mm: fix null-ptr-deref in kswapd_is_running()

kswapd_run/stop() will set pgdat->kswapd to NULL, which could race with
kswapd_is_running() in kcompactd(),

kswapd_run/stop()                       kcompactd()
                                          kswapd_is_running()
  pgdat->kswapd // error or nomal ptr
                                          verify pgdat->kswapd
                                            // load non-NULL
pgdat->kswapd
  pgdat->kswapd = NULL
                                          task_is_running(pgdat->kswapd)
                                            // Null pointer derefence

KASAN reports the null-ptr-deref shown below,

  vmscan: Failed to start kswapd on node 0
  ...
  BUG: KASAN: null-ptr-deref in kcompactd+0x440/0x504
  Read of size 8 at addr 0000000000000024 by task kcompactd0/37

  CPU: 0 PID: 37 Comm: kcompactd0 Kdump: loaded Tainted: G           OE     5.10.60 #1
  Hardware name: QEMU KVM Virtual Machine, BIOS 0.0.0 02/06/2015
  Call trace:
   dump_backtrace+0x0/0x394
   show_stack+0x34/0x4c
   dump_stack+0x158/0x1e4
   __kasan_report+0x138/0x140
   kasan_report+0x44/0xdc
   __asan_load8+0x94/0xd0
   kcompactd+0x440/0x504
   kthread+0x1a4/0x1f0
   ret_from_fork+0x10/0x18

At present kswapd/kcompactd_run() and kswapd/kcompactd_stop() are protected
by mem_hotplug_begin/done(), but without kcompactd(). There is no need to
involve memory hotplug lock in kcompactd(), so let's add a new mutex to
protect pgdat->kswapd accesses.

Also, because the kcompactd task will check the state of kswapd task, it's
better to call kcompactd_stop() before kswapd_stop() to reduce lock
conflicts.

[akpm@linux-foundation.org: add comments]
Link: https://lkml.kernel.org/r/20220827111959.186838-1-wangkefeng.wang@huawei.com
Signed-off-by: Kefeng Wang <wangkefeng.wang@huawei.com>
Cc: David Hildenbrand <david@redhat.com>
Cc: Muchun Song <muchun.song@linux.dev>
Signed-off-by: Andrew Morton <akpm@linux-foundation.org>

6 files changed, 55 insertions, 15 deletions

diff --git a/include/linux/memory_hotplug.h b/include/linux/memory_hotplug.h
index 54675791bc50..51052969dbfe 100644
--- a/include/linux/memory_hotplug.h
+++ b/include/linux/memory_hotplug.h
@@ -215,6 +215,22 @@ void put_online_mems(void);
 void mem_hotplug_begin(void);
 void mem_hotplug_done(void);
 
+/* See kswapd_is_running() */
+static inline void pgdat_kswapd_lock(pg_data_t *pgdat)
+{
+	mutex_lock(&pgdat->kswapd_lock);
+}
+
+static inline void pgdat_kswapd_unlock(pg_data_t *pgdat)
+{
+	mutex_unlock(&pgdat->kswapd_lock);
+}
+
+static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat)
+{
+	mutex_init(&pgdat->kswapd_lock);
+}
+
 #else /* ! CONFIG_MEMORY_HOTPLUG */
 #define pfn_to_online_page(pfn)			\
 ({						\
@@ -251,6 +267,10 @@ static inline bool movable_node_is_enabled(void)
 {
 	return false;
 }
+
+static inline void pgdat_kswapd_lock(pg_data_t *pgdat) {}
+static inline void pgdat_kswapd_unlock(pg_data_t *pgdat) {}
+static inline void pgdat_kswapd_lock_init(pg_data_t *pgdat) {}
 #endif /* ! CONFIG_MEMORY_HOTPLUG */
 
