x86/entry,xen: Early rewrite of restore_regs_and_return_to_kernel()

By doing an early rewrite of 'jmp native_iret` in
restore_regs_and_return_to_kernel() we can get rid of the last
INTERRUPT_RETURN user and paravirt_iret.
Suggested-by: Andrew Cooper <Andrew.Cooper3@citrix.com>
Signed-off-by: Peter Zijlstra (Intel) <peterz@infradead.org>
Acked-by: Josh Poimboeuf <jpoimboe@redhat.com>
Link: https://lore.kernel.org/r/20220308154317.815039833@infradead.org

arch/x86/entry/entry_64.S

@@ -609,7 +609,7 @@ SYM_INNER_LABEL(swapgs_restore_regs_and_return_to_usermode, SYM_L_GLOBAL)
 	/* Restore RDI. */
 	popq	%rdi
 	swapgs
-	jmp	native_iret
+	jmp	.Lnative_iret
 
 
 SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
@@ -626,9 +626,14 @@ SYM_INNER_LABEL(restore_regs_and_return_to_kernel, SYM_L_GLOBAL)
 	 * ARCH_HAS_MEMBARRIER_SYNC_CORE rely on IRET core serialization
 	 * when returning from IPI handler.
 	 */
-	INTERRUPT_RETURN
+#ifdef CONFIG_XEN_PV
+SYM_INNER_LABEL(early_xen_iret_patch, SYM_L_GLOBAL)
+	ANNOTATE_NOENDBR
+	.byte 0xe9
+	.long .Lnative_iret - (. + 4)
+#endif
 
-SYM_INNER_LABEL_ALIGN(native_iret, SYM_L_GLOBAL)
+.Lnative_iret:
 	UNWIND_HINT_IRET_REGS
 	/*
 	 * Are we returning to a stack segment from the LDT?  Note: in

arch/x86/include/asm/irqflags.h

@@ -141,13 +141,8 @@ static __always_inline void arch_local_irq_restore(unsigned long flags)
 #ifdef CONFIG_X86_64
 #ifdef CONFIG_XEN_PV
 #define SWAPGS	ALTERNATIVE "swapgs", "", X86_FEATURE_XENPV
-#define INTERRUPT_RETURN						\
-	ANNOTATE_RETPOLINE_SAFE;					\
-	ALTERNATIVE_TERNARY("jmp *paravirt_iret(%rip);",		\
-		X86_FEATURE_XENPV, "jmp xen_iret;", "jmp native_iret;")
 #else
 #define SWAPGS	swapgs
-#define INTERRUPT_RETURN	jmp native_iret
 #endif
 #endif
 #endif /* !__ASSEMBLY__ */

arch/x86/include/asm/paravirt_types.h

@@ -272,7 +272,6 @@ struct paravirt_patch_template {
 
 extern struct pv_info pv_info;
 extern struct paravirt_patch_template pv_ops;
-extern void (*paravirt_iret)(void);
 
 #define PARAVIRT_PATCH(x)					\
 	(offsetof(struct paravirt_patch_template, x) / sizeof(void *))

arch/x86/kernel/head_64.S

@@ -345,7 +345,6 @@ SYM_CODE_START_NOALIGN(vc_boot_ghcb)
 	/* Remove Error Code */
 	addq    $8, %rsp
 
-	/* Pure iret required here - don't use INTERRUPT_RETURN */
 	iretq
 SYM_CODE_END(vc_boot_ghcb)
 #endif
@@ -426,6 +425,8 @@ SYM_CODE_END(early_idt_handler_common)
  * early_idt_handler_array can't be used because it returns via the
  * paravirtualized INTERRUPT_RETURN and pv-ops don't work that early.
  *
+ * XXX it does, fix this.
+ *
  * This handler will end up in the .init.text section and not be
  * available to boot secondary CPUs.
  */

arch/x86/kernel/paravirt.c

@@ -132,8 +132,6 @@ void paravirt_set_sched_clock(u64 (*func)(void))
 }
 
 /* These are in entry.S */
-extern void native_iret(void);
-
 static struct resource reserve_ioports = {
 	.start = 0,
 	.end = IO_SPACE_LIMIT,
@@ -397,8 +395,6 @@ struct paravirt_patch_template pv_ops = {
 
 #ifdef CONFIG_PARAVIRT_XXL
 NOKPROBE_SYMBOL(native_load_idt);
-
-void (*paravirt_iret)(void) = native_iret;
 #endif
 
 EXPORT_SYMBOL(pv_ops);

arch/x86/xen/enlighten_pv.c

@@ -1177,6 +1177,8 @@ static void __init xen_domu_set_legacy_features(void)
 	x86_platform.legacy.rtc = 0;
 }
 
+extern void early_xen_iret_patch(void);
+
 /* First C function to be called on Xen boot */
 asmlinkage __visible void __init xen_start_kernel(void)
 {
@@ -1187,6 +1189,10 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	if (!xen_start_info)
 		return;
 
+	__text_gen_insn(&early_xen_iret_patch,
+			JMP32_INSN_OPCODE, &early_xen_iret_patch, &xen_iret,
+			JMP32_INSN_SIZE);
+
 	xen_domain_type = XEN_PV_DOMAIN;
 	xen_start_flags = xen_start_info->flags;
 
@@ -1195,7 +1201,6 @@ asmlinkage __visible void __init xen_start_kernel(void)
 	/* Install Xen paravirt ops */
 	pv_info = xen_info;
 	pv_ops.cpu = xen_cpu_ops.cpu;
-	paravirt_iret = xen_iret;
 	xen_init_irq_ops();
 
 	/*

arch/x86/xen/xen-asm.S

@@ -189,6 +189,7 @@ hypercall_iret = hypercall_page + __HYPERVISOR_iret * 32
  */
 SYM_CODE_START(xen_iret)
 	UNWIND_HINT_EMPTY
+	ANNOTATE_NOENDBR
 	pushq $0
 	jmp hypercall_iret
 SYM_CODE_END(xen_iret)