[PATCH] cpusets: automatic numa mempolicy rebinding

This patch automatically updates a tasks NUMA mempolicy when its cpuset
memory placement changes.  It does so within the context of the task,
without any need to support low level external mempolicy manipulation.

If a system is not using cpusets, or if running on a system with just the
root (all-encompassing) cpuset, then this remap is a no-op.  Only when a
task is moved between cpusets, or a cpusets memory placement is changed
does the following apply.  Otherwise, the main routine below,
rebind_policy() is not even called.

When mixing cpusets, scheduler affinity, and NUMA mempolicies, the
essential role of cpusets is to place jobs (several related tasks) on a set
of CPUs and Memory Nodes, the essential role of sched_setaffinity is to
manage a jobs processor placement within its allowed cpuset, and the
essential role of NUMA mempolicy (mbind, set_mempolicy) is to manage a jobs
memory placement within its allowed cpuset.

However, CPU affinity and NUMA memory placement are managed within the
kernel using absolute system wide numbering, not cpuset relative numbering.

This is ok until a job is migrated to a different cpuset, or what's the
same, a jobs cpuset is moved to different CPUs and Memory Nodes.

Then the CPU affinity and NUMA memory placement of the tasks in the job
need to be updated, to preserve their cpuset-relative position.  This can
be done for CPU affinity using sched_setaffinity() from user code, as one
task can modify anothers CPU affinity.  This cannot be done from an
external task for NUMA memory placement, as that can only be modified in
the context of the task using it.

However, it easy enough to remap a tasks NUMA mempolicy automatically when
a task is migrated, using the existing cpuset mechanism to trigger a
refresh of a tasks memory placement after its cpuset has changed.  All that
is needed is the old and new nodemask, and notice to the task that it needs
to rebind its mempolicy.  The tasks mems_allowed has the old mask, the
tasks cpuset has the new mask, and the existing
cpuset_update_current_mems_allowed() mechanism provides the notice.  The
bitmap/cpumask/nodemask remap operators provide the cpuset relative
calculations.

This patch leaves open a couple of issues:

 1) Updating vma and shmfs/tmpfs/hugetlbfs memory policies:

    These mempolicies may reference nodes outside of those allowed to
    the current task by its cpuset.  Tasks are migrated as part of jobs,
    which reside on what might be several cpusets in a subtree.  When such
    a job is migrated, all NUMA memory policy references to nodes within
    that cpuset subtree should be translated, and references to any nodes
    outside that subtree should be left untouched.  A future patch will
    provide the cpuset mechanism needed to mark such subtrees.  With that
    patch, we will be able to correctly migrate these other memory policies
    across a job migration.

 2) Updating cpuset, affinity and memory policies in user space:

    This is harder.  Any placement state stored in user space using
    system-wide numbering will be invalidated across a migration.  More
    work will be required to provide user code with a migration-safe means
    to manage its cpuset relative placement, while preserving the current
    API's that pass system wide numbers, not cpuset relative numbers across
    the kernel-user boundary.

Signed-off-by: Paul Jackson <pj@sgi.com>
Signed-off-by: Andrew Morton <akpm@osdl.org>
Signed-off-by: Linus Torvalds <torvalds@osdl.org>

3 files changed, 74 insertions, 0 deletions

diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 7af8cb836e78..8b67cf837ca9 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -154,6 +154,7 @@ struct mempolicy *get_vma_policy(struct task_struct *task,
 
 extern void numa_default_policy(void);
 extern void numa_policy_init(void);
+extern void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new);
 extern struct mempolicy default_policy;
 
 #else
@@ -226,6 +227,11 @@ static inline void numa_default_policy(void)
 {
 }
 
+static inline void numa_policy_rebind(const nodemask_t *old,
+					const nodemask_t *new)
+{
+}
+
 #endif /* CONFIG_NUMA */
 #endif /* __KERNEL__ */
 
diff --git a/kernel/cpuset.c b/kernel/cpuset.c
index 6633f3fb6417..5a737ed9dac7 100644
--- a/kernel/cpuset.c
+++ b/kernel/cpuset.c
@@ -32,6 +32,7 @@
 #include <linux/kernel.h>
 #include <linux/kmod.h>
 #include <linux/list.h>
+#include <linux/mempolicy.h>
 #include <linux/mm.h>
 #include <linux/module.h>
 #include <linux/mount.h>
@@ -600,6 +601,7 @@ static void refresh_mems(void)
 
 	if (current->cpuset_mems_generation != my_cpusets_mem_gen) {
 		struct cpuset *cs;
+		nodemask_t oldmem = current->mems_allowed;
 
 		down(&callback_sem);
 		task_lock(current);
@@ -608,6 +610,8 @@ static void refresh_mems(void)
 		current->cpuset_mems_generation = cs->mems_generation;
 		task_unlock(current);
 		up(&callback_sem);
+		if (!nodes_equal(oldmem, current->mems_allowed))
+			numa_policy_rebind(&oldmem, &current->mems_allowed);
 	}
 }
 
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index 2076b1542b8a..5abc57c2b8bd 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -457,6 +457,7 @@ long do_get_mempolicy(int *policy, nodemask_t *nmask,
 	struct vm_area_struct *vma = NULL;
 	struct mempolicy *pol = current->mempolicy;
 
+	cpuset_update_current_mems_allowed();
 	if (flags & ~(unsigned long)(MPOL_F_NODE|MPOL_F_ADDR))
 		return -EINVAL;
 	if (flags & MPOL_F_ADDR) {
@@ -1206,3 +1207,66 @@ void numa_default_policy(void)
 {
 	do_set_mempolicy(MPOL_DEFAULT, NULL);
 }
+
+/* Migrate a policy to a different set of nodes */
+static void rebind_policy(struct mempolicy *pol, const nodemask_t *old,
+							const nodemask_t *new)
+{
+	nodemask_t tmp;
+
+	if (!pol)
+		return;
+
+	switch (pol->policy) {
+	case MPOL_DEFAULT:
+		break;
+	case MPOL_INTERLEAVE:
+		nodes_remap(tmp, pol->v.nodes, *old, *new);
+		pol->v.nodes = tmp;
+		current->il_next = node_remap(current->il_next, *old, *new);
+		break;
+	case MPOL_PREFERRED:
+		pol->v.preferred_node = node_remap(pol->v.preferred_node,
+								*old, *new);
+		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((*z)->zone_pgdat->node_id, nodes);
+		nodes_remap(tmp, nodes, *old, *new);
+		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 (zonelist) {
+			/* Good - got mem - substitute new zonelist */
+			kfree(pol->v.zonelist);
+			pol->v.zonelist = zonelist;
+		}
+		break;
+	}
+	default:
+		BUG();
+		break;
+	}
+}
+
+/*
+ * Someone moved this task to different nodes.  Fixup mempolicies.
+ *
+ * TODO - fixup current->mm->vma and shmfs/tmpfs/hugetlbfs policies as well,
+ * once we have a cpuset mechanism to mark which cpuset subtree is migrating.
+ */
+void numa_policy_rebind(const nodemask_t *old, const nodemask_t *new)
+{
+	rebind_policy(current->mempolicy, old, new);
+}