[v4 03/17] Add cmpxchg16b support for x86-64

[Feng Wu <feng.wu@intel.com>]

This patch adds cmpxchg16b support for x86-64, so software
can perform 128-bit atomic write/read.

CC: Keir Fraser <keir@xen.org>
CC: Jan Beulich <jbeulich@suse.com>
CC: Andrew Cooper <andrew.cooper3@citrix.com>
Signed-off-by: Feng Wu <feng.wu@intel.com>
---
v4:
- Use pointer as the parameter of __cmpxchg16b().
- Use gcc's __uint128_t built-in type
- Make the parameters of __cmpxchg16b() void *

v3:
- Newly added.

 xen/include/asm-x86/x86_64/system.h | 32 ++++++++++++++++++++++++++++++++
 1 file changed, 32 insertions(+)

diff --git a/xen/include/asm-x86/x86_64/system.h b/xen/include/asm-x86/x86_64/system.h
index 662813a..0267797 100644
--- a/xen/include/asm-x86/x86_64/system.h
+++ b/xen/include/asm-x86/x86_64/system.h
@@ -6,6 +6,38 @@
                                    (unsigned long)(n),sizeof(*(ptr))))
 
 /*
+ * Atomic 16 bytes compare and exchange.  Compare OLD with MEM, if
+ * identical, store NEW in MEM.  Return the initial value in MEM.
+ * Success is indicated by comparing RETURN with OLD.
+ *
+ * This function can only be called when cpu_has_cx16 is ture.
+ */
+
+static always_inline __uint128_t __cmpxchg16b(
+    volatile void *ptr, void *old, void *new)
+{
+    uint64_t prev_high, prev_low;
+    uint64_t new_high = (*(__uint128_t *)new) >> 64;
+    uint64_t new_low = (uint64_t)(*(__uint128_t *)new);
+    uint64_t old_high = (*(__uint128_t *)old) >> 64;
+    uint64_t old_low = (uint64_t)(*(__uint128_t *)old);
+
+    ASSERT(cpu_has_cx16);
+
+    asm volatile ( "lock; cmpxchg16b %4"
+                   : "=d" (prev_high), "=a" (prev_low)
+                   : "c" (new_high), "b" (new_low),
+                   "m" (*__xg((volatile void *)ptr)),
+                   "0" (old_high), "1" (old_low)
+                   : "memory" );
+
+    return ( ((__uint128_t)prev_high) << 64 | prev_low );
+}
+
+#define cmpxchg16b(ptr,o,n)                                             \
+    __cmpxchg16b((ptr), (__uint128_t *)(o), (__uint128_t *)(n))
+
+/*
  * This function causes value _o to be changed to _n at location _p.
  * If this access causes a fault then we return 1, otherwise we return 0.
  * If no fault occurs then _o is updated to the value we saw at _p. If this
-- 
2.1.0