diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/backing-dev.c | 19 | ||||
| -rw-r--r-- | mm/huge_memory.c | 4 | ||||
| -rw-r--r-- | mm/hugetlb.c | 27 | ||||
| -rw-r--r-- | mm/kasan/kasan.c | 2 | ||||
| -rw-r--r-- | mm/memcontrol.c | 49 | ||||
| -rw-r--r-- | mm/memory.c | 8 | ||||
| -rw-r--r-- | mm/oom_kill.c | 2 | ||||
| -rw-r--r-- | mm/page-writeback.c | 6 | ||||
| -rw-r--r-- | mm/page_alloc.c | 3 | ||||
| -rw-r--r-- | mm/shmem.c | 34 | ||||
| -rw-r--r-- | mm/slab.c | 2 | ||||
| -rw-r--r-- | mm/slab.h | 2 | ||||
| -rw-r--r-- | mm/slab_common.c | 6 | ||||
| -rw-r--r-- | mm/slob.c | 2 | ||||
| -rw-r--r-- | mm/slub.c | 304 | ||||
| -rw-r--r-- | mm/vmalloc.c | 5 | ||||
| -rw-r--r-- | mm/vmstat.c | 8 | ||||
| -rw-r--r-- | mm/zswap.c | 6 |
18 files changed, 318 insertions, 171 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index 8ed2ffd..7340353 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -957,8 +957,9 @@ EXPORT_SYMBOL(congestion_wait); * jiffies for either a BDI to exit congestion of the given @sync queue * or a write to complete. * - * In the absence of zone congestion, cond_resched() is called to yield - * the processor if necessary but otherwise does not sleep. + * In the absence of zone congestion, a short sleep or a cond_resched is + * performed to yield the processor and to allow other subsystems to make + * a forward progress. * * The return value is 0 if the sleep is for the full timeout. Otherwise, * it is the number of jiffies that were still remaining when the function @@ -978,7 +979,19 @@ long wait_iff_congested(struct zone *zone, int sync, long timeout) */ if (atomic_read(&nr_wb_congested[sync]) == 0 || !test_bit(ZONE_CONGESTED, &zone->flags)) { - cond_resched(); + + /* + * Memory allocation/reclaim might be called from a WQ + * context and the current implementation of the WQ + * concurrency control doesn't recognize that a particular + * WQ is congested if the worker thread is looping without + * ever sleeping. Therefore we have to do a short sleep + * here rather than calling cond_resched(). + */ + if (current->flags & PF_WQ_WORKER) + schedule_timeout(1); + else + cond_resched(); /* In case we scheduled, work out time remaining */ ret = timeout - (jiffies - start); diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c29ddeb..62fe06b 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2009,7 +2009,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP)) + if (*vm_flags & VM_NO_THP) return -EINVAL; *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; @@ -2025,7 +2025,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_NOHUGEPAGE | VM_NO_THP)) + if (*vm_flags & VM_NO_THP) return -EINVAL; *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 827bb02..ef6963b 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -372,8 +372,10 @@ retry_locked: spin_unlock(&resv->lock); trg = kmalloc(sizeof(*trg), GFP_KERNEL); - if (!trg) + if (!trg) { + kfree(nrg); return -ENOMEM; + } spin_lock(&resv->lock); list_add(&trg->link, &resv->region_cache); @@ -483,8 +485,16 @@ static long region_del(struct resv_map *resv, long f, long t) retry: spin_lock(&resv->lock); list_for_each_entry_safe(rg, trg, head, link) { - if (rg->to <= f) + /* + * Skip regions before the range to be deleted. file_region + * ranges are normally of the form [from, to). However, there + * may be a "placeholder" entry in the map which is of the form + * (from, to) with from == to. Check for placeholder entries + * at the beginning of the range to be deleted. + */ + if (rg->to <= f && (rg->to != rg->from || rg->to != f)) continue; + if (rg->from >= t) break; @@ -1886,7 +1896,10 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, page = __alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; - + if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { + SetPagePrivate(page); + h->resv_huge_pages--; + } spin_lock(&hugetlb_lock); list_move(&page->lru, &h->hugepage_activelist); /* Fall