diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/cma.c | 29 | ||||
-rw-r--r-- | mm/filemap.c | 16 | ||||
-rw-r--r-- | mm/gup.c | 18 | ||||
-rw-r--r-- | mm/huge_memory.c | 42 | ||||
-rw-r--r-- | mm/hugetlb.c | 26 | ||||
-rw-r--r-- | mm/khugepaged.c | 27 | ||||
-rw-r--r-- | mm/kmemleak.c | 2 | ||||
-rw-r--r-- | mm/madvise.c | 4 | ||||
-rw-r--r-- | mm/memcontrol.c | 31 | ||||
-rw-r--r-- | mm/memory.c | 121 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 19 | ||||
-rw-r--r-- | mm/mmap.c | 2 | ||||
-rw-r--r-- | mm/mmu_context.c | 7 | ||||
-rw-r--r-- | mm/oom_kill.c | 2 | ||||
-rw-r--r-- | mm/page_alloc.c | 17 | ||||
-rw-r--r-- | mm/page_isolation.c | 8 | ||||
-rw-r--r-- | mm/page_owner.c | 4 | ||||
-rw-r--r-- | mm/pagewalk.c | 4 | ||||
-rw-r--r-- | mm/percpu.c | 2 | ||||
-rw-r--r-- | mm/shuffle.c | 18 | ||||
-rw-r--r-- | mm/slub.c | 57 | ||||
-rw-r--r-- | mm/swap_state.c | 5 | ||||
-rw-r--r-- | mm/swapfile.c | 16 | ||||
-rw-r--r-- | mm/vmalloc.c | 2 | ||||
-rw-r--r-- | mm/vmscan.c | 53 |
25 files changed, 371 insertions, 161 deletions
@@ -93,19 +93,15 @@ static void cma_clear_bitmap(struct cma *cma, unsigned long pfn, mutex_unlock(&cma->lock); } -static int __init cma_activate_area(struct cma *cma) +static void __init cma_activate_area(struct cma *cma) { - int bitmap_size = BITS_TO_LONGS(cma_bitmap_maxno(cma)) * sizeof(long); unsigned long base_pfn = cma->base_pfn, pfn = base_pfn; unsigned i = cma->count >> pageblock_order; struct zone *zone; - cma->bitmap = kzalloc(bitmap_size, GFP_KERNEL); - - if (!cma->bitmap) { - cma->count = 0; - return -ENOMEM; - } + cma->bitmap = bitmap_zalloc(cma_bitmap_maxno(cma), GFP_KERNEL); + if (!cma->bitmap) + goto out_error; WARN_ON_ONCE(!pfn_valid(pfn)); zone = page_zone(pfn_to_page(pfn)); @@ -135,25 +131,22 @@ static int __init cma_activate_area(struct cma *cma) spin_lock_init(&cma->mem_head_lock); #endif - return 0; + return; not_in_zone: - pr_err("CMA area %s could not be activated\n", cma->name); - kfree(cma->bitmap); + bitmap_free(cma->bitmap); +out_error: cma->count = 0; - return -EINVAL; + pr_err("CMA area %s could not be activated\n", cma->name); + return; } static int __init cma_init_reserved_areas(void) { int i; - for (i = 0; i < cma_area_count; i++) { - int ret = cma_activate_area(&cma_areas[i]); - - if (ret) - return ret; - } + for (i = 0; i < cma_area_count; i++) + cma_activate_area(&cma_areas[i]); return 0; } diff --git a/mm/filemap.c b/mm/filemap.c index 18c1f5830074..db542b494883 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -847,10 +847,10 @@ int replace_page_cache_page(struct page *old, struct page *new, gfp_t gfp_mask) } EXPORT_SYMBOL_GPL(replace_page_cache_page); -static int __add_to_page_cache_locked(struct page *page, - struct address_space *mapping, - pgoff_t offset, gfp_t gfp_mask, - void **shadowp) +noinline int __add_to_page_cache_locked(struct page *page, + struct address_space *mapping, + pgoff_t offset, gfp_t gfp_mask, + void **shadowp) { XA_STATE(xas, &mapping->i_pages, offset); int huge = PageHuge(page); @@ -2845,6 +2845,14 @@ filler: unlock_page(page); goto out; } + + /* + * A previous I/O error may have been due to temporary + * failures. + * Clear page error before actual read, PG_error will be + * set again if read page fails. + */ + ClearPageError(page); goto filler; out: @@ -2184,13 +2184,13 @@ static int gup_huge_pgd(pgd_t orig, pgd_t *pgdp, unsigned long addr, return 1; } -static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, +static int gup_pmd_range(pud_t *pudp, pud_t pud, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pmd_t *pmdp; - pmdp = pmd_offset(&pud, addr); + pmdp = pmd_offset_lockless(pudp, pud, addr); do { pmd_t pmd = READ_ONCE(*pmdp); @@ -2227,13 +2227,13 @@ static int gup_pmd_range(pud_t pud, unsigned long addr, unsigned long end, return 1; } -static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, +static int gup_pud_range(p4d_t *p4dp, p4d_t p4d, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; pud_t *pudp; - pudp = pud_offset(&p4d, addr); + pudp = pud_offset_lockless(p4dp, p4d, addr); do { pud_t pud = READ_ONCE(*pudp); @@ -2248,20 +2248,20 @@ static int gup_pud_range(p4d_t p4d, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pud_val(pud)), addr, PUD_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pmd_range(pud, addr, next, flags, pages, nr)) + } else if (!gup_pmd_range(pudp, pud, addr, next, flags, pages, nr)) return 0; } while (pudp++, addr = next, addr != end); return 1; } -static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, +static int gup_p4d_range(pgd_t *pgdp, pgd_t pgd, unsigned long addr, unsigned long end, unsigned int flags, struct page **pages, int *nr) { unsigned long next; p4d_t *p4dp; - p4dp = p4d_offset(&pgd, addr); + p4dp = p4d_offset_lockless(pgdp, pgd, addr); do { p4d_t p4d = READ_ONCE(*p4dp); @@ -2273,7 +2273,7 @@ static int gup_p4d_range(pgd_t pgd, unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(p4d_val(p4d)), addr, P4D_SHIFT, next, flags, pages, nr)) return 0; - } else if (!gup_pud_range(p4d, addr, next, flags, pages, nr)) + } else if (!gup_pud_range(p4dp, p4d, addr, next, flags, pages, nr)) return 0; } while (p4dp++, addr = next, addr != end); @@ -2301,7 +2301,7 @@ static void gup_pgd_range(unsigned long addr, unsigned long end, if (!gup_huge_pd(__hugepd(pgd_val(pgd)), addr, PGDIR_SHIFT, next, flags, pages, nr)) return; - } else if (!gup_p4d_range(pgd, addr, next, flags, pages, nr)) + } else if (!gup_p4d_range(pgdp, pgd, addr, next, flags, pages, nr)) return; } while (pgdp++, addr = next, addr != end); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index da9040a6838f..9295d9d70681 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2174,7 +2174,7 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, put_page(page); add_mm_counter(mm, mm_counter_file(page), -HPAGE_PMD_NR); return; - } else if (is_huge_zero_pmd(*pmd)) { + } else if (pmd_trans_huge(*pmd) && is_huge_zero_pmd(*pmd)) { /* * FIXME: Do we want to invalidate secondary mmu by calling * mmu_notifier_invalidate_range() see comments below inside @@ -2262,27 +2262,33 @@ static void __split_huge_pmd_locked(struct vm_area_struct *vma, pmd_t *pmd, pte = pte_offset_map(&_pmd, addr); BUG_ON(!pte_none(*pte)); set_pte_at(mm, addr, pte, entry); - atomic_inc(&page[i]._mapcount); - pte_unmap(pte); - } - - /* - * Set PG_double_map before dropping compound_mapcount to avoid - * false-negative page_mapped(). - */ - if (compound_mapcount(page) > 1 && !TestSetPageDoubleMap(page)) { - for (i = 0; i < HPAGE_PMD_NR; i++) + if (!pmd_migration) atomic_inc(&page[i]._mapcount); + pte_unmap(pte); } - if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { - /* Last compound_mapcount is gone. */ - __dec_node_page_state(page, NR_ANON_THPS); - if (TestClearPageDoubleMap(page)) { - /* No need in mapcount reference anymore */ + if (!pmd_migration) { + /* + * Set PG_double_map before dropping compound_mapcount to avoid + * false-negative page_mapped(). + */ + if (compound_mapcount(page) > 1 && + !TestSetPageDoubleMap(page)) { for (i = 0; i < HPAGE_PMD_NR; i++) - atomic_dec(&page[i]._mapcount); + atomic_inc(&page[i]._mapcount); + } + + lock_page_memcg(page); + if (atomic_add_negative(-1, compound_mapcount_ptr(page))) { + /* Last compound_mapcount is gone. */ + __dec_lruvec_page_state(page, NR_ANON_THPS); + if (TestClearPageDoubleMap(page)) { + /* No need in mapcount reference anymore */ + for (i = 0; i < HPAGE_PMD_NR; i++) + atomic_dec(&page[i]._mapcount); + } } + unlock_page_memcg(page); } smp_wmb(); /* make pte visible before pmd */ @@ -2563,7 +2569,7 @@ static void __split_huge_page(struct page *page, struct list_head *list, ClearPageCompound(head); - split_page_owner(head, HPAGE_PMD_ORDER); + split_page_owner(head, HPAGE_PMD_NR); /* See comment in __split_huge_page_tail() */ if (PageAnon(head)) { diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 2a83b03c54a6..62ec514dae65 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -3082,6 +3082,22 @@ static unsigned int cpuset_mems_nr(unsigned int *array) } #ifdef CONFIG_SYSCTL +static int proc_hugetlb_doulongvec_minmax(struct ctl_table *table, int write, + void *buffer, size_t *length, + loff_t *ppos, unsigned long *out) +{ + struct ctl_table dup_table; + + /* + * In order to avoid races with __do_proc_doulongvec_minmax(), we + * can duplicate the @table and alter the duplicate of it. + */ + dup_table = *table; + dup_table.data = out; + + return proc_doulongvec_minmax(&dup_table, write, buffer, length, ppos); +} + static int hugetlb_sysctl_handler_common(bool obey_mempolicy, struct ctl_table *table, int write, void __user *buffer, size_t *length, loff_t *ppos) @@ -3093,9 +3109,8 @@ static int hugetlb_sysctl_handler_common(bool obey_mempolicy, if (!hugepages_supported()) return -EOPNOTSUPP; - table->data = &tmp; - table->maxlen = sizeof(unsigned long); - ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); if (ret) goto out; @@ -3139,9 +3154,8 @@ int hugetlb_overcommit_handler(struct ctl_table *table, int write, if (write && hstate_is_gigantic(h)) return -EINVAL; - table->data = &tmp; - table->maxlen = sizeof(unsigned long); - ret = proc_doulongvec_minmax(table, write, buffer, length, ppos); + ret = proc_hugetlb_doulongvec_minmax(table, write, buffer, length, ppos, + &tmp); if (ret) goto out; diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 3623d1c5343f..f0d7e6483ba3 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -54,6 +54,9 @@ enum scan_result { #define CREATE_TRACE_POINTS #include <trace/events/huge_memory.h> +static struct task_struct *khugepaged_thread __read_mostly; +static DEFINE_MUTEX(khugepaged_mutex); + /* default scan 8*512 pte (or vmas) every 30 second */ static unsigned int khugepaged_pages_to_scan __read_mostly; static unsigned int khugepaged_pages_collapsed; @@ -832,6 +835,18 @@ static struct page *khugepaged_alloc_hugepage(bool *wait) static bool khugepaged_prealloc_page(struct page **hpage, bool *wait) { + /* + * If the hpage allocated earlier was briefly exposed in page cache + * before collapse_file() failed, it is possible that racing lookups + * have not yet completed, and would then be unpleasantly surprised by + * finding the hpage reused for the same mapping at a different offset. + * Just release the previous allocation if there is any danger of that. + */ + if (*hpage && page_count(*hpage) > 1) { + put_page(*hpage); + *hpage = NULL; + } + if (!