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, 196 insertions, 0 deletions

diff --git a/fs/proc/namespaces.c b/fs/proc/namespaces.c
new file mode 100644
index 000000000..ea6ec61a0
--- /dev/null
+++ b/fs/proc/namespaces.c
@@ -0,0 +1,196 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/proc_fs.h>
+#include <linux/nsproxy.h>
+#include <linux/ptrace.h>
+#include <linux/namei.h>
+#include <linux/file.h>
+#include <linux/utsname.h>
+#include <net/net_namespace.h>
+#include <linux/ipc_namespace.h>
+#include <linux/pid_namespace.h>
+#include <linux/user_namespace.h>
+#include "internal.h"
+
+
+static const struct proc_ns_operations *const ns_entries[] = {
+#ifdef CONFIG_NET_NS
+	&netns_operations,
+#endif
+#ifdef CONFIG_UTS_NS
+	&utsns_operations,
+#endif
+#ifdef CONFIG_IPC_NS
+	&ipcns_operations,
+#endif
+#ifdef CONFIG_PID_NS
+	&pidns_operations,
+	&pidns_for_children_operations,
+#endif
+#ifdef CONFIG_USER_NS
+	&userns_operations,
+#endif
+	&mntns_operations,
+#ifdef CONFIG_CGROUPS
+	&cgroupns_operations,
+#endif
+#ifdef CONFIG_TIME_NS
+	&timens_operations,
+	&timens_for_children_operations,
+#endif
+};
+
+static const char *proc_ns_get_link(struct dentry *dentry,
+				    struct inode *inode,
+				    struct delayed_call *done)
+{
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	struct path ns_path;
+	int error;
+
+	if (!dentry)
+		return ERR_PTR(-ECHILD);
+
+	task = get_proc_task(inode);
+	if (!task)
+		return ERR_PTR(-EACCES);
+
+	error = down_read_killable(&task->signal->exec_update_lock);
+	if (error)
+		goto out_put_task;
+
+	error = -EACCES;
+	if (!ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS))
+		goto out;
+
+	error = ns_get_path(&ns_path, task, ns_ops);
+	if (error)
+		goto out;
+
+	error = nd_jump_link(&ns_path);
+out:
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return ERR_PTR(error);
+}
+
+static int proc_ns_readlink(struct dentry *dentry, char __user *buffer, int buflen)
+{
+	struct inode *inode = d_inode(dentry);
+	const struct proc_ns_operations *ns_ops = PROC_I(inode)->ns_ops;
+	struct task_struct *task;
+	char name[50];
+	int res = -EACCES;
+
+	task = get_proc_task(inode);
+	if (!task)
+		return res;
+
+	res = down_read_killable(&task->signal->exec_update_lock);
+	if (res)
+		goto out_put_task;
+
+	res = -EACCES;
+	if (ptrace_may_access(task, PTRACE_MODE_READ_FSCREDS)) {
+		res = ns_get_name(name, sizeof(name), task, ns_ops);
+		if (res >= 0)
+			res = readlink_copy(buffer, buflen, name, strlen(name));
+	}
+	up_read(&task->signal->exec_update_lock);
+out_put_task:
+	put_task_struct(task);
+	return res;
+}
+
+static const struct inode_operations proc_ns_link_inode_operations = {
+	.readlink	= proc_ns_readlink,
+	.get_link	= proc_ns_get_link,
+	.setattr	= proc_nochmod_setattr,
+};
+
+static struct dentry *proc_ns_instantiate(struct dentry *dentry,
+	struct task_struct *task, const void *ptr)
+{
+	const struct proc_ns_operations *ns_ops = ptr;
+	struct inode *inode;
+	struct proc_inode *ei;
+
+	inode = proc_pid_make_inode(dentry->d_sb, task, S_IFLNK | S_IRWXUGO);
+	if (!inode)
+		return ERR_PTR(-ENOENT);
+
+	ei = PROC_I(inode);
+	inode->i_op = &proc_ns_link_inode_operations;
+	ei->ns_ops = ns_ops;
+	pid_update_inode(task, inode);
+
+	return d_splice_alias_ops(inode, dentry, &pid_dentry_operations);
+}
+
+static int proc_ns_dir_readdir(struct file *file, struct dir_context *ctx)
+{
+	struct task_struct *task = get_proc_task(file_inode(file));
+	const struct proc_ns_operations *const *entry, *const *last;
+
+	if (!task)
+		return -ENOENT;
+
+	if (!dir_emit_dots(file, ctx))
+		goto out;
+	if (ctx->pos >= 2 + ARRAY_SIZE(ns_entries))
+		goto out;
+	entry = ns_entries + (ctx->pos - 2);
+	last = &ns_entries[ARRAY_SIZE(ns_entries) - 1];
+	while (entry <= last) {
+		const struct proc_ns_operations *ops = *entry;
+		if (!proc_fill_cache(file, ctx, ops->name, strlen(ops->name),
+				     proc_ns_instantiate, task, ops))
+			break;
+		ctx->pos++;
+		entry++;
+	}
+out:
+	put_task_struct(task);
+	return 0;
+}
+
+const struct file_operations proc_ns_dir_operations = {
+	.read		= generic_read_dir,
+	.iterate_shared	= proc_ns_dir_readdir,
+	.llseek		= generic_file_llseek,
+};
+
+static struct dentry *proc_ns_dir_lookup(struct inode *dir,
+				struct dentry *dentry, unsigned int flags)
+{
+	struct task_struct *task = get_proc_task(dir);
+	const struct proc_ns_operations *const *entry, *const *last;
+	unsigned int len = dentry->d_name.len;
+	struct dentry *res = ERR_PTR(-ENOENT);
+
+	if (!task)
+		goto out_no_task;
+
+	last = &ns_entries[ARRAY_SIZE(ns_entries)];
+	for (entry = ns_entries; entry < last; entry++) {
+		if (strlen((*entry)->name) != len)
+			continue;
+		if (!memcmp(dentry->d_name.name, (*entry)->name, len))
+			break;
+	}
+	if (entry == last)
+		goto out;
+
+	res = proc_ns_instantiate(dentry, task, *entry);
+out:
+	put_task_struct(task);
+out_no_task:
+	return res;
+}
+
+const struct inode_operations proc_ns_dir_inode_operations = {
+	.lookup		= proc_ns_dir_lookup,
+	.getattr	= pid_getattr,
+	.setattr	= proc_nochmod_setattr,
+};