through */ @@ -3693,12 +3706,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | VM_FAULT_SET_HINDEX(hstate_index(h)); + } else { + ptep = huge_pte_alloc(mm, address, huge_page_size(h)); + if (!ptep) + return VM_FAULT_OOM; } - ptep = huge_pte_alloc(mm, address, huge_page_size(h)); - if (!ptep) - return VM_FAULT_OOM; - mapping = vma->vm_file->f_mapping; idx = vma_hugecache_offset(h, vma, address); diff --git a/mm/kasan/kasan.c b/mm/kasan/kasan.c index d41b21b..bc0a8d8 100644 --- a/mm/kasan/kasan.c +++ b/mm/kasan/kasan.c @@ -19,6 +19,7 @@ #include <linux/export.h> #include <linux/init.h> #include <linux/kernel.h> +#include <linux/kmemleak.h> #include <linux/memblock.h> #include <linux/memory.h> #include <linux/mm.h> @@ -444,6 +445,7 @@ int kasan_module_alloc(void *addr, size_t size) if (ret) { find_vm_area(addr)->flags |= VM_KASAN; + kmemleak_ignore(ret); return 0; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 9acfb16..e234c21 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2128,7 +2128,7 @@ done_restock: */ do { if (page_counter_read(&memcg->memory) > memcg->high) { - current->memcg_nr_pages_over_high += nr_pages; + current->memcg_nr_pages_over_high += batch; set_notify_resume(current); break; } @@ -4779,23 +4779,18 @@ static void mem_cgroup_clear_mc(void) spin_unlock(&mc.lock); } -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { - struct mem_cgroup *memcg = mem_cgroup_from_css(css); + struct cgroup_subsys_state *css; + struct mem_cgroup *memcg; struct mem_cgroup *from; struct task_struct *leader, *p; struct mm_struct *mm; unsigned long move_flags; int ret = 0; - /* - * We are now commited to this value whatever it is. Changes in this - * tunable will only affect upcoming migrations, not the current one. - * So we need to save it, and keep it going. - */ - move_flags = READ_ONCE(memcg->move_charge_at_immigrate); - if (!move_flags) + /* charge immigration isn't supported on the default hierarchy */ + if (cgroup_subsys_on_dfl(memory_cgrp_subsys)) return 0; /* @@ -4805,13 +4800,23 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, * multiple. */ p = NULL; - cgroup_taskset_for_each_leader(leader, tset) { + cgroup_taskset_for_each_leader(leader, css, tset) { WARN_ON_ONCE(p); p = leader; + memcg = mem_cgroup_from_css(css); } if (!p) return 0; + /* + * We are now commited to this value whatever it is. Changes in this + * tunable will only affect upcoming migrations, not the current one. + * So we need to save it, and keep it going. + */ + move_flags = READ_ONCE(memcg->move_charge_at_immigrate); + if (!move_flags) + return 0; + from = mem_cgroup_from_task(p); VM_BUG_ON(from == memcg); @@ -4842,8 +4847,7 @@ static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, return ret; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { if (mc.to) mem_cgroup_clear_mc(); @@ -4985,10 +4989,10 @@ retry: atomic_dec(&mc.from->moving_account); } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { - struct task_struct *p = cgroup_taskset_first(tset); + struct cgroup_subsys_state *css; + struct task_struct *p = cgroup_taskset_first(tset, &css); struct mm_struct *mm = get_task_mm(p); if (mm) { @@ -5000,17 +5004,14 @@ static void mem_cgroup_move_task(struct cgroup_subsys_state *css, mem_cgroup_clear_mc(); } #else /* !CONFIG_MMU */ -static int mem_cgroup_can_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static void mem_cgroup_cancel_attach(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } -static void mem_cgroup_move_task(struct cgroup_subsys_state *css, - struct cgroup_taskset *tset) +static void mem_cgroup_move_task(struct cgroup_taskset *tset) { } #endif @@ -5511,11 +5512,11 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) * mem_cgroup_replace_page - migrate a charge to another page * @oldpage: currently charged page * @newpage: page to transfer the charge to - * @lrucare: either or both pages might be on the LRU already * * Migrate the