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
  ...

21 files changed, 398 insertions, 130 deletions

diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index dad68bf46c77..8d28eb010d0d 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -21,6 +21,8 @@ typedef struct {
 extern long long atomic64_read(const atomic64_t *v);
 extern void	 atomic64_set(atomic64_t *v, long long i);
 
+#define atomic64_set_release(v, i)	atomic64_set((v), (i))
+
 #define ATOMIC64_OP(op)							\
 extern void	 atomic64_##op(long long a, atomic64_t *v);
 
diff --git a/include/asm-generic/futex.h b/include/asm-generic/futex.h
index bf2d34c9d804..f0d8b1c51343 100644
--- a/include/asm-generic/futex.h
+++ b/include/asm-generic/futex.h
@@ -13,7 +13,7 @@
  */
 
 /**
- * futex_atomic_op_inuser() - Atomic arithmetic operation with constant
+ * arch_futex_atomic_op_inuser() - Atomic arithmetic operation with constant
  *			  argument and comparison of the previous
  *			  futex value with another constant.
  *
@@ -25,18 +25,11 @@
  * <0 - On error
  */
 static inline int
-futex_atomic_op_inuser(int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval, ret;
 	u32 tmp;
 
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
 	preempt_disable();
 	pagefault_disable();
 
@@ -74,17 +67,9 @@ out_pagefault_enable:
 	pagefault_enable();
 	preempt_enable();
 
-	if (ret == 0) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (ret == 0)
+		*oval = oldval;
+
 	return ret;
 }
 
@@ -126,18 +111,9 @@ futex_atomic_cmpxchg_inatomic(u32 *uval, u32 __user *uaddr,
 
 #else
 static inline int
-futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
+arch_futex_atomic_op_inuser(int op, u32 oparg, int *oval, u32 __user *uaddr)
 {
-	int op = (encoded_op >> 28) & 7;
-	int cmp = (encoded_op >> 24) & 15;
-	int oparg = (encoded_op << 8) >> 20;
-	int cmparg = (encoded_op << 20) >> 20;
 	int oldval = 0, ret;
-	if (encoded_op & (FUTEX_OP_OPARG_SHIFT << 28))
-		oparg = 1 << oparg;
-
-	if (! access_ok (VERIFY_WRITE, uaddr, sizeof(u32)))
-		return -EFAULT;
 
 	pagefault_disable();
 
@@ -153,17 +129,9 @@ futex_atomic_op_inuser (int encoded_op, u32 __user *uaddr)
 
 	pagefault_enable();
 
-	if (!ret) {
-		switch (cmp) {
-		case FUTEX_OP_CMP_EQ: ret = (oldval == cmparg); break;
-		case FUTEX_OP_CMP_NE: ret = (oldval != cmparg); break;
-		case FUTEX_OP_CMP_LT: ret = (oldval < cmparg); break;
-		case FUTEX_OP_CMP_GE: ret = (oldval >= cmparg); break;
-		case FUTEX_OP_CMP_LE: ret = (oldval <= cmparg); break;
-		case FUTEX_OP_CMP_GT: ret = (oldval > cmparg); break;
-		default: ret = -ENOSYS;
-		}
-	}
+	if (!ret)
+		*oval = oldval;
+
 	return ret;
 }
 
diff --git a/include/linux/atomic.h b/include/linux/atomic.h
index c56be7410130..40d6bfec0e0d 100644
--- a/include/linux/atomic.h
+++ b/include/linux/atomic.h
@@ -38,6 +38,9 @@
  * Besides, if an arch has a special barrier for acquire/release, it could
  * implement its own __atomic_op_* and use the same framework for building
  * variants
+ *
+ * If an architecture overrides __atomic_op_acquire() it will probably want
+ * to define smp_mb__after_spinlock().
  */
 #ifndef __atomic_op_acquire
 #define __atomic_op_acquire(op, args...)				\
diff --git a/include/linux/blkdev.h b/include/linux/blkdev.h
index 2a5d52fa90f5..4b99b13c7e68 100644
--- a/include/linux/blkdev.h
+++ b/include/linux/blkdev.h
@@ -134,7 +134,7 @@ typedef __u32 __bitwise req_flags_t;
 struct request {
 	struct list_head queuelist;
 	union {
-		struct call_single_data csd;
+		call_single_data_t csd;
 		u64 fifo_time;
 	};
 
diff --git a/include/linux/completion.h b/include/linux/completion.h
index 5d5aaae3af43..cae5400022a3 100644
--- a/include/linux/completion.h
+++ b/include/linux/completion.h
@@ -9,6 +9,9 @@
  */
 
