linux-kernel.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Michael Jeanson <mjeanson@efficios.com>
To: linux-kernel@vger.kernel.org
Cc: mathieu.desnoyers@efficios.com,
	Michael Jeanson <mjeanson@efficios.com>,
	Steven Rostedt <rostedt@goodmis.org>,
	Peter Zijlstra <peterz@infradead.org>,
	Alexei Starovoitov <ast@kernel.org>, Yonghong Song <yhs@fb.com>,
	"Paul E . McKenney" <paulmck@kernel.org>,
	Ingo Molnar <mingo@redhat.com>,
	Arnaldo Carvalho de Melo <acme@kernel.org>,
	Mark Rutland <mark.rutland@arm.com>,
	Alexander Shishkin <alexander.shishkin@linux.intel.com>,
	Jiri Olsa <jolsa@redhat.com>, Namhyung Kim <namhyung@kernel.org>,
	Joel Fernandes <joel@joelfernandes.org>,
	bpf@vger.kernel.org
Subject: [RFC PATCH 5/6] tracing: convert sys_enter/exit to sleepable tracepoints
Date: Fri, 23 Oct 2020 15:53:51 -0400	[thread overview]
Message-ID: <20201023195352.26269-6-mjeanson@efficios.com> (raw)
In-Reply-To: <20201023195352.26269-1-mjeanson@efficios.com>

Convert the definition of the system call enter/exit tracepoints to
sleepable tracepoints now that all upstream tracers handle it.

Co-developed-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Michael Jeanson <mjeanson@efficios.com>
Cc: Steven Rostedt (VMware) <rostedt@goodmis.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Alexei Starovoitov <ast@kernel.org>
Cc: Yonghong Song <yhs@fb.com>
Cc: Paul E. McKenney <paulmck@kernel.org>
Cc: Ingo Molnar <mingo@redhat.com>
Cc: Arnaldo Carvalho de Melo <acme@kernel.org>
Cc: Mark Rutland <mark.rutland@arm.com>
Cc: Alexander Shishkin <alexander.shishkin@linux.intel.com>
Cc: Jiri Olsa <jolsa@redhat.com>
Cc: Namhyung Kim <namhyung@kernel.org>
Cc: Joel Fernandes (Google) <joel@joelfernandes.org>
Cc: bpf@vger.kernel.org
---
 include/trace/events/syscalls.h |  4 +-
 kernel/trace/trace_syscalls.c   | 68 ++++++++++++++++++++-------------
 2 files changed, 44 insertions(+), 28 deletions(-)

diff --git a/include/trace/events/syscalls.h b/include/trace/events/syscalls.h
index b6e0cbc2c71f..fbb8d8b48f81 100644
--- a/include/trace/events/syscalls.h
+++ b/include/trace/events/syscalls.h
@@ -15,7 +15,7 @@
 
 #ifdef CONFIG_HAVE_SYSCALL_TRACEPOINTS
 
-TRACE_EVENT_FN(sys_enter,
+TRACE_EVENT_FN_MAYSLEEP(sys_enter,
 
 	TP_PROTO(struct pt_regs *regs, long id),
 
@@ -41,7 +41,7 @@ TRACE_EVENT_FN(sys_enter,
 
 TRACE_EVENT_FLAGS(sys_enter, TRACE_EVENT_FL_CAP_ANY)
 
-TRACE_EVENT_FN(sys_exit,
+TRACE_EVENT_FN_MAYSLEEP(sys_exit,
 
 	TP_PROTO(struct pt_regs *regs, long ret),
 
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index d85a2f0f316b..48d92d59fb92 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -304,21 +304,23 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int syscall_nr;
 	int size;
 
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE) */
 	trace_file = rcu_dereference_sched(tr->enter_syscall_files[syscall_nr]);
 	if (!trace_file)
-		return;
+		goto end;
 
 	if (trace_trigger_soft_disabled(trace_file))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	size = sizeof(*entry) + sizeof(unsigned long) * sys_data->nb_args;
 
