Merge branch 'x86/espfix' of git://git.kernel.org/pub/scm/linux/kerne…

…l/git/tip/tip into next

Pull x86-64 espfix changes from Peter Anvin:
 "This is the espfix64 code, which fixes the IRET information leak as
  well as the associated functionality problem.  With this code applied,
  16-bit stack segments finally work as intended even on a 64-bit
  kernel.

  Consequently, this patchset also removes the runtime option that we
  added as an interim measure.

  To help the people working on Linux kernels for very small systems,
  this patchset also makes these compile-time configurable features"

* 'x86/espfix' of git://git.kernel.org/pub/scm/linux/kernel/git/tip/tip:
  Revert "x86-64, modify_ldt: Make support for 16-bit segments a runtime option"
  x86, espfix: Make it possible to disable 16-bit support
  x86, espfix: Make espfix64 a Kconfig option, fix UML
  x86, espfix: Fix broken header guard
  x86, espfix: Move espfix definitions into a separate header file
  x86-32, espfix: Remove filter for espfix32 due to race
  x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack

Documentation/x86/x86_64/mm.txt

@@ -12,6 +12,8 @@ ffffc90000000000 - ffffe8ffffffffff (=45 bits) vmalloc/ioremap space
 ffffe90000000000 - ffffe9ffffffffff (=40 bits) hole
 ffffea0000000000 - ffffeaffffffffff (=40 bits) virtual memory map (1TB)
 ... unused hole ...
+ffffff0000000000 - ffffff7fffffffff (=39 bits) %esp fixup stacks
+... unused hole ...
 ffffffff80000000 - ffffffffa0000000 (=512 MB)  kernel text mapping, from phys 0
 ffffffffa0000000 - ffffffffff5fffff (=1525 MB) module mapping space
 ffffffffff600000 - ffffffffffdfffff (=8 MB) vsyscalls

arch/x86/Kconfig

@@ -912,10 +912,27 @@ 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" if EXPERT
+	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_16BIT && X86_64
 
 config TOSHIBA
 	tristate "Toshiba Laptop support"

arch/x86/include/asm/espfix.h

@@ -0,0 +1,16 @@
+#ifndef _ASM_X86_ESPFIX_H
+#define _ASM_X86_ESPFIX_H
+
+#ifdef CONFIG_X86_64
+
+#include <asm/percpu.h>
+
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_stack);
+DECLARE_PER_CPU_READ_MOSTLY(unsigned long, espfix_waddr);
+
+extern void init_espfix_bsp(void);
+extern void init_espfix_ap(void);
+
+#endif /* CONFIG_X86_64 */
+
+#endif /* _ASM_X86_ESPFIX_H */

arch/x86/include/asm/pgtable_64_types.h

@@ -61,6 +61,8 @@ typedef struct { pteval_t pte; } pte_t;
 #define MODULES_VADDR    (__START_KERNEL_map + KERNEL_IMAGE_SIZE)
 #define MODULES_END      _AC(0xffffffffff000000, UL)
 #define MODULES_LEN   (MODULES_END - MODULES_VADDR)
+#define ESPFIX_PGD_ENTRY _AC(-2, UL)
+#define ESPFIX_BASE_ADDR (ESPFIX_PGD_ENTRY << PGDIR_SHIFT)
 
 #define EARLY_DYNAMIC_PAGE_TABLES	64
 

arch/x86/include/asm/setup.h

@@ -59,6 +59,8 @@ static inline void x86_ce4100_early_setup(void) { }
 
 #ifndef _SETUP
 
+#include <asm/espfix.h>
+
 /*
  * This is set up by the setup-routine at boot-time
  */

arch/x86/kernel/Makefile

@@ -29,6 +29,7 @@ obj-$(CONFIG_X86_64)	+= sys_x86_64.o x8664_ksyms_64.o
 obj-y			+= syscall_$(BITS).o vsyscall_gtod.o
 obj-$(CONFIG_X86_64)	+= vsyscall_64.o
 obj-$(CONFIG_X86_64)	+= vsyscall_emu_64.o
+obj-$(CONFIG_X86_ESPFIX64)	+= espfix_64.o
 obj-$(CONFIG_SYSFS)	+= ksysfs.o
 obj-y			+= bootflag.o e820.o
 obj-y			+= pci-dma.o quirks.o topology.o kdebugfs.o

arch/x86/kernel/entry_32.S

@@ -527,6 +527,7 @@ 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.
@@ -537,6 +538,7 @@ 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
 irq_return:
@@ -549,13 +551,9 @@ ENTRY(iret_exc)
 .previous
 	_ASM_EXTABLE(irq_return,iret_exc)
 
+#ifdef CONFIG_X86_ESPFIX32
 	CFI_RESTORE_STATE
 ldt_ss:
-	larl PT_OLDSS(%esp), %eax
-	jnz restore_nocheck
-	testl $0x00400000, %eax		# returning to 32bit stack?
-	jnz restore_nocheck		# allright, normal return
-
 #ifdef CONFIG_PARAVIRT
 	/*
 	 * The kernel can't run on a non-flat stack if paravirt mode
@@ -597,6 +595,7 @@ ldt_ss:
 	lss (%esp), %esp		/* switch to espfix segment */
 	CFI_ADJUST_CFA_OFFSET -8
 	jmp restore_nocheck
+#endif
 	CFI_ENDPROC
 ENDPROC(system_call)
 