 /*
diff --git a/include/linux/mmzone.h b/include/linux/mmzone.h
index fd61347b4b1f..18cf0fc5ce67 100644
--- a/include/linux/mmzone.h
+++ b/include/linux/mmzone.h
@@ -956,8 +956,10 @@ typedef struct pglist_data {
 	atomic_t nr_writeback_throttled;/* nr of writeback-throttled tasks */
 	unsigned long nr_reclaim_start;	/* nr pages written while throttled
 					 * when throttling started. */
-	struct task_struct *kswapd;	/* Protected by
-					   mem_hotplug_begin/done() */
+#ifdef CONFIG_MEMORY_HOTPLUG
+	struct mutex kswapd_lock;
+#endif
+	struct task_struct *kswapd;	/* Protected by kswapd_lock */
 	int kswapd_order;
 	enum zone_type kswapd_highest_zoneidx;
 
diff --git a/mm/compaction.c b/mm/compaction.c
index 640fa76228dd..262c4676b32c 100644
--- a/mm/compaction.c
+++ b/mm/compaction.c
@@ -1981,9 +1981,21 @@ static inline bool is_via_compact_memory(int order)
 	return order == -1;
 }
 
+/*
+ * Determine whether kswapd is (or recently was!) running on this node.
+ *
+ * pgdat_kswapd_lock() pins pgdat->kswapd, so a concurrent kswapd_stop() can't
+ * zero it.
+ */
 static bool kswapd_is_running(pg_data_t *pgdat)
 {
-	return pgdat->kswapd && task_is_running(pgdat->kswapd);
+	bool running;
+
+	pgdat_kswapd_lock(pgdat);
+	running = pgdat->kswapd && task_is_running(pgdat->kswapd);
+	pgdat_kswapd_unlock(pgdat);
+
+	return running;
 }
 
 /*
diff --git a/mm/memory_hotplug.c b/mm/memory_hotplug.c
index dc727aee4ad3..9ae1f98548b1 100644
--- a/mm/memory_hotplug.c
+++ b/mm/memory_hotplug.c
@@ -1940,8 +1940,8 @@ int __ref offline_pages(unsigned long start_pfn, unsigned long nr_pages,
 
 	node_states_clear_node(node, &arg);
 	if (arg.status_change_nid >= 0) {
-		kswapd_stop(node);
 		kcompactd_stop(node);
+		kswapd_stop(node);
 	}
 
 	writeback_set_ratelimit();
diff --git a/mm/page_alloc.c b/mm/page_alloc.c
index 1d4278115d71..09386b81e68e 100644
--- a/mm/page_alloc.c
+++ b/mm/page_alloc.c
@@ -7616,6 +7616,7 @@ static void __meminit pgdat_init_internals(struct pglist_data *pgdat)
 	int i;
 
 	pgdat_resize_init(pgdat);
+	pgdat_kswapd_lock_init(pgdat);
 
 	pgdat_init_split_queue(pgdat);
 	pgdat_init_kcompactd(pgdat);
diff --git a/mm/vmscan.c b/mm/vmscan.c
index bb993b21953d..02e720c83901 100644
--- a/mm/vmscan.c
+++ b/mm/vmscan.c
@@ -4643,16 +4643,17 @@ void kswapd_run(int nid)
 {
 	pg_data_t *pgdat = NODE_DATA(nid);
 
-	if (pgdat->kswapd)
-		return;
-
-	pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
-	if (IS_ERR(pgdat->kswapd)) {
-		/* failure at boot is fatal */
-		BUG_ON(system_state < SYSTEM_RUNNING);
-		pr_err("Failed to start kswapd on node %d\n", nid);
-		pgdat->kswapd = NULL;
+	pgdat_kswapd_lock(pgdat);
+	if (!pgdat->kswapd) {
+		pgdat->kswapd = kthread_run(kswapd, pgdat, "kswapd%d", nid);
+		if (IS_ERR(pgdat->kswapd)) {
+			/* failure at boot is fatal */
+			BUG_ON(system_state < SYSTEM_RUNNING);
+			pr_err("Failed to start kswapd on node %d\n", nid);
+			pgdat->kswapd = NULL;
+		}
 	}
+	pgdat_kswapd_unlock(pgdat);
 }
 
 /*
@@ -4661,12 +4662,16 @@ void kswapd_run(int nid)
  */
 void kswapd_stop(int nid)
 {
-	struct task_struct *kswapd = NODE_DATA(nid)->kswapd;
+	pg_data_t *pgdat = NODE_DATA(nid);
+	struct task_struct *kswapd;
 
+	pgdat_kswapd_lock(pgdat);
+	kswapd = pgdat->kswapd;
 	if (kswapd) {
 		kthread_stop(kswapd);
-		NODE_DATA(nid)->kswapd = NULL;
+		pgdat->kswapd = NULL;
 	}
+	pgdat_kswapd_unlock(pgdat);
 }
 
 static int __init kswapd_init(void)