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

Pull locking updates from Ingo Molnar:
 "The main changes in this cycle are:

   - rwsem scalability improvements, phase #2, by Waiman Long, which are
     rather impressive:

       "On a 2-socket 40-core 80-thread Skylake system with 40 reader
        and writer locking threads, the min/mean/max locking operations
        done in a 5-second testing window before the patchset were:

         40 readers, Iterations Min/Mean/Max = 1,807/1,808/1,810
         40 writers, Iterations Min/Mean/Max = 1,807/50,344/151,255

        After the patchset, they became:

         40 readers, Iterations Min/Mean/Max = 30,057/31,359/32,741
         40 writers, Iterations Min/Mean/Max = 94,466/95,845/97,098"

     There's a lot of changes to the locking implementation that makes
     it similar to qrwlock, including owner handoff for more fair
     locking.

     Another microbenchmark shows how across the spectrum the
     improvements are:

       "With a locking microbenchmark running on 5.1 based kernel, the
        total locking rates (in kops/s) on a 2-socket Skylake system
        with equal numbers of readers and writers (mixed) before and
        after this patchset were:

        # of Threads   Before Patch      After Patch
        ------------   ------------      -----------
             2            2,618             4,193
             4            1,202             3,726
             8              802             3,622
            16              729             3,359
            32              319             2,826
            64              102             2,744"

     The changes are extensive and the patch-set has been through
     several iterations addressing various locking workloads. There
     might be more regressions, but unless they are pathological I
     believe we want to use this new implementation as the baseline
     going forward.

   - jump-label optimizations by Daniel Bristot de Oliveira: the primary
     motivation was to remove IPI disturbance of isolated RT-workload
     CPUs, which resulted in the implementation of batched jump-label
     updates. Beyond the improvement of the real-time characteristics
     kernel, in one test this patchset improved static key update
     overhead from 57 msecs to just 1.4 msecs - which is a nice speedup
     as well.

   - atomic64_t cross-arch type cleanups by Mark Rutland: over the last
     ~10 years of atomic64_t existence the various types used by the
     APIs only had to be self-consistent within each architecture -
     which means they became wildly inconsistent across architectures.
     Mark puts and end to this by reworking all the atomic64
     implementations to use 's64' as the base type for atomic64_t, and
     to ensure that this type is consistently used for parameters and
     return values in the API, avoiding further problems in this area.

   - A large set of small improvements to lockdep by Yuyang Du: type
     cleanups, output cleanups, function return type and othr cleanups
     all around the place.

   - A set of percpu ops cleanups and fixes by Peter Zijlstra.

   - Misc other changes - please see the Git log for more details"

* 'locking-core-for-linus' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (82 commits)
  locking/lockdep: increase size of counters for lockdep statistics
  locking/atomics: Use sed(1) instead of non-standard head(1) option
  locking/lockdep: Move mark_lock() inside CONFIG_TRACE_IRQFLAGS && CONFIG_PROVE_LOCKING
  x86/jump_label: Make tp_vec_nr static
  x86/percpu: Optimize raw_cpu_xchg()
  x86/percpu, sched/fair: Avoid local_clock()
  x86/percpu, x86/irq: Relax {set,get}_irq_regs()
  x86/percpu: Relax smp_processor_id()
  x86/percpu: Differentiate this_cpu_{}() and __this_cpu_{}()
  locking/rwsem: Guard against making count negative
  locking/rwsem: Adaptive disabling of reader optimistic spinning
  locking/rwsem: Enable time-based spinning on reader-owned rwsem
  locking/rwsem: Make rwsem->owner an atomic_long_t
  locking/rwsem: Enable readers spinning on writer
  locking/rwsem: Clarify usage of owner's nonspinaable bit
  locking/rwsem: Wake up almost all readers in wait queue
  locking/rwsem: More optimal RT task handling of null owner
  locking/rwsem: Always release wait_lock before waking up tasks
  locking/rwsem: Implement lock handoff to prevent lock starvation
  locking/rwsem: Make rwsem_spin_on_owner() return owner state
  ...

8 files changed, 85 insertions, 46 deletions

diff --git a/include/asm-generic/atomic64.h b/include/asm-generic/atomic64.h
index d7a15096fb3b..370f01d4450f 100644
--- a/include/asm-generic/atomic64.h
+++ b/include/asm-generic/atomic64.h
@@ -10,24 +10,24 @@
 #include <linux/types.h>
 
 typedef struct {
-	long long counter;
+	s64 counter;
 } atomic64_t;
 
 #define ATOMIC64_INIT(i)	{ (i) }
 
-extern long long atomic64_read(const atomic64_t *v);
-extern void	 atomic64_set(atomic64_t *v, long long i);
+extern s64 atomic64_read(const atomic64_t *v);
+extern void atomic64_set(atomic64_t *v, s64 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);
+extern void	 atomic64_##op(s64 a, atomic64_t *v);
 
 #define ATOMIC64_OP_RETURN(op)						\
-extern long long atomic64_##op##_return(long long a, atomic64_t *v);
+extern s64 atomic64_##op##_return(s64 a, atomic64_t *v);
 
 #define ATOMIC64_FETCH_OP(op)						\
-extern long long atomic64_fetch_##op(long long a, atomic64_t *v);
+extern s64 atomic64_fetch_##op(s64 a, atomic64_t *v);
 
 #define ATOMIC64_OPS(op)	ATOMIC64_OP(op) ATOMIC64_OP_RETURN(op) ATOMIC64_FETCH_OP(op)
 
@@ -46,11 +46,11 @@ ATOMIC64_OPS(xor)
 #undef ATOMIC64_OP_RETURN
 #undef ATOMIC64_OP
 
-extern long long atomic64_dec_if_positive(atomic64_t *v);
+extern s64 atomic64_dec_if_positive(atomic64_t *v);
 #define atomic64_dec_if_positive atomic64_dec_if_positive
-extern long long atomic64_cmpxchg(atomic64_t *v, long long o, long long n);
-extern long long atomic64_xchg(atomic64_t *v, long long new);
-extern long long atomic64_fetch_add_unless(atomic64_t *v, long long a, long long u);
+extern s64 atomic64_cmpxchg(atomic64_t *v, s64 o, s64 n);
+extern s64 atomic64_xchg(atomic64_t *v, s64 new);
+extern s64 atomic64_fetch_add_unless(atomic64_t *v, s64 a, s64 u);
 #define atomic64_fetch_add_unless atomic64_fetch_add_unless
 
 #endif  /*  _ASM_GENERIC_ATOMIC64_H  */
diff --git a/include/linux/jump_label.h b/include/linux/jump_label.h
index 3e113a1fa0f1..3526c0aee954 100644
--- a/include/linux/jump_label.h
+++ b/include/linux/jump_label.h
@@ -215,6 +215,9 @@ extern void arch_jump_label_transform(struct jump_entry *entry,
 				      enum jump_label_type type);
 extern void arch_jump_label_transform_static(struct jump_entry *entry,
 					     enum jump_label_type type);
+extern bool arch_jump_label_transform_queue(struct jump_entry *entry,
+					    enum jump_label_type type);
+extern void arch_jump_label_transform_apply(void);
 extern int jump_label_text_reserved(void *start, void *end);
 extern void static_key_slow_inc(struct static_key *key);
 extern void static_key_slow_dec(struct static_key *key);
diff --git a/include/linux/lockdep.h b/include/linux/lockdep.h
index e8eef38b2213..57baa27f238c 100644
--- a/include/linux/lockdep.h
+++ b/include/linux/lockdep.h
@@ -203,11 +203,17 @@ struct lock_list {
 	struct lock_list		*parent;
 };
 
-/*
- * We record lock dependency chains, so that we can cache them:
+/**
+ * struct lock_chain - lock dependency chain record
+ *
+ * @irq_context: the same as irq_context in held_lock below
+ * @depth:       the number of held locks in this chain
+ * @base:        the index in chain_hlocks for this chain
+ * @entry:       the collided lock chains in lock_chain hash list
+ * @chain_key:   the hash key of this lock_chain
  */
 struct lock_chain {
-	/* see BUILD_BUG_ON()s in lookup_chain_cache() */
+	/* see BUILD_BUG_ON()s in add_chain_cache() */
 	unsigned int			irq_context :  2,
 					depth       :  6,
 					base	    : 24;
@@ -217,12 +223,8 @@ struct lock_chain {
 };
 
 #define MAX_LOCKDEP_KEYS_BITS		13
-/*
- * Subtract one because we offset hlock->class_idx by 1 in order
- * to make 0 mean no class. This avoids overflowing the class_idx
- * bitfield and hitting the BUG in hlock_class().
- */
-#define MAX_LOCKDEP_KEYS		((1UL << MAX_LOCKDEP_KEYS_BITS) - 1)
+#define MAX_LOCKDEP_KEYS		(1UL << MAX_LOCKDEP_KEYS_BITS)
+#define INITIAL_CHAIN_KEY		-1
 
 struct held_lock {
 	/*
@@ -247,6 +249,11 @@ struct held_lock {
 	u64 				waittime_stamp;
 	u64				holdtime_stamp;
 #endif
+	/*
+	 * class_idx is zero-indexed; it points to the element in
+	 * lock_classes this held lock instance belongs to. class_idx is in
+	 * the range from 0 to (MAX_LOCKDEP_KEYS-1) inclusive.
+	 */
 	unsigned int			class_idx:MAX_LOCKDEP_KEYS_BITS;
 	/*
 	 * The lock-stack is unified in that the lock chains of interrupt
@@ -281,6 +288,8 @@ extern void lockdep_free_key_range(void *start, unsigned long size);
 extern asmlinkage void lockdep_sys_exit(void);
 extern void lockdep_set_selftest_task(struct task_struct *task);
 
