[RFC,v2,07/12] vfio/ccw: vfio based subchannel passthrough driver

Commit Message

Dong Jia Shi Jan. 12, 2017, 7:25 a.m. UTC

From: Xiao Feng Ren <[e-mail]>

We use the IOMMU_TYPE1 of VFIO to realize the subchannels
passthrough, implement a vfio based subchannels passthrough
driver called "vfio-ccw".

Support qemu parameters in the style of:
"-device vfio-ccw,id=xx,hostid=xx(,guestid=xx),mdevid=xx"

Signed-off-by: Xiao Feng Ren <[e-mail]>
---
 default-configs/s390x-softmmu.mak |   1 +
 hw/s390x/s390-ccw.h               |   1 +
 hw/vfio/Makefile.objs             |   1 +
 hw/vfio/ccw.c                     | 209 ++++++++++++++++++++++++++++++++++++++
 include/hw/vfio/vfio-common.h     |   1 +
 5 files changed, 213 insertions(+)
 create mode 100644 hw/vfio/ccw.c

Comments

Alex Williamson Jan. 17, 2017, 10:49 p.m. UTC | #1

On Thu, 12 Jan 2017 08:25:08 +0100
Dong Jia Shi <[e-mail]> wrote:

> From: Xiao Feng Ren <[e-mail]>
> 
> We use the IOMMU_TYPE1 of VFIO to realize the subchannels
> passthrough, implement a vfio based subchannels passthrough
> driver called "vfio-ccw".
> 
> Support qemu parameters in the style of:
> "-device vfio-ccw,id=xx,hostid=xx(,guestid=xx),mdevid=xx"

Why not adopt the same syntax as vfio-pci with mdev devices,
sysfsdev=%s where %s is a path to the mdev device in sysfs, which can
be /sys/bus/mdev/devices/$UUID or as you create from the hostid
below /sys/bus/css/devices/%x.%x.%04x/$UUID.  It seems if we know where
to find the mdev device then we can determine the parent information on
our own through sysfs.

