Merge branch 'bpf-type-format'

Martin KaFai Lau says:

====================
This patch introduces BPF Type Format (BTF).

BTF (BPF Type Format) is the meta data format which describes
the data types of BPF program/map.  Hence, it basically focus
on the C programming language which the modern BPF is primary
using.  The first use case is to provide a generic pretty print
capability for a BPF map.

A modified pahole that can convert dwarf to BTF is here:

  https://github.com/iamkafai/pahole/tree/btf

Please see individual patch for details.

v5:
- Remove BTF_KIND_FLOAT and BTF_KIND_FUNC which are not
  currently used.  They can be added in the future.
  Some bpf_df_xxx() are removed together.
- Add comment in patch 7 to clarify that the new bpffs_map_fops
  should not be extended further.

v4:
- Fix warning (remove unneeded semicolon)
- Remove a redundant variable (nr_bytes) from btf_int_check_meta() in
  patch 1.  Caught by W=1.

v3:
- Rebase to bpf-next
- Fix sparse warning (by adding static)
- Add BTF header logging: btf_verifier_log_hdr()
- Fix the alignment test on btf->type_off
- Add tests for the BTF header
- Lower the max BTF size to 16MB.  It should be enough
  for some time.  We could raise it later if it would
  be needed.

v2:
- Use kvfree where needed in patch 1 and 2
- Also consider BTF_INT_OFFSET() in the btf_int_check_meta()
  in patch 1
- Fix an incorrect goto target in map_create() during
  the btf-error-path in patch 7
- re-org some local vars to keep the rev xmas tree in btf.c
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 50 insertions, 1 deletions

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 4ca46df19c9a..fe23dc5a3ec4 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -11,6 +11,7 @@
  */
 #include <linux/bpf.h>
 #include <linux/bpf_trace.h>
+#include <linux/btf.h>
 #include <linux/syscalls.h>
 #include <linux/slab.h>
 #include <linux/sched/signal.h>
@@ -26,6 +27,7 @@
 #include <linux/cred.h>
 #include <linux/timekeeping.h>
 #include <linux/ctype.h>
+#include <linux/btf.h>
 
 #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \
 			   (map)->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY || \
@@ -250,6 +252,7 @@ static void bpf_map_free_deferred(struct work_struct *work)
 
 	bpf_map_uncharge_memlock(map);
 	security_bpf_map_free(map);
+	btf_put(map->btf);
 	/* implementation dependent freeing */
 	map->ops->map_free(map);
 }
@@ -415,7 +418,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src)
 	return 0;
 }
 
-#define BPF_MAP_CREATE_LAST_FIELD map_ifindex
+#define BPF_MAP_CREATE_LAST_FIELD btf_value_id
 /* called via syscall */
 static int map_create(union bpf_attr *attr)
 {
@@ -449,6 +452,33 @@ static int map_create(union bpf_attr *attr)
 	atomic_set(&map->refcnt, 1);
 	atomic_set(&map->usercnt, 1);
 
+	if (bpf_map_support_seq_show(map) &&
+	    (attr->btf_key_id || attr->btf_value_id)) {
+		struct btf *btf;
+
+		if (!attr->btf_key_id || !attr->btf_value_id) {
+			err = -EINVAL;
+			goto free_map_nouncharge;
+		}
+
+		btf = btf_get_by_fd(attr->btf_fd);
+		if (IS_ERR(btf)) {
+			err = PTR_ERR(btf);
+			goto free_map_nouncharge;
+		}
+
+		err = map->ops->map_check_btf(map, btf, attr->btf_key_id,
+					      attr->btf_value_id);
+		if (err) {
+			btf_put(btf);
+			goto free_map_nouncharge;
+		}
+
+		map->btf = btf;
+		map->btf_key_id = attr->btf_key_id;
+		map->btf_value_id = attr->btf_value_id;
+	}
+
 	err = security_bpf_map_alloc(map);
 	if (err)
 		goto free_map_nouncharge;
@@ -481,6 +511,7 @@ free_map:
 free_map_sec:
 	security_bpf_map_free(map);
 free_map_nouncharge:
+	btf_put(map->btf);
 	map->ops->map_free(map);
 	return err;
 }
@@ -2016,6 +2047,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	else if (f.file->f_op == &bpf_map_fops)
 		err = bpf_map_get_info_by_fd(f.file->private_data, attr,
 					     uattr);
+	else if (f.file->f_op == &btf_fops)
+		err = btf_get_info_by_fd(f.file->private_data, attr, uattr);
 	else
 		err = -EINVAL;
 
@@ -2023,6 +2056,19 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr,
 	return err;
 }
 
+#define BPF_BTF_LOAD_LAST_FIELD btf_log_level
+
+static int bpf_btf_load(const union bpf_attr *attr)
+{
+	if (CHECK_ATTR(BPF_BTF_LOAD))
+		return -EINVAL;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	return btf_new_fd(attr);
+}
+
 SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size)
 {
 	union bpf_attr attr = {};
@@ -2103,6 +2149,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz
 	case BPF_RAW_TRACEPOINT_OPEN:
 		err = bpf_raw_tracepoint_open(&attr);
 		break;
+	case BPF_BTF_LOAD:
+		err = bpf_btf_load(&attr);
+		break;
 	default:
 		err = -EINVAL;
 		break;