* If pagelist != NULL then isolate pages from the LRU and
* put them on the pagelist.
*/
-static struct vm_area_struct *
+static int
check_range(struct mm_struct *mm, unsigned long start, unsigned long end,
const nodemask_t *nodes, unsigned long flags, void *private)
{
- int err;
- struct vm_area_struct *first, *vma, *prev;
-
+ int err = 0;
+ struct vm_area_struct *vma, *prev;
- first = find_vma(mm, start);
- if (!first)
- return ERR_PTR(-EFAULT);
+ vma = find_vma(mm, start);
+ if (!vma)
+ return -EFAULT;
prev = NULL;
- for (vma = first; vma && vma->vm_start < end; vma = vma->vm_next) {
+ for (; vma && vma->vm_start < end; vma = vma->vm_next) {
if (!(flags & MPOL_MF_DISCONTIG_OK)) {
if (!vma->vm_next && vma->vm_end < end)
- return ERR_PTR(-EFAULT);
+ return -EFAULT;
if (prev && prev->vm_end < vma->vm_start)
- return ERR_PTR(-EFAULT);
+ return -EFAULT;
}
if (!is_vm_hugetlb_page(vma) &&
((flags & MPOL_MF_STRICT) ||
start = vma->vm_start;
err = check_pgd_range(vma, start, endvma, nodes,
flags, private);
- if (err) {
- first = ERR_PTR(err);
+ if (err)
break;
- }
}
prev = vma;
}
- return first;
+ return err;
}
-/* Apply policy to a single VMA */
-static int policy_vma(struct vm_area_struct *vma, struct mempolicy *new)
+/*
+ * Apply policy to a single VMA
+ * This must be called with the mmap_sem held for writing.
+ */
+static int vma_replace_policy(struct vm_area_struct *vma,
+ struct mempolicy *pol)
{
- int err = 0;
- struct mempolicy *old = vma->vm_policy;
+ int err;
+ struct mempolicy *old;
+ struct mempolicy *new;
pr_debug("vma %lx-%lx/%lx vm_ops %p vm_file %p set_policy %p\n",
vma->vm_start, vma->vm_end, vma->vm_pgoff,
vma->vm_ops, vma->vm_file,
vma->vm_ops ? vma->vm_ops->set_policy : NULL);
- if (vma->vm_ops && vma->vm_ops->set_policy)
+ new = mpol_dup(pol);
+ if (IS_ERR(new))
+ return PTR_ERR(new);
+
+ if (vma->vm_ops && vma->vm_ops->set_policy) {
err = vma->vm_ops->set_policy(vma, new);
- if (!err) {
- mpol_get(new);
- vma->vm_policy = new;
- mpol_put(old);
+ if (err)
+ goto err_out;
}
+
+ old = vma->vm_policy;
+ vma->vm_policy = new; /* protected by mmap_sem */
+ mpol_put(old);
+
+ return 0;
+ err_out:
+ mpol_put(new);
return err;
}
if (err)
goto out;
}
- err = policy_vma(vma, new_pol);
+ err = vma_replace_policy(vma, new_pol);
if (err)
goto out;
}
nodemask_t nmask;
LIST_HEAD(pagelist);
int err = 0;
- struct vm_area_struct *vma;
nodes_clear(nmask);
node_set(source, nmask);
- vma = check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
+ /*
+ * This does not "check" the range but isolates all pages that
+ * need migration. Between passing in the full user address
+ * space range and MPOL_MF_DISCONTIG_OK, this call can not fail.
+ */
+ VM_BUG_ON(!(flags & (MPOL_MF_MOVE | MPOL_MF_MOVE_ALL)));
+ check_range(mm, mm->mmap->vm_start, mm->task_size, &nmask,
flags | MPOL_MF_DISCONTIG_OK, &pagelist);
- if (IS_ERR(vma))
- return PTR_ERR(vma);
if (!list_empty(&pagelist)) {
err = migrate_pages(&pagelist, new_node_page, dest,
- false, true);
+ false, MIGRATE_SYNC);
if (err)
putback_lru_pages(&pagelist);
}
/*
* Allocate a new page for page migration based on vma policy.
