diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 9 | ||||
-rw-r--r-- | mm/backing-dev.c | 4 | ||||
-rw-r--r-- | mm/cleancache.c | 4 | ||||
-rw-r--r-- | mm/filemap.c | 96 | ||||
-rw-r--r-- | mm/gup.c | 4 | ||||
-rw-r--r-- | mm/huge_memory.c | 123 | ||||
-rw-r--r-- | mm/hugetlb.c | 13 | ||||
-rw-r--r-- | mm/internal.h | 31 | ||||
-rw-r--r-- | mm/kasan/Makefile | 1 | ||||
-rw-r--r-- | mm/list_lru.c | 12 | ||||
-rw-r--r-- | mm/memblock.c | 2 | ||||
-rw-r--r-- | mm/memcontrol.c | 858 | ||||
-rw-r--r-- | mm/memory.c | 17 | ||||
-rw-r--r-- | mm/mempolicy.c | 14 | ||||
-rw-r--r-- | mm/mincore.c | 3 | ||||
-rw-r--r-- | mm/mlock.c | 2 | ||||
-rw-r--r-- | mm/mmap.c | 119 | ||||
-rw-r--r-- | mm/mprotect.c | 6 | ||||
-rw-r--r-- | mm/mremap.c | 2 | ||||
-rw-r--r-- | mm/page_alloc.c | 7 | ||||
-rw-r--r-- | mm/percpu.c | 18 | ||||
-rw-r--r-- | mm/pgtable-generic.c | 8 | ||||
-rw-r--r-- | mm/process_vm_access.c | 2 | ||||
-rw-r--r-- | mm/shmem.c | 25 | ||||
-rw-r--r-- | mm/slab.c | 12 | ||||
-rw-r--r-- | mm/slab.h | 7 | ||||
-rw-r--r-- | mm/slab_common.c | 15 | ||||
-rw-r--r-- | mm/slob.c | 4 | ||||
-rw-r--r-- | mm/slub.c | 48 | ||||
-rw-r--r-- | mm/swap_state.c | 5 | ||||
-rw-r--r-- | mm/swapfile.c | 18 | ||||
-rw-r--r-- | mm/truncate.c | 69 | ||||
-rw-r--r-- | mm/util.c | 43 | ||||
-rw-r--r-- | mm/vmpressure.c | 3 | ||||
-rw-r--r-- | mm/vmscan.c | 39 | ||||
-rw-r--r-- | mm/vmstat.c | 82 | ||||
-rw-r--r-- | mm/workingset.c | 4 | ||||
-rw-r--r-- | mm/zsmalloc.c | 14 |
38 files changed, 1052 insertions, 691 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index 97a4e06b15c0..03cbfa072f42 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -624,7 +624,7 @@ config ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT bool config DEFERRED_STRUCT_PAGE_INIT - bool "Defer initialisation of struct pages to kswapd" + bool "Defer initialisation of struct pages to kthreads" default n depends on ARCH_SUPPORTS_DEFERRED_STRUCT_PAGE_INIT depends on MEMORY_HOTPLUG @@ -633,9 +633,10 @@ config DEFERRED_STRUCT_PAGE_INIT single thread. On very large machines this can take a considerable amount of time. If this option is set, large machines will bring up a subset of memmap at boot and then initialise the rest in parallel - when kswapd starts. This has a potential performance impact on - processes running early in the lifetime of the systemm until kswapd - finishes the initialisation. + by starting one-off "pgdatinitX" kernel thread for each node X. This + has a potential performance impact on processes running early in the + lifetime of the system until these kthreads finish the + initialisation. config IDLE_PAGE_TRACKING bool "Enable idle page tracking" diff --git a/mm/backing-dev.c b/mm/backing-dev.c index cc5d29d2da9b..c554d173a65f 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -328,7 +328,7 @@ static int wb_init(struct bdi_writeback *wb, struct backing_dev_info *bdi, return 0; out_destroy_stat: - while (--i) + while (i--) percpu_counter_destroy(&wb->stat[i]); fprop_local_destroy_percpu(&wb->completions); out_put_cong: @@ -989,7 +989,7 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) * here rather than calling cond_resched(). */ if (current->flags & PF_WQ_WORKER) - schedule_timeout(1); + schedule_timeout_uninterruptible(1); else cond_resched(); diff --git a/mm/cleancache.c b/mm/cleancache.c index 8fc50811119b..ba5d8f3e6d68 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -22,7 +22,7 @@ * cleancache_ops is set by cleancache_register_ops to contain the pointers * to the cleancache "backend" implementation functions. */ -static struct cleancache_ops *cleancache_ops __read_mostly; +static const struct cleancache_ops *cleancache_ops __read_mostly; /* * Counters available via /sys/kernel/debug/cleancache (if debugfs is @@ -49,7 +49,7 @@ static void cleancache_register_ops_sb(struct super_block *sb, void *unused) /* * Register operations for cleancache. Returns 0 on success. */ -int cleancache_register_ops(struct cleancache_ops *ops) +int cleancache_register_ops(const struct cleancache_ops *ops) { if (cmpxchg(&cleancache_ops, NULL, ops)) return -EBUSY; diff --git a/mm/filemap.c b/mm/filemap.c index 847ee43c2806..23edccecadb0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -11,6 +11,7 @@ */ #include <linux/export.h> #include <linux/compiler.h> +#include <linux/dax.h> #include <linux/fs.h> #include <linux/uaccess.h> #include <linux/capability.h> @@ -123,9 +124,9 @@ static void page_cache_tree_delete(struct address_space *mapping, __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); if (shadow) { - mapping->nrshadows++; + mapping->nrexceptional++; /* - * Make sure the nrshadows update is committed before + * Make sure the nrexceptional update is committed before * the nrpages update so that final truncate racing * with reclaim does not see both counters 0 at the * same time and miss a shadow entry. @@ -481,6 +482,12 @@ int filemap_write_and_wait_range(struct address_space *mapping, { int err = 0; + if (dax_mapping(mapping) && mapping->nrexceptional) { + err = dax_writeback_mapping_range(mapping, lstart, lend); + if (err) + return err; + } + if (mapping->nrpages) { err = __filemap_fdatawrite_range(mapping, lstart, lend, WB_SYNC_ALL); @@ -579,9 +586,13 @@ static int page_cache_tree_insert(struct address_space *mapping, p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); if (!radix_tree_exceptional_entry(p)) return -EEXIST; + + if (WARN_ON(dax_mapping(mapping))) + return -EINVAL; + if (shadowp) *shadowp = p; - mapping->nrshadows--; + mapping->nrexceptional--; if (node) workingset_node_shadows_dec(node); } @@ -1245,9 +1256,9 @@ repeat: if (radix_tree_deref_retry(page)) goto restart; /* - * A shadow entry of a recently evicted page, - * or a swap entry from shmem/tmpfs. Return - * it without attempting to raise page count. + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. */ goto export; } @@ -1494,6 +1505,74 @@ repeat: } EXPORT_SYMBOL(find_get_pages_tag); +/** + * find_get_entries_tag - find and return entries that match @tag + * @mapping: the address_space to search + * @start: the starting page cache index + * @tag: the tag index + * @nr_entries: the maximum number of entries + * @entries: where the resulting entries are placed + * @indices: the cache indices corresponding to the entries in @entries + * + * Like find_get_entries, except we only return entries which are tagged with + * @tag. + */ +unsigned find_get_entries_tag(struct address_space *mapping, pgoff_t start, + int tag, unsigned int nr_entries, + struct page **entries, pgoff_t *indices) +{ + void **slot; + unsigned int ret = 0; + struct radix_tree_iter iter; + + if (!nr_entries) + return 0; + + rcu_read_lock(); +restart: + radix_tree_for_each_tagged(slot, &mapping->page_tree, + &iter, start, tag) { + struct page *page; +repeat: + page = radix_tree_deref_slot(slot); + if (unlikely(!page)) + continue; + if (radix_tree_exception(page)) { + if (radix_tree_deref_retry(page)) { + /* + * Transient condition which can only trigger + * when entry at index 0 moves out of or back + * to root: none yet gotten, safe to restart. + */ + goto restart; + } + + /* + * A shadow entry of a recently evicted page, a swap + * entry from shmem/tmpfs or a DAX entry. Return it + * without attempting to raise page count. + */ + goto export; + } + if (!page_cache_get_speculative(page)) + goto repeat; + + /* Has the page moved? */ + if (unlikely(page != *slot)) { + page_cache_release(page); + goto repeat; + } +export: + indices[ret] = iter.index; + entries[ret] = page; + if (++ret == nr_entries) + break; + } + rcu_read_unlock(); + return ret; +} +EXPORT_SYMBOL(find_get_entries_tag); + /* * CD/DVDs are error prone. When a medium error occurs, the driver may fail * a _large_ part of the i/o request. Imagine the worst scenario: @@ -1811,6 +1890,7 @@ EXPORT_SYMBOL(generic_file_read_iter); * page_cache_read - adds requested page to the page cache if not already there * @file: file to read * @offset: page index + * @gfp_mask: memory allocation flags * * This adds the requested page to the page cache if it isn't already there, * and schedules an I/O to read in its contents from disk. @@ -2684,11 +2764,11 @@ ssize_t generic_file_write_iter(struct kiocb *iocb, struct iov_iter *from) struct inode *inode = file->f_mapping->host; ssize_t ret; - mutex_lock(&inode->i_mutex); + inode_lock(inode); ret = generic_write_checks(iocb, from); if (ret > 0) ret = __generic_file_write_iter(iocb, from); - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); if (ret > 0) { ssize_t err; @@ -430,10 +430,8 @@ static int check_vma_flags(struct vm_area_struct *vma, unsigned long gup_flags) * Anon pages in shared mappings are surprising: now * just reject it. */ - if (!is_cow_mapping(vm_flags)) { - WARN_ON_ONCE(vm_flags & VM_MAYWRITE); + if (!is_cow_mapping(vm_flags)) return -EFAULT; - } } } else if (!(vm_flags & VM_READ)) { if (!(gup_flags & FOLL_FORCE)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index de3f43cde129..1c317b85ea7d 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -138,9 +138,6 @@ static struct khugepaged_scan khugepaged_scan = { .mm_head = LIST_HEAD_INIT(khugepaged_scan.mm_head), }; -static DEFINE_SPINLOCK(split_queue_lock); -static LIST_HEAD(split_queue); -static unsigned long split_queue_len; static struct shrinker deferred_split_shrinker; static void set_recommended_min_free_kbytes(void) @@ -861,7 +858,8 @@ static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, return false; entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_mkhuge(entry); - pgtable_trans_huge_deposit(mm, pmd, pgtable); + if (pgtable) + pgtable_trans_huge_deposit(mm, pmd, pgtable); set_pmd_at(mm, haddr, pmd, entry); atomic_long_inc(&mm->nr_ptes); return true; @@ -1039,13 +1037,15 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, spinlock_t *dst_ptl, *src_ptl; struct page *src_page; pmd_t pmd; - pgtable_t pgtable; + pgtable_t pgtable = NULL; int ret; - ret = -ENOMEM; - pgtable = pte_alloc_one(dst_mm, addr); - if (unlikely(!pgtable)) - goto out; + if (!vma_is_dax(vma)) { + ret = -ENOMEM; + pgtable = pte_alloc_one(dst_mm, addr); + if (unlikely(!pgtable)) + goto out; + } dst_ptl = pmd_lock(dst_mm, dst_pmd); src_ptl = pmd_lockptr(src_mm, src_pmd); @@ -1076,7 +1076,7 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, goto out_unlock; } - if (pmd_trans_huge(pmd)) { + if (!vma_is_dax(vma)) { /* thp accounting separate from pmd_devmap accounting */ src_page = pmd_page(pmd); VM_BUG_ON_PAGE(!PageHead(src_page), src_page); @@ -1560,7 +1560,8 @@ int madvise_free_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, struct mm_struct *mm = tlb->mm; int ret = 0; - if (!pmd_trans_huge_lock(pmd, vma, &ptl)) + ptl = pmd_trans_huge_lock(pmd, vma); + if (!ptl) goto out_unlocked; orig_pmd = *pmd; @@ -1627,7 +1628,8 @@ int zap_huge_pmd(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t orig_pmd; spinlock_t *ptl; - if (!__pmd_trans_huge_lock(pmd, vma, &ptl)) + ptl = __pmd_trans_huge_lock(pmd, vma); + if (!ptl) return 0; /* * For architectures like ppc64 we look at deposited pgtable @@ -1690,14 +1692,16 @@ bool move_huge_pmd(struct vm_area_struct *vma, struct vm_area_struct *new_vma, * We don't have to worry about the ordering of src and dst * ptlocks because exclusive mmap_sem prevents deadlock. */ - if (__pmd_trans_huge_lock(old_pmd, vma, &old_ptl)) { + old_ptl = __pmd_trans_huge_lock(old_pmd, vma); + if (old_ptl) { new_ptl = pmd_lockptr(mm, new_pmd); if (new_ptl != old_ptl) spin_lock_nested(new_ptl, SINGLE_DEPTH_NESTING); pmd = pmdp_huge_get_and_clear(mm, old_addr, old_pmd); VM_BUG_ON(!pmd_none(*new_pmd)); - if (pmd_move_must_withdraw(new_ptl, old_ptl)) { + if (pmd_move_must_withdraw(new_ptl, old_ptl) && + vma_is_anonymous(vma)) { pgtable_t pgtable; pgtable = pgtable_trans_huge_withdraw(mm, old_pmd); pgtable_trans_huge_deposit(mm, new_pmd, pgtable); @@ -1724,7 +1728,8 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, spinlock_t *ptl; int ret = 0; - if (__pmd_trans_huge_lock(pmd, vma, &ptl)) { + ptl = __pmd_trans_huge_lock(pmd, vma); + if (ptl) { pmd_t entry; bool preserve_write = prot_numa && pmd_write(*pmd); ret = 1; @@ -1760,14 +1765,14 @@ int change_huge_pmd(struct vm_area_struct *vma, pmd_t *pmd, * Note that if it returns true, this routine returns without unlocking page * table lock. So callers must unlock it. */ -bool __pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma, - spinlock_t **ptl) +spinlock_t *__pmd_trans_huge_lock(pmd_t *pmd, struct vm_area_struct *vma) { - *ptl = pmd_lock(vma->vm_mm, pmd); + spinlock_t *ptl; + ptl = pmd_lock(vma->vm_mm, pmd); if (likely(pmd_trans_huge(*pmd) || pmd_devmap(*pmd))) - return true; - spin_unlock(*ptl); - return false; + return ptl; + spin_unlock(ptl); + return NULL; } #define VM_NO_THP (VM_SPECIAL | VM_HUGETLB | VM_SHARED | VM_MAYSHARE) @@ -2068,7 +2073,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, if (likely(writable)) { if (likely(referenced)) { result = SCAN_SUCCEED; - trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero, + trace_mm_collapse_huge_page_isolate(page, none_or_zero, referenced, writable, result); return 1; } @@ -2078,7 +2083,7 @@ static int __collapse_huge_page_isolate(struct vm_area_struct *vma, out: release_pte_pages(pte, _pte); - trace_mm_collapse_huge_page_isolate(page_to_pfn(page), none_or_zero, + trace_mm_collapse_huge_page_isolate(page, none_or_zero, referenced, writable, result); return 0; } @@ -2576,7 +2581,7 @@ out_unmap: collapse_huge_page(mm, address, hpage, vma, node); } out: - trace_mm_khugepaged_scan_pmd(mm, page_to_pfn(page), writable, referenced, + trace_mm_khugepaged_scan_pmd(mm, page, writable, referenced, none_or_zero, result); return ret; } @@ -3355,9 +3360,11 @@ int total_mapcount(struct page *page) int split_huge_page_to_list(struct page *page, struct list_head *list) { struct page *head = compound_head(page); + struct pglist_data *pgdata = NODE_DATA(page_to_nid(head)); struct anon_vma *anon_vma; int count, mapcount, ret; bool mlocked; + unsigned long flags; VM_BUG_ON_PAGE(is_huge_zero_page(page), page); VM_BUG_ON_PAGE(!PageAnon(page), page); @@ -3397,19 +3404,19 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) lru_add_drain(); /* Prevent deferred_split_scan() touching ->_count */ - spin_lock(&split_queue_lock); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); count = page_count(head); mapcount = total_mapcount(head); if (!mapcount && count == 1) { if (!list_empty(page_deferred_list(head))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(head)); } - spin_unlock(&split_queue_lock); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); __split_huge_page(page, list); ret = 0; } else if (IS_ENABLED(CONFIG_DEBUG_VM) && mapcount) { - spin_unlock(&split_queue_lock); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); pr_alert("total_mapcount: %u, page_count(): %u\n", mapcount, count); if (PageTail(page)) @@ -3417,7 +3424,7 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) dump_page(page, "total_mapcount(head) > 0"); BUG(); } else { - spin_unlock(&split_queue_lock); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); unfreeze_page(anon_vma, head); ret = -EBUSY; } @@ -3432,64 +3439,65 @@ out: void free_transhuge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (!list_empty(page_deferred_list(page))) { - split_queue_len--; + pgdata->split_queue_len--; list_del(page_deferred_list(page)); } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); free_compound_page(page); } void deferred_split_huge_page(struct page *page) { + struct pglist_data *pgdata = NODE_DATA(page_to_nid(page)); unsigned long flags; VM_BUG_ON_PAGE(!PageTransHuge(page), page); - spin_lock_irqsave(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); if (list_empty(page_deferred_list(page))) { - list_add_tail(page_deferred_list(page), &split_queue); - split_queue_len++; + list_add_tail(page_deferred_list(page), &pgdata->split_queue); + pgdata->split_queue_len++; } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); } static unsigned long deferred_split_count(struct shrinker *shrink, struct shrink_control *sc) { - /* - * Split a page from split_queue will free up at least one page, - * at most HPAGE_PMD_NR - 1. We don't track exact number. - * Let's use HPAGE_PMD_NR / 2 as ballpark. - */ - return ACCESS_ONCE(split_queue_len) * HPAGE_PMD_NR / 2; + struct pglist_data *pgdata = NODE_DATA(sc->nid); + return ACCESS_ONCE(pgdata->split_queue_len); } static unsigned long deferred_split_scan(struct shrinker *shrink, struct shrink_control *sc) { + struct pglist_data *pgdata = NODE_DATA(sc->nid); unsigned long flags; LIST_HEAD(list), *pos, *next; struct page *page; int split = 0; - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_init(&split_queue, &list); - + spin_lock_irqsave(&pgdata->split_queue_lock, flags); /* Take pin on all head pages to avoid freeing them under us */ - list_for_each_safe(pos, next, &list) { + list_for_each_safe(pos, next, &pgdata->split_queue) { page = list_entry((void *)pos, struct page, mapping); page = compound_head(page); - /* race with put_compound_page() */ - if (!get_page_unless_zero(page)) { + if (get_page_unless_zero(page)) { + list_move(page_deferred_list(page), &list); + } else { + /* We lost race with put_compound_page() */ list_del_init(page_deferred_list(page)); - split_queue_len--; + pgdata->split_queue_len--; } + if (!--sc->nr_to_scan) + break; } - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); list_for_each_safe(pos, next, &list) { page = list_entry((void *)pos, struct page, mapping); @@ -3501,17 +3509,24 @@ static unsigned long deferred_split_scan(struct shrinker *shrink, put_page(page); } - spin_lock_irqsave(&split_queue_lock, flags); - list_splice_tail(&list, &split_queue); - spin_unlock_irqrestore(&split_queue_lock, flags); + spin_lock_irqsave(&pgdata->split_queue_lock, flags); + list_splice_tail(&list, &pgdata->split_queue); + spin_unlock_irqrestore(&pgdata->split_queue_lock, flags); - return split * HPAGE_PMD_NR / 2; + /* + * Stop shrinker if we didn't split any page, but the queue is empty. + * This can happen if pages were freed under us. + */ + if (!split && list_empty(&pgdata->split_queue)) + return SHRINK_STOP; + return split; } static struct shrinker deferred_split_shrinker = { .count_objects = deferred_split_count, .scan_objects = deferred_split_scan, .seeks = DEFAULT_SEEKS, + .flags = SHRINKER_NUMA_AWARE, }; #ifdef CONFIG_DEBUG_FS diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 12908dcf5831..01f2b48c8618 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1001,7 +1001,7 @@ static int hstate_next_node_to_free(struct hstate *h, nodemask_t *nodes_allowed) ((node = hstate_next_node_to_free(hs, mask)) || 1); \ nr_nodes--) -#if defined(CONFIG_CMA) && defined(CONFIG_X86_64) +#if defined(CONFIG_X86_64) && ((defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA)) static void destroy_compound_gigantic_page(struct page *page, unsigned int order) { @@ -1214,8 +1214,8 @@ void free_huge_page(struct page *page) set_page_private(page, 0); page->mapping = NULL; - BUG_ON(page_count(page)); - BUG_ON(page_mapcount(page)); + VM_BUG_ON_PAGE(page_count(page), page); + VM_BUG_ON_PAGE(page_mapcount(page), page); restore_reserve = PagePrivate(page); ClearPagePrivate(page); @@ -1286,6 +1286,7 @@ static void prep_compound_gigantic_page(struct page *page, unsigned int order) set_page_count(p, 0); set_compound_head(p, page); } + atomic_set(compound_mapcount_ptr(page), -1); } /* @@ -2629,8 +2630,10 @@ static int __init hugetlb_init(void) hugetlb_add_hstate(HUGETLB_PAGE_ORDER); } default_hstate_idx = hstate_index(size_to_hstate(default_hstate_size)); - if (default_hstate_max_huge_pages) - default_hstate.max_huge_pages = default_hstate_max_huge_pages; + if (default_hstate_max_huge_pages) { + if (!default_hstate.max_huge_pages) + default_hstate.max_huge_pages = default_hstate_max_huge_pages; + } hugetlb_init_hstates(); gather_bootmem_prealloc(); diff --git a/mm/internal.h b/mm/internal.h index ed8b5ffcf9b1..a38a21ebddb4 100644 --- a/mm/internal.h +++ b/mm/internal.h @@ -216,6 +216,37 @@ static inline bool is_cow_mapping(vm_flags_t flags) return (flags & (VM_SHARED | VM_MAYWRITE)) == VM_MAYWRITE; } +/* + * These three helpers classifies VMAs for virtual memory accounting. + */ + +/* + * Executable code area - executable, not writable, not stack + */ +static inline bool is_exec_mapping(vm_flags_t flags) +{ + return (flags & (VM_EXEC | VM_WRITE | VM_STACK)) == VM_EXEC; +} + +/* + * Stack area - atomatically grows in one direction + * + * VM_GROWSUP / VM_GROWSDOWN VMAs are always private anonymous: + * do_mmap() forbids all other combinations. + */ +static inline bool is_stack_mapping(vm_flags_t flags) +{ + return (flags & VM_STACK) == VM_STACK; +} + +/* + * Data area - private, writable, not stack + */ +static inline bool is_data_mapping(vm_flags_t flags) +{ + return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE; +} + /* mm/util.c */ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, struct rb_node *rb_parent); diff --git a/mm/kasan/Makefile b/mm/kasan/Makefile index 64710148941e..a61460d9f5b0 100644 --- a/mm/kasan/Makefile +++ b/mm/kasan/Makefile @@ -1,4 +1,5 @@ KASAN_SANITIZE := n +UBSAN_SANITIZE_kasan.o := n CFLAGS_REMOVE_kasan.o = -pg # Function splitter causes unnecessary splits in __asan_load1/__asan_store1 diff --git a/mm/list_lru.c b/mm/list_lru.c index afc71ea9a381..1d05cb9d363d 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -12,7 +12,7 @@ #include <linux/mutex.h> #include <linux/memcontrol.h> -#ifdef CONFIG_MEMCG_KMEM +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) static LIST_HEAD(list_lrus); static DEFINE_MUTEX(list_lrus_mutex); @@ -37,9 +37,9 @@ static void list_lru_register(struct list_lru *lru) static void list_lru_unregister(struct list_lru *lru) { } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ -#ifdef CONFIG_MEMCG_KMEM +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) static inline bool list_lru_memcg_aware(struct list_lru *lru) { /* @@ -104,7 +104,7 @@ list_lru_from_kmem(struct list_lru_node *nlru, void *ptr) { return &nlru->lru; } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ bool list_lru_add(struct list_lru *lru, struct list_head *item) { @@ -292,7 +292,7 @@ static void init_one_lru(struct list_lru_one *l) l->nr_items = 0; } -#ifdef CONFIG_MEMCG_KMEM +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) static void __memcg_destroy_list_lru_node(struct list_lru_memcg *memcg_lrus, int begin, int end) { @@ -529,7 +529,7 @@ static int memcg_init_list_lru(struct list_lru *lru, bool memcg_aware) static void memcg_destroy_list_lru(struct list_lru *lru) { } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ int __list_lru_init(struct list_lru *lru, bool memcg_aware, struct lock_class_key *key) diff --git a/mm/memblock.c b/mm/memblock.c index d2ed81e59a94..dd7989929f13 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1448,7 +1448,7 @@ void __init __memblock_free_late(phys_addr_t base, phys_addr_t size) * Remaining API functions */ -phys_addr_t __init memblock_phys_mem_size(void) +phys_addr_t __init_memblock memblock_phys_mem_size(void) { return memblock.memory.total_size; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 0eda67376df4..d06cae2de783 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -66,7 +66,6 @@ #include "internal.h" #include <net/sock.h> #include <net/ip.h> -#include <net/tcp_memcontrol.h> #include "slab.h" #include <asm/uaccess.h> @@ -83,6 +82,9 @@ struct mem_cgroup *root_mem_cgroup __read_mostly; /* Socket memory accounting disabled? */ static bool cgroup_memory_nosocket; +/* Kernel memory accounting disabled? */ +static bool cgroup_memory_nokmem; + /* Whether the swap controller is active */ #ifdef CONFIG_MEMCG_SWAP int do_swap_account __read_mostly; @@ -239,6 +241,7 @@ enum res_type { _MEMSWAP, _OOM_TYPE, _KMEM, + _TCP, }; #define MEMFILE_PRIVATE(x, val) ((x) << 16 | (val)) @@ -247,13 +250,6 @@ enum res_type { /* Used for OOM nofiier */ #define OOM_CONTROL (0) -/* - * The memcg_create_mutex will be held whenever a new cgroup is created. - * As a consequence, any change that needs to protect against new child cgroups - * appearing has to hold it as well. - */ -static DEFINE_MUTEX(memcg_create_mutex); - /* Some nice accessors for the vmpressure. */ struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) { @@ -297,7 +293,7 @@ static inline struct mem_cgroup *mem_cgroup_from_id(unsigned short id) return mem_cgroup_from_css(css); } -#ifdef CONFIG_MEMCG_KMEM +#ifndef CONFIG_SLOB /* * This will be the memcg's index in each cache's ->memcg_params.memcg_caches. * The main reason for not using cgroup id for this: @@ -349,7 +345,7 @@ void memcg_put_cache_ids(void) DEFINE_STATIC_KEY_FALSE(memcg_kmem_enabled_key); EXPORT_SYMBOL(memcg_kmem_enabled_key); -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* !CONFIG_SLOB */ static struct mem_cgroup_per_zone * mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) @@ -370,13 +366,6 @@ mem_cgroup_zone_zoneinfo(struct mem_cgroup *memcg, struct zone *zone) * * If memcg is bound to a traditional hierarchy, the css of root_mem_cgroup * is returned. - * - * XXX: The above description of behavior on the default hierarchy isn't - * strictly true yet as replace_page_cache_page() can modify the - * association before @page is released even on the default hierarchy; - * however, the current and planned usages don't mix the the two functions - * and replace_page_cache_page() will soon be updated to make the invariant - * actually true. */ struct cgroup_subsys_state *mem_cgroup_css_from_page(struct page *page) { @@ -896,17 +885,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, if (css == &root->css) break; - if (css_tryget(css)) { - /* - * Make sure the memcg is initialized: - * mem_cgroup_css_online() orders the the - * initialization against setting the flag. - */ - if (smp_load_acquire(&memcg->initialized)) - break; - - css_put(css); - } + if (css_tryget(css)) + break; memcg = NULL; } @@ -1233,7 +1213,7 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) pr_cont(":"); for (i = 0; i < MEM_CGROUP_STAT_NSTATS; i++) { - if (i == MEM_CGROUP_STAT_SWAP && !do_memsw_account()) + if (i == MEM_CGROUP_STAT_SWAP && !do_swap_account) continue; pr_cont(" %s:%luKB", mem_cgroup_stat_names[i], K(mem_cgroup_read_stat(iter, i))); @@ -1272,9 +1252,12 @@ static unsigned long mem_cgroup_get_limit(struct mem_cgroup *memcg) limit = memcg->memory.limit; if (mem_cgroup_swappiness(memcg)) { unsigned long memsw_limit; + unsigned long swap_limit; memsw_limit = memcg->memsw.limit; - limit = min(limit + total_swap_pages, memsw_limit); + swap_limit = memcg->swap.limit; + swap_limit = min(swap_limit, (unsigned long)total_swap_pages); + limit = min(limit + swap_limit, memsw_limit); } return limit; } @@ -2203,7 +2186,7 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, unlock_page_lru(page, isolated); } -#ifdef CONFIG_MEMCG_KMEM +#ifndef CONFIG_SLOB static int memcg_alloc_cache_id(void) { int id, size; @@ -2378,16 +2361,17 @@ int __memcg_kmem_charge_memcg(struct page *page, gfp_t gfp, int order, struct page_counter *counter; int ret; - if (!memcg_kmem_is_active(memcg)) + if (!memcg_kmem_online(memcg)) return 0; - if (!page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) - return -ENOMEM; - ret = try_charge(memcg, gfp, nr_pages); - if (ret) { - page_counter_uncharge(&memcg->kmem, nr_pages); + if (ret) return ret; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && + !page_counter_try_charge(&memcg->kmem, nr_pages, &counter)) { + cancel_charge(memcg, nr_pages); + return -ENOMEM; } page->mem_cgroup = memcg; @@ -2416,7 +2400,9 @@ void __memcg_kmem_uncharge(struct page *page, int order) VM_BUG_ON_PAGE(mem_cgroup_is_root(memcg), page); - page_counter_uncharge(&memcg->kmem, nr_pages); + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) + page_counter_uncharge(&memcg->kmem, nr_pages); + page_counter_uncharge(&memcg->memory, nr_pages); if (do_memsw_account()) page_counter_uncharge(&memcg->memsw, nr_pages); @@ -2424,7 +2410,7 @@ void __memcg_kmem_uncharge(struct page *page, int order) page->mem_cgroup = NULL; css_put_many(&memcg->css, nr_pages); } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* !CONFIG_SLOB */ #ifdef CONFIG_TRANSPARENT_HUGEPAGE @@ -2684,14 +2670,6 @@ static inline bool memcg_has_children(struct mem_cgroup *memcg) { bool ret; - /* - * The lock does not prevent addition or deletion of children, but - * it prevents a new child from being initialized based on this - * parent in css_online(), so it's enough to decide whether - * hierarchically inherited attributes can still be changed or not. - */ - lockdep_assert_held(&memcg_create_mutex); - rcu_read_lock(); ret = css_next_child(NULL, &memcg->css); rcu_read_unlock(); @@ -2754,10 +2732,8 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, struct mem_cgroup *memcg = mem_cgroup_from_css(css); struct mem_cgroup *parent_memcg = mem_cgroup_from_css(memcg->css.parent); - mutex_lock(&memcg_create_mutex); - if (memcg->use_hierarchy == val) - goto out; + return 0; /* * If parent's use_hierarchy is set, we can't make any modifications @@ -2776,9 +2752,6 @@ static int mem_cgroup_hierarchy_write(struct cgroup_subsys_state *css, } else retval = -EINVAL; -out: - mutex_unlock(&memcg_create_mutex); - return retval; } @@ -2794,6 +2767,18 @@ static unsigned long tree_stat(struct mem_cgroup *memcg, return val; } +static unsigned long tree_events(struct mem_cgroup *memcg, + enum mem_cgroup_events_index idx) +{ + struct mem_cgroup *iter; + unsigned long val = 0; + + for_each_mem_cgroup_tree(iter, memcg) + val += mem_cgroup_read_events(iter, idx); + + return val; +} + static unsigned long mem_cgroup_usage(struct mem_cgroup *memcg, bool swap) { unsigned long val; @@ -2836,6 +2821,9 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, case _KMEM: counter = &memcg->kmem; break; + case _TCP: + counter = &memcg->tcpmem; + break; default: BUG(); } @@ -2860,103 +2848,180 @@ static u64 mem_cgroup_read_u64(struct cgroup_subsys_state *css, } } -#ifdef CONFIG_MEMCG_KMEM -static int memcg_activate_kmem(struct mem_cgroup *memcg, - unsigned long nr_pages) +#ifndef CONFIG_SLOB +static int memcg_online_kmem(struct mem_cgroup *memcg) { - int err = 0; int memcg_id; BUG_ON(memcg->kmemcg_id >= 0); - BUG_ON(memcg->kmem_acct_activated); - BUG_ON(memcg->kmem_acct_active); - - /* - * For simplicity, we won't allow this to be disabled. It also can't - * be changed if the cgroup has children already, or if tasks had - * already joined. - * - * If tasks join before we set the limit, a person looking at - * kmem.usage_in_bytes will have no way to determine when it took - * place, which makes the value quite meaningless. - * - * After it first became limited, changes in the value of the limit are - * of course permitted. - */ - mutex_lock(&memcg_create_mutex); - if (cgroup_is_populated(memcg->css.cgroup) || - (memcg->use_hierarchy && memcg_has_children(memcg))) - err = -EBUSY; - mutex_unlock(&memcg_create_mutex); - if (err) - goto out; + BUG_ON(memcg->kmem_state); memcg_id = memcg_alloc_cache_id(); - if (memcg_id < 0) { - err = memcg_id; - goto out; - } - - /* - * We couldn't have accounted to this cgroup, because it hasn't got - * activated yet, so this should succeed. - */ - err = page_counter_limit(&memcg->kmem, nr_pages); - VM_BUG_ON(err); + if (memcg_id < 0) + return memcg_id; static_branch_inc(&memcg_kmem_enabled_key); /* - * A memory cgroup is considered kmem-active as soon as it gets + * A memory cgroup is considered kmem-online as soon as it gets * kmemcg_id. Setting the id after enabling static branching will * guarantee no one starts accounting before all call sites are * patched. */ memcg->kmemcg_id = memcg_id; - memcg->kmem_acct_activated = true; - memcg->kmem_acct_active = true; -out: - return err; + memcg->kmem_state = KMEM_ONLINE; + + return 0; } -static int memcg_update_kmem_limit(struct mem_cgroup *memcg, - unsigned long limit) +static int memcg_propagate_kmem(struct mem_cgroup *parent, + struct mem_cgroup *memcg) { - int ret; + int ret = 0; mutex_lock(&memcg_limit_mutex); - if (!memcg_kmem_is_active(memcg)) - ret = memcg_activate_kmem(memcg, limit); - else - ret = page_counter_limit(&memcg->kmem, limit); + /* + * If the parent cgroup is not kmem-online now, it cannot be + * onlined after this point, because it has at least one child + * already. + */ + if (memcg_kmem_online(parent) || + (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nokmem)) + ret = memcg_online_kmem(memcg); mutex_unlock(&memcg_limit_mutex); return ret; } -static int memcg_propagate_kmem(struct mem_cgroup *memcg) +static void memcg_offline_kmem(struct mem_cgroup *memcg) { - int ret = 0; - struct mem_cgroup *parent = parent_mem_cgroup(memcg); + struct cgroup_subsys_state *css; + struct mem_cgroup *parent, *child; + int kmemcg_id; + + if (memcg->kmem_state != KMEM_ONLINE) + return; + /* + * Clear the online state before clearing memcg_caches array + * entries. The slab_mutex in memcg_deactivate_kmem_caches() + * guarantees that no cache will be created for this cgroup + * after we are done (see memcg_create_kmem_cache()). + */ + memcg->kmem_state = KMEM_ALLOCATED; + memcg_deactivate_kmem_caches(memcg); + + kmemcg_id = memcg->kmemcg_id; + BUG_ON(kmemcg_id < 0); + + parent = parent_mem_cgroup(memcg); if (!parent) - return 0; + parent = root_mem_cgroup; - mutex_lock(&memcg_limit_mutex); /* - * If the parent cgroup is not kmem-active now, it cannot be activated - * after this point, because it has at least one child already. + * Change kmemcg_id of this cgroup and all its descendants to the + * parent's id, and then move all entries from this cgroup's list_lrus + * to ones of the parent. After we have finished, all list_lrus + * corresponding to this cgroup are guaranteed to remain empty. The + * ordering is imposed by list_lru_node->lock taken by + * memcg_drain_all_list_lrus(). */ - if (memcg_kmem_is_active(parent)) - ret = memcg_activate_kmem(memcg, PAGE_COUNTER_MAX); - mutex_unlock(&memcg_limit_mutex); - return ret; + css_for_each_descendant_pre(css, &memcg->css) { + child = mem_cgroup_from_css(css); + BUG_ON(child->kmemcg_id != kmemcg_id); + child->kmemcg_id = parent->kmemcg_id; + if (!memcg->use_hierarchy) + break; + } + memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id); + + memcg_free_cache_id(kmemcg_id); +} + +static void memcg_free_kmem(struct mem_cgroup *memcg) +{ + /* css_alloc() failed, offlining didn't happen */ + if (unlikely(memcg->kmem_state == KMEM_ONLINE)) + memcg_offline_kmem(memcg); + + if (memcg->kmem_state == KMEM_ALLOCATED) { + memcg_destroy_kmem_caches(memcg); + static_branch_dec(&memcg_kmem_enabled_key); + WARN_ON(page_counter_read(&memcg->kmem)); + } } #else +static int memcg_propagate_kmem(struct mem_cgroup *parent, struct mem_cgroup *memcg) +{ + return 0; +} +static int memcg_online_kmem(struct mem_cgroup *memcg) +{ + return 0; +} +static void memcg_offline_kmem(struct mem_cgroup *memcg) +{ +} +static void memcg_free_kmem(struct mem_cgroup *memcg) +{ +} +#endif /* !CONFIG_SLOB */ + static int memcg_update_kmem_limit(struct mem_cgroup *memcg, unsigned long limit) { - return -EINVAL; + int ret = 0; + + mutex_lock(&memcg_limit_mutex); + /* Top-level cgroup doesn't propagate from root */ + if (!memcg_kmem_online(memcg)) { + if (cgroup_is_populated(memcg->css.cgroup) || + (memcg->use_hierarchy && memcg_has_children(memcg))) + ret = -EBUSY; + if (ret) + goto out; + ret = memcg_online_kmem(memcg); + if (ret) + goto out; + } + ret = page_counter_limit(&memcg->kmem, limit); +out: + mutex_unlock(&memcg_limit_mutex); + return ret; +} + +static int memcg_update_tcp_limit(struct mem_cgroup *memcg, unsigned long limit) +{ + int ret; + + mutex_lock(&memcg_limit_mutex); + + ret = page_counter_limit(&memcg->tcpmem, limit); + if (ret) + goto out; + + if (!memcg->tcpmem_active) { + /* + * The active flag needs to be written after the static_key + * update. This is what guarantees that the socket activation + * function is the last one to run. See sock_update_memcg() for + * details, and note that we don't mark any socket as belonging + * to this memcg until that flag is up. + * + * We need to do this, because static_keys will span multiple + * sites, but we can't control their order. If we mark a socket + * as accounted, but the accounting functions are not patched in + * yet, we'll lose accounting. + * + * We never race with the readers in sock_update_memcg(), + * because when this value change, the code to process it is not + * patched in yet. + */ + static_branch_inc(&memcg_sockets_enabled_key); + memcg->tcpmem_active = true; + } +out: + mutex_unlock(&memcg_limit_mutex); + return ret; } -#endif /* CONFIG_MEMCG_KMEM */ /* * The user of this function is... @@ -2990,6 +3055,9 @@ static ssize_t mem_cgroup_write(struct kernfs_open_file *of, case _KMEM: ret = memcg_update_kmem_limit(memcg, nr_pages); break; + case _TCP: + ret = memcg_update_tcp_limit(memcg, nr_pages); + break; } break; case RES_SOFT_LIMIT: @@ -3016,6 +3084,9 @@ static ssize_t mem_cgroup_reset(struct kernfs_open_file *of, char *buf, case _KMEM: counter = &memcg->kmem; break; + case _TCP: + counter = &memcg->tcpmem; + break; default: BUG(); } @@ -3582,88 +3653,6 @@ static int mem_cgroup_oom_control_write(struct cgroup_subsys_state *css, return 0; } -#ifdef CONFIG_MEMCG_KMEM -static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - int ret; - - ret = memcg_propagate_kmem(memcg); - if (ret) - return ret; - - return tcp_init_cgroup(memcg, ss); -} - -static void memcg_deactivate_kmem(struct mem_cgroup *memcg) -{ - struct cgroup_subsys_state *css; - struct mem_cgroup *parent, *child; - int kmemcg_id; - - if (!memcg->kmem_acct_active) - return; - - /* - * Clear the 'active' flag before clearing memcg_caches arrays entries. - * Since we take the slab_mutex in memcg_deactivate_kmem_caches(), it - * guarantees no cache will be created for this cgroup after we are - * done (see memcg_create_kmem_cache()). - */ - memcg->kmem_acct_active = false; - - memcg_deactivate_kmem_caches(memcg); - - kmemcg_id = memcg->kmemcg_id; - BUG_ON(kmemcg_id < 0); - - parent = parent_mem_cgroup(memcg); - if (!parent) - parent = root_mem_cgroup; - - /* - * Change kmemcg_id of this cgroup and all its descendants to the - * parent's id, and then move all entries from this cgroup's list_lrus - * to ones of the parent. After we have finished, all list_lrus - * corresponding to this cgroup are guaranteed to remain empty. The - * ordering is imposed by list_lru_node->lock taken by - * memcg_drain_all_list_lrus(). - */ - css_for_each_descendant_pre(css, &memcg->css) { - child = mem_cgroup_from_css(css); - BUG_ON(child->kmemcg_id != kmemcg_id); - child->kmemcg_id = parent->kmemcg_id; - if (!memcg->use_hierarchy) - break; - } - memcg_drain_all_list_lrus(kmemcg_id, parent->kmemcg_id); - - memcg_free_cache_id(kmemcg_id); -} - -static void