@@ -329,7 +331,7 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	event = trace_buffer_lock_reserve(buffer,
 			sys_data->enter_event->event.type, size, irq_flags, pc);
 	if (!event)
-		return;
+		goto end;
 
 	entry = ring_buffer_event_data(event);
 	entry->nr = syscall_nr;
@@ -338,6 +340,8 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 
 	event_trigger_unlock_commit(trace_file, buffer, event, entry,
 				    irq_flags, pc);
+end:
+	preempt_enable_notrace();
 }
 
 static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
@@ -352,21 +356,23 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	int pc;
 	int syscall_nr;
 
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 
 	/* Here we're inside tp handler's rcu_read_lock_sched (__DO_TRACE()) */
 	trace_file = rcu_dereference_sched(tr->exit_syscall_files[syscall_nr]);
 	if (!trace_file)
-		return;
+		goto end;
 
 	if (trace_trigger_soft_disabled(trace_file))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	local_save_flags(irq_flags);
 	pc = preempt_count();
@@ -376,7 +382,7 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 			sys_data->exit_event->event.type, sizeof(*entry),
 			irq_flags, pc);
 	if (!event)
-		return;
+		goto end;
 
 	entry = ring_buffer_event_data(event);
 	entry->nr = syscall_nr;
@@ -384,6 +390,8 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 
 	event_trigger_unlock_commit(trace_file, buffer, event, entry,
 				    irq_flags, pc);
+end:
+	preempt_enable_notrace();
 }
 
 static int reg_event_syscall_enter(struct trace_event_file *file,
@@ -398,7 +406,7 @@ static int reg_event_syscall_enter(struct trace_event_file *file,
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!tr->sys_refcount_enter)
-		ret = register_trace_sys_enter(ftrace_syscall_enter, tr);
+		ret = register_trace_maysleep_sys_enter(ftrace_syscall_enter, tr);
 	if (!ret) {
 		rcu_assign_pointer(tr->enter_syscall_files[num], file);
 		tr->sys_refcount_enter++;
@@ -436,7 +444,7 @@ static int reg_event_syscall_exit(struct trace_event_file *file,
 		return -ENOSYS;
 	mutex_lock(&syscall_trace_lock);
 	if (!tr->sys_refcount_exit)
-		ret = register_trace_sys_exit(ftrace_syscall_exit, tr);
+		ret = register_trace_maysleep_sys_exit(ftrace_syscall_exit, tr);
 	if (!ret) {
 		rcu_assign_pointer(tr->exit_syscall_files[num], file);
 		tr->sys_refcount_exit++;
@@ -600,20 +608,22 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	int rctx;
 	int size;
 
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 	if (!test_bit(syscall_nr, enabled_perf_enter_syscalls))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	head = this_cpu_ptr(sys_data->enter_event->perf_events);
 	valid_prog_array = bpf_prog_array_valid(sys_data->enter_event);
 	if (!valid_prog_array && hlist_empty(head))
-		return;
+		goto end;
 
 	/* get the size after alignment with the u32 buffer size field */
 	size = sizeof(unsigned long) * sys_data->nb_args + sizeof(*rec);
@@ -622,7 +632,7 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 
 	rec = perf_trace_buf_alloc(size, NULL, &rctx);
 	if (!rec)
-		return;
+		goto end;
 
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, args);
@@ -632,12 +642,14 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	     !perf_call_bpf_enter(sys_data->enter_event, regs, sys_data, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
-		return;
+		goto end;
 	}
 
 	perf_trace_buf_submit(rec, size, rctx,
 			      sys_data->enter_event->event.type, 1, regs,
 			      head, NULL);
+end:
+	preempt_enable_notrace();
 }
 
 static int perf_sysenter_enable(struct trace_event_call *call)
@@ -649,7 +661,7 @@ static int perf_sysenter_enable(struct trace_event_call *call)
 
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_perf_refcount_enter)
-		ret = register_trace_sys_enter(perf_syscall_enter, NULL);
+		ret = register_trace_maysleep_sys_enter(perf_syscall_enter, NULL);
 	if (ret) {
 		pr_info("event trace: Could not activate syscall entry trace point");
 	} else {
@@ -699,20 +711,22 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	int rctx;
 	int size;
 
