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

Pull locking and misc x86 updates from Ingo Molnar:
 "Lots of changes in this cycle - in part because locking/core attracted
  a number of related x86 low level work which was easier to handle in a
  single tree:

   - Linux Kernel Memory Consistency Model updates (Alan Stern, Paul E.
     McKenney, Andrea Parri)

   - lockdep scalability improvements and micro-optimizations (Waiman
     Long)

   - rwsem improvements (Waiman Long)

   - spinlock micro-optimization (Matthew Wilcox)

   - qspinlocks: Provide a liveness guarantee (more fairness) on x86.
     (Peter Zijlstra)

   - Add support for relative references in jump tables on arm64, x86
     and s390 to optimize jump labels (Ard Biesheuvel, Heiko Carstens)

   - Be a lot less permissive on weird (kernel address) uaccess faults
     on x86: BUG() when uaccess helpers fault on kernel addresses (Jann
     Horn)

   - macrofy x86 asm statements to un-confuse the GCC inliner. (Nadav
     Amit)

   - ... and a handful of other smaller changes as well"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (57 commits)
  locking/lockdep: Make global debug_locks* variables read-mostly
  locking/lockdep: Fix debug_locks off performance problem
  locking/pvqspinlock: Extend node size when pvqspinlock is configured
  locking/qspinlock_stat: Count instances of nested lock slowpaths
  locking/qspinlock, x86: Provide liveness guarantee
  x86/asm: 'Simplify' GEN_*_RMWcc() macros
  locking/qspinlock: Rework some comments
  locking/qspinlock: Re-order code
  locking/lockdep: Remove duplicated 'lock_class_ops' percpu array
  x86/defconfig: Enable CONFIG_USB_XHCI_HCD=y
  futex: Replace spin_is_locked() with lockdep
  locking/lockdep: Make class->ops a percpu counter and move it under CONFIG_DEBUG_LOCKDEP=y
  x86/jump-labels: Macrofy inline assembly code to work around GCC inlining bugs
  x86/cpufeature: Macrofy inline assembly code to work around GCC inlining bugs
  x86/extable: Macrofy inline assembly code to work around GCC inlining bugs
  x86/paravirt: Work around GCC inlining bugs when compiling paravirt ops
  x86/bug: Macrofy the BUG table section handling, to work around GCC inlining bugs
  x86/alternatives: Macrofy lock prefixes to work around GCC inlining bugs
  x86/refcount: Work around GCC inlining bug
  x86/objtool: Use asm macros to work around GCC inlining bugs
  ...

4 files changed, 24 insertions, 18 deletions

diff --git a/include/asm-generic/bug.h b/include/asm-generic/bug.h
index 20561a60db9c..cdafa5edea49 100644
--- a/include/asm-generic/bug.h
+++ b/include/asm-generic/bug.h
@@ -17,10 +17,8 @@
 #ifndef __ASSEMBLY__
 #include <linux/kernel.h>
 
-#ifdef CONFIG_BUG
-
-#ifdef CONFIG_GENERIC_BUG
 struct bug_entry {
+#ifdef CONFIG_GENERIC_BUG
 #ifndef CONFIG_GENERIC_BUG_RELATIVE_POINTERS
 	unsigned long	bug_addr;
 #else
@@ -35,8 +33,10 @@ struct bug_entry {
 	unsigned short	line;
 #endif
 	unsigned short	flags;
-};
 #endif	/* CONFIG_GENERIC_BUG */
+};
+
+#ifdef CONFIG_BUG
 
 /*
  * Don't use BUG() or BUG_ON() unless there's really no way out; one
diff --git a/include/asm-generic/qrwlock.h b/include/asm-generic/qrwlock.h
index 0f7062bd55e5..36254d2da8e0 100644
--- a/include/asm-generic/qrwlock.h
+++ b/include/asm-generic/qrwlock.h
@@ -71,8 +71,8 @@ static inline int queued_write_trylock(struct qrwlock *lock)
 	if (unlikely(cnts))
 		return 0;
 
-	return likely(atomic_cmpxchg_acquire(&lock->cnts,
-					     cnts, cnts | _QW_LOCKED) == cnts);
+	return likely(atomic_try_cmpxchg_acquire(&lock->cnts, &cnts,
+				_QW_LOCKED));
 }
 /**
  * queued_read_lock - acquire read lock of a queue rwlock
@@ -96,8 +96,9 @@ static inline void queued_read_lock(struct qrwlock *lock)
  */
 static inline void queued_write_lock(struct qrwlock *lock)
 {
+	u32 cnts = 0;
 	/* Optimize for the unfair lock case where the fair flag is 0. */
-	if (atomic_cmpxchg_acquire(&lock->cnts, 0, _QW_LOCKED) == 0)
+	if (likely(atomic_try_cmpxchg_acquire(&lock->cnts, &cnts, _QW_LOCKED)))
 		return;
 
 	queued_write_lock_slowpath(lock);
diff --git a/include/asm-generic/qspinlock.h b/include/asm-generic/qspinlock.h
index 9cc457597ddf..7541fa707f5b 100644
--- a/include/asm-generic/qspinlock.h
+++ b/include/asm-generic/qspinlock.h
@@ -66,10 +66,12 @@ static __always_inline int queued_spin_is_contended(struct qspinlock *lock)
  */
 static __always_inline int queued_spin_trylock(struct qspinlock *lock)
 {
-	if (!atomic_read(&lock->val) &&
-	   (atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL) == 0))
-		return 1;
-	return 0;
+	u32 val = atomic_read(&lock->val);
+
+	if (unlikely(val))
+		return 0;
+
+	return likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL));
 }
 
 extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
@@ -80,11 +82,11 @@ extern void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val);
  */
 static __always_inline void queued_spin_lock(struct qspinlock *lock)
 {
-	u32 val;
+	u32 val = 0;
 
-	val = atomic_cmpxchg_acquire(&lock->val, 0, _Q_LOCKED_VAL);
-	if (likely(val == 0))
+	if (likely(atomic_try_cmpxchg_acquire(&lock->val, &val, _Q_LOCKED_VAL)))
 		return;
+
 	queued_spin_lock_slowpath(lock, val);
 }
 
diff --git a/include/asm-generic/vmlinux.lds.h b/include/asm-generic/vmlinux.lds.h
index d7701d466b60..d0bcea7c8f84 100644
--- a/include/asm-generic/vmlinux.lds.h
+++ b/include/asm-generic/vmlinux.lds.h
@@ -253,10 +253,6 @@
 	STRUCT_ALIGN();							\
 	*(__tracepoints)						\
 	/* implement dynamic printk debug */				\
-	. = ALIGN(8);                                                   \
-	__start___jump_table = .;					\
-	KEEP(*(__jump_table))                                           \
-	__stop___jump_table = .;					\
 	. = ALIGN(8);							\
 	__start___verbose = .;						\
 	KEEP(*(__verbose))                                              \
@@ -300,6 +296,12 @@
 	. = __start_init_task + THREAD_SIZE;				\
 	__end_init_task = .;
 
+#define JUMP_TABLE_DATA							\
+	. = ALIGN(8);							\
+	__start___jump_table = .;					\
+	KEEP(*(__jump_table))						\
+	__stop___jump_table = .;
+
 /*
  * Allow architectures to handle ro_after_init data on their
  * own by defining an empty RO_AFTER_INIT_DATA.
@@ -308,6 +310,7 @@
 #define RO_AFTER_INIT_DATA						\
 	__start_ro_after_init = .;					\
 	*(.data..ro_after_init)						\
+	JUMP_TABLE_DATA							\
 	__end_ro_after_init = .;
 #endif