summary refs log tree commit diff stats
path: root/hw
diff options
context:
space:
mode:
Diffstat (limited to 'hw')
-rw-r--r--hw/core/qdev-properties-system.c5
-rw-r--r--hw/display/Makefile.objs2
-rw-r--r--hw/display/vga-pci.c97
-rw-r--r--hw/display/virtio-gpu.c918
-rw-r--r--hw/net/pcnet.c8
-rw-r--r--hw/nvram/fw_cfg.c55
-rw-r--r--hw/ppc/mac_newworld.c2
-rw-r--r--hw/ppc/mac_oldworld.c2
-rw-r--r--hw/s390x/virtio-ccw.c60
-rw-r--r--hw/s390x/virtio-ccw.h18
-rw-r--r--hw/sparc/sun4m.c2
-rw-r--r--hw/sparc64/sun4u.c2
-rw-r--r--hw/vfio/Makefile.objs2
-rw-r--r--hw/vfio/calxeda-xgmac.c55
-rw-r--r--hw/vfio/platform.c615
15 files changed, 1750 insertions, 93 deletions
diff --git a/hw/core/qdev-properties-system.c b/hw/core/qdev-properties-system.c
index c413226a97..0309fe5767 100644
--- a/hw/core/qdev-properties-system.c
+++ b/hw/core/qdev-properties-system.c
@@ -389,7 +389,7 @@ void qdev_set_nic_properties(DeviceState *dev, NICInfo *nd)
     nd->instantiated = 1;
 }
 
-static int qdev_add_one_global(QemuOpts *opts, void *opaque)
+static int qdev_add_one_global(void *opaque, QemuOpts *opts, Error **errp)
 {
     GlobalProperty *g;
 
@@ -404,5 +404,6 @@ static int qdev_add_one_global(QemuOpts *opts, void *opaque)
 
 void qemu_add_globals(void)
 {
-    qemu_opts_foreach(qemu_find_opts("global"), qdev_add_one_global, NULL, 0);
+    qemu_opts_foreach(qemu_find_opts("global"),
+                      qdev_add_one_global, NULL, NULL);
 }
diff --git a/hw/display/Makefile.objs b/hw/display/Makefile.objs
index 3ea106d9f3..61c80f319d 100644
--- a/hw/display/Makefile.objs
+++ b/hw/display/Makefile.objs
@@ -34,3 +34,5 @@ obj-$(CONFIG_CG3) += cg3.o
 obj-$(CONFIG_VGA) += vga.o
 
 common-obj-$(CONFIG_QXL) += qxl.o qxl-logger.o qxl-render.o
+
+obj-$(CONFIG_VIRTIO) += virtio-gpu.o
diff --git a/hw/display/vga-pci.c b/hw/display/vga-pci.c
index ff5dfb2c23..0ed44c7831 100644
--- a/hw/display/vga-pci.c
+++ b/hw/display/vga-pci.c
@@ -54,9 +54,7 @@ typedef struct PCIVGAState {
     VGACommonState vga;
     uint32_t flags;
     MemoryRegion mmio;
-    MemoryRegion ioport;
-    MemoryRegion bochs;
-    MemoryRegion qext;
+    MemoryRegion mrs[3];
 } PCIVGAState;
 
 #define TYPE_PCI_VGA "pci-vga"
@@ -76,16 +74,16 @@ static const VMStateDescription vmstate_vga_pci = {
 static uint64_t pci_vga_ioport_read(void *ptr, hwaddr addr,
                                     unsigned size)
 {
-    PCIVGAState *d = ptr;
+    VGACommonState *s = ptr;
     uint64_t ret = 0;
 
     switch (size) {
     case 1:
-        ret = vga_ioport_read(&d->vga, addr);
+        ret = vga_ioport_read(s, addr + 0x3c0);
         break;
     case 2:
-        ret  = vga_ioport_read(&d->vga, addr);
-        ret |= vga_ioport_read(&d->vga, addr+1) << 8;
+        ret  = vga_ioport_read(s, addr + 0x3c0);
+        ret |= vga_ioport_read(s, addr + 0x3c1) << 8;
         break;
     }
     return ret;
@@ -94,11 +92,11 @@ static uint64_t pci_vga_ioport_read(void *ptr, hwaddr addr,
 static void pci_vga_ioport_write(void *ptr, hwaddr addr,
                                  uint64_t val, unsigned size)
 {
-    PCIVGAState *d = ptr;
+    VGACommonState *s = ptr;
 
     switch (size) {
     case 1:
-        vga_ioport_write(&d->vga, addr + 0x3c0, val);
+        vga_ioport_write(s, addr + 0x3c0, val);
         break;
     case 2:
         /*
@@ -106,8 +104,8 @@ static void pci_vga_ioport_write(void *ptr, hwaddr addr,
          * indexed registers with a single word write because the
          * index byte is updated first.
          */
-        vga_ioport_write(&d->vga, addr + 0x3c0, val & 0xff);
-        vga_ioport_write(&d->vga, addr + 0x3c1, (val >> 8) & 0xff);
+        vga_ioport_write(s, addr + 0x3c0, val & 0xff);
+        vga_ioport_write(s, addr + 0x3c1, (val >> 8) & 0xff);
         break;
     }
 }
@@ -125,21 +123,21 @@ static const MemoryRegionOps pci_vga_ioport_ops = {
 static uint64_t pci_vga_bochs_read(void *ptr, hwaddr addr,
                                    unsigned size)
 {
-    PCIVGAState *d = ptr;
+    VGACommonState *s = ptr;
     int index = addr >> 1;
 
-    vbe_ioport_write_index(&d->vga, 0, index);
-    return vbe_ioport_read_data(&d->vga, 0);
+    vbe_ioport_write_index(s, 0, index);
+    return vbe_ioport_read_data(s, 0);
 }
 
 static void pci_vga_bochs_write(void *ptr, hwaddr addr,
                                 uint64_t val, unsigned size)
 {
-    PCIVGAState *d = ptr;
+    VGACommonState *s = ptr;
     int index = addr >> 1;
 
-    vbe_ioport_write_index(&d->vga, 0, index);
-    vbe_ioport_write_data(&d->vga, 0, val);
+    vbe_ioport_write_index(s, 0, index);
+    vbe_ioport_write_data(s, 0, val);
 }
 
 static const MemoryRegionOps pci_vga_bochs_ops = {
@@ -154,13 +152,13 @@ static const MemoryRegionOps pci_vga_bochs_ops = {
 
 static uint64_t pci_vga_qext_read(void *ptr, hwaddr addr, unsigned size)
 {
-    PCIVGAState *d = ptr;
+    VGACommonState *s = ptr;
 
     switch (addr) {
     case PCI_VGA_QEXT_REG_SIZE:
         return PCI_VGA_QEXT_SIZE;
     case PCI_VGA_QEXT_REG_BYTEORDER:
-        return d->vga.big_endian_fb ?
+        return s->big_endian_fb ?
             PCI_VGA_QEXT_BIG_ENDIAN : PCI_VGA_QEXT_LITTLE_ENDIAN;
     default:
         return 0;
@@ -170,15 +168,15 @@ static uint64_t pci_vga_qext_read(void *ptr, hwaddr addr, unsigned size)
 static void pci_vga_qext_write(void *ptr, hwaddr addr,
                                uint64_t val, unsigned size)
 {
-    PCIVGAState *d = ptr;
+    VGACommonState *s = ptr;
 
     switch (addr) {
     case PCI_VGA_QEXT_REG_BYTEORDER:
         if (val == PCI_VGA_QEXT_BIG_ENDIAN) {
-            d->vga.big_endian_fb = true;
+            s->big_endian_fb = true;
         }
         if (val == PCI_VGA_QEXT_LITTLE_ENDIAN) {
-            d->vga.big_endian_fb = false;
+            s->big_endian_fb = false;
         }
         break;
     }
@@ -206,10 +204,34 @@ static const MemoryRegionOps pci_vga_qext_ops = {
     .endianness = DEVICE_LITTLE_ENDIAN,
 };
 
+static void pci_std_vga_mmio_region_init(VGACommonState *s,
+                                         MemoryRegion *parent,
+                                         MemoryRegion *subs,
+                                         bool qext)
+{
+    memory_region_init_io(&subs[0], NULL, &pci_vga_ioport_ops, s,
+                          "vga ioports remapped", PCI_VGA_IOPORT_SIZE);
+    memory_region_add_subregion(parent, PCI_VGA_IOPORT_OFFSET,
+                                &subs[0]);
+
+    memory_region_init_io(&subs[1], NULL, &pci_vga_bochs_ops, s,
+                          "bochs dispi interface", PCI_VGA_BOCHS_SIZE);
+    memory_region_add_subregion(parent, PCI_VGA_BOCHS_OFFSET,
+                                &subs[1]);
+
+    if (qext) {
+        memory_region_init_io(&subs[2], NULL, &pci_vga_qext_ops, s,
+                              "qemu extended regs", PCI_VGA_QEXT_SIZE);
+        memory_region_add_subregion(parent, PCI_VGA_QEXT_OFFSET,
+                                    &subs[2]);
+    }
+}
+
 static void pci_std_vga_realize(PCIDevice *dev, Error **errp)
 {
     PCIVGAState *d = PCI_VGA(dev);
     VGACommonState *s = &d->vga;
+    bool qext = false;
 
     /* vga + console init */
     vga_common_init(s, OBJECT(dev), true);
@@ -224,23 +246,12 @@ static void pci_std_vga_realize(PCIDevice *dev, Error **errp)
     /* mmio bar for vga register access */
     if (d->flags & (1 << PCI_VGA_FLAG_ENABLE_MMIO)) {
         memory_region_init(&d->mmio, NULL, "vga.mmio", 4096);
-        memory_region_init_io(&d->ioport, NULL, &pci_vga_ioport_ops, d,
-                              "vga ioports remapped", PCI_VGA_IOPORT_SIZE);
-        memory_region_init_io(&d->bochs, NULL, &pci_vga_bochs_ops, d,
-                              "bochs dispi interface", PCI_VGA_BOCHS_SIZE);
-
-        memory_region_add_subregion(&d->mmio, PCI_VGA_IOPORT_OFFSET,
-                                    &d->ioport);
-        memory_region_add_subregion(&d->mmio, PCI_VGA_BOCHS_OFFSET,
-                                    &d->bochs);
 
         if (d->flags & (1 << PCI_VGA_FLAG_ENABLE_QEXT)) {
-            memory_region_init_io(&d->qext, NULL, &pci_vga_qext_ops, d,
-                                  "qemu extended regs", PCI_VGA_QEXT_SIZE);
-            memory_region_add_subregion(&d->mmio, PCI_VGA_QEXT_OFFSET,
-                                        &d->qext);
+            qext = true;
             pci_set_byte(&d->dev.config[PCI_REVISION_ID], 2);
         }
+        pci_std_vga_mmio_region_init(s, &d->mmio, d->mrs, qext);
 
         pci_register_bar(&d->dev, 2, PCI_BASE_ADDRESS_SPACE_MEMORY, &d->mmio);
     }
@@ -262,6 +273,7 @@ static void pci_secondary_vga_realize(PCIDevice *dev, Error **errp)
 {
     PCIVGAState *d = PCI_VGA(dev);
     VGACommonState *s = &d->vga;
+    bool qext = false;
 
