Merge tag 'trace-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace

Pull tracing updates from Steven Rostedt:

 - Addition of multiprobes to kprobe and uprobe events (allows for more
   than one probe attached to the same location)

 - Addition of adding immediates to probe parameters

 - Clean up of the recordmcount.c code. This brings us closer to merging
   recordmcount into objtool, and reuse code.

 - Other small clean ups

* tag 'trace-v5.4' of git://git.kernel.org/pub/scm/linux/kernel/git/rostedt/linux-trace: (33 commits)
  selftests/ftrace: Update kprobe event error testcase
  tracing/probe: Reject exactly same probe event
  tracing/probe: Fix to allow user to enable events on unloaded modules
  selftests/ftrace: Select an existing function in kprobe_eventname test
  tracing/kprobe: Fix NULL pointer access in trace_porbe_unlink()
  tracing: Make sure variable reference alias has correct var_ref_idx
  tracing: Be more clever when dumping hex in __print_hex()
  ftrace: Simplify ftrace hash lookup code in clear_func_from_hash()
  tracing: Add "gfp_t" support in synthetic_events
  tracing: Rename tracing_reset() to tracing_reset_cpu()
  tracing: Document the stack trace algorithm in the comments
  tracing/arm64: Have max stack tracer handle the case of return address after data
  recordmcount: Clarify what cleanup() does
  recordmcount: Remove redundant cleanup() calls
  recordmcount: Kernel style formatting
  recordmcount: Kernel style function signature formatting
  recordmcount: Rewrite error/success handling
  selftests/ftrace: Add syntax error test for multiprobe
  selftests/ftrace: Add syntax error test for immediates
  selftests/ftrace: Add a testcase for kprobe multiprobe event
  ...

Documentation/trace/kprobetrace.rst

@@ -52,6 +52,7 @@ Synopsis of kprobe_events
   $retval	: Fetch return value.(\*2)
   $comm		: Fetch current task comm.
   +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*3)(\*4)
+  \IMM		: Store an immediate value to the argument.
   NAME=FETCHARG : Set NAME as the argument name of FETCHARG.
   FETCHARG:TYPE : Set TYPE as the type of FETCHARG. Currently, basic types
 		  (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types

Documentation/trace/uprobetracer.rst

@@ -45,6 +45,7 @@ Synopsis of uprobe_tracer
    $retval	: Fetch return value.(\*1)
    $comm	: Fetch current task comm.
    +|-[u]OFFS(FETCHARG) : Fetch memory at FETCHARG +|- OFFS address.(\*2)(\*3)
+   \IMM		: Store an immediate value to the argument.
    NAME=FETCHARG     : Set NAME as the argument name of FETCHARG.
    FETCHARG:TYPE     : Set TYPE as the type of FETCHARG. Currently, basic types
 		       (u8/u16/u32/u64/s8/s16/s32/s64), hexadecimal types

arch/arm64/include/asm/ftrace.h

@@ -14,6 +14,19 @@
 #define MCOUNT_ADDR		((unsigned long)_mcount)
 #define MCOUNT_INSN_SIZE	AARCH64_INSN_SIZE
 
+/*
+ * Currently, gcc tends to save the link register after the local variables
+ * on the stack. This causes the max stack tracer to report the function
+ * frame sizes for the wrong functions. By defining
+ * ARCH_FTRACE_SHIFT_STACK_TRACER, it will tell the stack tracer to expect
+ * to find the return address on the stack after the local variables have
+ * been set up.
+ *
+ * Note, this may change in the future, and we will need to deal with that
+ * if it were to happen.
+ */
+#define ARCH_FTRACE_SHIFT_STACK_TRACER 1
+
 #ifndef __ASSEMBLY__
 #include <linux/compat.h>
 

kernel/kprobes.c

@@ -961,9 +961,16 @@ static struct kprobe *alloc_aggr_kprobe(struct kprobe *p)
 
 #ifdef CONFIG_KPROBES_ON_FTRACE
 static struct ftrace_ops kprobe_ftrace_ops __read_mostly = {
+	.func = kprobe_ftrace_handler,
+	.flags = FTRACE_OPS_FL_SAVE_REGS,
+};
+
+static struct ftrace_ops kprobe_ipmodify_ops __read_mostly = {
 	.func = kprobe_ftrace_handler,
 	.flags = FTRACE_OPS_FL_SAVE_REGS | FTRACE_OPS_FL_IPMODIFY,
 };
+
+static int kprobe_ipmodify_enabled;
 static int kprobe_ftrace_enabled;
 
 /* Must ensure p->addr is really on ftrace */
@@ -976,58 +983,75 @@ static int prepare_kprobe(struct kprobe *p)
 }
 
 /* Caller must lock kprobe_mutex */
-static int arm_kprobe_ftrace(struct kprobe *p)
+static int __arm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
+			       int *cnt)
 {
 	int ret = 0;
 
-	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
-				   (unsigned long)p->addr, 0, 0);
+	ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 0, 0);
 	if (ret) {
 		pr_debug("Failed to arm kprobe-ftrace at %pS (%d)\n",
 			 p->addr, ret);
 		return ret;
 	}
 
-	if (kprobe_ftrace_enabled == 0) {
-		ret = register_ftrace_function(&kprobe_ftrace_ops);
+	if (*cnt == 0) {
+		ret = register_ftrace_function(ops);
 		if (ret) {
 			pr_debug("Failed to init kprobe-ftrace (%d)\n", ret);
 			goto err_ftrace;
 		}
 	}
 
-	kprobe_ftrace_enabled++;
+	(*cnt)++;
 	return ret;
 
 err_ftrace:
 	/*
-	 * Note: Since kprobe_ftrace_ops has IPMODIFY set, and ftrace requires a
-	 * non-empty filter_hash for IPMODIFY ops, we're safe from an accidental
-	 * empty filter_hash which would undesirably trace all functions.
+	 * At this point, sinec ops is not registered, we should be sefe from
+	 * registering empty filter.
 	 */
-	ftrace_set_filter_ip(&kprobe_ftrace_ops, (unsigned long)p->addr, 1, 0);
+	ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0);
 	return ret;
 }
 
+static int arm_kprobe_ftrace(struct kprobe *p)
+{
+	bool ipmodify = (p->post_handler != NULL);
+
+	return __arm_kprobe_ftrace(p,
+		ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops,
+		ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled);
+}
+
 /* Caller must lock kprobe_mutex */
-static int disarm_kprobe_ftrace(struct kprobe *p)
+static int __disarm_kprobe_ftrace(struct kprobe *p, struct ftrace_ops *ops,
+				  int *cnt)
 {
 	int ret = 0;
 
-	if (kprobe_ftrace_enabled == 1) {
-		ret = unregister_ftrace_function(&kprobe_ftrace_ops);
+	if (*cnt == 1) {
+		ret = unregister_ftrace_function(ops);
 		if (WARN(ret < 0, "Failed to unregister kprobe-ftrace (%d)\n", ret))
 			return ret;
 	}
 
-	kprobe_ftrace_enabled--;
+	(*cnt)--;
 
