[PATCH AUTOSEL 6.12 03/36] tracing/ftrace: disable preemption in syscall probe

[PATCH AUTOSEL 6.12 03/36] tracing/ftrace: disable preemption in syscall probe

[Sasha Levin]

From: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>

[ Upstream commit 13d750c2c03e9861e15268574ed2c239cca9c9d5 ]

In preparation for allowing system call enter/exit instrumentation to
handle page faults, make sure that ftrace can handle this change by
explicitly disabling preemption within the ftrace system call tracepoint
probes to respect the current expectations within ftrace ring buffer
code.

This change does not yet allow ftrace to take page faults per se within
its probe, but allows its existing probes to adapt to the upcoming
change.

Cc: Michael Jeanson <mjeanson@efficios.com>
Cc: Masami Hiramatsu <mhiramat@kernel.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: Namhyung Kim <namhyung@kernel.org>
Cc: Andrii Nakryiko <andrii.nakryiko@gmail.com>
Cc: bpf@vger.kernel.org
Cc: Joel Fernandes <joel@joelfernandes.org>
Link: https://lore.kernel.org/20241009010718.2050182-3-mathieu.desnoyers@efficios.com
Acked-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Mathieu Desnoyers <mathieu.desnoyers@efficios.com>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 include/trace/trace_events.h  | 36 +++++++++++++++++++++++++++++++----
 kernel/trace/trace_syscalls.c | 12 ++++++++++++
 2 files changed, 44 insertions(+), 4 deletions(-)

diff --git a/include/trace/trace_events.h b/include/trace/trace_events.h
index c2f9cabf154d1..fa0d51cad57a8 100644
--- a/include/trace/trace_events.h
+++ b/include/trace/trace_events.h
@@ -244,6 +244,9 @@ static struct trace_event_fields trace_event_fields_##call[] = {	\
 	tstruct								\
 	{} };
 
+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS DECLARE_EVENT_CLASS
+
 #undef DEFINE_EVENT_PRINT
 #define DEFINE_EVENT_PRINT(template, name, proto, args, print)
 
@@ -374,11 +377,11 @@ static inline notrace int trace_event_get_offsets_##call(		\
 
 #include "stages/stage6_event_callback.h"
 
-#undef DECLARE_EVENT_CLASS
-#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
-									\
+
+#undef __DECLARE_EVENT_CLASS
+#define __DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print) \
 static notrace void							\
-trace_event_raw_event_##call(void *__data, proto)			\
+do_trace_event_raw_event_##call(void *__data, proto)			\
 {									\
 	struct trace_event_file *trace_file = __data;			\
 	struct trace_event_data_offsets_##call __maybe_unused __data_offsets;\
@@ -403,6 +406,29 @@ trace_event_raw_event_##call(void *__data, proto)			\
 									\
 	trace_event_buffer_commit(&fbuffer);				\
 }
+
+#undef DECLARE_EVENT_CLASS
+#define DECLARE_EVENT_CLASS(call, proto, args, tstruct, assign, print)	\
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+trace_event_raw_event_##call(void *__data, proto)			\
+{									\
+	do_trace_event_raw_event_##call(__data, args);			\
+}
+
+#undef DECLARE_EVENT_SYSCALL_CLASS
+#define DECLARE_EVENT_SYSCALL_CLASS(call, proto, args, tstruct, assign, print) \
+__DECLARE_EVENT_CLASS(call, PARAMS(proto), PARAMS(args), PARAMS(tstruct), \
+		      PARAMS(assign), PARAMS(print))			\
+static notrace void							\
+trace_event_raw_event_##call(void *__data, proto)			\
+{									\
+	preempt_disable_notrace();					\
+	do_trace_event_raw_event_##call(__data, args);			\
+	preempt_enable_notrace();					\
+}
+
 /*
  * The ftrace_test_probe is compiled out, it is only here as a build time check
  * to make sure that if the tracepoint handling changes, the ftrace probe will
@@ -418,6 +444,8 @@ static inline void ftrace_test_probe_##call(void)			\
 
 #include TRACE_INCLUDE(TRACE_INCLUDE_FILE)
 
+#undef __DECLARE_EVENT_CLASS
+
 #include "stages/stage7_class_define.h"
 
 #undef DECLARE_EVENT_CLASS
diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 785733245eadf..f9b21bac9d45e 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -299,6 +299,12 @@ static void ftrace_syscall_enter(void *data, struct pt_regs *regs, long id)
 	int syscall_nr;
 	int size;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
@@ -338,6 +344,12 @@ static void ftrace_syscall_exit(void *data, struct pt_regs *regs, long ret)
 	struct trace_event_buffer fbuffer;
 	int syscall_nr;
 
