Merge branch 'bpf-trampoline'

Alexei Starovoitov says:

====================
Introduce BPF trampoline that works as a bridge between kernel functions, BPF
programs and other BPF programs.

The first use case is fentry/fexit BPF programs that are roughly equivalent to
kprobe/kretprobe. Unlike k[ret]probe there is practically zero overhead to call
a set of BPF programs before or after kernel function.

The second use case is heavily influenced by pain points in XDP development.
BPF trampoline allows attaching similar fentry/fexit BPF program to any
networking BPF program. It's now possible to see packets on input and output of
any XDP, TC, lwt, cgroup programs without disturbing them. This greatly helps
BPF-based network troubleshooting.

The third use case of BPF trampoline will be explored in the follow up patches.
The BPF trampoline will be used to dynamicly link BPF programs. It's more
generic mechanism than array and link list of programs used in tracing,
networking, cgroups. In many cases it can be used as a replacement for
bpf_tail_call-based program chaining. See [1] for long term design discussion.

v3 -> v4:
- Included Peter's
  "86/alternatives: Teach text_poke_bp() to emulate instructions" as a first patch.
  If it changes between now and merge window, I'll rebease to newer version.
  The patch is necessary to do s/text_poke/text_poke_bp/ in patch 3 to fix the race.
- In patch 4 fixed bpf_trampoline creation race spotted by Andrii.
- Added patch 15 that annotates prog->kern bpf context types. It made patches 16
  and 17 cleaner and more generic.
- Addressed Andrii's feedback in other patches.

v2 -> v3:
- Addressed Song's and Andrii's comments
- Fixed few minor bugs discovered while testing
- Added one more libbpf patch

v1 -> v2:
- Addressed Andrii's comments
- Added more test for fentry/fexit to kernel functions. Including stress test
  for maximum number of progs per trampoline.
- Fixed a race btf_resolve_helper_id()
- Added a patch to compare BTF types of functions arguments with actual types.
- Added support for attaching BPF program to another BPF program via trampoline
- Converted to use text_poke() API. That's the only viable mechanism to
  implement BPF-to-BPF attach. BPF-to-kernel attach can be refactored to use
  register_ftrace_direct() whenever it's available.

  [1] https://lore.kernel.org/bpf/20191112025112.bhzmrrh2pr76ssnh@ast-mbp.dhcp.thefacebook.com/
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

5 files changed, 192 insertions, 29 deletions

diff --git a/include/linux/bpf.h b/include/linux/bpf.h
index 7c7f518811a6..5b81cde47314 100644
--- a/include/linux/bpf.h
+++ b/include/linux/bpf.h
@@ -14,6 +14,8 @@
 #include <linux/numa.h>
 #include <linux/wait.h>
 #include <linux/u64_stats_sync.h>
+#include <linux/refcount.h>
+#include <linux/mutex.h>
 
 struct bpf_verifier_env;
 struct bpf_verifier_log;
@@ -246,7 +248,7 @@ struct bpf_func_proto {
 		};
 		enum bpf_arg_type arg_type[5];
 	};
-	u32 *btf_id; /* BTF ids of arguments */
+	int *btf_id; /* BTF ids of arguments */
 };
 
 /* bpf_context is intentionally undefined structure. Pointer to bpf_context is
@@ -384,6 +386,104 @@ struct bpf_prog_stats {
 	struct u64_stats_sync syncp;
 } __aligned(2 * sizeof(u64));
 
