Re: [PATCH bpf-next 8/9] libbpf: add opt-in strict BPF program section name handling logic

[Date Prev][Date Next][Thread Prev][Thread Next][Date Index][Thread Index]

 

On 09/16, Andrii Nakryiko wrote:

Implement strict ELF section name handling for BPF programs. It utilizes
`libbpf_set_strict_mode()` framework and adds new flag: LIBBPF_STRICT_SEC_NAME. 


If this flag is set, libbpf will enforce exact section name matching for
a lot of program types that previously allowed just partial prefix
match. E.g., if previously SEC("xdp_whatever_i_want") was allowed, now
in strict mode only SEC("xdp") will be accepted, which makes SEC("")
definitions cleaner and more structured. SEC() now won't be used as yet
another way to uniquely encode BPF program identifier (for that
C function name is better and is guaranteed to be unique within
bpf_object). Now SEC() is strictly BPF program type and, depending on
program type, extra load/attach parameter specification.



Libbpf completely supports multiple BPF programs in the same ELF
section, so multiple BPF programs of the same type/specification easily
co-exist together within the same bpf_object scope.



Additionally, a new (for now internal) convention is introduced: section
name that can be a stand-alone exact BPF program type specificator, but
also could have extra parameters after '/' delimiter. An example of such
section is "struct_ops", which can be specified by itself, but also
allows to specify the intended operation to be attached to, e.g.,
"struct_ops/dctcp_init". Note, that "struct_ops_some_op" is not allowed.
Such section definition is specified as "struct_ops+".



This change is part of libbpf 1.0 effort ([0], [1]).



   [0] Closes: https://github.com/libbpf/libbpf/issues/271
[1] https://github.com/libbpf/libbpf/wiki/Libbpf:-the-road-to-v1.0#stricter-and-more-uniform-bpf-program-section-name-sec-handling 


Signed-off-by: Andrii Nakryiko <andrii@xxxxxxxxxx>
---
  tools/lib/bpf/libbpf.c        | 135 ++++++++++++++++++++++------------
  tools/lib/bpf/libbpf_legacy.h |   9 +++
  2 files changed, 98 insertions(+), 46 deletions(-)



diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 56082865ceff..f0846f609e26 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -232,6 +232,7 @@ enum sec_def_flags {
  	SEC_ATTACHABLE_OPT = SEC_ATTACHABLE | SEC_EXP_ATTACH_OPT,
  	SEC_ATTACH_BTF = 4,
  	SEC_SLEEPABLE = 8,
+	SEC_SLOPPY_PFX = 16, /* allow non-strict prefix matching */
  };



  struct bpf_sec_def {
@@ -7976,15 +7977,15 @@ static struct bpf_link *attach_lsm(const struct bpf_program *prog, long cookie); static struct bpf_link *attach_iter(const struct bpf_program *prog, long cookie); 


