From 8efc4e5150efb68e9f2b1705917ad34c62f44369 Mon Sep 17 00:00:00 2001 From: zhenwei pi Date: Wed, 30 Sep 2020 18:04:40 +0800 Subject: [PATCH] target-i386: post memory failure event to QMP Post memory failure event through QMP to handle hardware memory corrupted event. Rather than simply printing to the log, QEMU could report more effective message to the client. For example, if a guest receives an MCE, evacuating the host could be a good idea. Signed-off-by: zhenwei pi Message-Id: <20200930100440.1060708-4-pizhenwei@bytedance.com> Signed-off-by: Paolo Bonzini --- target/i386/helper.c | 24 ++++++++++++++++++++---- target/i386/kvm.c | 13 ++++++++++++- 2 files changed, 32 insertions(+), 5 deletions(-) diff --git a/target/i386/helper.c b/target/i386/helper.c index 17e1684ff9..32fa21a7bb 100644 --- a/target/i386/helper.c +++ b/target/i386/helper.c @@ -18,6 +18,7 @@ */ #include "qemu/osdep.h" +#include "qapi/qapi-events-run-state.h" #include "cpu.h" #include "exec/exec-all.h" #include "qemu/qemu-print.h" @@ -851,6 +852,15 @@ typedef struct MCEInjectionParams { int flags; } MCEInjectionParams; +static void emit_guest_memory_failure(MemoryFailureAction action, bool ar, + bool recursive) +{ + MemoryFailureFlags mff = {.action_required = ar, .recursive = recursive}; + + qapi_event_send_memory_failure(MEMORY_FAILURE_RECIPIENT_GUEST, action, + &mff); +} + static void do_inject_x86_mce(CPUState *cs, run_on_cpu_data data) { MCEInjectionParams *params = data.host_ptr; @@ -859,16 +869,18 @@ static void do_inject_x86_mce(CPUState *cs, run_on_cpu_data data) uint64_t *banks = cenv->mce_banks + 4 * params->bank; g_autofree char *msg = NULL; bool need_reset = false; + bool recursive; + bool ar = !!(params->status & MCI_STATUS_AR); cpu_synchronize_state(cs); + recursive = !!(cenv->mcg_status & MCG_STATUS_MCIP); /* * If there is an MCE exception being processed, ignore this SRAO MCE * unless unconditional injection was requested. */ - if (!(params->flags & MCE_INJECT_UNCOND_AO) - && !(params->status & MCI_STATUS_AR) - && (cenv->mcg_status & MCG_STATUS_MCIP)) { + if (!(params->flags & MCE_INJECT_UNCOND_AO) && !ar && recursive) { + emit_guest_memory_failure(MEMORY_FAILURE_ACTION_IGNORE, ar, recursive); return; } @@ -896,7 +908,7 @@ static void do_inject_x86_mce(CPUState *cs, run_on_cpu_data data) return; } - if (cenv->mcg_status & MCG_STATUS_MCIP) { + if (recursive) { need_reset = true; msg = g_strdup_printf("CPU %d: Previous MCE still in progress, " "raising triple fault", cs->cpu_index); @@ -909,6 +921,8 @@ static void do_inject_x86_mce(CPUState *cs, run_on_cpu_data data) } if (need_reset) { + emit_guest_memory_failure(MEMORY_FAILURE_ACTION_RESET, ar, + recursive); monitor_printf(params->mon, "%s", msg); qemu_log_mask(CPU_LOG_RESET, "%s\n", msg); qemu_system_reset_request(SHUTDOWN_CAUSE_GUEST_RESET); @@ -934,6 +948,8 @@ static void do_inject_x86_mce(CPUState *cs, run_on_cpu_data data) } else { banks[1] |= MCI_STATUS_OVER; } + + emit_guest_memory_failure(MEMORY_FAILURE_ACTION_INJECT, ar, recursive); } void cpu_x86_inject_mce(Monitor *mon, X86CPU *cpu, int bank, diff --git a/target/i386/kvm.c b/target/i386/kvm.c index f6dae4cfb6..8b12387d30 100644 --- a/target/i386/kvm.c +++ b/target/i386/kvm.c @@ -13,6 +13,7 @@ */ #include "qemu/osdep.h" +#include "qapi/qapi-events-run-state.h" #include "qapi/error.h" #include #include @@ -549,8 +550,17 @@ static void kvm_mce_inject(X86CPU *cpu, hwaddr paddr, int code) (MCM_ADDR_PHYS << 6) | 0xc, flags); } +static void emit_hypervisor_memory_failure(MemoryFailureAction action, bool ar) +{ + MemoryFailureFlags mff = {.action_required = ar, .recursive = false}; + + qapi_event_send_memory_failure(MEMORY_FAILURE_RECIPIENT_HYPERVISOR, action, + &mff); +} + static void hardware_memory_error(void *host_addr) { + emit_hypervisor_memory_failure(MEMORY_FAILURE_ACTION_FATAL, true); error_report("QEMU got Hardware memory error at addr %p", host_addr); exit(1); } @@ -605,7 +615,8 @@ void kvm_arch_on_sigbus_vcpu(CPUState *c, int code, void *addr) hardware_memory_error(addr); } - /* Hope we are lucky for AO MCE */ + /* Hope we are lucky for AO MCE, just notify a event */ + emit_hypervisor_memory_failure(MEMORY_FAILURE_ACTION_IGNORE, false); } static void kvm_reset_exception(CPUX86State *env) -- 2.11.0