diff options
Diffstat (limited to 'mm/migrate.c')
| -rw-r--r-- | mm/migrate.c | 1076 |
1 files changed, 705 insertions, 371 deletions
diff --git a/mm/migrate.c b/mm/migrate.c index 1c25040693d2..3f1e0c2c942c 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -15,6 +15,7 @@ #include <linux/migrate.h> #include <linux/module.h> #include <linux/swap.h> +#include <linux/swapops.h> #include <linux/pagemap.h> #include <linux/buffer_head.h> #include <linux/mm_inline.h> @@ -23,13 +24,13 @@ #include <linux/topology.h> #include <linux/cpu.h> #include <linux/cpuset.h> -#include <linux/swapops.h> +#include <linux/writeback.h> +#include <linux/mempolicy.h> +#include <linux/vmalloc.h> +#include <linux/security.h> #include "internal.h" -/* The maximum number of pages to take off the LRU for migration */ -#define MIGRATE_CHUNK_SIZE 256 - #define lru_to_page(_head) (list_entry((_head)->prev, struct page, lru)) /* @@ -64,16 +65,11 @@ int isolate_lru_page(struct page *page, struct list_head *pagelist) } /* - * migrate_prep() needs to be called after we have compiled the list of pages - * to be migrated using isolate_lru_page() but before we begin a series of calls - * to migrate_pages(). + * migrate_prep() needs to be called before we start compiling a list of pages + * to be migrated using isolate_lru_page(). */ int migrate_prep(void) { - /* Must have swap device for migration */ - if (nr_swap_pages <= 0) - return -ENODEV; - /* * Clear the LRU lists so pages can be isolated. * Note that pages may be moved off the LRU after we have @@ -87,7 +83,6 @@ int migrate_prep(void) static inline void move_to_lru(struct page *page) { - list_del(&page->lru); if (PageActive(page)) { /* * lru_cache_add_active checks that @@ -113,113 +108,200 @@ int putback_lru_pages(struct list_head *l) int count = 0; list_for_each_entry_safe(page, page2, l, lru) { + list_del(&page->lru); move_to_lru(page); count++; } return count; } -/* - * Non migratable page - */ -int fail_migrate_page(struct page *newpage, struct page *page) +static inline int is_swap_pte(pte_t pte) { - return -EIO; + return !pte_none(pte) && !pte_present(pte) && !pte_file(pte); } -EXPORT_SYMBOL(fail_migrate_page); /* - * swapout a single page - * page is locked upon entry, unlocked on exit + * Restore a potential migration pte to a working pte entry */ -static int swap_page(struct page *page) +static void remove_migration_pte(struct vm_area_struct *vma, + struct page *old, struct page *new) { - struct address_space *mapping = page_mapping(page); + 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; + + pmd = pmd_offset(pud, addr); + if (!pmd_present(*pmd)) + return; + + ptep = pte_offset_map(pmd, addr); + + if (!is_swap_pte(*ptep)) { + pte_unmap(ptep); + return; + } - if (page_mapped(page) && mapping) - if (try_to_unmap(page, 1) != SWAP_SUCCESS) - goto unlock_retry; + ptl = pte_lockptr(mm, pmd); + spin_lock(ptl); + pte = *ptep; + if (!is_swap_pte(pte)) + goto out; - if (PageDirty(page)) { - /* Page is dirty, try to write it out here */ - switch(pageout(page, mapping)) { - case PAGE_KEEP: - case PAGE_ACTIVATE: - goto unlock_retry; + entry = pte_to_swp_entry(pte); - case PAGE_SUCCESS: - goto retry; + if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old) + goto out; - case PAGE_CLEAN: - ; /* try to free the page below */ - } - } + get_page(new); + pte = pte_mkold(mk_pte(new, vma->vm_page_prot)); + if (is_write_migration_entry(entry)) + pte = pte_mkwrite(pte); + set_pte_at(mm, addr, ptep, pte); - if (PagePrivate(page)) { - if (!try_to_release_page(page, GFP_KERNEL) || - (!mapping && page_count(page) == 1)) - goto unlock_retry; - } + if (PageAnon(new)) + page_add_anon_rmap(new, vma, addr); + else + page_add_file_rmap(new); - if (remove_mapping(mapping, page)) { - /* Success */ - unlock_page(page); - return 0; - } + /* No need to invalidate - it was non-present