Merge remote branch 'qemu-kvm/uq/master' into staging

cpu-all.h

@@ -863,10 +863,14 @@ target_phys_addr_t cpu_get_phys_page_debug(CPUState *env, target_ulong addr);
 extern int phys_ram_fd;
 extern ram_addr_t ram_size;
 
+/* RAM is pre-allocated and passed into qemu_ram_alloc_from_ptr */
+#define RAM_PREALLOC_MASK   (1 << 0)
+
 typedef struct RAMBlock {
     uint8_t *host;
     ram_addr_t offset;
     ram_addr_t length;
+    uint32_t flags;
     char idstr[256];
     QLIST_ENTRY(RAMBlock) next;
 #if defined(__linux__) && !defined(TARGET_S390X)
@@ -971,8 +975,4 @@ void dump_exec_info(FILE *f, fprintf_function cpu_fprintf);
 int cpu_memory_rw_debug(CPUState *env, target_ulong addr,
                         uint8_t *buf, int len, int is_write);
 
-void cpu_inject_x86_mce(CPUState *cenv, int bank, uint64_t status,
-                        uint64_t mcg_status, uint64_t addr, uint64_t misc,
-                        int broadcast);
-
 #endif /* CPU_ALL_H */

cpu-common.h

@@ -50,6 +50,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
                         ram_addr_t size, void *host);
 ram_addr_t qemu_ram_alloc(DeviceState *dev, const char *name, ram_addr_t size);
 void qemu_ram_free(ram_addr_t addr);
+void qemu_ram_remap(ram_addr_t addr, ram_addr_t length);
 /* This should only be used for ram local to a device.  */
 void *qemu_get_ram_ptr(ram_addr_t addr);
 /* Same but slower, to use for migration, where the order of

cpu-defs.h

@@ -203,6 +203,7 @@ typedef struct CPUWatchpoint {
     int nr_cores;  /* number of cores within this CPU package */        \
     int nr_threads;/* number of threads within this CPU */              \
     int running; /* Nonzero if cpu is currently running(usermode).  */  \
+    int thread_id;                                                      \
     /* user data */                                                     \
     void *opaque;                                                       \
                                                                         \

cpu-exec.c

@@ -196,6 +196,30 @@ static inline TranslationBlock *tb_find_fast(void)
     return tb;
 }
 
+static CPUDebugExcpHandler *debug_excp_handler;
+
+CPUDebugExcpHandler *cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)
+{
+    CPUDebugExcpHandler *old_handler = debug_excp_handler;
+
+    debug_excp_handler = handler;
+    return old_handler;
+}
+
+static void cpu_handle_debug_exception(CPUState *env)
+{
+    CPUWatchpoint *wp;
+
+    if (!env->watchpoint_hit) {
+        QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
+            wp->flags &= ~BP_WATCHPOINT_HIT;
+        }
+    }
+    if (debug_excp_handler) {
+        debug_excp_handler(env);
+    }
+}
+
 /* main execution loop */
 
 volatile sig_atomic_t exit_request;
@@ -269,6 +293,9 @@ int cpu_exec(CPUState *env1)
                 if (env->exception_index >= EXCP_INTERRUPT) {
                     /* exit request from the cpu execution loop */
                     ret = env->exception_index;
+                    if (ret == EXCP_DEBUG) {
+                        cpu_handle_debug_exception(env);
+                    }
                     break;
                 } else {
 #if defined(CONFIG_USER_ONLY)

cpus.c

@@ -148,7 +148,8 @@ static bool cpu_thread_is_idle(CPUState *env)
     if (env->stopped || !vm_running) {
         return true;
     }
-    if (!env->halted || qemu_cpu_has_work(env)) {
+    if (!env->halted || qemu_cpu_has_work(env) ||
+        (kvm_enabled() && kvm_irqchip_in_kernel())) {
         return false;
     }
     return true;
@@ -166,29 +167,8 @@ static bool all_cpu_threads_idle(void)
     return true;
 }
 
