locking changes for v4.6

index 72e17f7ebd6f..786e36e2f61d 100644
@@ -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.

index 89a2a9394927..f31ebb5dc26c 100644
@@ -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);
 

index ad8c9db61237..d544fa311757 100644
@@ -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();
 

index 5c03a6a9b054..f98be8383a39 100644
@@ -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) */

index c55576bbaa1f..a0684de5a93b 100644
@@ -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();

index a584e1c50918..bfb28caf97b1 100644
@@ -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")

index 9f7c21c22477..9decee2bfdbe 100644
@@ -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);

index 4ba229ac3f4f..f56cc418c87d 100644
@@ -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);
 

index 39e1cb201b8e..35a52a880b2f 100644
@@ -120,11 +120,6 @@ static __always_inline bool virt_spin_lock(struct qspinlock *lock)
 #endif
 
 /*
- * Initializier
- */
-#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
-
-/*
  * Remapping spinlock architecture specific functions to the corresponding
  * queued spinlock functions.
  */

index 85f888e86761..034acd0c4956 100644
@@ -33,6 +33,11 @@ typedef struct qspinlock {
 } arch_spinlock_t;
 
 /*
+ * Initializier
+ */
+#define	__ARCH_SPIN_LOCK_UNLOCKED	{ ATOMIC_INIT(0) }
+
+/*
  * Bitfields in the atomic value:
  *
  * When NR_CPUS < 16K

index 48f5aab117ae..a27f4f17c382 100644
@@ -263,8 +263,9 @@ static __always_inline void __write_once_size(volatile void *p, void *res, int s
  * In contrast to ACCESS_ONCE these two macros will also work on aggregate
  * data types like structs or unions. If the size of the accessed data
  * type exceeds the word size of the machine (e.g., 32 bits or 64 bits)
- * READ_ONCE() and WRITE_ONCE()  will fall back to memcpy and print a
- * compile-time warning.
+ * READ_ONCE() and WRITE_ONCE() will fall back to memcpy(). There's at
+ * least two memcpy()s: one for the __builtin_memcpy() and then one for
+ * the macro doing the copy of variable - '__u' allocated on the stack.
  *
  * Their two major use cases are: (1) Mediating communication between
  * process-level code and irq/NMI handlers, all running on the same CPU,

index 4dca42fd32f5..d026b190c530 100644
@@ -261,7 +261,6 @@ struct held_lock {
 /*
  * Initialization, self-test and debugging-output methods:
  */
-extern void lockdep_init(void);
 extern void lockdep_info(void);
 extern void lockdep_reset(void);
 extern void lockdep_reset_lock(struct lockdep_map *lock);

@@ -392,7 +391,6 @@ static inline void lockdep_on(void)
 # 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_init()				do { } while (0)
 # define lockdep_info()				do { } while (0)
 # define lockdep_init_map(lock, name, key, sub) \
 		do { (void)(name); (void)(key); } while (0)

index 58c9e374704b..b3008bcfb1dc 100644
@@ -499,11 +499,6 @@ asmlinkage __visible void __init start_kernel(void)
 	char *command_line;
 	char *after_dashes;
 
-	/*
-	 * Need to run as early as possible, to initialize the
-	 * lockdep hash:
-	 */
-	lockdep_init();
 	set_task_stack_end_magic(&init_task);
 	smp_setup_processor_id();
 	debug_objects_early_init();

217 lines not on this page · raw message

227 lines not on this page · raw message

index 5b9102a47ea5..c835270f0c2f 100644
@@ -67,7 +67,13 @@ void mcs_spin_lock(struct mcs_spinlock **lock, struct mcs_spinlock *node)
 	node->locked = 0;
 	node->next   = NULL;
 
-	prev = xchg_acquire(lock, node);
+	/*
+	 * We rely on the full barrier with global transitivity implied by the
+	 * below xchg() to order the initialization stores above against any
+	 * observation of @node. And to provide the ACQUIRE ordering associated
+	 * with a LOCK primitive.
+	 */
+	prev = xchg(lock, node);
 	if (likely(prev == NULL)) {
 		/*
 		 * Lock acquired, don't need to set node->locked to 1. Threads

index 0551c219c40e..e364b424b019 100644
@@ -716,6 +716,7 @@ static inline void
 __mutex_unlock_common_slowpath(struct mutex *lock, int nested)
 {
 	unsigned long flags;
+	WAKE_Q(wake_q);
 
 	/*
 	 * As a performance measurement, release the lock before doing other

@@ -743,11 +744,11 @@ __mutex_unlock_common_slowpath(struct mutex *lock, int nested)
 					   struct mutex_waiter, list);
 
 		debug_mutex_wake_waiter(lock, waiter);
-
-		wake_up_process(waiter->task);
+		wake_q_add(&wake_q, waiter->task);
 	}
 
 	spin_unlock_mutex(&lock->wait_lock, flags);
+	wake_up_q(&wake_q);
 }
 
 /*

index 393d1874b9e0..ce2f75e32ae1 100644
@@ -358,8 +358,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 * sequentiality; this is because not all clear_pending_set_locked()
 	 * implementations imply full barriers.
 	 */
-	while ((val = smp_load_acquire(&lock->val.counter)) & _Q_LOCKED_MASK)
-		cpu_relax();
+	smp_cond_acquire(!(atomic_read(&lock->val) & _Q_LOCKED_MASK));
 
 	/*
 	 * take ownership and clear the pending bit.

