Hi All
Really apologize for the delay, this is the draft RFC for
iommufd support for vdpa, This code provides the basic function
for iommufd support
The code was tested and passed in device vdpa_sim_net
The qemu code is
https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
The kernel code is
https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
ToDo
1. this code is out of date and needs to clean and rebase on the latest code
2. this code has some workaround, I Skip the check for
iommu_group and CACHE_COHERENCY, also some misc issues like need to add
mutex for iommfd operations
3. only test in emulated device, other modes not tested yet
After addressed these problems I will send out a new version for RFC. I will
provide the code in 3 weeks
Thanks
Cindy
Signed-off-by: Cindy Lu <[email protected]>
The test step is
1. create vdpa_sim device
...
vdpa dev add name vdpa15 mgmtdev vdpasim_net
...
2. load the VM with the command
-object iommufd,id=iommufd0 \
-device virtio-net-pci,netdev=vhost-vdpa1,disable-legacy=on,disable-modern=off\
-netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-0,id=vhost-vdpa1,iommufd=iommufd0\
3. in guest VM you can find the vdpa_sim port works well.
[root@ubuntunew ~]# ifconfig eth0
eth0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
inet6 fe80::5054:ff:fe12:3456 prefixlen 64 scopeid 0x20<link>
ether 52:54:00:12:34:56 txqueuelen 1000 (Ethernet)
RX packets 53 bytes 9108 (8.8 KiB)
RX errors 0 dropped 0 overruns 0 frame 0
TX packets 53 bytes 9108 (8.8 KiB)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
[root@ubuntunew ~]# ./test.sh eth0
[ 172.815279] pktgen: Packet Generator for packet performance testing. Version: 2.75
Adding queue 0 of eth0
Configuring devices eth0@0
Running... ctrl^C to stop
[root@ubuntunew ~]# ifconfig eth0
eth0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
inet6 fe80::5054:ff:fe12:3456 prefixlen 64 scopeid 0x20<link>
ether 52:54:00:12:34:56 txqueuelen 1000 (Ethernet)
RX packets 183455 bytes 11748533 (11.2 MiB)
RX errors 0 dropped 0 overruns 0 frame 0
TX packets 183473 bytes 11749685 (11.2 MiB)
TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
Cindy Lu (7):
vhost/iommufd: Add the functions support iommufd
Kconfig: Add the new file vhost/iommufd
vhost: Add 3 new uapi to support iommufd
vdpa: change the map/unmap process to support iommufd
vdpa: Add new vdpa_config_ops
vdpa_sim :Add support for iommufd
iommufd: Skip the CACHE_COHERENCY and iommu group check
drivers/iommu/iommufd/device.c | 6 +-
drivers/vdpa/vdpa_sim/vdpa_sim.c | 8 ++
drivers/vhost/Kconfig | 1 +
drivers/vhost/Makefile | 1 +
drivers/vhost/iommufd.c | 151 +++++++++++++++++++++++
drivers/vhost/vdpa.c | 201 +++++++++++++++++++++++++++++++
drivers/vhost/vhost.h | 21 ++++
include/linux/vdpa.h | 34 +++++-
include/uapi/linux/vhost.h | 71 +++++++++++
9 files changed, 490 insertions(+), 4 deletions(-)
create mode 100644 drivers/vhost/iommufd.c
--
2.34.3
VHOST_VDPA_SET_IOMMU_FD: bind the device to iommufd device
VDPA_DEVICE_ATTACH_IOMMUFD_AS: Attach a vdpa device to an iommufd
address space specified by IOAS id.
VDPA_DEVICE_DETACH_IOMMUFD_AS: Detach a vdpa device
from the iommufd address space
Signed-off-by: Cindy Lu <[email protected]>
---
drivers/vhost/vdpa.c | 191 +++++++++++++++++++++++++++++++++++++
include/uapi/linux/vhost.h | 71 ++++++++++++++
2 files changed, 262 insertions(+)
diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index ec32f785dfde..91da012084e9 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -18,6 +18,7 @@
#include <linux/mm.h>
#include <linux/slab.h>
#include <linux/iommu.h>
+#include <linux/iommufd.h>
#include <linux/uuid.h>
#include <linux/vdpa.h>
#include <linux/nospec.h>
@@ -25,6 +26,8 @@
#include "vhost.h"
+MODULE_IMPORT_NS(IOMMUFD);
+
enum {
VHOST_VDPA_BACKEND_FEATURES =
