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/alloc.c

@@ -76,22 +76,53 @@ void mlx4_bitmap_free(struct mlx4_bitmap *bitmap, u32 obj, int use_rr)
 	mlx4_bitmap_free_range(bitmap, obj, 1, use_rr);
 }
 
-u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt, int align)
+static unsigned long find_aligned_range(unsigned long *bitmap,
+					u32 start, u32 nbits,
+					int len, int align, u32 skip_mask)
+{
+	unsigned long end, i;
+
+again:
+	start = ALIGN(start, align);
+
+	while ((start < nbits) && (test_bit(start, bitmap) ||
+				   (start & skip_mask)))
+		start += align;
+
+	if (start >= nbits)
+		return -1;
+
+	end = start+len;
+	if (end > nbits)
+		return -1;
+
+	for (i = start + 1; i < end; i++) {
+		if (test_bit(i, bitmap) || ((u32)i & skip_mask)) {
+			start = i + 1;
+			goto again;
+		}
+	}
+
+	return start;
+}
+
+u32 mlx4_bitmap_alloc_range(struct mlx4_bitmap *bitmap, int cnt,
+			    int align, u32 skip_mask)
 {
 	u32 obj;
 
-	if (likely(cnt == 1 && align == 1))
+	if (likely(cnt == 1 && align == 1 && !skip_mask))
 		return mlx4_bitmap_alloc(bitmap);
 
 	spin_lock(&bitmap->lock);
 
-	obj = bitmap_find_next_zero_area(bitmap->table, bitmap->max,
-				bitmap->last, cnt, align - 1);
+	obj = find_aligned_range(bitmap->table, bitmap->last,
+				 bitmap->max, cnt, align, skip_mask);
 	if (obj >= bitmap->max) {
 		bitmap->top = (bitmap->top + bitmap->max + bitmap->reserved_top)
 				& bitmap->mask;
-		obj = bitmap_find_next_zero_area(bitmap->table, bitmap->max,
-						0, cnt, align - 1);
+		obj = find_aligned_range(bitmap->table, 0, bitmap->max,
+					 cnt, align, skip_mask);
 	}
 
 	if (obj < bitmap->max) {
@@ -118,6 +149,11 @@ u32 mlx4_bitmap_avail(struct mlx4_bitmap *bitmap)
 	return bitmap->avail;
 }
 
+static u32 mlx4_bitmap_masked_value(struct mlx4_bitmap *bitmap, u32 obj)
+{
+	return obj & (bitmap->max + bitmap->reserved_top - 1);
+}
+
 void mlx4_bitmap_free_range(struct mlx4_bitmap *bitmap, u32 obj, int cnt,
 			    int use_rr)
 {
@@ -147,6 +183,7 @@ int mlx4_bitmap_init(struct mlx4_bitmap *bitmap, u32 num, u32 mask,
 	bitmap->mask = mask;
 	bitmap->reserved_top = reserved_top;
 	bitmap->avail = num - reserved_top - reserved_bot;
+	bitmap->effective_len = bitmap->avail;
 	spin_lock_init(&bitmap->lock);
 	bitmap->table = kzalloc(BITS_TO_LONGS(bitmap->max) *
 				sizeof (long), GFP_KERNEL);
@@ -163,6 +200,382 @@ void mlx4_bitmap_cleanup(struct mlx4_bitmap *bitmap)
 	kfree(bitmap->table);
 }
 
