diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 2 | ||||
| -rw-r--r-- | mm/frontswap.c | 2 | ||||
| -rw-r--r-- | mm/huge_memory.c | 7 | ||||
| -rw-r--r-- | mm/hugetlb.c | 238 | ||||
| -rw-r--r-- | mm/memcontrol.c | 28 | ||||
| -rw-r--r-- | mm/memory.c | 19 | ||||
| -rw-r--r-- | mm/memory_hotplug.c | 90 | ||||
| -rw-r--r-- | mm/migrate.c | 25 | ||||
| -rw-r--r-- | mm/mmu_notifier.c | 79 | ||||
| -rw-r--r-- | mm/page_alloc.c | 8 | ||||
| -rw-r--r-- | mm/pagewalk.c | 70 | ||||
| -rw-r--r-- | mm/readahead.c | 2 | ||||
| -rw-r--r-- | mm/shmem.c | 45 | ||||
| -rw-r--r-- | mm/slab_common.c | 4 | ||||
| -rw-r--r-- | mm/swap_state.c | 18 | ||||
| -rw-r--r-- | mm/swapfile.c | 2 | ||||
| -rw-r--r-- | mm/truncate.c | 117 |
17 files changed, 516 insertions, 240 deletions
diff --git a/mm/Kconfig b/mm/Kconfig index e742d06285b7..f5e698e30d4a 100644 --- a/mm/Kconfig +++ b/mm/Kconfig @@ -173,7 +173,7 @@ config HAVE_BOOTMEM_INFO_NODE config MEMORY_HOTPLUG bool "Allow for memory hot-add" depends on SPARSEMEM || X86_64_ACPI_NUMA - depends on HOTPLUG && ARCH_ENABLE_MEMORY_HOTPLUG + depends on ARCH_ENABLE_MEMORY_HOTPLUG depends on (IA64 || X86 || PPC_BOOK3S_64 || SUPERH || S390) config MEMORY_HOTPLUG_SPARSE diff --git a/mm/frontswap.c b/mm/frontswap.c index 538367ef1372..1b24bdcb3197 100644 --- a/mm/frontswap.c +++ b/mm/frontswap.c @@ -319,7 +319,7 @@ void __frontswap_invalidate_area(unsigned type) return; frontswap_ops->invalidate_area(type); atomic_set(&sis->frontswap_pages, 0); - memset(sis->frontswap_map, 0, sis->max / sizeof(long)); + bitmap_zero(sis->frontswap_map, sis->max); } clear_bit(type, need_init); } diff --git a/mm/huge_memory.c b/mm/huge_memory.c index 03a89a2f464b..362c329b83fe 100644 --- a/mm/huge_memory.c +++ b/mm/huge_memory.c @@ -2325,7 +2325,12 @@ static void collapse_huge_page(struct mm_struct *mm, pte_unmap(pte); spin_lock(&mm->page_table_lock); BUG_ON(!pmd_none(*pmd)); - set_pmd_at(mm, address, pmd, _pmd); + /* + * We can only use set_pmd_at when establishing + * hugepmds and never for establishing regular pmds that + * points to regular pagetables. Use pmd_populate for that + */ + pmd_populate(mm, pmd, pmd_pgtable(_pmd)); spin_unlock(&mm->page_table_lock); anon_vma_unlock_write(vma->anon_vma); goto out; diff --git a/mm/hugetlb.c b/mm/hugetlb.c index f8feeeca6686..aed085ad11a8 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -690,6 +690,23 @@ int PageHuge(struct page *page) } EXPORT_SYMBOL_GPL(PageHuge); +pgoff_t __basepage_index(struct page *page) +{ + struct page *page_head = compound_head(page); + pgoff_t index = page_index(page_head); + unsigned long compound_idx; + + if (!PageHuge(page_head)) + return page_index(page); + + if (compound_order(page_head) >= MAX_ORDER) + compound_idx = page_to_pfn(page) - page_to_pfn(page_head); + else + compound_idx = page - page_head; + + return (index << compound_order(page_head)) + compound_idx; +} + static struct page *alloc_fresh_huge_page_node(struct hstate *h, int nid) { struct page *page; @@ -2839,7 +2856,7 @@ int hugetlb_fault(struct mm_struct *mm, struct vm_area_struct *vma, if (ptep) { entry = huge_ptep_get(ptep); if (unlikely(is_hugetlb_entry_migration(entry))) { - migration_entry_wait(mm, (pmd_t *)ptep, address); + migration_entry_wait_huge(mm, ptep); return 0; } else if (unlikely(is_hugetlb_entry_hwpoisoned(entry))) return VM_FAULT_HWPOISON_LARGE | @@ -2931,15 +2948,6 @@ out_mutex: return ret; } -/* Can be overriden by architectures */ -__attribute__((weak)) struct page * -follow_huge_pud(struct mm_struct *mm, unsigned long address, - pud_t *pud, int write) -{ - BUG(); - return NULL; -} - long follow_hugetlb_page(struct mm_struct *mm, struct vm_area_struct *vma, struct page **pages, struct vm_area_struct **vmas, unsigned long *position, unsigned long *nr_pages, @@ -3169,6 +3177,216 @@ void hugetlb_unreserve_pages(struct inode *inode, long offset, long freed) hugetlb_acct_memory(h, -(chg - freed)); } +#ifdef CONFIG_ARCH_WANT_HUGE_PMD_SHARE +static unsigned long page_table_shareable(struct vm_area_struct *svma, + struct vm_area_struct *vma, + unsigned long addr, pgoff_t idx) +{ + unsigned long saddr = ((idx - svma->vm_pgoff) << PAGE_SHIFT) + + svma->vm_start; + unsigned long sbase = saddr & PUD_MASK; + unsigned long s_end = sbase + PUD_SIZE; + + /* Allow segments to share if only one is marked locked */ + unsigned long vm_flags = vma->vm_flags & ~VM_LOCKED; + unsigned long svm_flags = svma->vm_flags & ~VM_LOCKED; + + /* + * match the virtual addresses, permission and the alignment of the + * page table page. + */ + if (pmd_index(addr) != pmd_index(saddr) || + vm_flags != svm_flags || + sbase < svma->vm_start || svma->vm_end < s_end) + return 0; + + return saddr; +} + +static int vma_shareable(struct vm_area_struct *vma, unsigned