charge from @oldpage to @newpage. * * Both pages must be locked, @newpage->mapping must be set up. + * Either or both pages might be on the LRU already. */ void mem_cgroup_replace_page(struct page *oldpage, struct page *newpage) { diff --git a/mm/memory.c b/mm/memory.c index deb679c..c387430 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -3015,9 +3015,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else { /* * The fault handler has no page to lock, so it holds - * i_mmap_lock for write to protect against truncate. + * i_mmap_lock for read to protect against truncate. */ - i_mmap_unlock_write(vma->vm_file->f_mapping); + i_mmap_unlock_read(vma->vm_file->f_mapping); } goto uncharge_out; } @@ -3031,9 +3031,9 @@ static int do_cow_fault(struct mm_struct *mm, struct vm_area_struct *vma, } else { /* * The fault handler has no page to lock, so it holds - * i_mmap_lock for write to protect against truncate. + * i_mmap_lock for read to protect against truncate. */ - i_mmap_unlock_write(vma->vm_file->f_mapping); + i_mmap_unlock_read(vma->vm_file->f_mapping); } return ret; uncharge_out: diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d13a339..c126809 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -608,6 +608,8 @@ void oom_kill_process(struct oom_control *oc, struct task_struct *p, continue; if (unlikely(p->flags & PF_KTHREAD)) continue; + if (is_global_init(p)) + continue; if (p->signal->oom_score_adj == OOM_SCORE_ADJ_MIN) continue; diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 2c90357..d15d88c 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2,7 +2,7 @@ * mm/page-writeback.c * * Copyright (C) 2002, Linus Torvalds. - * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra <pzijlstr@redhat.com> + * Copyright (C) 2007 Red Hat, Inc., Peter Zijlstra * * Contains functions related to writing back dirty pages at the * address_space level. @@ -1542,7 +1542,9 @@ static void balance_dirty_pages(struct address_space *mapping, for (;;) { unsigned long now = jiffies; unsigned long dirty, thresh, bg_thresh; - unsigned long m_dirty, m_thresh, m_bg_thresh; + unsigned long m_dirty = 0; /* stop bogus uninit warnings */ + unsigned long m_thresh = 0; + unsigned long m_bg_thresh = 0; /* * Unstable writes are a feature of certain networked diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 17a3c66..9d666df 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3647,8 +3647,9 @@ static void show_migration_types(unsigned char type) { static const char types[MIGRATE_TYPES] = { [MIGRATE_UNMOVABLE] = 'U', - [MIGRATE_RECLAIMABLE] = 'E', [MIGRATE_MOVABLE] = 'M', + [MIGRATE_RECLAIMABLE] = 'E', + [MIGRATE_HIGHATOMIC] = 'H', #ifdef CONFIG_CMA [MIGRATE_CMA] = 'C', #endif @@ -843,14 +843,14 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) list_add_tail(&info->swaplist, &shmem_swaplist); if (add_to_swap_cache(page, swap, GFP_ATOMIC) == 0) { - swap_shmem_alloc(swap); - shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); - spin_lock(&info->lock); - info->swapped++; shmem_recalc_inode(inode); + info->swapped++; spin_unlock(&info->lock); + swap_shmem_alloc(swap); + shmem_delete_from_page_cache(page, swp_to_radix_entry(swap)); + mutex_unlock(&shmem_swaplist_mutex); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); @@ -1078,7 +1078,7 @@ repeat: if (sgp != SGP_WRITE && sgp != SGP_FALLOC && ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { error = -EINVAL; - goto failed; + goto unlock; } if (page && sgp == SGP_WRITE) @@ -1246,11 +1246,15 @@ clear: /* Perhaps the file has been truncated since we checked */ if (sgp != SGP_WRITE && sgp != SGP_FALLOC && ((loff_t)index << PAGE_CACHE_SHIFT) >= i_size_read(inode)) { + if (alloced) { + ClearPageDirty(page); + delete_from_page_cache(page); + spin_lock(&info->lock); + shmem_recalc_inode(inode); + spin_unlock(&info->lock); + } error = -EINVAL; - if (alloced) - goto trunc; - else - goto failed; + goto unlock; } *pagep = page; return 0; @@ -1258,23 +1262,13 @@ clear: /* * Error recovery. */ -trunc: - info = SHMEM_I(inode); - ClearPageDirty(page); - delete_from_page_cache(page); - spin_lock(&info->lock); - info->alloced--; - inode->i_blocks -= BLOCKS_PER_PAGE; - spin_unlock(&info->lock); decused: - sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) percpu_counter_add(&sbinfo->used_blocks, -1); unacct: shmem_unacct_blocks(info->flags, 1); failed: - if (swap.val && error != -EINVAL && - !shmem_confirm_swap(mapping, index, swap)) + if (swap.val && !shmem_confirm_swap(mapping, index, swap)) error = -EEXIST; unlock: if (page) { @@ -3419,7 +3419,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) } EXPORT_SYMBOL(kmem_cache_free_bulk); -bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p) { return __kmem_cache_alloc_bulk(s, flags, size, p); @@ -170,7 +170,7 @@ ssize_t slabinfo_write(struct file *file, const char __user *buffer, * may be allocated or freed using these operations. */ void __kmem_cache_free_bulk(struct kmem_cache *, size_t, void **); -bool __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); +int __kmem_cache_alloc_bulk(struct kmem_cache *, gfp_t, size_t, void **); #ifdef CONFIG_MEMCG_KMEM /* diff --git a/mm/slab_common.c b/mm/slab_common.c index d88e97c..3c6a86b 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -112,7 +112,7 @@ void __kmem_cache_free_bulk(struct kmem_cache *s, size_t nr, void **p) kmem_cache_free(s, p[i]); } -bool __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, +int __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, void **p) { size_t i; @@ -121,10 +121,10 @@ bool __kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t nr, void *x = p[i] = kmem_cache_alloc(s, flags); if (!x) { __kmem_cache_free_bulk(s, i, p); - return false; + return 0; } } - return true; + return i; } #ifdef CONFIG_MEMCG_KMEM @@ -617,7 +617,7 @@ void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) } EXPORT_SYMBOL(kmem_cache_free_bulk); -bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void **p) { return __kmem_cache_alloc_bulk(s, flags, size, p); @@ -1065,11 +1065,15 @@ bad: return 0; } +/* Supports checking bulk free of a constructed freelist */ static noinline struct kmem_cache_node *free_debug_processing( - struct kmem_cache *s, struct page *page, void *object, + struct kmem_cache *s, struct page *page, + void *head, void *tail, int bulk_cnt, unsigned long addr, unsigned long *flags) { struct kmem_cache_node *n = get_node(s, page_to_nid(page)); + void *object = head; + int cnt = 0; spin_lock_irqsave(&n->list_lock, *flags); slab_lock(page); @@ -1077,6 +1081,9 @@ static noinline struct kmem_cache_node *free_debug_processing( if (!check_slab(s, page)) goto fail; +next_object: + cnt++; + if (!check_valid_pointer(s, page, object)) { slab_err(s, page, "Invalid object pointer 0x%p", object); goto fail; @@ -1107,8 +1114,19 @@ static noinline struct kmem_cache_node *free_debug_processing( if (s->flags & SLAB_STORE_USER) set_track(s, object, TRACK_FREE, addr); trace(s, page, object, 0); + /* Freepointer not overwritten by init_object(), SLAB_POISON moved it */ init_object(s, object, SLUB_RED_INACTIVE); + + /* Reached end of constructed freelist yet? */ + if (object != tail) { + object = get_freepointer(s, object); + goto next_object; + } out: + if (cnt != bulk_cnt) + slab_err(s, page, "Bulk freelist count(%d) invalid(%d)\n", + bulk_cnt, cnt); + slab_unlock(page); /* * Keep node_lock to preserve integrity @@ -1204,7 +1222,7 @@ unsigned long kmem_cache_flags(unsigned long object_size, return flags; } -#else +#else /* !CONFIG_SLUB_DEBUG */ static inline void setup_object_debug(struct kmem_cache *s, struct page *page, void *object) {} @@ -1212,7 +1230,8 @@ static inline int alloc_debug_processing(struct kmem_cache *s, struct page *page, void *object, unsigned long addr) { return 0; } static inline struct kmem_cache_node *free_debug_processing( - struct