+struct mlx4_zone_allocator {
+	struct list_head		entries;
+	struct list_head		prios;
+	u32				last_uid;
+	u32				mask;
+	/* protect the zone_allocator from concurrent accesses */
+	spinlock_t			lock;
+	enum mlx4_zone_alloc_flags	flags;
+};
+
+struct mlx4_zone_entry {
+	struct list_head		list;
+	struct list_head		prio_list;
+	u32				uid;
+	struct mlx4_zone_allocator	*allocator;
+	struct mlx4_bitmap		*bitmap;
+	int				use_rr;
+	int				priority;
+	int				offset;
+	enum mlx4_zone_flags		flags;
+};
+
+struct mlx4_zone_allocator *mlx4_zone_allocator_create(enum mlx4_zone_alloc_flags flags)
+{
+	struct mlx4_zone_allocator *zones = kmalloc(sizeof(*zones), GFP_KERNEL);
+
+	if (NULL == zones)
+		return NULL;
+
+	INIT_LIST_HEAD(&zones->entries);
+	INIT_LIST_HEAD(&zones->prios);
+	spin_lock_init(&zones->lock);
+	zones->last_uid = 0;
+	zones->mask = 0;
+	zones->flags = flags;
+
+	return zones;
+}
+
+int mlx4_zone_add_one(struct mlx4_zone_allocator *zone_alloc,
+		      struct mlx4_bitmap *bitmap,
+		      u32 flags,
+		      int priority,
+		      int offset,
+		      u32 *puid)
+{
+	u32 mask = mlx4_bitmap_masked_value(bitmap, (u32)-1);
+	struct mlx4_zone_entry *it;
+	struct mlx4_zone_entry *zone = kmalloc(sizeof(*zone), GFP_KERNEL);
+
+	if (NULL == zone)
+		return -ENOMEM;
+
+	zone->flags = flags;
+	zone->bitmap = bitmap;
+	zone->use_rr = (flags & MLX4_ZONE_USE_RR) ? MLX4_USE_RR : 0;
+	zone->priority = priority;
+	zone->offset = offset;
+
+	spin_lock(&zone_alloc->lock);
+
+	zone->uid = zone_alloc->last_uid++;
+	zone->allocator = zone_alloc;
+
+	if (zone_alloc->mask < mask)
+		zone_alloc->mask = mask;
+
+	list_for_each_entry(it, &zone_alloc->prios, prio_list)
+		if (it->priority >= priority)
+			break;
+
+	if (&it->prio_list == &zone_alloc->prios || it->priority > priority)
+		list_add_tail(&zone->prio_list, &it->prio_list);
+	list_add_tail(&zone->list, &it->list);
+
+	spin_unlock(&zone_alloc->lock);
+
+	*puid = zone->uid;
+
+	return 0;
+}
+
+/* Should be called under a lock */
+static int __mlx4_zone_remove_one_entry(struct mlx4_zone_entry *entry)
+{
+	struct mlx4_zone_allocator *zone_alloc = entry->allocator;
+
+	if (!list_empty(&entry->prio_list)) {
+		/* Check if we need to add an alternative node to the prio list */
+		if (!list_is_last(&entry->list, &zone_alloc->entries)) {
+			struct mlx4_zone_entry *next = list_first_entry(&entry->list,
+									typeof(*next),
+									list);
+
+			if (next->priority == entry->priority)
+				list_add_tail(&next->prio_list, &entry->prio_list);
+		}
+
+		list_del(&entry->prio_list);
+	}
+
+	list_del(&entry->list);
+
+	if (zone_alloc->flags & MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP) {
+		u32 mask = 0;
+		struct mlx4_zone_entry *it;
+
+		list_for_each_entry(it, &zone_alloc->prios, prio_list) {
+			u32 cur_mask = mlx4_bitmap_masked_value(it->bitmap, (u32)-1);
+
+			if (mask < cur_mask)
+				mask = cur_mask;
+		}
+		zone_alloc->mask = mask;
+	}
+
+	return 0;
+}
+
+void mlx4_zone_allocator_destroy(struct mlx4_zone_allocator *zone_alloc)
+{
+	struct mlx4_zone_entry *zone, *tmp;
+
+	spin_lock(&zone_alloc->lock);
+
+	list_for_each_entry_safe(zone, tmp, &zone_alloc->entries, list) {
+		list_del(&zone->list);
+		list_del(&zone->prio_list);
+		kfree(zone);
+	}
+
+	spin_unlock(&zone_alloc->lock);
+	kfree(zone_alloc);
+}
+
+/* Should be called under a lock */
+static u32 __mlx4_alloc_from_zone(struct mlx4_zone_entry *zone, int count,
+				  int align, u32 skip_mask, u32 *puid)
+{
+	u32 uid;
+	u32 res;
+	struct mlx4_zone_allocator *zone_alloc = zone->allocator;
+	struct mlx4_zone_entry *curr_node;
+
+	res = mlx4_bitmap_alloc_range(zone->bitmap, count,
+				      align, skip_mask);
+
+	if (res != (u32)-1) {
+		res += zone->offset;
+		uid = zone->uid;
+		goto out;
+	}
+
+	list_for_each_entry(curr_node, &zone_alloc->prios, prio_list) {
+		if (unlikely(curr_node->priority == zone->priority))
+			break;
+	}
+
+	if (zone->flags & MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO) {
+		struct mlx4_zone_entry *it = curr_node;
+
+		list_for_each_entry_continue_reverse(it, &zone_alloc->entries, list) {
+			res = mlx4_bitmap_alloc_range(it->bitmap, count,
+						      align, skip_mask);
+			if (res != (u32)-1) {
+				res += it->offset;
+				uid = it->uid;
+				goto out;
+			}
+		}
+	}
+
+	if (zone->flags & MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO) {
+		struct mlx4_zone_entry *it = curr_node;
+
+		list_for_each_entry_from(it, &zone_alloc->entries, list) {
+			if (unlikely(it == zone))
+				continue;
+
+			if (unlikely(it->priority != curr_node->priority))
+				break;
+
+			res = mlx4_bitmap_alloc_range(it->bitmap, count,
+						      align, skip_mask);
+			if (res != (u32)-1) {
+				res += it->offset;
+				uid = it->uid;
+				goto out;
+			}
+		}
+	}
+
+	if (zone->flags & MLX4_ZONE_FALLBACK_TO_HIGHER_PRIO) {
+		if (list_is_last(&curr_node->prio_list, &zone_alloc->prios))
+			goto out;
+
+		curr_node = list_first_entry(&curr_node->prio_list,
+					     typeof(*curr_node),
+					     prio_list);
+
+		list_for_each_entry_from(curr_node, &zone_alloc->entries, list) {
+			res = mlx4_bitmap_alloc_range(curr_node->bitmap, count,
+						      align, skip_mask);
+			if (res != (u32)-1) {
+				res += curr_node->offset;
+				uid = curr_node->uid;
+				goto out;
+			}
+		}
+	}
+
+out:
+	if (NULL != puid && res != (u32)-1)
+		*puid = uid;
+	return res;
+}
+
+/* Should be called under a lock */
+static void __mlx4_free_from_zone(struct mlx4_zone_entry *zone, u32 obj,
+				  u32 count)
+{
+	mlx4_bitmap_free_range(zone->bitmap, obj - zone->offset, count, zone->use_rr);
+}
+
+/* Should be called under a lock */
+static struct mlx4_zone_entry *__mlx4_find_zone_by_uid(
+		struct mlx4_zone_allocator *zones, u32 uid)
+{
+	struct mlx4_zone_entry *zone;
+
+	list_for_each_entry(zone, &zones->entries, list) {
+		if (zone->uid == uid)
+			return zone;
+	}
+
+	return NULL;
+}
+
+struct mlx4_bitmap *mlx4_zone_get_bitmap(struct mlx4_zone_allocator *zones, u32 uid)
+{
+	struct mlx4_zone_entry *zone;
+	struct mlx4_bitmap *bitmap;
+
+	spin_lock(&zones->lock);
+
+	zone = __mlx4_find_zone_by_uid(zones, uid);
+
+	bitmap = zone == NULL ? NULL : zone->bitmap;
+
+	spin_unlock(&zones->lock);
+
+	return bitmap;
+}
+
+int mlx4_zone_remove_one(struct mlx4_zone_allocator *zones, u32 uid)
+{
+	struct mlx4_zone_entry *zone;
+	int res;
+
+	spin_lock(&zones->lock);
+
+	zone = __mlx4_find_zone_by_uid(zones, uid);
+
+	if (NULL == zone) {
+		res = -1;
+		goto out;
+	}
+
+	res = __mlx4_zone_remove_one_entry(zone);
+
+out:
+	spin_unlock(&zones->lock);
+	kfree(zone);
+
+	return res;
+}
+
+/* Should be called under a lock */
+static struct mlx4_zone_entry *__mlx4_find_zone_by_uid_unique(
+		struct mlx4_zone_allocator *zones, u32 obj)
+{
+	struct mlx4_zone_entry *zone, *zone_candidate = NULL;
+	u32 dist = (u32)-1;
+
+	/* Search for the smallest zone that this obj could be
+	 * allocated from. This is done in order to handle
+	 * situations when small bitmaps are allocated from bigger
+	 * bitmaps (and the allocated space is marked as reserved in
+	 * the bigger bitmap.
+	 */
+	list_for_each_entry(zone, &zones->entries, list) {
+		if (obj >= zone->offset) {
+			u32 mobj = (obj - zone->offset) & zones->mask;
+
+			if (mobj < zone->bitmap->max) {
+				u32 curr_dist = zone->bitmap->effective_len;
+
+				if (curr_dist < dist) {
+					dist = curr_dist;
+					zone_candidate = zone;
+				}
+			}
+		}
+	}
+
+	return zone_candidate;
+}
+
+u32 mlx4_zone_alloc_entries(struct mlx4_zone_allocator *zones, u32 uid, int count,
+			    int align, u32 skip_mask, u32 *puid)
+{
+	struct mlx4_zone_entry *zone;
+	int res = -1;
+
+	spin_lock(&zones->lock);
+
+	zone = __mlx4_find_zone_by_uid(zones, uid);
+
+	if (NULL == zone)
+		goto out;
+
+	res = __mlx4_alloc_from_zone(zone, count, align, skip_mask, puid);
+
+out:
+	spin_unlock(&zones->lock);
+
+	return res;
+}
+
+u32 mlx4_zone_free_entries(struct mlx4_zone_allocator *zones, u32 uid, u32 obj, u32 count)
+{
+	struct mlx4_zone_entry *zone;
+	int res = 0;
+
+	spin_lock(&zones->lock);
+
+	zone = __mlx4_find_zone_by_uid(zones, uid);
+
+	if (NULL == zone) {
+		res = -1;
+		goto out;
+	}
+
+	__mlx4_free_from_zone(zone, obj, count);
+
+out:
+	spin_unlock(&zones->lock);
+
+	return res;
+}
+
+u32 mlx4_zone_free_entries_unique(struct mlx4_zone_allocator *zones, u32 obj, u32 count)
+{
+	struct mlx4_zone_entry *zone;
+	int res;
+
+	if (!(zones->flags & MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP))
+		return -EFAULT;
+
+	spin_lock(&zones->lock);
+
+	zone = __mlx4_find_zone_by_uid_unique(zones, obj);
+
+	if (NULL == zone) {
+		res = -1;
+		goto out;
+	}
+
+	__mlx4_free_from_zone(zone, obj, count);
+	res = 0;
+
+out:
+	spin_unlock(&zones->lock);
+
+	return res;
+}
 /*
  * Handling for queue buffers -- we allocate a bunch of memory and
  * register it in a memory region at HCA virtual address 0.  If the

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.c

@@ -144,7 +144,8 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags)
 		[15] = "Ethernet Backplane autoneg support",
 		[16] = "CONFIG DEV support",
 		[17] = "Asymmetric EQs support",
-		[18] = "More than 80 VFs support"
+		[18] = "More than 80 VFs support",
+		[19] = "Performance optimized for limited rule configuration flow steering support"
 	};
 	int i;
 
@@ -266,10 +267,16 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 #define QUERY_FUNC_CAP_MTT_QUOTA_OFFSET		0x64
 #define QUERY_FUNC_CAP_MCG_QUOTA_OFFSET		0x68
 
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET	0x6c
+
 #define QUERY_FUNC_CAP_FMR_FLAG			0x80
 #define QUERY_FUNC_CAP_FLAG_RDMA		0x40
 #define QUERY_FUNC_CAP_FLAG_ETH			0x80
 #define QUERY_FUNC_CAP_FLAG_QUOTAS		0x10
+#define QUERY_FUNC_CAP_FLAG_VALID_MAILBOX	0x04
+
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG	(1UL << 31)
+#define QUERY_FUNC_CAP_EXTRA_FLAGS_A0_QP_ALLOC_FLAG	(1UL << 30)
 
 /* when opcode modifier = 1 */
 #define QUERY_FUNC_CAP_PHYS_PORT_OFFSET		0x3
@@ -339,7 +346,7 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 			mlx4_get_active_ports(dev, slave);
 		/* enable rdma and ethernet interfaces, and new quota locations */
 		field = (QUERY_FUNC_CAP_FLAG_ETH | QUERY_FUNC_CAP_FLAG_RDMA |
-			 QUERY_FUNC_CAP_FLAG_QUOTAS);
+			 QUERY_FUNC_CAP_FLAG_QUOTAS | QUERY_FUNC_CAP_FLAG_VALID_MAILBOX);
 		MLX4_PUT(outbox->buf, field, QUERY_FUNC_CAP_FLAGS_OFFSET);
 
 		field = min(
@@ -401,6 +408,9 @@ int mlx4_QUERY_FUNC_CAP_wrapper(struct mlx4_dev *dev, int slave,
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET);
 		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_MCG_QUOTA_OFFSET_DEP);
 
+		size = QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG |
+			QUERY_FUNC_CAP_EXTRA_FLAGS_A0_QP_ALLOC_FLAG;
+		MLX4_PUT(outbox->buf, size, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
 	} else
 		err = -EINVAL;
 
@@ -493,6 +503,19 @@ int mlx4_QUERY_FUNC_CAP(struct mlx4_dev *dev, u8 gen_or_port,
 		MLX4_GET(size, outbox, QUERY_FUNC_CAP_RESERVED_EQ_OFFSET);
 		func_cap->reserved_eq = size & 0xFFFFFF;
 
+		func_cap->extra_flags = 0;
+
+		/* Mailbox data from 0x6c and onward should only be treated if
+		 * QUERY_FUNC_CAP_FLAG_VALID_MAILBOX is set in func_cap->flags
+		 */
+		if (func_cap->flags & QUERY_FUNC_CAP_FLAG_VALID_MAILBOX) {
+			MLX4_GET(size, outbox, QUERY_FUNC_CAP_EXTRA_FLAGS_OFFSET);
+			if (size & QUERY_FUNC_CAP_EXTRA_FLAGS_BF_QP_ALLOC_FLAG)
+				func_cap->extra_flags |= MLX4_QUERY_FUNC_FLAGS_BF_RES_QP;
+			if (size & QUERY_FUNC_CAP_EXTRA_FLAGS_A0_QP_ALLOC_FLAG)
+				func_cap->extra_flags |= MLX4_QUERY_FUNC_FLAGS_A0_RES_QP;
+		}
+
 		goto out;
 	}
 
@@ -658,6 +681,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 #define QUERY_DEV_CAP_FW_REASSIGN_MAC		0x9d
 #define QUERY_DEV_CAP_VXLAN			0x9e
 #define QUERY_DEV_CAP_MAD_DEMUX_OFFSET		0xb0
+#define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET	0xa8
+#define QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET	0xac
 
 	dev_cap->flags2 = 0;
 	mailbox = mlx4_alloc_cmd_mailbox(dev);
@@ -854,6 +879,13 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	if (field32 & (1 << 0))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_MAD_DEMUX;
 
+	MLX4_GET(dev_cap->dmfs_high_rate_qpn_base, outbox,
+		 QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_BASE_OFFSET);
+	dev_cap->dmfs_high_rate_qpn_base &= MGM_QPN_MASK;
+	MLX4_GET(dev_cap->dmfs_high_rate_qpn_range, outbox,
+		 QUERY_DEV_CAP_DMFS_HIGH_RATE_QPN_RANGE_OFFSET);
+	dev_cap->dmfs_high_rate_qpn_range &= MGM_QPN_MASK;
+
 	MLX4_GET(field32, outbox, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
 	if (field32 & (1 << 16))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_UPDATE_QP;
@@ -864,61 +896,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	if (field32 & (1 << 21))
 		dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_80_VFS;
 
-	if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
-		for (i = 1; i <= dev_cap->num_ports; ++i) {
-			MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
-			dev_cap->max_vl[i]	   = field >> 4;
-			MLX4_GET(field, outbox, QUERY_DEV_CAP_MTU_WIDTH_OFFSET);
-			dev_cap->ib_mtu[i]	   = field >> 4;
-			dev_cap->max_port_width[i] = field & 0xf;
-			MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_GID_OFFSET);
-			dev_cap->max_gids[i]	   = 1 << (field & 0xf);
-			MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PKEY_OFFSET);
-			dev_cap->max_pkeys[i]	   = 1 << (field & 0xf);
-		}
-	} else {
-#define QUERY_PORT_SUPPORTED_TYPE_OFFSET	0x00
-#define QUERY_PORT_MTU_OFFSET			0x01
-#define QUERY_PORT_ETH_MTU_OFFSET		0x02
-#define QUERY_PORT_WIDTH_OFFSET			0x06
-#define QUERY_PORT_MAX_GID_PKEY_OFFSET		0x07
-#define QUERY_PORT_MAX_MACVLAN_OFFSET		0x0a
-#define QUERY_PORT_MAX_VL_OFFSET		0x0b
-#define QUERY_PORT_MAC_OFFSET			0x10
-#define QUERY_PORT_TRANS_VENDOR_OFFSET		0x18
-#define QUERY_PORT_WAVELENGTH_OFFSET		0x1c
-#define QUERY_PORT_TRANS_CODE_OFFSET		0x20
-
-		for (i = 1; i <= dev_cap->num_ports; ++i) {
-			err = mlx4_cmd_box(dev, 0, mailbox->dma, i, 0, MLX4_CMD_QUERY_PORT,
-					   MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
-			if (err)
-				goto out;
-
-			MLX4_GET(field, outbox, QUERY_PORT_SUPPORTED_TYPE_OFFSET);
-			dev_cap->supported_port_types[i] = field & 3;
-			dev_cap->suggested_type[i] = (field >> 3) & 1;
-			dev_cap->default_sense[i] = (field >> 4) & 1;
-			MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
-			dev_cap->ib_mtu[i]	   = field & 0xf;
-			MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
-			dev_cap->max_port_width[i] = field & 0xf;
-			MLX4_GET(field, outbox, QUERY_PORT_MAX_GID_PKEY_OFFSET);
-			dev_cap->max_gids[i]	   = 1 << (field >> 4);
-			dev_cap->max_pkeys[i]	   = 1 << (field & 0xf);
-			MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
-			dev_cap->max_vl[i]	   = field & 0xf;
-			MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
-			dev_cap->log_max_macs[i]  = field & 0xf;
-			dev_cap->log_max_vlans[i] = field >> 4;
-			MLX4_GET(dev_cap->eth_mtu[i], outbox, QUERY_PORT_ETH_MTU_OFFSET);
-			MLX4_GET(dev_cap->def_mac[i], outbox, QUERY_PORT_MAC_OFFSET);
-			MLX4_GET(field32, outbox, QUERY_PORT_TRANS_VENDOR_OFFSET);
-			dev_cap->trans_type[i] = field32 >> 24;
-			dev_cap->vendor_oui[i] = field32 & 0xffffff;
-			MLX4_GET(dev_cap->wavelength[i], outbox, QUERY_PORT_WAVELENGTH_OFFSET);
-			MLX4_GET(dev_cap->trans_code[i], outbox, QUERY_PORT_TRANS_CODE_OFFSET);
-		}
+	for (i = 1; i <= dev_cap->num_ports; i++) {
+		err = mlx4_QUERY_PORT(dev, i, dev_cap->port_cap + i);
+		if (err)
+			goto out;
 	}
 
 	mlx4_dbg(dev, "Base MM extensions: flags %08x, rsvd L_Key %08x\n",
@@ -955,8 +936,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	mlx4_dbg(dev, "Max CQEs: %d, max WQEs: %d, max SRQ WQEs: %d\n",
 		 dev_cap->max_cq_sz, dev_cap->max_qp_sz, dev_cap->max_srq_sz);
 	mlx4_dbg(dev, "Local CA ACK delay: %d, max MTU: %d, port width cap: %d\n",
-		 dev_cap->local_ca_ack_delay, 128 << dev_cap->ib_mtu[1],
-		 dev_cap->max_port_width[1]);
+		 dev_cap->local_ca_ack_delay, 128 << dev_cap->port_cap[1].ib_mtu,
+		 dev_cap->port_cap[1].max_port_width);
 	mlx4_dbg(dev, "Max SQ desc size: %d, max SQ S/G: %d\n",
 		 dev_cap->max_sq_desc_sz, dev_cap->max_sq_sg);
 	mlx4_dbg(dev, "Max RQ desc size: %d, max RQ S/G: %d\n",
@@ -964,6 +945,10 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	mlx4_dbg(dev, "Max GSO size: %d\n", dev_cap->max_gso_sz);
 	mlx4_dbg(dev, "Max counters: %d\n", dev_cap->max_counters);
 	mlx4_dbg(dev, "Max RSS Table size: %d\n", dev_cap->max_rss_tbl_sz);
+	mlx4_dbg(dev, "DMFS high rate steer QPn base: %d\n",
+		 dev_cap->dmfs_high_rate_qpn_base);
+	mlx4_dbg(dev, "DMFS high rate steer QPn range: %d\n",
+		 dev_cap->dmfs_high_rate_qpn_range);
 
 	dump_dev_cap_flags(dev, dev_cap->flags);
 	dump_dev_cap_flags2(dev, dev_cap->flags2);
@@ -973,6 +958,89 @@ out:
 	return err;
 }
 
+int mlx4_QUERY_PORT(struct mlx4_dev *dev, int port, struct mlx4_port_cap *port_cap)
+{
+	struct mlx4_cmd_mailbox *mailbox;
+	u32 *outbox;
+	u8 field;
+	u32 field32;
+	int err;
+
+	mailbox = mlx4_alloc_cmd_mailbox(dev);
+	if (IS_ERR(mailbox))
+		return PTR_ERR(mailbox);
+	outbox = mailbox->buf;
+
+	if (dev->flags & MLX4_FLAG_OLD_PORT_CMDS) {
+		err = mlx4_cmd_box(dev, 0, mailbox->dma, 0, 0, MLX4_CMD_QUERY_DEV_CAP,
+				   MLX4_CMD_TIME_CLASS_A,
+				   MLX4_CMD_NATIVE);
+
+		if (err)
+			goto out;
+
+		MLX4_GET(field, outbox, QUERY_DEV_CAP_VL_PORT_OFFSET);
+		port_cap->max_vl	   = field >> 4;
+		MLX4_GET(field, outbox, QUERY_DEV_CAP_MTU_WIDTH_OFFSET);
+		port_cap->ib_mtu	   = field >> 4;
+		port_cap->max_port_width = field & 0xf;
+		MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_GID_OFFSET);
+		port_cap->max_gids	   = 1 << (field & 0xf);
+		MLX4_GET(field, outbox, QUERY_DEV_CAP_MAX_PKEY_OFFSET);
+		port_cap->max_pkeys	   = 1 << (field & 0xf);
+	} else {
+#define QUERY_PORT_SUPPORTED_TYPE_OFFSET	0x00
+#define QUERY_PORT_MTU_OFFSET			0x01
+#define QUERY_PORT_ETH_MTU_OFFSET		0x02
+#define QUERY_PORT_WIDTH_OFFSET			0x06
+#define QUERY_PORT_MAX_GID_PKEY_OFFSET		0x07
+#define QUERY_PORT_MAX_MACVLAN_OFFSET		0x0a
+#define QUERY_PORT_MAX_VL_OFFSET		0x0b
+#define QUERY_PORT_MAC_OFFSET			0x10
+#define QUERY_PORT_TRANS_VENDOR_OFFSET		0x18
+#define QUERY_PORT_WAVELENGTH_OFFSET		0x1c
+#define QUERY_PORT_TRANS_CODE_OFFSET		0x20
+
+		err = mlx4_cmd_box(dev, 0, mailbox->dma, port, 0, MLX4_CMD_QUERY_PORT,
+				   MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
+		if (err)
+			goto out;
+
+		MLX4_GET(field, outbox, QUERY_PORT_SUPPORTED_TYPE_OFFSET);
+		port_cap->supported_port_types = field & 3;
+		port_cap->suggested_type = (field >> 3) & 1;
+		port_cap->default_sense = (field >> 4) & 1;
+		port_cap->dmfs_optimized_state = (field >> 5) & 1;
+		MLX4_GET(field, outbox, QUERY_PORT_MTU_OFFSET);
+		port_cap->ib_mtu	   = field & 0xf;
+		MLX4_GET(field, outbox, QUERY_PORT_WIDTH_OFFSET);
+		port_cap->max_port_width = field & 0xf;
+		MLX4_GET(field, outbox, QUERY_PORT_MAX_GID_PKEY_OFFSET);
+		port_cap->max_gids	   = 1 << (field >> 4);
+		port_cap->max_pkeys	   = 1 << (field & 0xf);
+		MLX4_GET(field, outbox, QUERY_PORT_MAX_VL_OFFSET);
+		port_cap->max_vl	   = field & 0xf;
+		MLX4_GET(field, outbox, QUERY_PORT_MAX_MACVLAN_OFFSET);
+		port_cap->log_max_macs  = field & 0xf;
+		port_cap->log_max_vlans = field >> 4;
+		MLX4_GET(port_cap->eth_mtu, outbox, QUERY_PORT_ETH_MTU_OFFSET);
+		MLX4_GET(port_cap->def_mac, outbox, QUERY_PORT_MAC_OFFSET);
+		MLX4_GET(field32, outbox, QUERY_PORT_TRANS_VENDOR_OFFSET);
+		port_cap->trans_type = field32 >> 24;
+		port_cap->vendor_oui = field32 & 0xffffff;
+		MLX4_GET(port_cap->wavelength, outbox, QUERY_PORT_WAVELENGTH_OFFSET);
+		MLX4_GET(port_cap->trans_code, outbox, QUERY_PORT_TRANS_CODE_OFFSET);
+	}
+
+out:
+	mlx4_free_cmd_mailbox(dev, mailbox);
+	return err;
+}
+
+#define DEV_CAP_EXT_2_FLAG_VLAN_CONTROL (1 << 26)
+#define DEV_CAP_EXT_2_FLAG_80_VFS	(1 << 21)
+#define DEV_CAP_EXT_2_FLAG_FSM		(1 << 20)
+
 int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
 			       struct mlx4_vhcr *vhcr,
 			       struct mlx4_cmd_mailbox *inbox,
@@ -982,7 +1050,7 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
 	u64	flags;
 	int	err = 0;
 	u8	field;
-	u32	bmme_flags;
+	u32	bmme_flags, field32;
 	int	real_port;
 	int	slave_port;
 	int	first_port;
@@ -1053,6 +1121,12 @@ int mlx4_QUERY_DEV_CAP_wrapper(struct mlx4_dev *dev, int slave,
 	field &= ~0x80;
 	MLX4_PUT(outbox->buf, field, QUERY_DEV_CAP_FLOW_STEERING_IPOIB_OFFSET);
 
+	/* turn off host side virt features (VST, FSM, etc) for guests */
+	MLX4_GET(field32, outbox->buf, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
+	field32 &= ~(DEV_CAP_EXT_2_FLAG_VLAN_CONTROL | DEV_CAP_EXT_2_FLAG_80_VFS |
+		     DEV_CAP_EXT_2_FLAG_FSM);
+	MLX4_PUT(outbox->buf, field32, QUERY_DEV_CAP_EXT_2_FLAGS_OFFSET);
+
 	return 0;
 }
 
@@ -1471,6 +1545,12 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 	struct mlx4_cmd_mailbox *mailbox;
 	__be32 *inbox;
 	int err;
+	static const u8 a0_dmfs_hw_steering[] =  {
+		[MLX4_STEERING_DMFS_A0_DEFAULT]		= 0,
+		[MLX4_STEERING_DMFS_A0_DYNAMIC]		= 1,
+		[MLX4_STEERING_DMFS_A0_STATIC]		= 2,
+		[MLX4_STEERING_DMFS_A0_DISABLE]		= 3
+	};
 
 #define INIT_HCA_IN_SIZE		 0x200
 #define INIT_HCA_VERSION_OFFSET		 0x000
@@ -1504,6 +1584,7 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 #define  INIT_HCA_FS_PARAM_OFFSET         0x1d0
 #define  INIT_HCA_FS_BASE_OFFSET          (INIT_HCA_FS_PARAM_OFFSET + 0x00)
 #define  INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET  (INIT_HCA_FS_PARAM_OFFSET + 0x12)
+#define  INIT_HCA_FS_A0_OFFSET		  (INIT_HCA_FS_PARAM_OFFSET + 0x18)
 #define  INIT_HCA_FS_LOG_TABLE_SZ_OFFSET  (INIT_HCA_FS_PARAM_OFFSET + 0x1b)
 #define  INIT_HCA_FS_ETH_BITS_OFFSET      (INIT_HCA_FS_PARAM_OFFSET + 0x21)
 #define  INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x22)
@@ -1614,8 +1695,11 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 		/* Enable Ethernet flow steering
 		 * with udp unicast and tcp unicast
 		 */
-		MLX4_PUT(inbox, (u8) (MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN),
-			 INIT_HCA_FS_ETH_BITS_OFFSET);
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_STATIC)
+			MLX4_PUT(inbox,
+				 (u8)(MLX4_FS_UDP_UC_EN | MLX4_FS_TCP_UC_EN),
+				 INIT_HCA_FS_ETH_BITS_OFFSET);
 		MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
 			 INIT_HCA_FS_ETH_NUM_ADDRS_OFFSET);
 		/* Enable IPoIB flow steering
@@ -1625,6 +1709,13 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param)
 			 INIT_HCA_FS_IB_BITS_OFFSET);
 		MLX4_PUT(inbox, (u16) MLX4_FS_NUM_OF_L2_ADDR,
 			 INIT_HCA_FS_IB_NUM_ADDRS_OFFSET);
+
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+			MLX4_PUT(inbox,
+				 ((u8)(a0_dmfs_hw_steering[dev->caps.dmfs_high_steer_mode]
+				       << 6)),
+				 INIT_HCA_FS_A0_OFFSET);
 	} else {
 		MLX4_PUT(inbox, param->mc_base,	INIT_HCA_MC_BASE_OFFSET);
 		MLX4_PUT(inbox, param->log_mc_entry_sz,
@@ -1675,6 +1766,12 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 	u32 dword_field;
 	int err;
 	u8 byte_field;
+	static const u8 a0_dmfs_query_hw_steering[] =  {
+		[0] = MLX4_STEERING_DMFS_A0_DEFAULT,
+		[1] = MLX4_STEERING_DMFS_A0_DYNAMIC,
+		[2] = MLX4_STEERING_DMFS_A0_STATIC,
+		[3] = MLX4_STEERING_DMFS_A0_DISABLE
+	};
 
