aboutsummaryrefslogtreecommitdiff
diff options
context:
space:
mode:
authorChristoph Lameter <clameter@sgi.com>2006-03-22 00:09:12 -0800
committerLinus Torvalds <torvalds@g5.osdl.org>2006-03-22 07:54:06 -0800
commitb20a35035f983f4ac7e29c4a68f30e43510007e0 (patch)
treefdf090ddddbcc275349f62f71adc98649e2c683b
parent442295c94bf650221af3ef20fc68fa3e93876818 (diff)
downloadlinux-2.6.34-ux500-b20a35035f983f4ac7e29c4a68f30e43510007e0.tar.gz
[PATCH] page migration reorg
Centralize the page migration functions in anticipation of additional tinkering. Creates a new file mm/migrate.c 1. Extract buffer_migrate_page() from fs/buffer.c 2. Extract central migration code from vmscan.c 3. Extract some components from mempolicy.c 4. Export pageout() and remove_from_swap() from vmscan.c 5. Make it possible to configure NUMA systems without page migration and non-NUMA systems with page migration. I had to so some #ifdeffing in mempolicy.c that may need a cleanup. Signed-off-by: Christoph Lameter <clameter@sgi.com> Signed-off-by: Andrew Morton <akpm@osdl.org> Signed-off-by: Linus Torvalds <torvalds@osdl.org>
-rw-r--r--fs/buffer.c62
-rw-r--r--fs/xfs/linux-2.6/xfs_buf.c1
-rw-r--r--include/linux/migrate.h36
-rw-r--r--include/linux/swap.h34
-rw-r--r--mm/Kconfig6
-rw-r--r--mm/Makefile2
-rw-r--r--mm/mempolicy.c113
-rw-r--r--mm/migrate.c655
-rw-r--r--mm/swap_state.c1
-rw-r--r--mm/vmscan.c491
10 files changed, 741 insertions, 660 deletions
diff --git a/fs/buffer.c b/fs/buffer.c
index a9b39940200..1d3683d496f 100644
--- a/fs/buffer.c
+++ b/fs/buffer.c
@@ -3051,68 +3051,6 @@ asmlinkage long sys_bdflush(int func, long data)
}
/*
- * Migration function for pages with buffers. This function can only be used
- * if the underlying filesystem guarantees that no other references to "page"
- * exist.
- */
-#ifdef CONFIG_MIGRATION
-int buffer_migrate_page(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);
-
- head = page_buffers(page);
-
- rc = migrate_page_remove_references(newpage, page, 3);
- 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);
-#endif
-
-/*
* Buffer-head allocation
*/
static kmem_cache_t *bh_cachep;
diff --git a/fs/xfs/linux-2.6/xfs_buf.c b/fs/xfs/linux-2.6/xfs_buf.c
index bfb4f2917bb..8cdfa415165 100644
--- a/fs/xfs/linux-2.6/xfs_buf.c
+++ b/fs/xfs/linux-2.6/xfs_buf.c
@@ -29,6 +29,7 @@
#include <linux/blkdev.h>
#include <linux/hash.h>
#include <linux/kthread.h>
+#include <linux/migrate.h>
#include "xfs_linux.h"
STATIC kmem_zone_t *xfs_buf_zone;
diff --git a/include/linux/migrate.h b/include/linux/migrate.h
new file mode 100644
index 00000000000..7d09962c3c0
--- /dev/null
+++ b/include/linux/migrate.h
@@ -0,0 +1,36 @@
+#ifndef _LINUX_MIGRATE_H
+#define _LINUX_MIGRATE_H
+
+#include <linux/config.h>
+#include <linux/mm.h>
+
+#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 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);
+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 migrate_prep(void);
+
+#else
+
+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_prep(void) { return -ENOSYS; }
+
+/* Possible settings for the migrate_page() method in address_operations */
+#define migrate_page NULL
+#define fail_migrate_page NULL
+
+#endif /* CONFIG_MIGRATION */
+#endif /* _LINUX_MIGRATE_H */
diff --git a/include/linux/swap.h b/include/linux/swap.h
index 3dc6c89c49b..12415dd9445 100644
--- a/include/linux/swap.h
+++ b/include/linux/swap.h
@@ -175,6 +175,21 @@ extern void swap_setup(void);
extern unsigned long try_to_free_pages(struct zone **, gfp_t);
extern unsigned long shrink_all_memory(unsigned long nr_pages);
extern int vm_swappiness;
+extern int remove_mapping(struct address_space *mapping, struct page *page);