kmem_cache *s, struct page *page, void *object, + struct kmem_cache *s, struct page *page, + void *head, void *tail, int bulk_cnt, unsigned long addr, unsigned long *flags) { return NULL; } static inline int slab_pad_check(struct kmem_cache *s, struct page *page) @@ -1273,14 +1292,21 @@ static inline struct kmem_cache *slab_pre_alloc_hook(struct kmem_cache *s, return memcg_kmem_get_cache(s, flags); } -static inline void slab_post_alloc_hook(struct kmem_cache *s, - gfp_t flags, void *object) +static inline void slab_post_alloc_hook(struct kmem_cache *s, gfp_t flags, + size_t size, void **p) { + size_t i; + flags &= gfp_allowed_mask; - kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); - kmemleak_alloc_recursive(object, s->object_size, 1, s->flags, flags); + for (i = 0; i < size; i++) { + void *object = p[i]; + + kmemcheck_slab_alloc(s, flags, object, slab_ksize(s)); + kmemleak_alloc_recursive(object, s->object_size, 1, + s->flags, flags); + kasan_slab_alloc(s, object); + } memcg_kmem_put_cache(s); - kasan_slab_alloc(s, object); } static inline void slab_free_hook(struct kmem_cache *s, void *x) @@ -1308,6 +1334,29 @@ static inline void slab_free_hook(struct kmem_cache *s, void *x) kasan_slab_free(s, x); } +static inline void slab_free_freelist_hook(struct kmem_cache *s, + void *head, void *tail) +{ +/* + * Compiler cannot detect this function can be removed if slab_free_hook() + * evaluates to nothing. Thus, catch all relevant config debug options here. + */ +#if defined(CONFIG_KMEMCHECK) || \ + defined(CONFIG_LOCKDEP) || \ + defined(CONFIG_DEBUG_KMEMLEAK) || \ + defined(CONFIG_DEBUG_OBJECTS_FREE) || \ + defined(CONFIG_KASAN) + + void *object = head; + void *tail_obj = tail ? : head; + + do { + slab_free_hook(s, object); + } while ((object != tail_obj) && + (object = get_freepointer(s, object))); +#endif +} + static void setup_object(struct kmem_cache *s, struct page *page, void *object) { @@ -2295,23 +2344,15 @@ static inline void *get_freelist(struct kmem_cache *s, struct page *page) * And if we were unable to get a new slab from the partial slab lists then * we need to allocate a new slab. This is the slowest path since it involves * a call to the page allocator and the setup of a new slab. + * + * Version of __slab_alloc to use when we know that interrupts are + * already disabled (which is the case for bulk allocation). */ -static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, +static void *___slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr, struct kmem_cache_cpu *c) { void *freelist; struct page *page; - unsigned long flags; - - local_irq_save(flags); -#ifdef CONFIG_PREEMPT - /* - * We may have been preempted and rescheduled on a different - * cpu before disabling interrupts. Need to reload cpu area - * pointer. - */ - c = this_cpu_ptr(s->cpu_slab); -#endif page = c->page; if (!page) @@ -2369,7 +2410,6 @@ load_freelist: VM_BUG_ON(!c->page->frozen); c->freelist = get_freepointer(s, freelist); c->tid = next_tid(c->tid); - local_irq_restore(flags); return freelist; new_slab: @@ -2386,7 +2426,6 @@ new_slab: if (unlikely(!freelist)) { slab_out_of_memory(s, gfpflags, node); - local_irq_restore(flags); return NULL; } @@ -2402,11 +2441,35 @@ new_slab: deactivate_slab(s, page, get_freepointer(s, freelist)); c->page = NULL; c->freelist = NULL; - local_irq_restore(flags); return freelist; } /* + * Another one that disabled interrupt and compensates for possible + * cpu changes by refetching the per cpu area pointer. + */ +static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, + unsigned long addr, struct kmem_cache_cpu *c) +{ + void *p; + unsigned long flags; + + local_irq_save(flags); +#ifdef CONFIG_PREEMPT + /* + * We may have been preempted and rescheduled on a different + * cpu before disabling interrupts. Need to reload cpu area + * pointer. + */ + c = this_cpu_ptr(s->cpu_slab); +#endif + + p = ___slab_alloc(s, gfpflags, node, addr, c); + local_irq_restore(flags); + return