- * Start assuming that page is mapped by vma pointed to by @private.
+ * Start by assuming the page is mapped by the same vma as contains @start.
* Search forward from there, if not. N.B., this assumes that the
* list of pages handed to migrate_pages()--which is how we get here--
* is in virtual address order.
*/
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
{
- struct vm_area_struct *vma = (struct vm_area_struct *)private;
+ struct vm_area_struct *vma;
unsigned long uninitialized_var(address);
+ vma = find_vma(current->mm, start);
while (vma) {
address = page_address_in_vma(page, vma);
if (address != -EFAULT)
return -ENOSYS;
}
-static struct page *new_vma_page(struct page *page, unsigned long private, int **x)
+static struct page *new_page(struct page *page, unsigned long start, int **x)
{
return NULL;
}
unsigned short mode, unsigned short mode_flags,
nodemask_t *nmask, unsigned long flags)
{
- struct vm_area_struct *vma;
struct mm_struct *mm = current->mm;
struct mempolicy *new;
unsigned long end;
if (err)
goto mpol_out;
- vma = check_range(mm, start, end, nmask,
+ err = check_range(mm, start, end, nmask,
flags | MPOL_MF_INVERT, &pagelist);
-
- err = PTR_ERR(vma);
- if (!IS_ERR(vma)) {
+ if (!err) {
int nr_failed = 0;
err = mbind_range(mm, start, end, new);
if (!list_empty(&pagelist)) {
- nr_failed = migrate_pages(&pagelist, new_vma_page,
- (unsigned long)vma,
- false, true);
+ nr_failed = migrate_pages(&pagelist, new_page,
+ start, false, true);
if (nr_failed)
putback_lru_pages(&pagelist);
}
addr);
if (vpol)
pol = vpol;
- } else if (vma->vm_policy)
+ } else if (vma->vm_policy) {
pol = vma->vm_policy;
+
+ /*
+ * shmem_alloc_page() passes MPOL_F_SHARED policy with
+ * a pseudo vma whose vma->vm_ops=NULL. Take a reference
+ * count on these policies which will be dropped by
+ * mpol_cond_put() later
+ */
+ if (mpol_needs_cond_ref(pol))
+ mpol_get(pol);
+ }
}
if (!pol)
pol = &default_policy;
* task can change it's policy. The system default policy requires no
* such protection.
*/
-unsigned slab_node(struct mempolicy *policy)
+unsigned slab_node(void)
{
+ struct mempolicy *policy;
+
+ if (in_interrupt())
+ return numa_node_id();
+
+ policy = current->mempolicy;
if (!policy || policy->flags & MPOL_F_LOCAL)
return numa_node_id();
alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
unsigned long addr, int node)
{
- struct mempolicy *pol = get_vma_policy(current, vma, addr);
+ struct mempolicy *pol;
struct zonelist *zl;
struct page *page;
+ unsigned int cpuset_mems_cookie;
+
+retry_cpuset:
+ pol = get_vma_policy(current, vma, addr);
+ cpuset_mems_cookie = get_mems_allowed();
- get_mems_allowed();
if (unlikely(pol->mode == MPOL_INTERLEAVE)) {
unsigned nid;
nid = interleave_nid(pol, vma, addr, PAGE_SHIFT + order);
mpol_cond_put(pol);
page = alloc_page_interleave(gfp, order, nid);
- put_mems_allowed();
+ if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ goto retry_cpuset;
+
return page;
}
zl = policy_zonelist(gfp, pol, node);
struct page *page = __alloc_pages_nodemask(gfp, order,
zl, policy_nodemask(gfp, pol));
__mpol_put(pol);
- put_mems_allowed();
+ if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ goto retry_cpuset;
return page;
}
/*
*/
page = __alloc_pages_nodemask(gfp, order, zl,
policy_nodemask(gfp, pol));
- put_mems_allowed();
+ if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ goto retry_cpuset;
return page;
}
{
struct mempolicy *pol = current->mempolicy;
struct page *page;
+ unsigned int cpuset_mems_cookie;
if (!pol || in_interrupt() || (gfp & __GFP_THISNODE))
pol = &default_policy;
- get_mems_allowed();
+retry_cpuset:
+ cpuset_mems_cookie = get_mems_allowed();
+
/*
* No reference counting needed for current->mempolicy
* nor system default_policy
page = __alloc_pages_nodemask(gfp, order,
