diff options
Diffstat (limited to 'mm/migrate.c')
| -rw-r--r-- | mm/migrate.c | 1682 |
1 files changed, 1271 insertions, 411 deletions
diff --git a/mm/migrate.c b/mm/migrate.c index 4e0eccca5e2..be6dbf995c0 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -9,11 +9,11 @@ * IWAMOTO Toshihiro <iwamoto@valinux.co.jp> * Hirokazu Takahashi <taka@valinux.co.jp> * Dave Hansen <haveblue@us.ibm.com> - * Christoph Lameter <clameter@sgi.com> + * Christoph Lameter */ #include <linux/migrate.h> -#include <linux/module.h> +#include <linux/export.h> #include <linux/swap.h> #include <linux/swapops.h> #include <linux/pagemap.h> @@ -21,6 +21,7 @@ #include <linux/mm_inline.h> #include <linux/nsproxy.h> #include <linux/pagevec.h> +#include <linux/ksm.h> #include <linux/rmap.h> #include <linux/topology.h> #include <linux/cpu.h> @@ -30,44 +31,24 @@ #include <linux/vmalloc.h> #include <linux/security.h> #include <linux/memcontrol.h> +#include <linux/syscalls.h> +#include <linux/hugetlb.h> +#include <linux/hugetlb_cgroup.h> +#include <linux/gfp.h> +#include <linux/balloon_compaction.h> +#include <linux/mmu_notifier.h> -#include "internal.h" +#include <asm/tlbflush.h> -#define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) +#define CREATE_TRACE_POINTS +#include <trace/events/migrate.h> -/* - * Isolate one page from the LRU lists. If successful put it onto - * the indicated list with elevated page count. - * - * Result: - * -EBUSY: page not on LRU list - * 0: page removed from LRU list and added to the specified list. - */ -int isolate_lru_page(struct page *page, struct list_head *pagelist) -{ - int ret = -EBUSY; - - if (PageLRU(page)) { - struct zone *zone = page_zone(page); - - spin_lock_irq(&zone->lru_lock); - if (PageLRU(page) && get_page_unless_zero(page)) { - ret = 0; - ClearPageLRU(page); - if (PageActive(page)) - del_page_from_active_list(zone, page); - else - del_page_from_inactive_list(zone, page); - list_add_tail(&page->lru, pagelist); - } - spin_unlock_irq(&zone->lru_lock); - } - return ret; -} +#include "internal.h" /* * migrate_prep() needs to be called before we start compiling a list of pages - * to be migrated using isolate_lru_page(). + * to be migrated using isolate_lru_page(). If scheduling work on other CPUs is + * undesirable, use migrate_prep_local() */ int migrate_prep(void) { @@ -82,168 +63,147 @@ int migrate_prep(void) return 0; } -static inline void move_to_lru(struct page *page) +/* Do the necessary work of migrate_prep but not if it involves other CPUs */ +int migrate_prep_local(void) { - if (PageActive(page)) { - /* - * lru_cache_add_active checks that - * the PG_active bit is off. - */ - ClearPageActive(page); - lru_cache_add_active(page); - } else { - lru_cache_add(page); - } - put_page(page); + lru_add_drain(); + + return 0; } /* - * Add isolated pages on the list back to the LRU. + * Put previously isolated pages back onto the appropriate lists + * from where they were once taken off for compaction/migration. * - * returns the number of pages put back. + * This function shall be used whenever the isolated pageset has been + * built from lru, balloon, hugetlbfs page. See isolate_migratepages_range() + * and isolate_huge_page(). */ -int putback_lru_pages(struct list_head *l) +void putback_movable_pages(struct list_head *l) { struct page *page; struct page *page2; - int count = 0; list_for_each_entry_safe(page, page2, l, lru) { + if (unlikely(PageHuge(page))) { + putback_active_hugepage(page); + continue; + } list_del(&page->lru); - move_to_lru(page); - count++; + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + if (unlikely(isolated_balloon_page(page))) + balloon_page_putback(page); + else + putback_lru_page(page); } - return count; } /* * Restore a potential migration pte to a working pte entry */ -static void remove_migration_pte(struct vm_area_struct *vma, - struct page *old, struct page *new) +static int remove_migration_pte(struct page *new, struct vm_area_struct *vma, + unsigned long addr, void *old) { struct mm_struct *mm = vma->vm_mm; swp_entry_t entry; - pgd_t *pgd; - pud_t *pud; pmd_t *pmd; pte_t *ptep, pte; spinlock_t *ptl; - unsigned long addr = page_address_in_vma(new, vma); - if (addr == -EFAULT) - return; - - pgd = pgd_offset(mm, addr); - if (!pgd_present(*pgd)) - return; - - pud = pud_offset(pgd, addr); - if (!pud_present(*pud)) - return; + if (unlikely(PageHuge(new))) { + ptep = huge_pte_offset(mm, addr); + if (!ptep) + goto out; + ptl = huge_pte_lockptr(hstate_vma(vma), mm, ptep); + } else { + pmd = mm_find_pmd(mm, addr); + if (!pmd) + goto out; - pmd = pmd_offset(pud, addr); - if (!pmd_present(*pmd)) - return; + ptep = pte_offset_map(pmd, addr); - ptep = pte_offset_map(pmd, addr); + /* + * Peek to check is_swap_pte() before taking ptlock? No, we + * can race mremap's move_ptes(), which skips anon_vma lock. + */ - if (!is_swap_pte(*ptep)) { - pte_unmap(ptep); - return; - } + ptl = pte_lockptr(mm, pmd); + } - ptl = pte_lockptr(mm, pmd); spin_lock(ptl); pte = *ptep; if (!is_swap_pte(pte)) - goto out; + goto unlock; entry = pte_to_swp_entry(pte); - if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old) - goto out; - - /* - * Yes, ignore the return value from a GFP_ATOMIC mem_cgroup_charge. - * Failure is not an option here: we're now expected to remove every - * migration pte, and will cause crashes otherwise. Normally this - * is not an issue: mem_cgroup_prepare_migration bumped up the old - * page_cgroup count for safety, that's now attached to the new page, - * so this charge should just be another incrementation of the count, - * to keep in balance with rmap.c's mem_cgroup_uncharging. But if - * there's been a force_empty, those reference counts may no longer - * be reliable, and this charge can actually fail: oh well, we don't - * make the situation any worse by proceeding as if it had succeeded. - */ - mem_cgroup_charge(new, mm, GFP_ATOMIC); + if (!is_migration_entry(entry) || + migration_entry_to_page(entry) != old) + goto unlock; get_page(new); pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + if (pte_swp_soft_dirty(*ptep)) + pte = pte_mksoft_dirty(pte); if (is_write_migration_entry(entry)) pte = pte_mkwrite(pte); - flush_cache_page(vma, addr, pte_pfn(pte)); +#ifdef CONFIG_HUGETLB_PAGE + if (PageHuge(new)) { + pte = pte_mkhuge(pte); + pte = arch_make_huge_pte(pte, vma, new, 0); + } +#endif + flush_dcache_page(new); set_pte_at(mm, addr, ptep, pte); - if (PageAnon(new)) + if (PageHuge(new)) { + if (PageAnon(new)) + hugepage_add_anon_rmap(new, vma, addr); + else + page_dup_rmap(new); + } else if (PageAnon(new)) page_add_anon_rmap(new, vma, addr); else page_add_file_rmap(new); /* No need to invalidate - it was non-present before */ - update_mmu_cache(vma, addr, pte); - -out: + update_mmu_cache(vma, addr, ptep); +unlock: pte_unmap_unlock(ptep, ptl); +out: + return SWAP_AGAIN; } /* - * Note that remove_file_migration_ptes will only work on regular mappings, - * Nonlinear mappings do not use migration entries. - */ -static void remove_file_migration_ptes(struct page *old, struct page *new) -{ - struct vm_area_struct *vma; - struct address_space *mapping = page_mapping(new); - struct prio_tree_iter iter; - pgoff_t pgoff = new->index << (PAGE_CACHE_SHIFT - PAGE_SHIFT); - - if (!mapping) - return; - - spin_lock(&mapping->i_mmap_lock); - - vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, pgoff, pgoff) - remove_migration_pte(vma, old, new); - - spin_unlock(&mapping->i_mmap_lock); -} - -/* - * Must hold mmap_sem lock on at least one of the vmas containing - * the page so that the anon_vma cannot vanish. + * 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 void remove_anon_migration_ptes(struct page *old, struct page *new) +static int remove_linear_migration_ptes_from_nonlinear(struct page *page, + struct address_space *mapping, void *arg) { - struct anon_vma *anon_vma; struct vm_area_struct *vma; - unsigned long mapping; - - mapping = (unsigned long)new->mapping; - - if (!mapping || (mapping & PAGE_MAPPING_ANON) == 0) - return; - - /* - * We hold the mmap_sem lock. So no need to call page_lock_anon_vma. - */ - anon_vma = (struct anon_vma *) (mapping - PAGE_MAPPING_ANON); - spin_lock(&anon_vma->lock); + /* 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, &anon_vma->head, anon_vma_node) - remove_migration_pte(vma, old, new); + list_for_each_entry(vma, + &mapping->i_mmap_nonlinear, shared.nonlinear) { - spin_unlock(&anon_vma->lock); + 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; } /* @@ -252,28 +212,28 @@ static void remove_anon_migration_ptes(struct page *old, struct page *new) */ static void remove_migration_ptes(struct page *old, struct page *new) { - if (PageAnon(new)) - remove_anon_migration_ptes(old, new); - else - remove_file_migration_ptes(old, 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); } /* * Something used the pte of a page under migration. We need to * get to the page and wait until migration is finished. * When we return from this function the fault will be retried. - * - * This function is called from do_swap_page(). */ -void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, - unsigned long address) +static void __migration_entry_wait(struct mm_struct *mm, pte_t *ptep, + spinlock_t *ptl) { - pte_t *ptep, pte; - spinlock_t *ptl; + pte_t pte; swp_entry_t entry; struct page *page; - ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + spin_lock(ptl); pte = *ptep; if (!is_swap_pte(pte)) goto out; @@ -284,7 +244,15 @@ void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, page = migration_entry_to_page(entry); - get_page(page); + /* + * Once radix-tree replacement of page migration started, page_count + * *must* be zero. And, we don't want to call wait_on_page_locked() + * against a page without get_page(). + * So, we use get_page_unless_zero(), here. Even failed, page fault + * will occur again. + */ + if (!get_page_unless_zero(page)) + goto out; pte_unmap_unlock(ptep, ptl); wait_on_page_locked(page); put_page(page); @@ -293,34 +261,122 @@ out: pte_unmap_unlock(ptep, ptl); } +void migration_entry_wait(struct mm_struct *mm, pmd_t *pmd, + unsigned long address) +{ + spinlock_t *ptl = pte_lockptr(mm, pmd); + pte_t *ptep = pte_offset_map(pmd, address); + __migration_entry_wait(mm, ptep, ptl); +} + +void migration_entry_wait_huge(struct vm_area_struct *vma, + struct mm_struct *mm, pte_t *pte) +{ + spinlock_t *ptl = huge_pte_lockptr(hstate_vma(vma), mm, pte); + __migration_entry_wait(mm, pte, ptl); +} + +#ifdef CONFIG_BLOCK +/* Returns true if all buffers are successfully locked */ +static bool buffer_migrate_lock_buffers(struct buffer_head *head, + enum migrate_mode mode) +{ + struct buffer_head *bh = head; + + /* Simple case, sync compaction */ + if (mode != MIGRATE_ASYNC) { + do { + get_bh(bh); + lock_buffer(bh); + bh = bh->b_this_page; + + } while (bh != head); + + return true; + } + + /* async case, we cannot block on lock_buffer so use trylock_buffer */ + do { + get_bh(bh); + if (!trylock_buffer(bh)) { + /* + * We failed to lock the buffer and cannot stall in + * async migration. Release the taken locks + */ + struct buffer_head *failed_bh = bh; + put_bh(failed_bh); + bh = head; + while (bh != failed_bh) { + unlock_buffer(bh); + put_bh(bh); + bh = bh->b_this_page; + } + return false; + } + + bh = bh->b_this_page; + } while (bh != head); + return true; +} +#else +static inline bool buffer_migrate_lock_buffers(struct buffer_head *head, + enum migrate_mode mode) +{ + return true; +} +#endif /* CONFIG_BLOCK */ + /* * Replace the page in the mapping. * * The number of remaining references must be: * 1 for anonymous pages without a mapping * 2 for pages with a mapping - * 3 for pages with a mapping and PagePrivate set. + * 3 for pages with a mapping and PagePrivate/PagePrivate2 set. */ -static int migrate_page_move_mapping(struct address_space *mapping, - struct page *newpage, struct page *page) +int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page, + struct buffer_head *head, enum migrate_mode mode, + int extra_count) { + int expected_count = 1 + extra_count; void **pslot; if (!mapping) { /* Anonymous page without mapping */ - if (page_count(page) != 1) + if (page_count(page) != expected_count) return -EAGAIN; - return 0; + return MIGRATEPAGE_SUCCESS; } - write_lock_irq(&mapping->tree_lock); + spin_lock_irq(&mapping->tree_lock); pslot = radix_tree_lookup_slot(&mapping->page_tree, page_index(page)); - if (page_count(page) != 2 + !!PagePrivate(page) || - (struct page *)radix_tree_deref_slot(pslot) != page) { - write_unlock_irq(&mapping->tree_lock); + expected_count += 1 + page_has_private(page); + if (page_count(page) != expected_count || + radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { + spin_unlock_irq(&mapping->tree_lock); + return -EAGAIN; + } + + if (!page_freeze_refs(page, expected_count)) { + spin_unlock_irq(&mapping->tree_lock); + return -EAGAIN; + } + + /* + * In the async migration case of moving a page with buffers, lock the + * buffers using trylock before the mapping is moved. If the mapping + * was moved, we later failed to lock the buffers and could not move + * the mapping back due to an elevated page count, we would have to + * block waiting on other references to be dropped. + */ + if (mode == MIGRATE_ASYNC && head && + !buffer_migrate_lock_buffers(head, mode)) { + page_unfreeze_refs(page, expected_count); + spin_unlock_irq(&mapping->tree_lock); return -EAGAIN; } @@ -328,20 +384,19 @@ static int migrate_page_move_mapping(struct address_space *mapping, * Now we know that no one else is looking at the page. */ get_page(newpage); /* add cache reference */ -#ifdef CONFIG_SWAP if (PageSwapCache(page)) { SetPageSwapCache(newpage); set_page_private(newpage, page_private(page)); } -#endif radix_tree_replace_slot(pslot, newpage); /* - * Drop cache reference from old page. + * Drop cache reference from old page by unfreezing + * to one less reference. * We know this isn't the last reference. */ - __put_page(page); + page_unfreeze_refs(page, expected_count - 1); /* * If moved to a different zone then also account @@ -355,18 +410,117 @@ static int migrate_page_move_mapping(struct address_space *mapping, */ __dec_zone_page_state(page, NR_FILE_PAGES); __inc_zone_page_state(newpage, NR_FILE_PAGES); + if (!PageSwapCache(page) && PageSwapBacked(page)) { + __dec_zone_page_state(page, NR_SHMEM); + __inc_zone_page_state(newpage, NR_SHMEM); + } + spin_unlock_irq(&mapping->tree_lock); - write_unlock_irq(&mapping->tree_lock); + return MIGRATEPAGE_SUCCESS; +} - return 0; +/* + * The expected number of remaining references is the same as that + * of migrate_page_move_mapping(). + */ +int migrate_huge_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + int expected_count; + void **pslot; + + if (!mapping) { + if (page_count(page) != 1) + return -EAGAIN; + return MIGRATEPAGE_SUCCESS; + } + + spin_lock_irq(&mapping->tree_lock); + + pslot = radix_tree_lookup_slot(&mapping->page_tree, + page_index(page)); + + expected_count = 2 + page_has_private(page); + if (page_count(page) != expected_count || + radix_tree_deref_slot_protected(pslot, &mapping->tree_lock) != page) { + spin_unlock_irq(&mapping->tree_lock); + return -EAGAIN; + } + + if (!page_freeze_refs(page, expected_count)) { + spin_unlock_irq(&mapping->tree_lock); + return -EAGAIN; + } + + get_page(newpage); + + radix_tree_replace_slot(pslot, newpage); + + page_unfreeze_refs(page, expected_count - 1); + + spin_unlock_irq(&mapping->tree_lock); + return MIGRATEPAGE_SUCCESS; +} + +/* + * Gigantic pages are so large that we do not guarantee that page++ pointer + * arithmetic will work across the entire page. We need something more + * specialized. + */ +static void __copy_gigantic_page(struct page *dst, struct page *src, + int nr_pages) +{ + int i; + struct page *dst_base = dst; + struct page *src_base = src; + + for (i = 0; i < nr_pages; ) { + cond_resched(); + copy_highpage(dst, src); + + i++; + dst = mem_map_next(dst, dst_base, i); + src = mem_map_next(src, src_base, i); + } +} + +static void copy_huge_page(struct page *dst, struct page *src) +{ + int i; + int nr_pages; + + if (PageHuge(src)) { + /* hugetlbfs page */ + struct hstate *h = page_hstate(src); + nr_pages = pages_per_huge_page(h); + + if (unlikely(nr_pages > MAX_ORDER_NR_PAGES)) { + __copy_gigantic_page(dst, src, nr_pages); + return; + } + } else { + /* thp page */ + BUG_ON(!PageTransHuge(src)); + nr_pages = hpage_nr_pages(src); + } + + for (i = 0; i < nr_pages; i++) { + cond_resched(); + copy_highpage(dst + i, src + i); + } } /* * Copy the page to its new location */ -static void migrate_page_copy(struct page *newpage, struct page *page) +void migrate_page_copy(struct page *newpage, struct page *page) { - copy_highpage(newpage, page); + int cpupid; + + if (PageHuge(page) || PageTransHuge(page)) + copy_huge_page(newpage, page); + else + copy_highpage(newpage, page); if (PageError(page)) SetPageError(newpage); @@ -374,8 +528,11 @@ static void migrate_page_copy(struct page *newpage, struct page *page) SetPageReferenced(newpage); if (PageUptodate(page)) SetPageUptodate(newpage); - if (PageActive(page)) + if (TestClearPageActive(page)) { + VM_BUG_ON_PAGE(PageUnevictable(page), page); SetPageActive(newpage); + } else if (TestClearPageUnevictable(page)) + SetPageUnevictable(newpage); if (PageChecked(page)) SetPageChecked(newpage); if (PageMappedToDisk(page)) @@ -383,16 +540,35 @@ static void migrate_page_copy(struct page *newpage, struct page *page) if (PageDirty(page)) { clear_page_dirty_for_io(page); - set_page_dirty(newpage); + /* + * Want to mark the page and the radix tree as dirty, and + * redo the accounting that clear_page_dirty_for_io undid, + * but we can't use set_page_dirty because that function + * is actually a signal that all of the page has become dirty. + * Whereas only part of our page may be dirty. + */ + if (PageSwapBacked(page)) + SetPageDirty(newpage); + else + __set_page_dirty_nobuffers(newpage); } -#ifdef CONFIG_SWAP + /* + * Copy NUMA information to the new page, to prevent over-eager + * future migrations of this same page. + */ + cpupid = page_cpupid_xchg_last(page, -1); + page_cpupid_xchg_last(newpage, cpupid); + + mlock_migrate_page(newpage, page); + ksm_migrate_page(newpage, page); + /* + * Please do not reorder this without considering how mm/ksm.c's + * get_ksm_page() depends upon ksm_migrate_page() and PageSwapCache(). + */ ClearPageSwapCache(page); -#endif - ClearPageActive(page); ClearPagePrivate(page); set_page_private(page, 0); - page->mapping = NULL; /* * If any waiters have accumulated on the new page then @@ -406,34 +582,27 @@ static void migrate_page_copy(struct page *newpage, struct page *page) * Migration functions ***********************************************************/ -/* Always fail migration. Used for mappings that are not movable */ -int fail_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) -{ - return -EIO; -} -EXPORT_SYMBOL(fail_migrate_page); - /* * Common logic to directly migrate a single page suitable for - * pages that do not use PagePrivate. + * pages that do not use PagePrivate/PagePrivate2. * * Pages are locked upon entry and exit. */ int migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, + enum migrate_mode mode) { int rc; BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_move_mapping(mapping, newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page, NULL, mode, 0); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) return rc; migrate_page_copy(newpage, page); - return 0; + return MIGRATEPAGE_SUCCESS; } EXPORT_SYMBOL(migrate_page); @@ -444,28 +613,28 @@ EXPORT_SYMBOL(migrate_page); * exist. */ int buffer_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, enum migrate_mode mode) { struct buffer_head *bh, *head; int rc; if (!page_has_buffers(page)) - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, mode); head = page_buffers(page); - rc = migrate_page_move_mapping(mapping, newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page, head, mode, 0); - if (rc) + if (rc != MIGRATEPAGE_SUCCESS) return rc; - bh = head; - do { - get_bh(bh); - lock_buffer(bh); - bh = bh->b_this_page; - - } while (bh != head); + /* + * In the async case, migrate_page_move_mapping locked the buffers + * with an IRQ-safe spinlock held. In the sync case, the buffers + * need to be locked now + */ + if (mode != MIGRATE_ASYNC) + BUG_ON(!buffer_migrate_lock_buffers(head, mode)); ClearPagePrivate(page); set_page_private(newpage, page_private(page)); @@ -492,7 +661,7 @@ int buffer_migrate_page(struct address_space *mapping, } while (bh != head); - return 0; + return MIGRATEPAGE_SUCCESS; } EXPORT_SYMBOL(buffer_migrate_page); #endif @@ -507,7 +676,6 @@ static int writeout(struct address_space *mapping, struct page *page) .nr_to_write = 1, .range_start = 0, .range_end = LLONG_MAX, - .nonblocking = 1, .for_reclaim = 1 }; int rc; @@ -531,35 +699,36 @@ static int writeout(struct address_space *mapping, struct page *page) remove_migration_ptes(page, page); rc = mapping->a_ops->writepage(page, &wbc); - if (rc < 0) - /* I/O Error writing */ - return -EIO; if (rc != AOP_WRITEPAGE_ACTIVATE) /* unlocked. Relock */ lock_page(page); - return -EAGAIN; + return (rc < 0) ? -EIO : -EAGAIN; } /* * Default handling if a filesystem does not provide a migration function. */ static int fallback_migrate_page(struct address_space *mapping, - struct page *newpage, struct page *page) + struct page *newpage, struct page *page, enum migrate_mode mode) { - if (PageDirty(page)) + if (PageDirty(page)) { + /* Only writeback pages in full synchronous migration */ + if (mode != MIGRATE_SYNC) + return -EBUSY; return writeout(mapping, page); + } /* * Buffers may be managed in a filesystem specific way. * We must have no buffers or drop them. */ - if (PagePrivate(page) && + if (page_has_private(page) && !try_to_release_page(page, GFP_KERNEL)) return -EAGAIN; - return migrate_page(mapping, newpage, page); + return migrate_page(mapping, newpage, page, mode); } /* @@ -568,8 +737,13 @@ static int fallback_migrate_page(struct address_space *mapping, * * The new page will have replaced the old page if this function * is successful. + * + * Return value: + * < 0 - error code + * MIGRATEPAGE_SUCCESS - success */ -static int move_to_new_page(struct page *newpage, struct page *page) +static int move_to_new_page(struct page *newpage, struct page *page, + int remap_swapcache, enum migrate_mode mode) { struct address_space *mapping; int rc; @@ -579,83 +753,139 @@ static int move_to_new_page(struct page *newpage, struct page *page) * establishing additional references. We are the only one * holding a reference to the new page at this point. */ - if (TestSetPageLocked(newpage)) + if (!trylock_page(newpage)) BUG(); /* Prepare mapping for the new page.