x86/fred: Add a NMI entry stub for FRED

On a FRED system, NMIs nest both with themselves and faults, transient
information is saved into the stack frame, and NMI unblocking only
happens when the stack frame indicates that so should happen.

Thus, the NMI entry stub for FRED is really quite small...

Signed-off-by: H. Peter Anvin (Intel) <hpa@zytor.com>
Signed-off-by: Xin Li <xin3.li@intel.com>
Signed-off-by: Thomas Gleixner <tglx@linutronix.de>
Signed-off-by: Borislav Petkov (AMD) <bp@alien8.de>
Tested-by: Shan Kang <shan.kang@intel.com>
Link: https://lore.kernel.org/r/20231216063139.25567-1-xin3.li@intel.com

diff --git a/arch/x86/kernel/nmi.c b/arch/x86/kernel/nmi.c
index 17e955ab69feda933cca3708822f6f9f598e31bf..3130a66b0f48d026b32ce3aa7cd822bb95c32b75 100644 (file)
--- a/arch/x86/kernel/nmi.c
+++ b/arch/x86/kernel/nmi.c
@@ -35,6 +35,7 @@
 #include <asm/nospec-branch.h>
 #include <asm/microcode.h>
 #include <asm/sev.h>
+#include <asm/fred.h>
 
 #define CREATE_TRACE_POINTS
 #include <trace/events/nmi.h>
@@ -651,6 +652,47 @@ void nmi_backtrace_stall_check(const struct cpumask *btp)
 
 #endif
 
+#ifdef CONFIG_X86_FRED
+/*
+ * With FRED, CR2/DR6 is pushed to #PF/#DB stack frame during FRED
+ * event delivery, i.e., there is no problem of transient states.
+ * And NMI unblocking only happens when the stack frame indicates
+ * that so should happen.
+ *
+ * Thus, the NMI entry stub for FRED is really straightforward and
+ * as simple as most exception handlers. As such, #DB is allowed
+ * during NMI handling.
+ */
+DEFINE_FREDENTRY_NMI(exc_nmi)
+{
+       irqentry_state_t irq_state;
+
+       if (arch_cpu_is_offline(smp_processor_id())) {
+               if (microcode_nmi_handler_enabled())
+                       microcode_offline_nmi_handler();
+               return;
+       }
+
+       /*
+        * Save CR2 for eventual restore to cover the case where the NMI
+        * hits the VMENTER/VMEXIT region where guest CR2 is life. This
+        * prevents guest state corruption in case that the NMI handler
+        * takes a page fault.
+        */
+       this_cpu_write(nmi_cr2, read_cr2());
+
+       irq_state = irqentry_nmi_enter(regs);
+
+       inc_irq_stat(__nmi_count);
+       default_do_nmi(regs);
+
+       irqentry_nmi_exit(regs, irq_state);
+
+       if (unlikely(this_cpu_read(nmi_cr2) != read_cr2()))
+               write_cr2(this_cpu_read(nmi_cr2));
+}
+#endif
+
 void stop_nmi(void)
 {
        ignore_nmis++;