diff options
Diffstat (limited to 'mm')
-rw-r--r-- | mm/filemap.c | 2 | ||||
-rw-r--r-- | mm/frame_vector.c | 31 | ||||
-rw-r--r-- | mm/frontswap.c | 2 | ||||
-rw-r--r-- | mm/hugetlb.c | 11 | ||||
-rw-r--r-- | mm/kasan/report.c | 3 | ||||
-rw-r--r-- | mm/khugepaged.c | 24 | ||||
-rw-r--r-- | mm/ksm.c | 2 | ||||
-rw-r--r-- | mm/memblock.c | 10 | ||||
-rw-r--r-- | mm/memcontrol.c | 19 | ||||
-rw-r--r-- | mm/memfd.c | 30 | ||||
-rw-r--r-- | mm/memory-failure.c | 6 | ||||
-rw-r--r-- | mm/memory.c | 53 | ||||
-rw-r--r-- | mm/mempolicy.c | 18 | ||||
-rw-r--r-- | mm/migrate.c | 13 | ||||
-rw-r--r-- | mm/mmap.c | 28 | ||||
-rw-r--r-- | mm/mremap.c | 3 | ||||
-rw-r--r-- | mm/page_alloc.c | 94 | ||||
-rw-r--r-- | mm/page_io.c | 55 | ||||
-rw-r--r-- | mm/percpu.c | 2 | ||||
-rw-r--r-- | mm/readahead.c | 3 | ||||
-rw-r--r-- | mm/rmap.c | 56 | ||||
-rw-r--r-- | mm/shmem.c | 37 | ||||
-rw-r--r-- | mm/slub.c | 13 | ||||
-rw-r--r-- | mm/swap.c | 4 | ||||
-rw-r--r-- | mm/swapfile.c | 4 | ||||
-rw-r--r-- | mm/usercopy.c | 5 | ||||
-rw-r--r-- | mm/userfaultfd.c | 3 | ||||
-rw-r--r-- | mm/util.c | 33 | ||||
-rw-r--r-- | mm/zsmalloc.c | 37 |
29 files changed, 408 insertions, 193 deletions
diff --git a/mm/filemap.c b/mm/filemap.c index f2e777003b90..e61ec2c88bd0 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -3140,7 +3140,7 @@ ssize_t generic_perform_write(struct file *file, unsigned long offset; /* Offset into pagecache page */ unsigned long bytes; /* Bytes to write to page */ size_t copied; /* Bytes copied from user */ - void *fsdata; + void *fsdata = NULL; offset = (pos & (PAGE_SIZE - 1)); bytes = min_t(unsigned long, PAGE_SIZE - offset, diff --git a/mm/frame_vector.c b/mm/frame_vector.c index c64dca6e27c2..7124410a0016 100644 --- a/mm/frame_vector.c +++ b/mm/frame_vector.c @@ -37,7 +37,6 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, struct mm_struct *mm = current->mm; struct vm_area_struct *vma; int ret = 0; - int err; int locked; if (nr_frames == 0) @@ -72,32 +71,14 @@ int get_vaddr_frames(unsigned long start, unsigned int nr_frames, vec->is_pfns = false; ret = get_user_pages_locked(start, nr_frames, gup_flags, (struct page **)(vec->ptrs), &locked); - goto out; + if (likely(ret > 0)) + goto out; } - vec->got_ref = false; - vec->is_pfns = true; - do { - unsigned long *nums = frame_vector_pfns(vec); - - while (ret < nr_frames && start + PAGE_SIZE <= vma->vm_end) { - err = follow_pfn(vma, start, &nums[ret]); - if (err) { - if (ret == 0) - ret = err; - goto out; - } - start += PAGE_SIZE; - ret++; - } - /* - * We stop if we have enough pages or if VMA doesn't completely - * cover the tail page. - */ - if (ret >= nr_frames || start < vma->vm_end) - break; - vma = find_vma_intersection(mm, start, start + 1); - } while (vma && vma->vm_flags & (VM_IO | VM_PFNMAP)); + /* This used to (racily) return non-refcounted pfns. Let people know */ + WARN_ONCE(1, "get_vaddr_frames() cannot follow VM_IO mapping"); + vec->nr_frames = 0; + out: if (locked) up_read(&mm->mmap_sem); diff --git a/mm/frontswap.c b/mm/frontswap.c index 157e5bf63504..80bf870d881a 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -447,7 +447,7 @@ static int __frontswap_shrink(unsigned long target_pages, void frontswap_shrink(unsigned long target_pages) { unsigned long pages_to_unuse = 0; - int uninitialized_var(type), ret; + int type, ret; /* * we don't want to hold swap_lock while doing a very diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 0c5a2b4e003d..47e98a5726c4 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -2116,11 +2116,11 @@ struct page *alloc_huge_page(struct vm_area_struct *vma, page = alloc_buddy_huge_page_with_mpol(h, vma, addr); if (!page) goto out_uncharge_cgroup; + spin_lock(&hugetlb_lock); if (!avoid_reserve && vma_has_reserves(vma, gbl_chg)) { SetPagePrivate(page); h->resv_huge_pages--; } - spin_lock(&hugetlb_lock); list_move(&page->lru, &h->hugepage_activelist); /* Fall through */ } @@ -4837,7 +4837,14 @@ int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) pud_clear(pud); put_page(virt_to_page(ptep)); mm_dec_nr_pmds(mm); - *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; + /* + * This update of passed address optimizes loops sequentially + * processing addresses in increments of huge page size (PMD_SIZE + * in this case). By clearing the pud, a PUD_SIZE area is unmapped. + * Update address to the 'last page' in the cleared area so that + * calling loop can move to first page past this area. + */ + *addr |= PUD_SIZE - PMD_SIZE; return 1; } #define want_pmd_share() (1) diff --git a/mm/kasan/report.c b/mm/kasan/report.c index 5c169aa688fd..3ae996824a04 100644 --- a/mm/kasan/report.c +++ b/mm/kasan/report.c @@ -176,8 +176,7 @@ static void kasan_end_report(unsigned long *flags) pr_err("==================================================================\n"); add_taint(TAINT_BAD_PAGE, LOCKDEP_NOW_UNRELIABLE); spin_unlock_irqrestore(&report_lock, *flags); - if (panic_on_warn) - panic("panic_on_warn set ...\n"); + check_panic_on_warn("KASAN"); kasan_enable_current(); } diff --git a/mm/khugepaged.c b/mm/khugepaged.c index 5dd14ef2e1de..60f7df987567 100644 --- a/mm/khugepaged.c +++ b/mm/khugepaged.c @@ -23,6 +23,19 @@ #include <asm/pgalloc.h> #include "internal.h" +/* gross hack for <=4.19 stable */ +#if defined(CONFIG_S390) || defined(CONFIG_ARM) +static void tlb_remove_table_smp_sync(void *arg) +{ + /* Simply deliver the interrupt */ +} + +static void tlb_remove_table_sync_one(void) +{ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); +} +#endif + enum scan_result { SCAN_FAIL, SCAN_SUCCEED, @@ -1045,6 +1058,7 @@ static void collapse_huge_page(struct mm_struct *mm, _pmd = pmdp_collapse_flush(vma, address, pmd); spin_unlock(pmd_ptl); mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + tlb_remove_table_sync_one(); spin_lock(pte_ptl); isolated = __collapse_huge_page_isolate(vma, address, pte); @@ -1289,12 +1303,20 @@ static void retract_page_tables(struct address_space *mapping, pgoff_t pgoff) */ if (down_write_trylock(&mm->mmap_sem)) { if (!khugepaged_test_exit(mm)) { - spinlock_t *ptl = pmd_lock(mm, pmd); + spinlock_t *ptl; + unsigned long end = addr + HPAGE_PMD_SIZE; + + mmu_notifier_invalidate_range_start(mm, addr, + end); + ptl = pmd_lock(mm, pmd); /* assume page table is clear */ _pmd = pmdp_collapse_flush(vma, addr, pmd); spin_unlock(ptl); mm_dec_nr_ptes(mm); + tlb_remove_table_sync_one(); pte_free(mm, pmd_pgtable(_pmd)); + mmu_notifier_invalidate_range_end(mm, addr, + end); } up_write(&mm->mmap_sem); } @@ -2381,7 +2381,7 @@ next_mm: static void ksm_do_scan(unsigned int scan_npages) { struct rmap_item *rmap_item; - struct page *uninitialized_var(page); + struct page *page; while (scan_npages-- && likely(!freezing(current))) { cond_resched(); diff --git a/mm/memblock.c b/mm/memblock.c index 4f7c5c3c442c..4d471da3cc47 100644 --- a/mm/memblock.c +++ b/mm/memblock.c @@ -322,14 +322,20 @@ void __init memblock_discard(void) addr = __pa(memblock.reserved.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.reserved.max); - __memblock_free_late(addr, size); + if (memblock_reserved_in_slab) + kfree(memblock.reserved.regions); + else + __memblock_free_late(addr, size); } if (memblock.memory.regions != memblock_memory_init_regions) { addr = __pa(memblock.memory.regions); size = PAGE_ALIGN(sizeof(struct memblock_region) * memblock.memory.max); - __memblock_free_late(addr, size); + if (memblock_memory_in_slab) + kfree(memblock.memory.regions); + else + __memblock_free_late(addr, size); } } #endif diff --git a/mm/memcontrol.c b/mm/memcontrol.c index 87cd5bf1b487..5a366cf79821 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -919,7 +919,7 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, struct mem_cgroup *prev, struct mem_cgroup_reclaim_cookie *reclaim) { - struct mem_cgroup_reclaim_iter *uninitialized_var(iter); + struct mem_cgroup_reclaim_iter *iter; struct cgroup_subsys_state *css = NULL; struct mem_cgroup *memcg = NULL; struct mem_cgroup *pos = NULL; @@ -4120,6 +4120,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, unsigned int efd, cfd; struct fd efile; struct fd cfile; + struct dentry *cdentry; const char *name; char *endp; int ret; @@ -4171,6 +4172,16 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, goto out_put_cfile; /* + * The control file must be a regular cgroup1 file. As a regular cgroup + * file can't be renamed, it's safe to access its name afterwards. + */ + cdentry = cfile.file->f_path.dentry; + if (cdentry->d_sb->s_type != &cgroup_fs_type || !d_is_reg(cdentry)) { + ret = -EINVAL; + goto out_put_cfile; + } + + /* * Determine the event callbacks and set them in @event. This used * to be done via struct cftype but cgroup core no longer knows * about these events. The following is crude but the whole thing @@ -4178,7 +4189,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * * DO NOT ADD NEW FILES. */ - name = cfile.file->f_path.dentry->d_name.name; + name = cdentry->d_name.name; if (!strcmp(name, "memory.usage_in_bytes")) { event->register_event = mem_cgroup_usage_register_event; @@ -4202,7 +4213,7 @@ static ssize_t memcg_write_event_control(struct kernfs_open_file *of, * automatically removed on cgroup destruction but the removal is * asynchronous, so take an extra ref on @css. */ - cfile_css = css_tryget_online_from_dir(cfile.file->f_path.dentry->d_parent, + cfile_css = css_tryget_online_from_dir(cdentry->d_parent, &memory_cgrp_subsys); ret = -EINVAL; if (IS_ERR(cfile_css)) @@ -6404,7 +6415,7 @@ static int __init cgroup_memory(char *s) if (!strcmp(token, "nokmem")) cgroup_memory_nokmem = true; } - return 0; + return 1; } __setup("cgroup.memory=", cgroup_memory); diff --git a/mm/memfd.c b/mm/memfd.c index 9e68a4320a0e..2d19288a093e 100644 --- a/mm/memfd.c +++ b/mm/memfd.c @@ -34,26 +34,35 @@ static void memfd_tag_pins(struct address_space *mapping) void __rcu **slot; pgoff_t start; struct page *page; - unsigned int tagged = 0; + int latency = 0; + int cache_count; lru_add_drain(); start = 0; xa_lock_irq(&mapping->i_pages); radix_tree_for_each_slot(slot, &mapping->i_pages, &iter, start) { + cache_count = 1; page = radix_tree_deref_slot_protected(slot, &mapping->i_pages.xa_lock); - if (!page || radix_tree_exception(page)) { + if (!page || radix_tree_exception(page) || PageTail(page)) { if (radix_tree_deref_retry(page)) { slot = radix_tree_iter_retry(&iter); continue; } - } else if (page_count(page) - page_mapcount(page) > 1) { - radix_tree_tag_set(&mapping->i_pages, iter.index, - MEMFD_TAG_PINNED); + } else { + if (PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + if (cache_count != + page_count(page) - total_mapcount(page)) { + radix_tree_tag_set(&mapping->i_pages, + iter.index, MEMFD_TAG_PINNED); + } } - if (++tagged % 1024) + latency += cache_count; + if (latency < 1024) continue; + latency = 0; slot = radix_tree_iter_resume(slot, &iter); xa_unlock_irq(&mapping->i_pages); @@ -79,6 +88,7 @@ static int memfd_wait_for_pins(struct address_space *mapping) pgoff_t start; struct page *page; int error, scan; + int cache_count; memfd_tag_pins(mapping); @@ -107,8 +117,12 @@ static int memfd_wait_for_pins(struct address_space *mapping) page = NULL; } - if (page && - page_count(page) - page_mapcount(page) != 1) { + cache_count = 1; + if (page && PageTransHuge(page) && !PageHuge(page)) + cache_count = HPAGE_PMD_NR; + + if (page && cache_count != + page_count(page) - total_mapcount(page)) { if (scan < LAST_SCAN) goto continue_resched; diff --git a/mm/memory-failure.c b/mm/memory-failure.c index 3da3c63dccd1..c971d5e11f93 100644 --- a/mm/memory-failure.c +++ b/mm/memory-failure.c @@ -989,7 +989,7 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, * This check implies we don't kill processes if their pages * are in the swap cache early. Those are always late kills. */ - if (!page_mapped(hpage)) + if (!page_mapped(p)) return true; if (PageKsm(p)) { @@ -1033,10 +1033,10 @@ static bool hwpoison_user_mappings(struct page *p, unsigned long pfn, if (kill) collect_procs(hpage, &tokill, flags & MF_ACTION_REQUIRED); - unmap_success = try_to_unmap(hpage, ttu); + unmap_success = try_to_unmap(p, ttu); if (!unmap_success) pr_err("Memory failure: %#lx: failed to unmap page (mapcount=%d)\n", - pfn, page_mapcount(hpage)); + pfn, page_mapcount(p)); /* * try_to_unmap() might put mlocked page in lru cache, so call diff --git a/mm/memory.c b/mm/memory.c index 1d03085fde02..1e108db4405c 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -362,6 +362,11 @@ static void tlb_remove_table_smp_sync(void *arg) /* Simply deliver the interrupt */ } +void tlb_remove_table_sync_one(void) +{ + smp_call_function(tlb_remove_table_smp_sync, NULL, 1); +} + static void tlb_remove_table_one(void *table) { /* @@ -1302,6 +1307,17 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, return ret; } +/* Whether we should zap all COWed (private) pages too */ +static inline bool should_zap_cows(struct zap_details *details) +{ + /* By default, zap all pages */ + if (!details) + return true; + + /* Or, we zap COWed pages only if the caller wants to */ + return !details->check_mapping; +} + static unsigned long zap_pte_range(struct mmu_gather *tlb, struct vm_area_struct *vma, pmd_t *pmd, unsigned long addr, unsigned long end, @@ -1390,17 +1406,19 @@ again: continue; } - /* If details->check_mapping, we leave swap entries. */ - if (unlikely(details)) - continue; - entry = pte_to_swp_entry(ptent); - if (!non_swap_entry(entry)) + if (!non_swap_entry(entry)) { + /* Genuine swap entry, hence a private anon page */ + if (!should_zap_cows(details)) + continue; rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { + } else if (is_migration_entry(entry)) { struct page *page; page = migration_entry_to_page(entry); + if (details && details->check_mapping && + details->check_mapping != page_rmapping(page)) + continue; rss[mm_counter(page)]--; } if (unlikely(!free_swap_and_cache(entry))) @@ -3024,8 +3042,8 @@ void unmap_mapping_pages(struct address_space *mapping, pgoff_t start, void unmap_mapping_range(struct address_space *mapping, loff_t const holebegin, loff_t const holelen, int even_cows) { - pgoff_t hba = holebegin >> PAGE_SHIFT; - pgoff_t hlen = (holelen + PAGE_SIZE - 1) >> PAGE_SHIFT; + pgoff_t hba = (pgoff_t)(holebegin) >> PAGE_SHIFT; + pgoff_t hlen = ((pgoff_t)(holelen) + PAGE_SIZE - 1) >> PAGE_SHIFT; /* Check for overflow. */ if (sizeof(holelen) > sizeof(hlen)) { @@ -3416,11 +3434,20 @@ static vm_fault_t __do_fault(struct vm_fault *vmf) return ret; if (unlikely(PageHWPoison(vmf->page))) { - if (ret & VM_FAULT_LOCKED) - unlock_page(vmf->page); - put_page(vmf->page); + struct page *page = vmf->page; + vm_fault_t poisonret = VM_FAULT_HWPOISON; + if (ret & VM_FAULT_LOCKED) { + if (page_mapped(page)) + unmap_mapping_pages(page_mapping(page), + page->index, 1, false); + /* Retry if a clean page was removed from the cache. */ + if (invalidate_inode_page(page)) + poisonret = VM_FAULT_NOPAGE; + unlock_page(page); + } + put_page(page); vmf->page = NULL; - return VM_FAULT_HWPOISON; + return poisonret; } if (unlikely(!(ret & VM_FAULT_LOCKED))) @@ -4956,6 +4983,8 @@ long copy_huge_page_from_user(struct page *dst_page, if (rc) break; + flush_dcache_page(subpage); + cond_resched(); } return ret_val; diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 3cd27c1c729f..86fd6bedaff4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -348,7 +348,7 @@ static void mpol_rebind_preferred(struct mempolicy *pol, */ static void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask) { - if (!pol) + if (!pol || pol->mode == MPOL_LOCAL) return; if (!mpol_store_user_nodemask(pol) && !