long addr) +{ + unsigned long base = addr & PUD_MASK; + unsigned long end = base + PUD_SIZE; + + /* + * check on proper vm_flags and page table alignment + */ + if (vma->vm_flags & VM_MAYSHARE && + vma->vm_start <= base && end <= vma->vm_end) + return 1; + return 0; +} + +/* + * Search for a shareable pmd page for hugetlb. In any case calls pmd_alloc() + * and returns the corresponding pte. While this is not necessary for the + * !shared pmd case because we can allocate the pmd later as well, it makes the + * code much cleaner. pmd allocation is essential for the shared case because + * pud has to be populated inside the same i_mmap_mutex section - otherwise + * racing tasks could either miss the sharing (see huge_pte_offset) or select a + * bad pmd for sharing. + */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + struct vm_area_struct *vma = find_vma(mm, addr); + struct address_space *mapping = vma->vm_file->f_mapping; + pgoff_t idx = ((addr - vma->vm_start) >> PAGE_SHIFT) + + vma->vm_pgoff; + struct vm_area_struct *svma; + unsigned long saddr; + pte_t *spte = NULL; + pte_t *pte; + + if (!vma_shareable(vma, addr)) + return (pte_t *)pmd_alloc(mm, pud, addr); + + mutex_lock(&mapping->i_mmap_mutex); + vma_interval_tree_foreach(svma, &mapping->i_mmap, idx, idx) { + if (svma == vma) + continue; + + saddr = page_table_shareable(svma, vma, addr, idx); + if (saddr) { + spte = huge_pte_offset(svma->vm_mm, saddr); + if (spte) { + get_page(virt_to_page(spte)); + break; + } + } + } + + if (!spte) + goto out; + + spin_lock(&mm->page_table_lock); + if (pud_none(*pud)) + pud_populate(mm, pud, + (pmd_t *)((unsigned long)spte & PAGE_MASK)); + else + put_page(virt_to_page(spte)); + spin_unlock(&mm->page_table_lock); +out: + pte = (pte_t *)pmd_alloc(mm, pud, addr); + mutex_unlock(&mapping->i_mmap_mutex); + return pte; +} + +/* + * unmap huge page backed by shared pte. + * + * Hugetlb pte page is ref counted at the time of mapping. If pte is shared + * indicated by page_count > 1, unmap is achieved by clearing pud and + * decrementing the ref count. If count == 1, the pte page is not shared. + * + * called with vma->vm_mm->page_table_lock held. + * + * returns: 1 successfully unmapped a shared pte page + * 0 the underlying pte page is not shared, or it is the last user + */ +int huge_pmd_unshare(struct mm_struct *mm, unsigned long *addr, pte_t *ptep) +{ + pgd_t *pgd = pgd_offset(mm, *addr); + pud_t *pud = pud_offset(pgd, *addr); + + BUG_ON(page_count(virt_to_page(ptep)) == 0); + if (page_count(virt_to_page(ptep)) == 1) + return 0; + + pud_clear(pud); + put_page(virt_to_page(ptep)); + *addr = ALIGN(*addr, HPAGE_SIZE * PTRS_PER_PTE) - HPAGE_SIZE; + return 1; +} +#define want_pmd_share() (1) +#else /* !CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ +pte_t *huge_pmd_share(struct mm_struct *mm, unsigned long addr, pud_t *pud) +{ + return NULL; +} +#define want_pmd_share() (0) +#endif /* CONFIG_ARCH_WANT_HUGE_PMD_SHARE */ + +#ifdef CONFIG_ARCH_WANT_GENERAL_HUGETLB +pte_t *huge_pte_alloc(struct mm_struct *mm, + unsigned long addr, unsigned long sz) +{ + pgd_t *pgd; + pud_t *pud; + pte_t *pte = NULL; + + pgd = pgd_offset(mm, addr); + pud = pud_alloc(mm, pgd, addr); + if (pud) { + if (sz == PUD_SIZE) { + pte = (pte_t *)pud; + } else { + BUG_ON(sz != PMD_SIZE); + if (want_pmd_share() && pud_none(*pud)) + pte = huge_pmd_share(mm, addr, pud); + else + pte = (pte_t *)pmd_alloc(mm, pud, addr); + } + } + BUG_ON(pte && !pte_none(*pte) && !pte_huge(*pte)); + + return pte; +} + +pte_t *huge_pte_offset(struct mm_struct *mm, unsigned long addr) +{ + pgd_t *pgd; + pud_t *pud; + pmd_t *pmd = NULL; + + pgd = pgd_offset(mm, addr); + if (pgd_present(*pgd)) { + pud = pud_offset(pgd, addr); + if (pud_present(*pud)) { + if (pud_huge(*pud)) + return (pte_t *)pud; + pmd = pmd_offset(pud, addr); + } + } + return (pte_t *) pmd; +} + +struct page * +follow_huge_pmd(struct mm_struct *mm, unsigned long address, + pmd_t *pmd, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pmd); + if (page) + page += ((address & ~PMD_MASK) >> PAGE_SHIFT); + return page; +} + +struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + struct page *page; + + page = pte_page(*(pte_t *)pud); + if (page) + page += ((address & ~PUD_MASK) >> PAGE_SHIFT); + return page; +} + +#else /* !CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + +/* Can be overriden by architectures */ +__attribute__((weak)) struct page * +follow_huge_pud(struct mm_struct *mm, unsigned long address, + pud_t *pud, int write) +{ + BUG(); + return NULL; +} + +#endif /* CONFIG_ARCH_WANT_GENERAL_HUGETLB */ + #ifdef CONFIG_MEMORY_FAILURE /* Should be called in hugetlb_lock */ diff --git a/mm/memcontrol.c b/mm/memcontrol.c index cb1c9dedf9b6..194721839cf5 