 #include <linux/wait.h>
+#ifdef CONFIG_LOCKDEP_COMPLETIONS
+#include <linux/lockdep.h>
+#endif
 
 /*
  * struct completion - structure used to maintain state for a "completion"
@@ -25,13 +28,53 @@
 struct completion {
 	unsigned int done;
 	wait_queue_head_t wait;
+#ifdef CONFIG_LOCKDEP_COMPLETIONS
+	struct lockdep_map_cross map;
+#endif
 };
 
+#ifdef CONFIG_LOCKDEP_COMPLETIONS
+static inline void complete_acquire(struct completion *x)
+{
+	lock_acquire_exclusive((struct lockdep_map *)&x->map, 0, 0, NULL, _RET_IP_);
+}
+
+static inline void complete_release(struct completion *x)
+{
+	lock_release((struct lockdep_map *)&x->map, 0, _RET_IP_);
+}
+
+static inline void complete_release_commit(struct completion *x)
+{
+	lock_commit_crosslock((struct lockdep_map *)&x->map);
+}
+
+#define init_completion(x)						\
+do {									\
+	static struct lock_class_key __key;				\
+	lockdep_init_map_crosslock((struct lockdep_map *)&(x)->map,	\
+			"(complete)" #x,				\
+			&__key, 0);					\
+	__init_completion(x);						\
+} while (0)
+#else
+#define init_completion(x) __init_completion(x)
+static inline void complete_acquire(struct completion *x) {}
+static inline void complete_release(struct completion *x) {}
+static inline void complete_release_commit(struct completion *x) {}
+#endif
+
+#ifdef CONFIG_LOCKDEP_COMPLETIONS
+#define COMPLETION_INITIALIZER(work) \
+	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait), \
+	STATIC_CROSS_LOCKDEP_MAP_INIT("(complete)" #work, &(work)) }
+#else
 #define COMPLETION_INITIALIZER(work) \
 	{ 0, __WAIT_QUEUE_HEAD_INITIALIZER((work).wait) }
+#endif
 
 #define COMPLETION_INITIALIZER_ONSTACK(work) \
-	({ init_completion(&work); work; })
+	(*({ init_completion(&work); &work; }))
 
 /**
  * DECLARE_COMPLETION - declare and initialize a completion structure
@@ -70,7 +113,7 @@ struct completion {
  * This inline function will initialize a dynamically created completion
  * structure.
  */
-static inline void init_completion(struct completion *x)
+static inline void __init_completion(struct completion *x)
 {
 	x->done = 0;
 	init_waitqueue_head(&x->wait);
diff --git a/include/linux/cpuset.h b/include/linux/cpuset.h
index 898cfe2eeb42..e74655d941b7 100644
--- a/include/linux/cpuset.h
+++ b/include/linux/cpuset.h
@@ -37,12 +37,6 @@ static inline bool cpusets_enabled(void)
 	return static_branch_unlikely(&cpusets_enabled_key);
 }
 
-static inline int nr_cpusets(void)
-{
-	/* jump label reference count + the top-level cpuset */
-	return static_key_count(&cpusets_enabled_key.key) + 1;
-}
-
 static inline void cpuset_inc(void)
 {
 	static_branch_inc(&cpusets_pre_enable_key);
diff --git a/include/linux/futex.h b/include/linux/futex.h
index 7c5b694864cd..f36bfd26f998 100644
--- a/include/linux/futex.h
+++ b/include/linux/futex.h
@@ -54,7 +54,6 @@ union futex_key {
 
