| Message ID | 5cfa5c473ff6d069cb67760ffa04a2f84ef450a8.1661252818.git.duoming@zju.edu.cn (mailing list archive) |
|---|---|
| State | Awaiting Upstream |
| Delegated to: | Netdev Maintainers |
| Headers | show |
| Series | Add new APIs of devcoredump and fix bugs | expand |
| Context | Check | Description |
|---|---|---|
| netdev/tree_selection | success | Not a local patch |
Duoming Zhou <duoming@zju.edu.cn> wrote: > There are sleep in atomic context bugs when uploading device dump > data in mwifiex. The root cause is that dev_coredumpv could not > be used in atomic contexts, because it calls dev_set_name which > include operations that may sleep. The call tree shows execution > paths that could lead to bugs: > > (Interrupt context) > fw_dump_timer_fn > mwifiex_upload_device_dump > dev_coredumpv(..., GFP_KERNEL) > dev_coredumpm() > kzalloc(sizeof(*devcd), gfp); //may sleep > dev_set_name > kobject_set_name_vargs > kvasprintf_const(GFP_KERNEL, ...); //may sleep > kstrdup(s, GFP_KERNEL); //may sleep > > The corresponding fail log is shown below: > > [ 135.275938] usb 1-1: == mwifiex dump information to /sys/class/devcoredump start > [ 135.281029] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:265 > ... > [ 135.293613] Call Trace: > [ 135.293613] <IRQ> > [ 135.293613] dump_stack_lvl+0x57/0x7d > [ 135.293613] __might_resched.cold+0x138/0x173 > [ 135.293613] ? dev_coredumpm+0xca/0x2e0 > [ 135.293613] kmem_cache_alloc_trace+0x189/0x1f0 > [ 135.293613] ? devcd_match_failing+0x30/0x30 > [ 135.293613] dev_coredumpm+0xca/0x2e0 > [ 135.293613] ? devcd_freev+0x10/0x10 > [ 135.293613] dev_coredumpv+0x1c/0x20 > [ 135.293613] ? devcd_match_failing+0x30/0x30 > [ 135.293613] mwifiex_upload_device_dump+0x65/0xb0 > [ 135.293613] ? mwifiex_dnld_fw+0x1b0/0x1b0 > [ 135.293613] call_timer_fn+0x122/0x3d0 > [ 135.293613] ? msleep_interruptible+0xb0/0xb0 > [ 135.293613] ? lock_downgrade+0x3c0/0x3c0 > [ 135.293613] ? __next_timer_interrupt+0x13c/0x160 > [ 135.293613] ? lockdep_hardirqs_on_prepare+0xe/0x220 > [ 135.293613] ? mwifiex_dnld_fw+0x1b0/0x1b0 > [ 135.293613] __run_timers.part.0+0x3f8/0x540 > [ 135.293613] ? call_timer_fn+0x3d0/0x3d0 > [ 135.293613] ? arch_restore_msi_irqs+0x10/0x10 > [ 135.293613] ? lapic_next_event+0x31/0x40 > [ 135.293613] run_timer_softirq+0x4f/0xb0 > [ 135.293613] __do_softirq+0x1c2/0x651 > ... > [ 135.293613] RIP: 0010:default_idle+0xb/0x10 > [ 135.293613] RSP: 0018:ffff888006317e68 EFLAGS: 00000246 > [ 135.293613] RAX: ffffffff82ad8d10 RBX: ffff888006301cc0 RCX: ffffffff82ac90e1 > [ 135.293613] RDX: ffffed100d9ff1b4 RSI: ffffffff831ad140 RDI: ffffffff82ad8f20 > [ 135.293613] RBP: 0000000000000003 R08: 0000000000000000 R09: ffff88806cff8d9b > [ 135.293613] R10: ffffed100d9ff1b3 R11: 0000000000000001 R12: ffffffff84593410 > [ 135.293613] R13: 0000000000000000 R14: 0000000000000000 R15: 1ffff11000c62fd2 > ... > [ 135.389205] usb 1-1: == mwifiex dump information to /sys/class/devcoredump end > > This patch uses delayed work to replace timer and moves the operations > that may sleep into a delayed work in order to mitigate bugs, it was > tested on Marvell 88W8801 chip whose port is usb and the firmware is > usb8801_uapsta.bin. The following is the result after using delayed > work to replace timer. > > [ 134.936453] usb 1-1: == mwifiex dump information to /sys/class/devcoredump start > [ 135.043344] usb 1-1: == mwifiex dump information to /sys/class/devcoredump end > > As we can see, there is no bug now. > > Fixes: f5ecd02a8b20 ("mwifiex: device dump support for usb interface") > Signed-off-by: Duoming Zhou <duoming@zju.edu.cn> > Reviewed-by: Brian Norris <briannorris@chromium.org> > Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Patch applied to wireless-next.git, thanks. 551e4745c7f2 mwifiex: fix sleep in atomic context bugs caused by dev_coredumpv
