mt76usb: fix tx/rx stop

Disabling tasklets on stopping rx/tx is wrong. If blocked tasklet
is scheduled and we remove device we will get 100% cpu usage:

  PID USER      PR  NI    VIRT    RES    SHR S  %CPU  %MEM     TIME+ COMMAND
    9 root      20   0       0      0      0 R  93.8   0.0   1:47.19 ksoftirqd/0

by infinite loop in tasklet_action_common() and eventuall crash on next
mt76usb module load:

[ 2068.591964] RIP: 0010:tasklet_action_common.isra.17+0x66/0x100
[ 2068.591966] Code: 41 89 f5 eb 25 f0 48 0f ba 33 00 0f 83 b1 00 00 00 48 8b 7a 20 48 8b 42 18 e8 56 a3 b5 00 f0 80 23 fd 48 89 ea 48 85 ed 74 53 <48> 8b 2a 48 8d 5a 08 f0 48 0f ba 6a 08 01 72 0b 8b 42 10 85 c0 74
[ 2068.591968] RSP: 0018:ffff98758c34be58 EFLAGS: 00010206
[ 2068.591969] RAX: ffff98758e6966d0 RBX: ffff98756e69aef8 RCX: 0000000000000006
[ 2068.591970] RDX: 01060a053d060305 RSI: 0000000000000006 RDI: ffff98758e6966d0
[ 2068.591971] RBP: 01060a053d060305 R08: 0000000000000000 R09: 00000000000203c0
[ 2068.591971] R10: 000003ff65b34f08 R11: 0000000000000001 R12: ffff98758e6966d0
[ 2068.591972] R13: 0000000000000006 R14: 0000000000000040 R15: 0000000000000006
[ 2068.591974] FS:  0000000000000000(0000) GS:ffff98758e680000(0000) knlGS:0000000000000000
[ 2068.591975] CS:  0010 DS: 0000 ES: 0000 CR0: 0000000080050033
[ 2068.591975] CR2: 00002c5f73a6cc20 CR3: 00000002f920a001 CR4: 00000000003606e0
[ 2068.591977] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000
[ 2068.591978] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400
[ 2068.591978] Call Trace:
[ 2068.591985]  __do_softirq+0xe3/0x30a
[ 2068.591989]  ? sort_range+0x20/0x20
[ 2068.591990]  run_ksoftirqd+0x26/0x40
[ 2068.591992]  smpboot_thread_fn+0xc5/0x160
[ 2068.591995]  kthread+0x112/0x130
[ 2068.591997]  ? kthread_create_on_node+0x40/0x40
[ 2068.591998]  ret_from_fork+0x35/0x40
[ 2068.591999] Modules linked in: ccm arc4 fuse rfcomm cmac bnep sunrpc snd_hda_codec_hdmi snd_soc_skl snd_soc_core snd_soc_acpi_intel_match snd_hda_codec_realtek snd_soc_acpi snd_hda_codec_generic snd_soc_skl_ipc snd_soc_sst_ipc snd_soc_sst_dsp snd_hda_ext_core iTCO_wdt snd_hda_intel intel_rapl iTCO_vendor_support x86_pkg_temp_thermal intel_powerclamp btusb mei_wdt coretemp btrtl snd_hda_codec btbcm btintel intel_cstate snd_hwdep intel_uncore uvcvideo snd_hda_core videobuf2_vmalloc videobuf2_memops intel_rapl_perf wmi_bmof videobuf2_v4l2 intel_wmi_thunderbolt snd_seq bluetooth joydev videobuf2_common snd_seq_device snd_pcm videodev media i2c_i801 snd_timer idma64 ecdh_generic intel_lpss_pci intel_lpss mei_me mei ucsi_acpi typec_ucsi processor_thermal_device intel_soc_dts_iosf intel_pch_thermal typec thinkpad_acpi wmi snd soundcore rfkill int3403_thermal int340x_thermal_zone int3400_thermal acpi_thermal_rel acpi_pad pcc_cpufreq uas usb_storage crc32c_intel i915 i2c_algo_bit nvme serio_raw
[ 2068.592033]  drm_kms_helper e1000e nvme_core drm video ipv6 [last unloaded: cfg80211]

Fortunate thing is that this not happen frequently, as scheduling
tasklet on blocked state is very exceptional, though might happen.

