#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
+#include <linux/writeback.h>
#include "internal.h"
static inline void move_to_lru(struct page *page)
{
- list_del(&page->lru);
if (PageActive(page)) {
/*
* lru_cache_add_active checks that
int count = 0;
list_for_each_entry_safe(page, page2, l, lru) {
+ list_del(&page->lru);
move_to_lru(page);
count++;
}
/*
* Restore a potential migration pte to a working pte entry
*/
-static void remove_migration_pte(struct vm_area_struct *vma, unsigned long addr,
+static void remove_migration_pte(struct vm_area_struct *vma,
struct page *old, struct page *new)
{
struct mm_struct *mm = vma->vm_mm;
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))
if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
goto out;
- inc_mm_counter(mm, anon_rss);
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);
- page_add_anon_rmap(new, vma, addr);
+
+ 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);
+ lazy_mmu_prot_update(pte);
+
out:
pte_unmap_unlock(ptep, ptl);
}
/*
- * Get rid of all migration entries and replace them by
- * references to the indicated page.
- *
+ * 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.
*/
-static void remove_migration_ptes(struct page *old, struct page *new)
+static void remove_anon_migration_ptes(struct page *old, struct page *new)
{
struct anon_vma *anon_vma;
struct vm_area_struct *vma;
spin_lock(&anon_vma->lock);
list_for_each_entry(vma, &anon_vma->head, anon_vma_node)
- remove_migration_pte(vma, page_address_in_vma(new, vma),
- old, new);
+ 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.
{
struct page **radix_pointer;
+ if (!mapping) {
+ /* Anonymous page */
+ if (page_count(page) != 1)
+ return -EAGAIN;
+ return 0;
+ }
+
write_lock_irq(&mapping->tree_lock);
radix_pointer = (struct page **)radix_tree_lookup_slot(
&mapping->page_tree,
page_index(page));
- if (!page_mapping(page) ||
- page_count(page) != 2 + !!PagePrivate(page) ||
+ if (page_count(page) != 2 + !!PagePrivate(page) ||
*radix_pointer != page) {
write_unlock_irq(&mapping->tree_lock);
return -EAGAIN;
* Now we know that no one else is looking at the page.
*/
get_page(newpage);
+#ifdef CONFIG_SWAP
if (PageSwapCache(page)) {
SetPageSwapCache(newpage);
set_page_private(newpage, page_private(page));
}
+#endif
*radix_pointer = newpage;
__put_page(page);
set_page_dirty(newpage);
}
+#ifdef CONFIG_SWAP
ClearPageSwapCache(page);
+#endif
ClearPageActive(page);
ClearPagePrivate(page);
set_page_private(page, 0);
return rc;
migrate_page_copy(newpage, page);
-
- /*
- * 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.
- */
- remove_from_swap(newpage);
return 0;
}
EXPORT_SYMBOL(migrate_page);
}
EXPORT_SYMBOL(buffer_migrate_page);
-static int fallback_migrate_page(struct address_space *mapping,
- struct page *newpage, struct page *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;
+
/*
- * 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.
+ * 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.
*/
- if (PageDirty(page)) {
- switch (pageout(page, mapping)) {
- case PAGE_KEEP:
- case PAGE_ACTIVATE:
- return -EAGAIN;
+ remove_migration_ptes(page, page);
- case PAGE_SUCCESS:
- /* Relock since we lost the lock */
- lock_page(page);
- /* Must retry since page state may have changed */
- return -EAGAIN;
+ rc = mapping->a_ops->writepage(page, &wbc);
+ if (rc < 0)
+ /* I/O Error writing */
+ return -EIO;
- case PAGE_CLEAN:
- ; /* try to migrate the page below */
- }
- }
+ 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.
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(struct page *newpage, struct page *page, int force)
+{
+ int rc = 0;
+
+ if (page_count(page) == 1)
+ /* page was freed from under us. So we are done. */
+ goto ret;
+
+ rc = -EAGAIN;
+ if (TestSetPageLocked(page)) {
+ if (!force)
+ goto ret;
+ lock_page(page);
+ }
+
+ if (PageWriteback(page)) {
+ if (!force)
+ goto unlock;
+ wait_on_page_writeback(page);
+ }
+
+ /*
+ * Establish migration ptes or remove ptes
+ */
+ if (try_to_unmap(page, 1) != SWAP_FAIL) {
+ if (!page_mapped(page))
+ rc = move_to_new_page(newpage, page);
+ } else
+ /* A vma has VM_LOCKED set -> permanent failure */
+ rc = -EPERM;
+
+ if (rc)
+ remove_migration_ptes(page, page);
+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);
+ }
+ 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 pages isolated
+ * The second list contains new pages that the isolated pages
* can be moved to.
*
* 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;
+ int retry = 1;
int nr_failed = 0;
int pass = 0;
struct page *page;
if (!swapwrite)
current->flags |= PF_SWAPWRITE;
-redo:
- retry = 0;
-
- list_for_each_entry_safe(page, page2, from, lru) {
- struct page *newpage = NULL;
- struct address_space *mapping;
-
- cond_resched();
+ for(pass = 0; pass < 10 && retry; pass++) {
+ retry = 0;
- rc = 0;
- if (page_count(page) == 1)
- /* page was freed from under us. So we are done. */
- goto next;
+ list_for_each_entry_safe(page, page2, from, lru) {
- if (to && list_empty(to))
- break;
-
- /*
- * 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;
-
- /*
- * 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;
-
- /*
- * 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.
- */
- rc = -EPERM;
- if (try_to_unmap(page, 1) == SWAP_FAIL)
- /* A vma has VM_LOCKED set -> permanent failure */
- goto unlock_page;
-
- rc = -EAGAIN;
- if (page_mapped(page))
- goto unlock_page;
+ if (list_empty(to))
+ break;
- newpage = lru_to_page(to);
- lock_page(newpage);
- /* Prepare mapping for the new page.*/
- newpage->index = page->index;
- newpage->mapping = page->mapping;
+ cond_resched();
- /*
- * Pages are properly locked and writeback is complete.
- * Try to migrate the page.
- */
- mapping = page_mapping(page);
- if (!mapping)
- goto unlock_both;
+ rc = unmap_and_move(lru_to_page(to), page, pass > 2);
- 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);
-
-unlock_both:
- unlock_page(newpage);
-
-unlock_page:
- unlock_page(page);
-
-next:
- if (rc) {
- if (newpage)
- newpage->mapping = NULL;
-
- if (rc == -EAGAIN)
+ switch(rc) {
+ case -EAGAIN:
retry++;
- else {
+ break;
+ case 0:
+ break;
+ default:
/* Permanent failure */
- list_move(&page->lru, failed);
nr_failed++;
+ break;
}
- } else {
- if (newpage) {
- /* Successful migration. Return page to LRU */
- move_to_lru(newpage);
- }
- list_move(&page->lru, moved);
}
}
- if (retry && pass++ < 10)
- goto redo;
if (!swapwrite)
current->flags &= ~PF_SWAPWRITE;
+ putback_lru_pages(from);
return nr_failed + retry;
}
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;
if (nr_pages > MIGRATE_CHUNK_SIZE)
break;
}
- err = migrate_pages(pagelist, &newlist, &moved, &failed);
-
- putback_lru_pages(&moved); /* Call release pages instead ?? */
+ err = migrate_pages(pagelist, &newlist);
- 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;
}
projects / deliverable / linux.git / blobdiff