[PATCH 1/3] x86: Create and use a TOP_OF_KERNEL_STACK_PADDING macro

[Andy Lutomirski <luto@amacapital.net>]

x86_32, unlike x86_64, pads the top of the kernel stack.  Document
this padding and give it a name.

This should make no change whatsoever to the compiled kernel image.
It also doesn't fix any of the current bugs in this area.

Signed-off-by: Andy Lutomirski <luto@amacapital.net>
---
 arch/x86/include/asm/processor.h   |  3 ++-
 arch/x86/include/asm/thread_info.h | 30 ++++++++++++++++++++++++++++++
 2 files changed, 32 insertions(+), 1 deletion(-)

diff --git a/arch/x86/include/asm/processor.h b/arch/x86/include/asm/processor.h
index 48a61c1c626e..88d9aa745898 100644
--- a/arch/x86/include/asm/processor.h
+++ b/arch/x86/include/asm/processor.h
@@ -849,7 +849,8 @@ extern unsigned long thread_saved_pc(struct task_struct *tsk);
 #define task_pt_regs(task)                                             \
 ({                                                                     \
        struct pt_regs *__regs__;                                       \
-       __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task))-8); \
+       __regs__ = (struct pt_regs *)(KSTK_TOP(task_stack_page(task)) - \
+				     TOP_OF_KERNEL_STACK_PADDING);     \
        __regs__ - 1;                                                   \
 })
 
diff --git a/arch/x86/include/asm/thread_info.h b/arch/x86/include/asm/thread_info.h
index 7740edd56fed..74fd74ca50d3 100644
--- a/arch/x86/include/asm/thread_info.h
+++ b/arch/x86/include/asm/thread_info.h
@@ -49,6 +49,36 @@ struct thread_info {
 #define init_thread_info	(init_thread_union.thread_info)
 #define init_stack		(init_thread_union.stack)
 
+#ifdef CONFIG_X86_32
+
+/*
+ * TOP_OF_KERNEL_STACK_PADDING is a number of unused bytes that we
+ * reserve at the top of the kernel stack.  We do it because of a nasty
+ * 32-bit corner case.  On x86_32, the hardware stack frame is
+ * variable-length.  Except for vm86 mode, struct pt_regs assumes a
+ * maximum-length frame.  If we enter from CPL 0, the top 8 bytes of
+ * pt_regs don't actually exist.  Ordinarily this doesn't matter, but it
+ * does in at least one case:
+ *
+ * If we take an NMI early enough in sysenter, the we can end up with
+ * pt_regs that extends above sp0.  On the way out, in the espfix code,
+ * we can read the saved SS value, but that value will be above sp0.
+ * Without this offset, that can result in a page fault.  (We are
+ * careful that, in this case, the value we read doesn't matter.)
+ *
+ * In vm86 mode, the hardware frame is much longer still, but we neither
+ * access the extra members from NMI context, nor do we write such a
+ * frame at sp0 at all.
+ */
+#define TOP_OF_KERNEL_STACK_PADDING 8
+
+#else
+
+/* Phew, x86_64 has a fixed-length stack frame! */
+#define TOP_OF_KERNEL_STACK_PADDING 0
+
+#endif
+
 #else /* !__ASSEMBLY__ */
 
 #include <asm/asm-offsets.h>
-- 
2.3.0