break;
}
policy->policy = mode;
+ policy->cpuset_mems_allowed = cpuset_mems_allowed(current);
return policy;
}
static void gather_stats(struct page *, void *);
-static void migrate_page_add(struct vm_area_struct *vma,
- struct page *page, struct list_head *pagelist, unsigned long flags);
+static void migrate_page_add(struct page *page, struct list_head *pagelist,
+ unsigned long flags);
/* Scan through pages checking if pages follow certain conditions. */
static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
page = vm_normal_page(vma, addr, *pte);
if (!page)
continue;
+ /*
+ * The check for PageReserved here is important to avoid
+ * handling zero pages and other pages that may have been
+ * marked special by the system.
+ *
+ * If the PageReserved would not be checked here then f.e.
+ * the location of the zero page could have an influence
+ * on MPOL_MF_STRICT, zero pages would be counted for
+ * the per node stats, and there would be useless attempts
+ * to put zero pages on the migration list.
+ */
+ if (PageReserved(page))
+ continue;
nid = page_to_nid(page);
if (node_isset(nid, *nodes) == !!(flags & MPOL_MF_INVERT))
continue;
if (flags & MPOL_MF_STATS)
gather_stats(page, private);
- else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) {
- spin_unlock(ptl);
- migrate_page_add(vma, page, private, flags);
- spin_lock(ptl);
- }
+ else if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+ migrate_page_add(page, private, flags);
else
break;
} while (pte++, addr += PAGE_SIZE, addr != end);
static inline int vma_migratable(struct vm_area_struct *vma)
{
if (vma->vm_flags & (
- VM_LOCKED|VM_IO|VM_HUGETLB|VM_PFNMAP))
+ VM_LOCKED|VM_IO|VM_HUGETLB|VM_PFNMAP|VM_RESERVED))
return 0;
return 1;
}
int err;
struct vm_area_struct *first, *vma, *prev;
+ /* Clear the LRU lists so pages can be isolated */
+ if (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
+ lru_add_drain_all();
+
first = find_vma(mm, start);
if (!first)
return ERR_PTR(-EFAULT);
* page migration
*/
-/* Check if we are the only process mapping the page in question */
-static inline int single_mm_mapping(struct mm_struct *mm,
- struct address_space *mapping)
-{
- struct vm_area_struct *vma;
- struct prio_tree_iter iter;
- int rc = 1;
-
- spin_lock(&mapping->i_mmap_lock);
- vma_prio_tree_foreach(vma, &iter, &mapping->i_mmap, 0, ULONG_MAX)
- if (mm != vma->vm_mm) {
- rc = 0;
- goto out;
- }
- list_for_each_entry(vma, &mapping->i_mmap_nonlinear, shared.vm_set.list)
- if (mm != vma->vm_mm) {
- rc = 0;
- goto out;
- }
-out:
- spin_unlock(&mapping->i_mmap_lock);
- return rc;
-}
-
-/*
- * Add a page to be migrated to the pagelist
- */
-static void migrate_page_add(struct vm_area_struct *vma,
- struct page *page, struct list_head *pagelist, unsigned long flags)
+static void migrate_page_add(struct page *page, struct list_head *pagelist,
+ unsigned long flags)
{
/*
- * Avoid migrating a page that is shared by others and not writable.
+ * Avoid migrating a page that is shared with others.
*/
- if ((flags & MPOL_MF_MOVE_ALL) || !page->mapping || PageAnon(page) ||
- mapping_writably_mapped(page->mapping) ||
- single_mm_mapping(vma->vm_mm, page->mapping)) {
- int rc = isolate_lru_page(page);
-
- if (rc == 1)
+ if ((flags & MPOL_MF_MOVE_ALL) || page_mapcount(page) == 1) {
+ if (isolate_lru_page(page))
list_add(&page->lru, pagelist);
- /*
- * If the isolate attempt was not successful then we just
- * encountered an unswappable page. Something must be wrong.
- */
- WARN_ON(rc == 0);
}
}
return do_set_mempolicy(mode, &nodes);
}
-/* Macro needed until Paul implements this function in kernel/cpusets.c */
-#define cpuset_mems_allowed(task) node_online_map
-
asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
const unsigned long __user *old_nodes,
const unsigned long __user *new_nodes)
return nid;
}
+/*
+ * Depending on the memory policy provide a node from which to allocate the
+ * next slab entry.
+ */
+unsigned slab_node(struct mempolicy *policy)
+{
+ switch (policy->policy) {
+ case MPOL_INTERLEAVE:
+ return interleave_nodes(policy);
+
+ case MPOL_BIND:
+ /*
+ * Follow bind policy behavior and start allocation at the
+ * first node.
