bpf: Pass a set of bpf_core_relo-s to prog_load command.

struct bpf_core_relo is generated by llvm and processed by libbpf.
It's a de-facto uapi.
With CO-RE in the kernel the struct bpf_core_relo becomes uapi de-jure.
Add an ability to pass a set of 'struct bpf_core_relo' to prog_load command
and let the kernel perform CO-RE relocations.

Note the struct bpf_line_info and struct bpf_func_info have the same
layout when passed from LLVM to libbpf and from libbpf to the kernel
except "insn_off" fields means "byte offset" when LLVM generates it.
Then libbpf converts it to "insn index" to pass to the kernel.
The struct bpf_core_relo's "insn_off" field is always "byte offset".

Signed-off-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Acked-by: Andrii Nakryiko <andrii@kernel.org>
Link: https://lore.kernel.org/bpf/20211201181040.23337-6-alexei.starovoitov@gmail.com

7 files changed, 207 insertions, 56 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index cad0829710be..8bbf08fbab66 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -1732,6 +1732,14 @@ bool bpf_prog_has_kfunc_call(const struct bpf_prog *prog);
 const struct btf_func_model *
 bpf_jit_find_kfunc_model(const struct bpf_prog *prog,
 			 const struct bpf_insn *insn);
+struct bpf_core_ctx {
+	struct bpf_verifier_log *log;
+	const struct btf *btf;
+};
+
+int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
+		   int relo_idx, void *insn);
+
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
 {
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index 9e66b1880020..c26871263f1f 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -1342,8 +1342,10 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
-		__u32		:32;		/* pad */
+		__u32		core_relo_cnt;	/* number of bpf_core_relo */
 		__aligned_u64	fd_array;	/* array of FDs */
+		__aligned_u64	core_relos;
+		__u32		core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -6393,4 +6395,59 @@ enum bpf_core_relo_kind {
 	BPF_CORE_ENUMVAL_VALUE = 11,         /* enum value integer value */
 };
 
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE 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 field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   interpretation depends on specific relocation kind:
+ *     - for field-based relocations, string encodes an accessed field using
+ *       a sequence of field and array indices, separated by colon (:). It's
+ *       conceptually very close to LLVM's getelementptr ([0]) instruction's
+ *       arguments for identifying offset to a field.
+ *     - for type-based relocations, strings is expected to be just "0";
+ *     - for enum value-based relocations, string contains an index of enum
+ *       value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ *   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 field 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_core_relo {
+	__u32 insn_off;
+	__u32 type_id;
+	__u32 access_str_off;
+	enum bpf_core_relo_kind kind;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c
index c79595aad55b..0d070461e2b8 100644
--- a/kernel/bpf/btf.c
+++ b/kernel/bpf/btf.c
@@ -6439,3 +6439,9 @@ size_t bpf_core_essential_name_len(const char *name)
 	}
 	return n;
 }
+
+int bpf_core_apply(struct bpf_core_ctx *ctx, const struct bpf_core_relo *relo,
+		   int relo_idx, void *insn)
+{
+	return -EOPNOTSUPP;
+}
diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index 47089d1d67a4..b3ada4085f85 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2184,7 +2184,7 @@ static bool is_perfmon_prog_type(enum bpf_prog_type prog_type)
 }
 
 /* last field in 'union bpf_attr' used by this command */
-#define	BPF_PROG_LOAD_LAST_FIELD fd_array
+#define	BPF_PROG_LOAD_LAST_FIELD core_relo_rec_size
 
 static int bpf_prog_load(union bpf_attr *attr, bpfptr_t uattr)
 {
diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c
index 6c9c0d9a04a0..6522ffdea487 100644
--- a/kernel/bpf/verifier.c
+++ b/kernel/bpf/verifier.c
@@ -10273,6 +10273,78 @@ err_free:
 	return err;
 }
 
