mwifiex: fix sleep in atomic context bugs caused by dev_coredumpv

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: f5ecd02a8b ("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>
Signed-off-by: Kalle Valo <kvalo@kernel.org>
Link: https://lore.kernel.org/r/5cfa5c473ff6d069cb67760ffa04a2f84ef450a8.1661252818.git.duoming@zju.edu.cn
This commit is contained in:
Duoming Zhou 2022-08-23 19:21:27 +08:00 committed by Kalle Valo
parent 4c3140f4ce
commit 551e4745c7
3 changed files with 10 additions and 8 deletions

View File

@ -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);

View File

@ -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;
};

View File

@ -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);
}