Merge tag 'x86-urgent-2020-07-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip into master

Pull x86 fixes from Thomas Gleixner:
 "A pile of fixes for x86:

   - Fix the I/O bitmap invalidation on XEN PV, which was overlooked in
     the recent ioperm/iopl rework. This caused the TSS and XEN's I/O
     bitmap to get out of sync.

   - Use the proper vectors for HYPERV.

   - Make disabling of stack protector for the entry code work with GCC
     builds which enable stack protector by default. Removing the option
     is not sufficient, it needs an explicit -fno-stack-protector to
     shut it off.

   - Mark check_user_regs() noinstr as it is called from noinstr code.
     The missing annotation causes it to be placed in the text section
     which makes it instrumentable.

   - Add the missing interrupt disable in exc_alignment_check()

   - Fixup a XEN_PV build dependency in the 32bit entry code

   - A few fixes to make the Clang integrated assembler happy

   - Move EFI stub build to the right place for out of tree builds

   - Make prepare_exit_to_usermode() static. It's not longer called from
     ASM code"

* tag 'x86-urgent-2020-07-19' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  x86/boot: Don't add the EFI stub to targets
  x86/entry: Actually disable stack protector
  x86/ioperm: Fix io bitmap invalidation on Xen PV
  x86: math-emu: Fix up 'cmp' insn for clang ias
  x86/entry: Fix vectors to IDTENTRY_SYSVEC for CONFIG_HYPERV
  x86/entry: Add compatibility with IAS
  x86/entry/common: Make prepare_exit_to_usermode() static
  x86/entry: Mark check_user_regs() noinstr
  x86/traps: Disable interrupts in exc_aligment_check()
  x86/entry/32: Fix XEN_PV build dependency

arch/x86/boot/compressed/Makefile

@@ -90,8 +90,8 @@ endif
 
 vmlinux-objs-$(CONFIG_ACPI) += $(obj)/acpi.o
 
-vmlinux-objs-$(CONFIG_EFI_STUB) += $(objtree)/drivers/firmware/efi/libstub/lib.a
 vmlinux-objs-$(CONFIG_EFI_MIXED) += $(obj)/efi_thunk_$(BITS).o
+efi-obj-$(CONFIG_EFI_STUB) = $(objtree)/drivers/firmware/efi/libstub/lib.a
 
 # The compressed kernel is built with -fPIC/-fPIE so that a boot loader
 # can place it anywhere in memory and it will still run. However, since
@@ -115,7 +115,7 @@ endef
 quiet_cmd_check-and-link-vmlinux = LD      $@
       cmd_check-and-link-vmlinux = $(cmd_check_data_rel); $(cmd_ld)
 
-$(obj)/vmlinux: $(vmlinux-objs-y) FORCE
+$(obj)/vmlinux: $(vmlinux-objs-y) $(efi-obj-y) FORCE
 	$(call if_changed,check-and-link-vmlinux)
 
 OBJCOPYFLAGS_vmlinux.bin :=  -R .comment -S

arch/x86/entry/Makefile

@@ -7,12 +7,20 @@ KASAN_SANITIZE := n
 UBSAN_SANITIZE := n
 KCOV_INSTRUMENT := n
 
-CFLAGS_REMOVE_common.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_common.o		= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_syscall_32.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_syscall_64.o	= $(CC_FLAGS_FTRACE)
-CFLAGS_REMOVE_syscall_64.o = $(CC_FLAGS_FTRACE) -fstack-protector -fstack-protector-strong
+CFLAGS_REMOVE_syscall_32.o	= $(CC_FLAGS_FTRACE)
+CFLAGS_REMOVE_syscall_x32.o	= $(CC_FLAGS_FTRACE)
+
+CFLAGS_common.o			+= -fno-stack-protector
+CFLAGS_syscall_64.o		+= -fno-stack-protector
+CFLAGS_syscall_32.o		+= -fno-stack-protector
+CFLAGS_syscall_x32.o		+= -fno-stack-protector
 
 CFLAGS_syscall_64.o		+= $(call cc-option,-Wno-override-init,)
 CFLAGS_syscall_32.o		+= $(call cc-option,-Wno-override-init,)
+CFLAGS_syscall_x32.o		+= $(call cc-option,-Wno-override-init,)
+
 obj-y				:= entry_$(BITS).o thunk_$(BITS).o syscall_$(BITS).o
 obj-y				+= common.o
 

arch/x86/entry/common.c

@@ -46,7 +46,7 @@
 #include <trace/events/syscalls.h>
 
 /* Check that the stack and regs on entry from user mode are sane. */
-static void check_user_regs(struct pt_regs *regs)
+static noinstr void check_user_regs(struct pt_regs *regs)
 {
 	if (IS_ENABLED(CONFIG_DEBUG_ENTRY)) {
 		/*
@@ -294,7 +294,7 @@ static void __prepare_exit_to_usermode(struct pt_regs *regs)
 #endif
 }
 
