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>
#include <linux/rmap.h>
#include <linux/security.h>
#include <linux/syscalls.h>
+#include <linux/ctype.h>
#include <asm/tlbflush.h>
#include <asm/uaccess.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 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];
+
/* Check that the nodemask contains at least one populated zone */
-static int is_valid_nodemask(nodemask_t *nodemask)
+static int is_valid_nodemask(const nodemask_t *nodemask)
{
int nd, k;
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(unsigned short mode, unsigned short flags,
nodemask_t *nodes)
{
struct mempolicy *policy;
nodemask_t cpuset_context_nmask;
+ int ret;
pr_debug("setting mode %d flags %d nodes[0] %lx\n",
mode, flags, nodes ? nodes_addr(*nodes)[0] : -1);
- if (mode == MPOL_DEFAULT)
- return (nodes && nodes_weight(*nodes)) ? ERR_PTR(-EINVAL) :
- 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);
- 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);
- switch (mode) {
- case MPOL_INTERLEAVE:
- if (nodes_empty(*nodes) || nodes_empty(cpuset_context_nmask))
- goto free;
- policy->v.nodes = cpuset_context_nmask;
- break;
- case MPOL_PREFERRED:
- policy->v.preferred_node = first_node(cpuset_context_nmask);
- if (policy->v.preferred_node >= MAX_NUMNODES)
- goto free;
- break;
- case MPOL_BIND:
- if (!is_valid_nodemask(&cpuset_context_nmask))
- goto free;
- policy->v.nodes = cpuset_context_nmask;
- break;
- default:
- BUG();
- }
- policy->policy = mode;
+ policy->mode = mode;
policy->flags = flags;
- if (mpol_store_user_nodemask(policy))
- policy->w.user_nodemask = *nodes;
- else
- policy->w.cpuset_mems_allowed = cpuset_mems_allowed(current);
+
+ 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);
+ }
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;
+ }
-free:
- kmem_cache_free(policy_cache, policy);
- return ERR_PTR(-EINVAL);
+ 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)
{
- nodemask_t tmp;
- int static_nodes;
- int relative_nodes;
-
if (!pol)
return;
- static_nodes = pol->flags & MPOL_F_STATIC_NODES;
- relative_nodes = pol->flags & MPOL_F_RELATIVE_NODES;
if (!mpol_store_user_nodemask(pol) &&
nodes_equal(pol->w.cpuset_mems_allowed, *newmask))
return;
-
- switch (pol->policy) {
- case MPOL_DEFAULT:
- break;
- case MPOL_BIND:
- /* Fall through */
- case MPOL_INTERLEAVE:
- if (static_nodes)
- nodes_and(tmp, pol->w.user_nodemask, *newmask);
- else if (relative_nodes)
- mpol_relative_nodemask(&tmp, &pol->w.user_nodemask,
- newmask);
- else {
- nodes_remap(tmp, pol->v.nodes,
- pol->w.cpuset_mems_allowed, *newmask);
- pol->w.cpuset_mems_allowed = *newmask;
- }
- 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();
- }
- break;
- case MPOL_PREFERRED:
- if (static_nodes) {
- int node = first_node(pol->w.user_nodemask);
-
- if (node_isset(node, *newmask))
- pol->v.preferred_node = node;
- else
- pol->v.preferred_node = -1;
- } else if (relative_nodes) {
- mpol_relative_nodemask(&tmp, &pol->w.user_nodemask,
- newmask);
- pol->v.preferred_node = first_node(tmp);
- } else {
- pol->v.preferred_node = node_remap(pol->v.preferred_node,
- pol->w.cpuset_mems_allowed, *newmask);
- pol->w.cpuset_mems_allowed = *newmask;
- }
- break;
- default:
- BUG();
- break;
- }
+ mpol_ops[pol->mode].rebind(pol, newmask);
}
/*
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;
}
nodemask_t *nodes)
{
struct mempolicy *new;
+ struct mm_struct *mm = current->mm;
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)
{
nodes_clear(*nodes);
- switch (p->policy) {
- case MPOL_DEFAULT:
- break;
+ if (p == &default_policy)
+ return;
+
+ switch (p->mode) {
case MPOL_BIND:
/* 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 | pol->flags;
+ } else {
+ *policy = pol == &default_policy ? MPOL_DEFAULT :
+ pol->mode;
+ /*
+ * Internal mempolicy flags must be masked off before exposing
+ * the policy to userspace.
+ */
+ *policy |= (pol->flags & MPOL_MODE_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)
}
up_write(&mm->mmap_sem);
- mpol_free(new);
+ mpol_put(new);
return err;
}
*
* 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 nodemask representing a mempolicy */
-static nodemask_t *nodemask_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->policy == 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 representing a mempolicy */
-static struct zonelist *zonelist_policy(gfp_t gfp, struct mempolicy *policy)
+/* 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:
/*
- * Normally, MPOL_BIND allocations node-local 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
- * the zonelist for the first node in the mask instead.
+ * 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.
*/
- nd = numa_node_id();
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_zonelist(nd, gfp);
/*
* 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)
{
- unsigned short 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);
return zone->node;
}
- case MPOL_PREFERRED:
- if (policy->v.preferred_node >= 0)
- return policy->v.preferred_node;
- /* Fall through */
-
default:
- return numa_node_id();
+ BUG();
}
}
* @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 local node's zonelist,
- * and a pointer to the mempolicy's @nodemask for filtering the zonelist.
- * If it is also a policy for which get_vma_policy() returns an extra
- * reference, we must hold that reference until after the 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,
nodemask_t **nodemask)
{
- struct mempolicy *pol = get_vma_policy(current, vma, addr);
struct zonelist *zl;
- *mpol = NULL; /* probably no unref needed */
+ *mpol = get_vma_policy(current, vma, addr);
*nodemask = NULL; /* assume !MPOL_BIND */
- if (pol->policy == MPOL_BIND) {
- *nodemask = &pol->v.nodes;
- } else if (pol->policy == MPOL_INTERLEAVE) {
- unsigned nid;
- nid = interleave_nid(pol, vma, addr, HPAGE_SHIFT);
- if (unlikely(pol != &default_policy &&
- pol != current->mempolicy))
- __mpol_free(pol); /* finished with pol */
- return node_zonelist(nid, 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;
}
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_nodemask(gfp, 0,
- zl, nodemask_policy(gfp, pol));
- __mpol_free(pol);
+ zl, policy_nodemask(gfp, pol));
+ __mpol_put(pol);
return page;
}
/*
* fast path: default or task policy
*/
- return __alloc_pages_nodemask(gfp, 0, zl, nodemask_policy(gfp, pol));
+ 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_nodemask(gfp, order,
- zonelist_policy(gfp, pol), nodemask_policy(gfp, pol));
+ 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);
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 || !b)
return 0;
- if (a->policy != b->policy)
+ if (a->mode != b->mode)
return 0;
- if (a->policy != MPOL_DEFAULT && !mpol_match_intent(a, b))
+ if (a->mode != MPOL_DEFAULT && !mpol_match_intent(a, b))
return 0;
- switch (a->policy) {
- case MPOL_DEFAULT:
- return 1;
+ 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;
+ 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;
- 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, 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, flags, 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);
- }
+/**
+ * mpol_shared_policy_init - initialize shared policy for inode
+ * @sp: pointer to inode shared policy
+ * @mpol: struct mempolicy to install
+ *
+ * Install non-NULL @mpol in inode's shared policy rb-tree.
+ * On entry, the current task has a reference on a non-NULL @mpol.
+ * This must be released on exit.
