diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 754 |
1 files changed, 475 insertions, 279 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 0727896a88a..a5f3c278c57 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -162,17 +162,25 @@ static unsigned long __meminitdata dma_reserve; #if MAX_NUMNODES > 1 int nr_node_ids __read_mostly = MAX_NUMNODES; +int nr_online_nodes __read_mostly = 1; EXPORT_SYMBOL(nr_node_ids); +EXPORT_SYMBOL(nr_online_nodes); #endif int page_group_by_mobility_disabled __read_mostly; static void set_pageblock_migratetype(struct page *page, int migratetype) { + + if (unlikely(page_group_by_mobility_disabled)) + migratetype = MIGRATE_UNMOVABLE; + set_pageblock_flags_group(page, (unsigned long)migratetype, PB_migrate, PB_migrate_end); } +bool oom_killer_disabled __read_mostly; + #ifdef CONFIG_DEBUG_VM static int page_outside_zone_boundaries(struct zone *zone, struct page *page) { @@ -295,23 +303,6 @@ void prep_compound_page(struct page *page, unsigned long order) } } -#ifdef CONFIG_HUGETLBFS -void prep_compound_gigantic_page(struct page *page, unsigned long order) -{ - int i; - int nr_pages = 1 << order; - struct page *p = page + 1; - - set_compound_page_dtor(page, free_compound_page); - set_compound_order(page, order); - __SetPageHead(page); - for (i = 1; i < nr_pages; i++, p = mem_map_next(p, page, i)) { - __SetPageTail(p); - p->first_page = page; - } -} -#endif - static int destroy_compound_page(struct page *page, unsigned long order) { int i; @@ -418,7 +409,7 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; if (PageBuddy(buddy) && page_order(buddy) == order) { - BUG_ON(page_count(buddy) != 0); + VM_BUG_ON(page_count(buddy) != 0); return 1; } return 0; @@ -449,22 +440,22 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, */ static inline void __free_one_page(struct page *page, - struct zone *zone, unsigned int order) + struct zone *zone, unsigned int order, + int migratetype) { unsigned long page_idx; - int order_size = 1 << order; - int migratetype = get_pageblock_migratetype(page); if (unlikely(PageCompound(page))) if (unlikely(destroy_compound_page(page, order))) return; + VM_BUG_ON(migratetype == -1); + page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); - VM_BUG_ON(page_idx & (order_size - 1)); + VM_BUG_ON(page_idx & ((1 << order) - 1)); VM_BUG_ON(bad_range(zone, page)); - __mod_zone_page_state(zone, NR_FREE_PAGES, order_size); while (order < MAX_ORDER-1) { unsigned long combined_idx; struct page *buddy; @@ -488,12 +479,27 @@ static inline void __free_one_page(struct page *page, zone->free_area[order].nr_free++; } +#ifdef CONFIG_HAVE_MLOCKED_PAGE_BIT +/* + * free_page_mlock() -- clean up attempts to free and mlocked() page. + * Page should not be on lru, so no need to fix that up. + * free_pages_check() will verify... + */ +static inline void free_page_mlock(struct page *page) +{ + __ClearPageMlocked(page); + __dec_zone_page_state(page, NR_MLOCK); + __count_vm_event(UNEVICTABLE_MLOCKFREED); +} +#else +static void free_page_mlock(struct page *page) { } +#endif + static inline int free_pages_check(struct page *page) { - free_page_mlock(page); if (unlikely(page_mapcount(page) | (page->mapping != NULL) | - (page_count(page) != 0) | + (atomic_read(&page->_count) != 0) | (page->flags & PAGE_FLAGS_CHECK_AT_FREE))) { bad_page(page); return 1; @@ -520,6 +526,8 @@ static void free_pages_bulk(struct zone *zone, int count, spin_lock(&zone->lock); zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE); zone->pages_scanned = 0; + + __mod_zone_page_state(zone, NR_FREE_PAGES, count << order); while (count--) { struct page *page; @@ -527,17 +535,20 @@ static void free_pages_bulk(struct zone *zone, int count, page = list_entry(list->prev, struct page, lru); /* have to delete it as __free_one_page list manipulates */ list_del(&page->lru); - __free_one_page(page, zone, order); + __free_one_page(page, zone, order, page_private(page)); } spin_unlock(&zone->lock); } -static void free_one_page(struct zone *zone, struct page *page, int order) +static void free_one_page(struct zone *zone, struct page *page, int order, + int migratetype) { spin_lock(&zone->lock); zone_clear_flag(zone, ZONE_ALL_UNRECLAIMABLE); zone->pages_scanned = 0; - __free_one_page(page, zone, order); + + __mod_zone_page_state(zone, NR_FREE_PAGES, 1 << order); + __free_one_page(page, zone, order, migratetype); spin_unlock(&zone->lock); } @@ -546,6 +557,7 @@ static void __free_pages_ok(struct