From de874f3eb2a86fb52fa14f691b586132d375e75d Mon Sep 17 00:00:00 2001
From: Edward Cree <ecree@solarflare.com>
Date: Fri, 2 Jun 2023 10:32:26 +0800
Subject: [PATCH 01/12] bpf/verifier: display non-spill stack slot types in
 print_verifier_state

ANBZ: #5530

commit 8efea21d333d21e1f9177579ffdc69556314f603 upstream

If a stack slot does not hold a spilled register (STACK_SPILL), then each
 of its eight bytes could potentially have a different slot_type.  This
 information can be important for debugging, and previously we either did
 not print anything for the stack slot, or just printed fp-X=0 in the case
 where its first byte was STACK_ZERO.
Instead, print eight characters with either 0 (STACK_ZERO), m (STACK_MISC)
 or ? (STACK_INVALID) for any stack slot which is neither STACK_SPILL nor
 entirely STACK_INVALID.

Signed-off-by: Edward Cree <ecree@solarflare.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 kernel/bpf/verifier.c | 32 +++++++++++++++++++++++++-------
 1 file changed, 25 insertions(+), 7 deletions(-)

diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 9b74115452c6..5ef094796925 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -263,6 +263,13 @@ static const char * const reg_type_str[] = {
 	[PTR_TO_PACKET_END]	= "pkt_end",
 };
 
+static char slot_type_char[] = {
+	[STACK_INVALID]	= '?',
+	[STACK_SPILL]	= 'r',
+	[STACK_MISC]	= 'm',
+	[STACK_ZERO]	= '0',
+};
+
 static void print_liveness(struct bpf_verifier_env *env,
 			   enum bpf_reg_liveness live)
 {
@@ -349,15 +356,26 @@ static void print_verifier_state(struct bpf_verifier_env *env,
 		}
 	}
 	for (i = 0; i < state->allocated_stack / BPF_REG_SIZE; i++) {
-		if (state->stack[i].slot_type[0] == STACK_SPILL) {
-			verbose(env, " fp%d",
-				(-i - 1) * BPF_REG_SIZE);
-			print_liveness(env, state->stack[i].spilled_ptr.live);
+		char types_buf[BPF_REG_SIZE + 1];
+		bool valid = false;
+		int j;
+
+		for (j = 0; j < BPF_REG_SIZE; j++) {
+			if (state->stack[i].slot_type[j] != STACK_INVALID)
+				valid = true;
+			types_buf[j] = slot_type_char[
+					state->stack[i].slot_type[j]];
+		}
+		types_buf[BPF_REG_SIZE] = 0;
+		if (!valid)
+			continue;
+		verbose(env, " fp%d", (-i - 1) * BPF_REG_SIZE);
+		print_liveness(env, state->stack[i].spilled_ptr.live);
+		if (state->stack[i].slot_type[0] == STACK_SPILL)
 			verbose(env, "=%s",
 				reg_type_str[state->stack[i].spilled_ptr.type]);
-		}
-		if (state->stack[i].slot_type[0] == STACK_ZERO)
-			verbose(env, " fp%d=0", (-i - 1) * BPF_REG_SIZE);
+		else
+			verbose(env, "=%s", types_buf);
 	}
 	verbose(env, "\n");
 }
-- 
Gitee


From f4c1e370fb79a36310855ee5efe4b2d7924ca341 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 2 Jun 2023 16:20:00 +0800
Subject: [PATCH 02/12] tools/bpf: move bpf/lib netlink related functions into
 a new file

ANBZ: #5530

commit f7010770fbac47b1fc9fb723b1d2019eb23c04f2 upstream

There are no functionality change for this patch.

In the subsequent patches, more netlink related library functions
will be added and a separate file is better than cluttering bpf.c.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/lib/bpf/Build     |   2 +-
 tools/lib/bpf/bpf.c     | 129 -------------------------------
 tools/lib/bpf/netlink.c | 165 ++++++++++++++++++++++++++++++++++++++++
 3 files changed, 166 insertions(+), 130 deletions(-)
 create mode 100644 tools/lib/bpf/netlink.c

diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build
index 6eb9bacd1948..7bc31c905018 100644
--- a/tools/lib/bpf/Build
+++ b/tools/lib/bpf/Build
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o str_error.o netlink.o
diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c
index 482025b72839..eba3ad604244 100644
--- a/tools/lib/bpf/bpf.c
+++ b/tools/lib/bpf/bpf.c
@@ -28,16 +28,8 @@
 #include <linux/bpf.h>
 #include "bpf.h"
 #include "libbpf.h"
-#include "nlattr.h"
-#include <linux/rtnetlink.h>
-#include <linux/if_link.h>
-#include <sys/socket.h>
 #include <errno.h>
 
-#ifndef SOL_NETLINK
-#define SOL_NETLINK 270
-#endif
-
 /*
  * When building perf, unistd.h is overridden. __NR_bpf is
  * required to be defined explicitly.
@@ -521,127 +513,6 @@ int bpf_raw_tracepoint_open(const char *name, int prog_fd)
 	return sys_bpf(BPF_RAW_TRACEPOINT_OPEN, &attr, sizeof(attr));
 }
 
-int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
-{
-	struct sockaddr_nl sa;
-	int sock, seq = 0, len, ret = -1;
-	char buf[4096];
-	struct nlattr *nla, *nla_xdp;
-	struct {
-		struct nlmsghdr  nh;
-		struct ifinfomsg ifinfo;
-		char             attrbuf[64];
-	} req;
-	struct nlmsghdr *nh;
-	struct nlmsgerr *err;
-	socklen_t addrlen;
-	int one = 1;
-
-	memset(&sa, 0, sizeof(sa));
-	sa.nl_family = AF_NETLINK;
-
-	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
-	if (sock < 0) {
-		return -errno;
-	}
-
-	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
-		       &one, sizeof(one)) < 0) {
-		fprintf(stderr, "Netlink error reporting not supported\n");
-	}
-
-	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	addrlen = sizeof(sa);
-	if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	if (addrlen != sizeof(sa)) {
-		ret = -LIBBPF_ERRNO__INTERNAL;
-		goto cleanup;
-	}
-
-	memset(&req, 0, sizeof(req));
-	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
-	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
-	req.nh.nlmsg_type = RTM_SETLINK;
-	req.nh.nlmsg_pid = 0;
-	req.nh.nlmsg_seq = ++seq;
-	req.ifinfo.ifi_family = AF_UNSPEC;
-	req.ifinfo.ifi_index = ifindex;
-
-	/* started nested attribute for XDP */
-	nla = (struct nlattr *)(((char *)&req)
-				+ NLMSG_ALIGN(req.nh.nlmsg_len));
-	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
-	nla->nla_len = NLA_HDRLEN;
-
-	/* add XDP fd */
-	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-	nla_xdp->nla_type = IFLA_XDP_FD;
-	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
-	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
-	nla->nla_len += nla_xdp->nla_len;
-
-	/* if user passed in any flags, add those too */
-	if (flags) {
-		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
-		nla_xdp->nla_type = IFLA_XDP_FLAGS;
-		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
-		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
-		nla->nla_len += nla_xdp->nla_len;
-	}
-
-	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
-
-	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	len = recv(sock, buf, sizeof(buf), 0);
-	if (len < 0) {
-		ret = -errno;
-		goto cleanup;
-	}
-
-	for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
-	     nh = NLMSG_NEXT(nh, len)) {
-		if (nh->nlmsg_pid != sa.nl_pid) {
-			ret = -LIBBPF_ERRNO__WRNGPID;
-			goto cleanup;
-		}
-		if (nh->nlmsg_seq != seq) {
-			ret = -LIBBPF_ERRNO__INVSEQ;
-			goto cleanup;
-		}
-		switch (nh->nlmsg_type) {
-		case NLMSG_ERROR:
-			err = (struct nlmsgerr *)NLMSG_DATA(nh);
-			if (!err->error)
-				continue;
-			ret = err->error;
-			nla_dump_errormsg(nh);
-			goto cleanup;
-		case NLMSG_DONE:
-			break;
-		default:
-			break;
-		}
-	}
-
-	ret = 0;
-
-cleanup:
-	close(sock);
-	return ret;
-}
-
 int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size,
 		 bool do_log)
 {
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
new file mode 100644
index 000000000000..ccaa991fe9d8
--- /dev/null
+++ b/tools/lib/bpf/netlink.c
@@ -0,0 +1,165 @@
+// SPDX-License-Identifier: LGPL-2.1
+/* Copyright (c) 2018 Facebook */
+
+#include <stdlib.h>
+#include <memory.h>
+#include <unistd.h>
+#include <linux/bpf.h>
+#include <linux/rtnetlink.h>
+#include <sys/socket.h>
+#include <errno.h>
+#include <time.h>
+
+#include "bpf.h"
+#include "libbpf.h"
+#include "nlattr.h"
+
+#ifndef SOL_NETLINK
+#define SOL_NETLINK 270
+#endif
+
+static int bpf_netlink_open(__u32 *nl_pid)
+{
+	struct sockaddr_nl sa;
+	socklen_t addrlen;
+	int one = 1, ret;
+	int sock;
+
+	memset(&sa, 0, sizeof(sa));
+	sa.nl_family = AF_NETLINK;
+
+	sock = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE);
+	if (sock < 0)
+		return -errno;
+
+	if (setsockopt(sock, SOL_NETLINK, NETLINK_EXT_ACK,
+		       &one, sizeof(one)) < 0) {
+		fprintf(stderr, "Netlink error reporting not supported\n");
+	}
+
+	if (bind(sock, (struct sockaddr *)&sa, sizeof(sa)) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	addrlen = sizeof(sa);
+	if (getsockname(sock, (struct sockaddr *)&sa, &addrlen) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+
+	if (addrlen != sizeof(sa)) {
+		ret = -LIBBPF_ERRNO__INTERNAL;
+		goto cleanup;
+	}
+
+	*nl_pid = sa.nl_pid;
+	return sock;
+
+cleanup:
+	close(sock);
+	return ret;
+}
+
+static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq)
+{
+	struct nlmsgerr *err;
+	struct nlmsghdr *nh;
+	char buf[4096];
+	int len, ret;
+
+	while (1) {
+		len = recv(sock, buf, sizeof(buf), 0);
+		if (len < 0) {
+			ret = -errno;
+			goto done;
+		}
+
+		for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
+		     nh = NLMSG_NEXT(nh, len)) {
+			if (nh->nlmsg_pid != nl_pid) {
+				ret = -LIBBPF_ERRNO__WRNGPID;
+				goto done;
+			}
+			if (nh->nlmsg_seq != seq) {
+				ret = -LIBBPF_ERRNO__INVSEQ;
+				goto done;
+			}
+			switch (nh->nlmsg_type) {
+			case NLMSG_ERROR:
+				err = (struct nlmsgerr *)NLMSG_DATA(nh);
+				if (!err->error)
+					continue;
+				ret = err->error;
+				nla_dump_errormsg(nh);
+				goto done;
+			case NLMSG_DONE:
+				return 0;
+			default:
+				break;
+			}
+		}
+	}
+	ret = 0;
+done:
+	return ret;
+}
+
+int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
+{
+	int sock, seq = 0, ret;
+	struct nlattr *nla, *nla_xdp;
+	struct {
+		struct nlmsghdr  nh;
+		struct ifinfomsg ifinfo;
+		char             attrbuf[64];
+	} req;
+	__u32 nl_pid;
+
+	sock = bpf_netlink_open(&nl_pid);
+	if (sock < 0)
+		return sock;
+
+	memset(&req, 0, sizeof(req));
+	req.nh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg));
+	req.nh.nlmsg_flags = NLM_F_REQUEST | NLM_F_ACK;
+	req.nh.nlmsg_type = RTM_SETLINK;
+	req.nh.nlmsg_pid = 0;
+	req.nh.nlmsg_seq = ++seq;
+	req.ifinfo.ifi_family = AF_UNSPEC;
+	req.ifinfo.ifi_index = ifindex;
+
+	/* started nested attribute for XDP */
+	nla = (struct nlattr *)(((char *)&req)
+				+ NLMSG_ALIGN(req.nh.nlmsg_len));
+	nla->nla_type = NLA_F_NESTED | IFLA_XDP;
+	nla->nla_len = NLA_HDRLEN;
+
+	/* add XDP fd */
+	nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+	nla_xdp->nla_type = IFLA_XDP_FD;
+	nla_xdp->nla_len = NLA_HDRLEN + sizeof(int);
+	memcpy((char *)nla_xdp + NLA_HDRLEN, &fd, sizeof(fd));
+	nla->nla_len += nla_xdp->nla_len;
+
+	/* if user passed in any flags, add those too */
+	if (flags) {
+		nla_xdp = (struct nlattr *)((char *)nla + nla->nla_len);
+		nla_xdp->nla_type = IFLA_XDP_FLAGS;
+		nla_xdp->nla_len = NLA_HDRLEN + sizeof(flags);
+		memcpy((char *)nla_xdp + NLA_HDRLEN, &flags, sizeof(flags));
+		nla->nla_len += nla_xdp->nla_len;
+	}
+
+	req.nh.nlmsg_len += NLA_ALIGN(nla->nla_len);
+
+	if (send(sock, &req, req.nh.nlmsg_len, 0) < 0) {
+		ret = -errno;
+		goto cleanup;
+	}
+	ret = bpf_netlink_recv(sock, nl_pid, seq);
+
+cleanup:
+	close(sock);
+	return ret;
+}
-- 
Gitee


From 16726e6d68398b46b570dfb9d2690b07ab8c6fd1 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 2 Jun 2023 16:22:21 +0800
Subject: [PATCH 03/12] tools/bpf: add more netlink functionalities in lib/bpf

ANBZ: #5530

commit 36f1678d9e0b5d2e0236046d9659e0348b4719a8 upstream

This patch added a few netlink attribute parsing functions
and the netlink API functions to query networking links, tc classes,
tc qdiscs and tc filters. For example, the following API is
to get networking links:
  int nl_get_link(int sock, unsigned int nl_pid,
                  dump_nlmsg_t dump_link_nlmsg,
                  void *cookie);

Note that when the API is called, the user also provided a
callback function with the following signature:
  int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);

The "cookie" is the parameter the user passed to the API and will
be available for the callback function.
The "msg" is the information about the result, e.g., ifinfomsg or
tcmsg. The "tb" is the parsed netlink attributes.

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/lib/bpf/libbpf.h       |  16 ++++
 tools/lib/bpf/libbpf_errno.c |   1 +
 tools/lib/bpf/netlink.c      | 165 ++++++++++++++++++++++++++++++++++-
 tools/lib/bpf/nlattr.c       |  33 ++++---
 tools/lib/bpf/nlattr.h       |  38 ++++++++
 5 files changed, 238 insertions(+), 15 deletions(-)

diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 96c55fac54c3..e3b00e23e181 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -46,6 +46,7 @@ enum libbpf_errno {
 	LIBBPF_ERRNO__PROGTYPE,	/* Kernel doesn't support this program type */
 	LIBBPF_ERRNO__WRNGPID,	/* Wrong pid in netlink message */
 	LIBBPF_ERRNO__INVSEQ,	/* Invalid netlink sequence */
+	LIBBPF_ERRNO__NLPARSE,	/* netlink parsing error */
 	__LIBBPF_ERRNO__END,
 };
 
@@ -297,4 +298,19 @@ int bpf_perf_event_read_simple(void *mem, unsigned long size,
 			       unsigned long page_size,
 			       void **buf, size_t *buf_len,
 			       bpf_perf_event_print_t fn, void *priv);
+
+struct nlmsghdr;
+struct nlattr;
+typedef int (*dump_nlmsg_t)(void *cookie, void *msg, struct nlattr **tb);
+typedef int (*__dump_nlmsg_t)(struct nlmsghdr *nlmsg, dump_nlmsg_t,
+			      void *cookie);
+int bpf_netlink_open(unsigned int *nl_pid);
+int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
+		void *cookie);
+int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_class_nlmsg, void *cookie);
+int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie);
+int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+		  dump_nlmsg_t dump_filter_nlmsg, void *cookie);
 #endif
diff --git a/tools/lib/bpf/libbpf_errno.c b/tools/lib/bpf/libbpf_errno.c
index d2d17226d9d6..451283328fa9 100644
--- a/tools/lib/bpf/libbpf_errno.c
+++ b/tools/lib/bpf/libbpf_errno.c
@@ -43,6 +43,7 @@ static const char *libbpf_strerror_table[NR_ERRNO] = {
 	[ERRCODE_OFFSET(PROGTYPE)]	= "Kernel doesn't support this program type",
 	[ERRCODE_OFFSET(WRNGPID)]	= "Wrong pid in netlink message",
 	[ERRCODE_OFFSET(INVSEQ)]	= "Invalid netlink sequence",
+	[ERRCODE_OFFSET(NLPARSE)]	= "Incorrect netlink message parsing",
 };
 
 int libbpf_strerror(int err, char *buf, size_t size)
diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index ccaa991fe9d8..469e068dd0c5 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -18,7 +18,7 @@
 #define SOL_NETLINK 270
 #endif
 
-static int bpf_netlink_open(__u32 *nl_pid)
+int bpf_netlink_open(__u32 *nl_pid)
 {
 	struct sockaddr_nl sa;
 	socklen_t addrlen;
@@ -61,7 +61,9 @@ static int bpf_netlink_open(__u32 *nl_pid)
 	return ret;
 }
 
-static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq)
+static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
+			    __dump_nlmsg_t _fn, dump_nlmsg_t fn,
+			    void *cookie)
 {
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
@@ -98,6 +100,11 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq)
 			default:
 				break;
 			}
+			if (_fn) {
+				ret = _fn(nh, fn, cookie);
+				if (ret)
+					return ret;
+			}
 		}
 	}
 	ret = 0;
@@ -157,9 +164,161 @@ int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags)
 		ret = -errno;
 		goto cleanup;
 	}
-	ret = bpf_netlink_recv(sock, nl_pid, seq);
+	ret = bpf_netlink_recv(sock, nl_pid, seq, NULL, NULL, NULL);
 
 cleanup:
 	close(sock);
 	return ret;
 }
+
+static int __dump_link_nlmsg(struct nlmsghdr *nlh, dump_nlmsg_t dump_link_nlmsg,
+			     void *cookie)
+{
+	struct nlattr *tb[IFLA_MAX + 1], *attr;
+	struct ifinfomsg *ifi = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*ifi));
+	attr = (struct nlattr *) ((void *) ifi + NLMSG_ALIGN(sizeof(*ifi)));
+	if (nla_parse(tb, IFLA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_link_nlmsg(cookie, ifi, tb);
+}
+
+int nl_get_link(int sock, unsigned int nl_pid, dump_nlmsg_t dump_link_nlmsg,
+		void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct ifinfomsg ifm;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct ifinfomsg)),
+		.nlh.nlmsg_type = RTM_GETLINK,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.ifm.ifi_family = AF_PACKET,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_link_nlmsg,
+				dump_link_nlmsg, cookie);
+}
+
+static int __dump_class_nlmsg(struct nlmsghdr *nlh,
+			      dump_nlmsg_t dump_class_nlmsg, void *cookie)
+{
+	struct nlattr *tb[TCA_MAX + 1], *attr;
+	struct tcmsg *t = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_class_nlmsg(cookie, t, tb);
+}
+
+int nl_get_class(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_class_nlmsg, void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct tcmsg t;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+		.nlh.nlmsg_type = RTM_GETTCLASS,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.t.tcm_family = AF_UNSPEC,
+		.t.tcm_ifindex = ifindex,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_class_nlmsg,
+				dump_class_nlmsg, cookie);
+}
+
+static int __dump_qdisc_nlmsg(struct nlmsghdr *nlh,
+			      dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+{
+	struct nlattr *tb[TCA_MAX + 1], *attr;
+	struct tcmsg *t = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_qdisc_nlmsg(cookie, t, tb);
+}
+
+int nl_get_qdisc(int sock, unsigned int nl_pid, int ifindex,
+		 dump_nlmsg_t dump_qdisc_nlmsg, void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct tcmsg t;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+		.nlh.nlmsg_type = RTM_GETQDISC,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.t.tcm_family = AF_UNSPEC,
+		.t.tcm_ifindex = ifindex,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_qdisc_nlmsg,
+				dump_qdisc_nlmsg, cookie);
+}
+
+static int __dump_filter_nlmsg(struct nlmsghdr *nlh,
+			       dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+{
+	struct nlattr *tb[TCA_MAX + 1], *attr;
+	struct tcmsg *t = NLMSG_DATA(nlh);
+	int len;
+
+	len = nlh->nlmsg_len - NLMSG_LENGTH(sizeof(*t));
+	attr = (struct nlattr *) ((void *) t + NLMSG_ALIGN(sizeof(*t)));
+	if (nla_parse(tb, TCA_MAX, attr, len, NULL) != 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	return dump_filter_nlmsg(cookie, t, tb);
+}
+
+int nl_get_filter(int sock, unsigned int nl_pid, int ifindex, int handle,
+		  dump_nlmsg_t dump_filter_nlmsg, void *cookie)
+{
+	struct {
+		struct nlmsghdr nlh;
+		struct tcmsg t;
+	} req = {
+		.nlh.nlmsg_len = NLMSG_LENGTH(sizeof(struct tcmsg)),
+		.nlh.nlmsg_type = RTM_GETTFILTER,
+		.nlh.nlmsg_flags = NLM_F_DUMP | NLM_F_REQUEST,
+		.t.tcm_family = AF_UNSPEC,
+		.t.tcm_ifindex = ifindex,
+		.t.tcm_parent = handle,
+	};
+	int seq = time(NULL);
+
+	req.nlh.nlmsg_seq = seq;
+	if (send(sock, &req, req.nlh.nlmsg_len, 0) < 0)
+		return -errno;
+
+	return bpf_netlink_recv(sock, nl_pid, seq, __dump_filter_nlmsg,
+				dump_filter_nlmsg, cookie);
+}
diff --git a/tools/lib/bpf/nlattr.c b/tools/lib/bpf/nlattr.c
index 4719434278b2..49f514119bdb 100644
--- a/tools/lib/bpf/nlattr.c
+++ b/tools/lib/bpf/nlattr.c
@@ -26,11 +26,6 @@ static uint16_t nla_attr_minlen[NLA_TYPE_MAX+1] = {
 	[NLA_FLAG]	= 0,
 };
 
-static int nla_len(const struct nlattr *nla)
-{
-	return nla->nla_len - NLA_HDRLEN;
-}
-
 static struct nlattr *nla_next(const struct nlattr *nla, int *remaining)
 {
 	int totlen = NLA_ALIGN(nla->nla_len);
@@ -46,11 +41,6 @@ static int nla_ok(const struct nlattr *nla, int remaining)
 	       nla->nla_len <= remaining;
 }
 
-static void *nla_data(const struct nlattr *nla)
-{
-	return (char *) nla + NLA_HDRLEN;
-}
-
 static int nla_type(const struct nlattr *nla)
 {
 	return nla->nla_type & NLA_TYPE_MASK;
@@ -114,8 +104,8 @@ static inline int nlmsg_len(const struct nlmsghdr *nlh)
  * @see nla_validate
  * @return 0 on success or a negative error code.
  */
-static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
-		     struct nla_policy *policy)
+int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+	      struct nla_policy *policy)
 {
 	struct nlattr *nla;
 	int rem, err;
@@ -146,6 +136,25 @@ static int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int
 	return err;
 }
 
+/**
+ * Create attribute index based on nested attribute
+ * @arg tb              Index array to be filled (maxtype+1 elements).
+ * @arg maxtype         Maximum attribute type expected and accepted.
+ * @arg nla             Nested Attribute.
+ * @arg policy          Attribute validation policy.
+ *
+ * Feeds the stream of attributes nested into the specified attribute
+ * to nla_parse().
+ *
+ * @see nla_parse
+ * @return 0 on success or a negative error code.
+ */
+int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+		     struct nla_policy *policy)
+{
+	return nla_parse(tb, maxtype, nla_data(nla), nla_len(nla), policy);
+}
+
 /* dump netlink extended ack error message */
 int nla_dump_errormsg(struct nlmsghdr *nlh)
 {
diff --git a/tools/lib/bpf/nlattr.h b/tools/lib/bpf/nlattr.h
index 931a71f68f93..a6e2396bce7c 100644
--- a/tools/lib/bpf/nlattr.h
+++ b/tools/lib/bpf/nlattr.h
@@ -67,6 +67,44 @@ struct nla_policy {
 	     nla_ok(pos, rem); \
 	     pos = nla_next(pos, &(rem)))
 
+/**
+ * nla_data - head of payload
+ * @nla: netlink attribute
+ */
+static inline void *nla_data(const struct nlattr *nla)
+{
+	return (char *) nla + NLA_HDRLEN;
+}
+
+static inline uint8_t nla_getattr_u8(const struct nlattr *nla)
+{
+	return *(uint8_t *)nla_data(nla);
+}
+
+static inline uint32_t nla_getattr_u32(const struct nlattr *nla)
+{
+	return *(uint32_t *)nla_data(nla);
+}
+
+static inline const char *nla_getattr_str(const struct nlattr *nla)
+{
+	return (const char *)nla_data(nla);
+}
+
+/**
+ * nla_len - length of payload
+ * @nla: netlink attribute
+ */
+static inline int nla_len(const struct nlattr *nla)
+{
+	return nla->nla_len - NLA_HDRLEN;
+}
+
+int nla_parse(struct nlattr *tb[], int maxtype, struct nlattr *head, int len,
+	      struct nla_policy *policy);
+int nla_parse_nested(struct nlattr *tb[], int maxtype, struct nlattr *nla,
+		     struct nla_policy *policy);
+
 int nla_dump_errormsg(struct nlmsghdr *nlh);
 
 #endif /* __NLATTR_H */
-- 
Gitee


From c99ae20083067b4b016ec64499e1f8eaf5ceacd5 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 2 Jun 2023 16:27:30 +0800
Subject: [PATCH 04/12] tools/bpf: bpftool: add net support

ANBZ: #5530

commit f6f3bac08ff9855d803081a353a1fafaa8845739 upstream

Add "bpftool net" support. Networking devices are enumerated
to dump device index/name associated with xdp progs.

For each networking device, tc classes and qdiscs are enumerated
in order to check their bpf filters.
In addition, root handle and clsact ingress/egress are also checked for
bpf filters.  Not all filter information is printed out. Only ifindex,
kind, filter name, prog_id and tag are printed out, which are good
enough to show attachment information. If the filter action
is a bpf action, its bpf program id, bpf name and tag will be
printed out as well.

For example,
  $ ./bpftool net
  xdp [
  ifindex 2 devname eth0 prog_id 198
  ]
  tc_filters [
  ifindex 2 kind qdisc_htb name prefix_matcher.o:[cls_prefix_matcher_htb]
            prog_id 111727 tag d08fe3b4319bc2fd act []
  ifindex 2 kind qdisc_clsact_ingress name fbflow_icmp
            prog_id 130246 tag 3f265c7f26db62c9 act []
  ifindex 2 kind qdisc_clsact_egress name prefix_matcher.o:[cls_prefix_matcher_clsact]
            prog_id 111726 tag 99a197826974c876
  ifindex 2 kind qdisc_clsact_egress name cls_fg_dscp
            prog_id 108619 tag dc4630674fd72dcc act []
  ifindex 2 kind qdisc_clsact_egress name fbflow_egress
            prog_id 130245 tag 72d2d830d6888d2c
  ]
  $ ./bpftool -jp net
  [{
        "xdp": [{
                "ifindex": 2,
                "devname": "eth0",
                "prog_id": 198
            }
        ],
        "tc_filters": [{
                "ifindex": 2,
                "kind": "qdisc_htb",
                "name": "prefix_matcher.o:[cls_prefix_matcher_htb]",
                "prog_id": 111727,
                "tag": "d08fe3b4319bc2fd",
                "act": []
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_ingress",
                "name": "fbflow_icmp",
                "prog_id": 130246,
                "tag": "3f265c7f26db62c9",
                "act": []
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_egress",
                "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]",
                "prog_id": 111726,
                "tag": "99a197826974c876"
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_egress",
                "name": "cls_fg_dscp",
                "prog_id": 108619,
                "tag": "dc4630674fd72dcc",
                "act": []
            },{
                "ifindex": 2,
                "kind": "qdisc_clsact_egress",
                "name": "fbflow_egress",
                "prog_id": 130245,
                "tag": "72d2d830d6888d2c"
            }
        ]
    }
  ]

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 .../bpf/bpftool/Documentation/bpftool-net.rst | 133 ++++++++++
 tools/bpf/bpftool/Documentation/bpftool.rst   |   6 +-
 tools/bpf/bpftool/bash-completion/bpftool     |  17 +-
 tools/bpf/bpftool/main.c                      |   3 +-
 tools/bpf/bpftool/main.h                      |   7 +
 tools/bpf/bpftool/net.c                       | 233 ++++++++++++++++++
 tools/bpf/bpftool/netlink_dumper.c            | 181 ++++++++++++++
 tools/bpf/bpftool/netlink_dumper.h            | 103 ++++++++
 8 files changed, 676 insertions(+), 7 deletions(-)
 create mode 100644 tools/bpf/bpftool/Documentation/bpftool-net.rst
 create mode 100644 tools/bpf/bpftool/net.c
 create mode 100644 tools/bpf/bpftool/netlink_dumper.c
 create mode 100644 tools/bpf/bpftool/netlink_dumper.h

diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
new file mode 100644
index 000000000000..48a61837a264
--- /dev/null
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -0,0 +1,133 @@
+================
+bpftool-net
+================
+-------------------------------------------------------------------------------
+tool for inspection of netdev/tc related bpf prog attachments
+-------------------------------------------------------------------------------
+
+:Manual section: 8
+
+SYNOPSIS
+========
+
+	**bpftool** [*OPTIONS*] **net** *COMMAND*
+
+	*OPTIONS* := { [{ **-j** | **--json** }] [{ **-p** | **--pretty** }] }
+
+	*COMMANDS* :=
+	{ **show** | **list** } [ **dev** name ] | **help**
+
+NET COMMANDS
+============
+
+|	**bpftool** **net { show | list } [ dev name ]**
+|	**bpftool** **net help**
+
+DESCRIPTION
+===========
+	**bpftool net { show | list } [ dev name ]**
+		  List all networking device driver and tc attachment in the system.
+
+                  Output will start with all xdp program attachment, followed by
+                  all tc class/qdisc bpf program attachments. Both xdp programs and
+                  tc programs are ordered based on ifindex number. If multiple bpf
+                  programs attached to the same networking device through **tc filter**,
+                  the order will be first all bpf programs attached to tc classes, then
+                  all bpf programs attached to non clsact qdiscs, and finally all
+                  bpf programs attached to root and clsact qdisc.
+
+	**bpftool net help**
+		  Print short help message.
+
+OPTIONS
+=======
+	-h, --help
+		  Print short generic help message (similar to **bpftool help**).
+
+	-v, --version
+		  Print version number (similar to **bpftool version**).
+
+	-j, --json
+		  Generate JSON output. For commands that cannot produce JSON, this
+		  option has no effect.
+
+	-p, --pretty
+		  Generate human-readable JSON output. Implies **-j**.
+
+EXAMPLES
+========
+
+| **# bpftool net**
+
+::
+
+      xdp [
+      ifindex 2 devname eth0 prog_id 198
+      ]
+      tc_filters [
+      ifindex 2 kind qdisc_htb name prefix_matcher.o:[cls_prefix_matcher_htb]
+                prog_id 111727 tag d08fe3b4319bc2fd act []
+      ifindex 2 kind qdisc_clsact_ingress name fbflow_icmp
+                prog_id 130246 tag 3f265c7f26db62c9 act []
+      ifindex 2 kind qdisc_clsact_egress name prefix_matcher.o:[cls_prefix_matcher_clsact]
+                prog_id 111726 tag 99a197826974c876
+      ifindex 2 kind qdisc_clsact_egress name cls_fg_dscp
+                prog_id 108619 tag dc4630674fd72dcc act []
+      ifindex 2 kind qdisc_clsact_egress name fbflow_egress
+                prog_id 130245 tag 72d2d830d6888d2c
+      ]
+
+|
+| **# bpftool -jp net**
+
+::
+
+    [{
+            "xdp": [{
+                    "ifindex": 2,
+                    "devname": "eth0",
+                    "prog_id": 198
+                }
+            ],
+            "tc_filters": [{
+                    "ifindex": 2,
+                    "kind": "qdisc_htb",
+                    "name": "prefix_matcher.o:[cls_prefix_matcher_htb]",
+                    "prog_id": 111727,
+                    "tag": "d08fe3b4319bc2fd",
+                    "act": []
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_ingress",
+                    "name": "fbflow_icmp",
+                    "prog_id": 130246,
+                    "tag": "3f265c7f26db62c9",
+                    "act": []
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_egress",
+                    "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]",
+                    "prog_id": 111726,
+                    "tag": "99a197826974c876"
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_egress",
+                    "name": "cls_fg_dscp",
+                    "prog_id": 108619,
+                    "tag": "dc4630674fd72dcc",
+                    "act": []
+                },{
+                    "ifindex": 2,
+                    "kind": "qdisc_clsact_egress",
+                    "name": "fbflow_egress",
+                    "prog_id": 130245,
+                    "tag": "72d2d830d6888d2c"
+                }
+            ]
+        }
+    ]
+
+
+SEE ALSO
+========
+	**bpftool**\ (8), **bpftool-prog**\ (8), **bpftool-map**\ (8)
diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst
index b6f5d560460d..8dda77daeda9 100644
--- a/tools/bpf/bpftool/Documentation/bpftool.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool.rst
@@ -16,7 +16,7 @@ SYNOPSIS
 
 	**bpftool** **version**
 
-	*OBJECT* := { **map** | **program** | **cgroup** | **perf** }
+	*OBJECT* := { **map** | **program** | **cgroup** | **perf** | **net** }
 
 	*OPTIONS* := { { **-V** | **--version** } | { **-h** | **--help** }
 	| { **-j** | **--json** } [{ **-p** | **--pretty** }] }
@@ -32,6 +32,8 @@ SYNOPSIS
 
 	*PERF-COMMANDS* := { **show** | **list** | **help** }
 
+	*NET-COMMANDS* := { **show** | **list** | **help** }
+
 DESCRIPTION
 ===========
 	*bpftool* allows for inspection and simple modification of BPF objects
@@ -58,4 +60,4 @@ OPTIONS
 SEE ALSO
 ========
 	**bpftool-map**\ (8), **bpftool-prog**\ (8), **bpftool-cgroup**\ (8)
-        **bpftool-perf**\ (8)
+        **bpftool-perf**\ (8), **bpftool-net**\ (8)
diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool
index c2b6b2176f3b..ec577af2e5f0 100644
--- a/tools/bpf/bpftool/bash-completion/bpftool
+++ b/tools/bpf/bpftool/bash-completion/bpftool
@@ -494,10 +494,10 @@ _bpftool()
                     _filedir
                     return 0
                     ;;
-		tree)
-		    _filedir
-		    return 0
-		    ;;
+                tree)
+                    _filedir
+                    return 0
+                    ;;
                 attach|detach)
                     local ATTACH_TYPES='ingress egress sock_create sock_ops \
                         device bind4 bind6 post_bind4 post_bind6 connect4 \
@@ -552,6 +552,15 @@ _bpftool()
                     ;;
             esac
             ;;
+        net)
+            case $command in
+                *)
+                    [[ $prev == $object ]] && \
+                        COMPREPLY=( $( compgen -W 'help \
+                            show list' -- "$cur" ) )
+                    ;;
+            esac
+            ;;
     esac
 } &&
 complete -F _bpftool bpftool
diff --git a/tools/bpf/bpftool/main.c b/tools/bpf/bpftool/main.c
index d15a62be6cf0..79dc3f193547 100644
--- a/tools/bpf/bpftool/main.c
+++ b/tools/bpf/bpftool/main.c
@@ -85,7 +85,7 @@ static int do_help(int argc, char **argv)
 		"       %s batch file FILE\n"
 		"       %s version\n"
 		"\n"
-		"       OBJECT := { prog | map | cgroup | perf }\n"
+		"       OBJECT := { prog | map | cgroup | perf | net }\n"
 		"       " HELP_SPEC_OPTIONS "\n"
 		"",
 		bin_name, bin_name, bin_name);
@@ -215,6 +215,7 @@ static const struct cmd cmds[] = {
 	{ "map",	do_map },
 	{ "cgroup",	do_cgroup },
 	{ "perf",	do_perf },
+	{ "net",	do_net },
 	{ "version",	do_version },
 	{ 0 }
 };
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 057a227bdb9f..0a9d2779635c 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -136,6 +136,7 @@ int do_map(int argc, char **arg);
 int do_event_pipe(int argc, char **argv);
 int do_cgroup(int argc, char **arg);
 int do_perf(int argc, char **arg);
+int do_net(int argc, char **arg);
 
