diff options
Diffstat (limited to 'mm')
44 files changed, 1797 insertions, 1217 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 7ba8fea..dd8e2aa 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -318,7 +318,7 @@ static void wakeup_timer_fn(unsigned long data) if (bdi->wb.task) { trace_writeback_wake_thread(bdi); wake_up_process(bdi->wb.task); - } else { + } else if (bdi->dev) { /* * When bdi tasks are inactive for long time, they are killed. * In this case we have to wake-up the forker thread which @@ -584,6 +584,8 @@ EXPORT_SYMBOL(bdi_register_dev); */ static void bdi_wb_shutdown(struct backing_dev_info *bdi) { + struct task_struct *task; + if (!bdi_cap_writeback_dirty(bdi)) return; @@ -602,8 +604,13 @@ static void bdi_wb_shutdown(struct backing_dev_info *bdi) * Finally, kill the kernel thread. We don't need to be RCU * safe anymore, since the bdi is gone from visibility. */ - if (bdi->wb.task) - kthread_stop(bdi->wb.task); + spin_lock_bh(&bdi->wb_lock); + task = bdi->wb.task; + bdi->wb.task = NULL; + spin_unlock_bh(&bdi->wb_lock); + + if (task) + kthread_stop(task); } /* @@ -623,7 +630,9 @@ static void bdi_prune_sb(struct backing_dev_info *bdi) void bdi_unregister(struct backing_dev_info *bdi) { - if (bdi->dev) { + struct device *dev = bdi->dev; + + if (dev) { bdi_set_min_ratio(bdi, 0); trace_writeback_bdi_unregister(bdi); bdi_prune_sb(bdi); @@ -632,8 +641,12 @@ void bdi_unregister(struct backing_dev_info *bdi) if (!bdi_cap_flush_forker(bdi)) bdi_wb_shutdown(bdi); bdi_debug_unregister(bdi); - device_unregister(bdi->dev); + + spin_lock_bh(&bdi->wb_lock); bdi->dev = NULL; + spin_unlock_bh(&bdi->wb_lock); + + device_unregister(dev); } } EXPORT_SYMBOL(bdi_unregister); diff --git a/mm/bootmem.c b/mm/bootmem.c index 668e94d..0131170 100644 --- a/mm/bootmem.c +++ b/mm/bootmem.c @@ -766,14 +766,13 @@ void * __init alloc_bootmem_section(unsigned long size, unsigned long section_nr) { bootmem_data_t *bdata; - unsigned long pfn, goal, limit; + unsigned long pfn, goal; pfn = section_nr_to_pfn(section_nr); goal = pfn << PAGE_SHIFT; - limit = section_nr_to_pfn(section_nr + 1) << PAGE_SHIFT; bdata = &bootmem_node_data[early_pfn_to_nid(pfn)]; - return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, limit); + return alloc_bootmem_core(bdata, size, SMP_CACHE_BYTES, goal, 0); } #endif diff --git a/mm/bounce.c b/mm/bounce.c index 4e9ae72..d1be02c 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -50,9 +50,9 @@ static void bounce_copy_vec(struct bio_vec *to, unsigned char *vfrom) unsigned char *vto; local_irq_save(flags); - vto = kmap_atomic(to->bv_page, KM_BOUNCE_READ); + vto = kmap_atomic(to->bv_page); memcpy(vto + to->bv_offset, vfrom, to->bv_len); - kunmap_atomic(vto, KM_BOUNCE_READ); + kunmap_atomic(vto); local_irq_restore(flags); } diff --git a/mm/cleancache.c b/mm/cleancache.c index bcaae4c..5646c74 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -15,29 +15,34 @@ #include <linux/fs.h> #include <linux/exportfs.h> #include <linux/mm.h> +#include <linux/debugfs.h> #include <linux/cleancache.h> /* * This global enablement flag may be read thousands of times per second - * by cleancache_get/put/flush even on systems where cleancache_ops + * by cleancache_get/put/invalidate even on systems where cleancache_ops * is not claimed (e.g. cleancache is config'ed on but remains * disabled), so is preferred to the slower alternative: a function * call that checks a non-global. */ -int cleancache_enabled; +int cleancache_enabled __read_mostly; EXPORT_SYMBOL(cleancache_enabled); /* * cleancache_ops is set by cleancache_ops_register to contain the pointers * to the cleancache "backend" implementation functions. */ -static struct cleancache_ops cleancache_ops; +static struct cleancache_ops cleancache_ops __read_mostly; -/* useful stats available in /sys/kernel/mm/cleancache */ -static unsigned long cleancache_succ_gets; -static unsigned long cleancache_failed_gets; -static unsigned long cleancache_puts; -static unsigned long cleancache_flushes; +/* + * Counters available via /sys/kernel/debug/frontswap (if debugfs is + * properly configured. These are for information only so are not protected + * against increment races. + */ +static u64 cleancache_succ_gets; +static u64 cleancache_failed_gets; +static u64 cleancache_puts; +static u64 cleancache_invalidates; /* * register operations for cleancache, returning previous thus allowing @@ -148,10 +153,11 @@ void __cleancache_put_page(struct page *page) EXPORT_SYMBOL(__cleancache_put_page); /* - * Flush any data from cleancache associated with the poolid and the + * Invalidate any data from cleancache associated with the poolid and the * page's inode and page index so that a subsequent "get" will fail. */ -void __cleancache_flush_page(struct address_space *mapping, struct page *page) +void __cleancache_invalidate_page(struct address_space *mapping, + struct page *page) { /* careful... page->mapping is NULL sometimes when this is called */ int pool_id = mapping->host->i_sb->cleancache_poolid; @@ -160,85 +166,57 @@ void __cleancache_flush_page(struct address_space *mapping, struct page *page) if (pool_id >= 0) { VM_BUG_ON(!PageLocked(page)); if (cleancache_get_key(mapping->host, &key) >= 0) { - (*cleancache_ops.flush_page)(pool_id, key, page->index); - cleancache_flushes++; + (*cleancache_ops.invalidate_page)(pool_id, + key, page->index); + cleancache_invalidates++; } } } -EXPORT_SYMBOL(__cleancache_flush_page); +EXPORT_SYMBOL(__cleancache_invalidate_page); /* - * Flush all data from cleancache associated with the poolid and the + * Invalidate all data from cleancache associated with the poolid and the * mappings's inode so that all subsequent gets to this poolid/inode * will fail. */ -void __cleancache_flush_inode(struct address_space *mapping) +void __cleancache_invalidate_inode(struct address_space *mapping) { int pool_id = mapping->host->i_sb->cleancache_poolid; struct cleancache_filekey key = { .u.key = { 0 } }; if (pool_id >= 0 && cleancache_get_key(mapping->host, &key) >= 0) - (*cleancache_ops.flush_inode)(pool_id, key); + (*cleancache_ops.invalidate_inode)(pool_id, key); } -EXPORT_SYMBOL(__cleancache_flush_inode); +EXPORT_SYMBOL(__cleancache_invalidate_inode); /* * Called by any cleancache-enabled filesystem at time of unmount; * note that pool_id is surrendered and may be reutrned by a subsequent * cleancache_init_fs or cleancache_init_shared_fs */ -void __cleancache_flush_fs(struct super_block *sb) +void __cleancache_invalidate_fs(struct super_block *sb) { if (sb->cleancache_poolid >= 0) { int old_poolid = sb->cleancache_poolid; sb->cleancache_poolid = -1; - (*cleancache_ops.flush_fs)(old_poolid); + (*cleancache_ops.invalidate_fs)(old_poolid); } } -EXPORT_SYMBOL(__cleancache_flush_fs); - -#ifdef CONFIG_SYSFS - -/* see Documentation/ABI/xxx/sysfs-kernel-mm-cleancache */ - -#define CLEANCACHE_SYSFS_RO(_name) \ - static ssize_t cleancache_##_name##_show(struct kobject *kobj, \ - struct kobj_attribute *attr, char *buf) \ - { \ - return sprintf(buf, "%lu\n", cleancache_##_name); \ - } \ - static struct kobj_attribute cleancache_##_name##_attr = { \ - .attr = { .name = __stringify(_name), .mode = 0444 }, \ - .show = cleancache_##_name##_show, \ - } - -CLEANCACHE_SYSFS_RO(succ_gets); -CLEANCACHE_SYSFS_RO(failed_gets); -CLEANCACHE_SYSFS_RO(puts); -CLEANCACHE_SYSFS_RO(flushes); - -static struct attribute *cleancache_attrs[] = { - &cleancache_succ_gets_attr.attr, - &cleancache_failed_gets_attr.attr, - &cleancache_puts_attr.attr, - &cleancache_flushes_attr.attr, - NULL, -}; - -static struct attribute_group cleancache_attr_group = { - .attrs = cleancache_attrs, - .name = "cleancache", -}; - -#endif /* CONFIG_SYSFS */ +EXPORT_SYMBOL(__cleancache_invalidate_fs); static int __init init_cleancache(void) { -#ifdef CONFIG_SYSFS - int err; - - err = sysfs_create_group(mm_kobj, &cleancache_attr_group); -#endif /* CONFIG_SYSFS */ +#ifdef CONFIG_DEBUG_FS + struct dentry *root = debugfs_create_dir("cleancache", NULL); + if (root == NULL) + return -ENXIO; + debugfs_create_u64("succ_gets", S_IRUGO, root, &cleancache_succ_gets); + debugfs_create_u64("failed_gets", S_IRUGO, + root, &cleancache_failed_gets); + debugfs_create_u64("puts", S_IRUGO, root, &cleancache_puts); + debugfs_create_u64("invalidates", S_IRUGO, + root, &cleancache_invalidates); +#endif return 0; } module_init(init_cleancache) diff --git a/mm/compaction.c b/mm/compaction.c index 71a58f6..74a8c82 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -35,7 +35,7 @@ struct compact_control { unsigned long migrate_pfn; /* isolate_migratepages search base */ bool sync; /* Synchronous migration */ - unsigned int order; /* order a direct compactor needs */ + int order; /* order a direct compactor needs */ int migratetype; /* MOVABLE, RECLAIMABLE etc */ struct zone *zone; }; @@ -313,12 +313,34 @@ static isolate_migrate_t isolate_migratepages(struct zone *zone, } else if (!locked) spin_lock_irq(&zone->lru_lock); + /* + * migrate_pfn does not necessarily start aligned to a + * pageblock. Ensure that pfn_valid is called when moving + * into a new MAX_ORDER_NR_PAGES range in case of large + * memory holes within the zone + */ + if ((low_pfn & (MAX_ORDER_NR_PAGES - 1)) == 0) { + if (!pfn_valid(low_pfn)) { + low_pfn += MAX_ORDER_NR_PAGES - 1; + continue; + } + } + if (!pfn_valid_within(low_pfn)) continue; nr_scanned++; - /* Get the page and skip if free */ + /* + * Get the page and ensure the page is within the same zone. + * See the comment in isolate_freepages about overlapping + * nodes. It is deliberate that the new zone lock is not taken + * as memory compaction should not move pages between nodes. + */ page = pfn_to_page(low_pfn); + if (page_zone(page) != zone) + continue; + + /* Skip if free */ if (PageBuddy(page)) continue; @@ -653,49 +675,71 @@ unsigned long try_to_compact_pages(struct zonelist *zonelist, /* Compact all zones within a node */ -static int compact_node(int nid) +static int __compact_pgdat(pg_data_t *pgdat, struct compact_control *cc) { int zoneid; - pg_data_t *pgdat; struct zone *zone; - if (nid < 0 || nid >= nr_node_ids || !node_online(nid)) - return -EINVAL; - pgdat = NODE_DATA(nid); - - /* Flush pending updates to the LRU lists */ - lru_add_drain_all(); - for (zoneid = 0; zoneid < MAX_NR_ZONES; zoneid++) { - struct compact_control cc = { - .nr_freepages = 0, - .nr_migratepages = 0, - .order = -1, - .sync = true, - }; zone = &pgdat->node_zones[zoneid]; if (!populated_zone(zone)) continue; - cc.zone = zone; - INIT_LIST_HEAD(&cc.freepages); - INIT_LIST_HEAD(&cc.migratepages); - - compact_zone(zone, &cc); + cc->nr_freepages = 0; + cc->nr_migratepages = 0; + cc->zone = zone; + INIT_LIST_HEAD(&cc->freepages); + INIT_LIST_HEAD(&cc->migratepages); + + if (cc->order == -1 || !compaction_deferred(zone, cc->order)) + compact_zone(zone, cc); + + if (cc->order > 0) { + int ok = zone_watermark_ok(zone, cc->order, + low_wmark_pages(zone), 0, 0); + if (ok && cc->order > zone->compact_order_failed) + zone->compact_order_failed = cc->order + 1; + /* Currently async compaction is never deferred. */ + else if (!ok && cc->sync) + defer_compaction(zone, cc->order); + } - VM_BUG_ON(!list_empty(&cc.freepages)); - VM_BUG_ON(!list_empty(&cc.migratepages)); + VM_BUG_ON(!list_empty(&cc->freepages)); + VM_BUG_ON(!list_empty(&cc->migratepages)); } return 0; } +int compact_pgdat(pg_data_t *pgdat, int order) +{ + struct compact_control cc = { + .order = order, + .sync = false, + }; + + return __compact_pgdat(pgdat, &cc); +} + +static int compact_node(int nid) +{ + struct compact_control cc = { + .order = -1, + .sync = true, + }; + + return __compact_pgdat(NODE_DATA(nid), &cc); +} + /* Compact all nodes in the system */ static int compact_nodes(void) { int nid; + /* Flush pending updates to the LRU lists */ + lru_add_drain_all(); + for_each_online_node(nid) compact_node(nid); @@ -728,7 +772,14 @@ ssize_t sysfs_compact_node(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) { - compact_node(dev->id); + int nid = dev->id; + + if (nid >= 0 && nid < nr_node_ids && node_online(nid)) { + /* Flush pending updates to the LRU lists */ + lru_add_drain_all(); + + compact_node(nid); + } return count; } diff --git a/mm/filemap.c b/mm/filemap.c index 97f49ed..79c4b2b 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -101,9 +101,8 @@ * ->inode->i_lock (zap_pte_range->set_page_dirty) * ->private_lock (zap_pte_range->__set_page_dirty_buffers) * - * (code doesn't rely on that order, so you could switch it around) - * ->tasklist_lock (memory_failure, collect_procs_ao) - * ->i_mmap_mutex + * ->i_mmap_mutex + * ->tasklist_lock (memory_failure, collect_procs_ao) */ /* @@ -123,7 +122,7 @@ void __delete_from_page_cache(struct page *page) if (PageUptodate(page) && PageMappedToDisk(page)) cleancache_put_page(page); else - cleancache_flush_page(mapping, page); + cleancache_invalidate_page(mapping, page); radix_tree_delete(&mapping->page_tree, page->index); page->mapping = NULL; @@ -500,10 +499,13 @@ struct page *__page_cache_alloc(gfp_t gfp) struct page *page; if (cpuset_do_page_mem_spread()) { - get_mems_allowed(); - n = cpuset_mem_spread_node(); - page = alloc_pages_exact_node(n, gfp, 0); - put_mems_allowed(); + unsigned int cpuset_mems_cookie; + do { + cpuset_mems_cookie = get_mems_allowed(); + n = cpuset_mem_spread_node(); + page = alloc_pages_exact_node(n, gfp, 0); + } while (!put_mems_allowed(cpuset_mems_cookie) && !page); + return page; } return alloc_pages(gfp, 0); @@ -811,20 +813,19 @@ EXPORT_SYMBOL(find_or_create_page); unsigned find_get_pages(struct address_space *mapping, pgoff_t start, unsigned int nr_pages, struct page **pages) { - unsigned int i; - unsigned int ret; - unsigned int nr_found, nr_skip; + struct radix_tree_iter iter; + void **slot; + unsigned ret = 0; + + if (unlikely(!nr_pages)) + return 0; rcu_read_lock(); restart: - nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, NULL, start, nr_pages); - ret = 0; - nr_skip = 0; - for (i = 0; i < nr_found; i++) { + radix_tree_for_each_slot(slot, &mapping->page_tree, &iter, start) { struct page *page; repeat: - page = radix_tree_deref_slot((void **)pages[i]); + page = radix_tree_deref_slot(slot); if (unlikely(!page)) continue; @@ -835,7 +836,7 @@ repeat: * when entry at index 0 moves out of or back * to root: none yet gotten, safe to restart. */ - WARN_ON(start | i); + WARN_ON(iter.index); goto restart; } /* @@ -843,7 +844,6 @@ repeat: * here as an exceptional entry: so skip over it - * we only reach this from invalidate_mapping_pages(). */ - nr_skip++; continue; } @@ -851,21 +851,16 @@ repeat: goto repeat; /* Has the page moved? */ - if (unlikely(page != *((void **)pages[i]))) { + if (unlikely(page != *slot)) { page_cache_release(page); goto repeat; } pages[ret] = page; - ret++; + if (++ret == nr_pages) + break; } - /* - * If all entries were removed before we could secure them, - * try again, because callers stop trying once 0 is returned. - */ - if (unlikely(!ret && nr_found > nr_skip)) - goto restart; rcu_read_unlock(); return ret; } @@ -885,21 +880,22 @@ repeat: unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, unsigned int nr_pages, struct page **pages) { - unsigned int i; - unsigned int ret; - unsigned int nr_found; + struct radix_tree_iter iter; + void **slot; + unsigned int ret = 0; + + if (unlikely(!nr_pages)) + return 0; rcu_read_lock(); restart: - nr_found = radix_tree_gang_lookup_slot(&mapping->page_tree, - (void ***)pages, NULL, index, nr_pages); - ret = 0; - for (i = 0; i < nr_found; i++) { + radix_tree_for_each_contig(slot, &mapping->page_tree, &iter, index) { struct page *page; repeat: - page = radix_tree_deref_slot((void **)pages[i]); + page = radix_tree_deref_slot(slot); + /* The hole, there no reason to continue */ if (unlikely(!page)) - continue; + break; if (radix_tree_exception(page)) { if (radix_tree_deref_retry(page)) { @@ -922,7 +918,7 @@ repeat: goto repeat; /* Has the page moved? */ - if (unlikely(page != *((void **)pages[i]))) { + if (unlikely(page != *slot)) { page_cache_release(page); goto repeat; } @@ -932,14 +928,14 @@ repeat: * otherwise we can get both false positives and false * negatives, which is just confusing to the caller. */ - if (page->mapping == NULL || page->index != index) { + if (page->mapping == NULL || page->index != iter.index) { page_cache_release(page); break; } pages[ret] = page; - ret++; - index++; + if (++ret == nr_pages) + break; } rcu_read_unlock(); return ret; @@ -960,19 +956,20 @@ EXPORT_SYMBOL(find_get_pages_contig); unsigned find_get_pages_tag(struct address_space *mapping, pgoff_t *index, int tag, unsigned int nr_pages, struct page **pages) { - unsigned int i; - unsigned int ret; - unsigned int nr_found; + struct radix_tree_iter iter; + void **slot; + unsigned ret = 0; + + if (unlikely(!nr_pages)) + return 0; rcu_read_lock(); restart: - nr_found = radix_tree_gang_lookup_tag_slot(&mapping->page_tree, - (void ***)pages, *index, nr_pages, tag); - ret = 0; - for (i = 0; i < nr_found; i++) { + radix_tree_for_each_tagged(slot, &mapping->page_tree, + &iter, *index, tag) { struct page *page; repeat: - page = radix_tree_deref_slot((void **)pages[i]); + page = radix_tree_deref_slot(slot); if (unlikely(!page)) continue; @@ -996,21 +993,16 @@ repeat: goto repeat; /* Has the page moved? */ - if (unlikely(page != *((void **)pages[i]))) { + if (unlikely(page != *slot)) { page_cache_release(page); goto repeat; } pages[ret] = page; - ret++; + if (++ret == nr_pages) + break; } - /* - * If all entries were removed before we could secure them, - * try again, because callers stop trying once 0 is returned. - */ - if (unlikely(!ret && nr_found)) - goto restart; rcu_read_unlock(); if (ret) @@ -1318,10 +1310,10 @@ int file_read_actor(read_descriptor_t *desc, struct page *page, * taking the kmap. */ if (!fault_in_pages_writeable(desc->arg.buf, size)) { - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); left = __copy_to_user_inatomic(desc->arg.buf, kaddr + offset, size); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); if (left == 0) goto success; } @@ -1400,15 +1392,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, unsigned long seg = 0; size_t count; loff_t *ppos = &iocb->ki_pos; - struct blk_plug plug; count = 0; retval = generic_segment_checks(iov, &nr_segs, &count, VERIFY_WRITE); if (retval) return retval; - blk_start_plug(&plug); - /* coalesce the iovecs and go direct-to-BIO for O_DIRECT */ if (filp->f_flags & O_DIRECT) { loff_t size; @@ -1424,8 +1413,12 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, retval = filemap_write_and_wait_range(mapping, pos, pos + iov_length(iov, nr_segs) - 1); if (!retval) { + struct blk_plug plug; + + blk_start_plug(&plug); retval = mapping->a_ops->direct_IO(READ, iocb, iov, pos, nr_segs); + blk_finish_plug(&plug); } if (retval > 0) { *ppos = pos + retval; @@ -1481,7 +1474,6 @@ generic_file_aio_read(struct kiocb *iocb, const struct iovec *iov, break; } out: - blk_finish_plug(&plug); return retval; } EXPORT_SYMBOL(generic_file_aio_read); @@ -2045,7 +2037,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, size_t copied; BUG_ON(!in_atomic()); - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); if (likely(i->nr_segs == 1)) { int left; char __user *buf = i->iov->iov_base + i->iov_offset; @@ -2055,7 +2047,7 @@ size_t iov_iter_copy_from_user_atomic(struct page *page, copied = __iovec_copy_from_user_inatomic(kaddr + offset, i->iov, i->iov_offset, bytes); } - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); return copied; } @@ -2341,7 +2333,9 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, struct page *page; gfp_t gfp_notmask = 0; - gfp_mask = mapping_gfp_mask(mapping) | __GFP_WRITE; + gfp_mask = mapping_gfp_mask(mapping); + if (mapping_cap_account_dirty(mapping)) + gfp_mask |= __GFP_WRITE; if (flags & AOP_FLAG_NOFS) gfp_notmask = __GFP_FS; repeat: diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index f91b2f6..a4eb311 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -263,7 +263,12 @@ found: xip_pfn); if (err == -ENOMEM) return VM_FAULT_OOM; - BUG_ON(err); + /* + * 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; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index b3ffc21..f0e5306 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -671,6 +671,7 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, set_pmd_at(mm, haddr, pmd, entry); prepare_pmd_huge_pte(pgtable, mm); add_mm_counter(mm, MM_ANONPAGES, HPAGE_PMD_NR); + mm->nr_ptes++; spin_unlock(&mm->page_table_lock); } @@ -789,6 +790,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, pmd = pmd_mkold(pmd_wrprotect(pmd)); set_pmd_at(dst_mm, addr, dst_pmd, pmd); prepare_pmd_huge_pte(pgtable, dst_mm); + dst_mm->nr_ptes++; ret = 0; out_unlock: @@ -887,7 +889,6 @@ static int do_huge_pmd_wp_page_fallback(struct mm_struct *mm, } kfree(pages); - mm->nr_ptes++; smp_wmb(); /* make pte visible before pmd */ pmd_populate(mm, pmd, pgtable); page_remove_rmap(page); @@ -1030,31 +1031,23 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, { int ret = 0; - spin_lock(&tlb->mm->page_table_lock); - if (likely(pmd_trans_huge(*pmd))) { - if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&tlb->mm->page_table_lock); - wait_split_huge_page(vma->anon_vma, - pmd); - } else { - struct page *page; - pgtable_t pgtable; - pgtable = get_pmd_huge_pte(tlb->mm); - page = pmd_page(*pmd); - pmd_clear(pmd); - tlb_remove_pmd_tlb_entry(tlb, pmd, addr); - page_remove_rmap(page); - VM_BUG_ON(page_mapcount(page) < 0); - add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); - VM_BUG_ON(!PageHead(page)); - spin_unlock(&tlb->mm->page_table_lock); - tlb_remove_page(tlb, page); - pte_free(tlb->mm, pgtable); - ret = 1; - } - } else + if (__pmd_trans_huge_lock(pmd, vma) == 1) { + struct page *page; + pgtable_t pgtable; + pgtable = get_pmd_huge_pte(tlb->mm); + page = pmd_page(*pmd); + pmd_clear(pmd); + tlb_remove_pmd_tlb_entry(tlb, pmd, addr); + page_remove_rmap(page); + VM_BUG_ON(page_mapcount(page) < 0); + add_mm_counter(tlb->mm, MM_ANONPAGES, -HPAGE_PMD_NR); + VM_BUG_ON(!PageHead(page)); + tlb->mm->nr_ptes--; spin_unlock(&tlb->mm->page_table_lock); - + tlb_remove_page(tlb, page); + pte_free(tlb->mm, pgtable); + ret = 1; + } return ret; } @@ -1064,21 +1057,15 @@ int mincore_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, { int ret = 0; - spin_lock(&vma->vm_mm->page_table_lock); - if (likely(pmd_trans_huge(*pmd))) { - ret = !pmd_trans_splitting(*pmd); - spin_unlock(&vma->vm_mm->page_table_lock); - if (unlikely(!ret)) - wait_split_huge_page(vma->anon_vma, pmd); - else { - /* - * All logical pages in the range are present - * if backed by a huge page. - */ - memset(vec, 1, (end - addr) >> PAGE_SHIFT); - } - } else + if (__pmd_trans_huge_lock(pmd, vma) == 1) { + /* + * All logical pages in the range are present + * if