diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/backing-dev.c | 4 | ||||
| -rw-r--r-- | mm/compaction.c | 7 | ||||
| -rw-r--r-- | mm/debug.c | 31 | ||||
| -rw-r--r-- | mm/filemap.c | 1 | ||||
| -rw-r--r-- | mm/gup.c | 14 | ||||
| -rw-r--r-- | mm/huge_memory.c | 9 | ||||
| -rw-r--r-- | mm/hugetlb.c | 5 | ||||
| -rw-r--r-- | mm/hugetlb_cgroup.c | 2 | ||||
| -rw-r--r-- | mm/init-mm.c | 1 | ||||
| -rw-r--r-- | mm/khugepaged.c | 35 | ||||
| -rw-r--r-- | mm/kmemleak.c | 30 | ||||
| -rw-r--r-- | mm/ksm.c | 14 | ||||
| -rw-r--r-- | mm/madvise.c | 16 | ||||
| -rw-r--r-- | mm/memblock.c | 6 | ||||
| -rw-r--r-- | mm/memcontrol.c | 48 | ||||
| -rw-r--r-- | mm/memory-failure.c | 36 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 133 | ||||
| -rw-r--r-- | mm/mempolicy.c | 14 | ||||
| -rw-r--r-- | mm/memremap.c | 13 | ||||
| -rw-r--r-- | mm/mmu_notifier.c | 2 | ||||
| -rw-r--r-- | mm/page_alloc.c | 31 | ||||
| -rw-r--r-- | mm/page_ext.c | 23 | ||||
| -rw-r--r-- | mm/page_io.c | 6 | ||||
| -rw-r--r-- | mm/page_owner.c | 60 | ||||
| -rw-r--r-- | mm/rmap.c | 1 | ||||
| -rw-r--r-- | mm/shmem.c | 6 | ||||
| -rw-r--r-- | mm/shuffle.c | 2 | ||||
| -rw-r--r-- | mm/slab.c | 3 | ||||
| -rw-r--r-- | mm/slab.h | 4 | ||||
| -rw-r--r-- | mm/slab_common.c | 28 | ||||
| -rw-r--r-- | mm/slob.c | 62 | ||||
| -rw-r--r-- | mm/slub.c | 88 | ||||
| -rw-r--r-- | mm/sparse.c | 2 | ||||
| -rw-r--r-- | mm/truncate.c | 12 | ||||
| -rw-r--r-- | mm/vmpressure.c | 20 | ||||
| -rw-r--r-- | mm/vmscan.c | 86 | ||||
| -rw-r--r-- | mm/vmstat.c | 25 | ||||
| -rw-r--r-- | mm/z3fold.c | 10 |
38 files changed, 546 insertions, 344 deletions
diff --git a/mm/backing-dev.c b/mm/backing-dev.c index d9daa3e422d0..c360f6a6c844 100644 --- a/mm/backing-dev.c +++ b/mm/backing-dev.c @@ -239,8 +239,8 @@ static int __init default_bdi_init(void) { int err; - bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_FREEZABLE | - WQ_UNBOUND | WQ_SYSFS, 0); + bdi_wq = alloc_workqueue("writeback", WQ_MEM_RECLAIM | WQ_UNBOUND | + WQ_SYSFS, 0); if (!bdi_wq) return -ENOMEM; diff --git a/mm/compaction.c b/mm/compaction.c index ce08b39d85d4..672d3c78c6ab 100644 --- a/mm/compaction.c +++ b/mm/compaction.c @@ -270,14 +270,15 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, /* Ensure the start of the pageblock or zone is online and valid */ block_pfn = pageblock_start_pfn(pfn); - block_page = pfn_to_online_page(max(block_pfn, zone->zone_start_pfn)); + block_pfn = max(block_pfn, zone->zone_start_pfn); + block_page = pfn_to_online_page(block_pfn); if (block_page) { page = block_page; pfn = block_pfn; } /* Ensure the end of the pageblock or zone is online and valid */ - block_pfn += pageblock_nr_pages; + block_pfn = pageblock_end_pfn(pfn) - 1; block_pfn = min(block_pfn, zone_end_pfn(zone) - 1); end_page = pfn_to_online_page(block_pfn); if (!end_page) @@ -303,7 +304,7 @@ __reset_isolation_pfn(struct zone *zone, unsigned long pfn, bool check_source, page += (1 << PAGE_ALLOC_COSTLY_ORDER); pfn += (1 << PAGE_ALLOC_COSTLY_ORDER); - } while (page < end_page); + } while (page <= end_page); return false; } diff --git a/mm/debug.c b/mm/debug.c index 8345bb6e4769..0461df1207cb 100644 --- a/mm/debug.c +++ b/mm/debug.c @@ -67,28 +67,31 @@ void __dump_page(struct page *page, const char *reason) */ mapcount = PageSlab(page) ? 0 : page_mapcount(page); - pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx", - page, page_ref_count(page), mapcount, - page->mapping, page_to_pgoff(page)); if (PageCompound(page)) - pr_cont(" compound_mapcount: %d", compound_mapcount(page)); - pr_cont("\n"); - if (PageAnon(page)) - pr_warn("anon "); - else if (PageKsm(page)) - pr_warn("ksm "); + pr_warn("page:%px refcount:%d mapcount:%d mapping:%px " + "index:%#lx compound_mapcount: %d\n", + page, page_ref_count(page), mapcount, + page->mapping, page_to_pgoff(page), + compound_mapcount(page)); + else + pr_warn("page:%px refcount:%d mapcount:%d mapping:%px index:%#lx\n", + page, page_ref_count(page), mapcount, + page->mapping, page_to_pgoff(page)); + if (PageKsm(page)) + pr_warn("ksm flags: %#lx(%pGp)\n", page->flags, &page->flags); + else if (PageAnon(page)) + pr_warn("anon flags: %#lx(%pGp)\n", page->flags, &page->flags); else if (mapping) { - pr_warn("%ps ", mapping->a_ops); if (mapping->host && mapping->host->i_dentry.first) { struct dentry *dentry; dentry = container_of(mapping->host->i_dentry.first, struct dentry, d_u.d_alias); - pr_warn("name:\"%pd\" ", dentry); - } + pr_warn("%ps name:\"%pd\"\n", mapping->a_ops, dentry); + } else + pr_warn("%ps\n", mapping->a_ops); + pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags); } BUILD_BUG_ON(ARRAY_SIZE(pageflag_names) != __NR_PAGEFLAGS + 1); - pr_warn("flags: %#lx(%pGp)\n", page->flags, &page->flags); - hex_only: print_hex_dump(KERN_WARNING, "raw: ", DUMP_PREFIX_NONE, 32, sizeof(unsigned long), page, diff --git a/mm/filemap.c b/mm/filemap.c index 1146fcfa3215..85b7d087eb45 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -40,6 +40,7 @@ #include <linux/rmap.h> #include <linux/delayacct.h> #include <linux/psi.h> +#include <linux/ramfs.h> #include "internal.h" #define CREATE_TRACE_POINTS @@ -1973,7 +1973,8 @@ static unsigned long hugepte_addr_end(unsigned long addr, unsigned long end, } static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, - unsigned long end, int write, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { unsigned long pte_end; struct page *head, *page; @@ -1986,7 +1987,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, pte = READ_ONCE(*ptep); - if (!pte_access_permitted(pte, write)) + if (!pte_access_permitted(pte, flags & FOLL_WRITE)) return 0; /* hugepages are never "special" */ @@ -2023,7 +2024,7 @@ static int gup_hugepte(pte_t *ptep, unsigned long sz, unsigned long addr, } static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned int pdshift, unsigned long end, int write, + unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { pte_t *ptep; @@ -2033,7 +2034,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, ptep = hugepte_offset(hugepd, addr, pdshift); do { next = hugepte_addr_end(addr, end, sz); - if (!gup_hugepte(ptep, sz, addr, end, write, pages, nr)) + if (!gup_hugepte(ptep, sz, addr, end, flags, pages, nr)) return 0; } while (ptep++, addr = next, addr != end); @@ -2041,7 +2042,7 @@ static int gup_huge_pd(hugepd_t hugepd, unsigned long addr, } #else static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, - unsigned pdshift, unsigned long end, int write, + unsigned int pdshift, unsigned long end, unsigned int flags, struct page **pages, int *nr) { return 0; @@ -2049,7 +2050,8 @@ static inline int gup_huge_pd(hugepd_t hugepd, unsigned long addr, #endif /* CONFIG_ARCH_HAS_HUGEPD */ static int gup_huge_pmd(pmd_t orig, pmd_t *pmdp, unsigned long addr, - unsigned long end, unsigned int flags, struct page **pages, int *nr) + unsigned long end, unsigned int flags, + struct page **pages, int *nr) { struct page *head, *page; int refs; diff --git a/mm/huge_memory.c b/mm/huge_memory.c index c5cb6dcd6c69..13cc93785006 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2789,8 +2789,13 @@ int split_huge_page_to_list(struct page *page, struct list_head *list) ds_queue->split_queue_len--; list_del(page_deferred_list(head)); } - if (mapping) - __dec_node_page_state(page, NR_SHMEM_THPS); + if (mapping) { + if (PageSwapBacked(page)) + __dec_node_page_state(page, NR_SHMEM_THPS); + else + __dec_node_page_state(page, NR_FILE_THPS); + } + spin_unlock(&ds_queue->split_queue_lock); __split_huge_page(page, list, end, flags); if (PageSwapCache(head)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ef37c85423a5..b45a95363a84 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1084,11 +1084,10 @@ static bool pfn_range_valid_gigantic(struct zone *z, struct page *page; for (i = start_pfn; i < end_pfn; i++) { - if (!pfn_valid(i)) + page = pfn_to_online_page(i); + if (!page) return false; - page = pfn_to_page(i); - if (page_zone(page) != z) return false; diff --git a/mm/hugetlb_cgroup.c b/mm/hugetlb_cgroup.c index f1930fa0b445..2ac38bdc18a1 100644 --- a/mm/hugetlb_cgroup.c +++ b/mm/hugetlb_cgroup.c @@ -196,7 +196,7 @@ int hugetlb_cgroup_charge_cgroup(int idx, unsigned long nr_pages, again: rcu_read_lock(); h_cg = hugetlb_cgroup_from_task(current); - if (!css_tryget_online(&h_cg->css)) { + if (!css_tryget(&h_cg->css)) { rcu_read_unlock(); goto again; } diff --git a/mm/init-mm.c b/mm/init-mm.c index fb1e15028ef0..19603302a77f 100644 --- a/mm/init-mm.c +++ b/mm/init-mm.c @@ -5,6 +5,7 @@ #include <linux/spinlock.h> #include <linux/list.h> #include <linux/cpumask.h> +#include <linux/mman.h> #include <linux/atomic.h> #include <linux/user_namespace.h> diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 0a1b4b484ac5..a8a57bebb5fa 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1028,12 +1028,13 @@ static void collapse_huge_page(struct mm_struct *mm, anon_vma_lock_write(vma->anon_vma); - pte = pte_offset_map(pmd, address); - pte_ptl = pte_lockptr(mm, pmd); - mmu_notifier_range_init(&range, MMU_NOTIFY_CLEAR, 0, NULL, mm, address, address + HPAGE_PMD_SIZE); mmu_notifier_invalidate_range_start(&range); + + pte = pte_offset_map(pmd, address); + pte_ptl = pte_lockptr(mm, pmd); + pmd_ptl = pmd_lock(mm, pmd); /* probably unnecessary */ /* * After this gup_fast can't run anymore. This also removes @@ -1601,17 +1602,6 @@ static void collapse_file(struct mm_struct *mm, result = SCAN_FAIL; goto xa_unlocked; } - } else if (!PageUptodate(page)) { - xas_unlock_irq(&xas); - wait_on_page_locked(page); - if (!trylock_page(page)) { - result = SCAN_PAGE_LOCK; - goto xa_unlocked; - } - get_page(page); - } else if (PageDirty(page)) { - result = SCAN_FAIL; - goto xa_locked; } else if (trylock_page(page)) { get_page(page); xas_unlock_irq(&xas); @@ -1626,7 +1616,12 @@ static void collapse_file(struct mm_struct *mm, * without racing with truncate. */ VM_BUG_ON_PAGE(!PageLocked(page), page); - VM_BUG_ON_PAGE(!PageUptodate(page), page); + + /* make sure the page is up to date */ + if (unlikely(!PageUptodate(page))) { + result = SCAN_FAIL; + goto out_unlock; + } /* * If file was truncated then extended, or hole-punched, before @@ -1642,6 +1637,16 @@ static void collapse_file(struct mm_struct *mm, goto out_unlock; } + if (!is_shmem && PageDirty(page)) { + /* + * khugepaged only works on read-only fd, so this + * page is dirty because it hasn't been flushed + * since first write. + */ + result = SCAN_FAIL; + goto out_unlock; + } + if (isolate_lru_page(page)) { result = SCAN_DEL_PAGE_LRU; goto out_unlock; diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 03a8d84badad..244607663363 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -527,6 +527,16 @@ static struct kmemleak_object *find_and_get_object(unsigned long ptr, int alias) } /* + * Remove an object from the object_tree_root and object_list. Must be called + * with the kmemleak_lock held _if_ kmemleak is still enabled. + */ +static void __remove_object(struct kmemleak_object *object) +{ + rb_erase(&object->rb_node, &object_tree_root); + list_del_rcu(&object->object_list); +} + +/* * Look up an object in the object search tree and remove it from both * object_tree_root and object_list. The returned object's use_count should be * at least 1, as initially set by create_object(). @@ -538,10 +548,8 @@ static struct kmemleak_object *find_and_remove_object(unsigned long ptr, int ali write_lock_irqsave(&kmemleak_lock, flags); object = lookup_object(ptr, alias); - if (object) { - rb_erase(&object->rb_node, &object_tree_root); - list_del_rcu(&object->object_list); - } + if (object) + __remove_object(object); write_unlock_irqrestore(&kmemleak_lock, flags); return object; @@ -1834,12 +1842,16 @@ static const struct file_operations kmemleak_fops = { static void __kmemleak_do_cleanup(void) { - struct kmemleak_object *object; + struct kmemleak_object *object, *tmp; - rcu_read_lock(); - list_for_each_entry_rcu(object, &object_list, object_list) - delete_object_full(object->pointer); - rcu_read_unlock(); + /* + * Kmemleak has already been disabled, no need for RCU list traversal + * or kmemleak_lock held. + */ + list_for_each_entry_safe(object, tmp, &object_list, object_list) { + __remove_object(object); + __delete_object(object); + } } /* @@ -885,13 +885,13 @@ static int remove_stable_node(struct stable_node *stable_node) return 0; } - if (WARN_ON_ONCE(page_mapped(page))) { - /* - * This should not happen: but if it does, just refuse to let - * merge_across_nodes be switched - there is no need to panic. - */ - err = -EBUSY; - } else { + /* + * Page could be still mapped if this races with __mmput() running in + * between ksm_exit() and exit_mmap(). Just refuse to let + * merge_across_nodes/max_page_sharing be switched. + */ + err = -EBUSY; + if (!page_mapped(page)) { /* * The stable node did not yet appear stale to get_ksm_page(), * since that allows for an unmapped ksm page to be recognized diff --git a/mm/madvise.c b/mm/madvise.c index 2be9f3fdb05e..94c343b4c968 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -363,8 +363,12 @@ static int madvise_cold_or_pageout_pte_range(pmd_t *pmd, ClearPageReferenced(page); test_and_clear_page_young(page); if (pageout) { - if (!isolate_lru_page(page)) - list_add(&page->lru, &page_list); + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } } else deactivate_page(page); huge_unlock: @@ -441,8 +445,12 @@ regular_page: ClearPageReferenced(page); test_and_clear_page_young(page); if (pageout) { - if (!isolate_lru_page(page)) - list_add(&page->lru, &page_list); + if (!isolate_lru_page(page)) { + if (PageUnevictable(page)) + putback_lru_page(page); + else + list_add(&page->lru, &page_list); + } } else deactivate_page(page); } diff --git a/mm/memblock.c b/mm/memblock.c index 7d4f61ae666a..c4b16cae2bc9 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -1356,9 +1356,6 @@ static phys_addr_t __init memblock_alloc_range_nid(phys_addr_t size, align = SMP_CACHE_BYTES; } - if (end > memblock.current_limit) - end = memblock.current_limit; - again: found = memblock_find_in_range_node(size, align, start, end, nid, flags); @@ -1469,6 +1466,9 @@ static void * __init memblock_alloc_internal( if (WARN_ON_ONCE(slab_is_available())) return kzalloc_node(size, GFP_NOWAIT, nid); + if (max_addr > memblock.current_limit) + max_addr = memblock.current_limit; + alloc = memblock_alloc_range_nid(size, align, min_addr, max_addr, nid); /* retry allocation without lower limit */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index c313c49074ca..46ad252e6d6a 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -484,7 +484,7 @@ ino_t page_cgroup_ino(struct page *page) unsigned long ino = 0; rcu_read_lock(); - if (PageHead(page) && PageSlab(page)) + if (PageSlab(page) && !PageTail(page)) memcg = memcg_from_slab_page(page); else memcg = READ_ONCE(page->mem_cgroup); @@ -960,7 +960,7 @@ struct mem_cgroup *get_mem_cgroup_from_mm(struct mm_struct *mm) if (unlikely(!memcg)) memcg = root_mem_cgroup; } - } while (!css_tryget_online(&memcg->css)); + } while (!css_tryget(&memcg->css)); rcu_read_unlock(); return memcg; } @@ -1567,6 +1567,11 @@ unsigned long mem_cgroup_get_max(struct mem_cgroup *memcg) return max; } +unsigned long mem_cgroup_size(struct mem_cgroup *memcg) +{ + return page_counter_read(&memcg->memory); +} + static bool mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, int order) { @@ -2530,6 +2535,15 @@ retry: } /* + * Memcg doesn't have a dedicated reserve for atomic + * allocations. But like the global atomic pool, we need to + * put the burden of reclaim on regular allocation requests + * and let these go through as privileged allocations. + */ + if (gfp_mask & __GFP_ATOMIC) + goto force; + + /* * Unlike in global OOM situations, memcg is not in a physical * memory shortage. Allow dying and OOM-killed tasks to * bypass the last charges so that they can exit quickly and @@ -5009,12 +5023,6 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) { int node; - /* - * Flush percpu vmstats and vmevents to guarantee the value correctness - * on parent's and all ancestor levels. - */ - memcg_flush_percpu_vmstats(memcg, false); - memcg_flush_percpu_vmevents(memcg); for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->vmstats_percpu); @@ -5025,6 +5033,12 