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -1199,7 +1199,6 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, mz = mem_cgroup_zoneinfo(root, nid, zid); iter = &mz->reclaim_iter[reclaim->priority]; - last_visited = iter->last_visited; if (prev && reclaim->generation != iter->generation) { iter->last_visited = NULL; goto out_unlock; @@ -1218,13 +1217,12 @@ struct mem_cgroup *mem_cgroup_iter(struct mem_cgroup *root, * is alive. */ dead_count = atomic_read(&root->dead_count); - smp_rmb(); - last_visited = iter->last_visited; - if (last_visited) { - if ((dead_count != iter->last_dead_count) || - !css_tryget(&last_visited->css)) { + if (dead_count == iter->last_dead_count) { + smp_rmb(); + last_visited = iter->last_visited; + if (last_visited && + !css_tryget(&last_visited->css)) last_visited = NULL; - } } } @@ -3141,8 +3139,6 @@ int memcg_update_cache_size(struct kmem_cache *s, int num_groups) return -ENOMEM; } - INIT_WORK(&s->memcg_params->destroy, - kmem_cache_destroy_work_func); s->memcg_params->is_root_cache = true; /* @@ -4108,8 +4104,6 @@ __mem_cgroup_uncharge_common(struct page *page, enum charge_type ctype, if (mem_cgroup_disabled()) return NULL; - VM_BUG_ON(PageSwapCache(page)); - if (PageTransHuge(page)) { nr_pages <<= compound_order(page); VM_BUG_ON(!PageTransHuge(page)); @@ -4205,6 +4199,18 @@ void mem_cgroup_uncharge_page(struct page *page) if (page_mapped(page)) return; VM_BUG_ON(page->mapping && !PageAnon(page)); + /* + * If the page is in swap cache, uncharge should be deferred + * to the swap path, which also properly accounts swap usage + * and handles memcg lifetime. + * + * Note that this check is not stable and reclaim may add the + * page to swap cache at any time after this. However, if the + * page is not in swap cache by the time page->mapcount hits + * 0, there won't be any page table references to the swap + * slot, and reclaim will free it and not actually write the + * page to disk. + */ if (PageSwapCache(page)) return; __mem_cgroup_uncharge_common(page, MEM_CGROUP_CHARGE_TYPE_ANON, false); diff --git a/mm/memory.c b/mm/memory.c index 6dc1882fbd72..95d0cce63583 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -220,7 +220,6 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, bool fullmm) tlb->start = -1UL; tlb->end = 0; tlb->need_flush = 0; - tlb->fast_mode = (num_possible_cpus() == 1); tlb->local.next = NULL; tlb->local.nr = 0; tlb->local.max = ARRAY_SIZE(tlb->__pages); @@ -244,9 +243,6 @@ void tlb_flush_mmu(struct mmu_gather *tlb) tlb_table_flush(tlb); #endif - if (tlb_fast_mode(tlb)) - return; - for (batch = &tlb->local; batch; batch = batch->next) { free_pages_and_swap_cache(batch->pages, batch->nr); batch->nr = 0; @@ -288,11 +284,6 @@ int __tlb_remove_page(struct mmu_gather *tlb, struct page *page) VM_BUG_ON(!tlb->need_flush); - if (tlb_fast_mode(tlb)) { - free_page_and_swap_cache(page); - return 1; /* avoid calling tlb_flush_mmu() */ - } - batch = tlb->active; batch->pages[batch->nr++] = page; if (batch->nr == batch->max) { @@ -4210,7 +4201,7 @@ void print_vma_addr(char *prefix, unsigned long ip) up_read(&mm->mmap_sem); } -#ifdef CONFIG_PROVE_LOCKING +#if defined(CONFIG_PROVE_LOCKING) || defined(CONFIG_DEBUG_ATOMIC_SLEEP) void might_fault(void) { /* @@ -4222,13 +4213,17 @@ void might_fault(void) if (segment_eq(get_fs(), KERNEL_DS)) return; - might_sleep(); /* * it would be nicer only to annotate paths which are not under * pagefault_disable, however that requires a larger audit and * providing helpers like get_user_atomic. */ - if (!in_atomic() && current->mm) + if (in_atomic()) + return; + + __might_sleep(__FILE__, __LINE__, 0); + + if (current->mm) might_lock_read(¤t->mm->mmap_sem); } EXPORT_SYMBOL(might_fault); diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c index a221fac1f47d..081b4d654ed6 100644 --- a/mm/memory_hotplug.c +++ b/mm/memory_hotplug.c @@ -720,9 +720,12 @@ int __remove_pages(struct zone *zone, unsigned long phys_start_pfn, start = phys_start_pfn << PAGE_SHIFT; size = nr_pages * PAGE_SIZE; ret = release_mem_region_adjustable(&iomem_resource, start, size); - if (ret) - pr_warn("Unable to release resource <%016llx-%016llx> (%d)\n", - start, start + size - 1, ret); + if (ret) { + resource_size_t endres = start + size - 1; + + pr_warn("Unable to release resource <%pa-%pa> (%d)\n", + &start, &endres, ret); + } sections_to_remove = nr_pages / PAGES_PER_SECTION; for (i = 0; i < sections_to_remove; i++) { @@ -1618,6 +1621,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) { return __offline_pages(start_pfn, start_pfn + nr_pages, 120 * HZ); } +#endif /* CONFIG_MEMORY_HOTREMOVE */ /** * walk_memory_range - walks through all mem sections in [start_pfn, end_pfn) @@ -1631,7 +1635,7 @@ int offline_pages(unsigned long start_pfn, unsigned long