[RFC net-next v2 0/2] ethtool: Add support for frame preemption

[RFC net-next v2 0/2] ethtool: Add support for frame preemption

[Vinicius Costa Gomes]

Hi,

Changes from v1:
 - The per-queue preemptible/express setting is moved to applicable
   qdiscs (Jakub Kicinski and others);
 - "min-frag-size" now follows the 802.3br specification more closely,
   it's expressed as X in '64(1 + X) + 4' (Joergen Andreasen)

This is still an RFC because two main reasons, I want to confirm that
this approach (per-queue settings via qdiscs, device settings via
ethtool) looks good, even though there aren't much more options left ;-)
The other reason is that while testing this I found some weirdness
in the driver that I would need a bit more time to investigate.

(In case these patches are not enough to give an idea of how things
work, I can send the userspace patches, of course.)

The idea of this "hybrid" approach is that applications/users would do
the following steps to configure frame preemption:

$ tc qdisc replace dev $IFACE parent root handle 100 taprio \
      num_tc 3 \
      map 2 2 1 0 2 2 2 2 2 2 2 2 2 2 2 2 \
      queues 1@0 1@1 2@2 \
      base-time $BASE_TIME \
      sched-entry S 0f 10000000 \
      preempt 1110 \
      flags 0x2 

The "preempt" parameter is the only difference, it configures which
queues are marked as preemptible, in this example, queue 0 is marked
as "not preemptible", so it is express, the rest of the four queues
are preemptible.

The next step, of this example, would be to enable frame preemption in
the device, via ethtool, and set the minimum fragment size to 2:

$ sudo ./ethtool --set-frame-preemption $IFACE fp on min-frag-size 2


Cheers,


Vinicius Costa Gomes (2):
  ethtool: Add support for configuring frame preemption
  taprio: Add support for frame preemption offload

 include/linux/ethtool.h              |  19 ++++
 include/linux/netdevice.h            |   1 +
 include/net/pkt_sched.h              |   4 +
 include/uapi/linux/ethtool_netlink.h |  17 +++
 include/uapi/linux/pkt_sched.h       |   1 +
 net/ethtool/Makefile                 |   2 +-
 net/ethtool/netlink.c                |  19 ++++
 net/ethtool/netlink.h                |   4 +
 net/ethtool/preempt.c                | 151 +++++++++++++++++++++++++++
 net/sched/sch_taprio.c               |  41 +++++++-
 10 files changed, 254 insertions(+), 5 deletions(-)
 create mode 100644 net/ethtool/preempt.c

-- 
2.28.0

[RFC net-next v2 1/2] ethtool: Add support for configuring frame preemption

[Vinicius Costa Gomes]

Frame preemption (described in IEEE 802.3br-2016) defines the concept
of preemptible and express queues. It allows traffic from express
queues to "interrupt" traffic from preemptible queues, which are
"resumed" after the express traffic has finished transmitting.

Frame preemption can only be used when both the local device and the
link partner support it.

Only parameters for enabling/disabling frame preemption and
configuring the minimum fragment size are included here. Expressing
which queues are marked as preemptible is left to mqprio/taprio, as
having that information there should be easier on the user.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
---
 include/linux/ethtool.h              |  19 ++++
 include/uapi/linux/ethtool_netlink.h |  17 +++
 net/ethtool/Makefile                 |   2 +-
 net/ethtool/netlink.c                |  19 ++++
 net/ethtool/netlink.h                |   4 +
 net/ethtool/preempt.c                | 151 +++++++++++++++++++++++++++
 6 files changed, 211 insertions(+), 1 deletion(-)
 create mode 100644 net/ethtool/preempt.c

diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h
index 6408b446051f..8978b8e930b6 100644
--- a/include/linux/ethtool.h
+++ b/include/linux/ethtool.h
@@ -262,6 +262,19 @@ struct ethtool_pause_stats {
 	u64 rx_pause_frames;
 };
 
