[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]
Message-Id: <20250502-vmlinux-mmap-v2-3-95c271434519@isovalent.com>
Date: Fri, 02 May 2025 11:20:07 +0100
From: Lorenz Bauer <lmb@...valent.com>
To: Arnd Bergmann <arnd@...db.de>, Alexei Starovoitov <ast@...nel.org>,
Daniel Borkmann <daniel@...earbox.net>, Andrii Nakryiko <andrii@...nel.org>,
Martin KaFai Lau <martin.lau@...ux.dev>,
Eduard Zingerman <eddyz87@...il.com>, Song Liu <song@...nel.org>,
Yonghong Song <yonghong.song@...ux.dev>,
John Fastabend <john.fastabend@...il.com>, KP Singh <kpsingh@...nel.org>,
Stanislav Fomichev <sdf@...ichev.me>, Hao Luo <haoluo@...gle.com>,
Jiri Olsa <jolsa@...nel.org>, Mykola Lysenko <mykolal@...com>,
Shuah Khan <shuah@...nel.org>
Cc: linux-arch@...r.kernel.org, linux-kernel@...r.kernel.org,
bpf@...r.kernel.org, linux-kselftest@...r.kernel.org,
Lorenz Bauer <lmb@...valent.com>
Subject: [PATCH bpf-next v2 3/3] libbpf: Use mmap to parse vmlinux BTF from
sysfs
Teach libbpf to use mmap when parsing vmlinux BTF from /sys. We don't
apply this to fall-back paths on the regular file system because there
is no way to ensure that modifications underlying the MAP_PRIVATE
mapping are not visible to the process.
Signed-off-by: Lorenz Bauer <lmb@...valent.com>
---
tools/lib/bpf/btf.c | 82 ++++++++++++++++++++++++++++++++++++++++++++++-------
1 file changed, 71 insertions(+), 11 deletions(-)
diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c
index b7513d4cce55b263310c341bc254df6364e829d9..7fec41a2dc617c9d388f9ab10d9850ef759c74d9 100644
--- a/tools/lib/bpf/btf.c
+++ b/tools/lib/bpf/btf.c
@@ -12,6 +12,7 @@
#include <sys/utsname.h>
#include <sys/param.h>
#include <sys/stat.h>
+#include <sys/mman.h>
#include <linux/kernel.h>
#include <linux/err.h>
#include <linux/btf.h>
@@ -120,6 +121,9 @@ struct btf {
/* whether base_btf should be freed in btf_free for this instance */
bool owns_base;
+ /* whether raw_data is a (read-only) mmap */
+ bool raw_data_is_mmap;
+
/* BTF object FD, if loaded into kernel */
int fd;
@@ -951,6 +955,17 @@ static bool btf_is_modifiable(const struct btf *btf)
return (void *)btf->hdr != btf->raw_data;
}
+static void btf_free_raw_data(struct btf *btf)
+{
+ if (btf->raw_data_is_mmap) {
+ munmap(btf->raw_data, btf->raw_size);
+ btf->raw_data_is_mmap = false;
+ } else {
+ free(btf->raw_data);
+ }
+ btf->raw_data = NULL;
+}
+
void btf__free(struct btf *btf)
{
if (IS_ERR_OR_NULL(btf))
@@ -970,7 +985,7 @@ void btf__free(struct btf *btf)
free(btf->types_data);
strset__free(btf->strs_set);
}
- free(btf->raw_data);
+ btf_free_raw_data(btf);
free(btf->raw_data_swapped);
free(btf->type_offs);
if (btf->owns_base)
@@ -1030,7 +1045,7 @@ struct btf *btf__new_empty_split(struct btf *base_btf)
return libbpf_ptr(btf_new_empty(base_btf));
}
-static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
+static struct btf *btf_new_no_copy(void *data, __u32 size, struct btf *base_btf)
{
struct btf *btf;
int err;
@@ -1050,12 +1065,7 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
btf->start_str_off = base_btf->hdr->str_len;
}
- btf->raw_data = malloc(size);
- if (!btf->raw_data) {
- err = -ENOMEM;
- goto done;
- }
- memcpy(btf->raw_data, data, size);
+ btf->raw_data = data;
btf->raw_size = size;
btf->hdr = btf->raw_data;
@@ -1081,6 +1091,24 @@ static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
return btf;
}
+static struct btf *btf_new(const void *data, __u32 size, struct btf *base_btf)
+{
+ struct btf *btf;
+ void *raw_data;
+
+ raw_data = malloc(size);
+ if (!raw_data)
+ return ERR_PTR(-ENOMEM);
+
+ memcpy(raw_data, data, size);
+
+ btf = btf_new_no_copy(raw_data, size, base_btf);
+ if (IS_ERR(btf))
+ free(raw_data);
+
+ return btf;
+}
+
struct btf *btf__new(const void *data, __u32 size)
{
return libbpf_ptr(btf_new(data, size, NULL));
@@ -1659,8 +1687,7 @@ struct btf *btf__load_from_kernel_by_id(__u32 id)
static void btf_invalidate_raw_data(struct btf *btf)
{
if (btf->raw_data) {
- free(btf->raw_data);
- btf->raw_data = NULL;
+ btf_free_raw_data(btf);
}
if (btf->raw_data_swapped) {
free(btf->raw_data_swapped);
@@ -5290,7 +5317,40 @@ struct btf *btf__load_vmlinux_btf(void)
pr_warn("kernel BTF is missing at '%s', was CONFIG_DEBUG_INFO_BTF enabled?\n",
sysfs_btf_path);
} else {
- btf = btf__parse(sysfs_btf_path, NULL);
+ struct stat st;
+ void *data = NULL;
+ int fd;
+
+ fd = open(sysfs_btf_path, O_RDONLY);
+ if (fd < 0) {
+ err = -errno;
+ pr_warn("failed to open kernel BTF at '%s': %s\n",
+ sysfs_btf_path, errstr(err));
+ return libbpf_err_ptr(err);
+ }
+
+ if (fstat(fd, &st) < 0) {
+ err = -errno;
+ pr_warn("failed to stat kernel BTF at '%s': %s\n",
+ sysfs_btf_path, errstr(err));
+ close(fd);
+ return libbpf_err_ptr(err);
+ }
+
+ data = mmap(NULL, st.st_size, PROT_READ, MAP_PRIVATE, fd, 0);
+ close(fd);
+
+ if (data != MAP_FAILED) {
+ btf = libbpf_ptr(btf_new_no_copy(data, st.st_size, NULL));
+ if (!btf)
+ munmap(data, st.st_size);
+ else
+ btf->raw_data_is_mmap = true;
+ } else {
+ pr_debug("reading kernel BTF via file-based fallback\n");
+ btf = btf__parse(sysfs_btf_path, NULL);
+ }
+
if (!btf) {
err = -errno;
pr_warn("failed to read kernel BTF from '%s': %s\n",
--
2.49.0
Powered by blists - more mailing lists