diff options
Diffstat (limited to 'mm/page_alloc.c')
| -rw-r--r-- | mm/page_alloc.c | 401 |
1 files changed, 269 insertions, 132 deletions
diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 272c6de1bf4e..3c4eb750a199 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -670,6 +670,7 @@ out: void free_compound_page(struct page *page) { + mem_cgroup_uncharge(page); __free_pages_ok(page, compound_order(page)); } @@ -693,34 +694,27 @@ void prep_compound_page(struct page *page, unsigned int order) #ifdef CONFIG_DEBUG_PAGEALLOC unsigned int _debug_guardpage_minorder; -#ifdef CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT -DEFINE_STATIC_KEY_TRUE(_debug_pagealloc_enabled); -#else +bool _debug_pagealloc_enabled_early __read_mostly + = IS_ENABLED(CONFIG_DEBUG_PAGEALLOC_ENABLE_DEFAULT); +EXPORT_SYMBOL(_debug_pagealloc_enabled_early); DEFINE_STATIC_KEY_FALSE(_debug_pagealloc_enabled); -#endif EXPORT_SYMBOL(_debug_pagealloc_enabled); DEFINE_STATIC_KEY_FALSE(_debug_guardpage_enabled); static int __init early_debug_pagealloc(char *buf) { - bool enable = false; - - if (kstrtobool(buf, &enable)) - return -EINVAL; - - if (enable) - static_branch_enable(&_debug_pagealloc_enabled); - - return 0; + return kstrtobool(buf, &_debug_pagealloc_enabled_early); } early_param("debug_pagealloc", early_debug_pagealloc); -static void init_debug_guardpage(void) +void init_debug_pagealloc(void) { if (!debug_pagealloc_enabled()) return; + static_branch_enable(&_debug_pagealloc_enabled); + if (!debug_guardpage_minorder()) return; @@ -1174,12 +1168,18 @@ static __always_inline bool free_pages_prepare(struct page *page, debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } - arch_free_page(page, order); if (want_init_on_free()) kernel_init_free_pages(page, 1 << order); kernel_poison_pages(page, 1 << order, 0); - if (debug_pagealloc_enabled()) + /* + * arch_free_page() can make the page's contents inaccessible. s390 + * does this. So nothing which can access the page's contents should + * happen after this. + */ + arch_free_page(page, order); + + if (debug_pagealloc_enabled_static()) kernel_map_pages(page, 1 << order, 0); kasan_free_nondeferred_pages(page, order); @@ -1200,7 +1200,7 @@ static bool free_pcp_prepare(struct page *page) static bool bulkfree_pcp_prepare(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return free_pages_check(page); else return false; @@ -1214,7 +1214,7 @@ static bool bulkfree_pcp_prepare(struct page *page) */ static bool free_pcp_prepare(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return free_pages_prepare(page, 0, true); else return free_pages_prepare(page, 0, false); @@ -1941,6 +1941,14 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* + * The number of managed pages has changed due to the initialisation + * so the pcpu batch and high limits needs to be updated or the limits + * will be artificially small. + */ + for_each_populated_zone(zone) + zone_pcp_update(zone); + + /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -1958,10 +1966,6 @@ void __init page_alloc_init_late(void) for_each_populated_zone(zone) set_zone_contiguous(zone); - -#ifdef CONFIG_DEBUG_PAGEALLOC - init_debug_guardpage(); -#endif } #ifdef CONFIG_CMA @@ -2091,7 +2095,7 @@ static inline bool free_pages_prezeroed(void) */ static inline bool check_pcp_refill(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return check_new_page(page); else return false; @@ -2113,7 +2117,7 @@ static inline bool check_pcp_refill(struct page *page) } static inline bool check_new_pcp(struct page *page) { - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) return check_new_page(page); else return false; @@ -2140,7 +2144,7 @@ inline void post_alloc_hook(struct page *page, unsigned int order, set_page_refcounted(page); arch_alloc_page(page, order); - if (debug_pagealloc_enabled()) + if (debug_pagealloc_enabled_static()) kernel_map_pages(page, 1 << order, 1); kasan_alloc_pages(page, order); kernel_poison_pages(page, 1 << order, 1); @@ -2238,27 +2242,12 @@ static int move_freepages(struct zone *zone, unsigned int order; int pages_moved = 0; -#ifndef CONFIG_HOLES_IN_ZONE - /* - * page_zone is not safe to call in this context when - * CONFIG_HOLES_IN_ZONE is set. This bug check is probably redundant - * anyway as we check zone boundaries in move_freepages_block(). - * Remove at a later date when no bug reports exist related to - * grouping pages by mobility - */ - VM_BUG_ON(pfn_valid(page_to_pfn(start_page)) && - pfn_valid(page_to_pfn(end_page)) && - page_zone(start_page) != page_zone(end_page)); -#endif for (page = start_page; page <= end_page;) { if (!pfn_valid_within(page_to_pfn(page))) { page++; continue; } - /* Make sure we are not inadvertently changing nodes */ - VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); - if (!PageBuddy(page)) { /* * We assume that pages that could be isolated for @@ -2273,6 +2262,10 @@ static int move_freepages(struct zone *zone, continue; } + /* Make sure we are not inadvertently changing nodes */ + VM_BUG_ON_PAGE(page_to_nid(page) != zone_to_nid(zone), page); + VM_BUG_ON_PAGE(page_zone(page) != zone, page); + order = page_order(page); move_to_free_area(page, &zone->free_area[order], migratetype); page += 1 << order; @@ -3522,7 +3515,7 @@ bool zone_watermark_ok_safe(struct zone *z, unsigned int order, static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) { return node_distance(zone_to_nid(local_zone), zone_to_nid(zone)) <= - RECLAIM_DISTANCE; + node_reclaim_distance; } #else /* CONFIG_NUMA */ static bool zone_allows_reclaim(struct zone *local_zone, struct zone *zone) @@ -3724,10 +3717,6 @@ try_this_zone: static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) { unsigned int filter = SHOW_MEM_FILTER_NODES; - static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1); - - if (!__ratelimit(&show_mem_rs)) - return; /* * This documents exceptions given to allocations in certain @@ -3748,8 +3737,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) { struct va_format vaf; va_list args; - static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); + static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) return; @@ -3966,14 +3954,22 @@ should_compact_retry(struct alloc_context *ac, int order, int alloc_flags, goto check_priority; /* + * compaction was skipped because there are not enough order-0 pages + * to work with, so we retry only if it looks like reclaim can help. + */ + if (compaction_needs_reclaim(compact_result)) { + ret = compaction_zonelist_suitable(ac, order, alloc_flags); + goto out; + } + + /* * make sure the compaction wasn't deferred or didn't bail out early * due to locks contention before we declare that we should give up. - * But do not retry if the given zonelist is not suitable for - * compaction. + * But the next retry should use a higher priority if allowed, so + * we don't just keep bailing out endlessly. */ if (compaction_withdrawn(compact_result)) { - ret = compaction_zonelist_suitable(ac, order, alloc_flags); - goto out; + goto check_priority; } /* @@ -4471,18 +4467,28 @@ retry_cpuset: /* * Checks for costly allocations with __GFP_NORETRY, which - * includes THP page fault allocations + * includes some THP page fault allocations */ if (costly_order && (gfp_mask & __GFP_NORETRY)) { /* - * If compaction is deferred for high-order allocations, - * it is because sync compaction recently failed. If - * this is the case and the caller requested a THP - * allocation, we do not want to heavily disrupt the - * system, so we fail the allocation instead of entering - * direct reclaim. + * If allocating entire pageblock(s) and compaction + * failed because all zones are below low watermarks + * or is prohibited because it recently failed at this + * order, fail immediately unless the allocator has + * requested compaction and reclaim retry. + * + * Reclaim is + * - potentially very expensive because zones are far + * below their low watermarks or this is part of very + * bursty high order allocations, + * - not guaranteed to help because isolate_freepages() + * may not iterate over freed pages as part of its + * linear scan, and + * - unlikely to make entire pageblocks free on its + * own. */ - if (compact_result == COMPACT_DEFERRED) + if (compact_result == COMPACT_SKIPPED || + compact_result == COMPACT_DEFERRED) goto nopage; /* @@ -5323,6 +5329,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) " min:%lukB" " low:%lukB" " high:%lukB" + " reserved_highatomic:%luKB" " active_anon:%lukB" " inactive_anon:%lukB" " active_file:%lukB" @@ -5344,6 +5351,7 @@ void show_free_areas(unsigned int filter, nodemask_t *nodemask) K(min_wmark_pages(zone)), K(low_wmark_pages(zone)), K(high_wmark_pages(zone)), + K(zone->nr_reserved_highatomic), K(zone_page_state(zone, NR_ZONE_ACTIVE_ANON)), K(zone_page_state(zone, NR_ZONE_INACTIVE_ANON)), K(zone_page_state(zone, NR_ZONE_ACTIVE_FILE)), @@ -5840,6 +5848,23 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) return false; } +#ifdef CONFIG_SPARSEMEM +/* Skip PFNs that belong to non-present sections */ +static inline __meminit unsigned long next_pfn(unsigned long pfn) +{ + const unsigned long section_nr = pfn_to_section_nr(++pfn); + + if (present_section_nr(section_nr)) + return pfn; + return section_nr_to_pfn(next_present_section_nr(section_nr)); +} +#else +static inline __meminit unsigned long next_pfn(unsigned long pfn) +{ + return pfn++; +} +#endif + /* * Initially all pages are reserved - free ones are freed * up by memblock_free_all() once the early boot process is @@ -5873,16 +5898,20 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, } #endif - for (pfn = start_pfn; pfn < end_pfn; pfn++) { + for (pfn = start_pfn; pfn < end_pfn; ) { /* * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ if (context == MEMMAP_EARLY) { - if (!early_pfn_valid(pfn)) + if (!early_pfn_valid(pfn)) { + pfn = next_pfn(pfn); continue; - if (!early_pfn_in_nid(pfn, nid)) + } + if (!early_pfn_in_nid(pfn, nid)) { + pfn++; continue; + } if (overlap_memmap_init(zone, &pfn)) continue; if (defer_init(nid, pfn, end_pfn)) @@ -5910,16 +5939,17 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, set_pageblock_migratetype(page, MIGRATE_MOVABLE); cond_resched(); } + pfn++; } } #ifdef CONFIG_ZONE_DEVICE void __ref memmap_init_zone_device(struct zone *zone, unsigned long start_pfn, - unsigned long size, + unsigned long nr_pages, struct dev_pagemap *pgmap) { - unsigned long pfn, end_pfn = start_pfn + size; + unsigned long pfn, end_pfn = start_pfn + nr_pages; struct pglist_data *pgdat = zone->zone_pgdat; struct vmem_altmap *altmap = pgmap_altmap(pgmap); unsigned long zone_idx = zone_idx(zone); @@ -5936,7 +5966,7 @@ void __ref memmap_init_zone_device(struct zone *zone, */ if (altmap) { start_pfn = altmap->base_pfn + vmem_altmap_offset(altmap); - size = end_pfn - start_pfn; + nr_pages = end_pfn - start_pfn; } for (pfn = start_pfn; pfn < end_pfn; pfn++) { @@ -5982,8 +6012,8 @@ void __ref memmap_init_zone_device(struct zone *zone, } } - pr_info("%s initialised, %lu pages in %ums\n", dev_name(pgmap->dev), - size, jiffies_to_msecs(jiffies - start)); + pr_info("%s initialised %lu pages in %ums\n", __func__, + nr_pages, jiffies_to_msecs(jiffies - start)); } #endif @@ -6649,9 +6679,11 @@ static unsigned long __init calc_memmap_size(unsigned long spanned_pages, #ifdef CONFIG_TRANSPARENT_HUGEPAGE static void pgdat_init_split_queue(struct pglist_data *pgdat) { - spin_lock_init(&pgdat->split_queue_lock); - INIT_LIST_HEAD(&pgdat->split_queue); - pgdat->split_queue_len = 0; + struct deferred_split *ds_queue = &pgdat->deferred_split_queue; + + spin_lock_init(&ds_queue->split_queue_lock); + INIT_LIST_HEAD(&ds_queue->split_queue); + ds_queue->split_queue_len = 0; } #else static void pgdat_init_split_queue(struct pglist_data *pgdat) {} @@ -6678,7 +6710,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat) pgdat_page_ext_init(pgdat); spin_lock_init(&pgdat->lru_lock); - lruvec_init(node_lruvec(pgdat)); + lruvec_init(&pgdat->__lruvec); } static void __meminit zone_init_internals(struct zone *zone, enum zone_type idx, int nid, @@ -6880,10 +6912,10 @@ void __init free_area_init_node(int nid, unsigned long *zones_size, #if !defined(CONFIG_FLAT_NODE_MEM_MAP) /* - * Zero all valid struct pages in range [spfn, epfn), return number of struct - * pages zeroed + * Initialize all valid struct pages in the range [spfn, epfn) and mark them + * PageReserved(). Return the number of struct pages that were initialized. */ -static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) +static u64 __init init_unavailable_range(unsigned long spfn, unsigned long epfn) { unsigned long pfn; u64 pgcnt = 0; @@ -6894,7 +6926,13 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) + pageblock_nr_pages - 1; continue; } - mm_zero_struct_page(pfn_to_page(pfn)); + /* + * Use a fake node/zone (0) for now. Some of these pages + * (in memblock.reserved but not in memblock.memory) will + * get re-initialized via reserve_bootmem_region() later. + */ + __init_single_page(pfn_to_page(pfn), pfn, 0, 0); + __SetPageReserved(pfn_to_page(pfn)); pgcnt++; } @@ -6906,14 +6944,15 @@ static u64 zero_pfn_range(unsigned long spfn, unsigned long epfn) * initialized by going through __init_single_page(). But, there are some * struct pages which are reserved in memblock allocator and their fields * may be accessed (for example page_to_pfn() on some configuration accesses - * flags). We must explicitly zero those struct pages. + * flags). We must explicitly initialize those struct pages. * * This function also addresses a similar issue where struct pages are left * uninitialized because the physical address range is not covered by * memblock.memory or memblock.reserved. That could happen when memblock - * layout is manually configured via memmap=. + * layout is manually configured via memmap=, or when the highest physical + * address (max_pfn) does not end on a section boundary. */ -void __init zero_resv_unavail(void) +static void __init init_unavailable_mem(void) { phys_addr_t start, end; u64 i, pgcnt; @@ -6926,10 +6965,20 @@ void __init zero_resv_unavail(void) for_each_mem_range(i, &memblock.memory, NULL, NUMA_NO_NODE, MEMBLOCK_NONE, &start, &end, NULL) { if (next < start) - pgcnt += zero_pfn_range(PFN_DOWN(next), PFN_UP(start)); + pgcnt += init_unavailable_range(PFN_DOWN(next), + PFN_UP(start)); next = end; } - pgcnt += zero_pfn_range(PFN_DOWN(next), max_pfn); + + /* + * Early sections always have a fully populated memmap for the whole + * section - see pfn_valid(). If the last section has holes at the + * end and that section is marked "online", the memmap will be + * considered initialized. Make sure that memmap has a well defined + * state. + */ + pgcnt += init_unavailable_range(PFN_DOWN(next), + round_up(max_pfn, PAGES_PER_SECTION)); /* * Struct pages that do not have backing memory. This could be because @@ -6938,6 +6987,10 @@ void __init zero_resv_unavail(void) if (pgcnt) pr_info("Zeroed struct page in unavailable ranges: %lld pages", pgcnt); } +#else +static inline void __init init_unavailable_mem(void) +{ +} #endif /* !CONFIG_FLAT_NODE_MEM_MAP */ #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP @@ -7367,7 +7420,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Initialise every node */ mminit_verify_pageflags_layout(); setup_nr_node_ids(); - zero_resv_unavail(); + init_unavailable_mem(); for_each_online_node(nid) { pg_data_t *pgdat = NODE_DATA(nid); free_area_init_node(nid, NULL, @@ -7562,7 +7615,7 @@ void __init set_dma_reserve(unsigned long new_dma_reserve) void __init free_area_init(unsigned long *zones_size) { - zero_resv_unavail(); + init_unavailable_mem(); free_area_init_node(0, zones_size, __pa(PAGE_OFFSET) >> PAGE_SHIFT, NULL); } @@ -7955,6 +8008,15 @@ int lowmem_reserve_ratio_sysctl_handler(struct ctl_table *table, int write, return 0; } +static void __zone_pcp_update(struct zone *zone) +{ + unsigned int cpu; + + for_each_possible_cpu(cpu) + pageset_set_high_and_batch(zone, + per_cpu_ptr(zone->pageset, cpu)); +} + /* * percpu_pagelist_fraction - changes the pcp->high for each zone on each * cpu. It is the fraction of total pages in each zone that a hot per cpu @@ -7986,13 +8048,8 @@ int percpu_pagelist_fraction_sysctl_handler(struct ctl_table *table, int write, if (percpu_pagelist_fraction == old_percpu_pagelist_fraction) goto out; - for_each_populated_zone(zone) { - unsigned int