The patch titled page allocator: calculate the preferred zone for allocation only once has been added to the -mm tree. Its filename is page-allocator-calculate-the-preferred-zone-for-allocation-only-once.patch Before you just go and hit "reply", please: a) Consider who else should be cc'ed b) Prefer to cc a suitable mailing list as well c) Ideally: find the original patch on the mailing list and do a reply-to-all to that, adding suitable additional cc's *** Remember to use Documentation/SubmitChecklist when testing your code *** See http://userweb.kernel.org/~akpm/stuff/added-to-mm.txt to find out what to do about this The current -mm tree may be found at http://userweb.kernel.org/~akpm/mmotm/ ------------------------------------------------------ Subject: page allocator: calculate the preferred zone for allocation only once From: Mel Gorman <mel@xxxxxxxxx> get_page_from_freelist() can be called multiple times for an allocation. Part of this calculates the preferred_zone which is the first usable zone in the zonelist but the zone depends on the GFP flags specified at the beginning of the allocation call. This patch calculates preferred_zone once. It's safe to do this because if preferred_zone is NULL at the start of the call, no amount of direct reclaim or other actions will change the fact the allocation will fail. Signed-off-by: Mel Gorman <mel@xxxxxxxxx> Reviewed-by: KOSAKI Motohiro <kosaki.motohiro@xxxxxxxxxxxxxx> Reviewed-by: Pekka Enberg <penberg@xxxxxxxxxxxxxx> Cc: Christoph Lameter <cl@xxxxxxxxxxxxxxxxxxxx> Cc: Peter Zijlstra <a.p.zijlstra@xxxxxxxxx> Cc: Nick Piggin <nickpiggin@xxxxxxxxxxxx> Cc: Dave Hansen <dave@xxxxxxxxxxxxxxxxxx> Signed-off-by: Andrew Morton <akpm@xxxxxxxxxxxxxxxxxxxx> --- mm/page_alloc.c | 54 +++++++++++++++++++++++++++------------------- 1 file changed, 32 insertions(+), 22 deletions(-) diff -puN mm/page_alloc.c~page-allocator-calculate-the-preferred-zone-for-allocation-only-once mm/page_alloc.c --- a/mm/page_alloc.c~page-allocator-calculate-the-preferred-zone-for-allocation-only-once +++ a/mm/page_alloc.c @@ -1392,23 +1392,17 @@ static void zlc_mark_zone_full(struct zo */ static struct page * get_page_from_freelist(gfp_t gfp_mask, nodemask_t *nodemask, unsigned int order, - struct zonelist *zonelist, int high_zoneidx, int alloc_flags) + struct zonelist *zonelist, int high_zoneidx, int alloc_flags, + struct zone *preferred_zone) { struct zoneref *z; struct page *page = NULL; int classzone_idx; - struct zone *zone, *preferred_zone; + struct zone *zone; nodemask_t *allowednodes = NULL;/* zonelist_cache approximation */ int zlc_active = 0; /* set if using zonelist_cache */ int did_zlc_setup = 0; /* just call zlc_setup() one time */ - (void)first_zones_zonelist(zonelist, high_zoneidx, nodemask, - &preferred_zone); - if (!preferred_zone) - return NULL; - - classzone_idx = zone_idx(preferred_zone); - if (WARN_ON_ONCE(order >= MAX_ORDER)) return NULL; @@ -1504,7 +1498,7 @@ should_alloc_retry(gfp_t gfp_mask, unsig static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask) + nodemask_t *nodemask, struct zone *preferred_zone) { struct page *page; @@ -1521,7 +1515,8 @@ __alloc_pages_may_oom(gfp_t gfp_mask, un */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, zonelist, high_zoneidx, - ALLOC_WMARK_HIGH|ALLOC_CPUSET); + ALLOC_WMARK_HIGH|ALLOC_CPUSET, + preferred_zone); if (page) goto out; @@ -1541,7 +1536,8 @@ out: static inline struct page * __alloc_pages_direct_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask, int alloc_flags, unsigned long *did_some_progress) + nodemask_t *nodemask, int alloc_flags, struct zone *preferred_zone, + unsigned long *did_some_progress) { struct page *page = NULL; struct reclaim_state reclaim_state; @@ -1573,7 +1569,8 @@ __alloc_pages_direct_reclaim(gfp_t gfp_m if (likely(*did_some_progress)) page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, alloc_flags); + zonelist, high_zoneidx, + alloc_flags, preferred_zone); return page; } @@ -1593,13 +1590,14 @@ is_allocation_high_priority(struct task_ static inline struct page * __alloc_pages_high_priority(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask) + nodemask_t *nodemask, struct zone *preferred_zone) { struct page *page; do { page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, ALLOC_NO_WATERMARKS); + zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, + preferred_zone); if (!page && gfp_mask & __GFP_NOFAIL) congestion_wait(WRITE, HZ/50); @@ -1622,7 +1620,7 @@ void wake_all_kswapd(unsigned int order, static inline struct page * __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, - nodemask_t *nodemask) + nodemask_t *nodemask, struct zone *preferred_zone) { const gfp_t wait = gfp_mask & __GFP_WAIT; struct page *page = NULL; @@ -1672,7 +1670,8 @@ restart: * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, - high_zoneidx, alloc_flags); + high_zoneidx, alloc_flags, + preferred_zone); if (page) goto got_pg; @@ -1682,7 +1681,7 @@ rebalance: /* Do not dip into emergency reserves if specified */ if (!(gfp_mask & __GFP_NOMEMALLOC)) { page = __alloc_pages_high_priority(gfp_mask, order, - zonelist, high_zoneidx, nodemask); + zonelist, high_zoneidx, nodemask, preferred_zone); if (page) goto got_pg; } @@ -1699,7 +1698,8 @@ rebalance: page = __alloc_pages_direct_reclaim(gfp_mask, order, zonelist, high_zoneidx, nodemask, - alloc_flags, &did_some_progress); + alloc_flags, preferred_zone, + &did_some_progress); if (page) goto got_pg; @@ -1711,7 +1711,7 @@ rebalance: if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, - nodemask); + nodemask, preferred_zone); if (page) goto got_pg; @@ -1756,6 +1756,7 @@ __alloc_pages_nodemask(gfp_t gfp_mask, u struct zonelist *zonelist, nodemask_t *nodemask) { enum zone_type high_zoneidx = gfp_zone(gfp_mask); + struct zone *preferred_zone; struct page *page; lockdep_trace_alloc(gfp_mask); @@ -1773,11 +1774,20 @@ __alloc_pages_nodemask(gfp_t gfp_mask, u if (unlikely(!zonelist->_zonerefs->zone)) return NULL; + /* The preferred zone is used for statistics later */ + (void)first_zones_zonelist(zonelist, high_zoneidx, nodemask, + &preferred_zone); + if (!preferred_zone) + return NULL; + + /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, - zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET); + zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET, + preferred_zone); if (unlikely(!page)) page = __alloc_pages_slowpath(gfp_mask, order, - zonelist, high_zoneidx, nodemask); + zonelist, high_zoneidx, nodemask, + preferred_zone); return page; } _ Patches currently in -mm which might be from mel@xxxxxxxxx are vmscan-low-order-lumpy-reclaim-also-should-use-pageout_io_sync.patch page-allocator-replace-__alloc_pages_internal-with-__alloc_pages_nodemask.patch page-allocator-do-not-sanity-check-order-in-the-fast-path.patch page-allocator-do-not-sanity-check-order-in-the-fast-path-fix.patch page-allocator-do-not-check-numa-node-id-when-the-caller-knows-the-node-is-valid.patch page-allocator-check-only-once-if-the-zonelist-is-suitable-for-the-allocation.patch page-allocator-break-up-the-allocator-entry-point-into-fast-and-slow-paths.patch page-allocator-move-check-for-disabled-anti-fragmentation-out-of-fastpath.patch page-allocator-calculate-the-preferred-zone-for-allocation-only-once.patch page-allocator-calculate-the-preferred-zone-for-allocation-only-once-fix.patch page-allocator-calculate-the-migratetype-for-allocation-only-once.patch page-allocator-calculate-the-alloc_flags-for-allocation-only-once.patch page-allocator-remove-a-branch-by-assuming-__gfp_high-==-alloc_high.patch page-allocator-inline-__rmqueue_smallest.patch page-allocator-inline-buffered_rmqueue.patch page-allocator-inline-__rmqueue_fallback.patch page-allocator-do-not-call-get_pageblock_migratetype-more-than-necessary.patch page-allocator-do-not-disable-interrupts-in-free_page_mlock.patch page-allocator-do-not-setup-zonelist-cache-when-there-is-only-one-node.patch page-allocator-do-not-check-for-compound-pages-during-the-page-allocator-sanity-checks.patch page-allocator-use-allocation-flags-as-an-index-to-the-zone-watermark.patch page-allocator-update-nr_free_pages-only-as-necessary.patch page-allocator-get-the-pageblock-migratetype-without-disabling-interrupts.patch page-allocator-use-a-pre-calculated-value-instead-of-num_online_nodes-in-fast-paths.patch page-allocator-slab-use-nr_online_nodes-to-check-for-a-numa-platform.patch add-debugging-aid-for-memory-initialisation-problems.patch -- To unsubscribe from this list: send the line "unsubscribe mm-commits" in the body of a message to majordomo@xxxxxxxxxxxxxxx More majordomo info at http://vger.kernel.org/majordomo-info.html