[PATCH v2 29/33] x86/intel_rdt_rdtgroup.c: Tasks iterator and write

[Fenghua Yu]

From: Fenghua Yu <fenghua.yu@xxxxxxxxx>

"tasks" file in rdtgroup contains task pids. User can move a task pid
to one directory. A task can only stay in one directory at the same
time.

Each rdtgroup contains a rg_list. When a pid is written to this
rdtgroup's tasks, the task's rg_list is added in the rdtgroup's
linked list and deleted from its previous rdtgroup's linked list.

When user reads the "tasks" file, all pids are shown in the order
from small to large.

Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 161 +++++++++++++++++++++++--------
 1 file changed, 120 insertions(+), 41 deletions(-)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index 6c3161a..16f7195 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -63,6 +63,9 @@ static int rdtgroup_cpus_show(struct seq_file *s, void *v);
 static ssize_t rdtgroup_cpus_write(struct kernfs_open_file *of,
 			char *buf, size_t nbytes, loff_t off);
 
+static int rdtgroup_tasks_show(struct seq_file *s, void *v);
+static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
+				  char *buf, size_t nbytes, loff_t off);
 /* rdtgroup core interface files */
 static struct rftype rdtgroup_root_base_files[] = {
 	{
@@ -720,14 +723,41 @@ static __init void init_cache_domains(void)
 
 void rdtgroup_exit(struct task_struct *tsk)
 {
+	if (tsk->rdtgroup) {
+		atomic_dec(&tsk->rdtgroup->refcount);
+		tsk->rdtgroup = NULL;
+	}
+}
 
-	if (!list_empty(&tsk->rg_list)) {
-		struct rdtgroup *rdtgrp = tsk->rdtgroup;
+static void show_rdt_tasks(struct rdtgroup *r, struct seq_file *s)
+{
+	struct task_struct *p;
+	struct rdtgroup *this = r;
 
-		list_del_init(&tsk->rg_list);
-		tsk->rdtgroup = NULL;
-		atomic_dec(&rdtgrp->refcount);
+
+	if (r == root_rdtgrp)
+		return;
+
+	rcu_read_lock();
+	for_each_process(p) {
+		if (p->rdtgroup == this)
+			seq_printf(s, "%d\n", p->pid);
 	}
+	rcu_read_unlock();
+}
+
+static int rdtgroup_tasks_show(struct seq_file *s, void *v)
+{
+	struct kernfs_open_file *of = s->private;
+	struct rdtgroup *rdtgrp;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (rdtgrp == NULL)
+		return -ENODEV;
+
+	show_rdt_tasks(rdtgrp, s);
+	rdtgroup_kn_unlock(of->kn);
+	return 0;
 }
 
 static void rdtgroup_destroy_locked(struct rdtgroup *rdtgrp)
@@ -781,8 +811,6 @@ static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
 		goto out_unlock;
 	}
 
-	INIT_LIST_HEAD(&rdtgrp->pset.tasks);
-
 	cpumask_clear(&rdtgrp->cpu_mask);
 
 	rdtgrp->root = root;
@@ -843,7 +871,7 @@ static int rdtgroup_rmdir(struct kernfs_node *kn)
 	if (!rdtgrp)
 		return -ENODEV;
 
-	if (!list_empty(&rdtgrp->pset.tasks)) {
+	if (atomic_read(&rdtgrp->refcount)) {
 		ret = -EBUSY;
 		goto out;
 	}
@@ -857,28 +885,6 @@ out:
 	rdtgroup_kn_unlock(kn);
 	return ret;
 }
-static int
-rdtgroup_move_task_all(struct rdtgroup *src_rdtgrp, struct rdtgroup *dst_rdtgrp)
-{
-	struct list_head *tasks;
-
-	tasks = &src_rdtgrp->pset.tasks;
-	while (!list_empty(tasks)) {
-		struct task_struct *tsk;
-		struct list_head *pos;
-		pid_t pid;
-		int ret;
-
-		pos = tasks->next;
-		tsk = list_entry(pos, struct task_struct, rg_list);
-		pid = tsk->pid;
-		ret = rdtgroup_move_task(pid, dst_rdtgrp, false, NULL);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
 