-	ret = ftrace_set_filter_ip(&kprobe_ftrace_ops,
-			   (unsigned long)p->addr, 1, 0);
+	ret = ftrace_set_filter_ip(ops, (unsigned long)p->addr, 1, 0);
 	WARN_ONCE(ret < 0, "Failed to disarm kprobe-ftrace at %pS (%d)\n",
 		  p->addr, ret);
 	return ret;
 }
+
+static int disarm_kprobe_ftrace(struct kprobe *p)
+{
+	bool ipmodify = (p->post_handler != NULL);
+
+	return __disarm_kprobe_ftrace(p,
+		ipmodify ? &kprobe_ipmodify_ops : &kprobe_ftrace_ops,
+		ipmodify ? &kprobe_ipmodify_enabled : &kprobe_ftrace_enabled);
+}
 #else	/* !CONFIG_KPROBES_ON_FTRACE */
 #define prepare_kprobe(p)	arch_prepare_kprobe(p)
 #define arm_kprobe_ftrace(p)	(-ENODEV)

kernel/trace/ftrace.c

@@ -6036,11 +6036,7 @@ clear_func_from_hash(struct ftrace_init_func *func, struct ftrace_hash *hash)
 {
 	struct ftrace_func_entry *entry;
 
-	if (ftrace_hash_empty(hash))
-		return;
-
-	entry = __ftrace_lookup_ip(hash, func->ip);
-
+	entry = ftrace_lookup_ip(hash, func->ip);
 	/*
 	 * Do not allow this rec to match again.
 	 * Yeah, it may waste some memory, but will be removed

kernel/trace/trace.c

@@ -1854,7 +1854,7 @@ int __init register_tracer(struct tracer *type)
 	return ret;
 }
 
-void tracing_reset(struct trace_buffer *buf, int cpu)
+static void tracing_reset_cpu(struct trace_buffer *buf, int cpu)
 {
 	struct ring_buffer *buffer = buf->buffer;
 
@@ -4251,7 +4251,7 @@ static int tracing_open(struct inode *inode, struct file *file)
 		if (cpu == RING_BUFFER_ALL_CPUS)
 			tracing_reset_online_cpus(trace_buf);
 		else
-			tracing_reset(trace_buf, cpu);
+			tracing_reset_cpu(trace_buf, cpu);
 	}
 
 	if (file->f_mode & FMODE_READ) {
@@ -4815,15 +4815,15 @@ static const char readme_msg[] =
 #endif
 #endif /* CONFIG_STACK_TRACER */
 #ifdef CONFIG_DYNAMIC_EVENTS
-	"  dynamic_events\t\t- Add/remove/show the generic dynamic events\n"
+	"  dynamic_events\t\t- Create/append/remove/show the generic dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
 #ifdef CONFIG_KPROBE_EVENTS
-	"  kprobe_events\t\t- Add/remove/show the kernel dynamic events\n"
+	"  kprobe_events\t\t- Create/append/remove/show the kernel dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
 #ifdef CONFIG_UPROBE_EVENTS
-	"  uprobe_events\t\t- Add/remove/show the userspace dynamic events\n"
+	"  uprobe_events\t\t- Create/append/remove/show the userspace dynamic events\n"
 	"\t\t\t  Write into this file to define/undefine new trace events.\n"
 #endif
 #if defined(CONFIG_KPROBE_EVENTS) || defined(CONFIG_UPROBE_EVENTS)
@@ -4848,7 +4848,7 @@ static const char readme_msg[] =
 #else
 	"\t           $stack<index>, $stack, $retval, $comm,\n"
 #endif
-	"\t           +|-[u]<offset>(<fetcharg>)\n"
+	"\t           +|-[u]<offset>(<fetcharg>), \\imm-value, \\\"imm-string\"\n"
 	"\t     type: s8/16/32/64, u8/16/32/64, x8/16/32/64, string, symbol,\n"
 	"\t           b<bit-width>@<bit-offset>/<container-size>, ustring,\n"
 	"\t           <type>\\[<array-size>\\]\n"
@@ -6742,7 +6742,7 @@ tracing_snapshot_write(struct file *filp, const char __user *ubuf, size_t cnt,
 			if (iter->cpu_file == RING_BUFFER_ALL_CPUS)
 				tracing_reset_online_cpus(&tr->max_buffer);
 			else
-				tracing_reset(&tr->max_buffer, iter->cpu_file);
+				tracing_reset_cpu(&tr->max_buffer, iter->cpu_file);
 		}
 		break;
 	}

kernel/trace/trace.h

@@ -677,7 +677,6 @@ trace_buffer_iter(struct trace_iterator *iter, int cpu)
 
 int tracer_init(struct tracer *t, struct trace_array *tr);
 int tracing_is_enabled(void);
-void tracing_reset(struct trace_buffer *buf, int cpu);
 void tracing_reset_online_cpus(struct trace_buffer *buf);
 void tracing_reset_current(int cpu);
 void tracing_reset_all_online_cpus(void);

kernel/trace/trace_dynevent.c

@@ -47,6 +47,7 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type)
 			return -EINVAL;
 		event++;
 	}
+	argc--; argv++;
 
 	p = strchr(event, '/');
 	if (p) {
@@ -61,10 +62,13 @@ int dyn_event_release(int argc, char **argv, struct dyn_event_operations *type)
 	for_each_dyn_event_safe(pos, n) {
 		if (type && type != pos->ops)
 			continue;
-		if (pos->ops->match(system, event, pos)) {
-			ret = pos->ops->free(pos);
+		if (!pos->ops->match(system, event,
+				argc, (const char **)argv, pos))
+			continue;
+
+		ret = pos->ops->free(pos);
+		if (ret)
 			break;
-		}
 	}
 	mutex_unlock(&event_mutex);
 

kernel/trace/trace_dynevent.h

@@ -31,8 +31,9 @@ struct dyn_event;
  * @is_busy: Check whether given event is busy so that it can not be deleted.
  *  Return true if it is busy, otherwides false.
  * @free: Delete the given event. Return 0 if success, otherwides error.
- * @match: Check whether given event and system name match this event.
- *  Return true if it matches, otherwides false.
+ * @match: Check whether given event and system name match this event. The argc
+ *  and argv is used for exact match. Return true if it matches, otherwides
+ *  false.
  *
  * Except for @create, these methods are called under holding event_mutex.
  */
@@ -43,7 +44,7 @@ struct dyn_event_operations {
 	bool (*is_busy)(struct dyn_event *ev);
 	int (*free)(struct dyn_event *ev);
 	bool (*match)(const char *system, const char *event,
-			struct dyn_event *ev);
+		      int argc, const char **argv, struct dyn_event *ev);
 };
 