+/**
+ * struct ethtool_fp - Frame Preemption information
+ *
+ * @enabled: Enable frame preemption.
+ *
+ * @min_frag_size_mult: Minimum size for all non-final fragment size,
+ * expressed in terms of X in '(1 + X)*64 + 4'
+ */
+struct ethtool_fp {
+	u8 enabled;
+	u8 min_frag_size_mult;
+};
+
 /**
  * struct ethtool_ops - optional netdev operations
  * @supported_coalesce_params: supported types of interrupt coalescing.
@@ -405,6 +418,8 @@ struct ethtool_pause_stats {
  * @get_ethtool_phy_stats: Return extended statistics about the PHY device.
  *	This is only useful if the device maintains PHY statistics and
  *	cannot use the standard PHY library helpers.
+ * @get_preempt: Get the network device Frame Preemption parameters.
+ * @set_preempt: Set the network device Frame Preemption parameters.
  *
  * All operations are optional (i.e. the function pointer may be set
  * to %NULL) and callers must take this into account.  Callers must
@@ -503,6 +518,10 @@ struct ethtool_ops {
 				      struct ethtool_fecparam *);
 	int	(*set_fecparam)(struct net_device *,
 				      struct ethtool_fecparam *);
+	int	(*get_preempt)(struct net_device *,
+			       struct ethtool_fp *);
+	int	(*set_preempt)(struct net_device *,
+			       struct ethtool_fp *);
 	void	(*get_ethtool_phy_stats)(struct net_device *,
 					 struct ethtool_stats *, u64 *);
 	int	(*get_phy_tunable)(struct net_device *,
diff --git a/include/uapi/linux/ethtool_netlink.h b/include/uapi/linux/ethtool_netlink.h
index e2bf36e6964b..0b3dc0c263a9 100644
--- a/include/uapi/linux/ethtool_netlink.h
+++ b/include/uapi/linux/ethtool_netlink.h
@@ -42,6 +42,8 @@ enum {
 	ETHTOOL_MSG_CABLE_TEST_ACT,
 	ETHTOOL_MSG_CABLE_TEST_TDR_ACT,
 	ETHTOOL_MSG_TUNNEL_INFO_GET,
+	ETHTOOL_MSG_PREEMPT_GET,
+	ETHTOOL_MSG_PREEMPT_SET,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_USER_CNT,
@@ -80,6 +82,8 @@ enum {
 	ETHTOOL_MSG_CABLE_TEST_NTF,
 	ETHTOOL_MSG_CABLE_TEST_TDR_NTF,
 	ETHTOOL_MSG_TUNNEL_INFO_GET_REPLY,
+	ETHTOOL_MSG_PREEMPT_GET_REPLY,
+	ETHTOOL_MSG_PREEMPT_NTF,
 
 	/* add new constants above here */
 	__ETHTOOL_MSG_KERNEL_CNT,
@@ -628,6 +632,19 @@ enum {
 	ETHTOOL_A_TUNNEL_INFO_MAX = (__ETHTOOL_A_TUNNEL_INFO_CNT - 1)
 };
 