+	preempt_disable_notrace();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
-		return;
+		goto end;
 	if (!test_bit(syscall_nr, enabled_perf_exit_syscalls))
-		return;
+		goto end;
 
 	sys_data = syscall_nr_to_meta(syscall_nr);
 	if (!sys_data)
-		return;
+		goto end;
 
 	head = this_cpu_ptr(sys_data->exit_event->perf_events);
 	valid_prog_array = bpf_prog_array_valid(sys_data->exit_event);
 	if (!valid_prog_array && hlist_empty(head))
-		return;
+		goto end;
 
 	/* We can probably do that at build time */
 	size = ALIGN(sizeof(*rec) + sizeof(u32), sizeof(u64));
@@ -720,7 +734,7 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
 	rec = perf_trace_buf_alloc(size, NULL, &rctx);
 	if (!rec)
-		return;
+		goto end;
 
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
@@ -729,11 +743,13 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	     !perf_call_bpf_exit(sys_data->exit_event, regs, rec)) ||
 	    hlist_empty(head)) {
 		perf_swevent_put_recursion_context(rctx);
-		return;
+		goto end;
 	}
 
 	perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
 			      1, regs, head, NULL);
+end:
+	preempt_enable_notrace();
 }
 
 static int perf_sysexit_enable(struct trace_event_call *call)
@@ -745,7 +761,7 @@ static int perf_sysexit_enable(struct trace_event_call *call)
 
 	mutex_lock(&syscall_trace_lock);
 	if (!sys_perf_refcount_exit)
-		ret = register_trace_sys_exit(perf_syscall_exit, NULL);
+		ret = register_trace_maysleep_sys_exit(perf_syscall_exit, NULL);
 	if (ret) {
 		pr_info("event trace: Could not activate syscall exit trace point");
 	} else {
-- 
2.25.1


  parent reply	other threads:[~2020-10-23 19:54 UTC|newest]

Thread overview: 20+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-10-23 19:53 [RFC PATCH 0/6] Sleepable tracepoints Michael Jeanson
2020-10-23 19:53 ` [RFC PATCH 1/6] tracing: introduce sleepable tracepoints Michael Jeanson
2020-10-26 22:43   ` Alexei Starovoitov
2020-10-27 13:37     ` Mathieu Desnoyers
2020-10-28 21:23       ` Alexei Starovoitov
2021-02-11 19:36         ` Mathieu Desnoyers
2020-11-02 18:51       ` Joel Fernandes
2020-10-23 19:53 ` [RFC PATCH 2/6] tracing: ftrace: add support for " Michael Jeanson
2020-10-23 19:53 ` [RFC PATCH 3/6] tracing: bpf-trace: " Michael Jeanson
2020-10-23 19:53 ` [RFC PATCH 4/6] tracing: perf: " Michael Jeanson
2020-10-23 19:53 ` Michael Jeanson [this message]
2020-10-23 19:53 ` [RFC PATCH 6/6] tracing: use sched-RCU instead of SRCU for rcuidle tracepoints Michael Jeanson
2020-10-23 21:13   ` Joel Fernandes
2020-10-26  8:20     ` Peter Zijlstra
2020-10-26 14:28       ` Mathieu Desnoyers
2020-10-26 20:44         ` Steven Rostedt
2020-10-27 13:57           ` Mathieu Desnoyers
2020-11-02 18:43         ` Joel Fernandes
2020-10-26 12:05 ` [RFC PATCH 0/6] Sleepable tracepoints peter enderborg
2020-10-26 14:59   ` Mathieu Desnoyers

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20201023195352.26269-6-mjeanson@efficios.com \
    --to=mjeanson@efficios.com \
    --cc=acme@kernel.org \
    --cc=alexander.shishkin@linux.intel.com \
    --cc=ast@kernel.org \
    --cc=bpf@vger.kernel.org \
    --cc=joel@joelfernandes.org \
    --cc=jolsa@redhat.com \
    --cc=linux-kernel@vger.kernel.org \
    --cc=mark.rutland@arm.com \
    --cc=mathieu.desnoyers@efficios.com \
    --cc=mingo@redhat.com \
    --cc=namhyung@kernel.org \
    --cc=paulmck@kernel.org \
    --cc=peterz@infradead.org \
    --cc=rostedt@goodmis.org \
    --cc=yhs@fb.com \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).