+#define MIN_CORE_RELO_SIZE	sizeof(struct bpf_core_relo)
+#define MAX_CORE_RELO_SIZE	MAX_FUNCINFO_REC_SIZE
+
+static int check_core_relo(struct bpf_verifier_env *env,
+			   const union bpf_attr *attr,
+			   bpfptr_t uattr)
+{
+	u32 i, nr_core_relo, ncopy, expected_size, rec_size;
+	struct bpf_core_relo core_relo = {};
+	struct bpf_prog *prog = env->prog;
+	const struct btf *btf = prog->aux->btf;
+	struct bpf_core_ctx ctx = {
+		.log = &env->log,
+		.btf = btf,
+	};
+	bpfptr_t u_core_relo;
+	int err;
+
+	nr_core_relo = attr->core_relo_cnt;
+	if (!nr_core_relo)
+		return 0;
+	if (nr_core_relo > INT_MAX / sizeof(struct bpf_core_relo))
+		return -EINVAL;
+
+	rec_size = attr->core_relo_rec_size;
+	if (rec_size < MIN_CORE_RELO_SIZE ||
+	    rec_size > MAX_CORE_RELO_SIZE ||
+	    rec_size % sizeof(u32))
+		return -EINVAL;
+
+	u_core_relo = make_bpfptr(attr->core_relos, uattr.is_kernel);
+	expected_size = sizeof(struct bpf_core_relo);
+	ncopy = min_t(u32, expected_size, rec_size);
+
+	/* Unlike func_info and line_info, copy and apply each CO-RE
+	 * relocation record one at a time.
+	 */
+	for (i = 0; i < nr_core_relo; i++) {
+		/* future proofing when sizeof(bpf_core_relo) changes */
+		err = bpf_check_uarg_tail_zero(u_core_relo, expected_size, rec_size);
+		if (err) {
+			if (err == -E2BIG) {
+				verbose(env, "nonzero tailing record in core_relo");
+				if (copy_to_bpfptr_offset(uattr,
+							  offsetof(union bpf_attr, core_relo_rec_size),
+							  &expected_size, sizeof(expected_size)))
+					err = -EFAULT;
+			}
+			break;
+		}
+
+		if (copy_from_bpfptr(&core_relo, u_core_relo, ncopy)) {
+			err = -EFAULT;
+			break;
+		}
+
+		if (core_relo.insn_off % 8 || core_relo.insn_off / 8 >= prog->len) {
+			verbose(env, "Invalid core_relo[%u].insn_off:%u prog->len:%u\n",
+				i, core_relo.insn_off, prog->len);
+			err = -EINVAL;
+			break;
+		}
+
+		err = bpf_core_apply(&ctx, &core_relo, i,
+				     &prog->insnsi[core_relo.insn_off / 8]);
+		if (err)
+			break;
+		bpfptr_add(&u_core_relo, rec_size);
+	}
+	return err;
+}
+
 static int check_btf_info(struct bpf_verifier_env *env,
 			  const union bpf_attr *attr,
 			  bpfptr_t uattr)
@@ -10303,6 +10375,10 @@ static int check_btf_info(struct bpf_verifier_env *env,
 	if (err)
 		return err;
 
+	err = check_core_relo(env, attr, uattr);
+	if (err)
+		return err;
+
 	return 0;
 }
 
diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h
index 9e66b1880020..c26871263f1f 100644
--- a/tools/include/uapi/linux/bpf.h
+++ b/tools/include/uapi/linux/bpf.h
@@ -1342,8 +1342,10 @@ union bpf_attr {
 			/* or valid module BTF object fd or 0 to attach to vmlinux */
 			__u32		attach_btf_obj_fd;
 		};
-		__u32		:32;		/* pad */
+		__u32		core_relo_cnt;	/* number of bpf_core_relo */
 		__aligned_u64	fd_array;	/* array of FDs */
+		__aligned_u64	core_relos;
+		__u32		core_relo_rec_size; /* sizeof(struct bpf_core_relo) */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */
@@ -6393,4 +6395,59 @@ enum bpf_core_relo_kind {
 	BPF_CORE_ENUMVAL_VALUE = 11,         /* enum value integer value */
 };
 
+/*
+ * "struct bpf_core_relo" is used to pass relocation data form LLVM to libbpf
+ * and from libbpf to the kernel.
+ *
+ * CO-RE 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 field info;
+ * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
+ *   type or field;
+ * - access_str_off - offset into corresponding .BTF string section. String
+ *   interpretation depends on specific relocation kind:
+ *     - for field-based relocations, string encodes an accessed field using
+ *       a sequence of field and array indices, separated by colon (:). It's
+ *       conceptually very close to LLVM's getelementptr ([0]) instruction's
+ *       arguments for identifying offset to a field.
+ *     - for type-based relocations, strings is expected to be just "0";
+ *     - for enum value-based relocations, string contains an index of enum
+ *       value within its enum type;
+ * - kind - one of enum bpf_core_relo_kind;
+ *
+ * Example:
+ *   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 field 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_core_relo {
+	__u32 insn_off;
+	__u32 type_id;
+	__u32 access_str_off;
+	enum bpf_core_relo_kind kind;
+};
+
 #endif /* _UAPI__LINUX_BPF_H__ */
diff --git a/tools/lib/bpf/relo_core.h b/tools/lib/bpf/relo_core.h
index 3d0b86e7f439..f410691cc4e5 100644
--- a/tools/lib/bpf/relo_core.h
+++ b/tools/lib/bpf/relo_core.h
@@ -6,59 +6,6 @@
 
 #include <linux/bpf.h>
 
-/* The minimum bpf_core_relo checked by the loader
- *
- * CO-RE 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 field info;
- * - type_id - BTF type ID of the "root" (containing) entity of a relocatable
- *   type or field;
- * - access_str_off - offset into corresponding .BTF string section. String
- *   interpretation depends on specific relocation kind:
- *     - for field-based relocations, string encodes an accessed field using
- *     a sequence of field and array indices, separated by colon (:). It's
- *     conceptually very close to LLVM's getelementptr ([0]) instruction's
- *     arguments for identifying offset to a field.
- *     - for type-based relocations, strings is expected to be just "0";
- *     - for enum value-based relocations, string contains an index of enum
- *     value within its enum type;
- *
- * 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 field 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_core_relo {
-	__u32   insn_off;
-	__u32   type_id;
-	__u32   access_str_off;
-	enum bpf_core_relo_kind kind;
-};
-
 struct bpf_core_cand {
 	const struct btf *btf;
 	const struct btf_type *t;