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

10 files changed, 186 insertions, 27 deletions

diff --git a/hw/cirrus_vga.c b/hw/cirrus_vga.c
index 5f45b5dee7..2724f7b480 100644
--- a/hw/cirrus_vga.c
+++ b/hw/cirrus_vga.c
@@ -31,7 +31,6 @@
 #include "pci.h"
 #include "console.h"
 #include "vga_int.h"
-#include "kvm.h"
 #include "loader.h"
 
 /*
diff --git a/hw/ide/core.c b/hw/ide/core.c
index dd63664c0d..9c91a49767 100644
--- a/hw/ide/core.c
+++ b/hw/ide/core.c
@@ -465,7 +465,7 @@ static int ide_handle_rw_error(IDEState *s, int error, int op)
         s->bus->dma->ops->set_unit(s->bus->dma, s->unit);
         s->bus->dma->ops->add_status(s->bus->dma, op);
         bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read);
-        vm_stop(0);
+        vm_stop(VMSTOP_DISKFULL);
     } else {
         if (op & BM_STATUS_DMA_RETRY) {
             dma_buf_commit(s, 0);
diff --git a/hw/kvmclock.c b/hw/kvmclock.c
new file mode 100644
index 0000000000..b6ceddfba6
--- /dev/null
+++ b/hw/kvmclock.c
@@ -0,0 +1,125 @@
+/*
+ * QEMU KVM support, paravirtual clock device
+ *
+ * Copyright (C) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka        <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+#include "qemu-common.h"
+#include "sysemu.h"
+#include "sysbus.h"
+#include "kvm.h"
+#include "kvmclock.h"
+
+#if defined(CONFIG_KVM_PARA) && defined(KVM_CAP_ADJUST_CLOCK)
+
+#include <linux/kvm.h>
+#include <linux/kvm_para.h>
+
+typedef struct KVMClockState {
+    SysBusDevice busdev;
+    uint64_t clock;
+    bool clock_valid;
+} KVMClockState;
+
+static void kvmclock_pre_save(void *opaque)
+{
+    KVMClockState *s = opaque;
+    struct kvm_clock_data data;
+    int ret;
+
+    if (s->clock_valid) {
+        return;
+    }
+    ret = kvm_vm_ioctl(kvm_state, KVM_GET_CLOCK, &data);
+    if (ret < 0) {
+        fprintf(stderr, "KVM_GET_CLOCK failed: %s\n", strerror(ret));
+        data.clock = 0;
+    }
+    s->clock = data.clock;
+    /*
+     * If the VM is stopped, declare the clock state valid to avoid re-reading
+     * it on next vmsave (which would return a different value). Will be reset
+     * when the VM is continued.
+     */
+    s->clock_valid = !vm_running;
+}
+
+static int kvmclock_post_load(void *opaque, int version_id)
+{
+    KVMClockState *s = opaque;
+    struct kvm_clock_data data;
+
+    data.clock = s->clock;
+    data.flags = 0;
+    return kvm_vm_ioctl(kvm_state, KVM_SET_CLOCK, &data);
+}
+
+static void kvmclock_vm_state_change(void *opaque, int running, int reason)
+{
+    KVMClockState *s = opaque;
+
+    if (running) {
+        s->clock_valid = false;
+    }
+}
+
+static int kvmclock_init(SysBusDevice *dev)
+{
+    KVMClockState *s = FROM_SYSBUS(KVMClockState, dev);
+
+    qemu_add_vm_change_state_handler(kvmclock_vm_state_change, s);
+    return 0;
+}
+
+static const VMStateDescription kvmclock_vmsd = {
+    .name = "kvmclock",
+    .version_id = 1,
+    .minimum_version_id = 1,
+    .minimum_version_id_old = 1,
+    .pre_save = kvmclock_pre_save,
+    .post_load = kvmclock_post_load,
+    .fields = (VMStateField[]) {
+        VMSTATE_UINT64(clock, KVMClockState),
+        VMSTATE_END_OF_LIST()
+    }
+};
+
+static SysBusDeviceInfo kvmclock_info = {
+    .qdev.name = "kvmclock",
+    .qdev.size = sizeof(KVMClockState),
+    .qdev.vmsd = &kvmclock_vmsd,
+    .qdev.no_user = 1,
+    .init = kvmclock_init,
+};
+
+/* Note: Must be called after VCPU initialization. */
+void kvmclock_create(void)
+{
+    if (kvm_enabled() &&
+        first_cpu->cpuid_kvm_features & (1ULL << KVM_FEATURE_CLOCKSOURCE)) {
+        sysbus_create_simple("kvmclock", -1, NULL);
+    }
+}
+
+static void kvmclock_register_device(void)
+{
+    if (kvm_enabled()) {
+        sysbus_register_withprop(&kvmclock_info);
+    }
+}
+
+device_init(kvmclock_register_device);
+
+#else /* !(CONFIG_KVM_PARA && KVM_CAP_ADJUST_CLOCK) */
+
+void kvmclock_create(void)
+{
+}
+#endif /* !(CONFIG_KVM_PARA && KVM_CAP_ADJUST_CLOCK) */
diff --git a/hw/kvmclock.h b/hw/kvmclock.h
new file mode 100644
index 0000000000..7a83cbe8f6
--- /dev/null
+++ b/hw/kvmclock.h
@@ -0,0 +1,14 @@
+/*
+ * QEMU KVM support, paravirtual clock device
+ *
+ * Copyright (C) 2011 Siemens AG
+ *
+ * Authors:
+ *  Jan Kiszka        <jan.kiszka@siemens.com>
+ *
+ * This work is licensed under the terms of the GNU GPL version 2.
+ * See the COPYING file in the top-level directory.
+ *
+ */
+
+void kvmclock_create(void);
diff --git a/hw/pc_piix.c b/hw/pc_piix.c
index d0bd0cd1fa..291845478d 100644
--- a/hw/pc_piix.c
+++ b/hw/pc_piix.c
@@ -32,6 +32,7 @@
 #include "boards.h"
 #include "ide.h"
 #include "kvm.h"
+#include "kvmclock.h"
 #include "sysemu.h"
 #include "sysbus.h"
 #include "arch_init.h"
@@ -66,7 +67,8 @@ static void pc_init1(ram_addr_t ram_size,
                      const char *kernel_cmdline,
                      const char *initrd_filename,
                      const char *cpu_model,
-                     int pci_enabled)
+                     int pci_enabled,
+                     int kvmclock_enabled)
 {
     int i;
     ram_addr_t below_4g_mem_size, above_4g_mem_size;
@@ -86,6 +88,10 @@ static void pc_init1(ram_addr_t ram_size,
 
