Bpftool sync 2026-01-30

BPF-CHECKPOINT-COMMIT

@@ -1 +1 @@
-1d528e794f3db5d32279123a89957c44c4406a09
+22cc16c04b7893d8fc22810599f49a305d600b9e

CHECKPOINT-COMMIT

@@ -1 +1 @@
-6f0b824a61f212e9707ff68abcabfdfa4724b811
+08a7491843224f8b96518fbe70d9e48163046054

bash-completion/bpftool

@@ -1142,7 +1142,14 @@ _bpftool()
                             return 0
                             ;;
                         8)
-                            _bpftool_once_attr 'overwrite'
+                            case ${words[3]} in
+                                tcx_ingress|tcx_egress)
+                                    _bpftool_once_attr 'prepend'
+                                    ;;
+                                *)
+                                    _bpftool_once_attr 'overwrite'
+                                    ;;
+                            esac
                             return 0
                             ;;
                     esac

docs/bpftool-net.rst

@@ -24,7 +24,7 @@ NET COMMANDS
 ============
 
 | **bpftool** **net** { **show** | **list** } [ **dev** *NAME* ]
-| **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** ]
+| **bpftool** **net attach** *ATTACH_TYPE* *PROG* **dev** *NAME* [ **overwrite** | **prepend** ]
 | **bpftool** **net detach** *ATTACH_TYPE* **dev** *NAME*
 | **bpftool** **net help**
 |
@@ -58,11 +58,9 @@ bpftool net { show | list } [ dev *NAME* ]
     then all bpf programs attached to non clsact qdiscs, and finally all bpf
     programs attached to root and clsact qdisc.
 
-bpftool net attach *ATTACH_TYPE* *PROG* dev *NAME* [ overwrite ]
+bpftool net attach *ATTACH_TYPE* *PROG* dev *NAME* [ overwrite | prepend ]
     Attach bpf program *PROG* to network interface *NAME* with type specified
-    by *ATTACH_TYPE*. Previously attached bpf program can be replaced by the
-    command used with **overwrite** option. Currently, only XDP-related modes
-    are supported for *ATTACH_TYPE*.
+    by *ATTACH_TYPE*.
 
     *ATTACH_TYPE* can be of:
     **xdp** - try native XDP and fallback to generic XDP if NIC driver does not support it;
@@ -72,11 +70,18 @@ bpftool net attach *ATTACH_TYPE* *PROG* dev *NAME* [ overwrite ]
     **tcx_ingress** - Ingress TCX. runs on ingress net traffic;
     **tcx_egress** - Egress TCX. runs on egress net traffic;
 
+    For XDP-related attach types (**xdp**, **xdpgeneric**, **xdpdrv**,
+    **xdpoffload**), the **overwrite** option can be used to replace a
+    previously attached bpf program.
+
+    For **tcx_ingress** and **tcx_egress** attach types, the **prepend** option
+    can be used to attach the program at the beginning of the chain instead of
+    at the end.
+
 bpftool net detach *ATTACH_TYPE* dev *NAME*
     Detach bpf program attached to network interface *NAME* with type specified
     by *ATTACH_TYPE*. To detach bpf program, same *ATTACH_TYPE* previously used
-    for attach must be specified. Currently, only XDP-related modes are
-    supported for *ATTACH_TYPE*.
+    for attach must be specified.
 
 bpftool net help
     Print short help message.
@@ -191,6 +196,17 @@ EXAMPLES
       tc:
       lo(1) tcx/ingress tc_prog prog_id 29
 
+|
+| **# bpftool net attach tcx_ingress name tc_prog2 dev lo prepend**
+| **# bpftool net**
+|
+
+::
+
+      tc:
+      lo(1) tcx/ingress tc_prog2 prog_id 30
+      lo(1) tcx/ingress tc_prog prog_id 29
+
 |
 | **# bpftool net attach tcx_ingress name tc_prog dev lo**
 | **# bpftool net detach tcx_ingress dev lo**