     /* vga + console init */
     vga_common_init(s, OBJECT(dev), false);
@@ -269,23 +281,12 @@ static void pci_secondary_vga_realize(PCIDevice *dev, Error **errp)
 
     /* mmio bar */
     memory_region_init(&d->mmio, OBJECT(dev), "vga.mmio", 4096);
-    memory_region_init_io(&d->ioport, OBJECT(dev), &pci_vga_ioport_ops, d,
-                          "vga ioports remapped", PCI_VGA_IOPORT_SIZE);
-    memory_region_init_io(&d->bochs, OBJECT(dev), &pci_vga_bochs_ops, d,
-                          "bochs dispi interface", PCI_VGA_BOCHS_SIZE);
-
-    memory_region_add_subregion(&d->mmio, PCI_VGA_IOPORT_OFFSET,
-                                &d->ioport);
-    memory_region_add_subregion(&d->mmio, PCI_VGA_BOCHS_OFFSET,
-                                &d->bochs);
 
     if (d->flags & (1 << PCI_VGA_FLAG_ENABLE_QEXT)) {
-        memory_region_init_io(&d->qext, NULL, &pci_vga_qext_ops, d,
-                              "qemu extended regs", PCI_VGA_QEXT_SIZE);
-        memory_region_add_subregion(&d->mmio, PCI_VGA_QEXT_OFFSET,
-                                    &d->qext);
+        qext = true;
         pci_set_byte(&d->dev.config[PCI_REVISION_ID], 2);
     }
+    pci_std_vga_mmio_region_init(s, &d->mmio, d->mrs, qext);
 
