ath10k: implement NAPI support

Add NAPI support for rx and tx completion. NAPI poll is scheduled
from interrupt handler. The design is as below

 - on interrupt
     - schedule napi and mask interrupts
 - on poll
   - process all pipes (no actual Tx/Rx)
   - process Rx within budget
   - if quota exceeds budget reschedule napi poll by returning budget
   - process Tx completions and update budget if necessary
   - process Tx fetch indications (pull-push)
   - push any other pending Tx (if possible)
   - before resched or napi completion replenish htt rx ring buffer
   - if work done < budget, complete napi poll and unmask interrupts

This change also get rid of two tasklets (intr_tq and txrx_compl_task).

Measured peak throughput with NAPI on IPQ4019 platform in controlled
environment. No noticeable reduction in throughput is seen and also
observed improvements in CPU usage. Approx. 15% CPU usage got reduced
in UDP uplink case.

DL: AP DUT Tx
UL: AP DUT Rx

IPQ4019 (avg. cpu usage %)

========
                TOT              +NAPI
              ===========      =============
TCP DL       644 Mbps (42%)    645 Mbps (36%)
TCP UL       673 Mbps (30%)    675 Mbps (26%)
UDP DL       682 Mbps (49%)    680 Mbps (49%)
UDP UL       720 Mbps (28%)    717 Mbps (11%)

Signed-off-by: Rajkumar Manoharan <rmanohar@qti.qualcomm.com>
Signed-off-by: Kalle Valo <kvalo@qca.qualcomm.com>

drivers/net/wireless/ath/ath10k/ahb.c

@@ -462,13 +462,13 @@ static void ath10k_ahb_halt_chip(struct ath10k *ar)
 static irqreturn_t ath10k_ahb_interrupt_handler(int irq, void *arg)
 {
 	struct ath10k *ar = arg;
-	struct ath10k_pci *ar_pci = ath10k_pci_priv(ar);
 
 	if (!ath10k_pci_irq_pending(ar))
 		return IRQ_NONE;
 
 	ath10k_pci_disable_and_clear_legacy_irq(ar);
-	tasklet_schedule(&ar_pci->intr_tq);
+	ath10k_pci_irq_msi_fw_mask(ar);
+	napi_schedule(&ar->napi);
 
 	return IRQ_HANDLED;
 }
@@ -717,6 +717,9 @@ static void ath10k_ahb_hif_stop(struct ath10k *ar)
 	synchronize_irq(ar_ahb->irq);
 
 	ath10k_pci_flush(ar);
+
+	napi_synchronize(&ar->napi);
+	napi_disable(&ar->napi);
 }
 
 static int ath10k_ahb_hif_power_up(struct ath10k *ar)
@@ -748,6 +751,7 @@ static int ath10k_ahb_hif_power_up(struct ath10k *ar)
 		ath10k_err(ar, "could not wake up target CPU: %d\n", ret);
 		goto err_ce_deinit;
 	}
+	napi_enable(&ar->napi);
 
 	return 0;
 
@@ -831,7 +835,7 @@ static int ath10k_ahb_probe(struct platform_device *pdev)
 		goto err_resource_deinit;
 	}
 
-	ath10k_pci_init_irq_tasklets(ar);
+	ath10k_pci_init_napi(ar);
 
 	ret = ath10k_ahb_request_irq_legacy(ar);
 	if (ret)

drivers/net/wireless/ath/ath10k/core.c

@@ -2322,6 +2322,8 @@ struct ath10k *ath10k_core_create(size_t priv_size, struct device *dev,
 	INIT_WORK(&ar->register_work, ath10k_core_register_work);
 	INIT_WORK(&ar->restart_work, ath10k_core_restart);
 
+	init_dummy_netdev(&ar->napi_dev);
+
 	ret = ath10k_debug_create(ar);
 	if (ret)
 		goto err_free_aux_wq;

drivers/net/wireless/ath/ath10k/core.h

@@ -65,6 +65,10 @@
 #define ATH10K_KEEPALIVE_MAX_IDLE 3895
 #define ATH10K_KEEPALIVE_MAX_UNRESPONSIVE 3900
 
+/* NAPI poll budget */
+#define ATH10K_NAPI_BUDGET      64
+#define ATH10K_NAPI_QUOTA_LIMIT 60
+
 struct ath10k;
 
 enum ath10k_bus {
@@ -954,6 +958,10 @@ struct ath10k {
 	struct ath10k_thermal thermal;
 	struct ath10k_wow wow;
 
+	/* NAPI */
+	struct net_device napi_dev;
+	struct napi_struct napi;
+
 	/* must be last */
 	u8 drv_priv[0] __aligned(sizeof(void *));
 };

drivers/net/wireless/ath/ath10k/htt.h

@@ -1665,7 +1665,6 @@ struct ath10k_htt {
 
 	/* This is used to group tx/rx completions separately and process them
 	 * in batches to reduce cache stalls */
-	struct tasklet_struct txrx_compl_task;
 	struct sk_buff_head rx_compl_q;
 	struct sk_buff_head rx_in_ord_compl_q;
 	struct sk_buff_head tx_fetch_ind_q;
@@ -1798,5 +1797,6 @@ int ath10k_htt_tx(struct ath10k_htt *htt,
 		  struct sk_buff *msdu);
 void ath10k_htt_rx_pktlog_completion_handler(struct ath10k *ar,
 					     struct sk_buff *skb);
+int ath10k_htt_txrx_compl_task(struct ath10k *ar, int budget);
 
 #endif