kernel/lib: add additional debug capabilites for data corruption

Data corruptions in the kernel often end up in system crashes that
are easier to debug closer to the time of detection. Specifically,
if we do not panic immediately after lock or list corruptions have been
detected, the problem context is lost in the ensuing system mayhem.
Add support for allowing system crash immediately after such corruptions
are detected. The CONFIG option controls the enabling/disabling of the
feature.

Change-Id: I9b2eb62da506a13007acff63e85e9515145909ff
Signed-off-by: Syed Rameez Mustafa <rameezmustafa@codeaurora.org>
[abhimany: minor merge conflict resolution]
Signed-off-by: Abhimanyu Kapur <abhimany@codeaurora.org>

include/linux/bug.h

@@ -109,4 +109,10 @@ static inline enum bug_trap_type report_bug(unsigned long bug_addr,
 }
 
 #endif	/* CONFIG_GENERIC_BUG */
+
+#ifdef CONFIG_PANIC_ON_DATA_CORRUPTION
+#define PANIC_CORRUPTION 1
+#else
+#define PANIC_CORRUPTION 0
+#endif  /* CONFIG_PANIC_ON_DATA_CORRUPTION */
 #endif	/* _LINUX_BUG_H */

kernel/locking/spinlock_debug.c

@@ -12,6 +12,7 @@
 #include <linux/debug_locks.h>
 #include <linux/delay.h>
 #include <linux/export.h>
+#include <linux/bug.h>
 
 void __raw_spin_lock_init(raw_spinlock_t *lock, const char *name,
 			  struct lock_class_key *key)
@@ -64,6 +65,7 @@ static void spin_dump(raw_spinlock_t *lock, const char *msg)
 		owner ? owner->comm : "<none>",
 		owner ? task_pid_nr(owner) : -1,
 		lock->owner_cpu);
+	BUG_ON(PANIC_CORRUPTION);
 	dump_stack();
 }
 

kernel/workqueue.c

@@ -48,6 +48,7 @@
 #include <linux/nodemask.h>
 #include <linux/moduleparam.h>
 #include <linux/uaccess.h>
+#include <linux/bug.h>
 
 #include "workqueue_internal.h"
 
@@ -2042,6 +2043,7 @@ __acquires(&pool->lock)
 		       current->comm, preempt_count(), task_pid_nr(current),
 		       worker->current_func);
 		debug_show_held_locks(current);
+		BUG_ON(PANIC_CORRUPTION);
 		dump_stack();
 	}
 

lib/Kconfig.debug

@@ -1893,6 +1893,13 @@ config TEST_STATIC_KEYS
 
 	  If unsure, say N.
 
+config PANIC_ON_DATA_CORRUPTION
+	bool "Cause a Kernel Panic When Data Corruption is detected"
+	help
+	 Select this option to upgrade warnings for potentially
+	 recoverable data corruption scenarios to system-halting panics,
+	 for easier detection and debug.
+
 source "samples/Kconfig"
 
 source "lib/Kconfig.kgdb"

lib/list_debug.c

@@ -11,6 +11,7 @@
 #include <linux/bug.h>
 #include <linux/kernel.h>
 #include <linux/rculist.h>
+#include <linux/bug.h>
 
 /*
  * Insert a new entry between two known consecutive entries.
@@ -34,6 +35,10 @@ void __list_add(struct list_head *new,
 	WARN(new == prev || new == next,
 	     "list_add double add: new=%p, prev=%p, next=%p.\n",
 	     new, prev, next);
+
+	BUG_ON((prev->next != next || next->prev != prev ||
+		 new == prev || new == next) && PANIC_CORRUPTION);
+
 	next->prev = new;
 	new->next = next;
 	new->prev = prev;
@@ -59,8 +64,10 @@ void __list_del_entry(struct list_head *entry)
 		"but was %p\n", entry, prev->next) ||
 	    WARN(next->prev != entry,
 		"list_del corruption. next->prev should be %p, "
-		"but was %p\n", entry, next->prev))
+		"but was %p\n", entry, next->prev)) {
+		BUG_ON(PANIC_CORRUPTION);
 		return;
+	}
 
 	__list_del(prev, next);
 }