sched_ext: Maintain an online cid mask in the scheduler arenagrafted

Schedulers on the default cid mapping treat [0, nr_online_cids) as the
online set and restart on hotplug. Schedulers that install their own mapping
with scx_bpf_cid_override() have no way to learn which cids are online: the
count no longer identifies members and the CPU-form cpumask is unusable from
cid programs. This is an obvious hole in the cid API.

Add scx_bpf_online_cmask(), a kernel-maintained cmask in the scheduler's
arena, allocated alongside the per-CPU scratch masks and populated after the
cid mapping is finalized and before ops.init(), for child schedulers too.
The pointer stays valid through ops.exit() with no reference to take. It is
the arena offset as a void pointer, the same form struct_ops arena arguments
arrive in. The verifier types the void return as a scalar for the program's
arena cast.

The mask follows the SCX hotplug notifications: seeded from cpu_active_mask
and updated before ops.cid_online/offline() runs, so it lags cpu_online_mask
only inside a hotplug transition. Updates walk the scheduler list under the
lock that also serializes unlinking. Reads are live, not atomic snapshots.
Root initialization excludes hotplug.

v2: Reworded the getter kerneldoc (Andrea Righi).

Signed-off-by: Tejun Heo <tj@kernel.org>
Reviewed-by: Andrea Righi <arighi@nvidia.com>

