diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/huge_memory.c | 92 | ||||
-rw-r--r-- | mm/kmemleak.c | 7 | ||||
-rw-r--r-- | mm/memory.c | 29 | ||||
-rw-r--r-- | mm/memory_hotplug.c | 2 | ||||
-rw-r--r-- | mm/mlock.c | 18 | ||||
-rw-r--r-- | mm/mmap.c | 26 | ||||
-rw-r--r-- | mm/oom_kill.c | 37 | ||||
-rw-r--r-- | mm/page_alloc.c | 60 | ||||
-rw-r--r-- | mm/page_cgroup.c | 2 | ||||
-rw-r--r-- | mm/prio_tree.c | 1 | ||||
-rw-r--r-- | mm/shmem.c | 155 | ||||
-rw-r--r-- | mm/slab.c | 1 | ||||
-rw-r--r-- | mm/slub.c | 4 | ||||
-rw-r--r-- | mm/swap.c | 3 | ||||
-rw-r--r-- | mm/vmscan.c | 27 | ||||
-rw-r--r-- | mm/vmstat.c | 18 |
16 files changed, 275 insertions, 207 deletions
diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 0a619e0..83326ad 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -244,24 +244,28 @@ static ssize_t single_flag_show(struct kobject *kobj, struct kobj_attribute *attr, char *buf, enum transparent_hugepage_flag flag) { - if (test_bit(flag, &transparent_hugepage_flags)) - return sprintf(buf, "[yes] no\n"); - else - return sprintf(buf, "yes [no]\n"); + return sprintf(buf, "%d\n", + !!test_bit(flag, &transparent_hugepage_flags)); } + static ssize_t single_flag_store(struct kobject *kobj, struct kobj_attribute *attr, const char *buf, size_t count, enum transparent_hugepage_flag flag) { - if (!memcmp("yes", buf, - min(sizeof("yes")-1, count))) { + unsigned long value; + int ret; + + ret = kstrtoul(buf, 10, &value); + if (ret < 0) + return ret; + if (value > 1) + return -EINVAL; + + if (value) set_bit(flag, &transparent_hugepage_flags); - } else if (!memcmp("no", buf, - min(sizeof("no")-1, count))) { + else clear_bit(flag, &transparent_hugepage_flags); - } else - return -EINVAL; return count; } @@ -680,8 +684,11 @@ int do_huge_pmd_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, return VM_FAULT_OOM; page = alloc_hugepage_vma(transparent_hugepage_defrag(vma), vma, haddr, numa_node_id(), 0); - if (unlikely(!page)) + if (unlikely(!page)) { + count_vm_event(THP_FAULT_FALLBACK); goto out; + } + count_vm_event(THP_FAULT_ALLOC); if (unlikely(mem_cgroup_newpage_charge(page, mm, GFP_KERNEL))) { put_page(page); goto out; @@ -909,11 +916,13 @@ int do_huge_pmd_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, new_page = NULL; if (unlikely(!new_page)) { + count_vm_event(THP_FAULT_FALLBACK); ret = do_huge_pmd_wp_page_fallback(mm, vma, address, pmd, orig_pmd, page, haddr); put_page(page); goto out; } + count_vm_event(THP_FAULT_ALLOC); if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { put_page(new_page); @@ -1390,6 +1399,7 @@ int split_huge_page(struct page *page) BUG_ON(!PageSwapBacked(page)); __split_huge_page(page, anon_vma); + count_vm_event(THP_SPLIT); BUG_ON(PageCompound(page)); out_unlock: @@ -1398,6 +1408,9 @@ out: return ret; } +#define VM_NO_THP (VM_SPECIAL|VM_INSERTPAGE|VM_MIXEDMAP|VM_SAO| \ + VM_HUGETLB|VM_SHARED|VM_MAYSHARE) + int hugepage_madvise(struct vm_area_struct *vma, unsigned long *vm_flags, int advice) { @@ -1406,11 +1419,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_HUGEPAGE | - VM_SHARED | VM_MAYSHARE | - VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE | - VM_MIXEDMAP | VM_SAO)) + if (*vm_flags & (VM_HUGEPAGE | VM_NO_THP)) return -EINVAL; *vm_flags &= ~VM_NOHUGEPAGE; *vm_flags |= VM_HUGEPAGE; @@ -1426,11 +1435,7 @@ int hugepage_madvise(struct vm_area_struct *vma, /* * Be somewhat over-protective like KSM for now! */ - if (*vm_flags & (VM_NOHUGEPAGE | - VM_SHARED | VM_MAYSHARE | - VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_RESERVED | VM_HUGETLB | VM_INSERTPAGE | - VM_MIXEDMAP | VM_SAO)) + if (*vm_flags & (VM_NOHUGEPAGE | VM_NO_THP)) return -EINVAL; *vm_flags &= ~VM_HUGEPAGE; *vm_flags |= VM_NOHUGEPAGE; @@ -1564,10 +1569,14 @@ int khugepaged_enter_vma_merge(struct vm_area_struct *vma) * page fault if needed. */ return 0; - if (vma->vm_file || vma->vm_ops) + if (vma->vm_ops) /* khugepaged not yet working on file or special mappings */ return 0; - VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + /* + * If is_pfn_mapping() is true is_learn_pfn_mapping() must be + * true too, verify it here. + */ + VM_BUG_ON(is_linear_pfn_mapping(vma) || vma->vm_flags & VM_NO_THP); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; if (hstart < hend) @@ -1784,9 +1793,11 @@ static void collapse_huge_page(struct mm_struct *mm, node, __GFP_OTHER_NODE); if (unlikely(!new_page)) { up_read(&mm->mmap_sem); + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); *hpage = ERR_PTR(-ENOMEM); return; } + count_vm_event(THP_COLLAPSE_ALLOC); if (unlikely(mem_cgroup_newpage_charge(new_page, mm, GFP_KERNEL))) { up_read(&mm->mmap_sem); put_page(new_page); @@ -1816,12 +1827,15 @@ static void collapse_huge_page(struct mm_struct *mm, (vma->vm_flags & VM_NOHUGEPAGE)) goto out; - /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ - if (!vma->anon_vma || vma->vm_ops || vma->vm_file) + if (!vma->anon_vma || vma->vm_ops) goto out; if (is_vma_temporary_stack(vma)) goto out; - VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + /* + * If is_pfn_mapping() is true is_learn_pfn_mapping() must be + * true too, verify it here. + */ + VM_BUG_ON(is_linear_pfn_mapping(vma) || vma->vm_flags & VM_NO_THP); pgd = pgd_offset(mm, address); if (!pgd_present(*pgd)) @@ -2054,13 +2068,16 @@ static unsigned int khugepaged_scan_mm_slot(unsigned int pages, progress++; continue; } - /* VM_PFNMAP vmas may have vm_ops null but vm_file set */ - if (!vma->anon_vma || vma->vm_ops || vma->vm_file) + if (!vma->anon_vma || vma->vm_ops) goto skip; if (is_vma_temporary_stack(vma)) goto skip; - - VM_BUG_ON(is_linear_pfn_mapping(vma) || is_pfn_mapping(vma)); + /* + * If is_pfn_mapping() is true is_learn_pfn_mapping() + * must be true too, verify it here. + */ + VM_BUG_ON(is_linear_pfn_mapping(vma) || + vma->vm_flags & VM_NO_THP); hstart = (vma->vm_start + ~HPAGE_PMD_MASK) & HPAGE_PMD_MASK; hend = vma->vm_end & HPAGE_PMD_MASK; @@ -2151,8 +2168,11 @@ static void khugepaged_do_scan(struct page **hpage) #ifndef CONFIG_NUMA if (!*hpage) { *hpage = alloc_hugepage(khugepaged_defrag()); - if (unlikely(!*hpage)) + if (unlikely(!*hpage)) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); break; + } + count_vm_event(THP_COLLAPSE_ALLOC); } #else if (IS_ERR(*hpage)) @@ -2192,8 +2212,11 @@ static struct page *khugepaged_alloc_hugepage(void) do { hpage = alloc_hugepage(khugepaged_defrag()); - if (!hpage) + if (!hpage) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); khugepaged_alloc_sleep(); + } else + count_vm_event(THP_COLLAPSE_ALLOC); } while (unlikely(!hpage) && likely(khugepaged_enabled())); return hpage; @@ -2210,8 +2233,11 @@ static void khugepaged_loop(void) while (likely(khugepaged_enabled())) { #ifndef CONFIG_NUMA hpage = khugepaged_alloc_hugepage(); - if (unlikely(!hpage)) + if (unlikely(!hpage)) { + count_vm_event(THP_COLLAPSE_ALLOC_FAILED); break; + } + count_vm_event(THP_COLLAPSE_ALLOC); #else if (IS_ERR(hpage)) { khugepaged_alloc_sleep(); diff --git a/mm/kmemleak.c b/mm/kmemleak.c index c1d5867..aacee45 100644 --- a/mm/kmemleak.c +++ b/mm/kmemleak.c @@ -1414,9 +1414,12 @@ static void *kmemleak_seq_next(struct seq_file *seq, void *v, loff_t *pos) ++(*pos); list_for_each_continue_rcu(n, &object_list) { - next_obj = list_entry(n, struct kmemleak_object, object_list); - if (get_object(next_obj)) + struct kmemleak_object *obj = + list_entry(n, struct kmemleak_object, object_list); + if (get_object(obj)) { + next_obj = obj; break; + } } put_object(prev_obj); diff --git a/mm/memory.c b/mm/memory.c index 9da8cab..61e66f0 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -1359,7 +1359,7 @@ split_fallthrough: */ mark_page_accessed(page); } - if (flags & FOLL_MLOCK) { + if ((flags & FOLL_MLOCK) && (vma->vm_flags & VM_LOCKED)) { /* * The preliminary mapping check is mainly to avoid the * pointless overhead of lock_page on the ZERO_PAGE @@ -1410,6 +1410,12 @@ no_page_table: return page; } +static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) +{ + return stack_guard_page_start(vma, addr) || + stack_guard_page_end(vma, addr+PAGE_SIZE); +} + /** * __get_user_pages() - pin user pages in memory * @tsk: task_struct of target task @@ -1488,7 +1494,6 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, vma = find_extend_vma(mm, start); if (!vma && in_gate_area(mm, start)) { unsigned long pg = start & PAGE_MASK; - struct vm_area_struct *gate_vma = get_gate_vma(mm); pgd_t *pgd; pud_t *pud; pmd_t *pmd; @@ -1513,10 +1518,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, pte_unmap(pte); return i ? : -EFAULT; } + vma = get_gate_vma(mm); if (pages) { struct page *page; - page = vm_normal_page(gate_vma, start, *pte); + page = vm_normal_page(vma, start, *pte); if (!page) { if (!(gup_flags & FOLL_DUMP) && is_zero_pfn(pte_pfn(*pte))) @@ -1530,12 +1536,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, get_page(page); } pte_unmap(pte); - if (vmas) - vmas[i] = gate_vma; - i++; - start += PAGE_SIZE; - nr_pages--; - continue; + goto next_page; } if (!vma || @@ -1565,6 +1566,11 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, int ret; unsigned int fault_flags = 0; + /* For mlock, just skip the stack guard page. */ + if (foll_flags & FOLL_MLOCK) { + if (stack_guard_page(vma, start)) + goto next_page; + } if (foll_flags & FOLL_WRITE) fault_flags |= FAULT_FLAG_WRITE; if (nonblocking) @@ -1631,6 +1637,7 @@ int __get_user_pages(struct task_struct *tsk, struct mm_struct *mm, flush_anon_page(vma, page, start); flush_dcache_page(page); } +next_page: if (vmas) vmas[i] = vma; i++; @@ -3386,7 +3393,7 @@ int handle_mm_fault(struct mm_struct *mm, struct vm_area_struct *vma, * run pte_offset_map on the pmd, if an huge pmd could * materialize from under us from a different thread. */ - if (unlikely(__pte_alloc(mm, vma, pmd, address))) + if (unlikely(pmd_none(*pmd)) && __pte_alloc(mm, vma, pmd, address)) return VM_FAULT_OOM; /* if an huge pmd materialized from under us just retry later */ if (unlikely(pmd_trans_huge(*pmd))) @@ -3678,7 +3685,7 @@ static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, */ #ifdef CONFIG_HAVE_IOREMAP_PROT vma = find_vma(mm, addr); - if (!vma) + if (!vma || vma->vm_start > addr) break; if (vma->vm_ops && vma->vm_ops->access) ret = vma->vm_ops->access(vma, addr, buf, diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a2acaf8..9ca1d60 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -375,7 +375,7 @@ void online_page(struct page *page) #endif #ifdef CONFIG_FLATMEM - max_mapnr = max(page_to_pfn(page), max_mapnr); + max_mapnr = max(pfn, max_mapnr); #endif ClearPageReserved(page); @@ -135,13 +135,6 @@ void munlock_vma_page(struct page *page) } } -static inline int stack_guard_page(struct vm_area_struct *vma, unsigned long addr) -{ - return (vma->vm_flags & VM_GROWSDOWN) && - (vma->vm_start == addr) && - !vma_stack_continue(vma->vm_prev, addr); -} - /** * __mlock_vma_pages_range() - mlock a range of pages in the vma. * @vma: target vma @@ -169,7 +162,7 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, VM_BUG_ON(end > vma->vm_end); VM_BUG_ON(!rwsem_is_locked(&mm->mmap_sem)); - gup_flags = FOLL_TOUCH; + gup_flags = FOLL_TOUCH | FOLL_MLOCK; /* * We want to touch writable mappings with a write fault in order * to break COW, except for shared mappings because these don't COW @@ -185,15 +178,6 @@ static long __mlock_vma_pages_range(struct vm_area_struct *vma, if (vma->vm_flags & (VM_READ | VM_WRITE | VM_EXEC)) gup_flags |= FOLL_FORCE; - if (vma->vm_flags & VM_LOCKED) - gup_flags |= FOLL_MLOCK; - - /* We don't try to access the guard page of a stack vma */ - if (stack_guard_page(vma, start)) { - addr += PAGE_SIZE; - nr_pages--; - } - return __get_user_pages(current, mm, addr, nr_pages, gup_flags, NULL, NULL, nonblocking); } @@ -259,7 +259,7 @@ SYSCALL_DEFINE1(brk, unsigned long, brk) * randomize_va_space to 2, which will still cause mm->start_brk * to be arbitrarily shifted */ - if (mm->start_brk > PAGE_ALIGN(mm->end_data)) + if (current->brk_randomized) min_brk = mm->start_brk; else min_brk = mm->end_data; @@ -1767,10 +1767,13 @@ int expand_upwards(struct vm_area_struct *vma, unsigned long address) size = address - vma->vm_start; grow = (address - vma->vm_end) >> PAGE_SHIFT; - error = acct_stack_growth(vma, size, grow); - if (!error) { - vma->vm_end = address; - perf_event_mmap(vma); + error = -ENOMEM; + if (vma->vm_pgoff + (size >> PAGE_SHIFT) >= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + vma->vm_end = address; + perf_event_mmap(vma); + } } } vma_unlock_anon_vma(vma); @@ -1814,11 +1817,14 @@ static int expand_downwards(struct vm_area_struct *vma, size = vma->vm_end - address; grow = (vma->vm_start - address) >> PAGE_SHIFT; - error = acct_stack_growth(vma, size, grow); - if (!error) { - vma->vm_start = address; - vma->vm_pgoff -= grow; - perf_event_mmap(vma); + error = -ENOMEM; + if (grow <= vma->vm_pgoff) { + error = acct_stack_growth(vma, size, grow); + if (!error) { + vma->vm_start = address; + vma->vm_pgoff -= grow; + perf_event_mmap(vma); + } } } vma_unlock_anon_vma(vma); diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 6a819d1..f52e85c 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -84,24 +84,6 @@ static bool has_intersects_mems_allowed(struct task_struct *tsk, #endif /* CONFIG_NUMA */ /* - * If this is a system OOM (not a memcg OOM) and the task selected to be - * killed is not already running at high (RT) priorities, speed up the - * recovery by boosting the dying task to the lowest FIFO priority. - * That helps with the recovery and avoids interfering with RT tasks. - */ -static void boost_dying_task_prio(struct task_struct *p, - struct mem_cgroup *mem) -{ - struct sched_param param = { .sched_priority = 1 }; - - if (mem) - return; - - if (!rt_task(p)) - sched_setscheduler_nocheck(p, SCHED_FIFO, ¶m); -} - -/* * The process p may have detached its own ->mm while exiting or through * use_mm(), but one or more of its subthreads may still have a valid * pointer. Return p, or any of its subthreads with a valid ->mm, with @@ -190,10 +172,13 @@ unsigned int oom_badness(struct task_struct *p, struct mem_cgroup *mem, /* * The baseline for the badness score is the proportion of RAM that each - * task's rss and swap space use. + * task's rss, pagetable and swap space use. */ - points = (get_mm_rss(p->mm) + get_mm_counter(p->mm, MM_SWAPENTS)) * 1000 / - totalpages; + points = get_mm_rss(p->mm) + p->mm->nr_ptes; + points += get_mm_counter(p->mm, MM_SWAPENTS); + + points *= 1000; + points /= totalpages; task_unlock(p); /* @@ -452,13 +437,6 @@ static int oom_kill_task(struct task_struct *p, struct mem_cgroup *mem) set_tsk_thread_flag(p, TIF_MEMDIE); force_sig(SIGKILL, p); - /* - * We give our sacrificial lamb high priority and access to - * all the memory it needs. That way it should be able to - * exit() and clear out its resources quickly... - */ - boost_dying_task_prio(p, mem); - return 0; } #undef K @@ -482,7 +460,6 @@ static int oom_kill_process(struct task_struct *p, gfp_t gfp_mask, int order, */ if (p->flags & PF_EXITING) { set_tsk_thread_flag(p, TIF_MEMDIE); - boost_dying_task_prio(p, mem); return 0; } @@ -556,7 +533,6 @@ void mem_cgroup_out_of_memory(struct mem_cgroup *mem, gfp_t gfp_mask) */ if (fatal_signal_pending(current)) { set_thread_flag(TIF_MEMDIE); - boost_dying_task_prio(current, NULL); return; } @@ -712,7 +688,6 @@ void out_of_memory(struct zonelist *zonelist, gfp_t gfp_mask, */ if (fatal_signal_pending(current)) { set_thread_flag(TIF_MEMDIE); - boost_dying_task_prio(current, NULL); return; } diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 2747f5e5a..d49df78 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -54,6 +54,7 @@ #include <trace/events/kmem.h> #include <linux/ftrace_event.h> #include <linux/memcontrol.h> +#include <linux/prefetch.