 int prog_parse_fd(int *argc, char ***argv);
 int map_parse_fd(int *argc, char ***argv);
@@ -165,4 +166,10 @@ struct btf_dumper {
  */
 int btf_dumper_type(const struct btf_dumper *d, __u32 type_id,
 		    const void *data);
+
+struct nlattr;
+struct ifinfomsg;
+struct tcmsg;
+int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
+int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind);
 #endif
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
new file mode 100644
index 000000000000..77dd73dd9ade
--- /dev/null
+++ b/tools/bpf/bpftool/net.c
@@ -0,0 +1,233 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#define _GNU_SOURCE
+#include <stdlib.h>
+#include <string.h>
+#include <unistd.h>
+#include <libbpf.h>
+#include <net/if.h>
+#include <linux/if.h>
+#include <linux/rtnetlink.h>
+#include <linux/tc_act/tc_bpf.h>
+#include <sys/socket.h>
+
+#include <bpf.h>
+#include <nlattr.h>
+#include "main.h"
+#include "netlink_dumper.h"
+
+struct bpf_netdev_t {
+	int	*ifindex_array;
+	int	used_len;
+	int	array_len;
+	int	filter_idx;
+};
+
+struct tc_kind_handle {
+	char	kind[64];
+	int	handle;
+};
+
+struct bpf_tcinfo_t {
+	struct tc_kind_handle	*handle_array;
+	int			used_len;
+	int			array_len;
+	bool			is_qdisc;
+};
+
+static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+	struct bpf_netdev_t *netinfo = cookie;
+	struct ifinfomsg *ifinfo = msg;
+
+	if (netinfo->filter_idx > 0 && netinfo->filter_idx != ifinfo->ifi_index)
+		return 0;
+
+	if (netinfo->used_len == netinfo->array_len) {
+		netinfo->ifindex_array = realloc(netinfo->ifindex_array,
+			(netinfo->array_len + 16) * sizeof(int));
+		netinfo->array_len += 16;
+	}
+	netinfo->ifindex_array[netinfo->used_len++] = ifinfo->ifi_index;
+
+	return do_xdp_dump(ifinfo, tb);
+}
+
+static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+	struct bpf_tcinfo_t *tcinfo = cookie;
+	struct tcmsg *info = msg;
+
+	if (tcinfo->is_qdisc) {
+		/* skip clsact qdisc */
+		if (tb[TCA_KIND] &&
+		    strcmp(nla_data(tb[TCA_KIND]), "clsact") == 0)
+			return 0;
+		if (info->tcm_handle == 0)
+			return 0;
+	}
+
+	if (tcinfo->used_len == tcinfo->array_len) {
+		tcinfo->handle_array = realloc(tcinfo->handle_array,
+			(tcinfo->array_len + 16) * sizeof(struct tc_kind_handle));
+		tcinfo->array_len += 16;
+	}
+	tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle;
+	snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
+		 sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
+		 "%s_%s",
+		 tcinfo->is_qdisc ? "qdisc" : "class",
+		 tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
+	tcinfo->used_len++;
+
+	return 0;
+}
+
+static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb)
+{
+	const char *kind = cookie;
+
+	return do_filter_dump((struct tcmsg *)msg, tb, kind);
+}
+
+static int show_dev_tc_bpf(int sock, unsigned int nl_pid, int ifindex)
+{
+	struct bpf_tcinfo_t tcinfo;
+	int i, handle, ret;
+
+	tcinfo.handle_array = NULL;
+	tcinfo.used_len = 0;
+	tcinfo.array_len = 0;
+
+	tcinfo.is_qdisc = false;
+	ret = nl_get_class(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+			   &tcinfo);
+	if (ret)
+		return ret;
+
+	tcinfo.is_qdisc = true;
+	ret = nl_get_qdisc(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+			   &tcinfo);
+	if (ret)
+		return ret;
+
+	for (i = 0; i < tcinfo.used_len; i++) {
+		ret = nl_get_filter(sock, nl_pid, ifindex,
+				    tcinfo.handle_array[i].handle,
+				    dump_filter_nlmsg,
+				    tcinfo.handle_array[i].kind);
+		if (ret)
+			return ret;
+	}
+
+	/* root, ingress and egress handle */
+	handle = TC_H_ROOT;
+	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
+			    "root");
+	if (ret)
+		return ret;
+
+	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
+	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
+			    "qdisc_clsact_ingress");
+	if (ret)
+		return ret;
+
+	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
+	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
+			    "qdisc_clsact_egress");
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static int do_show(int argc, char **argv)
+{
+	int i, sock, ret, filter_idx = -1;
+	struct bpf_netdev_t dev_array;
+	unsigned int nl_pid;
+	char err_buf[256];
+
+	if (argc == 2) {
+		if (strcmp(argv[0], "dev") != 0)
+			usage();
+		filter_idx = if_nametoindex(argv[1]);
+		if (filter_idx == 0) {
+			fprintf(stderr, "invalid dev name %s\n", argv[1]);
+			return -1;
+		}
+	} else if (argc != 0) {
+		usage();
+	}
+
+	sock = bpf_netlink_open(&nl_pid);
+	if (sock < 0) {
+		fprintf(stderr, "failed to open netlink sock\n");
+		return -1;
+	}
+
+	dev_array.ifindex_array = NULL;
+	dev_array.used_len = 0;
+	dev_array.array_len = 0;
+	dev_array.filter_idx = filter_idx;
+
+	if (json_output)
+		jsonw_start_array(json_wtr);
+	NET_START_OBJECT;
+	NET_START_ARRAY("xdp", "\n");
+	ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
+	NET_END_ARRAY("\n");
+
+	if (!ret) {
+		NET_START_ARRAY("tc_filters", "\n");
+		for (i = 0; i < dev_array.used_len; i++) {
+			ret = show_dev_tc_bpf(sock, nl_pid,
+					      dev_array.ifindex_array[i]);
+			if (ret)
+				break;
+		}
+		NET_END_ARRAY("\n");
+	}
+	NET_END_OBJECT;
+	if (json_output)
+		jsonw_end_array(json_wtr);
+
+	if (ret) {
+		if (json_output)
+			jsonw_null(json_wtr);
+		libbpf_strerror(ret, err_buf, sizeof(err_buf));
+		fprintf(stderr, "Error: %s\n", err_buf);
+	}
+	free(dev_array.ifindex_array);
+	close(sock);
+	return ret;
+}
+
+static int do_help(int argc, char **argv)
+{
+	if (json_output) {
+		jsonw_null(json_wtr);
+		return 0;
+	}
+
+	fprintf(stderr,
+		"Usage: %s %s { show | list } [dev <devname>]\n"
+		"       %s %s help\n",
+		bin_name, argv[-2], bin_name, argv[-2]);
+
+	return 0;
+}
+
+static const struct cmd cmds[] = {
+	{ "show",	do_show },
+	{ "list",	do_show },
+	{ "help",	do_help },
+	{ 0 }
+};
+
+int do_net(int argc, char **argv)
+{
+	return cmd_select(cmds, argc, argv, do_help);
+}
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
new file mode 100644
index 000000000000..e12494fd1d2e
--- /dev/null
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -0,0 +1,181 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#include <stdlib.h>
+#include <string.h>
+#include <libbpf.h>
+#include <linux/rtnetlink.h>
+#include <linux/tc_act/tc_bpf.h>
+
+#include <nlattr.h>
+#include "main.h"
+#include "netlink_dumper.h"
+
+static void xdp_dump_prog_id(struct nlattr **tb, int attr,
+			     const char *type)
+{
+	if (!tb[attr])
+		return;
+
+	NET_DUMP_UINT(type, nla_getattr_u32(tb[attr]))
+}
+
+static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
+			   const char *name)
+{
+	struct nlattr *tb[IFLA_XDP_MAX + 1];
+	unsigned char mode;
+
+	if (nla_parse_nested(tb, IFLA_XDP_MAX, attr, NULL) < 0)
+		return -1;
+
+	if (!tb[IFLA_XDP_ATTACHED])
+		return 0;
+
+	mode = nla_getattr_u8(tb[IFLA_XDP_ATTACHED]);
+	if (mode == XDP_ATTACHED_NONE)
+		return 0;
+
+	NET_START_OBJECT;
+	NET_DUMP_UINT("ifindex", ifindex);
+
+	if (name)
+		NET_DUMP_STR("devname", name);
+
+	if (tb[IFLA_XDP_PROG_ID])
+		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[IFLA_XDP_PROG_ID]));
+
+	if (mode == XDP_ATTACHED_MULTI) {
+		xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic_prog_id");
+		xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "drv_prog_id");
+		xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload_prog_id");
+	}
+
+	NET_END_OBJECT_FINAL;
+	return 0;
+}
+
+int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
+{
+	if (!tb[IFLA_XDP])
+		return 0;
+
+	return do_xdp_dump_one(tb[IFLA_XDP], ifinfo->ifi_index,
+			       nla_getattr_str(tb[IFLA_IFNAME]));
+}
+
+static char *hexstring_n2a(const unsigned char *str, int len,
+			   char *buf, int blen)
+{
+	char *ptr = buf;
+	int i;
+
+	for (i = 0; i < len; i++) {
+		if (blen < 3)
+			break;
+		sprintf(ptr, "%02x", str[i]);
+		ptr += 2;
+		blen -= 2;
+	}
+	return buf;
+}
+
+static int do_bpf_dump_one_act(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
+	char buf[256];
+
+	if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	if (!tb[TCA_ACT_BPF_PARMS])
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	NET_START_OBJECT_NESTED2;
+	if (tb[TCA_ACT_BPF_NAME])
+		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+	if (tb[TCA_ACT_BPF_ID])
+		NET_DUMP_UINT("bpf_id", nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
+	if (tb[TCA_ACT_BPF_TAG])
+		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_ACT_BPF_TAG]),
+						  nla_len(tb[TCA_ACT_BPF_TAG]),
+						  buf, sizeof(buf)));
+	NET_END_OBJECT_NESTED;
+	return 0;
+}
+
+static int do_dump_one_act(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_ACT_MAX + 1];
+
+	if (!attr)
+		return 0;
+
+	if (nla_parse_nested(tb, TCA_ACT_MAX, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	if (tb[TCA_ACT_KIND] && strcmp(nla_data(tb[TCA_ACT_KIND]), "bpf") == 0)
+		return do_bpf_dump_one_act(tb[TCA_ACT_OPTIONS]);
+
+	return 0;
+}
+
+static int do_bpf_act_dump(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_ACT_MAX_PRIO + 1];
+	int act, ret;
+
+	if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	NET_START_ARRAY("act", "");
+	for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) {
+		ret = do_dump_one_act(tb[act]);
+		if (ret)
+			break;
+	}
+	NET_END_ARRAY(" ");
+
+	return ret;
+}
+
+static int do_bpf_filter_dump(struct nlattr *attr)
+{
+	struct nlattr *tb[TCA_BPF_MAX + 1];
+	char buf[256];
+	int ret;
+
+	if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
+		return -LIBBPF_ERRNO__NLPARSE;
+
+	if (tb[TCA_BPF_NAME])
+		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_BPF_NAME]));
+	if (tb[TCA_BPF_ID])
+		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[TCA_BPF_ID]));
+	if (tb[TCA_BPF_TAG])
+		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_BPF_TAG]),
+						  nla_len(tb[TCA_BPF_TAG]),
+						  buf, sizeof(buf)));
+	if (tb[TCA_BPF_ACT]) {
+		ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind)
+{
+	int ret = 0;
+
+	if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
+		NET_START_OBJECT;
+		NET_DUMP_UINT("ifindex", info->tcm_ifindex);
+		NET_DUMP_STR("kind", kind);
+		ret = do_bpf_filter_dump(tb[TCA_OPTIONS]);
+		NET_END_OBJECT_FINAL;
+	}
+
+	return ret;
+}
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
new file mode 100644
index 000000000000..552d8851ac06
--- /dev/null
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -0,0 +1,103 @@
+// SPDX-License-Identifier: GPL-2.0+
+// Copyright (C) 2018 Facebook
+
+#ifndef _NETLINK_DUMPER_H_
+#define _NETLINK_DUMPER_H_
+
+#define NET_START_OBJECT				\
+{							\
+	if (json_output)				\
+		jsonw_start_object(json_wtr);		\
+}
+
+#define NET_START_OBJECT_NESTED(name)			\
+{							\
+	if (json_output) {				\
+		jsonw_name(json_wtr, name);		\
+		jsonw_start_object(json_wtr);		\
+	} else {					\
+		fprintf(stderr, "%s {", name);		\
+	}						\
+}
+
+#define NET_START_OBJECT_NESTED2			\
+{							\
+	if (json_output)				\
+		jsonw_start_object(json_wtr);		\
+	else						\
+		fprintf(stderr, "{");			\
+}
+
+#define NET_END_OBJECT_NESTED				\
+{							\
+	if (json_output)				\
+		jsonw_end_object(json_wtr);		\
+	else						\
+		fprintf(stderr, "}");			\
+}
+
+#define NET_END_OBJECT					\
+{							\
+	if (json_output)				\
+		jsonw_end_object(json_wtr);		\
+}
+
+#define NET_END_OBJECT_FINAL				\
+{							\
+	if (json_output)				\
+		jsonw_end_object(json_wtr);		\
+	else						\
+		fprintf(stderr, "\n");			\
+}
+
+#define NET_START_ARRAY(name, newline)			\
+{							\
+	if (json_output) {				\
+		jsonw_name(json_wtr, name);		\
+		jsonw_start_array(json_wtr);		\
+	} else {					\
+		fprintf(stderr, "%s [%s", name, newline);\
+	}						\
+}
+
+#define NET_END_ARRAY(endstr)				\
+{							\
+	if (json_output)				\
+		jsonw_end_array(json_wtr);		\
+	else						\
+		fprintf(stderr, "]%s", endstr);		\
+}
+
+#define NET_DUMP_UINT(name, val)			\
+{							\
+	if (json_output)				\
+		jsonw_uint_field(json_wtr, name, val);	\
+	else						\
+		fprintf(stderr, "%s %d ", name, val);	\
+}
+
+#define NET_DUMP_LLUINT(name, val)			\
+{							\
+	if (json_output)				\
+		jsonw_lluint_field(json_wtr, name, val);\
+	else						\
+		fprintf(stderr, "%s %lld ", name, val);	\
+}
+
+#define NET_DUMP_STR(name, str)				\
+{							\
+	if (json_output)				\
+		jsonw_string_field(json_wtr, name, str);\
+	else						\
+		fprintf(stderr, "%s %s ", name, str);	\
+}
+
+#define NET_DUMP_STR_ONLY(str)				\
+{							\
+	if (json_output)				\
+		jsonw_string(json_wtr, str);		\
+	else						\
+		fprintf(stderr, "%s ", str);		\
+}
+
+#endif
-- 
Gitee


From 83b53756cc09d0c60882d9cd4dbb0fac17cd4732 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 2 Jun 2023 16:30:50 +0800
Subject: [PATCH 05/12] tools/bpf: fix a netlink recv issue
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ANBZ: #5530

commit 9d0b3c1f1451d1b9a33de3c70ae3d50ccd77db1a upstream

Commit f7010770fbac ("tools/bpf: move bpf/lib netlink related
functions into a new file") introduced a while loop for the
netlink recv path. This while loop is needed since the
buffer in recv syscall may not be enough to hold all the
information and in such cases multiple recv calls are needed.

There is a bug introduced by the above commit as
the while loop may block on recv syscall if there is no
more messages are expected. The netlink message header
flag NLM_F_MULTI is used to indicate that more messages
are expected and this patch fixed the bug by doing
further recv syscall only if multipart message is expected.

The patch added another fix regarding to message length of 0.
When netlink recv returns message length of 0, there will be
no more messages for returning data so the while loop
can end.

Fixes: f7010770fbac ("tools/bpf: move bpf/lib netlink related functions into a new file")
Reported-by: Björn Töpel <bjorn.topel@intel.com>
Tested-by: Björn Töpel <bjorn.topel@intel.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/lib/bpf/netlink.c | 9 ++++++++-
 1 file changed, 8 insertions(+), 1 deletion(-)

diff --git a/tools/lib/bpf/netlink.c b/tools/lib/bpf/netlink.c
index 469e068dd0c5..fde1d7bf8199 100644
--- a/tools/lib/bpf/netlink.c
+++ b/tools/lib/bpf/netlink.c
@@ -65,18 +65,23 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 			    __dump_nlmsg_t _fn, dump_nlmsg_t fn,
 			    void *cookie)
 {
+	bool multipart = true;
 	struct nlmsgerr *err;
 	struct nlmsghdr *nh;
 	char buf[4096];
 	int len, ret;
 
-	while (1) {
+	while (multipart) {
+		multipart = false;
 		len = recv(sock, buf, sizeof(buf), 0);
 		if (len < 0) {
 			ret = -errno;
 			goto done;
 		}
 
+		if (len == 0)
+			break;
+
 		for (nh = (struct nlmsghdr *)buf; NLMSG_OK(nh, len);
 		     nh = NLMSG_NEXT(nh, len)) {
 			if (nh->nlmsg_pid != nl_pid) {
@@ -87,6 +92,8 @@ static int bpf_netlink_recv(int sock, __u32 nl_pid, int seq,
 				ret = -LIBBPF_ERRNO__INVSEQ;
 				goto done;
 			}
+			if (nh->nlmsg_flags & NLM_F_MULTI)
+				multipart = true;
 			switch (nh->nlmsg_type) {
 			case NLMSG_ERROR:
 				err = (struct nlmsgerr *)NLMSG_DATA(nh);
-- 
Gitee


From 165d6f0ad582067e91c1422546628176eb927aa9 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 2 Jun 2023 16:34:15 +0800
Subject: [PATCH 06/12] tools/bpf: bpftool: improve output format for bpftool
 net

ANBZ: #5530

commit 7900efc19214e326913dc0f0e8ded24adc0018f2 upstream

This is a followup patch for Commit f6f3bac08ff9
("tools/bpf: bpftool: add net support").
Some improvements are made for the bpftool net output.
Specially, plain output is more concise such that
per attachment should nicely fit in one line.
Compared to previous output, the prog tag is removed
since it can be easily obtained with program id.
Similar to xdp attachments, the device name is added
to tc attachments.

The bpf program attached through shared block
mechanism is supported as well.
  $ ip link add dev v1 type veth peer name v2
  $ tc qdisc add dev v1 ingress_block 10 egress_block 20 clsact
  $ tc qdisc add dev v2 ingress_block 10 egress_block 20 clsact
  $ tc filter add block 10 protocol ip prio 25 bpf obj bpf_shared.o sec ingress flowid 1:1
  $ tc filter add block 20 protocol ip prio 30 bpf obj bpf_cyclic.o sec classifier flowid 1:1
  $ bpftool net
  xdp:

  tc:
  v2(7) clsact/ingress bpf_shared.o:[ingress] id 23
  v2(7) clsact/egress bpf_cyclic.o:[classifier] id 24
  v1(8) clsact/ingress bpf_shared.o:[ingress] id 23
  v1(8) clsact/egress bpf_cyclic.o:[classifier] id 24

The documentation and "bpftool net help" are updated
to make it clear that current implementation only
supports xdp and tc attachments. For programs
attached to cgroups, "bpftool cgroup" can be used
to dump attachments. For other programs e.g.
sk_{filter,skb,msg,reuseport} and lwt/seg6,
iproute2 tools should be used.

The new output:
  $ bpftool net
  xdp:
  eth0(2) driver id 198

  tc:
  eth0(2) clsact/ingress fbflow_icmp id 335 act [{icmp_action id 336}]
  eth0(2) clsact/egress fbflow_egress id 334
  $ bpftool -jp net
  [{
        "xdp": [{
                "devname": "eth0",
                "ifindex": 2,
                "mode": "driver",
                "id": 198
            }
        ],
        "tc": [{
                "devname": "eth0",
                "ifindex": 2,
                "kind": "clsact/ingress",
                "name": "fbflow_icmp",
                "id": 335,
               "act": [{
                        "name": "icmp_action",
                        "id": 336
                    }
                ]
            },{
                "devname": "eth0",
                "ifindex": 2,
                "kind": "clsact/egress",
                "name": "fbflow_egress",
                "id": 334
            }
        ]
    }
  ]

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 .../bpf/bpftool/Documentation/bpftool-net.rst |  78 +++++++------
 tools/bpf/bpftool/main.h                      |   3 +-
 tools/bpf/bpftool/net.c                       | 103 ++++++++++++------
 tools/bpf/bpftool/netlink_dumper.c            |  85 +++++++--------
 tools/bpf/bpftool/netlink_dumper.h            |  22 ++--
 5 files changed, 161 insertions(+), 130 deletions(-)

diff --git a/tools/bpf/bpftool/Documentation/bpftool-net.rst b/tools/bpf/bpftool/Documentation/bpftool-net.rst
index 48a61837a264..408ec30d8872 100644
--- a/tools/bpf/bpftool/Documentation/bpftool-net.rst
+++ b/tools/bpf/bpftool/Documentation/bpftool-net.rst
@@ -26,9 +26,20 @@ NET COMMANDS
 DESCRIPTION
 ===========
 	**bpftool net { show | list } [ dev name ]**
-		  List all networking device driver and tc attachment in the system.
-
-                  Output will start with all xdp program attachment, followed by
+                  List bpf program attachments in the kernel networking subsystem.
+
+                  Currently, only device driver xdp attachments and tc filter
+                  classification/action attachments are implemented, i.e., for
+                  program types **BPF_PROG_TYPE_SCHED_CLS**,
+                  **BPF_PROG_TYPE_SCHED_ACT** and **BPF_PROG_TYPE_XDP**.
+                  For programs attached to a particular cgroup, e.g.,
+                  **BPF_PROG_TYPE_CGROUP_SKB**, **BPF_PROG_TYPE_CGROUP_SOCK**,
+                  **BPF_PROG_TYPE_SOCK_OPS** and **BPF_PROG_TYPE_CGROUP_SOCK_ADDR**,
+                  users can use **bpftool cgroup** to dump cgroup attachments.
+                  For sk_{filter, skb, msg, reuseport} and lwt/seg6
+                  bpf programs, users should consult other tools, e.g., iproute2.
+
+                  The current output will start with all xdp program attachments, followed by
                   all tc class/qdisc bpf program attachments. Both xdp programs and
                   tc programs are ordered based on ifindex number. If multiple bpf
                   programs attached to the same networking device through **tc filter**,
@@ -61,21 +72,15 @@ EXAMPLES
 
 ::
 
-      xdp [
-      ifindex 2 devname eth0 prog_id 198
-      ]
-      tc_filters [
-      ifindex 2 kind qdisc_htb name prefix_matcher.o:[cls_prefix_matcher_htb]
-                prog_id 111727 tag d08fe3b4319bc2fd act []
-      ifindex 2 kind qdisc_clsact_ingress name fbflow_icmp
-                prog_id 130246 tag 3f265c7f26db62c9 act []
-      ifindex 2 kind qdisc_clsact_egress name prefix_matcher.o:[cls_prefix_matcher_clsact]
-                prog_id 111726 tag 99a197826974c876
-      ifindex 2 kind qdisc_clsact_egress name cls_fg_dscp
-                prog_id 108619 tag dc4630674fd72dcc act []
-      ifindex 2 kind qdisc_clsact_egress name fbflow_egress
-                prog_id 130245 tag 72d2d830d6888d2c
-      ]
+      xdp:
+      eth0(2) driver id 198
+
+      tc:
+      eth0(2) htb name prefix_matcher.o:[cls_prefix_matcher_htb] id 111727 act []
+      eth0(2) clsact/ingress fbflow_icmp id 130246 act []
+      eth0(2) clsact/egress prefix_matcher.o:[cls_prefix_matcher_clsact] id 111726
+      eth0(2) clsact/egress cls_fg_dscp id 108619 act []
+      eth0(2) clsact/egress fbflow_egress id 130245
 
 |
 | **# bpftool -jp net**
@@ -84,44 +89,45 @@ EXAMPLES
 
     [{
             "xdp": [{
-                    "ifindex": 2,
                     "devname": "eth0",
-                    "prog_id": 198
+                    "ifindex": 2,
+                    "mode": "driver",
+                    "id": 198
                 }
             ],
-            "tc_filters": [{
+            "tc": [{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_htb",
+                    "kind": "htb",
                     "name": "prefix_matcher.o:[cls_prefix_matcher_htb]",
-                    "prog_id": 111727,
-                    "tag": "d08fe3b4319bc2fd",
+                    "id": 111727,
                     "act": []
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_ingress",
+                    "kind": "clsact/ingress",
                     "name": "fbflow_icmp",
-                    "prog_id": 130246,
-                    "tag": "3f265c7f26db62c9",
+                    "id": 130246,
                     "act": []
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_egress",
+                    "kind": "clsact/egress",
                     "name": "prefix_matcher.o:[cls_prefix_matcher_clsact]",
-                    "prog_id": 111726,
-                    "tag": "99a197826974c876"
+                    "id": 111726,
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_egress",
+                    "kind": "clsact/egress",
                     "name": "cls_fg_dscp",
-                    "prog_id": 108619,
-                    "tag": "dc4630674fd72dcc",
+                    "id": 108619,
                     "act": []
                 },{
+                    "devname": "eth0",
                     "ifindex": 2,
-                    "kind": "qdisc_clsact_egress",
+                    "kind": "clsact/egress",
                     "name": "fbflow_egress",
-                    "prog_id": 130245,
-                    "tag": "72d2d830d6888d2c"
+                    "id": 130245,
                 }
             ]
         }
diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h
index 0a9d2779635c..38413a16ab92 100644
--- a/tools/bpf/bpftool/main.h
+++ b/tools/bpf/bpftool/main.h
@@ -171,5 +171,6 @@ struct nlattr;
 struct ifinfomsg;
 struct tcmsg;
 int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb);
-int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind);
+int do_filter_dump(struct tcmsg *ifinfo, struct nlattr **tb, const char *kind,
+		   const char *devname, int ifindex);
 #endif
diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index 77dd73dd9ade..ed205ee57655 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -2,6 +2,7 @@
 // Copyright (C) 2018 Facebook
 
 #define _GNU_SOURCE
+#include <errno.h>
 #include <stdlib.h>
 #include <string.h>
 #include <unistd.h>
@@ -17,8 +18,13 @@
 #include "main.h"
 #include "netlink_dumper.h"
 
+struct ip_devname_ifindex {
+	char	devname[64];
+	int	ifindex;
+};
+
 struct bpf_netdev_t {
-	int	*ifindex_array;
+	struct ip_devname_ifindex *devices;
 	int	used_len;
 	int	array_len;
 	int	filter_idx;
@@ -36,6 +42,12 @@ struct bpf_tcinfo_t {
 	bool			is_qdisc;
 };
 
+struct bpf_filter_t {
+	const char	*kind;
+	const char	*devname;
+	int		ifindex;
+};
+
 static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 {
 	struct bpf_netdev_t *netinfo = cookie;
@@ -45,11 +57,20 @@ static int dump_link_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 		return 0;
 
 	if (netinfo->used_len == netinfo->array_len) {
-		netinfo->ifindex_array = realloc(netinfo->ifindex_array,
-			(netinfo->array_len + 16) * sizeof(int));
+		netinfo->devices = realloc(netinfo->devices,
+			(netinfo->array_len + 16) *
+			sizeof(struct ip_devname_ifindex));
+		if (!netinfo->devices)
+			return -ENOMEM;
+
 		netinfo->array_len += 16;
 	}
-	netinfo->ifindex_array[netinfo->used_len++] = ifinfo->ifi_index;
+	netinfo->devices[netinfo->used_len].ifindex = ifinfo->ifi_index;
+	snprintf(netinfo->devices[netinfo->used_len].devname,
+		 sizeof(netinfo->devices[netinfo->used_len].devname),
+		 "%s",
+		 tb[IFLA_IFNAME] ? nla_getattr_str(tb[IFLA_IFNAME]) : "");
+	netinfo->used_len++;
 
 	return do_xdp_dump(ifinfo, tb);
 }
@@ -71,13 +92,15 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 	if (tcinfo->used_len == tcinfo->array_len) {
 		tcinfo->handle_array = realloc(tcinfo->handle_array,
 			(tcinfo->array_len + 16) * sizeof(struct tc_kind_handle));
+		if (!tcinfo->handle_array)
+			return -ENOMEM;
+
 		tcinfo->array_len += 16;
 	}
 	tcinfo->handle_array[tcinfo->used_len].handle = info->tcm_handle;
 	snprintf(tcinfo->handle_array[tcinfo->used_len].kind,
 		 sizeof(tcinfo->handle_array[tcinfo->used_len].kind),
-		 "%s_%s",
-		 tcinfo->is_qdisc ? "qdisc" : "class",
+		 "%s",
 		 tb[TCA_KIND] ? nla_getattr_str(tb[TCA_KIND]) : "unknown");
 	tcinfo->used_len++;
 
@@ -86,60 +109,71 @@ static int dump_class_qdisc_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 
 static int dump_filter_nlmsg(void *cookie, void *msg, struct nlattr **tb)
 {
-	const char *kind = cookie;
+	const struct bpf_filter_t *filter_info = cookie;
 
-	return do_filter_dump((struct tcmsg *)msg, tb, kind);
+	return do_filter_dump((struct tcmsg *)msg, tb, filter_info->kind,
+			      filter_info->devname, filter_info->ifindex);
 }
 
-static int show_dev_tc_bpf(int sock, unsigned int nl_pid, int ifindex)
+static int show_dev_tc_bpf(int sock, unsigned int nl_pid,
+			   struct ip_devname_ifindex *dev)
 {
+	struct bpf_filter_t filter_info;
 	struct bpf_tcinfo_t tcinfo;
-	int i, handle, ret;
+	int i, handle, ret = 0;
 
 	tcinfo.handle_array = NULL;
 	tcinfo.used_len = 0;
 	tcinfo.array_len = 0;
 
 	tcinfo.is_qdisc = false;
-	ret = nl_get_class(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+	ret = nl_get_class(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
 			   &tcinfo);
 	if (ret)
-		return ret;
+		goto out;
 
 	tcinfo.is_qdisc = true;
-	ret = nl_get_qdisc(sock, nl_pid, ifindex, dump_class_qdisc_nlmsg,
+	ret = nl_get_qdisc(sock, nl_pid, dev->ifindex, dump_class_qdisc_nlmsg,
 			   &tcinfo);
 	if (ret)
-		return ret;
+		goto out;
 
+	filter_info.devname = dev->devname;
+	filter_info.ifindex = dev->ifindex;
 	for (i = 0; i < tcinfo.used_len; i++) {
-		ret = nl_get_filter(sock, nl_pid, ifindex,
+		filter_info.kind = tcinfo.handle_array[i].kind;
+		ret = nl_get_filter(sock, nl_pid, dev->ifindex,
 				    tcinfo.handle_array[i].handle,
 				    dump_filter_nlmsg,
-				    tcinfo.handle_array[i].kind);
+				    &filter_info);
 		if (ret)
-			return ret;
+			goto out;
 	}
 
 	/* root, ingress and egress handle */
 	handle = TC_H_ROOT;
-	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
-			    "root");
+	filter_info.kind = "root";
+	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+			    dump_filter_nlmsg, &filter_info);
 	if (ret)
-		return ret;
+		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
-	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
-			    "qdisc_clsact_ingress");
+	filter_info.kind = "clsact/ingress";
+	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+			    dump_filter_nlmsg, &filter_info);
 	if (ret)
-		return ret;
+		goto out;
 
 	handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_EGRESS);
-	ret = nl_get_filter(sock, nl_pid, ifindex, handle, dump_filter_nlmsg,
-			    "qdisc_clsact_egress");
+	filter_info.kind = "clsact/egress";
+	ret = nl_get_filter(sock, nl_pid, dev->ifindex, handle,
+			    dump_filter_nlmsg, &filter_info);
 	if (ret)
-		return ret;
+		goto out;
 
+out:
+	free(tcinfo.handle_array);
 	return 0;
 }
 
@@ -168,7 +202,7 @@ static int do_show(int argc, char **argv)
 		return -1;
 	}
 
-	dev_array.ifindex_array = NULL;
+	dev_array.devices = NULL;
 	dev_array.used_len = 0;
 	dev_array.array_len = 0;
 	dev_array.filter_idx = filter_idx;
@@ -176,15 +210,15 @@ static int do_show(int argc, char **argv)
 	if (json_output)
 		jsonw_start_array(json_wtr);
 	NET_START_OBJECT;
-	NET_START_ARRAY("xdp", "\n");
+	NET_START_ARRAY("xdp", "%s:\n");
 	ret = nl_get_link(sock, nl_pid, dump_link_nlmsg, &dev_array);
 	NET_END_ARRAY("\n");
 
 	if (!ret) {
-		NET_START_ARRAY("tc_filters", "\n");
+		NET_START_ARRAY("tc", "%s:\n");
 		for (i = 0; i < dev_array.used_len; i++) {
 			ret = show_dev_tc_bpf(sock, nl_pid,
-					      dev_array.ifindex_array[i]);
+					      &dev_array.devices[i]);
 			if (ret)
 				break;
 		}
@@ -200,7 +234,7 @@ static int do_show(int argc, char **argv)
 		libbpf_strerror(ret, err_buf, sizeof(err_buf));
 		fprintf(stderr, "Error: %s\n", err_buf);
 	}
-	free(dev_array.ifindex_array);
+	free(dev_array.devices);
 	close(sock);
 	return ret;
 }
@@ -214,7 +248,12 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %s %s { show | list } [dev <devname>]\n"
-		"       %s %s help\n",
+		"       %s %s help\n"
+		"Note: Only xdp and tc attachments are supported now.\n"
+		"      For progs attached to cgroups, use \"bpftool cgroup\"\n"
+		"      to dump program attachments. For program types\n"
+		"      sk_{filter,skb,msg,reuseport} and lwt/seg6, please\n"
+		"      consult iproute2.\n",
 		bin_name, argv[-2], bin_name, argv[-2]);
 
 	return 0;
diff --git a/tools/bpf/bpftool/netlink_dumper.c b/tools/bpf/bpftool/netlink_dumper.c
index e12494fd1d2e..6f5e9cc6836c 100644
--- a/tools/bpf/bpftool/netlink_dumper.c
+++ b/tools/bpf/bpftool/netlink_dumper.c
@@ -12,12 +12,18 @@
 #include "netlink_dumper.h"
 
 static void xdp_dump_prog_id(struct nlattr **tb, int attr,
-			     const char *type)
+			     const char *mode,
+			     bool new_json_object)
 {
 	if (!tb[attr])
 		return;
 
-	NET_DUMP_UINT(type, nla_getattr_u32(tb[attr]))
+	if (new_json_object)
+		NET_START_OBJECT
+	NET_DUMP_STR("mode", " %s", mode);
+	NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[attr]))
+	if (new_json_object)
+		NET_END_OBJECT
 }
 
 static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
@@ -37,18 +43,26 @@ static int do_xdp_dump_one(struct nlattr *attr, unsigned int ifindex,
 		return 0;
 
 	NET_START_OBJECT;
-	NET_DUMP_UINT("ifindex", ifindex);
-
 	if (name)
-		NET_DUMP_STR("devname", name);
-
-	if (tb[IFLA_XDP_PROG_ID])
-		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[IFLA_XDP_PROG_ID]));
+		NET_DUMP_STR("devname", "%s", name);
+	NET_DUMP_UINT("ifindex", "(%d)", ifindex);
 
 	if (mode == XDP_ATTACHED_MULTI) {
-		xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic_prog_id");
-		xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "drv_prog_id");
-		xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload_prog_id");
+		if (json_output) {
+			jsonw_name(json_wtr, "multi_attachments");
+			jsonw_start_array(json_wtr);
+		}
+		xdp_dump_prog_id(tb, IFLA_XDP_SKB_PROG_ID, "generic", true);
+		xdp_dump_prog_id(tb, IFLA_XDP_DRV_PROG_ID, "driver", true);
+		xdp_dump_prog_id(tb, IFLA_XDP_HW_PROG_ID, "offload", true);
+		if (json_output)
+			jsonw_end_array(json_wtr);
+	} else if (mode == XDP_ATTACHED_DRV) {
+		xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "driver", false);
+	} else if (mode == XDP_ATTACHED_SKB) {
+		xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "generic", false);
+	} else if (mode == XDP_ATTACHED_HW) {
+		xdp_dump_prog_id(tb, IFLA_XDP_PROG_ID, "offload", false);
 	}
 
 	NET_END_OBJECT_FINAL;
@@ -64,26 +78,9 @@ int do_xdp_dump(struct ifinfomsg *ifinfo, struct nlattr **tb)
 			       nla_getattr_str(tb[IFLA_IFNAME]));
 }
 
-static char *hexstring_n2a(const unsigned char *str, int len,
-			   char *buf, int blen)
-{
-	char *ptr = buf;
-	int i;
-
-	for (i = 0; i < len; i++) {
-		if (blen < 3)
-			break;
-		sprintf(ptr, "%02x", str[i]);
-		ptr += 2;
-		blen -= 2;
-	}
-	return buf;
-}
-
 static int do_bpf_dump_one_act(struct nlattr *attr)
 {
 	struct nlattr *tb[TCA_ACT_BPF_MAX + 1];
-	char buf[256];
 
 	if (nla_parse_nested(tb, TCA_ACT_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
@@ -93,13 +90,11 @@ static int do_bpf_dump_one_act(struct nlattr *attr)
 
 	NET_START_OBJECT_NESTED2;
 	if (tb[TCA_ACT_BPF_NAME])
-		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
+		NET_DUMP_STR("name", "%s",
+			     nla_getattr_str(tb[TCA_ACT_BPF_NAME]));
 	if (tb[TCA_ACT_BPF_ID])
-		NET_DUMP_UINT("bpf_id", nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
-	if (tb[TCA_ACT_BPF_TAG])
-		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_ACT_BPF_TAG]),
-						  nla_len(tb[TCA_ACT_BPF_TAG]),
-						  buf, sizeof(buf)));
+		NET_DUMP_UINT("id", " id %u",
+			      nla_getattr_u32(tb[TCA_ACT_BPF_ID]));
 	NET_END_OBJECT_NESTED;
 	return 0;
 }
@@ -128,13 +123,13 @@ static int do_bpf_act_dump(struct nlattr *attr)
 	if (nla_parse_nested(tb, TCA_ACT_MAX_PRIO, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
-	NET_START_ARRAY("act", "");
+	NET_START_ARRAY("act", " %s [");
 	for (act = 0; act <= TCA_ACT_MAX_PRIO; act++) {
 		ret = do_dump_one_act(tb[act]);
 		if (ret)
 			break;
 	}
-	NET_END_ARRAY(" ");
+	NET_END_ARRAY("] ");
 
 	return ret;
 }
@@ -142,20 +137,15 @@ static int do_bpf_act_dump(struct nlattr *attr)
 static int do_bpf_filter_dump(struct nlattr *attr)
 {
 	struct nlattr *tb[TCA_BPF_MAX + 1];
-	char buf[256];
 	int ret;
 
 	if (nla_parse_nested(tb, TCA_BPF_MAX, attr, NULL) < 0)
 		return -LIBBPF_ERRNO__NLPARSE;
 
 	if (tb[TCA_BPF_NAME])
-		NET_DUMP_STR("name", nla_getattr_str(tb[TCA_BPF_NAME]));
+		NET_DUMP_STR("name", " %s", nla_getattr_str(tb[TCA_BPF_NAME]));
 	if (tb[TCA_BPF_ID])
-		NET_DUMP_UINT("prog_id", nla_getattr_u32(tb[TCA_BPF_ID]));
-	if (tb[TCA_BPF_TAG])
-		NET_DUMP_STR("tag", hexstring_n2a(nla_data(tb[TCA_BPF_TAG]),
-						  nla_len(tb[TCA_BPF_TAG]),
-						  buf, sizeof(buf)));
+		NET_DUMP_UINT("id", " id %u", nla_getattr_u32(tb[TCA_BPF_ID]));
 	if (tb[TCA_BPF_ACT]) {
 		ret = do_bpf_act_dump(tb[TCA_BPF_ACT]);
 		if (ret)
@@ -165,14 +155,17 @@ static int do_bpf_filter_dump(struct nlattr *attr)
 	return 0;
 }
 
-int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind)
+int do_filter_dump(struct tcmsg *info, struct nlattr **tb, const char *kind,
+		   const char *devname, int ifindex)
 {
 	int ret = 0;
 
 	if (tb[TCA_OPTIONS] && strcmp(nla_data(tb[TCA_KIND]), "bpf") == 0) {
 		NET_START_OBJECT;
-		NET_DUMP_UINT("ifindex", info->tcm_ifindex);
-		NET_DUMP_STR("kind", kind);
+		if (devname[0] != '\0')
+			NET_DUMP_STR("devname", "%s", devname);
+		NET_DUMP_UINT("ifindex", "(%u)", ifindex);
+		NET_DUMP_STR("kind", " %s", kind);
 		ret = do_bpf_filter_dump(tb[TCA_OPTIONS]);
 		NET_END_OBJECT_FINAL;
 	}
diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index 552d8851ac06..0788cfbbed0e 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -50,13 +50,13 @@
 		fprintf(stderr, "\n");			\
 }
 
-#define NET_START_ARRAY(name, newline)			\
+#define NET_START_ARRAY(name, fmt_str)			\
 {							\
 	if (json_output) {				\
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_array(json_wtr);		\
 	} else {					\
-		fprintf(stderr, "%s [%s", name, newline);\
+		fprintf(stderr, fmt_str, name);		\
 	}						\
 }
 
@@ -65,31 +65,23 @@
 	if (json_output)				\
 		jsonw_end_array(json_wtr);		\
 	else						\
-		fprintf(stderr, "]%s", endstr);		\
+		fprintf(stderr, "%s", endstr);		\
 }
 
-#define NET_DUMP_UINT(name, val)			\
+#define NET_DUMP_UINT(name, fmt_str, val)		\
 {							\
 	if (json_output)				\
 		jsonw_uint_field(json_wtr, name, val);	\
 	else						\
-		fprintf(stderr, "%s %d ", name, val);	\
+		fprintf(stderr, fmt_str, val);		\
 }
 
-#define NET_DUMP_LLUINT(name, val)			\
-{							\
-	if (json_output)				\
-		jsonw_lluint_field(json_wtr, name, val);\
-	else						\
-		fprintf(stderr, "%s %lld ", name, val);	\
-}
-
-#define NET_DUMP_STR(name, str)				\
+#define NET_DUMP_STR(name, fmt_str, str)		\
 {							\
 	if (json_output)				\
 		jsonw_string_field(json_wtr, name, str);\
 	else						\
-		fprintf(stderr, "%s %s ", name, str);	\
+		fprintf(stderr, fmt_str, str);		\
 }
 
 #define NET_DUMP_STR_ONLY(str)				\
-- 
Gitee


From 28922e3005fb85878363e0c2543fee3632d348ef Mon Sep 17 00:00:00 2001
From: Andrey Ignatov <rdna@fb.com>
Date: Fri, 2 Jun 2023 16:41:26 +0800
Subject: [PATCH 07/12] bpftool: Fix bpftool net output

ANBZ: #5530

commit 53d6eb08e9f185834231d5c32499b10310cce3aa upstream

Print `bpftool net` output to stdout instead of stderr. Only errors
should be printed to stderr. Regular output should go to stdout and this
is what all other subcommands of bpftool do, including --json and
--pretty formats of `bpftool net` itself.