     pci_register_bar(&d->dev, 0, PCI_BASE_ADDRESS_MEM_PREFETCH, &s->vram);
     pci_register_bar(&d->dev, 2, PCI_BASE_ADDRESS_SPACE_MEMORY, &d->mmio);
diff --git a/hw/display/virtio-gpu.c b/hw/display/virtio-gpu.c
new file mode 100644
index 0000000000..4b10ca1ebb
--- /dev/null
+++ b/hw/display/virtio-gpu.c
@@ -0,0 +1,918 @@
+/*
+ * Virtio GPU Device
+ *
+ * Copyright Red Hat, Inc. 2013-2014
+ *
+ * Authors:
+ *     Dave Airlie <airlied@redhat.com>
+ *     Gerd Hoffmann <kraxel@redhat.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 "qemu/iov.h"
+#include "ui/console.h"
+#include "trace.h"
+#include "hw/virtio/virtio.h"
+#include "hw/virtio/virtio-gpu.h"
+#include "hw/virtio/virtio-bus.h"
+
+static struct virtio_gpu_simple_resource*
+virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id);
+
+static void update_cursor_data_simple(VirtIOGPU *g,
+                                      struct virtio_gpu_scanout *s,
+                                      uint32_t resource_id)
+{
+    struct virtio_gpu_simple_resource *res;
+    uint32_t pixels;
+
+    res = virtio_gpu_find_resource(g, resource_id);
+    if (!res) {
+        return;
+    }
+
+    if (pixman_image_get_width(res->image)  != s->current_cursor->width ||
+        pixman_image_get_height(res->image) != s->current_cursor->height) {
+        return;
+    }
+
+    pixels = s->current_cursor->width * s->current_cursor->height;
+    memcpy(s->current_cursor->data,
+           pixman_image_get_data(res->image),
+           pixels * sizeof(uint32_t));
+}
+
+static void update_cursor(VirtIOGPU *g, struct virtio_gpu_update_cursor *cursor)
+{
+    struct virtio_gpu_scanout *s;
+
+    if (cursor->pos.scanout_id >= g->conf.max_outputs) {
+        return;
+    }
+    s = &g->scanout[cursor->pos.scanout_id];
+
+    if (cursor->hdr.type != VIRTIO_GPU_CMD_MOVE_CURSOR) {
+        if (!s->current_cursor) {
+            s->current_cursor = cursor_alloc(64, 64);
+        }
+
+        s->current_cursor->hot_x = cursor->hot_x;
+        s->current_cursor->hot_y = cursor->hot_y;
+
+        if (cursor->resource_id > 0) {
+            update_cursor_data_simple(g, s, cursor->resource_id);
+        }
+        dpy_cursor_define(s->con, s->current_cursor);
+    }
+    dpy_mouse_set(s->con, cursor->pos.x, cursor->pos.y,
+                  cursor->resource_id ? 1 : 0);
+}
+
+static void virtio_gpu_get_config(VirtIODevice *vdev, uint8_t *config)
+{
+    VirtIOGPU *g = VIRTIO_GPU(vdev);
+    memcpy(config, &g->virtio_config, sizeof(g->virtio_config));
+}
+
+static void virtio_gpu_set_config(VirtIODevice *vdev, const uint8_t *config)
+{
+    VirtIOGPU *g = VIRTIO_GPU(vdev);
+    struct virtio_gpu_config vgconfig;
+
+    memcpy(&vgconfig, config, sizeof(g->virtio_config));
+
+    if (vgconfig.events_clear) {
+        g->virtio_config.events_read &= ~vgconfig.events_clear;
+    }
+}
+
+static uint64_t virtio_gpu_get_features(VirtIODevice *vdev, uint64_t features)
+{
+    return features;
+}
+
+static void virtio_gpu_notify_event(VirtIOGPU *g, uint32_t event_type)
+{
+    g->virtio_config.events_read |= event_type;
+    virtio_notify_config(&g->parent_obj);
+}
+
+static struct virtio_gpu_simple_resource *
+virtio_gpu_find_resource(VirtIOGPU *g, uint32_t resource_id)
+{
+    struct virtio_gpu_simple_resource *res;
+
+    QTAILQ_FOREACH(res, &g->reslist, next) {
+        if (res->resource_id == resource_id) {
+            return res;
+        }
+    }
+    return NULL;
+}
+
+void virtio_gpu_ctrl_response(VirtIOGPU *g,
+                              struct virtio_gpu_ctrl_command *cmd,
+                              struct virtio_gpu_ctrl_hdr *resp,
+                              size_t resp_len)
+{
+    size_t s;
+
+    if (cmd->cmd_hdr.flags & VIRTIO_GPU_FLAG_FENCE) {
+        resp->flags |= VIRTIO_GPU_FLAG_FENCE;
+        resp->fence_id = cmd->cmd_hdr.fence_id;
+        resp->ctx_id = cmd->cmd_hdr.ctx_id;
+    }
+    s = iov_from_buf(cmd->elem.in_sg, cmd->elem.in_num, 0, resp, resp_len);
+    if (s != resp_len) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: response size incorrect %zu vs %zu\n",
+                      __func__, s, resp_len);
+    }
+    virtqueue_push(cmd->vq, &cmd->elem, s);
+    virtio_notify(VIRTIO_DEVICE(g), cmd->vq);
+    cmd->finished = true;
+}
+
+void virtio_gpu_ctrl_response_nodata(VirtIOGPU *g,
+                                     struct virtio_gpu_ctrl_command *cmd,
+                                     enum virtio_gpu_ctrl_type type)
+{
+    struct virtio_gpu_ctrl_hdr resp;
+
+    memset(&resp, 0, sizeof(resp));
+    resp.type = type;
+    virtio_gpu_ctrl_response(g, cmd, &resp, sizeof(resp));
+}
+
+static void
+virtio_gpu_fill_display_info(VirtIOGPU *g,
+                             struct virtio_gpu_resp_display_info *dpy_info)
+{
+    int i;
+
+    for (i = 0; i < g->conf.max_outputs; i++) {
+        if (g->enabled_output_bitmask & (1 << i)) {
+            dpy_info->pmodes[i].enabled = 1;
+            dpy_info->pmodes[i].r.width = g->req_state[i].width;
+            dpy_info->pmodes[i].r.height = g->req_state[i].height;
+        }
+    }
+}
+
+void virtio_gpu_get_display_info(VirtIOGPU *g,
+                                 struct virtio_gpu_ctrl_command *cmd)
+{
+    struct virtio_gpu_resp_display_info display_info;
+
+    trace_virtio_gpu_cmd_get_display_info();
+    memset(&display_info, 0, sizeof(display_info));
+    display_info.hdr.type = VIRTIO_GPU_RESP_OK_DISPLAY_INFO;
+    virtio_gpu_fill_display_info(g, &display_info);
+    virtio_gpu_ctrl_response(g, cmd, &display_info.hdr,
+                             sizeof(display_info));
+}
+
+static pixman_format_code_t get_pixman_format(uint32_t virtio_gpu_format)
+{
+    switch (virtio_gpu_format) {
+#ifdef HOST_WORDS_BIGENDIAN
+    case VIRTIO_GPU_FORMAT_B8G8R8X8_UNORM:
+        return PIXMAN_b8g8r8x8;
+    case VIRTIO_GPU_FORMAT_B8G8R8A8_UNORM:
+        return PIXMAN_b8g8r8a8;
+    case VIRTIO_GPU_FORMAT_X8R8G8B8_UNORM:
+        return PIXMAN_x8r8g8b8;
+    case VIRTIO_GPU_FORMAT_A8R8G8B8_UNORM:
+        return PIXMAN_a8r8g8b8;
+    case VIRTIO_GPU_FORMAT_R8G8B8X8_UNORM:
+        return PIXMAN_r8g8b8x8;
+    case VIRTIO_GPU_FORMAT_R8G8B8A8_UNORM:
+        return PIXMAN_r8g8b8a8;
+    case VIRTIO_GPU_FORMAT_X8B8G8R8_UNORM:
+        return PIXMAN_x8b8g8r8;
+    case VIRTIO_GPU_FORMAT_A8B8G8R8_UNORM:
+        return PIXMAN_a8b8g8r8;
+#else
+    case VIRTIO_GPU_FORMAT_B8G8R8X8_UNORM:
+        return PIXMAN_x8r8g8b8;
+    case VIRTIO_GPU_FORMAT_B8G8R8A8_UNORM:
+        return PIXMAN_a8r8g8b8;
+    case VIRTIO_GPU_FORMAT_X8R8G8B8_UNORM:
+        return PIXMAN_b8g8r8x8;
+    case VIRTIO_GPU_FORMAT_A8R8G8B8_UNORM:
+        return PIXMAN_b8g8r8a8;
+    case VIRTIO_GPU_FORMAT_R8G8B8X8_UNORM:
+        return PIXMAN_x8b8g8r8;
+    case VIRTIO_GPU_FORMAT_R8G8B8A8_UNORM:
+        return PIXMAN_a8b8g8r8;
+    case VIRTIO_GPU_FORMAT_X8B8G8R8_UNORM:
+        return PIXMAN_r8g8b8x8;
+    case VIRTIO_GPU_FORMAT_A8B8G8R8_UNORM:
+        return PIXMAN_r8g8b8a8;
+#endif
+    default:
+        return 0;
+    }
+}
+
+static void virtio_gpu_resource_create_2d(VirtIOGPU *g,
+                                          struct virtio_gpu_ctrl_command *cmd)
+{
+    pixman_format_code_t pformat;
+    struct virtio_gpu_simple_resource *res;
+    struct virtio_gpu_resource_create_2d c2d;
+
+    VIRTIO_GPU_FILL_CMD(c2d);
+    trace_virtio_gpu_cmd_res_create_2d(c2d.resource_id, c2d.format,
+                                       c2d.width, c2d.height);
+
+    if (c2d.resource_id == 0) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: resource id 0 is not allowed\n",
+                      __func__);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+
+    res = virtio_gpu_find_resource(g, c2d.resource_id);
+    if (res) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: resource already exists %d\n",
+                      __func__, c2d.resource_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+
+    res = g_new0(struct virtio_gpu_simple_resource, 1);
+
+    res->width = c2d.width;
+    res->height = c2d.height;
+    res->format = c2d.format;
+    res->resource_id = c2d.resource_id;
+
+    pformat = get_pixman_format(c2d.format);
+    if (!pformat) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: host couldn't handle guest format %d\n",
+                      __func__, c2d.format);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER;
+        return;
+    }
+    res->image = pixman_image_create_bits(pformat,
+                                          c2d.width,
+                                          c2d.height,
+                                          NULL, 0);
+
+    if (!res->image) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: resource creation failed %d %d %d\n",
+                      __func__, c2d.resource_id, c2d.width, c2d.height);
+        g_free(res);
+        cmd->error = VIRTIO_GPU_RESP_ERR_OUT_OF_MEMORY;
+        return;
+    }
+
+    QTAILQ_INSERT_HEAD(&g->reslist, res, next);
+}
+
+static void virtio_gpu_resource_destroy(VirtIOGPU *g,
+                                        struct virtio_gpu_simple_resource *res)
+{
+    pixman_image_unref(res->image);
+    QTAILQ_REMOVE(&g->reslist, res, next);
+    g_free(res);
+}
+
+static void virtio_gpu_resource_unref(VirtIOGPU *g,
+                                      struct virtio_gpu_ctrl_command *cmd)
+{
+    struct virtio_gpu_simple_resource *res;
+    struct virtio_gpu_resource_unref unref;
+
+    VIRTIO_GPU_FILL_CMD(unref);
+    trace_virtio_gpu_cmd_res_unref(unref.resource_id);
+
+    res = virtio_gpu_find_resource(g, unref.resource_id);
+    if (!res) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n",
+                      __func__, unref.resource_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+    virtio_gpu_resource_destroy(g, res);
+}
+
+static void virtio_gpu_transfer_to_host_2d(VirtIOGPU *g,
+                                           struct virtio_gpu_ctrl_command *cmd)
+{
+    struct virtio_gpu_simple_resource *res;
+    int h;
+    uint32_t src_offset, dst_offset, stride;
+    int bpp;
+    pixman_format_code_t format;
+    struct virtio_gpu_transfer_to_host_2d t2d;
+
+    VIRTIO_GPU_FILL_CMD(t2d);
+    trace_virtio_gpu_cmd_res_xfer_toh_2d(t2d.resource_id);
+
+    res = virtio_gpu_find_resource(g, t2d.resource_id);
+    if (!res || !res->iov) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n",
+                      __func__, t2d.resource_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+
+    if (t2d.r.x > res->width ||
+        t2d.r.y > res->height ||
+        t2d.r.width > res->width ||
+        t2d.r.height > res->height ||
+        t2d.r.x + t2d.r.width > res->width ||
+        t2d.r.y + t2d.r.height > res->height) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: transfer bounds outside resource"
+                      " bounds for resource %d: %d %d %d %d vs %d %d\n",
+                      __func__, t2d.resource_id, t2d.r.x, t2d.r.y,
+                      t2d.r.width, t2d.r.height, res->width, res->height);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER;
+        return;
+    }
+
+    format = pixman_image_get_format(res->image);
+    bpp = (PIXMAN_FORMAT_BPP(format) + 7) / 8;
+    stride = pixman_image_get_stride(res->image);
+
+    if (t2d.offset || t2d.r.x || t2d.r.y ||
+        t2d.r.width != pixman_image_get_width(res->image)) {
+        void *img_data = pixman_image_get_data(res->image);
+        for (h = 0; h < t2d.r.height; h++) {
+            src_offset = t2d.offset + stride * h;
+            dst_offset = (t2d.r.y + h) * stride + (t2d.r.x * bpp);
+
+            iov_to_buf(res->iov, res->iov_cnt, src_offset,
+                       (uint8_t *)img_data
+                       + dst_offset, t2d.r.width * bpp);
+        }
+    } else {
+        iov_to_buf(res->iov, res->iov_cnt, 0,
+                   pixman_image_get_data(res->image),
+                   pixman_image_get_stride(res->image)
+                   * pixman_image_get_height(res->image));
+    }
+}
+
+static void virtio_gpu_resource_flush(VirtIOGPU *g,
+                                      struct virtio_gpu_ctrl_command *cmd)
+{
+    struct virtio_gpu_simple_resource *res;
+    struct virtio_gpu_resource_flush rf;
+    pixman_region16_t flush_region;
+    int i;
+
+    VIRTIO_GPU_FILL_CMD(rf);
+    trace_virtio_gpu_cmd_res_flush(rf.resource_id,
+                                   rf.r.width, rf.r.height, rf.r.x, rf.r.y);
+
+    res = virtio_gpu_find_resource(g, rf.resource_id);
+    if (!res) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n",
+                      __func__, rf.resource_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+
+    if (rf.r.x > res->width ||
+        rf.r.y > res->height ||
+        rf.r.width > res->width ||
+        rf.r.height > res->height ||
+        rf.r.x + rf.r.width > res->width ||
+        rf.r.y + rf.r.height > res->height) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: flush bounds outside resource"
+                      " bounds for resource %d: %d %d %d %d vs %d %d\n",
+                      __func__, rf.resource_id, rf.r.x, rf.r.y,
+                      rf.r.width, rf.r.height, res->width, res->height);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER;
+        return;
+    }
+
+    pixman_region_init_rect(&flush_region,
+                            rf.r.x, rf.r.y, rf.r.width, rf.r.height);
+    for (i = 0; i < VIRTIO_GPU_MAX_SCANOUT; i++) {
+        struct virtio_gpu_scanout *scanout;
+        pixman_region16_t region, finalregion;
+        pixman_box16_t *extents;
+
+        if (!(res->scanout_bitmask & (1 << i))) {
+            continue;
+        }
+        scanout = &g->scanout[i];
+
+        pixman_region_init(&finalregion);
+        pixman_region_init_rect(&region, scanout->x, scanout->y,
+                                scanout->width, scanout->height);
+
+        pixman_region_intersect(&finalregion, &flush_region, &region);
+        pixman_region_translate(&finalregion, -scanout->x, -scanout->y);
+        extents = pixman_region_extents(&finalregion);
+        /* work out the area we need to update for each console */
+        dpy_gfx_update(g->scanout[i].con,
+                       extents->x1, extents->y1,
+                       extents->x2 - extents->x1,
+                       extents->y2 - extents->y1);
+
+        pixman_region_fini(&region);
+        pixman_region_fini(&finalregion);
+    }
+    pixman_region_fini(&flush_region);
+}
+
+static void virtio_gpu_set_scanout(VirtIOGPU *g,
+                                   struct virtio_gpu_ctrl_command *cmd)
+{
+    struct virtio_gpu_simple_resource *res;
+    struct virtio_gpu_scanout *scanout;
+    pixman_format_code_t format;
+    uint32_t offset;
+    int bpp;
+    struct virtio_gpu_set_scanout ss;
+
+    VIRTIO_GPU_FILL_CMD(ss);
+    trace_virtio_gpu_cmd_set_scanout(ss.scanout_id, ss.resource_id,
+                                     ss.r.width, ss.r.height, ss.r.x, ss.r.y);
+
+    g->enable = 1;
+    if (ss.resource_id == 0) {
+        scanout = &g->scanout[ss.scanout_id];
+        if (scanout->resource_id) {
+            res = virtio_gpu_find_resource(g, scanout->resource_id);
+            if (res) {
+                res->scanout_bitmask &= ~(1 << ss.scanout_id);
