Merge remote-tracking branch 'sstabellini/for_1.1_rc3' into staging

* sstabellini/for_1.1_rc3:
  Call xc_domain_shutdown with the reboot flag when the guest requests a reboot.
  xen: Fix PV-on-HVM
  xen_disk: properly update stats in ioreq_release()
  xen_disk: use bdrv_aio_flush instead of bdrv_flush
  xen_disk: remove syncwrite option
  xen: disable rtc_clock
  xen: do not initialize the interval timer and PCSPK emulator

4 files changed, 56 insertions, 33 deletions

diff --git a/hw/pc.c b/hw/pc.c
index 967c17a3f..e81a06c16 100644
--- a/hw/pc.c
+++ b/hw/pc.c
@@ -47,6 +47,7 @@
 #include "ui/qemu-spice.h"
 #include "memory.h"
 #include "exec-memory.h"
+#include "arch_init.h"
 
 /* output Bochs bios info messages */
 //#define DEBUG_BIOS
@@ -1097,7 +1098,7 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,
     qemu_irq pit_alt_irq = NULL;
     qemu_irq rtc_irq = NULL;
     qemu_irq *a20_line;
-    ISADevice *i8042, *port92, *vmmouse, *pit;
+    ISADevice *i8042, *port92, *vmmouse, *pit = NULL;
     qemu_irq *cpu_exit_irq;
 
     register_ioport_write(0x80, 1, 1, ioport80_write, NULL);
@@ -1126,16 +1127,18 @@ void pc_basic_device_init(ISABus *isa_bus, qemu_irq *gsi,
 
     qemu_register_boot_set(pc_boot_set, *rtc_state);
 
-    if (kvm_irqchip_in_kernel()) {
-        pit = kvm_pit_init(isa_bus, 0x40);
-    } else {
-        pit = pit_init(isa_bus, 0x40, pit_isa_irq, pit_alt_irq);
-    }
-    if (hpet) {
-        /* connect PIT to output control line of the HPET */
-        qdev_connect_gpio_out(hpet, 0, qdev_get_gpio_in(&pit->qdev, 0));
+    if (!xen_enabled()) {
+        if (kvm_irqchip_in_kernel()) {
+            pit = kvm_pit_init(isa_bus, 0x40);
+        } else {
+            pit = pit_init(isa_bus, 0x40, pit_isa_irq, pit_alt_irq);
+        }
+        if (hpet) {
+            /* connect PIT to output control line of the HPET */
+            qdev_connect_gpio_out(hpet, 0, qdev_get_gpio_in(&pit->qdev, 0));
+        }
+        pcspk_init(isa_bus, pit);
     }
-    pcspk_init(isa_bus, pit);
 
     for(i = 0; i < MAX_SERIAL_PORTS; i++) {
         if (serial_hds[i]) {
diff --git a/hw/xen_common.h b/hw/xen_common.h
index 7043c14ca..fe7f227f9 100644
--- a/hw/xen_common.h
+++ b/hw/xen_common.h
@@ -148,6 +148,6 @@ static inline int xen_xc_hvm_inject_msi(XenXC xen_xc, domid_t dom,
 }
 #endif
 
-void destroy_hvm_domain(void);
+void destroy_hvm_domain(bool reboot);
 
 #endif /* QEMU_HW_XEN_COMMON_H */
diff --git a/hw/xen_disk.c b/hw/xen_disk.c
index 22dbd1030..07594bc0c 100644
--- a/hw/xen_disk.c
+++ b/hw/xen_disk.c
@@ -48,7 +48,6 @@
 
 /* ------------------------------------------------------------- */
 
-static int syncwrite    = 0;
 static int batch_maps   = 0;
 
 static int max_requests = 32;
@@ -67,6 +66,7 @@ struct ioreq {
     QEMUIOVector        v;
     int                 presync;
     int                 postsync;
+    uint8_t             mapped;
 
     /* grant mapping */
     uint32_t            domids[BLKIF_MAX_SEGMENTS_PER_REQUEST];
@@ -154,7 +154,7 @@ static void ioreq_finish(struct ioreq *ioreq)
     blkdev->requests_finished++;
 }
 
-static void ioreq_release(struct ioreq *ioreq)
+static void ioreq_release(struct ioreq *ioreq, bool finish)
 {
     struct XenBlkDev *blkdev = ioreq->blkdev;
 
@@ -162,7 +162,11 @@ static void ioreq_release(struct ioreq *ioreq)
     memset(ioreq, 0, sizeof(*ioreq));
     ioreq->blkdev = blkdev;
     QLIST_INSERT_HEAD(&blkdev->freelist, ioreq, list);
-    blkdev->requests_finished--;
+    if (finish) {
+        blkdev->requests_finished--;
+    } else {
+        blkdev->requests_inflight--;
+    }
 }
 
 /*
@@ -189,15 +193,10 @@ static int ioreq_parse(struct ioreq *ioreq)
             ioreq->presync = 1;
             return 0;
         }
-        if (!syncwrite) {
-            ioreq->presync = ioreq->postsync = 1;
-        }
+        ioreq->presync = ioreq->postsync = 1;
         /* fall through */
     case BLKIF_OP_WRITE:
         ioreq->prot = PROT_READ; /* from memory */
-        if (syncwrite) {
-            ioreq->postsync = 1;
-        }
         break;
     default:
         xen_be_printf(&blkdev->xendev, 0, "error: unknown operation (%d)\n",
@@ -248,7 +247,7 @@ static void ioreq_unmap(struct ioreq *ioreq)
     XenGnttab gnt = ioreq->blkdev->xendev.gnttabdev;
     int i;
 
-    if (ioreq->v.niov == 0) {
+    if (ioreq->v.niov == 0 || ioreq->mapped == 0) {
         return;
     }
     if (batch_maps) {
@@ -274,6 +273,7 @@ static void ioreq_unmap(struct ioreq *ioreq)
             ioreq->page[i] = NULL;
         }
     }
+    ioreq->mapped = 0;
 }
 
 static int ioreq_map(struct ioreq *ioreq)
@@ -281,7 +281,7 @@ static int ioreq_map(struct ioreq *ioreq)
     XenGnttab gnt = ioreq->blkdev->xendev.gnttabdev;
     int i;
 
-    if (ioreq->v.niov == 0) {
+    if (ioreq->v.niov == 0 || ioreq->mapped == 1) {
         return 0;
     }
     if (batch_maps) {
@@ -313,9 +313,12 @@ static int ioreq_map(struct ioreq *ioreq)
             ioreq->blkdev->cnt_map++;
         }
     }
+    ioreq->mapped = 1;
     return 0;
 }
 
+static int ioreq_runio_qemu_aio(struct ioreq *ioreq);
+
 static void qemu_aio_complete(void *opaque, int ret)
 {
     struct ioreq *ioreq = opaque;
@@ -327,11 +330,19 @@ static void qemu_aio_complete(void *opaque, int ret)
     }
 
     ioreq->aio_inflight--;
+    if (ioreq->presync) {
+        ioreq->presync = 0;
+        ioreq_runio_qemu_aio(ioreq);
+        return;
+    }
     if (ioreq->aio_inflight > 0) {
         return;
     }
     if (ioreq->postsync) {
-        bdrv_flush(ioreq->blkdev->bs);
+        ioreq->postsync = 0;
+        ioreq->aio_inflight++;
+        bdrv_aio_flush(ioreq->blkdev->bs, qemu_aio_complete, ioreq);
+        return;
     }
 
     ioreq->status = ioreq->aio_errors ? BLKIF_RSP_ERROR : BLKIF_RSP_OKAY;
@@ -351,7 +362,8 @@ static int ioreq_runio_qemu_aio(struct ioreq *ioreq)
 
     ioreq->aio_inflight++;
     if (ioreq->presync) {
-        bdrv_flush(blkdev->bs); /* FIXME: aio_flush() ??? */
+        bdrv_aio_flush(ioreq->blkdev->bs, qemu_aio_complete, ioreq);
+        return 0;
     }
 
     switch (ioreq->req.operation) {
@@ -449,7 +461,7 @@ static void blk_send_response_all(struct XenBlkDev *blkdev)
     while (!QLIST_EMPTY(&blkdev->finished)) {
         ioreq = QLIST_FIRST(&blkdev->finished);
         send_notify += blk_send_response_one(ioreq);
-        ioreq_release(ioreq);
+        ioreq_release(ioreq, true);
     }
     if (send_notify) {
         xen_be_send_notify(&blkdev->xendev);
@@ -505,7 +517,7 @@ static void blk_handle_requests(struct XenBlkDev *blkdev)
             if (blk_send_response_one(ioreq)) {
                 xen_be_send_notify(&blkdev->xendev);
             }
-            ioreq_release(ioreq);
+            ioreq_release(ioreq, false);
             continue;
         }
 
diff --git a/xen-all.c b/xen-all.c
index bdf9c0fc7..b5220cc6a 100644
--- a/xen-all.c
+++ b/xen-all.c
@@ -603,6 +603,10 @@ void xen_vcpu_init(void)
         qemu_register_reset(xen_reset_vcpu, first_cpu);
         xen_reset_vcpu(first_cpu);
     }
+    /* if rtc_clock is left to default (host_clock), disable it */
+    if (rtc_clock == host_clock) {
+        qemu_clock_enable(rtc_clock, false);
+    }
 }
 
 /* get the ioreq packets from share mem */
@@ -856,7 +860,7 @@ static void cpu_handle_ioreq(void *opaque)
                     "data: %"PRIx64", count: %" FMT_ioreq_size ", size: %" FMT_ioreq_size "\n",
                     req->state, req->data_is_ptr, req->addr,
                     req->data, req->count, req->size);
-            destroy_hvm_domain();
+            destroy_hvm_domain(false);
             return;
         }
 
@@ -870,10 +874,11 @@ static void cpu_handle_ioreq(void *opaque)
          */
         if (runstate_is_running()) {
             if (qemu_shutdown_requested_get()) {
-                destroy_hvm_domain();
+                destroy_hvm_domain(false);
             }
             if (qemu_reset_requested_get()) {
                 qemu_system_reset(VMRESET_REPORT);
+                destroy_hvm_domain(true);
             }
         }
 
@@ -1159,7 +1164,7 @@ int xen_hvm_init(void)
     return 0;
 }
 
-void destroy_hvm_domain(void)
+void destroy_hvm_domain(bool reboot)
 {
     XenXC xc_handle;
     int sts;
@@ -1168,12 +1173,15 @@ void destroy_hvm_domain(void)
     if (xc_handle == XC_HANDLER_INITIAL_VALUE) {
         fprintf(stderr, "Cannot acquire xenctrl handle\n");
     } else {
-        sts = xc_domain_shutdown(xc_handle, xen_domid, SHUTDOWN_poweroff);
+        sts = xc_domain_shutdown(xc_handle, xen_domid,
+                                 reboot ? SHUTDOWN_reboot : SHUTDOWN_poweroff);
         if (sts != 0) {
-            fprintf(stderr, "? xc_domain_shutdown failed to issue poweroff, "
-                    "sts %d, %s\n", sts, strerror(errno));
+            fprintf(stderr, "xc_domain_shutdown failed to issue %s, "
+                    "sts %d, %s\n", reboot ? "reboot" : "poweroff",
+                    sts, strerror(errno));
         } else {
-            fprintf(stderr, "Issued domain %d poweroff\n", xen_domid);
+            fprintf(stderr, "Issued domain %d %s\n", xen_domid,
+                    reboot ? "reboot" : "poweroff");
         }
         xc_interface_close(xc_handle);
     }