x86: Reduce assembly code size of entry points

On many entries we push 8-bytes zero and exception constants are
small so we can just write a single byte saving 3 bytes for
instruction.
With ENDBR64 this reduces the size of many entry points from 32 to
16 bytes (due to alignment).
The push and the mov are overlapping stores either way.  Swapping
between movl and movb will make no difference at all on performance.
Similar code is already used in autogen_stubs.

Signed-off-by: Frediano Ziglio <frediano.ziglio@cloud.com>
Reviewed-by: Jan Beulich <jbeulich@suse.com>

xen/arch/x86/x86_64/entry.S

@@ -22,6 +22,14 @@
 #endif
 .endm
 
+.macro BUILD_BUG_ON condstr cond:vararg
+        .if \cond
+        .error "Condition \"\condstr\" not satisfied"
+        .endif
+.endm
+/* preprocessor macro to make error message more user friendly */
+#define BUILD_BUG_ON(cond) BUILD_BUG_ON #cond cond
+
 #ifdef CONFIG_PV
 /* %rbx: struct vcpu */
 FUNC_LOCAL(switch_to_kernel)
@@ -187,7 +195,8 @@ FUNC_LOCAL(restore_all_guest)
         SPEC_CTRL_EXIT_TO_PV    /* Req: a=spec_ctrl %rsp=regs/cpuinfo, Clob: cd */
 
         RESTORE_ALL
-        testw $TRAP_syscall,4(%rsp)
+        BUILD_BUG_ON(TRAP_syscall & 0xff)
+        testb $TRAP_syscall >> 8, 4+1(%rsp)
         jz    iret_exit_to_guest
 
         movq  24(%rsp),%r11           # RFLAGS
@@ -254,7 +263,8 @@ FUNC(lstar_enter)
         pushq $FLAT_KERNEL_CS64
         pushq %rcx
         pushq $0
-        movl  $TRAP_syscall, 4(%rsp)
+        BUILD_BUG_ON(TRAP_syscall & 0xff)
+        movb  $TRAP_syscall >> 8, 4+1(%rsp)
         SAVE_ALL
 
         SPEC_CTRL_ENTRY_FROM_PV /* Req: %rsp=regs/cpuinfo, %rdx=0, Clob: acd */
@@ -292,7 +302,8 @@ FUNC(cstar_enter)
         pushq $FLAT_USER_CS32
         pushq %rcx
         pushq $0
-        movl  $TRAP_syscall, 4(%rsp)
+        BUILD_BUG_ON(TRAP_syscall & 0xff)
+        movb  $TRAP_syscall >> 8, 4+1(%rsp)
         SAVE_ALL
 
         SPEC_CTRL_ENTRY_FROM_PV /* Req: %rsp=regs/cpuinfo, %rdx=0, Clob: acd */
@@ -334,7 +345,8 @@ LABEL(sysenter_eflags_saved, 0)
         pushq $3 /* ring 3 null cs */
         pushq $0 /* null rip */
         pushq $0
-        movl  $TRAP_syscall, 4(%rsp)
+        BUILD_BUG_ON(TRAP_syscall & 0xff)
+        movb  $TRAP_syscall >> 8, 4+1(%rsp)
         SAVE_ALL
 
         SPEC_CTRL_ENTRY_FROM_PV /* Req: %rsp=regs/cpuinfo, %rdx=0, Clob: acd */
@@ -389,7 +401,7 @@ FUNC(entry_int80)
         ENDBR64
         ALTERNATIVE "", clac, X86_FEATURE_XEN_SMAP
         pushq $0
-        movl  $0x80, 4(%rsp)
+        movb  $0x80, 4(%rsp)
         SAVE_ALL
 
         SPEC_CTRL_ENTRY_FROM_PV /* Req: %rsp=regs/cpuinfo, %rdx=0, Clob: acd */
@@ -561,7 +573,8 @@ __UNLIKELY_END(create_bounce_frame_bad_sp)
         /* Rewrite our stack frame and return to guest-OS mode. */
         /* IA32 Ref. Vol. 3: TF, VM, RF and NT flags are cleared on trap. */
         /* Also clear AC: alignment checks shouldn't trigger in kernel mode. */
-        orl   $TRAP_syscall,UREGS_entry_vector+8(%rsp)
+        BUILD_BUG_ON(TRAP_syscall & 0xff)
+        orb   $TRAP_syscall >> 8, UREGS_entry_vector+8+1(%rsp)
         andl  $~(X86_EFLAGS_AC|X86_EFLAGS_VM|X86_EFLAGS_RF|\
                  X86_EFLAGS_NT|X86_EFLAGS_TF),UREGS_eflags+8(%rsp)
         movq  $FLAT_KERNEL_SS,UREGS_ss+8(%rsp)
@@ -653,7 +666,7 @@ END(ret_from_intr)
         .section .init.text, "ax", @progbits
 FUNC(early_page_fault)
         ENDBR64
-        movl  $X86_EXC_PF, 4(%rsp)
+        movb  $X86_EXC_PF, 4(%rsp)
         SAVE_ALL
         movq  %rsp, %rdi
         call  do_early_page_fault
@@ -722,7 +735,7 @@ END(common_interrupt)
 
 FUNC(entry_PF)
         ENDBR64
-        movl  $X86_EXC_PF, 4(%rsp)
+        movb  $X86_EXC_PF, 4(%rsp)
 END(entry_PF)
 /* No special register assumptions. */
 FUNC(handle_exception, 0)
@@ -898,105 +911,106 @@ END(handle_exception)
 FUNC(entry_DE)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_DE, 4(%rsp)
+        /* no need to update exception type, already 0 */
+        BUILD_BUG_ON(X86_EXC_DE)
         jmp   handle_exception
 END(entry_DE)
 
 FUNC(entry_MF)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_MF, 4(%rsp)
+        movb  $X86_EXC_MF, 4(%rsp)
         jmp   handle_exception
 END(entry_MF)
 
 FUNC(entry_XM)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_XM, 4(%rsp)
+        movb  $X86_EXC_XM, 4(%rsp)
         jmp   handle_exception
 END(entry_XM)
 
 FUNC(entry_NM)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_NM, 4(%rsp)
+        movb  $X86_EXC_NM, 4(%rsp)
         jmp   handle_exception
 END(entry_NM)
 
 FUNC(entry_DB)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_DB, 4(%rsp)
+        movb  $X86_EXC_DB, 4(%rsp)
         jmp   handle_ist_exception
 END(entry_DB)
 
 FUNC(entry_BP)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_BP, 4(%rsp)
+        movb  $X86_EXC_BP, 4(%rsp)
         jmp   handle_exception
 END(entry_BP)
 
 FUNC(entry_OF)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_OF, 4(%rsp)
+        movb  $X86_EXC_OF, 4(%rsp)
         jmp   handle_exception
 END(entry_OF)
 
 FUNC(entry_BR)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_BR, 4(%rsp)
+        movb  $X86_EXC_BR, 4(%rsp)
         jmp   handle_exception
 END(entry_BR)
 
 FUNC(entry_UD)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_UD, 4(%rsp)
+        movb  $X86_EXC_UD, 4(%rsp)
         jmp   handle_exception
 END(entry_UD)
 
 FUNC(entry_TS)
         ENDBR64
-        movl  $X86_EXC_TS, 4(%rsp)
+        movb  $X86_EXC_TS, 4(%rsp)
         jmp   handle_exception
 END(entry_TS)
 
 FUNC(entry_NP)
         ENDBR64
-        movl  $X86_EXC_NP, 4(%rsp)
+        movb  $X86_EXC_NP, 4(%rsp)
         jmp   handle_exception
 END(entry_NP)
 
 FUNC(entry_SS)
         ENDBR64
-        movl  $X86_EXC_SS, 4(%rsp)
+        movb  $X86_EXC_SS, 4(%rsp)
         jmp   handle_exception
 END(entry_SS)
 
 FUNC(entry_GP)
         ENDBR64
-        movl  $X86_EXC_GP, 4(%rsp)
+        movb  $X86_EXC_GP, 4(%rsp)
         jmp   handle_exception
 END(entry_GP)
 
 FUNC(entry_AC)
         ENDBR64
-        movl  $X86_EXC_AC, 4(%rsp)
+        movb  $X86_EXC_AC, 4(%rsp)
         jmp   handle_exception
 END(entry_AC)
 
 FUNC(entry_CP)
         ENDBR64
-        movl  $X86_EXC_CP, 4(%rsp)
+        movb  $X86_EXC_CP, 4(%rsp)
         jmp   handle_exception
 END(entry_CP)
 
 FUNC(entry_DF)
         ENDBR64
-        movl  $X86_EXC_DF, 4(%rsp)
+        movb  $X86_EXC_DF, 4(%rsp)
         /* Set AC to reduce chance of further SMAP faults */
         ALTERNATIVE "", stac, X86_FEATURE_XEN_SMAP
         SAVE_ALL
@@ -1022,7 +1036,7 @@ END(entry_DF)
 FUNC(entry_NMI)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_NMI, 4(%rsp)
+        movb  $X86_EXC_NMI, 4(%rsp)
 END(entry_NMI)
 
 FUNC(handle_ist_exception)
@@ -1158,7 +1172,7 @@ END(handle_ist_exception)
 FUNC(entry_MC)
         ENDBR64
         pushq $0
-        movl  $X86_EXC_MC, 4(%rsp)
+        movb  $X86_EXC_MC, 4(%rsp)
         jmp   handle_ist_exception
 END(entry_MC)