8 files changed, 71 insertions, 100 deletions

diff --git a/arch/powerpc/include/asm/kvm_ppc.h b/arch/powerpc/include/asm/kvm_ppc.h
index b3bf4f61b30c..d283d3179fbc 100644
--- a/arch/powerpc/include/asm/kvm_ppc.h
+++ b/arch/powerpc/include/asm/kvm_ppc.h
@@ -143,6 +143,7 @@ extern void kvmppc_core_vcpu_put(struct kvm_vcpu *vcpu);
 
 extern int kvmppc_core_prepare_to_enter(struct kvm_vcpu *vcpu);
 extern int kvmppc_core_pending_dec(struct kvm_vcpu *vcpu);
+extern void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags);
 extern void kvmppc_core_queue_fpunavail(struct kvm_vcpu *vcpu);
 extern void kvmppc_core_queue_vec_unavail(struct kvm_vcpu *vcpu);
@@ -646,7 +647,7 @@ long int kvmppc_rm_h_confer(struct kvm_vcpu *vcpu, int target,
                             unsigned int yield_count);
 long kvmppc_h_random(struct kvm_vcpu *vcpu);
 void kvmhv_commence_exit(int trap);
-long kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
+void kvmppc_realmode_machine_check(struct kvm_vcpu *vcpu);
 void kvmppc_subcore_enter_guest(void);
 void kvmppc_subcore_exit_guest(void);
 long kvmppc_realmode_hmi_handler(void);
diff --git a/arch/powerpc/include/asm/mce.h b/arch/powerpc/include/asm/mce.h
index a8b8903e1844..17996bc9382b 100644
--- a/arch/powerpc/include/asm/mce.h
+++ b/arch/powerpc/include/asm/mce.h
@@ -209,7 +209,7 @@ extern int get_mce_event(struct machine_check_event *mce, bool release);
 extern void release_mce_event(void);
 extern void machine_check_queue_event(void);
 extern void machine_check_print_event_info(struct machine_check_event *evt,
-                                           bool user_mode);
+                                           bool user_mode, bool in_guest);
 #ifdef CONFIG_PPC_BOOK3S_64
 void flush_and_reload_slb(void);
 #endif /* CONFIG_PPC_BOOK3S_64 */
diff --git a/arch/powerpc/kernel/mce.c b/arch/powerpc/kernel/mce.c
index bd933a75f0bc..d501b48f287e 100644
--- a/arch/powerpc/kernel/mce.c
+++ b/arch/powerpc/kernel/mce.c
@@ -301,13 +301,13 @@ static void machine_check_process_queued_event(struct irq_work *work)
         while (__this_cpu_read(mce_queue_count) > 0) {
                 index = __this_cpu_read(mce_queue_count) - 1;
                 evt = this_cpu_ptr(&mce_event_queue[index]);
-                machine_check_print_event_info(evt, false);
+                machine_check_print_event_info(evt, false, false);
                 __this_cpu_dec(mce_queue_count);
         }
 }
 
 void machine_check_print_event_info(struct machine_check_event *evt,
-                                    bool user_mode)
+                                    bool user_mode, bool in_guest)
 {
         const char *level, *sevstr, *subtype;
         static const char *mc_ue_types[] = {
@@ -387,7 +387,9 @@ void machine_check_print_event_info(struct machine_check_event *evt,
                evt->disposition == MCE_DISPOSITION_RECOVERED ?
                "Recovered" : "Not recovered");
 
-        if (user_mode) {
+        if (in_guest) {
+                printk("%s  Guest NIP: %016llx\n", level, evt->srr0);
+        } else if (user_mode) {
                 printk("%s  NIP: [%016llx] PID: %d Comm: %s\n", level,
                         evt->srr0, current->pid, current->comm);
         } else {
diff --git a/arch/powerpc/kvm/book3s.c b/arch/powerpc/kvm/book3s.c
index 22a46c64536b..10c5579d20ce 100644
--- a/arch/powerpc/kvm/book3s.c
+++ b/arch/powerpc/kvm/book3s.c
@@ -195,6 +195,13 @@ void kvmppc_book3s_queue_irqprio(struct kvm_vcpu *vcpu, unsigned int vec)
 }
 EXPORT_SYMBOL_GPL(kvmppc_book3s_queue_irqprio);
 
