Merge branch 'Add bpf_get_func_ip helper'

Jiri Olsa says:

====================
Add bpf_get_func_ip helper that returns IP address of the
caller function for trampoline and krobe programs.

There're 2 specific implementation of the bpf_get_func_ip
helper, one for trampoline progs and one for kprobe/kretprobe
progs.

The trampoline helper call is replaced/inlined by the verifier
with simple move instruction. The kprobe/kretprobe is actual
helper call that returns prepared caller address.

Also available at:
  https://git.kernel.org/pub/scm/linux/kernel/git/jolsa/perf.git
  bpf/get_func_ip

v4 changes:
  - dropped jit/x86 check for get_func_ip tracing check [Alexei]
  - added code to bpf_get_func_ip_tracing [Alexei]
    and tested that it works without inlining [Alexei]
  - changed has_get_func_ip to check_get_func_ip [Andrii]
  - replaced test assert loop with explicit asserts [Andrii]
  - adde bpf_program__attach_kprobe_opts function
    and use it for offset setup [Andrii]
  - used bpf_program__set_autoload(false) for test6 [Andrii]
  - added Masami's ack

v3 changes:
  - resend with Masami in cc and v3 in each patch subject

v2 changes:
  - use kprobe_running to get kprobe instead of cpu var [Masami]
  - added support to add kprobe on function+offset
    and test for that [Alan]
====================

Signed-off-by: Alexei Starovoitov <ast@kernel.org>

arch/x86/net/bpf_jit_comp.c

@@ -1951,6 +1951,9 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	if (flags & BPF_TRAMP_F_CALL_ORIG)
 		stack_size += 8; /* room for return value of orig_call */
 
+	if (flags & BPF_TRAMP_F_IP_ARG)
+		stack_size += 8; /* room for IP address argument */
+
 	if (flags & BPF_TRAMP_F_SKIP_FRAME)
 		/* skip patched call instruction and point orig_call to actual
 		 * body of the kernel function.
@@ -1964,6 +1967,22 @@ int arch_prepare_bpf_trampoline(struct bpf_tramp_image *im, void *image, void *i
 	EMIT4(0x48, 0x83, 0xEC, stack_size); /* sub rsp, stack_size */
 	EMIT1(0x53);		 /* push rbx */
 
+	if (flags & BPF_TRAMP_F_IP_ARG) {
+		/* Store IP address of the traced function:
+		 * mov rax, QWORD PTR [rbp + 8]
+		 * sub rax, X86_PATCH_SIZE
+		 * mov QWORD PTR [rbp - stack_size], rax
+		 */
+		emit_ldx(&prog, BPF_DW, BPF_REG_0, BPF_REG_FP, 8);
+		EMIT4(0x48, 0x83, 0xe8, X86_PATCH_SIZE);
+		emit_stx(&prog, BPF_DW, BPF_REG_FP, BPF_REG_0, -stack_size);
+
+		/* Continue with stack_size for regs storage, stack will
+		 * be correctly restored with 'leave' instruction.
+		 */
+		stack_size -= 8;
+	}
+
 	save_regs(m, &prog, nr_args, stack_size);
 
 	if (flags & BPF_TRAMP_F_CALL_ORIG) {

include/linux/bpf.h

@@ -579,6 +579,11 @@ struct btf_func_model {
  */
 #define BPF_TRAMP_F_SKIP_FRAME		BIT(2)
 
+/* Store IP address of the caller on the trampoline stack,
+ * so it's available for trampoline's programs.
+ */
+#define BPF_TRAMP_F_IP_ARG		BIT(3)
+
 /* Each call __bpf_prog_enter + call bpf_func + call __bpf_prog_exit is ~50
  * bytes on x86.  Pick a number to fit into BPF_IMAGE_SIZE / 2
  */

