Virtualization - Sep 2023 - [PATCH RFC v3 0/4] vdpa: decouple reset of iotlb mapping from device reset

In order to reduce needlessly high setup and teardown cost
of iotlb mapping during live migration, it's crucial to
decouple the vhost-vdpa iotlb abstraction from the virtio
device life cycle, i.e. iotlb mappings should be left
intact across virtio device reset [1]. For it to work, the
on-chip IOMMU parent device should implement a separate
.reset_map() operation callback to restore 1:1 DMA mapping
without having to resort to the .reset() callback, which
is mainly used to reset virtio specific device state.
This new .reset_map() callback will be invoked only when
the vhost-vdpa driver is to be removed and detached from
the vdpa bus, such that other vdpa bus drivers, e.g. 
virtio-vdpa, can start with 1:1 DMA mapping when they
are attached. For the context, those on-chip IOMMU parent
devices, create the 1:1 DMA mapping at vdpa device add,
and they would implicitly destroy the 1:1 mapping when
the first .set_map or .dma_map callback is invoked.

[1] Reducing vdpa migration downtime because of memory pin / maps
https://www.mail-archive.com/qemu-devel at nongnu.org/msg953755.html

---
RFC v3:
- fix missing return due to merge error in patch #4

RFC v2:
- rebased on top of the "[PATCH RFC v2 0/3] vdpa: dedicated descriptor
table group" series:
 
https://lore.kernel.org/virtualization/1694248959-13369-1-git-send-email-si-wei.liu
at oracle.com/

---

Si-Wei Liu (4):
  vdpa: introduce .reset_map operation callback
  vdpa/mlx5: implement .reset_map driver op
  vhost-vdpa: should restore 1:1 dma mapping before detaching driver
  vhost-vdpa: introduce IOTLB_PERSIST backend feature bit

 drivers/vdpa/mlx5/core/mlx5_vdpa.h |  1 +
 drivers/vdpa/mlx5/core/mr.c        | 70 +++++++++++++++++++++++---------------
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 18 +++++++---
 drivers/vhost/vdpa.c               | 32 ++++++++++++++++-
 include/linux/vdpa.h               |  7 ++++
 include/uapi/linux/vhost_types.h   |  2 ++
 6 files changed, 96 insertions(+), 34 deletions(-)

-- 
1.8.3.1

On-chip IOMMU parent driver could use it to restore memory mapping
to the initial state.

Signed-off-by: Si-Wei Liu <si-wei.liu at oracle.com>
---
 include/linux/vdpa.h | 7 +++++++
 1 file changed, 7 insertions(+)

diff --git a/include/linux/vdpa.h b/include/linux/vdpa.h
index 17a4efa..daecf55 100644
--- a/include/linux/vdpa.h
+++ b/include/linux/vdpa.h
@@ -324,6 +324,12 @@ struct vdpa_map_file {
  *				@iova: iova to be unmapped
  *				@size: size of the area
  *				Returns integer: success (0) or error (< 0)
+ * @reset_map:			Reset device memory mapping (optional)
+ *				Needed for device that using device
+ *				specific DMA translation (on-chip IOMMU)
+ *				@vdev: vdpa device
+ *				@asid: address space identifier
+ *				Returns integer: success (0) or error (< 0)
  * @get_vq_dma_dev:		Get the dma device for a specific
  *				virtqueue (optional)
  *				@vdev: vdpa device
@@ -401,6 +407,7 @@ struct vdpa_config_ops {
 		       u64 iova, u64 size, u64 pa, u32 perm, void *opaque);
 	int (*dma_unmap)(struct vdpa_device *vdev, unsigned int asid,
 			 u64 iova, u64 size);
+	int (*reset_map)(struct vdpa_device *vdev, unsigned int asid);
 	int (*set_group_asid)(struct vdpa_device *vdev, unsigned int group,
 			      unsigned int asid);
 	struct device *(*get_vq_dma_dev)(struct vdpa_device *vdev, u16 idx);
-- 
1.8.3.1

Today, mlx5_vdpa gets started by preallocate 1:1 DMA mapping at
device creation time, while this 1:1 mapping will be implicitly
destroyed when the first .set_map call is invoked. Everytime
when the .reset callback is invoked, any mapping left behind will
be dropped then reset back to the initial 1:1 DMA mapping.

In order to reduce excessive memory mapping cost during live
migration, it is desirable to decouple the vhost-vdpa iotlb
abstraction from the virtio device life cycle, i.e. mappings
should be left intact across virtio device reset. Leverage the
.reset_map callback to reset memory mapping, then the device
.reset routine can run free from having to clean up memory
mappings.

