diff options
Diffstat (limited to 'mm')
| -rw-r--r-- | mm/Kconfig | 1 | ||||
| -rw-r--r-- | mm/Kconfig.debug | 9 | ||||
| -rw-r--r-- | mm/Makefile | 2 | ||||
| -rw-r--r-- | mm/debug.c | 1 | ||||
| -rw-r--r-- | mm/filemap.c | 30 | ||||
| -rw-r--r-- | mm/filemap_xip.c | 1 | ||||
| -rw-r--r-- | mm/fremap.c | 283 | ||||
| -rw-r--r-- | mm/gup.c | 6 | ||||
| -rw-r--r-- | mm/hugetlb.c | 2 | ||||
| -rw-r--r-- | mm/interval_tree.c | 34 | ||||
| -rw-r--r-- | mm/ksm.c | 4 | ||||
| -rw-r--r-- | mm/madvise.c | 13 | ||||
| -rw-r--r-- | mm/memcontrol.c | 210 | ||||
| -rw-r--r-- | mm/memory.c | 299 | ||||
| -rw-r--r-- | mm/migrate.c | 32 | ||||
| -rw-r--r-- | mm/mincore.c | 9 | ||||
| -rw-r--r-- | mm/mmap.c | 106 | ||||
| -rw-r--r-- | mm/mprotect.c | 2 | ||||
| -rw-r--r-- | mm/mremap.c | 2 | ||||
| -rw-r--r-- | mm/msync.c | 5 | ||||
| -rw-r--r-- | mm/nommu.c | 9 | ||||
| -rw-r--r-- | mm/page-writeback.c | 43 | ||||
| -rw-r--r-- | mm/page_alloc.c | 90 | ||||
| -rw-r--r-- | mm/pagewalk.c | 5 | ||||
| -rw-r--r-- | mm/rmap.c | 267 | ||||
| -rw-r--r-- | mm/shmem.c | 3 | ||||
| -rw-r--r-- | mm/slab.h | 4 | ||||
| -rw-r--r-- | mm/slab_common.c | 151 | ||||
| -rw-r--r-- | mm/slub.c | 37 | ||||
| -rw-r--r-- | mm/swap.c | 4 | ||||
| -rw-r--r-- | mm/vmscan.c | 26 | ||||
| -rw-r--r-- | mm/vmstat.c | 124 |
32 files changed, 567 insertions, 1247 deletions
@@ -325,6 +325,7 @@ config VIRT_TO_BUS config MMU_NOTIFIER bool + select SRCU config KSM bool "Enable KSM for page merging" diff --git a/mm/Kconfig.debug b/mm/Kconfig.debug index 56badfc..957d3da 100644 --- a/mm/Kconfig.debug +++ b/mm/Kconfig.debug @@ -14,7 +14,6 @@ config DEBUG_PAGEALLOC depends on !KMEMCHECK select PAGE_EXTENSION select PAGE_POISONING if !ARCH_SUPPORTS_DEBUG_PAGEALLOC - select PAGE_GUARD if ARCH_SUPPORTS_DEBUG_PAGEALLOC ---help--- Unmap pages from the kernel linear mapping after free_pages(). This results in a large slowdown, but helps to find certain types @@ -27,13 +26,5 @@ config DEBUG_PAGEALLOC that would result in incorrect warnings of memory corruption after a resume because free pages are not saved to the suspend image. -config WANT_PAGE_DEBUG_FLAGS - bool - config PAGE_POISONING bool - select WANT_PAGE_DEBUG_FLAGS - -config PAGE_GUARD - bool - select WANT_PAGE_DEBUG_FLAGS diff --git a/mm/Makefile b/mm/Makefile index 4bf586e..3548460 100644 --- a/mm/Makefile +++ b/mm/Makefile @@ -3,7 +3,7 @@ # mmu-y := nommu.o -mmu-$(CONFIG_MMU) := fremap.o gup.o highmem.o memory.o mincore.o \ +mmu-$(CONFIG_MMU) := gup.o highmem.o memory.o mincore.o \ mlock.o mmap.o mprotect.o mremap.o msync.o rmap.o \ vmalloc.o pagewalk.o pgtable-generic.o @@ -130,7 +130,6 @@ static const struct trace_print_flags vmaflags_names[] = { {VM_ACCOUNT, "account" }, {VM_NORESERVE, "noreserve" }, {VM_HUGETLB, "hugetlb" }, - {VM_NONLINEAR, "nonlinear" }, #if defined(CONFIG_X86) {VM_PAT, "pat" }, #elif defined(CONFIG_PPC) diff --git a/mm/filemap.c b/mm/filemap.c index bd8543c..bf7a271 100644 --- a/mm/filemap.c +++ b/mm/filemap.c @@ -1046,8 +1046,7 @@ EXPORT_SYMBOL(find_lock_entry); * @mapping: the address_space to search * @offset: the page index * @fgp_flags: PCG flags - * @cache_gfp_mask: gfp mask to use for the page cache data page allocation - * @radix_gfp_mask: gfp mask to use for radix tree node allocation + * @gfp_mask: gfp mask to use for the page cache data page allocation * * Looks up the page cache slot at @mapping & @offset. * @@ -1056,11 +1055,9 @@ EXPORT_SYMBOL(find_lock_entry); * FGP_ACCESSED: the page will be marked accessed * FGP_LOCK: Page is return locked * FGP_CREAT: If page is not present then a new page is allocated using - * @cache_gfp_mask and added to the page cache and the VM's LRU - * list. If radix tree nodes are allocated during page cache - * insertion then @radix_gfp_mask is used. The page is returned - * locked and with an increased refcount. Otherwise, %NULL is - * returned. + * @gfp_mask and added to the page cache and the VM's LRU + * list. The page is returned locked and with an increased + * refcount. Otherwise, %NULL is returned. * * If FGP_LOCK or FGP_CREAT are specified then the function may sleep even * if the GFP flags specified for FGP_CREAT are atomic. @@ -1068,7 +1065,7 @@ EXPORT_SYMBOL(find_lock_entry); * If there is a page cache page, it is returned with an increased refcount. */ struct page *pagecache_get_page(struct address_space *mapping, pgoff_t offset, - int fgp_flags, gfp_t cache_gfp_mask, gfp_t radix_gfp_mask) + int fgp_flags, gfp_t gfp_mask) { struct page *page; @@ -1105,13 +1102,11 @@ no_page: if (!page && (fgp_flags & FGP_CREAT)) { int err; if ((fgp_flags & FGP_WRITE) && mapping_cap_account_dirty(mapping)) - cache_gfp_mask |= __GFP_WRITE; - if (fgp_flags & FGP_NOFS) { - cache_gfp_mask &= ~__GFP_FS; - radix_gfp_mask &= ~__GFP_FS; - } + gfp_mask |= __GFP_WRITE; + if (fgp_flags & FGP_NOFS) + gfp_mask &= ~__GFP_FS; - page = __page_cache_alloc(cache_gfp_mask); + page = __page_cache_alloc(gfp_mask); if (!page) return NULL; @@ -1122,7 +1117,8 @@ no_page: if (fgp_flags & FGP_ACCESSED) __SetPageReferenced(page); - err = add_to_page_cache_lru(page, mapping, offset, radix_gfp_mask); + err = add_to_page_cache_lru(page, mapping, offset, + gfp_mask & GFP_RECLAIM_MASK); if (unlikely(err)) { page_cache_release(page); page = NULL; @@ -2091,7 +2087,6 @@ const struct vm_operations_struct generic_file_vm_ops = { .fault = filemap_fault, .map_pages = filemap_map_pages, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; /* This is used for a general mmap of a disk file */ @@ -2443,8 +2438,7 @@ struct page *grab_cache_page_write_begin(struct address_space *mapping, fgp_flags |= FGP_NOFS; page = pagecache_get_page(mapping, index, fgp_flags, - mapping_gfp_mask(mapping), - GFP_KERNEL); + mapping_gfp_mask(mapping)); if (page) wait_for_stable_page(page); diff --git a/mm/filemap_xip.c b/mm/filemap_xip.c index 0d105ae..70c09da 100644 --- a/mm/filemap_xip.c +++ b/mm/filemap_xip.c @@ -301,7 +301,6 @@ out: static const struct vm_operations_struct xip_file_vm_ops = { .fault = xip_file_fault, .page_mkwrite = filemap_page_mkwrite, - .remap_pages = generic_file_remap_pages, }; int xip_file_mmap(struct file * file, struct vm_area_struct * vma) diff --git a/mm/fremap.c b/mm/fremap.c deleted file mode 100644 index 2805d71..0000000 --- a/mm/fremap.c +++ /dev/null @@ -1,283 +0,0 @@ -/* - * linux/mm/fremap.c - * - * Explicit pagetable population and nonlinear (random) mappings support. - * - * started by Ingo Molnar, Copyright (C) 2002, 2003 - */ -#include <linux/export.h> -#include <linux/backing-dev.h> -#include <linux/mm.h> -#include <linux/swap.h> -#include <linux/file.h> -#include <linux/mman.h> -#include <linux/pagemap.h> -#include <linux/swapops.h> -#include <linux/rmap.h> -#include <linux/syscalls.h> -#include <linux/mmu_notifier.h> - -#include <asm/mmu_context.h> -#include <asm/cacheflush.h> -#include <asm/tlbflush.h> - -#include "internal.h" - -static int mm_counter(struct page *page) -{ - return PageAnon(page) ? MM_ANONPAGES : MM_FILEPAGES; -} - -static void zap_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, pte_t *ptep) -{ - pte_t pte = *ptep; - struct page *page; - swp_entry_t entry; - - if (pte_present(pte)) { - flush_cache_page(vma, addr, pte_pfn(pte)); - pte = ptep_clear_flush_notify(vma, addr, ptep); - page = vm_normal_page(vma, addr, pte); - if (page) { - if (pte_dirty(pte)) - set_page_dirty(page); - update_hiwater_rss(mm); - dec_mm_counter(mm, mm_counter(page)); - page_remove_rmap(page); - page_cache_release(page); - } - } else { /* zap_pte() is not called when pte_none() */ - if (!pte_file(pte)) { - update_hiwater_rss(mm); - entry = pte_to_swp_entry(pte); - if (non_swap_entry(entry)) { - if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - dec_mm_counter(mm, mm_counter(page)); - } - } else { - free_swap_and_cache(entry); - dec_mm_counter(mm, MM_SWAPENTS); - } - } - pte_clear_not_present_full(mm, addr, ptep, 0); - } -} - -/* - * Install a file pte to a given virtual memory address, release any - * previously existing mapping. - */ -static int install_file_pte(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long addr, unsigned long pgoff, pgprot_t prot) -{ - int err = -ENOMEM; - pte_t *pte, ptfile; - spinlock_t *ptl; - - pte = get_locked_pte(mm, addr, &ptl); - if (!pte) - goto out; - - ptfile = pgoff_to_pte(pgoff); - - if (!pte_none(*pte)) - zap_pte(mm, vma, addr, pte); - - set_pte_at(mm, addr, pte, pte_file_mksoft_dirty(ptfile)); - /* - * We don't need to run update_mmu_cache() here because the "file pte" - * being installed by install_file_pte() is not a real pte - it's a - * non-present entry (like a swap entry), noting what file offset should - * be mapped there when there's a fault (in a non-linear vma where - * that's not obvious). - */ - pte_unmap_unlock(pte, ptl); - err = 0; -out: - return err; -} - -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - struct mm_struct *mm = vma->vm_mm; - int err; - - do { - err = install_file_pte(mm, vma, addr, pgoff, vma->vm_page_prot); - if (err) - return err; - - size -= PAGE_SIZE; - addr += PAGE_SIZE; - pgoff++; - } while (size); - - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - -/** - * sys_remap_file_pages - remap arbitrary pages of an existing VM_SHARED vma - * @start: start of the remapped virtual memory range - * @size: size of the remapped virtual memory range - * @prot: new protection bits of the range (see NOTE) - * @pgoff: to-be-mapped page of the backing store file - * @flags: 0 or MAP_NONBLOCKED - the later will cause no IO. - * - * sys_remap_file_pages remaps arbitrary pages of an existing VM_SHARED vma - * (shared backing store file). - * - * This syscall works purely via pagetables, so it's the most efficient - * way to map the same (large) file into a given virtual window. Unlike - * mmap()/mremap() it does not create any new vmas. The new mappings are - * also safe across swapout. - * - * NOTE: the @prot parameter right now is ignored (but must be zero), - * and the vma's default protection is used. Arbitrary protections - * might be implemented in the future. - */ -SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, - unsigned long, prot, unsigned long, pgoff, unsigned long, flags) -{ - struct mm_struct *mm = current->mm; - struct address_space *mapping; - struct vm_area_struct *vma; - int err = -EINVAL; - int has_write_lock = 0; - vm_flags_t vm_flags = 0; - - pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " - "See Documentation/vm/remap_file_pages.txt.\n", - current->comm, current->pid); - - if (prot) - return err; - /* - * Sanitize the syscall parameters: - */ - start = start & PAGE_MASK; - size = size & PAGE_MASK; - - /* Does the address range wrap, or is the span zero-sized? */ - if (start + size <= start) - return err; - - /* Does pgoff wrap? */ - if (pgoff + (size >> PAGE_SHIFT) < pgoff) - return err; - - /* Can we represent this offset inside this architecture's pte's? */ -#if PTE_FILE_MAX_BITS < BITS_PER_LONG - if (pgoff + (size >> PAGE_SHIFT) >= (1UL << PTE_FILE_MAX_BITS)) - return err; -#endif - - /* We need down_write() to change vma->vm_flags. */ - down_read(&mm->mmap_sem); - retry: - vma = find_vma(mm, start); - - /* - * Make sure the vma is shared, that it supports prefaulting, - * and that the remapped range is valid and fully within - * the single existing vma. - */ - if (!vma || !(vma->vm_flags & VM_SHARED)) - goto out; - - if (!vma->vm_ops || !vma->vm_ops->remap_pages) - goto out; - - if (start < vma->vm_start || start + size > vma->vm_end) - goto out; - - /* Must set VM_NONLINEAR before any pages are populated. */ - if (!(vma->vm_flags & VM_NONLINEAR)) { - /* - * vm_private_data is used as a swapout cursor - * in a VM_NONLINEAR vma. - */ - if (vma->vm_private_data) - goto out; - - /* Don't need a nonlinear mapping, exit success */ - if (pgoff == linear_page_index(vma, start)) { - err = 0; - goto out; - } - - if (!has_write_lock) { -get_write_lock: - up_read(&mm->mmap_sem); - down_write(&mm->mmap_sem); - has_write_lock = 1; - goto retry; - } - mapping = vma->vm_file->f_mapping; - /* - * page_mkclean doesn't work on nonlinear vmas, so if - * dirty pages need to be accounted, emulate with linear - * vmas. - */ - if (mapping_cap_account_dirty(mapping)) { - unsigned long addr; - struct file *file = get_file(vma->vm_file); - /* mmap_region may free vma; grab the info now */ - vm_flags = vma->vm_flags; - - addr = mmap_region(file, start, size, vm_flags, pgoff); - fput(file); - if (IS_ERR_VALUE(addr)) { - err = addr; - } else { - BUG_ON(addr != start); - err = 0; - } - goto out_freed; - } - i_mmap_lock_write(mapping); - flush_dcache_mmap_lock(mapping); - vma->vm_flags |= VM_NONLINEAR; - vma_interval_tree_remove(vma, &mapping->i_mmap); - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - flush_dcache_mmap_unlock(mapping); - i_mmap_unlock_write(mapping); - } - - if (vma->vm_flags & VM_LOCKED) { - /* - * drop PG_Mlocked flag for over-mapped range - */ - if (!has_write_lock) - goto get_write_lock; - vm_flags = vma->vm_flags; - munlock_vma_pages_range(vma, start, start + size); - vma->vm_flags = vm_flags; - } - - mmu_notifier_invalidate_range_start(mm, start, start + size); - err = vma->vm_ops->remap_pages(vma, start, size, pgoff); - mmu_notifier_invalidate_range_end(mm, start, start + size); - - /* - * We can't clear VM_NONLINEAR because we'd have to do - * it after ->populate completes, and that would prevent - * downgrading the lock. (Locks can't be upgraded). - */ - -out: - if (vma) - vm_flags = vma->vm_flags; -out_freed: - if (likely(!has_write_lock)) - up_read(&mm->mmap_sem); - else - up_write(&mm->mmap_sem); - if (!err && ((vm_flags & VM_LOCKED) || !(flags & MAP_NONBLOCK))) - mm_populate(start, size); - - return err; -} @@ -55,7 +55,7 @@ retry: */ if (likely(!(flags & FOLL_MIGRATION))) goto no_page; - if (pte_none(pte) || pte_file(pte)) + if (pte_none(pte)) goto no_page; entry = pte_to_swp_entry(pte); if (!is_migration_entry(entry)) @@ -296,7 +296,7 @@ static int faultin_page(struct task_struct *tsk, struct vm_area_struct *vma, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return *flags & FOLL_HWPOISON ? -EHWPOISON : -EFAULT; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } @@ -571,7 +571,7 @@ int fixup_user_fault(struct task_struct *tsk, struct mm_struct *mm, return -ENOMEM; if (ret & (VM_FAULT_HWPOISON | VM_FAULT_HWPOISON_LARGE)) return -EHWPOISON; - if (ret & VM_FAULT_SIGBUS) + if (ret & (VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV)) return -EFAULT; BUG(); } diff --git a/mm/hugetlb.c b/mm/hugetlb.c index 85032de..be0e5d0 100644 --- a/mm/hugetlb.c +++ b/mm/hugetlb.c @@ -35,7 +35,7 @@ #include <linux/node.h> #include "internal.h" -unsigned long hugepages_treat_as_movable; +int hugepages_treat_as_movable; int hugetlb_max_hstate __read_mostly; unsigned int default_hstate_idx; diff --git a/mm/interval_tree.c b/mm/interval_tree.c index 8da581f..f2c2492 100644 --- a/mm/interval_tree.c +++ b/mm/interval_tree.c @@ -21,8 +21,8 @@ static inline unsigned long vma_last_pgoff(struct vm_area_struct *v) return v->vm_pgoff + ((v->vm_end - v->vm_start) >> PAGE_SHIFT) - 1; } -INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.linear.rb, - unsigned long, shared.linear.rb_subtree_last, +INTERVAL_TREE_DEFINE(struct vm_area_struct, shared.rb, + unsigned long, shared.rb_subtree_last, vma_start_pgoff, vma_last_pgoff,, vma_interval_tree) /* Insert node immediately after prev in the interval tree */ @@ -36,26 +36,26 @@ void vma_interval_tree_insert_after(struct vm_area_struct *node, VM_BUG_ON_VMA(vma_start_pgoff(node) != vma_start_pgoff(prev), node); - if (!prev->shared.linear.rb.rb_right) { + if (!prev->shared.rb.rb_right) { parent = prev; - link = &prev->shared.linear.rb.rb_right; + link = &prev->shared.rb.rb_right; } else { - parent = rb_entry(prev->shared.linear.rb.rb_right, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; - while (parent->shared.linear.rb.rb_left) { - parent = rb_entry(parent->shared.linear.rb.rb_left, - struct vm_area_struct, shared.linear.rb); - if (parent->shared.linear.rb_subtree_last < last) - parent->shared.linear.rb_subtree_last = last; + parent = rb_entry(prev->shared.rb.rb_right, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; + while (parent->shared.rb.rb_left) { + parent = rb_entry(parent->shared.rb.rb_left, + struct vm_area_struct, shared.rb); + if (parent->shared.rb_subtree_last < last) + parent->shared.rb_subtree_last = last; } - link = &parent->shared.linear.rb.rb_left; + link = &parent->shared.rb.rb_left; } - node->shared.linear.rb_subtree_last = last; - rb_link_node(&node->shared.linear.rb, &parent->shared.linear.rb, link); - rb_insert_augmented(&node->shared.linear.rb, root, + node->shared.rb_subtree_last = last; + rb_link_node(&node->shared.rb, &parent->shared.rb, link); + rb_insert_augmented(&node->shared.rb, root, &vma_interval_tree_augment); } @@ -376,7 +376,7 @@ static int break_ksm(struct vm_area_struct *vma, unsigned long addr) else ret = VM_FAULT_WRITE; put_page(page); - } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_OOM))); + } while (!(ret & (VM_FAULT_WRITE | VM_FAULT_SIGBUS | VM_FAULT_SIGSEGV | VM_FAULT_OOM))); /* * We must loop because handle_mm_fault() may back out if there's * any difficulty e.g. if pte accessed bit gets updated concurrently. @@ -1748,7 +1748,7 @@ int ksm_madvise(struct vm_area_struct *vma, unsigned long start, */ if (*vm_flags & (VM_MERGEABLE | VM_SHARED | VM_MAYSHARE | VM_PFNMAP | VM_IO | VM_DONTEXPAND | - VM_HUGETLB | VM_NONLINEAR | VM_MIXEDMAP)) + VM_HUGETLB | VM_MIXEDMAP)) return 0; /* just ignore the advice */ #ifdef VM_SAO diff --git a/mm/madvise.c b/mm/madvise.c index a271adc..d79fb5e 100644 --- a/mm/madvise.c +++ b/mm/madvise.c @@ -155,7 +155,7 @@ static int swapin_walk_pmd_entry(pmd_t *pmd, unsigned long start, pte = *(orig_pte + ((index - start) / PAGE_SIZE)); pte_unmap_unlock(orig_pte, ptl); - if (pte_present(pte) || pte_none(pte) || pte_file(pte)) + if (pte_present(pte) || pte_none(pte)) continue; entry = pte_to_swp_entry(pte); if (unlikely(non_swap_entry(entry))) @@ -278,14 +278,7 @@ static long madvise_dontneed(struct vm_area_struct *vma, if (vma->vm_flags & (VM_LOCKED|VM_HUGETLB|VM_PFNMAP)) return -EINVAL; - if (unlikely(vma->vm_flags & VM_NONLINEAR)) { - struct zap_details details = { - .nonlinear_vma = vma, - .last_index = ULONG_MAX, - }; - zap_page_range(vma, start, end - start, &details); - } else - zap_page_range(vma, start, end - start, NULL); + zap_page_range(vma, start, end - start, NULL); return 0; } @@ -303,7 +296,7 @@ static long madvise_remove(struct vm_area_struct *vma, *prev = NULL; /* tell sys_madvise we drop mmap_sem */ - if (vma->vm_flags & (VM_LOCKED|VM_NONLINEAR|VM_HUGETLB)) + if (vma->vm_flags & (VM_LOCKED | VM_HUGETLB)) return -EINVAL; f = vma->vm_file; diff --git a/mm/memcontrol.c b/mm/memcontrol.c index ef91e85..f3f8a4f 100644 --- a/mm/memcontrol.c +++ b/mm/memcontrol.c @@ -343,9 +343,6 @@ struct mem_cgroup { struct cg_proto tcp_mem; #endif #if defined(CONFIG_MEMCG_KMEM) - /* analogous to slab_common's slab_caches list, but per-memcg; - * protected by memcg_slab_mutex */ - struct list_head memcg_slab_caches; /* Index in the kmem_cache->memcg_params->memcg_caches array */ int kmemcg_id; #endif @@ -1477,9 +1474,9 @@ void mem_cgroup_print_oom_info(struct mem_cgroup *memcg, struct task_struct *p) pr_info("Task in "); pr_cont_cgroup_path(task_cgroup(p, memory_cgrp_id)); - pr_info(" killed as a result of limit of "); + pr_cont(" killed as a result of limit of "); pr_cont_cgroup_path(memcg->css.cgroup); - pr_info("\n"); + pr_cont("\n"); rcu_read_unlock(); @@ -2476,27 +2473,8 @@ static void commit_charge(struct page *page, struct mem_cgroup *memcg, } #ifdef CONFIG_MEMCG_KMEM -/* - * The memcg_slab_mutex is held whenever a per memcg kmem cache is created or - * destroyed. It protects memcg_caches arrays and memcg_slab_caches lists. - */ -static DEFINE_MUTEX(memcg_slab_mutex); - -/* - * This is a bit cumbersome, but it is rarely used and avoids a backpointer - * in the memcg_cache_params struct. - */ -static struct kmem_cache *memcg_params_to_cache(struct memcg_cache_params *p) -{ - struct kmem_cache *cachep; - - VM_BUG_ON(p->is_root_cache); - cachep = p->root_cache; - return cache_from_memcg_idx(cachep, memcg_cache_id(p->memcg)); -} - -static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, - unsigned long nr_pages) +int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, + unsigned long nr_pages) { struct page_counter *counter; int ret = 0; @@ -2533,8 +2511,7 @@ static int memcg_charge_kmem(struct mem_cgroup *memcg, gfp_t gfp, return ret; } -static void memcg_uncharge_kmem(struct mem_cgroup *memcg, - unsigned long nr_pages) +void memcg_uncharge_kmem(struct mem_cgroup *memcg, unsigned long nr_pages) { page_counter_uncharge(&memcg->memory, nr_pages); if (do_swap_account) @@ -2579,10 +2556,7 @@ static int memcg_alloc_cache_id(void) else if (size > MEMCG_CACHES_MAX_SIZE) size = MEMCG_CACHES_MAX_SIZE; - mutex_lock(&memcg_slab_mutex); err = memcg_update_all_caches(size); - mutex_unlock(&memcg_slab_mutex); - if (err) { ida_simple_remove(&kmem_limited_groups, id); return err; @@ -2605,123 +2579,20 @@ void memcg_update_array_size(int num) memcg_limited_groups_array_size = num; } -static void memcg_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache) -{ - static char memcg_name_buf[NAME_MAX + 1]; /* protected by - memcg_slab_mutex */ - struct kmem_cache *cachep; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - id = memcg_cache_id(memcg); - - /* - * Since per-memcg caches are created asynchronously on first - * allocation (see memcg_kmem_get_cache()), several threads can try to - * create the same cache, but only one of them may succeed. - */ - if (cache_from_memcg_idx(root_cache, id)) - return; - - cgroup_name(memcg->css.cgroup, memcg_name_buf, NAME_MAX + 1); - cachep = memcg_create_kmem_cache(memcg, root_cache, memcg_name_buf); - /* - * If we could not create a memcg cache, do not complain, because - * that's not critical at all as we can always proceed with the root - * cache. - */ - if (!cachep) - return; - - list_add(&cachep->memcg_params->list, &memcg->memcg_slab_caches); - - /* - * Since readers won't lock (see cache_from_memcg_idx()), we need a - * barrier here to ensure nobody will see the kmem_cache partially - * initialized. - */ - smp_wmb(); - - BUG_ON(root_cache->memcg_params->memcg_caches[id]); - root_cache->memcg_params->memcg_caches[id] = cachep; -} - -static void memcg_unregister_cache(struct kmem_cache *cachep) -{ - struct kmem_cache *root_cache; - struct mem_cgroup *memcg; - int id; - - lockdep_assert_held(&memcg_slab_mutex); - - BUG_ON(is_root_cache(cachep)); - - root_cache = cachep->memcg_params->root_cache; - memcg = cachep->memcg_params->memcg; - id = memcg_cache_id(memcg); - - BUG_ON(root_cache->memcg_params->memcg_caches[id] != cachep); - root_cache->memcg_params->memcg_caches[id] = NULL; - - list_del(&cachep->memcg_params->list); - - kmem_cache_destroy(cachep); -} - -int __memcg_cleanup_cache_params(struct kmem_cache *s) -{ - struct kmem_cache *c; - int i, failed = 0; - - mutex_lock(&memcg_slab_mutex); - for_each_memcg_cache_index(i) { - c = cache_from_memcg_idx(s, i); - if (!c) - continue; - - memcg_unregister_cache(c); - - if (cache_from_memcg_idx(s, i)) - failed++; - } - mutex_unlock(&memcg_slab_mutex); - return failed; -} - -static void memcg_unregister_all_caches(struct mem_cgroup *memcg) -{ - struct kmem_cache *cachep; - struct memcg_cache_params *params, *tmp; - - if (!memcg_kmem_is_active(memcg)) - return; - - mutex_lock(&memcg_slab_mutex); - list_for_each_entry_safe(params, tmp, &memcg->memcg_slab_caches, list) { - cachep = memcg_params_to_cache(params); - memcg_unregister_cache(cachep); - } - mutex_unlock(&memcg_slab_mutex); -} - -struct memcg_register_cache_work { +struct memcg_kmem_cache_create_work { struct mem_cgroup *memcg; struct kmem_cache *cachep; struct work_struct work; }; -static void memcg_register_cache_func(struct work_struct *w) +static void memcg_kmem_cache_create_func(struct work_struct *w) { - struct memcg_register_cache_work *cw = - container_of(w, struct memcg_register_cache_work, work); + struct memcg_kmem_cache_create_work *cw = + container_of(w, struct memcg_kmem_cache_create_work, work); struct mem_cgroup *memcg = cw->memcg; struct kmem_cache *cachep = cw->cachep; - mutex_lock(&memcg_slab_mutex); - memcg_register_cache(memcg, cachep); - mutex_unlock(&memcg_slab_mutex); + memcg_create_kmem_cache(memcg, cachep); css_put(&memcg->css); kfree(cw); @@ -2730,10 +2601,10 @@ static void memcg_register_cache_func(struct work_struct *w) /* * Enqueue the creation of a per-memcg kmem_cache. */ -static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void __memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { - struct memcg_register_cache_work *cw; + struct memcg_kmem_cache_create_work *cw; cw = kmalloc(sizeof(*cw), GFP_NOWAIT); if (!cw) @@ -2743,18 +2614,18 @@ static void __memcg_schedule_register_cache(struct mem_cgroup *memcg, cw->memcg = memcg; cw->cachep = cachep; + INIT_WORK(&cw->work, memcg_kmem_cache_create_func); - INIT_WORK(&cw->work, memcg_register_cache_func); schedule_work(&cw->work); } -static void memcg_schedule_register_cache(struct mem_cgroup *memcg, - struct kmem_cache *cachep) +static void memcg_schedule_kmem_cache_create(struct mem_cgroup *memcg, + struct kmem_cache *cachep) { /* * We need to stop accounting when we kmalloc, because if the * corresponding kmalloc cache is not yet created, the first allocation - * in __memcg_schedule_register_cache will recurse. + * in __memcg_schedule_kmem_cache_create will recurse. * * However, it is better to enclose the whole function. Depending on * the debugging options enabled, INIT_WORK(), for instance, can @@ -2763,24 +2634,10 @@ static void memcg_schedule_register_cache(struct mem_cgroup *memcg, * the safest choice is to do it like this, wrapping the whole function. */ current->memcg_kmem_skip_account = 1; - __memcg_schedule_register_cache(memcg, cachep); + __memcg_schedule_kmem_cache_create(memcg, cachep); current->memcg_kmem_skip_account = 0; } -int __memcg_charge_slab(struct kmem_cache *cachep, gfp_t gfp, int order) -{ - unsigned int nr_pages = 1 << order; - - return memcg_charge_kmem(cachep->memcg_params->memcg, gfp, nr_pages); -} - -void __memcg_uncharge_slab(struct kmem_cache *cachep, int order) -{ - unsigned int nr_pages = 1 << order; - - memcg_uncharge_kmem(cachep->memcg_params->memcg, nr_pages); -} - /* * Return the kmem_cache we're supposed to use for a slab allocation. * We try to use the current memcg's version of the cache. @@ -2825,7 +2682,7 @@ struct kmem_cache *__memcg_kmem_get_cache(struct kmem_cache *cachep) * could happen with the slab_mutex held. So it's better to * defer everything. */ - memcg_schedule_register_cache(memcg, cachep); + memcg_schedule_kmem_cache_create(memcg, cachep); out: css_put(&memcg->css); return cachep; @@ -3043,18 +2900,6 @@ static int mem_cgroup_move_swap_account(swp_entry_t entry, if (swap_cgroup_cmpxchg(entry, old_id, new_id) == old_id) { mem_cgroup_swap_statistics(from, false); mem_cgroup_swap_statistics(to, true); - /* - * This function is only called from task migration context now. - * It postpones page_counter and refcount handling till the end - * of task migration(mem_cgroup_clear_mc()) for performance - * improvement. But we cannot postpone css_get(to) because if - * the process that has been moved to @to does swap-in, the - * refcount of @to might be decreased to 0. - * - * We are in attach() phase, so the cgroup is guaranteed to be - * alive, so we can just call css_get(). - */ - css_get(&to->css); return 0; } return -EINVAL; @@ -4166,7 +4011,7 @@ static int memcg_init_kmem(struct mem_cgroup *memcg, struct cgroup_subsys *ss) static void memcg_destroy_kmem(struct mem_cgroup *memcg) { - memcg_unregister_all_caches(memcg); + memcg_destroy_kmem_caches(memcg); mem_cgroup_sockets_destroy(memcg); } #else @@ -4679,6 +4524,7 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) if (parent_css == NULL) { root_mem_cgroup = memcg; page_counter_init(&memcg->memory, NULL); + memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); } @@ -4693,7 +4539,6 @@ mem_cgroup_css_alloc(struct cgroup_subsys_state *parent_css) spin_lock_init(&memcg->event_list_lock); #ifdef CONFIG_MEMCG_KMEM memcg->kmemcg_id = -1; - INIT_LIST_HEAD(&memcg->memcg_slab_caches); #endif return &memcg->css; @@ -4724,6 +4569,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) if (parent->use_hierarchy) { page_counter_init(&memcg->memory, &parent->memory); + memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, &parent->memsw); page_counter_init(&memcg->kmem, &parent->kmem); @@ -4733,6 +4579,7 @@ mem_cgroup_css_online(struct cgroup_subsys_state *css) */ } else { page_counter_init(&memcg->memory, NULL); + memcg->soft_limit = PAGE_COUNTER_MAX; page_counter_init(&memcg->memsw, NULL); page_counter_init(&memcg->kmem, NULL); /* @@ -4807,7 +4654,7 @@ static void mem_cgroup_css_reset(struct cgroup_subsys_state *css) mem_cgroup_resize_limit(memcg, PAGE_COUNTER_MAX); mem_cgroup_resize_memsw_limit(memcg, PAGE_COUNTER_MAX); memcg_update_kmem_limit(memcg, PAGE_COUNTER_MAX); - memcg->soft_limit = 0; + memcg->soft_limit = PAGE_COUNTER_MAX; } #ifdef CONFIG_MMU @@ -4935,10 +4782,7 @@ static struct page *mc_handle_file_pte(struct vm_area_struct *vma, return NULL; mapping = vma->vm_file->f_mapping; - if (pte_none(ptent)) - pgoff = linear_page_index(vma, addr); - else /* pte_file(ptent) is true */ - pgoff = pte_to_pgoff(ptent); + pgoff = linear_page_index(vma, addr); /* page is moved even if it's not RSS of this task(page-faulted). */ #ifdef CONFIG_SWAP @@ -4970,7 +4814,7 @@ static enum mc_target_type get_mctgt_type(struct vm_area_struct *vma, page = mc_handle_present_pte(vma, addr, ptent); else if (is_swap_pte(ptent)) page = mc_handle_swap_pte(vma, addr, ptent, &ent); - else if (pte_none(ptent) || pte_file(ptent)) + else if (pte_none(ptent)) page = mc_handle_file_pte(vma, addr, ptent, &ent); if (!page && !ent.val) @@ -5782,7 +5626,7 @@ void mem_cgroup_uncharge_list(struct list_head *page_list) * mem_cgroup_migrate - migrate a charge to another page * @oldpage: currently charged page * @newpage: page to transfer the charge to - * @lrucare: both pages might be on the LRU already + * @lrucare: either or both pages might be on the LRU already * * Migrate the charge from @oldpage to @newpage. * diff --git a/mm/memory.c b/mm/memory.c index 649e7d44..d63849b 100644 --- a/mm/memory.c +++ b/mm/memory.c @@ -235,6 +235,9 @@ void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm, unsigned long static void tlb_flush_mmu_tlbonly(struct mmu_gather *tlb) { + if (!tlb->end) + return; + tlb_flush(tlb); mmu_notifier_invalidate_range(tlb->mm, tlb->start, tlb->end); #ifdef CONFIG_HAVE_RCU_TABLE_FREE @@ -247,7 +250,7 @@ static void tlb_flush_mmu_free(struct mmu_gather *tlb) { struct mmu_gather_batch *batch; - for (batch = &tlb->local; batch; batch = batch->next) { + for (batch = &tlb->local; batch && batch->nr; batch = batch->next) { free_pages_and_swap_cache(batch->pages, batch->nr); batch->nr = 0; } @@ -256,9 +259,6 @@ static void tlb_flush_mmu_free(struct mmu_gather *tlb) void tlb_flush_mmu(struct mmu_gather *tlb) { - if (!tlb->end) - return; - tlb_flush_mmu_tlbonly(tlb); tlb_flush_mmu_free(tlb); } @@ -754,6 +754,8 @@ struct page *vm_normal_page(struct vm_area_struct *vma, unsigned long addr, if (HAVE_PTE_SPECIAL) { if (likely(!pte_special(pte))) goto check_pfn; + if (vma->vm_ops && vma->vm_ops->find_special_page) + return vma->vm_ops->find_special_page(vma, addr); if (vma->vm_flags & (VM_PFNMAP | VM_MIXEDMAP)) return NULL; if (!is_zero_pfn(pfn)) @@ -811,42 +813,40 @@ copy_one_pte(struct mm_struct *dst_mm, struct mm_struct *src_mm, /* pte contains position in swap or file, so copy. */ if (unlikely(!pte_present(pte))) { - if (!pte_file(pte)) { - swp_entry_t entry = pte_to_swp_entry(pte); - - if (likely(!non_swap_entry(entry))) { - if (swap_duplicate(entry) < 0) - return entry.val; - - /* make sure dst_mm is on swapoff's mmlist. */ - if (unlikely(list_empty(&dst_mm->mmlist))) { - spin_lock(&mmlist_lock); - if (list_empty(&dst_mm->mmlist)) - list_add(&dst_mm->mmlist, - &src_mm->mmlist); - spin_unlock(&mmlist_lock); - } - rss[MM_SWAPENTS]++; - } else if (is_migration_entry(entry)) { - page = migration_entry_to_page(entry); - - if (PageAnon(page)) - rss[MM_ANONPAGES]++; - else - rss[MM_FILEPAGES]++; - - if (is_write_migration_entry(entry) && - is_cow_mapping(vm_flags)) { - /* - * COW mappings require pages in both - * parent and child to be set to read. - */ - make_migration_entry_read(&entry); - pte = swp_entry_to_pte(entry); - if (pte_swp_soft_dirty(*src_pte)) - pte = pte_swp_mksoft_dirty(pte); - set_pte_at(src_mm, addr, src_pte, pte); - } + swp_entry_t entry = pte_to_swp_entry(pte); + + if (likely(!non_swap_entry(entry))) { + if (swap_duplicate(entry) < 0) + return entry.val; + + /* make sure dst_mm is on swapoff's mmlist. */ + if (unlikely(list_empty(&dst_mm->mmlist))) { + spin_lock(&mmlist_lock); + if (list_empty(&dst_mm->mmlist)) + list_add(&dst_mm->mmlist, + &src_mm->mmlist); + spin_unlock(&mmlist_lock); + } + rss[MM_SWAPENTS]++; + } else if (is_migration_entry(entry)) { + page = migration_entry_to_page(entry); + + if (PageAnon(page)) + rss[MM_ANONPAGES]++; + else + rss[MM_FILEPAGES]++; + + if (is_write_migration_entry(entry) && + is_cow_mapping(vm_flags)) { + /* + * COW mappings require pages in both + * parent and child to be set to read. + */ + make_migration_entry_read(&entry); + pte = swp_entry_to_pte(entry); + if (pte_swp_soft_dirty(*src_pte)) + pte = pte_swp_mksoft_dirty(pte); + set_pte_at(src_mm, addr, src_pte, pte); } } goto out_set_pte; @@ -1020,11 +1020,9 @@ int copy_page_range(struct mm_struct *dst_mm, struct mm_struct *src_mm, * readonly mappings. The tradeoff is that copy_page_range is more * efficient than faulting. */ - if (!(vma->vm_flags & (VM_HUGETLB | VM_NONLINEAR | - VM_PFNMAP | VM_MIXEDMAP))) { - if (!vma->anon_vma) - return 0; - } + if (!