diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 11 | ||||
| -rw-r--r-- | mm/Makefile | 7 | ||||
| -rw-r--r-- | mm/backing-dev.c | 107 | ||||
| -rw-r--r-- | mm/cleancache.c | 2 | ||||
| -rw-r--r-- | mm/cma.c | 2 | ||||
| -rw-r--r-- | mm/compaction.c | 181 | ||||
| -rw-r--r-- | mm/debug.c | 4 | ||||
| -rw-r--r-- | mm/fadvise.c | 10 | ||||
| -rw-r--r-- | mm/filemap.c | 30 | ||||
| -rw-r--r-- | mm/filemap_xip.c | 478 | ||||
| -rw-r--r-- | mm/fremap.c | 283 | ||||
| -rw-r--r-- | mm/gup.c | 242 | ||||
| -rw-r--r-- | mm/huge_memory.c | 156 | ||||
| -rw-r--r-- | mm/hugetlb.c | 160 | ||||
| -rw-r--r-- | mm/hugetlb_cgroup.c | 2 | ||||
| -rw-r--r-- | mm/internal.h | 28 | ||||
| -rw-r--r-- | mm/interval_tree.c | 34 | ||||
| -rw-r--r-- | mm/iov_iter.c | 17 | ||||
| -rw-r--r-- | mm/kasan/Makefile | 8 | ||||
| -rw-r--r-- | mm/kasan/kasan.c | 516 | ||||
| -rw-r--r-- | mm/kasan/kasan.h | 75 | ||||
| -rw-r--r-- | mm/kasan/report.c | 269 | ||||
| -rw-r--r-- | mm/kmemleak.c | 6 | ||||
| -rw-r--r-- | mm/ksm.c | 2 | ||||
| -rw-r--r-- | mm/list_lru.c | 467 | ||||
| -rw-r--r-- | mm/madvise.c | 32 | ||||
| -rw-r--r-- | mm/memcontrol.c | 1075 | ||||
| -rw-r--r-- | mm/memory-failure.c | 13 | ||||
| -rw-r--r-- | mm/memory.c | 355 | ||||
| -rw-r--r-- | mm/mempolicy.c | 286 | ||||
| -rw-r--r-- | mm/migrate.c | 45 | ||||
| -rw-r--r-- | mm/mincore.c | 175 | ||||
| -rw-r--r-- | mm/mm_init.c | 4 | ||||
| -rw-r--r-- | mm/mmap.c | 100 | ||||
| -rw-r--r-- | mm/mmzone.c | 4 | ||||
| -rw-r--r-- | mm/mprotect.c | 50 | ||||
| -rw-r--r-- | mm/mremap.c | 2 | ||||
| -rw-r--r-- | mm/msync.c | 5 | ||||
| -rw-r--r-- | mm/nommu.c | 115 | ||||
| -rw-r--r-- | mm/oom_kill.c | 169 | ||||
| -rw-r--r-- | mm/page-writeback.c | 46 | ||||
| -rw-r--r-- | mm/page_alloc.c | 462 | ||||
| -rw-r--r-- | mm/page_counter.c | 7 | ||||
| -rw-r--r-- | mm/page_io.c | 9 | ||||
| -rw-r--r-- | mm/page_owner.c | 26 | ||||
| -rw-r--r-- | mm/pagewalk.c | 235 | ||||
| -rw-r--r-- | mm/percpu.c | 6 | ||||
| -rw-r--r-- | mm/pgtable-generic.c | 2 | ||||
| -rw-r--r-- | mm/process_vm_access.c | 7 | ||||
| -rw-r--r-- | mm/readahead.c | 4 | ||||
| -rw-r--r-- | mm/rmap.c | 237 | ||||
| -rw-r--r-- | mm/shmem.c | 29 | ||||
| -rw-r--r-- | mm/slab.c | 17 | ||||
| -rw-r--r-- | mm/slab.h | 67 | ||||
| -rw-r--r-- | mm/slab_common.c | 323 | ||||
| -rw-r--r-- | mm/slob.c | 2 | ||||
| -rw-r--r-- | mm/slub.c | 232 | ||||
| -rw-r--r-- | mm/swap.c | 6 | ||||
| -rw-r--r-- | mm/swap_state.c | 6 | ||||
| -rw-r--r-- | mm/truncate.c | 2 | ||||
| -rw-r--r-- | mm/util.c | 48 | ||||
| -rw-r--r-- | mm/vmalloc.c | 16 | ||||
| -rw-r--r-- | mm/vmscan.c | 121 | ||||
| -rw-r--r-- | mm/vmstat.c | 130 | ||||
| -rw-r--r-- | mm/workingset.c | 9 | ||||
| -rw-r--r-- | mm/zbud.c | 3 | ||||
| -rw-r--r-- | mm/zpool.c | 6 | ||||
| -rw-r--r-- | mm/zsmalloc.c | 239 | ||||
| -rw-r--r-- | mm/zswap.c | 5 |
69 files changed, 4518 insertions, 3311 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 1d1ae6b078fd..de5239c152f9 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -325,6 +325,7 @@ config VIRT_TO_BUS config MMU_NOTIFIER bool + select SRCU config KSM bool "Enable KSM for page merging" @@ -601,6 +602,16 @@ config PGTABLE_MAPPING You can check speed with zsmalloc benchmark: https://github.com/spartacus06/zsmapbench +config ZSMALLOC_STAT + bool "Export zsmalloc statistics" + depends on ZSMALLOC + select DEBUG_FS + help + This option enables code in the zsmalloc to collect various + statistics about whats happening in zsmalloc and exports that + information to userspace via debugfs. + If unsure, say N. + config GENERIC_EARLY_IOREMAP bool diff --git a/mm/Makefile b/mm/Makefile index 4bf586e66378..3c1caa2693bd 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -2,8 +2,11 @@ # Makefile for the linux memory manager. # +KASAN_SANITIZE_slab_common.o := n +KASAN_SANITIZE_slub.o := n + mmu-y := nommu.o -mmu-$(CONFIG_MMU) := fremap.o gup.o highmem.o memory.o mincore.o \ +mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ vmalloc.o pagewalk.o pgtable-generic.o @@ -49,9 +52,9 @@ obj-$(CONFIG_PAGE_POISONING) += debug-pagealloc.o obj-$(CONFIG_SLAB) += slab.o obj-$(CONFIG_SLUB) += slub.o obj-$(CONFIG_KMEMCHECK) += kmemcheck.o +obj-$(CONFIG_KASAN) += kasan/ obj-$(CONFIG_FAILSLAB) += failslab.o obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o -obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 915feea94c66..6dc4580df2af 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -14,19 +14,10 @@ static atomic_long_t bdi_seq = ATOMIC_LONG_INIT(0); -struct backing_dev_info default_backing_dev_info = { - .name = "default", - .ra_pages = VM_MAX_READAHEAD * 1024 / PAGE_CACHE_SIZE, - .state = 0, - .capabilities = BDI_CAP_MAP_COPY, -}; -EXPORT_SYMBOL_GPL(default_backing_dev_info); - struct backing_dev_info noop_backing_dev_info = { .name = "noop", .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK, }; -EXPORT_SYMBOL_GPL(noop_backing_dev_info); static struct class *bdi_class; @@ -40,17 +31,6 @@ LIST_HEAD(bdi_list); /* bdi_wq serves all asynchronous writeback tasks */ struct workqueue_struct *bdi_wq; -static void bdi_lock_two(struct bdi_writeback *wb1, struct bdi_writeback *wb2) -{ - if (wb1 < wb2) { - spin_lock(&wb1->list_lock); - spin_lock_nested(&wb2->list_lock, 1); - } else { - spin_lock(&wb2->list_lock); - spin_lock_nested(&wb1->list_lock, 1); - } -} - #ifdef CONFIG_DEBUG_FS #include <linux/debugfs.h> #include <linux/seq_file.h> @@ -269,9 +249,6 @@ static int __init default_bdi_init(void) if (!bdi_wq) return -ENOMEM; - err = bdi_init(&default_backing_dev_info); - if (!err) - bdi_register(&default_backing_dev_info, NULL, "default"); err = bdi_init(&noop_backing_dev_info); return err; @@ -360,19 +337,19 @@ EXPORT_SYMBOL(bdi_register_dev); */ static void bdi_wb_shutdown(struct backing_dev_info *bdi) { - if (!bdi_cap_writeback_dirty(bdi)) + /* Make sure nobody queues further work */ + spin_lock_bh(&bdi->wb_lock); + if (!test_and_clear_bit(BDI_registered, &bdi->state)) { + spin_unlock_bh(&bdi->wb_lock); return; + } + spin_unlock_bh(&bdi->wb_lock); /* * Make sure nobody finds us on the bdi_list anymore */ bdi_remove_from_list(bdi); - /* Make sure nobody queues further work */ - spin_lock_bh(&bdi->wb_lock); - clear_bit(BDI_registered, &bdi->state); - spin_unlock_bh(&bdi->wb_lock); - /* * Drain work list and shutdown the delayed_work. At this point, * @bdi->bdi_list is empty telling bdi_Writeback_workfn() that @bdi @@ -380,37 +357,22 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) */ mod_delayed_work(bdi_wq, &bdi->wb.dwork, 0); flush_delayed_work(&bdi->wb.dwork); - WARN_ON(!list_empty(&bdi->work_list)); - WARN_ON(delayed_work_pending(&bdi->wb.dwork)); } /* - * This bdi is going away now, make sure that no super_blocks point to it + * Called when the device behind @bdi has been removed or ejected. + * + * We can't really do much here except for reducing the dirty ratio at + * the moment. In the future we should be able to set a flag so that + * the filesystem can handle errors at mark_inode_dirty time instead + * of only at writeback time. */ -static void bdi_prune_sb(struct backing_dev_info *bdi) -{ - struct super_block *sb; - - spin_lock(&sb_lock); - list_for_each_entry(sb, &super_blocks, s_list) { - if (sb->s_bdi == bdi) - sb->s_bdi = &default_backing_dev_info; - } - spin_unlock(&sb_lock); -} - void bdi_unregister(struct backing_dev_info *bdi) { - if (bdi->dev) { - bdi_set_min_ratio(bdi, 0); - trace_writeback_bdi_unregister(bdi); - bdi_prune_sb(bdi); + if (WARN_ON_ONCE(!bdi->dev)) + return; - bdi_wb_shutdown(bdi); - bdi_debug_unregister(bdi); - device_unregister(bdi->dev); - bdi->dev = NULL; - } + bdi_set_min_ratio(bdi, 0); } EXPORT_SYMBOL(bdi_unregister); @@ -480,37 +442,19 @@ void bdi_destroy(struct backing_dev_info *bdi) { int i; - /* - * Splice our entries to the default_backing_dev_info. This - * condition shouldn't happen. @wb must be empty at this point and - * dirty inodes on it might cause other issues. This workaround is - * added by ce5f8e779519 ("writeback: splice dirty inode entries to - * default bdi on bdi_destroy()") without root-causing the issue. - * - * http://lkml.kernel.org/g/1253038617-30204-11-git-send-email-jens.axboe@oracle.com - * http://thread.gmane.org/gmane.linux.file-systems/35341/focus=35350 - * - * We should probably add WARN_ON() to find out whether it still - * happens and track it down if so. - */ - if (bdi_has_dirty_io(bdi)) { - struct bdi_writeback *dst = &default_backing_dev_info.wb; - - bdi_lock_two(&bdi->wb, dst); - list_splice(&bdi->wb.b_dirty, &dst->b_dirty); - list_splice(&bdi->wb.b_io, &dst->b_io); - list_splice(&bdi->wb.b_more_io, &dst->b_more_io); - spin_unlock(&bdi->wb.list_lock); - spin_unlock(&dst->list_lock); - } - - bdi_unregister(bdi); + bdi_wb_shutdown(bdi); + WARN_ON(!list_empty(&bdi->work_list)); WARN_ON(delayed_work_pending(&bdi->wb.dwork)); + if (bdi->dev) { + bdi_debug_unregister(bdi); + device_unregister(bdi->dev); + bdi->dev = NULL; + } + for (i = 0; i < NR_BDI_STAT_ITEMS; i++) percpu_counter_destroy(&bdi->bdi_stat[i]); - fprop_local_destroy_percpu(&bdi->completions); } EXPORT_SYMBOL(bdi_destroy); @@ -519,13 +463,12 @@ EXPORT_SYMBOL(bdi_destroy); * For use from filesystems to quickly init and register a bdi associated * with dirty writeback */ -int bdi_setup_and_register(struct backing_dev_info *bdi, char *name, - unsigned int cap) +int bdi_setup_and_register(struct backing_dev_info *bdi, char *name) { int err; bdi->name = name; - bdi->capabilities = cap; + bdi->capabilities = 0; err = bdi_init(bdi); if (err) return err; diff --git a/mm/cleancache.c b/mm/cleancache.c index d0eac4350403..053bcd8f12fb 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -25,7 +25,7 @@ static struct cleancache_ops *cleancache_ops __read_mostly; /* - * Counters available via /sys/kernel/debug/frontswap (if debugfs is + * Counters available via /sys/kernel/debug/cleancache (if debugfs is * properly configured. These are for information only so are not protected * against increment races. */ @@ -199,6 +199,7 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, cma->order_per_bit = order_per_bit; *res_cma = cma; cma_area_count++; + totalcma_pages += (size / PAGE_SIZE); return 0; } @@ -337,7 +338,6 @@ int __init cma_declare_contiguous(phys_addr_t base, if (ret) goto err; - totalcma_pages += (size / PAGE_SIZE); pr_info("Reserved %ld MiB at %pa\n", (unsigned long)size / SZ_1M, &base); return 0; diff --git a/mm/compaction.c b/mm/compaction.c index 546e571e9d60..8c0d9459b54a 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -16,6 +16,7 @@ #include <linux/sysfs.h> #include <linux/balloon_compaction.h> #include <linux/page-isolation.h> +#include <linux/kasan.h> #include "internal.h" #ifdef CONFIG_COMPACTION @@ -34,6 +35,17 @@ static inline void count_compact_events(enum vm_event_item item, long delta) #endif #if defined CONFIG_COMPACTION || defined CONFIG_CMA +#ifdef CONFIG_TRACEPOINTS +static const char *const compaction_status_string[] = { + "deferred", + "skipped", + "continue", + "partial", + "complete", + "no_suitable_page", + "not_suitable_zone", +}; +#endif #define CREATE_TRACE_POINTS #include <trace/events/compaction.h> @@ -61,6 +73,7 @@ static void map_pages(struct list_head *list) list_for_each_entry(page, list, lru) { arch_alloc_page(page, 0); kernel_map_pages(page, 1, 1); + kasan_alloc_pages(page, 0); } } @@ -113,6 +126,77 @@ static struct page *pageblock_pfn_to_page(unsigned long start_pfn, } #ifdef CONFIG_COMPACTION + +/* Do not skip compaction more than 64 times */ +#define COMPACT_MAX_DEFER_SHIFT 6 + +/* + * Compaction is deferred when compaction fails to result in a page + * allocation success. 1 << compact_defer_limit compactions are skipped up + * to a limit of 1 << COMPACT_MAX_DEFER_SHIFT + */ +void defer_compaction(struct zone *zone, int order) +{ + zone->compact_considered = 0; + zone->compact_defer_shift++; + + if (order < zone->compact_order_failed) + zone->compact_order_failed = order; + + if (zone->compact_defer_shift > COMPACT_MAX_DEFER_SHIFT) + zone->compact_defer_shift = COMPACT_MAX_DEFER_SHIFT; + + trace_mm_compaction_defer_compaction(zone, order); +} + +/* Returns true if compaction should be skipped this time */ +bool compaction_deferred(struct zone *zone, int order) +{ + unsigned long defer_limit = 1UL << zone->compact_defer_shift; + + if (order < zone->compact_order_failed) + return false; + + /* Avoid possible overflow */ + if (++zone->compact_considered > defer_limit) + zone->compact_considered = defer_limit; + + if (zone->compact_considered >= defer_limit) + return false; + + trace_mm_compaction_deferred(zone, order); + + return true; +} + +/* + * Update defer tracking counters after successful compaction of given order, + * which means an allocation either succeeded (alloc_success == true) or is + * expected to succeed. + */ +void compaction_defer_reset(struct zone *zone, int order, + bool alloc_success) +{ + if (alloc_success) { + zone->compact_considered = 0; + zone->compact_defer_shift = 0; + } + if (order >= zone->compact_order_failed) + zone->compact_order_failed = order + 1; + + trace_mm_compaction_defer_reset(zone, order); +} + +/* Returns true if restarting compaction after many failures */ +bool compaction_restarting(struct zone *zone, int order) +{ + if (order < zone->compact_order_failed) + return false; + + return zone->compact_defer_shift == COMPACT_MAX_DEFER_SHIFT && + zone->compact_considered >= 1UL << zone->compact_defer_shift; +} + /* Returns true if the pageblock should be scanned for pages to isolate. */ static inline bool isolation_suitable(struct compact_control *cc, struct page *page) @@ -408,6 +492,13 @@ static unsigned long isolate_freepages_block(struct compact_control *cc, /* If a page was split, advance to the end of it */ if (isolated) { + cc->nr_freepages += isolated; + if (!strict && + cc->nr_migratepages <= cc->nr_freepages) { + blockpfn += isolated; + break; + } + blockpfn += isolated - 1; cursor += isolated - 1; continue; @@ -421,11 +512,12 @@ isolate_fail: } + trace_mm_compaction_isolate_freepages(*start_pfn, blockpfn, + nr_scanned, total_isolated); + /* Record how far we have got within the block */ *start_pfn = blockpfn; - trace_mm_compaction_isolate_freepages(nr_scanned, total_isolated); - /* * If strict isolation is requested by CMA then check that all the * pages requested were isolated. If there were any failures, 0 is @@ -581,6 +673,7 @@ isolate_migratepages_block(struct compact_control *cc, unsigned long low_pfn, unsigned long flags = 0; bool locked = false; struct page *page = NULL, *valid_page = NULL; + unsigned long start_pfn = low_pfn; /* * Ensure that there are not too many pages isolated from the LRU @@ -741,7 +834,8 @@ isolate_success: if (low_pfn == end_pfn) update_pageblock_skip(cc, valid_page, nr_isolated, true); - trace_mm_compaction_isolate_migratepages(nr_scanned, nr_isolated); + trace_mm_compaction_isolate_migratepages(start_pfn, low_pfn, + nr_scanned, nr_isolated); count_compact_events(COMPACTMIGRATE_SCANNED, nr_scanned); if (nr_isolated) @@ -814,7 +908,6 @@ static void isolate_freepages(struct compact_control *cc) unsigned long isolate_start_pfn; /* exact pfn we start at */ unsigned long block_end_pfn; /* end of current pageblock */ unsigned long low_pfn; /* lowest pfn scanner is able to scan */ - int nr_freepages = cc->nr_freepages; struct list_head *freelist = &cc->freepages; /* @@ -839,11 +932,11 @@ static void isolate_freepages(struct compact_control *cc) * pages on cc->migratepages. We stop searching if the migrate * and free page scanners meet or enough free pages are isolated. */ - for (; block_start_pfn >= low_pfn && cc->nr_migratepages > nr_freepages; + for (; block_start_pfn >= low_pfn && + cc->nr_migratepages > cc->nr_freepages; block_end_pfn = block_start_pfn, block_start_pfn -= pageblock_nr_pages, isolate_start_pfn = block_start_pfn) { - unsigned long isolated; /* * This can iterate a massively long zone without finding any @@ -868,9 +961,8 @@ static void isolate_freepages(struct compact_control *cc) continue; /* Found a block suitable for isolating free pages from. */ - isolated = isolate_freepages_block(cc, &isolate_start_pfn, + isolate_freepages_block(cc, &isolate_start_pfn, block_end_pfn, freelist, false); - nr_freepages += isolated; /* * Remember where the free scanner should restart next time, @@ -902,8 +994,6 @@ static void isolate_freepages(struct compact_control *cc) */ if (block_start_pfn < low_pfn) cc->free_pfn = cc->migrate_pfn; - - cc->nr_freepages = nr_freepages; } /* @@ -1015,8 +1105,10 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, low_pfn = isolate_migratepages_block(cc, low_pfn, end_pfn, isolate_mode); - if (!low_pfn || cc->contended) + if (!low_pfn || cc->contended) { + acct_isolated(zone, cc); return ISOLATE_ABORT; + } /* * Either we isolated something and proceed with migration. Or @@ -1037,7 +1129,7 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, return cc->nr_migratepages ? ISOLATE_SUCCESS : ISOLATE_NONE; } -static int compact_finished(struct zone *zone, struct compact_control *cc, +static int __compact_finished(struct zone *zone, struct compact_control *cc, const int migratetype) { unsigned int order; @@ -1088,11 +1180,24 @@ static int compact_finished(struct zone *zone, struct compact_control *cc, return COMPACT_PARTIAL; /* Job done if allocation would set block type */ - if (cc->order >= pageblock_order && area->nr_free) + if (order >= pageblock_order && area->nr_free) return COMPACT_PARTIAL; } - return COMPACT_CONTINUE; + return COMPACT_NO_SUITABLE_PAGE; +} + +static int compact_finished(struct zone *zone, struct compact_control *cc, + const int migratetype) +{ + int ret; + + ret = __compact_finished(zone, cc, migratetype); + trace_mm_compaction_finished(zone, cc->order, ret); + if (ret == COMPACT_NO_SUITABLE_PAGE) + ret = COMPACT_CONTINUE; + + return ret; } /* @@ -1102,7 +1207,7 @@ static int compact_finished(struct zone *zone, struct compact_control *cc, * COMPACT_PARTIAL - If the allocation would succeed without compaction * COMPACT_CONTINUE - If compaction should run now */ -unsigned long compaction_suitable(struct zone *zone, int order, +static unsigned long __compaction_suitable(struct zone *zone, int order, int alloc_flags, int classzone_idx) { int fragindex; @@ -1146,11 +1251,24 @@ unsigned long compaction_suitable(struct zone *zone, int order, */ fragindex = fragmentation_index(zone, order); if (fragindex >= 0 && fragindex <= sysctl_extfrag_threshold) - return COMPACT_SKIPPED; + return COMPACT_NOT_SUITABLE_ZONE; return COMPACT_CONTINUE; } +unsigned long compaction_suitable(struct zone *zone, int order, + int alloc_flags, int classzone_idx) +{ + unsigned long ret; + + ret = __compaction_suitable(zone, order, alloc_flags, classzone_idx); + trace_mm_compaction_suitable(zone, order, ret); + if (ret == COMPACT_NOT_SUITABLE_ZONE) + ret = COMPACT_SKIPPED; + + return ret; +} + static int compact_zone(struct zone *zone, struct compact_control *cc) { int ret; @@ -1197,7 +1315,8 @@ static int compact_zone(struct zone *zone, struct compact_control *cc) zone->compact_cached_migrate_pfn[1] = cc->migrate_pfn; } - trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, cc->free_pfn, end_pfn); + trace_mm_compaction_begin(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync); migrate_prep_local(); @@ -1299,7 +1418,8 @@ out: zone->compact_cached_free_pfn = free_pfn; } - trace_mm_compaction_end(ret); + trace_mm_compaction_end(start_pfn, cc->migrate_pfn, + cc->free_pfn, end_pfn, sync, ret); return ret; } @@ -1335,22 +1455,20 @@ int sysctl_extfrag_threshold = 500; /** * try_to_compact_pages - Direct compact to satisfy a high-order allocation - * @zonelist: The zonelist used for the current allocation - * @order: The order of the current allocation * @gfp_mask: The GFP mask of the current allocation - * @nodemask: The allowed nodes to allocate from + * @order: The order of the current allocation + * @alloc_flags: The allocation flags of the current allocation + * @ac: The context of current allocation * @mode: The migration mode for async, sync light, or sync migration * @contended: Return value that determines if compaction was aborted due to * need_resched() or lock contention * * This is the main entry point for direct page compaction. */ -unsigned long try_to_compact_pages(struct zonelist *zonelist, - int order, gfp_t gfp_mask, nodemask_t *nodemask, - enum migrate_mode mode, int *contended, - int alloc_flags, int classzone_idx) +unsigned long try_to_compact_pages(gfp_t gfp_mask, unsigned int order, + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended) { - enum zone_type high_zoneidx = gfp_zone(gfp_mask); int may_enter_fs = gfp_mask & __GFP_FS; int may_perform_io = gfp_mask & __GFP_IO; struct zoneref *z; @@ -1364,9 +1482,11 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, if (!order || !may_enter_fs || !may_perform_io) return COMPACT_SKIPPED; + trace_mm_compaction_try_to_compact_pages(order, gfp_mask, mode); + /* Compact each zone in the list */ - for_each_zone_zonelist_nodemask(zone, z, zonelist, high_zoneidx, - nodemask) { + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, ac->high_zoneidx, + ac->nodemask) { int status; int zone_contended; @@ -1374,7 +1494,8 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, continue; status = compact_zone_order(zone, order, gfp_mask, mode, - &zone_contended, alloc_flags, classzone_idx); + &zone_contended, alloc_flags, + ac->classzone_idx); rc = max(status, rc); /* * It takes at least one zone that wasn't lock contended @@ -1384,7 +1505,7 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* If a normal allocation would succeed, stop compacting */ if (zone_watermark_ok(zone, order, low_wmark_pages(zone), - classzone_idx, alloc_flags)) { + ac->classzone_idx, alloc_flags)) { /* * We think the allocation will succeed in this zone, * but it is not certain, hence the false. The caller diff --git a/mm/debug.c b/mm/debug.c index 0e58f3211f89..3eb3ac2fcee7 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -130,7 +130,6 @@ static const struct trace_print_flags vmaflags_names[] = { {VM_ACCOUNT, "account" }, {VM_NORESERVE, "noreserve" }, {VM_HUGETLB, "hugetlb" }, - {VM_NONLINEAR, "nonlinear" }, #if defined(CONFIG_X86) {VM_PAT, "pat" }, #elif defined(CONFIG_PPC) @@ -174,7 +173,7 @@ void dump_mm(const struct mm_struct *mm) "get_unmapped_area %p\n" #endif "mmap_base %lu mmap_legacy_base %lu highest_vm_end %lu\n" - "pgd %p mm_users %d mm_count %d nr_ptes %lu map_count %d\n" + "pgd %p mm_users %d mm_count %d nr_ptes %lu nr_pmds %lu map_count %d\n" "hiwater_rss %lx hiwater_vm %lx total_vm %lx locked_vm %lx\n" "pinned_vm %lx shared_vm %lx exec_vm %lx stack_vm %lx\n" "start_code %lx end_code %lx start_data %lx end_data %lx\n" @@ -207,6 +206,7 @@ void dump_mm(const struct mm_struct *mm) mm->pgd, atomic_read(&mm->mm_users), atomic_read(&mm->mm_count), atomic_long_read((atomic_long_t *)&mm->nr_ptes), + mm_nr_pmds((struct mm_struct *)mm), mm->map_count, mm->hiwater_rss, mm->hiwater_vm, mm->total_vm, mm->locked_vm, mm->pinned_vm, mm->shared_vm, mm->exec_vm, mm->stack_vm, diff --git a/mm/fadvise.c b/mm/fadvise.c index 2ad7adf4f0a4..4a3907cf79f8 100644 --- a/mm/fadvise.c +++ b/mm/fadvise.c @@ -28,6 +28,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) { struct fd f = fdget(fd); + struct inode *inode; struct address_space *mapping; struct backing_dev_info *bdi; loff_t endbyte; /* inclusive */ @@ -39,7 +40,8 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) if (!f.file) return -EBADF; - if (S_ISFIFO(file_inode(f.file)->i_mode)) { + inode = file_inode(f.file); + if (S_ISFIFO(inode->i_mode)) { ret = -ESPIPE; goto out; } @@ -50,7 +52,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) goto out; } - if (mapping->a_ops->get_xip_mem) { + if (IS_DAX(inode)) { switch (advice) { case POSIX_FADV_NORMAL: case POSIX_FADV_RANDOM: @@ -73,7 +75,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) else endbyte--; /* inclusive */ - bdi = mapping->backing_dev_info; + bdi = inode_to_bdi(mapping->host); switch (advice) { case POSIX_FADV_NORMAL: @@ -113,7 +115,7 @@ SYSCALL_DEFINE4(fadvise64_64, int, fd, loff_t, offset, loff_t, len, int, advice) case POSIX_FADV_NOREUSE: break; case POSIX_FADV_DONTNEED: - if (!bdi_write_congested(mapping->backing_dev_info)) + if (!bdi_write_congested(bdi)) __filemap_fdatawrite_range(mapping, offset, endbyte, WB_SYNC_NONE); diff --git a/mm/filemap.c b/mm/filemap.c index 673e4581a2e5..ad7242043bdb 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -211,7 +211,7 @@ void __delete_from_page_cache(struct page *page, void *shadow) */ if (PageDirty(page) && mapping_cap_account_dirty(mapping)) { dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); } } @@ -1695,8 +1695,7 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) loff_t *ppos = &iocb->ki_pos; loff_t pos = *ppos; - /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ - if (file->f_flags & O_DIRECT) { + if (io_is_direct(file)) { struct address_space *mapping = file->f_mapping; struct inode *inode = mapping->host; size_t count = iov_iter_count(iter); @@ -1723,9 +1722,11 @@ generic_file_read_iter(struct kiocb *iocb, struct iov_iter *iter) * we've already read everything we wanted to, or if * there was a short read because we hit EOF, go ahead * and return. Otherwise fallthrough to buffered io for - * the rest of the read. + * the rest of the read. Buffered reads will not work for + * DAX files, so don't bother trying. */ - if (retval < 0 || !iov_iter_count(iter) || *ppos >= size) { + if (retval < 0 || !iov_iter_count(iter) || *ppos >= size || + IS_DAX(inode)) { file_accessed(file); goto out; } @@ -2087,7 +2088,6 @@ const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /* This is used for a general mmap of a disk file */ @@ -2565,7 +2565,7 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) size_t count = iov_iter_count(from); /* We can write back this queue in page reclaim */ - current->backing_dev_info = mapping->backing_dev_info; + current->backing_dev_info = inode_to_bdi(inode); err = generic_write_checks(file, &pos, &count, S_ISBLK(inode->i_mode)); if (err) goto out; @@ -2583,18 +2583,20 @@ ssize_t __generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) if (err) goto out; - /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ - if (unlikely(file->f_flags & O_DIRECT)) { + if (io_is_direct(file)) { loff_t endbyte; written = generic_file_direct_write(iocb, from, pos); - if (written < 0 || written == count) - goto out; - /* - * direct-io write to a hole: fall through to buffered I/O - * for completing the rest of the request. + * If the write stopped short of completing, fall back to + * buffered writes. Some filesystems do this for writes to + * holes, for example. For DAX files, a buffered write will + * not succeed (even if it did, DAX does not handle dirty + * page-cache pages correctly). */ + if (written < 0 || written == count || IS_DAX(inode)) + goto out; + pos += written; count -= written; diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c deleted file mode 100644 index 0d105aeff82f..000000000000 --- a/mm/filemap_xip.c +++ /dev/null @@ -1,478 +0,0 @@ -/* - * linux/mm/filemap_xip.c - * - * Copyright (C) 2005 IBM Corporation - * Author: Carsten Otte <cotte@de.ibm.com> - * - * derived from linux/mm/filemap.c - Copyright (C) Linus Torvalds - * - */ - -#include <linux/fs.h> -#include <linux/pagemap.h> -#include <linux/export.h> -#include <linux/uio.h> -#include <linux/rmap.h> -#include <linux/mmu_notifier.h> -#include <linux/sched.h> -#include <linux/seqlock.h> -#include <linux/mutex.h> -#include <linux/gfp.h> -#include <asm/tlbflush.h> -#include <asm/io.h> - -/* - * We do use our own empty page to avoid interference with other users - * of ZERO_PAGE(), such as /dev/zero - */ -static DEFINE_MUTEX(xip_sparse_mutex); -static seqcount_t xip_sparse_seq = SEQCNT_ZERO(xip_sparse_seq); -static struct page *__xip_sparse_page; - -/* called under xip_sparse_mutex */ -static struct page *xip_sparse_page(void) -{ - if (!__xip_sparse_page) { - struct page *page = alloc_page(GFP_HIGHUSER | __GFP_ZERO); - - if (page) - __xip_sparse_page = page; - } - return __xip_sparse_page; -} - -/* - * This is a file read routine for execute in place files, and uses - * the mapping->a_ops->get_xip_mem() function for the actual low-level - * stuff. - * - * Note the struct file* is not used at all. It may be NULL. - */ -static ssize_t -do_xip_mapping_read(struct address_space *mapping, - struct file_ra_state *_ra, - struct file *filp, - char __user *buf, - size_t len, - loff_t *ppos) -{ - struct inode *inode = mapping->host; - pgoff_t index, end_index; - unsigned long offset; - loff_t isize, pos; - size_t copied = 0, error = 0; - - BUG_ON(!mapping->a_ops->get_xip_mem); - - pos = *ppos; - index = pos >> PAGE_CACHE_SHIFT; - offset = pos & ~PAGE_CACHE_MASK; - - isize = i_size_read(inode); - if (!isize) - goto out; - - end_index = (isize - 1) >> PAGE_CACHE_SHIFT; - do { - unsigned long nr, left; - void *xip_mem; - unsigned long xip_pfn; - int zero = 0; - - /* nr is the maximum number of bytes to copy from this page */ - nr = PAGE_CACHE_SIZE; - if (index >= end_index) { - if (index > end_index) - goto out; - nr = ((isize - 1) & ~PAGE_CACHE_MASK) + 1; - if (nr <= offset) { - goto out; - } - } - nr = nr - offset; - if (nr > len - copied) - nr = len - copied; - - error = mapping->a_ops->get_xip_mem(mapping, index, 0, - &xip_mem, &xip_pfn); - if (unlikely(error)) { - if (error == -ENODATA) { - /* sparse */ - zero = 1; - } else - goto out; - } - - /* If users can be writing to this page using arbitrary - * virtual addresses, take care about potential aliasing - * before reading the page on the kernel side. - */ - if (mapping_writably_mapped(mapping)) - /* address based flush */ ; - - /* - * Ok, we have the mem, so now we can copy it to user space... - * - * The actor routine returns how many bytes were actually used.. - * NOTE! This may not be the same as how much of a user buffer - * we filled up (we may be padding etc), so we can only update - * "pos" here (the actor routine has to update the user buffer - * pointers and the remaining count). - */ - if (!zero) - left = __copy_to_user(buf+copied, xip_mem+offset, nr); - else - left = __clear_user(buf + copied, nr); - - if (left) { - error = -EFAULT; - goto out; - } - - copied += (nr - left); - offset += (nr - left); - index += offset >> PAGE_CACHE_SHIFT; - offset &= ~PAGE_CACHE_MASK; - } while (copied < len); - -out: - *ppos = pos + copied; - if (filp) - file_accessed(filp); - - return (copied ? copied : error); -} - -ssize_t -xip_file_read(struct file *filp, char __user *buf, size_t len, loff_t *ppos) -{ - if (!access_ok(VERIFY_WRITE, buf, len)) - return -EFAULT; - - return do_xip_mapping_read(filp->f_mapping, &filp->f_ra, filp, - buf, len, ppos); -} -EXPORT_SYMBOL_GPL(xip_file_read); - -/* - * __xip_unmap is invoked from xip_unmap and xip_write - * - * This function walks all vmas of the address_space and unmaps the - * __xip_sparse_page when found at pgoff. - */ -static void __xip_unmap(struct address_space * mapping, unsigned long pgoff) -{ - struct vm_area_struct *vma; - struct page *page; - unsigned count; - int locked = 0; - - count = read_seqcount_begin(&xip_sparse_seq); - - page = __xip_sparse_page; - if (!page) - return; - -retry: - i_mmap_lock_read(mapping); - vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { - pte_t *pte, pteval; - spinlock_t *ptl; - struct mm_struct *mm = vma->vm_mm; - unsigned long address = vma->vm_start + - ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - - BUG_ON(address < vma->vm_start || address >= vma->vm_end); - pte = page_check_address(page, mm, address, &ptl, 1); - if (pte) { - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush(vma, address, pte); - page_remove_rmap(page); - dec_mm_counter(mm, MM_FILEPAGES); - BUG_ON(pte_dirty(pteval)); - pte_unmap_unlock(pte, ptl); - /* must invalidate_page _before_ freeing the page */ - mmu_notifier_invalidate_page(mm, address); - page_cache_release(page); - } - } - i_mmap_unlock_read(mapping); - - if (locked) { - mutex_unlock(&xip_sparse_mutex); - } else if (read_seqcount_retry(&xip_sparse_seq, count)) { - mutex_lock(&xip_sparse_mutex); - locked = 1; - goto retry; - } -} - -/* - * xip_fault() is invoked via the vma operations vector for a - * mapped memory region to read in file data during a page fault. - * - * This function is derived from filemap_fault, but used for execute in place - */ -static int xip_file_fault(struct vm_area_struct *vma, struct vm_fault *vmf) -{ - struct file *file = vma->vm_file; - struct address_space *mapping = file->f_mapping; - struct inode *inode = mapping->host; - pgoff_t size; - void *xip_mem; - unsigned long xip_pfn; - struct page *page; - int error; - - /* XXX: are VM_FAULT_ codes OK? */ -again: - size = (i_size_read(inode) + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; - if (vmf->pgoff >= size) - return VM_FAULT_SIGBUS; - - error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0, - &xip_mem, &xip_pfn); - if (likely(!error)) - goto found; - if (error != -ENODATA) - return VM_FAULT_OOM; - - /* sparse block */ - if ((vma->vm_flags & (VM_WRITE | VM_MAYWRITE)) && - (vma->vm_flags & (VM_SHARED | VM_MAYSHARE)) && - (!(mapping->host->i_sb->s_flags & MS_RDONLY))) { - int err; - - /* maybe shared writable, allocate new block */ - mutex_lock(&xip_sparse_mutex); - error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 1, - &xip_mem, &xip_pfn); - mutex_unlock(&xip_sparse_mutex); - if (error) - return VM_FAULT_SIGBUS; - /* unmap sparse mappings at pgoff from all other vmas */ - __xip_unmap(mapping, vmf->pgoff); - -found: - err = vm_insert_mixed(vma, (unsigned long)vmf->virtual_address, - xip_pfn); - if (err == -ENOMEM) - return VM_FAULT_OOM; - /* - * err == -EBUSY is fine, we've raced against another thread - * that faulted-in the same page - */ - if (err != -EBUSY) - BUG_ON(err); - return VM_FAULT_NOPAGE; - } else { - int err, ret = VM_FAULT_OOM; - - mutex_lock(&xip_sparse_mutex); - write_seqcount_begin(&xip_sparse_seq); - error = mapping->a_ops->get_xip_mem(mapping, vmf->pgoff, 0, - &xip_mem, &xip_pfn); - if (unlikely(!error)) { - write_seqcount_end(&xip_sparse_seq); - mutex_unlock(&xip_sparse_mutex); - goto again; - } - if (error != -ENODATA) - goto out; - /* not shared and writable, use xip_sparse_page() */ - page = xip_sparse_page(); - if (!page) - goto out; - err = vm_insert_page(vma, (unsigned long)vmf->virtual_address, - page); - if (err == -ENOMEM) - goto out; - - ret = VM_FAULT_NOPAGE; -out: - write_seqcount_end(&xip_sparse_seq); - mutex_unlock(&xip_sparse_mutex); - - return ret; - } -} - -static const struct vm_operations_struct xip_file_vm_ops = { - .fault = xip_file_fault, - .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, -}; - -int xip_file_mmap(struct file * file, struct vm_area_struct * vma) -{ - BUG_ON(!file->f_mapping->a_ops->get_xip_mem); - - file_accessed(file); - vma->vm_ops = &xip_file_vm_ops; - vma->vm_flags |= VM_MIXEDMAP; - return 0; -} -EXPORT_SYMBOL_GPL(xip_file_mmap); - -static ssize_t -__xip_file_write(struct file *filp, const char __user *buf, - size_t count, loff_t pos, loff_t *ppos) -{ - struct address_space * mapping = filp->f_mapping; - const struct address_space_operations *a_ops = mapping->a_ops; - struct inode *inode = mapping->host; - long status = 0; - size_t bytes; - ssize_t written = 0; - - BUG_ON(!mapping->a_ops->get_xip_mem); - - do { - unsigned long index; - unsigned long offset; - size_t copied; - void *xip_mem; - unsigned long xip_pfn; - - offset = (pos & (PAGE_CACHE_SIZE -1)); /* Within page */ - index = pos >> PAGE_CACHE_SHIFT; - bytes = PAGE_CACHE_SIZE - offset; - if (bytes > count) - bytes = count; - - status = a_ops->get_xip_mem(mapping, index, 0, - &xip_mem, &xip_pfn); - if (status == -ENODATA) { - /* we allocate a new page unmap it */ - mutex_lock(&xip_sparse_mutex); - status = a_ops->get_xip_mem(mapping, index, 1, - &xip_mem, &xip_pfn); - mutex_unlock(&xip_sparse_mutex); - if (!status) - /* unmap page at pgoff from all other vmas */ - __xip_unmap(mapping, index); - } - - if (status) - break; - - copied = bytes - - __copy_from_user_nocache(xip_mem + offset, buf, bytes); - - if (likely(copied > 0)) { - status = copied; - - if (status >= 0) { - written += status; - count -= status; - pos += status; - buf += status; - } - } - if (unlikely(copied != bytes)) - if (status >= 0) - status = -EFAULT; - if (status < 0) - break; - } while (count); - *ppos = pos; - /* - * No need to use i_size_read() here, the i_size - * cannot change under us because we hold i_mutex. - */ - if (pos > inode->i_size) { - i_size_write(inode, pos); - mark_inode_dirty(inode); - } - - return written ? written : status; -} - -ssize_t -xip_file_write(struct file *filp, const char __user *buf, size_t len, - loff_t *ppos) -{ - struct address_space *mapping = filp->f_mapping; - struct inode *inode = mapping->host; - size_t count; - loff_t pos; - ssize_t ret; - - mutex_lock(&inode->i_mutex); - - if (!access_ok(VERIFY_READ, buf, len)) { - ret=-EFAULT; - goto out_up; - } - - pos = *ppos; - count = len; - - /* We can write back this queue in page reclaim */ - current->backing_dev_info = mapping->backing_dev_info; - - ret = generic_write_checks(filp, &pos, &count, S_ISBLK(inode->i_mode)); - if (ret) - goto out_backing; - if (count == 0) - goto out_backing; - - ret = file_remove_suid(filp); - if (ret) - goto out_backing; - - ret = file_update_time(filp); - if (ret) - goto out_backing; - - ret = __xip_file_write (filp, buf, count, pos, ppos); - - out_backing: - current->backing_dev_info = NULL; - out_up: - mutex_unlock(&inode->i_mutex); - return ret; -} -EXPORT_SYMBOL_GPL(xip_file_write); - -/* - * truncate a page used for execute in place - * functionality is analog to block_truncate_page but does use get_xip_mem - * to get the page instead of page cache - */ -int -xip_truncate_page(struct address_space *mapping, loff_t from) -{ - pgoff_t index = from >> PAGE_CACHE_SHIFT; - unsigned offset = from & (PAGE_CACHE_SIZE-1); - unsigned blocksize; - unsigned length; - void *xip_mem; - unsigned long xip_pfn; - int err; - - BUG_ON(!mapping->a_ops->get_xip_mem); - - blocksize = 1 << mapping->host->i_blkbits; - length = offset & (blocksize - 1); - - /* Block boundary? Nothing to do */ - if (!length) - return 0; - - length = blocksize - length; - - err = mapping->a_ops->get_xip_mem(mapping, index, 0, - &xip_mem, &xip_pfn); - if (unlikely(err)) { - if (err == -ENODATA) - /* Hole? No need to truncate */ - return 0; - else - return err; - } - memset(xip_mem + offset, 0, length); - return 0; -} -EXPORT_SYMBOL_GPL(xip_truncate_page); diff --git a/mm/fremap.c b/mm/fremap.c deleted file mode 100644 index 2805d71cf476..000000000000 --- a/mm/fremap.c +++ /dev/null @@ -1,283 +0,0 @@ -/* - * linux/mm/fremap.c - * - * Explicit pagetable population and nonlinear (random) mappings support. - * - * started by Ingo Molnar, Copyright (C) 2002, 2003 - */ -#include <linux/export.h> -#include <linux/backing-dev.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/file.h> -#include <linux/mman.h> -#include <linux/pagemap.h> -#include <linux/swapops.h> -#include <linux/rmap.h> -#include <linux/syscalls.h> -#include <linux/mmu_notifier.h> - -#include <asm/mmu_context.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> - -#include "internal.h" - -static int mm_counter(struct page *page) -{ - return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; -} - -static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - pte_t pte = *ptep; - struct page *page; - swp_entry_t entry; - - if (pte_present(pte)) { - flush_cache_page(vma, addr, pte_pfn(pte)); - pte = ptep_clear_flush_notify(vma, addr, ptep); - page = vm_normal_page(vma, addr, pte); - if (page) { - if (pte_dirty(pte)) - set_page_dirty(page); - update_hiwater_rss(mm); - dec_mm_counter(mm, mm_counter(page)); - page_remove_rmap(page); - page_cache_release(page); - } - } else { /* zap_pte() is not called when pte_none() */ - if (!pte_file(pte)) { - update_hiwater_rss(mm); - entry = pte_to_swp_entry(pte); - if (non_swap_entry(entry)) { - if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - dec_mm_counter(mm, mm_counter(page)); - } - } else { - free_swap_and_cache(entry); - dec_mm_counter(mm, MM_SWAPENTS); - } - } - pte_clear_not_present_full(mm, addr, ptep, 0); - } -} - -/* - * Install a file pte to a given virtual memory address, release any - * previously existing mapping. - */ -static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, unsigned long pgoff, pgprot_t prot) -{ - int err = -ENOMEM; - pte_t *pte, ptfile; - spinlock_t *ptl; - - pte = get_locked_pte(mm, addr, &ptl); - if (!pte) - goto out; - - ptfile = pgoff_to_pte(pgoff); - - if (!pte_none(*pte)) - zap_pte(mm, vma, addr, pte); - - set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile)); - /* - * We don't need to run update_mmu_cache() here because the "file pte" - * being installed by install_file_pte() is not a real pte - it's a - * non-present entry (like a swap entry), noting what file offset should - * be mapped there when there's a fault (in a non-linear vma where - * that's not obvious). - */ - pte_unmap_unlock(pte, ptl); - err = 0; -out: - return err; -} - -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - struct mm_struct *mm = vma->vm_mm; - int err; - - do { - err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot); - if (err) - return err; - - size -= PAGE_SIZE; - addr += PAGE_SIZE; - pgoff++; - } while (size); - - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - -/** - * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma - * @start: start of the remapped virtual memory range - * @size: size of the remapped virtual memory range - * @prot: new protection bits of the range (see NOTE) - * @pgoff: to-be-mapped page of the backing store file - * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO. - * - * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma - * (shared backing store file). - * - * This syscall works purely via pagetables, so it's the most efficient - * way to map the same (large) file into a given virtual window. Unlike - * mmap()/mremap() it does not create any new vmas. The new mappings are - * also safe across swapout. - * - * NOTE: the @prot parameter right now is ignored (but must be zero), - * and the vma's default protection is used. Arbitrary protections - * might be implemented in the future. - */ -SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, - unsigned long, prot, unsigned long, pgoff, unsigned long, flags) -{ - struct mm_struct *mm = current->mm; - struct address_space *mapping; - struct vm_area_struct *vma; - int err = -EINVAL; - int has_write_lock = 0; - vm_flags_t vm_flags = 0; - - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " - "See Documentation/vm/remap_file_pages.txt.\n", - current->comm, current->pid); - - if (prot) - return err; - /* - * Sanitize the syscall parameters: - */ - start = start & PAGE_MASK; - size = size & PAGE_MASK; - - /* Does the address range wrap, or is the span zero-sized? */ - if (start + size <= start) - return err; - - /* Does pgoff wrap? */ - if (pgoff + (size >> PAGE_SHIFT) < pgoff) - return err; - - /* Can we represent this offset inside this architecture's pte's? */ -#if PTE_FILE_MAX_BITS < BITS_PER_LONG - if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS)) - return err; -#endif - - /* We need down_write() to change vma->vm_flags. */ - down_read(&mm->mmap_sem); - retry: - vma = find_vma(mm, start); - - /* - * Make sure the vma is shared, that it supports prefaulting, - * and that the remapped range is valid and fully within - * the single existing vma. - */ - if (!vma || !(vma->vm_flags & VM_SHARED)) - goto out; - - if (!vma->vm_ops || !vma->vm_ops->remap_pages) - goto out; - - if (start < vma->vm_start || start + size > vma->vm_end) - goto out; - - /* Must set VM_NONLINEAR before any pages are populated. */ - if (!(vma->vm_flags & VM_NONLINEAR)) { - /* - * vm_private_data is used as a swapout cursor - * in a VM_NONLINEAR vma. - */ - if (vma->vm_private_data) - goto out; - - /* Don't need a nonlinear mapping, exit success */ - if (pgoff == linear_page_index(vma, start)) { - err = 0; - goto out; - } - - if (!has_write_lock) { -get_write_lock: - up_read(&mm->mmap_sem); - down_write(&mm->mmap_sem); - has_write_lock = 1; - goto retry; - } - mapping = vma->vm_file->f_mapping; - /* - * page_mkclean doesn't work on nonlinear vmas, so if - * dirty pages need to be accounted, emulate with linear - * vmas. - */ - if (mapping_cap_account_dirty(mapping)) { - unsigned long addr; - struct file *file = get_file(vma->vm_file); - /* mmap_region may free vma; grab the info now */ - vm_flags = vma->vm_flags; - - addr = mmap_region(file, start, size, vm_flags, pgoff); - fput(file); - if (IS_ERR_VALUE(addr)) { - err = addr; - } else { - BUG_ON(addr != start); - err = 0; - } - goto out_freed; - } - i_mmap_lock_write(mapping); - flush_dcache_mmap_lock(mapping); - vma->vm_flags |= VM_NONLINEAR; - vma_interval_tree_remove(vma, &mapping->i_mmap); - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - flush_dcache_mmap_unlock(mapping); - i_mmap_unlock_write(mapping); - } - - if (vma->vm_flags & VM_LOCKED) { - /* - * drop PG_Mlocked flag for over-mapped range - */ - if (!has_write_lock) - goto get_write_lock; - vm_flags = vma->vm_flags; - munlock_vma_pages_range(vma, start, start + size); - vma->vm_flags = vm_flags; - } - - mmu_notifier_invalidate_range_start(mm, start, start + size); - err = vma->vm_ops->remap_pages(vma, start, size, pgoff); - mmu_notifier_invalidate_range_end(mm, start, start + size); - - /* - * We can't clear VM_NONLINEAR because we'd have to do - * it after ->populate completes, and that would prevent - * downgrading the lock. (Locks can't be upgraded). - */ - -out: - if (vma) - vm_flags = vma->vm_flags; -out_freed: - if (likely(!has_write_lock)) - up_read(&mm->mmap_sem); - else - up_write(&mm->mmap_sem); - if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK))) - mm_populate(start, size); - - return err; -} @@ -55,7 +55,7 @@ retry: */ if (likely(!(flags & FOLL_MIGRATION))) goto no_page; - if (pte_none(pte) || pte_file(pte)) + if (pte_none(pte)) goto no_page; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) @@ -64,7 +64,7 @@ retry: migration_entry_wait(mm, pmd, address); goto retry; } - if ((flags & FOLL_NUMA) && pte_numa(pte)) + if ((flags & FOLL_NUMA) && pte_protnone(pte)) goto no_page; if ((flags & FOLL_WRITE) && !pte_write(pte)) { pte_unmap_unlock(ptep, ptl); @@ -167,10 +167,10 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pud_none(*pud)) return no_page_table(vma, flags); if (pud_huge(*pud) && vma->vm_flags & VM_HUGETLB) { - if (flags & FOLL_GET) - return NULL; - page = follow_huge_pud(mm, address, pud, flags & FOLL_WRITE); - return page; + page = follow_huge_pud(mm, address, pud, flags); + if (page) + return page; + return no_page_table(vma, flags); } if (unlikely(pud_bad(*pud))) return no_page_table(vma, flags); @@ -179,21 +179,12 @@ struct page *follow_page_mask(struct vm_area_struct *vma, if (pmd_none(*pmd)) return no_page_table(vma, flags); if (pmd_huge(*pmd) && vma->vm_flags & VM_HUGETLB) { - page = follow_huge_pmd(mm, address, pmd, flags & FOLL_WRITE); - if (flags & FOLL_GET) { - /* - * Refcount on tail pages are not well-defined and - * shouldn't be taken. The caller should handle a NULL - * return when trying to follow tail pages. - */ - if (PageHead(page)) - get_page(page); - else - page = NULL; - } - return page; + page = follow_huge_pmd(mm, address, pmd, flags); + if (page) + return page; + return no_page_table(vma, flags); } - if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) return no_page_table(vma, flags); if (pmd_trans_huge(*pmd)) { if (flags & FOLL_SPLIT) { @@ -584,6 +575,185 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return 0; } +static __always_inline long __get_user_pages_locked(struct task_struct *tsk, + struct mm_struct *mm, + unsigned long start, + unsigned long nr_pages, + int write, int force, + struct page **pages, + struct vm_area_struct **vmas, + int *locked, bool notify_drop, + unsigned int flags) +{ + long ret, pages_done; + bool lock_dropped; + + if (locked) { + /* if VM_FAULT_RETRY can be returned, vmas become invalid */ + BUG_ON(vmas); + /* check caller initialized locked */ + BUG_ON(*locked != 1); + } + + if (pages) + flags |= FOLL_GET; + if (write) + flags |= FOLL_WRITE; + if (force) + flags |= FOLL_FORCE; + + pages_done = 0; + lock_dropped = false; + for (;;) { + ret = __get_user_pages(tsk, mm, start, nr_pages, flags, pages, + vmas, locked); + if (!locked) + /* VM_FAULT_RETRY couldn't trigger, bypass */ + return ret; + + /* VM_FAULT_RETRY cannot return errors */ + if (!*locked) { + BUG_ON(ret < 0); + BUG_ON(ret >= nr_pages); + } + + if (!pages) + /* If it's a prefault don't insist harder */ + return ret; + + if (ret > 0) { + nr_pages -= ret; + pages_done += ret; + if (!nr_pages) + break; + } + if (*locked) { + /* VM_FAULT_RETRY didn't trigger */ + if (!pages_done) + pages_done = ret; + break; + } + /* VM_FAULT_RETRY triggered, so seek to the faulting offset */ + pages += ret; + start += ret << PAGE_SHIFT; + + /* + * Repeat on the address that fired VM_FAULT_RETRY + * without FAULT_FLAG_ALLOW_RETRY but with + * FAULT_FLAG_TRIED. + */ + *locked = 1; + lock_dropped = true; + down_read(&mm->mmap_sem); + ret = __get_user_pages(tsk, mm, start, 1, flags | FOLL_TRIED, + pages, NULL, NULL); + if (ret != 1) { + BUG_ON(ret > 1); + if (!pages_done) + pages_done = ret; + break; + } + nr_pages--; + pages_done++; + if (!nr_pages) + break; + pages++; + start += PAGE_SIZE; + } + if (notify_drop && lock_dropped && *locked) { + /* + * We must let the caller know we temporarily dropped the lock + * and so the critical section protected by it was lost. + */ + up_read(&mm->mmap_sem); + *locked = 0; + } + return pages_done; +} + +/* + * We can leverage the VM_FAULT_RETRY functionality in the page fault + * paths better by using either get_user_pages_locked() or + * get_user_pages_unlocked(). + * + * get_user_pages_locked() is suitable to replace the form: + * + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); + * + * to: + * + * int locked = 1; + * down_read(&mm->mmap_sem); + * do_something() + * get_user_pages_locked(tsk, mm, ..., pages, &locked); + * if (locked) + * up_read(&mm->mmap_sem); + */ +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked) +{ + return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, locked, true, FOLL_TOUCH); +} +EXPORT_SYMBOL(get_user_pages_locked); + +/* + * Same as get_user_pages_unlocked(...., FOLL_TOUCH) but it allows to + * pass additional gup_flags as last parameter (like FOLL_HWPOISON). + * + * NOTE: here FOLL_TOUCH is not set implicitly and must be set by the + * caller if required (just like with __get_user_pages). "FOLL_GET", + * "FOLL_WRITE" and "FOLL_FORCE" are set implicitly as needed + * according to the parameters "pages", "write", "force" + * respectively. + */ +__always_inline long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags) +{ + long ret; + int locked = 1; + down_read(&mm->mmap_sem); + ret = __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, NULL, &locked, false, gup_flags); + if (locked) + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(__get_user_pages_unlocked); + +/* + * get_user_pages_unlocked() is suitable to replace the form: + * + * down_read(&mm->mmap_sem); + * get_user_pages(tsk, mm, ..., pages, NULL); + * up_read(&mm->mmap_sem); + * + * with: + * + * get_user_pages_unlocked(tsk, mm, ..., pages); + * + * It is functionally equivalent to get_user_pages_fast so + * get_user_pages_fast should be used instead, if the two parameters + * "tsk" and "mm" are respectively equal to current and current->mm, + * or if "force" shall be set to 1 (get_user_pages_fast misses the + * "force" parameter). + */ +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write, + force, pages, FOLL_TOUCH); +} +EXPORT_SYMBOL(get_user_pages_unlocked); + /* * get_user_pages() - pin user pages in memory * @tsk: the task_struct to use for page fault accounting, or @@ -633,22 +803,18 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, * use the correct cache flushing APIs. * * See also get_user_pages_fast, for performance critical applications. + * + * get_user_pages should be phased out in favor of + * get_user_pages_locked|unlocked or get_user_pages_fast. Nothing + * should use get_user_pages because it cannot pass + * FAULT_FLAG_ALLOW_RETRY to handle_mm_fault. */ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, unsigned long start, unsigned long nr_pages, int write, int force, struct page **pages, struct vm_area_struct **vmas) { - int flags = FOLL_TOUCH; - - if (pages) - flags |= FOLL_GET; - if (write) - flags |= FOLL_WRITE; - if (force) - flags |= FOLL_FORCE; - - return __get_user_pages(tsk, mm, start, nr_pages, flags, pages, vmas, - NULL); + return __get_user_pages_locked(tsk, mm, start, nr_pages, write, force, + pages, vmas, NULL, false, FOLL_TOUCH); } EXPORT_SYMBOL(get_user_pages); @@ -740,10 +906,10 @@ static int gup_pte_range(pmd_t pmd, unsigned long addr, unsigned long end, /* * Similar to the PMD case below, NUMA hinting must take slow - * path + * path using the pte_protnone check. */ if (!pte_present(pte) || pte_special(pte) || - pte_numa(pte) || (write && !pte_write(pte))) + pte_protnone(pte) || (write && !pte_write(pte))) goto pte_unmap; VM_BUG_ON(!pfn_valid(pte_pfn(pte))); @@ -926,7 +1092,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, pmdp = pmd_offset(&pud, addr); do { - pmd_t pmd = ACCESS_ONCE(*pmdp); + pmd_t pmd = READ_ONCE(*pmdp); next = pmd_addr_end(addr, end); if (pmd_none(pmd) || pmd_trans_splitting(pmd)) @@ -938,7 +1104,7 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, * slowpath for accounting purposes and so that they * can be serialised against THP migration. */ - if (pmd_numa(pmd)) + if (pmd_protnone(pmd)) return 0; if (!gup_huge_pmd(pmd, pmdp, addr, next, write, @@ -1077,10 +1243,8 @@ int get_user_pages_fast(unsigned long start, int nr_pages, int write, start += nr << PAGE_SHIFT; pages += nr; - down_read(&mm->mmap_sem); - ret = get_user_pages(current, mm, start, - nr_pages - nr, write, 0, pages, NULL); - up_read(&mm->mmap_sem); + ret = get_user_pages_unlocked(current, mm, start, + nr_pages - nr, write, 0, pages); /* Have to be a bit careful with return values */ if (nr > 0) { diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 817a875f2b8c..fc00c8cb5a82 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -171,12 +171,7 @@ static int start_khugepaged(void) } static atomic_t huge_zero_refcount; -static struct page *huge_zero_page __read_mostly; - -static inline bool is_huge_zero_page(struct page *page) -{ - return ACCESS_ONCE(huge_zero_page) == page; -} +struct page *huge_zero_page __read_mostly; static inline bool is_huge_zero_pmd(pmd_t pmd) { @@ -766,15 +761,6 @@ static inline gfp_t alloc_hugepage_gfpmask(int defrag, gfp_t extra_gfp) return (GFP_TRANSHUGE & ~(defrag ? 0 : __GFP_WAIT)) | extra_gfp; } -static inline struct page *alloc_hugepage_vma(int defrag, - struct vm_area_struct *vma, - unsigned long haddr, int nd, - gfp_t extra_gfp) -{ - return alloc_pages_vma(alloc_hugepage_gfpmask(defrag, extra_gfp), - HPAGE_PMD_ORDER, vma, haddr, nd); -} - /* Caller must hold page table lock. */ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, @@ -795,6 +781,7 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pmd_t *pmd, unsigned int flags) { + gfp_t gfp; struct page *page; unsigned long haddr = address & HPAGE_PMD_MASK; @@ -829,8 +816,8 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, } return 0; } - page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); + gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); if (unlikely(!page)) { count_vm_event(THP_FAULT_FALLBACK); return VM_FAULT_FALLBACK; @@ -1118,10 +1105,12 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, spin_unlock(ptl); alloc: if (transparent_hugepage_enabled(vma) && - !transparent_hugepage_debug_cow()) - new_page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), - vma, haddr, numa_node_id(), 0); - else + !transparent_hugepage_debug_cow()) { + gfp_t gfp; + + gfp = alloc_hugepage_gfpmask(transparent_hugepage_defrag(vma), 0); + new_page = alloc_hugepage_vma(gfp, vma, haddr, HPAGE_PMD_ORDER); + } else new_page = NULL; if (unlikely(!new_page)) { @@ -1222,7 +1211,7 @@ struct page *follow_trans_huge_pmd(struct vm_area_struct *vma, return ERR_PTR(-EFAULT); /* Full NUMA hinting faults to serialise migration in fault paths */ - if ((flags & FOLL_NUMA) && pmd_numa(*pmd)) + if ((flags & FOLL_NUMA) && pmd_protnone(*pmd)) goto out; page = pmd_page(*pmd); @@ -1273,6 +1262,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, bool migrated = false; int flags = 0; + /* A PROT_NONE fault should not end up here */ + BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); + ptl = pmd_lock(mm, pmdp); if (unlikely(!pmd_same(pmd, *pmdp))) goto out_unlock; @@ -1283,8 +1275,9 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, * check_same as the page may no longer be mapped. */ if (unlikely(pmd_trans_migrating(*pmdp))) { + page = pmd_page(*pmdp); spin_unlock(ptl); - wait_migrate_huge_page(vma->anon_vma, pmdp); + wait_on_page_locked(page); goto out; } @@ -1352,7 +1345,7 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, /* * Migrate the THP to the requested node, returns with page unlocked - * and pmd_numa cleared. + * and access rights restored. */ spin_unlock(ptl); migrated = migrate_misplaced_transhuge_page(mm, vma, @@ -1365,9 +1358,8 @@ int do_huge_pmd_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out; clear_pmdnuma: BUG_ON(!PageLocked(page)); - pmd = pmd_mknonnuma(pmd); + pmd = pmd_modify(pmd, vma->vm_page_prot); set_pmd_at(mm, haddr, pmdp, pmd); - VM_BUG_ON(pmd_numa(*pmdp)); update_mmu_cache_pmd(vma, addr, pmdp); unlock_page(page); out_unlock: @@ -1423,26 +1415,6 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, return ret; } -int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - spinlock_t *ptl; - int ret = 0; - - if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { - /* - * All logical pages in the range are present - * if backed by a huge page. - */ - spin_unlock(ptl); - memset(vec, 1, (end - addr) >> PAGE_SHIFT); - ret = 1; - } - - return ret; -} - int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, unsigned long old_addr, unsigned long new_addr, unsigned long old_end, @@ -1510,29 +1482,24 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, if (__pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { pmd_t entry; - ret = 1; - if (!prot_numa) { + + /* + * Avoid trapping faults against the zero page. The read-only + * data is likely to be read-cached on the local CPU and + * local/remote hits to the zero page are not interesting. + */ + if (prot_numa && is_huge_zero_pmd(*pmd)) { + spin_unlock(ptl); + return 0; + } + + if (!prot_numa || !pmd_protnone(*pmd)) { + ret = 1; entry = pmdp_get_and_clear_notify(mm, addr, pmd); - if (pmd_numa(entry)) - entry = pmd_mknonnuma(entry); entry = pmd_modify(entry, newprot); ret = HPAGE_PMD_NR; set_pmd_at(mm, addr, pmd, entry); BUG_ON(pmd_write(entry)); - } else { - struct page *page = pmd_page(*pmd); - - /* - * Do not trap faults against the zero page. The - * read-only data is likely to be read-cached on the - * local CPU cache and it is less useful to know about - * local vs remote hits on the zero page. - */ - if (!is_huge_zero_page(page) && - !pmd_numa(*pmd)) { - pmdp_set_numa(mm, addr, pmd); - ret = HPAGE_PMD_NR; - } } spin_unlock(ptl); } @@ -1797,9 +1764,9 @@ static int __split_huge_page_map(struct page *page, pte_t *pte, entry; BUG_ON(PageCompound(page+i)); /* - * Note that pmd_numa is not transferred deliberately - * to avoid any possibility that pte_numa leaks to - * a PROT_NONE VMA by accident. + * Note that NUMA hinting access restrictions are not + * transferred to avoid any possibility of altering + * permissions across VMAs. */ entry = mk_pte(page + i, vma->vm_page_prot); entry = maybe_mkwrite(pte_mkdirty(entry), vma); @@ -2148,7 +2115,8 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, { struct page *page; pte_t *_pte; - int referenced = 0, none = 0; + int none = 0; + bool referenced = false, writable = false; for (_pte = pte; _pte < pte+HPAGE_PMD_NR; _pte++, address += PAGE_SIZE) { pte_t pteval = *_pte; @@ -2158,7 +2126,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, else goto out; } - if (!pte_present(pteval) || !pte_write(pteval)) + if (!pte_present(pteval)) goto out; page = vm_normal_page(vma, address, pteval); if (unlikely(!page)) @@ -2168,9 +2136,6 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, VM_BUG_ON_PAGE(!PageAnon(page), page); VM_BUG_ON_PAGE(!PageSwapBacked(page), page); - /* cannot use mapcount: can't collapse if there's a gup pin */ - if (page_count(page) != 1) - goto out; /* * We can do it before isolate_lru_page because the * page can't be freed from under us. NOTE: PG_lock @@ -2179,6 +2144,29 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, */ if (!trylock_page(page)) goto out; + + /* + * cannot use mapcount: can't collapse if there's a gup pin. + * The page must only be referenced by the scanned process + * and page swap cache. + */ + if (page_count(page) != 1 + !!PageSwapCache(page)) { + unlock_page(page); + goto out; + } + if (pte_write(pteval)) { + writable = true; + } else { + if (PageSwapCache(page) && !reuse_swap_page(page)) { + unlock_page(page); + goto out; + } + /* + * Page is not in the swap cache. It can be collapsed + * into a THP. + */ + } + /* * Isolate the page to avoid collapsing an hugepage * currently in use by the VM. @@ -2195,9 +2183,9 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, /* If there is no mapped pte young don't collapse the page */ if (pte_young(pteval) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) - referenced = 1; + referenced = true; } - if (likely(referenced)) + if (likely(referenced && writable)) return 1; out: release_pte_pages(pte, _pte); @@ -2550,11 +2538,12 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, { pmd_t *pmd; pte_t *pte, *_pte; - int ret = 0, referenced = 0, none = 0; + int ret = 0, none = 0; struct page *page; unsigned long _address; spinlock_t *ptl; int node = NUMA_NO_NODE; + bool writable = false, referenced = false; VM_BUG_ON(address & ~HPAGE_PMD_MASK); @@ -2573,8 +2562,11 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, else goto out_unmap; } - if (!pte_present(pteval) || !pte_write(pteval)) + if (!pte_present(pteval)) goto out_unmap; + if (pte_write(pteval)) + writable = true; + page = vm_normal_page(vma, _address, pteval); if (unlikely(!page)) goto out_unmap; @@ -2591,14 +2583,18 @@ static int khugepaged_scan_pmd(struct mm_struct *mm, VM_BUG_ON_PAGE(PageCompound(page), page); if (!PageLRU(page) || PageLocked(page) || !PageAnon(page)) goto out_unmap; - /* cannot use mapcount: can't collapse if there's a gup pin */ - if (page_count(page) != 1) + /* + * cannot use mapcount: can't collapse if there's a gup pin. + * The page must only be referenced by the scanned process + * and page swap cache. + */ + if (page_count(page) != 1 + !!PageSwapCache(page)) goto out_unmap; if (pte_young(pteval) || PageReferenced(page) || mmu_notifier_test_young(vma->vm_mm, address)) - referenced = 1; + referenced = true; } - if (referenced) + if (referenced && writable) ret = 1; out_unmap: pte_unmap_unlock(pte, ptl); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 85032de5e20f..0a9ac6c26832 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -35,7 +35,7 @@ #include <linux/node.h> #include "internal.h" -unsigned long hugepages_treat_as_movable; +int hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; @@ -2657,9 +2657,10 @@ again: goto unlock; /* - * HWPoisoned hugepage is already unmapped and dropped reference + * Migrating hugepage or HWPoisoned hugepage is already + * unmapped and its refcount is dropped, so just clear pte here. */ - if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { + if (unlikely(!pte_present(pte))) { huge_pte_clear(mm, address, ptep); goto unlock; } @@ -3134,6 +3135,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, struct page *pagecache_page = NULL; struct hstate *h = hstate_vma(vma); struct address_space *mapping; + int need_wait_lock = 0; address &= huge_page_mask(h); @@ -3172,6 +3174,16 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, ret = 0; /* + * entry could be a migration/hwpoison entry at this point, so this + * check prevents the kernel from going below assuming that we have + * a active hugepage in pagecache. This goto expects the 2nd page fault, + * and is_hugetlb_entry_(migration|hwpoisoned) check will properly + * handle it. + */ + if (!pte_present(entry)) + goto out_mutex; + + /* * If we are going to COW the mapping later, we examine the pending * reservations for this page now. This will ensure that any * allocations necessary to record that reservation occur outside the @@ -3190,30 +3202,31 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, vma, address); } + ptl = huge_pte_lock(h, mm, ptep); + + /* Check for a racing update before calling hugetlb_cow */ + if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) + goto out_ptl; + /* * hugetlb_cow() requires page locks of pte_page(entry) and * pagecache_page, so here we need take the former one * when page != pagecache_page or !pagecache_page. - * Note that locking order is always pagecache_page -> page, - * so no worry about deadlock. */ page = pte_page(entry); - get_page(page); if (page != pagecache_page) - lock_page(page); - - ptl = huge_pte_lockptr(h, mm, ptep); - spin_lock(ptl); - /* Check for a racing update before calling hugetlb_cow */ - if (unlikely(!pte_same(entry, huge_ptep_get(ptep)))) - goto out_ptl; + if (!trylock_page(page)) { + need_wait_lock = 1; + goto out_ptl; + } + get_page(page); if (flags & FAULT_FLAG_WRITE) { if (!huge_pte_write(entry)) { ret = hugetlb_cow(mm, vma, address, ptep, entry, pagecache_page, ptl); - goto out_ptl; + goto out_put_page; } entry = huge_pte_mkdirty(entry); } @@ -3221,7 +3234,10 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (huge_ptep_set_access_flags(vma, address, ptep, entry, flags & FAULT_FLAG_WRITE)) update_mmu_cache(vma, address, ptep); - +out_put_page: + if (page != pagecache_page) + unlock_page(page); + put_page(page); out_ptl: spin_unlock(ptl); @@ -3229,12 +3245,17 @@ out_ptl: unlock_page(pagecache_page); put_page(pagecache_page); } - if (page != pagecache_page) - unlock_page(page); - put_page(page); - out_mutex: mutex_unlock(&htlb_fault_mutex_table[hash]); + /* + * Generally it's safe to hold refcount during waiting page lock. But + * here we just wait to defer the next page fault to avoid busy loop and + * the page is not used after unlocked before returning from the current + * page fault. So we are safe from accessing freed page, even if we wait + * here without taking refcount. + */ + if (need_wait_lock) + wait_on_page_locked(page); return ret; } @@ -3364,7 +3385,26 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, spin_unlock(ptl); continue; } - if (!huge_pte_none(huge_ptep_get(ptep))) { + pte = huge_ptep_get(ptep); + if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { + spin_unlock(ptl); + continue; + } + if (unlikely(is_hugetlb_entry_migration(pte))) { + swp_entry_t entry = pte_to_swp_entry(pte); + + if (is_write_migration_entry(entry)) { + pte_t newpte; + + make_migration_entry_read(&entry); + newpte = swp_entry_to_pte(entry); + set_huge_pte_at(mm, address, ptep, newpte); + pages++; + } + spin_unlock(ptl); + continue; + } + if (!huge_pte_none(pte)) { pte = huge_ptep_get_and_clear(mm, address, ptep); pte = pte_mkhuge(huge_pte_modify(pte, newprot)); pte = arch_make_huge_pte(pte, vma, NULL, 0); @@ -3558,6 +3598,7 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) if (saddr) { spte = huge_pte_offset(svma->vm_mm, saddr); if (spte) { + mm_inc_nr_pmds(mm); get_page(virt_to_page(spte)); break; } @@ -3569,11 +3610,13 @@ pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) ptl = huge_pte_lockptr(hstate_vma(vma), mm, spte); spin_lock(ptl); - if (pud_none(*pud)) + if (pud_none(*pud)) { pud_populate(mm, pud, (pmd_t *)((unsigned long)spte & PAGE_MASK)); - else + } else { put_page(virt_to_page(spte)); + mm_inc_nr_pmds(mm); + } spin_unlock(ptl); out: pte = (pte_t *)pmd_alloc(mm, pud, addr); @@ -3604,6 +3647,7 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) pud_clear(pud); put_page(virt_to_page(ptep)); + mm_dec_nr_pmds(mm); *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; return 1; } @@ -3660,42 +3704,64 @@ pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) return (pte_t *) pmd; } -struct page * -follow_huge_pmd(struct mm_struct *mm, unsigned long address, - pmd_t *pmd, int write) -{ - struct page *page; +#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ - page = pte_page(*(pte_t *)pmd); - if (page) - page += ((address & ~PMD_MASK) >> PAGE_SHIFT); - return page; +/* + * These functions are overwritable if your architecture needs its own + * behavior. + */ +struct page * __weak +follow_huge_addr(struct mm_struct *mm, unsigned long address, + int write) +{ + return ERR_PTR(-EINVAL); } -struct page * -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) +struct page * __weak +follow_huge_pmd(struct mm_struct *mm, unsigned long address, + pmd_t *pmd, int flags) { - struct page *page; - - page = pte_page(*(pte_t *)pud); - if (page) - page += ((address & ~PUD_MASK) >> PAGE_SHIFT); + struct page *page = NULL; + spinlock_t *ptl; +retry: + ptl = pmd_lockptr(mm, pmd); + spin_lock(ptl); + /* + * make sure that the address range covered by this pmd is not + * unmapped from other threads. + */ + if (!pmd_huge(*pmd)) + goto out; + if (pmd_present(*pmd)) { + page = pte_page(*(pte_t *)pmd) + + ((address & ~PMD_MASK) >> PAGE_SHIFT); + if (flags & FOLL_GET) + get_page(page); + } else { + if (is_hugetlb_entry_migration(huge_ptep_get((pte_t *)pmd))) { + spin_unlock(ptl); + __migration_entry_wait(mm, (pte_t *)pmd, ptl); + goto retry; + } + /* + * hwpoisoned entry is treated as no_page_table in + * follow_page_mask(). + */ + } +out: + spin_unlock(ptl); return page; } -#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */ - -/* Can be overriden by architectures */ struct page * __weak follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) + pud_t *pud, int flags) { - BUG(); - return NULL; -} + if (flags & FOLL_GET) + return NULL; -#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + return pte_page(*(pte_t *)pud) + ((address & ~PUD_MASK) >> PAGE_SHIFT); +} #ifdef CONFIG_MEMORY_FAILURE diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index 037e1c00a5b7..6e0057439a46 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -279,7 +279,7 @@ static ssize_t hugetlb_cgroup_write(struct kernfs_open_file *of, return -EINVAL; buf = strstrip(buf); - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) return ret; diff --git a/mm/internal.h b/mm/internal.h index efad241f7014..a96da5b0029d 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -110,6 +110,28 @@ extern pmd_t *mm_find_pmd(struct mm_struct *mm, unsigned long address); */ /* + * Structure for holding the mostly immutable allocation parameters passed + * between functions involved in allocations, including the alloc_pages* + * family of functions. + * + * nodemask, migratetype and high_zoneidx are initialized only once in + * __alloc_pages_nodemask() and then never change. + * + * zonelist, preferred_zone and classzone_idx are set first in + * __alloc_pages_nodemask() for the fast path, and might be later changed + * in __alloc_pages_slowpath(). All other functions pass the whole strucure + * by a const pointer. + */ +struct alloc_context { + struct zonelist *zonelist; + nodemask_t *nodemask; + struct zone *preferred_zone; + int classzone_idx; + int migratetype; + enum zone_type high_zoneidx; +}; + +/* * Locate the struct page for both the matching buddy in our * pair (buddy1) and the combined O(n+1) page they form (page). * @@ -329,8 +351,10 @@ extern int mminit_loglevel; #define mminit_dprintk(level, prefix, fmt, arg...) \ do { \ if (level < mminit_loglevel) { \ - printk(level <= MMINIT_WARNING ? KERN_WARNING : KERN_DEBUG); \ - printk(KERN_CONT "mminit::" prefix " " fmt, ##arg); \ + if (level <= MMINIT_WARNING) \ + printk(KERN_WARNING "mminit::" prefix " " fmt, ##arg); \ + else \ + printk(KERN_DEBUG "mminit::" prefix " " fmt, ##arg); \ } \ } while (0) diff --git a/mm/interval_tree.c b/mm/interval_tree.c index 8da581fa9060..f2c2492681bf 100644 --- a/mm/interval_tree.c +++ b/mm/interval_tree.c @@ -21,8 +21,8 @@ static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) return v->vm_pgoff + ((v->vm_end - v->vm_start) >> PAGE_SHIFT) - 1; } -INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.linear.rb, - unsigned long, shared.linear.rb_subtree_last, +INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, + unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff,, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ @@ -36,26 +36,26 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node, VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); - if (!prev->shared.linear.rb.rb_right) { + if (!prev->shared.rb.rb_right) { parent = prev; - link = &prev->shared.linear.rb.rb_right; + link = &prev->shared.rb.rb_right; } else { - parent = rb_entry(prev->shared.linear.rb.rb_right, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; - while (parent->shared.linear.rb.rb_left) { - parent = rb_entry(parent->shared.linear.rb.rb_left, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; + parent = rb_entry(prev->shared.rb.rb_right, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; + while (parent->shared.rb.rb_left) { + parent = rb_entry(parent->shared.rb.rb_left, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; } - link = &parent->shared.linear.rb.rb_left; + link = &parent->shared.rb.rb_left; } - node->shared.linear.rb_subtree_last = last; - rb_link_node(&node->shared.linear.rb, &parent->shared.linear.rb, link); - rb_insert_augmented(&node->shared.linear.rb, root, + node->shared.rb_subtree_last = last; + rb_link_node(&node->shared.rb, &parent->shared.rb, link); + rb_insert_augmented(&node->shared.rb, root, &vma_interval_tree_augment); } diff --git a/mm/iov_iter.c b/mm/iov_iter.c index a1599ca4ab0e..827732047da1 100644 --- a/mm/iov_iter.c +++ b/mm/iov_iter.c @@ -501,18 +501,31 @@ size_t iov_iter_single_seg_count(const struct iov_iter *i) EXPORT_SYMBOL(iov_iter_single_seg_count); void iov_iter_kvec(struct iov_iter *i, int direction, - const struct kvec *iov, unsigned long nr_segs, + const struct kvec *kvec, unsigned long nr_segs, size_t count) { BUG_ON(!(direction & ITER_KVEC)); i->type = direction; - i->kvec = (struct kvec *)iov; + i->kvec = kvec; i->nr_segs = nr_segs; i->iov_offset = 0; i->count = count; } EXPORT_SYMBOL(iov_iter_kvec); +void iov_iter_bvec(struct iov_iter *i, int direction, + const struct bio_vec *bvec, unsigned long nr_segs, + size_t count) +{ + BUG_ON(!(direction & ITER_BVEC)); + i->type = direction; + i->bvec = bvec; + i->nr_segs = nr_segs; + i->iov_offset = 0; + i->count = count; +} +EXPORT_SYMBOL(iov_iter_bvec); + unsigned long iov_iter_alignment(const struct iov_iter *i) { unsigned long res = 0; diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile new file mode 100644 index 000000000000..bd837b8c2f41 --- /dev/null +++ b/mm/kasan/Makefile @@ -0,0 +1,8 @@ +KASAN_SANITIZE := n + +CFLAGS_REMOVE_kasan.o = -pg +# Function splitter causes unnecessary splits in __asan_load1/__asan_store1 +# see: https://gcc.gnu.org/bugzilla/show_bug.cgi?id=63533 +CFLAGS_kasan.o := $(call cc-option, -fno-conserve-stack -fno-stack-protector) + +obj-y := kasan.o report.o diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c new file mode 100644 index 000000000000..78fee632a7ee --- /dev/null +++ b/mm/kasan/kasan.c @@ -0,0 +1,516 @@ +/* + * This file contains shadow memory manipulation code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin <a.ryabinin@samsung.com> + * + * Some of code borrowed from https://github.com/xairy/linux by + * Andrey Konovalov <adech.fo@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#define DISABLE_BRANCH_PROFILING + +#include <linux/export.h> +#include <linux/init.h> +#include <linux/kernel.h> +#include <linux/memblock.h> +#include <linux/memory.h> +#include <linux/mm.h> +#include <linux/module.h> +#include <linux/printk.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/stacktrace.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/kasan.h> + +#include "kasan.h" +#include "../slab.h" + +/* + * Poisons the shadow memory for 'size' bytes starting from 'addr'. + * Memory addresses should be aligned to KASAN_SHADOW_SCALE_SIZE. + */ +static void kasan_poison_shadow(const void *address, size_t size, u8 value) +{ + void *shadow_start, *shadow_end; + + shadow_start = kasan_mem_to_shadow(address); + shadow_end = kasan_mem_to_shadow(address + size); + + memset(shadow_start, value, shadow_end - shadow_start); +} + +void kasan_unpoison_shadow(const void *address, size_t size) +{ + kasan_poison_shadow(address, size, 0); + + if (size & KASAN_SHADOW_MASK) { + u8 *shadow = (u8 *)kasan_mem_to_shadow(address + size); + *shadow = size & KASAN_SHADOW_MASK; + } +} + + +/* + * All functions below always inlined so compiler could + * perform better optimizations in each of __asan_loadX/__assn_storeX + * depending on memory access size X. + */ + +static __always_inline bool memory_is_poisoned_1(unsigned long addr) +{ + s8 shadow_value = *(s8 *)kasan_mem_to_shadow((void *)addr); + + if (unlikely(shadow_value)) { + s8 last_accessible_byte = addr & KASAN_SHADOW_MASK; + return unlikely(last_accessible_byte >= shadow_value); + } + + return false; +} + +static __always_inline bool memory_is_poisoned_2(unsigned long addr) +{ + u16 *shadow_addr = (u16 *)kasan_mem_to_shadow((void *)addr); + + if (unlikely(*shadow_addr)) { + if (memory_is_poisoned_1(addr + 1)) + return true; + + if (likely(((addr + 1) & KASAN_SHADOW_MASK) != 0)) + return false; + + return unlikely(*(u8 *)shadow_addr); + } + + return false; +} + +static __always_inline bool memory_is_poisoned_4(unsigned long addr) +{ + u16 *shadow_addr = (u16 *)kasan_mem_to_shadow((void *)addr); + + if (unlikely(*shadow_addr)) { + if (memory_is_poisoned_1(addr + 3)) + return true; + + if (likely(((addr + 3) & KASAN_SHADOW_MASK) >= 3)) + return false; + + return unlikely(*(u8 *)shadow_addr); + } + + return false; +} + +static __always_inline bool memory_is_poisoned_8(unsigned long addr) +{ + u16 *shadow_addr = (u16 *)kasan_mem_to_shadow((void *)addr); + + if (unlikely(*shadow_addr)) { + if (memory_is_poisoned_1(addr + 7)) + return true; + + if (likely(((addr + 7) & KASAN_SHADOW_MASK) >= 7)) + return false; + + return unlikely(*(u8 *)shadow_addr); + } + + return false; +} + +static __always_inline bool memory_is_poisoned_16(unsigned long addr) +{ + u32 *shadow_addr = (u32 *)kasan_mem_to_shadow((void *)addr); + + if (unlikely(*shadow_addr)) { + u16 shadow_first_bytes = *(u16 *)shadow_addr; + s8 last_byte = (addr + 15) & KASAN_SHADOW_MASK; + + if (unlikely(shadow_first_bytes)) + return true; + + if (likely(!last_byte)) + return false; + + return memory_is_poisoned_1(addr + 15); + } + + return false; +} + +static __always_inline unsigned long bytes_is_zero(const u8 *start, + size_t size) +{ + while (size) { + if (unlikely(*start)) + return (unsigned long)start; + start++; + size--; + } + + return 0; +} + +static __always_inline unsigned long memory_is_zero(const void *start, + const void *end) +{ + unsigned int words; + unsigned long ret; + unsigned int prefix = (unsigned long)start % 8; + + if (end - start <= 16) + return bytes_is_zero(start, end - start); + + if (prefix) { + prefix = 8 - prefix; + ret = bytes_is_zero(start, prefix); + if (unlikely(ret)) + return ret; + start += prefix; + } + + words = (end - start) / 8; + while (words) { + if (unlikely(*(u64 *)start)) + return bytes_is_zero(start, 8); + start += 8; + words--; + } + + return bytes_is_zero(start, (end - start) % 8); +} + +static __always_inline bool memory_is_poisoned_n(unsigned long addr, + size_t size) +{ + unsigned long ret; + + ret = memory_is_zero(kasan_mem_to_shadow((void *)addr), + kasan_mem_to_shadow((void *)addr + size - 1) + 1); + + if (unlikely(ret)) { + unsigned long last_byte = addr + size - 1; + s8 *last_shadow = (s8 *)kasan_mem_to_shadow((void *)last_byte); + + if (unlikely(ret != (unsigned long)last_shadow || + ((last_byte & KASAN_SHADOW_MASK) >= *last_shadow))) + return true; + } + return false; +} + +static __always_inline bool memory_is_poisoned(unsigned long addr, size_t size) +{ + if (__builtin_constant_p(size)) { + switch (size) { + case 1: + return memory_is_poisoned_1(addr); + case 2: + return memory_is_poisoned_2(addr); + case 4: + return memory_is_poisoned_4(addr); + case 8: + return memory_is_poisoned_8(addr); + case 16: + return memory_is_poisoned_16(addr); + default: + BUILD_BUG(); + } + } + + return memory_is_poisoned_n(addr, size); +} + + +static __always_inline void check_memory_region(unsigned long addr, + size_t size, bool write) +{ + struct kasan_access_info info; + + if (unlikely(size == 0)) + return; + + if (unlikely((void *)addr < + kasan_shadow_to_mem((void *)KASAN_SHADOW_START))) { + info.access_addr = (void *)addr; + info.access_size = size; + info.is_write = write; + info.ip = _RET_IP_; + kasan_report_user_access(&info); + return; + } + + if (likely(!memory_is_poisoned(addr, size))) + return; + + kasan_report(addr, size, write, _RET_IP_); +} + +void __asan_loadN(unsigned long addr, size_t size); +void __asan_storeN(unsigned long addr, size_t size); + +#undef memset +void *memset(void *addr, int c, size_t len) +{ + __asan_storeN((unsigned long)addr, len); + + return __memset(addr, c, len); +} + +#undef memmove +void *memmove(void *dest, const void *src, size_t len) +{ + __asan_loadN((unsigned long)src, len); + __asan_storeN((unsigned long)dest, len); + + return __memmove(dest, src, len); +} + +#undef memcpy +void *memcpy(void *dest, const void *src, size_t len) +{ + __asan_loadN((unsigned long)src, len); + __asan_storeN((unsigned long)dest, len); + + return __memcpy(dest, src, len); +} + +void kasan_alloc_pages(struct page *page, unsigned int order) +{ + if (likely(!PageHighMem(page))) + kasan_unpoison_shadow(page_address(page), PAGE_SIZE << order); +} + +void kasan_free_pages(struct page *page, unsigned int order) +{ + if (likely(!PageHighMem(page))) + kasan_poison_shadow(page_address(page), + PAGE_SIZE << order, + KASAN_FREE_PAGE); +} + +void kasan_poison_slab(struct page *page) +{ + kasan_poison_shadow(page_address(page), + PAGE_SIZE << compound_order(page), + KASAN_KMALLOC_REDZONE); +} + +void kasan_unpoison_object_data(struct kmem_cache *cache, void *object) +{ + kasan_unpoison_shadow(object, cache->object_size); +} + +void kasan_poison_object_data(struct kmem_cache *cache, void *object) +{ + kasan_poison_shadow(object, + round_up(cache->object_size, KASAN_SHADOW_SCALE_SIZE), + KASAN_KMALLOC_REDZONE); +} + +void kasan_slab_alloc(struct kmem_cache *cache, void *object) +{ + kasan_kmalloc(cache, object, cache->object_size); +} + +void kasan_slab_free(struct kmem_cache *cache, void *object) +{ + unsigned long size = cache->object_size; + unsigned long rounded_up_size = round_up(size, KASAN_SHADOW_SCALE_SIZE); + + /* RCU slabs could be legally used after free within the RCU period */ + if (unlikely(cache->flags & SLAB_DESTROY_BY_RCU)) + return; + + kasan_poison_shadow(object, rounded_up_size, KASAN_KMALLOC_FREE); +} + +void kasan_kmalloc(struct kmem_cache *cache, const void *object, size_t size) +{ + unsigned long redzone_start; + unsigned long redzone_end; + + if (unlikely(object == NULL)) + return; + + redzone_start = round_up((unsigned long)(object + size), + KASAN_SHADOW_SCALE_SIZE); + redzone_end = round_up((unsigned long)object + cache->object_size, + KASAN_SHADOW_SCALE_SIZE); + + kasan_unpoison_shadow(object, size); + kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start, + KASAN_KMALLOC_REDZONE); +} +EXPORT_SYMBOL(kasan_kmalloc); + +void kasan_kmalloc_large(const void *ptr, size_t size) +{ + struct page *page; + unsigned long redzone_start; + unsigned long redzone_end; + + if (unlikely(ptr == NULL)) + return; + + page = virt_to_page(ptr); + redzone_start = round_up((unsigned long)(ptr + size), + KASAN_SHADOW_SCALE_SIZE); + redzone_end = (unsigned long)ptr + (PAGE_SIZE << compound_order(page)); + + kasan_unpoison_shadow(ptr, size); + kasan_poison_shadow((void *)redzone_start, redzone_end - redzone_start, + KASAN_PAGE_REDZONE); +} + +void kasan_krealloc(const void *object, size_t size) +{ + struct page *page; + + if (unlikely(object == ZERO_SIZE_PTR)) + return; + + page = virt_to_head_page(object); + + if (unlikely(!PageSlab(page))) + kasan_kmalloc_large(object, size); + else + kasan_kmalloc(page->slab_cache, object, size); +} + +void kasan_kfree_large(const void *ptr) +{ + struct page *page = virt_to_page(ptr); + + kasan_poison_shadow(ptr, PAGE_SIZE << compound_order(page), + KASAN_FREE_PAGE); +} + +int kasan_module_alloc(void *addr, size_t size) +{ + void *ret; + size_t shadow_size; + unsigned long shadow_start; + + shadow_start = (unsigned long)kasan_mem_to_shadow(addr); + shadow_size = round_up(size >> KASAN_SHADOW_SCALE_SHIFT, + PAGE_SIZE); + + if (WARN_ON(!PAGE_ALIGNED(shadow_start))) + return -EINVAL; + + ret = __vmalloc_node_range(shadow_size, 1, shadow_start, + shadow_start + shadow_size, + GFP_KERNEL | __GFP_HIGHMEM | __GFP_ZERO, + PAGE_KERNEL, VM_NO_GUARD, NUMA_NO_NODE, + __builtin_return_address(0)); + return ret ? 