TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Thomas Hellstrom
On 10/21/2013 03:21 PM, Maarten Lankhorst wrote: > op 21-10-13 13:10, Thomas Hellstrom schreef: >> On 10/21/2013 12:24 PM, Maarten Lankhorst wrote: >>> op 21-10-13 12:10, Thomas Hellstrom schreef: On 10/21/2013 11:48 AM, Maarten Lankhorst wrote: > op 21-10-13 11:37, Thomas Hellstrom

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Maarten Lankhorst
op 21-10-13 13:10, Thomas Hellstrom schreef: > On 10/21/2013 12:24 PM, Maarten Lankhorst wrote: >> op 21-10-13 12:10, Thomas Hellstrom schreef: >>> On 10/21/2013 11:48 AM, Maarten Lankhorst wrote: op 21-10-13 11:37, Thomas Hellstrom schreef: > On 10/21/2013 11:01 AM, Maarten Lankhorst

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Thomas Hellstrom
On 10/21/2013 12:24 PM, Maarten Lankhorst wrote: > op 21-10-13 12:10, Thomas Hellstrom schreef: >> On 10/21/2013 11:48 AM, Maarten Lankhorst wrote: >>> op 21-10-13 11:37, Thomas Hellstrom schreef: On 10/21/2013 11:01 AM, Maarten Lankhorst wrote: > op 21-10-13 10:48, Thomas Hellstrom

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Maarten Lankhorst
op 21-10-13 12:10, Thomas Hellstrom schreef: > On 10/21/2013 11:48 AM, Maarten Lankhorst wrote: >> op 21-10-13 11:37, Thomas Hellstrom schreef: >>> On 10/21/2013 11:01 AM, Maarten Lankhorst wrote: op 21-10-13 10:48, Thomas Hellstrom schreef: > Hi! > > As discussed previously the

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Thomas Hellstrom
On 10/21/2013 11:48 AM, Maarten Lankhorst wrote: > op 21-10-13 11:37, Thomas Hellstrom schreef: >> On 10/21/2013 11:01 AM, Maarten Lankhorst wrote: >>> op 21-10-13 10:48, Thomas Hellstrom schreef: Hi! As discussed previously the current locking order in TTM of these locks is

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Maarten Lankhorst
op 21-10-13 11:37, Thomas Hellstrom schreef: > On 10/21/2013 11:01 AM, Maarten Lankhorst wrote: >> op 21-10-13 10:48, Thomas Hellstrom schreef: >>> Hi! >>> >>> As discussed previously the current locking order in TTM of these locks is >>> bo::reserve -> vm::mmap_sem. This leads to a hack in >>>

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Thomas Hellstrom
On 10/21/2013 11:01 AM, Maarten Lankhorst wrote: > op 21-10-13 10:48, Thomas Hellstrom schreef: >> Hi! >> >> As discussed previously the current locking order in TTM of these locks is >> bo::reserve -> vm::mmap_sem. This leads to a hack in >> the TTM fault() handle to try and revert the locking

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Jakob Bornecrantz
On Mon, Oct 21, 2013 at 10:48 AM, Thomas Hellstrom wrote: > Hi! > > As discussed previously the current locking order in TTM of these locks is > bo::reserve -> vm::mmap_sem. This leads to a hack in > the TTM fault() handle to try and revert the locking order. If a tryreserve > failed, we tried to

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Maarten Lankhorst
op 21-10-13 10:48, Thomas Hellstrom schreef: > Hi! > > As discussed previously the current locking order in TTM of these locks is > bo::reserve -> vm::mmap_sem. This leads to a hack in > the TTM fault() handle to try and revert the locking order. If a tryreserve > failed, we tried to have the vm

TTM Locking order of bo::reserve -> vm::mmap_sem

2013-10-21 Thread Thomas Hellstrom
Hi! As discussed previously the current locking order in TTM of these locks is bo::reserve -> vm::mmap_sem. This leads to a hack in the TTM fault() handle to try and revert the locking order. If a tryreserve failed, we tried to have the vm code release the mmap_sem() and then schedule, to give