     pc_cpus_init(cpu_model);
 
+    if (kvmclock_enabled) {
+        kvmclock_create();
+    }
+
     /* allocate ram and load rom/bios */
     pc_memory_init(ram_size, kernel_filename, kernel_cmdline, initrd_filename,
                    &below_4g_mem_size, &above_4g_mem_size);
@@ -193,7 +199,19 @@ static void pc_init_pci(ram_addr_t ram_size,
 {
     pc_init1(ram_size, boot_device,
              kernel_filename, kernel_cmdline,
-             initrd_filename, cpu_model, 1);
+             initrd_filename, cpu_model, 1, 1);
+}
+
+static void pc_init_pci_no_kvmclock(ram_addr_t ram_size,
+                                    const char *boot_device,
+                                    const char *kernel_filename,
+                                    const char *kernel_cmdline,
+                                    const char *initrd_filename,
+                                    const char *cpu_model)
+{
+    pc_init1(ram_size, boot_device,
+             kernel_filename, kernel_cmdline,
+             initrd_filename, cpu_model, 1, 0);
 }
 
 static void pc_init_isa(ram_addr_t ram_size,
@@ -207,7 +225,7 @@ static void pc_init_isa(ram_addr_t ram_size,
         cpu_model = "486";
     pc_init1(ram_size, boot_device,
              kernel_filename, kernel_cmdline,
-             initrd_filename, cpu_model, 0);
+             initrd_filename, cpu_model, 0, 1);
 }
 
 static QEMUMachine pc_machine = {
@@ -222,7 +240,7 @@ static QEMUMachine pc_machine = {
 static QEMUMachine pc_machine_v0_13 = {
     .name = "pc-0.13",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {
@@ -249,7 +267,7 @@ static QEMUMachine pc_machine_v0_13 = {
 static QEMUMachine pc_machine_v0_12 = {
     .name = "pc-0.12",
     .desc = "Standard PC",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {
@@ -280,7 +298,7 @@ static QEMUMachine pc_machine_v0_12 = {
 static QEMUMachine pc_machine_v0_11 = {
     .name = "pc-0.11",
     .desc = "Standard PC, qemu 0.11",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {
@@ -319,7 +337,7 @@ static QEMUMachine pc_machine_v0_11 = {
 static QEMUMachine pc_machine_v0_10 = {
     .name = "pc-0.10",
     .desc = "Standard PC, qemu 0.10",
-    .init = pc_init_pci,
+    .init = pc_init_pci_no_kvmclock,
     .max_cpus = 255,
     .compat_props = (GlobalProperty[]) {
         {
diff --git a/hw/scsi-disk.c b/hw/scsi-disk.c
index 488eedd2cd..b05e6547df 100644
--- a/hw/scsi-disk.c
+++ b/hw/scsi-disk.c
@@ -239,7 +239,7 @@ static int scsi_handle_rw_error(SCSIDiskReq *r, int error, int type)
         r->status |= SCSI_REQ_STATUS_RETRY | type;
 
         bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read);
-        vm_stop(0);
+        vm_stop(VMSTOP_DISKFULL);
     } else {
         if (type == SCSI_REQ_STATUS_RETRY_READ) {
             r->req.bus->complete(r->req.bus, SCSI_REASON_DATA, r->req.tag, 0);
diff --git a/hw/vga.c b/hw/vga.c
index e2151a2458..c22b8af833 100644
--- a/hw/vga.c
+++ b/hw/vga.c
@@ -28,7 +28,6 @@
 #include "vga_int.h"
 #include "pixel_ops.h"
 #include "qemu-timer.h"
-#include "kvm.h"
 
