#include <linux/init.h>
#include <linux/compat.h>
#include <linux/mempolicy.h>
+#include <linux/swap.h>
+
#include <asm/tlbflush.h>
#include <asm/uaccess.h>
+/* Internal MPOL_MF_xxx flags */
+#define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0) /* Skip checks for continuous vmas */
+
static kmem_cache_t *policy_cache;
static kmem_cache_t *sn_cache;
/* Highest zone. An specific allocation for a zone below that is not
policied. */
-static int policy_zone;
+int policy_zone = ZONE_DMA;
struct mempolicy default_policy = {
.refcnt = ATOMIC_INIT(1), /* never free it */
if (!zl)
return NULL;
num = 0;
- for_each_node_mask(nd, *nodes) {
- int k;
- for (k = MAX_NR_ZONES-1; k >= 0; k--) {
- struct zone *z = &NODE_DATA(nd)->node_zones[k];
- if (!z->present_pages)
- continue;
- zl->zones[num++] = z;
- if (k > policy_zone)
- policy_zone = k;
- }
- }
+ for_each_node_mask(nd, *nodes)
+ zl->zones[num++] = &NODE_DATA(nd)->node_zones[policy_zone];
zl->zones[num] = NULL;
return zl;
}
switch (mode) {
case MPOL_INTERLEAVE:
policy->v.nodes = *nodes;
+ if (nodes_weight(*nodes) == 0) {
+ kmem_cache_free(policy_cache, policy);
+ return ERR_PTR(-EINVAL);
+ }
break;
case MPOL_PREFERRED:
policy->v.preferred_node = first_node(*nodes);
return policy;
}
+/* 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)
+{
+ /*
+ * Avoid migrating a page that is shared by others and not writable.
+ */
+ 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)
+ 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);
+ }
+}
+
/* Ensure all existing pages follow the policy. */
static int check_pte_range(struct vm_area_struct *vma, pmd_t *pmd,
- unsigned long addr, unsigned long end, nodemask_t *nodes)
+ unsigned long addr, unsigned long end,
+ const nodemask_t *nodes, unsigned long flags,
+ struct list_head *pagelist)
{
pte_t *orig_pte;
pte_t *pte;
if (!page)
continue;
nid = page_to_nid(page);
- if (!node_isset(nid, *nodes))
- break;
+ if (!node_isset(nid, *nodes)) {
+ if (pagelist)
+ migrate_page_add(vma, page, pagelist, flags);
+ else
+ break;
+ }
} while (pte++, addr += PAGE_SIZE, addr != end);
pte_unmap_unlock(orig_pte, ptl);
return addr != end;
}
static inline int check_pmd_range(struct vm_area_struct *vma, pud_t *pud,
- unsigned long addr, unsigned long end, nodemask_t *nodes)
+ unsigned long addr, unsigned long end,
+ const nodemask_t *nodes, unsigned long flags,
+ struct list_head *pagelist)
{
pmd_t *pmd;
unsigned long next;
next = pmd_addr_end(addr, end);
if (pmd_none_or_clear_bad(pmd))
continue;
- if (check_pte_range(vma, pmd, addr, next, nodes))
+ if (check_pte_range(vma, pmd, addr, next, nodes,
+ flags, pagelist))
return -EIO;
} while (pmd++, addr = next, addr != end);
return 0;
}
static inline int check_pud_range(struct vm_area_struct *vma, pgd_t *pgd,
- unsigned long addr, unsigned long end, nodemask_t *nodes)
+ unsigned long addr, unsigned long end,
+ const nodemask_t *nodes, unsigned long flags,
+ struct list_head *pagelist)
{
pud_t *pud;
unsigned long next;
next = pud_addr_end(addr, end);
if (pud_none_or_clear_bad(pud))
continue;
- if (check_pmd_range(vma, pud, addr, next, nodes))
+ if (check_pmd_range(vma, pud, addr, next, nodes,
+ flags, pagelist))
return -EIO;
} while (pud++, addr = next, addr != end);
return 0;
}
static inline int check_pgd_range(struct vm_area_struct *vma,
- unsigned long addr, unsigned long end, nodemask_t *nodes)
+ unsigned long addr, unsigned long end,
+ const nodemask_t *nodes, unsigned long flags,
+ struct list_head *pagelist)
{
pgd_t *pgd;
unsigned long next;
next = pgd_addr_end(addr, end);
if (pgd_none_or_clear_bad(pgd))
continue;
- if (check_pud_range(vma, pgd, addr, next, nodes))
+ if (check_pud_range(vma, pgd, addr, next, nodes,
+ flags, pagelist))
return -EIO;
} while (pgd++, addr = next, addr != end);
return 0;
}
-/* Step 1: check the range */
+/* Check if a vma is migratable */
+static inline int vma_migratable(struct vm_area_struct *vma)
+{
+ if (vma->vm_flags & (
+ VM_LOCKED|VM_IO|VM_HUGETLB|VM_PFNMAP))
+ return 0;
+ return 1;
+}
+
+/*
+ * Check if all pages in a range are on a set of nodes.
