iwlwifi: Monitor and recover the aggregation TX flow failure

This change monitors the tx statistics to detect the drop in throughput.
When the throughput drops, the ratio of the actual_ack_count and the expected_
ack_count also drops.  At the same time, the aggregated ba_timeout (the number
of ba timeout retries) also rises.  If the actual_ack_count/expected_ack_count
ratio is 0 and the number of ba timeout retries rises to 16, no tx packets
(tcp, udp, or ping - icmp) can be delivered.  The driver recovers from this
situation by reseting the uCode firmware.  If the actual_ack_count/expected_
ack_count ratio drops below 50% (but not 0) and the aggregated ba_timeout
retries just exceed 5 (but not 16), then the driver can reset the radio to
bring the throughput up.

Signed-off-by: Trieu 'Andrew' Nguyen <trieux.t.nguyen@intel.com>
Signed-off-by: Reinette Chatre <reinette.chatre@intel.com>

3 files changed, 62 insertions, 1 deletions

diff --git a/drivers/net/wireless/iwlwifi/iwl-agn.c b/drivers/net/wireless/iwlwifi/iwl-agn.c
index 31b156d58d7f..4157c6c8645f 100644
--- a/drivers/net/wireless/iwlwifi/iwl-agn.c
+++ b/drivers/net/wireless/iwlwifi/iwl-agn.c
@@ -2941,10 +2941,21 @@ static int iwl_mac_ampdu_action(struct ieee80211_hw *hw,
 			return ret;
 	case IEEE80211_AMPDU_TX_START:
 		IWL_DEBUG_HT(priv, "start Tx\n");
-		return iwl_tx_agg_start(priv, sta->addr, tid, ssn);
+		ret = iwl_tx_agg_start(priv, sta->addr, tid, ssn);
+		if (ret == 0) {
+			priv->agg_tids_count++;
+			IWL_DEBUG_HT(priv, "priv->agg_tids_count = %u\n",
+				priv->agg_tids_count);
+		}
+		return ret;
 	case IEEE80211_AMPDU_TX_STOP:
 		IWL_DEBUG_HT(priv, "stop Tx\n");
 		ret = iwl_tx_agg_stop(priv, sta->addr, tid);
+		if ((ret == 0) && (priv->agg_tids_count > 0)) {
+			priv->agg_tids_count--;
+			IWL_DEBUG_HT(priv, "priv->agg_tids_count = %u\n",
+				priv->agg_tids_count);
+		}
 		if (test_bit(STATUS_EXIT_PENDING, &priv->status))
 			return 0;
 		else
@@ -3364,6 +3375,7 @@ static int iwl_init_drv(struct iwl_priv *priv)
 	priv->iw_mode = NL80211_IFTYPE_STATION;
 	priv->current_ht_config.smps = IEEE80211_SMPS_STATIC;
 	priv->missed_beacon_threshold = IWL_MISSED_BEACON_THRESHOLD_DEF;
+	priv->agg_tids_count = 0;
 
 	/* Choose which receivers/antennas to use */
 	if (priv->cfg->ops->hcmd->set_rxon_chain)
diff --git a/drivers/net/wireless/iwlwifi/iwl-dev.h b/drivers/net/wireless/iwlwifi/iwl-dev.h
index 71cf1558e640..f81317d478ee 100644
--- a/drivers/net/wireless/iwlwifi/iwl-dev.h
+++ b/drivers/net/wireless/iwlwifi/iwl-dev.h
@@ -1072,6 +1072,9 @@ struct iwl_priv {
 	/* storing the jiffies when the plcp error rate is received */
 	unsigned long plcp_jiffies;
 
+	/* reporting the number of tids has AGG on. 0 means no AGGREGATION */
+	u8 agg_tids_count;
+
 	/* force reset */
 	unsigned long last_force_reset_jiffies;
 
diff --git a/drivers/net/wireless/iwlwifi/iwl-rx.c b/drivers/net/wireless/iwlwifi/iwl-rx.c
index aba8f4c20c1b..fed554accedc 100644
--- a/drivers/net/wireless/iwlwifi/iwl-rx.c
+++ b/drivers/net/wireless/iwlwifi/iwl-rx.c
@@ -616,6 +616,11 @@ static void iwl_accumulative_statistics(struct iwl_priv *priv,
 
