Merge git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next

Pull networking updates from David Miller:

 1) Unified UDP encapsulation offload methods for drivers, from
    Alexander Duyck.

 2) Make DSA binding more sane, from Andrew Lunn.

 3) Support QCA9888 chips in ath10k, from Anilkumar Kolli.

 4) Several workqueue usage cleanups, from Bhaktipriya Shridhar.

 5) Add XDP (eXpress Data Path), essentially running BPF programs on RX
    packets as soon as the device sees them, with the option to mirror
    the packet on TX via the same interface.  From Brenden Blanco and
    others.

 6) Allow qdisc/class stats dumps to run lockless, from Eric Dumazet.

 7) Add VLAN support to b53 and bcm_sf2, from Florian Fainelli.

 8) Simplify netlink conntrack entry layout, from Florian Westphal.

 9) Add ipv4 forwarding support to mlxsw spectrum driver, from Ido
    Schimmel, Yotam Gigi, and Jiri Pirko.

10) Add SKB array infrastructure and convert tun and macvtap over to it.
    From Michael S Tsirkin and Jason Wang.

11) Support qdisc packet injection in pktgen, from John Fastabend.

12) Add neighbour monitoring framework to TIPC, from Jon Paul Maloy.

13) Add NV congestion control support to TCP, from Lawrence Brakmo.

14) Add GSO support to SCTP, from Marcelo Ricardo Leitner.

15) Allow GRO and RPS to function on macsec devices, from Paolo Abeni.

16) Support MPLS over IPV4, from Simon Horman.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1622 commits)
  xgene: Fix build warning with ACPI disabled.
  be2net: perform temperature query in adapter regardless of its interface state
  l2tp: Correctly return -EBADF from pppol2tp_getname.
  net/mlx5_core/health: Remove deprecated create_singlethread_workqueue
  net: ipmr/ip6mr: update lastuse on entry change
  macsec: ensure rx_sa is set when validation is disabled
  tipc: dump monitor attributes
  tipc: add a function to get the bearer name
  tipc: get monitor threshold for the cluster
  tipc: make cluster size threshold for monitoring configurable
  tipc: introduce constants for tipc address validation
  net: neigh: disallow transition to NUD_STALE if lladdr is unchanged in neigh_update()
  MAINTAINERS: xgene: Add driver and documentation path
  Documentation: dtb: xgene: Add MDIO node
  dtb: xgene: Add MDIO node
  drivers: net: xgene: ethtool: Use phy_ethtool_gset and sset
  drivers: net: xgene: Use exported functions
  drivers: net: xgene: Enable MDIO driver
  drivers: net: xgene: Add backward compatibility
  drivers: net: phy: xgene: Add MDIO driver
  ...

1 files changed, 261 insertions, 41 deletions

diff --git a/net/mac80211/tx.c b/net/mac80211/tx.c
index 203044379ce0..91461c415525 100644
--- a/net/mac80211/tx.c
+++ b/net/mac80211/tx.c
@@ -24,7 +24,10 @@
 #include <net/ieee80211_radiotap.h>
 #include <net/cfg80211.h>
 #include <net/mac80211.h>
+#include <net/codel.h>
+#include <net/codel_impl.h>
 #include <asm/unaligned.h>
+#include <net/fq_impl.h>
 
 #include "ieee80211_i.h"
 #include "driver-ops.h"
@@ -590,6 +593,9 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 	else if (tx->sta &&
 		 (key = rcu_dereference(tx->sta->ptk[tx->sta->ptk_idx])))
 		tx->key = key;
+	else if (ieee80211_is_group_privacy_action(tx->skb) &&
+		(key = rcu_dereference(tx->sdata->default_multicast_key)))
+		tx->key = key;
 	else if (ieee80211_is_mgmt(hdr->frame_control) &&
 		 is_multicast_ether_addr(hdr->addr1) &&
 		 ieee80211_is_robust_mgmt_frame(tx->skb) &&
@@ -622,7 +628,8 @@ ieee80211_tx_h_select_key(struct ieee80211_tx_data *tx)
 		case WLAN_CIPHER_SUITE_GCMP_256:
 			if (!ieee80211_is_data_present(hdr->frame_control) &&
 			    !ieee80211_use_mfp(hdr->frame_control, tx->sta,
-					       tx->skb))
+					       tx->skb) &&
+			    !ieee80211_is_group_privacy_action(tx->skb))
 				tx->key = NULL;
 			else
 				skip_hw = (tx->key->conf.flags &
@@ -1236,27 +1243,21 @@ ieee80211_tx_prepare(struct ieee80211_sub_if_data *sdata,
 	return TX_CONTINUE;
 }
 