backed by a huge page. + */ spin_unlock(&vma->vm_mm->page_table_lock); + memset(vec, 1, (end - addr) >> PAGE_SHIFT); + ret = 1; + } return ret; } @@ -1108,20 +1095,11 @@ int move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, goto out; } - spin_lock(&mm->page_table_lock); - if (likely(pmd_trans_huge(*old_pmd))) { - if (pmd_trans_splitting(*old_pmd)) { - spin_unlock(&mm->page_table_lock); - wait_split_huge_page(vma->anon_vma, old_pmd); - ret = -1; - } else { - pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); - VM_BUG_ON(!pmd_none(*new_pmd)); - set_pmd_at(mm, new_addr, new_pmd, pmd); - spin_unlock(&mm->page_table_lock); - ret = 1; - } - } else { + ret = __pmd_trans_huge_lock(old_pmd, vma); + if (ret == 1) { + pmd = pmdp_get_and_clear(mm, old_addr, old_pmd); + VM_BUG_ON(!pmd_none(*new_pmd)); + set_pmd_at(mm, new_addr, new_pmd, pmd); spin_unlock(&mm->page_table_lock); } out: @@ -1134,24 +1112,41 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, struct mm_struct *mm = vma->vm_mm; int ret = 0; - spin_lock(&mm->page_table_lock); + if (__pmd_trans_huge_lock(pmd, vma) == 1) { + pmd_t entry; + entry = pmdp_get_and_clear(mm, addr, pmd); + entry = pmd_modify(entry, newprot); + set_pmd_at(mm, addr, pmd, entry); + spin_unlock(&vma->vm_mm->page_table_lock); + ret = 1; + } + + return ret; +} + +/* + * Returns 1 if a given pmd maps a stable (not under splitting) thp. + * Returns -1 if it maps a thp under splitting. Returns 0 otherwise. + * + * Note that if it returns 1, this routine returns without unlocking page + * table locks. So callers must unlock them. + */ +int __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) +{ + spin_lock(&vma->vm_mm->page_table_lock); if (likely(pmd_trans_huge(*pmd))) { if (unlikely(pmd_trans_splitting(*pmd))) { - spin_unlock(&mm->page_table_lock); + spin_unlock(&vma->vm_mm->page_table_lock); wait_split_huge_page(vma->anon_vma, pmd); + return -1; } else { - pmd_t entry; - - entry = pmdp_get_and_clear(mm, addr, pmd); - entry = pmd_modify(entry, newprot); - set_pmd_at(mm, addr, pmd, entry); - spin_unlock(&vma->vm_mm->page_table_lock); - ret = 1; + /* Thp mapped by 'pmd' is stable, so we can + * handle it as it is. */ + return 1; } - } else - spin_unlock(&vma->vm_mm->page_table_lock); - - return ret; + } + spin_unlock(&vma->vm_mm->page_table_lock); + return 0; } pmd_t *page_check_address_pmd(struct page *page, @@ -1375,7 +1370,6 @@ static int __split_huge_page_map(struct page *page, pte_unmap(pte); } - mm->nr_ptes++; smp_wmb(); /* make pte visible before pmd */ /* * Up to this point the pmd is present and huge and @@ -1988,7 +1982,6 @@ static void collapse_huge_page(struct mm_struct *mm, set_pmd_at(mm, address, pmd, _pmd); update_mmu_cache(vma, address, _pmd); prepare_pmd_huge_pte(pgtable, mm); - mm->nr_ptes--; spin_unlock(&mm->page_table_lock); #ifndef CONFIG_NUMA @@ -2083,7 +2076,7 @@ static void collect_mm_slot(struct mm_slot *mm_slot) { struct mm_struct *mm = mm_slot->mm; - VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock)); + VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); if (khugepaged_test_exit(mm)) { /* free mm_slot */ @@ -2113,7 +2106,7 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, int progress = 0; VM_BUG_ON(!pages); - VM_BUG_ON(!spin_is_locked(&khugepaged_mm_lock)); + VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&khugepaged_mm_lock)); if (khugepaged_scan.mm_slot) mm_slot = khugepaged_scan.mm_slot; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 5f34bd8..b8ce6f4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -53,6 +53,84 @@ static unsigned long __initdata default_hstate_size; */ static DEFINE_SPINLOCK(hugetlb_lock); +static inline void unlock_or_release_subpool(struct hugepage_subpool *spool) +{ + bool free = (spool->count == 0) && (spool->used_hpages == 0); + + spin_unlock(&spool->lock); + + /* If no pages are used, and no other handles to the subpool + * remain, free the subpool the subpool remain */ + if (free) + kfree(spool); +} + +struct hugepage_subpool *hugepage_new_subpool(long nr_blocks) +{ + struct hugepage_subpool *spool; + + spool = kmalloc(sizeof(*spool), GFP_KERNEL); + if (!spool) + return NULL; + + spin_lock_init(&spool->lock); + spool->count = 1; + spool->max_hpages = nr_blocks; + spool->used_hpages = 0; + + return spool; +} + +void hugepage_put_subpool(struct hugepage_subpool *spool) +{ + spin_lock(&spool->lock); + BUG_ON(!spool->count); + spool->count--; + unlock_or_release_subpool(spool); +} + +static int hugepage_subpool_get_pages(struct hugepage_subpool *spool, + long delta) +{ + int ret = 0; + + if (!spool) + return 0; + + spin_lock(&spool->lock); + if ((spool->used_hpages + delta) <= spool->max_hpages) { + spool->used_hpages += delta; + } else { + ret = -ENOMEM; + } + spin_unlock(&spool->lock); + + return ret; +} + +static void hugepage_subpool_put_pages(struct hugepage_subpool *spool, + long delta) +{ + if (!spool) + return; + + spin_lock(&spool->lock); + spool->used_hpages -= delta; + /* If hugetlbfs_put_super couldn't free spool due to + * an outstanding quota reference, free it now. */ + unlock_or_release_subpool(spool); +} + +static inline struct hugepage_subpool *subpool_inode(struct inode *inode) +{ + return HUGETLBFS_SB(inode->i_sb)->spool; +} + +static inline struct hugepage_subpool *subpool_vma(struct vm_area_struct *vma) +{ + return subpool_inode(vma->vm_file->f_dentry->d_inode); +} + /* * Region tracking -- allows tracking of reservations and instantiated pages * across the pages in a mapping. @@ -454,14 +532,16 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, struct vm_area_struct *vma, unsigned long address, int avoid_reserve) { - struct page *page = NULL; + struct page *page; struct mempolicy *mpol; nodemask_t *nodemask; struct zonelist *zonelist; struct zone *zone; struct zoneref *z; + unsigned int cpuset_mems_cookie; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); zonelist = huge_zonelist(vma, address, htlb_alloc_mask, &mpol, &nodemask); /* @@ -488,10 +568,15 @@ static struct page *dequeue_huge_page_vma(struct hstate *h, } } } -err: + mpol_cond_put(mpol); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; return page; + +err: + mpol_cond_put(mpol); + return NULL; } static void update_and_free_page(struct hstate *h, struct page *page) @@ -533,9 +618,9 @@ static void free_huge_page(struct page *page) */ struct hstate *h = page_hstate(page); int nid = page_to_nid(page); - struct address_space *mapping; + struct hugepage_subpool *spool = + (struct hugepage_subpool *)page_private(page); - mapping = (struct address_space *) page_private(page); set_page_private(page, 0); page->mapping = NULL; BUG_ON(page_count(page)); @@ -551,8 +636,7 @@ static void free_huge_page(struct page *page) enqueue_huge_page(h, page); } spin_unlock(&hugetlb_lock); - if (mapping) - hugetlb_put_quota(mapping, 1); + hugepage_subpool_put_pages(spool, 1); } static void prep_new_huge_page(struct hstate *h, struct page *page, int nid) @@ -852,6 +936,7 @@ static int gather_surplus_pages(struct hstate *h, int delta) struct page *page, *tmp; int ret, i; int needed, allocated; + bool alloc_ok = true; needed = (h->resv_huge_pages + delta) - h->free_huge_pages; if (needed <= 0) { @@ -867,17 +952,13 @@ retry: spin_unlock(&hugetlb_lock); for (i = 0; i < needed; i++) { page = alloc_buddy_huge_page(h, NUMA_NO_NODE); - if (!page) - /* - * We were not able to allocate enough pages to - * satisfy the entire reservation so we free what - * we've allocated so far. - */ - goto free; - + if (!page) { + alloc_ok = false; + break; + } list_add(&page->lru, &surplus_list); } - allocated += needed; + allocated += i; /* * After retaking hugetlb_lock, we need to recalculate 'needed' @@ -886,9 +967,16 @@ retry: spin_lock(&hugetlb_lock); needed = (h->resv_huge_pages + delta) - (h->free_huge_pages + allocated); - if (needed > 0) - goto retry; - + if (needed > 0) { + if (alloc_ok) + goto retry; + /* + * We were not able to allocate enough pages to + * satisfy the entire reservation so we free what + * we've allocated so far. + */ + goto free; + } /* * The surplus_list now contains _at_least_ the number of extra pages * needed to accommodate the reservation. Add the appropriate number @@ -914,10 +1002,10 @@ retry: VM_BUG_ON(page_count(page)); enqueue_huge_page(h, page); } +free: spin_unlock(&hugetlb_lock); /* Free unnecessary surplus pages to the buddy allocator */ -free: if (!list_empty(&surplus_list)) { list_for_each_entry_safe(page, tmp, &surplus_list, lru) { list_del(&page->lru); @@ -966,11 +1054,12 @@ static void return_unused_surplus_pages(struct hstate *h, /* * Determine if the huge page at addr within the vma has an associated * reservation. Where it does not we will need to logically increase - * reservation and actually increase quota before an allocation can occur. - * Where any new reservation would be required the reservation change is - * prepared, but not committed. Once the page has been quota'd allocated - * an instantiated the change should be committed via vma_commit_reservation. - * No action is required on failure. + * reservation and actually increase subpool usage before an allocation + * can occur. Where any new reservation would be required the + * reservation change is prepared, but not committed. Once the page + * has been allocated from the subpool and instantiated the change should + * be committed via vma_commit_reservation. No action is required on + * failure. */ static long vma_needs_reservation(struct hstate *h, struct vm_area_struct *vma, unsigned long addr) @@ -1019,24 +1108,24 @@ static void vma_commit_reservation(struct hstate *h, static struct page *alloc_huge_page(struct vm_area_struct *vma, unsigned long addr, int avoid_reserve) { + struct hugepage_subpool *spool = subpool_vma(vma); struct hstate *h = hstate_vma(vma); struct page *page; - struct address_space *mapping = vma->vm_file->f_mapping; - struct inode *inode = mapping->host; long chg; /* - * Processes that did not create the mapping will have no reserves and - * will not have accounted against quota. Check that the quota can be - * made before satisfying the allocation - * MAP_NORESERVE mappings may also need pages and quota allocated - * if no reserve mapping overlaps. + * Processes that did not create the mapping will have no + * reserves and will not have accounted against subpool + * limit. Check that the subpool limit can be made before + * satisfying the allocation MAP_NORESERVE mappings may also + * need pages and subpool limit allocated allocated if no reserve + * mapping overlaps. */ chg = vma_needs_reservation(h, vma, addr); if (chg < 0) return ERR_PTR(-VM_FAULT_OOM); if (chg) - if (hugetlb_get_quota(inode->i_mapping, chg)) + if (hugepage_subpool_get_pages(spool, chg)) return ERR_PTR(-VM_FAULT_SIGBUS); spin_lock(&hugetlb_lock); @@ -1046,12 +1135,12 @@ static struct page *alloc_huge_page(struct vm_area_struct *vma, if (!page) { page = alloc_buddy_huge_page(h, NUMA_NO_NODE); if (!page) { - hugetlb_put_quota(inode->i_mapping, chg); + hugepage_subpool_put_pages(spool, chg); return ERR_PTR(-VM_FAULT_SIGBUS); } } - set_page_private(page, (unsigned long) mapping); + set_page_private(page, (unsigned long)spool); vma_commit_reservation(h, vma, addr); @@ -2072,6 +2161,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) { struct hstate *h = hstate_vma(vma); struct resv_map *reservations = vma_resv_map(vma); + struct hugepage_subpool *spool = subpool_vma(vma); unsigned long reserve; unsigned long start; unsigned long end; @@ -2087,7 +2177,7 @@ static void hugetlb_vm_op_close(struct vm_area_struct *vma) if (reserve) { hugetlb_acct_memory(h, -reserve); - hugetlb_put_quota(vma->vm_file->f_mapping, reserve); + hugepage_subpool_put_pages(spool, reserve); } } } @@ -2241,16 +2331,23 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, if (huge_pmd_unshare(mm, &address, ptep)) continue; + pte = huge_ptep_get(ptep); + if (huge_pte_none(pte)) + continue; + + /* + * HWPoisoned hugepage is already unmapped and dropped reference + */ + if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) + continue; + + page = pte_page(pte); /* * If a reference page is supplied, it is because a specific * page is being unmapped, not a range. Ensure the page we * are about to unmap is the actual page of interest. */ if (ref_page) { - pte = huge_ptep_get(ptep); - if (huge_pte_none(pte)) - continue; - page = pte_page(pte); if (page != ref_page) continue; @@ -2263,22 +2360,16 @@ void __unmap_hugepage_range(struct vm_area_struct *vma, unsigned long start, } pte = huge_ptep_get_and_clear(mm, address, ptep); - if (huge_pte_none(pte)) - continue; - - /* - * HWPoisoned hugepage is already unmapped and dropped reference - */ - if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) - continue; - - page = pte_page(pte); if (pte_dirty(pte)) set_page_dirty(page); list_add(&page->lru, &page_list); + + /* Bail out after unmapping reference page if supplied */ + if (ref_page) + break; } - spin_unlock(&mm->page_table_lock); flush_tlb_range(vma, start, end); + spin_unlock(&mm->page_table_lock); mmu_notifier_invalidate_range_end(mm, start, end); list_for_each_entry_safe(page, tmp, &page_list, lru) { page_remove_rmap(page); @@ -2316,7 +2407,7 @@ static int unmap_ref_private(struct mm_struct *mm, struct vm_area_struct *vma, */ address = address & huge_page_mask(h); pgoff = vma_hugecache_offset(h, vma, address); - mapping = (struct address_space *)page_private(page); + mapping = vma->vm_file->f_dentry->d_inode->i_mapping; /* * Take the mapping lock for the duration of the table walk. As @@ -2869,11 +2960,12 @@ int hugetlb_reserve_pages(struct inode *inode, { long ret, chg; struct hstate *h = hstate_inode(inode); + struct hugepage_subpool *spool = subpool_inode(inode); /* * Only apply hugepage reservation if asked. At fault time, an * attempt will be made for VM_NORESERVE to allocate a page - * and filesystem quota without using reserves + * without using reserves */ if (vm_flags & VM_NORESERVE) return 0; @@ -2900,17 +2992,17 @@ int hugetlb_reserve_pages(struct inode *inode, if (chg < 0) return chg; - /* There must be enough filesystem quota for the mapping */ - if (hugetlb_get_quota(inode->i_mapping, chg)) + /* There must be enough pages in the subpool for the mapping */ + if (hugepage_subpool_get_pages(spool, chg)) return -ENOSPC; /* * Check enough hugepages are available for the reservation. - * Hand back the quota if there are not + * Hand the pages back to the subpool if there are not */ ret = hugetlb_acct_memory(h, chg); if (ret < 0) { - hugetlb_put_quota(inode->i_mapping, chg); + hugepage_subpool_put_pages(spool, chg); return ret; } @@ -2934,12 +3026,13 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) { struct hstate *h = hstate_inode(inode); long chg = region_truncate(&inode->i_mapping->private_list, offset); + struct hugepage_subpool *spool = subpool_inode(inode); spin_lock(&inode->i_lock); inode->i_blocks -= (blocks_per_huge_page(h) * freed); spin_unlock(&inode->i_lock); - hugetlb_put_quota(inode->i_mapping, (chg - freed)); + hugepage_subpool_put_pages(spool, (chg - freed)); hugetlb_acct_memory(h, -(chg - freed)); } diff --git a/mm/hwpoison-inject.c b/mm/hwpoison-inject.c index c7fc7fd..cc448bb 100644 --- a/mm/hwpoison-inject.c +++ b/mm/hwpoison-inject.c @@ -45,7 +45,7 @@ static int hwpoison_inject(void *data, u64 val) * do a racy check with elevated page count, to make sure PG_hwpoison * will only be set for the targeted owner (or on a free page). * We temporarily take page lock for try_get_mem_cgroup_from_page(). - * __memory_failure() will redo the check reliably inside page lock. + * memory_failure() will redo the check reliably inside page lock. */ lock_page(hpage); err = hwpoison_filter(hpage); @@ -55,7 +55,7 @@ static int hwpoison_inject(void *data, u64 val) inject: printk(KERN_INFO "Injecting memory failure at pfn %lx\n", pfn); - return __memory_failure(pfn, 18, MF_COUNT_INCREASED); + return memory_failure(pfn, 18, MF_COUNT_INCREASED); } static int hwpoison_unpoison(void *data, u64 val) @@ -28,7 +28,6 @@ #include <linux/kthread.h> #include <linux/wait.h> #include <linux/slab.h> -#include <linux/memcontrol.h> #include <linux/rbtree.h> #include <linux/memory.h> #include <linux/mmu_notifier.h> @@ -375,6 +374,20 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) return (ret & VM_FAULT_OOM) ? -ENOMEM : 0; } +static struct vm_area_struct *find_mergeable_vma(struct mm_struct *mm, + unsigned long addr) +{ + struct vm_area_struct *vma; + if (ksm_test_exit(mm)) + return NULL; + vma = find_vma(mm, addr); + if (!vma || vma->vm_start > addr) + return NULL; + if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) + return NULL; + return vma; +} + static void break_cow(struct rmap_item *rmap_item) { struct mm_struct *mm = rmap_item->mm; @@ -388,15 +401,9 @@ static void break_cow(struct rmap_item *rmap_item) put_anon_vma(rmap_item->anon_vma); down_read(&mm->mmap_sem); - if (ksm_test_exit(mm)) - goto out; - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - goto out; - if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) - goto out; - break_ksm(vma, addr); -out: + vma = find_mergeable_vma(mm, addr); + if (vma) + break_ksm(vma, addr); up_read(&mm->mmap_sem); } @@ -422,12 +429,8 @@ static struct page *get_mergeable_page(struct rmap_item *rmap_item) struct page *page; down_read(&mm->mmap_sem); - if (ksm_test_exit(mm)) - goto out; - vma = find_vma(mm, addr); - if (!vma || vma->vm_start > addr) - goto out; - if (!(vma->vm_flags & VM_MERGEABLE) || !vma->anon_vma) + vma = find_mergeable_vma(mm, addr); + if (!vma) goto out; page = follow_page(vma, addr, FOLL_GET); @@ -673,9 +676,9 @@ error: static u32 calc_checksum(struct page *page) { u32 checksum; - void *addr = kmap_atomic(page, KM_USER0); + void *addr = kmap_atomic(page); checksum = jhash2(addr, PAGE_SIZE / 4, 17); - kunmap_atomic(addr, KM_USER0); + kunmap_atomic(addr); return checksum; } @@ -684,11 +687,11 @@ static int memcmp_pages(struct page *page1, struct page *page2) char *addr1, *addr2; int ret; - addr1 = kmap_atomic(page1, KM_USER0); - addr2 = kmap_atomic(page2, KM_USER1); + addr1 = kmap_atomic(page1); + addr2 = kmap_atomic(page2); ret = memcmp(addr1, addr2, PAGE_SIZE); - kunmap_atomic(addr2, KM_USER1); - kunmap_atomic(addr1, KM_USER0); + kunmap_atomic(addr2); + kunmap_atomic(addr1); return ret; } @@ -1572,16 +1575,6 @@ struct page *ksm_does_need_to_copy(struct page *page, new_page = alloc_page_vma(GFP_HIGHUSER_MOVABLE, vma, address); if (new_page) { - /* - * The memcg-specific accounting when moving - * pages around the LRU lists relies on the - * page's owner (memcg) to be valid. Usually, - * pages are assigned to a new owner before - * being put on the LRU list, but since this - * is not the case here, the stale owner from - * a previous allocation cycle must be reset. - */ - mem_cgroup_reset_owner(new_page); copy_user_highpage(new_page, page, address, vma); SetPageDirty(new_page); diff --git a/mm/madvise.c b/mm/madvise.c index 74bf193..1ccbba5 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -65,6 +65,12 @@ static long madvise_behavior(struct vm_area_struct * vma, } new_flags &= ~VM_DONTCOPY; break; + case MADV_DONTDUMP: + new_flags |= VM_NODUMP; + break; + case MADV_DODUMP: + new_flags &= ~VM_NODUMP; + break; case MADV_MERGEABLE: case MADV_UNMERGEABLE: error = ksm_madvise(vma, start, end, behavior, &new_flags); @@ -251,7 +257,7 @@ static int madvise_hwpoison(int bhv, unsigned long start, unsigned long end) printk(KERN_INFO "Injecting memory failure for page %lx at %lx\n", page_to_pfn(p), start); /* Ignore return value for now */ - __memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED); + memory_failure(page_to_pfn(p), 0, MF_COUNT_INCREASED); } return ret; } @@ -293,6 +299,8 @@ madvise_behavior_valid(int behavior) case MADV_HUGEPAGE: case MADV_NOHUGEPAGE: #endif + case MADV_DONTDUMP: + case MADV_DODUMP: return 1; default: diff --git a/mm/memblock.c b/mm/memblock.c index 77b5f22..99f2855 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -99,9 +99,6 @@ phys_addr_t __init_memblock memblock_find_in_range_node(phys_addr_t start, phys_addr_t this_start, this_end, cand; u64 i; - /* align @size to avoid excessive fragmentation on reserved array */ - size = round_up(size, align); - /* pump up @end */ if (end == MEMBLOCK_ALLOC_ACCESSIBLE) end = memblock.current_limit; @@ -731,6 +728,9 @@ static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, { phys_addr_t found; + /* align @size to avoid excessive fragmentation on reserved array */ + size = round_up(size, align); + found = memblock_find_in_range_node(0, max_addr, size, align, nid); if (found && !memblock_reserve(found, size)) return found; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 556859f..7d698df 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -89,7 +89,6 @@ enum mem_cgroup_stat_index { MEM_CGROUP_STAT_FILE_MAPPED, /* # of pages charged as file rss */ MEM_CGROUP_STAT_SWAPOUT, /* # of pages, swapped out */ MEM_CGROUP_STAT_DATA, /* end of data requires synchronization */ - MEM_CGROUP_ON_MOVE, /* someone is moving account between groups */ MEM_CGROUP_STAT_NSTATS, }; @@ -135,7 +134,7 @@ struct mem_cgroup_reclaim_iter { */ struct mem_cgroup_per_zone { struct lruvec lruvec; - unsigned long count[NR_LRU_LISTS]; + unsigned long lru_size[NR_LRU_LISTS]; struct mem_cgroup_reclaim_iter reclaim_iter[DEF_PRIORITY + 1]; @@ -144,11 +143,9 @@ struct mem_cgroup_per_zone { unsigned long long usage_in_excess;/* Set to the value by which */ /* the soft limit is exceeded*/ bool on_tree; - struct mem_cgroup *mem; /* Back pointer, we cannot */ + struct mem_cgroup *memcg; /* Back pointer, we cannot */ /* use container_of */ }; -/* Macro for accessing counter */ -#define MEM_CGROUP_ZSTAT(mz, idx) ((mz)->count[(idx)]) struct mem_cgroup_per_node { struct mem_cgroup_per_zone zoneinfo[MAX_NR_ZONES]; @@ -230,10 +227,30 @@ struct mem_cgroup { * the counter to account for memory usage */ struct res_counter res; - /* - * the counter to account for mem+swap usage. - */ - struct res_counter memsw; + + union { + /* + * the counter to account for mem+swap usage. + */ + struct res_counter memsw; + + /* + * rcu_freeing is used only when freeing struct mem_cgroup, + * so put it into a union to avoid wasting more memory. + * It must be disjoint from the css field. It could be + * in a union with the res field, but res plays a much + * larger part in mem_cgroup life than memsw, and might + * be of interest, even at time of free, when debugging. + * So share rcu_head with the less interesting memsw. + */ + struct rcu_head rcu_freeing; + /* + * But when using vfree(), that cannot be done at + * interrupt time, so we must then queue the work. + */ + struct work_struct work_freeing; + }; + /* * Per cgroup active and inactive list, similar to the * per zone LRU lists. @@ -280,6 +297,12 @@ struct mem_cgroup { */ unsigned long move_charge_at_immigrate; /* + * set > 0 if pages under this cgroup are moving to other cgroup. + */ + atomic_t moving_account; + /* taken only while moving_account > 0 */ + spinlock_t move_lock; + /* * percpu counter. */ struct mem_cgroup_stat_cpu *stat; @@ -592,9 +615,9 @@ retry: * we will to add it back at the end of reclaim to its correct * position in the tree. */ - __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); - if (!res_counter_soft_limit_excess(&mz->mem->res) || - !css_tryget(&mz->mem->css)) + __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + if (!res_counter_soft_limit_excess(&mz->memcg->res) || + !css_tryget(&mz->memcg->css)) goto retry; done: return mz; @@ -672,15 +695,19 @@ static unsigned long mem_cgroup_read_events(struct mem_cgroup *memcg, } static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, - bool file, int nr_pages) + bool anon, int nr_pages) { preempt_disable(); - if (file) - __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], + /* + * Here, RSS means 'mapped anon' and anon's SwapCache. Shmem/tmpfs is + * counted as CACHE even if it's on ANON LRU. + */ + if (anon) + __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS], nr_pages); else - __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_RSS], + __this_cpu_add(memcg->stat->count[MEM_CGROUP_STAT_CACHE], nr_pages); /* pagein of a big page is an event. So, ignore page size */ @@ -701,14 +728,14 @@ mem_cgroup_zone_nr_lru_pages(struct mem_cgroup *memcg, int nid, int zid, unsigned int lru_mask) { struct mem_cgroup_per_zone *mz; - enum lru_list l; + enum lru_list lru; unsigned long ret = 0; mz = mem_cgroup_zoneinfo(memcg, nid, zid); - for_each_lru(l) { - if (BIT(l) & lru_mask) - ret += MEM_CGROUP_ZSTAT(mz, l); + for_each_lru(lru) { + if (BIT(lru) & lru_mask) + ret += mz->lru_size[lru]; } return ret; } @@ -776,7 +803,8 @@ static void memcg_check_events(struct mem_cgroup *memcg, struct page *page) /* threshold event is triggered in finer grain than soft limit */ if (unlikely(mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_THRESH))) { - bool do_softlimit, do_numainfo; + bool do_softlimit; + bool do_numainfo __maybe_unused; do_softlimit = mem_cgroup_event_ratelimit(memcg, MEM_CGROUP_TARGET_SOFTLIMIT); @@ -1041,9 +1069,22 @@ struct lruvec *mem_cgroup_lru_add_list(struct zone *zone, struct page *page, pc = lookup_page_cgroup(page); memcg = pc->mem_cgroup; + + /* + * Surreptitiously switch any uncharged page to root: + * an uncharged page off lru does nothing to secure + * its former mem_cgroup from sudden removal. + * + * Our caller holds lru_lock, and PageCgroupUsed is updated + * under page_cgroup lock: between them, they make all uses + * of pc->mem_cgroup safe. + */ + if (!PageCgroupUsed(pc) && memcg != root_mem_cgroup) + pc->mem_cgroup = memcg = root_mem_cgroup; + mz = page_cgroup_zoneinfo(memcg, page); /* compound_order() is stabilized through lru_lock */ - MEM_CGROUP_ZSTAT(mz, lru) += 1 << compound_order(page); + mz->lru_size[lru] += 1 << compound_order(page); return &mz->lruvec; } @@ -1071,8 +1112,8 @@ void mem_cgroup_lru_del_list(struct page *page, enum lru_list lru) VM_BUG_ON(!memcg); mz = page_cgroup_zoneinfo(memcg, page); /* huge page split is done under lru_lock. so, we have no races. */ - VM_BUG_ON(MEM_CGROUP_ZSTAT(mz, lru) < (1 << compound_order(page))); - MEM_CGROUP_ZSTAT(mz, lru) -= 1 << compound_order(page); + VM_BUG_ON(mz->lru_size[lru] < (1 << compound_order(page))); + mz->lru_size[lru] -= 1 << compound_order(page); } void mem_cgroup_lru_del(struct page *page) @@ -1251,40 +1292,48 @@ int mem_cgroup_swappiness(struct mem_cgroup *memcg) return memcg->swappiness; } -static void mem_cgroup_start_move(struct mem_cgroup *memcg) -{ - int cpu; +/* + * memcg->moving_account is used for checking possibility that some thread is + * calling move_account(). When a thread on CPU-A starts moving pages under + * a memcg, other threads should check memcg->moving_account under + * rcu_read_lock(), like this: + * + * CPU-A CPU-B + * rcu_read_lock() + * memcg->moving_account+1 if (memcg->mocing_account) + * take heavy locks. + * synchronize_rcu() update something. + * rcu_read_unlock() + * start move here. + */ - get_online_cpus(); - spin_lock(&memcg->pcp_counter_lock); - for_each_online_cpu(cpu) - per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) += 1; - memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] += 1; - spin_unlock(&memcg->pcp_counter_lock); - put_online_cpus(); +/* for quick checking without looking up memcg */ +atomic_t memcg_moving __read_mostly; +static void mem_cgroup_start_move(struct mem_cgroup *memcg) +{ + atomic_inc(&memcg_moving); + atomic_inc(&memcg->moving_account); synchronize_rcu(); } static void mem_cgroup_end_move(struct mem_cgroup *memcg) { - int cpu; - - if (!memcg) - return; - get_online_cpus(); - spin_lock(&memcg->pcp_counter_lock); - for_each_online_cpu(cpu) - per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) -= 1; - memcg->nocpu_base.count[MEM_CGROUP_ON_MOVE] -= 1; - spin_unlock(&memcg->pcp_counter_lock); - put_online_cpus(); + /* + * Now, mem_cgroup_clear_mc() may call this function with NULL. + * We check NULL in callee rather than caller. + */ + if (memcg) { + atomic_dec(&memcg_moving); + atomic_dec(&memcg->moving_account); + } } + /* * 2 routines for checking "mem" is under move_account() or not. * - * mem_cgroup_stealed() - checking a cgroup is mc.from or not. This is used - * for avoiding race in accounting. If true, + * mem_cgroup_stolen() - checking whether a cgroup is mc.from or not. This + * is used for avoiding races in accounting. If true, * pc->mem_cgroup may be overwritten. * * mem_cgroup_under_move() - checking a cgroup is mc.from or mc.to or @@ -1292,10 +1341,10 @@ static void mem_cgroup_end_move(struct mem_cgroup *memcg) * waiting at hith-memory prressure caused by "move". */ -static bool mem_cgroup_stealed(struct mem_cgroup *memcg) +static bool mem_cgroup_stolen(struct mem_cgroup *memcg) { VM_BUG_ON(!rcu_read_lock_held()); - return this_cpu_read(memcg->stat->count[MEM_CGROUP_ON_MOVE]) > 0; + return atomic_read(&memcg->moving_account) > 0; } static bool mem_cgroup_under_move(struct mem_cgroup *memcg) @@ -1336,6 +1385,24 @@ static bool mem_cgroup_wait_acct_move(struct mem_cgroup *memcg) return false; } +/* + * Take this lock when + * - a code tries to modify page's memcg while it's USED. + * - a code tries to modify page state accounting in a memcg. + * see mem_cgroup_stolen(), too. + */ +static void move_lock_mem_cgroup(struct mem_cgroup *memcg, + unsigned long *flags) +{ + spin_lock_irqsave(&memcg->move_lock, *flags); +} + +static void move_unlock_mem_cgroup(struct mem_cgroup *memcg, + unsigned long *flags) +{ + spin_unlock_irqrestore(&memcg->move_lock, *flags); +} + /** * mem_cgroup_print_oom_info: Called from OOM with tasklist_lock held in read mode. * @memcg: The memory cgroup that went over limit @@ -1359,7 +1426,6 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) if (!memcg || !p) return; - rcu_read_lock(); mem_cgrp = memcg->css.cgroup; @@ -1738,22 +1804,22 @@ static DEFINE_SPINLOCK(memcg_oom_lock); static DECLARE_WAIT_QUEUE_HEAD(memcg_oom_waitq); struct oom_wait_info { - struct mem_cgroup *mem; + struct mem_cgroup *memcg; wait_queue_t wait; }; static int memcg_oom_wake_function(wait_queue_t *wait, unsigned mode, int sync, void *arg) { - struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg, - *oom_wait_memcg; + struct mem_cgroup *wake_memcg = (struct mem_cgroup *)arg; + struct mem_cgroup *oom_wait_memcg; struct oom_wait_info *oom_wait_info; oom_wait_info = container_of(wait, struct oom_wait_info, wait); - oom_wait_memcg = oom_wait_info->mem; + oom_wait_memcg = oom_wait_info->memcg; /* - * Both of oom_wait_info->mem and wake_mem are stable under us. + * Both of oom_wait_info->memcg and wake_memcg are stable under us. * Then we can use css_is_ancestor without taking care of RCU. */ if (!mem_cgroup_same_or_subtree(oom_wait_memcg, wake_memcg) @@ -1777,12 +1843,12 @@ static void memcg_oom_recover(struct mem_cgroup *memcg) /* * try to call OOM killer. returns false if we should exit memory-reclaim loop. */ -bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask) +bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask, int order) { struct oom_wait_info owait; bool locked, need_to_kill; - owait.mem = memcg; + owait.memcg = memcg; owait.wait.flags = 0; owait.wait.func = memcg_oom_wake_function; owait.wait.private = current; @@ -1807,7 +1873,7 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask) if (need_to_kill) { finish_wait(&memcg_oom_waitq, &owait.wait); - mem_cgroup_out_of_memory(memcg, mask); + mem_cgroup_out_of_memory(memcg, mask, order); } else { schedule(); finish_wait(&memcg_oom_waitq, &owait.wait); @@ -1847,41 +1913,66 @@ bool mem_cgroup_handle_oom(struct mem_cgroup *memcg, gfp_t mask) * by flags. * * Considering "move", this is an only case we see a race. To make the race - * small, we check MEM_CGROUP_ON_MOVE percpu value and detect there are - * possibility of race condition. If there is, we take a lock. + * small, we check mm->moving_account and detect there are possibility of race + * If there is, we take a lock. */ +void __mem_cgroup_begin_update_page_stat(struct page *page, + bool *locked, unsigned long *flags) +{ + struct mem_cgroup *memcg; + struct page_cgroup *pc; + + pc = lookup_page_cgroup(page); +again: + memcg = pc->mem_cgroup; + if (unlikely(!memcg || !PageCgroupUsed(pc))) + return; + /* + * If this memory cgroup is not under account moving, we don't + * need to take move_lock_page_cgroup(). Because we already hold + * rcu_read_lock(), any calls to move_account will be delayed until + * rcu_read_unlock() if mem_cgroup_stolen() == true. + */ + if (!mem_cgroup_stolen(memcg)) + return; + + move_lock_mem_cgroup(memcg, flags); + if (memcg != pc->mem_cgroup || !PageCgroupUsed(pc)) { + move_unlock_mem_cgroup(memcg, flags); + goto again; + } + *locked = true; +} + +void __mem_cgroup_end_update_page_stat(struct page *page, unsigned long *flags) +{ + struct page_cgroup *pc = lookup_page_cgroup(page); + + /* + * It's guaranteed that pc->mem_cgroup never changes while + * lock is held because a routine modifies pc->mem_cgroup + * should take move_lock_page_cgroup(). + */ + move_unlock_mem_cgroup(pc->mem_cgroup, flags); +} + void mem_cgroup_update_page_stat(struct page *page, enum mem_cgroup_page_stat_item idx, int val) { struct mem_cgroup *memcg; struct page_cgroup *pc = lookup_page_cgroup(page); - bool need_unlock = false; unsigned long uninitialized_var(flags); if (mem_cgroup_disabled()) return; - rcu_read_lock(); memcg = pc->mem_cgroup; if (unlikely(!memcg || !PageCgroupUsed(pc))) - goto out; - /* pc->mem_cgroup is unstable ? */ - if (unlikely(mem_cgroup_stealed(memcg)) || PageTransHuge(page)) { - /* take a lock against to access pc->mem_cgroup */ - move_lock_page_cgroup(pc, &flags); - need_unlock = true; - memcg = pc->mem_cgroup; - if (!memcg || !PageCgroupUsed(pc)) - goto out; - } + return; switch (idx) { case MEMCG_NR_FILE_MAPPED: - if (val > 0) - SetPageCgroupFileMapped(pc); - else if (!page_mapped(page)) - ClearPageCgroupFileMapped(pc); idx = MEM_CGROUP_STAT_FILE_MAPPED; break; default: @@ -1889,14 +1980,7 @@ void mem_cgroup_update_page_stat(struct page *page, } this_cpu_add(memcg->stat->count[idx], val); - -out: - if (unlikely(need_unlock)) - move_unlock_page_cgroup(pc, &flags); - rcu_read_unlock(); - return; } -EXPORT_SYMBOL(mem_cgroup_update_page_stat); /* * size of first charge trial. "32" comes from vmscan.c's magic value. @@ -2067,17 +2151,6 @@ static void mem_cgroup_drain_pcp_counter(struct mem_cgroup *memcg, int cpu) per_cpu(memcg->stat->events[i], cpu) = 0; memcg->nocpu_base.events[i] += x; } - /* need to clear ON_MOVE value, works as a kind of lock. */ - per_cpu(memcg->stat->count[MEM_CGROUP_ON_MOVE], cpu) = 0; - spin_unlock(&memcg->pcp_counter_lock); -} - -static void synchronize_mem_cgroup_on_move(struct mem_cgroup *memcg, int cpu) -{ - int idx = MEM_CGROUP_ON_MOVE; - - spin_lock(&memcg->pcp_counter_lock); - per_cpu(memcg->stat->count[idx], cpu) = memcg->nocpu_base.count[idx]; spin_unlock(&memcg->pcp_counter_lock); } @@ -2089,11 +2162,8 @@ static int __cpuinit memcg_cpu_hotplug_callback(struct notifier_block *nb, struct memcg_stock_pcp *stock; struct mem_cgroup *iter; - if ((action == CPU_ONLINE)) { - for_each_mem_cgroup(iter) - synchronize_mem_cgroup_on_move(iter, cpu); + if (action == CPU_ONLINE) return NOTIFY_OK; - } if ((action != CPU_DEAD) || action != CPU_DEAD_FROZEN) return NOTIFY_OK; @@ -2178,7 +2248,7 @@ static int mem_cgroup_do_charge(struct mem_cgroup *memcg, gfp_t gfp_mask, if (!oom_check) return CHARGE_NOMEM; /* check OOM */ - if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask)) + if (!mem_cgroup_handle_oom(mem_over_limit, gfp_mask, get_order(csize))) return CHARGE_OOM_DIE; return CHARGE_RETRY; @@ -2407,8 +2477,13 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, struct page *page, unsigned int nr_pages, struct page_cgroup *pc, - enum charge_type ctype) + enum charge_type ctype, + bool lrucare) { + struct zone *uninitialized_var(zone); + bool was_on_lru = false; + bool anon; + lock_page_cgroup(pc); if (unlikely(PageCgroupUsed(pc))) { unlock_page_cgroup(pc); @@ -2419,6 +2494,21 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, * we don't need page_cgroup_lock about tail pages, becase they are not * accessed by any other context at this point. */ + + /* + * In some cases, SwapCache and FUSE(splice_buf->radixtree), the page + * may already be on some other mem_cgroup's LRU. Take care of it. + */ + if (lrucare) { + zone = page_zone(page); + spin_lock_irq(&zone->lru_lock); + if (PageLRU(page)) { + ClearPageLRU(page); + del_page_from_lru_list(zone, page, page_lru(page)); + was_on_lru = true; + } + } + pc->mem_cgroup = memcg; /* * We access a page_cgroup asynchronously without lock_page_cgroup(). @@ -2428,23 +2518,25 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, * See mem_cgroup_add_lru_list(), etc. */ smp_wmb(); - switch (ctype) { - case MEM_CGROUP_CHARGE_TYPE_CACHE: - case MEM_CGROUP_CHARGE_TYPE_SHMEM: - SetPageCgroupCache(pc); - SetPageCgroupUsed(pc); - break; - case MEM_CGROUP_CHARGE_TYPE_MAPPED: - ClearPageCgroupCache(pc); - SetPageCgroupUsed(pc); - break; - default: - break; + SetPageCgroupUsed(pc); + + if (lrucare) { + if (was_on_lru) { + VM_BUG_ON(PageLRU(page)); + SetPageLRU(page); + add_page_to_lru_list(zone, page, page_lru(page)); + } + spin_unlock_irq(&zone->lru_lock); } - mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), nr_pages); + if (ctype == MEM_CGROUP_CHARGE_TYPE_MAPPED) + anon = true; + else + anon = false; + + mem_cgroup_charge_statistics(memcg, anon, nr_pages); unlock_page_cgroup(pc); - WARN_ON_ONCE(PageLRU(page)); + /* * "charge_statistics" updated event counter. Then, check it. * Insert ancestor (and ancestor's ancestors), to softlimit RB-tree. @@ -2455,8 +2547,7 @@ static void __mem_cgroup_commit_charge(struct mem_cgroup *memcg, #ifdef CONFIG_TRANSPARENT_HUGEPAGE -#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MOVE_LOCK) |\ - (1 << PCG_MIGRATION)) +#define PCGF_NOCOPY_AT_SPLIT ((1 << PCG_LOCK) | (1 << PCG_MIGRATION)) /* * Because tail pages are not marked as "used", set it. We're under * zone->lru_lock, 'splitting on pmd' and compound_lock. @@ -2507,6 +2598,7 @@ static int mem_cgroup_move_account(struct page *page, { unsigned long flags; int ret; + bool anon = PageAnon(page); VM_BUG_ON(from == to); VM_BUG_ON(PageLRU(page)); @@ -2526,23 +2618,23 @@ static int mem_cgroup_move_account(struct page *page, if (!PageCgroupUsed(pc) || pc->mem_cgroup != from) goto unlock; - move_lock_page_cgroup(pc, &flags); + move_lock_mem_cgroup(from, &flags); - if (PageCgroupFileMapped(pc)) { + if (!anon && page_mapped(page)) { /* Update mapped_file data for mem_cgroup */ preempt_disable(); __this_cpu_dec(from->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); __this_cpu_inc(to->stat->count[MEM_CGROUP_STAT_FILE_MAPPED]); preempt_enable(); } - mem_cgroup_charge_statistics(from, PageCgroupCache(pc), -nr_pages); + mem_cgroup_charge_statistics(from, anon, -nr_pages); if (uncharge) /* This is not "cancel", but cancel_charge does all we need. */ __mem_cgroup_cancel_charge(from, nr_pages); /* caller should have done css_get */ pc->mem_cgroup = to; - mem_cgroup_charge_statistics(to, PageCgroupCache(pc), nr_pages); + mem_cgroup_charge_statistics(to, anon, nr_pages); /* * We charges against "to" which may not have any tasks. Then, "to" * can be under rmdir(). But in current implementation, caller of @@ -2550,7 +2642,7 @@ static int mem_cgroup_move_account(struct page *page, * guaranteed that "to" is never removed. So, we don't check rmdir * status here. */ - move_unlock_page_cgroup(pc, &flags); + move_unlock_mem_cgroup(from, &flags); ret = 0; unlock: unlock_page_cgroup(pc); @@ -2642,7 +2734,7 @@ static int mem_cgroup_charge_common(struct page *page, struct mm_struct *mm, ret = __mem_cgroup_try_charge(mm, gfp_mask, nr_pages, &memcg, oom); if (ret == -ENOMEM) return ret; - __mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype); + __mem_cgroup_commit_charge(memcg, page, nr_pages, pc, ctype, false); return 0; } @@ -2662,35 +2754,6 @@ static void __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *ptr, enum charge_type ctype); -static void -__mem_cgroup_commit_charge_lrucare(struct page *page, struct mem_cgroup *memcg, - enum charge_type ctype) -{ - struct page_cgroup *pc = lookup_page_cgroup(page); - struct zone *zone = page_zone(page); - unsigned long flags; - bool removed = false; - - /* - * In some case, SwapCache, FUSE(splice_buf->radixtree), the page - * is already on LRU. It means the page may on some other page_cgroup's - * LRU. Take care of it. - */ - spin_lock_irqsave(&zone->lru_lock, flags); - if (PageLRU(page)) { - del_page_from_lru_list(zone, page, page_lru(page)); - ClearPageLRU(page); - removed = true; - } - __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype); - if (removed) { - add_page_to_lru_list(zone, page, page_lru(page)); - SetPageLRU(page); - } - spin_unlock_irqrestore(&zone->lru_lock, flags); - return; -} - int mem_cgroup_cache_charge(struct page *page, struct mm_struct *mm, gfp_t gfp_mask) { @@ -2768,13 +2831,16 @@ static void __mem_cgroup_commit_charge_swapin(struct page *page, struct mem_cgroup *memcg, enum charge_type ctype) { + struct page_cgroup *pc; + if (mem_cgroup_disabled()) return; if (!memcg) return; cgroup_exclude_rmdir(&memcg->css); - __mem_cgroup_commit_charge_lrucare(page, memcg, ctype); + pc = lookup_page_cgroup(page); + __mem_cgroup_commit_charge(memcg, page, 1, pc, ctype, true); /* * Now swap is on-memory. This means this page may be * counted both as mem and swap....double count. @@ -2878,7 +2944,6 @@ direct_uncharge: res_counter_uncharge(&memcg->memsw, nr_pages * PAGE_SIZE); if (unlikely(batch->memcg != memcg)) memcg_oom_recover(memcg); - return; } /* @@ -2890,6 +2955,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) struct mem_cgroup *memcg = NULL; unsigned int nr_pages = 1; struct page_cgroup *pc; + bool anon; if (mem_cgroup_disabled()) return NULL; @@ -2915,8 +2981,17 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) if (!PageCgroupUsed(pc)) goto unlock_out; + anon = PageAnon(page); + switch (ctype) { case MEM_CGROUP_CHARGE_TYPE_MAPPED: + /* + * Generally PageAnon tells if it's the anon statistics to be + * updated; but sometimes e.g. mem_cgroup_uncharge_page() is + * used before page reached the stage of being marked PageAnon. + */ + anon = true; + /* fallthrough */ case MEM_CGROUP_CHARGE_TYPE_DROP: /* See mem_cgroup_prepare_migration() */ if (page_mapped(page) || PageCgroupMigration(pc)) @@ -2933,7 +3008,7 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype) break; } - mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -nr_pages); + mem_cgroup_charge_statistics(memcg, anon, -nr_pages); ClearPageCgroupUsed(pc); /* @@ -3026,23 +3101,6 @@ void mem_cgroup_uncharge_end(void) batch->memcg = NULL; } -/* - * A function for resetting pc->mem_cgroup for newly allocated pages. - * This function should be called if the newpage will be added to LRU - * before start accounting. - */ -void mem_cgroup_reset_owner(struct page *newpage) -{ - struct page_cgroup *pc; - - if (mem_cgroup_disabled()) - return; - - pc = lookup_page_cgroup(newpage); - VM_BUG_ON(PageCgroupUsed(pc)); - pc->mem_cgroup = root_mem_cgroup; -} - #ifdef CONFIG_SWAP /* * called after __delete_from_swap_cache() and drop "page" account. @@ -3247,7 +3305,7 @@ int mem_cgroup_prepare_migration(struct page *page, ctype = MEM_CGROUP_CHARGE_TYPE_CACHE; else ctype = MEM_CGROUP_CHARGE_TYPE_SHMEM; - __mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype); + __mem_cgroup_commit_charge(memcg, newpage, 1, pc, ctype, false); return ret; } @@ -3257,6 +3315,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, { struct page *used, *unused; struct page_cgroup *pc; + bool anon; if (!memcg) return; @@ -3278,8 +3337,10 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, lock_page_cgroup(pc); ClearPageCgroupMigration(pc); unlock_page_cgroup(pc); - - __mem_cgroup_uncharge_common(unused, MEM_CGROUP_CHARGE_TYPE_FORCE); + anon = PageAnon(used); + __mem_cgroup_uncharge_common(unused, + anon ? MEM_CGROUP_CHARGE_TYPE_MAPPED + : MEM_CGROUP_CHARGE_TYPE_CACHE); /* * If a page is a file cache, radix-tree replacement is very atomic @@ -3289,7 +3350,7 @@ void mem_cgroup_end_migration(struct mem_cgroup *memcg, * and USED bit check in mem_cgroup_uncharge_page() will do enough * check. (see prepare_charge() also) */ - if (PageAnon(used)) + if (anon) mem_cgroup_uncharge_page(used); /* * At migration, we may charge account against cgroup which has no @@ -3319,7 +3380,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage, /* fix accounting on old pages */ lock_page_cgroup(pc); memcg = pc->mem_cgroup; - mem_cgroup_charge_statistics(memcg, PageCgroupCache(pc), -1); + mem_cgroup_charge_statistics(memcg, false, -1); ClearPageCgroupUsed(pc); unlock_page_cgroup(pc); @@ -3331,7 +3392,7 @@ void mem_cgroup_replace_page_cache(struct page *oldpage, * the newpage may be on LRU(or pagevec for LRU) already. We lock * LRU while we overwrite pc->mem_cgroup. */ - __mem_cgroup_commit_charge_lrucare(newpage, memcg, type); + __mem_cgroup_commit_charge(memcg, newpage, 1, pc, type, true); } #ifdef CONFIG_DEBUG_VM @@ -3530,7 +3591,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, break; nr_scanned = 0; - reclaimed = mem_cgroup_soft_reclaim(mz->mem, zone, + reclaimed = mem_cgroup_soft_reclaim(mz->memcg, zone, gfp_mask, &nr_scanned); nr_reclaimed += reclaimed; *total_scanned += nr_scanned; @@ -3557,13 +3618,13 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, next_mz = __mem_cgroup_largest_soft_limit_node(mctz); if (next_mz == mz) - css_put(&next_mz->mem->css); + css_put(&next_mz->memcg->css); else /* next_mz == NULL or other memcg */ break; } while (1); } - __mem_cgroup_remove_exceeded(mz->mem, mz, mctz); - excess = res_counter_soft_limit_excess(&mz->mem->res); + __mem_cgroup_remove_exceeded(mz->memcg, mz, mctz); + excess = res_counter_soft_limit_excess(&mz->memcg->res); /* * One school of thought says that we should not add * back the node to the tree if reclaim returns 0. @@ -3573,9 +3634,9 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, * term TODO. */ /* If excess == 0, no tree ops */ - __mem_cgroup_insert_exceeded(mz->mem, mz, mctz, excess); + __mem_cgroup_insert_exceeded(mz->memcg, mz, mctz, excess); spin_unlock(&mctz->lock); - css_put(&mz->mem->css); + css_put(&mz->memcg->css); loop++; /* * Could not reclaim anything and there are no more @@ -3588,7 +3649,7 @@ unsigned long mem_cgroup_soft_limit_reclaim(struct zone *zone, int order, break; } while (!nr_reclaimed); if (next_mz) - css_put(&next_mz->mem->css); + css_put(&next_mz->memcg->css); return nr_reclaimed; } @@ -3610,7 +3671,7 @@ static int mem_cgroup_force_empty_list(struct mem_cgroup *memcg, mz = mem_cgroup_zoneinfo(memcg, node, zid); list = &mz->lruvec.lists[lru]; - loop = MEM_CGROUP_ZSTAT(mz, lru); + loop = mz->lru_size[lru]; /* give some margin against EBUSY etc...*/ loop += 256; busy = NULL; @@ -3684,10 +3745,10 @@ move_account: mem_cgroup_start_move(memcg); for_each_node_state(node, N_HIGH_MEMORY) { for (zid = 0; !ret && zid < MAX_NR_ZONES; zid++) { - enum lru_list l; - for_each_lru(l) { + enum lru_list lru; + for_each_lru(lru) { ret = mem_cgroup_force_empty_list(memcg, - node, zid, l); + node, zid, lru); if (ret) break; } @@ -3841,7 +3902,6 @@ static u64 mem_cgroup_read(struct cgroup *cont, struct cftype *cft) break; default: BUG(); - break; } return val; } @@ -3920,7 +3980,6 @@ static void memcg_get_hierarchical_limit(struct mem_cgroup *memcg, out: *mem_limit = min_limit; *memsw_limit = min_memsw_limit; - return; } static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) @@ -4079,38 +4138,38 @@ static int mem_control_numa_stat_show(struct seq_file *m, void *arg) unsigned long total_nr, file_nr, anon_nr, unevictable_nr; unsigned long node_nr; struct cgroup *cont = m->private; - struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - total_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL); + total_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL); seq_printf(m, "total=%lu", total_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, LRU_ALL); + node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL); seq_printf(m, " N%d=%lu", nid, node_nr); } seq_putc(m, '\n'); - file_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_FILE); + file_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_FILE); seq_printf(m, "file=%lu", file_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, + node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_FILE); seq_printf(m, " N%d=%lu", nid, node_nr); } seq_putc(m, '\n'); - anon_nr = mem_cgroup_nr_lru_pages(mem_cont, LRU_ALL_ANON); + anon_nr = mem_cgroup_nr_lru_pages(memcg, LRU_ALL_ANON); seq_printf(m, "anon=%lu", anon_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, + node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, LRU_ALL_ANON); seq_printf(m, " N%d=%lu", nid, node_nr); } seq_putc(m, '\n'); - unevictable_nr = mem_cgroup_nr_lru_pages(mem_cont, BIT(LRU_UNEVICTABLE)); + unevictable_nr = mem_cgroup_nr_lru_pages(memcg, BIT(LRU_UNEVICTABLE)); seq_printf(m, "unevictable=%lu", unevictable_nr); for_each_node_state(nid, N_HIGH_MEMORY) { - node_nr = mem_cgroup_node_nr_lru_pages(mem_cont, nid, + node_nr = mem_cgroup_node_nr_lru_pages(memcg, nid, BIT(LRU_UNEVICTABLE)); seq_printf(m, " N%d=%lu", nid, node_nr); } @@ -4122,12 +4181,12 @@ static int mem_control_numa_stat_show(struct seq_file *m, void *arg) static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, struct cgroup_map_cb *cb) { - struct mem_cgroup *mem_cont = mem_cgroup_from_cont(cont); + struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); struct mcs_total_stat mystat; int i; memset(&mystat, 0, sizeof(mystat)); - mem_cgroup_get_local_stat(mem_cont, &mystat); + mem_cgroup_get_local_stat(memcg, &mystat); for (i = 0; i < NR_MCS_STAT; i++) { @@ -4139,14 +4198,14 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, /* Hierarchical information */ { unsigned long long limit, memsw_limit; - memcg_get_hierarchical_limit(mem_cont, &limit, &memsw_limit); + memcg_get_hierarchical_limit(memcg, &limit, &memsw_limit); cb->fill(cb, "hierarchical_memory_limit", limit); if (do_swap_account) cb->fill(cb, "hierarchical_memsw_limit", memsw_limit); } memset(&mystat, 0, sizeof(mystat)); - mem_cgroup_get_total_stat(mem_cont, &mystat); + mem_cgroup_get_total_stat(memcg, &mystat); for (i = 0; i < NR_MCS_STAT; i++) { if (i == MCS_SWAP && !do_swap_account) continue; @@ -4162,7 +4221,7 @@ static int mem_control_stat_show(struct cgroup *cont, struct cftype *cft, for_each_online_node(nid) for (zid = 0; zid < MAX_NR_ZONES; zid++) { - mz = mem_cgroup_zoneinfo(mem_cont, nid, zid); + mz = mem_cgroup_zoneinfo(memcg, nid, zid); recent_rotated[0] += mz->reclaim_stat.recent_rotated[0]; @@ -4407,11 +4466,8 @@ static void mem_cgroup_usage_unregister_event(struct cgroup *cgrp, else BUG(); - /* - * Something went wrong if we trying to unregister a threshold - * if we don't have thresholds - */ - BUG_ON(!thresholds); + if (!thresholds->primary) + goto unlock; usage = mem_cgroup_usage(memcg, type == _MEMSWAP); @@ -4461,7 +4517,7 @@ swap_buffers: /* To be sure that nobody uses thresholds */ synchronize_rcu(); - +unlock: mutex_unlock(&memcg->thresholds_lock); } @@ -4580,10 +4636,9 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) return mem_cgroup_sockets_init(cont, ss); }; -static void kmem_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static void kmem_cgroup_destroy(struct cgroup *cont) { - mem_cgroup_sockets_destroy(cont, ss); + mem_cgroup_sockets_destroy(cont); } #else static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) @@ -4591,8 +4646,7 @@ static int register_kmem_files(struct cgroup *cont, struct cgroup_subsys *ss) return 0; } -static void kmem_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static void kmem_cgroup_destroy(struct cgroup *cont) { } #endif @@ -4716,7 +4770,7 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) { struct mem_cgroup_per_node *pn; struct mem_cgroup_per_zone *mz; - enum lru_list l; + enum lru_list lru; int zone, tmp = node; /* * This routine is called against possible nodes. @@ -4734,11 +4788,11 @@ static int alloc_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) for (zone = 0; zone < MAX_NR_ZONES; zone++) { mz = &pn->zoneinfo[zone]; - for_each_lru(l) - INIT_LIST_HEAD(&mz->lruvec.lists[l]); + for_each_lru(lru) + INIT_LIST_HEAD(&mz->lruvec.lists[lru]); mz->usage_in_excess = 0; mz->on_tree = false; - mz->mem = memcg; + mz->memcg = memcg; } memcg->info.nodeinfo[node] = pn; return 0; @@ -4751,33 +4805,54 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) static struct mem_cgroup *mem_cgroup_alloc(void) { - struct mem_cgroup *mem; + struct mem_cgroup *memcg; int size = sizeof(struct mem_cgroup); /* Can be very big if MAX_NUMNODES is very big */ if (size < PAGE_SIZE) - mem = kzalloc(size, GFP_KERNEL); + memcg = kzalloc(size, GFP_KERNEL); else - mem = vzalloc(size); + memcg = vzalloc(size); - if (!mem) + if (!memcg) return NULL; - mem->stat = alloc_percpu(struct mem_cgroup_stat_cpu); - if (!mem->stat) + memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); + if (!memcg->stat) goto out_free; - spin_lock_init(&mem->pcp_counter_lock); - return mem; + spin_lock_init(&memcg->pcp_counter_lock); + return memcg; out_free: if (size < PAGE_SIZE) - kfree(mem); + kfree(memcg); else - vfree(mem); + vfree(memcg); return NULL; } /* + * Helpers for freeing a vzalloc()ed mem_cgroup by RCU, + * but in process context. The work_freeing structure is overlaid + * on the rcu_freeing structure, which itself is overlaid on memsw. + */ +static void vfree_work(struct work_struct *work) +{ + struct mem_cgroup *memcg; + + memcg = container_of(work, struct mem_cgroup, work_freeing); + vfree(memcg); +} +static void vfree_rcu(struct rcu_head *rcu_head) +{ + struct mem_cgroup *memcg; + + memcg = container_of(rcu_head, struct mem_cgroup, rcu_freeing); + INIT_WORK(&memcg->work_freeing, vfree_work); + schedule_work(&memcg->work_freeing); +} + +/* * At destroying mem_cgroup, references from swap_cgroup can remain. * (scanning all at force_empty is too costly...) * @@ -4800,9 +4875,9 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) free_percpu(memcg->stat); if (sizeof(struct mem_cgroup) < PAGE_SIZE) - kfree(memcg); + kfree_rcu(memcg, rcu_freeing); else - vfree(memcg); + call_rcu(&memcg->rcu_freeing, vfree_rcu); } static void mem_cgroup_get(struct mem_cgroup *memcg) @@ -4884,7 +4959,7 @@ err_cleanup: } static struct cgroup_subsys_state * __ref -mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) +mem_cgroup_create(struct cgroup *cont) { struct mem_cgroup *memcg, *parent; long error = -ENOMEM; @@ -4940,26 +5015,25 @@ mem_cgroup_create(struct cgroup_subsys *ss, struct cgroup *cont) atomic_set(&memcg->refcnt, 1); memcg->move_charge_at_immigrate = 0; mutex_init(&memcg->thresholds_lock); + spin_lock_init(&memcg->move_lock); return &memcg->css; free_out: __mem_cgroup_free(memcg); return ERR_PTR(error); } -static int mem_cgroup_pre_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static int mem_cgroup_pre_destroy(struct cgroup *cont) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); return mem_cgroup_force_empty(memcg, false); } -static void mem_cgroup_destroy(struct cgroup_subsys *ss, - struct cgroup *cont) +static void mem_cgroup_destroy(struct cgroup *cont) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); - kmem_cgroup_destroy(ss, cont); + kmem_cgroup_destroy(cont); mem_cgroup_put(memcg); } @@ -5036,7 +5110,7 @@ one_by_one: } /** - * is_target_pte_for_mc - check a pte whether it is valid for move charge + * get_mctgt_type - get target type of moving charge * @vma: the vma the pte to be checked belongs * @addr: the address corresponding to the pte to be checked * @ptent: the pte to be checked @@ -5059,7 +5133,7 @@ union mc_target { }; enum mc_target_type { - MC_TARGET_NONE, /* not used */ + MC_TARGET_NONE = 0, MC_TARGET_PAGE, MC_TARGET_SWAP, }; @@ -5140,12 +5214,12 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, return page; } -static int is_target_pte_for_mc(struct vm_area_struct *vma, +static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, unsigned long addr, pte_t ptent, union mc_target *target) { struct page *page = NULL; struct page_cgroup *pc; - int ret = 0; + enum mc_target_type ret = MC_TARGET_NONE; swp_entry_t ent = { .val = 0 }; if (pte_present(ptent)) @@ -5156,7 +5230,7 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma, page = mc_handle_file_pte(vma, addr, ptent, &ent); if (!page && !ent.val) - return 0; + return ret; if (page) { pc = lookup_page_cgroup(page); /* @@ -5182,6 +5256,41 @@ static int is_target_pte_for_mc(struct vm_area_struct *vma, return ret; } +#ifdef CONFIG_TRANSPARENT_HUGEPAGE +/* + * We don't consider swapping or file mapped pages because THP does not + * support them for now. + * Caller should make sure that pmd_trans_huge(pmd) is true. + */ +static enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd, union mc_target *target) +{ + struct page *page = NULL; + struct page_cgroup *pc; + enum mc_target_type ret = MC_TARGET_NONE; + + page = pmd_page(pmd); + VM_BUG_ON(!page || !PageHead(page)); + if (!move_anon()) + return ret; + pc = lookup_page_cgroup(page); + if (PageCgroupUsed(pc) && pc->mem_cgroup == mc.from) { + ret = MC_TARGET_PAGE; + if (target) { + get_page(page); + target->page = page; + } + } + return ret; +} +#else +static inline enum mc_target_type get_mctgt_type_thp(struct vm_area_struct *vma, + unsigned long addr, pmd_t pmd, union mc_target *target) +{ + return MC_TARGET_NONE; +} +#endif + static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -5190,11 +5299,18 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, pte_t *pte; spinlock_t *ptl; - split_huge_page_pmd(walk->mm, pmd); + if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) + mc.precharge += HPAGE_PMD_NR; + spin_unlock(&vma->vm_mm->page_table_lock); + return 0; + } + if (pmd_trans_unstable(pmd)) + return 0; pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; pte++, addr += PAGE_SIZE) - if (is_target_pte_for_mc(vma, addr, *pte, NULL)) + if (get_mctgt_type(vma, addr, *pte, NULL)) mc.precharge++; /* increment precharge temporarily */ pte_unmap_unlock(pte - 1, ptl); cond_resched(); @@ -5296,9 +5412,8 @@ static void mem_cgroup_clear_mc(void) mem_cgroup_end_move(from); } -static int mem_cgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); int ret = 0; @@ -5336,9 +5451,8 @@ static int mem_cgroup_can_attach(struct cgroup_subsys *ss, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { mem_cgroup_clear_mc(); } @@ -5351,23 +5465,57 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, struct vm_area_struct *vma = walk->private; pte_t *pte; spinlock_t *ptl; + enum mc_target_type target_type; + union mc_target target; + struct page *page; + struct page_cgroup *pc; - split_huge_page_pmd(walk->mm, pmd); + /* + * We don't take compound_lock() here but no race with splitting thp + * happens because: + * - if pmd_trans_huge_lock() returns 1, the relevant thp is not + * under splitting, which means there's no concurrent thp split, + * - if another thread runs into split_huge_page() just after we + * entered this if-block, the thread must wait for page table lock + * to be unlocked in __split_huge_page_splitting(), where the main + * part of thp split is not executed yet. + */ + if (pmd_trans_huge_lock(pmd, vma) == 1) { + if (!mc.precharge) { + spin_unlock(&vma->vm_mm->page_table_lock); + return 0; + } + target_type = get_mctgt_type_thp(vma, addr, *pmd, &target); + if (target_type == MC_TARGET_PAGE) { + page = target.page; + if (!isolate_lru_page(page)) { + pc = lookup_page_cgroup(page); + if (!mem_cgroup_move_account(page, HPAGE_PMD_NR, + pc, mc.from, mc.to, + false)) { + mc.precharge -= HPAGE_PMD_NR; + mc.moved_charge += HPAGE_PMD_NR; + } + putback_lru_page(page); + } + put_page(page); + } + spin_unlock(&vma->vm_mm->page_table_lock); + return 0; + } + + if (pmd_trans_unstable(pmd)) + return 0; retry: pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); for (; addr != end; addr += PAGE_SIZE) { pte_t ptent = *(pte++); - union mc_target target; - int type; - struct page *page; - struct page_cgroup *pc; swp_entry_t ent; if (!mc.precharge) break; - type = is_target_pte_for_mc(vma, addr, ptent, &target); - switch (type) { + switch (get_mctgt_type(vma, addr, ptent, &target)) { case MC_TARGET_PAGE: page = target.page; if (isolate_lru_page(page)) @@ -5380,7 +5528,7 @@ retry: mc.moved_charge++; } putback_lru_page(page); -put: /* is_target_pte_for_mc() gets the page */ +put: /* get_mctgt_type() gets the page */ put_page(page); break; case MC_TARGET_SWAP: @@ -5453,9 +5601,8 @@ retry: up_read(&mm->mmap_sem); } -static void mem_cgroup_move_task(struct cgroup_subsys *ss, - struct cgroup *cont, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup *cont, + struct cgroup_taskset *tset) { struct task_struct *p = cgroup_taskset_first(tset); struct mm_struct *mm = get_task_mm(p); @@ -5470,20 +5617,17 @@ static void mem_cgroup_move_task(struct cgroup_subsys *ss, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys *ss, - struct cgroup *cgroup, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup *cgroup, + struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_subsys *ss, - struct cgroup *cont, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup *cont, + struct cgroup_taskset *tset) { } #endif diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 56080ea..97cc273 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -187,33 +187,40 @@ int hwpoison_filter(struct page *p) EXPORT_SYMBOL_GPL(hwpoison_filter); /* - * Send all the processes who have the page mapped an ``action optional'' - * signal. + * Send all the processes who have the page mapped a signal. + * ``action optional'' if they are not immediately affected by the error + * ``action required'' if error happened in current execution context */ -static int kill_proc_ao(struct task_struct *t, unsigned long addr, int trapno, - unsigned long pfn, struct page *page) +static int kill_proc(struct task_struct *t, unsigned long addr, int trapno, + unsigned long pfn, struct page *page, int flags) { struct siginfo si; int ret; printk(KERN_ERR - "MCE %#lx: Killing %s:%d early due to hardware memory corruption\n", + "MCE %#lx: Killing %s:%d due to hardware memory corruption\n", pfn, t->comm, t->pid); si.si_signo = SIGBUS; si.si_errno = 0; - si.si_code = BUS_MCEERR_AO; si.si_addr = (void *)addr; #ifdef __ARCH_SI_TRAPNO si.si_trapno = trapno; #endif si.si_addr_lsb = compound_trans_order(compound_head(page)) + PAGE_SHIFT; - /* - * Don't use force here, it's convenient if the signal - * can be temporarily blocked. - * This could cause a loop when the user sets SIGBUS - * to SIG_IGN, but hopefully no one will do that? - */ - ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */ + + if ((flags & MF_ACTION_REQUIRED) && t == current) { + si.si_code = BUS_MCEERR_AR; + ret = force_sig_info(SIGBUS, &si, t); + } else { + /* + * Don't use force here, it's convenient if the signal + * can be temporarily blocked. + * This could cause a loop when the user sets SIGBUS + * to SIG_IGN, but hopefully no one will do that? + */ + si.si_code = BUS_MCEERR_AO; + ret = send_sig_info(SIGBUS, &si, t); /* synchronous? */ + } if (ret < 0) printk(KERN_INFO "MCE: Error sending signal to %s:%d: %d\n", t->comm, t->pid, ret); @@ -338,8 +345,9 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, * Also when FAIL is set do a force kill because something went * wrong earlier. */ -static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno, - int fail, struct page *page, unsigned long pfn) +static void kill_procs(struct list_head *to_kill, int doit, int trapno, + int fail, struct page *page, unsigned long pfn, + int flags) { struct to_kill *tk, *next; @@ -363,8 +371,8 @@ static void kill_procs_ao(struct list_head *to_kill, int doit, int trapno, * check for that, but we need to tell the * process anyways. */ - else if (kill_proc_ao(tk->tsk, tk->addr, trapno, - pfn, page) < 0) + else if (kill_proc(tk->tsk, tk->addr, trapno, + pfn, page, flags) < 0) printk(KERN_ERR "MCE %#lx: Cannot send advisory machine check signal to %s:%d\n", pfn, tk->tsk->comm, tk->tsk->pid); @@ -844,7 +852,7 @@ static int page_action(struct page_state *ps, struct page *p, * the pages and send SIGBUS to the processes if the data was dirty. */ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, - int trapno) + int trapno, int flags) { enum ttu_flags ttu = TTU_UNMAP | TTU_IGNORE_MLOCK | TTU_IGNORE_ACCESS; struct address_space *mapping; @@ -962,8 +970,8 @@ static int hwpoison_user_mappings(struct page *p, unsigned long pfn, * use a more force-full uncatchable kill to prevent * any accesses to the poisoned memory. */ - kill_procs_ao(&tokill, !!PageDirty(ppage), trapno, - ret != SWAP_SUCCESS, p, pfn); + kill_procs(&tokill, !!PageDirty(ppage), trapno, + ret != SWAP_SUCCESS, p, pfn, flags); return ret; } @@ -984,7 +992,25 @@ static void clear_page_hwpoison_huge_page(struct page *hpage) ClearPageHWPoison(hpage + i); } -int __memory_failure(unsigned long pfn, int trapno, int flags) +/** + * memory_failure - Handle memory failure of a page. + * @pfn: Page Number of the corrupted page + * @trapno: Trap number reported in the signal to user space. + * @flags: fine tune action taken + * + * This function is called by the low level machine check code + * of an architecture when it detects hardware memory corruption + * of a page. It tries its best to recover, which includes + * dropping pages, killing processes etc. + * + * The function is primarily of use for corruptions that + * happen outside the current execution context (e.g. when + * detected by a background scrubber) + * + * Must run in process context (e.g. a work queue) with interrupts + * enabled and no spinlocks hold. + */ +int memory_failure(unsigned long pfn, int trapno, int flags) { struct page_state *ps; struct page *p; @@ -1063,7 +1089,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * The check (unnecessarily) ignores LRU pages being isolated and * walked by the page reclaim code, however that's not a big loss. */ - if (!PageHuge(p) && !PageTransCompound(p)) { + if (!PageHuge(p) && !PageTransTail(p)) { if (!PageLRU(p)) shake_page(p, 0); if (!PageLRU(p)) { @@ -1130,7 +1156,7 @@ int __memory_failure(unsigned long pfn, int trapno, int flags) * Now take care of user space mappings. * Abort on fail: __delete_from_page_cache() assumes unmapped page. */ - if (hwpoison_user_mappings(p, pfn, trapno) != SWAP_SUCCESS) { + if (hwpoison_user_mappings(p, pfn, trapno, flags) != SWAP_SUCCESS) { printk(KERN_ERR "MCE %#lx: cannot unmap page, give up\n", pfn); res = -EBUSY; goto out; @@ -1156,29 +1182,7 @@ out: unlock_page(hpage); return res; } -EXPORT_SYMBOL_GPL(__memory_failure); - -/** - * memory_failure - Handle memory failure of a page. - * @pfn: Page Number of the corrupted page - * @trapno: Trap number reported in the signal to user space. - * - * This function is called by the low level machine check code - * of an architecture when it detects hardware memory corruption - * of a page. It tries its best to recover, which includes - * dropping pages, killing processes etc. - * - * The function is primarily of use for corruptions that - * happen outside the current execution context (e.g. when - * detected by a background scrubber) - * - * Must run in process context (e.g. a work queue) with interrupts - * enabled and no spinlocks hold. - */ -void memory_failure(unsigned long pfn, int trapno) -{ - __memory_failure(pfn, trapno, 0); -} +EXPORT_SYMBOL_GPL(memory_failure); #define MEMORY_FAILURE_FIFO_ORDER 4 #define MEMORY_FAILURE_FIFO_SIZE (1 << MEMORY_FAILURE_FIFO_ORDER) @@ -1251,7 +1255,7 @@ static void memory_failure_work_func(struct work_struct *work) spin_unlock_irqrestore(&mf_cpu->lock, proc_flags); if (!gotten) break; - __memory_failure(entry.pfn, entry.trapno, entry.flags); + memory_failure(entry.pfn, entry.trapno, entry.flags); } } diff --git a/mm/memory.c b/mm/memory.c index fa2f04e..6105f47 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -125,17 +125,17 @@ core_initcall(init_zero_pfn); #if defined(SPLIT_RSS_COUNTING) -static void __sync_task_rss_stat(struct task_struct *task, struct mm_struct *mm) +void sync_mm_rss(struct mm_struct *mm) { int i; for (i = 0; i < NR_MM_COUNTERS; i++) { - if (task->rss_stat.count[i]) { - add_mm_counter(mm, i, task->rss_stat.count[i]); - task->rss_stat.count[i] = 0; + if (current->rss_stat.count[i]) { + add_mm_counter(mm, i, current->rss_stat.count[i]); + current->rss_stat.count[i] = 0; } } - task->rss_stat.events = 0; + current->rss_stat.events = 0; } static void add_mm_counter_fast(struct mm_struct *mm, int member, int val) @@ -157,30 +157,7 @@ static void check_sync_rss_stat(struct task_struct *task) if (unlikely(task != current)) return; if (unlikely(task->rss_stat.events++ > TASK_RSS_EVENTS_THRESH)) - __sync_task_rss_stat(task, task->mm); -} - -unsigned long get_mm_counter(struct mm_struct *mm, int member) -{ - long val = 0; - - /* - * Don't use task->mm here...for avoiding to use task_get_mm().. - * The caller must guarantee task->mm is not invalid. - */ - val = atomic_long_read(&mm->rss_stat.count[member]); - /* - * counter is updated in asynchronous manner and may go to minus. - * But it's never be expected number for users. - */ - if (val < 0) - return 0; - return (unsigned long)val; -} - -void sync_mm_rss(struct task_struct *task, struct mm_struct *mm) -{ - __sync_task_rss_stat(task, mm); + sync_mm_rss(task->mm); } #else /* SPLIT_RSS_COUNTING */ @@ -661,7 +638,7 @@ static inline void add_mm_rss_vec(struct mm_struct *mm, int *rss) int i; if (current->mm == mm) - sync_mm_rss(current, mm); + sync_mm_rss(mm); for (i = 0; i < NR_MM_COUNTERS; i++) if (rss[i]) add_mm_counter(mm, i, rss[i]); @@ -1247,16 +1224,24 @@ static inline unsigned long zap_pmd_range(struct mmu_gather *tlb, do { next = pmd_addr_end(addr, end); if (pmd_trans_huge(*pmd)) { - if (next-addr != HPAGE_PMD_SIZE) { + if (next - addr != HPAGE_PMD_SIZE) { VM_BUG_ON(!rwsem_is_locked(&tlb->mm->mmap_sem)); split_huge_page_pmd(vma->vm_mm, pmd); } else if (zap_huge_pmd(tlb, vma, pmd, addr)) - continue; + goto next; /* fall through */ } - if (pmd_none_or_clear_bad(pmd)) - continue; + /* + * Here there can be other concurrent MADV_DONTNEED or + * trans huge page faults running, and if the pmd is + * none or trans huge it can change under us. This is + * because MADV_DONTNEED holds the mmap_sem in read + * mode. + */ + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) + goto next; next = zap_pte_range(tlb, vma, pmd, addr, next, details); +next: cond_resched(); } while (pmd++, addr = next, addr != end); @@ -1282,10 +1267,10 @@ static inline unsigned long zap_pud_range(struct mmu_gather *tlb, return addr; } -static unsigned long unmap_page_range(struct mmu_gather *tlb, - struct vm_area_struct *vma, - unsigned long addr, unsigned long end, - struct zap_details *details) +static void unmap_page_range(struct mmu_gather *tlb, + struct vm_area_struct *vma, + unsigned long addr, unsigned long end, + struct zap_details *details) { pgd_t *pgd; unsigned long next; @@ -1305,8 +1290,47 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, } while (pgd++, addr = next, addr != end); tlb_end_vma(tlb, vma); mem_cgroup_uncharge_end(); +} - return addr; + +static void unmap_single_vma(struct mmu_gather *tlb, + struct vm_area_struct *vma, unsigned long start_addr, + unsigned long end_addr, unsigned long *nr_accounted, + struct zap_details *details) +{ + unsigned long start = max(vma->vm_start, start_addr); + unsigned long end; + + if (start >= vma->vm_end) + return; + end = min(vma->vm_end, end_addr); + if (end <= vma->vm_start) + return; + + if (vma->vm_flags & VM_ACCOUNT) + *nr_accounted += (end - start) >> PAGE_SHIFT; + + if (unlikely(is_pfn_mapping(vma))) + untrack_pfn_vma(vma, 0, 0); + + if (start != end) { + if (unlikely(is_vm_hugetlb_page(vma))) { + /* + * It is undesirable to test vma->vm_file as it + * should be non-null for valid hugetlb area. + * However, vm_file will be NULL in the error + * cleanup path of do_mmap_pgoff. When + * hugetlbfs ->mmap method fails, + * do_mmap_pgoff() nullifies vma->vm_file + * before calling this function to clean up. + * Since no pte has actually been setup, it is + * safe to do nothing in this case. + */ + if (vma->vm_file) + unmap_hugepage_range(vma, start, end, NULL); + } else + unmap_page_range(tlb, vma, start, end, details); + } } /** @@ -1318,8 +1342,6 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, * @nr_accounted: Place number of unmapped pages in vm-accountable vma's here * @details: details of nonlinear truncation or shared cache invalidation * - * Returns the end address of the unmapping (restart addr if interrupted). - * * Unmap all pages in the vma list. * * Only addresses between `start' and `end' will be unmapped. @@ -1331,55 +1353,18 @@ static unsigned long unmap_page_range(struct mmu_gather *tlb, * ensure that any thus-far unmapped pages are flushed before unmap_vmas() * drops the lock and schedules. */ -unsigned long unmap_vmas(struct mmu_gather *tlb, +void unmap_vmas(struct mmu_gather *tlb, struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, unsigned long *nr_accounted, struct zap_details *details) { - unsigned long start = start_addr; struct mm_struct *mm = vma->vm_mm; mmu_notifier_invalidate_range_start(mm, start_addr, end_addr); - for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) { - unsigned long end; - - start = max(vma->vm_start, start_addr); - if (start >= vma->vm_end) - continue; - end = min(vma->vm_end, end_addr); - if (end <= vma->vm_start) - continue; - - if (vma->vm_flags & VM_ACCOUNT) - *nr_accounted += (end - start) >> PAGE_SHIFT; - - if (unlikely(is_pfn_mapping(vma))) - untrack_pfn_vma(vma, 0, 0); - - while (start != end) { - if (unlikely(is_vm_hugetlb_page(vma))) { - /* - * It is undesirable to test vma->vm_file as it - * should be non-null for valid hugetlb area. - * However, vm_file will be NULL in the error - * cleanup path of do_mmap_pgoff. When - * hugetlbfs ->mmap method fails, - * do_mmap_pgoff() nullifies vma->vm_file - * before calling this function to clean up. - * Since no pte has actually been setup, it is - * safe to do nothing in this case. - */ - if (vma->vm_file) - unmap_hugepage_range(vma, start, end, NULL); - - start = end; - } else - start = unmap_page_range(tlb, vma, start, end, details); - } - } - + for ( ; vma && vma->vm_start < end_addr; vma = vma->vm_next) + unmap_single_vma(tlb, vma, start_addr, end_addr, nr_accounted, + details); mmu_notifier_invalidate_range_end(mm, start_addr, end_addr); - return start; /* which is now the end (or restart) address */ } /** @@ -1388,8 +1373,10 @@ unsigned long unmap_vmas(struct mmu_gather *tlb, * @address: starting address of pages to zap * @size: number of bytes to zap * @details: details of nonlinear truncation or shared cache invalidation + * + * Caller must protect the VMA list */ -unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, +void zap_page_range(struct vm_area_struct *vma, unsigned long address, unsigned long size, struct zap_details *details) { struct mm_struct *mm = vma->vm_mm; @@ -1400,9 +1387,34 @@ unsigned long zap_page_range(struct vm_area_struct *vma, unsigned long address, lru_add_drain(); tlb_gather_mmu(&tlb, mm, 0); update_hiwater_rss(mm); - end = unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); + unmap_vmas(&tlb, vma, address, end, &nr_accounted, details); + tlb_finish_mmu(&tlb, address, end); +} + +/** + * zap_page_range_single - remove user pages in a given range + * @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 + * + * The range must fit into one VMA. + */ +static void zap_page_range_single(struct vm_area_struct *vma, unsigned long address, + unsigned long size, struct zap_details *details) +{ + struct mm_struct *mm = vma->vm_mm; + struct mmu_gather tlb; + unsigned long end = address + size; + unsigned long nr_accounted = 0; + + lru_add_drain(); + tlb_gather_mmu(&tlb, mm, 0); + update_hiwater_rss(mm); + mmu_notifier_invalidate_range_start(mm, address, end); + unmap_single_vma(&tlb, vma, address, end, &nr_accounted, details); + mmu_notifier_invalidate_range_end(mm, address, end); tlb_finish_mmu(&tlb, address, end); - return end; } /** @@ -1423,7 +1435,7 @@ int zap_vma_ptes(struct vm_area_struct *vma, unsigned long address, if (address < vma->vm_start || address + size > vma->vm_end || !(vma->vm_flags & VM_PFNMAP)) return -1; - zap_page_range(vma, address, size, NULL); + zap_page_range_single(vma, address, size, NULL); return 0; } EXPORT_SYMBOL_GPL(zap_vma_ptes); @@ -2447,7 +2459,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo * fails, we just zero-fill it. Live with it. */ if (unlikely(!src)) { - void *kaddr = kmap_atomic(dst, KM_USER0); + void *kaddr = kmap_atomic(dst); void __user *uaddr = (void __user *)(va & PAGE_MASK); /* @@ -2458,7 +2470,7 @@ static inline void cow_user_page(struct page *dst, struct page *src, unsigned lo */ if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) clear_page(kaddr); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); flush_dcache_page(dst); } else copy_user_highpage(dst, src, va, vma); @@ -2770,7 +2782,7 @@ static void unmap_mapping_range_vma(struct vm_area_struct *vma, unsigned long start_addr, unsigned long end_addr, struct zap_details *details) { - zap_page_range(vma, start_addr, end_addr - start_addr, details); + zap_page_range_single(vma, start_addr, end_addr - start_addr, details); } static inline void unmap_mapping_range_tree(struct prio_tree_root *root, @@ -3611,13 +3623,7 @@ static int __init gate_vma_init(void) gate_vma.vm_end = FIXADDR_USER_END; gate_vma.vm_flags = VM_READ | VM_MAYREAD | VM_EXEC | VM_MAYEXEC; gate_vma.vm_page_prot = __P101; - /* - * Make sure the vDSO gets into every core dump. - * Dumping its contents makes post-mortem fully interpretable later - * without matching up the same kernel and hardware config to see - * what PC values meant. - */ - gate_vma.vm_flags |= VM_ALWAYSDUMP; + return 0; } __initcall(gate_vma_init); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 06b145fb..cfb6c86 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -512,7 +512,7 @@ static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud, do { next = pmd_addr_end(addr, end); split_huge_page_pmd(vma->vm_mm, pmd); - if (pmd_none_or_clear_bad(pmd)) + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; if (check_pte_range(vma, pmd, addr, next, nodes, flags, private)) @@ -640,10 +640,11 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long vmstart; unsigned long vmend; - vma = find_vma_prev(mm, start, &prev); + vma = find_vma(mm, start); if (!vma || vma->vm_start > start) return -EFAULT; + prev = vma->vm_prev; if (start > vma->vm_start) prev = vma; @@ -1322,12 +1323,9 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, err = -ESRCH; goto out; } - mm = get_task_mm(task); - rcu_read_unlock(); + get_task_struct(task); err = -EINVAL; - if (!mm) - goto out; /* * Check if this process has the right to modify the specified @@ -1335,14 +1333,13 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, * capabilities, superuser privileges or the same * userid as the target process. */ - rcu_read_lock(); tcred = __task_cred(task); if (cred->euid != tcred->suid && cred->euid != tcred->uid && cred->uid != tcred->suid && cred->uid != tcred->uid && !capable(CAP_SYS_NICE)) { rcu_read_unlock(); err = -EPERM; - goto out; + goto out_put; } rcu_read_unlock(); @@ -1350,26 +1347,36 @@ SYSCALL_DEFINE4(migrate_pages, pid_t, pid, unsigned long, maxnode, /* Is the user allowed to access the target nodes? */ if (!nodes_subset(*new, task_nodes) && !capable(CAP_SYS_NICE)) { err = -EPERM; - goto out; + goto out_put; } if (!nodes_subset(*new, node_states[N_HIGH_MEMORY])) { err = -EINVAL; - goto out; + goto out_put; } err = security_task_movememory(task); if (err) - goto out; + goto out_put; - err = do_migrate_pages(mm, old, new, - capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); -out: + mm = get_task_mm(task); + put_task_struct(task); if (mm) - mmput(mm); + err = do_migrate_pages(mm, old, new, + capable(CAP_SYS_NICE) ? MPOL_MF_MOVE_ALL : MPOL_MF_MOVE); + else + err = -EINVAL; + + mmput(mm); +out: NODEMASK_SCRATCH_FREE(scratch); return err; + +out_put: + put_task_struct(task); + goto out; + } @@ -1843,18 +1850,24 @@ struct page * alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, unsigned long addr, int node) { - struct mempolicy *pol = get_vma_policy(current, vma, addr); + struct mempolicy *pol; struct zonelist *zl; struct page *page; + unsigned int cpuset_mems_cookie; + +retry_cpuset: + pol = get_vma_policy(current, vma, addr); + cpuset_mems_cookie = get_mems_allowed(); - get_mems_allowed(); if (unlikely(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); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; + return page; } zl = policy_zonelist(gfp, pol, node); @@ -1865,7 +1878,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, struct page *page = __alloc_pages_nodemask(gfp, order, zl, policy_nodemask(gfp, pol)); __mpol_put(pol); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; return page; } /* @@ -1873,7 +1887,8 @@ alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma, */ page = __alloc_pages_nodemask(gfp, order, zl, policy_nodemask(gfp, pol)); - put_mems_allowed(); + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; return page; } @@ -1900,11 +1915,14 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) { struct mempolicy *pol = current->mempolicy; struct page *page; + unsigned int cpuset_mems_cookie; if (!pol || in_interrupt() || (gfp & __GFP_THISNODE)) pol = &default_policy; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + /* * No reference counting needed for current->mempolicy * nor system default_policy @@ -1915,7 +1933,10 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order) page = __alloc_pages_nodemask(gfp, order, policy_zonelist(gfp, pol, numa_node_id()), policy_nodemask(gfp, pol)); - put_mems_allowed(); + + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; + return page; } EXPORT_SYMBOL(alloc_pages_current); diff --git a/mm/migrate.c b/mm/migrate.c index 9871a56..51c08a0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -445,7 +445,6 @@ void migrate_page_copy(struct page *newpage, struct page *page) ClearPageSwapCache(page); ClearPagePrivate(page); set_page_private(page, 0); - page->mapping = NULL; /* * If any waiters have accumulated on the new page then @@ -667,6 +666,7 @@ static int move_to_new_page(struct page *newpage, struct page *page, } else { if (remap_swapcache) remove_migration_ptes(page, newpage); + page->mapping = NULL; } unlock_page(newpage); @@ -839,8 +839,6 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, if (!newpage) return -ENOMEM; - mem_cgroup_reset_owner(newpage); - if (page_count(page) == 1) { /* page was freed from under us. So we are done. */ goto out; @@ -1176,20 +1174,17 @@ set_status: * Migrate an array of page address onto an array of nodes and fill * the corresponding array of status. */ -static int do_pages_move(struct mm_struct *mm, struct task_struct *task, +static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, unsigned long nr_pages, const void __user * __user *pages, const int __user *nodes, int __user *status, int flags) { struct page_to_node *pm; - nodemask_t task_nodes; unsigned long chunk_nr_pages; unsigned long chunk_start; int err; - task_nodes = cpuset_mems_allowed(task); - err = -ENOMEM; pm = (struct page_to_node *)__get_free_page(GFP_KERNEL); if (!pm) @@ -1351,6 +1346,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, struct task_struct *task; struct mm_struct *mm; int err; + nodemask_t task_nodes; /* Check flags */ if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) @@ -1366,11 +1362,7 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, rcu_read_unlock(); return -ESRCH; } - mm = get_task_mm(task); - rcu_read_unlock(); - - if (!mm) - return -EINVAL; + get_task_struct(task); /* * Check if this process has the right to modify the specified @@ -1378,7 +1370,6 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, * capabilities, superuser privileges or the same * userid as the target process. */ - rcu_read_lock(); tcred = __task_cred(task); if (cred->euid != tcred->suid && cred->euid != tcred->uid && cred->uid != tcred->suid && cred->uid != tcred->uid && @@ -1393,16 +1384,25 @@ SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, if (err) goto out; - if (nodes) { - err = do_pages_move(mm, task, nr_pages, pages, nodes, status, - flags); - } else { - err = do_pages_stat(mm, nr_pages, pages, status); - } + task_nodes = cpuset_mems_allowed(task); + mm = get_task_mm(task); + put_task_struct(task); + + if (mm) { + if (nodes) + err = do_pages_move(mm, task_nodes, nr_pages, pages, + nodes, status, flags); + else + err = do_pages_stat(mm, nr_pages, pages, status); + } else + err = -EINVAL; -out: mmput(mm); return err; + +out: + put_task_struct(task); + return err; } /* diff --git a/mm/mincore.c b/mm/mincore.c index 636a868..936b4ce 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -164,7 +164,7 @@ static void mincore_pmd_range(struct vm_area_struct *vma, pud_t *pud, } /* fall through */ } - if (pmd_none_or_clear_bad(pmd)) + 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); @@ -385,10 +385,11 @@ static int do_mlock(unsigned long start, size_t len, int on) return -EINVAL; if (end == start) return 0; - vma = find_vma_prev(current->mm, start, &prev); + vma = find_vma(current->mm, start); if (!vma || vma->vm_start > start) return -ENOMEM; + prev = vma->vm_prev; if (start > vma->vm_start) prev = vma; @@ -451,9 +451,8 @@ static void vma_link(struct mm_struct *mm, struct vm_area_struct *vma, } /* - * Helper for vma_adjust in the split_vma insert case: - * insert vm structure into list and rbtree and anon_vma, - * but it has already been inserted into prio_tree earlier. + * Helper for vma_adjust() in the split_vma insert case: insert a vma into the + * mm's list and rbtree. It has already been inserted into the prio_tree. */ static void __insert_vm_struct(struct mm_struct *mm, struct vm_area_struct *vma) { @@ -936,6 +935,19 @@ void vm_stat_account(struct mm_struct *mm, unsigned long flags, #endif /* CONFIG_PROC_FS */ /* + * If a hint addr is less than mmap_min_addr change hint to be as + * low as possible but still greater than mmap_min_addr + */ +static inline unsigned long round_hint_to_min(unsigned long hint) +{ + hint &= PAGE_MASK; + if (((void *)hint != NULL) && + (hint < mmap_min_addr)) + return PAGE_ALIGN(mmap_min_addr); + return hint; +} + +/* * The caller must hold down_write(¤t->mm->mmap_sem). */ @@ -1099,9 +1111,9 @@ SYSCALL_DEFINE6(mmap_pgoff, unsigned long, addr, unsigned long, len, * A dummy user value is used because we are not locking * memory so no accounting is necessary */ - len = ALIGN(len, huge_page_size(&default_hstate)); - file = hugetlb_file_setup(HUGETLB_ANON_FILE, len, VM_NORESERVE, - &user, HUGETLB_ANONHUGE_INODE); + file = hugetlb_file_setup(HUGETLB_ANON_FILE, addr, len, + VM_NORESERVE, &user, + HUGETLB_ANONHUGE_INODE); if (IS_ERR(file)) return PTR_ERR(file); } @@ -1235,7 +1247,7 @@ munmap_back: */ if (accountable_mapping(file, vm_flags)) { charged = len >> PAGE_SHIFT; - if (security_vm_enough_memory(charged)) + if (security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; vm_flags |= VM_ACCOUNT; } @@ -1266,8 +1278,9 @@ munmap_back: vma->vm_pgoff = pgoff; INIT_LIST_HEAD(&vma->anon_vma_chain); + error = -EINVAL; /* when rejecting VM_GROWSDOWN|VM_GROWSUP */ + if (file) { - error = -EINVAL; if (vm_flags & (VM_GROWSDOWN|VM_GROWSUP)) goto free_vma; if (vm_flags & VM_DENYWRITE) { @@ -1293,6 +1306,8 @@ munmap_back: pgoff = vma->vm_pgoff; vm_flags = vma->vm_flags; } else if (vm_flags & VM_SHARED) { + if (unlikely(vm_flags & (VM_GROWSDOWN|VM_GROWSUP))) + goto free_vma; error = shmem_zero_setup(vma); if (error) goto free_vma; @@ -1423,10 +1438,8 @@ void arch_unmap_area(struct mm_struct *mm, unsigned long addr) /* * Is this a new hole at the lowest possible address? */ - if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) { + if (addr >= TASK_UNMAPPED_BASE && addr < mm->free_area_cache) mm->free_area_cache = addr; - mm->cached_hole_size = ~0UL; - } } /* @@ -1441,7 +1454,7 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, { struct vm_area_struct *vma; struct mm_struct *mm = current->mm; - unsigned long addr = addr0; + unsigned long addr = addr0, start_addr; /* requested length too big for entire address space */ if (len > TASK_SIZE) @@ -1465,22 +1478,14 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, mm->free_area_cache = mm->mmap_base; } +try_again: /* either no address requested or can't fit in requested address hole */ - addr = mm->free_area_cache; - - /* make sure it can fit in the remaining address space */ - if (addr > len) { - vma = find_vma(mm, addr-len); - if (!vma || addr <= vma->vm_start) - /* remember the address as a hint for next time */ - return (mm->free_area_cache = addr-len); - } + start_addr = addr = mm->free_area_cache; - if (mm->mmap_base < len) - goto bottomup; - - addr = mm->mmap_base-len; + if (addr < len) + goto fail; + addr -= len; do { /* * Lookup failure means no vma is above this address, @@ -1500,7 +1505,21 @@ arch_get_unmapped_area_topdown(struct file *filp, const unsigned long addr0, addr = vma->vm_start-len; } while (len < vma->vm_start); -bottomup: +fail: + /* + * if hint left us with no space for the requested + * mapping then try again: + * + * Note: this is different with the case of bottomup + * which does the fully line-search, but we use find_vma + * here that causes some holes skipped. + */ + if (start_addr != mm->mmap_base) { + mm->free_area_cache = mm->mmap_base; + mm->cached_hole_size = 0; + goto try_again; + } + /* * A failed mmap() very likely causes application failure, * so fall back to the bottom-up function here. This scenario @@ -1605,7 +1624,6 @@ EXPORT_SYMBOL(find_vma); /* * Same as find_vma, but also return a pointer to the previous VMA in *pprev. - * Note: pprev is set to NULL when return value is NULL. */ struct vm_area_struct * find_vma_prev(struct mm_struct *mm, unsigned long addr, @@ -1614,7 +1632,16 @@ find_vma_prev(struct mm_struct *mm, unsigned long addr, struct vm_area_struct *vma; vma = find_vma(mm, addr); - *pprev = vma ? vma->vm_prev : NULL; + if (vma) { + *pprev = vma->vm_prev; + } else { + struct rb_node *rb_node = mm->mm_rb.rb_node; + *pprev = NULL; + while (rb_node) { + *pprev = rb_entry(rb_node, struct vm_area_struct, vm_rb); + rb_node = rb_node->rb_right; + } + } return vma; } @@ -2169,7 +2196,7 @@ unsigned long do_brk(unsigned long addr, unsigned long len) if (mm->map_count > sysctl_max_map_count) return -ENOMEM; - if (security_vm_enough_memory(len >> PAGE_SHIFT)) + if (security_vm_enough_memory_mm(mm, len >> PAGE_SHIFT)) return -ENOMEM; /* Can we just expand an old private anonymous mapping? */ @@ -2213,7 +2240,6 @@ void exit_mmap(struct mm_struct *mm) struct mmu_gather tlb; struct vm_area_struct *vma; unsigned long nr_accounted = 0; - unsigned long end; /* mm's last user has gone, and its about to be pulled down */ mmu_notifier_release(mm); @@ -2238,11 +2264,11 @@ void exit_mmap(struct mm_struct *mm) tlb_gather_mmu(&tlb, mm, 1); /* update_hiwater_rss(mm) here? but nobody should be looking */ /* Use -1 here to ensure all VMAs in the mm are unmapped */ - end = unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL); + unmap_vmas(&tlb, vma, 0, -1, &nr_accounted, NULL); vm_unacct_memory(nr_accounted); free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); - tlb_finish_mmu(&tlb, 0, end); + tlb_finish_mmu(&tlb, 0, -1); /* * Walk the list again, actually closing and freeing it, diff --git a/mm/mmu_context.c b/mm/mmu_context.c index cf332bc..3dcfaf4 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -53,7 +53,7 @@ void unuse_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); - sync_mm_rss(tsk, mm); + sync_mm_rss(mm); tsk->mm = NULL; /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); diff --git a/mm/mprotect.c b/mm/mprotect.c index 5a688a2..a409926 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -60,7 +60,7 @@ static void change_pte_range(struct mm_struct *mm, pmd_t *pmd, ptent = pte_mkwrite(ptent); ptep_modify_prot_commit(mm, addr, pte, ptent); - } else if (PAGE_MIGRATION && !pte_file(oldpte)) { + } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { @@ -168,7 +168,7 @@ mprotect_fixup(struct vm_area_struct *vma, struct vm_area_struct **pprev, if (!