include/linux/filter.h

@@ -559,7 +559,8 @@ struct bpf_prog {
 				kprobe_override:1, /* Do we override a kprobe? */
 				has_callchain_buf:1, /* callchain buffer allocated? */
 				enforce_expected_attach_type:1, /* Enforce expected_attach_type checking at attach time */
-				call_get_stack:1; /* Do we call bpf_get_stack() or bpf_get_stackid() */
+				call_get_stack:1, /* Do we call bpf_get_stack() or bpf_get_stackid() */
+				call_get_func_ip:1; /* Do we call get_func_ip() */
 	enum bpf_prog_type	type;		/* Type of BPF program */
 	enum bpf_attach_type	expected_attach_type; /* For some prog types */
 	u32			len;		/* Number of filter blocks */

include/uapi/linux/bpf.h

@@ -4841,6 +4841,12 @@ union bpf_attr {
  *		**-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
  *		**-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its
  *		own timer which would have led to a deadlock otherwise.
+ *
+ * u64 bpf_get_func_ip(void *ctx)
+ * 	Description
+ * 		Get address of the traced function (for tracing and kprobe programs).
+ * 	Return
+ * 		Address of the traced function.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5016,6 +5022,7 @@ union bpf_attr {
 	FN(timer_set_callback),		\
 	FN(timer_start),		\
 	FN(timer_cancel),		\
+	FN(get_func_ip),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

kernel/bpf/trampoline.c

@@ -172,7 +172,7 @@ static int register_fentry(struct bpf_trampoline *tr, void *new_addr)
 }
 
 static struct bpf_tramp_progs *
-bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total)
+bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total, bool *ip_arg)
 {
 	const struct bpf_prog_aux *aux;
 	struct bpf_tramp_progs *tprogs;
@@ -189,8 +189,10 @@ bpf_trampoline_get_progs(const struct bpf_trampoline *tr, int *total)
 		*total += tr->progs_cnt[kind];
 		progs = tprogs[kind].progs;
 
-		hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist)
+		hlist_for_each_entry(aux, &tr->progs_hlist[kind], tramp_hlist) {
+			*ip_arg |= aux->prog->call_get_func_ip;
 			*progs++ = aux->prog;
+		}
 	}
 	return tprogs;
 }
@@ -333,9 +335,10 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 	struct bpf_tramp_image *im;
 	struct bpf_tramp_progs *tprogs;
 	u32 flags = BPF_TRAMP_F_RESTORE_REGS;
+	bool ip_arg = false;
 	int err, total;
 
-	tprogs = bpf_trampoline_get_progs(tr, &total);
+	tprogs = bpf_trampoline_get_progs(tr, &total, &ip_arg);
 	if (IS_ERR(tprogs))
 		return PTR_ERR(tprogs);
 
@@ -357,6 +360,9 @@ static int bpf_trampoline_update(struct bpf_trampoline *tr)
 	    tprogs[BPF_TRAMP_MODIFY_RETURN].nr_progs)
 		flags = BPF_TRAMP_F_CALL_ORIG | BPF_TRAMP_F_SKIP_FRAME;
 
+	if (ip_arg)
+		flags |= BPF_TRAMP_F_IP_ARG;
+
 	err = arch_prepare_bpf_trampoline(im, im->image, im->image + PAGE_SIZE,
 					  &tr->func.model, flags, tprogs,
 					  tr->func.addr);

kernel/bpf/verifier.c

@@ -6161,6 +6161,29 @@ static int check_bpf_snprintf_call(struct bpf_verifier_env *env,
 	return err;
 }
 
+static int check_get_func_ip(struct bpf_verifier_env *env)
+{
+	enum bpf_attach_type eatype = env->prog->expected_attach_type;
+	enum bpf_prog_type type = resolve_prog_type(env->prog);
+	int func_id = BPF_FUNC_get_func_ip;
+
+	if (type == BPF_PROG_TYPE_TRACING) {
+		if (eatype != BPF_TRACE_FENTRY && eatype != BPF_TRACE_FEXIT &&
+		    eatype != BPF_MODIFY_RETURN) {
+			verbose(env, "func %s#%d supported only for fentry/fexit/fmod_ret programs\n",
+				func_id_name(func_id), func_id);
+			return -ENOTSUPP;
+		}
+		return 0;
+	} else if (type == BPF_PROG_TYPE_KPROBE) {
+		return 0;
+	}
+
+	verbose(env, "func %s#%d not supported for program type %d\n",
+		func_id_name(func_id), func_id, type);
+	return -ENOTSUPP;
+}
+
 static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn,
 			     int *insn_idx_p)
 {
@@ -6439,6 +6462,12 @@ static int check_helper_call(struct bpf_verifier_env *env, struct bpf_insn *insn
 	if (func_id == BPF_FUNC_get_stackid || func_id == BPF_FUNC_get_stack)
 		env->prog->call_get_stack = true;
 
+	if (func_id == BPF_FUNC_get_func_ip) {
+		if (check_get_func_ip(env))
+			return -ENOTSUPP;
+		env->prog->call_get_func_ip = true;
+	}
+
 	if (changes_data)
 		clear_all_pkt_pointers(env);
 	return 0;
@@ -12632,6 +12661,7 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 {
 	struct bpf_prog *prog = env->prog;
 	bool expect_blinding = bpf_jit_blinding_enabled(prog);
+	enum bpf_prog_type prog_type = resolve_prog_type(prog);
 	struct bpf_insn *insn = prog->insnsi;
 	const struct bpf_func_proto *fn;
 	const int insn_cnt = prog->len;
@@ -12998,6 +13028,21 @@ static int do_misc_fixups(struct bpf_verifier_env *env)
 			continue;
 		}
 
+		/* Implement bpf_get_func_ip inline. */
+		if (prog_type == BPF_PROG_TYPE_TRACING &&
+		    insn->imm == BPF_FUNC_get_func_ip) {
+			/* Load IP address from ctx - 8 */
+			insn_buf[0] = BPF_LDX_MEM(BPF_DW, BPF_REG_0, BPF_REG_1, -8);
+
+			new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, 1);
+			if (!new_prog)
+				return -ENOMEM;
+
+			env->prog = prog = new_prog;
+			insn      = new_prog->insnsi + i + delta;
+			continue;
+		}
+
 patch_call_imm:
 		fn = env->ops->get_func_proto(insn->imm, env->prog);
 		/* all functions that have prototype and verifier allowed

kernel/trace/bpf_trace.c

@@ -948,6 +948,33 @@ const struct bpf_func_proto bpf_snprintf_btf_proto = {
 	.arg5_type	= ARG_ANYTHING,
 };
 
+BPF_CALL_1(bpf_get_func_ip_tracing, void *, ctx)
+{
+	/* This helper call is inlined by verifier. */
+	return ((u64 *)ctx)[-1];
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_tracing = {
+	.func		= bpf_get_func_ip_tracing,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
+BPF_CALL_1(bpf_get_func_ip_kprobe, struct pt_regs *, regs)
+{
+	struct kprobe *kp = kprobe_running();
+
+	return kp ? (u64) kp->addr : 0;
+}
+
+static const struct bpf_func_proto bpf_get_func_ip_proto_kprobe = {
+	.func		= bpf_get_func_ip_kprobe,
+	.gpl_only	= true,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_PTR_TO_CTX,
+};
+
 const struct bpf_func_proto *
 bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -1058,6 +1085,8 @@ bpf_tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 		return &bpf_for_each_map_elem_proto;
 	case BPF_FUNC_snprintf:
 		return &bpf_snprintf_proto;
+	case BPF_FUNC_get_func_ip:
+		return &bpf_get_func_ip_proto_tracing;
 	default:
 		return bpf_base_func_proto(func_id);
 	}
@@ -1077,6 +1106,8 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_override_return:
 		return &bpf_override_return_proto;
 #endif
+	case BPF_FUNC_get_func_ip:
+		return &bpf_get_func_ip_proto_kprobe;
 	default:
 		return bpf_tracing_func_proto(func_id, prog);
 	}

tools/include/uapi/linux/bpf.h

@@ -4841,6 +4841,12 @@ union bpf_attr {
  *		**-EINVAL** if *timer* was not initialized with bpf_timer_init() earlier.
  *		**-EDEADLK** if callback_fn tried to call bpf_timer_cancel() on its
  *		own timer which would have led to a deadlock otherwise.
+ *
+ * u64 bpf_get_func_ip(void *ctx)
+ * 	Description
+ * 		Get address of the traced function (for tracing and kprobe programs).
+ * 	Return
+ * 		Address of the traced function.
  */
 #define __BPF_FUNC_MAPPER(FN)		\
 	FN(unspec),			\
@@ -5016,6 +5022,7 @@ union bpf_attr {
 	FN(timer_set_callback),		\
 	FN(timer_start),		\
 	FN(timer_cancel),		\
+	FN(get_func_ip),		\
 	/* */
 