 /* Register new dyn_event type -- must be called at first */

kernel/trace/trace_events_hist.c

@@ -13,6 +13,10 @@
 #include <linux/rculist.h>
 #include <linux/tracefs.h>
 
+/* for gfp flag names */
+#include <linux/trace_events.h>
+#include <trace/events/mmflags.h>
+
 #include "tracing_map.h"
 #include "trace.h"
 #include "trace_dynevent.h"
@@ -374,7 +378,7 @@ static int synth_event_show(struct seq_file *m, struct dyn_event *ev);
 static int synth_event_release(struct dyn_event *ev);
 static bool synth_event_is_busy(struct dyn_event *ev);
 static bool synth_event_match(const char *system, const char *event,
-			      struct dyn_event *ev);
+			int argc, const char **argv, struct dyn_event *ev);
 
 static struct dyn_event_operations synth_event_ops = {
 	.create = synth_event_create,
@@ -422,7 +426,7 @@ static bool synth_event_is_busy(struct dyn_event *ev)
 }
 
 static bool synth_event_match(const char *system, const char *event,
-			      struct dyn_event *ev)
+			int argc, const char **argv, struct dyn_event *ev)
 {
 	struct synth_event *sev = to_synth_event(ev);
 
@@ -752,6 +756,8 @@ static int synth_field_size(char *type)
 		size = sizeof(unsigned long);
 	else if (strcmp(type, "pid_t") == 0)
 		size = sizeof(pid_t);
+	else if (strcmp(type, "gfp_t") == 0)
+		size = sizeof(gfp_t);
 	else if (synth_field_is_string(type))
 		size = synth_field_string_size(type);
 
@@ -792,6 +798,8 @@ static const char *synth_field_fmt(char *type)
 		fmt = "%lu";
 	else if (strcmp(type, "pid_t") == 0)
 		fmt = "%d";
+	else if (strcmp(type, "gfp_t") == 0)
+		fmt = "%x";
 	else if (synth_field_is_string(type))
 		fmt = "%s";
 
@@ -834,9 +842,20 @@ static enum print_line_t print_synth_event(struct trace_iterator *iter,
 					 i == se->n_fields - 1 ? "" : " ");
 			n_u64 += STR_VAR_LEN_MAX / sizeof(u64);
 		} else {
+			struct trace_print_flags __flags[] = {
+			    __def_gfpflag_names, {-1, NULL} };
+
 			trace_seq_printf(s, print_fmt, se->fields[i]->name,
 					 entry->fields[n_u64],
 					 i == se->n_fields - 1 ? "" : " ");
+
+			if (strcmp(se->fields[i]->type, "gfp_t") == 0) {
+				trace_seq_puts(s, " (");
+				trace_print_flags_seq(s, "|",
+						      entry->fields[n_u64],
+						      __flags);
+				trace_seq_putc(s, ')');
+			}
 			n_u64++;
 		}
 	}
@@ -2785,6 +2804,8 @@ static struct hist_field *create_alias(struct hist_trigger_data *hist_data,
 		return NULL;
 	}
 
+	alias->var_ref_idx = var_ref->var_ref_idx;
+
 	return alias;
 }
 

kernel/trace/trace_output.c

@@ -219,10 +219,10 @@ trace_print_hex_seq(struct trace_seq *p, const unsigned char *buf, int buf_len,
 {
 	int i;
 	const char *ret = trace_seq_buffer_ptr(p);
+	const char *fmt = concatenate ? "%*phN" : "%*ph";
 
-	for (i = 0; i < buf_len; i++)
-		trace_seq_printf(p, "%s%2.2x", concatenate || i == 0 ? "" : " ",
-				 buf[i]);
+	for (i = 0; i < buf_len; i += 16)
+		trace_seq_printf(p, fmt, min(buf_len - i, 16), &buf[i]);
 	trace_seq_putc(p, 0);
 
 	return ret;

kernel/trace/trace_probe.c

@@ -316,6 +316,29 @@ static int parse_probe_vars(char *arg, const struct fetch_type *t,
 	return -EINVAL;
 }
 
+static int str_to_immediate(char *str, unsigned long *imm)
+{
+	if (isdigit(str[0]))
+		return kstrtoul(str, 0, imm);
+	else if (str[0] == '-')
+		return kstrtol(str, 0, (long *)imm);
+	else if (str[0] == '+')
+		return kstrtol(str + 1, 0, (long *)imm);
+	return -EINVAL;
+}
+
+static int __parse_imm_string(char *str, char **pbuf, int offs)
+{
+	size_t len = strlen(str);
+
+	if (str[len - 1] != '"') {
+		trace_probe_log_err(offs + len, IMMSTR_NO_CLOSE);
+		return -EINVAL;
+	}
+	*pbuf = kstrndup(str, len - 1, GFP_KERNEL);
+	return 0;
+}
+
 /* Recursive argument parser */
 static int
 parse_probe_arg(char *arg, const struct fetch_type *type,
@@ -430,7 +453,8 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 			ret = parse_probe_arg(arg, t2, &code, end, flags, offs);
 			if (ret)
 				break;
-			if (code->op == FETCH_OP_COMM) {
+			if (code->op == FETCH_OP_COMM ||
+			    code->op == FETCH_OP_DATA) {
 				trace_probe_log_err(offs, COMM_CANT_DEREF);
 				return -EINVAL;
 			}
@@ -444,6 +468,21 @@ parse_probe_arg(char *arg, const struct fetch_type *type,
 			code->offset = offset;
 		}
 		break;
+	case '\\':	/* Immediate value */
+		if (arg[1] == '"') {	/* Immediate string */
+			ret = __parse_imm_string(arg + 2, &tmp, offs + 2);
+			if (ret)
+				break;
+			code->op = FETCH_OP_DATA;
+			code->data = tmp;
+		} else {
+			ret = str_to_immediate(arg + 1, &code->immediate);
+			if (ret)
+				trace_probe_log_err(offs + 1, BAD_IMM);
+			else
+				code->op = FETCH_OP_IMM;
+		}
+		break;
 	}
 	if (!ret && code->op == FETCH_OP_NOP) {
 		/* Parsed, but do not find fetch method */
@@ -542,8 +581,11 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 		}
 	}
 
-	/* Since $comm can not be dereferred, we can find $comm by strcmp */
-	if (strcmp(arg, "$comm") == 0) {
+	/*
+	 * Since $comm and immediate string can not be dereferred,
+	 * we can find those by strcmp.
+	 */
+	if (strcmp(arg, "$comm") == 0 || strncmp(arg, "\\\"", 2) == 0) {
 		/* The type of $comm must be "string", and not an array. */
 		if (parg->count || (t && strcmp(t, "string")))
 			return -EINVAL;
@@ -580,7 +622,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 	if (!strcmp(parg->type->name, "string") ||
 	    !strcmp(parg->type->name, "ustring")) {
 		if (code->op != FETCH_OP_DEREF && code->op != FETCH_OP_UDEREF &&
-		    code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM) {
+		    code->op != FETCH_OP_IMM && code->op != FETCH_OP_COMM &&
+		    code->op != FETCH_OP_DATA) {
 			trace_probe_log_err(offset + (t ? (t - arg) : 0),
 					    BAD_STRING);
 			ret = -EINVAL;
@@ -589,9 +632,10 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 		if ((code->op == FETCH_OP_IMM || code->op == FETCH_OP_COMM) ||
 		     parg->count) {
 			/*
-			 * IMM and COMM is pointing actual address, those must
-			 * be kept, and if parg->count != 0, this is an array
-			 * of string pointers instead of string address itself.
+			 * IMM, DATA and COMM is pointing actual address, those
+			 * must be kept, and if parg->count != 0, this is an
+			 * array of string pointers instead of string address
+			 * itself.
 			 */
 			code++;
 			if (code->op != FETCH_OP_NOP) {
@@ -665,7 +709,8 @@ static int traceprobe_parse_probe_arg_body(char *arg, ssize_t *size,
 fail:
 	if (ret) {
 		for (code = tmp; code < tmp + FETCH_INSN_MAX; code++)
-			if (code->op == FETCH_NOP_SYMBOL)
+			if (code->op == FETCH_NOP_SYMBOL ||
+			    code->op == FETCH_OP_DATA)
 				kfree(code->data);
 	}
 	kfree(tmp);
@@ -736,7 +781,8 @@ void traceprobe_free_probe_arg(struct probe_arg *arg)
 	struct fetch_insn *code = arg->code;
 
