Re: [PATCH] Repair soft lockup with monitor mode of ath9k_htc card

From: Oleksij Rempel
Date: Fri Jan 30 2015 - 05:56:20 EST

Am 29.01.2015 um 00:14 schrieb yuweizheng@xxxxxxx:
> From: Yuwei Zheng <yuweizheng@xxxxxxx>
>
> In the environment with heavy wifi traffic, set the ar9271 into monitor mode, will
> trigger a deadloop panic.
>
> The ath9k_hif_usb_rx_cb function excute on the interrupt context, and ath9k_rx_tasklet excute
> on the soft irq context. In other words, the ath9k_hif_usb_rx_cb have more chance to excute than
> ath9k_rx_tasklet. So in the worst condition, the rx.rxbuf receive list is always full,
> and the do {}while(true) loop will not be break. The kernel get a soft lockup panic.

Please note, ath9k_htc is also used on HW where real hrtimer actually
exist. It should behave differently and produce different load on the
system. The overhead of setting up the hrtimers *may* not be worth it.
Depending on the load, it may provide lots of avoidable interrupts.
Did you tried to use simple tasklet_start?

> [59011.007210] BUG: soft lockup - CPU#0 stuck for 23s!
> [kworker/0:0:30609]
> [59011.030560] BUG: scheduling while atomic: kworker/0:0/30609/0x40010100
> [59013.804486] BUG: scheduling while atomic: kworker/0:0/30609/0x40010100
> [59013.858522] Kernel panic - not syncing: softlockup: hung tasks
>
> [59014.038891] Exception stack(0xdf4bbc38 to 0xdf4bbc80)
> [59014.046834] bc20: de57b950 60000113
> [59014.059579] bc40: 00000000 bb32bb32 60000113 de57b948 de57b500 dc7bb440 df4bbcd0 00000000
> [59014.072337] bc60: de57b950 60000113 df4bbcd0 df4bbc80 c04c259d c04c25a0 60000133 ffffffff
> [59014.085233] [<c04c28db>] (__irq_svc+0x3b/0x5c) from [<c04c25a0>] (_raw_spin_unlock_irqrestore+0xc/0x10)
> [59014.100437] [<c04c25a0>] (_raw_spin_unlock_irqrestore+0xc/0x10) from [<bf9c2089>] (ath9k_rx_tasklet+0x290/0x490 [ath9k_htc])
> [59014.118267] [<bf9c2089>] (ath9k_rx_tasklet+0x290/0x490 [ath9k_htc]) from [<c0036d23>] (tasklet_action+0x3b/0x98)
> [59014.134132] [<c0036d23>] (tasklet_action+0x3b/0x98) from [<c0036709>] (__do_softirq+0x99/0x16c)
> [59014.147784] [<c0036709>] (__do_softirq+0x99/0x16c) from [<c00369f7>] (irq_exit+0x5b/0x5c)
> [59014.160653] [<c00369f7>] (irq_exit+0x5b/0x5c) from [<c000cfc3>] (handle_IRQ+0x37/0x78)
> [59014.173124] [<c000cfc3>] (handle_IRQ+0x37/0x78) from [<c00085df>] (omap3_intc_handle_irq+0x5f/0x68)
> [59014.187225] [<c00085df>] (omap3_intc_handle_irq+0x5f/0x68) from [<c04c28db>](__irq_svc+0x3b/0x5c)
>
> This bug can be see with low performance board, such as uniprocessor beagle bone board.
