[PATCH v8 16/21] tracing/remotes: Add dump_on_panic tracefs file

[Vincent Donnefort <vdonnefort@google.com>]

When enabled, dump_on_panic will dump the content of the trace remote
buffer if the system panics.

Signed-off-by: Vincent Donnefort <vdonnefort@google.com>
---
 kernel/trace/trace_remote.c | 228 ++++++++++++++++++++++++++++++------
 1 file changed, 190 insertions(+), 38 deletions(-)

diff --git a/kernel/trace/trace_remote.c b/kernel/trace/trace_remote.c
index 276bf94e837b..2946f263c79c 100644
--- a/kernel/trace/trace_remote.c
+++ b/kernel/trace/trace_remote.c
@@ -7,6 +7,8 @@
 #include <linux/kstrtox.h>
 #include <linux/lockdep.h>
 #include <linux/mutex.h>
+#include <linux/nmi.h>
+#include <linux/panic_notifier.h>
 #include <linux/tracefs.h>
 #include <linux/trace_remote.h>
 #include <linux/trace_seq.h>
@@ -22,6 +24,7 @@ enum tri_type {
 	TRI_CONSUMING,
 	TRI_NONCONSUMING,
 	TRI_DMESG,
+	TRI_PANIC,
 };
 
 struct trace_remote_iterator {
@@ -59,6 +62,9 @@ struct trace_remote {
 	unsigned int			poll_cnt;
 	unsigned int			poll_ms;
 	bool				tracing_on;
+	bool				panic_on;
+	struct notifier_block		panic_notifier;
+	struct trace_remote_iterator	*panic_iter;
 	struct delayed_work		poll_work;
 };
 
@@ -71,10 +77,15 @@ static bool trace_remote_loaded(struct trace_remote *remote)
 	return !!remote->trace_buffer;
 }
 
+static void trace_remote_unload(struct trace_remote *remote);
+static int trace_remote_panic_load(struct trace_remote *remote);
+static void trace_remote_panic_unload(struct trace_remote *remote);
+
 static int trace_remote_load(struct trace_remote *remote)
 {
 	struct ring_buffer_remote *rb_remote = &remote->rb_remote;
 	struct trace_buffer_desc *desc;
+	int ret = 0;
 
 	lockdep_assert_held(&remote->lock);
 
@@ -89,15 +100,28 @@ static int trace_remote_load(struct trace_remote *remote)
 	rb_remote->swap_reader_page = remote->cbs->swap_reader_page;
 	rb_remote->priv = remote->priv;
 	rb_remote->reset = remote->cbs->reset;
+	remote->trace_buffer_desc = desc;
 	remote->trace_buffer = ring_buffer_alloc_remote(rb_remote);
 	if (!remote->trace_buffer) {
 		remote->cbs->unload_trace_buffer(desc, remote->priv);
 		return -ENOMEM;
 	}
 
-	remote->trace_buffer_desc = desc;
+	if (remote->panic_on) {
+		ret = trace_remote_panic_load(remote);
+		if (ret)
+			trace_remote_unload(remote);
+	}
 
-	return 0;
+	return ret;
+}
+
+static void trace_remote_unload(struct trace_remote *remote)
+{
+	trace_remote_panic_unload(remote);
+	ring_buffer_free(remote->trace_buffer);
+	remote->trace_buffer = NULL;
+	remote->cbs->unload_trace_buffer(remote->trace_buffer_desc, remote->priv);
 }
 
 static void trace_remote_try_unload(struct trace_remote *remote)
@@ -115,9 +139,7 @@ static void trace_remote_try_unload(struct trace_remote *remote)
 	if (!ring_buffer_empty(remote->trace_buffer))
 		return;
 
-	ring_buffer_free(remote->trace_buffer);
-	remote->trace_buffer = NULL;
-	remote->cbs->unload_trace_buffer(remote->trace_buffer_desc, remote->priv);
+	trace_remote_unload(remote);
 }
 
 static int trace_remote_enable_tracing(struct trace_remote *remote)
@@ -440,12 +462,20 @@ static struct trace_remote_iterator
 
 	lockdep_assert_held(&remote->lock);
 