+            }
+        }
+        if (ss.scanout_id == 0 ||
+            ss.scanout_id >= g->conf.max_outputs) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "%s: illegal scanout id specified %d",
+                          __func__, ss.scanout_id);
+            cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_SCANOUT_ID;
+            return;
+        }
+        dpy_gfx_replace_surface(g->scanout[ss.scanout_id].con, NULL);
+        scanout->ds = NULL;
+        scanout->width = 0;
+        scanout->height = 0;
+        return;
+    }
+
+    /* create a surface for this scanout */
+    if (ss.scanout_id >= VIRTIO_GPU_MAX_SCANOUT ||
+        ss.scanout_id >= g->conf.max_outputs) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout id specified %d",
+                      __func__, ss.scanout_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_SCANOUT_ID;
+        return;
+    }
+
+    res = virtio_gpu_find_resource(g, ss.resource_id);
+    if (!res) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n",
+                      __func__, ss.resource_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+
+    if (ss.r.x > res->width ||
+        ss.r.y > res->height ||
+        ss.r.width > res->width ||
+        ss.r.height > res->height ||
+        ss.r.x + ss.r.width > res->width ||
+        ss.r.y + ss.r.height > res->height) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal scanout %d bounds for"
+                      " resource %d, (%d,%d)+%d,%d vs %d %d\n",
+                      __func__, ss.scanout_id, ss.resource_id, ss.r.x, ss.r.y,
+                      ss.r.width, ss.r.height, res->width, res->height);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_PARAMETER;
+        return;
+    }
+
+    scanout = &g->scanout[ss.scanout_id];
+
+    format = pixman_image_get_format(res->image);
+    bpp = (PIXMAN_FORMAT_BPP(format) + 7) / 8;
+    offset = (ss.r.x * bpp) + ss.r.y * pixman_image_get_stride(res->image);
+    if (!scanout->ds || surface_data(scanout->ds)
+        != ((uint8_t *)pixman_image_get_data(res->image) + offset) ||
+        scanout->width != ss.r.width ||
+        scanout->height != ss.r.height) {
+        /* realloc the surface ptr */
+        scanout->ds = qemu_create_displaysurface_from
+            (ss.r.width, ss.r.height, format,
+             pixman_image_get_stride(res->image),
+             (uint8_t *)pixman_image_get_data(res->image) + offset);
+        if (!scanout->ds) {
+            cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC;
+            return;
+        }
+        dpy_gfx_replace_surface(g->scanout[ss.scanout_id].con, scanout->ds);
+    }
+
+    res->scanout_bitmask |= (1 << ss.scanout_id);
+    scanout->resource_id = ss.resource_id;
+    scanout->x = ss.r.x;
+    scanout->y = ss.r.y;
+    scanout->width = ss.r.width;
+    scanout->height = ss.r.height;
+}
+
+int virtio_gpu_create_mapping_iov(struct virtio_gpu_resource_attach_backing *ab,
+                                  struct virtio_gpu_ctrl_command *cmd,
+                                  struct iovec **iov)
+{
+    struct virtio_gpu_mem_entry *ents;
+    size_t esize, s;
+    int i;
+
+    if (ab->nr_entries > 16384) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: nr_entries is too big (%d > 1024)\n",
+                      __func__, ab->nr_entries);
+        return -1;
+    }
+
+    esize = sizeof(*ents) * ab->nr_entries;
+    ents = g_malloc(esize);
+    s = iov_to_buf(cmd->elem.out_sg, cmd->elem.out_num,
+                   sizeof(*ab), ents, esize);
+    if (s != esize) {
+        qemu_log_mask(LOG_GUEST_ERROR,
+                      "%s: command data size incorrect %zu vs %zu\n",
+                      __func__, s, esize);
+        g_free(ents);
+        return -1;
+    }
+
+    *iov = g_malloc0(sizeof(struct iovec) * ab->nr_entries);
+    for (i = 0; i < ab->nr_entries; i++) {
+        hwaddr len = ents[i].length;
+        (*iov)[i].iov_len = ents[i].length;
+        (*iov)[i].iov_base = cpu_physical_memory_map(ents[i].addr, &len, 1);
+        if (!(*iov)[i].iov_base || len != ents[i].length) {
+            qemu_log_mask(LOG_GUEST_ERROR, "%s: failed to map MMIO memory for"
+                          " resource %d element %d\n",
+                          __func__, ab->resource_id, i);
+            virtio_gpu_cleanup_mapping_iov(*iov, i);
+            g_free(ents);
+            g_free(*iov);
+            *iov = NULL;
+            return -1;
+        }
+    }
+    g_free(ents);
+    return 0;
+}
+
+void virtio_gpu_cleanup_mapping_iov(struct iovec *iov, uint32_t count)
+{
+    int i;
+
+    for (i = 0; i < count; i++) {
+        cpu_physical_memory_unmap(iov[i].iov_base, iov[i].iov_len, 1,
+                                  iov[i].iov_len);
+    }
+}
+
+static void virtio_gpu_cleanup_mapping(struct virtio_gpu_simple_resource *res)
+{
+    virtio_gpu_cleanup_mapping_iov(res->iov, res->iov_cnt);
+    g_free(res->iov);
+    res->iov = NULL;
+    res->iov_cnt = 0;
+}
+
+static void
+virtio_gpu_resource_attach_backing(VirtIOGPU *g,
+                                   struct virtio_gpu_ctrl_command *cmd)
+{
+    struct virtio_gpu_simple_resource *res;
+    struct virtio_gpu_resource_attach_backing ab;
+    int ret;
+
+    VIRTIO_GPU_FILL_CMD(ab);
+    trace_virtio_gpu_cmd_res_back_attach(ab.resource_id);
+
+    res = virtio_gpu_find_resource(g, ab.resource_id);
+    if (!res) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n",
+                      __func__, ab.resource_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+
+    ret = virtio_gpu_create_mapping_iov(&ab, cmd, &res->iov);
+    if (ret != 0) {
+        cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC;
+        return;
+    }
+
+    res->iov_cnt = ab.nr_entries;
+}
+
+static void
+virtio_gpu_resource_detach_backing(VirtIOGPU *g,
+                                   struct virtio_gpu_ctrl_command *cmd)
+{
+    struct virtio_gpu_simple_resource *res;
+    struct virtio_gpu_resource_detach_backing detach;
+
+    VIRTIO_GPU_FILL_CMD(detach);
+    trace_virtio_gpu_cmd_res_back_detach(detach.resource_id);
+
+    res = virtio_gpu_find_resource(g, detach.resource_id);
+    if (!res || !res->iov) {
+        qemu_log_mask(LOG_GUEST_ERROR, "%s: illegal resource specified %d\n",
+                      __func__, detach.resource_id);
+        cmd->error = VIRTIO_GPU_RESP_ERR_INVALID_RESOURCE_ID;
+        return;
+    }
+    virtio_gpu_cleanup_mapping(res);
+}
+
+static void virtio_gpu_simple_process_cmd(VirtIOGPU *g,
+                                          struct virtio_gpu_ctrl_command *cmd)
+{
+    VIRTIO_GPU_FILL_CMD(cmd->cmd_hdr);
+
+    switch (cmd->cmd_hdr.type) {
+    case VIRTIO_GPU_CMD_GET_DISPLAY_INFO:
+        virtio_gpu_get_display_info(g, cmd);
+        break;
+    case VIRTIO_GPU_CMD_RESOURCE_CREATE_2D:
+        virtio_gpu_resource_create_2d(g, cmd);
+        break;
+    case VIRTIO_GPU_CMD_RESOURCE_UNREF:
+        virtio_gpu_resource_unref(g, cmd);
+        break;
+    case VIRTIO_GPU_CMD_RESOURCE_FLUSH:
+        virtio_gpu_resource_flush(g, cmd);
+        break;
+    case VIRTIO_GPU_CMD_TRANSFER_TO_HOST_2D:
+        virtio_gpu_transfer_to_host_2d(g, cmd);
+        break;
+    case VIRTIO_GPU_CMD_SET_SCANOUT:
+        virtio_gpu_set_scanout(g, cmd);
+        break;
+    case VIRTIO_GPU_CMD_RESOURCE_ATTACH_BACKING:
+        virtio_gpu_resource_attach_backing(g, cmd);
+        break;
+    case VIRTIO_GPU_CMD_RESOURCE_DETACH_BACKING:
+        virtio_gpu_resource_detach_backing(g, cmd);
+        break;
+    default:
+        cmd->error = VIRTIO_GPU_RESP_ERR_UNSPEC;
+        break;
+    }
+    if (!cmd->finished) {
+        virtio_gpu_ctrl_response_nodata(g, cmd, cmd->error ? cmd->error :
+                                        VIRTIO_GPU_RESP_OK_NODATA);
+    }
+}
+
+static void virtio_gpu_handle_ctrl_cb(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOGPU *g = VIRTIO_GPU(vdev);
+    qemu_bh_schedule(g->ctrl_bh);
+}
+
+static void virtio_gpu_handle_cursor_cb(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOGPU *g = VIRTIO_GPU(vdev);
+    qemu_bh_schedule(g->cursor_bh);
+}
+
+static void virtio_gpu_handle_ctrl(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOGPU *g = VIRTIO_GPU(vdev);
+    struct virtio_gpu_ctrl_command *cmd;
+
+    if (!virtio_queue_ready(vq)) {
+        return;
+    }
+
+    cmd = g_new(struct virtio_gpu_ctrl_command, 1);
+    while (virtqueue_pop(vq, &cmd->elem)) {
+        cmd->vq = vq;
+        cmd->error = 0;
+        cmd->finished = false;
+        g->stats.requests++;
+
+        virtio_gpu_simple_process_cmd(g, cmd);
+        if (!cmd->finished) {
+            QTAILQ_INSERT_TAIL(&g->fenceq, cmd, next);
+            g->stats.inflight++;
+            if (g->stats.max_inflight < g->stats.inflight) {
+                g->stats.max_inflight = g->stats.inflight;
+            }
+            fprintf(stderr, "inflight: %3d (+)\r", g->stats.inflight);
+            cmd = g_new(struct virtio_gpu_ctrl_command, 1);
+        }
+    }
+    g_free(cmd);
+}
+
+static void virtio_gpu_ctrl_bh(void *opaque)
+{
+    VirtIOGPU *g = opaque;
+    virtio_gpu_handle_ctrl(&g->parent_obj, g->ctrl_vq);
+}
+
+static void virtio_gpu_handle_cursor(VirtIODevice *vdev, VirtQueue *vq)
+{
+    VirtIOGPU *g = VIRTIO_GPU(vdev);
+    VirtQueueElement elem;
+    size_t s;
+    struct virtio_gpu_update_cursor cursor_info;
+
+    if (!virtio_queue_ready(vq)) {
+        return;
+    }
+    while (virtqueue_pop(vq, &elem)) {
+        s = iov_to_buf(elem.out_sg, elem.out_num, 0,
+                       &cursor_info, sizeof(cursor_info));
+        if (s != sizeof(cursor_info)) {
+            qemu_log_mask(LOG_GUEST_ERROR,
+                          "%s: cursor size incorrect %zu vs %zu\n",
+                          __func__, s, sizeof(cursor_info));
+        } else {
+            update_cursor(g, &cursor_info);
+        }
+        virtqueue_push(vq, &elem, 0);
+        virtio_notify(vdev, vq);
+    }
+}
+
+static void virtio_gpu_cursor_bh(void *opaque)
+{
+    VirtIOGPU *g = opaque;
+    virtio_gpu_handle_cursor(&g->parent_obj, g->cursor_vq);
+}
+
+static void virtio_gpu_invalidate_display(void *opaque)
+{
+}
+
+static void virtio_gpu_update_display(void *opaque)
+{
+}
+
+static void virtio_gpu_text_update(void *opaque, console_ch_t *chardata)
+{
+}
+
+static int virtio_gpu_ui_info(void *opaque, uint32_t idx, QemuUIInfo *info)
+{
+    VirtIOGPU *g = opaque;
+
+    if (idx > g->conf.max_outputs) {
+        return -1;
+    }
+
+    g->req_state[idx].x = info->xoff;
+    g->req_state[idx].y = info->yoff;
+    g->req_state[idx].width = info->width;
+    g->req_state[idx].height = info->height;
+
+    if (info->width && info->height) {
+        g->enabled_output_bitmask |= (1 << idx);
+    } else {
+        g->enabled_output_bitmask &= ~(1 << idx);
+    }
+
+    /* send event to guest */
+    virtio_gpu_notify_event(g, VIRTIO_GPU_EVENT_DISPLAY);
+    return 0;
+}
+
+const GraphicHwOps virtio_gpu_ops = {
+    .invalidate = virtio_gpu_invalidate_display,
+    .gfx_update = virtio_gpu_update_display,
+    .text_update = virtio_gpu_text_update,
+    .ui_info = virtio_gpu_ui_info,
+};
+
+static void virtio_gpu_device_realize(DeviceState *qdev, Error **errp)
+{
+    VirtIODevice *vdev = VIRTIO_DEVICE(qdev);
+    VirtIOGPU *g = VIRTIO_GPU(qdev);
+    int i;
+
+    g->config_size = sizeof(struct virtio_gpu_config);
+    g->virtio_config.num_scanouts = g->conf.max_outputs;
+    virtio_init(VIRTIO_DEVICE(g), "virtio-gpu", VIRTIO_ID_GPU,
+                g->config_size);
+
+    g->req_state[0].width = 1024;
+    g->req_state[0].height = 768;
+
+    g->ctrl_vq   = virtio_add_queue(vdev, 64, virtio_gpu_handle_ctrl_cb);
+    g->cursor_vq = virtio_add_queue(vdev, 16, virtio_gpu_handle_cursor_cb);
+
+    g->ctrl_bh = qemu_bh_new(virtio_gpu_ctrl_bh, g);
+    g->cursor_bh = qemu_bh_new(virtio_gpu_cursor_bh, g);
+    QTAILQ_INIT(&g->reslist);
+    QTAILQ_INIT(&g->fenceq);
+
+    g->enabled_output_bitmask = 1;
+    g->qdev = qdev;
+
+    for (i = 0; i < g->conf.max_outputs; i++) {
+        g->scanout[i].con =
+            graphic_console_init(DEVICE(g), i, &virtio_gpu_ops, g);
+        if (i > 0) {
+            dpy_gfx_replace_surface(g->scanout[i].con, NULL);
+        }
+    }
+}
+
+static void virtio_gpu_instance_init(Object *obj)
+{
+}
+
+static void virtio_gpu_reset(VirtIODevice *vdev)
+{
+    VirtIOGPU *g = VIRTIO_GPU(vdev);
+    struct virtio_gpu_simple_resource *res, *tmp;
+    int i;
+
+    g->enable = 0;
+
+    QTAILQ_FOREACH_SAFE(res, &g->reslist, next, tmp) {
+        virtio_gpu_resource_destroy(g, res);
+    }
+    for (i = 0; i < g->conf.max_outputs; i++) {
+#if 0
+        g->req_state[i].x = 0;
+        g->req_state[i].y = 0;
+        if (i == 0) {
+            g->req_state[0].width = 1024;
+            g->req_state[0].height = 768;
+        } else {
+            g->req_state[i].width = 0;
+            g->req_state[i].height = 0;
+        }
+#endif
+        g->scanout[i].resource_id = 0;
+        g->scanout[i].width = 0;
+        g->scanout[i].height = 0;
+        g->scanout[i].x = 0;
+        g->scanout[i].y = 0;
+        g->scanout[i].ds = NULL;
+    }
+    g->enabled_output_bitmask = 1;
+}
+
+static Property virtio_gpu_properties[] = {
+    DEFINE_VIRTIO_GPU_PROPERTIES(VirtIOGPU, conf),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void virtio_gpu_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass);
+
+    vdc->realize = virtio_gpu_device_realize;
+    vdc->get_config = virtio_gpu_get_config;
+    vdc->set_config = virtio_gpu_set_config;
+    vdc->get_features = virtio_gpu_get_features;
+
+    vdc->reset = virtio_gpu_reset;
+
+    dc->props = virtio_gpu_properties;
+}
+
+static const TypeInfo virtio_gpu_info = {
+    .name = TYPE_VIRTIO_GPU,
+    .parent = TYPE_VIRTIO_DEVICE,
+    .instance_size = sizeof(VirtIOGPU),
+    .instance_init = virtio_gpu_instance_init,
+    .class_init = virtio_gpu_class_init,
+};
+
+static void virtio_register_types(void)
+{
+    type_register_static(&virtio_gpu_info);
+}
+
+type_init(virtio_register_types)
+
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_ctrl_hdr)                != 24);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_update_cursor)           != 56);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_resource_unref)          != 32);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_resource_create_2d)      != 40);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_set_scanout)             != 48);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_resource_flush)          != 48);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_transfer_to_host_2d)     != 56);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_mem_entry)               != 16);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_resource_attach_backing) != 32);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_resource_detach_backing) != 32);
+QEMU_BUILD_BUG_ON(sizeof(struct virtio_gpu_resp_display_info)       != 408);
diff --git a/hw/net/pcnet.c b/hw/net/pcnet.c
index bdfd38f4ca..68b9981983 100644
--- a/hw/net/pcnet.c
+++ b/hw/net/pcnet.c
@@ -1241,6 +1241,14 @@ static void pcnet_transmit(PCNetState *s)
         }
 
