Messages in this thread |  | | Date | Thu, 12 Dec 2013 23:53:46 +0000 | From | Mel Gorman <> | Subject | Re: [PATCH 1/3] x86: mm: Clean up inconsistencies when flushing TLB ranges |
| |
On Thu, Dec 12, 2013 at 09:59:33PM +0800, Alex Shi wrote: > On 12/12/2013 07:55 PM, Mel Gorman wrote: > > NR_TLB_LOCAL_FLUSH_ALL is not always accounted for correctly and the > > comparison with total_vm is done before taking tlb_flushall_shift into > > account. Clean it up. > > > > Signed-off-by: Mel Gorman <mgorman@suse.de> > > Reviewed-by: Alex Shi
Thanks.
> > --- > > arch/x86/mm/tlb.c | 12 ++++++------ > > 1 file changed, 6 insertions(+), 6 deletions(-) > > > > diff --git a/arch/x86/mm/tlb.c b/arch/x86/mm/tlb.c > > index ae699b3..09b8cb8 100644 > > --- a/arch/x86/mm/tlb.c > > +++ b/arch/x86/mm/tlb.c > > @@ -189,6 +189,7 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, > > { > > unsigned long addr; > > unsigned act_entries, tlb_entries = 0; > > + unsigned long nr_base_pages; > > > > preempt_disable(); > > if (current->active_mm != mm) > > @@ -210,18 +211,17 @@ void flush_tlb_mm_range(struct mm_struct *mm, unsigned long start, > > tlb_entries = tlb_lli_4k[ENTRIES]; > > else > > tlb_entries = tlb_lld_4k[ENTRIES]; > > + > > /* Assume all of TLB entries was occupied by this task */ > > the benchmark break this assumption?
No, but it's a small benchmark with very little else running at the time. It's an assumption that would only hold true on dedicated machines to a single application. It would not hold true on desktops, multi-tier server applications etc.
-- Mel Gorman SUSE Labs
|  |