0 : -ENOMEM; +} + +void kasan_module_free(void *addr) +{ + vfree(kasan_mem_to_shadow(addr)); +} + +static void register_global(struct kasan_global *global) +{ + size_t aligned_size = round_up(global->size, KASAN_SHADOW_SCALE_SIZE); + + kasan_unpoison_shadow(global->beg, global->size); + + kasan_poison_shadow(global->beg + aligned_size, + global->size_with_redzone - aligned_size, + KASAN_GLOBAL_REDZONE); +} + +void __asan_register_globals(struct kasan_global *globals, size_t size) +{ + int i; + + for (i = 0; i < size; i++) + register_global(&globals[i]); +} +EXPORT_SYMBOL(__asan_register_globals); + +void __asan_unregister_globals(struct kasan_global *globals, size_t size) +{ +} +EXPORT_SYMBOL(__asan_unregister_globals); + +#define DEFINE_ASAN_LOAD_STORE(size) \ + void __asan_load##size(unsigned long addr) \ + { \ + check_memory_region(addr, size, false); \ + } \ + EXPORT_SYMBOL(__asan_load##size); \ + __alias(__asan_load##size) \ + void __asan_load##size##_noabort(unsigned long); \ + EXPORT_SYMBOL(__asan_load##size##_noabort); \ + void __asan_store##size(unsigned long addr) \ + { \ + check_memory_region(addr, size, true); \ + } \ + EXPORT_SYMBOL(__asan_store##size); \ + __alias(__asan_store##size) \ + void __asan_store##size##_noabort(unsigned long); \ + EXPORT_SYMBOL(__asan_store##size##_noabort) + +DEFINE_ASAN_LOAD_STORE(1); +DEFINE_ASAN_LOAD_STORE(2); +DEFINE_ASAN_LOAD_STORE(4); +DEFINE_ASAN_LOAD_STORE(8); +DEFINE_ASAN_LOAD_STORE(16); + +void __asan_loadN(unsigned long addr, size_t size) +{ + check_memory_region(addr, size, false); +} +EXPORT_SYMBOL(__asan_loadN); + +__alias(__asan_loadN) +void __asan_loadN_noabort(unsigned long, size_t); +EXPORT_SYMBOL(__asan_loadN_noabort); + +void __asan_storeN(unsigned long addr, size_t size) +{ + check_memory_region(addr, size, true); +} +EXPORT_SYMBOL(__asan_storeN); + +__alias(__asan_storeN) +void __asan_storeN_noabort(unsigned long, size_t); +EXPORT_SYMBOL(__asan_storeN_noabort); + +/* to shut up compiler complaints */ +void __asan_handle_no_return(void) {} +EXPORT_SYMBOL(__asan_handle_no_return); + +#ifdef CONFIG_MEMORY_HOTPLUG +static int kasan_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + return (action == MEM_GOING_ONLINE) ? NOTIFY_BAD : NOTIFY_OK; +} + +static int __init kasan_memhotplug_init(void) +{ + pr_err("WARNING: KASan doesn't support memory hot-add\n"); + pr_err("Memory hot-add will be disabled\n"); + + hotplug_memory_notifier(kasan_mem_notifier, 0); + + return 0; +} + +module_init(kasan_memhotplug_init); +#endif diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h new file mode 100644 index 000000000000..4986b0acab21 --- /dev/null +++ b/mm/kasan/kasan.h @@ -0,0 +1,75 @@ +#ifndef __MM_KASAN_KASAN_H +#define __MM_KASAN_KASAN_H + +#include <linux/kasan.h> + +#define KASAN_SHADOW_SCALE_SIZE (1UL << KASAN_SHADOW_SCALE_SHIFT) +#define KASAN_SHADOW_MASK (KASAN_SHADOW_SCALE_SIZE - 1) + +#define KASAN_FREE_PAGE 0xFF /* page was freed */ +#define KASAN_FREE_PAGE 0xFF /* page was freed */ +#define KASAN_PAGE_REDZONE 0xFE /* redzone for kmalloc_large allocations */ +#define KASAN_KMALLOC_REDZONE 0xFC /* redzone inside slub object */ +#define KASAN_KMALLOC_FREE 0xFB /* object was freed (kmem_cache_free/kfree) */ +#define KASAN_GLOBAL_REDZONE 0xFA /* redzone for global variable */ + +/* + * Stack redzone shadow values + * (Those are compiler's ABI, don't change them) + */ +#define KASAN_STACK_LEFT 0xF1 +#define KASAN_STACK_MID 0xF2 +#define KASAN_STACK_RIGHT 0xF3 +#define KASAN_STACK_PARTIAL 0xF4 + +/* Don't break randconfig/all*config builds */ +#ifndef KASAN_ABI_VERSION +#define KASAN_ABI_VERSION 1 +#endif + +struct kasan_access_info { + const void *access_addr; + const void *first_bad_addr; + size_t access_size; + bool is_write; + unsigned long ip; +}; + +/* The layout of struct dictated by compiler */ +struct kasan_source_location { + const char *filename; + int line_no; + int column_no; +}; + +/* The layout of struct dictated by compiler */ +struct kasan_global { + const void *beg; /* Address of the beginning of the global variable. */ + size_t size; /* Size of the global variable. */ + size_t size_with_redzone; /* Size of the variable + size of the red zone. 32 bytes aligned */ + const void *name; + const void *module_name; /* Name of the module where the global variable is declared. */ + unsigned long has_dynamic_init; /* This needed for C++ */ +#if KASAN_ABI_VERSION >= 4 + struct kasan_source_location *location; +#endif +}; + +void kasan_report_error(struct kasan_access_info *info); +void kasan_report_user_access(struct kasan_access_info *info); + +static inline const void *kasan_shadow_to_mem(const void *shadow_addr) +{ + return (void *)(((unsigned long)shadow_addr - KASAN_SHADOW_OFFSET) + << KASAN_SHADOW_SCALE_SHIFT); +} + +static inline bool kasan_enabled(void) +{ + return !current->kasan_depth; +} + +void kasan_report(unsigned long addr, size_t size, + bool is_write, unsigned long ip); + +#endif diff --git a/mm/kasan/report.c b/mm/kasan/report.c new file mode 100644 index 000000000000..680ceedf810a --- /dev/null +++ b/mm/kasan/report.c @@ -0,0 +1,269 @@ +/* + * This file contains error reporting code. + * + * Copyright (c) 2014 Samsung Electronics Co., Ltd. + * Author: Andrey Ryabinin <a.ryabinin@samsung.com> + * + * Some of code borrowed from https://github.com/xairy/linux by + * Andrey Konovalov <adech.fo@gmail.com> + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + */ + +#include <linux/kernel.h> +#include <linux/mm.h> +#include <linux/printk.h> +#include <linux/sched.h> +#include <linux/slab.h> +#include <linux/stacktrace.h> +#include <linux/string.h> +#include <linux/types.h> +#include <linux/kasan.h> + +#include <asm/sections.h> + +#include "kasan.h" +#include "../slab.h" + +/* Shadow layout customization. */ +#define SHADOW_BYTES_PER_BLOCK 1 +#define SHADOW_BLOCKS_PER_ROW 16 +#define SHADOW_BYTES_PER_ROW (SHADOW_BLOCKS_PER_ROW * SHADOW_BYTES_PER_BLOCK) +#define SHADOW_ROWS_AROUND_ADDR 2 + +static const void *find_first_bad_addr(const void *addr, size_t size) +{ + u8 shadow_val = *(u8 *)kasan_mem_to_shadow(addr); + const void *first_bad_addr = addr; + + while (!shadow_val && first_bad_addr < addr + size) { + first_bad_addr += KASAN_SHADOW_SCALE_SIZE; + shadow_val = *(u8 *)kasan_mem_to_shadow(first_bad_addr); + } + return first_bad_addr; +} + +static void print_error_description(struct kasan_access_info *info) +{ + const char *bug_type = "unknown crash"; + u8 shadow_val; + + info->first_bad_addr = find_first_bad_addr(info->access_addr, + info->access_size); + + shadow_val = *(u8 *)kasan_mem_to_shadow(info->first_bad_addr); + + switch (shadow_val) { + case KASAN_FREE_PAGE: + case KASAN_KMALLOC_FREE: + bug_type = "use after free"; + break; + case KASAN_PAGE_REDZONE: + case KASAN_KMALLOC_REDZONE: + case KASAN_GLOBAL_REDZONE: + case 0 ... KASAN_SHADOW_SCALE_SIZE - 1: + bug_type = "out of bounds access"; + break; + case KASAN_STACK_LEFT: + case KASAN_STACK_MID: + case KASAN_STACK_RIGHT: + case KASAN_STACK_PARTIAL: + bug_type = "out of bounds on stack"; + break; + } + + pr_err("BUG: KASan: %s in %pS at addr %p\n", + bug_type, (void *)info->ip, + info->access_addr); + pr_err("%s of size %zu by task %s/%d\n", + info->is_write ? "Write" : "Read", + info->access_size, current->comm, task_pid_nr(current)); +} + +static inline bool kernel_or_module_addr(const void *addr) +{ + return (addr >= (void *)_stext && addr < (void *)_end) + || (addr >= (void *)MODULES_VADDR + && addr < (void *)MODULES_END); +} + +static inline bool init_task_stack_addr(const void *addr) +{ + return addr >= (void *)&init_thread_union.stack && + (addr <= (void *)&init_thread_union.stack + + sizeof(init_thread_union.stack)); +} + +static void print_address_description(struct kasan_access_info *info) +{ + const void *addr = info->access_addr; + + if ((addr >= (void *)PAGE_OFFSET) && + (addr < high_memory)) { + struct page *page = virt_to_head_page(addr); + + if (PageSlab(page)) { + void *object; + struct kmem_cache *cache = page->slab_cache; + void *last_object; + + object = virt_to_obj(cache, page_address(page), addr); + last_object = page_address(page) + + page->objects * cache->size; + + if (unlikely(object > last_object)) + object = last_object; /* we hit into padding */ + + object_err(cache, page, object, + "kasan: bad access detected"); + return; + } + dump_page(page, "kasan: bad access detected"); + } + + if (kernel_or_module_addr(addr)) { + if (!init_task_stack_addr(addr)) + pr_err("Address belongs to variable %pS\n", addr); + } + + dump_stack(); +} + +static bool row_is_guilty(const void *row, const void *guilty) +{ + return (row <= guilty) && (guilty < row + SHADOW_BYTES_PER_ROW); +} + +static int shadow_pointer_offset(const void *row, const void *shadow) +{ + /* The length of ">ff00ff00ff00ff00: " is + * 3 + (BITS_PER_LONG/8)*2 chars. + */ + return 3 + (BITS_PER_LONG/8)*2 + (shadow - row)*2 + + (shadow - row) / SHADOW_BYTES_PER_BLOCK + 1; +} + +static void print_shadow_for_address(const void *addr) +{ + int i; + const void *shadow = kasan_mem_to_shadow(addr); + const void *shadow_row; + + shadow_row = (void *)round_down((unsigned long)shadow, + SHADOW_BYTES_PER_ROW) + - SHADOW_ROWS_AROUND_ADDR * SHADOW_BYTES_PER_ROW; + + pr_err("Memory state around the buggy address:\n"); + + for (i = -SHADOW_ROWS_AROUND_ADDR; i <= SHADOW_ROWS_AROUND_ADDR; i++) { + const void *kaddr = kasan_shadow_to_mem(shadow_row); + char buffer[4 + (BITS_PER_LONG/8)*2]; + + snprintf(buffer, sizeof(buffer), + (i == 0) ? ">%p: " : " %p: ", kaddr); + + kasan_disable_current(); + print_hex_dump(KERN_ERR, buffer, + DUMP_PREFIX_NONE, SHADOW_BYTES_PER_ROW, 1, + shadow_row, SHADOW_BYTES_PER_ROW, 0); + kasan_enable_current(); + + if (row_is_guilty(shadow_row, shadow)) + pr_err("%*c\n", + shadow_pointer_offset(shadow_row, shadow), + '^'); + + shadow_row += SHADOW_BYTES_PER_ROW; + } +} + +static DEFINE_SPINLOCK(report_lock); + +void kasan_report_error(struct kasan_access_info *info) +{ + unsigned long flags; + + spin_lock_irqsave(&report_lock, flags); + pr_err("=================================" + "=================================\n"); + print_error_description(info); + print_address_description(info); + print_shadow_for_address(info->first_bad_addr); + pr_err("=================================" + "=================================\n"); + spin_unlock_irqrestore(&report_lock, flags); +} + +void kasan_report_user_access(struct kasan_access_info *info) +{ + unsigned long flags; + + spin_lock_irqsave(&report_lock, flags); + pr_err("=================================" + "=================================\n"); + pr_err("BUG: KASan: user-memory-access on address %p\n", + info->access_addr); + pr_err("%s of size %zu by task %s/%d\n", + info->is_write ? "Write" : "Read", + info->access_size, current->comm, task_pid_nr(current)); + dump_stack(); + pr_err("=================================" + "=================================\n"); + spin_unlock_irqrestore(&report_lock, flags); +} + +void kasan_report(unsigned long addr, size_t size, + bool is_write, unsigned long ip) +{ + struct kasan_access_info info; + + if (likely(!kasan_enabled())) + return; + + info.access_addr = (void *)addr; + info.access_size = size; + info.is_write = is_write; + info.ip = ip; + kasan_report_error(&info); +} + + +#define DEFINE_ASAN_REPORT_LOAD(size) \ +void __asan_report_load##size##_noabort(unsigned long addr) \ +{ \ + kasan_report(addr, size, false, _RET_IP_); \ +} \ +EXPORT_SYMBOL(__asan_report_load##size##_noabort) + +#define DEFINE_ASAN_REPORT_STORE(size) \ +void __asan_report_store##size##_noabort(unsigned long addr) \ +{ \ + kasan_report(addr, size, true, _RET_IP_); \ +} \ +EXPORT_SYMBOL(__asan_report_store##size##_noabort) + +DEFINE_ASAN_REPORT_LOAD(1); +DEFINE_ASAN_REPORT_LOAD(2); +DEFINE_ASAN_REPORT_LOAD(4); +DEFINE_ASAN_REPORT_LOAD(8); +DEFINE_ASAN_REPORT_LOAD(16); +DEFINE_ASAN_REPORT_STORE(1); +DEFINE_ASAN_REPORT_STORE(2); +DEFINE_ASAN_REPORT_STORE(4); +DEFINE_ASAN_REPORT_STORE(8); +DEFINE_ASAN_REPORT_STORE(16); + +void __asan_report_load_n_noabort(unsigned long addr, size_t size) +{ + kasan_report(addr, size, false, _RET_IP_); +} +EXPORT_SYMBOL(__asan_report_load_n_noabort); + +void __asan_report_store_n_noabort(unsigned long addr, size_t size) +{ + kasan_report(addr, size, true, _RET_IP_); +} +EXPORT_SYMBOL(__asan_report_store_n_noabort); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 3cda50c1e394..5405aff5a590 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -98,6 +98,7 @@ #include <asm/processor.h> #include <linux/atomic.h> +#include <linux/kasan.h> #include <linux/kmemcheck.h> #include <linux/kmemleak.h> #include <linux/memory_hotplug.h> @@ -1113,7 +1114,10 @@ static bool update_checksum(struct kmemleak_object *object) if (!kmemcheck_is_obj_initialized(object->pointer, object->size)) return false; + kasan_disable_current(); object->checksum = crc32(0, (void *)object->pointer, object->size); + kasan_enable_current(); + return object->checksum != old_csum; } @@ -1164,7 +1168,9 @@ static void scan_block(void *_start, void *_end, BYTES_PER_POINTER)) continue; + kasan_disable_current(); pointer = *ptr; + kasan_enable_current(); object = find_and_get_object(pointer, 1); if (!object) @@ -1748,7 +1748,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, */ if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP)) + VM_HUGETLB | VM_MIXEDMAP)) return 0; /* just ignore the advice */ #ifdef VM_SAO diff --git a/mm/list_lru.c b/mm/list_lru.c index f1a0db194173..909eca2c820e 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -9,18 +9,100 @@ #include <linux/mm.h> #include <linux/list_lru.h> #include <linux/slab.h> +#include <linux/mutex.h> +#include <linux/memcontrol.h> + +#ifdef CONFIG_MEMCG_KMEM +static LIST_HEAD(list_lrus); +static DEFINE_MUTEX(list_lrus_mutex); + +static void list_lru_register(struct list_lru *lru) +{ + mutex_lock(&list_lrus_mutex); + list_add(&lru->list, &list_lrus); + mutex_unlock(&list_lrus_mutex); +} + +static void list_lru_unregister(struct list_lru *lru) +{ + mutex_lock(&list_lrus_mutex); + list_del(&lru->list); + mutex_unlock(&list_lrus_mutex); +} +#else +static void list_lru_register(struct list_lru *lru) +{ +} + +static void list_lru_unregister(struct list_lru *lru) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ + +#ifdef CONFIG_MEMCG_KMEM +static inline bool list_lru_memcg_aware(struct list_lru *lru) +{ + return !!lru->node[0].memcg_lrus; +} + +static inline struct list_lru_one * +list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) +{ + /* + * The lock protects the array of per cgroup lists from relocation + * (see memcg_update_list_lru_node). + */ + lockdep_assert_held(&nlru->lock); + if (nlru->memcg_lrus && idx >= 0) + return nlru->memcg_lrus->lru[idx]; + + return &nlru->lru; +} + +static inline struct list_lru_one * +list_lru_from_kmem(struct list_lru_node *nlru, void *ptr) +{ + struct mem_cgroup *memcg; + + if (!nlru->memcg_lrus) + return &nlru->lru; + + memcg = mem_cgroup_from_kmem(ptr); + if (!memcg) + return &nlru->lru; + + return list_lru_from_memcg_idx(nlru, memcg_cache_id(memcg)); +} +#else +static inline bool list_lru_memcg_aware(struct list_lru *lru) +{ + return false; +} + +static inline struct list_lru_one * +list_lru_from_memcg_idx(struct list_lru_node *nlru, int idx) +{ + return &nlru->lru; +} + +static inline struct list_lru_one * +list_lru_from_kmem(struct list_lru_node *nlru, void *ptr) +{ + return &nlru->lru; +} +#endif /* CONFIG_MEMCG_KMEM */ bool list_lru_add(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; spin_lock(&nlru->lock); - WARN_ON_ONCE(nlru->nr_items < 0); + l = list_lru_from_kmem(nlru, item); if (list_empty(item)) { - list_add_tail(item, &nlru->list); - if (nlru->nr_items++ == 0) - node_set(nid, lru->active_nodes); + list_add_tail(item, &l->list); + l->nr_items++; spin_unlock(&nlru->lock); return true; } @@ -33,13 +115,13 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item) { int nid = page_to_nid(virt_to_page(item)); struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; spin_lock(&nlru->lock); + l = list_lru_from_kmem(nlru, item); if (!list_empty(item)) { list_del_init(item); - if (--nlru->nr_items == 0) - node_clear(nid, lru->active_nodes); - WARN_ON_ONCE(nlru->nr_items < 0); + l->nr_items--; spin_unlock(&nlru->lock); return true; } @@ -48,33 +130,72 @@ bool list_lru_del(struct list_lru *lru, struct list_head *item) } EXPORT_SYMBOL_GPL(list_lru_del); -unsigned long -list_lru_count_node(struct list_lru *lru, int nid) +void list_lru_isolate(struct list_lru_one *list, struct list_head *item) +{ + list_del_init(item); + list->nr_items--; +} +EXPORT_SYMBOL_GPL(list_lru_isolate); + +void list_lru_isolate_move(struct list_lru_one *list, struct list_head *item, + struct list_head *head) +{ + list_move(item, head); + list->nr_items--; +} +EXPORT_SYMBOL_GPL(list_lru_isolate_move); + +static unsigned long __list_lru_count_one(struct list_lru *lru, + int nid, int memcg_idx) { - unsigned long count = 0; struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; + unsigned long count; spin_lock(&nlru->lock); - WARN_ON_ONCE(nlru->nr_items < 0); - count += nlru->nr_items; + l = list_lru_from_memcg_idx(nlru, memcg_idx); + count = l->nr_items; spin_unlock(&nlru->lock); return count; } + +unsigned long list_lru_count_one(struct list_lru *lru, + int nid, struct mem_cgroup *memcg) +{ + return __list_lru_count_one(lru, nid, memcg_cache_id(memcg)); +} +EXPORT_SYMBOL_GPL(list_lru_count_one); + +unsigned long list_lru_count_node(struct list_lru *lru, int nid) +{ + long count = 0; + int memcg_idx; + + count += __list_lru_count_one(lru, nid, -1); + if (list_lru_memcg_aware(lru)) { + for_each_memcg_cache_index(memcg_idx) + count += __list_lru_count_one(lru, nid, memcg_idx); + } + return count; +} EXPORT_SYMBOL_GPL(list_lru_count_node); -unsigned long -list_lru_walk_node(struct list_lru *lru, int nid, list_lru_walk_cb isolate, - void *cb_arg, unsigned long *nr_to_walk) +static unsigned long +__list_lru_walk_one(struct list_lru *lru, int nid, int memcg_idx, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) { - struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_node *nlru = &lru->node[nid]; + struct list_lru_one *l; struct list_head *item, *n; unsigned long isolated = 0; spin_lock(&nlru->lock); + l = list_lru_from_memcg_idx(nlru, memcg_idx); restart: - list_for_each_safe(item, n, &nlru->list) { + list_for_each_safe(item, n, &l->list) { enum lru_status ret; /* @@ -85,14 +206,11 @@ restart: break; --*nr_to_walk; - ret = isolate(item, &nlru->lock, cb_arg); + ret = isolate(item, l, &nlru->lock, cb_arg); switch (ret) { case LRU_REMOVED_RETRY: assert_spin_locked(&nlru->lock); case LRU_REMOVED: - if (--nlru->nr_items == 0) - node_clear(nid, lru->active_nodes); - WARN_ON_ONCE(nlru->nr_items < 0); isolated++; /* * If the lru lock has been dropped, our list @@ -103,7 +221,7 @@ restart: goto restart; break; case LRU_ROTATE: - list_move_tail(item, &nlru->list); + list_move_tail(item, &l->list); break; case LRU_SKIP: break; @@ -122,31 +240,322 @@ restart: spin_unlock(&nlru->lock); return isolated; } + +unsigned long +list_lru_walk_one(struct list_lru *lru, int nid, struct mem_cgroup *memcg, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + return __list_lru_walk_one(lru, nid, memcg_cache_id(memcg), + isolate, cb_arg, nr_to_walk); +} +EXPORT_SYMBOL_GPL(list_lru_walk_one); + +unsigned long list_lru_walk_node(struct list_lru *lru, int nid, + list_lru_walk_cb isolate, void *cb_arg, + unsigned long *nr_to_walk) +{ + long isolated = 0; + int memcg_idx; + + isolated += __list_lru_walk_one(lru, nid, -1, isolate, cb_arg, + nr_to_walk); + if (*nr_to_walk > 0 && list_lru_memcg_aware(lru)) { + for_each_memcg_cache_index(memcg_idx) { + isolated += __list_lru_walk_one(lru, nid, memcg_idx, + isolate, cb_arg, nr_to_walk); + if (*nr_to_walk <= 0) + break; + } + } + return isolated; +} EXPORT_SYMBOL_GPL(list_lru_walk_node); -int list_lru_init_key(struct list_lru *lru, struct lock_class_key *key) +static void init_one_lru(struct list_lru_one *l) +{ + INIT_LIST_HEAD(&l->list); + l->nr_items = 0; +} + +#ifdef CONFIG_MEMCG_KMEM +static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus, + int begin, int end) +{ + int i; + + for (i = begin; i < end; i++) + kfree(memcg_lrus->lru[i]); +} + +static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus, + int begin, int end) +{ + int i; + + for (i = begin; i < end; i++) { + struct list_lru_one *l; + + l = kmalloc(sizeof(struct list_lru_one), GFP_KERNEL); + if (!l) + goto fail; + + init_one_lru(l); + memcg_lrus->lru[i] = l; + } + return 0; +fail: + __memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1); + return -ENOMEM; +} + +static int memcg_init_list_lru_node(struct list_lru_node *nlru) +{ + int size = memcg_nr_cache_ids; + + nlru->memcg_lrus = kmalloc(size * sizeof(void *), GFP_KERNEL); + if (!nlru->memcg_lrus) + return -ENOMEM; + + if (__memcg_init_list_lru_node(nlru->memcg_lrus, 0, size)) { + kfree(nlru->memcg_lrus); + return -ENOMEM; + } + + return 0; +} + +static void memcg_destroy_list_lru_node(struct list_lru_node *nlru) +{ + __memcg_destroy_list_lru_node(nlru->memcg_lrus, 0, memcg_nr_cache_ids); + kfree(nlru->memcg_lrus); +} + +static int memcg_update_list_lru_node(struct list_lru_node *nlru, + int old_size, int new_size) +{ + struct list_lru_memcg *old, *new; + + BUG_ON(old_size > new_size); + + old = nlru->memcg_lrus; + new = kmalloc(new_size * sizeof(void *), GFP_KERNEL); + if (!new) + return -ENOMEM; + + if (__memcg_init_list_lru_node(new, old_size, new_size)) { + kfree(new); + return -ENOMEM; + } + + memcpy(new, old, old_size * sizeof(void *)); + + /* + * The lock guarantees that we won't race with a reader + * (see list_lru_from_memcg_idx). + * + * Since list_lru_{add,del} may be called under an IRQ-safe lock, + * we have to use IRQ-safe primitives here to avoid deadlock. + */ + spin_lock_irq(&nlru->lock); + nlru->memcg_lrus = new; + spin_unlock_irq(&nlru->lock); + + kfree(old); + return 0; +} + +static void memcg_cancel_update_list_lru_node(struct list_lru_node *nlru, + int old_size, int new_size) +{ + /* do not bother shrinking the array back to the old size, because we + * cannot handle allocation failures here */ + __memcg_destroy_list_lru_node(nlru->memcg_lrus, old_size, new_size); +} + +static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +{ + int i; + + for (i = 0; i < nr_node_ids; i++) { + if (!memcg_aware) + lru->node[i].memcg_lrus = NULL; + else if (memcg_init_list_lru_node(&lru->node[i])) + goto fail; + } + return 0; +fail: + for (i = i - 1; i >= 0; i--) + memcg_destroy_list_lru_node(&lru->node[i]); + return -ENOMEM; +} + +static void memcg_destroy_list_lru(struct list_lru *lru) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for (i = 0; i < nr_node_ids; i++) + memcg_destroy_list_lru_node(&lru->node[i]); +} + +static int memcg_update_list_lru(struct list_lru *lru, + int old_size, int new_size) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return 0; + + for (i = 0; i < nr_node_ids; i++) { + if (memcg_update_list_lru_node(&lru->node[i], + old_size, new_size)) + goto fail; + } + return 0; +fail: + for (i = i - 1; i >= 0; i--) + memcg_cancel_update_list_lru_node(&lru->node[i], + old_size, new_size); + return -ENOMEM; +} + +static void memcg_cancel_update_list_lru(struct list_lru *lru, + int old_size, int new_size) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for (i = 0; i < nr_node_ids; i++) + memcg_cancel_update_list_lru_node(&lru->node[i], + old_size, new_size); +} + +int memcg_update_all_list_lrus(int new_size) +{ + int ret = 0; + struct list_lru *lru; + int old_size = memcg_nr_cache_ids; + + mutex_lock(&list_lrus_mutex); + list_for_each_entry(lru, &list_lrus, list) { + ret = memcg_update_list_lru(lru, old_size, new_size); + if (ret) + goto fail; + } +out: + mutex_unlock(&list_lrus_mutex); + return ret; +fail: + list_for_each_entry_continue_reverse(lru, &list_lrus, list) + memcg_cancel_update_list_lru(lru, old_size, new_size); + goto out; +} + +static void memcg_drain_list_lru_node(struct list_lru_node *nlru, + int src_idx, int dst_idx) +{ + struct list_lru_one *src, *dst; + + /* + * Since list_lru_{add,del} may be called under an IRQ-safe lock, + * we have to use IRQ-safe primitives here to avoid deadlock. + */ + spin_lock_irq(&nlru->lock); + + src = list_lru_from_memcg_idx(nlru, src_idx); + dst = list_lru_from_memcg_idx(nlru, dst_idx); + + list_splice_init(&src->list, &dst->list); + dst->nr_items += src->nr_items; + src->nr_items = 0; + + spin_unlock_irq(&nlru->lock); +} + +static void memcg_drain_list_lru(struct list_lru *lru, + int src_idx, int dst_idx) +{ + int i; + + if (!list_lru_memcg_aware(lru)) + return; + + for (i = 0; i < nr_node_ids; i++) + memcg_drain_list_lru_node(&lru->node[i], src_idx, dst_idx); +} + +void memcg_drain_all_list_lrus(int src_idx, int dst_idx) +{ + struct list_lru *lru; + + mutex_lock(&list_lrus_mutex); + list_for_each_entry(lru, &list_lrus, list) + memcg_drain_list_lru(lru, src_idx, dst_idx); + mutex_unlock(&list_lrus_mutex); +} +#else +static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) +{ + return 0; +} + +static void memcg_destroy_list_lru(struct list_lru *lru) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ + +int __list_lru_init(struct list_lru *lru, bool memcg_aware, + struct lock_class_key *key) { int i; size_t size = sizeof(*lru->node) * nr_node_ids; + int err = -ENOMEM; + + memcg_get_cache_ids(); lru->node = kzalloc(size, GFP_KERNEL); if (!lru->node) - return -ENOMEM; + goto out; - nodes_clear(lru->active_nodes); for (i = 0; i < nr_node_ids; i++) { spin_lock_init(&lru->node[i].lock); if (key) lockdep_set_class(&lru->node[i].lock, key); - INIT_LIST_HEAD(&lru->node[i].list); - lru->node[i].nr_items = 0; + init_one_lru(&lru->node[i].lru); } - return 0; + + err = memcg_init_list_lru(lru, memcg_aware); + if (err) { + kfree(lru->node); + goto out; + } + + list_lru_register(lru); +out: + memcg_put_cache_ids(); + return err; } -EXPORT_SYMBOL_GPL(list_lru_init_key); +EXPORT_SYMBOL_GPL(__list_lru_init); void list_lru_destroy(struct list_lru *lru) { + /* Already destroyed or not yet initialized? */ + if (!lru->node) + return; + + memcg_get_cache_ids(); + + list_lru_unregister(lru); + + memcg_destroy_list_lru(lru); kfree(lru->node); + lru->node = NULL; + + memcg_put_cache_ids(); } EXPORT_SYMBOL_GPL(list_lru_destroy); diff --git a/mm/madvise.c b/mm/madvise.c index a271adc93289..d551475517bf 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -155,7 +155,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, pte = *(orig_pte + ((index - start) / PAGE_SIZE)); pte_unmap_unlock(orig_pte, ptl); - if (pte_present(pte) || pte_none(pte) || pte_file(pte)) + if (pte_present(pte) || pte_none(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) @@ -222,21 +222,24 @@ static long madvise_willneed(struct vm_area_struct *vma, struct file *file = vma->vm_file; #ifdef CONFIG_SWAP - if (!file || mapping_cap_swap_backed(file->f_mapping)) { + if (!file) { *prev = vma; - if (!file) - force_swapin_readahead(vma, start, end); - else - force_shm_swapin_readahead(vma, start, end, - file->f_mapping); + force_swapin_readahead(vma, start, end); return 0; } -#endif + if (shmem_mapping(file->f_mapping)) { + *prev = vma; + force_shm_swapin_readahead(vma, start, end, + file->f_mapping); + return 0; + } +#else if (!file) return -EBADF; +#endif - if (file->f_mapping->a_ops->get_xip_mem) { + if (IS_DAX(file_inode(file))) { /* no bad return value, but ignore advice */ return 0; } @@ -278,14 +281,7 @@ static long madvise_dontneed(struct vm_area_struct *vma, if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) return -EINVAL; - if (unlikely(vma->vm_flags & VM_NONLINEAR)) { - struct zap_details details = { - .nonlinear_vma = vma, - .last_index = ULONG_MAX, - }; - zap_page_range(vma, start, end - start, &details); - } else - zap_page_range(vma, start, end - start, NULL); + zap_page_range(vma, start, end - start, NULL); return 0; } @@ -303,7 +299,7 @@ static long madvise_remove(struct vm_area_struct *vma, *prev = NULL; /* tell sys_madvise we drop mmap_sem */ - if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB)) + if (vma->vm_flags & (VM_LOCKED | VM_HUGETLB)) return -EINVAL; f = vma->vm_file; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 683b4782019b..d18d3a6e7337 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -72,22 +72,13 @@ EXPORT_SYMBOL(memory_cgrp_subsys); #define MEM_CGROUP_RECLAIM_RETRIES 5 static struct mem_cgroup *root_mem_cgroup __read_mostly; +/* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP -/* Turned on only when memory cgroup is enabled && really_do_swap_account = 1 */ int do_swap_account __read_mostly; - -/* for remember boot option*/ -#ifdef CONFIG_MEMCG_SWAP_ENABLED -static int really_do_swap_account __initdata = 1; -#else -static int really_do_swap_account __initdata; -#endif - #else #define do_swap_account 0 #endif - static const char * const mem_cgroup_stat_names[] = { "cache", "rss", @@ -97,14 +88,6 @@ static const char * const mem_cgroup_stat_names[] = { "swap", }; -enum mem_cgroup_events_index { - MEM_CGROUP_EVENTS_PGPGIN, /* # of pages paged in */ - MEM_CGROUP_EVENTS_PGPGOUT, /* # of pages paged out */ - MEM_CGROUP_EVENTS_PGFAULT, /* # of page-faults */ - MEM_CGROUP_EVENTS_PGMAJFAULT, /* # of major page-faults */ - MEM_CGROUP_EVENTS_NSTATS, -}; - static const char * const mem_cgroup_events_names[] = { "pgpgin", "pgpgout", @@ -138,7 +121,7 @@ enum mem_cgroup_events_target { struct mem_cgroup_stat_cpu { long count[MEM_CGROUP_STAT_NSTATS]; - unsigned long events[MEM_CGROUP_EVENTS_NSTATS]; + unsigned long events[MEMCG_NR_EVENTS]; unsigned long nr_page_events; unsigned long targets[MEM_CGROUP_NTARGETS]; }; @@ -284,6 +267,10 @@ struct mem_cgroup { struct page_counter memsw; struct page_counter kmem; + /* Normal memory consumption range */ + unsigned long low; + unsigned long high; + unsigned long soft_limit; /* vmpressure notifications */ @@ -325,9 +312,11 @@ struct mem_cgroup { /* * set > 0 if pages under this cgroup are moving to other cgroup. */ - atomic_t moving_account; + atomic_t moving_account; /* taken only while moving_account > 0 */ - spinlock_t move_lock; + spinlock_t move_lock; + struct task_struct *move_lock_task; + unsigned long move_lock_flags; /* * percpu counter. */ @@ -343,11 +332,10 @@ struct mem_cgroup { struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list, but per-memcg; - * protected by memcg_slab_mutex */ - struct list_head memcg_slab_caches; - /* Index in the kmem_cache->memcg_params->memcg_caches array */ + /* Index in the kmem_cache->memcg_params.memcg_caches array */ int kmemcg_id; + bool kmem_acct_activated; + bool kmem_acct_active; #endif int last_scanned_node; @@ -366,29 +354,26 @@ struct mem_cgroup { }; #ifdef CONFIG_MEMCG_KMEM -static bool memcg_kmem_is_active(struct mem_cgroup *memcg) +bool memcg_kmem_is_active(struct mem_cgroup *memcg) { - return memcg->kmemcg_id >= 0; + return memcg->kmem_acct_active; } #endif /* Stuffs for move charges at task migration. */ /* - * Types of charges to be moved. "move_charge_at_immitgrate" and - * "immigrate_flags" are treated as a left-shifted bitmap of these types. + * Types of charges to be moved. */ -enum move_type { - MOVE_CHARGE_TYPE_ANON, /* private anonymous page and swap of it */ - MOVE_CHARGE_TYPE_FILE, /* file page(including tmpfs) and swap of it */ - NR_MOVE_TYPE, -}; +#define MOVE_ANON 0x1U +#define MOVE_FILE 0x2U +#define MOVE_MASK (MOVE_ANON | MOVE_FILE) /* "mc" and its members are protected by cgroup_mutex */ static struct move_charge_struct { spinlock_t lock; /* for from, to */ struct mem_cgroup *from; struct mem_cgroup *to; - unsigned long immigrate_flags; + unsigned long flags; unsigned long precharge; unsigned long moved_charge; unsigned long moved_swap; @@ -399,16 +384,6 @@ static struct move_charge_struct { .waitq = __WAIT_QUEUE_HEAD_INITIALIZER(mc.waitq), }; -static bool move_anon(void) -{ - return test_bit(MOVE_CHARGE_TYPE_ANON, &mc.immigrate_flags); -} - -static bool move_file(void) -{ - return test_bit(MOVE_CHARGE_TYPE_FILE, &mc.immigrate_flags); -} - /* * Maximum loops in mem_cgroup_hierarchical_reclaim(), used for soft * limit reclaim to prevent infinite loops, if they ever occur. @@ -544,33 +519,35 @@ struct cg_proto *tcp_proto_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(tcp_proto_cgroup); -static void disarm_sock_keys(struct mem_cgroup *memcg) -{ - if (!memcg_proto_activated(&memcg->tcp_mem)) - return; - static_key_slow_dec(&memcg_socket_limit_enabled); -} -#else -static void disarm_sock_keys(struct mem_cgroup *memcg) -{ -} #endif #ifdef CONFIG_MEMCG_KMEM /* - * This will be the memcg's index in each cache's ->memcg_params->memcg_caches. + * This will be the memcg's index in each cache's ->memcg_params.memcg_caches. * The main reason for not using cgroup id for this: * this works better in sparse environments, where we have a lot of memcgs, * but only a few kmem-limited. Or also, if we have, for instance, 200 * memcgs, and none but the 200th is kmem-limited, we'd have to have a * 200 entry array for that. * - * The current size of the caches array is stored in - * memcg_limited_groups_array_size. It will double each time we have to - * increase it. + * The current size of the caches array is stored in memcg_nr_cache_ids. It + * will double each time we have to increase it. */ -static DEFINE_IDA(kmem_limited_groups); -int memcg_limited_groups_array_size; +static DEFINE_IDA(memcg_cache_ida); +int memcg_nr_cache_ids; + +/* Protects memcg_nr_cache_ids */ +static DECLARE_RWSEM(memcg_cache_ids_sem); + +void memcg_get_cache_ids(void) +{ + down_read(&memcg_cache_ids_sem); +} + +void memcg_put_cache_ids(void) +{ + up_read(&memcg_cache_ids_sem); +} /* * MIN_SIZE is different than 1, because we would like to avoid going through @@ -596,32 +573,8 @@ int memcg_limited_groups_array_size; struct static_key memcg_kmem_enabled_key; EXPORT_SYMBOL(memcg_kmem_enabled_key); -static void memcg_free_cache_id(int id); - -static void disarm_kmem_keys(struct mem_cgroup *memcg) -{ - if (memcg_kmem_is_active(memcg)) { - static_key_slow_dec(&memcg_kmem_enabled_key); - memcg_free_cache_id(memcg->kmemcg_id); - } - /* - * This check can't live in kmem destruction function, - * since the charges will outlive the cgroup - */ - WARN_ON(page_counter_read(&memcg->kmem)); -} -#else -static void disarm_kmem_keys(struct mem_cgroup *memcg) -{ -} #endif /* CONFIG_MEMCG_KMEM */ -static void disarm_static_keys(struct mem_cgroup *memcg) -{ - disarm_sock_keys(memcg); - disarm_kmem_keys(memcg); -} - static struct mem_cgroup_per_zone * mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) { @@ -1368,6 +1321,20 @@ int mem_cgroup_inactive_anon_is_low(struct lruvec *lruvec) return inactive * inactive_ratio < active; } +bool mem_cgroup_lruvec_online(struct lruvec *lruvec) +{ + struct mem_cgroup_per_zone *mz; + struct mem_cgroup *memcg; + + if (mem_cgroup_disabled()) + return true; + + mz = container_of(lruvec, struct mem_cgroup_per_zone, lruvec); + memcg = mz->memcg; + + return !!(memcg->css.flags & CSS_ONLINE); +} + #define mem_cgroup_from_counter(counter, member) \ container_of(counter, struct mem_cgroup, member) @@ -1560,7 +1527,7 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, * quickly exit and free its memory. */ if (fatal_signal_pending(current) || task_will_free_mem(current)) { - set_thread_flag(TIF_MEMDIE); + mark_tsk_oom_victim(current); return; } @@ -1934,7 +1901,7 @@ bool mem_cgroup_oom_synchronize(bool handle) if (!memcg) return false; - if (!handle) + if (!handle || oom_killer_disabled) goto cleanup; owait.memcg = memcg; @@ -1980,34 +1947,33 @@ cleanup: /** * mem_cgroup_begin_page_stat - begin a page state statistics transaction * @page: page that is going to change accounted state - * @locked: &memcg->move_lock slowpath was taken - * @flags: IRQ-state flags for &memcg->move_lock * * This function must mark the beginning of an accounted page state * change to prevent double accounting when the page is concurrently * being moved to another memcg: * - * memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + * memcg = mem_cgroup_begin_page_stat(page); * if (TestClearPageState(page)) * mem_cgroup_update_page_stat(memcg, state, -1); - * mem_cgroup_end_page_stat(memcg, locked, flags); - * - * The RCU lock is held throughout the transaction. The fast path can - * get away without acquiring the memcg->move_lock (@locked is false) - * because page moving starts with an RCU grace period. - * - * The RCU lock also protects the memcg from being freed when the page - * state that is going to change is the only thing preventing the page - * from being uncharged. E.g. end-writeback clearing PageWriteback(), - * which allows migration to go ahead and uncharge the page before the - * account transaction might be complete. + * mem_cgroup_end_page_stat(memcg); */ -struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page, - bool *locked, - unsigned long *flags) +struct mem_cgroup *mem_cgroup_begin_page_stat(struct page *page) { struct mem_cgroup *memcg; + unsigned long flags; + /* + * The RCU lock is held throughout the transaction. The fast + * path can get away without acquiring the memcg->move_lock + * because page moving starts with an RCU grace period. + * + * The RCU lock also protects the memcg from being freed when + * the page state that is going to change is the only thing + * preventing the page from being uncharged. + * E.g. end-writeback clearing PageWriteback(), which allows + * migration to go ahead and uncharge the page before the + * account transaction might be complete. + */ rcu_read_lock(); if (mem_cgroup_disabled()) @@ -2017,16 +1983,22 @@ again: if (unlikely(!memcg)) return NULL; - *locked = false; if (atomic_read(&memcg->moving_account) <= 0) return memcg; - spin_lock_irqsave(&memcg->move_lock, *flags); + spin_lock_irqsave(&memcg->move_lock, flags); if (memcg != page->mem_cgroup) { - spin_unlock_irqrestore(&memcg->move_lock, *flags); + spin_unlock_irqrestore(&memcg->move_lock, flags); goto again; } - *locked = true; + + /* + * When charge migration first begins, we can have locked and + * unlocked page stat updates happening concurrently. Track + * the task who has the lock for mem_cgroup_end_page_stat(). + */ + memcg->move_lock_task = current; + memcg->move_lock_flags = flags; return memcg; } @@ -2034,14 +2006,17 @@ again: /** * mem_cgroup_end_page_stat - finish a page state statistics transaction * @memcg: the memcg that was accounted against - * @locked: value received from mem_cgroup_begin_page_stat() - * @flags: value received from mem_cgroup_begin_page_stat() */ -void mem_cgroup_end_page_stat(struct mem_cgroup *memcg, bool *locked, - unsigned long *flags) +void mem_cgroup_end_page_stat(struct mem_cgroup *memcg) { - if (memcg && *locked) - spin_unlock_irqrestore(&memcg->move_lock, *flags); + if (memcg && memcg->move_lock_task == current) { + unsigned long flags = memcg->move_lock_flags; + + memcg->move_lock_task = NULL; + memcg->move_lock_flags = 0; + + spin_unlock_irqrestore(&memcg->move_lock, flags); + } rcu_read_unlock(); } @@ -2134,17 +2109,6 @@ static void drain_local_stock(struct work_struct *dummy) clear_bit(FLUSHING_CACHED_CHARGE, &stock->flags); } -static void __init memcg_stock_init(void) -{ - int cpu; - - for_each_possible_cpu(cpu) { - struct memcg_stock_pcp *stock = - &per_cpu(memcg_stock, cpu); - INIT_WORK(&stock->work, drain_local_stock); - } -} - /* * Cache charges(val) to local per_cpu area. * This will be consumed by consume_stock() function, later. @@ -2294,6 +2258,8 @@ retry: if (!(gfp_mask & __GFP_WAIT)) goto nomem; + mem_cgroup_events(mem_over_limit, MEMCG_MAX, 1); + nr_reclaimed = try_to_free_mem_cgroup_pages(mem_over_limit, nr_pages, gfp_mask, may_swap); @@ -2335,6 +2301,8 @@ retry: if (fatal_signal_pending(current)) goto bypass; + mem_cgroup_events(mem_over_limit, MEMCG_OOM, 1); + mem_cgroup_oom(mem_over_limit, gfp_mask, get_order(nr_pages)); nomem: if (!