Re: rng padlock changes causes NetBSD to crash

[Thor Lancelot Simon <tls%panix.com@localhost>]

On Wed, Feb 15, 2017 at 10:25:36AM +0200, Andrius V wrote:
> 
> Crash looks like this:
> 
> cpu_rng: VIA
> fatal privileged instruction fault in supervisor mode
> trap type 0 code 0 eip c0132377 cs 8 eflags 10046 cr2 0 ilevel 8 esp 80050033
> curlwp 0xc12427e0 pid 0 lid 1 lowest kstack 0xc14d82c0
> kernel: supervisor trap privileged instruction fault, code=0
> Stopped in pid 0.1 (system) at netbsd:cpu_rng+0x4a: xstore-rng.

Jonathan Kollasch found the bug: cpu_rng is called before the FPU
detection code, which would normally enable SSE.  SSE must be enabled
the PadLock instructions to actually work, regardless of what the MSR
values say.

Can you test the following patch, before I commit it?


Index: identcpu.c
===================================================================
RCS file: /cvsroot/src/sys/arch/x86/x86/identcpu.c,v
retrieving revision 1.52
diff -u -p -r1.52 identcpu.c
--- identcpu.c	2 Feb 2017 08:57:04 -0000	1.52
+++ identcpu.c	15 Feb 2017 16:32:15 -0000
@@ -551,7 +551,20 @@ cpu_probe_c3(struct cpu_info *ci)
 			}
 		    }
 
-		    /* Actually do the enables. */
+		    /*
+		     * Actually do the enables.  It's a little gross,
+		     * but per the PadLock programming guide, "Enabling
+		     * PadLock", condition 3, we must enable SSE too or
+		     * else the first use of RNG or ACE instructions
+		     * will generate a trap.
+		     *
+		     * We must do this early because of kernel RNG
+		     * initialization but it is safe without the full
+		     * FPU-detect as all these CPUs have SSE.
+		     */
+		    if (cpu_feature[0] & CPUID_FXSR)
+			lcr4(rcr4() | CR4_OSFXSR);
+
 		    if (rng_enable) {
 			msr = rdmsr(MSR_VIA_RNG);
 			msr |= MSR_VIA_RNG_ENABLE;