#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 "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))
/*
}
/*
- * 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)
{
* 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;
+ int *result = NULL;
+ struct page *newpage = get_new_page(page, private, &result);
+
+ if (!newpage)
+ return -ENOMEM;
if (page_count(page) == 1)
/* page was freed from under us. So we are done. */
- goto ret;
+ goto move_newpage;
rc = -EAGAIN;
if (TestSetPageLocked(page)) {
if (!force)
- goto ret;
+ goto move_newpage;
lock_page(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;
+ try_to_unmap(page, 1);
+ if (!page_mapped(page))
+ rc = move_to_new_page(newpage, page);
if (rc)
remove_migration_ptes(page, page);
+
unlock:
unlock_page(page);
-ret:
+
if (rc != -EAGAIN) {
- list_del(&newpage->lru);
- move_to_lru(newpage);
+ /*
+ * A page that has been migrated has all references
+ * removed and will be freed. A page that has not been
+ * migrated will have kepts its references and be
+ * restored.
+ */
+ list_del(&page->lru);
+ move_to_lru(page);
+ }
+
+move_newpage:
+ /*
+ * Move the new page to the LRU. If migration was not successful
+ * then this will free the page.
+ */
+ move_to_lru(newpage);
+ if (result) {
+ if (rc)
+ *result = rc;
+ else
+ *result = page_to_nid(newpage);
}
return rc;
}
/*
* 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.
+ * or no retryable pages exist anymore. All pages will be
+ * retruned to the LRU or freed.
*
- * Return: Number of pages not migrated when "to" ran empty.
+ * Return: Number of pages not migrated or error code.
*/
-int migrate_pages(struct list_head *from, struct list_head *to,
- struct list_head *moved, struct list_head *failed)
+int migrate_pages(struct list_head *from,
+ new_page_t get_new_page, unsigned long private)
{
int retry = 1;
int nr_failed = 0;
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;
case 0:
- list_move(&page->lru, moved);
break;
default:
/* Permanent failure */
- list_move(&page->lru, failed);
nr_failed++;
break;
}
}
}
-
+ rc = 0;
+out:
if (!swapwrite)
current->flags &= ~PF_SWAPWRITE;
+ putback_lru_pages(from);
+
+ if (rc)
+ return rc;
+
return nr_failed + retry;
}
+#ifdef CONFIG_NUMA
/*
- * 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
+ * Move a list of individual pages
*/
-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_to_node {
+ unsigned long addr;
struct page *page;
- struct list_head *p;
+ 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;
-redo:
- nr_pages = 0;
- list_for_each(p, pagelist) {
- if (vma) {
+ 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)
/*
- * 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.
+ * Node already in the right place
*/
- page = alloc_page_vma(GFP_HIGHUSER, vma,
- offset + vma->vm_start);
- offset += PAGE_SIZE;
- }
- else
- page = alloc_pages_node(dest, GFP_HIGHUSER, 0);
+ 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;
- if (!page) {
- err = -ENOMEM;
+ 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;
+ }
+
+ 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 *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;
}
- list_add_tail(&page->lru, &newlist);
- nr_pages++;
- if (nr_pages > MIGRATE_CHUNK_SIZE)
- break;
}
- err = migrate_pages(pagelist, &newlist, &moved, &failed);
+ /* End marker */
+ pm[nr_pages].node = MAX_NUMNODES;
+
+ if (nodes)
+ err = do_move_pages(mm, pm, flags & MPOL_MF_MOVE_ALL);
+ else
+ err = do_pages_stat(mm, pm);
- putback_lru_pages(&moved); /* Call release pages instead ?? */
+ if (err >= 0)
+ /* Return status information */
+ for (i = 0; i < nr_pages; i++)
+ if (put_user(pm[i].status, status + i))
+ err = -EFAULT;
- if (err >= 0 && list_empty(&newlist) && !list_empty(pagelist))
- goto redo;
out:
- /* Return leftover allocated pages */
- while (!list_empty(&newlist)) {
- page = list_entry(newlist.next, struct page, lru);
- list_del(&page->lru);
- __free_page(page);
- }
- list_splice(&failed, pagelist);
- if (err < 0)
- return err;
-
- /* Calculate number of leftover pages */
- nr_pages = 0;
- list_for_each(p, pagelist)
- nr_pages++;
- return nr_pages;
+ vfree(pm);
+out2:
+ mmput(mm);
+ return err;
+}
+#endif
+
+/*
+ * Call migration functions in the vma_ops that may prepare
+ * memory in a vm for migration. migration functions may perform
+ * the migration for vmas that do not have an underlying page struct.
+ */
+int migrate_vmas(struct mm_struct *mm, const nodemask_t *to,
+ const nodemask_t *from, unsigned long flags)
+{
+ struct vm_area_struct *vma;
+ int err = 0;
+
+ for(vma = mm->mmap; vma->vm_next && !err; vma = vma->vm_next) {
+ if (vma->vm_ops && vma->vm_ops->migrate) {
+ err = vma->vm_ops->migrate(vma, to, from, flags);
+ if (err)
+ break;
+ }
+ }
+ return err;
}