Skip to contentSkip to conversation

fix i386 mutex fastpath on FRAME_POINTER && !DEBUG_MUTEXES

PATCH Chuck Ebbert 1 participant 1 message Jan 12, 2006

lore
Share & tools
lore
#0 lore raw

In-Reply-To: <[email protected]>

Quoted 12 lines · Ingo Molnar
Quoted 10 lines · Chuck Ebbert
                LOCK    "   decl (%%eax)        \n"                     \
                        "   jns 1f              \n"                     \
                        "   call "#fail_fn"     \n"                     \
                        "1:                     \n"                     \
                                                                        \
                :"=a" (dummy)                                           \
                : "a" (count)                                           \
Quoted 4 lines
Quoted 2 lines

Will the extra taken forward conditional jump in the fastpath cause much of a slowdown?

yeah - the fastpath is much more common than the slowpath.

But that's how the spinlock code does it. Should that be changed to put the spinloops in .text.lock and make the fastpaths a fall-through?

Signature · 2 lines
Chuck
Currently reading: _Olympos_ by Dan Simmons