From e7340f73307abed9283d0a07570d06e228c205dd Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Jun 2006 02:03:29 -0700 Subject: [PATCH] page migration cleanup: remove useless definitions Remove the export for migrate_page_remove_references() and migrate_page_copy() that are unlikely to be used directly by filesystems implementing migration. The export was useful when buffer_migrate_page() lived in fs/buffer.c but it has now been moved to migrate.c in the migration reorg. Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 2 -- 1 file changed, 2 deletions(-) (limited to 'include/linux/migrate.h') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 6789c4940c9..e8d3b08cc35 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -7,8 +7,6 @@ extern int isolate_lru_page(struct page *p, struct list_head *pagelist); extern int putback_lru_pages(struct list_head *l); extern int migrate_page(struct page *, struct page *); -extern void migrate_page_copy(struct page *, struct page *); -extern int migrate_page_remove_references(struct page *, struct page *, int); extern int migrate_pages(struct list_head *l, struct list_head *t, struct list_head *moved, struct list_head *failed); extern int migrate_pages_to(struct list_head *pagelist, -- cgit v1.2.3-70-g09d2 From 2d1db3b1170db4e8bf0531dd636742269c2cf579 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Jun 2006 02:03:33 -0700 Subject: [PATCH] page migration cleanup: pass "mapping" to migration functions Change handling of address spaces. Pass a pointer to the address space in which the page is migrated to all migration function. This avoids repeatedly having to retrieve the address space pointer from the page and checking it for validity. The old page mapping will change once migration has gone to a certain step, so it is less confusing to have the pointer always available. Move the setting of the mapping and index for the new page into migrate_pages(). Signed-off-by: Christoph Lameter Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/fs.h | 6 +++-- include/linux/migrate.h | 6 +++-- mm/migrate.c | 70 ++++++++++++++++++++++++------------------------- 3 files changed, 42 insertions(+), 40 deletions(-) (limited to 'include/linux/migrate.h') diff --git a/include/linux/fs.h b/include/linux/fs.h index c823a3815e2..e917403f4d5 100644 --- a/include/linux/fs.h +++ b/include/linux/fs.h @@ -376,7 +376,8 @@ struct address_space_operations { struct page* (*get_xip_page)(struct address_space *, sector_t, int); /* migrate the contents of a page to the specified target */ - int (*migratepage) (struct page *, struct page *); + int (*migratepage) (struct address_space *, + struct page *, struct page *); }; struct backing_dev_info; @@ -1772,7 +1773,8 @@ extern void simple_release_fs(struct vfsmount **mount, int *count); extern ssize_t simple_read_from_buffer(void __user *, size_t, loff_t *, const void *, size_t); #ifdef CONFIG_MIGRATION -extern int buffer_migrate_page(struct page *, struct page *); +extern int buffer_migrate_page(struct address_space *, + struct page *, struct page *); #else #define buffer_migrate_page NULL #endif diff --git a/include/linux/migrate.h b/include/linux/migrate.h index e8d3b08cc35..287c47b5e5d 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -6,12 +6,14 @@ #ifdef CONFIG_MIGRATION extern int isolate_lru_page(struct page *p, struct list_head *pagelist); extern int putback_lru_pages(struct list_head *l); -extern int migrate_page(struct page *, struct page *); +extern int migrate_page(struct address_space *, + struct page *, struct page *); extern int migrate_pages(struct list_head *l, struct list_head *t, struct list_head *moved, struct list_head *failed); extern int migrate_pages_to(struct list_head *pagelist, struct vm_area_struct *vma, int dest); -extern int fail_migrate_page(struct page *, struct page *); +extern int fail_migrate_page(struct address_space *, + struct page *, struct page *); extern int migrate_prep(void); diff --git a/mm/migrate.c b/mm/migrate.c