net: Eliminate flush_scheduled_work() calls while RTNL is held.
If the RTNL is held when we invoke flush_scheduled_work() we could
deadlock. One such case is linkwatch, it is a work struct which tries
to grab the RTNL semaphore.
The most common case are net driver ->stop() methods. The
simplest conversion is to instead use cancel_{delayed_}work_sync()
explicitly on the various work struct the driver uses.
This is an OK transformation because these work structs are doing
things like resetting the chip, restarting link negotiation, and so
forth. And if we're bringing down the device, we're about to turn the
chip off and reset it anways. So if we cancel a pending work event,
that's fine here.
Some drivers were working around this deadlock by using a msleep()
polling loop of some sort, and those cases are converted to instead
use cancel_{delayed_}work_sync() as well.
Signed-off-by: David S. Miller <davem@davemloft.net>
diff --git a/drivers/net/bnx2.c b/drivers/net/bnx2.c
index 4b46e68..367b6d4 100644
--- a/drivers/net/bnx2.c
+++ b/drivers/net/bnx2.c
@@ -5724,14 +5724,12 @@
if (!netif_running(bp->dev))
return;
- bp->in_reset_task = 1;
bnx2_netif_stop(bp);
bnx2_init_nic(bp);
atomic_set(&bp->intr_sem, 1);
bnx2_netif_start(bp);
- bp->in_reset_task = 0;
}
static void
@@ -5907,12 +5905,7 @@
struct bnx2 *bp = netdev_priv(dev);
u32 reset_code;
- /* Calling flush_scheduled_work() may deadlock because
- * linkwatch_event() may be on the workqueue and it will try to get
- * the rtnl_lock which we are holding.
- */
- while (bp->in_reset_task)
- msleep(1);
+ cancel_work_sync(&bp->reset_task);
bnx2_disable_int_sync(bp);
bnx2_napi_disable(bp);
diff --git a/drivers/net/bnx2.h b/drivers/net/bnx2.h
index 1eaf5bb..2377cc1 100644
--- a/drivers/net/bnx2.h
+++ b/drivers/net/bnx2.h
@@ -6656,7 +6656,6 @@
int current_interval;
struct timer_list timer;
struct work_struct reset_task;
- int in_reset_task;
/* Used to synchronize phy accesses. */
spinlock_t phy_lock;
diff --git a/drivers/net/ehea/ehea_main.c b/drivers/net/ehea/ehea_main.c
index faae01d..075fd54 100644
--- a/drivers/net/ehea/ehea_main.c
+++ b/drivers/net/ehea/ehea_main.c
@@ -2605,7 +2605,8 @@
if (netif_msg_ifdown(port))
ehea_info("disabling port %s", dev->name);
- flush_scheduled_work();
+ cancel_work_sync(&port->reset_task);
+
mutex_lock(&port->port_lock);
netif_stop_queue(dev);
port_napi_disable(port);
diff --git a/drivers/net/hamradio/baycom_epp.c b/drivers/net/hamradio/baycom_epp.c
index dde9c7e..00bc7fb 100644
--- a/drivers/net/hamradio/baycom_epp.c
+++ b/drivers/net/hamradio/baycom_epp.c
@@ -959,7 +959,7 @@
unsigned char tmp[1];
bc->work_running = 0;
- flush_scheduled_work();
+ cancel_delayed_work_sync(&bc->run_work);
bc->stat = EPP_DCDBIT;
tmp[0] = 0;
pp->ops->epp_write_addr(pp, tmp, 1, 0);
diff --git a/drivers/net/smc911x.c b/drivers/net/smc911x.c
index 4e28002..e2ee91a 100644
--- a/drivers/net/smc911x.c
+++ b/drivers/net/smc911x.c
@@ -136,7 +136,6 @@
/* work queue */
struct work_struct phy_configure;
- int work_pending;
int tx_throttle;
spinlock_t lock;
@@ -960,11 +959,11 @@
* We should not be called if phy_type is zero.
*/
if (lp->phy_type == 0)
- goto smc911x_phy_configure_exit_nolock;
+ return;
if (smc911x_phy_reset(dev, phyaddr)) {
printk("%s: PHY reset timed out\n", dev->name);
- goto smc911x_phy_configure_exit_nolock;
+ return;
}
spin_lock_irqsave(&lp->lock, flags);
@@ -1033,8 +1032,6 @@
smc911x_phy_configure_exit:
spin_unlock_irqrestore(&lp->lock, flags);
-smc911x_phy_configure_exit_nolock:
- lp->work_pending = 0;
}
/*
@@ -1356,11 +1353,8 @@
* smc911x_phy_configure() calls msleep() which calls schedule_timeout()
* which calls schedule(). Hence we use a work queue.