>
>
> Signed-off-by: Yuwei Zheng <zhengyuwei@xxxxxx>
> Signed-off-by: Yuwei Zheng <yuweizheng@xxxxxxx>
>
>
> ---
> drivers/net/wireless/ath/ath9k/hif_usb.c | 58 ++++++++++++++++++++++----
> drivers/net/wireless/ath/ath9k/hif_usb.h | 5 +++
> drivers/net/wireless/ath/ath9k/htc.h | 13 ++++++
> drivers/net/wireless/ath/ath9k/htc_drv_debug.c | 49 ++++++++++++++++++++++
> drivers/net/wireless/ath/ath9k/htc_drv_txrx.c | 26 ++++++++++++
> 5 files changed, 144 insertions(+), 7 deletions(-)
>
> diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.c b/drivers/net/wireless/ath/ath9k/hif_usb.c
> index 8e7153b..18c6f0e 100644
> --- a/drivers/net/wireless/ath/ath9k/hif_usb.c
> +++ b/drivers/net/wireless/ath/ath9k/hif_usb.c
> @@ -658,7 +658,6 @@ static void ath9k_hif_usb_rx_cb(struct urb *urb)
> default:
> goto resubmit;
> }
> -
> if (likely(urb->actual_length != 0)) {
> skb_put(skb, urb->actual_length);
> ath9k_hif_usb_rx_stream(hif_dev, skb);
> @@ -667,12 +666,18 @@ static void ath9k_hif_usb_rx_cb(struct urb *urb)
> resubmit:
> skb_reset_tail_pointer(skb);
> skb_trim(skb, 0);
> -
> - usb_anchor_urb(urb, &hif_dev->rx_submitted);
> - ret = usb_submit_urb(urb, GFP_ATOMIC);
> - if (ret) {
> - usb_unanchor_urb(urb);
> - goto free;
> + if (atomic_read(&hif_dev->rx_urb_submit_delay) > 0) {
> + usb_anchor_urb(urb, &hif_dev->rx_delayed_submitted);
> + ret = tasklet_hrtimer_start(&hif_dev->rx_submit_timer,
> + ktime_set(0, atomic_read(&hif_dev->rx_urb_submit_delay)*1000),
> + HRTIMER_MODE_REL);
> + } else {
> + usb_anchor_urb(urb, &hif_dev->rx_submitted);
> + ret = usb_submit_urb(urb, GFP_ATOMIC);
> + if (ret) {
> + usb_unanchor_urb(urb);
> + goto free;
> + }
> }
>
> return;
> @@ -818,9 +823,39 @@ err:
> return -ENOMEM;
> }
>
> +static enum hrtimer_restart rx_urb_submit_timer_handler(struct hrtimer *me)
> +{
> + struct tasklet_hrtimer *thr =
> + container_of(me, struct tasklet_hrtimer, timer);
> + struct hif_device_usb *hif_dev =
> + container_of(thr, struct hif_device_usb, rx_submit_timer);
> + struct urb *urb = NULL;
> + struct sk_buff *skb = NULL;
> + int ret;
> +
> + while (true) {
> + urb = usb_get_from_anchor(&hif_dev->rx_delayed_submitted);
> + if (urb != NULL) {
> + skb = (struct sk_buff *)urb->context;
> + ret = usb_submit_urb(urb, GFP_ATOMIC);
> + if (ret != -EBUSY) {
> + usb_unanchor_urb(urb);
> + dev_kfree_skb_any(skb);
> + urb->context = NULL;
> + }
> + } else {
> + break;
> + }
> + }
> +
> + return HRTIMER_NORESTART;
> +}
> +
> static void ath9k_hif_usb_dealloc_rx_urbs(struct hif_device_usb *hif_dev)
> {
> usb_kill_anchored_urbs(&hif_dev->rx_submitted);
> + usb_kill_anchored_urbs(&hif_dev->rx_delayed_submitted);
> + tasklet_hrtimer_cancel(&hif_dev->rx_submit_timer);
> }
>
> static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
> @@ -830,6 +865,8 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
> int i, ret;
>
> init_usb_anchor(&hif_dev->rx_submitted);
> + init_usb_anchor(&hif_dev->rx_delayed_submitted);
> +
> spin_lock_init(&hif_dev->rx_lock);
>
> for (i = 0; i < MAX_RX_URB_NUM; i++) {
> @@ -871,6 +908,13 @@ static int ath9k_hif_usb_alloc_rx_urbs(struct hif_device_usb *hif_dev)
