diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/cma.c | 7 | ||||
| -rw-r--r-- | mm/filemap.c | 95 | ||||
| -rw-r--r-- | mm/hugetlb.c | 13 | ||||
| -rw-r--r-- | mm/kasan/kasan.h | 3 | ||||
| -rw-r--r-- | mm/ksm.c | 3 | ||||
| -rw-r--r-- | mm/list_lru.c | 2 | ||||
| -rw-r--r-- | mm/memblock.c | 28 | ||||
| -rw-r--r-- | mm/memcontrol.c | 19 | ||||
| -rw-r--r-- | mm/page-writeback.c | 14 | ||||
| -rw-r--r-- | mm/page_alloc.c | 21 | ||||
| -rw-r--r-- | mm/swapfile.c | 2 | ||||
| -rw-r--r-- | mm/usercopy.c | 1 | ||||
| -rw-r--r-- | mm/vmscan.c | 21 | ||||
| -rw-r--r-- | mm/workingset.c | 10 |
14 files changed, 130 insertions, 109 deletions
@@ -188,7 +188,8 @@ int __init cma_init_reserved_mem(phys_addr_t base, phys_addr_t size, return -EINVAL; /* ensure minimal alignment required by mm core */ - alignment = PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order); + alignment = PAGE_SIZE << + max_t(unsigned long, MAX_ORDER - 1, pageblock_order); /* alignment should be aligned with order_per_bit */ if (!IS_ALIGNED(alignment >> PAGE_SHIFT, 1 << order_per_bit)) @@ -271,8 +272,8 @@ int __init cma_declare_contiguous(phys_addr_t base, * migratetype page by page allocator's buddy algorithm. In the case, * you couldn't get a contiguous memory, which is not what we want. */ - alignment = max(alignment, - (phys_addr_t)PAGE_SIZE << max(MAX_ORDER - 1, pageblock_order)); + alignment = max(alignment, (phys_addr_t)PAGE_SIZE << + max_t(unsigned long, MAX_ORDER - 1, pageblock_order)); base = ALIGN(base, alignment); size = ALIGN(size, alignment); limit &= ~(alignment - 1); diff --git a/mm/filemap.c b/mm/filemap.c index a322c035c6b9..c46678d7d041 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -109,6 +109,48 @@ * ->tasklist_lock (memory_failure, collect_procs_ao) */ +static int page_cache_tree_insert(struct address_space *mapping, + struct page *page, void **shadowp) +{ + struct radix_tree_node *node; + void **slot; + int error; + + error = __radix_tree_create(&mapping->page_tree, page->index, + &node, &slot); + if (error) + return error; + if (*slot) { + void *p; + + p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); + if (!radix_tree_exceptional_entry(p)) + return -EEXIST; + if (shadowp) + *shadowp = p; + mapping->nrshadows--; + if (node) + workingset_node_shadows_dec(node); + } + radix_tree_replace_slot(slot, page); + mapping->nrpages++; + if (node) { + workingset_node_pages_inc(node); + /* + * Don't track node that contains actual pages. + * + * 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 (!list_empty(&node->private_list)) + list_lru_del(&workingset_shadow_nodes, + &node->private_list); + } + return 0; +} + static void page_cache_tree_delete(struct address_space *mapping, struct page *page, void *shadow) { @@ -122,6 +164,14 @@ static void page_cache_tree_delete(struct address_space *mapping, __radix_tree_lookup(&mapping->page_tree, page->index, &node, &slot); + if (!node) { + /* + * We need a node to properly account shadow + * entries. Don't plant any without. XXX + */ + shadow = NULL; + } + if (shadow) { mapping->nrshadows++; /* @@ -540,9 +590,8 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) memcg = mem_cgroup_begin_page_stat(old); spin_lock_irqsave(&mapping->tree_lock, flags); __delete_from_page_cache(old, NULL, memcg); - error = radix_tree_insert(&mapping->page_tree, offset, new); + error = page_cache_tree_insert(mapping, new, NULL); BUG_ON(error); - mapping->nrpages++; /* * hugetlb pages do not participate in page cache accounting. @@ -564,48 +613,6 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static int page_cache_tree_insert(struct address_space *mapping, - struct page *page, void **shadowp) -{ - struct radix_tree_node *node; - void **slot; - int error; - - error = __radix_tree_create(&mapping->page_tree, page->index, - &node, &slot); - if (error) - return error; - if (*slot) { - void *p; - - p = radix_tree_deref_slot_protected(slot, &mapping->tree_lock); - if (!radix_tree_exceptional_entry(p)) - return -EEXIST; - if (shadowp) - *shadowp = p; - mapping->nrshadows--; - if (node) - workingset_node_shadows_dec(node); - } - radix_tree_replace_slot(slot, page); - mapping->nrpages++; - if (node) { - workingset_node_pages_inc(node); - /* - * Don't track node that contains actual pages. - * - * 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 (!list_empty(&node->private_list)) - list_lru_del(&workingset_shadow_nodes, - &node->private_list); - } - return 0; -} - static int __add_to_page_cache_locked(struct page *page, struct address_space *mapping, pgoff_t offset, gfp_t gfp_mask, diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 125c7dd55322..4434cdd4cd9a 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1416,12 +1416,13 @@ static void dissolve_free_huge_page(struct page *page) { spin_lock(&hugetlb_lock); if (PageHuge(page) && !page_count(page)) { - struct hstate *h = page_hstate(page); - int nid = page_to_nid(page); - list_del(&page->lru); + struct page *head = compound_head(page); + struct hstate *h = page_hstate(head); + int nid = page_to_nid(head); + list_del(&head->lru); h->free_huge_pages--; h->free_huge_pages_node[nid]--; - update_and_free_page(h, page); + update_and_free_page(h, head); } spin_unlock(&hugetlb_lock); } @@ -1429,7 +1430,8 @@ static void dissolve_free_huge_page(struct page *page) /* * Dissolve free hugepages in a given pfn range. Used by memory hotplug to * make specified memory blocks removable from the system. - * Note that start_pfn should aligned with (minimum) hugepage size. + * Note that this will dissolve a free gigantic hugepage completely, if any + * part of it lies within the given range. */ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) { @@ -1438,7 +1440,6 @@ void dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) if (!hugepages_supported()) return; - VM_BUG_ON(!IS_ALIGNED(start_pfn, 1 << minimum_order)); for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) dissolve_free_huge_page(pfn_to_page(pfn)); } diff --git a/mm/kasan/kasan.h b/mm/kasan/kasan.h index 4f6c62e5c21e..37ff0ab6a8ff 100644 --- a/mm/kasan/kasan.h +++ b/mm/kasan/kasan.h @@ -52,6 +52,9 @@ struct kasan_global { #if KASAN_ABI_VERSION >= 4 struct kasan_source_location *location; #endif +#if KASAN_ABI_VERSION >= 5 + char *odr_indicator; +#endif }; static inline const void *kasan_shadow_to_mem(const void *shadow_addr) @@ -301,7 +301,8 @@ static inline struct rmap_item *alloc_rmap_item(void) { struct rmap_item *rmap_item; - rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL); + rmap_item = kmem_cache_zalloc(rmap_item_cache, GFP_KERNEL | + __GFP_NORETRY | __GFP_NOWARN); if (rmap_item) ksm_rmap_items++; return rmap_item; diff --git a/mm/list_lru.c b/mm/list_lru.c index afc71ea9a381..5d8dffd5b57c 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -554,6 +554,8 @@ int __list_lru_init(struct list_lru *lru, bool memcg_aware, err = memcg_init_list_lru(lru, memcg_aware); if (err) { kfree(lru->node); + /* Do this so a list_lru_destroy() doesn't crash: */ + lru->node = NULL; goto out; } diff --git a/mm/memblock.c b/mm/memblock.c index 7f0a860a357e..89e74fa82290 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -827,6 +827,17 @@ int __init_memblock memblock_mark_mirror(phys_addr_t base, phys_addr_t size) return memblock_setclr_flag(base, size, 1, MEMBLOCK_MIRROR); } +/** + * memblock_mark_nomap - Mark a memory region with flag MEMBLOCK_NOMAP. + * @base: the base phys addr of the region + * @size: the size of the region + * + * Return 0 on success, -errno on failure. + */ +int __init_memblock memblock_mark_nomap(phys_addr_t base, phys_addr_t size) +{ + return memblock_setclr_flag(base, size, 1, MEMBLOCK_NOMAP); +} /** * __next_reserved_mem_region - next function for for_each_reserved_region() @@ -918,6 +929,10 @@ void __init_memblock __next_mem_range(u64 *idx, int nid, ulong flags, if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) continue; + /* skip nomap memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) + continue; + if (!type_b) { if (out_start) *out_start = m_start; @@ -1027,6 +1042,10 @@ void __init_memblock __next_mem_range_rev(u64 *idx, int nid, ulong flags, if ((flags & MEMBLOCK_MIRROR) && !memblock_is_mirror(m)) continue; + /* skip nomap memory unless we were asked for it explicitly */ + if (!