-__visible noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
+static noinstr void prepare_exit_to_usermode(struct pt_regs *regs)
 {
 	instrumentation_begin();
 	__prepare_exit_to_usermode(regs);

arch/x86/include/asm/idtentry.h

@@ -469,16 +469,15 @@ __visible noinstr void func(struct pt_regs *regs,			\
 	.align 8
 SYM_CODE_START(irq_entries_start)
     vector=FIRST_EXTERNAL_VECTOR
-    pos = .
     .rept (FIRST_SYSTEM_VECTOR - FIRST_EXTERNAL_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_common_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
+	. = 0b + 8
-    pos=pos+8
+	vector = vector+1
-    vector=vector+1
     .endr
 SYM_CODE_END(irq_entries_start)
 
@@ -486,16 +485,15 @@ SYM_CODE_END(irq_entries_start)
 	.align 8
 SYM_CODE_START(spurious_entries_start)
     vector=FIRST_SYSTEM_VECTOR
-    pos = .
     .rept (NR_VECTORS - FIRST_SYSTEM_VECTOR)
 	UNWIND_HINT_IRET_REGS
+0 :
 	.byte	0x6a, vector
 	jmp	asm_spurious_interrupt
 	nop
 	/* Ensure that the above is 8 bytes max */
-	. = pos + 8
+	. = 0b + 8
-    pos=pos+8
+	vector = vector+1
-    vector=vector+1
     .endr
 SYM_CODE_END(spurious_entries_start)
 #endif
@@ -553,7 +551,7 @@ DECLARE_IDTENTRY_RAW(X86_TRAP_MC,	exc_machine_check);
 
 /* NMI */
 DECLARE_IDTENTRY_NMI(X86_TRAP_NMI,	exc_nmi);
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
 DECLARE_IDTENTRY_RAW(X86_TRAP_NMI,	xenpv_exc_nmi);
 #endif
 
@@ -563,7 +561,7 @@ DECLARE_IDTENTRY_DEBUG(X86_TRAP_DB,	exc_debug);
 #else
 DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	exc_debug);
 #endif
-#ifdef CONFIG_XEN_PV
+#if defined(CONFIG_XEN_PV) && defined(CONFIG_X86_64)
 DECLARE_IDTENTRY_RAW(X86_TRAP_DB,	xenpv_exc_debug);
 #endif
 
@@ -626,8 +624,8 @@ DECLARE_IDTENTRY_SYSVEC(POSTED_INTR_NESTED_VECTOR,	sysvec_kvm_posted_intr_nested
 
 #if IS_ENABLED(CONFIG_HYPERV)
 DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_CALLBACK_VECTOR,	sysvec_hyperv_callback);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_REENLIGHTENMENT_VECTOR,	sysvec_hyperv_reenlightenment);
-DECLARE_IDTENTRY_SYSVEC(HYPERVISOR_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
+DECLARE_IDTENTRY_SYSVEC(HYPERV_STIMER0_VECTOR,	sysvec_hyperv_stimer0);
 #endif
 
 #if IS_ENABLED(CONFIG_ACRN_GUEST)

arch/x86/include/asm/io_bitmap.h

@@ -19,12 +19,28 @@ struct task_struct;
 void io_bitmap_share(struct task_struct *tsk);
 void io_bitmap_exit(struct task_struct *tsk);
 
+static inline void native_tss_invalidate_io_bitmap(void)
+{
+	/*
+	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
+	 * TSS limit so any subsequent I/O access from user space will
+	 * trigger a #GP.
+	 *
+	 * This is correct even when VMEXIT rewrites the TSS limit
+	 * to 0x67 as the only requirement is that the base points
+	 * outside the limit.
+	 */
+	this_cpu_write(cpu_tss_rw.x86_tss.io_bitmap_base,
+		       IO_BITMAP_OFFSET_INVALID);
+}
+
 void native_tss_update_io_bitmap(void);
 
 #ifdef CONFIG_PARAVIRT_XXL
 #include <asm/paravirt.h>
 #else
 #define tss_update_io_bitmap native_tss_update_io_bitmap
+#define tss_invalidate_io_bitmap native_tss_invalidate_io_bitmap
 #endif
 
