Fix following schedule while atomic mt76x02_reset_state
since synchronize_rcu is run inside a RCU section
[44036.944222] mt76x2e 0000:06:00.0: MCU message 31 (seq 3) timed out
[44036.944281] BUG: sleeping function called from invalid context at kernel/rcu/tree_exp.h:818
[44036.944284] in_atomic(): 1, irqs_disabled(): 0, pid: 28066, name: kworker/u4:1
[44036.944287] INFO: lockdep is turned off.
[44036.944292] CPU: 1 PID: 28066 Comm: kworker/u4:1 Tainted: G W 5.0.0-rc7-wdn-t1+ #7
[44036.944294] Hardware name: Dell Inc. Studio XPS 1340/0K183D, BIOS A11 09/08/2009
[44036.944305] Workqueue: phy1 mt76x02_wdt_work [mt76x02_lib]
[44036.944308] Call Trace:
[44036.944317] dump_stack+0x67/0x90
[44036.944322] ___might_sleep.cold.88+0x9f/0xaf
[44036.944327] rcu_blocking_is_gp+0x13/0x50
[44036.944330] synchronize_rcu+0x17/0x80
[44036.944337] mt76_sta_state+0x138/0x1d0 [mt76]
[44036.944349] mt76x02_wdt_work+0x1c9/0x610 [mt76x02_lib]
[44036.944355] process_one_work+0x2a5/0x620
[44036.944361] worker_thread+0x35/0x3e0
[44036.944368] kthread+0x11c/0x140
[44036.944376] ret_from_fork+0x3a/0x50
[44036.944384] BUG: scheduling while atomic: kworker/u4:1/28066/0x00000002
[44036.944387] INFO: lockdep is turned off.
[44036.944389] Modules linked in: cmac ctr ccm af_packet snd_hda_codec_hdmi
Introduce __mt76_sta_remove in order to run sta_remove without holding dev->mutex.
Move __mt76_sta_remove outside RCU section in mt76x02_reset_state
Fixes: e4ebb8b403d1 ("mt76: mt76x2: implement full device restart on watchdog reset")
Signed-off-by: Lorenzo Bianconi <[email protected]>
---
drivers/net/wireless/mediatek/mt76/mac80211.c | 18 +++++++++++-------
drivers/net/wireless/mediatek/mt76/mt76.h | 2 ++
.../net/wireless/mediatek/mt76/mt76x02_mmio.c | 14 ++++++--------
3 files changed, 19 insertions(+), 15 deletions(-)
diff --git a/drivers/net/wireless/mediatek/mt76/mac80211.c b/drivers/net/wireless/mediatek/mt76/mac80211.c
index a033745adb2f..bde52943ecaf 100644
--- a/drivers/net/wireless/mediatek/mt76/mac80211.c
+++ b/drivers/net/wireless/mediatek/mt76/mac80211.c
@@ -679,19 +679,15 @@ mt76_sta_add(struct mt76_dev *dev, struct ieee80211_vif *vif,
return ret;
}
-static void
-mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
- struct ieee80211_sta *sta)
+void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta)
{
struct mt76_wcid *wcid = (struct mt76_wcid *)sta->drv_priv;
- int idx = wcid->idx;
- int i;
+ int i, idx = wcid->idx;
rcu_assign_pointer(dev->wcid[idx], NULL);
synchronize_rcu();
- mutex_lock(&dev->mutex);
-
if (dev->drv->sta_remove)
dev->drv->sta_remove(dev, vif, sta);
@@ -699,7 +695,15 @@ mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
for (i = 0; i < ARRAY_SIZE(sta->txq); i++)
mt76_txq_remove(dev, sta->txq[i]);
mt76_wcid_free(dev->wcid_mask, idx);
+}
+EXPORT_SYMBOL_GPL(__mt76_sta_remove);
+static void
+mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta)
+{
+ mutex_lock(&dev->mutex);
+ __mt76_sta_remove(dev, vif, sta);
mutex_unlock(&dev->mutex);
}
diff --git a/drivers/net/wireless/mediatek/mt76/mt76.h b/drivers/net/wireless/mediatek/mt76/mt76.h
index 477027bb9aaf..eb72e4bf3db6 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76.h
+++ b/drivers/net/wireless/mediatek/mt76/mt76.h
@@ -697,6 +697,8 @@ int mt76_sta_state(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
struct ieee80211_sta *sta,
enum ieee80211_sta_state old_state,
enum ieee80211_sta_state new_state);
+void __mt76_sta_remove(struct mt76_dev *dev, struct ieee80211_vif *vif,
+ struct ieee80211_sta *sta);
struct ieee80211_sta *mt76_rx_convert(struct sk_buff *skb);
diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
index 6a34a6afcfe4..898afcbcdf52 100644
--- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