page *page, unsigned int order) unsigned long flags; int i; int bad = 0; + int clearMlocked = PageMlocked(page); kmemcheck_free_shadow(page, order); @@ -563,8 +575,11 @@ static void __free_pages_ok(struct page *page, unsigned int order) kernel_map_pages(page, 1 << order, 0); local_irq_save(flags); + if (unlikely(clearMlocked)) + free_page_mlock(page); __count_vm_events(PGFREE, 1 << order); - free_one_page(page_zone(page), page, order); + free_one_page(page_zone(page), page, order, + get_pageblock_migratetype(page)); local_irq_restore(flags); } @@ -635,7 +650,7 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) { if (unlikely(page_mapcount(page) | (page->mapping != NULL) | - (page_count(page) != 0) | + (atomic_read(&page->_count) != 0) | (page->flags & PAGE_FLAGS_CHECK_AT_PREP))) { bad_page(page); return 1; @@ -660,7 +675,8 @@ static int prep_new_page(struct page *page, int order, gfp_t gfp_flags) * Go through the free lists for the given migratetype and remove * the smallest available page from the freelists */ -static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, +static inline +struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, int migratetype) { unsigned int current_order; @@ -678,7 +694,6 @@ static struct page *__rmqueue_smallest(struct zone *zone, unsigned int order, list_del(&page->lru); rmv_page_order(page); area->nr_free--; - __mod_zone_page_state(zone, NR_FREE_PAGES, - (1UL << order)); expand(zone, page, order, current_order, area, migratetype); return page; } @@ -769,8 +784,8 @@ static int move_freepages_block(struct zone *zone, struct page *page, } /* Remove an element from the buddy allocator from the fallback list */ -static struct page *__rmqueue_fallback(struct zone *zone, int order, - int start_migratetype) +static inline struct page * +__rmqueue_fallback(struct zone *zone, int order, int start_migratetype) { struct free_area * area; int current_order; @@ -818,8 +833,6 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order, /* Remove the page from the freelists */ list_del(&page->lru); rmv_page_order(page); - __mod_zone_page_state(zone, NR_FREE_PAGES, - -(1UL << order)); if (current_order == pageblock_order) set_pageblock_migratetype(page, @@ -830,8 +843,7 @@ static struct page *__rmqueue_fallback(struct zone *zone, int order, } } - /* Use MIGRATE_RESERVE rather than fail an allocation */ - return __rmqueue_smallest(zone, order, MIGRATE_RESERVE); + return NULL; } /* @@ -843,11 +855,23 @@ static struct page *__rmqueue(struct zone *zone, unsigned int order, { struct page *page; +retry_reserve: page = __rmqueue_smallest(zone, order, migratetype); - if (unlikely(!page)) + if (unlikely(!page) && migratetype != MIGRATE_RESERVE) { page = __rmqueue_fallback(zone, order, migratetype); + /* + * Use MIGRATE_RESERVE rather than fail an allocation. goto + * is used because __rmqueue_smallest is an inline function + * and we want just one call site + */ + if (!page) { + migratetype = MIGRATE_RESERVE; + goto retry_reserve; + } + } + return page; } @@ -881,6 +905,7 @@ static int rmqueue_bulk(struct zone *zone, unsigned int order, set_page_private(page, migratetype); list = &page->lru; } + __mod_zone_page_state(zone, NR_FREE_PAGES, -(i << order)); spin_unlock(&zone->lock); return i; } @@ -996,6 +1021,7 @@ static void free_hot_cold_page(struct page *page, int cold) struct zone *zone = page_zone(page); struct per_cpu_pages *pcp; unsigned long flags; + int clearMlocked = PageMlocked(page); kmemcheck_free_shadow(page, 0); @@ -1012,13 +1038,16 @@ static void free_hot_cold_page(struct page *page, int cold) kernel_map_pages(page, 1, 0); pcp = &zone_pcp(zone, get_cpu())->pcp; + set_page_private(page, get_pageblock_migratetype(page)); local_irq_save(flags); + if (unlikely(clearMlocked)) + free_page_mlock(page); __count_vm_event(PGFREE); + if (cold) list_add_tail(&page->lru, &pcp->list); else list_add(&page->lru, &pcp->list); - set_page_private(page, get_pageblock_migratetype(page)); pcp->count++; if (pcp->count >= pcp->high) { free_pages_bulk(zone, pcp->batch, &pcp->list, 0); @@ -1071,14 +1100,15 @@ void split_page(struct page *page, unsigned int order) * we cheat by calling it from here, in the order > 0 path. Saves a branch * or two. */ -static struct page *buffered_rmqueue(struct zone *preferred_zone, - struct zone *zone, int order, gfp_t gfp_flags) +static inline +struct page *buffered_rmqueue(struct zone *preferred_zone, + struct zone *zone, int order, gfp_t gfp_flags, + int migratetype) { unsigned long flags; struct page *page; int cold = !!