| Message ID | 20240822014255.10211-1-pkshih@realtek.com |
|---|---|
| State | New |
| Headers | show |
| Series | [v2,1/2] wifi: mac80211: export ieee80211_purge_tx_queue() for drivers | expand |
Hi Peter, Could you please test v2 again? Thanks. Ping-Ke Shih <pkshih@realtek.com> wrote: > When removing kernel modules by: > rmmod rtw88_8723cs rtw88_8703b rtw88_8723x rtw88_sdio rtw88_core > > Driver uses skb_queue_purge() to purge TX skb, but not report tx status > causing "Have pending ack frames!" warning. Use ieee80211_purge_tx_queue() > to correct this. > > Since ieee80211_purge_tx_queue() doesn't take locks, to prevent racing > between TX work and purge TX queue, flush and destroy TX work in advance. > > wlan0: deauthenticating from aa:f5:fd:60:4c:a8 by local > choice (Reason: 3=DEAUTH_LEAVING) > ------------[ cut here ]------------ > Have pending ack frames! > WARNING: CPU: 3 PID: 9232 at net/mac80211/main.c:1691 > ieee80211_free_ack_frame+0x5c/0x90 [mac80211] > CPU: 3 PID: 9232 Comm: rmmod Tainted: G C > 6.10.1-200.fc40.aarch64 #1 > Hardware name: pine64 Pine64 PinePhone Braveheart > (1.1)/Pine64 PinePhone Braveheart (1.1), BIOS 2024.01 01/01/2024 > pstate: 60400005 (nZCv daif +PAN -UAO -TCO -DIT -SSBS BTYPE=--) > pc : ieee80211_free_ack_frame+0x5c/0x90 [mac80211] > lr : ieee80211_free_ack_frame+0x5c/0x90 [mac80211] > sp : ffff80008c1b37b0 > x29: ffff80008c1b37b0 x28: ffff000003be8000 x27: 0000000000000000 > x26: 0000000000000000 x25: ffff000003dc14b8 x24: ffff80008c1b37d0 > x23: ffff000000ff9f80 x22: 0000000000000000 x21: 000000007fffffff > x20: ffff80007c7e93d8 x19: ffff00006e66f400 x18: 0000000000000000 > x17: ffff7ffffd2b3000 x16: ffff800083fc0000 x15: 0000000000000000 > x14: 0000000000000000 x13: 2173656d61726620 x12: 6b636120676e6964 > x11: 0000000000000000 x10: 000000000000005d x9 : ffff8000802af2b0 > x8 : ffff80008c1b3430 x7 : 0000000000000001 x6 : 0000000000000001 > x5 : 0000000000000000 x4 : 0000000000000000 x3 : 0000000000000000 > x2 : 0000000000000000 x1 : 0000000000000000 x0 : ffff000003be8000 > Call trace: > ieee80211_free_ack_frame+0x5c/0x90 [mac80211] > idr_for_each+0x74/0x110 > ieee80211_free_hw+0x44/0xe8 [mac80211] > rtw_sdio_remove+0x9c/0xc0 [rtw88_sdio] > sdio_bus_remove+0x44/0x180 > device_remove+0x54/0x90 > device_release_driver_internal+0x1d4/0x238 > driver_detach+0x54/0xc0 > bus_remove_driver+0x78/0x108 > driver_unregister+0x38/0x78 > sdio_unregister_driver+0x2c/0x40 > rtw_8723cs_driver_exit+0x18/0x1000 [rtw88_8723cs] > __do_sys_delete_module.isra.0+0x190/0x338 > __arm64_sys_delete_module+0x1c/0x30 > invoke_syscall+0x74/0x100 > el0_svc_common.constprop.0+0x48/0xf0 > do_el0_svc+0x24/0x38 > el0_svc+0x3c/0x158 > el0t_64_sync_handler+0x120/0x138 > el0t_64_sync+0x194/0x198 > ---[ end trace 0000000000000000 ]--- > > Reported-by: Peter Robinson <pbrobinson@gmail.com> > Closes: > https://lore.kernel.org/linux-wireless/CALeDE9OAa56KMzgknaCD3quOgYuEHFx9_hcT=OFgmMAb+8MPyA@mail.gmail. > com/ > Signed-off-by: Ping-Ke Shih <pkshih@realtek.com> > --- > v2: > - flush and destroy TX work before doing purge_tx_queue > - remove "Tested-by: Peter Robinson" since code changed > --- > drivers/net/wireless/realtek/rtw88/sdio.c | 6 +++--- > drivers/net/wireless/realtek/rtw88/usb.c | 5 +++-- > 2 files changed, 6 insertions(+), 5 deletions(-) > > diff --git a/drivers/net/wireless/realtek/rtw88/sdio.c b/drivers/net/wireless/realtek/rtw88/sdio.c > index 21d0754dd7f6..b67e551fcee3 100644 > --- a/drivers/net/wireless/realtek/rtw88/sdio.c > +++ b/drivers/net/wireless/realtek/rtw88/sdio.c > @@ -1297,12 +1297,12 @@ static void rtw_sdio_deinit_tx(struct rtw_dev *rtwdev) > struct rtw_sdio *rtwsdio = (struct rtw_sdio *)rtwdev->priv; > int i; > > - for (i = 0; i < RTK_MAX_TX_QUEUE_NUM; i++) > - skb_queue_purge(&rtwsdio->tx_queue[i]); > - > flush_workqueue(rtwsdio->txwq); > destroy_workqueue(rtwsdio->txwq); > kfree(rtwsdio->tx_handler_data); > + > + for (i = 0; i < RTK_MAX_TX_QUEUE_NUM; i++) > + ieee80211_purge_tx_queue(rtwdev->hw, &rtwsdio->tx_queue[i]); > } > > int rtw_sdio_probe(struct sdio_func *sdio_func, > diff --git a/drivers/net/wireless/realtek/rtw88/usb.c b/drivers/net/wireless/realtek/rtw88/usb.c > index e83ab6fb83f5..dbc7d8d73494 100644 > --- a/drivers/net/wireless/realtek/rtw88/usb.c > +++ b/drivers/net/wireless/realtek/rtw88/usb.c > @@ -423,10 +423,11 @@ static void rtw_usb_tx_handler(struct work_struct *work) > > static void rtw_usb_tx_queue_purge(struct rtw_usb *rtwusb) > { > + struct rtw_dev *rtwdev = rtwusb->rtwdev; > int i; > > for (i = 0; i < ARRAY_SIZE(rtwusb->tx_queue); i++) > - skb_queue_purge(&rtwusb->tx_queue[i]); > + ieee80211_purge_tx_queue(rtwdev->hw, &rtwusb->tx_queue[i]); > } > > static void rtw_usb_write_port_complete(struct urb *urb) > @@ -889,9 +890,9 @@ static void rtw_usb_deinit_tx(struct rtw_dev *rtwdev) > { > struct rtw_usb *rtwusb = rtw_get_usb_priv(rtwdev); > > - rtw_usb_tx_queue_purge(rtwusb); > flush_workqueue(rtwusb->txwq); > destroy_workqueue(rtwusb->txwq); > + rtw_usb_tx_queue_purge(rtwusb); > } > > static int rtw_usb_intf_init(struct rtw_dev *rtwdev, > -- > 2.25.1 >
diff --git a/include/net/mac80211.h b/include/net/mac80211.h index 0a04eaf5343c..651fa926c94a 100644 --- a/include/net/mac80211.h +++ b/include/net/mac80211.h @@ -3180,6 +3180,19 @@ ieee80211_get_alt_retry_rate(const struct ieee80211_hw *hw, */ void ieee80211_free_txskb(struct ieee80211_hw *hw, struct sk_buff *skb); +/** + * ieee80211_purge_tx_queue - purge TX skb queue + * @hw: the hardware + * @skbs: the skbs + * + * Free a set of transmit skbs. Use this function when device is going to stop + * but some transmit skbs without TX status are still queued. + * This function does not take the list lock and the caller must hold the + * relevant locks to use it. + */ +void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, + struct sk_buff_head *skbs); + /** * DOC: Hardware crypto acceleration * diff --git a/net/mac80211/ieee80211_i.h b/net/mac80211/ieee80211_i.h index a3485e4c6132..da705bf50d93 100644 --- a/net/mac80211/ieee80211_i.h +++ b/net/mac80211/ieee80211_i.h @@ -2072,8 +2072,6 @@ void __ieee80211_subif_start_xmit(struct sk_buff *skb, u32 info_flags, u32 ctrl_flags, u64 *cookie); -void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, - struct sk_buff_head *skbs); struct sk_buff * ieee80211_build_data_template(struct ieee80211_sub_if_data *sdata, struct sk_buff *skb, u32 info_flags); diff --git a/net/mac80211/status.c b/net/mac80211/status.c index dd8f857a1fbc..d1cf987de13b 100644 --- a/net/mac80211/status.c +++ b/net/mac80211/status.c @@ -1301,3 +1301,4 @@ void ieee80211_purge_tx_queue(struct ieee80211_hw *hw, while ((skb = __skb_dequeue(skbs))) ieee80211_free_txskb(hw, skb); } +EXPORT_SYMBOL(ieee80211_purge_tx_queue);
Drivers need to purge TX SKB when stopping. Using skb_queue_purge() can't report TX status to mac80211, causing ieee80211_free_ack_frame() warns "Have pending ack frames!". Export ieee80211_purge_tx_queue() for drivers to not have to reimplement it. Signed-off-by: Ping-Ke Shih <pkshih@realtek.com> --- v2: - correct wording in commit message, and mention reason why we export the symbol - add comment to note ieee80211_purge_tx_queue() doesn't take locks - remove prototype from net/mac80211/ieee80211_i.h --- include/net/mac80211.h | 13 +++++++++++++ net/mac80211/ieee80211_i.h | 2 -- net/mac80211/status.c | 1 + 3 files changed, 14 insertions(+), 2 deletions(-)