Due to different RX/TX tasklet processing fix is different for those.

For RX we have to assure rx_tasklet do fail to resubmit buffers
by poisoning urb's and kill the tasklet.

For TX we need to handle all stop cases properly (suspend, module
unload, device removal).

Signed-off-by: Stanislaw Gruszka <sgruszka@redhat.com>
Signed-off-by: Felix Fietkau <nbd@nbd.name>

diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index 60b86ca00b3dd6d0a9147c80fe1ed1aa02475ed5..12c8f16096d9106c4040a519a1aeb566eaf66fbe 100644 (file)
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -390,7 +390,7 @@ void mt76_rx(struct mt76_dev *dev, enum mt76_rxq_id q, struct sk_buff *skb)
 }
 EXPORT_SYMBOL_GPL(mt76_rx);
 
-static bool mt76_has_tx_pending(struct mt76_dev *dev)
+bool mt76_has_tx_pending(struct mt76_dev *dev)
 {
        struct mt76_queue *q;
        int i;
@@ -403,6 +403,7 @@ static bool mt76_has_tx_pending(struct mt76_dev *dev)
 
        return false;
 }
+EXPORT_SYMBOL_GPL(mt76_has_tx_pending);
 
 void mt76_set_channel(struct mt76_dev *dev)
 {

diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 75a0d150a224a1002b851cc53a13ba74e201e78e..90d6e9df02a92d073c1732271cc1e6a70cc4ce75 100644 (file)
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -696,6 +696,7 @@ void mt76_release_buffered_frames(struct ieee80211_hw *hw,
                                  u16 tids, int nframes,
                                  enum ieee80211_frame_release_type reason,
                                  bool more_data);
+bool mt76_has_tx_pending(struct mt76_dev *dev);
 void mt76_set_channel(struct mt76_dev *dev);
 int mt76_get_survey(struct ieee80211_hw *hw, int idx,
                    struct survey_info *survey);
@@ -790,10 +791,10 @@ int mt76u_vendor_request(struct mt76_dev *dev, u8 req,
 void mt76u_single_wr(struct mt76_dev *dev, const u8 req,
                     const u16 offset, const u32 val);
 int mt76u_init(struct mt76_dev *dev, struct usb_interface *intf);
-int mt76u_submit_rx_buffers(struct mt76_dev *dev);
 int mt76u_alloc_queues(struct mt76_dev *dev);
-void mt76u_stop_queues(struct mt76_dev *dev);
-void mt76u_stop_stat_wk(struct mt76_dev *dev);
+void mt76u_stop_tx(struct mt76_dev *dev);
+void mt76u_stop_rx(struct mt76_dev *dev);
+int mt76u_resume_rx(struct mt76_dev *dev);
 void mt76u_queues_deinit(struct mt76_dev *dev);
 
 struct sk_buff *

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
index 53ec7dc38b9df810ef2746b49019d95aae9f7842..406ebfa74195d5aeea4934f607d791513cd86889 100644 (file)
--- a/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x0/usb.c
@@ -86,7 +86,7 @@ static void mt76x0u_mac_stop(struct mt76x02_dev *dev)
        clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
        cancel_delayed_work_sync(&dev->cal_work);
        cancel_delayed_work_sync(&dev->mt76.mac_work);
-       mt76u_stop_stat_wk(&dev->mt76);
+       mt76u_stop_tx(&dev->mt76);
        mt76x02u_exit_beacon_config(dev);
 
        if (test_bit(MT76_REMOVED, &dev->mt76.state))
@@ -313,7 +313,7 @@ static int __maybe_unused mt76x0_suspend(struct usb_interface *usb_intf,
 {
        struct mt76x02_dev *dev = usb_get_intfdata(usb_intf);
 
-       mt76u_stop_queues(&dev->mt76);
+       mt76u_stop_rx(&dev->mt76);
        clear_bit(MT76_STATE_MCU_RUNNING, &dev->mt76.state);
        mt76x0_chip_onoff(dev, false, false);
 
