Merge tag 'locking-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:

 - rwsem cleanups & optimizations/fixes:
    - Conditionally wake waiters in reader/writer slowpaths
    - Always try to wake waiters in out_nolock path

 - Add try_cmpxchg64() implementation, with arch optimizations - and use
   it to micro-optimize sched_clock_{local,remote}()

 - Various force-inlining fixes to address objdump instrumentation-check
   warnings

 - Add lock contention tracepoints:

    lock:contention_begin
    lock:contention_end

 - Misc smaller fixes & cleanups

* tag 'locking-core-2022-05-23' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  sched/clock: Use try_cmpxchg64 in sched_clock_{local,remote}
  locking/atomic/x86: Introduce arch_try_cmpxchg64
  locking/atomic: Add generic try_cmpxchg64 support
  futex: Remove a PREEMPT_RT_FULL reference.
  locking/qrwlock: Change "queue rwlock" to "queued rwlock"
  lockdep: Delete local_irq_enable_in_hardirq()
  locking/mutex: Make contention tracepoints more consistent wrt adaptive spinning
  locking: Apply contention tracepoints in the slow path
  locking: Add lock contention tracepoints
  locking/rwsem: Always try to wake waiters in out_nolock path
  locking/rwsem: Conditionally wake waiters in reader/writer slowpaths
  locking/rwsem: No need to check for handoff bit if wait queue empty
  lockdep: Fix -Wunused-parameter for _THIS_IP_
  x86/mm: Force-inline __phys_addr_nodebug()
  x86/kvm/svm: Force-inline GHCB accessors
  task_stack, x86/cea: Force-inline stack helpers

5 files changed, 33 insertions, 6 deletions

diff --git a/arch/x86/include/asm/cmpxchg_32.h b/arch/x86/include/asm/cmpxchg_32.h
index 0a7fe0321613..215f5a65790f 100644
--- a/arch/x86/include/asm/cmpxchg_32.h
+++ b/arch/x86/include/asm/cmpxchg_32.h
@@ -42,6 +42,9 @@ static inline void set_64bit(volatile u64 *ptr, u64 value)
 #define arch_cmpxchg64_local(ptr, o, n)					\
 	((__typeof__(*(ptr)))__cmpxchg64_local((ptr), (unsigned long long)(o), \
 					       (unsigned long long)(n)))
+#define arch_try_cmpxchg64(ptr, po, n)					\
+	__try_cmpxchg64((ptr), (unsigned long long *)(po), \
+			(unsigned long long)(n))
 #endif
 
 static inline u64 __cmpxchg64(volatile u64 *ptr, u64 old, u64 new)
@@ -70,6 +73,24 @@ static inline u64 __cmpxchg64_local(volatile u64 *ptr, u64 old, u64 new)
 	return prev;
 }
 
+static inline bool __try_cmpxchg64(volatile u64 *ptr, u64 *pold, u64 new)
+{
+	bool success;
+	u64 old = *pold;
+	asm volatile(LOCK_PREFIX "cmpxchg8b %[ptr]"
+		     CC_SET(z)
+		     : CC_OUT(z) (success),
+		       [ptr] "+m" (*ptr),
+		       "+A" (old)
+		     : "b" ((u32)new),
+		       "c" ((u32)(new >> 32))
+		     : "memory");
+
+	if (unlikely(!success))
+		*pold = old;
+	return success;
+}
+
 #ifndef CONFIG_X86_CMPXCHG64
 /*
  * Building a kernel capable running on 80386 and 80486. It may be necessary
diff --git a/arch/x86/include/asm/cmpxchg_64.h b/arch/x86/include/asm/cmpxchg_64.h
index 072e5459fe2f..250187ac8248 100644
--- a/arch/x86/include/asm/cmpxchg_64.h
+++ b/arch/x86/include/asm/cmpxchg_64.h
@@ -19,6 +19,12 @@ static inline void set_64bit(volatile u64 *ptr, u64 val)
 	arch_cmpxchg_local((ptr), (o), (n));				\
 })
 
+#define arch_try_cmpxchg64(ptr, po, n)					\
+({									\
+	BUILD_BUG_ON(sizeof(*(ptr)) != 8);				\
+	arch_try_cmpxchg((ptr), (po), (n));				\
+})
+
 #define system_has_cmpxchg_double() boot_cpu_has(X86_FEATURE_CX16)
 
 #endif /* _ASM_X86_CMPXCHG_64_H */
diff --git a/arch/x86/include/asm/cpu_entry_area.h b/arch/x86/include/asm/cpu_entry_area.h
index dd5ea1bdf04c..75efc4c6f076 100644
--- a/arch/x86/include/asm/cpu_entry_area.h
+++ b/arch/x86/include/asm/cpu_entry_area.h
@@ -143,7 +143,7 @@ extern void cea_set_pte(void *cea_vaddr, phys_addr_t pa, pgprot_t flags);
 
 extern struct cpu_entry_area *get_cpu_entry_area(int cpu);
 
-static inline struct entry_stack *cpu_entry_stack(int cpu)
+static __always_inline struct entry_stack *cpu_entry_stack(int cpu)
 {
 	return &get_cpu_entry_area(cpu)->entry_stack_page.stack;
 }
diff --git a/arch/x86/include/asm/page_64.h b/arch/x86/include/asm/page_64.h
index e9c86299b835..baa70451b8df 100644
--- a/arch/x86/include/asm/page_64.h
+++ b/arch/x86/include/asm/page_64.h
@@ -16,7 +16,7 @@ extern unsigned long page_offset_base;
 extern unsigned long vmalloc_base;
 extern unsigned long vmemmap_base;
 
-static inline unsigned long __phys_addr_nodebug(unsigned long x)
+static __always_inline unsigned long __phys_addr_nodebug(unsigned long x)
 {
 	unsigned long y = x - __START_KERNEL_map;
 
diff --git a/arch/x86/include/asm/svm.h b/arch/x86/include/asm/svm.h
index ec623e7da33d..1b07fba11704 100644
--- a/arch/x86/include/asm/svm.h
+++ b/arch/x86/include/asm/svm.h
@@ -569,23 +569,23 @@ struct vmcb {
 	(offsetof(struct ghcb_save_area, field) / sizeof(u64))
 
 #define DEFINE_GHCB_ACCESSORS(field)						\
-	static inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb)	\
+	static __always_inline bool ghcb_##field##_is_valid(const struct ghcb *ghcb) \
 	{									\
 		return test_bit(GHCB_BITMAP_IDX(field),				\
 				(unsigned long *)&ghcb->save.valid_bitmap);	\
 	}									\
 										\
-	static inline u64 ghcb_get_##field(struct ghcb *ghcb)			\
+	static __always_inline u64 ghcb_get_##field(struct ghcb *ghcb)		\
 	{									\
 		return ghcb->save.field;					\
 	}									\
 										\
-	static inline u64 ghcb_get_##field##_if_valid(struct ghcb *ghcb)	\
+	static __always_inline u64 ghcb_get_##field##_if_valid(struct ghcb *ghcb) \
 	{									\
 		return ghcb_##field##_is_valid(ghcb) ? ghcb->save.field : 0;	\
 	}									\
 										\
-	static inline void ghcb_set_##field(struct ghcb *ghcb, u64 value)	\
+	static __always_inline void ghcb_set_##field(struct ghcb *ghcb, u64 value) \
 	{									\
 		__set_bit(GHCB_BITMAP_IDX(field),				\
 			  (unsigned long *)&ghcb->save.valid_bitmap);		\