Merge tag 'vfio-v7.3-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Add nv_falcon vfio selftest driver.

   The Falcon is a general-purpose microcontroller embedded within
   NVIDIA GPUs, presenting a relatively simple DMA programming
   interface.

   This adds another selftest target for vfio-pci with real DMA
   transfers (Rubin Du, Alex Williamson)

 - Add allocation assertion helpers to vfio selftests and use them to
   avoid variable length arrays and the compiler errors they generate
   (Alex Mastro)

 - Fix use-after-free hazard where an init path error in MSI support
   leaves a stray pointer that can later be reused or double-freed
   (Xiang Mei)

 - Fix previous refactor of PCI BAR mappings to honor non_mappable_bars
   flag, which otherwise generates a warning when trying to pci_iomap()
   a 256TiB BAR on ISM devices on s390 (Farhan Ali)

 - Add igb vfio selftest driver.

   Like nv_falcon, this provides another target for DMA testing with
   vfio selftests, but importantly this driver supports both physical
   82576 NICs and the emulation model in QEMU.

   This therefore enables a vfio selftest vector with no physical
   hardware requirements (Josh Hilke, Alex Williamson)

 - Mark selftest fixture objects __maybe_unused to accommodate builds
   with clang -Wunused-but-set-global (David Matlack)

 - Add error recovery for vfio-pci devices on s390x.

   This expands devices which expose the existing error eventfd and
   introduces a device feature for reporting firmware defined error
   state information to the user, allowing recovery through hypervisor
   channels (Farhan Ali)

* tag 'vfio-v7.3-rc1' of https://github.com/awilliam/linux-vfio:
  vfio/pci: Remove the pcie check for VFIO_PCI_ERR_IRQ_INDEX
  vfio-pci/zdev: Add a device feature for error information
  s390/pci: Store PCI error information for passthrough devices
  PCI/MSI: Enable memory decoding before restoring MSI-X messages
  PCI: Fail FLR when config space is inaccessible
  PCI: Avoid saving config space state if inaccessible
  PCI: Allow per function PCI slots to fix slot reset on s390
  PCI: Introduce PCI_SLOT_PLACEHOLDER constant for slot_nr placeholder value
  selftests: harness: Mark test fixture objects __maybe_unused
  vfio: selftests: Retry on EAGAIN during device reset
  vfio: selftests: igb: Add driver for Intel 82576 device
  vfio: selftests: Add helpers to re-enable interrupts
  vfio/pci: Avoid mapping BARs for devices with non-mappable BARs
  vfio/pci: clear vdev->msi_perm after freeing it on init failure
  vfio: selftests: Avoid VLAs
  vfio: selftests: Add allocation assert helpers
  vfio: selftests: Add NVIDIA Falcon driver for DMA testing
  vfio: selftests: Allow drivers without send_msi() support
  vfio: selftests: Add generic PCI command register helpers
  vfio: selftests: Add memcpy chunking to vfio_pci_driver_memcpy()

5 files changed, 75 insertions, 13 deletions

diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index a10ed733f0e3..9914f3ac69ae 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -1272,6 +1272,7 @@ static int vfio_msi_cap_len(struct vfio_pci_core_device *vdev, u8 pos)
 	ret = init_pci_cap_msi_perm(vdev->msi_perm, len, flags);
 	if (ret) {
 		kfree(vdev->msi_perm);
+		vdev->msi_perm = NULL;
 		return ret;
 	}
 
diff --git a/drivers/vfio/pci/vfio_pci_core.c b/drivers/vfio/pci/vfio_pci_core.c
index 3f11a9624b9c..362c375a0579 100644
--- a/drivers/vfio/pci/vfio_pci_core.c
+++ b/drivers/vfio/pci/vfio_pci_core.c
@@ -554,6 +554,9 @@ static void vfio_pci_core_map_bars(struct vfio_pci_core_device *vdev)
 
 		vdev->barmap[bar] = IOMEM_ERR_PTR(-ENODEV);
 
+		if (pdev->non_mappable_bars)
+			continue;
+
 		if (!pci_resource_len(pdev, i))
 			continue;
 
