absl: speed up Mutex::Lock

Currently Mutex::Lock contains not inlined non-tail call:
TryAcquireWithSpinning -> GetMutexGlobals -> LowLevelCallOnce -> init closure
This turns the function into non-leaf with stack frame allocation
and additional register use. Remove this non-tail call to make the function leaf.
Move spin iterations initialization to LockSlow.

Current Lock happy path:

00000000001edc20 <absl::Mutex::Lock()>:
  1edc20:	55                   	push   %rbp
  1edc21:	48 89 e5             	mov    %rsp,%rbp
  1edc24:	53                   	push   %rbx
  1edc25:	50                   	push   %rax
  1edc26:	48 89 fb             	mov    %rdi,%rbx
  1edc29:	48 8b 07             	mov    (%rdi),%rax
  1edc2c:	a8 19                	test   $0x19,%al
  1edc2e:	75 0e                	jne    1edc3e <absl::Mutex::Lock()+0x1e>
  1edc30:	48 89 c1             	mov    %rax,%rcx
  1edc33:	48 83 c9 08          	or     $0x8,%rcx
  1edc37:	f0 48 0f b1 0b       	lock cmpxchg %rcx,(%rbx)
  1edc3c:	74 42                	je     1edc80 <absl::Mutex::Lock()+0x60>
  ... unhappy path ...
  1edc80:	48 83 c4 08          	add    $0x8,%rsp
  1edc84:	5b                   	pop    %rbx
  1edc85:	5d                   	pop    %rbp
  1edc86:	c3                   	ret

New Lock happy path:

00000000001eea80 <absl::Mutex::Lock()>:
  1eea80:	48 8b 07             	mov    (%rdi),%rax
  1eea83:	a8 19                	test   $0x19,%al
  1eea85:	75 0f                	jne    1eea96 <absl::Mutex::Lock()+0x16>
  1eea87:	48 89 c1             	mov    %rax,%rcx
  1eea8a:	48 83 c9 08          	or     $0x8,%rcx
  1eea8e:	f0 48 0f b1 0f       	lock cmpxchg %rcx,(%rdi)
  1eea93:	75 01                	jne    1eea96 <absl::Mutex::Lock()+0x16>
  1eea95:	c3                   	ret
  ... unhappy path ...

PiperOrigin-RevId: 577790105
Change-Id: I20793534050302ff9f7a20aed93791c088d98562

0 files changed, 0 insertions, 0 deletions