(vma->vm_flags & (VM_HUGETLB | VM_PFNMAP | VM_MIXEDMAP)) && + !vma->anon_vma) + return 0; if (is_vm_hugetlb_page(vma)) return copy_hugetlb_page_range(dst_mm, src_mm, vma); @@ -1082,6 +1080,7 @@ static unsigned long zap_pte_range(struct mmu_gather *tlb, spinlock_t *ptl; pte_t *start_pte; pte_t *pte; + swp_entry_t entry; again: init_rss_vec(rss); @@ -1107,28 +1106,12 @@ again: if (details->check_mapping && details->check_mapping != page->mapping) continue; - /* - * Each page->index must be checked when - * invalidating or truncating nonlinear. - */ - if (details->nonlinear_vma && - (page->index < details->first_index || - page->index > details->last_index)) - continue; } ptent = ptep_get_and_clear_full(mm, addr, pte, tlb->fullmm); tlb_remove_tlb_entry(tlb, pte, addr); if (unlikely(!page)) continue; - if (unlikely(details) && details->nonlinear_vma - && linear_page_index(details->nonlinear_vma, - addr) != page->index) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(ptent)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, addr, pte, ptfile); - } if (PageAnon(page)) rss[MM_ANONPAGES]--; else { @@ -1151,33 +1134,25 @@ again: } continue; } - /* - * If details->check_mapping, we leave swap entries; - * if details->nonlinear_vma, we leave file entries. - */ + /* If details->check_mapping, we leave swap entries. */ if (unlikely(details)) continue; - if (pte_file(ptent)) { - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) - print_bad_pte(vma, addr, ptent, NULL); - } else { - swp_entry_t entry = pte_to_swp_entry(ptent); - if (!non_swap_entry(entry)) - rss[MM_SWAPENTS]--; - else if (is_migration_entry(entry)) { - struct page *page; + entry = pte_to_swp_entry(ptent); + if (!non_swap_entry(entry)) + rss[MM_SWAPENTS]--; + else if (is_migration_entry(entry)) { + struct page *page; - page = migration_entry_to_page(entry); + page = migration_entry_to_page(entry); - if (PageAnon(page)) - rss[MM_ANONPAGES]--; - else - rss[MM_FILEPAGES]--; - } - if (unlikely(!free_swap_and_cache(entry))) - print_bad_pte(vma, addr, ptent, NULL); + if (PageAnon(page)) + rss[MM_ANONPAGES]--; + else + rss[MM_FILEPAGES]--; } + if (unlikely(!free_swap_and_cache(entry))) + print_bad_pte(vma, addr, ptent, NULL); pte_clear_not_present_full(mm, addr, pte, tlb->fullmm); } while (pte++, addr += PAGE_SIZE, addr != end); @@ -1277,7 +1252,7 @@ static void unmap_page_range(struct mmu_gather *tlb, pgd_t *pgd; unsigned long next; - if (details && !details->check_mapping && !details->nonlinear_vma) + if (details && !details->check_mapping) details = NULL; BUG_ON(addr >= end); @@ -1371,7 +1346,7 @@ void unmap_vmas(struct mmu_gather *tlb, * @vma: vm_area_struct holding the applicable pages * @start: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * Caller must protect the VMA list */ @@ -1397,7 +1372,7 @@ void zap_page_range(struct vm_area_struct *vma, unsigned long start, * @vma: vm_area_struct holding the applicable pages * @address: starting address of pages to zap * @size: number of bytes to zap - * @details: details of nonlinear truncation or shared cache invalidation + * @details: details of shared cache invalidation * * The range must fit into one VMA. */ @@ -1922,12 +1897,11 @@ int apply_to_page_range(struct mm_struct *mm, unsigned long addr, EXPORT_SYMBOL_GPL(apply_to_page_range); /* - * handle_pte_fault chooses page fault handler according to an entry - * which was read non-atomically. Before making any commitment, on - * those architectures or configurations (e.g. i386 with PAE) which - * might give a mix of unmatched parts, do_swap_page and do_nonlinear_fault - * must check under lock before unmapping the pte and proceeding - * (but do_wp_page is only called after already making such a check; + * handle_pte_fault chooses page fault handler according to an entry which was + * read non-atomically. Before making any commitment, on those architectures + * or configurations (e.g. i386 with PAE) which might give a mix of unmatched + * parts, do_swap_page must check under lock before unmapping the pte and + * proceeding (but do_wp_page is only called after already making such a check; * and do_anonymous_page can safely check later on). */ static inline int pte_unmap_same(struct mm_struct *mm, pmd_t *pmd, @@ -2033,7 +2007,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, pte_t entry; int ret = 0; int page_mkwrite = 0; - struct page *dirty_page = NULL; + bool dirty_shared = false; unsigned long mmun_start = 0; /* For mmu_notifiers */ unsigned long mmun_end = 0; /* For mmu_notifiers */ struct mem_cgroup *memcg; @@ -2084,6 +2058,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock_page(old_page); } else if (unlikely((vma->vm_flags & (VM_WRITE|VM_SHARED)) == (VM_WRITE|VM_SHARED))) { + page_cache_get(old_page); /* * Only catch write-faults on shared writable pages, * read-only shared pages can get COWed by @@ -2091,7 +2066,7 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, */ if (vma->vm_ops && vma->vm_ops->page_mkwrite) { int tmp; - page_cache_get(old_page); + pte_unmap_unlock(page_table, ptl); tmp = do_page_mkwrite(vma, old_page, address); if (unlikely(!tmp || (tmp & @@ -2111,11 +2086,10 @@ static int do_wp_page(struct mm_struct *mm, struct vm_area_struct *vma, unlock_page(old_page); goto unlock; } - page_mkwrite = 1; } - dirty_page = old_page; - get_page(dirty_page); + + dirty_shared = true; reuse: /* @@ -2134,38 +2108,29 @@ reuse: pte_unmap_unlock(page_table, ptl); ret |= VM_FAULT_WRITE; - if (!dirty_page) - return ret; + if (dirty_shared) { + struct address_space *mapping; + int dirtied; - /* - * Yes, Virginia, this is actually required to prevent a race - * with clear_page_dirty_for_io() from clearing the page dirty - * bit after it clear all dirty ptes, but before a racing - * do_wp_page installs a dirty pte. - * - * do_shared_fault is protected similarly. - */ - if (!page_mkwrite) { - wait_on_page_locked(dirty_page); - set_page_dirty_balance(dirty_page); - /* file_update_time outside page_lock */ - if (vma->vm_file) - file_update_time(vma->vm_file); - } - put_page(dirty_page); - if (page_mkwrite) { - struct address_space *mapping = dirty_page->mapping; - - set_page_dirty(dirty_page); - unlock_page(dirty_page); - page_cache_release(dirty_page); - if (mapping) { + if (!page_mkwrite) + lock_page(old_page); + + dirtied = set_page_dirty(old_page); + VM_BUG_ON_PAGE(PageAnon(old_page), old_page); + mapping = old_page->mapping; + unlock_page(old_page); + page_cache_release(old_page); + + if ((dirtied || page_mkwrite) && mapping) { /* * Some device drivers do not set page.mapping * but still dirty their pages */ balance_dirty_pages_ratelimited(mapping); } + + if (!page_mkwrite) + file_update_time(vma->vm_file); } return ret; @@ -2324,25 +2289,11 @@ static inline void unmap_mapping_range_tree(struct rb_root *root, } } -static inline void unmap_mapping_range_list(struct list_head *head, - struct zap_details *details) -{ - struct vm_area_struct *vma; - - /* - * In nonlinear VMAs there is no correspondence between virtual address - * offset and file offset. So we must perform an exhaustive search - * across *all* the pages in each nonlinear VMA, not just the pages - * whose virtual address lies outside the file truncation point. - */ - list_for_each_entry(vma, head, shared.nonlinear) { - details->nonlinear_vma = vma; - unmap_mapping_range_vma(vma, vma->vm_start, vma->vm_end, details); - } -} - /** - * unmap_mapping_range - unmap the portion of all mmaps in the specified address_space corresponding to the specified page range in the underlying file. + * unmap_mapping_range - unmap the portion of all mmaps in the specified + * address_space corresponding to the specified page range in the underlying + * file. + * * @mapping: the address space containing mmaps to be unmapped. * @holebegin: byte in first page to unmap, relative to the start of * the underlying file. This will be rounded down to a PAGE_SIZE @@ -2371,19 +2322,16 @@ void unmap_mapping_range(struct address_space *mapping, } details.check_mapping = even_cows? NULL: mapping; - details.nonlinear_vma = NULL; details.first_index = hba; details.last_index = hba + hlen - 1; if (details.last_index < details.first_index) details.last_index = ULONG_MAX; - i_mmap_lock_read(mapping); + i_mmap_lock_write(mapping); if (unlikely(!RB_EMPTY_ROOT(&mapping->i_mmap))) unmap_mapping_range_tree(&mapping->i_mmap, &details); - if (unlikely(!list_empty(&mapping->i_mmap_nonlinear))) - unmap_mapping_range_list(&mapping->i_mmap_nonlinear, &details); - i_mmap_unlock_read(mapping); + i_mmap_unlock_write(mapping); } EXPORT_SYMBOL(unmap_mapping_range); @@ -2593,7 +2541,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (prev && prev->vm_end == address) return prev->vm_flags & VM_GROWSDOWN ? 0 : -ENOMEM; - expand_downwards(vma, address - PAGE_SIZE); + return expand_downwards(vma, address - PAGE_SIZE); } if ((vma->vm_flags & VM_GROWSUP) && address + PAGE_SIZE == vma->vm_end) { struct vm_area_struct *next = vma->vm_next; @@ -2602,7 +2550,7 @@ static inline int check_stack_guard_page(struct vm_area_struct *vma, unsigned lo if (next && next->vm_start == address + PAGE_SIZE) return next->vm_flags & VM_GROWSUP ? 0 : -ENOMEM; - expand_upwards(vma, address + PAGE_SIZE); + return expand_upwards(vma, address + PAGE_SIZE); } return 0; } @@ -2625,7 +2573,7 @@ static int do_anonymous_page(struct mm_struct *mm, struct vm_area_struct *vma, /* Check if we need to add a guard page to the stack */ if (check_stack_guard_page(vma, address) < 0) - return VM_FAULT_SIGBUS; + return VM_FAULT_SIGSEGV; /* Use the zero-page for reads */ if (!(flags & FAULT_FLAG_WRITE) && !mm_forbids_zeropage(mm)) { @@ -2743,8 +2691,6 @@ void do_set_pte(struct vm_area_struct *vma, unsigned long address, entry = mk_pte(page, vma->vm_page_prot); if (write) entry = maybe_mkwrite(pte_mkdirty(entry), vma); - else if (pte_file(*pte) && pte_file_soft_dirty(*pte)) - entry = pte_mksoft_dirty(entry); if (anon) { inc_mm_counter_fast(vma->vm_mm, MM_ANONPAGES); page_add_new_anon_rmap(page, vma, address); @@ -2879,8 +2825,7 @@ static int do_read_fault(struct mm_struct *mm, struct vm_area_struct *vma, * if page by the offset is not ready to be mapped (cold cache or * something). */ - if (vma->vm_ops->map_pages && !(flags & FAULT_FLAG_NONLINEAR) && - fault_around_bytes >> PAGE_SHIFT > 1) { + if (vma->vm_ops->map_pages && fault_around_bytes >> PAGE_SHIFT > 1) { pte = pte_offset_map_lock(mm, pmd, address, &ptl); do_fault_around(vma, address, pte, pgoff, flags); if (!pte_same(*pte, orig_pte)) @@ -3012,8 +2957,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, balance_dirty_pages_ratelimited(mapping); } - /* file_update_time outside page_lock */ - if (vma->vm_file && !vma->vm_ops->page_mkwrite) + if (!vma->vm_ops->page_mkwrite) file_update_time(vma->vm_file); return ret; @@ -3025,7 +2969,7 @@ static int do_shared_fault(struct mm_struct *mm, struct vm_area_struct *vma, * The mmap_sem may have been released depending on flags and our * return value. See filemap_fault() and __lock_page_or_retry(). */ -static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, +static int do_fault(struct mm_struct *mm, struct vm_area_struct *vma, unsigned long address, pte_t *page_table, pmd_t *pmd, unsigned int flags, pte_t orig_pte) { @@ -3042,46 +2986,6 @@ static int do_linear_fault(struct mm_struct *mm, struct vm_area_struct *vma, return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); } -/* - * Fault of a previously existing named mapping. Repopulate the pte - * from the encoded file_pte if possible. This enables swappable - * nonlinear vmas. - * - * We enter with non-exclusive mmap_sem (to exclude vma changes, - * but allow concurrent faults), and pte mapped but not yet locked. - * We return with pte unmapped and unlocked. - * The mmap_sem may have been released depending on flags and our - * return value. See filemap_fault() and __lock_page_or_retry(). - */ -static int do_nonlinear_fault(struct mm_struct *mm, struct vm_area_struct *vma, - unsigned long address, pte_t *page_table, pmd_t *pmd, - unsigned int flags, pte_t orig_pte) -{ - pgoff_t pgoff; - - flags |= FAULT_FLAG_NONLINEAR; - - if (!pte_unmap_same(mm, pmd, page_table, orig_pte)) - return 0; - - if (unlikely(!