before */ + update_mmu_cache(vma, addr, pte); + lazy_mmu_prot_update(pte); -unlock_retry: - unlock_page(page); +out: + pte_unmap_unlock(ptep, ptl); +} -retry: - return -EAGAIN; +/* + * 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); } /* - * Remove references for a page and establish the new page with the correct - * basic settings to be able to stop accesses to the page. + * Must hold mmap_sem lock on at least one of the vmas containing + * the page so that the anon_vma cannot vanish. */ -int migrate_page_remove_references(struct page *newpage, - struct page *page, int nr_refs) +static void remove_anon_migration_ptes(struct page *old, struct page *new) { - struct address_space *mapping = page_mapping(page); - struct page **radix_pointer; + struct anon_vma *anon_vma; + struct vm_area_struct *vma; + unsigned long mapping; - /* - * Avoid doing any of the following work if the page count - * indicates that the page is in use or truncate has removed - * the page. - */ - if (!mapping || page_mapcount(page) + nr_refs != page_count(page)) - return -EAGAIN; + mapping = (unsigned long)new->mapping; - /* - * Establish swap ptes for anonymous pages or destroy pte - * maps for files. - * - * In order to reestablish file backed mappings the fault handlers - * will take the radix tree_lock which may then be used to stop - * processses from accessing this page until the new page is ready. - * - * A process accessing via a swap pte (an anonymous page) will take a - * page_lock on the old page which will block the process until the - * migration attempt is complete. At that time the PageSwapCache bit - * will be examined. If the page was migrated then the PageSwapCache - * bit will be clear and the operation to retrieve the page will be - * retried which will find the new page in the radix tree. Then a new - * direct mapping may be generated based on the radix tree contents. - * - * If the page was not migrated then the PageSwapCache bit - * is still set and the operation may continue. - */ - if (try_to_unmap(page, 1) == SWAP_FAIL) - /* A vma has VM_LOCKED set -> permanent failure */ - return -EPERM; + if (!mapping || (mapping & PAGE_MAPPING_ANON) == 0) + return; /* - * Give up if we were unable to remove all mappings. + * We hold the mmap_sem lock. So no need to call page_lock_anon_vma. */ - if (page_mapcount(page)) - return -EAGAIN; + anon_vma = (struct anon_vma *) (mapping - PAGE_MAPPING_ANON); + spin_lock(&anon_vma->lock); + + list_for_each_entry(vma, &anon_vma->head, anon_vma_node) + remove_migration_pte(vma, old, new); + + spin_unlock(&anon_vma->lock); +} + +/* + * Get rid of all migration entries and replace them by + * references to the indicated page. + */ +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); +} + +/* + * 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) +{ + pte_t *ptep, pte; + spinlock_t *ptl; + swp_entry_t entry; + struct page *page; + + ptep = pte_offset_map_lock(mm, pmd, address, &ptl); + pte = *ptep; + if (!is_swap_pte(pte)) + goto out; + + entry = pte_to_swp_entry(pte); + if (!is_migration_entry(entry)) + goto out; + + page = migration_entry_to_page(entry); + + get_page(page); + pte_unmap_unlock(ptep, ptl); + wait_on_page_locked(page); + put_page(page); + return; +out: + pte_unmap_unlock(ptep, ptl); +} + +/* + * 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. + */ +static int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + struct page **radix_pointer; + + if (!mapping) { + /* Anonymous page */ + if (page_count(page) != 1) + return -EAGAIN; + return 0; + } write_lock_irq(&mapping->tree_lock); @@ -227,7 +309,7 @@ int migrate_page_remove_references(struct page *newpage, &mapping->page_tree, page_index(page)); - if (!page_mapping(page) || page_count(page) != nr_refs || + if (page_count(page) != 2 + !!PagePrivate(page) || *radix_pointer != page) { write_unlock_irq(&mapping->tree_lock); return -EAGAIN; @@ -235,19 +317,14 @@ int migrate_page_remove_references(struct page *newpage, /* * Now we know that no one else is looking at the page. - * - * Certain minimal information about a page must be available - * in order for other subsystems to properly handle the page if they - * find it through the radix tree update before we are finished - * copying the page. */ get_page(newpage); - newpage->index = page->index; - newpage->mapping = page->mapping; +#ifdef CONFIG_SWAP if (PageSwapCache(page)) { SetPageSwapCache(newpage); set_page_private(newpage, page_private(page)); } +#endif *radix_pointer = newpage; __put_page(page); @@ -255,12 +332,11 @@ int migrate_page_remove_references(struct page *newpage, return 0; } -EXPORT_SYMBOL(migrate_page_remove_references); /* * Copy the page to its new location */ -void migrate_page_copy(struct page *newpage, struct page *page) +static void migrate_page_copy(struct page *newpage, struct page *page) { copy_highpage(newpage, page); @@ -282,7 +358,9 @@ void migrate_page_copy(struct page *newpage, struct page *page) set_page_dirty(newpage); } +#ifdef CONFIG_SWAP ClearPageSwapCache(page); +#endif ClearPageActive(page); ClearPagePrivate(page); set_page_private(page, 0); @@ -295,7 +373,18 @@ void migrate_page_copy(struct page *newpage, struct page *page) if (PageWriteback(newpage)) end_page_writeback(newpage); } -EXPORT_SYMBOL(migrate_page_copy); + +/************************************************************ + * 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 @@ -303,51 +392,284 @@ EXPORT_SYMBOL(migrate_page_copy); * * Pages are locked upon entry and exit. */ -int migrate_page(struct page *newpage, struct page *page) +int migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) { int rc; BUG_ON(PageWriteback(page)); /* Writeback must be complete */ - rc = migrate_page_remove_references(newpage, page, 2); + rc = migrate_page_move_mapping(mapping, newpage, page); + + if (rc) + return rc; + + migrate_page_copy(newpage, page); + return 0; +} +EXPORT_SYMBOL(migrate_page); + +/* + * Migration function for pages with buffers. This function can only be used + * if the underlying filesystem guarantees that no other references to "page" + * exist. + */ +int buffer_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) +{ + struct buffer_head *bh, *head; + int rc; + + if (!page_has_buffers(page)) + return migrate_page(mapping, newpage, page); + + head = page_buffers(page); + + rc = migrate_page_move_mapping(mapping, newpage, page); if (rc) return rc; + bh = head; + do { + get_bh(bh); + lock_buffer(bh); + bh = bh->b_this_page; + + } while (bh != head); + + ClearPagePrivate(page); + set_page_private(newpage, page_private(page)); + set_page_private(page, 0); + put_page(page); + get_page(newpage); + + bh = head; + do { + set_bh_page(bh, newpage, bh_offset(bh)); + bh = bh->b_this_page; + + } while (bh != head); + + SetPagePrivate(newpage); + migrate_page_copy(newpage, page); + bh = head; + do { + unlock_buffer(bh); + put_bh(bh); + bh = bh->b_this_page; + + } while (bh != head); + + return 0; +} +EXPORT_SYMBOL(buffer_migrate_page); + +/* + * Writeback a page to clean the dirty state + */ +static int writeout(struct address_space *mapping, struct page *page) +{ + struct writeback_control wbc = { + .sync_mode = WB_SYNC_NONE, + .nr_to_write = 1, + .range_start = 0, + .range_end = LLONG_MAX, + .nonblocking = 1, + .for_reclaim = 1 + }; + int rc; + + if (!mapping->a_ops->writepage) + /* No write method for the address space */ + return -EINVAL; + + if (!clear_page_dirty_for_io(page)) + /* Someone else already triggered a write */ + return -EAGAIN; + /* - * Remove auxiliary swap entries and replace - * them with real ptes. - * - * Note that a real pte entry will allow processes that are not - * waiting on the page lock to use the new