diff --git a/drivers/net/wireless/marvell/mwifiex/init.c b/drivers/net/wireless/marvell/mwifiex/init.c index fc77489cc51..7dddb4b5dea 100644 --- a/drivers/net/wireless/marvell/mwifiex/init.c +++ b/drivers/net/wireless/marvell/mwifiex/init.c @@ -51,9 +51,10 @@ static void wakeup_timer_fn(struct timer_list *t) adapter->if_ops.card_reset(adapter); } -static void fw_dump_timer_fn(struct timer_list *t) +static void fw_dump_work(struct work_struct *work) { - struct mwifiex_adapter *adapter = from_timer(adapter, t, devdump_timer); + struct mwifiex_adapter *adapter = + container_of(work, struct mwifiex_adapter, devdump_work.work); mwifiex_upload_device_dump(adapter); } @@ -309,7 +310,7 @@ static void mwifiex_init_adapter(struct mwifiex_adapter *adapter) adapter->active_scan_triggered = false; timer_setup(&adapter->wakeup_timer, wakeup_timer_fn, 0); adapter->devdump_len = 0; - timer_setup(&adapter->devdump_timer, fw_dump_timer_fn, 0); + INIT_DELAYED_WORK(&adapter->devdump_work, fw_dump_work); } /* @@ -388,7 +389,7 @@ static void mwifiex_adapter_cleanup(struct mwifiex_adapter *adapter) { del_timer(&adapter->wakeup_timer); - del_timer_sync(&adapter->devdump_timer); + cancel_delayed_work_sync(&adapter->devdump_work); mwifiex_cancel_all_pending_cmd(adapter); wake_up_interruptible(&adapter->cmd_wait_q.wait); wake_up_interruptible(&adapter->hs_activate_wait_q); diff --git a/drivers/net/wireless/marvell/mwifiex/main.h b/drivers/net/wireless/marvell/mwifiex/main.h index 87729d251fe..63f861e6b28 100644 --- a/drivers/net/wireless/marvell/mwifiex/main.h +++ b/drivers/net/wireless/marvell/mwifiex/main.h @@ -37,6 +37,7 @@ #include <linux/pm_runtime.h> #include <linux/slab.h> #include <linux/of_irq.h> +#include <linux/workqueue.h> #include "decl.h" #include "ioctl.h" @@ -1043,7 +1044,7 @@ struct mwifiex_adapter { /* Device dump data/length */ void *devdump_data; int devdump_len; - struct timer_list devdump_timer; + struct delayed_work devdump_work; bool ignore_btcoex_events; }; diff --git a/drivers/net/wireless/marvell/mwifiex/sta_event.c b/drivers/net/wireless/marvell/mwifiex/sta_event.c index b95e90a7d12..e80e372cce8 100644 --- a/drivers/net/wireless/marvell/mwifiex/sta_event.c +++ b/drivers/net/wireless/marvell/mwifiex/sta_event.c @@ -611,8 +611,8 @@ mwifiex_fw_dump_info_event(struct mwifiex_private *priv, * transmission event get lost, in this cornel case, * user would still get partial of the dump. */ - mod_timer(&adapter->devdump_timer, - jiffies + msecs_to_jiffies(MWIFIEX_TIMER_10S)); + schedule_delayed_work(&adapter->devdump_work, + msecs_to_jiffies(MWIFIEX_TIMER_10S)); } /* Overflow check */ @@ -631,7 +631,7 @@ mwifiex_fw_dump_info_event(struct mwifiex_private *priv, return; upload_dump: - del_timer_sync(&adapter->devdump_timer); + cancel_delayed_work_sync(&adapter->devdump_work); mwifiex_upload_device_dump(adapter); }
