[01/35] net: enic: Cure the enic api locking trainwreck

Commit Message

Thomas Gleixner Sept. 27, 2020, 7:48 p.m. UTC

From: Thomas Gleixner <[e-mail]>

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 <[e-mail]>
Cc: Christian Benvenuti <[e-mail]>
Cc: Govindarajulu Varadarajan <[e-mail]>
Cc: Dave Miller <[e-mail]>
Cc: Jakub Kicinski <[e-mail]>
Cc: [e-mail]
---
 drivers/net/ethernet/cisco/enic/enic.h      |    1 +
 drivers/net/ethernet/cisco/enic/enic_api.c  |    6 ++++++
 drivers/net/ethernet/cisco/enic/enic_main.c |   27 +++++++++++++++++++++------
 3 files changed, 28 insertions(+), 6 deletions(-)

Patch

--- 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 */
--- 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(struc
 	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);
--- a/drivers/net/ethernet/cisco/enic/enic_main.c
+++ b/drivers/net/ethernet/cisco/enic/enic_main.c
@@ -2106,8 +2106,6 @@  static int enic_dev_wait(struct vnic_dev
 	int done;
 	int err;
 
-	BUG_ON(in_interrupt());
-
 	err = start(vdev, arg);
 	if (err)
 		return err;
@@ -2295,6 +2293,13 @@  static int enic_set_rss_nic_cfg(struct e
 		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);
@@ -2304,7 +2309,9 @@  static void enic_reset(struct work_struc
 
 	rtnl_lock();
 
-	spin_lock(&enic->enic_api_lock);
+	/* Stop any activity from infiniband */
+	enic_set_api_state(enic, true);
+
 	enic_stop(enic->netdev);
 	enic_dev_soft_reset(enic);
 	enic_reset_addr_lists(enic);
@@ -2312,7 +2319,10 @@  static void enic_reset(struct work_struc
 	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_state(enic, false);
+
 	call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
 	rtnl_unlock();
@@ -2324,7 +2334,9 @@  static void enic_tx_hang_reset(struct wo
 
 	rtnl_lock();
 
-	spin_lock(&enic->enic_api_lock);
+	/* Stop any activity from infiniband */
+	enic_set_api_state(enic, true);
+
 	enic_dev_hang_notify(enic);
 	enic_stop(enic->netdev);
 	enic_dev_hang_reset(enic);
@@ -2333,7 +2345,10 @@  static void enic_tx_hang_reset(struct wo
 	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_state(enic, false);
+
 	call_netdevice_notifiers(NETDEV_REBOOT, enic->netdev);
 
 	rtnl_unlock();