page via the page tables - * before the new page is unlocked. + * A dirty page may imply that the underlying filesystem has + * the page on some queue. So the page must be clean for + * migration. Writeout may mean we loose the lock and the + * page state is no longer what we checked for earlier. + * At this point we know that the migration attempt cannot + * be successful. */ - remove_from_swap(newpage); - return 0; + 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; +} + +/* + * 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) +{ + if (PageDirty(page)) + return writeout(mapping, page); + + /* + * Buffers may be managed in a filesystem specific way. + * We must have no buffers or drop them. + */ + if (page_has_buffers(page) && + !try_to_release_page(page, GFP_KERNEL)) + return -EAGAIN; + + return migrate_page(mapping, newpage, page); +} + +/* + * Move a page to a newly allocated page + * The page is locked and all ptes have been successfully removed. + * + * The new page will have replaced the old page if this function + * is successful. + */ +static int move_to_new_page(struct page *newpage, struct page *page) +{ + struct address_space *mapping; + int rc; + + /* + * Block others from accessing the page when we get around to + * establishing additional references. We are the only one + * holding a reference to the new page at this point. + */ + if (TestSetPageLocked(newpage)) + BUG(); + + /* Prepare mapping for the new page.*/ + newpage->index = page->index; + newpage->mapping = page->mapping; + + mapping = page_mapping(page); + if (!mapping) + rc = migrate_page(mapping, newpage, page); + 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. + */ + rc = mapping->a_ops->migratepage(mapping, + newpage, page); + else + rc = fallback_migrate_page(mapping, newpage, page); + + if (!rc) + remove_migration_ptes(page, newpage); + else + newpage->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) +{ + 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 move_newpage; + + rc = -EAGAIN; + if (TestSetPageLocked(page)) { + if (!force) + goto move_newpage; + lock_page(page); + } + + if (PageWriteback(page)) { + if (!force) + goto unlock; + wait_on_page_writeback(page); + } + + /* + * Establish migration ptes or remove ptes + */ + try_to_unmap(page, 1); + if (!page_mapped(page)) + rc = move_to_new_page(newpage, page); + + if (rc) + remove_migration_ptes(page, page); + +unlock: + unlock_page(page); + + 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); + } + +move_newpage: + /* + * Move the new page to the LRU. If migration was not successful + * then this will free the page. + */ + move_to_lru(newpage); + if (result) { + if (rc) + *result = rc; + else + *result = page_to_nid(newpage); + } + return rc; } -EXPORT_SYMBOL(migrate_page); /* * migrate_pages * - * Two lists are passed to this function. The first list - * contains the pages isolated from the LRU to be migrated. - * The second list contains new pages that the pages isolated - * can be moved to. If the second list is NULL then all - * pages are swapped out. + * 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. * * The function returns after 10 attempts or if no pages * are movable anymore because to has become empty - * or no retryable pages exist anymore. + * or no retryable pages exist anymore. All pages will be + * retruned to the LRU or freed. * - * Return: Number of pages not migrated when "to" ran empty. + * Return: Number of pages not migrated or error code. */ -int migrate_pages(struct list_head *from, struct list_head *to, - struct list_head *moved, struct list_head *failed) +int migrate_pages(struct list_head *from, + new_page_t get_new_page, unsigned long private) { - int retry; + int retry = 1; int nr_failed = 0; int pass = 0; struct page *page; @@ -358,305 +680,317 @@ int migrate_pages(struct list_head *from, struct list_head *to, if (!swapwrite) current->flags |= PF_SWAPWRITE; -redo: - retry = 0; + for(pass = 0; pass < 10 && retry; pass++) { + retry = 0; + + list_for_each_entry_safe(page, page2, from, lru) { + cond_resched(); + + rc = unmap_and_move(get_new_page, private, + page, pass > 2); + + switch(rc) { + case -ENOMEM: + goto out; + case -EAGAIN: + retry++; + break; + case 0: + break; + default: + /* Permanent failure */ + nr_failed++; + break; + } + } + } + rc = 0; +out: + if (!swapwrite) + current->flags &= ~PF_SWAPWRITE; + + putback_lru_pages(from); + + if (rc) + return rc; - list_for_each_entry_safe(page, page2, from, lru) { - struct page *newpage = NULL; - struct address_space *mapping; + return nr_failed + retry; +} - cond_resched(); +#ifdef CONFIG_NUMA +/* + * Move a list of individual pages + */ +struct page_to_node { + unsigned long addr; + struct page *page; + int node; + int status; +}; - rc = 0; - if (page_count(page) == 1) - /* page was freed from under us. So we are done. */ - goto next; +static struct page *new_page_node(struct page *p, unsigned long private, + int **result) +{ + struct page_to_node *pm = (struct page_to_node *)private; - if (to && list_empty(to)) - break; + while (pm->node != MAX_NUMNODES && pm->page != p) + pm++; - /* - * Skip locked pages during the first two passes to give the - * functions holding the lock time to release the page. Later we - * use lock_page() to have a higher chance of acquiring the - * lock. - */ - rc = -EAGAIN; - if (pass > 2) - lock_page(page); - else - if (TestSetPageLocked(page)) - goto next; + if (pm->node == MAX_NUMNODES) + return NULL; - /* - * Only wait on writeback if we have already done a pass where - * we we may have triggered writeouts for lots of pages. - */ - if (pass > 0) { - wait_on_page_writeback(page); - } else { - if (PageWriteback(page)) - goto unlock_page; - } + *result = &pm->status; - /* - * Anonymous pages must have swap cache references otherwise - * the information contained in the page maps cannot be - * preserved. - */ - if (PageAnon(page) && !PageSwapCache(page)) { - if (!add_to_swap(page, GFP_KERNEL)) { - rc = -ENOMEM; - goto unlock_page; - } - } + return alloc_pages_node(pm->node, GFP_HIGHUSER, 0); +} - if (!to) { - rc = swap_page(page); - goto next; - } +/* + * 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. + */ +static int do_move_pages(struct mm_struct *mm, struct page_to_node *pm, + int migrate_all) +{ + int err; + struct page_to_node *pp; + LIST_HEAD(pagelist); + + down_read(&mm->mmap_sem); - newpage = lru_to_page(to); - lock_page(newpage); + /* + * 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; /* - * Pages are properly locked and writeback is complete. - * Try to migrate the page. + * A valid page pointer that will not match any of the + * pages that will be moved. */ - mapping = page_mapping(page); - if (!mapping) - goto unlock_both; + pp->page = ZERO_PAGE(0); - 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. - */ - rc = mapping->a_ops->migratepage(newpage, page); - goto unlock_both; - } - - /* Make sure the dirty bit is up to date */ - if (try_to_unmap(page, 1) == SWAP_FAIL) { - rc = -EPERM; - goto unlock_both; - } + err = -EFAULT; + vma = find_vma(mm, pp->addr); + if (!vma) + goto set_status; - if (page_mapcount(page)) { - rc = -EAGAIN; - goto unlock_both; - } + page = follow_page(vma, pp->addr, FOLL_GET); + err = -ENOENT; + if (!page) + goto set_status; - /* - * Default handling if a filesystem does not provide - * a migration function. We can only migrate clean - * pages so try to write out any dirty pages first. - */ - if (PageDirty(page)) { - switch (pageout(page, mapping)) { - case PAGE_KEEP: - case PAGE_ACTIVATE: - goto unlock_both; - - case PAGE_SUCCESS: - unlock_page(newpage); - goto next; - - case PAGE_CLEAN: - ; /* try to migrate the page below */ - } - } + if (PageReserved(page)) /* Check for zero page */ + goto put_and_set; - /* - * Buffers are managed in a filesystem specific way. - * We must have no buffers or drop them. - */ - if (!page_has_buffers(page) || - try_to_release_page(page, GFP_KERNEL)) { - rc = migrate_page(newpage, page); - goto unlock_both; - } + pp->page = page; + err = page_to_nid(page); - /* - * On early passes with mapped pages simply - * retry. There may be a lock held for some - * buffers that may go away. Later - * swap them out. - */ - if (pass > 4) { + if (err == pp->node) /* - * Persistently unable to drop buffers..... As a - * measure of last resort we fall back to - * swap_page(). + * Node already in the right place */ - unlock_page(newpage); - newpage = NULL; - rc = swap_page(page); - goto next; - } + goto put_and_set; -unlock_both: - unlock_page(newpage); - -unlock_page: - unlock_page(page); - -next: - if (rc == -EAGAIN) { - retry++; - } else if (rc) { - /* Permanent failure */ - list_move(&page->lru, failed); - nr_failed++; - } else { - if (newpage) { - /* Successful migration. Return page to LRU */ - move_to_lru(newpage); - } - list_move(&page->lru, moved); - } + err = -EACCES; + if (page_mapcount(page) > 1 && + !migrate_all) + goto put_and_set; + + err = isolate_lru_page(page, &pagelist); +put_and_set: + /* + * Either remove the duplicate refcount from + * isolate_lru_page() or drop the page ref if it was + * not isolated. + */ + put_page(page); +set_status: + pp->status = err; } - if (retry && pass++ < 10) - goto redo; - if (!swapwrite) - current->flags &= ~PF_SWAPWRITE; + if (!list_empty(&pagelist)) + err = migrate_pages(&pagelist, new_page_node, + (unsigned long)pm); + else + err = -ENOENT; - return nr_failed + retry; + up_read(&mm->mmap_sem); + return err; } /* - * Migration function for pages with buffers. This function can only be used - * if the underlying filesystem guarantees that no other references to "page" - * exist. + * 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. */ -int buffer_migrate_page(struct page *newpage, struct page *page) +static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm) { - struct address_space *mapping = page->mapping; - struct buffer_head *bh, *head; - int rc; + down_read(&mm->mmap_sem); + + for ( ; pm->node != MAX_NUMNODES; pm++) { + struct vm_area_struct *vma; + struct page *page; + int err; + + err = -EFAULT; + vma = find_vma(mm, pm->addr); + if (!vma) + goto set_status; + + page = follow_page(vma, pm->addr, 0); + err = -ENOENT; + /* Use PageReserved to check for zero page */ + if (!page || PageReserved(page)) + goto set_status; + + err = page_to_nid(page); +set_status: + pm->status = err; + } - if (!mapping) - return -EAGAIN; + up_read(&mm->mmap_sem); + return 0; +} - if (!page_has_buffers(page)) - return migrate_page(newpage, page); +/* + * 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) +{ + int err = 0; + int i; + struct task_struct *task; + nodemask_t task_nodes; + struct mm_struct *mm; + struct page_to_node *pm = NULL; - head = page_buffers(page); + /* Check flags */ + if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) + return -EINVAL; - rc = migrate_page_remove_references(newpage, page, 3); + if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) + return -EPERM; - if (rc) - return rc; + /* Find the mm_struct */ + read_lock(&tasklist_lock); + task = pid ? find_task_by_pid(pid) : current; + if (!task) { + read_unlock(&tasklist_lock); + return -ESRCH; + } + mm = get_task_mm(task); + read_unlock(&tasklist_lock); - bh = head; - do { - get_bh(bh); - lock_buffer(bh); - bh = bh->b_this_page; + if (!mm) + return -EINVAL; - } while (bh != head); + /* + * Check if this process has the right to modify the specified + * process. The right exists if the process has administrative + * 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) && + !capable(CAP_SYS_NICE)) { + err = -EPERM; + goto out2; + } - ClearPagePrivate(page); - set_page_private(newpage, page_private(page)); - set_page_private(page, 0); - put_page(page); - get_page(newpage); + err = security_task_movememory(task); + if (err) + goto out2; - bh = head; - do { - set_bh_page(bh, newpage, bh_offset(bh)); - bh = bh->b_this_page; - } while (bh != head); + task_nodes = cpuset_mems_allowed(task); - SetPagePrivate(newpage); + /* 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; + } - migrate_page_copy(newpage, page); + pm = vmalloc((nr_pages + 1) * sizeof(struct page_to_node)); + if (!pm) { + err = -ENOMEM; + goto out2; + } - bh = head; - do { - unlock_buffer(bh); - put_bh(bh); - bh = bh->b_this_page; + /* + * 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 *p; - } while (bh != head); + err = -EFAULT; + if (get_user(p, pages + i)) + goto out; - return 0; -} -EXPORT_SYMBOL(buffer_migrate_page); + pm[i].addr = (unsigned long)p; + if (nodes) { + int node; -/* - * Migrate the list 'pagelist' of pages to a certain destination. - * - * Specify destination with either non-NULL vma or dest_node >= 0 - * Return the number of pages not migrated or error code - */ -int migrate_pages_to(struct list_head *pagelist, - struct vm_area_struct *vma, int dest) -{ - LIST_HEAD(newlist); - LIST_HEAD(moved); - LIST_HEAD(failed); - int err = 0; - unsigned long offset = 0; - int nr_pages; - struct page *page; - struct list_head *p; + if (get_user(node, nodes + i)) + goto out; -redo: - nr_pages = 0; - list_for_each(p, pagelist) { - if (vma) { - /* - * The address passed to alloc_page_vma is used to - * generate the proper interleave behavior. We fake - * the address here by an increasing offset in order - * to get the proper distribution of pages. - * - * No decision has been made as to which page - * a certain old page is moved to so we cannot - * specify the correct address. - */ - page = alloc_page_vma(GFP_HIGHUSER, vma, - offset + vma->vm_start); - offset += PAGE_SIZE; - } - else - page = alloc_pages_node(dest, GFP_HIGHUSER, 0); + err = -ENODEV; + if (!node_online(node)) + goto out; - if (!page) { - err = -ENOMEM; - goto out; + err = -EACCES; + if (!node_isset(node, task_nodes)) + goto out; + + pm[i].node = node; } - list_add_tail(&page->lru, &newlist); - nr_pages++; - if (nr_pages > MIGRATE_CHUNK_SIZE) - break; } - err = migrate_pages(pagelist, &newlist, &moved, &failed); + /* End marker */ + pm[nr_pages].node = MAX_NUMNODES; + + if (nodes) + err = do_move_pages(mm, pm, flags & MPOL_MF_MOVE_ALL); + else + err = do_pages_stat(mm, pm); - putback_lru_pages(&moved); /* Call release pages instead ?? */ + if (err >= 0) + /* Return status information */ + for (i = 0; i < nr_pages; i++) + if (put_user(pm[i].status, status + i)) + err = -EFAULT; - if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist)) - goto redo; out: - /* Return leftover allocated pages */ - while (!list_empty(&newlist)) { - page = list_entry(newlist.next, struct page, lru); - list_del(&page->lru); - __free_page(page); - } - list_splice(&failed, pagelist); - if (err < 0) - return err; - - /* Calculate number of leftover pages */ - nr_pages = 0; - list_for_each(p, pagelist) - nr_pages++; - return nr_pages; + vfree(pm); +out2: + mmput(mm); + return err; +} +#endif + +/* + * Call migration functions in the vma_ops that may prepare + * memory in a vm for migration. migration functions may perform + * the migration for vmas that do not have an underlying page struct. + */ +int migrate_vmas(struct mm_struct *mm, const nodemask_t *to, + const nodemask_t *from, unsigned long flags) +{ + struct vm_area_struct *vma; + int err = 0; + + for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) { + if (vma->vm_ops && vma->vm_ops->migrate) { + err = vma->vm_ops->migrate(vma, to, from, flags); + if (err) + break; + } + } + return err; } |