memcg_destroy_kmem(struct mem_cgroup *memcg) -{ - if (memcg->kmem_acct_activated) { - memcg_destroy_kmem_caches(memcg); - static_branch_dec(&memcg_kmem_enabled_key); - WARN_ON(page_counter_read(&memcg->kmem)); - } - tcp_destroy_cgroup(memcg); -} -#else -static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) -{ - return 0; -} - -static void memcg_deactivate_kmem(struct mem_cgroup *memcg) -{ -} - -static void memcg_destroy_kmem(struct mem_cgroup *memcg) -{ -} -#endif - #ifdef CONFIG_CGROUP_WRITEBACK struct list_head *mem_cgroup_cgwb_list(struct mem_cgroup *memcg) @@ -4051,7 +4040,6 @@ static struct cftype mem_cgroup_legacy_files[] = { .seq_show = memcg_numa_stat_show, }, #endif -#ifdef CONFIG_MEMCG_KMEM { .name = "kmem.limit_in_bytes", .private = MEMFILE_PRIVATE(_KMEM, RES_LIMIT), @@ -4084,7 +4072,29 @@ static struct cftype mem_cgroup_legacy_files[] = { .seq_show = memcg_slab_show, }, #endif -#endif + { + .name = "kmem.tcp.limit_in_bytes", + .private = MEMFILE_PRIVATE(_TCP, RES_LIMIT), + .write = mem_cgroup_write, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.tcp.usage_in_bytes", + .private = MEMFILE_PRIVATE(_TCP, RES_USAGE), + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.tcp.failcnt", + .private = MEMFILE_PRIVATE(_TCP, RES_FAILCNT), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, + { + .name = "kmem.tcp.max_usage_in_bytes", + .private = MEMFILE_PRIVATE(_TCP, RES_MAX_USAGE), + .write = mem_cgroup_reset, + .read_u64 = mem_cgroup_read_u64, + }, { }, /* terminate */ }; @@ -4123,147 +4133,92 @@ static void free_mem_cgroup_per_zone_info(struct mem_cgroup *memcg, int node) kfree(memcg->nodeinfo[node]); } -static struct mem_cgroup *mem_cgroup_alloc(void) -{ - struct mem_cgroup *memcg; - size_t size; - - size = sizeof(struct mem_cgroup); - size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); - - memcg = kzalloc(size, GFP_KERNEL); - if (!memcg) - return NULL; - - memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); - if (!memcg->stat) - goto out_free; - - if (memcg_wb_domain_init(memcg, GFP_KERNEL)) - goto out_free_stat; - - return memcg; - -out_free_stat: - free_percpu(memcg->stat); -out_free: - kfree(memcg); - return NULL; -} - -/* - * At destroying mem_cgroup, references from swap_cgroup can remain. - * (scanning all at force_empty is too costly...) - * - * Instead of clearing all references at force_empty, we remember - * the number of reference from swap_cgroup and free mem_cgroup when - * it goes down to 0. - * - * Removal of cgroup itself succeeds regardless of refs from swap. - */ - -static void __mem_cgroup_free(struct mem_cgroup *memcg) +static void mem_cgroup_free(struct mem_cgroup *memcg) { int node; - cancel_work_sync(&memcg->high_work); - - mem_cgroup_remove_from_trees(memcg); - + memcg_wb_domain_exit(memcg); for_each_node(node) free_mem_cgroup_per_zone_info(memcg, node); - free_percpu(memcg->stat); - memcg_wb_domain_exit(memcg); kfree(memcg); } -static struct cgroup_subsys_state * __ref -mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) +static struct mem_cgroup *mem_cgroup_alloc(void) { struct mem_cgroup *memcg; - long error = -ENOMEM; + size_t size; int node; - memcg = mem_cgroup_alloc(); + size = sizeof(struct mem_cgroup); + size += nr_node_ids * sizeof(struct mem_cgroup_per_node *); + + memcg = kzalloc(size, GFP_KERNEL); if (!memcg) - return ERR_PTR(error); + return NULL; + + memcg->stat = alloc_percpu(struct mem_cgroup_stat_cpu); + if (!memcg->stat) + goto fail; for_each_node(node) if (alloc_mem_cgroup_per_zone_info(memcg, node)) - goto free_out; + goto fail; - /* root ? */ - if (parent_css == NULL) { - root_mem_cgroup = memcg; - page_counter_init(&memcg->memory, NULL); - memcg->high = PAGE_COUNTER_MAX; - memcg->soft_limit = PAGE_COUNTER_MAX; - page_counter_init(&memcg->memsw, NULL); - page_counter_init(&memcg->kmem, NULL); - } + if (memcg_wb_domain_init(memcg, GFP_KERNEL)) + goto fail; INIT_WORK(&memcg->high_work, high_work_func); memcg->last_scanned_node = MAX_NUMNODES; INIT_LIST_HEAD(&memcg->oom_notify); - memcg->move_charge_at_immigrate = 0; mutex_init(&memcg->thresholds_lock); spin_lock_init(&memcg->move_lock); vmpressure_init(&memcg->vmpressure); INIT_LIST_HEAD(&memcg->event_list); spin_lock_init(&memcg->event_list_lock); -#ifdef CONFIG_MEMCG_KMEM + memcg->socket_pressure = jiffies; +#ifndef CONFIG_SLOB memcg->kmemcg_id = -1; #endif #ifdef CONFIG_CGROUP_WRITEBACK INIT_LIST_HEAD(&memcg->cgwb_list); #endif -#ifdef CONFIG_INET - memcg->socket_pressure = jiffies; -#endif - return &memcg->css; - -free_out: - __mem_cgroup_free(memcg); - return ERR_PTR(error); + return memcg; +fail: + mem_cgroup_free(memcg); + return NULL; } -static int -mem_cgroup_css_online(struct cgroup_subsys_state *css) +static struct cgroup_subsys_state * __ref +mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); - struct mem_cgroup *parent = mem_cgroup_from_css(css->parent); - int ret; - - if (css->id > MEM_CGROUP_ID_MAX) - return -ENOSPC; - - if (!parent) - return 0; - - mutex_lock(&memcg_create_mutex); + struct mem_cgroup *parent = mem_cgroup_from_css(parent_css); + struct mem_cgroup *memcg; + long error = -ENOMEM; - memcg->use_hierarchy = parent->use_hierarchy; - memcg->oom_kill_disable = parent->oom_kill_disable; - memcg->swappiness = mem_cgroup_swappiness(parent); + memcg = mem_cgroup_alloc(); + if (!memcg) + return ERR_PTR(error); - if (parent->use_hierarchy) { + memcg->high = PAGE_COUNTER_MAX; + memcg->soft_limit = PAGE_COUNTER_MAX; + if (parent) { + memcg->swappiness = mem_cgroup_swappiness(parent); + memcg->oom_kill_disable = parent->oom_kill_disable; + } + if (parent && parent->use_hierarchy) { + memcg->use_hierarchy = true; page_counter_init(&memcg->memory, &parent->memory); - memcg->high = PAGE_COUNTER_MAX; - memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_init(&memcg->swap, &parent->swap); page_counter_init(&memcg->memsw, &parent->memsw); page_counter_init(&memcg->kmem, &parent->kmem); - - /* - * No need to take a reference to the parent because cgroup - * core guarantees its existence. - */ + page_counter_init(&memcg->tcpmem, &parent->tcpmem); } else { page_counter_init(&memcg->memory, NULL); - memcg->high = PAGE_COUNTER_MAX; - memcg->soft_limit = PAGE_COUNTER_MAX; + page_counter_init(&memcg->swap, NULL); page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); + page_counter_init(&memcg->tcpmem, NULL); /* * Deeper hierachy with use_hierarchy == false doesn't make * much sense so let cgroup subsystem know about this @@ -4272,23 +4227,31 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) if (parent != root_mem_cgroup) memory_cgrp_subsys.broken_hierarchy = true; } - mutex_unlock(&memcg_create_mutex); - ret = memcg_init_kmem(memcg, &memory_cgrp_subsys); - if (ret) - return ret; + /* The following stuff does not apply to the root */ + if (!parent) { + root_mem_cgroup = memcg; + return &memcg->css; + } + + error = memcg_propagate_kmem(parent, memcg); + if (error) + goto fail; -#ifdef CONFIG_INET if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) static_branch_inc(&memcg_sockets_enabled_key); -#endif - /* - * Make sure the memcg is initialized: mem_cgroup_iter() - * orders reading memcg->initialized against its callers - * reading the memcg members. - */ - smp_store_release(&memcg->initialized, 1); + return &memcg->css; +fail: + mem_cgroup_free(memcg); + return NULL; +} + +static int +mem_cgroup_css_online(struct cgroup_subsys_state *css) +{ + if (css->id > MEM_CGROUP_ID_MAX) + return -ENOSPC; return 0; } @@ -4310,10 +4273,7 @@ static void mem_cgroup_css_offline(struct cgroup_subsys_state *css) } spin_unlock(&memcg->event_list_lock); - vmpressure_cleanup(&memcg->vmpressure); - - memcg_deactivate_kmem(memcg); - + memcg_offline_kmem(memcg); wb_memcg_offline(memcg); } @@ -4328,12 +4288,17 @@ static void mem_cgroup_css_free(struct cgroup_subsys_state *css) { struct mem_cgroup *memcg = mem_cgroup_from_css(css); - memcg_destroy_kmem(memcg); -#ifdef CONFIG_INET if (cgroup_subsys_on_dfl(memory_cgrp_subsys) && !cgroup_memory_nosocket) static_branch_dec(&memcg_sockets_enabled_key); -#endif - __mem_cgroup_free(memcg); + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && memcg->tcpmem_active) + static_branch_dec(&memcg_sockets_enabled_key); + + vmpressure_cleanup(&memcg->vmpressure); + cancel_work_sync(&memcg->high_work); + mem_cgroup_remove_from_trees(memcg); + memcg_free_kmem(memcg); + mem_cgroup_free(memcg); } /** @@ -4673,7 +4638,8 @@ static int mem_cgroup_count_precharge_pte_range(pmd_t *pmd, pte_t *pte; spinlock_t *ptl; - if (pmd_trans_huge_lock(pmd, vma, &ptl)) { + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { if (get_mctgt_type_thp(vma, addr, *pmd, NULL) == MC_TARGET_PAGE) mc.precharge += HPAGE_PMD_NR; spin_unlock(ptl); @@ -4861,7 +4827,8 @@ static int mem_cgroup_move_charge_pte_range(pmd_t *pmd, union mc_target target; struct page *page; - if (pmd_trans_huge_lock(pmd, vma, &ptl)) { + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { if (mc.precharge < HPAGE_PMD_NR) { spin_unlock(ptl); return 0; @@ -5143,6 +5110,59 @@ static int memory_events_show(struct seq_file *m, void *v) return 0; } +static int memory_stat_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + int i; + + /* + * Provide statistics on the state of the memory subsystem as + * well as cumulative event counters that show past behavior. + * + * This list is ordered following a combination of these gradients: + * 1) generic big picture -> specifics and details + * 2) reflecting userspace activity -> reflecting kernel heuristics + * + * Current memory state: + */ + + seq_printf(m, "anon %llu\n", + (u64)tree_stat(memcg, MEM_CGROUP_STAT_RSS) * PAGE_SIZE); + seq_printf(m, "file %llu\n", + (u64)tree_stat(memcg, MEM_CGROUP_STAT_CACHE) * PAGE_SIZE); + seq_printf(m, "sock %llu\n", + (u64)tree_stat(memcg, MEMCG_SOCK) * PAGE_SIZE); + + seq_printf(m, "file_mapped %llu\n", + (u64)tree_stat(memcg, MEM_CGROUP_STAT_FILE_MAPPED) * + PAGE_SIZE); + seq_printf(m, "file_dirty %llu\n", + (u64)tree_stat(memcg, MEM_CGROUP_STAT_DIRTY) * + PAGE_SIZE); + seq_printf(m, "file_writeback %llu\n", + (u64)tree_stat(memcg, MEM_CGROUP_STAT_WRITEBACK) * + PAGE_SIZE); + + for (i = 0; i < NR_LRU_LISTS; i++) { + struct mem_cgroup *mi; + unsigned long val = 0; + + for_each_mem_cgroup_tree(mi, memcg) + val += mem_cgroup_nr_lru_pages(mi, BIT(i)); + seq_printf(m, "%s %llu\n", + mem_cgroup_lru_names[i], (u64)val * PAGE_SIZE); + } + + /* Accumulated memory events */ + + seq_printf(m, "pgfault %lu\n", + tree_events(memcg, MEM_CGROUP_EVENTS_PGFAULT)); + seq_printf(m, "pgmajfault %lu\n", + tree_events(memcg, MEM_CGROUP_EVENTS_PGMAJFAULT)); + + return 0; +} + static struct cftype memory_files[] = { { .name = "current", @@ -5173,6 +5193,11 @@ static struct cftype memory_files[] = { .file_offset = offsetof(struct mem_cgroup, events_file), .seq_show = memory_events_show, }, + { + .name = "stat", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = memory_stat_show, + }, { } /* terminate */ }; @@ -5269,7 +5294,7 @@ int mem_cgroup_try_charge(struct page *page, struct mm_struct *mm, if (page->mem_cgroup) goto out; - if (do_memsw_account()) { + if (do_swap_account) { swp_entry_t ent = { .val = page_private(page), }; unsigned short id = lookup_swap_cgroup_id(ent); @@ -5504,7 +5529,8 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) { struct mem_cgroup *memcg; - int isolated; + unsigned int nr_pages; + bool compound; VM_BUG_ON_PAGE(!PageLocked(oldpage), oldpage); VM_BUG_ON_PAGE(!PageLocked(newpage), newpage); @@ -5524,14 +5550,22 @@ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) if (!memcg) return; - lock_page_lru(oldpage, &isolated); - oldpage->mem_cgroup = NULL; - unlock_page_lru(oldpage, isolated); + /* Force-charge the new page. The old one will be freed soon */ + compound = PageTransHuge(newpage); + nr_pages = compound ? hpage_nr_pages(newpage) : 1; + + page_counter_charge(&memcg->memory, nr_pages); + if (do_memsw_account()) + page_counter_charge(&memcg->memsw, nr_pages); + css_get_many(&memcg->css, nr_pages); commit_charge(newpage, memcg, true); -} -#ifdef CONFIG_INET + local_irq_disable(); + mem_cgroup_charge_statistics(memcg, newpage, compound, nr_pages); + memcg_check_events(memcg, newpage); + local_irq_enable(); +} DEFINE_STATIC_KEY_FALSE(memcg_sockets_enabled_key); EXPORT_SYMBOL(memcg_sockets_enabled_key); @@ -5558,10 +5592,8 @@ void sock_update_memcg(struct sock *sk) memcg = mem_cgroup_from_task(current); if (memcg == root_mem_cgroup) goto out; -#ifdef CONFIG_MEMCG_KMEM - if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcp_mem.active) + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) && !memcg->tcpmem_active) goto out; -#endif if (css_tryget_online(&memcg->css)) sk->sk_memcg = memcg; out: @@ -5587,24 +5619,24 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) { gfp_t gfp_mask = GFP_KERNEL; -#ifdef CONFIG_MEMCG_KMEM if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { - struct page_counter *counter; + struct page_counter *fail; - if (page_counter_try_charge(&memcg->tcp_mem.memory_allocated, - nr_pages, &counter)) { - memcg->tcp_mem.memory_pressure = 0; + if (page_counter_try_charge(&memcg->tcpmem, nr_pages, &fail)) { + memcg->tcpmem_pressure = 0; return true; } - page_counter_charge(&memcg->tcp_mem.memory_allocated, nr_pages); - memcg->tcp_mem.memory_pressure = 1; + page_counter_charge(&memcg->tcpmem, nr_pages); + memcg->tcpmem_pressure = 1; return false; } -#endif + /* Don't block in the packet receive path */ if (in_softirq()) gfp_mask = GFP_NOWAIT; + this_cpu_add(memcg->stat->count[MEMCG_SOCK], nr_pages); + if (try_charge(memcg, gfp_mask, nr_pages) == 0) return true; @@ -5619,19 +5651,17 @@ bool mem_cgroup_charge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) */ void mem_cgroup_uncharge_skmem(struct mem_cgroup *memcg, unsigned int nr_pages) { -#ifdef CONFIG_MEMCG_KMEM if (!cgroup_subsys_on_dfl(memory_cgrp_subsys)) { - page_counter_uncharge(&memcg->tcp_mem.memory_allocated, - nr_pages); + page_counter_uncharge(&memcg->tcpmem, nr_pages); return; } -#endif + + this_cpu_sub(memcg->stat->count[MEMCG_SOCK], nr_pages); + page_counter_uncharge(&memcg->memory, nr_pages); css_put_many(&memcg->css, nr_pages); } -#endif /* CONFIG_INET */ - static int __init cgroup_memory(char *s) { char *token; @@ -5641,6 +5671,8 @@ static int __init cgroup_memory(char *s) continue; if (!strcmp(token, "nosocket")) cgroup_memory_nosocket = true; + if (!strcmp(token, "nokmem")) + cgroup_memory_nokmem = true; } return 0; } @@ -5730,32 +5762,107 @@ void mem_cgroup_swapout(struct page *page, swp_entry_t entry) memcg_check_events(memcg, page); } +/* + * mem_cgroup_try_charge_swap - try charging a swap entry + * @page: page being added to swap + * @entry: swap entry to charge + * + * Try to charge @entry to the memcg that @page belongs to. + * + * Returns 0 on success, -ENOMEM on failure. + */ +int mem_cgroup_try_charge_swap(struct page *page, swp_entry_t entry) +{ + struct mem_cgroup *memcg; + struct page_counter *counter; + unsigned short oldid; + + if (!cgroup_subsys_on_dfl(memory_cgrp_subsys) || !do_swap_account) + return 0; + + memcg = page->mem_cgroup; + + /* Readahead page, never charged */ + if (!memcg) + return 0; + + if (!mem_cgroup_is_root(memcg) && + !page_counter_try_charge(&memcg->swap, 1, &counter)) + return -ENOMEM; + + oldid = swap_cgroup_record(entry, mem_cgroup_id(memcg)); + VM_BUG_ON_PAGE(oldid, page); + mem_cgroup_swap_statistics(memcg, true); + + css_get(&memcg->css); + return 0; +} + /** * mem_cgroup_uncharge_swap - uncharge a swap entry * @entry: swap entry to uncharge * - * Drop the memsw charge associated with @entry. + * Drop the swap charge associated with @entry. */ void mem_cgroup_uncharge_swap(swp_entry_t entry) { struct mem_cgroup *memcg; unsigned short id; - if (!do_memsw_account()) + if (!do_swap_account) return; id = swap_cgroup_record(entry, 0); rcu_read_lock(); memcg = mem_cgroup_from_id(id); if (memcg) { - if (!mem_cgroup_is_root(memcg)) - page_counter_uncharge(&memcg->memsw, 1); + if (!mem_cgroup_is_root(memcg)) { + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) + page_counter_uncharge(&memcg->swap, 1); + else + page_counter_uncharge(&memcg->memsw, 1); + } mem_cgroup_swap_statistics(memcg, false); css_put(&memcg->css); } rcu_read_unlock(); } +long mem_cgroup_get_nr_swap_pages(struct mem_cgroup *memcg) +{ + long nr_swap_pages = get_nr_swap_pages(); + + if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return nr_swap_pages; + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) + nr_swap_pages = min_t(long, nr_swap_pages, + READ_ONCE(memcg->swap.limit) - + page_counter_read(&memcg->swap)); + return nr_swap_pages; +} + +bool mem_cgroup_swap_full(struct page *page) +{ + struct mem_cgroup *memcg; + + VM_BUG_ON_PAGE(!PageLocked(page), page); + + if (vm_swap_full()) + return true; + if (!do_swap_account || !cgroup_subsys_on_dfl(memory_cgrp_subsys)) + return false; + + memcg = page->mem_cgroup; + if (!memcg) + return false; + + for (; memcg != root_mem_cgroup; memcg = parent_mem_cgroup(memcg)) + if (page_counter_read(&memcg->swap) * 2 >= memcg->swap.limit) + return true; + + return false; +} + /* for remember boot option*/ #ifdef CONFIG_MEMCG_SWAP_ENABLED static int really_do_swap_account __initdata = 1; @@ -5773,6 +5880,63 @@ static int __init enable_swap_account(char *s) } __setup("swapaccount=", enable_swap_account); +static u64 swap_current_read(struct cgroup_subsys_state *css, + struct cftype *cft) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(css); + + return (u64)page_counter_read(&memcg->swap) * PAGE_SIZE; +} + +static int swap_max_show(struct seq_file *m, void *v) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(seq_css(m)); + unsigned long max = READ_ONCE(memcg->swap.limit); + + if (max == PAGE_COUNTER_MAX) + seq_puts(m, "max\n"); + else + seq_printf(m, "%llu\n", (u64)max * PAGE_SIZE); + + return 0; +} + +static ssize_t swap_max_write(struct kernfs_open_file *of, + char *buf, size_t nbytes, loff_t off) +{ + struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of)); + unsigned long max; + int err; + + buf = strstrip(buf); + err = page_counter_memparse(buf, "max", &max); + if (err) + return err; + + mutex_lock(&memcg_limit_mutex); + err = page_counter_limit(&memcg->swap, max); + mutex_unlock(&memcg_limit_mutex); + if (err) + return err; + + return nbytes; +} + +static struct cftype swap_files[] = { + { + .name = "swap.current", + .flags = CFTYPE_NOT_ON_ROOT, + .read_u64 = swap_current_read, + }, + { + .name = "swap.max", + .flags = CFTYPE_NOT_ON_ROOT, + .seq_show = swap_max_show, + .write = swap_max_write, + }, + { } /* terminate */ +}; + static struct cftype memsw_cgroup_files[] = { { .name = "memsw.usage_in_bytes", @@ -5804,6 +5968,8 @@ static int __init mem_cgroup_swap_init(void) { if (!mem_cgroup_disabled() && really_do_swap_account) { do_swap_account = 1; + WARN_ON(cgroup_add_dfl_cftypes(&memory_cgrp_subsys, + swap_files)); WARN_ON(cgroup_add_legacy_cftypes(&memory_cgrp_subsys, memsw_cgroup_files)); } diff --git a/mm/memory.c b/mm/memory.c index ff17850a52d9..635451abc8f7 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1591,10 +1591,15 @@ int vm_insert_mixed(struct vm_area_struct *vma, unsigned long addr, * than insert_pfn). If a zero_pfn were inserted into a VM_MIXEDMAP * without pte special, it would there be refcounted as a normal page. */ - if (!HAVE_PTE_SPECIAL && pfn_t_valid(pfn)) { + if (!HAVE_PTE_SPECIAL && !pfn_t_devmap(pfn) && pfn_t_valid(pfn)) { struct page *page; - page = pfn_t_to_page(pfn); + /* + * At this point we are committed to insert_page() + * regardless of whether the caller specified flags that + * result in pfn_t_has_page() == false. + */ + page = pfn_to_page(pfn_t_to_pfn(pfn)); return insert_page(vma, addr, page, vma->vm_page_prot); } return insert_pfn(vma, addr, pfn, vma->vm_page_prot); @@ -2232,11 +2237,6 @@ static int wp_page_shared(struct mm_struct *mm, struct vm_area_struct *vma, page_cache_get(old_page); - /* - * Only catch write-faults on shared writable pages, - * read-only shared pages can get COWed by - * get_user_pages(.write=1, .force=1). - */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; @@ -2582,7 +2582,8 @@ static int do_swap_page(struct mm_struct *mm, struct vm_area_struct *vma, } swap_free(entry); - if (vm_swap_full() || (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) + if (mem_cgroup_swap_full(page) || + (vma->vm_flags & VM_LOCKED) || PageMlocked(page)) try_to_free_swap(page); unlock_page(page); if (page != swapcache) { diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 27d135408a22..4c4187c0e1de 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -548,8 +548,7 @@ retry: goto retry; } - if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) - migrate_page_add(page, qp->pagelist, flags); + migrate_page_add(page, qp->pagelist, flags); } pte_unmap_unlock(pte - 1, ptl); cond_resched(); @@ -625,7 +624,7 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, unsigned long endvma = vma->vm_end; unsigned long flags = qp->flags; - if (vma->vm_flags & VM_PFNMAP) + if (!vma_migratable(vma)) return 1; if (endvma > end) @@ -644,16 +643,13 @@ static int queue_pages_test_walk(unsigned long start, unsigned long end, if (flags & MPOL_MF_LAZY) { /* Similar to task_numa_work, skip inaccessible VMAs */ - if (vma_migratable(vma) && - vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)) + if (vma->vm_flags & (VM_READ | VM_EXEC | VM_WRITE)) change_prot_numa(vma, start, endvma); return 1; } - if ((flags & MPOL_MF_STRICT) || - ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) && - vma_migratable(vma))) - /* queue pages from current vma */ + /* queue pages from current vma */ + if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) return 0; return 1; } diff --git a/mm/mincore.c b/mm/mincore.c index 2a565ed8bb49..563f32045490 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -117,7 +117,8 @@ static int mincore_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, unsigned char *vec = walk->private; int nr = (end - addr) >> PAGE_SHIFT; - if (pmd_trans_huge_lock(pmd, vma, &ptl)) { + ptl = pmd_trans_huge_lock(pmd, vma); + if (ptl) { memset(vec, 1, nr); spin_unlock(ptl); goto out; diff --git a/mm/mlock.c b/mm/mlock.c index e1e2b1207bf2..96f001041928 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -175,7 +175,7 @@ static void __munlock_isolation_failed(struct page *page) */ unsigned int munlock_vma_page(struct page *page) { - unsigned int nr_pages; + int nr_pages; struct zone *zone = page_zone(page); /* For try_to_munlock() and to serialize with page migration */ diff --git a/mm/mmap.c b/mm/mmap.c index 84b12624ceb0..76d1ec29149b 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -42,6 +42,7 @@ #include <linux/memory.h> #include <linux/printk.h> #include <linux/userfaultfd_k.h> +#include <linux/moduleparam.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -69,6 +70,8 @@ const int mmap_rnd_compat_bits_max = CONFIG_ARCH_MMAP_RND_COMPAT_BITS_MAX; int mmap_rnd_compat_bits __read_mostly = CONFIG_ARCH_MMAP_RND_COMPAT_BITS; #endif +static bool ignore_rlimit_data = true; +core_param(ignore_rlimit_data, ignore_rlimit_data, bool, 0644); static void unmap_region(struct mm_struct *mm, struct vm_area_struct *vma, struct vm_area_struct *prev, @@ -387,8 +390,9 @@ static long vma_compute_subtree_gap(struct vm_area_struct *vma) } #ifdef CONFIG_DEBUG_VM_RB -static int browse_rb(struct rb_root *root) +static int browse_rb(struct mm_struct *mm) { + struct rb_root *root = &mm->mm_rb; int i = 0, j, bug = 0; struct rb_node *nd, *pn = NULL; unsigned long prev = 0, pend = 0; @@ -411,12 +415,14 @@ static int browse_rb(struct rb_root *root) vma->vm_start, vma->vm_end); bug = 1; } + spin_lock(&mm->page_table_lock); if (vma->rb_subtree_gap != vma_compute_subtree_gap(vma)) { pr_emerg("free gap %lx, correct %lx\n", vma->rb_subtree_gap, vma_compute_subtree_gap(vma)); bug = 1; } + spin_unlock(&mm->page_table_lock); i++; pn = nd; prev = vma->vm_start; @@ -453,12 +459,16 @@ static void validate_mm(struct mm_struct *mm) struct vm_area_struct *vma = mm->mmap; while (vma) { + struct anon_vma *anon_vma = vma->anon_vma; struct anon_vma_chain *avc; - vma_lock_anon_vma(vma); - list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) - anon_vma_interval_tree_verify(avc); - vma_unlock_anon_vma(vma); + if (anon_vma) { + anon_vma_lock_read(anon_vma); + list_for_each_entry(avc, &vma->anon_vma_chain, same_vma) + anon_vma_interval_tree_verify(avc); + anon_vma_unlock_read(anon_vma); + } + highest_address = vma->vm_end; vma = vma->vm_next; i++; @@ -472,7 +482,7 @@ static void validate_mm(struct mm_struct *mm) mm->highest_vm_end, highest_address); bug = 1; } - i = browse_rb(&mm->mm_rb); + i = browse_rb(mm); if (i != mm->map_count) { if (i != -1) pr_emerg("map_count %d rb %d\n", mm->map_count, i); @@ -2139,32 +2149,27 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns int expand_upwards(struct vm_area_struct *vma, unsigned long address) { struct mm_struct *mm = vma->vm_mm; - int error; + int error = 0; if (!