From 966d713e86db1916a0b45a324a935d009737316e Mon Sep 17 00:00:00 2001 From: Mahesh Salgaonkar Date: Mon, 23 Mar 2015 22:24:45 +0530 Subject: [PATCH] KVM: PPC: Book3S HV: Deliver machine check with MSR(RI=0) to guest as MCE For the machine check interrupt that happens while we are in the guest, kvm layer attempts the recovery, and then delivers the machine check interrupt directly to the guest if recovery fails. On successful recovery we go back to normal functioning of the guest. But there can be cases where a machine check interrupt can happen with MSR(RI=0) while we are in the guest. This means MC interrupt is unrecoverable and we have to deliver a machine check to the guest since the machine check interrupt might have trashed valid values in SRR0/1. The current implementation do not handle this case, causing guest to crash with Bad kernel stack pointer instead of machine check oops message. [26281.490060] Bad kernel stack pointer 3fff9ccce5b0 at c00000000000490c [26281.490434] Oops: Bad kernel stack pointer, sig: 6 [#1] [26281.490472] SMP NR_CPUS=2048 NUMA pSeries This patch fixes this issue by checking MSR(RI=0) in KVM layer and forwarding unrecoverable interrupt to guest which then panics with proper machine check Oops message. Signed-off-by: Mahesh Salgaonkar Acked-by: Paul Mackerras Signed-off-by: Paul Mackerras --- arch/powerpc/kvm/book3s_hv_rmhandlers.S | 12 ++++++++---- 1 file changed, 8 insertions(+), 4 deletions(-) diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S index b98889e9851d..fb8d29650612 100644 --- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S +++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S @@ -2377,7 +2377,6 @@ machine_check_realmode: mr r3, r9 /* get vcpu pointer */ bl kvmppc_realmode_machine_check nop - cmpdi r3, 0 /* Did we handle MCE ? */ ld r9, HSTATE_KVM_VCPU(r13) li r12, BOOK3S_INTERRUPT_MACHINE_CHECK /* @@ -2390,13 +2389,18 @@ machine_check_realmode: * The old code used to return to host for unhandled errors which * was causing guest to hang with soft lockups inside guest and * makes it difficult to recover guest instance. + * + * if we receive machine check with MSR(RI=0) then deliver it to + * guest as machine check causing guest to crash. */ - ld r10, VCPU_PC(r9) ld r11, VCPU_MSR(r9) + andi. r10, r11, MSR_RI /* check for unrecoverable exception */ + beq 1f /* Deliver a machine check to guest */ + ld r10, VCPU_PC(r9) + cmpdi r3, 0 /* Did we handle MCE ? */ bne 2f /* Continue guest execution. */ /* If not, deliver a machine check. SRR0/1 are already set */ - li r10, BOOK3S_INTERRUPT_MACHINE_CHECK - ld r11, VCPU_MSR(r9) +1: li r10, BOOK3S_INTERRUPT_MACHINE_CHECK bl kvmppc_msr_interrupt 2: b fast_interrupt_c_return