Merge branch 'taprio-Some-fixes'

Vinicius Costa Gomes says:

====================
taprio: Some fixes

Changes from v3:
  - Replaced ENOTSUPP error code with EOPNOTSUPP (Jakub Kicinski);
  - Added the missing policy validation for the flags netlink argument
    (Jakub Kicinski);
  - Fixed the destroy() flow to also destroy the priority to traffic
    class mapping (David Miller);
  - Fixed dropping packets when taprio offloading is used together
    with ETF offloading (more on this below);

Changes from v2:
  - Squashed commits 2/3 and 3/3 into a single one (I think a single
    commit is going to be easier to review);
  - Removed an "improvement" that was causing changes in user visible
    behavior;

Changes from v1:
  - Fixed ignoring the 'flags' argument when adding a new
    instance (Vladimir Oltean);
  - Changed the order of commits;

Updated cover letter:

One bit that might need some attention is the fix for not dropping all
packets when taprio and ETF offloading are used, patch 5/5. The
behavior when the fix is applied is that packets that have a 'txtime'
that would fall outside of their transmission window are now dropped
by taprio. The question that might be raised is: should taprio be
responsible for dropping these packets, or should it be handled lower
in the stack?

My opinion is: taprio has all the information, and it's able to give
feeback to the user. Lower in the stack, those packets might go into
the void, and the only feedback could be a hard to find counter
increasing.

Patch 1/5: Reported by Po Liu, is more of a improvement of usability for
drivers implementing offloading features, now they can rely on the
value of dev->num_tc, instead of going through some hops to get this
value.

Patch 2/5: Use 'q->flags' as the source of truth for the offloading
flags. Tries to solidify the current behavior, while avoiding going
into invalid states, one of which was causing a "rcu stall" (more
information in the commit message).

Patch 3/5: Adds the missing netlink attribute validation for
TCA_TAPRIO_ATTR_FLAGS.

Patch 4/5: Replaces the usage of netdev_set_num_tc() with
netdev_reset_tc() in taprio_destroy(), taprio_destroy() is called when
applying a configuration fails, making sure that the device traffic
class configuration goes back to the default state.

@Vladimir: If possible, I would appreciate your Ack on patch 2/5. I
have been looking at this code for so long that I might have missed
something obvious (and my growing dislike for the word 'flags' may be
affecting my judgement :-).
====================

Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 57 insertions, 35 deletions

diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index c609373c866181..660fc45ee40fc0 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -31,6 +31,7 @@ static DEFINE_SPINLOCK(taprio_list_lock);
 
 #define TXTIME_ASSIST_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_TXTIME_ASSIST)
 #define FULL_OFFLOAD_IS_ENABLED(flags) ((flags) & TCA_TAPRIO_ATTR_FLAG_FULL_OFFLOAD)
+#define TAPRIO_FLAGS_INVALID U32_MAX
 
 struct sched_entry {
 	struct list_head list;
@@ -766,6 +767,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_SCHED_CLOCKID]              = { .type = NLA_S32 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME]           = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
+	[TCA_TAPRIO_ATTR_FLAGS]                      = { .type = NLA_U32 },
 };
 
 static int fill_sched_entry(struct nlattr **tb, struct sched_entry *entry,
@@ -1367,6 +1369,33 @@ static int taprio_mqprio_cmp(const struct net_device *dev,
 	return 0;
 }
 
+/* The semantics of the 'flags' argument in relation to 'change()'
+ * requests, are interpreted following two rules (which are applied in
+ * this order): (1) an omitted 'flags' argument is interpreted as
+ * zero; (2) the 'flags' of a "running" taprio instance cannot be
+ * changed.
+ */
+static int taprio_new_flags(const struct nlattr *attr, u32 old,
+			    struct netlink_ext_ack *extack)
+{
+	u32 new = 0;
+
+	if (attr)
+		new = nla_get_u32(attr);
+
+	if (old != TAPRIO_FLAGS_INVALID && old != new) {
+		NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported");
+		return -EOPNOTSUPP;
+	}
+
+	if (!taprio_flags_valid(new)) {
+		NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid");
+		return -EINVAL;
+	}
+
+	return new;
+}
+
 static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 			 struct netlink_ext_ack *extack)
 {
@@ -1375,7 +1404,6 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	struct taprio_sched *q = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
 	struct tc_mqprio_qopt *mqprio = NULL;
-	u32 taprio_flags = 0;
 	unsigned long flags;
 	ktime_t start;
 	int i, err;
@@ -1388,21 +1416,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 	if (tb[TCA_TAPRIO_ATTR_PRIOMAP])
 		mqprio = nla_data(tb[TCA_TAPRIO_ATTR_PRIOMAP]);
 
