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

Pull networking updates from David Miller:

 1) Add BQL support to via-rhine, from Tino Reichardt.

 2) Integrate SWITCHDEV layer support into the DSA layer, so DSA drivers
    can support hw switch offloading.  From Floria Fainelli.

 3) Allow 'ip address' commands to initiate multicast group join/leave,
    from Madhu Challa.

 4) Many ipv4 FIB lookup optimizations from Alexander Duyck.

 5) Support EBPF in cls_bpf classifier and act_bpf action, from Daniel
    Borkmann.

 6) Remove the ugly compat support in ARP for ugly layers like ax25,
    rose, etc.  And use this to clean up the neigh layer, then use it to
    implement MPLS support.  All from Eric Biederman.

 7) Support L3 forwarding offloading in switches, from Scott Feldman.

 8) Collapse the LOCAL and MAIN ipv4 FIB tables when possible, to speed
    up route lookups even further.  From Alexander Duyck.

 9) Many improvements and bug fixes to the rhashtable implementation,
    from Herbert Xu and Thomas Graf.  In particular, in the case where
    an rhashtable user bulk adds a large number of items into an empty
    table, we expand the table much more sanely.

10) Don't make the tcp_metrics hash table per-namespace, from Eric
    Biederman.

11) Extend EBPF to access SKB fields, from Alexei Starovoitov.

12) Split out new connection request sockets so that they can be
    established in the main hash table.  Much less false sharing since
    hash lookups go direct to the request sockets instead of having to
    go first to the listener then to the request socks hashed
    underneath.  From Eric Dumazet.

13) Add async I/O support for crytpo AF_ALG sockets, from Tadeusz Struk.

14) Support stable privacy address generation for RFC7217 in IPV6.  From
    Hannes Frederic Sowa.

15) Hash network namespace into IP frag IDs, also from Hannes Frederic
    Sowa.

16) Convert PTP get/set methods to use 64-bit time, from Richard
    Cochran.

* git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next: (1816 commits)
  fm10k: Bump driver version to 0.15.2
  fm10k: corrected VF multicast update
  fm10k: mbx_update_max_size does not drop all oversized messages
  fm10k: reset head instead of calling update_max_size
  fm10k: renamed mbx_tx_dropped to mbx_tx_oversized
  fm10k: update xcast mode before synchronizing multicast addresses
  fm10k: start service timer on probe
  fm10k: fix function header comment
  fm10k: comment next_vf_mbx flow
  fm10k: don't handle mailbox events in iov_event path and always process mailbox
  fm10k: use separate workqueue for fm10k driver
  fm10k: Set PF queues to unlimited bandwidth during virtualization
  fm10k: expose tx_timeout_count as an ethtool stat
  fm10k: only increment tx_timeout_count in Tx hang path
  fm10k: remove extraneous "Reset interface" message
  fm10k: separate PF only stats so that VF does not display them
  fm10k: use hw->mac.max_queues for stats
  fm10k: only show actual queues, not the maximum in hardware
  fm10k: allow creation of VLAN on default vid
  fm10k: fix unused warnings
  ...

1 files changed, 125 insertions, 101 deletions

diff --git a/net/mac80211/sta_info.c b/net/mac80211/sta_info.c
index 00ca8dcc2bcf..12971b71d0fa 100644
--- a/net/mac80211/sta_info.c
+++ b/net/mac80211/sta_info.c
@@ -64,32 +64,20 @@
  * freed before they are done using it.
  */
 
+static const struct rhashtable_params sta_rht_params = {
+	.nelem_hint = 3, /* start small */
+	.head_offset = offsetof(struct sta_info, hash_node),
+	.key_offset = offsetof(struct sta_info, sta.addr),
+	.key_len = ETH_ALEN,
+	.hashfn = sta_addr_hash,
+};
+
 /* Caller must hold local->sta_mtx */
 static int sta_info_hash_del(struct ieee80211_local *local,
 			     struct sta_info *sta)
 {
-	struct sta_info *s;
-
-	s = rcu_dereference_protected(local->sta_hash[STA_HASH(sta->sta.addr)],
-				      lockdep_is_held(&local->sta_mtx));
-	if (!s)
-		return -ENOENT;
-	if (s == sta) {
-		rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)],
-				   s->hnext);
-		return 0;
-	}
-
-	while (rcu_access_pointer(s->hnext) &&
-	       rcu_access_pointer(s->hnext) != sta)
-		s = rcu_dereference_protected(s->hnext,
-					lockdep_is_held(&local->sta_mtx));
-	if (rcu_access_pointer(s->hnext)) {
-		rcu_assign_pointer(s->hnext, sta->hnext);
-		return 0;
-	}
-
-	return -ENOENT;
+	return rhashtable_remove_fast(&local->sta_hash, &sta->hash_node,
+				      sta_rht_params);
 }
 
 static void __cleanup_single_sta(struct sta_info *sta)
@@ -118,6 +106,16 @@ static void __cleanup_single_sta(struct sta_info *sta)
 		atomic_dec(&ps->num_sta_ps);
 	}
 
