Received-SPF: pass (google.com: best guess record for domain of linux-kernel-owner@vger.kernel.org designates 209.132.180.67 as permitted sender) client-ip=209.132.180.67;
From:   Yang Shi <yang.shi@linux.alibaba.com>
To:     mhocko@suse.com, mgorman@techsingularity.net, riel@surriel.com,
        hannes@cmpxchg.org, akpm@linux-foundation.org,
        dave.hansen@intel.com, keith.busch@intel.com,
        dan.j.williams@intel.com, fengguang.wu@intel.com, fan.du@intel.com,
        ying.huang@intel.com, ziy@nvidia.com
Cc:     yang.shi@linux.alibaba.com, linux-mm@kvack.org,
        linux-kernel@vger.kernel.org
Subject: [v2 PATCH 2/9] mm: page_alloc: make find_next_best_node find return cpuless node
Date:   Thu, 11 Apr 2019 11:56:52 +0800
Message-Id: <1554955019-29472-3-git-send-email-yang.shi@linux.alibaba.com>
In-Reply-To: <1554955019-29472-1-git-send-email-yang.shi@linux.alibaba.com>
References: <1554955019-29472-1-git-send-email-yang.shi@linux.alibaba.com>
Sender: linux-kernel-owner@vger.kernel.org
Precedence: bulk

Need find the cloest cpuless node to demote DRAM pages.  Add
"cpuless" parameter to find_next_best_node() to skip DRAM node on
demand.

Signed-off-by: Yang Shi <yang.shi@linux.alibaba.com>
---
 mm/internal.h   | 11 +++++++++++
 mm/page_alloc.c | 14 ++++++++++----
 2 files changed, 21 insertions(+), 4 deletions(-)

diff --git a/mm/internal.h b/mm/internal.h
index 9eeaf2b..a514808 100644
--- a/mm/internal.h
+++ b/mm/internal.h
@@ -292,6 +292,17 @@ static inline bool is_data_mapping(vm_flags_t flags)
 	return (flags & (VM_WRITE | VM_SHARED | VM_STACK)) == VM_WRITE;
 }
 
+#ifdef CONFIG_NUMA
+extern int find_next_best_node(int node, nodemask_t *used_node_mask,
+			       bool cpuless);
+#else
+static inline int find_next_best_node(int node, nodemask_t *used_node_mask,
+				      bool cpuless)
+{
+	return 0;
+}
+#endif
+
 /* mm/util.c */
 void __vma_link_list(struct mm_struct *mm, struct vm_area_struct *vma,
 		struct vm_area_struct *prev, struct rb_node *rb_parent);
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 7cd88a4..bda17c2 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -5362,6 +5362,7 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
  * find_next_best_node - find the next node that should appear in a given node's fallback list
  * @node: node whose fallback list we're appending
  * @used_node_mask: nodemask_t of already used nodes
+ * @cpuless: find next best cpuless node
  *
  * We use a number of factors to determine which is the next node that should
  * appear on a given node's fallback list.  The node should not have appeared
@@ -5373,7 +5374,8 @@ int numa_zonelist_order_handler(struct ctl_table *table, int write,
  *
  * Return: node id of the found node or %NUMA_NO_NODE if no node is found.
  */
-static int find_next_best_node(int node, nodemask_t *used_node_mask)
+int find_next_best_node(int node, nodemask_t *used_node_mask,
+			bool cpuless)
 {
 	int n, val;
 	int min_val = INT_MAX;
@@ -5381,13 +5383,18 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 	const struct cpumask *tmp = cpumask_of_node(0);
 
 	/* Use the local node if we haven't already */
-	if (!node_isset(node, *used_node_mask)) {
+	if (!node_isset(node, *used_node_mask) &&
+	    !cpuless) {
 		node_set(node, *used_node_mask);
 		return node;
 	}
 
 	for_each_node_state(n, N_MEMORY) {
 
+		/* Find next best cpuless node */
+		if (cpuless && (node_state(n, N_CPU)))
+			continue;
+
 		/* Don't want a node to appear more than once */
 		if (node_isset(n, *used_node_mask))
 			continue;
@@ -5419,7 +5426,6 @@ static int find_next_best_node(int node, nodemask_t *used_node_mask)
 	return best_node;
 }
 
-
 /*
  * Build zonelists ordered by node and zones within node.
  * This results in maximum locality--normal zone overflows into local
@@ -5481,7 +5487,7 @@ static void build_zonelists(pg_data_t *pgdat)
 	nodes_clear(used_mask);
 
 	memset(node_order, 0, sizeof(node_order));
-	while ((node = find_next_best_node(local_node, &used_mask)) >= 0) {
+	while ((node = find_next_best_node(local_node, &used_mask, false)) >= 0) {
 		/*
 		 * We don't want to pressure a particular node.
 		 * So adding penalty to the first node in same
-- 
1.8.3.1