target/ppc: Build rtas error log upon an MCE

Upon a machine check exception (MCE) in a guest address space,
KVM causes a guest exit to enable QEMU to build and pass the
error to the guest in the PAPR defined rtas error log format.

This patch builds the rtas error log, copies it to the rtas_addr
and then invokes the guest registered machine check handler. The
handler in the guest takes suitable action(s) depending on the type
and criticality of the error. For example, if an error is
unrecoverable memory corruption in an application inside the
guest, then the guest kernel sends a SIGBUS to the application.
For recoverable errors, the guest performs recovery actions and
logs the error.

Signed-off-by: Aravinda Prasad <arawinda.p@gmail.com>
[Assume SLOF has allocated enough room for rtas error log]
Signed-off-by: Ganesh Goudar <ganeshgr@linux.ibm.com>
Reviewed-by: David Gibson <david@gibson.dropbear.id.au>
Message-Id: <20200130184423.20519-5-ganeshgr@linux.ibm.com>
Signed-off-by: David Gibson <david@gibson.dropbear.id.au>

2 files changed, 245 insertions, 1 deletions

diff --git a/hw/ppc/spapr_events.c b/hw/ppc/spapr_events.c
index dfc0de840a..54eaf28a9e 100644
--- a/hw/ppc/spapr_events.c
+++ b/hw/ppc/spapr_events.c
@@ -214,6 +214,104 @@ struct hp_extended_log {
     struct rtas_event_log_v6_hp hp;
 } QEMU_PACKED;
 