+ * If pagelist != NULL then isolate pages from the LRU and
+ * put them on the pagelist.
+ */
static struct vm_area_struct *
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
- nodemask_t *nodes, unsigned long flags)
+ const nodemask_t *nodes, unsigned long flags,
+ struct list_head *pagelist)
{
int err;
struct vm_area_struct *first, *vma, *prev;
return ERR_PTR(-EFAULT);
prev = NULL;
for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
- if (!vma->vm_next && vma->vm_end < end)
- return ERR_PTR(-EFAULT);
- if (prev && prev->vm_end < vma->vm_start)
- return ERR_PTR(-EFAULT);
- if ((flags & MPOL_MF_STRICT) && !is_vm_hugetlb_page(vma)) {
+ if (!(flags & MPOL_MF_DISCONTIG_OK)) {
+ if (!vma->vm_next && vma->vm_end < end)
+ return ERR_PTR(-EFAULT);
+ if (prev && prev->vm_end < vma->vm_start)
+ return ERR_PTR(-EFAULT);
+ }
+ if (!is_vm_hugetlb_page(vma) &&
+ ((flags & MPOL_MF_STRICT) ||
+ ((flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) &&
+ vma_migratable(vma)))) {
unsigned long endvma = vma->vm_end;
+
if (endvma > end)
endvma = end;
if (vma->vm_start > start)
start = vma->vm_start;
- err = check_pgd_range(vma, start, endvma, nodes);
+ err = check_pgd_range(vma, start, endvma, nodes,
+ flags, pagelist);
if (err) {
first = ERR_PTR(err);
break;
return mpol_check_policy(mode, nodes);
}
+static int swap_pages(struct list_head *pagelist)
+{
+ LIST_HEAD(moved);
+ LIST_HEAD(failed);
+ int n;
+
+ n = migrate_pages(pagelist, NULL, &moved, &failed);
+ putback_lru_pages(&failed);
+ putback_lru_pages(&moved);
+
+ return n;
+}
+
long do_mbind(unsigned long start, unsigned long len,
unsigned long mode, nodemask_t *nmask, unsigned long flags)
{
struct mempolicy *new;
unsigned long end;
int err;
+ LIST_HEAD(pagelist);
- if ((flags & ~(unsigned long)(MPOL_MF_STRICT)) || mode > MPOL_MAX)
+ if ((flags & ~(unsigned long)(MPOL_MF_STRICT|MPOL_MF_MOVE|MPOL_MF_MOVE_ALL))
+ || mode > MPOL_MAX)
return -EINVAL;
+ if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_RESOURCE))
+ return -EPERM;
+
if (start & ~PAGE_MASK)
return -EINVAL;
+
if (mode == MPOL_DEFAULT)
flags &= ~MPOL_MF_STRICT;
+
len = (len + PAGE_SIZE - 1) & PAGE_MASK;
end = start + len;
+
if (end < start)
return -EINVAL;
if (end == start)
return 0;
+
if (mpol_check_policy(mode, nmask))
return -EINVAL;
+
new = mpol_new(mode, nmask);
if (IS_ERR(new))
return PTR_ERR(new);
+ /*
+ * If we are using the default policy then operation
+ * on discontinuous address spaces is okay after all
+ */
+ if (!new)
+ flags |= MPOL_MF_DISCONTIG_OK;
+
PDprintk("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
mode,nodes_addr(nodes)[0]);
down_write(&mm->mmap_sem);
- vma = check_range(mm, start, end, nmask, flags);
+ vma = check_range(mm, start, end, nmask, flags,
+ (flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)) ? &pagelist : NULL);
err = PTR_ERR(vma);
- if (!IS_ERR(vma))
+ if (!IS_ERR(vma)) {
+ int nr_failed = 0;
+
err = mbind_range(vma, start, end, new);
+ if (!list_empty(&pagelist))
+ nr_failed = swap_pages(&pagelist);
+
+ if (!err && nr_failed && (flags & MPOL_MF_STRICT))
+ err = -EIO;
+ }
+ if (!list_empty(&pagelist))
+ putback_lru_pages(&pagelist);
+
up_write(&mm->mmap_sem);
mpol_free(new);
return err;
return err;
}
+/*
+ * For now migrate_pages simply swaps out the pages from nodes that are in
+ * the source set but not in the target set. In the future, we would
+ * want a function that moves pages between the two nodesets in such
+ * a way as to preserve the physical layout as much as possible.
+ *
+ * Returns the number of page that could not be moved.
