linux/drivers/net/ethernet/cisco/enic/enic_api.c

40 lines
940 B
C
Raw Permalink Normal View History

// SPDX-License-Identifier: GPL-2.0-only
// Copyright 2013 Cisco Systems, Inc. All rights reserved.
#include <linux/netdevice.h>
#include <linux/spinlock.h>
#include "vnic_dev.h"
#include "vnic_devcmd.h"
#include "enic_res.h"
#include "enic.h"
#include "enic_api.h"
int enic_api_devcmd_proxy_by_index(struct net_device *netdev, int vf,
enum vnic_devcmd_cmd cmd, u64 *a0, u64 *a1, int wait)
{
int err;
struct enic *enic = netdev_priv(netdev);
struct vnic_dev *vdev = enic->vdev;
spin_lock(&enic->enic_api_lock);
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>
2020-09-29 22:25:10 +02:00
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);
err = vnic_dev_cmd(vdev, cmd, a0, a1, wait);
vnic_dev_cmd_proxy_end(vdev);
spin_unlock_bh(&enic->devcmd_lock);
spin_unlock(&enic->enic_api_lock);
return err;
}
EXPORT_SYMBOL(enic_api_devcmd_proxy_by_index);