@@ -435,7 +434,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 	 *
 	 * The PV pv_wait_head_or_lock function, if active, will acquire
 	 * the lock and return a non-zero value. So we have to skip the
-	 * smp_load_acquire() call. As the next PV queue head hasn't been
+	 * smp_cond_acquire() call. As the next PV queue head hasn't been
 	 * designated yet, there is no way for the locked value to become
 	 * _Q_SLOW_VAL. So both the set_locked() and the
 	 * atomic_cmpxchg_relaxed() calls will be safe.

@@ -466,7 +465,7 @@ void queued_spin_lock_slowpath(struct qspinlock *lock, u32 val)
 			break;
 		}
 		/*
-		 * The smp_load_acquire() call above has provided the necessary
+		 * The smp_cond_acquire() call above has provided the necessary
 		 * acquire semantics required for locking. At most two
 		 * iterations of this loop may be ran.
 		 */

index 87bb235c3448..21ede57f68b3 100644
@@ -55,6 +55,11 @@ struct pv_node {
 };
 
 /*
+ * Include queued spinlock statistics code
+ */
+#include "qspinlock_stat.h"
+
+/*
  * By replacing the regular queued_spin_trylock() with the function below,
  * it will be called once when a lock waiter enter the PV slowpath before
  * being queued. By allowing one lock stealing attempt here when the pending

@@ -65,9 +70,11 @@ struct pv_node {
 static inline bool pv_queued_spin_steal_lock(struct qspinlock *lock)
 {
 	struct __qspinlock *l = (void *)lock;
+	int ret = !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
+		   (cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
 
-	return !(atomic_read(&lock->val) & _Q_LOCKED_PENDING_MASK) &&
-		(cmpxchg(&l->locked, 0, _Q_LOCKED_VAL) == 0);
+	qstat_inc(qstat_pv_lock_stealing, ret);
+	return ret;
 }
 
 /*

@@ -138,11 +145,6 @@ static __always_inline int trylock_clear_pending(struct qspinlock *lock)
 #endif /* _Q_PENDING_BITS == 8 */
 
 /*
- * Include queued spinlock statistics code
- */
-#include "qspinlock_stat.h"
-
-/*
  * Lock and MCS node addresses hash table for fast lookup
  *
  * Hashing is done on a per-cacheline basis to minimize the need to access

@@ -398,6 +400,11 @@ pv_wait_head_or_lock(struct qspinlock *lock, struct mcs_spinlock *node)
 	if (READ_ONCE(pn->state) == vcpu_hashed)
 		lp = (struct qspinlock **)1;
 
+	/*
+	 * Tracking # of slowpath locking operations
+	 */
+	qstat_inc(qstat_pv_lock_slowpath, true);
+
 	for (;; waitcnt++) {
 		/*
 		 * Set correct vCPU state to be used by queue node wait-early

index 640dcecdd1df..eb2a2c9bc3fc 100644
@@ -22,6 +22,7 @@
  *   pv_kick_wake	- # of vCPU kicks used for computing pv_latency_wake
  *   pv_latency_kick	- average latency (ns) of vCPU kick operation
  *   pv_latency_wake	- average latency (ns) from vCPU kick to wakeup
+ *   pv_lock_slowpath	- # of locking operations via the slowpath
  *   pv_lock_stealing	- # of lock stealing operations
  *   pv_spurious_wakeup	- # of spurious wakeups
  *   pv_wait_again	- # of vCPU wait's that happened after a vCPU kick

@@ -45,6 +46,7 @@ enum qlock_stats {
 	qstat_pv_kick_wake,
 	qstat_pv_latency_kick,
 	qstat_pv_latency_wake,
+	qstat_pv_lock_slowpath,
 	qstat_pv_lock_stealing,
 	qstat_pv_spurious_wakeup,
 	qstat_pv_wait_again,

@@ -70,6 +72,7 @@ static const char * const qstat_names[qstat_num + 1] = {
 	[qstat_pv_spurious_wakeup] = "pv_spurious_wakeup",
 	[qstat_pv_latency_kick]	   = "pv_latency_kick",
 	[qstat_pv_latency_wake]    = "pv_latency_wake",
+	[qstat_pv_lock_slowpath]   = "pv_lock_slowpath",
 	[qstat_pv_lock_stealing]   = "pv_lock_stealing",
 	[qstat_pv_wait_again]      = "pv_wait_again",
 	[qstat_pv_wait_early]      = "pv_wait_early",