(oldflags & (VM_ACCOUNT|VM_WRITE|VM_HUGETLB| VM_SHARED|VM_NORESERVE))) { charged = nrpages; - if (security_vm_enough_memory(charged)) + if (security_vm_enough_memory_mm(mm, charged)) return -ENOMEM; newflags |= VM_ACCOUNT; } @@ -262,10 +262,11 @@ SYSCALL_DEFINE3(mprotect, unsigned long, start, size_t, len, down_write(¤t->mm->mmap_sem); - vma = find_vma_prev(current->mm, start, &prev); + vma = find_vma(current->mm, start); error = -ENOMEM; if (!vma) goto out; + prev = vma->vm_prev; if (unlikely(grows & PROT_GROWSDOWN)) { if (vma->vm_start >= end) goto out; diff --git a/mm/mremap.c b/mm/mremap.c index 87bb839..db8d983 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -329,7 +329,7 @@ static struct vm_area_struct *vma_to_resize(unsigned long addr, if (vma->vm_flags & VM_ACCOUNT) { unsigned long charged = (new_len - old_len) >> PAGE_SHIFT; - if (security_vm_enough_memory(charged)) + if (security_vm_enough_memory_mm(mm, charged)) goto Efault; *p = charged; } @@ -696,9 +696,11 @@ static void add_vma_to_mm(struct mm_struct *mm, struct vm_area_struct *vma) if (vma->vm_file) { mapping = vma->vm_file->f_mapping; + mutex_lock(&mapping->i_mmap_mutex); flush_dcache_mmap_lock(mapping); vma_prio_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); + mutex_unlock(&mapping->i_mmap_mutex); } /* add the VMA to the tree */ @@ -760,9 +762,11 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) if (vma->vm_file) { mapping = vma->vm_file->f_mapping; + mutex_lock(&mapping->i_mmap_mutex); flush_dcache_mmap_lock(mapping); vma_prio_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); + mutex_unlock(&mapping->i_mmap_mutex); } /* remove from the MM's tree and list */ @@ -775,8 +779,6 @@ static void delete_vma_from_mm(struct vm_area_struct *vma) if (vma->vm_next) vma->vm_next->vm_prev = vma->vm_prev; - - vma->vm_mm = NULL; } /* @@ -2052,6 +2054,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, high = (size + PAGE_SIZE - 1) >> PAGE_SHIFT; down_write(&nommu_region_sem); + mutex_lock(&inode->i_mapping->i_mmap_mutex); /* search for VMAs that fall within the dead zone */ vma_prio_tree_foreach(vma, &iter, &inode->i_mapping->i_mmap, @@ -2059,6 +2062,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, /* found one - only interested if it's shared out of the page * cache */ if (vma->vm_flags & VM_SHARED) { + mutex_unlock(&inode->i_mapping->i_mmap_mutex); up_write(&nommu_region_sem); return -ETXTBSY; /* not quite true, but near enough */ } @@ -2086,6 +2090,7 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, } } + mutex_unlock(&inode->i_mapping->i_mmap_mutex); up_write(&nommu_region_sem); return 0; } diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 2958fd8..46bf2ed5 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -34,6 +34,7 @@ #include <linux/ptrace.h> #include <linux/freezer.h> #include <linux/ftrace.h> +#include <linux/ratelimit.h> #define CREATE_TRACE_POINTS #include <trace/events/oom.h> @@ -309,7 +310,7 @@ static enum oom_constraint constrained_alloc(struct zonelist *zonelist, */ static struct task_struct *select_bad_process(unsigned int *ppoints, unsigned long totalpages, struct mem_cgroup *memcg, - const nodemask_t *nodemask) + const nodemask_t *nodemask, bool force_kill) { struct task_struct *g, *p; struct task_struct *chosen = NULL; @@ -335,7 +336,8 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, if (test_tsk_thread_flag(p, TIF_MEMDIE)) { if (unlikely(frozen(p))) __thaw_task(p); - return ERR_PTR(-1UL); + if (!force_kill) + return ERR_PTR(-1UL); } if (!p->mm) continue; @@ -353,7 +355,7 @@ static struct task_struct *select_bad_process(unsigned int *ppoints, if (p == current) { chosen = p; *ppoints = 1000; - } else { + } else if (!force_kill) { /* * If this task is not being ptraced on exit, * then wait for it to finish before killing @@ -434,66 +436,18 @@ static void dump_header(struct task_struct *p, gfp_t gfp_mask, int order, } #define K(x) ((x) << (PAGE_SHIFT-10)) -static int oom_kill_task(struct task_struct *p) -{ - struct task_struct *q; - struct mm_struct *mm; - - p = find_lock_task_mm(p); - if (!p) - return 1; - - /* mm cannot be safely dereferenced after task_unlock(p) */ - mm = p->mm; - - pr_err("Killed process %d (%s) total-vm:%lukB, anon-rss:%lukB, file-rss:%lukB\n", - task_pid_nr(p), p->comm, K(p->mm->total_vm), - K(get_mm_counter(p->mm, MM_ANONPAGES)), - K(get_mm_counter(p->mm, MM_FILEPAGES))); - task_unlock(p); - - /* - * Kill all user processes sharing p->mm in other thread groups, if any. - * They don't get access to memory reserves or a higher scheduler - * priority, though, to avoid depletion of all memory or task - * starvation. This prevents mm->mmap_sem livelock when an oom killed - * task cannot exit because it requires the semaphore and its contended - * by another thread trying to allocate memory itself. That thread will - * now get access to memory reserves since it has a pending fatal - * signal. - */ - for_each_process(q) - if (q->mm == mm && !same_thread_group(q, p) && - !(q->flags & PF_KTHREAD)) { - if (q->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) - continue; - - task_lock(q); /* Protect ->comm from prctl() */ - pr_err("Kill process %d (%s) sharing same memory\n", - task_pid_nr(q), q->comm); - task_unlock(q); - force_sig(SIGKILL, q); - } - - set_tsk_thread_flag(p, TIF_MEMDIE); - force_sig(SIGKILL, p); - - return 0; -} -#undef K - -static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, - unsigned int points, unsigned long totalpages, - struct mem_cgroup *memcg, nodemask_t *nodemask, - const char *message) +static void oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, + unsigned int points, unsigned long totalpages, + struct mem_cgroup *memcg, nodemask_t *nodemask, + const char *message) { struct task_struct *victim = p; struct task_struct *child; struct task_struct *t = p; + struct mm_struct *mm; unsigned int victim_points = 0; - - if (printk_ratelimit()) - dump_header(p, gfp_mask, order, memcg, nodemask); + static DEFINE_RATELIMIT_STATE(oom_rs, DEFAULT_RATELIMIT_INTERVAL, + DEFAULT_RATELIMIT_BURST); /* * If the task is already exiting, don't alarm the sysadmin or kill @@ -501,9 +455,12 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ if (p->flags & PF_EXITING) { set_tsk_thread_flag(p, TIF_MEMDIE); - return 0; + return; } + if (__ratelimit(&oom_rs)) + dump_header(p, gfp_mask, order, memcg, nodemask); + task_lock(p); pr_err("%s: Kill process %d (%s) score %d or sacrifice child\n", message, task_pid_nr(p), p->comm, points); @@ -533,8 +490,44 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, } } while_each_thread(p, t); - return oom_kill_task(victim); + victim = find_lock_task_mm(victim); + if (!victim) + return; + + /* mm cannot safely be dereferenced after task_unlock(victim) */ + mm = victim->mm; + 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)), + K(get_mm_counter(victim->mm, MM_FILEPAGES))); + task_unlock(victim); + + /* + * Kill all user processes sharing victim->mm in other thread groups, if + * any. They don't get access to memory reserves, though, to avoid + * depletion of all memory. This prevents mm->mmap_sem livelock when an + * oom killed thread cannot exit because it requires the semaphore and + * its contended by another thread trying to allocate memory itself. + * That thread will now get access to memory reserves since it has a + * pending fatal signal. + */ + for_each_process(p) + if (p->mm == mm && !same_thread_group(p, victim) && + !(p->flags & PF_KTHREAD)) { + if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) + continue; + + task_lock(p); /* Protect ->comm from prctl() */ + pr_err("Kill process %d (%s) sharing same memory\n", + task_pid_nr(p), p->comm); + task_unlock(p); + do_send_sig_info(SIGKILL, SEND_SIG_FORCED, p, true); + } + + set_tsk_thread_flag(victim, TIF_MEMDIE); + do_send_sig_info(SIGKILL, SEND_SIG_FORCED, victim, true); } +#undef K /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. @@ -561,7 +554,8 @@ static void check_panic_on_oom(enum oom_constraint constraint, gfp_t gfp_mask, } #ifdef CONFIG_CGROUP_MEM_RES_CTLR -void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask) +void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, + int order) { unsigned long limit; unsigned int points = 0; @@ -577,18 +571,13 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask) return; } - check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, 0, NULL); + check_panic_on_oom(CONSTRAINT_MEMCG, gfp_mask, order, NULL); limit = mem_cgroup_get_limit(memcg) >> PAGE_SHIFT; read_lock(&tasklist_lock); -retry: - p = select_bad_process(&points, limit, memcg, NULL); - if (!p || PTR_ERR(p) == -1UL) - goto out; - - if (oom_kill_process(p, gfp_mask, 0, points, limit, memcg, NULL, - "Memory cgroup out of memory")) - goto retry; -out: + p = select_bad_process(&points, limit, memcg, NULL, false); + if (p && PTR_ERR(p) != -1UL) + oom_kill_process(p, gfp_mask, order, points, limit, memcg, NULL, + "Memory cgroup out of memory"); read_unlock(&tasklist_lock); } #endif @@ -700,6 +689,7 @@ static void clear_system_oom(void) * @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 * * If we run out of memory, we have the choice between either * killing a random task (bad), letting the system crash (worse) @@ -707,7 +697,7 @@ static void clear_system_oom(void) * don't have to be perfect here, we just have to be good. */ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, - int order, nodemask_t *nodemask) + int order, nodemask_t *nodemask, bool force_kill) { const nodemask_t *mpol_mask; struct task_struct *p; @@ -745,33 +735,25 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, if (sysctl_oom_kill_allocating_task && !oom_unkillable_task(current, NULL, nodemask) && current->mm) { - /* - * oom_kill_process() needs tasklist_lock held. If it returns - * non-zero, current could not be killed so we must fallback to - * the tasklist scan. - */ - if (!oom_kill_process(current, gfp_mask, order, 0, totalpages, - NULL, nodemask, - "Out of memory (oom_kill_allocating_task)")) - goto out; - } - -retry: - p = select_bad_process(&points, totalpages, NULL, mpol_mask); - if (PTR_ERR(p) == -1UL) + oom_kill_process(current, gfp_mask, order, 0, totalpages, NULL, + nodemask, + "Out of memory (oom_kill_allocating_task)"); goto out; + } + p = select_bad_process(&points, totalpages, NULL, mpol_mask, + force_kill); /* Found nothing?!?! Either we hang forever, or we panic. */ if (!p) { dump_header(NULL, gfp_mask, order, NULL, mpol_mask); read_unlock(&tasklist_lock); panic("Out of memory and no killable processes...\n"); } - - if (oom_kill_process(p, gfp_mask, order, points, totalpages, NULL, - nodemask, "Out of memory")) - goto retry; - killed = 1; + if (PTR_ERR(p) != -1UL) { + oom_kill_process(p, gfp_mask, order, points, totalpages, NULL, + nodemask, "Out of memory"); + killed = 1; + } out: read_unlock(&tasklist_lock); @@ -792,7 +774,7 @@ out: void pagefault_out_of_memory(void) { if (try_set_system_oom()) { - out_of_memory(NULL, 0, 0, NULL); + out_of_memory(NULL, 0, 0, NULL, false); clear_system_oom(); } if (!test_thread_flag(TIF_MEMDIE)) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 363ba70..26adea8 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -95,6 +95,8 @@ unsigned long vm_dirty_bytes; */ unsigned int dirty_writeback_interval = 5 * 100; /* centiseconds */ +EXPORT_SYMBOL_GPL(dirty_writeback_interval); + /* * The longest time for which data is allowed to remain dirty */ @@ -1472,6 +1474,7 @@ void throttle_vm_writeout(gfp_t gfp_mask) for ( ; ; ) { global_dirty_limits(&background_thresh, &dirty_thresh); + dirty_thresh = hard_dirty_limit(dirty_thresh); /* * Boost the allowable dirty threshold a bit for page diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d2186ec..a712fb9 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1161,11 +1161,47 @@ void drain_local_pages(void *arg) } /* - * Spill all the per-cpu pages from all CPUs back into the buddy allocator + * Spill all the per-cpu pages from all CPUs back into the buddy allocator. + * + * Note that this code is protected against sending an IPI to an offline + * CPU but does not guarantee sending an IPI to newly hotplugged CPUs: + * on_each_cpu_mask() blocks hotplug and won't talk to offlined CPUs but + * nothing keeps CPUs from showing up after we populated the cpumask and + * before the call to on_each_cpu_mask(). */ void drain_all_pages(void) { - on_each_cpu(drain_local_pages, NULL, 1); + int cpu; + struct per_cpu_pageset *pcp; + struct zone *zone; + + /* + * Allocate in the BSS so we wont require allocation in + * direct reclaim path for CONFIG_CPUMASK_OFFSTACK=y + */ + static cpumask_t cpus_with_pcps; + + /* + * We don't care about racing with CPU hotplug event + * as offline notification will cause the notified + * cpu to drain that CPU pcps and on_each_cpu_mask + * disables preemption as part of its processing + */ + for_each_online_cpu(cpu) { + bool has_pcps = false; + for_each_populated_zone(zone) { + pcp = per_cpu_ptr(zone->pageset, cpu); + if (pcp->pcp.count) { + has_pcps = true; + break; + } + } + if (has_pcps) + cpumask_set_cpu(cpu, &cpus_with_pcps); + else + cpumask_clear_cpu(cpu, &cpus_with_pcps); + } + on_each_cpu_mask(&cpus_with_pcps, drain_local_pages, NULL, 1); } #ifdef CONFIG_HIBERNATION @@ -1968,7 +2004,7 @@ __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); + out_of_memory(zonelist, gfp_mask, order, nodemask, false); out: clear_zonelist_oom(zonelist, gfp_mask); @@ -1990,7 +2026,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, if (!order) return NULL; - if (compaction_deferred(preferred_zone)) { + if (compaction_deferred(preferred_zone, order)) { *deferred_compaction = true; return NULL; } @@ -2012,6 +2048,8 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, if (page) { preferred_zone->compact_considered = 0; preferred_zone->compact_defer_shift = 0; + if (order >= preferred_zone->compact_order_failed) + preferred_zone->compact_order_failed = order + 1; count_vm_event(COMPACTSUCCESS); return page; } @@ -2028,7 +2066,7 @@ __alloc_pages_direct_compact(gfp_t gfp_mask, unsigned int order, * defer if the failure was a sync compaction failure. */ if (sync_migration) - defer_compaction(preferred_zone); + defer_compaction(preferred_zone, order); cond_resched(); } @@ -2306,6 +2344,10 @@ rebalance: if ((gfp_mask & __GFP_FS) && !(gfp_mask & __GFP_NORETRY)) { if (oom_killer_disabled) goto nopage; + /* Coredumps can quickly deplete all memory reserves */ + if ((current->flags & PF_DUMPCORE) && + !(gfp_mask & __GFP_NOFAIL)) + goto nopage; page = __alloc_pages_may_oom(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, @@ -2378,8 +2420,9 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, { enum zone_type high_zoneidx = gfp_zone(gfp_mask); struct zone *preferred_zone; - struct page *page; + struct page *page = NULL; int migratetype = allocflags_to_migratetype(gfp_mask); + unsigned int cpuset_mems_cookie; gfp_mask &= gfp_allowed_mask; @@ -2398,15 +2441,15 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, if (unlikely(!zonelist->_zonerefs->zone)) return NULL; - get_mems_allowed(); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + /* The preferred zone is used for statistics later */ first_zones_zonelist(zonelist, high_zoneidx, nodemask ? : &cpuset_current_mems_allowed, &preferred_zone); - if (!preferred_zone) { - put_mems_allowed(); - return NULL; - } + if (!preferred_zone) + goto out; /* First allocation attempt */ page = get_page_from_freelist(gfp_mask|__GFP_HARDWALL, nodemask, order, @@ -2416,9 +2459,19 @@ __alloc_pages_nodemask(gfp_t gfp_mask, unsigned int order, page = __alloc_pages_slowpath(gfp_mask, order, zonelist, high_zoneidx, nodemask, preferred_zone, migratetype); - put_mems_allowed(); trace_mm_page_alloc(page, order, gfp_mask, migratetype); + +out: + /* + * When updating a task's mems_allowed, it is possible to race with + * parallel threads in such a way that an allocation can fail while + * the mask is being updated. If a page allocation is about to fail, + * check if the cpuset changed during allocation and if so, retry. + */ + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page)) + goto retry_cpuset; + return page; } EXPORT_SYMBOL(__alloc_pages_nodemask); @@ -2632,13 +2685,15 @@ void si_meminfo_node(struct sysinfo *val, int nid) bool skip_free_areas_node(unsigned int flags, int nid) { bool ret = false; + unsigned int cpuset_mems_cookie; if (!(flags & SHOW_MEM_FILTER_NODES)) goto out; - get_mems_allowed(); - ret = !node_isset(nid, cpuset_current_mems_allowed); - put_mems_allowed(); + do { + cpuset_mems_cookie = get_mems_allowed(); + ret = !node_isset(nid, cpuset_current_mems_allowed); + } while (!put_mems_allowed(cpuset_mems_cookie)); out: return ret; } @@ -3925,18 +3980,6 @@ void __init free_bootmem_with_active_regions(int nid, unsigned long max_low_pfn) } } -int __init add_from_early_node_map(struct range *range, int az, - int nr_range, int nid) -{ - unsigned long start_pfn, end_pfn; - int i; - - /* need to go over early_node_map to find out good range for node */ - for_each_mem_pfn_range(i, nid, &start_pfn, &end_pfn, NULL) - nr_range = add_range(range, az, nr_range, start_pfn, end_pfn); - return nr_range; -} - /** * sparse_memory_present_with_active_regions - Call memory_present for each active range * @nid: The node to call memory_present for. If MAX_NUMNODES, all nodes will be used. @@ -4521,7 +4564,7 @@ static unsigned long __init early_calculate_totalpages(void) * memory. When they don't, some nodes will have more kernelcore than * others */ -static void __init find_zone_movable_pfns_for_nodes(unsigned long *movable_pfn) +static void __init find_zone_movable_pfns_for_nodes(void) { int i, nid; unsigned long usable_startpfn; @@ -4713,7 +4756,7 @@ void __init free_area_init_nodes(unsigned long *max_zone_pfn) /* Find the PFNs that ZONE_MOVABLE begins at in each node */ memset(zone_movable_pfn, 0, sizeof(zone_movable_pfn)); - find_zone_movable_pfns_for_nodes(zone_movable_pfn); + find_zone_movable_pfns_for_nodes(); /* Print out the zone ranges */ printk("Zone PFN ranges:\n"); @@ -4823,6 +4866,7 @@ static int page_alloc_cpu_notify(struct notifier_block *self, int cpu = (unsigned long)hcpu; if (action == CPU_DEAD || action == CPU_DEAD_FROZEN) { + lru_add_drain_cpu(cpu); drain_pages(cpu); /* @@ -5236,6 +5280,7 @@ void *__init alloc_large_system_hash(const char *tablename, max = ((unsigned long long)nr_all_pages << PAGE_SHIFT) >> 4; do_div(max, bucketsize); } + max = min(max, 0x80000000ULL); if (numentries > max) numentries = max; diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index de1616a..1ccbd71 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -379,13 +379,15 @@ static struct swap_cgroup *lookup_swap_cgroup(swp_entry_t ent, pgoff_t offset = swp_offset(ent); struct swap_cgroup_ctrl *ctrl; struct page *mappage; + struct swap_cgroup *sc; ctrl = &swap_cgroup_ctrl[swp_type(ent)]; if (ctrlp) *ctrlp = ctrl; mappage = ctrl->map[offset / SC_PER_PAGE]; - return page_address(mappage) + offset % SC_PER_PAGE; + sc = page_address(mappage); + return sc + offset % SC_PER_PAGE; } /** diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 2f5cf10..aa9701e 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -59,7 +59,7 @@ again: continue; split_huge_page_pmd(walk->mm, pmd); - if (pmd_none_or_clear_bad(pmd)) + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) goto again; err = walk_pte_range(pmd, addr, next, walk); if (err) diff --git a/mm/percpu-vm.c b/mm/percpu-vm.c index 12a48a88..405d331 100644 --- a/mm/percpu-vm.c +++ b/mm/percpu-vm.c @@ -184,8 +184,7 @@ static void pcpu_unmap_pages(struct pcpu_chunk *chunk, page_end - page_start); } - for (i = page_start; i < page_end; i++) - __clear_bit(i, populated); + bitmap_clear(populated, page_start, page_end - page_start); } /** diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index eb663fb..5a74fea 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -70,10 +70,11 @@ int pmdp_clear_flush_young(struct vm_area_struct *vma, unsigned long address, pmd_t *pmdp) { int young; -#ifndef CONFIG_TRANSPARENT_HUGEPAGE +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + VM_BUG_ON(address & ~HPAGE_PMD_MASK); +#else BUG(); #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ - VM_BUG_ON(address & ~HPAGE_PMD_MASK); young = pmdp_test_and_clear_young(vma, address, pmdp); if (young) flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); @@ -120,6 +120,21 @@ static void anon_vma_chain_free(struct anon_vma_chain *anon_vma_chain) kmem_cache_free(anon_vma_chain_cachep, anon_vma_chain); } +static void anon_vma_chain_link(struct vm_area_struct *vma, + struct anon_vma_chain *avc, + struct anon_vma *anon_vma) +{ + avc->vma = vma; + avc->anon_vma = anon_vma; + list_add(&avc->same_vma, &vma->anon_vma_chain); + + /* + * It's critical to add new vmas to the tail of the anon_vma, + * see comment in huge_memory.c:__split_huge_page(). + */ + list_add_tail(&avc->same_anon_vma, &anon_vma->head); +} + /** * anon_vma_prepare - attach an anon_vma to a memory region * @vma: the memory region in question @@ -175,10 +190,7 @@ int anon_vma_prepare(struct vm_area_struct *vma) spin_lock(&mm->page_table_lock); if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; - avc->anon_vma = anon_vma; - avc->vma = vma; - list_add(&avc->same_vma, &vma->anon_vma_chain); - list_add_tail(&avc->same_anon_vma, &anon_vma->head); + anon_vma_chain_link(vma, avc, anon_vma); allocated = NULL; avc = NULL; } @@ -224,21 +236,6 @@ static inline void unlock_anon_vma_root(struct anon_vma *root) mutex_unlock(&root->mutex); } -static void anon_vma_chain_link(struct vm_area_struct *vma, - struct anon_vma_chain *avc, - struct anon_vma *anon_vma) -{ - avc->vma = vma; - avc->anon_vma = anon_vma; - list_add(&avc->same_vma, &vma->anon_vma_chain); - - /* - * It's critical to add new vmas to the tail of the anon_vma, - * see comment in huge_memory.c:__split_huge_page(). - */ - list_add_tail(&avc->same_anon_vma, &anon_vma->head); -} - /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. @@ -1151,10 +1148,15 @@ void page_add_new_anon_rmap(struct page *page, */ void page_add_file_rmap(struct page *page) { + bool locked; + unsigned long flags; + + mem_cgroup_begin_update_page_stat(page, &locked, &flags); if (atomic_inc_and_test(&page->_mapcount)) { __inc_zone_page_state(page, NR_FILE_MAPPED); mem_cgroup_inc_page_stat(page, MEMCG_NR_FILE_MAPPED); } + mem_cgroup_end_update_page_stat(page, &locked, &flags); } /** @@ -1165,9 +1167,21 @@ void page_add_file_rmap(struct page *page) */ void page_remove_rmap(struct page *page) { + bool anon = PageAnon(page); + bool locked; + unsigned long flags; + + /* + * The anon case has no mem_cgroup page_stat to update; but may + * uncharge_page() below, where the lock ordering can deadlock if + * we hold the lock against page_stat move: so avoid it on anon. + */ + if (!anon) + mem_cgroup_begin_update_page_stat(page, &locked, &flags); + /* page still mapped by someone else? */ if (!atomic_add_negative(-1, &page->_mapcount)) - return; + goto out; /* * Now that the last pte has gone, s390 must transfer dirty @@ -1176,7 +1190,7 @@ void page_remove_rmap(struct page *page) * not if it's in swapcache - there might be another pte slot * containing the swap entry, but page not yet written to swap. */ - if ((!PageAnon(page) || PageSwapCache(page)) && + if ((!anon || PageSwapCache(page)) && page_test_and_clear_dirty(page_to_pfn(page), 1)) set_page_dirty(page); /* @@ -1184,8 +1198,8 @@ void page_remove_rmap(struct page *page) * and not charged by memcg for now. */ if (unlikely(PageHuge(page))) - return; - if (PageAnon(page)) { + goto out; + if (anon) { mem_cgroup_uncharge_page(page); if (!PageTransHuge(page)) __dec_zone_page_state(page, NR_ANON_PAGES); @@ -1205,6 +1219,9 @@ void page_remove_rmap(struct page *page) * Leaving it set also helps swapoff to reinstate ptes * faster for those pages still in swapcache. */ +out: + if (!anon) + mem_cgroup_end_update_page_stat(page, &locked, &flags); } /* @@ -1282,7 +1299,7 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } dec_mm_counter(mm, MM_ANONPAGES); inc_mm_counter(mm, MM_SWAPENTS); - } else if (PAGE_MIGRATION) { + } else if (IS_ENABLED(CONFIG_MIGRATION)) { /* * Store the pfn of the page in a special migration * pte. do_swap_page() will wait until the migration @@ -1293,7 +1310,8 @@ int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, } set_pte_at(mm, address, pte, swp_entry_to_pte(entry)); BUG_ON(pte_file(*pte)); - } else if (PAGE_MIGRATION && (TTU_ACTION(flags) == TTU_MIGRATION)) { + } else if (IS_ENABLED(CONFIG_MIGRATION) && + (TTU_ACTION(flags) == TTU_MIGRATION)) { /* Establish migration entry for a file page */ swp_entry_t entry; entry = make_migration_entry(page, pte_write(pteval)); @@ -1499,7 +1517,7 @@ static int try_to_unmap_anon(struct page *page, enum ttu_flags flags) * locking requirements of exec(), migration skips * temporary VMAs until after exec() completes. */ - if (PAGE_MIGRATION && (flags & TTU_MIGRATION) && + if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION) && is_vma_temporary_stack(vma)) continue; @@ -127,7 +127,7 @@ static inline struct shmem_sb_info *SHMEM_SB(struct super_block *sb) static inline int shmem_acct_size(unsigned long flags, loff_t size) { return (flags & VM_NORESERVE) ? - 0 : security_vm_enough_memory_kern(VM_ACCT(size)); + 0 : security_vm_enough_memory_mm(current->mm, VM_ACCT(size)); } static inline void shmem_unacct_size(unsigned long flags, loff_t size) @@ -145,7 +145,7 @@ static inline void shmem_unacct_size(unsigned long flags, loff_t size) static inline int shmem_acct_block(unsigned long flags) { return (flags & VM_NORESERVE) ? - security_vm_enough_memory_kern(VM_ACCT(PAGE_CACHE_SIZE)) : 0; + security_vm_enough_memory_mm(current->mm, VM_ACCT(PAGE_CACHE_SIZE)) : 0; } static inline void shmem_unacct_blocks(unsigned long flags, long pages) @@ -1178,6 +1178,12 @@ static struct inode *shmem_get_inode(struct super_block *sb, const struct inode static const struct inode_operations shmem_symlink_inode_operations; static const struct inode_operations shmem_short_symlink_operations; +#ifdef CONFIG_TMPFS_XATTR +static int shmem_initxattrs(struct inode *, const struct xattr *, void *); +#else +#define shmem_initxattrs NULL +#endif + static int shmem_write_begin(struct file *file, struct address_space *mapping, loff_t pos, unsigned len, unsigned flags, @@ -1490,7 +1496,7 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) if (inode) { error = security_inode_init_security(inode, dir, &dentry->d_name, - NULL, NULL); + shmem_initxattrs, NULL); if (error) { if (error != -EOPNOTSUPP) { iput(inode); @@ -1630,7 +1636,7 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s return -ENOSPC; error = security_inode_init_security(inode, dir, &dentry->d_name, - NULL, NULL); + shmem_initxattrs, NULL); if (error) { if (error != -EOPNOTSUPP) { iput(inode); @@ -1656,9 +1662,9 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s } inode->i_mapping->a_ops = &shmem_aops; inode->i_op = &shmem_symlink_inode_operations; - kaddr = kmap_atomic(page, KM_USER0); + kaddr = kmap_atomic(page); memcpy(kaddr, symname, len); - kunmap_atomic(kaddr, KM_USER0); + kunmap_atomic(kaddr); set_page_dirty(page); unlock_page(page); page_cache_release(page); @@ -1704,6 +1710,66 @@ static void shmem_put_link(struct dentry *dentry, struct nameidata *nd, void *co * filesystem level, though. */ +/* + * Allocate new xattr and copy in the value; but leave the name to callers. + */ +static struct shmem_xattr *shmem_xattr_alloc(const void *value, size_t size) +{ + struct shmem_xattr *new_xattr; + size_t len; + + /* wrap around? */ + len = sizeof(*new_xattr) + size; + if (len <= sizeof(*new_xattr)) + return NULL; + + new_xattr = kmalloc(len, GFP_KERNEL); + if (!new_xattr) + return NULL; + + new_xattr->size = size; + memcpy(new_xattr->value, value, size); + return new_xattr; +} + +/* + * Callback for security_inode_init_security() for acquiring xattrs. + */ +static int shmem_initxattrs(struct inode *inode, + const struct xattr *xattr_array, + void *fs_info) +{ + struct shmem_inode_info *info = SHMEM_I(inode); + const struct xattr *xattr; + struct shmem_xattr *new_xattr; + size_t len; + + for (xattr = xattr_array; xattr->name != NULL; xattr++) { + new_xattr = shmem_xattr_alloc(xattr->value, xattr->value_len); + if (!new_xattr) + return -ENOMEM; + + len = strlen(xattr->name) + 1; + new_xattr->name = kmalloc(XATTR_SECURITY_PREFIX_LEN + len, + GFP_KERNEL); + if (!new_xattr->name) { + kfree(new_xattr); + return -ENOMEM; + } + + memcpy(new_xattr->name, XATTR_SECURITY_PREFIX, + XATTR_SECURITY_PREFIX_LEN); + memcpy(new_xattr->name + XATTR_SECURITY_PREFIX_LEN, + xattr->name, len); + + spin_lock(&info->lock); + list_add(&new_xattr->list, &info->xattr_list); + spin_unlock(&info->lock); + } + + return 0; +} + static int shmem_xattr_get(struct dentry *dentry, const char *name, void *buffer, size_t size) { @@ -1731,24 +1797,17 @@ static int shmem_xattr_get(struct dentry *dentry, const char *name, return ret; } -static int shmem_xattr_set(struct dentry *dentry, const char *name, +static int shmem_xattr_set(struct inode *inode, const char *name, const void *value, size_t size, int flags) { - struct inode *inode = dentry->d_inode; struct shmem_inode_info *info = SHMEM_I(inode); struct shmem_xattr *xattr; struct shmem_xattr *new_xattr = NULL; - size_t len; int err = 0; /* value == NULL means remove */ if (value) { - /* wrap around? */ - len = sizeof(*new_xattr) + size; - if (len <= sizeof(*new_xattr)) - return -ENOMEM; - - new_xattr = kmalloc(len, GFP_KERNEL); + new_xattr = shmem_xattr_alloc(value, size); if (!new_xattr) return -ENOMEM; @@ -1757,9 +1816,6 @@ static int shmem_xattr_set(struct dentry *dentry, const char *name, kfree(new_xattr); return -ENOMEM; } - - new_xattr->size = size; - memcpy(new_xattr->value, value, size); } spin_lock(&info->lock); @@ -1858,7 +1914,7 @@ static int shmem_setxattr(struct dentry *dentry, const char *name, if (size == 0) value = ""; /* empty EA, do not remove */ - return shmem_xattr_set(dentry, name, value, size, flags); + return shmem_xattr_set(dentry->d_inode, name, value, size, flags); } @@ -1878,7 +1934,7 @@ static int shmem_removexattr(struct dentry *dentry, const char *name) if (err) return err; - return shmem_xattr_set(dentry, name, NULL, 0, XATTR_REPLACE); + return shmem_xattr_set(dentry->d_inode, name, NULL, 0, XATTR_REPLACE); } static bool xattr_is_trusted(const char *name) @@ -2175,7 +2231,6 @@ static void shmem_put_super(struct super_block *sb) int shmem_fill_super(struct super_block *sb, void *data, int silent) { struct inode *inode; - struct dentry *root; struct shmem_sb_info *sbinfo; int err = -ENOMEM; @@ -2232,14 +2287,11 @@ int shmem_fill_super(struct super_block *sb, void *data, int silent) goto failed; inode->i_uid = sbinfo->uid; inode->i_gid = sbinfo->gid; - root = d_alloc_root(inode); - if (!root) - goto failed_iput; - sb->s_root = root; + sb->s_root = d_make_root(inode); + if (!sb->s_root) + goto failed; return 0; -failed_iput: - iput(inode); failed: shmem_put_super(sb); return err; @@ -1731,6 +1731,52 @@ static int __init cpucache_init(void) } __initcall(cpucache_init); +static noinline void +slab_out_of_memory(struct kmem_cache *cachep, gfp_t gfpflags, int nodeid) +{ + struct kmem_list3 *l3; + struct slab *slabp; + unsigned long flags; + int node; + + printk(KERN_WARNING + "SLAB: Unable to allocate memory on node %d (gfp=0x%x)\n", + nodeid, gfpflags); + printk(KERN_WARNING " cache: %s, object size: %d, order: %d\n", + cachep->name, cachep->buffer_size, cachep->gfporder); + + for_each_online_node(node) { + unsigned long active_objs = 0, num_objs = 0, free_objects = 0; + unsigned long active_slabs = 0, num_slabs = 0; + + l3 = cachep->nodelists[node]; + if (!l3) + continue; + + spin_lock_irqsave(&l3->list_lock, flags); + list_for_each_entry(slabp, &l3->slabs_full, list) { + active_objs += cachep->num; + active_slabs++; + } + list_for_each_entry(slabp, &l3->slabs_partial, list) { + active_objs += slabp->inuse; + active_slabs++; + } + list_for_each_entry(slabp, &l3->slabs_free, list) + num_slabs++; + + free_objects += l3->free_objects; + spin_unlock_irqrestore(&l3->list_lock, flags); + + num_slabs += active_slabs; + num_objs = num_slabs * cachep->num; + printk(KERN_WARNING + " node %d: slabs: %ld/%ld, objs: %ld/%ld, free: %ld\n", + node, active_slabs, num_slabs, active_objs, num_objs, + free_objects); + } +} + /* * Interface to system's page allocator. No need to hold the cache-lock. * @@ -1757,8 +1803,11 @@ static void *kmem_getpages(struct kmem_cache *cachep, gfp_t flags, int nodeid) flags |= __GFP_RECLAIMABLE; page = alloc_pages_exact_node(nodeid, flags | __GFP_NOTRACK, cachep->gfporder); - if (!page) + if (!page) { + if (!(flags & __GFP_NOWARN) && printk_ratelimit()) + slab_out_of_memory(cachep, flags, nodeid); return NULL; + } nr_pages = (1 << cachep->gfporder); if (cachep->flags & SLAB_RECLAIM_ACCOUNT) @@ -3284,12 +3333,10 @@ static void *alternate_node_alloc(struct kmem_cache *cachep, gfp_t flags) if (in_interrupt() || (flags & __GFP_THISNODE)) return NULL; nid_alloc = nid_here = numa_mem_id(); - get_mems_allowed(); if (cpuset_do_slab_mem_spread() && (cachep->flags & SLAB_MEM_SPREAD)) nid_alloc = cpuset_slab_spread_node(); else if (current->mempolicy) nid_alloc = slab_node(current->mempolicy); - put_mems_allowed(); if (nid_alloc != nid_here) return ____cache_alloc_node(cachep, flags, nid_alloc); return NULL; @@ -3312,14 +3359,17 @@ static void *fallback_alloc(struct kmem_cache *cache, gfp_t flags) enum zone_type high_zoneidx = gfp_zone(flags); void *obj = NULL; int nid; + unsigned int cpuset_mems_cookie; if (flags & __GFP_THISNODE) return NULL; - get_mems_allowed(); - zonelist = node_zonelist(slab_node(current->mempolicy), flags); local_flags = flags & (GFP_CONSTRAINT_MASK|GFP_RECLAIM_MASK); +retry_cpuset: + cpuset_mems_cookie = get_mems_allowed(); + zonelist = node_zonelist(slab_node(current->mempolicy), flags); + retry: /* * Look through allowed nodes for objects available @@ -3372,7 +3422,9 @@ retry: } } } - put_mems_allowed(); + + if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !obj)) + goto retry_cpuset; return obj; } @@ -3693,13 +3745,12 @@ static inline void __cache_free(struct kmem_cache *cachep, void *objp, if (likely(ac->avail < ac->limit)) { STATS_INC_FREEHIT(cachep); - ac->entry[ac->avail++] = objp; - return; } else { STATS_INC_FREEMISS(cachep); cache_flusharray(cachep, ac); - ac->entry[ac->avail++] = objp; } + + ac->entry[ac->avail++] = objp; } /** @@ -29,6 +29,7 @@ #include <linux/math64.h> #include <linux/fault-inject.h> #include <linux/stacktrace.h> +#include <linux/prefetch.h> #include <trace/events/kmem.h> @@ -269,6 +270,11 @@ static inline void *get_freepointer(struct kmem_cache *s, void *object) return *(void **)(object + s->offset); } +static void prefetch_freepointer(const struct kmem_cache *s, void *object) +{ + prefetch(object + s->offset); +} + static inline void *get_freepointer_safe(struct kmem_cache *s, void *object) { void *p; @@ -1560,6 +1566,7 @@ static void *get_partial_node(struct kmem_cache *s, } else { page->freelist = t; available = put_cpu_partial(s, page, 0); + stat(s, CPU_PARTIAL_NODE); } if (kmem_cache_debug(s) || available > s->cpu_partial / 2) break; @@ -1581,6 +1588,7 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags, struct zone *zone; enum zone_type high_zoneidx = gfp_zone(flags); void *object; + unsigned int cpuset_mems_cookie; /* * The defrag ratio allows a configuration of the tradeoffs between @@ -1604,23 +1612,32 @@ static struct page *get_any_partial(struct kmem_cache *s, gfp_t flags, get_cycles() % 1024 > s->remote_node_defrag_ratio) return NULL; - get_mems_allowed(); - zonelist = node_zonelist(slab_node(current->mempolicy), flags); - for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { - struct kmem_cache_node *n; - - n = get_node(s, zone_to_nid(zone)); - - if (n && cpuset_zone_allowed_hardwall(zone, flags) && - n->nr_partial > s->min_partial) { - object = get_partial_node(s, n, c); - if (object) { - put_mems_allowed(); - return object; + do { + cpuset_mems_cookie = get_mems_allowed(); + zonelist = node_zonelist(slab_node(current->mempolicy), flags); + for_each_zone_zonelist(zone, z, zonelist, high_zoneidx) { + struct kmem_cache_node *n; + + n = get_node(s, zone_to_nid(zone)); + + if (n && cpuset_zone_allowed_hardwall(zone, flags) && + n->nr_partial > s->min_partial) { + object = get_partial_node(s, n, c); + if (object) { + /* + * Return the object even if + * put_mems_allowed indicated that + * the cpuset mems_allowed was + * updated in parallel. It's a + * harmless race between the alloc + * and the cpuset update. + */ + put_mems_allowed(cpuset_mems_cookie); + return object; + } } } - } - put_mems_allowed(); + } while (!put_mems_allowed(cpuset_mems_cookie)); #endif return NULL; } @@ -1973,6 +1990,7 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) local_irq_restore(flags); pobjects = 0; pages = 0; + stat(s, CPU_PARTIAL_DRAIN); } } @@ -1984,7 +2002,6 @@ int put_cpu_partial(struct kmem_cache *s, struct page *page, int drain) page->next = oldpage; } while (this_cpu_cmpxchg(s->cpu_slab->partial, oldpage, page) != oldpage); - stat(s, CPU_PARTIAL_FREE); return pobjects; } @@ -2018,9 +2035,17 @@ static void flush_cpu_slab(void *d) __flush_cpu_slab(s, smp_processor_id()); } +static bool has_cpu_slab(int cpu, void *info) +{ + struct kmem_cache *s = info; + struct kmem_cache_cpu *c = per_cpu_ptr(s->cpu_slab, cpu); + + return !!(c->page); +} + static void flush_all(struct kmem_cache *s) { - on_each_cpu(flush_cpu_slab, s, 1); + on_each_cpu_cond(has_cpu_slab, flush_cpu_slab, s, 1, GFP_ATOMIC); } /* @@ -2309,6 +2334,8 @@ redo: object = __slab_alloc(s, gfpflags, node, addr, c); else { + void *next_object = get_freepointer_safe(s, object); + /* * The cmpxchg will only match if there was no additional * operation and if we are on the right processor. @@ -2324,11 +2351,12 @@ redo: if (unlikely(!this_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, object, tid, - get_freepointer_safe(s, object), next_tid(tid)))) { + next_object, next_tid(tid)))) { note_cmpxchg_failure("slab_alloc", s, tid); goto redo; } + prefetch_freepointer(s, next_object); stat(s, ALLOC_FASTPATH); } @@ -2465,9 +2493,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page, * If we just froze the page then put it onto the * per cpu partial list. */ - if (new.frozen && !was_frozen) + if (new.frozen && !was_frozen) { put_cpu_partial(s, page, 1); - + stat(s, CPU_PARTIAL_FREE); + } /* * The list lock was not taken therefore no list * activity can be necessary. @@ -3929,13 +3958,14 @@ struct kmem_cache *kmem_cache_create(const char *name, size_t size, if (kmem_cache_open(s, n, size, align, flags, ctor)) { list_add(&s->list, &slab_caches); + up_write(&slub_lock); if (sysfs_slab_add(s)) { + down_write(&slub_lock); list_del(&s->list); kfree(n); kfree(s); goto err; } - up_write(&slub_lock); return s; } kfree(n); @@ -5059,6 +5089,8 @@ STAT_ATTR(CMPXCHG_DOUBLE_CPU_FAIL, cmpxchg_double_cpu_fail); STAT_ATTR(CMPXCHG_DOUBLE_FAIL, cmpxchg_double_fail); STAT_ATTR(CPU_PARTIAL_ALLOC, cpu_partial_alloc); STAT_ATTR(CPU_PARTIAL_FREE, cpu_partial_free); +STAT_ATTR(CPU_PARTIAL_NODE, cpu_partial_node); +STAT_ATTR(CPU_PARTIAL_DRAIN, cpu_partial_drain); #endif static struct attribute *slab_attrs[] = { @@ -5124,6 +5156,8 @@ static struct attribute *slab_attrs[] = { &cmpxchg_double_cpu_fail_attr.attr, &cpu_partial_alloc_attr.attr, &cpu_partial_free_attr.attr, + &cpu_partial_node_attr.attr, + &cpu_partial_drain_attr.attr, #endif #ifdef CONFIG_FAILSLAB &failslab_attr.attr, diff --git a/mm/sparse.c b/mm/sparse.c index 61d7cde..a8bc7d3 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -353,29 +353,21 @@ static void __init sparse_early_usemaps_alloc_node(unsigned long**usemap_map, usemap = sparse_early_usemaps_alloc_pgdat_section(NODE_DATA(nodeid), usemap_count); - if (usemap) { - for (pnum = pnum_begin; pnum < pnum_end; pnum++) { - if (!present_section_nr(pnum)) - continue; - usemap_map[pnum] = usemap; - usemap += size; + if (!usemap) { + usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count); + if (!usemap) { + printk(KERN_WARNING "%s: allocation failed\n", __func__); + return; } - return; } - usemap = alloc_bootmem_node(NODE_DATA(nodeid), size * usemap_count); - if (usemap) { - for (pnum = pnum_begin; pnum < pnum_end; pnum++) { - if (!present_section_nr(pnum)) - continue; - usemap_map[pnum] = usemap; - usemap += size; - check_usemap_section_nr(nodeid, usemap_map[pnum]); - } - return; + for (pnum = pnum_begin; pnum < pnum_end; pnum++) { + if (!present_section_nr(pnum)) + continue; + usemap_map[pnum] = usemap; + usemap += size; + check_usemap_section_nr(nodeid, usemap_map[pnum]); } - - printk(KERN_WARNING "%s: allocation failed\n", __func__); } #ifndef CONFIG_SPARSEMEM_VMEMMAP @@ -496,7 +496,7 @@ static void lru_deactivate_fn(struct page *page, void *arg) * Either "cpu" is the current CPU, and preemption has already been * disabled; or "cpu" is being hot-unplugged, and is already dead. */ -static void drain_cpu_pagevecs(int cpu) +void lru_add_drain_cpu(int cpu) { struct pagevec *pvecs = per_cpu(lru_add_pvecs, cpu); struct pagevec *pvec; @@ -553,7 +553,7 @@ void deactivate_page(struct page *page) void lru_add_drain(void) { - drain_cpu_pagevecs(get_cpu()); + lru_add_drain_cpu(get_cpu()); put_cpu(); } @@ -652,14 +652,14 @@ EXPORT_SYMBOL(__pagevec_release); void lru_add_page_tail(struct zone* zone, struct page *page, struct page *page_tail) { - int active; + int uninitialized_var(active); enum lru_list lru; const int file = 0; VM_BUG_ON(!PageHead(page)); VM_BUG_ON(PageCompound(page_tail)); VM_BUG_ON(PageLRU(page_tail)); - VM_BUG_ON(!spin_is_locked(&zone->lru_lock)); + VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&zone->lru_lock)); SetPageLRU(page_tail); @@ -672,7 +672,6 @@ void lru_add_page_tail(struct zone* zone, active = 0; lru = LRU_INACTIVE_ANON; } - update_page_reclaim_stat(zone, page_tail, file, active); } else { SetPageUnevictable(page_tail); lru = LRU_UNEVICTABLE; @@ -693,6 +692,9 @@ void lru_add_page_tail(struct zone* zone, list_head = page_tail->lru.prev; list_move_tail(&page_tail->lru, list_head); } + + if (!PageUnevictable(page)) + update_page_reclaim_stat(zone, page_tail, file, active); } #endif /* CONFIG_TRANSPARENT_HUGEPAGE */ @@ -710,8 +712,8 @@ static void __pagevec_lru_add_fn(struct page *page, void *arg) SetPageLRU(page); if (active) SetPageActive(page); - update_page_reclaim_stat(zone, page, file, active); add_page_to_lru_list(zone, page, lru); + update_page_reclaim_stat(zone, page, file, active); } /* diff --git a/mm/swap_state.c b/mm/swap_state.c index 470038a..9d3dd37 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -300,16 +300,6 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, new_page = alloc_page_vma(gfp_mask, vma, addr); if (!new_page) break; /* Out of memory */ - /* - * The memcg-specific accounting when moving - * pages around the LRU lists relies on the - * page's owner (memcg) to be valid. Usually, - * pages are assigned to a new owner before - * being put on the LRU list, but since this - * is not the case here, the stale owner from - * a previous allocation cycle must be reset. - */ - mem_cgroup_reset_owner(new_page); } /* @@ -382,25 +372,23 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, struct page *swapin_readahead(swp_entry_t entry, gfp_t gfp_mask, struct vm_area_struct *vma, unsigned long addr) { - int nr_pages; struct page *page; - unsigned long offset; - unsigned long end_offset; + unsigned long offset = swp_offset(entry); + unsigned long start_offset, end_offset; + unsigned long mask = (1UL << page_cluster) - 1; - /* - * Get starting offset for readaround, and number of pages to read. - * Adjust starting address by readbehind (for NUMA interleave case)? - * No, it's very unlikely that swap layout would follow vma layout, - * more likely that neighbouring