index 8095c607a49..f65e69d9452 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -173,15 +173,11 @@ retry: * 2 for pages with a mapping * 3 for pages with a mapping and PagePrivate set. */ -static int migrate_page_move_mapping(struct page *newpage, - struct page *page) +static int migrate_page_move_mapping(struct address_space *mapping, + struct page *newpage, struct page *page) { - struct address_space *mapping = page_mapping(page); struct page **radix_pointer; - if (!mapping) - return -EAGAIN; - write_lock_irq(&mapping->tree_lock); radix_pointer = (struct page **)radix_tree_lookup_slot( @@ -197,15 +193,8 @@ static int migrate_page_move_mapping(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; if (PageSwapCache(page)) { SetPageSwapCache(newpage); set_page_private(newpage, page_private(page)); @@ -262,7 +251,8 @@ static void migrate_page_copy(struct page *newpage, struct page *page) ***********************************************************/ /* Always fail migration. Used for mappings that are not movable */ -int fail_migrate_page(struct page *newpage, struct page *page) +int fail_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) { return -EIO; } @@ -274,13 +264,14 @@ EXPORT_SYMBOL(fail_migrate_page); * * 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_move_mapping(newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page); if (rc) return rc; @@ -305,21 +296,18 @@ EXPORT_SYMBOL(migrate_page); * if the underlying filesystem guarantees that no other references to "page" * exist. */ -int buffer_migrate_page(struct page *newpage, struct page *page) +int buffer_migrate_page(struct address_space *mapping, + struct page *newpage, struct page *page) { - struct address_space *mapping = page->mapping; struct buffer_head *bh, *head; int rc; - if (!mapping) - return -EAGAIN; - if (!page_has_buffers(page)) - return migrate_page(newpage, page); + return migrate_page(mapping, newpage, page); head = page_buffers(page); - rc = migrate_page_move_mapping(newpage, page); + rc = migrate_page_move_mapping(mapping, newpage, page); if (rc) return rc; @@ -448,9 +436,6 @@ redo: goto next; } - newpage = lru_to_page(to); - lock_page(newpage); - /* * Establish swap ptes for anonymous pages or destroy pte * maps for files. @@ -473,11 +458,18 @@ redo: rc = -EPERM; if (try_to_unmap(page, 1) == SWAP_FAIL) /* A vma has VM_LOCKED set -> permanent failure */ - goto unlock_both; + goto unlock_page; rc = -EAGAIN; if (page_mapped(page)) - goto unlock_both; + goto unlock_page; + + newpage = lru_to_page(to); + lock_page(newpage); + /* Prepare mapping for the new page.*/ + newpage->index = page->index; + newpage->mapping = page->mapping; + /* * Pages are properly locked and writeback is complete. * Try to migrate the page. @@ -494,7 +486,8 @@ redo: * own migration function. This is the most common * path for page migration. */ - rc = mapping->a_ops->migratepage(newpage, page); + rc = mapping->a_ops->migratepage(mapping, + newpage, page); goto unlock_both; } @@ -524,7 +517,7 @@ redo: */ if (!page_has_buffers(page) || try_to_release_page(page, GFP_KERNEL)) { - rc = migrate_page(newpage, page); + rc = migrate_page(mapping, newpage, page); goto unlock_both; } @@ -553,12 +546,17 @@ unlock_page: unlock_page(page); next: - if (rc == -EAGAIN) { - retry++; - } else if (rc) { - /* Permanent failure */ - list_move(&page->lru, failed); - nr_failed++; + if (rc) { + if (newpage) + newpage->mapping = NULL; + + if (rc == -EAGAIN) + retry++; + else { + /* Permanent failure */ + list_move(&page->lru, failed); + nr_failed++; + } } else { if (newpage) { /* Successful migration. Return page to LRU */ -- cgit v1.2.3-70-g09d2 From aaa994b300a172afafab47938804836b923e5ef7 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Jun 2006 02:03:52 -0700 Subject: [PATCH] page migration: handle freeing of pages in migrate_pages() Do not leave pages on the lists passed to migrate_pages(). Seems that we will not need any postprocessing of pages. This will simplify