p; +} + +/* * Inlined fastpath so that allocation functions (kmalloc, kmem_cache_alloc) * have the fastpath folded into their functions. So no function call * overhead for requests that can be satisfied on the fastpath. @@ -2419,7 +2482,7 @@ new_slab: static __always_inline void *slab_alloc_node(struct kmem_cache *s, gfp_t gfpflags, int node, unsigned long addr) { - void **object; + void *object; struct kmem_cache_cpu *c; struct page *page; unsigned long tid; @@ -2498,7 +2561,7 @@ redo: if (unlikely(gfpflags & __GFP_ZERO) && object) memset(object, 0, s->object_size); - slab_post_alloc_hook(s, gfpflags, object); + slab_post_alloc_hook(s, gfpflags, 1, &object); return object; } @@ -2569,10 +2632,11 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); * handling required then we can return immediately. */ static void __slab_free(struct kmem_cache *s, struct page *page, - void *x, unsigned long addr) + void *head, void *tail, int cnt, + unsigned long addr) + { void *prior; - void **object = (void *)x; int was_frozen; struct page new; unsigned long counters; @@ -2582,7 +2646,8 @@ static void __slab_free(struct kmem_cache *s, struct page *page, stat(s, FREE_SLOWPATH); if (kmem_cache_debug(s) && - !(n = free_debug_processing(s, page, x, addr, &flags))) + !(n = free_debug_processing(s, page, head, tail, cnt, + addr, &flags))) return; do { @@ -2592,10 +2657,10 @@ static void __slab_free(struct kmem_cache *s, struct page *page, } prior = page->freelist; counters = page->counters; - set_freepointer(s, object, prior); + set_freepointer(s, tail, prior); new.counters = counters; was_frozen = new.frozen; - new.inuse--; + new.inuse -= cnt; if ((!new.inuse || !prior) && !was_frozen) { if (kmem_cache_has_cpu_partial(s) && !prior) { @@ -2626,7 +2691,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, } while (!cmpxchg_double_slab(s, page, prior, counters, - object, new.counters, + head, new.counters, "__slab_free")); if (likely(!n)) { @@ -2691,15 +2756,20 @@ slab_empty: * * If fastpath is not possible then fall back to __slab_free where we deal * with all sorts of special processing. + * + * Bulk free of a freelist with several objects (all pointing to the + * same page) possible by specifying head and tail ptr, plus objects + * count (cnt). Bulk free indicated by tail pointer being set. */ -static __always_inline void slab_free(struct kmem_cache *s, - struct page *page, void *x, unsigned long addr) +static __always_inline void slab_free(struct kmem_cache *s, struct page *page, + void *head, void *tail, int cnt, + unsigned long addr) { - void **object = (void *)x; + void *tail_obj = tail ? : head; struct kmem_cache_cpu *c; unsigned long tid; - slab_free_hook(s, x); + slab_free_freelist_hook(s, head, tail); redo: /* @@ -2718,19 +2788,19 @@ redo: barrier(); if (likely(page == c->page)) { - set_freepointer(s, object, c->freelist); + set_freepointer(s, tail_obj, c->freelist); if (unlikely(!this_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, c->freelist, tid, - object, next_tid(tid)))) { + head, next_tid(tid)))) { note_cmpxchg_failure("slab_free", s, tid); goto redo; } stat(s, FREE_FASTPATH); } else - __slab_free(s, page, x, addr); + __slab_free(s, page, head, tail_obj, cnt, addr); } @@ -2739,59 +2809,116 @@ void kmem_cache_free(struct kmem_cache *s, void *x) s = cache_from_obj(s, x); if (!s) return; - slab_free(s, virt_to_head_page(x), x, _RET_IP_); + slab_free(s, virt_to_head_page(x), x, NULL, 1, _RET_IP_); trace_kmem_cache_free(_RET_IP_, x); } EXPORT_SYMBOL(kmem_cache_free); -/* Note that interrupts must be enabled when calling this function. */ -void kmem_cache_free_bulk(struct kmem_cache *s, size_t size, void **p) -{ - struct kmem_cache_cpu *c; +struct detached_freelist { struct page *page; - int i; + void *tail; + void *freelist; + int cnt; +}; - local_irq_disable(); - c = this_cpu_ptr(s->cpu_slab); +/* + * This function progressively scans the