* Simple NUMA memory policy for the Linux kernel.
*
* Copyright 2003,2004 Andi Kleen, SuSE Labs.
+ * (C) Copyright 2005 Christoph Lameter, Silicon Graphics, Inc.
* Subject to the GNU Public License, version 2.
*
* NUMA policy allows the user to give hints in which node(s) memory should
* offset into the backing object or offset into the mapping
* for anonymous memory. For process policy an process counter
* is used.
+ *
* bind Only allocate memory on a specific set of nodes,
* no fallback.
+ * FIXME: memory is allocated starting with the first node
+ * to the last. It would be better if bind would truly restrict
+ * the allocation to memory nodes instead
+ *
* preferred Try a specific node first before normal fallback.
* As a special case node -1 here means do the allocation
* on the local CPU. This is normally identical to default,
* but useful to set in a VMA when you have a non default
* process policy.
+ *
* default Allocate on the local node first, or when on a VMA
* use the process policy. This is what Linux always did
* in a NUMA aware kernel and still does by, ahem, default.
}
return nodes_subset(*nodes, node_online_map) ? 0 : -EINVAL;
}
-
-/* Copy a node mask from user space. */
-static int get_nodes(nodemask_t *nodes, unsigned long __user *nmask,
- unsigned long maxnode, int mode)
-{
- unsigned long k;
- unsigned long nlongs;
- unsigned long endmask;
-
- --maxnode;
- nodes_clear(*nodes);
- if (maxnode == 0 || !nmask)
- return 0;
-
- nlongs = BITS_TO_LONGS(maxnode);
- if ((maxnode % BITS_PER_LONG) == 0)
- endmask = ~0UL;
- else
- endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;
-
- /* When the user specified more nodes than supported just check
- if the non supported part is all zero. */
- if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
- if (nlongs > PAGE_SIZE/sizeof(long))
- return -EINVAL;
- for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
- unsigned long t;
- if (get_user(t, nmask + k))
- return -EFAULT;
- if (k == nlongs - 1) {
- if (t & endmask)
- return -EINVAL;
- } else if (t)
- return -EINVAL;
- }
- nlongs = BITS_TO_LONGS(MAX_NUMNODES);
- endmask = ~0UL;
- }
-
- if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
- return -EFAULT;
- nodes_addr(*nodes)[nlongs-1] &= endmask;
- /* Update current mems_allowed */
- cpuset_update_current_mems_allowed();
- /* Ignore nodes not set in current->mems_allowed */
- /* AK: shouldn't this error out instead? */
- cpuset_restrict_to_mems_allowed(nodes_addr(*nodes));
- return mpol_check_policy(mode, nodes);
-}
-
/* Generate a custom zonelist for the BIND policy. */
static struct zonelist *bind_zonelist(nodemask_t *nodes)
{
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);
orig_pte = pte = pte_offset_map_lock(vma->vm_mm, pmd, addr, &ptl);
do {
- unsigned long pfn;
+ struct page *page;
unsigned int nid;
if (!pte_present(*pte))
continue;
- pfn = pte_pfn(*pte);
- if (!pfn_valid(pfn)) {
- print_bad_pte(vma, *pte, addr);
+ page = vm_normal_page(vma, addr, *pte);
+ if (!page)
continue;
- }
- nid = pfn_to_nid(pfn);
+ nid = page_to_nid(page);
if (!node_isset(nid, *nodes))
break;
} while (pte++, addr += PAGE_SIZE, addr != end);
first = find_vma(mm, start);
if (!first)
return ERR_PTR(-EFAULT);
- if (first->vm_flags & VM_RESERVED)
- return ERR_PTR(-EACCES);
prev = NULL;
for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
if (!vma->vm_next && vma->vm_end < end)
return err;
}
-/* Change policy for a memory range */
-asmlinkage long sys_mbind(unsigned long start, unsigned long len,
- unsigned long mode,
- unsigned long __user *nmask, unsigned long maxnode,
- unsigned flags)
+static int contextualize_policy(int mode, nodemask_t *nodes)
+{
+ if (!nodes)
+ return 0;
+
+ /* Update current mems_allowed */
+ cpuset_update_current_mems_allowed();
+ /* Ignore nodes not set in current->mems_allowed */
+ cpuset_restrict_to_mems_allowed(nodes->bits);
+ return mpol_check_policy(mode, nodes);
+}
+
+long do_mbind(unsigned long start, unsigned long len,
+ unsigned long mode, nodemask_t *nmask, unsigned long flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
struct mempolicy *new;
