target/ppc: Handle NMI guest exit

Memory error such as bit flips that cannot be corrected
by hardware are passed on to the kernel for handling.
If the memory address in error belongs to guest then
the guest kernel is responsible for taking suitable action.
Patch [1] enhances KVM to exit guest with exit reason
set to KVM_EXIT_NMI in such cases. This patch handles
KVM_EXIT_NMI exit.

[1] https://www.spinics.net/lists/kvm-ppc/msg12637.html
    (e20bbd3d and related commits)

Signed-off-by: Aravinda Prasad <arawinda.p@gmail.com>
Signed-off-by: Ganesh Goudar <ganeshgr@linux.ibm.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Reviewed-by: Greg Kurz <groug@kaod.org>
Message-Id: <20200130184423.20519-4-ganeshgr@linux.ibm.com>
[dwg: #ifdefs to fix compile for 32-bit target]
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

diff --git a/hw/ppc/spapr.c b/hw/ppc/spapr.c
index aa739e943ff8cf5823c9f11c506e2b21270dd7e3..06e295cdf129acf4b56ef39a32e201b4f29e9dec 100644 (file)
--- a/hw/ppc/spapr.c
+++ b/hw/ppc/spapr.c
@@ -1677,6 +1677,12 @@ static void spapr_machine_reset(MachineState *machine)
     first_ppc_cpu->env.gpr[5] = 0;
 
     spapr->cas_reboot = false;
+
+    spapr->mc_status = -1;
+    spapr->guest_machine_check_addr = -1;
+
+    /* Signal all vCPUs waiting on this condition */
+    qemu_cond_broadcast(&spapr->mc_delivery_cond);
 }
 
 static void spapr_create_nvram(SpaprMachineState *spapr)
@@ -2971,6 +2977,8 @@ static void spapr_machine_init(MachineState *machine)
 
         kvmppc_spapr_enable_inkernel_multitce();
     }
+
+    qemu_cond_init(&spapr->mc_delivery_cond);
 }
 
 static int spapr_kvm_type(MachineState *machine, const char *vm_type)

diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
index e355e000d07698dea8b36bef8f102e589c47c5d1..dfc0de840a508b20c5bcfac640affa1d27c23fa8 100644 (file)
--- a/hw/ppc/spapr_events.c
+++ b/hw/ppc/spapr_events.c
@@ -40,6 +40,7 @@
 #include "hw/ppc/spapr_drc.h"
 #include "qemu/help_option.h"
 #include "qemu/bcd.h"
+#include "qemu/main-loop.h"
 #include "hw/ppc/spapr_ovec.h"
 #include <libfdt.h>
 
@@ -622,6 +623,42 @@ void spapr_hotplug_req_remove_by_count_indexed(SpaprDrcType drc_type,
                             RTAS_LOG_V6_HP_ACTION_REMOVE, drc_type, &drc_id);
 }
 
+void spapr_mce_req_event(PowerPCCPU *cpu)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+    CPUState *cs = CPU(cpu);
+
+    if (spapr->guest_machine_check_addr == -1) {
+        /*
+         * This implies that we have hit a machine check either when the
+         * guest has not registered FWNMI (i.e., "ibm,nmi-register" not
+         * called) or between system reset and "ibm,nmi-register".
+         * Fall back to the old machine check behavior in such cases.
+         */
+        cs->exception_index = POWERPC_EXCP_MCHECK;
+        ppc_cpu_do_interrupt(cs);
+        return;
+    }
+
+    while (spapr->mc_status != -1) {
+        /*
+         * Check whether the same CPU got machine check error
+         * while still handling the mc error (i.e., before
+         * that CPU called "ibm,nmi-interlock")
+         */
+        if (spapr->mc_status == cpu->vcpu_id) {
+            qemu_system_guest_panicked(NULL);
+            return;
+        }
+        qemu_cond_wait_iothread(&spapr->mc_delivery_cond);
+        /* Meanwhile if the system is reset, then just return */
+        if (spapr->guest_machine_check_addr == -1) {
+            return;
+        }
+    }
+    spapr->mc_status = cpu->vcpu_id;
+}
+
 static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,
                             uint32_t token, uint32_t nargs,
                             target_ulong args,

diff --git a/include/hw/ppc/spapr.h b/include/hw/ppc/spapr.h
index 7bc5fc3a9e5d4cb44ceec530652b9f42a6529fcf..909d3976f9d95448047a536fd332c27bbab95b64 100644 (file)
--- a/include/hw/ppc/spapr.h
+++ b/include/hw/ppc/spapr.h
@@ -191,6 +191,15 @@ struct SpaprMachineState {
      * occurs during the unplug process. */
     QTAILQ_HEAD(, SpaprDimmState) pending_dimm_unplugs;
 
