diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/cleancache.c | 3 | ||||
| -rw-r--r-- | mm/filemap.c | 146 | ||||
| -rw-r--r-- | mm/frontswap.c | 3 | ||||
| -rw-r--r-- | mm/hmm.c | 14 | ||||
| -rw-r--r-- | mm/huge_memory.c | 7 | ||||
| -rw-r--r-- | mm/hugetlb.c | 29 | ||||
| -rw-r--r-- | mm/interval_tree.c | 3 | ||||
| -rw-r--r-- | mm/khugepaged.c | 7 | ||||
| -rw-r--r-- | mm/ksm.c | 3 | ||||
| -rw-r--r-- | mm/list_lru.c | 2 | ||||
| -rw-r--r-- | mm/memcontrol.c | 41 | ||||
| -rw-r--r-- | mm/memfd.c | 2 | ||||
| -rw-r--r-- | mm/memory-failure.c | 7 | ||||
| -rw-r--r-- | mm/mempolicy.c | 2 | ||||
| -rw-r--r-- | mm/migrate.c | 2 | ||||
| -rw-r--r-- | mm/mlock.c | 7 | ||||
| -rw-r--r-- | mm/mmu_gather.c | 24 | ||||
| -rw-r--r-- | mm/mmu_notifier.c | 4 | ||||
| -rw-r--r-- | mm/oom_kill.c | 12 | ||||
| -rw-r--r-- | mm/page_alloc.c | 3 | ||||
| -rw-r--r-- | mm/page_idle.c | 4 | ||||
| -rw-r--r-- | mm/page_io.c | 20 | ||||
| -rw-r--r-- | mm/shmem.c | 2 | ||||
| -rw-r--r-- | mm/swap_state.c | 4 | ||||
| -rw-r--r-- | mm/usercopy.c | 6 | ||||
| -rw-r--r-- | mm/userfaultfd.c | 4 | ||||
| -rw-r--r-- | mm/vmalloc.c | 18 | ||||
| -rw-r--r-- | mm/vmpressure.c | 5 | ||||
| -rw-r--r-- | mm/vmscan.c | 33 |
29 files changed, 232 insertions, 185 deletions
diff --git a/mm/cleancache.c b/mm/cleancache.c index 2bf12da9baa0..2397f7c36cc7 100644 --- a/mm/cleancache.c +++ b/mm/cleancache.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Cleancache frontend * @@ -7,8 +8,6 @@ * * Copyright (C) 2009-2010 Oracle Corp. All rights reserved. * Author: Dan Magenheimer - * - * This work is licensed under the terms of the GNU GPL, version 2. */ #include <linux/module.h> diff --git a/mm/filemap.c b/mm/filemap.c index df2006ba0cfa..6dd9a2274c80 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -281,11 +281,11 @@ EXPORT_SYMBOL(delete_from_page_cache); * @pvec: pagevec with pages to delete * * The function walks over mapping->i_pages and removes pages passed in @pvec - * from the mapping. The function expects @pvec to be sorted by page index - * and is optimised for it to be dense. + * from the mapping. The function expects @pvec to be sorted by page index. * It tolerates holes in @pvec (mapping entries at those indices are not * modified). The function expects only THP head pages to be present in the - * @pvec. + * @pvec and takes care to delete all corresponding tail pages from the + * mapping as well. * * The function expects the i_pages lock to be held. */ @@ -294,44 +294,40 @@ static void page_cache_delete_batch(struct address_space *mapping, { XA_STATE(xas, &mapping->i_pages, pvec->pages[0]->index); int total_pages = 0; - int i = 0; + int i = 0, tail_pages = 0; struct page *page; mapping_set_update(&xas, mapping); xas_for_each(&xas, page, ULONG_MAX) { - if (i >= pagevec_count(pvec)) + if (i >= pagevec_count(pvec) && !tail_pages) break; - - /* A swap/dax/shadow entry got inserted? Skip it. */ if (xa_is_value(page)) continue; - /* - * A page got inserted in our range? Skip it. We have our - * pages locked so they are protected from being removed. - * If we see a page whose index is higher than ours, it - * means our page has been removed, which shouldn't be - * possible because we're holding the PageLock. - */ - if (page != pvec->pages[i]) { - VM_BUG_ON_PAGE(page->index > pvec->pages[i]->index, - page); - continue; - } - - WARN_ON_ONCE(!PageLocked(page)); - - if (page->index == xas.xa_index) + if (!tail_pages) { + /* + * Some page got inserted in our range? Skip it. We + * have our pages locked so they are protected from + * being removed. + */ + if (page != pvec->pages[i]) { + VM_BUG_ON_PAGE(page->index > + pvec->pages[i]->index, page); + continue; + } + WARN_ON_ONCE(!PageLocked(page)); + if (PageTransHuge(page) && !PageHuge(page)) + tail_pages = HPAGE_PMD_NR - 1; page->mapping = NULL; - /* Leave page->index set: truncation lookup relies on it */ - - /* - * Move to the next page in the vector if this is a regular - * page or the index is of the last sub-page of this compound - * page. - */ - if (page->index + (1UL << compound_order(page)) - 1 == - xas.xa_index) + /* + * Leave page->index set: truncation lookup relies + * upon it + */ i++; + } else { + VM_BUG_ON_PAGE(page->index + HPAGE_PMD_NR - tail_pages + != pvec->pages[i]->index, page); + tail_pages--; + } xas_store(&xas, NULL); total_pages++; } @@ -1498,7 +1494,7 @@ EXPORT_SYMBOL(page_cache_prev_miss); struct page *find_get_entry(struct address_space *mapping, pgoff_t