Skip to contentSkip to conversation

tools/bpf: add bpftool net support

PATCH Applied Yonghong Song 3 participants 10 messages Sep 6, 2018 – Sep 13, 2018

Subsystems (5)
lore
Share & tools
lore
#0 lore raw

cover tools/bpf: add bpftool net support

As bpf usage becomes more pervasive, people starts to worry about their cpu and memory cost. On a particular host, people often wanted to know all running bpf programs and their attachment context. So they can relate
a performance/memory anormly quickly to a particular bpf program or an application.

bpftool already provides a pretty good coverage for perf and cgroup related attachments. This patch set enabled to dump attachment info for xdp and tc bpf programs.

Currently, users can already use "ip link show <dev>" and "tc filter show dev <dev> ..." to dump bpf program attachment information for xdp and tc bpf programs. The main reason to implement such functionality in bpftool as well is for better user experience. We want the bpftool to be the ultimate tool for bpf introspection. The bpftool net implementation will only present necessary bpf attachment information to the user, ignoring most other ip/tc specific information.

For example, the below is a pretty json print for xdp and tc_filters.

  $ ./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"
            }
        ]
    }
  ]

Patch #1 synced kernel uapi header if_link.h to tools directory. Patch #2 moved tools/bpf/lib/bpf.c netlink related functions to a new file. Patch #3 implemented additional functions in libbpf which will be used in Patch #4.
Patch #4 implemented bpftool net support to dump
xdp and tc bpf program attachments.

Yonghong Song (4):
tools/bpf: sync kernel uapi header if_link.h to tools tools/bpf: move bpf/lib netlink related functions into a new file tools/bpf: add more netlink functionalities in lib/bpf tools/bpf: bpftool: add net support

 .../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 ++++++
 tools/include/uapi/linux/if_link.h            |  17 +
 tools/lib/bpf/Build                           |   2 +-
 tools/lib/bpf/bpf.c                           | 129 -------
 tools/lib/bpf/libbpf.h                        |  16 +
 tools/lib/bpf/libbpf_errno.c                  |   1 +
 tools/lib/bpf/netlink.c                       | 324 ++++++++++++++++++
 tools/lib/bpf/nlattr.c                        |  33 +-
 tools/lib/bpf/nlattr.h                        |  38 ++
 16 files changed, 1094 insertions(+), 149 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
 create mode 100644 tools/lib/bpf/netlink.c
Signature · 1 line
2.17.1
#1 lore raw

PATCH 1/4 tools/bpf: sync kernel uapi header if_link.h to tools

Among others, this header will be used later for
bpftool net support.

---
 tools/include/uapi/linux/if_link.h | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)
tools/include/uapi/linux/if_link.h +17 -0
index cf01b6824244..43391e2d1153 100644
@@ -164,6 +164,8 @@ enum {
 	IFLA_CARRIER_UP_COUNT,
 	IFLA_CARRIER_DOWN_COUNT,
 	IFLA_NEW_IFINDEX,
+	IFLA_MIN_MTU,
+	IFLA_MAX_MTU,
 	__IFLA_MAX
 };
 
@@ -334,6 +336,7 @@ enum {
 	IFLA_BRPORT_GROUP_FWD_MASK,
 	IFLA_BRPORT_NEIGH_SUPPRESS,
 	IFLA_BRPORT_ISOLATED,
+	IFLA_BRPORT_BACKUP_PORT,
 	__IFLA_BRPORT_MAX
 };
 #define IFLA_BRPORT_MAX (__IFLA_BRPORT_MAX - 1)
@@ -459,6 +462,16 @@ enum {
 
 #define IFLA_MACSEC_MAX (__IFLA_MACSEC_MAX - 1)
 