+
+/* possible outcome of pageout() */
+typedef enum {
+ /* failed to write page out, page is locked */
+ PAGE_KEEP,
+ /* move page to the active list, page is locked */
+ PAGE_ACTIVATE,
+ /* page has been sent to the disk successfully, page is unlocked */
+ PAGE_SUCCESS,
+ /* page is clean and locked */
+ PAGE_CLEAN,
+} pageout_t;
+
+extern pageout_t pageout(struct page *page, struct address_space *mapping);
#ifdef CONFIG_NUMA
extern int zone_reclaim_mode;
@@ -188,25 +203,6 @@ static inline int zone_reclaim(struct zone *z, gfp_t mask, unsigned int order)
}
#endif
-#ifdef CONFIG_MIGRATION
-extern int isolate_lru_page(struct page *p);
-extern unsigned long 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 unsigned long migrate_pages(struct list_head *l, struct list_head *t,
- struct list_head *moved, struct list_head *failed);
-extern int fail_migrate_page(struct page *, struct page *);
-#else
-static inline int isolate_lru_page(struct page *p) { 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; }
-/* Possible settings for the migrate_page() method in address_operations */
-#define migrate_page NULL
-#define fail_migrate_page NULL
-#endif
-
#ifdef CONFIG_MMU
/* linux/mm/shmem.c */
extern int shmem_unuse(swp_entry_t entry, struct page *page);
diff --git a/mm/Kconfig b/mm/Kconfig
index a9cb80ae640..bd80460360d 100644
--- a/mm/Kconfig
+++ b/mm/Kconfig
@@ -137,5 +137,11 @@ config SPLIT_PTLOCK_CPUS
# support for page migration
#
config MIGRATION
+ bool "Page migration"
def_bool y if NUMA || SPARSEMEM || DISCONTIGMEM
depends on SWAP
+ help
+ Allows the migration of the physical location of pages of processes
+ while the virtual addresses are not changed. This is useful for
+ example on NUMA systems to put pages nearer to the processors accessing
+ the page.
diff --git a/mm/Makefile b/mm/Makefile
index 9aa03fa1dcc..f10c753dce6 100644
--- a/mm/Makefile
+++ b/mm/Makefile
@@ -22,3 +22,5 @@ obj-$(CONFIG_SLOB) += slob.o
obj-$(CONFIG_SLAB) += slab.o
obj-$(CONFIG_MEMORY_HOTPLUG) += memory_hotplug.o
obj-$(CONFIG_FS_XIP) += filemap_xip.o
+obj-$(CONFIG_MIGRATION) += migrate.o
+
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 96195dcb62e..e93cc740c22 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -86,6 +86,7 @@
#include <linux/swap.h>
#include <linux/seq_file.h>
#include <linux/proc_fs.h>
+#include <linux/migrate.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
@@ -95,9 +96,6 @@
#define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1) /* Invert check for nodemask */
#define MPOL_MF_STATS (MPOL_MF_INTERNAL << 2) /* Gather statistics */
-/* The number of pages to migrate per call to migrate_pages() */
-#define MIGRATE_CHUNK_SIZE 256
-
static struct kmem_cache *policy_cache;
static struct kmem_cache *sn_cache;
@@ -331,17 +329,10 @@ check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
struct vm_area_struct *first, *vma, *prev;
if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- /* Must have swap device for migration */
- if (nr_swap_pages <= 0)
- return ERR_PTR(-ENODEV);
- /*
- * Clear the LRU lists so pages can be isolated.
- * Note that pages may be moved off the LRU after we have
- * drained them. Those pages will fail to migrate like other
- * pages that may be busy.
- */
- lru_add_drain_all();
+ err = migrate_prep();
+ if (err)
+ return ERR_PTR(err);
}
first = find_vma(mm, start);
@@ -550,92 +541,18 @@ long do_get_mempolicy(int *policy, nodemask_t *nmask,
return err;
}
+#ifdef CONFIG_MIGRATION
/*
* page migration
*/
-
static void migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags)
{
/*
* Avoid migrating a page that is shared with others.