 #define QUERY_HCA_GLOBAL_CAPS_OFFSET	0x04
 #define QUERY_HCA_CORE_CLOCK_OFFSET	0x0c
@@ -1727,6 +1824,10 @@ int mlx4_QUERY_HCA(struct mlx4_dev *dev,
 			 INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET);
 		MLX4_GET(param->log_mc_table_sz, outbox,
 			 INIT_HCA_FS_LOG_TABLE_SZ_OFFSET);
+		MLX4_GET(byte_field, outbox,
+			 INIT_HCA_FS_A0_OFFSET);
+		param->dmfs_high_steer_mode =
+			a0_dmfs_query_hw_steering[(byte_field >> 6) & 3];
 	} else {
 		MLX4_GET(param->mc_base, outbox, INIT_HCA_MC_BASE_OFFSET);
 		MLX4_GET(param->log_mc_entry_sz, outbox,

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/main.c

@@ -105,7 +105,8 @@ MODULE_PARM_DESC(enable_64b_cqe_eqe,
 		 "Enable 64 byte CQEs/EQEs when the FW supports this (default: True)");
 
 #define PF_CONTEXT_BEHAVIOUR_MASK	(MLX4_FUNC_CAP_64B_EQE_CQE | \
-					 MLX4_FUNC_CAP_EQE_CQE_STRIDE)
+					 MLX4_FUNC_CAP_EQE_CQE_STRIDE | \
+					 MLX4_FUNC_CAP_DMFS_A0_STATIC)
 
 static char mlx4_version[] =
 	DRV_NAME ": Mellanox ConnectX core driver v"
@@ -254,6 +255,46 @@ static void mlx4_enable_cqe_eqe_stride(struct mlx4_dev *dev)
 	}
 }
 
+static int _mlx4_dev_port(struct mlx4_dev *dev, int port,
+			  struct mlx4_port_cap *port_cap)
+{
+	dev->caps.vl_cap[port]	    = port_cap->max_vl;
+	dev->caps.ib_mtu_cap[port]	    = port_cap->ib_mtu;
+	dev->phys_caps.gid_phys_table_len[port]  = port_cap->max_gids;
+	dev->phys_caps.pkey_phys_table_len[port] = port_cap->max_pkeys;
+	/* set gid and pkey table operating lengths by default
+	 * to non-sriov values
+	 */
+	dev->caps.gid_table_len[port]  = port_cap->max_gids;
+	dev->caps.pkey_table_len[port] = port_cap->max_pkeys;
+	dev->caps.port_width_cap[port] = port_cap->max_port_width;
+	dev->caps.eth_mtu_cap[port]    = port_cap->eth_mtu;
+	dev->caps.def_mac[port]        = port_cap->def_mac;
+	dev->caps.supported_type[port] = port_cap->supported_port_types;
+	dev->caps.suggested_type[port] = port_cap->suggested_type;
+	dev->caps.default_sense[port] = port_cap->default_sense;
+	dev->caps.trans_type[port]	    = port_cap->trans_type;
+	dev->caps.vendor_oui[port]     = port_cap->vendor_oui;
+	dev->caps.wavelength[port]     = port_cap->wavelength;
+	dev->caps.trans_code[port]     = port_cap->trans_code;
+
+	return 0;
+}
+
+static int mlx4_dev_port(struct mlx4_dev *dev, int port,
+			 struct mlx4_port_cap *port_cap)
+{
+	int err = 0;
+
+	err = mlx4_QUERY_PORT(dev, port, port_cap);
+
+	if (err)
+		mlx4_err(dev, "QUERY_PORT command failed.\n");
+
+	return err;
+}
+
+#define MLX4_A0_STEERING_TABLE_SIZE	256
 static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 {
 	int err;
@@ -289,24 +330,11 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 				      dev->caps.num_sys_eqs :
 				      MLX4_MAX_EQ_NUM;
 	for (i = 1; i <= dev->caps.num_ports; ++i) {
-		dev->caps.vl_cap[i]	    = dev_cap->max_vl[i];
-		dev->caps.ib_mtu_cap[i]	    = dev_cap->ib_mtu[i];
-		dev->phys_caps.gid_phys_table_len[i]  = dev_cap->max_gids[i];
-		dev->phys_caps.pkey_phys_table_len[i] = dev_cap->max_pkeys[i];
-		/* set gid and pkey table operating lengths by default
-		 * to non-sriov values */
-		dev->caps.gid_table_len[i]  = dev_cap->max_gids[i];
-		dev->caps.pkey_table_len[i] = dev_cap->max_pkeys[i];
-		dev->caps.port_width_cap[i] = dev_cap->max_port_width[i];
-		dev->caps.eth_mtu_cap[i]    = dev_cap->eth_mtu[i];
-		dev->caps.def_mac[i]        = dev_cap->def_mac[i];
-		dev->caps.supported_type[i] = dev_cap->supported_port_types[i];
-		dev->caps.suggested_type[i] = dev_cap->suggested_type[i];
-		dev->caps.default_sense[i] = dev_cap->default_sense[i];
-		dev->caps.trans_type[i]	    = dev_cap->trans_type[i];
-		dev->caps.vendor_oui[i]     = dev_cap->vendor_oui[i];
-		dev->caps.wavelength[i]     = dev_cap->wavelength[i];
-		dev->caps.trans_code[i]     = dev_cap->trans_code[i];
+		err = _mlx4_dev_port(dev, i, dev_cap->port_cap + i);
+		if (err) {
+			mlx4_err(dev, "QUERY_PORT command failed, aborting\n");
+			return err;
+		}
 	}
 
 	dev->caps.uar_page_size	     = PAGE_SIZE;
@@ -415,13 +443,13 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 			dev->caps.possible_type[i] = dev->caps.port_type[i];
 		}
 
-		if (dev->caps.log_num_macs > dev_cap->log_max_macs[i]) {
-			dev->caps.log_num_macs = dev_cap->log_max_macs[i];
+		if (dev->caps.log_num_macs > dev_cap->port_cap[i].log_max_macs) {
+			dev->caps.log_num_macs = dev_cap->port_cap[i].log_max_macs;
 			mlx4_warn(dev, "Requested number of MACs is too much for port %d, reducing to %d\n",
 				  i, 1 << dev->caps.log_num_macs);
 		}
-		if (dev->caps.log_num_vlans > dev_cap->log_max_vlans[i]) {
-			dev->caps.log_num_vlans = dev_cap->log_max_vlans[i];
+		if (dev->caps.log_num_vlans > dev_cap->port_cap[i].log_max_vlans) {
+			dev->caps.log_num_vlans = dev_cap->port_cap[i].log_max_vlans;
 			mlx4_warn(dev, "Requested number of VLANs is too much for port %d, reducing to %d\n",
 				  i, 1 << dev->caps.log_num_vlans);
 		}
@@ -437,6 +465,28 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 		dev->caps.num_ports;
 	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_EXCH] = MLX4_NUM_FEXCH;
 
+	if (dev_cap->dmfs_high_rate_qpn_base > 0 &&
+	    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN)
+		dev->caps.dmfs_high_rate_qpn_base = dev_cap->dmfs_high_rate_qpn_base;
+	else
+		dev->caps.dmfs_high_rate_qpn_base =
+			dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+
+	if (dev_cap->dmfs_high_rate_qpn_range > 0 &&
+	    dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_FS_EN) {
+		dev->caps.dmfs_high_rate_qpn_range = dev_cap->dmfs_high_rate_qpn_range;
+		dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DEFAULT;
+		dev->caps.flags2 |= MLX4_DEV_CAP_FLAG2_FS_A0;
+	} else {
+		dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_NOT_SUPPORTED;
+		dev->caps.dmfs_high_rate_qpn_base =
+			dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+		dev->caps.dmfs_high_rate_qpn_range = MLX4_A0_STEERING_TABLE_SIZE;
+	}
+
+	dev->caps.reserved_qps_cnt[MLX4_QP_REGION_RSS_RAW_ETH] =
+		dev->caps.dmfs_high_rate_qpn_range;
+
 	dev->caps.reserved_qps = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW] +
 		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_ETH_ADDR] +
 		dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FC_ADDR] +
@@ -466,8 +516,14 @@ static int mlx4_dev_cap(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap)
 	    mlx4_is_master(dev))
 		dev->caps.function_caps |= MLX4_FUNC_CAP_64B_EQE_CQE;
 