There are sleep in atomic context bugs when uploading device dump data in mwifiex. The root cause is that dev_coredumpv could not be used in atomic contexts, because it calls dev_set_name which include operations that may sleep. The call tree shows execution paths that could lead to bugs: (Interrupt context) fw_dump_timer_fn mwifiex_upload_device_dump dev_coredumpv(..., GFP_KERNEL) dev_coredumpm() kzalloc(sizeof(*devcd), gfp); //may sleep dev_set_name kobject_set_name_vargs kvasprintf_const(GFP_KERNEL, ...); //may sleep kstrdup(s, GFP_KERNEL); //may sleep The corresponding fail log is shown below: [ 135.275938] usb 1-1: == mwifiex dump information to /sys/class/devcoredump start [ 135.281029] BUG: sleeping function called from invalid context at include/linux/sched/mm.h:265 ... [ 135.293613] Call Trace: [ 135.293613] <IRQ> [ 135.293613] dump_stack_lvl+0x57/0x7d [ 135.293613] __might_resched.cold+0x138/0x173 [ 135.293613] ? dev_coredumpm+0xca/0x2e0 [ 135.293613] kmem_cache_alloc_trace+0x189/0x1f0 [ 135.293613] ? devcd_match_failing+0x30/0x30 [ 135.293613] dev_coredumpm+0xca/0x2e0 [ 135.293613] ? devcd_freev+0x10/0x10 [ 135.293613] dev_coredumpv+0x1c/0x20 [ 135.293613] ? devcd_match_failing+0x30/0x30 [ 135.293613] mwifiex_upload_device_dump+0x65/0xb0 [ 135.293613] ? mwifiex_dnld_fw+0x1b0/0x1b0 [ 135.293613] call_timer_fn+0x122/0x3d0 [ 135.293613] ? msleep_interruptible+0xb0/0xb0 [ 135.293613] ? lock_downgrade+0x3c0/0x3c0 [ 135.293613] ? __next_timer_interrupt+0x13c/0x160 [ 135.293613] ? lockdep_hardirqs_on_prepare+0xe/0x220 [ 135.293613] ? mwifiex_dnld_fw+0x1b0/0x1b0 [ 135.293613] __run_timers.part.0+0x3f8/0x540 [ 135.293613] ? call_timer_fn+0x3d0/0x3d0 [ 135.293613] ? arch_restore_msi_irqs+0x10/0x10 [ 135.293613] ? lapic_next_event+0x31/0x40 [ 135.293613] run_timer_softirq+0x4f/0xb0 [ 135.293613] __do_softirq+0x1c2/0x651 ... [ 135.293613] RIP: 0010:default_idle+0xb/0x10 [ 135.293613] RSP: 0018:ffff888006317e68 EFLAGS: 00000246 [ 135.293613] RAX: ffffffff82ad8d10 RBX: ffff888006301cc0 RCX: ffffffff82ac90e1 [ 135.293613] RDX: ffffed100d9ff1b4 RSI: ffffffff831ad140 RDI: ffffffff82ad8f20 [ 135.293613] RBP: 0000000000000003 R08: 0000000000000000 R09: ffff88806cff8d9b [ 135.293613] R10: ffffed100d9ff1b3 R11: 0000000000000001 R12: ffffffff84593410 [ 135.293613] R13: 0000000000000000 R14: 0000000000000000 R15: 1ffff11000c62fd2 ... [ 135.389205] usb 1-1: == mwifiex dump information to /sys/class/devcoredump end This patch uses delayed work to replace timer and moves the operations that may sleep into a delayed work in order to mitigate bugs, it was tested on Marvell 88W8801 chip whose port is usb and the firmware is usb8801_uapsta.bin. The following is the result after using delayed work to replace timer. [ 134.936453] usb 1-1: == mwifiex dump information to /sys/class/devcoredump start [ 135.043344] usb 1-1: == mwifiex dump information to /sys/class/devcoredump end As we can see, there is no bug now. Fixes: f5ecd02a8b20 ("mwifiex: device dump support for usb interface") Signed-off-by: Duoming Zhou <duoming@zju.edu.cn> Reviewed-by: Brian Norris <briannorris@chromium.org> Acked-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> --- Changes since v6: - Use clang-format to adjust the format of code. drivers/net/wireless/marvell/mwifiex/init.c | 9 +++++---- drivers/net/wireless/marvell/mwifiex/main.h | 3 ++- drivers/net/wireless/marvell/mwifiex/sta_event.c | 6 +++--- 3 files changed, 10 insertions(+), 8 deletions(-)