tracing/probes: Support $argN in return probe (kprobe and fprobe)

Support accessing $argN in the return probe events. This will help users to
record entry data in function return (exit) event for simplfing the function
entry/exit information in one event, and record the result values (e.g.
allocated object/initialized object) at function exit.

For example, if we have a function `int init_foo(struct foo *obj, int param)`
sometimes we want to check how `obj` is initialized. In such case, we can
define a new return event like below;

 # echo 'r init_foo retval=$retval param=$arg2 field1=+0($arg1)' >> kprobe_events

Thus it records the function parameter `param` and its result `obj->field1`
(the dereference will be done in the function exit timing) value at once.

This also support fprobe, BTF args and'$arg*'. So if CONFIG_DEBUG_INFO_BTF
is enabled, we can trace both function parameters and the return value
by following command.

 # echo 'f target_function%return $arg* $retval' >> dynamic_events

Link: https://lore.kernel.org/all/170952365552.229804.224112990211602895.stgit@devnote2/

Signed-off-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>

Author: mhiramat

kernel/trace/trace.c

@@ -5755,6 +5755,7 @@ static const char readme_msg[] =
 	"\t           $stack<index>, $stack, $retval, $comm,\n"
 #endif
 	"\t           +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
+	"\t     kernel return probes support: $retval, $arg<N>, $comm\n"
 	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, char, string, symbol,\n"
 	"\t           b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
 	"\t           symstr, <type>\\[<array-size>\\]\n"

kernel/trace/trace_eprobe.c

@@ -390,8 +390,8 @@ static int get_eprobe_size(struct trace_probe *tp, void *rec)
 
 /* Note that we don't verify it, since the code does not come from user space */
 static int
-process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
-		   void *base)
+process_fetch_insn(struct fetch_insn *code, void *rec, void *edata,
+		   void *dest, void *base)
 {
 	unsigned long val;
 	int ret;
@@ -438,7 +438,7 @@ __eprobe_trace_func(struct eprobe_data *edata, void *rec)
 		return;
 
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
-	store_trace_args(&entry[1], &edata->ep->tp, rec, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &edata->ep->tp, rec, NULL, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }

kernel/trace/trace_fprobe.c

@@ -4,6 +4,7 @@
  * Copyright (C) 2022 Google LLC.
  */
 #define pr_fmt(fmt)	"trace_fprobe: " fmt
+#include <asm/ptrace.h>
 
 #include <linux/fprobe.h>
 #include <linux/module.h>
@@ -129,8 +130,8 @@ static bool trace_fprobe_is_registered(struct trace_fprobe *tf)
  * from user space.
  */
 static int
-process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
-		   void *base)
+process_fetch_insn(struct fetch_insn *code, void *rec, void *edata,
+		   void *dest, void *base)
 {
 	struct pt_regs *regs = rec;
 	unsigned long val;
@@ -152,6 +153,9 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
 	case FETCH_OP_ARG:
 		val = regs_get_kernel_argument(regs, code->param);
 		break;
+	case FETCH_OP_EDATA:
+		val = *(unsigned long *)((unsigned long)edata + code->offset);
+		break;
 #endif
 	case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
 		code++;
@@ -184,7 +188,7 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	dsize = __get_data_size(&tf->tp, regs);
+	dsize = __get_data_size(&tf->tp, regs, NULL);
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + tf->tp.size + dsize);
@@ -194,7 +198,7 @@ __fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	fbuffer.regs = regs;
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
 	entry->ip = entry_ip;
-	store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }
@@ -211,10 +215,23 @@ fentry_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 NOKPROBE_SYMBOL(fentry_trace_func);
 
 /* function exit handler */
+static int trace_fprobe_entry_handler(struct fprobe *fp, unsigned long entry_ip,
+				unsigned long ret_ip, struct pt_regs *regs,
+				void *entry_data)
+{
+	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
+
+	if (tf->tp.entry_arg)
+		store_trace_entry_data(entry_data, &tf->tp, regs);
+
+	return 0;
+}
+NOKPROBE_SYMBOL(trace_fprobe_entry_handler)
+
 static nokprobe_inline void
 __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 		   unsigned long ret_ip, struct pt_regs *regs,
-		   struct trace_event_file *trace_file)
+		   void *entry_data, struct trace_event_file *trace_file)
 {
 	struct fexit_trace_entry_head *entry;
 	struct trace_event_buffer fbuffer;
@@ -227,7 +244,7 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	dsize = __get_data_size(&tf->tp, regs);
+	dsize = __get_data_size(&tf->tp, regs, entry_data);
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + tf->tp.size + dsize);
@@ -238,19 +255,19 @@ __fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	entry = fbuffer.entry = ring_buffer_event_data(fbuffer.event);
 	entry->func = entry_ip;
 	entry->ret_ip = ret_ip;
-	store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }
 
 static void
 fexit_trace_func(struct trace_fprobe *tf, unsigned long entry_ip,
-		 unsigned long ret_ip, struct pt_regs *regs)
+		 unsigned long ret_ip, struct pt_regs *regs, void *entry_data)
 {
 	struct event_file_link *link;
 
 	trace_probe_for_each_link_rcu(link, &tf->tp)
-		__fexit_trace_func(tf, entry_ip, ret_ip, regs, link->file);
+		__fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data, link->file);
 }
 NOKPROBE_SYMBOL(fexit_trace_func);
 