+/* XFRM section */
+enum {
+	IFLA_XFRM_UNSPEC,
+	IFLA_XFRM_LINK,
+	IFLA_XFRM_IF_ID,
+	__IFLA_XFRM_MAX
+};
+
+#define IFLA_XFRM_MAX (__IFLA_XFRM_MAX - 1)
+
 enum macsec_validation_type {
 	MACSEC_VALIDATE_DISABLED = 0,
 	MACSEC_VALIDATE_CHECK = 1,
@@ -920,6 +933,7 @@ enum {
 	XDP_ATTACHED_DRV,
 	XDP_ATTACHED_SKB,
 	XDP_ATTACHED_HW,
+	XDP_ATTACHED_MULTI,
 };
 
 enum {
@@ -928,6 +942,9 @@ enum {
 	IFLA_XDP_ATTACHED,
 	IFLA_XDP_FLAGS,
 	IFLA_XDP_PROG_ID,
+	IFLA_XDP_DRV_PROG_ID,
+	IFLA_XDP_SKB_PROG_ID,
+	IFLA_XDP_HW_PROG_ID,
 	__IFLA_XDP_MAX,
 };
 
Signature · 1 line
2.17.1
#2 lore raw

PATCH 2/4 tools/bpf: move bpf/lib netlink related functions into a new file

In reply to Yonghong Song

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.

---
 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
tools/lib/bpf/Build +1 -1
index 13a861135127..512b2c0ba0d2 100644
@@ -1 +1 @@
-libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o
+libbpf-y := libbpf.o bpf.o nlattr.o btf.o libbpf_errno.o netlink.o
tools/lib/bpf/bpf.c +0 -129

143 lines not on this page · raw message

tools/lib/bpf/netlink.c new file +165 -0

165 lines not on this page · raw message

Signature · 1 line
2.17.1
#3 lore raw

PATCH 3/4 tools/bpf: add more netlink functionalities in lib/bpf

In reply to Yonghong Song

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.

---
 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(-)
tools/lib/bpf/libbpf.h +16 -0
index 96c55fac54c3..e3b00e23e181 100644
@@ -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
tools/lib/bpf/libbpf_errno.c +1 -0
index d9ba851bd7f9..2464ade3b326 100644
@@ -42,6 +42,7 @@ 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)
tools/lib/bpf/netlink.c +162 -3

191 lines not on this page · raw message

tools/lib/bpf/nlattr.c +21 -12
index 4719434278b2..49f514119bdb 100644
@@ -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)
 {
tools/lib/bpf/nlattr.h +38 -0
index 931a71f68f93..a6e2396bce7c 100644
@@ -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 */
Signature · 1 line
2.17.1
#4 lore raw

PATCH 4/4 tools/bpf: bpftool: add net support

In reply to Yonghong Song

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"
            }
        ]
    }
  ]
---
 .../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
tools/bpf/bpftool/Documentation/bpftool-net.rst new file +133 -0
new file mode 100644
index 000000000000..48a61837a264
@@ -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)
tools/bpf/bpftool/Documentation/bpftool.rst +4 -2
index b6f5d560460d..8dda77daeda9 100644
@@ -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)
tools/bpf/bpftool/bash-completion/bpftool +13 -4
index 598066c40191..df1060b852c1 100644
@@ -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
tools/bpf/bpftool/main.c +2 -1
index d15a62be6cf0..79dc3f193547 100644
@@ -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 }
 };
tools/bpf/bpftool/main.h +7 -0
index 238e734d75b3..02dfbcb92a23 100644
@@ -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
tools/bpf/bpftool/net.c new file +233 -0

233 lines not on this page · raw message

tools/bpf/bpftool/netlink_dumper.c new file +181 -0

181 lines not on this page · raw message

tools/bpf/bpftool/netlink_dumper.h new file +103 -0

103 lines not on this page · raw message

Signature · 1 line
2.17.1
maintainer
#5 lore raw

Re: [PATCH bpf-next 4/4] tools/bpf: bpftool: add net support

Quoted 12 lines · Yonghong Song

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.