+/* FRAME PREEMPTION */
+
+enum {
+	ETHTOOL_A_PREEMPT_UNSPEC,
+	ETHTOOL_A_PREEMPT_HEADER,			/* nest - _A_HEADER_* */
+	ETHTOOL_A_PREEMPT_ENABLED,			/* u8 */
+	ETHTOOL_A_PREEMPT_MIN_FRAG_SIZE_MULT,		/* u8 */
+
+	/* add new constants above here */
+	__ETHTOOL_A_PREEMPT_CNT,
+	ETHTOOL_A_PREEMPT_MAX = (__ETHTOOL_A_PREEMPT_CNT - 1)
+};
+
 /* generic netlink info */
 #define ETHTOOL_GENL_NAME "ethtool"
 #define ETHTOOL_GENL_VERSION 1
diff --git a/net/ethtool/Makefile b/net/ethtool/Makefile
index 7a849ff22dad..4e584903e3ef 100644
--- a/net/ethtool/Makefile
+++ b/net/ethtool/Makefile
@@ -7,4 +7,4 @@ obj-$(CONFIG_ETHTOOL_NETLINK)	+= ethtool_nl.o
 ethtool_nl-y	:= netlink.o bitset.o strset.o linkinfo.o linkmodes.o \
 		   linkstate.o debug.o wol.o features.o privflags.o rings.o \
 		   channels.o coalesce.o pause.o eee.o tsinfo.o cabletest.o \
-		   tunnels.o
+		   tunnels.o preempt.o
diff --git a/net/ethtool/netlink.c b/net/ethtool/netlink.c
index 50d3c8896f91..bc7d66e3ba38 100644
--- a/net/ethtool/netlink.c
+++ b/net/ethtool/netlink.c
@@ -245,6 +245,7 @@ ethnl_default_requests[__ETHTOOL_MSG_USER_CNT] = {
 	[ETHTOOL_MSG_PAUSE_GET]		= &ethnl_pause_request_ops,
 	[ETHTOOL_MSG_EEE_GET]		= &ethnl_eee_request_ops,
 	[ETHTOOL_MSG_TSINFO_GET]	= &ethnl_tsinfo_request_ops,
+	[ETHTOOL_MSG_PREEMPT_GET]	= &ethnl_preempt_request_ops,
 };
 
 static struct ethnl_dump_ctx *ethnl_dump_context(struct netlink_callback *cb)
@@ -551,6 +552,7 @@ ethnl_default_notify_ops[ETHTOOL_MSG_KERNEL_MAX + 1] = {
 	[ETHTOOL_MSG_COALESCE_NTF]	= &ethnl_coalesce_request_ops,
 	[ETHTOOL_MSG_PAUSE_NTF]		= &ethnl_pause_request_ops,
 	[ETHTOOL_MSG_EEE_NTF]		= &ethnl_eee_request_ops,
+	[ETHTOOL_MSG_PREEMPT_NTF]	= &ethnl_preempt_request_ops,
 };
 
 /* default notification handler */
@@ -643,6 +645,7 @@ static const ethnl_notify_handler_t ethnl_notify_handlers[] = {
 	[ETHTOOL_MSG_COALESCE_NTF]	= ethnl_default_notify,
 	[ETHTOOL_MSG_PAUSE_NTF]		= ethnl_default_notify,
 	[ETHTOOL_MSG_EEE_NTF]		= ethnl_default_notify,
+	[ETHTOOL_MSG_PREEMPT_NTF]	= ethnl_default_notify,
 };
 
 void ethtool_notify(struct net_device *dev, unsigned int cmd, const void *data)
@@ -912,6 +915,22 @@ static const struct genl_ops ethtool_genl_ops[] = {
 		.policy = ethnl_tunnel_info_get_policy,
 		.maxattr = ARRAY_SIZE(ethnl_tunnel_info_get_policy) - 1,
 	},
+	{
+		.cmd	= ETHTOOL_MSG_PREEMPT_GET,
+		.doit	= ethnl_default_doit,
+		.start	= ethnl_default_start,
+		.dumpit	= ethnl_default_dumpit,
+		.done	= ethnl_default_done,
+		.policy = ethnl_preempt_get_policy,
+		.maxattr = ARRAY_SIZE(ethnl_preempt_get_policy) - 1,
+	},
+	{
+		.cmd	= ETHTOOL_MSG_PREEMPT_SET,
+		.flags	= GENL_UNS_ADMIN_PERM,
+		.doit	= ethnl_set_preempt,
+		.policy = ethnl_preempt_set_policy,
+		.maxattr = ARRAY_SIZE(ethnl_preempt_set_policy) - 1,
+	},
 };
 
