1 files changed, 89 insertions, 6 deletions

diff --git a/mm/mempolicy.c b/mm/mempolicy.c
index f6248affaf38..028e8dd82b44 100644
--- a/mm/mempolicy.c
+++ b/mm/mempolicy.c
@@ -134,6 +134,8 @@ static struct mempolicy preferred_node_policy[MAX_NUMNODES];
  * @node: Node id to start the search
  *
  * Lookup the next closest node by distance if @nid is not online.
+ *
+ * Return: this @node if it is online, otherwise the closest node by distance
  */
 int numa_map_to_online_node(int node)
 {
@@ -296,6 +298,7 @@ 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;
 }
@@ -810,7 +813,8 @@ static int mbind_range(struct mm_struct *mm, unsigned long start,
 			((vmstart - vma->vm_start) >> PAGE_SHIFT);
 		prev = vma_merge(mm, prev, vmstart, vmend, vma->vm_flags,
 				 vma->anon_vma, vma->vm_file, pgoff,
-				 new_pol, vma->vm_userfaultfd_ctx);
+				 new_pol, vma->vm_userfaultfd_ctx,
+				 vma_anon_name(vma));
 		if (prev) {
 			vma = prev;
 			next = vma->vm_next;
@@ -1477,6 +1481,77 @@ 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)
@@ -1801,6 +1876,11 @@ 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;
 }
 
@@ -2061,7 +2141,7 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
 	preferred_gfp &= ~(__GFP_DIRECT_RECLAIM | __GFP_NOFAIL);
 	page = __alloc_pages(preferred_gfp, order, nid, &pol->nodes);
 	if (!page)
-		page = __alloc_pages(gfp, order, numa_node_id(), NULL);
+		page = __alloc_pages(gfp, order, nid, NULL);
 
 	return page;
 }
@@ -2072,7 +2152,6 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
  * @order: Order of the GFP allocation.
  * @vma: Pointer to VMA or NULL if not available.
  * @addr: Virtual address of the allocation.  Must be inside @vma.
- * @node: Which node to prefer for allocation (modulo policy).
  * @hugepage: For hugepages try only the preferred node if possible.
  *
  * Allocate a page for a specific address in @vma, using the appropriate
@@ -2083,9 +2162,10 @@ static struct page *alloc_pages_preferred_many(gfp_t gfp, unsigned int order,
  * Return: The page on success or NULL if allocation fails.
  */
 struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
-		unsigned long addr, int node, bool hugepage)
+		unsigned long addr, bool hugepage)
 {
 	struct mempolicy *pol;
+	int node = numa_node_id();
 	struct page *page;
 	int preferred_nid;
 	nodemask_t *nmask;
@@ -2102,6 +2182,7 @@ struct page *alloc_pages_vma(gfp_t gfp, int order, struct vm_area_struct *vma,
 	}
 
 	if (pol->mode == MPOL_PREFERRED_MANY) {
+		node = policy_node(gfp, pol, node);
 		page = alloc_pages_preferred_many(gfp, order, node, pol);
 		mpol_cond_put(pol);
 		goto out;
@@ -2185,7 +2266,7 @@ struct page *alloc_pages(gfp_t gfp, unsigned order)
 		page = alloc_page_interleave(gfp, order, interleave_nodes(pol));
 	else if (pol->mode == MPOL_PREFERRED_MANY)
 		page = alloc_pages_preferred_many(gfp, order,
-				numa_node_id(), pol);
+				  policy_node(gfp, pol, numa_node_id()), pol);
 	else
 		page = __alloc_pages(gfp, order,
 				policy_node(gfp, pol, numa_node_id()),
@@ -2341,6 +2422,8 @@ 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;
@@ -2884,7 +2967,7 @@ static const char * const policy_modes[] =
  * Format of input:
  *	<mode>[=<flags>][:<nodelist>]
  *
- * On success, returns 0, else 1
+ * Return: %0 on success, else %1
  */
 int mpol_parse_str(char *str, struct mempolicy **mpol)
 {