ath10k: enable napi on RX path for sdio

For tcp RX, the quantity of tcp acks to remote is 1/2 of the quantity
of tcp data from remote, then it will have many small length packets
on TX path of sdio bus, then it reduce the RX packets's bandwidth of
tcp.

This patch enable napi on RX path, then the RX packet of tcp will not
feed to tcp stack immeditely from mac80211 since GRO is enabled by
default, it will feed to tcp stack after napi complete, if rx bundle
is enabled, then it will feed to tcp stack one time for each bundle
of RX. For example, RX bundle size is 32, then tcp stack will receive
one large length packet, its length is neary 1500*32, then tcp stack
will send a tcp ack for this large packet, this will reduce the tcp
acks ratio from 1/2 to 1/32. This results in significant performance
improvement for tcp RX.

Tcp rx throughout is 240Mbps without this patch, and it arrive 390Mbps
with this patch. The cpu usage has no obvious difference with and
without NAPI.

call stack for each RX packet on GRO path:
(skb length is about 1500 bytes)
  skb_gro_receive ([kernel.kallsyms])
  tcp4_gro_receive ([kernel.kallsyms])
  inet_gro_receive ([kernel.kallsyms])
  dev_gro_receive ([kernel.kallsyms])
  napi_gro_receive ([kernel.kallsyms])
  ieee80211_deliver_skb ([mac80211])
  ieee80211_rx_handlers ([mac80211])
  ieee80211_prepare_and_rx_handle ([mac80211])
  ieee80211_rx_napi ([mac80211])
  ath10k_htt_rx_proc_rx_ind_hl ([ath10k_core])
  ath10k_htt_rx_pktlog_completion_handler ([ath10k_core])
  ath10k_sdio_napi_poll ([ath10k_sdio])
  net_rx_action ([kernel.kallsyms])
  softirqentry_text_start ([kernel.kallsyms])
  do_softirq ([kernel.kallsyms])

call stack for napi complete and send tcp ack from tcp stack:
(skb length is about 1500*32 bytes)
 _tcp_ack_snd_check ([kernel.kallsyms])
 tcp_v4_do_rcv ([kernel.kallsyms])
 tcp_v4_rcv ([kernel.kallsyms])
 local_deliver_finish ([kernel.kallsyms])
 ip_local_deliver ([kernel.kallsyms])
 ip_rcv_finish ([kernel.kallsyms])
 ip_rcv ([kernel.kallsyms])
 netif_receive_skb_core ([kernel.kallsyms])
 netif_receive_skb_one_core([kernel.kallsyms])
 netif_receive_skb ([kernel.kallsyms])
 netif_receive_skb_internal ([kernel.kallsyms])
 napi_gro_complete ([kernel.kallsyms])
 napi_gro_flush ([kernel.kallsyms])
 napi_complete_done ([kernel.kallsyms])
 ath10k_sdio_napi_poll ([ath10k_sdio])
 net_rx_action ([kernel.kallsyms])
 __softirqentry_text_start ([kernel.kallsyms])
 do_softirq ([kernel.kallsyms])

Tested with QCA6174 SDIO with firmware
WLAN.RMH.4.4.1-00017-QCARMSWP-1.

Signed-off-by: Wen Gong <wgong@codeaurora.org>
Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

1 files changed, 28 insertions, 0 deletions

diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index b8e249909699..e36deda23644 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -1339,6 +1339,9 @@ static void ath10k_rx_indication_async_work(struct work_struct *work)
 		ep = &ar->htc.endpoint[cb->eid];
 		ep->ep_ops.ep_rx_complete(ar, skb);
 	}
+
+	if (test_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags))
+		napi_schedule(&ar->napi);
 }
 
 static void ath10k_sdio_write_async_work(struct work_struct *work)
@@ -1729,6 +1732,8 @@ static int ath10k_sdio_hif_start(struct ath10k *ar)
 	struct ath10k_sdio *ar_sdio = ath10k_sdio_priv(ar);
 	int ret;
 
+	napi_enable(&ar->napi);
+
 	/* Sleep 20 ms before HIF interrupts are disabled.
 	 * This will give target plenty of time to process the BMI done
 	 * request before interrupts are disabled.
@@ -1853,6 +1858,9 @@ static void ath10k_sdio_hif_stop(struct ath10k *ar)
 	}
 
 	spin_unlock_bh(&ar_sdio->wr_async_lock);
+
+	napi_synchronize(&ar->napi);
+	napi_disable(&ar->napi);
 }
 
 #ifdef CONFIG_PM
@@ -2047,6 +2055,20 @@ static SIMPLE_DEV_PM_OPS(ath10k_sdio_pm_ops, ath10k_sdio_pm_suspend,
 
 #endif /* CONFIG_PM_SLEEP */
 
+static int ath10k_sdio_napi_poll(struct napi_struct *ctx, int budget)
+{
+	struct ath10k *ar = container_of(ctx, struct ath10k, napi);
+	int done;
+
+	done = ath10k_htt_rx_hl_indication(ar, budget);
+	ath10k_dbg(ar, ATH10K_DBG_SDIO, "napi poll: done: %d, budget:%d\n", done, budget);
+
+	if (done < budget)
+		napi_complete_done(ctx, done);
+
+	return done;
+}
+
 static int ath10k_sdio_probe(struct sdio_func *func,
 			     const struct sdio_device_id *id)
 {
@@ -2072,6 +2094,9 @@ static int ath10k_sdio_probe(struct sdio_func *func,
 		return -ENOMEM;
 	}
 
+	netif_napi_add(&ar->napi_dev, &ar->napi, ath10k_sdio_napi_poll,
+		       ATH10K_NAPI_BUDGET);
+
 	ath10k_dbg(ar, ATH10K_DBG_BOOT,
 		   "sdio new func %d vendor 0x%x device 0x%x block 0x%x/0x%x\n",
 		   func->num, func->vendor, func->device,
@@ -2184,6 +2209,9 @@ static void ath10k_sdio_remove(struct sdio_func *func)
 		   func->num, func->vendor, func->device);
 
 	ath10k_core_unregister(ar);
+
+	netif_napi_del(&ar->napi);
+
 	ath10k_core_destroy(ar);
 
 	flush_workqueue(ar_sdio->workqueue);