+ */
+void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
+{
+ sp->root = RB_ROOT; /* empty tree == default mempolicy */
+ spin_lock_init(&sp->lock);
+
+ if (mpol) {
+ struct vm_area_struct pvma;
+ struct mempolicy *new;
+
+ /* contextualize the tmpfs mount point mempolicy */
+ new = mpol_new(mpol->mode, mpol->flags, &mpol->w.user_nodemask);
+ mpol_put(mpol); /* drop our ref on sb mpol */
+ if (IS_ERR(new))
+ return; /* no valid nodemask intersection */
+
+ /* Create pseudo-vma that contains just the policy */
+ memset(&pvma, 0, sizeof(struct vm_area_struct));
+ pvma.vm_end = TASK_SIZE; /* policy covers entire file */
+ mpol_set_shared_policy(sp, &pvma, new); /* adds ref */
+ mpol_put(new); /* drop initial ref */
}
}
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);
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);
}
/*
- * Display pages allocated per node and memory policy via /proc.
+ * Parse and format mempolicy from/to strings
*/
+/*
+ * "local" is pseudo-policy: MPOL_PREFERRED with MPOL_F_LOCAL flag
+ * Used only for mpol_parse_str() and mpol_to_str()
+ */
+#define MPOL_LOCAL (MPOL_INTERLEAVE + 1)
static const char * const policy_types[] =
- { "default", "prefer", "bind", "interleave" };
+ { "default", "prefer", "bind", "interleave", "local" };
-/*
+
+#ifdef CONFIG_TMPFS
+/**
+ * mpol_parse_str - parse string to mempolicy
+ * @str: string containing mempolicy to parse
+ * @mpol: pointer to struct mempolicy pointer, returned on success.
+ * @no_context: flag whether to "contextualize" the mempolicy
+ *
+ * Format of input:
+ * <mode>[=<flags>][:<nodelist>]
+ *
+ * if @no_context is true, save the input nodemask in w.user_nodemask in
+ * the returned mempolicy. This will be used to "clone" the mempolicy in
+ * a specific context [cpuset] at a later time. Used to parse tmpfs mpol
+ * mount option. Note that if 'static' or 'relative' mode flags were
+ * specified, the input nodemask will already have been saved. Saving
+ * it again is redundant, but safe.
+ *
+ * On success, returns 0, else 1
+ */
+int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
+{
+ struct mempolicy *new = NULL;
+ unsigned short uninitialized_var(mode);
+ unsigned short uninitialized_var(mode_flags);
+ nodemask_t nodes;
+ char *nodelist = strchr(str, ':');
+ char *flags = strchr(str, '=');
+ int i;
+ int err = 1;
+
+ if (nodelist) {
+ /* NUL-terminate mode or flags string */
+ *nodelist++ = '\0';
+ if (nodelist_parse(nodelist, nodes))
+ goto out;
+ if (!nodes_subset(nodes, node_states[N_HIGH_MEMORY]))
+ goto out;
+ } else
+ nodes_clear(nodes);
+
+ if (flags)
+ *flags++ = '\0'; /* terminate mode string */
+
+ for (i = 0; i <= MPOL_LOCAL; i++) {
+ if (!strcmp(str, policy_types[i])) {
+ mode = i;
+ break;
+ }
+ }
+ if (i > MPOL_LOCAL)
+ goto out;
+
+ switch (mode) {
+ case MPOL_PREFERRED:
+ /*
+ * Insist on a nodelist of one node only
+ */
+ if (nodelist) {
+ char *rest = nodelist;
+ while (isdigit(*rest))
+ rest++;
+ if (!*rest)
+ err = 0;
+ }
+ break;
+ case MPOL_INTERLEAVE:
+ /*
+ * Default to online nodes with memory if no nodelist
+ */
+ if (!nodelist)
+ nodes = node_states[N_HIGH_MEMORY];
+ err = 0;
+ break;
+ case MPOL_LOCAL:
+ /*
+ * Don't allow a nodelist; mpol_new() checks flags
+ */
+ if (nodelist)
+ goto out;
+ mode = MPOL_PREFERRED;
+ break;
+
+ /*
+ * case MPOL_BIND: mpol_new() enforces non-empty nodemask.
