[PATCH bpf-next 07/16] libbpf: Add arena percpu feature probe

[Xu Kuohai]

From: Xu Kuohai <xukuohai@xxxxxxxxxx>

Arena percpu requires kernel and JIT support for the percpu pseudo
ldimm64. Probe it at load time and fail objects carrying arena percpu
data with -EOPNOTSUPP when it is missing.

Signed-off-by: Xu Kuohai <xukuohai@xxxxxxxxxx>
---
 tools/lib/bpf/features.c        | 50 +++++++++++++++++++++++++++++++++
 tools/lib/bpf/libbpf.c          |  6 ++++
 tools/lib/bpf/libbpf_internal.h |  2 ++
 3 files changed, 58 insertions(+)

diff --git a/tools/lib/bpf/features.c b/tools/lib/bpf/features.c
index adb5d2e7fdfa..f9c7d1545c1e 100644
--- a/tools/lib/bpf/features.c
+++ b/tools/lib/bpf/features.c
@@ -2,6 +2,7 @@
 /* Copyright (c) 2023 Meta Platforms, Inc. and affiliates. */
 #include <linux/kernel.h>
 #include <linux/filter.h>
+#include <sys/mman.h>
 #include "bpf.h"
 #include "libbpf.h"
 #include "libbpf_common.h"
@@ -728,6 +729,52 @@ static int probe_kern_percpu_data(int token_fd)
 	return probe_fd(ret);
 }
 
+static int probe_kern_arena_percpu_data(int token_fd)
+{
+	int possible_cpus;
+	size_t page_sz = sysconf(_SC_PAGE_SIZE);
+	bool *mask = NULL;
+	struct bpf_insn insns[] = {
+		BPF_LD_IMM64_RAW_FULL(BPF_REG_0, BPF_PSEUDO_ARENA_PERCPU, 0, 0, 0, 0),
+		BPF_EXIT_INSN(),
+	};
+	LIBBPF_OPTS(bpf_map_create_opts, map_opts,
+		.token_fd = token_fd,
+		.map_flags = BPF_F_MMAPABLE | (token_fd ? BPF_F_TOKEN_FD : 0),
+		.arena_percpu_chunk_sz = page_sz,
+	);
+	LIBBPF_OPTS(bpf_prog_load_opts, prog_opts,
+		.token_fd = token_fd,
+		.prog_flags = token_fd ? BPF_F_TOKEN_FD : 0,
+	);
+	void *mmaped;
+	int ret, map_fd, insn_cnt = ARRAY_SIZE(insns);
+
+	ret = parse_cpu_mask_file("/sys/devices/system/cpu/possible", &mask, &possible_cpus);
+	if (ret < 0 || possible_cpus <= 0) {
+		free(mask);
+		return -EINVAL;
+	}
+	free(mask);
+
+	map_fd = bpf_map_create(BPF_MAP_TYPE_ARENA, "arena_percpu", 0, 0, possible_cpus, &map_opts);
+	if (map_fd < 0)
+		return 0;
+
+	mmaped = mmap(NULL, possible_cpus * page_sz, PROT_READ | PROT_WRITE, MAP_SHARED, map_fd, 0);
+	if (mmaped == MAP_FAILED) {
+		close(map_fd);
+		return 0;
+	}
+
+	insns[0].imm = map_fd;
+	ret = bpf_prog_load(BPF_PROG_TYPE_SOCKET_FILTER, NULL, "GPL", insns, insn_cnt, &prog_opts);
+	munmap(mmaped, possible_cpus * page_sz);
+	close(map_fd);
+
+	return probe_fd(ret);
+}
+
 typedef int (*feature_probe_fn)(int /* token_fd */);
 
 static struct kern_feature_cache feature_cache;
@@ -824,6 +871,9 @@ static struct kern_feature_desc {
 	[FEAT_EXCL_MAP_FD_ARRAY_CNT] = {
 		"exclusive map bound through fd_array_cnt", probe_kern_excl_map_fd_array_cnt,
 	},
+	[FEAT_ARENA_PERCPU_DATA] = {
+		"kernel supports arena percpu data", probe_kern_arena_percpu_data,
+	},
 };
 
 bool feat_supported(struct kern_feature_cache *cache, enum kern_feature_id feat_id)
diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 8634778e8ba5..be2ddaf96631 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -8288,6 +8288,12 @@ static int bpf_object__relocate(struct bpf_object *obj, const char *targ_btf_pat
 			return -EOPNOTSUPP;
 		}
 
+		if (obj->arena_percpu.present && !kernel_supports(obj, FEAT_ARENA_PERCPU_DATA)) {
+			pr_warn("map '%s': kernel doesn't support %s variables\n",
+				arena_map->name, ARENA_PERCPU_SEC);
+			return -EOPNOTSUPP;
+		}
+
 		if (data_sz + percpu_sz > mmap_sz) {
 			pr_warn("map '%s': declared ARENA map size (%zu) is too small to hold "
 				"global %s of size %zu plus the percpu data size %zu\n",
diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index e90b5336bac0..2aaf681f8cb8 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -408,6 +408,8 @@ enum kern_feature_id {
 	FEAT_FD_ARRAY_CNT,
 	/* Kernel checks an exclusive map bound through fd_array_cnt against the final digest */
 	FEAT_EXCL_MAP_FD_ARRAY_CNT,
+	/* Kernel supports arena percpu data */
+	FEAT_ARENA_PERCPU_DATA,
 	__FEAT_CNT,
 };
 
-- 
2.47.3