x86: fix wait code asm() constraints

In __prepare_to_wait(), properly mark early clobbered registers. By
doing so, we at once eliminate the need to save/restore rCX and rDI.

In check_wakeup_from_wait(), make the current constraints match by
removing the code that actuall alters registers. By adjusting the
resume address in __prepare_to_wait(), we can simply re-use the copying
operation there (rather than doing a second pointless copy in the
opposite direction after branching to the resume point), which at once
eliminates the need for re-loading rCX and rDI inside the asm().

Signed-off-by: Jan Beulich <jbeulich@xxxxxxxx>

--- a/xen/common/wait.c
+++ b/xen/common/wait.c
@@ -126,6 +126,7 @@ static void __prepare_to_wait(struct wai
 {
     char *cpu_info = (char *)get_cpu_info();
     struct vcpu *curr = current;
+    unsigned long dummy;
 
     ASSERT(wqv->esp == 0);
 
@@ -140,27 +141,27 @@ static void __prepare_to_wait(struct wai
 
     asm volatile (
 #ifdef CONFIG_X86_64
-        "push %%rax; push %%rbx; push %%rcx; push %%rdx; push %%rdi; "
+        "push %%rax; push %%rbx; push %%rdx; "
         "push %%rbp; push %%r8; push %%r9; push %%r10; push %%r11; "
         "push %%r12; push %%r13; push %%r14; push %%r15; call 1f; "
-        "1: mov 80(%%rsp),%%rdi; mov 96(%%rsp),%%rcx; mov %%rsp,%%rsi; "
+        "1: mov %%rsp,%%rsi; addq $2f-1b,(%%rsp); "
         "sub %%rsi,%%rcx; cmp %3,%%rcx; jbe 2f; "
         "xor %%esi,%%esi; jmp 3f; "
         "2: rep movsb; mov %%rsp,%%rsi; 3: pop %%rax; "
         "pop %%r15; pop %%r14; pop %%r13; pop %%r12; "
         "pop %%r11; pop %%r10; pop %%r9; pop %%r8; "
-        "pop %%rbp; pop %%rdi; pop %%rdx; pop %%rcx; pop %%rbx; pop %%rax"
+        "pop %%rbp; pop %%rdx; pop %%rbx; pop %%rax"
 #else
-        "push %%eax; push %%ebx; push %%ecx; push %%edx; push %%edi; "
+        "push %%eax; push %%ebx; push %%edx; "
         "push %%ebp; call 1f; "
-        "1: mov 8(%%esp),%%edi; mov 16(%%esp),%%ecx; mov %%esp,%%esi; "
+        "1: mov %%esp,%%esi; addl $2f-1b,(%%esp); "
         "sub %%esi,%%ecx; cmp %3,%%ecx; jbe 2f; "
         "xor %%esi,%%esi; jmp 3f; "
         "2: rep movsb; mov %%esp,%%esi; 3: pop %%eax; "
-        "pop %%ebp; pop %%edi; pop %%edx; pop %%ecx; pop %%ebx; pop %%eax"
+        "pop %%ebp; pop %%edx; pop %%ebx; pop %%eax"
 #endif
-        : "=S" (wqv->esp)
-        : "c" (cpu_info), "D" (wqv->stack), "i" (PAGE_SIZE)
+        : "=&S" (wqv->esp), "=&c" (dummy), "=&D" (dummy)
+        : "i" (PAGE_SIZE), "1" (cpu_info), "2" (wqv->stack)
         : "memory" );
 
     if ( unlikely(wqv->esp == 0) )
@@ -200,7 +201,7 @@ void check_wakeup_from_wait(void)
     }
 
     asm volatile (
-        "mov %1,%%"__OP"sp; rep movsb; jmp *(%%"__OP"sp)"
+        "mov %1,%%"__OP"sp; jmp *(%0)"
         : : "S" (wqv->stack), "D" (wqv->esp),
         "c" ((char *)get_cpu_info() - (char *)wqv->esp)
         : "memory" );