> usb_free_urb(urb);
> }
>
> + /* add for flow control*/
> + atomic_set(&hif_dev->rx_urb_submit_delay, 0);
> + tasklet_hrtimer_init(&hif_dev->rx_submit_timer,
> + rx_urb_submit_timer_handler,
> + CLOCK_MONOTONIC,
> + HRTIMER_MODE_REL);
> +
> return 0;
>
> err_submit:
> diff --git a/drivers/net/wireless/ath/ath9k/hif_usb.h b/drivers/net/wireless/ath/ath9k/hif_usb.h
> index 51496e7..56d6be8 100644
> --- a/drivers/net/wireless/ath/ath9k/hif_usb.h
> +++ b/drivers/net/wireless/ath/ath9k/hif_usb.h
> @@ -98,9 +98,14 @@ struct hif_device_usb {
> struct hif_usb_tx tx;
> struct usb_anchor regout_submitted;
> struct usb_anchor rx_submitted;
> + struct usb_anchor rx_delayed_submitted; /* delayed submit anchor */
> struct usb_anchor reg_in_submitted;
> struct usb_anchor mgmt_submitted;
> struct sk_buff *remain_skb;
> +
> + struct tasklet_hrtimer rx_submit_timer;/* delayed submit hrtimer */
> + atomic_t rx_urb_submit_delay; /*us*/
> +
> const char *fw_name;
> int rx_remain_len;
> int rx_pkt_len;
> diff --git a/drivers/net/wireless/ath/ath9k/htc.h b/drivers/net/wireless/ath/ath9k/htc.h
> index 9dde265..453d0a8 100644
> --- a/drivers/net/wireless/ath/ath9k/htc.h
> +++ b/drivers/net/wireless/ath/ath9k/htc.h
> @@ -331,6 +331,10 @@ static inline struct ath9k_htc_tx_ctl *HTC_SKB_CB(struct sk_buff *skb)
>
> #define TX_QSTAT_INC(q) (priv->debug.tx_stats.queue_stats[q]++)
>
> +#define TASKLETRX_STAT_INC(c) (hif_dev->htc_handle->drv_priv->debug.taskletrx_stats.c++)
> +#define TASKLETRX_STAT_ADD(c, a) (hif_dev->htc_handle->drv_priv->debug.taskletrx_stats.c += a)
> +#define TASKLETRX_STAT_SET(c, a) (hif_dev->htc_handle->drv_priv->debug.taskletrx_stats.c = a)
> +
> void ath9k_htc_err_stat_rx(struct ath9k_htc_priv *priv,
> struct ath_rx_status *rs);
>
> @@ -352,11 +356,20 @@ struct ath_skbrx_stats {
> u32 skb_dropped;
> };
>
> +struct ath_taskletrx_stats {
> + u32 taskletrx_looptimes;
> + u32 taskletrx_highwater;
> + u32 taskletrx_lowwater;
> + u32 taskletrx_watermark_triggered;
> + u32 taskletrx_urb_submit_delay;
> +};
> +
> struct ath9k_debug {
> struct dentry *debugfs_phy;
> struct ath_tx_stats tx_stats;
> struct ath_rx_stats rx_stats;
> struct ath_skbrx_stats skbrx_stats;
> + struct ath_taskletrx_stats taskletrx_stats;
> };
>
> void ath9k_htc_get_et_strings(struct ieee80211_hw *hw,
> diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
> index 8cef1ed..7c8322e 100644
> --- a/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
> +++ b/drivers/net/wireless/ath/ath9k/htc_drv_debug.c
> @@ -286,6 +286,51 @@ static const struct file_operations fops_skb_rx = {
> .llseek = default_llseek,
> };
>
> +static ssize_t read_file_tasklet_rx(struct file *file, char __user *user_buf,
> + size_t count, loff_t *ppos)
> +{
> + struct ath9k_htc_priv *priv = file->private_data;
> + char *buf;
> + unsigned int len = 0, size = 1500;
> + ssize_t retval = 0;
> +
> + buf = kzalloc(size, GFP_KERNEL);
> + if (buf == NULL)
> + return -ENOMEM;
> +
> + len += scnprintf(buf + len, size - len,
> + "%20s : %10u\n", "Loop times",
> + priv->debug.taskletrx_stats.taskletrx_looptimes);
