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, 133 insertions, 0 deletions

diff --git a/fs/nfs/getroot.c b/fs/nfs/getroot.c
new file mode 100644
index 000000000..ff7424bc4
--- /dev/null
+++ b/fs/nfs/getroot.c
@@ -0,0 +1,133 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/* getroot.c: get the root dentry for an NFS mount
+ *
+ * Copyright (C) 2006 Red Hat, Inc. All Rights Reserved.
+ * Written by David Howells (dhowells@redhat.com)
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+
+#include <linux/time.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/string.h>
+#include <linux/stat.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/sunrpc/clnt.h>
+#include <linux/sunrpc/stats.h>
+#include <linux/nfs_fs.h>
+#include <linux/nfs_mount.h>
+#include <linux/lockd/bind.h>
+#include <linux/seq_file.h>
+#include <linux/mount.h>
+#include <linux/vfs.h>
+#include <linux/namei.h>
+#include <linux/security.h>
+
+#include <linux/uaccess.h>
+
+#include "internal.h"
+
+#define NFSDBG_FACILITY		NFSDBG_CLIENT
+
+/*
+ * get a root dentry from the root filehandle
+ */
+int nfs_get_root(struct super_block *s, struct fs_context *fc)
+{
+	struct nfs_fs_context *ctx = nfs_fc2context(fc);
+	struct nfs_server *server = NFS_SB(s), *clone_server;
+	struct nfs_fsinfo fsinfo;
+	struct dentry *root;
+	struct inode *inode;
+	char *name;
+	int error = -ENOMEM;
+	unsigned long kflags = 0, kflags_out = 0;
+
+	name = kstrdup(fc->source, GFP_KERNEL);
+	if (!name)
+		goto out;
+
+	/* get the actual root for this mount */
+	fsinfo.fattr = nfs_alloc_fattr_with_label(server);
+	if (fsinfo.fattr == NULL)
+		goto out_name;
+
+	error = server->nfs_client->rpc_ops->getroot(server, ctx->mntfh, &fsinfo);
+	if (error < 0) {
+		dprintk("nfs_get_root: getattr error = %d\n", -error);
+		nfs_errorf(fc, "NFS: Couldn't getattr on root");
+		goto out_fattr;
+	}
+
+	inode = nfs_fhget(s, ctx->mntfh, fsinfo.fattr);
+	if (IS_ERR(inode)) {
+		dprintk("nfs_get_root: get root inode failed\n");
+		error = PTR_ERR(inode);
+		nfs_errorf(fc, "NFS: Couldn't get root inode");
+		goto out_fattr;
+	}
+
+	/* root dentries normally start off anonymous and get spliced in later
+	 * if the dentry tree reaches them; however if the dentry already
+	 * exists, we'll pick it up at this point and use it as the root
+	 */
+	root = d_obtain_root(inode);
+	if (IS_ERR(root)) {
+		dprintk("nfs_get_root: get root dentry failed\n");
+		error = PTR_ERR(root);
+		nfs_errorf(fc, "NFS: Couldn't get root dentry");
+		goto out_fattr;
+	}
+
+	security_d_instantiate(root, inode);
+	spin_lock(&root->d_lock);
+	if (IS_ROOT(root) && !root->d_fsdata &&
+	    !(root->d_flags & DCACHE_NFSFS_RENAMED)) {
+		root->d_fsdata = name;
+		name = NULL;
+	}
+	spin_unlock(&root->d_lock);
+	if (!s->s_root)
+		s->s_root = dget(root);
+	fc->root = root;
+	if (server->caps & NFS_CAP_SECURITY_LABEL)
+		kflags |= SECURITY_LSM_NATIVE_LABELS;
+	if (ctx->clone_data.sb) {
+		if (d_inode(fc->root)->i_fop != &nfs_dir_operations) {
+			error = -ESTALE;
+			goto error_splat_root;
+		}
+		/* clone lsm security options from the parent to the new sb */
+		error = security_sb_clone_mnt_opts(ctx->clone_data.sb,
+						   s, kflags, &kflags_out);
+		if (error)
+			goto error_splat_root;
+		clone_server = NFS_SB(ctx->clone_data.sb);
+		server->has_sec_mnt_opts = clone_server->has_sec_mnt_opts;
+	} else {
+		error = security_sb_set_mnt_opts(s, fc->security,
+							kflags, &kflags_out);
+	}
+	if (error)
+		goto error_splat_root;
+	if (server->caps & NFS_CAP_SECURITY_LABEL &&
+		!(kflags_out & SECURITY_LSM_NATIVE_LABELS))
+		server->caps &= ~NFS_CAP_SECURITY_LABEL;
+
+	nfs_setsecurity(inode, fsinfo.fattr);
+	error = 0;
+
+out_fattr:
+	nfs_free_fattr(fsinfo.fattr);
+out_name:
+	kfree(name);
+out:
+	return error;
+error_splat_root:
+	dput(fc->root);
+	fc->root = NULL;
+	goto out_fattr;
+}