mac80211: fix AP powersave TX vs. wakeup race

There is a race between the TX path and the STA wakeup: while
a station is sleeping, mac80211 buffers frames until it wakes
up, then the frames are transmitted. However, the RX and TX
path are concurrent, so the packet indicating wakeup can be
processed while a packet is being transmitted.

This can lead to a situation where the buffered frames list
is emptied on the one side, while a frame is being added on
the other side, as the station is still seen as sleeping in
the TX path.

As a result, the newly added frame will not be send anytime
soon. It might be sent much later (and out of order) when the
station goes to sleep and wakes up the next time.

Additionally, it can lead to the crash below.

Fix all this by synchronising both paths with a new lock.
Both path are not fastpath since they handle PS situations.

In a later patch we'll remove the extra skb queue locks to
reduce locking overhead.

BUG: unable to handle kernel
NULL pointer dereference at 000000b0
IP: [<ff6f1791>] ieee80211_report_used_skb+0x11/0x3e0 [mac80211]
*pde = 00000000
Oops: 0000 [#1] SMP DEBUG_PAGEALLOC
EIP: 0060:[<ff6f1791>] EFLAGS: 00210282 CPU: 1
EIP is at ieee80211_report_used_skb+0x11/0x3e0 [mac80211]
EAX: e5900da0 EBX: 00000000 ECX: 00000001 EDX: 00000000
ESI: e41d00c0 EDI: e5900da0 EBP: ebe458e4 ESP: ebe458b0
 DS: 007b ES: 007b FS: 00d8 GS: 00e0 SS: 0068
CR0: 8005003b CR2: 000000b0 CR3: 25a78000 CR4: 000407d0
DR0: 00000000 DR1: 00000000 DR2: 00000000 DR3: 00000000
DR6: ffff0ff0 DR7: 00000400
Process iperf (pid: 3934, ti=ebe44000 task=e757c0b0 task.ti=ebe44000)
iwlwifi 0000:02:00.0: I iwl_pcie_enqueue_hcmd Sending command LQ_CMD (#4e), seq: 0x0903, 92 bytes at 3[3]:9
Stack:
 e403b32c ebe458c4 00200002 00200286 e403b338 ebe458cc c10960bb e5900da0
 ff76a6ec ebe458d8 00000000 e41d00c0 e5900da0 ebe458f0 ff6f1b75 e403b210
 ebe4598c ff723dc1 00000000 ff76a6ec e597c978 e403b758 00000002 00000002
Call Trace:
 [<ff6f1b75>] ieee80211_free_txskb+0x15/0x20 [mac80211]
 [<ff723dc1>] invoke_tx_handlers+0x1661/0x1780 [mac80211]
 [<ff7248a5>] ieee80211_tx+0x75/0x100 [mac80211]
 [<ff7249bf>] ieee80211_xmit+0x8f/0xc0 [mac80211]
 [<ff72550e>] ieee80211_subif_start_xmit+0x4fe/0xe20 [mac80211]
 [<c149ef70>] dev_hard_start_xmit+0x450/0x950
 [<c14b9aa9>] sch_direct_xmit+0xa9/0x250
 [<c14b9c9b>] __qdisc_run+0x4b/0x150
 [<c149f732>] dev_queue_xmit+0x2c2/0xca0

Cc: stable@vger.kernel.org
Reported-by: Yaara Rozenblum <yaara.rozenblum@intel.com>
Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Reviewed-by: Stanislaw Gruszka <sgruszka@redhat.com>
[reword commit log, use a separate lock]
Signed-off-by: Johannes Berg <johannes.berg@intel.com>

net/mac80211/sta_info.c

@@ -330,6 +330,7 @@ struct sta_info *sta_info_alloc(struct ieee80211_sub_if_data *sdata,
 	rcu_read_unlock();
 
 	spin_lock_init(&sta->lock);
+	spin_lock_init(&sta->ps_lock);
 	INIT_WORK(&sta->drv_unblock_wk, sta_unblock);
 	INIT_WORK(&sta->ampdu_mlme.work, ieee80211_ba_session_work);
 	mutex_init(&sta->ampdu_mlme.mtx);
@@ -1109,6 +1110,8 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 
 	skb_queue_head_init(&pending);
 
