* IWAMOTO Toshihiro <iwamoto@valinux.co.jp>
* Hirokazu Takahashi <taka@valinux.co.jp>
* Dave Hansen <haveblue@us.ibm.com>
- * Christoph Lameter <clameter@sgi.com>
+ * Christoph Lameter
*/
#include <linux/migrate.h>
#include <linux/pagemap.h>
#include <linux/buffer_head.h>
#include <linux/mm_inline.h>
+#include <linux/nsproxy.h>
#include <linux/pagevec.h>
#include <linux/rmap.h>
#include <linux/topology.h>
#include <linux/cpu.h>
#include <linux/cpuset.h>
#include <linux/writeback.h>
+#include <linux/mempolicy.h>
+#include <linux/vmalloc.h>
+#include <linux/security.h>
+#include <linux/memcontrol.h>
+#include <linux/syscalls.h>
#include "internal.h"
struct zone *zone = page_zone(page);
spin_lock_irq(&zone->lru_lock);
- if (PageLRU(page)) {
+ if (PageLRU(page) && get_page_unless_zero(page)) {
ret = 0;
- get_page(page);
ClearPageLRU(page);
if (PageActive(page))
del_page_from_active_list(zone, page);
}
/*
- * 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)
{
return count;
}
-static inline int is_swap_pte(pte_t pte)
-{
- return !pte_none(pte) && !pte_present(pte) && !pte_file(pte);
-}
-
/*
* Restore a potential migration pte to a working pte entry
*/
if (!is_migration_entry(entry) || migration_entry_to_page(entry) != old)
goto out;
+ /*
+ * Yes, ignore the return value from a GFP_ATOMIC mem_cgroup_charge.
+ * Failure is not an option here: we're now expected to remove every
+ * migration pte, and will cause crashes otherwise. Normally this
+ * is not an issue: mem_cgroup_prepare_migration bumped up the old
+ * page_cgroup count for safety, that's now attached to the new page,
+ * so this charge should just be another incrementation of the count,
+ * to keep in balance with rmap.c's mem_cgroup_uncharging. But if
+ * there's been a force_empty, those reference counts may no longer
+ * be reliable, and this charge can actually fail: oh well, we don't
+ * make the situation any worse by proceeding as if it had succeeded.
+ */
+ mem_cgroup_charge(new, mm, GFP_ATOMIC);
+
get_page(new);
pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
if (is_write_migration_entry(entry))
pte = pte_mkwrite(pte);
+ flush_cache_page(vma, addr, pte_pfn(pte));
set_pte_at(mm, addr, ptep, pte);
if (PageAnon(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);
page = migration_entry_to_page(entry);
- get_page(page);
+ /*
+ * Once radix-tree replacement of page migration started, page_count
+ * *must* be zero. And, we don't want to call wait_on_page_locked()
+ * against a page without get_page().
+ * So, we use get_page_unless_zero(), here. Even failed, page fault
+ * will occur again.
+ */
+ if (!get_page_unless_zero(page))
+ goto out;
pte_unmap_unlock(ptep, ptl);
wait_on_page_locked(page);
put_page(page);
static int migrate_page_move_mapping(struct address_space *mapping,
struct page *newpage, struct page *page)
{
- struct page **radix_pointer;
+ int expected_count;
+ void **pslot;
if (!mapping) {
- /* Anonymous page */
+ /* Anonymous page without mapping */
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));
+ pslot = radix_tree_lookup_slot(&mapping->page_tree,
+ page_index(page));
- if (page_count(page) != 2 + !!PagePrivate(page) ||
- *radix_pointer != page) {
+ expected_count = 2 + !!PagePrivate(page);
+ if (page_count(page) != expected_count ||
+ (struct page *)radix_tree_deref_slot(pslot) != page) {
+ write_unlock_irq(&mapping->tree_lock);
+ return -EAGAIN;
+ }
+
+ if (!page_freeze_refs(page, expected_count)) {
write_unlock_irq(&mapping->tree_lock);
return -EAGAIN;
}
/*
* Now we know that no one else is looking at the page.
