Re: thp and memory barrier assumptions

2012-08-03 Thread Andrea Arcangeli
On Thu, Jul 26, 2012 at 10:33:25PM +0200, Peter Zijlstra wrote: > On Thu, 2012-07-26 at 22:31 +0200, Peter Zijlstra wrote: > > __do_huge_pmd_anonymous_page() contains: > > > > /* > > * The spinlocking to take the lru_lock inside > > *

Re: thp and memory barrier assumptions

2012-08-03 Thread Andrea Arcangeli
On Thu, Jul 26, 2012 at 10:33:25PM +0200, Peter Zijlstra wrote: On Thu, 2012-07-26 at 22:31 +0200, Peter Zijlstra wrote: __do_huge_pmd_anonymous_page() contains: /* * The spinlocking to take the lru_lock inside *

Re: thp and memory barrier assumptions

2012-07-26 Thread Peter Zijlstra
On Thu, 2012-07-26 at 22:31 +0200, Peter Zijlstra wrote: > __do_huge_pmd_anonymous_page() contains: > > /* > * The spinlocking to take the lru_lock inside > * page_add_new_anon_rmap() acts as a full memory > * barrier to be sure

thp and memory barrier assumptions

2012-07-26 Thread Peter Zijlstra
__do_huge_pmd_anonymous_page() contains: /* * The spinlocking to take the lru_lock inside * page_add_new_anon_rmap() acts as a full memory * barrier to be sure clear_huge_page writes become * visible after the

thp and memory barrier assumptions

2012-07-26 Thread Peter Zijlstra
__do_huge_pmd_anonymous_page() contains: /* * The spinlocking to take the lru_lock inside * page_add_new_anon_rmap() acts as a full memory * barrier to be sure clear_huge_page writes become * visible after the

Re: thp and memory barrier assumptions

2012-07-26 Thread Peter Zijlstra
On Thu, 2012-07-26 at 22:31 +0200, Peter Zijlstra wrote: __do_huge_pmd_anonymous_page() contains: /* * The spinlocking to take the lru_lock inside * page_add_new_anon_rmap() acts as a full memory * barrier to be sure