From 6e712d427cb0542afdd5220edb6e4f4f8a5b952d Mon Sep 17 00:00:00 2001 From: Michal Kazior Date: Tue, 24 Sep 2013 10:18:36 +0200 Subject: [PATCH] ath10k: replenish HTT RX buffers in a tasklet This starves FW RX ring buffer in case of excessive RX. This prevents from CPU being overwhelmed by RX indications/completions by naturally forbiddin FW to submit more RX. This fixes RX starvation on slow machines when under heavy RX traffic. kvalo: remove extra newline Signed-off-by: Michal Kazior Signed-off-by: Kalle Valo --- drivers/net/wireless/ath/ath10k/htt.h | 6 ++++++ drivers/net/wireless/ath/ath10k/htt_rx.c | 35 +++++++++++++++++++++++++++++--- 2 files changed, 38 insertions(+), 3 deletions(-) diff --git a/drivers/net/wireless/ath/ath10k/htt.h b/drivers/net/wireless/ath/ath10k/htt.h index e090902..1a337e9 100644 --- a/drivers/net/wireless/ath/ath10k/htt.h +++ b/drivers/net/wireless/ath/ath10k/htt.h @@ -19,6 +19,7 @@ #define _HTT_H_ #include +#include #include "htc.h" #include "rx_desc.h" @@ -1268,6 +1269,7 @@ struct ath10k_htt { /* set if host-fw communication goes haywire * used to avoid further failures */ bool rx_confused; + struct tasklet_struct rx_replenish_task; }; #define RX_HTT_HDR_STATUS_LEN 64 @@ -1308,6 +1310,10 @@ struct htt_rx_desc { #define HTT_RX_BUF_SIZE 1920 #define HTT_RX_MSDU_SIZE (HTT_RX_BUF_SIZE - (int)sizeof(struct htt_rx_desc)) +/* Refill a bunch of RX buffers for each refill round so that FW/HW can handle + * aggregated traffic more nicely. */ +#define ATH10K_HTT_MAX_NUM_REFILL 16 + /* * DMA_MAP expects the buffer to be an integral number of cache lines. * Rather than checking the actual cache line size, this code makes a diff --git a/drivers/net/wireless/ath/ath10k/htt_rx.c b/drivers/net/wireless/ath/ath10k/htt_rx.c index c4637f1..90d4f74 100644 --- a/drivers/net/wireless/ath/ath10k/htt_rx.c +++ b/drivers/net/wireless/ath/ath10k/htt_rx.c @@ -182,10 +182,27 @@ static int ath10k_htt_rx_ring_fill_n(struct ath10k_htt *htt, int num) static void ath10k_htt_rx_msdu_buff_replenish(struct ath10k_htt *htt) { - int ret, num_to_fill; + int ret, num_deficit, num_to_fill; + /* Refilling the whole RX ring buffer proves to be a bad idea. The + * reason is RX may take up significant amount of CPU cycles and starve + * other tasks, e.g. TX on an ethernet device while acting as a bridge + * with ath10k wlan interface. This ended up with very poor performance + * once CPU the host system was overwhelmed with RX on ath10k. + * + * By limiting the number of refills the replenishing occurs + * progressively. This in turns makes use of the fact tasklets are + * processed in FIFO order. This means actual RX processing can starve + * out refilling. If there's not enough buffers on RX ring FW will not + * report RX until it is refilled with enough buffers. This + * automatically balances load wrt to CPU power. + * + * This probably comes at a cost of lower maximum throughput but + * improves the avarage and stability. */ spin_lock_bh(&htt->rx_ring.lock); - num_to_fill = htt->rx_ring.fill_level - htt->rx_ring.fill_cnt; + num_deficit = htt->rx_ring.fill_level - htt->rx_ring.fill_cnt; + num_to_fill = min(ATH10K_HTT_MAX_NUM_REFILL, num_deficit); + num_deficit -= num_to_fill; ret = ath10k_htt_rx_ring_fill_n(htt, num_to_fill); if (ret == -ENOMEM) { /* @@ -196,6 +213,8 @@ static void ath10k_htt_rx_msdu_buff_replenish(struct ath10k_htt *htt) */ mod_timer(&htt->rx_ring.refill_retry_timer, jiffies + msecs_to_jiffies(HTT_RX_RING_REFILL_RETRY_MS)); + } else if (num_deficit > 0) { + tasklet_schedule(&htt->rx_replenish_task); } spin_unlock_bh(&htt->rx_ring.lock); } @@ -217,6 +236,7 @@ void ath10k_htt_rx_detach(struct ath10k_htt *htt) int sw_rd_idx = htt->rx_ring.sw_rd_idx.msdu_payld; del_timer_sync(&htt->rx_ring.refill_retry_timer); + tasklet_kill(&htt->rx_replenish_task); while (sw_rd_idx != __le32_to_cpu(*(htt->rx_ring.alloc_idx.vaddr))) { struct sk_buff *skb = @@ -446,6 +466,12 @@ static int ath10k_htt_rx_amsdu_pop(struct ath10k_htt *htt, return msdu_chaining; } +static void ath10k_htt_rx_replenish_task(unsigned long ptr) +{ + struct ath10k_htt *htt = (struct ath10k_htt *)ptr; + ath10k_htt_rx_msdu_buff_replenish(htt); +} + int ath10k_htt_rx_attach(struct ath10k_htt *htt) { dma_addr_t paddr; @@ -506,6 +532,9 @@ int ath10k_htt_rx_attach(struct ath10k_htt *htt) if (__ath10k_htt_rx_ring_fill_n(htt, htt->rx_ring.fill_level)) goto err_fill_ring; + tasklet_init(&htt->rx_replenish_task, ath10k_htt_rx_replenish_task, + (unsigned long)htt); + ath10k_dbg(ATH10K_DBG_BOOT, "htt rx ring size %d fill_level %d\n", htt->rx_ring.size, htt->rx_ring.fill_level); return 0; @@ -956,7 +985,7 @@ static void ath10k_htt_rx_handler(struct ath10k_htt *htt, } } - ath10k_htt_rx_msdu_buff_replenish(htt); + tasklet_schedule(&htt->rx_replenish_task); } static void ath10k_htt_rx_frag_handler(struct ath10k_htt *htt, -- 2.7.4