*/ newpage->index = page->index; newpage->mapping = page->mapping; + if (PageSwapBacked(page)) + SetPageSwapBacked(newpage); mapping = page_mapping(page); if (!mapping) - rc = migrate_page(mapping, newpage, page); + rc = migrate_page(mapping, newpage, page, mode); else if (mapping->a_ops->migratepage) /* - * Most pages have a mapping and most filesystems - * should provide a migration function. Anonymous - * pages are part of swap space which also has its - * own migration function. This is the most common - * path for page migration. + * Most pages have a mapping and most filesystems provide a + * migratepage callback. Anonymous pages are part of swap + * space which also has its own migratepage callback. This + * is the most common path for page migration. */ rc = mapping->a_ops->migratepage(mapping, - newpage, page); + newpage, page, mode); else - rc = fallback_migrate_page(mapping, newpage, page); + rc = fallback_migrate_page(mapping, newpage, page, mode); - if (!rc) { - mem_cgroup_page_migration(page, newpage); - remove_migration_ptes(page, newpage); - } else + if (rc != MIGRATEPAGE_SUCCESS) { newpage->mapping = NULL; + } else { + if (remap_swapcache) + remove_migration_ptes(page, newpage); + page->mapping = NULL; + } unlock_page(newpage); return rc; } -/* - * Obtain the lock on page, remove all ptes and migrate the page - * to the newly allocated page in newpage. - */ -static int unmap_and_move(new_page_t get_new_page, unsigned long private, - struct page *page, int force) +static int __unmap_and_move(struct page *page, struct page *newpage, + int force, enum migrate_mode mode) { - int rc = 0; - int *result = NULL; - struct page *newpage = get_new_page(page, private, &result); - int rcu_locked = 0; - int charge = 0; + int rc = -EAGAIN; + int remap_swapcache = 1; + struct mem_cgroup *mem; + struct anon_vma *anon_vma = NULL; - if (!newpage) - return -ENOMEM; + if (!trylock_page(page)) { + if (!force || mode == MIGRATE_ASYNC) + goto out; - if (page_count(page) == 1) - /* page was freed from under us. So we are done. */ - goto move_newpage; + /* + * It's not safe for direct compaction to call lock_page. + * For example, during page readahead pages are added locked + * to the LRU. Later, when the IO completes the pages are + * marked uptodate and unlocked. However, the queueing + * could be merging multiple pages for one bio (e.g. + * mpage_readpages). If an allocation happens for the + * second or third page, the process can end up locking + * the same page twice and deadlocking. Rather than + * trying to be clever about what pages can be locked, + * avoid the use of lock_page for direct compaction + * altogether. + */ + if (current->flags & PF_MEMALLOC) + goto out; - rc = -EAGAIN; - if (TestSetPageLocked(page)) { - if (!force) - goto move_newpage; lock_page(page); } + /* charge against new page */ + mem_cgroup_prepare_migration(page, newpage, &mem); + if (PageWriteback(page)) { + /* + * Only in the case of a full synchronous migration is it + * necessary to wait for PageWriteback. In the async case, + * the retry loop is too short and in the sync-light case, + * the overhead of stalling is too much + */ + if (mode != MIGRATE_SYNC) { + rc = -EBUSY; + goto uncharge; + } if (!force) - goto unlock; + goto uncharge; wait_on_page_writeback(page); } /* * By try_to_unmap(), page->mapcount goes down to 0 here. In this case, * we cannot notice that anon_vma is freed while we migrates a page. - * This rcu_read_lock() delays freeing anon_vma pointer until the end + * This get_anon_vma() delays freeing anon_vma pointer until the end * of migration. File cache pages are no problem because of page_lock() * File Caches may use write_page() or lock_page() in migration, then, * just care Anon page here. */ - if (PageAnon(page)) { - rcu_read_lock(); - rcu_locked = 1; + if (PageAnon(page) && !PageKsm(page)) { + /* + * Only page_lock_anon_vma_read() understands the subtleties of + * getting a hold on an anon_vma from outside one of its mms. + */ + anon_vma = page_get_anon_vma(page); + if (anon_vma) { + /* + * Anon page + */ + } else if (PageSwapCache(page)) { + /* + * We cannot be sure that the anon_vma of an unmapped + * swapcache page is safe to use because we don't + * know in advance if the VMA that this page belonged + * to still exists. If the VMA and others sharing the + * data have been freed, then the anon_vma could + * already be invalid. + * + * To avoid this possibility, swapcache pages get + * migrated but are not remapped when migration + * completes + */ + remap_swapcache = 0; + } else { + goto uncharge; + } + } + + if (unlikely(balloon_page_movable(page))) { + /* + * A ballooned page does not need any special attention from + * physical to virtual reverse mapping procedures. + * Skip any attempt to unmap PTEs or to remap swap cache, + * in order to avoid burning cycles at rmap level, and perform + * the page migration right away (proteced by page lock). + */ + rc = balloon_page_migrate(newpage, page, mode); + goto uncharge; } /* @@ -671,57 +901,99 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, * free the metadata, so the page can be freed. */ if (!page->mapping) { - if (!PageAnon(page) && PagePrivate(page)) { - /* - * Go direct to try_to_free_buffers() here because - * a) that's what try_to_release_page() would do anyway - * b) we may be under rcu_read_lock() here, so we can't - * use GFP_KERNEL which is what try_to_release_page() - * needs to be effective. - */ + VM_BUG_ON_PAGE(PageAnon(page), page); + if (page_has_private(page)) { try_to_free_buffers(page); + goto uncharge; } - goto rcu_unlock; + goto skip_unmap; } - charge = mem_cgroup_prepare_migration(page); /* Establish migration ptes or remove ptes */ - try_to_unmap(page, 1); + try_to_unmap(page, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); +skip_unmap: if (!page_mapped(page)) - rc = move_to_new_page(newpage, page); + rc = move_to_new_page(newpage, page, remap_swapcache, mode); - if (rc) { + if (rc && remap_swapcache) remove_migration_ptes(page, page); - if (charge) - mem_cgroup_end_migration(page); - } else if (charge) - mem_cgroup_end_migration(newpage); -rcu_unlock: - if (rcu_locked) - rcu_read_unlock(); -unlock: + /* Drop an anon_vma reference if we took one */ + if (anon_vma) + put_anon_vma(anon_vma); +uncharge: + mem_cgroup_end_migration(mem, page, newpage, + (rc == MIGRATEPAGE_SUCCESS || + rc == MIGRATEPAGE_BALLOON_SUCCESS)); unlock_page(page); +out: + return rc; +} + +/* + * Obtain the lock on page, remove all ptes and migrate the page + * to the newly allocated page in newpage. + */ +static int unmap_and_move(new_page_t