> Signed-off-by: Xiao Feng Ren <[e-mail]>
> ---
>  default-configs/s390x-softmmu.mak |   1 +
>  hw/s390x/s390-ccw.h               |   1 +
>  hw/vfio/Makefile.objs             |   1 +
>  hw/vfio/ccw.c                     | 209 ++++++++++++++++++++++++++++++++++++++
>  include/hw/vfio/vfio-common.h     |   1 +
>  5 files changed, 213 insertions(+)
>  create mode 100644 hw/vfio/ccw.c
> 
> diff --git a/default-configs/s390x-softmmu.mak b/default-configs/s390x-softmmu.mak
> index 36e15de..5576b0a 100644
> --- a/default-configs/s390x-softmmu.mak
> +++ b/default-configs/s390x-softmmu.mak
> @@ -4,4 +4,5 @@ CONFIG_VIRTIO=y
>  CONFIG_SCLPCONSOLE=y
>  CONFIG_S390_FLIC=y
>  CONFIG_S390_FLIC_KVM=$(CONFIG_KVM)
> +CONFIG_VFIO_CCW=$(CONFIG_LINUX)
>  CONFIG_WDT_DIAG288=y
> diff --git a/hw/s390x/s390-ccw.h b/hw/s390x/s390-ccw.h
> index 9ced8cb..1fa4a97 100644
> --- a/hw/s390x/s390-ccw.h
> +++ b/hw/s390x/s390-ccw.h
> @@ -26,6 +26,7 @@
>  typedef struct S390CCWDevice {
>      CcwDevice parent_obj;
>      CssDevId hostid;
> +    char *mdevid;
>  } S390CCWDevice;
>  
>  typedef struct S390CCWDeviceClass {
> diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
> index c25e32b..4c3a462 100644
> --- a/hw/vfio/Makefile.objs
> +++ b/hw/vfio/Makefile.objs
> @@ -1,6 +1,7 @@
>  ifeq ($(CONFIG_LINUX), y)
>  obj-$(CONFIG_SOFTMMU) += common.o
>  obj-$(CONFIG_PCI) += pci.o pci-quirks.o
> +obj-$(CONFIG_VFIO_CCW) += ccw.o
>  obj-$(CONFIG_SOFTMMU) += platform.o
>  obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o
>  obj-$(CONFIG_SOFTMMU) += amd-xgbe.o
> diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
> new file mode 100644
> index 0000000..881010b
> --- /dev/null
> +++ b/hw/vfio/ccw.c
> @@ -0,0 +1,209 @@
> +/*
> + * vfio based subchannel assignment support
> + *
> + * Copyright 2017 IBM Corp.
> + * Author(s): Dong Jia Shi <[e-mail]>
> + *            Xiao Feng Ren <[e-mail]>
> + *            Pierre Morel <[e-mail]>
> + *
> + * This work is licensed under the terms of the GNU GPL, version 2 or(at
> + * your option) any version. See the COPYING file in the top-level
> + * directory.
> + */
> +
> +#include <linux/vfio.h>
> +#include <sys/ioctl.h>
> +
> +#include "qemu/osdep.h"
> +#include "qapi/error.h"
> +#include "hw/sysbus.h"
> +#include "hw/vfio/vfio.h"
> +#include "hw/vfio/vfio-common.h"
> +#include "hw/s390x/s390-ccw.h"
> +#include "hw/s390x/ccw-device.h"
> +
> +#define TYPE_VFIO_CCW "vfio-ccw"
> +typedef struct VFIOCCWDevice {
> +    S390CCWDevice cdev;
> +    VFIODevice vdev;
> +} VFIOCCWDevice;
> +
> +static void vfio_ccw_compute_needs_reset(VFIODevice *vdev)
> +{
> +    vdev->needs_reset = false;
> +}
> +
> +/*
> + * We don't need vfio_hot_reset_multi and vfio_eoi operationis for
> + * vfio_ccw device now.
> + */
> +struct VFIODeviceOps vfio_ccw_ops = {
> +    .vfio_compute_needs_reset = vfio_ccw_compute_needs_reset,
> +};
> +
> +static void vfio_ccw_reset(DeviceState *dev)
> +{
> +    CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev);
> +    S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev);
> +    VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev);
> +
> +    ioctl(vcdev->vdev.fd, VFIO_DEVICE_RESET);
> +}
> +
> +static void vfio_put_device(VFIOCCWDevice *vcdev)
> +{
> +    g_free(vcdev->vdev.name);
> +    vfio_put_base_device(&vcdev->vdev);
> +}
> +
> +static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, char **path,
> +                                     Error **errp)
> +{
> +    struct stat st;
> +    int groupid;
> +    GError *gerror = NULL;
> +
> +    /* Check that host subchannel exists. */
> +    path[0] = g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x",
> +                              cdev->hostid.cssid,
> +                              cdev->hostid.ssid,
> +                              cdev->hostid.devid);
> +    if (stat(path[0], &st) < 0) {
> +        error_setg(errp, "vfio: no such host subchannel %s", path[0]);
> +        return NULL;
> +    }
> +
> +    /* Check that mediated device exists. */
> +    path[1] = g_strdup_printf("%s/%s", path[0], cdev->mdevid);
> +    if (stat(path[0], &st) < 0) {
> +        error_setg(errp, "vfio: no such mediated device %s", path[1]);
> +        return NULL;
> +    }
> +
> +    /* Get the iommu_group patch as the interim variable. */
> +    path[2] = g_strconcat(path[1], "/iommu_group", NULL);