+void kvmppc_core_queue_machine_check(struct kvm_vcpu *vcpu, ulong flags)
+{
+        /* might as well deliver this straight away */
+        kvmppc_inject_interrupt(vcpu, BOOK3S_INTERRUPT_MACHINE_CHECK, flags);
+}
+EXPORT_SYMBOL_GPL(kvmppc_core_queue_machine_check);
+
 void kvmppc_core_queue_program(struct kvm_vcpu *vcpu, ulong flags)
 {
         /* might as well deliver this straight away */
diff --git a/arch/powerpc/kvm/book3s_hv.c b/arch/powerpc/kvm/book3s_hv.c
index ba8db3881ef9..60458947b99e 100644
--- a/arch/powerpc/kvm/book3s_hv.c
+++ b/arch/powerpc/kvm/book3s_hv.c
@@ -1217,6 +1217,22 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
                 r = RESUME_GUEST;
                 break;
         case BOOK3S_INTERRUPT_MACHINE_CHECK:
+                /* Print the MCE event to host console. */
+                machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
+
+                /*
+                 * If the guest can do FWNMI, exit to userspace so it can
+                 * deliver a FWNMI to the guest.
+                 * Otherwise we synthesize a machine check for the guest
+                 * so that it knows that the machine check occurred.
+                 */
+                if (!vcpu->kvm->arch.fwnmi_enabled) {
+                        ulong flags = vcpu->arch.shregs.msr & 0x083c0000;
+                        kvmppc_core_queue_machine_check(vcpu, flags);
+                        r = RESUME_GUEST;
+                        break;
+                }
+
                 /* Exit to guest with KVM_EXIT_NMI as exit reason */
                 run->exit_reason = KVM_EXIT_NMI;
                 run->hw.hardware_exit_reason = vcpu->arch.trap;
@@ -1229,8 +1245,6 @@ static int kvmppc_handle_exit_hv(struct kvm_run *run, struct kvm_vcpu *vcpu,
                         run->flags |= KVM_RUN_PPC_NMI_DISP_NOT_RECOV;
 
                 r = RESUME_HOST;
-                /* Print the MCE event to host console. */
-                machine_check_print_event_info(&vcpu->arch.mce_evt, false);
                 break;
         case BOOK3S_INTERRUPT_PROGRAM:
         {
@@ -1394,7 +1408,7 @@ static int kvmppc_handle_nested_exit(struct kvm_run *run, struct kvm_vcpu *vcpu)
                 /* Pass the machine check to the L1 guest */
                 r = RESUME_HOST;
                 /* Print the MCE event to host console. */
-                machine_check_print_event_info(&vcpu->arch.mce_evt, false);
+                machine_check_print_event_info(&vcpu->arch.mce_evt, false, true);
                 break;
         /*
          * We get these next two if the guest accesses a page which it thinks
@@ -3457,6 +3471,7 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
         unsigned long host_dscr = mfspr(SPRN_DSCR);
         unsigned long host_tidr = mfspr(SPRN_TIDR);
         unsigned long host_iamr = mfspr(SPRN_IAMR);
+        unsigned long host_amr = mfspr(SPRN_AMR);
         s64 dec;
         u64 tb;
         int trap, save_pmu;
@@ -3573,13 +3588,15 @@ int kvmhv_p9_guest_entry(struct kvm_vcpu *vcpu, u64 time_limit,
 
         mtspr(SPRN_PSPB, 0);
         mtspr(SPRN_WORT, 0);
-        mtspr(SPRN_AMR, 0);
         mtspr(SPRN_UAMOR, 0);
         mtspr(SPRN_DSCR, host_dscr);
         mtspr(SPRN_TIDR, host_tidr);
         mtspr(SPRN_IAMR, host_iamr);
         mtspr(SPRN_PSPB, 0);
 
