+ */
+u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
+			    int align, u32 skip_mask, u32 *puid);
+
+/* Free <count> objects, start from <obj> of the uid <uid> from zone_allocator
+ * <zones>.
+ */
+u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones,
+			   u32 uid, u32 obj, u32 count);
+
+/* If <zones> was allocated with MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP, instead of
+ * specifying the uid when freeing an object, zone allocator could figure it by
+ * itself. Other parameters are similar to mlx4_zone_free.
+ */
+u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count);
+
+/* Returns a pointer to mlx4_bitmap that was attached to <zones> with <uid> */
+struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 uid);
+
 #endif /* MLX4_H */

drivers/net/ethernet/mellanox/mlx4/mlx4_en.h

@@ -778,7 +778,7 @@ netdev_tx_t mlx4_en_xmit(struct sk_buff *skb, struct net_device *dev);
 
 int mlx4_en_create_tx_ring(struct mlx4_en_priv *priv,
 			   struct mlx4_en_tx_ring **pring,
-			   int qpn, u32 size, u16 stride,
+			   u32 size, u16 stride,
 			   int node, int queue_index);
 void mlx4_en_destroy_tx_ring(struct mlx4_en_priv *priv,
 			     struct mlx4_en_tx_ring **pring);

drivers/net/ethernet/mellanox/mlx4/resource_tracker.c

@@ -1543,16 +1543,21 @@ static int qp_alloc_res(struct mlx4_dev *dev, int slave, int op, int cmd,
 	int align;
 	int base;
 	int qpn;
+	u8 flags;
 
 	switch (op) {
 	case RES_OP_RESERVE:
 		count = get_param_l(&in_param) & 0xffffff;
+		/* Turn off all unsupported QP allocation flags that the
+		 * slave tries to set.
+		 */
+		flags = (get_param_l(&in_param) >> 24) & dev->caps.alloc_res_qp_mask;
 		align = get_param_h(&in_param);
 		err = mlx4_grant_resource(dev, slave, RES_QP, count, 0);
 		if (err)
 			return err;
 
-		err = __mlx4_qp_reserve_range(dev, count, align, &base);
+		err = __mlx4_qp_reserve_range(dev, count, align, &base, flags);
 		if (err) {
 			mlx4_release_resource(dev, slave, RES_QP, count, 0);
 			return err;

include/linux/mlx4/device.h

@@ -117,6 +117,14 @@ enum {
 	MLX4_STEERING_MODE_DEVICE_MANAGED
 };
 
+enum {
+	MLX4_STEERING_DMFS_A0_DEFAULT,
+	MLX4_STEERING_DMFS_A0_DYNAMIC,
+	MLX4_STEERING_DMFS_A0_STATIC,
+	MLX4_STEERING_DMFS_A0_DISABLE,
+	MLX4_STEERING_DMFS_A0_NOT_SUPPORTED
+};
+
 static inline const char *mlx4_steering_mode_str(int steering_mode)
 {
 	switch (steering_mode) {
@@ -191,7 +199,26 @@ enum {
 	MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP	= 1LL <<  15,
 	MLX4_DEV_CAP_FLAG2_CONFIG_DEV		= 1LL <<  16,
 	MLX4_DEV_CAP_FLAG2_SYS_EQS		= 1LL <<  17,
-	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18
+	MLX4_DEV_CAP_FLAG2_80_VFS		= 1LL <<  18,
+	MLX4_DEV_CAP_FLAG2_FS_A0		= 1LL <<  19
+};
+
+enum {
+	MLX4_QUERY_FUNC_FLAGS_BF_RES_QP		= 1LL << 0,
+	MLX4_QUERY_FUNC_FLAGS_A0_RES_QP		= 1LL << 1
+};
+
+/* bit enums for an 8-bit flags field indicating special use
+ * QPs which require special handling in qp_reserve_range.
+ * Currently, this only includes QPs used by the ETH interface,
+ * where we expect to use blueflame.  These QPs must not have
+ * bits 6 and 7 set in their qp number.
+ *
+ * This enum may use only bits 0..7.
+ */
+enum {
+	MLX4_RESERVE_A0_QP	= 1 << 6,
+	MLX4_RESERVE_ETH_BF_QP	= 1 << 7,
 };
 
 enum {
@@ -207,7 +234,8 @@ enum {
 
 enum {
 	MLX4_FUNC_CAP_64B_EQE_CQE	= 1L << 0,
-	MLX4_FUNC_CAP_EQE_CQE_STRIDE	= 1L << 1
+	MLX4_FUNC_CAP_EQE_CQE_STRIDE	= 1L << 1,
+	MLX4_FUNC_CAP_DMFS_A0_STATIC	= 1L << 2
 };
 
 
@@ -333,6 +361,8 @@ enum {
 
 enum mlx4_qp_region {
 	MLX4_QP_REGION_FW = 0,
+	MLX4_QP_REGION_RSS_RAW_ETH,
+	MLX4_QP_REGION_BOTTOM = MLX4_QP_REGION_RSS_RAW_ETH,
 	MLX4_QP_REGION_ETH_ADDR,
 	MLX4_QP_REGION_FC_ADDR,
 	MLX4_QP_REGION_FC_EXCH,
@@ -462,6 +492,7 @@ struct mlx4_caps {
 	int			reserved_mcgs;
 	int			num_qp_per_mgm;
 	int			steering_mode;
+	int			dmfs_high_steer_mode;
 	int			fs_log_max_ucast_qp_range_size;
 	int			num_pds;
 	int			reserved_pds;
@@ -501,6 +532,9 @@ struct mlx4_caps {
 	u64			phys_port_id[MLX4_MAX_PORTS + 1];
 	int			tunnel_offload_mode;
 	u8			rx_checksum_flags_port[MLX4_MAX_PORTS + 1];
+	u8			alloc_res_qp_mask;
+	u32			dmfs_high_rate_qpn_base;
+	u32			dmfs_high_rate_qpn_range;
 };
 
 struct mlx4_buf_list {
@@ -621,6 +655,11 @@ struct mlx4_cq {
 
 	atomic_t		refcount;
 	struct completion	free;
+	struct {
+		struct list_head list;
+		void (*comp)(struct mlx4_cq *);
+		void		*priv;
+	} tasklet_ctx;
 };
 
 struct mlx4_qp {
@@ -869,7 +908,9 @@ static inline int mlx4_num_reserved_sqps(struct mlx4_dev *dev)
 static inline int mlx4_is_qp_reserved(struct mlx4_dev *dev, u32 qpn)
 {
 	return (qpn < dev->phys_caps.base_sqpn + 8 +
-		16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev));
+		16 * MLX4_MFUNC_MAX * !!mlx4_is_master(dev) &&
+		qpn >= dev->phys_caps.base_sqpn) ||
+	       (qpn < dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW]);
 }
 
 static inline int mlx4_is_guest_proxy(struct mlx4_dev *dev, int slave, u32 qpn)
@@ -945,8 +986,8 @@ int mlx4_cq_alloc(struct mlx4_dev *dev, int nent, struct mlx4_mtt *mtt,
 		  struct mlx4_uar *uar, u64 db_rec, struct mlx4_cq *cq,
 		  unsigned vector, int collapsed, int timestamp_en);
 void mlx4_cq_free(struct mlx4_dev *dev, struct mlx4_cq *cq);
-
-int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base);
+int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
+			  int *base, u8 flags);
 void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt);
 
 int mlx4_qp_alloc(struct mlx4_dev *dev, int qpn, struct mlx4_qp *qp,