(1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) |
@@ -69,6 +72,15 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
struct vhost_iotlb *iotlb, u64 start,
u64 last, u32 asid);
+void vhost_vdpa_lockdep_assert_held(struct vdpa_device *vdpa)
+{
+ struct vhost_vdpa *v = vdpa_get_drvdata(vdpa);
+
+ if (WARN_ON(!v))
+ return;
+ lockdep_assert_held(&v->vdev.mutex);
+}
+
static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
{
struct vhost_vdpa_as *as = container_of(iotlb, struct
@@ -497,6 +509,173 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v)
return ops->suspend(vdpa);
}
+static long vhost_vdpa_tmp_set_iommufd(struct vhost_vdpa *v, void __user *argp)
+{
+ struct device *dma_dev = vdpa_get_dma_dev(v->vdpa);
+ struct vhost_vdpa_set_iommufd set_iommufd;
+ struct vdpa_device *vdpa = v->vdpa;
+ struct iommufd_ctx *ictx;
+ unsigned long minsz;
+ u32 pt_id, dev_id;
+ struct fd f;
+ long r = 0;
+ int idx;
+
+ minsz = offsetofend(struct vhost_vdpa_set_iommufd, ioas_id);
+ if (copy_from_user(&set_iommufd, argp, minsz))
+ return -EFAULT;
+
+ if (set_iommufd.group_id >= v->nvqs)
+ return -ENOBUFS;
+
+ idx = array_index_nospec(set_iommufd.group_id, v->nvqs);
+
+ /* Unset IOMMUFD */
+ if (set_iommufd.iommufd < 0) {
+ if (!test_bit(idx, vdpa->vq_bitmap))
+ return -EINVAL;
+
+ if (!vdpa->iommufd_ictx || !vdpa->iommufd_device)
+ return -EINVAL;
+ if (atomic_read(&vdpa->iommufd_users)) {
+ atomic_dec(&vdpa->iommufd_users);
+ return 0;
+ }
+ vdpa_iommufd_unbind(v->vdpa);
+ vdpa->iommufd_device = NULL;
+ vdpa->iommufd_ictx = NULL;
+ clear_bit(idx, vdpa->vq_bitmap);
+ return iommu_attach_device(v->domain, dma_dev);
+ }
+ /* First opened virtqueue of this vdpa device */
+
+ if (!vdpa->vq_bitmap) {
+ vdpa->vq_bitmap = bitmap_alloc(v->nvqs, GFP_KERNEL);
+ }
+ ///if (test_bit(idx, vdpa->vq_bitmap))
+ //return -EBUSY;
+
+ /* For same device but different groups, ++refcount only */
+ if (vdpa->iommufd_device)
+ goto out_inc;
+
+ r = -EBADF;
+ f = fdget(set_iommufd.iommufd);
+ if (!f.file)
+ goto out_bitmap_free;
+
+ r = -EINVAL;
+ ictx = iommufd_ctx_from_file(f.file);
+ if (IS_ERR(ictx))
+ goto out_fdput;
+
+ if (v->domain)
+ iommu_detach_device(v->domain, dma_dev);
+
+#if 0
+ iommu_group_add_device(iommu_group_alloc(), &vdpa->dev);
+#endif
+ pt_id = set_iommufd.ioas_id;
+ r = vdpa_iommufd_bind(vdpa, ictx, &pt_id, &dev_id);
+ if (r)
+ goto out_reattach;
+
+ set_iommufd.out_dev_id = dev_id;
+ set_iommufd.out_hwpt_id = pt_id;
+ r = copy_to_user(argp + minsz, &set_iommufd.out_dev_id,
+ sizeof(set_iommufd.out_dev_id) +
+ sizeof(set_iommufd.out_hwpt_id)) ?
+ -EFAULT :
+ 0;
+ if (r)
+ goto out_device_unbind;
+ printk(KERN_ERR "[%s] %d called %p\n", __func__, __LINE__,
+ vdpa->iommufd_ictx);
+
+ vdpa->iommufd_ictx = ictx;
+
+out_inc:
+ atomic_inc(&vdpa->iommufd_users);
+ set_bit(idx, vdpa->vq_bitmap);
+
+ goto out_fdput;
+
+out_device_unbind:
+
+ vdpa_iommufd_unbind(vdpa);
+out_reattach:
+
+ iommu_attach_device(v->domain, dma_dev);
+ iommufd_ctx_put(ictx);
+out_fdput:
+ fdput(f);
+out_bitmap_free:
+ bitmap_free(vdpa->vq_bitmap);
+ return r;
+}
+int vdpa_ioctl_device_attach(struct vhost_vdpa *v, void __user *arg)
+{
+ struct vdpa_device_attach_iommufd_as attach;
+ unsigned long minsz;
+ int ret;
+
+ minsz = offsetofend(struct vdpa_device_attach_iommufd_as, ioas_id);
+
+ if (copy_from_user(&attach, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (attach.argsz < minsz || attach.flags ||
+ attach.ioas_id == IOMMUFD_INVALID_ID)
+ return -EINVAL;
+
+ if (!v->vdpa->config->bind_iommufd)
+ return -ENODEV;
+
+ if (!v->vdpa->iommufd_ictx) {
+ ret = -EINVAL;
+ return ret;
+ }
+
+ ret = v->vdpa->config->attach_ioas(v->vdpa, &attach.ioas_id);
+
+ if (ret)
+ return ret;
+
+ ret = copy_to_user(
+ (void __user *)arg +
+ offsetofend(struct vdpa_device_attach_iommufd_as,
+ flags),
+ &attach.ioas_id, sizeof(attach.ioas_id)) ?
