x86/entry: Add some paranoid entry/exit CR3 handling comments

Andi Kleen was just asking me about the NMI CR3 handling and why
we restore it unconditionally.  I was *sure* we had documented it
well.  We did not.

Add some documentation.  We have common entry code where the CR3
value is stashed, but three places in two big code paths where we
restore it.  I put bulk of the comments in this common path and
then refer to it from the other spots.

Signed-off-by: Dave Hansen <dave.hansen@linux.intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Cc: luto@kernel.org
Cc: bp@alien8.de
Cc: "H. Peter Anvin" <hpa@zytor.come
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Borislav Petkov <bp@alien8.de>
Link: https://lkml.kernel.org/r/20181012232118.3EAAE77B@viggo.jf.intel.com

diff --git a/arch/x86/entry/entry_64.S b/arch/x86/entry/entry_64.S
index 957dfb693eccd5152700ec87ab3811b8cfb93e56..1d9b4a300c8ceda8970fed215a8bb55e46af6de7 100644 (file)
--- a/arch/x86/entry/entry_64.S
+++ b/arch/x86/entry/entry_64.S
@@ -1187,6 +1187,18 @@ ENTRY(paranoid_entry)
        xorl    %ebx, %ebx
 
 1:
+       /*
+        * Always stash CR3 in %r14.  This value will be restored,
+        * verbatim, at exit.  Needed if kernel is interrupted
+        * after switching to the user CR3 value but before
+        * returning to userspace.
+        *
+        * This is also why CS (stashed in the "iret frame" by the
+        * hardware at entry) can not be used: this may be a return
+        * to kernel code, but with a user CR3 value.  The %ebx flag
+        * for SWAPGS is also unusable for CR3 because there is a
+        * window with a user GS and a kernel CR3.
+        */
        SAVE_AND_SWITCH_TO_KERNEL_CR3 scratch_reg=%rax save_reg=%r14
 
        ret
@@ -1211,11 +1223,13 @@ ENTRY(paranoid_exit)
        testl   %ebx, %ebx                      /* swapgs needed? */
        jnz     .Lparanoid_exit_no_swapgs
        TRACE_IRQS_IRETQ
+       /* Always restore stashed CR3 value (see paranoid_entry) */
        RESTORE_CR3     scratch_reg=%rbx save_reg=%r14
        SWAPGS_UNSAFE_STACK
        jmp     .Lparanoid_exit_restore
 .Lparanoid_exit_no_swapgs:
        TRACE_IRQS_IRETQ_DEBUG
+       /* Always restore stashed CR3 value (see paranoid_entry) */
        RESTORE_CR3     scratch_reg=%rbx save_reg=%r14
 .Lparanoid_exit_restore:
        jmp restore_regs_and_return_to_kernel
@@ -1626,6 +1640,7 @@ end_repeat_nmi:
        movq    $-1, %rsi
        call    do_nmi
 
+       /* Always restore stashed CR3 value (see paranoid_entry) */
        RESTORE_CR3 scratch_reg=%r15 save_reg=%r14
 
        testl   %ebx, %ebx                      /* swapgs needed? */