+struct rtas_event_log_v6_mc {
+#define RTAS_LOG_V6_SECTION_ID_MC                   0x4D43 /* MC */
+    struct rtas_event_log_v6_section_header hdr;
+    uint32_t fru_id;
+    uint32_t proc_id;
+    uint8_t error_type;
+#define RTAS_LOG_V6_MC_TYPE_UE                           0
+#define RTAS_LOG_V6_MC_TYPE_SLB                          1
+#define RTAS_LOG_V6_MC_TYPE_ERAT                         2
+#define RTAS_LOG_V6_MC_TYPE_TLB                          4
+#define RTAS_LOG_V6_MC_TYPE_D_CACHE                      5
+#define RTAS_LOG_V6_MC_TYPE_I_CACHE                      7
+    uint8_t sub_err_type;
+#define RTAS_LOG_V6_MC_UE_INDETERMINATE                  0
+#define RTAS_LOG_V6_MC_UE_IFETCH                         1
+#define RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_IFETCH         2
+#define RTAS_LOG_V6_MC_UE_LOAD_STORE                     3
+#define RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_LOAD_STORE     4
+#define RTAS_LOG_V6_MC_SLB_PARITY                        0
+#define RTAS_LOG_V6_MC_SLB_MULTIHIT                      1
+#define RTAS_LOG_V6_MC_SLB_INDETERMINATE                 2
+#define RTAS_LOG_V6_MC_ERAT_PARITY                       1
+#define RTAS_LOG_V6_MC_ERAT_MULTIHIT                     2
+#define RTAS_LOG_V6_MC_ERAT_INDETERMINATE                3
+#define RTAS_LOG_V6_MC_TLB_PARITY                        1
+#define RTAS_LOG_V6_MC_TLB_MULTIHIT                      2
+#define RTAS_LOG_V6_MC_TLB_INDETERMINATE                 3
+    uint8_t reserved_1[6];
+    uint64_t effective_address;
+    uint64_t logical_address;
+} QEMU_PACKED;
+
+struct mc_extended_log {
+    struct rtas_event_log_v6 v6hdr;
+    struct rtas_event_log_v6_mc mc;
+} QEMU_PACKED;
+
+struct MC_ierror_table {
+    unsigned long srr1_mask;
+    unsigned long srr1_value;
+    bool nip_valid; /* nip is a valid indicator of faulting address */
+    uint8_t error_type;
+    uint8_t error_subtype;
+    unsigned int initiator;
+    unsigned int severity;
+};
+
+static const struct MC_ierror_table mc_ierror_table[] = {
+{ 0x00000000081c0000, 0x0000000000040000, true,
+  RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_IFETCH,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000080000, true,
+  RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_PARITY,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x00000000000c0000, true,
+  RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_MULTIHIT,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000100000, true,
+  RTAS_LOG_V6_MC_TYPE_ERAT, RTAS_LOG_V6_MC_ERAT_MULTIHIT,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000140000, true,
+  RTAS_LOG_V6_MC_TYPE_TLB, RTAS_LOG_V6_MC_TLB_MULTIHIT,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000000081c0000, 0x0000000000180000, true,
+  RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_IFETCH,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, } };
+
+struct MC_derror_table {
+    unsigned long dsisr_value;
+    bool dar_valid; /* dar is a valid indicator of faulting address */
+    uint8_t error_type;
+    uint8_t error_subtype;
+    unsigned int initiator;
+    unsigned int severity;
+};
+
+static const struct MC_derror_table mc_derror_table[] = {
+{ 0x00008000, false,
+  RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_LOAD_STORE,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00004000, true,
+  RTAS_LOG_V6_MC_TYPE_UE, RTAS_LOG_V6_MC_UE_PAGE_TABLE_WALK_LOAD_STORE,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000800, true,
+  RTAS_LOG_V6_MC_TYPE_ERAT, RTAS_LOG_V6_MC_ERAT_MULTIHIT,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000400, true,
+  RTAS_LOG_V6_MC_TYPE_TLB, RTAS_LOG_V6_MC_TLB_MULTIHIT,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000080, true,
+  RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_MULTIHIT,  /* Before PARITY */
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, },
+{ 0x00000100, true,
+  RTAS_LOG_V6_MC_TYPE_SLB, RTAS_LOG_V6_MC_SLB_PARITY,
+  RTAS_LOG_INITIATOR_CPU, RTAS_LOG_SEVERITY_ERROR_SYNC, } };
+
+#define SRR1_MC_LOADSTORE(srr1) ((srr1) & PPC_BIT(42))
+
 typedef enum EventClass {
     EVENT_CLASS_INTERNAL_ERRORS     = 0,
     EVENT_CLASS_EPOW                = 1,
@@ -623,7 +721,125 @@ 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)
+static uint32_t spapr_mce_get_elog_type(PowerPCCPU *cpu, bool recovered,
+                                        struct mc_extended_log *ext_elog)
+{
+    int i;
+    CPUPPCState *env = &cpu->env;
+    uint32_t summary;
+    uint64_t dsisr = env->spr[SPR_DSISR];
+
+    summary = RTAS_LOG_VERSION_6 | RTAS_LOG_OPTIONAL_PART_PRESENT;
+    if (recovered) {
+        summary |= RTAS_LOG_DISPOSITION_FULLY_RECOVERED;
+    } else {
+        summary |= RTAS_LOG_DISPOSITION_NOT_RECOVERED;
+    }
+
+    if (SRR1_MC_LOADSTORE(env->spr[SPR_SRR1])) {
+        for (i = 0; i < ARRAY_SIZE(mc_derror_table); i++) {
+            if (!(dsisr & mc_derror_table[i].dsisr_value)) {
+                continue;
+            }
+
+            ext_elog->mc.error_type = mc_derror_table[i].error_type;
+            ext_elog->mc.sub_err_type = mc_derror_table[i].error_subtype;
+            if (mc_derror_table[i].dar_valid) {
+                ext_elog->mc.effective_address = cpu_to_be64(env->spr[SPR_DAR]);
+            }
+
+            summary |= mc_derror_table[i].initiator
+                        | mc_derror_table[i].severity;
+
+            return summary;
+        }
+    } else {
+        for (i = 0; i < ARRAY_SIZE(mc_ierror_table); i++) {
+            if ((env->spr[SPR_SRR1] & mc_ierror_table[i].srr1_mask) !=
+                    mc_ierror_table[i].srr1_value) {
+                continue;
+            }
+
+            ext_elog->mc.error_type = mc_ierror_table[i].error_type;
+            ext_elog->mc.sub_err_type = mc_ierror_table[i].error_subtype;
+            if (mc_ierror_table[i].nip_valid) {
+                ext_elog->mc.effective_address = cpu_to_be64(env->nip);
+            }
+
+            summary |= mc_ierror_table[i].initiator
+                        | mc_ierror_table[i].severity;
+
+            return summary;
+        }
+    }
+
+    summary |= RTAS_LOG_INITIATOR_CPU;
+    return summary;
+}
+
+static void spapr_mce_dispatch_elog(PowerPCCPU *cpu, bool recovered)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+    CPUState *cs = CPU(cpu);
+    uint64_t rtas_addr;
+    CPUPPCState *env = &cpu->env;
+    PowerPCCPUClass *pcc = POWERPC_CPU_GET_CLASS(cpu);
+    target_ulong msr = 0;
+    struct rtas_error_log log;
+    struct mc_extended_log *ext_elog;
+    uint32_t summary;
+
+    /*
+     * Properly set bits in MSR before we invoke the handler.
+     * SRR0/1, DAR and DSISR are properly set by KVM
+     */
+    if (!(*pcc->interrupts_big_endian)(cpu)) {
+        msr |= (1ULL << MSR_LE);
+    }
+
+    if (env->msr & (1ULL << MSR_SF)) {
+        msr |= (1ULL << MSR_SF);
+    }
+
+    msr |= (1ULL << MSR_ME);
+
+    ext_elog = g_malloc0(sizeof(*ext_elog));
+    summary = spapr_mce_get_elog_type(cpu, recovered, ext_elog);
+
+    log.summary = cpu_to_be32(summary);
+    log.extended_length = cpu_to_be32(sizeof(*ext_elog));
+
+    spapr_init_v6hdr(&ext_elog->v6hdr);
+    ext_elog->mc.hdr.section_id = cpu_to_be16(RTAS_LOG_V6_SECTION_ID_MC);
+    ext_elog->mc.hdr.section_length =
+                    cpu_to_be16(sizeof(struct rtas_event_log_v6_mc));
+    ext_elog->mc.hdr.section_version = 1;
+
+    /* get rtas addr from fdt */
+    rtas_addr = spapr_get_rtas_addr();
+    if (!rtas_addr) {
+        /* Unable to fetch rtas_addr. Hence reset the guest */
+        ppc_cpu_do_system_reset(cs);
+        g_free(ext_elog);
+        return;
+    }
+
+    stq_be_phys(&address_space_memory, rtas_addr + RTAS_ERROR_LOG_OFFSET,
+                env->gpr[3]);
+    cpu_physical_memory_write(rtas_addr + RTAS_ERROR_LOG_OFFSET +
+                              sizeof(env->gpr[3]), &log, sizeof(log));
+    cpu_physical_memory_write(rtas_addr + RTAS_ERROR_LOG_OFFSET +
+                              sizeof(env->gpr[3]) + sizeof(log), ext_elog,
+                              sizeof(*ext_elog));
+
+    env->gpr[3] = rtas_addr + RTAS_ERROR_LOG_OFFSET;
+    env->msr = msr;
+    env->nip = spapr->guest_machine_check_addr;
+
+    g_free(ext_elog);
+}
+
+void spapr_mce_req_event(PowerPCCPU *cpu, bool recovered)
 {
     SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
     CPUState *cs = CPU(cpu);
@@ -657,6 +873,8 @@ void spapr_mce_req_event(PowerPCCPU *cpu)
         }
     }
     spapr->mc_status = cpu->vcpu_id;
+
+    spapr_mce_dispatch_elog(cpu, recovered);
 }
 
