This is the mail archive of the
libc-ports@sources.redhat.com
mailing list for the libc-ports project.
Re: [PATCH] Optimize libc_lock_lock for MIPS XLP.
On 15/06/2012, at 2:49 PM, Maxim Kuvyrkov wrote:
> On 15/06/2012, at 2:44 PM, Chris Metcalf wrote:
>
>> On 6/14/2012 9:20 PM, Maxim Kuvyrkov wrote:
> ...
>>> As I read it, in case of a contended lock __lll_lock_wait will reset the value of the lock to "2" before calling lll_futex_wait(). I agree that there is a timing window in which the other threads will see a value of the lock greater than "2", but the value will not get as high as hundreds or billions as it will be constantly reset to "2" in atomic_exchange in lll_lock_wait().
>>>
>>> I do not see how threads will get into a busywait state, though. Would you please elaborate on that?
>>
>> You are correct. I was thinking the that the while loop had a cmpxchg, but
>> since it's just a straight-up exchange, the flow will be something like:
>>
>> - Fail to initially call lll_futex_wait() if the lock is contended
>> - Fall through to while loop
>> - Spin as long as the lock is contended enough that *futex > 2
>> - Enter futex_wait
>>
>> So a little busy under high contention, but probably settles out reasonably
>> well.
>
Attached is an improved patch that also optimizes __libc_lock_trylock using XLP's atomic instructions.
The patch also removes unnecessary indirection step represented by new macros lll_add_lock, which is then used to define __libc_lock_lock, and defines __libc_lock_lock and __libc_lock_trylock directly in lowlevellock.h . This makes changes outside of ports/ trivial.
Tested on MIPS XLP with no regressions. OK to apply for 2.17?
--
Maxim Kuvyrkov
CodeSourcery / Mentor Graphics
Allow overrides of __libc_lock_lock and __libc_lock_trylock.
* nptl/sysdeps/pthread/bits/libc-lockP.h (__libc_lock_lock)
(__libc_lock_trylock): Allow pre-existing definitions.
---
nptl/sysdeps/pthread/bits/libc-lockP.h | 8 ++++++--
1 files changed, 6 insertions(+), 2 deletions(-)
diff --git a/nptl/sysdeps/pthread/bits/libc-lockP.h b/nptl/sysdeps/pthread/bits/libc-lockP.h
index 0ebac91..9c61662 100644
--- a/nptl/sysdeps/pthread/bits/libc-lockP.h
+++ b/nptl/sysdeps/pthread/bits/libc-lockP.h
@@ -176,8 +176,10 @@ typedef pthread_key_t __libc_key_t;
/* Lock the named lock variable. */
#if !defined NOT_IN_libc || defined IS_IN_libpthread
-# define __libc_lock_lock(NAME) \
+# ifndef __libc_lock_lock
+# define __libc_lock_lock(NAME) \
({ lll_lock (NAME, LLL_PRIVATE); 0; })
+# endif
#else
# define __libc_lock_lock(NAME) \
__libc_maybe_call (__pthread_mutex_lock, (&(NAME)), 0)
@@ -189,8 +191,10 @@ typedef pthread_key_t __libc_key_t;
/* Try to lock the named lock variable. */
#if !defined NOT_IN_libc || defined IS_IN_libpthread
-# define __libc_lock_trylock(NAME) \
+# ifndef __libc_lock_trylock
+# define __libc_lock_trylock(NAME) \
lll_trylock (NAME)
+# endif
#else
# define __libc_lock_trylock(NAME) \
__libc_maybe_call (__pthread_mutex_trylock, (&(NAME)), 0)
--
1.7.4.1
Optimize libc_lock_lock for XLP.
2012-06-28 Tom de Vries <vries@codesourcery.com>
Maxim Kuvyrkov <maxim@codesourcery.com>
* sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h (__libc_lock_lock)
(__libc_lock_trylock): Define for XLP.
---
sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h | 39 ++++++++++++++++++++-
1 files changed, 37 insertions(+), 2 deletions(-)
diff --git a/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h b/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h
index 88b601e..a441e6b 100644
--- a/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h
+++ b/sysdeps/unix/sysv/linux/mips/nptl/lowlevellock.h
@@ -1,5 +1,4 @@
-/* Copyright (C) 2003, 2004, 2005, 2006, 2007, 2008,
- 2009 Free Software Foundation, Inc.
+/* Copyright (C) 2003-2012 Free Software Foundation, Inc.
This file is part of the GNU C Library.
The GNU C Library is free software; you can redistribute it and/or
@@ -291,4 +290,40 @@ extern int __lll_timedwait_tid (int *, const struct timespec *)
__res; \
})
+#ifdef _MIPS_ARCH_XLP
+/* Implement __libc_lock_lock using exchange_and_add, which expands into
+ a single LDADD instruction on XLP. This is a simplified expansion of
+ ({ lll_lock (NAME, LLL_PRIVATE); 0; }).
+
+ __lll_lock_wait_private() resets lock value to '2', which prevents unbounded
+ increase of the lock value and [with billions of threads] overflow.
+
+ As atomic.h currently only supports a full-barrier atomic_exchange_and_add,
+ using a full-barrier operation instead of an acquire-barrier operation is
+ not beneficial for MIPS in general. Limit this optimization to XLP for
+ now. */
+# define __libc_lock_lock(NAME) \
+ ({ \
+ int *__futex = &(NAME); \
+ if (__builtin_expect (atomic_exchange_and_add (__futex, 1), 0)) \
+ __lll_lock_wait_private (__futex); \
+ 0; \
+ })
+
+# define __libc_lock_trylock(NAME) \
+ ({ \
+ int *__futex = &(NAME); \
+ int __result; \
+ if (atomic_exchange_and_add (__futex, 1) == 0) \
+ __result = 0; \
+ else \
+ /* The lock is already locked. Set it to 'contended' state to avoid \
+ unbounded increase from subsequent trylocks. This slightly degrades \
+ performance of locked-but-uncontended case, as lll_futex_wake() will be \
+ called unnecessarily. */ \
+ __result = (atomic_exchange_acq (__futex, 2) != 0); \
+ __result; \
+ })
+#endif
+
#endif /* lowlevellock.h */
--
1.7.4.1