Fixes: commit f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Signed-off-by: Andrey Ignatov <rdna@fb.com>
Acked-by: Yonghong Song <yhs@fb.com>
Acked-by: Song Liu <songliubraving@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/bpf/bpftool/netlink_dumper.h | 18 +++++++++---------
 1 file changed, 9 insertions(+), 9 deletions(-)

diff --git a/tools/bpf/bpftool/netlink_dumper.h b/tools/bpf/bpftool/netlink_dumper.h
index 0788cfbbed0e..e3516b586a34 100644
--- a/tools/bpf/bpftool/netlink_dumper.h
+++ b/tools/bpf/bpftool/netlink_dumper.h
@@ -16,7 +16,7 @@
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_object(json_wtr);		\
 	} else {					\
-		fprintf(stderr, "%s {", name);		\
+		fprintf(stdout, "%s {", name);		\
 	}						\
 }
 
@@ -25,7 +25,7 @@
 	if (json_output)				\
 		jsonw_start_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "{");			\
+		fprintf(stdout, "{");			\
 }
 
 #define NET_END_OBJECT_NESTED				\
@@ -33,7 +33,7 @@
 	if (json_output)				\
 		jsonw_end_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "}");			\
+		fprintf(stdout, "}");			\
 }
 
 #define NET_END_OBJECT					\
@@ -47,7 +47,7 @@
 	if (json_output)				\
 		jsonw_end_object(json_wtr);		\
 	else						\
-		fprintf(stderr, "\n");			\
+		fprintf(stdout, "\n");			\
 }
 
 #define NET_START_ARRAY(name, fmt_str)			\
@@ -56,7 +56,7 @@
 		jsonw_name(json_wtr, name);		\
 		jsonw_start_array(json_wtr);		\
 	} else {					\
-		fprintf(stderr, fmt_str, name);		\
+		fprintf(stdout, fmt_str, name);		\
 	}						\
 }
 
@@ -65,7 +65,7 @@
 	if (json_output)				\
 		jsonw_end_array(json_wtr);		\
 	else						\
-		fprintf(stderr, "%s", endstr);		\
+		fprintf(stdout, "%s", endstr);		\
 }
 
 #define NET_DUMP_UINT(name, fmt_str, val)		\
@@ -73,7 +73,7 @@
 	if (json_output)				\
 		jsonw_uint_field(json_wtr, name, val);	\
 	else						\
-		fprintf(stderr, fmt_str, val);		\
+		fprintf(stdout, fmt_str, val);		\
 }
 
 #define NET_DUMP_STR(name, fmt_str, str)		\
@@ -81,7 +81,7 @@
 	if (json_output)				\
 		jsonw_string_field(json_wtr, name, str);\
 	else						\
-		fprintf(stderr, fmt_str, str);		\
+		fprintf(stdout, fmt_str, str);		\
 }
 
 #define NET_DUMP_STR_ONLY(str)				\
@@ -89,7 +89,7 @@
 	if (json_output)				\
 		jsonw_string(json_wtr, str);		\
 	else						\
-		fprintf(stderr, "%s ", str);		\
+		fprintf(stdout, "%s ", str);		\
 }
 
 #endif
-- 
Gitee


From 4e6879dc2a580f3817304a5c62fba1436b5e5c43 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Wed, 5 Jul 2023 14:11:36 +0800
Subject: [PATCH 08/12] tools/bpftool: copy a few net uapi headers to tools
 directory

ANBZ: #5530

commit 49a249c387268882e8393dd1fafc51e3b21cb7a2 upstream

Commit f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
added certain networking support to bpftool.
The implementation relies on a relatively recent uapi header file
linux/tc_act/tc_bpf.h on the host which contains the marco
definition of TCA_ACT_BPF_ID.

Unfortunately, this is not the case for all distributions.
See the email message below where rhel-7.2 does not have
an up-to-date linux/tc_act/tc_bpf.h.
  https://www.mail-archive.com/linux-kernel@vger.kernel.org/msg1799211.html
Further investigation found that linux/pkt_cls.h is also needed for macro
TCA_BPF_TAG.

This patch fixed the issue by copying linux/tc_act/tc_bpf.h
and linux/pkt_cls.h from kernel include/uapi directory to
tools/include/uapi directory so building the bpftool does not depend
on host system for these files.

Fixes: f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Reported-by: kernel test robot <rong.a.chen@intel.com>
Cc: Li Zhijian <zhijianx.li@intel.com>
Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/include/uapi/linux/pkt_cls.h       | 612 +++++++++++++++++++++++
 tools/include/uapi/linux/tc_act/tc_bpf.h |  37 ++
 2 files changed, 649 insertions(+)
 create mode 100644 tools/include/uapi/linux/pkt_cls.h
 create mode 100644 tools/include/uapi/linux/tc_act/tc_bpf.h

diff --git a/tools/include/uapi/linux/pkt_cls.h b/tools/include/uapi/linux/pkt_cls.h
new file mode 100644
index 000000000000..682cda46aa1b
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_cls.h
@@ -0,0 +1,612 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_CLS_H
+#define __LINUX_PKT_CLS_H
+
+#include <linux/types.h>
+#include <linux/pkt_sched.h>
+
+#define TC_COOKIE_MAX_SIZE 16
+
+/* Action attributes */
+enum {
+	TCA_ACT_UNSPEC,
+	TCA_ACT_KIND,
+	TCA_ACT_OPTIONS,
+	TCA_ACT_INDEX,
+	TCA_ACT_STATS,
+	TCA_ACT_PAD,
+	TCA_ACT_COOKIE,
+	__TCA_ACT_MAX
+};
+
+#define TCA_ACT_MAX __TCA_ACT_MAX
+#define TCA_OLD_COMPAT (TCA_ACT_MAX+1)
+#define TCA_ACT_MAX_PRIO 32
+#define TCA_ACT_BIND	1
+#define TCA_ACT_NOBIND	0
+#define TCA_ACT_UNBIND	1
+#define TCA_ACT_NOUNBIND	0
+#define TCA_ACT_REPLACE		1
+#define TCA_ACT_NOREPLACE	0
+
+#define TC_ACT_UNSPEC	(-1)
+#define TC_ACT_OK		0
+#define TC_ACT_RECLASSIFY	1
+#define TC_ACT_SHOT		2
+#define TC_ACT_PIPE		3
+#define TC_ACT_STOLEN		4
+#define TC_ACT_QUEUED		5
+#define TC_ACT_REPEAT		6
+#define TC_ACT_REDIRECT		7
+#define TC_ACT_TRAP		8 /* For hw path, this means "trap to cpu"
+				   * and don't further process the frame
+				   * in hardware. For sw path, this is
+				   * equivalent of TC_ACT_STOLEN - drop
+				   * the skb and act like everything
+				   * is alright.
+				   */
+#define TC_ACT_VALUE_MAX	TC_ACT_TRAP
+
+/* There is a special kind of actions called "extended actions",
+ * which need a value parameter. These have a local opcode located in
+ * the highest nibble, starting from 1. The rest of the bits
+ * are used to carry the value. These two parts together make
+ * a combined opcode.
+ */
+#define __TC_ACT_EXT_SHIFT 28
+#define __TC_ACT_EXT(local) ((local) << __TC_ACT_EXT_SHIFT)
+#define TC_ACT_EXT_VAL_MASK ((1 << __TC_ACT_EXT_SHIFT) - 1)
+#define TC_ACT_EXT_OPCODE(combined) ((combined) & (~TC_ACT_EXT_VAL_MASK))
+#define TC_ACT_EXT_CMP(combined, opcode) (TC_ACT_EXT_OPCODE(combined) == opcode)
+
+#define TC_ACT_JUMP __TC_ACT_EXT(1)
+#define TC_ACT_GOTO_CHAIN __TC_ACT_EXT(2)
+#define TC_ACT_EXT_OPCODE_MAX	TC_ACT_GOTO_CHAIN
+
+/* Action type identifiers*/
+enum {
+	TCA_ID_UNSPEC=0,
+	TCA_ID_POLICE=1,
+	/* other actions go here */
+	__TCA_ID_MAX=255
+};
+
+#define TCA_ID_MAX __TCA_ID_MAX
+
+struct tc_police {
+	__u32			index;
+	int			action;
+#define TC_POLICE_UNSPEC	TC_ACT_UNSPEC
+#define TC_POLICE_OK		TC_ACT_OK
+#define TC_POLICE_RECLASSIFY	TC_ACT_RECLASSIFY
+#define TC_POLICE_SHOT		TC_ACT_SHOT
+#define TC_POLICE_PIPE		TC_ACT_PIPE
+
+	__u32			limit;
+	__u32			burst;
+	__u32			mtu;
+	struct tc_ratespec	rate;
+	struct tc_ratespec	peakrate;
+	int			refcnt;
+	int			bindcnt;
+	__u32			capab;
+};
+
+struct tcf_t {
+	__u64   install;
+	__u64   lastuse;
+	__u64   expires;
+	__u64   firstuse;
+};
+
+struct tc_cnt {
+	int                   refcnt;
+	int                   bindcnt;
+};
+
+#define tc_gen \
+	__u32                 index; \
+	__u32                 capab; \
+	int                   action; \
+	int                   refcnt; \
+	int                   bindcnt
+
+enum {
+	TCA_POLICE_UNSPEC,
+	TCA_POLICE_TBF,
+	TCA_POLICE_RATE,
+	TCA_POLICE_PEAKRATE,
+	TCA_POLICE_AVRATE,
+	TCA_POLICE_RESULT,
+	TCA_POLICE_TM,
+	TCA_POLICE_PAD,
+	__TCA_POLICE_MAX
+#define TCA_POLICE_RESULT TCA_POLICE_RESULT
+};
+
+#define TCA_POLICE_MAX (__TCA_POLICE_MAX - 1)
+
+/* tca flags definitions */
+#define TCA_CLS_FLAGS_SKIP_HW	(1 << 0) /* don't offload filter to HW */
+#define TCA_CLS_FLAGS_SKIP_SW	(1 << 1) /* don't use filter in SW */
+#define TCA_CLS_FLAGS_IN_HW	(1 << 2) /* filter is offloaded to HW */
+#define TCA_CLS_FLAGS_NOT_IN_HW (1 << 3) /* filter isn't offloaded to HW */
+#define TCA_CLS_FLAGS_VERBOSE	(1 << 4) /* verbose logging */
+
+/* U32 filters */
+
+#define TC_U32_HTID(h) ((h)&0xFFF00000)
+#define TC_U32_USERHTID(h) (TC_U32_HTID(h)>>20)
+#define TC_U32_HASH(h) (((h)>>12)&0xFF)
+#define TC_U32_NODE(h) ((h)&0xFFF)
+#define TC_U32_KEY(h) ((h)&0xFFFFF)
+#define TC_U32_UNSPEC	0
+#define TC_U32_ROOT	(0xFFF00000)
+
+enum {
+	TCA_U32_UNSPEC,
+	TCA_U32_CLASSID,
+	TCA_U32_HASH,
+	TCA_U32_LINK,
+	TCA_U32_DIVISOR,
+	TCA_U32_SEL,
+	TCA_U32_POLICE,
+	TCA_U32_ACT,
+	TCA_U32_INDEV,
+	TCA_U32_PCNT,
+	TCA_U32_MARK,
+	TCA_U32_FLAGS,
+	TCA_U32_PAD,
+	__TCA_U32_MAX
+};
+
+#define TCA_U32_MAX (__TCA_U32_MAX - 1)
+
+struct tc_u32_key {
+	__be32		mask;
+	__be32		val;
+	int		off;
+	int		offmask;
+};
+
+struct tc_u32_sel {
+	unsigned char		flags;
+	unsigned char		offshift;
+	unsigned char		nkeys;
+
+	__be16			offmask;
+	__u16			off;
+	short			offoff;
+
+	short			hoff;
+	__be32			hmask;
+	struct tc_u32_key	keys[0];
+};
+
+struct tc_u32_mark {
+	__u32		val;
+	__u32		mask;
+	__u32		success;
+};
+
+struct tc_u32_pcnt {
+	__u64 rcnt;
+	__u64 rhit;
+	__u64 kcnts[0];
+};
+
+/* Flags */
+
+#define TC_U32_TERMINAL		1
+#define TC_U32_OFFSET		2
+#define TC_U32_VAROFFSET	4
+#define TC_U32_EAT		8
+
+#define TC_U32_MAXDEPTH 8
+
+
+/* RSVP filter */
+
+enum {
+	TCA_RSVP_UNSPEC,
+	TCA_RSVP_CLASSID,
+	TCA_RSVP_DST,
+	TCA_RSVP_SRC,
+	TCA_RSVP_PINFO,
+	TCA_RSVP_POLICE,
+	TCA_RSVP_ACT,
+	__TCA_RSVP_MAX
+};
+
+#define TCA_RSVP_MAX (__TCA_RSVP_MAX - 1 )
+
+struct tc_rsvp_gpi {
+	__u32	key;
+	__u32	mask;
+	int	offset;
+};
+
+struct tc_rsvp_pinfo {
+	struct tc_rsvp_gpi dpi;
+	struct tc_rsvp_gpi spi;
+	__u8	protocol;
+	__u8	tunnelid;
+	__u8	tunnelhdr;
+	__u8	pad;
+};
+
+/* ROUTE filter */
+
+enum {
+	TCA_ROUTE4_UNSPEC,
+	TCA_ROUTE4_CLASSID,
+	TCA_ROUTE4_TO,
+	TCA_ROUTE4_FROM,
+	TCA_ROUTE4_IIF,
+	TCA_ROUTE4_POLICE,
+	TCA_ROUTE4_ACT,
+	__TCA_ROUTE4_MAX
+};
+
+#define TCA_ROUTE4_MAX (__TCA_ROUTE4_MAX - 1)
+
+
+/* FW filter */
+
+enum {
+	TCA_FW_UNSPEC,
+	TCA_FW_CLASSID,
+	TCA_FW_POLICE,
+	TCA_FW_INDEV, /*  used by CONFIG_NET_CLS_IND */
+	TCA_FW_ACT, /* used by CONFIG_NET_CLS_ACT */
+	TCA_FW_MASK,
+	__TCA_FW_MAX
+};
+
+#define TCA_FW_MAX (__TCA_FW_MAX - 1)
+
+/* TC index filter */
+
+enum {
+	TCA_TCINDEX_UNSPEC,
+	TCA_TCINDEX_HASH,
+	TCA_TCINDEX_MASK,
+	TCA_TCINDEX_SHIFT,
+	TCA_TCINDEX_FALL_THROUGH,
+	TCA_TCINDEX_CLASSID,
+	TCA_TCINDEX_POLICE,
+	TCA_TCINDEX_ACT,
+	__TCA_TCINDEX_MAX
+};
+
+#define TCA_TCINDEX_MAX     (__TCA_TCINDEX_MAX - 1)
+
+/* Flow filter */
+
+enum {
+	FLOW_KEY_SRC,
+	FLOW_KEY_DST,
+	FLOW_KEY_PROTO,
+	FLOW_KEY_PROTO_SRC,
+	FLOW_KEY_PROTO_DST,
+	FLOW_KEY_IIF,
+	FLOW_KEY_PRIORITY,
+	FLOW_KEY_MARK,
+	FLOW_KEY_NFCT,
+	FLOW_KEY_NFCT_SRC,
+	FLOW_KEY_NFCT_DST,
+	FLOW_KEY_NFCT_PROTO_SRC,
+	FLOW_KEY_NFCT_PROTO_DST,
+	FLOW_KEY_RTCLASSID,
+	FLOW_KEY_SKUID,
+	FLOW_KEY_SKGID,
+	FLOW_KEY_VLAN_TAG,
+	FLOW_KEY_RXHASH,
+	__FLOW_KEY_MAX,
+};
+
+#define FLOW_KEY_MAX	(__FLOW_KEY_MAX - 1)
+
+enum {
+	FLOW_MODE_MAP,
+	FLOW_MODE_HASH,
+};
+
+enum {
+	TCA_FLOW_UNSPEC,
+	TCA_FLOW_KEYS,
+	TCA_FLOW_MODE,
+	TCA_FLOW_BASECLASS,
+	TCA_FLOW_RSHIFT,
+	TCA_FLOW_ADDEND,
+	TCA_FLOW_MASK,
+	TCA_FLOW_XOR,
+	TCA_FLOW_DIVISOR,
+	TCA_FLOW_ACT,
+	TCA_FLOW_POLICE,
+	TCA_FLOW_EMATCHES,
+	TCA_FLOW_PERTURB,
+	__TCA_FLOW_MAX
+};
+
+#define TCA_FLOW_MAX	(__TCA_FLOW_MAX - 1)
+
+/* Basic filter */
+
+enum {
+	TCA_BASIC_UNSPEC,
+	TCA_BASIC_CLASSID,
+	TCA_BASIC_EMATCHES,
+	TCA_BASIC_ACT,
+	TCA_BASIC_POLICE,
+	__TCA_BASIC_MAX
+};
+
+#define TCA_BASIC_MAX (__TCA_BASIC_MAX - 1)
+
+
+/* Cgroup classifier */
+
+enum {
+	TCA_CGROUP_UNSPEC,
+	TCA_CGROUP_ACT,
+	TCA_CGROUP_POLICE,
+	TCA_CGROUP_EMATCHES,
+	__TCA_CGROUP_MAX,
+};
+
+#define TCA_CGROUP_MAX (__TCA_CGROUP_MAX - 1)
+
+/* BPF classifier */
+
+#define TCA_BPF_FLAG_ACT_DIRECT		(1 << 0)
+
+enum {
+	TCA_BPF_UNSPEC,
+	TCA_BPF_ACT,
+	TCA_BPF_POLICE,
+	TCA_BPF_CLASSID,
+	TCA_BPF_OPS_LEN,
+	TCA_BPF_OPS,
+	TCA_BPF_FD,
+	TCA_BPF_NAME,
+	TCA_BPF_FLAGS,
+	TCA_BPF_FLAGS_GEN,
+	TCA_BPF_TAG,
+	TCA_BPF_ID,
+	__TCA_BPF_MAX,
+};
+
+#define TCA_BPF_MAX (__TCA_BPF_MAX - 1)
+
+/* Flower classifier */
+
+enum {
+	TCA_FLOWER_UNSPEC,
+	TCA_FLOWER_CLASSID,
+	TCA_FLOWER_INDEV,
+	TCA_FLOWER_ACT,
+	TCA_FLOWER_KEY_ETH_DST,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_DST_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_SRC_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ETH_TYPE,	/* be16 */
+	TCA_FLOWER_KEY_IP_PROTO,	/* u8 */
+	TCA_FLOWER_KEY_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_SRC_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_IPV4_DST_MASK,	/* be32 */
+	TCA_FLOWER_KEY_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_SRC_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_IPV6_DST_MASK,	/* struct in6_addr */
+	TCA_FLOWER_KEY_TCP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_TCP_DST,		/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC,		/* be16 */
+	TCA_FLOWER_KEY_UDP_DST,		/* be16 */
+
+	TCA_FLOWER_FLAGS,
+	TCA_FLOWER_KEY_VLAN_ID,		/* be16 */
+	TCA_FLOWER_KEY_VLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_VLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_KEY_ID,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_SRC_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST,	/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV4_DST_MASK,/* be32 */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_SRC_MASK,/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST,	/* struct in6_addr */
+	TCA_FLOWER_KEY_ENC_IPV6_DST_MASK,/* struct in6_addr */
+
+	TCA_FLOWER_KEY_TCP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_TCP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_UDP_DST_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_SRC_MASK,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_SCTP_SRC,	/* be16 */
+	TCA_FLOWER_KEY_SCTP_DST,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_SRC_PORT_MASK,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT,	/* be16 */
+	TCA_FLOWER_KEY_ENC_UDP_DST_PORT_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_FLAGS,		/* be32 */
+	TCA_FLOWER_KEY_FLAGS_MASK,	/* be32 */
+
+	TCA_FLOWER_KEY_ICMPV4_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV4_TYPE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_CODE_MASK,/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE,	/* u8 */
+	TCA_FLOWER_KEY_ICMPV6_TYPE_MASK,/* u8 */
+
+	TCA_FLOWER_KEY_ARP_SIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_SIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP,		/* be32 */
+	TCA_FLOWER_KEY_ARP_TIP_MASK,	/* be32 */
+	TCA_FLOWER_KEY_ARP_OP,		/* u8 */
+	TCA_FLOWER_KEY_ARP_OP_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ARP_SHA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_SHA_MASK,	/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA,		/* ETH_ALEN */
+	TCA_FLOWER_KEY_ARP_THA_MASK,	/* ETH_ALEN */
+
+	TCA_FLOWER_KEY_MPLS_TTL,	/* u8 - 8 bits */
+	TCA_FLOWER_KEY_MPLS_BOS,	/* u8 - 1 bit */
+	TCA_FLOWER_KEY_MPLS_TC,		/* u8 - 3 bits */
+	TCA_FLOWER_KEY_MPLS_LABEL,	/* be32 - 20 bits */
+
+	TCA_FLOWER_KEY_TCP_FLAGS,	/* be16 */
+	TCA_FLOWER_KEY_TCP_FLAGS_MASK,	/* be16 */
+
+	TCA_FLOWER_KEY_IP_TOS,		/* u8 */
+	TCA_FLOWER_KEY_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_IP_TTL,		/* u8 */
+	TCA_FLOWER_KEY_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_CVLAN_ID,	/* be16 */
+	TCA_FLOWER_KEY_CVLAN_PRIO,	/* u8   */
+	TCA_FLOWER_KEY_CVLAN_ETH_TYPE,	/* be16 */
+
+	TCA_FLOWER_KEY_ENC_IP_TOS,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TOS_MASK,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL,	/* u8 */
+	TCA_FLOWER_KEY_ENC_IP_TTL_MASK,	/* u8 */
+
+	TCA_FLOWER_KEY_ENC_OPTS,
+	TCA_FLOWER_KEY_ENC_OPTS_MASK,
+
+	TCA_FLOWER_IN_HW_COUNT,
+
+	__TCA_FLOWER_MAX,
+};
+
+#define TCA_FLOWER_MAX (__TCA_FLOWER_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPTS_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPTS_GENEVE, /* Nested
+					 * TCA_FLOWER_KEY_ENC_OPT_GENEVE_
+					 * attributes
+					 */
+	__TCA_FLOWER_KEY_ENC_OPTS_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPTS_MAX (__TCA_FLOWER_KEY_ENC_OPTS_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_UNSPEC,
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_CLASS,            /* u16 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_TYPE,             /* u8 */
+	TCA_FLOWER_KEY_ENC_OPT_GENEVE_DATA,             /* 4 to 128 bytes */
+
+	__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX,
+};
+
+#define TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX \
+		(__TCA_FLOWER_KEY_ENC_OPT_GENEVE_MAX - 1)
+
+enum {
+	TCA_FLOWER_KEY_FLAGS_IS_FRAGMENT = (1 << 0),
+	TCA_FLOWER_KEY_FLAGS_FRAG_IS_FIRST = (1 << 1),
+};
+
+/* Match-all classifier */
+
+enum {
+	TCA_MATCHALL_UNSPEC,
+	TCA_MATCHALL_CLASSID,
+	TCA_MATCHALL_ACT,
+	TCA_MATCHALL_FLAGS,
+	__TCA_MATCHALL_MAX,
+};
+
+#define TCA_MATCHALL_MAX (__TCA_MATCHALL_MAX - 1)
+
+/* Extended Matches */
+
+struct tcf_ematch_tree_hdr {
+	__u16		nmatches;
+	__u16		progid;
+};
+
+enum {
+	TCA_EMATCH_TREE_UNSPEC,
+	TCA_EMATCH_TREE_HDR,
+	TCA_EMATCH_TREE_LIST,
+	__TCA_EMATCH_TREE_MAX
+};
+#define TCA_EMATCH_TREE_MAX (__TCA_EMATCH_TREE_MAX - 1)
+
+struct tcf_ematch_hdr {
+	__u16		matchid;
+	__u16		kind;
+	__u16		flags;
+	__u16		pad; /* currently unused */
+};
+
+/*  0                   1
+ *  0 1 2 3 4 5 6 7 8 9 0 1 2 3 4 5
+ * +-----------------------+-+-+---+
+ * |         Unused        |S|I| R |
+ * +-----------------------+-+-+---+
+ *
+ * R(2) ::= relation to next ematch
+ *          where: 0 0 END (last ematch)
+ *                 0 1 AND
+ *                 1 0 OR
+ *                 1 1 Unused (invalid)
+ * I(1) ::= invert result
+ * S(1) ::= simple payload
+ */
+#define TCF_EM_REL_END	0
+#define TCF_EM_REL_AND	(1<<0)
+#define TCF_EM_REL_OR	(1<<1)
+#define TCF_EM_INVERT	(1<<2)
+#define TCF_EM_SIMPLE	(1<<3)
+
+#define TCF_EM_REL_MASK	3
+#define TCF_EM_REL_VALID(v) (((v) & TCF_EM_REL_MASK) != TCF_EM_REL_MASK)
+
+enum {
+	TCF_LAYER_LINK,
+	TCF_LAYER_NETWORK,
+	TCF_LAYER_TRANSPORT,
+	__TCF_LAYER_MAX
+};
+#define TCF_LAYER_MAX (__TCF_LAYER_MAX - 1)
+
+/* Ematch type assignments
+ *   1..32767		Reserved for ematches inside kernel tree
+ *   32768..65535	Free to use, not reliable
+ */
+#define	TCF_EM_CONTAINER	0
+#define	TCF_EM_CMP		1
+#define	TCF_EM_NBYTE		2
+#define	TCF_EM_U32		3
+#define	TCF_EM_META		4
+#define	TCF_EM_TEXT		5
+#define	TCF_EM_VLAN		6
+#define	TCF_EM_CANID		7
+#define	TCF_EM_IPSET		8
+#define	TCF_EM_IPT		9
+#define	TCF_EM_MAX		9
+
+enum {
+	TCF_EM_PROG_TC
+};
+
+enum {
+	TCF_EM_OPND_EQ,
+	TCF_EM_OPND_GT,
+	TCF_EM_OPND_LT
+};
+
+#endif
diff --git a/tools/include/uapi/linux/tc_act/tc_bpf.h b/tools/include/uapi/linux/tc_act/tc_bpf.h
new file mode 100644
index 000000000000..6e89a5df49a4
--- /dev/null
+++ b/tools/include/uapi/linux/tc_act/tc_bpf.h
@@ -0,0 +1,37 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * Copyright (c) 2015 Jiri Pirko <jiri@resnulli.us>
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#ifndef __LINUX_TC_BPF_H
+#define __LINUX_TC_BPF_H
+
+#include <linux/pkt_cls.h>
+
+#define TCA_ACT_BPF 13
+
+struct tc_act_bpf {
+	tc_gen;
+};
+
+enum {
+	TCA_ACT_BPF_UNSPEC,
+	TCA_ACT_BPF_TM,
+	TCA_ACT_BPF_PARMS,
+	TCA_ACT_BPF_OPS_LEN,
+	TCA_ACT_BPF_OPS,
+	TCA_ACT_BPF_FD,
+	TCA_ACT_BPF_NAME,
+	TCA_ACT_BPF_PAD,
+	TCA_ACT_BPF_TAG,
+	TCA_ACT_BPF_ID,
+	__TCA_ACT_BPF_MAX,
+};
+#define TCA_ACT_BPF_MAX (__TCA_ACT_BPF_MAX - 1)
+
+#endif
-- 
Gitee


