x86-64, espfix: Don't leak bits 31:16 of %esp returning to 16-bit stack

The IRET instruction, when returning to a 16-bit segment, only
restores the bottom 16 bits of the user space stack pointer.  This
causes some 16-bit software to break, but it also leaks kernel state
to user space.  We have a software workaround for that ("espfix") for
the 32-bit kernel, but it relies on a nonzero stack segment base which
is not available in 64-bit mode.

In checkin:

    b3b42ac2cbae x86-64, modify_ldt: Ban 16-bit segments on 64-bit kernels

we "solved" this by forbidding 16-bit segments on 64-bit kernels, with
the logic that 16-bit support is crippled on 64-bit kernels anyway (no
V86 support), but it turns out that people are doing stuff like
running old Win16 binaries under Wine and expect it to work.

This works around this by creating percpu "ministacks", each of which
is mapped 2^16 times 64K apart.  When we detect that the return SS is
on the LDT, we copy the IRET frame to the ministack and use the
relevant alias to return to userspace.  The ministacks are mapped
readonly, so if IRET faults we promote #GP to #DF which is an IST
vector and thus has its own stack; we then do the fixup in the #DF
handler.

(Making #GP an IST exception would make the msr_safe functions unsafe
in NMI/MC context, and quite possibly have other effects.)

Special thanks to:

- Andy Lutomirski, for the suggestion of using very small stack slots
  and copy (as opposed to map) the IRET frame there, and for the
  suggestion to mark them readonly and let the fault promote to #DF.
- Konrad Wilk for paravirt fixup and testing.
- Borislav Petkov for testing help and useful comments.

Reported-by: Brian Gerst <brgerst@gmail.com>
Signed-off-by: H. Peter Anvin <hpa@linux.intel.com>
Link: http://lkml.kernel.org/r/1398816946-3351-1-git-send-email-hpa@linux.intel.com
Cc: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Andrew Lutomriski <amluto@gmail.com>
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Dirk Hohndel <dirk@hohndel.org>
Cc: Arjan van de Ven <arjan.van.de.ven@intel.com>
Cc: comex <comexk@gmail.com>
Cc: Alexander van Heukelum <heukelum@fastmail.fm>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: <stable@vger.kernel.org> # consider after upstream merge

1 files changed, 69 insertions, 4 deletions

diff --git a/arch/x86/kernel/entry_64.S b/arch/x86/kernel/entry_64.S
index 1e96c36..bffaa98 100644
--- a/arch/x86/kernel/entry_64.S
+++ b/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.  */
@@ -1040,8 +1041,16 @@ 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.
+	 */
+	testb $4,(SS-RIP)(%rsp)
+	jnz irq_return_ldt
+
+irq_return_iret:
 	INTERRUPT_RETURN
-	_ASM_EXTABLE(irq_return, bad_iret)
+	_ASM_EXTABLE(irq_return_iret, bad_iret)
 
 #ifdef CONFIG_PARAVIRT
 ENTRY(native_iret)
@@ -1049,6 +1058,30 @@ ENTRY(native_iret)
 	_ASM_EXTABLE(native_iret, bad_iret)
 #endif
 
+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
+
 	.section .fixup,"ax"
 bad_iret:
 	/*
@@ -1110,9 +1143,41 @@ 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.
+	 */
+	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)
+
 /*
  * End of kprobes section
  */
@@ -1314,7 +1379,7 @@ zeroentry overflow do_overflow
 zeroentry bounds do_bounds
 zeroentry invalid_op do_invalid_op
 zeroentry device_not_available do_device_not_available
-paranoiderrorentry double_fault do_double_fault
+paranoiderrorentry double_fault __do_double_fault
 zeroentry coprocessor_segment_overrun do_coprocessor_segment_overrun
 errorentry invalid_TSS do_invalid_TSS
 errorentry segment_not_present do_segment_not_present
@@ -1601,7 +1666,7 @@ 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 */