@@ -704,6 +703,7 @@ END(syscall_badsys)
  * 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 */
 	mov GDT_ESPFIX_SS + 4, %al /* bits 16..23 */
 	mov GDT_ESPFIX_SS + 7, %ah /* bits 24..31 */
@@ -713,8 +713,10 @@ END(syscall_badsys)
 	pushl_cfi %eax
 	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
@@ -725,6 +727,7 @@ END(syscall_badsys)
 	/* switch to normal stack */
 	FIXUP_ESPFIX_STACK
 27:
+#endif
 .endm
 
 /*
@@ -1355,11 +1358,13 @@ END(debug)
 ENTRY(nmi)
 	RING0_INT_FRAME
 	ASM_CLAC
+#ifdef CONFIG_X86_ESPFIX32
 	pushl_cfi %eax
 	movl %ss, %eax
 	cmpw $__ESPFIX_SS, %ax
 	popl_cfi %eax
 	je nmi_espfix_stack
+#endif
 	cmpl $ia32_sysenter_target,(%esp)
 	je nmi_stack_fixup
 	pushl_cfi %eax
@@ -1399,6 +1404,7 @@ 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.
 	 *
@@ -1420,6 +1426,7 @@ 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)
 

arch/x86/kernel/entry_64.S

@@ -58,6 +58,7 @@
 #include <asm/asm.h>
 #include <asm/context_tracking.h>
 #include <asm/smap.h>
+#include <asm/pgtable_types.h>
 #include <linux/err.h>
 
 /* Avoid __ASSEMBLER__'ifying <linux/audit.h> just for this.  */
@@ -1040,15 +1041,51 @@ restore_args:
 	RESTORE_ARGS 1,8,1
 
 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
-	_ASM_EXTABLE(irq_return, bad_iret)
+	_ASM_EXTABLE(irq_return_iret, bad_iret)
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
 	iretq
 	_ASM_EXTABLE(native_iret, bad_iret)
 #endif
 
+#ifdef CONFIG_X86_ESPFIX64
+irq_return_ldt:
+	pushq_cfi %rax
+	pushq_cfi %rdi
+	SWAPGS
+	movq PER_CPU_VAR(espfix_waddr),%rdi
+	movq %rax,(0*8)(%rdi)	/* RAX */
+	movq (2*8)(%rsp),%rax	/* RIP */
+	movq %rax,(1*8)(%rdi)
+	movq (3*8)(%rsp),%rax	/* CS */
+	movq %rax,(2*8)(%rdi)
+	movq (4*8)(%rsp),%rax	/* RFLAGS */
+	movq %rax,(3*8)(%rdi)
+	movq (6*8)(%rsp),%rax	/* SS */
+	movq %rax,(5*8)(%rdi)
+	movq (5*8)(%rsp),%rax	/* RSP */
+	movq %rax,(4*8)(%rdi)
+	andl $0xffff0000,%eax
+	popq_cfi %rdi
+	orq PER_CPU_VAR(espfix_stack),%rax
+	SWAPGS
+	movq %rax,%rsp
+	popq_cfi %rax
+	jmp irq_return_iret
+#endif
+
 	.section .fixup,"ax"
 bad_iret:
 	/*
@@ -1110,9 +1147,45 @@ ENTRY(retint_kernel)
 	call preempt_schedule_irq
 	jmp exit_intr
 #endif
-
 	CFI_ENDPROC
 END(common_interrupt)
+
+	/*
+	 * If IRET takes a fault on the espfix stack, then we
+	 * end up promoting it to a doublefault.  In that case,
+	 * 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
+	movq RSP(%rdi),%rax		/* Trap on the espfix stack? */
+	sarq $PGDIR_SHIFT,%rax
+	cmpl $ESPFIX_PGD_ENTRY,%eax
+	jne do_double_fault		/* No, just deliver the fault */
+	cmpl $__KERNEL_CS,CS(%rdi)
+	jne do_double_fault
+	movq RIP(%rdi),%rax
+	cmpq $irq_return_iret,%rax
+#ifdef CONFIG_PARAVIRT
+	je 1f
+	cmpq $native_iret,%rax
+#endif
+	jne do_double_fault		/* This shouldn't happen... */
+1:
+	movq PER_CPU_VAR(kernel_stack),%rax
+	subq $(6*8-KERNEL_STACK_OFFSET),%rax	/* Reset to original stack */
+	movq %rax,RSP(%rdi)
+	movq $0,(%rax)			/* Missing (lost) #GP error code */
+	movq $general_protection,RIP(%rdi)
+	retq
+	CFI_ENDPROC
+END(__do_double_fault)
+#else
+# define __do_double_fault do_double_fault
+#endif
+
 /*
  * End of kprobes section
  */
@@ -1289,7 +1362,7 @@ idtentry overflow do_overflow has_error_code=0
 idtentry bounds do_bounds has_error_code=0
 idtentry invalid_op do_invalid_op has_error_code=0
 idtentry device_not_available do_device_not_available has_error_code=0
-idtentry double_fault do_double_fault has_error_code=1 paranoid=1
+idtentry double_fault __do_double_fault has_error_code=1 paranoid=1
 idtentry coprocessor_segment_overrun do_coprocessor_segment_overrun has_error_code=0
 idtentry invalid_TSS do_invalid_TSS has_error_code=1
 idtentry segment_not_present do_segment_not_present has_error_code=1
@@ -1576,7 +1649,7 @@ error_sti:
  */
 error_kernelspace:
 	incl %ebx
-	leaq irq_return(%rip),%rcx
+	leaq irq_return_iret(%rip),%rcx
 	cmpq %rcx,RIP+8(%rsp)
 	je error_swapgs
 	movl %ecx,%eax	/* zero extend */