diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/Kconfig | 8 | ||||
-rw-r--r-- | mm/Makefile | 2 | ||||
-rw-r--r-- | mm/bounce.c | 21 | ||||
-rw-r--r-- | mm/filemap.c | 34 | ||||
-rw-r--r-- | mm/huge_memory.c | 77 | ||||
-rw-r--r-- | mm/hugetlb.c | 51 | ||||
-rw-r--r-- | mm/madvise.c | 31 | ||||
-rw-r--r-- | mm/memblock.c | 12 | ||||
-rw-r--r-- | mm/memcontrol.c | 338 | ||||
-rw-r--r-- | mm/memory-failure.c | 4 | ||||
-rw-r--r-- | mm/memory.c | 52 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 93 | ||||
-rw-r--r-- | mm/migrate.c | 24 | ||||
-rw-r--r-- | mm/mmap.c | 196 | ||||
-rw-r--r-- | mm/nobootmem.c | 6 | ||||
-rw-r--r-- | mm/nommu.c | 78 | ||||
-rw-r--r-- | mm/page-writeback.c | 4 | ||||
-rw-r--r-- | mm/page_alloc.c | 78 | ||||
-rw-r--r-- | mm/page_io.c | 36 | ||||
-rw-r--r-- | mm/rmap.c | 3 | ||||
-rw-r--r-- | mm/shmem.c | 5 | ||||
-rw-r--r-- | mm/slub.c | 9 | ||||
-rw-r--r-- | mm/sparse-vmemmap.c | 27 | ||||
-rw-r--r-- | mm/sparse.c | 82 | ||||
-rw-r--r-- | mm/swap.c | 11 | ||||
-rw-r--r-- | mm/swap_state.c | 6 | ||||
-rw-r--r-- | mm/swapfile.c | 2 | ||||
-rw-r--r-- | mm/vmalloc.c | 218 | ||||
-rw-r--r-- | mm/vmpressure.c | 374 | ||||
-rw-r--r-- | mm/vmscan.c | 16 | ||||
-rw-r--r-- | mm/vmstat.c | 6 |
31 files changed, 1461 insertions, 443 deletions
@@ -263,8 +263,14 @@ config ZONE_DMA_FLAG default "1" config BOUNCE - def_bool y + bool "Enable bounce buffers" + default y depends on BLOCK && MMU && (ZONE_DMA || HIGHMEM) + help + Enable bounce buffers for devices that cannot access + the full range of memory available to the CPU. Enabled + by default when ZONE_DMA or HIGHMEM is selected, but you + may say n to override this. # On the 'tile' arch, USB OHCI needs the bounce pool since tilegx will often # have more than 4GB of memory, but we don't currently use the IOTLB to present diff --git a/mm/Makefile b/mm/Makefile index 3a46287..72c5acb 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -50,7 +50,7 @@ obj-$(CONFIG_FS_XIP) += filemap_xip.o obj-$(CONFIG_MIGRATION) += migrate.o obj-$(CONFIG_QUICKLIST) += quicklist.o obj-$(CONFIG_TRANSPARENT_HUGEPAGE) += huge_memory.o -obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o +obj-$(CONFIG_MEMCG) += memcontrol.o page_cgroup.o vmpressure.o obj-$(CONFIG_CGROUP_HUGETLB) += hugetlb_cgroup.o obj-$(CONFIG_MEMORY_FAILURE) += memory-failure.o obj-$(CONFIG_HWPOISON_INJECT) += hwpoison-inject.o diff --git a/mm/bounce.c b/mm/bounce.c index 5f89017..a5c2ec3 100644 --- a/mm/bounce.c +++ b/mm/bounce.c @@ -181,32 +181,13 @@ static void bounce_end_io_read_isa(struct bio *bio, int err) #ifdef CONFIG_NEED_BOUNCE_POOL static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) { - struct page *page; - struct backing_dev_info *bdi; - struct address_space *mapping; - struct bio_vec *from; - int i; - if (bio_data_dir(bio) != WRITE) return 0; if (!bdi_cap_stable_pages_required(&q->backing_dev_info)) return 0; - /* - * Based on the first page that has a valid mapping, decide whether or - * not we have to employ bounce buffering to guarantee stable pages. - */ - bio_for_each_segment(from, bio, i) { - page = from->bv_page; - mapping = page_mapping(page); - if (!mapping) - continue; - bdi = mapping->backing_dev_info; - return mapping->host->i_sb->s_flags & MS_SNAP_STABLE; - } - - return 0; + return test_bit(BIO_SNAP_STABLE, &bio->bi_flags); } #else static int must_snapshot_stable_pages(struct request_queue *q, struct bio *bio) diff --git a/mm/filemap.c b/mm/filemap.c index e1979fd..e989fb1 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -35,6 +35,9 @@ #include <linux/cleancache.h> #include "internal.h" +#define CREATE_TRACE_POINTS +#include <trace/events/filemap.h> + /* * FIXME: remove all knowledge of the buffer layer from the core VM */ @@ -113,6 +116,7 @@ void __delete_from_page_cache(struct page *page) { struct address_space *mapping = page->mapping; + trace_mm_filemap_delete_from_page_cache(page); /* * if we're uptodate, flush out into the cleancache, otherwise * invalidate any existing cleancache entries. We can't leave @@ -184,6 +188,17 @@ static int sleep_on_page_killable(void *word) return fatal_signal_pending(current) ? -EINTR : 0; } +static int filemap_check_errors(struct address_space *mapping) +{ + int ret = 0; + /* Check for outstanding write errors */ + if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) + ret = -ENOSPC; + if (test_and_clear_bit(AS_EIO, &mapping->flags)) + ret = -EIO; + return ret; +} + /** * __filemap_fdatawrite_range - start writeback on mapping dirty pages in range * @mapping: address space structure to write @@ -265,10 +280,10 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, pgoff_t end = end_byte >> PAGE_CACHE_SHIFT; struct pagevec pvec; int nr_pages; - int ret = 0; + int ret2, ret = 0; if (end_byte < start_byte) - return 0; + goto out; pagevec_init(&pvec, 0); while ((index <= end) && @@ -291,12 +306,10 @@ int filemap_fdatawait_range(struct address_space *mapping, loff_t start_byte, pagevec_release(&pvec); cond_resched(); } - - /* Check for outstanding write errors */ - if (test_and_clear_bit(AS_ENOSPC, &mapping->flags)) - ret = -ENOSPC; - if (test_and_clear_bit(AS_EIO, &mapping->flags)) - ret = -EIO; +out: + ret2 = filemap_check_errors(mapping); + if (!ret) + ret = ret2; return ret; } @@ -337,6 +350,8 @@ int filemap_write_and_wait(struct address_space *mapping) if (!err) err = err2; } + } else { + err = filemap_check_errors(mapping); } return err; } @@ -368,6 +383,8 @@ int filemap_write_and_wait_range(struct address_space *mapping, if (!err) err = err2; } + } else { + err = filemap_check_errors(mapping); } return err; } @@ -464,6 +481,7 @@ int add_to_page_cache_locked(struct page *page, struct address_space *mapping, mapping->nrpages++; __inc_zone_page_state(page, NR_FILE_PAGES); spin_unlock_irq(&mapping->tree_lock); + trace_mm_filemap_add_to_page_cache(page); } else { page->mapping = NULL; /* Leave page->index set: truncation relies upon it */ diff --git a/mm/huge_memory.c b/mm/huge_memory.c index e2f7f5aa..03a89a2 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -163,35 +163,34 @@ static int start_khugepaged(void) } static atomic_t huge_zero_refcount; -static unsigned long huge_zero_pfn __read_mostly; +static struct page *huge_zero_page __read_mostly; -static inline bool is_huge_zero_pfn(unsigned long pfn) +static inline bool is_huge_zero_page(struct page *page) { - unsigned long zero_pfn = ACCESS_ONCE(huge_zero_pfn); - return zero_pfn && pfn == zero_pfn; + return ACCESS_ONCE(huge_zero_page) == page; } static inline bool is_huge_zero_pmd(pmd_t pmd) { - return is_huge_zero_pfn(pmd_pfn(pmd)); + return is_huge_zero_page(pmd_page(pmd)); } -static unsigned long get_huge_zero_page(void) +static struct page *get_huge_zero_page(void) { struct page *zero_page; retry: if (likely(atomic_inc_not_zero(&huge_zero_refcount))) - return ACCESS_ONCE(huge_zero_pfn); + return ACCESS_ONCE(huge_zero_page); zero_page = alloc_pages((GFP_TRANSHUGE | __GFP_ZERO) & ~__GFP_MOVABLE, HPAGE_PMD_ORDER); if (!zero_page) { count_vm_event(THP_ZERO_PAGE_ALLOC_FAILED); - return 0; + return NULL; } count_vm_event(THP_ZERO_PAGE_ALLOC); preempt_disable(); - if (cmpxchg(&huge_zero_pfn, 0, page_to_pfn(zero_page))) { + if (cmpxchg(&huge_zero_page, NULL, zero_page)) { preempt_enable(); __free_page(zero_page); goto retry; @@ -200,7 +199,7 @@ retry: /* We take additional reference here. It will be put back by shrinker */ atomic_set(&huge_zero_refcount, 2); preempt_enable(); - return ACCESS_ONCE(huge_zero_pfn); + return ACCESS_ONCE(huge_zero_page); } static void put_huge_zero_page(void) @@ -220,9 +219,9 @@ static int shrink_huge_zero_page(struct shrinker *shrink, return atomic_read(&huge_zero_refcount) == 1 ? HPAGE_PMD_NR : 0; if (atomic_cmpxchg(&huge_zero_refcount, 1, 0) == 1) { - unsigned long zero_pfn = xchg(&huge_zero_pfn, 0); - BUG_ON(zero_pfn == 0); - __free_page(__pfn_to_page(zero_pfn)); + struct page *zero_page = xchg(&huge_zero_page, NULL); + BUG_ON(zero_page == NULL); + __free_page(zero_page); } return 0; @@ -713,6 +712,11 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, return VM_FAULT_OOM; clear_huge_page(page, haddr, HPAGE_PMD_NR); + /* + * The memory barrier inside __SetPageUptodate makes sure that + * clear_huge_page writes become visible before the set_pmd_at() + * write. + */ __SetPageUptodate(page); spin_lock(&mm->page_table_lock); @@ -724,12 +728,6 @@ static int __do_huge_pmd_anonymous_page(struct mm_struct *mm, } else { pmd_t entry; entry = mk_huge_pmd(page, vma); - /* - * The spinlocking to take the lru_lock inside - * page_add_new_anon_rmap() acts as a full memory - * barrier to be sure clear_huge_page writes become - * visible after the set_pmd_at() write. - */ page_add_new_anon_rmap(page, vma, haddr); set_pmd_at(mm, haddr, pmd, entry); pgtable_trans_huge_deposit(mm, pgtable); @@ -765,12 +763,12 @@ static inline struct page *alloc_hugepage(int defrag) static bool set_huge_zero_page(pgtable_t pgtable, struct mm_struct *mm, struct vm_area_struct *vma, unsigned long haddr, pmd_t *pmd, - unsigned long zero_pfn) + struct page *zero_page) { pmd_t entry; if (!pmd_none(*pmd)) return false; - entry = pfn_pmd(zero_pfn, vma->vm_page_prot); + entry = mk_pmd(zero_page, vma->vm_page_prot); entry = pmd_wrprotect(entry); entry = pmd_mkhuge(entry); set_pmd_at(mm, haddr, pmd, entry); @@ -795,20 +793,20 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, if (!(flags & FAULT_FLAG_WRITE) && transparent_hugepage_use_zero_page()) { pgtable_t pgtable; - unsigned long zero_pfn; + struct page *zero_page; bool set; pgtable = pte_alloc_one(mm, haddr); if (unlikely(!pgtable)) return VM_FAULT_OOM; - zero_pfn = get_huge_zero_page(); - if (unlikely(!zero_pfn)) { + zero_page = get_huge_zero_page(); + if (unlikely(!zero_page)) { pte_free(mm, pgtable); count_vm_event(THP_FAULT_FALLBACK); goto out; } spin_lock(&mm->page_table_lock); set = set_huge_zero_page(pgtable, mm, vma, haddr, pmd, - zero_pfn); + zero_page); spin_unlock(&mm->page_table_lock); if (!set) { pte_free(mm, pgtable); @@ -887,16 +885,16 @@ int copy_huge_pmd(struct mm_struct *dst_mm, struct mm_struct *src_mm, * a page table. */ if (is_huge_zero_pmd(pmd)) { - unsigned long zero_pfn; + struct page *zero_page; bool set; /* * get_huge_zero_page() will never allocate a new page here, * since we already have a zero page to copy. It just takes a * reference. */ - zero_pfn = get_huge_zero_page(); + zero_page = get_huge_zero_page(); set = set_huge_zero_page(pgtable, dst_mm, vma, addr, dst_pmd, - zero_pfn); + zero_page); BUG_ON(!set); /* unexpected !pmd_none(dst_pmd) */ ret = 0; goto out_unlock; @@ -1560,7 +1558,8 @@ static int __split_huge_page_splitting(struct page *page, return ret; } -static void __split_huge_page_refcount(struct page *page) +static void __split_huge_page_refcount(struct page *page, + struct list_head *list) { int i; struct zone *zone = page_zone(page); @@ -1646,7 +1645,7 @@ static void __split_huge_page_refcount(struct page *page) BUG_ON(!PageDirty(page_tail)); BUG_ON(!PageSwapBacked(page_tail)); - lru_add_page_tail(page, page_tail, lruvec); + lru_add_page_tail(page, page_tail, lruvec, list); } atomic_sub(tail_count, &page->_count); BUG_ON(atomic_read(&page->_count) <= 0); @@ -1753,7 +1752,8 @@ static int __split_huge_page_map(struct page *page, /* must be called with anon_vma->root->rwsem held */ static void __split_huge_page(struct page *page, - struct anon_vma *anon_vma) + struct anon_vma *anon_vma, + struct list_head *list) { int mapcount, mapcount2; pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); @@ -1784,7 +1784,7 @@ static void __split_huge_page(struct page *page, mapcount, page_mapcount(page)); BUG_ON(mapcount != page_mapcount(page)); - __split_huge_page_refcount(page); + __split_huge_page_refcount(page, list); mapcount2 = 0; anon_vma_interval_tree_foreach(avc, &anon_vma->rb_root, pgoff, pgoff) { @@ -1799,12 +1799,19 @@ static void __split_huge_page(struct page *page, BUG_ON(mapcount != mapcount2); } -int split_huge_page(struct page *page) +/* + * Split a hugepage into normal pages. This doesn't change the position of head + * page. If @list is null, tail pages will be added to LRU list, otherwise, to + * @list. Both head page and tail pages will inherit mapping, flags, and so on + * from the hugepage. + * Return 0 if the hugepage is split successfully otherwise return 1. + */ +int split_huge_page_to_list(struct page *page, struct list_head *list) { struct anon_vma *anon_vma; int ret = 1; - BUG_ON(is_huge_zero_pfn(page_to_pfn(page))); + BUG_ON(is_huge_zero_page(page)); BUG_ON(!PageAnon(page)); /* @@ -1824,7 +1831,7 @@ int split_huge_page(struct page *page) goto out_unlock; BUG_ON(!PageSwapBacked(page)); - __split_huge_page(page, anon_vma); + __split_huge_page(page, anon_vma, list); count_vm_event(THP_SPLIT); BUG_ON(PageCompound(page)); diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ca9a7c6..9b9aeef 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2121,6 +2121,21 @@ int hugetlb_report_node_meminfo(int nid, char *buf) nid, h->surplus_huge_pages_node[nid]); } +void hugetlb_show_meminfo(void) +{ + struct hstate *h; + int nid; + + for_each_node_state(nid, N_MEMORY) + for_each_hstate(h) + pr_info("Node %d hugepages_total=%u hugepages_free=%u hugepages_surp=%u hugepages_size=%lukB\n", + nid, + h->nr_huge_pages_node[nid], + h->free_huge_pages_node[nid], + h->surplus_huge_pages_node[nid], + 1UL << (huge_page_order(h) + PAGE_SHIFT - 10)); +} + /* Return the number pages of memory we physically have, in PAGE_SIZE units. */ unsigned long hugetlb_total_pages(void) { @@ -2247,10 +2262,11 @@ static pte_t make_huge_pte(struct vm_area_struct *vma, struct page *page, pte_t entry; if (writable) { - entry = - pte_mkwrite(pte_mkdirty(mk_pte(page, vma->vm_page_prot))); + entry = huge_pte_mkwrite(huge_pte_mkdirty(mk_huge_pte(page, + vma->vm_page_prot))); } else { - entry = huge_pte_wrprotect(mk_pte(page, vma->vm_page_prot)); + entry = huge_pte_wrprotect(mk_huge_pte(page, + vma->vm_page_prot)); } entry = pte_mkyoung(entry); entry = pte_mkhuge(entry); @@ -2264,7 +2280,7 @@ static void set_huge_ptep_writable(struct vm_area_struct *vma, { pte_t entry; - entry = pte_mkwrite(pte_mkdirty(huge_ptep_get(ptep))); + entry = huge_pte_mkwrite(huge_pte_mkdirty(huge_ptep_get(ptep))); if (huge_ptep_set_access_flags(vma, address, ptep, entry, 1)) update_mmu_cache(vma, address, ptep); } @@ -2379,7 +2395,7 @@ again: * HWPoisoned hugepage is already unmapped and dropped reference */ if (unlikely(is_hugetlb_entry_hwpoisoned(pte))) { - pte_clear(mm, address, ptep); + huge_pte_clear(mm, address, ptep); continue; } @@ -2403,7 +2419,7 @@ again: pte = huge_ptep_get_and_clear(mm, address, ptep); tlb_remove_tlb_entry(tlb, ptep, address); - if (pte_dirty(pte)) + if (huge_pte_dirty(pte)) set_page_dirty(page); page_remove_rmap(page); @@ -2856,7 +2872,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, * page now as it is used to determine if a reservation has been * consumed. */ - if ((flags & FAULT_FLAG_WRITE) && !pte_write(entry)) { + if ((flags & FAULT_FLAG_WRITE) && !huge_pte_write(entry)) { if (vma_needs_reservation(h, vma, address) < 0) { ret = VM_FAULT_OOM; goto out_mutex; @@ -2886,12 +2902,12 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (flags & FAULT_FLAG_WRITE) { - if (!pte_write(entry)) { + if (!huge_pte_write(entry)) { ret = hugetlb_cow(mm, vma, address, ptep, entry, pagecache_page); goto out_page_table_lock; } - entry = pte_mkdirty(entry); + entry = huge_pte_mkdirty(entry); } entry = pte_mkyoung(entry); if (huge_ptep_set_access_flags(vma, address, ptep, entry, @@ -2961,8 +2977,19 @@ long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, break; } - if (absent || - ((flags & FOLL_WRITE) && !pte_write(huge_ptep_get(pte)))) { + /* + * We need call hugetlb_fault for both hugepages under migration + * (in which case hugetlb_fault waits for the migration,) and + * hwpoisoned hugepages (in which case we need to prevent the + * caller from accessing to them.) In order to do this, we use + * here is_swap_pte instead of is_hugetlb_entry_migration and + * is_hugetlb_entry_hwpoisoned. This is because it simply covers + * both cases, and because we can't follow correct pages + * directly from any kind of swap entries. + */ + if (absent || is_swap_pte(huge_ptep_get(pte)) || + ((flags & FOLL_WRITE) && + !huge_pte_write(huge_ptep_get(pte)))) { int ret; spin_unlock(&mm->page_table_lock); @@ -3032,7 +3059,7 @@ unsigned long hugetlb_change_protection(struct vm_area_struct *vma, } if (!huge_pte_none(huge_ptep_get(ptep))) { pte = huge_ptep_get_and_clear(mm, address, ptep); - pte = pte_mkhuge(pte_modify(pte, newprot)); + pte = pte_mkhuge(huge_pte_modify(pte, newprot)); pte = arch_make_huge_pte(pte, vma, NULL, 0); set_huge_pte_at(mm, address, ptep, pte); pages++; diff --git a/mm/madvise.c b/mm/madvise.c index c58c94b..7055883 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -473,27 +473,27 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) if (!madvise_behavior_valid(behavior)) return error; - write = madvise_need_mmap_write(behavior); - if (write) - down_write(¤t->mm->mmap_sem); - else - down_read(¤t->mm->mmap_sem); - if (start & ~PAGE_MASK) - goto out; + return error; len = (len_in + ~PAGE_MASK) & PAGE_MASK; /* Check to see whether len was rounded up from small -ve to zero */ if (len_in && !len) - goto out; + return error; end = start + len; if (end < start) - goto out; + return error; error = 0; if (end == start) - goto out; + return error; + + write = madvise_need_mmap_write(behavior); + if (write) + down_write(¤t->mm->mmap_sem); + else + down_read(¤t->mm->mmap_sem); /* * If the interval [start,end) covers some unmapped address @@ -509,14 +509,14 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) /* Still start < end. */ error = -ENOMEM; if (!vma) - goto out_plug; + goto out; /* Here start < (end|vma->vm_end). */ if (start < vma->vm_start) { unmapped_error = -ENOMEM; start = vma->vm_start; if (start >= end) - goto out_plug; + goto out; } /* Here vma->vm_start <= start < (end|vma->vm_end) */ @@ -527,21 +527,20 @@ SYSCALL_DEFINE3(madvise, unsigned long, start, size_t, len_in, int, behavior) /* Here vma->vm_start <= start < tmp <= (end|vma->vm_end). */ error = madvise_vma(vma, &prev, start, tmp, behavior); if (error) - goto out_plug; + goto out; start = tmp; if (prev && start < prev->vm_end) start = prev->vm_end; error = unmapped_error; if (start >= end) - goto out_plug; + goto out; if (prev) vma = prev->vm_next; else /* madvise_remove dropped mmap_sem */ vma = find_vma(current->mm, start); } -out_plug: - blk_finish_plug(&plug); out: + blk_finish_plug(&plug); if (write) up_write(¤t->mm->mmap_sem); else diff --git a/mm/memblock.c b/mm/memblock.c index b8d9147..c5fad93 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -322,10 +322,11 @@ static void __init_memblock memblock_merge_regions(struct memblock_type *type) /** * memblock_insert_region - insert new memblock region - * @type: memblock type to insert into - * @idx: index for the insertion point - * @base: base address of the new region - * @size: size of the new region + * @type: memblock type to insert into + * @idx: index for the insertion point + * @base: base address of the new region + * @size: size of the new region + * @nid: node id of the new region * * Insert new memblock region [@base,@base+@size) into @type at @idx. * @type must already have extra room to accomodate the new region. @@ -771,6 +772,9 @@ static phys_addr_t __init memblock_alloc_base_nid(phys_addr_t size, { phys_addr_t found; + if (WARN_ON(!align)) + align = __alignof__(long long); + /* align @size to avoid excessive fragmentation on reserved array */ size = round_up(size, align); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 2b55222..0f1d921 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -49,6 +49,7 @@ #include <linux/fs.h> #include <linux/seq_file.h> #include <linux/vmalloc.h> +#include <linux/vmpressure.h> #include <linux/mm_inline.h> #include <linux/page_cgroup.h> #include <linux/cpu.h> @@ -152,8 +153,13 @@ struct mem_cgroup_stat_cpu { }; struct mem_cgroup_reclaim_iter { - /* css_id of the last scanned hierarchy member */ - int position; + /* + * last scanned hierarchy member. Valid only if last_dead_count + * matches memcg->dead_count of the hierarchy root group. + */ + struct mem_cgroup *last_visited; + unsigned long last_dead_count; + /* scan generation, increased every round-trip */ unsigned int generation; }; @@ -256,6 +262,9 @@ struct mem_cgroup { */ struct res_counter res; + /* vmpressure notifications */ + struct vmpressure vmpressure; + union { /* * the counter to account for mem+swap usage. @@ -335,6 +344,7 @@ struct mem_cgroup { struct mem_cgroup_stat_cpu nocpu_base; spinlock_t pcp_counter_lock; + atomic_t dead_count; #if defined(CONFIG_MEMCG_KMEM) && defined(CONFIG_INET) struct tcp_memcontrol tcp_mem; #endif @@ -353,6 +363,7 @@ struct mem_cgroup { atomic_t numainfo_events; atomic_t numainfo_updating; #endif + /* * Per cgroup active and inactive list, similar to the * per zone LRU lists. @@ -504,6 +515,24 @@ struct mem_cgroup *mem_cgroup_from_css(struct cgroup_subsys_state *s) return container_of(s, struct mem_cgroup, css); } +/* Some nice accessors for the vmpressure. */ +struct vmpressure *memcg_to_vmpressure(struct mem_cgroup *memcg) +{ + if (!memcg) + memcg = root_mem_cgroup; + return &memcg->vmpressure; +} + +struct cgroup_subsys_state *vmpressure_to_css(struct vmpressure *vmpr) +{ + return &container_of(vmpr, struct mem_cgroup, vmpressure)->css; +} + +struct vmpressure *css_to_vmpressure(struct cgroup_subsys_state *css) +{ + return &mem_cgroup_from_css(css)->vmpressure; +} + static inline bool mem_cgroup_is_root(struct mem_cgroup *memcg) { return (memcg == root_mem_cgroup); @@ -1067,6 +1096,51 @@ struct mem_cgroup *try_get_mem_cgroup_from_mm(struct mm_struct *mm) return memcg; } +/* + * Returns a next (in a pre-order walk) alive memcg (with elevated css + * ref. count) or NULL if the whole root's subtree has been visited. + * + * helper function to be used by mem_cgroup_iter + */ +static struct mem_cgroup *__mem_cgroup_iter_next(struct mem_cgroup *root, + struct mem_cgroup *last_visited) +{ + struct cgroup *prev_cgroup, *next_cgroup; + + /* + * Root is not visited by cgroup iterators so it needs an + * explicit visit. + */ + if (!last_visited) + return root; + + prev_cgroup = (last_visited == root) ? NULL + : last_visited->css.cgroup; +skip_node: + next_cgroup = cgroup_next_descendant_pre( + prev_cgroup, root->css.cgroup); + + /* + * Even if we found a group we have to make sure it is + * alive. css && !memcg means that the groups should be + * skipped and we should continue the tree walk. + * last_visited css is safe to use because it is + * protected by css_get and the tree walk is rcu safe. + */ + if (next_cgroup) { + struct mem_cgroup *mem = mem_cgroup_from_cont( + next_cgroup); + if (css_tryget(&mem->css)) + return mem; + else { + prev_cgroup = next_cgroup; + goto skip_node; + } + } + + return NULL; +} + /** * mem_cgroup_iter - iterate over memory cgroup hierarchy * @root: hierarchy root @@ -1089,7 +1163,8 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup_reclaim_cookie *reclaim) { struct mem_cgroup *memcg = NULL; - int id = 0; + struct mem_cgroup *last_visited = NULL; + unsigned long uninitialized_var(dead_count); if (mem_cgroup_disabled()) return NULL; @@ -1098,20 +1173,17 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, root = root_mem_cgroup; if (prev && !reclaim) - id = css_id(&prev->css); - - if (prev && prev != root) - css_put(&prev->css); + last_visited = prev; if (!root->use_hierarchy && root != root_mem_cgroup) { if (prev) - return NULL; + goto out_css_put; return root; } + rcu_read_lock(); while (!memcg) { struct mem_cgroup_reclaim_iter *uninitialized_var(iter); - struct cgroup_subsys_state *css; if (reclaim) { int nid = zone_to_nid(reclaim->zone); @@ -1120,31 +1192,60 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, mz = mem_cgroup_zoneinfo(root, nid, zid); iter = &mz->reclaim_iter[reclaim->priority]; - if (prev && reclaim->generation != iter->generation) - return NULL; - id = iter->position; + last_visited = iter->last_visited; + if (prev && reclaim->generation != iter->generation) { + iter->last_visited = NULL; + goto out_unlock; + } + + /* + * If the dead_count mismatches, a destruction + * has happened or is happening concurrently. + * If the dead_count matches, a destruction + * might still happen concurrently, but since + * we checked under RCU, that destruction + * won't free the object until we release the + * RCU reader lock. Thus, the dead_count + * check verifies the pointer is still valid, + * css_tryget() verifies the cgroup pointed to + * is alive. + */ + dead_count = atomic_read(&root->dead_count); + smp_rmb(); + last_visited = iter->last_visited; + if (last_visited) { + if ((dead_count != iter->last_dead_count) || + !css_tryget(&last_visited->css)) { + last_visited = NULL; + } + } } - rcu_read_lock(); - css = css_get_next(&mem_cgroup_subsys, id + 1, &root->css, &id); - if (css) { - if (css == &root->css || css_tryget(css)) - memcg = mem_cgroup_from_css(css); - } else - id = 0; - rcu_read_unlock(); + memcg = __mem_cgroup_iter_next(root, last_visited); if (reclaim) { - iter->position = id; - if (!css) + if (last_visited) + css_put(&last_visited->css); + + iter->last_visited = memcg; + smp_wmb(); + iter->last_dead_count = dead_count; + + if (!memcg) iter->generation++; else if (!prev && memcg) reclaim->generation = iter->generation; } - if (prev && !css) - return NULL; + if (prev && !memcg) + goto out_unlock; } +out_unlock: + rcu_read_unlock(); +out_css_put: + if (prev && prev != root) + css_put(&prev->css); + return memcg; } @@ -1686,11 +1787,11 @@ static void mem_cgroup_out_of_memory(struct mem_cgroup *memcg, gfp_t gfp_mask, struct task_struct *chosen = NULL; /* - * If current has a pending SIGKILL, then automatically select it. The - * goal is to allow it to allocate so that it may quickly exit and free - * its memory. + * If current has a pending SIGKILL or is exiting, then automatically + * select it. The goal is to allow it to allocate so that it may + * quickly exit and free its memory. */ - if (fatal_signal_pending(current)) { + if (fatal_signal_pending(current) || current->flags & PF_EXITING) { set_thread_flag(TIF_MEMDIE); return; } @@ -3114,12 +3215,12 @@ void memcg_release_cache(struct kmem_cache *s) root = s->memcg_params->root_cache; root->memcg_params->memcg_caches[id] = NULL; - mem_cgroup_put(memcg); mutex_lock(&memcg->slab_caches_mutex); list_del(&s->memcg_params->list); mutex_unlock(&memcg->slab_caches_mutex); + mem_cgroup_put(memcg); out: kfree(s->memcg_params); } @@ -3220,52 +3321,53 @@ void mem_cgroup_destroy_cache(struct kmem_cache *cachep) schedule_work(&cachep->memcg_params->destroy); } -static char *memcg_cache_name(struct mem_cgroup *memcg, struct kmem_cache *s) -{ - char *name; - struct dentry *dentry; - - rcu_read_lock(); - dentry = rcu_dereference(memcg->css.cgroup->dentry); - rcu_read_unlock(); - - BUG_ON(dentry == NULL); - - name = kasprintf(GFP_KERNEL, "%s(%d:%s)", s->name, - memcg_cache_id(memcg), dentry->d_name.name); - - return name; -} +/* + * This lock protects updaters, not readers. We want readers to be as fast as + * they can, and they will either see NULL or a valid cache value. Our model + * allow them to see NULL, in which case the root memcg will be selected. + * + * We need this lock because multiple allocations to the same cache from a non + * will span more than one worker. Only one of them can create the cache. + */ +static DEFINE_MUTEX(memcg_cache_mutex); +/* + * Called with memcg_cache_mutex held + */ static struct kmem_cache *kmem_cache_dup(struct mem_cgroup *memcg, struct kmem_cache *s) { - char *name; struct kmem_cache *new; + static char *tmp_name = NULL; - name = memcg_cache_name(memcg, s); - if (!name) - return NULL; + lockdep_assert_held(&memcg_cache_mutex); + + /* + * kmem_cache_create_memcg duplicates the given name and + * cgroup_name for this name requires RCU context. + * This static temporary buffer is used to prevent from + * pointless shortliving allocation. + */ + if (!tmp_name) { + tmp_name = kmalloc(PATH_MAX, GFP_KERNEL); + if (!tmp_name) + return NULL; + } + + rcu_read_lock(); + snprintf(tmp_name, PATH_MAX, "%s(%d:%s)", s->name, + memcg_cache_id(memcg), cgroup_name(memcg->css.cgroup)); + rcu_read_unlock(); - new = kmem_cache_create_memcg(memcg, name, s->object_size, s->align, + new = kmem_cache_create_memcg(memcg, tmp_name, s->object_size, s->align, (s->flags & ~SLAB_PANIC), s->ctor, s); if (new) new->allocflags |= __GFP_KMEMCG; - kfree(name); return new; } -/* - * This lock protects updaters, not readers. We want readers to be as fast as - * they can, and they will either see NULL or a valid cache value. Our model - * allow them to see NULL, in which case the root memcg will be selected. - * - * We need this lock because multiple allocations to the same cache from a non - * will span more than one worker. Only one of them can create the cache. - */ -static DEFINE_MUTEX(memcg_cache_mutex); static struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, struct kmem_cache *cachep) { @@ -3382,7 +3484,6 @@ static void memcg_create_cache_work_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. - * Called with rcu_read_lock. */ static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, struct kmem_cache *cachep) @@ -3390,12 +3491,8 @@ static void __memcg_create_cache_enqueue(struct mem_cgroup *memcg, struct create_work *cw; cw = kmalloc(sizeof(struct create_work), GFP_NOWAIT); - if (cw == NULL) - return; - - /* The corresponding put will be done in the workqueue. */ - if (!css_tryget(&memcg->css)) { - kfree(cw); + if (cw == NULL) { + css_put(&memcg->css); return; } @@ -3451,10 +3548,9 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, rcu_read_lock(); memcg = mem_cgroup_from_task(rcu_dereference(current->mm->owner)); - rcu_read_unlock(); if (!memcg_can_account_kmem(memcg)) - return cachep; + goto out; idx = memcg_cache_id(memcg); @@ -3463,29 +3559,38 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep, * code updating memcg_caches will issue a write barrier to match this. */ read_barrier_depends(); - if (unlikely(cachep->memcg_params->memcg_caches[idx] == NULL)) { - /* - * If we are in a safe context (can wait, and not in interrupt - * context), we could be be predictable and return right away. - * This would guarantee that the allocation being performed - * already belongs in the new cache. - * - * However, there are some clashes that can arrive from locking. - * For instance, because we acquire the slab_mutex while doing - * kmem_cache_dup, this means no further allocation could happen - * with the slab_mutex held. - * - * Also, because cache creation issue get_online_cpus(), this - * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex, - * that ends up reversed during cpu hotplug. (cpuset allocates - * a bunch of GFP_KERNEL memory during cpuup). Due to all that, - * better to defer everything. - */ - memcg_create_cache_enqueue(memcg, cachep); - return cachep; + if (likely(cachep->memcg_params->memcg_caches[idx])) { + cachep = cachep->memcg_params->memcg_caches[idx]; + goto out; } - return cachep->memcg_params->memcg_caches[idx]; + /* The corresponding put will be done in the workqueue. */ + if (!css_tryget(&memcg->css)) + goto out; + rcu_read_unlock(); + + /* + * If we are in a safe context (can wait, and not in interrupt + * context), we could be be predictable and return right away. + * This would guarantee that the allocation being performed + * already belongs in the new cache. + * + * However, there are some clashes that can arrive from locking. + * For instance, because we acquire the slab_mutex while doing + * kmem_cache_dup, this means no further allocation could happen + * with the slab_mutex held. + * + * Also, because cache creation issue get_online_cpus(), this + * creates a lock chain: memcg_slab_mutex -> cpu_hotplug_mutex, + * that ends up reversed during cpu hotplug. (cpuset allocates + * a bunch of GFP_KERNEL memory during cpuup). Due to all that, + * better to defer everything. + */ + memcg_create_cache_enqueue(memcg, cachep); + return cachep; +out: + rcu_read_unlock(); + return cachep; } EXPORT_SYMBOL(__memcg_kmem_get_cache); @@ -4947,9 +5052,6 @@ static ssize_t mem_cgroup_read(struct cgroup *cont, struct cftype *cft, type = MEMFILE_TYPE(cft->private); name = MEMFILE_ATTR(cft->private); - if (!do_swap_account && type == _MEMSWAP) - return -EOPNOTSUPP; - switch (type) { case _MEM: if (name == RES_USAGE) @@ -5084,9 +5186,6 @@ static int mem_cgroup_write(struct cgroup *cont, struct cftype *cft, type = MEMFILE_TYPE(cft->private); name = MEMFILE_ATTR(cft->private); - if (!do_swap_account && type == _MEMSWAP) - return -EOPNOTSUPP; - switch (name) { case RES_LIMIT: if (mem_cgroup_is_root(memcg)) { /* Can't set limit on root */ @@ -5163,9 +5262,6 @@ static int mem_cgroup_reset(struct cgroup *cont, unsigned int event) type = MEMFILE_TYPE(event); name = MEMFILE_ATTR(event); - if (!do_swap_account && type == _MEMSWAP) - return -EOPNOTSUPP; - switch (name) { case RES_MAX_USAGE: if (type == _MEM) @@ -5744,7 +5840,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) return ret; return mem_cgroup_sockets_init(memcg, ss); -}; +} static void kmem_cgroup_destroy(struct mem_cgroup *memcg) { @@ -5817,6 +5913,7 @@ static struct cftype mem_cgroup_files[] = { }, { .name = "use_hierarchy", + .flags = CFTYPE_INSANE, .write_u64 = mem_cgroup_hierarchy_write, .read_u64 = mem_cgroup_hierarchy_read, }, @@ -5838,6 +5935,11 @@ static struct cftype mem_cgroup_files[] = { .unregister_event = mem_cgroup_oom_unregister_event, .private = MEMFILE_PRIVATE(_OOM_TYPE, OOM_CONTROL), }, + { + .name = "pressure_level", + .register_event = vmpressure_register_event, + .unregister_event = vmpressure_unregister_event, + }, #ifdef CONFIG_NUMA { .name = "numa_stat", @@ -6119,6 +6221,7 @@ mem_cgroup_css_alloc(struct cgroup *cont) memcg->move_charge_at_immigrate = 0; mutex_init(&memcg->thresholds_lock); spin_lock_init(&memcg->move_lock); + vmpressure_init(&memcg->vmpressure); return &memcg->css; @@ -6184,10 +6287,29 @@ mem_cgroup_css_online(struct cgroup *cont) return error; } +/* + * Announce all parents that a group from their hierarchy is gone. + */ +static void mem_cgroup_invalidate_reclaim_iterators(struct mem_cgroup *memcg) +{ + struct mem_cgroup *parent = memcg; + + while ((parent = parent_mem_cgroup(parent))) + atomic_inc(&parent->dead_count); + + /* + * if the root memcg is not hierarchical we have to check it + * explicitely. + */ + if (!root_mem_cgroup->use_hierarchy) + atomic_inc(&root_mem_cgroup->dead_count); +} + static void mem_cgroup_css_offline(struct cgroup *cont) { struct mem_cgroup *memcg = mem_cgroup_from_cont(cont); + mem_cgroup_invalidate_reclaim_iterators(memcg); mem_cgroup_reparent_charges(memcg); mem_cgroup_destroy_all_caches(memcg); } @@ -6787,6 +6909,21 @@ static void mem_cgroup_move_task(struct cgroup *cont, } #endif +/* + * Cgroup retains root cgroups across [un]mount cycles making it necessary + * to verify sane_behavior flag on each mount attempt. + */ +static void mem_cgroup_bind(struct cgroup *root) +{ + /* + * use_hierarchy is forced with sane_behavior. cgroup core + * guarantees that @root doesn't have any children, so turning it + * on for the root memcg is enough. + */ + if (cgroup_sane_behavior(root)) + mem_cgroup_from_cont(root)->use_hierarchy = true; +} + struct cgroup_subsys mem_cgroup_subsys = { .name = "memory", .subsys_id = mem_cgroup_subsys_id, @@ -6797,6 +6934,7 @@ struct cgroup_subsys mem_cgroup_subsys = { .can_attach = mem_cgroup_can_attach, .cancel_attach = mem_cgroup_cancel_attach, .attach = mem_cgroup_move_task, + .bind = mem_cgroup_bind, .base_cftypes = mem_cgroup_files, .early_init = 0, .use_id = 1, diff --git a/mm/memory-failure.c b/mm/memory-failure.c index df0694c..ceb0c7f 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -785,10 +785,10 @@ static struct page_state { { sc|dirty, sc, "clean swapcache", me_swapcache_clean }, { mlock|dirty, mlock|dirty, "dirty mlocked LRU", me_pagecache_dirty }, - { mlock, mlock, "clean mlocked LRU", me_pagecache_clean }, + { mlock|dirty, mlock, "clean mlocked LRU", me_pagecache_clean }, { unevict|dirty, unevict|dirty, "dirty unevictable LRU", me_pagecache_dirty }, - { unevict, unevict, "clean unevictable LRU", me_pagecache_clean }, + { unevict|dirty, unevict, "clean unevictable LRU", me_pagecache_clean }, { lru|dirty, lru|dirty, "dirty LRU", me_pagecache_dirty }, { lru|dirty, lru, "clean LRU", me_pagecache_clean }, diff --git a/mm/memory.c b/mm/memory.c index 13cbc42..f7a1fba 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -2393,6 +2393,53 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(remap_pfn_range); +/** + * vm_iomap_memory - remap memory to userspace + * @vma: user vma to map to + * @start: start of area + * @len: size of area + * + * This is a simplified io_remap_pfn_range() for common driver use. The + * driver just needs to give us the physical memory range to be mapped, + * we'll figure out the rest from the vma information. + * + * NOTE! Some drivers might want to tweak vma->vm_page_prot first to get + * whatever write-combining details or similar. + */ +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long vm_len, pfn, pages; + + /* Check that the physical memory area passed in looks valid */ + if (start + len < start) + return -EINVAL; + /* + * You *really* shouldn't map things that aren't page-aligned, + * but we've historically allowed it because IO