 #ifdef CONFIG_FUTEX
 extern void exit_robust_list(struct task_struct *curr);
-extern void exit_pi_state_list(struct task_struct *curr);
 #ifdef CONFIG_HAVE_FUTEX_CMPXCHG
 #define futex_cmpxchg_enabled 1
 #else
@@ -64,8 +63,14 @@ extern int futex_cmpxchg_enabled;
 static inline void exit_robust_list(struct task_struct *curr)
 {
 }
+#endif
+
+#ifdef CONFIG_FUTEX_PI
+extern void exit_pi_state_list(struct task_struct *curr);
+#else
 static inline void exit_pi_state_list(struct task_struct *curr)
 {
 }
 #endif
+
 #endif
diff --git a/include/linux/irqflags.h b/include/linux/irqflags.h
index 5dd1272d1ab2..5fdd93bb9300 100644
--- a/include/linux/irqflags.h
+++ b/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)
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 2afd74b9d844..cd5861651b17 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -163,6 +163,8 @@ extern void jump_label_apply_nops(struct module *mod);
 extern int static_key_count(struct static_key *key);
 extern void static_key_enable(struct static_key *key);
 extern void static_key_disable(struct static_key *key);
+extern void static_key_enable_cpuslocked(struct static_key *key);
+extern void static_key_disable_cpuslocked(struct static_key *key);
 
 /*
  * We should be using ATOMIC_INIT() for initializing .enabled, but
@@ -234,24 +236,29 @@ static inline int jump_label_apply_nops(struct module *mod)
 
 static inline void static_key_enable(struct static_key *key)
 {
-	int count = static_key_count(key);
-
-	WARN_ON_ONCE(count < 0 || count > 1);
+	STATIC_KEY_CHECK_USE();
 
-	if (!count)
-		static_key_slow_inc(key);
+	if (atomic_read(&key->enabled) != 0) {
+		WARN_ON_ONCE(atomic_read(&key->enabled) != 1);
+		return;
+	}
+	atomic_set(&key->enabled, 1);
 }
 
 static inline void static_key_disable(struct static_key *key)
 {
-	int count = static_key_count(key);
-
-	WARN_ON_ONCE(count < 0 || count > 1);
+	STATIC_KEY_CHECK_USE();
 
-	if (count)
-		static_key_slow_dec(key);
+	if (atomic_read(&key->enabled) != 1) {
+		WARN_ON_ONCE(atomic_read(&key->enabled) != 0);
+		return;
+	}
+	atomic_set(&key->enabled, 0);
 }
 
+#define static_key_enable_cpuslocked(k)		static_key_enable((k))
+#define static_key_disable_cpuslocked(k)	static_key_disable((k))
+
 #define STATIC_KEY_INIT_TRUE	{ .enabled = ATOMIC_INIT(1) }
 #define STATIC_KEY_INIT_FALSE	{ .enabled = ATOMIC_INIT(0) }
 
@@ -413,8 +420,10 @@ extern bool ____wrong_branch_error(void);
  * Normal usage; boolean enable/disable.
  */
 
-#define static_branch_enable(x)		static_key_enable(&(x)->key)
-#define static_branch_disable(x)	static_key_disable(&(x)->key)
+#define static_branch_enable(x)			static_key_enable(&(x)->key)
+#define static_branch_disable(x)		static_key_disable(&(x)->key)
+#define static_branch_enable_cpuslocked(x)	static_key_enable_cpuslocked(&(x)->key)
+#define static_branch_disable_cpuslocked(x)	static_key_disable_cpuslocked(&(x)->key)
 
 #endif /* __ASSEMBLY__ */
 
diff --git a/include/linux/kasan-checks.h b/include/linux/kasan-checks.h
index b7f8aced7870..41960fecf783 100644
--- a/include/linux/kasan-checks.h
+++ b/include/linux/kasan-checks.h
@@ -2,11 +2,13 @@
 #define _LINUX_KASAN_CHECKS_H
 
 #ifdef CONFIG_KASAN
-void kasan_check_read(const void *p, unsigned int size);
-void kasan_check_write(const void *p, unsigned int size);
+void kasan_check_read(const volatile void *p, unsigned int size);
+void kasan_check_write(const volatile void *p, unsigned int size);
 #else
-static inline void kasan_check_read(const void *p, unsigned int size) { }
-static inline void kasan_check_write(const void *p, unsigned int size) { }
+static inline void kasan_check_read(const volatile void *p, unsigned int size)
+{ }
+static inline void kasan_check_write(const volatile void *p, unsigned int size)
+{ }
 #endif
 
 #endif
diff --git a/include/linux/kernel.h b/include/linux/kernel.h
index bd6d96cf80b1..6607225d0ea4 100644
--- a/include/linux/kernel.h
+++ b/include/linux/kernel.h
@@ -277,6 +277,13 @@ extern int oops_may_print(void);
 void do_exit(long error_code) __noreturn;
 void complete_and_exit(struct completion *, long) __noreturn;
 