offset) { XA_STATE(xas, &mapping->i_pages, offset); - struct page *page; + struct page *head, *page; rcu_read_lock(); repeat: @@ -1513,19 +1509,25 @@ repeat: if (!page || xa_is_value(page)) goto out; - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) + goto repeat; + + /* The page was split under us? */ + if (compound_head(page) != head) { + put_page(head); goto repeat; + } /* - * Has the page moved or been split? + * Has the page moved? * This is part of the lockless pagecache protocol. See * include/linux/pagemap.h for details. */ if (unlikely(page != xas_reload(&xas))) { - put_page(page); + put_page(head); goto repeat; } - page = find_subpage(page, offset); out: rcu_read_unlock(); @@ -1707,6 +1709,7 @@ unsigned find_get_entries(struct address_space *mapping, rcu_read_lock(); xas_for_each(&xas, page, ULONG_MAX) { + struct page *head; if (xas_retry(&xas, page)) continue; /* @@ -1717,13 +1720,17 @@ unsigned find_get_entries(struct address_space *mapping, if (xa_is_value(page)) goto export; - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto retry; - /* Has the page moved or been split? */ + /* The page was split under us? */ + if (compound_head(page) != head) + goto put_page; + + /* Has the page moved? */ if (unlikely(page != xas_reload(&xas))) goto put_page; - page = find_subpage(page, xas.xa_index); export: indices[ret] = xas.xa_index; @@ -1732,7 +1739,7 @@ export: break; continue; put_page: - put_page(page); + put_page(head); retry: xas_reset(&xas); } @@ -1774,27 +1781,33 @@ unsigned find_get_pages_range(struct address_space *mapping, pgoff_t *start, rcu_read_lock(); xas_for_each(&xas, page, end) { + struct page *head; if (xas_retry(&xas, page)) continue; /* Skip over shadow, swap and DAX entries */ if (xa_is_value(page)) continue; - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto retry; - /* Has the page moved or been split? */ + /* The page was split under us? */ + if (compound_head(page) != head) + goto put_page; + + /* Has the page moved? */ if (unlikely(page != xas_reload(&xas))) goto put_page; - pages[ret] = find_subpage(page, xas.xa_index); + pages[ret] = page; if (++ret == nr_pages) { *start = xas.xa_index + 1; goto out; } continue; put_page: - put_page(page); + put_page(head); retry: xas_reset(&xas); } @@ -1839,6 +1852,7 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, rcu_read_lock(); for (page = xas_load(&xas); page; page = xas_next(&xas)) { + struct page *head; if (xas_retry(&xas, page)) continue; /* @@ -1848,19 +1862,24 @@ unsigned find_get_pages_contig(struct address_space *mapping, pgoff_t index, if (xa_is_value(page)) break; - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto retry; - /* Has the page moved or been split? */ + /* The page was split under us? */ + if (compound_head(page) != head) + goto put_page; + + /* Has the page moved? */ if (unlikely(page != xas_reload(&xas))) goto put_page; - pages[ret] = find_subpage(page, xas.xa_index); + pages[ret] = page; if (++ret == nr_pages) break; continue; put_page: - put_page(page); + put_page(head); retry: xas_reset(&xas); } @@ -1896,6 +1915,7 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, rcu_read_lock(); xas_for_each_marked(&xas, page, end, tag) { + struct page *head; if (xas_retry(&xas, page)) continue; /* @@ -1906,21 +1926,26 @@ unsigned find_get_pages_range_tag(struct address_space *mapping, pgoff_t *index, if (xa_is_value(page)) continue; - if (!page_cache_get_speculative(page)) + head = compound_head(page); + if (!page_cache_get_speculative(head)) goto retry; - /* Has the page moved or been split? */ + /* The page was split under us? */ + if (compound_head(page) != head) + goto put_page; + + /* Has the page moved? */ if (unlikely(page != xas_reload(&xas))) goto put_page; - pages[ret] = find_subpage(page, xas.xa_index); + pages[ret] = page; if (++ret == nr_pages) { *index = xas.xa_index + 1; goto out; } continue; put_page: - put_page(page); + put_page(head); retry: xas_reset(&xas); } @@ -2603,7 +2628,7 @@ void filemap_map_pages(struct vm_fault *vmf, pgoff_t last_pgoff = start_pgoff; unsigned long max_idx; XA_STATE(xas, &mapping->i_pages, start_pgoff); - struct page *page; + struct page *head, *page; rcu_read_lock(); xas_for_each(&xas, page, end_pgoff) { @@ -2612,19 +2637,24 @@ void filemap_map_pages(struct vm_fault *vmf, if (xa_is_value(page)) goto next; + head = compound_head(page); + /* * Check for a locked page first, as a speculative * reference may adversely influence page