*hpage) *hpage = khugepaged_alloc_hugepage(wait); @@ -1592,7 +1607,7 @@ static void collapse_file(struct mm_struct *mm, xas_unlock_irq(&xas); page_cache_sync_readahead(mapping, &file->f_ra, file, index, - PAGE_SIZE); + end - index); /* drain pagevecs to help isolate_lru_page() */ lru_add_drain(); page = find_lock_page(mapping, index); @@ -2165,8 +2180,6 @@ static void set_recommended_min_free_kbytes(void) int start_stop_khugepaged(void) { - static struct task_struct *khugepaged_thread __read_mostly; - static DEFINE_MUTEX(khugepaged_mutex); int err = 0; mutex_lock(&khugepaged_mutex); @@ -2193,3 +2206,11 @@ fail: mutex_unlock(&khugepaged_mutex); return err; } + +void khugepaged_min_free_kbytes_update(void) +{ + mutex_lock(&khugepaged_mutex); + if (khugepaged_enabled() && khugepaged_thread) + set_recommended_min_free_kbytes(); + mutex_unlock(&khugepaged_mutex); +} diff --git a/mm/kmemleak.c b/mm/kmemleak.c index 244607663363..312942d78405 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1947,7 +1947,7 @@ void __init kmemleak_init(void) create_object((unsigned long)__bss_start, __bss_stop - __bss_start, KMEMLEAK_GREY, GFP_ATOMIC); /* only register .data..ro_after_init if not within .data */ - if (__start_ro_after_init < _sdata || __end_ro_after_init > _edata) + if (&__start_ro_after_init < &_sdata || &__end_ro_after_init > &_edata) create_object((unsigned long)__start_ro_after_init, __end_ro_after_init - __start_ro_after_init, KMEMLEAK_GREY, GFP_ATOMIC); diff --git a/mm/madvise.c b/mm/madvise.c index d8cfc3a0c153..1107e99e498b 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -288,9 +288,9 @@ static long madvise_willneed(struct vm_area_struct *vma, */ *prev = NULL; /* tell sys_madvise we drop mmap_sem */ get_file(file); - up_read(¤t->mm->mmap_sem); offset = (loff_t)(start - vma->vm_start) + ((loff_t)vma->vm_pgoff << PAGE_SHIFT); + up_read(¤t->mm->mmap_sem); vfs_fadvise(file, offset, end - start, POSIX_FADV_WILLNEED); fput(file); down_read(¤t->mm->mmap_sem); @@ -380,9 +380,9 @@ huge_unlock: return 0; } +regular_page: if (pmd_trans_unstable(pmd)) return 0; -regular_page: #endif tlb_change_page_size(tlb, PAGE_SIZE); orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 402c8bc65e08..edf98f8588ee 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -5398,7 +5398,7 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, struct page *page = NULL; swp_entry_t ent = pte_to_swp_entry(ptent); - if (!(mc.flags & MOVE_ANON) || non_swap_entry(ent)) + if (!(mc.flags & MOVE_ANON)) return NULL; /* @@ -5417,6 +5417,9 @@ static struct page *mc_handle_swap_pte(struct vm_area_struct *vma, return page; } + if (non_swap_entry(ent)) + return NULL; + /* * Because lookup_swap_cache() updates some statistics counter, * we call find_get_page() with swapper_space directly. @@ -5489,7 +5492,6 @@ static int mem_cgroup_move_account(struct page *page, { struct lruvec *from_vec, *to_vec; struct pglist_data *pgdat; - unsigned long flags; unsigned int nr_pages = compound ? hpage_nr_pages(page) : 1; int ret; bool anon; @@ -5516,18 +5518,13 @@ static int mem_cgroup_move_account(struct page *page, from_vec = mem_cgroup_lruvec(pgdat, from); to_vec = mem_cgroup_lruvec(pgdat, to); - spin_lock_irqsave(&from->move_lock, flags); + lock_page_memcg(page); if (!anon && page_mapped(page)) { __mod_lruvec_state(from_vec, NR_FILE_MAPPED, -nr_pages); __mod_lruvec_state(to_vec, NR_FILE_MAPPED, nr_pages); } - /* - * move_lock grabbed above and caller set from->moving_account, so - * mod_memcg_page_state will serialize updates to PageDirty. - * So mapping should be stable for dirty pages. - */ if (!anon && PageDirty(page)) { struct address_space *mapping = page_mapping(page); @@ -5543,15 +5540,23 @@ static int mem_cgroup_move_account(struct page *page, } /* + * All state has been migrated, let's switch to the new memcg. + * * It is safe to change page->mem_cgroup here because the page - * is referenced, charged, and isolated - we can't race with - * uncharging, charging, migration, or LRU putback. + * is referenced, charged, isolated, and locked: we can't race + * with (un)charging, migration, LRU putback, or anything else + * that would rely on a stable page->mem_cgroup. + * + * Note that lock_page_memcg is a memcg lock, not a page lock, + * to save space. As soon as we switch page->mem_cgroup to a + * new memcg that isn't locked, the above state can change + * concurrently again. Make sure we're truly done with it. */ + smp_mb(); - /* caller should have done css_get */ - page->mem_cgroup = to; + page->mem_cgroup = to; /* caller should have done css_get */ - spin_unlock_irqrestore(&from->move_lock, flags); + __unlock_page_memcg(from); ret = 0; diff --git a/mm/memory.c b/mm/memory.c