+#ifdef CONFIG_ARCH_HAS_REFCOUNT
+void refcount_error_report(struct pt_regs *regs, const char *err);
+#else
+static inline void refcount_error_report(struct pt_regs *regs, const char *err)
+{ }
+#endif
+
 /* Internal, do not use. */
 int __must_check _kstrtoul(const char *s, unsigned int base, unsigned long *res);
 int __must_check _kstrtol(const char *s, unsigned int base, long *res);
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);
diff --git a/include/linux/mm_types.h b/include/linux/mm_types.h
index 3cadee0a3508..57378c7cb5f8 100644
--- a/include/linux/mm_types.h
+++ b/include/linux/mm_types.h
@@ -526,26 +526,6 @@ extern void tlb_gather_mmu(struct mmu_gather *tlb, struct mm_struct *mm,
 extern void tlb_finish_mmu(struct mmu_gather *tlb,
 				unsigned long start, unsigned long end);
 
-/*
- * Memory barriers to keep this state in sync are graciously provided by
- * the page table locks, outside of which no page table modifications happen.
- * The barriers are used to ensure the order between tlb_flush_pending updates,
- * which happen while the lock is not taken, and the PTE updates, which happen
- * while the lock is taken, are serialized.
- */
-static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
-{
-	return atomic_read(&mm->tlb_flush_pending) > 0;
-}
-
-/*
- * Returns true if there are two above TLB batching threads in parallel.
- */
-static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
-{
-	return atomic_read(&mm->tlb_flush_pending) > 1;
-}
-
 static inline void init_tlb_flush_pending(struct mm_struct *mm)
 {
 	atomic_set(&mm->tlb_flush_pending, 0);
@@ -554,27 +534,82 @@ static inline void init_tlb_flush_pending(struct mm_struct *mm)
 static inline void inc_tlb_flush_pending(struct mm_struct *mm)
 {
 	atomic_inc(&mm->tlb_flush_pending);
-
 	/*
-	 * Guarantee that the tlb_flush_pending increase does not leak into the
-	 * critical section updating the page tables
+	 * The only time this value is relevant is when there are indeed pages
+	 * to flush. And we'll only flush pages after changing them, which
+	 * requires the PTL.
+	 *
+	 * So the ordering here is:
+	 *
+	 *	atomic_inc(&mm->tlb_flush_pending);
+	 *	spin_lock(&ptl);
+	 *	...
+	 *	set_pte_at();
+	 *	spin_unlock(&ptl);
+	 *
+	 *				spin_lock(&ptl)
+	 *				mm_tlb_flush_pending();
+	 *				....
+	 *				spin_unlock(&ptl);
+	 *
+	 *	flush_tlb_range();
+	 *	atomic_dec(&mm->tlb_flush_pending);
+	 *
+	 * Where the increment if constrained by the PTL unlock, it thus
+	 * ensures that the increment is visible if the PTE modification is
+	 * visible. After all, if there is no PTE modification, nobody cares
+	 * about TLB flushes either.
+	 *
+	 * This very much relies on users (mm_tlb_flush_pending() and
+	 * mm_tlb_flush_nested()) only caring about _specific_ PTEs (and
+	 * therefore specific PTLs), because with SPLIT_PTE_PTLOCKS and RCpc
+	 * locks (PPC) the unlock of one doesn't order against the lock of
+	 * another PTL.
+	 *
+	 * The decrement is ordered by the flush_tlb_range(), such that
+	 * mm_tlb_flush_pending() will not return false unless all flushes have
+	 * completed.
 	 */
-	smp_mb__before_spinlock();
 }
 
-/* Clearing is done after a TLB flush, which also provides a barrier. */
 static inline void dec_tlb_flush_pending(struct mm_struct *mm)
 {
 	/*
-	 * Guarantee that the tlb_flush_pending does not not leak into the
-	 * critical section, since we must order the PTE change and changes to
-	 * the pending TLB flush indication. We could have relied on TLB flush
-	 * as a memory barrier, but this behavior is not clearly documented.
+	 * See inc_tlb_flush_pending().
+	 *
+	 * This cannot be smp_mb__before_atomic() because smp_mb() simply does
+	 * not order against TLB invalidate completion, which is what we need.
+	 *
+	 * Therefore we must rely on tlb_flush_*() to guarantee order.
 	 */
-	smp_mb__before_atomic();
 	atomic_dec(&mm->tlb_flush_pending);
 }
 
