grows down?
make bind policy root only? It can trigger oom much faster and the
kernel is not always grateful with that.
- could replace all the switch()es with a mempolicy_ops structure.
*/
#include <linux/mempolicy.h>
policied. */
enum zone_type policy_zone = 0;
+/*
+ * run-time system-wide default policy => local allocation
+ */
struct mempolicy default_policy = {
.refcnt = ATOMIC_INIT(1), /* never free it */
- .policy = MPOL_DEFAULT,
+ .mode = MPOL_PREFERRED,
+ .flags = MPOL_F_LOCAL,
};
-static void mpol_rebind_policy(struct mempolicy *pol,
- const nodemask_t *newmask);
+static const struct mempolicy_operations {
+ int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
+ void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
+} mpol_ops[MPOL_MAX];
-/* Do sanity checking on a policy */
-static int mpol_check_policy(int mode, nodemask_t *nodes)
+/* Check that the nodemask contains at least one populated zone */
+static int is_valid_nodemask(const nodemask_t *nodemask)
{
- int was_empty, is_empty;
+ int nd, k;
- if (!nodes)
- return 0;
+ /* Check that there is something useful in this mask */
+ k = policy_zone;
- /*
- * "Contextualize" the in-coming nodemast for cpusets:
- * Remember whether in-coming nodemask was empty, If not,
- * restrict the nodes to the allowed nodes in the cpuset.
- * This is guaranteed to be a subset of nodes with memory.
- */
- cpuset_update_task_memory_state();
- is_empty = was_empty = nodes_empty(*nodes);
- if (!was_empty) {
- nodes_and(*nodes, *nodes, cpuset_current_mems_allowed);
- is_empty = nodes_empty(*nodes); /* after "contextualization" */
- }
+ for_each_node_mask(nd, *nodemask) {
+ struct zone *z;
- switch (mode) {
- case MPOL_DEFAULT:
- /*
- * require caller to specify an empty nodemask
- * before "contextualization"
- */
- if (!was_empty)
- return -EINVAL;
- break;
- case MPOL_BIND:
- case MPOL_INTERLEAVE:
- /*
- * require at least 1 valid node after "contextualization"
- */
- if (is_empty)
- return -EINVAL;
- break;
- case MPOL_PREFERRED:
- /*
- * Did caller specify invalid nodes?
- * Don't silently accept this as "local allocation".
- */
- if (!was_empty && is_empty)
- return -EINVAL;
- break;
+ for (k = 0; k <= policy_zone; k++) {
+ z = &NODE_DATA(nd)->node_zones[k];
+ if (z->present_pages > 0)
+ return 1;
+ }
}
+
return 0;
}
-/* Generate a custom zonelist for the BIND policy. */
-static struct zonelist *bind_zonelist(nodemask_t *nodes)
+static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
{
- struct zonelist *zl;
- int num, max, nd;
- enum zone_type k;
+ return pol->flags & (MPOL_F_STATIC_NODES | MPOL_F_RELATIVE_NODES);
+}
- max = 1 + MAX_NR_ZONES * nodes_weight(*nodes);
- max++; /* space for zlcache_ptr (see mmzone.h) */
- zl = kmalloc(sizeof(struct zone *) * max, GFP_KERNEL);
- if (!zl)
- return ERR_PTR(-ENOMEM);
- zl->zlcache_ptr = NULL;
- num = 0;
- /* First put in the highest zones from all nodes, then all the next
- lower zones etc. Avoid empty zones because the memory allocator
- doesn't like them. If you implement node hot removal you
- have to fix that. */
- k = MAX_NR_ZONES - 1;
- while (1) {
- for_each_node_mask(nd, *nodes) {
- struct zone *z = &NODE_DATA(nd)->node_zones[k];
- if (z->present_pages > 0)
- zl->zones[num++] = z;
- }
- if (k == 0)
- break;
- k--;
- }
- if (num == 0) {
- kfree(zl);
- return ERR_PTR(-EINVAL);
- }
- zl->zones[num] = NULL;
- return zl;
+static void mpol_relative_nodemask(nodemask_t *ret, const nodemask_t *orig,
+ const nodemask_t *rel)
+{
+ nodemask_t tmp;
+ nodes_fold(tmp, *orig, nodes_weight(*rel));
+ nodes_onto(*ret, tmp, *rel);
+}
+
+static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
+{
+ if (nodes_empty(*nodes))
+ return -EINVAL;
+ pol->v.nodes = *nodes;
+ return 0;
+}
+
+static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
+{
+ if (!nodes)
+ pol->flags |= MPOL_F_LOCAL; /* local allocation */
+ else if (nodes_empty(*nodes))
+ return -EINVAL; /* no allowed nodes */
+ else
+ pol->v.preferred_node = first_node(*nodes);
+ return 0;
+}
+
+static int mpol_new_bind(struct mempolicy *pol, const nodemask_t *nodes)
+{
+ if (!is_valid_nodemask(nodes))
+ return -EINVAL;
+ pol->v.nodes = *nodes;
+ return 0;
}
/* Create a new policy */
-static struct mempolicy *mpol_new(int mode, nodemask_t *nodes)
+static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
+ nodemask_t *nodes)
{
struct mempolicy *policy;
+ nodemask_t cpuset_context_nmask;
+ int ret;
- pr_debug("setting mode %d nodes[0] %lx\n",
- mode, nodes ? nodes_addr(*nodes)[0] : -1);
+ pr_debug("setting mode %d flags %d nodes[0] %lx\n",
+ mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
- if (mode == MPOL_DEFAULT)
- return NULL;
+ if (mode == MPOL_DEFAULT) {
+ if (nodes && !nodes_empty(*nodes))
+ return ERR_PTR(-EINVAL);
+ return NULL; /* simply delete any existing policy */
+ }
+ VM_BUG_ON(!nodes);
+
+ /*
+ * MPOL_PREFERRED cannot be used with MPOL_F_STATIC_NODES or
+ * MPOL_F_RELATIVE_NODES if the nodemask is empty (local allocation).
