/*
* Lengths of PCIe/PCI-X Extended Config Capabilities
- * 0: Removed or masked from the user visible capabilty list
+ * 0: Removed or masked from the user visible capability list
* FF: Variable length
*/
static const u16 pci_ext_cap_length[PCI_EXT_CAP_ID_MAX + 1] = {
* ignore whether a read/write exceeds the defined capability
* structure. We can do this because:
* - Standard config space is already dword aligned
- * - Capabilities are all dword alinged (bits 0:1 of next reserved)
+ * - Capabilities are all dword aligned (bits 0:1 of next reserved)
* - Express capabilities defined as dword aligned
*/
size = round_up(size, 4);
return 0;
}
+static int vfio_exp_config_write(struct vfio_pci_device *vdev, int pos,
+ int count, struct perm_bits *perm,
+ int offset, __le32 val)
+{
+ __le16 *ctrl = (__le16 *)(vdev->vconfig + pos -
+ offset + PCI_EXP_DEVCTL);
+
+ count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+ if (count < 0)
+ return count;
+
+ /*
+ * The FLR bit is virtualized, if set and the device supports PCIe
+ * FLR, issue a reset_function. Regardless, clear the bit, the spec
+ * requires it to be always read as zero. NB, reset_function might
+ * not use a PCIe FLR, we don't have that level of granularity.
+ */
+ if (*ctrl & cpu_to_le16(PCI_EXP_DEVCTL_BCR_FLR)) {
+ u32 cap;
+ int ret;
+
+ *ctrl &= ~cpu_to_le16(PCI_EXP_DEVCTL_BCR_FLR);
+
+ ret = pci_user_read_config_dword(vdev->pdev,
+ pos - offset + PCI_EXP_DEVCAP,
+ &cap);
+
+ if (!ret && (cap & PCI_EXP_DEVCAP_FLR))
+ pci_try_reset_function(vdev->pdev);
+ }
+
+ return count;
+}
+
/* Permissions for PCI Express capability */
static int __init init_pci_cap_exp_perm(struct perm_bits *perm)
{
if (alloc_perm_bits(perm, PCI_CAP_EXP_ENDPOINT_SIZEOF_V2))
return -ENOMEM;
+ perm->writefn = vfio_exp_config_write;
+
p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
/*
- * Allow writes to device control fields (includes FLR!)
- * but not to devctl_phantom which could confuse IOMMU
- * or to the ARI bit in devctl2 which is set at probe time
+ * Allow writes to device control fields, except devctl_phantom,
+ * which could confuse IOMMU, and the ARI bit in devctl2, which
+ * is set at probe time. FLR gets virtualized via our writefn.
*/
- p_setw(perm, PCI_EXP_DEVCTL, NO_VIRT, ~PCI_EXP_DEVCTL_PHANTOM);
+ p_setw(perm, PCI_EXP_DEVCTL,
+ PCI_EXP_DEVCTL_BCR_FLR, ~PCI_EXP_DEVCTL_PHANTOM);
p_setw(perm, PCI_EXP_DEVCTL2, NO_VIRT, ~PCI_EXP_DEVCTL2_ARI);
return 0;
}
+static int vfio_af_config_write(struct vfio_pci_device *vdev, int pos,
+ int count, struct perm_bits *perm,
+ int offset, __le32 val)
+{
+ u8 *ctrl = vdev->vconfig + pos - offset + PCI_AF_CTRL;
+
+ count = vfio_default_config_write(vdev, pos, count, perm, offset, val);
+ if (count < 0)
+ return count;
+
+ /*
+ * The FLR bit is virtualized, if set and the device supports AF
+ * FLR, issue a reset_function. Regardless, clear the bit, the spec
+ * requires it to be always read as zero. NB, reset_function might
+ * not use an AF FLR, we don't have that level of granularity.
+ */
+ if (*ctrl & PCI_AF_CTRL_FLR) {
+ u8 cap;
+ int ret;
+
+ *ctrl &= ~PCI_AF_CTRL_FLR;
+
+ ret = pci_user_read_config_byte(vdev->pdev,
+ pos - offset + PCI_AF_CAP,
+ &cap);
+
+ if (!ret && (cap & PCI_AF_CAP_FLR) && (cap & PCI_AF_CAP_TP))
+ pci_try_reset_function(vdev->pdev);
+ }
+
+ return count;
+}
+
/* Permissions for Advanced Function capability */
static int __init init_pci_cap_af_perm(struct perm_bits *perm)
{
if (alloc_perm_bits(perm, pci_cap_length[PCI_CAP_ID_AF]))
return -ENOMEM;
+ perm->writefn = vfio_af_config_write;
+
p_setb(perm, PCI_CAP_LIST_NEXT, (u8)ALL_VIRT, NO_WRITE);
- p_setb(perm, PCI_AF_CTRL, NO_VIRT, PCI_AF_CTRL_FLR);
+ p_setb(perm, PCI_AF_CTRL, PCI_AF_CTRL_FLR, PCI_AF_CTRL_FLR);
return 0;
}
* space which tracks reads and writes to bits that we emulate for
* the user. Initial values filled from device.
*
- * Using shared stuct perm_bits between all vfio-pci devices saves
+ * Using shared struct perm_bits between all vfio-pci devices saves
* us from allocating cfg_size buffers for virt and write for every
* device. We could remove vconfig and allocate individual buffers
- * for each area requring emulated bits, but the array of pointers
+ * for each area requiring emulated bits, but the array of pointers
* would be comparable in size (at least for standard config space).
*/
int vfio_config_init(struct vfio_pci_device *vdev)