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) static void mem_cgroup_free(struct mem_cgroup *memcg) { memcg_wb_domain_exit(memcg); + /* + * Flush percpu vmstats and vmevents to guarantee the value correctness + * on parent's and all ancestor levels. + */ + memcg_flush_percpu_vmstats(memcg, false); + memcg_flush_percpu_vmevents(memcg); __mem_cgroup_free(memcg); } @@ -5415,6 +5429,8 @@ static int mem_cgroup_move_account(struct page *page, struct mem_cgroup *from, struct mem_cgroup *to) { + struct lruvec *from_vec, *to_vec; + struct pglist_data *pgdat; unsigned long flags; unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret; @@ -5438,11 +5454,15 @@ static int mem_cgroup_move_account(struct page *page, anon = PageAnon(page); + pgdat = page_pgdat(page); + from_vec = mem_cgroup_lruvec(pgdat, from); + to_vec = mem_cgroup_lruvec(pgdat, to); + spin_lock_irqsave(&from->move_lock, flags); if (!anon && page_mapped(page)) { - __mod_memcg_state(from, NR_FILE_MAPPED, -nr_pages); - __mod_memcg_state(to, NR_FILE_MAPPED, nr_pages); + __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); } /* @@ -5454,14 +5474,14 @@ static int mem_cgroup_move_account(struct page *page, struct address_space *mapping = page_mapping(page); if (mapping_cap_account_dirty(mapping)) { - __mod_memcg_state(from, NR_FILE_DIRTY, -nr_pages); - __mod_memcg_state(to, NR_FILE_DIRTY, nr_pages); + __mod_lruvec_state(from_vec, NR_FILE_DIRTY, -nr_pages); + __mod_lruvec_state(to_vec, NR_FILE_DIRTY, nr_pages); } } if (PageWriteback(page)) { - __mod_memcg_state(from, NR_WRITEBACK, -nr_pages); - __mod_memcg_state(to, NR_WRITEBACK, nr_pages); + __mod_lruvec_state(from_vec, NR_WRITEBACK, -nr_pages); + __mod_lruvec_state(to_vec, NR_WRITEBACK, nr_pages); } #ifdef CONFIG_TRANSPARENT_HUGEPAGE diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 7ef849da8278..3151c87dff73 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -199,7 +199,6 @@ struct to_kill { struct task_struct *tsk; unsigned long addr; short size_shift; - char addr_valid; }; /* @@ -324,22 +323,27 @@ static void add_to_kill(struct task_struct *tsk, struct page *p, } } tk->addr = page_address_in_vma(p, vma); - tk->addr_valid = 1; if (is_zone_device_page(p)) tk->size_shift = dev_pagemap_mapping_shift(p, vma); else tk->size_shift = compound_order(compound_head(p)) + PAGE_SHIFT; /* - * In theory we don't have to kill when the page was - * munmaped. But it could be also a mremap. Since that's - * likely very rare kill anyways just out of paranoia, but use - * a SIGKILL because the error is not contained anymore. + * Send SIGKILL if "tk->addr == -EFAULT". Also, as + * "tk->size_shift" is always non-zero for !is_zone_device_page(), + * so "tk->size_shift == 0" effectively checks no mapping on + * ZONE_DEVICE. Indeed, when a devdax page is mmapped N times + * to a process' address space, it's possible not all N VMAs + * contain mappings for the page, but at least one VMA does. + * Only deliver SIGBUS with payload derived from the VMA that + * has a mapping for the page. */ - if (tk->addr == -EFAULT || tk->size_shift == 0) { + if (tk->addr == -EFAULT) { pr_info("Memory failure: Unable to find user space address %lx in %s\n", page_to_pfn(p), tsk->comm); - tk->addr_valid = 0; + } else if (tk->size_shift == 0) { + kfree(tk); + return; } get_task_struct(tsk); tk->tsk = tsk; @@ -366,7 +370,7 @@ static void kill_procs(struct list_head *to_kill, int forcekill, bool fail, * make sure the process doesn't catch the * signal and then access the memory. Just kill it. */ - if (fail || tk->addr_valid == 0) { + if (fail || tk->addr == -EFAULT) { pr_err("Memory failure: %#lx: forcibly killing %s:%d because of failure to unmap corrupted page\n", pfn, tk->tsk->comm, tk->tsk->pid); do_send_sig_info(SIGKILL, SEND_SIG_PRIV, @@ -1253,17 +1257,19 @@ int memory_failure(unsigned long pfn, int flags) if (!sysctl_memory_failure_recovery) panic("Memory failure on page %lx", pfn); - if (!pfn_valid(pfn)) { + p = pfn_to_online_page(pfn); + if (!p) { + if (pfn_valid(pfn)) { + pgmap = get_dev_pagemap(pfn, NULL); + if (pgmap) + return memory_failure_dev_pagemap(pfn, flags, + pgmap); + } pr_err("Memory failure: %#lx: memory outside kernel control\n", pfn); return -ENXIO; } - pgmap = get_dev_pagemap(pfn, NULL); - if (pgmap) - return memory_failure_dev_pagemap(pfn, flags, pgmap); - - p = pfn_to_page(pfn); if (PageHuge(p)) return memory_failure_hugetlb(pfn, flags); if (TestSetPageHWPoison(p)) { diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index b1be791f772d..f307bd82d750 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -331,7 +331,7 @@ static unsigned long find_smallest_section_pfn(int nid, struct zone *zone, unsigned long end_pfn) { for (; start_pfn < end_pfn; start_pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(start_pfn))) + if (unlikely(!pfn_to_online_page(start_pfn))) continue; if (unlikely(pfn_to_nid(start_pfn) != nid)) @@ -356,7 +356,7 @@ static unsigned long find_biggest_section_pfn(int nid, struct zone *zone, /* pfn is the end pfn of a memory section. */ pfn = end_pfn - 1; for (; pfn >= start_pfn; pfn -= PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (unlikely(pfn_to_nid(pfn) != nid)) @@ -415,7 +415,7 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, */ pfn = zone_start_pfn; for (; pfn < zone_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) + if (unlikely(!pfn_to_online_page(pfn))) continue; if (page_zone(pfn_to_page(pfn)) != zone) @@ -436,67 +436,33 @@ static void shrink_zone_span(struct zone *zone, unsigned long start_pfn, zone_span_writeunlock(zone); } -static void shrink_pgdat_span(struct pglist_data *pgdat, - unsigned long start_pfn, unsigned long end_pfn) +static void update_pgdat_span(struct pglist_data *pgdat) { - unsigned long pgdat_start_pfn = pgdat->node_start_pfn; - unsigned long p = pgdat_end_pfn(pgdat); /* pgdat_end_pfn namespace clash */ - unsigned long pgdat_end_pfn = p; - unsigned long pfn; - int nid = pgdat->node_id; - - if (pgdat_start_pfn == start_pfn) { - /* - * If the section is smallest section in the pgdat, it need - * shrink pgdat->node_start_pfn and pgdat->node_spanned_pages. - * In this case, we find second smallest valid mem_section - * for shrinking zone. - */ - pfn = find_smallest_section_pfn(nid, NULL, end_pfn, - pgdat_end_pfn); - if (pfn) { - pgdat->node_start_pfn = pfn; - pgdat->node_spanned_pages = pgdat_end_pfn - pfn; - } - } else if (pgdat_end_pfn == end_pfn) { - /* - * If the section is biggest section in the pgdat, it need - * shrink pgdat->node_spanned_pages. - * In this case, we find second biggest valid mem_section for - * shrinking zone. - */ - pfn = find_biggest_section_pfn(nid, NULL, pgdat_start_pfn, - start_pfn); - if (pfn) - pgdat->node_spanned_pages = pfn - pgdat_start_pfn + 1; - } + unsigned long node_start_pfn = 0, node_end_pfn = 0; + struct zone *zone; - /* - * If the section is not biggest or smallest mem_section in the pgdat, - * it only creates a hole in the pgdat. So in this case, we need not - * change the pgdat. - * But perhaps, the pgdat has only hole data. Thus it check the pgdat - * has only hole or not. - */ - pfn = pgdat_start_pfn; - for (; pfn < pgdat_end_pfn; pfn += PAGES_PER_SUBSECTION) { - if (unlikely(!pfn_valid(pfn))) - continue; + for (zone = pgdat->node_zones; + zone < pgdat->node_zones + MAX_NR_ZONES; zone++) { + unsigned long zone_end_pfn = zone->zone_start_pfn + + zone->spanned_pages; - if (pfn_to_nid(pfn) != nid) + /* No need to lock the zones, they can't change. */ + if (!zone->spanned_pages) continue; - - /* Skip range to be removed */ - if (pfn >= start_pfn && pfn < end_pfn) + if (!node_end_pfn) { + node_start_pfn = zone->zone_start_pfn; + node_end_pfn = zone_end_pfn; continue; + } - /* If we find valid section, we have nothing to do */ - return; + if (zone_end_pfn > node_end_pfn) + node_end_pfn = zone_end_pfn; + if (zone->zone_start_pfn < node_start_pfn) + node_start_pfn = zone->zone_start_pfn; } - /* The pgdat has no valid section */ - pgdat->node_start_pfn = 0; - pgdat->node_spanned_pages = 0; + pgdat->node_start_pfn = node_start_pfn; + pgdat->node_spanned_pages = node_end_pfn - node_start_pfn; } static void __remove_zone(struct zone *zone, unsigned long start_pfn, @@ -505,9 +471,19 @@ static void __remove_zone(struct zone *zone, unsigned long start_pfn, struct pglist_data *pgdat = zone->zone_pgdat; unsigned long flags; +#ifdef CONFIG_ZONE_DEVICE + /* + * Zone shrinking code cannot properly deal with ZONE_DEVICE. So + * we will not try to shrink the zones - which is okay as + * set_zone_contiguous() cannot deal with ZONE_DEVICE either way. + */ + if (zone_idx(zone) == ZONE_DEVICE) + return; +#endif + pgdat_resize_lock(zone->zone_pgdat, &flags); shrink_zone_span(zone, start_pfn, start_pfn + nr_pages); - shrink_pgdat_span(pgdat, start_pfn, start_pfn + nr_pages); + update_pgdat_span(pgdat); pgdat_resize_unlock(zone->zone_pgdat, &flags); } @@ -1680,6 +1656,18 @@ static int check_cpu_on_node(pg_data_t *pgdat) return 0; } +static int check_no_memblock_for_node_cb(struct memory_block *mem, void *arg) +{ + int nid = *(int *)arg; + + /* + * If a memory block belongs to multiple nodes, the stored nid is not + * reliable. However, such blocks are always online (e.g., cannot get + * offlined) and, therefore, are still spanned by the node. + */ + return mem->nid == nid ? -EEXIST : 0; +} + /** * try_offline_node * @nid: the node ID @@ -1692,25 +1680,24 @@ static int check_cpu_on_node(pg_data_t *pgdat) void try_offline_node(int nid) { pg_data_t *pgdat = NODE_DATA(nid); - unsigned long start_pfn = pgdat->node_start_pfn; - unsigned long end_pfn = start_pfn + pgdat->node_spanned_pages; - unsigned long pfn; - - for (pfn = start_pfn; pfn < end_pfn; pfn += PAGES_PER_SECTION) { - unsigned long section_nr = pfn_to_section_nr(pfn); - - if (!present_section_nr(section_nr)) - continue; + int rc; - if (pfn_to_nid(pfn) != nid) - continue; + /* + * If the node still spans pages (especially ZONE_DEVICE), don't + * offline it. A node spans memory after move_pfn_range_to_zone(), + * e.g., after the memory block was onlined. + */ + if (pgdat->node_spanned_pages) + return; - /* - * some memory sections of this node are not removed, and we - * can't offline node now. - */ + /* + * Especially offline memory blocks might not be spanned by the + * node. They will get spanned by the node once they get onlined. + * However, they link to the node in sysfs and can get onlined later. + */ + rc = for_each_memory_block(&nid, check_no_memblock_for_node_cb); + if (rc) return; - } if (check_cpu_on_node(pgdat)) return; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 4ae967bcf954..e08c94170ae4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -672,7 +672,9 @@ static const struct mm_walk_ops queue_pages_walk_ops = { * 1 - there is unmovable page, but MPOL_MF_MOVE* & MPOL_MF_STRICT were * specified. * 0 - queue pages successfully or no misplaced page. - * -EIO - there is misplaced page and only MPOL_MF_STRICT was specified. + * errno - i.e. misplaced pages with MPOL_MF_STRICT specified (-EIO) or + * memory range specified by nodemask and maxnode points outside + * your accessible address space (-EFAULT) */ static int queue_pages_range(struct mm_struct *mm, unsigned long start, unsigned long end, @@ -1286,7 +1288,7 @@ static long do_mbind(unsigned long start, unsigned long len, flags | MPOL_MF_INVERT, &pagelist); if (ret < 0) { - err = -EIO; + err = ret; goto up_out; } @@ -1305,10 +1307,12 @@ static long do_mbind(unsigned long start, unsigned long len, if ((ret > 0) || (nr_failed && (flags & MPOL_MF_STRICT))) err = -EIO; - } else - putback_movable_pages(&pagelist); - + } else { up_out: + if (!list_empty(&pagelist)) + putback_movable_pages(&pagelist); + } + up_write(&mm->mmap_sem); mpol_out: mpol_put(new); diff --git a/mm/memremap.c b/mm/memremap.c index 32c79b51af86..03ccbdfeb697 100644 --- a/mm/memremap.c +++ b/mm/memremap.c @@ -13,8 +13,6 @@ #include <linux/xarray.h> static DEFINE_XARRAY(pgmap_array); -#define SECTION_MASK ~((1UL << PA_SECTION_SHIFT) - 1) -#define SECTION_SIZE (1UL << PA_SECTION_SHIFT) #ifdef CONFIG_DEV_PAGEMAP_OPS DEFINE_STATIC_KEY_FALSE(devmap_managed_key); @@ -105,6 +103,7 @@ static void dev_pagemap_cleanup(struct dev_pagemap *pgmap) void memunmap_pages(struct dev_pagemap *pgmap) { struct resource *res = &pgmap->res; + struct page *first_page; unsigned long pfn; int nid; @@ -113,14 +112,16 @@ void memunmap_pages(struct dev_pagemap *pgmap) put_page(pfn_to_page(pfn)); dev_pagemap_cleanup(pgmap); + /* make sure to access a memmap that was actually initialized */ + first_page = pfn_to_page(pfn_first(pgmap)); + /* pages are dead and unused, undo the arch mapping */ - nid = page_to_nid(pfn_to_page(PHYS_PFN(res->start))); + nid = page_to_nid(first_page); mem_hotplug_begin(); if (pgmap->type == MEMORY_DEVICE_PRIVATE) { - pfn = PHYS_PFN(res->start); - __remove_pages(page_zone(pfn_to_page(pfn)), pfn, - PHYS_PFN(resource_size(res)), NULL); + __remove_pages(page_zone(first_page), PHYS_PFN(res->start), + PHYS_PFN(resource_size(res)), NULL); } else { arch_remove_memory(nid, res->start, resource_size(res), pgmap_altmap(pgmap)); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index 7fde88695f35..9a889e456168 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -180,7 +180,7 @@ int __mmu_notifier_invalidate_range_start(struct mmu_notifier_range *range) mn->ops->invalidate_range_start, _ret, !mmu_notifier_range_blockable(range) ? "non-" : ""); WARN_ON(mmu_notifier_range_blockable(range) || - ret != -EAGAIN); + _ret != -EAGAIN); ret = _ret; } } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 15c2050c629b..f391c0c4ed1d 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1175,11 +1175,17 @@ static __always_inline bool free_pages_prepare(struct page *page, debug_check_no_obj_freed(page_address(page), PAGE_SIZE << order); } - arch_free_page(page, order); if (want_init_on_free()) kernel_init_free_pages(page, 1 << order); kernel_poison_pages(page, 1 << order, 0); + /* + * arch_free_page() can make the page's contents inaccessible. s390 + * does this. So nothing which can access the page's contents should + * happen after this. + */ + arch_free_page(page, order); + if (debug_pagealloc_enabled()) kernel_map_pages(page, 1 << order, 0); @@ -1942,6 +1948,14 @@ void __init page_alloc_init_late(void) wait_for_completion(&pgdat_init_all_done_comp); /* + * The number of managed pages has changed due to the initialisation + * so the pcpu batch and high limits needs to be updated or the limits + * will be artificially small. + */ + for_each_populated_zone(zone) + zone_pcp_update(zone); + + /* * We initialized the rest of the deferred pages. Permanently disable * on-demand struct page initialization. */ @@ -3714,10 +3728,6 @@ try_this_zone: static void warn_alloc_show_mem(gfp_t gfp_mask, nodemask_t *nodemask) { unsigned int filter = SHOW_MEM_FILTER_NODES; - static DEFINE_RATELIMIT_STATE(show_mem_rs, HZ, 1); - - if (!__ratelimit(&show_mem_rs)) - return; /* * This documents exceptions given to allocations in certain @@ -3738,8 +3748,7 @@ void warn_alloc(gfp_t gfp_mask, nodemask_t *nodemask, const char *fmt, ...) { struct va_format vaf; va_list args; - static DEFINE_RATELIMIT_STATE(nopage_rs, DEFAULT_RATELIMIT_INTERVAL, - DEFAULT_RATELIMIT_BURST); + static DEFINE_RATELIMIT_STATE(nopage_rs, 10*HZ, 1); if ((gfp_mask & __GFP_NOWARN) || !__ratelimit(&nopage_rs)) return; @@ -4467,12 +4476,14 @@ retry_cpuset: if (page) goto got_pg; - if (order >= pageblock_order && (gfp_mask & __GFP_IO)) { + if (order >= pageblock_order && (gfp_mask & __GFP_IO) && + !(gfp_mask & __GFP_RETRY_MAYFAIL)) { /* * If allocating entire pageblock(s) and compaction * failed because all zones are below low watermarks * or is prohibited because it recently failed at this - * order, fail immediately. + * order, fail immediately unless the allocator has + * requested compaction and reclaim retry. * * Reclaim is * - potentially very expensive because zones are far @@ -8506,7 +8517,6 @@ void free_contig_range(unsigned long pfn, unsigned int nr_pages) WARN(count != 0, "%d pages are still in use!\n", count); } -#ifdef CONFIG_MEMORY_HOTPLUG /* * The zone indicated has a new number of managed_pages; batch sizes and percpu * page high values need to be recalulated. @@ -8520,7 +8530,6 @@ void __meminit zone_pcp_update(struct zone *zone) per_cpu_ptr(zone->pageset, cpu)); mutex_unlock(&pcp_batch_high_lock); } -#endif void zone_pcp_reset(struct zone *zone) { diff --git a/mm/page_ext.c b/mm/page_ext.c index 5f5769c7db3b..4ade843ff588 100644 --- a/mm/page_ext.c +++ b/mm/page_ext.c @@ -67,8 +67,9 @@ static struct page_ext_operations *page_ext_ops[] = { #endif }; +unsigned long page_ext_size = sizeof(struct page_ext); + static unsigned long total_usage; -static unsigned long extra_mem; static bool __init invoke_need_callbacks(void) { @@ -78,9 +79,8 @@ static bool __init invoke_need_callbacks(void) for (i = 0; i < entries; i++) { if (page_ext_ops[i]->need && page_ext_ops[i]->need()) { - page_ext_ops[i]->offset = sizeof(struct page_ext) + - extra_mem; - extra_mem += page_ext_ops[i]->size; + page_ext_ops[i]->offset = page_ext_size; + page_ext_size += page_ext_ops[i]->size; need = true; } } @@ -99,14 +99,9 @@ static void __init invoke_init_callbacks(void) } } -static unsigned long get_entry_size(void) -{ - return sizeof(struct page_ext) + extra_mem; -} - static inline struct page_ext *get_entry(void *base, unsigned long index) { - return base + get_entry_size() * index; + return base + page_ext_size * index; } #if !defined(CONFIG_SPARSEMEM) @@ -156,7 +151,7 @@ static int __init alloc_node_page_ext(int nid) !IS_ALIGNED(node_end_pfn(nid), MAX_ORDER_NR_PAGES)) nr_pages += MAX_ORDER_NR_PAGES; - table_size = get_entry_size() * nr_pages; + table_size = page_ext_size * nr_pages; base = memblock_alloc_try_nid( table_size, PAGE_SIZE, __pa(MAX_DMA_ADDRESS), @@ -234,7 +229,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) if (section->page_ext) return 0; - table_size = get_entry_size() * PAGES_PER_SECTION; + table_size = page_ext_size * PAGES_PER_SECTION; base = alloc_page_ext(table_size, nid); /* @@ -254,7 +249,7 @@ static int __meminit init_section_page_ext(unsigned long pfn, int nid) * we need to apply a mask. */ pfn &= PAGE_SECTION_MASK; - section->page_ext = (void *)base - get_entry_size() * pfn; + section->page_ext = (void *)base - page_ext_size * pfn; total_usage += table_size; return 0; } @@ -267,7 +262,7 @@ static void free_page_ext(void *addr) struct page *page = virt_to_page(addr); size_t table_size; - table_size = get_entry_size() * PAGES_PER_SECTION; + table_size = page_ext_size * PAGES_PER_SECTION; BUG_ON(PageReserved(page)); kmemleak_free(addr); diff --git a/mm/page_io.c b/mm/page_io.c index 24ee600f9131..60a66a58b9bf 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -73,6 +73,7 @@ static void swap_slot_free_notify(struct page *page) { struct swap_info_struct *sis; struct gendisk *disk; + swp_entry_t entry; /* * There is no guarantee that the page is in swap cache - the software @@ -104,11 +105,10 @@ static void swap_slot_free_notify(struct page *page) * we again wish to reclaim it. */ disk = sis->bdev->bd_disk; - if (disk->fops->swap_slot_free_notify) { - swp_entry_t entry; + entry.val = page_private(page); + if (disk->fops->swap_slot_free_notify && __swap_count(entry) == 1) { unsigned long offset; - entry.val = page_private(page); offset = swp_offset(entry); SetPageDirty(page); diff --git a/mm/page_owner.c b/mm/page_owner.c index dee931184788..18ecde9f45b2 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -24,12 +24,10 @@ struct page_owner { short last_migrate_reason; gfp_t gfp_mask; depot_stack_handle_t handle; -#ifdef CONFIG_DEBUG_PAGEALLOC depot_stack_handle_t free_handle; -#endif }; -static bool page_owner_disabled = true; +static bool page_owner_enabled = false; DEFINE_STATIC_KEY_FALSE(page_owner_inited); static depot_stack_handle_t dummy_handle; @@ -44,7 +42,7 @@ static int __init early_page_owner_param(char *buf) return -EINVAL; if (strcmp(buf, "on") == 0) - page_owner_disabled = false; + page_owner_enabled = true; return 0; } @@ -52,10 +50,7 @@ early_param("page_owner", early_page_owner_param); static bool need_page_owner(void) { - if (page_owner_disabled) - return false; - - return true; + return page_owner_enabled; } static __always_inline depot_stack_handle_t create_dummy_stack(void) @@ -84,7 +79,7 @@ static noinline void register_early_stack(void) static void init_page_owner(void) { - if (page_owner_disabled) + if (!page_owner_enabled) return; register_dummy_stack(); @@ -148,25 +143,19 @@ void __reset_page_owner(struct page *page, unsigned int order) { int i; struct page_ext *page_ext; -#ifdef CONFIG_DEBUG_PAGEALLOC depot_stack_handle_t handle = 0; struct page_owner *page_owner; - if (debug_pagealloc_enabled()) - handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); -#endif + handle = save_stack(GFP_NOWAIT | __GFP_NOWARN); + page_ext = lookup_page_ext(page); + if (unlikely(!page_ext)) + return; for (i = 0; i < (1 << order); i++) { - page_ext = lookup_page_ext(page + i); - if (unlikely(!page_ext)) - continue; - __clear_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags); -#ifdef CONFIG_DEBUG_PAGEALLOC - if (debug_pagealloc_enabled()) { - page_owner = get_page_owner(page_ext); - page_owner->free_handle = handle; - } -#endif + __clear_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); + page_owner = get_page_owner(page_ext); + page_owner->free_handle = handle; + page_ext = page_ext_next(page_ext); } } @@ -184,9 +173,9 @@ static inline void __set_page_owner_handle(struct page *page, page_owner->gfp_mask = gfp_mask; page_owner->last_migrate_reason = -1; __set_bit(PAGE_EXT_OWNER, &page_ext->flags); - __set_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags); - page_ext = lookup_page_ext(page + i); + page_ext = page_ext_next(page_ext); } } @@ -224,12 +213,10 @@ void __split_page_owner(struct page *page, unsigned int order) if (unlikely(!page_ext)) return; - page_owner = get_page_owner(page_ext); - page_owner->order = 0; - for (i = 1; i < (1 << order); i++) { - page_ext = lookup_page_ext(page + i); + for (i = 0; i < (1 << order); i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; + page_ext = page_ext_next(page_ext); } } @@ -260,7 +247,7 @@ void __copy_page_owner(struct page *oldpage, struct page *newpage) * the new page, which will be freed. */ __set_bit(PAGE_EXT_OWNER, &new_ext->flags); - __set_bit(PAGE_EXT_OWNER_ACTIVE, &new_ext->flags); + __set_bit(PAGE_EXT_OWNER_ALLOCATED, &new_ext->flags); } void pagetypeinfo_showmixedcount_print(struct seq_file *m, @@ -284,7 +271,8 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, * not matter as the mixed block count will still be correct */ for (; pfn < end_pfn; ) { - if (!pfn_valid(pfn)) { + page = pfn_to_online_page(pfn); + if (!page) { pfn = ALIGN(pfn + 1, MAX_ORDER_NR_PAGES); continue; } @@ -292,13 +280,13 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, block_end_pfn = ALIGN(pfn + 1, pageblock_nr_pages); block_end_pfn = min(block_end_pfn, end_pfn); - page = pfn_to_page(pfn); pageblock_mt = get_pageblock_migratetype(page); for (; pfn < block_end_pfn; pfn++) { if (!pfn_valid_within(pfn)) continue; + /* The pageblock is online, no need to recheck. */ page = pfn_to_page(pfn); if (page_zone(page) != zone) @@ -320,7 +308,7 @@ void pagetypeinfo_showmixedcount_print(struct seq_file *m, if (unlikely(!page_ext)) continue; - if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); @@ -435,7 +423,7 @@ void __dump_page_owner(struct page *page) return; } - if (test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) pr_alert("page_owner tracks the page as allocated\n"); else pr_alert("page_owner tracks the page as freed\n"); @@ -451,7 +439,6 @@ void __dump_page_owner(struct page *page) stack_trace_print(entries, nr_entries, 0); } -#ifdef CONFIG_DEBUG_PAGEALLOC handle = READ_ONCE(page_owner->free_handle); if (!handle) { pr_alert("page_owner free stack trace missing\n"); @@ -460,7 +447,6 @@ void __dump_page_owner(struct page *page) pr_alert("page last free stack trace:\n"); stack_trace_print(entries, nr_entries, 0); } -#endif if (page_owner->last_migrate_reason != -1) pr_alert("page has been migrated, last migrate reason: %s\n", @@ -527,7 +513,7 @@ read_page_owner(struct file *file, char __user *buf, size_t count, loff_t *ppos) * Although we do have the info about past allocation of free * pages, it's not relevant