[RFC PATCH 2/4] bpf tools: Collect BPF_MAP_TYPE_PERF_EVENT_ARRAY map definitions from 'maps' section

[Kaixu Xia]

In order to make use of the new ability of eBPF programs to access
hardware PMU counter, we need to get the event & map match. So we
introduce the struct perf_event_map_def that contains struct bpf_map
_def and struct perf_event_attr. We can get the necessary info from
'maps' section and store the pointers to struct perf_event in
BPF_MAP_TYPE_PERF_EVENT_ARRAY maps.

Signed-off-by: Kaixu Xia <xiakaixu@xxxxxxxxxx>
---
 tools/lib/bpf/libbpf.c | 76 ++++++++++++++++++++++++++++++++++++++++----------
 tools/lib/bpf/libbpf.h | 13 +++++++++
 2 files changed, 74 insertions(+), 15 deletions(-)

diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c
index 1ff6a19..83d79c4 100644
--- a/tools/lib/bpf/libbpf.c
+++ b/tools/lib/bpf/libbpf.c
@@ -570,7 +570,7 @@ bpf_object__find_prog_by_idx(struct bpf_object *obj, int idx)
 
 static int
 bpf_program__collect_reloc(struct bpf_program *prog,
-			   size_t nr_maps, GElf_Shdr *shdr,
+			   size_t max_maps, GElf_Shdr *shdr,
 			   Elf_Data *data, Elf_Data *symbols)
 {
 	int i, nrels;
@@ -616,9 +616,9 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 		}
 
 		map_idx = sym.st_value / sizeof(struct bpf_map_def);
-		if (map_idx >= nr_maps) {
+		if (map_idx >= max_maps) {
 			pr_warning("bpf relocation: map_idx %d large than %d\n",
-				   (int)map_idx, (int)nr_maps - 1);
+				   (int)map_idx, (int)max_maps - 1);
 			return -EINVAL;
 		}
 
@@ -629,11 +629,42 @@ bpf_program__collect_reloc(struct bpf_program *prog,
 }
 
 static int
+bpf_object__collect_perf_event_maps(void *data, int **pfd)
+{
+	int i, event_fd;
+	int maps_fd = **pfd;
+	int attr_length = ATTR_LENGTH;
+	int nr_cpus = sysconf(_SC_NPROCESSORS_CONF);
+	struct perf_event_attr *attr;
+
+	attr = (struct perf_event_attr *)(data + sizeof(struct bpf_map_def));
+	if (attr->type != PERF_TYPE_RAW &&
+	    attr->type != PERF_TYPE_HARDWARE)
+		return -EINVAL;
+	attr->disabled = 1;
+
+	do {
+		(*pfd)++;
+		**pfd = -1;
+	} while (--attr_length);
+
+	for (i = 0; i < nr_cpus; i++) {
+		event_fd = perf_event_open(attr, -1/*pid*/, i/*cpu*/, -1/*group_fd*/, 0);
+		if (event_fd < 0) {
+			pr_warning("event syscall failed\n");
+			return -EINVAL;
+		}
+		bpf_update_elem(maps_fd, &i, &event_fd, BPF_ANY);
+	}
+	return 0;
+}
+
+static int
 bpf_object__create_maps(struct bpf_object *obj)
 {
 	unsigned int i;
-	size_t nr_maps;
-	int *pfd;
+	size_t nr_maps, j;
+	int *pfd, err;
 
 	nr_maps = obj->maps_buf_sz / sizeof(struct bpf_map_def);
 	if (!obj->maps_buf || !nr_maps) {
@@ -664,24 +695,37 @@ bpf_object__create_maps(struct bpf_object *obj)
 				      def.value_size,
 				      def.max_entries);
 		if (*pfd < 0) {
-			size_t j;
-			int err = *pfd;
-
+			err = *pfd;
 			pr_warning("failed to create map: %s\n",
 				   strerror(errno));
-			for (j = 0; j < i; j++)
-				zclose(obj->map_fds[j]);
-			obj->nr_map_fds = 0;
-			zfree(&obj->map_fds);
-			return err;
+			goto out_close;
 		}
 		pr_debug("create map: fd=%d\n", *pfd);
+
+		if (def.type == BPF_MAP_TYPE_PERF_EVENT_ARRAY) {
+			void *data = obj->maps_buf + i * sizeof(struct bpf_map_def);
+
+			err = bpf_object__collect_perf_event_maps(data, &pfd);
+			if (err < 0) {
+				pr_warning("failed to collect perf_event maps: %s\n",
+					    strerror(errno));
+				goto out_close;
+			}
+			i += ATTR_LENGTH;
+		}
 		pfd++;
 	}
 
 	zfree(&obj->maps_buf);
 	obj->maps_buf_sz = 0;
 	return 0;
+
+out_close:
+	for (j = 0; j < i; j++)
+		zclose(obj->map_fds[j]);
+	obj->nr_map_fds = 0;
+	zfree(&obj->map_fds);
+	return err;
 }
 
 static int
@@ -705,6 +749,8 @@ bpf_program__relocate(struct bpf_program *prog, int *map_fds)
 			return -ERANGE;
 		}
 		insns[insn_idx].src_reg = BPF_PSEUDO_MAP_FD;
+		if (map_fds[map_idx] == -1)
+			return -EINVAL;
 		insns[insn_idx].imm = map_fds[map_idx];
 	}
 
@@ -748,7 +794,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 		Elf_Data *data = obj->efile.reloc[i].data;
 		int idx = shdr->sh_info;
 		struct bpf_program *prog;
-		size_t nr_maps = obj->maps_buf_sz /
+		size_t max_maps = obj->maps_buf_sz /
 				 sizeof(struct bpf_map_def);
 
 		if (shdr->sh_type != SHT_REL) {
@@ -763,7 +809,7 @@ static int bpf_object__collect_reloc(struct bpf_object *obj)
 			return -ENOENT;
 		}
 
-		err = bpf_program__collect_reloc(prog, nr_maps,
+		err = bpf_program__collect_reloc(prog, max_maps,
 						 shdr, data,
 						 obj->efile.symbols);
 		if (err)
diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h
index 9fa7b09..8361dd5 100644
--- a/tools/lib/bpf/libbpf.h
+++ b/tools/lib/bpf/libbpf.h
@@ -10,6 +10,7 @@
 
 #include <stdio.h>
 #include <stdbool.h>
+#include <linux/perf_event.h>
 
 /*
  * In include/linux/compiler-gcc.h, __printf is defined. However
@@ -100,4 +101,16 @@ struct bpf_map_def {
 	unsigned int max_entries;
 };
 
+#define ATTR_LENGTH ((sizeof(struct perf_event_attr) + \
+		     sizeof(struct bpf_map_def) - 1) /\
+		     sizeof(struct bpf_map_def))
+
+struct perf_event_map_def {
+	struct bpf_map_def map_def;
+	union {
+		struct perf_event_attr attr;
+		struct bpf_map_def align[ATTR_LENGTH];
+	};
+};
+
 #endif
-- 
1.8.3.4

--
To unsubscribe from this list: send the line "unsubscribe linux-kernel" in
the body of a message to majordomo@xxxxxxxxxxxxxxx
More majordomo info at  http://vger.kernel.org/majordomo-info.html
Please read the FAQ at  http://www.tux.org/lkml/