*/
- if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
- if (isolate_lru_page(page))
- list_add_tail(&page->lru, pagelist);
- }
-}
-
-/*
- * 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
- */
-static 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;
-
-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, &moved, &failed);
-
- 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);
- }
- 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;
+ if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1)
+ isolate_lru_page(page, pagelist);
}
/*
@@ -742,8 +659,23 @@ int do_migrate_pages(struct mm_struct *mm,
if (err < 0)
return err;
return busy;
+
}
+#else
+
+static void migrate_page_add(struct page *page, struct list_head *pagelist,
+ unsigned long flags)
+{
+}
+
+int do_migrate_pages(struct mm_struct *mm,
+ const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+{
+ return -ENOSYS;
+}
+#endif
+
long do_mbind(unsigned long start, unsigned long len,
unsigned long mode, nodemask_t *nmask, unsigned long flags)
{
@@ -808,6 +740,7 @@ long do_mbind(unsigned long start, unsigned long len,
if (!err && nr_failed && (flags & MPOL_MF_STRICT))
err = -EIO;
}
+
if (!list_empty(&pagelist))
putback_lru_pages(&pagelist);
diff --git a/mm/migrate.c b/mm/migrate.c
new file mode 100644
index 00000000000..09f6e4aa87f
--- /dev/null
+++ b/mm/migrate.c
@@ -0,0 +1,655 @@
+/*
+ * Memory Migration functionality - linux/mm/migration.c
+ *
+ * Copyright (C) 2006 Silicon Graphics, Inc., Christoph Lameter
+ *
+ * Page migration was first developed in the context of the memory hotplug
+ * project. The main authors of the migration code are:
+ *
+ * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
+ * Hirokazu Takahashi <taka@valinux.co.jp>
+ * Dave Hansen <haveblue@us.ibm.com>
+ * Christoph Lameter <clameter@sgi.com>
+ */
+
+#include <linux/migrate.h>
+#include <linux/module.h>
+#include <linux/swap.h>
+#include <linux/pagemap.h>
+#include <linux/buffer_head.h> /* for try_to_release_page(),
+ buffer_heads_over_limit */
+#include <linux/mm_inline.h>
+#include <linux/pagevec.h>
+#include <linux/rmap.h>
+#include <linux/topology.h>
+#include <linux/cpu.h>
+#include <linux/cpuset.h>
+#include <linux/swapops.h>
+
+#include "internal.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))
+
+/*
+ * 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)) {
+ ret = 0;
+ get_page(page);
+ 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;
+}
+
+/*
+ * 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().
+ */
+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
+ * drained them. Those pages will fail to migrate like other
+ * pages that may be busy.
+ */
+ lru_add_drain_all();
+
+ return 0;
+}
+
+static inline void move_to_lru(struct page *page)
+{
+ list_del(&page->lru);
+ 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);
+}
+
+/*
+ * Add isolated pages on the list back to the LRU.
+ *
+ * returns the number of pages put back.
+ */
+int putback_lru_pages(struct list_head *l)
+{
+ struct page *page;
+ struct page *page2;
+ int count = 0;
+
+ list_for_each_entry_safe(page, page2, l, lru) {
+ move_to_lru(page);
+ count++;
+ }
+ return count;
+}
+
+/*
+ * Non migratable page
+ */
+int fail_migrate_page(struct page *newpage, struct page *page)
+{
+ return -EIO;
+}
+EXPORT_SYMBOL(fail_migrate_page);
+
+/*
+ * swapout a single page
+ * page is locked upon entry, unlocked on exit
+ */
+static int swap_page(struct page *page)
+{
+ struct address_space *mapping = page_mapping(page);
+
+ if (page_mapped(page) && mapping)
+ if (try_to_unmap(page, 1) != SWAP_SUCCESS)
+ goto unlock_retry;
+
+ 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;
+
+ case PAGE_SUCCESS:
+ goto retry;
+
+ case PAGE_CLEAN:
+ ; /* try to free the page below */
+ }
+ }
+
+ if (PagePrivate(page)) {
+ if (!try_to_release_page(page, GFP_KERNEL) ||
+ (!mapping && page_count(page) == 1))
+ goto unlock_retry;
+ }
+
+ if (remove_mapping(mapping, page)) {
+ /* Success */
+ unlock_page(page);
+ return 0;
+ }
+
+unlock_retry:
+ unlock_page(page);
+
+retry:
+ return -EAGAIN;
+}
+EXPORT_SYMBOL(swap_page);
+
+/*
+ * Remove references for a page and establish the new page with the correct
+ * basic settings to be able to stop accesses to the page.
