Daniel Borkmann says:

====================
pull-request: bpf-next 2023-02-11

We've added 96 non-merge commits during the last 14 day(s) which contain
a total of 152 files changed, 4884 insertions(+), 962 deletions(-).

There is a minor conflict in drivers/net/ethernet/intel/ice/ice_main.c
between commit 5b246e533d01 ("ice: split probe into smaller functions")
from the net-next tree and commit 66c0e13ad236 ("drivers: net: turn on
XDP features") from the bpf-next tree. Remove the hunk given ice_cfg_netdev()
is otherwise there a 2nd time, and add XDP features to the existing
ice_cfg_netdev() one:

        [...]
        ice_set_netdev_features(netdev);
        netdev->xdp_features = NETDEV_XDP_ACT_BASIC | NETDEV_XDP_ACT_REDIRECT |
                               NETDEV_XDP_ACT_XSK_ZEROCOPY;
        ice_set_ops(netdev);
        [...]

Stephen's merge conflict mail:
https://lore.kernel.org/bpf/20230207101951.21a114fa@canb.auug.org.au/

The main changes are:

1) Add support for BPF trampoline on s390x which finally allows to remove many
   test cases from the BPF CI's DENYLIST.s390x, from Ilya Leoshkevich.

2) Add multi-buffer XDP support to ice driver, from Maciej Fijalkowski.

3) Add capability to export the XDP features supported by the NIC.
   Along with that, add a XDP compliance test tool,
   from Lorenzo Bianconi & Marek Majtyka.

4) Add __bpf_kfunc tag for marking kernel functions as kfuncs,
   from David Vernet.

5) Add a deep dive documentation about the verifier's register
   liveness tracking algorithm, from Eduard Zingerman.

6) Fix and follow-up cleanups for resolve_btfids to be compiled
   as a host program to avoid cross compile issues,
   from Jiri Olsa & Ian Rogers.

7) Batch of fixes to the BPF selftest for xdp_hw_metadata which resulted
   when testing on different NICs, from Jesper Dangaard Brouer.

8) Fix libbpf to better detect kernel version code on Debian, from Hao Xiang.

9) Extend libbpf to add an option for when the perf buffer should
   wake up, from Jon Doron.

10) Follow-up fix on xdp_metadata selftest to just consume on TX
    completion, from Stanislav Fomichev.

11) Extend the kfuncs.rst document with description on kfunc
    lifecycle & stability expectations, from David Vernet.

12) Fix bpftool prog profile to skip attaching to offline CPUs,
    from Tonghao Zhang.

====================

Link: https://lore.kernel.org/r/20230211002037.8489-1-daniel@iogearbox.net
Signed-off-by: Jakub Kicinski <kuba@kernel.org>

7 files changed, 281 insertions, 13 deletions

diff --git a/net/core/Makefile b/net/core/Makefile
index 10edd66a8a37..8f367813bc68 100644
--- a/net/core/Makefile
+++ b/net/core/Makefile
@@ -12,7 +12,8 @@ obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
 obj-y		     += dev.o dev_addr_lists.o dst.o netevent.o \
 			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
 			sock_diag.o dev_ioctl.o tso.o sock_reuseport.o \
-			fib_notifier.o xdp.o flow_offload.o gro.o
+			fib_notifier.o xdp.o flow_offload.o gro.o \
+			netdev-genl.o netdev-genl-gen.o
 
 obj-$(CONFIG_NETDEV_ADDR_LIST_TEST) += dev_addr_lists_test.o
 
diff --git a/net/core/dev.c b/net/core/dev.c
index bb42150a38ec..7307a0c15c9f 100644
--- a/net/core/dev.c
+++ b/net/core/dev.c
@@ -1614,6 +1614,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd)
 	N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO)
 	N(PRE_CHANGEADDR) N(OFFLOAD_XSTATS_ENABLE) N(OFFLOAD_XSTATS_DISABLE)
 	N(OFFLOAD_XSTATS_REPORT_USED) N(OFFLOAD_XSTATS_REPORT_DELTA)
+	N(XDP_FEAT_CHANGE)
 	}
 #undef N
 	return "UNKNOWN_NETDEV_EVENT";
diff --git a/net/core/filter.c b/net/core/filter.c
index d8f9b53f3db6..2ce06a72a5ba 100644
--- a/net/core/filter.c
+++ b/net/core/filter.c
@@ -4318,16 +4318,13 @@ int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp,
 	struct bpf_redirect_info *ri = this_cpu_ptr(&bpf_redirect_info);
 	enum bpf_map_type map_type = ri->map_type;
 