+ * All other modes require a valid pointer to a non-empty nodemask.
+ */
+ if (mode == MPOL_PREFERRED) {
+ if (nodes_empty(*nodes)) {
+ if (((flags & MPOL_F_STATIC_NODES) ||
+ (flags & MPOL_F_RELATIVE_NODES)))
+ return ERR_PTR(-EINVAL);
+ nodes = NULL; /* flag local alloc */
+ }
+ } else if (nodes_empty(*nodes))
+ return ERR_PTR(-EINVAL);
policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
if (!policy)
return ERR_PTR(-ENOMEM);
atomic_set(&policy->refcnt, 1);
- switch (mode) {
- case MPOL_INTERLEAVE:
- policy->v.nodes = *nodes;
- if (nodes_weight(policy->v.nodes) == 0) {
- kmem_cache_free(policy_cache, policy);
- return ERR_PTR(-EINVAL);
- }
- break;
- case MPOL_PREFERRED:
- policy->v.preferred_node = first_node(*nodes);
- if (policy->v.preferred_node >= MAX_NUMNODES)
- policy->v.preferred_node = -1;
- break;
- case MPOL_BIND:
- policy->v.zonelist = bind_zonelist(nodes);
- if (IS_ERR(policy->v.zonelist)) {
- void *error_code = policy->v.zonelist;
- kmem_cache_free(policy_cache, policy);
- return error_code;
- }
- break;
+ policy->mode = mode;
+ policy->flags = flags;
+
+ if (nodes) {
+ /*
+ * cpuset related setup doesn't apply to local allocation
+ */
+ cpuset_update_task_memory_state();
+ if (flags & MPOL_F_RELATIVE_NODES)
+ mpol_relative_nodemask(&cpuset_context_nmask, nodes,
+ &cpuset_current_mems_allowed);
+ else
+ nodes_and(cpuset_context_nmask, *nodes,
+ cpuset_current_mems_allowed);
+ if (mpol_store_user_nodemask(policy))
+ policy->w.user_nodemask = *nodes;
+ else
+ policy->w.cpuset_mems_allowed =
+ cpuset_mems_allowed(current);
+ }
+
+ ret = mpol_ops[mode].create(policy,
+ nodes ? &cpuset_context_nmask : NULL);
+ if (ret < 0) {
+ kmem_cache_free(policy_cache, policy);
+ return ERR_PTR(ret);
}
- policy->policy = mode;
- policy->cpuset_mems_allowed = cpuset_mems_allowed(current);
return policy;
}
+/* Slow path of a mpol destructor. */
+void __mpol_put(struct mempolicy *p)
+{
+ if (!atomic_dec_and_test(&p->refcnt))
+ return;
+ kmem_cache_free(policy_cache, p);
+}
+
+static void mpol_rebind_default(struct mempolicy *pol, const nodemask_t *nodes)
+{
+}
+
+static void mpol_rebind_nodemask(struct mempolicy *pol,
+ const nodemask_t *nodes)
+{
+ nodemask_t tmp;
+
+ if (pol->flags & MPOL_F_STATIC_NODES)
+ nodes_and(tmp, pol->w.user_nodemask, *nodes);
+ else if (pol->flags & MPOL_F_RELATIVE_NODES)
+ mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
+ else {
+ nodes_remap(tmp, pol->v.nodes, pol->w.cpuset_mems_allowed,
+ *nodes);
+ pol->w.cpuset_mems_allowed = *nodes;
+ }
+
+ pol->v.nodes = tmp;
+ if (!node_isset(current->il_next, tmp)) {
+ current->il_next = next_node(current->il_next, tmp);
+ if (current->il_next >= MAX_NUMNODES)
+ current->il_next = first_node(tmp);
+ if (current->il_next >= MAX_NUMNODES)
+ current->il_next = numa_node_id();
+ }
+}
+
+static void mpol_rebind_preferred(struct mempolicy *pol,
+ const nodemask_t *nodes)
+{
+ nodemask_t tmp;
+
+ if (pol->flags & MPOL_F_STATIC_NODES) {
+ int node = first_node(pol->w.user_nodemask);
+
+ if (node_isset(node, *nodes)) {
+ pol->v.preferred_node = node;
+ pol->flags &= ~MPOL_F_LOCAL;
+ } else
+ pol->flags |= MPOL_F_LOCAL;
+ } else if (pol->flags & MPOL_F_RELATIVE_NODES) {
+ mpol_relative_nodemask(&tmp, &pol->w.user_nodemask, nodes);
+ pol->v.preferred_node = first_node(tmp);
+ } else if (!(pol->flags & MPOL_F_LOCAL)) {
+ pol->v.preferred_node = node_remap(pol->v.preferred_node,
+ pol->w.cpuset_mems_allowed,
+ *nodes);
+ pol->w.cpuset_mems_allowed = *nodes;
+ }
+}
+
+/* Migrate a policy to a different set of nodes */
+static void mpol_rebind_policy(struct mempolicy *pol,
+ const nodemask_t *newmask)
+{
+ if (!pol)
+ return;
+ if (!mpol_store_user_nodemask(pol) &&
+ nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
+ return;
+ mpol_ops[pol->mode].rebind(pol, newmask);
+}
+
+/*
+ * 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.