*/
- get_page(newpage);
+ get_page(newpage); /* add cache reference */
#ifdef CONFIG_SWAP
if (PageSwapCache(page)) {
SetPageSwapCache(newpage);
}
#endif
- *radix_pointer = newpage;
+ radix_tree_replace_slot(pslot, newpage);
+
+ page_unfreeze_refs(page, expected_count);
+ /*
+ * Drop cache reference from old page.
+ * We know this isn't the last reference.
+ */
__put_page(page);
+
+ /*
+ * If moved to a different zone then also account
+ * the page for that zone. Other VM counters will be
+ * taken care of when we establish references to the
+ * new page and drop references to the old page.
+ *
+ * Note that anonymous pages are accounted for
+ * via NR_FILE_PAGES and NR_ANON_PAGES if they
+ * are mapped to swap space.
+ */
+ __dec_zone_page_state(page, NR_FILE_PAGES);
+ __inc_zone_page_state(newpage, NR_FILE_PAGES);
+
write_unlock_irq(&mapping->tree_lock);
+ if (!PageSwapCache(newpage)) {
+ mem_cgroup_uncharge_cache_page(page);
+ }
return 0;
}
if (PageDirty(page)) {
clear_page_dirty_for_io(page);
- set_page_dirty(newpage);
+ /*
+ * Want to mark the page and the radix tree as dirty, and
+ * redo the accounting that clear_page_dirty_for_io undid,
+ * but we can't use set_page_dirty because that function
+ * is actually a signal that all of the page has become dirty.
+ * Wheras only part of our page may be dirty.
+ */
+ __set_page_dirty_nobuffers(newpage);
}
#ifdef CONFIG_SWAP
}
EXPORT_SYMBOL(migrate_page);
+#ifdef CONFIG_BLOCK
/*
* Migration function for pages with buffers. This function can only be used
* if the underlying filesystem guarantees that no other references to "page"
return 0;
}
EXPORT_SYMBOL(buffer_migrate_page);
+#endif
/*
* Writeback a page to clean the dirty state
* Buffers may be managed in a filesystem specific way.
* We must have no buffers or drop them.
*/
- if (page_has_buffers(page) &&
+ if (PagePrivate(page) &&
!try_to_release_page(page, GFP_KERNEL))
return -EAGAIN;
else
rc = fallback_migrate_page(mapping, newpage, page);
- if (!rc)
+ if (!rc) {
remove_migration_ptes(page, newpage);
- else
+ } else
newpage->mapping = NULL;
unlock_page(newpage);
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);
+ int rcu_locked = 0;
+ int charge = 0;
if (!newpage)
return -ENOMEM;
/* page was freed from under us. So we are done. */
goto move_newpage;
+ charge = mem_cgroup_prepare_migration(page, newpage);
+ if (charge == -ENOMEM) {
+ rc = -ENOMEM;
+ goto move_newpage;
+ }
+ /* prepare cgroup just returns 0 or -ENOMEM */
+ BUG_ON(charge);
+
rc = -EAGAIN;
if (TestSetPageLocked(page)) {
if (!force)
goto unlock;
wait_on_page_writeback(page);
}
+ /*
+ * By try_to_unmap(), page->mapcount goes down to 0 here. In this case,
+ * we cannot notice that anon_vma is freed while we migrates a page.
+ * This rcu_read_lock() delays freeing anon_vma pointer until the end
+ * of migration. File cache pages are no problem because of page_lock()
+ * File Caches may use write_page() or lock_page() in migration, then,
+ * just care Anon page here.
+ */
+ if (PageAnon(page)) {
+ rcu_read_lock();
+ rcu_locked = 1;
+ }
/*
- * Establish migration ptes or remove ptes
+ * Corner case handling:
+ * 1. When a new swap-cache page is read into, it is added to the LRU
+ * and treated as swapcache but it has no rmap yet.