+static inline bool mm_tlb_flush_pending(struct mm_struct *mm)
+{
+	/*
+	 * Must be called after having acquired the PTL; orders against that
+	 * PTLs release and therefore ensures that if we observe the modified
+	 * PTE we must also observe the increment from inc_tlb_flush_pending().
+	 *
+	 * That is, it only guarantees to return true if there is a flush
+	 * pending for _this_ PTL.
+	 */
+	return atomic_read(&mm->tlb_flush_pending);
+}
+
+static inline bool mm_tlb_flush_nested(struct mm_struct *mm)
+{
+	/*
+	 * Similar to mm_tlb_flush_pending(), we must have acquired the PTL
+	 * for which there is a TLB flush pending in order to guarantee
+	 * we've seen both that PTE modification and the increment.
+	 *
+	 * (no requirement on actually still holding the PTL, that is irrelevant)
+	 */
+	return atomic_read(&mm->tlb_flush_pending) > 1;
+}
+
 struct vm_fault;
 
 struct vm_special_mapping {
diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h
index c99ba7914c0a..461bd5757af6 100644
--- a/include/linux/netdevice.h
+++ b/include/linux/netdevice.h
@@ -2774,7 +2774,7 @@ struct softnet_data {
 	unsigned int		input_queue_head ____cacheline_aligned_in_smp;
 
 	/* Elements below can be accessed between CPUs for RPS/RFS */
-	struct call_single_data	csd ____cacheline_aligned_in_smp;
+	call_single_data_t	csd ____cacheline_aligned_in_smp;
 	struct softnet_data	*rps_ipi_next;
 	unsigned int		cpu;
 	unsigned int		input_queue_tail;
diff --git a/include/linux/refcount.h b/include/linux/refcount.h
index 591792c8e5b0..48b7c9c68c4d 100644
--- a/include/linux/refcount.h
+++ b/include/linux/refcount.h
@@ -53,6 +53,9 @@ extern __must_check bool refcount_sub_and_test(unsigned int i, refcount_t *r);
 extern __must_check bool refcount_dec_and_test(refcount_t *r);
 extern void refcount_dec(refcount_t *r);
 #else
+# ifdef CONFIG_ARCH_HAS_REFCOUNT
+#  include <asm/refcount.h>
+# else
 static inline __must_check bool refcount_add_not_zero(unsigned int i, refcount_t *r)
 {
 	return atomic_add_unless(&r->refs, i, 0);
@@ -87,6 +90,7 @@ static inline void refcount_dec(refcount_t *r)
 {
 	atomic_dec(&r->refs);
 }
+# endif /* !CONFIG_ARCH_HAS_REFCOUNT */
 #endif /* CONFIG_REFCOUNT_FULL */
 
 extern __must_check bool refcount_dec_if_one(refcount_t *r);
diff --git a/include/linux/rwsem-spinlock.h b/include/linux/rwsem-spinlock.h
index ae0528b834cd..e784761a4443 100644
--- a/include/linux/rwsem-spinlock.h
+++ b/include/linux/rwsem-spinlock.h
@@ -32,6 +32,7 @@ struct rw_semaphore {
 #define RWSEM_UNLOCKED_VALUE		0x00000000
 
 extern void __down_read(struct rw_semaphore *sem);
+extern int __must_check __down_read_killable(struct rw_semaphore *sem);
 extern int __down_read_trylock(struct rw_semaphore *sem);
 extern void __down_write(struct rw_semaphore *sem);
 extern int __must_check __down_write_killable(struct rw_semaphore *sem);
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index dd1d14250340..0ad7318ff299 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -44,6 +44,7 @@ struct rw_semaphore {
 };
 
 extern struct rw_semaphore *rwsem_down_read_failed(struct rw_semaphore *sem);
+extern struct rw_semaphore *rwsem_down_read_failed_killable(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_down_write_failed_killable(struct rw_semaphore *sem);
 extern struct rw_semaphore *rwsem_wake(struct rw_semaphore *);
diff --git a/include/linux/sched.h b/include/linux/sched.h
index e5fbce866073..9ba42c663fba 100644
--- a/include/linux/sched.h
+++ b/include/linux/sched.h
@@ -847,7 +847,17 @@ struct task_struct {
 	int				lockdep_depth;
 	unsigned int			lockdep_recursion;
 	struct held_lock		held_locks[MAX_LOCK_DEPTH];
-	gfp_t				lockdep_reclaim_gfp;
+#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];
+	unsigned int hist_id;
+	/* For overwrite check at each context exit */
+	unsigned int hist_id_save[XHLOCK_CTX_NR];
 #endif
 
