1 files changed, 169 insertions, 27 deletions

diff --git a/net/sched/sch_mqprio.c b/net/sched/sch_mqprio.c
index 48ed87b91086..dc5a0ff50b14 100644
--- a/net/sched/sch_mqprio.c
+++ b/net/sched/sch_mqprio.c
@@ -5,6 +5,7 @@
  * Copyright (c) 2010 John Fastabend <john.r.fastabend@intel.com>
  */
 
+#include <linux/ethtool_netlink.h>
 #include <linux/types.h>
 #include <linux/slab.h>
 #include <linux/kernel.h>
@@ -27,15 +28,19 @@ struct mqprio_sched {
 	u32 flags;
 	u64 min_rate[TC_QOPT_MAX_QUEUE];
 	u64 max_rate[TC_QOPT_MAX_QUEUE];
+	u32 fp[TC_QOPT_MAX_QUEUE];
 };
 
 static int mqprio_enable_offload(struct Qdisc *sch,
 				 const struct tc_mqprio_qopt *qopt,
 				 struct netlink_ext_ack *extack)
 {
-	struct tc_mqprio_qopt_offload mqprio = {.qopt = *qopt};
 	struct mqprio_sched *priv = qdisc_priv(sch);
 	struct net_device *dev = qdisc_dev(sch);
+	struct tc_mqprio_qopt_offload mqprio = {
+		.qopt = *qopt,
+		.extack = extack,
+	};
 	int err, i;
 
 	switch (priv->mode) {
@@ -60,6 +65,8 @@ static int mqprio_enable_offload(struct Qdisc *sch,
 		return -EINVAL;
 	}
 
+	mqprio_fp_to_offload(priv->fp, &mqprio);
+
 	err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_QDISC_MQPRIO,
 					    &mqprio);
 	if (err)
@@ -133,91 +140,193 @@ static int mqprio_parse_opt(struct net_device *dev, struct tc_mqprio_qopt *qopt,
 	/* If ndo_setup_tc is not present then hardware doesn't support offload
 	 * and we should return an error.
 	 */
-	if (qopt->hw && !dev->netdev_ops->ndo_setup_tc)
+	if (qopt->hw && !dev->netdev_ops->ndo_setup_tc) {
+		NL_SET_ERR_MSG(extack,
+			       "Device does not support hardware offload");
 		return -EINVAL;
+	}
 
 	return 0;
 }
 
+static const struct
+nla_policy mqprio_tc_entry_policy[TCA_MQPRIO_TC_ENTRY_MAX + 1] = {
+	[TCA_MQPRIO_TC_ENTRY_INDEX]	= NLA_POLICY_MAX(NLA_U32,
+							 TC_QOPT_MAX_QUEUE),
+	[TCA_MQPRIO_TC_ENTRY_FP]	= NLA_POLICY_RANGE(NLA_U32,
+							   TC_FP_EXPRESS,
+							   TC_FP_PREEMPTIBLE),
+};
+
 static const struct nla_policy mqprio_policy[TCA_MQPRIO_MAX + 1] = {
 	[TCA_MQPRIO_MODE]	= { .len = sizeof(u16) },
 	[TCA_MQPRIO_SHAPER]	= { .len = sizeof(u16) },
 	[TCA_MQPRIO_MIN_RATE64]	= { .type = NLA_NESTED },
 	[TCA_MQPRIO_MAX_RATE64]	= { .type = NLA_NESTED },
+	[TCA_MQPRIO_TC_ENTRY]	= { .type = NLA_NESTED },
 };
 
-static int parse_attr(struct nlattr *tb[], int maxtype, struct nlattr *nla,
-		      const struct nla_policy *policy, int len)
+static int mqprio_parse_tc_entry(u32 fp[TC_QOPT_MAX_QUEUE],
+				 struct nlattr *opt,
+				 unsigned long *seen_tcs,
+				 struct netlink_ext_ack *extack)
 {
-	int nested_len = nla_len(nla) - NLA_ALIGN(len);
+	struct nlattr *tb[TCA_MQPRIO_TC_ENTRY_MAX + 1];
+	int err, tc;
+
+	err = nla_parse_nested(tb, TCA_MQPRIO_TC_ENTRY_MAX, opt,
+			       mqprio_tc_entry_policy, extack);
+	if (err < 0)
+		return err;
+
+	if (NL_REQ_ATTR_CHECK(extack, opt, tb, TCA_MQPRIO_TC_ENTRY_INDEX)) {
+		NL_SET_ERR_MSG(extack, "TC entry index missing");
+		return -EINVAL;
+	}
+
+	tc = nla_get_u32(tb[TCA_MQPRIO_TC_ENTRY_INDEX]);
+	if (*seen_tcs & BIT(tc)) {
+		NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_TC_ENTRY_INDEX],
+				    "Duplicate tc entry");
+		return -EINVAL;
+	}
+
+	*seen_tcs |= BIT(tc);
 