-	if (type == TRI_NONCONSUMING && !trace_remote_loaded(remote))
-		return NULL;
-
-	ret = trace_remote_get(remote, cpu);
-	if (ret)
-		return ERR_PTR(ret);
+	switch (type) {
+	case TRI_NONCONSUMING:
+		if (!trace_remote_loaded(remote))
+			return NULL;
+		fallthrough;
+	case TRI_CONSUMING:
+	case TRI_DMESG:
+		ret = trace_remote_get(remote, cpu);
+		if (ret)
+			return ERR_PTR(ret);
+		break;
+	case TRI_PANIC:
+		break;
+	}
 
 	if (!trace_remote_has_cpu(remote, cpu)) {
 		ret = -ENODEV;
@@ -453,40 +483,46 @@ static struct trace_remote_iterator
 	}
 
 	iter = kzalloc_obj(*iter);
-	if (iter) {
-		iter->remote = remote;
-		iter->cpu = cpu;
-		iter->type = type;
-		trace_seq_init(&iter->seq);
+	if (!iter) {
+		ret = -ENOMEM;
+		goto err;
+	}
 
-		switch (type) {
-		case TRI_DMESG:
-			/* only one dmesg iter allowed */
-			if (WARN_ON_ONCE(remote->dmesg)) {
-				ret = -EBUSY;
-				break;
-			}
-			smp_store_release(&remote->dmesg, iter);
-			fallthrough;
-		case TRI_CONSUMING:
-			trace_remote_inc_poll(remote);
-			break;
-		case TRI_NONCONSUMING:
-			ret = __alloc_ring_buffer_iter(iter, cpu);
-			break;
+	iter->remote = remote;
+	iter->cpu = cpu;
+	iter->type = type;
+	trace_seq_init(&iter->seq);
+
+	switch (type) {
+	case TRI_DMESG:
+		/* only one dmesg iter allowed */
+		if (WARN_ON_ONCE(remote->dmesg)) {
+			ret = -EBUSY;
+			goto err;
 		}
-
+		smp_store_release(&remote->dmesg, iter);
+		fallthrough;
+	case TRI_CONSUMING:
+		trace_remote_inc_poll(remote);
+		break;
+	case TRI_PANIC:
+	case TRI_NONCONSUMING:
+		ret = __alloc_ring_buffer_iter(iter, cpu);
 		if (ret)
 			goto err;
-
-		return iter;
+		break;
 	}
-	ret = -ENOMEM;
+
+	return iter;
 
 err:
 	kfree(iter);
-	trace_remote_put(remote);
-
+	switch (type) {
+	case TRI_PANIC:
+		break;
+	default:
+		trace_remote_put(remote);
+	}
 	return ERR_PTR(ret);
 }
 
@@ -509,14 +545,18 @@ static void trace_remote_iter_free(struct trace_remote_iterator *iter)
 		fallthrough;
 	case TRI_CONSUMING:
 		trace_remote_dec_poll(remote);
+		trace_remote_put(remote);
 		break;
 	case TRI_NONCONSUMING:
+		__free_ring_buffer_iter(iter, iter->cpu);
+		trace_remote_put(remote);
+		break;
+	case TRI_PANIC:
 		__free_ring_buffer_iter(iter, iter->cpu);
 		break;
 	}
 
 	kfree(iter);
-	trace_remote_put(remote);
 }
 
 static bool trace_remote_iter_is_consuming(struct trace_remote_iterator *iter)
@@ -990,6 +1030,113 @@ static int dmesg_show(struct seq_file *s, void *unused)
 }
 DEFINE_TRACE_REMOTE_ATTRIBUTE(dmesg);
 