memory might + * just have smaller alignment. + */ + len += start & ~PAGE_MASK; + pfn = start >> PAGE_SHIFT; + pages = (len + ~PAGE_MASK) >> PAGE_SHIFT; + if (pfn + pages < pfn) + return -EINVAL; + + /* We start the mapping 'vm_pgoff' pages into the area */ + if (vma->vm_pgoff > pages) + return -EINVAL; + pfn += vma->vm_pgoff; + pages -= vma->vm_pgoff; + + /* Can we fit all of the mapping? */ + vm_len = vma->vm_end - vma->vm_start; + if (vm_len >> PAGE_SHIFT > pages) + return -EINVAL; + + /* Ok, let it rip */ + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + static int apply_to_pte_range(struct mm_struct *mm, pmd_t *pmd, unsigned long addr, unsigned long end, pte_fn_t fn, void *data) @@ -3197,6 +3244,11 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, page = alloc_zeroed_user_highpage_movable(vma, address); if (!page) goto oom; + /* + * The memory barrier inside __SetPageUptodate makes sure that + * preceeding stores to the page contents become visible before + * the set_pte_at() write. + */ __SetPageUptodate(page); if (mem_cgroup_newpage_charge(page, mm, GFP_KERNEL)) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index ee37657..a221fac 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -436,6 +436,40 @@ static int __meminit __add_section(int nid, struct zone *zone, return register_new_memory(nid, __pfn_to_section(phys_start_pfn)); } +/* + * Reasonably generic function for adding memory. It is + * expected that archs that support memory hotplug will + * call this function after deciding the zone to which to + * add the new pages. + */ +int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, + unsigned long nr_pages) +{ + unsigned long i; + int err = 0; + int start_sec, end_sec; + /* during initialize mem_map, align hot-added range to section */ + start_sec = pfn_to_section_nr(phys_start_pfn); + end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); + + for (i = start_sec; i <= end_sec; i++) { + err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); + + /* + * EEXIST is finally dealt with by ioresource collision + * check. see add_memory() => register_memory_resource() + * Warning will be printed if there is collision. + */ + if (err && (err != -EEXIST)) + break; + err = 0; + } + + return err; +} +EXPORT_SYMBOL_GPL(__add_pages); + +#ifdef CONFIG_MEMORY_HOTREMOVE /* find the smallest valid pfn in the range [start_pfn, end_pfn) */ static int find_smallest_section_pfn(int nid, struct zone *zone, unsigned long start_pfn, @@ -658,39 +692,6 @@ static int __remove_section(struct zone *zone, struct mem_section *ms) return 0; } -/* - * Reasonably generic function for adding memory. It is - * expected that archs that support memory hotplug will - * call this function after deciding the zone to which to - * add the new pages. - */ -int __ref __add_pages(int nid, struct zone *zone, unsigned long phys_start_pfn, - unsigned long nr_pages) -{ - unsigned long i; - int err = 0; - int start_sec, end_sec; - /* during initialize mem_map, align hot-added range to section */ - start_sec = pfn_to_section_nr(phys_start_pfn); - end_sec = pfn_to_section_nr(phys_start_pfn + nr_pages - 1); - - for (i = start_sec; i <= end_sec; i++) { - err = __add_section(nid, zone, i << PFN_SECTION_SHIFT); - - /* - * EEXIST is finally dealt with by ioresource collision - * check. see add_memory() => register_memory_resource() - * Warning will be printed if there is collision. - */ - if (err && (err != -EEXIST)) - break; - err = 0; - } - - return err; -} -EXPORT_SYMBOL_GPL(__add_pages); - /** * __remove_pages() - remove sections of pages from a zone * @zone: zone from which pages need to be removed @@ -705,8 +706,10 @@ EXPORT_SYMBOL_GPL(__add_pages); int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, unsigned long nr_pages) { - unsigned long i, ret = 0; + unsigned long i; int sections_to_remove; + resource_size_t start, size; + int ret = 0; /* * We can only remove entire sections @@ -714,7 +717,12 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, BUG_ON(phys_start_pfn & ~PAGE_SECTION_MASK); BUG_ON(nr_pages % PAGES_PER_SECTION); - release_mem_region(phys_start_pfn << PAGE_SHIFT, nr_pages * PAGE_SIZE); + start = phys_start_pfn << PAGE_SHIFT; + size = nr_pages * PAGE_SIZE; + ret = release_mem_region_adjustable(&iomem_resource, start, size); + if (ret) + pr_warn("Unable to release resource <%016llx-%016llx> (%d)\n", + start, start + size - 1, ret); sections_to_remove = nr_pages / PAGES_PER_SECTION; for (i = 0; i < sections_to_remove; i++) { @@ -726,6 +734,7 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, return ret; } EXPORT_SYMBOL_GPL(__remove_pages); +#endif /* CONFIG_MEMORY_HOTREMOVE */ int set_online_page_callback(online_page_callback_t callback) { @@ -1613,7 +1622,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) /** * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn) * @start_pfn: start pfn of the memory range - * @end_pfn: end pft of the memory range + * @end_pfn: end pfn of the memory range * @arg: argument passed to func * @func: callback for each memory section walked * @@ -1681,11 +1690,15 @@ static int is_memblock_offlined_cb(struct memory_block *mem, void *arg) { int ret = !is_memblock_offlined(mem); - if (unlikely(ret)) + if (unlikely(ret)) { + phys_addr_t beginpa, endpa; + + beginpa = PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)); + endpa = PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1; pr_warn("removing memory fails, because memory " - "[%#010llx-%#010llx] is onlined\n", - PFN_PHYS(section_nr_to_pfn(mem->start_section_nr)), - PFN_PHYS(section_nr_to_pfn(mem->end_section_nr + 1))-1); + "[%pa-%pa] is onlined\n", + &beginpa, &endpa); + } return ret; } diff --git a/mm/migrate.c b/mm/migrate.c index 3bbaf5d..27ed225 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -736,7 +736,7 @@ static int __unmap_and_move(struct page *page, struct page *newpage, if (PageWriteback(page)) { /* - * Only in the case of a full syncronous migration is it + * Only in the case of a full synchronous migration is it * necessary to wait for PageWriteback. In the async case, * the retry loop is too short and in the sync-light case, * the overhead of stalling is too much @@ -973,19 +973,23 @@ out: } /* - * migrate_pages + * migrate_pages - migrate the pages specified in a list, to the free pages + * supplied as the target for the page migration * - * The function takes one list of pages to migrate and a function - * that determines from the page to be migrated and the private data - * the target of the move and allocates the page. + * @from: The list of pages to be migrated. + * @get_new_page: The function used to allocate free pages to be used + * as the target of the page migration. + * @private: Private data to be passed on to get_new_page() + * @mode: The migration mode that specifies the constraints for + * page migration, if any. + * @reason: The reason for page migration. * - * The function returns after 10 attempts or if no pages - * are movable anymore because to has become empty - * or no retryable pages exist anymore. - * Caller should call putback_lru_pages to return pages to the LRU + * The function returns after 10 attempts or if no pages are movable any more + * because the list has become empty or no retryable pages exist any more. + * The caller should call putback_lru_pages() to return pages to the LRU * or free list only if ret != 0. * - * Return: Number of pages not migrated or error code. + * Returns the number of pages that were not migrated, or an error code. */ int migrate_pages(struct list_head *from, new_page_t get_new_page, unsigned long private, enum migrate_mode mode, int reason) @@ -6,6 +6,7 @@ * Address space accounting code <alan@lxorguk.ukuu.org.uk> */ +#include <linux/kernel.h> #include <linux/slab.h> #include <linux/backing-dev.h> #include <linux/mm.h> @@ -33,6 +34,8 @@ #include <linux/uprobes.h> #include <linux/rbtree_augmented.h> #include <linux/sched/sysctl.h> +#include <linux/notifier.h> +#include <linux/memory.h> #include <asm/uaccess.h> #include <asm/cacheflush.h> @@ -84,6 +87,8 @@ EXPORT_SYMBOL(vm_get_page_prot); int sysctl_overcommit_memory __read_mostly = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio __read_mostly = 50; /* default is 50% */ int sysctl_max_map_count __read_mostly = DEFAULT_MAX_MAP_COUNT; +unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ +unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ /* * Make sure vm_committed_as in one cacheline and not cacheline shared with * other variables. It can be updated by several CPUs frequently. @@ -122,7 +127,7 @@ EXPORT_SYMBOL_GPL(vm_memory_committed); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed; + unsigned long free, allowed, reserve; vm_acct_memory(pages); @@ -163,10 +168,10 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) free -= totalreserve_pages; /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - free -= free / 32; + free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); if (free > pages) return 0; @@ -177,16 +182,19 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) allowed = (totalram_pages - hugetlb_total_pages()) * sysctl_overcommit_ratio / 100; /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - allowed -= allowed / 32; + allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); allowed += total_swap_pages; - /* Don't let a single process grow too big: - leave 3% of the size of this process for other processes */ - if (mm) - allowed -= mm->total_vm / 32; + /* + * Don't let a single process grow so big a user can't recover + */ + if (mm) { + reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + allowed -= min(mm->total_vm / 32, reserve); + } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; @@ -543,6 +551,34 @@ static int find_vma_links(struct mm_struct *mm, unsigned long addr, return 0; } +static unsigned long count_vma_pages_range(struct mm_struct *mm, + unsigned long addr, unsigned long end) +{ + unsigned long nr_pages = 0; + struct vm_area_struct *vma; + + /* Find first overlaping mapping */ + vma = find_vma_intersection(mm, addr, end); + if (!vma) + return 0; + + nr_pages = (min(end, vma->vm_end) - + max(addr, vma->vm_start)) >> PAGE_SHIFT; + + /* Iterate over the rest of the overlaps */ + for (vma = vma->vm_next; vma; vma = vma->vm_next) { + unsigned long overlap_len; + + if (vma->vm_start > end) + break; + + overlap_len = min(end, vma->vm_end) - vma->vm_start; + nr_pages += overlap_len >> PAGE_SHIFT; + } + + return nr_pages; +} + void __vma_link_rb(struct mm_struct *mm, struct vm_area_struct *vma, struct rb_node **rb_link, struct rb_node *rb_parent) { @@ -829,7 +865,7 @@ again: remove_next = 1 + (end > next->vm_end); if (next->anon_vma) anon_vma_merge(vma, next); mm->map_count--; - mpol_put(vma_policy(next)); + vma_set_policy(vma, vma_policy(next)); kmem_cache_free(vm_area_cachep, next); /* * In mprotect's case 6 (see comments on vma_merge), @@ -1435,6 +1471,23 @@ unsigned long mmap_region(struct file *file, unsigned long addr, unsigned long charged = 0; struct inode *inode = file ? file_inode(file) : NULL; + /* Check against address space limit. */ + if (!may_expand_vm(mm, len >> PAGE_SHIFT)) { + unsigned long nr_pages; + + /* + * MAP_FIXED may remove pages of mappings that intersects with + * requested mapping. Account for the pages it would unmap. + */ + if (!