net: enic: Cure the enic api locking trainwreck

enic_dev_wait() has a BUG_ON(in_interrupt()).

Chasing the callers of enic_dev_wait() revealed the gems of enic_reset()
and enic_tx_hang_reset() which are both invoked through work queues in
order to be able to call rtnl_lock(). So far so good.

After locking rtnl both functions acquire enic::enic_api_lock which
serializes against the (ab)use from infiniband. This is where the
trainwreck starts.

enic::enic_api_lock is a spin_lock() which implicitly disables preemption,
but both functions invoke a ton of functions under that lock which can
sleep. The BUG_ON(in_interrupt()) does not trigger in that case because it
can't detect the preempt disabled condition.

This clearly has never been tested with any of the mandatory debug options
for 7+ years, which would have caught that for sure.

Cure it by adding a enic_api_busy member to struct enic, which is modified
and evaluated with enic::enic_api_lock held.

If enic_api_devcmd_proxy_by_index() observes enic::enic_api_busy as true,
it drops enic::enic_api_lock and busy waits for enic::enic_api_busy to
become false.

It would be smarter to wait for a completion of that busy period, but
enic_api_devcmd_proxy_by_index() is called with other spin locks held which
obviously can't sleep.

Remove the BUG_ON(in_interrupt()) check as well because it's incomplete and
with proper debugging enabled the problem would have been caught from the
debug checks in schedule_timeout().

Fixes: 0b038566c0ea ("drivers/net: enic: Add an interface for USNIC to interact with firmware")
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: David S. Miller <davem@davemloft.net>

diff --git a/drivers/net/ethernet/cisco/enic/enic.h b/drivers/net/ethernet/cisco/enic/enic.h
index 18f3aeb88f22a11d45ca967fd3c908bec4ef7967..c67a16a48d624bceb4758e5be1cdca7d3c3e78bd 100644 (file)
--- a/drivers/net/ethernet/cisco/enic/enic.h
+++ b/drivers/net/ethernet/cisco/enic/enic.h
@@ -169,6 +169,7 @@ struct enic {
        u16 num_vfs;
 #endif
        spinlock_t enic_api_lock;
+       bool enic_api_busy;
        struct enic_port_profile *pp;
 
        /* work queue cache line section */

diff --git a/drivers/net/ethernet/cisco/enic/enic_api.c b/drivers/net/ethernet/cisco/enic/enic_api.c
index 89915681473c20007dc05df0662ae7e6d19c8b2d..3bdc74fba1e333bef390dc1426e9fdf76f110cf1 100644 (file)
--- a/drivers/net/ethernet/cisco/enic/enic_api.c
+++ b/drivers/net/ethernet/cisco/enic/enic_api.c
@@ -34,6 +34,12 @@ int enic_api_devcmd_proxy_by_index(struct net_device *netdev, int vf,
        struct vnic_dev *vdev = enic->vdev;
 
        spin_lock(&enic->enic_api_lock);
+       while (enic->enic_api_busy) {
+               spin_unlock(&enic->enic_api_lock);
+               cpu_relax();
+               spin_lock(&enic->enic_api_lock);
+       }
+
        spin_lock_bh(&enic->devcmd_lock);
 
        vnic_dev_cmd_proxy_by_index_start(vdev, vf);

diff --git a/drivers/net/ethernet/cisco/enic/enic_main.c b/drivers/net/ethernet/cisco/enic/enic_main.c
index 4f0329d8778f8974bd900fb660c941daa1c9d74d..fb269d587b741d9d7a3a109bb8cbc87191ee3b51 100644 (file)
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2107,8 +2107,6 @@ static int enic_dev_wait(struct vnic_dev *vdev,
        int done;
        int err;
 
-       BUG_ON(in_interrupt());
-
        err = start(vdev, arg);
        if (err)
                return err;
@@ -2297,6 +2295,13 @@ static int enic_set_rss_nic_cfg(struct enic *enic)
                rss_hash_bits, rss_base_cpu, rss_enable);
 }
 
+static void enic_set_api_busy(struct enic *enic, bool busy)
+{
+       spin_lock(&enic->enic_api_lock);
+       enic->enic_api_busy = busy;
+       spin_unlock(&enic->enic_api_lock);
+}
+
 static void enic_reset(struct work_struct *work)
 {
        struct enic *enic = container_of(work, struct enic, reset);
@@ -2306,7 +2311,9 @@ static void enic_reset(struct work_struct *work)
 
        rtnl_lock();
 
-       spin_lock(&enic->enic_api_lock);
+       /* Stop any activity from infiniband */
+       enic_set_api_busy(enic, true);
+
        enic_stop(enic->netdev);
        enic_dev_soft_reset(enic);
        enic_reset_addr_lists(enic);
@@ -2314,7 +2321,10 @@ static void enic_reset(struct work_struct *work)
        enic_set_rss_nic_cfg(enic);
        enic_dev_set_ig_vlan_rewrite_mode(enic);
        enic_open(enic->netdev);
-       spin_unlock(&enic->enic_api_lock);
+
+       /* Allow infiniband to fiddle with the device again */
+       enic_set_api_busy(enic, false);
+
        call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
        rtnl_unlock();
@@ -2326,7 +2336,9 @@ static void enic_tx_hang_reset(struct work_struct *work)
 
        rtnl_lock();
 
-       spin_lock(&enic->enic_api_lock);
+       /* Stop any activity from infiniband */
+       enic_set_api_busy(enic, true);
+
        enic_dev_hang_notify(enic);
        enic_stop(enic->netdev);
        enic_dev_hang_reset(enic);
@@ -2335,7 +2347,10 @@ static void enic_tx_hang_reset(struct work_struct *work)
        enic_set_rss_nic_cfg(enic);
        enic_dev_set_ig_vlan_rewrite_mode(enic);
        enic_open(enic->netdev);
-       spin_unlock(&enic->enic_api_lock);
+
+       /* Allow infiniband to fiddle with the device again */
+       enic_set_api_busy(enic, false);
+
        call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
        rtnl_unlock();