+ */
+int migrate_page_remove_references(struct page *newpage,
+ struct page *page, int nr_refs)
+{
+ struct address_space *mapping = page_mapping(page);
+ struct page **radix_pointer;
+
+ /*
+ * 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;
+
+ /*
+ * 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;
+
+ /*
+ * Give up if we were unable to remove all mappings.
+ */
+ if (page_mapcount(page))
+ return -EAGAIN;
+
+ 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) != nr_refs ||
+ *radix_pointer != page) {
+ write_unlock_irq(&mapping->tree_lock);
+ return 1;
+ }
+
+ /*
+ * 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));
+ }
+
+ *radix_pointer = newpage;
+ __put_page(page);
+ write_unlock_irq(&mapping->tree_lock);
+
+ 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)
+{
+ copy_highpage(newpage, page);
+
+ if (PageError(page))
+ SetPageError(newpage);
+ if (PageReferenced(page))
+ SetPageReferenced(newpage);
+ if (PageUptodate(page))
+ SetPageUptodate(newpage);
+ if (PageActive(page))
+ SetPageActive(newpage);
+ if (PageChecked(page))
+ SetPageChecked(newpage);
+ if (PageMappedToDisk(page))
+ SetPageMappedToDisk(newpage);
+
+ if (PageDirty(page)) {
+ clear_page_dirty_for_io(page);
+ set_page_dirty(newpage);
+ }
+
+ ClearPageSwapCache(page);
+ ClearPageActive(page);
+ ClearPagePrivate(page);
+ set_page_private(page, 0);
+ page->mapping = NULL;
+
+ /*
+ * If any waiters have accumulated on the new page then
+ * wake them up.
+ */
+ if (PageWriteback(newpage))
+ end_page_writeback(newpage);
+}
+EXPORT_SYMBOL(migrate_page_copy);
+
+/*
+ * Common logic to directly migrate a single page suitable for
+ * pages that do not use PagePrivate.
+ *
+ * Pages are locked upon entry and exit.
+ */
+int migrate_page(struct page *newpage, struct page *page)
+{
+ int rc;
+
+ BUG_ON(PageWriteback(page)); /* Writeback must be complete */
+
+ rc = migrate_page_remove_references(newpage, page, 2);
+
+ if (rc)
+ 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);
+
+/*
+ * 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 returns after 10 attempts or if no pages
+ * are movable anymore because to has become empty
+ * or no retryable pages exist anymore.
+ *
+ * Return: Number of pages not migrated when "to" ran empty.
+ */
+int migrate_pages(struct list_head *from, struct list_head *to,
+ struct list_head *moved, struct list_head *failed)
+{
+ int retry;
+ int nr_failed = 0;
+ int pass = 0;
+ struct page *page;
+ struct page *page2;
+ int swapwrite = current->flags & PF_SWAPWRITE;
+ int rc;
+
+ 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();
+
+ rc = 0;
+ if (page_count(page) == 1)
+ /* page was freed from under us. So we are done. */
+ goto next;
+
+ 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;
+ }
+
+ /*
+ * 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;
+ }
+ }
+
+ if (!to) {
+ rc = swap_page(page);
+ goto next;
+ }
+
+ newpage = lru_to_page(to);
+ lock_page(newpage);
+
+ /*
+ * Pages are properly locked and writeback is complete.
+ * Try to migrate the page.
+ */
+ mapping = page_mapping(page);
+ if (!mapping)
+ goto unlock_both;
+
+ 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;
+ }
+
+ /*
+ * 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 */
+ }
+ }
+
+ /*
+ * 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;
+ }
+
+ /*
+ * 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) {
+ /*
+ * Persistently unable to drop buffers..... As a
+ * measure of last resort we fall back to
+ * swap_page().