array with free objects (with + * a limited look ahead) and extract objects belonging to the same + * page. It builds a detached freelist directly within the given + * page/objects. This can happen without any need for + * synchronization, because the objects are owned by running process. + * The freelist is build up as a single linked list in the objects. + * The idea is, that this detached freelist can then be bulk + * transferred to the real freelist(s), but only requiring a single + * synchronization primitive. Look ahead in the array is limited due + * to performance reasons. + */ +static int build_detached_freelist(struct kmem_cache *s, size_t size, + void **p, struct detached_freelist *df) +{ + size_t first_skipped_index = 0; + int lookahead = 3; + void *object; - for (i = 0; i < size; i++) { - void *object = p[i]; + /* Always re-init detached_freelist */ + df->page = NULL; - BUG_ON(!object); - /* kmem cache debug support */ - s = cache_from_obj(s, object); - if (unlikely(!s)) - goto exit; - slab_free_hook(s, object); + do { + object = p[--size]; + } while (!object && size); - page = virt_to_head_page(object); + if (!object) + return 0; - if (c->page == page) { - /* Fastpath: local CPU free */ - set_freepointer(s, object, c->freelist); - c->freelist = object; - } else { - c->tid = next_tid(c->tid); - local_irq_enable(); - /* Slowpath: overhead locked cmpxchg_double_slab */ - __slab_free(s, page, object, _RET_IP_); - local_irq_disable(); - c = this_cpu_ptr(s->cpu_slab); + /* Start new detached freelist */ + set_freepointer(s, object, NULL); + df->page = virt_to_head_page(object); + df->tail = object; + df->freelist = object; + p[size] = NULL; /* mark object processed */ + df->cnt = 1; + + while (size) { + object = p[--size]; + if (!object) + continue; /* Skip processed objects */ + + /* df->page is always set at this point */ + if (df->page == virt_to_head_page(object)) { + /* Opportunity build freelist */ + set_freepointer(s, object, df->freelist); + df->freelist = object; + df->cnt++; + p[size] = NULL; /* mark object processed */ + + continue; } + + /* Limit look ahead search */ + if (!--lookahead) + break; + + if (!first_skipped_index) + first_skipped_index = size + 1; } -exit: - c->tid = next_tid(c->tid); - local_irq_enable(); + + return first_skipped_index; +} + + +/* Note that interrupts must be enabled when calling this function. */ +void kmem_cache_free_bulk(struct kmem_cache *orig_s, size_t size, void **p) +{ + if (WARN_ON(!size)) + return; + + do { + struct detached_freelist df; + struct kmem_cache *s; + + /* Support for memcg */ + s = cache_from_obj(orig_s, p[size - 1]); + + size = build_detached_freelist(s, size, p, &df); + if (unlikely(!df.page)) + continue; + + slab_free(s, df.page, df.freelist, df.tail, df.cnt, _RET_IP_); + } while (likely(size)); } EXPORT_SYMBOL(kmem_cache_free_bulk); /* Note that interrupts must be enabled when calling this function. */ -bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, - void **p) +int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, + void **p) { struct kmem_cache_cpu *c; int i; + /* memcg and kmem_cache debug support */ + s = slab_pre_alloc_hook(s, flags); + if (unlikely(!s)) + return false; /* * Drain objects in the per cpu slab, while disabling local * IRQs, which protects against PREEMPT and interrupts @@ -2804,36 +2931,20 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, void *object = c->freelist; if (unlikely(!object)) { - local_irq_enable(); /* * Invoking slow path likely have side-effect * of re-populating per CPU c->freelist */ - p[i] = __slab_alloc(s, flags, NUMA_NO_NODE, + p[i] = ___slab_alloc(s, flags, NUMA_NO_NODE, _RET_IP_, c); - if (unlikely(!p[i])) { - __kmem_cache_free_bulk(s, i, p); - return false; - } - local_irq_disable(); + if (unlikely(!p[i])) + goto error; + c = this_cpu_ptr(s->cpu_slab); continue; /* goto for-loop */ } - - /* kmem_cache debug support */ - s = slab_pre_alloc_hook(s, flags); - if (unlikely(!s)) { - __kmem_cache_free_bulk(s, i, p); - c->tid = next_tid(c->tid); - local_irq_enable(); - return false; - } - c->freelist = get_freepointer(s, object); p[i] = object; - - /* kmem_cache debug support */ - slab_post_alloc_hook(s, flags, object); } c->tid = next_tid(c->tid); local_irq_enable(); @@ -2846,7 +2957,14 @@ bool kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, memset(p[j], 0, s->object_size); } - return true; + /* memcg and kmem_cache debug support */ + slab_post_alloc_hook(s, flags, size, p); + return i; +error: + local_irq_enable(); + slab_post_alloc_hook(s, flags, i, p); + __kmem_cache_free_bulk(s, i, p); + return 0; } EXPORT_SYMBOL(kmem_cache_alloc_bulk); @@ -3511,7 +3629,7 @@ void kfree(const void *x) __free_kmem_pages(page, compound_order(page)); return; } - slab_free(page->slab_cache, page, object, _RET_IP_); + slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); } EXPORT_SYMBOL(kfree); diff --git a/mm/vmalloc.c b/mm/vmalloc.c index d045634..8e3c9c5 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -1443,7 +1443,6 @@ struct vm_struct *remove_vm_area(const void *addr) vmap_debug_free_range(va->va_start, va->va_end); kasan_free_shadow(vm); free_unmap_vmap_area(va); - vm->size -= PAGE_SIZE; return vm; } @@ -1468,8 +1467,8 @@ static void __vunmap(const void *addr, int deallocate_pages) return; } - debug_check_no_locks_freed(addr, area->size); - debug_check_no_obj_freed(addr, area->size); + debug_check_no_locks_freed(addr, get_vm_area_size(area)); + debug_check_no_obj_freed(addr, get_vm_area_size(area)); if (deallocate_pages) { int i; diff --git a/mm/vmstat.c b/mm/vmstat.c index 879a2be..0d5712b 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -921,8 +921,8 @@ static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, #ifdef CONFIG_PROC_FS static char * const migratetype_names[MIGRATE_TYPES] = { "Unmovable", - "Reclaimable", "Movable", + "Reclaimable", "HighAtomic", #ifdef CONFIG_CMA "CMA", @@ -1379,6 +1379,7 @@ static const struct file_operations proc_vmstat_file_operations = { #endif /* CONFIG_PROC_FS */ #ifdef CONFIG_SMP +static struct workqueue_struct *vmstat_wq; static DEFINE_PER_CPU(struct delayed_work, vmstat_work); int sysctl_stat_interval __read_mostly = HZ; static cpumask_var_t cpu_stat_off; @@ -1391,7 +1392,7 @@ static void vmstat_update(struct work_struct *w) * to occur in the future. Keep on running the * update worker thread. */ - schedule_delayed_work_on(smp_processor_id(), + queue_delayed_work_on(smp_processor_id(), vmstat_wq, this_cpu_ptr(&vmstat_work), round_jiffies_relative(sysctl_stat_interval)); } else { @@ -1460,7 +1461,7 @@ static void vmstat_shepherd(struct work_struct *w) if (need_update(cpu) && cpumask_test_and_clear_cpu(cpu, cpu_stat_off)) - schedule_delayed_work_on(cpu, + queue_delayed_work_on(cpu, vmstat_wq, &per_cpu(vmstat_work, cpu), 0); put_online_cpus(); @@ -1549,6 +1550,7 @@ static int __init setup_vmstat(void) start_shepherd_timer(); cpu_notifier_register_done(); + vmstat_wq = alloc_workqueue("vmstat", WQ_FREEZABLE|WQ_MEM_RECLAIM, 0); #endif #ifdef CONFIG_PROC_FS proc_create("buddyinfo", S_IRUGO, NULL, &fragmentation_file_operations); @@ -541,6 +541,7 @@ static struct zswap_pool *zswap_pool_last_get(void) return last; } +/* type and compressor must be null-terminated */ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) { struct zswap_pool *pool; @@ -548,10 +549,9 @@ static struct zswap_pool *zswap_pool_find_get(char *type, char *compressor) assert_spin_locked(&zswap_pools_lock); list_for_each_entry_rcu(pool, &zswap_pools, list) { - if (strncmp(pool->tfm_name, compressor, sizeof(pool->tfm_name))) + if (strcmp(pool->tfm_name, compressor)) continue; - if (strncmp(zpool_get_type(pool->zpool), type, - sizeof(zswap_zpool_type))) + if (strcmp(zpool_get_type(pool->zpool), type)) continue; /* if we can't get it, it's about to be destroyed */ if (!zswap_pool_get(pool)) |
