[PATCH 27/32] x86/intel_rdt_rdtgroup.c: Implement rscctrl file system commands

[Fenghua Yu]

From: Fenghua Yu <fenghua.yu@xxxxxxxxx>

Four basic file system commands are implement for rscctrl.
mount, umount, mkdir, and rmdir.

Signed-off-by: Fenghua Yu <fenghua.yu@xxxxxxxxx>
Reviewed-by: Tony Luck <tony.luck@xxxxxxxxx>
---
 arch/x86/kernel/cpu/intel_rdt_rdtgroup.c | 237 +++++++++++++++++++++++++++++++
 1 file changed, 237 insertions(+)

diff --git a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
index b2140a8..91ea3509 100644
--- a/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
+++ b/arch/x86/kernel/cpu/intel_rdt_rdtgroup.c
@@ -856,6 +856,139 @@ static void rdtgroup_idr_remove(struct idr *idr, int id)
 	spin_unlock_bh(&rdtgroup_idr_lock);
 }
 
+
+static int rdtgroup_mkdir(struct kernfs_node *parent_kn, const char *name,
+			umode_t mode)
+{
+	struct rdtgroup *parent, *rdtgrp;
+	struct rdtgroup_root *root;
+	struct kernfs_node *kn;
+	int level, ret;
+
+	if (parent_kn != root_rdtgrp->kn)
+		return -EPERM;
+
+	/* Do not accept '\n' to avoid unparsable situation.
+	 */
+	if (strchr(name, '\n'))
+		return -EINVAL;
+
+	parent = rdtgroup_kn_lock_live(parent_kn);
+	if (!parent)
+		return -ENODEV;
+	root = parent->root;
+	level = parent->level + 1;
+
+	/* allocate the rdtgroup and its ID, 0 is reserved for the root */
+	rdtgrp = kzalloc(sizeof(*rdtgrp) +
+			 sizeof(rdtgrp->ancestor_ids[0]) * (level + 1),
+			 GFP_KERNEL);
+	if (!rdtgrp) {
+		ret = -ENOMEM;
+		goto out_unlock;
+	}
+
+	/*
+	 * Temporarily set the pointer to NULL, so idr_find() won't return
+	 * a half-baked rdtgroup.
+	 */
+	rdtgrp->id = rdtgroup_idr_alloc(&root->rdtgroup_idr, NULL, 2, 0,
+					GFP_KERNEL);
+	if (rdtgrp->id < 0) {
+		ret = -ENOMEM;
+		goto out_cancel_ref;
+	}
+
+	INIT_LIST_HEAD(&rdtgrp->pset.tasks);
+
+	init_rdtgroup_housekeeping(rdtgrp);
+	cpumask_clear(&rdtgrp->cpu_mask);
+
+	rdtgrp->root = root;
+	rdtgrp->level = level;
+
+	if (test_bit(RDTGRP_CPUSET_CLONE_CHILDREN, &parent->flags))
+		set_bit(RDTGRP_CPUSET_CLONE_CHILDREN, &rdtgrp->flags);
+
+	/* create the directory */
+	kn = kernfs_create_dir(parent->kn, name, mode, rdtgrp);
+	if (IS_ERR(kn)) {
+		ret = PTR_ERR(kn);
+		goto out_free_id;
+	}
+	rdtgrp->kn = kn;
+
+	/*
+	 * This extra ref will be put in kernfs_remove() and guarantees
+	 * that @rdtgrp->kn is always accessible.
+	 */
+	kernfs_get(kn);
+
+	atomic_inc(&root->nr_rdtgrps);
+
+	/*
+	 * @rdtgrp is now fully operational.  If something fails after this
+	 * point, it'll be released via the normal destruction path.
+	 */
+	rdtgroup_idr_replace(&root->rdtgroup_idr, rdtgrp, rdtgrp->id);
+
+	ret = rdtgroup_kn_set_ugid(kn);
+	if (ret)
+		goto out_destroy;
+
+	ret = rdtgroup_partition_populate_dir(kn);
+	if (ret)
+		goto out_destroy;
+
+	kernfs_activate(kn);
+
+	list_add_tail(&rdtgrp->rdtgroup_list, &rdtgroup_lists);
+	/* Generate default schema for rdtgrp. */
+	ret = get_default_resources(rdtgrp);
+	if (ret)
+		goto out_destroy;
+
+	ret = 0;
+	goto out_unlock;
+
+out_free_id:
+	rdtgroup_idr_remove(&root->rdtgroup_idr, rdtgrp->id);
+out_cancel_ref:
+	kfree(rdtgrp);
+out_unlock:
+	rdtgroup_kn_unlock(parent_kn);
+	return ret;
+
+out_destroy:
+	rdtgroup_destroy_locked(rdtgrp);
+	goto out_unlock;
+}
+
+static int rdtgroup_rmdir(struct kernfs_node *kn)
+{
+	struct rdtgroup *rdtgrp;
+	int cpu;
+	int ret = 0;
+
+	rdtgrp = rdtgroup_kn_lock_live(kn);
+	if (!rdtgrp)
+		return -ENODEV;
+
+	if (!list_empty(&rdtgrp->pset.tasks)) {
+		ret = -EBUSY;
+		goto out;
+	}
+
+	for_each_cpu(cpu, &rdtgrp->cpu_mask)
+		per_cpu(cpu_rdtgroup, cpu) = 0;
+
+	ret = rdtgroup_destroy_locked(rdtgrp);
+
+out:
+	rdtgroup_kn_unlock(kn);
+	return ret;
+}
+
 static int
 rdtgroup_move_task_all(struct rdtgroup *src_rdtgrp, struct rdtgroup *dst_rdtgrp)
 {
@@ -957,6 +1090,11 @@ static void release_root_closid(void)
 	}
 }
 