+ *
+ * Call holding a reference to mm. Takes mm->mmap_sem during call.
+ */
+
+void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *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);
+}
+
+static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
+ [MPOL_DEFAULT] = {
+ .rebind = mpol_rebind_default,
+ },
+ [MPOL_INTERLEAVE] = {
+ .create = mpol_new_interleave,
+ .rebind = mpol_rebind_nodemask,
+ },
+ [MPOL_PREFERRED] = {
+ .create = mpol_new_preferred,
+ .rebind = mpol_rebind_preferred,
+ },
+ [MPOL_BIND] = {
+ .create = mpol_new_bind,
+ .rebind = mpol_rebind_nodemask,
+ },
+};
+
static void gather_stats(struct page *, void *, int pte_dirty);
static void migrate_page_add(struct page *page, struct list_head *pagelist,
unsigned long flags);
if (!err) {
mpol_get(new);
vma->vm_policy = new;
- mpol_free(old);
+ mpol_put(old);
}
return err;
}
}
/* Set the process memory policy */
-static long do_set_mempolicy(int mode, nodemask_t *nodes)
+static long do_set_mempolicy(unsigned short mode, unsigned short flags,
+ nodemask_t *nodes)
{
struct mempolicy *new;
+ struct mm_struct *mm = current->mm;
- if (mpol_check_policy(mode, nodes))
- return -EINVAL;
- new = mpol_new(mode, nodes);
+ new = mpol_new(mode, flags, nodes);
if (IS_ERR(new))
return PTR_ERR(new);
- mpol_free(current->mempolicy);
+
+ /*
+ * prevent changing our mempolicy while show_numa_maps()
+ * is using it.
+ * Note: do_set_mempolicy() can be called at init time
+ * with no 'mm'.
+ */
+ if (mm)
+ down_write(&mm->mmap_sem);
+ mpol_put(current->mempolicy);
current->mempolicy = new;
mpol_set_task_struct_flag();
- if (new && new->policy == MPOL_INTERLEAVE)
+ if (new && new->mode == MPOL_INTERLEAVE &&
+ nodes_weight(new->v.nodes))
current->il_next = first_node(new->v.nodes);
+ if (mm)
+ up_write(&mm->mmap_sem);
+
return 0;
}
-/* Fill a zone bitmap for a policy */
-static void get_zonemask(struct mempolicy *p, nodemask_t *nodes)
+/*
+ * Return nodemask for policy for get_mempolicy() query
+ */
+static void get_policy_nodemask(struct mempolicy *p, nodemask_t *nodes)
{
- int i;
-
nodes_clear(*nodes);
- switch (p->policy) {
+ if (p == &default_policy)
+ return;
+
+ switch (p->mode) {
case MPOL_BIND:
- for (i = 0; p->v.zonelist->zones[i]; i++)
- node_set(zone_to_nid(p->v.zonelist->zones[i]),
- *nodes);
- break;
- case MPOL_DEFAULT:
- break;
+ /* Fall through */
case MPOL_INTERLEAVE:
*nodes = p->v.nodes;
break;
case MPOL_PREFERRED:
- /* or use current node instead of memory_map? */
- if (p->v.preferred_node < 0)
- *nodes = node_states[N_HIGH_MEMORY];
- else
+ if (!(p->flags & MPOL_F_LOCAL))
node_set(p->v.preferred_node, *nodes);
+ /* else return empty node mask for local allocation */
break;
default:
BUG();
}
if (flags & MPOL_F_ADDR) {
+ /*
+ * Do NOT fall back to task policy if the
+ * vma/shared policy at addr is NULL. We
+ * want to return MPOL_DEFAULT in this case.
+ */
down_read(&mm->mmap_sem);
vma = find_vma_intersection(mm, addr, addr+1);
if (!vma) {
return -EINVAL;
if (!pol)
- pol = &default_policy;
+ pol = &default_policy; /* indicates default behavior */
if (flags & MPOL_F_NODE) {
if (flags & MPOL_F_ADDR) {
goto out;
*policy = err;
} else if (pol == current->mempolicy &&
- pol->policy == MPOL_INTERLEAVE) {
+ pol->mode == MPOL_INTERLEAVE) {
*policy = current->il_next;
} else {
err = -EINVAL;
goto out;
}
- } else
- *policy = pol->policy;
+ } else {
+ *policy = pol == &default_policy ? MPOL_DEFAULT :
+ pol->mode;
+ *policy |= pol->flags;
+ }
if (vma) {
up_read(¤t->mm->mmap_sem);
err = 0;
if (nmask)
- get_zonemask(pol, nmask);
+ get_policy_nodemask(pol, nmask);
out:
+ mpol_cond_put(pol);
if (vma)
up_read(¤t->mm->mmap_sem);
return err;
int err = 0;
nodemask_t tmp;
- down_read(&mm->mmap_sem);
+ down_read(&mm->mmap_sem);
err = migrate_vmas(mm, from_nodes, to_nodes, flags);
if (err)
#endif
static long do_mbind(unsigned long start, unsigned long len,
- unsigned long mode, nodemask_t *nmask,
- unsigned long flags)
+ unsigned short mode, unsigned short mode_flags,
+ nodemask_t *nmask, unsigned long flags)
{
struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
int err;
LIST_HEAD(pagelist);
- if ((flags & ~(unsigned long)(MPOL_MF_STRICT |
- MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
- || mode > MPOL_MAX)
+ if (flags & ~(unsigned long)(MPOL_MF_STRICT |
+ MPOL_MF_MOVE | MPOL_MF_MOVE_ALL))
return -EINVAL;
if ((flags & MPOL_MF_MOVE_ALL) && !capable(CAP_SYS_NICE))
return -EPERM;
if (end == start)
return 0;
- if (mpol_check_policy(mode, nmask))
- return -EINVAL;
-
- new = mpol_new(mode, nmask);
+ new = mpol_new(mode, mode_flags, nmask);
if (IS_ERR(new))
return PTR_ERR(new);
if (!new)
flags |= MPOL_MF_DISCONTIG_OK;
- pr_debug("mbind %lx-%lx mode:%ld nodes:%lx\n",start,start+len,
- mode, nmask ? nodes_addr(*nmask)[0] : -1);
+ pr_debug("mbind %lx-%lx mode:%d flags:%d nodes:%lx\n",
+ start, start + len, mode, mode_flags,
+ nmask ? nodes_addr(*nmask)[0] : -1);
down_write(&mm->mmap_sem);
vma = check_range(mm, start, end, nmask,
}
up_write(&mm->mmap_sem);
- mpol_free(new);
+ mpol_put(new);
return err;
}
{
nodemask_t nodes;
int err;
+ unsigned short mode_flags;
+ mode_flags = mode & MPOL_MODE_FLAGS;
+ mode &= ~MPOL_MODE_FLAGS;
+ if (mode >= MPOL_MAX)
+ return -EINVAL;
+ if ((mode_flags & MPOL_F_STATIC_NODES) &&
+ (mode_flags & MPOL_F_RELATIVE_NODES))
+ return -EINVAL;
err = get_nodes(&nodes, nmask, maxnode);
if (err)
return err;
- return do_mbind(start, len, mode, &nodes, flags);
+ return do_mbind(start, len, mode, mode_flags, &nodes, flags);
}
/* Set the process memory policy */
{
int err;
nodemask_t nodes;
+ unsigned short flags;
- if (mode < 0 || mode > MPOL_MAX)
+ flags = mode & MPOL_MODE_FLAGS;
+ mode &= ~MPOL_MODE_FLAGS;
+ if ((unsigned int)mode >= MPOL_MAX)
+ return -EINVAL;
+ if ((flags & MPOL_F_STATIC_NODES) && (flags & MPOL_F_RELATIVE_NODES))
return -EINVAL;
err = get_nodes(&nodes, nmask, maxnode);
if (err)
return err;
- return do_set_mempolicy(mode, &nodes);
+ return do_set_mempolicy(mode, flags, &nodes);
}
asmlinkage long sys_migrate_pages(pid_t pid, unsigned long maxnode,
*
* Returns effective policy for a VMA at specified address.
* Falls back to @task or system default policy, as necessary.
- * Returned policy has extra reference count if shared, vma,
- * or some other task's policy [show_numa_maps() can pass
- * @task != current]. It is the caller's responsibility to
- * free the reference in these cases.
+ * Current or other task's task mempolicy and non-shared vma policies
+ * are protected by the task's mmap_sem, which must be held for read by
+ * the caller.
+ * Shared policies [those marked as MPOL_F_SHARED] require an extra reference
+ * count--added by the get_policy() vm_op, as appropriate--to protect against
+ * freeing by another task. It is the caller's responsibility to free the
+ * extra reference for shared policies.
*/
-static struct mempolicy * get_vma_policy(struct task_struct *task,
+static struct mempolicy *get_vma_policy(struct task_struct *task,
struct vm_area_struct *vma, unsigned long addr)
{
struct mempolicy *pol = task->mempolicy;
- int shared_pol = 0;
if (vma) {
if (vma->vm_ops && vma->vm_ops->get_policy) {
- pol = vma->vm_ops->get_policy(vma, addr);
- shared_pol = 1; /* if pol non-NULL, add ref below */
- } else if (vma->vm_policy &&
- vma->vm_policy->policy != MPOL_DEFAULT)
+ struct mempolicy *vpol = vma->vm_ops->get_policy(vma,
+ addr);
+ if (vpol)
+ pol = vpol;
+ } else if (vma->vm_policy)
pol = vma->vm_policy;
}
if (!pol)
pol = &default_policy;
- else if (!shared_pol && pol != current->mempolicy)
- mpol_get(pol); /* vma or other task's policy */
return pol;
}
-/* Return a zonelist representing a mempolicy */
-static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
+/*
+ * Return a nodemask representing a mempolicy for filtering nodes for
+ * page allocation
+ */
+static nodemask_t *policy_nodemask(gfp_t gfp, struct mempolicy *policy)
+{
+ /* Lower zones don't get a nodemask applied for MPOL_BIND */
+ if (unlikely(policy->mode == MPOL_BIND) &&
+ gfp_zone(gfp) >= policy_zone &&
+ cpuset_nodemask_valid_mems_allowed(&policy->v.nodes))
+ return &policy->v.nodes;
+
+ return NULL;
+}
+
+/* Return a zonelist indicated by gfp for node representing a mempolicy */
+static struct zonelist *policy_zonelist(gfp_t gfp, struct mempolicy *policy)
{
- int nd;
+ int nd = numa_node_id();
- switch (policy->policy) {
+ switch (policy->mode) {
case MPOL_PREFERRED:
- nd = policy->v.preferred_node;
- if (nd < 0)
- nd = numa_node_id();
+ if (!(policy->flags & MPOL_F_LOCAL))
+ nd = policy->v.preferred_node;
break;
case MPOL_BIND:
- /* Lower zones don't get a policy applied */
- /* Careful: current->mems_allowed might have moved */
- if (gfp_zone(gfp) >= policy_zone)
- if (cpuset_zonelist_valid_mems_allowed(policy->v.zonelist))
- return policy->v.zonelist;
- /*FALL THROUGH*/
+ /*
+ * Normally, MPOL_BIND allocations are node-local within the
+ * allowed nodemask. However, if __GFP_THISNODE is set and the
+ * current node is part of the mask, we use the zonelist for
+ * the first node in the mask instead.
+ */
+ if (unlikely(gfp & __GFP_THISNODE) &&
+ unlikely(!node_isset(nd, policy->v.nodes)))
+ nd = first_node(policy->v.nodes);
+ break;
case MPOL_INTERLEAVE: /* should not happen */
- case MPOL_DEFAULT:
- nd = numa_node_id();
break;
default:
- nd = 0;
BUG();
}
- return NODE_DATA(nd)->node_zonelists + gfp_zone(gfp);
+ return node_zonelist(nd, gfp);
}
/* Do dynamic interleaving for a process */
next = next_node(nid, policy->v.nodes);
if (next >= MAX_NUMNODES)
next = first_node(policy->v.nodes);
- me->il_next = next;
+ if (next < MAX_NUMNODES)
+ me->il_next = next;
return nid;
}
/*
* Depending on the memory policy provide a node from which to allocate the
* next slab entry.
+ * @policy must be protected by freeing by the caller. If @policy is
+ * the current task's mempolicy, this protection is implicit, as only the
+ * task can change it's policy. The system default policy requires no
+ * such protection.
*/
unsigned slab_node(struct mempolicy *policy)
{
- int pol = policy ? policy->policy : MPOL_DEFAULT;
+ if (!policy || policy->flags & MPOL_F_LOCAL)
+ return numa_node_id();
+
+ switch (policy->mode) {
+ case MPOL_PREFERRED:
+ /*
+ * handled MPOL_F_LOCAL above
+ */
+ return policy->v.preferred_node;
- switch (pol) {
case MPOL_INTERLEAVE:
return interleave_nodes(policy);
- case MPOL_BIND:
+ case MPOL_BIND: {
/*
* Follow bind policy behavior and start allocation at the
* first node.
*/
- return zone_to_nid(policy->v.zonelist->zones[0]);
-
- case MPOL_PREFERRED:
- if (policy->v.preferred_node >= 0)
- return policy->v.preferred_node;
- /* Fall through */
+ struct zonelist *zonelist;
+ struct zone *zone;
+ enum zone_type highest_zoneidx = gfp_zone(GFP_KERNEL);
+ zonelist = &NODE_DATA(numa_node_id())->node_zonelists[0];
+ (void)first_zones_zonelist(zonelist, highest_zoneidx,
+ &policy->v.nodes,
+ &zone);
+ return zone->node;
+ }
default:
- return numa_node_id();
+ BUG();
}
}
struct vm_area_struct *vma, unsigned long off)
{
unsigned nnodes = nodes_weight(pol->v.nodes);
- unsigned target = (unsigned)off % nnodes;
+ unsigned target;
int c;
int nid = -1;
+ if (!nnodes)
+ return numa_node_id();
+ target = (unsigned int)off % nnodes;
c = 0;
do {
nid = next_node(nid, pol->v.nodes);
* @vma = virtual memory area whose policy is sought
* @addr = address in @vma for shared policy lookup and interleave policy
* @gfp_flags = for requested zone
- * @mpol = pointer to mempolicy pointer for reference counted 'BIND policy
+ * @mpol = pointer to mempolicy pointer for reference counted mempolicy
+ * @nodemask = pointer to nodemask pointer for MPOL_BIND nodemask
*
- * Returns a zonelist suitable for a huge page allocation.