 static void check_exception(PowerPCCPU *cpu, SpaprMachineState *spapr,
diff --git a/hw/ppc/spapr_rtas.c b/hw/ppc/spapr_rtas.c
index 85135e0e1a..89b7eb6c54 100644
--- a/hw/ppc/spapr_rtas.c
+++ b/hw/ppc/spapr_rtas.c
@@ -476,6 +476,32 @@ void spapr_dt_rtas_tokens(void *fdt, int rtas)
     }
 }
 
+hwaddr spapr_get_rtas_addr(void)
+{
+    SpaprMachineState *spapr = SPAPR_MACHINE(qdev_get_machine());
+    int rtas_node;
+    const fdt32_t *rtas_data;
+    void *fdt = spapr->fdt_blob;
+
+    /* fetch rtas addr from fdt */
+    rtas_node = fdt_path_offset(fdt, "/rtas");
+    if (rtas_node < 0) {
+        return 0;
+    }
+
+    rtas_data = fdt_getprop(fdt, rtas_node, "linux,rtas-base", NULL);
+    if (!rtas_data) {
+        return 0;
+    }
+
+    /*
+     * We assume that the OS called RTAS instantiate-rtas, but some other
+     * OS might call RTAS instantiate-rtas-64 instead. This fine as of now
+     * as SLOF only supports 32-bit variant.
+     */
+    return (hwaddr)fdt32_to_cpu(*rtas_data);
+}
+
 static void core_rtas_register_types(void)
 {
     spapr_rtas_register(RTAS_DISPLAY_CHARACTER, "display-character",