aboutsummaryrefslogtreecommitdiff
path: root/mm
diff options
context:
space:
mode:
authorMel Gorman <mgorman@techsingularity.net>2017-11-15 17:38:03 -0800
committerLinus Torvalds <torvalds@linux-foundation.org>2017-11-15 18:21:06 -0800
commit453f85d43fa9ee243f0fc3ac4e1be45615301e3f (patch)
treef414b8ef3a3c92903c960225a2ded020a7158494 /mm
parent2d4894b5d2ae0fe1725ea7abd57b33bfbbe45492 (diff)
download96b-common-453f85d43fa9ee243f0fc3ac4e1be45615301e3f.tar.gz
mm: remove __GFP_COLD
As the page free path makes no distinction between cache hot and cold pages, there is no real useful ordering of pages in the free list that allocation requests can take advantage of. Juding from the users of __GFP_COLD, it is likely that a number of them are the result of copying other sites instead of actually measuring the impact. Remove the __GFP_COLD parameter which simplifies a number of paths in the page allocator. This is potentially controversial but bear in mind that the size of the per-cpu pagelists versus modern cache sizes means that the whole per-cpu list can often fit in the L3 cache. Hence, there is only a potential benefit for microbenchmarks that alloc/free pages in a tight loop. It's even worse when THP is taken into account which has little or no chance of getting a cache-hot page as the per-cpu list is bypassed and the zeroing of multiple pages will thrash the cache anyway. The truncate microbenchmarks are not shown as this patch affects the allocation path and not the free path. A page fault microbenchmark was tested but it showed no sigificant difference which is not surprising given that the __GFP_COLD branches are a miniscule percentage of the fault path. Link: http://lkml.kernel.org/r/20171018075952.10627-9-mgorman@techsingularity.net Signed-off-by: Mel Gorman <mgorman@techsingularity.net> Acked-by: Vlastimil Babka <vbabka@suse.cz> Cc: Andi Kleen <ak@linux.intel.com> Cc: Dave Chinner <david@fromorbit.com> Cc: Dave Hansen <dave.hansen@intel.com> Cc: Jan Kara <jack@suse.cz> Cc: Johannes Weiner <hannes@cmpxchg.org> Signed-off-by: Andrew Morton <akpm@linux-foundation.org> Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>
Diffstat (limited to 'mm')
-rw-r--r--mm/filemap.c6
-rw-r--r--mm/page_alloc.c20
-rw-r--r--mm/percpu-vm.c2
3 files changed, 10 insertions, 18 deletions
diff --git a/mm/filemap.c b/mm/filemap.c
index 90a9f261f85f..923fc2ebd74a 100644
--- a/mm/filemap.c
+++ b/mm/filemap.c
@@ -2272,7 +2272,7 @@ no_cached_page:
* Ok, it wasn't cached, so we need to create a new
* page..
*/
- page = page_cache_alloc_cold(mapping);
+ page = page_cache_alloc(mapping);
if (!page) {
error = -ENOMEM;
goto out;
@@ -2384,7 +2384,7 @@ static int page_cache_read(struct file *file, pgoff_t offset, gfp_t gfp_mask)
int ret;
do {
- page = __page_cache_alloc(gfp_mask|__GFP_COLD);
+ page = __page_cache_alloc(gfp_mask);
if (!page)
return -ENOMEM;
@@ -2788,7 +2788,7 @@ static struct page *do_read_cache_page(struct address_space *mapping,
repeat:
page = find_get_page(mapping, index);
if (!page) {
- page = __page_cache_alloc(gfp | __GFP_COLD);
+ page = __page_cache_alloc(gfp);
if (!page)
return ERR_PTR(-ENOMEM);
err = add_to_page_cache_lru(page, mapping, index, gfp);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index f265d37b3152..370b64d03e3f 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -2336,7 +2336,7 @@ retry:
*/
static int rmqueue_bulk(struct zone *zone, unsigned int order,
unsigned long count, struct list_head *list,
- int migratetype, bool cold)
+ int migratetype)
{
int i, alloced = 0;
@@ -2358,10 +2358,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order,
* merge IO requests if the physical pages are ordered
* properly.
*/
- if (likely(!cold))
- list_add(&page->lru, list);
- else
- list_add_tail(&page->lru, list);
+ list_add(&page->lru, list);
list = &page->lru;
alloced++;
if (is_migrate_cma(get_pcppage_migratetype(page)))
@@ -2795,7 +2792,7 @@ static inline void zone_statistics(struct zone *preferred_zone, struct zone *z)
/* Remove page from the per-cpu list, caller must protect the list */
static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
- bool cold, struct per_cpu_pages *pcp,
+ struct per_cpu_pages *pcp,
struct list_head *list)
{
struct page *page;
@@ -2804,16 +2801,12 @@ static struct page *__rmqueue_pcplist(struct zone *zone, int migratetype,
if (list_empty(list)) {
pcp->count += rmqueue_bulk(zone, 0,
pcp->batch, list,
- migratetype, cold);
+ migratetype);
if (unlikely(list_empty(list)))
return NULL;
}
- if (cold)
- page = list_last_entry(list, struct page, lru);
- else
- page = list_first_entry(list, struct page, lru);
-
+ page = list_first_entry(list, struct page, lru);
list_del(&page->lru);
pcp->count--;
} while (check_new_pcp(page));
@@ -2828,14 +2821,13 @@ static struct page *rmqueue_pcplist(struct zone *preferred_zone,
{
struct per_cpu_pages *pcp;
struct list_head *list;
- bool cold = ((gfp_flags & __GFP_COLD) != 0);
struct page *page;
unsigned long flags;
local_irq_save(flags);
pcp = &this_cpu_ptr(zone->pageset)->pcp;
list = &pcp->lists[migratetype];
- page = __rmqueue_pcplist(zone, migratetype, cold, pcp, list);
+ page = __rmqueue_pcplist(zone, migratetype, pcp, list);
if (page) {
__count_zid_vm_events(PGALLOC, page_zonenum(page), 1 << order);
zone_statistics(preferred_zone, zone);
diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c
index 15dab691ea70..9158e5a81391 100644
--- a/mm/percpu-vm.c
+++ b/mm/percpu-vm.c
@@ -81,7 +81,7 @@ static void pcpu_free_pages(struct pcpu_chunk *chunk,
static int pcpu_alloc_pages(struct pcpu_chunk *chunk,
struct page **pages, int page_start, int page_end)
{
- const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM | __GFP_COLD;
+ const gfp_t gfp = GFP_KERNEL | __GFP_HIGHMEM;
unsigned int cpu, tcpu;
int i;