Signed-off-by: Si-Wei Liu <si-wei.liu at oracle.com>

---
RFC v1 -> v2:
  - fix error path when both CVQ and DVQ fall in same asid
---
 drivers/vdpa/mlx5/core/mlx5_vdpa.h |  1 +
 drivers/vdpa/mlx5/core/mr.c        | 70 +++++++++++++++++++++++---------------
 drivers/vdpa/mlx5/net/mlx5_vnet.c  | 18 +++++++---
 3 files changed, 56 insertions(+), 33 deletions(-)

diff --git a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
index b53420e..5c9a25a 100644
--- a/drivers/vdpa/mlx5/core/mlx5_vdpa.h
+++ b/drivers/vdpa/mlx5/core/mlx5_vdpa.h
@@ -123,6 +123,7 @@ int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct
vhost_iotlb *iotlb,
 			unsigned int asid);
 void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev);
 void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev, unsigned int asid);
+int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid);
 
 #define mlx5_vdpa_warn(__dev, format, ...)                                     
\
 	dev_warn((__dev)->mdev->device, "%s:%d:(pid %d) warning: "
format, __func__, __LINE__,     \
diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c
index 5a1971fc..ec2c7b4e1 100644
--- a/drivers/vdpa/mlx5/core/mr.c
+++ b/drivers/vdpa/mlx5/core/mr.c
@@ -489,21 +489,15 @@ static void destroy_user_mr(struct mlx5_vdpa_dev *mvdev,
struct mlx5_vdpa_mr *mr
 	}
 }
 
-static void _mlx5_vdpa_destroy_cvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int
asid)
+static void _mlx5_vdpa_destroy_cvq_mr(struct mlx5_vdpa_dev *mvdev)
 {
-	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
-		return;
-
 	prune_iotlb(mvdev);
 }
 
-static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev, unsigned int
asid)
+static void _mlx5_vdpa_destroy_dvq_mr(struct mlx5_vdpa_dev *mvdev)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
-		return;
-
 	if (!mr->initialized)
 		return;
 
@@ -521,8 +515,10 @@ void mlx5_vdpa_destroy_mr_asid(struct mlx5_vdpa_dev *mvdev,
unsigned int asid)
 
 	mutex_lock(&mr->mkey_mtx);
 
-	_mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
-	_mlx5_vdpa_destroy_cvq_mr(mvdev, asid);
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid)
+		_mlx5_vdpa_destroy_dvq_mr(mvdev);
+	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid)
+		_mlx5_vdpa_destroy_cvq_mr(mvdev);
 
 	mutex_unlock(&mr->mkey_mtx);
 }
@@ -534,25 +530,17 @@ void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev)
 }
 
 static int _mlx5_vdpa_create_cvq_mr(struct mlx5_vdpa_dev *mvdev,
-				    struct vhost_iotlb *iotlb,
-				    unsigned int asid)
+				    struct vhost_iotlb *iotlb)
 {
-	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] != asid)
-		return 0;
-
 	return dup_iotlb(mvdev, iotlb);
 }
 
 static int _mlx5_vdpa_create_dvq_mr(struct mlx5_vdpa_dev *mvdev,
-				    struct vhost_iotlb *iotlb,
-				    unsigned int asid)
+				    struct vhost_iotlb *iotlb)
 {
 	struct mlx5_vdpa_mr *mr = &mvdev->mr;
 	int err;
 
-	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] != asid)
-		return 0;
-
 	if (mr->initialized)
 		return 0;
 
@@ -574,18 +562,22 @@ static int _mlx5_vdpa_create_mr(struct mlx5_vdpa_dev
*mvdev,
 {
 	int err;
 
-	err = _mlx5_vdpa_create_dvq_mr(mvdev, iotlb, asid);
-	if (err)
-		return err;
-
-	err = _mlx5_vdpa_create_cvq_mr(mvdev, iotlb, asid);
-	if (err)
-		goto out_err;
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid) {
+		err = _mlx5_vdpa_create_dvq_mr(mvdev, iotlb);
+		if (err)
+			return err;
+	}
+	if (mvdev->group2asid[MLX5_VDPA_CVQ_GROUP] == asid) {
+		err = _mlx5_vdpa_create_cvq_mr(mvdev, iotlb);
+		if (err)
+			goto out_err;
+	}
 
 	return 0;
 
 out_err:
-	_mlx5_vdpa_destroy_dvq_mr(mvdev, asid);
+	if (mvdev->group2asid[MLX5_VDPA_DATAVQ_GROUP] == asid)
+		_mlx5_vdpa_destroy_dvq_mr(mvdev);
 
 	return err;
 }
@@ -601,6 +593,28 @@ int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct
vhost_iotlb *iotlb,
 	return err;
 }
 
