Re: [Linaro-mm-sig] [PATCH 04/11] mm: page_alloc: introduce alloc_contig_range()

On Mon, 16 Jan 2012 10:01:10 +0100, Mel Gorman mel@csn.ul.ie wrote:

On Fri, Jan 13, 2012 at 09:04:31PM +0100, Michal Nazarewicz wrote:

...

...

On Thu, Dec 29, 2011 at 01:39:05PM +0100, Marek Szyprowski wrote:

...

From: Michal Nazarewicz mina86@mina86.com

• /* Make sure all pages are isolated. */
• if (!ret) {

• lru_add_drain_all();
  

• drain_all_pages();
  

• if (WARN_ON(test_pages_isolated(start, end)))
  

• 	ret = -EBUSY;
  

• }

On Tue, 10 Jan 2012 15:16:13 +0100, Mel Gorman mel@csn.ul.ie wrote:

...

Another global IPI seems overkill. Drain pages only from the local CPU (drain_pages(get_cpu()); put_cpu()) and test if the pages are isolated.

Is get_cpu() + put_cpu() required? Won't drain_local_pages() work?

drain_local_pages() calls smp_processor_id() without preemption disabled.

Thanks, I wasn't sure if preemption is an issue.