 /* integer value in 'imm' field of BPF_CALL instruction selects which helper

tools/lib/bpf/libbpf.c

@@ -10346,19 +10346,25 @@ static int perf_event_open_probe(bool uprobe, bool retprobe, const char *name,
 	return pfd;
 }
 
-struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
-					    bool retprobe,
-					    const char *func_name)
+struct bpf_program_attach_kprobe_opts {
+	bool retprobe;
+	unsigned long offset;
+};
+
+static struct bpf_link*
+bpf_program__attach_kprobe_opts(struct bpf_program *prog,
+				const char *func_name,
+				struct bpf_program_attach_kprobe_opts *opts)
 {
 	char errmsg[STRERR_BUFSIZE];
 	struct bpf_link *link;
 	int pfd, err;
 
-	pfd = perf_event_open_probe(false /* uprobe */, retprobe, func_name,
-				    0 /* offset */, -1 /* pid */);
+	pfd = perf_event_open_probe(false /* uprobe */, opts->retprobe, func_name,
+				    opts->offset, -1 /* pid */);
 	if (pfd < 0) {
 		pr_warn("prog '%s': failed to create %s '%s' perf event: %s\n",
-			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+			prog->name, opts->retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(pfd, errmsg, sizeof(errmsg)));
 		return libbpf_err_ptr(pfd);
 	}
@@ -10367,23 +10373,53 @@ struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
 	if (err) {
 		close(pfd);
 		pr_warn("prog '%s': failed to attach to %s '%s': %s\n",
-			prog->name, retprobe ? "kretprobe" : "kprobe", func_name,
+			prog->name, opts->retprobe ? "kretprobe" : "kprobe", func_name,
 			libbpf_strerror_r(err, errmsg, sizeof(errmsg)));
 		return libbpf_err_ptr(err);
 	}
 	return link;
 }
 
+struct bpf_link *bpf_program__attach_kprobe(struct bpf_program *prog,
+					    bool retprobe,
+					    const char *func_name)
+{
+	struct bpf_program_attach_kprobe_opts opts = {
+		.retprobe = retprobe,
+	};
+
+	return bpf_program__attach_kprobe_opts(prog, func_name, &opts);
+}
+
 static struct bpf_link *attach_kprobe(const struct bpf_sec_def *sec,
 				      struct bpf_program *prog)
 {
+	struct bpf_program_attach_kprobe_opts opts;
+	unsigned long offset = 0;
+	struct bpf_link *link;
 	const char *func_name;
-	bool retprobe;
+	char *func;
+	int n, err;
 
 	func_name = prog->sec_name + sec->len;
-	retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+	opts.retprobe = strcmp(sec->sec, "kretprobe/") == 0;
+
+	n = sscanf(func_name, "%m[a-zA-Z0-9_.]+%lx", &func, &offset);
+	if (n < 1) {
+		err = -EINVAL;
+		pr_warn("kprobe name is invalid: %s\n", func_name);
+		return libbpf_err_ptr(err);
+	}
+	if (opts.retprobe && offset != 0) {
+		err = -EINVAL;
+		pr_warn("kretprobes do not support offset specification\n");
+		return libbpf_err_ptr(err);
+	}
 
-	return bpf_program__attach_kprobe(prog, retprobe, func_name);
+	opts.offset = offset;
+	link = bpf_program__attach_kprobe_opts(prog, func, &opts);
+	free(func);
+	return link;
 }
 
 struct bpf_link *bpf_program__attach_uprobe(struct bpf_program *prog,