locking/lockdep: Implement the 'crossrelease' feature

Lockdep is a runtime locking correctness validator that detects and
reports a deadlock or its possibility by checking dependencies between
locks. It's useful since it does not report just an actual deadlock but
also the possibility of a deadlock that has not actually happened yet.
That enables problems to be fixed before they affect real systems.

However, this facility is only applicable to typical locks, such as
spinlocks and mutexes, which are normally released within the context in
which they were acquired. However, synchronization primitives like page
locks or completions, which are allowed to be released in any context,
also create dependencies and can cause a deadlock.

So lockdep should track these locks to do a better job. The 'crossrelease'
implementation makes these primitives also be tracked.
Signed-off-by: Byungchul Park <byungchul.park@lge.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Thomas Gleixner <tglx@linutronix.de>
Cc: akpm@linux-foundation.org
Cc: boqun.feng@gmail.com
Cc: kernel-team@lge.com
Cc: kirill@shutemov.name
Cc: npiggin@gmail.com
Cc: walken@google.com
Cc: willy@infradead.org
Link: http://lkml.kernel.org/r/1502089981-21272-6-git-send-email-byungchul.park@lge.comSigned-off-by: Ingo Molnar <mingo@kernel.org>

include/linux/irqflags.h

@@ -23,10 +23,26 @@
 # define trace_softirq_context(p)	((p)->softirq_context)
 # define trace_hardirqs_enabled(p)	((p)->hardirqs_enabled)
 # define trace_softirqs_enabled(p)	((p)->softirqs_enabled)
-# define trace_hardirq_enter()	do { current->hardirq_context++; } while (0)
-# define trace_hardirq_exit()	do { current->hardirq_context--; } while (0)
-# define lockdep_softirq_enter()	do { current->softirq_context++; } while (0)
-# define lockdep_softirq_exit()	do { current->softirq_context--; } while (0)
+# define trace_hardirq_enter()			\
+do {						\
+	current->hardirq_context++;		\
+	crossrelease_hist_start(XHLOCK_HARD);	\
+} while (0)
+# define trace_hardirq_exit()			\
+do {						\
+	current->hardirq_context--;		\
+	crossrelease_hist_end(XHLOCK_HARD);	\
+} while (0)
+# define lockdep_softirq_enter()		\
+do {						\
+	current->softirq_context++;		\
+	crossrelease_hist_start(XHLOCK_SOFT);	\
+} while (0)
+# define lockdep_softirq_exit()			\
+do {						\
+	current->softirq_context--;		\
+	crossrelease_hist_end(XHLOCK_SOFT);	\
+} while (0)
 # define INIT_TRACE_IRQFLAGS	.softirqs_enabled = 1,
 #else
 # define trace_hardirqs_on()		do { } while (0)

include/linux/lockdep.h

@@ -155,6 +155,12 @@ struct lockdep_map {
 	int				cpu;
 	unsigned long			ip;
 #endif
+#ifdef CONFIG_LOCKDEP_CROSSRELEASE
+	/*
+	 * Whether it's a crosslock.
+	 */
+	int				cross;
+#endif
 };
 
 static inline void lockdep_copy_map(struct lockdep_map *to,
@@ -258,7 +264,61 @@ struct held_lock {
 	unsigned int hardirqs_off:1;
 	unsigned int references:12;					/* 32 bits */
 	unsigned int pin_count;
+#ifdef CONFIG_LOCKDEP_CROSSRELEASE
+	/*
+	 * Generation id.
+	 *
+	 * A value of cross_gen_id will be stored when holding this,
+	 * which is globally increased whenever each crosslock is held.
+	 */
+	unsigned int gen_id;
+#endif
+};
+
+#ifdef CONFIG_LOCKDEP_CROSSRELEASE
+#define MAX_XHLOCK_TRACE_ENTRIES 5
+
+/*
+ * This is for keeping locks waiting for commit so that true dependencies
+ * can be added at commit step.
+ */
+struct hist_lock {
+	/*
+	 * Seperate stack_trace data. This will be used at commit step.
+	 */
+	struct stack_trace	trace;
+	unsigned long		trace_entries[MAX_XHLOCK_TRACE_ENTRIES];
+
+	/*
+	 * Seperate hlock instance. This will be used at commit step.
+	 *
+	 * TODO: Use a smaller data structure containing only necessary
+	 * data. However, we should make lockdep code able to handle the
+	 * smaller one first.
+	 */
+	struct held_lock	hlock;
+};
+
+/*
+ * To initialize a lock as crosslock, lockdep_init_map_crosslock() should
+ * be called instead of lockdep_init_map().
+ */
+struct cross_lock {
+	/*
+	 * Seperate hlock instance. This will be used at commit step.
+	 *
+	 * TODO: Use a smaller data structure containing only necessary
+	 * data. However, we should make lockdep code able to handle the
+	 * smaller one first.
+	 */
+	struct held_lock	hlock;
+};
+
+struct lockdep_map_cross {
+	struct lockdep_map map;
+	struct cross_lock xlock;
 };
+#endif
 
 /*
  * Initialization, self-test and debugging-output methods:
@@ -281,13 +341,6 @@ extern void lockdep_on(void);
 extern void lockdep_init_map(struct lockdep_map *lock, const char *name,
 			     struct lock_class_key *key, int subclass);
 
-/*
- * To initialize a lockdep_map statically use this macro.
- * Note that _name must not be NULL.
- */
-#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
-	{ .name = (_name), .key = (void *)(_key), }
-
 /*
  * Reinitialize a lock key - for cases where there is special locking or
  * special initialization of locks so that the validator gets the scope
@@ -460,6 +513,49 @@ struct pin_cookie { };
 