 #else

arch/x86/include/asm/paravirt.h

@@ -302,6 +302,11 @@ static inline void write_idt_entry(gate_desc *dt, int entry, const gate_desc *g)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static inline void tss_invalidate_io_bitmap(void)
+{
+	PVOP_VCALL0(cpu.invalidate_io_bitmap);
+}
+
 static inline void tss_update_io_bitmap(void)
 {
 	PVOP_VCALL0(cpu.update_io_bitmap);

arch/x86/include/asm/paravirt_types.h

@@ -141,6 +141,7 @@ struct pv_cpu_ops {
 	void (*load_sp0)(unsigned long sp0);
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	void (*invalidate_io_bitmap)(void);
 	void (*update_io_bitmap)(void);
 #endif
 

arch/x86/kernel/paravirt.c

@@ -324,7 +324,8 @@ struct paravirt_patch_template pv_ops = {
 	.cpu.swapgs		= native_swapgs,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-	.cpu.update_io_bitmap	= native_tss_update_io_bitmap,
+	.cpu.invalidate_io_bitmap	= native_tss_invalidate_io_bitmap,
+	.cpu.update_io_bitmap		= native_tss_update_io_bitmap,
 #endif
 
 	.cpu.start_context_switch	= paravirt_nop,

arch/x86/kernel/process.c

@@ -322,20 +322,6 @@ void arch_setup_new_exec(void)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
-static inline void tss_invalidate_io_bitmap(struct tss_struct *tss)
-{
-	/*
-	 * Invalidate the I/O bitmap by moving io_bitmap_base outside the
-	 * TSS limit so any subsequent I/O access from user space will
-	 * trigger a #GP.
-	 *
-	 * This is correct even when VMEXIT rewrites the TSS limit
-	 * to 0x67 as the only requirement is that the base points
-	 * outside the limit.
-	 */
-	tss->x86_tss.io_bitmap_base = IO_BITMAP_OFFSET_INVALID;
-}
-
 static inline void switch_to_bitmap(unsigned long tifp)
 {
 	/*
@@ -346,7 +332,7 @@ static inline void switch_to_bitmap(unsigned long tifp)
 	 * user mode.
 	 */
 	if (tifp & _TIF_IO_BITMAP)
-		tss_invalidate_io_bitmap(this_cpu_ptr(&cpu_tss_rw));
+		tss_invalidate_io_bitmap();
 }
 
 static void tss_copy_io_bitmap(struct tss_struct *tss, struct io_bitmap *iobm)
@@ -380,7 +366,7 @@ void native_tss_update_io_bitmap(void)
 	u16 *base = &tss->x86_tss.io_bitmap_base;
 
 	if (!test_thread_flag(TIF_IO_BITMAP)) {
-		tss_invalidate_io_bitmap(tss);
+		native_tss_invalidate_io_bitmap();
 		return;
 	}
 

arch/x86/kernel/traps.c

@@ -303,6 +303,8 @@ DEFINE_IDTENTRY_ERRORCODE(exc_alignment_check)
 
 	do_trap(X86_TRAP_AC, SIGBUS, "alignment check", regs,
 		error_code, BUS_ADRALN, NULL);
+
+	local_irq_disable();
 }
 
 #ifdef CONFIG_VMAP_STACK

arch/x86/math-emu/wm_sqrt.S

@@ -209,7 +209,7 @@ sqrt_stage_2_finish:
 
 #ifdef PARANOID
 /* It should be possible to get here only if the arg is ffff....ffff */
-	cmp	$0xffffffff,FPU_fsqrt_arg_1
+	cmpl	$0xffffffff,FPU_fsqrt_arg_1
 	jnz	sqrt_stage_2_error
 #endif /* PARANOID */
 

arch/x86/xen/enlighten_pv.c

@@ -870,6 +870,17 @@ static void xen_load_sp0(unsigned long sp0)
 }
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+static void xen_invalidate_io_bitmap(void)
+{
+	struct physdev_set_iobitmap iobitmap = {
+		.bitmap = 0,
+		.nr_ports = 0,
+	};
+
+	native_tss_invalidate_io_bitmap();
+	HYPERVISOR_physdev_op(PHYSDEVOP_set_iobitmap, &iobitmap);
+}
+
 static void xen_update_io_bitmap(void)
 {
 	struct physdev_set_iobitmap iobitmap;
@@ -1099,6 +1110,7 @@ static const struct pv_cpu_ops xen_cpu_ops __initconst = {
 	.load_sp0 = xen_load_sp0,
 
 #ifdef CONFIG_X86_IOPL_IOPERM
+	.invalidate_io_bitmap = xen_invalidate_io_bitmap,
 	.update_io_bitmap = xen_update_io_bitmap,
 #endif
 	.io_delay = xen_io_delay,