+	/*
+	 * Syscall probe called with preemption enabled, but the ring
+	 * buffer and per-cpu data require preemption to be disabled.
+	 */
+	guard(preempt_notrace)();
+
 	syscall_nr = trace_get_syscall_nr(current, regs);
 	if (syscall_nr < 0 || syscall_nr >= NR_syscalls)
 		return;
-- 
2.43.0

[PATCH AUTOSEL 6.12 16/36] bpf: put bpf_link's program when link is safe to be deallocated

[Sasha Levin]

From: Andrii Nakryiko <andrii@kernel.org>

[ Upstream commit f44ec8733a8469143fde1984b5e6931b2e2f6f3f ]

In general, BPF link's underlying BPF program should be considered to be
reachable through attach hook -> link -> prog chain, and, pessimistically,
we have to assume that as long as link's memory is not safe to free,
attach hook's code might hold a pointer to BPF program and use it.

As such, it's not (generally) correct to put link's program early before
waiting for RCU GPs to go through. More eager bpf_prog_put() that we
currently do is mostly correct due to BPF program's release code doing
similar RCU GP waiting, but as will be shown in the following patches,
BPF program can be non-sleepable (and, thus, reliant on only "classic"
RCU GP), while BPF link's attach hook can have sleepable semantics and
needs to be protected by RCU Tasks Trace, and for such cases BPF link
has to go through RCU Tasks Trace + "classic" RCU GPs before being
deallocated. And so, if we put BPF program early, we might free BPF
program before we free BPF link, leading to use-after-free situation.

So, this patch defers bpf_prog_put() until we are ready to perform
bpf_link's deallocation. At worst, this delays BPF program freeing by
one extra RCU GP, but that seems completely acceptable. Alternatively,
we'd need more elaborate ways to determine BPF hook, BPF link, and BPF
program lifetimes, and how they relate to each other, which seems like
an unnecessary complication.

Note, for most BPF links we still will perform eager bpf_prog_put() and
link dealloc, so for those BPF links there are no observable changes
whatsoever. Only BPF links that use deferred dealloc might notice
slightly delayed freeing of BPF programs.

Also, to reduce code and logic duplication, extract program put + link
dealloc logic into bpf_link_dealloc() helper.

Link: https://lore.kernel.org/20241101181754.782341-1-andrii@kernel.org
Tested-by: Jordan Rife <jrife@google.com>
Signed-off-by: Andrii Nakryiko <andrii@kernel.org>
Signed-off-by: Steven Rostedt (Google) <rostedt@goodmis.org>
Signed-off-by: Sasha Levin <sashal@kernel.org>
---
 kernel/bpf/syscall.c | 22 +++++++++++++++++-----
 1 file changed, 17 insertions(+), 5 deletions(-)

diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c
index c5aa127ed4cc0..2e99fedb9e4ab 100644
--- a/kernel/bpf/syscall.c
+++ b/kernel/bpf/syscall.c
@@ -2976,12 +2976,24 @@ void bpf_link_inc(struct bpf_link *link)
 	atomic64_inc(&link->refcnt);
 }
 
+static void bpf_link_dealloc(struct bpf_link *link)
+{
+	/* now that we know that bpf_link itself can't be reached, put underlying BPF program */
+	if (link->prog)
+		bpf_prog_put(link->prog);
+
+	/* free bpf_link and its containing memory */
+	if (link->ops->dealloc_deferred)
+		link->ops->dealloc_deferred(link);
+	else
+		link->ops->dealloc(link);
+}
+
 static void bpf_link_defer_dealloc_rcu_gp(struct rcu_head *rcu)
 {
 	struct bpf_link *link = container_of(rcu, struct bpf_link, rcu);
 
-	/* free bpf_link and its containing memory */
-	link->ops->dealloc_deferred(link);
+	bpf_link_dealloc(link);
 }
 
 static void bpf_link_defer_dealloc_mult_rcu_gp(struct rcu_head *rcu)
@@ -3003,7 +3015,6 @@ static void bpf_link_free(struct bpf_link *link)
 		sleepable = link->prog->sleepable;
 		/* detach BPF program, clean up used resources */
 		ops->release(link);
-		bpf_prog_put(link->prog);
 	}
 	if (ops->dealloc_deferred) {
 		/* schedule BPF link deallocation; if underlying BPF program
@@ -3014,8 +3025,9 @@ static void bpf_link_free(struct bpf_link *link)
 			call_rcu_tasks_trace(&link->rcu, bpf_link_defer_dealloc_mult_rcu_gp);
 		else
 			call_rcu(&link->rcu, bpf_link_defer_dealloc_rcu_gp);
-	} else if (ops->dealloc)
-		ops->dealloc(link);
+	} else if (ops->dealloc) {
+		bpf_link_dealloc(link);
+	}
 }
 
 static void bpf_link_put_deferred(struct work_struct *work)
-- 
2.43.0