 	while (code && code->op != FETCH_OP_END) {
-		if (code->op == FETCH_NOP_SYMBOL)
+		if (code->op == FETCH_NOP_SYMBOL ||
+		    code->op == FETCH_OP_DATA)
 			kfree(code->data);
 		code++;
 	}
@@ -886,44 +932,85 @@ int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	return 0;
 }
 
+static void trace_probe_event_free(struct trace_probe_event *tpe)
+{
+	kfree(tpe->class.system);
+	kfree(tpe->call.name);
+	kfree(tpe->call.print_fmt);
+	kfree(tpe);
+}
+
+int trace_probe_append(struct trace_probe *tp, struct trace_probe *to)
+{
+	if (trace_probe_has_sibling(tp))
+		return -EBUSY;
+
+	list_del_init(&tp->list);
+	trace_probe_event_free(tp->event);
+
+	tp->event = to->event;
+	list_add_tail(&tp->list, trace_probe_probe_list(to));
+
+	return 0;
+}
+
+void trace_probe_unlink(struct trace_probe *tp)
+{
+	list_del_init(&tp->list);
+	if (list_empty(trace_probe_probe_list(tp)))
+		trace_probe_event_free(tp->event);
+	tp->event = NULL;
+}
 
 void trace_probe_cleanup(struct trace_probe *tp)
 {
-	struct trace_event_call *call = trace_probe_event_call(tp);
 	int i;
 
 	for (i = 0; i < tp->nr_args; i++)
 		traceprobe_free_probe_arg(&tp->args[i]);
 
-	if (call->class)
-		kfree(call->class->system);
-	kfree(call->name);
-	kfree(call->print_fmt);
+	if (tp->event)
+		trace_probe_unlink(tp);
 }
 
 int trace_probe_init(struct trace_probe *tp, const char *event,
 		     const char *group)
 {
-	struct trace_event_call *call = trace_probe_event_call(tp);
+	struct trace_event_call *call;
+	int ret = 0;
 
 	if (!event || !group)
 		return -EINVAL;
 
-	call->class = &tp->class;
-	call->name = kstrdup(event, GFP_KERNEL);
-	if (!call->name)
+	tp->event = kzalloc(sizeof(struct trace_probe_event), GFP_KERNEL);
+	if (!tp->event)
 		return -ENOMEM;
 
-	tp->class.system = kstrdup(group, GFP_KERNEL);
-	if (!tp->class.system) {
-		kfree(call->name);
-		call->name = NULL;
-		return -ENOMEM;
+	INIT_LIST_HEAD(&tp->event->files);
+	INIT_LIST_HEAD(&tp->event->class.fields);
+	INIT_LIST_HEAD(&tp->event->probes);
+	INIT_LIST_HEAD(&tp->list);
+	list_add(&tp->event->probes, &tp->list);
+
+	call = trace_probe_event_call(tp);
+	call->class = &tp->event->class;
+	call->name = kstrdup(event, GFP_KERNEL);
+	if (!call->name) {
+		ret = -ENOMEM;
+		goto error;
+	}
+
+	tp->event->class.system = kstrdup(group, GFP_KERNEL);
+	if (!tp->event->class.system) {
+		ret = -ENOMEM;
+		goto error;
 	}
-	INIT_LIST_HEAD(&tp->files);
-	INIT_LIST_HEAD(&tp->class.fields);
 
 	return 0;
+
+error:
+	trace_probe_cleanup(tp);
+	return ret;
 }
 
 int trace_probe_register_event_call(struct trace_probe *tp)
@@ -952,7 +1039,7 @@ int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file)
 
 	link->file = file;
 	INIT_LIST_HEAD(&link->list);
-	list_add_tail_rcu(&link->list, &tp->files);
+	list_add_tail_rcu(&link->list, &tp->event->files);
 	trace_probe_set_flag(tp, TP_FLAG_TRACE);
 	return 0;
 }
@@ -983,8 +1070,45 @@ int trace_probe_remove_file(struct trace_probe *tp,
 	synchronize_rcu();
 	kfree(link);
 
-	if (list_empty(&tp->files))
+	if (list_empty(&tp->event->files))
 		trace_probe_clear_flag(tp, TP_FLAG_TRACE);
 
 	return 0;
 }
+
+/*
+ * Return the smallest index of different type argument (start from 1).
+ * If all argument types and name are same, return 0.
+ */
+int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b)
+{
+	int i;
+
+	for (i = 0; i < a->nr_args; i++) {
+		if ((b->nr_args <= i) ||
+		    ((a->args[i].type != b->args[i].type) ||
+		     (a->args[i].count != b->args[i].count) ||
+		     strcmp(a->args[i].name, b->args[i].name)))
+			return i + 1;
+	}
+
+	return 0;
+}
+
+bool trace_probe_match_command_args(struct trace_probe *tp,
+				    int argc, const char **argv)
+{
+	char buf[MAX_ARGSTR_LEN + 1];
+	int i;
+
+	if (tp->nr_args < argc)
+		return false;
+
+	for (i = 0; i < argc; i++) {
+		snprintf(buf, sizeof(buf), "%s=%s",
+			 tp->args[i].name, tp->args[i].comm);
+		if (strcmp(buf, argv[i]))
+			return false;
+	}
+	return true;
+}

kernel/trace/trace_probe.h

@@ -89,6 +89,7 @@ enum fetch_op {
 	FETCH_OP_COMM,		/* Current comm */
 	FETCH_OP_ARG,		/* Function argument : .param */
 	FETCH_OP_FOFFS,		/* File offset: .immediate */
+	FETCH_OP_DATA,		/* Allocated data: .data */
 	// Stage 2 (dereference) op
 	FETCH_OP_DEREF,		/* Dereference: .offset */
 	FETCH_OP_UDEREF,	/* User-space Dereference: .offset */
@@ -222,11 +223,18 @@ struct probe_arg {
 	const struct fetch_type	*type;	/* Type of this argument */
 };
 