include/uapi/linux/bpf.h

@@ -119,6 +119,14 @@ enum bpf_cgroup_iter_order {
 	BPF_CGROUP_ITER_DESCENDANTS_PRE,	/* walk descendants in pre-order. */
 	BPF_CGROUP_ITER_DESCENDANTS_POST,	/* walk descendants in post-order. */
 	BPF_CGROUP_ITER_ANCESTORS_UP,		/* walk ancestors upward. */
+	/*
+	 * Walks the immediate children of the specified parent
+	 * cgroup_subsys_state. Unlike BPF_CGROUP_ITER_DESCENDANTS_PRE,
+	 * BPF_CGROUP_ITER_DESCENDANTS_POST, and BPF_CGROUP_ITER_ANCESTORS_UP
+	 * the iterator does not include the specified parent as one of the
+	 * returned iterator elements.
+	 */
+	BPF_CGROUP_ITER_CHILDREN,
 };
 
 union bpf_iter_link_info {
@@ -1145,6 +1153,7 @@ enum bpf_attach_type {
 	BPF_NETKIT_PEER,
 	BPF_TRACE_KPROBE_SESSION,
 	BPF_TRACE_UPROBE_SESSION,
+	BPF_TRACE_FSESSION,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -1384,6 +1393,8 @@ enum {
 	BPF_NOEXIST	= 1, /* create new element if it didn't exist */
 	BPF_EXIST	= 2, /* update existing element */
 	BPF_F_LOCK	= 4, /* spin_lock-ed map_lookup/map_update */
+	BPF_F_CPU	= 8, /* cpu flag for percpu maps, upper 32-bit of flags is a cpu number */
+	BPF_F_ALL_CPUS	= 16, /* update value across all CPUs for percpu maps */
 };
 
 /* flags for BPF_MAP_CREATE command */

include/uapi/linux/perf_event.h

@@ -2,7 +2,7 @@
 /*
  * Performance events:
  *
- *    Copyright (C) 2008-2009, Thomas Gleixner <tglx@linutronix.de>
+ *    Copyright (C) 2008-2009, Linutronix GmbH, Thomas Gleixner <tglx@kernel.org>
  *    Copyright (C) 2008-2011, Red Hat, Inc., Ingo Molnar
  *    Copyright (C) 2008-2011, Red Hat, Inc., Peter Zijlstra
  *
@@ -382,6 +382,7 @@ enum perf_event_read_format {
 #define PERF_ATTR_SIZE_VER6			120	/* Add: aux_sample_size */
 #define PERF_ATTR_SIZE_VER7			128	/* Add: sig_data */
 #define PERF_ATTR_SIZE_VER8			136	/* Add: config3 */
+#define PERF_ATTR_SIZE_VER9			144	/* add: config4 */
 
 /*
  * 'struct perf_event_attr' contains various attributes that define
@@ -545,6 +546,7 @@ struct perf_event_attr {
 	__u64	sig_data;
 
 	__u64	config3; /* extension of config2 */
+	__u64	config4; /* extension of config3 */
 };
 
 /*

src/Makefile

@@ -124,8 +124,8 @@ ifeq ($(check_feat),1)
 include Makefile.feature
 endif
 
-LIBS = $(LIBBPF) -lelf -lz -lcrypto
-LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lz -lcrypto
+LIBS = $(LIBBPF) -lelf -lcrypto -lz
+LIBS_BOOTSTRAP = $(LIBBPF_BOOTSTRAP) -lelf -lcrypto -lz
 
 ifeq ($(feature-libelf-zstd),1)
 LIBS += -lzstd

src/common.c

@@ -1191,6 +1191,7 @@ const char *bpf_attach_type_input_str(enum bpf_attach_type t)
 	case BPF_TRACE_FENTRY:			return "fentry";
 	case BPF_TRACE_FEXIT:			return "fexit";
 	case BPF_MODIFY_RETURN:			return "mod_ret";
+	case BPF_TRACE_FSESSION:		return "fsession";
 	case BPF_SK_REUSEPORT_SELECT:		return "sk_skb_reuseport_select";
 	case BPF_SK_REUSEPORT_SELECT_OR_MIGRATE:	return "sk_skb_reuseport_select_or_migrate";
 	default:	return libbpf_bpf_attach_type_str(t);