(vm_flags & MAP_FIXED)) + return -ENOMEM; + + nr_pages = count_vma_pages_range(mm, addr, addr + len); + + if (!may_expand_vm(mm, (len >> PAGE_SHIFT) - nr_pages)) + return -ENOMEM; + } + /* Clear old maps */ error = -ENOMEM; munmap_back: @@ -1444,10 +1497,6 @@ munmap_back: goto munmap_back; } - /* Check against address space limit. */ - if (!may_expand_vm(mm, len >> PAGE_SHIFT)) - return -ENOMEM; - /* * Private writable mapping: check memory availability */ @@ -1935,9 +1984,6 @@ struct vm_area_struct *find_vma(struct mm_struct *mm, unsigned long addr) { struct vm_area_struct *vma = NULL; - if (WARN_ON_ONCE(!mm)) /* Remove this in linux-3.6 */ - return NULL; - /* Check the cache first. */ /* (Cache hit rate is typically around 35%.) */ vma = ACCESS_ONCE(mm->mmap_cache); @@ -2305,7 +2351,7 @@ static void unmap_region(struct mm_struct *mm, update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, - next ? next->vm_start : 0); + next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); } @@ -2685,7 +2731,7 @@ void exit_mmap(struct mm_struct *mm) /* Use -1 here to ensure all VMAs in the mm are unmapped */ unmap_vmas(&tlb, vma, 0, -1); - free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, 0); + free_pgtables(&tlb, vma, FIRST_USER_ADDRESS, USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, 0, -1); /* @@ -3097,3 +3143,115 @@ void __init mmap_init(void) ret = percpu_counter_init(&vm_committed_as, 0); VM_BUG_ON(ret); } + +/* + * Initialise sysctl_user_reserve_kbytes. + * + * This is intended to prevent a user from starting a single memory hogging + * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER + * mode. + * + * The default value is min(3% of free memory, 128MB) + * 128MB is enough to recover with sshd/login, bash, and top/kill. + */ +static int init_user_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); + return 0; +} +module_init(init_user_reserve) + +/* + * Initialise sysctl_admin_reserve_kbytes. + * + * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin + * to log in and kill a memory hogging process. + * + * Systems with more than 256MB will reserve 8MB, enough to recover + * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will + * only reserve 3% of free pages by default. + */ +static int init_admin_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); + return 0; +} +module_init(init_admin_reserve) + +/* + * Reinititalise user and admin reserves if memory is added or removed. + * + * The default user reserve max is 128MB, and the default max for the + * admin reserve is 8MB. These are usually, but not always, enough to + * enable recovery from a memory hogging process using login/sshd, a shell, + * and tools like top. It may make sense to increase or even disable the + * reserve depending on the existence of swap or variations in the recovery + * tools. So, the admin may have changed them. + * + * If memory is added and the reserves have been eliminated or increased above + * the default max, then we'll trust the admin. + * + * If memory is removed and there isn't enough free memory, then we + * need to reset the reserves. + * + * Otherwise keep the reserve set by the admin. + */ +static int reserve_mem_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + unsigned long tmp, free_kbytes; + + switch (action) { + case MEM_ONLINE: + /* Default max is 128MB. Leave alone if modified by operator. */ + tmp = sysctl_user_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 17)) + init_user_reserve(); + + /* Default max is 8MB. Leave alone if modified by operator. */ + tmp = sysctl_admin_reserve_kbytes; + if (0 < tmp && tmp < (1UL << 13)) + init_admin_reserve(); + + break; + case MEM_OFFLINE: + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + if (sysctl_user_reserve_kbytes > free_kbytes) { + init_user_reserve(); + pr_info("vm.user_reserve_kbytes reset to %lu\n", + sysctl_user_reserve_kbytes); + } + + if (sysctl_admin_reserve_kbytes > free_kbytes) { + init_admin_reserve(); + pr_info("vm.admin_reserve_kbytes reset to %lu\n", + sysctl_admin_reserve_kbytes); + } + break; + default: + break; + } + return NOTIFY_OK; +} + +static struct notifier_block reserve_mem_nb = { + .notifier_call = reserve_mem_notifier, +}; + +static int __meminit init_reserve_notifier(void) +{ + if (register_hotmemory_notifier(&reserve_mem_nb)) + printk("Failed registering memory add/remove notifier for admin reserve"); + + return 0; +} +module_init(init_reserve_notifier) diff --git a/mm/nobootmem.c b/mm/nobootmem.c index 5e07d36..bdd3fa2 100644 --- a/mm/nobootmem.c +++ b/mm/nobootmem.c @@ -45,9 +45,9 @@ static void * __init __alloc_memory_core_early(int nid, u64 size, u64 align, if (!addr) return NULL; + memblock_reserve(addr, size); ptr = phys_to_virt(addr); memset(ptr, 0, size); - memblock_reserve(addr, size); /* * The min_count is set to 0 so that bootmem allocated blocks * are never reported as leaks. @@ -120,7 +120,7 @@ static unsigned long __init __free_memory_core(phys_addr_t start, return end_pfn - start_pfn; } -unsigned long __init free_low_memory_core_early(int nodeid) +static unsigned long __init free_low_memory_core_early(void) { unsigned long count = 0; phys_addr_t start, end, size; @@ -170,7 +170,7 @@ unsigned long __init free_all_bootmem(void) * because in some case like Node0 doesn't have RAM installed * low ram will be on Node1 */ - return free_low_memory_core_early(MAX_NUMNODES); + return free_low_memory_core_early(); } /** @@ -63,6 +63,8 @@ int sysctl_overcommit_memory = OVERCOMMIT_GUESS; /* heuristic overcommit */ int sysctl_overcommit_ratio = 50; /* default is 50% */ int sysctl_max_map_count = DEFAULT_MAX_MAP_COUNT; int sysctl_nr_trim_pages = CONFIG_NOMMU_INITIAL_TRIM_EXCESS; +unsigned long sysctl_user_reserve_kbytes __read_mostly = 1UL << 17; /* 128MB */ +unsigned long sysctl_admin_reserve_kbytes __read_mostly = 1UL << 13; /* 8MB */ int heap_stack_gap = 0; atomic_long_t mmap_pages_allocated; @@ -228,8 +230,7 @@ int follow_pfn(struct vm_area_struct *vma, unsigned long address, } EXPORT_SYMBOL(follow_pfn); -DEFINE_RWLOCK(vmlist_lock); -struct vm_struct *vmlist; +LIST_HEAD(vmap_area_list); void vfree(const void *addr) { @@ -1838,6 +1839,16 @@ int remap_pfn_range(struct vm_area_struct *vma, unsigned long addr, } EXPORT_SYMBOL(remap_pfn_range); +int vm_iomap_memory(struct vm_area_struct *vma, phys_addr_t start, unsigned long len) +{ + unsigned long pfn = start >> PAGE_SHIFT; + unsigned long vm_len = vma->vm_end - vma->vm_start; + + pfn += vma->vm_pgoff; + return io_remap_pfn_range(vma, vma->vm_start, pfn, vm_len, vma->vm_page_prot); +} +EXPORT_SYMBOL(vm_iomap_memory); + int remap_vmalloc_range(struct vm_area_struct *vma, void *addr, unsigned long pgoff) { @@ -1888,7 +1899,7 @@ EXPORT_SYMBOL(unmap_mapping_range); */ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) { - unsigned long free, allowed; + unsigned long free, allowed, reserve; vm_acct_memory(pages); @@ -1929,10 +1940,10 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) free -= totalreserve_pages; /* - * Leave the last 3% for root + * Reserve some for root */ if (!cap_sys_admin) - free -= free / 32; + free -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); if (free > pages) return 0; @@ -1942,16 +1953,19 @@ int __vm_enough_memory(struct mm_struct *mm, long pages, int cap_sys_admin) allowed = totalram_pages * sysctl_overcommit_ratio / 100; /* - * Leave the last 3% for root + * Reserve some 3% for root */ if (!cap_sys_admin) - allowed -= allowed / 32; + allowed -= sysctl_admin_reserve_kbytes >> (PAGE_SHIFT - 10); allowed += total_swap_pages; - /* Don't let a single process grow too big: - leave 3% of the size of this process for other processes */ - if (mm) - allowed -= mm->total_vm / 32; + /* + * Don't let a single process grow so big a user can't recover + */ + if (mm) { + reserve = sysctl_user_reserve_kbytes >> (PAGE_SHIFT - 10); + allowed -= min(mm->total_vm / 32, reserve); + } if (percpu_counter_read_positive(&vm_committed_as) < allowed) return 0; @@ -2113,3 +2127,45 @@ int nommu_shrink_inode_mappings(struct inode *inode, size_t size, up_write(&nommu_region_sem); return 0; } + +/* + * Initialise sysctl_user_reserve_kbytes. + * + * This is intended to prevent a user from starting a single memory hogging + * process, such that they cannot recover (kill the hog) in OVERCOMMIT_NEVER + * mode. + * + * The default value is min(3% of free memory, 128MB) + * 128MB is enough to recover with sshd/login, bash, and top/kill. + */ +static int __meminit init_user_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_user_reserve_kbytes = min(free_kbytes / 32, 1UL << 17); + return 0; +} +module_init(init_user_reserve) + +/* + * Initialise sysctl_admin_reserve_kbytes. + * + * The purpose of sysctl_admin_reserve_kbytes is to allow the sys admin + * to log in and kill a memory hogging process. + * + * Systems with more than 256MB will reserve 8MB, enough to recover + * with sshd, bash, and top in OVERCOMMIT_GUESS. Smaller systems will + * only reserve 3% of free pages by default. + */ +static int __meminit init_admin_reserve(void) +{ + unsigned long free_kbytes; + + free_kbytes = global_page_state(NR_FREE_PAGES) << (PAGE_SHIFT - 10); + + sysctl_admin_reserve_kbytes = min(free_kbytes / 32, 1UL << 13); + return 0; +} +module_init(init_admin_reserve) diff --git a/mm/page-writeback.c b/mm/page-writeback.c index efe6814..4514ad7 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -2311,10 +2311,6 @@ void wait_for_stable_page(struct page *page) if (!bdi_cap_stable_pages_required(bdi)) return; -#ifdef CONFIG_NEED_BOUNCE_POOL - if (mapping->host->i_sb->s_flags & MS_SNAP_STABLE) - return; -#endif /* CONFIG_NEED_BOUNCE_POOL */ wait_on_page_writeback(page); } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 8fcced7..98cbdf6 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -58,6 +58,7 @@ #include <linux/prefetch.h> #include <linux/migrate.h> #include <linux/page-debug-flags.h> +#include <linux/hugetlb.h> #include <linux/sched/rt.h> #include <asm/tlbflush.h> @@ -1397,6 +1398,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); } +EXPORT_SYMBOL_GPL(split_page); static int __isolate_free_page(struct page *page, unsigned int order) { @@ -1940,9 +1942,24 @@ zonelist_scan: continue; default: /* did we reclaim enough */ - if (!zone_watermark_ok(zone, order, mark, + if (zone_watermark_ok(zone, order, mark, classzone_idx, alloc_flags)) + goto try_this_zone; + + /* + * Failed to reclaim enough to meet watermark. + * Only mark the zone full if checking the min + * watermark or if we failed to reclaim just + * 1<<order pages or else the page allocator + * fastpath will prematurely mark zones full + * when the watermark is between the low and + * min watermarks. + */ + if (((alloc_flags & ALLOC_WMARK_MASK) == ALLOC_WMARK_MIN) || + ret == ZONE_RECLAIM_SOME) goto this_zone_full; + + continue; } } @@ -2002,6 +2019,13 @@ void warn_alloc_failed(gfp_t gfp_mask, int order, const char *fmt, ...) return; /* + * Walking all memory to count page types is very expensive and should + * be inhibited in non-blockable contexts. + */ + if (!(gfp_mask & __GFP_WAIT)) + filter |= SHOW_MEM_FILTER_PAGE_COUNT; + + /* * This documents exceptions given to allocations in certain * contexts that are allowed to allocate outside current's set * of allowed nodes. @@ -3105,6 +3129,8 @@ void show_free_areas(unsigned int filter) printk("= %lukB\n", K(total)); } + hugetlb_show_meminfo(); + printk("%ld total pagecache pages\n", global_page_state(NR_FILE_PAGES)); show_swap_cache_info(); @@ -4161,10 +4187,23 @@ int __meminit __early_pfn_to_nid(unsigned long pfn) { unsigned long start_pfn, end_pfn; int i, nid; + /* + * NOTE: The following SMP-unsafe globals are only used early in boot + * when the kernel is running single-threaded. + */ + static unsigned long __meminitdata last_start_pfn, last_end_pfn; + static int __meminitdata last_nid; + + if (last_start_pfn <= pfn && pfn < last_end_pfn) + return last_nid; for_each_mem_pfn_range(i, MAX_NUMNODES, &start_pfn, &end_pfn, &nid) - if (start_pfn <= pfn && pfn < end_pfn) + if (start_pfn <= pfn && pfn < end_pfn) { + last_start_pfn = start_pfn; + last_end_pfn = end_pfn; + last_nid = nid; return nid; + } /* This is a memory hole */ return -1; } @@ -4710,7 +4749,7 @@ void __paginginit free_area_init_node(int nid, unsigned long *zones_size, /* * Figure out the number of possible node ids. */ -static void __init setup_nr_node_ids(void) +void __init setup_nr_node_ids(void) { unsigned int node; unsigned int highest = 0; @@ -4719,10 +4758,6 @@ static void __init setup_nr_node_ids(void) highest = node; nr_node_ids = highest + 1; } -#else -static inline void setup_nr_node_ids(void) -{ -} #endif /** @@ -5113,6 +5148,35 @@ early_param("movablecore", cmdline_parse_movablecore); #endif /* CONFIG_HAVE_MEMBLOCK_NODE_MAP */ +unsigned long free_reserved_area(unsigned long start, unsigned long end, + int poison, char *s) +{ + unsigned long pages, pos; + + pos = start = PAGE_ALIGN(start); + end &= PAGE_MASK; + for (pages = 0; pos < end; pos += PAGE_SIZE, pages++) { + if (poison) + memset((void *)pos, poison, PAGE_SIZE); + free_reserved_page(virt_to_page(pos)); + } + + if (pages && s) + pr_info("Freeing %s memory: %ldK (%lx - %lx)\n", + s, pages << (PAGE_SHIFT - 10), start, end); + + return pages; +} + +#ifdef CONFIG_HIGHMEM +void free_highmem_page(struct page *page) +{ + __free_reserved_page(page); + totalram_pages++; + totalhigh_pages++; +} +#endif + /** * set_dma_reserve - set the specified number of pages reserved in the first zone * @new_dma_reserve: The number of pages to mark reserved diff --git a/mm/page_io.c b/mm/page_io.c index 78eee32..bb5d752 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -42,7 +42,7 