(vma->vm_flags & VM_NONLINEAR))) { - /* - * Page table corrupted: show pte and kill process. - */ - print_bad_pte(vma, address, orig_pte, NULL); - return VM_FAULT_SIGBUS; - } - - pgoff = pte_to_pgoff(orig_pte); - if (!(flags & FAULT_FLAG_WRITE)) - return do_read_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - if (!(vma->vm_flags & VM_SHARED)) - return do_cow_fault(mm, vma, address, pmd, pgoff, flags, - orig_pte); - return do_shared_fault(mm, vma, address, pmd, pgoff, flags, orig_pte); -} - static int numa_migrate_prep(struct page *page, struct vm_area_struct *vma, unsigned long addr, int page_nid, int *flags) @@ -3209,15 +3113,12 @@ static int handle_pte_fault(struct mm_struct *mm, if (pte_none(entry)) { if (vma->vm_ops) { if (likely(vma->vm_ops->fault)) - return do_linear_fault(mm, vma, address, - pte, pmd, flags, entry); + return do_fault(mm, vma, address, pte, + pmd, flags, entry); } return do_anonymous_page(mm, vma, address, pte, pmd, flags); } - if (pte_file(entry)) - return do_nonlinear_fault(mm, vma, address, - pte, pmd, flags, entry); return do_swap_page(mm, vma, address, pte, pmd, flags, entry); } diff --git a/mm/migrate.c b/mm/migrate.c index 344cdf6..6e284bc 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -179,37 +179,6 @@ out: } /* - * Congratulations to trinity for discovering this bug. - * mm/fremap.c's remap_file_pages() accepts any range within a single vma to - * convert that vma to VM_NONLINEAR; and generic_file_remap_pages() will then - * replace the specified range by file ptes throughout (maybe populated after). - * If page migration finds a page within that range, while it's still located - * by vma_interval_tree rather than lost to i_mmap_nonlinear list, no problem: - * zap_pte() clears the temporary migration entry before mmap_sem is dropped. - * But if the migrating page is in a part of the vma outside the range to be - * remapped, then it will not be cleared, and remove_migration_ptes() needs to - * deal with it. Fortunately, this part of the vma is of course still linear, - * so we just need to use linear location on the nonlinear list. - */ -static int remove_linear_migration_ptes_from_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - /* hugetlbfs does not support remap_pages, so no huge pgoff worries */ - pgoff_t pgoff = page->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - unsigned long addr; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - addr = vma->vm_start + ((pgoff - vma->vm_pgoff) << PAGE_SHIFT); - if (addr >= vma->vm_start && addr < vma->vm_end) - remove_migration_pte(page, vma, addr, arg); - } - return SWAP_AGAIN; -} - -/* * Get rid of all migration entries and replace them by * references to the indicated page. */ @@ -218,7 +187,6 @@ static void remove_migration_ptes(struct page *old, struct page *new) struct rmap_walk_control rwc = { .rmap_one = remove_migration_pte, .arg = old, - .file_nonlinear = remove_linear_migration_ptes_from_nonlinear, }; rmap_walk(new, &rwc); diff --git a/mm/mincore.c b/mm/mincore.c index c8c528b..46527c0 100644 --- a/mm/mincore.c +++ b/mm/mincore.c @@ -124,17 +124,13 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, ptep = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl); do { pte_t pte = *ptep; - pgoff_t pgoff; next = addr + PAGE_SIZE; if (pte_none(pte)) mincore_unmapped_range(vma, addr, next, vec); else if (pte_present(pte)) *vec = 1; - else if (pte_file(pte)) { - pgoff = pte_to_pgoff(pte); - *vec = mincore_page(vma->vm_file->f_mapping, pgoff); - } else { /* pte is a swap entry */ + else { /* pte is a swap entry */ swp_entry_t entry = pte_to_swp_entry(pte); if (non_swap_entry(entry)) { @@ -145,9 +141,8 @@ static void mincore_pte_range(struct vm_area_struct *vma, pmd_t *pmd, *vec = 1; } else { #ifdef CONFIG_SWAP - pgoff = entry.val; *vec = mincore_page(swap_address_space(entry), - pgoff); + entry.val); #else WARN_ON(1); *vec = 1; @@ -243,10 +243,7 @@ static void __remove_shared_vm_struct(struct vm_area_struct *vma, mapping_unmap_writable(mapping); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - list_del_init(&vma->shared.nonlinear); - else - vma_interval_tree_remove(vma, &mapping->i_mmap); + vma_interval_tree_remove(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } @@ -649,10 +646,7 @@ static void __vma_link_file(struct vm_area_struct *vma) atomic_inc(&mapping->i_mmap_writable); flush_dcache_mmap_lock(mapping); - if (unlikely(vma->vm_flags & VM_NONLINEAR)) - vma_nonlinear_insert(vma, &mapping->i_mmap_nonlinear); - else - vma_interval_tree_insert(vma, &mapping->i_mmap); + vma_interval_tree_insert(vma, &mapping->i_mmap); flush_dcache_mmap_unlock(mapping); } } @@ -778,23 +772,22 @@ again: remove_next = 1 + (end > next->vm_end); if (exporter && exporter->anon_vma && !importer->anon_vma) { int error; + importer->anon_vma = exporter->anon_vma; error = anon_vma_clone(importer, exporter); - if (error) + if (error) { + importer->anon_vma = NULL; return error; - importer->anon_vma = exporter->anon_vma; + } } } if (file) { mapping = file->f_mapping; - if (!(vma->vm_flags & VM_NONLINEAR)) { - root = &mapping->i_mmap; - uprobe_munmap(vma, vma->vm_start, vma->vm_end); + root = &mapping->i_mmap; + uprobe_munmap(vma, vma->vm_start, vma->vm_end); - if (adjust_next) - uprobe_munmap(next, next->vm_start, - next->vm_end); - } + if (adjust_next) + uprobe_munmap(next, next->vm_start, next->vm_end); i_mmap_lock_write(mapping); if (insert) { @@ -2099,14 +2092,17 @@ static int acct_stack_growth(struct vm_area_struct *vma, unsigned long size, uns { struct mm_struct *mm = vma->vm_mm; struct rlimit *rlim = current->signal->rlim; - unsigned long new_start; + unsigned long new_start, actual_size; /* address space limit tests */ if (!may_expand_vm(mm, grow)) return -ENOMEM; /* Stack limit test */ - if (size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) + actual_size = size; + if (size && (vma->vm_flags & (VM_GROWSUP | VM_GROWSDOWN))) + actual_size -= PAGE_SIZE; + if (actual_size > ACCESS_ONCE(rlim[RLIMIT_STACK].rlim_cur)) return -ENOMEM; /* mlock limit tests */ @@ -2629,6 +2625,75 @@ SYSCALL_DEFINE2(munmap, unsigned long, addr, size_t, len) return vm_munmap(addr, len); } + +/* + * Emulation of deprecated remap_file_pages() syscall. + */ +SYSCALL_DEFINE5(remap_file_pages, unsigned long, start, unsigned long, size, + unsigned long, prot, unsigned long, pgoff, unsigned long, flags) +{ + + struct mm_struct *mm = current->mm; + struct vm_area_struct *vma; + unsigned long populate = 0; + unsigned long ret = -EINVAL; + struct file *file; + + pr_warn_once("%s (%d) uses deprecated remap_file_pages() syscall. " + "See Documentation/vm/remap_file_pages.txt.\n", + current->comm, current->pid); + + if (prot) + return ret; + start = start & PAGE_MASK; + size = size & PAGE_MASK; + + if (start + size <= start) + return ret; + + /* Does pgoff wrap? */ + if (pgoff + (size >> PAGE_SHIFT) < pgoff) + return ret; + + down_write(&mm->mmap_sem); + vma = find_vma(mm, start); + + if (!vma || !(vma->vm_flags & VM_SHARED)) + goto out; + + if (start < vma->vm_start || start + size > vma->vm_end) + goto out; + + if (pgoff == linear_page_index(vma, start)) { + ret = 0; + goto out; + } + + prot |= vma->vm_flags & VM_READ ? PROT_READ : 0; + prot |= vma->vm_flags & VM_WRITE ? PROT_WRITE : 0; + prot |= vma->vm_flags & VM_EXEC ? PROT_EXEC : 0; + + flags &= MAP_NONBLOCK; + flags |= MAP_SHARED | MAP_FIXED | MAP_POPULATE; + if (vma->vm_flags & VM_LOCKED) { + flags |= MAP_LOCKED; + /* drop PG_Mlocked flag for over-mapped range */ + munlock_vma_pages_range(vma, start, start + size); + } + + file = get_file(vma->vm_file); + ret = do_mmap_pgoff(vma->vm_file, start, size, + prot, flags, pgoff, &populate); + fput(file); +out: + up_write(&mm->mmap_sem); + if (populate) + mm_populate(ret, populate); + if (!IS_ERR_VALUE(ret)) + ret = 0; + return ret; +} + static inline void verify_mm_writelocked(struct mm_struct *mm) { #ifdef CONFIG_DEBUG_VM @@ -3103,8 +3168,7 @@ static void vm_lock_mapping(struct mm_struct *mm, struct address_space *mapping) * * mmap_sem in write mode is required in order to block all operations * that could modify pagetables and free pages without need of - * altering the vma layout (for example populate_range() with - * nonlinear vmas). It's also needed in write mode to avoid new + * altering the vma layout. It's also needed in write mode to avoid new * anon_vmas to be associated with existing vmas. * * A single task can't take more than one mm_take_all_locks() in a row diff --git a/mm/mprotect.c b/mm/mprotect.c index ace9345..3312166 100644 --- a/mm/mprotect.c +++ b/mm/mprotect.c @@ -105,7 +105,7 @@ static unsigned long change_pte_range(struct vm_area_struct *vma, pmd_t *pmd, } if (updated) pages++; - } else if (IS_ENABLED(CONFIG_MIGRATION) && !pte_file(oldpte)) { + } else if (IS_ENABLED(CONFIG_MIGRATION)) { swp_entry_t entry = pte_to_swp_entry(oldpte); if (is_write_migration_entry(entry)) { diff --git a/mm/mremap.c b/mm/mremap.c index 17fa018..57dadc0 100644 --- a/mm/mremap.c +++ b/mm/mremap.c @@ -81,8 +81,6 @@ static pte_t move_soft_dirty_pte(pte_t pte) pte = pte_mksoft_dirty(pte); else if (is_swap_pte(pte)) pte = pte_swp_mksoft_dirty(pte); - else if (pte_file(pte)) - pte = pte_file_mksoft_dirty(pte); #endif return pte; } @@ -86,10 +86,7 @@ SYSCALL_DEFINE3(msync, unsigned long, start, size_t, len, int, flags) (vma->vm_flags & VM_SHARED)) { get_file(file); up_read(&mm->mmap_sem); - if (vma->vm_flags & VM_NONLINEAR) - error = vfs_fsync(file, 1); - else - error = vfs_fsync_range(file, fstart, fend, 1); + error = vfs_fsync_range(file, fstart, fend, 1); fput(file); if (error || start >= end) goto out; @@ -59,6 +59,7 @@ #endif void *high_memory; +EXPORT_SYMBOL(high_memory); struct page *mem_map; unsigned long max_mapnr; unsigned long highest_memmap_pfn; @@ -1983,14 +1984,6 @@ void filemap_map_pages(struct vm_area_struct *vma, struct vm_fault *vmf) } EXPORT_SYMBOL(filemap_map_pages); -int generic_file_remap_pages(struct vm_area_struct *vma, unsigned long addr, - unsigned long size, pgoff_t pgoff) -{ - BUG(); - return 0; -} -EXPORT_SYMBOL(generic_file_remap_pages); - static int __access_remote_vm(struct task_struct *tsk, struct mm_struct *mm, unsigned long addr, void *buf, int len, int write) { diff --git a/mm/page-writeback.c b/mm/page-writeback.c index d5d81f5..6f43352 100644 --- a/mm/page-writeback.c +++ b/mm/page-writeback.c @@ -1541,16 +1541,6 @@ pause: bdi_start_background_writeback(bdi); } -void set_page_dirty_balance(struct page *page) -{ - if (set_page_dirty(page)) { - struct address_space *mapping = page_mapping(page); - - if (mapping) - balance_dirty_pages_ratelimited(mapping); - } -} - static DEFINE_PER_CPU(int, bdp_ratelimits); /* @@ -2123,32 +2113,25 @@ EXPORT_SYMBOL(account_page_dirtied); * page dirty in that