From d5cae250ab947930330ec184f5d750d4fefb3a33 Mon Sep 17 00:00:00 2001
From: Daniel Borkmann <daniel@iogearbox.net>
Date: Wed, 5 Jul 2023 14:24:03 +0800
Subject: [PATCH 09/12] bpf: pull in pkt_sched.h header for tooling to fix
 bpftool build

ANBZ: #5530

commit ad6dd7a9c47ba587c0aba57f73737764cd31136f upstream

Dan reported that bpftool does not compile for him:

  $ make tools/bpf
    DESCEND  bpf

  Auto-detecting system features:
  ..                        libbfd: [ on  ]
  ..        disassembler-four-args: [ OFF ]

    DESCEND  bpftool

  Auto-detecting system features:
  ..                        libbfd: [ on  ]
  ..        disassembler-four-args: [ OFF ]

    CC       /opt/linux.git/tools/bpf/bpftool/net.o
  In file included from /opt/linux.git/tools/include/uapi/linux/pkt_cls.h:6:0,
                 from /opt/linux.git/tools/include/uapi/linux/tc_act/tc_bpf.h:14,
                 from net.c:13:
  net.c: In function 'show_dev_tc_bpf':
  net.c:164:21: error: 'TC_H_CLSACT' undeclared (first use in this function)
    handle = TC_H_MAKE(TC_H_CLSACT, TC_H_MIN_INGRESS);
  [...]

Fix it by importing pkt_sched.h header copy into tooling
infrastructure.

Fixes: 49a249c38726 ("tools/bpftool: copy a few net uapi headers to tools directory")
Fixes: f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Reported-by: Dan Gilson <dan_gilson@yahoo.com>
Reference: https://bugzilla.kernel.org/show_bug.cgi?id=202315
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/include/uapi/linux/pkt_sched.h | 1163 ++++++++++++++++++++++++++
 1 file changed, 1163 insertions(+)
 create mode 100644 tools/include/uapi/linux/pkt_sched.h