+ */
+ unlock_page(newpage);
+ newpage = NULL;
+ rc = swap_page(page);
+ goto next;
+ }
+
+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);
+ }
+ }
+ if (retry && pass++ < 10)
+ goto redo;
+
+ if (!swapwrite)
+ current->flags &= ~PF_SWAPWRITE;
+
+ return nr_failed + retry;
+}
+
+/*
+ * 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 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);
+
+ head = page_buffers(page);
+
+ rc = migrate_page_remove_references(newpage, page, 3);
+
+ 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);
+
+/*
+ * 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;
+
+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, &moved, &failed);
+
+ 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);
+ }
+ 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;
+}
diff --git a/mm/swap_state.c b/mm/swap_state.c
index db8a3d3e163..d7af296833f 100644
--- a/mm/swap_state.c
+++ b/mm/swap_state.c
@@ -15,6 +15,7 @@
#include <linux/buffer_head.h>
#include <linux/backing-dev.h>
#include <linux/pagevec.h>
+#include <linux/migrate.h>
#include <asm/pgtable.h>
diff --git a/mm/vmscan.c b/mm/vmscan.c
index 548e023c193..fd572bbdc9f 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -42,18 +42,6 @@
#include "internal.h"
-/* possible outcome of pageout() */
-typedef enum {
- /* failed to write page out, page is locked */
- PAGE_KEEP,
- /* move page to the active list, page is locked */
- PAGE_ACTIVATE,
- /* page has been sent to the disk successfully, page is unlocked */
- PAGE_SUCCESS,
- /* page is clean and locked */
- PAGE_CLEAN,
-} pageout_t;
-
struct scan_control {
/* Incremented by the number of inactive pages that were scanned */
unsigned long nr_scanned;
@@ -304,7 +292,7 @@ static void handle_write_error(struct address_space *mapping,
* pageout is called by shrink_page_list() for each dirty page.
* Calls ->writepage().
*/
-static pageout_t pageout(struct page *page, struct address_space *mapping)
+pageout_t pageout(struct page *page, struct address_space *mapping)
{
/*
* If the page is dirty, only perform writeback if that write
@@ -372,7 +360,7 @@ static pageout_t pageout(struct page *page, struct address_space *mapping)
return PAGE_CLEAN;
}
-static int remove_mapping(struct address_space *mapping, struct page *page)
+int remove_mapping(struct address_space *mapping, struct page *page)
{
if (!mapping)
return 0; /* truncate got there first */
@@ -570,481 +558,6 @@ keep:
return nr_reclaimed;
}
-#ifdef CONFIG_MIGRATION
-static inline void move_to_lru(struct page *page)
-{
- list_del(&page->lru);
- 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);
-}
-
-/*
- * Add isolated pages on the list back to the LRU.
- *
- * returns the number of pages put back.
- */
-unsigned long putback_lru_pages(struct list_head *l)
-{
- struct page *page;
- struct page *page2;
- unsigned long count = 0;
-
- list_for_each_entry_safe(page, page2, l, lru) {
- move_to_lru(page);
- count++;
- }
- return count;
-}
-
-/*
- * Non migratable page
- */
-int fail_migrate_page(struct page *newpage, struct page *page)
-{
- return -EIO;
-}
-EXPORT_SYMBOL(fail_migrate_page);
-
-/*
- * swapout a single page
- * page is locked upon entry, unlocked on exit
- */
-static int swap_page(struct page *page)
-{
- struct address_space *mapping = page_mapping(page);
-
- if (page_mapped(page) && mapping)
- if (try_to_unmap(page, 1) != SWAP_SUCCESS)
- goto unlock_retry;
-
- 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;
-
- case PAGE_SUCCESS:
- goto retry;
-
- case PAGE_CLEAN:
- ; /* try to free the page below */
- }
- }
-
- if (PagePrivate(page)) {
- if (!try_to_release_page(page, GFP_KERNEL) ||
- (!mapping && page_count(page) == 1))
- goto unlock_retry;
- }
-
- if (remove_mapping(mapping, page)) {
- /* Success */
- unlock_page(page);
- return 0;
- }
-
-unlock_retry:
- unlock_page(page);
-
-retry:
- return -EAGAIN;
-}
-EXPORT_SYMBOL(swap_page);
-
-/*
- * Page migration was first developed in the context of the memory hotplug
- * project. The main authors of the migration code are:
- *
- * IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
- * Hirokazu Takahashi <taka@valinux.co.jp>
- * Dave Hansen <haveblue@us.ibm.com>
- * Christoph Lameter <clameter@sgi.com>
- */
-
-/*
- * Remove references for a page and establish the new page with the correct
- * basic settings to be able to stop accesses to the page.
- */
-int migrate_page_remove_references(struct page *newpage,
- struct page *page, int nr_refs)
-{
- struct address_space *mapping = page_mapping(page);
- struct page **radix_pointer;
-
- /*
- * 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;
-
- /*
- * 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;
-
- /*
- * Give up if we were unable to remove all mappings.