-	if (!mlx4_is_slave(dev))
+	if (!mlx4_is_slave(dev)) {
 		mlx4_enable_cqe_eqe_stride(dev);
+		dev->caps.alloc_res_qp_mask =
+			(dev->caps.bf_reg_size ? MLX4_RESERVE_ETH_BF_QP : 0) |
+			MLX4_RESERVE_A0_QP;
+	} else {
+		dev->caps.alloc_res_qp_mask = 0;
+	}
 
 	return 0;
 }
@@ -718,7 +774,8 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 
 	if ((func_cap.pf_context_behaviour | PF_CONTEXT_BEHAVIOUR_MASK) !=
 	    PF_CONTEXT_BEHAVIOUR_MASK) {
-		mlx4_err(dev, "Unknown pf context behaviour\n");
+		mlx4_err(dev, "Unknown pf context behaviour %x known flags %x\n",
+			 func_cap.pf_context_behaviour, PF_CONTEXT_BEHAVIOUR_MASK);
 		return -ENOSYS;
 	}
 
@@ -817,6 +874,13 @@ static int mlx4_slave_cap(struct mlx4_dev *dev)
 
 	slave_adjust_steering_mode(dev, &dev_cap, &hca_param);
 
+	if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_BF_RES_QP &&
+	    dev->caps.bf_reg_size)
+		dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_ETH_BF_QP;
+
+	if (func_cap.extra_flags & MLX4_QUERY_FUNC_FLAGS_A0_RES_QP)
+		dev->caps.alloc_res_qp_mask |= MLX4_RESERVE_A0_QP;
+
 	return 0;
 
 err_mem:
@@ -1598,10 +1662,46 @@ static int choose_log_fs_mgm_entry_size(int qp_per_entry)
 	return (i <= MLX4_MAX_MGM_LOG_ENTRY_SIZE) ? i : -1;
 }
 
+static const char *dmfs_high_rate_steering_mode_str(int dmfs_high_steer_mode)
+{
+	switch (dmfs_high_steer_mode) {
+	case MLX4_STEERING_DMFS_A0_DEFAULT:
+		return "default performance";
+
+	case MLX4_STEERING_DMFS_A0_DYNAMIC:
+		return "dynamic hybrid mode";
+
+	case MLX4_STEERING_DMFS_A0_STATIC:
+		return "performance optimized for limited rule configuration (static)";
+
+	case MLX4_STEERING_DMFS_A0_DISABLE:
+		return "disabled performance optimized steering";
+
+	case MLX4_STEERING_DMFS_A0_NOT_SUPPORTED:
+		return "performance optimized steering not supported";
+
+	default:
+		return "Unrecognized mode";
+	}
+}
+
+#define MLX4_DMFS_A0_STEERING			(1UL << 2)
+
 static void choose_steering_mode(struct mlx4_dev *dev,
 				 struct mlx4_dev_cap *dev_cap)
 {
-	if (mlx4_log_num_mgm_entry_size == -1 &&
+	if (mlx4_log_num_mgm_entry_size <= 0) {
+		if ((-mlx4_log_num_mgm_entry_size) & MLX4_DMFS_A0_STEERING) {
+			if (dev->caps.dmfs_high_steer_mode ==
+			    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+				mlx4_err(dev, "DMFS high rate mode not supported\n");
+			else
+				dev->caps.dmfs_high_steer_mode =
+					MLX4_STEERING_DMFS_A0_STATIC;
+		}
+	}
+
+	if (mlx4_log_num_mgm_entry_size <= 0 &&
 	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_FS_EN &&
 	    (!mlx4_is_mfunc(dev) ||
 	     (dev_cap->fs_max_num_qp_per_entry >= (dev->num_vfs + 1))) &&
@@ -1614,6 +1714,9 @@ static void choose_steering_mode(struct mlx4_dev *dev,
 		dev->caps.fs_log_max_ucast_qp_range_size =
 			dev_cap->fs_log_max_ucast_qp_range_size;
 	} else {
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+			dev->caps.dmfs_high_steer_mode = MLX4_STEERING_DMFS_A0_DISABLE;
 		if (dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_UC_STEER &&
 		    dev->caps.flags & MLX4_DEV_CAP_FLAG_VEP_MC_STEER)
 			dev->caps.steering_mode = MLX4_STEERING_MODE_B0;
@@ -1640,7 +1743,8 @@ static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
 				       struct mlx4_dev_cap *dev_cap)
 {
 	if (dev->caps.steering_mode == MLX4_STEERING_MODE_DEVICE_MANAGED &&
-	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS)
+	    dev_cap->flags2 & MLX4_DEV_CAP_FLAG2_VXLAN_OFFLOADS &&
+	    dev->caps.dmfs_high_steer_mode != MLX4_STEERING_DMFS_A0_STATIC)
 		dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_VXLAN;
 	else
 		dev->caps.tunnel_offload_mode = MLX4_TUNNEL_OFFLOAD_MODE_NONE;
@@ -1649,6 +1753,35 @@ static void choose_tunnel_offload_mode(struct mlx4_dev *dev,
 		 == MLX4_TUNNEL_OFFLOAD_MODE_VXLAN) ? "vxlan" : "none");
 }
 
+static int mlx4_validate_optimized_steering(struct mlx4_dev *dev)
+{
+	int i;
+	struct mlx4_port_cap port_cap;
+
+	if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_NOT_SUPPORTED)
+		return -EINVAL;
+
+	for (i = 1; i <= dev->caps.num_ports; i++) {
+		if (mlx4_dev_port(dev, i, &port_cap)) {
+			mlx4_err(dev,
+				 "QUERY_DEV_CAP command failed, can't veify DMFS high rate steering.\n");
+		} else if ((dev->caps.dmfs_high_steer_mode !=
+			    MLX4_STEERING_DMFS_A0_DEFAULT) &&
+			   (port_cap.dmfs_optimized_state ==
+			    !!(dev->caps.dmfs_high_steer_mode ==
+			    MLX4_STEERING_DMFS_A0_DISABLE))) {
+			mlx4_err(dev,
+				 "DMFS high rate steer mode differ, driver requested %s but %s in FW.\n",
+				 dmfs_high_rate_steering_mode_str(
+					dev->caps.dmfs_high_steer_mode),
+				 (port_cap.dmfs_optimized_state ?
+					"enabled" : "disabled"));
+		}
+	}
+
+	return 0;
+}
+
 static int mlx4_init_fw(struct mlx4_dev *dev)
 {
 	struct mlx4_mod_stat_cfg   mlx4_cfg;
@@ -1701,6 +1834,10 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 		choose_steering_mode(dev, &dev_cap);
 		choose_tunnel_offload_mode(dev, &dev_cap);
 
+		if (dev->caps.dmfs_high_steer_mode == MLX4_STEERING_DMFS_A0_STATIC &&
+		    mlx4_is_master(dev))
+			dev->caps.function_caps |= MLX4_FUNC_CAP_DMFS_A0_STATIC;
+
 		err = mlx4_get_phys_port_id(dev);
 		if (err)
 			mlx4_err(dev, "Fail to get physical port id\n");
@@ -1787,6 +1924,24 @@ static int mlx4_init_hca(struct mlx4_dev *dev)
 				mlx4_err(dev, "Failed to map internal clock. Timestamping is not supported\n");
 			}
 		}
+
+		if (dev->caps.dmfs_high_steer_mode !=
+		    MLX4_STEERING_DMFS_A0_NOT_SUPPORTED) {
+			if (mlx4_validate_optimized_steering(dev))
+				mlx4_warn(dev, "Optimized steering validation failed\n");
+
+			if (dev->caps.dmfs_high_steer_mode ==
+			    MLX4_STEERING_DMFS_A0_DISABLE) {
+				dev->caps.dmfs_high_rate_qpn_base =
+					dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+				dev->caps.dmfs_high_rate_qpn_range =
+					MLX4_A0_STEERING_TABLE_SIZE;
+			}
+
+			mlx4_dbg(dev, "DMFS high rate steer mode is: %s\n",
+				 dmfs_high_rate_steering_mode_str(
+					dev->caps.dmfs_high_steer_mode));
+		}
 	} else {
 		err = mlx4_init_slave(dev);
 		if (err) {
@@ -3159,10 +3314,11 @@ static int __init mlx4_verify_params(void)
 		port_type_array[0] = true;
 	}
 
-	if (mlx4_log_num_mgm_entry_size != -1 &&
-	    (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
-	     mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE)) {
-		pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-1 or %d..%d)\n",
+	if (mlx4_log_num_mgm_entry_size < -7 ||
+	    (mlx4_log_num_mgm_entry_size > 0 &&
+	     (mlx4_log_num_mgm_entry_size < MLX4_MIN_MGM_LOG_ENTRY_SIZE ||
+	      mlx4_log_num_mgm_entry_size > MLX4_MAX_MGM_LOG_ENTRY_SIZE))) {
+		pr_warn("mlx4_core: mlx4_log_num_mgm_entry_size (%d) not in legal range (-7..0 or %d..%d)\n",
 			mlx4_log_num_mgm_entry_size,
 			MLX4_MIN_MGM_LOG_ENTRY_SIZE,
 			MLX4_MAX_MGM_LOG_ENTRY_SIZE);