         bcnt = 4096 - GET_FIELD(tmd.length, TMDL, BCNT);
+
+        /* if multi-tmd packet outsizes s->buffer then skip it silently.
+           Note: this is not what real hw does */
+        if (s->xmit_pos + bcnt > sizeof(s->buffer)) {
+            s->xmit_pos = -1;
+            goto txdone;
+        }
+
         s->phys_mem_read(s->dma_opaque, PHYSADDR(s, tmd.tbadr),
                          s->buffer + s->xmit_pos, bcnt, CSR_BSWP(s));
         s->xmit_pos += bcnt;
diff --git a/hw/nvram/fw_cfg.c b/hw/nvram/fw_cfg.c
index 68eff77983..88481b78c4 100644
--- a/hw/nvram/fw_cfg.c
+++ b/hw/nvram/fw_cfg.c
@@ -46,7 +46,6 @@ typedef struct FWCfgEntry {
     uint32_t len;
     uint8_t *data;
     void *callback_opaque;
-    FWCfgCallback callback;
     FWCfgReadCallback read_callback;
 } FWCfgEntry;
 
@@ -232,19 +231,7 @@ static void fw_cfg_reboot(FWCfgState *s)
 
 static void fw_cfg_write(FWCfgState *s, uint8_t value)
 {
-    int arch = !!(s->cur_entry & FW_CFG_ARCH_LOCAL);
-    FWCfgEntry *e = &s->entries[arch][s->cur_entry & FW_CFG_ENTRY_MASK];
-
-    trace_fw_cfg_write(s, value);
-
-    if (s->cur_entry & FW_CFG_WRITE_CHANNEL && e->callback &&
-        s->cur_offset < e->len) {
-        e->data[s->cur_offset++] = value;
-        if (s->cur_offset == e->len) {
-            e->callback(e->callback_opaque, e->data);
-            s->cur_offset = 0;
-        }
-    }
+    /* nothing, write support removed in QEMU v2.4+ */
 }
 
 static int fw_cfg_select(FWCfgState *s, uint16_t key)
@@ -436,6 +423,7 @@ static void fw_cfg_add_bytes_read_callback(FWCfgState *s, uint16_t key,
     key &= FW_CFG_ENTRY_MASK;
 
     assert(key < FW_CFG_MAX_ENTRY && len < UINT32_MAX);
+    assert(s->entries[arch][key].data == NULL); /* avoid key conflict */
 
     s->entries[arch][key].data = data;
     s->entries[arch][key].len = (uint32_t)len;
@@ -458,7 +446,6 @@ static void *fw_cfg_modify_bytes_read(FWCfgState *s, uint16_t key,
     s->entries[arch][key].data = data;
     s->entries[arch][key].len = len;
     s->entries[arch][key].callback_opaque = NULL;
-    s->entries[arch][key].callback = NULL;
 
     return ptr;
 }
@@ -484,6 +471,16 @@ void fw_cfg_add_i16(FWCfgState *s, uint16_t key, uint16_t value)
     fw_cfg_add_bytes(s, key, copy, sizeof(value));
 }
 
+void fw_cfg_modify_i16(FWCfgState *s, uint16_t key, uint16_t value)
+{
+    uint16_t *copy, *old;
+
+    copy = g_malloc(sizeof(value));
+    *copy = cpu_to_le16(value);
+    old = fw_cfg_modify_bytes_read(s, key, copy, sizeof(value));
+    g_free(old);
+}
+
 void fw_cfg_add_i32(FWCfgState *s, uint16_t key, uint32_t value)
 {
     uint32_t *copy;
@@ -502,23 +499,6 @@ void fw_cfg_add_i64(FWCfgState *s, uint16_t key, uint64_t value)
     fw_cfg_add_bytes(s, key, copy, sizeof(value));
 }
 
-void fw_cfg_add_callback(FWCfgState *s, uint16_t key, FWCfgCallback callback,
-                         void *callback_opaque, void *data, size_t len)
-{
-    int arch = !!(key & FW_CFG_ARCH_LOCAL);
-
-    assert(key & FW_CFG_WRITE_CHANNEL);
-
-    key &= FW_CFG_ENTRY_MASK;
-
-    assert(key < FW_CFG_MAX_ENTRY && len <= UINT32_MAX);
-
-    s->entries[arch][key].data = data;
-    s->entries[arch][key].len = (uint32_t)len;
-    s->entries[arch][key].callback_opaque = callback_opaque;
-    s->entries[arch][key].callback = callback;
-}
-
 void fw_cfg_add_file_callback(FWCfgState *s,  const char *filename,
                               FWCfgReadCallback callback, void *callback_opaque,
                               void *data, size_t len)
@@ -535,18 +515,19 @@ void fw_cfg_add_file_callback(FWCfgState *s,  const char *filename,
     index = be32_to_cpu(s->files->count);
     assert(index < FW_CFG_FILE_SLOTS);
 
-    fw_cfg_add_bytes_read_callback(s, FW_CFG_FILE_FIRST + index,
-                                   callback, callback_opaque, data, len);
-
     pstrcpy(s->files->f[index].name, sizeof(s->files->f[index].name),
             filename);
     for (i = 0; i < index; i++) {
         if (strcmp(s->files->f[index].name, s->files->f[i].name) == 0) {
-            trace_fw_cfg_add_file_dupe(s, s->files->f[index].name);
-            return;
+            error_report("duplicate fw_cfg file name: %s",
+                         s->files->f[index].name);
+            exit(1);
         }
     }
 