(gfp_mask & __GFP_NOFAIL)) @@ -2346,6 +2314,16 @@ done_restock: css_get_many(&memcg->css, batch); if (batch > nr_pages) refill_stock(memcg, batch - nr_pages); + /* + * If the hierarchy is above the normal consumption range, + * make the charging task trim their excess contribution. + */ + do { + if (page_counter_read(&memcg->memory) <= memcg->high) + continue; + mem_cgroup_events(memcg, MEMCG_HIGH, 1); + try_to_free_mem_cgroup_pages(memcg, nr_pages, gfp_mask, true); + } while ((memcg = parent_mem_cgroup(memcg))); done: return ret; } @@ -2476,27 +2454,8 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, } #ifdef CONFIG_MEMCG_KMEM -/* - * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or - * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. - */ -static DEFINE_MUTEX(memcg_slab_mutex); - -/* - * This is a bit cumbersome, but it is rarely used and avoids a backpointer - * in the memcg_cache_params struct. - */ -static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) -{ - struct kmem_cache *cachep; - - VM_BUG_ON(p->is_root_cache); - cachep = p->root_cache; - return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg)); -} - -static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, - unsigned long nr_pages) +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, + unsigned long nr_pages) { struct page_counter *counter; int ret = 0; @@ -2533,8 +2492,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, return ret; } -static void memcg_uncharge_kmem(struct mem_cgroup *memcg, - unsigned long nr_pages) +void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages) { page_counter_uncharge(&memcg->memory, nr_pages); if (do_swap_account) @@ -2560,18 +2518,19 @@ static int memcg_alloc_cache_id(void) int id, size; int err; - id = ida_simple_get(&kmem_limited_groups, + id = ida_simple_get(&memcg_cache_ida, 0, MEMCG_CACHES_MAX_SIZE, GFP_KERNEL); if (id < 0) return id; - if (id < memcg_limited_groups_array_size) + if (id < memcg_nr_cache_ids) return id; /* * There's no space for the new id in memcg_caches arrays, * so we have to grow them. */ + down_write(&memcg_cache_ids_sem); size = 2 * (id + 1); if (size < MEMCG_CACHES_MIN_SIZE) @@ -2579,12 +2538,16 @@ static int memcg_alloc_cache_id(void) else if (size > MEMCG_CACHES_MAX_SIZE) size = MEMCG_CACHES_MAX_SIZE; - mutex_lock(&memcg_slab_mutex); err = memcg_update_all_caches(size); - mutex_unlock(&memcg_slab_mutex); + if (!err) + err = memcg_update_all_list_lrus(size); + if (!err) + memcg_nr_cache_ids = size; + + up_write(&memcg_cache_ids_sem); if (err) { - ida_simple_remove(&kmem_limited_groups, id); + ida_simple_remove(&memcg_cache_ida, id); return err; } return id; @@ -2592,136 +2555,23 @@ static int memcg_alloc_cache_id(void) static void memcg_free_cache_id(int id) { - ida_simple_remove(&kmem_limited_groups, id); + ida_simple_remove(&memcg_cache_ida, id); } -/* - * We should update the current array size iff all caches updates succeed. This - * can only be done from the slab side. The slab mutex needs to be held when - * calling this. - */ -void memcg_update_array_size(int num) -{ - memcg_limited_groups_array_size = num; -} - -static void memcg_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) -{ - static char memcg_name_buf[NAME_MAX + 1]; /* protected by - memcg_slab_mutex */ - struct kmem_cache *cachep; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - id = memcg_cache_id(memcg); - - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can try to - * create the same cache, but only one of them may succeed. - */ - if (cache_from_memcg_idx(root_cache, id)) - return; - - cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); - cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); - /* - * If we could not create a memcg cache, do not complain, because - * that's not critical at all as we can always proceed with the root - * cache. - */ - if (!cachep) - return; - - list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); - - /* - * Since readers won't lock (see cache_from_memcg_idx()), we need a - * barrier here to ensure nobody will see the kmem_cache partially - * initialized. - */ - smp_wmb(); - - BUG_ON(root_cache->memcg_params->memcg_caches[id]); - root_cache->memcg_params->memcg_caches[id] = cachep; -} - -static void memcg_unregister_cache(struct kmem_cache *cachep) -{ - struct kmem_cache *root_cache; - struct mem_cgroup *memcg; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - BUG_ON(is_root_cache(cachep)); - - root_cache = cachep->memcg_params->root_cache; - memcg = cachep->memcg_params->memcg; - id = memcg_cache_id(memcg); - - BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); - root_cache->memcg_params->memcg_caches[id] = NULL; - - list_del(&cachep->memcg_params->list); - - kmem_cache_destroy(cachep); -} - -int __memcg_cleanup_cache_params(struct kmem_cache *s) -{ - struct kmem_cache *c; - int i, failed = 0; - - mutex_lock(&memcg_slab_mutex); - for_each_memcg_cache_index(i) { - c = cache_from_memcg_idx(s, i); - if (!c) - continue; - - memcg_unregister_cache(c); - - if (cache_from_memcg_idx(s, i)) - failed++; - } - mutex_unlock(&memcg_slab_mutex); - return failed; -} - -static void memcg_unregister_all_caches(struct mem_cgroup *memcg) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *params, *tmp; - - if (!memcg_kmem_is_active(memcg)) - return; - - mutex_lock(&memcg_slab_mutex); - list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { - cachep = memcg_params_to_cache(params); - memcg_unregister_cache(cachep); - } - mutex_unlock(&memcg_slab_mutex); -} - -struct memcg_register_cache_work { +struct memcg_kmem_cache_create_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void memcg_register_cache_func(struct work_struct *w) +static void memcg_kmem_cache_create_func(struct work_struct *w) { - struct memcg_register_cache_work *cw = - container_of(w, struct memcg_register_cache_work, work); + struct memcg_kmem_cache_create_work *cw = + container_of(w, struct memcg_kmem_cache_create_work, work); struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; - mutex_lock(&memcg_slab_mutex); - memcg_register_cache(memcg, cachep); - mutex_unlock(&memcg_slab_mutex); + memcg_create_kmem_cache(memcg, cachep); css_put(&memcg->css); kfree(cw); @@ -2730,10 +2580,10 @@ static void memcg_register_cache_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct memcg_register_cache_work *cw; + struct memcg_kmem_cache_create_work *cw; cw = kmalloc(sizeof(*cw), GFP_NOWAIT); if (!cw) @@ -2743,18 +2593,18 @@ static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, cw->memcg = memcg; cw->cachep = cachep; + INIT_WORK(&cw->work, memcg_kmem_cache_create_func); - INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_schedule_register_cache will recurse. + * in __memcg_schedule_kmem_cache_create will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -2763,24 +2613,10 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ current->memcg_kmem_skip_account = 1; - __memcg_schedule_register_cache(memcg, cachep); + __memcg_schedule_kmem_cache_create(memcg, cachep); current->memcg_kmem_skip_account = 0; } -int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) -{ - unsigned int nr_pages = 1 << order; - - return memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages); -} - -void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) -{ - unsigned int nr_pages = 1 << order; - - memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages); -} - /* * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. @@ -2798,18 +2634,19 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) { struct mem_cgroup *memcg; struct kmem_cache *memcg_cachep; + int kmemcg_id; - VM_BUG_ON(!cachep->memcg_params); - VM_BUG_ON(!cachep->memcg_params->is_root_cache); + VM_BUG_ON(!is_root_cache(cachep)); if (current->memcg_kmem_skip_account) return cachep; memcg = get_mem_cgroup_from_mm(current->mm); - if (!memcg_kmem_is_active(memcg)) + kmemcg_id = ACCESS_ONCE(memcg->kmemcg_id); + if (kmemcg_id < 0) goto out; - memcg_cachep = cache_from_memcg_idx(cachep, memcg_cache_id(memcg)); + memcg_cachep = cache_from_memcg_idx(cachep, kmemcg_id); if (likely(memcg_cachep)) return memcg_cachep; @@ -2825,7 +2662,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) * could happen with the slab_mutex held. So it's better to * defer everything. */ - memcg_schedule_register_cache(memcg, cachep); + memcg_schedule_kmem_cache_create(memcg, cachep); out: css_put(&memcg->css); return cachep; @@ -2834,7 +2671,7 @@ out: void __memcg_kmem_put_cache(struct kmem_cache *cachep) { if (!is_root_cache(cachep)) - css_put(&cachep->memcg_params->memcg->css); + css_put(&cachep->memcg_params.memcg->css); } /* @@ -2899,6 +2736,24 @@ void __memcg_kmem_uncharge_pages(struct page *page, int order) memcg_uncharge_kmem(memcg, 1 << order); page->mem_cgroup = NULL; } + +struct mem_cgroup *__mem_cgroup_from_kmem(void *ptr) +{ + struct mem_cgroup *memcg = NULL; + struct kmem_cache *cachep; + struct page *page; + + page = virt_to_head_page(ptr); + if (PageSlab(page)) { + cachep = page->slab_cache; + if (!is_root_cache(cachep)) + memcg = cachep->memcg_params.memcg; + } else + /* page allocated by alloc_kmem_pages */ + memcg = page->mem_cgroup; + + return memcg; +} #endif /* CONFIG_MEMCG_KMEM */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -3433,8 +3288,9 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg, int err = 0; int memcg_id; - if (memcg_kmem_is_active(memcg)) - return 0; + BUG_ON(memcg->kmemcg_id >= 0); + BUG_ON(memcg->kmem_acct_activated); + BUG_ON(memcg->kmem_acct_active); /* * For simplicity, we won't allow this to be disabled. It also can't @@ -3477,6 +3333,8 @@ static int memcg_activate_kmem(struct mem_cgroup *memcg, * patched. */ memcg->kmemcg_id = memcg_id; + memcg->kmem_acct_activated = true; + memcg->kmem_acct_active = true; out: return err; } @@ -3533,7 +3391,7 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, int ret; buf = strstrip(buf); - ret = page_counter_memparse(buf, &nr_pages); + ret = page_counter_memparse(buf, "-1", &nr_pages); if (ret) return ret; @@ -3609,7 +3467,7 @@ static int mem_cgroup_move_charge_write(struct cgroup_subsys_state *css, { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - if (val >= (1 << NR_MOVE_TYPE)) + if (val & ~MOVE_MASK) return -EINVAL; /* @@ -3687,6 +3545,10 @@ static int memcg_stat_show(struct seq_file *m, void *v) struct mem_cgroup *mi; unsigned int i; + BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_stat_names) != + MEM_CGROUP_STAT_NSTATS); + BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_events_names) != + MEM_CGROUP_EVENTS_NSTATS); BUILD_BUG_ON(ARRAY_SIZE(mem_cgroup_lru_names) != NR_LRU_LISTS); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { @@ -3901,7 +3763,7 @@ static int __mem_cgroup_usage_register_event(struct mem_cgroup *memcg, unsigned long usage; int i, size, ret; - ret = page_counter_memparse(args, &threshold); + ret = page_counter_memparse(args, "-1", &threshold); if (ret) return ret; @@ -4152,9 +4014,59 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) return mem_cgroup_sockets_init(memcg, ss); } +static void memcg_deactivate_kmem(struct mem_cgroup *memcg) +{ + struct cgroup_subsys_state *css; + struct mem_cgroup *parent, *child; + int kmemcg_id; + + if (!memcg->kmem_acct_active) + return; + + /* + * Clear the 'active' flag before clearing memcg_caches arrays entries. + * Since we take the slab_mutex in memcg_deactivate_kmem_caches(), it + * guarantees no cache will be created for this cgroup after we are + * done (see memcg_create_kmem_cache()). + */ + memcg->kmem_acct_active = false; + + memcg_deactivate_kmem_caches(memcg); + + kmemcg_id = memcg->kmemcg_id; + BUG_ON(kmemcg_id < 0); + + parent = parent_mem_cgroup(memcg); + if (!parent) + parent = root_mem_cgroup; + + /* + * Change kmemcg_id of this cgroup and all its descendants to the + * parent's id, and then move all entries from this cgroup's list_lrus + * to ones of the parent. After we have finished, all list_lrus + * corresponding to this cgroup are guaranteed to remain empty. The + * ordering is imposed by list_lru_node->lock taken by + * memcg_drain_all_list_lrus(). + */ + css_for_each_descendant_pre(css, &memcg->css) { + child = mem_cgroup_from_css(css); + BUG_ON(child->kmemcg_id != kmemcg_id); + child->kmemcg_id = parent->kmemcg_id; + if (!memcg->use_hierarchy) + break; + } + memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id); + + memcg_free_cache_id(kmemcg_id); +} + static void memcg_destroy_kmem(struct mem_cgroup *memcg) { - memcg_unregister_all_caches(memcg); + if (memcg->kmem_acct_activated) { + memcg_destroy_kmem_caches(memcg); + static_key_slow_dec(&memcg_kmem_enabled_key); + WARN_ON(page_counter_read(&memcg->kmem)); + } mem_cgroup_sockets_destroy(memcg); } #else @@ -4163,6 +4075,10 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) return 0; } +static void memcg_deactivate_kmem(struct mem_cgroup *memcg) +{ +} + static void memcg_destroy_kmem(struct mem_cgroup *memcg) { } @@ -4391,7 +4307,7 @@ out_kfree: return ret; } -static struct cftype mem_cgroup_files[] = { +static struct cftype mem_cgroup_legacy_files[] = { { .name = "usage_in_bytes", .private = MEMFILE_PRIVATE(_MEM, RES_USAGE), @@ -4502,34 +4418,6 @@ static struct cftype mem_cgroup_files[] = { { }, /* terminate */ }; -#ifdef CONFIG_MEMCG_SWAP -static struct cftype memsw_cgroup_files[] = { - { - .name = "memsw.usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "memsw.max_usage_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "memsw.limit_in_bytes", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), - .write = mem_cgroup_write, - .read_u64 = mem_cgroup_read_u64, - }, - { - .name = "memsw.failcnt", - .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), - .write = mem_cgroup_reset, - .read_u64 = mem_cgroup_read_u64, - }, - { }, /* terminate */ -}; -#endif static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; @@ -4609,8 +4497,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) free_mem_cgroup_per_zone_info(memcg, node); free_percpu(memcg->stat); - - disarm_static_keys(memcg); kfree(memcg); } @@ -4625,29 +4511,6 @@ struct mem_cgroup *parent_mem_cgroup(struct mem_cgroup *memcg) } EXPORT_SYMBOL(parent_mem_cgroup); -static void __init mem_cgroup_soft_limit_tree_init(void) -{ - struct mem_cgroup_tree_per_node *rtpn; - struct mem_cgroup_tree_per_zone *rtpz; - int tmp, node, zone; - - for_each_node(node) { - tmp = node; - if (!node_state(node, N_NORMAL_MEMORY)) - tmp = -1; - rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, tmp); - BUG_ON(!rtpn); - - soft_limit_tree.rb_tree_per_node[node] = rtpn; - - for (zone = 0; zone < MAX_NR_ZONES; zone++) { - rtpz = &rtpn->rb_tree_per_zone[zone]; - rtpz->rb_root = RB_ROOT; - spin_lock_init(&rtpz->lock); - } - } -} - static struct cgroup_subsys_state * __ref mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { @@ -4667,6 +4530,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (parent_css == NULL) { root_mem_cgroup = memcg; page_counter_init(&memcg->memory, NULL); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); @@ -4682,7 +4546,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) spin_lock_init(&memcg->event_list_lock); #ifdef CONFIG_MEMCG_KMEM memcg->kmemcg_id = -1; - INIT_LIST_HEAD(&memcg->memcg_slab_caches); #endif return &memcg->css; @@ -4713,6 +4576,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) if (parent->use_hierarchy) { page_counter_init(&memcg->memory, &parent->memory); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, &parent->memsw); page_counter_init(&memcg->kmem, &parent->kmem); @@ -4723,6 +4587,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) */ } else { page_counter_init(&memcg->memory, NULL); + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); @@ -4768,6 +4633,8 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) spin_unlock(&memcg->event_list_lock); vmpressure_cleanup(&memcg->vmpressure); + + memcg_deactivate_kmem(memcg); } static void mem_cgroup_css_free(struct cgroup_subsys_state *css) @@ -4798,6 +4665,8 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX); mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX); memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX); + memcg->low = 0; + memcg->high = PAGE_COUNTER_MAX; memcg->soft_limit = PAGE_COUNTER_MAX; } @@ -4874,12 +4743,12 @@ static struct page *mc_handle_present_pte(struct vm_area_struct *vma, if (!page || !page_mapped(page)) return NULL; if (PageAnon(page)) { - /* we don't move shared anon */ - if (!move_anon()) + if (!(mc.flags & MOVE_ANON)) return NULL; - } else if (!move_file()) - /* we ignore mapcount for file pages */ - return NULL; + } else { + if (!(mc.flags & MOVE_FILE)) + return NULL; + } if (!get_page_unless_zero(page)) return NULL; @@ -4893,7 +4762,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, struct page *page = NULL; swp_entry_t ent = pte_to_swp_entry(ptent); - if (!move_anon() || non_swap_entry(ent)) + if (!(mc.flags & MOVE_ANON) || non_swap_entry(ent)) return NULL; /* * Because lookup_swap_cache() updates some statistics counter, @@ -4922,14 +4791,11 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, if (!vma->vm_file) /* anonymous vma */ return NULL; - if (!move_file()) + if (!(mc.flags & MOVE_FILE)) return NULL; mapping = vma->vm_file->f_mapping; - if (pte_none(ptent)) - pgoff = linear_page_index(vma, addr); - else /* pte_file(ptent) is true */ - pgoff = pte_to_pgoff(ptent); + pgoff = linear_page_index(vma, addr); /* page is moved even if it's not RSS of this task(page-faulted). */ #ifdef CONFIG_SWAP @@ -4961,7 +4827,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, page = mc_handle_present_pte(vma, addr, ptent); else if (is_swap_pte(ptent)) page = mc_handle_swap_pte(vma, addr, ptent, &ent); - else if (pte_none(ptent) || pte_file(ptent)) + else if (pte_none(ptent)) page = mc_handle_file_pte(vma, addr, ptent, &ent); if (!page && !ent.val) @@ -5004,7 +4870,7 @@ static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, page = pmd_page(pmd); VM_BUG_ON_PAGE(!page || !PageHead(page), page); - if (!move_anon()) + if (!(mc.flags & MOVE_ANON)) return ret; if (page->mem_cgroup == mc.from) { ret = MC_TARGET_PAGE; @@ -5027,7 +4893,7 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) { - struct vm_area_struct *vma = walk->private; + struct vm_area_struct *vma = walk->vma; pte_t *pte; spinlock_t *ptl; @@ -5053,20 +4919,13 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, static unsigned long mem_cgroup_count_precharge(struct mm_struct *mm) { unsigned long precharge; - struct vm_area_struct *vma; + struct mm_walk mem_cgroup_count_precharge_walk = { + .pmd_entry = mem_cgroup_count_precharge_pte_range, + .mm = mm, + }; down_read(&mm->mmap_sem); - for (vma = mm->mmap; vma; vma = vma->vm_next) { - struct mm_walk mem_cgroup_count_precharge_walk = { - .pmd_entry = mem_cgroup_count_precharge_pte_range, - .mm = mm, - .private = vma, - }; - if (is_vm_hugetlb_page(vma)) - continue; - walk_page_range(vma->vm_start, vma->vm_end, - &mem_cgroup_count_precharge_walk); - } + walk_page_range(0, ~0UL, &mem_cgroup_count_precharge_walk); up_read(&mm->mmap_sem); precharge = mc.precharge; @@ -5146,15 +5005,15 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, struct task_struct *p = cgroup_taskset_first(tset); int ret = 0; struct mem_cgroup *memcg = mem_cgroup_from_css(css); - unsigned long move_charge_at_immigrate; + unsigned long move_flags; /* * We are now commited to this value whatever it is. Changes in this * tunable will only affect upcoming migrations, not the current one. * So we need to save it, and keep it going. */ - move_charge_at_immigrate = memcg->move_charge_at_immigrate; - if (move_charge_at_immigrate) { + move_flags = ACCESS_ONCE(memcg->move_charge_at_immigrate); + if (move_flags) { struct mm_struct *mm; struct mem_cgroup *from = mem_cgroup_from_task(p); @@ -5174,7 +5033,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, spin_lock(&mc.lock); mc.from = from; mc.to = memcg; - mc.immigrate_flags = move_charge_at_immigrate; + mc.flags = move_flags; spin_unlock(&mc.lock); /* We set mc.moving_task later */ @@ -5199,7 +5058,7 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, struct mm_walk *walk) { int ret = 0; - struct vm_area_struct *vma = walk->private; + struct vm_area_struct *vma = walk->vma; pte_t *pte; spinlock_t *ptl; enum mc_target_type target_type; @@ -5295,7 +5154,10 @@ put: /* get_mctgt_type() gets the page */ static void mem_cgroup_move_charge(struct mm_struct *mm) { - struct vm_area_struct *vma; + struct mm_walk mem_cgroup_move_charge_walk = { + .pmd_entry = mem_cgroup_move_charge_pte_range, + .mm = mm, + }; lru_add_drain_all(); /* @@ -5318,24 +5180,11 @@ retry: cond_resched(); goto retry; } - for (vma = mm->mmap; vma; vma = vma->vm_next) { - int ret; - struct mm_walk mem_cgroup_move_charge_walk = { - .pmd_entry = mem_cgroup_move_charge_pte_range, - .mm = mm, - .private = vma, - }; - if (is_vm_hugetlb_page(vma)) - continue; - ret = walk_page_range(vma->vm_start, vma->vm_end, - &mem_cgroup_move_charge_walk); - if (ret) - /* - * means we have consumed all precharges and failed in - * doing additional charge. Just abandon here. - */ - break; - } + /* + * When we have consumed all precharges and failed in doing + * additional charge, the page walk just aborts. + */ + walk_page_range(0, ~0UL, &mem_cgroup_move_charge_walk); up_read(&mm->mmap_sem); atomic_dec(&mc.from->moving_account); } @@ -5386,118 +5235,211 @@ static void mem_cgroup_bind(struct cgroup_subsys_state *root_css) mem_cgroup_from_css(root_css)->use_hierarchy = true; } -struct cgroup_subsys memory_cgrp_subsys = { - .css_alloc = mem_cgroup_css_alloc, - .css_online = mem_cgroup_css_online, - .css_offline = mem_cgroup_css_offline, - .css_free = mem_cgroup_css_free, - .css_reset = mem_cgroup_css_reset, - .can_attach = mem_cgroup_can_attach, - .cancel_attach = mem_cgroup_cancel_attach, - .attach = mem_cgroup_move_task, - .bind = mem_cgroup_bind, - .legacy_cftypes = mem_cgroup_files, - .early_init = 0, -}; +static u64 memory_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + return mem_cgroup_usage(mem_cgroup_from_css(css), false); +} -#ifdef CONFIG_MEMCG_SWAP -static int __init enable_swap_account(char *s) +static int memory_low_show(struct seq_file *m, void *v) { - if (!strcmp(s, "1")) - really_do_swap_account = 1; - else if (!strcmp(s, "0")) - really_do_swap_account = 0; - return 1; + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long low = ACCESS_ONCE(memcg->low); + + if (low == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)low * PAGE_SIZE); + + return 0; } -__setup("swapaccount=", enable_swap_account); -static void __init memsw_file_init(void) +static ssize_t memory_low_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { - WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, - memsw_cgroup_files)); + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long low; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &low); + if (err) + return err; + + memcg->low = low; + + return nbytes; } -static void __init enable_swap_cgroup(void) +static int memory_high_show(struct seq_file *m, void *v) { - if (!mem_cgroup_disabled() && really_do_swap_account) { - do_swap_account = 1; - memsw_file_init(); - } + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long high = ACCESS_ONCE(memcg->high); + + if (high == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)high * PAGE_SIZE); + + return 0; } -#else -static void __init enable_swap_cgroup(void) +static ssize_t memory_high_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) { + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long high; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &high); + if (err) + return err; + + memcg->high = high; + + return nbytes; } -#endif -#ifdef CONFIG_MEMCG_SWAP -/** - * mem_cgroup_swapout - transfer a memsw charge to swap - * @page: page whose memsw charge to transfer - * @entry: swap entry to move the charge to - * - * Transfer the memsw charge of @page to @entry. - */ -void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +static int memory_max_show(struct seq_file *m, void *v) { - struct mem_cgroup *memcg; - unsigned short oldid; + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long max = ACCESS_ONCE(memcg->memory.limit); - VM_BUG_ON_PAGE(PageLRU(page), page); - VM_BUG_ON_PAGE(page_count(page), page); + if (max == PAGE_COUNTER_MAX) + seq_puts(m, "infinity\n"); + else + seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE); - if (!do_swap_account) - return; + return 0; +} - memcg = page->mem_cgroup; +static ssize_t memory_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long max; + int err; - /* Readahead page, never charged */ - if (!memcg) - return; + buf = strstrip(buf); + err = page_counter_memparse(buf, "infinity", &max); + if (err) + return err; - oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); - VM_BUG_ON_PAGE(oldid, page); - mem_cgroup_swap_statistics(memcg, true); + err = mem_cgroup_resize_limit(memcg, max); + if (err) + return err; - page->mem_cgroup = NULL; + return nbytes; +} - if (!mem_cgroup_is_root(memcg)) - page_counter_uncharge(&memcg->memory, 1); +static int memory_events_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); - /* XXX: caller holds IRQ-safe mapping->tree_lock */ - VM_BUG_ON(!irqs_disabled()); + seq_printf(m, "low %lu\n", mem_cgroup_read_events(memcg, MEMCG_LOW)); + seq_printf(m, "high %lu\n", mem_cgroup_read_events(memcg, MEMCG_HIGH)); + seq_printf(m, "max %lu\n", mem_cgroup_read_events(memcg, MEMCG_MAX)); + seq_printf(m, "oom %lu\n", mem_cgroup_read_events(memcg, MEMCG_OOM)); - mem_cgroup_charge_statistics(memcg, page, -1); - memcg_check_events(memcg, page); + return 0; } +static struct cftype memory_files[] = { + { + .name = "current", + .read_u64 = memory_current_read, + }, + { + .name = "low", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_low_show, + .write = memory_low_write, + }, + { + .name = "high", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_high_show, + .write = memory_high_write, + }, + { + .name = "max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_max_show, + .write = memory_max_write, + }, + { + .name = "events", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_events_show, + }, + { } /* terminate */ +}; + +struct cgroup_subsys memory_cgrp_subsys = { + .css_alloc = mem_cgroup_css_alloc, + .css_online = mem_cgroup_css_online, + .css_offline = mem_cgroup_css_offline, + .css_free = mem_cgroup_css_free, + .css_reset = mem_cgroup_css_reset, + .can_attach = mem_cgroup_can_attach, + .cancel_attach = mem_cgroup_cancel_attach, + .attach = mem_cgroup_move_task, + .bind = mem_cgroup_bind, + .dfl_cftypes = memory_files, + .legacy_cftypes = mem_cgroup_legacy_files, + .early_init = 0, +}; + /** - * mem_cgroup_uncharge_swap - uncharge a swap entry - * @entry: swap entry to uncharge + * mem_cgroup_events - count memory events against a cgroup + * @memcg: the memory cgroup + * @idx: the event index + * @nr: the number of events to account for + */ +void mem_cgroup_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx, + unsigned int nr) +{ + this_cpu_add(memcg->stat->events[idx], nr); +} + +/** + * mem_cgroup_low - check if memory consumption is below the normal range + * @root: the highest ancestor to consider + * @memcg: the memory cgroup to check * - * Drop the memsw charge associated with @entry. + * Returns %true if memory consumption of @memcg, and that of all + * configurable ancestors up to @root, is below the normal range. */ -void mem_cgroup_uncharge_swap(swp_entry_t entry) +bool mem_cgroup_low(struct mem_cgroup *root, struct mem_cgroup *memcg) { - struct mem_cgroup *memcg; - unsigned short id; + if (mem_cgroup_disabled()) + return false; - if (!do_swap_account) - return; + /* + * The toplevel group doesn't have a configurable range, so + * it's never low when looked at directly, and it is not + * considered an ancestor when assessing the hierarchy. + */ - id = swap_cgroup_record(entry, 0); - rcu_read_lock(); - memcg = mem_cgroup_lookup(id); - if (memcg) { - if (!mem_cgroup_is_root(memcg)) - page_counter_uncharge(&memcg->memsw, 1); - mem_cgroup_swap_statistics(memcg, false); - css_put(&memcg->css); + if (memcg == root_mem_cgroup) + return false; + + if (page_counter_read(&memcg->memory) > memcg->low) + return false; + + while (memcg != root) { + memcg = parent_mem_cgroup(memcg); + + if (memcg == root_mem_cgroup) + break; + + if (page_counter_read(&memcg->memory) > memcg->low) + return false; } - rcu_read_unlock(); + return true; } -#endif /** * mem_cgroup_try_charge - try charging a page @@ -5773,7 +5715,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) * mem_cgroup_migrate - migrate a charge to another page * @oldpage: currently charged page * @newpage: page to transfer the charge to - * @lrucare: both pages might be on the LRU already + * @lrucare: either or both pages might be on the LRU already * * Migrate the charge from @oldpage to @newpage. * @@ -5831,10 +5773,155 @@ void mem_cgroup_migrate(struct page *oldpage, struct page *newpage, */ static int __init mem_cgroup_init(void) { + int cpu, node; + hotcpu_notifier(memcg_cpu_hotplug_callback, 0); - enable_swap_cgroup(); - mem_cgroup_soft_limit_tree_init(); - memcg_stock_init(); + + for_each_possible_cpu(cpu) + INIT_WORK(&per_cpu_ptr(&memcg_stock, cpu)->work, + drain_local_stock); + + for_each_node(node) { + struct mem_cgroup_tree_per_node *rtpn; + int zone; + + rtpn = kzalloc_node(sizeof(*rtpn), GFP_KERNEL, + node_online(node) ? node : NUMA_NO_NODE); + + for (zone = 0; zone < MAX_NR_ZONES; zone++) { + struct mem_cgroup_tree_per_zone *rtpz; + + rtpz = &rtpn->rb_tree_per_zone[zone]; + rtpz->rb_root = RB_ROOT; + spin_lock_init(&rtpz->lock); + } + soft_limit_tree.rb_tree_per_node[node] = rtpn; + } + return 0; } subsys_initcall(mem_cgroup_init); + +#ifdef CONFIG_MEMCG_SWAP +/** + * mem_cgroup_swapout - transfer a memsw charge to swap + * @page: page whose memsw charge to transfer + * @entry: swap entry to move the charge to + * + * Transfer the memsw charge of @page to @entry. + */ +void mem_cgroup_swapout(struct page *page, swp_entry_t entry) +{ + struct mem_cgroup *memcg; + unsigned short oldid; + + VM_BUG_ON_PAGE(PageLRU(page), page); + VM_BUG_ON_PAGE(page_count(page), page); + + if (!do_swap_account) + return; + + memcg = page->mem_cgroup; + + /* Readahead page, never charged */ + if (!memcg) + return; + + oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); + VM_BUG_ON_PAGE(oldid, page); + mem_cgroup_swap_statistics(memcg, true); + + page->mem_cgroup = NULL; + + if (!mem_cgroup_is_root(memcg)) + page_counter_uncharge(&memcg->memory, 1); + + /* XXX: caller holds IRQ-safe mapping->tree_lock */ + VM_BUG_ON(!irqs_disabled()); + + mem_cgroup_charge_statistics(memcg, page, -1); + memcg_check_events(memcg, page); +} + +/** + * mem_cgroup_uncharge_swap - uncharge a swap entry + * @entry: swap entry to uncharge + * + * Drop the memsw charge associated with @entry. + */ +void mem_cgroup_uncharge_swap(swp_entry_t entry) +{ + struct mem_cgroup *memcg; + unsigned short id; + + if (!do_swap_account) + return; + + id = swap_cgroup_record(entry, 0); + rcu_read_lock(); + memcg = mem_cgroup_lookup(id); + if (memcg) { + if (!mem_cgroup_is_root(memcg)) + page_counter_uncharge(&memcg->memsw, 1); + mem_cgroup_swap_statistics(memcg, false); + css_put(&memcg->css); + } + rcu_read_unlock(); +} + +/* for remember boot option*/ +#ifdef CONFIG_MEMCG_SWAP_ENABLED +static int really_do_swap_account __initdata = 1; +#else +static int really_do_swap_account __initdata; +#endif + +static int __init enable_swap_account(char *s) +{ + if (!strcmp(s, "1")) + really_do_swap_account = 1; + else if (!strcmp(s, "0")) + really_do_swap_account = 0; + return 1; +} +__setup("swapaccount=", enable_swap_account); + +static struct cftype memsw_cgroup_files[] = { + { + .name = "memsw.usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_USAGE), + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_MAX_USAGE), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.limit_in_bytes", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "memsw.failcnt", + .private = MEMFILE_PRIVATE(_MEMSWAP, RES_FAILCNT), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { }, /* terminate */ +}; + +static int __init mem_cgroup_swap_init(void) +{ + if (!mem_cgroup_disabled() && really_do_swap_account) { + do_swap_account = 1; + WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, + memsw_cgroup_files)); + } + return 0; +} +subsys_initcall(mem_cgroup_swap_init); + +#endif /* CONFIG_MEMCG_SWAP */ diff --git a/mm/memory-failure.c b/mm/memory-failure.c index feb803bf3443..d487f8dc6d39 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -242,15 +242,8 @@ void shake_page(struct page *p, int access) * Only call shrink_node_slabs here (which would also shrink * other caches) if access is not potentially fatal. */ - if (access) { - int nr; - int nid = page_to_nid(p); - do { - nr = shrink_node_slabs(GFP_KERNEL, nid, 1000, 1000); - if (page_count(p) == 1) - break; - } while (nr > 10); - } + if (access) + drop_slab_node(page_to_nid(p)); } EXPORT_SYMBOL_GPL(shake_page); @@ -1654,8 +1647,6 @@ static int __soft_offline_page(struct page *page, int flags) * setting PG_hwpoison. */ if (!is_free_buddy_page(page)) - lru_add_drain_all(); - if (!is_free_buddy_page(page)) drain_all_pages(page_zone(page)); SetPageHWPoison(page); if (!is_free_buddy_page(page)) diff --git a/mm/memory.c b/mm/memory.c index 2c3536cc6c63..8068893697bb 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -428,6 +428,7 @@ static inline void free_pmd_range(struct mmu_gather *tlb, pud_t *pud, pmd = pmd_offset(pud, start); pud_clear(pud); pmd_free_tlb(tlb, pmd, start); + mm_dec_nr_pmds(tlb->mm); } static inline void free_pud_range(struct mmu_gather *tlb, pgd_t *pgd, @@ -754,6 +755,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, if (HAVE_PTE_SPECIAL) { if (likely(!pte_special(pte))) goto check_pfn; + if (vma->vm_ops && vma->vm_ops->find_special_page) + return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (!is_zero_pfn(pfn)) @@ -811,42 +814,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { - if (!pte_file(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + set_pte_at(src_mm, addr, src_pte, pte); } } goto out_set_pte; @@ -1020,11 +1021,9 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR | - VM_PFNMAP | VM_MIXEDMAP))) { - if (!vma->anon_vma) - return 0; - } + if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && + !vma->anon_vma) + return 0; if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); @@ -1082,6 +1081,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, spinlock_t *ptl; pte_t *start_pte; pte_t *pte; + swp_entry_t entry; again: init_rss_vec(rss); @@ -1107,28 +1107,12 @@ again: if (details->check_mapping && details->check_mapping != page->mapping) continue; - /* - * Each page->index must be checked when - * invalidating or truncating nonlinear. - */ - if (details->nonlinear_vma && - (page->index < details->first_index || - page->index > details->last_index)) - continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; - if (unlikely(details) && details->nonlinear_vma - && linear_page_index(details->nonlinear_vma, - addr) != page->index) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(ptent)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, addr, pte, ptfile); - } if (PageAnon(page)) rss[MM_ANONPAGES]--; else { @@ -1151,33 +1135,25 @@ again: } continue; } - /* - * If details->check_mapping, we leave swap entries; - * if details->nonlinear_vma, we leave file entries. - */ + /* If details->check_mapping, we leave swap entries. */ if (unlikely(details)) continue; - if (pte_file(ptent)) { - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) - print_bad_pte(vma, addr, ptent, NULL); - } else { - swp_entry_t entry = pte_to_swp_entry(ptent); - if (!non_swap_entry(entry)) - rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { - struct page *page; + entry = pte_to_swp_entry(ptent); + if (!non_swap_entry(entry)) + rss[MM_SWAPENTS]--; + else if (is_migration_entry(entry)) { + struct page *page; - page = migration_entry_to_page(entry); + page = migration_entry_to_page(entry); - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else - rss[MM_FILEPAGES]--; - } - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); + if (PageAnon(page)) + rss[MM_ANONPAGES]--; + else + rss[MM_FILEPAGES]--; } + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1277,7 +1253,7 @@ static void unmap_page_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; - if (details && !details->check_mapping && !details->nonlinear_vma) + if (details && !details->check_mapping) details = NULL; BUG_ON(addr >= end); @@ -1371,7 +1347,7 @@ void unmap_vmas(struct mmu_gather *tlb, * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * Caller must protect the VMA list */ @@ -1397,7 +1373,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * The range must fit into one VMA. */ @@ -1922,12 +1898,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, EXPORT_SYMBOL_GPL(apply_to_page_range); /* - * handle_pte_fault chooses page fault handler according to an entry - * which was read non-atomically. Before making any commitment, on - * those architectures or configurations (e.g. i386 with PAE) which - * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault - * must check under lock before unmapping the pte and proceeding - * (but do_wp_page is only called after already making such a check; + * handle_pte_fault chooses page fault handler according to an entry which was + * read non-atomically. Before making any commitment, on those architectures + * or configurations (e.g. i386 with PAE) which might give a mix of unmatched + * parts, do_swap_page must check under lock before unmapping the pte and + * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, @@ -1990,6 +1965,7 @@ static int do_page_mkwrite(struct vm_area_struct *vma, struct page *page, vmf.pgoff = page->index; vmf.flags = FAULT_FLAG_WRITE|FAULT_FLAG_MKWRITE; vmf.page = page; + vmf.cow_page = NULL; ret = vma->vm_ops->page_mkwrite(vma, &vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE))) @@ -2033,7 +2009,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_t entry; int ret = 0; int page_mkwrite = 0; - struct page *dirty_page = NULL; + bool dirty_shared = false; unsigned long mmun_start = 0; /* For mmu_notifiers */ unsigned long mmun_end = 0; /* For mmu_notifiers */ struct mem_cgroup *memcg; @@ -2084,6 +2060,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock_page(old_page); } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { + page_cache_get(old_page); /* * Only catch write-faults on shared writable pages, * read-only shared pages can get COWed by @@ -2091,7 +2068,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; - page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); tmp = do_page_mkwrite(vma, old_page, address); if (unlikely(!tmp || (tmp & @@ -2111,11 +2088,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock_page(old_page); goto unlock; } - page_mkwrite = 1; } - dirty_page = old_page; - get_page(dirty_page); + + dirty_shared = true; reuse: /* @@ -2134,20 +2110,20 @@ reuse: pte_unmap_unlock(page_table, ptl); ret |= VM_FAULT_WRITE; - if (!dirty_page) - return ret; - - if (!page_mkwrite) { + if (dirty_shared) { struct address_space *mapping; int dirtied; - lock_page(dirty_page); - dirtied = set_page_dirty(dirty_page); - VM_BUG_ON_PAGE(PageAnon(dirty_page), dirty_page); - mapping = dirty_page->mapping; - unlock_page(dirty_page); + if (!page_mkwrite) + lock_page(old_page); + + dirtied = set_page_dirty(old_page); + VM_BUG_ON_PAGE(PageAnon(old_page), old_page); + mapping = old_page->mapping; + unlock_page(old_page); + page_cache_release(old_page); - if (dirtied && mapping) { + if ((dirtied || page_mkwrite) && mapping) { /* * Some device drivers do not set page.mapping * but still dirty their pages @@ -2155,25 +2131,9 @@ reuse: balance_dirty_pages_ratelimited(mapping); } - /* file_update_time outside page_lock */ - if (vma->vm_file) + if (!page_mkwrite) file_update_time(vma->vm_file); } - put_page(dirty_page); - if (page_mkwrite) { - struct address_space *mapping = dirty_page->mapping; - - set_page_dirty(dirty_page); - unlock_page(dirty_page); - page_cache_release(dirty_page); - if (mapping) { - /* - * Some device drivers do not set page.mapping - * but still dirty their pages - */ - balance_dirty_pages_ratelimited(mapping); - } - } return ret; } @@ -2331,25 +2291,11 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, } } -static inline void unmap_mapping_range_list(struct list_head *head, - struct zap_details *details) -{ - struct vm_area_struct *vma; - - /* - * In nonlinear VMAs there is no correspondence between virtual address - * offset and file offset. So we must perform an exhaustive search - * across *all* the pages in each nonlinear VMA, not just the pages - * whose virtual address lies outside the file truncation point. - */ - list_for_each_entry(vma, head, shared.nonlinear) { - details->nonlinear_vma = vma; - unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details); - } -} - /** - * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file. + * unmap_mapping_range - unmap the portion of all mmaps in the specified + * address_space corresponding to the specified page range in the underlying + * file. + * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE @@ -2378,18 +2324,16 @@ void unmap_mapping_range(struct address_space *mapping, } details.check_mapping = even_cows? NULL: mapping; - details.nonlinear_vma = NULL; details.first_index = hba; details.last_index = hba + hlen - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; + /* DAX uses i_mmap_lock to serialise file truncate vs page fault */ i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); - if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) - unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); i_mmap_unlock_write(mapping); } EXPORT_SYMBOL(unmap_mapping_range); @@ -2696,7 +2640,8 @@ oom: * See filemap_fault() and __lock_page_retry(). */ static int __do_fault(struct vm_area_struct *vma, unsigned long address, - pgoff_t pgoff, unsigned int flags, struct page **page) + pgoff_t pgoff, unsigned int flags, + struct page *cow_page, struct page **page) { struct vm_fault vmf; int ret; @@ -2705,10 +2650,13 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, vmf.pgoff = pgoff; vmf.flags = flags; vmf.page = NULL; + vmf.cow_page = cow_page; ret = vma->vm_ops->fault(vma, &vmf); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; + if (!vmf.page) + goto out; if (unlikely(PageHWPoison(vmf.page))) { if (ret & VM_FAULT_LOCKED) @@ -2722,6 +2670,7 @@ static int __do_fault(struct vm_area_struct *vma, unsigned long address, else VM_BUG_ON_PAGE(!PageLocked(vmf.page), vmf.page); + out: *page = vmf.page; return ret; } @@ -2750,8 +2699,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, entry = mk_pte(page, vma->vm_page_prot); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - else if (pte_file(*pte) && pte_file_soft_dirty(*pte)) - entry = pte_mksoft_dirty(entry); if (anon) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); @@ -2886,8 +2833,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) && - fault_around_bytes >> PAGE_SHIFT > 1) { + if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); do_fault_around(vma, address, pte, pgoff, flags); if (!pte_same(*pte, orig_pte)) @@ -2895,7 +2841,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(pte, ptl); } - ret = __do_fault(vma, address, pgoff, flags, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; @@ -2935,26 +2881,43 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; } - ret = __do_fault(vma, address, pgoff, flags, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, new_page, &fault_page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) goto uncharge_out; - copy_user_highpage(new_page, fault_page, address, vma); + if (fault_page) + copy_user_highpage(new_page, fault_page, address, vma); __SetPageUptodate(new_page); pte = pte_offset_map_lock(mm, pmd, address, &ptl); if (unlikely(!pte_same(*pte, orig_pte))) { pte_unmap_unlock(pte, ptl); - unlock_page(fault_page); - page_cache_release(fault_page); + if (fault_page) { + unlock_page(fault_page); + page_cache_release(fault_page); + } else { + /* + * The fault handler has no page to lock, so it holds + * i_mmap_lock for read to protect against truncate. + */ + i_mmap_unlock_read(vma->vm_file->f_mapping); + } goto uncharge_out; } do_set_pte(vma, address, new_page, pte, true, true); mem_cgroup_commit_charge(new_page, memcg, false); lru_cache_add_active_or_unevictable(new_page, vma); pte_unmap_unlock(pte, ptl); - unlock_page(fault_page); - page_cache_release(fault_page); + if (fault_page) { + unlock_page(fault_page); + page_cache_release(fault_page); + } else { + /* + * The fault handler has no page to lock, so it holds + * i_mmap_lock for read to protect against truncate. + */ + i_mmap_unlock_read(vma->vm_file->f_mapping); + } return ret; uncharge_out: mem_cgroup_cancel_charge(new_page, memcg); @@ -2973,7 +2936,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, int dirtied = 0; int ret, tmp; - ret = __do_fault(vma, address, pgoff, flags, &fault_page); + ret = __do_fault(vma, address, pgoff, flags, NULL, &fault_page); if (unlikely(ret & (VM_FAULT_ERROR | VM_FAULT_NOPAGE | VM_FAULT_RETRY))) return ret; @@ -3019,8 +2982,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, balance_dirty_pages_ratelimited(mapping); } - /* file_update_time outside page_lock */ - if (vma->vm_file && !vma->vm_ops->page_mkwrite) + if (!vma->vm_ops->page_mkwrite) file_update_time(vma->vm_file); return ret; @@ -3032,7 +2994,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, * The mmap_sem may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ -static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, +static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, unsigned int flags, pte_t orig_pte) { @@ -3049,46 +3011,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } -/* - * Fault of a previously existing named mapping. Repopulate the pte - * from the encoded file_pte if possible. This enables swappable - * nonlinear vmas. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte mapped but not yet locked. - * We return with pte unmapped and unlocked. - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). - */ -static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) -{ - pgoff_t pgoff; - - flags |= FAULT_FLAG_NONLINEAR; - - if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) - return 0; - - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { - /* - * Page table corrupted: show pte and kill process. - */ - print_bad_pte(vma, address, orig_pte, NULL); - return VM_FAULT_SIGBUS; - } - - pgoff = pte_to_pgoff(orig_pte); - if (!(flags & FAULT_FLAG_WRITE)) - return do_read_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - if (!(vma->vm_flags & VM_SHARED)) - return do_cow_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); -} - static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) @@ -3115,14 +3037,17 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, bool migrated = false; int flags = 0; + /* A PROT_NONE fault should not end up here */ + BUG_ON(!(vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE))); + /* * The "pte" at this point cannot be used safely without * validation through pte_unmap_same(). It's of NUMA type but * the pfn may be screwed if the read is non atomic. * - * ptep_modify_prot_start is not called as this is clearing - * the _PAGE_NUMA bit and it is not really expected that there - * would be concurrent hardware modifications to the PTE. + * We can safely just do a "set_pte_at()", because the old + * page table entry is not accessible, so there would be no + * concurrent hardware modifications to the PTE. */ ptl = pte_lockptr(mm, pmd); spin_lock(ptl); @@ -3131,7 +3056,9 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, goto out; } - pte = pte_mknonnuma(pte); + /* Make it present again */ + pte = pte_modify(pte, vma->vm_page_prot); + pte = pte_mkyoung(pte); set_pte_at(mm, addr, ptep, pte); update_mmu_cache(vma, addr, ptep); @@ -3140,7 +3067,6 @@ static int do_numa_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_unmap_unlock(ptep, ptl); return 0; } - BUG_ON(is_zero_pfn(page_to_pfn(page))); /* * Avoid grouping on DSO/COW pages in specific and RO pages @@ -3216,20 +3142,17 @@ static int handle_pte_fault(struct mm_struct *mm, if (pte_none(entry)) { if (vma->vm_ops) { if (likely(vma->vm_ops->fault)) - return do_linear_fault(mm, vma, address, - pte, pmd, flags, entry); + return do_fault(mm, vma, address, pte, + pmd, flags, entry); } return do_anonymous_page(mm, vma, address, pte, pmd, flags); } - if (pte_file(entry)) - return do_nonlinear_fault(mm, vma, address, - pte, pmd, flags, entry); return do_swap_page(mm, vma, address, pte, pmd, flags, entry); } - if (pte_numa(entry)) + if (pte_protnone(entry)) return do_numa_page(mm, vma, address, entry, pte, pmd); ptl = pte_lockptr(mm, pmd); @@ -3307,7 +3230,7 @@ static int __handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (pmd_trans_splitting(orig_pmd)) return 0; - if (pmd_numa(orig_pmd)) + if (pmd_protnone(orig_pmd)) return do_huge_pmd_numa_page(mm, vma, address, orig_pmd, pmd); @@ -3428,15 +3351,17 @@ int __pmd_alloc(struct mm_struct *mm, pud_t *pud, unsigned long address) spin_lock(&mm->page_table_lock); #ifndef __ARCH_HAS_4LEVEL_HACK - if (pud_present(*pud)) /* Another has populated it */ - pmd_free(mm, new); - else + if (!pud_present(*pud)) { + mm_inc_nr_pmds(mm); pud_populate(mm, pud, new); -#else - if (pgd_present(*pud)) /* Another has populated it */ + } else /* Another has populated it */ pmd_free(mm, new); - else +#else + if (!pgd_present(*pud)) { + mm_inc_nr_pmds(mm); pgd_populate(mm, pud, new); + } else /* Another has populated it */ + pmd_free(mm, new); #endif /* __ARCH_HAS_4LEVEL_HACK */ spin_unlock(&mm->page_table_lock); return 0; @@ -3561,7 +3486,7 @@ int generic_access_phys(struct vm_area_struct *vma, unsigned long addr, if (follow_phys(vma, addr, write, &prot, &phys_addr)) return -EINVAL; - maddr = ioremap_prot(phys_addr, PAGE_SIZE, prot); + maddr = ioremap_prot(phys_addr, PAGE_ALIGN(len + offset), prot); if (write) memcpy_toio(maddr + offset, buf, len); else diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 0e0961b8c39c..4721046a134a 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -471,24 +471,34 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX] = { static void migrate_page_add(struct page *page, struct list_head *pagelist, unsigned long flags); +struct queue_pages { + struct list_head *pagelist; + unsigned long flags; + nodemask_t *nmask; + struct vm_area_struct *prev; +}; + /* * Scan through pages checking if pages follow certain conditions, * and move them to the pagelist if they do. */ -static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - const nodemask_t *nodes, unsigned long flags, - void *private) +static int queue_pages_pte_range(pmd_t *pmd, unsigned long addr, + unsigned long end, struct mm_walk *walk) { - pte_t *orig_pte; + struct vm_area_struct *vma = walk->vma; + struct page *page; + struct queue_pages *qp = walk->private; + unsigned long flags = qp->flags; + int nid; pte_t *pte; spinlock_t *ptl; - orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - do { - struct page *page; - int nid; + split_huge_page_pmd(vma, addr, pmd); + if (pmd_trans_unstable(pmd)) + return 0; + pte = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr != end; pte++, addr += PAGE_SIZE) { if (!pte_present(*pte)) continue; page = vm_normal_page(vma, addr, *pte); @@ -501,114 +511,46 @@ static int queue_pages_pte_range(struct vm_area_struct *vma, pmd_t *pmd, if (PageReserved(page)) continue; nid = page_to_nid(page); - if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) + if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT)) continue; if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) - migrate_page_add(page, private, flags); - else - break; - } while (pte++, addr += PAGE_SIZE, addr != end); - pte_unmap_unlock(orig_pte, ptl); - return addr != end; + migrate_page_add(page, qp->pagelist, flags); + } + pte_unmap_unlock(pte - 1, ptl); + cond_resched(); + return 0; } -static void queue_pages_hugetlb_pmd_range(struct vm_area_struct *vma, - pmd_t *pmd, const nodemask_t *nodes, unsigned long flags, - void *private) +static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, + unsigned long addr, unsigned long end, + struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE + struct queue_pages *qp = walk->private; + unsigned long flags = qp->flags; int nid; struct page *page; spinlock_t *ptl; pte_t entry; - ptl = huge_pte_lock(hstate_vma(vma), vma->vm_mm, (pte_t *)pmd); - entry = huge_ptep_get((pte_t *)pmd); + ptl = huge_pte_lock(hstate_vma(walk->vma), walk->mm, pte); + entry = huge_ptep_get(pte); if (!pte_present(entry)) goto unlock; page = pte_page(entry); nid = page_to_nid(page); - if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT)) + if (node_isset(nid, *qp->nmask) == !!(flags & MPOL_MF_INVERT)) goto unlock; /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) - isolate_huge_page(page, private); + isolate_huge_page(page, qp->pagelist); unlock: spin_unlock(ptl); #else BUG(); #endif -} - -static inline int queue_pages_pmd_range(struct vm_area_struct *vma, pud_t *pud, - unsigned long addr, unsigned long end, - const nodemask_t *nodes, unsigned long flags, - void *private) -{ - pmd_t *pmd; - unsigned long next; - - pmd = pmd_offset(pud, addr); - do { - next = pmd_addr_end(addr, end); - if (!pmd_present(*pmd)) - continue; - if (pmd_huge(*pmd) && is_vm_hugetlb_page(vma)) { - queue_pages_hugetlb_pmd_range(vma, pmd, nodes, - flags, private); - continue; - } - split_huge_page_pmd(vma, addr, pmd); - if (pmd_none_or_trans_huge_or_clear_bad(pmd)) - continue; - if (queue_pages_pte_range(vma, pmd, addr, next, nodes, - flags, private)) - return -EIO; - } while (pmd++, addr = next, addr != end); - return 0; -} - -static inline int queue_pages_pud_range(struct vm_area_struct *vma, pgd_t *pgd, - unsigned long addr, unsigned long end, - const nodemask_t *nodes, unsigned long flags, - void *private) -{ - pud_t *pud; - unsigned long next; - - pud = pud_offset(pgd, addr); - do { - next = pud_addr_end(addr, end); - if (pud_huge(*pud) && is_vm_hugetlb_page(vma)) - continue; - if (pud_none_or_clear_bad(pud)) - continue; - if (queue_pages_pmd_range(vma, pud, addr, next, nodes, - flags, private)) - return -EIO; - } while (pud++, addr = next, addr != end); - return 0; -} - -static inline int queue_pages_pgd_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - const nodemask_t *nodes, unsigned long flags, - void *private) -{ - pgd_t *pgd; - unsigned long next; - - pgd = pgd_offset(vma->vm_mm, addr); - do { - next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) - continue; - if (queue_pages_pud_range(vma, pgd, addr, next, nodes, - flags, private)) - return -EIO; - } while (pgd++, addr = next, addr != end); return 0; } @@ -627,7 +569,7 @@ unsigned long change_prot_numa(struct vm_area_struct *vma, { int nr_updated; - nr_updated = change_protection(vma, addr, end, vma->vm_page_prot, 0, 1); + nr_updated = change_protection(vma, addr, end, PAGE_NONE, 0, 1); if (nr_updated) count_vm_numa_events(NUMA_PTE_UPDATES, nr_updated); @@ -641,6 +583,49 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, } #endif /* CONFIG_NUMA_BALANCING */ +static int queue_pages_test_walk(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + struct queue_pages *qp = walk->private; + unsigned long endvma = vma->vm_end; + unsigned long flags = qp->flags; + + if (vma->vm_flags & VM_PFNMAP) + return 1; + + if (endvma > end) + endvma = end; + if (vma->vm_start > start) + start = vma->vm_start; + + if (!(flags & MPOL_MF_DISCONTIG_OK)) { + if (!vma->vm_next && vma->vm_end < end) + return -EFAULT; + if (qp->prev && qp->prev->vm_end < vma->vm_start) + return -EFAULT; + } + + qp->prev = vma; + + if (vma->vm_flags & VM_PFNMAP) + return 1; + + if (flags & MPOL_MF_LAZY) { + /* Similar to task_numa_work, skip inaccessible VMAs */ + if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)) + change_prot_numa(vma, start, endvma); + return 1; + } + + if ((flags & MPOL_MF_STRICT) || + ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) && + vma_migratable(vma))) + /* queue pages from current vma */ + return 0; + return 1; +} + /* * Walk through page tables and collect pages to be migrated. * @@ -650,50 +635,24 @@ static unsigned long change_prot_numa(struct vm_area_struct *vma, */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, - const nodemask_t *nodes, unsigned long flags, void *private) -{ - int err = 0; - struct vm_area_struct *vma, *prev; - - vma = find_vma(mm, start); - if (!vma) - return -EFAULT; - prev = NULL; - for (; vma && vma->vm_start < end; vma = vma->vm_next) { - unsigned long endvma = vma->vm_end; - - if (endvma > end) - endvma = end; - if (vma->vm_start > start) - start = vma->vm_start; - - if (!(flags & MPOL_MF_DISCONTIG_OK)) { - if (!vma->vm_next && vma->vm_end < end) - return -EFAULT; - if (prev && prev->vm_end < vma->vm_start) - return -EFAULT; - } - - if (flags & MPOL_MF_LAZY) { - /* Similar to task_numa_work, skip inaccessible VMAs */ - if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)) - change_prot_numa(vma, start, endvma); - goto next; - } - - if ((flags & MPOL_MF_STRICT) || - ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) && - vma_migratable(vma))) { - - err = queue_pages_pgd_range(vma, start, endvma, nodes, - flags, private); - if (err) - break; - } -next: - prev = vma; - } - return err; + nodemask_t *nodes, unsigned long flags, + struct list_head *pagelist) +{ + struct queue_pages qp = { + .pagelist = pagelist, + .flags = flags, + .nmask = nodes, + .prev = NULL, + }; + struct mm_walk queue_pages_walk = { + .hugetlb_entry = queue_pages_hugetlb, + .pmd_entry = queue_pages_pte_range, + .test_walk = queue_pages_test_walk, + .mm = mm, + .private = &qp, + }; + + return walk_page_range(start, end, &queue_pages_walk); } /* @@ -1988,43 +1947,63 @@ static struct page *alloc_page_interleave(gfp_t gfp, unsigned order, * @order:Order of the GFP allocation. * @vma: Pointer to VMA or NULL if not available. * @addr: Virtual Address of the allocation. Must be inside the VMA. + * @node: Which node to prefer for allocation (modulo policy). + * @hugepage: for hugepages try only the preferred node if possible * * This function allocates a page from the kernel page pool and applies * a NUMA policy associated with the VMA or the current process. * When VMA is not NULL caller must hold down_read on the mmap_sem of the * mm_struct of the VMA to prevent it from going away. Should be used for - * all allocations for pages that will be mapped into - * user space. Returns NULL when no page can be allocated. - * - * Should be called with the mm_sem of the vma hold. + * all allocations for pages that will be mapped into user space. Returns + * NULL when no page can be allocated. */ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, - unsigned long addr, int node) + unsigned long addr, int node, bool hugepage) { struct mempolicy *pol; struct page *page; unsigned int cpuset_mems_cookie; + struct zonelist *zl; + nodemask_t *nmask; retry_cpuset: pol = get_vma_policy(vma, addr); cpuset_mems_cookie = read_mems_allowed_begin(); - if (unlikely(pol->mode == MPOL_INTERLEAVE)) { + if (unlikely(IS_ENABLED(CONFIG_TRANSPARENT_HUGEPAGE) && hugepage && + pol->mode != MPOL_INTERLEAVE)) { + /* + * For hugepage allocation and non-interleave policy which + * allows the current node, we only try to allocate from the + * current node and don't fall back to other nodes, as the + * cost of remote accesses would likely offset THP benefits. + * + * If the policy is interleave, or does not allow the current + * node in its nodemask, we allocate the standard way. + */ + nmask = policy_nodemask(gfp, pol); + if (!nmask || node_isset(node, *nmask)) { + mpol_cond_put(pol); + page = alloc_pages_exact_node(node, gfp, order); + goto out; + } + } + + if (pol->mode == MPOL_INTERLEAVE) { unsigned nid; nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order); mpol_cond_put(pol); page = alloc_page_interleave(gfp, order, nid); - if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) - goto retry_cpuset; - - return page; + goto out; } - page = __alloc_pages_nodemask(gfp, order, - policy_zonelist(gfp, pol, node), - policy_nodemask(gfp, pol)); + + nmask = policy_nodemask(gfp, pol); + zl = policy_zonelist(gfp, pol, node); mpol_cond_put(pol); + page = __alloc_pages_nodemask(gfp, order, zl, nmask); +out: if (unlikely(!page && read_mems_allowed_retry(cpuset_mems_cookie))) goto retry_cpuset; return page; @@ -2838,8 +2817,7 @@ void mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol) p += snprintf(p, buffer + maxlen - p, "relative"); } - if (!nodes_empty(nodes)) { - p += snprintf(p, buffer + maxlen - p, ":"); - p += nodelist_scnprintf(p, buffer + maxlen - p, nodes); - } + if (!nodes_empty(nodes)) + p += scnprintf(p, buffer + maxlen - p, ":%*pbl", + nodemask_pr_args(&nodes)); } diff --git a/mm/migrate.c b/mm/migrate.c index 344cdf692fc8..85e042686031 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -179,37 +179,6 @@ out: } /* - * Congratulations to trinity for discovering this bug. - * mm/fremap.c's remap_file_pages() accepts any range within a single vma to - * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then - * replace the specified range by file ptes throughout (maybe populated after). - * If page migration finds a page within that range, while it's still located - * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: - * zap_pte() clears the temporary migration entry before mmap_sem is dropped. - * But if the migrating page is in a part of the vma outside the range to be - * remapped, then it will not be cleared, and remove_migration_ptes() needs to - * deal with it. Fortunately, this part of the vma is of course still linear, - * so we just need to use linear location on the nonlinear list. - */ -static int remove_linear_migration_ptes_from_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - unsigned long addr; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - if (addr >= vma->vm_start && addr < vma->vm_end) - remove_migration_pte(page, vma, addr, arg); - } - return SWAP_AGAIN; -} - -/* * Get rid of all migration entries and replace them by * references to the indicated page. */ @@ -218,7 +187,6 @@ static void remove_migration_ptes(struct page *old, struct page *new) struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = old, - .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, }; rmap_walk(new, &rwc); @@ -229,7 +197,7 @@ static void remove_migration_ptes(struct page *old, struct page *new) * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ -static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, +void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, spinlock_t *ptl) { pte_t pte; @@ -1268,7 +1236,8 @@ static int do_move_page_to_node_array(struct mm_struct *mm, goto put_and_set; if (PageHuge(page)) { - isolate_huge_page(page, &pagelist); + if (PageHead(page)) + isolate_huge_page(page, &pagelist); goto put_and_set; } @@ -1685,12 +1654,6 @@ bool pmd_trans_migrating(pmd_t pmd) return PageLocked(page); } -void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd) -{ - struct page *page = pmd_page(*pmd); - wait_on_page_locked(page); -} - /* * Attempt to migrate a misplaced page to the specified destination * node. Caller is expected to have an elevated reference count on @@ -1884,7 +1847,7 @@ out_fail: out_dropref: ptl = pmd_lock(mm, pmd); if (pmd_same(*pmd, entry)) { - entry = pmd_mknonnuma(entry); + entry = pmd_modify(entry, vma->vm_page_prot); set_pmd_at(mm, mmun_start, pmd, entry); update_mmu_cache_pmd(vma, address, &entry); } diff --git a/mm/mincore.c b/mm/mincore.c index c8c528b36641..be25efde64a4 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -19,38 +19,25 @@ #include <asm/uaccess.h> #include <asm/pgtable.h> -static void mincore_hugetlb_page_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - unsigned char *vec) +static int mincore_hugetlb(pte_t *pte, unsigned long hmask, unsigned long addr, + unsigned long end, struct mm_walk *walk) { #ifdef CONFIG_HUGETLB_PAGE - struct hstate *h; + unsigned char present; + unsigned char *vec = walk->private; - h = hstate_vma(vma); - while (1) { - unsigned char present; - pte_t *ptep; - /* - * Huge pages are always in RAM for now, but - * theoretically it needs to be checked. - */ - ptep = huge_pte_offset(current->mm, - addr & huge_page_mask(h)); - present = ptep && !huge_pte_none(huge_ptep_get(ptep)); - while (1) { - *vec = present; - vec++; - addr += PAGE_SIZE; - if (addr == end) - return; - /* check hugepage border */ - if (!(addr & ~huge_page_mask(h))) - break; - } - } + /* + * Hugepages under user process are always in RAM and never + * swapped out, but theoretically it needs to be checked. + */ + present = pte && !huge_pte_none(huge_ptep_get(pte)); + for (; addr != end; vec++, addr += PAGE_SIZE) + *vec = present; + walk->private = vec; #else BUG(); #endif + return 0; } /* @@ -94,9 +81,8 @@ static unsigned char mincore_page(struct address_space *mapping, pgoff_t pgoff) return present; } -static void mincore_unmapped_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - unsigned char *vec) +static int __mincore_unmapped_range(unsigned long addr, unsigned long end, + struct vm_area_struct *vma, unsigned char *vec) { unsigned long nr = (end - addr) >> PAGE_SHIFT; int i; @@ -111,30 +97,47 @@ static void mincore_unmapped_range(struct vm_area_struct *vma, for (i = 0; i < nr; i++) vec[i] = 0; } + return nr; +} + +static int mincore_unmapped_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + walk->private += __mincore_unmapped_range(addr, end, + walk->vma, walk->private); + return 0; } -static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, - unsigned long addr, unsigned long end, - unsigned char *vec) +static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, + struct mm_walk *walk) { - unsigned long next; spinlock_t *ptl; + struct vm_area_struct *vma = walk->vma; pte_t *ptep; + unsigned char *vec = walk->private; + int nr = (end - addr) >> PAGE_SHIFT; + + if (pmd_trans_huge_lock(pmd, vma, &ptl) == 1) { + memset(vec, 1, nr); + spin_unlock(ptl); + goto out; + } + + if (pmd_trans_unstable(pmd)) { + __mincore_unmapped_range(addr, end, vma, vec); + goto out; + } - ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); - do { + ptep = pte_offset_map_lock(walk->mm, pmd, addr, &ptl); + for (; addr != end; ptep++, addr += PAGE_SIZE) { pte_t pte = *ptep; - pgoff_t pgoff; - next = addr + PAGE_SIZE; if (pte_none(pte)) - mincore_unmapped_range(vma, addr, next, vec); + __mincore_unmapped_range(addr, addr + PAGE_SIZE, + vma, vec); else if (pte_present(pte)) *vec = 1; - else if (pte_file(pte)) { - pgoff = pte_to_pgoff(pte); - *vec = mincore_page(vma->vm_file->f_mapping, pgoff); - } else { /* pte is a swap entry */ + else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); if (non_swap_entry(entry)) { @@ -145,9 +148,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, *vec = 1; } else { #ifdef CONFIG_SWAP - pgoff = entry.val; *vec = mincore_page(swap_address_space(entry), - pgoff); + entry.val); #else WARN_ON(1); *vec = 1; @@ -155,69 +157,12 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } } vec++; - } while (ptep++, addr = next, addr != end); + } pte_unmap_unlock(ptep - 1, ptl); -} - -static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - unsigned long next; - pmd_t *pmd; - - pmd = pmd_offset(pud, addr); - do { - next = pmd_addr_end(addr, end); - if (pmd_trans_huge(*pmd)) { - if (mincore_huge_pmd(vma, pmd, addr, next, vec)) { - vec += (next - addr) >> PAGE_SHIFT; - continue; - } - /* fall through */ - } - if (pmd_none_or_trans_huge_or_clear_bad(pmd)) - mincore_unmapped_range(vma, addr, next, vec); - else - mincore_pte_range(vma, pmd, addr, next, vec); - vec += (next - addr) >> PAGE_SHIFT; - } while (pmd++, addr = next, addr != end); -} - -static void mincore_pud_range(struct vm_area_struct *vma, pgd_t *pgd, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - unsigned long next; - pud_t *pud; - - pud = pud_offset(pgd, addr); - do { - next = pud_addr_end(addr, end); - if (pud_none_or_clear_bad(pud)) - mincore_unmapped_range(vma, addr, next, vec); - else - mincore_pmd_range(vma, pud, addr, next, vec); - vec += (next - addr) >> PAGE_SHIFT; - } while (pud++, addr = next, addr != end); -} - -static void mincore_page_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - unsigned char *vec) -{ - unsigned long next; - pgd_t *pgd; - - pgd = pgd_offset(vma->vm_mm, addr); - do { - next = pgd_addr_end(addr, end); - if (pgd_none_or_clear_bad(pgd)) - mincore_unmapped_range(vma, addr, next, vec); - else - mincore_pud_range(vma, pgd, addr, next, vec); - vec += (next - addr) >> PAGE_SHIFT; - } while (pgd++, addr = next, addr != end); +out: + walk->private += nr; + cond_resched(); + return 0; } /* @@ -229,18 +174,22 @@ static long do_mincore(unsigned long addr, unsigned long pages, unsigned char *v { struct vm_area_struct *vma; unsigned long end; + int err; + struct mm_walk mincore_walk = { + .pmd_entry = mincore_pte_range, + .pte_hole = mincore_unmapped_range, + .hugetlb_entry = mincore_hugetlb, + .private = vec, + }; vma = find_vma(current->mm, addr); if (!vma || addr < vma->vm_start) return -ENOMEM; - + mincore_walk.mm = vma->vm_mm; end = min(vma->vm_end, addr + (pages << PAGE_SHIFT)); - - if (is_vm_hugetlb_page(vma)) - mincore_hugetlb_page_range(vma, addr, end, vec); - else - mincore_page_range(vma, addr, end, vec); - + err = walk_page_range(addr, end, &mincore_walk); + if (err < 0) + return err; return (end - addr) >> PAGE_SHIFT; } diff --git a/mm/mm_init.c b/mm/mm_init.c index 4074caf9936b..5f420f7fafa1 100644 --- a/mm/mm_init.c +++ b/mm/mm_init.c @@ -14,14 +14,14 @@ #include "internal.h" #ifdef CONFIG_DEBUG_MEMORY_INIT -int mminit_loglevel; +int __meminitdata mminit_loglevel; #ifndef SECTIONS_SHIFT #define SECTIONS_SHIFT 0 #endif /* The zonelists are simply reported, validation is manual. */ -void mminit_verify_zonelist(void) +void __init mminit_verify_zonelist(void) { int nid; diff --git a/mm/mmap.c b/mm/mmap.c index 7f684d5a8087..da9990acc08b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -152,7 +152,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed, reserve; + long free, allowed, reserve; VM_WARN_ONCE(percpu_counter_read(&vm_committed_as) < -(s64)vm_committed_as_batch * num_online_cpus(), @@ -220,7 +220,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ if (mm) { reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed -= min(mm->total_vm / 32, reserve); + allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) @@ -243,10 +243,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - list_del_init(&vma->shared.nonlinear); - else - vma_interval_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } @@ -649,10 +646,7 @@ static void __vma_link_file(struct vm_area_struct *vma) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } @@ -789,14 +783,11 @@ again: remove_next = 1 + (end > next->vm_end); if (file) { mapping = file->f_mapping; - if (!(vma->vm_flags & VM_NONLINEAR)) { - root = &mapping->i_mmap; - uprobe_munmap(vma, vma->vm_start, vma->vm_end); + root = &mapping->i_mmap; + uprobe_munmap(vma, vma->vm_start, vma->vm_end); - if (adjust_next) - uprobe_munmap(next, next->vm_start, - next->vm_end); - } + if (adjust_next) + uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { @@ -2634,6 +2625,75 @@ SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) return vm_munmap(addr, len); } + +/* + * Emulation of deprecated remap_file_pages() syscall. + */ +SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, + unsigned long, prot, unsigned long, pgoff, unsigned long, flags) +{ + + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long populate = 0; + unsigned long ret = -EINVAL; + struct file *file; + + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " + "See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); + + if (prot) + return ret; + start = start & PAGE_MASK; + size = size & PAGE_MASK; + + if (start + size <= start) + return ret; + + /* Does pgoff wrap? */ + if (pgoff + (size >> PAGE_SHIFT) < pgoff) + return ret; + + down_write(&mm->mmap_sem); + vma = find_vma(mm, start); + + if (!vma || !(vma->vm_flags & VM_SHARED)) + goto out; + + if (start < vma->vm_start || start + size > vma->vm_end) + goto out; + + if (pgoff == linear_page_index(vma, start)) { + ret = 0; + goto out; + } + + prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; + prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; + prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma->vm_flags & VM_LOCKED) { + flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ + munlock_vma_pages_range(vma, start, start + size); + } + + file = get_file(vma->vm_file); + ret = do_mmap_pgoff(vma->vm_file, start, size, + prot, flags, pgoff, &populate); + fput(file); +out: + up_write(&mm->mmap_sem); + if (populate) + mm_populate(ret, populate); + if (!IS_ERR_VALUE(ret)) + ret = 0; + return ret; +} + static inline void verify_mm_writelocked(struct mm_struct *mm) { #ifdef CONFIG_DEBUG_VM @@ -2791,9 +2851,6 @@ void exit_mmap(struct mm_struct *mm) vma = remove_vma(vma); } vm_unacct_memory(nr_accounted); - - WARN_ON(atomic_long_read(&mm->nr_ptes) > - (FIRST_USER_ADDRESS+PMD_SIZE-1)>>PMD_SHIFT); } /* Insert vm structure into process list sorted by address @@ -3108,8 +3165,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * * mmap_sem in write mode is required in order to block all operations * that could modify pagetables and free pages without need of - * altering the vma layout (for example populate_range() with - * nonlinear vmas). It's also needed in write mode to avoid new + * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row diff --git a/mm/mmzone.c b/mm/mmzone.c index bf34fb8556db..7d87ebb0d632 100644 --- a/mm/mmzone.c +++ b/mm/mmzone.c @@ -54,8 +54,7 @@ static inline int zref_in_nodemask(struct zoneref *zref, nodemask_t *nodes) /* Returns the next zone at or below highest_zoneidx in a zonelist */ struct zoneref *next_zones_zonelist(struct zoneref *z, enum zone_type highest_zoneidx, - nodemask_t *nodes, - struct zone **zone) + nodemask_t *nodes) { /* * Find the next suitable zone to use for the allocation. @@ -69,7 +68,6 @@ struct zoneref *next_zones_zonelist(struct zoneref *z, (z->zone && !zref_in_nodemask(z, nodes))) z++; - *zone = zonelist_zone(z); return z; } diff --git a/mm/mprotect.c b/mm/mprotect.c index ace93454ce8e..44727811bf4c 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -75,37 +75,35 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, oldpte = *pte; if (pte_present(oldpte)) { pte_t ptent; - bool updated = false; - if (!prot_numa) { - ptent = ptep_modify_prot_start(mm, addr, pte); - if (pte_numa(ptent)) - ptent = pte_mknonnuma(ptent); - ptent = pte_modify(ptent, newprot); - /* - * Avoid taking write faults for pages we - * know to be dirty. - */ - if (dirty_accountable && pte_dirty(ptent) && - (pte_soft_dirty(ptent) || - !(vma->vm_flags & VM_SOFTDIRTY))) - ptent = pte_mkwrite(ptent); - ptep_modify_prot_commit(mm, addr, pte, ptent); - updated = true; - } else { + /* + * Avoid trapping faults against the zero or KSM + * pages. See similar comment in change_huge_pmd. + */ + if (prot_numa) { struct page *page; page = vm_normal_page(vma, addr, oldpte); - if (page && !PageKsm(page)) { - if (!pte_numa(oldpte)) { - ptep_set_numa(mm, addr, pte); - updated = true; - } - } + if (!page || PageKsm(page)) + continue; + + /* Avoid TLB flush if possible */ + if (pte_protnone(oldpte)) + continue; } - if (updated) - pages++; - } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { + + ptent = ptep_modify_prot_start(mm, addr, pte); + ptent = pte_modify(ptent, newprot); + + /* Avoid taking write faults for known dirty pages */ + if (dirty_accountable && pte_dirty(ptent) && + (pte_soft_dirty(ptent) || + !(vma->vm_flags & VM_SOFTDIRTY))) { + ptent = pte_mkwrite(ptent); + } + ptep_modify_prot_commit(mm, addr, pte, ptent); + pages++; + } else if (IS_ENABLED(CONFIG_MIGRATION)) { swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { diff --git a/mm/mremap.c b/mm/mremap.c index 17fa018f5f39..57dadc025c64 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -81,8 +81,6 @@ static pte_t move_soft_dirty_pte(pte_t pte) pte = pte_mksoft_dirty(pte); else if (is_swap_pte(pte)) pte = pte_swp_mksoft_dirty(pte); - else if (pte_file(pte)) - pte = pte_file_mksoft_dirty(pte); #endif return pte; } diff --git a/mm/msync.c b/mm/msync.c index 992a1673d488..bb04d53ae852 100644 --- a/mm/msync.c +++ b/mm/msync.c @@ -86,10 +86,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - if (vma->vm_flags & VM_NONLINEAR) - error = vfs_fsync(file, 1); - else - error = vfs_fsync_range(file, fstart, fend, 1); + error = vfs_fsync_range(file, fstart, fend, 1); fput(file); if (error || start >= end) goto out; diff --git a/mm/nommu.c b/mm/nommu.c index b51eadf6d952..7296360fc057 100644 --- a/mm/nommu.c +++ b/mm/nommu.c @@ -59,6 +59,7 @@ #endif void *high_memory; +EXPORT_SYMBOL(high_memory); struct page *mem_map; unsigned long max_mapnr; unsigned long highest_memmap_pfn; @@ -213,6 +214,39 @@ long get_user_pages(struct task_struct *tsk, struct mm_struct *mm, } EXPORT_SYMBOL(get_user_pages); +long get_user_pages_locked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + int *locked) +{ + return get_user_pages(tsk, mm, start, nr_pages, write, force, + pages, NULL); +} +EXPORT_SYMBOL(get_user_pages_locked); + +long __get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages, + unsigned int gup_flags) +{ + long ret; + down_read(&mm->mmap_sem); + ret = get_user_pages(tsk, mm, start, nr_pages, write, force, + pages, NULL); + up_read(&mm->mmap_sem); + return ret; +} +EXPORT_SYMBOL(__get_user_pages_unlocked); + +long get_user_pages_unlocked(struct task_struct *tsk, struct mm_struct *mm, + unsigned long start, unsigned long nr_pages, + int write, int force, struct page **pages) +{ + return __get_user_pages_unlocked(tsk, mm, start, nr_pages, write, + force, pages, 0); +} +EXPORT_SYMBOL(get_user_pages_unlocked); + /** * follow_pfn - look up PFN at a user virtual address * @vma: memory mapping @@ -946,9 +980,6 @@ static int validate_mmap_request(struct file *file, return -EOVERFLOW; if (file) { - /* validate file mapping requests */ - struct address_space *mapping; - /* files must support mmap */ if (!file->f_op->mmap) return -ENODEV; @@ -957,28 +988,22 @@ static int validate_mmap_request(struct file *file, * - we support chardevs that provide their own "memory" * - we support files/blockdevs that are memory backed */ - mapping = file->f_mapping; - if (!mapping) - mapping = file_inode(file)->i_mapping; - - capabilities = 0; - if (mapping && mapping->backing_dev_info) - capabilities = mapping->backing_dev_info->capabilities; - - if (!capabilities) { + if (file->f_op->mmap_capabilities) { + capabilities = file->f_op->mmap_capabilities(file); + } else { /* no explicit capabilities set, so assume some * defaults */ switch (file_inode(file)->i_mode & S_IFMT) { case S_IFREG: case S_IFBLK: - capabilities = BDI_CAP_MAP_COPY; + capabilities = NOMMU_MAP_COPY; break; case S_IFCHR: capabilities = - BDI_CAP_MAP_DIRECT | - BDI_CAP_READ_MAP | - BDI_CAP_WRITE_MAP; + NOMMU_MAP_DIRECT | + NOMMU_MAP_READ | + NOMMU_MAP_WRITE; break; default: @@ -989,9 +1014,9 @@ static int validate_mmap_request(struct file *file, /* eliminate any capabilities that we can't support on this * device */ if (!file->f_op->get_unmapped_area) - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; if (!file->f_op->read) - capabilities &= ~BDI_CAP_MAP_COPY; + capabilities &= ~NOMMU_MAP_COPY; /* The file shall have been opened with read permission. */ if (!(file->f_mode & FMODE_READ)) @@ -1010,29 +1035,29 @@ static int validate_mmap_request(struct file *file, if (locks_verify_locked(file)) return -EAGAIN; - if (!(capabilities & BDI_CAP_MAP_DIRECT)) + if (!(capabilities & NOMMU_MAP_DIRECT)) return -ENODEV; /* we mustn't privatise shared mappings */ - capabilities &= ~BDI_CAP_MAP_COPY; + capabilities &= ~NOMMU_MAP_COPY; } else { /* we're going to read the file into private memory we * allocate */ - if (!(capabilities & BDI_CAP_MAP_COPY)) + if (!(capabilities & NOMMU_MAP_COPY)) return -ENODEV; /* we don't permit a private writable mapping to be * shared with the backing device */ if (prot & PROT_WRITE) - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; } - if (capabilities & BDI_CAP_MAP_DIRECT) { - if (((prot & PROT_READ) && !(capabilities & BDI_CAP_READ_MAP)) || - ((prot & PROT_WRITE) && !(capabilities & BDI_CAP_WRITE_MAP)) || - ((prot & PROT_EXEC) && !(capabilities & BDI_CAP_EXEC_MAP)) + if (capabilities & NOMMU_MAP_DIRECT) { + if (((prot & PROT_READ) && !(capabilities & NOMMU_MAP_READ)) || + ((prot & PROT_WRITE) && !(capabilities & NOMMU_MAP_WRITE)) || + ((prot & PROT_EXEC) && !(capabilities & NOMMU_MAP_EXEC)) ) { - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; if (flags & MAP_SHARED) { printk(KERN_WARNING "MAP_SHARED not completely supported on !MMU\n"); @@ -1049,21 +1074,21 @@ static int validate_mmap_request(struct file *file, } else if ((prot & PROT_READ) && !(prot & PROT_EXEC)) { /* handle implication of PROT_EXEC by PROT_READ */ if (current->personality & READ_IMPLIES_EXEC) { - if (capabilities & BDI_CAP_EXEC_MAP) + if (capabilities & NOMMU_MAP_EXEC) prot |= PROT_EXEC; } } else if ((prot & PROT_READ) && (prot & PROT_EXEC) && - !(capabilities & BDI_CAP_EXEC_MAP) + !(capabilities & NOMMU_MAP_EXEC) ) { /* backing file is not executable, try to copy */ - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; } } else { /* anonymous mappings are always memory backed and can be * privately mapped */ - capabilities = BDI_CAP_MAP_COPY; + capabilities = NOMMU_MAP_COPY; /* handle PROT_EXEC implication by PROT_READ */ if ((prot & PROT_READ) && @@ -1095,7 +1120,7 @@ static unsigned long determine_vm_flags(struct file *file, vm_flags = calc_vm_prot_bits(prot) | calc_vm_flag_bits(flags); /* vm_flags |= mm->def_flags; */ - if (!(capabilities & BDI_CAP_MAP_DIRECT)) { + if (!(capabilities & NOMMU_MAP_DIRECT)) { /* attempt to share read-only copies of mapped file chunks */ vm_flags |= VM_MAYREAD | VM_MAYWRITE | VM_MAYEXEC; if (file && !(prot & PROT_WRITE)) @@ -1104,7 +1129,7 @@ static unsigned long determine_vm_flags(struct file *file, /* overlay a shareable mapping on the backing device or inode * if possible - used for chardevs, ramfs/tmpfs/shmfs and * romfs/cramfs */ - vm_flags |= VM_MAYSHARE | (capabilities & BDI_CAP_VMFLAGS); + vm_flags |= VM_MAYSHARE | (capabilities & NOMMU_VMFLAGS); if (flags & MAP_SHARED) vm_flags |= VM_SHARED; } @@ -1157,7 +1182,7 @@ static int do_mmap_private(struct vm_area_struct *vma, * shared mappings on devices or memory * - VM_MAYSHARE will be set if it may attempt to share */ - if (capabilities & BDI_CAP_MAP_DIRECT) { + if (capabilities & NOMMU_MAP_DIRECT) { ret = vma->vm_file->f_op->mmap(vma->vm_file, vma); if (ret == 0) { /* shouldn't return success if we're not sharing */ @@ -1346,7 +1371,7 @@ unsigned long do_mmap_pgoff(struct file *file, if ((pregion->vm_pgoff != pgoff || rpglen != pglen) && !(pgoff >= pregion->vm_pgoff && pgend <= rpgend)) { /* new mapping is not a subset of the region */ - if (!(capabilities & BDI_CAP_MAP_DIRECT)) + if (!(capabilities & NOMMU_MAP_DIRECT)) goto sharing_violation; continue; } @@ -1385,7 +1410,7 @@ unsigned long do_mmap_pgoff(struct file *file, * - this is the hook for quasi-memory character devices to * tell us the location of a shared mapping */ - if (capabilities & BDI_CAP_MAP_DIRECT) { + if (capabilities & NOMMU_MAP_DIRECT) { addr = file->f_op->get_unmapped_area(file, addr, len, pgoff, flags); if (IS_ERR_VALUE(addr)) { @@ -1397,10 +1422,10 @@ unsigned long do_mmap_pgoff(struct file *file, * the mapping so we'll have to attempt to copy * it */ ret = -ENODEV; - if (!(capabilities & BDI_CAP_MAP_COPY)) + if (!