policy_zonelist(gfp, pol, numa_node_id()),
policy_nodemask(gfp, pol));
- put_mems_allowed();
+
+ if (unlikely(!put_mems_allowed(cpuset_mems_cookie) && !page))
+ goto retry_cpuset;
+
return page;
}
EXPORT_SYMBOL(alloc_pages_current);
} else
*new = *old;
- rcu_read_lock();
if (current_cpuset_is_being_rebound()) {
nodemask_t mems = cpuset_mems_allowed(current);
if (new->flags & MPOL_F_REBINDING)
else
mpol_rebind_policy(new, &mems, MPOL_REBIND_ONCE);
}
- rcu_read_unlock();
atomic_set(&new->refcnt, 1);
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;
-}
-
/* Slow path of a mempolicy comparison */
int __mpol_equal(struct mempolicy *a, struct mempolicy *b)
{
*/
/* lookup first element intersecting start-end */
-/* Caller holds sp->lock */
+/* Caller holds sp->mutex */
static struct sp_node *
sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
{
if (!sp->root.rb_node)
return NULL;
- spin_lock(&sp->lock);
+ mutex_lock(&sp->mutex);
sn = sp_lookup(sp, idx, idx+1);
if (sn) {
mpol_get(sn->policy);
pol = sn->policy;
}
- spin_unlock(&sp->lock);
+ mutex_unlock(&sp->mutex);
return pol;
}
+static void sp_free(struct sp_node *n)
+{
+ mpol_put(n->policy);
+ kmem_cache_free(sn_cache, n);
+}
+
static void sp_delete(struct shared_policy *sp, struct sp_node *n)
{
pr_debug("deleting %lx-l%lx\n", n->start, n->end);
rb_erase(&n->nd, &sp->root);
- mpol_put(n->policy);
- kmem_cache_free(sn_cache, n);
+ sp_free(n);
}
static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
struct mempolicy *pol)
{
- struct sp_node *n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
+ struct sp_node *n;
+ struct mempolicy *newpol;
+ n = kmem_cache_alloc(sn_cache, GFP_KERNEL);
if (!n)
return NULL;
+
+ newpol = mpol_dup(pol);
+ if (IS_ERR(newpol)) {
+ kmem_cache_free(sn_cache, n);
+ return NULL;
+ }
+ newpol->flags |= MPOL_F_SHARED;
+
n->start = start;
n->end = end;
- mpol_get(pol);
- pol->flags |= MPOL_F_SHARED; /* for unref */
- n->policy = pol;
+ n->policy = newpol;
+
return n;
}
static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
unsigned long end, struct sp_node *new)
{
- struct sp_node *n, *new2 = NULL;
+ struct sp_node *n;
+ int ret = 0;
-restart:
- spin_lock(&sp->lock);
+ mutex_lock(&sp->mutex);
n = sp_lookup(sp, start, end);
/* Take care of old policies in the same range. */
while (n && n->start < end) {
} else {
/* Old policy spanning whole new range. */
if (n->end > end) {
+ struct sp_node *new2;
+ new2 = sp_alloc(end, n->end, n->policy);
if (!new2) {
- spin_unlock(&sp->lock);
- new2 = sp_alloc(end, n->end, n->policy);
- if (!new2)
- return -ENOMEM;
- goto restart;
+ ret = -ENOMEM;
+ goto out;
}
n->end = start;
sp_insert(sp, new2);
- new2 = NULL;
break;
} else
n->end = start;
}
if (new)
sp_insert(sp, new);
- spin_unlock(&sp->lock);
- if (new2) {
- mpol_put(new2->policy);
- kmem_cache_free(sn_cache, new2);
- }
- return 0;
+out:
+ mutex_unlock(&sp->mutex);
+ return ret;
}
/**
int ret;
sp->root = RB_ROOT; /* empty tree == default mempolicy */
- spin_lock_init(&sp->lock);
+ mutex_init(&sp->mutex);
if (mpol) {
struct vm_area_struct pvma;
}
err = shared_policy_replace(info, vma->vm_pgoff, vma->vm_pgoff+sz, new);
if (err && new)
- kmem_cache_free(sn_cache, new);
+ sp_free(new);
return err;
}
if (!p->root.rb_node)
return;
- spin_lock(&p->lock);
+ mutex_lock(&p->mutex);
next = rb_first(&p->root);
while (next) {
n = rb_entry(next, struct sp_node, nd);
next = rb_next(&n->nd);
- rb_erase(&n->nd, &p->root);
- mpol_put(n->policy);
- kmem_cache_free(sn_cache, n);
+ sp_delete(p, n);
}
- spin_unlock(&p->lock);
+ mutex_unlock(&p->mutex);
}
/* assumes fs == KERNEL_DS */
*/
/*
- * "local" is pseudo-policy: MPOL_PREFERRED with MPOL_F_LOCAL flag
- * Used only for mpol_parse_str() and mpol_to_str()
+ * "local" is implemented internally by MPOL_PREFERRED with MPOL_F_LOCAL flag.