- * If the effective policy is 'BIND, returns pointer to policy's zonelist.
- * If it is also a policy for which get_vma_policy() returns an extra
- * reference, we must hold that reference until after allocation.
- * In that case, return policy via @mpol so hugetlb allocation can drop
- * the reference. For non-'BIND referenced policies, we can/do drop the
- * reference here, so the caller doesn't need to know about the special case
- * for default and current task policy.
+ * Returns a zonelist suitable for a huge page allocation and a pointer
+ * to the struct mempolicy for conditional unref after allocation.
+ * If the effective policy is 'BIND, returns a pointer to the mempolicy's
+ * @nodemask for filtering the zonelist.
*/
struct zonelist *huge_zonelist(struct vm_area_struct *vma, unsigned long addr,
- gfp_t gfp_flags, struct mempolicy **mpol)
+ gfp_t gfp_flags, struct mempolicy **mpol,
+ nodemask_t **nodemask)
{
- struct mempolicy *pol = get_vma_policy(current, vma, addr);
struct zonelist *zl;
- *mpol = NULL; /* probably no unref needed */
- if (pol->policy == MPOL_INTERLEAVE) {
- unsigned nid;
+ *mpol = get_vma_policy(current, vma, addr);
+ *nodemask = NULL; /* assume !MPOL_BIND */
- nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
- if (unlikely(pol != &default_policy &&
- pol != current->mempolicy))
- __mpol_free(pol); /* finished with pol */
- return NODE_DATA(nid)->node_zonelists + gfp_zone(gfp_flags);
- }
-
- zl = zonelist_policy(GFP_HIGHUSER, pol);
- if (unlikely(pol != &default_policy && pol != current->mempolicy)) {
- if (pol->policy != MPOL_BIND)
- __mpol_free(pol); /* finished with pol */
- else
- *mpol = pol; /* unref needed after allocation */
+ if (unlikely((*mpol)->mode == MPOL_INTERLEAVE)) {
+ zl = node_zonelist(interleave_nid(*mpol, vma, addr,
+ HPAGE_SHIFT), gfp_flags);
+ } else {
+ zl = policy_zonelist(gfp_flags, *mpol);
+ if ((*mpol)->mode == MPOL_BIND)
+ *nodemask = &(*mpol)->v.nodes;
}
return zl;
}
struct zonelist *zl;
struct page *page;
- zl = NODE_DATA(nid)->node_zonelists + gfp_zone(gfp);
+ zl = node_zonelist(nid, gfp);
page = __alloc_pages(gfp, order, zl);
- if (page && page_zone(page) == zl->zones[0])
+ if (page && page_zone(page) == zonelist_zone(&zl->_zonerefs[0]))
inc_zone_page_state(page, NUMA_INTERLEAVE_HIT);
return page;
}
cpuset_update_task_memory_state();
- if (unlikely(pol->policy == MPOL_INTERLEAVE)) {
+ if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
unsigned nid;
nid = interleave_nid(pol, vma, addr, PAGE_SHIFT);
- if (unlikely(pol != &default_policy &&
- pol != current->mempolicy))
- __mpol_free(pol); /* finished with pol */
+ mpol_cond_put(pol);
return alloc_page_interleave(gfp, 0, nid);
}
- zl = zonelist_policy(gfp, pol);
- if (pol != &default_policy && pol != current->mempolicy) {
+ zl = policy_zonelist(gfp, pol);
+ if (unlikely(mpol_needs_cond_ref(pol))) {
/*
- * slow path: ref counted policy -- shared or vma
+ * slow path: ref counted shared policy
*/
- struct page *page = __alloc_pages(gfp, 0, zl);
- __mpol_free(pol);
+ struct page *page = __alloc_pages_nodemask(gfp, 0,
+ zl, policy_nodemask(gfp, pol));
+ __mpol_put(pol);
return page;
}
/*
* fast path: default or task policy
*/
- return __alloc_pages(gfp, 0, zl);
+ return __alloc_pages_nodemask(gfp, 0, zl, policy_nodemask(gfp, pol));
}
/**
cpuset_update_task_memory_state();
if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
pol = &default_policy;
- if (pol->policy == MPOL_INTERLEAVE)
+
+ /*
+ * No reference counting needed for current->mempolicy
+ * nor system default_policy
+ */
+ if (pol->mode == MPOL_INTERLEAVE)
return alloc_page_interleave(gfp, order, interleave_nodes(pol));
- return __alloc_pages(gfp, order, zonelist_policy(gfp, pol));
+ return __alloc_pages_nodemask(gfp, order,
+ policy_zonelist(gfp, pol), policy_nodemask(gfp, pol));
}
EXPORT_SYMBOL(alloc_pages_current);
/*
- * If mpol_copy() sees current->cpuset == cpuset_being_rebound, then it
+ * If mpol_dup() 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().