1 files changed, 159 insertions, 0 deletions

diff --git a/fs/ecryptfs/kthread.c b/fs/ecryptfs/kthread.c
new file mode 100644
index 000000000..ae4cb4e2e
--- /dev/null
+++ b/fs/ecryptfs/kthread.c
@@ -0,0 +1,159 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * eCryptfs: Linux filesystem encryption layer
+ *
+ * Copyright (C) 2008 International Business Machines Corp.
+ *   Author(s): Michael A. Halcrow <mahalcro@us.ibm.com>
+ */
+
+#include <linux/kthread.h>
+#include <linux/freezer.h>
+#include <linux/slab.h>
+#include <linux/wait.h>
+#include <linux/mount.h>
+#include "ecryptfs_kernel.h"
+
+struct ecryptfs_open_req {
+	struct file **lower_file;
+	struct path path;
+	struct completion done;
+	struct list_head kthread_ctl_list;
+};
+
+static struct ecryptfs_kthread_ctl {
+#define ECRYPTFS_KTHREAD_ZOMBIE 0x00000001
+	u32 flags;
+	struct mutex mux;
+	struct list_head req_list;
+	wait_queue_head_t wait;
+} ecryptfs_kthread_ctl;
+
+static struct task_struct *ecryptfs_kthread;
+
+/**
+ * ecryptfs_threadfn
+ * @ignored: ignored
+ *
+ * The eCryptfs kernel thread that has the responsibility of getting
+ * the lower file with RW permissions.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+static int ecryptfs_threadfn(void *ignored)
+{
+	set_freezable();
+	while (1)  {
+		struct ecryptfs_open_req *req;
+
+		wait_event_freezable(
+			ecryptfs_kthread_ctl.wait,
+			(!list_empty(&ecryptfs_kthread_ctl.req_list)
+			 || kthread_should_stop()));
+		mutex_lock(&ecryptfs_kthread_ctl.mux);
+		if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+			mutex_unlock(&ecryptfs_kthread_ctl.mux);
+			goto out;
+		}
+		while (!list_empty(&ecryptfs_kthread_ctl.req_list)) {
+			req = list_first_entry(&ecryptfs_kthread_ctl.req_list,
+					       struct ecryptfs_open_req,
+					       kthread_ctl_list);
+			list_del(&req->kthread_ctl_list);
+			*req->lower_file = dentry_open(&req->path,
+				(O_RDWR | O_LARGEFILE), current_cred());
+			complete(&req->done);
+		}
+		mutex_unlock(&ecryptfs_kthread_ctl.mux);
+	}
+out:
+	return 0;
+}
+
+int __init ecryptfs_init_kthread(void)
+{
+	int rc = 0;
+
+	mutex_init(&ecryptfs_kthread_ctl.mux);
+	init_waitqueue_head(&ecryptfs_kthread_ctl.wait);
+	INIT_LIST_HEAD(&ecryptfs_kthread_ctl.req_list);
+	ecryptfs_kthread = kthread_run(&ecryptfs_threadfn, NULL,
+				       "ecryptfs-kthread");
+	if (IS_ERR(ecryptfs_kthread)) {
+		rc = PTR_ERR(ecryptfs_kthread);
+		printk(KERN_ERR "%s: Failed to create kernel thread; rc = [%d]"
+		       "\n", __func__, rc);
+	}
+	return rc;
+}
+
+void ecryptfs_destroy_kthread(void)
+{
+	struct ecryptfs_open_req *req, *tmp;
+
+	mutex_lock(&ecryptfs_kthread_ctl.mux);
+	ecryptfs_kthread_ctl.flags |= ECRYPTFS_KTHREAD_ZOMBIE;
+	list_for_each_entry_safe(req, tmp, &ecryptfs_kthread_ctl.req_list,
+				 kthread_ctl_list) {
+		list_del(&req->kthread_ctl_list);
+		*req->lower_file = ERR_PTR(-EIO);
+		complete(&req->done);
+	}
+	mutex_unlock(&ecryptfs_kthread_ctl.mux);
+	kthread_stop(ecryptfs_kthread);
+	wake_up(&ecryptfs_kthread_ctl.wait);
+}
+
+/**
+ * ecryptfs_privileged_open
+ * @lower_file: Result of dentry_open by root on lower dentry
+ * @lower_dentry: Lower dentry for file to open
+ * @lower_mnt: Lower vfsmount for file to open
+ * @cred: credential to use for this call
+ *
+ * This function gets a r/w file opened against the lower dentry.
+ *
+ * Returns zero on success; non-zero otherwise
+ */
+int ecryptfs_privileged_open(struct file **lower_file,
+			     struct dentry *lower_dentry,
+			     struct vfsmount *lower_mnt,
+			     const struct cred *cred)
+{
+	struct ecryptfs_open_req req;
+	int flags = O_LARGEFILE;
+	int rc = 0;
+
+	init_completion(&req.done);
+	req.lower_file = lower_file;
+	req.path.dentry = lower_dentry;
+	req.path.mnt = lower_mnt;
+
+	/* Corresponding dput() and mntput() are done when the
+	 * lower file is fput() when all eCryptfs files for the inode are
+	 * released. */
+	flags |= IS_RDONLY(d_inode(lower_dentry)) ? O_RDONLY : O_RDWR;
+	(*lower_file) = dentry_open(&req.path, flags, cred);
+	if (!IS_ERR(*lower_file))
+		goto out;
+	if ((flags & O_ACCMODE) == O_RDONLY) {
+		rc = PTR_ERR((*lower_file));
+		goto out;
+	}
+	mutex_lock(&ecryptfs_kthread_ctl.mux);
+	if (ecryptfs_kthread_ctl.flags & ECRYPTFS_KTHREAD_ZOMBIE) {
+		rc = -EIO;
+		mutex_unlock(&ecryptfs_kthread_ctl.mux);
+		printk(KERN_ERR "%s: We are in the middle of shutting down; "
+		       "aborting privileged request to open lower file\n",
+			__func__);
+		goto out;
+	}
+	list_add_tail(&req.kthread_ctl_list, &ecryptfs_kthread_ctl.req_list);
+	mutex_unlock(&ecryptfs_kthread_ctl.mux);
+	wake_up(&ecryptfs_kthread_ctl.wait);
+	wait_for_completion(&req.done);
+	if (IS_ERR(*lower_file))
+		rc = PTR_ERR(*lower_file);
+out:
+	return rc;
+}