unsigned long end;
- nodemask_t nodes;
int err;
if ((flags & ~(unsigned long)(MPOL_MF_STRICT)) || mode > MPOL_MAX)
return -EINVAL;
if (end == start)
return 0;
-
- err = get_nodes(&nodes, nmask, maxnode, mode);
- if (err)
- return err;
-
- new = mpol_new(mode, &nodes);
+ if (mpol_check_policy(mode, nmask))
+ return -EINVAL;
+ new = mpol_new(mode, nmask);
if (IS_ERR(new))
return PTR_ERR(new);
mode,nodes_addr(nodes)[0]);
down_write(&mm->mmap_sem);
- vma = check_range(mm, start, end, &nodes, flags);
+ vma = check_range(mm, start, end, nmask, flags);
err = PTR_ERR(vma);
if (!IS_ERR(vma))
err = mbind_range(vma, start, end, new);
}
/* Set the process memory policy */
-asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
- unsigned long maxnode)
+long do_set_mempolicy(int mode, nodemask_t *nodes)
{
- int err;
struct mempolicy *new;
- nodemask_t nodes;
- if (mode < 0 || mode > MPOL_MAX)
+ if (contextualize_policy(mode, nodes))
return -EINVAL;
- err = get_nodes(&nodes, nmask, maxnode, mode);
- if (err)
- return err;
- new = mpol_new(mode, &nodes);
+ new = mpol_new(mode, nodes);
if (IS_ERR(new))
return PTR_ERR(new);
mpol_free(current->mempolicy);
switch (p->policy) {
case MPOL_BIND:
for (i = 0; p->v.zonelist->zones[i]; i++)
- node_set(p->v.zonelist->zones[i]->zone_pgdat->node_id, *nodes);
+ node_set(p->v.zonelist->zones[i]->zone_pgdat->node_id,
+ *nodes);
break;
case MPOL_DEFAULT:
break;
return err;
}
-/* Copy a kernel node mask to user space */
-static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
- nodemask_t *nodes)
-{
- unsigned long copy = ALIGN(maxnode-1, 64) / 8;
- const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);
-
- if (copy > nbytes) {
- if (copy > PAGE_SIZE)
- return -EINVAL;
- if (clear_user((char __user *)mask + nbytes, copy - nbytes))
- return -EFAULT;
- copy = nbytes;
- }
- return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
-}
-
/* Retrieve NUMA policy */
-asmlinkage long sys_get_mempolicy(int __user *policy,
- unsigned long __user *nmask,
- unsigned long maxnode,
- unsigned long addr, unsigned long flags)
+long do_get_mempolicy(int *policy, nodemask_t *nmask,
+ unsigned long addr, unsigned long flags)
{
- int err, pval;
+ int err;
struct mm_struct *mm = current->mm;
struct vm_area_struct *vma = NULL;
struct mempolicy *pol = current->mempolicy;
+ cpuset_update_current_mems_allowed();
if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR))
return -EINVAL;
- if (nmask != NULL && maxnode < MAX_NUMNODES)
- return -EINVAL;
if (flags & MPOL_F_ADDR) {
down_read(&mm->mmap_sem);
vma = find_vma_intersection(mm, addr, addr+1);
err = lookup_node(mm, addr);
if (err < 0)
goto out;
- pval = err;
+ *policy = err;
} else if (pol == current->mempolicy &&
pol->policy == MPOL_INTERLEAVE) {
- pval = current->il_next;
+ *policy = current->il_next;
} else {
err = -EINVAL;
goto out;
}
} else
- pval = pol->policy;
+ *policy = pol->policy;
if (vma) {
up_read(¤t->mm->mmap_sem);
vma = NULL;
}
- if (policy && put_user(pval, policy))
- return -EFAULT;
-
err = 0;
- if (nmask) {
- nodemask_t nodes;
- get_zonemask(pol, &nodes);
- err = copy_nodes_to_user(nmask, maxnode, &nodes);
- }
+ if (nmask)
+ get_zonemask(pol, nmask);
out:
if (vma)
return err;
}
+/*
+ * 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,
+ unsigned long maxnode)
+{
+ unsigned long k;
+ unsigned long nlongs;
+ unsigned long endmask;
+
+ --maxnode;
+ nodes_clear(*nodes);
+ if (maxnode == 0 || !nmask)
+ return 0;
+
+ nlongs = BITS_TO_LONGS(maxnode);
+ if ((maxnode % BITS_PER_LONG) == 0)
+ endmask = ~0UL;
+ else
+ endmask = (1UL << (maxnode % BITS_PER_LONG)) - 1;
+
+ /* When the user specified more nodes than supported just check
+ if the non supported part is all zero. */
+ if (nlongs > BITS_TO_LONGS(MAX_NUMNODES)) {
+ if (nlongs > PAGE_SIZE/sizeof(long))
+ return -EINVAL;
+ for (k = BITS_TO_LONGS(MAX_NUMNODES); k < nlongs; k++) {
+ unsigned long t;
+ if (get_user(t, nmask + k))
+ return -EFAULT;
+ if (k == nlongs - 1) {
+ if (t & endmask)
+ return -EINVAL;
+ } else if (t)
+ return -EINVAL;
+ }
+ nlongs = BITS_TO_LONGS(MAX_NUMNODES);
+ endmask = ~0UL;
+ }
+
