[PATCH 18/18] mm/mempolicy: Advertise new MPOL_PREFERRED_MANY

[Ben Widawsky <ben.widawsky@intel.com>]

See comments in code, and previous commit messages for details of
implementation and usage.

Fix whitespace while here.

Cc: Andrew Morton <akpm@linux-foundation.org>
Cc: Dave Hansen <dave.hansen@linux.intel.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Jonathan Corbet <corbet@lwn.net>
Cc: Michal Hocko <mhocko@kernel.org>
Cc: Vlastimil Babka <vbabka@suse.cz>
Signed-off-by: Ben Widawsky <ben.widawsky@intel.com>
---
 .../admin-guide/mm/numa_memory_policy.rst        | 16 ++++++++++++----
 include/uapi/linux/mempolicy.h                   |  6 +++---
 mm/mempolicy.c                                   | 14 ++++++--------
 mm/page_alloc.c                                  |  3 ---
 4 files changed, 21 insertions(+), 18 deletions(-)

diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
index 1ad020c459b8..b69963a37fc8 100644
--- a/Documentation/admin-guide/mm/numa_memory_policy.rst
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -245,6 +245,14 @@ MPOL_INTERLEAVED
 	address range or file.  During system boot up, the temporary
 	interleaved system default policy works in this mode.
 
+MPOL_PREFERRED_MANY
+        This mode specifies that the allocation should be attempted from the
+        nodemask specified in the policy. If that allocation fails, the kernel
+        will search other nodes, in order of increasing distance from the first
+        set bit in the nodemask based on information provided by the platform
+        firmware. It is similar to MPOL_PREFERRED with the main exception that
+        is is an error to have an empty nodemask.
+
 NUMA memory policy supports the following optional mode flags:
 
 MPOL_F_STATIC_NODES
@@ -253,10 +261,10 @@ MPOL_F_STATIC_NODES
 	nodes changes after the memory policy has been defined.
 
 	Without this flag, any time a mempolicy is rebound because of a
-	change in the set of allowed nodes, the node (Preferred) or
-	nodemask (Bind, Interleave) is remapped to the new set of
-	allowed nodes.  This may result in nodes being used that were
-	previously undesired.
+        change in the set of allowed nodes, the preferred nodemask (Preferred
+        Many), preferred node (Preferred) or nodemask (Bind, Interleave) is
+        remapped to the new set of allowed nodes.  This may result in nodes
+        being used that were previously undesired.
 
 	With this flag, if the user-specified nodes overlap with the
 	nodes allowed by the task's cpuset, then the memory policy is
diff --git a/include/uapi/linux/mempolicy.h b/include/uapi/linux/mempolicy.h
index 3354774af61e..ad3eee651d4e 100644
--- a/include/uapi/linux/mempolicy.h
+++ b/include/uapi/linux/mempolicy.h
@@ -16,13 +16,13 @@
  */
 
 /* Policies */
-enum {
-	MPOL_DEFAULT,
+enum { MPOL_DEFAULT,
 	MPOL_PREFERRED,
 	MPOL_BIND,
 	MPOL_INTERLEAVE,
 	MPOL_LOCAL,
-	MPOL_MAX,	/* always last member of enum */
+	MPOL_PREFERRED_MANY,
+	MPOL_MAX, /* always last member of enum */
 };
 
 /* Flags for set_mempolicy */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index fb49bea41ab8..07e916f8f6b7 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -108,8 +108,6 @@
 
 #include "internal.h"
 
-#define MPOL_PREFERRED_MANY MPOL_MAX
-
 /* Internal flags */
 #define MPOL_MF_DISCONTIG_OK (MPOL_MF_INTERNAL << 0)	/* Skip checks for continuous vmas */
 #define MPOL_MF_INVERT (MPOL_MF_INTERNAL << 1)		/* Invert check for nodemask */
@@ -180,7 +178,7 @@ struct mempolicy *get_task_policy(struct task_struct *p)
 static const struct mempolicy_operations {
 	int (*create)(struct mempolicy *pol, const nodemask_t *nodes);
 	void (*rebind)(struct mempolicy *pol, const nodemask_t *nodes);
-} mpol_ops[MPOL_MAX + 1];
+} mpol_ops[MPOL_MAX];
 
 static inline int mpol_store_user_nodemask(const struct mempolicy *pol)
 {
@@ -385,8 +383,8 @@ static void mpol_rebind_preferred_common(struct mempolicy *pol,
 }
 
 /* MPOL_PREFERRED_MANY allows multiple nodes to be set in 'nodes' */
-static void __maybe_unused mpol_rebind_preferred_many(struct mempolicy *pol,
-						      const nodemask_t *nodes)
+static void mpol_rebind_preferred_many(struct mempolicy *pol,
+				       const nodemask_t *nodes)
 {
 	mpol_rebind_preferred_common(pol, nodes, nodes);
 }
@@ -448,7 +446,7 @@ void mpol_rebind_mm(struct mm_struct *mm, nodemask_t *new)
 	mmap_write_unlock(mm);
 }
 
-static const struct mempolicy_operations mpol_ops[MPOL_MAX + 1] = {
+static const struct mempolicy_operations mpol_ops[MPOL_MAX] = {
 	[MPOL_DEFAULT] = {
 		.rebind = mpol_rebind_default,
 	},
@@ -466,8 +464,8 @@ static const struct mempolicy_operations mpol_ops[MPOL_MAX + 1] = {
 	},
 	/* MPOL_LOCAL is converted to MPOL_PREFERRED on policy creation */
 	[MPOL_PREFERRED_MANY] = {
-		.create = NULL,
-		.rebind = NULL,
+		.create = mpol_new_preferred_many,
+		.rebind = mpol_rebind_preferred_many,
 	},
 };
 
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 0f90419fe0d8..b89c9c2637bf 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -4867,9 +4867,6 @@ struct zonelist *preferred_zonelist(gfp_t gfp_mask, const nodemask_t *prefmask,
 	nodemask_t pref;
 	int nid, local_node = numa_mem_id();
 
-	/* Multi nodes not supported yet */
-	VM_BUG_ON(prefmask && nodes_weight(*prefmask) != 1);
-
 #define _isset(mask, node)                                                     \
 	(!(mask) || nodes_empty(*(mask)) ? 1 : node_isset(node, *(mask)))
 	/*
-- 
2.27.0