(pol->flags & MPOL_F_LOCAL) && nodes_equal(pol->w.cpuset_mems_allowed, *newmask)) @@ -571,7 +571,8 @@ static int queue_pages_hugetlb(pte_t *pte, unsigned long hmask, goto unlock; /* With MPOL_MF_MOVE, we migrate only unshared hugepage. */ if (flags & (MPOL_MF_MOVE_ALL) || - (flags & MPOL_MF_MOVE && page_mapcount(page) == 1)) + (flags & MPOL_MF_MOVE && page_mapcount(page) == 1 && + !hugetlb_pmd_shared(pte))) isolate_huge_page(page, qp->pagelist); unlock: spin_unlock(ptl); @@ -732,7 +733,6 @@ static int vma_replace_policy(struct vm_area_struct *vma, static int mbind_range(struct mm_struct *mm, unsigned long start, unsigned long end, struct mempolicy *new_pol) { - struct vm_area_struct *next; struct vm_area_struct *prev; struct vm_area_struct *vma; int err = 0; @@ -748,8 +748,7 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, if (start > vma->vm_start) prev = vma; - for (; vma && vma->vm_start < end; prev = vma, vma = next) { - next = vma->vm_next; + for (; vma && vma->vm_start < end; prev = vma, vma = vma->vm_next) { vmstart = max(start, vma->vm_start); vmend = min(end, vma->vm_end); @@ -763,10 +762,6 @@ static int mbind_range(struct mm_struct *mm, unsigned long start, new_pol, vma->vm_userfaultfd_ctx); if (prev) { vma = prev; - next = vma->vm_next; - if (mpol_equal(vma_policy(vma), new_pol)) - continue; - /* vma_merge() joined vma && vma->next, case 8 */ goto replace; } if (vma->vm_start != vmstart) { @@ -1152,7 +1147,7 @@ int do_migrate_pages(struct mm_struct *mm, const nodemask_t *from, static struct page *new_page(struct page *page, unsigned long start) { struct vm_area_struct *vma; - unsigned long uninitialized_var(address); + unsigned long address; vma = find_vma(current->mm, start); while (vma) { @@ -1550,7 +1545,7 @@ static int kernel_get_mempolicy(int __user *policy, unsigned long flags) { int err; - int uninitialized_var(pval); + int pval; nodemask_t nodes; if (nmask != NULL && maxnode < nr_node_ids) @@ -2569,6 +2564,7 @@ alloc_new: mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL); if (!mpol_new) goto err_out; + atomic_set(&mpol_new->refcnt, 1); goto restart; } diff --git a/mm/migrate.c b/mm/migrate.c index a69b842f95da..171573613c39 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -472,6 +472,10 @@ int migrate_page_move_mapping(struct address_space *mapping, pslot = radix_tree_lookup_slot(&mapping->i_pages, page_index(page)); + if (pslot == NULL) { + xa_unlock_irq(&mapping->i_pages); + return -EAGAIN; + } expected_count += hpage_nr_pages(page) + page_has_private(page); if (page_count(page) != expected_count || @@ -590,6 +594,10 @@ int migrate_huge_page_move_mapping(struct address_space *mapping, xa_lock_irq(&mapping->i_pages); pslot = radix_tree_lookup_slot(&mapping->i_pages, page_index(page)); + if (pslot == NULL) { + xa_unlock_irq(&mapping->i_pages); + return -EAGAIN; + } expected_count = 2 + page_has_private(page); if (page_count(page) != expected_count || @@ -2351,13 +2359,14 @@ next: migrate->dst[migrate->npages] = 0; migrate->src[migrate->npages++] = mpfn; } - arch_leave_lazy_mmu_mode(); - pte_unmap_unlock(ptep - 1, ptl); /* Only flush the TLB if we actually modified any entries */ if (unmapped) flush_tlb_range(walk->vma, start, end); + arch_leave_lazy_mmu_mode(); + pte_unmap_unlock(ptep - 1, ptl); + return 0; } diff --git a/mm/mmap.c b/mm/mmap.c index f875386e7acd..38541885ea45 100644 --- a/mm/mmap.c +++ b/mm/mmap.c @@ -1640,8 +1640,12 @@ int vma_wants_writenotify(struct vm_area_struct *vma, pgprot_t vm_page_prot) pgprot_val(vm_pgprot_modify(vm_page_prot, vm_flags))) return 0; - /* Do we need to track softdirty? */ - if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY)) + /* + * Do we need to track softdirty? hugetlb does not support softdirty + * tracking yet. + */ + if (IS_ENABLED(CONFIG_MEM_SOFT_DIRTY) && !(vm_flags & VM_SOFTDIRTY) && + !is_vm_hugetlb_page(vma)) return 1; /* Specialty mapping? */ @@ -1821,7 +1825,6 @@ unmap_and_free_vma: /* Undo any partial mapping done by a device driver. */ unmap_region(mm, vma, prev, vma->vm_start, vma->vm_end); - charged = 0; if (vm_flags & VM_SHARED) mapping_unmap_writable(file->f_mapping); allow_write_and_free_vma: @@ -2469,7 +2472,7 @@ static int __init cmdline_parse_stack_guard_gap(char *p) if (!*endptr) stack_guard_gap = val << PAGE_SHIFT; - return 0; + return 1; } __setup("stack_guard_gap=", cmdline_parse_stack_guard_gap); @@ -2564,11 +2567,28 @@ static void unmap_region(struct mm_struct *mm, { struct vm_area_struct *next = prev ? prev->vm_next : mm->mmap; struct mmu_gather tlb; + struct vm_area_struct *cur_vma; lru_add_drain(); tlb_gather_mmu(&tlb, mm, start, end); update_hiwater_rss(mm); unmap_vmas(&tlb, vma, start, end); + + /* + * Ensure we have no stale TLB entries by the time this mapping is + * removed from the rmap. + * Note that we don't have to worry about nested flushes here because + * we're holding the mm semaphore for removing the mapping - so any + * concurrent flush in this region has to be coming through the rmap, + * and we synchronize against that using the rmap lock. + */ + for (cur_vma = vma; cur_vma; cur_vma = cur_vma->vm_next) { + if ((cur_vma->vm_flags & (VM_PFNMAP|VM_MIXEDMAP)) != 0) { + tlb_flush_mmu(&tlb); + break; + } + } + free_pgtables(&tlb, vma, prev ? prev->vm_end : FIRST_USER_ADDRESS, next ? next->vm_start : USER_PGTABLES_CEILING); tlb_finish_mmu(&tlb, start, end); diff --git a/mm/mremap.c b/mm/mremap.c index 33d8bbe24ddd..3cf9d77b3334 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -201,6 +201,9 @@ unsigned long move_page_tables(struct vm_area_struct *vma, unsigned long mmun_start; /* For mmu_notifiers */ unsigned long mmun_end; /* For mmu_notifiers */ + if (!len) + return 0; + old_end = old_addr + len; flush_cache_range(vma, old_addr, old_end); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index afcaa657a022..4553cc848abc 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -3779,6 +3779,30 @@ void fs_reclaim_release(gfp_t gfp_mask) EXPORT_SYMBOL_GPL(fs_reclaim_release); #endif +/* + * Zonelists may change due to hotplug during allocation. Detect when zonelists + * have been rebuilt so allocation retries. Reader side does not lock and + * retries the allocation if zonelist changes. Writer side is protected by the + * embedded spin_lock. + */ +static DEFINE_SEQLOCK(zonelist_update_seq); + +static unsigned int zonelist_iter_begin(void) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqbegin(&zonelist_update_seq); + + return 0; +} + +static unsigned int check_retry_zonelist(unsigned int seq) +{ + if (IS_ENABLED(CONFIG_MEMORY_HOTREMOVE)) + return read_seqretry(&zonelist_update_seq, seq); + + return seq; +} + /* Perform direct synchronous page reclaim */ static int __perform_reclaim(gfp_t gfp_mask, unsigned int order, @@ -4084,6 +4108,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, int compaction_retries; int no_progress_loops; unsigned int cpuset_mems_cookie; + unsigned int zonelist_iter_cookie; int reserve_flags; /* @@ -4094,11 +4119,12 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (__GFP_ATOMIC|__GFP_DIRECT_RECLAIM))) gfp_mask &= ~__GFP_ATOMIC; -retry_cpuset: +restart: compaction_retries = 0; no_progress_loops = 0; compact_priority = DEF_COMPACT_PRIORITY; cpuset_mems_cookie = read_mems_allowed_begin(); + zonelist_iter_cookie = zonelist_iter_begin(); /* * The fast path uses conservative alloc_flags to succeed only until @@ -4247,9 +4273,13 @@ retry: goto retry; - /* Deal with possible cpuset update races before we start OOM killing */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* Reclaim has failed us, start killing things */ page = __alloc_pages_may_oom(gfp_mask, order, ac, &did_some_progress); @@ -4269,9 +4299,13 @@ retry: } nopage: - /* Deal with possible cpuset update races before we fail */ - if (check_retry_cpuset(cpuset_mems_cookie, ac)) - goto retry_cpuset; + /* + * Deal with possible cpuset update races or zonelist updates to avoid + * a unnecessary OOM kill. + */ + if (check_retry_cpuset(cpuset_mems_cookie, ac) || + check_retry_zonelist(zonelist_iter_cookie)) + goto restart; /* * Make sure that __GFP_NOFAIL request doesn't leak out and make sure @@ -4569,6 +4603,18 @@ refill: /* reset page count bias and offset to start of new frag */ nc->pagecnt_bias = PAGE_FRAG_CACHE_MAX_SIZE + 1; offset = size - fragsz; + if (unlikely(offset < 0)) { + /* + * The caller is trying to allocate a fragment + * with fragsz > PAGE_SIZE but the cache isn't big + * enough to satisfy the request, this may + * happen in low memory conditions. + * We don't release the cache page because + * it could make memory pressure worse + * so we simply return NULL here. + */ + return NULL; + } } nc->pagecnt_bias--; @@ -5091,7 +5137,7 @@ static int build_zonerefs_node(pg_data_t *pgdat, struct zoneref *zonerefs) do { zone_type--; zone = pgdat->node_zones + zone_type; - if (managed_zone(zone)) { + if (populated_zone(zone)) { zoneref_set_zone(zone, &zonerefs[nr_zones++]); check_highest_zone(zone_type); } @@ -5379,9 +5425,22 @@ static void __build_all_zonelists(void *data) int nid; int __maybe_unused cpu; pg_data_t *self = data; - static DEFINE_SPINLOCK(lock); + unsigned long flags; - spin_lock(&lock); + /* + * Explicitly disable this CPU's interrupts before taking seqlock + * to prevent any IRQ handler from calling into the page allocator + * (e.g. GFP_ATOMIC) that could hit zonelist_iter_begin and livelock. + */ + local_irq_save(flags); + /* + * Explicitly disable this CPU's synchronous printk() before taking + * seqlock to prevent any printk() from trying to hold port->lock, for + * tty_insert_flip_string_and_push_buffer() on other CPU might be + * calling kmalloc(GFP_ATOMIC | __GFP_NOWARN) with port->lock held. + */ + printk_deferred_enter(); + write_seqlock(&zonelist_update_seq); #ifdef CONFIG_NUMA memset(node_load, 0, sizeof(node_load)); @@ -5414,7 +5473,9 @@ static void __build_all_zonelists(void *data) #endif } - spin_unlock(&lock); + write_sequnlock(&zonelist_update_seq); + printk_deferred_exit(); + local_irq_restore(flags); } static noinline void __init @@ -6855,10 +6916,17 @@ restart: out2: /* Align start of ZONE_MOVABLE on all nids to MAX_ORDER_NR_PAGES */ - for (nid = 0; nid < MAX_NUMNODES; nid++) + for (nid = 0; nid < MAX_NUMNODES; nid++) { + unsigned long start_pfn, end_pfn; + zone_movable_pfn[nid] = roundup(zone_movable_pfn[nid], MAX_ORDER_NR_PAGES); + get_pfn_range_for_nid(nid, &start_pfn, &end_pfn); + if (zone_movable_pfn[nid] >= end_pfn) + zone_movable_pfn[nid] = 0; + } + out: /* restore the node_state */ node_states[N_MEMORY] = saved_node_state; @@ -7110,7 +7178,7 @@ void __init mem_init_print_info(const char *str) */ #define adj_init_size(start, end, size, pos, adj) \ do { \ - if (start <= pos && pos < end && size > adj) \ + if (&start[0] <= &pos[0] && &pos[0] < &end[0] && size > adj) \ size -= adj; \ } while (0) diff --git a/mm/page_io.c b/mm/page_io.c index 9b646f07f47f..929e7829e02d 100644 --- a/mm/page_io.c +++ b/mm/page_io.c @@ -71,55 +71,6 @@ void end_swap_bio_write(struct bio *bio) bio_put(bio); } -static void swap_slot_free_notify(struct page *page) -{ - struct swap_info_struct *sis; - struct gendisk *disk; - swp_entry_t entry; - - /* - * There is no guarantee that the page is in swap cache - the software - * suspend code (at least) uses end_swap_bio_read() against a non- - * swapcache page. So we must check PG_swapcache before proceeding with - * this optimization. - */ - if (unlikely(!PageSwapCache(page))) - return; - - sis = page_swap_info(page); - if (!