-struct trace_probe {
+/* Event call and class holder */
+struct trace_probe_event {
 	unsigned int			flags;	/* For TP_FLAG_* */
 	struct trace_event_class	class;
 	struct trace_event_call		call;
 	struct list_head 		files;
+	struct list_head		probes;
+};
+
+struct trace_probe {
+	struct list_head		list;
+	struct trace_probe_event	*event;
 	ssize_t				size;	/* trace entry size */
 	unsigned int			nr_args;
 	struct probe_arg		args[];
@@ -240,19 +248,19 @@ struct event_file_link {
 static inline bool trace_probe_test_flag(struct trace_probe *tp,
 					 unsigned int flag)
 {
-	return !!(tp->flags & flag);
+	return !!(tp->event->flags & flag);
 }
 
 static inline void trace_probe_set_flag(struct trace_probe *tp,
 					unsigned int flag)
 {
-	tp->flags |= flag;
+	tp->event->flags |= flag;
 }
 
 static inline void trace_probe_clear_flag(struct trace_probe *tp,
 					  unsigned int flag)
 {
-	tp->flags &= ~flag;
+	tp->event->flags &= ~flag;
 }
 
 static inline bool trace_probe_is_enabled(struct trace_probe *tp)
@@ -262,45 +270,76 @@ static inline bool trace_probe_is_enabled(struct trace_probe *tp)
 
 static inline const char *trace_probe_name(struct trace_probe *tp)
 {
-	return trace_event_name(&tp->call);
+	return trace_event_name(&tp->event->call);
 }
 
 static inline const char *trace_probe_group_name(struct trace_probe *tp)
 {
-	return tp->call.class->system;
+	return tp->event->call.class->system;
 }
 
 static inline struct trace_event_call *
 	trace_probe_event_call(struct trace_probe *tp)
 {
-	return &tp->call;
+	return &tp->event->call;
+}
+
+static inline struct trace_probe_event *
+trace_probe_event_from_call(struct trace_event_call *event_call)
+{
+	return container_of(event_call, struct trace_probe_event, call);
+}
+
+static inline struct trace_probe *
+trace_probe_primary_from_call(struct trace_event_call *call)
+{
+	struct trace_probe_event *tpe = trace_probe_event_from_call(call);
+
+	return list_first_entry(&tpe->probes, struct trace_probe, list);
+}
+
+static inline struct list_head *trace_probe_probe_list(struct trace_probe *tp)
+{
+	return &tp->event->probes;
+}
+
+static inline bool trace_probe_has_sibling(struct trace_probe *tp)
+{
+	struct list_head *list = trace_probe_probe_list(tp);
+
+	return !list_empty(list) && !list_is_singular(list);
 }
 
 static inline int trace_probe_unregister_event_call(struct trace_probe *tp)
 {
 	/* tp->event is unregistered in trace_remove_event_call() */
-	return trace_remove_event_call(&tp->call);
+	return trace_remove_event_call(&tp->event->call);
 }
 
 static inline bool trace_probe_has_single_file(struct trace_probe *tp)
 {
-	return !!list_is_singular(&tp->files);
+	return !!list_is_singular(&tp->event->files);
 }
 
 int trace_probe_init(struct trace_probe *tp, const char *event,
 		     const char *group);
 void trace_probe_cleanup(struct trace_probe *tp);
+int trace_probe_append(struct trace_probe *tp, struct trace_probe *to);
+void trace_probe_unlink(struct trace_probe *tp);
 int trace_probe_register_event_call(struct trace_probe *tp);
 int trace_probe_add_file(struct trace_probe *tp, struct trace_event_file *file);
 int trace_probe_remove_file(struct trace_probe *tp,
 			    struct trace_event_file *file);
 struct event_file_link *trace_probe_get_file_link(struct trace_probe *tp,
 						struct trace_event_file *file);
+int trace_probe_compare_arg_type(struct trace_probe *a, struct trace_probe *b);
+bool trace_probe_match_command_args(struct trace_probe *tp,
+				    int argc, const char **argv);
 
 #define trace_probe_for_each_link(pos, tp)	\
-	list_for_each_entry(pos, &(tp)->files, list)
+	list_for_each_entry(pos, &(tp)->event->files, list)
 #define trace_probe_for_each_link_rcu(pos, tp)	\
-	list_for_each_entry_rcu(pos, &(tp)->files, list)
+	list_for_each_entry_rcu(pos, &(tp)->event->files, list)
 
 /* Check the name is good for event/group/fields */
 static inline bool is_good_name(const char *name)
@@ -370,6 +409,8 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(BAD_VAR,		"Invalid $-valiable specified"),	\
 	C(BAD_REG_NAME,		"Invalid register name"),		\
 	C(BAD_MEM_ADDR,		"Invalid memory address"),		\
+	C(BAD_IMM,		"Invalid immediate value"),		\
+	C(IMMSTR_NO_CLOSE,	"String is not closed with '\"'"),	\
 	C(FILE_ON_KPROBE,	"File offset is not available with kprobe"), \
 	C(BAD_FILE_OFFS,	"Invalid file offset value"),		\
 	C(SYM_ON_UPROBE,	"Symbol is not available with uprobe"),	\
@@ -393,7 +434,10 @@ extern int traceprobe_define_arg_fields(struct trace_event_call *event_call,
 	C(ARG_TOO_LONG,		"Argument expression is too long"),	\
 	C(NO_ARG_BODY,		"No argument expression"),		\
 	C(BAD_INSN_BNDRY,	"Probe point is not an instruction boundary"),\
-	C(FAIL_REG_PROBE,	"Failed to register probe event"),
+	C(FAIL_REG_PROBE,	"Failed to register probe event"),\
+	C(DIFF_PROBE_TYPE,	"Probe type is different from existing probe"),\
+	C(DIFF_ARG_TYPE,	"Argument type or name is different from existing probe"),\
+	C(SAME_PROBE,		"There is already the exact same probe event"),
 