*/
-/* Slow path of a mempolicy copy */
-struct mempolicy *__mpol_copy(struct mempolicy *old)
+/* Slow path of a mempolicy duplicate */
+struct mempolicy *__mpol_dup(struct mempolicy *old)
{
struct mempolicy *new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
}
*new = *old;
atomic_set(&new->refcnt, 1);
- if (new->policy == MPOL_BIND) {
- int sz = ksize(old->v.zonelist);
- new->v.zonelist = kmemdup(old->v.zonelist, sz, GFP_KERNEL);
- if (!new->v.zonelist) {
- kmem_cache_free(policy_cache, new);
- return ERR_PTR(-ENOMEM);
- }
- }
return new;
}
+/*
+ * If *frompol needs [has] an extra ref, copy *frompol to *tompol ,
+ * eliminate the * MPOL_F_* flags that require conditional ref and
+ * [NOTE!!!] drop the extra ref. Not safe to reference *frompol directly
+ * after return. Use the returned value.
+ *
+ * Allows use of a mempolicy for, e.g., multiple allocations with a single
+ * policy lookup, even if the policy needs/has extra ref on lookup.
+ * shmem_readahead needs this.
+ */
+struct mempolicy *__mpol_cond_copy(struct mempolicy *tompol,
+ struct mempolicy *frompol)
+{
+ if (!mpol_needs_cond_ref(frompol))
+ return frompol;
+
+ *tompol = *frompol;
+ tompol->flags &= ~MPOL_F_SHARED; /* copy doesn't need unref */
+ __mpol_put(frompol);
+ return tompol;
+}
+
+static int mpol_match_intent(const struct mempolicy *a,
+ const struct mempolicy *b)
+{
+ if (a->flags != b->flags)
+ return 0;
+ if (!mpol_store_user_nodemask(a))
+ return 1;
+ return nodes_equal(a->w.user_nodemask, b->w.user_nodemask);
+}
+
/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
if (!a || !b)
return 0;
- if (a->policy != b->policy)
+ if (a->mode != b->mode)
return 0;
- switch (a->policy) {
- case MPOL_DEFAULT:
- return 1;
+ if (a->mode != MPOL_DEFAULT && !mpol_match_intent(a, b))
+ return 0;
+ switch (a->mode) {
+ case MPOL_BIND:
+ /* Fall through */
case MPOL_INTERLEAVE:
return nodes_equal(a->v.nodes, b->v.nodes);
case MPOL_PREFERRED:
- return a->v.preferred_node == b->v.preferred_node;
- case MPOL_BIND: {
- int i;
- for (i = 0; a->v.zonelist->zones[i]; i++)
- if (a->v.zonelist->zones[i] != b->v.zonelist->zones[i])
- return 0;
- return b->v.zonelist->zones[i] == NULL;
- }
+ return a->v.preferred_node == b->v.preferred_node &&
+ a->flags == b->flags;
default:
BUG();
return 0;
}
}
-/* Slow path of a mpol destructor. */
-void __mpol_free(struct mempolicy *p)
-{
- if (!atomic_dec_and_test(&p->refcnt))
- return;
- if (p->policy == MPOL_BIND)
- kfree(p->v.zonelist);
- p->policy = MPOL_DEFAULT;
- kmem_cache_free(policy_cache, p);
-}
-
/*
* Shared memory backing store policy support.
*
rb_link_node(&new->nd, parent, p);
rb_insert_color(&new->nd, &sp->root);
pr_debug("inserting %lx-%lx: %d\n", new->start, new->end,
- new->policy ? new->policy->policy : 0);
+ new->policy ? new->policy->mode : 0);
}
/* Find shared policy intersecting idx */
{
pr_debug("deleting %lx-l%lx\n", n->start, n->end);
rb_erase(&n->nd, &sp->root);
- mpol_free(n->policy);
+ mpol_put(n->policy);
kmem_cache_free(sn_cache, n);
}
n->start = start;
n->end = end;
mpol_get(pol);
+ pol->flags |= MPOL_F_SHARED; /* for unref */
n->policy = pol;
return n;
}
sp_insert(sp, new);
spin_unlock(&sp->lock);
if (new2) {
- mpol_free(new2->policy);
+ mpol_put(new2->policy);
kmem_cache_free(sn_cache, new2);
}
return 0;
}
-void mpol_shared_policy_init(struct shared_policy *info, int policy,
- nodemask_t *policy_nodes)
+void mpol_shared_policy_init(struct shared_policy *info, unsigned short policy,
+ unsigned short flags, 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);
+ /* Falls back to NULL policy [MPOL_DEFAULT] on any error */
+ newpol = mpol_new(policy, flags, policy_nodes);
if (!IS_ERR(newpol)) {
/* Create pseudo-vma that contains just the policy */
struct vm_area_struct pvma;
/* Policy covers entire file */
pvma.vm_end = TASK_SIZE;
mpol_set_shared_policy(info, &pvma, newpol);
- mpol_free(newpol);
+ mpol_put(newpol);
}
}
}
struct sp_node *new = NULL;
