Xu Yilun <yilun...@linux.intel.com> writes:
> When device is TSM Bound, some of its MMIO regions are controlled by
> secure firmware. E.g. TDX Connect would require these MMIO regions
> mappeed in S-EPT and never unmapped until device Unbound. Zapping bars
> irrespective of TSM Bound state may cause unexpected secure firmware
> errors. It is always safe to do TSM Unbind first, transiting the device
> to shared, then do whatever needed as before.
>
> Signed-off-by: Xu Yilun <yilun...@linux.intel.com>
> ---
> drivers/vfio/pci/vfio_pci_config.c | 4 +++
> drivers/vfio/pci/vfio_pci_core.c | 41 +++++++++++++++++++-----------
> drivers/vfio/pci/vfio_pci_priv.h | 3 +++
> 3 files changed, 33 insertions(+), 15 deletions(-)
>
> diff --git a/drivers/vfio/pci/vfio_pci_config.c
> b/drivers/vfio/pci/vfio_pci_config.c
> index 7ac062bd5044..4ffe661c9e59 100644
> --- a/drivers/vfio/pci/vfio_pci_config.c
> +++ b/drivers/vfio/pci/vfio_pci_config.c
> @@ -590,6 +590,7 @@ static int vfio_basic_config_write(struct
> vfio_pci_core_device *vdev, int pos,
> new_mem = !!(new_cmd & PCI_COMMAND_MEMORY);
>
> if (!new_mem) {
> + vfio_pci_tsm_unbind(vdev);
> vfio_pci_zap_and_down_write_memory_lock(vdev);
> vfio_pci_dma_buf_move(vdev, true);
>
Don't we need to re-bind the vdev with tsm_bind for the continued use of TDI?
> } else {
> @@ -712,6 +713,7 @@ static void vfio_lock_and_set_power_state(struct
> vfio_pci_core_device *vdev,
> pci_power_t state)
> {
> if (state >= PCI_D3hot) {
> + vfio_pci_tsm_unbind(vdev);
> vfio_pci_zap_and_down_write_memory_lock(vdev);
> vfio_pci_dma_buf_move(vdev, true);
> } else {
> @@ -907,6 +909,7 @@ static int vfio_exp_config_write(struct
> vfio_pci_core_device *vdev, int pos,
> &cap);
>
> if (!ret && (cap & PCI_EXP_DEVCAP_FLR)) {
> + vfio_pci_tsm_unbind(vdev);
> vfio_pci_zap_and_down_write_memory_lock(vdev);
> vfio_pci_dma_buf_move(vdev, true);
> pci_try_reset_function(vdev->pdev);
> @@ -992,6 +995,7 @@ static int vfio_af_config_write(struct
> vfio_pci_core_device *vdev, int pos,
> &cap);
>
> if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP)) {
> + vfio_pci_tsm_unbind(vdev);
> vfio_pci_zap_and_down_write_memory_lock(vdev);
> vfio_pci_dma_buf_move(vdev, true);
> pci_try_reset_function(vdev->pdev);
> diff --git a/drivers/vfio/pci/vfio_pci_core.c
> b/drivers/vfio/pci/vfio_pci_core.c
> index 92544e54c9c3..a8437fcecca1 100644
> --- a/drivers/vfio/pci/vfio_pci_core.c
> +++ b/drivers/vfio/pci/vfio_pci_core.c
> @@ -286,6 +286,7 @@ static int vfio_pci_runtime_pm_entry(struct
> vfio_pci_core_device *vdev,
> * The vdev power related flags are protected with 'memory_lock'
> * semaphore.
> */
> + vfio_pci_tsm_unbind(vdev);
> vfio_pci_zap_and_down_write_memory_lock(vdev);
> vfio_pci_dma_buf_move(vdev, true);
>
> @@ -693,11 +694,7 @@ void vfio_pci_core_close_device(struct vfio_device
> *core_vdev)
> eeh_dev_release(vdev->pdev);
> #endif
>
> - if (vdev->is_tsm_bound) {
> - vfio_iommufd_tsm_unbind(&vdev->vdev);
> - pci_release_regions(vdev->pdev);
> - vdev->is_tsm_bound = false;
> - }
> + __vfio_pci_tsm_unbind(vdev);
>
> vfio_pci_core_disable(vdev);
>
> @@ -1222,6 +1219,7 @@ static int vfio_pci_ioctl_reset(struct
> vfio_pci_core_device *vdev,
> if (!vdev->reset_works)
> return -EINVAL;
>
> + vfio_pci_tsm_unbind(vdev);
> vfio_pci_zap_and_down_write_memory_lock(vdev);
>
> /*
> @@ -1491,12 +1489,32 @@ static int vfio_pci_ioctl_tsm_bind(struct
> vfio_pci_core_device *vdev,
> return ret;
> }
>
> +void __vfio_pci_tsm_unbind(struct vfio_pci_core_device *vdev)
> +{
> + struct pci_dev *pdev = vdev->pdev;
> +
> + lockdep_assert_held(&vdev->vdev.dev_set->lock);
> +
> + if (!vdev->is_tsm_bound)
> + return;
> +
> + vfio_iommufd_tsm_unbind(&vdev->vdev);
> + pci_release_regions(pdev);
> + vdev->is_tsm_bound = false;
>
Do we really need to check vdev->is_tsm_bound? The tsm_ops lock already
ensures that concurrent TSM operations can't happen, and repeated calls
to bind()/unbind() seem to be handled safely by pci_tsm_bind and pci_tsm_unbind.
> +}
> +
> +void vfio_pci_tsm_unbind(struct vfio_pci_core_device *vdev)
> +{
> + mutex_lock(&vdev->vdev.dev_set->lock);
> + __vfio_pci_tsm_unbind(vdev);
> + mutex_unlock(&vdev->vdev.dev_set->lock);
> +}
>
If is_tsm_bound is no longer needed, and pci_release_regions /
request_region_exclusive are now handled within pci_tsm_unbind / bind,
do we still need mutex_lock() to guard this path?
> +
> static int vfio_pci_ioctl_tsm_unbind(struct vfio_pci_core_device *vdev,
> void __user *arg)
> {
> unsigned long minsz = offsetofend(struct vfio_pci_tsm_unbind, flags);
> struct vfio_pci_tsm_unbind tsm_unbind;
> - struct pci_dev *pdev = vdev->pdev;
>
> if (copy_from_user(&tsm_unbind, arg, minsz))
> return -EFAULT;
> @@ -1504,15 +1522,7 @@ static int vfio_pci_ioctl_tsm_unbind(struct
> vfio_pci_core_device *vdev,
> if (tsm_unbind.argsz < minsz || tsm_unbind.flags)
> return -EINVAL;
>
> - mutex_lock(&vdev->vdev.dev_set->lock);
> -
> - if (!vdev->is_tsm_bound)
> - return 0;
> -
> - vfio_iommufd_tsm_unbind(&vdev->vdev);
> - pci_release_regions(pdev);
> - vdev->is_tsm_bound = false;
> - mutex_unlock(&vdev->vdev.dev_set->lock);
> + vfio_pci_tsm_unbind(vdev);
>
> return 0;
> }
> @@ -2526,6 +2536,7 @@ static int vfio_pci_dev_set_hot_reset(struct
> vfio_device_set *dev_set,
> break;
> }
>
> + __vfio_pci_tsm_unbind(vdev);
> /*
> * Take the memory write lock for each device and zap BAR
> * mappings to prevent the user accessing the device while in
> diff --git a/drivers/vfio/pci/vfio_pci_priv.h
> b/drivers/vfio/pci/vfio_pci_priv.h
> index 6f3e8eafdc35..e5bf27f46a73 100644
> --- a/drivers/vfio/pci/vfio_pci_priv.h
> +++ b/drivers/vfio/pci/vfio_pci_priv.h
> @@ -130,4 +130,7 @@ static inline void vfio_pci_dma_buf_move(struct
> vfio_pci_core_device *vdev,
> }
> #endif
>
> +void __vfio_pci_tsm_unbind(struct vfio_pci_core_device *vdev);
> +void vfio_pci_tsm_unbind(struct vfio_pci_core_device *vdev);
> +
> #endif
> --
> 2.25.1