-static CPUDebugExcpHandler *debug_excp_handler;
-
-CPUDebugExcpHandler *cpu_set_debug_excp_handler(CPUDebugExcpHandler *handler)
+static void cpu_handle_guest_debug(CPUState *env)
 {
-    CPUDebugExcpHandler *old_handler = debug_excp_handler;
-
-    debug_excp_handler = handler;
-    return old_handler;
-}
-
-static void cpu_handle_debug_exception(CPUState *env)
-{
-    CPUWatchpoint *wp;
-
-    if (!env->watchpoint_hit) {
-        QTAILQ_FOREACH(wp, &env->watchpoints, entry) {
-            wp->flags &= ~BP_WATCHPOINT_HIT;
-        }
-    }
-    if (debug_excp_handler) {
-        debug_excp_handler(env);
-    }
-
     gdb_set_stop_cpu(env);
     qemu_system_debug_request();
 #ifdef CONFIG_IOTHREAD
@@ -245,11 +225,58 @@ static void qemu_init_sigbus(void)
     prctl(PR_MCE_KILL, PR_MCE_KILL_SET, PR_MCE_KILL_EARLY, 0, 0);
 }
 
+static void qemu_kvm_eat_signals(CPUState *env)
+{
+    struct timespec ts = { 0, 0 };
+    siginfo_t siginfo;
+    sigset_t waitset;
+    sigset_t chkset;
+    int r;
+
+    sigemptyset(&waitset);
+    sigaddset(&waitset, SIG_IPI);
+    sigaddset(&waitset, SIGBUS);
+
+    do {
+        r = sigtimedwait(&waitset, &siginfo, &ts);
+        if (r == -1 && !(errno == EAGAIN || errno == EINTR)) {
+            perror("sigtimedwait");
+            exit(1);
+        }
+
+        switch (r) {
+        case SIGBUS:
+            if (kvm_on_sigbus_vcpu(env, siginfo.si_code, siginfo.si_addr)) {
+                sigbus_reraise();
+            }
+            break;
+        default:
+            break;
+        }
+
+        r = sigpending(&chkset);
+        if (r == -1) {
+            perror("sigpending");
+            exit(1);
+        }
+    } while (sigismember(&chkset, SIG_IPI) || sigismember(&chkset, SIGBUS));
+
+#ifndef CONFIG_IOTHREAD
+    if (sigismember(&chkset, SIGIO) || sigismember(&chkset, SIGALRM)) {
+        qemu_notify_event();
+    }
+#endif
+}
+
 #else /* !CONFIG_LINUX */
 
 static void qemu_init_sigbus(void)
 {
 }
+
+static void qemu_kvm_eat_signals(CPUState *env)
+{
+}
 #endif /* !CONFIG_LINUX */
 
 #ifndef _WIN32
@@ -455,49 +482,6 @@ static void qemu_tcg_init_cpu_signals(void)
 #endif
 }
 
-static void qemu_kvm_eat_signals(CPUState *env)
-{
-    struct timespec ts = { 0, 0 };
-    siginfo_t siginfo;
-    sigset_t waitset;
-    sigset_t chkset;
-    int r;
-
-    sigemptyset(&waitset);
-    sigaddset(&waitset, SIG_IPI);
-    sigaddset(&waitset, SIGBUS);
-
-    do {
-        r = sigtimedwait(&waitset, &siginfo, &ts);
-        if (r == -1 && !(errno == EAGAIN || errno == EINTR)) {
-            perror("sigtimedwait");
-            exit(1);
-        }
-
-        switch (r) {
-        case SIGBUS:
-            if (kvm_on_sigbus_vcpu(env, siginfo.si_code, siginfo.si_addr)) {
-                sigbus_reraise();
-            }
-            break;
-        default:
-            break;
-        }
-
-        r = sigpending(&chkset);
-        if (r == -1) {
-            perror("sigpending");
-            exit(1);
-        }
-    } while (sigismember(&chkset, SIG_IPI) || sigismember(&chkset, SIGBUS));
-
-#ifndef CONFIG_IOTHREAD
-    if (sigismember(&chkset, SIGIO) || sigismember(&chkset, SIGALRM)) {
-        qemu_notify_event();
-    }
-#endif
-}
-
 #else /* _WIN32 */
 