index cb7c940cf800..2157bb28117a 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -118,6 +118,18 @@ int randomize_va_space __read_mostly = 2; #endif +#ifndef arch_faults_on_old_pte +static inline bool arch_faults_on_old_pte(void) +{ + /* + * Those arches which don't have hw access flag feature need to + * implement their own helper. By default, "true" means pagefault + * will be hit on old pte. + */ + return true; +} +#endif + static int __init disable_randmaps(char *s) { randomize_va_space = 0; @@ -2145,32 +2157,101 @@ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, return same; } -static inline void cow_user_page(struct page *dst, struct page *src, unsigned long va, struct vm_area_struct *vma) +static inline bool cow_user_page(struct page *dst, struct page *src, + struct vm_fault *vmf) { + bool ret; + void *kaddr; + void __user *uaddr; + bool locked = false; + struct vm_area_struct *vma = vmf->vma; + struct mm_struct *mm = vma->vm_mm; + unsigned long addr = vmf->address; + debug_dma_assert_idle(src); + if (likely(src)) { + copy_user_highpage(dst, src, addr, vma); + return true; + } + /* * If the source page was a PFN mapping, we don't have * a "struct page" for it. We do a best-effort copy by * just copying from the original user address. If that * fails, we just zero-fill it. Live with it. */ - if (unlikely(!src)) { - void *kaddr = kmap_atomic(dst); - void __user *uaddr = (void __user *)(va & PAGE_MASK); + kaddr = kmap_atomic(dst); + uaddr = (void __user *)(addr & PAGE_MASK); + + /* + * On architectures with software "accessed" bits, we would + * take a double page fault, so mark it accessed here. + */ + if (arch_faults_on_old_pte() && !pte_young(vmf->orig_pte)) { + pte_t entry; + + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* + * Other thread has already handled the fault + * and we don't need to do anything. If it's + * not the case, the fault will be triggered + * again on the same address. + */ + ret = false; + goto pte_unlock; + } + + entry = pte_mkyoung(vmf->orig_pte); + if (ptep_set_access_flags(vma, addr, vmf->pte, entry, 0)) + update_mmu_cache(vma, addr, vmf->pte); + } + + /* + * This really shouldn't fail, because the page is there + * in the page tables. But it might just be unreadable, + * in which case we just give up and fill the result with + * zeroes. + */ + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + if (locked) + goto warn; + + /* Re-validate under PTL if the page is still mapped */ + vmf->pte = pte_offset_map_lock(mm, vmf->pmd, addr, &vmf->ptl); + locked = true; + if (!likely(pte_same(*vmf->pte, vmf->orig_pte))) { + /* The PTE changed under us. Retry page fault. */ + ret = false; + goto pte_unlock; + } /* - * This really shouldn't fail, because the page is there - * in the page tables. But it might just be unreadable, - * in which case we just give up and fill the result with - * zeroes. + * The same page can be mapped back since last copy attampt. + * Try to copy again under PTL. */ - if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) + if (__copy_from_user_inatomic(kaddr, uaddr, PAGE_SIZE)) { + /* + * Give a warn in case there can be some obscure + * use-case + */ +warn: + WARN_ON_ONCE(1); clear_page(kaddr); - kunmap_atomic(kaddr); - flush_dcache_page(dst); - } else - copy_user_highpage(dst, src, va, vma); + } + } + + ret = true; + +pte_unlock: + if (locked) + pte_unmap_unlock(vmf->pte, vmf->ptl); + kunmap_atomic(kaddr); + flush_dcache_page(dst); + + return ret; } static gfp_t __get_fault_gfp_mask(struct vm_area_struct *vma) @@ -2342,7 +2423,19 @@ static vm_fault_t wp_page_copy(struct vm_fault *vmf) vmf->address); if (!new_page) goto oom; - cow_user_page(new_page, old_page, vmf->address, vma); + + if (!cow_user_page(new_page, old_page, vmf)) { + /* + * COW failed, if the fault was solved by other, + * it's fine. If not, userspace would re-fault on + * the same address and we will handle the fault + * from the second attempt. + */ + put_page(new_page); + if (old_page) + put_page(old_page); + return 0; + } } if (mem_cgroup_try_charge_delay(new_page, mm, GFP_KERNEL, &memcg, false)) diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index 3128d9584712..308beca3ffeb 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -725,7 +725,7 @@ void __ref move_pfn_range_to_zone(struct zone *zone, unsigned long start_pfn, * are reserved so nobody should be touching them so we should be safe */ memmap_init_zone(nr_pages, nid, zone_idx(zone), start_pfn, - MEMMAP_HOTPLUG, altmap); + MEMINIT_HOTPLUG, altmap); set_zone_contiguous(zone); } @@ -1082,7 +1082,8 @@ int __ref add_memory_resource(int nid, struct resource *res) } /* link memory sections under this node.