+	/* sync with ieee80211_tx_h_unicast_ps_buf */
+	spin_lock(&sta->ps_lock);
 	/* Send all buffered frames to the station */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
 		int count = skb_queue_len(&pending), tmp;
@@ -1128,6 +1131,7 @@ void ieee80211_sta_ps_deliver_wakeup(struct sta_info *sta)
 	}
 
 	ieee80211_add_pending_skbs_fn(local, &pending, clear_sta_ps_flags, sta);
+	spin_unlock(&sta->ps_lock);
 
 	/* This station just woke up and isn't aware of our SMPS state */
 	if (!ieee80211_smps_is_restrictive(sta->known_smps_mode,

net/mac80211/sta_info.h

@@ -267,6 +267,7 @@ struct ieee80211_tx_latency_stat {
  * @drv_unblock_wk: used for driver PS unblocking
  * @listen_interval: listen interval of this station, when we're acting as AP
  * @_flags: STA flags, see &enum ieee80211_sta_info_flags, do not use directly
+ * @ps_lock: used for powersave (when mac80211 is the AP) related locking
  * @ps_tx_buf: buffers (per AC) of frames to transmit to this station
  *	when it leaves power saving state or polls
  * @tx_filtered: buffers (per AC) of frames we already tried to
@@ -356,10 +357,8 @@ struct sta_info {
 	/* use the accessors defined below */
 	unsigned long _flags;
 
-	/*
-	 * STA powersave frame queues, no more than the internal
-	 * locking required.
-	 */
+	/* STA powersave lock and frame queues */
+	spinlock_t ps_lock;
 	struct sk_buff_head ps_tx_buf[IEEE80211_NUM_ACS];
 	struct sk_buff_head tx_filtered[IEEE80211_NUM_ACS];
 	unsigned long driver_buffered_tids;

net/mac80211/tx.c

@@ -478,6 +478,20 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		       sta->sta.addr, sta->sta.aid, ac);
 		if (tx->local->total_ps_buffered >= TOTAL_MAX_TX_BUFFER)
 			purge_old_ps_buffers(tx->local);
+
+		/* sync with ieee80211_sta_ps_deliver_wakeup */
+		spin_lock(&sta->ps_lock);
+		/*
+		 * STA woke up the meantime and all the frames on ps_tx_buf have
+		 * been queued to pending queue. No reordering can happen, go
+		 * ahead and Tx the packet.
+		 */
+		if (!test_sta_flag(sta, WLAN_STA_PS_STA) &&
+		    !test_sta_flag(sta, WLAN_STA_PS_DRIVER)) {
+			spin_unlock(&sta->ps_lock);
+			return TX_CONTINUE;
+		}
+
 		if (skb_queue_len(&sta->ps_tx_buf[ac]) >= STA_MAX_TX_BUFFER) {
 			struct sk_buff *old = skb_dequeue(&sta->ps_tx_buf[ac]);
 			ps_dbg(tx->sdata,
@@ -492,6 +506,7 @@ ieee80211_tx_h_unicast_ps_buf(struct ieee80211_tx_data *tx)
 		info->flags |= IEEE80211_TX_INTFL_NEED_TXPROCESSING;
 		info->flags &= ~IEEE80211_TX_TEMPORARY_FLAGS;
 		skb_queue_tail(&sta->ps_tx_buf[ac], tx->skb);
+		spin_unlock(&sta->ps_lock);
 
 		if (!timer_pending(&local->sta_cleanup))
 			mod_timer(&local->sta_cleanup,