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -2317,6 +2318,21 @@ void free_pages(unsigned long addr, unsigned int order) EXPORT_SYMBOL(free_pages); +static void *make_alloc_exact(unsigned long addr, unsigned order, size_t size) +{ + if (addr) { + unsigned long alloc_end = addr + (PAGE_SIZE << order); + unsigned long used = addr + PAGE_ALIGN(size); + + split_page(virt_to_page((void *)addr), order); + while (used < alloc_end) { + free_page(used); + used += PAGE_SIZE; + } + } + return (void *)addr; +} + /** * alloc_pages_exact - allocate an exact number physically-contiguous pages. * @size: the number of bytes to allocate @@ -2336,22 +2352,33 @@ void *alloc_pages_exact(size_t size, gfp_t gfp_mask) unsigned long addr; addr = __get_free_pages(gfp_mask, order); - if (addr) { - unsigned long alloc_end = addr + (PAGE_SIZE << order); - unsigned long used = addr + PAGE_ALIGN(size); - - split_page(virt_to_page((void *)addr), order); - while (used < alloc_end) { - free_page(used); - used += PAGE_SIZE; - } - } - - return (void *)addr; + return make_alloc_exact(addr, order, size); } EXPORT_SYMBOL(alloc_pages_exact); /** + * alloc_pages_exact_nid - allocate an exact number of physically-contiguous + * pages on a node. + * @nid: the preferred node ID where memory should be allocated + * @size: the number of bytes to allocate + * @gfp_mask: GFP flags for the allocation + * + * Like alloc_pages_exact(), but try to allocate on node nid first before falling + * back. + * Note this is not alloc_pages_exact_node() which allocates on a specific node, + * but is not exact. + */ +void *alloc_pages_exact_nid(int nid, size_t size, gfp_t gfp_mask) +{ + unsigned order = get_order(size); + struct page *p = alloc_pages_node(nid, gfp_mask, order); + if (!p) + return NULL; + return make_alloc_exact((unsigned long)page_address(p), order, size); +} +EXPORT_SYMBOL(alloc_pages_exact_nid); + +/** * free_pages_exact - release memory allocated via alloc_pages_exact() * @virt: the value returned by alloc_pages_exact. * @size: size of allocation, same value as passed to alloc_pages_exact(). @@ -3176,7 +3203,7 @@ static __init_refok int __build_all_zonelists(void *data) * Called with zonelists_mutex held always * unless system_state == SYSTEM_BOOTING. */ -void build_all_zonelists(void *data) +void __ref build_all_zonelists(void *data) { set_zonelist_order(); @@ -3564,7 +3591,7 @@ int zone_wait_table_init(struct zone *zone, unsigned long zone_size_pages) if (!slab_is_available()) { zone->wait_table = (wait_queue_head_t *) - alloc_bootmem_node(pgdat, alloc_size); + alloc_bootmem_node_nopanic(pgdat, alloc_size); } else { /* * This case means that a zone whose size was 0 gets new memory @@ -4141,7 +4168,8 @@ static void __init setup_usemap(struct pglist_data *pgdat, unsigned long usemapsize = usemap_size(zonesize); zone->pageblock_flags = NULL; if (usemapsize) - zone->pageblock_flags = alloc_bootmem_node(pgdat, usemapsize); + zone->pageblock_flags = alloc_bootmem_node_nopanic(pgdat, + usemapsize); } #else static inline void setup_usemap(struct pglist_data *pgdat, @@ -4307,7 +4335,7 @@ static void __init_refok alloc_node_mem_map(struct pglist_data *pgdat) size = (end - start) * sizeof(struct page); map = alloc_remap(pgdat->node_id, size); if (!map) - map = alloc_bootmem_node(pgdat, size); + map = alloc_bootmem_node_nopanic(pgdat, size); pgdat->node_mem_map = map + (pgdat->node_start_pfn - start); } #ifndef CONFIG_NEED_MULTIPLE_NODES diff --git a/mm/page_cgroup.c b/mm/page_cgroup.c index 9905501..2daadc3 100644 --- a/mm/page_cgroup.c +++ b/mm/page_cgroup.c @@ -134,7 +134,7 @@ static void *__init_refok alloc_page_cgroup(size_t size, int nid) { void *addr = NULL; - addr = alloc_pages_exact(size, GFP_KERNEL | __GFP_NOWARN); + addr = alloc_pages_exact_nid(nid, size, GFP_KERNEL | __GFP_NOWARN); if (addr) return addr; diff --git a/mm/prio_tree.c b/mm/prio_tree.c index 603ae98..799dcfd 100644 --- a/mm/prio_tree.c +++ b/mm/prio_tree.c @@ -13,6 +13,7 @@ #include <linux/mm.h> #include <linux/prio_tree.h> +#include <linux/prefetch.h> /* * See lib/prio_tree.c for details on the general radix priority search tree @@ -421,7 +421,8 @@ static swp_entry_t *shmem_swp_alloc(struct shmem_inode_info *info, unsigned long * a waste to allocate index if we cannot allocate data. */ if (sbinfo->max_blocks) { - if (percpu_counter_compare(&sbinfo->used_blocks, (sbinfo->max_blocks - 1)) > 0) + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks - 1) >= 0) return ERR_PTR(-ENOSPC); percpu_counter_inc(&sbinfo->used_blocks); spin_lock(&inode->i_lock); @@ -851,7 +852,7 @@ static inline int shmem_find_swp(swp_entry_t entry, swp_entry_t *dir, swp_entry_ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, struct page *page) { - struct inode *inode; + struct address_space *mapping; unsigned long idx; unsigned long size; unsigned long limit; @@ -874,8 +875,10 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s if (size > SHMEM_NR_DIRECT) size = SHMEM_NR_DIRECT; offset = shmem_find_swp(entry, ptr, ptr+size); - if (offset >= 0) + if (offset >= 0) { + shmem_swp_balance_unmap(); goto found; + } if (!info->i_indirect) goto lost2; @@ -913,11 +916,11 @@ static int shmem_unuse_inode(struct shmem_inode_info *info, swp_entry_t entry, s if (size > ENTRIES_PER_PAGE) size = ENTRIES_PER_PAGE; offset = shmem_find_swp(entry, ptr, ptr+size); - shmem_swp_unmap(ptr); if (offset >= 0) { shmem_dir_unmap(dir); goto found; } + shmem_swp_unmap(ptr); } } lost1: @@ -927,8 +930,7 @@ lost2: return 0; found: idx += offset; - inode = igrab(&info->vfs_inode); - spin_unlock(&info->lock); + ptr += offset; /* * Move _head_ to start search for next from here. @@ -939,37 +941,18 @@ found: */ if (shmem_swaplist.next != &info->swaplist) list_move_tail(&shmem_swaplist, &info->swaplist); - mutex_unlock(&shmem_swaplist_mutex); - error = 1; - if (!inode) - goto out; /* - * Charge page using GFP_KERNEL while we can wait. - * Charged back to the user(not to caller) when swap account is used. - * add_to_page_cache() will be called with GFP_NOWAIT. + * We rely on shmem_swaplist_mutex, not only to protect the swaplist, + * but also to hold up shmem_evict_inode(): so inode cannot be freed + * beneath us (pagelock doesn't help until the page is in pagecache). */ - error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); - if (error) - goto out; - error = radix_tree_preload(GFP_KERNEL); - if (error) { - mem_cgroup_uncharge_cache_page(page); - goto out; - } - error = 1; - - spin_lock(&info->lock); - ptr = shmem_swp_entry(info, idx, NULL); - if (ptr && ptr->val == entry.val) { - error = add_to_page_cache_locked(page, inode->i_mapping, - idx, GFP_NOWAIT); - /* does mem_cgroup_uncharge_cache_page on error */ - } else /* we must compensate for our precharge above */ - mem_cgroup_uncharge_cache_page(page); + mapping = info->vfs_inode.i_mapping; + error = add_to_page_cache_locked(page, mapping, idx, GFP_NOWAIT); + /* which does mem_cgroup_uncharge_cache_page on error */ if (error == -EEXIST) { - struct page *filepage = find_get_page(inode->i_mapping, idx); + struct page *filepage = find_get_page(mapping, idx); error = 1; if (filepage) { /* @@ -989,14 +972,8 @@ found: swap_free(entry); error = 1; /* not an error, but entry was found */ } - if (ptr) - shmem_swp_unmap(ptr); + shmem_swp_unmap(ptr); spin_unlock(&info->lock); - radix_tree_preload_end(); -out: - unlock_page(page); - page_cache_release(page); - iput(inode); /* allows for NULL */ return error; } @@ -1008,6 +985,26 @@ int shmem_unuse(swp_entry_t entry, struct page *page) struct list_head *p, *next; struct shmem_inode_info *info; int found = 0; + int error; + + /* + * Charge page using GFP_KERNEL while we can wait, before taking + * the shmem_swaplist_mutex which might hold up shmem_writepage(). + * Charged back to the user (not to caller) when swap account is used. + * add_to_page_cache() will be called with GFP_NOWAIT. + */ + error = mem_cgroup_cache_charge(page, current->mm, GFP_KERNEL); + if (error) + goto out; + /* + * Try to preload while we can wait, to not make a habit of + * draining atomic reserves; but don't latch on to this cpu, + * it's