the handling of pages by the callers of migrate_pages(). Signed-off-by: Christoph Lameter Cc: Hugh Dickins Cc: Jes Sorensen Cc: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 7 +++---- mm/mempolicy.c | 8 +------- mm/migrate.c | 48 +++++++++++++++++++++++------------------------- 3 files changed, 27 insertions(+), 36 deletions(-) (limited to 'include/linux/migrate.h') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 287c47b5e5d..83af25949fa 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -8,8 +8,7 @@ extern int isolate_lru_page(struct page *p, struct list_head *pagelist); extern int putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *); -extern int migrate_pages(struct list_head *l, struct list_head *t, - struct list_head *moved, struct list_head *failed); +extern int migrate_pages(struct list_head *l, struct list_head *t); extern int migrate_pages_to(struct list_head *pagelist, struct vm_area_struct *vma, int dest); extern int fail_migrate_page(struct address_space *, @@ -22,8 +21,8 @@ extern int migrate_prep(void); static inline int isolate_lru_page(struct page *p, struct list_head *list) { return -ENOSYS; } static inline int putback_lru_pages(struct list_head *l) { return 0; } -static inline int migrate_pages(struct list_head *l, struct list_head *t, - struct list_head *moved, struct list_head *failed) { return -ENOSYS; } +static inline int migrate_pages(struct list_head *l, struct list_head *t) + { return -ENOSYS; } static inline int migrate_pages_to(struct list_head *pagelist, struct vm_area_struct *vma, int dest) { return 0; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 8778f58880c..244f3f130e4 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -603,11 +603,8 @@ int migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nmask, flags | MPOL_MF_DISCONTIG_OK, &pagelist); - if (!list_empty(&pagelist)) { + if (!list_empty(&pagelist)) err = migrate_pages_to(&pagelist, NULL, dest); - if (!list_empty(&pagelist)) - putback_lru_pages(&pagelist); - } return err; } @@ -773,9 +770,6 @@ long do_mbind(unsigned long start, unsigned long len, err = -EIO; } - if (!list_empty(&pagelist)) - putback_lru_pages(&pagelist); - up_write(&mm->mmap_sem); mpol_free(new); return err; diff --git a/mm/migrate.c b/mm/migrate.c index 09038163bfe..d3a1810a4c9 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -624,6 +624,15 @@ unlock: unlock_page(page); ret: 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); + list_del(&newpage->lru); move_to_lru(newpage); } @@ -640,12 +649,12 @@ ret: * * 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. */ -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, struct list_head *to) { int retry = 1; int nr_failed = 0; @@ -675,11 +684,9 @@ int migrate_pages(struct list_head *from, struct list_head *to, retry++; break; case 0: - list_move(&page->lru, moved); break; default: /* Permanent failure */ - list_move(&page->lru, failed); nr_failed++; break; } @@ -689,6 +696,7 @@ int migrate_pages(struct list_head *from, struct list_head *to, if (!swapwrite) current->flags &= ~PF_SWAPWRITE; + putback_lru_pages(from); return nr_failed + retry; } @@ -702,11 +710,10 @@ 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; + int nr_failed = 0; struct page *page; struct list_head *p; @@ -740,26 +747,17 @@ redo: if (nr_pages > MIGRATE_CHUNK_SIZE) break; } - err = migrate_pages(pagelist, &newlist, &moved, &failed); + err = migrate_pages(pagelist, &newlist); - putback_lru_pages(&moved); /* Call release pages instead ?? */ - - 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); + if (err >= 0) { + nr_failed += err; + if (list_empty(&newlist) && !list_empty(pagelist)) + goto redo; } - list_splice(&failed, pagelist); - if (err < 0) - return err; +out: /* Calculate number of leftover pages */ - nr_pages = 0; list_for_each(p, pagelist) - nr_pages++; - return nr_pages; + nr_failed++; + return nr_failed; } -- cgit v1.2.3-70-g09d2 From 95a402c3847cc16f4ba03013cd01404fa0f14c2e Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Jun 