(vma->vm_flags & VM_GROWSUP)) return -EFAULT; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ + /* Guard against wrapping around to address 0. */ + if (address < PAGE_ALIGN(address+4)) + address = PAGE_ALIGN(address+4); + else + return -ENOMEM; + + /* We must make sure the anon_vma is allocated. */ if (unlikely(anon_vma_prepare(vma))) return -ENOMEM; - vma_lock_anon_vma(vma); /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. - * Also guard against wrapping around to address 0. */ - if (address < PAGE_ALIGN(address+4)) - address = PAGE_ALIGN(address+4); - else { - vma_unlock_anon_vma(vma); - return -ENOMEM; - } - error = 0; + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address > vma->vm_end) { @@ -2182,7 +2187,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2205,7 +2210,7 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2221,25 +2226,21 @@ int expand_downwards(struct vm_area_struct *vma, struct mm_struct *mm = vma->vm_mm; int error; - /* - * We must make sure the anon_vma is allocated - * so that the anon_vma locking is not a noop. - */ - if (unlikely(anon_vma_prepare(vma))) - return -ENOMEM; - address &= PAGE_MASK; error = security_mmap_addr(address); if (error) return error; - vma_lock_anon_vma(vma); + /* We must make sure the anon_vma is allocated. */ + if (unlikely(anon_vma_prepare(vma))) + return -ENOMEM; /* * vma->vm_start/vm_end cannot change under us because the caller * is required to hold the mmap_sem in read mode. We need the * anon_vma lock to serialize against concurrent expand_stacks. */ + anon_vma_lock_write(vma->anon_vma); /* Somebody else might have raced and expanded it already */ if (address < vma->vm_start) { @@ -2257,7 +2258,7 @@ int expand_downwards(struct vm_area_struct *vma, * updates, but we only hold a shared mmap_sem * lock here, so we need to protect against * concurrent vma expansions. - * vma_lock_anon_vma() doesn't help here, as + * anon_vma_lock_write() doesn't help here, as * we don't guarantee that all growable vmas * in a mm share the same root anon vma. * So, we reuse mm->page_table_lock to guard @@ -2278,7 +2279,7 @@ int expand_downwards(struct vm_area_struct *vma, } } } - vma_unlock_anon_vma(vma); + anon_vma_unlock_write(vma->anon_vma); khugepaged_enter_vma_merge(vma, vma->vm_flags); validate_mm(mm); return error; @@ -2663,12 +2664,29 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, if (!vma || !(vma->vm_flags & VM_SHARED)) goto out; - if (start < vma->vm_start || start + size > vma->vm_end) + if (start < vma->vm_start) goto out; - if (pgoff == linear_page_index(vma, start)) { - ret = 0; - goto out; + if (start + size > vma->vm_end) { + struct vm_area_struct *next; + + for (next = vma->vm_next; next; next = next->vm_next) { + /* hole between vmas ? */ + if (next->vm_start != next->vm_prev->vm_end) + goto out; + + if (next->vm_file != vma->vm_file) + goto out; + + if (next->vm_flags != vma->vm_flags) + goto out; + + if (start + size <= next->vm_end) + break; + } + + if (!next) + goto out; } prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; @@ -2678,9 +2696,16 @@ SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, flags &= MAP_NONBLOCK; flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; if (vma->vm_flags & VM_LOCKED) { + struct vm_area_struct *tmp; flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ - munlock_vma_pages_range(vma, start, start + size); + for (tmp = vma; tmp->vm_start >= start + size; + tmp = tmp->vm_next) { + munlock_vma_pages_range(tmp, + max(tmp->vm_start, start), + min(tmp->vm_end, start + size)); + } } file = get_file(vma->vm_file); @@ -2982,9 +3007,17 @@ bool may_expand_vm(struct mm_struct *mm, vm_flags_t flags, unsigned long npages) if (mm->total_vm + npages > rlimit(RLIMIT_AS) >> PAGE_SHIFT) return false; - if ((flags & (VM_WRITE | VM_SHARED | (VM_STACK_FLAGS & - (VM_GROWSUP | VM_GROWSDOWN)))) == VM_WRITE) - return mm->data_vm + npages <= rlimit(RLIMIT_DATA); + if (is_data_mapping(flags) && + mm->data_vm + npages > rlimit(RLIMIT_DATA) >> PAGE_SHIFT) { + if (ignore_rlimit_data) + pr_warn_once("%s (%d): VmData %lu exceed data ulimit " + "%lu. Will be forbidden soon.\n", + current->comm, current->pid, + (mm->data_vm + npages) << PAGE_SHIFT, + rlimit(RLIMIT_DATA)); + else + return false; + } return true; } @@ -2993,11 +3026,11 @@ void vm_stat_account(struct mm_struct *mm, vm_flags_t flags, long npages) { mm->total_vm += npages; - if ((flags & (VM_EXEC | VM_WRITE)) == VM_EXEC) + if (is_exec_mapping(flags)) mm->exec_vm += npages; - else if (flags & (VM_STACK_FLAGS & (VM_GROWSUP | VM_GROWSDOWN))) + else if (is_stack_mapping(flags)) mm->stack_vm += npages; - else if ((flags & (VM_WRITE | VM_SHARED)) == VM_WRITE) + else if (is_data_mapping(flags)) mm->data_vm += npages; } diff --git a/mm/mprotect.c b/mm/mprotect.c index 8eb7bb40dc40..f7cb3d4d9c2e 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -160,9 +160,11 @@ static inline unsigned long change_pmd_range(struct vm_area_struct *vma, } if (pmd_trans_huge(*pmd) || pmd_devmap(*pmd)) { - if (next - addr != HPAGE_PMD_SIZE) + if (next - addr != HPAGE_PMD_SIZE) { split_huge_pmd(vma, pmd, addr); - else { + if (pmd_none(*pmd)) + continue; + } else { int nr_ptes = change_huge_pmd(vma, pmd, addr, newprot, prot_numa); diff --git a/mm/mremap.c b/mm/mremap.c index d77946a997f7..8eeba02fc991 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -210,6 +210,8 @@ unsigned long move_page_tables(struct vm_area_struct *vma, } } split_huge_pmd(vma, old_pmd, old_addr); + if (pmd_none(*old_pmd)) + continue; VM_BUG_ON(pmd_trans_huge(*old_pmd)); } if (pmd_none(*new_pmd) && __pte_alloc(new_vma->vm_mm, new_vma, diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 63358d9f9aa9..838ca8bb64f7 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -5210,6 +5210,11 @@ static void __paginginit free_area_init_core(struct pglist_data *pgdat) pgdat->numabalancing_migrate_nr_pages = 0; pgdat->numabalancing_migrate_next_window = jiffies; #endif +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + spin_lock_init(&pgdat->split_queue_lock); + INIT_LIST_HEAD(&pgdat->split_queue); + pgdat->split_queue_len = 0; +#endif init_waitqueue_head(&pgdat->kswapd_wait); init_waitqueue_head(&pgdat->pfmemalloc_wait); pgdat_page_ext_init(pgdat); @@ -6615,7 +6620,7 @@ bool is_pageblock_removable_nolock(struct page *page) return !has_unmovable_pages(zone, page, 0, true); } -#ifdef CONFIG_CMA +#if (defined(CONFIG_MEMORY_ISOLATION) && defined(CONFIG_COMPACTION)) || defined(CONFIG_CMA) static unsigned long pfn_max_align_down(unsigned long pfn) { diff --git a/mm/percpu.c b/mm/percpu.c index 8a943b97a053..998607adf6eb 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -305,16 +305,12 @@ static void *pcpu_mem_zalloc(size_t size) /** * pcpu_mem_free - free memory * @ptr: memory to free - * @size: size of the area * * Free @ptr. @ptr should have been allocated using pcpu_mem_zalloc(). */ -static void pcpu_mem_free(void *ptr, size_t size) +static void pcpu_mem_free(void *ptr) { - if (size <= PAGE_SIZE) - kfree(ptr); - else - vfree(ptr); + kvfree(ptr); } /** @@ -463,8 +459,8 @@ out_unlock: * pcpu_mem_free() might end up calling vfree() which uses * IRQ-unsafe lock and thus can't be called under pcpu_lock. */ - pcpu_mem_free(old, old_size); - pcpu_mem_free(new, new_size); + pcpu_mem_free(old); + pcpu_mem_free(new); return 0; } @@ -732,7 +728,7 @@ static struct pcpu_chunk *pcpu_alloc_chunk(void) chunk->map = pcpu_mem_zalloc(PCPU_DFL_MAP_ALLOC * sizeof(chunk->map[0])); if (!chunk->map) { - pcpu_mem_free(chunk, pcpu_chunk_struct_size); + pcpu_mem_free(chunk); return NULL; } @@ -753,8 +749,8 @@ static void pcpu_free_chunk(struct pcpu_chunk *chunk) { if (!chunk) return; - pcpu_mem_free(chunk->map, chunk->map_alloc * sizeof(chunk->map[0])); - pcpu_mem_free(chunk, pcpu_chunk_struct_size); + pcpu_mem_free(chunk->map); + pcpu_mem_free(chunk); } /** diff --git a/mm/pgtable-generic.c b/mm/pgtable-generic.c index 9d4767698a1c..06a005b979a7 100644 --- a/mm/pgtable-generic.c +++ b/mm/pgtable-generic.c @@ -90,9 +90,9 @@ pte_t ptep_clear_flush(struct vm_area_struct *vma, unsigned long address, * ARCHes with special requirements for evicting THP backing TLB entries can * implement this. Otherwise also, it can help optimize normal TLB flush in * THP regime. stock flush_tlb_range() typically has optimization to nuke the - * entire TLB TLB if flush span is greater than a threshhold, which will + * entire TLB if flush span is greater than a threshold, which will * likely be true for a single huge page. Thus a single thp flush will - * invalidate the entire TLB which is not desitable. + * invalidate the entire TLB which is not desirable. * e.g. see arch/arc: flush_pmd_tlb_range */ #define flush_pmd_tlb_range(vma, addr, end) flush_tlb_range(vma, addr, end) @@ -195,7 +195,9 @@ pmd_t pmdp_collapse_flush(struct vm_area_struct *vma, unsigned long address, VM_BUG_ON(address & ~HPAGE_PMD_MASK); VM_BUG_ON(pmd_trans_huge(*pmdp)); pmd = pmdp_huge_get_and_clear(vma->vm_mm, address, pmdp); - flush_pmd_tlb_range(vma, address, address + HPAGE_PMD_SIZE); + + /* collapse entails shooting down ptes not pmd */ + flush_tlb_range(vma, address, address + HPAGE_PMD_SIZE); return pmd; } #endif diff --git a/mm/process_vm_access.c b/mm/process_vm_access.c index e88d071648c2..5d453e58ddbf 100644 --- a/mm/process_vm_access.c +++ b/mm/process_vm_access.c @@ -194,7 +194,7 @@ static ssize_t process_vm_rw_core(pid_t pid, struct iov_iter *iter, goto free_proc_pages; } - mm = mm_access(task, PTRACE_MODE_ATTACH); + mm = mm_access(task, PTRACE_MODE_ATTACH_REALCREDS); if (!mm || IS_ERR(mm)) { rc = IS_ERR(mm) ? PTR_ERR(mm) : -ESRCH; /* diff --git a/mm/shmem.c b/mm/shmem.c index b98e1011858c..440e2a7e6c1c 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -701,8 +701,7 @@ static void shmem_evict_inode(struct inode *inode) list_del_init(&info->swaplist); mutex_unlock(&shmem_swaplist_mutex); } - } else - kfree(info->symlink); + } simple_xattrs_free(&info->xattrs); WARN_ON(inode->i_blocks); @@ -912,6 +911,9 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) if (!swap.val) goto redirty; + if (mem_cgroup_try_charge_swap(page, swap)) + goto free_swap; + /* * Add inode to shmem_unuse()'s list of swapped-out inodes, * if it's not already there. Do it now before the page is @@ -940,6 +942,7 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) } mutex_unlock(&shmem_swaplist_mutex); +free_swap: swapcache_free(swap); redirty: set_page_dirty(page); @@ -1898,7 +1901,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) if (whence != SEEK_DATA && whence != SEEK_HOLE) return generic_file_llseek_size(file, offset, whence, MAX_LFS_FILESIZE, i_size_read(inode)); - mutex_lock(&inode->i_mutex); + inode_lock(inode); /* We're holding i_mutex so we can access i_size directly */ if (offset < 0) @@ -1922,7 +1925,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) if (offset >= 0) offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return offset; } @@ -2087,7 +2090,7 @@ int shmem_add_seals(struct file *file, unsigned int seals) if (seals & ~(unsigned int)F_ALL_SEALS) return -EINVAL; - mutex_lock(&inode->i_mutex); + inode_lock(inode); if (info->seals & F_SEAL_SEAL) { error = -EPERM; @@ -2110,7 +2113,7 @@ int shmem_add_seals(struct file *file, unsigned int seals) error = 0; unlock: - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return error; } EXPORT_SYMBOL_GPL(shmem_add_seals); @@ -2160,7 +2163,7 @@ static long shmem_fallocate(struct file *file, int mode, loff_t offset, if (mode & ~(FALLOC_FL_KEEP_SIZE | FALLOC_FL_PUNCH_HOLE)) return -EOPNOTSUPP; - mutex_lock(&inode->i_mutex); + inode_lock(inode); if (mode & FALLOC_FL_PUNCH_HOLE) { struct address_space *mapping = file->f_mapping; @@ -2273,7 +2276,7 @@ undone: inode->i_private = NULL; spin_unlock(&inode->i_lock); out: - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return error; } @@ -2545,13 +2548,12 @@ static int shmem_symlink(struct inode *dir, struct dentry *dentry, const char *s info = SHMEM_I(inode); inode->i_size = len-1; if (len <= SHORT_SYMLINK_LEN) { - info->symlink = kmemdup(symname, len, GFP_KERNEL); - if (!info->symlink) { + inode->i_link = kmemdup(symname, len, GFP_KERNEL); + if (!inode->i_link) { iput(inode); return -ENOMEM; } inode->i_op = &shmem_short_symlink_operations; - inode->i_link = info->symlink; } else { inode_nohighmem(inode); error = shmem_getpage(inode, 0, &page, SGP_WRITE, NULL); @@ -3128,6 +3130,7 @@ static struct inode *shmem_alloc_inode(struct super_block *sb) static void shmem_destroy_callback(struct rcu_head *head) { struct inode *inode = container_of(head, struct inode, i_rcu); + kfree(inode->i_link); kmem_cache_free(shmem_inode_cachep, SHMEM_I(inode)); } diff --git a/mm/slab.c b/mm/slab.c index 6ecc697a8bc4..621fbcb35a36 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -2275,7 +2275,7 @@ __kmem_cache_create (struct kmem_cache *cachep, unsigned long flags) err = setup_cpu_cache(cachep, gfp); if (err) { - __kmem_cache_shutdown(cachep); + __kmem_cache_release(cachep); return err; } @@ -2414,12 +2414,13 @@ int __kmem_cache_shrink(struct kmem_cache *cachep, bool deactivate) int __kmem_cache_shutdown(struct kmem_cache *cachep) { + return __kmem_cache_shrink(cachep, false); +} + +void __kmem_cache_release(struct kmem_cache *cachep) +{ int i; struct kmem_cache_node *n; - int rc = __kmem_cache_shrink(cachep, false); - - if (rc) - return rc; free_percpu(cachep->cpu_cache); @@ -2430,7 +2431,6 @@ int __kmem_cache_shutdown(struct kmem_cache *cachep) kfree(n); cachep->node[i] = NULL; } - return 0; } /* diff --git a/mm/slab.h b/mm/slab.h index c63b8699cfa3..2eedacea439d 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -140,6 +140,7 @@ static inline unsigned long kmem_cache_flags(unsigned long object_size, #define CACHE_CREATE_MASK (SLAB_CORE_FLAGS | SLAB_DEBUG_FLAGS | SLAB_CACHE_FLAGS) int __kmem_cache_shutdown(struct kmem_cache *); +void __kmem_cache_release(struct kmem_cache *); int __kmem_cache_shrink(struct kmem_cache *, bool); void slab_kmem_cache_release(struct kmem_cache *); @@ -173,7 +174,7 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer, void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); -#ifdef CONFIG_MEMCG_KMEM +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) /* * Iterate over all memcg caches of the given root cache. The caller must hold * slab_mutex. @@ -251,7 +252,7 @@ static __always_inline int memcg_charge_slab(struct page *page, extern void slab_init_memcg_params(struct kmem_cache *); -#else /* !CONFIG_MEMCG_KMEM */ +#else /* CONFIG_MEMCG && !CONFIG_SLOB */ #define for_each_memcg_cache(iter, root) \ for ((void)(iter), (void)(root); 0; ) @@ -292,7 +293,7 @@ static inline int memcg_charge_slab(struct page *page, gfp_t gfp, int order, static inline void slab_init_memcg_params(struct kmem_cache *s) { } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ static inline struct kmem_cache *cache_from_obj(struct kmem_cache *s, void *x) { diff --git a/mm/slab_common.c b/mm/slab_common.c index e016178063e1..065b7bdabdc3 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -128,7 +128,7 @@ int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, return i; } -#ifdef CONFIG_MEMCG_KMEM +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) void slab_init_memcg_params(struct kmem_cache *s) { s->memcg_params.is_root_cache = true; @@ -221,7 +221,7 @@ static inline int init_memcg_params(struct kmem_cache *s, static inline void destroy_memcg_params(struct kmem_cache *s) { } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ /* * Find a mergeable slab cache @@ -477,7 +477,7 @@ static void release_caches(struct list_head *release, bool need_rcu_barrier) } } -#ifdef CONFIG_MEMCG_KMEM +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) /* * memcg_create_kmem_cache - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. @@ -503,10 +503,10 @@ void memcg_create_kmem_cache(struct mem_cgroup *memcg, mutex_lock(&slab_mutex); /* - * The memory cgroup could have been deactivated while the cache + * The memory cgroup could have been offlined while the cache * creation work was pending. */ - if (!memcg_kmem_is_active(memcg)) + if (!memcg_kmem_online(memcg)) goto out_unlock; idx = memcg_cache_id(memcg); @@ -689,10 +689,11 @@ static inline int shutdown_memcg_caches(struct kmem_cache *s, { return 0; } -#endif /* CONFIG_MEMCG_KMEM */ +#endif /* CONFIG_MEMCG && !CONFIG_SLOB */ void slab_kmem_cache_release(struct kmem_cache *s) { + __kmem_cache_release(s); destroy_memcg_params(s); kfree_const(s->name); kmem_cache_free(kmem_cache, s); @@ -1123,7 +1124,7 @@ static int slab_show(struct seq_file *m, void *p) return 0; } -#ifdef CONFIG_MEMCG_KMEM +#if defined(CONFIG_MEMCG) && !defined(CONFIG_SLOB) int memcg_slab_show(struct seq_file *m, void *p) { struct kmem_cache *s = list_entry(p, struct kmem_cache, list); diff --git a/mm/slob.c b/mm/slob.c index 17e8f8cc7c53..5ec158054ffe 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -630,6 +630,10 @@ int __kmem_cache_shutdown(struct kmem_cache *c) return 0; } +void __kmem_cache_release(struct kmem_cache *c) +{ +} + int __kmem_cache_shrink(struct kmem_cache *d, bool deactivate) { return 0; diff --git a/mm/slub.c b/mm/slub.c index b21fd24b08b1..d8fbd4a6ed59 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1592,18 +1592,12 @@ static inline void add_partial(struct kmem_cache_node *n, __add_partial(n, page, tail); } -static inline void -__remove_partial(struct kmem_cache_node *n, struct page *page) -{ - list_del(&page->lru); - n->nr_partial--; -} - static inline void remove_partial(struct kmem_cache_node *n, struct page *page) { lockdep_assert_held(&n->list_lock); - __remove_partial(n, page); + list_del(&page->lru); + n->nr_partial--; } /* @@ -3184,6 +3178,12 @@ static void free_kmem_cache_nodes(struct kmem_cache *s) } } +void __kmem_cache_release(struct kmem_cache *s) +{ + free_percpu(s->cpu_slab); + free_kmem_cache_nodes(s); +} + static int init_kmem_cache_nodes(struct kmem_cache *s) { int node; @@ -3443,28 +3443,31 @@ static void list_slab_objects(struct kmem_cache *s, struct page *page, /* * Attempt to free all partial slabs on a node. - * This is called from kmem_cache_close(). We must be the last thread - * using the cache and therefore we do not need to lock anymore. + * This is called from __kmem_cache_shutdown(). We must take list_lock + * because sysfs file might still access partial list after the shutdowning. */ static void free_partial(struct kmem_cache *s, struct kmem_cache_node *n) { struct page *page, *h; + BUG_ON(irqs_disabled()); + spin_lock_irq(&n->list_lock); list_for_each_entry_safe(page, h, &n->partial, lru) { if (!page->inuse) { - __remove_partial(n, page); + remove_partial(n, page); discard_slab(s, page); } else { list_slab_objects(s, page, - "Objects remaining in %s on kmem_cache_close()"); + "Objects remaining in %s on __kmem_cache_shutdown()"); } } + spin_unlock_irq(&n->list_lock); } /* * Release all resources used by a slab cache. */ -static inline int kmem_cache_close(struct kmem_cache *s) +int __kmem_cache_shutdown(struct kmem_cache *s) { int node; struct kmem_cache_node *n; @@ -3476,16 +3479,9 @@ static inline int kmem_cache_close(struct kmem_cache *s) if (n->nr_partial || slabs_node(s, node)) return 1; } - free_percpu(s->cpu_slab); - free_kmem_cache_nodes(s); return 0; } -int __kmem_cache_shutdown(struct kmem_cache *s) -{ - return kmem_cache_close(s); -} - /******************************************************************** * Kmalloc subsystem *******************************************************************/ @@ -3980,7 +3976,7 @@ int __kmem_cache_create(struct kmem_cache *s, unsigned long flags) memcg_propagate_slab_attrs(s); err = sysfs_slab_add(s); if (err) - kmem_cache_close(s); + __kmem_cache_release(s); return err; } @@ -5207,7 +5203,7 @@ static ssize_t slab_attr_store(struct kobject *kobj, return -EIO; err = attribute->store(s, buf, len); -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (slab_state >= FULL && err >= 0 && is_root_cache(s)) { struct kmem_cache *c; @@ -5242,7 +5238,7 @@ static ssize_t slab_attr_store(struct kobject *kobj, static void memcg_propagate_slab_attrs(struct kmem_cache *s) { -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG int i; char *buffer = NULL; struct kmem_cache *root_cache; @@ -5328,7 +5324,7 @@ static struct kset *slab_kset; static inline struct kset *cache_kset(struct kmem_cache *s) { -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (!is_root_cache(s)) return s->memcg_params.root_cache->memcg_kset; #endif @@ -5405,7 +5401,7 @@ static int sysfs_slab_add(struct kmem_cache *s) if (err) goto out_del_kobj; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG if (is_root_cache(s)) { s->memcg_kset = kset_create_and_add("cgroup", NULL, &s->kobj); if (!s->memcg_kset) { @@ -5438,7 +5434,7 @@ void sysfs_slab_remove(struct kmem_cache *s) */ return; -#ifdef CONFIG_MEMCG_KMEM +#ifdef CONFIG_MEMCG kset_unregister(s->memcg_kset); #endif kobject_uevent(&s->kobj, KOBJ_REMOVE); diff --git a/mm/swap_state.c b/mm/swap_state.c index 676ff2991380..69cb2464e7dc 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -170,6 +170,11 @@ int add_to_swap(struct page *page, struct list_head *list) if (!entry.val) return 0; + if (mem_cgroup_try_charge_swap(page, entry)) { + swapcache_free(entry); + return 0; + } + if (unlikely(PageTransHuge(page))) if (unlikely(split_huge_page_to_list(page, list))) { swapcache_free(entry); diff --git a/mm/swapfile.c b/mm/swapfile.c index 2bb30aa3a412..d2c37365e2d6 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -785,14 +785,12 @@ static unsigned char swap_entry_free(struct swap_info_struct *p, count--; } - if (!count) - mem_cgroup_uncharge_swap(entry); - usage = count | has_cache; p->swap_map[offset] = usage; /* free if no reference */ if (!usage) { + mem_cgroup_uncharge_swap(entry); dec_cluster_info_page(p, p->cluster_info, offset); if (offset < p->lowest_bit) p->lowest_bit = offset; @@ -1008,7 +1006,7 @@ int free_swap_and_cache(swp_entry_t entry) * Also recheck PageSwapCache now page is locked (above). */ if (PageSwapCache(page) && !PageWriteback(page) && - (!page_mapped(page) || vm_swap_full())) { + (!page_mapped(page) || mem_cgroup_swap_full(page))) { delete_from_swap_cache(page); SetPageDirty(page); } @@ -1958,9 +1956,9 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) set_blocksize(bdev, old_block_size); blkdev_put(bdev, FMODE_READ | FMODE_WRITE | FMODE_EXCL); } else { - mutex_lock(&inode->i_mutex); + inode_lock(inode); inode->i_flags &= ~S_SWAPFILE; - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); } filp_close(swap_file, NULL); @@ -2185,7 +2183,7 @@ static int claim_swapfile(struct swap_info_struct *p, struct inode *inode) p->flags |= SWP_BLKDEV; } else if (S_ISREG(inode->i_mode)) { p->bdev = inode->i_sb->s_bdev; - mutex_lock(&inode->i_mutex); + inode_lock(inode); if (IS_SWAPFILE(inode)) return -EBUSY; } else @@ -2418,7 +2416,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) mapping = swap_file->f_mapping; inode = mapping->host; - /* If S_ISREG(inode->i_mode) will do mutex_lock(&inode->i_mutex); */ + /* If S_ISREG(inode->i_mode) will do inode_lock(inode); */ error = claim_swapfile(p, inode); if (unlikely(error)) goto bad_swap; @@ -2563,7 +2561,7 @@ bad_swap: vfree(cluster_info); if (swap_file) { if (inode && S_ISREG(inode->i_mode)) { - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); inode = NULL; } filp_close(swap_file, NULL); @@ -2576,7 +2574,7 @@ out: if (name) putname(name); if (inode && S_ISREG(inode->i_mode)) - mutex_unlock(&inode->i_mutex); + inode_unlock(inode); return error; } diff --git a/mm/truncate.c b/mm/truncate.c index 76e35ad97102..e3ee0e27cd17 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -9,6 +9,7 @@ #include <linux/kernel.h> #include <linux/backing-dev.h> +#include <linux/dax.h> #include <linux/gfp.h> #include <linux/mm.h> #include <linux/swap.h> @@ -34,31 +35,39 @@ static void clear_exceptional_entry(struct address_space *mapping, return; spin_lock_irq(&mapping->tree_lock); - /* - * Regular page slots are stabilized by the page lock even - * without the tree itself locked. These unlocked entries - * need verification under the tree lock. - */ - if (!__radix_tree_lookup(&mapping->page_tree, index, &node, &slot)) - goto unlock; - if (*slot != entry) - goto unlock; - radix_tree_replace_slot(slot, NULL); - mapping->nrshadows--; - if (!node) - goto unlock; - workingset_node_shadows_dec(node); - /* - * Don't track node without shadow entries. - * - * Avoid acquiring the list_lru lock if already untracked. - * The list_empty() test is safe as node->private_list is - * protected by mapping->tree_lock. - */ - if (!workingset_node_shadows(node) && - !list_empty(&node->private_list)) - list_lru_del(&workingset_shadow_nodes, &node->private_list); - __radix_tree_delete_node(&mapping->page_tree, node); + + if (dax_mapping(mapping)) { + if (radix_tree_delete_item(&mapping->page_tree, index, entry)) + mapping->nrexceptional--; + } else { + /* + * Regular page slots are stabilized by the page lock even + * without the tree itself locked. These unlocked entries + * need verification under the tree lock. + */ + if (!