From a9e3760b0838299649c0d57cca44daaf40ba3c33 Mon Sep 17 00:00:00 2001 From: Tejun Heo Date: Mon, 14 Sep 2026 22:12:34 -1000 Subject: sched_ext: Maintain an online cid mask in the scheduler arena 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 Reviewed-by: Andrea Righi --- fs/fs_struct.c | 155 +++++++++++++++++++++++++++++++++++++++++++++++++++++++++ 1 file changed, 155 insertions(+) create mode 100644 fs/fs_struct.c (limited to 'fs/fs_struct.c') diff --git a/fs/fs_struct.c b/fs/fs_struct.c new file mode 100644 index 000000000..394875d06 --- /dev/null +++ b/fs/fs_struct.c @@ -0,0 +1,155 @@ +// SPDX-License-Identifier: GPL-2.0-only +#include +#include +#include +#include +#include +#include +#include +#include +#include "internal.h" + +/* + * Replace the fs->{rootmnt,root} with {mnt,dentry}. Put the old values. + * It can block. + */ +void set_fs_root(struct fs_struct *fs, const struct path *path) +{ + struct path old_root; + + path_get(path); + write_seqlock(&fs->seq); + old_root = fs->root; + fs->root = *path; + write_sequnlock(&fs->seq); + if (old_root.dentry) + path_put(&old_root); +} + +/* + * Replace the fs->{pwdmnt,pwd} with {mnt,dentry}. Put the old values. + * It can block. + */ +void set_fs_pwd(struct fs_struct *fs, const struct path *path) +{ + struct path old_pwd; + + path_get(path); + write_seqlock(&fs->seq); + old_pwd = fs->pwd; + fs->pwd = *path; + write_sequnlock(&fs->seq); + + if (old_pwd.dentry) + path_put(&old_pwd); +} + +static inline int replace_path(struct path *p, const struct path *old, const struct path *new) +{ + if (likely(p->dentry != old->dentry || p->mnt != old->mnt)) + return 0; + *p = *new; + return 1; +} + +void chroot_fs_refs(const struct path *old_root, const struct path *new_root) +{ + struct task_struct *g, *p; + struct fs_struct *fs; + int count = 0; + + read_lock(&tasklist_lock); + for_each_process_thread(g, p) { + task_lock(p); + fs = p->fs; + if (fs) { + int hits = 0; + write_seqlock(&fs->seq); + hits += replace_path(&fs->root, old_root, new_root); + hits += replace_path(&fs->pwd, old_root, new_root); + while (hits--) { + count++; + path_get(new_root); + } + write_sequnlock(&fs->seq); + } + task_unlock(p); + } + read_unlock(&tasklist_lock); + while (count--) + path_put(old_root); +} + +void free_fs_struct(struct fs_struct *fs) +{ + path_put(&fs->root); + path_put(&fs->pwd); + kmem_cache_free(fs_cachep, fs); +} + +void exit_fs(struct task_struct *tsk) +{ + struct fs_struct *fs = tsk->fs; + + if (fs) { + int kill; + task_lock(tsk); + read_seqlock_excl(&fs->seq); + tsk->fs = NULL; + kill = !--fs->users; + read_sequnlock_excl(&fs->seq); + task_unlock(tsk); + if (kill) + free_fs_struct(fs); + } +} + +struct fs_struct *copy_fs_struct(struct fs_struct *old) +{ + struct fs_struct *fs = kmem_cache_alloc(fs_cachep, GFP_KERNEL); + /* We don't need to lock fs - think why ;-) */ + if (fs) { + fs->users = 1; + fs->in_exec = 0; + seqlock_init(&fs->seq); + fs->umask = old->umask; + + read_seqlock_excl(&old->seq); + fs->root = old->root; + path_get(&fs->root); + fs->pwd = old->pwd; + path_get(&fs->pwd); + read_sequnlock_excl(&old->seq); + } + return fs; +} + +int unshare_fs_struct(void) +{ + struct fs_struct *fs = current->fs; + struct fs_struct *new_fs = copy_fs_struct(fs); + int kill; + + if (!new_fs) + return -ENOMEM; + + task_lock(current); + read_seqlock_excl(&fs->seq); + kill = !--fs->users; + current->fs = new_fs; + read_sequnlock_excl(&fs->seq); + task_unlock(current); + + if (kill) + free_fs_struct(fs); + + return 0; +} +EXPORT_SYMBOL_GPL(unshare_fs_struct); + +/* to be mentioned only in INIT_TASK */ +struct fs_struct init_fs = { + .users = 1, + .seq = __SEQLOCK_UNLOCKED(init_fs.seq), + .umask = 0022, +}; -- cgit v1.3.1