- */
- if (page_mapcount(page))
- return -EAGAIN;
-
- 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) != nr_refs ||
- *radix_pointer != page) {
- write_unlock_irq(&mapping->tree_lock);
- return -EAGAIN;
- }
-
- /*
- * 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));
- }
-
- *radix_pointer = newpage;
- __put_page(page);
- write_unlock_irq(&mapping->tree_lock);
-
- 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)
-{
- copy_highpage(newpage, page);
-
- if (PageError(page))
- SetPageError(newpage);
- if (PageReferenced(page))
- SetPageReferenced(newpage);
- if (PageUptodate(page))
- SetPageUptodate(newpage);
- if (PageActive(page))
- SetPageActive(newpage);
- if (PageChecked(page))
- SetPageChecked(newpage);
- if (PageMappedToDisk(page))
- SetPageMappedToDisk(newpage);
-
- if (PageDirty(page)) {
- clear_page_dirty_for_io(page);
- set_page_dirty(newpage);
- }
-
- ClearPageSwapCache(page);
- ClearPageActive(page);
- ClearPagePrivate(page);
- set_page_private(page, 0);
- page->mapping = NULL;
-
- /*
- * If any waiters have accumulated on the new page then
- * wake them up.
- */
- if (PageWriteback(newpage))
- end_page_writeback(newpage);
-}
-EXPORT_SYMBOL(migrate_page_copy);
-
-/*
- * Common logic to directly migrate a single page suitable for
- * pages that do not use PagePrivate.
- *
- * Pages are locked upon entry and exit.
- */
-int migrate_page(struct page *newpage, struct page *page)
-{
- int rc;
-
- BUG_ON(PageWriteback(page)); /* Writeback must be complete */
-
- rc = migrate_page_remove_references(newpage, page, 2);
-
- if (rc)
- 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);
-
-/*
- * 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 returns after 10 attempts or if no pages
- * are movable anymore because to has become empty
- * or no retryable pages exist anymore.
- *
- * Return: Number of pages not migrated when "to" ran empty.
- */
-unsigned long migrate_pages(struct list_head *from, struct list_head *to,
- struct list_head *moved, struct list_head *failed)
-{
- unsigned long retry;
- unsigned long nr_failed = 0;
- int pass = 0;
- struct page *page;
- struct page *page2;
- int swapwrite = current->flags & PF_SWAPWRITE;
- int rc;
-
- 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();
-
- rc = 0;
- if (page_count(page) == 1)
- /* page was freed from under us. So we are done. */
- goto next;
-
- 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;
- }
-
- /*
- * 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;
- }
- }
-
- if (!to) {
- rc = swap_page(page);
- goto next;
- }
-
- newpage = lru_to_page(to);
- lock_page(newpage);
-
- /*
- * Pages are properly locked and writeback is complete.
- * Try to migrate the page.
- */
- mapping = page_mapping(page);
- if (!mapping)
- goto unlock_both;
-
- 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;
- }
-
- /*
- * 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 */
- }
- }
-
- /*
- * 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;
- }
-
- /*
- * 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) {
- /*
- * Persistently unable to drop buffers..... As a
- * measure of last resort we fall back to
- * swap_page().
- */
- unlock_page(newpage);
- newpage = NULL;
- rc = swap_page(page);
- goto next;
- }
-
-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);
- }
- }
- if (retry && pass++ < 10)
- goto redo;
-
- if (!swapwrite)
- current->flags &= ~PF_SWAPWRITE;
-
- return nr_failed + retry;
-}
-
-/*
- * Isolate one page from the LRU lists and put it on the
- * indicated list with elevated refcount.
- *
- * Result:
- * 0 = page not on LRU list
- * 1 = page removed from LRU list and added to the specified list.
- */
-int isolate_lru_page(struct page *page)
-{
- int ret = 0;
-
- if (PageLRU(page)) {
- struct zone *zone = page_zone(page);
- spin_lock_irq(&zone->lru_lock);
- if (PageLRU(page)) {
- ret = 1;
- get_page(page);
- ClearPageLRU(page);
- if (PageActive(page))
- del_page_from_active_list(zone, page);
- else
- del_page_from_inactive_list(zone, page);
- }
- spin_unlock_irq(&zone->lru_lock);
- }
-
- return ret;
-}
-#endif
-
/*
* zone->lru_lock is heavily contended. Some of the functions that
* shrink the lists perform better by taking out a batch of pages