 #undef C
 #define C(a, b)		TP_ERR_##a

kernel/trace/trace_stack.c

@@ -53,6 +53,104 @@ static void print_max_stack(void)
 	}
 }
 
+/*
+ * The stack tracer looks for a maximum stack at each call from a function. It
+ * registers a callback from ftrace, and in that callback it examines the stack
+ * size. It determines the stack size from the variable passed in, which is the
+ * address of a local variable in the stack_trace_call() callback function.
+ * The stack size is calculated by the address of the local variable to the top
+ * of the current stack. If that size is smaller than the currently saved max
+ * stack size, nothing more is done.
+ *
+ * If the size of the stack is greater than the maximum recorded size, then the
+ * following algorithm takes place.
+ *
+ * For architectures (like x86) that store the function's return address before
+ * saving the function's local variables, the stack will look something like
+ * this:
+ *
+ *   [ top of stack ]
+ *    0: sys call entry frame
+ *   10: return addr to entry code
+ *   11: start of sys_foo frame
+ *   20: return addr to sys_foo
+ *   21: start of kernel_func_bar frame
+ *   30: return addr to kernel_func_bar
+ *   31: [ do trace stack here ]
+ *
+ * The save_stack_trace() is called returning all the functions it finds in the
+ * current stack. Which would be (from the bottom of the stack to the top):
+ *
+ *   return addr to kernel_func_bar
+ *   return addr to sys_foo
+ *   return addr to entry code
+ *
+ * Now to figure out how much each of these functions' local variable size is,
+ * a search of the stack is made to find these values. When a match is made, it
+ * is added to the stack_dump_trace[] array. The offset into the stack is saved
+ * in the stack_trace_index[] array. The above example would show:
+ *
+ *        stack_dump_trace[]        |   stack_trace_index[]
+ *        ------------------        +   -------------------
+ *  return addr to kernel_func_bar  |          30
+ *  return addr to sys_foo          |          20
+ *  return addr to entry            |          10
+ *
+ * The print_max_stack() function above, uses these values to print the size of
+ * each function's portion of the stack.
+ *
+ *  for (i = 0; i < nr_entries; i++) {
+ *     size = i == nr_entries - 1 ? stack_trace_index[i] :
+ *                    stack_trace_index[i] - stack_trace_index[i+1]
+ *     print "%d %d %d %s\n", i, stack_trace_index[i], size, stack_dump_trace[i]);
+ *  }
+ *
+ * The above shows
+ *
+ *     depth size  location
+ *     ----- ----  --------
+ *  0    30   10   kernel_func_bar
+ *  1    20   10   sys_foo
+ *  2    10   10   entry code
+ *
+ * Now for architectures that might save the return address after the functions
+ * local variables (saving the link register before calling nested functions),
+ * this will cause the stack to look a little different:
+ *
+ * [ top of stack ]
+ *  0: sys call entry frame
+ * 10: start of sys_foo_frame
+ * 19: return addr to entry code << lr saved before calling kernel_func_bar
+ * 20: start of kernel_func_bar frame
+ * 29: return addr to sys_foo_frame << lr saved before calling next function
+ * 30: [ do trace stack here ]
+ *
+ * Although the functions returned by save_stack_trace() may be the same, the
+ * placement in the stack will be different. Using the same algorithm as above
+ * would yield:
+ *
+ *        stack_dump_trace[]        |   stack_trace_index[]
+ *        ------------------        +   -------------------
+ *  return addr to kernel_func_bar  |          30
+ *  return addr to sys_foo          |          29
+ *  return addr to entry            |          19
+ *
+ * Where the mapping is off by one:
+ *
+ *   kernel_func_bar stack frame size is 29 - 19 not 30 - 29!
+ *
+ * To fix this, if the architecture sets ARCH_RET_ADDR_AFTER_LOCAL_VARS the
+ * values in stack_trace_index[] are shifted by one to and the number of
+ * stack trace entries is decremented by one.
+ *
+ *        stack_dump_trace[]        |   stack_trace_index[]
+ *        ------------------        +   -------------------
+ *  return addr to kernel_func_bar  |          29
+ *  return addr to sys_foo          |          19
+ *
+ * Although the entry function is not displayed, the first function (sys_foo)
+ * will still include the stack size of it.
+ */
 static void check_stack(unsigned long ip, unsigned long *stack)
 {
 	unsigned long this_size, flags; unsigned long *p, *top, *start;
@@ -158,6 +256,20 @@ static void check_stack(unsigned long ip, unsigned long *stack)
 			i++;
 	}
 
+#ifdef ARCH_FTRACE_SHIFT_STACK_TRACER
+	/*
+	 * Some archs will store the link register before calling
+	 * nested functions. This means the saved return address
+	 * comes after the local storage, and we need to shift
+	 * for that.
+	 */
+	if (x > 1) {
+		memmove(&stack_trace_index[0], &stack_trace_index[1],
+			sizeof(stack_trace_index[0]) * (x - 1));
+		x--;
+	}
+#endif
+
 	stack_trace_nr_entries = x;
 
 	if (task_stack_end_corrupted(current)) {

scripts/recordmcount.h

@@ -174,7 +174,7 @@ static int MIPS_is_fake_mcount(Elf_Rel const *rp)
 }
 
 /* Append the new shstrtab, Elf_Shdr[], __mcount_loc and its relocations. */
-static void append_func(Elf_Ehdr *const ehdr,
+static int append_func(Elf_Ehdr *const ehdr,
 			Elf_Shdr *const shstr,
 			uint_t const *const mloc0,
 			uint_t const *const mlocp,
@@ -202,15 +202,20 @@ static void append_func(Elf_Ehdr *const ehdr,
 	new_e_shoff = t;
 
 	/* body for new shstrtab */
-	ulseek(fd_map, sb.st_size, SEEK_SET);
-	uwrite(fd_map, old_shstr_sh_offset + (void *)ehdr, old_shstr_sh_size);
-	uwrite(fd_map, mc_name, 1 + strlen(mc_name));
+	if (ulseek(sb.st_size, SEEK_SET) < 0)
+		return -1;
+	if (uwrite(old_shstr_sh_offset + (void *)ehdr, old_shstr_sh_size) < 0)
+		return -1;
+	if (uwrite(mc_name, 1 + strlen(mc_name)) < 0)
+		return -1;
 
 	/* old(modified) Elf_Shdr table, word-byte aligned */
-	ulseek(fd_map, t, SEEK_SET);
+	if (ulseek(t, SEEK_SET) < 0)
+		return -1;
 	t += sizeof(Elf_Shdr) * old_shnum;
-	uwrite(fd_map, old_shoff + (void *)ehdr,
-	       sizeof(Elf_Shdr) * old_shnum);
+	if (uwrite(old_shoff + (void *)ehdr,
+	       sizeof(Elf_Shdr) * old_shnum) < 0)
+		return -1;
 
 	/* new sections __mcount_loc and .rel__mcount_loc */
 	t += 2*sizeof(mcsec);
@@ -225,7 +230,8 @@ static void append_func(Elf_Ehdr *const ehdr,
 	mcsec.sh_info = 0;
 	mcsec.sh_addralign = _w(_size);
 	mcsec.sh_entsize = _w(_size);
-	uwrite(fd_map, &mcsec, sizeof(mcsec));
+	if (uwrite(&mcsec, sizeof(mcsec)) < 0)
+		return -1;
 
 	mcsec.sh_name = w(old_shstr_sh_size);
 	mcsec.sh_type = (sizeof(Elf_Rela) == rel_entsize)
@@ -239,15 +245,22 @@ static void append_func(Elf_Ehdr *const ehdr,
 	mcsec.sh_info = w(old_shnum);
 	mcsec.sh_addralign = _w(_size);
 	mcsec.sh_entsize = _w(rel_entsize);
-	uwrite(fd_map, &mcsec, sizeof(mcsec));
 
-	uwrite(fd_map, mloc0, (void *)mlocp - (void *)mloc0);
-	uwrite(fd_map, mrel0, (void *)mrelp - (void *)mrel0);
+	if (uwrite(&mcsec, sizeof(mcsec)) < 0)
+		return -1;
+
+	if (uwrite(mloc0, (void *)mlocp - (void *)mloc0) < 0)
+		return -1;
+	if (uwrite(mrel0, (void *)mrelp - (void *)mrel0) < 0)
+		return -1;
 
 	ehdr->e_shoff = _w(new_e_shoff);
 	ehdr->e_shnum = w2(2 + w2(ehdr->e_shnum));  /* {.rel,}__mcount_loc */
-	ulseek(fd_map, 0, SEEK_SET);
-	uwrite(fd_map, ehdr, sizeof(*ehdr));
+	if (ulseek(0, SEEK_SET) < 0)
+		return -1;
+	if (uwrite(ehdr, sizeof(*ehdr)) < 0)
+		return -1;
+	return 0;
 }
 
 static unsigned get_mcountsym(Elf_Sym const *const sym0,
@@ -351,9 +364,9 @@ static uint_t *sift_rel_mcount(uint_t *mlocp,
  * that are not going to be traced. The mcount calls here will be converted
  * into nops.
  */
-static void nop_mcount(Elf_Shdr const *const relhdr,
-		       Elf_Ehdr const *const ehdr,
-		       const char *const txtname)
+static int nop_mcount(Elf_Shdr const *const relhdr,
+		      Elf_Ehdr const *const ehdr,
+		      const char *const txtname)
 {
 	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
 		+ (void *)ehdr);
@@ -376,15 +389,18 @@ static void nop_mcount(Elf_Shdr const *const relhdr,
 			mcountsym = get_mcountsym(sym0, relp, str0);
 
 		if (mcountsym == Elf_r_sym(relp) && !is_fake_mcount(relp)) {
-			if (make_nop)
+			if (make_nop) {
 				ret = make_nop((void *)ehdr, _w(shdr->sh_offset) + _w(relp->r_offset));
+				if (ret < 0)
+					return -1;
+			}
 			if (warn_on_notrace_sect && !once) {
 				printf("Section %s has mcount callers being ignored\n",
 				       txtname);
 				once = 1;
 				/* just warn? */
 				if (!make_nop)
-					return;
+					return 0;
 			}
 		}
 
@@ -396,14 +412,16 @@ static void nop_mcount(Elf_Shdr const *const relhdr,
 			Elf_Rel rel;
 			rel = *(Elf_Rel *)relp;
 			Elf_r_info(&rel, Elf_r_sym(relp), rel_type_nop);
-			ulseek(fd_map, (void *)relp - (void *)ehdr, SEEK_SET);
-			uwrite(fd_map, &rel, sizeof(rel));
+			if (ulseek((void *)relp - (void *)ehdr, SEEK_SET) < 0)
+				return -1;
+			if (uwrite(&rel, sizeof(rel)) < 0)
+				return -1;
 		}
 		relp = (Elf_Rel const *)(rel_entsize + (void *)relp);
 	}
+	return 0;
 }
 
-
 /*
  * Find a symbol in the given section, to be used as the base for relocating
  * the table of offsets of calls to mcount.  A local or global symbol suffices,
@@ -414,9 +432,10 @@ static void nop_mcount(Elf_Shdr const *const relhdr,
  *    Num:    Value  Size Type    Bind   Vis      Ndx Name
  *      2: 00000000     0 SECTION LOCAL  DEFAULT    1
  */
-static unsigned find_secsym_ndx(unsigned const txtndx,
+static int find_secsym_ndx(unsigned const txtndx,
 				char const *const txtname,
 				uint_t *const recvalp,
+				unsigned int *sym_index,
 				Elf_Shdr const *const symhdr,
 				Elf_Ehdr const *const ehdr)
 {
@@ -438,21 +457,20 @@ static unsigned find_secsym_ndx(unsigned const txtndx,
 				continue;
 
 			*recvalp = _w(symp->st_value);
-			return symp - sym0;
+			*sym_index = symp - sym0;
+			return 0;
 		}
 	}
 	fprintf(stderr, "Cannot find symbol for section %u: %s.\n",
 		txtndx, txtname);
-	fail_file();
+	return -1;
 }
 
-
 /* Evade ISO C restriction: no declaration after statement in has_rel_mcount. */
-static char const *
-__has_rel_mcount(Elf_Shdr const *const relhdr,  /* is SHT_REL or SHT_RELA */
-		 Elf_Shdr const *const shdr0,
-		 char const *const shstrtab,
-		 char const *const fname)
+static char const * __has_rel_mcount(Elf_Shdr const *const relhdr, /* reltype */
+				     Elf_Shdr const *const shdr0,
+				     char const *const shstrtab,
+				     char const *const fname)
 {
 	/* .sh_info depends on .sh_type == SHT_REL[,A] */
 	Elf_Shdr const *const txthdr = &shdr0[w(relhdr->sh_info)];
@@ -461,7 +479,7 @@ __has_rel_mcount(Elf_Shdr const *const relhdr,  /* is SHT_REL or SHT_RELA */
 	if (strcmp("__mcount_loc", txtname) == 0) {
 		fprintf(stderr, "warning: __mcount_loc already exists: %s\n",
 			fname);
-		succeed_file();
+		return already_has_rel_mcount;
 	}
 	if (w(txthdr->sh_type) != SHT_PROGBITS ||
 	    !(_w(txthdr->sh_flags) & SHF_EXECINSTR))
@@ -491,6 +509,10 @@ static unsigned tot_relsize(Elf_Shdr const *const shdr0,
 
 	for (; nhdr; --nhdr, ++shdrp) {
 		txtname = has_rel_mcount(shdrp, shdr0, shstrtab, fname);
+		if (txtname == already_has_rel_mcount) {
+			totrelsz = 0;
+			break;
+		}
 		if (txtname && is_mcounted_section_name(txtname))
 			totrelsz += _w(shdrp->sh_size);
 	}
@@ -499,8 +521,8 @@ static unsigned tot_relsize(Elf_Shdr const *const shdr0,
 
 
 /* Overall supervision for Elf32 ET_REL file. */
-static void
-do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
+static int do_func(Elf_Ehdr *const ehdr, char const *const fname,
+		   unsigned const reltype)
 {
 	Elf_Shdr *const shdr0 = (Elf_Shdr *)(_w(ehdr->e_shoff)
 		+ (void *)ehdr);
@@ -513,26 +535,54 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 	unsigned k;
 
 	/* Upper bound on space: assume all relevant relocs are for mcount. */
-	unsigned const totrelsz = tot_relsize(shdr0, nhdr, shstrtab, fname);
-	Elf_Rel *const mrel0 = umalloc(totrelsz);
-	Elf_Rel *      mrelp = mrel0;
+	unsigned       totrelsz;
 
-	/* 2*sizeof(address) <= sizeof(Elf_Rel) */
-	uint_t *const mloc0 = umalloc(totrelsz>>1);
-	uint_t *      mlocp = mloc0;
+	Elf_Rel *      mrel0;
+	Elf_Rel *      mrelp;
+
+	uint_t *      mloc0;
+	uint_t *      mlocp;
 
 	unsigned rel_entsize = 0;
 	unsigned symsec_sh_link = 0;
 