nr_pages) * * Returns the return value of func. */ -static int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, +int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, void *arg, int (*func)(struct memory_block *, void *)) { struct memory_block *mem = NULL; @@ -1668,24 +1672,7 @@ static int walk_memory_range(unsigned long start_pfn, unsigned long end_pfn, return 0; } -/** - * offline_memory_block_cb - callback function for offlining memory block - * @mem: the memory block to be offlined - * @arg: buffer to hold error msg - * - * Always return 0, and put the error msg in arg if any. - */ -static int offline_memory_block_cb(struct memory_block *mem, void *arg) -{ - int *ret = arg; - int error = offline_memory_block(mem); - - if (error != 0 && *ret == 0) - *ret = error; - - return 0; -} - +#ifdef CONFIG_MEMORY_HOTREMOVE static int is_memblock_offlined_cb(struct memory_block *mem, void *arg) { int ret = !is_memblock_offlined(mem); @@ -1811,54 +1798,22 @@ void try_offline_node(int nid) } EXPORT_SYMBOL(try_offline_node); -int __ref remove_memory(int nid, u64 start, u64 size) +void __ref remove_memory(int nid, u64 start, u64 size) { - unsigned long start_pfn, end_pfn; - int ret = 0; - int retry = 1; - - start_pfn = PFN_DOWN(start); - end_pfn = PFN_UP(start + size - 1); - - /* - * When CONFIG_MEMCG is on, one memory block may be used by other - * blocks to store page cgroup when onlining pages. But we don't know - * in what order pages are onlined. So we iterate twice to offline - * memory: - * 1st iterate: offline every non primary memory block. - * 2nd iterate: offline primary (i.e. first added) memory block. - */ -repeat: - walk_memory_range(start_pfn, end_pfn, &ret, - offline_memory_block_cb); - if (ret) { - if (!retry) - return ret; - - retry = 0; - ret = 0; - goto repeat; - } + int ret; lock_memory_hotplug(); /* - * we have offlined all memory blocks like this: - * 1. lock memory hotplug - * 2. offline a memory block - * 3. unlock memory hotplug - * - * repeat step1-3 to offline the memory block. All memory blocks - * must be offlined before removing memory. But we don't hold the - * lock in the whole operation. So we should check whether all - * memory blocks are offlined. + * All memory blocks must be offlined before removing memory. Check + * whether all memory blocks in question are offline and trigger a BUG() + * if this is not the case. */ - - ret = walk_memory_range(start_pfn, end_pfn, NULL, + ret = walk_memory_range(PFN_DOWN(start), PFN_UP(start + size - 1), NULL, is_memblock_offlined_cb); if (ret) { unlock_memory_hotplug(); - return ret; + BUG(); } /* remove memmap entry */ @@ -1869,17 +1824,6 @@ repeat: try_offline_node(nid); unlock_memory_hotplug(); - - return 0; -} -#else -int offline_pages(unsigned long start_pfn, unsigned long nr_pages) -{ - return -EINVAL; } -int remove_memory(int nid, u64 start, u64 size) -{ - return -EINVAL; -} -#endif /* CONFIG_MEMORY_HOTREMOVE */ EXPORT_SYMBOL_GPL(remove_memory); +#endif /* CONFIG_MEMORY_HOTREMOVE */ diff --git a/mm/migrate.c b/mm/migrate.c index 27ed22579fd9..6f0c24438bba 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -165,7 +165,7 @@ static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, pte = arch_make_huge_pte(pte, vma, new, 0); } #endif - flush_cache_page(vma, addr, pte_pfn(pte)); + flush_dcache_page(new); set_pte_at(mm, addr, ptep, pte); if (PageHuge(new)) { @@ -200,15 +200,14 @@ static void remove_migration_ptes(struct page *old, struct page *new) * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. */ -void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) +static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { - pte_t *ptep, pte; - spinlock_t *ptl; + pte_t pte; swp_entry_t entry; struct page *page; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + spin_lock(ptl); pte = *ptep; if (!is_swap_pte(pte)) goto out; @@ -236,6 +235,20 @@ out: pte_unmap_unlock(ptep, ptl); } +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl = pte_lockptr(mm, pmd); + pte_t *ptep = pte_offset_map(pmd, address); + __migration_entry_wait(mm, ptep, ptl); +} + +void migration_entry_wait_huge(struct mm_struct *mm, pte_t *pte) +{ + spinlock_t *ptl = &(mm)->page_table_lock; + __migration_entry_wait(mm, pte, ptl); +} + #ifdef CONFIG_BLOCK /* Returns true if all buffers are successfully locked */ static bool buffer_migrate_lock_buffers(struct buffer_head *head, diff --git a/mm/mmu_notifier.c b/mm/mmu_notifier.c index be04122fb277..6725ff183374 100644 --- a/mm/mmu_notifier.c +++ b/mm/mmu_notifier.c @@ -40,48 +40,44 @@ void __mmu_notifier_release(struct mm_struct *mm) int id; /* - * srcu_read_lock() here will block synchronize_srcu() in - * mmu_notifier_unregister() until all registered - * ->release() callouts this function