+struct btf_func_model {
+	u8 ret_size;
+	u8 nr_args;
+	u8 arg_size[MAX_BPF_FUNC_ARGS];
+};
+
+/* Restore arguments before returning from trampoline to let original function
+ * continue executing. This flag is used for fentry progs when there are no
+ * fexit progs.
+ */
+#define BPF_TRAMP_F_RESTORE_REGS	BIT(0)
+/* Call original function after fentry progs, but before fexit progs.
+ * Makes sense for fentry/fexit, normal calls and indirect calls.
+ */
+#define BPF_TRAMP_F_CALL_ORIG		BIT(1)
+/* Skip current frame and return to parent.  Makes sense for fentry/fexit
+ * programs only. Should not be used with normal calls and indirect calls.
+ */
+#define BPF_TRAMP_F_SKIP_FRAME		BIT(2)
+
+/* Different use cases for BPF trampoline:
+ * 1. replace nop at the function entry (kprobe equivalent)
+ *    flags = BPF_TRAMP_F_RESTORE_REGS
+ *    fentry = a set of programs to run before returning from trampoline
+ *
+ * 2. replace nop at the function entry (kprobe + kretprobe equivalent)
+ *    flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME
+ *    orig_call = fentry_ip + MCOUNT_INSN_SIZE
+ *    fentry = a set of program to run before calling original function
+ *    fexit = a set of program to run after original function
+ *
+ * 3. replace direct call instruction anywhere in the function body
+ *    or assign a function pointer for indirect call (like tcp_congestion_ops->cong_avoid)
+ *    With flags = 0
+ *      fentry = a set of programs to run before returning from trampoline
+ *    With flags = BPF_TRAMP_F_CALL_ORIG
+ *      orig_call = original callback addr or direct function addr
+ *      fentry = a set of program to run before calling original function
+ *      fexit = a set of program to run after original function
+ */
+int arch_prepare_bpf_trampoline(void *image, struct btf_func_model *m, u32 flags,
+				struct bpf_prog **fentry_progs, int fentry_cnt,
+				struct bpf_prog **fexit_progs, int fexit_cnt,
+				void *orig_call);
+/* these two functions are called from generated trampoline */
+u64 notrace __bpf_prog_enter(void);
+void notrace __bpf_prog_exit(struct bpf_prog *prog, u64 start);
+
+enum bpf_tramp_prog_type {
+	BPF_TRAMP_FENTRY,
+	BPF_TRAMP_FEXIT,
+	BPF_TRAMP_MAX
+};
+
+struct bpf_trampoline {
+	/* hlist for trampoline_table */
+	struct hlist_node hlist;
+	/* serializes access to fields of this trampoline */
+	struct mutex mutex;
+	refcount_t refcnt;
+	u64 key;
+	struct {
+		struct btf_func_model model;
+		void *addr;
+	} func;
+	/* list of BPF programs using this trampoline */
+	struct hlist_head progs_hlist[BPF_TRAMP_MAX];
+	/* Number of attached programs. A counter per kind. */
+	int progs_cnt[BPF_TRAMP_MAX];
+	/* Executable image of trampoline */
+	void *image;
+	u64 selector;
+};
+#ifdef CONFIG_BPF_JIT
+struct bpf_trampoline *bpf_trampoline_lookup(u64 key);
+int bpf_trampoline_link_prog(struct bpf_prog *prog);
+int bpf_trampoline_unlink_prog(struct bpf_prog *prog);
+void bpf_trampoline_put(struct bpf_trampoline *tr);
+#else
+static inline struct bpf_trampoline *bpf_trampoline_lookup(u64 key)
+{
+	return NULL;
+}
+static inline int bpf_trampoline_link_prog(struct bpf_prog *prog)
+{
+	return -ENOTSUPP;
+}
+static inline int bpf_trampoline_unlink_prog(struct bpf_prog *prog)
+{
+	return -ENOTSUPP;
+}
+static inline void bpf_trampoline_put(struct bpf_trampoline *tr) {}
+#endif
+
+struct bpf_func_info_aux {
+	bool unreliable;
+};
+
 struct bpf_prog_aux {
 	atomic_t refcnt;
 	u32 used_map_cnt;
@@ -395,9 +495,14 @@ struct bpf_prog_aux {
 	u32 func_cnt; /* used by non-func prog as the number of func progs */
 	u32 func_idx; /* 0 for non-func prog, the index in func array for func prog */
 	u32 attach_btf_id; /* in-kernel BTF type id to attach to */
+	struct bpf_prog *linked_prog;
 	bool verifier_zext; /* Zero extensions has been inserted by verifier. */
 	bool offload_requested;
 	bool attach_btf_trace; /* true if attaching to BTF-enabled raw tp */
+	bool func_proto_unreliable;
+	enum bpf_tramp_prog_type trampoline_prog_type;
+	struct bpf_trampoline *trampoline;
+	struct hlist_node tramp_hlist;
 	/* BTF_KIND_FUNC_PROTO for valid attach_btf_id */
 	const struct btf_type *attach_func_proto;
 	/* function name for valid attach_btf_id */
@@ -419,6 +524,7 @@ struct bpf_prog_aux {
 	struct bpf_prog_offload *offload;
 	struct btf *btf;
 	struct bpf_func_info *func_info;
+	struct bpf_func_info_aux *func_info_aux;
 	/* bpf_line_info loaded from userspace.  linfo->insn_off
 	 * has the xlated insn offset.
 	 * Both the main and sub prog share the same linfo.
@@ -648,7 +754,7 @@ DECLARE_PER_CPU(int, bpf_prog_active);
 extern const struct file_operations bpf_map_fops;
 extern const struct file_operations bpf_prog_fops;
 
