M5 step 1: build OpenBSD hfsc/fq_codel back ends into pf.ko (ml_* API, ifq_q handshake, scheduler types); priq still attached, 14/14 suite unchanged

module/include/pfk.h

@@ -1212,5 +1212,94 @@ struct pfk_pflog_stat {
 };
 #define PFKIOCGETPFLOGSTAT	_IOR('L', 1, struct pfk_pflog_stat)
 
+
+/*
+ * Pieces the staged scheduler back ends (fq_codel(4)/hfsc(4) ports) need from
+ * OpenBSD <net/if_var.h>, <net/if_fq_codel.h> and <net/if_hfsc.h>.
+ */
+#ifndef nsecuptime
+#define nsecuptime()	 getnsecuptime()
+#endif
+
+struct fqcodel_pktcntr { uint64_t packets; uint64_t bytes; };
+struct hfsc_pktcntr	 { uint64_t packets; uint64_t bytes; };
+
+struct fqcodel_stats {
+	struct fqcodel_pktcntr xmit_cnt;
+	struct fqcodel_pktcntr drop_cnt;
+	uint32_t	 target, interval, tc_interval_drop;
+	uint32_t	 rcvtime, mtu, qlimit, qlength;
+	uint64_t	 delaysum, delaysumsq;
+	uint8_t		 ecn, limit, flows, lscroll, flags;
+};
+
+/* ifq scheduler hand-off (see pfsrc/ifq.c): enter returns the scheduler's
+ * queue when it owns the interface queue, NULL otherwise. */
+void	*ifq_q_enter(struct ifqueue *, const struct ifq_ops *);
+void	 ifq_q_leave(struct ifqueue *, void *);
+
+
+/*
+ * OpenBSD <net/if_hfsc.h> pieces the staged hfsc(4) back end needs.
+ * PFLINUX: the port keeps the BSD scheduler sources verbatim, so the
+ * user-visible service curve, the class-stats record and the class-table
+ * limits live here instead of in a separate kernel header.
+ */
+struct hfsc_sc {				/* user-supplied service curve */
+	u_int64_t	m1;			/* slope1 (bytes/sec) */
+	u_int64_t	d;			/* ordinate of the knee (us) */
+	u_int64_t	m2;			/* slope2 (bytes/sec) */
+};
+
+struct hfsc_class_stats {
+	u_int		class_id;
+	u_int32_t	class_handle;
+	struct hfsc_sc	rsc, fsc, usc;
+	u_int64_t	total, cumul;
+	u_int64_t	d, e, vt, f;
+	u_int64_t	initvt, vtperiod, parentperiod;
+	int		nactive;
+	u_int64_t	vtoff, cvtmax, myf, cfmin, cvtmin, myfadj, vtadj;
+	u_int		period;
+	struct hfsc_pktcntr xmit_cnt, drop_cnt;
+	u_int64_t	cur_time;
+	u_int64_t	machclk_freq;
+	int		qlength;
+	int		qlimit;
+	int		qtype;
+};
+
+/* OpenBSD's global nanoseconds-per-clocktick (HFSC_CLK_PER_TICK).  The port
+ * has no clock_rate machinery, so derive it from the kernel's HZ. */
+#ifndef tick_nsec
+#define tick_nsec		(1000000000LL / HZ)
+#endif
+
+#define HFSC_ROOT_CLASS		0x1		/* root class of the tree */
+#define HFSC_DEFAULTCLASS	0x8		/* auto-created default class */
+#define HFSC_MAX_CLASSES	64
+#define HFSC_DEFAULT_CLASSES	8
+#define HFSC_DEFAULT_QLIMIT	1000
+
+/*
+ * PFLINUX notes on the scheduler back ends:
+ *
+ * - splnet()/splx(): OpenBSD raises the software interrupt level around
+ *   class-table surgery.  This port runs the whole data path in one ordered
+ *   work queue and guards the queue with ifq_mtx, so these are no-ops; they
+ *   are kept as markers of the critical regions.
+ * - KERNEL_ASSERT_LOCKED(): the schedulers are only reached from ifq/pf paths
+ *   that already hold the queue mutex; asserted structurally, not by spl.
+ * - HFSC_ENABLED(): the scheduler owns the interface queue once it attached
+ *   its private state through ifq_q_enter().
+ */
+#define splnet()		0
+#define splx(s)			((void)(s))
+#define KERNEL_ASSERT_LOCKED()	do { } while (0)
+#define HFSC_ENABLED(_ifq)	((_ifq)->ifq_q != NULL)
+
+#define PKTCNTR_INC(_c, _len)	do { (_c)->packets++; (_c)->bytes += (_len); } \
+				  while (0)
+
 #endif /* _PFK_H */
 

