On Thu, Apr 06, 2017 at 08:16:19AM -0700, Linus Torvalds wrote:
> In theory x86 could use monitor/mwait for it too, in practice I think
> it tends to still be too high latency (because it was originally just
> designed for the idle loop). mwait got extended to actually be useful,
> but I'm not sure what the latency is for the modern one.
I've been meaning to test mwait-c0 for this, but never got around to it.
Something like the below, which is ugly (because I couldn't be bothered
to resolve the header recursion and thus duplicates the monitor/mwait
functions) and broken (because it hard assumes the hardware can do
monitor/mwait).
But it builds and boots, no clue if its better or worse. Changing mwait
eax to 0 would give us C1 and might also be worth a try I suppose.
---
arch/x86/include/asm/barrier.h | 30 ++++++++++++++++++++++++++++++
1 file changed, 30 insertions(+)
diff --git a/arch/x86/include/asm/barrier.h b/arch/x86/include/asm/barrier.h
index bfb28ca..faab9cd 100644
--- a/arch/x86/include/asm/barrier.h
+++ b/arch/x86/include/asm/barrier.h
@@ -80,6 +80,36 @@ do { \
#define __smp_mb__before_atomic() barrier()
#define __smp_mb__after_atomic() barrier()
+static inline void ___monitor(const void *eax, unsigned long ecx,
+ unsigned long edx)
+{
+ /* "monitor %eax, %ecx, %edx;" */
+ asm volatile(".byte 0x0f, 0x01, 0xc8;"
+ :: "a" (eax), "c" (ecx), "d"(edx));
+}
+
+static inline void ___mwait(unsigned long eax, unsigned long ecx)
+{
+ /* "mwait %eax, %ecx;" */
+ asm volatile(".byte 0x0f, 0x01, 0xc9;"
+ :: "a" (eax), "c" (ecx));
+}
+
+#define smp_cond_load_acquire(ptr, cond_expr) \
+({ \
+ typeof(ptr) __PTR = (ptr); \
+ typeof(*ptr) VAL; \
+ for (;;) { \
+ ___monitor(__PTR, 0, 0); \
+ VAL = READ_ONCE(*__PTR); \
+ if (cond_expr) \
+ break; \
+ ___mwait(0xf0 /* C0 */, 0x01 /* INT */); \
+ } \
+ smp_acquire__after_ctrl_dep(); \
+ VAL; \
+})
+
#include <asm-generic/barrier.h>
#endif /* _ASM_X86_BARRIER_H */
