xen: Work around Clang-IAS macro \@ expansion bug

https://github.com/llvm/llvm-project/issues/60792

It turns out that Clang-IAS does not expand \@ uniquely in a translaition
unit, and the XSA-426 change tickles this bug:

  <instantiation>:4:1: error: invalid symbol redefinition
  .L1_fill_rsb_loop:
  ^
  make[3]: *** [Rules.mk:247: arch/x86/acpi/cpu_idle.o] Error 1

Extend DO_OVERWRITE_RSB with an optional parameter so C callers can mix %= in
too, which Clang does seem to expand properly.

Fixes: 63305e5392 ("x86/spec-ctrl: Mitigate Cross-Thread Return Address Predictions")
Signed-off-by: Andrew Cooper <andrew.cooper3@citrix.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/include/asm/spec_ctrl.h

@@ -83,7 +83,7 @@ static always_inline void spec_ctrl_new_guest_context(void)
     wrmsrl(MSR_PRED_CMD, PRED_CMD_IBPB);
 
     /* (ab)use alternative_input() to specify clobbers. */
-    alternative_input("", "DO_OVERWRITE_RSB", X86_BUG_IBPB_NO_RET,
+    alternative_input("", "DO_OVERWRITE_RSB xu=%=", X86_BUG_IBPB_NO_RET,
                       : "rax", "rcx");
 }
 
@@ -172,7 +172,7 @@ static always_inline void spec_ctrl_enter_idle(struct cpu_info *info)
      *
      * (ab)use alternative_input() to specify clobbers.
      */
-    alternative_input("", "DO_OVERWRITE_RSB", X86_FEATURE_SC_RSB_IDLE,
+    alternative_input("", "DO_OVERWRITE_RSB xu=%=", X86_FEATURE_SC_RSB_IDLE,
                       : "rax", "rcx");
 }
 

xen/arch/x86/include/asm/spec_ctrl_asm.h

@@ -117,11 +117,16 @@
 .L\@_done:
 .endm
 
-.macro DO_OVERWRITE_RSB tmp=rax
+.macro DO_OVERWRITE_RSB tmp=rax xu
 /*
  * Requires nothing
  * Clobbers \tmp (%rax by default), %rcx
  *
+ * xu is an optional parameter to add eXtra Uniqueness.  It is intended for
+ * passing %= in from an asm() block, in order to work around
+ * https://github.com/llvm/llvm-project/issues/60792 where Clang-IAS doesn't
+ * expand \@ uniquely.
+ *
  * Requires 256 bytes of {,shadow}stack space, but %rsp/SSP has no net
  * change. Based on Google's performance numbers, the loop is unrolled to 16
  * iterations and two calls per iteration.
@@ -136,27 +141,27 @@
     mov $16, %ecx                   /* 16 iterations, two calls per loop */
     mov %rsp, %\tmp                 /* Store the current %rsp */
 
-.L\@_fill_rsb_loop:
+.L\@_fill_rsb_loop\xu:
 
     .irp n, 1, 2                    /* Unrolled twice. */
-    call .L\@_insert_rsb_entry_\n   /* Create an RSB entry. */
+    call .L\@_insert_rsb_entry\xu\n /* Create an RSB entry. */
     int3                            /* Halt rogue speculation. */
 
-.L\@_insert_rsb_entry_\n:
+.L\@_insert_rsb_entry\xu\n:
     .endr
 
     sub $1, %ecx
-    jnz .L\@_fill_rsb_loop
+    jnz .L\@_fill_rsb_loop\xu
     mov %\tmp, %rsp                 /* Restore old %rsp */
 
 #ifdef CONFIG_XEN_SHSTK
     mov $1, %ecx
     rdsspd %ecx
     cmp $1, %ecx
-    je .L\@_shstk_done
+    je .L\@_shstk_done\xu
     mov $64, %ecx                   /* 64 * 4 bytes, given incsspd */
     incsspd %ecx                    /* Restore old SSP */
-.L\@_shstk_done:
+.L\@_shstk_done\xu:
 #endif
 .endm