 #ifdef CONFIG_UBSAN
diff --git a/include/linux/sched/mm.h b/include/linux/sched/mm.h
index 2b24a6974847..2b0a281f9d26 100644
--- a/include/linux/sched/mm.h
+++ b/include/linux/sched/mm.h
@@ -167,6 +167,14 @@ static inline gfp_t current_gfp_context(gfp_t flags)
 	return flags;
 }
 
+#ifdef CONFIG_LOCKDEP
+extern void fs_reclaim_acquire(gfp_t gfp_mask);
+extern void fs_reclaim_release(gfp_t gfp_mask);
+#else
+static inline void fs_reclaim_acquire(gfp_t gfp_mask) { }
+static inline void fs_reclaim_release(gfp_t gfp_mask) { }
+#endif
+
 static inline unsigned int memalloc_noio_save(void)
 {
 	unsigned int flags = current->flags & PF_MEMALLOC_NOIO;
diff --git a/include/linux/smp.h b/include/linux/smp.h
index 68123c1fe549..98b1fe027fc9 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -14,13 +14,17 @@
 #include <linux/llist.h>
 
 typedef void (*smp_call_func_t)(void *info);
-struct call_single_data {
+struct __call_single_data {
 	struct llist_node llist;
 	smp_call_func_t func;
 	void *info;
 	unsigned int flags;
 };
 
+/* Use __aligned() to avoid to use 2 cache lines for 1 csd */
+typedef struct __call_single_data call_single_data_t
+	__aligned(sizeof(struct __call_single_data));
+
 /* total number of cpus in this system (may exceed NR_CPUS) */
 extern unsigned int total_cpus;
 
@@ -48,7 +52,7 @@ void on_each_cpu_cond(bool (*cond_func)(int cpu, void *info),
 		smp_call_func_t func, void *info, bool wait,
 		gfp_t gfp_flags);
 
-int smp_call_function_single_async(int cpu, struct call_single_data *csd);
+int smp_call_function_single_async(int cpu, call_single_data_t *csd);
 
 #ifdef CONFIG_SMP
 
diff --git a/include/linux/spinlock.h b/include/linux/spinlock.h
index ef018a6e4985..69e079c5ff98 100644
--- a/include/linux/spinlock.h
+++ b/include/linux/spinlock.h
@@ -118,16 +118,39 @@ do {								\
 #endif
 
 /*
- * Despite its name it doesn't necessarily has to be a full barrier.
- * It should only guarantee that a STORE before the critical section
- * can not be reordered with LOADs and STOREs inside this section.
- * spin_lock() is the one-way barrier, this LOAD can not escape out
- * of the region. So the default implementation simply ensures that
- * a STORE can not move into the critical section, smp_wmb() should
- * serialize it with another STORE done by spin_lock().
+ * This barrier must provide two things:
+ *
+ *   - it must guarantee a STORE before the spin_lock() is ordered against a
+ *     LOAD after it, see the comments at its two usage sites.
+ *
+ *   - it must ensure the critical section is RCsc.
+ *
+ * The latter is important for cases where we observe values written by other
+ * CPUs in spin-loops, without barriers, while being subject to scheduling.
+ *
+ * CPU0			CPU1			CPU2
+ *
+ *			for (;;) {
+ *			  if (READ_ONCE(X))
+ *			    break;
+ *			}
+ * X=1
+ *			<sched-out>
+ *						<sched-in>
+ *						r = X;
+ *
+ * without transitivity it could be that CPU1 observes X!=0 breaks the loop,
+ * we get migrated and CPU2 sees X==0.
+ *
+ * Since most load-store architectures implement ACQUIRE with an smp_mb() after
+ * the LL/SC loop, they need no further barriers. Similarly all our TSO
+ * architectures imply an smp_mb() for each atomic instruction and equally don't
+ * need more.
+ *
+ * Architectures that can implement ACQUIRE better need to take care.
  */
-#ifndef smp_mb__before_spinlock
-#define smp_mb__before_spinlock()	smp_wmb()
+#ifndef smp_mb__after_spinlock
+#define smp_mb__after_spinlock()	do { } while (0)
 #endif
 
 #ifdef CONFIG_DEBUG_SPINLOCK