 //#define DEBUG_VGA
 //#define DEBUG_VGA_MEM
@@ -1573,34 +1572,36 @@ static void vga_sync_dirty_bitmap(VGACommonState *s)
 
 void vga_dirty_log_start(VGACommonState *s)
 {
-    if (kvm_enabled() && s->map_addr)
-        kvm_log_start(s->map_addr, s->map_end - s->map_addr);
+    if (s->map_addr) {
+        cpu_physical_log_start(s->map_addr, s->map_end - s->map_addr);
+    }
 
-    if (kvm_enabled() && s->lfb_vram_mapped) {
-        kvm_log_start(isa_mem_base + 0xa0000, 0x8000);
-        kvm_log_start(isa_mem_base + 0xa8000, 0x8000);
+    if (s->lfb_vram_mapped) {
+        cpu_physical_log_start(isa_mem_base + 0xa0000, 0x8000);
+        cpu_physical_log_start(isa_mem_base + 0xa8000, 0x8000);
     }
 
 #ifdef CONFIG_BOCHS_VBE
-    if (kvm_enabled() && s->vbe_mapped) {
-        kvm_log_start(VBE_DISPI_LFB_PHYSICAL_ADDRESS, s->vram_size);
+    if (s->vbe_mapped) {
+        cpu_physical_log_start(VBE_DISPI_LFB_PHYSICAL_ADDRESS, s->vram_size);
     }
 #endif
 }
 
 void vga_dirty_log_stop(VGACommonState *s)
 {
-    if (kvm_enabled() && s->map_addr)
-	kvm_log_stop(s->map_addr, s->map_end - s->map_addr);
+    if (s->map_addr) {
+        cpu_physical_log_stop(s->map_addr, s->map_end - s->map_addr);
+    }
 
-    if (kvm_enabled() && s->lfb_vram_mapped) {
-	kvm_log_stop(isa_mem_base + 0xa0000, 0x8000);
-	kvm_log_stop(isa_mem_base + 0xa8000, 0x8000);
+    if (s->lfb_vram_mapped) {
+        cpu_physical_log_stop(isa_mem_base + 0xa0000, 0x8000);
+        cpu_physical_log_stop(isa_mem_base + 0xa8000, 0x8000);
     }
 
 #ifdef CONFIG_BOCHS_VBE
-    if (kvm_enabled() && s->vbe_mapped) {
-	kvm_log_stop(VBE_DISPI_LFB_PHYSICAL_ADDRESS, s->vram_size);
+    if (s->vbe_mapped) {
+        cpu_physical_log_stop(VBE_DISPI_LFB_PHYSICAL_ADDRESS, s->vram_size);
     }
 #endif
 }
diff --git a/hw/vhost.c b/hw/vhost.c
index 38cc3b365b..0ca3507f44 100644
--- a/hw/vhost.c
+++ b/hw/vhost.c
@@ -607,6 +607,8 @@ int vhost_dev_init(struct vhost_dev *hdev, int devfd, bool force)
     hdev->client.set_memory = vhost_client_set_memory;
     hdev->client.sync_dirty_bitmap = vhost_client_sync_dirty_bitmap;
     hdev->client.migration_log = vhost_client_migration_log;
+    hdev->client.log_start = NULL;
+    hdev->client.log_stop = NULL;
     hdev->mem = qemu_mallocz(offsetof(struct vhost_memory, regions));
     hdev->log = NULL;
     hdev->log_size = 0;
diff --git a/hw/virtio-blk.c b/hw/virtio-blk.c
index ffac5a4d8f..b14fb995e8 100644
--- a/hw/virtio-blk.c
+++ b/hw/virtio-blk.c
@@ -78,7 +78,7 @@ static int virtio_blk_handle_rw_error(VirtIOBlockReq *req, int error,
         req->next = s->rq;
         s->rq = req;
         bdrv_mon_event(s->bs, BDRV_ACTION_STOP, is_read);
-        vm_stop(0);
+        vm_stop(VMSTOP_DISKFULL);
     } else {
         virtio_blk_req_complete(req, VIRTIO_BLK_S_IOERR);
         bdrv_mon_event(s->bs, BDRV_ACTION_REPORT, is_read);
diff --git a/hw/watchdog.c b/hw/watchdog.c
index e9dd56e229..1c900a1189 100644
--- a/hw/watchdog.c
+++ b/hw/watchdog.c
@@ -132,7 +132,7 @@ void watchdog_perform_action(void)
 
     case WDT_PAUSE:             /* same as 'stop' command in monitor */
         watchdog_mon_event("pause");
-        vm_stop(0);
+        vm_stop(VMSTOP_WATCHDOG);
         break;
 
     case WDT_DEBUG: