diff --git a/MAINTAINERS b/MAINTAINERS index ea4d0058fd1b..60b1163dba28 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -4716,6 +4716,7 @@ L: linux-iio@vger.kernel.org S: Maintained F: drivers/iio/ F: drivers/staging/iio/ +F: include/linux/iio/ IKANOS/ADI EAGLE ADSL USB DRIVER M: Matthieu Castet diff --git a/drivers/block/zram/zram_drv.c b/drivers/block/zram/zram_drv.c index 2ad0b5bce44b..3920ee45aa59 100644 --- a/drivers/block/zram/zram_drv.c +++ b/drivers/block/zram/zram_drv.c @@ -560,7 +560,8 @@ static int zram_bvec_write(struct zram *zram, struct bio_vec *bvec, u32 index, } if (page_zero_filled(uncmem)) { - kunmap_atomic(user_mem); + if (user_mem) + kunmap_atomic(user_mem); /* Free memory associated with this sector now. */ bit_spin_lock(ZRAM_ACCESS, &meta->table[index].value); zram_free_page(zram, index); diff --git a/fs/notify/fsnotify.c b/fs/notify/fsnotify.c index 9d3e9c50066a..89326acd4561 100644 --- a/fs/notify/fsnotify.c +++ b/fs/notify/fsnotify.c @@ -229,8 +229,16 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, &fsnotify_mark_srcu); } + /* + * We need to merge inode & vfsmount mark lists so that inode mark + * ignore masks are properly reflected for mount mark notifications. + * That's why this traversal is so complicated... + */ while (inode_node || vfsmount_node) { - inode_group = vfsmount_group = NULL; + inode_group = NULL; + inode_mark = NULL; + vfsmount_group = NULL; + vfsmount_mark = NULL; if (inode_node) { inode_mark = hlist_entry(srcu_dereference(inode_node, &fsnotify_mark_srcu), @@ -244,21 +252,19 @@ int fsnotify(struct inode *to_tell, __u32 mask, void *data, int data_is, vfsmount_group = vfsmount_mark->group; } - if (inode_group > vfsmount_group) { - /* handle inode */ - ret = send_to_group(to_tell, inode_mark, NULL, mask, - data, data_is, cookie, file_name); - /* we didn't use the vfsmount_mark */ - vfsmount_group = NULL; - } else if (vfsmount_group > inode_group) { - ret = send_to_group(to_tell, NULL, vfsmount_mark, mask, - data, data_is, cookie, file_name); - inode_group = NULL; - } else { - ret = send_to_group(to_tell, inode_mark, vfsmount_mark, - mask, data, data_is, cookie, - file_name); + if (inode_group && vfsmount_group) { + int cmp = fsnotify_compare_groups(inode_group, + vfsmount_group); + if (cmp > 0) { + inode_group = NULL; + inode_mark = NULL; + } else if (cmp < 0) { + vfsmount_group = NULL; + vfsmount_mark = NULL; + } } + ret = send_to_group(to_tell, inode_mark, vfsmount_mark, mask, + data, data_is, cookie, file_name); if (ret && (mask & ALL_FSNOTIFY_PERM_EVENTS)) goto out; diff --git a/fs/notify/fsnotify.h b/fs/notify/fsnotify.h index 9c0898c4cfe1..3b68b0ae0a97 100644 --- a/fs/notify/fsnotify.h +++ b/fs/notify/fsnotify.h @@ -12,6 +12,10 @@ extern void fsnotify_flush_notify(struct fsnotify_group *group); /* protects reads of inode and vfsmount marks list */ extern struct srcu_struct fsnotify_mark_srcu; +/* compare two groups for sorting of marks lists */ +extern int fsnotify_compare_groups(struct fsnotify_group *a, + struct fsnotify_group *b); + extern void fsnotify_set_inode_mark_mask_locked(struct fsnotify_mark *fsn_mark, __u32 mask); /* add a mark to an inode */ diff --git a/fs/notify/inode_mark.c b/fs/notify/inode_mark.c index e8497144b323..dfbf5447eea4 100644 --- a/fs/notify/inode_mark.c +++ b/fs/notify/inode_mark.c @@ -194,6 +194,7 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, { struct fsnotify_mark *lmark, *last = NULL; int ret = 0; + int cmp; mark->flags |= FSNOTIFY_MARK_FLAG_INODE; @@ -219,11 +220,8 @@ int fsnotify_add_inode_mark(struct fsnotify_mark *mark, goto out; } - if (mark->group->priority < lmark->group->priority) - continue; - - if ((mark->group->priority == lmark->group->priority) && - (mark->group < lmark->group)) + cmp = fsnotify_compare_groups(lmark->group, mark->group); + if (cmp < 0) continue; hlist_add_before_rcu(&mark->i.i_list, &lmark->i.i_list); diff --git a/fs/notify/mark.c b/fs/notify/mark.c index d90deaa08e78..34c38fabf514 100644 --- a/fs/notify/mark.c +++ b/fs/notify/mark.c @@ -209,6 +209,42 @@ void fsnotify_set_mark_ignored_mask_locked(struct fsnotify_mark *mark, __u32 mas mark->ignored_mask = mask; } +/* + * Sorting function for lists of fsnotify marks. + * + * Fanotify supports different notification classes (reflected as priority of + * notification group). Events shall be passed to notification groups in + * decreasing priority order. To achieve this marks in notification lists for + * inodes and vfsmounts are sorted so that priorities of corresponding groups + * are descending. + * + * Furthermore correct handling of the ignore mask requires processing inode + * and vfsmount marks of each group together. Using the group address as + * further sort criterion provides a unique sorting order and thus we can + * merge inode and vfsmount lists of marks in linear time and find groups + * present in both lists. + * + * A return value of 1 signifies that b has priority over a. + * A return value of 0 signifies that the two marks have to be handled together. + * A return value of -1 signifies that a has priority over b. + */ +int fsnotify_compare_groups(struct fsnotify_group *a, struct fsnotify_group *b) +{ + if (a == b) + return 0; + if (!a) + return 1; + if (!b) + return -1; + if (a->priority < b->priority) + return 1; + if (a->priority > b->priority) + return -1; + if (a < b) + return 1; + return -1; +} + /* * Attach an initialized mark to a given group and fs object. * These marks may be used for the fsnotify backend to determine which diff --git a/fs/notify/vfsmount_mark.c b/fs/notify/vfsmount_mark.c index ac851e8376b1..faefa72a11eb 100644 --- a/fs/notify/vfsmount_mark.c +++ b/fs/notify/vfsmount_mark.c @@ -153,6 +153,7 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, struct mount *m = real_mount(mnt); struct fsnotify_mark *lmark, *last = NULL; int ret = 0; + int cmp; mark->flags |= FSNOTIFY_MARK_FLAG_VFSMOUNT; @@ -178,11 +179,8 @@ int fsnotify_add_vfsmount_mark(struct fsnotify_mark *mark, goto out; } - if (mark->group->priority < lmark->group->priority) - continue; - - if ((mark->group->priority == lmark->group->priority) && - (mark->group < lmark->group)) + cmp = fsnotify_compare_groups(lmark->group, mark->group); + if (cmp < 0) continue; hlist_add_before_rcu(&mark->m.m_list, &lmark->m.m_list); diff --git a/include/linux/bootmem.h b/include/linux/bootmem.h index 4e2bd4c95b66..0995c2de8162 100644 --- a/include/linux/bootmem.h +++ b/include/linux/bootmem.h @@ -46,6 +46,7 @@ extern unsigned long init_bootmem_node(pg_data_t *pgdat, extern unsigned long init_bootmem(unsigned long addr, unsigned long memend); extern unsigned long free_all_bootmem(void); +extern void reset_node_managed_pages(pg_data_t *pgdat); extern void reset_all_zones_managed_pages(void); extern void free_bootmem_node(pg_data_t *pgdat, diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h index 48bf12ef6620..ffe66e381c04 100644 --- a/include/linux/mmzone.h +++ b/include/linux/mmzone.h @@ -431,6 +431,15 @@ struct zone { */ int nr_migrate_reserve_block; +#ifdef CONFIG_MEMORY_ISOLATION + /* + * Number of isolated pageblock. It is used to solve incorrect + * freepage counting problem due to racy retrieving migratetype + * of pageblock. Protected by zone->lock. + */ + unsigned long nr_isolate_pageblock; +#endif + #ifdef CONFIG_MEMORY_HOTPLUG /* see spanned/present_pages for more description */ seqlock_t span_seqlock; diff --git a/include/linux/page-isolation.h b/include/linux/page-isolation.h index 3fff8e774067..2dc1e1697b45 100644 --- a/include/linux/page-isolation.h +++ b/include/linux/page-isolation.h @@ -2,6 +2,10 @@ #define __LINUX_PAGEISOLATION_H #ifdef CONFIG_MEMORY_ISOLATION +static inline bool has_isolate_pageblock(struct zone *zone) +{ + return zone->nr_isolate_pageblock; +} static inline bool is_migrate_isolate_page(struct page *page) { return get_pageblock_migratetype(page) == MIGRATE_ISOLATE; @@ -11,6 +15,10 @@ static inline bool is_migrate_isolate(int migratetype) return migratetype == MIGRATE_ISOLATE; } #else +static inline bool has_isolate_pageblock(struct zone *zone) +{ + return false; +} static inline bool is_migrate_isolate_page(struct page *page) { return false; diff --git a/kernel/panic.c b/kernel/panic.c index d09dc5c32c67..cf80672b7924 100644 --- a/kernel/panic.c +++ b/kernel/panic.c @@ -244,6 +244,7 @@ static const struct tnt tnts[] = { * 'I' - Working around severe firmware bug. * 'O' - Out-of-tree module has been loaded. * 'E' - Unsigned module has been loaded. + * 'L' - A soft lockup has previously occurred. * * The string is overwritten by the next call to print_tainted(). */ diff --git a/mm/bootmem.c b/mm/bootmem.c index 8a000cebb0d7..477be696511d 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -243,13 +243,10 @@ static unsigned long __init free_all_bootmem_core(bootmem_data_t *bdata) static int reset_managed_pages_done __initdata; -static inline void __init reset_node_managed_pages(pg_data_t *pgdat) +void reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; - if (reset_managed_pages_done) - return; - for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) z->managed_pages = 0; } @@ -258,8 +255,12 @@ void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; + if (reset_managed_pages_done) + return; + for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); + reset_managed_pages_done = 1; } diff --git a/mm/compaction.c b/mm/compaction.c index ec74cf0123ef..f9792ba3537c 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -479,6 +479,16 @@ isolate_freepages_range(struct compact_control *cc, block_end_pfn = min(block_end_pfn, end_pfn); + /* + * pfn could pass the block_end_pfn if isolated freepage + * is more than pageblock order. In this case, we adjust + * scanning range to right one. + */ + if (pfn >= block_end_pfn) { + block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); + block_end_pfn = min(block_end_pfn, end_pfn); + } + if (!pageblock_pfn_to_page(pfn, block_end_pfn, cc->zone)) break; @@ -1029,8 +1039,12 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, } acct_isolated(zone, cc); - /* Record where migration scanner will be restarted */ - cc->migrate_pfn = low_pfn; + /* + * Record where migration scanner will be restarted. If we end up in + * the same pageblock as the free scanner, make the scanners fully + * meet so that compact_finished() terminates compaction. + */ + cc->migrate_pfn = (end_pfn <= cc->free_pfn) ? low_pfn : cc->free_pfn; return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } diff --git a/mm/internal.h b/mm/internal.h index 829304090b90..a4f90ba7068e 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -108,6 +108,31 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); /* * in mm/page_alloc.c */ + +/* + * Locate the struct page for both the matching buddy in our + * pair (buddy1) and the combined O(n+1) page they form (page). + * + * 1) Any buddy B1 will have an order O twin B2 which satisfies + * the following equation: + * B2 = B1 ^ (1 << O) + * For example, if the starting buddy (buddy2) is #8 its order + * 1 buddy is #10: + * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 + * + * 2) Any buddy B will have an order O+1 parent P which + * satisfies the following equation: + * P = B & ~(1 << O) + * + * Assumption: *_mem_map is contiguous at least up to MAX_ORDER + */ +static inline unsigned long +__find_buddy_index(unsigned long page_idx, unsigned int order) +{ + return page_idx ^ (1 << order); +} + +extern int __isolate_free_page(struct page *page, unsigned int order); extern void __free_pages_bootmem(struct page *page, unsigned int order); extern void prep_compound_page(struct page *page, unsigned long order); #ifdef CONFIG_MEMORY_FAILURE diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 252e1dbbed86..1bf4807cb21e 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -31,6 +31,7 @@ #include #include #include +#include #include @@ -1066,6 +1067,16 @@ out: } #endif /* CONFIG_MEMORY_HOTPLUG_SPARSE */ +static void reset_node_present_pages(pg_data_t *pgdat) +{ + struct zone *z; + + for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) + z->present_pages = 0; + + pgdat->node_present_pages = 0; +} + /* we are OK calling __meminit stuff here - we have CONFIG_MEMORY_HOTPLUG */ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) { @@ -1096,6 +1107,21 @@ static pg_data_t __ref *hotadd_new_pgdat(int nid, u64 start) build_all_zonelists(pgdat, NULL); mutex_unlock(&zonelists_mutex); + /* + * zone->managed_pages