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, 120 insertions, 0 deletions

diff --git a/include/net/gue.h b/include/net/gue.h
new file mode 100644
index 000000000..caefd6da8
--- /dev/null
+++ b/include/net/gue.h
@@ -0,0 +1,120 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef __NET_GUE_H
+#define __NET_GUE_H
+
+/* Definitions for the GUE header, standard and private flags, lengths
+ * of optional fields are below.
+ *
+ * Diagram of GUE header:
+ *
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |Ver|C|  Hlen   | Proto/ctype   |        Standard flags       |P|
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                                                               |
+ * ~                      Fields (optional)                        ~
+ * |                                                               |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |            Private flags (optional, P bit is set)             |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ * |                                                               |
+ * ~                   Private fields (optional)                   ~
+ * |                                                               |
+ * +-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+-+
+ *
+ * C bit indicates control message when set, data message when unset.
+ * For a control message, proto/ctype is interpreted as a type of
+ * control message. For data messages, proto/ctype is the IP protocol
+ * of the next header.
+ *
+ * P bit indicates private flags field is present. The private flags
+ * may refer to options placed after this field.
+ */
+
+#include <asm/byteorder.h>
+#include <linux/types.h>
+
+struct guehdr {
+	union {
+		struct {
+#if defined(__LITTLE_ENDIAN_BITFIELD)
+			__u8	hlen:5,
+				control:1,
+				version:2;
+#elif defined (__BIG_ENDIAN_BITFIELD)
+			__u8	version:2,
+				control:1,
+				hlen:5;
+#else
+#error  "Please fix <asm/byteorder.h>"
+#endif
+			__u8	proto_ctype;
+			__be16	flags;
+		};
+		__be32	word;
+	};
+};
+
+/* Standard flags in GUE header */
+
+#define GUE_FLAG_PRIV	htons(1<<0)	/* Private flags are in options */
+#define GUE_LEN_PRIV	4
+
+#define GUE_FLAGS_ALL	(GUE_FLAG_PRIV)
+
+/* Private flags in the private option extension */
+
+#define GUE_PFLAG_REMCSUM	htonl(1U << 31)
+#define GUE_PLEN_REMCSUM	4
+
+#define GUE_PFLAGS_ALL	(GUE_PFLAG_REMCSUM)
+
+/* Functions to compute options length corresponding to flags.
+ * If we ever have a lot of flags this can be potentially be
+ * converted to a more optimized algorithm (table lookup
+ * for instance).
+ */
+static inline size_t guehdr_flags_len(__be16 flags)
+{
+	return ((flags & GUE_FLAG_PRIV) ? GUE_LEN_PRIV : 0);
+}
+
+static inline size_t guehdr_priv_flags_len(__be32 flags)
+{
+	return (flags & GUE_PFLAG_REMCSUM) ? GUE_PLEN_REMCSUM : 0;
+}
+
+/* Validate standard and private flags. Returns non-zero (meaning invalid)
+ * if there is an unknown standard or private flags, or the options length for
+ * the flags exceeds the options length specific in hlen of the GUE header.
+ */
+static inline int validate_gue_flags(struct guehdr *guehdr, size_t optlen)
+{
+	__be16 flags = guehdr->flags;
+	size_t len;
+
+	if (flags & ~GUE_FLAGS_ALL)
+		return 1;
+
+	len = guehdr_flags_len(flags);
+	if (len > optlen)
+		return 1;
+
+	if (flags & GUE_FLAG_PRIV) {
+		/* Private flags are last four bytes accounted in
+		 * guehdr_flags_len
+		 */
+		__be32 pflags = *(__be32 *)((void *)&guehdr[1] +
+					    len - GUE_LEN_PRIV);
+
+		if (pflags & ~GUE_PFLAGS_ALL)
+			return 1;
+
+		len += guehdr_priv_flags_len(pflags);
+		if (len > optlen)
+			return 1;
+	}
+
+	return 0;
+}
+
+#endif