@@ -269,7 +286,7 @@ static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	if (hlist_empty(head))
 		return 0;
 
-	dsize = __get_data_size(&tf->tp, regs);
+	dsize = __get_data_size(&tf->tp, regs, NULL);
 	__size = sizeof(*entry) + tf->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
@@ -280,7 +297,7 @@ static int fentry_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
 
 	entry->ip = entry_ip;
 	memset(&entry[1], 0, dsize);
-	store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, regs, NULL, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
 	return 0;
@@ -289,7 +306,8 @@ NOKPROBE_SYMBOL(fentry_perf_func);
 
 static void
 fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
-		unsigned long ret_ip, struct pt_regs *regs)
+		unsigned long ret_ip, struct pt_regs *regs,
+		void *entry_data)
 {
 	struct trace_event_call *call = trace_probe_event_call(&tf->tp);
 	struct fexit_trace_entry_head *entry;
@@ -301,7 +319,7 @@ fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
 	if (hlist_empty(head))
 		return;
 
-	dsize = __get_data_size(&tf->tp, regs);
+	dsize = __get_data_size(&tf->tp, regs, entry_data);
 	__size = sizeof(*entry) + tf->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
@@ -312,7 +330,7 @@ fexit_perf_func(struct trace_fprobe *tf, unsigned long entry_ip,
 
 	entry->func = entry_ip;
 	entry->ret_ip = ret_ip;
-	store_trace_args(&entry[1], &tf->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tf->tp, regs, entry_data, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
 }
@@ -343,10 +361,10 @@ static void fexit_dispatcher(struct fprobe *fp, unsigned long entry_ip,
 	struct trace_fprobe *tf = container_of(fp, struct trace_fprobe, fp);
 
 	if (trace_probe_test_flag(&tf->tp, TP_FLAG_TRACE))
-		fexit_trace_func(tf, entry_ip, ret_ip, regs);
+		fexit_trace_func(tf, entry_ip, ret_ip, regs, entry_data);
 #ifdef CONFIG_PERF_EVENTS
 	if (trace_probe_test_flag(&tf->tp, TP_FLAG_PROFILE))
-		fexit_perf_func(tf, entry_ip, ret_ip, regs);
+		fexit_perf_func(tf, entry_ip, ret_ip, regs, entry_data);
 #endif
 }
 NOKPROBE_SYMBOL(fexit_dispatcher);
@@ -1109,6 +1127,11 @@ static int __trace_fprobe_create(int argc, const char *argv[])
 			goto error;	/* This can be -ENOMEM */
 	}
 
+	if (is_return && tf->tp.entry_arg) {
+		tf->fp.entry_handler = trace_fprobe_entry_handler;
+		tf->fp.entry_data_size = traceprobe_get_entry_data_size(&tf->tp);
+	}
+
 	ret = traceprobe_set_print_fmt(&tf->tp,
 			is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL);
 	if (ret < 0)

kernel/trace/trace_kprobe.c

@@ -740,6 +740,9 @@ static unsigned int number_of_same_symbols(char *func_name)
 	return ctx.count;
 }
 
+static int trace_kprobe_entry_handler(struct kretprobe_instance *ri,
+				      struct pt_regs *regs);
+
 static int __trace_kprobe_create(int argc, const char *argv[])
 {
 	/*
@@ -948,6 +951,11 @@ static int __trace_kprobe_create(int argc, const char *argv[])
 		if (ret)
 			goto error;	/* This can be -ENOMEM */
 	}
+	/* entry handler for kretprobe */
+	if (is_return && tk->tp.entry_arg) {
+		tk->rp.entry_handler = trace_kprobe_entry_handler;
+		tk->rp.data_size = traceprobe_get_entry_data_size(&tk->tp);
+	}
 
 	ptype = is_return ? PROBE_PRINT_RETURN : PROBE_PRINT_NORMAL;
 	ret = traceprobe_set_print_fmt(&tk->tp, ptype);
@@ -1303,8 +1311,8 @@ static const struct file_operations kprobe_profile_ops = {
 