module/include/pfk_if.h

@@ -74,6 +74,79 @@ ml_dequeue(struct mbuf_list *ml)
 	return m;
 }
 
+
+/* BSD <net/if_var.h> mbuf_list helpers (net/if_var.h ml_*) */
+static inline void
+ml_init(struct mbuf_list *ml)
+{
+	ml->ml_first = ml->ml_last = NULL;
+	ml->ml_len = 0;
+}
+
+static inline void
+ml_enqueue(struct mbuf_list *ml, struct mbuf *m)
+{
+	m->m_next = NULL;
+	if (ml->ml_last == NULL)
+		ml->ml_first = m;
+	else
+		ml->ml_last->m_next = m;
+	ml->ml_last = m;
+	ml->ml_len++;
+}
+
+static inline struct mbuf *
+ml_dequeue_tail(struct mbuf_list *ml)
+{
+	struct mbuf *m, *prev = NULL;
+
+	if (ml->ml_first == NULL)
+		return NULL;
+	for (m = ml->ml_first; m->m_next; m = m->m_next)
+		prev = m;
+	if (prev == NULL)			/* single element */
+		ml->ml_first = NULL;
+	else
+		prev->m_next = NULL;
+	ml->ml_last = prev;
+	ml->ml_len--;
+	m->m_next = NULL;
+	return m;
+}
+
+/* append every packet in m2 to m1 (m2 becomes empty) */
+static inline void
+ml_enlist(struct mbuf_list *m1, struct mbuf_list *m2)
+{
+	if (m2->ml_first == NULL)
+		return;
+	if (m1->ml_last == NULL)
+		m1->ml_first = m2->ml_first;
+	else
+		m1->ml_last->m_next = m2->ml_first;
+	m1->ml_last = m2->ml_last;
+	m1->ml_len += m2->ml_len;
+	m2->ml_first = m2->ml_last = NULL;
+	m2->ml_len = 0;
+}
+
+static inline unsigned int
+ml_len(const struct mbuf_list *ml)
+{
+	return (unsigned int)ml->ml_len;
+}
+
+static inline int
+ml_empty(const struct mbuf_list *ml)
+{
+	return ml->ml_first == NULL;
+}
+
+void	ml_purge(struct mbuf_list *ml);	/* compat/pfk_mbuf.c (needs m_freem) */
+
+#define MBUF_LIST_FIRST(_ml)		((_ml)->ml_first)
+#define MBUF_LIST_INITIALIZER()		{ NULL, NULL, 0 }
+
 /* egress interface (default-route dev), maintained on fib/net events */
 struct pfk_ifnet *pfk_egress_if(void);
 void pfk_egress_refresh(void);

module/include/pfk_mbuf.h

@@ -73,7 +73,7 @@ struct pkthdr {
 	u_int32_t		 ph_flowid;
 	u_int			 ph_ifidx;
 	u_int			 ph_rtableid;
-	struct pfk_timeval	 ph_timestamp;
+	int64_t			 ph_timestamp;	/* OpenBSD 8.0: nanoseconds */
 	struct pfk_ifnet	*ifp;
 	struct pfk_ifnet	*rcvif;
 	u_short			 ph;		/* tso segs: unused, kept as pad */