+static int trace_remote_panic_handler(struct notifier_block *self, unsigned long ev, void *v)
+{
+	struct trace_remote *remote = container_of(self, struct trace_remote, panic_notifier);
+	struct trace_remote_iterator *iter = smp_load_acquire(&remote->panic_iter);
+	int cpu;
+
+	if (!iter) {
+		pr_warn("Unexpected error: no panic iterator for the trace remote\n");
+		return NOTIFY_DONE;
+	}
+
+	for_each_possible_cpu(cpu)
+		ring_buffer_iter_reset(iter->rb_iters[cpu]);
+
+	while (trace_remote_iter_read_event(iter)) {
+		trace_seq_init(&iter->seq);
+
+		trace_remote_iter_print_event(iter);
+		trace_seq_putc(&iter->seq, 0);
+		pr_emerg("%s", seq_buf_str(&iter->seq.seq));
+
+		trace_remote_iter_move(iter);
+		touch_nmi_watchdog();
+	}
+
+	return NOTIFY_DONE;
+}
+
+static int trace_remote_panic_load(struct trace_remote *remote)
+{
+	struct notifier_block *notifier = &remote->panic_notifier;
+	struct trace_remote_iterator *iter;
+
+	lockdep_assert_held(&remote->lock);
+
+	if (remote->panic_iter)
+		return 0;
+
+	iter = trace_remote_iter(remote, RING_BUFFER_ALL_CPUS, TRI_PANIC);
+	if (IS_ERR(iter))
+		return PTR_ERR(iter);
+
+	smp_store_release(&remote->panic_iter, iter);
+
+	notifier->notifier_call = trace_remote_panic_handler;
+	notifier->priority = INT_MAX - 1;
+	atomic_notifier_chain_register(&panic_notifier_list, notifier);
+
+	return 0;
+}
+
+static void trace_remote_panic_unload(struct trace_remote *remote)
+{
+	struct trace_remote_iterator *iter = remote->panic_iter;
+
+	lockdep_assert_held(&remote->lock);
+
+	if (!iter)
+		return;
+
+	atomic_notifier_chain_unregister(&panic_notifier_list, &remote->panic_notifier);
+	smp_store_release(&remote->panic_iter, NULL);
+	trace_remote_iter_free(iter);
+}
+
+static ssize_t dump_on_panic_write(struct file *filp, const char __user *ubuf,
+				   size_t cnt, loff_t *ppos)
+{
+	struct seq_file *seq = filp->private_data;
+	struct trace_remote *remote = seq->private;
+	bool enable;
+	int ret;
+
+	ret = kstrtobool_from_user(ubuf, cnt, &enable);
+	if (ret)
+		return ret;
+
+	guard(mutex)(&remote->lock);
+
+	if (enable == remote->panic_on)
+		return cnt;
+
+	if (trace_remote_loaded(remote)) {
+		if (enable) {
+			ret = trace_remote_panic_load(remote);
+			if (ret)
+				return ret;
+		} else {
+			trace_remote_panic_unload(remote);
+		}
+	}
+
+	WRITE_ONCE(remote->panic_on, enable);
+
+	return cnt;
+}
+
+static int dump_on_panic_show(struct seq_file *s, void *unused)
+{
+	struct trace_remote *remote = s->private;
+
+	seq_printf(s, "%d\n", READ_ONCE(remote->panic_on));
+
+	return 0;
+}
+DEFINE_TRACE_REMOTE_ATTRIBUTE(dump_on_panic);
+
 static int trace_remote_init_tracefs(const char *name, struct trace_remote *remote)
 {
 	struct dentry *remote_d, *percpu_d, *d;
@@ -1017,6 +1164,11 @@ static int trace_remote_init_tracefs(const char *name, struct trace_remote *remo
 	if (!d)
 		goto err;
 
+	d = trace_create_file("dump_on_panic", TRACEFS_MODE_WRITE, remote_d, remote,
+			      &dump_on_panic_fops);
+	if (!d)
+		goto err;
+
 	d = trace_create_file("buffer_size_kb", TRACEFS_MODE_WRITE, remote_d, remote,
 			      &buffer_size_kb_fops);
 	if (!d)
-- 
2.56.0.455.g6c5a503b38-goog