Re: [RFC] mm: a question about high-order check in __zone_watermark_ok()

From: Vlastimil Babka
Date: Mon Sep 26 2016 - 04:52:51 EST


[+CC Joonsoo Kim]

On 09/26/2016 10:47 AM, Xishi Qiu wrote:
commit 97a16fc82a7c5b0cfce95c05dfb9561e306ca1b1
(mm, page_alloc: only enforce watermarks for order-0 allocations)
rewrite the high-order check in __zone_watermark_ok(), but I think it
quietly fix a bug. Please see the following.

Before this patch, the high-order check is this:
__zone_watermark_ok()
...
for (o = 0; o < order; o++) {
/* At the next order, this order's pages become unavailable */
free_pages -= z->free_area[o].nr_free << o;

/* Require fewer higher order pages to be free */
min >>= 1;

if (free_pages <= min)
return false;
}
...

If we have cma memory, and we alloc a high-order movable page, then it's right.

But if we alloc a high-order unmovable page(e.g. alloc kernel stack in dup_task_struct()),
and there are a lot of high-order cma pages, but little high-order unmovable
pages, the it is still return *true*, but we will alloc *failed* finally, because
we cannot fallback from migrate_unmovable to migrate_cma, right?

Yeah I think this limitation was known to CMA people.

Also if we doing __alloc_pages_slowpath(), the compact will not work, because
__zone_watermark_ok() always return true, and it lead to alloc a high-order
unmovable page failed, then do direct reclaim.

I guess that can happen as well.

Thanks,
Xishi Qiu