> +
> +    /* Get the link file path of the device iommu_group. */
> +    path[3] = g_file_read_link(path[2], &gerror);
> +    if (!path[3]) {
> +        error_setg(errp, "vfio: error no iommu_group for subchannel");
> +        return NULL;
> +    }
> +
> +    /* Get the device groupid. */
> +    if (sscanf(basename(path[3]), "%d", &groupid) != 1) {
> +        error_setg(errp, "vfio: error reading %s:%m", path[3]);
> +        return NULL;
> +    }
> +
> +    return vfio_get_group(groupid, &address_space_memory, errp);
> +}
> +
> +static void vfio_ccw_put_group(VFIOGroup *group, char **path)
> +{
> +    g_free(path);
> +    vfio_put_group(group);
> +}
> +
> +static void vfio_ccw_realize(DeviceState *dev, Error **errp)
> +{
> +    VFIODevice *vbasedev;
> +    VFIOGroup *group;
> +    CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev);
> +    S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev);
> +    VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev);
> +    S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev);
> +    char *path[4] = {NULL, NULL, NULL, NULL};
> +
> +    /* Call the class init function for subchannel. */
> +    if (cdc->realize) {
> +        cdc->realize(cdev, errp);
> +        if (*errp) {
> +            return;
> +        }
> +    }
> +
> +    group = vfio_ccw_get_group(cdev, path, errp);
> +    if (!group) {
> +        goto out_group_err;
> +    }
> +
> +    vcdev->vdev.ops = &vfio_ccw_ops;
> +    vcdev->vdev.type = VFIO_DEVICE_TYPE_CCW;
> +    vcdev->vdev.name = g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid,
> +                                       cdev->hostid.ssid, cdev->hostid.devid);
> +    QLIST_FOREACH(vbasedev, &group->device_list, next) {
> +        if (strcmp(vbasedev->name, vcdev->vdev.name) == 0) {
> +            error_setg(errp, "vfio: subchannel %s has already been attached",
> +                       basename(path[0]));
> +            goto out_device_err;
> +        }
> +    }
> +
> +    if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, errp)) {
> +        goto out_device_err;
> +    }
> +
> +    return;
> +
> +out_device_err:
> +    vfio_ccw_put_group(group, path);
> +out_group_err:
> +    if (cdc->unrealize) {
> +        cdc->unrealize(cdev, errp);
> +    }
> +}
> +
> +static void vfio_ccw_unrealize(DeviceState *dev, Error **errp)
> +{
> +    CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev);
> +    S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev);
> +    VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev);
> +    S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev);
> +    VFIOGroup *group = vcdev->vdev.group;
> +
> +    if (cdc->unrealize) {
> +        cdc->unrealize(cdev, errp);
> +    }
> +
> +    vfio_put_device(vcdev);
> +    vfio_put_group(group);
> +}
> +
> +static Property vfio_ccw_properties[] = {
> +    DEFINE_PROP_CSS_DEV_ID("hostid", VFIOCCWDevice, cdev.hostid),
> +    DEFINE_PROP_CSS_DEV_ID("guestid", VFIOCCWDevice, cdev.parent_obj.bus_id),
> +    DEFINE_PROP_STRING("mdevid", VFIOCCWDevice, cdev.mdevid),
> +    DEFINE_PROP_END_OF_LIST(),
> +};
> +
> +static const VMStateDescription vfio_ccw_vmstate = {
> +    .name = TYPE_VFIO_CCW,
> +    .unmigratable = 1,
> +};
> +
> +static void vfio_ccw_class_init(ObjectClass *klass, void *data)
> +{
> +    DeviceClass *dc = DEVICE_CLASS(klass);
> +
> +    dc->props = vfio_ccw_properties;
> +    dc->vmsd = &vfio_ccw_vmstate;
> +    dc->desc = "VFIO-based subchannel assignment";
> +    dc->realize = vfio_ccw_realize;
> +    dc->unrealize = vfio_ccw_unrealize;
> +    dc->reset = vfio_ccw_reset;
> +}
> +
> +static const TypeInfo vfio_ccw_info = {
> +    .name = TYPE_VFIO_CCW,
> +    .parent = TYPE_S390_CCW,
> +    .instance_size = sizeof(VFIOCCWDevice),
> +    .class_init = vfio_ccw_class_init,
> +};
> +
> +static void register_vfio_ccw_type(void)
> +{
> +    type_register_static(&vfio_ccw_info);
> +}
> +
> +type_init(register_vfio_ccw_type)
> diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
> index c582de1..9521013 100644
> --- a/include/hw/vfio/vfio-common.h
> +++ b/include/hw/vfio/vfio-common.h
> @@ -45,6 +45,7 @@
>  enum {
>      VFIO_DEVICE_TYPE_PCI = 0,
>      VFIO_DEVICE_TYPE_PLATFORM = 1,
> +    VFIO_DEVICE_TYPE_CCW = 2,
>  };
>  
>  typedef struct VFIOMmap {

