Merge branch 'bpf-send-sig'

Yonghong Song says:

====================
This patch tries to solve the following specific use case.

Currently, bpf program can already collect stack traces
through kernel function get_perf_callchain()
when certain events happens (e.g., cache miss counter or
cpu clock counter overflows). But such stack traces are
not enough for jitted programs, e.g., hhvm (jited php).
To get real stack trace, jit engine internal data structures
need to be traversed in order to get the real user functions.

bpf program itself may not be the best place to traverse
the jit engine as the traversing logic could be complex and
it is not a stable interface either.

Instead, hhvm implements a signal handler,
e.g. for SIGALARM, and a set of program locations which
it can dump stack traces. When it receives a signal, it will
dump the stack in next such program location.

This patch implements bpf_send_signal() helper to send
a signal to hhvm in real time, resulting in intended stack traces.

Patch #1 implemented the bpf_send_helper() in the kernel.
Patch #2 synced uapi header bpf.h to tools directory.
Patch #3 added a self test which covers tracepoint
and perf_event bpf programs.

Changelogs:
  v4 => v5:
    . pass the "current" task struct to irq_work as well
      since the current task struct may change between
      nmi and subsequent irq_work_interrupt.
      Discovered by Daniel.
  v3 => v4:
    . fix one typo and declare "const char *id_path = ..."
      to avoid directly use the long string in the func body
      in Patch #3.
  v2 => v3:
    . change the standalone test to be part of prog_tests.
  RFC v1 => v2:
    . previous version allows to send signal to an arbitrary
      pid. This version just sends the signal to current
      task to avoid unstable pid and potential races between
      sending signals and task state changes for the pid.
====================

Signed-off-by: Daniel Borkmann <daniel@iogearbox.net>

1 files changed, 72 insertions, 0 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f92d6ad5e080..70029eafc71f 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -567,6 +567,63 @@ static const struct bpf_func_proto bpf_probe_read_str_proto = {
 	.arg3_type	= ARG_ANYTHING,
 };
 
+struct send_signal_irq_work {
+	struct irq_work irq_work;
+	struct task_struct *task;
+	u32 sig;
+};
+
+static DEFINE_PER_CPU(struct send_signal_irq_work, send_signal_work);
+
+static void do_bpf_send_signal(struct irq_work *entry)
+{
+	struct send_signal_irq_work *work;
+
+	work = container_of(entry, struct send_signal_irq_work, irq_work);
+	group_send_sig_info(work->sig, SEND_SIG_PRIV, work->task, PIDTYPE_TGID);
+}
+
+BPF_CALL_1(bpf_send_signal, u32, sig)
+{
+	struct send_signal_irq_work *work = NULL;
+
+	/* Similar to bpf_probe_write_user, task needs to be
+	 * in a sound condition and kernel memory access be
+	 * permitted in order to send signal to the current
+	 * task.
+	 */
+	if (unlikely(current->flags & (PF_KTHREAD | PF_EXITING)))
+		return -EPERM;
+	if (unlikely(uaccess_kernel()))
+		return -EPERM;
+	if (unlikely(!nmi_uaccess_okay()))
+		return -EPERM;
+
+	if (in_nmi()) {
+		work = this_cpu_ptr(&send_signal_work);
+		if (work->irq_work.flags & IRQ_WORK_BUSY)
+			return -EBUSY;
+
+		/* Add the current task, which is the target of sending signal,
+		 * to the irq_work. The current task may change when queued
+		 * irq works get executed.
+		 */
+		work->task = current;
+		work->sig = sig;
+		irq_work_queue(&work->irq_work);
+		return 0;
+	}
+
+	return group_send_sig_info(sig, SEND_SIG_PRIV, current, PIDTYPE_TGID);
+}
+
+static const struct bpf_func_proto bpf_send_signal_proto = {
+	.func		= bpf_send_signal,
+	.gpl_only	= false,
+	.ret_type	= RET_INTEGER,
+	.arg1_type	= ARG_ANYTHING,
+};
+
 static const struct bpf_func_proto *
 tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 {
@@ -617,6 +674,8 @@ tracing_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 	case BPF_FUNC_get_current_cgroup_id:
 		return &bpf_get_current_cgroup_id_proto;
 #endif
+	case BPF_FUNC_send_signal:
+		return &bpf_send_signal_proto;
 	default:
 		return NULL;
 	}
@@ -1343,5 +1402,18 @@ static int __init bpf_event_init(void)
 	return 0;
 }
 
+static int __init send_signal_irq_work_init(void)
+{
+	int cpu;
+	struct send_signal_irq_work *work;
+
+	for_each_possible_cpu(cpu) {
+		work = per_cpu_ptr(&send_signal_work, cpu);
+		init_irq_work(&work->irq_work, do_bpf_send_signal);
+	}
+	return 0;
+}
+
 fs_initcall(bpf_event_init);
+subsys_initcall(send_signal_irq_work_init);
 #endif /* CONFIG_MODULES */