thunderbolt: Use separate lock class for each ring

When connected to another host and then unplugging cable lockdep
triggers following:

 ======================================================
 WARNING: possible circular locking dependency detected
 7.1.0-rc2+ #1775 Tainted: G     U
 ------------------------------------------------------
 kworker/u16:6/312 is trying to acquire lock:
 ffff8881179c70a8 ((work_completion)(&ring->work)){+.+.}-{0:0}, at: __flush_work+0x3cf/0xd10

 but task is already holding lock:
 ffff8881a8b810b0 (&net->connection_lock){+.+.}-{4:4}, at: tbnet_tear_down+0x110/0x720 [thunderbolt_net]

 which lock already depends on the new lock.

 the existing dependency chain (in reverse order) is:

 -> #1 (&net->connection_lock){+.+.}-{4:4}:
        __mutex_lock+0x19a/0x2490
        mutex_lock_nested+0x1b/0x30
        tbnet_handle_packet+0x74c/0xd70 [thunderbolt_net]
        tb_xdomain_handle_request+0x37c/0x4b0 [thunderbolt]
        tb_domain_event_cb+0xc9/0x140 [thunderbolt]
        tb_ctl_handle_event+0xd6/0x2c0 [thunderbolt]
        tb_ctl_rx_callback+0x22c/0xa10 [thunderbolt]
        ring_work+0x715/0xcb0 [thunderbolt]
        process_one_work+0x902/0x1790
        worker_thread+0x5cd/0xfe0
        kthread+0x339/0x420
        ret_from_fork+0x79a/0x9d0
        ret_from_fork_asm+0x1a/0x30

 -> #0 ((work_completion)(&ring->work)){+.+.}-{0:0}:
        __lock_acquire+0x1592/0x2640
        lock_acquire+0x1a3/0x300
        __flush_work+0x3e9/0xd10
        flush_work+0x21/0x30
        tb_ring_stop+0x240/0x840 [thunderbolt]
        tbnet_tear_down+0x2ff/0x720 [thunderbolt_net]
        tbnet_stop+0x47/0x1a0 [thunderbolt_net]
        __dev_close_many+0x19e/0x4e0
        netif_close_many+0x1e8/0x640
        unregister_netdevice_many_notify+0x6d3/0x22d0
        unregister_netdevice_queue+0x2b9/0x3a0
        unregister_netdev+0x1c/0x70
        tbnet_remove+0x52/0xb0 [thunderbolt_net]
        tb_service_remove+0x8a/0xe0 [thunderbolt]
        device_remove+0xc5/0x190
        device_release_driver_internal+0x3db/0x590
        device_release_driver+0x12/0x20
        bus_remove_device+0x2c1/0x580
        device_del+0x3d9/0x9f0
        device_unregister+0x17/0xc0
        unregister_service+0x46/0x60 [thunderbolt]
        device_for_each_child_reverse+0xfa/0x180
        tb_xdomain_unregister+0x57/0xe0 [thunderbolt]
        unregister_unplugged_xdomain+0x101/0x1a0 [thunderbolt]
        bus_for_each_dev+0x111/0x1a0
        tb_domain_unregister_unplugged_xdomains+0x98/0xe0 [thunderbolt]
        tb_handle_hotplug+0xc3/0x2bb0 [thunderbolt]
        process_one_work+0x902/0x1790
        worker_thread+0x5cd/0xfe0
        kthread+0x339/0x420
        ret_from_fork+0x79a/0x9d0
        ret_from_fork_asm+0x1a/0x30

 other info that might help us debug this:

  Possible unsafe locking scenario:

        CPU0                    CPU1
        ----                    ----
   lock(&net->connection_lock);
                                lock((work_completion)(&ring->work));
                                lock(&net->connection_lock);
   lock((work_completion)(&ring->work));

This in fact is false positive because they involve unrelated rings (and
unrelated work structures). In the first one it is ring 0 which is used
for control traffic and in the second it is dealing with another ring
used for the high-speed traffic.

Fix this by using separate lock class for each ring worker.

Signed-off-by: Mika Westerberg <mika.westerberg@linux.intel.com>

drivers/thunderbolt/nhi.c

@@ -15,6 +15,7 @@
 #include <linux/dma-mapping.h>
 #include <linux/interrupt.h>
 #include <linux/iommu.h>
+#include <linux/lockdep.h>
 #include <linux/module.h>
 #include <linux/delay.h>
 #include <linux/property.h>
@@ -560,6 +561,8 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
 	INIT_LIST_HEAD(&ring->in_flight);
 	INIT_WORK(&ring->work, ring_work);
 	init_waitqueue_head(&ring->wait);
+	lockdep_register_key(&ring->lock_key);
+	lockdep_init_map(&ring->work.lockdep_map, "ring.work", &ring->lock_key, 0);
 
 	ring->nhi = nhi;
 	ring->hop = hop;
@@ -599,6 +602,7 @@ static struct tb_ring *tb_ring_alloc(struct tb_nhi *nhi, u32 hop, int size,
 			  ring->size * sizeof(*ring->descriptors),
 			  ring->descriptors, ring->descriptors_dma);
 err_free_ring:
+	lockdep_unregister_key(&ring->lock_key);
 	kfree(ring);
 
 	return NULL;
@@ -848,6 +852,7 @@ void tb_ring_free(struct tb_ring *ring)
 	 * to finish before freeing the ring.
 	 */
 	flush_work(&ring->work);
+	lockdep_unregister_key(&ring->lock_key);
 	kfree(ring);
 }
 EXPORT_SYMBOL_GPL(tb_ring_free);

include/linux/thunderbolt.h

@@ -22,6 +22,7 @@ struct device;
 #include <linux/device.h>
 #include <linux/idr.h>
 #include <linux/list.h>
+#include <linux/lockdep.h>
 #include <linux/mutex.h>
 #include <linux/device-id/tb.h>
 #include <linux/pci.h>
@@ -565,6 +566,7 @@ struct tb_nhi {
  * @interval_nsec: Interval counter if interrupt throttling is to be
  *		   used with this ring (in ns)
  * @wait: Used to signal that the ring may be empty now
+ * @lock_key: Lock validator class key per-ring
  */
 struct tb_ring {
 	spinlock_t lock;
@@ -590,6 +592,7 @@ struct tb_ring {
 	void *poll_data;
 	unsigned int interval_nsec;
 	wait_queue_head_t wait;
+	struct lock_class_key lock_key;
 };
 
 /* Leave ring interrupt enabled on suspend */