okay if sometimes we get rescheduled after this. + */ + error = radix_tree_preload(GFP_KERNEL); + if (error) + goto uncharge; + radix_tree_preload_end(); mutex_lock(&shmem_swaplist_mutex); list_for_each_safe(p, next, &shmem_swaplist) { @@ -1015,17 +1012,19 @@ int shmem_unuse(swp_entry_t entry, struct page *page) found = shmem_unuse_inode(info, entry, page); cond_resched(); if (found) - goto out; + break; } mutex_unlock(&shmem_swaplist_mutex); - /* - * Can some race bring us here? We've been holding page lock, - * so I think not; but would rather try again later than BUG() - */ + +uncharge: + if (!found) + mem_cgroup_uncharge_cache_page(page); + if (found < 0) + error = found; +out: unlock_page(page); page_cache_release(page); -out: - return (found < 0) ? found : 0; + return error; } /* @@ -1063,7 +1062,25 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) else swap.val = 0; + /* + * Add inode to shmem_unuse()'s list of swapped-out inodes, + * if it's not already there. Do it now because we cannot take + * mutex while holding spinlock, and must do so before the page + * is moved to swap cache, when its pagelock no longer protects + * the inode from eviction. But don't unlock the mutex until + * we've taken the spinlock, because shmem_unuse_inode() will + * prune a !swapped inode from the swaplist under both locks. + */ + if (swap.val) { + mutex_lock(&shmem_swaplist_mutex); + if (list_empty(&info->swaplist)) + list_add_tail(&info->swaplist, &shmem_swaplist); + } + spin_lock(&info->lock); + if (swap.val) + mutex_unlock(&shmem_swaplist_mutex); + if (index >= info->next_index) { BUG_ON(!(info->flags & SHMEM_TRUNCATE)); goto unlock; @@ -1083,21 +1100,10 @@ static int shmem_writepage(struct page *page, struct writeback_control *wbc) delete_from_page_cache(page); shmem_swp_set(info, entry, swap.val); shmem_swp_unmap(entry); - if (list_empty(&info->swaplist)) - inode = igrab(inode); - else - inode = NULL; spin_unlock(&info->lock); swap_shmem_alloc(swap); BUG_ON(page_mapped(page)); swap_writepage(page, wbc); - if (inode) { - mutex_lock(&shmem_swaplist_mutex); - /* move instead of add in case we're racing */ - list_move_tail(&info->swaplist, &shmem_swaplist); - mutex_unlock(&shmem_swaplist_mutex); - iput(inode); - } return 0; } @@ -1397,21 +1403,16 @@ repeat: shmem_swp_unmap(entry); sbinfo = SHMEM_SB(inode->i_sb); if (sbinfo->max_blocks) { - if ((percpu_counter_compare(&sbinfo->used_blocks, sbinfo->max_blocks) > 0) || - shmem_acct_block(info->flags)) { - spin_unlock(&info->lock); - error = -ENOSPC; - goto failed; - } + if (percpu_counter_compare(&sbinfo->used_blocks, + sbinfo->max_blocks) >= 0 || + shmem_acct_block(info->flags)) + goto nospace; percpu_counter_inc(&sbinfo->used_blocks); spin_lock(&inode->i_lock); inode->i_blocks += BLOCKS_PER_PAGE; spin_unlock(&inode->i_lock); - } else if (shmem_acct_block(info->flags)) { - spin_unlock(&info->lock); - error = -ENOSPC; - goto failed; - } + } else if (shmem_acct_block(info->flags)) + goto nospace; if (!filepage) { int ret; @@ -1491,6 +1492,24 @@ done: error = 0; goto out; +nospace: + /* + * Perhaps the page was brought in from swap between find_lock_page + * and taking info->lock? We allow for that at add_to_page_cache_lru, + * but must also avoid reporting a spurious ENOSPC while working on a + * full tmpfs. (When filepage has been passed in to shmem_getpage, it + * is already in page cache, which prevents this race from occurring.) + */ + if (!filepage) { + struct page *page = find_get_page(mapping, idx); + if (page) { + spin_unlock(&info->lock); + page_cache_release(page); + goto repeat; + } + } + spin_unlock(&info->lock); + error = -ENOSPC; failed: if (*pagep != filepage) { unlock_page(filepage); @@ -115,6 +115,7 @@ #include <linux/debugobjects.h> #include <linux/kmemcheck.h> #include <linux/memory.h> +#include <linux/prefetch.h> #include <asm/cacheflush.h> #include <asm/tlbflush.h> @@ -1940,7 +1940,7 @@ redo: * Since this is without lock semantics the protection is only