-	if (nested_len >= nla_attr_size(0))
-		return nla_parse_deprecated(tb, maxtype,
-					    nla_data(nla) + NLA_ALIGN(len),
-					    nested_len, policy, NULL);
+	if (tb[TCA_MQPRIO_TC_ENTRY_FP])
+		fp[tc] = nla_get_u32(tb[TCA_MQPRIO_TC_ENTRY_FP]);
 
-	memset(tb, 0, sizeof(struct nlattr *) * (maxtype + 1));
 	return 0;
 }
 
+static int mqprio_parse_tc_entries(struct Qdisc *sch, struct nlattr *nlattr_opt,
+				   int nlattr_opt_len,
+				   struct netlink_ext_ack *extack)
+{
+	struct mqprio_sched *priv = qdisc_priv(sch);
+	struct net_device *dev = qdisc_dev(sch);
+	bool have_preemption = false;
+	unsigned long seen_tcs = 0;
+	u32 fp[TC_QOPT_MAX_QUEUE];
+	struct nlattr *n;
+	int tc, rem;
+	int err = 0;
+
+	for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++)
+		fp[tc] = priv->fp[tc];
+
+	nla_for_each_attr(n, nlattr_opt, nlattr_opt_len, rem) {
+		if (nla_type(n) != TCA_MQPRIO_TC_ENTRY)
+			continue;
+
+		err = mqprio_parse_tc_entry(fp, n, &seen_tcs, extack);
+		if (err)
+			goto out;
+	}
+
+	for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) {
+		priv->fp[tc] = fp[tc];
+		if (fp[tc] == TC_FP_PREEMPTIBLE)
+			have_preemption = true;
+	}
+
+	if (have_preemption && !ethtool_dev_mm_supported(dev)) {
+		NL_SET_ERR_MSG(extack, "Device does not support preemption");
+		return -EOPNOTSUPP;
+	}
+out:
+	return err;
+}
+
+/* Parse the other netlink attributes that represent the payload of
+ * TCA_OPTIONS, which are appended right after struct tc_mqprio_qopt.
+ */
 static int mqprio_parse_nlattr(struct Qdisc *sch, struct tc_mqprio_qopt *qopt,
-			       struct nlattr *opt)
+			       struct nlattr *opt,
+			       struct netlink_ext_ack *extack)
 {
+	struct nlattr *nlattr_opt = nla_data(opt) + NLA_ALIGN(sizeof(*qopt));
+	int nlattr_opt_len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt));
 	struct mqprio_sched *priv = qdisc_priv(sch);
-	struct nlattr *tb[TCA_MQPRIO_MAX + 1];
+	struct nlattr *tb[TCA_MQPRIO_MAX + 1] = {};
 	struct nlattr *attr;
 	int i, rem, err;
 
-	err = parse_attr(tb, TCA_MQPRIO_MAX, opt, mqprio_policy,
-			 sizeof(*qopt));
-	if (err < 0)
-		return err;
+	if (nlattr_opt_len >= nla_attr_size(0)) {
+		err = nla_parse_deprecated(tb, TCA_MQPRIO_MAX, nlattr_opt,
+					   nlattr_opt_len, mqprio_policy,
+					   NULL);
+		if (err < 0)
+			return err;
+	}
 
-	if (!qopt->hw)
+	if (!qopt->hw) {
+		NL_SET_ERR_MSG(extack,
+			       "mqprio TCA_OPTIONS can only contain netlink attributes in hardware mode");
 		return -EINVAL;
+	}
 
 	if (tb[TCA_MQPRIO_MODE]) {
 		priv->flags |= TC_MQPRIO_F_MODE;
-		priv->mode = *(u16 *)nla_data(tb[TCA_MQPRIO_MODE]);
+		priv->mode = nla_get_u16(tb[TCA_MQPRIO_MODE]);
 	}
 
 	if (tb[TCA_MQPRIO_SHAPER]) {
 		priv->flags |= TC_MQPRIO_F_SHAPER;
-		priv->shaper = *(u16 *)nla_data(tb[TCA_MQPRIO_SHAPER]);
+		priv->shaper = nla_get_u16(tb[TCA_MQPRIO_SHAPER]);
 	}
 