+        if (host_amr != vcpu->arch.amr)
+                mtspr(SPRN_AMR, host_amr);
+
         msr_check_and_set(MSR_FP | MSR_VEC | MSR_VSX);
         store_fp_state(&vcpu->arch.fp);
 #ifdef CONFIG_ALTIVEC
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. */
diff --git a/arch/powerpc/kvm/book3s_hv_rmhandlers.S b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
index 541b121477e4..3a5e719ef032 100644
--- a/arch/powerpc/kvm/book3s_hv_rmhandlers.S
+++ b/arch/powerpc/kvm/book3s_hv_rmhandlers.S
@@ -58,6 +58,8 @@ END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
 #define STACK_SLOT_DAWR         (SFS-56)
 #define STACK_SLOT_DAWRX        (SFS-64)
 #define STACK_SLOT_HFSCR        (SFS-72)
+#define STACK_SLOT_AMR          (SFS-80)
+#define STACK_SLOT_UAMOR        (SFS-88)
 /* the following is used by the P9 short path */
 #define STACK_SLOT_NVGPRS       (SFS-152)       /* 18 gprs */
 
@@ -726,11 +728,9 @@ BEGIN_FTR_SECTION
         mfspr   r5, SPRN_TIDR
         mfspr   r6, SPRN_PSSCR
         mfspr   r7, SPRN_PID
-        mfspr   r8, SPRN_IAMR
         std     r5, STACK_SLOT_TID(r1)
         std     r6, STACK_SLOT_PSSCR(r1)
         std     r7, STACK_SLOT_PID(r1)
-        std     r8, STACK_SLOT_IAMR(r1)
         mfspr   r5, SPRN_HFSCR
         std     r5, STACK_SLOT_HFSCR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
@@ -738,11 +738,18 @@ BEGIN_FTR_SECTION
         mfspr   r5, SPRN_CIABR
         mfspr   r6, SPRN_DAWR
         mfspr   r7, SPRN_DAWRX
+        mfspr   r8, SPRN_IAMR
         std     r5, STACK_SLOT_CIABR(r1)
         std     r6, STACK_SLOT_DAWR(r1)
         std     r7, STACK_SLOT_DAWRX(r1)
+        std     r8, STACK_SLOT_IAMR(r1)
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_207S)
 
+        mfspr   r5, SPRN_AMR
+        std     r5, STACK_SLOT_AMR(r1)
+        mfspr   r6, SPRN_UAMOR
+        std     r6, STACK_SLOT_UAMOR(r1)
+
 BEGIN_FTR_SECTION
         /* Set partition DABR */
         /* Do this before re-enabling PMU to avoid P7 DABR corruption bug */
@@ -1631,22 +1638,25 @@ ALT_FTR_SECTION_END_IFCLR(CPU_FTR_ARCH_300)
         mtspr   SPRN_PSPB, r0
         mtspr   SPRN_WORT, r0
 BEGIN_FTR_SECTION
-        mtspr   SPRN_IAMR, r0
         mtspr   SPRN_TCSCR, r0
         /* Set MMCRS to 1<<31 to freeze and disable the SPMC counters */
         li      r0, 1
         sldi    r0, r0, 31
         mtspr   SPRN_MMCRS, r0
 END_FTR_SECTION_IFCLR(CPU_FTR_ARCH_300)
-8:
 
-        /* Save and reset AMR and UAMOR before turning on the MMU */
+        /* Save and restore AMR, IAMR and UAMOR before turning on the MMU */
+        ld      r8, STACK_SLOT_IAMR(r1)
+        mtspr   SPRN_IAMR, r8
+
+8:      /* Power7 jumps back in here */
         mfspr   r5,SPRN_AMR
         mfspr   r6,SPRN_UAMOR
         std     r5,VCPU_AMR(r9)
         std     r6,VCPU_UAMOR(r9)
-        li      r6,0
-        mtspr   SPRN_AMR,r6
+        ld      r5,STACK_SLOT_AMR(r1)
+        ld      r6,STACK_SLOT_UAMOR(r1)
+        mtspr   SPRN_AMR, r5
         mtspr   SPRN_UAMOR, r6
 
