libbpf: Auto-bump RLIMIT_MEMLOCK if kernel needs it for BPF

The need to increase RLIMIT_MEMLOCK to do anything useful with BPF is
one of the first extremely frustrating gotchas that all new BPF users go
through and in some cases have to learn it a very hard way.

Luckily, starting with upstream Linux kernel version 5.11, BPF subsystem
dropped the dependency on memlock and uses memcg-based memory accounting
instead. Unfortunately, detecting memcg-based BPF memory accounting is
far from trivial (as can be evidenced by this patch), so in practice
most BPF applications still do unconditional RLIMIT_MEMLOCK increase.

As we move towards libbpf 1.0, it would be good to allow users to forget
about RLIMIT_MEMLOCK vs memcg and let libbpf do the sensible adjustment
automatically. This patch paves the way forward in this matter. Libbpf
will do feature detection of memcg-based accounting, and if detected,
will do nothing. But if the kernel is too old, just like BCC, libbpf
will automatically increase RLIMIT_MEMLOCK on behalf of user
application ([0]).

As this is technically a breaking change, during the transition period
applications have to opt into libbpf 1.0 mode by setting
LIBBPF_STRICT_AUTO_RLIMIT_MEMLOCK bit when calling
libbpf_set_strict_mode().

Libbpf allows to control the exact amount of set RLIMIT_MEMLOCK limit
with libbpf_set_memlock_rlim_max() API. Passing 0 will make libbpf do
nothing with RLIMIT_MEMLOCK. libbpf_set_memlock_rlim_max() has to be
called before the first bpf_prog_load(), bpf_btf_load(), or
bpf_object__load() call, otherwise it has no effect and will return
-EBUSY.

  [0] Closes: https://github.com/libbpf/libbpf/issues/369

Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Link: https://lore.kernel.org/bpf/20211214195904.1785155-2-andrii@kernel.org

1 files changed, 9 insertions, 38 deletions

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index c6d84b01a59e..684c34ce1a26 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -187,42 +187,6 @@ const char *libbpf_version_string(void)
 #undef __S
 }
 
-enum kern_feature_id {
-	/* v4.14: kernel support for program & map names. */
-	FEAT_PROG_NAME,
-	/* v5.2: kernel support for global data sections. */
-	FEAT_GLOBAL_DATA,
-	/* BTF support */
-	FEAT_BTF,
-	/* BTF_KIND_FUNC and BTF_KIND_FUNC_PROTO support */
-	FEAT_BTF_FUNC,
-	/* BTF_KIND_VAR and BTF_KIND_DATASEC support */
-	FEAT_BTF_DATASEC,
-	/* BTF_FUNC_GLOBAL is supported */
-	FEAT_BTF_GLOBAL_FUNC,
-	/* BPF_F_MMAPABLE is supported for arrays */
-	FEAT_ARRAY_MMAP,
-	/* kernel support for expected_attach_type in BPF_PROG_LOAD */
-	FEAT_EXP_ATTACH_TYPE,
-	/* bpf_probe_read_{kernel,user}[_str] helpers */
-	FEAT_PROBE_READ_KERN,
-	/* BPF_PROG_BIND_MAP is supported */
-	FEAT_PROG_BIND_MAP,
-	/* Kernel support for module BTFs */
-	FEAT_MODULE_BTF,
-	/* BTF_KIND_FLOAT support */
-	FEAT_BTF_FLOAT,
-	/* BPF perf link support */
-	FEAT_PERF_LINK,
-	/* BTF_KIND_DECL_TAG support */
-	FEAT_BTF_DECL_TAG,
-	/* BTF_KIND_TYPE_TAG support */
-	FEAT_BTF_TYPE_TAG,
-	__FEAT_CNT,
-};
-
-static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id);
-
 enum reloc_type {
 	RELO_LD64,
 	RELO_CALL,
@@ -4352,6 +4316,10 @@ bpf_object__probe_loading(struct bpf_object *obj)
 	if (obj->gen_loader)
 		return 0;
 
+	ret = bump_rlimit_memlock();
+	if (ret)
+		pr_warn("Failed to bump RLIMIT_MEMLOCK (err = %d), you might need to do it explicitly!\n", ret);
+
 	/* make sure basic loading works */
 	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, NULL);
 	if (ret < 0)
@@ -4718,14 +4686,17 @@ static struct kern_feature_desc {
 	[FEAT_BTF_TYPE_TAG] = {
 		"BTF_KIND_TYPE_TAG support", probe_kern_btf_type_tag,
 	},
+	[FEAT_MEMCG_ACCOUNT] = {
+		"memcg-based memory accounting", probe_memcg_account,
+	},
 };
 
-static bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
+bool kernel_supports(const struct bpf_object *obj, enum kern_feature_id feat_id)
 {
 	struct kern_feature_desc *feat = &feature_probes[feat_id];
 	int ret;
 
-	if (obj->gen_loader)
+	if (obj && obj->gen_loader)
 		/* To generate loader program assume the latest kernel
 		 * to avoid doing extra prog_load, map_create syscalls.
 		 */