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, 81 insertions, 0 deletions

diff --git a/lib/usercopy.c b/lib/usercopy.c
new file mode 100644
index 000000000..e2f0bf104
--- /dev/null
+++ b/lib/usercopy.c
@@ -0,0 +1,81 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <linux/errno.h>
+#include <linux/export.h>
+#include <linux/fault-inject-usercopy.h>
+#include <linux/instrumented.h>
+#include <linux/kernel.h>
+#include <linux/nospec.h>
+#include <linux/string.h>
+#include <linux/uaccess.h>
+#include <linux/wordpart.h>
+
+/* out-of-line parts */
+
+#if !defined(INLINE_COPY_USER)
+unsigned long _copy_from_user(void *to, const void __user *from, unsigned long n)
+{
+	return _inline_copy_from_user(to, from, n);
+}
+EXPORT_SYMBOL(_copy_from_user);
+
+unsigned long _copy_to_user(void __user *to, const void *from, unsigned long n)
+{
+	return _inline_copy_to_user(to, from, n);
+}
+EXPORT_SYMBOL(_copy_to_user);
+#endif
+
+/**
+ * check_zeroed_user: check if a userspace buffer only contains zero bytes
+ * @from: Source address, in userspace.
+ * @size: Size of buffer.
+ *
+ * This is effectively shorthand for "memchr_inv(from, 0, size) == NULL" for
+ * userspace addresses (and is more efficient because we don't care where the
+ * first non-zero byte is).
+ *
+ * Returns:
+ *  * 0: There were non-zero bytes present in the buffer.
+ *  * 1: The buffer was full of zero bytes.
+ *  * -EFAULT: access to userspace failed.
+ */
+int check_zeroed_user(const void __user *from, size_t size)
+{
+	unsigned long val;
+	uintptr_t align = (uintptr_t) from % sizeof(unsigned long);
+
+	if (unlikely(size == 0))
+		return 1;
+
+	from -= align;
+	size += align;
+
+	if (!user_read_access_begin(from, size))
+		return -EFAULT;
+
+	unsafe_get_user(val, (unsigned long __user *) from, err_fault);
+	if (align)
+		val &= ~aligned_byte_mask(align);
+
+	while (size > sizeof(unsigned long)) {
+		if (unlikely(val))
+			goto done;
+
+		from += sizeof(unsigned long);
+		size -= sizeof(unsigned long);
+
+		unsafe_get_user(val, (unsigned long __user *) from, err_fault);
+	}
+
+	if (size < sizeof(unsigned long))
+		val &= aligned_byte_mask(size);
+
+done:
+	user_read_access_end();
+	return (val == 0);
+err_fault:
+	user_read_access_end();
+	return -EFAULT;
+}
+EXPORT_SYMBOL(check_zeroed_user);