 #endif /* !LOCKDEP */
 
+enum xhlock_context_t {
+	XHLOCK_HARD,
+	XHLOCK_SOFT,
+	XHLOCK_PROC,
+	XHLOCK_CTX_NR,
+};
+
+#ifdef CONFIG_LOCKDEP_CROSSRELEASE
+extern void lockdep_init_map_crosslock(struct lockdep_map *lock,
+				       const char *name,
+				       struct lock_class_key *key,
+				       int subclass);
+extern void lock_commit_crosslock(struct lockdep_map *lock);
+
+#define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .map.name = (_name), .map.key = (void *)(_key), \
+	  .map.cross = 1, }
+
+/*
+ * To initialize a lockdep_map statically use this macro.
+ * Note that _name must not be NULL.
+ */
+#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .name = (_name), .key = (void *)(_key), .cross = 0, }
+
+extern void crossrelease_hist_start(enum xhlock_context_t c);
+extern void crossrelease_hist_end(enum xhlock_context_t c);
+extern void lockdep_init_task(struct task_struct *task);
+extern void lockdep_free_task(struct task_struct *task);
+#else
+/*
+ * To initialize a lockdep_map statically use this macro.
+ * Note that _name must not be NULL.
+ */
+#define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .name = (_name), .key = (void *)(_key), }
+
+static inline void crossrelease_hist_start(enum xhlock_context_t c) {}
+static inline void crossrelease_hist_end(enum xhlock_context_t c) {}
+static inline void lockdep_init_task(struct task_struct *task) {}
+static inline void lockdep_free_task(struct task_struct *task) {}
+#endif
+
 #ifdef CONFIG_LOCK_STAT
 
 extern void lock_contended(struct lockdep_map *lock, unsigned long ip);

include/linux/sched.h

@@ -848,6 +848,14 @@ struct task_struct {
 	struct held_lock		held_locks[MAX_LOCK_DEPTH];
 #endif
 
+#ifdef CONFIG_LOCKDEP_CROSSRELEASE
+#define MAX_XHLOCKS_NR 64UL
+	struct hist_lock *xhlocks; /* Crossrelease history locks */
+	unsigned int xhlock_idx;
+	/* For restoring at history boundaries */
+	unsigned int xhlock_idx_hist[XHLOCK_CTX_NR];
+#endif
+
 #ifdef CONFIG_UBSAN
 	unsigned int			in_ubsan;
 #endif

kernel/exit.c

@@ -920,6 +920,7 @@ void __noreturn do_exit(long code)
 	exit_rcu();
 	TASKS_RCU(__srcu_read_unlock(&tasks_rcu_exit_srcu, tasks_rcu_i));
 
+	lockdep_free_task(tsk);
 	do_task_dead();
 }
 EXPORT_SYMBOL_GPL(do_exit);

kernel/fork.c

@@ -484,6 +484,8 @@ void __init fork_init(void)
 	cpuhp_setup_state(CPUHP_BP_PREPARE_DYN, "fork:vm_stack_cache",
 			  NULL, free_vm_stack_cache);
 #endif
+
+	lockdep_init_task(&init_task);
 }
 
 int __weak arch_dup_task_struct(struct task_struct *dst,
@@ -1691,6 +1693,7 @@ static __latent_entropy struct task_struct *copy_process(
 	p->lockdep_depth = 0; /* no locks held yet */
 	p->curr_chain_key = 0;
 	p->lockdep_recursion = 0;
+	lockdep_init_task(p);
 #endif
 
 #ifdef CONFIG_DEBUG_MUTEXES
@@ -1949,6 +1952,7 @@ static __latent_entropy struct task_struct *copy_process(
 bad_fork_cleanup_perf:
 	perf_event_free_task(p);
 bad_fork_cleanup_policy:
+	lockdep_free_task(p);
 #ifdef CONFIG_NUMA
 	mpol_put(p->mempolicy);
 bad_fork_cleanup_threadgroup_lock:

kernel/workqueue.c

@@ -2093,6 +2093,7 @@ __acquires(&pool->lock)
 
 	lock_map_acquire_read(&pwq->wq->lockdep_map);
 	lock_map_acquire(&lockdep_map);
+	crossrelease_hist_start(XHLOCK_PROC);
 	trace_workqueue_execute_start(work);
 	worker->current_func(work);
 	/*
@@ -2100,6 +2101,7 @@ __acquires(&pool->lock)
 	 * point will only record its address.
 	 */
 	trace_workqueue_execute_end(work);
+	crossrelease_hist_end(XHLOCK_PROC);
 	lock_map_release(&lockdep_map);
 	lock_map_release(&pwq->wq->lockdep_map);
 

lib/Kconfig.debug

@@ -1150,6 +1150,18 @@ config LOCK_STAT
 	 CONFIG_LOCK_STAT defines "contended" and "acquired" lock events.
 	 (CONFIG_LOCKDEP defines "acquire" and "release" events.)
 
+config LOCKDEP_CROSSRELEASE
+	bool "Lock debugging: make lockdep work for crosslocks"
+	depends on PROVE_LOCKING
+	default n
+	help
+	 This makes lockdep work for crosslock which is a lock allowed to
+	 be released in a different context from the acquisition context.
+	 Normally a lock must be released in the context acquiring the lock.
+	 However, relexing this constraint helps synchronization primitives
+	 such as page locks or completions can use the lock correctness
+	 detector, lockdep.
+
 config DEBUG_LOCKDEP
 	bool "Lock dependency engine debugging"
 	depends on DEBUG_KERNEL && LOCKDEP