> + len += scnprintf(buf + len, size - len,
> + "%20s : %10u\n", "High watermark",
> + priv->debug.taskletrx_stats.taskletrx_highwater);
> + len += scnprintf(buf + len, size - len,
> + "%20s : %10u\n", "Low watermark",
> + priv->debug.taskletrx_stats.taskletrx_lowwater);
> +
> + len += scnprintf(buf + len, size - len,
> + "%20s : %10u\n", "WM triggered",
> + priv->debug.taskletrx_stats.taskletrx_watermark_triggered);
> +
> + len += scnprintf(buf + len, size - len,
> + "%20s : %10u\n", "URB delay",
> + priv->debug.taskletrx_stats.taskletrx_urb_submit_delay);
> + if (len > size)
> + len = size;
> +
> + retval = simple_read_from_buffer(user_buf, count, ppos, buf, len);
> + kfree(buf);
> +
> + return retval;
> +}
> +
> +static const struct file_operations fops_tasklet_rx = {
> + .read = read_file_tasklet_rx,
> + .open = simple_open,
> + .owner = THIS_MODULE,
> + .llseek = default_llseek,
> +};
> +
> static ssize_t read_file_slot(struct file *file, char __user *user_buf,
> size_t count, loff_t *ppos)
> {
> @@ -518,7 +563,11 @@ int ath9k_htc_init_debug(struct ath_hw *ah)
> debugfs_create_file("skb_rx", S_IRUSR, priv->debug.debugfs_phy,
> priv, &fops_skb_rx);
>
> + debugfs_create_file("tasklet_rx", S_IRUSR, priv->debug.debugfs_phy,
> + priv, &fops_tasklet_rx);
> +
> ath9k_cmn_debug_recv(priv->debug.debugfs_phy, &priv->debug.rx_stats);
> +
> ath9k_cmn_debug_phy_err(priv->debug.debugfs_phy, &priv->debug.rx_stats);
>
> debugfs_create_file("slot", S_IRUSR, priv->debug.debugfs_phy,
> diff --git a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
> index a0f58e2..f5e6217 100644
> --- a/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
> +++ b/drivers/net/wireless/ath/ath9k/htc_drv_txrx.c
> @@ -1061,7 +1061,28 @@ void ath9k_rx_tasklet(unsigned long data)
> unsigned long flags;
> struct ieee80211_hdr *hdr;
>
> + /* add for adaptive flow control*/
> + int looptimes = 0;
> + int highwatermark = ATH9K_HTC_RXBUF*3/4;
> + int lowwatermark = ATH9K_HTC_RXBUF/4;
> + unsigned int delay = 0;
> +
> + struct htc_target *htc = priv->htc;
> + struct hif_device_usb *hif_dev = htc->hif_dev;
> +
> + TASKLETRX_STAT_SET(taskletrx_highwater, highwatermark);
> + TASKLETRX_STAT_SET(taskletrx_lowwater, lowwatermark);
> +
> do {
> + looptimes++;
> + TASKLETRX_STAT_SET(taskletrx_looptimes, looptimes);
> + if (looptimes > highwatermark) {
> + delay = looptimes*10;
> + atomic_set(&hif_dev->rx_urb_submit_delay, delay);
> + TASKLETRX_STAT_INC(taskletrx_watermark_triggered);
> + TASKLETRX_STAT_SET(taskletrx_urb_submit_delay, delay);
> + }
> +
> spin_lock_irqsave(&priv->rx.rxbuflock, flags);
> list_for_each_entry(tmp_buf, &priv->rx.rxbuf, list) {
> if (tmp_buf->in_process) {
> @@ -1072,6 +1093,11 @@ void ath9k_rx_tasklet(unsigned long data)
>
> if (rxbuf == NULL) {
> spin_unlock_irqrestore(&priv->rx.rxbuflock, flags);
> + if (looptimes < lowwatermark) {
> + atomic_set(&hif_dev->rx_urb_submit_delay, 0);
> + TASKLETRX_STAT_SET(taskletrx_urb_submit_delay, 0);
> + }
> +
> break;
> }
>
>


--
Regards,
Oleksij

Attachment: signature.asc
Description: OpenPGP digital signature