+	if (sta->sta.txq[0]) {
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
+			int n = skb_queue_len(&txqi->queue);
+
+			ieee80211_purge_tx_queue(&local->hw, &txqi->queue);
+			atomic_sub(n, &sdata->txqs_len[txqi->txq.ac]);
+		}
+	}
+
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		local->total_ps_buffered -= skb_queue_len(&sta->ps_tx_buf[ac]);
 		ieee80211_purge_tx_queue(&local->hw, &sta->ps_tx_buf[ac]);
@@ -159,18 +157,8 @@ struct sta_info *sta_info_get(struct ieee80211_sub_if_data *sdata,
 			      const u8 *addr)
 {
 	struct ieee80211_local *local = sdata->local;
-	struct sta_info *sta;
 
-	sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)],
-				    lockdep_is_held(&local->sta_mtx));
-	while (sta) {
-		if (sta->sdata == sdata &&
-		    ether_addr_equal(sta->sta.addr, addr))
-			break;
-		sta = rcu_dereference_check(sta->hnext,
-					    lockdep_is_held(&local->sta_mtx));
-	}
-	return sta;
+	return rhashtable_lookup_fast(&local->sta_hash, addr, sta_rht_params);
 }
 
 /*
@@ -182,18 +170,24 @@ struct sta_info *sta_info_get_bss(struct ieee80211_sub_if_data *sdata,
 {
 	struct ieee80211_local *local = sdata->local;
 	struct sta_info *sta;
+	struct rhash_head *tmp;
+	const struct bucket_table *tbl;
 
-	sta = rcu_dereference_check(local->sta_hash[STA_HASH(addr)],
-				    lockdep_is_held(&local->sta_mtx));
-	while (sta) {
-		if ((sta->sdata == sdata ||
-		     (sta->sdata->bss && sta->sdata->bss == sdata->bss)) &&
-		    ether_addr_equal(sta->sta.addr, addr))
-			break;
-		sta = rcu_dereference_check(sta->hnext,
-					    lockdep_is_held(&local->sta_mtx));
+	rcu_read_lock();
+	tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
+
+	for_each_sta_info(local, tbl, addr, sta, tmp) {
+		if (sta->sdata == sdata ||
+		    (sta->sdata->bss && sta->sdata->bss == sdata->bss)) {
+			rcu_read_unlock();
+			/* this is safe as the caller must already hold
+			 * another rcu read section or the mutex
+			 */
+			return sta;
+		}
 	}
-	return sta;
+	rcu_read_unlock();
+	return NULL;
 }
 
 struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
@@ -229,19 +223,13 @@ struct sta_info *sta_info_get_by_idx(struct ieee80211_sub_if_data *sdata,
  */
 void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 {
-	int i;
-
 	if (sta->rate_ctrl)
 		rate_control_free_sta(sta);
 
-	if (sta->tx_lat) {
-		for (i = 0; i < IEEE80211_NUM_TIDS; i++)
-			kfree(sta->tx_lat[i].bins);
-		kfree(sta->tx_lat);
-	}
-
 	sta_dbg(sta->sdata, "Destroyed STA %pM\n", sta->sta.addr);
 
+	if (sta->sta.txq[0])
+		kfree(to_txq_info(sta->sta.txq[0]));
 	kfree(rcu_dereference_raw(sta->sta.rates));
 	kfree(sta);
 }
@@ -250,9 +238,8 @@ void sta_info_free(struct ieee80211_local *local, struct sta_info *sta)
 static void sta_info_hash_add(struct ieee80211_local *local,
 			      struct sta_info *sta)
 {
-	lockdep_assert_held(&local->sta_mtx);
-	sta->hnext = local->sta_hash[STA_HASH(sta->sta.addr)];
-	rcu_assign_pointer(local->sta_hash[STA_HASH(sta->sta.addr)], sta);
+	rhashtable_insert_fast(&local->sta_hash, &sta->hash_node,
+			       sta_rht_params);
 }
 
 static void sta_deliver_ps_frames(struct work_struct *wk)
@@ -293,44 +280,15 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 				const u8 *addr, gfp_t gfp)
 {
 	struct ieee80211_local *local = sdata->local;
+	struct ieee80211_hw *hw = &local->hw;
 	struct sta_info *sta;
 	struct timespec uptime;
-	struct ieee80211_tx_latency_bin_ranges *tx_latency;
 	int i;
 