 static const struct genl_multicast_group ethtool_nl_mcgrps[] = {
diff --git a/net/ethtool/netlink.h b/net/ethtool/netlink.h
index d8efec516d86..8f65e53ccd59 100644
--- a/net/ethtool/netlink.h
+++ b/net/ethtool/netlink.h
@@ -344,6 +344,7 @@ extern const struct ethnl_request_ops ethnl_coalesce_request_ops;
 extern const struct ethnl_request_ops ethnl_pause_request_ops;
 extern const struct ethnl_request_ops ethnl_eee_request_ops;
 extern const struct ethnl_request_ops ethnl_tsinfo_request_ops;
+extern const struct ethnl_request_ops ethnl_preempt_request_ops;
 
 extern const struct nla_policy ethnl_header_policy[ETHTOOL_A_HEADER_FLAGS + 1];
 extern const struct nla_policy ethnl_header_policy_stats[ETHTOOL_A_HEADER_FLAGS + 1];
@@ -375,6 +376,8 @@ extern const struct nla_policy ethnl_tsinfo_get_policy[ETHTOOL_A_TSINFO_HEADER +
 extern const struct nla_policy ethnl_cable_test_act_policy[ETHTOOL_A_CABLE_TEST_HEADER + 1];
 extern const struct nla_policy ethnl_cable_test_tdr_act_policy[ETHTOOL_A_CABLE_TEST_TDR_CFG + 1];
 extern const struct nla_policy ethnl_tunnel_info_get_policy[ETHTOOL_A_TUNNEL_INFO_HEADER + 1];
+extern const struct nla_policy ethnl_preempt_get_policy[ETHTOOL_A_PREEMPT_MAX + 1];
+extern const struct nla_policy ethnl_preempt_set_policy[ETHTOOL_A_PREEMPT_MAX + 1];
 
 int ethnl_set_linkinfo(struct sk_buff *skb, struct genl_info *info);
 int ethnl_set_linkmodes(struct sk_buff *skb, struct genl_info *info);
@@ -392,5 +395,6 @@ int ethnl_act_cable_test_tdr(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_doit(struct sk_buff *skb, struct genl_info *info);
 int ethnl_tunnel_info_start(struct netlink_callback *cb);
 int ethnl_tunnel_info_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+int ethnl_set_preempt(struct sk_buff *skb, struct genl_info *info);
 
