Merge tag 'ftrace-v6.14' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace

Pull ftrace updates from Steven Rostedt:

 - Have fprobes built on top of function graph infrastructure

   The fprobe logic is an optimized kprobe that uses ftrace to attach to
   functions when a probe is needed at the start or end of the function.
   The fprobe and kretprobe logic implements a similar method as the
   function graph tracer to trace the end of the function. That is to
   hijack the return address and jump to a trampoline to do the trace
   when the function exits. To do this, a shadow stack needs to be
   created to store the original return address. Fprobes and function
   graph do this slightly differently. Fprobes (and kretprobes) has
   slots per callsite that are reserved to save the return address. This
   is fine when just a few points are traced. But users of fprobes, such
   as BPF programs, are starting to add many more locations, and this
   method does not scale.

   The function graph tracer was created to trace all functions in the
   kernel. In order to do this, when function graph tracing is started,
   every task gets its own shadow stack to hold the return address that
   is going to be traced. The function graph tracer has been updated to
   allow multiple users to use its infrastructure. Now have fprobes be
   one of those users. This will also allow for the fprobe and kretprobe
   methods to trace the return address to become obsolete. With new
   technologies like CFI that need to know about these methods of
   hijacking the return address, going toward a solution that has only
   one method of doing this will make the kernel less complex.

 - Cleanup with guard() and free() helpers

   There were several places in the code that had a lot of "goto out" in
   the error paths to either unlock a lock or free some memory that was
   allocated. But this is error prone. Convert the code over to use the
   guard() and free() helpers that let the compiler unlock locks or free
   memory when the function exits.

 - Remove disabling of interrupts in the function graph tracer

   When function graph tracer was first introduced, it could race with
   interrupts and NMIs. To prevent that race, it would disable
   interrupts and not trace NMIs. But the code has changed to allow NMIs
   and also interrupts. This change was done a long time ago, but the
   disabling of interrupts was never removed. Remove the disabling of
   interrupts in the function graph tracer is it is not needed. This
   greatly improves its performance.

 - Allow the :mod: command to enable tracing module functions on the
   kernel command line.

   The function tracer already has a way to enable functions to be
   traced in modules by writing ":mod:<module>" into set_ftrace_filter.
   That will enable either all the functions for the module if it is
   loaded, or if it is not, it will cache that command, and when the
   module is loaded that matches <module>, its functions will be
   enabled. This also allows init functions to be traced. But currently
   events do not have that feature.

   Because enabling function tracing can be done very early at boot up
   (before scheduling is enabled), the commands that can be done when
   function tracing is started is limited. Having the ":mod:" command to
   trace module functions as they are loaded is very useful. Update the
   kernel command line function filtering to allow it.

* tag 'ftrace-v6.14' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace: (26 commits)
  ftrace: Implement :mod: cache filtering on kernel command line
  tracing: Adopt __free() and guard() for trace_fprobe.c
  bpf: Use ftrace_get_symaddr() for kprobe_multi probes
  ftrace: Add ftrace_get_symaddr to convert fentry_ip to symaddr
  Documentation: probes: Update fprobe on function-graph tracer
  selftests/ftrace: Add a test case for repeating register/unregister fprobe
  selftests: ftrace: Remove obsolate maxactive syntax check
  tracing/fprobe: Remove nr_maxactive from fprobe
  fprobe: Add fprobe_header encoding feature
  fprobe: Rewrite fprobe on function-graph tracer
  s390/tracing: Enable HAVE_FTRACE_GRAPH_FUNC
  ftrace: Add CONFIG_HAVE_FTRACE_GRAPH_FUNC
  bpf: Enable kprobe_multi feature if CONFIG_FPROBE is enabled
  tracing/fprobe: Enable fprobe events with CONFIG_DYNAMIC_FTRACE_WITH_ARGS
  tracing: Add ftrace_fill_perf_regs() for perf event
  tracing: Add ftrace_partial_regs() for converting ftrace_regs to pt_regs
  fprobe: Use ftrace_regs in fprobe exit handler
  fprobe: Use ftrace_regs in fprobe entry handler
  fgraph: Pass ftrace_regs to retfunc
  fgraph: Replace fgraph_ret_regs with ftrace_regs
  ...