makes have - * returned. + * SRCU here will block mmu_notifier_unregister until + * ->release returns. */ id = srcu_read_lock(&srcu); + hlist_for_each_entry_rcu(mn, &mm->mmu_notifier_mm->list, hlist) + /* + * If ->release runs before mmu_notifier_unregister it must be + * handled, as it's the only way for the driver to flush all + * existing sptes and stop the driver from establishing any more + * sptes before all the pages in the mm are freed. + */ + if (mn->ops->release) + mn->ops->release(mn, mm); + srcu_read_unlock(&srcu, id); + spin_lock(&mm->mmu_notifier_mm->lock); while (unlikely(!hlist_empty(&mm->mmu_notifier_mm->list))) { mn = hlist_entry(mm->mmu_notifier_mm->list.first, struct mmu_notifier, hlist); - /* - * Unlink. This will prevent mmu_notifier_unregister() - * from also making the ->release() callout. + * We arrived before mmu_notifier_unregister so + * mmu_notifier_unregister will do nothing other than to wait + * for ->release to finish and for mmu_notifier_unregister to + * return. */ hlist_del_init_rcu(&mn->hlist); - spin_unlock(&mm->mmu_notifier_mm->lock); - - /* - * Clear sptes. (see 'release' description in mmu_notifier.h) - */ - if (mn->ops->release) - mn->ops->release(mn, mm); - - spin_lock(&mm->mmu_notifier_mm->lock); } spin_unlock(&mm->mmu_notifier_mm->lock); /* - * All callouts to ->release() which we have done are complete. - * Allow synchronize_srcu() in mmu_notifier_unregister() to complete - */ - srcu_read_unlock(&srcu, id); - - /* - * mmu_notifier_unregister() may have unlinked a notifier and may - * still be calling out to it. Additionally, other notifiers - * may have been active via vmtruncate() et. al. Block here - * to ensure that all notifier callouts for this mm have been - * completed and the sptes are really cleaned up before returning - * to exit_mmap(). + * synchronize_srcu here prevents mmu_notifier_release from returning to + * exit_mmap (which would proceed with freeing all pages in the mm) + * until the ->release method returns, if it was invoked by + * mmu_notifier_unregister. + * + * The mmu_notifier_mm can't go away from under us because one mm_count + * is held by exit_mmap. */ synchronize_srcu(&srcu); } @@ -292,31 +288,34 @@ void mmu_notifier_unregister(struct mmu_notifier *mn, struct mm_struct *mm) { BUG_ON(atomic_read(&mm->mm_count) <= 0); - spin_lock(&mm->mmu_notifier_mm->lock); if (!hlist_unhashed(&mn->hlist)) { + /* + * SRCU here will force exit_mmap to wait for ->release to + * finish before freeing the pages. + */ int id; + id = srcu_read_lock(&srcu); /* - * Ensure we synchronize up with __mmu_notifier_release(). + * exit_mmap will block in mmu_notifier_release to guarantee + * that ->release is called before freeing the pages. */ - id = srcu_read_lock(&srcu); - - hlist_del_rcu(&mn->hlist); - spin_unlock(&mm->mmu_notifier_mm->lock); - if (mn->ops->release) mn->ops->release(mn, mm); + srcu_read_unlock(&srcu, id); + spin_lock(&mm->mmu_notifier_mm->lock); /* - * Allow __mmu_notifier_release() to complete. + * Can not use list_del_rcu() since __mmu_notifier_release + * can delete it before we hold the lock. */ - srcu_read_unlock(&srcu, id); - } else + hlist_del_init_rcu(&mn->hlist); spin_unlock(&mm->mmu_notifier_mm->lock); + } /* - * Wait for any running method to finish, including ->release() if it - * was run by __mmu_notifier_release() instead of us. + * Wait for any running method to finish, of course including + * ->release if it was run by mmu_notifier_relase instead of us. */ synchronize_srcu(&srcu); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 98cbdf6e5532..c3edb624fccf 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -1628,6 +1628,7 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, long min = mark; long lowmem_reserve = z->lowmem_reserve[classzone_idx]; int o; + long free_cma = 0; free_pages -= (1 << order) - 1; if (alloc_flags & ALLOC_HIGH) @@ -1637,9 +1638,10 @@ static bool __zone_watermark_ok(struct zone *z, int order, unsigned long mark, #ifdef CONFIG_CMA /* If allocation can't use CMA areas don't use free CMA pages */ if (!