+static struct kernfs_syscall_ops rdtgroup_kf_syscall_ops = {
+	.mkdir			= rdtgroup_mkdir,
+	.rmdir			= rdtgroup_rmdir,
+};
+
 static void setup_task_rg_lists(struct rdtgroup *rdtgrp, bool enable)
 {
 	struct task_struct *p, *g;
@@ -1009,6 +1147,105 @@ static void setup_task_rg_lists(struct rdtgroup *rdtgrp, bool enable)
  */
 static bool rdtgrp_dfl_root_visible;
 
+bool rdtgroup_mounted;
+
+static struct dentry *rdt_mount(struct file_system_type *fs_type,
+			 int flags, const char *unused_dev_name,
+			 void *data)
+{
+	struct super_block *pinned_sb = NULL;
+	struct rdtgroup_root *root;
+	struct dentry *dentry;
+	int ret;
+	bool new_sb;
+
+	/*
+	 * The first time anyone tries to mount a rdtgroup, enable the list
+	 * linking tasks and fix up all existing tasks.
+	 */
+	if (rdtgroup_mounted)
+		return ERR_PTR(-EBUSY);
+
+	rdt_opts.cdp_enabled = false;
+	rdt_opts.verbose = false;
+	cdp_enabled = false;
+
+	ret = parse_rdtgroupfs_options(data);
+	if (ret)
+		goto out_mount;
+
+	if (rdt_opts.cdp_enabled) {
+		cdp_enabled = true;
+		cconfig.max_closid >>= cdp_enabled;
+		pr_info("CDP is enabled\n");
+	}
+
+	init_msrs(cdp_enabled);
+
+	rdtgrp_dfl_root_visible = true;
+	root = &rdtgrp_dfl_root;
+
+	ret = get_default_resources(&root->rdtgrp);
+	if (ret)
+		return ERR_PTR(-ENOSPC);
+
+out_mount:
+	dentry = kernfs_mount(fs_type, flags, root->kf_root,
+			      RDTGROUP_SUPER_MAGIC,
+			      &new_sb);
+	if (IS_ERR(dentry) || !new_sb)
+		goto out_unlock;
+
+	/*
+	 * If @pinned_sb, we're reusing an existing root and holding an
+	 * extra ref on its sb.  Mount is complete.  Put the extra ref.
+	 */
+	if (pinned_sb) {
+		WARN_ON(new_sb);
+		deactivate_super(pinned_sb);
+	}
+
+	setup_task_rg_lists(&root->rdtgrp, true);
+
+	cpumask_clear(&root->rdtgrp.cpu_mask);
+	rdtgroup_mounted = true;
+
+	return dentry;
+
+out_unlock:
+	return ERR_PTR(ret);
+}
+
+static void rdt_kill_sb(struct super_block *sb)
+{
+	int ret;
+
+	mutex_lock(&rdtgroup_mutex);
+
+	ret = rmdir_all_sub();
+	if (ret)
+		goto out_unlock;
+
+	setup_task_rg_lists(root_rdtgrp, false);
+	release_root_closid();
+	root_rdtgrp->resource.valid = false;
+
+	/* Restore max_closid to original value. */
+	cconfig.max_closid <<= cdp_enabled;
+
+	kernfs_kill_sb(sb);
+	rdtgroup_mounted = false;
+out_unlock:
+
+	mutex_unlock(&rdtgroup_mutex);
+}
+
+static struct file_system_type rdt_fs_type = {
+	.name = "rscctrl",
+	.mount = rdt_mount,
+	.kill_sb = rdt_kill_sb,
+};
+
 static ssize_t rdtgroup_file_write(struct kernfs_open_file *of, char *buf,
 				 size_t nbytes, loff_t off)
 {
-- 
2.5.0