1 files changed, 107 insertions, 96 deletions

diff --git a/kernel/trace/ftrace.c b/kernel/trace/ftrace.c
index 2e113f8b13a2..b2955e504193 100644
--- a/kernel/trace/ftrace.c
+++ b/kernel/trace/ftrace.c
@@ -536,24 +536,21 @@ static int function_stat_show(struct seq_file *m, void *v)
 {
 	struct ftrace_profile *rec = v;
 	char str[KSYM_SYMBOL_LEN];
-	int ret = 0;
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	static struct trace_seq s;
 	unsigned long long avg;
 	unsigned long long stddev;
 #endif
-	mutex_lock(&ftrace_profile_lock);
+	guard(mutex)(&ftrace_profile_lock);
 
 	/* we raced with function_profile_reset() */
-	if (unlikely(rec->counter == 0)) {
-		ret = -EBUSY;
-		goto out;
-	}
+	if (unlikely(rec->counter == 0))
+		return -EBUSY;
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
 	avg = div64_ul(rec->time, rec->counter);
 	if (tracing_thresh && (avg < tracing_thresh))
-		goto out;
+		return 0;
 #endif
 
 	kallsyms_lookup(rec->ip, NULL, NULL, NULL, str);
@@ -590,10 +587,8 @@ static int function_stat_show(struct seq_file *m, void *v)
 	trace_print_seq(m, &s);
 #endif
 	seq_putc(m, '\n');
-out:
-	mutex_unlock(&ftrace_profile_lock);
 
-	return ret;
+	return 0;
 }
 
 static void ftrace_profile_reset(struct ftrace_profile_stat *stat)
@@ -789,27 +784,24 @@ function_profile_call(unsigned long ip, unsigned long parent_ip,
 {
 	struct ftrace_profile_stat *stat;
 	struct ftrace_profile *rec;
-	unsigned long flags;
 
 	if (!ftrace_profile_enabled)
 		return;
 
-	local_irq_save(flags);
+	guard(preempt_notrace)();
 
 	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
-		goto out;
+		return;
 
 	rec = ftrace_find_profiled_func(stat, ip);
 	if (!rec) {
 		rec = ftrace_profile_alloc(stat, ip);
 		if (!rec)
-			goto out;
+			return;
 	}
 
 	rec->counter++;
- out:
-	local_irq_restore(flags);
 }
 
 #ifdef CONFIG_FUNCTION_GRAPH_TRACER
@@ -827,7 +819,8 @@ struct profile_fgraph_data {
 };
 
 static int profile_graph_entry(struct ftrace_graph_ent *trace,
-			       struct fgraph_ops *gops)
+			       struct fgraph_ops *gops,
+			       struct ftrace_regs *fregs)
 {
 	struct profile_fgraph_data *profile_data;
 
@@ -849,26 +842,27 @@ static int profile_graph_entry(struct ftrace_graph_ent *trace,
 }
 
 static void profile_graph_return(struct ftrace_graph_ret *trace,
-				 struct fgraph_ops *gops)
+				 struct fgraph_ops *gops,
+				 struct ftrace_regs *fregs)
 {
 	struct profile_fgraph_data *profile_data;
 	struct ftrace_profile_stat *stat;
 	unsigned long long calltime;
 	unsigned long long rettime = trace_clock_local();
 	struct ftrace_profile *rec;
-	unsigned long flags;
 	int size;
 
-	local_irq_save(flags);
+	guard(preempt_notrace)();
+
 	stat = this_cpu_ptr(&ftrace_profile_stats);
 	if (!stat->hash || !ftrace_profile_enabled)
-		goto out;
+		return;
 
 	profile_data = fgraph_retrieve_data(gops->idx, &size);
 
 	/* If the calltime was zero'd ignore it */
 	if (!profile_data || !profile_data->calltime)
-		goto out;
+		return;
 
 	calltime = rettime - profile_data->calltime;
 
@@ -896,9 +890,6 @@ static void profile_graph_return(struct ftrace_graph_ret *trace,
 		rec->time += calltime;
 		rec->time_squared += calltime * calltime;
 	}
-
- out:
-	local_irq_restore(flags);
 }
 
 static struct fgraph_ops fprofiler_ops = {
@@ -946,20 +937,16 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
 
 	val = !!val;
 