+	int result = 0;
+
+	totrelsz = tot_relsize(shdr0, nhdr, shstrtab, fname);
+	if (totrelsz == 0)
+		return 0;
+	mrel0 = umalloc(totrelsz);
+	mrelp = mrel0;
+	if (!mrel0)
+		return -1;
+
+	/* 2*sizeof(address) <= sizeof(Elf_Rel) */
+	mloc0 = umalloc(totrelsz>>1);
+	mlocp = mloc0;
+	if (!mloc0) {
+		free(mrel0);
+		return -1;
+	}
+
 	for (relhdr = shdr0, k = nhdr; k; --k, ++relhdr) {
 		char const *const txtname = has_rel_mcount(relhdr, shdr0,
 			shstrtab, fname);
+		if (txtname == already_has_rel_mcount) {
+			result = 0;
+			file_updated = 0;
+			goto out; /* Nothing to be done; don't append! */
+		}
 		if (txtname && is_mcounted_section_name(txtname)) {
+			unsigned int recsym;
 			uint_t recval = 0;
-			unsigned const recsym = find_secsym_ndx(
-				w(relhdr->sh_info), txtname, &recval,
-				&shdr0[symsec_sh_link = w(relhdr->sh_link)],
-				ehdr);
+
+			symsec_sh_link = w(relhdr->sh_link);
+			result = find_secsym_ndx(w(relhdr->sh_info), txtname,
+						&recval, &recsym,
+						&shdr0[symsec_sh_link],
+						ehdr);
+			if (result)
+				goto out;
 
 			rel_entsize = _w(relhdr->sh_entsize);
 			mlocp = sift_rel_mcount(mlocp,
@@ -543,13 +593,17 @@ do_func(Elf_Ehdr *const ehdr, char const *const fname, unsigned const reltype)
 			 * This section is ignored by ftrace, but still
 			 * has mcount calls. Convert them to nops now.
 			 */
-			nop_mcount(relhdr, ehdr, txtname);
+			if (nop_mcount(relhdr, ehdr, txtname) < 0) {
+				result = -1;
+				goto out;
+			}
 		}
 	}
-	if (mloc0 != mlocp) {
-		append_func(ehdr, shstr, mloc0, mlocp, mrel0, mrelp,
-			    rel_entsize, symsec_sh_link);
-	}
+	if (!result && mloc0 != mlocp)
+		result = append_func(ehdr, shstr, mloc0, mlocp, mrel0, mrelp,
+				     rel_entsize, symsec_sh_link);
+out:
 	free(mrel0);
 	free(mloc0);
+	return result;
 }

tools/testing/selftests/ftrace/test.d/functions

@@ -115,7 +115,7 @@ ftrace_errlog_check() { # err-prefix command-with-error-pos-by-^ command-file
     command=$(echo "$2" | tr -d ^)
     echo "Test command: $command"
     echo > error_log
-    (! echo "$command" > "$3" ) 2> /dev/null
+    (! echo "$command" >> "$3" ) 2> /dev/null
     grep "$1: error:" -A 3 error_log
     N=$(tail -n 1 error_log | wc -c)
     # "  Command: " and "^\n" => 13

tools/testing/selftests/ftrace/test.d/kprobe/kprobe_eventname.tc

@@ -24,7 +24,21 @@ test -d events/kprobes2/event2 || exit_failure
 
 :;: "Add an event on dot function without name" ;:
 
-FUNC=`grep -m 10 " [tT] .*\.isra\..*$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "`
+find_dot_func() {
+	if [ ! -f available_filter_functions ]; then
+		grep -m 10 " [tT] .*\.isra\..*$" /proc/kallsyms | tail -n 1 | cut -f 3 -d " "
+		return;
+	fi
+
+	grep " [tT] .*\.isra\..*" /proc/kallsyms | cut -f 3 -d " " | while read f; do
+		if grep -s $f available_filter_functions; then
+			echo $f
+			break
+		fi
+	done
+}
+
+FUNC=`find_dot_func | tail -n 1`
 [ "x" != "x$FUNC" ] || exit_unresolved
 echo "p $FUNC" > kprobe_events
 EVENT=`grep $FUNC kprobe_events | cut -f 1 -d " " | cut -f 2 -d:`

tools/testing/selftests/ftrace/test.d/kprobe/kprobe_multiprobe.tc

+#!/bin/sh
+# SPDX-License-Identifier: GPL-2.0
+# description: Create/delete multiprobe on kprobe event
+
+[ -f kprobe_events ] || exit_unsupported
+
+grep -q "Create/append/" README || exit_unsupported
+
+# Choose 2 symbols for target
+SYM1=_do_fork
+SYM2=do_exit
+EVENT_NAME=kprobes/testevent
+
+DEF1="p:$EVENT_NAME $SYM1"
+DEF2="p:$EVENT_NAME $SYM2"
+
+:;: "Define an event which has 2 probes" ;:
+echo $DEF1 >> kprobe_events
+echo $DEF2 >> kprobe_events
+cat kprobe_events | grep "$DEF1"
+cat kprobe_events | grep "$DEF2"
+
+:;: "Remove the event by name (should remove both)" ;:
+echo "-:$EVENT_NAME" >> kprobe_events
+test `cat kprobe_events | wc -l` -eq 0
+
+:;: "Remove just 1 event" ;:
+echo $DEF1 >> kprobe_events
+echo $DEF2 >> kprobe_events
+echo "-:$EVENT_NAME $SYM1" >> kprobe_events
+! cat kprobe_events | grep "$DEF1"
+cat kprobe_events | grep "$DEF2"
+
+:;: "Appending different type must fail" ;:
+! echo "$DEF1 \$stack" >> kprobe_events

tools/testing/selftests/ftrace/test.d/kprobe/kprobe_syntax_errors.tc

@@ -41,6 +41,11 @@ check_error 'p vfs_read ^%none_reg'	# BAD_REG_NAME
 check_error 'p vfs_read ^@12345678abcde'	# BAD_MEM_ADDR
 check_error 'p vfs_read ^@+10'		# FILE_ON_KPROBE
 
+grep -q "imm-value" README && \
+check_error 'p vfs_read arg1=\^x'	# BAD_IMM
+grep -q "imm-string" README && \
+check_error 'p vfs_read arg1=\"abcd^'	# IMMSTR_NO_CLOSE
+
 check_error 'p vfs_read ^+0@0)'		# DEREF_NEED_BRACE
 check_error 'p vfs_read ^+0ab1(@0)'	# BAD_DEREF_OFFS
 check_error 'p vfs_read +0(+0(@0^)'	# DEREF_OPEN_BRACE
@@ -82,4 +87,15 @@ case $(uname -m) in
     ;;
 esac
 
+# multiprobe errors
+if grep -q "Create/append/" README && grep -q "imm-value" README; then
+echo 'p:kprobes/testevent _do_fork' > kprobe_events
+check_error '^r:kprobes/testevent do_exit'	# DIFF_PROBE_TYPE
+echo 'p:kprobes/testevent _do_fork abcd=\1' > kprobe_events
+check_error 'p:kprobes/testevent _do_fork ^bcd=\1'	# DIFF_ARG_TYPE
+check_error 'p:kprobes/testevent _do_fork ^abcd=\1:u8'	# DIFF_ARG_TYPE
+check_error 'p:kprobes/testevent _do_fork ^abcd=\"foo"'	# DIFF_ARG_TYPE
+check_error '^p:kprobes/testevent _do_fork'	# SAME_PROBE
+fi
+
 exit 0