+ -EFAULT :
+ 0;
+
+ if (ret)
+ return ret;
+
+ return 0;
+}
+
+int vdpa_ioctl_device_detach(struct vhost_vdpa *v, void __user *arg)
+{
+ struct vdpa_device_detach_iommufd_as detach;
+ unsigned long minsz;
+
+ minsz = offsetofend(struct vdpa_device_detach_iommufd_as, flags);
+
+ if (copy_from_user(&detach, (void __user *)arg, minsz))
+ return -EFAULT;
+
+ if (detach.argsz < minsz || detach.flags)
+ return -EINVAL;
+
+ if (!v->vdpa->config->bind_iommufd)
+ return -ENODEV;
+
+ if (v->vdpa->iommufd_ictx) {
+ return -EINVAL;
+ }
+ return v->vdpa->config->detach_ioas(v->vdpa);
+}
static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
void __user *argp)
@@ -655,6 +834,18 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
case VHOST_SET_LOG_FD:
r = -ENOIOCTLCMD;
break;
+ case VHOST_VDPA_SET_IOMMU_FD:
+
+ r = vhost_vdpa_tmp_set_iommufd(v, argp);
+ break;
+ case VDPA_DEVICE_ATTACH_IOMMUFD_AS:
+ r = vdpa_ioctl_device_attach(v, (void __user *)arg);
+ break;
+
+ case VDPA_DEVICE_DETACH_IOMMUFD_AS:
+ r = vdpa_ioctl_device_detach(v, (void __user *)arg);
+ break;
+
case VHOST_VDPA_SET_CONFIG_CALL:
r = vhost_vdpa_set_config_call(v, argp);
break;
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index f9f115a7c75b..cdda0c1860d8 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -45,6 +45,7 @@
#define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
/* Specify an eventfd file descriptor to signal on log write. */
#define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+/* Specify an iommufd file descriptor for IO address translation */
/* Ring setup. */
/* Set number of descriptors in ring. This parameter can not
@@ -180,4 +181,74 @@
*/
#define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D)
+/* vhost vdpa set iommufd
+ * Input parameters:
+ * @iommufd: file descriptor from /dev/iommu; pass -1 to unset
+ * @group_id: identifier of the group that a virtqueue belongs to
+ * @ioas_id: IOAS identifier returned from ioctl(IOMMU_IOAS_ALLOC)
+ * Output parameters:
+ * @out_dev_id: device identifier
+ * @out_hwpt_id: hardware IO pagetable identifier
+ */
+struct vhost_vdpa_set_iommufd {
+ __s32 iommufd;
+ __u32 group_id;
+ __u32 ioas_id;
+ __u32 out_dev_id;
+ __u32 out_hwpt_id;
+};
+
+#define VHOST_VDPA_SET_IOMMU_FD \
+ _IOW(VHOST_VIRTIO, 0x7e, struct vhost_vdpa_set_iommufd)
+
+/*
+ * VDPA_DEVICE_ATTACH_IOMMUFD_AS -
+ * _IOW(VHOST_VIRTIO, 0x7f, struct vdpa_device_attach_iommufd_as)
+ *
+ * Attach a vdpa device to an iommufd address space specified by IOAS
+ * id.
+ *
+ * Available only after a device has been bound to iommufd via
+ * VHOST_VDPA_SET_IOMMU_FD
+ *
+ * Undo by VDPA_DEVICE_DETACH_IOMMUFD_AS or device fd close.
+ *
+ * @argsz: user filled size of this data.
+ * @flags: must be 0.
+ * @ioas_id: Input the target id which can represent an ioas
+ * allocated via iommufd subsystem.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vdpa_device_attach_iommufd_as {
+ __u32 argsz;
+ __u32 flags;
+ __u32 ioas_id;
+};
+
+#define VDPA_DEVICE_ATTACH_IOMMUFD_AS \
+ _IOW(VHOST_VIRTIO, 0x7f, struct vdpa_device_attach_iommufd_as)
+
+/*
+ * VDPA_DEVICE_DETACH_IOMMUFD_AS
+ *
+ * Detach a vdpa device from the iommufd address space it has been
+ * attached to. After it, device should be in a blocking DMA state.
+ *
+ * Available only after a device has been bound to iommufd via
+ * VHOST_VDPA_SET_IOMMU_FD
+ *
+ * @argsz: user filled size of this data.
+ * @flags: must be 0.
+ *
+ * Return: 0 on success, -errno on failure.
+ */
+struct vdpa_device_detach_iommufd_as {
+ __u32 argsz;
+ __u32 flags;
+};
+
+#define VDPA_DEVICE_DETACH_IOMMUFD_AS \
+ _IOW(VHOST_VIRTIO, 0x83, struct vdpa_device_detach_iommufd_as)
+
#endif
--
2.34.3
Add new vdpa_config_ops to support iommufd
Signed-off-by: Cindy Lu <[email protected]>
---
drivers/vdpa/vdpa_sim/vdpa_sim.c | 8 ++++++++
1 file changed, 8 insertions(+)
diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
index cb88891b44a8..55e6f45bb274 100644
--- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
+++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
@@ -727,6 +727,10 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
.dma_map = vdpasim_dma_map,
.dma_unmap = vdpasim_dma_unmap,
.free = vdpasim_free,
+ .bind_iommufd = vdpa_iommufd_emulated_bind,
+ .unbind_iommufd = vdpa_iommufd_emulated_unbind,
+ .attach_ioas = vdpa_iommufd_emulated_attach_ioas,
+ .detach_ioas = vdpa_iommufd_emulated_detach_ioas,
};
static const struct vdpa_config_ops vdpasim_batch_config_ops = {
@@ -759,6 +763,10 @@ static const struct vdpa_config_ops vdpasim_batch_config_ops = {
.set_group_asid = vdpasim_set_group_asid,
.set_map = vdpasim_set_map,
.free = vdpasim_free,
+ .bind_iommufd = vdpa_iommufd_emulated_bind,
+ .unbind_iommufd = vdpa_iommufd_emulated_unbind,
+ .attach_ioas = vdpa_iommufd_emulated_attach_ioas,
+ .detach_ioas = vdpa_iommufd_emulated_detach_ioas,
};
MODULE_VERSION(DRV_VERSION);
--
2.34.3
On Sun, Sep 24, 2023 at 01:05:36AM +0800, Cindy Lu wrote:
> +/* vhost vdpa set iommufd
> + * Input parameters:
> + * @iommufd: file descriptor from /dev/iommu; pass -1 to unset
> + * @group_id: identifier of the group that a virtqueue belongs to
> + * @ioas_id: IOAS identifier returned from ioctl(IOMMU_IOAS_ALLOC)
> + * Output parameters:
> + * @out_dev_id: device identifier
> + * @out_hwpt_id: hardware IO pagetable identifier
> + */
> +struct vhost_vdpa_set_iommufd {
> + __s32 iommufd;
> + __u32 group_id;
> + __u32 ioas_id;
> + __u32 out_dev_id;
> + __u32 out_hwpt_id;
> +};
> +
> +#define VHOST_VDPA_SET_IOMMU_FD \
> + _IOW(VHOST_VIRTIO, 0x7e, struct vhost_vdpa_set_iommufd)
> +
> +/*
> + * VDPA_DEVICE_ATTACH_IOMMUFD_AS -
> + * _IOW(VHOST_VIRTIO, 0x7f, struct vdpa_device_attach_iommufd_as)
> + *
> + * Attach a vdpa device to an iommufd address space specified by IOAS
> + * id.