2006 02:03:53 -0700 Subject: [PATCH] page migration: use allocator function for migrate_pages() Instead of passing a list of new pages, pass a function to allocate a new page. This allows the correct placement of MPOL_INTERLEAVE pages during page migration. It also further simplifies the callers of migrate pages. migrate_pages() becomes similar to migrate_pages_to() so drop migrate_pages_to(). The batching of new page allocations becomes unnecessary. Signed-off-by: Christoph Lameter Cc: Hugh Dickins Cc: Jes Sorensen Cc: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Cc: Andi Kleen Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- include/linux/migrate.h | 11 ++--- mm/mempolicy.c | 23 +++++++++- mm/migrate.c | 115 ++++++++++++++---------------------------------- 3 files changed, 59 insertions(+), 90 deletions(-) (limited to 'include/linux/migrate.h') diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 83af25949fa..5b95d6568dc 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -3,14 +3,15 @@ #include +typedef struct page *new_page_t(struct page *, unsigned long private); + #ifdef CONFIG_MIGRATION extern int isolate_lru_page(struct page *p, struct list_head *pagelist); extern int putback_lru_pages(struct list_head *l); extern int migrate_page(struct address_space *, struct page *, struct page *); -extern int migrate_pages(struct list_head *l, struct list_head *t); -extern int migrate_pages_to(struct list_head *pagelist, - struct vm_area_struct *vma, int dest); +extern int migrate_pages(struct list_head *l, new_page_t x, unsigned long); + extern int fail_migrate_page(struct address_space *, struct page *, struct page *); @@ -21,8 +22,8 @@ extern int migrate_prep(void); static inline int isolate_lru_page(struct page *p, struct list_head *list) { return -ENOSYS; } static inline int putback_lru_pages(struct list_head *l) { return 0; } -static inline int migrate_pages(struct list_head *l, struct list_head *t) - { return -ENOSYS; } +static inline int migrate_pages(struct list_head *l, new_page_t x, + unsigned long private) { return -ENOSYS; } static inline int migrate_pages_to(struct list_head *pagelist, struct vm_area_struct *vma, int dest) { return 0; } diff --git a/mm/mempolicy.c b/mm/mempolicy.c index 244f3f130e4..f432642e9e6 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -87,6 +87,7 @@ #include #include #include +#include #include #include @@ -587,6 +588,11 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, isolate_lru_page(page, pagelist); } +static struct page *new_node_page(struct page *page, unsigned long node) +{ + return alloc_pages_node(node, GFP_HIGHUSER, 0); +} + /* * Migrate pages from one node to a target node. * Returns error or the number of pages not migrated. @@ -604,7 +610,8 @@ int migrate_to_node(struct mm_struct *mm, int source, int dest, int flags) flags | MPOL_MF_DISCONTIG_OK, &pagelist); if (!list_empty(&pagelist)) - err = migrate_pages_to(&pagelist, NULL, dest); + err = migrate_pages(&pagelist, new_node_page, dest); + return err; } @@ -691,6 +698,12 @@ int do_migrate_pages(struct mm_struct *mm, } +static struct page *new_vma_page(struct page *page, unsigned long private) +{ + struct vm_area_struct *vma = (struct vm_area_struct *)private; + + return alloc_page_vma(GFP_HIGHUSER, vma, page_address_in_vma(page, vma)); +} #else static void migrate_page_add(struct page *page, struct list_head *pagelist, @@ -703,6 +716,11 @@ int do_migrate_pages(struct mm_struct *mm, { return -ENOSYS; } + +static struct page *new_vma_page(struct page *page, unsigned long private) +{ + return NULL; +} #endif long do_mbind(unsigned long start, unsigned long len, @@ -764,7 +782,8 @@ long do_mbind(unsigned long start, unsigned long len, err = mbind_range(vma, start, end, new); if (!list_empty(&pagelist)) - nr_failed = migrate_pages_to(&pagelist, vma, -1); + nr_failed = migrate_pages(&pagelist, new_vma_page, + (unsigned long)vma); if (!err && nr_failed && (flags & MPOL_MF_STRICT)) err = -EIO; diff --git a/mm/migrate.c b/mm/migrate.c index d3a1810a4c9..251a8d15825 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -28,9 +28,6 @@ #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)) /* @@ -587,18 +584,23 @@ static int move_to_new_page(struct page *newpage, struct page *page) * Obtain the lock on page, remove all ptes and migrate the page * to the newly allocated page in newpage. */ -static int unmap_and_move(struct page *newpage, struct page *page, int force) +static int unmap_and_move(new_page_t get_new_page, unsigned long private, + struct page *page, int force) { int rc = 0; + struct page *newpage = get_new_page(page, private); + + if (!newpage) + return -ENOMEM; if (page_count(page) == 1) /* page was freed from under us. So we are done. */ - goto ret; + goto move_newpage; rc = -EAGAIN; if (TestSetPageLocked(page)) { if (!force) - goto ret; + goto move_newpage; lock_page(page); } @@ -622,7 +624,7 @@ static int unmap_and_move(struct page *newpage, struct page *page, int force) remove_migration_ptes(page, page); unlock: unlock_page(page); -ret: + if (rc != -EAGAIN) { /* * A page that has been migrated has all references @@ -632,29 +634,33 @@ ret: */ list_del(&page->lru); move_to_lru(page); - - list_del(&newpage->lru); - move_to_lru(newpage); } + +move_newpage: + /* + * Move the new page to the LRU. If migration was not successful + * then this will free the page. + */ + move_to_lru(newpage); return rc; } /* * 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 isolated pages - * can be moved to. + * 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. All pages will be * retruned to the LRU or freed. * - * Return: Number of pages not migrated. + * Return: Number of pages not migrated or error code. */ -int migrate_pages(struct list_head *from, struct list_head *to) +int migrate_pages(struct list_head *from, + new_page_t get_new_page, unsigned long private) { int retry = 1; int nr_failed = 0; @@ -671,15 +677,14 @@ int migrate_pages(struct list_head *from, struct list_head *to) retry = 0; list_for_each_entry_safe(page, page2, from, lru) { - - if (list_empty(to)) - break; - cond_resched(); - rc = unmap_and_move(lru_to_page(to), page, pass > 2); + rc = unmap_and_move(get_new_page, private, + page, pass > 2); switch(rc) { + case -ENOMEM: + goto out; case -EAGAIN: retry++; break; @@ -692,72 +697,16 @@ int migrate_pages(struct list_head *from, struct list_head *to) } } } - + rc = 0; +out: if (!swapwrite) current->flags &= ~PF_SWAPWRITE; putback_lru_pages(from); - return nr_failed + retry; -} -/* - * 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); - int err = 0; - unsigned long offset = 0; - int nr_pages; - int nr_failed = 0; - struct page *page; - struct list_head *p; - -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); - - if (!page) { - err = -ENOMEM; - goto out; - } - list_add_tail(&page->lru, &newlist); - nr_pages++; - if (nr_pages > MIGRATE_CHUNK_SIZE) - break; - } - err = migrate_pages(pagelist, &newlist); - - if (err >= 0) { - nr_failed += err; - if (list_empty(&newlist) && !list_empty(pagelist)) - goto redo; - } -out: + if (rc) + return rc; - /* Calculate number of leftover pages */ - list_for_each(p, pagelist) - nr_failed++; - return nr_failed; + return nr_failed + retry; } + -- cgit v1.2.3-70-g09d2 From 742755a1d8ce2b548428f7aacf1758b4bba50080 Mon Sep 17 00:00:00 2001 From: Christoph Lameter Date: Fri, 23 Jun 2006 02:03:55 -0700 Subject: [PATCH] page migration: sys_move_pages(): support moving of individual pages move_pages() is used to move individual pages of a process. The function can be used to determine the location of pages and to move them onto the desired node. move_pages() returns status information for each page. long move_pages(pid, number_of_pages_to_move, addresses_of_pages[], nodes[] or NULL, status[], flags); The addresses of pages is an array of void * pointing to the pages to be moved. The nodes array contains the node numbers that the