+ * case MPOL_DEFAULT: mpol_new() enforces empty nodemask, ignores flags.
+ */
+ }
+
+ mode_flags = 0;
+ if (flags) {
+ /*
+ * Currently, we only support two mutually exclusive
+ * mode flags.
+ */
+ if (!strcmp(flags, "static"))
+ mode_flags |= MPOL_F_STATIC_NODES;
+ else if (!strcmp(flags, "relative"))
+ mode_flags |= MPOL_F_RELATIVE_NODES;
+ else
+ err = 1;
+ }
+
+ new = mpol_new(mode, mode_flags, &nodes);
+ if (IS_ERR(new))
+ err = 1;
+ else if (no_context)
+ new->w.user_nodemask = nodes; /* save for contextualization */
+
+out:
+ /* Restore string for error message */
+ if (nodelist)
+ *--nodelist = ':';
+ if (flags)
+ *--flags = '=';
+ if (!err)
+ *mpol = new;
+ return err;
+}
+#endif /* CONFIG_TMPFS */
+
+/**
+ * mpol_to_str - format a mempolicy structure for printing
+ * @buffer: to contain formatted mempolicy string
+ * @maxlen: length of @buffer
+ * @pol: pointer to mempolicy to be formatted
+ * @no_context: "context free" mempolicy - use nodemask in w.user_nodemask
+ *
* Convert a mempolicy into a string.
* Returns the number of characters in buffer (if positive)
* or an error (negative)
*/
-static inline int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
{
char *p = buffer;
int l;
nodemask_t nodes;
- unsigned short mode = pol ? pol->policy : MPOL_DEFAULT;
+ unsigned short mode;
unsigned short flags = pol ? pol->flags : 0;
+ /*
+ * Sanity check: room for longest mode, flag and some nodes
+ */
+ VM_BUG_ON(maxlen < strlen("interleave") + strlen("relative") + 16);
+
+ if (!pol || pol == &default_policy)
+ mode = MPOL_DEFAULT;
+ else
+ mode = pol->mode;
+
switch (mode) {
case MPOL_DEFAULT:
nodes_clear(nodes);
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:
/* Fall through */
case MPOL_INTERLEAVE:
- nodes = pol->v.nodes;
+ if (no_context)
+ nodes = pol->w.user_nodemask;
+ else
+ nodes = pol->v.nodes;
break;
default:
BUG();
- return -EFAULT;
}
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) {
- int need_bar = 0;
-
+ if (flags & MPOL_MODE_FLAGS) {
if (buffer + maxlen < p + 2)
return -ENOSPC;
*p++ = '=';
+ /*
+ * Currently, the only defined flags are mutually exclusive
+ */
if (flags & MPOL_F_STATIC_NODES)
- p += sprintf(p, "%sstatic", need_bar++ ? "|" : "");
- if (flags & MPOL_F_RELATIVE_NODES)
- p += sprintf(p, "%srelative", need_bar++ ? "|" : "");
+ p += snprintf(p, buffer + maxlen - p, "static");
+ else if (flags & MPOL_F_RELATIVE_NODES)
+ p += snprintf(p, buffer + maxlen - p, "relative");
}
if (!nodes_empty(nodes)) {
if (buffer + maxlen < p + 2)
return -ENOSPC;
- *p++ = '=';
+ *p++ = ':';
p += nodelist_scnprintf(p, buffer + maxlen - p, nodes);
}
return p - buffer;
}
#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;
return 0;
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_to_str(buffer, sizeof(buffer), pol, 0);
+ mpol_cond_put(pol);
seq_printf(m, "%08lx %s", vma->vm_start, buffer);