(gfp_flags & __GFP_COLD); int cpu; - int migratetype = allocflags_to_migratetype(gfp_flags); again: cpu = get_cpu(); @@ -1115,8 +1145,22 @@ again: list_del(&page->lru); pcp->count--; } else { + if (unlikely(gfp_flags & __GFP_NOFAIL)) { + /* + * __GFP_NOFAIL is not to be used in new code. + * + * All __GFP_NOFAIL callers should be fixed so that they + * properly detect and handle allocation failures. + * + * We most definitely don't want callers attempting to + * allocate greater than single-page units with + * __GFP_NOFAIL. + */ + WARN_ON_ONCE(order > 0); + } spin_lock_irqsave(&zone->lock, flags); page = __rmqueue(zone, order, migratetype); + __mod_zone_page_state(zone, NR_FREE_PAGES, -(1 << order)); spin_unlock(&zone->lock); if (!page) goto failed; @@ -1138,10 +1182,15 @@ failed: return NULL; } -#define ALLOC_NO_WATERMARKS 0x01 /* don't check watermarks at all */ -#define ALLOC_WMARK_MIN 0x02 /* use pages_min watermark */ -#define ALLOC_WMARK_LOW 0x04 /* use pages_low watermark */ -#define ALLOC_WMARK_HIGH 0x08 /* use pages_high watermark */ +/* The ALLOC_WMARK bits are used as an index to zone->watermark */ +#define ALLOC_WMARK_MIN WMARK_MIN +#define ALLOC_WMARK_LOW WMARK_LOW +#define ALLOC_WMARK_HIGH WMARK_HIGH +#define ALLOC_NO_WATERMARKS 0x04 /* don't check watermarks at all */ + +/* Mask to get the watermark bits */ +#define ALLOC_WMARK_MASK (ALLOC_NO_WATERMARKS-1) + #define ALLOC_HARDER 0x10 /* try to alloc harder */ #define ALLOC_HIGH 0x20 /* __GFP_HIGH set */ #define ALLOC_CPUSET 0x40 /* check for correct cpuset */ @@ -1399,23 +1448,18 @@ static void zlc_mark_zone_full(struct zonelist *zonelist, struct zoneref *z) */ 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, int migratetype) { 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); - zonelist_scan: /* * Scan zonelist, looking for a zone with enough free. @@ -1430,31 +1474,49 @@ zonelist_scan: !cpuset_zone_allowed_softwall(zone, gfp_mask)) goto try_next_zone; + BUILD_BUG_ON(ALLOC_NO_WATERMARKS < NR_WMARK); if (!(alloc_flags & ALLOC_NO_WATERMARKS)) { unsigned long mark; - if (alloc_flags & ALLOC_WMARK_MIN) - mark = zone->pages_min; - else if (alloc_flags & ALLOC_WMARK_LOW) - mark = zone->pages_low; - else - mark = zone->pages_high; - if (!zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) { - if (!zone_reclaim_mode || - !zone_reclaim(zone, gfp_mask, order)) + int ret; + + mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; + if (zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) + goto try_this_zone; + + if (zone_reclaim_mode == 0) + goto this_zone_full; + + ret = zone_reclaim(zone, gfp_mask, order); + switch (ret) { + case ZONE_RECLAIM_NOSCAN: + /* did not scan */ + goto try_next_zone; + case ZONE_RECLAIM_FULL: + /* scanned but unreclaimable */ + goto this_zone_full; + default: + /* did we reclaim enough */ + if (!zone_watermark_ok(zone, order, mark, + classzone_idx, alloc_flags)) goto this_zone_full; } } - page = buffered_rmqueue(preferred_zone, zone, order, gfp_mask); +try_this_zone: + page = buffered_rmqueue(preferred_zone, zone, order, + gfp_mask, migratetype); if (page) break; this_zone_full: if (NUMA_BUILD) zlc_mark_zone_full(zonelist, z); try_next_zone: - if (NUMA_BUILD && !did_zlc_setup) { - /* we do zlc_setup after the first zone is tried */ + if (NUMA_BUILD && !did_zlc_setup && nr_online_nodes > 1) { + /* + * we do zlc_setup after the first zone is tried but only + * if there are multiple nodes make it worthwhile + */ allowednodes = zlc_setup(zonelist, alloc_flags); zlc_active = 1; did_zlc_setup = 1; @@ -1469,47 +1531,217 @@ try_next_zone: return page; } +static inline int +should_alloc_retry(gfp_t gfp_mask, unsigned int order, + unsigned long pages_reclaimed) +{ + /* Do not loop if specifically requested */ + if (gfp_mask & __GFP_NORETRY) + return 0; + + /* + * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER + * means __GFP_NOFAIL, but that may not be true in other + * implementations. + */ + if (order <= PAGE_ALLOC_COSTLY_ORDER) + return 1; + + /* + * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is + * specified, then we retry until we no longer reclaim any pages + * (above), or we've reclaimed an order of pages at least as + * large as the allocation's order. In both cases, if the + * allocation still fails, we stop retrying. + */ + if (gfp_mask & __GFP_REPEAT && pages_reclaimed < (1 << order)) + return 1; + + /* + * Don't