diff --git a/tools/include/uapi/linux/pkt_sched.h b/tools/include/uapi/linux/pkt_sched.h
new file mode 100644
index 000000000000..25060205bf3f
--- /dev/null
+++ b/tools/include/uapi/linux/pkt_sched.h
@@ -0,0 +1,1163 @@
+/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */
+#ifndef __LINUX_PKT_SCHED_H
+#define __LINUX_PKT_SCHED_H
+
+#include <linux/types.h>
+
+/* Logical priority bands not depending on specific packet scheduler.
+   Every scheduler will map them to real traffic classes, if it has
+   no more precise mechanism to classify packets.
+
+   These numbers have no special meaning, though their coincidence
+   with obsolete IPv6 values is not occasional :-). New IPv6 drafts
+   preferred full anarchy inspired by diffserv group.
+
+   Note: TC_PRIO_BESTEFFORT does not mean that it is the most unhappy
+   class, actually, as rule it will be handled with more care than
+   filler or even bulk.
+ */
+
+#define TC_PRIO_BESTEFFORT		0
+#define TC_PRIO_FILLER			1
+#define TC_PRIO_BULK			2
+#define TC_PRIO_INTERACTIVE_BULK	4
+#define TC_PRIO_INTERACTIVE		6
+#define TC_PRIO_CONTROL			7
+
+#define TC_PRIO_MAX			15
+
+/* Generic queue statistics, available for all the elements.
+   Particular schedulers may have also their private records.
+ */
+
+struct tc_stats {
+	__u64	bytes;			/* Number of enqueued bytes */
+	__u32	packets;		/* Number of enqueued packets	*/
+	__u32	drops;			/* Packets dropped because of lack of resources */
+	__u32	overlimits;		/* Number of throttle events when this
+					 * flow goes out of allocated bandwidth */
+	__u32	bps;			/* Current flow byte rate */
+	__u32	pps;			/* Current flow packet rate */
+	__u32	qlen;
+	__u32	backlog;
+};
+
+struct tc_estimator {
+	signed char	interval;
+	unsigned char	ewma_log;
+};
+
+/* "Handles"
+   ---------
+
+    All the traffic control objects have 32bit identifiers, or "handles".
+
+    They can be considered as opaque numbers from user API viewpoint,
+    but actually they always consist of two fields: major and
+    minor numbers, which are interpreted by kernel specially,
+    that may be used by applications, though not recommended.
+
+    F.e. qdisc handles always have minor number equal to zero,
+    classes (or flows) have major equal to parent qdisc major, and
+    minor uniquely identifying class inside qdisc.
+
+    Macros to manipulate handles:
+ */
+
+#define TC_H_MAJ_MASK (0xFFFF0000U)
+#define TC_H_MIN_MASK (0x0000FFFFU)
+#define TC_H_MAJ(h) ((h)&TC_H_MAJ_MASK)
+#define TC_H_MIN(h) ((h)&TC_H_MIN_MASK)
+#define TC_H_MAKE(maj,min) (((maj)&TC_H_MAJ_MASK)|((min)&TC_H_MIN_MASK))
+
+#define TC_H_UNSPEC	(0U)
+#define TC_H_ROOT	(0xFFFFFFFFU)
+#define TC_H_INGRESS    (0xFFFFFFF1U)
+#define TC_H_CLSACT	TC_H_INGRESS
+
+#define TC_H_MIN_PRIORITY	0xFFE0U
+#define TC_H_MIN_INGRESS	0xFFF2U
+#define TC_H_MIN_EGRESS		0xFFF3U
+
+/* Need to corrospond to iproute2 tc/tc_core.h "enum link_layer" */
+enum tc_link_layer {
+	TC_LINKLAYER_UNAWARE, /* Indicate unaware old iproute2 util */
+	TC_LINKLAYER_ETHERNET,
+	TC_LINKLAYER_ATM,
+};
+#define TC_LINKLAYER_MASK 0x0F /* limit use to lower 4 bits */
+
+struct tc_ratespec {
+	unsigned char	cell_log;
+	__u8		linklayer; /* lower 4 bits */
+	unsigned short	overhead;
+	short		cell_align;
+	unsigned short	mpu;
+	__u32		rate;
+};
+
+#define TC_RTAB_SIZE	1024
+
+struct tc_sizespec {
+	unsigned char	cell_log;
+	unsigned char	size_log;
+	short		cell_align;
+	int		overhead;
+	unsigned int	linklayer;
+	unsigned int	mpu;
+	unsigned int	mtu;
+	unsigned int	tsize;
+};
+
+enum {
+	TCA_STAB_UNSPEC,
+	TCA_STAB_BASE,
+	TCA_STAB_DATA,
+	__TCA_STAB_MAX
+};
+
+#define TCA_STAB_MAX (__TCA_STAB_MAX - 1)
+
+/* FIFO section */
+
+struct tc_fifo_qopt {
+	__u32	limit;	/* Queue length: bytes for bfifo, packets for pfifo */
+};
+
+/* SKBPRIO section */
+
+/*
+ * Priorities go from zero to (SKBPRIO_MAX_PRIORITY - 1).
+ * SKBPRIO_MAX_PRIORITY should be at least 64 in order for skbprio to be able
+ * to map one to one the DS field of IPV4 and IPV6 headers.
+ * Memory allocation grows linearly with SKBPRIO_MAX_PRIORITY.
+ */
+
+#define SKBPRIO_MAX_PRIORITY 64
+
+struct tc_skbprio_qopt {
+	__u32	limit;		/* Queue length in packets. */
+};
+
+/* PRIO section */
+
+#define TCQ_PRIO_BANDS	16
+#define TCQ_MIN_PRIO_BANDS 2
+
+struct tc_prio_qopt {
+	int	bands;			/* Number of bands */
+	__u8	priomap[TC_PRIO_MAX+1];	/* Map: logical priority -> PRIO band */
+};
+
+/* MULTIQ section */
+
+struct tc_multiq_qopt {
+	__u16	bands;			/* Number of bands */
+	__u16	max_bands;		/* Maximum number of queues */
+};
+
+/* PLUG section */
+
+#define TCQ_PLUG_BUFFER                0
+#define TCQ_PLUG_RELEASE_ONE           1
+#define TCQ_PLUG_RELEASE_INDEFINITE    2
+#define TCQ_PLUG_LIMIT                 3
+
+struct tc_plug_qopt {
+	/* TCQ_PLUG_BUFFER: Inset a plug into the queue and
+	 *  buffer any incoming packets
+	 * TCQ_PLUG_RELEASE_ONE: Dequeue packets from queue head
+	 *   to beginning of the next plug.
+	 * TCQ_PLUG_RELEASE_INDEFINITE: Dequeue all packets from queue.
+	 *   Stop buffering packets until the next TCQ_PLUG_BUFFER
+	 *   command is received (just act as a pass-thru queue).
+	 * TCQ_PLUG_LIMIT: Increase/decrease queue size
+	 */
+	int             action;
+	__u32           limit;
+};
+
+/* TBF section */
+
+struct tc_tbf_qopt {
+	struct tc_ratespec rate;
+	struct tc_ratespec peakrate;
+	__u32		limit;
+	__u32		buffer;
+	__u32		mtu;
+};
+
+enum {
+	TCA_TBF_UNSPEC,
+	TCA_TBF_PARMS,
+	TCA_TBF_RTAB,
+	TCA_TBF_PTAB,
+	TCA_TBF_RATE64,
+	TCA_TBF_PRATE64,
+	TCA_TBF_BURST,
+	TCA_TBF_PBURST,
+	TCA_TBF_PAD,
+	__TCA_TBF_MAX,
+};
+
+#define TCA_TBF_MAX (__TCA_TBF_MAX - 1)
+
+
+/* TEQL section */
+
+/* TEQL does not require any parameters */
+
+/* SFQ section */
+
+struct tc_sfq_qopt {
+	unsigned	quantum;	/* Bytes per round allocated to flow */
+	int		perturb_period;	/* Period of hash perturbation */
+	__u32		limit;		/* Maximal packets in queue */
+	unsigned	divisor;	/* Hash divisor  */
+	unsigned	flows;		/* Maximal number of flows  */
+};
+
+struct tc_sfqred_stats {
+	__u32           prob_drop;      /* Early drops, below max threshold */
+	__u32           forced_drop;	/* Early drops, after max threshold */
+	__u32           prob_mark;      /* Marked packets, below max threshold */
+	__u32           forced_mark;    /* Marked packets, after max threshold */
+	__u32           prob_mark_head; /* Marked packets, below max threshold */
+	__u32           forced_mark_head;/* Marked packets, after max threshold */
+};
+
+struct tc_sfq_qopt_v1 {
+	struct tc_sfq_qopt v0;
+	unsigned int	depth;		/* max number of packets per flow */
+	unsigned int	headdrop;
+/* SFQRED parameters */
+	__u32		limit;		/* HARD maximal flow queue length (bytes) */
+	__u32		qth_min;	/* Min average length threshold (bytes) */
+	__u32		qth_max;	/* Max average length threshold (bytes) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;
+	__u32		max_P;		/* probability, high resolution */
+/* SFQRED stats */
+	struct tc_sfqred_stats stats;
+};
+
+
+struct tc_sfq_xstats {
+	__s32		allot;
+};
+
+/* RED section */
+
+enum {
+	TCA_RED_UNSPEC,
+	TCA_RED_PARMS,
+	TCA_RED_STAB,
+	TCA_RED_MAX_P,
+	__TCA_RED_MAX,
+};
+
+#define TCA_RED_MAX (__TCA_RED_MAX - 1)
+
+struct tc_red_qopt {
+	__u32		limit;		/* HARD maximal queue length (bytes)	*/
+	__u32		qth_min;	/* Min average length threshold (bytes) */
+	__u32		qth_max;	/* Max average length threshold (bytes) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;
+#define TC_RED_ECN		1
+#define TC_RED_HARDDROP		2
+#define TC_RED_ADAPTATIVE	4
+};
+
+struct tc_red_xstats {
+	__u32           early;          /* Early drops */
+	__u32           pdrop;          /* Drops due to queue limits */
+	__u32           other;          /* Drops due to drop() calls */
+	__u32           marked;         /* Marked packets */
+};
+
+/* GRED section */
+
+#define MAX_DPs 16
+
+enum {
+       TCA_GRED_UNSPEC,
+       TCA_GRED_PARMS,
+       TCA_GRED_STAB,
+       TCA_GRED_DPS,
+       TCA_GRED_MAX_P,
+       TCA_GRED_LIMIT,
+       TCA_GRED_VQ_LIST,	/* nested TCA_GRED_VQ_ENTRY */
+       __TCA_GRED_MAX,
+};
+
+#define TCA_GRED_MAX (__TCA_GRED_MAX - 1)
+
+enum {
+	TCA_GRED_VQ_ENTRY_UNSPEC,
+	TCA_GRED_VQ_ENTRY,	/* nested TCA_GRED_VQ_* */
+	__TCA_GRED_VQ_ENTRY_MAX,
+};
+#define TCA_GRED_VQ_ENTRY_MAX (__TCA_GRED_VQ_ENTRY_MAX - 1)
+
+enum {
+	TCA_GRED_VQ_UNSPEC,
+	TCA_GRED_VQ_PAD,
+	TCA_GRED_VQ_DP,			/* u32 */
+	TCA_GRED_VQ_STAT_BYTES,		/* u64 */
+	TCA_GRED_VQ_STAT_PACKETS,	/* u32 */
+	TCA_GRED_VQ_STAT_BACKLOG,	/* u32 */
+	TCA_GRED_VQ_STAT_PROB_DROP,	/* u32 */
+	TCA_GRED_VQ_STAT_PROB_MARK,	/* u32 */
+	TCA_GRED_VQ_STAT_FORCED_DROP,	/* u32 */
+	TCA_GRED_VQ_STAT_FORCED_MARK,	/* u32 */
+	TCA_GRED_VQ_STAT_PDROP,		/* u32 */
+	TCA_GRED_VQ_STAT_OTHER,		/* u32 */
+	TCA_GRED_VQ_FLAGS,		/* u32 */
+	__TCA_GRED_VQ_MAX
+};
+
+#define TCA_GRED_VQ_MAX (__TCA_GRED_VQ_MAX - 1)
+
+struct tc_gred_qopt {
+	__u32		limit;        /* HARD maximal queue length (bytes)    */
+	__u32		qth_min;      /* Min average length threshold (bytes) */
+	__u32		qth_max;      /* Max average length threshold (bytes) */
+	__u32		DP;           /* up to 2^32 DPs */
+	__u32		backlog;
+	__u32		qave;
+	__u32		forced;
+	__u32		early;
+	__u32		other;
+	__u32		pdrop;
+	__u8		Wlog;         /* log(W)               */
+	__u8		Plog;         /* log(P_max/(qth_max-qth_min)) */
+	__u8		Scell_log;    /* cell size for idle damping */
+	__u8		prio;         /* prio of this VQ */
+	__u32		packets;
+	__u32		bytesin;
+};
+
+/* gred setup */
+struct tc_gred_sopt {
+	__u32		DPs;
+	__u32		def_DP;
+	__u8		grio;
+	__u8		flags;
+	__u16		pad1;
+};
+
+/* CHOKe section */
+
+enum {
+	TCA_CHOKE_UNSPEC,
+	TCA_CHOKE_PARMS,
+	TCA_CHOKE_STAB,
+	TCA_CHOKE_MAX_P,
+	__TCA_CHOKE_MAX,
+};
+
+#define TCA_CHOKE_MAX (__TCA_CHOKE_MAX - 1)
+
+struct tc_choke_qopt {
+	__u32		limit;		/* Hard queue length (packets)	*/
+	__u32		qth_min;	/* Min average threshold (packets) */
+	__u32		qth_max;	/* Max average threshold (packets) */
+	unsigned char   Wlog;		/* log(W)		*/
+	unsigned char   Plog;		/* log(P_max/(qth_max-qth_min))	*/
+	unsigned char   Scell_log;	/* cell size for idle damping */
+	unsigned char	flags;		/* see RED flags */
+};
+
+struct tc_choke_xstats {
+	__u32		early;          /* Early drops */
+	__u32		pdrop;          /* Drops due to queue limits */
+	__u32		other;          /* Drops due to drop() calls */
+	__u32		marked;         /* Marked packets */
+	__u32		matched;	/* Drops due to flow match */
+};
+
+/* HTB section */
+#define TC_HTB_NUMPRIO		8
+#define TC_HTB_MAXDEPTH		8
+#define TC_HTB_PROTOVER		3 /* the same as HTB and TC's major */
+
+struct tc_htb_opt {
+	struct tc_ratespec 	rate;
+	struct tc_ratespec 	ceil;
+	__u32	buffer;
+	__u32	cbuffer;
+	__u32	quantum;
+	__u32	level;		/* out only */
+	__u32	prio;
+};
+struct tc_htb_glob {
+	__u32 version;		/* to match HTB/TC */
+	__u32 rate2quantum;	/* bps->quantum divisor */
+	__u32 defcls;		/* default class number */
+	__u32 debug;		/* debug flags */
+
+	/* stats */
+	__u32 direct_pkts; /* count of non shaped packets */
+};
+enum {
+	TCA_HTB_UNSPEC,
+	TCA_HTB_PARMS,
+	TCA_HTB_INIT,
+	TCA_HTB_CTAB,
+	TCA_HTB_RTAB,
+	TCA_HTB_DIRECT_QLEN,
+	TCA_HTB_RATE64,
+	TCA_HTB_CEIL64,
+	TCA_HTB_PAD,
+	__TCA_HTB_MAX,
+};
+
+#define TCA_HTB_MAX (__TCA_HTB_MAX - 1)
+
+struct tc_htb_xstats {
+	__u32 lends;
+	__u32 borrows;
+	__u32 giants;	/* unused since 'Make HTB scheduler work with TSO.' */
+	__s32 tokens;
+	__s32 ctokens;
+};
+
+/* HFSC section */
+
+struct tc_hfsc_qopt {
+	__u16	defcls;		/* default class */
+};
+
+struct tc_service_curve {
+	__u32	m1;		/* slope of the first segment in bps */
+	__u32	d;		/* x-projection of the first segment in us */
+	__u32	m2;		/* slope of the second segment in bps */
+};
+
+struct tc_hfsc_stats {
+	__u64	work;		/* total work done */
+	__u64	rtwork;		/* work done by real-time criteria */
+	__u32	period;		/* current period */
+	__u32	level;		/* class level in hierarchy */
+};
+
+enum {
+	TCA_HFSC_UNSPEC,
+	TCA_HFSC_RSC,
+	TCA_HFSC_FSC,
+	TCA_HFSC_USC,
+	__TCA_HFSC_MAX,
+};
+
+#define TCA_HFSC_MAX (__TCA_HFSC_MAX - 1)
+
+
+/* CBQ section */
+
+#define TC_CBQ_MAXPRIO		8
+#define TC_CBQ_MAXLEVEL		8
+#define TC_CBQ_DEF_EWMA		5
+
+struct tc_cbq_lssopt {
+	unsigned char	change;
+	unsigned char	flags;
+#define TCF_CBQ_LSS_BOUNDED	1
+#define TCF_CBQ_LSS_ISOLATED	2
+	unsigned char  	ewma_log;
+	unsigned char  	level;
+#define TCF_CBQ_LSS_FLAGS	1
+#define TCF_CBQ_LSS_EWMA	2
+#define TCF_CBQ_LSS_MAXIDLE	4
+#define TCF_CBQ_LSS_MINIDLE	8
+#define TCF_CBQ_LSS_OFFTIME	0x10
+#define TCF_CBQ_LSS_AVPKT	0x20
+	__u32		maxidle;
+	__u32		minidle;
+	__u32		offtime;
+	__u32		avpkt;
+};
+
+struct tc_cbq_wrropt {
+	unsigned char	flags;
+	unsigned char	priority;
+	unsigned char	cpriority;
+	unsigned char	__reserved;
+	__u32		allot;
+	__u32		weight;
+};
+
+struct tc_cbq_ovl {
+	unsigned char	strategy;
+#define	TC_CBQ_OVL_CLASSIC	0
+#define	TC_CBQ_OVL_DELAY	1
+#define	TC_CBQ_OVL_LOWPRIO	2
+#define	TC_CBQ_OVL_DROP		3
+#define	TC_CBQ_OVL_RCLASSIC	4
+	unsigned char	priority2;
+	__u16		pad;
+	__u32		penalty;
+};
+
+struct tc_cbq_police {
+	unsigned char	police;
+	unsigned char	__res1;
+	unsigned short	__res2;
+};
+
+struct tc_cbq_fopt {
+	__u32		split;
+	__u32		defmap;
+	__u32		defchange;
+};
+
+struct tc_cbq_xstats {
+	__u32		borrows;
+	__u32		overactions;
+	__s32		avgidle;
+	__s32		undertime;
+};
+
+enum {
+	TCA_CBQ_UNSPEC,
+	TCA_CBQ_LSSOPT,
+	TCA_CBQ_WRROPT,
+	TCA_CBQ_FOPT,
+	TCA_CBQ_OVL_STRATEGY,
+	TCA_CBQ_RATE,
+	TCA_CBQ_RTAB,
+	TCA_CBQ_POLICE,
+	__TCA_CBQ_MAX,
+};
+
+#define TCA_CBQ_MAX	(__TCA_CBQ_MAX - 1)
+
+/* dsmark section */
+
+enum {
+	TCA_DSMARK_UNSPEC,
+	TCA_DSMARK_INDICES,
+	TCA_DSMARK_DEFAULT_INDEX,
+	TCA_DSMARK_SET_TC_INDEX,
+	TCA_DSMARK_MASK,
+	TCA_DSMARK_VALUE,
+	__TCA_DSMARK_MAX,
+};
+
+#define TCA_DSMARK_MAX (__TCA_DSMARK_MAX - 1)
+
+/* ATM  section */
+
+enum {
+	TCA_ATM_UNSPEC,
+	TCA_ATM_FD,		/* file/socket descriptor */
+	TCA_ATM_PTR,		/* pointer to descriptor - later */
+	TCA_ATM_HDR,		/* LL header */
+	TCA_ATM_EXCESS,		/* excess traffic class (0 for CLP)  */
+	TCA_ATM_ADDR,		/* PVC address (for output only) */
+	TCA_ATM_STATE,		/* VC state (ATM_VS_*; for output only) */
+	__TCA_ATM_MAX,
+};
+
+#define TCA_ATM_MAX	(__TCA_ATM_MAX - 1)
+
+/* Network emulator */
+
+enum {
+	TCA_NETEM_UNSPEC,
+	TCA_NETEM_CORR,
+	TCA_NETEM_DELAY_DIST,
+	TCA_NETEM_REORDER,
+	TCA_NETEM_CORRUPT,
+	TCA_NETEM_LOSS,
+	TCA_NETEM_RATE,
+	TCA_NETEM_ECN,
+	TCA_NETEM_RATE64,
+	TCA_NETEM_PAD,
+	TCA_NETEM_LATENCY64,
+	TCA_NETEM_JITTER64,
+	TCA_NETEM_SLOT,
+	TCA_NETEM_SLOT_DIST,
+	__TCA_NETEM_MAX,
+};
+
+#define TCA_NETEM_MAX (__TCA_NETEM_MAX - 1)
+
+struct tc_netem_qopt {
+	__u32	latency;	/* added delay (us) */
+	__u32   limit;		/* fifo limit (packets) */
+	__u32	loss;		/* random packet loss (0=none ~0=100%) */
+	__u32	gap;		/* re-ordering gap (0 for none) */
+	__u32   duplicate;	/* random packet dup  (0=none ~0=100%) */
+	__u32	jitter;		/* random jitter in latency (us) */
+};
+
+struct tc_netem_corr {
+	__u32	delay_corr;	/* delay correlation */
+	__u32	loss_corr;	/* packet loss correlation */
+	__u32	dup_corr;	/* duplicate correlation  */
+};
+
+struct tc_netem_reorder {
+	__u32	probability;
+	__u32	correlation;
+};
+
+struct tc_netem_corrupt {
+	__u32	probability;
+	__u32	correlation;
+};
+
+struct tc_netem_rate {
+	__u32	rate;	/* byte/s */
+	__s32	packet_overhead;
+	__u32	cell_size;
+	__s32	cell_overhead;
+};
+
+struct tc_netem_slot {
+	__s64   min_delay; /* nsec */
+	__s64   max_delay;
+	__s32   max_packets;
+	__s32   max_bytes;
+	__s64	dist_delay; /* nsec */
+	__s64	dist_jitter; /* nsec */
+};
+
+enum {
+	NETEM_LOSS_UNSPEC,
+	NETEM_LOSS_GI,		/* General Intuitive - 4 state model */
+	NETEM_LOSS_GE,		/* Gilbert Elliot models */
+	__NETEM_LOSS_MAX
+};
+#define NETEM_LOSS_MAX (__NETEM_LOSS_MAX - 1)
+
+/* State transition probabilities for 4 state model */
+struct tc_netem_gimodel {
+	__u32	p13;
+	__u32	p31;
+	__u32	p32;
+	__u32	p14;
+	__u32	p23;
+};
+
+/* Gilbert-Elliot models */
+struct tc_netem_gemodel {
+	__u32 p;
+	__u32 r;
+	__u32 h;
+	__u32 k1;
+};
+
+#define NETEM_DIST_SCALE	8192
+#define NETEM_DIST_MAX		16384
+
+/* DRR */
+
+enum {
+	TCA_DRR_UNSPEC,
+	TCA_DRR_QUANTUM,
+	__TCA_DRR_MAX
+};
+
+#define TCA_DRR_MAX	(__TCA_DRR_MAX - 1)
+
+struct tc_drr_stats {
+	__u32	deficit;
+};
+
+/* MQPRIO */
+#define TC_QOPT_BITMASK 15
+#define TC_QOPT_MAX_QUEUE 16
+
+enum {
+	TC_MQPRIO_HW_OFFLOAD_NONE,	/* no offload requested */
+	TC_MQPRIO_HW_OFFLOAD_TCS,	/* offload TCs, no queue counts */
+	__TC_MQPRIO_HW_OFFLOAD_MAX
+};
+
+#define TC_MQPRIO_HW_OFFLOAD_MAX (__TC_MQPRIO_HW_OFFLOAD_MAX - 1)
+
+enum {
+	TC_MQPRIO_MODE_DCB,
+	TC_MQPRIO_MODE_CHANNEL,
+	__TC_MQPRIO_MODE_MAX
+};
+
+#define __TC_MQPRIO_MODE_MAX (__TC_MQPRIO_MODE_MAX - 1)
+
+enum {
+	TC_MQPRIO_SHAPER_DCB,
+	TC_MQPRIO_SHAPER_BW_RATE,	/* Add new shapers below */
+	__TC_MQPRIO_SHAPER_MAX
+};
+
+#define __TC_MQPRIO_SHAPER_MAX (__TC_MQPRIO_SHAPER_MAX - 1)
+
+struct tc_mqprio_qopt {
+	__u8	num_tc;
+	__u8	prio_tc_map[TC_QOPT_BITMASK + 1];
+	__u8	hw;
+	__u16	count[TC_QOPT_MAX_QUEUE];
+	__u16	offset[TC_QOPT_MAX_QUEUE];
+};
+
+#define TC_MQPRIO_F_MODE		0x1
+#define TC_MQPRIO_F_SHAPER		0x2
+#define TC_MQPRIO_F_MIN_RATE		0x4
+#define TC_MQPRIO_F_MAX_RATE		0x8
+
+enum {
+	TCA_MQPRIO_UNSPEC,
+	TCA_MQPRIO_MODE,
+	TCA_MQPRIO_SHAPER,
+	TCA_MQPRIO_MIN_RATE64,
+	TCA_MQPRIO_MAX_RATE64,
+	__TCA_MQPRIO_MAX,
+};
+
+#define TCA_MQPRIO_MAX (__TCA_MQPRIO_MAX - 1)
+
+/* SFB */
+
+enum {
+	TCA_SFB_UNSPEC,
+	TCA_SFB_PARMS,
+	__TCA_SFB_MAX,
+};
+
+#define TCA_SFB_MAX (__TCA_SFB_MAX - 1)
+
+/*
+ * Note: increment, decrement are Q0.16 fixed-point values.
+ */
+struct tc_sfb_qopt {
+	__u32 rehash_interval;	/* delay between hash move, in ms */
+	__u32 warmup_time;	/* double buffering warmup time in ms (warmup_time < rehash_interval) */
+	__u32 max;		/* max len of qlen_min */
+	__u32 bin_size;		/* maximum queue length per bin */
+	__u32 increment;	/* probability increment, (d1 in Blue) */
+	__u32 decrement;	/* probability decrement, (d2 in Blue) */
+	__u32 limit;		/* max SFB queue length */
+	__u32 penalty_rate;	/* inelastic flows are rate limited to 'rate' pps */
+	__u32 penalty_burst;
+};
+
+struct tc_sfb_xstats {
+	__u32 earlydrop;
+	__u32 penaltydrop;
+	__u32 bucketdrop;
+	__u32 queuedrop;
+	__u32 childdrop; /* drops in child qdisc */
+	__u32 marked;
+	__u32 maxqlen;
+	__u32 maxprob;
+	__u32 avgprob;
+};
+
+#define SFB_MAX_PROB 0xFFFF
+
+/* QFQ */
+enum {
+	TCA_QFQ_UNSPEC,
+	TCA_QFQ_WEIGHT,
+	TCA_QFQ_LMAX,
+	__TCA_QFQ_MAX
+};
+
+#define TCA_QFQ_MAX	(__TCA_QFQ_MAX - 1)
+
+struct tc_qfq_stats {
+	__u32 weight;
+	__u32 lmax;
+};
+
+/* CODEL */
+
+enum {
+	TCA_CODEL_UNSPEC,
+	TCA_CODEL_TARGET,
+	TCA_CODEL_LIMIT,
+	TCA_CODEL_INTERVAL,
+	TCA_CODEL_ECN,
+	TCA_CODEL_CE_THRESHOLD,
+	__TCA_CODEL_MAX
+};
+
+#define TCA_CODEL_MAX	(__TCA_CODEL_MAX - 1)
+
+struct tc_codel_xstats {
+	__u32	maxpacket; /* largest packet we've seen so far */
+	__u32	count;	   /* how many drops we've done since the last time we
+			    * entered dropping state
+			    */
+	__u32	lastcount; /* count at entry to dropping state */
+	__u32	ldelay;    /* in-queue delay seen by most recently dequeued packet */
+	__s32	drop_next; /* time to drop next packet */
+	__u32	drop_overlimit; /* number of time max qdisc packet limit was hit */
+	__u32	ecn_mark;  /* number of packets we ECN marked instead of dropped */
+	__u32	dropping;  /* are we in dropping state ? */
+	__u32	ce_mark;   /* number of CE marked packets because of ce_threshold */
+};
+
+/* FQ_CODEL */
+
+enum {
+	TCA_FQ_CODEL_UNSPEC,
+	TCA_FQ_CODEL_TARGET,
+	TCA_FQ_CODEL_LIMIT,
+	TCA_FQ_CODEL_INTERVAL,
+	TCA_FQ_CODEL_ECN,
+	TCA_FQ_CODEL_FLOWS,
+	TCA_FQ_CODEL_QUANTUM,
+	TCA_FQ_CODEL_CE_THRESHOLD,
+	TCA_FQ_CODEL_DROP_BATCH_SIZE,
+	TCA_FQ_CODEL_MEMORY_LIMIT,
+	__TCA_FQ_CODEL_MAX
+};
+
+#define TCA_FQ_CODEL_MAX	(__TCA_FQ_CODEL_MAX - 1)
+
+enum {
+	TCA_FQ_CODEL_XSTATS_QDISC,
+	TCA_FQ_CODEL_XSTATS_CLASS,
+};
+
+struct tc_fq_codel_qd_stats {
+	__u32	maxpacket;	/* largest packet we've seen so far */
+	__u32	drop_overlimit; /* number of time max qdisc
+				 * packet limit was hit
+				 */
+	__u32	ecn_mark;	/* number of packets we ECN marked
+				 * instead of being dropped
+				 */
+	__u32	new_flow_count; /* number of time packets
+				 * created a 'new flow'
+				 */
+	__u32	new_flows_len;	/* count of flows in new list */
+	__u32	old_flows_len;	/* count of flows in old list */
+	__u32	ce_mark;	/* packets above ce_threshold */
+	__u32	memory_usage;	/* in bytes */
+	__u32	drop_overmemory;
+};
+
+struct tc_fq_codel_cl_stats {
+	__s32	deficit;
+	__u32	ldelay;		/* in-queue delay seen by most recently
+				 * dequeued packet
+				 */
+	__u32	count;
+	__u32	lastcount;
+	__u32	dropping;
+	__s32	drop_next;
+};
+
+struct tc_fq_codel_xstats {
+	__u32	type;
+	union {
+		struct tc_fq_codel_qd_stats qdisc_stats;
+		struct tc_fq_codel_cl_stats class_stats;
+	};
+};
+
+/* FQ */
+
+enum {
+	TCA_FQ_UNSPEC,
+
+	TCA_FQ_PLIMIT,		/* limit of total number of packets in queue */
+
+	TCA_FQ_FLOW_PLIMIT,	/* limit of packets per flow */
+
+	TCA_FQ_QUANTUM,		/* RR quantum */
+
+	TCA_FQ_INITIAL_QUANTUM,		/* RR quantum for new flow */
+
+	TCA_FQ_RATE_ENABLE,	/* enable/disable rate limiting */
+
+	TCA_FQ_FLOW_DEFAULT_RATE,/* obsolete, do not use */
+
+	TCA_FQ_FLOW_MAX_RATE,	/* per flow max rate */
+
+	TCA_FQ_BUCKETS_LOG,	/* log2(number of buckets) */
+
+	TCA_FQ_FLOW_REFILL_DELAY,	/* flow credit refill delay in usec */
+
+	TCA_FQ_ORPHAN_MASK,	/* mask applied to orphaned skb hashes */
+
+	TCA_FQ_LOW_RATE_THRESHOLD, /* per packet delay under this rate */
+
+	TCA_FQ_CE_THRESHOLD,	/* DCTCP-like CE-marking threshold */
+
+	__TCA_FQ_MAX
+};
+
+#define TCA_FQ_MAX	(__TCA_FQ_MAX - 1)
+
+struct tc_fq_qd_stats {
+	__u64	gc_flows;
+	__u64	highprio_packets;
+	__u64	tcp_retrans;
+	__u64	throttled;
+	__u64	flows_plimit;
+	__u64	pkts_too_long;
+	__u64	allocation_errors;
+	__s64	time_next_delayed_flow;
+	__u32	flows;
+	__u32	inactive_flows;
+	__u32	throttled_flows;
+	__u32	unthrottle_latency_ns;
+	__u64	ce_mark;		/* packets above ce_threshold */
+};
+
+/* Heavy-Hitter Filter */
+
+enum {
+	TCA_HHF_UNSPEC,
+	TCA_HHF_BACKLOG_LIMIT,
+	TCA_HHF_QUANTUM,
+	TCA_HHF_HH_FLOWS_LIMIT,
+	TCA_HHF_RESET_TIMEOUT,
+	TCA_HHF_ADMIT_BYTES,
+	TCA_HHF_EVICT_TIMEOUT,
+	TCA_HHF_NON_HH_WEIGHT,
+	__TCA_HHF_MAX
+};
+
+#define TCA_HHF_MAX	(__TCA_HHF_MAX - 1)
+
+struct tc_hhf_xstats {
+	__u32	drop_overlimit; /* number of times max qdisc packet limit
+				 * was hit
+				 */
+	__u32	hh_overlimit;   /* number of times max heavy-hitters was hit */
+	__u32	hh_tot_count;   /* number of captured heavy-hitters so far */
+	__u32	hh_cur_count;   /* number of current heavy-hitters */
+};
+
+/* PIE */
+enum {
+	TCA_PIE_UNSPEC,
+	TCA_PIE_TARGET,
+	TCA_PIE_LIMIT,
+	TCA_PIE_TUPDATE,
+	TCA_PIE_ALPHA,
+	TCA_PIE_BETA,
+	TCA_PIE_ECN,
+	TCA_PIE_BYTEMODE,
+	__TCA_PIE_MAX
+};
+#define TCA_PIE_MAX   (__TCA_PIE_MAX - 1)
+
+struct tc_pie_xstats {
+	__u32 prob;             /* current probability */
+	__u32 delay;            /* current delay in ms */
+	__u32 avg_dq_rate;      /* current average dq_rate in bits/pie_time */
+	__u32 packets_in;       /* total number of packets enqueued */
+	__u32 dropped;          /* packets dropped due to pie_action */
+	__u32 overlimit;        /* dropped due to lack of space in queue */
+	__u32 maxq;             /* maximum queue size */
+	__u32 ecn_mark;         /* packets marked with ecn*/
+};
+
+/* CBS */
+struct tc_cbs_qopt {
+	__u8 offload;
+	__u8 _pad[3];
+	__s32 hicredit;
+	__s32 locredit;
+	__s32 idleslope;
+	__s32 sendslope;
+};
+
+enum {
+	TCA_CBS_UNSPEC,
+	TCA_CBS_PARMS,
+	__TCA_CBS_MAX,
+};
+
+#define TCA_CBS_MAX (__TCA_CBS_MAX - 1)
+
+
+/* ETF */
+struct tc_etf_qopt {
+	__s32 delta;
+	__s32 clockid;
+	__u32 flags;
+#define TC_ETF_DEADLINE_MODE_ON	BIT(0)
+#define TC_ETF_OFFLOAD_ON	BIT(1)
+};
+
+enum {
+	TCA_ETF_UNSPEC,
+	TCA_ETF_PARMS,
+	__TCA_ETF_MAX,
+};
+
+#define TCA_ETF_MAX (__TCA_ETF_MAX - 1)
+
+
+/* CAKE */
+enum {
+	TCA_CAKE_UNSPEC,
+	TCA_CAKE_PAD,
+	TCA_CAKE_BASE_RATE64,
+	TCA_CAKE_DIFFSERV_MODE,
+	TCA_CAKE_ATM,
+	TCA_CAKE_FLOW_MODE,
+	TCA_CAKE_OVERHEAD,
+	TCA_CAKE_RTT,
+	TCA_CAKE_TARGET,
+	TCA_CAKE_AUTORATE,
+	TCA_CAKE_MEMORY,
+	TCA_CAKE_NAT,
+	TCA_CAKE_RAW,
+	TCA_CAKE_WASH,
+	TCA_CAKE_MPU,
+	TCA_CAKE_INGRESS,
+	TCA_CAKE_ACK_FILTER,
+	TCA_CAKE_SPLIT_GSO,
+	__TCA_CAKE_MAX
+};
+#define TCA_CAKE_MAX	(__TCA_CAKE_MAX - 1)
+
+enum {
+	__TCA_CAKE_STATS_INVALID,
+	TCA_CAKE_STATS_PAD,
+	TCA_CAKE_STATS_CAPACITY_ESTIMATE64,
+	TCA_CAKE_STATS_MEMORY_LIMIT,
+	TCA_CAKE_STATS_MEMORY_USED,
+	TCA_CAKE_STATS_AVG_NETOFF,
+	TCA_CAKE_STATS_MIN_NETLEN,
+	TCA_CAKE_STATS_MAX_NETLEN,
+	TCA_CAKE_STATS_MIN_ADJLEN,
+	TCA_CAKE_STATS_MAX_ADJLEN,
+	TCA_CAKE_STATS_TIN_STATS,
+	TCA_CAKE_STATS_DEFICIT,
+	TCA_CAKE_STATS_COBALT_COUNT,
+	TCA_CAKE_STATS_DROPPING,
+	TCA_CAKE_STATS_DROP_NEXT_US,
+	TCA_CAKE_STATS_P_DROP,
+	TCA_CAKE_STATS_BLUE_TIMER_US,
+	__TCA_CAKE_STATS_MAX
+};
+#define TCA_CAKE_STATS_MAX (__TCA_CAKE_STATS_MAX - 1)
+
+enum {
+	__TCA_CAKE_TIN_STATS_INVALID,
+	TCA_CAKE_TIN_STATS_PAD,
+	TCA_CAKE_TIN_STATS_SENT_PACKETS,
+	TCA_CAKE_TIN_STATS_SENT_BYTES64,
+	TCA_CAKE_TIN_STATS_DROPPED_PACKETS,
+	TCA_CAKE_TIN_STATS_DROPPED_BYTES64,
+	TCA_CAKE_TIN_STATS_ACKS_DROPPED_PACKETS,
+	TCA_CAKE_TIN_STATS_ACKS_DROPPED_BYTES64,
+	TCA_CAKE_TIN_STATS_ECN_MARKED_PACKETS,
+	TCA_CAKE_TIN_STATS_ECN_MARKED_BYTES64,
+	TCA_CAKE_TIN_STATS_BACKLOG_PACKETS,
+	TCA_CAKE_TIN_STATS_BACKLOG_BYTES,
+	TCA_CAKE_TIN_STATS_THRESHOLD_RATE64,
+	TCA_CAKE_TIN_STATS_TARGET_US,
+	TCA_CAKE_TIN_STATS_INTERVAL_US,
+	TCA_CAKE_TIN_STATS_WAY_INDIRECT_HITS,
+	TCA_CAKE_TIN_STATS_WAY_MISSES,
+	TCA_CAKE_TIN_STATS_WAY_COLLISIONS,
+	TCA_CAKE_TIN_STATS_PEAK_DELAY_US,
+	TCA_CAKE_TIN_STATS_AVG_DELAY_US,
+	TCA_CAKE_TIN_STATS_BASE_DELAY_US,
+	TCA_CAKE_TIN_STATS_SPARSE_FLOWS,
+	TCA_CAKE_TIN_STATS_BULK_FLOWS,
+	TCA_CAKE_TIN_STATS_UNRESPONSIVE_FLOWS,
+	TCA_CAKE_TIN_STATS_MAX_SKBLEN,
+	TCA_CAKE_TIN_STATS_FLOW_QUANTUM,
+	__TCA_CAKE_TIN_STATS_MAX
+};
+#define TCA_CAKE_TIN_STATS_MAX (__TCA_CAKE_TIN_STATS_MAX - 1)
+#define TC_CAKE_MAX_TINS (8)
+
+enum {
+	CAKE_FLOW_NONE = 0,
+	CAKE_FLOW_SRC_IP,
+	CAKE_FLOW_DST_IP,
+	CAKE_FLOW_HOSTS,    /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_DST_IP */
+	CAKE_FLOW_FLOWS,
+	CAKE_FLOW_DUAL_SRC, /* = CAKE_FLOW_SRC_IP | CAKE_FLOW_FLOWS */
+	CAKE_FLOW_DUAL_DST, /* = CAKE_FLOW_DST_IP | CAKE_FLOW_FLOWS */
+	CAKE_FLOW_TRIPLE,   /* = CAKE_FLOW_HOSTS  | CAKE_FLOW_FLOWS */
+	CAKE_FLOW_MAX,
+};
+
+enum {
+	CAKE_DIFFSERV_DIFFSERV3 = 0,
+	CAKE_DIFFSERV_DIFFSERV4,
+	CAKE_DIFFSERV_DIFFSERV8,
+	CAKE_DIFFSERV_BESTEFFORT,
+	CAKE_DIFFSERV_PRECEDENCE,
+	CAKE_DIFFSERV_MAX
+};
+
+enum {
+	CAKE_ACK_NONE = 0,
+	CAKE_ACK_FILTER,
+	CAKE_ACK_AGGRESSIVE,
+	CAKE_ACK_MAX
+};
+
+enum {
+	CAKE_ATM_NONE = 0,
+	CAKE_ATM_ATM,
+	CAKE_ATM_PTM,
+	CAKE_ATM_MAX
+};
+
+
+/* TAPRIO */
+enum {
+	TC_TAPRIO_CMD_SET_GATES = 0x00,
+	TC_TAPRIO_CMD_SET_AND_HOLD = 0x01,
+	TC_TAPRIO_CMD_SET_AND_RELEASE = 0x02,
+};
+
+enum {
+	TCA_TAPRIO_SCHED_ENTRY_UNSPEC,
+	TCA_TAPRIO_SCHED_ENTRY_INDEX, /* u32 */
+	TCA_TAPRIO_SCHED_ENTRY_CMD, /* u8 */
+	TCA_TAPRIO_SCHED_ENTRY_GATE_MASK, /* u32 */
+	TCA_TAPRIO_SCHED_ENTRY_INTERVAL, /* u32 */
+	__TCA_TAPRIO_SCHED_ENTRY_MAX,
+};
+#define TCA_TAPRIO_SCHED_ENTRY_MAX (__TCA_TAPRIO_SCHED_ENTRY_MAX - 1)
+
+/* The format for schedule entry list is:
+ * [TCA_TAPRIO_SCHED_ENTRY_LIST]
+ *   [TCA_TAPRIO_SCHED_ENTRY]
+ *     [TCA_TAPRIO_SCHED_ENTRY_CMD]
+ *     [TCA_TAPRIO_SCHED_ENTRY_GATES]
+ *     [TCA_TAPRIO_SCHED_ENTRY_INTERVAL]
+ */
+enum {
+	TCA_TAPRIO_SCHED_UNSPEC,
+	TCA_TAPRIO_SCHED_ENTRY,
+	__TCA_TAPRIO_SCHED_MAX,
+};
+
+#define TCA_TAPRIO_SCHED_MAX (__TCA_TAPRIO_SCHED_MAX - 1)
+
+enum {
+	TCA_TAPRIO_ATTR_UNSPEC,
+	TCA_TAPRIO_ATTR_PRIOMAP, /* struct tc_mqprio_qopt */
+	TCA_TAPRIO_ATTR_SCHED_ENTRY_LIST, /* nested of entry */
+	TCA_TAPRIO_ATTR_SCHED_BASE_TIME, /* s64 */
+	TCA_TAPRIO_ATTR_SCHED_SINGLE_ENTRY, /* single entry */
+	TCA_TAPRIO_ATTR_SCHED_CLOCKID, /* s32 */
+	TCA_TAPRIO_PAD,
+	__TCA_TAPRIO_ATTR_MAX,
+};
+
+#define TCA_TAPRIO_ATTR_MAX (__TCA_TAPRIO_ATTR_MAX - 1)
+
+#endif
-- 
Gitee