@@ -323,16 +323,12 @@ static int __maybe_unused mt76x0_suspend(struct usb_interface *usb_intf,
 static int __maybe_unused mt76x0_resume(struct usb_interface *usb_intf)
 {
        struct mt76x02_dev *dev = usb_get_intfdata(usb_intf);
-       struct mt76_usb *usb = &dev->mt76.usb;
        int ret;
 
-       ret = mt76u_submit_rx_buffers(&dev->mt76);
+       ret = mt76u_resume_rx(&dev->mt76);
        if (ret < 0)
                goto err;
 
-       tasklet_enable(&usb->rx_tasklet);
-       tasklet_enable(&dev->mt76.tx_tasklet);
-
        ret = mt76x0u_init_hardware(dev);
        if (ret)
                goto err;

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
index c55ad617edceafd438207d3f528f46f470d5e766..7a994a783510225df54eeb4863001c8ddca16a50 100644 (file)
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb.c
@@ -107,7 +107,7 @@ static int __maybe_unused mt76x2u_suspend(struct usb_interface *intf,
 {
        struct mt76x02_dev *dev = usb_get_intfdata(intf);
 
-       mt76u_stop_queues(&dev->mt76);
+       mt76u_stop_rx(&dev->mt76);
 
        return 0;
 }
@@ -115,16 +115,12 @@ static int __maybe_unused mt76x2u_suspend(struct usb_interface *intf,
 static int __maybe_unused mt76x2u_resume(struct usb_interface *intf)
 {
        struct mt76x02_dev *dev = usb_get_intfdata(intf);
-       struct mt76_usb *usb = &dev->mt76.usb;
        int err;
 
-       err = mt76u_submit_rx_buffers(&dev->mt76);
+       err = mt76u_resume_rx(&dev->mt76);
        if (err < 0)
                goto err;
 
-       tasklet_enable(&usb->rx_tasklet);
-       tasklet_enable(&dev->mt76.tx_tasklet);
-
        err = mt76x2u_init_hardware(dev);
        if (err < 0)
                goto err;

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
index 96ee596a69ec963532724b098af842d53e86b927..f2c57d5b87f939598a5deea6081480e962abe5d3 100644 (file)
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_init.c
@@ -244,7 +244,6 @@ fail:
 
 void mt76x2u_stop_hw(struct mt76x02_dev *dev)
 {
-       mt76u_stop_stat_wk(&dev->mt76);
        cancel_delayed_work_sync(&dev->cal_work);
        cancel_delayed_work_sync(&dev->mt76.mac_work);
        mt76x2u_mac_stop(dev);

diff --git a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
index dcf67f4845bec6c7f2084cc9382a720629a31a5a..305977a874a42f975b87fb438b00d83bc55c8539 100644 (file)
--- a/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x2/usb_main.c
@@ -42,6 +42,7 @@ static void mt76x2u_stop(struct ieee80211_hw *hw)
 
        mutex_lock(&dev->mt76.mutex);
        clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
+       mt76u_stop_tx(&dev->mt76);
        mt76x2u_stop_hw(dev);
        mutex_unlock(&dev->mt76.mutex);
 }

diff --git a/drivers/net/wireless/mediatek/mt76/usb.c b/drivers/net/wireless/mediatek/mt76/usb.c
index d2c6718b59333d78d291c1ea45646ce3277570ca..c299c6591072439d106f644e01e7821becb78227 100644 (file)
--- a/drivers/net/wireless/mediatek/mt76/usb.c
+++ b/drivers/net/wireless/mediatek/mt76/usb.c
@@ -540,7 +540,7 @@ static void mt76u_rx_tasklet(unsigned long data)
        rcu_read_unlock();
 }
 
-int mt76u_submit_rx_buffers(struct mt76_dev *dev)
+static int mt76u_submit_rx_buffers(struct mt76_dev *dev)
 {
        struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
        unsigned long flags;
@@ -558,7 +558,6 @@ int mt76u_submit_rx_buffers(struct mt76_dev *dev)
 
        return err;
 }
-EXPORT_SYMBOL_GPL(mt76u_submit_rx_buffers);
 
 static int mt76u_alloc_rx(struct mt76_dev *dev)
 {
@@ -605,14 +604,29 @@ static void mt76u_free_rx(struct mt76_dev *dev)
        memset(&q->rx_page, 0, sizeof(q->rx_page));
 }
 
