#include <linux/security.h>
#include <linux/memcontrol.h>
#include <linux/syscalls.h>
+#include <linux/hugetlb.h>
#include <linux/gfp.h>
#include "internal.h"
pte_t *ptep, pte;
spinlock_t *ptl;
- pgd = pgd_offset(mm, addr);
- if (!pgd_present(*pgd))
- goto out;
+ if (unlikely(PageHuge(new))) {
+ ptep = huge_pte_offset(mm, addr);
+ if (!ptep)
+ goto out;
+ ptl = &mm->page_table_lock;
+ } else {
+ pgd = pgd_offset(mm, addr);
+ if (!pgd_present(*pgd))
+ goto out;
- pud = pud_offset(pgd, addr);
- if (!pud_present(*pud))
- goto out;
+ pud = pud_offset(pgd, addr);
+ if (!pud_present(*pud))
+ goto out;
- pmd = pmd_offset(pud, addr);
- if (!pmd_present(*pmd))
- goto out;
+ pmd = pmd_offset(pud, addr);
+ if (!pmd_present(*pmd))
+ goto out;
- ptep = pte_offset_map(pmd, addr);
+ ptep = pte_offset_map(pmd, addr);
- if (!is_swap_pte(*ptep)) {
- pte_unmap(ptep);
- goto out;
- }
+ if (!is_swap_pte(*ptep)) {
+ pte_unmap(ptep);
+ goto out;
+ }
+
+ ptl = pte_lockptr(mm, pmd);
+ }
- ptl = pte_lockptr(mm, pmd);
spin_lock(ptl);
pte = *ptep;
if (!is_swap_pte(pte))
pte = pte_mkold(mk_pte(new, vma->vm_page_prot));
if (is_write_migration_entry(entry))
pte = pte_mkwrite(pte);
+#ifdef CONFIG_HUGETLB_PAGE
+ if (PageHuge(new))
+ pte = pte_mkhuge(pte);
+#endif
flush_cache_page(vma, addr, pte_pfn(pte));
set_pte_at(mm, addr, ptep, pte);
- if (PageAnon(new))
+ if (PageHuge(new)) {
+ if (PageAnon(new))
+ hugepage_add_anon_rmap(new, vma, addr);
+ else
+ page_dup_rmap(new);
+ } else if (PageAnon(new))
page_add_anon_rmap(new, vma, addr);
else
page_add_file_rmap(new);
return 0;
}
+/*
+ * The expected number of remaining references is the same as that
+ * of migrate_page_move_mapping().
+ */
+int migrate_huge_page_move_mapping(struct address_space *mapping,
+ struct page *newpage, struct page *page)
+{
+ int expected_count;
+ void **pslot;
+
+ if (!mapping) {
+ if (page_count(page) != 1)
+ return -EAGAIN;
+ return 0;
+ }
+
+ spin_lock_irq(&mapping->tree_lock);
+
+ pslot = radix_tree_lookup_slot(&mapping->page_tree,
+ page_index(page));
+
+ expected_count = 2 + page_has_private(page);
+ if (page_count(page) != expected_count ||
+ (struct page *)radix_tree_deref_slot(pslot) != page) {
+ spin_unlock_irq(&mapping->tree_lock);
+ return -EAGAIN;
+ }
+
+ if (!page_freeze_refs(page, expected_count)) {
+ spin_unlock_irq(&mapping->tree_lock);
+ return -EAGAIN;
+ }
+
+ get_page(newpage);
+
+ radix_tree_replace_slot(pslot, newpage);
+
+ page_unfreeze_refs(page, expected_count);
+
+ __put_page(page);
+
+ spin_unlock_irq(&mapping->tree_lock);
+ return 0;
+}
+
/*
* Copy the page to its new location
*/
-static void migrate_page_copy(struct page *newpage, struct page *page)
+void migrate_page_copy(struct page *newpage, struct page *page)
{
- copy_highpage(newpage, page);
+ if (PageHuge(page))
+ copy_huge_page(newpage, page);
+ else
+ copy_highpage(newpage, page);
if (PageError(page))
SetPageError(newpage);
.nr_to_write = 1,
.range_start = 0,
.range_end = LLONG_MAX,
- .nonblocking = 1,
.for_reclaim = 1
};
int rc;
return rc;
}
+/*
+ * Counterpart of unmap_and_move_page() for hugepage migration.
+ *
+ * This function doesn't wait the completion of hugepage I/O
+ * because there is no race between I/O and migration for hugepage.
+ * Note that currently hugepage I/O occurs only in direct I/O
+ * where no lock is held and PG_writeback is irrelevant,
+ * and writeback status of all subpages are counted in the reference
+ * count of the head page (i.e. if all subpages of a 2MB hugepage are
+ * under direct I/O, the reference of the head page is 512 and a bit more.)
