x86: fix ticket spin lock asm constraints
PATCH 1/1 x86: fix ticket spin lock asm constraints
In addition to these changes I doubt the 'volatile' on all the ticket lock asm()-s are really necessary.
Signed-off-by Jan Beulich <[email protected]>
Cc Nick Piggin <[email protected]>
--- include/asm-x86/spinlock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)
include/asm-x86/spinlock.h +3 -3
@@ -101,7 +101,7 @@ static __always_inline int __ticket_spin"1:" "sete %b1\n\t" "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=Q" (new), "+m" (lock->slock) + : "=&a" (tmp), "=&Q" (new), "+m" (lock->slock) : : "memory", "cc");
@@ -146,7 +146,7 @@ static __always_inline void __ticket_spi/* don't need lfence here, because loads are in-order */ "jmp 1b\n" "2:" - : "+Q" (inc), "+m" (lock->slock), "=r" (tmp) + : "+r" (inc), "+m" (lock->slock), "=&r" (tmp) : : "memory", "cc"); }
@@ -166,7 +166,7 @@ static __always_inline int __ticket_spin"1:" "sete %b1\n\t" "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=r" (new), "+m" (lock->slock) + : "=&a" (tmp), "=&q" (new), "+m" (lock->slock) : : "memory", "cc");
Hi,
All these ticket lock patches look pretty good to me. Thanks for going over it so thoroughly.
Quoted 41 lines · Jan Beulich
In addition to these changes I doubt the 'volatile' on all the ticket lock asm()-s are really necessary.
Signed-off-by Jan Beulich <[email protected]>Cc Nick Piggin <[email protected]>--- include/asm-x86/spinlock.h | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-)include/asm-x86/spinlock.h +3
-3@@ -101,7 +101,7 @@ static __always_inline int __ticket_spin"1:" "sete %b1\n\t" "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=Q" (new), "+m" (lock->slock) + : "=&a" (tmp), "=&Q" (new), "+m" (lock->slock) : : "memory", "cc");@@ -146,7 +146,7 @@ static __always_inline void __ticket_spi/* don't need lfence here, because loads are in-order */ "jmp 1b\n" "2:" - : "+Q" (inc), "+m" (lock->slock), "=r" (tmp) + : "+r" (inc), "+m" (lock->slock), "=&r" (tmp) : : "memory", "cc"); }@@ -166,7 +166,7 @@ static __always_inline int __ticket_spin"1:" "sete %b1\n\t" "movzbl %b1,%0\n\t" - : "=&a" (tmp), "=r" (new), "+m" (lock->slock) + : "=&a" (tmp), "=&q" (new), "+m" (lock->slock) : : "memory", "cc");
Quoted 4 lines · Nick Piggin
Hi,
All these ticket lock patches look pretty good to me. Thanks for going over it so thoroughly.
yes - and they are all working fine here as well in testing. They are queued up for v2.6.28.
Ingo