migration. */ - if (PageLocked(page)) + if (PageLocked(head)) goto next; - if (!page_cache_get_speculative(page)) + if (!page_cache_get_speculative(head)) goto next; - /* Has the page moved or been split? */ + /* The page was split under us? */ + if (compound_head(page) != head) + goto skip; + + /* Has the page moved? */ if (unlikely(page != xas_reload(&xas))) goto skip; - page = find_subpage(page, xas.xa_index); if (!PageUptodate(page) || PageReadahead(page) || diff --git a/mm/frontswap.c b/mm/frontswap.c index 157e5bf63504..60bb20e8a951 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Frontswap frontend * @@ -7,8 +8,6 @@ * * Copyright (C) 2009-2012 Oracle Corp. All rights reserved. * Author: Dan Magenheimer - * - * This work is licensed under the terms of the GNU GPL, version 2. */ #include <linux/mman.h> @@ -1354,9 +1354,8 @@ static void hmm_devmem_ref_release(struct percpu_ref *ref) complete(&devmem->completion); } -static void hmm_devmem_ref_exit(void *data) +static void hmm_devmem_ref_exit(struct percpu_ref *ref) { - struct percpu_ref *ref = data; struct hmm_devmem *devmem; devmem = container_of(ref, struct hmm_devmem, ref); @@ -1433,10 +1432,6 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, if (ret) return ERR_PTR(ret); - ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit, &devmem->ref); - if (ret) - return ERR_PTR(ret); - size = ALIGN(size, PA_SECTION_SIZE); addr = min((unsigned long)iomem_resource.end, (1UL << MAX_PHYSMEM_BITS) - 1); @@ -1475,6 +1470,7 @@ struct hmm_devmem *hmm_devmem_add(const struct hmm_devmem_ops *ops, devmem->pagemap.ref = &devmem->ref; devmem->pagemap.data = devmem; devmem->pagemap.kill = hmm_devmem_ref_kill; + devmem->pagemap.cleanup = hmm_devmem_ref_exit; result = devm_memremap_pages(devmem->device, &devmem->pagemap); if (IS_ERR(result)) @@ -1512,11 +1508,6 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, if (ret) return ERR_PTR(ret); - ret = devm_add_action_or_reset(device, hmm_devmem_ref_exit, - &devmem->ref); - if (ret) - return ERR_PTR(ret); - devmem->pfn_first = devmem->resource->start >> PAGE_SHIFT; devmem->pfn_last = devmem->pfn_first + (resource_size(devmem->resource) >> PAGE_SHIFT); @@ -1529,6 +1520,7 @@ struct hmm_devmem *hmm_devmem_add_resource(const struct hmm_devmem_ops *ops, devmem->pagemap.ref = &devmem->ref; devmem->pagemap.data = devmem; devmem->pagemap.kill = hmm_devmem_ref_kill; + devmem->pagemap.cleanup = hmm_devmem_ref_exit; result = devm_memremap_pages(devmem->device, &devmem->pagemap); if (IS_ERR(result)) diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 9f8bce9a6b32..885642c82aaa 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -1,8 +1,6 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Copyright (C) 2009 Red Hat, Inc. - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -2498,9 +2496,6 @@ static void __split_huge_page(struct page *page, struct list_head *list, if (IS_ENABLED(CONFIG_SHMEM) && PageSwapBacked(head)) shmem_uncharge(head->mapping->host, 1); put_page(head + i); - } else if (!PageAnon(page)) { - __xa_store(&head->mapping->i_pages, head[i].index, - head + i, 0); } } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index ac843d32b019..ede7e7f5d1ab 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -1510,16 +1510,29 @@ static int free_pool_huge_page(struct hstate *h, nodemask_t *nodes_allowed, /* * Dissolve a given free hugepage into free buddy pages. This function does - * nothing for in-use (including surplus) hugepages. Returns -EBUSY if the - * dissolution fails because a give page is not a free hugepage, or because - * free hugepages are fully reserved. + * nothing for in-use hugepages and non-hugepages. + * This function returns values like below: + * + * -EBUSY: failed to dissolved free hugepages or the hugepage is in-use + * (allocated or reserved.) + * 0: successfully dissolved free hugepages or the page is not a + * hugepage (considered as already dissolved) */ int dissolve_free_huge_page(struct page *page) { int rc = -EBUSY; + /* Not to disrupt normal path by vainly holding hugetlb_lock */ + if (!PageHuge(page)) + return 0; + spin_lock(&hugetlb_lock); - if (PageHuge(page) && !page_count(page)) { + if (!PageHuge(page)) { + rc = 0; + goto out; + } + + if (!page_count(page)) { struct page *head = compound_head(page); struct hstate *h = page_hstate(head); int nid = page_to_nid(head); @@ -1564,11 +1577,9 @@ int dissolve_free_huge_pages(unsigned long start_pfn, unsigned long end_pfn) for (pfn = start_pfn; pfn < end_pfn; pfn += 1 << minimum_order) { page = pfn_to_page(pfn); - if (PageHuge(page) && !page_count(page)) { - rc = dissolve_free_huge_page(page); - if (rc) - break; - } + rc = dissolve_free_huge_page(page); + if (rc) + break; } return rc; diff --git a/mm/interval_tree.c b/mm/interval_tree.c index 27ddfd29112a..11c75fb07584 100644 --- a/mm/interval_tree.c +++ b/mm/interval_tree.c @@ -1,9 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * mm/interval_tree.c - interval tree for mapping->i_mmap * * Copyright (C) 2012, Michel Lespinasse <walken@google.com> - * - * This file is released under the GPL v2. */ #include <linux/mm.h> diff --git a/mm/khugepaged.c b/mm/khugepaged.c index a335f7c1fac4..eaaa21b23215 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -1004,6 +1004,9 @@ static void collapse_huge_page(struct mm_struct *mm, * handled by the anon_vma lock + PG_lock. */ down_write(&mm->mmap_sem); + result = SCAN_ANY_PROCESS; + if (!mmget_still_valid(mm)) + goto out; result = hugepage_vma_revalidate(mm, address, &vma); if (result) goto out; @@ -1375,7 +1378,7 @@ static void collapse_shmem(struct mm_struct *mm, result = SCAN_FAIL; goto xa_locked; } - xas_store(&xas, new_page); + xas_store(&xas, new_page + (index % HPAGE_PMD_NR)); nr_none++; continue; } @@ -1451,7 +1454,7 @@ static void collapse_shmem(struct mm_struct *mm, list_add_tail(&page->lru, &pagelist); /* Finally, replace with the new page. */ - xas_store(&xas, new_page); + xas_store(&xas, new_page + (index % HPAGE_PMD_NR)); continue; out_unlock: unlock_page(page); @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Memory merging support. * @@ -10,8 +11,6 @@ * Andrea Arcangeli * Chris Wright * Hugh Dickins - * - * This work is licensed under the terms of the GNU GPL, version 2. */ #include <linux/errno.h> diff --git a/mm/list_lru.c b/mm/list_lru.c index e4709fdaa8e6..927d85be32f6 100644 --- a/mm/list_lru.c +++ b/mm/list_lru.c @@ -354,7 +354,7 @@ static int __memcg_init_list_lru_node(struct list_lru_memcg *memcg_lrus, } return 0; fail: - __memcg_destroy_list_lru_node(memcg_lrus, begin, i - 1); + __memcg_destroy_list_lru_node(memcg_lrus, begin, i); return -ENOMEM; } diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ca0bc6e6be13..ba9138a4a1de 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -691,11 +691,12 @@ void __mod_memcg_state(struct mem_cgroup *memcg, int idx, int val) if (mem_cgroup_disabled()) return; + __this_cpu_add(memcg->vmstats_local->stat[idx], val); + x = val + __this_cpu_read(memcg->vmstats_percpu->stat[idx]); if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) { struct mem_cgroup *mi; - atomic_long_add(x, &memcg->vmstats_local[idx]); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &mi->vmstats[idx]); x = 0; @@ -745,11 +746,12 @@ void __mod_lruvec_state(struct lruvec *lruvec, enum node_stat_item idx, __mod_memcg_state(memcg, idx, val); /* Update lruvec */ + __this_cpu_add(pn->lruvec_stat_local->count[idx], val); + x = val + __this_cpu_read(pn->lruvec_stat_cpu->count[idx]); if (unlikely(abs(x) > MEMCG_CHARGE_BATCH)) { struct mem_cgroup_per_node *pi; - atomic_long_add(x, &pn->lruvec_stat_local[idx]); for (pi = pn; pi; pi = parent_nodeinfo(pi, pgdat->node_id)) atomic_long_add(x, &pi->lruvec_stat[idx]); x = 0; @@ -771,11 +773,12 @@ void __count_memcg_events(struct mem_cgroup *memcg, enum vm_event_item idx, if (mem_cgroup_disabled()) return; + __this_cpu_add(memcg->vmstats_local->events[idx], count); + x = count + __this_cpu_read(memcg->vmstats_percpu->events[idx]); if (unlikely(x > MEMCG_CHARGE_BATCH)) { struct mem_cgroup *mi; - atomic_long_add(x, &memcg->vmevents_local[idx]); for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &mi->vmevents[idx]); x = 0; @@ -790,7 +793,12 @@ static unsigned long memcg_events(struct mem_cgroup *memcg, int event) static unsigned long memcg_events_local(struct mem_cgroup *memcg, int event) { - return atomic_long_read(&memcg->vmevents_local[event]); + long x = 0; + int cpu; + + for_each_possible_cpu(cpu) + x += per_cpu(memcg->vmstats_local->events[event], cpu); + return x; } static void mem_cgroup_charge_statistics(struct mem_cgroup *memcg, @@ -2191,11 +2199,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu) long x; x = this_cpu_xchg(memcg->vmstats_percpu->stat[i], 0); - if (x) { - atomic_long_add(x, &memcg->vmstats_local[i]); + if (x) for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &memcg->vmstats[i]); - } if (i >= NR_VM_NODE_STAT_ITEMS) continue; @@ -2205,12 +2211,10 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu) pn = mem_cgroup_nodeinfo(memcg, nid); x = this_cpu_xchg(pn->lruvec_stat_cpu->count[i], 0); - if (x) { - atomic_long_add(x, &pn->lruvec_stat_local[i]); + if (x) do { atomic_long_add(x, &pn->lruvec_stat[i]); } while ((pn = parent_nodeinfo(pn, nid))); - } } } @@ -2218,11 +2222,9 @@ static int memcg_hotplug_cpu_dead(unsigned int cpu) long x; x = this_cpu_xchg(memcg->vmstats_percpu->events[i], 0); - if (x) { - atomic_long_add(x, &memcg->vmevents_local[i]); + if (x) for (mi = memcg; mi; mi = parent_mem_cgroup(mi)) atomic_long_add(x, &memcg->vmevents[i]); - } } } @@ -4483,8 +4485,15 @@ static int alloc_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) if (!pn) return 1; + pn->lruvec_stat_local = alloc_percpu(struct lruvec_stat); + if (!pn->lruvec_stat_local) { + kfree(pn); + return 1; + } + pn->lruvec_stat_cpu = alloc_percpu(struct lruvec_stat); if (!pn->lruvec_stat_cpu) { + free_percpu(pn->lruvec_stat_local); kfree(pn); return 1; } @@ -4506,6 +4515,7 @@ static void free_mem_cgroup_per_node_info(struct mem_cgroup *memcg, int node) return; free_percpu(pn->lruvec_stat_cpu); + free_percpu(pn->lruvec_stat_local); kfree(pn); } @@ -4516,6 +4526,7 @@ static void __mem_cgroup_free(struct mem_cgroup *memcg) for_each_node(node) free_mem_cgroup_per_node_info(memcg, node); free_percpu(memcg->vmstats_percpu); + free_percpu(memcg->vmstats_local); kfree(memcg); } @@ -4544,6 +4555,10 @@ static struct mem_cgroup *mem_cgroup_alloc(void) if (memcg->id.id < 0) goto fail; + memcg->vmstats_local = alloc_percpu(struct memcg_vmstats_percpu); + if (!memcg->vmstats_local) + goto fail; + memcg->vmstats_percpu = alloc_percpu(struct memcg_vmstats_percpu); if (!memcg->vmstats_percpu) goto fail; diff --git a/mm/memfd.c b/mm/memfd.c index 2647c898990c..650e65a46b9c 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -39,7 +39,6 @@ static void memfd_tag_pins(struct xa_state *xas) xas_for_each(xas, page, ULONG_MAX) { if (xa_is_value(page)) continue; - page = find_subpage(page, xas->xa_index); if (page_count(page) - page_mapcount(page) > 1) xas_set_mark(xas, MEMFD_TAG_PINNED); @@ -89,7 +88,6 @@ static int memfd_wait_for_pins(struct address_space *mapping) bool clear = true; if (xa_is_value(page)) continue; - page = find_subpage(page, xas.xa_index); if (page_count(page) - page_mapcount(page) != 1) { /* * On the last scan, we clean up all those tags diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 8da0334b9ca0..d9cc6606f409 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -1730,6 +1730,8 @@ static int soft_offline_huge_page(struct page *page, int flags) if (!ret) { if (set_hwpoison_free_buddy_page(page)) num_poisoned_pages_inc(); + else + ret = -EBUSY; } } return ret; @@ -1854,11 +1856,8 @@ static int soft_offline_in_use_page(struct page *page, int flags) static int soft_offline_free_page(struct page *page) { - int rc = 0; - struct page *head = compound_head(page); + int rc = dissolve_free_huge_page(page); - if (PageHuge(head)) - rc = dissolve_free_huge_page(page); if (!rc) { if (set_hwpoison_free_buddy_page(page)) num_poisoned_pages_inc(); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 01600d80ae01..fdcb73536319 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -306,7 +306,7 @@ static void mpol_rebind_nodemask(struct mempolicy *pol, const nodemask_t *nodes) else { nodes_remap(tmp, pol->v.nodes,pol->w.cpuset_mems_allowed, *nodes); - pol->w.cpuset_mems_allowed = tmp; + pol->w.cpuset_mems_allowed = *nodes; } if (nodes_empty(tmp)) diff --git a/mm/migrate.c b/mm/migrate.c index f2ecc2855a12..e9594bc0d406 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -463,7 +463,7 @@ int migrate_page_move_mapping(struct address_space *mapping, for (i = 1; i < HPAGE_PMD_NR; i++) { xas_next(&xas); - xas_store(&xas, newpage); + xas_store(&xas, newpage + i); } } diff --git a/mm/mlock.c b/mm/mlock.c index 080f3b36415b..a90099da4fb4 100644 --- a/mm/mlock.c +++ b/mm/mlock.c @@ -636,11 +636,11 @@ static int apply_vma_lock_flags(unsigned long start, size_t len, * is also counted. * Return value: previously mlocked page counts */ -static int count_mm_mlocked_page_nr(struct mm_struct *mm, +static unsigned long count_mm_mlocked_page_nr(struct mm_struct *mm, unsigned long start, size_t len) { struct vm_area_struct *vma; - int count = 0; + unsigned long count = 0; if (mm == NULL) mm = current->mm; @@ -797,7 +797,8 @@ SYSCALL_DEFINE1(mlockall, int, flags) unsigned