[PATCH wq/for-4.5-fixes] workqueue: skip flush dependency checks for legacy workqueues

[Tejun Heo <tj@kernel.org>]

fca839c00a12 ("workqueue: warn if memory reclaim tries to flush
!WQ_MEM_RECLAIM workqueue") implemented flush dependency warning which
triggers if a PF_MEMALLOC task or WQ_MEM_RECLAIM workqueue tries to
flush a !WQ_MEM_RECLAIM workquee.

This assumes that workqueues marked with WQ_MEM_RECLAIM sit in memory
reclaim path and making it depend on something which may need more
memory to make forward progress can lead to deadlocks.  Unfortunately,
workqueues created with the legacy create*_workqueue() interface
always have WQ_MEM_RECLAIM regardless of whether they are depended
upon memory reclaim or not.  These spurious WQ_MEM_RECLAIM markings
cause spurious triggering of the flush dependency checks.

  WARNING: CPU: 0 PID: 6 at kernel/workqueue.c:2361 check_flush_dependency+0x138/0x144()
  workqueue: WQ_MEM_RECLAIM deferwq:deferred_probe_work_func is flushing !WQ_MEM_RECLAIM events:lru_add_drain_per_cpu
  ...
  Workqueue: deferwq deferred_probe_work_func
  [<c0017acc>] (unwind_backtrace) from [<c0013134>] (show_stack+0x10/0x14)
  [<c0013134>] (show_stack) from [<c0245f18>] (dump_stack+0x94/0xd4)
  [<c0245f18>] (dump_stack) from [<c0026f9c>] (warn_slowpath_common+0x80/0xb0)
  [<c0026f9c>] (warn_slowpath_common) from [<c0026ffc>] (warn_slowpath_fmt+0x30/0x40)
  [<c0026ffc>] (warn_slowpath_fmt) from [<c00390b8>] (check_flush_dependency+0x138/0x144)
  [<c00390b8>] (check_flush_dependency) from [<c0039ca0>] (flush_work+0x50/0x15c)
  [<c0039ca0>] (flush_work) from [<c00c51b0>] (lru_add_drain_all+0x130/0x180)
  [<c00c51b0>] (lru_add_drain_all) from [<c00f728c>] (migrate_prep+0x8/0x10)
  [<c00f728c>] (migrate_prep) from [<c00bfbc4>] (alloc_contig_range+0xd8/0x338)
  [<c00bfbc4>] (alloc_contig_range) from [<c00f8f18>] (cma_alloc+0xe0/0x1ac)
  [<c00f8f18>] (cma_alloc) from [<c001cac4>] (__alloc_from_contiguous+0x38/0xd8)
  [<c001cac4>] (__alloc_from_contiguous) from [<c001ceb4>] (__dma_alloc+0x240/0x278)
  [<c001ceb4>] (__dma_alloc) from [<c001cf78>] (arm_dma_alloc+0x54/0x5c)
  [<c001cf78>] (arm_dma_alloc) from [<c0355ea4>] (dmam_alloc_coherent+0xc0/0xec)
  [<c0355ea4>] (dmam_alloc_coherent) from [<c039cc4c>] (ahci_port_start+0x150/0x1dc)
  [<c039cc4c>] (ahci_port_start) from [<c0384734>] (ata_host_start.part.3+0xc8/0x1c8)
  [<c0384734>] (ata_host_start.part.3) from [<c03898dc>] (ata_host_activate+0x50/0x148)
  [<c03898dc>] (ata_host_activate) from [<c039d558>] (ahci_host_activate+0x44/0x114)
  [<c039d558>] (ahci_host_activate) from [<c039f05c>] (ahci_platform_init_host+0x1d8/0x3c8)
  [<c039f05c>] (ahci_platform_init_host) from [<c039e6bc>] (tegra_ahci_probe+0x448/0x4e8)
  [<c039e6bc>] (tegra_ahci_probe) from [<c0347058>] (platform_drv_probe+0x50/0xac)
  [<c0347058>] (platform_drv_probe) from [<c03458cc>] (driver_probe_device+0x214/0x2c0)
  [<c03458cc>] (driver_probe_device) from [<c0343cc0>] (bus_for_each_drv+0x60/0x94)
  [<c0343cc0>] (bus_for_each_drv) from [<c03455d8>] (__device_attach+0xb0/0x114)
  [<c03455d8>] (__device_attach) from [<c0344ab8>] (bus_probe_device+0x84/0x8c)
  [<c0344ab8>] (bus_probe_device) from [<c0344f48>] (deferred_probe_work_func+0x68/0x98)
  [<c0344f48>] (deferred_probe_work_func) from [<c003b738>] (process_one_work+0x120/0x3f8)
  [<c003b738>] (process_one_work) from [<c003ba48>] (worker_thread+0x38/0x55c)
  [<c003ba48>] (worker_thread) from [<c0040f14>] (kthread+0xdc/0xf4)
  [<c0040f14>] (kthread) from [<c000f778>] (ret_from_fork+0x14/0x3c)

Fix it by marking workqueues created via create*_workqueue() with
__WQ_LEGACY and disabling flush dependency checks on them.

Signed-off-by: Tejun Heo <tj@kernel.org>
Reported-by: Thierry Reding <thierry.reding@gmail.com>
Link: http://lkml.kernel.org/g/20160126173843.GA11115@ulmo.nvidia.com
---
Hello, Thierry.

Can youp please verify the fix?

Thanks.

 include/linux/workqueue.h |    9 +++++----
 kernel/workqueue.c        |    3 ++-
 2 files changed, 7 insertions(+), 5 deletions(-)

diff --git a/include/linux/workqueue.h b/include/linux/workqueue.h
index 0e32bc7..ca73c50 100644
--- a/include/linux/workqueue.h
+++ b/include/linux/workqueue.h
@@ -311,6 +311,7 @@ enum {
 
 	__WQ_DRAINING		= 1 << 16, /* internal: workqueue is draining */
 	__WQ_ORDERED		= 1 << 17, /* internal: workqueue is ordered */
+	__WQ_LEGACY		= 1 << 18, /* internal: create*_workqueue() */
 
 	WQ_MAX_ACTIVE		= 512,	  /* I like 512, better ideas? */
 	WQ_MAX_UNBOUND_PER_CPU	= 4,	  /* 4 * #cpus for unbound wq */
@@ -411,12 +412,12 @@ __alloc_workqueue_key(const char *fmt, unsigned int flags, int max_active,
 	alloc_workqueue(fmt, WQ_UNBOUND | __WQ_ORDERED | (flags), 1, ##args)
 
 #define create_workqueue(name)						\
-	alloc_workqueue("%s", WQ_MEM_RECLAIM, 1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, 1, (name))
 #define create_freezable_workqueue(name)				\
-	alloc_workqueue("%s", WQ_FREEZABLE | WQ_UNBOUND | WQ_MEM_RECLAIM, \
-			1, (name))
+	alloc_workqueue("%s", __WQ_LEGACY | WQ_FREEZABLE | WQ_UNBOUND |	\
+			WQ_MEM_RECLAIM, 1, (name))
 #define create_singlethread_workqueue(name)				\
-	alloc_ordered_workqueue("%s", WQ_MEM_RECLAIM, name)
+	alloc_ordered_workqueue("%s", __WQ_LEGACY | WQ_MEM_RECLAIM, name)
 
 extern void destroy_workqueue(struct workqueue_struct *wq);
 
diff --git a/kernel/workqueue.c b/kernel/workqueue.c
index 61a0264..dc7faad 100644
--- a/kernel/workqueue.c
+++ b/kernel/workqueue.c
@@ -2355,7 +2355,8 @@ static void check_flush_dependency(struct workqueue_struct *target_wq,
 	WARN_ONCE(current->flags & PF_MEMALLOC,
 		  "workqueue: PF_MEMALLOC task %d(%s) is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  current->pid, current->comm, target_wq->name, target_func);
-	WARN_ONCE(worker && (worker->current_pwq->wq->flags & WQ_MEM_RECLAIM),
+	WARN_ONCE(worker && ((worker->current_pwq->wq->flags &
+			      (WQ_MEM_RECLAIM | __WQ_LEGACY)) == WQ_MEM_RECLAIM),
 		  "workqueue: WQ_MEM_RECLAIM %s:%pf is flushing !WQ_MEM_RECLAIM %s:%pf",
 		  worker->current_pwq->wq->name, worker->current_func,
 		  target_wq->name, target_func);