+extern void lockdep_init_task(struct task_struct *task);
+
 extern void lockdep_off(void);
 extern void lockdep_on(void);
 
@@ -385,7 +394,7 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 		WARN_ON(debug_locks && !lockdep_is_held(l));	\
 	} while (0)
 
-#define lockdep_assert_held_exclusive(l)	do {			\
+#define lockdep_assert_held_write(l)	do {			\
 		WARN_ON(debug_locks && !lockdep_is_held_type(l, 0));	\
 	} while (0)
 
@@ -405,6 +414,10 @@ extern void lock_unpin_lock(struct lockdep_map *lock, struct pin_cookie);
 
 #else /* !CONFIG_LOCKDEP */
 
+static inline void lockdep_init_task(struct task_struct *task)
+{
+}
+
 static inline void lockdep_off(void)
 {
 }
@@ -466,7 +479,7 @@ struct lockdep_map { };
 #define lockdep_is_held_type(l, r)		(1)
 
 #define lockdep_assert_held(l)			do { (void)(l); } while (0)
-#define lockdep_assert_held_exclusive(l)	do { (void)(l); } while (0)
+#define lockdep_assert_held_write(l)	do { (void)(l); } while (0)
 #define lockdep_assert_held_read(l)		do { (void)(l); } while (0)
 #define lockdep_assert_held_once(l)		do { (void)(l); } while (0)
 
@@ -497,7 +510,6 @@ enum xhlock_context_t {
 	{ .name = (_name), .key = (void *)(_key), }
 
 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) {}
 
 #ifdef CONFIG_LOCK_STAT
diff --git a/include/linux/percpu-rwsem.h b/include/linux/percpu-rwsem.h
index 2809b44cbbee..3998cdf9cd14 100644
--- a/include/linux/percpu-rwsem.h
+++ b/include/linux/percpu-rwsem.h
@@ -121,7 +121,7 @@ static inline void percpu_rwsem_release(struct percpu_rw_semaphore *sem,
 	lock_release(&sem->rw_sem.dep_map, 1, ip);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	if (!read)
-		sem->rw_sem.owner = RWSEM_OWNER_UNKNOWN;
+		atomic_long_set(&sem->rw_sem.owner, RWSEM_OWNER_UNKNOWN);
 #endif
 }
 
@@ -131,7 +131,7 @@ static inline void percpu_rwsem_acquire(struct percpu_rw_semaphore *sem,
 	lock_acquire(&sem->rw_sem.dep_map, 0, 1, read, 1, NULL, ip);
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	if (!read)
-		sem->rw_sem.owner = current;
+		atomic_long_set(&sem->rw_sem.owner, (long)current);
 #endif
 }
 
diff --git a/include/linux/rwsem.h b/include/linux/rwsem.h
index 2ea18a3def04..e401358c4e7e 100644
--- a/include/linux/rwsem.h
+++ b/include/linux/rwsem.h
@@ -34,12 +34,13 @@
  */
 struct rw_semaphore {
 	atomic_long_t count;
-#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	/*
-	 * Write owner. Used as a speculative check to see
-	 * if the owner is running on the cpu.
+	 * Write owner or one of the read owners as well flags regarding
+	 * the current state of the rwsem. Can be used as a speculative
+	 * check to see if the write owner is running on the cpu.
 	 */
-	struct task_struct *owner;
+	atomic_long_t owner;
+#ifdef CONFIG_RWSEM_SPIN_ON_OWNER
 	struct optimistic_spin_queue osq; /* spinner MCS lock */
 #endif
 	raw_spinlock_t wait_lock;
@@ -50,10 +51,10 @@ struct rw_semaphore {
 };
 
 /*
- * Setting bit 1 of the owner field but not bit 0 will indicate
+ * Setting all bits of the owner field except bit 0 will indicate
  * that the rwsem is writer-owned with an unknown owner.
  */
-#define RWSEM_OWNER_UNKNOWN	((struct task_struct *)-2L)
+#define RWSEM_OWNER_UNKNOWN	(-2L)
 