let big-order allocations loop unless the caller + * explicitly requests that. + */ + if (gfp_mask & __GFP_NOFAIL) + return 1; + + return 0; +} + +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, struct zone *preferred_zone, + int migratetype) +{ + struct page *page; + + /* Acquire the OOM killer lock for the zones in zonelist */ + if (!try_set_zone_oom(zonelist, gfp_mask)) { + schedule_timeout_uninterruptible(1); + return NULL; + } + + /* + * Go through the zonelist yet one more time, keep very high watermark + * here, this is only to catch a parallel oom killing, we must fail if + * we're still under heavy pressure. + */ + page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, + order, zonelist, high_zoneidx, + ALLOC_WMARK_HIGH|ALLOC_CPUSET, + preferred_zone, migratetype); + if (page) + goto out; + + /* The OOM killer will not help higher order allocs */ + if (order > PAGE_ALLOC_COSTLY_ORDER && !(gfp_mask & __GFP_NOFAIL)) + goto out; + + /* Exhausted what can be done so it's blamo time */ + out_of_memory(zonelist, gfp_mask, order); + +out: + clear_zonelist_oom(zonelist, gfp_mask); + return page; +} + +/* The really slow allocator path where we enter direct reclaim */ +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, struct zone *preferred_zone, + int migratetype, unsigned long *did_some_progress) +{ + struct page *page = NULL; + struct reclaim_state reclaim_state; + struct task_struct *p = current; + + cond_resched(); + + /* We now go into synchronous reclaim */ + cpuset_memory_pressure_bump(); + + /* + * The task's cpuset might have expanded its set of allowable nodes + */ + p->flags |= PF_MEMALLOC; + lockdep_set_current_reclaim_state(gfp_mask); + reclaim_state.reclaimed_slab = 0; + p->reclaim_state = &reclaim_state; + + *did_some_progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); + + p->reclaim_state = NULL; + lockdep_clear_current_reclaim_state(); + p->flags &= ~PF_MEMALLOC; + + cond_resched(); + + if (order != 0) + drain_all_pages(); + + if (likely(*did_some_progress)) + page = get_page_from_freelist(gfp_mask, nodemask, order, + zonelist, high_zoneidx, + alloc_flags, preferred_zone, + migratetype); + return page; +} + /* - * This is the 'heart' of the zoned buddy allocator. + * This is called in the allocator slow-path if the allocation request is of + * sufficient urgency to ignore watermarks and take other desperate measures */ -struct page * -__alloc_pages_internal(gfp_t gfp_mask, unsigned int order, - struct zonelist *zonelist, nodemask_t *nodemask) +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, struct zone *preferred_zone, + int migratetype) +{ + struct page *page; + + do { + page = get_page_from_freelist(gfp_mask, nodemask, order, + zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); + + if (!page && gfp_mask & __GFP_NOFAIL) + congestion_wait(WRITE, HZ/50); + } while (!page && (gfp_mask & __GFP_NOFAIL)); + + return page; +} + +static inline +void wake_all_kswapd(unsigned int order, struct zonelist *zonelist, + enum zone_type high_zoneidx) { - const gfp_t wait = gfp_mask & __GFP_WAIT; - enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zoneref *z; struct zone *zone; - struct page *page; - struct reclaim_state reclaim_state; - struct task_struct *p = current; - int do_retry; - int alloc_flags; - unsigned long did_some_progress; - unsigned long pages_reclaimed = 0; - lockdep_trace_alloc(gfp_mask); + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) + wakeup_kswapd(zone, order); +} - might_sleep_if(wait); +static inline int +gfp_to_alloc_flags(gfp_t gfp_mask) +{ + struct task_struct *p = current; + int alloc_flags = ALLOC_WMARK_MIN | ALLOC_CPUSET; + const gfp_t wait = gfp_mask & __GFP_WAIT; - if (should_fail_alloc_page(gfp_mask, order)) - return NULL; + /* __GFP_HIGH is assumed to be the same as ALLOC_HIGH to save a branch. */ + BUILD_BUG_ON(__GFP_HIGH != ALLOC_HIGH); -restart: - z = zonelist->_zonerefs; /* the list of zones suitable for gfp_mask */ + /* + * The caller may dip into page reserves a bit more if the caller + * cannot run direct reclaim, or if the caller has realtime scheduling + * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will + * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). + */ + alloc_flags |= (gfp_mask & __GFP_HIGH); - if (unlikely(!z->zone)) { + if (!wait) { + alloc_flags |= ALLOC_HARDER; /* - * Happens if we have an empty zonelist as a result of - * GFP_THISNODE being used on a memoryless node + * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. + * See also cpuset_zone_allowed() comment in kernel/cpuset.c. */ - return NULL; + alloc_flags &= ~ALLOC_CPUSET; + } else if (unlikely(rt_task(p))) + alloc_flags |= ALLOC_HARDER; + + if (likely(!