against * code executing on this cpu *not* from access by other cpus. */ - if (unlikely(!this_cpu_cmpxchg_double( + if (unlikely(!irqsafe_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, object, tid, get_freepointer(s, object), next_tid(tid)))) { @@ -2145,7 +2145,7 @@ redo: set_freepointer(s, object, c->freelist); #ifdef CONFIG_CMPXCHG_LOCAL - if (unlikely(!this_cpu_cmpxchg_double( + if (unlikely(!irqsafe_cpu_cmpxchg_double( s->cpu_slab->freelist, s->cpu_slab->tid, c->freelist, tid, object, next_tid(tid)))) { @@ -396,6 +396,9 @@ static void lru_deactivate_fn(struct page *page, void *arg) if (!PageLRU(page)) return; + if (PageUnevictable(page)) + return; + /* Some processes are using the page */ if (page_mapped(page)) return; diff --git a/mm/vmscan.c b/mm/vmscan.c index c7f5a6d..c917720 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -41,6 +41,8 @@ #include <linux/memcontrol.h> #include <linux/delayacct.h> #include <linux/sysctl.h> +#include <linux/oom.h> +#include <linux/prefetch.h> #include <asm/tlbflush.h> #include <asm/div64.h> @@ -936,7 +938,7 @@ keep_lumpy: * back off and wait for congestion to clear because further reclaim * will encounter the same problem */ - if (nr_dirty == nr_congested && nr_dirty != 0) + if (nr_dirty && nr_dirty == nr_congested && scanning_global_lru(sc)) zone_set_flag(zone, ZONE_CONGESTED); free_page_list(&free_pages); @@ -1988,17 +1990,12 @@ static bool zone_reclaimable(struct zone *zone) return zone->pages_scanned < zone_reclaimable_pages(zone) * 6; } -/* - * As hibernation is going on, kswapd is freezed so that it can't mark - * the zone into all_unreclaimable. It can't handle OOM during hibernation. - * So let's check zone's unreclaimable in direct reclaim as well as kswapd. - */ +/* All zones in zonelist are unreclaimable? */ static bool all_unreclaimable(struct zonelist *zonelist, struct scan_control *sc) { struct zoneref *z; struct zone *zone; - bool all_unreclaimable = true; for_each_zone_zonelist_nodemask(zone, z, zonelist, gfp_zone(sc->gfp_mask), sc->nodemask) { @@ -2006,13 +2003,11 @@ static bool all_unreclaimable(struct zonelist *zonelist, continue; if (!cpuset_zone_allowed_hardwall(zone, GFP_KERNEL)) continue; - if (zone_reclaimable(zone)) { - all_unreclaimable = false; - break; - } + if (!zone->all_unreclaimable) + return false; } - return all_unreclaimable; + return true; } /* @@ -2108,6 +2103,14 @@ out: if (sc->nr_reclaimed) return sc->nr_reclaimed; + /* + * As hibernation is going on, kswapd is freezed so that it can't mark + * the zone into all_unreclaimable. Thus bypassing all_unreclaimable + * check. + */ + if (oom_killer_disabled) + return 0; + /* top priority shrink_zones still had more to do? don't OOM, then */ if (scanning_global_lru(sc) && !all_unreclaimable(zonelist, sc)) return 1; diff --git a/mm/vmstat.c b/mm/vmstat.c index 772b39b..897ea9e 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -321,9 +321,12 @@ static inline void mod_state(struct zone *zone, /* * The fetching of the stat_threshold is racy. We may apply * a counter threshold to the wrong the cpu if we get - * rescheduled while executing here. However, the following - * will apply the threshold again and therefore bring the - * counter under the threshold. + * rescheduled while executing here. However, the next + * counter update will apply the threshold again and + * therefore bring the counter under the threshold again. + * + * Most of the time the thresholds are the same anyways + * for all cpus in a zone. */ t = this_cpu_read(pcp->stat_threshold); @@ -945,7 +948,16 @@ static const char * const vmstat_text[] = { "unevictable_pgs_cleared", "unevictable_pgs_stranded", "unevictable_pgs_mlockfreed", + +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + "thp_fault_alloc", + "thp_fault_fallback", + "thp_collapse_alloc", + "thp_collapse_alloc_failed", + "thp_split", #endif + +#endif /* CONFIG_VM_EVENTS_COUNTERS */ }; static void zoneinfo_show_print(struct seq_file *m, pg_data_t *pgdat, |