-static void ieee80211_drv_tx(struct ieee80211_local *local,
-			     struct ieee80211_vif *vif,
-			     struct ieee80211_sta *pubsta,
-			     struct sk_buff *skb)
+static struct txq_info *ieee80211_get_txq(struct ieee80211_local *local,
+					  struct ieee80211_vif *vif,
+					  struct ieee80211_sta *pubsta,
+					  struct sk_buff *skb)
 {
 	struct ieee80211_hdr *hdr = (struct ieee80211_hdr *) skb->data;
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
 	struct ieee80211_tx_info *info = IEEE80211_SKB_CB(skb);
-	struct ieee80211_tx_control control = {
-		.sta = pubsta,
-	};
 	struct ieee80211_txq *txq = NULL;
-	struct txq_info *txqi;
-	u8 ac;
 
 	if ((info->flags & IEEE80211_TX_CTL_SEND_AFTER_DTIM) ||
 	    (info->control.flags & IEEE80211_TX_CTRL_PS_RESPONSE))
-		goto tx_normal;
+		return NULL;
 
 	if (!ieee80211_is_data(hdr->frame_control))
-		goto tx_normal;
+		return NULL;
 
 	if (pubsta) {
 		u8 tid = skb->priority & IEEE80211_QOS_CTL_TID_MASK;
@@ -1267,51 +1268,234 @@ static void ieee80211_drv_tx(struct ieee80211_local *local,
 	}
 
 	if (!txq)
-		goto tx_normal;
+		return NULL;
 
-	ac = txq->ac;
-	txqi = to_txq_info(txq);
-	atomic_inc(&sdata->txqs_len[ac]);
-	if (atomic_read(&sdata->txqs_len[ac]) >= local->hw.txq_ac_max_pending)
-		netif_stop_subqueue(sdata->dev, ac);
+	return to_txq_info(txq);
+}
+
+static void ieee80211_set_skb_enqueue_time(struct sk_buff *skb)
+{
+	IEEE80211_SKB_CB(skb)->control.enqueue_time = codel_get_time();
+}
+
+static void ieee80211_set_skb_vif(struct sk_buff *skb, struct txq_info *txqi)
+{
+	IEEE80211_SKB_CB(skb)->control.vif = txqi->txq.vif;
+}
+
+static u32 codel_skb_len_func(const struct sk_buff *skb)
+{
+	return skb->len;
+}
+
+static codel_time_t codel_skb_time_func(const struct sk_buff *skb)
+{
+	const struct ieee80211_tx_info *info;
+
+	info = (const struct ieee80211_tx_info *)skb->cb;
+	return info->control.enqueue_time;
+}
+
+static struct sk_buff *codel_dequeue_func(struct codel_vars *cvars,
+					  void *ctx)
+{
+	struct ieee80211_local *local;
+	struct txq_info *txqi;
+	struct fq *fq;
+	struct fq_flow *flow;
+
+	txqi = ctx;
+	local = vif_to_sdata(txqi->txq.vif)->local;
+	fq = &local->fq;
+
+	if (cvars == &txqi->def_cvars)
+		flow = &txqi->def_flow;
+	else
+		flow = &fq->flows[cvars - local->cvars];
+
+	return fq_flow_dequeue(fq, flow);
+}
+
+static void codel_drop_func(struct sk_buff *skb,
+			    void *ctx)
+{
+	struct ieee80211_local *local;
+	struct ieee80211_hw *hw;
+	struct txq_info *txqi;
+
+	txqi = ctx;
+	local = vif_to_sdata(txqi->txq.vif)->local;
+	hw = &local->hw;
+
+	ieee80211_free_txskb(hw, skb);
+}
+
+static struct sk_buff *fq_tin_dequeue_func(struct fq *fq,
+					   struct fq_tin *tin,
+					   struct fq_flow *flow)
+{
+	struct ieee80211_local *local;
+	struct txq_info *txqi;
+	struct codel_vars *cvars;
+	struct codel_params *cparams;
+	struct codel_stats *cstats;
+
+	local = container_of(fq, struct ieee80211_local, fq);
+	txqi = container_of(tin, struct txq_info, tin);
+	cparams = &local->cparams;
+	cstats = &local->cstats;
+
+	if (flow == &txqi->def_flow)
+		cvars = &txqi->def_cvars;
+	else
+		cvars = &local->cvars[flow - fq->flows];
+
+	return codel_dequeue(txqi,
+			     &flow->backlog,
+			     cparams,
+			     cvars,
+			     cstats,
+			     codel_skb_len_func,
+			     codel_skb_time_func,
+			     codel_drop_func,
+			     codel_dequeue_func);
+}
+
+static void fq_skb_free_func(struct fq *fq,
+			     struct fq_tin *tin,
+			     struct fq_flow *flow,
+			     struct sk_buff *skb)
+{
+	struct ieee80211_local *local;
+
+	local = container_of(fq, struct ieee80211_local, fq);
+	ieee80211_free_txskb(&local->hw, skb);
+}
+
+static struct fq_flow *fq_flow_get_default_func(struct fq *fq,
+						struct fq_tin *tin,
+						int idx,
+						struct sk_buff *skb)
+{
+	struct txq_info *txqi;
+
+	txqi = container_of(tin, struct txq_info, tin);
+	return &txqi->def_flow;
+}
+
+static void ieee80211_txq_enqueue(struct ieee80211_local *local,
+				  struct txq_info *txqi,
+				  struct sk_buff *skb)
+{
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
+
+	ieee80211_set_skb_enqueue_time(skb);
+	fq_tin_enqueue(fq, tin, skb,
+		       fq_skb_free_func,
+		       fq_flow_get_default_func);
+}
+
+void ieee80211_txq_init(struct ieee80211_sub_if_data *sdata,
+			struct sta_info *sta,
+			struct txq_info *txqi, int tid)
+{
+	fq_tin_init(&txqi->tin);
+	fq_flow_init(&txqi->def_flow);
+	codel_vars_init(&txqi->def_cvars);
+
+	txqi->txq.vif = &sdata->vif;
+
+	if (sta) {
+		txqi->txq.sta = &sta->sta;
+		sta->sta.txq[tid] = &txqi->txq;
+		txqi->txq.tid = tid;
+		txqi->txq.ac = ieee802_1d_to_ac[tid & 7];
+	} else {
+		sdata->vif.txq = &txqi->txq;
+		txqi->txq.tid = 0;
+		txqi->txq.ac = IEEE80211_AC_BE;
+	}
+}
+
+void ieee80211_txq_purge(struct ieee80211_local *local,
+			 struct txq_info *txqi)
+{
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
+
+	fq_tin_reset(fq, tin, fq_skb_free_func);
+}
+
+int ieee80211_txq_setup_flows(struct ieee80211_local *local)
+{
+	struct fq *fq = &local->fq;
+	int ret;
+	int i;
 