+ if (copy_from_user(nodes_addr(*nodes), nmask, nlongs*sizeof(unsigned long)))
+ return -EFAULT;
+ nodes_addr(*nodes)[nlongs-1] &= endmask;
+ return 0;
+}
+
+/* Copy a kernel node mask to user space */
+static int copy_nodes_to_user(unsigned long __user *mask, unsigned long maxnode,
+ nodemask_t *nodes)
+{
+ unsigned long copy = ALIGN(maxnode-1, 64) / 8;
+ const int nbytes = BITS_TO_LONGS(MAX_NUMNODES) * sizeof(long);
+
+ if (copy > nbytes) {
+ if (copy > PAGE_SIZE)
+ return -EINVAL;
+ if (clear_user((char __user *)mask + nbytes, copy - nbytes))
+ return -EFAULT;
+ copy = nbytes;
+ }
+ return copy_to_user(mask, nodes_addr(*nodes), copy) ? -EFAULT : 0;
+}
+
+asmlinkage long sys_mbind(unsigned long start, unsigned long len,
+ unsigned long mode,
+ unsigned long __user *nmask, unsigned long maxnode,
+ unsigned flags)
+{
+ nodemask_t nodes;
+ int err;
+
+ err = get_nodes(&nodes, nmask, maxnode);
+ if (err)
+ return err;
+ return do_mbind(start, len, mode, &nodes, flags);
+}
+
+/* Set the process memory policy */
+asmlinkage long sys_set_mempolicy(int mode, unsigned long __user *nmask,
+ unsigned long maxnode)
+{
+ int err;
+ nodemask_t nodes;
+
+ if (mode < 0 || mode > MPOL_MAX)
+ return -EINVAL;
+ err = get_nodes(&nodes, nmask, maxnode);
+ if (err)
+ return err;
+ return do_set_mempolicy(mode, &nodes);
+}
+
+/* Retrieve NUMA policy */
+asmlinkage long sys_get_mempolicy(int __user *policy,
+ unsigned long __user *nmask,
+ unsigned long maxnode,
+ unsigned long addr, unsigned long flags)
+{
+ int err, pval;
+ nodemask_t nodes;
+
+ if (nmask != NULL && maxnode < MAX_NUMNODES)
+ return -EINVAL;
+
+ err = do_get_mempolicy(&pval, &nodes, addr, flags);
+
+ if (err)
+ return err;
+
+ if (policy && put_user(pval, policy))
+ return -EFAULT;
+
+ if (nmask)
+ err = copy_nodes_to_user(nmask, maxnode, &nodes);
+
+ return err;
+}
+
#ifdef CONFIG_COMPAT
asmlinkage long compat_sys_get_mempolicy(int __user *policy,
if (vma) {
if (vma->vm_ops && vma->vm_ops->get_policy)
- pol = vma->vm_ops->get_policy(vma, addr);
+ pol = vma->vm_ops->get_policy(vma, addr);
else if (vma->vm_policy &&
vma->vm_policy->policy != MPOL_DEFAULT)
pol = vma->vm_policy;
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));
/* Set interleaving policy for system init. This way not all
the data structures allocated at system boot end up in node zero. */
- if (sys_set_mempolicy(MPOL_INTERLEAVE, nodes_addr(node_online_map),
- MAX_NUMNODES) < 0)
+ if (do_set_mempolicy(MPOL_INTERLEAVE, &node_online_map))
printk("numa_policy_init: interleaving failed\n");
}
-/* Reset policy of current process to default.
- * Assumes fs == KERNEL_DS */
+/* Reset policy of current process to default */
void numa_default_policy(void)
{
- sys_set_mempolicy(MPOL_DEFAULT, NULL, 0);
+ do_set_mempolicy(MPOL_DEFAULT, NULL);
+}
+
+/* Migrate a policy to a different set of nodes */
+static void rebind_policy(struct mempolicy *pol, const nodemask_t *old,
+ const nodemask_t *new)
+{
+ nodemask_t tmp;
+
+ if (!pol)
+ return;
+
+ switch (pol->policy) {
+ case MPOL_DEFAULT:
+ break;
+ case MPOL_INTERLEAVE:
+ nodes_remap(tmp, pol->v.nodes, *old, *new);
+ pol->v.nodes = tmp;
+ current->il_next = node_remap(current->il_next, *old, *new);
+ break;
+ case MPOL_PREFERRED:
+ pol->v.preferred_node = node_remap(pol->v.preferred_node,
+ *old, *new);
+ break;
+ case MPOL_BIND: {
+ nodemask_t nodes;
+ struct zone **z;
+ struct zonelist *zonelist;
+
+ 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 = tmp;
+
+ zonelist = bind_zonelist(&nodes);
+
+ /* If no mem, then zonelist is NULL and we keep old zonelist.
+ * If that old zonelist has no remaining mems_allowed nodes,
+ * then zonelist_policy() will "FALL THROUGH" to MPOL_DEFAULT.
+ */
+
+ if (zonelist) {
+ /* Good - got mem - substitute new zonelist */
+ kfree(pol->v.zonelist);
+ pol->v.zonelist = zonelist;
+ }
+ break;
+ }
+ default:
+ BUG();
+ break;
+ }
+}
+
+/*
+ * Someone moved this task to different nodes. Fixup mempolicies.
+ *
+ * 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.
+ */
+void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new)
+{
+ rebind_policy(current->mempolicy, old, new);
}