 #endif /* _NET_ETHTOOL_NETLINK_H */
diff --git a/net/ethtool/preempt.c b/net/ethtool/preempt.c
new file mode 100644
index 000000000000..4d97d1180a65
--- /dev/null
+++ b/net/ethtool/preempt.c
@@ -0,0 +1,151 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "netlink.h"
+#include "common.h"
+
+struct preempt_req_info {
+	struct ethnl_req_info		base;
+};
+
+struct preempt_reply_data {
+	struct ethnl_reply_data		base;
+	struct ethtool_fp		fp;
+};
+
+#define PREEMPT_REPDATA(__reply_base) \
+	container_of(__reply_base, struct preempt_reply_data, base)
+
+const struct nla_policy
+ethnl_preempt_get_policy[ETHTOOL_A_PREEMPT_MAX + 1] = {
+	[ETHTOOL_A_PREEMPT_UNSPEC]		= { .type = NLA_REJECT },
+	[ETHTOOL_A_PREEMPT_HEADER]		= { .type = NLA_NESTED },
+	[ETHTOOL_A_PREEMPT_ENABLED]		= { .type = NLA_REJECT },
+	[ETHTOOL_A_PREEMPT_MIN_FRAG_SIZE_MULT]	= { .type = NLA_REJECT },
+};
+
+static int preempt_prepare_data(const struct ethnl_req_info *req_base,
+				struct ethnl_reply_data *reply_base,
+				struct genl_info *info)
+{
+	struct preempt_reply_data *data = PREEMPT_REPDATA(reply_base);
+	struct net_device *dev = reply_base->dev;
+	int ret;
+
+	if (!dev->ethtool_ops->get_preempt)
+		return -EOPNOTSUPP;
+
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		return ret;
+
+	ret = dev->ethtool_ops->get_preempt(dev, &data->fp);
+	ethnl_ops_complete(dev);
+
+	return ret;
+}
+
+static int preempt_reply_size(const struct ethnl_req_info *req_base,
+			      const struct ethnl_reply_data *reply_base)
+{
+	int len = 0;
+
+	len += nla_total_size(sizeof(u8)); /* _PREEMPT_ENABLED */
+	len += nla_total_size(sizeof(u8)); /* _PREEMPT_MIN_FRAG_SIZE */
+
+	return len;
+}
+
+static int preempt_fill_reply(struct sk_buff *skb,
+			      const struct ethnl_req_info *req_base,
+			      const struct ethnl_reply_data *reply_base)
+{
+	const struct preempt_reply_data *data = PREEMPT_REPDATA(reply_base);
+	const struct ethtool_fp *preempt = &data->fp;
+
+	if (nla_put_u8(skb, ETHTOOL_A_PREEMPT_ENABLED, preempt->enabled))
+		return -EMSGSIZE;
+
+	if (nla_put_u8(skb, ETHTOOL_A_PREEMPT_MIN_FRAG_SIZE_MULT,
+		       preempt->min_frag_size_mult))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+const struct ethnl_request_ops ethnl_preempt_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_PREEMPT_GET,
+	.reply_cmd		= ETHTOOL_MSG_PREEMPT_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_PREEMPT_HEADER,
+	.req_info_size		= sizeof(struct preempt_req_info),
+	.reply_data_size	= sizeof(struct preempt_reply_data),
+
+	.prepare_data		= preempt_prepare_data,
+	.reply_size		= preempt_reply_size,
+	.fill_reply		= preempt_fill_reply,
+};
+
+const struct nla_policy
+ethnl_preempt_set_policy[ETHTOOL_A_PREEMPT_MAX + 1] = {
+	[ETHTOOL_A_PREEMPT_UNSPEC]			= { .type = NLA_REJECT },
+	[ETHTOOL_A_PREEMPT_HEADER]			= { .type = NLA_NESTED },
+	[ETHTOOL_A_PREEMPT_ENABLED]			= { .type = NLA_U8 },
+	[ETHTOOL_A_PREEMPT_MIN_FRAG_SIZE_MULT]		= { .type = NLA_U8 },
+};
+
+int ethnl_set_preempt(struct sk_buff *skb, struct genl_info *info)
+{
+	struct ethnl_req_info req_info = {};
+	struct nlattr **tb = info->attrs;
+	struct ethtool_fp preempt = {};
+	struct net_device *dev;
+	bool mod = false;
+	int ret;
+
+	ret = ethnl_parse_header_dev_get(&req_info,
+					 tb[ETHTOOL_A_PREEMPT_HEADER],
+					 genl_info_net(info), info->extack,
+					 true);
+	if (ret < 0)
+		return ret;
+	dev = req_info.dev;
+	ret = -EOPNOTSUPP;
+	if (!dev->ethtool_ops->get_preempt ||
+	    !dev->ethtool_ops->set_preempt)
+		goto out_dev;
+
+	rtnl_lock();
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		goto out_rtnl;
+
+	ret = dev->ethtool_ops->get_preempt(dev, &preempt);
+	if (ret < 0) {
+		GENL_SET_ERR_MSG(info, "failed to retrieve frame preemption settings");
+		goto out_ops;
+	}
+
+	ethnl_update_u8(&preempt.enabled,
+			tb[ETHTOOL_A_PREEMPT_ENABLED], &mod);
+	ethnl_update_u8(&preempt.min_frag_size_mult,
+			tb[ETHTOOL_A_PREEMPT_MIN_FRAG_SIZE_MULT], &mod);
+
+	ret = 0;
+	if (!mod)
+		goto out_ops;
+
+	ret = dev->ethtool_ops->set_preempt(dev, &preempt);
+	if (ret < 0) {
+		GENL_SET_ERR_MSG(info, "frame preemption settings update failed");
+		goto out_ops;
+	}
+
+	ethtool_notify(dev, ETHTOOL_MSG_PREEMPT_NTF, NULL);
+
+out_ops:
+	ethnl_ops_complete(dev);
+out_rtnl:
+	rtnl_unlock();
+out_dev:
+	dev_put(dev);
+	return ret;
+}
-- 
2.28.0