(alloc_flags & ALLOC_CMA)) - free_pages -= zone_page_state(z, NR_FREE_CMA_PAGES); + free_cma = zone_page_state(z, NR_FREE_CMA_PAGES); #endif - if (free_pages <= min + lowmem_reserve) + + if (free_pages - free_cma <= min + lowmem_reserve) return false; for (o = 0; o < order; o++) { /* At the next order, this order's pages become unavailable */ @@ -5158,7 +5160,7 @@ unsigned long free_reserved_area(unsigned long start, unsigned long end, for (pages = 0; pos < end; pos += PAGE_SIZE, pages++) { if (poison) memset((void *)pos, poison, PAGE_SIZE); - free_reserved_page(virt_to_page(pos)); + free_reserved_page(virt_to_page((void *)pos)); } if (pages && s) diff --git a/mm/pagewalk.c b/mm/pagewalk.c index 35aa294656cd..5da2cbcfdbb5 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -127,28 +127,7 @@ static int walk_hugetlb_range(struct vm_area_struct *vma, return 0; } -static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk) -{ - struct vm_area_struct *vma; - - /* We don't need vma lookup at all. */ - if (!walk->hugetlb_entry) - return NULL; - - VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); - vma = find_vma(walk->mm, addr); - if (vma && vma->vm_start <= addr && is_vm_hugetlb_page(vma)) - return vma; - - return NULL; -} - #else /* CONFIG_HUGETLB_PAGE */ -static struct vm_area_struct* hugetlb_vma(unsigned long addr, struct mm_walk *walk) -{ - return NULL; -} - static int walk_hugetlb_range(struct vm_area_struct *vma, unsigned long addr, unsigned long end, struct mm_walk *walk) @@ -198,30 +177,53 @@ int walk_page_range(unsigned long addr, unsigned long end, if (!walk->mm) return -EINVAL; + VM_BUG_ON(!rwsem_is_locked(&walk->mm->mmap_sem)); + pgd = pgd_offset(walk->mm, addr); do { - struct vm_area_struct *vma; + struct vm_area_struct *vma = NULL; next = pgd_addr_end(addr, end); /* - * handle hugetlb vma individually because pagetable walk for - * the hugetlb page is dependent on the architecture and - * we can't handled it in the same manner as non-huge pages. + * This function was not intended to be vma based. + * But there are vma special cases to be handled: + * - hugetlb vma's + * - VM_PFNMAP vma's */ - vma = hugetlb_vma(addr, walk); + vma = find_vma(walk->mm, addr); if (vma) { - if (vma->vm_end < next) + /* + * There are no page structures backing a VM_PFNMAP + * range, so do not allow split_huge_page_pmd(). + */ + if ((vma->vm_start <= addr) && + (vma->vm_flags & VM_PFNMAP)) { next = vma->vm_end; + pgd = pgd_offset(walk->mm, next); + continue; + } /* - * Hugepage is very tightly coupled with vma, so - * walk through hugetlb entries within a given vma. + * Handle hugetlb vma individually because pagetable + * walk for the hugetlb page is dependent on the + * architecture and we can't handled it in the same + * manner as non-huge pages. */ - err = walk_hugetlb_range(vma, addr, next, walk); - if (err) - break; - pgd = pgd_offset(walk->mm, next); - continue; + if (walk->hugetlb_entry && (vma->vm_start <= addr) && + is_vm_hugetlb_page(vma)) { + if (vma->vm_end < next) + next = vma->vm_end; + /* + * Hugepage is very tightly coupled with vma, + * so walk through hugetlb entries within a + * given vma. + */ + err = walk_hugetlb_range(vma, addr, next, walk); + if (err) + break; + pgd = pgd_offset(walk->mm, next); + continue; + } } if (pgd_none_or_clear_bad(pgd)) { diff --git a/mm/readahead.c b/mm/readahead.c index daed28dd5830..829a77c62834 100644 --- a/mm/readahead.c +++ b/mm/readahead.c @@ -48,7 +48,7 @@ static void read_cache_pages_invalidate_page(struct address_space *mapping, if (!trylock_page(page)) BUG(); page->mapping = mapping; - do_invalidatepage(page, 0); + do_invalidatepage(page, 0, PAGE_CACHE_SIZE); page->mapping = NULL; unlock_page(page); } diff --git a/mm/shmem.c b/mm/shmem.c index 5e6a8422658b..a87990cf9f94 100644 --- a/mm/shmem.c +++ b/mm/shmem.c @@ -1798,10 +1798,7 @@ static loff_t shmem_file_llseek(struct file *file, loff_t offset, int whence) } } - if (offset >= 0 && offset != file->f_pos) { - file->f_pos = offset; - file->f_version = 0; - } + offset = vfs_setpos(file, offset, MAX_LFS_FILESIZE); mutex_unlock(&inode->i_mutex); return offset; } @@ -1939,6 +1936,13 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) inode = shmem_get_inode(dir->i_sb, dir, mode, dev, VM_NORESERVE); if (inode) { +#ifdef CONFIG_TMPFS_POSIX_ACL + error = generic_acl_init(inode, dir); + if (error) { + iput(inode); + return error; + } +#endif error = security_inode_init_security(inode, dir, &dentry->d_name, shmem_initxattrs, NULL); @@ -1948,6 +1952,33 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) return error; } } + + error = 0; + dir->i_size += BOGO_DIRENT_SIZE; + dir->i_ctime = dir->i_mtime = CURRENT_TIME; + d_instantiate(dentry, inode); + dget(dentry); /* Extra count - pin the dentry in core */ + } + return error; +} + +static int +shmem_tmpfile(struct inode *dir, struct dentry *dentry, umode_t mode) +{ + struct inode *inode; + int error = -ENOSPC; + + inode = shmem_get_inode(dir->i_sb, dir, mode, 0, VM_NORESERVE); + if (inode) { + error = security_inode_init_security(inode, dir, + NULL, + shmem_initxattrs, NULL); + if (error) { + if (error != -EOPNOTSUPP) { + iput(inode); + return error; + } + } #ifdef CONFIG_TMPFS_POSIX_ACL error = generic_acl_init(inode, dir); if (error) { @@ -1957,10 +1988,7 @@ shmem_mknod(struct inode *dir, struct dentry *dentry, umode_t mode, dev_t dev) #else error = 0; #endif - dir->i_size += BOGO_DIRENT_SIZE; - dir->i_ctime = dir->i_mtime = CURRENT_TIME; - d_instantiate(dentry, inode); - dget(dentry); /* Extra count - pin the dentry in core */ + d_tmpfile(dentry, inode); } return error; } @@ -2723,6 +2751,7 @@ static const struct inode_operations shmem_dir_inode_operations = { .rmdir = shmem_rmdir, .mknod = shmem_mknod, .rename = shmem_rename, + .tmpfile = shmem_tmpfile, #endif #ifdef CONFIG_TMPFS_XATTR .setxattr = shmem_setxattr, diff --git a/mm/slab_common.c b/mm/slab_common.c index ff3218a0f5e1..2d414508e9ec 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -373,8 +373,10 @@ struct kmem_cache *kmalloc_slab(size_t size, gfp_t flags) { int index; - if (WARN_ON_ONCE(size > KMALLOC_MAX_SIZE)) + if (size > KMALLOC_MAX_SIZE) { + WARN_ON_ONCE(!(flags & __GFP_NOWARN)); return NULL; + } if (size <= 192) { if (!size) diff --git a/mm/swap_state.c b/mm/swap_state.c index b3d40dcf3624..f24ab0dff554 100644 --- a/mm/swap_state.c +++ b/mm/swap_state.c @@ -336,8 +336,24 @@ struct page *read_swap_cache_async(swp_entry_t entry, gfp_t gfp_mask, * Swap entry may have been freed since our caller observed it. */ err = swapcache_prepare(entry); - if (err == -EEXIST) { /* seems racy */ + if (err == -EEXIST) { radix_tree_preload_end(); + /* + * We might race against get_swap_page() and stumble + * across a SWAP_HAS_CACHE swap_map entry whose page + * has not been brought into the swapcache yet, while + * the other end is scheduled away waiting on discard + * I/O completion at scan_swap_map(). + * + * In order to avoid turning this transitory state + * into a permanent loop around this -EEXIST case + * if !CONFIG_PREEMPT and the I/O completion happens + * to be waiting on the CPU waitqueue where we are now + * busy looping, we just conditionally invoke the + * scheduler here, if there are some more important + * tasks to run. + */ + cond_resched(); continue; } if (err) { /* swp entry is obsolete ? */ diff --git a/mm/swapfile.c b/mm/swapfile.c index 6c340d908b27..746af55b8455 100644 --- a/mm/swapfile.c +++ b/mm/swapfile.c @@ -2116,7 +2116,7 @@ SYSCALL_DEFINE2(swapon, const char __user *, specialfile, int, swap_flags) } /* frontswap enabled? set up bit-per-page map for frontswap */ if (frontswap_enabled) - frontswap_map = vzalloc(maxpages / sizeof(long)); + frontswap_map = vzalloc(BITS_TO_LONGS(maxpages) * sizeof(long)); if (p->bdev) { if (blk_queue_nonrot(bdev_get_queue(p->bdev))) { diff --git a/mm/truncate.c b/mm/truncate.c index c75b736e54b7..e2e8a8a7eb9d 100644 --- a/mm/truncate.c +++ b/mm/truncate.c @@ -26,7 +26,8 @@ /** * do_invalidatepage - invalidate part or all of a page * @page: the page which is affected - * @offset: the index of the truncation point + * @offset: start of the range to invalidate + * @length: length of the range to invalidate * * do_invalidatepage() is called when all or part of the page has become * invalidated by a truncate operation. @@ -37,24 +38,18 @@ * point. Because the caller is about to free (and possibly reuse) those * blocks on-disk. */ -void do_invalidatepage(struct page *page, unsigned long offset) +void do_invalidatepage(struct page *page, unsigned int offset, + unsigned int length) { - void (*invalidatepage)(struct page *, unsigned long); + void (*invalidatepage)(struct page *, unsigned int, unsigned int); + invalidatepage = page->mapping->a_ops->invalidatepage; #ifdef CONFIG_BLOCK if (!invalidatepage) invalidatepage = block_invalidatepage; #endif if (invalidatepage) - (*invalidatepage)(page, offset); -} - -static inline void truncate_partial_page(struct page *page, unsigned partial) -{ - zero_user_segment(page, partial, PAGE_CACHE_SIZE); - cleancache_invalidate_page(page->mapping, page); - if (page_has_private(page)) - do_invalidatepage(page, partial); + (*invalidatepage)(page, offset, length); } /* @@ -103,7 +98,7 @@ truncate_complete_page(struct address_space *mapping, struct page *page) return -EIO; if (page_has_private(page)) - do_invalidatepage(page, 0); + do_invalidatepage(page, 0, PAGE_CACHE_SIZE); cancel_dirty_page(page, PAGE_CACHE_SIZE); @@ -185,11 +180,11 @@ int invalidate_inode_page(struct page *page) * truncate_inode_pages_range - truncate range of pages specified by start & end byte offsets * @mapping: mapping to truncate * @lstart: offset from which to truncate - * @lend: offset to which to truncate + * @lend: offset to which to truncate (inclusive) * * Truncate the page cache, removing the pages that are between - * specified offsets (and zeroing out partial page - * (if lstart is not page aligned)). + * specified offsets (and zeroing out partial pages + * if lstart or lend + 1 is not page aligned). * * Truncate takes two passes - the first pass is nonblocking. It will not * block on page locks and it will not block on writeback. The second pass @@ -200,35 +195,58 @@ int