BMC/Intel-BMC/linux.git/arch/x86/include/asm/rwsem.h, branch dev

x86 rwsem: avoid taking slow path when stealing write lock

2013-05-07T14:20:17+00:00

modify __down_write[_nested] and __down_write_trylock to grab the write lock whenever the active count is 0, even if there are queued waiters (they must be writers pending wakeup, since the active count is 0). Note that this is an optimization only; architectures without this optimization will still work fine: - __down_write() would take the slow path which would take the wait_lock and then try stealing the lock (as in the spinlocked rwsem implementation) - __down_write_trylock() would fail, but callers must be ready to deal with that - since there are some writers pending wakeup, they could have raced with us and obtained the lock before we steal it. Signed-off-by: Michel Lespinasse Reviewed-by: Peter Hurley Acked-by: Davidlohr Bueso Signed-off-by: Linus Torvalds

x86: Use xadd helper more widely

2011-08-29T20:44:12+00:00

This covers the trivial cases from open-coded xadd to the xadd macros. Signed-off-by: Jeremy Fitzhardinge Link: http://lkml.kernel.org/r/4E5BCC40.3030501@goop.org Signed-off-by: H. Peter Anvin

rwsem: Move duplicate function prototypes to linux/rwsem.h

2011-01-27T11:30:39+00:00

All architecture specific rwsem headers carry the same function prototypes. Just x86 adds asmregparm, which is an empty define on all other architectures. S390 has a stale rwsem_downgrade_write() prototype. Remove the duplicates and add the prototypes to linux/rwsem.h Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Benjamin Herrenschmidt Cc: Richard Henderson Acked-by: Tony Luck Acked-by: Heiko Carstens Cc: Paul Mundt Acked-by: David Miller Cc: Chris Zankel LKML-Reference: <20110126195833.970840140@linutronix.de> Signed-off-by: Thomas Gleixner

rwsem: Unify the duplicate rwsem_is_locked() inlines

2011-01-27T11:30:39+00:00

Instead of having the same implementation in each architecture, move it to linux/rwsem.h and remove the duplicates. It's unlikely that an arch will ever implement something different, but we can deal with that when it happens. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Benjamin Herrenschmidt Cc: Matt Turner Acked-by: Tony Luck Acked-by: Heiko Carstens Cc: Paul Mundt Acked-by: David Miller Cc: Chris Zankel LKML-Reference: <20110126195833.876773757@linutronix.de> Signed-off-by: Thomas Gleixner

rwsem: Move duplicate init macros and functions to linux/rwsem.h

2011-01-27T11:30:39+00:00

The rwsem initializers and related macros and functions are mostly the same. Some of them lack the lockdep initializer, but having it in place does not matter for architectures which do not support lockdep. powerpc, sparc, x86: No functional change sh, s390: Removes the duplicate init_rwsem (inline and #define) alpha, ia64, xtensa: Use the lockdep capable init function in lib/rwsem.c which is just uninlining the init function for the LOCKDEP=n case Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Benjamin Herrenschmidt Cc: Matt Turner Acked-by: Tony Luck Acked-by: Heiko Carstens Cc: Paul Mundt Acked-by: David Miller Cc: Chris Zankel LKML-Reference: <20110126195833.771812729@linutronix.de>

rwsem: Move duplicate struct rwsem declaration to linux/rwsem.h

2011-01-27T11:30:39+00:00

The difference between these declarations is the data type of the count member and the lack of lockdep in some architectures/ long is equivivalent to signed long and the #ifdef guarded dep_map member does not hurt anyone. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Benjamin Herrenschmidt Cc: Matt Turner Acked-by: Tony Luck Acked-by: Heiko Carstens Cc: Paul Mundt Acked-by: David Miller Cc: Chris Zankel LKML-Reference: <20110126195833.679641914@linutronix.de> Signed-off-by: Thomas Gleixner

x86: Cleanup rwsem_count_t typedef

2011-01-27T11:30:38+00:00

Remove the typedef which has no real reason to be there. Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Benjamin Herrenschmidt Cc: Matt Turner Cc: Tony Luck Cc: Heiko Carstens Cc: Paul Mundt Cc: David Miller Cc: Chris Zankel LKML-Reference: <20110126195833.580335506@linutronix.de>

rwsem: Cleanup includes

2011-01-27T11:30:38+00:00

All rwsem implementations include the same headers. Include them from include/linux/rwsem.h Signed-off-by: Thomas Gleixner Cc: Peter Zijlstra Cc: David Howells Cc: Benjamin Herrenschmidt Cc: Matt Turner Acked-by: Tony Luck Acked-by: Heiko Carstens Cc: Paul Mundt Acked-by: David Miller Cc: Chris Zankel LKML-Reference: <20110126195833.483520950@linutronix.de>

x86, rwsem: Minor cleanups

2010-07-21T00:41:14+00:00

Clarified few comments and made initialization of %edx/%rdx more uniform accross __down_write_nested, __up_read and __up_write functions. Signed-off-by: Michel Lespinasse LKML-Reference: <201007202219.o6KMJkiA021048@imap1.linux-foundation.org> Acked-by: David Howells Cc: Mike Waychison Cc: Suleiman Souhlal Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: H. Peter Anvin

x86, rwsem: Stay on fast path when count > 0 in __up_write()

2010-07-21T00:41:00+00:00

When count > 0 there is no need to take the call_rwsem_wake path. If we did take that path, it would just return without doing anything due to the active count not being zero. Signed-off-by: Michel Lespinasse LKML-Reference: <201007202219.o6KMJj9x021042@imap1.linux-foundation.org> Acked-by: David Howells Cc: Mike Waychison Cc: Suleiman Souhlal Cc: Ying Han Signed-off-by: Andrew Morton Signed-off-by: H. Peter Anvin