-	/* XDP_REDIRECT is not fully supported yet for xdp frags since
-	 * not all XDP capable drivers can map non-linear xdp_frame in
-	 * ndo_xdp_xmit.
-	 */
-	if (unlikely(xdp_buff_has_frags(xdp) &&
-		     map_type != BPF_MAP_TYPE_CPUMAP))
-		return -EOPNOTSUPP;
+	if (map_type == BPF_MAP_TYPE_XSKMAP) {
+		/* XDP_REDIRECT is not supported AF_XDP yet. */
+		if (unlikely(xdp_buff_has_frags(xdp)))
+			return -EOPNOTSUPP;
 
-	if (map_type == BPF_MAP_TYPE_XSKMAP)
 		return __xdp_do_redirect_xsk(ri, dev, xdp, xdp_prog);
+	}
 
 	return __xdp_do_redirect_frame(ri, dev, xdp_convert_buff_to_frame(xdp),
 				       xdp_prog);
@@ -7536,7 +7533,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv4_proto = {
 	.arg1_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
 	.arg1_size	= sizeof(struct iphdr),
 	.arg2_type	= ARG_PTR_TO_MEM,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
 BPF_CALL_3(bpf_tcp_raw_gen_syncookie_ipv6, struct ipv6hdr *, iph,
@@ -7568,7 +7565,7 @@ static const struct bpf_func_proto bpf_tcp_raw_gen_syncookie_ipv6_proto = {
 	.arg1_type	= ARG_PTR_TO_FIXED_SIZE_MEM,
 	.arg1_size	= sizeof(struct ipv6hdr),
 	.arg2_type	= ARG_PTR_TO_MEM,
-	.arg3_type	= ARG_CONST_SIZE,
+	.arg3_type	= ARG_CONST_SIZE_OR_ZERO,
 };
 