+ */
+ return policy->v.zonelist->zones[0]->zone_pgdat->node_id;
+
+ case MPOL_PREFERRED:
+ if (policy->v.preferred_node >= 0)
+ return policy->v.preferred_node;
+ /* Fall through */
+
+ default:
+ return numa_node_id();
+ }
+}
+
/* Do static interleaving for a VMA with known offset. */
static unsigned offset_il_node(struct mempolicy *pol,
struct vm_area_struct *vma, unsigned long off)
}
EXPORT_SYMBOL(alloc_pages_current);
+/*
+ * If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it
+ * rebinds the mempolicy its copying by calling mpol_rebind_policy()
+ * with the mems_allowed returned by cpuset_mems_allowed(). This
+ * keeps mempolicies cpuset relative after its cpuset moves. See
+ * further kernel/cpuset.c update_nodemask().
+ */
+void *cpuset_being_rebound;
+
/* Slow path of a mempolicy copy */
struct mempolicy *__mpol_copy(struct mempolicy *old)
{
if (!new)
return ERR_PTR(-ENOMEM);
+ if (current_cpuset_is_being_rebound()) {
+ nodemask_t mems = cpuset_mems_allowed(current);
+ mpol_rebind_policy(old, &mems);
+ }
*new = *old;
atomic_set(&new->refcnt, 1);
if (new->policy == MPOL_BIND) {
return 0;
}
+void mpol_shared_policy_init(struct shared_policy *info, int policy,
+ nodemask_t *policy_nodes)
+{
+ info->root = RB_ROOT;
+ spin_lock_init(&info->lock);
+
+ if (policy != MPOL_DEFAULT) {
+ struct mempolicy *newpol;
+
+ /* Falls back to MPOL_DEFAULT on any error */
+ newpol = mpol_new(policy, policy_nodes);
+ if (!IS_ERR(newpol)) {
+ /* Create pseudo-vma that contains just the policy */
+ struct vm_area_struct pvma;
+
+ memset(&pvma, 0, sizeof(struct vm_area_struct));
+ /* Policy covers entire file */
+ pvma.vm_end = TASK_SIZE;
+ mpol_set_shared_policy(info, &pvma, newpol);
+ mpol_free(newpol);
+ }
+ }
+}
+
int mpol_set_shared_policy(struct shared_policy *info,
struct vm_area_struct *vma, struct mempolicy *npol)
{
}
/* Migrate a policy to a different set of nodes */
-static void rebind_policy(struct mempolicy *pol, const nodemask_t *old,
- const nodemask_t *new)
+void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *newmask)
{
+ nodemask_t *mpolmask;
nodemask_t tmp;
if (!pol)
return;
+ mpolmask = &pol->cpuset_mems_allowed;
+ if (nodes_equal(*mpolmask, *newmask))
+ return;
switch (pol->policy) {
case MPOL_DEFAULT:
break;
case MPOL_INTERLEAVE:
- nodes_remap(tmp, pol->v.nodes, *old, *new);
+ nodes_remap(tmp, pol->v.nodes, *mpolmask, *newmask);
pol->v.nodes = tmp;
- current->il_next = node_remap(current->il_next, *old, *new);
+ *mpolmask = *newmask;
+ current->il_next = node_remap(current->il_next,
+ *mpolmask, *newmask);
break;
case MPOL_PREFERRED:
pol->v.preferred_node = node_remap(pol->v.preferred_node,
- *old, *new);
+ *mpolmask, *newmask);
+ *mpolmask = *newmask;
break;
case MPOL_BIND: {
nodemask_t nodes;
nodes_clear(nodes);
for (z = pol->v.zonelist->zones; *z; z++)
node_set((*z)->zone_pgdat->node_id, nodes);
- nodes_remap(tmp, nodes, *old, *new);
+ nodes_remap(tmp, nodes, *mpolmask, *newmask);
nodes = tmp;
zonelist = bind_zonelist(&nodes);
kfree(pol->v.zonelist);
pol->v.zonelist = zonelist;
}
+ *mpolmask = *newmask;
break;
}
default:
}
/*
- * Someone moved this task to different nodes. Fixup mempolicies.
+ * Wrapper for mpol_rebind_policy() that just requires task
+ * pointer, and updates task mempolicy.
+ */
+
+void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *new)
+{
+ mpol_rebind_policy(tsk->mempolicy, new);
+}
+
+/*
+ * Rebind each vma in mm to new nodemask.
*
- * TODO - fixup current->mm->vma and shmfs/tmpfs/hugetlbfs policies as well,
- * once we have a cpuset mechanism to mark which cpuset subtree is migrating.
+ * Call holding a reference to mm. Takes mm->mmap_sem during call.
*/
-void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new)
+
+void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
{
- rebind_policy(current->mempolicy, old, new);
+ struct vm_area_struct *vma;
+
+ down_write(&mm->mmap_sem);
+ for (vma = mm->mmap; vma; vma = vma->vm_next)
+ mpol_rebind_policy(vma->vm_policy, new);
+ up_write(&mm->mmap_sem);
}
/*