(flags & MEMBLOCK_NOMAP) && memblock_is_nomap(m)) + continue; + if (!type_b) { if (out_start) *out_start = m_start; @@ -1538,6 +1557,15 @@ int __init_memblock memblock_is_memory(phys_addr_t addr) return memblock_search(&memblock.memory, addr) != -1; } +int __init_memblock memblock_is_map_memory(phys_addr_t addr) +{ + int i = memblock_search(&memblock.memory, addr); + + if (i == -1) + return false; + return !memblock_is_nomap(&memblock.memory.regions[i]); +} + #ifdef CONFIG_HAVE_MEMBLOCK_NODE_MAP int __init_memblock memblock_search_pfn_nid(unsigned long pfn, unsigned long *start_pfn, unsigned long *end_pfn) diff --git a/mm/memcontrol.c b/mm/memcontrol.c index b62b33a3cfec..5d9c8a3136bc 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -2055,6 +2055,15 @@ retry: current->flags & PF_EXITING)) goto force; + /* + * Prevent unbounded recursion when reclaim operations need to + * allocate memory. This might exceed the limits temporarily, + * but we prefer facilitating memory reclaim and getting back + * under the limit over triggering OOM kills in these cases. + */ + if (unlikely(current->flags & PF_MEMALLOC)) + goto force; + if (unlikely(task_in_memcg_oom(current))) goto nomem; @@ -4972,11 +4981,6 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) return ret; } -static int mem_cgroup_allow_attach(struct cgroup_taskset *tset) -{ - return subsys_cgroup_allow_attach(tset); -} - static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { if (mc.to) @@ -5131,10 +5135,6 @@ static int mem_cgroup_can_attach(struct cgroup_taskset *tset) { return 0; } -static int mem_cgroup_allow_attach(struct cgroup_taskset *tset) -{ - return 0; -} static void mem_cgroup_cancel_attach(struct cgroup_taskset *tset) { } @@ -5352,7 +5352,6 @@ struct cgroup_subsys memory_cgrp_subsys = { .css_reset = mem_cgroup_css_reset, .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, - .allow_attach = mem_cgroup_allow_attach, .post_attach = mem_cgroup_move_task, .bind = mem_cgroup_bind, .dfl_cftypes = memory_files, diff --git a/mm/page-writeback.c b/mm/page-writeback.c index 6b4fa64a5c91..15cb026ef807 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -278,7 +278,12 @@ static unsigned long zone_dirtyable_memory(struct zone *zone) unsigned long nr_pages; nr_pages = zone_page_state(zone, NR_FREE_PAGES); - nr_pages -= min(nr_pages, zone->dirty_balance_reserve); + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + nr_pages -= min(nr_pages, zone->totalreserve_pages); nr_pages += zone_page_state(zone, NR_INACTIVE_FILE); nr_pages += zone_page_state(zone, NR_ACTIVE_FILE); @@ -332,7 +337,12 @@ static unsigned long global_dirtyable_memory(void) unsigned long x; x = global_page_state(NR_FREE_PAGES); - x -= min(x, dirty_balance_reserve); + /* + * Pages reserved for the kernel should not be considered + * dirtyable, to prevent a situation where reclaim has to + * clean pages in order to balance the zones. + */ + x -= min(x, totalreserve_pages); x += global_page_state(NR_INACTIVE_FILE); x += global_page_state(NR_ACTIVE_FILE); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index af5901c65ba8..3048c5dbda16 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -114,13 +114,6 @@ static DEFINE_SPINLOCK(managed_page_count_lock); unsigned long totalram_pages __read_mostly; unsigned long totalreserve_pages __read_mostly; unsigned long totalcma_pages __read_mostly; -/* - * When calculating the number of globally allowed dirty pages, there - * is a certain number of per-zone reserves that should not be - * considered dirtyable memory. This is the sum of those reserves - * over all existing zones that contribute dirtyable memory. - */ -unsigned long dirty_balance_reserve __read_mostly; int percpu_pagelist_fraction; gfp_t gfp_allowed_mask __read_mostly = GFP_BOOT_MASK; @@ -6090,20 +6083,12 @@ static void calculate_totalreserve_pages(void) if (max > zone->managed_pages) max = zone->managed_pages; + + zone->totalreserve_pages = max; + reserve_pages += max; - /* - * Lowmem reserves are not available to - * GFP_HIGHUSER page cache allocations and - * kswapd tries to balance zones to their high - * watermark. As a result, neither should be - * regarded as dirtyable memory, to prevent a - * situation where reclaim has to clean pages - * in order to balance the zones. - */ - zone->dirty_balance_reserve = max; } } - dirty_balance_reserve = reserve_pages; totalreserve_pages = reserve_pages; } diff --git a/mm/swapfile.c b/mm/swapfile.c index 3ae1225084c9..45656508512b 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2268,6 +2268,8 @@ static unsigned long read_swap_header(struct swap_info_struct *p, swab32s(&swap_header->info.version); swab32s(&swap_header->info.last_page); swab32s(&swap_header->info.nr_badpages); + if (swap_header->info.nr_badpages > MAX_SWAP_BADPAGES) + return 0; for (i = 0; i < swap_header->info.nr_badpages; i++) swab32s(&swap_header->info.badpages[i]); } diff --git a/mm/usercopy.c b/mm/usercopy.c index 089328f2b920..b34996a3860b 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -15,6 +15,7 @@ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt #include <linux/mm.h> +#include <linux/sched.h> #include <linux/slab.h> #include <asm/sections.h> diff --git a/mm/vmscan.c b/mm/vmscan.c index 6801adacadb0..d82765ba44f4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2265,23 +2265,6 @@ out: } } -#ifdef CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH -static void init_tlb_ubc(void) -{ - /* - * This deliberately does not clear the cpumask as it's expensive - * and unnecessary. If there happens to be data in there then the - * first SWAP_CLUSTER_MAX pages will send an unnecessary IPI and - * then will be cleared. - */ - current->tlb_ubc.flush_required = false; -} -#else -static inline void init_tlb_ubc(void) -{ -} -#endif /* CONFIG_ARCH_WANT_BATCHED_UNMAP_TLB_FLUSH */ - /* * This is a basic per-zone page freer. Used by both kswapd and direct reclaim. */ @@ -2316,8 +2299,6 @@ static void shrink_lruvec(struct lruvec *lruvec, int swappiness, scan_adjusted = (global_reclaim(sc) && !current_is_kswapd() && sc->priority == DEF_PRIORITY); - init_tlb_ubc(); - blk_start_plug(&plug); while (nr[LRU_INACTIVE_ANON] || nr[LRU_ACTIVE_FILE] || nr[LRU_INACTIVE_FILE]) { @@ -3043,7 +3024,9 @@ unsigned long try_to_free_mem_cgroup_pages(struct mem_cgroup *memcg, sc.may_writepage, sc.gfp_mask); + current->flags |= PF_MEMALLOC; nr_reclaimed = do_try_to_free_pages(zonelist, &sc); + current->flags &= ~PF_MEMALLOC; trace_mm_vmscan_memcg_reclaim_end(nr_reclaimed); diff --git a/mm/workingset.c b/mm/workingset.c index aa017133744b..df66f426fdcf 100644 --- a/mm/workingset.c +++ b/mm/workingset.c @@ -341,21 +341,19 @@ static enum lru_status shadow_lru_isolate(struct list_head *item, * no pages, so we expect to be able to remove them all and * delete and free the empty node afterwards. */ - - BUG_ON(!node->count); - BUG_ON(node->count & RADIX_TREE_COUNT_MASK); + BUG_ON(!workingset_node_shadows(node)); + BUG_ON(workingset_node_pages(node)); for (i = 0; i < RADIX_TREE_MAP_SIZE; i++) { if (node->slots[i]) { BUG_ON(!radix_tree_exceptional_entry(node->slots[i])); node->slots[i] = NULL; - BUG_ON(node->count < (1U << RADIX_TREE_COUNT_SHIFT)); - node->count -= 1U << RADIX_TREE_COUNT_SHIFT; + workingset_node_shadows_dec(node); BUG_ON(!mapping->nrshadows); mapping->nrshadows--; } } - BUG_ON(node->count); + BUG_ON(workingset_node_shadows(node)); inc_zone_state(page_zone(virt_to_page(node)), WORKINGSET_NODERECLAIM); if (!__radix_tree_delete_node(&mapping->page_tree, node)) BUG(); |