 /*
  * Forcibly remove all of subdirectories under root.
@@ -1088,22 +1094,16 @@ void rdtgroup_fork(struct task_struct *child)
 {
 	struct rdtgroup *rdtgrp;
 
-	INIT_LIST_HEAD(&child->rg_list);
+	child->rdtgroup = NULL;
 	if (!rdtgroup_mounted)
 		return;
 
-	mutex_lock(&rdtgroup_mutex);
-
 	rdtgrp = current->rdtgroup;
 	if (!rdtgrp)
-		goto out;
+		return;
 
-	list_add_tail(&child->rg_list, &rdtgrp->pset.tasks);
 	child->rdtgroup = rdtgrp;
 	atomic_inc(&rdtgrp->refcount);
-
-out:
-	mutex_unlock(&rdtgroup_mutex);
 }
 
 static struct dentry *rdt_mount(struct file_system_type *fs_type,
@@ -1161,8 +1161,6 @@ out_mount:
 		deactivate_super(pinned_sb);
 	}
 
-	INIT_LIST_HEAD(&root->rdtgrp.pset.tasks);
-
 	cpumask_copy(&root->rdtgrp.cpu_mask, cpu_online_mask);
 	static_key_slow_inc(&rdt_enable_key);
 	rdtgroup_mounted = true;
@@ -1188,7 +1186,6 @@ static void rdt_kill_sb(struct super_block *sb)
 	cconfig.max_closid <<= cdp_enabled;
 
 	kernfs_kill_sb(sb);
-	INIT_LIST_HEAD(&root_rdtgrp->pset.tasks);
 	rdtgroup_mounted = false;
 
 	mutex_unlock(&rdtgroup_mutex);
@@ -1281,3 +1278,85 @@ end:
 
 	return ret ?: nbytes;
 }
+
+static int _rdtgroup_move_task(struct task_struct *tsk, struct rdtgroup *rdtgrp)
+{
+	if (tsk->rdtgroup)
+		atomic_dec(&tsk->rdtgroup->refcount);
+
+	if (rdtgrp == root_rdtgrp)
+		tsk->rdtgroup = NULL;
+	else
+		tsk->rdtgroup = rdtgrp;
+
+	atomic_inc(&rdtgrp->refcount);
+
+	return 0;
+}
+
+static int rdtgroup_move_task(pid_t pid, struct rdtgroup *rdtgrp,
+			      bool threadgroup, struct kernfs_open_file *of)
+{
+	struct task_struct *tsk;
+	int ret;
+
+	rcu_read_lock();
+	if (pid) {
+		tsk = find_task_by_vpid(pid);
+		if (!tsk) {
+			ret = -ESRCH;
+			goto out_unlock_rcu;
+		}
+	} else {
+		tsk = current;
+	}
+
+	if (threadgroup)
+		tsk = tsk->group_leader;
+
+	get_task_struct(tsk);
+	rcu_read_unlock();
+
+	ret = rdtgroup_procs_write_permission(tsk, of);
+	if (!ret)
+		_rdtgroup_move_task(tsk, rdtgrp);
+
+	put_task_struct(tsk);
+	goto out_unlock_threadgroup;
+
+out_unlock_rcu:
+	rcu_read_unlock();
+out_unlock_threadgroup:
+	return ret;
+}
+
+ssize_t _rdtgroup_procs_write(struct rdtgroup *rdtgrp,
+			   struct kernfs_open_file *of, char *buf,
+			   size_t nbytes, loff_t off, bool threadgroup)
+{
+	pid_t pid;
+	int ret;
+
+	if (kstrtoint(strstrip(buf), 0, &pid) || pid < 0)
+		return -EINVAL;
+
+	ret = rdtgroup_move_task(pid, rdtgrp, threadgroup, of);
+
+	return ret ?: nbytes;
+}
+
+static ssize_t rdtgroup_tasks_write(struct kernfs_open_file *of,
+				  char *buf, size_t nbytes, loff_t off)
+{
+	struct rdtgroup *rdtgrp;
+	int ret;
+
+	rdtgrp = rdtgroup_kn_lock_live(of->kn);
+	if (!rdtgrp)
+		return -ENODEV;
+
+	ret = _rdtgroup_procs_write(rdtgrp, of, buf, nbytes, off, false);
+
+	rdtgroup_kn_unlock(of->kn);
+	return ret;
+}
-- 
2.5.0