1 files changed, 72 insertions, 58 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index d1b315e98627..e2df1c1fb41f 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -2132,7 +2132,7 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
  */
 
 /* lookup first element intersecting start-end */
-/* Caller holds sp->mutex */
+/* Caller holds sp->lock */
 static struct sp_node *
 sp_lookup(struct shared_policy *sp, unsigned long start, unsigned long end)
 {
@@ -2196,13 +2196,13 @@ mpol_shared_policy_lookup(struct shared_policy *sp, unsigned long idx)
 
         if (!sp->root.rb_node)
                 return NULL;
-        mutex_lock(&sp->mutex);
+        spin_lock(&sp->lock);
         sn = sp_lookup(sp, idx, idx+1);
         if (sn) {
                 mpol_get(sn->policy);
                 pol = sn->policy;
         }
-        mutex_unlock(&sp->mutex);
+        spin_unlock(&sp->lock);
         return pol;
 }
 
@@ -2328,6 +2328,14 @@ static void sp_delete(struct shared_policy *sp, struct sp_node *n)
         sp_free(n);
 }
 
+static void sp_node_init(struct sp_node *node, unsigned long start,
+                        unsigned long end, struct mempolicy *pol)
+{
+        node->start = start;
+        node->end = end;
+        node->policy = pol;
+}
+
 static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
                                 struct mempolicy *pol)
 {
@@ -2344,10 +2352,7 @@ static struct sp_node *sp_alloc(unsigned long start, unsigned long end,
                 return NULL;
         }
         newpol->flags |= MPOL_F_SHARED;
-
-        n->start = start;
-        n->end = end;
-        n->policy = newpol;
+        sp_node_init(n, start, end, newpol);
 
         return n;
 }
@@ -2357,9 +2362,12 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
                                  unsigned long end, struct sp_node *new)
 {
         struct sp_node *n;
+        struct sp_node *n_new = NULL;
+        struct mempolicy *mpol_new = NULL;
         int ret = 0;
 
-        mutex_lock(&sp->mutex);
+restart:
+        spin_lock(&sp->lock);
         n = sp_lookup(sp, start, end);
         /* Take care of old policies in the same range. */
         while (n && n->start < end) {
@@ -2372,14 +2380,16 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
                 } 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) {
-                                        ret = -ENOMEM;
-                                        goto out;
-                                }
+                                if (!n_new)
+                                        goto alloc_new;
+
+                                *mpol_new = *n->policy;
+                                atomic_set(&mpol_new->refcnt, 1);
+                                sp_node_init(n_new, n->end, end, mpol_new);
+                                sp_insert(sp, n_new);
                                 n->end = start;
-                                sp_insert(sp, new2);
+                                n_new = NULL;
+                                mpol_new = NULL;
                                 break;
                         } else
                                 n->end = start;
@@ -2390,9 +2400,27 @@ static int shared_policy_replace(struct shared_policy *sp, unsigned long start,
         }
         if (new)
                 sp_insert(sp, new);
-out:
-        mutex_unlock(&sp->mutex);
+        spin_unlock(&sp->lock);
+        ret = 0;
+
+err_out:
+        if (mpol_new)
+                mpol_put(mpol_new);
+        if (n_new)
+                kmem_cache_free(sn_cache, n_new);
+
         return ret;
+
+alloc_new:
+        spin_unlock(&sp->lock);
+        ret = -ENOMEM;
+        n_new = kmem_cache_alloc(sn_cache, GFP_KERNEL);
+        if (!n_new)
+                goto err_out;
+        mpol_new = kmem_cache_alloc(policy_cache, GFP_KERNEL);
+        if (!mpol_new)
+                goto err_out;
+        goto restart;
 }
 
 /**
@@ -2410,7 +2438,7 @@ void mpol_shared_policy_init(struct shared_policy *sp, struct mempolicy *mpol)
         int ret;
 
         sp->root = RB_ROOT;             /* empty tree == default mempolicy */
-        mutex_init(&sp->mutex);
+        spin_lock_init(&sp->lock);
 
         if (mpol) {
                 struct vm_area_struct pvma;
@@ -2476,14 +2504,14 @@ void mpol_free_shared_policy(struct shared_policy *p)
 
         if (!p->root.rb_node)
                 return;
-        mutex_lock(&p->mutex);
+        spin_lock(&p->lock);
         next = rb_first(&p->root);
         while (next) {
                 n = rb_entry(next, struct sp_node, nd);
                 next = rb_next(&n->nd);
                 sp_delete(p, n);
         }
-        mutex_unlock(&p->mutex);
+        spin_unlock(&p->lock);
 }
 
 #ifdef CONFIG_NUMA_BALANCING
@@ -2595,8 +2623,7 @@ void numa_default_policy(void)
  */
 
 /*
- * "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.
  */
 static const char * const policy_modes[] =
 {
@@ -2610,28 +2637,20 @@ 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
  *
  * 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)
 {
         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, '=');
@@ -2719,24 +2738,23 @@ int mpol_parse_str(char *str, struct mempolicy **mpol, int no_context)
         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:
@@ -2756,13 +2774,12 @@ 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
  *
  * 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)
 {
         char *p = buffer;
         int l;
@@ -2788,7 +2805,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
         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;
@@ -2796,10 +2813,7 @@ int mpol_to_str(char *buffer, int maxlen, struct mempolicy *pol, int no_context)
         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: