[PATCH v2 63/70] x86/traps: Rework write_stub_trampoline() to not hardcode the jmp

[Andrew Cooper]

For CET-IBT, we will need to optionally insert an endbr64 instruction at the
start of the stub.  Don't hardcode the jmp displacement assuming that it
starts at byte 24 of the stub.

Also add extra comments describing what is going on.  The mix of %rax and %rsp
is far from trivial to follow.

Signed-off-by: Andrew Cooper <andrew.coop...@citrix.com>
Reviewed-by: Jan Beulich <jbeul...@suse.com>
---
CC: Jan Beulich <jbeul...@suse.com>
CC: Roger Pau Monné <roger....@citrix.com>
CC: Wei Liu <w...@xen.org>

v2:
 * Retain the rounding up to 16 bytes.
---
 xen/arch/x86/x86_64/traps.c | 35 ++++++++++++++++++++++-------------
 1 file changed, 22 insertions(+), 13 deletions(-)

diff --git a/xen/arch/x86/x86_64/traps.c b/xen/arch/x86/x86_64/traps.c
index d661d7ffcaaf..edc6820b85c7 100644
--- a/xen/arch/x86/x86_64/traps.c
+++ b/xen/arch/x86/x86_64/traps.c
@@ -293,30 +293,39 @@ static unsigned int write_stub_trampoline(
     unsigned char *stub, unsigned long stub_va,
     unsigned long stack_bottom, unsigned long target_va)
 {
+    unsigned char *p = stub;
+
+    /* Store guest %rax into %ss slot */
     /* movabsq %rax, stack_bottom - 8 */
-    stub[0] = 0x48;
-    stub[1] = 0xa3;
-    *(uint64_t *)&stub[2] = stack_bottom - 8;
+    *p++ = 0x48;
+    *p++ = 0xa3;
+    *(uint64_t *)p = stack_bottom - 8;
+    p += 8;
 
+    /* Store guest %rsp in %rax */
     /* movq %rsp, %rax */
-    stub[10] = 0x48;
-    stub[11] = 0x89;
-    stub[12] = 0xe0;
+    *p++ = 0x48;
+    *p++ = 0x89;
+    *p++ = 0xe0;
 
+    /* Switch to Xen stack */
     /* movabsq $stack_bottom - 8, %rsp */
-    stub[13] = 0x48;
-    stub[14] = 0xbc;
-    *(uint64_t *)&stub[15] = stack_bottom - 8;
+    *p++ = 0x48;
+    *p++ = 0xbc;
+    *(uint64_t *)p = stack_bottom - 8;
+    p += 8;
 
+    /* Store guest %rsp into %rsp slot */
     /* pushq %rax */
-    stub[23] = 0x50;
+    *p++ = 0x50;
 
     /* jmp target_va */
-    stub[24] = 0xe9;
-    *(int32_t *)&stub[25] = target_va - (stub_va + 29);
+    *p++ = 0xe9;
+    *(int32_t *)p = target_va - (stub_va + (p - stub) + 4);
+    p += 4;
 
     /* Round up to a multiple of 16 bytes. */
-    return 32;
+    return ROUNDUP(p - stub, 16);
 }
 
 DEFINE_PER_CPU(struct stubs, stubs);
-- 
2.11.0