swap pages came from the same node: - * so use the same "addr" to choose the same node for each swap read. - */ - nr_pages = valid_swaphandles(entry, &offset); - for (end_offset = offset + nr_pages; offset < end_offset; offset++) { + /* Read a page_cluster sized and aligned cluster around offset. */ + start_offset = offset & ~mask; + end_offset = offset | mask; + if (!start_offset) /* First page is swap header. */ + start_offset++; + + for (offset = start_offset; offset <= end_offset ; offset++) { /* Ok, do the async read-ahead now */ page = read_swap_cache_async(swp_entry(swp_type(entry), offset), gfp_mask, vma, addr); if (!page) - break; + continue; page_cache_release(page); } lru_add_drain(); /* Push any new pages onto the LRU now */ diff --git a/mm/swapfile.c b/mm/swapfile.c index d999f09..fafc26d 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -932,9 +932,7 @@ static inline int unuse_pmd_range(struct vm_area_struct *vma, pud_t *pud, pmd = pmd_offset(pud, addr); do { next = pmd_addr_end(addr, end); - if (unlikely(pmd_trans_huge(*pmd))) - continue; - if (pmd_none_or_clear_bad(pmd)) + if (pmd_none_or_trans_huge_or_clear_bad(pmd)) continue; ret = unuse_pte_range(vma, pmd, addr, next, entry, page); if (ret) @@ -1563,6 +1561,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) if (!capable(CAP_SYS_ADMIN)) return -EPERM; + BUG_ON(!current->mm); + pathname = getname(specialfile); err = PTR_ERR(pathname); if (IS_ERR(pathname)) @@ -1590,7 +1590,7 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - if (!security_vm_enough_memory(p->pages)) + if (!security_vm_enough_memory_mm(current->mm, p->pages)) vm_unacct_memory(p->pages); else { err = -ENOMEM; @@ -2022,6 +2022,9 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) struct page *page = NULL; struct inode *inode = NULL; + if (swap_flags & ~SWAP_FLAGS_VALID) + return -EINVAL; + if (!capable(CAP_SYS_ADMIN)) return -EPERM; @@ -2105,7 +2108,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) p->flags |= SWP_SOLIDSTATE; p->cluster_next = 1 + (random32() % p->highest_bit); } - if (discard_swap(p) == 0 && (swap_flags & SWAP_FLAG_DISCARD)) + if ((swap_flags & SWAP_FLAG_DISCARD) && discard_swap(p) == 0) p->flags |= SWP_DISCARDABLE; } @@ -2290,58 +2293,6 @@ int swapcache_prepare(swp_entry_t entry) } /* - * swap_lock prevents swap_map being freed. Don't grab an extra - * reference on the swaphandle, it doesn't matter if it becomes unused. - */ -int valid_swaphandles(swp_entry_t entry, unsigned long *offset) -{ - struct swap_info_struct *si; - int our_page_cluster = page_cluster; - pgoff_t target, toff; - pgoff_t base, end; - int nr_pages = 0; - - if (!our_page_cluster) /* no readahead */ - return 0; - - si = swap_info[swp_type(entry)]; - target = swp_offset(entry); - base = (target >> our_page_cluster) << our_page_cluster; - end = base + (1 << our_page_cluster); - if (!base) /* first page is swap header */ - base++; - - spin_lock(&swap_lock); - if (end > si->max) /* don't go beyond end of map */ - end = si->max; - - /* Count contiguous allocated slots above our target */ - for (toff = target; ++toff < end; nr_pages++) { - /* Don't read in free or bad pages */ - if (!si->swap_map[toff]) - break; - if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD) - break; - } - /* Count contiguous allocated slots below our target */ - for (toff = target; --toff >= base; nr_pages++) { - /* Don't read in free or bad pages */ - if (!si->swap_map[toff]) - break; - if (swap_count(si->swap_map[toff]) == SWAP_MAP_BAD) - break; - } - spin_unlock(&swap_lock); - - /* - * Indicate starting offset, and return number of pages to get: - * if only 1, say 0, since there's then no readahead to be done. - */ - *offset = ++toff; - return nr_pages? ++nr_pages: 0; -} - -/* * add_swap_count_continuation - called when a swap count is duplicated * beyond SWAP_MAP_MAX, it allocates a new page and links that to the entry's * page of the original vmalloc'ed swap_map, to hold the continuation count @@ -2427,9 +2378,9 @@ int add_swap_count_continuation(swp_entry_t entry, gfp_t gfp_mask) if (!(count & COUNT_CONTINUED)) goto out; - map = kmap_atomic(list_page, KM_USER0) + offset; + map = kmap_atomic(list_page) + offset; count = *map; - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); /* * If this continuation count now has some space in it, @@ -2472,7 +2423,7 @@ static bool swap_count_continued(struct swap_info_struct *si, offset &= ~PAGE_MASK; page = list_entry(head->lru.next, struct page, lru); - map = kmap_atomic(page, KM_USER0) + offset; + map = kmap_atomic(page) + offset; if (count == SWAP_MAP_MAX) /* initial increment from swap_map */ goto init_map; /* jump over SWAP_CONT_MAX checks */ @@ -2482,26 +2433,26 @@ static bool swap_count_continued(struct swap_info_struct *si, * Think of how you add 1 to 999 */ while (*map == (SWAP_CONT_MAX | COUNT_CONTINUED)) { - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); BUG_ON(page == head); - map = kmap_atomic(page, KM_USER0) + offset; + map = kmap_atomic(page) + offset; } if (*map == SWAP_CONT_MAX) { - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); if (page == head) return false; /* add count continuation */ - map = kmap_atomic(page, KM_USER0) + offset; + map = kmap_atomic(page) + offset; init_map: *map = 0; /* we didn't zero the page */ } *map += 1; - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); while (page != head) { - map = kmap_atomic(page, KM_USER0) + offset; + map = kmap_atomic(page) + offset; *map = COUNT_CONTINUED; - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); } return true; /* incremented */ @@ -2512,22 +2463,22 @@ init_map: *map = 0; /* we didn't zero the page */ */ BUG_ON(count != COUNT_CONTINUED); while (*map == COUNT_CONTINUED) { - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); page = list_entry(page->lru.next, struct page, lru); BUG_ON(page == head); - map = kmap_atomic(page, KM_USER0) + offset; + map = kmap_atomic(page) + offset; } BUG_ON(*map == 0); *map -= 1; if (*map == 0) count = 0; - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); while (page != head) { - map = kmap_atomic(page, KM_USER0) + offset; + map = kmap_atomic(page) + offset; *map = SWAP_CONT_MAX | count; count = COUNT_CONTINUED; - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); page = list_entry(page->lru.prev, struct page, lru); } return count == COUNT_CONTINUED; diff --git a/mm/truncate.c b/mm/truncate.c index a188058..61a183b 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -52,7 +52,7 @@ void do_invalidatepage(struct page *page, unsigned long offset) static inline void truncate_partial_page(struct page *page, unsigned partial) { zero_user_segment(page, partial, PAGE_CACHE_SIZE); - cleancache_flush_page(page->mapping, page); + cleancache_invalidate_page(page->mapping, page); if (page_has_private(page)) do_invalidatepage(page, partial); } @@ -213,7 +213,7 @@ void truncate_inode_pages_range(struct address_space *mapping, pgoff_t end; int i; - cleancache_flush_inode(mapping); + cleancache_invalidate_inode(mapping); if (mapping->nrpages == 0) return; @@ -292,7 +292,7 @@ void truncate_inode_pages_range(struct address_space *mapping, mem_cgroup_uncharge_end(); index++; } - cleancache_flush_inode(mapping); + cleancache_invalidate_inode(mapping); } EXPORT_SYMBOL(truncate_inode_pages_range); @@ -444,7 +444,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, int ret2 = 0; int did_range_unmap = 0; - cleancache_flush_inode(mapping); + cleancache_invalidate_inode(mapping); pagevec_init(&pvec, 0); index = start; while (index <= end && pagevec_lookup(&pvec, mapping, index, @@ -500,7 +500,7 @@ int invalidate_inode_pages2_range(struct address_space *mapping, cond_resched(); index++; } - cleancache_flush_inode(mapping); + cleancache_invalidate_inode(mapping); return ret; } EXPORT_SYMBOL_GPL(invalidate_inode_pages2_range); @@ -626,3 +626,43 @@ int vmtruncate_range(struct inode *inode, loff_t lstart, loff_t lend) return 0; } + +/** + * truncate_pagecache_range - unmap and remove pagecache that is hole-punched + * @inode: inode + * @lstart: offset of beginning of hole + * @lend: offset of last byte of hole + * + * This function should typically be called before the filesystem + * releases resources associated with the freed range (eg. deallocates + * blocks). This way, pagecache will always stay logically coherent + * with on-disk format, and the filesystem would not have to deal with + * situations such as writepage being called for a page that has already + * had its underlying blocks deallocated. + */ +void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) +{ + struct address_space *mapping = inode->i_mapping; + loff_t unmap_start = round_up(lstart, PAGE_SIZE); + loff_t unmap_end = round_down(1 + lend, PAGE_SIZE) - 1; + /* + * This rounding is currently just for example: unmap_mapping_range + * expands its hole outwards, whereas we want it to contract the hole + * inwards. However, existing callers of truncate_pagecache_range are + * doing their own page rounding first; and truncate_inode_pages_range + * currently BUGs if lend is not pagealigned-1 (it handles partial + * page at start of hole, but not partial page at end of hole). Note + * unmap_mapping_range allows holelen 0 for all, and we allow lend -1. + */ + + /* + * Unlike in truncate_pagecache, unmap_mapping_range is called only + * once (before truncating pagecache), and without "even_cows" flag: + * hole-punching should not remove private COWed pages from the hole. + */ + if ((u64)unmap_end > (u64)unmap_start) + unmap_mapping_range(mapping, unmap_start, + 1 + unmap_end - unmap_start, 0); + truncate_inode_pages_range(mapping, lstart, lend); +} +EXPORT_SYMBOL(truncate_pagecache_range); @@ -239,6 +239,47 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, next->vm_prev = vma; } +/* Check if the vma is being used as a stack by this task */ +static int vm_is_stack_for_task(struct task_struct *t, + struct vm_area_struct *vma) +{ + return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); +} + +/* + * Check if the vma is being used as a stack. + * If is_group is non-zero, check in the entire thread group or else + * just check in the current task. Returns the pid of the task that + * the vma is stack for. + */ +pid_t vm_is_stack(struct task_struct *task, + struct vm_area_struct *vma, int in_group) +{ + pid_t ret = 0; + + if (vm_is_stack_for_task(task, vma)) + return task->pid; + + if (in_group) { + struct task_struct *t; + rcu_read_lock(); + if (!pid_alive(task)) + goto done; + + t = task; + do { + if (vm_is_stack_for_task(t, vma)) { + ret = t->pid; + goto done; + } + } while_each_thread(task, t); +done: + rcu_read_unlock(); + } + + return ret; +} + #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm) { diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 86ce9a5..94dff88 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1906,9 +1906,9 @@ static int aligned_vread(char *buf, char *addr, unsigned long count) * we can expect USER0 is not used (see vread/vwrite's * function description) */ - void *map = kmap_atomic(p, KM_USER0); + void *map = kmap_atomic(p); memcpy(buf, map + offset, length); - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); } else memset(buf, 0, length); @@ -1945,9 +1945,9 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) * we can expect USER0 is not used (see vread/vwrite's * function description) */ - void *map = kmap_atomic(p, KM_USER0); + void *map = kmap_atomic(p); memcpy(map + offset, buf, length); - kunmap_atomic(map, KM_USER0); + kunmap_atomic(map); } addr += length; buf += length; diff --git a/mm/vmscan.c b/mm/vmscan.c index c52b235..33c332b 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1138,7 +1138,7 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file) * @mz: The mem_cgroup_zone to pull pages from. * @dst: The temp list to put pages on to. * @nr_scanned: The number of pages that were scanned. - * @order: The caller's attempted allocation order + * @sc: The scan_control struct for this reclaim session * @mode: One of the LRU isolation modes * @active: True [1] if isolating active pages * @file: True [1] if isolating file [!anon] pages @@ -1147,8 +1147,8 @@ int __isolate_lru_page(struct page *page, isolate_mode_t mode, int file) */ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, struct mem_cgroup_zone *mz, struct list_head *dst, - unsigned long *nr_scanned, int order, isolate_mode_t mode, - int active, int file) + unsigned long *nr_scanned, struct scan_control *sc, + isolate_mode_t mode, int active, int file) { struct lruvec *lruvec; struct list_head *src; @@ -1194,7 +1194,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, BUG(); } - if (!order) + if (!sc->order || !(sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM)) continue; /* @@ -1208,8 +1208,8 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, */ zone_id = page_zone_id(page); page_pfn = page_to_pfn(page); - pfn = page_pfn & ~((1 << order) - 1); - end_pfn = pfn + (1 << order); + pfn = page_pfn & ~((1 << sc->order) - 1); + end_pfn = pfn + (1 << sc->order); for (; pfn < end_pfn; pfn++) { struct page *cursor_page; @@ -1275,7 +1275,7 @@ static unsigned long isolate_lru_pages(unsigned long nr_to_scan, *nr_scanned = scan; - trace_mm_vmscan_lru_isolate(order, + trace_mm_vmscan_lru_isolate(sc->order, nr_to_scan, scan, nr_taken, nr_lumpy_taken, nr_lumpy_dirty, nr_lumpy_failed, @@ -1413,7 +1413,6 @@ update_isolated_counts(struct mem_cgroup_zone *mz, unsigned long *nr_anon, unsigned long *nr_file) { - struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz); struct zone *zone = mz->zone; unsigned int count[NR_LRU_LISTS] = { 0, }; unsigned long nr_active = 0; @@ -1434,6 +1433,7 @@ update_isolated_counts(struct mem_cgroup_zone *mz, count[lru] += numpages; } + preempt_disable(); __count_vm_events(PGDEACTIVATE, nr_active); __mod_zone_page_state(zone, NR_ACTIVE_FILE, @@ -1448,8 +1448,9 @@ update_isolated_counts(struct mem_cgroup_zone *mz, *nr_anon = count[LRU_ACTIVE_ANON] + count[LRU_INACTIVE_ANON]; *nr_file = count[LRU_ACTIVE_FILE] + count[LRU_INACTIVE_FILE]; - reclaim_stat->recent_scanned[0] += *nr_anon; - reclaim_stat->recent_scanned[1] += *nr_file; + __mod_zone_page_state(zone, NR_ISOLATED_ANON, *nr_anon); + __mod_zone_page_state(zone, NR_ISOLATED_FILE, *nr_file); + preempt_enable(); } /* @@ -1509,8 +1510,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz, unsigned long nr_file; unsigned long nr_dirty = 0; unsigned long nr_writeback = 0; - isolate_mode_t reclaim_mode = ISOLATE_INACTIVE; + isolate_mode_t isolate_mode = ISOLATE_INACTIVE; struct zone *zone = mz->zone; + struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz); while (unlikely(too_many_isolated(zone, file, sc))) { congestion_wait(BLK_RW_ASYNC, HZ/10); @@ -1522,20 +1524,19 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz, set_reclaim_mode(priority, sc, false); if (sc->reclaim_mode & RECLAIM_MODE_LUMPYRECLAIM) - reclaim_mode |= ISOLATE_ACTIVE; + isolate_mode |= ISOLATE_ACTIVE; lru_add_drain(); if (!sc->may_unmap) - reclaim_mode |= ISOLATE_UNMAPPED; + isolate_mode |= ISOLATE_UNMAPPED; if (!sc->may_writepage) - reclaim_mode |= ISOLATE_CLEAN; + isolate_mode |= ISOLATE_CLEAN; spin_lock_irq(&zone->lru_lock); - nr_taken = isolate_lru_pages(nr_to_scan, mz, &page_list, - &nr_scanned, sc->order, - reclaim_mode, 0, file); + nr_taken = isolate_lru_pages(nr_to_scan, mz, &page_list, &nr_scanned, + sc, isolate_mode, 0, file); if (global_reclaim(sc)) { zone->pages_scanned += nr_scanned; if (current_is_kswapd()) @@ -1545,19 +1546,13 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz, __count_zone_vm_events(PGSCAN_DIRECT, zone, nr_scanned); } + spin_unlock_irq(&zone->lru_lock); - if (nr_taken == 0) { - spin_unlock_irq(&zone->lru_lock); + if (nr_taken == 0) return 0; - } update_isolated_counts(mz, &page_list, &nr_anon, &nr_file); - __mod_zone_page_state(zone, NR_ISOLATED_ANON, nr_anon); - __mod_zone_page_state(zone, NR_ISOLATED_FILE, nr_file); - - spin_unlock_irq(&zone->lru_lock); - nr_reclaimed = shrink_page_list(&page_list, mz, sc, priority, &nr_dirty, &nr_writeback); @@ -1570,6 +1565,9 @@ shrink_inactive_list(unsigned long nr_to_scan, struct mem_cgroup_zone *mz, spin_lock_irq(&zone->lru_lock); + reclaim_stat->recent_scanned[0] += nr_anon; + reclaim_stat->recent_scanned[1] += nr_file; + if (current_is_kswapd()) __count_vm_events(KSWAPD_STEAL, nr_reclaimed); __count_zone_vm_events(PGSTEAL, zone, nr_reclaimed); @@ -1643,18 +1641,6 @@ static void move_active_pages_to_lru(struct zone *zone, unsigned long pgmoved = 0; struct page *page; - if (buffer_heads_over_limit) { - spin_unlock_irq(&zone->lru_lock); - list_for_each_entry(page, list, lru) { - if (page_has_private(page) && trylock_page(page)) { - if (page_has_private(page)) - try_to_release_page(page, 0); - unlock_page(page); - } - } - spin_lock_irq(&zone->lru_lock); - } - while (!list_empty(list)) { struct lruvec *lruvec; @@ -1699,21 +1685,22 @@ static void shrink_active_list(unsigned long nr_to_scan, struct page *page; struct zone_reclaim_stat *reclaim_stat = get_reclaim_stat(mz); unsigned long nr_rotated = 0; - isolate_mode_t reclaim_mode = ISOLATE_ACTIVE; + isolate_mode_t isolate_mode = ISOLATE_ACTIVE; struct zone *zone = mz->zone; lru_add_drain(); + reset_reclaim_mode(sc); + if (!sc->may_unmap) - reclaim_mode |= ISOLATE_UNMAPPED; + isolate_mode |= ISOLATE_UNMAPPED; if (!sc->may_writepage) - reclaim_mode |= ISOLATE_CLEAN; + isolate_mode |= ISOLATE_CLEAN; spin_lock_irq(&zone->lru_lock); - nr_taken = isolate_lru_pages(nr_to_scan, mz, &l_hold, - &nr_scanned, sc->order, - reclaim_mode, 1, file); + nr_taken = isolate_lru_pages(nr_to_scan, mz, &l_hold, &nr_scanned, sc, + isolate_mode, 1, file); if (global_reclaim(sc)) zone->pages_scanned += nr_scanned; @@ -1737,6 +1724,14 @@ static void shrink_active_list(unsigned long nr_to_scan, continue; } + if (unlikely(buffer_heads_over_limit)) { + if (page_has_private(page) && trylock_page(page)) { + if (page_has_private(page)) + try_to_release_page(page, 0); + unlock_page(page); + } + } + if (page_referenced(page, 0, mz->mem_cgroup, &vm_flags)) { nr_rotated += hpage_nr_pages(page); /* @@ -2112,7 +2107,12 @@ restart: * with multiple processes reclaiming pages, the total * freeing target can get unreasonably large. */ - if (nr_reclaimed >= nr_to_reclaim && priority < DEF_PRIORITY) + if (nr_reclaimed >= nr_to_reclaim) + nr_to_reclaim = 0; + else + nr_to_reclaim -= nr_reclaimed; + + if (!nr_to_reclaim && priority < DEF_PRIORITY) break; } blk_finish_plug(&plug); @@ -2195,7 +2195,7 @@ static inline bool compaction_ready(struct zone *zone, struct scan_control *sc) * If compaction is deferred, reclaim up to a point where * compaction will have a chance of success when re-enabled */ - if (compaction_deferred(zone)) + if (compaction_deferred(zone, sc->order)) return watermark_ok; /* If compaction is not ready to start, keep reclaiming */ @@ -2235,6 +2235,14 @@ static bool shrink_zones(int priority, struct zonelist *zonelist, unsigned long nr_soft_scanned; bool aborted_reclaim = false; + /* + * If the number of buffer_heads in the machine exceeds the maximum + * allowed level, force direct reclaim to scan the highmem zone as + * highmem pages could be pinning lowmem pages storing buffer_heads + */ + if (buffer_heads_over_limit) + sc->gfp_mask |= __GFP_HIGHMEM; + for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { if (!populated_zone(zone)) @@ -2255,8 +2263,8 @@ static bool shrink_zones(int priority, struct zonelist *zonelist, * Even though compaction is invoked for any * non-zero order, only frequent costly order * reclamation is disruptive enough to become a - * noticable problem, like transparent huge page - * allocations. + * noticeable problem, like transparent huge + * page allocations. */ if (compaction_ready(zone, sc)) { aborted_reclaim = true; @@ -2337,7 +2345,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, unsigned long writeback_threshold; bool aborted_reclaim; - get_mems_allowed(); delayacct_freepages_start(); if (global_reclaim(sc)) @@ -2401,7 +2408,6 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, out: delayacct_freepages_end(); - put_mems_allowed(); if (sc->nr_reclaimed) return sc->nr_reclaimed; @@ -2724,6 +2730,17 @@ loop_again: */ age_active_anon(zone, &sc, priority); + /* + * If the number of buffer_heads in the machine + * exceeds the maximum allowed level and this node + * has a highmem zone, force kswapd to reclaim from + * it to relieve lowmem pressure. + */ + if (buffer_heads_over_limit && is_highmem_idx(i)) { + end_zone = i; + break; + } + if (!zone_watermark_ok_safe(zone, order, high_wmark_pages(zone), 0, 0)) { end_zone = i; @@ -2753,7 +2770,7 @@ loop_again: */ for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; - int nr_slab; + int nr_slab, testorder; unsigned long balance_gap; if (!populated_zone(zone)) @@ -2786,7 +2803,21 @@ loop_again: (zone->present_pages + KSWAPD_ZONE_BALANCE_GAP_RATIO-1) / KSWAPD_ZONE_BALANCE_GAP_RATIO); - if (!zone_watermark_ok_safe(zone, order, + /* + * Kswapd reclaims only single pages with compaction + * enabled. Trying too hard to reclaim until contiguous + * free pages have become available can hurt performance + * by evicting too much useful data from memory. + * Do not reclaim more than needed for compaction. + */ + testorder = order; + if (COMPACTION_BUILD && order && + compaction_suitable(zone, order) != + COMPACT_SKIPPED) + testorder = 0; + + if ((buffer_heads_over_limit && is_highmem_idx(i)) || + !zone_watermark_ok_safe(zone, testorder, high_wmark_pages(zone) + balance_gap, end_zone, 0)) { shrink_zone(priority, zone, &sc); @@ -2815,7 +2846,7 @@ loop_again: continue; } - if (!zone_watermark_ok_safe(zone, order, + if (!zone_watermark_ok_safe(zone, testorder, high_wmark_pages(zone), end_zone, 0)) { all_zones_ok = 0; /* @@ -2903,6 +2934,8 @@ out: * and it is potentially going to sleep here. */ if (order) { + int zones_need_compaction = 1; + for (i = 0; i <= end_zone; i++) { struct zone *zone = pgdat->node_zones + i; @@ -2912,6 +2945,11 @@ out: if (zone->all_unreclaimable && priority != DEF_PRIORITY) continue; + /* Would compaction fail due to lack of free memory? */ + if (COMPACTION_BUILD && + compaction_suitable(zone, order) == COMPACT_SKIPPED) + goto loop_again; + /* Confirm the zone is balanced for order-0 */ if (!zone_watermark_ok(zone, 0, high_wmark_pages(zone), 0, 0)) { @@ -2919,11 +2957,17 @@ out: goto loop_again; } + /* Check if the memory needs to be defragmented. */ + if (zone_watermark_ok(zone, order, + low_wmark_pages(zone), *classzone_idx, 0)) + zones_need_compaction = 0; + /* If balanced, clear the congested flag */ zone_clear_flag(zone, ZONE_CONGESTED); - if (i <= *classzone_idx) - balanced += zone->present_pages; } + + if (zones_need_compaction) + compact_pgdat(pgdat, order); } /* |