unsigned long sz = vma_pages(vma);
- pr_debug("set_shared_policy %lx sz %lu %d %lx\n",
+ pr_debug("set_shared_policy %lx sz %lu %d %d %lx\n",
vma->vm_pgoff,
- sz, npol? npol->policy : -1,
+ sz, npol ? npol->mode : -1,
+ npol ? npol->flags : -1,
npol ? nodes_addr(npol->v.nodes)[0] : -1);
if (npol) {
n = rb_entry(next, struct sp_node, nd);
next = rb_next(&n->nd);
rb_erase(&n->nd, &p->root);
- mpol_free(n->policy);
+ mpol_put(n->policy);
kmem_cache_free(sn_cache, n);
}
spin_unlock(&p->lock);
if (unlikely(nodes_empty(interleave_nodes)))
node_set(prefer, interleave_nodes);
- if (do_set_mempolicy(MPOL_INTERLEAVE, &interleave_nodes))
+ if (do_set_mempolicy(MPOL_INTERLEAVE, 0, &interleave_nodes))
printk("numa_policy_init: interleaving failed\n");
}
/* Reset policy of current process to default */
void numa_default_policy(void)
{
- do_set_mempolicy(MPOL_DEFAULT, NULL);
-}
-
-/* Migrate a policy to a different set of nodes */
-static 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, *mpolmask, *newmask);
- pol->v.nodes = tmp;
- *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,
- *mpolmask, *newmask);
- *mpolmask = *newmask;
- 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(zone_to_nid(*z), nodes);
- nodes_remap(tmp, nodes, *mpolmask, *newmask);
- 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 (!IS_ERR(zonelist)) {
- /* Good - got mem - substitute new zonelist */
- kfree(pol->v.zonelist);
- pol->v.zonelist = zonelist;
- }
- *mpolmask = *newmask;
- break;
- }
- default:
- BUG();
- break;
- }
-}
-
-/*
- * 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.
- *
- * Call holding a reference to mm. Takes mm->mmap_sem during call.
- */
-
-void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *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);
+ do_set_mempolicy(MPOL_DEFAULT, 0, NULL);
}
/*
- * Display pages allocated per node and memory policy via /proc.
+ * "local" is pseudo-policy: MPOL_PREFERRED with MPOL_F_LOCAL flag
+ * Used only for mpol_to_str()
*/
-
+#define MPOL_LOCAL (MPOL_INTERLEAVE + 1)
static const char * const policy_types[] =
- { "default", "prefer", "bind", "interleave" };
+ { "default", "prefer", "bind", "interleave", "local" };
/*
* Convert a mempolicy into a string.
char *p = buffer;
int l;
nodemask_t nodes;
- int mode = pol ? pol->policy : MPOL_DEFAULT;
+ unsigned short mode;
+ unsigned short flags = pol ? pol->flags : 0;
+
+ if (!pol || pol == &default_policy)
+ mode = MPOL_DEFAULT;
+ else
+ mode = pol->mode;
switch (mode) {
case MPOL_DEFAULT:
case MPOL_PREFERRED:
nodes_clear(nodes);
- node_set(pol->v.preferred_node, nodes);
+ if (flags & MPOL_F_LOCAL)
+ mode = MPOL_LOCAL; /* pseudo-policy */
+ else
+ node_set(pol->v.preferred_node, nodes);
break;
case MPOL_BIND:
- get_zonemask(pol, &nodes);
- break;
-
+ /* Fall through */
case MPOL_INTERLEAVE:
nodes = pol->v.nodes;
break;
}
l = strlen(policy_types[mode]);
- if (buffer + maxlen < p + l + 1)
- return -ENOSPC;
+ if (buffer + maxlen < p + l + 1)
+ return -ENOSPC;
strcpy(p, policy_types[mode]);
p += l;
+ if (flags & MPOL_MODE_FLAGS) {
+ int need_bar = 0;
+
+ if (buffer + maxlen < p + 2)
+ return -ENOSPC;
+ *p++ = '=';
+
+ if (flags & MPOL_F_STATIC_NODES)
+ p += sprintf(p, "%sstatic", need_bar++ ? "|" : "");
+ if (flags & MPOL_F_RELATIVE_NODES)
+ p += sprintf(p, "%srelative", need_bar++ ? "|" : "");
+ }
+
if (!nodes_empty(nodes)) {
if (buffer + maxlen < p + 2)
return -ENOSPC;
}
#endif
+/*
+ * Display pages allocated per node and memory policy via /proc.
+ */
int show_numa_map(struct seq_file *m, void *v)
{
struct proc_maps_private *priv = m->private;
pol = get_vma_policy(priv->task, vma, vma->vm_start);
mpol_to_str(buffer, sizeof(buffer), pol);
- /*
- * unref shared or other task's mempolicy
- */
- if (pol != &default_policy && pol != current->mempolicy)
- __mpol_free(pol);
+ mpol_cond_put(pol);
seq_printf(m, "%08lx %s", vma->vm_start, buffer);
git.openpandora.org / pandora-kernel.git / blobdiff