-	mutex_lock(&ftrace_profile_lock);
+	guard(mutex)(&ftrace_profile_lock);
 	if (ftrace_profile_enabled ^ val) {
 		if (val) {
 			ret = ftrace_profile_init();
-			if (ret < 0) {
-				cnt = ret;
-				goto out;
-			}
+			if (ret < 0)
+				return ret;
 
 			ret = register_ftrace_profiler();
-			if (ret < 0) {
-				cnt = ret;
-				goto out;
-			}
+			if (ret < 0)
+				return ret;
 			ftrace_profile_enabled = 1;
 		} else {
 			ftrace_profile_enabled = 0;
@@ -970,8 +957,6 @@ ftrace_profile_write(struct file *filp, const char __user *ubuf,
 			unregister_ftrace_profiler();
 		}
 	}
- out:
-	mutex_unlock(&ftrace_profile_lock);
 
 	*ppos += cnt;
 
@@ -1671,14 +1656,12 @@ unsigned long ftrace_location(unsigned long ip)
 	loc = ftrace_location_range(ip, ip);
 	if (!loc) {
 		if (!kallsyms_lookup_size_offset(ip, &size, &offset))
-			goto out;
+			return 0;
 
 		/* map sym+0 to __fentry__ */
 		if (!offset)
 			loc = ftrace_location_range(ip, ip + size - 1);
 	}
-
-out:
 	return loc;
 }
 
@@ -2073,7 +2056,7 @@ rollback:
 			continue;
 
 		if (rec == end)
-			goto err_out;
+			return -EBUSY;
 
 		in_old = !!ftrace_lookup_ip(old_hash, rec->ip);
 		in_new = !!ftrace_lookup_ip(new_hash, rec->ip);
@@ -2086,7 +2069,6 @@ rollback:
 			rec->flags |= FTRACE_FL_IPMODIFY;
 	} while_for_each_ftrace_rec();
 
-err_out:
 	return -EBUSY;
 }
 
@@ -4982,10 +4964,6 @@ static int cache_mod(struct trace_array *tr,
 	return ftrace_add_mod(tr, func, module, enable);
 }
 
-static int
-ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
-		 int reset, int enable);
-
 #ifdef CONFIG_MODULES
 static void process_mod_list(struct list_head *head, struct ftrace_ops *ops,
 			     char *mod, bool enable)
@@ -5615,20 +5593,15 @@ static DEFINE_MUTEX(ftrace_cmd_mutex);
 __init int register_ftrace_command(struct ftrace_func_command *cmd)
 {
 	struct ftrace_func_command *p;
-	int ret = 0;
 
-	mutex_lock(&ftrace_cmd_mutex);
+	guard(mutex)(&ftrace_cmd_mutex);
 	list_for_each_entry(p, &ftrace_commands, list) {
-		if (strcmp(cmd->name, p->name) == 0) {
-			ret = -EBUSY;
-			goto out_unlock;
-		}
+		if (strcmp(cmd->name, p->name) == 0)
+			return -EBUSY;
 	}
 	list_add(&cmd->list, &ftrace_commands);
- out_unlock:
-	mutex_unlock(&ftrace_cmd_mutex);
 
-	return ret;
+	return 0;
 }
 
 /*
@@ -5638,20 +5611,17 @@ __init int register_ftrace_command(struct ftrace_func_command *cmd)
 __init int unregister_ftrace_command(struct ftrace_func_command *cmd)
 {
 	struct ftrace_func_command *p, *n;
-	int ret = -ENODEV;
 
-	mutex_lock(&ftrace_cmd_mutex);
+	guard(mutex)(&ftrace_cmd_mutex);
+
 	list_for_each_entry_safe(p, n, &ftrace_commands, list) {
 		if (strcmp(cmd->name, p->name) == 0) {
-			ret = 0;
 			list_del_init(&p->list);
-			goto out_unlock;
+			return 0;
 		}
 	}
- out_unlock:
-	mutex_unlock(&ftrace_cmd_mutex);
 
