x86: Ignore NMIs that come in during early boot

Don Zickus reports:

A customer generated an external NMI using their iLO to test kdump
worked.  Unfortunately, the machine hung.  Disabling the nmi_watchdog
made things work.

I speculated the external NMI fired, caused the machine to panic (as
expected) and the perf NMI from the watchdog came in and was latched.
My guess was this somehow caused the hang.

   ----

It appears that the latched NMI stays latched until the early page
table generation on 64 bits, which causes exceptions to happen which
end in IRET, which re-enable NMI.  Therefore, ignore NMIs that come in
during early execution, until we have proper exception handling.

Reported-and-tested-by: Don Zickus <[email protected]>
Link: http://lkml.kernel.org/r/[email protected]
Signed-off-by: H. Peter Anvin <[email protected]>
Cc: <[email protected]> # v3.5+, older with some backport effort

arch/x86/kernel/head_32.S

@@ -544,6 +544,10 @@ ENDPROC(early_idt_handlers)
 	/* This is global to keep gas from relaxing the jumps */
 ENTRY(early_idt_handler)
 	cld
+
+	cmpl $X86_TRAP_NMI,(%esp)
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,%ss:early_recursion_flag
 	je hlt_loop
 	incl %ss:early_recursion_flag
@@ -594,8 +598,9 @@ ex_entry:
 	pop %edx
 	pop %ecx
 	pop %eax
-	addl $8,%esp		/* drop vector number and error code */
 	decl %ss:early_recursion_flag
+is_nmi:
+	addl $8,%esp		/* drop vector number and error code */
 	iret
 ENDPROC(early_idt_handler)
 

arch/x86/kernel/head_64.S

@@ -343,6 +343,9 @@ early_idt_handlers:
 ENTRY(early_idt_handler)
 	cld
 
+	cmpl $X86_TRAP_NMI,(%rsp)
+	je is_nmi		# Ignore NMI
+
 	cmpl $2,early_recursion_flag(%rip)
 	jz  1f
 	incl early_recursion_flag(%rip)
@@ -405,8 +408,9 @@ ENTRY(early_idt_handler)
 	popq %rdx
 	popq %rcx
 	popq %rax
-	addq $16,%rsp		# drop vector number and error code
 	decl early_recursion_flag(%rip)
+is_nmi:
+	addq $16,%rsp		# drop vector number and error code
 	INTERRUPT_RETURN
 ENDPROC(early_idt_handler)