cpu; - - for_each_possible_cpu(cpu) - pageset_set_high_and_batch(zone, - per_cpu_ptr(zone->pageset, cpu)); - } + for_each_populated_zone(zone) + __zone_pcp_update(zone); out: mutex_unlock(&pcp_batch_high_lock); return ret; @@ -8140,20 +8197,22 @@ void *__init alloc_large_system_hash(const char *tablename, /* * This function checks whether pageblock includes unmovable pages or not. - * If @count is not zero, it is okay to include less @count unmovable pages * * PageLRU check without isolation or lru_lock could race so that * MIGRATE_MOVABLE block might include unmovable pages. And __PageMovable * check without lock_page also may miss some movable non-lru pages at * race condition. So you can't expect this function should be exact. + * + * Returns a page without holding a reference. If the caller wants to + * dereference that page (e.g., dumping), it has to make sure that that it + * cannot get removed (e.g., via memory unplug) concurrently. + * */ -bool has_unmovable_pages(struct zone *zone, struct page *page, int count, - int migratetype, int flags) +struct page *has_unmovable_pages(struct zone *zone, struct page *page, + int migratetype, int flags) { - unsigned long found; unsigned long iter = 0; unsigned long pfn = page_to_pfn(page); - const char *reason = "unmovable page"; /* * TODO we could make this much more efficient by not checking every @@ -8170,22 +8229,19 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * so consider them movable here. */ if (is_migrate_cma(migratetype)) - return false; + return NULL; - reason = "CMA page"; - goto unmovable; + return page; } - for (found = 0; iter < pageblock_nr_pages; iter++) { - unsigned long check = pfn + iter; - - if (!pfn_valid_within(check)) + for (; iter < pageblock_nr_pages; iter++) { + if (!pfn_valid_within(pfn + iter)) continue; - page = pfn_to_page(check); + page = pfn_to_page(pfn + iter); if (PageReserved(page)) - goto unmovable; + return page; /* * If the zone is movable and we have ruled out all reserved @@ -8205,9 +8261,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, unsigned int skip_pages; if (!hugepage_migration_supported(page_hstate(head))) - goto unmovable; + return page; - skip_pages = (1 << compound_order(head)) - (page - head); + skip_pages = compound_nr(head) - (page - head); iter += skip_pages - 1; continue; } @@ -8228,14 +8284,12 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * The HWPoisoned page may be not in buddy system, and * page_count() is not 0. */ - if ((flags & SKIP_HWPOISON) && PageHWPoison(page)) + if ((flags & MEMORY_OFFLINE) && PageHWPoison(page)) continue; - if (__PageMovable(page)) + if (__PageMovable(page) || PageLRU(page)) continue; - if (!PageLRU(page)) - found++; /* * If there are RECLAIMABLE pages, we need to check * it. But now, memory offline itself doesn't call @@ -8249,15 +8303,9 @@ bool has_unmovable_pages(struct zone *zone, struct page *page, int count, * is set to both of a memory hole page and a _used_ kernel * page at boot. */ - if (found > count) - goto unmovable; + return page; } - return false; -unmovable: - WARN_ON_ONCE(zone_idx(zone) == ZONE_MOVABLE); - if (flags & REPORT_FAILURE) - dump_page(pfn_to_page(pfn + iter), reason); - return true; + return NULL; } #ifdef CONFIG_CONTIG_ALLOC @@ -8444,7 +8492,7 @@ int alloc_contig_range(unsigned long start, unsigned long end, } /* Make sure the range is really isolated. */ - if (test_pages_isolated(outer_start, end, false)) { + if (test_pages_isolated(outer_start, end, 0)) { pr_info_ratelimited("%s: [%lx, %lx) PFNs busy\n", __func__, outer_start, end); ret = -EBUSY; @@ -8469,6 +8517,107 @@ done: pfn_max_align_up(end), migratetype); return ret; } + +static int __alloc_contig_pages(unsigned long start_pfn, + unsigned long nr_pages, gfp_t gfp_mask) +{ + unsigned long end_pfn = start_pfn + nr_pages; + + return alloc_contig_range(start_pfn, end_pfn, MIGRATE_MOVABLE, + gfp_mask); +} + +static bool pfn_range_valid_contig(struct zone *z, unsigned long start_pfn, + unsigned long nr_pages) +{ + unsigned long i, end_pfn = start_pfn + nr_pages; + struct page *page; + + for (i = start_pfn; i < end_pfn; i++) { + page = pfn_to_online_page(i); + if (!page) + return false; + + if (page_zone(page) != z) + return false; + + if (PageReserved(page)) + return false; + + if (page_count(page) > 0) + return false; + + if (PageHuge(page)) + return false; + } + return true; +} + +static bool zone_spans_last_pfn(const struct zone *zone, + unsigned long start_pfn, unsigned long nr_pages) +{ + unsigned long last_pfn = start_pfn + nr_pages - 1; + + return zone_spans_pfn(zone, last_pfn); +} + +/** + * alloc_contig_pages() -- tries to find and allocate contiguous range of pages + * @nr_pages: Number of contiguous pages to allocate + * @gfp_mask: GFP mask to limit search and used during compaction + * @nid: Target node + * @nodemask: Mask for other possible nodes + * + * This routine is a wrapper around alloc_contig_range(). It scans over zones + * on an applicable zonelist to find a contiguous pfn range which can then be + * tried for allocation with alloc_contig_range(). This routine is intended + * for allocation requests which can not be fulfilled with the buddy allocator. + * + * The allocated memory is always aligned to a page boundary. If nr_pages is a + * power of two then the alignment is guaranteed to be to the given nr_pages + * (e.g. 1GB request would be aligned to 1GB). + * + * Allocated pages can be freed with free_contig_range() or by manually calling + * __free_page() on each allocated page. + * + * Return: pointer to contiguous pages on success, or NULL if not successful. + */ +struct page *alloc_contig_pages(unsigned long nr_pages, gfp_t gfp_mask, + int nid, nodemask_t *nodemask) +{ + unsigned long ret, pfn, flags; + struct zonelist *zonelist; + struct zone *zone; + struct zoneref *z; + + zonelist = node_zonelist(nid, gfp_mask); + for_each_zone_zonelist_nodemask(zone, z, zonelist, + gfp_zone(gfp_mask), nodemask) { + spin_lock_irqsave(&zone->lock, flags); + + pfn = ALIGN(zone->zone_start_pfn, nr_pages); + while (zone_spans_last_pfn(zone, pfn, nr_pages)) { + if (pfn_range_valid_contig(zone, pfn, nr_pages)) { + /* + * We release the zone lock here because + * alloc_contig_range() will also lock the zone + * at some point. If there's an allocation + * spinning on this lock, it may win the race + * and cause alloc_contig_range() to fail... + */ + spin_unlock_irqrestore(&zone->lock, flags); + ret = __alloc_contig_pages(pfn, nr_pages, + gfp_mask); + if (!ret) + return pfn_to_page(pfn); + spin_lock_irqsave(&zone->lock, flags); + } + pfn += nr_pages; + } + spin_unlock_irqrestore(&zone->lock, flags); + } + return NULL; +} #endif /* CONFIG_CONTIG_ALLOC */ void free_contig_range(unsigned long pfn, unsigned int nr_pages) @@ -8484,21 +8633,16 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) WARN(count != 0, "%d pages are still in use!\n", count); } -#ifdef CONFIG_MEMORY_HOTPLUG /* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalulated. */ void __meminit zone_pcp_update(struct zone *zone) { - unsigned cpu; mutex_lock(&pcp_batch_high_lock); - for_each_possible_cpu(cpu) - pageset_set_high_and_batch(zone, - per_cpu_ptr(zone->pageset, cpu)); + __zone_pcp_update(zone); mutex_unlock(&pcp_batch_high_lock); } -#endif void zone_pcp_reset(struct zone *zone) { @@ -8529,7 +8673,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) { struct page *page; struct zone *zone; - unsigned int order, i; + unsigned int order; unsigned long pfn; unsigned long flags; unsigned long offlined_pages = 0; @@ -8557,7 +8701,6 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) */ if (unlikely(!PageBuddy(page) && PageHWPoison(page))) { pfn++; - SetPageReserved(page); offlined_pages++; continue; } @@ -8566,13 +8709,7 @@ __offline_isolated_pages(unsigned long start_pfn, unsigned long end_pfn) BUG_ON(!PageBuddy(page)); order = page_order(page); offlined_pages += 1 << order; -#ifdef CONFIG_DEBUG_VM - pr_info("remove from free list %lx %d %lx\n", - pfn, 1 << order, end_pfn); -#endif del_page_from_free_area(page, &zone->free_area[order]); - for (i = 0; i < (1 << order); i++) - SetPageReserved((page+i)); pfn += (1 << order); } spin_unlock_irqrestore(&zone->lock, flags); |