get_new_page, free_page_t put_new_page, + unsigned long private, struct page *page, int force, + enum migrate_mode mode) +{ + int rc = 0; + int *result = NULL; + struct page *newpage = get_new_page(page, private, &result); + if (!newpage) + return -ENOMEM; + + if (page_count(page) == 1) { + /* page was freed from under us. So we are done. */ + goto out; + } + + if (unlikely(PageTransHuge(page))) + if (unlikely(split_huge_page(page))) + goto out; + + rc = __unmap_and_move(page, newpage, force, mode); + + if (unlikely(rc == MIGRATEPAGE_BALLOON_SUCCESS)) { + /* + * A ballooned page has been migrated already. + * Now, it's the time to wrap-up counters, + * handle the page back to Buddy and return. + */ + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + balloon_page_free(page); + return MIGRATEPAGE_SUCCESS; + } +out: if (rc != -EAGAIN) { - /* - * A page that has been migrated has all references - * removed and will be freed. A page that has not been - * migrated will have kepts its references and be - * restored. - */ - list_del(&page->lru); - move_to_lru(page); + /* + * A page that has been migrated has all references + * removed and will be freed. A page that has not been + * migrated will have kepts its references and be + * restored. + */ + list_del(&page->lru); + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + putback_lru_page(page); } -move_newpage: /* - * Move the new page to the LRU. If migration was not successful - * then this will free the page. + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, putback_lru_page() will drop the reference grabbed + * during isolation. */ - move_to_lru(newpage); + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) { + ClearPageSwapBacked(newpage); + put_new_page(newpage, private); + } else + putback_lru_page(newpage); + if (result) { if (rc) *result = rc; @@ -732,24 +1004,126 @@ move_newpage: } /* - * migrate_pages + * Counterpart of unmap_and_move_page() for hugepage migration. * - * The function takes one list of pages to migrate and a function - * that determines from the page to be migrated and the private data - * the target of the move and allocates the page. + * This function doesn't wait the completion of hugepage I/O + * because there is no race between I/O and migration for hugepage. + * Note that currently hugepage I/O occurs only in direct I/O + * where no lock is held and PG_writeback is irrelevant, + * and writeback status of all subpages are counted in the reference + * count of the head page (i.e. if all subpages of a 2MB hugepage are + * under direct I/O, the reference of the head page is 512 and a bit more.) + * This means that when we try to migrate hugepage whose subpages are + * doing direct I/O, some references remain after try_to_unmap() and + * hugepage migration fails without data corruption. * - * The function returns after 10 attempts or if no pages - * are movable anymore because to has become empty - * or no retryable pages exist anymore. All pages will be - * returned to the LRU or freed. + * There is also no race when direct I/O is issued on the page under migration, + * because then pte is replaced with migration swap entry and direct I/O code + * will wait in the page fault for migration to complete. + */ +static int unmap_and_move_huge_page(new_page_t get_new_page, + free_page_t put_new_page, unsigned long private, + struct page *hpage, int force, + enum migrate_mode mode) +{ + int rc = 0; + int *result = NULL; + struct page *new_hpage; + struct anon_vma *anon_vma = NULL; + + /* + * Movability of hugepages depends on architectures and hugepage size. + * This check is necessary because some callers of hugepage migration + * like soft offline and memory hotremove don't walk through page + * tables or check whether the hugepage is pmd-based or not before + * kicking migration. + */ + if (!hugepage_migration_supported(page_hstate(hpage))) { + putback_active_hugepage(hpage); + return -ENOSYS; + } + + new_hpage = get_new_page(hpage, private, &result); + if (!new_hpage) + return -ENOMEM; + + rc = -EAGAIN; + + if (!trylock_page(hpage)) { + if (!force || mode != MIGRATE_SYNC) + goto out; + lock_page(hpage); + } + + if (PageAnon(hpage)) + anon_vma = page_get_anon_vma(hpage); + + try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS); + + if (!page_mapped(hpage)) + rc = move_to_new_page(new_hpage, hpage, 1, mode); + + if (rc != MIGRATEPAGE_SUCCESS) + remove_migration_ptes(hpage, hpage); + + if (anon_vma) + put_anon_vma(anon_vma); + + if (rc == MIGRATEPAGE_SUCCESS) + hugetlb_cgroup_migrate(hpage, new_hpage); + + unlock_page(hpage); +out: + if (rc != -EAGAIN) + putback_active_hugepage(hpage); + + /* + * If migration was not successful and there's a freeing callback, use + * it. Otherwise, put_page() will drop the reference grabbed during + * isolation. + */ + if (rc != MIGRATEPAGE_SUCCESS && put_new_page) + put_new_page(new_hpage, private); + else + put_page(new_hpage); + + if (result) { + if (rc) + *result = rc; + else + *result = page_to_nid(new_hpage); + } + return rc; +} + +/* + * migrate_pages - migrate the pages specified in a list, to the free pages + * supplied as the target for the page migration + * + * @from: The list of pages to be migrated. + * @get_new_page: The function used to allocate free pages to be used + * as the target of the page migration. + * @put_new_page: The function used to free target pages if migration + * fails, or NULL if no special handling is necessary. + * @private: Private data to be passed on to get_new_page() + * @mode: The migration mode that specifies the constraints for + * page migration, if any. + * @reason: The reason for page migration. + * + * The function returns after 10 attempts or if no pages are movable any more + * because the list has become empty or no retryable pages exist any more. + * The caller should call putback_lru_pages() to return pages to the LRU + * or free list only if ret != 0. * - * Return: Number of pages not migrated or error code. + * Returns the number of pages that were not migrated, or an error code. */ -int migrate_pages(struct list_head *from, - new_page_t get_new_page, unsigned long private) +int migrate_pages(struct list_head *from, new_page_t get_new_page, + free_page_t put_new_page, unsigned long private, + enum migrate_mode mode, int reason) { int retry = 1; int nr_failed = 0; + int nr_succeeded = 0; int pass = 0; struct page *page; struct page *page2; @@ -765,8 +1139,13 @@ int migrate_pages(struct list_head *from, list_for_each_entry_safe(page, page2, from, lru) { cond_resched(); - rc = unmap_and_move(get_new_page, private, - page, pass > 2); + if (PageHuge(page)) + rc = unmap_and_move_huge_page(get_new_page, + put_new_page, private, page, + pass > 2, mode); + else + rc = unmap_and_move(get_new_page, put_new_page, + private, page, pass > 2, mode); switch(rc) { case -ENOMEM: @@ -774,26 +1153,33 @@ int migrate_pages(struct list_head *from, case -EAGAIN: retry++; break; - case 0: + case MIGRATEPAGE_SUCCESS: + nr_succeeded++; break; default: - /* Permanent failure */ + /* + * Permanent failure (-EBUSY, -ENOSYS, etc.): + * unlike -EAGAIN case, the failed page is + * removed from migration page list and not + * retried in the next outer loop. + */ nr_failed++; break; } } } - rc = 0; + rc = nr_failed + retry; out: + if (nr_succeeded) + count_vm_events(PGMIGRATE_SUCCESS, nr_succeeded); + if (nr_failed) + count_vm_events(PGMIGRATE_FAIL, nr_failed); + trace_mm_migrate_pages(nr_succeeded, nr_failed, mode, reason); + if (!swapwrite) current->flags &= ~PF_SWAPWRITE; - putback_lru_pages(from); - - if (rc) - return rc; - - return nr_failed + retry; + return rc; } #ifdef CONFIG_NUMA @@ -820,17 +1206,23 @@ static struct page *new_page_node(struct page *p, unsigned long private, *result = &pm->status; - return alloc_pages_node(pm->node, - GFP_HIGHUSER_MOVABLE | GFP_THISNODE, 0); + if (PageHuge(p)) + return alloc_huge_page_node(page_hstate(compound_head(p)), + pm->node); + else + return alloc_pages_exact_node(pm->node, + GFP_HIGHUSER_MOVABLE | __GFP_THISNODE, 0); } /* * Move a set of pages as indicated in the pm array. The addr * field must be set to the virtual address of the page to be moved * and the node number must contain a valid target node. + * The pm array ends with node = MAX_NUMNODES. */ -static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm, - int migrate_all) +static int do_move_page_to_node_array(struct mm_struct *mm, + struct page_to_node *pm, + int migrate_all) { int err; struct page_to_node *pp; @@ -841,28 +1233,27 @@ static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm, /* * Build a list of pages to migrate */ - migrate_prep(); for (pp = pm; pp->node != MAX_NUMNODES; pp++) { struct vm_area_struct *vma; struct page *page; - /* - * A valid page pointer that will not match any of the - * pages that will be moved. - */ - pp->page = ZERO_PAGE(0); - err = -EFAULT; vma = find_vma(mm, pp->addr); - if (!vma || !vma_migratable(vma)) + if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma)) + goto set_status; + + page = follow_page(vma, pp->addr, FOLL_GET|FOLL_SPLIT); + + err = PTR_ERR(page); + if (IS_ERR(page)) goto set_status; - page = follow_page(vma, pp->addr, FOLL_GET); err = -ENOENT; if (!page) goto set_status; - if (PageReserved(page)) /* Check for zero page */ + /* Use PageReserved to check for zero page */ + if (PageReserved(page)) goto put_and_set; pp->page = page; @@ -879,7 +1270,17 @@ static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm, !migrate_all) goto put_and_set; - err = isolate_lru_page(page, &pagelist); + if (PageHuge(page)) { + isolate_huge_page(page, &pagelist); + goto put_and_set; + } + + err = isolate_lru_page(page); + if (!err) { + list_add_tail(&page->lru, &pagelist); + inc_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + } put_and_set: /* * Either remove the duplicate refcount from @@ -891,36 +1292,131 @@ set_status: pp->status = err; } - if (!list_empty(&pagelist)) - err = migrate_pages(&pagelist, new_page_node, - (unsigned long)pm); - else - err = -ENOENT; + err = 0; + if (!list_empty(&pagelist)) { + err = migrate_pages(&pagelist, new_page_node, NULL, + (unsigned long)pm, MIGRATE_SYNC, MR_SYSCALL); + if (err) + putback_movable_pages(&pagelist); + } up_read(&mm->mmap_sem); return err; } /* - * Determine the nodes of a list of pages. The addr in the pm array - * must have been set to the virtual address of which we want to determine - * the node number. + * Migrate an array of page address onto an array of nodes and fill + * the corresponding array of status. + */ +static int do_pages_move(struct mm_struct *mm, nodemask_t task_nodes, + unsigned long nr_pages, + const void __user * __user *pages, + const int __user *nodes, + int __user *status, int flags) +{ + struct page_to_node *pm; + unsigned long chunk_nr_pages; + unsigned long chunk_start; + int err; + + err = -ENOMEM; + pm = (struct page_to_node *)__get_free_page(GFP_KERNEL); + if (!pm) + goto out; + + migrate_prep(); + + /* + * Store a chunk of page_to_node array in a page, + * but keep the last one as a marker + */ + chunk_nr_pages = (PAGE_SIZE / sizeof(struct page_to_node)) - 1; + + for (chunk_start = 0; + chunk_start < nr_pages; + chunk_start += chunk_nr_pages) { + int j; + + if (chunk_start + chunk_nr_pages > nr_pages) + chunk_nr_pages = nr_pages - chunk_start; + + /* fill the chunk pm with addrs and nodes from user-space */ + for (j = 0; j < chunk_nr_pages; j++) { + const void __user *p; + int node; + + err = -EFAULT; + if (get_user(p, pages + j + chunk_start)) + goto out_pm; + pm[j].addr = (unsigned long) p; + + if (get_user(node, nodes + j + chunk_start)) + goto out_pm; + + err = -ENODEV; + if (node < 0 || node >= MAX_NUMNODES) + goto out_pm; + + if (!node_state(node, N_MEMORY)) + goto out_pm; + + err = -EACCES; + if (!node_isset(node, task_nodes)) + goto out_pm; + + pm[j].node = node; + } + + /* End marker for this chunk */ + pm[chunk_nr_pages].node = MAX_NUMNODES; + + /* Migrate this chunk */ + err = do_move_page_to_node_array(mm, pm, + flags & MPOL_MF_MOVE_ALL); + if (err < 0) + goto out_pm; + + /* Return status information */ + for (j = 0; j < chunk_nr_pages; j++) + if (put_user(pm[j].status, status + j + chunk_start)) { + err = -EFAULT; + goto out_pm; + } + } + err = 0; + +out_pm: + free_page((unsigned long)pm); +out: + return err; +} + +/* + * Determine the nodes of an array of pages and store it in an array of status. */ -static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm) +static void do_pages_stat_array(struct mm_struct *mm, unsigned long nr_pages, + const void __user **pages, int *status) { + unsigned long i; + down_read(&mm->mmap_sem); - for ( ; pm->node != MAX_NUMNODES; pm++) { + for (i = 0; i < nr_pages; i++) { + unsigned long addr = (unsigned long)(*pages); struct vm_area_struct *vma; struct page *page; - int err; + int err = -EFAULT; - err = -EFAULT; - vma = find_vma(mm, pm->addr); - if (!vma) + vma = find_vma(mm, addr); + if (!vma || addr < vma->vm_start) + goto set_status; + + page = follow_page(vma, addr, 0); + + err = PTR_ERR(page); + if (IS_ERR(page)) goto set_status; - page = follow_page(vma, pm->addr, 0); err = -ENOENT; /* Use PageReserved to check for zero page */ if (!page || PageReserved(page)) @@ -928,28 +1424,63 @@ static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm) err = page_to_nid(page); set_status: - pm->status = err; + *status = err; + + pages++; + status++; } up_read(&mm->mmap_sem); - return 0; +} + +/* + * Determine the nodes of a user array of pages and store it in + * a user array of status. + */ +static int do_pages_stat(struct mm_struct *mm, unsigned long nr_pages, + const void __user * __user *pages, + int __user *status) +{ +#define DO_PAGES_STAT_CHUNK_NR 16 + const void __user *chunk_pages[DO_PAGES_STAT_CHUNK_NR]; + int chunk_status[DO_PAGES_STAT_CHUNK_NR]; + + while (nr_pages) { + unsigned long chunk_nr; + + chunk_nr = nr_pages; + if (chunk_nr > DO_PAGES_STAT_CHUNK_NR) + chunk_nr = DO_PAGES_STAT_CHUNK_NR; + + if (copy_from_user(chunk_pages, pages, chunk_nr * sizeof(*chunk_pages))) + break; + + do_pages_stat_array(mm, chunk_nr, chunk_pages, chunk_status); + + if (copy_to_user(status, chunk_status, chunk_nr * sizeof(*status))) + break; + + pages += chunk_nr; + status += chunk_nr; + nr_pages -= chunk_nr; + } + return nr_pages ? -EFAULT : 0; } /* * Move a list of pages in the address space of the currently executing * process. */ -asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, - const void __user * __user *pages, - const int __user *nodes, - int __user *status, int flags) +SYSCALL_DEFINE6(move_pages, pid_t, pid, unsigned long, nr_pages, + const void __user * __user *, pages, + const int __user *, nodes, + int __user *, status, int, flags) { - int err = 0; - int i; + const struct cred *cred = current_cred(), *tcred; struct task_struct *task; - nodemask_t task_nodes; struct mm_struct *mm; - struct page_to_node *pm = NULL; + int err; + nodemask_t task_nodes; /* Check flags */ if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) @@ -959,17 +1490,13 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, return -EPERM; /* Find the mm_struct */ - read_lock(&tasklist_lock); + rcu_read_lock(); task = pid ? find_task_by_vpid(pid) : current; if (!task) { - read_unlock(&tasklist_lock); + rcu_read_unlock(); return -ESRCH; } - mm = get_task_mm(task); - read_unlock(&tasklist_lock); - - if (!mm) - return -EINVAL; + get_task_struct(task); /* * Check if this process has the right to modify the specified @@ -977,83 +1504,40 @@ asmlinkage long sys_move_pages(pid_t pid, unsigned long nr_pages, * capabilities, superuser privileges or the same * userid as the target process. */ - if ((current->euid != task->suid) && (current->euid != task->uid) && - (current->uid != task->suid) && (current->uid != task->uid) && + tcred = __task_cred(task); + if (!uid_eq(cred->euid, tcred->suid) && !uid_eq(cred->euid, tcred->uid) && + !uid_eq(cred->uid, tcred->suid) && !uid_eq(cred->uid, tcred->uid) && !capable(CAP_SYS_NICE)) { + rcu_read_unlock(); err = -EPERM; - goto out2; + goto out; } + rcu_read_unlock(); err = security_task_movememory(task); if (err) - goto out2; - + goto out; task_nodes = cpuset_mems_allowed(task); + mm = get_task_mm(task); + put_task_struct(task); - /* Limit nr_pages so that the multiplication may not overflow */ - if (nr_pages >= ULONG_MAX / sizeof(struct page_to_node) - 1) { - err = -E2BIG; - goto out2; - } - - pm = vmalloc((nr_pages + 1) * sizeof(struct page_to_node)); - if (!pm) { - err = -ENOMEM; - goto out2; - } - - /* - * Get parameters from user space and initialize the pm - * array. Return various errors if the user did something wrong. - */ - for (i = 0; i < nr_pages; i++) { - const void __user *p; - - err = -EFAULT; - if (get_user(p, pages + i)) - goto out; - - pm[i].addr = (unsigned long)p; - if (nodes) { - int node; - - if (get_user(node, nodes + i)) - goto out; - - err = -ENODEV; - if (!node_state(node, N_HIGH_MEMORY)) - goto out; - - err = -EACCES; - if (!node_isset(node, task_nodes)) - goto out; - - pm[i].node = node; - } else - pm[i].node = 0; /* anything to not match MAX_NUMNODES */ - } - /* End marker */ - pm[nr_pages].node = MAX_NUMNODES; + if (!mm) + return -EINVAL; if (nodes) - err = do_move_pages(mm, pm, flags & MPOL_MF_MOVE_ALL); + err = do_pages_move(mm, task_nodes, nr_pages, pages, + nodes, status, flags); else - err = do_pages_stat(mm, pm); + err = do_pages_stat(mm, nr_pages, pages, status); - if (err >= 0) - /* Return status information */ - for (i = 0; i < nr_pages; i++) - if (put_user(pm[i].status, status + i)) - err = -EFAULT; + mmput(mm); + return err; out: - vfree(pm); -out2: - mmput(mm); + put_task_struct(task); return err; } -#endif /* * Call migration functions in the vma_ops that may prepare @@ -1066,7 +1550,7 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, struct vm_area_struct *vma; int err = 0; - for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) { + for (vma = mm->mmap; vma && !err; vma = vma->vm_next) { if (vma->vm_ops && vma->vm_ops->migrate) { err = vma->vm_ops->migrate(vma, to, from, flags); if (err) @@ -1075,3 +1559,379 @@ int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, } return err; } + +#ifdef CONFIG_NUMA_BALANCING +/* + * Returns true if this is a safe migration target node for misplaced NUMA + * pages. Currently it only checks the watermarks which crude + */ +static bool migrate_balanced_pgdat(struct pglist_data *pgdat, + unsigned long nr_migrate_pages) +{ + int z; + for (z = pgdat->nr_zones - 1; z >= 0; z--) { + struct zone *zone = pgdat->node_zones + z; + + if (!populated_zone(zone)) + continue; + + if (!zone_reclaimable(zone)) + continue; + + /* Avoid waking kswapd by allocating pages_to_migrate pages. */ + if (!zone_watermark_ok(zone, 0, + high_wmark_pages(zone) + + nr_migrate_pages, + 0, 0)) + continue; + return true; + } + return false; +} + +static struct page *alloc_misplaced_dst_page(struct page *page, + unsigned long data, + int **result) +{ + int nid = (int) data; + struct page *newpage; + + newpage = alloc_pages_exact_node(nid, + (GFP_HIGHUSER_MOVABLE | + __GFP_THISNODE | __GFP_NOMEMALLOC | + __GFP_NORETRY | __GFP_NOWARN) & + ~GFP_IOFS, 0); + + return newpage; +} + +/* + * page migration rate limiting control. + * Do not migrate more than @pages_to_migrate in a @migrate_interval_millisecs + * window of time. Default here says do not migrate more than 1280M per second. + * If a node is rate-limited then PTE NUMA updates are also rate-limited. However + * as it is faults that reset the window, pte updates will happen unconditionally + * if there has not been a fault since @pteupdate_interval_millisecs after the + * throttle window closed. + */ +static unsigned int migrate_interval_millisecs __read_mostly = 100; +static unsigned int pteupdate_interval_millisecs __read_mostly = 1000; +static unsigned int ratelimit_pages __read_mostly = 128 << (20 - PAGE_SHIFT); + +/* Returns true if NUMA migration is currently rate limited */ +bool migrate_ratelimited(int node) +{ + pg_data_t *pgdat = NODE_DATA(node); + + if (time_after(jiffies, pgdat->numabalancing_migrate_next_window + + msecs_to_jiffies(pteupdate_interval_millisecs))) + return false; + + if (pgdat->numabalancing_migrate_nr_pages < ratelimit_pages) + return false; + + return true; +} + +/* Returns true if the node is migrate rate-limited after the update */ +static bool numamigrate_update_ratelimit(pg_data_t *pgdat, + unsigned long nr_pages) +{ + /* + * Rate-limit the amount of data that is being migrated to a node. + * Optimal placement is no good if the memory bus is saturated and + * all the time is being spent migrating! + */ + if (time_after(jiffies, pgdat->numabalancing_migrate_next_window)) { + spin_lock(&pgdat->numabalancing_migrate_lock); + pgdat->numabalancing_migrate_nr_pages = 0; + pgdat->numabalancing_migrate_next_window = jiffies + + msecs_to_jiffies(migrate_interval_millisecs); + spin_unlock(&pgdat->numabalancing_migrate_lock); + } + if (pgdat->numabalancing_migrate_nr_pages > ratelimit_pages) { + trace_mm_numa_migrate_ratelimit(current, pgdat->node_id, + nr_pages); + return true; + } + + /* + * This is an unlocked non-atomic update so errors are possible. + * The consequences are failing to migrate when we potentiall should + * have which is not severe enough to warrant locking. If it is ever + * a problem, it can be converted to a per-cpu counter. + */ + pgdat->numabalancing_migrate_nr_pages += nr_pages; + return false; +} + +static int numamigrate_isolate_page(pg_data_t *pgdat, struct page *page) +{ + int page_lru; + + VM_BUG_ON_PAGE(compound_order(page) && !PageTransHuge(page), page); + + /* Avoid migrating to a node that is nearly full */ + if (!migrate_balanced_pgdat(pgdat, 1UL << compound_order(page))) + return 0; + + if (isolate_lru_page(page)) + return 0; + + /* + * migrate_misplaced_transhuge_page() skips page migration's usual + * check on page_count(), so we must do it here, now that the page + * has been isolated: a GUP pin, or any other pin, prevents migration. + * The expected page