*/
#define MPOL_LOCAL MPOL_MAX
static const char * const policy_modes[] =
#ifdef CONFIG_TMPFS
/**
- * mpol_parse_str - parse string to mempolicy
+ * mpol_parse_str - parse string to mempolicy, for tmpfs mpol mount option.
* @str: string containing mempolicy to parse
* @mpol: pointer to struct mempolicy pointer, returned on success.
- * @no_context: flag whether to "contextualize" the mempolicy
+ * @unused: redundant argument, to be removed later.
*
* 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)
+int mpol_parse_str(char *str, struct mempolicy **mpol, int unused)
{
struct mempolicy *new = NULL;
unsigned short mode;
- unsigned short uninitialized_var(mode_flags);
+ unsigned short mode_flags;
nodemask_t nodes;
char *nodelist = strchr(str, ':');
char *flags = strchr(str, '=');
if (IS_ERR(new))
goto out;
- if (no_context) {
- /* save for contextualization */
- new->w.user_nodemask = nodes;
- } else {
- int ret;
- NODEMASK_SCRATCH(scratch);
- if (scratch) {
- task_lock(current);
- ret = mpol_set_nodemask(new, &nodes, scratch);
- task_unlock(current);
- } else
- ret = -ENOMEM;
- NODEMASK_SCRATCH_FREE(scratch);
- if (ret) {
- mpol_put(new);
- goto out;
- }
- }
+ /*
+ * Save nodes for mpol_to_str() to show the tmpfs mount options
+ * for /proc/mounts, /proc/pid/mounts and /proc/pid/mountinfo.
+ */
+ if (mode != MPOL_PREFERRED)
+ new->v.nodes = nodes;
+ else if (nodelist)
+ new->v.preferred_node = first_node(nodes);
+ else
+ new->flags |= MPOL_F_LOCAL;
+
+ /*
+ * Save nodes for contextualization: this will be used to "clone"
+ * the mempolicy in a specific context [cpuset] at a later time.
+ */
+ new->w.user_nodemask = nodes;
+
err = 0;
out:
* @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
+ * @unused: redundant argument, to be removed later.
*
* Convert a mempolicy into a string.
* Returns the number of characters in buffer (if positive)
* or an error (negative)
*/
-int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
+int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int unused)
{
char *p = buffer;
int l;
case MPOL_PREFERRED:
nodes_clear(nodes);
if (flags & MPOL_F_LOCAL)
- mode = MPOL_LOCAL; /* pseudo-policy */
+ mode = MPOL_LOCAL;
else
node_set(pol->v.preferred_node, nodes);
break;
case MPOL_BIND:
/* Fall through */
case MPOL_INTERLEAVE:
- if (no_context)
- nodes = pol->w.user_nodemask;
- else
- nodes = pol->v.nodes;
+ nodes = pol->v.nodes;
break;
default:
- BUG();
+ return -EINVAL;
}
l = strlen(policy_modes[mode]);