[RFC net-next v2 2/2] taprio: Add support for frame preemption offload

[Vinicius Costa Gomes]

This adds a way to configure which queues are marked as preemptible
and which are marked as express.

Even if this is not a "real" offload, because it can't be executed
purely in software, having this information near where the mapping of
queues is specified, makes it, hopefully, easier to understand.

Signed-off-by: Vinicius Costa Gomes <vinicius.gomes@intel.com>
---
 include/linux/netdevice.h      |  1 +
 include/net/pkt_sched.h        |  4 ++++
 include/uapi/linux/pkt_sched.h |  1 +
 net/sched/sch_taprio.c         | 41 ++++++++++++++++++++++++++++++----
 4 files changed, 43 insertions(+), 4 deletions(-)

diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index a0df43b13839..99589945bb10 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -852,6 +852,7 @@ enum tc_setup_type {
 	TC_SETUP_QDISC_ETS,
 	TC_SETUP_QDISC_TBF,
 	TC_SETUP_QDISC_FIFO,
+	TC_SETUP_PREEMPT,
 };
 
 /* These structures hold the attributes of bpf state that are being passed
diff --git a/include/net/pkt_sched.h b/include/net/pkt_sched.h
index 4ed32e6b0201..71b50b644cfa 100644
--- a/include/net/pkt_sched.h
+++ b/include/net/pkt_sched.h
@@ -178,6 +178,10 @@ struct tc_taprio_qopt_offload {
 	struct tc_taprio_sched_entry entries[];
 };
 
+struct tc_preempt_qopt_offload {
+	u32 preemptible_queues;
+};
+
 /* Reference counting */
 struct tc_taprio_qopt_offload *taprio_offload_get(struct tc_taprio_qopt_offload
 						  *offload);
diff --git a/include/uapi/linux/pkt_sched.h b/include/uapi/linux/pkt_sched.h
index 9e7c2c607845..f0240ddaeee3 100644
--- a/include/uapi/linux/pkt_sched.h
+++ b/include/uapi/linux/pkt_sched.h
@@ -1240,6 +1240,7 @@ enum {
 	TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION, /* s64 */
 	TCA_TAPRIO_ATTR_FLAGS, /* u32 */
 	TCA_TAPRIO_ATTR_TXTIME_DELAY, /* u32 */
+	TCA_TAPRIO_ATTR_PREEMPT_QUEUES, /* u32 */
 	__TCA_TAPRIO_ATTR_MAX,
 };
 
diff --git a/net/sched/sch_taprio.c b/net/sched/sch_taprio.c
index b0ad7687ee2c..f9aa3f26aad9 100644
--- a/net/sched/sch_taprio.c
+++ b/net/sched/sch_taprio.c
@@ -63,6 +63,7 @@ struct taprio_sched {
 	struct Qdisc **qdiscs;
 	struct Qdisc *root;
 	u32 flags;
+	u32 preemptible_queues;
 	enum tk_offsets tk_offset;
 	int clockid;
 	atomic64_t picos_per_byte; /* Using picoseconds because for 10Gbps+
@@ -775,6 +776,7 @@ static const struct nla_policy taprio_policy[TCA_TAPRIO_ATTR_MAX + 1] = {
 	[TCA_TAPRIO_ATTR_SCHED_CYCLE_TIME_EXTENSION] = { .type = NLA_S64 },
 	[TCA_TAPRIO_ATTR_FLAGS]                      = { .type = NLA_U32 },
 	[TCA_TAPRIO_ATTR_TXTIME_DELAY]		     = { .type = NLA_U32 },
+	[TCA_TAPRIO_ATTR_PREEMPT_QUEUES]	     = { .type = NLA_U32 },
 };
 
