1 files changed, 173 insertions, 24 deletions

diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c
index f92d6ad5e080..ca1255d14576 100644
--- a/kernel/trace/bpf_trace.c
+++ b/kernel/trace/bpf_trace.c
@@ -19,6 +19,9 @@
 #include "trace_probe.h"
 #include "trace.h"
 
+#define bpf_event_rcu_dereference(p)					\
+	rcu_dereference_protected(p, lockdep_is_held(&bpf_event_mutex))
+
 #ifdef CONFIG_MODULES
 struct bpf_trace_module {
 	struct module *module;
@@ -410,8 +413,6 @@ static const struct bpf_func_proto bpf_perf_event_read_value_proto = {
 	.arg4_type	= ARG_CONST_SIZE,
 };
 
-static DEFINE_PER_CPU(struct perf_sample_data, bpf_trace_sd);
-
 static __always_inline u64
 __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 			u64 flags, struct perf_sample_data *sd)
@@ -442,24 +443,50 @@ __bpf_perf_event_output(struct pt_regs *regs, struct bpf_map *map,
 	return perf_event_output(event, sd, regs);
 }
 
+/*
+ * Support executing tracepoints in normal, irq, and nmi context that each call
+ * bpf_perf_event_output
+ */
+struct bpf_trace_sample_data {
+	struct perf_sample_data sds[3];
+};
+
+static DEFINE_PER_CPU(struct bpf_trace_sample_data, bpf_trace_sds);
+static DEFINE_PER_CPU(int, bpf_trace_nest_level);
 BPF_CALL_5(bpf_perf_event_output, struct pt_regs *, regs, struct bpf_map *, map,
 	   u64, flags, void *, data, u64, size)
 {
-	struct perf_sample_data *sd = this_cpu_ptr(&bpf_trace_sd);
+	struct bpf_trace_sample_data *sds = this_cpu_ptr(&bpf_trace_sds);
+	int nest_level = this_cpu_inc_return(bpf_trace_nest_level);
 	struct perf_raw_record raw = {
 		.frag = {
 			.size = size,
 			.data = data,
 		},
 	};
+	struct perf_sample_data *sd;
+	int err;
 
-	if (unlikely(flags & ~(BPF_F_INDEX_MASK)))
-		return -EINVAL;
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(sds->sds))) {
+		err = -EBUSY;
+		goto out;
+	}
+
+	sd = &sds->sds[nest_level - 1];
+
+	if (unlikely(flags & ~(BPF_F_INDEX_MASK))) {
+		err = -EINVAL;
+		goto out;
+	}
 
 	perf_sample_data_init(sd, 0, 0);
 	sd->raw = &raw;
 
-	return __bpf_perf_event_output(regs, map, flags, sd);
+	err = __bpf_perf_event_output(regs, map, flags, sd);
+
+out:
+	this_cpu_dec(bpf_trace_nest_level);
+	return err;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto = {
@@ -567,6 +594,69 @@ 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()) {
+		/* Do an early check on signal validity. Otherwise,
+		 * the error is lost in deferred irq_work.
+		 */
+		if (unlikely(!valid_signal(sig)))
+			return -EINVAL;
+
+		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 +707,8 @@ 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;
 	}
@@ -822,16 +914,48 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog)
 /*
  * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp
  * to avoid potential recursive reuse issue when/if tracepoints are added
- * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack
+ * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack.
+ *
+ * Since raw tracepoints run despite bpf_prog_active, support concurrent usage
+ * in normal, irq, and nmi context.
  */
-static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs);
+struct bpf_raw_tp_regs {
+	struct pt_regs regs[3];
+};
+static DEFINE_PER_CPU(struct bpf_raw_tp_regs, bpf_raw_tp_regs);
+static DEFINE_PER_CPU(int, bpf_raw_tp_nest_level);
+static struct pt_regs *get_bpf_raw_tp_regs(void)
+{
+	struct bpf_raw_tp_regs *tp_regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	int nest_level = this_cpu_inc_return(bpf_raw_tp_nest_level);
+
+	if (WARN_ON_ONCE(nest_level > ARRAY_SIZE(tp_regs->regs))) {
+		this_cpu_dec(bpf_raw_tp_nest_level);
+		return ERR_PTR(-EBUSY);
+	}
+
+	return &tp_regs->regs[nest_level - 1];
+}
+
+static void put_bpf_raw_tp_regs(void)
+{
+	this_cpu_dec(bpf_raw_tp_nest_level);
+}
+
 BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags, void *, data, u64, size)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return ____bpf_perf_event_output(regs, map, flags, data, size);
+	ret = ____bpf_perf_event_output(regs, map, flags, data, size);
+
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
@@ -848,12 +972,18 @@ static const struct bpf_func_proto bpf_perf_event_output_proto_raw_tp = {
 BPF_CALL_3(bpf_get_stackid_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   struct bpf_map *, map, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
 	/* similar to bpf_perf_event_output_tp, but pt_regs fetched differently */
-	return bpf_get_stackid((unsigned long) regs, (unsigned long) map,
-			       flags, 0, 0);
+	ret = bpf_get_stackid((unsigned long) regs, (unsigned long) map,
+			      flags, 0, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
@@ -868,11 +998,17 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = {
 BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args,
 	   void *, buf, u32, size, u64, flags)
 {
-	struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs);
+	struct pt_regs *regs = get_bpf_raw_tp_regs();
+	int ret;
+
+	if (IS_ERR(regs))
+		return PTR_ERR(regs);
 