count is 3: 1 for page's mapcount and 1 for the + * caller's pin and 1 for the reference taken by isolate_lru_page(). + */ + if (PageTransHuge(page) && page_count(page) != 3) { + putback_lru_page(page); + return 0; + } + + page_lru = page_is_file_cache(page); + mod_zone_page_state(page_zone(page), NR_ISOLATED_ANON + page_lru, + hpage_nr_pages(page)); + + /* + * Isolating the page has taken another reference, so the + * caller's reference can be safely dropped without the page + * disappearing underneath us during migration. + */ + put_page(page); + return 1; +} + +bool pmd_trans_migrating(pmd_t pmd) +{ + struct page *page = pmd_page(pmd); + return PageLocked(page); +} + +void wait_migrate_huge_page(struct anon_vma *anon_vma, pmd_t *pmd) +{ + struct page *page = pmd_page(*pmd); + wait_on_page_locked(page); +} + +/* + * Attempt to migrate a misplaced page to the specified destination + * node. Caller is expected to have an elevated reference count on + * the page that will be dropped by this function before returning. + */ +int migrate_misplaced_page(struct page *page, struct vm_area_struct *vma, + int node) +{ + pg_data_t *pgdat = NODE_DATA(node); + int isolated; + int nr_remaining; + LIST_HEAD(migratepages); + + /* + * Don't migrate file pages that are mapped in multiple processes + * with execute permissions as they are probably shared libraries. + */ + if (page_mapcount(page) != 1 && page_is_file_cache(page) && + (vma->vm_flags & VM_EXEC)) + goto out; + + /* + * Rate-limit the amount of data that is being migrated to a node. + * Optimal placement is no good if the memory bus is saturated and + * all the time is being spent migrating! + */ + if (numamigrate_update_ratelimit(pgdat, 1)) + goto out; + + isolated = numamigrate_isolate_page(pgdat, page); + if (!isolated) + goto out; + + list_add(&page->lru, &migratepages); + nr_remaining = migrate_pages(&migratepages, alloc_misplaced_dst_page, + NULL, node, MIGRATE_ASYNC, + MR_NUMA_MISPLACED); + if (nr_remaining) { + if (!list_empty(&migratepages)) { + list_del(&page->lru); + dec_zone_page_state(page, NR_ISOLATED_ANON + + page_is_file_cache(page)); + putback_lru_page(page); + } + isolated = 0; + } else + count_vm_numa_event(NUMA_PAGE_MIGRATE); + BUG_ON(!list_empty(&migratepages)); + return isolated; + +out: + put_page(page); + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#if defined(CONFIG_NUMA_BALANCING) && defined(CONFIG_TRANSPARENT_HUGEPAGE) +/* + * Migrates a THP to a given target node. page must be locked and is unlocked + * before returning. + */ +int migrate_misplaced_transhuge_page(struct mm_struct *mm, + struct vm_area_struct *vma, + pmd_t *pmd, pmd_t entry, + unsigned long address, + struct page *page, int node) +{ + spinlock_t *ptl; + pg_data_t *pgdat = NODE_DATA(node); + int isolated = 0; + struct page *new_page = NULL; + struct mem_cgroup *memcg = NULL; + int page_lru = page_is_file_cache(page); + unsigned long mmun_start = address & HPAGE_PMD_MASK; + unsigned long mmun_end = mmun_start + HPAGE_PMD_SIZE; + pmd_t orig_entry; + + /* + * Rate-limit the amount of data that is being migrated to a node. + * Optimal placement is no good if the memory bus is saturated and + * all the time is being spent migrating! + */ + if (numamigrate_update_ratelimit(pgdat, HPAGE_PMD_NR)) + goto out_dropref; + + new_page = alloc_pages_node(node, + (GFP_TRANSHUGE | __GFP_THISNODE) & ~__GFP_WAIT, + HPAGE_PMD_ORDER); + if (!new_page) + goto out_fail; + + isolated = numamigrate_isolate_page(pgdat, page); + if (!isolated) { + put_page(new_page); + goto out_fail; + } + + if (mm_tlb_flush_pending(mm)) + flush_tlb_range(vma, mmun_start, mmun_end); + + /* Prepare a page as a migration target */ + __set_page_locked(new_page); + SetPageSwapBacked(new_page); + + /* anon mapping, we can simply copy page->mapping to the new page: */ + new_page->mapping = page->mapping; + new_page->index = page->index; + migrate_page_copy(new_page, page); + WARN_ON(PageLRU(new_page)); + + /* Recheck the target PMD */ + mmu_notifier_invalidate_range_start(mm, mmun_start, mmun_end); + ptl = pmd_lock(mm, pmd); + if (unlikely(!pmd_same(*pmd, entry) || page_count(page) != 2)) { +fail_putback: + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + + /* Reverse changes made by migrate_page_copy() */ + if (TestClearPageActive(new_page)) + SetPageActive(page); + if (TestClearPageUnevictable(new_page)) + SetPageUnevictable(page); + mlock_migrate_page(page, new_page); + + unlock_page(new_page); + put_page(new_page); /* Free it */ + + /* Retake the callers reference and putback on LRU */ + get_page(page); + putback_lru_page(page); + mod_zone_page_state(page_zone(page), + NR_ISOLATED_ANON + page_lru, -HPAGE_PMD_NR); + + goto out_unlock; + } + + /* + * Traditional migration needs to prepare the memcg charge + * transaction early to prevent the old page from being + * uncharged when installing migration entries. Here we can + * save the potential rollback and start the charge transfer + * only when migration is already known to end successfully. + */ + mem_cgroup_prepare_migration(page, new_page, &memcg); + + orig_entry = *pmd; + entry = mk_pmd(new_page, vma->vm_page_prot); + entry = pmd_mkhuge(entry); + entry = maybe_pmd_mkwrite(pmd_mkdirty(entry), vma); + + /* + * Clear the old entry under pagetable lock and establish the new PTE. + * Any parallel GUP will either observe the old page blocking on the + * page lock, block on the page table lock or observe the new page. + * The SetPageUptodate on the new page and page_add_new_anon_rmap + * guarantee the copy is visible before the pagetable update. + */ + flush_cache_range(vma, mmun_start, mmun_end); + page_add_anon_rmap(new_page, vma, mmun_start); + pmdp_clear_flush(vma, mmun_start, pmd); + set_pmd_at(mm, mmun_start, pmd, entry); + flush_tlb_range(vma, mmun_start, mmun_end); + update_mmu_cache_pmd(vma, address, &entry); + + if (page_count(page) != 2) { + set_pmd_at(mm, mmun_start, pmd, orig_entry); + flush_tlb_range(vma, mmun_start, mmun_end); + update_mmu_cache_pmd(vma, address, &entry); + page_remove_rmap(new_page); + goto fail_putback; + } + + page_remove_rmap(page); + + /* + * Finish the charge transaction under the page table lock to + * prevent split_huge_page() from dividing up the charge + * before it's fully transferred to the new page. + */ + mem_cgroup_end_migration(memcg, page, new_page, true); + spin_unlock(ptl); + mmu_notifier_invalidate_range_end(mm, mmun_start, mmun_end); + + /* Take an "isolate" reference and put new page on the LRU. */ + get_page(new_page); + putback_lru_page(new_page); + + unlock_page(new_page); + unlock_page(page); + put_page(page); /* Drop the rmap reference */ + put_page(page); /* Drop the LRU isolation reference */ + + count_vm_events(PGMIGRATE_SUCCESS, HPAGE_PMD_NR); + count_vm_numa_events(NUMA_PAGE_MIGRATE, HPAGE_PMD_NR); + + mod_zone_page_state(page_zone(page), + NR_ISOLATED_ANON + page_lru, + -HPAGE_PMD_NR); + return isolated; + +out_fail: + count_vm_events(PGMIGRATE_FAIL, HPAGE_PMD_NR); +out_dropref: + ptl = pmd_lock(mm, pmd); + if (pmd_same(*pmd, entry)) { + entry = pmd_mknonnuma(entry); + set_pmd_at(mm, mmun_start, pmd, entry); + update_mmu_cache_pmd(vma, address, &entry); + } + spin_unlock(ptl); + +out_unlock: + unlock_page(page); + put_page(page); + return 0; +} +#endif /* CONFIG_NUMA_BALANCING */ + +#endif /* CONFIG_NUMA */ |