  static const struct bpf_sec_def section_defs[] = {
-	SEC_DEF("socket",		SOCKET_FILTER, 0, SEC_NONE),
- SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE), - SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE), 
+	SEC_DEF("socket",		SOCKET_FILTER, 0, SEC_SLOPPY_PFX),
+ SEC_DEF("sk_reuseport/migrate", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT_OR_MIGRATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("sk_reuseport", SK_REUSEPORT, BPF_SK_REUSEPORT_SELECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), 
  	SEC_DEF("kprobe/",		KPROBE,	0, SEC_NONE, attach_kprobe),
  	SEC_DEF("uprobe/",		KPROBE,	0, SEC_NONE),
  	SEC_DEF("kretprobe/",		KPROBE, 0, SEC_NONE, attach_kprobe),
  	SEC_DEF("uretprobe/",		KPROBE, 0, SEC_NONE),
-	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_NONE),
-	SEC_DEF("action",		SCHED_ACT, 0, SEC_NONE),
+	SEC_DEF("classifier",		SCHED_CLS, 0, SEC_SLOPPY_PFX),
+	SEC_DEF("action",		SCHED_ACT, 0, SEC_SLOPPY_PFX),
  	SEC_DEF("tracepoint/",		TRACEPOINT, 0, SEC_NONE, attach_tp),
  	SEC_DEF("tp/",			TRACEPOINT, 0, SEC_NONE, attach_tp),
  	SEC_DEF("raw_tracepoint/",	RAW_TRACEPOINT, 0, SEC_NONE, attach_raw_tp),
@@ -8003,44 +8004,44 @@ static const struct bpf_sec_def section_defs[] = {
  	SEC_DEF("syscall",		SYSCALL, 0, SEC_SLEEPABLE),
  	SEC_DEF("xdp_devmap/",		XDP, BPF_XDP_DEVMAP, SEC_ATTACHABLE),
  	SEC_DEF("xdp_cpumap/",		XDP, BPF_XDP_CPUMAP, SEC_ATTACHABLE),
-	SEC_DEF("xdp",			XDP, BPF_XDP, SEC_ATTACHABLE_OPT),
-	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_NONE),
-	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_NONE),
-	SEC_DEF("lwt_out",		LWT_OUT, 0, SEC_NONE),
-	SEC_DEF("lwt_xmit",		LWT_XMIT, 0, SEC_NONE),
-	SEC_DEF("lwt_seg6local",	LWT_SEG6LOCAL, 0, SEC_NONE),
- SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT), - SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT), 
-	SEC_DEF("cgroup/skb",		CGROUP_SKB, 0, SEC_NONE),
- SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE), - SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE), - SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT), - SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT), 
-	SEC_DEF("sockops",		SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT),
- SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT), - SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT), 
-	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_NONE),
-	SEC_DEF("sk_msg",		SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT),
-	SEC_DEF("lirc_mode2",		LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT),
- SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT), - SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE), - SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE), - SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE), - SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE), - SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE), - SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE), - SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE), - SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE), 
-	SEC_DEF("struct_ops",		STRUCT_OPS, 0, SEC_NONE),
+	SEC_DEF("xdp",			XDP, BPF_XDP, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX),
+	SEC_DEF("perf_event",		PERF_EVENT, 0, SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_in",		LWT_IN, 0, SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_out",		LWT_OUT, 0, SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_xmit",		LWT_XMIT, 0, SEC_SLOPPY_PFX),
+	SEC_DEF("lwt_seg6local",	LWT_SEG6LOCAL, 0, SEC_SLOPPY_PFX),
+ SEC_DEF("cgroup_skb/ingress", CGROUP_SKB, BPF_CGROUP_INET_INGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup_skb/egress", CGROUP_SKB, BPF_CGROUP_INET_EGRESS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), 
+	SEC_DEF("cgroup/skb",		CGROUP_SKB, 0, SEC_SLOPPY_PFX),
+ SEC_DEF("cgroup/sock_create", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock_release", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_RELEASE, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sock", CGROUP_SOCK, BPF_CGROUP_INET_SOCK_CREATE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind4", CGROUP_SOCK, BPF_CGROUP_INET4_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/post_bind6", CGROUP_SOCK, BPF_CGROUP_INET6_POST_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/dev", CGROUP_DEVICE, BPF_CGROUP_DEVICE, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sockops", SOCK_OPS, BPF_CGROUP_SOCK_OPS, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_parser", SK_SKB, BPF_SK_SKB_STREAM_PARSER, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("sk_skb/stream_verdict",SK_SKB, BPF_SK_SKB_STREAM_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), 
+	SEC_DEF("sk_skb",		SK_SKB, 0, SEC_SLOPPY_PFX),
+ SEC_DEF("sk_msg", SK_MSG, BPF_SK_MSG_VERDICT, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("lirc_mode2", LIRC_MODE2, BPF_LIRC_MODE2, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("flow_dissector", FLOW_DISSECTOR, BPF_FLOW_DISSECTOR, SEC_ATTACHABLE_OPT | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/bind6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_BIND, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/connect6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_CONNECT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sendmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_SENDMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg4", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP4_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/recvmsg6", CGROUP_SOCK_ADDR, BPF_CGROUP_UDP6_RECVMSG, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getpeername6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETPEERNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname4", CGROUP_SOCK_ADDR, BPF_CGROUP_INET4_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockname6", CGROUP_SOCK_ADDR, BPF_CGROUP_INET6_GETSOCKNAME, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/sysctl", CGROUP_SYSCTL, BPF_CGROUP_SYSCTL, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/getsockopt", CGROUP_SOCKOPT, BPF_CGROUP_GETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), + SEC_DEF("cgroup/setsockopt", CGROUP_SOCKOPT, BPF_CGROUP_SETSOCKOPT, SEC_ATTACHABLE | SEC_SLOPPY_PFX), 
+	SEC_DEF("struct_ops+",		STRUCT_OPS, 0, SEC_NONE),
  	SEC_DEF("sk_lookup/",		SK_LOOKUP, BPF_SK_LOOKUP, SEC_ATTACHABLE),
  };