 #define REG_RECALIB_PERIOD (60)
 
+/* the threshold ratio of actual_ack_cnt to expected_ack_cnt in percent */
+#define ACK_CNT_RATIO (50)
+#define BA_TIMEOUT_CNT (5)
+#define BA_TIMEOUT_MAX (16)
+
 #define PLCP_MSG "plcp_err exceeded %u, %u, %u, %u, %u, %d, %u mSecs\n"
 void iwl_rx_statistics(struct iwl_priv *priv,
 			      struct iwl_rx_mem_buffer *rxb)
@@ -625,6 +630,9 @@ void iwl_rx_statistics(struct iwl_priv *priv,
 	int combined_plcp_delta;
 	unsigned int plcp_msec;
 	unsigned long plcp_received_jiffies;
+	int actual_ack_cnt_delta;
+	int expected_ack_cnt_delta;
+	int ba_timeout_delta;
 
 	IWL_DEBUG_RX(priv, "Statistics notification received (%d vs %d).\n",
 		     (int)sizeof(priv->statistics),
@@ -639,6 +647,44 @@ void iwl_rx_statistics(struct iwl_priv *priv,
 #ifdef CONFIG_IWLWIFI_DEBUG
 	iwl_accumulative_statistics(priv, (__le32 *)&pkt->u.stats);
 #endif
+	actual_ack_cnt_delta = le32_to_cpu(pkt->u.stats.tx.actual_ack_cnt) -
+		le32_to_cpu(priv->statistics.tx.actual_ack_cnt);
+	expected_ack_cnt_delta = le32_to_cpu(
+			pkt->u.stats.tx.expected_ack_cnt) -
+		le32_to_cpu(priv->statistics.tx.expected_ack_cnt);
+	ba_timeout_delta = le32_to_cpu(
+			pkt->u.stats.tx.agg.ba_timeout) -
+		le32_to_cpu(priv->statistics.tx.agg.ba_timeout);
+	if ((priv->agg_tids_count > 0) &&
+		(expected_ack_cnt_delta > 0) &&
+		(((actual_ack_cnt_delta * 100) / expected_ack_cnt_delta) <
+			ACK_CNT_RATIO) &&
+		(ba_timeout_delta > BA_TIMEOUT_CNT)) {
+		IWL_DEBUG_RADIO(priv,
+			"actual_ack_cnt delta = %d, expected_ack_cnt = %d\n",
+			actual_ack_cnt_delta, expected_ack_cnt_delta);
+
+#ifdef CONFIG_IWLWIFI_DEBUG
+		IWL_DEBUG_RADIO(priv, "rx_detected_cnt delta = %d\n",
+			priv->delta_statistics.tx.rx_detected_cnt);
+		IWL_DEBUG_RADIO(priv,
+			"ack_or_ba_timeout_collision delta = %d\n",
+			priv->delta_statistics.tx.ack_or_ba_timeout_collision);
+#endif
+		IWL_DEBUG_RADIO(priv, "agg ba_timeout delta = %d\n",
+			ba_timeout_delta);
+		if ((actual_ack_cnt_delta == 0) &&
+			(ba_timeout_delta >=
+				BA_TIMEOUT_MAX)) {
+			IWL_DEBUG_RADIO(priv,
+				"call iwl_force_reset(IWL_FW_RESET)\n");
+			iwl_force_reset(priv, IWL_FW_RESET);
+		} else {
+			IWL_DEBUG_RADIO(priv,
+				"call iwl_force_reset(IWL_RF_RESET)\n");
+			iwl_force_reset(priv, IWL_RF_RESET);
+		}
+	}
 	/*
 	 * check for plcp_err and trigger radio reset if it exceeds
 	 * the plcp error threshold plcp_delta.