x86/entry/32: Add PTI CR3 switches to NMI handler code

The NMI handler is special, as it needs to leave with the same CR3 as it
was entered with. This is required because the NMI can happen within kernel
context but with user CR3 already loaded, i.e. after switching to user CR3
but before returning to user space.

Signed-off-by: Joerg Roedel <jroedel@suse.de>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Tested-by: Pavel Machek <pavel@ucw.cz>
Cc: "H . Peter Anvin" <hpa@zytor.com>
Cc: linux-mm@kvack.org
Cc: Linus Torvalds <torvalds@linux-foundation.org>
Cc: Andy Lutomirski <luto@kernel.org>
Cc: Dave Hansen <dave.hansen@intel.com>
Cc: Josh Poimboeuf <jpoimboe@redhat.com>
Cc: Juergen Gross <jgross@suse.com>
Cc: Peter Zijlstra <peterz@infradead.org>
Cc: Borislav Petkov <bp@alien8.de>
Cc: Jiri Kosina <jkosina@suse.cz>
Cc: Boris Ostrovsky <boris.ostrovsky@oracle.com>
Cc: Brian Gerst <brgerst@gmail.com>
Cc: David Laight <David.Laight@aculab.com>
Cc: Denys Vlasenko <dvlasenk@redhat.com>
Cc: Eduardo Valentin <eduval@amazon.com>
Cc: Greg KH <gregkh@linuxfoundation.org>
Cc: Will Deacon <will.deacon@arm.com>
Cc: aliguori@amazon.com
Cc: daniel.gruss@iaik.tugraz.at
Cc: hughd@google.com
Cc: keescook@google.com
Cc: Andrea Arcangeli <aarcange@redhat.com>
Cc: Waiman Long <llong@redhat.com>
Cc: "David H . Gutteridge" <dhgutteridge@sympatico.ca>
Cc: joro@8bytes.org
Link: https://lkml.kernel.org/r/1531906876-13451-14-git-send-email-joro@8bytes.org

arch/x86/entry/entry_32.S

@@ -210,8 +210,19 @@
 
 .endm
 
-.macro SAVE_ALL_NMI
+.macro SAVE_ALL_NMI cr3_reg:req
 	SAVE_ALL
+
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We can enter with either user or kernel cr3, the code will
+	 * store the old cr3 in \cr3_reg and switches to the kernel cr3
+	 * if necessary.
+	 */
+	SWITCH_TO_KERNEL_CR3 scratch_reg=\cr3_reg
+
+.Lend_\@:
 .endm
 /*
  * This is a sneaky trick to help the unwinder find pt_regs on the stack.  The
@@ -259,7 +270,23 @@
 	POP_GS_EX
 .endm
 
-.macro RESTORE_ALL_NMI pop=0
+.macro RESTORE_ALL_NMI cr3_reg:req pop=0
+	/*
+	 * Now switch the CR3 when PTI is enabled.
+	 *
+	 * We enter with kernel cr3 and switch the cr3 to the value
+	 * stored on \cr3_reg, which is either a user or a kernel cr3.
+	 */
+	ALTERNATIVE "jmp .Lswitched_\@", "", X86_FEATURE_PTI
+
+	testl	$PTI_SWITCH_MASK, \cr3_reg
+	jz	.Lswitched_\@
+
+	/* User cr3 in \cr3_reg - write it to hardware cr3 */
+	movl	\cr3_reg, %cr3
+
+.Lswitched_\@:
+
 	RESTORE_REGS pop=\pop
 .endm
 
@@ -1331,7 +1358,7 @@ ENTRY(nmi)
 #endif
 
 	pushl	%eax				# pt_regs->orig_ax
-	SAVE_ALL_NMI
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	xorl	%edx, %edx			# zero error code
 	movl	%esp, %eax			# pt_regs pointer
@@ -1359,7 +1386,7 @@ ENTRY(nmi)
 
 .Lnmi_return:
 	CHECK_AND_APPLY_ESPFIX
-	RESTORE_ALL_NMI pop=4
+	RESTORE_ALL_NMI cr3_reg=%edi pop=4
 	jmp	.Lirq_return
 
 #ifdef CONFIG_X86_ESPFIX32
@@ -1375,12 +1402,12 @@ ENTRY(nmi)
 	pushl	16(%esp)
 	.endr
 	pushl	%eax
-	SAVE_ALL_NMI
+	SAVE_ALL_NMI cr3_reg=%edi
 	ENCODE_FRAME_POINTER
 	FIXUP_ESPFIX_STACK			# %eax == %esp
 	xorl	%edx, %edx			# zero error code
 	call	do_nmi
-	RESTORE_ALL_NMI
+	RESTORE_ALL_NMI cr3_reg=%edi
 	lss	12+4(%esp), %esp		# back to espfix stack
 	jmp	.Lirq_return
 #endif