diff options
author | Abhishek Sahu <abhsahu@nvidia.com> | 2022-05-18 16:46:10 +0530 |
---|---|---|
committer | Alex Williamson <alex.williamson@redhat.com> | 2022-05-18 10:00:48 -0600 |
commit | f4162eb1e2fc9b423dfb8f3a7b2b55a337efcc60 (patch) | |
tree | 9eccd4aea36b155977b043aa7a3406c5448bdc77 /drivers/vfio/pci | |
parent | 2b2c651baf1c24414be4f76b152de80fae7c7786 (diff) | |
download | linux-stable-f4162eb1e2fc9b423dfb8f3a7b2b55a337efcc60.tar.gz linux-stable-f4162eb1e2fc9b423dfb8f3a7b2b55a337efcc60.tar.bz2 linux-stable-f4162eb1e2fc9b423dfb8f3a7b2b55a337efcc60.zip |
vfio/pci: Change the PF power state to D0 before enabling VFs
According to [PCIe v5 9.6.2] for PF Device Power Management States
"The PF's power management state (D-state) has global impact on its
associated VFs. If a VF does not implement the Power Management
Capability, then it behaves as if it is in an equivalent
power state of its associated PF.
If a VF implements the Power Management Capability, the Device behavior
is undefined if the PF is placed in a lower power state than the VF.
Software should avoid this situation by placing all VFs in lower power
state before lowering their associated PF's power state."
From the vfio driver side, user can enable SR-IOV when the PF is in D3hot
state. If VF does not implement the Power Management Capability, then
the VF will be actually in D3hot state and then the VF BAR access will
fail. If VF implements the Power Management Capability, then VF will
assume that its current power state is D0 when the PF is D3hot and
in this case, the behavior is undefined.
To support PF power management, we need to create power management
dependency between PF and its VF's. The runtime power management support
may help with this where power management dependencies are supported
through device links. But till we have such support in place, we can
disallow the PF to go into low power state, if PF has VF enabled.
There can be a case, where user first enables the VF's and then
disables the VF's. If there is no user of PF, then the PF can put into
D3hot state again. But with this patch, the PF will still be in D0
state after disabling VF's since detecting this case inside
vfio_pci_core_sriov_configure() requires access to
struct vfio_device::open_count along with its locks. But the subsequent
patches related to runtime PM will handle this case since runtime PM
maintains its own usage count.
Also, vfio_pci_core_sriov_configure() can be called at any time
(with and without vfio pci device user), so the power state change
and SR-IOV enablement need to be protected with the required locks.
Signed-off-by: Abhishek Sahu <abhsahu@nvidia.com>
Link: https://lore.kernel.org/r/20220518111612.16985-3-abhsahu@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
Diffstat (limited to 'drivers/vfio/pci')
-rw-r--r-- | drivers/vfio/pci/vfio_pci_core.c | 16 |
1 files changed, 16 insertions, 0 deletions
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c index 05a3aa95ba52..9489ceea8875 100644 --- a/drivers/vfio/pci/vfio_pci_core.c +++ b/drivers/vfio/pci/vfio_pci_core.c @@ -217,6 +217,10 @@ int vfio_pci_set_power_state(struct vfio_pci_core_device *vdev, pci_power_t stat bool needs_restore = false, needs_save = false; int ret; + /* Prevent changing power state for PFs with VFs enabled */ + if (pci_num_vf(pdev) && state > PCI_D0) + return -EBUSY; + if (vdev->needs_pm_restore) { if (pdev->current_state < PCI_D3hot && state >= PCI_D3hot) { pci_save_state(pdev); @@ -1944,7 +1948,19 @@ int vfio_pci_core_sriov_configure(struct vfio_pci_core_device *vdev, } list_add_tail(&vdev->sriov_pfs_item, &vfio_pci_sriov_pfs); mutex_unlock(&vfio_pci_sriov_pfs_mutex); + + /* + * The PF power state should always be higher than the VF power + * state. If PF is in the low power state, then change the + * power state to D0 first before enabling SR-IOV. + * Also, this function can be called at any time, and userspace + * PCI_PM_CTRL write can race against this code path, + * so protect the same with 'memory_lock'. + */ + down_write(&vdev->memory_lock); + vfio_pci_set_power_state(vdev, PCI_D0); ret = pci_enable_sriov(pdev, nr_virtfn); + up_write(&vdev->memory_lock); if (ret) goto out_del; return nr_virtfn; |