pages should be moved to. If a NULL is passed instead of an array then no pages are moved but the status array is updated. The status request may be used to determine the page state before issuing another move_pages() to move pages. The status array will contain the state of all individual page migration attempts when the function terminates. The status array is only valid if move_pages() completed successfullly. Possible page states in status[]: 0..MAX_NUMNODES The page is now on the indicated node. -ENOENT Page is not present -EACCES Page is mapped by multiple processes and can only be moved if MPOL_MF_MOVE_ALL is specified. -EPERM The page has been mlocked by a process/driver and cannot be moved. -EBUSY Page is busy and cannot be moved. Try again later. -EFAULT Invalid address (no VMA or zero page). -ENOMEM Unable to allocate memory on target node. -EIO Unable to write back page. The page must be written back in order to move it since the page is dirty and the filesystem does not provide a migration function that would allow the moving of dirty pages. -EINVAL A dirty page cannot be moved. The filesystem does not provide a migration function and has no ability to write back pages. The flags parameter indicates what types of pages to move: MPOL_MF_MOVE Move pages that are only mapped by the process. MPOL_MF_MOVE_ALL Also move pages that are mapped by multiple processes. Requires sufficient capabilities. Possible return codes from move_pages() -ENOENT No pages found that would require moving. All pages are either already on the target node, not present, had an invalid address or could not be moved because they were mapped by multiple processes. -EINVAL Flags other than MPOL_MF_MOVE(_ALL) specified or an attempt to migrate pages in a kernel thread. -EPERM MPOL_MF_MOVE_ALL specified without sufficient priviledges. or an attempt to move a process belonging to another user. -EACCES One of the target nodes is not allowed by the current cpuset. -ENODEV One of the target nodes is not online. -ESRCH Process does not exist. -E2BIG Too many pages to move. -ENOMEM Not enough memory to allocate control array. -EFAULT Parameters could not be accessed. A test program for move_pages() may be found with the patches on ftp.kernel.org:/pub/linux/kernel/people/christoph/pmig/patches-2.6.17-rc4-mm3 From: Christoph Lameter Detailed results for sys_move_pages() Pass a pointer to an integer to get_new_page() that may be used to indicate where the completion status of a migration operation should be placed. This allows sys_move_pags() to report back exactly what happened to each page. Wish there would be a better way to do this. Looks a bit hacky. Signed-off-by: Christoph Lameter Cc: Hugh Dickins Cc: Jes Sorensen Cc: KAMEZAWA Hiroyuki Cc: Lee Schermerhorn Cc: Andi Kleen Cc: Michael Kerrisk Signed-off-by: Andrew Morton Signed-off-by: Linus Torvalds --- Documentation/vm/page_migration | 29 ++--- arch/ia64/kernel/entry.S | 2 +- include/asm-ia64/unistd.h | 2 +- include/linux/migrate.h | 2 +- include/linux/syscalls.h | 5 + kernel/sys_ni.c | 1 + mm/mempolicy.c | 4 +- mm/migrate.c | 268 +++++++++++++++++++++++++++++++++++++++- 8 files changed, 288 insertions(+), 25 deletions(-) (limited to 'include/linux/migrate.h') diff --git a/Documentation/vm/page_migration b/Documentation/vm/page_migration index 0a5d5fb1885..99f89aa1016 100644 --- a/Documentation/vm/page_migration +++ b/Documentation/vm/page_migration @@ -26,8 +26,13 @@ a process are located. See also the numa_maps manpage in the numactl package. Manual migration is useful if for example the scheduler has relocated a process to a processor on a distant node. A batch scheduler or an administrator may detect the situation and move the pages of the process -nearer to the new processor. At some point in the future we may have -some mechanism in the scheduler that will automatically move the pages. +nearer to the new processor. The kernel itself does only provide +manual page migration support. Automatic