 HANDLE qemu_event_handle;
@@ -526,10 +510,6 @@ static void qemu_event_increment(void)
     }
 }
 
-static void qemu_kvm_eat_signals(CPUState *env)
-{
-}
-
 static int qemu_signal_init(void)
 {
     return 0;
@@ -796,6 +776,7 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
 
     qemu_mutex_lock(&qemu_global_mutex);
     qemu_thread_get_self(env->thread);
+    env->thread_id = qemu_get_thread_id();
 
     r = kvm_init_vcpu(env);
     if (r < 0) {
@@ -818,7 +799,7 @@ static void *qemu_kvm_cpu_thread_fn(void *arg)
         if (cpu_can_run(env)) {
             r = kvm_cpu_exec(env);
             if (r == EXCP_DEBUG) {
-                cpu_handle_debug_exception(env);
+                cpu_handle_guest_debug(env);
             }
         }
         qemu_kvm_wait_io_event(env);
@@ -837,6 +818,7 @@ static void *qemu_tcg_cpu_thread_fn(void *arg)
     /* signal CPU creation */
     qemu_mutex_lock(&qemu_global_mutex);
     for (env = first_cpu; env != NULL; env = env->next_cpu) {
+        env->thread_id = qemu_get_thread_id();
         env->created = 1;
     }
     qemu_cond_signal(&qemu_cpu_cond);
@@ -1110,7 +1092,7 @@ bool cpu_exec_all(void)
                 r = tcg_cpu_exec(env);
             }
             if (r == EXCP_DEBUG) {
-                cpu_handle_debug_exception(env);
+                cpu_handle_guest_debug(env);
                 break;
             }
         } else if (env->stop || env->stopped) {

exec.c

@@ -638,6 +638,9 @@ void cpu_exec_init(CPUState *env)
     env->numa_node = 0;
     QTAILQ_INIT(&env->breakpoints);
     QTAILQ_INIT(&env->watchpoints);
+#ifndef CONFIG_USER_ONLY
+    env->thread_id = qemu_get_thread_id();
+#endif
     *penv = env;
 #if defined(CONFIG_USER_ONLY)
     cpu_list_unlock();
@@ -2867,6 +2870,7 @@ ram_addr_t qemu_ram_alloc_from_ptr(DeviceState *dev, const char *name,
 
     if (host) {
         new_block->host = host;
+        new_block->flags |= RAM_PREALLOC_MASK;
     } else {
         if (mem_path) {
 #if defined (__linux__) && !defined(TARGET_S390X)
@@ -2920,7 +2924,9 @@ void qemu_ram_free(ram_addr_t addr)
     QLIST_FOREACH(block, &ram_list.blocks, next) {
         if (addr == block->offset) {
             QLIST_REMOVE(block, next);
-            if (mem_path) {
+            if (block->flags & RAM_PREALLOC_MASK) {
+                ;
+            } else if (mem_path) {
 #if defined (__linux__) && !defined(TARGET_S390X)
                 if (block->fd) {
                     munmap(block->host, block->length);
@@ -2928,6 +2934,8 @@ void qemu_ram_free(ram_addr_t addr)
                 } else {
                     qemu_vfree(block->host);
                 }
+#else
+                abort();
 #endif
             } else {
 #if defined(TARGET_S390X) && defined(CONFIG_KVM)
@@ -2943,6 +2951,66 @@ void qemu_ram_free(ram_addr_t addr)
 