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, return bio; } -static void end_swap_bio_write(struct bio *bio, int err) +void end_swap_bio_write(struct bio *bio, int err) { const int uptodate = test_bit(BIO_UPTODATE, &bio->bi_flags); struct page *page = bio->bi_io_vec[0].bv_page; @@ -185,9 +185,7 @@ bad_bmap: */ int swap_writepage(struct page *page, struct writeback_control *wbc) { - struct bio *bio; - int ret = 0, rw = WRITE; - struct swap_info_struct *sis = page_swap_info(page); + int ret = 0; if (try_to_free_swap(page)) { unlock_page(page); @@ -199,6 +197,17 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) end_page_writeback(page); goto out; } + ret = __swap_writepage(page, wbc, end_swap_bio_write); +out: + return ret; +} + +int __swap_writepage(struct page *page, struct writeback_control *wbc, + void (*end_write_func)(struct bio *, int)) +{ + struct bio *bio; + int ret = 0, rw = WRITE; + struct swap_info_struct *sis = page_swap_info(page); if (sis->flags & SWP_FILE) { struct kiocb kiocb; @@ -214,6 +223,7 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) kiocb.ki_left = PAGE_SIZE; kiocb.ki_nbytes = PAGE_SIZE; + set_page_writeback(page); unlock_page(page); ret = mapping->a_ops->direct_IO(KERNEL_WRITE, &kiocb, &iov, @@ -222,11 +232,27 @@ int swap_writepage(struct page *page, struct writeback_control *wbc) if (ret == PAGE_SIZE) { count_vm_event(PSWPOUT); ret = 0; + } else { + /* + * In the case of swap-over-nfs, this can be a + * temporary failure if the system has limited + * memory for allocating transmit buffers. + * Mark the page dirty and avoid + * rotate_reclaimable_page but rate-limit the + * messages but do not flag PageError like + * the normal direct-to-bio case as it could + * be temporary. + */ + set_page_dirty(page); + ClearPageReclaim(page); + pr_err_ratelimited("Write error on dio swapfile (%Lu)\n", + page_file_offset(page)); } + end_page_writeback(page); return ret; } - bio = get_swap_bio(GFP_NOIO, page, end_swap_bio_write); + bio = get_swap_bio(GFP_NOIO, page, end_write_func); if (bio == NULL) { set_page_dirty(page); unlock_page(page); @@ -1513,6 +1513,9 @@ static int try_to_unmap_file(struct page *page, enum ttu_flags flags) unsigned long max_nl_size = 0; unsigned int mapcount; + if (PageHuge(page)) + pgoff = page->index << compound_order(page); + mutex_lock(&mapping->i_mmap_mutex); vma_interval_tree_foreach(vma, &mapping->i_mmap, pgoff, pgoff) { unsigned long address = vma_address(page, vma); @@ -25,6 +25,7 @@ #include <linux/init.h> #include <linux/vfs.h> #include <linux/mount.h> +#include <linux/ramfs.h> #include <linux/pagemap.h> #include <linux/file.h> #include <linux/mm.h> @@ -2830,8 +2831,6 @@ out4: * effectively equivalent, but much lighter weight. */ -#include <linux/ramfs.h> - static struct file_system_type shmem_fs_type = { .name = "tmpfs", .mount = ramfs_mount, @@ -2931,11 +2930,9 @@ struct file *shmem_file_setup(const char *name, loff_t size, unsigned long flags d_instantiate(path.dentry, inode); inode->i_size = size; clear_nlink(inode); /* It is unlinked */ -#ifndef CONFIG_MMU res = ERR_PTR(ramfs_nommu_expand_for_mapping(inode, size)); if (IS_ERR(res)) goto put_dentry; -#endif res = alloc_file(&path, FMODE_WRITE | FMODE_READ, &shmem_file_operations); @@ -18,6 +18,7 @@ #include <linux/slab.h> #include "slab.h" #include <linux/proc_fs.h> +#include <linux/notifier.h> #include <linux/seq_file.h> #include <linux/kmemcheck.h> #include <linux/cpu.h> @@ -3483,7 +3484,6 @@ int kmem_cache_shrink(struct kmem_cache *s) } EXPORT_SYMBOL(kmem_cache_shrink); -#if defined(CONFIG_MEMORY_HOTPLUG) static int slab_mem_going_offline_callback(void *arg) { struct kmem_cache *s; @@ -3598,7 +3598,10 @@ static int slab_memory_callback(struct notifier_block *self, return ret; } -#endif /* CONFIG_MEMORY_HOTPLUG */ +static struct notifier_block slab_memory_callback_nb = { + .notifier_call = slab_memory_callback, + .priority = SLAB_CALLBACK_PRI, +}; /******************************************************************** * Basic setup of slabs @@ -3651,7 +3654,7 @@ void __init kmem_cache_init(void) create_boot_cache(kmem_cache_node, "kmem_cache_node", sizeof(struct kmem_cache_node), SLAB_HWCACHE_ALIGN); - hotplug_memory_notifier(slab_memory_callback, SLAB_CALLBACK_PRI); + register_hotmemory_notifier(&slab_memory_callback_nb); /* Able to allocate the per node structures */ slab_state = PARTIAL; diff --git a/mm/sparse-vmemmap.c b/mm/sparse-vmemmap.c index 1b7e22a..27eeab3 100644 --- a/mm/sparse-vmemmap.c +++ b/mm/sparse-vmemmap.c @@ -53,10 +53,12 @@ void * __meminit vmemmap_alloc_block(unsigned long size, int node) struct page *page; if (node_state(node, N_HIGH_MEMORY)) - page = alloc_pages_node(node, - GFP_KERNEL | __GFP_ZERO, get_order(size)); + page = alloc_pages_node( + node, GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, + get_order(size)); else - page = alloc_pages(GFP_KERNEL | __GFP_ZERO, + page = alloc_pages( + GFP_KERNEL | __GFP_ZERO | __GFP_REPEAT, get_order(size)); if (page) return page_address(page); @@ -145,11 +147,10 @@ pgd_t * __meminit vmemmap_pgd_populate(unsigned long addr, int node) return pgd; } -int __meminit vmemmap_populate_basepages(struct page *start_page, - unsigned long size, int node) +int __meminit vmemmap_populate_basepages(unsigned long start, + unsigned long end, int node) { - unsigned long addr = (unsigned long)start_page; - unsigned long end = (unsigned long)(start_page + size); + unsigned long addr = start; pgd_t *pgd; pud_t *pud; pmd_t *pmd; @@ -176,9 +177,15 @@ int __meminit vmemmap_populate_basepages(struct page *start_page, struct page * __meminit sparse_mem_map_populate(unsigned long pnum, int nid) { - struct page *map = pfn_to_page(pnum * PAGES_PER_SECTION); - int error = vmemmap_populate(map, PAGES_PER_SECTION, nid); - if (error) + unsigned long start; + unsigned long end; + struct page *map; + + map = pfn_to_page(pnum * PAGES_PER_SECTION); + start = (unsigned long)map; + end = (unsigned long)(map + PAGES_PER_SECTION); + + if (vmemmap_populate(start, end, nid)) return NULL; return map; diff --git a/mm/sparse.c b/mm/sparse.c index 7ca6dc8..1c91f0d3 100644 --- a/mm/sparse.c +++ b/mm/sparse.c @@ -615,12 +615,20 @@ static inline struct page *kmalloc_section_memmap(unsigned long pnum, int nid, } static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) { - vmemmap_free(memmap, nr_pages); + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + + vmemmap_free(start, end); } +#ifdef CONFIG_MEMORY_HOTREMOVE static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) { - vmemmap_free(memmap, nr_pages); + unsigned long start = (unsigned long)memmap; + unsigned long end = (unsigned long)(memmap + nr_pages); + + vmemmap_free(start, end); } +#endif /* CONFIG_MEMORY_HOTREMOVE */ #else static struct page *__kmalloc_section_memmap(unsigned long nr_pages) { @@ -658,6 +666,7 @@ static void __kfree_section_memmap(struct page *memmap, unsigned long nr_pages) get_order(sizeof(struct page) * nr_pages)); } +#ifdef CONFIG_MEMORY_HOTREMOVE static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) { unsigned long maps_section_nr, removing_section_nr, i; @@ -684,40 +693,9 @@ static void free_map_bootmem(struct page *memmap, unsigned long nr_pages) put_page_bootmem(page); } } +#endif /* CONFIG_MEMORY_HOTREMOVE */ #endif /* CONFIG_SPARSEMEM_VMEMMAP */ -static void free_section_usemap(struct page *memmap, unsigned long *usemap) -{ - struct page *usemap_page; - unsigned long nr_pages; - - if (!usemap) - return; - - usemap_page = virt_to_page(usemap); - /* - * Check to see if allocation came from hot-plug-add - */ - if (PageSlab(usemap_page) || PageCompound(usemap_page)) { - kfree(usemap); - if (memmap) - __kfree_section_memmap(memmap, PAGES_PER_SECTION); - return; - } - - /* - * The usemap came from bootmem. This is packed with other usemaps - * on the section which has pgdat at boot time. Just keep it as is now. - */ - - if (memmap) { - nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) - >> PAGE_SHIFT; - - free_map_bootmem(memmap, nr_pages); - } -} - /* * returns the number of sections whose mem_maps were properly * set. If this is <=0, then that means that the passed-in @@ -794,6 +772,39 @@ static inline void clear_hwpoisoned_pages(struct page *memmap, int nr_pages) } #endif +#ifdef CONFIG_MEMORY_HOTREMOVE +static void free_section_usemap(struct page *memmap, unsigned long *usemap) +{ + struct page *usemap_page; + unsigned long nr_pages; + + if (!usemap) + return; + + usemap_page = virt_to_page(usemap); + /* + * Check to see if allocation came from hot-plug-add + */ + if (PageSlab(usemap_page) || PageCompound(usemap_page)) { + kfree(usemap); + if (memmap) + __kfree_section_memmap(memmap, PAGES_PER_SECTION); + return; + } + + /* + * The usemap came from bootmem. This is packed with other usemaps + * on the section which has pgdat at boot time. Just keep it as is now. + */ + + if (memmap) { + nr_pages = PAGE_ALIGN(PAGES_PER_SECTION * sizeof(struct page)) + >> PAGE_SHIFT; + + free_map_bootmem(memmap, nr_pages); + } +} + void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) { struct page *memmap = NULL; @@ -813,4 +824,5 @@ void sparse_remove_one_section(struct zone *zone, struct mem_section *ms) clear_hwpoisoned_pages(memmap, PAGES_PER_SECTION); free_section_usemap(memmap, usemap); } -#endif +#endif /* CONFIG_MEMORY_HOTREMOVE */ +#endif /* CONFIG_MEMORY_HOTPLUG */ @@ -737,7 +737,7 @@ EXPORT_SYMBOL(__pagevec_release); #ifdef CONFIG_TRANSPARENT_HUGEPAGE /* used by __split_huge_page_refcount() */ void lru_add_page_tail(struct page *page, struct page *page_tail, - struct lruvec *lruvec) + struct lruvec *lruvec, struct list_head *list) { int uninitialized_var(active); enum lru_list lru; @@ -749,7 +749,8 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, VM_BUG_ON(NR_CPUS != 1 && !spin_is_locked(&lruvec_zone(lruvec)->lru_lock)); - SetPageLRU(page_tail); + if (!list) + SetPageLRU(page_tail); if (page_evictable(page_tail)) { if (PageActive(page)) { @@ -767,7 +768,11 @@ void lru_add_page_tail(struct page *page, struct page *page_tail, if (likely(PageLRU(page))) list_add_tail(&page_tail->lru, &page->lru); - else { + else if (list) { + /* page reclaim is reclaiming a huge page */ + get_page(page_tail); + list_add_tail(&page_tail->lru, list); + } else { struct list_head *list_head; /* * Head page has not yet been counted, as an hpage, diff --git a/mm/swap_state.c b/mm/swap_state.c index 7efcf15..b3d40dc 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -78,7 +78,7 @@ void show_swap_cache_info(void) * __add_to_swap_cache resembles add_to_page_cache_locked on swapper_space, * but sets SwapCache flag and private instead of mapping and index. */ -static int __add_to_swap_cache(struct page *page, swp_entry_t entry) +int __add_to_swap_cache(struct page *page, swp_entry_t entry) { int error; struct address_space *address_space; @@ -160,7 +160,7 @@ void __delete_from_swap_cache(struct page *page) * Allocate swap space for the page and add the page to the * swap cache. Caller needs to hold the page lock. */ -int add_to_swap(struct page *page) +int add_to_swap(struct page *page, struct list_head *list) { swp_entry_t entry; int err; @@ -173,7 +173,7 @@ int add_to_swap(struct page *page) return 0; if (unlikely(PageTransHuge(page))) - if (unlikely(split_huge_page(page))) { + if (unlikely(split_huge_page_to_list(page, list))) { swapcache_free(entry, NULL); return 0; } diff --git a/mm/swapfile.c b/mm/swapfile.c index a1f7772..d417efd 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2120,7 +2120,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) if (p->bdev) { if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { p->flags |= SWP_SOLIDSTATE; - p->cluster_next = 1 + (random32() % p->highest_bit); + p->cluster_next = 1 + (prandom_u32() % p->highest_bit); } if ((swap_flags & SWAP_FLAG_DISCARD) && discard_swap(p) == 0) p->flags |= SWP_DISCARDABLE; diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 0f751f2..72043d6 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -249,19 +249,9 @@ EXPORT_SYMBOL(vmalloc_to_pfn); #define VM_LAZY_FREEING 0x02 #define VM_VM_AREA 0x04 -struct vmap_area { - unsigned long va_start; - unsigned long va_end; - unsigned long flags; - struct rb_node rb_node; /* address sorted rbtree */ - struct list_head list; /* address sorted list */ - struct list_head purge_list; /* "lazy purge" list */ - struct vm_struct *vm; - struct rcu_head rcu_head; -}; - static DEFINE_SPINLOCK(vmap_area_lock); -static LIST_HEAD(vmap_area_list); +/* Export for kexec only */ +LIST_HEAD(vmap_area_list); static struct rb_root vmap_area_root = RB_ROOT; /* The vmap cache globals are protected by vmap_area_lock */ @@ -313,7 +303,7 @@ static void __insert_vmap_area(struct vmap_area *va) rb_link_node(&va->rb_node, parent, p); rb_insert_color(&va->rb_node, &vmap_area_root); - /* address-sort this list so it is usable like the vmlist */ + /* address-sort this list */ tmp = rb_prev(&va->rb_node); if (tmp) { struct vmap_area *prev; @@ -1125,6 +1115,7 @@ void *vm_map_ram(struct page **pages, unsigned int count, int node, pgprot_t pro } EXPORT_SYMBOL(vm_map_ram); +static struct vm_struct *vmlist __initdata; /** * vm_area_add_early - add vmap area early during boot * @vm: vm_struct to add @@ -1283,41 +1274,35 @@ int map_vm_area(struct vm_struct *area, pgprot_t prot, struct page ***pages) } EXPORT_SYMBOL_GPL(map_vm_area); -/*** Old vmalloc interfaces ***/ -DEFINE_RWLOCK(vmlist_lock); -struct vm_struct *vmlist; - static void setup_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { + spin_lock(&vmap_area_lock); vm->flags = flags; vm->addr = (void *)va->va_start; vm->size = va->va_end - va->va_start; vm->caller = caller; va->vm = vm; va->flags |= VM_VM_AREA; + spin_unlock(&vmap_area_lock); } -static void insert_vmalloc_vmlist(struct vm_struct *vm) +static void clear_vm_unlist(struct vm_struct *vm) { - struct vm_struct *tmp, **p; - + /* + * Before removing VM_UNLIST, + * we should make sure that vm has proper values. + * Pair with smp_rmb() in show_numa_info(). + */ + smp_wmb(); vm->flags &= ~VM_UNLIST; - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != NULL; p = &tmp->next) { - if (tmp->addr >= vm->addr) - break; - } - vm->next = *p; - *p = vm; - write_unlock(&vmlist_lock); } static void insert_vmalloc_vm(struct vm_struct *vm, struct vmap_area *va, unsigned long flags, const void *caller) { setup_vmalloc_vm(vm, va, flags, caller); - insert_vmalloc_vmlist(vm); + clear_vm_unlist(vm); } static struct vm_struct *__get_vm_area_node(unsigned long size, @@ -1360,10 +1345,9 @@ static struct vm_struct *__get_vm_area_node(unsigned long size, /* * When this function is called from __vmalloc_node_range, - * we do not add vm_struct to vmlist here to avoid - * accessing uninitialized members of vm_struct such as - * pages and nr_pages fields. They will be set later. - * To distinguish it from others, we use a VM_UNLIST flag. + * we add VM_UNLIST flag to avoid accessing uninitialized + * members of vm_struct such as pages and nr_pages fields. + * They will be set later. */ if (flags & VM_UNLIST) setup_vmalloc_vm(area, va, flags, caller); @@ -1447,19 +1431,10 @@ struct vm_struct *remove_vm_area(const void *addr) if (va && va->flags & VM_VM_AREA) { struct vm_struct *vm = va->vm; - if (!(vm->flags & VM_UNLIST)) { - struct vm_struct *tmp, **p; - /* - * remove from list and disallow access to - * this vm_struct before unmap. (address range - * confliction is maintained by vmap.) - */ - write_lock(&vmlist_lock); - for (p = &vmlist; (tmp = *p) != vm; p = &tmp->next) - ; - *p = tmp->next; - write_unlock(&vmlist_lock); - } + spin_lock(&vmap_area_lock); + va->vm = NULL; + va->flags &= ~VM_VM_AREA; + spin_unlock(&vmap_area_lock); vmap_debug_free_range(va->va_start, va->va_end); free_unmap_vmap_area(va); @@ -1680,10 +1655,11 @@ void *__vmalloc_node_range(unsigned long size, unsigned long align, return NULL; /* - * In this function, newly allocated vm_struct is not added - * to vmlist at __get_vm_area_node(). so, it is added here. + * In this function, newly allocated vm_struct has VM_UNLIST flag. + * It means that vm_struct is not fully initialized. + * Now, it is fully initialized, so remove this flag here. */ - insert_vmalloc_vmlist(area); + clear_vm_unlist(area); /* * A ref_count = 3 is needed because the vm_struct and vmap_area @@ -2005,7 +1981,8 @@ static int aligned_vwrite(char *buf, char *addr, unsigned long count) long vread(char *buf, char *addr, unsigned long count) { - struct vm_struct *tmp; + struct vmap_area *va; + struct vm_struct *vm; char *vaddr, *buf_start = buf; unsigned long buflen = count; unsigned long n; @@ -2014,10 +1991,17 @@ long vread(char *buf, char *addr, unsigned long count) if ((unsigned long) addr + count < count) count = -(unsigned long) addr; - read_lock(&vmlist_lock); - for (tmp = vmlist; count && tmp; tmp = tmp->next) { - vaddr = (char *) tmp->addr; - if (addr >= vaddr + tmp->size - PAGE_SIZE) + spin_lock(&vmap_area_lock); + list_for_each_entry(va, &vmap_area_list, list) { + if (!count) + break; + + if (!(va->flags & VM_VM_AREA)) + continue; + + vm = va->vm; + vaddr = (char *) vm->addr; + if (addr >= vaddr + vm->size - PAGE_SIZE) continue; while (addr < vaddr) { if (count == 0) @@ -2027,10 +2011,10 @@ long vread(char *buf, char *addr, unsigned long count) addr++; count--; } - n = vaddr + tmp->size - PAGE_SIZE - addr; + n = vaddr + vm->size - PAGE_SIZE - addr; if (n > count) n = count; - if (!(tmp->flags & VM_IOREMAP)) + if (!(vm->flags & VM_IOREMAP)) aligned_vread(buf, addr, n); else /* IOREMAP area is treated as memory hole */ memset(buf, 0, n); @@ -2039,7 +2023,7 @@ long vread(char *buf, char *addr, unsigned long count) count -= n; } finished: - read_unlock(&vmlist_lock); + spin_unlock(&vmap_area_lock); if (buf == buf_start) return 0; @@ -2078,7 +2062,8 @@ finished: long vwrite(char *buf, char *addr, unsigned long count) { - struct vm_struct *tmp; + struct vmap_area *va; + struct vm_struct *vm; char *vaddr; unsigned long n, buflen; int copied = 0; @@ -2088,10 +2073,17 @@ long vwrite(char *buf, char *addr, unsigned long count) count = -(unsigned long) addr; buflen = count; - read_lock(&vmlist_lock); - for (tmp = vmlist; count && tmp; tmp = tmp->next) { - vaddr = (char *) tmp->addr; - if (addr >= vaddr + tmp->size - PAGE_SIZE) + spin_lock(&vmap_area_lock); + list_for_each_entry(va, &vmap_area_list, list) { + if (!count) + break; + + if (!(va->flags & VM_VM_AREA)) + continue; + + vm = va->vm; + vaddr = (char *) vm->addr; + if (addr >= vaddr + vm->size - PAGE_SIZE) continue; while (addr < vaddr) { if (count == 0) @@ -2100,10 +2092,10 @@ long vwrite(char *buf, char *addr, unsigned long count) addr++; count--; } - n = vaddr + tmp->size - PAGE_SIZE - addr; + n = vaddr + vm->size - PAGE_SIZE - addr; if (n > count) n = count; - if (!(tmp->flags & VM_IOREMAP)) { + if (!(vm->flags & VM_IOREMAP)) { aligned_vwrite(buf, addr, n); copied++; } @@ -2112,7 +2104,7 @@ long vwrite(char *buf, char *addr, unsigned long count) count -= n; } finished: - read_unlock(&vmlist_lock); + spin_unlock(&vmap_area_lock); if (!copied) return 0; return buflen; @@ -2519,19 +2511,19 @@ void pcpu_free_vm_areas(struct vm_struct **vms, int nr_vms) #ifdef CONFIG_PROC_FS static void *s_start(struct seq_file *m, loff_t *pos) - __acquires(&vmlist_lock) + __acquires(&vmap_area_lock) { loff_t n = *pos; - struct vm_struct *v; + struct vmap_area *va; - read_lock(&vmlist_lock); - v = vmlist; - while (n > 0 && v) { + spin_lock(&vmap_area_lock); + va = list_entry((&vmap_area_list)->next, typeof(*va), list); + while (n > 0 && &va->list != &vmap_area_list) { n--; - v = v->next; + va = list_entry(va->list.next, typeof(*va), list); } - if (!n) - return v; + if (!n && &va->list != &vmap_area_list) + return va; return NULL; @@ -2539,16 +2531,20 @@ static void *s_start(struct seq_file *m, loff_t *pos) static void *s_next(struct seq_file *m, void *p, loff_t *pos) { - struct vm_struct *v = p; + struct vmap_area *va = p, *next; ++*pos; - return v->next; + next = list_entry(va->list.next, typeof(*va), list); + if (&next->list != &vmap_area_list) + return next; + + return NULL; } static void s_stop(struct seq_file *m, void *p) - __releases(&vmlist_lock) + __releases(&vmap_area_lock) { - read_unlock(&vmlist_lock); + spin_unlock(&vmap_area_lock); } static void show_numa_info(struct seq_file *m, struct vm_struct *v) @@ -2559,6 +2555,11 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) if (!counters) return; + /* Pair with smp_wmb() in clear_vm_unlist() */ + smp_rmb(); + if (v->flags & VM_UNLIST) + return; + memset(counters, 0, nr_node_ids * sizeof(unsigned int)); for (nr = 0; nr < v->nr_pages; nr++) @@ -2572,7 +2573,20 @@ static void show_numa_info(struct seq_file *m, struct vm_struct *v) static int s_show(struct seq_file *m, void *p) { - struct vm_struct *v = p; + struct vmap_area *va = p; + struct vm_struct *v; + + if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING)) + return 0; + + if (!(va->flags & VM_VM_AREA)) { + seq_printf(m, "0x%pK-0x%pK %7ld vm_map_ram\n", + (void *)va->va_start, (void *)va->va_end, + va->va_end - va->va_start); + return 0; + } + + v = va->vm; seq_printf(m, "0x%pK-0x%pK %7ld", v->addr, v->addr + v->size, v->size); @@ -2645,5 +2659,53 @@ static int __init proc_vmalloc_init(void) return 0; } module_init(proc_vmalloc_init); + +void get_vmalloc_info(struct vmalloc_info *vmi) +{ + struct vmap_area *va; + unsigned long free_area_size; + unsigned long prev_end; + + vmi->used = 0; + vmi->largest_chunk = 0; + + prev_end = VMALLOC_START; + + spin_lock(&vmap_area_lock); + + if (list_empty(&vmap_area_list)) { + vmi->largest_chunk = VMALLOC_TOTAL; + goto out; + } + + list_for_each_entry(va, &vmap_area_list, list) { + unsigned long addr = va->va_start; + + /* + * Some archs keep another range for modules in vmalloc space + */ + if (addr < VMALLOC_START) + continue; + if (addr >= VMALLOC_END) + break; + + if (va->flags & (VM_LAZY_FREE | VM_LAZY_FREEING)) + continue; + + vmi->used += (va->va_end - va->va_start); + + free_area_size = addr - prev_end; + if (vmi->largest_chunk < free_area_size) + vmi->largest_chunk = free_area_size; + + prev_end = va->va_end; + } + + if (VMALLOC_END - prev_end > vmi->largest_chunk) + vmi->largest_chunk = VMALLOC_END - prev_end; + +out: + spin_unlock(&vmap_area_lock); +} #endif diff --git a/mm/vmpressure.c b/mm/vmpressure.c new file mode 100644 index 0000000..736a601 --- /dev/null +++ b/mm/vmpressure.c @@ -0,0 +1,374 @@ +/* + * Linux VM pressure + * + * Copyright 2012 Linaro Ltd. + * Anton Vorontsov <anton.vorontsov@linaro.org> + * + * Based on ideas from Andrew Morton, David Rientjes, KOSAKI Motohiro, + * Leonid Moiseichuk, Mel Gorman, Minchan Kim and Pekka Enberg. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License version 2 as published + * by the Free Software Foundation. + */ + +#include <linux/cgroup.h> +#include <linux/fs.h> +#include <linux/log2.h> +#include <linux/sched.h> +#include <linux/mm.h> +#include <linux/vmstat.h> +#include <linux/eventfd.h> +#include <linux/swap.h> +#include <linux/printk.h> +#include <linux/vmpressure.h> + +/* + * The window size (vmpressure_win) is the number of scanned pages before + * we try to analyze scanned/reclaimed ratio. So the window is used as a + * rate-limit tunable for the "low" level notification, and also for + * averaging the ratio for medium/critical levels. Using small window + * sizes can cause lot of false positives, but too big window size will + * delay the notifications. + * + * As the vmscan reclaimer logic works with chunks which are multiple of + * SWAP_CLUSTER_MAX, it makes sense to use it for the window size as well. + * + * TODO: Make the window size depend on machine size, as we do for vmstat + * thresholds. Currently we set it to 512 pages (2MB for 4KB pages). + */ +static const unsigned long vmpressure_win = SWAP_CLUSTER_MAX * 16; + +/* + * These thresholds are used when we account memory pressure through + * scanned/reclaimed ratio. The current values were chosen empirically. In + * essence, they are percents: the higher the value, the more number + * unsuccessful reclaims there were. + */ +static const unsigned int vmpressure_level_med = 60; +static const unsigned int vmpressure_level_critical = 95; + +/* + * When there are too little pages left to scan, vmpressure() may miss the + * critical pressure as number of pages will be less than "window size". + * However, in that case the vmscan priority will raise fast as the + * reclaimer will try to scan LRUs more deeply. + * + * The vmscan logic considers these special priorities: + * + * prio == DEF_PRIORITY (12): reclaimer starts with that value + * prio <= DEF_PRIORITY - 2 : kswapd becomes somewhat overwhelmed + * prio == 0 : close to OOM, kernel scans every page in an lru + * + * Any value in this range is acceptable for this tunable (i.e. from 12 to + * 0). Current value for the vmpressure_level_critical_prio is chosen + * empirically, but the number, in essence, means that we consider + * critical level when scanning depth is ~10% of the lru size (vmscan + * scans 'lru_size >> prio' pages, so it is