-	if (tb[TCA_TAPRIO_ATTR_FLAGS]) {
-		taprio_flags = nla_get_u32(tb[TCA_TAPRIO_ATTR_FLAGS]);
-
-		if (q->flags != 0 && q->flags != taprio_flags) {
-			NL_SET_ERR_MSG_MOD(extack, "Changing 'flags' of a running schedule is not supported");
-			return -EOPNOTSUPP;
-		} else if (!taprio_flags_valid(taprio_flags)) {
-			NL_SET_ERR_MSG_MOD(extack, "Specified 'flags' are not valid");
-			return -EINVAL;
-		}
+	err = taprio_new_flags(tb[TCA_TAPRIO_ATTR_FLAGS],
+			       q->flags, extack);
+	if (err < 0)
+		return err;
 
-		q->flags = taprio_flags;
-	}
+	q->flags = err;
 
-	err = taprio_parse_mqprio_opt(dev, mqprio, extack, taprio_flags);
+	err = taprio_parse_mqprio_opt(dev, mqprio, extack, q->flags);
 	if (err < 0)
 		return err;
 
@@ -1444,7 +1465,20 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 
 	taprio_set_picos_per_byte(dev, q);
 
-	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
+	if (mqprio) {
+		netdev_set_num_tc(dev, mqprio->num_tc);
+		for (i = 0; i < mqprio->num_tc; i++)
+			netdev_set_tc_queue(dev, i,
+					    mqprio->count[i],
+					    mqprio->offset[i]);
+
+		/* Always use supplied priority mappings */
+		for (i = 0; i <= TC_BITMASK; i++)
+			netdev_set_prio_tc_map(dev, i,
+					       mqprio->prio_tc_map[i]);
+	}
+
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags))
 		err = taprio_enable_offload(dev, mqprio, q, new_admin, extack);
 	else
 		err = taprio_disable_offload(dev, q, extack);
@@ -1464,27 +1498,14 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		q->txtime_delay = nla_get_u32(tb[TCA_TAPRIO_ATTR_TXTIME_DELAY]);
 	}
 
-	if (!TXTIME_ASSIST_IS_ENABLED(taprio_flags) &&
-	    !FULL_OFFLOAD_IS_ENABLED(taprio_flags) &&
+	if (!TXTIME_ASSIST_IS_ENABLED(q->flags) &&
+	    !FULL_OFFLOAD_IS_ENABLED(q->flags) &&
 	    !hrtimer_active(&q->advance_timer)) {
 		hrtimer_init(&q->advance_timer, q->clockid, HRTIMER_MODE_ABS);
 		q->advance_timer.function = advance_sched;
 	}
 
-	if (mqprio) {
-		netdev_set_num_tc(dev, mqprio->num_tc);
-		for (i = 0; i < mqprio->num_tc; i++)
-			netdev_set_tc_queue(dev, i,
-					    mqprio->count[i],
-					    mqprio->offset[i]);
-
-		/* Always use supplied priority mappings */
-		for (i = 0; i <= TC_BITMASK; i++)
-			netdev_set_prio_tc_map(dev, i,
-					       mqprio->prio_tc_map[i]);
-	}
-
-	if (FULL_OFFLOAD_IS_ENABLED(taprio_flags)) {
+	if (FULL_OFFLOAD_IS_ENABLED(q->flags)) {
 		q->dequeue = taprio_dequeue_offload;
 		q->peek = taprio_peek_offload;
 	} else {
@@ -1501,9 +1522,9 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 		goto unlock;
 	}
 
-	if (TXTIME_ASSIST_IS_ENABLED(taprio_flags)) {
-		setup_txtime(q, new_admin, start);
+	setup_txtime(q, new_admin, start);
 
+	if (TXTIME_ASSIST_IS_ENABLED(q->flags)) {
 		if (!oper) {
 			rcu_assign_pointer(q->oper_sched, new_admin);
 			err = 0;
@@ -1528,7 +1549,7 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 
 		spin_unlock_irqrestore(&q->current_entry_lock, flags);
 
-		if (FULL_OFFLOAD_IS_ENABLED(taprio_flags))
+		if (FULL_OFFLOAD_IS_ENABLED(q->flags))
 			taprio_offload_config_changed(q);
 	}
 
@@ -1567,7 +1588,7 @@ static void taprio_destroy(struct Qdisc *sch)
 	}
 	q->qdiscs = NULL;
 
-	netdev_set_num_tc(dev, 0);
+	netdev_reset_tc(dev);
 
 	if (q->oper_sched)
 		call_rcu(&q->oper_sched->rcu, taprio_free_sched_cb);
@@ -1597,6 +1618,7 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	 * and get the valid one on taprio_change().
 	 */
 	q->clockid = -1;
+	q->flags = TAPRIO_FLAGS_INVALID;
 
 	spin_lock(&taprio_list_lock);
 	list_add(&q->taprio_list, &taprio_list);