summaryrefslogtreecommitdiffstats
path: root/kernel
diff options
context:
space:
mode:
authorAndrii Nakryiko <andriin@fb.com>2019-08-12 11:39:47 -0700
committerDaniel Borkmann <daniel@iogearbox.net>2019-08-13 16:14:15 +0200
commit341dfcf8d78eaa3a2dc96dea06f0392eb2978364 (patch)
tree5a4f45f7703c707a91712224603f64744cd1a99c /kernel
parenta664a834579ae8a6166ac9e5a3232976cab2c24d (diff)
downloadlinux-341dfcf8d78eaa3a2dc96dea06f0392eb2978364.tar.bz2
btf: expose BTF info through sysfs
Make .BTF section allocated and expose its contents through sysfs. /sys/kernel/btf directory is created to contain all the BTFs present inside kernel. Currently there is only kernel's main BTF, represented as /sys/kernel/btf/kernel file. Once kernel modules' BTFs are supported, each module will expose its BTF as /sys/kernel/btf/<module-name> file. Current approach relies on a few pieces coming together: 1. pahole is used to take almost final vmlinux image (modulo .BTF and kallsyms) and generate .BTF section by converting DWARF info into BTF. This section is not allocated and not mapped to any segment, though, so is not yet accessible from inside kernel at runtime. 2. objcopy dumps .BTF contents into binary file and subsequently convert binary file into linkable object file with automatically generated symbols _binary__btf_kernel_bin_start and _binary__btf_kernel_bin_end, pointing to start and end, respectively, of BTF raw data. 3. final vmlinux image is generated by linking this object file (and kallsyms, if necessary). sysfs_btf.c then creates /sys/kernel/btf/kernel file and exposes embedded BTF contents through it. This allows, e.g., libbpf and bpftool access BTF info at well-known location, without resorting to searching for vmlinux image on disk (location of which is not standardized and vmlinux image might not be even available in some scenarios, e.g., inside qemu during testing). Alternative approach using .incbin assembler directive to embed BTF contents directly was attempted but didn't work, because sysfs_proc.o is not re-compiled during link-vmlinux.sh stage. This is required, though, to update embedded BTF data (initially empty data is embedded, then pahole generates BTF info and we need to regenerate sysfs_btf.o with updated contents, but it's too late at that point). If BTF couldn't be generated due to missing or too old pahole, sysfs_btf.c handles that gracefully by detecting that _binary__btf_kernel_bin_start (weak symbol) is 0 and not creating /sys/kernel/btf at all. v2->v3: - added Documentation/ABI/testing/sysfs-kernel-btf (Greg K-H); - created proper kobject (btf_kobj) for btf directory (Greg K-H); - undo v2 change of reusing vmlinux, as it causes extra kallsyms pass due to initially missing __binary__btf_kernel_bin_{start/end} symbols; v1->v2: - allow kallsyms stage to re-use vmlinux generated by gen_btf(); Reviewed-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org> Signed-off-by: Andrii Nakryiko <andriin@fb.com> Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>
Diffstat (limited to 'kernel')
-rw-r--r--kernel/bpf/Makefile3
-rw-r--r--kernel/bpf/sysfs_btf.c51
2 files changed, 54 insertions, 0 deletions
diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile
index 29d781061cd5..e1d9adb212f9 100644
--- a/kernel/bpf/Makefile
+++ b/kernel/bpf/Makefile
@@ -22,3 +22,6 @@ obj-$(CONFIG_CGROUP_BPF) += cgroup.o
ifeq ($(CONFIG_INET),y)
obj-$(CONFIG_BPF_SYSCALL) += reuseport_array.o
endif
+ifeq ($(CONFIG_SYSFS),y)
+obj-$(CONFIG_DEBUG_INFO_BTF) += sysfs_btf.o
+endif
diff --git a/kernel/bpf/sysfs_btf.c b/kernel/bpf/sysfs_btf.c
new file mode 100644
index 000000000000..092e63b9758b
--- /dev/null
+++ b/kernel/bpf/sysfs_btf.c
@@ -0,0 +1,51 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Provide kernel BTF information for introspection and use by eBPF tools.
+ */
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/kobject.h>
+#include <linux/init.h>
+#include <linux/sysfs.h>
+
+/* See scripts/link-vmlinux.sh, gen_btf() func for details */
+extern char __weak _binary__btf_kernel_bin_start[];
+extern char __weak _binary__btf_kernel_bin_end[];
+
+static ssize_t
+btf_kernel_read(struct file *file, struct kobject *kobj,
+ struct bin_attribute *bin_attr,
+ char *buf, loff_t off, size_t len)
+{
+ memcpy(buf, _binary__btf_kernel_bin_start + off, len);
+ return len;
+}
+
+static struct bin_attribute bin_attr_btf_kernel __ro_after_init = {
+ .attr = { .name = "kernel", .mode = 0444, },
+ .read = btf_kernel_read,
+};
+
+static struct kobject *btf_kobj;
+
+static int __init btf_kernel_init(void)
+{
+ int err;
+
+ if (!_binary__btf_kernel_bin_start)
+ return 0;
+
+ btf_kobj = kobject_create_and_add("btf", kernel_kobj);
+ if (IS_ERR(btf_kobj)) {
+ err = PTR_ERR(btf_kobj);
+ btf_kobj = NULL;
+ return err;
+ }
+
+ bin_attr_btf_kernel.size = _binary__btf_kernel_bin_end -
+ _binary__btf_kernel_bin_start;
+
+ return sysfs_create_bin_file(btf_kobj, &bin_attr_btf_kernel);
+}
+
+subsys_initcall(btf_kernel_init);