Merge branch 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - Add 'cross-release' support to lockdep, which allows APIs like
   completions, where it's not the 'owner' who releases the lock, to be
   tracked. It's all activated automatically under
   CONFIG_PROVE_LOCKING=y.

 - Clean up (restructure) the x86 atomics op implementation to be more
   readable, in preparation of KASAN annotations. (Dmitry Vyukov)

 - Fix static keys (Paolo Bonzini)

 - Add killable versions of down_read() et al (Kirill Tkhai)

 - Rework and fix jump_label locking (Marc Zyngier, Paolo Bonzini)

 - Rework (and fix) tlb_flush_pending() barriers (Peter Zijlstra)

 - Remove smp_mb__before_spinlock() and convert its usages, introduce
   smp_mb__after_spinlock() (Peter Zijlstra)

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (56 commits)
  locking/lockdep/selftests: Fix mixed read-write ABBA tests
  sched/completion: Avoid unnecessary stack allocation for COMPLETION_INITIALIZER_ONSTACK()
  acpi/nfit: Fix COMPLETION_INITIALIZER_ONSTACK() abuse
  locking/pvqspinlock: Relax cmpxchg's to improve performance on some architectures
  smp: Avoid using two cache lines for struct call_single_data
  locking/lockdep: Untangle xhlock history save/restore from task independence
  locking/refcounts, x86/asm: Disable CONFIG_ARCH_HAS_REFCOUNT for the time being
  futex: Remove duplicated code and fix undefined behaviour
  Documentation/locking/atomic: Finish the document...
  locking/lockdep: Fix workqueue crossrelease annotation
  workqueue/lockdep: 'Fix' flush_work() annotation
  locking/lockdep/selftests: Add mixed read-write ABBA tests
  mm, locking/barriers: Clarify tlb_flush_pending() barriers
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE and CONFIG_LOCKDEP_COMPLETIONS truly non-interactive
  locking/lockdep: Explicitly initialize wq_barrier::done::map
  locking/lockdep: Rename CONFIG_LOCKDEP_COMPLETE to CONFIG_LOCKDEP_COMPLETIONS
  locking/lockdep: Reword title of LOCKDEP_CROSSRELEASE config
  locking/lockdep: Make CONFIG_LOCKDEP_CROSSRELEASE part of CONFIG_PROVE_LOCKING
  locking/refcounts, x86/asm: Implement fast refcount overflow protection
  locking/lockdep: Fix the rollback and overwrite detection logic in crossrelease
  ...

1 files changed, 149 insertions, 16 deletions

diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index fffe49f188e6..bfa8e0b0d6f1 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -18,6 +18,8 @@ extern int lock_stat;
 
 #define MAX_LOCKDEP_SUBCLASSES		8UL
 
+#include <linux/types.h>
+
 #ifdef CONFIG_LOCKDEP
 
 #include <linux/linkage.h>
@@ -29,7 +31,7 @@ extern int lock_stat;
  * We'd rather not expose kernel/lockdep_states.h this wide, but we do need
  * the total number of states... :-(
  */
-#define XXX_LOCK_USAGE_STATES		(1+3*4)
+#define XXX_LOCK_USAGE_STATES		(1+2*4)
 