invalidate_inode_page(struct page *page) * We pass down the cache-hot hint to the page freeing code. Even if the * mapping is large, it is probably the case that the final pages are the most * recently touched, and freeing happens in ascending file offset order. + * + * Note that since ->invalidatepage() accepts range to invalidate + * truncate_inode_pages_range is able to handle cases where lend + 1 is not + * page aligned properly. */ void truncate_inode_pages_range(struct address_space *mapping, loff_t lstart, loff_t lend) { - const pgoff_t start = (lstart + PAGE_CACHE_SIZE-1) >> PAGE_CACHE_SHIFT; - const unsigned partial = lstart & (PAGE_CACHE_SIZE - 1); - struct pagevec pvec; - pgoff_t index; - pgoff_t end; - int i; + pgoff_t start; /* inclusive */ + pgoff_t end; /* exclusive */ + unsigned int partial_start; /* inclusive */ + unsigned int partial_end; /* exclusive */ + struct pagevec pvec; + pgoff_t index; + int i; cleancache_invalidate_inode(mapping); if (mapping->nrpages == 0) return; - BUG_ON((lend & (PAGE_CACHE_SIZE - 1)) != (PAGE_CACHE_SIZE - 1)); - end = (lend >> PAGE_CACHE_SHIFT); + /* Offsets within partial pages */ + partial_start = lstart & (PAGE_CACHE_SIZE - 1); + partial_end = (lend + 1) & (PAGE_CACHE_SIZE - 1); + + /* + * 'start' and 'end' always covers the range of pages to be fully + * truncated. Partial pages are covered with 'partial_start' at the + * start of the range and 'partial_end' at the end of the range. + * Note that 'end' is exclusive while 'lend' is inclusive. + */ + start = (lstart + PAGE_CACHE_SIZE - 1) >> PAGE_CACHE_SHIFT; + if (lend == -1) + /* + * lend == -1 indicates end-of-file so we have to set 'end' + * to the highest possible pgoff_t and since the type is + * unsigned we're using -1. + */ + end = -1; + else + end = (lend + 1) >> PAGE_CACHE_SHIFT; pagevec_init(&pvec, 0); index = start; - while (index <= end && pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + while (index < end && pagevec_lookup(&pvec, mapping, index, + min(end - index, (pgoff_t)PAGEVEC_SIZE))) { mem_cgroup_uncharge_start(); for (i = 0; i < pagevec_count(&pvec); i++) { struct page *page = pvec.pages[i]; /* We rely upon deletion not changing page->index */ index = page->index; - if (index > end) + if (index >= end) break; if (!trylock_page(page)) @@ -247,27 +265,56 @@ void truncate_inode_pages_range(struct address_space *mapping, index++; } - if (partial) { + if (partial_start) { struct page *page = find_lock_page(mapping, start - 1); if (page) { + unsigned int top = PAGE_CACHE_SIZE; + if (start > end) { + /* Truncation within a single page */ + top = partial_end; + partial_end = 0; + } wait_on_page_writeback(page); - truncate_partial_page(page, partial); + zero_user_segment(page, partial_start, top); + cleancache_invalidate_page(mapping, page); + if (page_has_private(page)) + do_invalidatepage(page, partial_start, + top - partial_start); unlock_page(page); page_cache_release(page); } } + if (partial_end) { + struct page *page = find_lock_page(mapping, end); + if (page) { + wait_on_page_writeback(page); + zero_user_segment(page, 0, partial_end); + cleancache_invalidate_page(mapping, page); + if (page_has_private(page)) + do_invalidatepage(page, 0, + partial_end); + unlock_page(page); + page_cache_release(page); + } + } + /* + * If the truncation happened within a single page no pages + * will be released, just zeroed, so we can bail out now. + */ + if (start >= end) + return; index = start; for ( ; ; ) { cond_resched(); if (!pagevec_lookup(&pvec, mapping, index, - min(end - index, (pgoff_t)PAGEVEC_SIZE - 1) + 1)) { + min(end - index, (pgoff_t)PAGEVEC_SIZE))) { if (index == start) break; index = start; continue; } - if (index == start && pvec.pages[0]->index > end) { + if (index == start && pvec.pages[0]->index >= end) { pagevec_release(&pvec); break; } @@ -277,7 +324,7 @@ void truncate_inode_pages_range(struct address_space *mapping, /* We rely upon deletion not changing page->index */ index = page->index; - if (index > end) + if (index >= end) break; lock_page(page); @@ -598,10 +645,8 @@ void truncate_pagecache_range(struct inode *inode, loff_t lstart, loff_t lend) * This rounding is currently just for example: unmap_mapping_range * expands its hole outwards, whereas we want it to contract the hole * inwards. However, existing callers of truncate_pagecache_range are - * doing their own page rounding first; and truncate_inode_pages_range - * currently BUGs if lend is not pagealigned-1 (it handles partial - * page at start of hole, but not partial page at end of hole). Note - * unmap_mapping_range allows holelen 0 for all, and we allow lend -1. + * doing their own page rounding first. Note that unmap_mapping_range + * allows holelen 0 for all, and we allow lend -1 for end of file. */ /* |