--
To unsubscribe from this list: send the line "unsubscribe kvm" in
the body of a message to [e-mail]
More majordomo info at  http://vger.kernel.org/majordomo-info.html

Patch

diff --git a/default-configs/s390x-softmmu.mak b/default-configs/s390x-softmmu.mak
index 36e15de..5576b0a 100644
--- a/default-configs/s390x-softmmu.mak
+++ b/default-configs/s390x-softmmu.mak
@@ -4,4 +4,5 @@  CONFIG_VIRTIO=y
 CONFIG_SCLPCONSOLE=y
 CONFIG_S390_FLIC=y
 CONFIG_S390_FLIC_KVM=$(CONFIG_KVM)
+CONFIG_VFIO_CCW=$(CONFIG_LINUX)
 CONFIG_WDT_DIAG288=y
diff --git a/hw/s390x/s390-ccw.h b/hw/s390x/s390-ccw.h
index 9ced8cb..1fa4a97 100644
--- a/hw/s390x/s390-ccw.h
+++ b/hw/s390x/s390-ccw.h
@@ -26,6 +26,7 @@ 
 typedef struct S390CCWDevice {
     CcwDevice parent_obj;
     CssDevId hostid;
+    char *mdevid;
 } S390CCWDevice;
 
 typedef struct S390CCWDeviceClass {
diff --git a/hw/vfio/Makefile.objs b/hw/vfio/Makefile.objs
index c25e32b..4c3a462 100644
--- a/hw/vfio/Makefile.objs
+++ b/hw/vfio/Makefile.objs
@@ -1,6 +1,7 @@ 
 ifeq ($(CONFIG_LINUX), y)
 obj-$(CONFIG_SOFTMMU) += common.o
 obj-$(CONFIG_PCI) += pci.o pci-quirks.o
+obj-$(CONFIG_VFIO_CCW) += ccw.o
 obj-$(CONFIG_SOFTMMU) += platform.o
 obj-$(CONFIG_SOFTMMU) += calxeda-xgmac.o
 obj-$(CONFIG_SOFTMMU) += amd-xgbe.o
diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c
new file mode 100644
index 0000000..881010b
--- /dev/null
+++ b/hw/vfio/ccw.c
@@ -0,0 +1,209 @@ 
+/*
+ * vfio based subchannel assignment support
+ *
+ * Copyright 2017 IBM Corp.
+ * Author(s): Dong Jia Shi <[e-mail]>
+ *            Xiao Feng Ren <[e-mail]>
+ *            Pierre Morel <[e-mail]>
+ *
+ * This work is licensed under the terms of the GNU GPL, version 2 or(at
+ * your option) any version. See the COPYING file in the top-level
+ * directory.
+ */
+
+#include <linux/vfio.h>
+#include <sys/ioctl.h>
+
+#include "qemu/osdep.h"
+#include "qapi/error.h"
+#include "hw/sysbus.h"
+#include "hw/vfio/vfio.h"
+#include "hw/vfio/vfio-common.h"
+#include "hw/s390x/s390-ccw.h"
+#include "hw/s390x/ccw-device.h"
+
+#define TYPE_VFIO_CCW "vfio-ccw"
+typedef struct VFIOCCWDevice {
+    S390CCWDevice cdev;
+    VFIODevice vdev;
+} VFIOCCWDevice;
+
+static void vfio_ccw_compute_needs_reset(VFIODevice *vdev)
+{
+    vdev->needs_reset = false;
+}
+
+/*
+ * We don't need vfio_hot_reset_multi and vfio_eoi operationis for
+ * vfio_ccw device now.
+ */
+struct VFIODeviceOps vfio_ccw_ops = {
+    .vfio_compute_needs_reset = vfio_ccw_compute_needs_reset,
+};
+
+static void vfio_ccw_reset(DeviceState *dev)
+{
+    CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev);
+    S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev);
+    VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev);
+
+    ioctl(vcdev->vdev.fd, VFIO_DEVICE_RESET);
+}
+
+static void vfio_put_device(VFIOCCWDevice *vcdev)
+{
+    g_free(vcdev->vdev.name);
+    vfio_put_base_device(&vcdev->vdev);
+}
+
+static VFIOGroup *vfio_ccw_get_group(S390CCWDevice *cdev, char **path,
+                                     Error **errp)
+{
+    struct stat st;
+    int groupid;
+    GError *gerror = NULL;
+
+    /* Check that host subchannel exists. */
+    path[0] = g_strdup_printf("/sys/bus/css/devices/%x.%x.%04x",
+                              cdev->hostid.cssid,
+                              cdev->hostid.ssid,
+                              cdev->hostid.devid);
+    if (stat(path[0], &st) < 0) {
+        error_setg(errp, "vfio: no such host subchannel %s", path[0]);
+        return NULL;
+    }
+
+    /* Check that mediated device exists. */
+    path[1] = g_strdup_printf("%s/%s", path[0], cdev->mdevid);
+    if (stat(path[0], &st) < 0) {
+        error_setg(errp, "vfio: no such mediated device %s", path[1]);
+        return NULL;
+    }
+
+    /* Get the iommu_group patch as the interim variable. */
+    path[2] = g_strconcat(path[1], "/iommu_group", NULL);
+
+    /* Get the link file path of the device iommu_group. */