 /*
  * NR_LOCKDEP_CACHING_CLASSES ... Number of classes
@@ -155,6 +157,12 @@ 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,
@@ -258,8 +266,95 @@ 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 {
+	/*
+	 * Id for each entry in the ring buffer. This is used to
+	 * decide whether the ring buffer was overwritten or not.
+	 *
+	 * For example,
+	 *
+	 *           |<----------- hist_lock ring buffer size ------->|
+	 *           pppppppppppppppppppppiiiiiiiiiiiiiiiiiiiiiiiiiiiii
+	 * wrapped > iiiiiiiiiiiiiiiiiiiiiiiiiii.......................
+	 *
+	 *           where 'p' represents an acquisition in process
+	 *           context, 'i' represents an acquisition in irq
+	 *           context.
+	 *
+	 * In this example, the ring buffer was overwritten by
+	 * acquisitions in irq context, that should be detected on
+	 * rollback or commit.
+	 */
+	unsigned int hist_id;
+
+	/*
+	 * 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 {
+	/*
+	 * When more than one acquisition of crosslocks are overlapped,
+	 * we have to perform commit for them based on cross_gen_id of
+	 * the first acquisition, which allows us to add more true
+	 * dependencies.
+	 *
+	 * Moreover, when no acquisition of a crosslock is in progress,
+	 * we should not perform commit because the lock might not exist
+	 * any more, which might cause incorrect memory access. So we
+	 * have to track the number of acquisitions of a crosslock.
+	 */
+	int nr_acquire;
+
+	/*
+	 * 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:
  */
@@ -282,13 +377,6 @@ 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
  * of dependencies wrong: they are either too broad (they need a class-split)
@@ -363,10 +451,6 @@ static inline void lock_set_subclass(struct lockdep_map *lock,
 
 extern void lock_downgrade(struct lockdep_map *lock, unsigned long ip);
 
-extern void lockdep_set_current_reclaim_state(gfp_t gfp_mask);
-extern void lockdep_clear_current_reclaim_state(void);
-extern void lockdep_trace_alloc(gfp_t mask);
-
 struct pin_cookie { unsigned int val; };
 
 #define NIL_COOKIE (struct pin_cookie){ .val = 0U, }
@@ -375,7 +459,7 @@ extern struct pin_cookie lock_pin_lock(struct lockdep_map *lock);
 extern void lock_repin_lock(struct lockdep_map *lock, struct pin_cookie);
 extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 
-# define INIT_LOCKDEP				.lockdep_recursion = 0, .lockdep_reclaim_gfp = 0,
+# define INIT_LOCKDEP				.lockdep_recursion = 0,
 
 #define lockdep_depth(tsk)	(debug_locks ? (tsk)->lockdep_depth : 0)
 
@@ -416,9 +500,6 @@ static inline void lockdep_on(void)
 # define lock_downgrade(l, i)			do { } while (0)
 # define lock_set_class(l, n, k, s, i)		do { } while (0)
 # define lock_set_subclass(l, s, i)		do { } while (0)
-# define lockdep_set_current_reclaim_state(g)	do { } while (0)
-# define lockdep_clear_current_reclaim_state()	do { } while (0)
-# define lockdep_trace_alloc(g)			do { } while (0)
 # define lockdep_info()				do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) \
 		do { (void)(name); (void)(key); } while (0)
@@ -467,6 +548,58 @@ struct pin_cookie { };
 
 #endif /* !LOCKDEP */
 
+enum xhlock_context_t {
+	XHLOCK_HARD,
+	XHLOCK_SOFT,
+	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);
+
+/*
+ * What we essencially have to initialize is 'nr_acquire'. Other members
+ * will be initialized in add_xlock().
+ */
+#define STATIC_CROSS_LOCK_INIT() \
+	{ .nr_acquire = 0,}
+
+#define STATIC_CROSS_LOCKDEP_MAP_INIT(_name, _key) \
+	{ .map.name = (_name), .map.key = (void *)(_key), \
+	  .map.cross = 1, .xlock = STATIC_CROSS_LOCK_INIT(), }
+
+/*
+ * 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_invariant_state(bool force);
+extern void lockdep_init_task(struct task_struct *task);
+extern void lockdep_free_task(struct task_struct *task);
+#else /* !CROSSRELEASE */
+#define lockdep_init_map_crosslock(m, n, k, s) do {} while (0)
+/*
+ * 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_invariant_state(bool force) {}
+static inline void lockdep_init_task(struct task_struct *task) {}
+static inline void lockdep_free_task(struct task_struct *task) {}
+#endif /* CROSSRELEASE */
+
 #ifdef CONFIG_LOCK_STAT
 
 extern void lock_contended(struct lockdep_map *lock, unsigned long ip);