 }
 
+#ifndef _WIN32
+void qemu_ram_remap(ram_addr_t addr, ram_addr_t length)
+{
+    RAMBlock *block;
+    ram_addr_t offset;
+    int flags;
+    void *area, *vaddr;
+
+    QLIST_FOREACH(block, &ram_list.blocks, next) {
+        offset = addr - block->offset;
+        if (offset < block->length) {
+            vaddr = block->host + offset;
+            if (block->flags & RAM_PREALLOC_MASK) {
+                ;
+            } else {
+                flags = MAP_FIXED;
+                munmap(vaddr, length);
+                if (mem_path) {
+#if defined(__linux__) && !defined(TARGET_S390X)
+                    if (block->fd) {
+#ifdef MAP_POPULATE
+                        flags |= mem_prealloc ? MAP_POPULATE | MAP_SHARED :
+                            MAP_PRIVATE;
+#else
+                        flags |= MAP_PRIVATE;
+#endif
+                        area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                    flags, block->fd, offset);
+                    } else {
+                        flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+                        area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                    flags, -1, 0);
+                    }
+#else
+                    abort();
+#endif
+                } else {
+#if defined(TARGET_S390X) && defined(CONFIG_KVM)
+                    flags |= MAP_SHARED | MAP_ANONYMOUS;
+                    area = mmap(vaddr, length, PROT_EXEC|PROT_READ|PROT_WRITE,
+                                flags, -1, 0);
+#else
+                    flags |= MAP_PRIVATE | MAP_ANONYMOUS;
+                    area = mmap(vaddr, length, PROT_READ | PROT_WRITE,
+                                flags, -1, 0);
+#endif
+                }
+                if (area != vaddr) {
+                    fprintf(stderr, "Could not remap addr: %lx@%lx\n",
+                            length, addr);
+                    exit(1);
+                }
+                qemu_madvise(vaddr, length, QEMU_MADV_MERGEABLE);
+            }
+            return;
+        }
+    }
+}
+#endif /* !_WIN32 */
+
 /* Return a host pointer to ram allocated with qemu_ram_alloc.
    With the exception of the softmmu code in this file, this should
    only be used for local memory (e.g. video ram) that the device owns,

kvm-all.c

@@ -211,6 +211,7 @@ int kvm_init_vcpu(CPUState *env)
 
     env->kvm_fd = ret;
     env->kvm_state = s;
+    env->kvm_vcpu_dirty = 1;
 
     mmap_size = kvm_ioctl(s, KVM_GET_VCPU_MMAP_SIZE, 0);
     if (mmap_size < 0) {
@@ -830,7 +831,7 @@ static int kvm_handle_internal_error(CPUState *env, struct kvm_run *run)
         fprintf(stderr, "emulation failure\n");
         if (!kvm_arch_stop_on_emulation_error(env)) {
             cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
-            return 0;
+            return EXCP_INTERRUPT;
         }
     }
     /* FIXME: Should trigger a qmp message to let management know
@@ -889,11 +890,11 @@ void kvm_cpu_synchronize_post_init(CPUState *env)
 int kvm_cpu_exec(CPUState *env)
 {
     struct kvm_run *run = env->kvm_run;
-    int ret;
+    int ret, run_ret;
 
     DPRINTF("kvm_cpu_exec()\n");
 
-    if (kvm_arch_process_irqchip_events(env)) {
+    if (kvm_arch_process_async_events(env)) {
         env->exit_request = 0;
         return EXCP_HLT;
     }
@@ -919,7 +920,7 @@ int kvm_cpu_exec(CPUState *env)
         cpu_single_env = NULL;
         qemu_mutex_unlock_iothread();
 
-        ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
+        run_ret = kvm_vcpu_ioctl(env, KVM_RUN, 0);
 
         qemu_mutex_lock_iothread();
         cpu_single_env = env;
@@ -927,18 +928,16 @@ int kvm_cpu_exec(CPUState *env)
 
         kvm_flush_coalesced_mmio_buffer();
 