Quoted 5 lines

For example,

  $ ./bpftool net
  xdp [
  ifindex 2 devname eth0 prog_id 198
  ]

Could we make the output more terse? E.g. the 'ifindex' and 'devname' is basically zero information but will take lots of space. 'eth0 (2)' would for example make it shorter. Also info is missing whether the attached prog is driver/hw/generic XDP. :(

Quoted 11 lines

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
Quoted 1 line

]

Similar comment here. Do we need the tag here? I think it's not really needed, e.g. the output of bpftool perf [0] doesn't provide it either and therefore makes the list as nice one-liners, so overview is much nicer there. Is there a reason that tc progs do not show dev name as opposed to xdp progs? Can we shorten everything to make it a one-liner like in bpftool perf?

Should we have a small indicator here if the tc prog was offloaded?

Does the dump work with tc shared blocks?

Should we also dump networking related cgroup BPF progs here under bpftool net?

Thanks,
Daniel

[0] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b04df400c30235fa347313c9e2a0695549bd2c8e

maintainer
#6 lore raw

Re: [PATCH bpf-next 4/4] tools/bpf: bpftool: add net support

Quoted 42 lines · Daniel Borkmann
Quoted 12 lines · Yonghong Song

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.

Quoted 5 lines

For example,

  $ ./bpftool net
  xdp [
  ifindex 2 devname eth0 prog_id 198
  ]

Could we make the output more terse? E.g. the 'ifindex' and 'devname' is basically zero information but will take lots of space. 'eth0 (2)' would for example make it shorter. Also info is missing whether the attached prog is driver/hw/generic XDP. :(

Quoted 11 lines

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
Quoted 1 line

]

Similar comment here. Do we need the tag here? I think it's not really needed, e.g. the output of bpftool perf [0] doesn't provide it either and therefore makes the list as nice one-liners, so overview is much nicer there. Is there a reason that tc progs do not show dev name as opposed to xdp progs? Can we shorten everything to make it a one-liner like in bpftool perf?

Quoted 5 lines

Should we have a small indicator here if the tc prog was offloaded?

Does the dump work with tc shared blocks?

Should we also dump networking related cgroup BPF progs here under bpftool net?

One more thought, I think it would make sense to also explicitly document current limitations of the progs that this listing does not show where user should consult other tools aka iproute2 e.g. lwt, seg6, tc bpf actions, etc, so the current scope would be more clear for users.

Quoted 5 lines

Thanks,
Daniel

[0] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b04df400c30235fa347313c9e2a0695549bd2c8e

#7 lore raw

Re: [PATCH bpf-next 4/4] tools/bpf: bpftool: add net support

Quoted 45 lines · Daniel Borkmann
Quoted 44 lines · Daniel Borkmann
Quoted 12 lines · Yonghong Song

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.

Quoted 5 lines

For example,

   $ ./bpftool net
   xdp [
   ifindex 2 devname eth0 prog_id 198
   ]

Could we make the output more terse? E.g. the 'ifindex' and 'devname' is basically zero information but will take lots of space. 'eth0 (2)' would for example make it shorter. Also info is missing whether the attached prog is driver/hw/generic XDP. :(

Quoted 4 lines
   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
Quoted 8 lines
             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
   ]

Similar comment here. Do we need the tag here? I think it's not really needed, e.g. the output of bpftool perf [0] doesn't provide it either and therefore makes the list as nice one-liners, so overview is much nicer there. Is there a reason that tc progs do not show dev name as opposed to xdp progs? Can we shorten everything to make it a one-liner like in bpftool perf?

Should we have a small indicator here if the tc prog was offloaded?

Quoted 8 lines
Quoted 3 lines

Does the dump work with tc shared blocks?

Should we also dump networking related cgroup BPF progs here under bpftool net?

One more thought, I think it would make sense to also explicitly document current limitations of the progs that this listing does not show where user should consult other tools aka iproute2 e.g. lwt, seg6, tc bpf actions, etc, so the current scope would be more clear for users.