for current memory usage. */ - if (!test_bit(PAGE_EXT_OWNER_ACTIVE, &page_ext->flags)) + if (!test_bit(PAGE_EXT_OWNER_ALLOCATED, &page_ext->flags)) continue; page_owner = get_page_owner(page_ext); diff --git a/mm/rmap.c b/mm/rmap.c index d9a23bb773bf..0c7b2a9400d4 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -61,6 +61,7 @@ #include <linux/mmu_notifier.h> #include <linux/migrate.h> #include <linux/hugetlb.h> +#include <linux/huge_mm.h> #include <linux/backing-dev.h> #include <linux/page_idle.h> #include <linux/memremap.h> diff --git a/mm/shmem.c b/mm/shmem.c index cd570cc79c76..220be9fa2c41 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -3482,6 +3482,12 @@ static int shmem_parse_options(struct fs_context *fc, void *data) { char *options = data; + if (options) { + int err = security_sb_eat_lsm_opts(options, &fc->security); + if (err) + return err; + } + while (options != NULL) { char *this_char = options; for (;;) { diff --git a/mm/shuffle.c b/mm/shuffle.c index 3ce12481b1dc..b3fe97fd6654 100644 --- a/mm/shuffle.c +++ b/mm/shuffle.c @@ -33,7 +33,7 @@ __meminit void page_alloc_shuffle(enum mm_shuffle_ctl ctl) } static bool shuffle_param; -extern int shuffle_show(char *buffer, const struct kernel_param *kp) +static int shuffle_show(char *buffer, const struct kernel_param *kp) { return sprintf(buffer, "%c\n", test_bit(SHUFFLE_ENABLE, &shuffle_state) ? 'Y' : 'N'); diff --git a/mm/slab.c b/mm/slab.c index 9df370558e5d..66e5d8032bae 100644 --- a/mm/slab.c +++ b/mm/slab.c @@ -4206,9 +4206,12 @@ void __check_heap_object(const void *ptr, unsigned long n, struct page *page, /** * __ksize -- Uninstrumented ksize. + * @objp: pointer to the object * * Unlike ksize(), __ksize() is uninstrumented, and does not provide the same * safety checks as ksize() with KASAN instrumentation enabled. + * + * Return: size of the actual memory used by @objp in bytes */ size_t __ksize(const void *objp) { diff --git a/mm/slab.h b/mm/slab.h index 68e455f2b698..b2b01694dc43 100644 --- a/mm/slab.h +++ b/mm/slab.h @@ -323,8 +323,8 @@ static inline struct kmem_cache *memcg_root_cache(struct kmem_cache *s) * Expects a pointer to a slab page. Please note, that PageSlab() check * isn't sufficient, as it returns true also for tail compound slab pages, * which do not have slab_cache pointer set. - * So this function assumes that the page can pass PageHead() and PageSlab() - * checks. + * So this function assumes that the page can pass PageSlab() && !PageTail() + * check. * * The kmem_cache can be reparented asynchronously. The caller must ensure * the memcg lifetime, e.g. by taking rcu_read_lock() or cgroup_mutex. diff --git a/mm/slab_common.c b/mm/slab_common.c index 6491c3a41805..f9fb27b4c843 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -178,10 +178,13 @@ static int init_memcg_params(struct kmem_cache *s, static void destroy_memcg_params(struct kmem_cache *s) { - if (is_root_cache(s)) + if (is_root_cache(s)) { kvfree(rcu_access_pointer(s->memcg_params.memcg_caches)); - else + } else { + mem_cgroup_put(s->memcg_params.memcg); + WRITE_ONCE(s->memcg_params.memcg, NULL); percpu_ref_exit(&s->memcg_params.refcnt); + } } static void free_memcg_params(struct rcu_head *rcu) @@ -253,8 +256,6 @@ static void memcg_unlink_cache(struct kmem_cache *s) } else { list_del(&s->memcg_params.children_node); list_del(&s->memcg_params.kmem_caches_node); - mem_cgroup_put(s->memcg_params.memcg); - WRITE_ONCE(s->memcg_params.memcg, NULL); } } #else @@ -1030,10 +1031,19 @@ void __init create_boot_cache(struct kmem_cache *s, const char *name, unsigned int useroffset, unsigned int usersize) { int err; + unsigned int align = ARCH_KMALLOC_MINALIGN; s->name = name; s->size = s->object_size = size; - s->align = calculate_alignment(flags, ARCH_KMALLOC_MINALIGN, size); + + /* + * For power of two sizes, guarantee natural alignment for kmalloc + * caches, regardless of SL*B debugging options. + */ + if (is_power_of_2(size)) + align = max(align, size); + s->align = calculate_alignment(flags, align, size); + s->useroffset = useroffset; s->usersize = usersize; @@ -1287,12 +1297,16 @@ void __init create_kmalloc_caches(slab_flags_t flags) */ void *kmalloc_order(size_t size, gfp_t flags, unsigned int order) { - void *ret; + void *ret = NULL; struct page *page; flags |= __GFP_COMP; page = alloc_pages(flags, order); - ret = page ? page_address(page) : NULL; + if (likely(page)) { + ret = page_address(page); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); + } ret = kasan_kmalloc_large(ret, size, flags); /* As ret might get tagged, call kmemleak hook after KASAN. */ kmemleak_alloc(ret, size, 1, flags); diff --git a/mm/slob.c b/mm/slob.c index cf377beab962..fa53e9f73893 100644 --- a/mm/slob.c +++ b/mm/slob.c @@ -190,7 +190,7 @@ static int slob_last(slob_t *s) static void *slob_new_pages(gfp_t gfp, int order, int node) { - void *page; + struct page *page; #ifdef CONFIG_NUMA if (node != NUMA_NO_NODE) @@ -202,14 +202,21 @@ static void *slob_new_pages(gfp_t gfp, int order, int node) if (!page) return NULL; + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); return page_address(page); } static void slob_free_pages(void *b, int order) { + struct page *sp = virt_to_page(b); + if (current->reclaim_state) current->reclaim_state->reclaimed_slab += 1 << order; - free_pages((unsigned long)b, order); + + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(sp, order); } /* @@ -217,6 +224,7 @@ static void slob_free_pages(void *b, int order) * @sp: Page to look in. * @size: Size of the allocation. * @align: Allocation alignment. + * @align_offset: Offset in the allocated block that will be aligned. * @page_removed_from_list: Return parameter. * * Tries to find a chunk of memory at least @size bytes big within @page. @@ -227,7 +235,7 @@ static void slob_free_pages(void *b, int order) * true (set to false otherwise). */ static void *slob_page_alloc(struct page *sp, size_t size, int align, - bool *page_removed_from_list) + int align_offset, bool *page_removed_from_list) { slob_t *prev, *cur, *aligned = NULL; int delta = 0, units = SLOB_UNITS(size); @@ -236,8 +244,17 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align, for (prev = NULL, cur = sp->freelist; ; prev = cur, cur = slob_next(cur)) { slobidx_t avail = slob_units(cur); + /* + * 'aligned' will hold the address of the slob block so that the + * address 'aligned'+'align_offset' is aligned according to the + * 'align' parameter. This is for kmalloc() which prepends the + * allocated block with its size, so that the block itself is + * aligned when needed. + */ if (align) { - aligned = (slob_t *)ALIGN((unsigned long)cur, align); + aligned = (slob_t *) + (ALIGN((unsigned long)cur + align_offset, align) + - align_offset); delta = aligned - cur; } if (avail >= units + delta) { /* room enough? */ @@ -281,7 +298,8 @@ static void *slob_page_alloc(struct page *sp, size_t size, int align, /* * slob_alloc: entry point into the slob allocator. */ -static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) +static void *slob_alloc(size_t size, gfp_t gfp, int align, int node, + int align_offset) { struct page *sp; struct list_head *slob_list; @@ -312,7 +330,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) if (sp->units < SLOB_UNITS(size)) continue; - b = slob_page_alloc(sp, size, align, &page_removed_from_list); + b = slob_page_alloc(sp, size, align, align_offset, &page_removed_from_list); if (!b) continue; @@ -349,7 +367,7 @@ static void *slob_alloc(size_t size, gfp_t gfp, int align, int node) INIT_LIST_HEAD(&sp->slab_list); set_slob(b, SLOB_UNITS(PAGE_SIZE), b + SLOB_UNITS(PAGE_SIZE)); set_slob_page_free(sp, slob_list); - b = slob_page_alloc(sp, size, align, &_unused); + b = slob_page_alloc(sp, size, align, align_offset, &_unused); BUG_ON(!b); spin_unlock_irqrestore(&slob_lock, flags); } @@ -451,7 +469,7 @@ static __always_inline void * __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) { unsigned int *m; - int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); + int minalign = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); void *ret; gfp &= gfp_allowed_mask; @@ -459,19 +477,28 @@ __do_kmalloc_node(size_t size, gfp_t gfp, int node, unsigned long caller) fs_reclaim_acquire(gfp); fs_reclaim_release(gfp); - if (size < PAGE_SIZE - align) { + if (size < PAGE_SIZE - minalign) { + int align = minalign; + + /* + * For power of two sizes, guarantee natural alignment for + * kmalloc()'d objects. + */ + if (is_power_of_2(size)) + align = max(minalign, (int) size); + if (!size) return ZERO_SIZE_PTR; - m = slob_alloc(size + align, gfp, align, node); + m = slob_alloc(size + minalign, gfp, align, node, minalign); if (!m) return NULL; *m = size; - ret = (void *)m + align; + ret = (void *)m + minalign; trace_kmalloc_node(caller, ret, - size, size + align, gfp, node); + size, size + minalign, gfp, node); } else { unsigned int order = get_order(size); @@ -521,8 +548,13 @@ void kfree(const void *block) int align = max_t(size_t, ARCH_KMALLOC_MINALIGN, ARCH_SLAB_MINALIGN); unsigned int *m = (unsigned int *)(block - align); slob_free(m, *m + align); - } else - __free_pages(sp, compound_order(sp)); + } else { + unsigned int order = compound_order(sp); + mod_node_page_state(page_pgdat(sp), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(sp, order); + + } } EXPORT_SYMBOL(kfree); @@ -567,7 +599,7 @@ static void *slob_alloc_node(struct kmem_cache *c, gfp_t flags, int node) fs_reclaim_release(flags); if (c->size < PAGE_SIZE) { - b = slob_alloc(c->size, flags, c->align, node); + b = slob_alloc(c->size, flags, c->align, node, 0); trace_kmem_cache_alloc_node(_RET_IP_, b, c->object_size, SLOB_UNITS(c->size) * SLOB_UNIT, flags, node); diff --git a/mm/slub.c b/mm/slub.c index 42c1b3af3c98..e72e802fc569 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1433,12 +1433,15 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, void *old_tail = *tail ? *tail : *head; int rsize; - if (slab_want_init_on_free(s)) { - void *p = NULL; + /* Head and tail of the reconstructed freelist */ + *head = NULL; + *tail = NULL; - do { - object = next; - next = get_freepointer(s, object); + do { + object = next; + next = get_freepointer(s, object); + + if (slab_want_init_on_free(s)) { /* * Clear the object and the metadata, but don't touch * the redzone. @@ -1448,29 +1451,8 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, : 0; memset((char *)object + s->inuse, 0, s->size - s->inuse - rsize); - set_freepointer(s, object, p); - p = object; - } while (object != old_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_LOCKDEP) || \ - defined(CONFIG_DEBUG_KMEMLEAK) || \ - defined(CONFIG_DEBUG_OBJECTS_FREE) || \ - defined(CONFIG_KASAN) - - next = *head; - - /* Head and tail of the reconstructed freelist */ - *head = NULL; - *tail = NULL; - - do { - object = next; - next = get_freepointer(s, object); + } /* If object's reuse doesn't have to be delayed */ if (!slab_free_hook(s, object)) { /* Move object to the new freelist */ @@ -1485,9 +1467,6 @@ static inline bool slab_free_freelist_hook(struct kmem_cache *s, *tail = NULL; return *head != NULL; -#else - return true; -#endif } static void *setup_object(struct kmem_cache *s, struct page *page, @@ -2672,6 +2651,17 @@ static void *__slab_alloc(struct kmem_cache *s, gfp_t gfpflags, int node, } /* + * If the object has been wiped upon free, make sure it's fully initialized by + * zeroing out freelist pointer. + */ +static __always_inline void maybe_wipe_obj_freeptr(struct kmem_cache *s, + void *obj) +{ + if (unlikely(slab_want_init_on_free(s)) && obj) + memset((void *)((char *)obj + s->offset), 0, sizeof(void *)); +} + +/* * 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. @@ -2759,12 +2749,8 @@ redo: prefetch_freepointer(s, next_object); stat(s, ALLOC_FASTPATH); } - /* - * If the object has been wiped upon free, make sure it's fully - * initialized by zeroing out freelist pointer. - */ - if (unlikely(slab_want_init_on_free(s)) && object) - memset(object + s->offset, 0, sizeof(void *)); + + maybe_wipe_obj_freeptr(s, object); if (unlikely(slab_want_init_on_alloc(gfpflags, s)) && object) memset(object, 0, s->object_size); @@ -3178,10 +3164,13 @@ int kmem_cache_alloc_bulk(struct kmem_cache *s, gfp_t flags, size_t size, goto error; c = this_cpu_ptr(s->cpu_slab); + maybe_wipe_obj_freeptr(s, p[i]); + continue; /* goto for-loop */ } c->freelist = get_freepointer(s, object); p[i] = object; + maybe_wipe_obj_freeptr(s, p[i]); } c->tid = next_tid(c->tid); local_irq_enable(); @@ -3821,11 +3810,15 @@ static void *kmalloc_large_node(size_t size, gfp_t flags, int node) { struct page *page; void *ptr = NULL; + unsigned int order = get_order(size); flags |= __GFP_COMP; - page = alloc_pages_node(node, flags, get_order(size)); - if (page) + page = alloc_pages_node(node, flags, order); + if (page) { ptr = page_address(page); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + 1 << order); + } return kmalloc_large_node_hook(ptr, size, flags); } @@ -3951,9 +3944,13 @@ void kfree(const void *x) page = virt_to_head_page(x); if (unlikely(!PageSlab(page))) { + unsigned int order = compound_order(page); + BUG_ON(!PageCompound(page)); kfree_hook(object); - __free_pages(page, compound_order(page)); + mod_node_page_state(page_pgdat(page), NR_SLAB_UNRECLAIMABLE, + -(1 << order)); + __free_pages(page, order); return; } slab_free(page->slab_cache, page, object, NULL, 1, _RET_IP_); @@ -4838,7 +4835,17 @@ static ssize_t show_slab_objects(struct kmem_cache *s, } } - get_online_mems(); + /* + * It is impossible to take "mem_hotplug_lock" here with "kernfs_mutex" + * already held which will conflict with an existing lock order: + * + * mem_hotplug_lock->slab_mutex->kernfs_mutex + * + * We don't really need mem_hotplug_lock (to hold off + * slab_mem_going_offline_callback) here because slab's memory hot + * unplug code doesn't destroy the kmem_cache->node[] data. + */ + #ifdef CONFIG_SLUB_DEBUG if (flags & SO_ALL) { struct kmem_cache_node *n; @@ -4879,7 +4886,6 @@ static ssize_t show_slab_objects(struct kmem_cache *s, x += sprintf(buf + x, " N%d=%lu", node, nodes[node]); #endif - put_online_mems(); kfree(nodes); return x + sprintf(buf + x, "\n"); } diff --git a/mm/sparse.c b/mm/sparse.c index bf32de9e666b..f6891c1992b1 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -219,7 +219,7 @@ static inline unsigned long first_present_section_nr(void) return next_present_section_nr(-1); } -void subsection_mask_set(unsigned long *map, unsigned long pfn, +static void subsection_mask_set(unsigned long *map, unsigned long pfn, unsigned long nr_pages) { int idx = subsection_map_index(pfn); diff --git a/mm/truncate.c b/mm/truncate.c index 8563339041f6..dd9ebc1da356 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -592,6 +592,16 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, unlock_page(page); continue; } + + /* Take a pin outside pagevec */ + get_page(page); + + /* + * Drop extra pins before trying to invalidate + * the huge page. + */ + pagevec_remove_exceptionals(&pvec); + pagevec_release(&pvec); } ret = invalidate_inode_page(page); @@ -602,6 +612,8 @@ unsigned long invalidate_mapping_pages(struct address_space *mapping, */ if (!ret) deactivate_file_page(page); + if (PageTransHuge(page)) + put_page(page); count += ret; } pagevec_remove_exceptionals(&pvec); diff --git a/mm/vmpressure.c b/mm/vmpressure.c index f3b50811497a..4bac22fe1aa2 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -355,6 +355,9 @@ void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) * "hierarchy" or "local"). * * To be used as memcg event method. + * + * Return: 0 on success, -ENOMEM on memory failure or -EINVAL if @args could + * not be parsed. */ int vmpressure_register_event(struct mem_cgroup *memcg, struct eventfd_ctx *eventfd, const char *args) @@ -362,7 +365,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg, struct vmpressure *vmpr = memcg_to_vmpressure(memcg); struct vmpressure_event *ev; enum vmpressure_modes mode = VMPRESSURE_NO_PASSTHROUGH; - enum vmpressure_levels level = -1; + enum vmpressure_levels level; char *spec, *spec_orig; char *token; int ret = 0; @@ -375,20 +378,18 @@ int vmpressure_register_event(struct mem_cgroup *memcg, /* Find required level */ token = strsep(&spec, ","); - level = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); - if (level < 0) { - ret = level; + ret = match_string(vmpressure_str_levels, VMPRESSURE_NUM_LEVELS, token); + if (ret < 0) goto out; - } + level = ret; /* Find optional mode */ token = strsep(&spec, ","); if (token) { - mode = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); - if (mode < 0) { - ret = mode; + ret = match_string(vmpressure_str_modes, VMPRESSURE_NUM_MODES, token); + if (ret < 0) goto out; - } + mode = ret; } ev = kzalloc(sizeof(*ev), GFP_KERNEL); @@ -404,6 +405,7 @@ int vmpressure_register_event(struct mem_cgroup *memcg, mutex_lock(&vmpr->events_lock); list_add(&ev->node, &vmpr->events); mutex_unlock(&vmpr->events_lock); + ret = 0; out: kfree(spec_orig); return ret; diff --git a/mm/vmscan.c b/mm/vmscan.c index e5d52d6a24af..ee4eecc7e1c2 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -351,12 +351,13 @@ unsigned long zone_reclaimable_pages(struct zone *zone) */ unsigned long lruvec_lru_size(struct lruvec *lruvec, enum lru_list lru, int zone_idx) { - unsigned long lru_size; + unsigned long lru_size = 0; int zid; - if (!mem_cgroup_disabled()) - lru_size = lruvec_page_state_local(lruvec, NR_LRU_BASE + lru); - else + if (!mem_cgroup_disabled()) { + for (zid = 0; zid < MAX_NR_ZONES; zid++) + lru_size += mem_cgroup_get_zone_lru_size(lruvec, lru, zid); + } else lru_size = node_page_state(lruvec_pgdat(lruvec), NR_LRU_BASE + lru); for (zid = zone_idx + 1; zid < MAX_NR_ZONES; zid++) { @@ -932,10 +933,7 @@ static int __remove_mapping(struct address_space *mapping, struct page *page, * Note that if SetPageDirty is always performed via set_page_dirty, * and thus under the i_pages lock, then this ordering is not required. */ - if (unlikely(PageTransHuge(page)) && PageSwapCache(page)) - refcount = 1 + HPAGE_PMD_NR; - else - refcount = 2; + refcount = 1 + compound_nr(page); if (!page_ref_freeze(page, refcount)) goto cannot_free; /* note: atomic_cmpxchg in page_ref_freeze provides the smp_rmb */ @@ -2459,17 +2457,70 @@ out: *lru_pages = 0; for_each_evictable_lru(lru) { int file = is_file_lru(lru); - unsigned long size; + unsigned long lruvec_size; unsigned long scan; + unsigned long protection; + + lruvec_size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); + protection = mem_cgroup_protection(memcg, + sc->memcg_low_reclaim); + + if (protection) { + /* + * Scale a cgroup's reclaim pressure by proportioning + * its current usage to its memory.low or memory.min + * setting. + * + * This is important, as otherwise scanning aggression + * becomes extremely binary -- from nothing as we + * approach the memory protection threshold, to totally + * nominal as we exceed it. This results in requiring + * setting extremely liberal protection thresholds. It + * also means we simply get no protection at all if we + * set it too low, which is not ideal. + * + * If there is any protection in place, we reduce scan + * pressure by how much of the total memory used is + * within protection thresholds. + * + * There is one special case: in the first reclaim pass, + * we skip over all groups that are within their low + * protection. If that fails to reclaim enough pages to + * satisfy the reclaim goal, we come back and override + * the best-effort low protection. However, we still + * ideally want to honor how well-behaved groups are in + * that case instead of simply punishing them all + * equally. As such, we reclaim them based on how much + * memory they are using, reducing the scan pressure + * again by how much of the total memory used is under + * hard protection. + */ + unsigned long cgroup_size = mem_cgroup_size(memcg); + + /* Avoid TOCTOU with earlier protection check */ + cgroup_size = max(cgroup_size, protection); + + scan = lruvec_size - lruvec_size * protection / + cgroup_size; + + /* + * Minimally target SWAP_CLUSTER_MAX pages to keep + * reclaim moving forwards, avoiding decremeting + * sc->priority further than desirable. + */ + scan = max(scan, SWAP_CLUSTER_MAX); + } else { + scan = lruvec_size; + } + + scan >>= sc->priority; - size = lruvec_lru_size(lruvec, lru, sc->reclaim_idx); - scan = size >> sc->priority; /* * If the cgroup's already been deleted, make sure to * scrape out the remaining cache. */ if (!scan && !mem_cgroup_online(memcg)) - scan = min(size, SWAP_CLUSTER_MAX); + scan = min(lruvec_size, SWAP_CLUSTER_MAX); switch (scan_balance) { case SCAN_EQUAL: @@ -2489,7 +2540,7 @@ out: case SCAN_ANON: /* Scan one type exclusively */ if ((scan_balance == SCAN_FILE) != file) { - size = 0; + lruvec_size = 0; scan = 0; } break; @@ -2498,7 +2549,7 @@ out: BUG(); } - *lru_pages += size; + *lru_pages += lruvec_size; nr[lru] = scan; } } @@ -2742,6 +2793,13 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) memcg_memory_event(memcg, MEMCG_LOW); break; case MEMCG_PROT_NONE: + /* + * All protection thresholds breached. We may + * still choose to vary the scan pressure + * applied based on by how much the cgroup in + * question has exceeded its protection + * thresholds (see get_scan_count). + */ break; } diff --git a/mm/vmstat.c b/mm/vmstat.c index 6afc892a148a..a8222041bd44 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -1383,12 +1383,29 @@ static void pagetypeinfo_showfree_print(struct seq_file *m, unsigned long freecount = 0; struct free_area *area; struct list_head *curr; + bool overflow = false; area = &(zone->free_area[order]); - list_for_each(curr, &area->free_list[mtype]) - freecount++; - seq_printf(m, "%6lu ", freecount); + list_for_each(curr, &area->free_list[mtype]) { + /* + * Cap the free_list iteration because it might + * be really large and we are under a spinlock + * so a long time spent here could trigger a + * hard lockup detector. Anyway this is a + * debugging tool so knowing there is a handful + * of pages of this order should be more than + * sufficient. + */ + if (++freecount >= 100000) { + overflow = true; + break; + } + } + seq_printf(m, "%s%6lu ", overflow ? ">" : "", freecount); + spin_unlock_irq(&zone->lock); + cond_resched(); + spin_lock_irq(&zone->lock); } seq_putc(m, '\n'); } @@ -1972,7 +1989,7 @@ void __init init_mm_internals(void) #endif #ifdef CONFIG_PROC_FS proc_create_seq("buddyinfo", 0444, NULL, &fragmentation_op); - proc_create_seq("pagetypeinfo", 0444, NULL, &pagetypeinfo_op); + proc_create_seq("pagetypeinfo", 0400, NULL, &pagetypeinfo_op); proc_create_seq("vmstat", 0444, NULL, &vmstat_op); proc_create_seq("zoneinfo", 0444, NULL, &zoneinfo_op); #endif diff --git a/mm/z3fold.c b/mm/z3fold.c index 05bdf90646e7..6d3d3f698ebb 100644 --- a/mm/z3fold.c +++ b/mm/z3fold.c @@ -998,9 +998,11 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) struct z3fold_header *zhdr; struct page *page; enum buddy bud; + bool page_claimed; zhdr = handle_to_z3fold_header(handle); page = virt_to_page(zhdr); + page_claimed = test_and_set_bit(PAGE_CLAIMED, &page->private); if (test_bit(PAGE_HEADLESS, &page->private)) { /* if a headless page is under reclaim, just leave. @@ -1008,7 +1010,7 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) * has not been set before, we release this page * immediately so we don't care about its value any more. */ - if (!test_and_set_bit(PAGE_CLAIMED, &page->private)) { + if (!page_claimed) { spin_lock(&pool->lock); list_del(&page->lru); spin_unlock(&pool->lock); @@ -1044,13 +1046,15 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) atomic64_dec(&pool->pages_nr); return; } - if (test_bit(PAGE_CLAIMED, &page->private)) { + if (page_claimed) { + /* the page has not been claimed by us */ z3fold_page_unlock(zhdr); return; } if (unlikely(PageIsolated(page)) || test_and_set_bit(NEEDS_COMPACTING, &page->private)) { z3fold_page_unlock(zhdr); + clear_bit(PAGE_CLAIMED, &page->private); return; } if (zhdr->cpu < 0 || !cpu_online(zhdr->cpu)) { @@ -1060,10 +1064,12 @@ static void z3fold_free(struct z3fold_pool *pool, unsigned long handle) zhdr->cpu = -1; kref_get(&zhdr->refcount); do_compact_page(zhdr, true); + clear_bit(PAGE_CLAIMED, &page->private); return; } kref_get(&zhdr->refcount); queue_work_on(zhdr->cpu, pool->compact_wq, &zhdr->work); + clear_bit(PAGE_CLAIMED, &page->private); z3fold_page_unlock(zhdr); } |