*/ - ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1)); + ret = link_mem_sections(nid, PFN_DOWN(start), PFN_UP(start + size - 1), + MEMINIT_HOTPLUG); BUG_ON(ret); /* create new memmap entry */ @@ -1566,6 +1567,20 @@ static int __ref __offline_pages(unsigned long start_pfn, /* check again */ ret = walk_system_ram_range(start_pfn, end_pfn - start_pfn, NULL, check_pages_isolated_cb); + /* + * per-cpu pages are drained in start_isolate_page_range, but if + * there are still pages that are not free, make sure that we + * drain again, because when we isolated range we might + * have raced with another thread that was adding pages to pcp + * list. + * + * Forward progress should be still guaranteed because + * pages on the pcp list can only belong to MOVABLE_ZONE + * because has_unmovable_pages explicitly checks for + * PageBuddy on freed pages on other zones. + */ + if (ret) + drain_all_pages(zone); } while (ret); /* Ok, all of our target is isolated. diff --git a/mm/mmap.c b/mm/mmap.c index a3584a90c55c..ba78f1f1b1bd 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -2126,6 +2126,7 @@ arch_get_unmapped_area(struct file *filp, unsigned long addr, info.low_limit = mm->mmap_base; info.high_limit = mmap_end; info.align_mask = 0; + info.align_offset = 0; return vm_unmapped_area(&info); } #endif @@ -2167,6 +2168,7 @@ arch_get_unmapped_area_topdown(struct file *filp, unsigned long addr, info.low_limit = max(PAGE_SIZE, mmap_min_addr); info.high_limit = arch_get_mmap_base(addr, mm->mmap_base); info.align_mask = 0; + info.align_offset = 0; addr = vm_unmapped_area(&info); /* diff --git a/mm/mmu_context.c b/mm/mmu_context.c index 3e612ae748e9..a1da47e02747 100644 --- a/mm/mmu_context.c +++ b/mm/mmu_context.c @@ -25,13 +25,16 @@ void use_mm(struct mm_struct *mm) struct task_struct *tsk = current; task_lock(tsk); + /* Hold off tlb flush IPIs while switching mm's */ + local_irq_disable(); active_mm = tsk->active_mm; if (active_mm != mm) { mmgrab(mm); tsk->active_mm = mm; } tsk->mm = mm; - switch_mm(active_mm, mm, tsk); + switch_mm_irqs_off(active_mm, mm, tsk); + local_irq_enable(); task_unlock(tsk); #ifdef finish_arch_post_lock_switch finish_arch_post_lock_switch(); @@ -56,9 +59,11 @@ void unuse_mm(struct mm_struct *mm) task_lock(tsk); sync_mm_rss(mm); + local_irq_disable(); tsk->mm = NULL; /* active_mm is still 'mm' */ enter_lazy_tlb(mm, tsk); + local_irq_enable(); task_unlock(tsk); } EXPORT_SYMBOL_GPL(unuse_mm); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index d58c481b3df8..212e71874301 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -63,6 +63,8 @@ int sysctl_oom_dump_tasks = 1; * and mark_oom_victim */ DEFINE_MUTEX(oom_lock); +/* Serializes oom_score_adj and oom_score_adj_min updates */ +DEFINE_MUTEX(oom_adj_mutex); static inline bool is_memcg_oom(struct oom_control *oc) { diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 67a9943aa595..c20e664866c3 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -68,6 +68,7 @@ #include <linux/lockdep.h> #include <linux/nmi.h> #include <linux/psi.h> +#include <linux/khugepaged.h> #include <asm/sections.h> #include <asm/tlbflush.h> @@ -3129,7 +3130,7 @@ void split_page(struct page *page, unsigned int order) for (i = 1; i < (1 << order); i++) set_page_refcounted(page + i); - split_page_owner(page, order); + split_page_owner(page, 1 << order); } EXPORT_SYMBOL_GPL(split_page); @@ -3384,7 +3385,7 @@ static inline bool __should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) #endif /* CONFIG_FAIL_PAGE_ALLOC */ -static noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) +noinline bool should_fail_alloc_page(gfp_t gfp_mask, unsigned int order) { return __should_fail_alloc_page(gfp_mask, order); } @@ -5875,7 +5876,7 @@ overlap_memmap_init(unsigned long zone, unsigned long *pfn) * done. Non-atomic initialization, single-pass. */ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, - unsigned long start_pfn, enum memmap_context context, + unsigned long start_pfn, enum meminit_context context, struct vmem_altmap *altmap) { unsigned long pfn, end_pfn = start_pfn + size; @@ -5907,7 +5908,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, * There can be holes in boot-time mem_map[]s handed to this * function. They do not exist on hotplugged memory. */ - if (context == MEMMAP_EARLY) { + if (context == MEMINIT_EARLY) { if (!early_pfn_valid(pfn)) continue; if (!early_pfn_in_nid(pfn, nid)) @@ -5920,7 +5921,7 @@ void __meminit memmap_init_zone(unsigned long size, int nid, unsigned long zone, page = pfn_to_page(pfn); __init_single_page(page, pfn, zone, nid); - if (context == MEMMAP_HOTPLUG) + if (context == MEMINIT_HOTPLUG) __SetPageReserved(page); /* @@ -6002,7 +6003,7 @@ void __ref memmap_init_zone_device(struct zone *zone, * check here not to call set_pageblock_migratetype() against * pfn out of zone. * - * Please note that MEMMAP_HOTPLUG path doesn't clear memmap + * Please note that MEMINIT_HOTPLUG path doesn't clear memmap * because this is done early in section_activate() */ if (!