iwlwifi: add a W/A for a scheduler hardware bug

In case we need to move the scheduler write pointer by
steps of 0x40, 0x80 or 0xc0, the scheduler gets stuck.
This leads to hardware error interrupts with status:
0x5A5A5A5A or alike.

In order to work around this, detect in the transport
layer that we are going to hit this case and tell iwlmvm
to increment the sequence number of the packets. This
allows to keep the requirement that the WiFi sequence
number is in sync with the index in the scheduler Tx queue
and it also allows to avoid the problematic sequence.
This means that from time to time, we will start a queue
from ssn + 1, but that shouldn't be a problem since we
don't switch to new queues for AMPDU now that we have
DQA which allows to keep the same queue while toggling
the AMPDU state.

This bug has been fixed on 9000 devices and up.

Signed-off-by: Emmanuel Grumbach <emmanuel.grumbach@intel.com>
Signed-off-by: Luca Coelho <luciano.coelho@intel.com>

3 files changed, 42 insertions, 27 deletions

diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
index e616472afd45..7171928872de 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/mvm.h
@@ -1744,7 +1744,7 @@ static inline bool iwl_mvm_vif_low_latency(struct iwl_mvm_vif *mvmvif)
 }
 
 /* hw scheduler queue config */
-void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
+bool iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 			u16 ssn, const struct iwl_trans_txq_scd_cfg *cfg,
 			unsigned int wdg_timeout);
 int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm, int mac80211_queue,
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
index 0249300c4600..aa41ee8ed916 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/sta.c
@@ -758,7 +758,7 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	bool using_inactive_queue = false, same_sta = false;
 	unsigned long disable_agg_tids = 0;
 	enum iwl_mvm_agg_state queue_state;
-	bool shared_queue = false;
+	bool shared_queue = false, inc_ssn;
 	int ssn;
 	unsigned long tfd_queue_mask;
 	int ret;
@@ -885,8 +885,12 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 	}
 
 	ssn = IEEE80211_SEQ_TO_SN(le16_to_cpu(hdr->seq_ctrl));
-	iwl_mvm_enable_txq(mvm, queue, mac_queue, ssn, &cfg,
-			   wdg_timeout);
+	inc_ssn = iwl_mvm_enable_txq(mvm, queue, mac_queue,
+				     ssn, &cfg, wdg_timeout);
+	if (inc_ssn) {
+		ssn = (ssn + 1) & IEEE80211_SCTL_SEQ;
+		le16_add_cpu(&hdr->seq_ctrl, 0x10);
+	}
 
 	/*
 	 * Mark queue as shared in transport if shared
@@ -898,6 +902,13 @@ static int iwl_mvm_sta_alloc_queue(struct iwl_mvm *mvm,
 		iwl_trans_txq_set_shared_mode(mvm->trans, queue, true);
 
 	spin_lock_bh(&mvmsta->lock);
+	/*
+	 * This looks racy, but it is not. We have only one packet for
+	 * this ra/tid in our Tx path since we stop the Qdisc when we
+	 * need to allocate a new TFD queue.
+	 */
+	if (inc_ssn)
+		mvmsta->tid_data[tid].seq_number += 0x10;
 	mvmsta->tid_data[tid].txq_id = queue;
 	mvmsta->tid_data[tid].is_tid_active = true;
 	mvmsta->tfd_queue_msk |= BIT(queue);
diff --git a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
index 8ba8b71dd1a4..0093e78dd571 100644
--- a/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
+++ b/drivers/net/wireless/intel/iwlwifi/mvm/utils.c
@@ -757,35 +757,39 @@ int iwl_mvm_tvqm_enable_txq(struct iwl_mvm *mvm, int mac80211_queue,
 	return queue;
 }
 
-void iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
+bool iwl_mvm_enable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,
 			u16 ssn, const struct iwl_trans_txq_scd_cfg *cfg,
 			unsigned int wdg_timeout)
 {
+	struct iwl_scd_txq_cfg_cmd cmd = {
+		.scd_queue = queue,
+		.action = SCD_CFG_ENABLE_QUEUE,
+		.window = cfg->frame_limit,
+		.sta_id = cfg->sta_id,
+		.ssn = cpu_to_le16(ssn),
+		.tx_fifo = cfg->fifo,
+		.aggregate = cfg->aggregate,
+		.tid = cfg->tid,
+	};
+	bool inc_ssn;
+
 	if (WARN_ON(iwl_mvm_has_new_tx_api(mvm)))
-		return;
+		return false;
 
 	/* Send the enabling command if we need to */
-	if (iwl_mvm_update_txq_mapping(mvm, queue, mac80211_queue,
-				       cfg->sta_id, cfg->tid)) {
-		struct iwl_scd_txq_cfg_cmd cmd = {
-			.scd_queue = queue,
-			.action = SCD_CFG_ENABLE_QUEUE,
-			.window = cfg->frame_limit,
-			.sta_id = cfg->sta_id,
-			.ssn = cpu_to_le16(ssn),
-			.tx_fifo = cfg->fifo,
-			.aggregate = cfg->aggregate,
-			.tid = cfg->tid,
-		};
-
-		iwl_trans_txq_enable_cfg(mvm->trans, queue, ssn, NULL,
-					 wdg_timeout);
-		WARN(iwl_mvm_send_cmd_pdu(mvm, SCD_QUEUE_CFG, 0,
-					  sizeof(struct iwl_scd_txq_cfg_cmd),
-					  &cmd),
-		     "Failed to configure queue %d on FIFO %d\n", queue,
-		     cfg->fifo);
-	}
+	if (!iwl_mvm_update_txq_mapping(mvm, queue, mac80211_queue,
+					cfg->sta_id, cfg->tid))
+		return false;
+
+	inc_ssn = iwl_trans_txq_enable_cfg(mvm->trans, queue, ssn,
+					   NULL, wdg_timeout);
+	if (inc_ssn)
+		le16_add_cpu(&cmd.ssn, 1);
+
+	WARN(iwl_mvm_send_cmd_pdu(mvm, SCD_QUEUE_CFG, 0, sizeof(cmd), &cmd),
+	     "Failed to configure queue %d on FIFO %d\n", queue, cfg->fifo);
+
+	return inc_ssn;
 }
 
 int iwl_mvm_disable_txq(struct iwl_mvm *mvm, int queue, int mac80211_queue,