long lock_limit; int ret; - if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT))) + if (!flags || (flags & ~(MCL_CURRENT | MCL_FUTURE | MCL_ONFAULT)) || + flags == MCL_ONFAULT) return -EINVAL; if (!can_do_mlock()) diff --git a/mm/mmu_gather.c b/mm/mmu_gather.c index 99740e1dd273..8c943a6e1696 100644 --- a/mm/mmu_gather.c +++ b/mm/mmu_gather.c @@ -245,14 +245,28 @@ void tlb_finish_mmu(struct mmu_gather *tlb, { /* * If there are parallel threads are doing PTE changes on same range - * under non-exclusive lock(e.g., mmap_sem read-side) but defer TLB - * flush by batching, a thread has stable TLB entry can fail to flush - * the TLB by observing pte_none|!pte_dirty, for example so flush TLB - * forcefully if we detect parallel PTE batching threads. + * under non-exclusive lock (e.g., mmap_sem read-side) but defer TLB + * flush by batching, one thread may end up seeing inconsistent PTEs + * and result in having stale TLB entries. So flush TLB forcefully + * if we detect parallel PTE batching threads. + * + * However, some syscalls, e.g. munmap(), may free page tables, this + * needs force flush everything in the given range. Otherwise this + * may result in having stale TLB entries for some architectures, + * e.g. aarch64, that could specify flush what level TLB. */ if (mm_tlb_flush_nested(tlb->mm)) { + /* + * The aarch64 yields better performance with fullmm by + * avoiding multiple CPUs spamming TLBI messages at the + * same time. + * + * On x86 non-fullmm doesn't yield significant difference + * against fullmm. + */ + tlb->fullmm = 1; __tlb_reset_range(tlb); - __tlb_adjust_range(tlb, start, end - start); + tlb->freed_tables = 1; } tlb_flush_mmu(tlb); diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index ee36068077b6..513b9607409d 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -1,12 +1,10 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * linux/mm/mmu_notifier.c * * Copyright (C) 2008 Qumranet, Inc. * Copyright (C) 2008 SGI * Christoph Lameter <cl@linux.com> - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/rculist.h> diff --git a/mm/oom_kill.c b/mm/oom_kill.c index 5a58778c91d4..f719b64741d6 100644 --- a/mm/oom_kill.c +++ b/mm/oom_kill.c @@ -987,8 +987,7 @@ static void oom_kill_process(struct oom_control *oc, const char *message) /* * Determines whether the kernel must panic because of the panic_on_oom sysctl. */ -static void check_panic_on_oom(struct oom_control *oc, - enum oom_constraint constraint) +static void check_panic_on_oom(struct oom_control *oc) { if (likely(!sysctl_panic_on_oom)) return; @@ -998,7 +997,7 @@ static void check_panic_on_oom(struct oom_control *oc, * does not panic for cpuset, mempolicy, or memcg allocation * failures. */ - if (constraint != CONSTRAINT_NONE) + if (oc->constraint != CONSTRAINT_NONE) return; } /* Do not panic for oom kills triggered by sysrq */ @@ -1035,7 +1034,6 @@ EXPORT_SYMBOL_GPL(unregister_oom_notifier); bool out_of_memory(struct oom_control *oc) { unsigned long freed = 0; - enum oom_constraint constraint = CONSTRAINT_NONE; if (oom_killer_disabled) return false; @@ -1071,10 +1069,10 @@ bool out_of_memory(struct oom_control *oc) * Check if there were limitations on the allocation (only relevant for * NUMA and memcg) that may require different handling. */ - constraint = constrained_alloc(oc); - if (constraint != CONSTRAINT_MEMORY_POLICY) + oc->constraint = constrained_alloc(oc); + if (oc->constraint != CONSTRAINT_MEMORY_POLICY) oc->nodemask = NULL; - check_panic_on_oom(oc, constraint); + check_panic_on_oom(oc); if (!is_memcg_oom(oc) && sysctl_oom_kill_allocating_task && current->mm && !oom_unkillable_task(current, NULL, oc->nodemask) && diff --git a/mm/page_alloc.c b/mm/page_alloc.c index d66bc8abe0af..8e3bc949ebcc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1826,7 +1826,8 @@ deferred_grow_zone(struct zone *zone, unsigned int order) first_deferred_pfn)) { pgdat->first_deferred_pfn = ULONG_MAX; pgdat_resize_unlock(pgdat, &flags); - return true; + /* Retry only once. */ + return first_deferred_pfn != ULONG_MAX; } /* diff --git a/mm/page_idle.c b/mm/page_idle.c index 0b39ec0c945c..295512465065 100644 --- a/mm/page_idle.c +++ b/mm/page_idle.c @@ -136,7 +136,7 @@ static ssize_t page_idle_bitmap_read(struct file *file, struct kobject *kobj, end_pfn = pfn + count * BITS_PER_BYTE; if (end_pfn > max_pfn) - end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS); + end_pfn = max_pfn; for (; pfn < end_pfn; pfn++) { bit = pfn % BITMAP_CHUNK_BITS; @@ -181,7 +181,7 @@ static ssize_t page_idle_bitmap_write(struct file *file, struct kobject *kobj, end_pfn = pfn + count * BITS_PER_BYTE; if (end_pfn > max_pfn) - end_pfn = ALIGN(max_pfn, BITMAP_CHUNK_BITS); + end_pfn = max_pfn; for (; pfn < end_pfn; pfn++) { bit = pfn % BITMAP_CHUNK_BITS; diff --git a/mm/page_io.c b/mm/page_io.c index 2e8019d0e048..a39aac2f8c8d 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -29,10 +29,9 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, struct page *page, bio_end_io_t end_io) { - int i, nr = hpage_nr_pages(page); struct bio *bio; - bio = bio_alloc(gfp_flags, nr); + bio = bio_alloc(gfp_flags, 1); if (bio) { struct block_device *bdev; @@ -41,9 +40,7 @@ static struct bio *get_swap_bio(gfp_t gfp_flags, bio->bi_iter.bi_sector <<= PAGE_SHIFT - 9; bio->bi_end_io = end_io; - for (i = 0; i < nr; i++) - bio_add_page(bio, page + i, PAGE_SIZE, 0); - VM_BUG_ON(bio->bi_iter.bi_size != PAGE_SIZE * nr); + bio_add_page(bio, page, PAGE_SIZE * hpage_nr_pages(page), 0); } return bio; } @@ -140,8 +137,10 @@ out: unlock_page(page); WRITE_ONCE(bio->bi_private, NULL); bio_put(bio); - blk_wake_io_task(waiter); - put_task_struct(waiter); + if (waiter) { + blk_wake_io_task(waiter); + put_task_struct(waiter); + } } int generic_swapfile_activate(struct swap_info_struct *sis, @@ -398,11 +397,12 @@ int swap_readpage(struct page *page, bool synchronous) * Keep this task valid during swap readpage because the oom killer may * attempt to access it in the page fault retry time check. */ - get_task_struct(current); - bio->bi_private = current; bio_set_op_attrs(bio, REQ_OP_READ, 0); - if (synchronous) + if (synchronous) { bio->bi_opf |= REQ_HIPRI; + get_task_struct(current); + bio->bi_private = current; + } count_vm_event(PSWPIN); bio_get(bio); qc = submit_bio(bio); diff --git a/mm/shmem.c b/mm/shmem.c index 1bb3b8dc8bb2..f4dce9c8670d 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -614,7 +614,7 @@ static int shmem_add_to_page_cache(struct page *page, if (xas_error(&xas)) goto unlock; next: - xas_store(&xas, page); + xas_store(&xas, page + i); if (++i < nr) { xas_next(&xas); goto next; diff --git a/mm/swap_state.c b/mm/swap_state.c index eb714165afd2..85245fdec8d9 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -132,7 +132,7 @@ int add_to_swap_cache(struct page *page, swp_entry_t entry, gfp_t gfp) for (i = 0; i < nr; i++) { VM_BUG_ON_PAGE(xas.xa_index != idx + i, page); set_page_private(page + i, entry.val + i); - xas_store(&xas, page); + xas_store(&xas, page + i); xas_next(&xas); } address_space->nrpages += nr; @@ -167,7 +167,7 @@ void __delete_from_swap_cache(struct page *page, swp_entry_t entry) for (i = 0; i < nr; i++) { void *entry = xas_store(&xas, NULL); - VM_BUG_ON_PAGE(entry != page, entry); + VM_BUG_ON_PAGE(entry != page + i, entry); set_page_private(page + i, 0); xas_next(&xas); } diff --git a/mm/usercopy.c b/mm/usercopy.c index 14faadcedd06..2a09796edef8 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * This implements the various checks for CONFIG_HARDENED_USERCOPY*, * which are designed to protect kernel memory from needless exposure @@ -6,11 +7,6 @@ * * Copyright (C) 2001-2016 PaX Team, Bradley Spengler, Open Source * Security Inc. - * - * 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. - * */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 9932d5755e4c..c7ae74ce5ff3 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -1,10 +1,8 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * mm/userfaultfd.c * * Copyright (C) 2015 Red Hat, Inc. - * - * This work is licensed under the terms of the GNU GPL, version 2. See - * the COPYING file in the top-level directory. */ #include <linux/mm.h> diff --git a/mm/vmalloc.c b/mm/vmalloc.c index 7350a124524b..0f76cca32a1c 100644 --- a/mm/vmalloc.c +++ b/mm/vmalloc.c @@ -913,7 +913,7 @@ adjust_va_to_fit_type(struct vmap_area *va, unsigned long nva_start_addr, unsigned long size, enum fit_type type) { - struct vmap_area *lva; + struct vmap_area *lva = NULL; if (type == FL_FIT_TYPE) { /* @@ -972,7 +972,7 @@ adjust_va_to_fit_type(struct vmap_area *va, if (type != FL_FIT_TYPE) { augment_tree_propagate_from(va); - if (type == NE_FIT_TYPE) + if (lva) /* type == NE_FIT_TYPE */ insert_vmap_area_augment(lva, &va->rb_node, &free_vmap_area_root, &free_vmap_area_list); } @@ -2123,9 +2123,9 @@ static inline void set_area_direct_map(const struct vm_struct *area, /* Handle removing and