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/qp.c

@@ -42,6 +42,10 @@
 #include "mlx4.h"
 #include "icm.h"
 
+/* QP to support BF should have bits 6,7 cleared */
+#define MLX4_BF_QP_SKIP_MASK	0xc0
+#define MLX4_MAX_BF_QP_RANGE	0x40
+
 void mlx4_qp_event(struct mlx4_dev *dev, u32 qpn, int event_type)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
@@ -207,26 +211,45 @@ int mlx4_qp_modify(struct mlx4_dev *dev, struct mlx4_mtt *mtt,
 EXPORT_SYMBOL_GPL(mlx4_qp_modify);
 
 int __mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align,
-				   int *base)
+			    int *base, u8 flags)
 {
+	u32 uid;
+	int bf_qp = !!(flags & (u8)MLX4_RESERVE_ETH_BF_QP);
+
 	struct mlx4_priv *priv = mlx4_priv(dev);
 	struct mlx4_qp_table *qp_table = &priv->qp_table;
 
-	*base = mlx4_bitmap_alloc_range(&qp_table->bitmap, cnt, align);
+	if (cnt > MLX4_MAX_BF_QP_RANGE && bf_qp)
+		return -ENOMEM;
+
+	uid = MLX4_QP_TABLE_ZONE_GENERAL;
+	if (flags & (u8)MLX4_RESERVE_A0_QP) {
+		if (bf_qp)
+			uid = MLX4_QP_TABLE_ZONE_RAW_ETH;
+		else
+			uid = MLX4_QP_TABLE_ZONE_RSS;
+	}
+
+	*base = mlx4_zone_alloc_entries(qp_table->zones, uid, cnt, align,
+					bf_qp ? MLX4_BF_QP_SKIP_MASK : 0, NULL);
 	if (*base == -1)
 		return -ENOMEM;
 
 	return 0;
 }
 
-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)
 {
 	u64 in_param = 0;
 	u64 out_param;
 	int err;
 
+	/* Turn off all unsupported QP allocation flags */
+	flags &= dev->caps.alloc_res_qp_mask;
+
 	if (mlx4_is_mfunc(dev)) {
-		set_param_l(&in_param, cnt);
+		set_param_l(&in_param, (((u32)flags) << 24) | (u32)cnt);
 		set_param_h(&in_param, align);
 		err = mlx4_cmd_imm(dev, in_param, &out_param,
 				   RES_QP, RES_OP_RESERVE,
@@ -238,7 +261,7 @@ int mlx4_qp_reserve_range(struct mlx4_dev *dev, int cnt, int align, int *base)
 		*base = get_param_l(&out_param);
 		return 0;
 	}
-	return __mlx4_qp_reserve_range(dev, cnt, align, base);
+	return __mlx4_qp_reserve_range(dev, cnt, align, base, flags);
 }
 EXPORT_SYMBOL_GPL(mlx4_qp_reserve_range);
 
@@ -249,7 +272,7 @@ void __mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
 
 	if (mlx4_is_qp_reserved(dev, (u32) base_qpn))
 		return;
-	mlx4_bitmap_free_range(&qp_table->bitmap, base_qpn, cnt, MLX4_USE_RR);
+	mlx4_zone_free_entries_unique(qp_table->zones, base_qpn, cnt);
 }
 
 void mlx4_qp_release_range(struct mlx4_dev *dev, int base_qpn, int cnt)
@@ -459,28 +482,261 @@ static int mlx4_CONF_SPECIAL_QP(struct mlx4_dev *dev, u32 base_qpn)
 			MLX4_CMD_TIME_CLASS_B, MLX4_CMD_NATIVE);
 }
 
+#define MLX4_QP_TABLE_RSS_ETH_PRIORITY 2
+#define MLX4_QP_TABLE_RAW_ETH_PRIORITY 1
+#define MLX4_QP_TABLE_RAW_ETH_SIZE     256
+
+static int mlx4_create_zones(struct mlx4_dev *dev,
+			     u32 reserved_bottom_general,
+			     u32 reserved_top_general,
+			     u32 reserved_bottom_rss,
+			     u32 start_offset_rss,
+			     u32 max_table_offset)
+{
+	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
+	struct mlx4_bitmap (*bitmap)[MLX4_QP_TABLE_ZONE_NUM] = NULL;
+	int bitmap_initialized = 0;
+	u32 last_offset;
+	int k;
+	int err;
+
+	qp_table->zones = mlx4_zone_allocator_create(MLX4_ZONE_ALLOC_FLAGS_NO_OVERLAP);
+
+	if (NULL == qp_table->zones)
+		return -ENOMEM;
+
+	bitmap = kmalloc(sizeof(*bitmap), GFP_KERNEL);
+
+	if (NULL == bitmap) {
+		err = -ENOMEM;
+		goto free_zone;
+	}
+
+	err = mlx4_bitmap_init(*bitmap + MLX4_QP_TABLE_ZONE_GENERAL, dev->caps.num_qps,
+			       (1 << 23) - 1, reserved_bottom_general,
+			       reserved_top_general);
+
+	if (err)
+		goto free_bitmap;
+
+	++bitmap_initialized;
+
+	err = mlx4_zone_add_one(qp_table->zones, *bitmap + MLX4_QP_TABLE_ZONE_GENERAL,
+				MLX4_ZONE_FALLBACK_TO_HIGHER_PRIO |
+				MLX4_ZONE_USE_RR, 0,
+				0, qp_table->zones_uids + MLX4_QP_TABLE_ZONE_GENERAL);
+
+	if (err)
+		goto free_bitmap;
+
+	err = mlx4_bitmap_init(*bitmap + MLX4_QP_TABLE_ZONE_RSS,
+			       reserved_bottom_rss,
+			       reserved_bottom_rss - 1,
+			       dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW],
+			       reserved_bottom_rss - start_offset_rss);
+
+	if (err)
+		goto free_bitmap;
+
+	++bitmap_initialized;
+
+	err = mlx4_zone_add_one(qp_table->zones, *bitmap + MLX4_QP_TABLE_ZONE_RSS,
+				MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO |
+				MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO |
+				MLX4_ZONE_USE_RR, MLX4_QP_TABLE_RSS_ETH_PRIORITY,
+				0, qp_table->zones_uids + MLX4_QP_TABLE_ZONE_RSS);
+
+	if (err)
+		goto free_bitmap;
+
+	last_offset = dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW];
+	/*  We have a single zone for the A0 steering QPs area of the FW. This area
+	 *  needs to be split into subareas. One set of subareas is for RSS QPs
+	 *  (in which qp number bits 6 and/or 7 are set); the other set of subareas
+	 *  is for RAW_ETH QPs, which require that both bits 6 and 7 are zero.
+	 *  Currently, the values returned by the FW (A0 steering area starting qp number
+	 *  and A0 steering area size) are such that there are only two subareas -- one
+	 *  for RSS and one for RAW_ETH.
+	 */
+	for (k = MLX4_QP_TABLE_ZONE_RSS + 1; k < sizeof(*bitmap)/sizeof((*bitmap)[0]);
+	     k++) {
+		int size;
+		u32 offset = start_offset_rss;
+		u32 bf_mask;
+		u32 requested_size;
+
+		/* Assuming MLX4_BF_QP_SKIP_MASK is consecutive ones, this calculates
+		 * a mask of all LSB bits set until (and not including) the first
+		 * set bit of  MLX4_BF_QP_SKIP_MASK. For example, if MLX4_BF_QP_SKIP_MASK
+		 * is 0xc0, bf_mask will be 0x3f.
+		 */
+		bf_mask = (MLX4_BF_QP_SKIP_MASK & ~(MLX4_BF_QP_SKIP_MASK - 1)) - 1;
+		requested_size = min((u32)MLX4_QP_TABLE_RAW_ETH_SIZE, bf_mask + 1);
+
+		if (((last_offset & MLX4_BF_QP_SKIP_MASK) &&
+		     ((int)(max_table_offset - last_offset)) >=
+		     roundup_pow_of_two(MLX4_BF_QP_SKIP_MASK)) ||
+		    (!(last_offset & MLX4_BF_QP_SKIP_MASK) &&
+		     !((last_offset + requested_size - 1) &
+		       MLX4_BF_QP_SKIP_MASK)))
+			size = requested_size;
+		else {
+			u32 candidate_offset =
+				(last_offset | MLX4_BF_QP_SKIP_MASK | bf_mask) + 1;
+
+			if (last_offset & MLX4_BF_QP_SKIP_MASK)
+				last_offset = candidate_offset;
+
+			/* From this point, the BF bits are 0 */
+
+			if (last_offset > max_table_offset) {
+				/* need to skip */
+				size = -1;
+			} else {
+				size = min3(max_table_offset - last_offset,
+					    bf_mask - (last_offset & bf_mask),
+					    requested_size);
+				if (size < requested_size) {
+					int candidate_size;
+
+					candidate_size = min3(
+						max_table_offset - candidate_offset,
+						bf_mask - (last_offset & bf_mask),
+						requested_size);
+
+					/*  We will not take this path if last_offset was
+					 *  already set above to candidate_offset
+					 */
+					if (candidate_size > size) {
+						last_offset = candidate_offset;
+						size = candidate_size;
+					}
+				}
+			}
+		}
+
+		if (size > 0) {
+			/* mlx4_bitmap_alloc_range will find a contiguous range of "size"
+			 * QPs in which both bits 6 and 7 are zero, because we pass it the
+			 * MLX4_BF_SKIP_MASK).
+			 */
+			offset = mlx4_bitmap_alloc_range(
+					*bitmap + MLX4_QP_TABLE_ZONE_RSS,
+					size, 1,
+					MLX4_BF_QP_SKIP_MASK);
+
+			if (offset == (u32)-1) {
+				err = -ENOMEM;
+				break;
+			}
+
+			last_offset = offset + size;
+
+			err = mlx4_bitmap_init(*bitmap + k, roundup_pow_of_two(size),
+					       roundup_pow_of_two(size) - 1, 0,
+					       roundup_pow_of_two(size) - size);
+		} else {
+			/* Add an empty bitmap, we'll allocate from different zones (since
+			 * at least one is reserved)
+			 */
+			err = mlx4_bitmap_init(*bitmap + k, 1,
+					       MLX4_QP_TABLE_RAW_ETH_SIZE - 1, 0,
+					       0);
+			mlx4_bitmap_alloc_range(*bitmap + k, 1, 1, 0);
+		}
+
+		if (err)
+			break;
+
+		++bitmap_initialized;
+
+		err = mlx4_zone_add_one(qp_table->zones, *bitmap + k,
+					MLX4_ZONE_ALLOW_ALLOC_FROM_LOWER_PRIO |
+					MLX4_ZONE_ALLOW_ALLOC_FROM_EQ_PRIO |
+					MLX4_ZONE_USE_RR, MLX4_QP_TABLE_RAW_ETH_PRIORITY,
+					offset, qp_table->zones_uids + k);
+
+		if (err)
+			break;
+	}
+
+	if (err)
+		goto free_bitmap;
+
+	qp_table->bitmap_gen = *bitmap;
+
+	return err;
+
+free_bitmap:
+	for (k = 0; k < bitmap_initialized; k++)
+		mlx4_bitmap_cleanup(*bitmap + k);
+	kfree(bitmap);
+free_zone:
+	mlx4_zone_allocator_destroy(qp_table->zones);
+	return err;
+}
+
+static void mlx4_cleanup_qp_zones(struct mlx4_dev *dev)
+{
+	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
+
+	if (qp_table->zones) {
+		int i;
+
+		for (i = 0;
+		     i < sizeof(qp_table->zones_uids)/sizeof(qp_table->zones_uids[0]);
+		     i++) {
+			struct mlx4_bitmap *bitmap =
+				mlx4_zone_get_bitmap(qp_table->zones,
+						     qp_table->zones_uids[i]);
+
+			mlx4_zone_remove_one(qp_table->zones, qp_table->zones_uids[i]);
+			if (NULL == bitmap)
+				continue;
+
+			mlx4_bitmap_cleanup(bitmap);
+		}
+		mlx4_zone_allocator_destroy(qp_table->zones);
+		kfree(qp_table->bitmap_gen);
+		qp_table->bitmap_gen = NULL;
+		qp_table->zones = NULL;
+	}
+}
+
 int mlx4_init_qp_table(struct mlx4_dev *dev)
 {
 	struct mlx4_qp_table *qp_table = &mlx4_priv(dev)->qp_table;
 	int err;
 	int reserved_from_top = 0;
+	int reserved_from_bot;
 	int k;
+	int fixed_reserved_from_bot_rv = 0;
+	int bottom_reserved_for_rss_bitmap;
+	u32 max_table_offset = dev->caps.dmfs_high_rate_qpn_base +
+			dev->caps.dmfs_high_rate_qpn_range;
 