+    fw_cfg_add_bytes_read_callback(s, FW_CFG_FILE_FIRST + index,
+                                   callback, callback_opaque, data, len);
+
     s->files->f[index].size   = cpu_to_be32(len);
     s->files->f[index].select = cpu_to_be16(FW_CFG_FILE_FIRST + index);
     trace_fw_cfg_add_file(s, index, s->files->f[index].name, len);
diff --git a/hw/ppc/mac_newworld.c b/hw/ppc/mac_newworld.c
index a365bf9223..0f3e34122a 100644
--- a/hw/ppc/mac_newworld.c
+++ b/hw/ppc/mac_newworld.c
@@ -119,7 +119,7 @@ static const MemoryRegionOps unin_ops = {
 static void fw_cfg_boot_set(void *opaque, const char *boot_device,
                             Error **errp)
 {
-    fw_cfg_add_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
+    fw_cfg_modify_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
 }
 
 static uint64_t translate_kernel_address(void *opaque, uint64_t addr)
diff --git a/hw/ppc/mac_oldworld.c b/hw/ppc/mac_oldworld.c
index f26133dedd..99879dd2d5 100644
--- a/hw/ppc/mac_oldworld.c
+++ b/hw/ppc/mac_oldworld.c
@@ -52,7 +52,7 @@
 static void fw_cfg_boot_set(void *opaque, const char *boot_device,
                             Error **errp)
 {
-    fw_cfg_add_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
+    fw_cfg_modify_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
 }
 
 static uint64_t translate_kernel_address(void *opaque, uint64_t addr)
diff --git a/hw/s390x/virtio-ccw.c b/hw/s390x/virtio-ccw.c
index ef90feddea..ab5fc7f40e 100644
--- a/hw/s390x/virtio-ccw.c
+++ b/hw/s390x/virtio-ccw.c
@@ -1,8 +1,9 @@
 /*
  * virtio ccw target implementation
  *
- * Copyright 2012,2014 IBM Corp.
+ * Copyright 2012,2015 IBM Corp.
  * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ *            Pierre Morel <pmorel@linux.vnet.ibm.com>
  *
  * This work is licensed under the terms of the GNU GPL, version 2 or (at
  * your option) any later version. See the COPYING file in the top-level
@@ -1310,6 +1311,7 @@ static void virtio_ccw_save_config(DeviceState *d, QEMUFile *f)
 {
     VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
     SubchDev *s = dev->sch;
+    VirtIODevice *vdev = virtio_ccw_get_vdev(s);
 
     subch_device_save(s, f);
     if (dev->indicators != NULL) {
@@ -1333,6 +1335,7 @@ static void virtio_ccw_save_config(DeviceState *d, QEMUFile *f)
         qemu_put_be32(f, 0);
         qemu_put_be64(f, 0UL);
     }
+    qemu_put_be16(f, vdev->config_vector);
     qemu_put_be64(f, dev->routes.adapter.ind_offset);
     qemu_put_byte(f, dev->thinint_isc);
 }
@@ -1341,6 +1344,7 @@ static int virtio_ccw_load_config(DeviceState *d, QEMUFile *f)
 {
     VirtioCcwDevice *dev = VIRTIO_CCW_DEVICE(d);
     SubchDev *s = dev->sch;
+    VirtIODevice *vdev = virtio_ccw_get_vdev(s);
     int len;
 
     s->driver_data = dev;
@@ -1366,6 +1370,7 @@ static int virtio_ccw_load_config(DeviceState *d, QEMUFile *f)
         qemu_get_be64(f);
         dev->summary_indicator = NULL;
     }
+    qemu_get_be16s(f, &vdev->config_vector);
     dev->routes.adapter.ind_offset = qemu_get_be64(f);
     dev->thinint_isc = qemu_get_byte(f);
     if (s->thinint_active) {
@@ -1730,6 +1735,56 @@ static const TypeInfo virtio_ccw_bus_info = {
     .class_init = virtio_ccw_bus_class_init,
 };
 
+#ifdef CONFIG_VIRTFS
+static Property virtio_ccw_9p_properties[] = {
+    DEFINE_PROP_STRING("devno", VirtioCcwDevice, bus_id),
+    DEFINE_PROP_BIT("ioeventfd", VirtioCcwDevice, flags,
+            VIRTIO_CCW_FLAG_USE_IOEVENTFD_BIT, true),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void virtio_ccw_9p_realize(VirtioCcwDevice *ccw_dev, Error **errp)
+{
+    V9fsCCWState *dev = VIRTIO_9P_CCW(ccw_dev);
+    DeviceState *vdev = DEVICE(&dev->vdev);
+    Error *err = NULL;
+
+    qdev_set_parent_bus(vdev, BUS(&ccw_dev->bus));
+    object_property_set_bool(OBJECT(vdev), true, "realized", &err);
+    if (err) {
+        error_propagate(errp, err);
+    }
+}
+
+static void virtio_ccw_9p_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VirtIOCCWDeviceClass *k = VIRTIO_CCW_DEVICE_CLASS(klass);
+
+    k->exit = virtio_ccw_exit;
+    k->realize = virtio_ccw_9p_realize;
+    dc->reset = virtio_ccw_reset;
+    dc->props = virtio_ccw_9p_properties;
+    set_bit(DEVICE_CATEGORY_STORAGE, dc->categories);
+}
+
+static void virtio_ccw_9p_instance_init(Object *obj)
+{
+    V9fsCCWState *dev = VIRTIO_9P_CCW(obj);
+
+    virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev),
+                                TYPE_VIRTIO_9P);
+}
+
+static const TypeInfo virtio_ccw_9p_info = {
+    .name          = TYPE_VIRTIO_9P_CCW,
+    .parent        = TYPE_VIRTIO_CCW_DEVICE,
+    .instance_size = sizeof(V9fsCCWState),
+    .instance_init = virtio_ccw_9p_instance_init,
+    .class_init    = virtio_ccw_9p_class_init,
+};
+#endif
+
 static void virtio_ccw_register(void)
 {
     type_register_static(&virtio_ccw_bus_info);
@@ -1745,6 +1800,9 @@ static void virtio_ccw_register(void)
 #endif
     type_register_static(&virtio_ccw_rng);
     type_register_static(&virtual_css_bridge_info);
+#ifdef CONFIG_VIRTFS
+    type_register_static(&virtio_ccw_9p_info);
+#endif
 }
 
 type_init(virtio_ccw_register)
diff --git a/hw/s390x/virtio-ccw.h b/hw/s390x/virtio-ccw.h
index ad3af7626a..d729263960 100644
--- a/hw/s390x/virtio-ccw.h
+++ b/hw/s390x/virtio-ccw.h
@@ -1,8 +1,9 @@
 /*
  * virtio ccw target definitions
  *
- * Copyright 2012 IBM Corp.
+ * Copyright 2012,2015 IBM Corp.
  * Author(s): Cornelia Huck <cornelia.huck@de.ibm.com>
+ *            Pierre Morel <pmorel@linux.vnet.ibm.com>
  *
  * This work is licensed under the terms of the GNU GPL, version 2 or (at
  * your option) any later version. See the COPYING file in the top-level
@@ -189,4 +190,19 @@ typedef struct VirtIORNGCcw {
 VirtualCssBus *virtual_css_bus_init(void);
 void virtio_ccw_device_update_status(SubchDev *sch);
 VirtIODevice *virtio_ccw_get_vdev(SubchDev *sch);
+
+#ifdef CONFIG_VIRTFS
+#include "hw/9pfs/virtio-9p.h"
+
+#define TYPE_VIRTIO_9P_CCW "virtio-9p-ccw"
+#define VIRTIO_9P_CCW(obj) \
+    OBJECT_CHECK(V9fsCCWState, (obj), TYPE_VIRTIO_9P_CCW)
+
+typedef struct V9fsCCWState {
+    VirtioCcwDevice parent_obj;
+    V9fsState vdev;
+} V9fsCCWState;
+
+#endif /* CONFIG_VIRTFS */
+
 #endif
diff --git a/hw/sparc/sun4m.c b/hw/sparc/sun4m.c
index 8a3599c403..68ac4d8bba 100644
--- a/hw/sparc/sun4m.c
+++ b/hw/sparc/sun4m.c
@@ -124,7 +124,7 @@ void DMA_register_channel (int nchan,
 static void fw_cfg_boot_set(void *opaque, const char *boot_device,
                             Error **errp)
 {
-    fw_cfg_add_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
+    fw_cfg_modify_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
 }
 
 static void nvram_init(Nvram *nvram, uint8_t *macaddr,
diff --git a/hw/sparc64/sun4u.c b/hw/sparc64/sun4u.c
index 6f34e87935..30cfa0e0a0 100644
--- a/hw/sparc64/sun4u.c
+++ b/hw/sparc64/sun4u.c
@@ -127,7 +127,7 @@ void DMA_register_channel (int nchan,
 static void fw_cfg_boot_set(void *opaque, const char *boot_device,
                             Error **errp)
 {
-    fw_cfg_add_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
+    fw_cfg_modify_i16(opaque, FW_CFG_BOOT_DEVICE, boot_device[0]);
 }
 