is set to an approximate value in + * free_area_init_core(), which will cause + * /sys/device/system/node/nodeX/meminfo has wrong data. + * So reset it to 0 before any memory is onlined. + */ + reset_node_managed_pages(pgdat); + + /* + * When memory is hot-added, all the memory is in offline state. So + * clear all zones' present_pages because they will be updated in + * online_pages() and offline_pages(). + */ + reset_node_present_pages(pgdat); + return pgdat; } diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 7c7ab32ee503..90b50468333e 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -145,12 +145,10 @@ static unsigned long __init free_low_memory_core_early(void) static int reset_managed_pages_done __initdata; -static inline void __init reset_node_managed_pages(pg_data_t *pgdat) +void reset_node_managed_pages(pg_data_t *pgdat) { struct zone *z; - if (reset_managed_pages_done) - return; for (z = pgdat->node_zones; z < pgdat->node_zones + MAX_NR_ZONES; z++) z->managed_pages = 0; } @@ -159,8 +157,12 @@ void __init reset_all_zones_managed_pages(void) { struct pglist_data *pgdat; + if (reset_managed_pages_done) + return; + for_each_online_pgdat(pgdat) reset_node_managed_pages(pgdat); + reset_managed_pages_done = 1; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 9cd36b822444..616a2c956b4b 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -466,29 +466,6 @@ static inline void rmv_page_order(struct page *page) set_page_private(page, 0); } -/* - * Locate the struct page for both the matching buddy in our - * pair (buddy1) and the combined O(n+1) page they form (page). - * - * 1) Any buddy B1 will have an order O twin B2 which satisfies - * the following equation: - * B2 = B1 ^ (1 << O) - * For example, if the starting buddy (buddy2) is #8 its order - * 1 buddy is #10: - * B2 = 8 ^ (1 << 1) = 8 ^ 2 = 10 - * - * 2) Any buddy B will have an order O+1 parent P which - * satisfies the following equation: - * P = B & ~(1 << O) - * - * Assumption: *_mem_map is contiguous at least up to MAX_ORDER - */ -static inline unsigned long -__find_buddy_index(unsigned long page_idx, unsigned int order) -{ - return page_idx ^ (1 << order); -} - /* * This function checks whether a page is free && is the buddy * we can do coalesce a page and its buddy if @@ -569,6 +546,7 @@ static inline void __free_one_page(struct page *page, unsigned long combined_idx; unsigned long uninitialized_var(buddy_idx); struct page *buddy; + int max_order = MAX_ORDER; VM_BUG_ON(!zone_is_initialized(zone)); @@ -577,13 +555,24 @@ static inline void __free_one_page(struct page *page, return; VM_BUG_ON(migratetype == -1); + if (is_migrate_isolate(migratetype)) { + /* + * We restrict max order of merging to prevent merge + * between freepages on isolate pageblock and normal + * pageblock. Without this, pageblock isolation + * could cause incorrect freepage accounting. + */ + max_order = min(MAX_ORDER, pageblock_order + 1); + } else { + __mod_zone_freepage_state(zone, 1 << order, migratetype); + } - page_idx = pfn & ((1 << MAX_ORDER) - 1); + page_idx = pfn & ((1 << max_order) - 1); VM_BUG_ON_PAGE(page_idx & ((1 << order) - 1), page); VM_BUG_ON_PAGE(bad_range(zone, page), page); - while (order < MAX_ORDER-1) { + while (order < max_order - 1) { buddy_idx = __find_buddy_index(page_idx, order); buddy = page + (buddy_idx - page_idx); if (!page_is_buddy(page, buddy, order)) @@ -594,9 +583,11 @@ static inline void __free_one_page(struct page *page, */ if (page_is_guard(buddy)) { clear_page_guard_flag(buddy); - set_page_private(page, 0); - __mod_zone_freepage_state(zone, 1 << order, - migratetype); + set_page_private(buddy, 0); + if (!is_migrate_isolate(migratetype)) { + __mod_zone_freepage_state(zone, 1 << order, + migratetype); + } } else { list_del(&buddy->lru); zone->free_area[order].nr_free--; @@ -715,14 +706,12 @@ static void free_pcppages_bulk(struct zone *zone, int count, /* must delete as __free_one_page list manipulates */ list_del(&page->lru); mt = get_freepage_migratetype(page); + if (unlikely(has_isolate_pageblock(zone))) + mt = get_pageblock_migratetype(page); + /* MIGRATE_MOVABLE