__radix_tree_lookup(&mapping->page_tree, index, &node, + &slot)) + goto unlock; + if (*slot != entry) + goto unlock; + radix_tree_replace_slot(slot, NULL); + mapping->nrexceptional--; + if (!node) + goto unlock; + workingset_node_shadows_dec(node); + /* + * Don't track node without shadow entries. + * + * Avoid acquiring the list_lru lock if already untracked. + * The list_empty() test is safe as node->private_list is + * protected by mapping->tree_lock. + */ + if (!workingset_node_shadows(node) && + !list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + __radix_tree_delete_node(&mapping->page_tree, node); + } unlock: spin_unlock_irq(&mapping->tree_lock); } @@ -228,7 +237,7 @@ void truncate_inode_pages_range(struct address_space *mapping, int i; cleancache_invalidate_inode(mapping); - if (mapping->nrpages == 0 && mapping->nrshadows == 0) + if (mapping->nrpages == 0 && mapping->nrexceptional == 0) return; /* Offsets within partial pages */ @@ -402,7 +411,7 @@ EXPORT_SYMBOL(truncate_inode_pages); */ void truncate_inode_pages_final(struct address_space *mapping) { - unsigned long nrshadows; + unsigned long nrexceptional; unsigned long nrpages; /* @@ -416,14 +425,14 @@ void truncate_inode_pages_final(struct address_space *mapping) /* * When reclaim installs eviction entries, it increases - * nrshadows first, then decreases nrpages. Make sure we see + * nrexceptional first, then decreases nrpages. Make sure we see * this in the right order or we might miss an entry. */ nrpages = mapping->nrpages; smp_rmb(); - nrshadows = mapping->nrshadows; + nrexceptional = mapping->nrexceptional; - if (nrpages || nrshadows) { + if (nrpages || nrexceptional) { /* * As truncation uses a lockless tree lookup, cycle * the tree lock to make sure any ongoing tree diff --git a/mm/util.c b/mm/util.c index 6d1f9200f74e..4fb14ca5a419 100644 --- a/mm/util.c +++ b/mm/util.c @@ -230,36 +230,11 @@ void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *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) +int vma_is_stack_for_task(struct vm_area_struct *vma, struct task_struct *t) { 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 task_struct of the task - * that the vma is stack for. Must be called under rcu_read_lock(). - */ -struct task_struct *task_of_stack(struct task_struct *task, - struct vm_area_struct *vma, bool in_group) -{ - if (vm_is_stack_for_task(task, vma)) - return task; - - if (in_group) { - struct task_struct *t; - - for_each_thread(task, t) { - if (vm_is_stack_for_task(t, vma)) - return t; - } - } - - return NULL; -} - #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm) { @@ -476,17 +451,25 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen) int res = 0; unsigned int len; struct mm_struct *mm = get_task_mm(task); + unsigned long arg_start, arg_end, env_start, env_end; if (!mm) goto out; if (!mm->arg_end) goto out_mm; /* Shh! No looking before we're done */ - len = mm->arg_end - mm->arg_start; + down_read(&mm->mmap_sem); + arg_start = mm->arg_start; + arg_end = mm->arg_end; + env_start = mm->env_start; + env_end = mm->env_end; + up_read(&mm->mmap_sem); + + len = arg_end - arg_start; if (len > buflen) len = buflen; - res = access_process_vm(task, mm->arg_start, buffer, len, 0); + res = access_process_vm(task, arg_start, buffer, len, 0); /* * If the nul at the end of args has been overwritten, then @@ -497,10 +480,10 @@ int get_cmdline(struct task_struct *task, char *buffer, int buflen) if (len < res) { res = len; } else { - len = mm->env_end - mm->env_start; + len = env_end - env_start; if (len > buflen - res) len = buflen - res; - res += access_process_vm(task, mm->env_start, + res += access_process_vm(task, env_start, buffer+res, len, 0); res = strnlen(buffer, res); } diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 9a6c0704211c..149fdf6c5c56 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -248,9 +248,8 @@ void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, bool tree, if (tree) { spin_lock(&vmpr->sr_lock); - vmpr->tree_scanned += scanned; + scanned = vmpr->tree_scanned += scanned; vmpr->tree_reclaimed += reclaimed; - scanned = vmpr->scanned; spin_unlock(&vmpr->sr_lock); if (scanned < vmpressure_win) diff --git a/mm/vmscan.c b/mm/vmscan.c index 5ac86956ff9d..71b1c29948db 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -46,6 +46,7 @@ #include <linux/oom.h> #include <linux/prefetch.h> #include <linux/printk.h> +#include <linux/dax.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -411,7 +412,7 @@ static unsigned long shrink_slab(gfp_t gfp_mask, int nid, struct shrinker *shrinker; unsigned long freed = 0; - if (memcg && !memcg_kmem_is_active(memcg)) + if (memcg && !memcg_kmem_online(memcg)) return 0; if (nr_scanned == 0) @@ -671,9 +672,15 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * inode reclaim needs to empty out the radix tree or * the nodes are lost. Don't plant shadows behind its * back. + * + * We also don't store shadows for DAX mappings because the + * only page cache pages found in these are zero pages + * covering holes, and because we don't want to mix DAX + * exceptional entries and shadow exceptional entries in the + * same page_tree. */ if (reclaimed && page_is_file_cache(page) && - !mapping_exiting(mapping)) + !mapping_exiting(mapping) && !dax_mapping(mapping)) shadow = workingset_eviction(mapping, page); __delete_from_page_cache(page, shadow, memcg); spin_unlock_irqrestore(&mapping->tree_lock, flags); @@ -1214,7 +1221,7 @@ cull_mlocked: activate_locked: /* Not a candidate for swapping, so reclaim swap space. */ - if (PageSwapCache(page) && vm_swap_full()) + if (PageSwapCache(page) && mem_cgroup_swap_full(page)) try_to_free_swap(page); VM_BUG_ON_PAGE(PageActive(page), page); SetPageActive(page); @@ -1436,7 +1443,7 @@ int isolate_lru_page(struct page *page) int ret = -EBUSY; VM_BUG_ON_PAGE(!page_count(page), page); - VM_BUG_ON_PAGE(PageTail(page), page); + WARN_RATELIMIT(PageTail(page), "trying to isolate tail page"); if (PageLRU(page)) { struct zone *zone = page_zone(page); @@ -1966,10 +1973,11 @@ enum scan_balance { * nr[0] = anon inactive pages to scan; nr[1] = anon active pages to scan * nr[2] = file inactive pages to scan; nr[3] = file active pages to scan */ -static void get_scan_count(struct lruvec *lruvec, int swappiness, +static void get_scan_count(struct lruvec *lruvec, struct mem_cgroup *memcg, struct scan_control *sc, unsigned long *nr, unsigned long *lru_pages) { + int swappiness = mem_cgroup_swappiness(memcg); struct zone_reclaim_stat *reclaim_stat = &lruvec->reclaim_stat; u64 fraction[2]; u64 denominator = 0; /* gcc */ @@ -1996,14 +2004,14 @@ static void get_scan_count(struct lruvec *lruvec, int swappiness, if (current_is_kswapd()) { if (!zone_reclaimable(zone)) force_scan = true; - if (!mem_cgroup_lruvec_online(lruvec)) + if (!mem_cgroup_online(memcg)) force_scan = true; } if (!global_reclaim(sc)) force_scan = true; /* If we have no swap space, do not bother scanning anon pages. */ - if (!sc->may_swap || (get_nr_swap_pages() <= 0)) { + if (!sc->may_swap || mem_cgroup_get_nr_swap_pages(memcg) <= 0) { scan_balance = SCAN_FILE; goto out; } @@ -2193,9 +2201,10 @@ static inline void init_tlb_ubc(void) /* * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. */ -static void shrink_lruvec(struct lruvec *lruvec, int swappiness, - struct scan_control *sc, unsigned long *lru_pages) +static void shrink_zone_memcg(struct zone *zone, struct mem_cgroup *memcg, + struct scan_control *sc, unsigned long *lru_pages) { + struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); unsigned long nr[NR_LRU_LISTS]; unsigned long targets[NR_LRU_LISTS]; unsigned long nr_to_scan; @@ -2205,7 +2214,7 @@ static void shrink_lruvec(struct lruvec *lruvec, int swappiness, struct blk_plug plug; bool scan_adjusted; - get_scan_count(lruvec, swappiness, sc, nr, lru_pages); + get_scan_count(lruvec, memcg, sc, nr, lru_pages); /* Record the original scan target for proportional adjustments later */ memcpy(targets, nr, sizeof(nr)); @@ -2409,8 +2418,6 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, unsigned long lru_pages; unsigned long reclaimed; unsigned long scanned; - struct lruvec *lruvec; - int swappiness; if (mem_cgroup_low(root, memcg)) { if (!sc->may_thrash) @@ -2418,12 +2425,10 @@ static bool shrink_zone(struct zone *zone, struct scan_control *sc, mem_cgroup_events(memcg, MEMCG_LOW, 1); } - lruvec = mem_cgroup_zone_lruvec(zone, memcg); - swappiness = mem_cgroup_swappiness(memcg); reclaimed = sc->nr_reclaimed; scanned = sc->nr_scanned; - shrink_lruvec(lruvec, swappiness, sc, &lru_pages); + shrink_zone_memcg(zone, memcg, sc, &lru_pages); zone_lru_pages += lru_pages; if (memcg && is_classzone) @@ -2893,8 +2898,6 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, .may_unmap = 1, .may_swap = !noswap, }; - struct lruvec *lruvec = mem_cgroup_zone_lruvec(zone, memcg); - int swappiness = mem_cgroup_swappiness(memcg); unsigned long lru_pages; sc.gfp_mask = (gfp_mask & GFP_RECLAIM_MASK) | @@ -2911,7 +2914,7 @@ unsigned long mem_cgroup_shrink_node_zone(struct mem_cgroup *memcg, * will pick up pages from other mem cgroup's as well. We hack * the priority and make it zero. */ - shrink_lruvec(lruvec, swappiness, &sc, &lru_pages); + shrink_zone_memcg(zone, memcg, &sc, &lru_pages); trace_mm_vmscan_memcg_softlimit_reclaim_end(sc.nr_reclaimed); diff --git a/mm/vmstat.c b/mm/vmstat.c index 64bd0aa13f75..084c6725b373 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1396,10 +1396,15 @@ static void vmstat_update(struct work_struct *w) * Counters were updated so we expect more updates * to occur in the future. Keep on running the * update worker thread. + * If we were marked on cpu_stat_off clear the flag + * so that vmstat_shepherd doesn't schedule us again. */ - queue_delayed_work_on(smp_processor_id(), vmstat_wq, - this_cpu_ptr(&vmstat_work), - round_jiffies_relative(sysctl_stat_interval)); + if (!cpumask_test_and_clear_cpu(smp_processor_id(), + cpu_stat_off)) { + queue_delayed_work_on(smp_processor_id(), vmstat_wq, + this_cpu_ptr(&vmstat_work), + round_jiffies_relative(sysctl_stat_interval)); + } } else { /* * We did not update any counters so the app may be in @@ -1408,17 +1413,7 @@ static void vmstat_update(struct work_struct *w) * Defer the checking for differentials to the * shepherd thread on a different processor. */ - int r; - /* - * Shepherd work thread does not race since it never - * changes the bit if its zero but the cpu - * online / off line code may race if - * worker threads are still allowed during - * shutdown / startup. - */ - r = cpumask_test_and_set_cpu(smp_processor_id(), - cpu_stat_off); - VM_BUG_ON(r); + cpumask_set_cpu(smp_processor_id(), cpu_stat_off); } } @@ -1427,18 +1422,6 @@ static void vmstat_update(struct work_struct *w) * until the diffs stay at zero. The function is used by NOHZ and can only be * invoked when tick processing is not active. */ -void quiet_vmstat(void) -{ - if (system_state != SYSTEM_RUNNING) - return; - - do { - if (!cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off)) - cancel_delayed_work(this_cpu_ptr(&vmstat_work)); - - } while (refresh_cpu_vm_stats(false)); -} - /* * Check if the diffs for a certain cpu indicate that * an update is needed. @@ -1462,6 +1445,30 @@ static bool need_update(int cpu) return false; } +void quiet_vmstat(void) +{ + if (system_state != SYSTEM_RUNNING) + return; + + /* + * If we are already in hands of the shepherd then there + * is nothing for us to do here. + */ + if (cpumask_test_and_set_cpu(smp_processor_id(), cpu_stat_off)) + return; + + if (!need_update(smp_processor_id())) + return; + + /* + * Just refresh counters and do not care about the pending delayed + * vmstat_update. It doesn't fire that often to matter and canceling + * it would be too expensive from this path. + * vmstat_shepherd will take care about that for us. + */ + refresh_cpu_vm_stats(false); +} + /* * Shepherd worker thread that checks the @@ -1479,18 +1486,25 @@ static void vmstat_shepherd(struct work_struct *w) get_online_cpus(); /* Check processors whose vmstat worker threads have been disabled */ - for_each_cpu(cpu, cpu_stat_off) - if (need_update(cpu) && - cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - - queue_delayed_work_on(cpu, vmstat_wq, - &per_cpu(vmstat_work, cpu), 0); + for_each_cpu(cpu, cpu_stat_off) { + struct delayed_work *dw = &per_cpu(vmstat_work, cpu); + if (need_update(cpu)) { + if (cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) + queue_delayed_work_on(cpu, vmstat_wq, dw, 0); + } else { + /* + * Cancel the work if quiet_vmstat has put this + * cpu on cpu_stat_off because the work item might + * be still scheduled + */ + cancel_delayed_work(dw); + } + } put_online_cpus(); schedule_delayed_work(&shepherd, round_jiffies_relative(sysctl_stat_interval)); - } static void __init start_shepherd_timer(void) @@ -1498,7 +1512,7 @@ static void __init start_shepherd_timer(void) int cpu; for_each_possible_cpu(cpu) - INIT_DELAYED_WORK(per_cpu_ptr(&vmstat_work, cpu), + INIT_DEFERRABLE_WORK(per_cpu_ptr(&vmstat_work, cpu), vmstat_update); if (!alloc_cpumask_var(&cpu_stat_off, GFP_KERNEL)) diff --git a/mm/workingset.c b/mm/workingset.c index aa017133744b..61ead9e5549d 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -351,8 +351,8 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, node->slots[i] = NULL; BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT)); node->count -= 1U << RADIX_TREE_COUNT_SHIFT; - BUG_ON(!mapping->nrshadows); - mapping->nrshadows--; + BUG_ON(!mapping->nrexceptional); + mapping->nrexceptional--; } } BUG_ON(node->count); diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index e7414cec220b..2d7c4c11fc63 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -309,7 +309,12 @@ static void free_handle(struct zs_pool *pool, unsigned long handle) static void record_obj(unsigned long handle, unsigned long obj) { - *(unsigned long *)handle = obj; + /* + * lsb of @obj represents handle lock while other bits + * represent object value the handle is pointing so + * updating shouldn't do store tearing. + */ + WRITE_ONCE(*(unsigned long *)handle, obj); } /* zpool driver */ @@ -1635,6 +1640,13 @@ static int migrate_zspage(struct zs_pool *pool, struct size_class *class, free_obj = obj_malloc(d_page, class, handle); zs_object_copy(free_obj, used_obj, class); index++; + /* + * record_obj updates handle's value to free_obj and it will + * invalidate lock bit(ie, HANDLE_PIN_BIT) of handle, which + * breaks synchronization using pin_tag(e,g, zs_free) so + * let's keep the lock bit. + */ + free_obj |= BIT(HANDLE_PIN_BIT); record_obj(handle, free_obj); unpin_tag(handle); obj_free(pool, class, used_obj); |