+int mlx5_vdpa_reset_mr(struct mlx5_vdpa_dev *mvdev, unsigned int asid)
+{
+	struct mlx5_vdpa_mr *mr = &mvdev->mr;
+	int err = 0;
+
+	if (asid != 0)
+		return 0;
+
+	mutex_lock(&mr->mkey_mtx);
+	if (!mr->user_mr)
+		goto out;
+	_mlx5_vdpa_destroy_dvq_mr(mvdev);
+	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
+		err = _mlx5_vdpa_create_dvq_mr(mvdev, NULL);
+		if (err)
+			mlx5_vdpa_warn(mvdev, "create DMA MR failed\n");
+	}
+out:
+	mutex_unlock(&mr->mkey_mtx);
+	return err;
+}
+
 int mlx5_vdpa_handle_set_map(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb
*iotlb,
 			     bool *change_map, unsigned int asid)
 {
diff --git a/drivers/vdpa/mlx5/net/mlx5_vnet.c
b/drivers/vdpa/mlx5/net/mlx5_vnet.c
index 37be945..3cb5db6 100644
--- a/drivers/vdpa/mlx5/net/mlx5_vnet.c
+++ b/drivers/vdpa/mlx5/net/mlx5_vnet.c
@@ -2824,7 +2824,6 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	unregister_link_notifier(ndev);
 	teardown_driver(ndev);
 	clear_vqs_ready(ndev);
-	mlx5_vdpa_destroy_mr(&ndev->mvdev);
 	ndev->mvdev.status = 0;
 	ndev->mvdev.suspended = false;
 	ndev->cur_num_vqs = 0;
@@ -2835,10 +2834,6 @@ static int mlx5_vdpa_reset(struct vdpa_device *vdev)
 	init_group_to_asid_map(mvdev);
 	++mvdev->generation;
 
-	if (MLX5_CAP_GEN(mvdev->mdev, umem_uid_0)) {
-		if (mlx5_vdpa_create_mr(mvdev, NULL, 0))
-			mlx5_vdpa_warn(mvdev, "create MR failed\n");
-	}
 	up_write(&ndev->reslock);
 
 	return 0;
@@ -2903,6 +2898,18 @@ static int mlx5_vdpa_set_map(struct vdpa_device *vdev,
unsigned int asid,
 	return err;
 }
 
+static int mlx5_vdpa_reset_map(struct vdpa_device *vdev, unsigned int asid)
+{
+	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
+	struct mlx5_vdpa_net *ndev = to_mlx5_vdpa_ndev(mvdev);
+	int err;
+
+	down_write(&ndev->reslock);
+	err = mlx5_vdpa_reset_mr(mvdev, asid);
+	up_write(&ndev->reslock);
+	return err;
+}
+
 static struct device *mlx5_get_vq_dma_dev(struct vdpa_device *vdev, u16 idx)
 {
 	struct mlx5_vdpa_dev *mvdev = to_mvdev(vdev);
@@ -3162,6 +3169,7 @@ static int mlx5_set_group_asid(struct vdpa_device *vdev,
u32 group,
 	.set_config = mlx5_vdpa_set_config,
 	.get_generation = mlx5_vdpa_get_generation,
 	.set_map = mlx5_vdpa_set_map,
+	.reset_map = mlx5_vdpa_reset_map,
 	.set_group_asid = mlx5_set_group_asid,
 	.get_vq_dma_dev = mlx5_get_vq_dma_dev,
 	.free = mlx5_vdpa_free,
-- 
1.8.3.1

Devices with on-chip IOMMU may need to restore iotlb to 1:1 identity
mapping from IOVA to PA. Before vhost-vdpa is going away, give them
a chance to clean up and reset iotlb back to 1:1 identify mapping
mode. This is done so that any vdpa bus driver may start with 1:1
identity mapping by default.