> + *
> + * Available only after a device has been bound to iommufd via
> + * VHOST_VDPA_SET_IOMMU_FD
> + *
> + * Undo by VDPA_DEVICE_DETACH_IOMMUFD_AS or device fd close.
> + *
> + * @argsz: user filled size of this data.
> + * @flags: must be 0.
> + * @ioas_id: Input the target id which can represent an ioas
> + * allocated via iommufd subsystem.
> + *
> + * Return: 0 on success, -errno on failure.
> + */
> +struct vdpa_device_attach_iommufd_as {
> + __u32 argsz;
> + __u32 flags;
> + __u32 ioas_id;
> +};
I don't know this at all, but it seems really weird that the API
taking in the iommfd is more specific (eg includes the group_id) than
the API taking in the ioas.
I'd expect that you have one iommfd setup per virtio FD.
And the various virtio queues would be able to be linked to their own
IOAS.
I'm not sure multiple iommufd's per virito FD is worthwhile.
Jason
On Sun, Sep 24, 2023 at 01:05:39AM +0800, Cindy Lu wrote:
> Add new vdpa_config_ops to support iommufd
>
> Signed-off-by: Cindy Lu <[email protected]>
> ---
> drivers/vdpa/vdpa_sim/vdpa_sim.c | 8 ++++++++
> 1 file changed, 8 insertions(+)
>
> diff --git a/drivers/vdpa/vdpa_sim/vdpa_sim.c b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> index cb88891b44a8..55e6f45bb274 100644
> --- a/drivers/vdpa/vdpa_sim/vdpa_sim.c
> +++ b/drivers/vdpa/vdpa_sim/vdpa_sim.c
> @@ -727,6 +727,10 @@ static const struct vdpa_config_ops vdpasim_config_ops = {
> .dma_map = vdpasim_dma_map,
> .dma_unmap = vdpasim_dma_unmap,
> .free = vdpasim_free,
> + .bind_iommufd = vdpa_iommufd_emulated_bind,
> + .unbind_iommufd = vdpa_iommufd_emulated_unbind,
> + .attach_ioas = vdpa_iommufd_emulated_attach_ioas,
> + .detach_ioas = vdpa_iommufd_emulated_detach_ioas,
> };
Er, this series never calls iommufd_access_pin_pages() or
iommufd_access_rw(), so something pretty big is missing
Jason
On Sun, Sep 24, 2023 at 1:05 AM Cindy Lu <[email protected]> wrote:
>
> Hi All
> Really apologize for the delay, this is the draft RFC for
> iommufd support for vdpa, This code provides the basic function
> for iommufd support
>
> The code was tested and passed in device vdpa_sim_net
> The qemu code is
> https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
> The kernel code is
> https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
>
> ToDo
> 1. this code is out of date and needs to clean and rebase on the latest code
> 2. this code has some workaround, I Skip the check for
> iommu_group and CACHE_COHERENCY, also some misc issues like need to add
> mutex for iommfd operations
> 3. only test in emulated device, other modes not tested yet
>
> After addressed these problems I will send out a new version for RFC. I will
> provide the code in 3 weeks
Something more needs to be done after a quick glance at the codes.
1) The support for device with platform IOMMU support
2) The support for multiple ASes per device
...
Thanks
>
> Thanks
> Cindy
> Signed-off-by: Cindy Lu <[email protected]>
> The test step is
> 1. create vdpa_sim device
> ...
> vdpa dev add name vdpa15 mgmtdev vdpasim_net
> ...
> 2. load the VM with the command
> -object iommufd,id=iommufd0 \
> -device virtio-net-pci,netdev=vhost-vdpa1,disable-legacy=on,disable-modern=off\
> -netdev type=vhost-vdpa,vhostdev=/dev/vhost-vdpa-0,id=vhost-vdpa1,iommufd=iommufd0\
>
> 3. in guest VM you can find the vdpa_sim port works well.
