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, 156 insertions, 0 deletions

diff --git a/lib/strncpy_from_user.c b/lib/strncpy_from_user.c
new file mode 100644
index 000000000..5bb752ff7
--- /dev/null
+++ b/lib/strncpy_from_user.c
@@ -0,0 +1,156 @@
+// SPDX-License-Identifier: GPL-2.0
+#include <linux/compiler.h>
+#include <linux/export.h>
+#include <linux/fault-inject-usercopy.h>
+#include <linux/kasan-checks.h>
+#include <linux/thread_info.h>
+#include <linux/uaccess.h>
+#include <linux/kernel.h>
+#include <linux/errno.h>
+#include <linux/mm.h>
+
+#include <asm/byteorder.h>
+#include <asm/word-at-a-time.h>
+
+#ifdef CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS
+#define IS_UNALIGNED(src, dst)	0
+#else
+#define IS_UNALIGNED(src, dst)	\
+	(((long) dst | (long) src) & (sizeof(long) - 1))
+#endif
+
+/*
+ * Do a strncpy, return length of string without final '\0'.
+ * 'count' is the user-supplied count (return 'count' if we
+ * hit it), 'max' is the address space maximum (and we return
+ * -EFAULT if we hit it).
+ */
+static __always_inline long do_strncpy_from_user(char *dst, const char __user *src,
+					unsigned long count, unsigned long max)
+{
+	const struct word_at_a_time constants = WORD_AT_A_TIME_CONSTANTS;
+	unsigned long res = 0;
+
+	if (IS_UNALIGNED(src, dst))
+		goto byte_at_a_time;
+
+	while (max >= sizeof(unsigned long)) {
+		unsigned long c, data, mask;
+
+		/* Fall back to byte-at-a-time if we get a page fault */
+		unsafe_get_user(c, (unsigned long __user *)(src+res), byte_at_a_time);
+
+		/*
+		 * Note that we mask out the bytes following the NUL. This is
+		 * important to do because string oblivious code may read past
+		 * the NUL. For those routines, we don't want to give them
+		 * potentially random bytes after the NUL in `src`.
+		 *
+		 * One example of such code is BPF map keys. BPF treats map keys
+		 * as an opaque set of bytes. Without the post-NUL mask, any BPF
+		 * maps keyed by strings returned from strncpy_from_user() may
+		 * have multiple entries for semantically identical strings.
+		 */
+		if (has_zero(c, &data, &constants)) {
+			data = prep_zero_mask(c, data, &constants);
+			data = create_zero_mask(data);
+			mask = zero_bytemask(data);
+			*(unsigned long *)(dst+res) = c & mask;
+			return res + find_zero(data);
+		}
+
+		*(unsigned long *)(dst+res) = c;
+
+		res += sizeof(unsigned long);
+		max -= sizeof(unsigned long);
+	}
+
+byte_at_a_time:
+	while (max) {
+		char c;
+
+		unsafe_get_user(c,src+res, efault);
+		dst[res] = c;
+		if (!c)
+			return res;
+		res++;
+		max--;
+	}
+
+	/*
+	 * Uhhuh. We hit 'max'. But was that the user-specified maximum
+	 * too? If so, that's ok - we got as much as the user asked for.
+	 */
+	if (res >= count)
+		return res;
+
+	/*
+	 * Nope: we hit the address space limit, and we still had more
+	 * characters the caller would have wanted. That's an EFAULT.
+	 */
+efault:
+	return -EFAULT;
+}
+
+/**
+ * strncpy_from_user: - Copy a NUL terminated string from userspace.
+ * @dst:   Destination address, in kernel space.  This buffer must be at
+ *         least @count bytes long.
+ * @src:   Source address, in user space.
+ * @count: Maximum number of bytes to copy, including the trailing NUL.
+ *
+ * Copies a NUL-terminated string from userspace to kernel space.
+ *
+ * On success, returns the length of the string (not including the trailing
+ * NUL).
+ *
+ * If access to userspace fails, returns -EFAULT (some data may have been
+ * copied).
+ *
+ * If @count is smaller than the length of the string, copies @count bytes
+ * and returns @count.
+ */
+long strncpy_from_user(char *dst, const char __user *src, long count)
+{
+	unsigned long max_addr, src_addr;
+
+	might_fault();
+	if (should_fail_usercopy())
+		return -EFAULT;
+	if (unlikely(count <= 0))
+		return 0;
+
+	kasan_check_write(dst, count);
+	check_object_size(dst, count, false);
+
+	if (can_do_masked_user_access()) {
+		long retval;
+
+		src = masked_user_read_access_begin(src);
+		retval = do_strncpy_from_user(dst, src, count, count);
+		user_read_access_end();
+		return retval;
+	}
+
+	max_addr = TASK_SIZE_MAX;
+	src_addr = (unsigned long)untagged_addr(src);
+	if (likely(src_addr < max_addr)) {
+		unsigned long max = max_addr - src_addr;
+		long retval;
+
+		/*
+		 * Truncate 'max' to the user-specified limit, so that
+		 * we only have one limit we need to check in the loop
+		 */
+		if (max > count)
+			max = count;
+
+		if (user_read_access_begin(src, max)) {
+			retval = do_strncpy_from_user(dst, src, count, max);
+			user_read_access_end();
+			return retval;
+		}
+	}
+	return -EFAULT;
+}
+EXPORT_SYMBOL(strncpy_from_user);