 BPF_CALL_2(bpf_tcp_raw_check_syncookie_ipv4, struct iphdr *, iph,
diff --git a/net/core/netdev-genl-gen.c b/net/core/netdev-genl-gen.c
new file mode 100644
index 000000000000..48812ec843f5
--- /dev/null
+++ b/net/core/netdev-genl-gen.c
@@ -0,0 +1,48 @@
+// SPDX-License-Identifier: BSD-3-Clause
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN kernel source */
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include "netdev-genl-gen.h"
+
+#include <linux/netdev.h>
+
+/* NETDEV_CMD_DEV_GET - do */
+static const struct nla_policy netdev_dev_get_nl_policy[NETDEV_A_DEV_IFINDEX + 1] = {
+	[NETDEV_A_DEV_IFINDEX] = NLA_POLICY_MIN(NLA_U32, 1),
+};
+
+/* Ops table for netdev */
+static const struct genl_split_ops netdev_nl_ops[2] = {
+	{
+		.cmd		= NETDEV_CMD_DEV_GET,
+		.doit		= netdev_nl_dev_get_doit,
+		.policy		= netdev_dev_get_nl_policy,
+		.maxattr	= NETDEV_A_DEV_IFINDEX,
+		.flags		= GENL_CMD_CAP_DO,
+	},
+	{
+		.cmd	= NETDEV_CMD_DEV_GET,
+		.dumpit	= netdev_nl_dev_get_dumpit,
+		.flags	= GENL_CMD_CAP_DUMP,
+	},
+};
+
+static const struct genl_multicast_group netdev_nl_mcgrps[] = {
+	[NETDEV_NLGRP_MGMT] = { "mgmt", },
+};
+
+struct genl_family netdev_nl_family __ro_after_init = {
+	.name		= NETDEV_FAMILY_NAME,
+	.version	= NETDEV_FAMILY_VERSION,
+	.netnsok	= true,
+	.parallel_ops	= true,
+	.module		= THIS_MODULE,
+	.split_ops	= netdev_nl_ops,
+	.n_split_ops	= ARRAY_SIZE(netdev_nl_ops),
+	.mcgrps		= netdev_nl_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(netdev_nl_mcgrps),
+};
diff --git a/net/core/netdev-genl-gen.h b/net/core/netdev-genl-gen.h
new file mode 100644
index 000000000000..b16dc7e026bb
--- /dev/null
+++ b/net/core/netdev-genl-gen.h
@@ -0,0 +1,23 @@
+/* SPDX-License-Identifier: BSD-3-Clause */
+/* Do not edit directly, auto-generated from: */
+/*	Documentation/netlink/specs/netdev.yaml */
+/* YNL-GEN kernel header */
+
+#ifndef _LINUX_NETDEV_GEN_H
+#define _LINUX_NETDEV_GEN_H
+
+#include <net/netlink.h>
+#include <net/genetlink.h>
+
+#include <linux/netdev.h>
+
+int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info);
+int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb);
+
+enum {
+	NETDEV_NLGRP_MGMT,
+};
+
+extern struct genl_family netdev_nl_family;
+
+#endif /* _LINUX_NETDEV_GEN_H */
diff --git a/net/core/netdev-genl.c b/net/core/netdev-genl.c
new file mode 100644
index 000000000000..a4270fafdf11
--- /dev/null
+++ b/net/core/netdev-genl.c
@@ -0,0 +1,179 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include <linux/netdevice.h>
+#include <linux/notifier.h>
+#include <linux/rtnetlink.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+
+#include "netdev-genl-gen.h"
+
+static int
+netdev_nl_dev_fill(struct net_device *netdev, struct sk_buff *rsp,
+		   u32 portid, u32 seq, int flags, u32 cmd)
+{
+	void *hdr;
+
+	hdr = genlmsg_put(rsp, portid, seq, &netdev_nl_family, flags, cmd);
+	if (!hdr)
+		return -EMSGSIZE;
+
+	if (nla_put_u32(rsp, NETDEV_A_DEV_IFINDEX, netdev->ifindex) ||
+	    nla_put_u64_64bit(rsp, NETDEV_A_DEV_XDP_FEATURES,
+			      netdev->xdp_features, NETDEV_A_DEV_PAD)) {
+		genlmsg_cancel(rsp, hdr);
+		return -EINVAL;
+	}
+
+	genlmsg_end(rsp, hdr);
+
+	return 0;
+}
+
+static void
+netdev_genl_dev_notify(struct net_device *netdev, int cmd)
+{
+	struct sk_buff *ntf;
+
+	if (!genl_has_listeners(&netdev_nl_family, dev_net(netdev),
+				NETDEV_NLGRP_MGMT))
+		return;
+
+	ntf = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!ntf)
+		return;
+
+	if (netdev_nl_dev_fill(netdev, ntf, 0, 0, 0, cmd)) {
+		nlmsg_free(ntf);
+		return;
+	}
+
+	genlmsg_multicast_netns(&netdev_nl_family, dev_net(netdev), ntf,
+				0, NETDEV_NLGRP_MGMT, GFP_KERNEL);
+}
+
+int netdev_nl_dev_get_doit(struct sk_buff *skb, struct genl_info *info)
+{
+	struct net_device *netdev;
+	struct sk_buff *rsp;
+	u32 ifindex;
+	int err;
+
+	if (GENL_REQ_ATTR_CHECK(info, NETDEV_A_DEV_IFINDEX))
+		return -EINVAL;
+