+++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
@@ -419,6 +419,7 @@ static void mt76x02_key_sync(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
mt76x02_mac_wcid_sync_pn(dev, wcid->idx, key);
}
+/* need to run with mt76.mutex held */
static void mt76x02_reset_state(struct mt76x02_dev *dev)
{
int i;
@@ -426,11 +427,11 @@ static void mt76x02_reset_state(struct mt76x02_dev *dev)
clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
rcu_read_lock();
-
ieee80211_iter_keys_rcu(dev->mt76.hw, NULL, mt76x02_key_sync, NULL);
+ rcu_read_unlock();
for (i = 0; i < ARRAY_SIZE(dev->mt76.wcid); i++) {
- struct mt76_wcid *wcid = rcu_dereference(dev->mt76.wcid[i]);
+ struct mt76_wcid *wcid = dev->mt76.wcid[i];
struct mt76x02_sta *msta;
struct ieee80211_sta *sta;
struct ieee80211_vif *vif;
@@ -445,13 +446,10 @@ static void mt76x02_reset_state(struct mt76x02_dev *dev)
priv = msta->vif;
vif = container_of(priv, struct ieee80211_vif, drv_priv);
- mt76_sta_state(dev->mt76.hw, vif, sta,
- IEEE80211_STA_NONE, IEEE80211_STA_NOTEXIST);
+ __mt76_sta_remove(&dev->mt76, vif, sta);
memset(msta, 0, sizeof(*msta));
}
- rcu_read_unlock();
-
dev->vif_mask = 0;
dev->beacon_mask = 0;
}
@@ -471,11 +469,11 @@ static void mt76x02_watchdog_reset(struct mt76x02_dev *dev)
for (i = 0; i < ARRAY_SIZE(dev->mt76.napi); i++)
napi_disable(&dev->mt76.napi[i]);
+ mutex_lock(&dev->mt76.mutex);
+
if (restart)
mt76x02_reset_state(dev);
- mutex_lock(&dev->mt76.mutex);
-
if (dev->beacon_mask)
mt76_clear(dev, MT_BEACON_TIME_CFG,
MT_BEACON_TIME_CFG_BEACON_TX |
--
2.20.1
On 2019-03-10 23:47, Lorenzo Bianconi wrote:
> Fix following schedule while atomic mt76x02_reset_state
> since synchronize_rcu is run inside a RCU section
>
> [44036.944222] mt76x2e 0000:06:00.0: MCU message 31 (seq 3) timed out
> [44036.944281] BUG: sleeping function called from invalid context at kernel/rcu/tree_exp.h:818
> [44036.944284] in_atomic(): 1, irqs_disabled(): 0, pid: 28066, name: kworker/u4:1
> [44036.944287] INFO: lockdep is turned off.
> [44036.944292] CPU: 1 PID: 28066 Comm: kworker/u4:1 Tainted: G W 5.0.0-rc7-wdn-t1+ #7
> [44036.944294] Hardware name: Dell Inc. Studio XPS 1340/0K183D, BIOS A11 09/08/2009
> [44036.944305] Workqueue: phy1 mt76x02_wdt_work [mt76x02_lib]
> [44036.944308] Call Trace:
> [44036.944317] dump_stack+0x67/0x90
> [44036.944322] ___might_sleep.cold.88+0x9f/0xaf
> [44036.944327] rcu_blocking_is_gp+0x13/0x50
> [44036.944330] synchronize_rcu+0x17/0x80
> [44036.944337] mt76_sta_state+0x138/0x1d0 [mt76]
> [44036.944349] mt76x02_wdt_work+0x1c9/0x610 [mt76x02_lib]
> [44036.944355] process_one_work+0x2a5/0x620
> [44036.944361] worker_thread+0x35/0x3e0
> [44036.944368] kthread+0x11c/0x140
> [44036.944376] ret_from_fork+0x3a/0x50
> [44036.944384] BUG: scheduling while atomic: kworker/u4:1/28066/0x00000002
> [44036.944387] INFO: lockdep is turned off.
> [44036.944389] Modules linked in: cmac ctr ccm af_packet snd_hda_codec_hdmi
>
> Introduce __mt76_sta_remove in order to run sta_remove without holding dev->mutex.
> Move __mt76_sta_remove outside RCU section in mt76x02_reset_state
>
> Fixes: e4ebb8b403d1 ("mt76: mt76x2: implement full device restart on watchdog reset")
> Signed-off-by: Lorenzo Bianconi <[email protected]>
> diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
> index 6a34a6afcfe4..898afcbcdf52 100644
> --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
> +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
> @@ -419,6 +419,7 @@ static void mt76x02_key_sync(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
> mt76x02_mac_wcid_sync_pn(dev, wcid->idx, key);
> }
>
> +/* need to run with mt76.mutex held */
> static void mt76x02_reset_state(struct mt76x02_dev *dev)
You can replace that comment with a call to lockdep_assert_held in the
function.
