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

Pull locking changes from Ingo Molnar:
 "Various updates:

   - Futex scalability improvements: remove page lock use for shared
     futex get_futex_key(), which speeds up 'perf bench futex hash'
     benchmarks by over 40% on a 60-core Westmere.  This makes anon-mem
     shared futexes perform close to private futexes.  (Mel Gorman)

   - lockdep hash collision detection and fix (Alfredo Alvarez
     Fernandez)

   - lockdep testing enhancements (Alfredo Alvarez Fernandez)

   - robustify lockdep init by using hlists (Andrew Morton, Andrey
     Ryabinin)

   - mutex and csd_lock micro-optimizations (Davidlohr Bueso)

   - small x86 barriers tweaks (Michael S Tsirkin)

   - qspinlock updates (Waiman Long)"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (25 commits)
  locking/csd_lock: Use smp_cond_acquire() in csd_lock_wait()
  locking/csd_lock: Explicitly inline csd_lock*() helpers
  futex: Replace barrier() in unqueue_me() with READ_ONCE()
  locking/lockdep: Detect chain_key collisions
  locking/lockdep: Prevent chain_key collisions
  tools/lib/lockdep: Fix link creation warning
  tools/lib/lockdep: Add tests for AA and ABBA locking
  tools/lib/lockdep: Add userspace version of READ_ONCE()
  tools/lib/lockdep: Fix the build on recent kernels
  locking/qspinlock: Move __ARCH_SPIN_LOCK_UNLOCKED to qspinlock_types.h
  locking/mutex: Allow next waiter lockless wakeup
  locking/pvqspinlock: Enable slowpath locking count tracking
  locking/qspinlock: Use smp_cond_acquire() in pending code
  locking/pvqspinlock: Move lock stealing count tracking code into pv_queued_spin_steal_lock()
  locking/mcs: Fix mcs_spin_lock() ordering
  futex: Remove requirement for lock_page() in get_futex_key()
  futex: Rename barrier references in ordering guarantees
  locking/atomics: Update comment about READ_ONCE() and structures
  locking/lockdep: Eliminate lockdep_init()
  locking/lockdep: Convert hash tables to hlists
  ...

9 files changed, 9 insertions, 34 deletions

diff --git a/arch/c6x/kernel/setup.c b/arch/c6x/kernel/setup.c
index 72e17f7ebd6f..786e36e2f61d 100644
--- a/arch/c6x/kernel/setup.c
+++ b/arch/c6x/kernel/setup.c
@@ -281,8 +281,6 @@ notrace void __init machine_init(unsigned long dt_ptr)
 	 */
 	set_ist(_vectors_start);
 
-	lockdep_init();
-
 	/*
 	 * dtb is passed in from bootloader.
 	 * fdt is linked in blob.
diff --git a/arch/microblaze/kernel/setup.c b/arch/microblaze/kernel/setup.c
index 89a2a9394927..f31ebb5dc26c 100644
--- a/arch/microblaze/kernel/setup.c
+++ b/arch/microblaze/kernel/setup.c
@@ -130,8 +130,6 @@ void __init machine_early_init(const char *cmdline, unsigned int ram,
 	memset(__bss_start, 0, __bss_stop-__bss_start);
 	memset(_ssbss, 0, _esbss-_ssbss);
 
-	lockdep_init();
-
 /* initialize device tree for usage in early_printk */
 	early_init_devtree(_fdt_start);
 
diff --git a/arch/powerpc/kernel/setup_32.c b/arch/powerpc/kernel/setup_32.c
index ad8c9db61237..d544fa311757 100644
--- a/arch/powerpc/kernel/setup_32.c
+++ b/arch/powerpc/kernel/setup_32.c
@@ -114,8 +114,6 @@ extern unsigned int memset_nocache_branch; /* Insn to be replaced by NOP */
 
 notrace void __init machine_init(u64 dt_ptr)
 {
-	lockdep_init();
-
 	/* Enable early debugging if any specified (see udbg.h) */
 	udbg_early_init();
 
diff --git a/arch/powerpc/kernel/setup_64.c b/arch/powerpc/kernel/setup_64.c
index 5c03a6a9b054..f98be8383a39 100644
--- a/arch/powerpc/kernel/setup_64.c
+++ b/arch/powerpc/kernel/setup_64.c
@@ -255,9 +255,6 @@ void __init early_setup(unsigned long dt_ptr)
 	setup_paca(&boot_paca);
 	fixup_boot_paca();
 
-	/* Initialize lockdep early or else spinlocks will blow */
-	lockdep_init();
-
 	/* -------- printk is now safe to use ------- */
 
 	/* Enable early debugging if any specified (see udbg.h) */
diff --git a/arch/s390/kernel/early.c b/arch/s390/kernel/early.c
index c55576bbaa1f..a0684de5a93b 100644
--- a/arch/s390/kernel/early.c
+++ b/arch/s390/kernel/early.c
@@ -448,7 +448,6 @@ void __init startup_init(void)
 	rescue_initrd();
 	clear_bss_section();
 	init_kernel_storage_key();
-	lockdep_init();
 	lockdep_off();
 	setup_lowcore_early();
 	setup_facility_list();
diff --git a/arch/sparc/kernel/head_64.S b/arch/sparc/kernel/head_64.S
index f2d30cab5b3f..cd1f592cd347 100644
--- a/arch/sparc/kernel/head_64.S
+++ b/arch/sparc/kernel/head_64.S
@@ -696,14 +696,6 @@ tlb_fixup_done:
 	call	__bzero
 	 sub	%o1, %o0, %o1
 
-#ifdef CONFIG_LOCKDEP
-	/* We have this call this super early, as even prom_init can grab
-	 * spinlocks and thus call into the lockdep code.
-	 */
-	call	lockdep_init
-	 nop
-#endif
-
 	call	prom_init
 	 mov	%l7, %o0			! OpenPROM cif handler
 
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index a584e1c50918..bfb28caf97b1 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -6,18 +6,17 @@
 
 /*
  * Force strict CPU ordering.
- * And yes, this is required on UP too when we're talking
+ * And yes, this might be required on UP too when we're talking
  * to devices.
  */
 
 #ifdef CONFIG_X86_32
-/*
- * Some non-Intel clones support out of order store. wmb() ceases to be a
- * nop for these.
- */
-#define mb() alternative("lock; addl $0,0(%%esp)", "mfence", X86_FEATURE_XMM2)
-#define rmb() alternative("lock; addl $0,0(%%esp)", "lfence", X86_FEATURE_XMM2)
-#define wmb() alternative("lock; addl $0,0(%%esp)", "sfence", X86_FEATURE_XMM)
+#define mb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "mfence", \
+				      X86_FEATURE_XMM2) ::: "memory", "cc")
+#define rmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "lfence", \
+				       X86_FEATURE_XMM2) ::: "memory", "cc")
+#define wmb() asm volatile(ALTERNATIVE("lock; addl $0,0(%%esp)", "sfence", \
+				       X86_FEATURE_XMM2) ::: "memory", "cc")
 #else
 #define mb() 	asm volatile("mfence":::"memory")
 #define rmb()	asm volatile("lfence":::"memory")
diff --git a/arch/x86/kernel/process.c b/arch/x86/kernel/process.c
index 9f7c21c22477..9decee2bfdbe 100644
--- a/arch/x86/kernel/process.c
+++ b/arch/x86/kernel/process.c
@@ -418,9 +418,9 @@ static void mwait_idle(void)
 	if (!current_set_polling_and_test()) {
 		trace_cpu_idle_rcuidle(1, smp_processor_id());
 		if (this_cpu_has(X86_BUG_CLFLUSH_MONITOR)) {
-			smp_mb(); /* quirk */
+			mb(); /* quirk */
 			clflush((void *)&current_thread_info()->flags);
-			smp_mb(); /* quirk */
+			mb(); /* quirk */
 		}
 
 		__monitor((void *)&current_thread_info()->flags, 0, 0);
diff --git a/arch/x86/lguest/boot.c b/arch/x86/lguest/boot.c
index 4ba229ac3f4f..f56cc418c87d 100644
--- a/arch/x86/lguest/boot.c
+++ b/arch/x86/lguest/boot.c
@@ -1520,12 +1520,6 @@ __init void lguest_init(void)
 	 */
 	reserve_top_address(lguest_data.reserve_mem);
 
-	/*
-	 * If we don't initialize the lock dependency checker now, it crashes
-	 * atomic_notifier_chain_register, then paravirt_disable_iospace.
-	 */
-	lockdep_init();
-
 	/* Hook in our special panic hypercall code. */
 	atomic_notifier_chain_register(&panic_notifier_list, &paniced);