bpf: add support for sys_enter_* and sys_exit_* tracepoints

Currently, bpf programs cannot be attached to sys_enter_* and sys_exit_*
style tracepoints. The iovisor/bcc issue #748
(https://github.com/iovisor/bcc/issues/748) documents this issue.
For example, if you try to attach a bpf program to tracepoints
syscalls/sys_enter_newfstat, you will get the following error:
   # ./tools/trace.py t:syscalls:sys_enter_newfstat
   Ioctl(PERF_EVENT_IOC_SET_BPF): Invalid argument
   Failed to attach BPF to tracepoint

The main reason is that syscalls/sys_enter_* and syscalls/sys_exit_*
tracepoints are treated differently from other tracepoints and there
is no bpf hook to it.

This patch adds bpf support for these syscalls tracepoints by
  . permitting bpf attachment in ioctl PERF_EVENT_IOC_SET_BPF
  . calling bpf programs in perf_syscall_enter and perf_syscall_exit

The legality of bpf program ctx access is also checked.
Function trace_event_get_offsets returns correct max offset for each
specific syscall tracepoint, which is compared against the maximum offset
access in bpf program.

Signed-off-by: Yonghong Song <yhs@fb.com>
Acked-by: Alexei Starovoitov <ast@kernel.org>
Signed-off-by: David S. Miller <davem@davemloft.net>

1 files changed, 51 insertions, 2 deletions

diff --git a/kernel/trace/trace_syscalls.c b/kernel/trace/trace_syscalls.c
index 5e10395da88e..7a1a92036563 100644
--- a/kernel/trace/trace_syscalls.c
+++ b/kernel/trace/trace_syscalls.c
@@ -559,11 +559,29 @@ static DECLARE_BITMAP(enabled_perf_exit_syscalls, NR_syscalls);
 static int sys_perf_refcount_enter;
 static int sys_perf_refcount_exit;
 
+static int perf_call_bpf_enter(struct bpf_prog *prog, struct pt_regs *regs,
+			      struct syscall_metadata *sys_data,
+			      struct syscall_trace_enter *rec) {
+	struct syscall_tp_t {
+		unsigned long long regs;
+		unsigned long syscall_nr;
+		unsigned long args[sys_data->nb_args];
+	} param;
+	int i;
+
+	*(struct pt_regs **)&param = regs;
+	param.syscall_nr = rec->nr;
+	for (i = 0; i < sys_data->nb_args; i++)
+		param.args[i] = rec->args[i];
+	return trace_call_bpf(prog, &param);
+}
+
 static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_enter *rec;
 	struct hlist_head *head;
+	struct bpf_prog *prog;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -578,8 +596,9 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	if (!sys_data)
 		return;
 
+	prog = READ_ONCE(sys_data->enter_event->prog);
 	head = this_cpu_ptr(sys_data->enter_event->perf_events);
-	if (hlist_empty(head))
+	if (!prog && hlist_empty(head))
 		return;
 
 	/* get the size after alignment with the u32 buffer size field */
@@ -594,6 +613,13 @@ static void perf_syscall_enter(void *ignore, struct pt_regs *regs, long id)
 	rec->nr = syscall_nr;
 	syscall_get_arguments(current, regs, 0, sys_data->nb_args,
 			       (unsigned long *)&rec->args);
+
+	if ((prog && !perf_call_bpf_enter(prog, regs, sys_data, rec)) ||
+	    hlist_empty(head)) {
+		perf_swevent_put_recursion_context(rctx);
+		return;
+	}
+
 	perf_trace_buf_submit(rec, size, rctx,
 			      sys_data->enter_event->event.type, 1, regs,
 			      head, NULL);
@@ -633,11 +659,26 @@ static void perf_sysenter_disable(struct trace_event_call *call)
 	mutex_unlock(&syscall_trace_lock);
 }
 
+static int perf_call_bpf_exit(struct bpf_prog *prog, struct pt_regs *regs,
+			      struct syscall_trace_exit *rec) {
+	struct syscall_tp_t {
+		unsigned long long regs;
+		unsigned long syscall_nr;
+		unsigned long ret;
+	} param;
+
+	*(struct pt_regs **)&param = regs;
+	param.syscall_nr = rec->nr;
+	param.ret = rec->ret;
+	return trace_call_bpf(prog, &param);
+}
+
 static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 {
 	struct syscall_metadata *sys_data;
 	struct syscall_trace_exit *rec;
 	struct hlist_head *head;
+	struct bpf_prog *prog;
 	int syscall_nr;
 	int rctx;
 	int size;
@@ -652,8 +693,9 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 	if (!sys_data)
 		return;
 
+	prog = READ_ONCE(sys_data->exit_event->prog);
 	head = this_cpu_ptr(sys_data->exit_event->perf_events);
-	if (hlist_empty(head))
+	if (!prog && hlist_empty(head))
 		return;
 
 	/* We can probably do that at build time */
@@ -666,6 +708,13 @@ static void perf_syscall_exit(void *ignore, struct pt_regs *regs, long ret)
 
 	rec->nr = syscall_nr;
 	rec->ret = syscall_get_return_value(current, regs);
+
+	if ((prog && !perf_call_bpf_exit(prog, regs, rec)) ||
+	    hlist_empty(head)) {
+		perf_swevent_put_recursion_context(rctx);
+		return;
+	}
+
 	perf_trace_buf_submit(rec, size, rctx, sys_data->exit_event->event.type,
 			      1, regs, head, NULL);
 }