> @@ -426,11 +427,11 @@ static void mt76x02_reset_state(struct mt76x02_dev *dev)
> clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
>
> rcu_read_lock();
> -
> ieee80211_iter_keys_rcu(dev->mt76.hw, NULL, mt76x02_key_sync, NULL);
> + rcu_read_unlock();
>
> for (i = 0; i < ARRAY_SIZE(dev->mt76.wcid); i++) {
> - struct mt76_wcid *wcid = rcu_dereference(dev->mt76.wcid[i]);
> + struct mt76_wcid *wcid = dev->mt76.wcid[i];
This should use rcu_dereference_protected() instead of accessing the
pointer directly.
Thanks,
- Felix
> On 2019-03-10 23:47, Lorenzo Bianconi wrote:
> > Fix following schedule while atomic mt76x02_reset_state
> > since synchronize_rcu is run inside a RCU section
> >
> > [44036.944222] mt76x2e 0000:06:00.0: MCU message 31 (seq 3) timed out
> > [44036.944281] BUG: sleeping function called from invalid context at kernel/rcu/tree_exp.h:818
> > [44036.944284] in_atomic(): 1, irqs_disabled(): 0, pid: 28066, name: kworker/u4:1
> > [44036.944287] INFO: lockdep is turned off.
> > [44036.944292] CPU: 1 PID: 28066 Comm: kworker/u4:1 Tainted: G W 5.0.0-rc7-wdn-t1+ #7
> > [44036.944294] Hardware name: Dell Inc. Studio XPS 1340/0K183D, BIOS A11 09/08/2009
> > [44036.944305] Workqueue: phy1 mt76x02_wdt_work [mt76x02_lib]
> > [44036.944308] Call Trace:
> > [44036.944317] dump_stack+0x67/0x90
> > [44036.944322] ___might_sleep.cold.88+0x9f/0xaf
> > [44036.944327] rcu_blocking_is_gp+0x13/0x50
> > [44036.944330] synchronize_rcu+0x17/0x80
> > [44036.944337] mt76_sta_state+0x138/0x1d0 [mt76]
> > [44036.944349] mt76x02_wdt_work+0x1c9/0x610 [mt76x02_lib]
> > [44036.944355] process_one_work+0x2a5/0x620
> > [44036.944361] worker_thread+0x35/0x3e0
> > [44036.944368] kthread+0x11c/0x140
> > [44036.944376] ret_from_fork+0x3a/0x50
> > [44036.944384] BUG: scheduling while atomic: kworker/u4:1/28066/0x00000002
> > [44036.944387] INFO: lockdep is turned off.
> > [44036.944389] Modules linked in: cmac ctr ccm af_packet snd_hda_codec_hdmi
> >
> > Introduce __mt76_sta_remove in order to run sta_remove without holding dev->mutex.
> > Move __mt76_sta_remove outside RCU section in mt76x02_reset_state
> >
> > Fixes: e4ebb8b403d1 ("mt76: mt76x2: implement full device restart on watchdog reset")
> > Signed-off-by: Lorenzo Bianconi <[email protected]>
> > diff --git a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
> > index 6a34a6afcfe4..898afcbcdf52 100644
> > --- a/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
> > +++ b/drivers/net/wireless/mediatek/mt76/mt76x02_mmio.c
> > @@ -419,6 +419,7 @@ static void mt76x02_key_sync(struct ieee80211_hw *hw, struct ieee80211_vif *vif,
> > mt76x02_mac_wcid_sync_pn(dev, wcid->idx, key);
> > }
> >
> > +/* need to run with mt76.mutex held */
> > static void mt76x02_reset_state(struct mt76x02_dev *dev)
> You can replace that comment with a call to lockdep_assert_held in the
> function.
>
> > @@ -426,11 +427,11 @@ static void mt76x02_reset_state(struct mt76x02_dev *dev)
> > clear_bit(MT76_STATE_RUNNING, &dev->mt76.state);
> >
> > rcu_read_lock();
> > -
> > ieee80211_iter_keys_rcu(dev->mt76.hw, NULL, mt76x02_key_sync, NULL);
> > + rcu_read_unlock();
> >
> > for (i = 0; i < ARRAY_SIZE(dev->mt76.wcid); i++) {
> > - struct mt76_wcid *wcid = rcu_dereference(dev->mt76.wcid[i]);
> > + struct mt76_wcid *wcid = dev->mt76.wcid[i];
> This should use rcu_dereference_protected() instead of accessing the
> pointer directly.
>
ack, I will fix them in v2.
Regards,
Lorenzo
> Thanks,
>
> - Felix