> [root@ubuntunew ~]# ifconfig eth0
> eth0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
> inet6 fe80::5054:ff:fe12:3456 prefixlen 64 scopeid 0x20<link>
> ether 52:54:00:12:34:56 txqueuelen 1000 (Ethernet)
> RX packets 53 bytes 9108 (8.8 KiB)
> RX errors 0 dropped 0 overruns 0 frame 0
> TX packets 53 bytes 9108 (8.8 KiB)
> TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
>
> [root@ubuntunew ~]# ./test.sh eth0
> [ 172.815279] pktgen: Packet Generator for packet performance testing. Version: 2.75
> Adding queue 0 of eth0
> Configuring devices eth0@0
> Running... ctrl^C to stop
>
> [root@ubuntunew ~]# ifconfig eth0
> eth0: flags=4163<UP,BROADCAST,RUNNING,MULTICAST> mtu 1500
> inet6 fe80::5054:ff:fe12:3456 prefixlen 64 scopeid 0x20<link>
> ether 52:54:00:12:34:56 txqueuelen 1000 (Ethernet)
> RX packets 183455 bytes 11748533 (11.2 MiB)
> RX errors 0 dropped 0 overruns 0 frame 0
> TX packets 183473 bytes 11749685 (11.2 MiB)
> TX errors 0 dropped 0 overruns 0 carrier 0 collisions 0
>
> Cindy Lu (7):
> vhost/iommufd: Add the functions support iommufd
> Kconfig: Add the new file vhost/iommufd
> vhost: Add 3 new uapi to support iommufd
> vdpa: change the map/unmap process to support iommufd
> vdpa: Add new vdpa_config_ops
> vdpa_sim :Add support for iommufd
> iommufd: Skip the CACHE_COHERENCY and iommu group check
>
> drivers/iommu/iommufd/device.c | 6 +-
> drivers/vdpa/vdpa_sim/vdpa_sim.c | 8 ++
> drivers/vhost/Kconfig | 1 +
> drivers/vhost/Makefile | 1 +
> drivers/vhost/iommufd.c | 151 +++++++++++++++++++++++
> drivers/vhost/vdpa.c | 201 +++++++++++++++++++++++++++++++
> drivers/vhost/vhost.h | 21 ++++
> include/linux/vdpa.h | 34 +++++-
> include/uapi/linux/vhost.h | 71 +++++++++++
> 9 files changed, 490 insertions(+), 4 deletions(-)
> create mode 100644 drivers/vhost/iommufd.c
>
> --
> 2.34.3
>
On Sun, Sep 24, 2023 at 1:05 AM Cindy Lu <[email protected]> wrote:
>
> VHOST_VDPA_SET_IOMMU_FD: bind the device to iommufd device
>
> VDPA_DEVICE_ATTACH_IOMMUFD_AS: Attach a vdpa device to an iommufd
> address space specified by IOAS id.
>
> VDPA_DEVICE_DETACH_IOMMUFD_AS: Detach a vdpa device
> from the iommufd address space
>
> Signed-off-by: Cindy Lu <[email protected]>
> ---
> drivers/vhost/vdpa.c | 191 +++++++++++++++++++++++++++++++++++++
> include/uapi/linux/vhost.h | 71 ++++++++++++++
> 2 files changed, 262 insertions(+)
>
> diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
> index ec32f785dfde..91da012084e9 100644
> --- a/drivers/vhost/vdpa.c
> +++ b/drivers/vhost/vdpa.c
> @@ -18,6 +18,7 @@
> #include <linux/mm.h>
> #include <linux/slab.h>
> #include <linux/iommu.h>
> +#include <linux/iommufd.h>
> #include <linux/uuid.h>
> #include <linux/vdpa.h>
> #include <linux/nospec.h>
> @@ -25,6 +26,8 @@
>
> #include "vhost.h"
>
> +MODULE_IMPORT_NS(IOMMUFD);
> +
> enum {
> VHOST_VDPA_BACKEND_FEATURES =
> (1ULL << VHOST_BACKEND_F_IOTLB_MSG_V2) |
> @@ -69,6 +72,15 @@ static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v,
> struct vhost_iotlb *iotlb, u64 start,
> u64 last, u32 asid);
>
> +void vhost_vdpa_lockdep_assert_held(struct vdpa_device *vdpa)
> +{
> + struct vhost_vdpa *v = vdpa_get_drvdata(vdpa);
> +
> + if (WARN_ON(!v))
> + return;
> + lockdep_assert_held(&v->vdev.mutex);
> +}
> +
> static inline u32 iotlb_to_asid(struct vhost_iotlb *iotlb)
> {
> struct vhost_vdpa_as *as = container_of(iotlb, struct
> @@ -497,6 +509,173 @@ static long vhost_vdpa_suspend(struct vhost_vdpa *v)
>
> return ops->suspend(vdpa);
> }
> +static long vhost_vdpa_tmp_set_iommufd(struct vhost_vdpa *v, void __user *argp)
> +{
> + struct device *dma_dev = vdpa_get_dma_dev(v->vdpa);
> + struct vhost_vdpa_set_iommufd set_iommufd;
> + struct vdpa_device *vdpa = v->vdpa;
> + struct iommufd_ctx *ictx;
> + unsigned long minsz;
> + u32 pt_id, dev_id;
> + struct fd f;
> + long r = 0;
> + int idx;
> +
> + minsz = offsetofend(struct vhost_vdpa_set_iommufd, ioas_id);
> + if (copy_from_user(&set_iommufd, argp, minsz))
> + return -EFAULT;
> +
> + if (set_iommufd.group_id >= v->nvqs)
> + return -ENOBUFS;
Needs to be v->ngroups but as replied below, but I think it should be asid.