*/
- if (lp->phy_type != 0) {
- if (schedule_work(&lp->phy_configure)) {
- lp->work_pending = 1;
- }
- }
+ if (lp->phy_type != 0)
+ schedule_work(&lp->phy_configure);
/* We can accept TX packets again */
dev->trans_start = jiffies;
@@ -1531,16 +1525,8 @@
if (lp->phy_type != 0) {
/* We need to ensure that no calls to
* smc911x_phy_configure are pending.
-
- * flush_scheduled_work() cannot be called because we
- * are running with the netlink semaphore held (from
- * devinet_ioctl()) and the pending work queue
- * contains linkwatch_event() (scheduled by
- * netif_carrier_off() above). linkwatch_event() also
- * wants the netlink semaphore.
*/
- while (lp->work_pending)
- schedule();
+ cancel_work_sync(&lp->phy_configure);
smc911x_phy_powerdown(dev, lp->mii.phy_id);
}
diff --git a/drivers/net/smc91x.c b/drivers/net/smc91x.c
index a188e33..f2051b2 100644
--- a/drivers/net/smc91x.c
+++ b/drivers/net/smc91x.c
@@ -1016,15 +1016,8 @@
/* We need to ensure that no calls to smc_phy_configure are
pending.
-
- flush_scheduled_work() cannot be called because we are
- running with the netlink semaphore held (from
- devinet_ioctl()) and the pending work queue contains
- linkwatch_event() (scheduled by netif_carrier_off()
- above). linkwatch_event() also wants the netlink semaphore.
*/
- while(lp->work_pending)
- yield();
+ cancel_work_sync(&lp->phy_configure);
bmcr = smc_phy_read(dev, phy, MII_BMCR);
smc_phy_write(dev, phy, MII_BMCR, bmcr | BMCR_PDOWN);
@@ -1161,7 +1154,6 @@
smc_phy_configure_exit:
SMC_SELECT_BANK(lp, 2);
spin_unlock_irq(&lp->lock);
- lp->work_pending = 0;
}
/*
@@ -1389,11 +1381,8 @@
* smc_phy_configure() calls msleep() which calls schedule_timeout()
* which calls schedule(). Hence we use a work queue.
*/
- if (lp->phy_type != 0) {
- if (schedule_work(&lp->phy_configure)) {
- lp->work_pending = 1;
- }
- }
+ if (lp->phy_type != 0)
+ schedule_work(&lp->phy_configure);
/* We can accept TX packets again */
dev->trans_start = jiffies;
diff --git a/drivers/net/tulip/tulip_core.c b/drivers/net/tulip/tulip_core.c
index 55670b5..af8d2c4 100644
--- a/drivers/net/tulip/tulip_core.c
+++ b/drivers/net/tulip/tulip_core.c
@@ -731,7 +731,7 @@
void __iomem *ioaddr = tp->base_addr;
unsigned long flags;
- flush_scheduled_work();
+ cancel_work_sync(&tp->media_work);
#ifdef CONFIG_TULIP_NAPI
napi_disable(&tp->napi);
diff --git a/drivers/net/usb/kaweth.c b/drivers/net/usb/kaweth.c
index 0dcfc03..7c66b05 100644
--- a/drivers/net/usb/kaweth.c
+++ b/drivers/net/usb/kaweth.c
@@ -706,7 +706,7 @@
usb_kill_urb(kaweth->rx_urb);
usb_kill_urb(kaweth->tx_urb);
- flush_scheduled_work();
+ cancel_delayed_work_sync(&kaweth->lowmem_work);
/* a scheduled work may have resubmitted,
we hit them again */
diff --git a/drivers/net/wireless/hostap/hostap_main.c b/drivers/net/wireless/hostap/hostap_main.c
index 20d387f..f7aec93 100644
--- a/drivers/net/wireless/hostap/hostap_main.c
+++ b/drivers/net/wireless/hostap/hostap_main.c
@@ -682,7 +682,13 @@
netif_device_detach(dev);
}
- flush_scheduled_work();
+ cancel_work_sync(&local->reset_queue);
+ cancel_work_sync(&local->set_multicast_list_queue);
+ cancel_work_sync(&local->set_tim_queue);
+#ifndef PRISM2_NO_STATION_MODES
+ cancel_work_sync(&local->info_queue);
+#endif
+ cancel_work_sync(&local->comms_qual_update);
module_put(local->hw_module);