 static int sun4u_NVRAM_set_params(Nvram *nvram, uint16_t NVRAM_size,
diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
index e31f30ec09..d540c9d140 100644
--- a/hw/vfio/Makefile.objs
+++ b/hw/vfio/Makefile.objs
@@ -1,4 +1,6 @@
 ifeq ($(CONFIG_LINUX), y)
 obj-$(CONFIG_SOFTMMU) += common.o
 obj-$(CONFIG_PCI) += pci.o
+obj-$(CONFIG_SOFTMMU) += platform.o
+obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o
 endif
diff --git a/hw/vfio/calxeda-xgmac.c b/hw/vfio/calxeda-xgmac.c
new file mode 100644
index 0000000000..eb914f0d0b
--- /dev/null
+++ b/hw/vfio/calxeda-xgmac.c
@@ -0,0 +1,55 @@
+/*
+ * calxeda xgmac VFIO device
+ *
+ * Copyright Linaro Limited, 2014
+ *
+ * Authors:
+ *  Eric Auger <eric.auger@linaro.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ */
+
+#include "hw/vfio/vfio-calxeda-xgmac.h"
+
+static void calxeda_xgmac_realize(DeviceState *dev, Error **errp)
+{
+    VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev);
+    VFIOCalxedaXgmacDeviceClass *k = VFIO_CALXEDA_XGMAC_DEVICE_GET_CLASS(dev);
+
+    vdev->compat = g_strdup("calxeda,hb-xgmac");
+
+    k->parent_realize(dev, errp);
+}
+
+static const VMStateDescription vfio_platform_calxeda_xgmac_vmstate = {
+    .name = TYPE_VFIO_CALXEDA_XGMAC,
+    .unmigratable = 1,
+};
+
+static void vfio_calxeda_xgmac_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+    VFIOCalxedaXgmacDeviceClass *vcxc =
+        VFIO_CALXEDA_XGMAC_DEVICE_CLASS(klass);
+    vcxc->parent_realize = dc->realize;
+    dc->realize = calxeda_xgmac_realize;
+    dc->desc = "VFIO Calxeda XGMAC";
+    dc->vmsd = &vfio_platform_calxeda_xgmac_vmstate;
+}
+
+static const TypeInfo vfio_calxeda_xgmac_dev_info = {
+    .name = TYPE_VFIO_CALXEDA_XGMAC,
+    .parent = TYPE_VFIO_PLATFORM,
+    .instance_size = sizeof(VFIOCalxedaXgmacDevice),
+    .class_init = vfio_calxeda_xgmac_class_init,
+    .class_size = sizeof(VFIOCalxedaXgmacDeviceClass),
+};
+
+static void register_calxeda_xgmac_dev_type(void)
+{
+    type_register_static(&vfio_calxeda_xgmac_dev_info);
+}
+
+type_init(register_calxeda_xgmac_dev_type)
diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c
new file mode 100644
index 0000000000..9382bb7f36
--- /dev/null
+++ b/hw/vfio/platform.c
@@ -0,0 +1,615 @@
+/*
+ * vfio based device assignment support - platform devices
+ *
+ * Copyright Linaro Limited, 2014
+ *
+ * Authors:
+ *  Kim Phillips <kim.phillips@linaro.org>
+ *  Eric Auger <eric.auger@linaro.org>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2.  See
+ * the COPYING file in the top-level directory.
+ *
+ * Based on vfio based PCI device assignment support:
+ *  Copyright Red Hat, Inc. 2012
+ */
+
+#include <linux/vfio.h>
+#include <sys/ioctl.h>
+
+#include "hw/vfio/vfio-platform.h"
+#include "qemu/error-report.h"
+#include "qemu/range.h"
+#include "sysemu/sysemu.h"
+#include "exec/memory.h"
+#include "qemu/queue.h"
+#include "hw/sysbus.h"
+#include "trace.h"
+#include "hw/platform-bus.h"
+
+/*
+ * Functions used whatever the injection method
+ */
+
+/**
+ * vfio_init_intp - allocate, initialize the IRQ struct pointer
+ * and add it into the list of IRQs
+ * @vbasedev: the VFIO device handle
+ * @info: irq info struct retrieved from VFIO driver
+ */
+static VFIOINTp *vfio_init_intp(VFIODevice *vbasedev,
+                                struct vfio_irq_info info)
+{
+    int ret;
+    VFIOPlatformDevice *vdev =
+        container_of(vbasedev, VFIOPlatformDevice, vbasedev);
+    SysBusDevice *sbdev = SYS_BUS_DEVICE(vdev);
+    VFIOINTp *intp;
+
+    intp = g_malloc0(sizeof(*intp));
+    intp->vdev = vdev;
+    intp->pin = info.index;
+    intp->flags = info.flags;
+    intp->state = VFIO_IRQ_INACTIVE;
+
+    sysbus_init_irq(sbdev, &intp->qemuirq);
+
+    /* Get an eventfd for trigger */
+    ret = event_notifier_init(&intp->interrupt, 0);
+    if (ret) {
+        g_free(intp);
+        error_report("vfio: Error: trigger event_notifier_init failed ");
+        return NULL;
+    }
+
+    QLIST_INSERT_HEAD(&vdev->intp_list, intp, next);
+    return intp;
+}
+
+/**
+ * vfio_set_trigger_eventfd - set VFIO eventfd handling
+ *
+ * @intp: IRQ struct handle
+ * @handler: handler to be called on eventfd signaling
+ *
+ * Setup VFIO signaling and attach an optional user-side handler
+ * to the eventfd
+ */
+static int vfio_set_trigger_eventfd(VFIOINTp *intp,
+                                    eventfd_user_side_handler_t handler)
+{
+    VFIODevice *vbasedev = &intp->vdev->vbasedev;
+    struct vfio_irq_set *irq_set;
+    int argsz, ret;
+    int32_t *pfd;
+
+    argsz = sizeof(*irq_set) + sizeof(*pfd);
+    irq_set = g_malloc0(argsz);
+    irq_set->argsz = argsz;
+    irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | VFIO_IRQ_SET_ACTION_TRIGGER;
+    irq_set->index = intp->pin;
+    irq_set->start = 0;
+    irq_set->count = 1;
+    pfd = (int32_t *)&irq_set->data;
+    *pfd = event_notifier_get_fd(&intp->interrupt);
+    qemu_set_fd_handler(*pfd, (IOHandler *)handler, NULL, intp);
+    ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set);
+    g_free(irq_set);
+    if (ret < 0) {
+        error_report("vfio: Failed to set trigger eventfd: %m");
+        qemu_set_fd_handler(*pfd, NULL, NULL, NULL);
+    }
+    return ret;
+}
+
+/*
+ * Functions only used when eventfds are handled on user-side
+ * ie. without irqfd
+ */
+
+/**
+ * vfio_mmap_set_enabled - enable/disable the fast path mode
+ * @vdev: the VFIO platform device
+ * @enabled: the target mmap state
+ *
+ * enabled = true ~ fast path = MMIO region is mmaped (no KVM TRAP);
+ * enabled = false ~ slow path = MMIO region is trapped and region callbacks
+ * are called; slow path enables to trap the device IRQ status register reset
+*/
+
+static void vfio_mmap_set_enabled(VFIOPlatformDevice *vdev, bool enabled)
+{
+    int i;
+
+    trace_vfio_platform_mmap_set_enabled(enabled);
+
+    for (i = 0; i < vdev->vbasedev.num_regions; i++) {
+        VFIORegion *region = vdev->regions[i];
+
+        memory_region_set_enabled(&region->mmap_mem, enabled);
+    }
+}
+
+/**
+ * vfio_intp_mmap_enable - timer function, restores the fast path
+ * if there is no more active IRQ
+ * @opaque: actually points to the VFIO platform device
+ *
+ * Called on mmap timer timout, this function checks whether the
+ * IRQ is still active and if not, restores the fast path.
+ * by construction a single eventfd is handled at a time.
+ * if the IRQ is still active, the timer is re-programmed.
+ */
+static void vfio_intp_mmap_enable(void *opaque)
+{
+    VFIOINTp *tmp;
+    VFIOPlatformDevice *vdev = (VFIOPlatformDevice *)opaque;
+
+    qemu_mutex_lock(&vdev->intp_mutex);
+    QLIST_FOREACH(tmp, &vdev->intp_list, next) {
+        if (tmp->state == VFIO_IRQ_ACTIVE) {
+            trace_vfio_platform_intp_mmap_enable(tmp->pin);
+            /* re-program the timer to check active status later */
+            timer_mod(vdev->mmap_timer,
+                      qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
+                          vdev->mmap_timeout);
+            qemu_mutex_unlock(&vdev->intp_mutex);
+            return;
+        }
+    }
+    vfio_mmap_set_enabled(vdev, true);
+    qemu_mutex_unlock(&vdev->intp_mutex);
+}
+
+/**
+ * vfio_intp_inject_pending_lockheld - Injects a pending IRQ
+ * @opaque: opaque pointer, in practice the VFIOINTp handle
+ *
+ * The function is called on a previous IRQ completion, from
+ * vfio_platform_eoi, while the intp_mutex is locked.
+ * Also in such situation, the slow path already is set and
+ * the mmap timer was already programmed.
+ */
+static void vfio_intp_inject_pending_lockheld(VFIOINTp *intp)
+{
+    trace_vfio_platform_intp_inject_pending_lockheld(intp->pin,
+                              event_notifier_get_fd(&intp->interrupt));
+
+    intp->state = VFIO_IRQ_ACTIVE;
+
+    /* trigger the virtual IRQ */
+    qemu_set_irq(intp->qemuirq, 1);
+}
+
+/**
+ * vfio_intp_interrupt - The user-side eventfd handler
+ * @opaque: opaque pointer which in practice is the VFIOINTp handle
+ *
+ * the function is entered in event handler context:
+ * the vIRQ is injected into the guest if there is no other active
+ * or pending IRQ.
+ */
+static void vfio_intp_interrupt(VFIOINTp *intp)
+{
+    int ret;
+    VFIOINTp *tmp;
+    VFIOPlatformDevice *vdev = intp->vdev;
+    bool delay_handling = false;
+
+    qemu_mutex_lock(&vdev->intp_mutex);
+    if (intp->state == VFIO_IRQ_INACTIVE) {
+        QLIST_FOREACH(tmp, &vdev->intp_list, next) {
+            if (tmp->state == VFIO_IRQ_ACTIVE ||
+                tmp->state == VFIO_IRQ_PENDING) {
+                delay_handling = true;
+                break;
+            }
+        }
+    }
+    if (delay_handling) {
+        /*
+         * the new IRQ gets a pending status and is pushed in
+         * the pending queue
+         */
+        intp->state = VFIO_IRQ_PENDING;
+        trace_vfio_intp_interrupt_set_pending(intp->pin);
+        QSIMPLEQ_INSERT_TAIL(&vdev->pending_intp_queue,
+                             intp, pqnext);
+        ret = event_notifier_test_and_clear(&intp->interrupt);
+        qemu_mutex_unlock(&vdev->intp_mutex);
+        return;
+    }
+
+    trace_vfio_platform_intp_interrupt(intp->pin,
+                              event_notifier_get_fd(&intp->interrupt));
+
+    ret = event_notifier_test_and_clear(&intp->interrupt);
+    if (!ret) {
+        error_report("Error when clearing fd=%d (ret = %d)\n",
+                     event_notifier_get_fd(&intp->interrupt), ret);
+    }
+
+    intp->state = VFIO_IRQ_ACTIVE;
+
+    /* sets slow path */
+    vfio_mmap_set_enabled(vdev, false);
+
+    /* trigger the virtual IRQ */
+    qemu_set_irq(intp->qemuirq, 1);
+
+    /*
+     * Schedule the mmap timer which will restore fastpath when no IRQ
+     * is active anymore
+     */
+    if (vdev->mmap_timeout) {
+        timer_mod(vdev->mmap_timer,
+                  qemu_clock_get_ms(QEMU_CLOCK_VIRTUAL) +
+                      vdev->mmap_timeout);
+    }
+    qemu_mutex_unlock(&vdev->intp_mutex);
+}
+
+/**
+ * vfio_platform_eoi - IRQ completion routine
+ * @vbasedev: the VFIO device handle
+ *
+ * De-asserts the active virtual IRQ and unmasks the physical IRQ
+ * (effective for level sensitive IRQ auto-masked by the  VFIO driver).
+ * Then it handles next pending IRQ if any.
+ * eoi function is called on the first access to any MMIO region
+ * after an IRQ was triggered, trapped since slow path was set.
+ * It is assumed this access corresponds to the IRQ status
+ * register reset. With such a mechanism, a single IRQ can be
+ * handled at a time since there is no way to know which IRQ
+ * was completed by the guest (we would need additional details
+ * about the IRQ status register mask).
+ */
+static void vfio_platform_eoi(VFIODevice *vbasedev)
+{
+    VFIOINTp *intp;
+    VFIOPlatformDevice *vdev =