+    path[3] = g_file_read_link(path[2], &gerror);
+    if (!path[3]) {
+        error_setg(errp, "vfio: error no iommu_group for subchannel");
+        return NULL;
+    }
+
+    /* Get the device groupid. */
+    if (sscanf(basename(path[3]), "%d", &groupid) != 1) {
+        error_setg(errp, "vfio: error reading %s:%m", path[3]);
+        return NULL;
+    }
+
+    return vfio_get_group(groupid, &address_space_memory, errp);
+}
+
+static void vfio_ccw_put_group(VFIOGroup *group, char **path)
+{
+    g_free(path);
+    vfio_put_group(group);
+}
+
+static void vfio_ccw_realize(DeviceState *dev, Error **errp)
+{
+    VFIODevice *vbasedev;
+    VFIOGroup *group;
+    CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev);
+    S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev);
+    VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev);
+    S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev);
+    char *path[4] = {NULL, NULL, NULL, NULL};
+
+    /* Call the class init function for subchannel. */
+    if (cdc->realize) {
+        cdc->realize(cdev, errp);
+        if (*errp) {
+            return;
+        }
+    }
+
+    group = vfio_ccw_get_group(cdev, path, errp);
+    if (!group) {
+        goto out_group_err;
+    }
+
+    vcdev->vdev.ops = &vfio_ccw_ops;
+    vcdev->vdev.type = VFIO_DEVICE_TYPE_CCW;
+    vcdev->vdev.name = g_strdup_printf("%x.%x.%04x", cdev->hostid.cssid,
+                                       cdev->hostid.ssid, cdev->hostid.devid);
+    QLIST_FOREACH(vbasedev, &group->device_list, next) {
+        if (strcmp(vbasedev->name, vcdev->vdev.name) == 0) {
+            error_setg(errp, "vfio: subchannel %s has already been attached",
+                       basename(path[0]));
+            goto out_device_err;
+        }
+    }
+
+    if (vfio_get_device(group, cdev->mdevid, &vcdev->vdev, errp)) {
+        goto out_device_err;
+    }
+
+    return;
+
+out_device_err:
+    vfio_ccw_put_group(group, path);
+out_group_err:
+    if (cdc->unrealize) {
+        cdc->unrealize(cdev, errp);
+    }
+}
+
+static void vfio_ccw_unrealize(DeviceState *dev, Error **errp)
+{
+    CcwDevice *ccw_dev = DO_UPCAST(CcwDevice, parent_obj, dev);
+    S390CCWDevice *cdev = DO_UPCAST(S390CCWDevice, parent_obj, ccw_dev);
+    VFIOCCWDevice *vcdev = DO_UPCAST(VFIOCCWDevice, cdev, cdev);
+    S390CCWDeviceClass *cdc = S390_CCW_DEVICE_GET_CLASS(cdev);
+    VFIOGroup *group = vcdev->vdev.group;
+
+    if (cdc->unrealize) {
+        cdc->unrealize(cdev, errp);
+    }
+
+    vfio_put_device(vcdev);
+    vfio_put_group(group);
+}
+
+static Property vfio_ccw_properties[] = {
+    DEFINE_PROP_CSS_DEV_ID("hostid", VFIOCCWDevice, cdev.hostid),
+    DEFINE_PROP_CSS_DEV_ID("guestid", VFIOCCWDevice, cdev.parent_obj.bus_id),
+    DEFINE_PROP_STRING("mdevid", VFIOCCWDevice, cdev.mdevid),
+    DEFINE_PROP_END_OF_LIST(),
+};
+
+static const VMStateDescription vfio_ccw_vmstate = {
+    .name = TYPE_VFIO_CCW,
+    .unmigratable = 1,
+};
+
+static void vfio_ccw_class_init(ObjectClass *klass, void *data)
+{
+    DeviceClass *dc = DEVICE_CLASS(klass);
+
+    dc->props = vfio_ccw_properties;
+    dc->vmsd = &vfio_ccw_vmstate;
+    dc->desc = "VFIO-based subchannel assignment";
+    dc->realize = vfio_ccw_realize;
+    dc->unrealize = vfio_ccw_unrealize;
+    dc->reset = vfio_ccw_reset;
+}
+
+static const TypeInfo vfio_ccw_info = {
+    .name = TYPE_VFIO_CCW,
+    .parent = TYPE_S390_CCW,
+    .instance_size = sizeof(VFIOCCWDevice),
+    .class_init = vfio_ccw_class_init,
+};
+
+static void register_vfio_ccw_type(void)
+{
+    type_register_static(&vfio_ccw_info);
+}
+
+type_init(register_vfio_ccw_type)
diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h
index c582de1..9521013 100644
--- a/include/hw/vfio/vfio-common.h
+++ b/include/hw/vfio/vfio-common.h
@@ -45,6 +45,7 @@ 
 enum {
     VFIO_DEVICE_TYPE_PCI = 0,
     VFIO_DEVICE_TYPE_PLATFORM = 1,
+    VFIO_DEVICE_TYPE_CCW = 2,
 };
 
 typedef struct VFIOMmap {