-	return ret;
+	return -ENODEV;
 }
 
 static int ftrace_process_regex(struct ftrace_iterator *iter,
@@ -5661,7 +5631,7 @@ static int ftrace_process_regex(struct ftrace_iterator *iter,
 	struct trace_array *tr = iter->ops->private;
 	char *func, *command, *next = buff;
 	struct ftrace_func_command *p;
-	int ret = -EINVAL;
+	int ret;
 
 	func = strsep(&next, ":");
 
@@ -5678,17 +5648,14 @@ static int ftrace_process_regex(struct ftrace_iterator *iter,
 
 	command = strsep(&next, ":");
 
-	mutex_lock(&ftrace_cmd_mutex);
+	guard(mutex)(&ftrace_cmd_mutex);
+
 	list_for_each_entry(p, &ftrace_commands, list) {
-		if (strcmp(p->name, command) == 0) {
-			ret = p->func(tr, hash, func, command, next, enable);
-			goto out_unlock;
-		}
+		if (strcmp(p->name, command) == 0)
+			return p->func(tr, hash, func, command, next, enable);
 	}
- out_unlock:
-	mutex_unlock(&ftrace_cmd_mutex);
 
-	return ret;
+	return -EINVAL;
 }
 
 static ssize_t
@@ -5722,12 +5689,10 @@ ftrace_regex_write(struct file *file, const char __user *ubuf,
 					   parser->idx, enable);
 		trace_parser_clear(parser);
 		if (ret < 0)
-			goto out;
+			return ret;
 	}
 
-	ret = read;
- out:
-	return ret;
+	return read;
 }
 
 ssize_t
@@ -5788,7 +5753,7 @@ ftrace_match_addr(struct ftrace_hash *hash, unsigned long *ips,
 static int
 ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		unsigned long *ips, unsigned int cnt,
-		int remove, int reset, int enable)
+		int remove, int reset, int enable, char *mod)
 {
 	struct ftrace_hash **orig_hash;
 	struct ftrace_hash *hash;
@@ -5814,7 +5779,15 @@ ftrace_set_hash(struct ftrace_ops *ops, unsigned char *buf, int len,
 		goto out_regex_unlock;
 	}
 
-	if (buf && !ftrace_match_records(hash, buf, len)) {
+	if (buf && !match_records(hash, buf, len, mod)) {
+		/* If this was for a module and nothing was enabled, flag it */
+		if (mod)
+			(*orig_hash)->flags |= FTRACE_HASH_FL_MOD;
+
+		/*
+		 * Even if it is a mod, return error to let caller know
+		 * nothing was added
+		 */
 		ret = -EINVAL;
 		goto out_regex_unlock;
 	}
@@ -5839,7 +5812,7 @@ static int
 ftrace_set_addr(struct ftrace_ops *ops, unsigned long *ips, unsigned int cnt,
 		int remove, int reset, int enable)
 {
-	return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable);
+	return ftrace_set_hash(ops, NULL, 0, ips, cnt, remove, reset, enable, NULL);
 }
 
 #ifdef CONFIG_DYNAMIC_FTRACE_WITH_DIRECT_CALLS
@@ -6217,7 +6190,38 @@ static int
 ftrace_set_regex(struct ftrace_ops *ops, unsigned char *buf, int len,
 		 int reset, int enable)
 {
-	return ftrace_set_hash(ops, buf, len, NULL, 0, 0, reset, enable);
+	char *mod = NULL, *func, *command, *next = buf;
+	char *tmp __free(kfree) = NULL;
+	struct trace_array *tr = ops->private;
+	int ret;
+
+	func = strsep(&next, ":");
+
+	/* This can also handle :mod: parsing */
+	if (next) {
+		if (!tr)
+			return -EINVAL;
+
+		command = strsep(&next, ":");
+		if (strcmp(command, "mod") != 0)
+			return -EINVAL;
+
+		mod = next;
+		len = command - func;
+		/* Save the original func as ftrace_set_hash() can modify it */
+		tmp = kstrdup(func, GFP_KERNEL);
+	}
+
+	ret = ftrace_set_hash(ops, func, len, NULL, 0, 0, reset, enable, mod);
+
+	if (tr && mod && ret < 0) {
+		/* Did tmp fail to allocate? */
+		if (!tmp)
+			return -ENOMEM;
+		ret = cache_mod(tr, tmp, mod, enable);
+	}
+
+	return ret;
 }
 