actually 12.5%, or one + * eights). + */ +static const unsigned int vmpressure_level_critical_prio = ilog2(100 / 10); + +static struct vmpressure *work_to_vmpressure(struct work_struct *work) +{ + return container_of(work, struct vmpressure, work); +} + +static struct vmpressure *cg_to_vmpressure(struct cgroup *cg) +{ + return css_to_vmpressure(cgroup_subsys_state(cg, mem_cgroup_subsys_id)); +} + +static struct vmpressure *vmpressure_parent(struct vmpressure *vmpr) +{ + struct cgroup *cg = vmpressure_to_css(vmpr)->cgroup; + struct mem_cgroup *memcg = mem_cgroup_from_cont(cg); + + memcg = parent_mem_cgroup(memcg); + if (!memcg) + return NULL; + return memcg_to_vmpressure(memcg); +} + +enum vmpressure_levels { + VMPRESSURE_LOW = 0, + VMPRESSURE_MEDIUM, + VMPRESSURE_CRITICAL, + VMPRESSURE_NUM_LEVELS, +}; + +static const char * const vmpressure_str_levels[] = { + [VMPRESSURE_LOW] = "low", + [VMPRESSURE_MEDIUM] = "medium", + [VMPRESSURE_CRITICAL] = "critical", +}; + +static enum vmpressure_levels vmpressure_level(unsigned long pressure) +{ + if (pressure >= vmpressure_level_critical) + return VMPRESSURE_CRITICAL; + else if (pressure >= vmpressure_level_med) + return VMPRESSURE_MEDIUM; + return VMPRESSURE_LOW; +} + +static enum vmpressure_levels vmpressure_calc_level(unsigned long scanned, + unsigned long reclaimed) +{ + unsigned long scale = scanned + reclaimed; + unsigned long pressure; + + /* + * We calculate the ratio (in percents) of how many pages were + * scanned vs. reclaimed in a given time frame (window). Note that + * time is in VM reclaimer's "ticks", i.e. number of pages + * scanned. This makes it possible to set desired reaction time + * and serves as a ratelimit. + */ + pressure = scale - (reclaimed * scale / scanned); + pressure = pressure * 100 / scale; + + pr_debug("%s: %3lu (s: %lu r: %lu)\n", __func__, pressure, + scanned, reclaimed); + + return vmpressure_level(pressure); +} + +struct vmpressure_event { + struct eventfd_ctx *efd; + enum vmpressure_levels level; + struct list_head node; +}; + +static bool vmpressure_event(struct vmpressure *vmpr, + unsigned long scanned, unsigned long reclaimed) +{ + struct vmpressure_event *ev; + enum vmpressure_levels level; + bool signalled = false; + + level = vmpressure_calc_level(scanned, reclaimed); + + mutex_lock(&vmpr->events_lock); + + list_for_each_entry(ev, &vmpr->events, node) { + if (level >= ev->level) { + eventfd_signal(ev->efd, 1); + signalled = true; + } + } + + mutex_unlock(&vmpr->events_lock); + + return signalled; +} + +static void vmpressure_work_fn(struct work_struct *work) +{ + struct vmpressure *vmpr = work_to_vmpressure(work); + unsigned long scanned; + unsigned long reclaimed; + + /* + * Several contexts might be calling vmpressure(), so it is + * possible that the work was rescheduled again before the old + * work context cleared the counters. In that case we will run + * just after the old work returns, but then scanned might be zero + * here. No need for any locks here since we don't care if + * vmpr->reclaimed is in sync. + */ + if (!vmpr->scanned) + return; + + mutex_lock(&vmpr->sr_lock); + scanned = vmpr->scanned; + reclaimed = vmpr->reclaimed; + vmpr->scanned = 0; + vmpr->reclaimed = 0; + mutex_unlock(&vmpr->sr_lock); + + do { + if (vmpressure_event(vmpr, scanned, reclaimed)) + break; + /* + * If not handled, propagate the event upward into the + * hierarchy. + */ + } while ((vmpr = vmpressure_parent(vmpr))); +} + +/** + * vmpressure() - Account memory pressure through scanned/reclaimed ratio + * @gfp: reclaimer's gfp mask + * @memcg: cgroup memory controller handle + * @scanned: number of pages scanned + * @reclaimed: number of pages reclaimed + * + * This function should be called from the vmscan reclaim path to account + * "instantaneous" memory pressure (scanned/reclaimed ratio). The raw + * pressure index is then further refined and averaged over time. + * + * This function does not return any value. + */ +void vmpressure(gfp_t gfp, struct mem_cgroup *memcg, + unsigned long scanned, unsigned long reclaimed) +{ + struct vmpressure *vmpr = memcg_to_vmpressure(memcg); + + /* + * Here we only want to account pressure that userland is able to + * help us with. For example, suppose that DMA zone is under + * pressure; if we notify userland about that kind of pressure, + * then it will be mostly a waste as it will trigger unnecessary + * freeing of memory by userland (since userland is more likely to + * have HIGHMEM/MOVABLE pages instead of the DMA fallback). That + * is why we include only movable, highmem and FS/IO pages. + * Indirect reclaim (kswapd) sets sc->gfp_mask to GFP_KERNEL, so + * we account it too. + */ + if (!(gfp & (__GFP_HIGHMEM | __GFP_MOVABLE | __GFP_IO | __GFP_FS))) + return; + + /* + * If we got here with no pages scanned, then that is an indicator + * that reclaimer was unable to find any shrinkable LRUs at the + * current scanning depth. But it does not mean that we should + * report the critical pressure, yet. If the scanning priority + * (scanning depth) goes too high (deep), we will be notified + * through vmpressure_prio(). But so far, keep calm. + */ + if (!scanned) + return; + + mutex_lock(&vmpr->sr_lock); + vmpr->scanned += scanned; + vmpr->reclaimed += reclaimed; + scanned = vmpr->scanned; + mutex_unlock(&vmpr->sr_lock); + + if (scanned < vmpressure_win || work_pending(&vmpr->work)) + return; + schedule_work(&vmpr->work); +} + +/** + * vmpressure_prio() - Account memory pressure through reclaimer priority level + * @gfp: reclaimer's gfp mask + * @memcg: cgroup memory controller handle + * @prio: reclaimer's priority + * + * This function should be called from the reclaim path every time when + * the vmscan's reclaiming priority (scanning depth) changes. + * + * This function does not return any value. + */ +void vmpressure_prio(gfp_t gfp, struct mem_cgroup *memcg, int prio) +{ + /* + * We only use prio for accounting critical level. For more info + * see comment for vmpressure_level_critical_prio variable above. + */ + if (prio > vmpressure_level_critical_prio) + return; + + /* + * OK, the prio is below the threshold, updating vmpressure + * information before shrinker dives into long shrinking of long + * range vmscan. Passing scanned = vmpressure_win, reclaimed = 0 + * to the vmpressure() basically means that we signal 'critical' + * level. + */ + vmpressure(gfp, memcg, vmpressure_win, 0); +} + +/** + * vmpressure_register_event() - Bind vmpressure notifications to an eventfd + * @cg: cgroup that is interested in vmpressure notifications + * @cft: cgroup control files handle + * @eventfd: eventfd context to link notifications with + * @args: event arguments (used to set up a pressure level threshold) + * + * This function associates eventfd context with the vmpressure + * infrastructure, so that the notifications will be delivered to the + * @eventfd. The @args parameter is a string that denotes pressure level + * threshold (one of vmpressure_str_levels, i.e. "low", "medium", or + * "critical"). + * + * This function should not be used directly, just pass it to (struct + * cftype).register_event, and then cgroup core will handle everything by + * itself. + */ +int vmpressure_register_event(struct cgroup *cg, struct cftype *cft, + struct eventfd_ctx *eventfd, const char *args) +{ + struct vmpressure *vmpr = cg_to_vmpressure(cg); + struct vmpressure_event *ev; + int level; + + for (level = 0; level < VMPRESSURE_NUM_LEVELS; level++) { + if (!strcmp(vmpressure_str_levels[level], args)) + break; + } + + if (level >= VMPRESSURE_NUM_LEVELS) + return -EINVAL; + + ev = kzalloc(sizeof(*ev), GFP_KERNEL); + if (!ev) + return -ENOMEM; + + ev->efd = eventfd; + ev->level = level; + + mutex_lock(&vmpr->events_lock); + list_add(&ev->node, &vmpr->events); + mutex_unlock(&vmpr->events_lock); + + return 0; +} + +/** + * vmpressure_unregister_event() - Unbind eventfd from vmpressure + * @cg: cgroup handle + * @cft: cgroup control files handle + * @eventfd: eventfd context that was used to link vmpressure with the @cg + * + * This function does internal manipulations to detach the @eventfd from + * the vmpressure notifications, and then frees internal resources + * associated with the @eventfd (but the @eventfd itself is not freed). + * + * This function should not be used directly, just pass it to (struct + * cftype).unregister_event, and then cgroup core will handle everything + * by itself. + */ +void vmpressure_unregister_event(struct cgroup *cg, struct cftype *cft, + struct eventfd_ctx *eventfd) +{ + struct vmpressure *vmpr = cg_to_vmpressure(cg); + struct vmpressure_event *ev; + + mutex_lock(&vmpr->events_lock); + list_for_each_entry(ev, &vmpr->events, node) { + if (ev->efd != eventfd) + continue; + list_del(&ev->node); + kfree(ev); + break; + } + mutex_unlock(&vmpr->events_lock); +} + +/** + * vmpressure_init() - Initialize vmpressure control structure + * @vmpr: Structure to be initialized + * + * This function should be called on every allocated vmpressure structure + * before any usage. + */ +void vmpressure_init(struct vmpressure *vmpr) +{ + mutex_init(&vmpr->sr_lock); + mutex_init(&vmpr->events_lock); + INIT_LIST_HEAD(&vmpr->events); + INIT_WORK(&vmpr->work, vmpressure_work_fn); +} diff --git a/mm/vmscan.c b/mm/vmscan.c index 88c5fed..fa6a853 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -19,6 +19,7 @@ #include <linux/pagemap.h> #include <linux/init.h> #include <linux/highmem.h> +#include <linux/vmpressure.h> #include <linux/vmstat.h> #include <linux/file.h> #include <linux/writeback.h> @@ -780,7 +781,7 @@ static unsigned long shrink_page_list(struct list_head *page_list, if (PageAnon(page) && !PageSwapCache(page)) { if (!(sc->gfp_mask & __GFP_IO)) goto keep_locked; - if (!add_to_swap(page)) + if (!add_to_swap(page, page_list)) goto activate_locked; may_enter_fs = 1; } @@ -1982,6 +1983,11 @@ static void shrink_zone(struct zone *zone, struct scan_control *sc) } memcg = mem_cgroup_iter(root, memcg, &reclaim); } while (memcg); + + vmpressure(sc->gfp_mask, sc->target_mem_cgroup, + sc->nr_scanned - nr_scanned, + sc->nr_reclaimed - nr_reclaimed); + } while (should_continue_reclaim(zone, sc->nr_reclaimed - nr_reclaimed, sc->nr_scanned - nr_scanned, sc)); } @@ -2167,6 +2173,8 @@ static unsigned long do_try_to_free_pages(struct zonelist *zonelist, count_vm_event(ALLOCSTALL); do { + vmpressure_prio(sc->gfp_mask, sc->target_mem_cgroup, + sc->priority); sc->nr_scanned = 0; aborted_reclaim = shrink_zones(zonelist, sc); @@ -2619,7 +2627,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, bool pgdat_is_balanced = false; int i; int end_zone = 0; /* Inclusive. 0 = ZONE_DMA */ - unsigned long total_scanned; struct reclaim_state *reclaim_state = current->reclaim_state; unsigned long nr_soft_reclaimed; unsigned long nr_soft_scanned; @@ -2639,7 +2646,6 @@ static unsigned long balance_pgdat(pg_data_t *pgdat, int order, .gfp_mask = sc.gfp_mask, }; loop_again: - total_scanned = 0; sc.priority = DEF_PRIORITY; sc.nr_reclaimed = 0; sc.may_writepage = !laptop_mode; @@ -2730,7 +2736,6 @@ loop_again: order, sc.gfp_mask, &nr_soft_scanned); sc.nr_reclaimed += nr_soft_reclaimed; - total_scanned += nr_soft_scanned; /* * We put equal pressure on every zone, unless @@ -2765,7 +2770,6 @@ loop_again: reclaim_state->reclaimed_slab = 0; nr_slab = shrink_slab(&shrink, sc.nr_scanned, lru_pages); sc.nr_reclaimed += reclaim_state->reclaimed_slab; - total_scanned += sc.nr_scanned; if (nr_slab == 0 && !zone_reclaimable(zone)) zone->all_unreclaimable = 1; @@ -3188,9 +3192,9 @@ int kswapd_run(int nid) if (IS_ERR(pgdat->kswapd)) { /* failure at boot is fatal */ BUG_ON(system_state == SYSTEM_BOOTING); - pgdat->kswapd = NULL; pr_err("Failed to start kswapd on node %d\n", nid); ret = PTR_ERR(pgdat->kswapd); + pgdat->kswapd = NULL; } return ret; } diff --git a/mm/vmstat.c b/mm/vmstat.c index e1d8ed1..f42745e 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -52,7 +52,6 @@ void all_vm_events(unsigned long *ret) } EXPORT_SYMBOL_GPL(all_vm_events); -#ifdef CONFIG_HOTPLUG /* * Fold the foreign cpu events into our own. * @@ -69,7 +68,6 @@ void vm_events_fold_cpu(int cpu) fold_state->event[i] = 0; } } -#endif /* CONFIG_HOTPLUG */ #endif /* CONFIG_VM_EVENT_COUNTERS */ @@ -495,6 +493,10 @@ void refresh_cpu_vm_stats(int cpu) atomic_long_add(global_diff[i], &vm_stat[i]); } +/* + * this is only called if !populated_zone(zone), which implies no other users of + * pset->vm_stat_diff[] exsist. + */ void drain_zonestat(struct zone *zone, struct per_cpu_pageset *pset) { int i; |