x86/boot: Reuse code to relocate trampoline

Move code from efi-boot.h to a separate, new, reloc-trampoline.c file.
Reuse this new code, compiling it for 32bit as well, to replace assembly
code in head.S doing the same thing.

Signed-off-by: Frediano Ziglio <frediano.ziglio@cloud.com>
Reviewed-by: Andrew Cooper <andrew.cooper3@citrix.com>
Acked-by: Marek Marczykowski-Górecki <marmarek@invisiblethingslab.com>

xen/arch/x86/boot/Makefile

@@ -1,11 +1,15 @@
 obj-bin-y += head.o
 obj-bin-y += built-in-32.o
+obj-bin-y += $(obj64)
 
 obj32 := cmdline.32.o
 obj32 += reloc.32.o
+obj32 += reloc-trampoline.32.o
 
-nocov-y   += $(obj32)
-noubsan-y += $(obj32)
+obj64 := reloc-trampoline.o
+
+nocov-y   += $(obj32) $(obj64)
+noubsan-y += $(obj32) $(obj64)
 targets   += $(obj32)
 
 obj32 := $(addprefix $(obj)/,$(obj32))
@@ -75,7 +79,7 @@ cmd_combine = \
               --bin1      $(obj)/built-in-32.base.bin \
               --bin2      $(obj)/built-in-32.offset.bin \
               --map       $(obj)/built-in-32.offset.map \
-              --exports   cmdline_parse_early,reloc \
+              --exports   cmdline_parse_early,reloc,reloc_trampoline32 \
               --output    $@
 
 targets += built-in-32.S

xen/arch/x86/boot/build32.lds.S

@@ -45,6 +45,11 @@ SECTIONS
          */
         DECLARE_IMPORT(__base_relocs_start);
         DECLARE_IMPORT(__base_relocs_end);
+        DECLARE_IMPORT(__trampoline_rel_start);
+        DECLARE_IMPORT(__trampoline_rel_stop);
+        DECLARE_IMPORT(__trampoline_seg_start);
+        DECLARE_IMPORT(__trampoline_seg_stop);
+        DECLARE_IMPORT(trampoline_phys);
         . = . + GAP;
         *(.text)
         *(.text.*)

xen/arch/x86/boot/head.S

@@ -706,28 +706,7 @@ trampoline_setup:
         mov     %edx, sym_offs(l1_bootmap)(%esi, %ecx, 8)
 
         /* Apply relocations to bootstrap trampoline. */
-        mov     sym_esi(trampoline_phys), %edx
-        lea     sym_esi(__trampoline_rel_start), %edi
-        lea     sym_esi(__trampoline_rel_stop), %ecx
-1:
-        mov     (%edi), %eax
-        add     %edx, (%edi, %eax)
-        add     $4,%edi
-
-        cmp     %ecx, %edi
-        jb      1b
-
-        /* Patch in the trampoline segment. */
-        shr     $4,%edx
-        lea     sym_esi(__trampoline_seg_start), %edi
-        lea     sym_esi(__trampoline_seg_stop), %ecx
-1:
-        mov     (%edi), %eax
-        mov     %dx, (%edi, %eax)
-        add     $4,%edi
-
-        cmp     %ecx, %edi
-        jb      1b
+        call    reloc_trampoline32
 
         /* Do not parse command line on EFI platform here. */
         cmpb    $0, sym_esi(efi_platform)

xen/arch/x86/boot/reloc-trampoline.c

@@ -0,0 +1,36 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+
+#include <xen/compiler.h>
+#include <xen/stdint.h>
+#include <asm/trampoline.h>
+
+extern const int32_t __trampoline_rel_start[], __trampoline_rel_stop[];
+extern const int32_t __trampoline_seg_start[], __trampoline_seg_stop[];
+
+#if defined(__i386__)
+void reloc_trampoline32(void)
+#elif defined (__x86_64__)
+void reloc_trampoline64(void)
+#else
+#error Unknown architecture
+#endif
+{
+    unsigned long phys = trampoline_phys;
+    const int32_t *trampoline_ptr;
+
+    /*
+     * Apply relocations to trampoline.
+     *
+     * This modifies the trampoline in place within Xen, so that it will
+     * operate correctly when copied into place.
+     */
+    for ( trampoline_ptr = __trampoline_rel_start;
+          trampoline_ptr < __trampoline_rel_stop;
+          ++trampoline_ptr )
+        *(uint32_t *)(*trampoline_ptr + (long)trampoline_ptr) += phys;
+
+    for ( trampoline_ptr = __trampoline_seg_start;
+          trampoline_ptr < __trampoline_seg_stop;
+          ++trampoline_ptr )
+        *(uint16_t *)(*trampoline_ptr + (long)trampoline_ptr) = phys >> 4;
+}

xen/arch/x86/efi/efi-boot.h

@@ -103,27 +103,16 @@ static void __init efi_arch_relocate_image(unsigned long delta)
     }
 }
 
-extern const int32_t __trampoline_rel_start[], __trampoline_rel_stop[];
-extern const int32_t __trampoline_seg_start[], __trampoline_seg_stop[];
+void reloc_trampoline64(void);
 
 static void __init relocate_trampoline(unsigned long phys)
 {
-    const int32_t *trampoline_ptr;
-
     trampoline_phys = phys;
 
     if ( !efi_enabled(EFI_LOADER) )
         return;
 
-    /* Apply relocations to trampoline. */
-    for ( trampoline_ptr = __trampoline_rel_start;
-          trampoline_ptr < __trampoline_rel_stop;
-          ++trampoline_ptr )
-        *(u32 *)(*trampoline_ptr + (long)trampoline_ptr) += phys;
-    for ( trampoline_ptr = __trampoline_seg_start;
-          trampoline_ptr < __trampoline_seg_stop;
-          ++trampoline_ptr )
-        *(u16 *)(*trampoline_ptr + (long)trampoline_ptr) = phys >> 4;
+    reloc_trampoline64();
 }
 
 static void __init place_string(u32 *addr, const char *s)