resetting vm mappings related to the vm_struct. */ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) { - unsigned long addr = (unsigned long)area->addr; unsigned long start = ULONG_MAX, end = 0; int flush_reset = area->flags & VM_FLUSH_RESET_PERMS; + int flush_dmap = 0; int i; /* @@ -2135,8 +2135,8 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) * execute permissions, without leaving a RW+X window. */ if (flush_reset && !IS_ENABLED(CONFIG_ARCH_HAS_SET_DIRECT_MAP)) { - set_memory_nx(addr, area->nr_pages); - set_memory_rw(addr, area->nr_pages); + set_memory_nx((unsigned long)area->addr, area->nr_pages); + set_memory_rw((unsigned long)area->addr, area->nr_pages); } remove_vm_area(area->addr); @@ -2160,9 +2160,11 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) * the vm_unmap_aliases() flush includes the direct map. */ for (i = 0; i < area->nr_pages; i++) { - if (page_address(area->pages[i])) { + unsigned long addr = (unsigned long)page_address(area->pages[i]); + if (addr) { start = min(addr, start); - end = max(addr, end); + end = max(addr + PAGE_SIZE, end); + flush_dmap = 1; } } @@ -2172,7 +2174,7 @@ static void vm_remove_mappings(struct vm_struct *area, int deallocate_pages) * reset the direct map permissions to the default. */ set_area_direct_map(area, set_direct_map_invalid_noflush); - _vm_unmap_aliases(start, end, 1); + _vm_unmap_aliases(start, end, flush_dmap); set_area_direct_map(area, set_direct_map_default_noflush); } diff --git a/mm/vmpressure.c b/mm/vmpressure.c index 4854584ec436..f3b50811497a 100644 --- a/mm/vmpressure.c +++ b/mm/vmpressure.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0-only /* * Linux VM pressure * @@ -6,10 +7,6 @@ * * 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> diff --git a/mm/vmscan.c b/mm/vmscan.c index 7acd0afdfc2a..910e02c793ff 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -1505,7 +1505,7 @@ unsigned long reclaim_clean_pages_from_list(struct zone *zone, list_for_each_entry_safe(page, next, page_list, lru) { if (page_is_file_cache(page) && !PageDirty(page) && - !__PageMovable(page)) { + !__PageMovable(page) && !PageUnevictable(page)) { ClearPageActive(page); list_move(&page->lru, &clean_pages); } @@ -1953,8 +1953,8 @@ shrink_inactive_list(unsigned long nr_to_scan, struct lruvec *lruvec, if (global_reclaim(sc)) __count_vm_events(item, nr_reclaimed); __count_memcg_events(lruvec_memcg(lruvec), item, nr_reclaimed); - reclaim_stat->recent_rotated[0] = stat.nr_activate[0]; - reclaim_stat->recent_rotated[1] = stat.nr_activate[1]; + reclaim_stat->recent_rotated[0] += stat.nr_activate[0]; + reclaim_stat->recent_rotated[1] += stat.nr_activate[1]; move_pages_to_lru(lruvec, &page_list); @@ -3644,19 +3644,18 @@ out: } /* - * pgdat->kswapd_classzone_idx is the highest zone index that a recent - * allocation request woke kswapd for. When kswapd has not woken recently, - * the value is MAX_NR_ZONES which is not a valid index. This compares a - * given classzone and returns it or the highest classzone index kswapd - * was recently woke for. + * The pgdat->kswapd_classzone_idx is used to pass the highest zone index to be + * reclaimed by kswapd from the waker. If the value is MAX_NR_ZONES which is not + * a valid index then either kswapd runs for first time or kswapd couldn't sleep + * after previous reclaim attempt (node is still unbalanced). In that case + * return the zone index of the previous kswapd reclaim cycle. */ static enum zone_type kswapd_classzone_idx(pg_data_t *pgdat, - enum zone_type classzone_idx) + enum zone_type prev_classzone_idx) { if (pgdat->kswapd_classzone_idx == MAX_NR_ZONES) - return classzone_idx; - - return max(pgdat->kswapd_classzone_idx, classzone_idx); + return prev_classzone_idx; + return pgdat->kswapd_classzone_idx; } static void kswapd_try_to_sleep(pg_data_t *pgdat, int alloc_order, int reclaim_order, @@ -3797,7 +3796,7 @@ kswapd_try_sleep: /* Read the new order and classzone_idx */ alloc_order = reclaim_order = pgdat->kswapd_order; - classzone_idx = kswapd_classzone_idx(pgdat, 0); + classzone_idx = kswapd_classzone_idx(pgdat, classzone_idx); pgdat->kswapd_order = 0; pgdat->kswapd_classzone_idx = MAX_NR_ZONES; @@ -3851,8 +3850,12 @@ void wakeup_kswapd(struct zone *zone, gfp_t gfp_flags, int order, if (!cpuset_zone_allowed(zone, gfp_flags)) return; pgdat = zone->zone_pgdat; - pgdat->kswapd_classzone_idx = kswapd_classzone_idx(pgdat, - classzone_idx); + + 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; |