Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-30 Thread Joonsoo Kim
On Mon, Jul 29, 2013 at 11:53:05AM -0700, Davidlohr Bueso wrote: > On Mon, 2013-07-29 at 14:31 +0900, Joonsoo Kim wrote: > > There is a race condition if we map a same file on different processes. > > Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. > > When we do mmap, we

Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-30 Thread Joonsoo Kim
On Mon, Jul 29, 2013 at 04:58:57PM +0800, Hillf Danton wrote: > On Mon, Jul 29, 2013 at 1:31 PM, Joonsoo Kim wrote: > > There is a race condition if we map a same file on different processes. > > Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. > > When we do mmap, we

Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-30 Thread Joonsoo Kim
On Mon, Jul 29, 2013 at 04:58:57PM +0800, Hillf Danton wrote: On Mon, Jul 29, 2013 at 1:31 PM, Joonsoo Kim iamjoonsoo@lge.com wrote: There is a race condition if we map a same file on different processes. Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. When we

Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-30 Thread Joonsoo Kim
On Mon, Jul 29, 2013 at 11:53:05AM -0700, Davidlohr Bueso wrote: On Mon, 2013-07-29 at 14:31 +0900, Joonsoo Kim wrote: There is a race condition if we map a same file on different processes. Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. When we do mmap, we don't

Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-29 Thread Davidlohr Bueso
On Mon, 2013-07-29 at 14:31 +0900, Joonsoo Kim wrote: > There is a race condition if we map a same file on different processes. > Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. > When we do mmap, we don't grab a hugetlb_instantiation_mutex, but, > grab a mmap_sem. This

Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-29 Thread Hillf Danton
On Mon, Jul 29, 2013 at 1:31 PM, Joonsoo Kim wrote: > There is a race condition if we map a same file on different processes. > Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. > When we do mmap, we don't grab a hugetlb_instantiation_mutex, but, > grab a mmap_sem. This

Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-29 Thread Hillf Danton
On Mon, Jul 29, 2013 at 1:31 PM, Joonsoo Kim iamjoonsoo@lge.com wrote: There is a race condition if we map a same file on different processes. Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. When we do mmap, we don't grab a hugetlb_instantiation_mutex, but, grab a

Re: [PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-29 Thread Davidlohr Bueso
On Mon, 2013-07-29 at 14:31 +0900, Joonsoo Kim wrote: There is a race condition if we map a same file on different processes. Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. When we do mmap, we don't grab a hugetlb_instantiation_mutex, but, grab a mmap_sem. This

[PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-28 Thread Joonsoo Kim
There is a race condition if we map a same file on different processes. Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. When we do mmap, we don't grab a hugetlb_instantiation_mutex, but, grab a mmap_sem. This doesn't prevent other process to modify region structure, so it

[PATCH 05/18] mm, hugetlb: protect region tracking via newly introduced resv_map lock

2013-07-28 Thread Joonsoo Kim
There is a race condition if we map a same file on different processes. Region tracking is protected by mmap_sem and hugetlb_instantiation_mutex. When we do mmap, we don't grab a hugetlb_instantiation_mutex, but, grab a mmap_sem. This doesn't prevent other process to modify region structure, so it