list may include MIGRATE_RESERVEs */ __free_one_page(page, page_to_pfn(page), zone, 0, mt); trace_mm_page_pcpu_drain(page, 0, mt); - if (likely(!is_migrate_isolate_page(page))) { - __mod_zone_page_state(zone, NR_FREE_PAGES, 1); - if (is_migrate_cma(mt)) - __mod_zone_page_state(zone, NR_FREE_CMA_PAGES, 1); - } } while (--to_free && --batch_free && !list_empty(list)); } spin_unlock(&zone->lock); @@ -739,9 +728,11 @@ static void free_one_page(struct zone *zone, if (nr_scanned) __mod_zone_page_state(zone, NR_PAGES_SCANNED, -nr_scanned); + if (unlikely(has_isolate_pageblock(zone) || + is_migrate_isolate(migratetype))) { + migratetype = get_pfnblock_migratetype(page, pfn); + } __free_one_page(page, pfn, zone, order, migratetype); - if (unlikely(!is_migrate_isolate(migratetype))) - __mod_zone_freepage_state(zone, 1 << order, migratetype); spin_unlock(&zone->lock); } @@ -1484,7 +1475,7 @@ void split_page(struct page *page, unsigned int order) } EXPORT_SYMBOL_GPL(split_page); -static int __isolate_free_page(struct page *page, unsigned int order) +int __isolate_free_page(struct page *page, unsigned int order) { unsigned long watermark; struct zone *zone; @@ -6408,13 +6399,12 @@ 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)) { - pr_warn("alloc_contig_range test_pages_isolated(%lx, %lx) failed\n", - outer_start, end); + pr_info("%s: [%lx, %lx) PFNs busy\n", + __func__, outer_start, end); ret = -EBUSY; goto done; } - /* Grab isolated pages from freelists. */ outer_end = isolate_freepages_range(&cc, outer_start, end); if (!outer_end) { diff --git a/mm/page_isolation.c b/mm/page_isolation.c index d1473b2e9481..c8778f7e208e 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -60,6 +60,7 @@ out: int migratetype = get_pageblock_migratetype(page); set_pageblock_migratetype(page, MIGRATE_ISOLATE); + zone->nr_isolate_pageblock++; nr_pages = move_freepages_block(zone, page, MIGRATE_ISOLATE); __mod_zone_freepage_state(zone, -nr_pages, migratetype); @@ -75,16 +76,54 @@ void unset_migratetype_isolate(struct page *page, unsigned migratetype) { struct zone *zone; unsigned long flags, nr_pages; + struct page *isolated_page = NULL; + unsigned int order; + unsigned long page_idx, buddy_idx; + struct page *buddy; zone = page_zone(page); spin_lock_irqsave(&zone->lock, flags); if (get_pageblock_migratetype(page) != MIGRATE_ISOLATE) goto out; - nr_pages = move_freepages_block(zone, page, migratetype); - __mod_zone_freepage_state(zone, nr_pages, migratetype); + + /* + * Because freepage with more than pageblock_order on isolated + * pageblock is restricted to merge due to freepage counting problem, + * it is possible that there is free buddy page. + * move_freepages_block() doesn't care of merge so we need other + * approach in order to merge them. Isolation and free will make + * these pages to be merged. + */ + if (PageBuddy(page)) { + order = page_order(page); + if (order >= pageblock_order) { + page_idx = page_to_pfn(page) & ((1 << MAX_ORDER) - 1); + buddy_idx = __find_buddy_index(page_idx, order); + buddy = page + (buddy_idx - page_idx); + + if (!is_migrate_isolate_page(buddy)) { + __isolate_free_page(page, order); + set_page_refcounted(page); + isolated_page = page; + } + } + } + + /* + * If we isolate freepage with more than pageblock_order, there + * should be no freepage in the range, so we could avoid costly + * pageblock scanning for freepage moving. + */ + if (!isolated_page) { + nr_pages = move_freepages_block(zone, page, migratetype); + __mod_zone_freepage_state(zone, nr_pages, migratetype); + } set_pageblock_migratetype(page, migratetype); + zone->nr_isolate_pageblock--; out: spin_unlock_irqrestore(&zone->lock, flags); + if (isolated_page) + __free_pages(isolated_page, order); } static inline struct page * diff --git a/mm/slab_common.c b/mm/slab_common.c index 406944207b61..dcdab81bd240 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -259,6 +259,10 @@ struct kmem_cache *find_mergeable(size_t size, size_t align, if (s->size - size >= sizeof(void *)) continue; + if (IS_ENABLED(CONFIG_SLAB) && align && + (align > s->align || s->align % align)) + continue; + return s; } return NULL;