 static int fill_sched_entry(struct taprio_sched *q, struct nlattr **tb,
@@ -1267,6 +1269,7 @@ static int taprio_disable_offload(struct net_device *dev,
 				  struct netlink_ext_ack *extack)
 {
 	const struct net_device_ops *ops = dev->netdev_ops;
+	struct tc_preempt_qopt_offload preempt = { };
 	struct tc_taprio_qopt_offload *offload;
 	int err;
 
@@ -1285,13 +1288,15 @@ static int taprio_disable_offload(struct net_device *dev,
 	offload->enable = 0;
 
 	err = ops->ndo_setup_tc(dev, TC_SETUP_QDISC_TAPRIO, offload);
-	if (err < 0) {
+	if (err < 0)
+		NL_SET_ERR_MSG(extack,
+			       "Device failed to disable offload");
+
+	err = ops->ndo_setup_tc(dev, TC_SETUP_PREEMPT, &preempt);
+	if (err < 0)
 		NL_SET_ERR_MSG(extack,
 			       "Device failed to disable offload");
-		goto out;
-	}
 
-out:
 	taprio_offload_free(offload);
 
 	return err;
@@ -1508,6 +1513,29 @@ static int taprio_change(struct Qdisc *sch, struct nlattr *opt,
 					       mqprio->prio_tc_map[i]);
 	}
 
+	/* It's valid to enable frame preemption without any kind of
+	 * offloading being enabled, so keep it separated.
+	 */
+	if (tb[TCA_TAPRIO_ATTR_PREEMPT_QUEUES]) {
+		u32 preempt = nla_get_u32(tb[TCA_TAPRIO_ATTR_PREEMPT_QUEUES]);
+		struct tc_preempt_qopt_offload qopt = { };
+
+		if (preempt == U32_MAX) {
+			NL_SET_ERR_MSG(extack, "At least one queue must be not be preemptible");
+			err = -EINVAL;
+			goto free_sched;
+		}
+
+		qopt.preemptible_queues = preempt;
+
+		err = dev->netdev_ops->ndo_setup_tc(dev, TC_SETUP_PREEMPT,
+						    &qopt);
+		if (err)
+			goto free_sched;
+
+		q->preemptible_queues = preempt;
+	}
+
 	if (FULL_OFFLOAD_IS_ENABLED(q->flags))
 		err = taprio_enable_offload(dev, q, new_admin, extack);
 	else
@@ -1649,6 +1677,7 @@ static int taprio_init(struct Qdisc *sch, struct nlattr *opt,
 	 */
 	q->clockid = -1;
 	q->flags = TAPRIO_FLAGS_INVALID;
+	q->preemptible_queues = U32_MAX;
 
 	spin_lock(&taprio_list_lock);
 	list_add(&q->taprio_list, &taprio_list);
@@ -1832,6 +1861,10 @@ static int taprio_dump(struct Qdisc *sch, struct sk_buff *skb)
 	if (q->flags && nla_put_u32(skb, TCA_TAPRIO_ATTR_FLAGS, q->flags))
 		goto options_error;
 
+	if (q->preemptible_queues != U32_MAX &&
+	    nla_put_u32(skb, TCA_TAPRIO_ATTR_PREEMPT_QUEUES, q->preemptible_queues))
+		goto options_error;
+
 	if (q->txtime_delay &&
 	    nla_put_u32(skb, TCA_TAPRIO_ATTR_TXTIME_DELAY, q->txtime_delay))
 		goto options_error;
-- 
2.28.0