(gfp_mask & __GFP_NOMEMALLOC))) { + if (!in_interrupt() && + ((p->flags & PF_MEMALLOC) || + unlikely(test_thread_flag(TIF_MEMDIE)))) + alloc_flags |= ALLOC_NO_WATERMARKS; } - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, - zonelist, high_zoneidx, ALLOC_WMARK_LOW|ALLOC_CPUSET); - if (page) - goto got_pg; + return alloc_flags; +} + +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, struct zone *preferred_zone, + int migratetype) +{ + const gfp_t wait = gfp_mask & __GFP_WAIT; + struct page *page = NULL; + int alloc_flags; + unsigned long pages_reclaimed = 0; + unsigned long did_some_progress; + struct task_struct *p = current; + + /* + * In the slowpath, we sanity check order to avoid ever trying to + * reclaim >= MAX_ORDER areas which will never succeed. Callers may + * be using allocators in order of preference for an area that is + * too large. + */ + if (WARN_ON_ONCE(order >= MAX_ORDER)) + return NULL; /* * GFP_THISNODE (meaning __GFP_THISNODE, __GFP_NORETRY and @@ -1522,154 +1754,83 @@ restart: if (NUMA_BUILD && (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) - wakeup_kswapd(zone, order); + wake_all_kswapd(order, zonelist, high_zoneidx); /* * OK, we're below the kswapd watermark and have kicked background * reclaim. Now things get more complex, so set up alloc_flags according * to how we want to proceed. - * - * The caller may dip into page reserves a bit more if the caller - * cannot run direct reclaim, or if the caller has realtime scheduling - * policy or is asking for __GFP_HIGH memory. GFP_ATOMIC requests will - * set both ALLOC_HARDER (!wait) and ALLOC_HIGH (__GFP_HIGH). */ - alloc_flags = ALLOC_WMARK_MIN; - if ((unlikely(rt_task(p)) && !in_interrupt()) || !wait) - alloc_flags |= ALLOC_HARDER; - if (gfp_mask & __GFP_HIGH) - alloc_flags |= ALLOC_HIGH; - if (wait) - alloc_flags |= ALLOC_CPUSET; + alloc_flags = gfp_to_alloc_flags(gfp_mask); - /* - * Go through the zonelist again. Let __GFP_HIGH and allocations - * coming from realtime tasks go deeper into reserves. - * - * This is the last chance, in general, before the goto nopage. - * Ignore cpuset if GFP_ATOMIC (!wait) rather than fail alloc. - * See also cpuset_zone_allowed() comment in kernel/cpuset.c. - */ +restart: + /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, - high_zoneidx, alloc_flags); + high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, + preferred_zone, migratetype); if (page) goto got_pg; - /* This allocation should allow future memory freeing. */ - rebalance: - if (((p->flags & PF_MEMALLOC) || unlikely(test_thread_flag(TIF_MEMDIE))) - && !in_interrupt()) { - if (!(gfp_mask & __GFP_NOMEMALLOC)) { -nofail_alloc: - /* go through the zonelist yet again, ignoring mins */ - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, ALLOC_NO_WATERMARKS); - if (page) - goto got_pg; - if (gfp_mask & __GFP_NOFAIL) { - congestion_wait(WRITE, HZ/50); - goto nofail_alloc; - } - } - goto nopage; + /* Allocate without watermarks if the context allows */ + if (alloc_flags & ALLOC_NO_WATERMARKS) { + page = __alloc_pages_high_priority(gfp_mask, order, + zonelist, high_zoneidx, nodemask, + preferred_zone, migratetype); + if (page) + goto got_pg; } /* Atomic allocations - we can't balance anything */ if (!wait) goto nopage; - cond_resched(); + /* Avoid recursion of direct reclaim */ + if (p->flags & PF_MEMALLOC) + goto nopage; + + /* Try direct reclaim and then allocating */ + page = __alloc_pages_direct_reclaim(gfp_mask, order, + zonelist, high_zoneidx, + nodemask, + alloc_flags, preferred_zone, + migratetype, &did_some_progress); + if (page) + goto got_pg; - /* We now go into synchronous reclaim */ - cpuset_memory_pressure_bump(); /* - * The task's cpuset might have expanded its set of allowable nodes + * If we failed to make any progress reclaiming, then we are + * running out of options and have to consider going OOM */ - cpuset_update_task_memory_state(); - p->flags |= PF_MEMALLOC; - - lockdep_set_current_reclaim_state(gfp_mask); - reclaim_state.reclaimed_slab = 0; - p->reclaim_state = &reclaim_state; - - did_some_progress = try_to_free_pages(zonelist, order, - gfp_mask, nodemask); - - p->reclaim_state = NULL; - lockdep_clear_current_reclaim_state(); - p->flags &= ~PF_MEMALLOC; - - cond_resched(); + if (!did_some_progress) { + if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { + if (oom_killer_disabled) + goto nopage; + page = __alloc_pages_may_oom(gfp_mask, order, + zonelist, high_zoneidx, + nodemask, preferred_zone, + migratetype); + if (page) + goto got_pg; - if (order != 0) - drain_all_pages(); + /* + * The OOM killer does not trigger for high-order + * ~__GFP_NOFAIL allocations so if no progress is being + * made, there are no other options and retrying is + * unlikely to help. + */ + if (order > PAGE_ALLOC_COSTLY_ORDER && + !