(pfn & (pageblock_nr_pages - 1))) { @@ -6028,7 +6029,7 @@ static void __meminit zone_init_free_lists(struct zone *zone) void __meminit __weak memmap_init(unsigned long size, int nid, unsigned long zone, unsigned long start_pfn) { - memmap_init_zone(size, nid, zone, start_pfn, MEMMAP_EARLY, NULL); + memmap_init_zone(size, nid, zone, start_pfn, MEMINIT_EARLY, NULL); } static int zone_batchsize(struct zone *zone) @@ -7870,6 +7871,8 @@ int __meminit init_per_zone_wmark_min(void) setup_min_slab_ratio(); #endif + khugepaged_min_free_kbytes_update(); + return 0; } postcore_initcall(init_per_zone_wmark_min) diff --git a/mm/page_isolation.c b/mm/page_isolation.c index 89c19c0feadb..da0f6e1ae01e 100644 --- a/mm/page_isolation.c +++ b/mm/page_isolation.c @@ -187,6 +187,14 @@ __first_valid_page(unsigned long pfn, unsigned long nr_pages) * pageblocks we may have modified and return -EBUSY to caller. This * prevents two threads from simultaneously working on overlapping ranges. * + * Please note that there is no strong synchronization with the page allocator + * either. Pages might be freed while their page blocks are marked ISOLATED. + * In some cases pages might still end up on pcp lists and that would allow + * for their allocation even when they are in fact isolated already. Depending + * on how strong of a guarantee the caller needs drain_all_pages might be needed + * (e.g. __offline_pages will need to call it after check for isolated range for + * a next retry). + * * Return: the number of isolated pageblocks on success and -EBUSY if any part * of range cannot be isolated. */ diff --git a/mm/page_owner.c b/mm/page_owner.c index 18ecde9f45b2..83d08943bcde 100644 --- a/mm/page_owner.c +++ b/mm/page_owner.c @@ -204,7 +204,7 @@ void __set_page_owner_migrate_reason(struct page *page, int reason) page_owner->last_migrate_reason = reason; } -void __split_page_owner(struct page *page, unsigned int order) +void __split_page_owner(struct page *page, unsigned int nr) { int i; struct page_ext *page_ext = lookup_page_ext(page); @@ -213,7 +213,7 @@ void __split_page_owner(struct page *page, unsigned int order) if (unlikely(!page_ext)) return; - for (i = 0; i < (1 << order); i++) { + for (i = 0; i < nr; i++) { page_owner = get_page_owner(page_ext); page_owner->order = 0; page_ext = page_ext_next(page_ext); diff --git a/mm/pagewalk.c b/mm/pagewalk.c index d48c2a986ea3..4eb09e089881 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -16,9 +16,9 @@ static int walk_pte_range(pmd_t *pmd, unsigned long addr, unsigned long end, err = ops->pte_entry(pte, addr, addr + PAGE_SIZE, walk); if (err) break; - addr += PAGE_SIZE; - if (addr == end) + if (addr >= end - PAGE_SIZE) break; + addr += PAGE_SIZE; pte++; } diff --git a/mm/percpu.c b/mm/percpu.c index 7e06a1e58720..806bc16f88eb 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -1328,7 +1328,7 @@ static struct pcpu_chunk * __init pcpu_alloc_first_chunk(unsigned long tmp_addr, /* allocate chunk */ alloc_size = sizeof(struct pcpu_chunk) + - BITS_TO_LONGS(region_size >> PAGE_SHIFT); + BITS_TO_LONGS(region_size >> PAGE_SHIFT) * sizeof(unsigned long); chunk = memblock_alloc(alloc_size, SMP_CACHE_BYTES); if (!chunk) panic("%s: Failed to allocate %zu bytes\n", __func__, diff --git a/mm/shuffle.c b/mm/shuffle.c index b3fe97fd6654..56958ffa5a3a 100644 --- a/mm/shuffle.c +++ b/mm/shuffle.c @@ -58,25 +58,25 @@ module_param_call(shuffle, shuffle_store, shuffle_show, &shuffle_param, 0400); * For two pages to be swapped in the shuffle, they must be free (on a * 'free_area' lru), have the same order, and have the same migratetype. */ -static struct page * __meminit shuffle_valid_page(unsigned long pfn, int order) +static struct page * __meminit shuffle_valid_page(struct zone *zone, + unsigned long pfn, int order) { - struct page *page; + struct page *page = pfn_to_online_page(pfn); /* * Given we're dealing with randomly selected pfns in a zone we * need to ask questions like... */ - /* ...is the pfn even in the memmap? */ - if (!pfn_valid_within(pfn)) + /* ... is the page managed by the buddy? */ + if (!page) return NULL; - /* ...is the pfn in a present section or a hole? */ - if (!pfn_present(pfn)) + /* ... is the page assigned to the same zone? */ + if (page_zone(page) != zone) return NULL; /* ...is the page free and currently on a free_area list? */ - page = pfn_to_page(pfn); if (!PageBuddy(page)) return NULL; @@ -123,7 +123,7 @@ void __meminit __shuffle_zone(struct zone *z) * page_j randomly selected in the span @zone_start_pfn to * @spanned_pages. */ - page_i = shuffle_valid_page(i, order); + page_i = shuffle_valid_page(z, i, order); if (!page_i) continue; @@ -137,7 +137,7 @@ void __meminit __shuffle_zone(struct zone *z) j = z->zone_start_pfn + ALIGN_DOWN(get_random_long() % z->spanned_pages, order_pages); - page_j = shuffle_valid_page(j, order); + page_j = shuffle_valid_page(z, j, order); if (page_j && page_j != page_i) break; } diff --git a/mm/slub.c b/mm/slub.c index 709e31002504..d69934eac9e9 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -533,15 +533,32 @@ static void print_section(char *level, char *text, u8 *addr, metadata_access_disable(); } +/* + * See comment in calculate_sizes(). + */ +static inline bool freeptr_outside_object(struct kmem_cache *s) +{ + return s->offset >= s->inuse; +} + +/* + * Return offset of the end of info block which is inuse + free pointer if + * not overlapping with object. + */ +static inline unsigned int get_info_end(struct kmem_cache *s) +{ + if (freeptr_outside_object(s)) + return s->inuse + sizeof(void *); + else + return s->inuse; +} + static struct track *get_track(struct kmem_cache *s, void *object, enum track_item alloc) { struct track *p; - if (s->offset) - p = object + s->offset + sizeof(void *); - else - p = object + s->inuse; + p = object + get_info_end(s); return p + alloc; } @@ -645,12 +662,12 @@ static void slab_fix(struct kmem_cache *s, char *fmt, ...) } static bool freelist_corrupted(struct kmem_cache *s, struct page *page, - void *freelist, void *nextfree) + void **freelist, void *nextfree) { if ((s->flags & SLAB_CONSISTENCY_CHECKS) && - !check_valid_pointer(s, page, nextfree)) { - object_err(s, page, freelist, "Freechain corrupt"); - freelist = NULL; + !check_valid_pointer(s, page, nextfree) && freelist) { + object_err(s, page, *freelist, "Freechain corrupt"); + *freelist = NULL; slab_fix(s, "Isolate corrupted freechain"); return true; } @@ -682,10 +699,7 @@ static void print_trailer(struct kmem_cache *s, struct page *page, u8 *p) print_section(KERN_ERR, "Redzone ", p + s->object_size, s->inuse - s->object_size); - if (s->offset) - off = s->offset + sizeof(void *); - else - off = s->inuse; + off = get_info_end(s); if (s->flags & SLAB_STORE_USER) off += 2 * sizeof(struct track); @@ -776,7 +790,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, * object address * Bytes of the object to be managed. * If the freepointer may overlay the object then the free - * pointer is the first word of the object. + * pointer is at the middle of the object. * * Poisoning uses 0x6b (POISON_FREE) and the last byte is * 0xa5 (POISON_END) @@ -810,11 +824,7 @@ static int check_bytes_and_report(struct kmem_cache *s, struct page *page, static int check_pad_bytes(struct kmem_cache *s, struct page *page, u8 *p) { - unsigned long off = s->inuse; /* The end of info */ - - if (s->offset) - /* Freepointer is placed after the object. */ - off += sizeof(void *); + unsigned long off = get_info_end(s); /* The end of info */ if (s->flags & SLAB_STORE_USER) /* We also have user information there */ @@ -900,7 +910,7 @@ static int check_object(struct kmem_cache *s, struct page *page, check_pad_bytes(s, page, p); } - if (!s->offset && val == SLUB_RED_ACTIVE) + if (!freeptr_outside_object(s) && val == SLUB_RED_ACTIVE) /* * Object and freepointer overlap. Cannot check * freepointer while object is allocated. @@ -1394,7 +1404,7 @@ static inline void dec_slabs_node(struct kmem_cache *s, int node, int objects) {} static bool freelist_corrupted(struct kmem_cache *s, struct page *page, - void *freelist, void *nextfree) + void **freelist, void *nextfree) { return false; } @@ -2086,7 +2096,7 @@ static void deactivate_slab(struct kmem_cache *s, struct page *page, * 'freelist' is already corrupted. So isolate all objects * starting at 'freelist'. */ - if (freelist_corrupted(s, page, freelist, nextfree)) + if (freelist_corrupted(s, page, &freelist, nextfree)) break; do { @@ -3585,6 +3595,11 @@ static int calculate_sizes(struct kmem_cache *s, int forced_order) * * This is the case if we do RCU, have a constructor or * destructor or are poisoning the objects. + * + * The assumption that s->offset >= s->inuse means free + * pointer is outside of the object is used in the + * freeptr_outside_object() function. If that is no + * longer true, the function needs to be modified. */ s->offset = size; size += sizeof(void *); diff --git a/mm/swap_state.c b/mm/swap_state.c index 4ce014dc4571..7c434fcfff0d 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -511,10 +511,11 @@ static unsigned long swapin_nr_pages(unsigned long offset) return 1; hits = atomic_xchg(&swapin_readahead_hits, 0); - pages = __swapin_nr_pages(prev_offset, offset, hits, max_pages, + pages = __swapin_nr_pages(READ_ONCE(prev_offset), offset, hits, + max_pages, atomic_read(&last_readahead_pages)); if (!hits) - prev_offset = offset; + WRITE_ONCE(prev_offset, offset); atomic_set(&last_readahead_pages, pages); return pages; diff --git a/mm/swapfile.c b/mm/swapfile.c index 891a3ef48651..ff83ffe7a910 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -1038,7 +1038,7 @@ start_over: goto nextsi; } if (size == SWAPFILE_CLUSTER) { - if (!(si->flags & SWP_FS)) + if (si->flags & SWP_BLKDEV) n_ret = swap_alloc_cluster(si, swp_entries); } else n_ret = scan_swap_map_slots(si, SWAP_HAS_CACHE, @@ -2132,7 +2132,7 @@ int try_to_unuse(unsigned int type, bool frontswap, swp_entry_t entry; unsigned int i; - if (!si->inuse_pages) + if (!READ_ONCE(si->inuse_pages)) return 0; if (!frontswap) @@ -2148,7 +2148,7 @@ retry: spin_lock(&mmlist_lock); p = &init_mm.mmlist; - while (si->inuse_pages && + while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (p = p->next) != &init_mm.mmlist) { @@ -2177,7 +2177,7 @@ retry: mmput(prev_mm); i = 0; - while (si->inuse_pages && + while (READ_ONCE(si->inuse_pages) && !signal_pending(current) && (i = find_next_to_unuse(si, i, frontswap)) != 0) { @@ -2219,7 +2219,7 @@ retry: * been preempted after get_swap_page(), temporarily hiding that swap. * It's easy and robust (though cpu-intensive) just to keep retrying. */ - if (si->inuse_pages) { + if (READ_ONCE(si->inuse_pages)) { if (!signal_pending(current)) goto retry; retval = -EINTR; @@ -2737,10 +2737,10 @@ static void *swap_next(struct seq_file *swap, void *v, loff_t *pos) else type = si->type + 1; + ++(*pos); for (; (si = swap_type_to_swap_info(type)); type++) { if (!