Commit 364eeb79 authored Nov 19, 2024 by Linus Torvalds

Merge tag 'locking-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip

Pull locking updates from Ingo Molnar:
 "Lockdep:
   - Enable PROVE_RAW_LOCK_NESTING with PROVE_LOCKING (Sebastian Andrzej
     Siewior)
   - Add lockdep_cleanup_dead_cpu() (David Woodhouse)

  futexes:
   - Use atomic64_inc_return() in get_inode_sequence_number() (Uros
     Bizjak)
   - Use atomic64_try_cmpxchg_relaxed() in get_inode_sequence_number()
     (Uros Bizjak)

  RT locking:
   - Add sparse annotation PREEMPT_RT's locking (Sebastian Andrzej
     Siewior)

  spinlocks:
   - Use atomic_try_cmpxchg_release() in osq_unlock() (Uros Bizjak)

  atomics:
   - x86: Use ALT_OUTPUT_SP() for __alternative_atomic64() (Uros Bizjak)
   - x86: Use ALT_OUTPUT_SP() for __arch_{,try_}cmpxchg64_emu() (Uros
     Bizjak)

  KCSAN, seqlocks:
   - Support seqcount_latch_t (Marco Elver)

  <linux/cleanup.h>:
   - Add if_not_guard() conditional guard helper (David Lechner)
   - Adjust scoped_guard() macros to avoid potential warning (Przemek
     Kitszel)
   - Remove address space of returned pointer (Uros Bizjak)

  WW mutexes:
   - locking/ww_mutex: Adjust to lockdep nest_lock requirements (Thomas
     Hellström)

  Rust integration:
   - Fix raw_spin_lock initialization on PREEMPT_RT (Eder Zulian)

  Misc cleanups & fixes:
   - lockdep: Fix wait-type check related warnings (Ahmed Ehab)
   - lockdep: Use info level for initial info messages (Jiri Slaby)
   - spinlocks: Make __raw_* lock ops static (Geert Uytterhoeven)
   - pvqspinlock: Convert fields of 'enum vcpu_state' to uppercase
     (Qiuxu Zhuo)
   - iio: magnetometer: Fix if () scoped_guard() formatting (Stephen
     Rothwell)
   - rtmutex: Fix misleading comment (Peter Zijlstra)
   - percpu-rw-semaphores: Fix grammar in percpu-rw-semaphore.rst (Xiu
     Jianfeng)"

* tag 'locking-core-2024-11-18' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip: (29 commits)
  locking/Documentation: Fix grammar in percpu-rw-semaphore.rst
  iio: magnetometer: fix if () scoped_guard() formatting
  rust: helpers: Avoid raw_spin_lock initialization for PREEMPT_RT
  kcsan, seqlock: Fix incorrect assumption in read_seqbegin()
  seqlock, treewide: Switch to non-raw seqcount_latch interface
  kcsan, seqlock: Support seqcount_latch_t
  time/sched_clock: Broaden sched_clock()'s instrumentation coverage
  time/sched_clock: Swap update_clock_read_data() latch writes
  locking/atomic/x86: Use ALT_OUTPUT_SP() for __arch_{,try_}cmpxchg64_emu()
  locking/atomic/x86: Use ALT_OUTPUT_SP() for __alternative_atomic64()
  cleanup: Add conditional guard helper
  cleanup: Adjust scoped_guard() macros to avoid potential warning
  locking/osq_lock: Use atomic_try_cmpxchg_release() in osq_unlock()
  cleanup: Remove address space of returned pointer
  locking/rtmutex: Fix misleading comment
  locking/rt: Annotate unlock followed by lock for sparse.
  locking/rt: Add sparse annotation for RCU.
  locking/rt: Remove one __cond_lock() in RT's spin_trylock_irqsave()
  locking/rt: Add sparse annotation PREEMPT_RT's sleeping locks.
  locking/pvqspinlock: Convert fields of 'enum vcpu_state' to uppercase
  ...

parents d8d78a90 3b49a347

Documentation/locking/percpu-rw-semaphore.rst

+2 −2

Original line number	Diff line number	Diff line
		@@ -16,8 +16,8 @@ writing is very expensive, it calls synchronize_rcu() that can take
		hundreds of milliseconds.

		The lock is declared with "struct percpu_rw_semaphore" type.
		The lock is initialized percpu_init_rwsem, it returns 0 on success and
		-ENOMEM on allocation failure.
		The lock is initialized with percpu_init_rwsem, it returns 0 on success
		and -ENOMEM on allocation failure.
		The lock must be freed with percpu_free_rwsem to avoid memory leak.

		The lock is locked for read with percpu_down_read, percpu_up_read and

Documentation/locking/seqlock.rst

+1 −1

Original line number	Diff line number	Diff line
		@@ -153,7 +153,7 @@ Use seqcount_latch_t when the write side sections cannot be protected
		from interruption by readers. This is typically the case when the read
		side can be invoked from NMI handlers.

		Check `raw_write_seqcount_latch()` for more information.
		Check `write_seqcount_latch()` for more information.


		.. _seqlock_t:

arch/x86/include/asm/atomic64_32.h

+2 −1

Original line number	Diff line number	Diff line
		@@ -51,7 +51,8 @@ static __always_inline s64 arch_atomic64_read_nonatomic(const atomic64_t *v)
		#ifdef CONFIG_X86_CMPXCHG64
		#define __alternative_atomic64(f, g, out, in...) \
		asm volatile("call %c[func]" \
		: out : [func] "i" (atomic64_##g##_cx8), ## in)
		: ALT_OUTPUT_SP(out) \
		: [func] "i" (atomic64_##g##_cx8), ## in)

		#define ATOMIC64_DECL(sym) ATOMIC64_DECL_ONE(sym##_cx8)
		#else

arch/x86/include/asm/cmpxchg_32.h

+3 −3

Original line number	Diff line number	Diff line
		@@ -94,7 +94,7 @@ static __always_inline bool __try_cmpxchg64_local(volatile u64 ptr, u64 oldp,
		asm volatile(ALTERNATIVE(_lock_loc \
		"call cmpxchg8b_emu", \
		_lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
		: "+a" (o.low), "+d" (o.high) \
		: ALT_OUTPUT_SP("+a" (o.low), "+d" (o.high)) \
		: "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
		: "memory"); \
		\
		@@ -123,8 +123,8 @@ static __always_inline u64 arch_cmpxchg64_local(volatile u64 *ptr, u64 old, u64
		"call cmpxchg8b_emu", \
		_lock "cmpxchg8b %a[ptr]", X86_FEATURE_CX8) \
		CC_SET(e) \
		: CC_OUT(e) (ret), \
		"+a" (o.low), "+d" (o.high) \
		: ALT_OUTPUT_SP(CC_OUT(e) (ret), \
		"+a" (o.low), "+d" (o.high)) \
		: "b" (n.low), "c" (n.high), [ptr] "S" (_ptr) \
		: "memory"); \
		\

arch/x86/kernel/tsc.c

+3 −2

Original line number	Diff line number	Diff line
		@@ -174,10 +174,11 @@ static void __set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long ts

		c2n = per_cpu_ptr(&cyc2ns, cpu);

		raw_write_seqcount_latch(&c2n->seq);
		write_seqcount_latch_begin(&c2n->seq);
		c2n->data[0] = data;
		raw_write_seqcount_latch(&c2n->seq);
		write_seqcount_latch(&c2n->seq);
		c2n->data[1] = data;
		write_seqcount_latch_end(&c2n->seq);
		}

		static void set_cyc2ns_scale(unsigned long khz, int cpu, unsigned long long tsc_now)