I will do a followup patch to address a few issues mentioned in my previous email (mostly more concise output, briefly mentioning limitation of the tool, etc.) and also add more information in the documentation and also in the 'bpf net help' output to set user's
expectation right about what this tool can do and how to find more
information.

Quoted 7 lines
Quoted 6 lines

Thanks,
Daniel

   [0] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b04df400c30235fa347313c9e2a0695549bd2c8e
#8 lore raw

Re: [PATCH bpf-next 4/4] tools/bpf: bpftool: add net support

In reply to Daniel Borkmann
Quoted 19 lines · Daniel Borkmann
Quoted 12 lines · Yonghong Song

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.

Quoted 5 lines

For example,

   $ ./bpftool net
   xdp [
   ifindex 2 devname eth0 prog_id 198
   ]
Quoted 3 lines

Could we make the output more terse? E.g. the 'ifindex' and 'devname' is basically zero information but will take lots of space. 'eth0 (2)' would for example make it shorter. Also info is missing whether the attached prog is driver/hw/generic XDP. :(

Right 'eth0 (2)' is a good idea. Similarly to other bpftool plain output, agree we should have concise printout. For the above xdp output, I guess I tested on an old kernel and will test on newer kernel to ensure it works properly.

Quoted 14 lines
Quoted 13 lines
   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
   ]
Quoted 5 lines

Similar comment here. Do we need the tag here? I think it's not really needed, e.g. the output of bpftool perf [0] doesn't provide it either and therefore makes the list as nice one-liners, so overview is much nicer there. Is there a reason that tc progs do not show dev name as opposed to xdp progs? Can we shorten everything to make it a one-liner like in bpftool perf?

Yes, we should remove 'tag'. Users can use prog_id to find tag. There is no IFNAME attribute in the tc filter return message. But I already got them in previous iplink message, so I can print out here.

Quoted 1 line

Should we have a small indicator here if the tc prog was offloaded?

Not sure about this one. As you suggested in the next email, we can have a message like if users want more information they can use more specific tools 'ip link ...', 'tc filter ...' etc.

Quoted 2 lines

Does the dump work with tc shared blocks?

I does not.I did not have experiences with tc shared block and that is why I did not add support for it.

Quoted 2 lines

Should we also dump networking related cgroup BPF progs here under bpftool net?

probably not, but in additional to the above suggestions about using different tools, we can add a message to suggest check bpftool cgroup tree for cgroup related net programs.

Quoted 6 lines

Thanks,
Daniel

   [0] https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git/commit/?id=b04df400c30235fa347313c9e2a0695549bd2c8e
#9 lore raw
In reply to Yonghong Song
Quoted 70 lines · Yonghong Song

As bpf usage becomes more pervasive, people starts to worry about their cpu and memory cost. On a particular host, people often wanted to know all running bpf programs and their attachment context. So they can relate
a performance/memory anormly quickly to a particular bpf program or an application.

bpftool already provides a pretty good coverage for perf and cgroup related attachments. This patch set enabled to dump attachment info for xdp and tc bpf programs.

Currently, users can already use "ip link show <dev>" and "tc filter show dev <dev> ..." to dump bpf program attachment information for xdp and tc bpf programs. The main reason to implement such functionality in bpftool as well is for better user experience. We want the bpftool to be the ultimate tool for bpf introspection. The bpftool net implementation will only present necessary bpf attachment information to the user, ignoring most other ip/tc specific information.

For example, the below is a pretty json print for xdp and tc_filters.

  $ ./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"
            }
        ]
    }
  ]
Quoted 6 lines

Patch #1 synced kernel uapi header if_link.h to tools directory. Patch #2 moved tools/bpf/lib/bpf.c netlink related functions to a new file. Patch #3 implemented additional functions in libbpf which will be used in Patch #4.
Patch #4 implemented bpftool net support to dump
xdp and tc bpf program attachments.

Applied, Thanks