From bd1fd3b971dd35f1228a7092cd09f2b3fb670b4c Mon Sep 17 00:00:00 2001
From: Alan Maguire <alan.maguire@oracle.com>
Date: Fri, 9 Jun 2023 17:25:12 +0800
Subject: [PATCH 10/12] bpftool: Fix compilation failure for net.o with older
 glibc
MIME-Version: 1.0
Content-Type: text/plain; charset=UTF-8
Content-Transfer-Encoding: 8bit

ANBZ: #5530

commit 6f02b540d7597f357bc6ee711346761045d4e108 upstream

For older glibc ~2.17, #include'ing both linux/if.h and net/if.h
fails due to complaints about redefinition of interface flags:

  CC       net.o
In file included from net.c:13:0:
/usr/include/linux/if.h:71:2: error: redeclaration of enumerator ‘IFF_UP’
  IFF_UP    = 1<<0,  /* sysfs */
  ^
/usr/include/net/if.h:44:5: note: previous definition of ‘IFF_UP’ was here
     IFF_UP = 0x1,  /* Interface is up.  */

The issue was fixed in kernel headers in [1], but since compilation
of net.c picks up system headers the problem can recur.

Dropping #include <linux/if.h> resolves the issue and it is
not needed for compilation anyhow.

[1] https://lore.kernel.org/netdev/1461512707-23058-1-git-send-email-mikko.rapeli__34748.27880641$1462831734$gmane$org@iki.fi/

Fixes: f6f3bac08ff9 ("tools/bpf: bpftool: add net support")
Signed-off-by: Alan Maguire <alan.maguire@oracle.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Martin KaFai Lau <kafai@fb.com>
Link: https://lore.kernel.org/bpf/1609948746-15369-1-git-send-email-alan.maguire@oracle.com
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/bpf/bpftool/net.c | 1 -
 1 file changed, 1 deletion(-)

diff --git a/tools/bpf/bpftool/net.c b/tools/bpf/bpftool/net.c
index ed205ee57655..63b47b8e5e41 100644
--- a/tools/bpf/bpftool/net.c
+++ b/tools/bpf/bpftool/net.c
@@ -8,7 +8,6 @@
 #include <unistd.h>
 #include <libbpf.h>
 #include <net/if.h>
-#include <linux/if.h>
 #include <linux/rtnetlink.h>
 #include <linux/tc_act/tc_bpf.h>
 #include <sys/socket.h>
-- 
Gitee


From 6478c7b08ddd7512423ccad576c230a385408835 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 2 Jun 2023 17:10:48 +0800
Subject: [PATCH 11/12] bpf: add bpffs pretty print for program array map

ANBZ: #5530

commit a7c19db38d62fc1ce797dba19936e9f81cf2b9fb upstream

Added bpffs pretty print for program array map. For a particular
array index, if the program array points to a valid program,
the "<index>: <prog_id>" will be printed out like
   0: 6
which means bpf program with id "6" is installed at index "0".

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 kernel/bpf/arraymap.c | 25 ++++++++++++++++++++++++-
 1 file changed, 24 insertions(+), 1 deletion(-)

diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c
index 0c17aab3ce5f..1b2cccff5983 100644
--- a/kernel/bpf/arraymap.c
+++ b/kernel/bpf/arraymap.c
@@ -529,6 +529,29 @@ static void bpf_fd_array_map_clear(struct bpf_map *map)
 		fd_array_map_delete_elem(map, &i);
 }
 
+static void prog_array_map_seq_show_elem(struct bpf_map *map, void *key,
+					 struct seq_file *m)
+{
+	void **elem, *ptr;
+	u32 prog_id;
+
+	rcu_read_lock();
+
+	elem = array_map_lookup_elem(map, key);
+	if (elem) {
+		ptr = READ_ONCE(*elem);
+		if (ptr) {
+			seq_printf(m, "%u: ", *(u32 *)key);
+			prog_id = prog_fd_array_sys_lookup_elem(ptr);
+			btf_type_seq_show(map->btf, map->btf_value_type_id,
+					  &prog_id, m);
+			seq_puts(m, "\n");
+		}
+	}
+
+	rcu_read_unlock();
+}
+
 const struct bpf_map_ops prog_array_map_ops = {
 	.map_alloc_check = fd_array_map_alloc_check,
 	.map_alloc = array_map_alloc,
@@ -540,7 +563,7 @@ const struct bpf_map_ops prog_array_map_ops = {
 	.map_fd_put_ptr = prog_fd_array_put_ptr,
 	.map_fd_sys_lookup_elem = prog_fd_array_sys_lookup_elem,
 	.map_release_uref = bpf_fd_array_map_clear,
-	.map_check_btf = map_check_no_btf,
+	.map_seq_show_elem = prog_array_map_seq_show_elem,
 };
 
 static struct bpf_event_entry *bpf_event_entry_gen(struct file *perf_file,
-- 
Gitee


From 13c00472b4e788d9c325cf663bcc271bd94e9220 Mon Sep 17 00:00:00 2001
From: Yonghong Song <yhs@fb.com>
Date: Fri, 2 Jun 2023 17:13:50 +0800
Subject: [PATCH 12/12] tools/bpf: bpftool: support prog array map and map of
 maps

ANBZ: #5530

commit ad3338d2508cd7752accdd39881deced1ec2b8a1 upstream

Currently, prog array map and map of maps are not supported
in bpftool. This patch added the support.
Different from other map types, for prog array map and
map of maps, the key returned bpf_get_next_key() may not
point to a valid value. So for these two map types,
no error will be printed out when such a scenario happens.

The following is the plain and json dump if btf is not available:
  $ ./bpftool map dump id 10
    key: 08 00 00 00  value: 5c 01 00 00
    Found 1 element
  $ ./bpftool -jp map dump id 10
    [{
        "key": ["0x08","0x00","0x00","0x00"
        ],
        "value": ["0x5c","0x01","0x00","0x00"
        ]
    }]

If the BTF is available, the dump looks below:
  $ ./bpftool map dump id 2
    [{
            "key": 0,
            "value": 7
        }
    ]
  $ ./bpftool -jp map dump id 2
    [{
        "key": ["0x00","0x00","0x00","0x00"
        ],
        "value": ["0x07","0x00","0x00","0x00"
        ],
        "formatted": {
            "key": 0,
            "value": 7
        }
    }]

Signed-off-by: Yonghong Song <yhs@fb.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: zhaoxuezhi <zhaoxuezhi@uniontech.com>
---
 tools/bpf/bpftool/map.c | 11 +++--------
 1 file changed, 3 insertions(+), 8 deletions(-)

diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c
index ec73d83d0d31..f41e2907a336 100644
--- a/tools/bpf/bpftool/map.c
+++ b/tools/bpf/bpftool/map.c
@@ -660,12 +660,6 @@ static int do_dump(int argc, char **argv)
 	if (fd < 0)
 		return -1;
 
-	if (map_is_map_of_maps(info.type) || map_is_map_of_progs(info.type)) {
-		p_err("Dumping maps of maps and program maps not supported");
-		close(fd);
-		return -1;
-	}
-
 	key = malloc(info.key_size);
 	value = alloc_value(&info);
 	if (!key || !value) {
@@ -719,7 +713,9 @@ static int do_dump(int argc, char **argv)
 				} else {
 					print_entry_plain(&info, key, value);
 				}
-		} else {
+			num_elems++;
+		} else if (!map_is_map_of_maps(info.type) &&
+			   !map_is_map_of_progs(info.type)) {
 			if (json_output) {
 				jsonw_name(json_wtr, "key");
 				print_hex_data_json(key, info.key_size);
@@ -736,7 +732,6 @@ static int do_dump(int argc, char **argv)
 		}
 
 		prev_key = key;
-		num_elems++;
 	}
 
 	if (json_output)
-- 
Gitee