> +
> + idx = array_index_nospec(set_iommufd.group_id, v->nvqs);
> +
> + /* Unset IOMMUFD */
> + if (set_iommufd.iommufd < 0) {
> + if (!test_bit(idx, vdpa->vq_bitmap))
> + return -EINVAL;
> +
> + if (!vdpa->iommufd_ictx || !vdpa->iommufd_device)
> + return -EINVAL;
> + if (atomic_read(&vdpa->iommufd_users)) {
> + atomic_dec(&vdpa->iommufd_users);
> + return 0;
> + }
> + vdpa_iommufd_unbind(v->vdpa);
> + vdpa->iommufd_device = NULL;
> + vdpa->iommufd_ictx = NULL;
> + clear_bit(idx, vdpa->vq_bitmap);
> + return iommu_attach_device(v->domain, dma_dev);
> + }
> + /* First opened virtqueue of this vdpa device */
> +
> + if (!vdpa->vq_bitmap) {
> + vdpa->vq_bitmap = bitmap_alloc(v->nvqs, GFP_KERNEL);
> + }
> + ///if (test_bit(idx, vdpa->vq_bitmap))
> + //return -EBUSY;
> +
> + /* For same device but different groups, ++refcount only */
> + if (vdpa->iommufd_device)
> + goto out_inc;
> +
> + r = -EBADF;
> + f = fdget(set_iommufd.iommufd);
> + if (!f.file)
> + goto out_bitmap_free;
> +
> + r = -EINVAL;
> + ictx = iommufd_ctx_from_file(f.file);
> + if (IS_ERR(ictx))
> + goto out_fdput;
> +
> + if (v->domain)
> + iommu_detach_device(v->domain, dma_dev);
> +
> +#if 0
> + iommu_group_add_device(iommu_group_alloc(), &vdpa->dev);
> +#endif
> + pt_id = set_iommufd.ioas_id;
> + r = vdpa_iommufd_bind(vdpa, ictx, &pt_id, &dev_id);
> + if (r)
> + goto out_reattach;
> +
> + set_iommufd.out_dev_id = dev_id;
> + set_iommufd.out_hwpt_id = pt_id;
> + r = copy_to_user(argp + minsz, &set_iommufd.out_dev_id,
> + sizeof(set_iommufd.out_dev_id) +
> + sizeof(set_iommufd.out_hwpt_id)) ?
> + -EFAULT :
> + 0;
> + if (r)
> + goto out_device_unbind;
> + printk(KERN_ERR "[%s] %d called %p\n", __func__, __LINE__,
> + vdpa->iommufd_ictx);
> +
> + vdpa->iommufd_ictx = ictx;
> +
> +out_inc:
> + atomic_inc(&vdpa->iommufd_users);
> + set_bit(idx, vdpa->vq_bitmap);
> +
> + goto out_fdput;
> +
> +out_device_unbind:
> +
> + vdpa_iommufd_unbind(vdpa);
> +out_reattach:
> +
> + iommu_attach_device(v->domain, dma_dev);
> + iommufd_ctx_put(ictx);
> +out_fdput:
> + fdput(f);
> +out_bitmap_free:
> + bitmap_free(vdpa->vq_bitmap);
> + return r;
> +}
> +int vdpa_ioctl_device_attach(struct vhost_vdpa *v, void __user *arg)
> +{
> + struct vdpa_device_attach_iommufd_as attach;
> + unsigned long minsz;
> + int ret;
> +
> + minsz = offsetofend(struct vdpa_device_attach_iommufd_as, ioas_id);
> +
> + if (copy_from_user(&attach, (void __user *)arg, minsz))
> + return -EFAULT;
> +
> + if (attach.argsz < minsz || attach.flags ||
> + attach.ioas_id == IOMMUFD_INVALID_ID)
> + return -EINVAL;
> +
> + if (!v->vdpa->config->bind_iommufd)
> + return -ENODEV;
> +
> + if (!v->vdpa->iommufd_ictx) {
> + ret = -EINVAL;
> + return ret;
> + }
> +
> + ret = v->vdpa->config->attach_ioas(v->vdpa, &attach.ioas_id);
> +
> + if (ret)
> + return ret;
> +
> + ret = copy_to_user(
> + (void __user *)arg +
> + offsetofend(struct vdpa_device_attach_iommufd_as,
> + flags),
> + &attach.ioas_id, sizeof(attach.ioas_id)) ?
> + -EFAULT :
> + 0;
> +
> + if (ret)
> + return ret;
> +
> + return 0;
> +}
> +
> +int vdpa_ioctl_device_detach(struct vhost_vdpa *v, void __user *arg)
> +{
> + struct vdpa_device_detach_iommufd_as detach;
> + unsigned long minsz;
> +
> + minsz = offsetofend(struct vdpa_device_detach_iommufd_as, flags);
> +
> + if (copy_from_user(&detach, (void __user *)arg, minsz))
> + return -EFAULT;
> +
> + if (detach.argsz < minsz || detach.flags)
> + return -EINVAL;
> +
> + if (!v->vdpa->config->bind_iommufd)
> + return -ENODEV;
> +
> + if (v->vdpa->iommufd_ictx) {
> + return -EINVAL;
> + }
> + return v->vdpa->config->detach_ioas(v->vdpa);
> +}
>
> static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
> void __user *argp)
> @@ -655,6 +834,18 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
> case VHOST_SET_LOG_FD:
> r = -ENOIOCTLCMD;
> break;
> + case VHOST_VDPA_SET_IOMMU_FD:
> +
> + r = vhost_vdpa_tmp_set_iommufd(v, argp);
> + break;
> + case VDPA_DEVICE_ATTACH_IOMMUFD_AS:
> + r = vdpa_ioctl_device_attach(v, (void __user *)arg);
> + break;
> +
> + case VDPA_DEVICE_DETACH_IOMMUFD_AS:
> + r = vdpa_ioctl_device_detach(v, (void __user *)arg);
> + break;
> +
> case VHOST_VDPA_SET_CONFIG_CALL:
> r = vhost_vdpa_set_config_call(v, argp);
> break;
> diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
> index f9f115a7c75b..cdda0c1860d8 100644
> --- a/include/uapi/linux/vhost.h
> +++ b/include/uapi/linux/vhost.h
> @@ -45,6 +45,7 @@
> #define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
> /* Specify an eventfd file descriptor to signal on log write. */
> #define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
> +/* Specify an iommufd file descriptor for IO address translation */
>
> /* Ring setup. */
> /* Set number of descriptors in ring. This parameter can not
> @@ -180,4 +181,74 @@
> */
> #define VHOST_VDPA_SUSPEND _IO(VHOST_VIRTIO, 0x7D)
>
> +/* vhost vdpa set iommufd
> + * Input parameters:
> + * @iommufd: file descriptor from /dev/iommu; pass -1 to unset
> + * @group_id: identifier of the group that a virtqueue belongs to
> + * @ioas_id: IOAS identifier returned from ioctl(IOMMU_IOAS_ALLOC)
> + * Output parameters:
> + * @out_dev_id: device identifier
> + * @out_hwpt_id: hardware IO pagetable identifier
> + */
> +struct vhost_vdpa_set_iommufd {
> + __s32 iommufd;
> + __u32 group_id;
This needs to be ASID of a vdpa device, as the current address space
could be shared among various groups. And the device do translation
based on:
virtqueue -> group -> AS -> IOAS of iommufd
Thanks
> + __u32 ioas_id;
> + __u32 out_dev_id;
> + __u32 out_hwpt_id;
> +};
> +
> +#define VHOST_VDPA_SET_IOMMU_FD \
> + _IOW(VHOST_VIRTIO, 0x7e, struct vhost_vdpa_set_iommufd)
> +
> +/*
> + * VDPA_DEVICE_ATTACH_IOMMUFD_AS -
> + * _IOW(VHOST_VIRTIO, 0x7f, struct vdpa_device_attach_iommufd_as)
> + *
> + * Attach a vdpa device to an iommufd address space specified by IOAS
> + * id.