-        if (ret == -EINTR || ret == -EAGAIN) {
-            DPRINTF("io window exit\n");
-            ret = 0;
-            break;
-        }
-
-        if (ret < 0) {
-            DPRINTF("kvm run failed %s\n", strerror(-ret));
+        if (run_ret < 0) {
+            if (run_ret == -EINTR || run_ret == -EAGAIN) {
+                DPRINTF("io window exit\n");
+                ret = EXCP_INTERRUPT;
+                break;
+            }
+            DPRINTF("kvm run failed %s\n", strerror(-run_ret));
             abort();
         }
 
-        ret = 0; /* exit loop */
         switch (run->exit_reason) {
         case KVM_EXIT_IO:
             DPRINTF("handle_io\n");
@@ -947,7 +946,7 @@ int kvm_cpu_exec(CPUState *env)
                           run->io.direction,
                           run->io.size,
                           run->io.count);
-            ret = 1;
+            ret = 0;
             break;
         case KVM_EXIT_MMIO:
             DPRINTF("handle_mmio\n");
@@ -955,14 +954,16 @@ int kvm_cpu_exec(CPUState *env)
                                    run->mmio.data,
                                    run->mmio.len,
                                    run->mmio.is_write);
-            ret = 1;
+            ret = 0;
             break;
         case KVM_EXIT_IRQ_WINDOW_OPEN:
             DPRINTF("irq_window_open\n");
+            ret = EXCP_INTERRUPT;
             break;
         case KVM_EXIT_SHUTDOWN:
             DPRINTF("shutdown\n");
             qemu_system_reset_request();
+            ret = EXCP_INTERRUPT;
             break;
         case KVM_EXIT_UNKNOWN:
             fprintf(stderr, "KVM: unknown exit, hardware reason %" PRIx64 "\n",
@@ -974,31 +975,18 @@ int kvm_cpu_exec(CPUState *env)
             ret = kvm_handle_internal_error(env, run);
             break;
 #endif
-        case KVM_EXIT_DEBUG:
-            DPRINTF("kvm_exit_debug\n");
-#ifdef KVM_CAP_SET_GUEST_DEBUG
-            if (kvm_arch_debug(&run->debug.arch)) {
-                ret = EXCP_DEBUG;
-                goto out;
-            }
-            /* re-enter, this exception was guest-internal */
-            ret = 1;
-#endif /* KVM_CAP_SET_GUEST_DEBUG */
-            break;
         default:
             DPRINTF("kvm_arch_handle_exit\n");
             ret = kvm_arch_handle_exit(env, run);
             break;
         }
-    } while (ret > 0);
+    } while (ret == 0);
 
     if (ret < 0) {
         cpu_dump_state(env, stderr, fprintf, CPU_DUMP_CODE);
         vm_stop(VMSTOP_PANIC);
     }
-    ret = EXCP_INTERRUPT;
 
-out:
     env->exit_request = 0;
     cpu_single_env = NULL;
     return ret;

kvm.h

@@ -102,7 +102,7 @@ void kvm_arch_post_run(CPUState *env, struct kvm_run *run);
 
 int kvm_arch_handle_exit(CPUState *env, struct kvm_run *run);
 
-int kvm_arch_process_irqchip_events(CPUState *env);
+int kvm_arch_process_async_events(CPUState *env);
 
 int kvm_arch_get_registers(CPUState *env);
 
@@ -136,8 +136,6 @@ struct kvm_sw_breakpoint {
 
 QTAILQ_HEAD(kvm_sw_breakpoint_head, kvm_sw_breakpoint);
 
-int kvm_arch_debug(struct kvm_debug_exit_arch *arch_info);
-
 struct kvm_sw_breakpoint *kvm_find_sw_breakpoint(CPUState *env,
                                                  target_ulong pc);
 

monitor.c

@@ -897,6 +897,9 @@ static void print_cpu_iter(QObject *obj, void *opaque)
         monitor_printf(mon, " (halted)");
     }
 
+    monitor_printf(mon, " thread_id=%" PRId64 " ",
+                   qdict_get_int(cpu, "thread_id"));
+
     monitor_printf(mon, "\n");
 }
 