@@ -279,19 +282,6 @@ static inline void __pv_wait(u8 *ptr, u8 val)
 #define pv_kick(c)	__pv_kick(c)
 #define pv_wait(p, v)	__pv_wait(p, v)
 
-/*
- * PV unfair trylock count tracking function
- */
-static inline int qstat_spin_steal_lock(struct qspinlock *lock)
-{
-	int ret = pv_queued_spin_steal_lock(lock);
-
-	qstat_inc(qstat_pv_lock_stealing, ret);
-	return ret;
-}
-#undef  queued_spin_trylock
-#define queued_spin_trylock(l)	qstat_spin_steal_lock(l)
-
 #else /* CONFIG_QUEUED_LOCK_STAT */
 
 static inline void qstat_inc(enum qlock_stats stat, bool cond)	{ }

index d903c02223af..300d29391e07 100644
@@ -105,13 +105,12 @@ void __init call_function_init(void)
  * previous function call. For multi-cpu calls its even more interesting
  * as we'll have to ensure no other cpu is observing our csd.
  */
-static void csd_lock_wait(struct call_single_data *csd)
+static __always_inline void csd_lock_wait(struct call_single_data *csd)
 {
-	while (smp_load_acquire(&csd->flags) & CSD_FLAG_LOCK)
-		cpu_relax();
+	smp_cond_acquire(!(csd->flags & CSD_FLAG_LOCK));
 }
 
-static void csd_lock(struct call_single_data *csd)
+static __always_inline void csd_lock(struct call_single_data *csd)
 {
 	csd_lock_wait(csd);
 	csd->flags |= CSD_FLAG_LOCK;

@@ -124,7 +123,7 @@ static void csd_lock(struct call_single_data *csd)
 	smp_wmb();
 }
 
-static void csd_unlock(struct call_single_data *csd)
+static __always_inline void csd_unlock(struct call_single_data *csd)
 {
 	WARN_ON(!(csd->flags & CSD_FLAG_LOCK));
 

151 lines not on this page · raw message

index 9be663340f0a..d1c89cc06f5f 100644
@@ -11,11 +11,6 @@ static __thread struct task_struct current_obj;
 bool debug_locks = true;
 bool debug_locks_silent;
 
-__attribute__((constructor)) static void liblockdep_init(void)
-{
-	lockdep_init();
-}
-
 __attribute__((destructor)) static void liblockdep_exit(void)
 {
 	debug_check_no_locks_held();

index a60c14b9662a..6e66277ec437 100644
@@ -44,7 +44,6 @@ void lock_acquire(struct lockdep_map *lock, unsigned int subclass,
 void lock_release(struct lockdep_map *lock, int nested,
 			unsigned long ip);
 extern void debug_check_no_locks_freed(const void *from, unsigned long len);
-extern void lockdep_init(void);
 
 #define STATIC_LOCKDEP_MAP_INIT(_name, _key) \
 	{ .name = (_name), .key = (void *)(_key), }

index f42b7e9aa48f..a0a2e3a266af 100644
@@ -1,2 +1,8 @@
 #include <linux/lockdep.h>
+
+/* Trivial API wrappers, we don't (yet) have RCU in user-space: */
+#define hlist_for_each_entry_rcu	hlist_for_each_entry
+#define hlist_add_head_rcu		hlist_add_head
+#define hlist_del_rcu			hlist_del
+
 #include "../../../kernel/locking/lockdep.c"

index 21cdf869a01b..52844847569c 100644
@@ -439,7 +439,5 @@ __attribute__((constructor)) static void init_preload(void)
 	ll_pthread_rwlock_unlock = dlsym(RTLD_NEXT, "pthread_rwlock_unlock");
 #endif
 
-	lockdep_init();
-
 	__init_state = done;
 }

index 0f782ff404ac..18211a5f354f 100644
@@ -1,13 +1,13 @@
 #include <liblockdep/mutex.h>
 
-void main(void)
+int main(void)
 {
-	pthread_mutex_t a, b;
+	pthread_mutex_t a;
 
 	pthread_mutex_init(&a, NULL);
-	pthread_mutex_init(&b, NULL);
 
 	pthread_mutex_lock(&a);
-	pthread_mutex_lock(&b);
 	pthread_mutex_lock(&a);
+
+	return 0;
 }

new file mode 100644
index 000000000000..0f782ff404ac
@@ -0,0 +1,13 @@
+#include <liblockdep/mutex.h>
+
+void main(void)
+{
+	pthread_mutex_t a, b;
+
+	pthread_mutex_init(&a, NULL);
+	pthread_mutex_init(&b, NULL);
+
+	pthread_mutex_lock(&a);
+	pthread_mutex_lock(&b);
+	pthread_mutex_lock(&a);
+}

46 lines not on this page · raw message

index 6386dc3182a0..fd3e56a83fc2 100644
@@ -3,6 +3,7 @@
 
 #define __used		__attribute__((__unused__))
 #define unlikely
+#define READ_ONCE(x) (x)
 #define WRITE_ONCE(x, val) x=(val)
 #define RCU_INIT_POINTER(p, v) p=(v)