@@ -877,8 +880,7 @@ static int vfio_pci_get_irq_count(struct vfio_pci_core_device *vdev, int irq_typ
 			return (flags & PCI_MSIX_FLAGS_QSIZE) + 1;
 		}
 	} else if (irq_type == VFIO_PCI_ERR_IRQ_INDEX) {
-		if (pci_is_pcie(vdev->pdev))
-			return 1;
+		return 1;
 	} else if (irq_type == VFIO_PCI_REQ_IRQ_INDEX) {
 		return 1;
 	}
@@ -1254,11 +1256,8 @@ static int vfio_pci_ioctl_get_irq_info(struct vfio_pci_core_device *vdev,
 	switch (info.index) {
 	case VFIO_PCI_INTX_IRQ_INDEX ... VFIO_PCI_MSIX_IRQ_INDEX:
 	case VFIO_PCI_REQ_IRQ_INDEX:
-		break;
 	case VFIO_PCI_ERR_IRQ_INDEX:
-		if (pci_is_pcie(vdev->pdev))
-			break;
-		fallthrough;
+		break;
 	default:
 		return -EINVAL;
 	}
@@ -1625,6 +1624,8 @@ int vfio_pci_core_ioctl_feature(struct vfio_device *device, u32 flags,
 		return vfio_pci_core_feature_token(vdev, flags, arg, argsz);
 	case VFIO_DEVICE_FEATURE_DMA_BUF:
 		return vfio_pci_core_feature_dma_buf(vdev, flags, arg, argsz);
+	case VFIO_DEVICE_FEATURE_ZPCI_ERROR:
+		return vfio_pci_zdev_feature_err(device, flags, arg, argsz);
 	default:
 		return -ENOTTY;
 	}
diff --git a/drivers/vfio/pci/vfio_pci_intrs.c b/drivers/vfio/pci/vfio_pci_intrs.c
index 33944d4d9dc4..64f80f64ff57 100644
--- a/drivers/vfio/pci/vfio_pci_intrs.c
+++ b/drivers/vfio/pci/vfio_pci_intrs.c
@@ -859,8 +859,7 @@ int vfio_pci_set_irqs_ioctl(struct vfio_pci_core_device *vdev, uint32_t flags,
 	case VFIO_PCI_ERR_IRQ_INDEX:
 		switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
 		case VFIO_IRQ_SET_ACTION_TRIGGER:
-			if (pci_is_pcie(vdev->pdev))
-				func = vfio_pci_set_err_trigger;
+			func = vfio_pci_set_err_trigger;
 			break;
 		}
 		break;
diff --git a/drivers/vfio/pci/vfio_pci_priv.h b/drivers/vfio/pci/vfio_pci_priv.h
index fca9d0dfac90..4e7162234a2e 100644
--- a/drivers/vfio/pci/vfio_pci_priv.h
+++ b/drivers/vfio/pci/vfio_pci_priv.h
@@ -93,6 +93,8 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 				struct vfio_info_cap *caps);
 int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev);
 void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev);
+int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags,
+			      void __user *arg, size_t argsz);
 #else
 static inline int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 					      struct vfio_info_cap *caps)
@@ -107,6 +109,13 @@ static inline int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
 
 static inline void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
 {}
+
+static inline int vfio_pci_zdev_feature_err(struct vfio_device *device,
+					    u32 flags, void __user *arg,
+					    size_t argsz)
+{
+	return -ENOTTY;
+}
 #endif
 
 static inline bool vfio_pci_is_vga(struct pci_dev *pdev)
diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c
index 0990fdb146b7..f47f36314a1c 100644
--- a/drivers/vfio/pci/vfio_pci_zdev.c
+++ b/drivers/vfio/pci/vfio_pci_zdev.c
@@ -24,7 +24,7 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 {
 	struct vfio_device_info_cap_zpci_base cap = {
 		.header.id = VFIO_DEVICE_INFO_CAP_ZPCI_BASE,
-		.header.version = 2,
+		.header.version = 3,
 		.start_dma = zdev->start_dma,
 		.end_dma = zdev->end_dma,
 		.pchid = zdev->pchid,
@@ -32,7 +32,8 @@ static int zpci_base_cap(struct zpci_dev *zdev, struct vfio_info_cap *caps)
 		.fmb_length = zdev->fmb_length,
 		.pft = zdev->pft,
 		.gid = zdev->pfgid,
-		.fh = zdev->fh
+		.fh = zdev->fh,
+		.ccdf_err_length = sizeof(struct zpci_ccdf_err)
 	};
 
 	return vfio_info_add_capability(caps, &cap.header, sizeof(cap));
@@ -141,27 +142,78 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev,
 	return ret;
 }
 
+int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags,
+			      void __user *arg, size_t argsz)
+{
+	struct vfio_device_feature_zpci_err err;
+	struct vfio_pci_core_device *vdev;
+	struct zpci_ccdf_err ccdf = {};
+	struct zpci_dev *zdev;
+	int ret;
+
+	vdev = container_of(device, struct vfio_pci_core_device, vdev);
+	zdev = to_zpci(vdev->pdev);
+	if (!zdev)
+		return -ENODEV;
+
+	ret = vfio_check_feature(flags, argsz, VFIO_DEVICE_FEATURE_GET,
+				 sizeof(err));
+	if (ret != 1)
+		return ret;
+
+	if (copy_from_user(&err, arg, sizeof(err)))
+		return -EFAULT;
+
+	if (!err.data)
+		return -EINVAL;
+
+	ret = zpci_get_pending_error(zdev, &ccdf);
+	if (ret)
+		return ret;
+
+	if (copy_to_user(u64_to_user_ptr(err.data), &ccdf, sizeof(ccdf))) {
+		dev_warn_ratelimited(device->dev,
+				     "Failed to handle PCI error event for PCI function 0x%x",
+				     zdev->fid);
+		return -EFAULT;
+	}
+
+	return 0;
+}
+
 int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev)
 {
 	struct zpci_dev *zdev = to_zpci(vdev->pdev);
+	int ret;
 
 	if (!zdev)
 		return -ENODEV;
 
+	zpci_start_mediated_recovery(zdev);
+
 	if (!vdev->vdev.kvm)
 		return 0;
 
+	ret = -ENOENT;
 	if (zpci_kvm_hook.kvm_register)
-		return zpci_kvm_hook.kvm_register(zdev, vdev->vdev.kvm);
+		ret = zpci_kvm_hook.kvm_register(zdev, vdev->vdev.kvm);
+
+	if (ret)
+		zpci_stop_mediated_recovery(zdev);
 
-	return -ENOENT;
+	return ret;
 }
 
 void vfio_pci_zdev_close_device(struct vfio_pci_core_device *vdev)
 {
 	struct zpci_dev *zdev = to_zpci(vdev->pdev);
 
-	if (!zdev || !vdev->vdev.kvm)
+	if (!zdev)
+		return;
+
+	zpci_stop_mediated_recovery(zdev);
+
+	if (!vdev->vdev.kvm)
 		return;
 
 	if (zpci_kvm_hook.kvm_unregister)