(sis->flags & SWP_BLKDEV)) - return; - - /* - * The swap subsystem performs lazy swap slot freeing, - * expecting that the page will be swapped out again. - * So we can avoid an unnecessary write if the page - * isn't redirtied. - * This is good for real swap storage because we can - * reduce unnecessary I/O and enhance wear-leveling - * if an SSD is used as the as swap device. - * But if in-memory swap device (eg zram) is used, - * this causes a duplicated copy between uncompressed - * data in VM-owned memory and compressed data in - * zram-owned memory. So let's free zram-owned memory - * and make the VM-owned decompressed page *dirty*, - * so the page should be swapped out somewhere again if - * we again wish to reclaim it. - */ - disk = sis->bdev->bd_disk; - entry.val = page_private(page); - if (disk->fops->swap_slot_free_notify && - __swap_count(sis, entry) == 1) { - unsigned long offset; - - offset = swp_offset(entry); - - SetPageDirty(page); - disk->fops->swap_slot_free_notify(sis->bdev, - offset); - } -} - static void end_swap_bio_read(struct bio *bio) { struct page *page = bio_first_page_all(bio); @@ -135,7 +86,6 @@ static void end_swap_bio_read(struct bio *bio) } SetPageUptodate(page); - swap_slot_free_notify(page); out: unlock_page(page); WRITE_ONCE(bio->bi_private, NULL); @@ -373,11 +323,6 @@ int swap_readpage(struct page *page, bool synchronous) ret = bdev_read_page(sis->bdev, map_swap_page(page, &sis->bdev), page); if (!ret) { - if (trylock_page(page)) { - swap_slot_free_notify(page); - unlock_page(page); - } - count_vm_event(PSWPIN); return 0; } diff --git a/mm/percpu.c b/mm/percpu.c index 0151f276ae68..6ae4993214b4 100644 --- a/mm/percpu.c +++ b/mm/percpu.c @@ -2283,7 +2283,7 @@ static struct pcpu_alloc_info * __init pcpu_build_alloc_info( const size_t static_size = __per_cpu_end - __per_cpu_start; int nr_groups = 1, nr_units = 0; size_t size_sum, min_unit_size, alloc_size; - int upa, max_upa, uninitialized_var(best_upa); /* units_per_alloc */ + int upa, max_upa, best_upa; /* units_per_alloc */ int last_allocs, group, unit; unsigned int cpu, tcpu; struct pcpu_alloc_info *ai; diff --git a/mm/readahead.c b/mm/readahead.c index 4e630143a0ba..96d0f652222a 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -593,7 +593,8 @@ ssize_t ksys_readahead(int fd, loff_t offset, size_t count) */ ret = -EINVAL; if (!f.file->f_mapping || !f.file->f_mapping->a_ops || - !S_ISREG(file_inode(f.file)->i_mode)) + (!S_ISREG(file_inode(f.file)->i_mode) && + !S_ISBLK(file_inode(f.file)->i_mode))) goto out; ret = vfs_fadvise(f.file, offset, count, POSIX_FADV_WILLNEED); diff --git a/mm/rmap.c b/mm/rmap.c index 699f445e3e78..3c2a43938152 100644 --- a/mm/rmap.c +++ b/mm/rmap.c @@ -82,7 +82,8 @@ static inline struct anon_vma *anon_vma_alloc(void) anon_vma = kmem_cache_alloc(anon_vma_cachep, GFP_KERNEL); if (anon_vma) { atomic_set(&anon_vma->refcount, 1); - anon_vma->degree = 1; /* Reference for first vma */ + anon_vma->num_children = 0; + anon_vma->num_active_vmas = 0; anon_vma->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called @@ -190,6 +191,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) anon_vma = anon_vma_alloc(); if (unlikely(!anon_vma)) goto out_enomem_free_avc; + anon_vma->num_children++; /* self-parent link for new root */ allocated = anon_vma; } @@ -199,8 +201,7 @@ int __anon_vma_prepare(struct vm_area_struct *vma) if (likely(!vma->anon_vma)) { vma->anon_vma = anon_vma; anon_vma_chain_link(vma, avc, anon_vma); - /* vma reference or self-parent link for new root */ - anon_vma->degree++; + anon_vma->num_active_vmas++; allocated = NULL; avc = NULL; } @@ -279,19 +280,19 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) anon_vma_chain_link(dst, avc, anon_vma); /* - * Reuse existing anon_vma if its degree lower than two, - * that means it has no vma and only one anon_vma child. + * Reuse existing anon_vma if it has no vma and only one + * anon_vma child. * - * Do not chose parent anon_vma, otherwise first child - * will always reuse it. Root anon_vma is never reused: + * Root anon_vma is never reused: * it has self-parent reference and at least one child. */ - if (!dst->anon_vma && anon_vma != src->anon_vma && - anon_vma->degree < 2) + if (!dst->anon_vma && + anon_vma->num_children < 2 && + anon_vma->num_active_vmas == 0) dst->anon_vma = anon_vma; } if (dst->anon_vma) - dst->anon_vma->degree++; + dst->anon_vma->num_active_vmas++; unlock_anon_vma_root(root); return 0; @@ -341,6 +342,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) anon_vma = anon_vma_alloc(); if (!anon_vma) goto out_error; + anon_vma->num_active_vmas++; avc = anon_vma_chain_alloc(GFP_KERNEL); if (!avc) goto out_error_free_anon_vma; @@ -361,7 +363,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) vma->anon_vma = anon_vma; anon_vma_lock_write(anon_vma); anon_vma_chain_link(vma, avc, anon_vma); - anon_vma->parent->degree++; + anon_vma->parent->num_children++; anon_vma_unlock_write(anon_vma); return 0; @@ -393,7 +395,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * to free them outside the lock. */ if (RB_EMPTY_ROOT(&anon_vma->rb_root.rb_root)) { - anon_vma->parent->degree--; + anon_vma->parent->num_children--; continue; } @@ -401,7 +403,7 @@ void unlink_anon_vmas(struct vm_area_struct *vma) anon_vma_chain_free(avc); } if (vma->anon_vma) - vma->anon_vma->degree--; + vma->anon_vma->num_active_vmas--; unlock_anon_vma_root(root); /* @@ -412,7 +414,8 @@ void unlink_anon_vmas(struct vm_area_struct *vma) list_for_each_entry_safe(avc, next, &vma->anon_vma_chain, same_vma) { struct anon_vma *anon_vma = avc->anon_vma; - VM_WARN_ON(anon_vma->degree); + VM_WARN_ON(anon_vma->num_children); + VM_WARN_ON(anon_vma->num_active_vmas); put_anon_vma(anon_vma); list_del(&avc->same_vma); @@ -1594,7 +1597,30 @@ static bool try_to_unmap_one(struct page *page, struct vm_area_struct *vma, /* MADV_FREE page check */ if (!PageSwapBacked(page)) { - if (!PageDirty(page)) { + int ref_count, map_count; + + /* + * Synchronize with gup_pte_range(): + * - clear PTE; barrier; read refcount + * - inc refcount; barrier; read PTE + */ + smp_mb(); + + ref_count = page_ref_count(page); + map_count = page_mapcount(page); + + /* + * Order reads for page refcount and dirty flag + * (see comments in __remove_mapping()). + */ + smp_rmb(); + + /* + * The only page refs must be one from isolation + * plus the rmap(s) (dropped by discard:). + */ + if (ref_count == 1 + map_count && + !PageDirty(page)) { /* Invalidate as we cleared the pte */ mmu_notifier_invalidate_range(mm, address, address + PAGE_SIZE); diff --git a/mm/shmem.c b/mm/shmem.c index 9fd0e72757cf..0788616696dc 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -451,7 +451,7 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, struct shmem_inode_info *info; struct page *page; unsigned long batch = sc ? sc->nr_to_scan : 128; - int removed = 0, split = 0; + int split = 0; if (list_empty(&sbinfo->shrinklist)) return SHRINK_STOP; @@ -466,7 +466,6 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, /* inode is about to be evicted */ if (!inode) { list_del_init(&info->shrinklist); - removed++; goto next; } @@ -474,12 +473,12 @@ static unsigned long shmem_unused_huge_shrink(struct shmem_sb_info *sbinfo, if (round_up(inode->i_size, PAGE_SIZE) == round_up(inode->i_size, HPAGE_PMD_SIZE)) { list_move(&info->shrinklist, &to_remove); - removed++; goto next; } list_move(&info->shrinklist, &list); next: + sbinfo->shrinklist_len--; if (!--batch) break; } @@ -499,7 +498,7 @@ next: inode = &info->vfs_inode; if (nr_to_split && split >= nr_to_split) - goto leave; + goto move_back; page = find_get_page(inode->i_mapping, (inode->i_size & HPAGE_PMD_MASK) >> PAGE_SHIFT); @@ -513,38 +512,44 @@ next: } /* - * Leave the inode on the list if we failed to lock - * the page at this time. + * Move the inode on the list back to shrinklist if we failed + * to lock the page at this time. * * Waiting for the lock may lead to deadlock in the * reclaim path. */ if (!trylock_page(page)) { put_page(page); - goto leave; + goto move_back; } ret = split_huge_page(page); unlock_page(page); put_page(page); - /* If split failed leave the inode on the list */ + /* If split failed move the inode on the list back to shrinklist */ if (ret) - goto leave; + goto move_back; split++; drop: list_del_init(&info->shrinklist); - removed++; -leave: + goto put; +move_back: + /* + * Make sure the inode is either on the global list or deleted + * from any local list before iput() since it could be deleted + * in another thread once we put the inode (then the local list + * is corrupted). + */ + spin_lock(&sbinfo->shrinklist_lock); + list_move(&info->shrinklist, &sbinfo->shrinklist); + sbinfo->shrinklist_len++; + spin_unlock(&sbinfo->shrinklist_lock); +put: iput(inode); } - spin_lock(&sbinfo->shrinklist_lock); - list_splice_tail(&list, &sbinfo->shrinklist); - sbinfo->shrinklist_len -= removed; - spin_unlock(&sbinfo->shrinklist_lock); - return split; } diff --git a/mm/slub.c b/mm/slub.c index 499fb073d1ff..edf766f1de63 100644 --- a/mm/slub.c +++ b/mm/slub.c @@ -1179,7 +1179,7 @@ static noinline int free_debug_processing( struct kmem_cache_node *n = get_node(s, page_to_nid(page)); void *object = head; int cnt = 0; - unsigned long uninitialized_var(flags); + unsigned long flags; int ret = 0; spin_lock_irqsave(&n->list_lock, flags); @@ -2162,6 +2162,7 @@ redo: c->page = NULL; c->freelist = NULL; + c->tid = next_tid(c->tid); } /* @@ -2295,8 +2296,6 @@ static inline void flush_slab(struct kmem_cache *s, struct kmem_cache_cpu *c) { stat(s, CPUSLAB_FLUSH); deactivate_slab(s, c->page, c->freelist, c); - - c->tid = next_tid(c->tid); } /* @@ -2583,6 +2582,7 @@ redo: if (!freelist) { c->page = NULL; + c->tid = next_tid(c->tid); stat(s, DEACTIVATE_BYPASS); goto new_slab; } @@ -2826,7 +2826,7 @@ static void __slab_free(struct kmem_cache *s, struct page *page, struct page new; unsigned long counters; struct kmem_cache_node *n = NULL; - unsigned long uninitialized_var(flags); + unsigned long flags; stat(s, FREE_SLOWPATH); @@ -5688,7 +5688,8 @@ static char *create_unique_id(struct kmem_cache *s) char *name = kmalloc(ID_STR_LENGTH, GFP_KERNEL); char *p = name; - BUG_ON(!name); + if (!name) + return ERR_PTR(-ENOMEM); *p++ = ':'; /* @@ -5770,6 +5771,8 @@ static int sysfs_slab_add(struct kmem_cache *s) * for the symlinks. */ name = create_unique_id(s); + if (IS_ERR(name)) + return PTR_ERR(name); } s->kobj.kset = kset; diff --git a/mm/swap.c b/mm/swap.c index 45fdbfb6b2a6..ce13e428380e 100644 --- a/mm/swap.c +++ b/mm/swap.c @@ -721,8 +721,8 @@ void release_pages(struct page **pages, int nr) LIST_HEAD(pages_to_free); struct pglist_data *locked_pgdat = NULL; struct lruvec *lruvec; - unsigned long uninitialized_var(flags); - unsigned int uninitialized_var(lock_batch); + unsigned long flags; + unsigned int lock_batch; for (i = 0; i < nr; i++) { struct page *page = pages[i]; diff --git a/mm/swapfile.c b/mm/swapfile.c index 057e6907bf7b..a4a80b9765b7 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -620,6 +620,7 @@ static void __del_from_avail_list(struct swap_info_struct *p) { int nid; + assert_spin_locked(&p->lock); for_each_node(nid) plist_del(&p->avail_lists[nid], &swap_avail_heads[nid]); } @@ -1008,6 +1009,7 @@ start_over: goto check_out; pr_debug("scan_swap_map of si %d failed to find offset\n", si->type); + cond_resched(); spin_lock(&swap_avail_lock); nextsi: @@ -2574,8 +2576,8 @@ SYSCALL_DEFINE1(swapoff, const char __user *, specialfile) spin_unlock(&swap_lock); goto out_dput; } - del_from_avail_list(p); spin_lock(&p->lock); + del_from_avail_list(p); if (p->prio < 0) { struct swap_info_struct *si = p; int nid; diff --git a/mm/usercopy.c b/mm/usercopy.c index e81d11715d95..a65fbc628215 100644 --- a/mm/usercopy.c +++ b/mm/usercopy.c @@ -298,7 +298,10 @@ static bool enable_checks __initdata = true; static int __init parse_hardened_usercopy(char *str) { - return strtobool(str, &enable_checks); + if (strtobool(str, &enable_checks)) + pr_warn("Invalid option string for hardened_usercopy: '%s'\n", + str); + return 1; } __setup("hardened_usercopy=", parse_hardened_usercopy); diff --git a/mm/userfaultfd.c b/mm/userfaultfd.c index 93a12cc107c9..aae19c29bcfa 100644 --- a/mm/userfaultfd.c +++ b/mm/userfaultfd.c @@ -55,6 +55,8 @@ static int mcopy_atomic_pte(struct mm_struct *dst_mm, /* don't free the page */ goto out; } + + flush_dcache_page(page); } else { page = *pagep; *pagep = NULL; @@ -574,6 +576,7 @@ retry: err = -EFAULT; goto out; } + flush_dcache_page(page); goto retry; } else BUG_ON(page); diff --git a/mm/util.c b/mm/util.c index 621afcea2bfa..e63eeb95f0f0 100644 --- a/mm/util.c +++ b/mm/util.c @@ -14,6 +14,7 @@ #include <linux/hugetlb.h> #include <linux/vmalloc.h> #include <linux/userfaultfd_k.h> +#include <linux/random.h> #include <asm/sections.h> #include <linux/uaccess.h> @@ -286,6 +287,38 @@ int vma_is_stack_for_current(struct vm_area_struct *vma) return (vma->vm_start <= KSTK_ESP(t) && vma->vm_end >= KSTK_ESP(t)); } +/** + * randomize_page - Generate a random, page aligned address + * @start: The smallest acceptable address the caller will take. + * @range: The size of the area, starting at @start, within which the + * random address must fall. + * + * If @start + @range would overflow, @range is capped. + * + * NOTE: Historical use of randomize_range, which this replaces, presumed that + * @start was already page aligned. We now align it regardless. + * + * Return: A page aligned address within [start, start + range). On error, + * @start is returned. + */ +unsigned long randomize_page(unsigned long start, unsigned long range) +{ + if (!PAGE_ALIGNED(start)) { + range -= PAGE_ALIGN(start) - start; + start = PAGE_ALIGN(start); + } + + if (start > ULONG_MAX - range) + range = ULONG_MAX - start; + + range >>= PAGE_SHIFT; + + if (range == 0) + return start; + + return start + (get_random_long() % range << PAGE_SHIFT); +} + #if defined(CONFIG_MMU) && !defined(HAVE_ARCH_PICK_MMAP_LAYOUT) void arch_pick_mmap_layout(struct mm_struct *mm, struct rlimit *rlim_stack) { diff --git a/mm/zsmalloc.c b/mm/zsmalloc.c index 11e81b3ff0cf..4d71356ea66a 100644 --- a/mm/zsmalloc.c +++ b/mm/zsmalloc.c @@ -1812,11 +1812,40 @@ static enum fullness_group putback_zspage(struct size_class *class, */ static void lock_zspage(struct zspage *zspage) { - struct page *page = get_first_page(zspage); + struct page *curr_page, *page; - do { - lock_page(page); - } while ((page = get_next_page(page)) != NULL); + /* + * Pages we haven't locked yet can be migrated off the list while we're + * trying to lock them, so we need to be careful and only attempt to + * lock each page under migrate_read_lock(). Otherwise, the page we lock + * may no longer belong to the zspage. This means that we may wait for + * the wrong page to unlock, so we must take a reference to the page + * prior to waiting for it to unlock outside migrate_read_lock(). + */ + while (1) { + migrate_read_lock(zspage); + page = get_first_page(zspage); + if (trylock_page(page)) + break; + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + } + + curr_page = page; + while ((page = get_next_page(curr_page))) { + if (trylock_page(page)) { + curr_page = page; + } else { + get_page(page); + migrate_read_unlock(zspage); + wait_on_page_locked(page); + put_page(page); + migrate_read_lock(zspage); + } + } + migrate_read_unlock(zspage); } static struct dentry *zs_mount(struct file_system_type *fs_type, |