 /* Note that we don't verify it, since the code does not come from user space */
 static int
-process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
-		   void *base)
+process_fetch_insn(struct fetch_insn *code, void *rec, void *edata,
+		   void *dest, void *base)
 {
 	struct pt_regs *regs = rec;
 	unsigned long val;
@@ -1329,6 +1337,9 @@ process_fetch_insn(struct fetch_insn *code, void *rec, void *dest,
 	case FETCH_OP_ARG:
 		val = regs_get_kernel_argument(regs, code->param);
 		break;
+	case FETCH_OP_EDATA:
+		val = *(unsigned long *)((unsigned long)edata + code->offset);
+		break;
 #endif
 	case FETCH_NOP_SYMBOL:	/* Ignore a place holder */
 		code++;
@@ -1359,7 +1370,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	dsize = __get_data_size(&tk->tp, regs);
+	dsize = __get_data_size(&tk->tp, regs, NULL);
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + tk->tp.size + dsize);
@@ -1368,7 +1379,7 @@ __kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs,
 
 	fbuffer.regs = regs;
 	entry->ip = (unsigned long)tk->rp.kp.addr;
-	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tk->tp, regs, NULL, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }
@@ -1384,6 +1395,31 @@ kprobe_trace_func(struct trace_kprobe *tk, struct pt_regs *regs)
 NOKPROBE_SYMBOL(kprobe_trace_func);
 
 /* Kretprobe handler */
+
+static int trace_kprobe_entry_handler(struct kretprobe_instance *ri,
+				      struct pt_regs *regs)
+{
+	struct kretprobe *rp = get_kretprobe(ri);
+	struct trace_kprobe *tk;
+
+	/*
+	 * There is a small chance that get_kretprobe(ri) returns NULL when
+	 * the kretprobe is unregister on another CPU between kretprobe's
+	 * trampoline_handler and this function.
+	 */
+	if (unlikely(!rp))
+		return -ENOENT;
+
+	tk = container_of(rp, struct trace_kprobe, rp);
+
+	/* store argument values into ri->data as entry data */
+	if (tk->tp.entry_arg)
+		store_trace_entry_data(ri->data, &tk->tp, regs);
+
+	return 0;
+}
+
+
 static nokprobe_inline void
 __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 		       struct pt_regs *regs,
@@ -1399,7 +1435,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	if (trace_trigger_soft_disabled(trace_file))
 		return;
 
-	dsize = __get_data_size(&tk->tp, regs);
+	dsize = __get_data_size(&tk->tp, regs, ri->data);
 
 	entry = trace_event_buffer_reserve(&fbuffer, trace_file,
 					   sizeof(*entry) + tk->tp.size + dsize);
@@ -1409,7 +1445,7 @@ __kretprobe_trace_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	fbuffer.regs = regs;
 	entry->func = (unsigned long)tk->rp.kp.addr;
 	entry->ret_ip = get_kretprobe_retaddr(ri);
-	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tk->tp, regs, ri->data, sizeof(*entry), dsize);
 
 	trace_event_buffer_commit(&fbuffer);
 }
@@ -1557,7 +1593,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 	if (hlist_empty(head))
 		return 0;
 
-	dsize = __get_data_size(&tk->tp, regs);
+	dsize = __get_data_size(&tk->tp, regs, NULL);
 	__size = sizeof(*entry) + tk->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
@@ -1568,7 +1604,7 @@ kprobe_perf_func(struct trace_kprobe *tk, struct pt_regs *regs)
 
 	entry->ip = (unsigned long)tk->rp.kp.addr;
 	memset(&entry[1], 0, dsize);
-	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tk->tp, regs, NULL, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
 	return 0;
@@ -1593,7 +1629,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 	if (hlist_empty(head))
 		return;
 
-	dsize = __get_data_size(&tk->tp, regs);
+	dsize = __get_data_size(&tk->tp, regs, ri->data);
 	__size = sizeof(*entry) + tk->tp.size + dsize;
 	size = ALIGN(__size + sizeof(u32), sizeof(u64));
 	size -= sizeof(u32);
@@ -1604,7 +1640,7 @@ kretprobe_perf_func(struct trace_kprobe *tk, struct kretprobe_instance *ri,
 
 	entry->func = (unsigned long)tk->rp.kp.addr;
 	entry->ret_ip = get_kretprobe_retaddr(ri);
-	store_trace_args(&entry[1], &tk->tp, regs, sizeof(*entry), dsize);
+	store_trace_args(&entry[1], &tk->tp, regs, ri->data, sizeof(*entry), dsize);
 	perf_trace_buf_submit(entry, size, rctx, call->event.type, 1, regs,
 			      head, NULL);
 }