 /**
@@ -6381,6 +6385,14 @@ ftrace_set_early_filter(struct ftrace_ops *ops, char *buf, int enable)
 
 	ftrace_ops_init(ops);
 
+	/* The trace_array is needed for caching module function filters */
+	if (!ops->private) {
+		struct trace_array *tr = trace_get_global_array();
+
+		ops->private = tr;
+		ftrace_init_trace_array(tr);
+	}
+
 	while (buf) {
 		func = strsep(&buf, ",");
 		ftrace_set_regex(ops, func, strlen(func), 0, enable);
@@ -7814,9 +7826,14 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 
 void ftrace_init_trace_array(struct trace_array *tr)
 {
+	if (tr->flags & TRACE_ARRAY_FL_MOD_INIT)
+		return;
+
 	INIT_LIST_HEAD(&tr->func_probes);
 	INIT_LIST_HEAD(&tr->mod_trace);
 	INIT_LIST_HEAD(&tr->mod_notrace);
+
+	tr->flags |= TRACE_ARRAY_FL_MOD_INIT;
 }
 #else
 
@@ -7845,7 +7862,8 @@ static void ftrace_update_trampoline(struct ftrace_ops *ops)
 __init void ftrace_init_global_array_ops(struct trace_array *tr)
 {
 	tr->ops = &global_ops;
-	tr->ops->private = tr;
+	if (!global_ops.private)
+		global_ops.private = tr;
 	ftrace_init_trace_array(tr);
 	init_array_fgraph_ops(tr, tr->ops);
 }
@@ -8287,7 +8305,7 @@ pid_write(struct file *filp, const char __user *ubuf,
 	if (!cnt)
 		return 0;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	switch (type) {
 	case TRACE_PIDS:
@@ -8303,14 +8321,13 @@ pid_write(struct file *filp, const char __user *ubuf,
 					     lockdep_is_held(&ftrace_lock));
 		break;
 	default:
-		ret = -EINVAL;
 		WARN_ON_ONCE(1);
-		goto out;
+		return -EINVAL;
 	}
 
 	ret = trace_pid_write(filtered_pids, &pid_list, ubuf, cnt);
 	if (ret < 0)
-		goto out;
+		return ret;
 
 	switch (type) {
 	case TRACE_PIDS:
@@ -8339,11 +8356,8 @@ pid_write(struct file *filp, const char __user *ubuf,
 
 	ftrace_update_pid_func();
 	ftrace_startup_all(0);
- out:
-	mutex_unlock(&ftrace_lock);
 
-	if (ret > 0)
-		*ppos += ret;
+	*ppos += ret;
 
 	return ret;
 }
@@ -8746,17 +8760,17 @@ static int
 ftrace_enable_sysctl(const struct ctl_table *table, int write,
 		     void *buffer, size_t *lenp, loff_t *ppos)
 {
-	int ret = -ENODEV;
+	int ret;
 
-	mutex_lock(&ftrace_lock);
+	guard(mutex)(&ftrace_lock);
 
 	if (unlikely(ftrace_disabled))
-		goto out;
+		return -ENODEV;
 
 	ret = proc_dointvec(table, write, buffer, lenp, ppos);
 
 	if (ret || !write || (last_ftrace_enabled == !!ftrace_enabled))
-		goto out;
+		return ret;
 
 	if (ftrace_enabled) {
 
@@ -8770,8 +8784,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write,
 	} else {
 		if (is_permanent_ops_registered()) {
 			ftrace_enabled = true;
-			ret = -EBUSY;
-			goto out;
+			return -EBUSY;
 		}
 
 		/* stopping ftrace calls (just send to ftrace_stub) */
@@ -8781,9 +8794,7 @@ ftrace_enable_sysctl(const struct ctl_table *table, int write,
 	}
 
 	last_ftrace_enabled = !!ftrace_enabled;
- out:
-	mutex_unlock(&ftrace_lock);
-	return ret;
+	return 0;
 }
 
 static struct ctl_table ftrace_sysctls[] = {