-#define BPF_PROG_TYPE(_id, _name) \
+#define BPF_PROG_TYPE(_id, _name, prog_ctx_type, kern_ctx_type) \
 	extern const struct bpf_prog_ops _name ## _prog_ops; \
 	extern const struct bpf_verifier_ops _name ## _verifier_ops;
 #define BPF_MAP_TYPE(_id, _ops) \
@@ -782,7 +888,16 @@ int btf_struct_access(struct bpf_verifier_log *log,
 		      const struct btf_type *t, int off, int size,
 		      enum bpf_access_type atype,
 		      u32 *next_btf_id);
-u32 btf_resolve_helper_id(struct bpf_verifier_log *log, void *, int);
+int btf_resolve_helper_id(struct bpf_verifier_log *log,
+			  const struct bpf_func_proto *fn, int);
+
+int btf_distill_func_proto(struct bpf_verifier_log *log,
+			   struct btf *btf,
+			   const struct btf_type *func_proto,
+			   const char *func_name,
+			   struct btf_func_model *m);
+
+int btf_check_func_arg_match(struct bpf_verifier_env *env, int subprog);
 
 #else /* !CONFIG_BPF_SYSCALL */
 static inline struct bpf_prog *bpf_prog_get(u32 ufd)
@@ -1107,6 +1222,15 @@ static inline u32 bpf_sock_convert_ctx_access(enum bpf_access_type type,
 #endif
 
 #ifdef CONFIG_INET
+struct sk_reuseport_kern {
+	struct sk_buff *skb;
+	struct sock *sk;
+	struct sock *selected_sk;
+	void *data_end;
+	u32 hash;
+	u32 reuseport_id;
+	bool bind_inany;
+};
 bool bpf_tcp_sock_is_valid_access(int off, int size, enum bpf_access_type type,
 				  struct bpf_insn_access_aux *info);
 
@@ -1157,4 +1281,12 @@ static inline u32 bpf_xdp_sock_convert_ctx_access(enum bpf_access_type type,
 }
 #endif /* CONFIG_INET */
 
+enum bpf_text_poke_type {
+	BPF_MOD_NOP_TO_CALL,
+	BPF_MOD_CALL_TO_CALL,
+	BPF_MOD_CALL_TO_NOP,
+};
+int bpf_arch_text_poke(void *ip, enum bpf_text_poke_type t,
+		       void *addr1, void *addr2);
+
 #endif /* _LINUX_BPF_H */
diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h
index de14872b01ba..93740b3614d7 100644
--- a/include/linux/bpf_types.h
+++ b/include/linux/bpf_types.h
@@ -2,42 +2,68 @@
 /* internal file - do not include directly */
 