+        container_of(vbasedev, VFIOPlatformDevice, vbasedev);
+
+    qemu_mutex_lock(&vdev->intp_mutex);
+    QLIST_FOREACH(intp, &vdev->intp_list, next) {
+        if (intp->state == VFIO_IRQ_ACTIVE) {
+            trace_vfio_platform_eoi(intp->pin,
+                                event_notifier_get_fd(&intp->interrupt));
+            intp->state = VFIO_IRQ_INACTIVE;
+
+            /* deassert the virtual IRQ */
+            qemu_set_irq(intp->qemuirq, 0);
+
+            if (intp->flags & VFIO_IRQ_INFO_AUTOMASKED) {
+                /* unmasks the physical level-sensitive IRQ */
+                vfio_unmask_single_irqindex(vbasedev, intp->pin);
+            }
+
+            /* a single IRQ can be active at a time */
+            break;
+        }
+    }
+    /* in case there are pending IRQs, handle the first one */
+    if (!QSIMPLEQ_EMPTY(&vdev->pending_intp_queue)) {
+        intp = QSIMPLEQ_FIRST(&vdev->pending_intp_queue);
+        vfio_intp_inject_pending_lockheld(intp);
+        QSIMPLEQ_REMOVE_HEAD(&vdev->pending_intp_queue, pqnext);
+    }
+    qemu_mutex_unlock(&vdev->intp_mutex);
+}
+
+/**
+ * vfio_start_eventfd_injection - starts the virtual IRQ injection using
+ * user-side handled eventfds
+ * @intp: the IRQ struct pointer
+ */
+
+static int vfio_start_eventfd_injection(VFIOINTp *intp)
+{
+    int ret;
+
+    ret = vfio_set_trigger_eventfd(intp, vfio_intp_interrupt);
+    if (ret) {
+        error_report("vfio: Error: Failed to pass IRQ fd to the driver: %m");
+    }
+    return ret;
+}
+
+/* VFIO skeleton */
+
+static void vfio_platform_compute_needs_reset(VFIODevice *vbasedev)
+{
+    vbasedev->needs_reset = true;
+}
+
+/* not implemented yet */
+static int vfio_platform_hot_reset_multi(VFIODevice *vbasedev)
+{
+    return -1;
+}
+
+/**
+ * vfio_populate_device - Allocate and populate MMIO region
+ * and IRQ structs according to driver returned information
+ * @vbasedev: the VFIO device handle
+ *
+ */
+static int vfio_populate_device(VFIODevice *vbasedev)
+{
+    VFIOINTp *intp, *tmp;
+    int i, ret = -1;
+    VFIOPlatformDevice *vdev =
+        container_of(vbasedev, VFIOPlatformDevice, vbasedev);
+
+    if (!(vbasedev->flags & VFIO_DEVICE_FLAGS_PLATFORM)) {
+        error_report("vfio: Um, this isn't a platform device");
+        return ret;
+    }
+
+    vdev->regions = g_new0(VFIORegion *, vbasedev->num_regions);
+
+    for (i = 0; i < vbasedev->num_regions; i++) {
+        struct vfio_region_info reg_info = { .argsz = sizeof(reg_info) };
+        VFIORegion *ptr;
+
+        vdev->regions[i] = g_malloc0(sizeof(VFIORegion));
+        ptr = vdev->regions[i];
+        reg_info.index = i;
+        ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_REGION_INFO, &reg_info);
+        if (ret) {
+            error_report("vfio: Error getting region %d info: %m", i);
+            goto reg_error;
+        }
+        ptr->flags = reg_info.flags;
+        ptr->size = reg_info.size;
+        ptr->fd_offset = reg_info.offset;
+        ptr->nr = i;
+        ptr->vbasedev = vbasedev;
+
+        trace_vfio_platform_populate_regions(ptr->nr,
+                            (unsigned long)ptr->flags,
+                            (unsigned long)ptr->size,
+                            ptr->vbasedev->fd,
+                            (unsigned long)ptr->fd_offset);
+    }
+
+    vdev->mmap_timer = timer_new_ms(QEMU_CLOCK_VIRTUAL,
+                                    vfio_intp_mmap_enable, vdev);
+
+    QSIMPLEQ_INIT(&vdev->pending_intp_queue);
+
+    for (i = 0; i < vbasedev->num_irqs; i++) {
+        struct vfio_irq_info irq = { .argsz = sizeof(irq) };
+
+        irq.index = i;
+        ret = ioctl(vbasedev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq);
+        if (ret) {
+            error_printf("vfio: error getting device %s irq info",
+                         vbasedev->name);
+            goto irq_err;
+        } else {
+            trace_vfio_platform_populate_interrupts(irq.index,
+                                                    irq.count,
+                                                    irq.flags);
+            intp = vfio_init_intp(vbasedev, irq);
+            if (!intp) {
+                error_report("vfio: Error installing IRQ %d up", i);
+                goto irq_err;
+            }
+        }
+    }
+    return 0;
+irq_err:
+    timer_del(vdev->mmap_timer);
+    QLIST_FOREACH_SAFE(intp, &vdev->intp_list, next, tmp) {
+        QLIST_REMOVE(intp, next);
+        g_free(intp);
+    }
+reg_error:
+    for (i = 0; i < vbasedev->num_regions; i++) {
+        g_free(vdev->regions[i]);
+    }
+    g_free(vdev->regions);
+    return ret;
+}
+
+/* specialized functions for VFIO Platform devices */
+static VFIODeviceOps vfio_platform_ops = {
+    .vfio_compute_needs_reset = vfio_platform_compute_needs_reset,
+    .vfio_hot_reset_multi = vfio_platform_hot_reset_multi,
+    .vfio_eoi = vfio_platform_eoi,
+};
+
+/**
+ * vfio_base_device_init - perform preliminary VFIO setup
+ * @vbasedev: the VFIO device handle
+ *
+ * Implement the VFIO command sequence that allows to discover
+ * assigned device resources: group extraction, device
+ * fd retrieval, resource query.
+ * Precondition: the device name must be initialized
+ */
+static int vfio_base_device_init(VFIODevice *vbasedev)
+{
+    VFIOGroup *group;
+    VFIODevice *vbasedev_iter;
+    char path[PATH_MAX], iommu_group_path[PATH_MAX], *group_name;
+    ssize_t len;
+    struct stat st;
+    int groupid;
+    int ret;
+
+    /* name must be set prior to the call */
+    if (!vbasedev->name || strchr(vbasedev->name, '/')) {
+        return -EINVAL;
+    }
+
+    /* Check that the host device exists */
+    g_snprintf(path, sizeof(path), "/sys/bus/platform/devices/%s/",
+               vbasedev->name);
+
+    if (stat(path, &st) < 0) {
+        error_report("vfio: error: no such host device: %s", path);
+        return -errno;
+    }
+
+    g_strlcat(path, "iommu_group", sizeof(path));
+    len = readlink(path, iommu_group_path, sizeof(iommu_group_path));
+    if (len < 0 || len >= sizeof(iommu_group_path)) {
+        error_report("vfio: error no iommu_group for device");
+        return len < 0 ? -errno : -ENAMETOOLONG;
+    }
+
+    iommu_group_path[len] = 0;
+    group_name = basename(iommu_group_path);
+
+    if (sscanf(group_name, "%d", &groupid) != 1) {
+        error_report("vfio: error reading %s: %m", path);
+        return -errno;
+    }
+
+    trace_vfio_platform_base_device_init(vbasedev->name, groupid);
+
+    group = vfio_get_group(groupid, &address_space_memory);
+    if (!group) {
+        error_report("vfio: failed to get group %d", groupid);
+        return -ENOENT;
+    }
+
+    g_snprintf(path, sizeof(path), "%s", vbasedev->name);
+
+    QLIST_FOREACH(vbasedev_iter, &group->device_list, next) {
+        if (strcmp(vbasedev_iter->name, vbasedev->name) == 0) {
+            error_report("vfio: error: device %s is already attached", path);
+            vfio_put_group(group);
+            return -EBUSY;
+        }
+    }
+    ret = vfio_get_device(group, path, vbasedev);
+    if (ret) {
+        error_report("vfio: failed to get device %s", path);
+        vfio_put_group(group);
+        return ret;
+    }
+
+    ret = vfio_populate_device(vbasedev);
+    if (ret) {
+        error_report("vfio: failed to populate device %s", path);
+        vfio_put_group(group);
+    }
+
+    return ret;
+}
+
+/**
+ * vfio_map_region - initialize the 2 memory regions for a given
+ * MMIO region index
+ * @vdev: the VFIO platform device handle
+ * @nr: the index of the region
+ *
+ * Init the top memory region and the mmapped memory region beneath
+ * VFIOPlatformDevice is used since VFIODevice is not a QOM Object
+ * and could not be passed to memory region functions
+*/
+static void vfio_map_region(VFIOPlatformDevice *vdev, int nr)
+{
+    VFIORegion *region = vdev->regions[nr];
+    uint64_t size = region->size;
+    char name[64];
+
+    if (!size) {
+        return;
+    }
+
+    g_snprintf(name, sizeof(name), "VFIO %s region %d",
+               vdev->vbasedev.name, nr);
+
+    /* A "slow" read/write mapping underlies all regions */
+    memory_region_init_io(&region->mem, OBJECT(vdev), &vfio_region_ops,
+                          region, name, size);
+
+    g_strlcat(name, " mmap", sizeof(name));
+
+    if (vfio_mmap_region(OBJECT(vdev), region, &region->mem,
+                         &region->mmap_mem, &region->mmap, size, 0, name)) {
+        error_report("%s unsupported. Performance may be slow", name);
+    }
+}
+
+/**
+ * vfio_platform_realize  - the device realize function
+ * @dev: device state pointer
+ * @errp: error
+ *
+ * initialize the device, its memory regions and IRQ structures
+ * IRQ are started separately
+ */
+static void vfio_platform_realize(DeviceState *dev, Error **errp)
+{
+    VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev);
+    SysBusDevice *sbdev = SYS_BUS_DEVICE(dev);
+    VFIODevice *vbasedev = &vdev->vbasedev;
+    VFIOINTp *intp;
+    int i, ret;
+
+    vbasedev->type = VFIO_DEVICE_TYPE_PLATFORM;
+    vbasedev->ops = &vfio_platform_ops;
+
+    trace_vfio_platform_realize(vbasedev->name, vdev->compat);
+
+    ret = vfio_base_device_init(vbasedev);
+    if (ret) {
+        error_setg(errp, "vfio: vfio_base_device_init failed for %s",
+                   vbasedev->name);
+        return;
+    }
+
+    for (i = 0; i < vbasedev->num_regions; i++) {
+        vfio_map_region(vdev, i);
+        sysbus_init_mmio(sbdev, &vdev->regions[i]->mem);
+    }
+
+    QLIST_FOREACH(intp, &vdev->intp_list, next) {
+        vfio_start_eventfd_injection(intp);
+    }
+}
+
+static const VMStateDescription vfio_platform_vmstate = {
+    .name = TYPE_VFIO_PLATFORM,
+    .unmigratable = 1,
+};
+
+static Property vfio_platform_dev_properties[] = {
+    DEFINE_PROP_STRING("host", VFIOPlatformDevice, vbasedev.name),
+    DEFINE_PROP_BOOL("x-mmap", VFIOPlatformDevice, vbasedev.allow_mmap, true),
+    DEFINE_PROP_UINT32("mmap-timeout-ms", VFIOPlatformDevice,
+                       mmap_timeout, 1100),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static void vfio_platform_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->realize = vfio_platform_realize;
+    dc->props = vfio_platform_dev_properties;
+    dc->vmsd = &vfio_platform_vmstate;
+    dc->desc = "VFIO-based platform device assignment";
+    set_bit(DEVICE_CATEGORY_MISC, dc->categories);
+}
+
+static const TypeInfo vfio_platform_dev_info = {
+    .name = TYPE_VFIO_PLATFORM,
+    .parent = TYPE_SYS_BUS_DEVICE,
+    .instance_size = sizeof(VFIOPlatformDevice),
+    .class_init = vfio_platform_class_init,
+    .class_size = sizeof(VFIOPlatformDeviceClass),
+    .abstract   = true,
+};
+
+static void register_vfio_platform_dev_type(void)
+{
+    type_register_static(&vfio_platform_dev_info);
+}
+
+type_init(register_vfio_platform_dev_type)