(si->flags & SWP_USED) || !si->swap_map) continue; - ++*pos; return si; } @@ -3284,7 +3284,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = inode_drain_writes(inode); if (error) { inode->i_flags &= ~S_SWAPFILE; - goto bad_swap_unlock_inode; + goto free_swap_address_space; } mutex_lock(&swapon_mutex); @@ -3309,6 +3309,8 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) error = 0; goto out; +free_swap_address_space: + exit_swap_address_space(p->type); bad_swap_unlock_inode: inode_unlock(inode); bad_swap: diff --git a/mm/vmalloc.c b/mm/vmalloc.c index ad4d00bd7914..5797e1eeaa7e 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -85,6 +85,8 @@ static void vunmap_pmd_range(pud_t *pud, unsigned long addr, unsigned long end) if (pmd_none_or_clear_bad(pmd)) continue; vunmap_pte_range(pmd, addr, next); + + cond_resched(); } while (pmd++, addr = next, addr != end); } diff --git a/mm/vmscan.c b/mm/vmscan.c index 7fde5f904c8d..10feb872d9a4 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2775,6 +2775,14 @@ static bool shrink_node(pg_data_t *pgdat, struct scan_control *sc) unsigned long reclaimed; unsigned long scanned; + /* + * This loop can become CPU-bound when target memcgs + * aren't eligible for reclaim - either because they + * don't have any reclaimable pages, or because their + * memory is explicitly protected. Avoid soft lockups. + */ + cond_resched(); + switch (mem_cgroup_protected(root, memcg)) { case MEMCG_PROT_MIN: /* @@ -3160,8 +3168,9 @@ static bool allow_direct_reclaim(pg_data_t *pgdat) /* kswapd must be awake if processes are being throttled */ if (!wmark_ok && waitqueue_active(&pgdat->kswapd_wait)) { - pgdat->kswapd_classzone_idx = min(pgdat->kswapd_classzone_idx, - (enum zone_type)ZONE_NORMAL); + if (READ_ONCE(pgdat->kswapd_classzone_idx) > ZONE_NORMAL) + WRITE_ONCE(pgdat->kswapd_classzone_idx, ZONE_NORMAL); + wake_up_interruptible(&pgdat->kswapd_wait); } @@ -3793,9 +3802,9 @@ out: static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat, enum zone_type prev_classzone_idx) { - if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) - return prev_classzone_idx; - return pgdat->kswapd_classzone_idx; + enum zone_type curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx); + + return curr_idx == MAX_NR_ZONES ? prev_classzone_idx : curr_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, @@ -3839,8 +3848,11 @@ static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_o * the previous request that slept prematurely. */ if (remaining) { - pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); - pgdat->kswapd_order = max(pgdat->kswapd_order, reclaim_order); + WRITE_ONCE(pgdat->kswapd_classzone_idx, + kswapd_classzone_idx(pgdat, classzone_idx)); + + if (READ_ONCE(pgdat->kswapd_order) < reclaim_order) + WRITE_ONCE(pgdat->kswapd_order, reclaim_order); } finish_wait(&pgdat->kswapd_wait, &wait); @@ -3917,12 +3929,12 @@ static int kswapd(void *p) tsk->flags |= PF_MEMALLOC | PF_SWAPWRITE | PF_KSWAPD; set_freezable(); - pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = MAX_NR_ZONES; + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES); for ( ; ; ) { bool ret; - alloc_order = reclaim_order = pgdat->kswapd_order; + alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); kswapd_try_sleep: @@ -3930,10 +3942,10 @@ kswapd_try_sleep: classzone_idx); /* Read the new order and classzone_idx */ - alloc_order = reclaim_order = pgdat->kswapd_order; + alloc_order = reclaim_order = READ_ONCE(pgdat->kswapd_order); classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); - pgdat->kswapd_order = 0; - pgdat->kswapd_classzone_idx = MAX_NR_ZONES; + WRITE_ONCE(pgdat->kswapd_order, 0); + WRITE_ONCE(pgdat->kswapd_classzone_idx, MAX_NR_ZONES); ret = try_to_freeze(); if (kthread_should_stop()) @@ -3977,20 +3989,23 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, enum zone_type classzone_idx) { pg_data_t *pgdat; + enum zone_type curr_idx; if (!managed_zone(zone)) return; if (!cpuset_zone_allowed(zone, gfp_flags)) return; + pgdat = zone->zone_pgdat; + curr_idx = READ_ONCE(pgdat->kswapd_classzone_idx); + + if (curr_idx == MAX_NR_ZONES || curr_idx < classzone_idx) + WRITE_ONCE(pgdat->kswapd_classzone_idx, classzone_idx); + + if (READ_ONCE(pgdat->kswapd_order) < order) + WRITE_ONCE(pgdat->kswapd_order, order); - if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) - pgdat->kswapd_classzone_idx = classzone_idx; - else - pgdat->kswapd_classzone_idx = max(pgdat->kswapd_classzone_idx, - classzone_idx); - pgdat->kswapd_order = max(pgdat->kswapd_order, order); if (!waitqueue_active(&pgdat->kswapd_wait)) return; |