-	spin_lock_bh(&txqi->queue.lock);
-	txqi->byte_cnt += skb->len;
-	__skb_queue_tail(&txqi->queue, skb);
-	spin_unlock_bh(&txqi->queue.lock);
+	if (!local->ops->wake_tx_queue)
+		return 0;
 
-	drv_wake_tx_queue(local, txqi);
+	ret = fq_init(fq, 4096);
+	if (ret)
+		return ret;
+
+	codel_params_init(&local->cparams);
+	codel_stats_init(&local->cstats);
+	local->cparams.interval = MS2TIME(100);
+	local->cparams.target = MS2TIME(20);
+	local->cparams.ecn = true;
+
+	local->cvars = kcalloc(fq->flows_cnt, sizeof(local->cvars[0]),
+			       GFP_KERNEL);
+	if (!local->cvars) {
+		spin_lock_bh(&fq->lock);
+		fq_reset(fq, fq_skb_free_func);
+		spin_unlock_bh(&fq->lock);
+		return -ENOMEM;
+	}
 
-	return;
+	for (i = 0; i < fq->flows_cnt; i++)
+		codel_vars_init(&local->cvars[i]);
 
-tx_normal:
-	drv_tx(local, &control, skb);
+	return 0;
+}
+
+void ieee80211_txq_teardown_flows(struct ieee80211_local *local)
+{
+	struct fq *fq = &local->fq;
+
+	if (!local->ops->wake_tx_queue)
+		return;
+
+	kfree(local->cvars);
+	local->cvars = NULL;
+
+	spin_lock_bh(&fq->lock);
+	fq_reset(fq, fq_skb_free_func);
+	spin_unlock_bh(&fq->lock);
 }
 
 struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 				     struct ieee80211_txq *txq)
 {
 	struct ieee80211_local *local = hw_to_local(hw);
-	struct ieee80211_sub_if_data *sdata = vif_to_sdata(txq->vif);
 	struct txq_info *txqi = container_of(txq, struct txq_info, txq);
 	struct ieee80211_hdr *hdr;
 	struct sk_buff *skb = NULL;
-	u8 ac = txq->ac;
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin = &txqi->tin;
 
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
 
 	if (test_bit(IEEE80211_TXQ_STOP, &txqi->flags))
 		goto out;
 