Signed-off-by: Si-Wei Liu <si-wei.liu at oracle.com>
---
 drivers/vhost/vdpa.c | 17 +++++++++++++++++
 1 file changed, 17 insertions(+)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index eabac06..71fbd559 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -131,6 +131,15 @@ static struct vhost_vdpa_as
*vhost_vdpa_find_alloc_as(struct vhost_vdpa *v,
 	return vhost_vdpa_alloc_as(v, asid);
 }
 
+static void vhost_vdpa_reset_map(struct vhost_vdpa *v, u32 asid)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (ops->reset_map)
+		ops->reset_map(vdpa, asid);
+}
+
 static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32 asid)
 {
 	struct vhost_vdpa_as *as = asid_to_as(v, asid);
@@ -140,6 +149,14 @@ static int vhost_vdpa_remove_as(struct vhost_vdpa *v, u32
asid)
 
 	hlist_del(&as->hash_link);
 	vhost_vdpa_iotlb_unmap(v, &as->iotlb, 0ULL, 0ULL - 1, asid);
+	/*
+	 * Devices with on-chip IOMMU need to restore iotlb
+	 * to 1:1 identity mapping before vhost-vdpa is going
+	 * to be removed and detached from the device. Give
+	 * them a chance to do so, as this cannot be done
+	 * efficiently via the whole-range unmap call above.
+	 */
+	vhost_vdpa_reset_map(v, asid);
 	kfree(as);
 
 	return 0;
-- 
1.8.3.1

Userspace needs this feature flag to distinguish if vhost-vdpa
iotlb in the kernel supports persistent IOTLB mapping across
device reset. There are two cases that backend may claim
this feature bit on:

- parent device that has to work with platform IOMMU
- parent device with on-chip IOMMU that has the expected
  .reset_map support in driver

Signed-off-by: Si-Wei Liu <si-wei.liu at oracle.com>
---
RFC v2 -> v3:
  - fix missing return due to merge error

---
 drivers/vhost/vdpa.c             | 16 +++++++++++++++-
 include/uapi/linux/vhost_types.h |  2 ++
 2 files changed, 17 insertions(+), 1 deletion(-)

diff --git a/drivers/vhost/vdpa.c b/drivers/vhost/vdpa.c
index 71fbd559..b404504 100644
--- a/drivers/vhost/vdpa.c
+++ b/drivers/vhost/vdpa.c
@@ -414,6 +414,14 @@ static bool vhost_vdpa_has_desc_group(const struct
vhost_vdpa *v)
 	return ops->get_vq_desc_group;
 }
 
+static bool vhost_vdpa_has_persistent_map(const struct vhost_vdpa *v)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return (!ops->set_map && !ops->dma_map) || ops->reset_map;
+}
+
 static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
 {
 	struct vdpa_device *vdpa = v->vdpa;
@@ -716,7 +724,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 		if (features & ~(VHOST_VDPA_BACKEND_FEATURES |
 				 BIT_ULL(VHOST_BACKEND_F_DESC_ASID) |
 				 BIT_ULL(VHOST_BACKEND_F_SUSPEND) |
-				 BIT_ULL(VHOST_BACKEND_F_RESUME)))
+				 BIT_ULL(VHOST_BACKEND_F_RESUME) |
+				 BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST)))
 			return -EOPNOTSUPP;
 		if ((features & BIT_ULL(VHOST_BACKEND_F_SUSPEND)) &&
 		     !vhost_vdpa_can_suspend(v))
@@ -730,6 +739,9 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 		if ((features & BIT_ULL(VHOST_BACKEND_F_DESC_ASID)) &&
 		     !vhost_vdpa_has_desc_group(v))
 			return -EOPNOTSUPP;
+		if ((features & BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST)) &&
+		     !vhost_vdpa_has_persistent_map(v))
+			return -EOPNOTSUPP;
 		vhost_set_backend_features(&v->vdev, features);
 		return 0;
 	}
@@ -785,6 +797,8 @@ static long vhost_vdpa_unlocked_ioctl(struct file *filep,
 			features |= BIT_ULL(VHOST_BACKEND_F_RESUME);
 		if (vhost_vdpa_has_desc_group(v))
 			features |= BIT_ULL(VHOST_BACKEND_F_DESC_ASID);
+		if (vhost_vdpa_has_persistent_map(v))
+			features |= BIT_ULL(VHOST_BACKEND_F_IOTLB_PERSIST);
 		if (copy_to_user(featurep, &features, sizeof(features)))
 			r = -EFAULT;
 		break;
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index 6acc604..0fdb6f0 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -186,5 +186,7 @@ struct vhost_vdpa_iova_range {
  * buffers may reside. Requires VHOST_BACKEND_F_IOTLB_ASID.
  */
 #define VHOST_BACKEND_F_DESC_ASID    0x6
+/* IOTLB don't flush memory mapping across device reset */
+#define VHOST_BACKEND_F_IOTLB_PERSIST  0x7
 
 #endif
-- 
1.8.3.1