-static void mt76u_stop_rx(struct mt76_dev *dev)
+void mt76u_stop_rx(struct mt76_dev *dev)
 {
        struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
        int i;
 
        for (i = 0; i < q->ndesc; i++)
-               usb_kill_urb(q->entry[i].urb);
+               usb_poison_urb(q->entry[i].urb);
+
+       tasklet_kill(&dev->usb.rx_tasklet);
+}
+EXPORT_SYMBOL_GPL(mt76u_stop_rx);
+
+int mt76u_resume_rx(struct mt76_dev *dev)
+{
+       struct mt76_queue *q = &dev->q_rx[MT_RXQ_MAIN];
+       int i;
+
+       for (i = 0; i < q->ndesc; i++)
+               usb_unpoison_urb(q->entry[i].urb);
+
+       return mt76u_submit_rx_buffers(dev);
 }
+EXPORT_SYMBOL_GPL(mt76u_resume_rx);
 
 static void mt76u_tx_tasklet(unsigned long data)
 {
@@ -834,38 +848,54 @@ static void mt76u_free_tx(struct mt76_dev *dev)
        }
 }
 
-static void mt76u_stop_tx(struct mt76_dev *dev)
+void mt76u_stop_tx(struct mt76_dev *dev)
 {
+       struct mt76_queue_entry entry;
        struct mt76_queue *q;
-       int i, j;
+       int i, j, ret;
 
-       for (i = 0; i < IEEE80211_NUM_ACS; i++) {
-               q = dev->q_tx[i].q;
-               for (j = 0; j < q->ndesc; j++)
-                       usb_kill_urb(q->entry[j].urb);
-       }
-}
+       ret = wait_event_timeout(dev->tx_wait, !mt76_has_tx_pending(dev), HZ/5);
+       if (!ret) {
+               dev_err(dev->dev, "timed out waiting for pending tx\n");
 
-void mt76u_stop_queues(struct mt76_dev *dev)
-{
-       tasklet_disable(&dev->usb.rx_tasklet);
-       tasklet_disable(&dev->tx_tasklet);
+               for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+                       q = dev->q_tx[i].q;
+                       for (j = 0; j < q->ndesc; j++)
+                               usb_kill_urb(q->entry[j].urb);
+               }
 
-       mt76u_stop_rx(dev);
-       mt76u_stop_tx(dev);
-}
-EXPORT_SYMBOL_GPL(mt76u_stop_queues);
+               tasklet_kill(&dev->tx_tasklet);
+
+               /* On device removal we maight queue skb's, but mt76u_tx_kick()
+                * will fail to submit urb, cleanup those skb's manually.
+                */
+               for (i = 0; i < IEEE80211_NUM_ACS; i++) {
+                       q = dev->q_tx[i].q;
+
+                       /* Assure we are in sync with killed tasklet. */
+                       spin_lock_bh(&q->lock);
+                       while (q->queued) {
+                               entry = q->entry[q->head];
+                               q->head = (q->head + 1) % q->ndesc;
+                               q->queued--;
+
+                               dev->drv->tx_complete_skb(dev, i, &entry);
+                       }
+                       spin_unlock_bh(&q->lock);
+               }
+       }
 
-void mt76u_stop_stat_wk(struct mt76_dev *dev)
-{
        cancel_delayed_work_sync(&dev->usb.stat_work);
        clear_bit(MT76_READING_STATS, &dev->state);
+
+       mt76_tx_status_check(dev, NULL, true);
 }
-EXPORT_SYMBOL_GPL(mt76u_stop_stat_wk);
+EXPORT_SYMBOL_GPL(mt76u_stop_tx);
 
 void mt76u_queues_deinit(struct mt76_dev *dev)
 {
-       mt76u_stop_queues(dev);
+       mt76u_stop_rx(dev);
+       mt76u_stop_tx(dev);
 
        mt76u_free_rx(dev);
        mt76u_free_tx(dev);