+	ifindex = nla_get_u32(info->attrs[NETDEV_A_DEV_IFINDEX]);
+
+	rsp = genlmsg_new(GENLMSG_DEFAULT_SIZE, GFP_KERNEL);
+	if (!rsp)
+		return -ENOMEM;
+
+	rtnl_lock();
+
+	netdev = __dev_get_by_index(genl_info_net(info), ifindex);
+	if (netdev)
+		err = netdev_nl_dev_fill(netdev, rsp, info->snd_portid,
+					 info->snd_seq, 0, info->genlhdr->cmd);
+	else
+		err = -ENODEV;
+
+	rtnl_unlock();
+
+	if (err)
+		goto err_free_msg;
+
+	return genlmsg_reply(rsp, info);
+
+err_free_msg:
+	nlmsg_free(rsp);
+	return err;
+}
+
+int netdev_nl_dev_get_dumpit(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct net_device *netdev;
+	int idx = 0, s_idx;
+	int h, s_h;
+	int err;
+
+	s_h = cb->args[0];
+	s_idx = cb->args[1];
+
+	rtnl_lock();
+
+	for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) {
+		struct hlist_head *head;
+
+		idx = 0;
+		head = &net->dev_index_head[h];
+		hlist_for_each_entry(netdev, head, index_hlist) {
+			if (idx < s_idx)
+				goto cont;
+			err = netdev_nl_dev_fill(netdev, skb,
+						 NETLINK_CB(cb->skb).portid,
+						 cb->nlh->nlmsg_seq, 0,
+						 NETDEV_CMD_DEV_GET);
+			if (err < 0)
+				break;
+cont:
+			idx++;
+		}
+	}
+
+	rtnl_unlock();
+
+	if (err != -EMSGSIZE)
+		return err;
+
+	cb->args[1] = idx;
+	cb->args[0] = h;
+	cb->seq = net->dev_base_seq;
+
+	return skb->len;
+}
+
+static int netdev_genl_netdevice_event(struct notifier_block *nb,
+				       unsigned long event, void *ptr)
+{
+	struct net_device *netdev = netdev_notifier_info_to_dev(ptr);
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_ADD_NTF);
+		break;
+	case NETDEV_UNREGISTER:
+		netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_DEL_NTF);
+		break;
+	case NETDEV_XDP_FEAT_CHANGE:
+		netdev_genl_dev_notify(netdev, NETDEV_CMD_DEV_CHANGE_NTF);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block netdev_genl_nb = {
+	.notifier_call	= netdev_genl_netdevice_event,
+};
+
+static int __init netdev_genl_init(void)
+{
+	int err;
+
+	err = register_netdevice_notifier(&netdev_genl_nb);
+	if (err)
+		return err;
+
+	err = genl_register_family(&netdev_nl_family);
+	if (err)
+		goto err_unreg_ntf;
+
+	return 0;
+
+err_unreg_ntf:
+	unregister_netdevice_notifier(&netdev_genl_nb);
+	return err;
+}
+
+subsys_initcall(netdev_genl_init);
diff --git a/net/core/xdp.c b/net/core/xdp.c
index 03938fe6d33a..8c92fc553317 100644
--- a/net/core/xdp.c
+++ b/net/core/xdp.c
@@ -4,6 +4,7 @@
  * Copyright (c) 2017 Jesper Dangaard Brouer, Red Hat Inc.
  */
 #include <linux/bpf.h>
+#include <linux/btf.h>
 #include <linux/btf_ids.h>
 #include <linux/filter.h>
 #include <linux/types.h>
@@ -721,7 +722,7 @@ __diag_ignore_all("-Wmissing-prototypes",
  *
  * Returns 0 on success or ``-errno`` on error.
  */
-int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
+__bpf_kfunc int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
 {
 	return -EOPNOTSUPP;
 }
@@ -733,7 +734,7 @@ int bpf_xdp_metadata_rx_timestamp(const struct xdp_md *ctx, u64 *timestamp)
  *
  * Returns 0 on success or ``-errno`` on error.
  */
-int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash)
+__bpf_kfunc int bpf_xdp_metadata_rx_hash(const struct xdp_md *ctx, u32 *hash)
 {
 	return -EOPNOTSUPP;
 }
@@ -772,3 +773,21 @@ static int __init xdp_metadata_init(void)
 	return register_btf_kfunc_id_set(BPF_PROG_TYPE_XDP, &xdp_metadata_kfunc_set);
 }
 late_initcall(xdp_metadata_init);
+
+void xdp_features_set_redirect_target(struct net_device *dev, bool support_sg)
+{
+	dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT;
+	if (support_sg)
+		dev->xdp_features |= NETDEV_XDP_ACT_NDO_XMIT_SG;
+
+	call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_set_redirect_target);
+
+void xdp_features_clear_redirect_target(struct net_device *dev)
+{
+	dev->xdp_features &= ~(NETDEV_XDP_ACT_NDO_XMIT |
+			       NETDEV_XDP_ACT_NDO_XMIT_SG);
+	call_netdevice_notifiers(NETDEV_XDP_FEAT_CHANGE, dev);
+}
+EXPORT_SYMBOL_GPL(xdp_features_clear_redirect_target);