         /* Switch DSCR back to host value */
@@ -1746,11 +1756,9 @@ BEGIN_FTR_SECTION
         ld      r5, STACK_SLOT_TID(r1)
         ld      r6, STACK_SLOT_PSSCR(r1)
         ld      r7, STACK_SLOT_PID(r1)
-        ld      r8, STACK_SLOT_IAMR(r1)
         mtspr   SPRN_TIDR, r5
         mtspr   SPRN_PSSCR, r6
         mtspr   SPRN_PID, r7
-        mtspr   SPRN_IAMR, r8
 END_FTR_SECTION_IFSET(CPU_FTR_ARCH_300)
 
 #ifdef CONFIG_PPC_RADIX_MMU
@@ -2836,49 +2844,15 @@ kvm_cede_exit:
 #endif /* CONFIG_KVM_XICS */
 3:      b       guest_exit_cont
 
-        /* Try to handle a machine check in real mode */
+        /* Try to do machine check recovery in real mode */
 machine_check_realmode:
         mr      r3, r9          /* get vcpu pointer */
         bl      kvmppc_realmode_machine_check
         nop
+        /* all machine checks go to virtual mode for further handling */
         ld      r9, HSTATE_KVM_VCPU(r13)
         li      r12, BOOK3S_INTERRUPT_MACHINE_CHECK
-        /*
-         * For the guest that is FWNMI capable, deliver all the MCE errors
-         * (handled/unhandled) by exiting the guest with KVM_EXIT_NMI exit
-         * reason. This new approach injects machine check errors in guest
-         * address space to guest with additional information in the form
-         * of RTAS event, thus enabling guest kernel to suitably handle
-         * such errors.
-         *
-         * For the guest that is not FWNMI capable (old QEMU) fallback
-         * to old behaviour for backward compatibility:
-         * Deliver unhandled/fatal (e.g. UE) MCE errors to guest either
-         * through machine check interrupt (set HSRR0 to 0x200).
-         * For handled errors (no-fatal), just go back to guest execution
-         * with current HSRR0.
-         * if we receive machine check with MSR(RI=0) then deliver it to
-         * guest as machine check causing guest to crash.
-         */
-        ld      r11, VCPU_MSR(r9)
-        rldicl. r0, r11, 64-MSR_HV_LG, 63 /* check if it happened in HV mode */
-        bne     guest_exit_cont         /* if so, exit to host */
-        /* Check if guest is capable of handling NMI exit */
-        ld      r10, VCPU_KVM(r9)
-        lbz     r10, KVM_FWNMI(r10)
-        cmpdi   r10, 1                  /* FWNMI capable? */
-        beq     guest_exit_cont         /* if so, exit with KVM_EXIT_NMI. */
-
-        /* if not, fall through for backward compatibility. */
-        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 */
-1:      li      r10, BOOK3S_INTERRUPT_MACHINE_CHECK
-        bl      kvmppc_msr_interrupt
-2:      b       fast_interrupt_c_return
+        b       guest_exit_cont
 
 /*
  * Call C code to handle a HMI in real mode.
diff --git a/arch/powerpc/platforms/powernv/opal.c b/arch/powerpc/platforms/powernv/opal.c
index 79586f127521..05c85be0370f 100644
--- a/arch/powerpc/platforms/powernv/opal.c
+++ b/arch/powerpc/platforms/powernv/opal.c
@@ -587,7 +587,7 @@ int opal_machine_check(struct pt_regs *regs)
                        evt.version);
                 return 0;
         }
-        machine_check_print_event_info(&evt, user_mode(regs));
+        machine_check_print_event_info(&evt, user_mode(regs), false);
 
         if (opal_recover_mce(regs, &evt))
                 return 1;