case, but not all the buffers. This is a "bottom-up" * dirtying, whereas __set_page_dirty_buffers() is a "top-down" dirtying. * - * Most callers have locked the page, which pins the address_space in memory. - * But zap_pte_range() does not lock the page, however in that case the - * mapping is pinned by the vma's ->vm_file reference. - * - * We take care to handle the case where the page was truncated from the - * mapping by re-checking page_mapping() inside tree_lock. + * The caller must ensure this doesn't race with truncation. Most will simply + * hold the page lock, but e.g. zap_pte_range() calls with the page mapped and + * the pte lock held, which also locks out truncation. */ int __set_page_dirty_nobuffers(struct page *page) { if (!TestSetPageDirty(page)) { struct address_space *mapping = page_mapping(page); - struct address_space *mapping2; unsigned long flags; if (!mapping) return 1; spin_lock_irqsave(&mapping->tree_lock, flags); - mapping2 = page_mapping(page); - if (mapping2) { /* Race with truncate? */ - BUG_ON(mapping2 != mapping); - WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); - account_page_dirtied(page, mapping); - radix_tree_tag_set(&mapping->page_tree, - page_index(page), PAGECACHE_TAG_DIRTY); - } + BUG_ON(page_mapping(page) != mapping); + WARN_ON_ONCE(!PagePrivate(page) && !PageUptodate(page)); + account_page_dirtied(page, mapping); + radix_tree_tag_set(&mapping->page_tree, page_index(page), + PAGECACHE_TAG_DIRTY); spin_unlock_irqrestore(&mapping->tree_lock, flags); if (mapping->host) { /* !PageAnon && !swapper_space */ @@ -2305,12 +2288,10 @@ int clear_page_dirty_for_io(struct page *page) /* * We carefully synchronise fault handlers against * installing a dirty pte and marking the page dirty - * at this point. We do this by having them hold the - * page lock at some point after installing their - * pte, but before marking the page dirty. - * Pages are always locked coming in here, so we get - * the desired exclusion. See mm/memory.c:do_wp_page() - * for more comments. + * at this point. We do this by having them hold the + * page lock while dirtying the page, and pages are + * always locked coming in here, so we get the desired + * exclusion. */ if (TestClearPageDirty(page)) { dec_zone_page_state(page, NR_FILE_DIRTY); diff --git a/mm/page_alloc.c b/mm/page_alloc.c index 7633c50..f121050 100644 --- a/mm/page_alloc.c +++ b/mm/page_alloc.c @@ -552,17 +552,15 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, return 0; if (page_is_guard(buddy) && page_order(buddy) == order) { - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - if (page_zone_id(page) != page_zone_id(buddy)) return 0; + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + return 1; } if (PageBuddy(buddy) && page_order(buddy) == order) { - VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); - /* * zone check is done late to avoid uselessly * calculating zone/node ids for pages that could @@ -571,6 +569,8 @@ static inline int page_is_buddy(struct page *page, struct page *buddy, if (page_zone_id(page) != page_zone_id(buddy)) return 0; + VM_BUG_ON_PAGE(page_count(buddy) != 0, buddy); + return 1; } return 0; @@ -2332,12 +2332,21 @@ static inline struct page * __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, struct zonelist *zonelist, enum zone_type high_zoneidx, nodemask_t *nodemask, struct zone *preferred_zone, - int classzone_idx, int migratetype) + int classzone_idx, int migratetype, unsigned long *did_some_progress) { struct page *page; - /* Acquire the per-zone oom lock for each zone */ + *did_some_progress = 0; + + if (oom_killer_disabled) + return NULL; + + /* + * Acquire the per-zone oom lock for each zone. If that + * fails, somebody else is making progress for us. + */ if (!oom_zonelist_trylock(zonelist, gfp_mask)) { + *did_some_progress = 1; schedule_timeout_uninterruptible(1); return NULL; } @@ -2363,12 +2372,18 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, goto out; if (!(gfp_mask & __GFP_NOFAIL)) { + /* Coredumps can quickly deplete all memory reserves */ + if (current->flags & PF_DUMPCORE) + goto out; /* The OOM killer will not help higher order allocs */ if (order > PAGE_ALLOC_COSTLY_ORDER) goto out; /* The OOM killer does not needlessly kill tasks for lowmem */ if (high_zoneidx < ZONE_NORMAL) goto out; + /* The OOM killer does not compensate for light reclaim */ + if (!(gfp_mask & __GFP_FS)) + goto out; /* * GFP_THISNODE contains __GFP_NORETRY and we never hit this. * Sanity check for bare calls of __GFP_THISNODE, not real OOM. @@ -2381,7 +2396,7 @@ __alloc_pages_may_oom(gfp_t gfp_mask, unsigned int order, } /* Exhausted what can be done so it's blamo time */ out_of_memory(zonelist, gfp_mask, order, nodemask, false); - + *did_some_progress = 1; out: oom_zonelist_unlock(zonelist, gfp_mask); return page; @@ -2658,7 +2673,7 @@ __alloc_pages_slowpath(gfp_t gfp_mask, unsigned int order, (gfp_mask & GFP_THISNODE) == GFP_THISNODE) goto nopage; -restart: +retry: if (!(gfp_mask & __GFP_NO_KSWAPD)) wake_all_kswapds(order, zonelist, high_zoneidx, preferred_zone, nodemask); @@ -2681,7 +2696,6 @@ restart: classzone_idx = zonelist_zone_idx(preferred_zoneref); } -rebalance: /* This is the last chance, in general, before the goto nopage. */ page = get_page_from_freelist(gfp_mask, nodemask, order, zonelist, high_zoneidx, alloc_flags & ~ALLOC_NO_WATERMARKS, @@ -2788,54 +2802,28 @@ rebalance: if (page) goto got_pg; - /* - * If we failed to make any progress reclaiming, then we are - * running out of options and have to consider going OOM - */ - if (!did_some_progress) { - if (oom_gfp_allowed(gfp_mask)) { - if (oom_killer_disabled) - goto nopage; - /* Coredumps can quickly deplete all memory reserves */ - if ((current->flags & PF_DUMPCORE) && - !(gfp_mask & __GFP_NOFAIL)) - goto nopage; - page = __alloc_pages_may_oom(gfp_mask, order, - zonelist, high_zoneidx, - nodemask, preferred_zone, - classzone_idx, migratetype); - if (page) - goto got_pg; - - if (!(gfp_mask & __GFP_NOFAIL)) { - /* - * The oom killer is not called for high-order - * allocations that may fail, so if no progress - * is being made, there are no other options and - * retrying is unlikely to help. - */ - if (order > PAGE_ALLOC_COSTLY_ORDER) - goto nopage; - /* - * The oom killer is not called for lowmem - * allocations to prevent needlessly killing - * innocent tasks. - */ - if (high_zoneidx < ZONE_NORMAL) - goto nopage; - } - - goto restart; - } - } - /* Check if we should retry the allocation */ pages_reclaimed += did_some_progress; if (should_alloc_retry(gfp_mask, order, did_some_progress, pages_reclaimed)) { + /* + * If we fail to make progress by freeing individual + * pages, but the allocation wants us to keep going, + * start OOM killing tasks. + */ + if (!did_some_progress) { + page = __alloc_pages_may_oom(gfp_mask, order, zonelist, + high_zoneidx, nodemask, + preferred_zone, classzone_idx, + migratetype,&did_some_progress); + if (page) + goto got_pg; + if (!did_some_progress) + goto nopage; + } /* Wait for some write requests to complete then retry */ wait_iff_congested(preferred_zone, BLK_RW_ASYNC, HZ/50); - goto rebalance; + goto retry; } else { /* * High-order allocations do not necessarily loop after diff --git a/mm/pagewalk.c b/mm/pagewalk.c index ad83195..b264bda 100644 --- a/mm/pagewalk.c +++ b/mm/pagewalk.c @@ -199,7 +199,10 @@ int walk_page_range(unsigned long addr, unsigned long end, */ if ((vma->vm_start <= addr) && (vma->vm_flags & VM_PFNMAP)) { - next = vma->vm_end; + if (walk->pte_hole) + err = walk->pte_hole(addr, next, walk); + if (err) + break; pgd = pgd_offset(walk->mm, next); continue; } @@ -72,6 +72,8 @@ 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->parent = anon_vma; /* * Initialise the anon_vma root to point to itself. If called * from fork, the root will be reset to the parents anon_vma. @@ -188,6 +190,8 @@ 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++; allocated = NULL; avc = NULL; } @@ -236,6 +240,14 @@ static inline void unlock_anon_vma_root(struct anon_vma *root) /* * Attach the anon_vmas from src to dst. * Returns 0 on success, -ENOMEM on failure. + * + * If dst->anon_vma is NULL this function tries to find and reuse existing + * anon_vma which has no vmas and only one child anon_vma. This prevents + * degradation of anon_vma hierarchy to endless linear chain in case of + * constantly forking task. On the other hand, an anon_vma with more than one + * child isn't reused even if there was no alive vma, thus rmap walker has a + * good chance of avoiding scanning the whole hierarchy when it searches where + * page is mapped. */ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) { @@ -256,7 +268,21 @@ int anon_vma_clone(struct vm_area_struct *dst, struct vm_area_struct *src) anon_vma = pavc->anon_vma; root = lock_anon_vma_root(root, anon_vma); 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. + * + * Do not chose parent anon_vma, otherwise first child + * will always reuse it. 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) + dst->anon_vma = anon_vma; } + if (dst->anon_vma) + dst->anon_vma->degree++; unlock_anon_vma_root(root); return 0; @@ -280,6 +306,9 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) if (!pvma->anon_vma) return 0; + /* Drop inherited anon_vma, we'll reuse existing or allocate new. */ + vma->anon_vma = NULL; + /* * First, attach the new VMA to the parent VMA's anon_vmas, * so rmap can find non-COWed pages in child processes. @@ -288,6 +317,10 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) if (error) return error; + /* An existing anon_vma has been reused, all done then. */ + if (vma->anon_vma) + return 0; + /* Then add our own anon_vma. */ anon_vma = anon_vma_alloc(); if (!anon_vma) @@ -301,6 +334,7 @@ int anon_vma_fork(struct vm_area_struct *vma, struct vm_area_struct *pvma) * lock any of the anon_vmas in this anon_vma tree. */ anon_vma->root = pvma->anon_vma->root; + anon_vma->parent = pvma->anon_vma; /* * With refcounts, an anon_vma can stay around longer than the * process it belongs to. The root anon_vma needs to be pinned until @@ -311,6 +345,7 @@ 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_unlock_write(anon_vma); return 0; @@ -341,12 +376,16 @@ void unlink_anon_vmas(struct vm_area_struct *vma) * Leave empty anon_vmas on the list - we'll need * to free them outside the lock. */ - if (RB_EMPTY_ROOT(&anon_vma->rb_root)) + if (RB_EMPTY_ROOT(&anon_vma->rb_root)) { + anon_vma->parent->degree--; continue; + } list_del(&avc->same_vma); anon_vma_chain_free(avc); } + if (vma->anon_vma) + vma->anon_vma->degree--; unlock_anon_vma_root(root); /* @@ -357,6 +396,7 @@ 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; + BUG_ON(anon_vma->degree); put_anon_vma(anon_vma); list_del(&avc->same_vma); @@ -550,9 +590,8 @@ unsigned long page_address_in_vma(struct page *page, struct vm_area_struct *vma) if (!vma->anon_vma || !page__anon_vma || vma->anon_vma->root != page__anon_vma->root) return -EFAULT; - } else if (page->mapping && !(vma->vm_flags & VM_NONLINEAR)) { - if (!vma->vm_file || - vma->vm_file->f_mapping != page->mapping) + } else if (page->mapping) { + if (!vma->vm_file || vma->vm_file->f_mapping != page->mapping) return -EFAULT; } else return -EFAULT; @@ -1234,7 +1273,6 @@ static int try_to_unmap_one(struct page *page, struct vm_area_struct *vma, if (pte_soft_dirty(pteval)) swp_pte = pte_swp_mksoft_dirty(swp_pte); set_pte_at(mm, address, pte, swp_pte); - BUG_ON(pte_file(*pte)); } else if (IS_ENABLED(CONFIG_MIGRATION) && (flags & TTU_MIGRATION)) { /* Establish migration entry for a file page */ @@ -1276,211 +1314,6 @@ out_mlock: return ret; } -/* - * objrmap doesn't work for nonlinear VMAs because the assumption that - * offset-into-file correlates with offset-into-virtual-addresses does not hold. - * Consequently, given a particular page and its ->index, we cannot locate the - * ptes which are mapping that page without an exhaustive linear search. - * - * So what this code does is a mini "virtual scan" of each nonlinear VMA which - * maps the file to which the target page belongs. The ->vm_private_data field - * holds the current cursor into that scan. Successive searches will circulate - * around the vma's virtual address space. - * - * So as more replacement pressure is applied to the pages in a nonlinear VMA, - * more scanning pressure is placed against them as well. Eventually pages - * will become fully unmapped and are eligible for eviction. - * - * For very sparsely populated VMAs this is a little inefficient - chances are - * there there won't be many ptes located within the scan cluster. In this case - * maybe we could scan further - to the end of the pte page, perhaps. - * - * Mlocked pages: check VM_LOCKED under mmap_sem held for read, if we can - * acquire it without blocking. If vma locked, mlock the pages in the cluster, - * rather than unmapping them. If we encounter the "check_page" that vmscan is - * trying to unmap, return SWAP_MLOCK, else default SWAP_AGAIN. - */ -#define CLUSTER_SIZE min(32*PAGE_SIZE, PMD_SIZE) -#define CLUSTER_MASK (~(CLUSTER_SIZE - 1)) - -static int try_to_unmap_cluster(unsigned long cursor, unsigned int *mapcount, - struct vm_area_struct *vma, struct page *check_page) -{ - struct mm_struct *mm = vma->vm_mm; - pmd_t *pmd; - pte_t *pte; - pte_t pteval; - spinlock_t *ptl; - struct page *page; - unsigned long address; - unsigned long mmun_start; /* For mmu_notifiers */ - unsigned long mmun_end; /* For mmu_notifiers */ - unsigned long end; - int ret = SWAP_AGAIN; - int locked_vma = 0; - - address = (vma->vm_start + cursor) & CLUSTER_MASK; - end = address + CLUSTER_SIZE; - if (address < vma->vm_start) - address = vma->vm_start; - if (end > vma->vm_end) - end = vma->vm_end; - - pmd = mm_find_pmd(mm, address); - if (!pmd) - return ret; - - mmun_start = address; - mmun_end = end; - mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); - - /* - * If we can acquire the mmap_sem for read, and vma is VM_LOCKED, - * keep the sem while scanning the cluster for mlocking pages. - */ - if (down_read_trylock(&vma->vm_mm->mmap_sem)) { - locked_vma = (vma->vm_flags & VM_LOCKED); - if (!locked_vma) - up_read(&vma->vm_mm->mmap_sem); /* don't need it */ - } - - pte = pte_offset_map_lock(mm, pmd, address, &ptl); - - /* Update high watermark before we lower rss */ - update_hiwater_rss(mm); - - for (; address < end; pte++, address += PAGE_SIZE) { - if (!pte_present(*pte)) - continue; - page = vm_normal_page(vma, address, *pte); - BUG_ON(!page || PageAnon(page)); - - if (locked_vma) { - if (page == check_page) { - /* we know we have check_page locked */ - mlock_vma_page(page); - ret = SWAP_MLOCK; - } else if (trylock_page(page)) { - /* - * If we can lock the page, perform mlock. - * Otherwise leave the page alone, it will be - * eventually encountered again later. - */ - mlock_vma_page(page); - unlock_page(page); - } - continue; /* don't unmap */ - } - - /* - * No need for _notify because we're within an - * mmu_notifier_invalidate_range_ {start|end} scope. - */ - if (ptep_clear_flush_young(vma, address, pte)) - continue; - - /* Nuke the page table entry. */ - flush_cache_page(vma, address, pte_pfn(*pte)); - pteval = ptep_clear_flush_notify(vma, address, pte); - - /* If nonlinear, store the file page offset in the pte. */ - if (page->index != linear_page_index(vma, address)) { - pte_t ptfile = pgoff_to_pte(page->index); - if (pte_soft_dirty(pteval)) - ptfile = pte_file_mksoft_dirty(ptfile); - set_pte_at(mm, address, pte, ptfile); - } - - /* Move the dirty bit to the physical page now the pte is gone. */ - if (pte_dirty(pteval)) - set_page_dirty(page); - - page_remove_rmap(page); - page_cache_release(page); - dec_mm_counter(mm, MM_FILEPAGES); - (*mapcount)--; - } - pte_unmap_unlock(pte - 1, ptl); - mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); - if (locked_vma) - up_read(&vma->vm_mm->mmap_sem); - return ret; -} - -static int try_to_unmap_nonlinear(struct page *page, - struct address_space *mapping, void *arg) -{ - struct vm_area_struct *vma; - int ret = SWAP_AGAIN; - unsigned long cursor; - unsigned long max_nl_cursor = 0; - unsigned long max_nl_size = 0; - unsigned int mapcount; - - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - if (cursor > max_nl_cursor) - max_nl_cursor = cursor; - cursor = vma->vm_end - vma->vm_start; - if (cursor > max_nl_size) - max_nl_size = cursor; - } - - if (max_nl_size == 0) { /* all nonlinears locked or reserved ? */ - return SWAP_FAIL; - } - - /* - * We don't try to search for this page in the nonlinear vmas, - * and page_referenced wouldn't have found it anyway. Instead - * just walk the nonlinear vmas trying to age and unmap some. - * The mapcount of the page we came in with is irrelevant, - * but even so use it as a guide to how hard we should try? - */ - mapcount = page_mapcount(page); - if (!mapcount) - return ret; - - cond_resched(); - - max_nl_size = (max_nl_size + CLUSTER_SIZE - 1) & CLUSTER_MASK; - if (max_nl_cursor == 0) - max_nl_cursor = CLUSTER_SIZE; - - do { - list_for_each_entry(vma, - &mapping->i_mmap_nonlinear, shared.nonlinear) { - - cursor = (unsigned long) vma->vm_private_data; - while (cursor < max_nl_cursor && - cursor < vma->vm_end - vma->vm_start) { - if (try_to_unmap_cluster(cursor, &mapcount, - vma, page) == SWAP_MLOCK) - ret = SWAP_MLOCK; - cursor += CLUSTER_SIZE; - vma->vm_private_data = (void *) cursor; - if ((int)mapcount <= 0) - return ret; - } - vma->vm_private_data = (void *) max_nl_cursor; - } - cond_resched(); - max_nl_cursor += CLUSTER_SIZE; - } while (max_nl_cursor <= max_nl_size); - - /* - * Don't loop forever (perhaps all the remaining pages are - * in locked vmas). Reset cursor on all unreserved nonlinear - * vmas, now forgetting on which ones it had fallen behind. - */ - list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.nonlinear) - vma->vm_private_data = NULL; - - return ret; -} - bool is_vma_temporary_stack(struct vm_area_struct *vma) { int maybe_stack = vma->vm_flags & (VM_GROWSDOWN | VM_GROWSUP); @@ -1526,7 +1359,6 @@ int try_to_unmap(struct page *page, enum ttu_flags flags) .rmap_one = try_to_unmap_one, .arg = (void *)flags, .done = page_not_mapped, - .file_nonlinear = try_to_unmap_nonlinear, .anon_lock = page_lock_anon_vma_read, }; @@ -1572,12 +1404,6 @@ int try_to_munlock(struct page *page) .rmap_one = try_to_unmap_one, .arg = (void *)TTU_MUNLOCK, .done = page_not_mapped, - /* - * We don't bother to try to find the munlocked page in - * nonlinears. It's costly. Instead, later, page reclaim logic - * may call try_to_unmap() and recover PG_mlocked lazily. - */ - .file_nonlinear = NULL, .anon_lock = page_lock_anon_vma_read, }; @@ -1708,13 +1534,6 @@ static int rmap_walk_file(struct page *page, struct rmap_walk_control *rwc) goto done; } - if (!rwc->file_nonlinear) - goto done; - - if (list_empty(&mapping->i_mmap_nonlinear)) - goto done; - - ret = rwc->file_nonlinear(page, mapping, rwc->arg); done: i_mmap_unlock_read(mapping); return ret; @@ -1013,7 +1013,7 @@ static int shmem_replace_page(struct page **pagep, gfp_t gfp, */ oldpage = newpage; } else { - mem_cgroup_migrate(oldpage, newpage, false); + mem_cgroup_migrate(oldpage, newpage, true); lru_cache_add_anon(newpage); *pagep = newpage; } @@ -3201,7 +3201,6 @@ static const struct vm_operations_struct shmem_vm_ops = { .set_policy = shmem_set_policy, .get_policy = shmem_get_policy, #endif - .remap_pages = generic_file_remap_pages, }; static struct dentry *shmem_mount(struct file_system_type *fs_type, @@ -235,7 +235,7 @@ static __always_inline int memcg_charge_slab(struct kmem_cache *s, return 0; if (is_root_cache(s)) return 0; - return __memcg_charge_slab(s, gfp, order); + return memcg_charge_kmem(s->memcg_params->memcg, gfp, 1 << order); } static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) @@ -244,7 +244,7 @@ static __always_inline void memcg_uncharge_slab(struct kmem_cache *s, int order) return; if (is_root_cache(s)) return; - __memcg_uncharge_slab(s, order); + memcg_uncharge_kmem(s->memcg_params->memcg, 1 << order); } #else static inline bool is_root_cache(struct kmem_cache *s) diff --git a/mm/slab_common.c b/mm/slab_common.c index e03dd6f..6e1e4cf 100644 --- a/mm/slab_common.c +++ b/mm/slab_common.c @@ -331,7 +331,7 @@ out: out_free_cache: memcg_free_cache_params(s); - kfree(s); + kmem_cache_free(kmem_cache, s); goto out; } @@ -425,21 +425,64 @@ out_unlock: } EXPORT_SYMBOL(kmem_cache_create); +static int do_kmem_cache_shutdown(struct kmem_cache *s, + struct list_head *release, bool *need_rcu_barrier) +{ + if (__kmem_cache_shutdown(s) != 0) { + printk(KERN_ERR "kmem_cache_destroy %s: " + "Slab cache still has objects\n", s->name); + dump_stack(); + return -EBUSY; + } + + if (s->flags & SLAB_DESTROY_BY_RCU) + *need_rcu_barrier = true; + +#ifdef CONFIG_MEMCG_KMEM + if (!is_root_cache(s)) { + struct kmem_cache *root_cache = s->memcg_params->root_cache; + int memcg_id = memcg_cache_id(s->memcg_params->memcg); + + BUG_ON(root_cache->memcg_params->memcg_caches[memcg_id] != s); + root_cache->memcg_params->memcg_caches[memcg_id] = NULL; + } +#endif + list_move(&s->list, release); + return 0; +} + +static void do_kmem_cache_release(struct list_head *release, + bool need_rcu_barrier) +{ + struct kmem_cache *s, *s2; + + if (need_rcu_barrier) + rcu_barrier(); + + list_for_each_entry_safe(s, s2, release, list) { +#ifdef SLAB_SUPPORTS_SYSFS + sysfs_slab_remove(s); +#else + slab_kmem_cache_release(s); +#endif + } +} + #ifdef CONFIG_MEMCG_KMEM /* * memcg_create_kmem_cache - Create a cache for a memory cgroup. * @memcg: The memory cgroup the new cache is for. * @root_cache: The parent of the new cache. - * @memcg_name: The name of the memory cgroup (used for naming the new cache). * * This function attempts to create a kmem cache that will serve allocation * requests going from @memcg to @root_cache. The new cache inherits properties * from its parent. */ -struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, - struct kmem_cache *root_cache, - const char *memcg_name) +void memcg_create_kmem_cache(struct mem_cgroup *memcg, + struct kmem_cache *root_cache) { + static char memcg_name_buf[NAME_MAX + 1]; /* protected by slab_mutex */ + int memcg_id = memcg_cache_id(memcg); struct kmem_cache *s = NULL; char *cache_name; @@ -448,8 +491,18 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, mutex_lock(&slab_mutex); + /* + * Since per-memcg caches are created asynchronously on first + * allocation (see memcg_kmem_get_cache()), several threads can try to + * create the same cache, but only one of them may succeed. + */ + if (cache_from_memcg_idx(root_cache, memcg_id)) + goto out_unlock; + + cgroup_name(mem_cgroup_css(memcg)->cgroup, + memcg_name_buf, sizeof(memcg_name_buf)); cache_name = kasprintf(GFP_KERNEL, "%s(%d:%s)", root_cache->name, - memcg_cache_id(memcg), memcg_name); + memcg_cache_id(memcg), memcg_name_buf); if (!cache_name) goto out_unlock; @@ -457,49 +510,73 @@ struct kmem_cache *memcg_create_kmem_cache(struct mem_cgroup *memcg, root_cache->size, root_cache->align, root_cache->flags, root_cache->ctor, memcg, root_cache); + /* + * If we could not create a memcg cache, do not complain, because + * that's not critical at all as we can always proceed with the root + * cache. + */ if (IS_ERR(s)) { kfree(cache_name); - s = NULL; + goto out_unlock; } + /* + * Since readers won't lock (see cache_from_memcg_idx()), we need a + * barrier here to ensure nobody will see the kmem_cache partially + * initialized. + */ + smp_wmb(); + root_cache->memcg_params->memcg_caches[memcg_id] = s; + out_unlock: mutex_unlock(&slab_mutex); put_online_mems(); put_online_cpus(); - - return s; } -static int memcg_cleanup_cache_params(struct kmem_cache *s) +void memcg_destroy_kmem_caches(struct mem_cgroup *memcg) { - int rc; + LIST_HEAD(release); + bool need_rcu_barrier = false; + struct kmem_cache *s, *s2; - if (!s->memcg_params || - !s->memcg_params->is_root_cache) - return 0; + get_online_cpus(); + get_online_mems(); - mutex_unlock(&slab_mutex); - rc = __memcg_cleanup_cache_params(s); mutex_lock(&slab_mutex); + list_for_each_entry_safe(s, s2, &slab_caches, list) { + if (is_root_cache(s) || s->memcg_params->memcg != memcg) + continue; + /* + * The cgroup is about to be freed and therefore has no charges + * left. Hence, all its caches must be empty by now. + */ + BUG_ON(do_kmem_cache_shutdown(s, &release, &need_rcu_barrier)); + } + mutex_unlock(&slab_mutex); - return rc; -} -#else -static int memcg_cleanup_cache_params(struct kmem_cache *s) -{ - return 0; + put_online_mems(); + put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } #endif /* CONFIG_MEMCG_KMEM */ void slab_kmem_cache_release(struct kmem_cache *s) { + memcg_free_cache_params(s); kfree(s->name); kmem_cache_free(kmem_cache, s); } void kmem_cache_destroy(struct kmem_cache *s) { + int i; + LIST_HEAD(release); + bool need_rcu_barrier = false; + bool busy = false; + get_online_cpus(); get_online_mems(); @@ -509,35 +586,23 @@ void kmem_cache_destroy(struct kmem_cache *s) if (s->refcount) goto out_unlock; - if (memcg_cleanup_cache_params(s) != 0) - goto out_unlock; + for_each_memcg_cache_index(i) { + struct kmem_cache *c = cache_from_memcg_idx(s, i); - if (__kmem_cache_shutdown(s) != 0) { - printk(KERN_ERR "kmem_cache_destroy %s: " - "Slab cache still has objects\n", s->name); - dump_stack(); - goto out_unlock; + if (c && do_kmem_cache_shutdown(c, &release, &need_rcu_barrier)) + busy = true; } - list_del(&s->list); - - mutex_unlock(&slab_mutex); - if (s->flags & SLAB_DESTROY_BY_RCU) - rcu_barrier(); - - memcg_free_cache_params(s); -#ifdef SLAB_SUPPORTS_SYSFS - sysfs_slab_remove(s); -#else - slab_kmem_cache_release(s); -#endif - goto out; + if (!busy) + do_kmem_cache_shutdown(s, &release, &need_rcu_barrier); out_unlock: mutex_unlock(&slab_mutex); -out: + put_online_mems(); put_online_cpus(); + + do_kmem_cache_release(&release, need_rcu_barrier); } EXPORT_SYMBOL(kmem_cache_destroy); @@ -2398,13 +2398,24 @@ redo: * reading from one cpu area. That does not matter as long * as we end up on the original cpu again when doing the cmpxchg. * - * Preemption is disabled for the retrieval of the tid because that - * must occur from the current processor. We cannot allow rescheduling - * on a different processor between the determination of the pointer - * and the retrieval of the tid. + * We should guarantee that tid and kmem_cache are retrieved on + * the same cpu. It could be different if CONFIG_PREEMPT so we need + * to check if it is matched or not. */ - preempt_disable(); - c = this_cpu_ptr(s->cpu_slab); + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); + + /* + * Irqless object alloc/free algorithm used here depends on sequence + * of fetching cpu_slab's data. tid should be fetched before anything + * on c to guarantee that object and page associated with previous tid + * won't be used with current tid. If we fetch tid first, object and + * page could be one associated with next tid and our alloc/free + * request will be failed. In this case, we will retry. So, no problem. + */ + barrier(); /* * The transaction ids are globally unique per cpu and per operation on @@ -2412,8 +2423,6 @@ redo: * occurs on the right processor and that there was no operation on the * linked list in between. */ - tid = c->tid; - preempt_enable(); object = c->freelist; page = c->page; @@ -2512,7 +2521,7 @@ EXPORT_SYMBOL(kmem_cache_alloc_node_trace); #endif /* - * Slow patch handling. This may still be called frequently since objects + * Slow path handling. This may still be called frequently since objects * have a longer lifetime than the cpu slabs in most processing loads. * * So we still attempt to reduce cache line usage. Just take the slab @@ -2659,11 +2668,13 @@ redo: * data is retrieved via this pointer. If we are on the same cpu * during the cmpxchg then the free will succedd. */ - preempt_disable(); - c = this_cpu_ptr(s->cpu_slab); + do { + tid = this_cpu_read(s->cpu_slab->tid); + c = raw_cpu_ptr(s->cpu_slab); + } while (IS_ENABLED(CONFIG_PREEMPT) && unlikely(tid != c->tid)); - tid = c->tid; - preempt_enable(); + /* Same with comment on barrier() in slab_alloc_node() */ + barrier(); if (likely(page == c->page)) { set_freepointer(s, object, c->freelist); @@ -1140,10 +1140,8 @@ void __init swap_setup(void) if (bdi_init(swapper_spaces[0].backing_dev_info)) panic("Failed to init swap bdi"); - for (i = 0; i < MAX_SWAPFILES; i++) { + for (i = 0; i < MAX_SWAPFILES; i++) spin_lock_init(&swapper_spaces[i].tree_lock); - INIT_LIST_HEAD(&swapper_spaces[i].i_mmap_nonlinear); - } #endif /* Use a smaller cluster for small-memory machines */ diff --git a/mm/vmscan.c b/mm/vmscan.c index bd9a72b..dcd90c8 100644 --- a/mm/vmscan.c +++ b/mm/vmscan.c @@ -2656,7 +2656,7 @@ static bool throttle_direct_reclaim(gfp_t gfp_mask, struct zonelist *zonelist, * should make reasonable progress. */ for_each_zone_zonelist_nodemask(zone, z, zonelist, - gfp_mask, nodemask) { + gfp_zone(gfp_mask), nodemask) { if (zone_idx(zone) > ZONE_NORMAL) continue; @@ -2921,18 +2921,20 @@ static bool prepare_kswapd_sleep(pg_data_t *pgdat, int order, long remaining, return false; /* - * There is a potential race between when kswapd checks its watermarks - * and a process gets throttled. There is also a potential race if - * processes get throttled, kswapd wakes, a large process exits therby - * balancing the zones that causes kswapd to miss a wakeup. If kswapd - * is going to sleep, no process should be sleeping on pfmemalloc_wait - * so wake them now if necessary. If necessary, processes will wake - * kswapd and get throttled again + * The throttled processes are normally woken up in balance_pgdat() as + * soon as pfmemalloc_watermark_ok() is true. But there is a potential + * race between when kswapd checks the watermarks and a process gets + * throttled. There is also a potential race if processes get + * throttled, kswapd wakes, a large process exits thereby balancing the + * zones, which causes kswapd to exit balance_pgdat() before reaching + * the wake up checks. If kswapd is going to sleep, no process should + * be sleeping on pfmemalloc_wait, so wake them now if necessary. If + * the wake up is premature, processes will wake kswapd and get + * throttled again. The difference from wake ups in balance_pgdat() is + * that here we are under prepare_to_wait(). */ - if (waitqueue_active(&pgdat->pfmemalloc_wait)) { - wake_up(&pgdat->pfmemalloc_wait); - return false; - } + if (waitqueue_active(&pgdat->pfmemalloc_wait)) + wake_up_all(&pgdat->pfmemalloc_wait); return pgdat_balanced(pgdat, order, classzone_idx); } diff --git a/mm/vmstat.c b/mm/vmstat.c index 1284f89..9943e5f 100644 --- a/mm/vmstat.c +++ b/mm/vmstat.c @@ -17,6 +17,9 @@ #include <linux/cpu.h> #include <linux/cpumask.h> #include <linux/vmstat.h> +#include <linux/proc_fs.h> +#include <linux/seq_file.h> +#include <linux/debugfs.h> #include <linux/sched.h> #include <linux/math64.h> #include <linux/writeback.h> @@ -670,66 +673,6 @@ int fragmentation_index(struct zone *zone, unsigned int order) } #endif -#if defined(CONFIG_PROC_FS) || defined(CONFIG_COMPACTION) -#include <linux/proc_fs.h> -#include <linux/seq_file.h> - -static char * const migratetype_names[MIGRATE_TYPES] = { - "Unmovable", - "Reclaimable", - "Movable", - "Reserve", -#ifdef CONFIG_CMA - "CMA", -#endif -#ifdef CONFIG_MEMORY_ISOLATION - "Isolate", -#endif -}; - -static void *frag_start(struct seq_file *m, loff_t *pos) -{ - pg_data_t *pgdat; - loff_t node = *pos; - for (pgdat = first_online_pgdat(); - pgdat && node; - pgdat = next_online_pgdat(pgdat)) - --node; - - return pgdat; -} - -static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) -{ - pg_data_t *pgdat = (pg_data_t *)arg; - - (*pos)++; - return next_online_pgdat(pgdat); -} - -static void frag_stop(struct seq_file *m, void *arg) -{ -} - -/* Walk all the zones in a node and print using a callback */ -static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, - void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) -{ - struct zone *zone; - struct zone *node_zones = pgdat->node_zones; - unsigned long flags; - - for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { - if (!populated_zone(zone)) - continue; - - spin_lock_irqsave(&zone->lock, flags); - print(m, pgdat, zone); - spin_unlock_irqrestore(&zone->lock, flags); - } -} -#endif - #if defined(CONFIG_PROC_FS) || defined(CONFIG_SYSFS) || defined(CONFIG_NUMA) #ifdef CONFIG_ZONE_DMA #define TEXT_FOR_DMA(xx) xx "_dma", @@ -907,7 +850,66 @@ const char * const vmstat_text[] = { #endif /* CONFIG_PROC_FS || CONFIG_SYSFS || CONFIG_NUMA */ +#if (defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION)) || \ + defined(CONFIG_PROC_FS) +static void *frag_start(struct seq_file *m, loff_t *pos) +{ + pg_data_t *pgdat; + loff_t node = *pos; + + for (pgdat = first_online_pgdat(); + pgdat && node; + pgdat = next_online_pgdat(pgdat)) + --node; + + return pgdat; +} + +static void *frag_next(struct seq_file *m, void *arg, loff_t *pos) +{ + pg_data_t *pgdat = (pg_data_t *)arg; + + (*pos)++; + return next_online_pgdat(pgdat); +} + +static void frag_stop(struct seq_file *m, void *arg) +{ +} + +/* Walk all the zones in a node and print using a callback */ +static void walk_zones_in_node(struct seq_file *m, pg_data_t *pgdat, + void (*print)(struct seq_file *m, pg_data_t *, struct zone *)) +{ + struct zone *zone; + struct zone *node_zones = pgdat->node_zones; + unsigned long flags; + + for (zone = node_zones; zone - node_zones < MAX_NR_ZONES; ++zone) { + if (!populated_zone(zone)) + continue; + + spin_lock_irqsave(&zone->lock, flags); + print(m, pgdat, zone); + spin_unlock_irqrestore(&zone->lock, flags); + } +} +#endif + #ifdef CONFIG_PROC_FS +static char * const migratetype_names[MIGRATE_TYPES] = { + "Unmovable", + "Reclaimable", + "Movable", + "Reserve", +#ifdef CONFIG_CMA + "CMA", +#endif +#ifdef CONFIG_MEMORY_ISOLATION + "Isolate", +#endif +}; + static void frag_show_print(struct seq_file *m, pg_data_t *pgdat, struct zone *zone) { @@ -1536,8 +1538,6 @@ static int __init setup_vmstat(void) module_init(setup_vmstat) #if defined(CONFIG_DEBUG_FS) && defined(CONFIG_COMPACTION) -#include <linux/debugfs.h> - /* * Return an index indicating how much of the available free memory is |