3 files changed, 95 insertions, 1 deletions

diff --git a/Documentation/admin-guide/mm/numa_memory_policy.rst b/Documentation/admin-guide/mm/numa_memory_policy.rst
index 64fd0ba0d0570a..5a6afecbb0d070 100644
--- a/Documentation/admin-guide/mm/numa_memory_policy.rst
+++ b/Documentation/admin-guide/mm/numa_memory_policy.rst
@@ -408,7 +408,7 @@ follows:
 Memory Policy APIs
 ==================
 
-Linux supports 3 system calls for controlling memory policy.  These APIS
+Linux supports 4 system calls for controlling memory policy.  These APIS
 always affect only the calling task, the calling task's address space, or
 some shared object mapped into the calling task's address space.
 
@@ -460,6 +460,20 @@ requested via the 'flags' argument.
 
 See the mbind(2) man page for more details.
 
+Set home node for a Range of Task's Address Spacec::
+
+	long sys_set_mempolicy_home_node(unsigned long start, unsigned long len,
+					 unsigned long home_node,
+					 unsigned long flags);
+
+sys_set_mempolicy_home_node set the home node for a VMA policy present in the
+task's address range. The system call updates the home node only for the existing
+mempolicy range. Other address ranges are ignored. A home node is the NUMA node
+closest to which page allocation will come from. Specifying the home node override
+the default allocation policy to allocate memory close to the local node for an
+executing CPU.
+
+
 Memory Policy Command Line Interface
 ====================================
 
diff --git a/include/linux/mempolicy.h b/include/linux/mempolicy.h
index 3c7595e81150b7..668389b4b53d7a 100644
--- a/include/linux/mempolicy.h
+++ b/include/linux/mempolicy.h
@@ -46,6 +46,7 @@ struct mempolicy {
 	unsigned short mode; 	/* See MPOL_* above */
 	unsigned short flags;	/* See set_mempolicy() MPOL_F_* above */
 	nodemask_t nodes;	/* interleave/bind/perfer */
+	int home_node;		/* Home node to use for MPOL_BIND and MPOL_PREFERRED_MANY */
 
 	union {
 		nodemask_t cpuset_mems_allowed;	/* relative to these nodes */
diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index de70f119984a22..fc6cae7926f3ed 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -296,6 +296,7 @@ static struct mempolicy *mpol_new(unsigned short mode, unsigned short flags,
 	atomic_set(&policy->refcnt, 1);
 	policy->mode = mode;
 	policy->flags = flags;
+	policy->home_node = NUMA_NO_NODE;
 
 	return policy;
 }
@@ -1478,6 +1479,77 @@ static long kernel_mbind(unsigned long start, unsigned long len,
 	return do_mbind(start, len, lmode, mode_flags, &nodes, flags);
 }
 
+SYSCALL_DEFINE4(set_mempolicy_home_node, unsigned long, start, unsigned long, len,
+		unsigned long, home_node, unsigned long, flags)
+{
+	struct mm_struct *mm = current->mm;
+	struct vm_area_struct *vma;
+	struct mempolicy *new;
+	unsigned long vmstart;
+	unsigned long vmend;
+	unsigned long end;
+	int err = -ENOENT;
+
+	start = untagged_addr(start);
+	if (start & ~PAGE_MASK)
+		return -EINVAL;
+	/*
+	 * flags is used for future extension if any.
+	 */
+	if (flags != 0)
+		return -EINVAL;
+
+	/*
+	 * Check home_node is online to avoid accessing uninitialized
+	 * NODE_DATA.
+	 */
+	if (home_node >= MAX_NUMNODES || !node_online(home_node))
+		return -EINVAL;
+
+	len = (len + PAGE_SIZE - 1) & PAGE_MASK;
+	end = start + len;
+
+	if (end < start)
+		return -EINVAL;
+	if (end == start)
+		return 0;
+	mmap_write_lock(mm);
+	vma = find_vma(mm, start);
+	for (; vma && vma->vm_start < end;  vma = vma->vm_next) {
+
+		vmstart = max(start, vma->vm_start);
+		vmend   = min(end, vma->vm_end);
+		new = mpol_dup(vma_policy(vma));
+		if (IS_ERR(new)) {
+			err = PTR_ERR(new);
+			break;
+		}
+		/*
+		 * Only update home node if there is an existing vma policy
+		 */
+		if (!new)
+			continue;
+
+		/*
+		 * If any vma in the range got policy other than MPOL_BIND
+		 * or MPOL_PREFERRED_MANY we return error. We don't reset
+		 * the home node for vmas we already updated before.
+		 */
+		if (new->mode != MPOL_BIND && new->mode != MPOL_PREFERRED_MANY) {
+			err = -EOPNOTSUPP;
+			break;
+		}
+
+		new->home_node = home_node;
+		err = mbind_range(mm, vmstart, vmend, new);
+		mpol_put(new);
+		if (err)
+			break;
+	}
+	mmap_write_unlock(mm);
+	return err;
+}
+
 SYSCALL_DEFINE6(mbind, unsigned long, start, unsigned long, len,
 		unsigned long, mode, const unsigned long __user *, nmask,
 		unsigned long, maxnode, unsigned int, flags)
@@ -1802,6 +1874,11 @@ static int policy_node(gfp_t gfp, struct mempolicy *policy, int nd)
 		WARN_ON_ONCE(policy->mode == MPOL_BIND && (gfp & __GFP_THISNODE));
 	}
 
+	if ((policy->mode == MPOL_BIND ||
+	     policy->mode == MPOL_PREFERRED_MANY) &&
+	    policy->home_node != NUMA_NO_NODE)
+		return policy->home_node;
+
 	return nd;
 }
 
@@ -2344,6 +2421,8 @@ bool __mpol_equal(struct mempolicy *a, struct mempolicy *b)
 		return false;
 	if (a->flags != b->flags)
 		return false;
+	if (a->home_node != b->home_node)
+		return false;
 	if (mpol_store_user_nodemask(a))
 		if (!nodes_equal(a->w.user_nodemask, b->w.user_nodemask))
 			return false;