Re: [PATCH] dax: fix deadlock with DAX 4k holes

2017-01-04 Thread Xiong Zhou
On Tue, Jan 03, 2017 at 02:36:05PM -0700, Ross Zwisler wrote: > Currently in DAX if we have three read faults on the same hole address we > can end up with the following: > > Thread 0 Thread 1Thread 2 > >

Re: [PATCH] dax: fix deadlock with DAX 4k holes

2017-01-04 Thread Xiong Zhou
On Tue, Jan 03, 2017 at 02:36:05PM -0700, Ross Zwisler wrote: > Currently in DAX if we have three read faults on the same hole address we > can end up with the following: > > Thread 0 Thread 1Thread 2 > >

Re: [PATCH] dax: fix deadlock with DAX 4k holes

2017-01-03 Thread Jan Kara
On Tue 03-01-17 14:36:05, Ross Zwisler wrote: > Currently in DAX if we have three read faults on the same hole address we > can end up with the following: > > Thread 0 Thread 1Thread 2 > > dax_iomap_fault >

Re: [PATCH] dax: fix deadlock with DAX 4k holes

2017-01-03 Thread Jan Kara
On Tue 03-01-17 14:36:05, Ross Zwisler wrote: > Currently in DAX if we have three read faults on the same hole address we > can end up with the following: > > Thread 0 Thread 1Thread 2 > > dax_iomap_fault >

[PATCH] dax: fix deadlock with DAX 4k holes

2017-01-03 Thread Ross Zwisler
Currently in DAX if we have three read faults on the same hole address we can end up with the following: Thread 0Thread 1Thread 2 dax_iomap_fault grab_mapping_entry lock_slot

[PATCH] dax: fix deadlock with DAX 4k holes

2017-01-03 Thread Ross Zwisler
Currently in DAX if we have three read faults on the same hole address we can end up with the following: Thread 0Thread 1Thread 2 dax_iomap_fault grab_mapping_entry lock_slot