diff mbox series

ath10k: sdio: Add missing BH locking around napi_schdule()

Message ID 20210824144339.2796122-1-festevam@denx.de (mailing list archive)
State Accepted
Commit 019edd01d174ce4bb2e517dd332922514d176601
Delegated to: Kalle Valo
Headers show
Series ath10k: sdio: Add missing BH locking around napi_schdule() | expand

Commit Message

Fabio Estevam Aug. 24, 2021, 2:43 p.m. UTC
On a i.MX-based board with a QCA9377 Wifi chip, the following errors
are seen after launching the 'hostapd' application:

hostapd /etc/wifi.conf
Configuration file: /etc/wifi.conf
wlan0: interface state UNINITIALIZED->COUNTRY_UPDATE
NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
Using interface wlan0 with hwaddr 00:1f:7b:31:04:a0 and ssid "thessid"
IPv6: ADDRCONF(NETDEV_CHANGE): wlan0: link becomes ready
wlan0: interface state COUNTRY_UPDATE->ENABLED
wlan0: AP-ENABLED
NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
...

Fix this problem by adding the BH locking around napi-schedule(),
in the same way it was done in commit e63052a5dd3c ("mlx5e: add
add missing BH locking around napi_schdule()").

Its commit log provides the following explanation:

"It's not correct to call napi_schedule() in pure process
context. Because we use __raise_softirq_irqoff() we require
callers to be in a context which will eventually lead to
softirq handling (hardirq, bh disabled, etc.).
    
With code as is users will see:
    
NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
"

Fixes: cfee8793a74d ("ath10k: enable napi on RX path for sdio")
Signed-off-by: Fabio Estevam <festevam@denx.de>
---
 drivers/net/wireless/ath/ath10k/sdio.c | 5 ++++-
 1 file changed, 4 insertions(+), 1 deletion(-)

Comments

Fabio Estevam Aug. 31, 2021, 6:21 p.m. UTC | #1
Hi Kalle,

On Tue, Aug 24, 2021 at 11:46 AM Fabio Estevam <festevam@denx.de> wrote:
>
> On a i.MX-based board with a QCA9377 Wifi chip, the following errors
> are seen after launching the 'hostapd' application:
>
> hostapd /etc/wifi.conf
> Configuration file: /etc/wifi.conf
> wlan0: interface state UNINITIALIZED->COUNTRY_UPDATE
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> Using interface wlan0 with hwaddr 00:1f:7b:31:04:a0 and ssid "thessid"
> IPv6: ADDRCONF(NETDEV_CHANGE): wlan0: link becomes ready
> wlan0: interface state COUNTRY_UPDATE->ENABLED
> wlan0: AP-ENABLED
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> ...
>
> Fix this problem by adding the BH locking around napi-schedule(),
> in the same way it was done in commit e63052a5dd3c ("mlx5e: add
> add missing BH locking around napi_schdule()").
>
> Its commit log provides the following explanation:
>
> "It's not correct to call napi_schedule() in pure process
> context. Because we use __raise_softirq_irqoff() we require
> callers to be in a context which will eventually lead to
> softirq handling (hardirq, bh disabled, etc.).
>
> With code as is users will see:
>
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> "
>
> Fixes: cfee8793a74d ("ath10k: enable napi on RX path for sdio")
> Signed-off-by: Fabio Estevam <festevam@denx.de>

Gentle ping on this one.
Kalle Valo Sept. 28, 2021, 2:36 p.m. UTC | #2
Fabio Estevam <festevam@denx.de> wrote:

> On a i.MX-based board with a QCA9377 Wifi chip, the following errors
> are seen after launching the 'hostapd' application:
> 
> hostapd /etc/wifi.conf
> Configuration file: /etc/wifi.conf
> wlan0: interface state UNINITIALIZED->COUNTRY_UPDATE
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> Using interface wlan0 with hwaddr 00:1f:7b:31:04:a0 and ssid "thessid"
> IPv6: ADDRCONF(NETDEV_CHANGE): wlan0: link becomes ready
> wlan0: interface state COUNTRY_UPDATE->ENABLED
> wlan0: AP-ENABLED
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> ...
> 
> Fix this problem by adding the BH locking around napi-schedule(),
> in the same way it was done in commit e63052a5dd3c ("mlx5e: add
> add missing BH locking around napi_schdule()").
> 
> Its commit log provides the following explanation:
> 
> "It's not correct to call napi_schedule() in pure process
> context. Because we use __raise_softirq_irqoff() we require
> callers to be in a context which will eventually lead to
> softirq handling (hardirq, bh disabled, etc.).
> 
> With code as is users will see:
> 
> NOHZ tick-stop error: Non-RCU local softirq work is pending, handler #08!!!
> "
> 
> Fixes: cfee8793a74d ("ath10k: enable napi on RX path for sdio")
> Signed-off-by: Fabio Estevam <festevam@denx.de>
> Signed-off-by: Kalle Valo <kvalo@codeaurora.org>

Patch applied to ath-next branch of ath.git, thanks.

019edd01d174 ath10k: sdio: Add missing BH locking around napi_schdule()
diff mbox series

Patch

diff --git a/drivers/net/wireless/ath/ath10k/sdio.c b/drivers/net/wireless/ath/ath10k/sdio.c
index b746052737e0..eb705214f3f0 100644
--- a/drivers/net/wireless/ath/ath10k/sdio.c
+++ b/drivers/net/wireless/ath/ath10k/sdio.c
@@ -1363,8 +1363,11 @@  static void ath10k_rx_indication_async_work(struct work_struct *work)
 		ep->ep_ops.ep_rx_complete(ar, skb);
 	}
 
-	if (test_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags))
+	if (test_bit(ATH10K_FLAG_CORE_REGISTERED, &ar->dev_flags)) {
+		local_bh_disable();
 		napi_schedule(&ar->napi);
+		local_bh_enable();
+	}
 }
 
 static int ath10k_sdio_read_rtc_state(struct ath10k_sdio *ar_sdio, unsigned char *state)