arm: Adding support for atomic half word exchange
PATCH v2 1/1 arm: Adding support for atomic half word exchange
Hello Will,
This is my second version of the patch which covers the byte exclusive case as pointed out by you. Please share your opinion on this.
v1-->v2 : Extended the guard code to cover the byte exchange case as well following opinion of Will Deacon.
Checkpatch has been run and issues were taken care of.
Since support for half-word atomic exchange was not there and Qspinlock on ARM requires it, modified __xchg() to add support for that as well. ARMv6 and lower does not support ldrex{b,h} so, added a guard code to prevent build breaks.
--- arch/arm/include/asm/cmpxchg.h | 17 +++++++++++++++++ 1 file changed, 17 insertions(+)
arch/arm/include/asm/cmpxchg.h +17 -0
@@ -39,6 +39,7 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int sizeswitch (size) {#if __LINUX_ARM_ARCH__ >=6 +#if !defined(CONFIG_CPU_V6 )case 1 : asmvolatile ("@ __xchg1\n" "1: ldrexb %0, [%3]\n"
@@ -49,6 +50,22 @@ static inline unsigned long __xchg(unsigned long x, volatile void *ptr, int size : "r" (x), "r" (ptr) : "memory", "cc");break ; + +/* +* Half-word atomic exchange, required +* for Qspinlock support on ARM. +*/ +case 2 : + asmvolatile ("@ __xchg2\n" +"1: ldrexh %0, [%3]\n" +" strexh %1, %2, [%3]\n" +" teq %1, #0\n" +" bne 1b" + :"=&r" (ret),"=&r" (tmp) + :"r" (x),"r" (ptr) + :"memory" ,"cc" ); +break ; +#endif case 4 : asmvolatile ("@ __xchg4\n" "1: ldrex %0, [%3]\n"
Quoted 3 lines · Sarbojit Ganguly
This is my second version of the patch which covers the byte exclusive case as pointed out by you.
Please share your opinion on this.
The patch you posted is corrupted (the whitespace looks completely off) so it can't be applied like this. Please take a look at your email/git settings.
Will