 	perf_fetch_caller_regs(regs);
-	return bpf_get_stack((unsigned long) regs, (unsigned long) buf,
-			     (unsigned long) size, flags, 0);
+	ret = bpf_get_stack((unsigned long) regs, (unsigned long) buf,
+			    (unsigned long) size, flags, 0);
+	put_bpf_raw_tp_regs();
+	return ret;
 }
 
 static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = {
@@ -1034,7 +1170,7 @@ static DEFINE_MUTEX(bpf_event_mutex);
 int perf_event_attach_bpf_prog(struct perf_event *event,
 			       struct bpf_prog *prog)
 {
-	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *old_array;
 	struct bpf_prog_array *new_array;
 	int ret = -EEXIST;
 
@@ -1052,7 +1188,7 @@ int perf_event_attach_bpf_prog(struct perf_event *event,
 	if (event->prog)
 		goto unlock;
 
-	old_array = event->tp_event->prog_array;
+	old_array = bpf_event_rcu_dereference(event->tp_event->prog_array);
 	if (old_array &&
 	    bpf_prog_array_length(old_array) >= BPF_TRACE_MAX_PROGS) {
 		ret = -E2BIG;
@@ -1075,7 +1211,7 @@ unlock:
 
 void perf_event_detach_bpf_prog(struct perf_event *event)
 {
-	struct bpf_prog_array __rcu *old_array;
+	struct bpf_prog_array *old_array;
 	struct bpf_prog_array *new_array;
 	int ret;
 
@@ -1084,7 +1220,7 @@ void perf_event_detach_bpf_prog(struct perf_event *event)
 	if (!event->prog)
 		goto unlock;
 
-	old_array = event->tp_event->prog_array;
+	old_array = bpf_event_rcu_dereference(event->tp_event->prog_array);
 	ret = bpf_prog_array_copy(old_array, event->prog, NULL, &new_array);
 	if (ret == -ENOENT)
 		goto unlock;
@@ -1106,6 +1242,7 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 {
 	struct perf_event_query_bpf __user *uquery = info;
 	struct perf_event_query_bpf query = {};
+	struct bpf_prog_array *progs;
 	u32 *ids, prog_cnt, ids_len;
 	int ret;
 
@@ -1130,10 +1267,8 @@ int perf_event_query_prog_array(struct perf_event *event, void __user *info)
 	 */
 
 	mutex_lock(&bpf_event_mutex);
-	ret = bpf_prog_array_copy_info(event->tp_event->prog_array,
-				       ids,
-				       ids_len,
-				       &prog_cnt);
+	progs = bpf_event_rcu_dereference(event->tp_event->prog_array);
+	ret = bpf_prog_array_copy_info(progs, ids, ids_len, &prog_cnt);
 	mutex_unlock(&bpf_event_mutex);
 
 	if (copy_to_user(&uquery->prog_cnt, &prog_cnt, sizeof(prog_cnt)) ||
@@ -1296,6 +1431,20 @@ int bpf_get_perf_event_info(const struct perf_event *event, u32 *prog_id,
 	return err;
 }
 
+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;
+}
+
+subsys_initcall(send_signal_irq_work_init);
+
 #ifdef CONFIG_MODULES
 static int bpf_event_notify(struct notifier_block *nb, unsigned long op,
 			    void *module)