+ */
+int do_migrate_pages(struct mm_struct *mm,
+ const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags)
+{
+ LIST_HEAD(pagelist);
+ int count = 0;
+ nodemask_t nodes;
+
+ nodes_andnot(nodes, *from_nodes, *to_nodes);
+ nodes_complement(nodes, nodes);
+
+ down_read(&mm->mmap_sem);
+ check_range(mm, mm->mmap->vm_start, TASK_SIZE, &nodes,
+ flags | MPOL_MF_DISCONTIG_OK, &pagelist);
+
+ if (!list_empty(&pagelist)) {
+ count = swap_pages(&pagelist);
+ putback_lru_pages(&pagelist);
+ }
+
+ up_read(&mm->mmap_sem);
+ return count;
+}
+
/*
* User space interface with variable sized bitmaps for nodelists.
*/
/* Copy a node mask from user space. */
-static int get_nodes(nodemask_t *nodes, unsigned long __user *nmask,
+static int get_nodes(nodemask_t *nodes, const unsigned long __user *nmask,
unsigned long maxnode)
{
unsigned long k;
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)
+{
+ struct mm_struct *mm;
+ struct task_struct *task;
+ nodemask_t old;
+ nodemask_t new;
+ nodemask_t task_nodes;
+ int err;
+
+ err = get_nodes(&old, old_nodes, maxnode);
+ if (err)
+ return err;
+
+ err = get_nodes(&new, new_nodes, maxnode);
+ if (err)
+ return err;
+
+ /* 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 priviledges 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_ADMIN)) {
+ err = -EPERM;
+ goto out;
+ }
+
+ task_nodes = cpuset_mems_allowed(task);
+ /* Is the user allowed to access the target nodes? */
+ if (!nodes_subset(new, task_nodes) && !capable(CAP_SYS_ADMIN)) {
+ err = -EPERM;
+ goto out;
+ }
+
+ err = do_migrate_pages(mm, &old, &new, MPOL_MF_MOVE);
+out:
+ mmput(mm);
+ return err;
+}
+
+
/* Retrieve NUMA policy */
asmlinkage long sys_get_mempolicy(int __user *policy,
unsigned long __user *nmask,
return nid;
}
+/* Determine a node number for interleave */
+static inline unsigned interleave_nid(struct mempolicy *pol,
+ struct vm_area_struct *vma, unsigned long addr, int shift)
+{
+ if (vma) {
+ unsigned long off;
+
+ off = vma->vm_pgoff;
+ off += (addr - vma->vm_start) >> shift;
+ return offset_il_node(pol, vma, off);
+ } else
+ return interleave_nodes(pol);
+}
+
+/* Return a zonelist suitable for a huge page allocation. */
+struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr)
+{
+ struct mempolicy *pol = get_vma_policy(current, vma, addr);
+
+ if (pol->policy == MPOL_INTERLEAVE) {
+ unsigned nid;
+
+ nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
+ return NODE_DATA(nid)->node_zonelists + gfp_zone(GFP_HIGHUSER);
+ }
+ return zonelist_policy(GFP_HIGHUSER, pol);
+}
+
/* Allocate a page in interleaved policy.
Own path because it needs to do special accounting. */
static struct page *alloc_page_interleave(gfp_t gfp, unsigned order,
if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
unsigned nid;
- if (vma) {
- unsigned long off;
- off = vma->vm_pgoff;
- off += (addr - vma->vm_start) >> PAGE_SHIFT;
- nid = offset_il_node(pol, vma, off);
- } else {
- /* fall back to process interleaving */
- nid = interleave_nodes(pol);
- }
+
+ nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
return alloc_page_interleave(gfp, 0, nid);
}
return __alloc_pages(gfp, 0, zonelist_policy(gfp, pol));
kmem_cache_free(policy_cache, p);
}
-/*
- * Hugetlb policy. Same as above, just works with node numbers instead of
- * zonelists.
- */
-
-/* Find first node suitable for an allocation */
-int mpol_first_node(struct vm_area_struct *vma, unsigned long addr)
-{
- struct mempolicy *pol = get_vma_policy(current, vma, addr);
-
- switch (pol->policy) {
- case MPOL_DEFAULT:
- return numa_node_id();
- case MPOL_BIND:
- return pol->v.zonelist->zones[0]->zone_pgdat->node_id;
- case MPOL_INTERLEAVE:
- return interleave_nodes(pol);
- case MPOL_PREFERRED:
- return pol->v.preferred_node >= 0 ?
- pol->v.preferred_node : numa_node_id();
- }
- BUG();
- return 0;
-}
-
-/* Find secondary valid nodes for an allocation */
-int mpol_node_valid(int nid, struct vm_area_struct *vma, unsigned long addr)
-{
- struct mempolicy *pol = get_vma_policy(current, vma, addr);
-
- switch (pol->policy) {
- case MPOL_PREFERRED:
- case MPOL_DEFAULT:
- case MPOL_INTERLEAVE:
- return 1;
- case MPOL_BIND: {
- struct zone **z;
- for (z = pol->v.zonelist->zones; *z; z++)
- if ((*z)->zone_pgdat->node_id == nid)
- return 1;
- return 0;
- }
- default:
- BUG();
- return 0;
- }
-}
-
/*
* Shared memory backing store policy support.
*