(capabilities & NOMMU_MAP_COPY)) goto error_just_free; - capabilities &= ~BDI_CAP_MAP_DIRECT; + capabilities &= ~NOMMU_MAP_DIRECT; } else { vma->vm_start = region->vm_start = addr; vma->vm_end = region->vm_end = addr + len; @@ -1411,7 +1436,7 @@ unsigned long do_mmap_pgoff(struct file *file, vma->vm_region = region; /* set up the mapping - * - the region is filled in if BDI_CAP_MAP_DIRECT is still set + * - the region is filled in if NOMMU_MAP_DIRECT is still set */ if (file && vma->vm_flags & VM_SHARED) ret = do_mmap_shared_file(vma); @@ -1894,7 +1919,7 @@ EXPORT_SYMBOL(unmap_mapping_range); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed, reserve; + long free, allowed, reserve; vm_acct_memory(pages); @@ -1958,7 +1983,7 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) */ if (mm) { reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); - allowed -= min(mm->total_vm / 32, reserve); + allowed -= min_t(long, mm->total_vm / 32, reserve); } if (percpu_counter_read_positive(&vm_committed_as) < allowed) @@ -1983,14 +2008,6 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_map_pages); -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - BUG(); - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d503e9ce1c7b..642f38cb175a 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -169,8 +169,8 @@ unsigned long oom_badness(struct task_struct *p, struct mem_cgroup *memcg, * The baseline for the badness score is the proportion of RAM that each * task's rss, pagetable and swap space use. */ - points = get_mm_rss(p->mm) + atomic_long_read(&p->mm->nr_ptes) + - get_mm_counter(p->mm, MM_SWAPENTS); + points = get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS) + + atomic_long_read(&p->mm->nr_ptes) + mm_nr_pmds(p->mm); task_unlock(p); /* @@ -266,8 +266,6 @@ enum oom_scan_t oom_scan_process_thread(struct task_struct *task, * Don't allow any other task to have access to the reserves. */ if (test_tsk_thread_flag(task, TIF_MEMDIE)) { - if (unlikely(frozen(task))) - __thaw_task(task); if (!force_kill) return OOM_SCAN_ABORT; } @@ -353,7 +351,7 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) struct task_struct *p; struct task_struct *task; - pr_info("[ pid ] uid tgid total_vm rss nr_ptes swapents oom_score_adj name\n"); + pr_info("[ pid ] uid tgid total_vm rss nr_ptes nr_pmds swapents oom_score_adj name\n"); rcu_read_lock(); for_each_process(p) { if (oom_unkillable_task(p, memcg, nodemask)) @@ -369,10 +367,11 @@ static void dump_tasks(struct mem_cgroup *memcg, const nodemask_t *nodemask) continue; } - pr_info("[%5d] %5d %5d %8lu %8lu %7ld %8lu %5hd %s\n", + pr_info("[%5d] %5d %5d %8lu %8lu %7ld %7ld %8lu %5hd %s\n", task->pid, from_kuid(&init_user_ns, task_uid(task)), task->tgid, task->mm->total_vm, get_mm_rss(task->mm), atomic_long_read(&task->mm->nr_ptes), + mm_nr_pmds(task->mm), get_mm_counter(task->mm, MM_SWAPENTS), task->signal->oom_score_adj, task->comm); task_unlock(task); @@ -400,20 +399,98 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } /* - * Number of OOM killer invocations (including memcg OOM killer). - * Primarily used by PM freezer to check for potential races with - * OOM killed frozen task. + * Number of OOM victims in flight */ -static atomic_t oom_kills = ATOMIC_INIT(0); +static atomic_t oom_victims = ATOMIC_INIT(0); +static DECLARE_WAIT_QUEUE_HEAD(oom_victims_wait); -int oom_kills_count(void) +bool oom_killer_disabled __read_mostly; +static DECLARE_RWSEM(oom_sem); + +/** + * mark_tsk_oom_victim - marks the given taks as OOM victim. + * @tsk: task to mark + * + * Has to be called with oom_sem taken for read and never after + * oom has been disabled already. + */ +void mark_tsk_oom_victim(struct task_struct *tsk) { - return atomic_read(&oom_kills); + WARN_ON(oom_killer_disabled); + /* OOM killer might race with memcg OOM */ + if (test_and_set_tsk_thread_flag(tsk, TIF_MEMDIE)) + return; + /* + * Make sure that the task is woken up from uninterruptible sleep + * if it is frozen because OOM killer wouldn't be able to free + * any memory and livelock. freezing_slow_path will tell the freezer + * that TIF_MEMDIE tasks should be ignored. + */ + __thaw_task(tsk); + atomic_inc(&oom_victims); +} + +/** + * unmark_oom_victim - unmarks the current task as OOM victim. + * + * Wakes up all waiters in oom_killer_disable() + */ +void unmark_oom_victim(void) +{ + if (!test_and_clear_thread_flag(TIF_MEMDIE)) + return; + + down_read(&oom_sem); + /* + * There is no need to signal the lasst oom_victim if there + * is nobody who cares. + */ + if (!atomic_dec_return(&oom_victims) && oom_killer_disabled) + wake_up_all(&oom_victims_wait); + up_read(&oom_sem); +} + +/** + * oom_killer_disable - disable OOM killer + * + * Forces all page allocations to fail rather than trigger OOM killer. + * Will block and wait until all OOM victims are killed. + * + * The function cannot be called when there are runnable user tasks because + * the userspace would see unexpected allocation failures as a result. Any + * new usage of this function should be consulted with MM people. + * + * Returns true if successful and false if the OOM killer cannot be + * disabled. + */ +bool oom_killer_disable(void) +{ + /* + * Make sure to not race with an ongoing OOM killer + * and that the current is not the victim. + */ + down_write(&oom_sem); + if (test_thread_flag(TIF_MEMDIE)) { + up_write(&oom_sem); + return false; + } + + oom_killer_disabled = true; + up_write(&oom_sem); + + wait_event(oom_victims_wait, !atomic_read(&oom_victims)); + + return true; } -void note_oom_kill(void) +/** + * oom_killer_enable - enable OOM killer + */ +void oom_killer_enable(void) { - atomic_inc(&oom_kills); + down_write(&oom_sem); + oom_killer_disabled = false; + up_write(&oom_sem); } #define K(x) ((x) << (PAGE_SHIFT-10)) @@ -438,11 +515,14 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, * If the task is already exiting, don't alarm the sysadmin or kill * its children or threads, just set TIF_MEMDIE so it can die quickly */ - if (task_will_free_mem(p)) { - set_tsk_thread_flag(p, TIF_MEMDIE); + task_lock(p); + if (p->mm && task_will_free_mem(p)) { + mark_tsk_oom_victim(p); + task_unlock(p); put_task_struct(p); return; } + task_unlock(p); if (__ratelimit(&oom_rs)) dump_header(p, gfp_mask, order, memcg, nodemask); @@ -492,6 +572,7 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, /* mm cannot safely be dereferenced after task_unlock(victim) */ mm = victim->mm; + mark_tsk_oom_victim(victim); pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", task_pid_nr(victim), victim->comm, K(victim->mm->total_vm), K(get_mm_counter(victim->mm, MM_ANONPAGES)), @@ -522,7 +603,6 @@ void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, } rcu_read_unlock(); - set_tsk_thread_flag(victim, TIF_MEMDIE); do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); put_task_struct(victim); } @@ -611,7 +691,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) } /** - * out_of_memory - kill the "best" process when we run out of memory + * __out_of_memory - kill the "best" process when we run out of memory * @zonelist: zonelist pointer * @gfp_mask: memory allocation flags * @order: amount of memory being requested as a power of 2 @@ -623,7 +703,7 @@ void oom_zonelist_unlock(struct zonelist *zonelist, gfp_t gfp_mask) * OR try to be smart about which process to kill. Note that we * don't have to be perfect here, we just have to be good. */ -void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, +static void __out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, int order, nodemask_t *nodemask, bool force_kill) { const nodemask_t *mpol_mask; @@ -643,9 +723,13 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, * If current has a pending SIGKILL or is exiting, then automatically * select it. The goal is to allow it to allocate so that it may * quickly exit and free its memory. + * + * But don't select if current has already released its mm and cleared + * TIF_MEMDIE flag at exit_mm(), otherwise an OOM livelock may occur. */ - if (fatal_signal_pending(current) || task_will_free_mem(current)) { - set_thread_flag(TIF_MEMDIE); + if (current->mm && + (fatal_signal_pending(current) || task_will_free_mem(current))) { + mark_tsk_oom_victim(current); return; } @@ -688,6 +772,32 @@ out: schedule_timeout_killable(1); } +/** + * out_of_memory - tries to invoke OOM killer. + * @zonelist: zonelist pointer + * @gfp_mask: memory allocation flags + * @order: amount of memory being requested as a power of 2 + * @nodemask: nodemask passed to page allocator + * @force_kill: true if a task must be killed, even if others are exiting + * + * invokes __out_of_memory if the OOM is not disabled by oom_killer_disable() + * when it returns false. Otherwise returns true. + */ +bool out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, + int order, nodemask_t *nodemask, bool force_kill) +{ + bool ret = false; + + down_read(&oom_sem); + if (!oom_killer_disabled) { + __out_of_memory(zonelist, gfp_mask, order, nodemask, force_kill); + ret = true; + } + up_read(&oom_sem); + + return ret; +} + /* * The pagefault handler calls here because it is out of memory, so kill a * memory-hogging task. If any populated zone has ZONE_OOM_LOCKED set, a @@ -697,12 +807,25 @@ void pagefault_out_of_memory(void) { struct zonelist *zonelist; + down_read(&oom_sem); if (mem_cgroup_oom_synchronize(true)) - return; + goto unlock; zonelist = node_zonelist(first_memory_node, GFP_KERNEL); if (oom_zonelist_trylock(zonelist, GFP_KERNEL)) { - out_of_memory(NULL, 0, 0, NULL, false); + if (!oom_killer_disabled) + __out_of_memory(NULL, 0, 0, NULL, false); + else + /* + * There shouldn't be any user tasks runable while the + * OOM killer is disabled so the current task has to + * be a racing OOM victim for which oom_killer_disable() + * is waiting for. + */ + WARN_ON(test_thread_flag(TIF_MEMDIE)); + oom_zonelist_unlock(zonelist, GFP_KERNEL); } +unlock: + up_read(&oom_sem); } diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6f4335238e33..45e187b2d971 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1351,7 +1351,7 @@ static void balance_dirty_pages(struct address_space *mapping, unsigned long task_ratelimit; unsigned long dirty_ratelimit; unsigned long pos_ratio; - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); bool strictlimit = bdi->capabilities & BDI_CAP_STRICTLIMIT; unsigned long start_time = jiffies; @@ -1574,7 +1574,7 @@ DEFINE_PER_CPU(int, dirty_throttle_leaks) = 0; */ void balance_dirty_pages_ratelimited(struct address_space *mapping) { - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); int ratelimit; int *p; @@ -1929,7 +1929,7 @@ continue_unlock: if (!clear_page_dirty_for_io(page)) goto continue_unlock; - trace_wbc_writepage(wbc, mapping->backing_dev_info); + trace_wbc_writepage(wbc, inode_to_bdi(mapping->host)); ret = (*writepage)(page, wbc, data); if (unlikely(ret)) { if (ret == AOP_WRITEPAGE_ACTIVATE) { @@ -2094,10 +2094,12 @@ void account_page_dirtied(struct page *page, struct address_space *mapping) trace_writeback_dirty_page(page, mapping); if (mapping_cap_account_dirty(mapping)) { + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); + __inc_zone_page_state(page, NR_FILE_DIRTY); __inc_zone_page_state(page, NR_DIRTIED); - __inc_bdi_stat(mapping->backing_dev_info, BDI_RECLAIMABLE); - __inc_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED); + __inc_bdi_stat(bdi, BDI_RECLAIMABLE); + __inc_bdi_stat(bdi, BDI_DIRTIED); task_io_account_write(PAGE_CACHE_SIZE); current->nr_dirtied++; this_cpu_inc(bdp_ratelimits); @@ -2156,7 +2158,7 @@ void account_page_redirty(struct page *page) if (mapping && mapping_cap_account_dirty(mapping)) { current->nr_dirtied--; dec_zone_page_state(page, NR_DIRTIED); - dec_bdi_stat(mapping->backing_dev_info, BDI_DIRTIED); + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_DIRTIED); } } EXPORT_SYMBOL(account_page_redirty); @@ -2168,9 +2170,12 @@ EXPORT_SYMBOL(account_page_redirty); */ int redirty_page_for_writepage(struct writeback_control *wbc, struct page *page) { + int ret; + wbc->pages_skipped++; + ret = __set_page_dirty_nobuffers(page); account_page_redirty(page); - return __set_page_dirty_nobuffers(page); + return ret; } EXPORT_SYMBOL(redirty_page_for_writepage); @@ -2295,7 +2300,7 @@ int clear_page_dirty_for_io(struct page *page) */ if (TestClearPageDirty(page)) { dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(mapping->backing_dev_info, + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); return 1; } @@ -2308,14 +2313,12 @@ EXPORT_SYMBOL(clear_page_dirty_for_io); int test_clear_page_writeback(struct page *page) { struct address_space *mapping = page_mapping(page); - unsigned long memcg_flags; struct mem_cgroup *memcg; - bool locked; int ret; - memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); + memcg = mem_cgroup_begin_page_stat(page); if (mapping) { - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2338,21 +2341,19 @@ int test_clear_page_writeback(struct page *page) dec_zone_page_state(page, NR_WRITEBACK); inc_zone_page_state(page, NR_WRITTEN); } - mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags); + mem_cgroup_end_page_stat(memcg); return ret; } int __test_set_page_writeback(struct page *page, bool keep_write) { struct address_space *mapping = page_mapping(page); - unsigned long memcg_flags; struct mem_cgroup *memcg; - bool locked; int ret; - memcg = mem_cgroup_begin_page_stat(page, &locked, &memcg_flags); + memcg = mem_cgroup_begin_page_stat(page); if (mapping) { - struct backing_dev_info *bdi = mapping->backing_dev_info; + struct backing_dev_info *bdi = inode_to_bdi(mapping->host); unsigned long flags; spin_lock_irqsave(&mapping->tree_lock, flags); @@ -2380,7 +2381,7 @@ int __test_set_page_writeback(struct page *page, bool keep_write) mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_WRITEBACK); inc_zone_page_state(page, NR_WRITEBACK); } - mem_cgroup_end_page_stat(memcg, &locked, &memcg_flags); + mem_cgroup_end_page_stat(memcg); return ret; } @@ -2406,12 +2407,7 @@ EXPORT_SYMBOL(mapping_tagged); */ void wait_for_stable_page(struct page *page) { - struct address_space *mapping = page_mapping(page); - struct backing_dev_info *bdi = mapping->backing_dev_info; - - if (!bdi_cap_stable_pages_required(bdi)) - return; - - wait_on_page_writeback(page); + if (bdi_cap_stable_pages_required(inode_to_bdi(page->mapping->host))) + wait_on_page_writeback(page); } EXPORT_SYMBOL_GPL(wait_for_stable_page); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8e20f9c2fa5a..a47f0b229a1a 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -25,6 +25,7 @@ #include <linux/compiler.h> #include <linux/kernel.h> #include <linux/kmemcheck.h> +#include <linux/kasan.h> #include <linux/module.h> #include <linux/suspend.h> #include <linux/pagevec.h> @@ -172,7 +173,7 @@ static void __free_pages_ok(struct page *page, unsigned int order); * 1G machine -> (16M dma, 784M normal, 224M high) * NORMAL allocation will leave 784M/256 of ram reserved in the ZONE_DMA * HIGHMEM allocation will leave 224M/32 of ram reserved in ZONE_NORMAL - * HIGHMEM allocation will (224M+784M)/256 of ram reserved in ZONE_DMA + * HIGHMEM allocation will leave (224M+784M)/256 of ram reserved in ZONE_DMA * * TBD: should special case ZONE_DMA32 machines here - in those we normally * don't need any ZONE_NORMAL reservation @@ -244,8 +245,6 @@ void set_pageblock_migratetype(struct page *page, int 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) { @@ -381,36 +380,6 @@ void prep_compound_page(struct page *page, unsigned long order) } } -/* update __split_huge_page_refcount if you change this function */ -static int destroy_compound_page(struct page *page, unsigned long order) -{ - int i; - int nr_pages = 1 << order; - int bad = 0; - - if (unlikely(compound_order(page) != order)) { - bad_page(page, "wrong compound order", 0); - bad++; - } - - __ClearPageHead(page); - - for (i = 1; i < nr_pages; i++) { - struct page *p = page + i; - - if (unlikely(!PageTail(p))) { - bad_page(page, "PageTail not set", 0); - bad++; - } else if (unlikely(p->first_page != page)) { - bad_page(page, "first_page not consistent", 0); - bad++; - } - __ClearPageTail(p); - } - - return bad; -} - static inline void prep_zero_page(struct page *page, unsigned int order, gfp_t gfp_flags) { @@ -552,17 +521,15 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; if (page_is_guard(buddy) && page_order(buddy) == order) { - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - if (page_zone_id(page) != page_zone_id(buddy)) return 0; + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - /* * zone check is done late to avoid uselessly * calculating zone/node ids for pages that could @@ -571,6 +538,8 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, if (page_zone_id(page) != page_zone_id(buddy)) return 0; + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + return 1; } return 0; @@ -613,10 +582,7 @@ static inline void __free_one_page(struct page *page, int max_order = MAX_ORDER; VM_BUG_ON(!zone_is_initialized(zone)); - - if (unlikely(PageCompound(page))) - if (unlikely(destroy_compound_page(page, order))) - return; + VM_BUG_ON_PAGE(page->flags & PAGE_FLAGS_CHECK_AT_PREP, page); VM_BUG_ON(migratetype == -1); if (is_migrate_isolate(migratetype)) { @@ -797,21 +763,41 @@ static void free_one_page(struct zone *zone, spin_unlock(&zone->lock); } +static int free_tail_pages_check(struct page *head_page, struct page *page) +{ + if (!IS_ENABLED(CONFIG_DEBUG_VM)) + return 0; + if (unlikely(!PageTail(page))) { + bad_page(page, "PageTail not set", 0); + return 1; + } + if (unlikely(page->first_page != head_page)) { + bad_page(page, "first_page not consistent", 0); + return 1; + } + return 0; +} + static bool free_pages_prepare(struct page *page, unsigned int order) { - int i; - int bad = 0; + bool compound = PageCompound(page); + int i, bad = 0; VM_BUG_ON_PAGE(PageTail(page), page); - VM_BUG_ON_PAGE(PageHead(page) && compound_order(page) != order, page); + VM_BUG_ON_PAGE(compound && compound_order(page) != order, page); trace_mm_page_free(page, order); kmemcheck_free_shadow(page, order); + kasan_free_pages(page, order); if (PageAnon(page)) page->mapping = NULL; - for (i = 0; i < (1 << order); i++) + bad += free_pages_check(page); + for (i = 1; i < (1 << order); i++) { + if (compound) + bad += free_tail_pages_check(page, page + i); bad += free_pages_check(page + i); + } if (bad) return false; @@ -970,7 +956,8 @@ static inline int check_new_page(struct page *page) return 0; } -static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) +static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags, + int alloc_flags) { int i; @@ -985,6 +972,7 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) arch_alloc_page(page, order); kernel_map_pages(page, 1 << order, 1); + kasan_alloc_pages(page, order); if (gfp_flags & __GFP_ZERO) prep_zero_page(page, order, gfp_flags); @@ -994,6 +982,14 @@ static int prep_new_page(struct page *page, unsigned int order, gfp_t gfp_flags) set_page_owner(page, order, gfp_flags); + /* + * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was necessary to + * allocate the page. The expectation is that the caller is taking + * steps that will free more memory. The caller should avoid the page + * being used for !PFMEMALLOC purposes. + */ + page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); + return 0; } @@ -1130,39 +1126,34 @@ static void change_pageblock_range(struct page *pageblock_page, } /* - * If breaking a large block of pages, move all free pages to the preferred - * allocation list. If falling back for a reclaimable kernel allocation, be - * more aggressive about taking ownership of free pages. + * When we are falling back to another migratetype during allocation, try to + * steal extra free pages from the same pageblocks to satisfy further + * allocations, instead of polluting multiple pageblocks. * - * On the other hand, never change migration type of MIGRATE_CMA pageblocks - * nor move CMA pages to different free lists. We don't want unmovable pages - * to be allocated from MIGRATE_CMA areas. + * If we are stealing a relatively large buddy page, it is likely there will + * be more free pages in the pageblock, so try to steal them all. For + * reclaimable and unmovable allocations, we steal regardless of page size, + * as fragmentation caused by those allocations polluting movable pageblocks + * is worse than movable allocations stealing from unmovable and reclaimable + * pageblocks. * - * Returns the new migratetype of the pageblock (or the same old migratetype - * if it was unchanged). + * If we claim more than half of the pageblock, change pageblock's migratetype + * as well. */ -static int try_to_steal_freepages(struct zone *zone, struct page *page, +static void try_to_steal_freepages(struct zone *zone, struct page *page, int start_type, int fallback_type) { int current_order = page_order(page); - /* - * When borrowing from MIGRATE_CMA, we need to release the excess - * buddy pages to CMA itself. We also ensure the freepage_migratetype - * is set to CMA so it is returned to the correct freelist in case - * the page ends up being not actually allocated from the pcp lists. - */ - if (is_migrate_cma(fallback_type)) - return fallback_type; - /* Take ownership for orders >= pageblock_order */ if (current_order >= pageblock_order) { change_pageblock_range(page, current_order, start_type); - return start_type; + return; } if (current_order >= pageblock_order / 2 || start_type == MIGRATE_RECLAIMABLE || + start_type == MIGRATE_UNMOVABLE || page_group_by_mobility_disabled) { int pages; @@ -1170,15 +1161,9 @@ static int try_to_steal_freepages(struct zone *zone, struct page *page, /* Claim the whole block if over half of it is free */ if (pages >= (1 << (pageblock_order-1)) || - page_group_by_mobility_disabled) { - + page_group_by_mobility_disabled) set_pageblock_migratetype(page, start_type); - return start_type; - } - } - - return fallback_type; } /* Remove an element from the buddy allocator from the fallback list */ @@ -1188,14 +1173,15 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) struct free_area *area; unsigned int current_order; struct page *page; - int migratetype, new_type, i; /* Find the largest possible block of pages in the other list */ for (current_order = MAX_ORDER-1; current_order >= order && current_order <= MAX_ORDER-1; --current_order) { + int i; for (i = 0;; i++) { - migratetype = fallbacks[start_migratetype][i]; + int migratetype = fallbacks[start_migratetype][i]; + int buddy_type = start_migratetype; /* MIGRATE_RESERVE handled later if necessary */ if (migratetype == MIGRATE_RESERVE) @@ -1209,25 +1195,39 @@ __rmqueue_fallback(struct zone *zone, unsigned int order, int start_migratetype) struct page, lru); area->nr_free--; - new_type = try_to_steal_freepages(zone, page, - start_migratetype, - migratetype); + if (!is_migrate_cma(migratetype)) { + try_to_steal_freepages(zone, page, + start_migratetype, + migratetype); + } else { + /* + * When borrowing from MIGRATE_CMA, we need to + * release the excess buddy pages to CMA + * itself, and we do not try to steal extra + * free pages. + */ + buddy_type = migratetype; + } /* Remove the page from the freelists */ list_del(&page->lru); rmv_page_order(page); expand(zone, page, order, current_order, area, - new_type); - /* The freepage_migratetype may differ from pageblock's + buddy_type); + + /* + * The freepage_migratetype may differ from pageblock's * migratetype depending on the decisions in - * try_to_steal_freepages. This is OK as long as it does - * not differ for MIGRATE_CMA type. + * try_to_steal_freepages(). This is OK as long as it + * does not differ for MIGRATE_CMA pageblocks. For CMA + * we need to make sure unallocated pages flushed from + * pcp lists are returned to the correct freelist. */ - set_freepage_migratetype(page, new_type); + set_freepage_migratetype(page, buddy_type); trace_mm_page_alloc_extfrag(page, order, current_order, - start_migratetype, migratetype, new_type); + start_migratetype, migratetype); return page; } @@ -1642,9 +1642,7 @@ int split_free_page(struct page *page) } /* - * Really, prep_compound_page() should be called from __rmqueue_bulk(). But - * we cheat by calling it from here, in the order > 0 path. Saves a branch - * or two. + * Allocate a page from the given zone. Use pcplists for order-0 allocations. */ static inline struct page *buffered_rmqueue(struct zone *preferred_zone, @@ -1655,7 +1653,6 @@ struct page *buffered_rmqueue(struct zone *preferred_zone, struct page *page; bool cold = ((gfp_flags & __GFP_COLD) != 0); -again: if (likely(order == 0)) { struct per_cpu_pages *pcp; struct list_head *list; @@ -1711,8 +1708,6 @@ again: local_irq_restore(flags); VM_BUG_ON_PAGE(bad_range(zone, page), page); - if (prep_new_page(page, order, gfp_flags)) - goto again; return page; failed: @@ -2033,10 +2028,10 @@ static void reset_alloc_batches(struct zone *preferred_zone) * a page. */ 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 zone *preferred_zone, int classzone_idx, int migratetype) +get_page_from_freelist(gfp_t gfp_mask, unsigned int order, int alloc_flags, + const struct alloc_context *ac) { + struct zonelist *zonelist = ac->zonelist; struct zoneref *z; struct page *page = NULL; struct zone *zone; @@ -2055,8 +2050,8 @@ zonelist_scan: * Scan zonelist, looking for a zone with enough free. * See also __cpuset_node_allowed() comment in kernel/cpuset.c. */ - for_each_zone_zonelist_nodemask(zone, z, zonelist, - high_zoneidx, nodemask) { + for_each_zone_zonelist_nodemask(zone, z, zonelist, ac->high_zoneidx, + ac->nodemask) { unsigned long mark; if (IS_ENABLED(CONFIG_NUMA) && zlc_active && @@ -2073,7 +2068,7 @@ zonelist_scan: * time the page has in memory before being reclaimed. */ if (alloc_flags & ALLOC_FAIR) { - if (!zone_local(preferred_zone, zone)) + if (!zone_local(ac->preferred_zone, zone)) break; if (test_bit(ZONE_FAIR_DEPLETED, &zone->flags)) { nr_fair_skipped++; @@ -2111,7 +2106,7 @@ zonelist_scan: mark = zone->watermark[alloc_flags & ALLOC_WMARK_MASK]; if (!zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) { + ac->classzone_idx, alloc_flags)) { int ret; /* Checked here to keep the fast path fast */ @@ -2132,7 +2127,7 @@ zonelist_scan: } if (zone_reclaim_mode == 0 || - !zone_allows_reclaim(preferred_zone, zone)) + !zone_allows_reclaim(ac->preferred_zone, zone)) goto this_zone_full; /* @@ -2154,7 +2149,7 @@ zonelist_scan: default: /* did we reclaim enough */ if (zone_watermark_ok(zone, order, mark, - classzone_idx, alloc_flags)) + ac->classzone_idx, alloc_flags)) goto try_this_zone; /* @@ -2175,27 +2170,18 @@ zonelist_scan: } try_this_zone: - page = buffered_rmqueue(preferred_zone, zone, order, - gfp_mask, migratetype); - if (page) - break; + page = buffered_rmqueue(ac->preferred_zone, zone, order, + gfp_mask, ac->migratetype); + if (page) { + if (prep_new_page(page, order, gfp_mask, alloc_flags)) + goto try_this_zone; + return page; + } this_zone_full: if (IS_ENABLED(CONFIG_NUMA) && zlc_active) zlc_mark_zone_full(zonelist, z); } - if (page) { - /* - * page->pfmemalloc is set when ALLOC_NO_WATERMARKS was - * necessary to allocate the page. The expectation is - * that the caller is taking steps that will free more - * memory. The caller should avoid the page being used - * for !PFMEMALLOC purposes. - */ - page->pfmemalloc = !!(alloc_flags & ALLOC_NO_WATERMARKS); - return page; - } - /* * The first pass makes sure allocations are spread fairly within the * local node. However, the local node might have free pages left @@ -2208,7 +2194,7 @@ this_zone_full: alloc_flags &= ~ALLOC_FAIR; if (nr_fair_skipped) { zonelist_rescan = true; - reset_alloc_batches(preferred_zone); + reset_alloc_batches(ac->preferred_zone); } if (nr_online_nodes > 1) zonelist_rescan = true; @@ -2330,44 +2316,29 @@ should_alloc_retry(gfp_t gfp_mask, unsigned int order, 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 classzone_idx, int migratetype, unsigned long *did_some_progress) + const struct alloc_context *ac, unsigned long *did_some_progress) { struct page *page; *did_some_progress = 0; - if (oom_killer_disabled) - return NULL; - /* * Acquire the per-zone oom lock for each zone. If that * fails, somebody else is making progress for us. */ - if (!oom_zonelist_trylock(zonelist, gfp_mask)) { + if (!oom_zonelist_trylock(ac->zonelist, gfp_mask)) { *did_some_progress = 1; schedule_timeout_uninterruptible(1); return NULL; } /* - * PM-freezer should be notified that there might be an OOM killer on - * its way to kill and wake somebody up. This is too early and we might - * end up not killing anything but false positives are acceptable. - * See freeze_processes. - */ - note_oom_kill(); - - /* * 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, classzone_idx, migratetype); + page = get_page_from_freelist(gfp_mask | __GFP_HARDWALL, order, + ALLOC_WMARK_HIGH|ALLOC_CPUSET, ac); if (page) goto out; @@ -2379,7 +2350,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, if (order > PAGE_ALLOC_COSTLY_ORDER) goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ - if (high_zoneidx < ZONE_NORMAL) + if (ac->high_zoneidx < ZONE_NORMAL) goto out; /* The OOM killer does not compensate for light reclaim */ if (!(gfp_mask & __GFP_FS)) @@ -2395,10 +2366,10 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; } /* Exhausted what can be done so it's blamo time */ - out_of_memory(zonelist, gfp_mask, order, nodemask, false); - *did_some_progress = 1; + if (out_of_memory(ac->zonelist, gfp_mask, order, ac->nodemask, false)) + *did_some_progress = 1; out: - oom_zonelist_unlock(zonelist, gfp_mask); + oom_zonelist_unlock(ac->zonelist, gfp_mask); return page; } @@ -2406,10 +2377,9 @@ out: /* Try memory compaction for high-order allocations before reclaim */ static struct page * __alloc_pages_direct_compact(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 classzone_idx, int migratetype, enum migrate_mode mode, - int *contended_compaction, bool *deferred_compaction) + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended_compaction, + bool *deferred_compaction) { unsigned long compact_result; struct page *page; @@ -2418,10 +2388,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, return NULL; current->flags |= PF_MEMALLOC; - compact_result = try_to_compact_pages(zonelist, order, gfp_mask, - nodemask, mode, - contended_compaction, - alloc_flags, classzone_idx); + compact_result = try_to_compact_pages(gfp_mask, order, alloc_flags, ac, + mode, contended_compaction); current->flags &= ~PF_MEMALLOC; switch (compact_result) { @@ -2440,10 +2408,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, */ count_vm_event(COMPACTSTALL); - page = get_page_from_freelist(gfp_mask, nodemask, - order, zonelist, high_zoneidx, - alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, classzone_idx, migratetype); + page = get_page_from_freelist(gfp_mask, order, + alloc_flags & ~ALLOC_NO_WATERMARKS, ac); if (page) { struct zone *zone = page_zone(page); @@ -2467,10 +2433,9 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, #else static inline struct page * __alloc_pages_direct_compact(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 classzone_idx, int migratetype, enum migrate_mode mode, - int *contended_compaction, bool *deferred_compaction) + int alloc_flags, const struct alloc_context *ac, + enum migrate_mode mode, int *contended_compaction, + bool *deferred_compaction) { return NULL; } @@ -2478,8 +2443,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, /* Perform direct synchronous page reclaim */ static int -__perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, - nodemask_t *nodemask) +__perform_reclaim(gfp_t gfp_mask, unsigned int order, + const struct alloc_context *ac) { struct reclaim_state reclaim_state; int progress; @@ -2493,7 +2458,8 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, reclaim_state.reclaimed_slab = 0; current->reclaim_state = &reclaim_state; - progress = try_to_free_pages(zonelist, order, gfp_mask, nodemask); + progress = try_to_free_pages(ac->zonelist, order, gfp_mask, + ac->nodemask); current->reclaim_state = NULL; lockdep_clear_current_reclaim_state(); @@ -2507,28 +2473,23 @@ __perform_reclaim(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, /* 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 classzone_idx, int migratetype, unsigned long *did_some_progress) + int alloc_flags, const struct alloc_context *ac, + unsigned long *did_some_progress) { struct page *page = NULL; bool drained = false; - *did_some_progress = __perform_reclaim(gfp_mask, order, zonelist, - nodemask); + *did_some_progress = __perform_reclaim(gfp_mask, order, ac); if (unlikely(!(*did_some_progress))) return NULL; /* After successful reclaim, reconsider all zones for allocation */ if (IS_ENABLED(CONFIG_NUMA)) - zlc_clear_zones_full(zonelist); + zlc_clear_zones_full(ac->zonelist); retry: - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, - alloc_flags & ~ALLOC_NO_WATERMARKS, - preferred_zone, classzone_idx, - migratetype); + page = get_page_from_freelist(gfp_mask, order, + alloc_flags & ~ALLOC_NO_WATERMARKS, ac); /* * If an allocation failed after direct reclaim, it could be because @@ -2549,36 +2510,30 @@ retry: */ 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 classzone_idx, int migratetype) + const struct alloc_context *ac) { struct page *page; do { - page = get_page_from_freelist(gfp_mask, nodemask, order, - zonelist, high_zoneidx, ALLOC_NO_WATERMARKS, - preferred_zone, classzone_idx, migratetype); + page = get_page_from_freelist(gfp_mask, order, + ALLOC_NO_WATERMARKS, ac); if (!page && gfp_mask & __GFP_NOFAIL) - wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); + wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, + HZ/50); } while (!page && (gfp_mask & __GFP_NOFAIL)); return page; } -static void wake_all_kswapds(unsigned int order, - struct zonelist *zonelist, - enum zone_type high_zoneidx, - struct zone *preferred_zone, - nodemask_t *nodemask) +static void wake_all_kswapds(unsigned int order, const struct alloc_context *ac) { struct zoneref *z; struct zone *zone; - for_each_zone_zonelist_nodemask(zone, z, zonelist, - high_zoneidx, nodemask) - wakeup_kswapd(zone, order, zone_idx(preferred_zone)); + for_each_zone_zonelist_nodemask(zone, z, ac->zonelist, + ac->high_zoneidx, ac->nodemask) + wakeup_kswapd(zone, order, zone_idx(ac->preferred_zone)); } static inline int @@ -2637,9 +2592,7 @@ bool gfp_pfmemalloc_allowed(gfp_t gfp_mask) 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 classzone_idx, int migratetype) + struct alloc_context *ac) { const gfp_t wait = gfp_mask & __GFP_WAIT; struct page *page = NULL; @@ -2675,8 +2628,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, retry: if (!(gfp_mask & __GFP_NO_KSWAPD)) - wake_all_kswapds(order, zonelist, high_zoneidx, - preferred_zone, nodemask); + wake_all_kswapds(order, ac); /* * OK, we're below the kswapd watermark and have kicked background @@ -2689,17 +2641,16 @@ retry: * Find the true preferred zone if the allocation is unconstrained by * cpusets. */ - if (!(alloc_flags & ALLOC_CPUSET) && !nodemask) { + if (!(alloc_flags & ALLOC_CPUSET) && !ac->nodemask) { struct zoneref *preferred_zoneref; - preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, - NULL, &preferred_zone); - classzone_idx = zonelist_zone_idx(preferred_zoneref); + preferred_zoneref = first_zones_zonelist(ac->zonelist, + ac->high_zoneidx, NULL, &ac->preferred_zone); + ac->classzone_idx = zonelist_zone_idx(preferred_zoneref); } /* 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 & ~ALLOC_NO_WATERMARKS, - preferred_zone, classzone_idx, migratetype); + page = get_page_from_freelist(gfp_mask, order, + alloc_flags & ~ALLOC_NO_WATERMARKS, ac); if (page) goto got_pg; @@ -2710,11 +2661,10 @@ retry: * the allocation is high priority and these type of * allocations are system rather than user orientated */ - zonelist = node_zonelist(numa_node_id(), gfp_mask); + ac->zonelist = node_zonelist(numa_node_id(), gfp_mask); + + page = __alloc_pages_high_priority(gfp_mask, order, ac); - page = __alloc_pages_high_priority(gfp_mask, order, - zonelist, high_zoneidx, nodemask, - preferred_zone, classzone_idx, migratetype); if (page) { goto got_pg; } @@ -2743,11 +2693,9 @@ retry: * Try direct compaction. The first pass is asynchronous. Subsequent * attempts after direct reclaim are synchronous */ - page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, - high_zoneidx, nodemask, alloc_flags, - preferred_zone, - classzone_idx, migratetype, - migration_mode, &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, alloc_flags, ac, + migration_mode, + &contended_compaction, &deferred_compaction); if (page) goto got_pg; @@ -2793,12 +2741,8 @@ retry: migration_mode = MIGRATE_SYNC_LIGHT; /* Try direct reclaim and then allocating */ - page = __alloc_pages_direct_reclaim(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, - alloc_flags, preferred_zone, - classzone_idx, migratetype, - &did_some_progress); + page = __alloc_pages_direct_reclaim(gfp_mask, order, alloc_flags, ac, + &did_some_progress); if (page) goto got_pg; @@ -2812,17 +2756,15 @@ retry: * start OOM killing tasks. */ if (!did_some_progress) { - page = __alloc_pages_may_oom(gfp_mask, order, zonelist, - high_zoneidx, nodemask, - preferred_zone, classzone_idx, - migratetype,&did_some_progress); + page = __alloc_pages_may_oom(gfp_mask, order, ac, + &did_some_progress); if (page) goto got_pg; if (!did_some_progress) goto nopage; } /* Wait for some write requests to complete then retry */ - wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); + wait_iff_congested(ac->preferred_zone, BLK_RW_ASYNC, HZ/50); goto retry; } else { /* @@ -2830,11 +2772,9 @@ retry: * direct reclaim and reclaim/compaction depends on compaction * being called after reclaim so call directly if necessary */ - page = __alloc_pages_direct_compact(gfp_mask, order, zonelist, - high_zoneidx, nodemask, alloc_flags, - preferred_zone, - classzone_idx, migratetype, - migration_mode, &contended_compaction, + page = __alloc_pages_direct_compact(gfp_mask, order, + alloc_flags, ac, migration_mode, + &contended_compaction, &deferred_compaction); if (page) goto got_pg; @@ -2842,11 +2782,7 @@ retry: nopage: warn_alloc_failed(gfp_mask, order, NULL); - return page; got_pg: - if (kmemcheck_enabled) - kmemcheck_pagealloc_alloc(page, order, gfp_mask); - return page; } @@ -2857,14 +2793,16 @@ 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 zoneref *preferred_zoneref; struct page *page = NULL; - int migratetype = gfpflags_to_migratetype(gfp_mask); unsigned int cpuset_mems_cookie; int alloc_flags = ALLOC_WMARK_LOW|ALLOC_CPUSET|ALLOC_FAIR; - int classzone_idx; + gfp_t alloc_mask; /* The gfp_t that was actually used for allocation */ + struct alloc_context ac = { + .high_zoneidx = gfp_zone(gfp_mask), + .nodemask = nodemask, + .migratetype = gfpflags_to_migratetype(gfp_mask), + }; gfp_mask &= gfp_allowed_mask; @@ -2883,37 +2821,40 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (unlikely(!zonelist->_zonerefs->zone)) return NULL; - if (IS_ENABLED(CONFIG_CMA) && migratetype == MIGRATE_MOVABLE) + if (IS_ENABLED(CONFIG_CMA) && ac.migratetype == MIGRATE_MOVABLE) alloc_flags |= ALLOC_CMA; retry_cpuset: cpuset_mems_cookie = read_mems_allowed_begin(); + /* We set it here, as __alloc_pages_slowpath might have changed it */ + ac.zonelist = zonelist; /* The preferred zone is used for statistics later */ - preferred_zoneref = first_zones_zonelist(zonelist, high_zoneidx, - nodemask ? : &cpuset_current_mems_allowed, - &preferred_zone); - if (!preferred_zone) + preferred_zoneref = first_zones_zonelist(ac.zonelist, ac.high_zoneidx, + ac.nodemask ? : &cpuset_current_mems_allowed, + &ac.preferred_zone); + if (!ac.preferred_zone) goto out; - classzone_idx = zonelist_zone_idx(preferred_zoneref); + ac.classzone_idx = zonelist_zone_idx(preferred_zoneref); /* First allocation attempt */ - page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, - zonelist, high_zoneidx, alloc_flags, - preferred_zone, classzone_idx, migratetype); + alloc_mask = gfp_mask|__GFP_HARDWALL; + page = get_page_from_freelist(alloc_mask, order, alloc_flags, &ac); if (unlikely(!page)) { /* * Runtime PM, block IO and its error handling path * can deadlock because I/O on the device might not * complete. */ - gfp_mask = memalloc_noio_flags(gfp_mask); - page = __alloc_pages_slowpath(gfp_mask, order, - zonelist, high_zoneidx, nodemask, - preferred_zone, classzone_idx, migratetype); + alloc_mask = memalloc_noio_flags(gfp_mask); + + page = __alloc_pages_slowpath(alloc_mask, order, &ac); } - trace_mm_page_alloc(page, order, gfp_mask, migratetype); + if (kmemcheck_enabled && page) + kmemcheck_pagealloc_alloc(page, order, gfp_mask); + + trace_mm_page_alloc(page, order, alloc_mask, ac.migratetype); out: /* @@ -3933,18 +3874,29 @@ static int __build_all_zonelists(void *data) return 0; } +static noinline void __init +build_all_zonelists_init(void) +{ + __build_all_zonelists(NULL); + mminit_verify_zonelist(); + cpuset_init_current_mems_allowed(); +} + /* * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. + * + * __ref due to (1) call of __meminit annotated setup_zone_pageset + * [we're only called with non-NULL zone through __meminit paths] and + * (2) call of __init annotated helper build_all_zonelists_init + * [protected by SYSTEM_BOOTING]. */ void __ref build_all_zonelists(pg_data_t *pgdat, struct zone *zone) { set_zonelist_order(); if (system_state == SYSTEM_BOOTING) { - __build_all_zonelists(NULL); - mminit_verify_zonelist(); - cpuset_init_current_mems_allowed(); + build_all_zonelists_init(); } else { #ifdef CONFIG_MEMORY_HOTPLUG if (zone) @@ -5047,8 +4999,8 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, pgdat->node_start_pfn = node_start_pfn; #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); - printk(KERN_INFO "Initmem setup node %d [mem %#010Lx-%#010Lx]\n", nid, - (u64) start_pfn << PAGE_SHIFT, (u64) (end_pfn << PAGE_SHIFT) - 1); + pr_info("Initmem setup node %d [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, ((u64)end_pfn << PAGE_SHIFT) - 1); #endif calculate_node_totalpages(pgdat, start_pfn, end_pfn, zones_size, zholes_size); @@ -5420,9 +5372,10 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) arch_zone_highest_possible_pfn[i]) pr_cont("empty\n"); else - pr_cont("[mem %0#10lx-%0#10lx]\n", - arch_zone_lowest_possible_pfn[i] << PAGE_SHIFT, - (arch_zone_highest_possible_pfn[i] + pr_cont("[mem %#018Lx-%#018Lx]\n", + (u64)arch_zone_lowest_possible_pfn[i] + << PAGE_SHIFT, + ((u64)arch_zone_highest_possible_pfn[i] << PAGE_SHIFT) - 1); } @@ -5430,15 +5383,16 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) pr_info("Movable zone start for each node\n"); for (i = 0; i < MAX_NUMNODES; i++) { if (zone_movable_pfn[i]) - pr_info(" Node %d: %#010lx\n", i, - zone_movable_pfn[i] << PAGE_SHIFT); + pr_info(" Node %d: %#018Lx\n", i, + (u64)zone_movable_pfn[i] << PAGE_SHIFT); } /* Print out the early node map */ pr_info("Early memory node ranges\n"); for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) - pr_info(" node %3d: [mem %#010lx-%#010lx]\n", nid, - start_pfn << PAGE_SHIFT, (end_pfn << PAGE_SHIFT) - 1); + pr_info(" node %3d: [mem %#018Lx-%#018Lx]\n", nid, + (u64)start_pfn << PAGE_SHIFT, + ((u64)end_pfn << PAGE_SHIFT) - 1); /* Initialise every node */ mminit_verify_pageflags_layout(); diff --git a/mm/page_counter.c b/mm/page_counter.c index a009574fbba9..11b4beda14ba 100644 --- a/mm/page_counter.c +++ b/mm/page_counter.c @@ -166,18 +166,19 @@ int page_counter_limit(struct page_counter *counter, unsigned long limit) /** * page_counter_memparse - memparse() for page counter limits * @buf: string to parse + * @max: string meaning maximum possible value * @nr_pages: returns the result in number of pages * * Returns -EINVAL, or 0 and @nr_pages on success. @nr_pages will be * limited to %PAGE_COUNTER_MAX. */ -int page_counter_memparse(const char *buf, unsigned long *nr_pages) +int page_counter_memparse(const char *buf, const char *max, + unsigned long *nr_pages) { - char unlimited[] = "-1"; char *end; u64 bytes; - if (!strncmp(buf, unlimited, sizeof(unlimited))) { + if (!strcmp(buf, max)) { *nr_pages = PAGE_COUNTER_MAX; return 0; } diff --git a/mm/page_io.c b/mm/page_io.c index 955db8b0d497..e6045804c8d8 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -269,14 +269,9 @@ int __swap_writepage(struct page *page, struct writeback_control *wbc, .bv_len = PAGE_SIZE, .bv_offset = 0 }; - struct iov_iter from = { - .type = ITER_BVEC | WRITE, - .count = PAGE_SIZE, - .iov_offset = 0, - .nr_segs = 1, - }; - from.bvec = &bv; /* older gcc versions are broken */ + struct iov_iter from; + iov_iter_bvec(&from, ITER_BVEC | WRITE, &bv, 1, PAGE_SIZE); init_sync_kiocb(&kiocb, swap_file); kiocb.ki_pos = page_file_offset(page); kiocb.ki_nbytes = PAGE_SIZE; diff --git a/mm/page_owner.c b/mm/page_owner.c index 9ab4a9b5bc09..0993f5f36b01 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -59,20 +59,19 @@ void __reset_page_owner(struct page *page, unsigned int order) void __set_page_owner(struct page *page, unsigned int order, gfp_t gfp_mask) { - struct page_ext *page_ext; - struct stack_trace *trace; - - page_ext = lookup_page_ext(page); + struct page_ext *page_ext = lookup_page_ext(page); + struct stack_trace trace = { + .nr_entries = 0, + .max_entries = ARRAY_SIZE(page_ext->trace_entries), + .entries = &page_ext->trace_entries[0], + .skip = 3, + }; - trace = &page_ext->trace; - trace->nr_entries = 0; - trace->max_entries = ARRAY_SIZE(page_ext->trace_entries); - trace->entries = &page_ext->trace_entries[0]; - trace->skip = 3; - save_stack_trace(&page_ext->trace); + save_stack_trace(&trace); page_ext->order = order; page_ext->gfp_mask = gfp_mask; + page_ext->nr_entries = trace.nr_entries; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); } @@ -84,6 +83,10 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, int ret; int pageblock_mt, page_mt; char *kbuf; + struct stack_trace trace = { + .nr_entries = page_ext->nr_entries, + .entries = &page_ext->trace_entries[0], + }; kbuf = kmalloc(count, GFP_KERNEL); if (!kbuf) @@ -121,8 +124,7 @@ print_page_owner(char __user *buf, size_t count, unsigned long pfn, if (ret >= count) goto err; - ret += snprint_stack_trace(kbuf + ret, count - ret, - &page_ext->trace, 0); + ret += snprint_stack_trace(kbuf + ret, count - ret, &trace, 0); if (ret >= count) goto err; diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ad83195521f2..75c1f2878519 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -35,7 +35,7 @@ static int walk_pmd_range(pud_t *pud, unsigned long addr, unsigned long end, do { again: next = pmd_addr_end(addr, end); - if (pmd_none(*pmd)) { + if (pmd_none(*pmd) || !walk->vma) { if (walk->pte_hole) err = walk->pte_hole(addr, next, walk); if (err) @@ -59,7 +59,7 @@ again: continue; split_huge_page_pmd_mm(walk->mm, addr, pmd); - if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + if (pmd_trans_unstable(pmd)) goto again; err = walk_pte_range(pmd, addr, next, walk); if (err) @@ -86,9 +86,7 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, break; continue; } - if (walk->pud_entry) - err = walk->pud_entry(pud, addr, next, walk); - if (!err && (walk->pmd_entry || walk->pte_entry)) + if (walk->pmd_entry || walk->pte_entry) err = walk_pmd_range(pud, addr, next, walk); if (err) break; @@ -97,6 +95,32 @@ static int walk_pud_range(pgd_t *pgd, unsigned long addr, unsigned long end, return err; } +static int walk_pgd_range(unsigned long addr, unsigned long end, + struct mm_walk *walk) +{ + pgd_t *pgd; + unsigned long next; + int err = 0; + + pgd = pgd_offset(walk->mm, addr); + do { + next = pgd_addr_end(addr, end); + if (pgd_none_or_clear_bad(pgd)) { + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; + continue; + } + if (walk->pmd_entry || walk->pte_entry) + err = walk_pud_range(pgd, addr, next, walk); + if (err) + break; + } while (pgd++, addr = next, addr != end); + + return err; +} + #ifdef CONFIG_HUGETLB_PAGE static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, unsigned long end) @@ -105,10 +129,10 @@ static unsigned long hugetlb_entry_end(struct hstate *h, unsigned long addr, return boundary < end ? boundary : end; } -static int walk_hugetlb_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, +static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { + struct vm_area_struct *vma = walk->vma; struct hstate *h = hstate_vma(vma); unsigned long next; unsigned long hmask = huge_page_mask(h); @@ -121,15 +145,14 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, if (pte && walk->hugetlb_entry) err = walk->hugetlb_entry(pte, hmask, addr, next, walk); if (err) - return err; + break; } while (addr = next, addr != end); - return 0; + return err; } #else /* CONFIG_HUGETLB_PAGE */ -static int walk_hugetlb_range(struct vm_area_struct *vma, - unsigned long addr, unsigned long end, +static int walk_hugetlb_range(unsigned long addr, unsigned long end, struct mm_walk *walk) { return 0; @@ -137,112 +160,138 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, #endif /* CONFIG_HUGETLB_PAGE */ +/* + * Decide whether we really walk over the current vma on [@start, @end) + * or skip it via the returned value. Return 0 if we do walk over the + * current vma, and return 1 if we skip the vma. Negative values means + * error, where we abort the current walk. + */ +static int walk_page_test(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + struct vm_area_struct *vma = walk->vma; + + if (walk->test_walk) + return walk->test_walk(start, end, walk); + + /* + * vma(VM_PFNMAP) doesn't have any valid struct pages behind VM_PFNMAP + * range, so we don't walk over it as we do for normal vmas. However, + * Some callers are interested in handling hole range and they don't + * want to just ignore any single address range. Such users certainly + * define their ->pte_hole() callbacks, so let's delegate them to handle + * vma(VM_PFNMAP). + */ + if (vma->vm_flags & VM_PFNMAP) { + int err = 1; + if (walk->pte_hole) + err = walk->pte_hole(start, end, walk); + return err ? err : 1; + } + return 0; +} + +static int __walk_page_range(unsigned long start, unsigned long end, + struct mm_walk *walk) +{ + int err = 0; + struct vm_area_struct *vma = walk->vma; + + if (vma && is_vm_hugetlb_page(vma)) { + if (walk->hugetlb_entry) + err = walk_hugetlb_range(start, end, walk); + } else + err = walk_pgd_range(start, end, walk); + return err; +} /** - * walk_page_range - walk a memory map's page tables with a callback - * @addr: starting address - * @end: ending address - * @walk: set of callbacks to invoke for each level of the tree + * walk_page_range - walk page table with caller specific callbacks * - * Recursively walk the page table for the memory area in a VMA, - * calling supplied callbacks. Callbacks are called in-order (first - * PGD, first PUD, first PMD, first PTE, second PTE... second PMD, - * etc.). If lower-level callbacks are omitted, walking depth is reduced. + * Recursively walk the page table tree of the process represented by @walk->mm + * within the virtual address range [@start, @end). During walking, we can do + * some caller-specific works for each entry, by setting up pmd_entry(), + * pte_entry(), and/or hugetlb_entry(). If you don't set up for some of these + * callbacks, the associated entries/pages are just ignored. + * The return values of these callbacks are commonly defined like below: + * - 0 : succeeded to handle the current entry, and if you don't reach the + * end address yet, continue to walk. + * - >0 : succeeded to handle the current entry, and return to the caller + * with caller specific value. + * - <0 : failed to handle the current entry, and return to the caller + * with error code. * - * Each callback receives an entry pointer and the start and end of the - * associated range, and a copy of the original mm_walk for access to - * the ->private or ->mm fields. + * Before starting to walk page table, some callers want to check whether + * they really want to walk over the current vma, typically by checking + * its vm_flags. walk_page_test() and @walk->test_walk() are used for this + * purpose. * - * Usually no locks are taken, but splitting transparent huge page may - * take page table lock. And the bottom level iterator will map PTE - * directories from highmem if necessary. + * struct mm_walk keeps current values of some common data like vma and pmd, + * which are useful for the access from callbacks. If you want to pass some + * caller-specific data to callbacks, @walk->private should be helpful. * - * If any callback returns a non-zero value, the walk is aborted and - * the return value is propagated back to the caller. Otherwise 0 is returned. - * - * walk->mm->mmap_sem must be held for at least read if walk->hugetlb_entry - * is !NULL. + * Locking: + * Callers of walk_page_range() and walk_page_vma() should hold + * @walk->mm->mmap_sem, because these function traverse vma list and/or + * access to vma's data. */ -int walk_page_range(unsigned long addr, unsigned long end, +int walk_page_range(unsigned long start, unsigned long end, struct mm_walk *walk) { - pgd_t *pgd; - unsigned long next; int err = 0; + unsigned long next; + struct vm_area_struct *vma; - if (addr >= end) - return err; + if (start >= end) + return -EINVAL; if (!walk->mm) return -EINVAL; VM_BUG_ON_MM(!rwsem_is_locked(&walk->mm->mmap_sem), walk->mm); - pgd = pgd_offset(walk->mm, addr); + vma = find_vma(walk->mm, start); do { - struct vm_area_struct *vma = NULL; - - next = pgd_addr_end(addr, end); + if (!vma) { /* after the last vma */ + walk->vma = NULL; + next = end; + } else if (start < vma->vm_start) { /* outside vma */ + walk->vma = NULL; + next = min(end, vma->vm_start); + } else { /* inside vma */ + walk->vma = vma; + next = min(end, vma->vm_end); + vma = vma->vm_next; - /* - * This function was not intended to be vma based. - * But there are vma special cases to be handled: - * - hugetlb vma's - * - VM_PFNMAP vma's - */ - vma = find_vma(walk->mm, addr); - if (vma) { - /* - * There are no page structures backing a VM_PFNMAP - * range, so do not allow split_huge_page_pmd(). - */ - if ((vma->vm_start <= addr) && - (vma->vm_flags & VM_PFNMAP)) { - next = vma->vm_end; - pgd = pgd_offset(walk->mm, next); - continue; - } - /* - * Handle hugetlb vma individually because pagetable - * walk for the hugetlb page is dependent on the - * architecture and we can't handled it in the same - * manner as non-huge pages. - */ - if (walk->hugetlb_entry && (vma->vm_start <= addr) && - is_vm_hugetlb_page(vma)) { - if (vma->vm_end < next) - next = vma->vm_end; - /* - * Hugepage is very tightly coupled with vma, - * so walk through hugetlb entries within a - * given vma. - */ - err = walk_hugetlb_range(vma, addr, next, walk); - if (err) - break; - pgd = pgd_offset(walk->mm, next); + err = walk_page_test(start, next, walk); + if (err > 0) continue; - } - } - - if (pgd_none_or_clear_bad(pgd)) { - if (walk->pte_hole) - err = walk->pte_hole(addr, next, walk); - if (err) + if (err < 0) break; - pgd++; - continue; } - if (walk->pgd_entry) - err = walk->pgd_entry(pgd, addr, next, walk); - if (!err && - (walk->pud_entry || walk->pmd_entry || walk->pte_entry)) - err = walk_pud_range(pgd, addr, next, walk); + if (walk->vma || walk->pte_hole) + err = __walk_page_range(start, next, walk); if (err) break; - pgd++; - } while (addr = next, addr < end); - + } while (start = next, start < end); return err; } + +int walk_page_vma(struct vm_area_struct *vma, struct mm_walk *walk) +{ + int err; + + if (!walk->mm) + return -EINVAL; + + VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); + VM_BUG_ON(!vma); + walk->vma = vma; + err = walk_page_test(vma->vm_start, vma->vm_end, walk); + if (err > 0) + return 0; + if (err < 0) + return err; + return __walk_page_range(vma->vm_start, vma->vm_end, walk); +} diff --git a/mm/percpu.c b/mm/percpu.c index d39e2f4e335c..73c97a5f4495 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1528,7 +1528,6 @@ static void pcpu_dump_alloc_info(const char *lvl, int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, void *base_addr) { - static char cpus_buf[4096] __initdata; static int smap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata; static int dmap[PERCPU_DYNAMIC_EARLY_SLOTS] __initdata; size_t dyn_size = ai->dyn_size; @@ -1541,12 +1540,11 @@ int __init pcpu_setup_first_chunk(const struct pcpu_alloc_info *ai, int *unit_map; int group, unit, i; - cpumask_scnprintf(cpus_buf, sizeof(cpus_buf), cpu_possible_mask); - #define PCPU_SETUP_BUG_ON(cond) do { \ if (unlikely(cond)) { \ pr_emerg("PERCPU: failed to initialize, %s", #cond); \ - pr_emerg("PERCPU: cpu_possible_mask=%s\n", cpus_buf); \ + pr_emerg("PERCPU: cpu_possible_mask=%*pb\n", \ + cpumask_pr_args(cpu_possible_mask)); \ pcpu_dump_alloc_info(KERN_EMERG, ai); \ BUG(); \ } \ diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index dfb79e028ecb..c25f94b33811 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -193,8 +193,6 @@ void pmdp_invalidate(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { pmd_t entry = *pmdp; - if (pmd_numa(entry)) - entry = pmd_mknonnuma(entry); set_pmd_at(vma->vm_mm, address, pmdp, pmd_mknotpresent(entry)); flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); } diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index 5077afcd9e11..b1597690530c 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -99,11 +99,8 @@ static int process_vm_rw_single_vec(unsigned long addr, size_t bytes; /* Get the pages we're interested in */ - down_read(&mm->mmap_sem); - pages = get_user_pages(task, mm, pa, pages, - vm_write, 0, process_pages, NULL); - up_read(&mm->mmap_sem); - + pages = get_user_pages_unlocked(task, mm, pa, pages, + vm_write, 0, process_pages); if (pages <= 0) return -EFAULT; diff --git a/mm/readahead.c b/mm/readahead.c index 17b9172ec37f..935675844b2e 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -27,7 +27,7 @@ void file_ra_state_init(struct file_ra_state *ra, struct address_space *mapping) { - ra->ra_pages = mapping->backing_dev_info->ra_pages; + ra->ra_pages = inode_to_bdi(mapping->host)->ra_pages; ra->prev_pos = -1; } EXPORT_SYMBOL_GPL(file_ra_state_init); @@ -541,7 +541,7 @@ page_cache_async_readahead(struct address_space *mapping, /* * Defer asynchronous read-ahead on IO congestion. */ - if (bdi_read_congested(mapping->backing_dev_info)) + if (bdi_read_congested(inode_to_bdi(mapping->host))) return; /* do read-ahead */ diff --git a/mm/rmap.c b/mm/rmap.c index 71cd5bd0c17d..5e3e09081164 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -590,9 +590,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { - if (!vma->vm_file || - vma->vm_file->f_mapping != page->mapping) + } else if (page->mapping) { + if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; @@ -1086,24 +1085,20 @@ void page_add_new_anon_rmap(struct page *page, void page_add_file_rmap(struct page *page) { struct mem_cgroup *memcg; - unsigned long flags; - bool locked; - memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + memcg = mem_cgroup_begin_page_stat(page); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); mem_cgroup_inc_page_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED); } - mem_cgroup_end_page_stat(memcg, &locked, &flags); + mem_cgroup_end_page_stat(memcg); } static void page_remove_file_rmap(struct page *page) { struct mem_cgroup *memcg; - unsigned long flags; - bool locked; - memcg = mem_cgroup_begin_page_stat(page, &locked, &flags); + memcg = mem_cgroup_begin_page_stat(page); /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) @@ -1124,7 +1119,7 @@ static void page_remove_file_rmap(struct page *page) if (unlikely(PageMlocked(page))) clear_page_mlock(page); out: - mem_cgroup_end_page_stat(memcg, &locked, &flags); + mem_cgroup_end_page_stat(memcg); } /** @@ -1274,7 +1269,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); - BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ @@ -1316,211 +1310,6 @@ out_mlock: return ret; } -/* - * objrmap doesn't work for nonlinear VMAs because the assumption that - * offset-into-file correlates with offset-into-virtual-addresses does not hold. - * Consequently, given a particular page and its ->index, we cannot locate the - * ptes which are mapping that page without an exhaustive linear search. - * - * So what this code does is a mini "virtual scan" of each nonlinear VMA which - * maps the file to which the target page belongs. The ->vm_private_data field - * holds the current cursor into that scan. Successive searches will circulate - * around the vma's virtual address space. - * - * So as more replacement pressure is applied to the pages in a nonlinear VMA, - * more scanning pressure is placed against them as well. Eventually pages - * will become fully unmapped and are eligible for eviction. - * - * For very sparsely populated VMAs this is a little inefficient - chances are - * there there won't be many ptes located within the scan cluster. In this case - * maybe we could scan further - to the end of the pte page, perhaps. - * - * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can - * acquire it without blocking. If vma locked, mlock the pages in the cluster, - * rather than unmapping them. If we encounter the "check_page" that vmscan is - * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN. - */ -#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE) -#define CLUSTER_MASK (~(CLUSTER_SIZE - 1)) - -static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, - struct vm_area_struct *vma, struct page *check_page) -{ - struct mm_struct *mm = vma->vm_mm; - pmd_t *pmd; - pte_t *pte; - pte_t pteval; - spinlock_t *ptl; - struct page *page; - unsigned long address; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - unsigned long end; - int ret = SWAP_AGAIN; - int locked_vma = 0; - - address = (vma->vm_start + cursor) & CLUSTER_MASK; - end = address + CLUSTER_SIZE; - if (address < vma->vm_start) - address = vma->vm_start; - if (end > vma->vm_end) - end = vma->vm_end; - - pmd = mm_find_pmd(mm, address); - if (!pmd) - return ret; - - mmun_start = address; - mmun_end = end; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - - /* - * If we can acquire the mmap_sem for read, and vma is VM_LOCKED, - * keep the sem while scanning the cluster for mlocking pages. - */ - if (down_read_trylock(&vma->vm_mm->mmap_sem)) { - locked_vma = (vma->vm_flags & VM_LOCKED); - if (!locked_vma) - up_read(&vma->vm_mm->mmap_sem); /* don't need it */ - } - - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - - for (; address < end; pte++, address += PAGE_SIZE) { - if (!pte_present(*pte)) - continue; - page = vm_normal_page(vma, address, *pte); - BUG_ON(!page || PageAnon(page)); - - if (locked_vma) { - if (page == check_page) { - /* we know we have check_page locked */ - mlock_vma_page(page); - ret = SWAP_MLOCK; - } else if (trylock_page(page)) { - /* - * If we can lock the page, perform mlock. - * Otherwise leave the page alone, it will be - * eventually encountered again later. - */ - mlock_vma_page(page); - unlock_page(page); - } - continue; /* don't unmap */ - } - - /* - * No need for _notify because we're within an - * mmu_notifier_invalidate_range_ {start|end} scope. - */ - if (ptep_clear_flush_young(vma, address, pte)) - continue; - - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush_notify(vma, address, pte); - - /* If nonlinear, store the file page offset in the pte. */ - if (page->index != linear_page_index(vma, address)) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(pteval)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, address, pte, ptfile); - } - - /* Move the dirty bit to the physical page now the pte is gone. */ - if (pte_dirty(pteval)) - set_page_dirty(page); - - page_remove_rmap(page); - page_cache_release(page); - dec_mm_counter(mm, MM_FILEPAGES); - (*mapcount)--; - } - pte_unmap_unlock(pte - 1, ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - if (locked_vma) - up_read(&vma->vm_mm->mmap_sem); - return ret; -} - -static int try_to_unmap_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - int ret = SWAP_AGAIN; - unsigned long cursor; - unsigned long max_nl_cursor = 0; - unsigned long max_nl_size = 0; - unsigned int mapcount; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - if (cursor > max_nl_cursor) - max_nl_cursor = cursor; - cursor = vma->vm_end - vma->vm_start; - if (cursor > max_nl_size) - max_nl_size = cursor; - } - - if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - return SWAP_FAIL; - } - - /* - * We don't try to search for this page in the nonlinear vmas, - * and page_referenced wouldn't have found it anyway. Instead - * just walk the nonlinear vmas trying to age and unmap some. - * The mapcount of the page we came in with is irrelevant, - * but even so use it as a guide to how hard we should try? - */ - mapcount = page_mapcount(page); - if (!mapcount) - return ret; - - cond_resched(); - - max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; - if (max_nl_cursor == 0) - max_nl_cursor = CLUSTER_SIZE; - - do { - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - while (cursor < max_nl_cursor && - cursor < vma->vm_end - vma->vm_start) { - if (try_to_unmap_cluster(cursor, &mapcount, - vma, page) == SWAP_MLOCK) - ret = SWAP_MLOCK; - cursor += CLUSTER_SIZE; - vma->vm_private_data = (void *) cursor; - if ((int)mapcount <= 0) - return ret; - } - vma->vm_private_data = (void *) max_nl_cursor; - } - cond_resched(); - max_nl_cursor += CLUSTER_SIZE; - } while (max_nl_cursor <= max_nl_size); - - /* - * Don't loop forever (perhaps all the remaining pages are - * in locked vmas). Reset cursor on all unreserved nonlinear - * vmas, now forgetting on which ones it had fallen behind. - */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) - vma->vm_private_data = NULL; - - return ret; -} - bool is_vma_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -1566,7 +1355,6 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, - .file_nonlinear = try_to_unmap_nonlinear, .anon_lock = page_lock_anon_vma_read, }; @@ -1612,12 +1400,6 @@ int try_to_munlock(struct page *page) .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, - /* - * We don't bother to try to find the munlocked page in - * nonlinears. It's costly. Instead, later, page reclaim logic - * may call try_to_unmap() and recover PG_mlocked lazily. - */ - .file_nonlinear = NULL, .anon_lock = page_lock_anon_vma_read, }; @@ -1748,13 +1530,6 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) goto done; } - if (!rwc->file_nonlinear) - goto done; - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto done; - - ret = rwc->file_nonlinear(page, mapping, rwc->arg); done: i_mmap_unlock_read(mapping); return ret; diff --git a/mm/shmem.c b/mm/shmem.c index 73ba1df7c8ba..a63031fa3e0c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -191,11 +191,6 @@ static const struct inode_operations shmem_dir_inode_operations; static const struct inode_operations shmem_special_inode_operations; static const struct vm_operations_struct shmem_vm_ops; -static struct backing_dev_info shmem_backing_dev_info __read_mostly = { - .ra_pages = 0, /* No readahead */ - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, -}; - static LIST_HEAD(shmem_swaplist); static DEFINE_MUTEX(shmem_swaplist_mutex); @@ -765,11 +760,11 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) goto redirty; /* - * shmem_backing_dev_info's capabilities prevent regular writeback or - * sync from ever calling shmem_writepage; but a stacking filesystem - * might use ->writepage of its underlying filesystem, in which case - * tmpfs should write out to swap only in response to memory pressure, - * and not for the writeback threads or sync. + * Our capabilities prevent regular writeback or sync from ever calling + * shmem_writepage; but a stacking filesystem might use ->writepage of + * its underlying filesystem, in which case tmpfs should write out to + * swap only in response to memory pressure, and not for the writeback + * threads or sync. */ if (!wbc->for_reclaim) { WARN_ON_ONCE(1); /* Still happens? Tell us about it! */ @@ -1013,7 +1008,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - mem_cgroup_migrate(oldpage, newpage, false); + mem_cgroup_migrate(oldpage, newpage, true); lru_cache_add_anon(newpage); *pagep = newpage; } @@ -1131,7 +1126,7 @@ repeat: * truncated or holepunched since swap was confirmed. * shmem_undo_range() will have done some of the * unaccounting, now delete_from_swap_cache() will do - * the rest (including mem_cgroup_uncharge_swapcache). + * the rest. * Reset swap.val? No, leave it so "failed" goes back to * "repeat": reading a hole and writing should succeed. */ @@ -1415,7 +1410,6 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode inode->i_ino = get_next_ino(); inode_init_owner(inode, dir, mode); inode->i_blocks = 0; - inode->i_mapping->backing_dev_info = &shmem_backing_dev_info; inode->i_atime = inode->i_mtime = inode->i_ctime = CURRENT_TIME; inode->i_generation = get_seconds(); info = SHMEM_I(inode); @@ -1461,7 +1455,7 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode bool shmem_mapping(struct address_space *mapping) { - return mapping->backing_dev_info == &shmem_backing_dev_info; + return mapping->host->i_sb->s_op == &shmem_ops; } #ifdef CONFIG_TMPFS @@ -3201,7 +3195,6 @@ static const struct vm_operations_struct shmem_vm_ops = { .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif - .remap_pages = generic_file_remap_pages, }; static struct dentry *shmem_mount(struct file_system_type *fs_type, @@ -3226,10 +3219,6 @@ int __init shmem_init(void) if (shmem_inode_cachep) return 0; - error = bdi_init(&shmem_backing_dev_info); - if (error) - goto out4; - error = shmem_init_inodecache(); if (error) goto out3; @@ -3253,8 +3242,6 @@ out1: out2: shmem_destroy_inodecache(); out3: - bdi_destroy(&shmem_backing_dev_info); -out4: shm_mnt = ERR_PTR(error); return error; } diff --git a/mm/slab.c b/mm/slab.c index 65b5dcb6f671..c4b89eaf4c96 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2382,7 +2382,7 @@ out: return nr_freed; } -int __kmem_cache_shrink(struct kmem_cache *cachep) +int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate) { int ret = 0; int node; @@ -2404,7 +2404,7 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep) { int i; struct kmem_cache_node *n; - int rc = __kmem_cache_shrink(cachep); + int rc = __kmem_cache_shrink(cachep, false); if (rc) return rc; @@ -3708,8 +3708,7 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, int batchcount, int shared, gfp_t gfp) { int ret; - struct kmem_cache *c = NULL; - int i = 0; + struct kmem_cache *c; ret = __do_tune_cpucache(cachep, limit, batchcount, shared, gfp); @@ -3719,12 +3718,10 @@ static int do_tune_cpucache(struct kmem_cache *cachep, int limit, if ((ret < 0) || !is_root_cache(cachep)) return ret; - VM_BUG_ON(!mutex_is_locked(&slab_mutex)); - for_each_memcg_cache_index(i) { - c = cache_from_memcg_idx(cachep, i); - if (c) - /* return value determined by the parent cache only */ - __do_tune_cpucache(c, limit, batchcount, shared, gfp); + lockdep_assert_held(&slab_mutex); + for_each_memcg_cache(c, cachep) { + /* return value determined by the root cache only */ + __do_tune_cpucache(c, limit, batchcount, shared, gfp); } return ret; diff --git a/mm/slab.h b/mm/slab.h index 1cf4005482dd..4c3ac12dd644 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -86,8 +86,6 @@ extern struct kmem_cache *create_kmalloc_cache(const char *name, size_t size, extern void create_boot_cache(struct kmem_cache *, const char *name, size_t size, unsigned long flags); -struct mem_cgroup; - int slab_unmergeable(struct kmem_cache *s); struct kmem_cache *find_mergeable(size_t size, size_t align, unsigned long flags, const char *name, void (*ctor)(void *)); @@ -140,7 +138,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size, #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS) int __kmem_cache_shutdown(struct kmem_cache *); -int __kmem_cache_shrink(struct kmem_cache *); +int __kmem_cache_shrink(struct kmem_cache *, bool); void slab_kmem_cache_release(struct kmem_cache *); struct seq_file; @@ -165,16 +163,27 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer, size_t count, loff_t *ppos); #ifdef CONFIG_MEMCG_KMEM +/* + * Iterate over all memcg caches of the given root cache. The caller must hold + * slab_mutex. + */ +#define for_each_memcg_cache(iter, root) \ + list_for_each_entry(iter, &(root)->memcg_params.list, \ + memcg_params.list) + +#define for_each_memcg_cache_safe(iter, tmp, root) \ + list_for_each_entry_safe(iter, tmp, &(root)->memcg_params.list, \ + memcg_params.list) + static inline bool is_root_cache(struct kmem_cache *s) { - return !s->memcg_params || s->memcg_params->is_root_cache; + return s->memcg_params.is_root_cache; } static inline bool slab_equal_or_root(struct kmem_cache *s, - struct kmem_cache *p) + struct kmem_cache *p) { - return (p == s) || - (s->memcg_params && (p == s->memcg_params->root_cache)); + return p == s || p == s->memcg_params.root_cache; } /* @@ -185,37 +194,30 @@ static inline bool slab_equal_or_root(struct kmem_cache *s, static inline const char *cache_name(struct kmem_cache *s) { if (!is_root_cache(s)) - return s->memcg_params->root_cache->name; + s = s->memcg_params.root_cache; return s->name; } /* * Note, we protect with RCU only the memcg_caches array, not per-memcg caches. - * That said the caller must assure the memcg's cache won't go away. Since once - * created a memcg's cache is destroyed only along with the root cache, it is - * true if we are going to allocate from the cache or hold a reference to the - * root cache by other means. Otherwise, we should hold either the slab_mutex - * or the memcg's slab_caches_mutex while calling this function and accessing - * the returned value. + * That said the caller must assure the memcg's cache won't go away by either + * taking a css reference to the owner cgroup, or holding the slab_mutex. */ static inline struct kmem_cache * cache_from_memcg_idx(struct kmem_cache *s, int idx) { struct kmem_cache *cachep; - struct memcg_cache_params *params; - - if (!s->memcg_params) - return NULL; + struct memcg_cache_array *arr; rcu_read_lock(); - params = rcu_dereference(s->memcg_params); + arr = rcu_dereference(s->memcg_params.memcg_caches); /* * Make sure we will access the up-to-date value. The code updating * memcg_caches issues a write barrier to match this (see - * memcg_register_cache()). + * memcg_create_kmem_cache()). */ - cachep = lockless_dereference(params->memcg_caches[idx]); + cachep = lockless_dereference(arr->entries[idx]); rcu_read_unlock(); return cachep; @@ -225,7 +227,7 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) { if (is_root_cache(s)) return s; - return s->memcg_params->root_cache; + return s->memcg_params.root_cache; } static __always_inline int memcg_charge_slab(struct kmem_cache *s, @@ -235,7 +237,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s, return 0; if (is_root_cache(s)) return 0; - return __memcg_charge_slab(s, gfp, order); + return memcg_charge_kmem(s->memcg_params.memcg, gfp, 1 << order); } static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) @@ -244,9 +246,18 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) return; if (is_root_cache(s)) return; - __memcg_uncharge_slab(s, order); + memcg_uncharge_kmem(s->memcg_params.memcg, 1 << order); } -#else + +extern void slab_init_memcg_params(struct kmem_cache *); + +#else /* !CONFIG_MEMCG_KMEM */ + +#define for_each_memcg_cache(iter, root) \ + for ((void)(iter), (void)(root); 0; ) +#define for_each_memcg_cache_safe(iter, tmp, root) \ + for ((void)(iter), (void)(tmp), (void)(root); 0; ) + static inline bool is_root_cache(struct kmem_cache *s) { return true; @@ -282,7 +293,11 @@ static inline int memcg_charge_slab(struct kmem_cache *s, gfp_t gfp, int order) static inline void memcg_uncharge_slab(struct kmem_cache *s, int order) { } -#endif + +static inline void slab_init_memcg_params(struct kmem_cache *s) +{ +} +#endif /* CONFIG_MEMCG_KMEM */ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) { diff --git a/mm/slab_common.c b/mm/slab_common.c index e03dd6f2a272..999bb3424d44 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -106,62 +106,67 @@ static inline int kmem_cache_sanity_check(const char *name, size_t size) #endif #ifdef CONFIG_MEMCG_KMEM -static int memcg_alloc_cache_params(struct mem_cgroup *memcg, - struct kmem_cache *s, struct kmem_cache *root_cache) +void slab_init_memcg_params(struct kmem_cache *s) { - size_t size; + s->memcg_params.is_root_cache = true; + INIT_LIST_HEAD(&s->memcg_params.list); + RCU_INIT_POINTER(s->memcg_params.memcg_caches, NULL); +} + +static int init_memcg_params(struct kmem_cache *s, + struct mem_cgroup *memcg, struct kmem_cache *root_cache) +{ + struct memcg_cache_array *arr; - if (!memcg_kmem_enabled()) + if (memcg) { + s->memcg_params.is_root_cache = false; + s->memcg_params.memcg = memcg; + s->memcg_params.root_cache = root_cache; return 0; + } - if (!memcg) { - size = offsetof(struct memcg_cache_params, memcg_caches); - size += memcg_limited_groups_array_size * sizeof(void *); - } else - size = sizeof(struct memcg_cache_params); + slab_init_memcg_params(s); - s->memcg_params = kzalloc(size, GFP_KERNEL); - if (!s->memcg_params) - return -ENOMEM; + if (!memcg_nr_cache_ids) + return 0; - if (memcg) { - s->memcg_params->memcg = memcg; - s->memcg_params->root_cache = root_cache; - } else - s->memcg_params->is_root_cache = true; + arr = kzalloc(sizeof(struct memcg_cache_array) + + memcg_nr_cache_ids * sizeof(void *), + GFP_KERNEL); + if (!arr) + return -ENOMEM; + RCU_INIT_POINTER(s->memcg_params.memcg_caches, arr); return 0; } -static void memcg_free_cache_params(struct kmem_cache *s) +static void destroy_memcg_params(struct kmem_cache *s) { - kfree(s->memcg_params); + if (is_root_cache(s)) + kfree(rcu_access_pointer(s->memcg_params.memcg_caches)); } -static int memcg_update_cache_params(struct kmem_cache *s, int num_memcgs) +static int update_memcg_params(struct kmem_cache *s, int new_array_size) { - int size; - struct memcg_cache_params *new_params, *cur_params; - - BUG_ON(!is_root_cache(s)); + struct memcg_cache_array *old, *new; - size = offsetof(struct memcg_cache_params, memcg_caches); - size += num_memcgs * sizeof(void *); + if (!is_root_cache(s)) + return 0; - new_params = kzalloc(size, GFP_KERNEL); - if (!new_params) + new = kzalloc(sizeof(struct memcg_cache_array) + + new_array_size * sizeof(void *), GFP_KERNEL); + if (!new) return -ENOMEM; - cur_params = s->memcg_params; - memcpy(new_params->memcg_caches, cur_params->memcg_caches, - memcg_limited_groups_array_size * sizeof(void *)); - - new_params->is_root_cache = true; - - rcu_assign_pointer(s->memcg_params, new_params); - if (cur_params) - kfree_rcu(cur_params, rcu_head); + old = rcu_dereference_protected(s->memcg_params.memcg_caches, + lockdep_is_held(&slab_mutex)); + if (old) + memcpy(new->entries, old->entries, + memcg_nr_cache_ids * sizeof(void *)); + rcu_assign_pointer(s->memcg_params.memcg_caches, new); + if (old) + kfree_rcu(old, rcu); return 0; } @@ -169,34 +174,28 @@ int memcg_update_all_caches(int num_memcgs) { struct kmem_cache *s; int ret = 0; - mutex_lock(&slab_mutex); + mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) { - if (!is_root_cache(s)) - continue; - - ret = memcg_update_cache_params(s, num_memcgs); + ret = update_memcg_params(s, num_memcgs); /* * Instead of freeing the memory, we'll just leave the caches * up to this point in an updated state. */ if (ret) - goto out; + break; } - - memcg_update_array_size(num_memcgs); -out: mutex_unlock(&slab_mutex); return ret; } #else -static inline int memcg_alloc_cache_params(struct mem_cgroup *memcg, - struct kmem_cache *s, struct kmem_cache *root_cache) +static inline int init_memcg_params(struct kmem_cache *s, + struct mem_cgroup *memcg, struct kmem_cache *root_cache) { return 0; } -static inline void memcg_free_cache_params(struct kmem_cache *s) +static inline void destroy_memcg_params(struct kmem_cache *s) { } #endif /* CONFIG_MEMCG_KMEM */ @@ -296,8 +295,8 @@ unsigned long calculate_alignment(unsigned long flags, } static struct kmem_cache * -do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align, - unsigned long flags, void (*ctor)(void *), +do_kmem_cache_create(const char *name, size_t object_size, size_t size, + size_t align, unsigned long flags, void (*ctor)(void *), struct mem_cgroup *memcg, struct kmem_cache *root_cache) { struct kmem_cache *s; @@ -314,7 +313,7 @@ do_kmem_cache_create(char *name, size_t object_size, size_t size, size_t align, s->align = align; s->ctor = ctor; - err = memcg_alloc_cache_params(memcg, s, root_cache); + err = init_memcg_params(s, memcg, root_cache); if (err) goto out_free_cache; @@ -330,8 +329,8 @@ out: return s; out_free_cache: - memcg_free_cache_params(s); - kfree(s); + destroy_memcg_params(s); + kmem_cache_free(kmem_cache, s); goto out; } @@ -364,11 +363,12 @@ kmem_cache_create(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { struct kmem_cache *s; - char *cache_name; + const char *cache_name; int err; get_online_cpus(); get_online_mems(); + memcg_get_cache_ids(); mutex_lock(&slab_mutex); @@ -390,7 +390,7 @@ kmem_cache_create(const char *name, size_t size, size_t align, if (s) goto out_unlock; - cache_name = kstrdup(name, GFP_KERNEL); + cache_name = kstrdup_const(name, GFP_KERNEL); if (!cache_name) { err = -ENOMEM; goto out_unlock; @@ -401,12 +401,13 @@ kmem_cache_create(const char *name, size_t size, size_t align, flags, ctor, NULL, NULL); if (IS_ERR(s)) { err = PTR_ERR(s); - kfree(cache_name); + kfree_const(cache_name); } out_unlock: mutex_unlock(&slab_mutex); + memcg_put_cache_ids(); put_online_mems(); put_online_cpus(); @@ -425,31 +426,91 @@ out_unlock: } EXPORT_SYMBOL(kmem_cache_create); +static int do_kmem_cache_shutdown(struct kmem_cache *s, + struct list_head *release, bool *need_rcu_barrier) +{ + if (__kmem_cache_shutdown(s) != 0) { + printk(KERN_ERR "kmem_cache_destroy %s: " + "Slab cache still has objects\n", s->name); + dump_stack(); + return -EBUSY; + } + + if (s->flags & SLAB_DESTROY_BY_RCU) + *need_rcu_barrier = true; + +#ifdef CONFIG_MEMCG_KMEM + if (!is_root_cache(s)) + list_del(&s->memcg_params.list); +#endif + list_move(&s->list, release); + return 0; +} + +static void do_kmem_cache_release(struct list_head *release, + bool need_rcu_barrier) +{ + struct kmem_cache *s, *s2; + + if (need_rcu_barrier) + rcu_barrier(); + + list_for_each_entry_safe(s, s2, release, list) { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_remove(s); +#else + slab_kmem_cache_release(s); +#endif + } +} + #ifdef CONFIG_MEMCG_KMEM /* * memcg_create_kmem_cache - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. - * @memcg_name: The name of the memory cgroup (used for naming the new cache). * * This function attempts to create a kmem cache that will serve allocation * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ -struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache, - const char *memcg_name) +void memcg_create_kmem_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { + static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */ + struct cgroup_subsys_state *css = mem_cgroup_css(memcg); + struct memcg_cache_array *arr; struct kmem_cache *s = NULL; char *cache_name; + int idx; get_online_cpus(); get_online_mems(); mutex_lock(&slab_mutex); + /* + * The memory cgroup could have been deactivated while the cache + * creation work was pending. + */ + if (!memcg_kmem_is_active(memcg)) + goto out_unlock; + + idx = memcg_cache_id(memcg); + arr = rcu_dereference_protected(root_cache->memcg_params.memcg_caches, + lockdep_is_held(&slab_mutex)); + + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (arr->entries[idx]) + goto out_unlock; + + cgroup_name(css->cgroup, memcg_name_buf, sizeof(memcg_name_buf)); cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - memcg_cache_id(memcg), memcg_name); + css->id, memcg_name_buf); if (!cache_name) goto out_unlock; @@ -457,49 +518,108 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, root_cache->size, root_cache->align, root_cache->flags, root_cache->ctor, memcg, root_cache); + /* + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. + */ if (IS_ERR(s)) { kfree(cache_name); - s = NULL; + goto out_unlock; } + list_add(&s->memcg_params.list, &root_cache->memcg_params.list); + + /* + * Since readers won't lock (see cache_from_memcg_idx()), we need a + * barrier here to ensure nobody will see the kmem_cache partially + * initialized. + */ + smp_wmb(); + arr->entries[idx] = s; + out_unlock: mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); - - return s; } -static int memcg_cleanup_cache_params(struct kmem_cache *s) +void memcg_deactivate_kmem_caches(struct mem_cgroup *memcg) { - int rc; + int idx; + struct memcg_cache_array *arr; + struct kmem_cache *s, *c; - if (!s->memcg_params || - !s->memcg_params->is_root_cache) - return 0; + idx = memcg_cache_id(memcg); + + get_online_cpus(); + get_online_mems(); - mutex_unlock(&slab_mutex); - rc = __memcg_cleanup_cache_params(s); mutex_lock(&slab_mutex); + list_for_each_entry(s, &slab_caches, list) { + if (!is_root_cache(s)) + continue; + + arr = rcu_dereference_protected(s->memcg_params.memcg_caches, + lockdep_is_held(&slab_mutex)); + c = arr->entries[idx]; + if (!c) + continue; + + __kmem_cache_shrink(c, true); + arr->entries[idx] = NULL; + } + mutex_unlock(&slab_mutex); - return rc; + put_online_mems(); + put_online_cpus(); } -#else -static int memcg_cleanup_cache_params(struct kmem_cache *s) + +void memcg_destroy_kmem_caches(struct mem_cgroup *memcg) { - return 0; + LIST_HEAD(release); + bool need_rcu_barrier = false; + struct kmem_cache *s, *s2; + + get_online_cpus(); + get_online_mems(); + + mutex_lock(&slab_mutex); + list_for_each_entry_safe(s, s2, &slab_caches, list) { + if (is_root_cache(s) || s->memcg_params.memcg != memcg) + continue; + /* + * The cgroup is about to be freed and therefore has no charges + * left. Hence, all its caches must be empty by now. + */ + BUG_ON(do_kmem_cache_shutdown(s, &release, &need_rcu_barrier)); + } + mutex_unlock(&slab_mutex); + + put_online_mems(); + put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } #endif /* CONFIG_MEMCG_KMEM */ void slab_kmem_cache_release(struct kmem_cache *s) { - kfree(s->name); + destroy_memcg_params(s); + kfree_const(s->name); kmem_cache_free(kmem_cache, s); } void kmem_cache_destroy(struct kmem_cache *s) { + struct kmem_cache *c, *c2; + LIST_HEAD(release); + bool need_rcu_barrier = false; + bool busy = false; + + BUG_ON(!is_root_cache(s)); + get_online_cpus(); get_online_mems(); @@ -509,35 +629,21 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->refcount) goto out_unlock; - if (memcg_cleanup_cache_params(s) != 0) - goto out_unlock; - - if (__kmem_cache_shutdown(s) != 0) { - printk(KERN_ERR "kmem_cache_destroy %s: " - "Slab cache still has objects\n", s->name); - dump_stack(); - goto out_unlock; + for_each_memcg_cache_safe(c, c2, s) { + if (do_kmem_cache_shutdown(c, &release, &need_rcu_barrier)) + busy = true; } - list_del(&s->list); - - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_free_cache_params(s); -#ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_remove(s); -#else - slab_kmem_cache_release(s); -#endif - goto out; + if (!busy) + do_kmem_cache_shutdown(s, &release, &need_rcu_barrier); out_unlock: mutex_unlock(&slab_mutex); -out: + put_online_mems(); put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -554,7 +660,7 @@ int kmem_cache_shrink(struct kmem_cache *cachep) get_online_cpus(); get_online_mems(); - ret = __kmem_cache_shrink(cachep); + ret = __kmem_cache_shrink(cachep, false); put_online_mems(); put_online_cpus(); return ret; @@ -576,6 +682,9 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, size_t siz s->name = name; s->size = s->object_size = size; s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size); + + slab_init_memcg_params(s); + err = __kmem_cache_create(s, flags); if (err) @@ -789,6 +898,7 @@ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) page = alloc_kmem_pages(flags, order); ret = page ? page_address(page) : NULL; kmemleak_alloc(ret, size, 1, flags); + kasan_kmalloc_large(ret, size); return ret; } EXPORT_SYMBOL(kmalloc_order); @@ -855,16 +965,11 @@ memcg_accumulate_slabinfo(struct kmem_cache *s, struct slabinfo *info) { struct kmem_cache *c; struct slabinfo sinfo; - int i; if (!is_root_cache(s)) return; - for_each_memcg_cache_index(i) { - c = cache_from_memcg_idx(s, i); - if (!c) - continue; - + for_each_memcg_cache(c, s) { memset(&sinfo, 0, sizeof(sinfo)); get_slabinfo(c, &sinfo); @@ -916,7 +1021,7 @@ int memcg_slab_show(struct seq_file *m, void *p) if (p == slab_caches.next) print_slabinfo_header(m); - if (!is_root_cache(s) && s->memcg_params->memcg == memcg) + if (!is_root_cache(s) && s->memcg_params.memcg == memcg) cache_show(s, m); return 0; } @@ -973,8 +1078,10 @@ static __always_inline void *__do_krealloc(const void *p, size_t new_size, if (p) ks = ksize(p); - if (ks >= new_size) + if (ks >= new_size) { + kasan_krealloc((void *)p, new_size); return (void *)p; + } ret = kmalloc_track_caller(new_size, flags); if (ret && p) diff --git a/mm/slob.c b/mm/slob.c index 96a86206a26b..94a7fede6d48 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -618,7 +618,7 @@ int __kmem_cache_shutdown(struct kmem_cache *c) return 0; } -int __kmem_cache_shrink(struct kmem_cache *d) +int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate) { return 0; } diff --git a/mm/slub.c b/mm/slub.c index fe376fe1f4fe..6832c4eab104 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -20,6 +20,7 @@ #include <linux/proc_fs.h> #include <linux/notifier.h> #include <linux/seq_file.h> +#include <linux/kasan.h> #include <linux/kmemcheck.h> #include <linux/cpu.h> #include <linux/cpuset.h> @@ -468,12 +469,30 @@ static char *slub_debug_slabs; static int disable_higher_order_debug; /* + * slub is about to manipulate internal object metadata. This memory lies + * outside the range of the allocated object, so accessing it would normally + * be reported by kasan as a bounds error. metadata_access_enable() is used + * to tell kasan that these accesses are OK. + */ +static inline void metadata_access_enable(void) +{ + kasan_disable_current(); +} + +static inline void metadata_access_disable(void) +{ + kasan_enable_current(); +} + +/* * Object debugging */ static void print_section(char *text, u8 *addr, unsigned int length) { + metadata_access_enable(); print_hex_dump(KERN_ERR, text, DUMP_PREFIX_ADDRESS, 16, 1, addr, length, 1); + metadata_access_disable(); } static struct track *get_track(struct kmem_cache *s, void *object, @@ -503,7 +522,9 @@ static void set_track(struct kmem_cache *s, void *object, trace.max_entries = TRACK_ADDRS_COUNT; trace.entries = p->addrs; trace.skip = 3; + metadata_access_enable(); save_stack_trace(&trace); + metadata_access_disable(); /* See rant in lockdep.c */ if (trace.nr_entries != 0 && @@ -629,7 +650,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) dump_stack(); } -static void object_err(struct kmem_cache *s, struct page *page, +void object_err(struct kmem_cache *s, struct page *page, u8 *object, char *reason) { slab_bug(s, "%s", reason); @@ -677,7 +698,9 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, u8 *fault; u8 *end; + metadata_access_enable(); fault = memchr_inv(start, value, bytes); + metadata_access_disable(); if (!fault) return 1; @@ -770,7 +793,9 @@ static int slab_pad_check(struct kmem_cache *s, struct page *page) if (!remainder) return 1; + metadata_access_enable(); fault = memchr_inv(end - remainder, POISON_INUSE, remainder); + metadata_access_disable(); if (!fault) return 1; while (end > fault && end[-1] == POISON_INUSE) @@ -1226,11 +1251,13 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, static inline void kmalloc_large_node_hook(void *ptr, size_t size, gfp_t flags) { kmemleak_alloc(ptr, size, 1, flags); + kasan_kmalloc_large(ptr, size); } static inline void kfree_hook(const void *x) { kmemleak_free(x); + kasan_kfree_large(x); } static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, @@ -1253,6 +1280,7 @@ static inline void slab_post_alloc_hook(struct kmem_cache *s, kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags); memcg_kmem_put_cache(s); + kasan_slab_alloc(s, object); } static inline void slab_free_hook(struct kmem_cache *s, void *x) @@ -1276,6 +1304,8 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) #endif if (!