bpf: Introduce pseudo_btf_id

Pseudo_btf_id is a type of ld_imm insn that associates a btf_id to a
ksym so that further dereferences on the ksym can use the BTF info
to validate accesses. Internally, when seeing a pseudo_btf_id ld insn,
the verifier reads the btf_id stored in the insn[0]'s imm field and
marks the dst_reg as PTR_TO_BTF_ID. The btf_id points to a VAR_KIND,
which is encoded in btf_vminux by pahole. If the VAR is not of a struct
type, the dst reg will be marked as PTR_TO_MEM instead of PTR_TO_BTF_ID
and the mem_size is resolved to the size of the VAR's type.

>From the VAR btf_id, the verifier can also read the address of the
ksym's corresponding kernel var from kallsyms and use that to fill
dst_reg.

Therefore, the proper functionality of pseudo_btf_id depends on (1)
kallsyms and (2) the encoding of kernel global VARs in pahole, which
should be available since pahole v1.18.

Signed-off-by: Hao Luo <haoluo@google.com>
Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Acked-by: Andrii Nakryiko <andriin@fb.com>
Link: https://lore.kernel.org/bpf/20200929235049.2533242-2-haoluo@google.com

3 files changed, 49 insertions, 9 deletions

diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 363b4f1c562a..e83ef6f6bf43 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -308,6 +308,13 @@ struct bpf_insn_aux_data {
 			u32 map_index;		/* index into used_maps[] */
 			u32 map_off;		/* offset from value base address */
 		};
+		struct {
+			enum bpf_reg_type reg_type;	/* type of pseudo_btf_id */
+			union {
+				u32 btf_id;	/* btf_id for struct typed var */
+				u32 mem_size;	/* mem_size for non-struct typed var */
+			};
+		} btf_var;
 	};
 	u64 map_key_state; /* constant (32 bit) key tracking for maps */
 	int ctx_field_size; /* the ctx field size for load insn, maybe 0 */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 024e16ff7dcc..af1244180588 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -145,6 +145,21 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 	return BTF_INFO_KIND(t->info) == BTF_KIND_FUNC_PROTO;
 }
 
+static inline bool btf_type_is_var(const struct btf_type *t)
+{
+	return BTF_INFO_KIND(t->info) == BTF_KIND_VAR;
+}
+
+/* union is only a special case of struct:
+ * all its offsetof(member) == 0
+ */
+static inline bool btf_type_is_struct(const struct btf_type *t)
+{
+	u8 kind = BTF_INFO_KIND(t->info);
+
+	return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION;
+}
+
 static inline u16 btf_type_vlen(const struct btf_type *t)
 {
 	return BTF_INFO_VLEN(t->info);
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 4f556cfcbfbe..2aa156af24d6 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -356,18 +356,36 @@ enum bpf_link_type {
 #define BPF_F_SLEEPABLE		(1U << 4)
 
 /* When BPF ldimm64's insn[0].src_reg != 0 then this can have
- * two extensions:
- *
- * insn[0].src_reg:  BPF_PSEUDO_MAP_FD   BPF_PSEUDO_MAP_VALUE
- * insn[0].imm:      map fd              map fd
- * insn[1].imm:      0                   offset into value
- * insn[0].off:      0                   0
- * insn[1].off:      0                   0
- * ldimm64 rewrite:  address of map      address of map[0]+offset
- * verifier type:    CONST_PTR_TO_MAP    PTR_TO_MAP_VALUE
+ * the following extensions:
+ *
+ * insn[0].src_reg:  BPF_PSEUDO_MAP_FD
+ * insn[0].imm:      map fd
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map
+ * verifier type:    CONST_PTR_TO_MAP
  */
 #define BPF_PSEUDO_MAP_FD	1
+/* insn[0].src_reg:  BPF_PSEUDO_MAP_VALUE
+ * insn[0].imm:      map fd
+ * insn[1].imm:      offset into value
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of map[0]+offset
+ * verifier type:    PTR_TO_MAP_VALUE
+ */
 #define BPF_PSEUDO_MAP_VALUE	2
+/* insn[0].src_reg:  BPF_PSEUDO_BTF_ID
+ * insn[0].imm:      kernel btd id of VAR
+ * insn[1].imm:      0
+ * insn[0].off:      0
+ * insn[1].off:      0
+ * ldimm64 rewrite:  address of the kernel variable
+ * verifier type:    PTR_TO_BTF_ID or PTR_TO_MEM, depending on whether the var
+ *                   is struct/union.
+ */
+#define BPF_PSEUDO_BTF_ID	3
 
 /* when bpf_call->src_reg == BPF_PSEUDO_CALL, bpf_call->imm == pc-relative
  * offset to another bpf function