+ * Calling try_to_unmap() against a page->mapping==NULL page will
+ * trigger a BUG. So handle it here.
+ * 2. An orphaned page (see truncate_complete_page) might have
+ * fs-private metadata. The page can be picked up due to memory
+ * offlining. Everywhere else except page reclaim, the page is
+ * invisible to the vm, so the page can not be migrated. So try to
+ * free the metadata, so the page can be freed.
*/
- 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 (!page->mapping) {
+ if (!PageAnon(page) && PagePrivate(page)) {
+ /*
+ * Go direct to try_to_free_buffers() here because
+ * a) that's what try_to_release_page() would do anyway
+ * b) we may be under rcu_read_lock() here, so we can't
+ * use GFP_KERNEL which is what try_to_release_page()
+ * needs to be effective.
+ */
+ try_to_free_buffers(page);
+ }
+ goto rcu_unlock;
+ }
+
+ /* Establish migration ptes or remove ptes */
+ try_to_unmap(page, 1);
+
+ if (!page_mapped(page))
+ rc = move_to_new_page(newpage, page);
if (rc)
remove_migration_ptes(page, page);
+rcu_unlock:
+ if (rcu_locked)
+ rcu_read_unlock();
+
unlock:
+
unlock_page(page);
if (rc != -EAGAIN) {
}
move_newpage:
+ if (!charge)
+ mem_cgroup_end_migration(newpage);
/*
* Move the new page to the LRU. If migration was not successful
* then this will free the page.
*/
move_to_lru(newpage);
+ if (result) {
+ if (rc)
+ *result = rc;
+ else
+ *result = page_to_nid(newpage);
+ }
return rc;
}
* 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.
+ * returned to the LRU or freed.
*
* Return: Number of pages not migrated or error code.
*/
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_MOVABLE | GFP_THISNODE, 0);
+}
+
+/*
+ * Move a set of pages as indicated in the pm array. The addr
+ * field must be set to the virtual address of the page to be moved
+ * and the node number must contain a valid target node.
+ */
+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 || !vma_migratable(vma))
+ goto set_status;
+
+ page = follow_page(vma, pp->addr, FOLL_GET);
+
+ err = PTR_ERR(page);
+ if (IS_ERR(page))
+ goto set_status;
+
+ 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 = PTR_ERR(page);
+ if (IS_ERR(page))
+ goto set_status;
+
+ 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_vpid(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;
+ }
+
+ err = security_task_movememory(task);
+ if (err)
+ 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 __user *p;
+
+ err = -EFAULT;
+ if (get_user(p, pages + i))
+ goto out;
+
+ pm[i].addr = (unsigned long)p;
+ if (nodes) {
+ int node;
+
+ if (get_user(node, nodes + i))
+ goto out;
+
+ err = -ENODEV;
+ if (!node_state(node, N_HIGH_MEMORY))
+ goto out;
+
+ err = -EACCES;
+ if (!node_isset(node, task_nodes))
+ goto out;
+
+ pm[i].node = node;
+ } else
+ pm[i].node = 0; /* anything to not match MAX_NUMNODES */
+ }
+ /* End marker */
+ pm[nr_pages].node = MAX_NUMNODES;
+
+ if (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;
+}
+
+/*
+ * Call migration functions in the vma_ops that may prepare
+ * memory in a vm for migration. migration functions may perform
+ * the migration for vmas that do not have an underlying page struct.
+ */
+int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
+ const nodemask_t *from, unsigned long flags)
+{
+ struct vm_area_struct *vma;
+ int err = 0;
+
+ for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) {
+ if (vma->vm_ops && vma->vm_ops->migrate) {
+ err = vma->vm_ops->migrate(vma, to, from, flags);
+ if (err)
+ break;
+ }
+ }
+ return err;
+}
+#endif
git://ftp.safe.ca / safe / jmp / linux-2.6 / blobdiff