printk: queue wake_up_klogd irq_work only if per-CPU areas are ready

printk_deferred(), similarly to printk_safe/printk_nmi, does not
immediately attempt to print a new message on the consoles, avoiding
calls into non-reentrant kernel paths, e.g. scheduler or timekeeping,
which potentially can deadlock the system.

Those printk() flavors, instead, rely on per-CPU flush irq_work to print
messages from safer contexts.  For same reasons (recursive scheduler or
timekeeping calls) printk() uses per-CPU irq_work in order to wake up
user space syslog/kmsg readers.

However, only printk_safe/printk_nmi do make sure that per-CPU areas
have been initialised and that it's safe to modify per-CPU irq_work.
This means that, for instance, should printk_deferred() be invoked "too
early", that is before per-CPU areas are initialised, printk_deferred()
will perform illegal per-CPU access.

Lech Perczak [0] reports that after commit 1b710b1b10ef ("char/random:
silence a lockdep splat with printk()") user-space syslog/kmsg readers
are not able to read new kernel messages.

The reason is printk_deferred() being called too early (as was pointed
out by Petr and John).

Fix printk_deferred() and do not queue per-CPU irq_work before per-CPU
areas are initialized.

Link: https://lore.kernel.org/lkml/aa0732c6-5c4e-8a8b-a1c1-75ebe3dca05b@camlintechnologies.com/
Reported-by: Lech Perczak <l.perczak@camlintechnologies.com>
Signed-off-by: Sergey Senozhatsky <sergey.senozhatsky@gmail.com>
Tested-by: Jann Horn <jannh@google.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Cc: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Cc: Theodore Ts'o <tytso@mit.edu>
Cc: John Ogness <john.ogness@linutronix.de>
Signed-off-by: Linus Torvalds <torvalds@linux-foundation.org>

1 files changed, 34 insertions, 0 deletions

diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 633f41a11d75..9a9b6156270b 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -460,6 +460,18 @@ static char __log_buf[__LOG_BUF_LEN] __aligned(LOG_ALIGN);
 static char *log_buf = __log_buf;
 static u32 log_buf_len = __LOG_BUF_LEN;
 
+/*
+ * We cannot access per-CPU data (e.g. per-CPU flush irq_work) before
+ * per_cpu_areas are initialised. This variable is set to true when
+ * it's safe to access per-CPU data.
+ */
+static bool __printk_percpu_data_ready __read_mostly;
+
+bool printk_percpu_data_ready(void)
+{
+	return __printk_percpu_data_ready;
+}
+
 /* Return log buffer address */
 char *log_buf_addr_get(void)
 {
@@ -1146,12 +1158,28 @@ static void __init log_buf_add_cpu(void)
 static inline void log_buf_add_cpu(void) {}
 #endif /* CONFIG_SMP */
 
+static void __init set_percpu_data_ready(void)
+{
+	printk_safe_init();
+	/* Make sure we set this flag only after printk_safe() init is done */
+	barrier();
+	__printk_percpu_data_ready = true;
+}
+
 void __init setup_log_buf(int early)
 {
 	unsigned long flags;
 	char *new_log_buf;
 	unsigned int free;
 
+	/*
+	 * Some archs call setup_log_buf() multiple times - first is very
+	 * early, e.g. from setup_arch(), and second - when percpu_areas
+	 * are initialised.
+	 */
+	if (!early)
+		set_percpu_data_ready();
+
 	if (log_buf != __log_buf)
 		return;
 
@@ -2975,6 +3003,9 @@ static DEFINE_PER_CPU(struct irq_work, wake_up_klogd_work) = {
 
 void wake_up_klogd(void)
 {
+	if (!printk_percpu_data_ready())
+		return;
+
 	preempt_disable();
 	if (waitqueue_active(&log_wait)) {
 		this_cpu_or(printk_pending, PRINTK_PENDING_WAKEUP);
@@ -2985,6 +3016,9 @@ void wake_up_klogd(void)
 
 void defer_console_output(void)
 {
+	if (!printk_percpu_data_ready())
+		return;
+
 	preempt_disable();
 	__this_cpu_or(printk_pending, PRINTK_PENDING_OUTPUT);
 	irq_work_queue(this_cpu_ptr(&wake_up_klogd_work));