@@ -941,6 +944,7 @@ static void do_info_cpus(Monitor *mon, QObject **ret_data)
 #elif defined(TARGET_MIPS)
         qdict_put(cpu, "PC", qint_from_int(env->active_tc.PC));
 #endif
+        qdict_put(cpu, "thread_id", qint_from_int(env->thread_id));
 
         qlist_append(cpu_list, cpu);
     }
@@ -2709,12 +2713,15 @@ static void do_inject_mce(Monitor *mon, const QDict *qdict)
     uint64_t mcg_status = qdict_get_int(qdict, "mcg_status");
     uint64_t addr = qdict_get_int(qdict, "addr");
     uint64_t misc = qdict_get_int(qdict, "misc");
-    int broadcast = qdict_get_try_bool(qdict, "broadcast", 0);
+    int flags = MCE_INJECT_UNCOND_AO;
 
+    if (qdict_get_try_bool(qdict, "broadcast", 0)) {
+        flags |= MCE_INJECT_BROADCAST;
+    }
     for (cenv = first_cpu; cenv != NULL; cenv = cenv->next_cpu) {
-        if (cenv->cpu_index == cpu_index && cenv->mcg_cap) {
-            cpu_inject_x86_mce(cenv, bank, status, mcg_status, addr, misc,
-                               broadcast);
+        if (cenv->cpu_index == cpu_index) {
+            cpu_x86_inject_mce(mon, cenv, bank, status, mcg_status, addr, misc,
+                               flags);
             break;
         }
     }

os-posix.c

@@ -41,6 +41,7 @@
 
 #ifdef CONFIG_LINUX
 #include <sys/prctl.h>
+#include <sys/syscall.h>
 #endif
 
 #ifdef CONFIG_EVENTFD
@@ -382,3 +383,12 @@ int qemu_create_pidfile(const char *filename)
 
     return 0;
 }
+
+int qemu_get_thread_id(void)
+{
+#if defined (__linux__)
+    return syscall(SYS_gettid);
+#else
+    return getpid();
+#endif
+}

os-win32.c

@@ -266,3 +266,8 @@ int qemu_create_pidfile(const char *filename)
     }
     return 0;
 }
+
+int qemu_get_thread_id(void)
+{
+    return GetCurrentThreadId();
+}

osdep.h

@@ -128,6 +128,7 @@ void qemu_vfree(void *ptr);
 int qemu_madvise(void *addr, size_t len, int advice);
 
 int qemu_create_pidfile(const char *filename);
+int qemu_get_thread_id(void);
 
 #ifdef _WIN32
 static inline void qemu_timersub(const struct timeval *val1,

qemu-common.h

@@ -18,6 +18,9 @@ typedef struct QEMUFile QEMUFile;
 typedef struct QEMUBH QEMUBH;
 typedef struct DeviceState DeviceState;
 
+struct Monitor;
+typedef struct Monitor Monitor;
+
 /* we put basic includes here to avoid repeating them in device drivers */
 #include <stdlib.h>
 #include <stdio.h>
@@ -327,9 +330,6 @@ void qemu_iovec_memset(QEMUIOVector *qiov, int c, size_t count);
 void qemu_iovec_memset_skip(QEMUIOVector *qiov, int c, size_t count,
                             size_t skip);
 
-struct Monitor;
-typedef struct Monitor Monitor;
-
 /* Convert a byte between binary and BCD.  */
 static inline uint8_t to_bcd(uint8_t val)
 {

qmp-commands.hx

@@ -1194,6 +1194,7 @@ Return a json-array. Each CPU is represented by a json-object, which contains:
      "nip": PPC (json-int)
      "pc" and "npc": sparc (json-int)
      "PC": mips (json-int)
+- "thread_id": ID of the underlying host thread (json-int)
 
 Example:
 
@@ -1205,12 +1206,14 @@ Example:
             "current":true,
             "halted":false,
             "pc":3227107138
+            "thread_id":3134
          },
          {
             "CPU":1,
             "current":false,
             "halted":true,
             "pc":7108165
+            "thread_id":3135
          }