 	spin_lock_init(&qp_table->lock);
 	INIT_RADIX_TREE(&dev->qp_table_tree, GFP_ATOMIC);
 	if (mlx4_is_slave(dev))
 		return 0;
 
-	/*
-	 * We reserve 2 extra QPs per port for the special QPs.  The
+	/* We reserve 2 extra QPs per port for the special QPs.  The
 	 * block of special QPs must be aligned to a multiple of 8, so
 	 * round up.
 	 *
 	 * We also reserve the MSB of the 24-bit QP number to indicate
 	 * that a QP is an XRC QP.
 	 */
-	dev->phys_caps.base_sqpn =
-		ALIGN(dev->caps.reserved_qps_cnt[MLX4_QP_REGION_FW], 8);
+	for (k = 0; k <= MLX4_QP_REGION_BOTTOM; k++)
+		fixed_reserved_from_bot_rv += dev->caps.reserved_qps_cnt[k];
+
+	if (fixed_reserved_from_bot_rv < max_table_offset)
+		fixed_reserved_from_bot_rv = max_table_offset;
+
+	/* We reserve at least 1 extra for bitmaps that we don't have enough space for*/
+	bottom_reserved_for_rss_bitmap =
+		roundup_pow_of_two(fixed_reserved_from_bot_rv + 1);
+	dev->phys_caps.base_sqpn = ALIGN(bottom_reserved_for_rss_bitmap, 8);
 
 	{
 		int sort[MLX4_NUM_QP_REGION];
@@ -490,8 +746,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 		for (i = 1; i < MLX4_NUM_QP_REGION; ++i)
 			sort[i] = i;
 
-		for (i = MLX4_NUM_QP_REGION; i > 0; --i) {
-			for (j = 2; j < i; ++j) {
+		for (i = MLX4_NUM_QP_REGION; i > MLX4_QP_REGION_BOTTOM; --i) {
+			for (j = MLX4_QP_REGION_BOTTOM + 2; j < i; ++j) {
 				if (dev->caps.reserved_qps_cnt[sort[j]] >
 				    dev->caps.reserved_qps_cnt[sort[j - 1]]) {
 					tmp             = sort[j];
@@ -501,13 +757,12 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 			}
 		}
 
-		for (i = 1; i < MLX4_NUM_QP_REGION; ++i) {
+		for (i = MLX4_QP_REGION_BOTTOM + 1; i < MLX4_NUM_QP_REGION; ++i) {
 			last_base -= dev->caps.reserved_qps_cnt[sort[i]];
 			dev->caps.reserved_qps_base[sort[i]] = last_base;
 			reserved_from_top +=
 				dev->caps.reserved_qps_cnt[sort[i]];
 		}
-
 	}
 
        /* Reserve 8 real SQPs in both native and SRIOV modes.
@@ -520,10 +775,17 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	* b. All the proxy SQPs (8 per function)
 	* c. All the tunnel QPs (8 per function)
 	*/
+	reserved_from_bot = mlx4_num_reserved_sqps(dev);
+	if (reserved_from_bot + reserved_from_top > dev->caps.num_qps) {
+		mlx4_err(dev, "Number of reserved QPs is higher than number of QPs\n");
+		return -EINVAL;
+	}
+
+	err = mlx4_create_zones(dev, reserved_from_bot, reserved_from_bot,
+				bottom_reserved_for_rss_bitmap,
+				fixed_reserved_from_bot_rv,
+				max_table_offset);
 
-	err = mlx4_bitmap_init(&qp_table->bitmap, dev->caps.num_qps,
-			       (1 << 23) - 1, mlx4_num_reserved_sqps(dev),
-			       reserved_from_top);
 	if (err)
 		return err;
 
@@ -559,7 +821,8 @@ int mlx4_init_qp_table(struct mlx4_dev *dev)
 	err = mlx4_CONF_SPECIAL_QP(dev, dev->phys_caps.base_sqpn);
 	if (err)
 		goto err_mem;
-	return 0;
+
+	return err;
 
 err_mem:
 	kfree(dev->caps.qp0_tunnel);
@@ -568,6 +831,7 @@ err_mem:
 	kfree(dev->caps.qp1_proxy);
 	dev->caps.qp0_tunnel = dev->caps.qp0_proxy =
 		dev->caps.qp1_tunnel = dev->caps.qp1_proxy = NULL;
+	mlx4_cleanup_qp_zones(dev);
 	return err;
 }
 
@@ -577,7 +841,8 @@ void mlx4_cleanup_qp_table(struct mlx4_dev *dev)
 		return;
 
 	mlx4_CONF_SPECIAL_QP(dev, 0);
-	mlx4_bitmap_cleanup(&mlx4_priv(dev)->qp_table.bitmap);
+
+	mlx4_cleanup_qp_zones(dev);
 }
 
 int mlx4_qp_query(struct mlx4_dev *dev, struct mlx4_qp *qp,

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,