-	skb = __skb_dequeue(&txqi->queue);
+	skb = fq_tin_dequeue(fq, tin, fq_tin_dequeue_func);
 	if (!skb)
 		goto out;
 
-	txqi->byte_cnt -= skb->len;
-
-	atomic_dec(&sdata->txqs_len[ac]);
-	if (__netif_subqueue_stopped(sdata->dev, ac))
-		ieee80211_propagate_queue_wake(local, sdata->vif.hw_queue[ac]);
+	ieee80211_set_skb_vif(skb, txqi);
 
 	hdr = (struct ieee80211_hdr *)skb->data;
 	if (txq->sta && ieee80211_is_data_qos(hdr->frame_control)) {
@@ -1327,7 +1511,7 @@ struct sk_buff *ieee80211_tx_dequeue(struct ieee80211_hw *hw,
 	}
 
 out:
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 
 	if (skb && skb_has_frag_list(skb) &&
 	    !ieee80211_hw_check(&local->hw, TX_FRAG_LIST))
@@ -1343,7 +1527,10 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 			       struct sk_buff_head *skbs,
 			       bool txpending)
 {
+	struct ieee80211_tx_control control = {};
+	struct fq *fq = &local->fq;
 	struct sk_buff *skb, *tmp;
+	struct txq_info *txqi;
 	unsigned long flags;
 
 	skb_queue_walk_safe(skbs, skb, tmp) {
@@ -1358,6 +1545,21 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 		}
 #endif
 
+		txqi = ieee80211_get_txq(local, vif, sta, skb);
+		if (txqi) {
+			info->control.vif = vif;
+
+			__skb_unlink(skb, skbs);
+
+			spin_lock_bh(&fq->lock);
+			ieee80211_txq_enqueue(local, txqi, skb);
+			spin_unlock_bh(&fq->lock);
+
+			drv_wake_tx_queue(local, txqi);
+
+			continue;
+		}
+
 		spin_lock_irqsave(&local->queue_stop_reason_lock, flags);
 		if (local->queue_stop_reasons[q] ||
 		    (!txpending && !skb_queue_empty(&local->pending[q]))) {
@@ -1400,9 +1602,10 @@ static bool ieee80211_tx_frags(struct ieee80211_local *local,
 		spin_unlock_irqrestore(&local->queue_stop_reason_lock, flags);
 
 		info->control.vif = vif;
+		control.sta = sta;
 
 		__skb_unlink(skb, skbs);
-		ieee80211_drv_tx(local, vif, sta, skb);
+		drv_tx(local, &control, skb);
 	}
 
 	return true;
@@ -2882,6 +3085,9 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 				      struct sk_buff *skb)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct fq *fq = &local->fq;
+	struct fq_tin *tin;
+	struct fq_flow *flow;
 	u8 tid = skb->priority & IEEE80211_QOS_CTL_TAG1D_MASK;
 	struct ieee80211_txq *txq = sta->sta.txq[tid];
 	struct txq_info *txqi;
@@ -2893,6 +3099,7 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	__be16 len;
 	void *data;
 	bool ret = false;
+	unsigned int orig_len;
 	int n = 1, nfrags;
 
 	if (!ieee80211_hw_check(&local->hw, TX_AMSDU))
@@ -2909,12 +3116,20 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 		max_amsdu_len = min_t(int, max_amsdu_len,
 				      sta->sta.max_rc_amsdu_len);
 
-	spin_lock_bh(&txqi->queue.lock);
+	spin_lock_bh(&fq->lock);
+
+	/* TODO: Ideally aggregation should be done on dequeue to remain
+	 * responsive to environment changes.
+	 */
 
-	head = skb_peek_tail(&txqi->queue);
+	tin = &txqi->tin;
+	flow = fq_flow_classify(fq, tin, skb, fq_flow_get_default_func);
+	head = skb_peek_tail(&flow->queue);
 	if (!head)
 		goto out;
 
+	orig_len = head->len;
+
 	if (skb->len + head->len > max_amsdu_len)
 		goto out;
 
@@ -2953,8 +3168,13 @@ static bool ieee80211_amsdu_aggregate(struct ieee80211_sub_if_data *sdata,
 	head->data_len += skb->len;
 	*frag_tail = skb;
 
+	flow->backlog += head->len - orig_len;
+	tin->backlog_bytes += head->len - orig_len;
+
+	fq_recalc_backlog(fq, tin, flow);
+
 out:
-	spin_unlock_bh(&txqi->queue.lock);
+	spin_unlock_bh(&fq->lock);
 
 	return ret;
 }