 	if (tb[TCA_MQPRIO_MIN_RATE64]) {
-		if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+		if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MIN_RATE64],
+					    "min_rate accepted only when shaper is in bw_rlimit mode");
 			return -EINVAL;
+		}
 		i = 0;
 		nla_for_each_nested(attr, tb[TCA_MQPRIO_MIN_RATE64],
 				    rem) {
-			if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64)
+			if (nla_type(attr) != TCA_MQPRIO_MIN_RATE64) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "Attribute type expected to be TCA_MQPRIO_MIN_RATE64");
 				return -EINVAL;
+			}
 			if (i >= qopt->num_tc)
 				break;
-			priv->min_rate[i] = *(u64 *)nla_data(attr);
+			priv->min_rate[i] = nla_get_u64(attr);
 			i++;
 		}
 		priv->flags |= TC_MQPRIO_F_MIN_RATE;
 	}
 
 	if (tb[TCA_MQPRIO_MAX_RATE64]) {
-		if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE)
+		if (priv->shaper != TC_MQPRIO_SHAPER_BW_RATE) {
+			NL_SET_ERR_MSG_ATTR(extack, tb[TCA_MQPRIO_MAX_RATE64],
+					    "max_rate accepted only when shaper is in bw_rlimit mode");
 			return -EINVAL;
+		}
 		i = 0;
 		nla_for_each_nested(attr, tb[TCA_MQPRIO_MAX_RATE64],
 				    rem) {
-			if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64)
+			if (nla_type(attr) != TCA_MQPRIO_MAX_RATE64) {
+				NL_SET_ERR_MSG_ATTR(extack, attr,
+						    "Attribute type expected to be TCA_MQPRIO_MAX_RATE64");
 				return -EINVAL;
+			}
 			if (i >= qopt->num_tc)
 				break;
-			priv->max_rate[i] = *(u64 *)nla_data(attr);
+			priv->max_rate[i] = nla_get_u64(attr);
 			i++;
 		}
 		priv->flags |= TC_MQPRIO_F_MAX_RATE;
 	}
 
+	if (tb[TCA_MQPRIO_TC_ENTRY]) {
+		err = mqprio_parse_tc_entries(sch, nlattr_opt, nlattr_opt_len,
+					      extack);
+		if (err)
+			return err;
+	}
+
 	return 0;
 }
 
@@ -231,7 +340,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
 	int i, err = -EOPNOTSUPP;
 	struct tc_mqprio_qopt *qopt = NULL;
 	struct tc_mqprio_caps caps;
-	int len;
+	int len, tc;
 
 	BUILD_BUG_ON(TC_MAX_QUEUE != TC_QOPT_MAX_QUEUE);
 	BUILD_BUG_ON(TC_BITMASK != TC_QOPT_BITMASK);
@@ -249,6 +358,9 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
 	if (!opt || nla_len(opt) < sizeof(*qopt))
 		return -EINVAL;
 
+	for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++)
+		priv->fp[tc] = TC_FP_EXPRESS;
+
 	qdisc_offload_query_caps(dev, TC_SETUP_QDISC_MQPRIO,
 				 &caps, sizeof(caps));
 
@@ -258,7 +370,7 @@ static int mqprio_init(struct Qdisc *sch, struct nlattr *opt,
 
 	len = nla_len(opt) - NLA_ALIGN(sizeof(*qopt));
 	if (len > 0) {
-		err = mqprio_parse_nlattr(sch, qopt, opt);
+		err = mqprio_parse_nlattr(sch, qopt, opt, extack);
 		if (err)
 			return err;
 	}
@@ -399,6 +511,33 @@ nla_put_failure:
 	return -1;
 }
 
+static int mqprio_dump_tc_entries(struct mqprio_sched *priv,
+				  struct sk_buff *skb)
+{
+	struct nlattr *n;
+	int tc;
+
+	for (tc = 0; tc < TC_QOPT_MAX_QUEUE; tc++) {
+		n = nla_nest_start(skb, TCA_MQPRIO_TC_ENTRY);
+		if (!n)
+			return -EMSGSIZE;
+
+		if (nla_put_u32(skb, TCA_MQPRIO_TC_ENTRY_INDEX, tc))
+			goto nla_put_failure;
+
+		if (nla_put_u32(skb, TCA_MQPRIO_TC_ENTRY_FP, priv->fp[tc]))
+			goto nla_put_failure;
+
+		nla_nest_end(skb, n);
+	}
+
+	return 0;
+
+nla_put_failure:
+	nla_nest_cancel(skb, n);
+	return -EMSGSIZE;
+}
+
 static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 {
 	struct net_device *dev = qdisc_dev(sch);
@@ -449,6 +588,9 @@ static int mqprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	    (dump_rates(priv, &opt, skb) != 0))
 		goto nla_put_failure;
 
+	if (mqprio_dump_tc_entries(priv, skb))
+		goto nla_put_failure;
+
 	return nla_nest_end(skb, nla);
 nla_put_failure:
 	nlmsg_trim(skb, nla);