summaryrefslogtreecommitdiff
path: root/arch/powerpc/kvm/book3s_hv_ras.c
diff options
context:
space:
mode:
authorPaul Mackerras <paulus@ozlabs.org>2019-02-21 05:38:49 +0300
committerMichael Ellerman <mpe@ellerman.id.au>2019-02-21 15:16:44 +0300
commit884dfb722db899e36d8c382783347aab57f96caa (patch)
tree22220c664d3d299fbb81ef86ba85e4ab4e9b4d1c /arch/powerpc/kvm/book3s_hv_ras.c
parentd976f6807ea613c54fcb74bd7ae68a43fdd62e1f (diff)
downloadlinux-884dfb722db899e36d8c382783347aab57f96caa.tar.xz
KVM: PPC: Book3S HV: Simplify machine check handling
This makes the handling of machine check interrupts that occur inside a guest simpler and more robust, with less done in assembler code and in real mode. Now, when a machine check occurs inside a guest, we always get the machine check event struct and put a copy in the vcpu struct for the vcpu where the machine check occurred. We no longer call machine_check_queue_event() from kvmppc_realmode_mc_power7(), because on POWER8, when a vcpu is running on an offline secondary thread and we call machine_check_queue_event(), that calls irq_work_queue(), which doesn't work because the CPU is offline, but instead triggers the WARN_ON(lazy_irq_pending()) in pnv_smp_cpu_kill_self() (which fires again and again because nothing clears the condition). All that machine_check_queue_event() actually does is to cause the event to be printed to the console. For a machine check occurring in the guest, we now print the event in kvmppc_handle_exit_hv() instead. The assembly code at label machine_check_realmode now just calls C code and then continues exiting the guest. We no longer either synthesize a machine check for the guest in assembly code or return to the guest without a machine check. The code in kvmppc_handle_exit_hv() is extended to handle the case where the guest is not FWNMI-capable. In that case we now always synthesize a machine check interrupt for the guest. Previously, if the host thinks it has recovered the machine check fully, it would return to the guest without any notification that the machine check had occurred. If the machine check was caused by some action of the guest (such as creating duplicate SLB entries), it is much better to tell the guest that it has caused a problem. Therefore we now always generate a machine check interrupt for guests that are not FWNMI-capable. Reviewed-by: Aravinda Prasad <aravinda@linux.vnet.ibm.com> Reviewed-by: Mahesh Salgaonkar <mahesh@linux.vnet.ibm.com> Signed-off-by: Paul Mackerras <paulus@ozlabs.org> Signed-off-by: Michael Ellerman <mpe@ellerman.id.au>
Diffstat (limited to 'arch/powerpc/kvm/book3s_hv_ras.c')
-rw-r--r--arch/powerpc/kvm/book3s_hv_ras.c58
1 files changed, 14 insertions, 44 deletions
diff --git a/arch/powerpc/kvm/book3s_hv_ras.c b/arch/powerpc/kvm/book3s_hv_ras.c
index 0787f12c1a1b..8c24c3bea0bf 100644
--- a/arch/powerpc/kvm/book3s_hv_ras.c
+++ b/arch/powerpc/kvm/book3s_hv_ras.c
@@ -66,10 +66,8 @@ static void reload_slb(struct kvm_vcpu *vcpu)
/*
* On POWER7, see if we can handle a machine check that occurred inside
* the guest in real mode, without switching to the host partition.
- *
- * Returns: 0 => exit guest, 1 => deliver machine check to guest
*/
-static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
+static void kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
{
unsigned long srr1 = vcpu->arch.shregs.msr;
struct machine_check_event mce_evt;
@@ -111,52 +109,24 @@ static long kvmppc_realmode_mc_power7(struct kvm_vcpu *vcpu)
}
/*
- * See if we have already handled the condition in the linux host.
- * We assume that if the condition is recovered then linux host
- * will have generated an error log event that we will pick
- * up and log later.
- * Don't release mce event now. We will queue up the event so that
- * we can log the MCE event info on host console.
+ * Now get the event and stash it in the vcpu struct so it can
+ * be handled by the primary thread in virtual mode. We can't
+ * call machine_check_queue_event() here if we are running on
+ * an offline secondary thread.
*/
- if (!get_mce_event(&mce_evt, MCE_EVENT_DONTRELEASE))
- goto out;
-
- if (mce_evt.version == MCE_V1 &&
- (mce_evt.severity == MCE_SEV_NO_ERROR ||
- mce_evt.disposition == MCE_DISPOSITION_RECOVERED))
- handled = 1;
-
-out:
- /*
- * For guest that supports FWNMI capability, hook the MCE event into
- * vcpu structure. We are going to exit the guest with KVM_EXIT_NMI
- * exit reason. On our way to exit we will pull this event from vcpu
- * structure and print it from thread 0 of the core/subcore.
- *
- * For guest that does not support FWNMI capability (old QEMU):
- * We are now going enter guest either through machine check
- * interrupt (for unhandled errors) or will continue from
- * current HSRR0 (for handled errors) in guest. Hence
- * queue up the event so that we can log it from host console later.
- */
- if (vcpu->kvm->arch.fwnmi_enabled) {
- /*
- * Hook up the mce event on to vcpu structure.
- * First clear the old event.
- */
- memset(&vcpu->arch.mce_evt, 0, sizeof(vcpu->arch.mce_evt));
- if (get_mce_event(&mce_evt, MCE_EVENT_RELEASE)) {
- vcpu->arch.mce_evt = mce_evt;
- }
- } else
- machine_check_queue_event();
+ if (get_mce_event(&mce_evt, MCE_EVENT_RELEASE)) {
+ if (handled && mce_evt.version == MCE_V1)
+ mce_evt.disposition = MCE_DISPOSITION_RECOVERED;
+ } else {
+ memset(&mce_evt, 0, sizeof(mce_evt));
+ }
- return handled;
+ vcpu->arch.mce_evt = mce_evt;
}
-long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
+void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu)
{
- return kvmppc_realmode_mc_power7(vcpu);
+ kvmppc_realmode_mc_power7(vcpu);
}
/* Check if dynamic split is in force and return subcore size accordingly. */