Merge git://git.kernel.org/pub/scm/linux/kernel/git/bpf/bpf-next

Daniel Borkmann says:

====================
The following pull-request contains BPF updates for your *net-next* tree.

There is a small merge conflict in libbpf (Cc Andrii so he's in the loop
as well):

        for (i = 1; i <= btf__get_nr_types(btf); i++) {
                t = (struct btf_type *)btf__type_by_id(btf, i);

                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
  <<<<<<< HEAD
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t+1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && kind == BTF_KIND_DATASEC) {
  =======
                        t->size = sizeof(int);
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 32);
                } else if (!has_datasec && btf_is_datasec(t)) {
  >>>>>>> 72ef80b5ee131e96172f19e74b4f98fa3404efe8
                        /* replace DATASEC with STRUCT */

Conflict is between the two commits 1d4126c4e119 ("libbpf: sanitize VAR to
conservative 1-byte INT") and b03bc6853c0e ("libbpf: convert libbpf code to
use new btf helpers"), so we need to pick the sanitation fixup as well as
use the new btf_is_datasec() helper and the whitespace cleanup. Looks like
the following:

  [...]
                if (!has_datasec && btf_is_var(t)) {
                        /* replace VAR with INT */
                        t->info = BTF_INFO_ENC(BTF_KIND_INT, 0, 0);
                        /*
                         * using size = 1 is the safest choice, 4 will be too
                         * big and cause kernel BTF validation failure if
                         * original variable took less than 4 bytes
                         */
                        t->size = 1;
                        *(int *)(t + 1) = BTF_INT_ENC(0, 0, 8);
                } else if (!has_datasec && btf_is_datasec(t)) {
                        /* replace DATASEC with STRUCT */
  [...]

The main changes are:

1) Addition of core parts of compile once - run everywhere (co-re) effort,
   that is, relocation of fields offsets in libbpf as well as exposure of
   kernel's own BTF via sysfs and loading through libbpf, from Andrii.

   More info on co-re: http://vger.kernel.org/bpfconf2019.html#session-2
   and http://vger.kernel.org/lpc-bpf2018.html#session-2

2) Enable passing input flags to the BPF flow dissector to customize parsing
   and allowing it to stop early similar to the C based one, from Stanislav.

3) Add a BPF helper function that allows generating SYN cookies from XDP and
   tc BPF, from Petar.

4) Add devmap hash-based map type for more flexibility in device lookup for
   redirects, from Toke.

5) Improvements to XDP forwarding sample code now utilizing recently enabled
   devmap lookups, from Jesper.

6) Add support for reporting the effective cgroup progs in bpftool, from Jakub
   and Takshak.

7) Fix reading kernel config from bpftool via /proc/config.gz, from Peter.

8) Fix AF_XDP umem pages mapping for 32 bit architectures, from Ivan.

9) Follow-up to add two more BPF loop tests for the selftest suite, from Alexei.

10) Add perf event output helper also for other skb-based program types, from Allan.

11) Fix a co-re related compilation error in selftests, from Yonghong.
====================

Signed-off-by: Jakub Kicinski <jakub.kicinski@netronome.com>

1 files changed, 105 insertions, 0 deletions

diff --git a/tools/lib/bpf/libbpf_internal.h b/tools/lib/bpf/libbpf_internal.h
index 2ac29bd36226..2e83a34f8c79 100644
--- a/tools/lib/bpf/libbpf_internal.h
+++ b/tools/lib/bpf/libbpf_internal.h
@@ -29,6 +29,10 @@
 #ifndef max
 # define max(x, y) ((x) < (y) ? (y) : (x))
 #endif
+#ifndef offsetofend
+# define offsetofend(TYPE, FIELD) \
+	(offsetof(TYPE, FIELD) + sizeof(((TYPE *)0)->FIELD))
+#endif
 
 extern void libbpf_print(enum libbpf_print_level level,
 			 const char *format, ...)
@@ -46,4 +50,105 @@ do {				\
 int libbpf__load_raw_btf(const char *raw_types, size_t types_len,
 			 const char *str_sec, size_t str_len);
 
+struct btf_ext_info {
+	/*
+	 * info points to the individual info section (e.g. func_info and
+	 * line_info) from the .BTF.ext. It does not include the __u32 rec_size.
+	 */
+	void *info;
+	__u32 rec_size;
+	__u32 len;
+};
+
+#define for_each_btf_ext_sec(seg, sec)					\
+	for (sec = (seg)->info;						\
+	     (void *)sec < (seg)->info + (seg)->len;			\
+	     sec = (void *)sec + sizeof(struct btf_ext_info_sec) +	\
+		   (seg)->rec_size * sec->num_info)
+
+#define for_each_btf_ext_rec(seg, sec, i, rec)				\
+	for (i = 0, rec = (void *)&(sec)->data;				\
+	     i < (sec)->num_info;					\
+	     i++, rec = (void *)rec + (seg)->rec_size)
+
+struct btf_ext {
+	union {
+		struct btf_ext_header *hdr;
+		void *data;
+	};
+	struct btf_ext_info func_info;
+	struct btf_ext_info line_info;
+	struct btf_ext_info offset_reloc_info;
+	__u32 data_size;
+};
+
+struct btf_ext_info_sec {
+	__u32	sec_name_off;
+	__u32	num_info;
+	/* Followed by num_info * record_size number of bytes */
+	__u8	data[0];
+};
+
+/* The minimum bpf_func_info checked by the loader */
+struct bpf_func_info_min {
+	__u32   insn_off;
+	__u32   type_id;
+};
+
+/* The minimum bpf_line_info checked by the loader */
+struct bpf_line_info_min {
+	__u32	insn_off;
+	__u32	file_name_off;
+	__u32	line_off;
+	__u32	line_col;
+};
+
+/* The minimum bpf_offset_reloc checked by the loader
+ *
+ * Offset relocation captures the following data:
+ * - insn_off - instruction offset (in bytes) within a BPF program that needs
+ *   its insn->imm field to be relocated with actual offset;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   offset;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   itself encodes an accessed field using a sequence of field and array
+ *   indicies, separated by colon (:). It's conceptually very close to LLVM's
+ *   getelementptr ([0]) instruction's arguments for identifying offset to 
+ *   a field.
+ *
+ * Example to provide a better feel.
+ *
+ *   struct sample {
+ *       int a;
+ *       struct {
+ *           int b[10];
+ *       };
+ *   };
+ *
+ *   struct sample *s = ...;
+ *   int x = &s->a;     // encoded as "0:0" (a is field #0)
+ *   int y = &s->b[5];  // encoded as "0:1:0:5" (anon struct is field #1, 
+ *                      // b is field #0 inside anon struct, accessing elem #5)
+ *   int z = &s[10]->b; // encoded as "10:1" (ptr is used as an array)
+ *
+ * type_id for all relocs in this example  will capture BTF type id of
+ * `struct sample`.
+ *
+ * Such relocation is emitted when using __builtin_preserve_access_index()
+ * Clang built-in, passing expression that captures field address, e.g.:
+ *
+ * bpf_probe_read(&dst, sizeof(dst),
+ *		  __builtin_preserve_access_index(&src->a.b.c));
+ *
+ * In this case Clang will emit offset relocation recording necessary data to
+ * be able to find offset of embedded `a.b.c` field within `src` struct.
+ *
+ *   [0] https://llvm.org/docs/LangRef.html#getelementptr-instruction
+ */
+struct bpf_offset_reloc {
+	__u32   insn_off;
+	__u32   type_id;
+	__u32   access_str_off;
+};
+
 #endif /* __LIBBPF_LIBBPF_INTERNAL_H */