memcg: introduce per-memcg swapin interface

hulk inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I7CGGT
CVE: NA

--------------------------------

Add a new per-memcg swapin interface to load data into memory in advance
to improve access efficiency.
Usage:
	# echo 0 > memory.force_swapin
Signed-off-by: NLiu Shixin <liushixin2@huawei.com>

Documentation/admin-guide/cgroup-v1/memory.rst

@@ -78,6 +78,7 @@ Brief summary of control files.
  memory.stat			     show various statistics
  memory.use_hierarchy		     set/show hierarchical account enabled
  memory.force_empty		     trigger forced page reclaim
+ memory.force_swapin		     trigger forced swapin anon page
  memory.pressure_level		     set memory pressure notifications
  memory.swappiness		     set/show swappiness parameter of vmscan
 				     (See sysctl's vm.swappiness)

include/linux/mm.h

@@ -2650,6 +2650,7 @@ extern int __do_munmap(struct mm_struct *, unsigned long, size_t,
 		       struct list_head *uf, bool downgrade);
 extern int do_munmap(struct mm_struct *, unsigned long, size_t,
 		     struct list_head *uf);
+extern void force_swapin_vma(struct vm_area_struct *vma);
 extern int do_madvise(struct mm_struct *mm, unsigned long start, size_t len_in, int behavior);
 
 extern unsigned long __do_mmap_mm(struct mm_struct *mm, struct file *file,

mm/madvise.c

@@ -259,6 +259,25 @@ static void force_shm_swapin_readahead(struct vm_area_struct *vma,
 
 	lru_add_drain();	/* Push any new pages onto the LRU now */
 }
+
+void force_swapin_vma(struct vm_area_struct *vma)
+{
+	struct file *file = vma->vm_file;
+
+	if (!can_madv_lru_vma(vma))
+		return;
+
+	if (!file) {
+		walk_page_vma(vma, &swapin_walk_ops, vma);
+		lru_add_drain();
+	} else if (shmem_mapping(file->f_mapping))
+		force_shm_swapin_readahead(vma, vma->vm_start,
+			vma->vm_end, file->f_mapping);
+}
+#else
+void force_swapin_vma(struct vm_area_struct *vma)
+{
+}
 #endif		/* CONFIG_SWAP */
 
 /*

mm/memcontrol.c

@@ -4106,6 +4106,32 @@ static __init int memcg_swap_qos_sysctls_init(void)
 }
 late_initcall(memcg_swap_qos_sysctls_init);
 #endif
+
+static int mem_cgroup_task_swapin(struct task_struct *task, void *arg)
+{
+	struct mm_struct *mm = task->mm;
+	struct vm_area_struct *vma;
+	struct blk_plug plug;
+
+	mmap_read_lock(mm);
+	blk_start_plug(&plug);
+	for (vma = mm->mmap; vma; vma = vma->vm_next)
+		force_swapin_vma(vma);
+	blk_finish_plug(&plug);
+	mmap_read_unlock(mm);
+
+	return 0;
+}
+
+static ssize_t memory_swapin(struct kernfs_open_file *of, char *buf,
+			      size_t nbytes, loff_t off)
+{
+	struct mem_cgroup *memcg = mem_cgroup_from_css(of_css(of));
+
+	mem_cgroup_scan_tasks(memcg, mem_cgroup_task_swapin, NULL);
+
+	return nbytes;
+}
 #endif
 
 #ifdef CONFIG_NUMA
@@ -5800,6 +5826,13 @@ static struct cftype mem_cgroup_legacy_files[] = {
 		.name = "reclaim",
 		.write = memory_reclaim,
 	},
+#ifdef CONFIG_MEMCG_SWAP_QOS
+	{
+		.name = "force_swapin",
+		.flags = CFTYPE_NOT_ON_ROOT,
+		.write = memory_swapin,
+	},
+#endif
 	{
 		.name = "high_async_ratio",
 		.flags = CFTYPE_NOT_ON_ROOT,