search for: mlx5_vdpa_create_mr

...drivers/vdpa/mlx5/core/mr.c:194:2: note: in expansion of macro 'MLX5_SET' 194 | MLX5_SET(create_mkey_in, in, uid, mvdev->res.uid); | ^~~~~~~~ drivers/vdpa/mlx5/core/mr.c: At top level: >> drivers/vdpa/mlx5/core/mr.c:414:5: warning: no previous prototype for 'mlx5_vdpa_create_mr' [-Wmissing-prototypes] 414 | int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) | ^~~~~~~~~~~~~~~~~~~ >> drivers/vdpa/mlx5/core/mr.c:425:6: warning: no previous prototype for 'mlx5_vdpa_destroy_mr' [-Wmissing-prototypes] 425 | v...

...5_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); #defi...

...dule_init(mlx5_vdpa_core_init); > +module_exit(mlx5_vdpa_core_exit); > diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c > index ef1c550f8266..c093eab6c714 100644 > --- a/drivers/vdpa/mlx5/core/mr.c > +++ b/drivers/vdpa/mlx5/core/mr.c > @@ -434,6 +434,7 @@ int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) > mutex_unlock(&mr->mkey_mtx); > return err; > } > +EXPORT_SYMBOL(mlx5_vdpa_create_mr); > > void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) > { > @@ -456,6 +457,7 @@ void mlx5_vdpa_destroy_mr(stru...

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

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

...mlx5_vdpa_core_exit); > > > diff --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c > > > index ef1c550f8266..c093eab6c714 100644 > > > --- a/drivers/vdpa/mlx5/core/mr.c > > > +++ b/drivers/vdpa/mlx5/core/mr.c > > > @@ -434,6 +434,7 @@ int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) > > > mutex_unlock(&mr->mkey_mtx); > > > return err; > > > } > > > +EXPORT_SYMBOL(mlx5_vdpa_create_mr); > > > > > > void mlx5_vdpa_destroy_mr(struct mlx5_vdpa_dev *mvdev) &gt...

...f --git a/drivers/vdpa/mlx5/core/mr.c b/drivers/vdpa/mlx5/core/mr.c > > > > > index ef1c550f8266..c093eab6c714 100644 > > > > > --- a/drivers/vdpa/mlx5/core/mr.c > > > > > +++ b/drivers/vdpa/mlx5/core/mr.c > > > > > @@ -434,6 +434,7 @@ int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) > > > > > mutex_unlock(&mr->mkey_mtx); > > > > > return err; > > > > > } > > > > > +EXPORT_SYMBOL(mlx5_vdpa_create_mr); > > > > > > > > > >...

This patch series is based on Eugenio's fix for handling CVQs in a different ASID [0]. The first patch is the actual fix. The next 2 patches are fixing a possible issue that I found while implementing patch 1. The patches are ordered like this for clarity. [0] https://lore.kernel.org/lkml/20230112142218.725622-1-eperezma at redhat.com/ Dragos Tatulea (1): vdpa/mlx5: Fix

This patch series is based on Eugenio's fix for handling CVQs in a different ASID [0]. The first patch is the actual fix. The next 2 patches are fixing a possible issue that I found while implementing patch 1. The patches are ordered like this for clarity. [0] https://lore.kernel.org/lkml/20230112142218.725622-1-eperezma at redhat.com/ Dragos Tatulea (1): vdpa/mlx5: Fix

...page.h:108:40: note: in definition of macro 'pfn_to_page' 108 | # define pfn_to_page(pfn) (vmem_map + (pfn)) | ^~~ drivers/vdpa/mlx5/core/mr.c: At top level: drivers/vdpa/mlx5/core/mr.c:414:5: warning: no previous prototype for 'mlx5_vdpa_create_mr' [-Wmissing-prototypes] 414 | int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) | ^~~~~~~~~~~~~~~~~~~ drivers/vdpa/mlx5/core/mr.c:425:6: warning: no previous prototype for 'mlx5_vdpa_destroy_mr' [-Wmissing-prototypes] 425 | void ml...

...drivers/vdpa/mlx5/core/mr.c > > > > > > > index ef1c550f8266..c093eab6c714 100644 > > > > > > > --- a/drivers/vdpa/mlx5/core/mr.c > > > > > > > +++ b/drivers/vdpa/mlx5/core/mr.c > > > > > > > @@ -434,6 +434,7 @@ int mlx5_vdpa_create_mr(struct mlx5_vdpa_dev *mvdev, struct vhost_iotlb *iotlb) > > > > > > > mutex_unlock(&mr->mkey_mtx); > > > > > > > return err; > > > > > > > } > > > > > > > +EXPORT_SYMBOL(mlx5_vdpa_create_mr); > > &...

..._change_map(struct mlx5_vdpa_net *ndev, struct vhost_iotlb *iotlb) > +{ > + int err; > + > + suspend_vqs(ndev); > + err = save_channels_info(ndev); > + if (err) > + goto err_mr; > + > + teardown_driver(ndev); > + mlx5_vdpa_destroy_mr(&ndev->mvdev); > + err = mlx5_vdpa_create_mr(&ndev->mvdev, iotlb); > + if (err) > + goto err_mr; > + > + restore_channels_info(ndev); > + err = setup_driver(ndev); > + if (err) > + goto err_setup; > + > + return 0; > + > +err_setup: > + mlx5_vdpa_destroy_mr(&ndev->mvdev); > +err_mr: >...