+ * This means that when we try to migrate hugepage whose subpages are
+ * doing direct I/O, some references remain after try_to_unmap() and
+ * hugepage migration fails without data corruption.
+ *
+ * There is also no race when direct I/O is issued on the page under migration,
+ * because then pte is replaced with migration swap entry and direct I/O code
+ * will wait in the page fault for migration to complete.
+ */
+static int unmap_and_move_huge_page(new_page_t get_new_page,
+ unsigned long private, struct page *hpage,
+ int force, int offlining)
+{
+ int rc = 0;
+ int *result = NULL;
+ struct page *new_hpage = get_new_page(hpage, private, &result);
+ int rcu_locked = 0;
+ struct anon_vma *anon_vma = NULL;
+
+ if (!new_hpage)
+ return -ENOMEM;
+
+ rc = -EAGAIN;
+
+ if (!trylock_page(hpage)) {
+ if (!force)
+ goto out;
+ lock_page(hpage);
+ }
+
+ if (PageAnon(hpage)) {
+ rcu_read_lock();
+ rcu_locked = 1;
+
+ if (page_mapped(hpage)) {
+ anon_vma = page_anon_vma(hpage);
+ atomic_inc(&anon_vma->external_refcount);
+ }
+ }
+
+ try_to_unmap(hpage, TTU_MIGRATION|TTU_IGNORE_MLOCK|TTU_IGNORE_ACCESS);
+
+ if (!page_mapped(hpage))
+ rc = move_to_new_page(new_hpage, hpage, 1);
+
+ if (rc)
+ remove_migration_ptes(hpage, hpage);
+
+ if (anon_vma && atomic_dec_and_lock(&anon_vma->external_refcount,
+ &anon_vma->lock)) {
+ int empty = list_empty(&anon_vma->head);
+ spin_unlock(&anon_vma->lock);
+ if (empty)
+ anon_vma_free(anon_vma);
+ }
+
+ if (rcu_locked)
+ rcu_read_unlock();
+out:
+ unlock_page(hpage);
+
+ if (rc != -EAGAIN) {
+ list_del(&hpage->lru);
+ put_page(hpage);
+ }
+
+ put_page(new_hpage);
+
+ if (result) {
+ if (rc)
+ *result = rc;
+ else
+ *result = page_to_nid(new_hpage);
+ }
+ return rc;
+}
+
/*
* migrate_pages
*
*
* 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
- * returned to the LRU or freed.
+ * or no retryable pages exist anymore.
+ * Caller should call putback_lru_pages to return pages to the LRU
+ * or free list.
*
* Return: Number of pages not migrated or error code.
*/
if (!swapwrite)
current->flags &= ~PF_SWAPWRITE;
- putback_lru_pages(from);
+ if (rc)
+ return rc;
+
+ return nr_failed + retry;
+}
+
+int migrate_huge_pages(struct list_head *from,
+ new_page_t get_new_page, unsigned long private, int offlining)
+{
+ int retry = 1;
+ int nr_failed = 0;
+ int pass = 0;
+ struct page *page;
+ struct page *page2;
+ int rc;
+
+ for (pass = 0; pass < 10 && retry; pass++) {
+ retry = 0;
+
+ list_for_each_entry_safe(page, page2, from, lru) {
+ cond_resched();
+
+ rc = unmap_and_move_huge_page(get_new_page,
+ private, page, pass > 2, offlining);
+
+ switch(rc) {
+ case -ENOMEM:
+ goto out;
+ case -EAGAIN:
+ retry++;
+ break;
+ case 0:
+ break;
+ default:
+ /* Permanent failure */
+ nr_failed++;
+ break;
+ }
+ }
+ }
+ rc = 0;
+out:
+
+ list_for_each_entry_safe(page, page2, from, lru)
+ put_page(page);
if (rc)
return rc;
err = -EFAULT;
vma = find_vma(mm, pp->addr);
- if (!vma || !vma_migratable(vma))
+ if (!vma || pp->addr < vma->vm_start || !vma_migratable(vma))
goto set_status;
page = follow_page(vma, pp->addr, FOLL_GET);
}
err = 0;
- if (!list_empty(&pagelist))
+ if (!list_empty(&pagelist)) {
err = migrate_pages(&pagelist, new_page_node,
(unsigned long)pm, 0);
+ if (err)
+ putback_lru_pages(&pagelist);
+ }
up_read(&mm->mmap_sem);
return err;
int err = -EFAULT;
vma = find_vma(mm, addr);
- if (!vma)
+ if (!vma || addr < vma->vm_start)
goto set_status;
page = follow_page(vma, addr, 0);
git://bbs.cooldavid.org / net-next-2.6.git / blobdiff