-	sta = kzalloc(sizeof(*sta) + local->hw.sta_data_size, gfp);
+	sta = kzalloc(sizeof(*sta) + hw->sta_data_size, gfp);
 	if (!sta)
 		return NULL;
 
-	rcu_read_lock();
-	tx_latency = rcu_dereference(local->tx_latency);
-	/* init stations Tx latency statistics && TID bins */
-	if (tx_latency) {
-		sta->tx_lat = kzalloc(IEEE80211_NUM_TIDS *
-				      sizeof(struct ieee80211_tx_latency_stat),
-				      GFP_ATOMIC);
-		if (!sta->tx_lat) {
-			rcu_read_unlock();
-			goto free;
-		}
-
-		if (tx_latency->n_ranges) {
-			for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
-				/* size of bins is size of the ranges +1 */
-				sta->tx_lat[i].bin_count =
-					tx_latency->n_ranges + 1;
-				sta->tx_lat[i].bins =
-					kcalloc(sta->tx_lat[i].bin_count,
-						sizeof(u32), GFP_ATOMIC);
-				if (!sta->tx_lat[i].bins) {
-					rcu_read_unlock();
-					goto free;
-				}
-			}
-		}
-	}
-	rcu_read_unlock();
-
 	spin_lock_init(&sta->lock);
 	spin_lock_init(&sta->ps_lock);
 	INIT_WORK(&sta->drv_deliver_wk, sta_deliver_ps_frames);
@@ -359,8 +317,24 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	for (i = 0; i < ARRAY_SIZE(sta->chain_signal_avg); i++)
 		ewma_init(&sta->chain_signal_avg[i], 1024, 8);
 
+	if (local->ops->wake_tx_queue) {
+		void *txq_data;
+		int size = sizeof(struct txq_info) +
+			   ALIGN(hw->txq_data_size, sizeof(void *));
+
+		txq_data = kcalloc(ARRAY_SIZE(sta->sta.txq), size, gfp);
+		if (!txq_data)
+			goto free;
+
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			struct txq_info *txq = txq_data + i * size;
+
+			ieee80211_init_tx_queue(sdata, sta, txq, i);
+		}
+	}
+
 	if (sta_prepare_rate_control(local, sta, gfp))
-		goto free;
+		goto free_txq;
 
 	for (i = 0; i < IEEE80211_NUM_TIDS; i++) {
 		/*
@@ -382,7 +356,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	if (sdata->vif.type == NL80211_IFTYPE_AP ||
 	    sdata->vif.type == NL80211_IFTYPE_AP_VLAN) {
 		struct ieee80211_supported_band *sband =
-			local->hw.wiphy->bands[ieee80211_get_sdata_band(sdata)];
+			hw->wiphy->bands[ieee80211_get_sdata_band(sdata)];
 		u8 smps = (sband->ht_cap.cap & IEEE80211_HT_CAP_SM_PS) >>
 				IEEE80211_HT_CAP_SM_PS_SHIFT;
 		/*
@@ -405,14 +379,13 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	}
 
 	sta_dbg(sdata, "Allocated STA %pM\n", sta->sta.addr);
+
 	return sta;
 
+free_txq:
+	if (sta->sta.txq[0])
+		kfree(to_txq_info(sta->sta.txq[0]));
 free:
-	if (sta->tx_lat) {
-		for (i = 0; i < IEEE80211_NUM_TIDS; i++)
-			kfree(sta->tx_lat[i].bins);
-		kfree(sta->tx_lat);
-	}
 	kfree(sta);
 	return NULL;
 }
@@ -684,6 +657,8 @@ static void __sta_info_recalc_tim(struct sta_info *sta, bool ignore_pending)
 
 		indicate_tim |=
 			sta->driver_buffered_tids & tids;
+		indicate_tim |=
+			sta->txq_buffered_tids & tids;
 	}
 
  done:
@@ -992,19 +967,32 @@ static void sta_info_cleanup(unsigned long data)
 		  round_jiffies(jiffies + STA_INFO_CLEANUP_INTERVAL));
 }
 
-void sta_info_init(struct ieee80211_local *local)
+u32 sta_addr_hash(const void *key, u32 length, u32 seed)
+{
+	return jhash(key, ETH_ALEN, seed);
+}
+
+int sta_info_init(struct ieee80211_local *local)
 {
+	int err;
+
+	err = rhashtable_init(&local->sta_hash, &sta_rht_params);
+	if (err)
+		return err;
+
 	spin_lock_init(&local->tim_lock);
 	mutex_init(&local->sta_mtx);
 	INIT_LIST_HEAD(&local->sta_list);
 
 	setup_timer(&local->sta_cleanup, sta_info_cleanup,
 		    (unsigned long)local);
+	return 0;
 }
 
 void sta_info_stop(struct ieee80211_local *local)
 {
 	del_timer_sync(&local->sta_cleanup);
+	rhashtable_destroy(&local->sta_hash);
 }
 