src/gen.c

@@ -731,10 +731,10 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		{							    \n\
 			struct %1$s *skel;				    \n\
 									    \n\
-			skel = skel_alloc(sizeof(*skel));		    \n\
+			skel = (struct %1$s *)skel_alloc(sizeof(*skel));    \n\
 			if (!skel)					    \n\
 				goto cleanup;				    \n\
-			skel->ctx.sz = (void *)&skel->links - (void *)skel; \n\
+			skel->ctx.sz = (char *)&skel->links - (char *)skel; \n\
 		",
 		obj_name, opts.data_sz);
 	bpf_object__for_each_map(map, obj) {
@@ -755,7 +755,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 		\n\
 		\";							    \n\
 									    \n\
-				skel->%1$s = skel_prep_map_data((void *)data, %2$zd,\n\
+				skel->%1$s = (__typeof__(skel->%1$s))skel_prep_map_data((void *)data, %2$zd,\n\
 								sizeof(data) - 1);\n\
 				if (!skel->%1$s)			    \n\
 					goto cleanup;			    \n\
@@ -857,7 +857,7 @@ static int gen_trace(struct bpf_object *obj, const char *obj_name, const char *h
 
 		codegen("\
 		\n\
-			skel->%1$s = skel_finalize_map_data(&skel->maps.%1$s.initial_value,  \n\
+			skel->%1$s = (__typeof__(skel->%1$s))skel_finalize_map_data(&skel->maps.%1$s.initial_value,\n\
 							%2$zd, %3$s, skel->maps.%1$s.map_fd);\n\
 			if (!skel->%1$s)				    \n\
 				return -ENOMEM;				    \n\

src/net.c

@@ -666,10 +666,16 @@ static int get_tcx_type(enum net_attach_type attach_type)
 	}
 }
 
-static int do_attach_tcx(int progfd, enum net_attach_type attach_type, int ifindex)
+static int do_attach_tcx(int progfd, enum net_attach_type attach_type, int ifindex, bool prepend)
 {
 	int type = get_tcx_type(attach_type);
 
+	if (prepend) {
+		LIBBPF_OPTS(bpf_prog_attach_opts, opts,
+			.flags = BPF_F_BEFORE
+		);
+		return bpf_prog_attach_opts(progfd, ifindex, type, &opts);
+	}
 	return bpf_prog_attach(progfd, ifindex, type, 0);
 }
 
@@ -685,6 +691,7 @@ static int do_attach(int argc, char **argv)
 	enum net_attach_type attach_type;
 	int progfd, ifindex, err = 0;
 	bool overwrite = false;
+	bool prepend = false;
 
 	/* parse attach args */
 	if (!REQ_ARGS(5))
@@ -709,9 +716,25 @@ static int do_attach(int argc, char **argv)
 
 	if (argc) {
 		if (is_prefix(*argv, "overwrite")) {
+			if (attach_type != NET_ATTACH_TYPE_XDP &&
+			    attach_type != NET_ATTACH_TYPE_XDP_GENERIC &&
+			    attach_type != NET_ATTACH_TYPE_XDP_DRIVER &&
+			    attach_type != NET_ATTACH_TYPE_XDP_OFFLOAD) {
+				p_err("'overwrite' is only supported for xdp types");
+				err = -EINVAL;
+				goto cleanup;
+			}
 			overwrite = true;
+		} else if (is_prefix(*argv, "prepend")) {
+			if (attach_type != NET_ATTACH_TYPE_TCX_INGRESS &&
+			    attach_type != NET_ATTACH_TYPE_TCX_EGRESS) {
+				p_err("'prepend' is only supported for tcx_ingress/tcx_egress");
+				err = -EINVAL;
+				goto cleanup;
+			}
+			prepend = true;
 		} else {
-			p_err("expected 'overwrite', got: '%s'?", *argv);
+			p_err("expected 'overwrite' or 'prepend', got: '%s'?", *argv);
 			err = -EINVAL;
 			goto cleanup;
 		}
@@ -728,7 +751,7 @@ static int do_attach(int argc, char **argv)
 	/* attach tcx prog */
 	case NET_ATTACH_TYPE_TCX_INGRESS:
 	case NET_ATTACH_TYPE_TCX_EGRESS:
-		err = do_attach_tcx(progfd, attach_type, ifindex);
+		err = do_attach_tcx(progfd, attach_type, ifindex, prepend);
 		break;
 	default:
 		break;
@@ -985,7 +1008,7 @@ static int do_help(int argc, char **argv)
 
 	fprintf(stderr,
 		"Usage: %1$s %2$s { show | list } [dev <devname>]\n"
-		"       %1$s %2$s attach ATTACH_TYPE PROG dev <devname> [ overwrite ]\n"
+		"       %1$s %2$s attach ATTACH_TYPE PROG dev <devname> [ overwrite | prepend ]\n"
 		"       %1$s %2$s detach ATTACH_TYPE dev <devname>\n"
 		"       %1$s %2$s help\n"
 		"\n"