mempolicy: disallow static or relative flags for local preferred mode

MPOL_F_STATIC_NODES and MPOL_F_RELATIVE_NODES don't mean anything for MPOL_PREFERRED policies that were created with an empty nodemask (for purely local allocations). They'll never be invalidated because the allowed mems of a task changes or need to be rebound relative to a cpuset's placement.

Also fixes a bug identified by Lee Schermerhorn that disallowed empty nodemasks to be passed to MPOL_PREFERRED to specify local allocations.

Cc Paul Jackson <[email protected]>

Cc Christoph Lameter <[email protected]>

Cc Lee Schermerhorn <[email protected]>

Cc Andi Kleen <[email protected]>

Cc Randy Dunlap <[email protected]>

Signed-off-by David Rientjes <[email protected]>

---
 Documentation/vm/numa_memory_policy.txt |   16 ++++++++++++++--
 mm/mempolicy.c                          |   24 +++++++++++++++++-------
 2 files changed, 31 insertions(+), 9 deletions(-)

Documentation/vm/numa_memory_policy.txt +14 -2

@@ -210,6 +210,12 @@ Components of Memory Policies
 	    local allocation for a specific range of addresses--i.e. for
 	    VMA policies.
 
+	    It is possible for the user to specify that local allocation is
+	    always preferred by passing an empty nodemask with this mode.
+	    If an empty nodemask is passed, the policy cannot use the
+	    MPOL_F_STATIC_NODES or MPOL_F_RELATIVE_NODES flags described
+	    below.
+
 	MPOL_INTERLEAVED:  This mode specifies that page allocations be
 	interleaved, on a page granularity, across the nodes specified in
 	the policy.  This mode also behaves slightly differently, based on

@@ -259,7 +265,10 @@ Components of Memory Policies
 	    occurs over that node.  If no nodes from the user's nodemask are
 	    now allowed, the Default behavior is used.
 
-	    MPOL_F_STATIC_NODES cannot be used with MPOL_F_RELATIVE_NODES.
+	    MPOL_F_STATIC_NODES cannot be combined with the
+	    MPOL_F_RELATIVE_NODES flag.  It also cannot be used for
+	    MPOL_PREFERRED policies that were created with an empty nodemask
+	    (local allocation).
 
 	MPOL_F_RELATIVE_NODES:  This flag specifies that the nodemask passed
 	by the user will be mapped relative to the set of the task or VMA's

@@ -306,7 +315,10 @@ Components of Memory Policies
 	    set of memory nodes allowed by the task's cpuset, as that may
 	    change over time.
 
-	    MPOL_F_RELATIVE_NODES cannot be used with MPOL_F_STATIC_NODES.
+	    MPOL_F_RELATIVE_NODES cannot be combined with the
+	    MPOL_F_STATIC_NODES flag.  It also cannot be used for
+	    MPOL_PREFERRED policies that were created with an empty nodemask
+	    (local allocation).
 
 MEMORY POLICY APIs
 

mm/mempolicy.c +1 -3

@@ -151,9 +151,7 @@ static int mpol_new_interleave(struct mempolicy *pol, const nodemask_t *nodes)
 
 static int mpol_new_preferred(struct mempolicy *pol, const nodemask_t *nodes)
 {
-	if (nodes_empty(*nodes))
-		return -EINVAL;
-	pol->v.preferred_node = first_node(*nodes);
+	pol->v.preferred_node = !nodes_empty(*nodes) ? first_node(*nodes) : -1;
 	return 0;
 }
 

@@ -176,10 +174,22 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	pr_debug("setting mode %d flags %d nodes[0] %lx\n",

mm/mempolicy.c +11 -0

+	/*
+	 * 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) && ((flags & MPOL_F_STATIC_NODES) ||
+					    (flags & MPOL_F_RELATIVE_NODES)))
+			return ERR_PTR(-EINVAL);
+	} else if (nodes_empty(*nodes))
+		return ERR_PTR(-EINVAL);
 	policy = kmem_cache_alloc(policy_cache, GFP_KERNEL);
 	if (!policy)
 		return ERR_PTR(-ENOMEM);