(gfp_mask & __GFP_NOFAIL)) + goto nopage; - if (likely(did_some_progress)) { - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, alloc_flags); - if (page) - goto got_pg; - } else if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { - if (!try_set_zone_oom(zonelist, gfp_mask)) { - schedule_timeout_uninterruptible(1); goto restart; } - - /* - * Go through the zonelist yet one more time, keep - * very high watermark here, this is only to catch - * a parallel oom killing, we must fail if we're still - * under heavy pressure. - */ - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, - order, zonelist, high_zoneidx, - ALLOC_WMARK_HIGH|ALLOC_CPUSET); - if (page) { - clear_zonelist_oom(zonelist, gfp_mask); - goto got_pg; - } - - /* The OOM killer will not help higher order allocs so fail */ - if (order > PAGE_ALLOC_COSTLY_ORDER) { - clear_zonelist_oom(zonelist, gfp_mask); - goto nopage; - } - - out_of_memory(zonelist, gfp_mask, order); - clear_zonelist_oom(zonelist, gfp_mask); - goto restart; } - /* - * Don't let big-order allocations loop unless the caller explicitly - * requests that. Wait for some write requests to complete then retry. - * - * In this implementation, order <= PAGE_ALLOC_COSTLY_ORDER - * means __GFP_NOFAIL, but that may not be true in other - * implementations. - * - * For order > PAGE_ALLOC_COSTLY_ORDER, if __GFP_REPEAT is - * specified, then we retry until we no longer reclaim any pages - * (above), or we've reclaimed an order of pages at least as - * large as the allocation's order. In both cases, if the - * allocation still fails, we stop retrying. - */ + /* Check if we should retry the allocation */ pages_reclaimed += did_some_progress; - do_retry = 0; - if (!(gfp_mask & __GFP_NORETRY)) { - if (order <= PAGE_ALLOC_COSTLY_ORDER) { - do_retry = 1; - } else { - if (gfp_mask & __GFP_REPEAT && - pages_reclaimed < (1 << order)) - do_retry = 1; - } - if (gfp_mask & __GFP_NOFAIL) - do_retry = 1; - } - if (do_retry) { + if (should_alloc_retry(gfp_mask, order, pages_reclaimed)) { + /* Wait for some write requests to complete then retry */ congestion_wait(WRITE, HZ/50); goto rebalance; } @@ -1687,8 +1848,53 @@ got_pg: if (kmemcheck_enabled) kmemcheck_pagealloc_alloc(page, order, gfp_mask); return page; + +} + +/* + * This is the 'heart' of the zoned buddy allocator. + */ +struct page * +__alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, + struct zonelist *zonelist, nodemask_t *nodemask) +{ + enum zone_type high_zoneidx = gfp_zone(gfp_mask); + struct zone *preferred_zone; + struct page *page; + int migratetype = allocflags_to_migratetype(gfp_mask); + + lockdep_trace_alloc(gfp_mask); + + might_sleep_if(gfp_mask & __GFP_WAIT); + + if (should_fail_alloc_page(gfp_mask, order)) + return NULL; + + /* + * Check the zones suitable for the gfp_mask contain at least one + * valid zone. It's possible to have an empty zonelist as a result + * of GFP_THISNODE and a memoryless node + */ + if (unlikely(!zonelist->_zonerefs->zone)) + return NULL; + + /* The preferred zone is used for statistics later */ + 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, + preferred_zone, migratetype); + if (unlikely(!page)) + page = __alloc_pages_slowpath(gfp_mask, order, + zonelist, high_zoneidx, nodemask, + preferred_zone, migratetype); + + return page; } -EXPORT_SYMBOL(__alloc_pages_internal); +EXPORT_SYMBOL(__alloc_pages_nodemask); /* * Common helper functions. @@ -1817,7 +2023,7 @@ static unsigned int nr_free_zone_pages(int offset) for_each_zone_zonelist(zone, z, zonelist, offset) { unsigned long size = zone->present_pages; - unsigned long high = zone->pages_high; + unsigned long high = high_wmark_pages(zone); if (size > high) sum += size - high; } @@ -1909,19 +2115,14 @@ void show_free_areas(void) printk("Active_anon:%lu active_file:%lu inactive_anon:%lu\n" " inactive_file:%lu" -//TODO: check/adjust line lengths -#ifdef CONFIG_UNEVICTABLE_LRU " unevictable:%lu" -#endif " dirty:%lu writeback:%lu unstable:%lu\n" " free:%lu slab:%lu mapped:%lu pagetables:%lu bounce:%lu\n", global_page_state(NR_ACTIVE_ANON), global_page_state(NR_ACTIVE_FILE), global_page_state(NR_INACTIVE_ANON), global_page_state(NR_INACTIVE_FILE), -#ifdef CONFIG_UNEVICTABLE_LRU global_page_state(NR_UNEVICTABLE), -#endif global_page_state(NR_FILE_DIRTY), global_page_state(NR_WRITEBACK), global_page_state(NR_UNSTABLE_NFS), @@ -1945,25 +2146,21 @@ void show_free_areas(void) " inactive_anon:%lukB" " active_file:%lukB" " inactive_file:%lukB" -#ifdef CONFIG_UNEVICTABLE_LRU " unevictable:%lukB" -#endif " present:%lukB" " pages_scanned:%lu" " all_unreclaimable? %s" "\n", zone->name, K(zone_page_state(zone, NR_FREE_PAGES)), - K(zone->pages_min), - K(zone->pages_low), - K(zone->pages_high), + K(min_wmark_pages(zone)), + K(low_wmark_pages(zone)), + K(high_wmark_pages(zone)), K(zone_page_state(zone, NR_ACTIVE_ANON)), K(zone_page_state(zone, NR_INACTIVE_ANON)), K(zone_page_state(zone, NR_ACTIVE_FILE)), K(zone_page_state(zone, NR_INACTIVE_FILE)), -#ifdef CONFIG_UNEVICTABLE_LRU K(zone_page_state(zone, NR_UNEVICTABLE)), -#endif K(zone->present_pages), zone->pages_scanned, (zone_is_all_unreclaimable(zone) ? "yes" : "no") @@ -2121,7 +2318,7 @@ int numa_zonelist_order_handler(ctl_table *table, int write, } -#define MAX_NODE_LOAD (num_online_nodes()) +#define MAX_NODE_LOAD (nr_online_nodes) static int node_load[MAX_NUMNODES]; /** @@ -2330,7 +2527,7 @@ static void build_zonelists(pg_data_t *pgdat) /* NUMA-aware ordering of nodes */ local_node = pgdat->node_id; - load = num_online_nodes(); + load = nr_online_nodes; prev_node = local_node; nodes_clear(used_mask); @@ -2481,7 +2678,7 @@ void build_all_zonelists(void) printk("Built %i zonelists in %s order, mobility grouping %s. " "Total pages: %ld\n", - num_online_nodes(), + nr_online_nodes, zonelist_order_name[current_zonelist_order], page_group_by_mobility_disabled ? "off" : "on", vm_total_pages); @@ -2560,8 +2757,8 @@ static inline unsigned long wait_table_bits(unsigned long size) /* * Mark a number of pageblocks as MIGRATE_RESERVE. The number - * of blocks reserved is based on zone->pages_min. The memory within the - * reserve will tend to store contiguous free pages. Setting min_free_kbytes + * of blocks reserved is based on min_wmark_pages(zone). The memory within + * the reserve will tend to store contiguous free pages. Setting min_free_kbytes * higher will lead to a bigger reserve which will get freed as contiguous * blocks as reclaim kicks in */ @@ -2574,7 +2771,7 @@ static void setup_zone_migrate_reserve(struct zone *zone) /* Get the start pfn, end pfn and the number of blocks to reserve */ start_pfn = zone->zone_start_pfn; end_pfn = start_pfn + zone->spanned_pages; - reserve = roundup(zone->pages_min, pageblock_nr_pages) >> + reserve = roundup(min_wmark_pages(zone), pageblock_nr_pages) >> pageblock_order; for (pfn = start_pfn; pfn < end_pfn; pfn += pageblock_nr_pages) { @@ -3506,7 +3703,7 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat, zone_pcp_init(zone); for_each_lru(l) { INIT_LIST_HEAD(&zone->lru[l].list); - zone->lru[l].nr_scan = 0; + zone->lru[l].nr_saved_scan = 0; } zone->reclaim_stat.recent_rotated[0] = 0; zone->reclaim_stat.recent_rotated[1] = 0; @@ -4043,6 +4240,11 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) early_node_map[i].start_pfn, early_node_map[i].end_pfn); + /* + * find_zone_movable_pfns_for_nodes/early_calculate_totalpages init + * that node_mask, clear it at first + */ + nodes_clear(node_states[N_HIGH_MEMORY]); /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); @@ -4177,8 +4379,8 @@ static void calculate_totalreserve_pages(void) max = zone->lowmem_reserve[j]; } - /* we treat pages_high as reserved pages. */ - max += zone->pages_high; + /* we treat the high watermark as reserved pages. */ + max += high_wmark_pages(zone); if (max > zone->present_pages) max = zone->present_pages; @@ -4228,12 +4430,13 @@ static void setup_per_zone_lowmem_reserve(void) } /** - * setup_per_zone_pages_min - called when min_free_kbytes changes. + * setup_per_zone_wmarks - called when min_free_kbytes changes + * or when memory is hot-{added|removed} * - * Ensures that the pages_{min,low,high} values for each zone are set correctly - * with respect to min_free_kbytes. + * Ensures that the watermark[min,low,high] values for each zone are set + * correctly with respect to min_free_kbytes. */ -void setup_per_zone_pages_min(void) +void setup_per_zone_wmarks(void) { unsigned long pages_min = min_free_kbytes >> (PAGE_SHIFT - 10); unsigned long lowmem_pages = 0; @@ -4258,7 +4461,7 @@ void setup_per_zone_pages_min(void) * need highmem pages, so cap pages_min to a small * value here. * - * The (pages_high-pages_low) and (pages_low-pages_min) + * The WMARK_HIGH-WMARK_LOW and (WMARK_LOW-WMARK_MIN) * deltas controls asynch page reclaim, and so should * not be capped for highmem. */ @@ -4269,17 +4472,17 @@ void setup_per_zone_pages_min(void) min_pages = SWAP_CLUSTER_MAX; if (min_pages > 128) min_pages = 128; - zone->pages_min = min_pages; + zone->watermark[WMARK_MIN] = min_pages; } else { /* * If it's a lowmem zone, reserve a number of pages * proportionate to the zone's size. */ - zone->pages_min = tmp; + zone->watermark[WMARK_MIN] = tmp; } - zone->pages_low = zone->pages_min + (tmp >> 2); - zone->pages_high = zone->pages_min + (tmp >> 1); + zone->watermark[WMARK_LOW] = min_wmark_pages(zone) + (tmp >> 2); + zone->watermark[WMARK_HIGH] = min_wmark_pages(zone) + (tmp >> 1); setup_zone_migrate_reserve(zone); spin_unlock_irqrestore(&zone->lock, flags); } @@ -4289,8 +4492,6 @@ void setup_per_zone_pages_min(void) } /** - * setup_per_zone_inactive_ratio - called when min_free_kbytes changes. - * * The inactive anon list should be small enough that the VM never has to * do too much work, but large enough that each inactive page has a chance * to be referenced again before it is swapped out. @@ -4311,21 +4512,26 @@ void setup_per_zone_pages_min(void) * 1TB 101 10GB * 10TB 320 32GB */ -static void setup_per_zone_inactive_ratio(void) +void calculate_zone_inactive_ratio(struct zone *zone) { - struct zone *zone; - - for_each_zone(zone) { - unsigned int gb, ratio; + unsigned int gb, ratio; - /* Zone size in gigabytes */ - gb = zone->present_pages >> (30 - PAGE_SHIFT); + /* Zone size in gigabytes */ + gb = zone->present_pages >> (30 - PAGE_SHIFT); + if (gb) ratio = int_sqrt(10 * gb); - if (!ratio) - ratio = 1; + else + ratio = 1; - zone->inactive_ratio = ratio; - } + zone->inactive_ratio = ratio; +} + +static void __init setup_per_zone_inactive_ratio(void) +{ + struct zone *zone; + + for_each_zone(zone) + calculate_zone_inactive_ratio(zone); } /* @@ -4352,7 +4558,7 @@ static void setup_per_zone_inactive_ratio(void) * 8192MB: 11584k * 16384MB: 16384k */ -static int __init init_per_zone_pages_min(void) +static int __init init_per_zone_wmark_min(void) { unsigned long lowmem_kbytes; @@ -4363,12 +4569,12 @@ static int __init init_per_zone_pages_min(void) min_free_kbytes = 128; if (min_free_kbytes > 65536) min_free_kbytes = 65536; - setup_per_zone_pages_min(); + setup_per_zone_wmarks(); setup_per_zone_lowmem_reserve(); setup_per_zone_inactive_ratio(); return 0; } -module_init(init_per_zone_pages_min) +module_init(init_per_zone_wmark_min) /* * min_free_kbytes_sysctl_handler - just a wrapper around proc_dointvec() so @@ -4380,7 +4586,7 @@ int min_free_kbytes_sysctl_handler(ctl_table *table, int write, { proc_dointvec(table, write, file, buffer, length, ppos); if (write) - setup_per_zone_pages_min(); + setup_per_zone_wmarks(); return 0; } @@ -4424,7 +4630,7 @@ int sysctl_min_slab_ratio_sysctl_handler(ctl_table *table, int write, * whenever sysctl_lowmem_reserve_ratio changes. * * The reserve ratio obviously has absolutely no relation with the - * pages_min watermarks. The lowmem reserve ratio can only make sense + * minimum watermarks. The lowmem reserve ratio can only make sense * if in function of the boot time zone sizes. */ int lowmem_reserve_ratio_sysctl_handler(ctl_table *table, int write, @@ -4531,23 +4737,13 @@ void *__init alloc_large_system_hash(const char *tablename, else if (hashdist) table = __vmalloc(size, GFP_ATOMIC, PAGE_KERNEL); else { - unsigned long order = get_order(size); - table = (void*) __get_free_pages(GFP_ATOMIC, order); /* * If bucketsize is not a power-of-two, we may free - * some pages at the end of hash table. + * some pages at the end of hash table which + * alloc_pages_exact() automatically does */ - if (table) { - unsigned long alloc_end = (unsigned long)table + - (PAGE_SIZE << order); - unsigned long used = (unsigned long)table + - PAGE_ALIGN(size); - split_page(virt_to_page(table), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_SIZE; - } - } + if (get_order(size) < MAX_ORDER) + table = alloc_pages_exact(size, GFP_ATOMIC); } } while (!table && size > PAGE_SIZE && --log2qty); |