 #ifdef CONFIG_NET
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act)
-BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCKET_FILTER, sk_filter,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_CLS, tc_cls_act,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SCHED_ACT, tc_cls_act,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_XDP, xdp,
+	      struct xdp_md, struct xdp_buff)
 #ifdef CONFIG_CGROUP_BPF
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SKB, cg_skb,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK, cg_sock,
+	      struct bpf_sock, struct sock)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCK_ADDR, cg_sock_addr,
+	      struct bpf_sock_addr, struct bpf_sock_addr_kern)
 #endif
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit)
-BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb)
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg)
-BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_IN, lwt_in,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_OUT, lwt_out,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_XMIT, lwt_xmit,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LWT_SEG6LOCAL, lwt_seg6local,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SOCK_OPS, sock_ops,
+	      struct bpf_sock_ops, struct bpf_sock_ops_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_SKB, sk_skb,
+	      struct __sk_buff, struct sk_buff)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_MSG, sk_msg,
+	      struct sk_msg_md, struct sk_msg)
+BPF_PROG_TYPE(BPF_PROG_TYPE_FLOW_DISSECTOR, flow_dissector,
+	      struct __sk_buff, struct bpf_flow_dissector)
 #endif
 #ifdef CONFIG_BPF_EVENTS
-BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe)
-BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint)
-BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event)
-BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint)
-BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable)
-BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing)
+BPF_PROG_TYPE(BPF_PROG_TYPE_KPROBE, kprobe,
+	      bpf_user_pt_regs_t, struct pt_regs)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACEPOINT, tracepoint,
+	      __u64, u64)
+BPF_PROG_TYPE(BPF_PROG_TYPE_PERF_EVENT, perf_event,
+	      struct bpf_perf_event_data, struct bpf_perf_event_data_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT, raw_tracepoint,
+	      struct bpf_raw_tracepoint_args, u64)
+BPF_PROG_TYPE(BPF_PROG_TYPE_RAW_TRACEPOINT_WRITABLE, raw_tracepoint_writable,
+	      struct bpf_raw_tracepoint_args, u64)
+BPF_PROG_TYPE(BPF_PROG_TYPE_TRACING, tracing,
+	      void *, void *)
 #endif
 #ifdef CONFIG_CGROUP_BPF
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl)
-BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_DEVICE, cg_dev,
+	      struct bpf_cgroup_dev_ctx, struct bpf_cgroup_dev_ctx)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SYSCTL, cg_sysctl,
+	      struct bpf_sysctl, struct bpf_sysctl_kern)
+BPF_PROG_TYPE(BPF_PROG_TYPE_CGROUP_SOCKOPT, cg_sockopt,
+	      struct bpf_sockopt, struct bpf_sockopt_kern)
 #endif
 #ifdef CONFIG_BPF_LIRC_MODE2
-BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2)
+BPF_PROG_TYPE(BPF_PROG_TYPE_LIRC_MODE2, lirc_mode2,
+	      __u32, u32)
 #endif
 #ifdef CONFIG_INET
-BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport)
+BPF_PROG_TYPE(BPF_PROG_TYPE_SK_REUSEPORT, sk_reuseport,
+	      struct sk_reuseport_md, struct sk_reuseport_kern)
 #endif
 
 BPF_MAP_TYPE(BPF_MAP_TYPE_ARRAY, array_map_ops)
diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h
index 6e7284ea1468..cdd08bf0ec06 100644
--- a/include/linux/bpf_verifier.h
+++ b/include/linux/bpf_verifier.h
@@ -343,6 +343,7 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log)
 #define BPF_MAX_SUBPROGS 256
 
 struct bpf_subprog_info {
+	/* 'start' has to be the first field otherwise find_subprog() won't work */
 	u32 start; /* insn idx of function entry point */
 	u32 linfo_idx; /* The idx to the main_prog->aux->linfo */
 	u16 stack_depth; /* max. stack depth used by this function */
diff --git a/include/linux/btf.h b/include/linux/btf.h
index 9dee00859c5f..79d4abc2556a 100644
--- a/include/linux/btf.h
+++ b/include/linux/btf.h
@@ -88,6 +88,7 @@ static inline bool btf_type_is_func_proto(const struct btf_type *t)
 const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id);
 const char *btf_name_by_offset(const struct btf *btf, u32 offset);
 struct btf *btf_parse_vmlinux(void);
+struct btf *bpf_prog_get_target_btf(const struct bpf_prog *prog);
 #else
 static inline const struct btf_type *btf_type_by_id(const struct btf *btf,
 						    u32 type_id)
diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h
index df6809a76404..4842a134b202 100644
--- a/include/uapi/linux/bpf.h
+++ b/include/uapi/linux/bpf.h
@@ -201,6 +201,8 @@ enum bpf_attach_type {
 	BPF_CGROUP_GETSOCKOPT,
 	BPF_CGROUP_SETSOCKOPT,
 	BPF_TRACE_RAW_TP,
+	BPF_TRACE_FENTRY,
+	BPF_TRACE_FEXIT,
 	__MAX_BPF_ATTACH_TYPE
 };
 
@@ -423,6 +425,7 @@ union bpf_attr {
 		__aligned_u64	line_info;	/* line info */
 		__u32		line_info_cnt;	/* number of bpf_line_info records */
 		__u32		attach_btf_id;	/* in-kernel BTF type id to attach to */
+		__u32		attach_prog_fd; /* 0 to attach to vmlinux */
 	};
 
 	struct { /* anonymous struct used by BPF_OBJ_* commands */