1 files changed, 38 insertions, 3 deletions

diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index f1dde2c0fe99..964ff22bf281 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -587,12 +587,46 @@ static int __init init_pci_cap_basic_perm(struct perm_bits *perm)
         return 0;
 }
 
+static int vfio_pm_config_write(struct vfio_pci_device *vdev, int pos,
+                                int count, struct perm_bits *perm,
+                                int offset, __le32 val)
+{
+        count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+        if (count < 0)
+                return count;
+
+        if (offset == PCI_PM_CTRL) {
+                pci_power_t state;
+
+                switch (le32_to_cpu(val) & PCI_PM_CTRL_STATE_MASK) {
+                case 0:
+                        state = PCI_D0;
+                        break;
+                case 1:
+                        state = PCI_D1;
+                        break;
+                case 2:
+                        state = PCI_D2;
+                        break;
+                case 3:
+                        state = PCI_D3hot;
+                        break;
+                }
+
+                pci_set_power_state(vdev->pdev, state);
+        }
+
+        return count;
+}
+
 /* Permissions for the Power Management capability */
 static int __init init_pci_cap_pm_perm(struct perm_bits *perm)
 {
         if (alloc_perm_bits(perm, pci_cap_length[PCI_CAP_ID_PM]))
                 return -ENOMEM;
 
+        perm->writefn = vfio_pm_config_write;
+
         /*
          * We always virtualize the next field so we can remove
          * capabilities from the chain if we want to.
@@ -600,10 +634,11 @@ static int __init init_pci_cap_pm_perm(struct perm_bits *perm)
         p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
 
         /*
-         * Power management is defined *per function*,
-         * so we let the user write this
+         * Power management is defined *per function*, so we can let
+         * the user change power state, but we trap and initiate the
+         * change ourselves, so the state bits are read-only.
          */
-        p_setd(perm, PCI_PM_CTRL, NO_VIRT, ALL_WRITE);
+        p_setd(perm, PCI_PM_CTRL, NO_VIRT, ~PCI_PM_CTRL_STATE_MASK);
         return 0;
 }