x86, espfix: Make it possible to disable 16-bit support

commit 34273f41d57ee8d854dcd2a1d754cbb546cb548f upstream.

Embedded systems, which may be very memory-size-sensitive, are
extremely unlikely to ever encounter any 16-bit software, so make it
a CONFIG_EXPERT option to turn off support for any 16-bit software
whatsoever.

Signed-off-by: H. Peter Anvin <hpa@zytor.com>
Link: http://lkml.kernel.org/r/1398816946-3351-1-git-send-email-hpa@linux.intel.com
Signed-off-by: Greg Kroah-Hartman <gregkh@linuxfoundation.org>
Signed-off-by: Ben Hutchings <ben@decadent.org.uk>
(cherry picked from 3.2 commit 70d87cbbd92a3611655b39003176ee1033796bf7)
[wt: backport notes for 2.6.32 :
  - Fixed arch/x86/kernel/ldt.c (no IS_ENABLED on 2.6.32).
  - No CONFIG_EXPERT condition in 2.6.32.
/wt]
Signed-off-by: Willy Tarreau <w@1wt.eu>

Signed-off-by: Stefan Bader <stefan.bader@canonical.com>

4 files changed, 44 insertions, 5 deletions

diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig
index 026fe602684a5..67c318736c991 100644
--- a/arch/x86/Kconfig
+++ b/arch/x86/Kconfig
@@ -882,14 +882,27 @@ config VM86
 	default y
 	depends on X86_32
 	---help---
-	  This option is required by programs like DOSEMU to run 16-bit legacy
-	  code on X86 processors. It also may be needed by software like
-	  XFree86 to initialize some video cards via BIOS. Disabling this
-	  option saves about 6k.
+	  This option is required by programs like DOSEMU to run
+	  16-bit real mode legacy code on x86 processors. It also may
+	  be needed by software like XFree86 to initialize some video
+	  cards via BIOS. Disabling this option saves about 6K.
+
+config X86_16BIT
+	bool "Enable support for 16-bit segments"
+	default y
+	---help---
+	  This option is required by programs like Wine to run 16-bit
+	  protected mode legacy code on x86 processors.  Disabling
+	  this option saves about 300 bytes on i386, or around 6K text
+	  plus 16K runtime memory on x86-64,
+
+config X86_ESPFIX32
+	def_bool y
+	depends on X86_16BIT && X86_32
 
 config X86_ESPFIX64
 	def_bool y
-	depends on X86_64
+	depends on X86_16BIT && X86_64
 
 config TOSHIBA
 	tristate "Toshiba Laptop support"
diff --git a/arch/x86/kernel/entry_32.S b/arch/x86/kernel/entry_32.S
index db7dbe703f0d7..c1207f71f8377 100644
--- a/arch/x86/kernel/entry_32.S
+++ b/arch/x86/kernel/entry_32.S
@@ -543,6 +543,7 @@ syscall_exit:
 restore_all:
 	TRACE_IRQS_IRET
 restore_all_notrace:
+#ifdef CONFIG_X86_ESPFIX32
 	movl PT_EFLAGS(%esp), %eax	# mix EFLAGS, SS and CS
 	# Warning: PT_OLDSS(%esp) contains the wrong/random values if we
 	# are returning to the kernel.
@@ -553,6 +554,7 @@ restore_all_notrace:
 	cmpl $((SEGMENT_LDT << 8) | USER_RPL), %eax
 	CFI_REMEMBER_STATE
 	je ldt_ss			# returning to user-space with LDT SS
+#endif
 restore_nocheck:
 	RESTORE_REGS 4			# skip orig_eax/error_code
 	CFI_ADJUST_CFA_OFFSET -4
@@ -569,6 +571,7 @@ ENTRY(iret_exc)
 	.long irq_return,iret_exc
 .previous
 
+#ifdef CONFIG_X86_ESPFIX32
 	CFI_RESTORE_STATE
 ldt_ss:
 #ifdef CONFIG_PARAVIRT
@@ -614,6 +617,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -736,6 +740,7 @@ PTREGSCALL(vm86old)
  * the high word of the segment base from the GDT and swiches to the
  * normal stack and adjusts ESP with the matching offset.
  */
+#ifdef CONFIG_X86_ESPFIX32
 	/* fixup the stack */
 	PER_CPU(gdt_page, %ebx)
 	mov GDT_ENTRY_ESPFIX_SS * 8 + 4(%ebx), %al /* bits 16..23 */
@@ -748,8 +753,10 @@ PTREGSCALL(vm86old)
 	CFI_ADJUST_CFA_OFFSET 4
 	lss (%esp), %esp		/* switch to the normal stack segment */
 	CFI_ADJUST_CFA_OFFSET -8
+#endif
 .endm
 .macro UNWIND_ESPFIX_STACK
+#ifdef CONFIG_X86_ESPFIX32
 	movl %ss, %eax
 	/* see if on espfix stack */
 	cmpw $__ESPFIX_SS, %ax
@@ -760,6 +767,7 @@ PTREGSCALL(vm86old)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1323,6 +1331,7 @@ END(debug)
  */
 ENTRY(nmi)
 	RING0_INT_FRAME
+#ifdef CONFIG_X86_ESPFIX32
 	pushl %eax
 	CFI_ADJUST_CFA_OFFSET 4
 	movl %ss, %eax
@@ -1330,6 +1339,7 @@ ENTRY(nmi)
 	popl %eax
 	CFI_ADJUST_CFA_OFFSET -4
 	je nmi_espfix_stack
+#endif
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
 	pushl %eax
@@ -1372,6 +1382,7 @@ nmi_debug_stack_check:
 	FIX_STACK 24, nmi_stack_correct, 1
 	jmp nmi_stack_correct
 
+#ifdef CONFIG_X86_ESPFIX32
 nmi_espfix_stack:
 	/* We have a RING0_INT_FRAME here.
 	 *
@@ -1397,6 +1408,7 @@ nmi_espfix_stack:
 	lss 12+4(%esp), %esp		# back to espfix stack
 	CFI_ADJUST_CFA_OFFSET -24
 	jmp irq_return
+#endif
 	CFI_ENDPROC
 END(nmi)
 
diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index a69901ec55dc3..cf9e7d22b501a 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/arch/x86/kernel/entry_64.S
@@ -863,8 +863,10 @@ irq_return:
 	 * Are we returning to a stack segment from the LDT?  Note: in
 	 * 64-bit mode SS:RSP on the exception stack is always valid.
 	 */
+#ifdef CONFIG_X86_ESPFIX64
 	testb $4,(SS-RIP)(%rsp)
 	jnz irq_return_ldt
+#endif
 
 irq_return_iret:
 	INTERRUPT_RETURN
@@ -882,6 +884,7 @@ ENTRY(native_iret)
 	.previous
 #endif
 
+#ifdef CONFIG_X86_ESPFIX64
 irq_return_ldt:
 	pushq_cfi %rax
 	pushq_cfi %rdi
@@ -905,6 +908,7 @@ irq_return_ldt:
 	movq %rax,%rsp
 	popq_cfi %rax
 	jmp irq_return_iret
+#endif
 
 	.section .fixup,"ax"
 bad_iret:
@@ -980,6 +984,7 @@ END(common_interrupt)
 	 * modify the stack to make it look like we just entered
 	 * the #GP handler from user space, similar to bad_iret.
 	 */
+#ifdef CONFIG_X86_ESPFIX64
 	ALIGN
 __do_double_fault:
 	XCPT_FRAME 1 RDI+8
@@ -1005,6 +1010,9 @@ __do_double_fault:
 	retq
 	CFI_ENDPROC
 END(__do_double_fault)
+#else
+# define __do_double_fault do_double_fault
+#endif
 
 /*
  * APIC interrupts.
diff --git a/arch/x86/kernel/ldt.c b/arch/x86/kernel/ldt.c
index ec6ef60cbd170..4e668bb213839 100644
--- a/arch/x86/kernel/ldt.c
+++ b/arch/x86/kernel/ldt.c
@@ -229,6 +229,12 @@ static int write_ldt(void __user *ptr, unsigned long bytecount, int oldmode)
 		}
 	}
 
+#ifndef CONFIG_X86_16BIT
+	if (!ldt_info.seg_32bit) {
+		error = -EINVAL;
+		goto out_unlock;
+	}
+#endif
 	fill_ldt(&ldt, &ldt_info);
 	if (oldmode)
 		ldt.avl = 0;