(s->flags & SLAB_DEBUG_OBJECTS)) debug_check_no_obj_freed(x, s->object_size); + + kasan_slab_free(s, x); } /* @@ -1370,8 +1400,11 @@ static void setup_object(struct kmem_cache *s, struct page *page, void *object) { setup_object_debug(s, page, object); - if (unlikely(s->ctor)) + if (unlikely(s->ctor)) { + kasan_unpoison_object_data(s, object); s->ctor(object); + kasan_poison_object_data(s, object); + } } static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) @@ -1404,6 +1437,8 @@ static struct page *new_slab(struct kmem_cache *s, gfp_t flags, int node) if (unlikely(s->flags & SLAB_POISON)) memset(start, POISON_INUSE, PAGE_SIZE << order); + kasan_poison_slab(page); + for_each_object_idx(p, idx, s, start, page->objects) { setup_object(s, page, p); if (likely(idx < page->objects)) @@ -2007,6 +2042,7 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) int pages; int pobjects; + preempt_disable(); do { pages = 0; pobjects = 0; @@ -2040,6 +2076,14 @@ static void put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage); + if (unlikely(!s->cpu_partial)) { + unsigned long flags; + + local_irq_save(flags); + unfreeze_partials(s, this_cpu_ptr(s->cpu_slab)); + local_irq_restore(flags); + } + preempt_enable(); #endif } @@ -2398,13 +2442,24 @@ redo: * reading from one cpu area. That does not matter as long * as we end up on the original cpu again when doing the cmpxchg. * - * Preemption is disabled for the retrieval of the tid because that - * must occur from the current processor. We cannot allow rescheduling - * on a different processor between the determination of the pointer - * and the retrieval of the tid. + * We should guarantee that tid and kmem_cache are retrieved on + * the same cpu. It could be different if CONFIG_PREEMPT so we need + * to check if it is matched or not. */ - preempt_disable(); - c = this_cpu_ptr(s->cpu_slab); + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + + /* + * Irqless object alloc/free algorithm used here depends on sequence + * of fetching cpu_slab's data. tid should be fetched before anything + * on c to guarantee that object and page associated with previous tid + * won't be used with current tid. If we fetch tid first, object and + * page could be one associated with next tid and our alloc/free + * request will be failed. In this case, we will retry. So, no problem. + */ + barrier(); /* * The transaction ids are globally unique per cpu and per operation on @@ -2412,8 +2467,6 @@ redo: * occurs on the right processor and that there was no operation on the * linked list in between. */ - tid = c->tid; - preempt_enable(); object = c->freelist; page = c->page; @@ -2479,6 +2532,7 @@ void *kmem_cache_alloc_trace(struct kmem_cache *s, gfp_t gfpflags, size_t size) { void *ret = slab_alloc(s, gfpflags, _RET_IP_); trace_kmalloc(_RET_IP_, ret, size, s->size, gfpflags); + kasan_kmalloc(s, ret, size); return ret; } EXPORT_SYMBOL(kmem_cache_alloc_trace); @@ -2505,6 +2559,8 @@ void *kmem_cache_alloc_node_trace(struct kmem_cache *s, trace_kmalloc_node(_RET_IP_, ret, size, s->size, gfpflags, node); + + kasan_kmalloc(s, ret, size); return ret; } EXPORT_SYMBOL(kmem_cache_alloc_node_trace); @@ -2512,7 +2568,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif /* - * Slow patch handling. This may still be called frequently since objects + * Slow path handling. This may still be called frequently since objects * have a longer lifetime than the cpu slabs in most processing loads. * * So we still attempt to reduce cache line usage. Just take the slab @@ -2659,11 +2715,13 @@ redo: * data is retrieved via this pointer. If we are on the same cpu * during the cmpxchg then the free will succedd. */ - preempt_disable(); - c = this_cpu_ptr(s->cpu_slab); + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); - tid = c->tid; - preempt_enable(); + /* Same with comment on barrier() in slab_alloc_node() */ + barrier(); if (likely(page == c->page)) { set_freepointer(s, object, c->freelist); @@ -2888,6 +2946,7 @@ static void early_kmem_cache_node_alloc(int node) init_object(kmem_cache_node, n, SLUB_RED_ACTIVE); init_tracking(kmem_cache_node, n); #endif + kasan_kmalloc(kmem_cache_node, n, sizeof(struct kmem_cache_node)); init_kmem_cache_node(n); inc_slabs_node(kmem_cache_node, node, page->objects); @@ -3260,6 +3319,8 @@ void *__kmalloc(size_t size, gfp_t flags) trace_kmalloc(_RET_IP_, ret, size, s->size, flags); + kasan_kmalloc(s, ret, size); + return ret; } EXPORT_SYMBOL(__kmalloc); @@ -3303,12 +3364,14 @@ void *__kmalloc_node(size_t size, gfp_t flags, int node) trace_kmalloc_node(_RET_IP_, ret, size, s->size, flags, node); + kasan_kmalloc(s, ret, size); + return ret; } EXPORT_SYMBOL(__kmalloc_node); #endif -size_t ksize(const void *object) +static size_t __ksize(const void *object) { struct page *page; @@ -3324,6 +3387,15 @@ size_t ksize(const void *object) return slab_ksize(page->slab_cache); } + +size_t ksize(const void *object) +{ + size_t size = __ksize(object); + /* We assume that ksize callers could use whole allocated area, + so we need unpoison this area. */ + kasan_krealloc(object, size); + return size; +} EXPORT_SYMBOL(ksize); void kfree(const void *x) @@ -3347,69 +3419,92 @@ void kfree(const void *x) } EXPORT_SYMBOL(kfree); +#define SHRINK_PROMOTE_MAX 32 + /* - * kmem_cache_shrink removes empty slabs from the partial lists and sorts - * the remaining slabs by the number of items in use. The slabs with the - * most items in use come first. New allocations will then fill those up - * and thus they can be removed from the partial lists. + * kmem_cache_shrink discards empty slabs and promotes the slabs filled + * up most to the head of the partial lists. New allocations will then + * fill those up and thus they can be removed from the partial lists. * * The slabs with the least items are placed last. This results in them * being allocated from last increasing the chance that the last objects * are freed in them. */ -int __kmem_cache_shrink(struct kmem_cache *s) +int __kmem_cache_shrink(struct kmem_cache *s, bool deactivate) { int node; int i; struct kmem_cache_node *n; struct page *page; struct page *t; - int objects = oo_objects(s->max); - struct list_head *slabs_by_inuse = - kmalloc(sizeof(struct list_head) * objects, GFP_KERNEL); + struct list_head discard; + struct list_head promote[SHRINK_PROMOTE_MAX]; unsigned long flags; + int ret = 0; - if (!slabs_by_inuse) - return -ENOMEM; + if (deactivate) { + /* + * Disable empty slabs caching. Used to avoid pinning offline + * memory cgroups by kmem pages that can be freed. + */ + s->cpu_partial = 0; + s->min_partial = 0; + + /* + * s->cpu_partial is checked locklessly (see put_cpu_partial), + * so we have to make sure the change is visible. + */ + kick_all_cpus_sync(); + } flush_all(s); for_each_kmem_cache_node(s, node, n) { - if (!n->nr_partial) - continue; - - for (i = 0; i < objects; i++) - INIT_LIST_HEAD(slabs_by_inuse + i); + INIT_LIST_HEAD(&discard); + for (i = 0; i < SHRINK_PROMOTE_MAX; i++) + INIT_LIST_HEAD(promote + i); spin_lock_irqsave(&n->list_lock, flags); /* - * Build lists indexed by the items in use in each slab. + * Build lists of slabs to discard or promote. * * Note that concurrent frees may occur while we hold the * list_lock. page->inuse here is the upper limit. */ list_for_each_entry_safe(page, t, &n->partial, lru) { - list_move(&page->lru, slabs_by_inuse + page->inuse); - if (!page->inuse) + int free = page->objects - page->inuse; + + /* Do not reread page->inuse */ + barrier(); + + /* We do not keep full slabs on the list */ + BUG_ON(free <= 0); + + if (free == page->objects) { + list_move(&page->lru, &discard); n->nr_partial--; + } else if (free <= SHRINK_PROMOTE_MAX) + list_move(&page->lru, promote + free - 1); } /* - * Rebuild the partial list with the slabs filled up most - * first and the least used slabs at the end. + * Promote the slabs filled up most to the head of the + * partial list. */ - for (i = objects - 1; i > 0; i--) - list_splice(slabs_by_inuse + i, n->partial.prev); + for (i = SHRINK_PROMOTE_MAX - 1; i >= 0; i--) + list_splice(promote + i, &n->partial); spin_unlock_irqrestore(&n->list_lock, flags); /* Release empty slabs */ - list_for_each_entry_safe(page, t, slabs_by_inuse, lru) + list_for_each_entry_safe(page, t, &discard, lru) discard_slab(s, page); + + if (slabs_node(s, node)) + ret = 1; } - kfree(slabs_by_inuse); - return 0; + return ret; } static int slab_mem_going_offline_callback(void *arg) @@ -3418,7 +3513,7 @@ static int slab_mem_going_offline_callback(void *arg) mutex_lock(&slab_mutex); list_for_each_entry(s, &slab_caches, list) - __kmem_cache_shrink(s); + __kmem_cache_shrink(s, false); mutex_unlock(&slab_mutex); return 0; @@ -3566,6 +3661,7 @@ static struct kmem_cache * __init bootstrap(struct kmem_cache *static_cache) p->slab_cache = s; #endif } + slab_init_memcg_params(s); list_add(&s->list, &slab_caches); return s; } @@ -3624,13 +3720,10 @@ struct kmem_cache * __kmem_cache_alias(const char *name, size_t size, size_t align, unsigned long flags, void (*ctor)(void *)) { - struct kmem_cache *s; + struct kmem_cache *s, *c; s = find_mergeable(size, align, flags, name, ctor); if (s) { - int i; - struct kmem_cache *c; - s->refcount++; /* @@ -3640,10 +3733,7 @@ __kmem_cache_alias(const char *name, size_t size, size_t align, s->object_size = max(s->object_size, (int)size); s->inuse = max_t(int, s->inuse, ALIGN(size, sizeof(void *))); - for_each_memcg_cache_index(i) { - c = cache_from_memcg_idx(s, i); - if (!c) - continue; + for_each_memcg_cache(c, s) { c->object_size = s->object_size; c->inuse = max_t(int, c->inuse, ALIGN(size, sizeof(void *))); @@ -4070,20 +4160,16 @@ static int list_locations(struct kmem_cache *s, char *buf, if (num_online_cpus() > 1 && !cpumask_empty(to_cpumask(l->cpus)) && - len < PAGE_SIZE - 60) { - len += sprintf(buf + len, " cpus="); - len += cpulist_scnprintf(buf + len, - PAGE_SIZE - len - 50, - to_cpumask(l->cpus)); - } + len < PAGE_SIZE - 60) + len += scnprintf(buf + len, PAGE_SIZE - len - 50, + " cpus=%*pbl", + cpumask_pr_args(to_cpumask(l->cpus))); if (nr_online_nodes > 1 && !nodes_empty(l->nodes) && - len < PAGE_SIZE - 60) { - len += sprintf(buf + len, " nodes="); - len += nodelist_scnprintf(buf + len, - PAGE_SIZE - len - 50, - l->nodes); - } + len < PAGE_SIZE - 60) + len += scnprintf(buf + len, PAGE_SIZE - len - 50, + " nodes=%*pbl", + nodemask_pr_args(&l->nodes)); len += sprintf(buf + len, "\n"); } @@ -4680,12 +4766,9 @@ static ssize_t shrink_show(struct kmem_cache *s, char *buf) static ssize_t shrink_store(struct kmem_cache *s, const char *buf, size_t length) { - if (buf[0] == '1') { - int rc = kmem_cache_shrink(s); - - if (rc) - return rc; - } else + if (buf[0] == '1') + kmem_cache_shrink(s); + else return -EINVAL; return length; } @@ -4909,7 +4992,7 @@ static ssize_t slab_attr_store(struct kobject *kobj, err = attribute->store(s, buf, len); #ifdef CONFIG_MEMCG_KMEM if (slab_state >= FULL && err >= 0 && is_root_cache(s)) { - int i; + struct kmem_cache *c; mutex_lock(&slab_mutex); if (s->max_attr_size < len) @@ -4932,11 +5015,8 @@ static ssize_t slab_attr_store(struct kobject *kobj, * directly either failed or succeeded, in which case we loop * through the descendants with best-effort propagation. */ - for_each_memcg_cache_index(i) { - struct kmem_cache *c = cache_from_memcg_idx(s, i); - if (c) - attribute->store(c, buf, len); - } + for_each_memcg_cache(c, s) + attribute->store(c, buf, len); mutex_unlock(&slab_mutex); } #endif @@ -4953,7 +5033,7 @@ static void memcg_propagate_slab_attrs(struct kmem_cache *s) if (is_root_cache(s)) return; - root_cache = s->memcg_params->root_cache; + root_cache = s->memcg_params.root_cache; /* * This mean this cache had no attribute written. Therefore, no point @@ -5033,7 +5113,7 @@ static inline struct kset *cache_kset(struct kmem_cache *s) { #ifdef CONFIG_MEMCG_KMEM if (!is_root_cache(s)) - return s->memcg_params->root_cache->memcg_kset; + return s->memcg_params.root_cache->memcg_kset; #endif return slab_kset; } diff --git a/mm/swap.c b/mm/swap.c index 8a12b33936b4..cd3a5e64cea9 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -1138,12 +1138,8 @@ void __init swap_setup(void) #ifdef CONFIG_SWAP int i; - if (bdi_init(swapper_spaces[0].backing_dev_info)) - panic("Failed to init swap bdi"); - for (i = 0; i < MAX_SWAPFILES; i++) { + for (i = 0; i < MAX_SWAPFILES; i++) spin_lock_init(&swapper_spaces[i].tree_lock); - INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); - } #endif /* Use a smaller cluster for small-memory machines */ diff --git a/mm/swap_state.c b/mm/swap_state.c index 9711342987a0..405923f77334 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -32,17 +32,11 @@ static const struct address_space_operations swap_aops = { #endif }; -static struct backing_dev_info swap_backing_dev_info = { - .name = "swap", - .capabilities = BDI_CAP_NO_ACCT_AND_WRITEBACK | BDI_CAP_SWAP_BACKED, -}; - struct address_space swapper_spaces[MAX_SWAPFILES] = { [0 ... MAX_SWAPFILES - 1] = { .page_tree = RADIX_TREE_INIT(GFP_ATOMIC|__GFP_NOWARN), .i_mmap_writable = ATOMIC_INIT(0), .a_ops = &swap_aops, - .backing_dev_info = &swap_backing_dev_info, } }; diff --git a/mm/truncate.c b/mm/truncate.c index f1e4d6052369..ddec5a5966d7 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -112,7 +112,7 @@ void cancel_dirty_page(struct page *page, unsigned int account_size) struct address_space *mapping = page->mapping; if (mapping && mapping_cap_account_dirty(mapping)) { dec_zone_page_state(page, NR_FILE_DIRTY); - dec_bdi_stat(mapping->backing_dev_info, + dec_bdi_stat(inode_to_bdi(mapping->host), BDI_RECLAIMABLE); if (account_size) task_io_account_cancelled_write(account_size); diff --git a/mm/util.c b/mm/util.c index fec39d4509a9..3981ae9d1b15 100644 --- a/mm/util.c +++ b/mm/util.c @@ -12,10 +12,30 @@ #include <linux/hugetlb.h> #include <linux/vmalloc.h> +#include <asm/sections.h> #include <asm/uaccess.h> #include "internal.h" +static inline int is_kernel_rodata(unsigned long addr) +{ + return addr >= (unsigned long)__start_rodata && + addr < (unsigned long)__end_rodata; +} + +/** + * kfree_const - conditionally free memory + * @x: pointer to the memory + * + * Function calls kfree only if @x is not in .rodata section. + */ +void kfree_const(const void *x) +{ + if (!is_kernel_rodata((unsigned long)x)) + kfree(x); +} +EXPORT_SYMBOL(kfree_const); + /** * kstrdup - allocate space for and copy an existing string * @s: the string to duplicate @@ -38,6 +58,24 @@ char *kstrdup(const char *s, gfp_t gfp) EXPORT_SYMBOL(kstrdup); /** + * kstrdup_const - conditionally duplicate an existing const string + * @s: the string to duplicate + * @gfp: the GFP mask used in the kmalloc() call when allocating memory + * + * Function returns source string if it is in .rodata section otherwise it + * fallbacks to kstrdup. + * Strings allocated by kstrdup_const should be freed by kfree_const. + */ +const char *kstrdup_const(const char *s, gfp_t gfp) +{ + if (is_kernel_rodata((unsigned long)s)) + return s; + + return kstrdup(s, gfp); +} +EXPORT_SYMBOL(kstrdup_const); + +/** * kstrndup - allocate space for and copy an existing string * @s: the string to duplicate * @max: read at most @max chars from @s @@ -240,14 +278,8 @@ int __weak get_user_pages_fast(unsigned long start, int nr_pages, int write, struct page **pages) { struct mm_struct *mm = current->mm; - int ret; - - down_read(&mm->mmap_sem); - ret = get_user_pages(current, mm, start, nr_pages, - write, 0, pages, NULL); - up_read(&mm->mmap_sem); - - return ret; + return get_user_pages_unlocked(current, mm, start, nr_pages, + write, 0, pages); } EXPORT_SYMBOL_GPL(get_user_pages_fast); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 39c338896416..35b25e1340ca 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1324,10 +1324,8 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, if (unlikely(!area)) return NULL; - /* - * We always allocate a guard page. - */ - size += PAGE_SIZE; + if (!(flags & VM_NO_GUARD)) + size += PAGE_SIZE; va = alloc_vmap_area(size, align, start, end, node, gfp_mask); if (IS_ERR(va)) { @@ -1621,6 +1619,7 @@ fail: * @end: vm area range end * @gfp_mask: flags for the page level allocator * @prot: protection mask for the allocated pages + * @vm_flags: additional vm area flags (e.g. %VM_NO_GUARD) * @node: node to use for allocation or NUMA_NO_NODE * @caller: caller's return address * @@ -1630,7 +1629,8 @@ fail: */ void *__vmalloc_node_range(unsigned long size, unsigned long align, unsigned long start, unsigned long end, gfp_t gfp_mask, - pgprot_t prot, int node, const void *caller) + pgprot_t prot, unsigned long vm_flags, int node, + const void *caller) { struct vm_struct *area; void *addr; @@ -1640,8 +1640,8 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, if (!size || (size >> PAGE_SHIFT) > totalram_pages) goto fail; - area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED, - start, end, node, gfp_mask, caller); + area = __get_vm_area_node(size, align, VM_ALLOC | VM_UNINITIALIZED | + vm_flags, start, end, node, gfp_mask, caller); if (!area) goto fail; @@ -1690,7 +1690,7 @@ static void *__vmalloc_node(unsigned long size, unsigned long align, int node, const void *caller) { return __vmalloc_node_range(size, align, VMALLOC_START, VMALLOC_END, - gfp_mask, prot, node, caller); + gfp_mask, prot, 0, node, caller); } void *__vmalloc(unsigned long size, gfp_t gfp_mask, pgprot_t prot) diff --git a/mm/vmscan.c b/mm/vmscan.c index dcd90c891d8e..5e8eadd71bac 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -91,6 +91,9 @@ struct scan_control { /* Can pages be swapped as part of reclaim? */ unsigned int may_swap:1; + /* Can cgroups be reclaimed below their normal consumption range? */ + unsigned int may_thrash:1; + unsigned int hibernation_mode:1; /* One of the zones is ready for compaction */ @@ -229,10 +232,10 @@ EXPORT_SYMBOL(unregister_shrinker); #define SHRINK_BATCH 128 -static unsigned long shrink_slabs(struct shrink_control *shrinkctl, - struct shrinker *shrinker, - unsigned long nr_scanned, - unsigned long nr_eligible) +static unsigned long do_shrink_slab(struct shrink_control *shrinkctl, + struct shrinker *shrinker, + unsigned long nr_scanned, + unsigned long nr_eligible) { unsigned long freed = 0; unsigned long long delta; @@ -341,9 +344,10 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl, } /** - * shrink_node_slabs - shrink slab caches of a given node + * shrink_slab - shrink slab caches * @gfp_mask: allocation context * @nid: node whose slab caches to target + * @memcg: memory cgroup whose slab caches to target * @nr_scanned: pressure numerator * @nr_eligible: pressure denominator * @@ -352,6 +356,12 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl, * @nid is passed along to shrinkers with SHRINKER_NUMA_AWARE set, * unaware shrinkers will receive a node id of 0 instead. * + * @memcg specifies the memory cgroup to target. If it is not NULL, + * only shrinkers with SHRINKER_MEMCG_AWARE set will be called to scan + * objects from the memory cgroup specified. Otherwise all shrinkers + * are called, and memcg aware shrinkers are supposed to scan the + * global list then. + * * @nr_scanned and @nr_eligible form a ratio that indicate how much of * the available objects should be scanned. Page reclaim for example * passes the number of pages scanned and the number of pages on the @@ -362,13 +372,17 @@ static unsigned long shrink_slabs(struct shrink_control *shrinkctl, * * Returns the number of reclaimed slab objects. */ -unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid, - unsigned long nr_scanned, - unsigned long nr_eligible) +static unsigned long shrink_slab(gfp_t gfp_mask, int nid, + struct mem_cgroup *memcg, + unsigned long nr_scanned, + unsigned long nr_eligible) { struct shrinker *shrinker; unsigned long freed = 0; + if (memcg && !memcg_kmem_is_active(memcg)) + return 0; + if (nr_scanned == 0) nr_scanned = SWAP_CLUSTER_MAX; @@ -387,12 +401,16 @@ unsigned long shrink_node_slabs(gfp_t gfp_mask, int nid, struct shrink_control sc = { .gfp_mask = gfp_mask, .nid = nid, + .memcg = memcg, }; + if (memcg && !(shrinker->flags & SHRINKER_MEMCG_AWARE)) + continue; + if (!(shrinker->flags & SHRINKER_NUMA_AWARE)) sc.nid = 0; - freed += shrink_slabs(&sc, shrinker, nr_scanned, nr_eligible); + freed += do_shrink_slab(&sc, shrinker, nr_scanned, nr_eligible); } up_read(&shrinker_rwsem); @@ -401,6 +419,29 @@ out: return freed; } +void drop_slab_node(int nid) +{ + unsigned long freed; + + do { + struct mem_cgroup *memcg = NULL; + + freed = 0; + do { + freed += shrink_slab(GFP_KERNEL, nid, memcg, + 1000, 1000); + } while ((memcg = mem_cgroup_iter(NULL, memcg, NULL)) != NULL); + } while (freed > 10); +} + +void drop_slab(void) +{ + int nid; + + for_each_online_node(nid) + drop_slab_node(nid); +} + static inline int is_page_cache_freeable(struct page *page) { /* @@ -497,7 +538,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping, } if (mapping->a_ops->writepage == NULL) return PAGE_ACTIVATE; - if (!may_write_to_queue(mapping->backing_dev_info, sc)) + if (!may_write_to_queue(inode_to_bdi(mapping->host), sc)) return PAGE_KEEP; if (clear_page_dirty_for_io(page)) { @@ -876,7 +917,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, */ mapping = page_mapping(page); if (((dirty || writeback) && mapping && - bdi_write_congested(mapping->backing_dev_info)) || + bdi_write_congested(inode_to_bdi(mapping->host))) || (writeback && PageReclaim(page))) nr_congested++; @@ -1903,8 +1944,12 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, * latencies, so it's better to scan a minimum amount there as * well. */ - if (current_is_kswapd() && !zone_reclaimable(zone)) - force_scan = true; + if (current_is_kswapd()) { + if (!zone_reclaimable(zone)) + force_scan = true; + if (!mem_cgroup_lruvec_online(lruvec)) + force_scan = true; + } if (!global_reclaim(sc)) force_scan = true; @@ -2269,6 +2314,7 @@ static inline bool should_continue_reclaim(struct zone *zone, static bool shrink_zone(struct zone *zone, struct scan_control *sc, bool is_classzone) { + struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_reclaimed, nr_scanned; bool reclaimable = false; @@ -2287,15 +2333,28 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, memcg = mem_cgroup_iter(root, NULL, &reclaim); do { unsigned long lru_pages; + unsigned long scanned; struct lruvec *lruvec; int swappiness; + if (mem_cgroup_low(root, memcg)) { + if (!sc->may_thrash) + continue; + mem_cgroup_events(memcg, MEMCG_LOW, 1); + } + lruvec = mem_cgroup_zone_lruvec(zone, memcg); swappiness = mem_cgroup_swappiness(memcg); + scanned = sc->nr_scanned; shrink_lruvec(lruvec, swappiness, sc, &lru_pages); zone_lru_pages += lru_pages; + if (memcg && is_classzone) + shrink_slab(sc->gfp_mask, zone_to_nid(zone), + memcg, sc->nr_scanned - scanned, + lru_pages); + /* * Direct reclaim and kswapd have to scan all memory * cgroups to fulfill the overall scan target for the @@ -2311,26 +2370,20 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, mem_cgroup_iter_break(root, memcg); break; } - memcg = mem_cgroup_iter(root, memcg, &reclaim); - } while (memcg); + } while ((memcg = mem_cgroup_iter(root, memcg, &reclaim))); /* * Shrink the slab caches in the same proportion that * the eligible LRU pages were scanned. */ - if (global_reclaim(sc) && is_classzone) { - struct reclaim_state *reclaim_state; - - shrink_node_slabs(sc->gfp_mask, zone_to_nid(zone), - sc->nr_scanned - nr_scanned, - zone_lru_pages); - - reclaim_state = current->reclaim_state; - if (reclaim_state) { - sc->nr_reclaimed += - reclaim_state->reclaimed_slab; - reclaim_state->reclaimed_slab = 0; - } + if (global_reclaim(sc) && is_classzone) + shrink_slab(sc->gfp_mask, zone_to_nid(zone), NULL, + sc->nr_scanned - nr_scanned, + zone_lru_pages); + + if (reclaim_state) { + sc->nr_reclaimed += reclaim_state->reclaimed_slab; + reclaim_state->reclaimed_slab = 0; } vmpressure(sc->gfp_mask, sc->target_mem_cgroup, @@ -2515,10 +2568,11 @@ static bool shrink_zones(struct zonelist *zonelist, struct scan_control *sc) static unsigned long do_try_to_free_pages(struct zonelist *zonelist, struct scan_control *sc) { + int initial_priority = sc->priority; unsigned long total_scanned = 0; unsigned long writeback_threshold; bool zones_reclaimable; - +retry: delayacct_freepages_start(); if (global_reclaim(sc)) @@ -2568,6 +2622,13 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, if (sc->compaction_ready) return 1; + /* Untapped cgroup reserves? Don't OOM, retry. */ + if (!sc->may_thrash) { + sc->priority = initial_priority; + sc->may_thrash = 1; + goto retry; + } + /* Any of the zones still reclaimable? Don't OOM. */ if (zones_reclaimable) return 1; @@ -3175,7 +3236,7 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, */ if (waitqueue_active(&pgdat->pfmemalloc_wait) && pfmemalloc_watermark_ok(pgdat)) - wake_up(&pgdat->pfmemalloc_wait); + wake_up_all(&pgdat->pfmemalloc_wait); /* * Fragmentation may mean that the system cannot be rebalanced diff --git a/mm/vmstat.c b/mm/vmstat.c index 1284f89fca08..4f5cd974e11a 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -17,6 +17,9 @@ #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/vmstat.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> #include <linux/sched.h> #include <linux/math64.h> #include <linux/writeback.h> @@ -670,66 +673,6 @@ int fragmentation_index(struct zone *zone, unsigned int order) } #endif -#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION) -#include <linux/proc_fs.h> -#include <linux/seq_file.h> - -static char * const migratetype_names[MIGRATE_TYPES] = { - "Unmovable", - "Reclaimable", - "Movable", - "Reserve", -#ifdef CONFIG_CMA - "CMA", -#endif -#ifdef CONFIG_MEMORY_ISOLATION - "Isolate", -#endif -}; - -static void *frag_start(struct seq_file *m, loff_t *pos) -{ - pg_data_t *pgdat; - loff_t node = *pos; - for (pgdat = first_online_pgdat(); - pgdat && node; - pgdat = next_online_pgdat(pgdat)) - --node; - - return pgdat; -} - -static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) -{ - pg_data_t *pgdat = (pg_data_t *)arg; - - (*pos)++; - return next_online_pgdat(pgdat); -} - -static void frag_stop(struct seq_file *m, void *arg) -{ -} - -/* Walk all the zones in a node and print using a callback */ -static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, - void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) -{ - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!populated_zone(zone)) - continue; - - spin_lock_irqsave(&zone->lock, flags); - print(m, pgdat, zone); - spin_unlock_irqrestore(&zone->lock, flags); - } -} -#endif - #if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) #ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", @@ -907,7 +850,66 @@ const char * const vmstat_text[] = { #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ +#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ + defined(CONFIG_PROC_FS) +static void *frag_start(struct seq_file *m, loff_t *pos) +{ + pg_data_t *pgdat; + loff_t node = *pos; + + for (pgdat = first_online_pgdat(); + pgdat && node; + pgdat = next_online_pgdat(pgdat)) + --node; + + return pgdat; +} + +static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + (*pos)++; + return next_online_pgdat(pgdat); +} + +static void frag_stop(struct seq_file *m, void *arg) +{ +} + +/* Walk all the zones in a node and print using a callback */ +static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, + void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) +{ + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + unsigned long flags; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { + if (!populated_zone(zone)) + continue; + + spin_lock_irqsave(&zone->lock, flags); + print(m, pgdat, zone); + spin_unlock_irqrestore(&zone->lock, flags); + } +} +#endif + #ifdef CONFIG_PROC_FS +static char * const migratetype_names[MIGRATE_TYPES] = { + "Unmovable", + "Reclaimable", + "Movable", + "Reserve", +#ifdef CONFIG_CMA + "CMA", +#endif +#ifdef CONFIG_MEMORY_ISOLATION + "Isolate", +#endif +}; + static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { @@ -1435,8 +1437,8 @@ static void vmstat_shepherd(struct work_struct *w) if (need_update(cpu) && cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - schedule_delayed_work_on(cpu, &per_cpu(vmstat_work, cpu), - __round_jiffies_relative(sysctl_stat_interval, cpu)); + schedule_delayed_work_on(cpu, + &per_cpu(vmstat_work, cpu), 0); put_online_cpus(); @@ -1450,7 +1452,7 @@ static void __init start_shepherd_timer(void) int cpu; for_each_possible_cpu(cpu) - INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), + INIT_DELAYED_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL)) @@ -1536,8 +1538,6 @@ static int __init setup_vmstat(void) module_init(setup_vmstat) #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) -#include <linux/debugfs.h> - /* * Return an index indicating how much of the available free memory is diff --git a/mm/workingset.c b/mm/workingset.c index f7216fa7da27..aa017133744b 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -275,7 +275,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ local_irq_disable(); - shadow_nodes = list_lru_count_node(&workingset_shadow_nodes, sc->nid); + shadow_nodes = list_lru_shrink_count(&workingset_shadow_nodes, sc); local_irq_enable(); pages = node_present_pages(sc->nid); @@ -302,6 +302,7 @@ static unsigned long count_shadow_nodes(struct shrinker *shrinker, } static enum lru_status shadow_lru_isolate(struct list_head *item, + struct list_lru_one *lru, spinlock_t *lru_lock, void *arg) { @@ -332,7 +333,7 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, goto out; } - list_del_init(item); + list_lru_isolate(lru, item); spin_unlock(lru_lock); /* @@ -376,8 +377,8 @@ static unsigned long scan_shadow_nodes(struct shrinker *shrinker, /* list_lru lock nests inside IRQ-safe mapping->tree_lock */ local_irq_disable(); - ret = list_lru_walk_node(&workingset_shadow_nodes, sc->nid, - shadow_lru_isolate, NULL, &sc->nr_to_scan); + ret = list_lru_shrink_walk(&workingset_shadow_nodes, sc, + shadow_lru_isolate, NULL); local_irq_enable(); return ret; } diff --git a/mm/zbud.c b/mm/zbud.c index 4e387bea702e..2ee4e4520493 100644 --- a/mm/zbud.c +++ b/mm/zbud.c @@ -130,7 +130,8 @@ static struct zbud_ops zbud_zpool_ops = { .evict = zbud_zpool_evict }; -static void *zbud_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops) +static void *zbud_zpool_create(char *name, gfp_t gfp, + struct zpool_ops *zpool_ops) { return zbud_create_pool(gfp, zpool_ops ? &zbud_zpool_ops : NULL); } diff --git a/mm/zpool.c b/mm/zpool.c index 739cdf0d183a..bacdab6e47de 100644 --- a/mm/zpool.c +++ b/mm/zpool.c @@ -129,6 +129,7 @@ static void zpool_put_driver(struct zpool_driver *driver) /** * zpool_create_pool() - Create a new zpool * @type The type of the zpool to create (e.g. zbud, zsmalloc) + * @name The name of the zpool (e.g. zram0, zswap) * @gfp The GFP flags to use when allocating the pool. * @ops The optional ops callback. * @@ -140,7 +141,8 @@ static void zpool_put_driver(struct zpool_driver *driver) * * Returns: New zpool on success, NULL on failure. */ -struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops) +struct zpool *zpool_create_pool(char *type, char *name, gfp_t gfp, + struct zpool_ops *ops) { struct zpool_driver *driver; struct zpool *zpool; @@ -168,7 +170,7 @@ struct zpool *zpool_create_pool(char *type, gfp_t gfp, struct zpool_ops *ops) zpool->type = driver->type; zpool->driver = driver; - zpool->pool = driver->create(gfp, ops); + zpool->pool = driver->create(name, gfp, ops); zpool->ops = ops; if (!zpool->pool) { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index b72403927aa4..0dec1fa5f656 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -91,6 +91,7 @@ #include <linux/hardirq.h> #include <linux/spinlock.h> #include <linux/types.h> +#include <linux/debugfs.h> #include <linux/zsmalloc.h> #include <linux/zpool.h> @@ -168,6 +169,22 @@ enum fullness_group { ZS_FULL }; +enum zs_stat_type { + OBJ_ALLOCATED, + OBJ_USED, + NR_ZS_STAT_TYPE, +}; + +#ifdef CONFIG_ZSMALLOC_STAT + +static struct dentry *zs_stat_root; + +struct zs_size_stat { + unsigned long objs[NR_ZS_STAT_TYPE]; +}; + +#endif + /* * number of size_classes */ @@ -200,6 +217,10 @@ struct size_class { /* Number of PAGE_SIZE sized pages to combine to form a 'zspage' */ int pages_per_zspage; +#ifdef CONFIG_ZSMALLOC_STAT + struct zs_size_stat stats; +#endif + spinlock_t lock; struct page *fullness_list[_ZS_NR_FULLNESS_GROUPS]; @@ -217,10 +238,16 @@ struct link_free { }; struct zs_pool { + char *name; + struct size_class **size_class; gfp_t flags; /* allocation flags used when growing pool */ atomic_long_t pages_allocated; + +#ifdef CONFIG_ZSMALLOC_STAT + struct dentry *stat_dentry; +#endif }; /* @@ -246,9 +273,9 @@ struct mapping_area { #ifdef CONFIG_ZPOOL -static void *zs_zpool_create(gfp_t gfp, struct zpool_ops *zpool_ops) +static void *zs_zpool_create(char *name, gfp_t gfp, struct zpool_ops *zpool_ops) { - return zs_create_pool(gfp); + return zs_create_pool(name, gfp); } static void zs_zpool_destroy(void *pool) @@ -942,6 +969,166 @@ static bool can_merge(struct size_class *prev, int size, int pages_per_zspage) return true; } +#ifdef CONFIG_ZSMALLOC_STAT + +static inline void zs_stat_inc(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ + class->stats.objs[type] += cnt; +} + +static inline void zs_stat_dec(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ + class->stats.objs[type] -= cnt; +} + +static inline unsigned long zs_stat_get(struct size_class *class, + enum zs_stat_type type) +{ + return class->stats.objs[type]; +} + +static int __init zs_stat_init(void) +{ + if (!debugfs_initialized()) + return -ENODEV; + + zs_stat_root = debugfs_create_dir("zsmalloc", NULL); + if (!zs_stat_root) + return -ENOMEM; + + return 0; +} + +static void __exit zs_stat_exit(void) +{ + debugfs_remove_recursive(zs_stat_root); +} + +static int zs_stats_size_show(struct seq_file *s, void *v) +{ + int i; + struct zs_pool *pool = s->private; + struct size_class *class; + int objs_per_zspage; + unsigned long obj_allocated, obj_used, pages_used; + unsigned long total_objs = 0, total_used_objs = 0, total_pages = 0; + + seq_printf(s, " %5s %5s %13s %10s %10s\n", "class", "size", + "obj_allocated", "obj_used", "pages_used"); + + for (i = 0; i < zs_size_classes; i++) { + class = pool->size_class[i]; + + if (class->index != i) + continue; + + spin_lock(&class->lock); + obj_allocated = zs_stat_get(class, OBJ_ALLOCATED); + obj_used = zs_stat_get(class, OBJ_USED); + spin_unlock(&class->lock); + + objs_per_zspage = get_maxobj_per_zspage(class->size, + class->pages_per_zspage); + pages_used = obj_allocated / objs_per_zspage * + class->pages_per_zspage; + + seq_printf(s, " %5u %5u %10lu %10lu %10lu\n", i, + class->size, obj_allocated, obj_used, pages_used); + + total_objs += obj_allocated; + total_used_objs += obj_used; + total_pages += pages_used; + } + + seq_puts(s, "\n"); + seq_printf(s, " %5s %5s %10lu %10lu %10lu\n", "Total", "", + total_objs, total_used_objs, total_pages); + + return 0; +} + +static int zs_stats_size_open(struct inode *inode, struct file *file) +{ + return single_open(file, zs_stats_size_show, inode->i_private); +} + +static const struct file_operations zs_stat_size_ops = { + .open = zs_stats_size_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; + +static int zs_pool_stat_create(char *name, struct zs_pool *pool) +{ + struct dentry *entry; + + if (!zs_stat_root) + return -ENODEV; + + entry = debugfs_create_dir(name, zs_stat_root); + if (!entry) { + pr_warn("debugfs dir <%s> creation failed\n", name); + return -ENOMEM; + } + pool->stat_dentry = entry; + + entry = debugfs_create_file("obj_in_classes", S_IFREG | S_IRUGO, + pool->stat_dentry, pool, &zs_stat_size_ops); + if (!entry) { + pr_warn("%s: debugfs file entry <%s> creation failed\n", + name, "obj_in_classes"); + return -ENOMEM; + } + + return 0; +} + +static void zs_pool_stat_destroy(struct zs_pool *pool) +{ + debugfs_remove_recursive(pool->stat_dentry); +} + +#else /* CONFIG_ZSMALLOC_STAT */ + +static inline void zs_stat_inc(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ +} + +static inline void zs_stat_dec(struct size_class *class, + enum zs_stat_type type, unsigned long cnt) +{ +} + +static inline unsigned long zs_stat_get(struct size_class *class, + enum zs_stat_type type) +{ + return 0; +} + +static int __init zs_stat_init(void) +{ + return 0; +} + +static void __exit zs_stat_exit(void) +{ +} + +static inline int zs_pool_stat_create(char *name, struct zs_pool *pool) +{ + return 0; +} + +static inline void zs_pool_stat_destroy(struct zs_pool *pool) +{ +} + +#endif + unsigned long zs_get_total_pages(struct zs_pool *pool) { return atomic_long_read(&pool->pages_allocated); @@ -1074,7 +1261,10 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) set_zspage_mapping(first_page, class->index, ZS_EMPTY); atomic_long_add(class->pages_per_zspage, &pool->pages_allocated); + spin_lock(&class->lock); + zs_stat_inc(class, OBJ_ALLOCATED, get_maxobj_per_zspage( + class->size, class->pages_per_zspage)); } obj = (unsigned long)first_page->freelist; @@ -1088,6 +1278,7 @@ unsigned long zs_malloc(struct zs_pool *pool, size_t size) kunmap_atomic(vaddr); first_page->inuse++; + zs_stat_inc(class, OBJ_USED, 1); /* Now move the zspage to another fullness group, if required */ fix_fullness_group(pool, first_page); spin_unlock(&class->lock); @@ -1128,6 +1319,12 @@ void zs_free(struct zs_pool *pool, unsigned long obj) first_page->inuse--; fullness = fix_fullness_group(pool, first_page); + + zs_stat_dec(class, OBJ_USED, 1); + if (fullness == ZS_EMPTY) + zs_stat_dec(class, OBJ_ALLOCATED, get_maxobj_per_zspage( + class->size, class->pages_per_zspage)); + spin_unlock(&class->lock); if (fullness == ZS_EMPTY) { @@ -1148,7 +1345,7 @@ EXPORT_SYMBOL_GPL(zs_free); * On success, a pointer to the newly created pool is returned, * otherwise NULL. */ -struct zs_pool *zs_create_pool(gfp_t flags) +struct zs_pool *zs_create_pool(char *name, gfp_t flags) { int i; struct zs_pool *pool; @@ -1158,9 +1355,16 @@ struct zs_pool *zs_create_pool(gfp_t flags) if (!pool) return NULL; + pool->name = kstrdup(name, GFP_KERNEL); + if (!pool->name) { + kfree(pool); + return NULL; + } + pool->size_class = kcalloc(zs_size_classes, sizeof(struct size_class *), GFP_KERNEL); if (!pool->size_class) { + kfree(pool->name); kfree(pool); return NULL; } @@ -1210,6 +1414,9 @@ struct zs_pool *zs_create_pool(gfp_t flags) pool->flags = flags; + if (zs_pool_stat_create(name, pool)) + goto err; + return pool; err: @@ -1222,6 +1429,8 @@ void zs_destroy_pool(struct zs_pool *pool) { int i; + zs_pool_stat_destroy(pool); + for (i = 0; i < zs_size_classes; i++) { int fg; struct size_class *class = pool->size_class[i]; @@ -1242,6 +1451,7 @@ void zs_destroy_pool(struct zs_pool *pool) } kfree(pool->size_class); + kfree(pool->name); kfree(pool); } EXPORT_SYMBOL_GPL(zs_destroy_pool); @@ -1250,17 +1460,30 @@ static int __init zs_init(void) { int ret = zs_register_cpu_notifier(); - if (ret) { - zs_unregister_cpu_notifier(); - return ret; - } + if (ret) + goto notifier_fail; init_zs_size_classes(); #ifdef CONFIG_ZPOOL zpool_register_driver(&zs_zpool_driver); #endif + + ret = zs_stat_init(); + if (ret) { + pr_err("zs stat initialization failed\n"); + goto stat_fail; + } return 0; + +stat_fail: +#ifdef CONFIG_ZPOOL + zpool_unregister_driver(&zs_zpool_driver); +#endif +notifier_fail: + zs_unregister_cpu_notifier(); + + return ret; } static void __exit zs_exit(void) @@ -1269,6 +1492,8 @@ static void __exit zs_exit(void) zpool_unregister_driver(&zs_zpool_driver); #endif zs_unregister_cpu_notifier(); + + zs_stat_exit(); } module_init(zs_init); diff --git a/mm/zswap.c b/mm/zswap.c index 0cfce9bc51e4..4249e82ff934 100644 --- a/mm/zswap.c +++ b/mm/zswap.c @@ -906,11 +906,12 @@ static int __init init_zswap(void) pr_info("loading zswap\n"); - zswap_pool = zpool_create_pool(zswap_zpool_type, gfp, &zswap_zpool_ops); + zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp, + &zswap_zpool_ops); if (!zswap_pool && strcmp(zswap_zpool_type, ZSWAP_ZPOOL_DEFAULT)) { pr_info("%s zpool not available\n", zswap_zpool_type); zswap_zpool_type = ZSWAP_ZPOOL_DEFAULT; - zswap_pool = zpool_create_pool(zswap_zpool_type, gfp, + zswap_pool = zpool_create_pool(zswap_zpool_type, "zswap", gfp, &zswap_zpool_ops); } if (!zswap_pool) { |