printk/panic: Add option to allow non-panic CPUs to write to the ring buffer.

Commit 779dbc2e78d7 ("printk: Avoid non-panic CPUs writing to ringbuffer")
aimed to isolate panic-related messages. However, when panic() itself
malfunctions, messages from non-panic CPUs become crucial for debugging.

While commit bcc954c6caba ("printk/panic: Allow cpu backtraces to
be written into ringbuffer during panic") enables non-panic CPU
backtraces, it may not provide sufficient diagnostic information.

Introduce the "debug_non_panic_cpus" command-line option, enabling
non-panic CPU messages to be stored in the ring buffer during a panic.
This also prevents discarding non-finalized messages from non-panic CPUs
during console flushing, providing a more comprehensive view of system
state during critical failures.

Link: https://lore.kernel.org/all/Z8cLEkqLL2IOyNIj@pathway/
Signed-off-by: Donghyeok Choe <d7271.choe@samsung.com>
Reviewed-by: Petr Mladek <pmladek@suse.com>
Link: https://lore.kernel.org/r/20250318022320.2428155-1-d7271.choe@samsung.com
[pmladek@suse.com: Added documentation, added module_parameter, removed printk_ prefix.]
Tested-by: Petr Mladek <pmladek@suse.com>
Signed-off-by: Petr Mladek <pmladek@suse.com>

4 files changed, 36 insertions, 6 deletions

diff --git a/Documentation/admin-guide/kernel-parameters.txt b/Documentation/admin-guide/kernel-parameters.txt
index 05f5935eeac8..961bc82f0599 100644
--- a/Documentation/admin-guide/kernel-parameters.txt
+++ b/Documentation/admin-guide/kernel-parameters.txt
@@ -5013,6 +5013,14 @@
 			Format: <bool>
 			default: 0 (auto_verbose is enabled)
 
+	printk.debug_non_panic_cpus=
+			Allows storing messages from non-panic CPUs into
+			the printk log buffer during panic(). They are
+			flushed to consoles by the panic-CPU on
+			a best-effort basis.
+			Format: <bool> (1/Y/y=enable, 0/N/n=disable)
+			Default: disabled
+
 	printk.devkmsg={on,off,ratelimit}
 			Control writing to /dev/kmsg.
 			on - unlimited logging to /dev/kmsg from userspace
diff --git a/kernel/printk/internal.h b/kernel/printk/internal.h
index a91bdf802967..48a24e7b309d 100644
--- a/kernel/printk/internal.h
+++ b/kernel/printk/internal.h
@@ -64,6 +64,7 @@ struct dev_printk_info;
 
 extern struct printk_ringbuffer *prb;
 extern bool printk_kthreads_running;
+extern bool debug_non_panic_cpus;
 
 __printf(4, 0)
 int vprintk_store(int facility, int level,
diff --git a/kernel/printk/printk.c b/kernel/printk/printk.c
index 2590498d8353..74b4734a87b9 100644
--- a/kernel/printk/printk.c
+++ b/kernel/printk/printk.c
@@ -2375,6 +2375,22 @@ void printk_legacy_allow_panic_sync(void)
 	}
 }
 
+bool __read_mostly debug_non_panic_cpus;
+
+#ifdef CONFIG_PRINTK_CALLER
+static int __init debug_non_panic_cpus_setup(char *str)
+{
+	debug_non_panic_cpus = true;
+	pr_info("allow messages from non-panic CPUs in panic()\n");
+
+	return 0;
+}
+early_param("debug_non_panic_cpus", debug_non_panic_cpus_setup);
+module_param(debug_non_panic_cpus, bool, 0644);
+MODULE_PARM_DESC(debug_non_panic_cpus,
+		 "allow messages from non-panic CPUs in panic()");
+#endif
+
 asmlinkage int vprintk_emit(int facility, int level,
 			    const struct dev_printk_info *dev_info,
 			    const char *fmt, va_list args)
@@ -2391,7 +2407,9 @@ asmlinkage int vprintk_emit(int facility, int level,
 	 * non-panic CPUs are generating any messages, they will be
 	 * silently dropped.
 	 */
-	if (other_cpu_in_panic() && !panic_triggering_all_cpu_backtrace)
+	if (other_cpu_in_panic() &&
+	    !debug_non_panic_cpus &&
+	    !panic_triggering_all_cpu_backtrace)
 		return 0;
 
 	printk_get_console_flush_type(&ft);
diff --git a/kernel/printk/printk_ringbuffer.c b/kernel/printk/printk_ringbuffer.c
index 88e8f3a61922..d9fb053cff67 100644
--- a/kernel/printk/printk_ringbuffer.c
+++ b/kernel/printk/printk_ringbuffer.c
@@ -2133,9 +2133,9 @@ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq,
 			 * there may be other finalized records beyond that
 			 * need to be printed for a panic situation. If this
 			 * is the panic CPU, skip this
-			 * non-existent/non-finalized record unless it is
-			 * at or beyond the head, in which case it is not
-			 * possible to continue.
+			 * non-existent/non-finalized record unless non-panic
+			 * CPUs are still running and their debugging is
+			 * explicitly enabled.
 			 *
 			 * Note that new messages printed on panic CPU are
 			 * finalized when we are here. The only exception
@@ -2143,10 +2143,13 @@ static bool _prb_read_valid(struct printk_ringbuffer *rb, u64 *seq,
 			 * But it would have the sequence number returned
 			 * by "prb_next_reserve_seq() - 1".
 			 */
-			if (this_cpu_in_panic() && ((*seq + 1) < prb_next_reserve_seq(rb)))
+			if (this_cpu_in_panic() &&
+			    (!debug_non_panic_cpus || legacy_allow_panic_sync) &&
+			    ((*seq + 1) < prb_next_reserve_seq(rb))) {
 				(*seq)++;
-			else
+			} else {
 				return false;
+			}
 		}
 	}