page migration may be implemented +through user space processes that move pages. A special function call +"move_pages" allows the moving of individual pages within a process. +A NUMA profiler may f.e. obtain a log showing frequent off node +accesses and may use the result to move pages to more advantageous +locations. Larger installations usually partition the system using cpusets into sections of nodes. Paul Jackson has equipped cpusets with the ability to @@ -62,22 +67,14 @@ A. In kernel use of migrate_pages() It also prevents the swapper or other scans to encounter the page. -2. Generate a list of newly allocates pages. These pages will contain the - contents of the pages from the first list after page migration is - complete. +2. We need to have a function of type new_page_t that can be + passed to migrate_pages(). This function should figure out + how to allocate the correct new page given the old page. 3. The migrate_pages() function is called which attempts - to do the migration. It returns the moved pages in the - list specified as the third parameter and the failed - migrations in the fourth parameter. When the function - returns the first list will contain the pages that could still be retried. - -4. The leftover pages of various types are returned - to the LRU using putback_to_lru_pages() or otherwise - disposed of. The pages will still have the refcount as - increased by isolate_lru_pages() if putback_to_lru_pages() is not - used! The kernel may want to handle the various cases of failures in - different ways. + to do the migration. It will call the function to allocate + the new page for each page that is considered for + moving. B. How migrate_pages() works ---------------------------- diff --git a/arch/ia64/kernel/entry.S b/arch/ia64/kernel/entry.S index bcb80ca5cf4..32c999f58d1 100644 --- a/arch/ia64/kernel/entry.S +++ b/arch/ia64/kernel/entry.S @@ -1584,7 +1584,7 @@ sys_call_table: data8 sys_keyctl data8 sys_ioprio_set data8 sys_ioprio_get // 1275 - data8 sys_ni_syscall + data8 sys_move_pages data8 sys_inotify_init data8 sys_inotify_add_watch data8 sys_inotify_rm_watch diff --git a/include/asm-ia64/unistd.h b/include/asm-ia64/unistd.h index 632f2eedf72..bb0eb727dcd 100644 --- a/include/asm-ia64/unistd.h +++ b/include/asm-ia64/unistd.h @@ -265,7 +265,7 @@ #define __NR_keyctl 1273 #define __NR_ioprio_set 1274 #define __NR_ioprio_get 1275 -/* 1276 is available for reuse (was briefly sys_set_zone_reclaim) */ +#define __NR_move_pages 1276 #define __NR_inotify_init 1277 #define __NR_inotify_add_watch 1278 #define __NR_inotify_rm_watch 1279 diff --git a/include/linux/migrate.h b/include/linux/migrate.h index 5b95d6568dc..5dba23a1c0d 100644 --- a/include/linux/migrate.h +++ b/include/linux/migrate.h @@ -3,7 +3,7 @@ #include -typedef struct page *new_page_t(struct page *, unsigned long private); +typedef struct page *new_page_t(struct page *, unsigned long private, int **); #ifdef CONFIG_MIGRATION extern int isolate_lru_page(struct page *p, struct list_head *pagelist); diff --git a/include/linux/syscalls.h b/include/linux/syscalls.h index bd67a4413df..7e3f2349091 100644 --- a/include/linux/syscalls.h +++ b/include/linux/syscalls.h @@ -516,6 +516,11 @@ asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask, asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode, const unsigned long __user *from, const unsigned long __user *to); +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); asmlinkage long sys_mbind(unsigned long start, unsigned long len, unsigned long mode, unsigned long __user *nmask, diff --git a/kernel/sys_ni.c b/kernel/sys_ni.c index 5433195040f..597229749de 100644 --- a/kernel/sys_ni.c +++ b/kernel/sys_ni.c @@ -87,6 +87,7 @@ cond_syscall(sys_inotify_init); cond_syscall(sys_inotify_add_watch); cond_syscall(sys_inotify_rm_watch); cond_syscall(sys_migrate_pages); +cond_syscall(sys_move_pages); cond_syscall(sys_chown16); cond_syscall(sys_fchown16); cond_syscall(sys_getegid16); diff --git