iwlwifi: mvm: fix mac80211's hw_queue in DQA mode

When in non-DQA mode, mac80211 actually gets a pretty much perfect
idea (in vif->hw_queue/cab_queue) of which queues we're using. But
in DQA mode, this isn't true - nonetheless, we were adding all the
queues, even the ones stations are using, to the queue allocation
bitmap.

Fix this, we should only add the queues we really are using in DQA
mode:
 * IWL_MVM_OFFCHANNEL_QUEUE, as we use this in both modes
 * mvm->aux_queue, as we use this in both modes - mac80211
   never really knows about it but we use it as a cookie
   internally, so can't reuse it
 * possibly the GCAST queue (cab_queue)
 * all the "queues" we told mac80211 about we were using on each
   interface (vif->hw_queue), these are entirely virtual in this
   mode

Also add back the failure now when we can't allocate any more of
these - now virtual - queues; this was skipped in DQA mode and
would lead to having multiple ACs or even interfaces use the same
queue number in mac80211 (10, since that's the limit), which would
stop far too many queues if stopped.
Signed-off-by: Johannes Berg <johannes.berg@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>

drivers/net/wireless/intel/iwlwifi/mvm/mac-ctxt.c

@@ -257,7 +257,7 @@ unsigned long iwl_mvm_get_used_hw_queues(struct iwl_mvm *mvm,
 	};
 
 	if (iwl_mvm_is_dqa_supported(mvm))
-		data.used_hw_queues |= BIT(IWL_MVM_DQA_CMD_QUEUE);
+		data.used_hw_queues |= BIT(IWL_MVM_DQA_GCAST_QUEUE);
 	else
 		data.used_hw_queues |= BIT(IWL_MVM_CMD_QUEUE);
 
@@ -268,6 +268,14 @@ unsigned long iwl_mvm_get_used_hw_queues(struct iwl_mvm *mvm,
 		mvm->hw, IEEE80211_IFACE_ITER_RESUME_ALL,
 		iwl_mvm_iface_hw_queues_iter, &data);
 
+	/*
+	 * for DQA, the hw_queue in mac80211 is never really used for
+	 * real traffic (only the few queue IDs covered above), so
+	 * we can reuse the real HW queue IDs the stations use
+	 */
+	if (iwl_mvm_is_dqa_supported(mvm))
+		return data.used_hw_queues;
+
 	/* don't assign the same hw queues as TDLS stations */
 	ieee80211_iterate_stations_atomic(mvm->hw,
 					  iwl_mvm_mac_sta_hw_queues_iter,
@@ -344,7 +352,7 @@ static int iwl_mvm_mac_ctxt_allocate_resources(struct iwl_mvm *mvm,
 		.found_vif = false,
 	};
 	u32 ac;
-	int ret, i;
+	int ret, i, queue_limit;
 	unsigned long used_hw_queues;
 
 	/*
@@ -430,17 +438,29 @@ static int iwl_mvm_mac_ctxt_allocate_resources(struct iwl_mvm *mvm,
 		return 0;
 	}
 
+	if (iwl_mvm_is_dqa_supported(mvm)) {
+		/*
+		 * queues in mac80211 almost entirely independent of
+		 * the ones here - no real limit
+		 */
+		queue_limit = IEEE80211_MAX_QUEUES;
+		BUILD_BUG_ON(IEEE80211_MAX_QUEUES >
+			     BITS_PER_BYTE *
+			     sizeof(mvm->hw_queue_to_mac80211[0]));
+	} else {
+		/* need to not use too many in this case */
+		queue_limit = mvm->first_agg_queue;
+	}
+
 	/*
 	 * Find available queues, and allocate them to the ACs. When in
 	 * DQA-mode they aren't really used, and this is done only so the
 	 * mac80211 ieee80211_check_queues() function won't fail
 	 */
 	for (ac = 0; ac < IEEE80211_NUM_ACS; ac++) {
-		u8 queue = find_first_zero_bit(&used_hw_queues,
-					       mvm->first_agg_queue);
+		u8 queue = find_first_zero_bit(&used_hw_queues, queue_limit);
 
-		if (!iwl_mvm_is_dqa_supported(mvm) &&
-		    queue >= mvm->first_agg_queue) {
+		if (queue >= queue_limit) {
 			IWL_ERR(mvm, "Failed to allocate queue\n");
 			ret = -EIO;
 			goto exit_fail;