> + *
> + * Available only after a device has been bound to iommufd via
> + * VHOST_VDPA_SET_IOMMU_FD
> + *
> + * Undo by VDPA_DEVICE_DETACH_IOMMUFD_AS or device fd close.
> + *
> + * @argsz: user filled size of this data.
> + * @flags: must be 0.
> + * @ioas_id: Input the target id which can represent an ioas
> + * allocated via iommufd subsystem.
> + *
> + * Return: 0 on success, -errno on failure.
> + */
> +struct vdpa_device_attach_iommufd_as {
> + __u32 argsz;
> + __u32 flags;
> + __u32 ioas_id;
> +};
> +
> +#define VDPA_DEVICE_ATTACH_IOMMUFD_AS \
> + _IOW(VHOST_VIRTIO, 0x7f, struct vdpa_device_attach_iommufd_as)
> +
> +/*
> + * VDPA_DEVICE_DETACH_IOMMUFD_AS
> + *
> + * Detach a vdpa device from the iommufd address space it has been
> + * attached to. After it, device should be in a blocking DMA state.
> + *
> + * Available only after a device has been bound to iommufd via
> + * VHOST_VDPA_SET_IOMMU_FD
> + *
> + * @argsz: user filled size of this data.
> + * @flags: must be 0.
> + *
> + * Return: 0 on success, -errno on failure.
> + */
> +struct vdpa_device_detach_iommufd_as {
> + __u32 argsz;
> + __u32 flags;
> +};
> +
> +#define VDPA_DEVICE_DETACH_IOMMUFD_AS \
> + _IOW(VHOST_VIRTIO, 0x83, struct vdpa_device_detach_iommufd_as)
> +
> #endif
> --
> 2.34.3
>
On Sun, Sep 24, 2023 at 01:05:33AM +0800, Cindy Lu wrote:
> Hi All
> Really apologize for the delay, this is the draft RFC for
> iommufd support for vdpa, This code provides the basic function
> for iommufd support
>
> The code was tested and passed in device vdpa_sim_net
> The qemu code is
> https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
> The kernel code is
> https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
>
> ToDo
> 1. this code is out of date and needs to clean and rebase on the latest code
> 2. this code has some workaround, I Skip the check for
> iommu_group and CACHE_COHERENCY, also some misc issues like need to add
> mutex for iommfd operations
> 3. only test in emulated device, other modes not tested yet
>
> After addressed these problems I will send out a new version for RFC. I will
> provide the code in 3 weeks
What's the status here?
--
MST
On Thu, Oct 26, 2023 at 2:42 PM Michael S. Tsirkin <[email protected]> wrote:
>
> On Sun, Sep 24, 2023 at 01:05:33AM +0800, Cindy Lu wrote:
> > Hi All
> > Really apologize for the delay, this is the draft RFC for
> > iommufd support for vdpa, This code provides the basic function
> > for iommufd support
> >
> > The code was tested and passed in device vdpa_sim_net
> > The qemu code is
> > https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
> > The kernel code is
> > https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
> >
> > ToDo
> > 1. this code is out of date and needs to clean and rebase on the latest code
> > 2. this code has some workaround, I Skip the check for
> > iommu_group and CACHE_COHERENCY, also some misc issues like need to add
> > mutex for iommfd operations
> > 3. only test in emulated device, other modes not tested yet
> >
> > After addressed these problems I will send out a new version for RFC. I will
> > provide the code in 3 weeks
>
> What's the status here?
>
Hi Michael
The code is finished, but I found some bug after adding the support for ASID,
will post the new version after this bug is fixed, should be next week
Thanks
Cindy
> --
> MST
>
On Thu, Oct 26, 2023 at 02:48:07PM +0800, Cindy Lu wrote:
> On Thu, Oct 26, 2023 at 2:42 PM Michael S. Tsirkin <[email protected]> wrote:
> >
> > On Sun, Sep 24, 2023 at 01:05:33AM +0800, Cindy Lu wrote:
> > > Hi All
> > > Really apologize for the delay, this is the draft RFC for
> > > iommufd support for vdpa, This code provides the basic function
> > > for iommufd support
> > >
> > > The code was tested and passed in device vdpa_sim_net
> > > The qemu code is
> > > https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
> > > The kernel code is
> > > https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
> > >
> > > ToDo
> > > 1. this code is out of date and needs to clean and rebase on the latest code
> > > 2. this code has some workaround, I Skip the check for
> > > iommu_group and CACHE_COHERENCY, also some misc issues like need to add
> > > mutex for iommfd operations
> > > 3. only test in emulated device, other modes not tested yet
> > >
> > > After addressed these problems I will send out a new version for RFC. I will
> > > provide the code in 3 weeks
> >
> > What's the status here?