a/mm/mempolicy.c b/mm/mempolicy.c index f432642e9e6..05b84acf0bb 100644 --- a/mm/mempolicy.c +++ b/mm/mempolicy.c @@ -588,7 +588,7 @@ static void migrate_page_add(struct page *page, struct list_head *pagelist, isolate_lru_page(page, pagelist); } -static struct page *new_node_page(struct page *page, unsigned long node) +static struct page *new_node_page(struct page *page, unsigned long node, int **x) { return alloc_pages_node(node, GFP_HIGHUSER, 0); } @@ -698,7 +698,7 @@ int do_migrate_pages(struct mm_struct *mm, } -static struct page *new_vma_page(struct page *page, unsigned long private) +static struct page *new_vma_page(struct page *page, unsigned long private, int **x) { struct vm_area_struct *vma = (struct vm_area_struct *)private; diff --git a/mm/migrate.c b/mm/migrate.c index 251a8d15825..033a12f4c94 100644 --- a/mm/migrate.c +++ b/mm/migrate.c @@ -25,6 +25,8 @@ #include #include #include +#include +#include #include "internal.h" @@ -62,9 +64,8 @@ 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) { @@ -588,7 +589,8 @@ static int unmap_and_move(new_page_t get_new_page, unsigned long private, struct page *page, int force) { int rc = 0; - struct page *newpage = get_new_page(page, private); + int *result = NULL; + struct page *newpage = get_new_page(page, private, &result); if (!newpage) return -ENOMEM; @@ -642,6 +644,12 @@ move_newpage: * then this will free the page. */ move_to_lru(newpage); + if (result) { + if (rc) + *result = rc; + else + *result = page_to_nid(newpage); + } return rc; } @@ -710,3 +718,255 @@ out: return nr_failed + retry; } +#ifdef CONFIG_NUMA +/* + * Move a list of individual pages + */ +struct page_to_node { + unsigned long addr; + struct page *page; + int node; + int status; +}; + +static struct page *new_page_node(struct page *p, unsigned long private, + int **result) +{ + struct page_to_node *pm = (struct page_to_node *)private; + + while (pm->node != MAX_NUMNODES && pm->page != p) + pm++; + + if (pm->node == MAX_NUMNODES) + return NULL; + + *result = &pm->status; + + return alloc_pages_node(pm->node, GFP_HIGHUSER, 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. + */ +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); + + /* + * 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) + 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 */ + goto put_and_set; + + pp->page = page; + err = page_to_nid(page); + + if (err == pp->node) + /* + * Node already in the right place + */ + goto put_and_set; + + 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 (!list_empty(&pagelist)) + err = migrate_pages(&pagelist, new_page_node, + (unsigned long)pm); + else + err = -ENOENT; + + 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. + */ +static int do_pages_stat(struct mm_struct *mm, struct page_to_node *pm) +{ + 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; + } + + up_read(&mm->mmap_sem); + return 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) +{ + int err = 0; + int i; + struct task_struct *task; + nodemask_t task_nodes; + struct mm_struct *mm; + struct page_to_node *pm = NULL; + + /* Check flags */ + if (flags & ~(MPOL_MF_MOVE|MPOL_MF_MOVE_ALL)) + return -EINVAL; + + if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE)) + return -EPERM; + + /* 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); + + if (!mm) + return -EINVAL; + + /* + * 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; + } + + task_nodes = cpuset_mems_allowed(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 *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_online(node)) + goto out; + + err = -EACCES; + if (!node_isset(node, task_nodes)) + goto out; + + pm[i].node = node; + } + } + /* 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); + + if (err >= 0) + /* Return status information */ + for (i = 0; i < nr_pages; i++) + if (put_user(pm[i].status, status + i)) + err = -EFAULT; + +out: + vfree(pm); +out2: + mmput(mm); + return err; +} +#endif + -- cgit v1.2.3-70-g09d2