@@ -18,6 +18,7 @@
#include <linux/cma.h>
#include <linux/bitops.h>
+#include <asm/asm-prototypes.h>
#include <asm/cputable.h>
#include <asm/kvm_ppc.h>
#include <asm/kvm_book3s.h>
@@ -633,7 +634,19 @@ int kvmppc_rm_h_eoi(struct kvm_vcpu *vcpu, unsigned long xirr)
void kvmppc_bad_interrupt(struct pt_regs *regs)
{
- die("Bad interrupt in KVM entry/exit code", regs, SIGABRT);
+ /*
+ * 100 could happen at any time, 200 can happen due to invalid real
+ * address access for example (or any time due to a hardware problem).
+ */
+ if (TRAP(regs) == 0x100) {
+ get_paca()->in_nmi++;
+ system_reset_exception(regs);
+ get_paca()->in_nmi--;
+ } else if (TRAP(regs) == 0x200) {
+ machine_check_exception(regs);
+ } else {
+ die("Bad interrupt in KVM entry/exit code", regs, SIGABRT);
+ }
panic("Bad KVM trap");
}
It's possible to take a SRESET or MCE in these paths due to a bug in the host code or a NMI IPI, etc. A recent bug attempting to load a virtual address from real mode gave th complete but cryptic error, abridged: Oops: Bad interrupt in KVM entry/exit code, sig: 6 [#1] LE SMP NR_CPUS=2048 NUMA PowerNV CPU: 53 PID: 6582 Comm: qemu-system-ppc Not tainted NIP: c0000000000155ac LR: c0000000000c2430 CTR: c000000000015580 REGS: c000000fff76dd80 TRAP: 0200 Not tainted MSR: 9000000000201003 <SF,HV,ME,RI,LE> CR: 48082222 XER: 00000000 CFAR: 0000000102900ef0 DAR: d00017fffd941a28 DSISR: 00000040 SOFTE: 3 NIP [c0000000000155ac] perf_trace_tlbie+0x2c/0x1a0 LR [c0000000000c2430] do_tlbies+0x230/0x2f0 Sending the NMIs through the Linux handlers gives a nicer output: Severe Machine check interrupt [Not recovered] NIP [c0000000000155ac]: perf_trace_tlbie+0x2c/0x1a0 Initiator: CPU Error type: Real address [Load (bad)] Effective address: d00017fffcc01a28 opal: Machine check interrupt unrecoverable: MSR(RI=0) opal: Hardware platform error: Unrecoverable Machine Check exception CPU: 0 PID: 6700 Comm: qemu-system-ppc Tainted: G M NIP: c0000000000155ac LR: c0000000000c23c0 CTR: c000000000015580 REGS: c000000fff9e9d80 TRAP: 0200 Tainted: G M MSR: 9000000000201001 <SF,HV,ME,LE> CR: 48082222 XER: 00000000 CFAR: 000000010cbc1a30 DAR: d00017fffcc01a28 DSISR: 00000040 SOFTE: 3 NIP [c0000000000155ac] perf_trace_tlbie+0x2c/0x1a0 LR [c0000000000c23c0] do_tlbies+0x1c0/0x280 Signed-off-by: Nicholas Piggin <npiggin@gmail.com> --- Since RFC: - Do not clear MSR_RI bit by hand to prevent the Linux exception handlers returning. Catch that with the panic instead (in the case of the MCE in the changelog, it has the SRR1[RI] bit clear anyway, so no change). arch/powerpc/kvm/book3s_hv_builtin.c | 15 ++++++++++++++- 1 file changed, 14 insertions(+), 1 deletion(-)