> >
> Hi Michael
> The code is finished, but I found some bug after adding the support for ASID,
> will post the new version after this bug is fixed, should be next week
> Thanks
> Cindy
We'll miss this merge window then.
> > --
> > MST
> >
On Thu, Oct 26, 2023 at 2:49 PM Michael S. Tsirkin <[email protected]> wrote:
>
> On Thu, Oct 26, 2023 at 02:48:07PM +0800, Cindy Lu wrote:
> > On Thu, Oct 26, 2023 at 2:42 PM Michael S. Tsirkin <[email protected]> wrote:
> > >
> > > On Sun, Sep 24, 2023 at 01:05:33AM +0800, Cindy Lu wrote:
> > > > Hi All
> > > > Really apologize for the delay, this is the draft RFC for
> > > > iommufd support for vdpa, This code provides the basic function
> > > > for iommufd support
> > > >
> > > > The code was tested and passed in device vdpa_sim_net
> > > > The qemu code is
> > > > https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
> > > > The kernel code is
> > > > https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
> > > >
> > > > ToDo
> > > > 1. this code is out of date and needs to clean and rebase on the latest code
> > > > 2. this code has some workaround, I Skip the check for
> > > > iommu_group and CACHE_COHERENCY, also some misc issues like need to add
> > > > mutex for iommfd operations
> > > > 3. only test in emulated device, other modes not tested yet
> > > >
> > > > After addressed these problems I will send out a new version for RFC. I will
> > > > provide the code in 3 weeks
> > >
> > > What's the status here?
> > >
> > Hi Michael
> > The code is finished, but I found some bug after adding the support for ASID,
> > will post the new version after this bug is fixed, should be next week
> > Thanks
> > Cindy
>
>
> We'll miss this merge window then.
>
thanks Micheal， I will try my best. will post the new version as soon as I can
Thanks
Cindy
> > > --
> > > MST
> > >
>
On Thu, Oct 26, 2023 at 02:48:07PM +0800, Cindy Lu wrote:
> On Thu, Oct 26, 2023 at 2:42 PM Michael S. Tsirkin <[email protected]> wrote:
> >
> > On Sun, Sep 24, 2023 at 01:05:33AM +0800, Cindy Lu wrote:
> > > Hi All
> > > Really apologize for the delay, this is the draft RFC for
> > > iommufd support for vdpa, This code provides the basic function
> > > for iommufd support
> > >
> > > The code was tested and passed in device vdpa_sim_net
> > > The qemu code is
> > > https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
> > > The kernel code is
> > > https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
> > >
> > > ToDo
> > > 1. this code is out of date and needs to clean and rebase on the latest code
> > > 2. this code has some workaround, I Skip the check for
> > > iommu_group and CACHE_COHERENCY, also some misc issues like need to add
> > > mutex for iommfd operations
> > > 3. only test in emulated device, other modes not tested yet
> > >
> > > After addressed these problems I will send out a new version for RFC. I will
> > > provide the code in 3 weeks
> >
> > What's the status here?
> >
> Hi Michael
> The code is finished, but I found some bug after adding the support for ASID,
> will post the new version after this bug is fixed, should be next week
> Thanks
> Cindy
The week is almost gone, what's going on?
> > --
> > MST
> >
On Thu, Nov 2, 2023 at 6:02 PM Michael S. Tsirkin <[email protected]> wrote:
>
> On Thu, Oct 26, 2023 at 02:48:07PM +0800, Cindy Lu wrote:
> > On Thu, Oct 26, 2023 at 2:42 PM Michael S. Tsirkin <[email protected]> wrote:
> > >
> > > On Sun, Sep 24, 2023 at 01:05:33AM +0800, Cindy Lu wrote:
> > > > Hi All
> > > > Really apologize for the delay, this is the draft RFC for
> > > > iommufd support for vdpa, This code provides the basic function
> > > > for iommufd support
> > > >
> > > > The code was tested and passed in device vdpa_sim_net
> > > > The qemu code is
> > > > https://gitlab.com/lulu6/gitlabqemutmp/-/tree/iommufdRFC
> > > > The kernel code is
> > > > https://gitlab.com/lulu6/vhost/-/tree/iommufdRFC
> > > >
> > > > ToDo
> > > > 1. this code is out of date and needs to clean and rebase on the latest code
> > > > 2. this code has some workaround, I Skip the check for
> > > > iommu_group and CACHE_COHERENCY, also some misc issues like need to add
> > > > mutex for iommfd operations
> > > > 3. only test in emulated device, other modes not tested yet
> > > >
> > > > After addressed these problems I will send out a new version for RFC. I will
> > > > provide the code in 3 weeks
> > >
> > > What's the status here?
> > >
> > Hi Michael
> > The code is finished, but I found some bug after adding the support for ASID,
> > will post the new version after this bug is fixed, should be next week
> > Thanks
> > Cindy
>
> The week is almost gone, what's going on?
>
thanks, Micheal, I will send it out tomorrow
Thanks
Cindy
>
> > > --
> > > MST
> > >
>