 
@@ -1068,16 +1056,21 @@ void ieee80211_sta_expire(struct ieee80211_sub_if_data *sdata,
 }
 
 struct ieee80211_sta *ieee80211_find_sta_by_ifaddr(struct ieee80211_hw *hw,
-					       const u8 *addr,
-					       const u8 *localaddr)
+						   const u8 *addr,
+						   const u8 *localaddr)
 {
-	struct sta_info *sta, *nxt;
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct sta_info *sta;
+	struct rhash_head *tmp;
+	const struct bucket_table *tbl;
+
+	tbl = rht_dereference_rcu(local->sta_hash.tbl, &local->sta_hash);
 
 	/*
 	 * Just return a random station if localaddr is NULL
 	 * ... first in list.
 	 */
-	for_each_sta_info(hw_to_local(hw), addr, sta, nxt) {
+	for_each_sta_info(local, tbl, addr, sta, tmp) {
 		if (localaddr &&
 		    !ether_addr_equal(sta->sdata->vif.addr, localaddr))
 			continue;
@@ -1115,7 +1108,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	struct ieee80211_sub_if_data *sdata = sta->sdata;
 	struct ieee80211_local *local = sdata->local;
 	struct sk_buff_head pending;
-	int filtered = 0, buffered = 0, ac;
+	int filtered = 0, buffered = 0, ac, i;
 	unsigned long flags;
 	struct ps_data *ps;
 
@@ -1134,10 +1127,22 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	BUILD_BUG_ON(BITS_TO_LONGS(IEEE80211_NUM_TIDS) > 1);
 	sta->driver_buffered_tids = 0;
+	sta->txq_buffered_tids = 0;
 
 	if (!(local->hw.flags & IEEE80211_HW_AP_LINK_PS))
 		drv_sta_notify(local, sdata, STA_NOTIFY_AWAKE, &sta->sta);
 
+	if (sta->sta.txq[0]) {
+		for (i = 0; i < ARRAY_SIZE(sta->sta.txq); i++) {
+			struct txq_info *txqi = to_txq_info(sta->sta.txq[i]);
+
+			if (!skb_queue_len(&txqi->queue))
+				continue;
+
+			drv_wake_tx_queue(local, txqi);
+		}
+	}
+
 	skb_queue_head_init(&pending);
 
 	/* sync with ieee80211_tx_h_unicast_ps_buf */
@@ -1275,7 +1280,7 @@ static void ieee80211_send_null_response(struct ieee80211_sub_if_data *sdata,
 	}
 
 	info->band = chanctx_conf->def.chan->band;
-	ieee80211_xmit(sdata, skb);
+	ieee80211_xmit(sdata, sta, skb);
 	rcu_read_unlock();
 }
 
@@ -1319,8 +1324,10 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		/* if we already have frames from software, then we can't also
 		 * release from hardware queues
 		 */
-		if (skb_queue_empty(&frames))
+		if (skb_queue_empty(&frames)) {
 			driver_release_tids |= sta->driver_buffered_tids & tids;
+			driver_release_tids |= sta->txq_buffered_tids & tids;
+		}
 
 		if (driver_release_tids) {
 			/* If the driver has data on more than one TID then
@@ -1491,6 +1498,9 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 
 		sta_info_recalc_tim(sta);
 	} else {
+		unsigned long tids = sta->txq_buffered_tids & driver_release_tids;
+		int tid;
+
 		/*
 		 * We need to release a frame that is buffered somewhere in the
 		 * driver ... it'll have to handle that.
@@ -1510,8 +1520,22 @@ ieee80211_sta_ps_deliver_response(struct sta_info *sta,
 		 * that the TID(s) became empty before returning here from the
 		 * release function.
 		 * Either way, however, when the driver tells us that the TID(s)
-		 * became empty we'll do the TIM recalculation.
+		 * became empty or we find that a txq became empty, we'll do the
+		 * TIM recalculation.
 		 */
+
+		if (!sta->sta.txq[0])
+			return;
+
+		for (tid = 0; tid < ARRAY_SIZE(sta->sta.txq); tid++) {
+			struct txq_info *txqi = to_txq_info(sta->sta.txq[tid]);
+
+			if (!(tids & BIT(tid)) || skb_queue_len(&txqi->queue))
+				continue;
+
+			sta_info_recalc_tim(sta);
+			break;
+		}
 	}
 }