3 files changed, 137 insertions, 0 deletions

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 74357cb9bc7c..c7ac77e873b3 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -150,6 +150,16 @@ extern void numa_policy_init(void);
 extern void mpol_rebind_policy(struct mempolicy *pol, const nodemask_t *new);
 extern void mpol_rebind_task(struct task_struct *tsk,
                                         const nodemask_t *new);
+extern void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new);
+#define set_cpuset_being_rebound(x) (cpuset_being_rebound = (x))
+
+#ifdef CONFIG_CPUSET
+#define current_cpuset_is_being_rebound() \
+                                (cpuset_being_rebound == current->cpuset)
+#else
+#define current_cpuset_is_being_rebound() 0
+#endif
+
 extern struct mempolicy default_policy;
 extern struct zonelist *huge_zonelist(struct vm_area_struct *vma,
                 unsigned long addr);
@@ -165,6 +175,8 @@ static inline void check_highest_zone(int k)
 int do_migrate_pages(struct mm_struct *mm,
         const nodemask_t *from_nodes, const nodemask_t *to_nodes, int flags);
 
+extern void *cpuset_being_rebound;      /* Trigger mpol_copy vma rebind */
+
 #else
 
 struct mempolicy {};
@@ -234,6 +246,12 @@ static inline void mpol_rebind_task(struct task_struct *tsk,
 {
 }
 
+static inline void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
+{
+}
+
+#define set_cpuset_being_rebound(x) do {} while (0)
+
 static inline struct zonelist *huge_zonelist(struct vm_area_struct *vma,
                 unsigned long addr)
 {
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6004719f26ee..19f87565be17 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -812,12 +812,24 @@ static int update_cpumask(struct cpuset *cs, char *buf)
 }
 
 /*
+ * Handle user request to change the 'mems' memory placement
+ * of a cpuset.  Needs to validate the request, update the
+ * cpusets mems_allowed and mems_generation, and for each
+ * task in the cpuset, rebind any vma mempolicies.
+ *
  * Call with manage_sem held.  May take callback_sem during call.
+ * Will take tasklist_lock, scan tasklist for tasks in cpuset cs,
+ * lock each such tasks mm->mmap_sem, scan its vma's and rebind
+ * their mempolicies to the cpusets new mems_allowed.
  */
 
 static int update_nodemask(struct cpuset *cs, char *buf)
 {
         struct cpuset trialcs;
+        struct task_struct *g, *p;
+        struct mm_struct **mmarray;
+        int i, n, ntasks;
+        int fudge;
         int retval;
 
         trialcs = *cs;
@@ -839,6 +851,76 @@ static int update_nodemask(struct cpuset *cs, char *buf)
         cs->mems_generation = atomic_read(&cpuset_mems_generation);
         up(&callback_sem);
 
+        set_cpuset_being_rebound(cs);           /* causes mpol_copy() rebind */
+
+        fudge = 10;                             /* spare mmarray[] slots */
+        fudge += cpus_weight(cs->cpus_allowed); /* imagine one fork-bomb/cpu */
+        retval = -ENOMEM;
+
+        /*
+         * Allocate mmarray[] to hold mm reference for each task
+         * in cpuset cs.  Can't kmalloc GFP_KERNEL while holding
+         * tasklist_lock.  We could use GFP_ATOMIC, but with a
+         * few more lines of code, we can retry until we get a big
+         * enough mmarray[] w/o using GFP_ATOMIC.
+         */
+        while (1) {
+                ntasks = atomic_read(&cs->count);       /* guess */
+                ntasks += fudge;
+                mmarray = kmalloc(ntasks * sizeof(*mmarray), GFP_KERNEL);
+                if (!mmarray)
+                        goto done;
+                write_lock_irq(&tasklist_lock);         /* block fork */
+                if (atomic_read(&cs->count) <= ntasks)
+                        break;                          /* got enough */
+                write_unlock_irq(&tasklist_lock);       /* try again */
+                kfree(mmarray);
+        }
+
+        n = 0;
+
+        /* Load up mmarray[] with mm reference for each task in cpuset. */
+        do_each_thread(g, p) {
+                struct mm_struct *mm;
+
+                if (n >= ntasks) {
+                        printk(KERN_WARNING
+                                "Cpuset mempolicy rebind incomplete.\n");
+                        continue;
+                }
+                if (p->cpuset != cs)
+                        continue;
+                mm = get_task_mm(p);
+                if (!mm)
+                        continue;
+                mmarray[n++] = mm;
+        } while_each_thread(g, p);
+        write_unlock_irq(&tasklist_lock);
+
+        /*
+         * Now that we've dropped the tasklist spinlock, we can
+         * rebind the vma mempolicies of each mm in mmarray[] to their
+         * new cpuset, and release that mm.  The mpol_rebind_mm()
+         * call takes mmap_sem, which we couldn't take while holding
+         * tasklist_lock.  Forks can happen again now - the mpol_copy()
+         * cpuset_being_rebound check will catch such forks, and rebind
+         * their vma mempolicies too.  Because we still hold the global
+         * cpuset manage_sem, we know that no other rebind effort will
+         * be contending for the global variable cpuset_being_rebound.
+         * It's ok if we rebind the same mm twice; mpol_rebind_mm()
+         * is idempotent.
+         */
+        for (i = 0; i < n; i++) {
+                struct mm_struct *mm = mmarray[i];
+
+                mpol_rebind_mm(mm, &cs->mems_allowed);
+                mmput(mm);
+        }
+
+        /* We're done rebinding vma's to this cpusets new mems_allowed. */
+        kfree(mmarray);
+        set_cpuset_being_rebound(NULL);
+        retval = 0;
 done:
         return retval;
 }
@@ -1011,6 +1093,7 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
         struct cpuset *oldcs;
         cpumask_t cpus;
         nodemask_t from, to;
+        struct mm_struct *mm;
 
         if (sscanf(pidbuf, "%d", &pid) != 1)
                 return -EIO;
@@ -1060,6 +1143,13 @@ static int attach_task(struct cpuset *cs, char *pidbuf, char **ppathbuf)
         to = cs->mems_allowed;
 
         up(&callback_sem);
+
+        mm = get_task_mm(tsk);
+        if (mm) {
+                mpol_rebind_mm(mm, &to);
+                mmput(mm);
+        }
+
         if (is_memory_migrate(cs))
                 do_migrate_pages(tsk->mm, &from, &to, MPOL_MF_MOVE_ALL);
         put_task_struct(tsk);
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index c39bd86f4ea0..1850d0aef4ac 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -1131,6 +1131,15 @@ struct page *alloc_pages_current(gfp_t gfp, unsigned order)
 }
 EXPORT_SYMBOL(alloc_pages_current);
 
+/*
+ * If mpol_copy() 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().
+ */
+void *cpuset_being_rebound;
+
 /* Slow path of a mempolicy copy */
 struct mempolicy *__mpol_copy(struct mempolicy *old)
 {
@@ -1138,6 +1147,10 @@ struct mempolicy *__mpol_copy(struct mempolicy *old)
 
         if (!new)
                 return ERR_PTR(-ENOMEM);
+        if (current_cpuset_is_being_rebound()) {
+                nodemask_t mems = cpuset_mems_allowed(current);
+                mpol_rebind_policy(old, &mems);
+        }
         *new = *old;
         atomic_set(&new->refcnt, 1);
         if (new->policy == MPOL_BIND) {
@@ -1481,6 +1494,22 @@ void mpol_rebind_task(struct task_struct *tsk, const nodemask_t *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);
+}
+
+/*
  * Display pages allocated per node and memory policy via /proc.
  */