[PATCH 09/31] x86/entry/32: Leave the kernel via trampoline stack

[Joerg Roedel]

From: Joerg Roedel <jroedel@xxxxxxx>

Switch back to the trampoline stack before returning to
userspace.

Signed-off-by: Joerg Roedel <jroedel@xxxxxxx>
---
 arch/x86/entry/entry_32.S | 55 +++++++++++++++++++++++++++++++++++++++++++++++
 1 file changed, 55 insertions(+)

diff --git a/arch/x86/entry/entry_32.S b/arch/x86/entry/entry_32.S
index e714b53..ba3d8c2 100644
--- a/arch/x86/entry/entry_32.S
+++ b/arch/x86/entry/entry_32.S
@@ -338,6 +338,59 @@
 .endm
 
 /*
+ * Switch back from the kernel stack to the entry stack.
+ *
+ * The %esp register must point to pt_regs on the task stack. It will
+ * first calculate the size of the stack-frame to copy, depending on
+ * whether we return to VM86 mode or not. With that it uses 'rep movsb'
+ * to copy the contents of the stack over to the entry stack.
+ *
+ * We must be very careful here, as we can't trust the contents of the
+ * task-stack once we switched to the entry-stack. When an NMI happens
+ * while on the entry-stack, the NMI handler will switch back to the top
+ * of the task stack, overwriting our stack-frame we are about to copy.
+ * Therefore we switch the stack only after everything is copied over.
+ */
+.macro SWITCH_TO_ENTRY_STACK
+
+	ALTERNATIVE     "", "jmp .Lend_\@", X86_FEATURE_XENPV
+
+	/* Bytes to copy */
+	movl	$PTREGS_SIZE, %ecx
+
+#ifdef CONFIG_VM86
+	testl	$(X86_EFLAGS_VM), PT_EFLAGS(%esp)
+	jz	.Lcopy_pt_regs_\@
+
+	/* Additional 4 registers to copy when returning to VM86 mode */
+	addl    $(4 * 4), %ecx
+
+.Lcopy_pt_regs_\@:
+#endif
+
+	/* Initialize source and destination for movsb */
+	movl	PER_CPU_VAR(cpu_tss_rw + TSS_sp0), %edi
+	subl	%ecx, %edi
+	movl	%esp, %esi
+
+	/* Save future stack pointer in %ebx */
+	movl %edi, %ebx
+
+	/* Copy over the stack-frame */
+	cld
+	rep movsb
+
+	/*
+	 * Switch to entry-stack - needs to happen after everything is
+	 * copied because the NMI handler will overwrite the task-stack
+	 * when on entry-stack
+	 */
+	movl	%ebx, %esp
+
+.Lend_\@:
+.endm
+
+/*
  * %eax: prev task
  * %edx: next task
  */
@@ -578,6 +631,7 @@ ENTRY(entry_SYSENTER_32)
 
 /* Opportunistic SYSEXIT */
 	TRACE_IRQS_ON			/* User mode traces as IRQs on. */
+	SWITCH_TO_ENTRY_STACK		/* Switch to per-cpu entry stack */
 	movl	PT_EIP(%esp), %edx	/* pt_regs->ip */
 	movl	PT_OLDESP(%esp), %ecx	/* pt_regs->sp */
 1:	mov	PT_FS(%esp), %fs
@@ -665,6 +719,7 @@ ENTRY(entry_INT80_32)
 
 restore_all:
 	TRACE_IRQS_IRET
+	SWITCH_TO_ENTRY_STACK
 .Lrestore_all_notrace:
 	CHECK_AND_APPLY_ESPFIX
 .Lrestore_nocheck:
-- 
2.7.4