On Tue, Sep 29, 2015 at 02:05:07PM -0700, Andrew Morton wrote:
> > static bool __zone_watermark_ok(struct zone *z, unsigned int order,
> > unsigned long mark, int classzone_idx, int alloc_flags,
> > @@ -2317,7 +2319,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
> > {
> > long min = mark;
> > int o;
> > - long free_cma = 0;
> > + const bool alloc_harder = (alloc_flags & ALLOC_HARDER);
>
> hmpf. Setting a bool to 0x10 is a bit grubby.
>
Should be safe, but I see your point. For any other type it would be
truncated and look like a bug.
> > /* free_pages may go negative - that's OK */
> > free_pages -= (1 << order) - 1;
> > @@ -2330,7 +2332,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
> > * the high-atomic reserves. This will over-estimate the size of the
> > * atomic reserve but it avoids a search.
> > */
> > - if (likely(!(alloc_flags & ALLOC_HARDER)))
> > + if (likely(!alloc_harder))
> > free_pages -= z->nr_reserved_highatomic;
> > else
> > min -= min / 4;
> > @@ -2338,22 +2340,43 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
> > #ifdef CONFIG_CMA
> > /* If allocation can't use CMA areas don't use free CMA pages */
> > if (!(alloc_flags & ALLOC_CMA))
> > - free_cma = zone_page_state(z, NR_FREE_CMA_PAGES);
> > + free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
> > #endif
> >
> > - if (free_pages - free_cma <= min + z->lowmem_reserve[classzone_idx])
> > + if (free_pages <= min + z->lowmem_reserve[classzone_idx])
> > return false;
> > - 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;
> > + /* order-0 watermarks are ok */
>
> because?
>
The wizard of oz because because!
This should fix it up better than clicking my shoes three times.
---8<---
From: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
Subject: [PATCH] mm, page_alloc: only enforce watermarks for order-0
allocations -fix
This patch is updating comments for clarity and converts a bool to an
int. The code as-is is ok as the compiler is meant to cast it correctly
but it looks odd to people who know the value would be truncated and
lost for other types.
This is a fix to the mmotm patch
mm-page_alloc-only-enforce-watermarks-for-order-0-allocations.patch
Signed-off-by: Mel Gorman <mgorman@xxxxxxxxxxxxxxxxxxx>
---
mm/page_alloc.c | 11 ++++++++---
1 file changed, 8 insertions(+), 3 deletions(-)
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 25731624d734..fedec98aafca 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2332,7 +2332,7 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
{
long min = mark;
int o;
- const bool alloc_harder = (alloc_flags & ALLOC_HARDER);
+ const int alloc_harder = (alloc_flags & ALLOC_HARDER);
/* free_pages may go negative - that's OK */
free_pages -= (1 << order) - 1;
@@ -2356,14 +2356,19 @@ static bool __zone_watermark_ok(struct zone *z, unsigned int order,
free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES);
#endif
+ /*
+ * Check watermarks for an order-0 allocation request. If these
+ * are not met, then a high-order request also cannot go ahead
+ * even if a suitable page happened to be free.
+ */
if (free_pages <= min + z->lowmem_reserve[classzone_idx])
return false;
- /* order-0 watermarks are ok */
+ /* If this is an order-0 request then the watermark is fine */
if (!order)
return true;
- /* Check at least one high-order page is free */
+ /* For a high-order request, check at least one suitable page is free */
for (o = order; o < MAX_ORDER; o++) {
struct free_area *area = &z->free_area[o];
int mt;
--
To unsubscribe, send a message with 'unsubscribe linux-mm' in
the body to majordomo@xxxxxxxxx. For more info on Linux MM,
see: http://www.linux-mm.org/ .
Don't email: <a href=mailto:"dont@xxxxxxxxx";> email@xxxxxxxxx </a>