 /* In all implementations count != 0 means locked */
 static inline int rwsem_is_locked(struct rw_semaphore *sem)
@@ -73,13 +74,14 @@ static inline int rwsem_is_locked(struct rw_semaphore *sem)
 #endif
 
 #ifdef CONFIG_RWSEM_SPIN_ON_OWNER
-#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED, .owner = NULL
+#define __RWSEM_OPT_INIT(lockname) , .osq = OSQ_LOCK_UNLOCKED
 #else
 #define __RWSEM_OPT_INIT(lockname)
 #endif
 
 #define __RWSEM_INITIALIZER(name)				\
 	{ __RWSEM_INIT_COUNT(name),				\
+	  .owner = ATOMIC_LONG_INIT(0),				\
 	  .wait_list = LIST_HEAD_INIT((name).wait_list),	\
 	  .wait_lock = __RAW_SPIN_LOCK_UNLOCKED(name.wait_lock)	\
 	  __RWSEM_OPT_INIT(name)				\
diff --git a/include/linux/sched/wake_q.h b/include/linux/sched/wake_q.h
index ad826d2a4557..26a2013ac39c 100644
--- a/include/linux/sched/wake_q.h
+++ b/include/linux/sched/wake_q.h
@@ -51,6 +51,11 @@ static inline void wake_q_init(struct wake_q_head *head)
 	head->lastp = &head->first;
 }
 
+static inline bool wake_q_empty(struct wake_q_head *head)
+{
+	return head->first == WAKE_Q_TAIL;
+}
+
 extern void wake_q_add(struct wake_q_head *head, struct task_struct *task);
 extern void wake_q_add_safe(struct wake_q_head *head, struct task_struct *task);
 extern void wake_up_q(struct wake_q_head *head);
diff --git a/include/linux/smp.h b/include/linux/smp.h
index bb8b451ab01f..6fc856c9eda5 100644
--- a/include/linux/smp.h
+++ b/include/linux/smp.h
@@ -180,29 +180,46 @@ static inline int get_boot_cpu_id(void)
 
 #endif /* !SMP */
 
-/*
- * smp_processor_id(): get the current CPU ID.
+/**
+ * raw_processor_id() - get the current (unstable) CPU id
+ *
+ * For then you know what you are doing and need an unstable
+ * CPU id.
+ */
+
+/**
+ * smp_processor_id() - get the current (stable) CPU id
+ *
+ * This is the normal accessor to the CPU id and should be used
+ * whenever possible.
+ *
+ * The CPU id is stable when:
  *
- * if DEBUG_PREEMPT is enabled then we check whether it is
- * used in a preemption-safe way. (smp_processor_id() is safe
- * if it's used in a preemption-off critical section, or in
- * a thread that is bound to the current CPU.)
+ *  - IRQs are disabled;
+ *  - preemption is disabled;
+ *  - the task is CPU affine.
  *
- * NOTE: raw_smp_processor_id() is for internal use only
- * (smp_processor_id() is the preferred variant), but in rare
- * instances it might also be used to turn off false positives
- * (i.e. smp_processor_id() use that the debugging code reports but
- * which use for some reason is legal). Don't use this to hack around
- * the warning message, as your code might not work under PREEMPT.
+ * When CONFIG_DEBUG_PREEMPT; we verify these assumption and WARN
+ * when smp_processor_id() is used when the CPU id is not stable.
  */
+
+/*
+ * Allow the architecture to differentiate between a stable and unstable read.
+ * For example, x86 uses an IRQ-safe asm-volatile read for the unstable but a
+ * regular asm read for the stable.
+ */
+#ifndef __smp_processor_id
+#define __smp_processor_id(x) raw_smp_processor_id(x)
+#endif
+
 #ifdef CONFIG_DEBUG_PREEMPT
   extern unsigned int debug_smp_processor_id(void);
 # define smp_processor_id() debug_smp_processor_id()
 #else
-# define smp_processor_id() raw_smp_processor_id()
+# define smp_processor_id() __smp_processor_id()
 #endif
 
-#define get_cpu()		({ preempt_disable(); smp_processor_id(); })
+#define get_cpu()		({ preempt_disable(); __smp_processor_id(); })
 #define put_cpu()		preempt_enable()
 
 /*
diff --git a/include/linux/types.h b/include/linux/types.h
index 231114ae38f4..05030f608be3 100644
--- a/include/linux/types.h
+++ b/include/linux/types.h
@@ -174,7 +174,7 @@ typedef struct {
 
 #ifdef CONFIG_64BIT
 typedef struct {
-	long counter;
+	s64 counter;
 } atomic64_t;
 #endif