@@ -8048,11 +8049,53 @@ static const struct bpf_sec_def section_defs[] = {



  static const struct bpf_sec_def *find_sec_def(const char *sec_name)
  {
-	int i, n = ARRAY_SIZE(section_defs);
+	const struct bpf_sec_def *sec_def;
+	enum sec_def_flags sec_flags;
+	int i, n = ARRAY_SIZE(section_defs), len;
+	bool strict = libbpf_mode & LIBBPF_STRICT_SEC_NAME;



  	for (i = 0; i < n; i++) {
-		if (str_has_pfx(sec_name, section_defs[i].sec))
-			return &section_defs[i];
+		sec_def = &section_defs[i];
+		sec_flags = sec_def->cookie;
+		len = strlen(sec_def->sec);
+
+		/* "type/" always has to have proper SEC("type/extras") form */
+		if (sec_def->sec[len - 1] == '/') {
+			if (str_has_pfx(sec_name, sec_def->sec))
+				return sec_def;
+			continue;
+		}
+
+		/* "type+" means it can be either exact SEC("type") or
+		 * well-formed SEC("type/extras") with proper '/' separator
+		 */
+		if (sec_def->sec[len - 1] == '+') {
+			len--;
+			/* not even a prefix */
+			if (strncmp(sec_name, sec_def->sec, len) != 0)
+				continue;
+			/* exact match or has '/' separator */
+			if (sec_name[len] == '\0' || sec_name[len] == '/')
+				return sec_def;
+			continue;
+		}
+
+		/* SEC_SLOPPY_PFX definitions are allowed to be just prefix
+		 * matches, unless strict section name mode
+		 * (LIBBPF_STRICT_SEC_NAME) is enabled, in which case the
+		 * match has to be exact.
+		 */
+		if ((sec_flags & SEC_SLOPPY_PFX) && !strict)  {
+			if (str_has_pfx(sec_name, sec_def->sec))
+				return sec_def;
+			continue;
+		}
+
+		/* Definitions not marked SEC_SLOPPY_PFX (e.g.,
+		 * SEC("syscall")) are exact matches in both modes.
+		 */
+		if (strcmp(sec_name, sec_def->sec) == 0)
+			return sec_def;
  	}
  	return NULL;
  }
diff --git a/tools/lib/bpf/libbpf_legacy.h b/tools/lib/bpf/libbpf_legacy.h
index df0d03dcffab..74e6f860f703 100644
--- a/tools/lib/bpf/libbpf_legacy.h
+++ b/tools/lib/bpf/libbpf_legacy.h
@@ -46,6 +46,15 @@ enum libbpf_strict_mode {
  	 */
  	LIBBPF_STRICT_DIRECT_ERRS = 0x02,



+	/*
+	 * Enforce strict BPF program section (SEC()) names.
+ * E.g., while prefiously SEC("xdp_whatever") or SEC("perf_event_blah") were 
+	 * allowed, with LIBBPF_STRICT_SEC_PREFIX this will become
+	 * unrecognized by libbpf and would have to be just SEC("xdp") and
+	 * SEC("xdp") and SEC("perf_event").
+	 */
+	LIBBPF_STRICT_SEC_NAME = 0x04,


To clarify: I'm assuming, as discussed, we'll still support that old,
non-conforming naming in libbpf 1.0, right? It just won't be enabled
by default.

Btw, forgot to update you, I've enabled LIBBPF_STRICT_DIRECT_ERRS and
LIBBPF_STRICT_CLEAN_PTRS and everything seems to be working fine 🤞
[Index of Archives]     [Linux Samsung SoC]     [Linux Rockchip SoC]     [Linux Actions SoC]     [Linux for Synopsys ARC Processors]     [Linux NFS]     [Linux NILFS]     [Linux USB Devel]     [Video for Linux]     [Linux Audio Users]     [Yosemite News]     [Linux Kernel]     [Linux SCSI]

  Powered by Linux