+    /* State related to "ibm,nmi-register" and "ibm,nmi-interlock" calls */
+    target_ulong guest_machine_check_addr;
+    /*
+     * mc_status is set to -1 if mc is not in progress, else is set to the CPU
+     * handling the mc.
+     */
+    int mc_status;
+    QemuCond mc_delivery_cond;
+
     /*< public >*/
     char *kvm_type;
     char *host_model;
@@ -804,6 +813,7 @@ void spapr_clear_pending_events(SpaprMachineState *spapr);
 int spapr_max_server_number(SpaprMachineState *spapr);
 void spapr_store_hpte(PowerPCCPU *cpu, hwaddr ptex,
                       uint64_t pte0, uint64_t pte1);
+void spapr_mce_req_event(PowerPCCPU *cpu);
 
 /* DRC callbacks. */
 void spapr_core_release(DeviceState *dev);

diff --git a/target/ppc/kvm.c b/target/ppc/kvm.c
index 4438d0c7435c23f6a0c0040dc1883c7118aff4d2..56a6865521a1330fb7fc49da4f086e8354babffa 100644 (file)
--- a/target/ppc/kvm.c
+++ b/target/ppc/kvm.c
@@ -1705,6 +1705,13 @@ int kvm_arch_handle_exit(CPUState *cs, struct kvm_run *run)
         ret = 0;
         break;
 
+#if defined(TARGET_PPC64)
+    case KVM_EXIT_NMI:
+        trace_kvm_handle_nmi_exception();
+        ret = kvm_handle_nmi(cpu, run);
+        break;
+#endif
+
     default:
         fprintf(stderr, "KVM: unknown exit reason %d\n", run->exit_reason);
         ret = -1;
@@ -2800,6 +2807,17 @@ int kvm_arch_msi_data_to_gsi(uint32_t data)
     return data & 0xffff;
 }
 
+#if defined(TARGET_PPC64)
+int kvm_handle_nmi(PowerPCCPU *cpu, struct kvm_run *run)
+{
+    cpu_synchronize_state(CPU(cpu));
+
+    spapr_mce_req_event(cpu);
+
+    return 0;
+}
+#endif
+
 int kvmppc_enable_hwrng(void)
 {
     if (!kvm_enabled() || !kvm_check_extension(kvm_state, KVM_CAP_PPC_HWRNG)) {

diff --git a/target/ppc/kvm_ppc.h b/target/ppc/kvm_ppc.h
index 2c60dedd0df15a2e6caf64e0e6a42cd1fb45a417..9e4f2357ccf024061c68021bf27046220c18d20f 100644 (file)
--- a/target/ppc/kvm_ppc.h
+++ b/target/ppc/kvm_ppc.h
@@ -84,6 +84,8 @@ void kvm_check_mmu(PowerPCCPU *cpu, Error **errp);
 void kvmppc_set_reg_ppc_online(PowerPCCPU *cpu, unsigned int online);
 void kvmppc_set_reg_tb_offset(PowerPCCPU *cpu, int64_t tb_offset);
 
+int kvm_handle_nmi(PowerPCCPU *cpu, struct kvm_run *run);
+
 #else
 
 static inline uint32_t kvmppc_get_tbfreq(void)

diff --git a/target/ppc/trace-events b/target/ppc/trace-events
index 3dc674070689e3be36cf1ccb0bba7924ffc3d4fc..6d15aa90b4f6fd153ce4e87fb38ec37397d88bc4 100644 (file)
--- a/target/ppc/trace-events
+++ b/target/ppc/trace-events
@@ -28,3 +28,4 @@ kvm_handle_papr_hcall(void) "handle PAPR hypercall"
 kvm_handle_epr(void) "handle epr"
 kvm_handle_watchdog_expiry(void) "handle watchdog expiry"
 kvm_handle_debug_exception(void) "handle debug exception"
+kvm_handle_nmi_exception(void) "handle NMI exception"