[PATCH v4 1/2] hisi_acc_vfio_pci: fix NULL dereference in reset_prepare on PF passthrough

[Longfang Liu]

When a PF is bound to the driver via driver_override and passed
through to a VM, its pf_qm stays NULL. The PCI error handler
reset_prepare() runs during open_device through
pci_try_reset_function(), before the mig_ops gate, and dereferences
the NULL pf_qm for the timeout log, crashing the kernel.

Move the mig_ops check to the entry of reset_prepare() and
aer_reset_done() so non-migration devices skip the QM_RESETTING
coordination. Also clear set_reset_flag together with QM_RESETTING
in aer_reset_done(); the flag was never cleared before, so a later
timed-out reset could release a foreign lock. Replace
pci_iov_vf_id() >= 0 with pdev->is_virtfn in probe() for clearer
on-VF gating.

Fixes: b0eed085903e ("hisi_acc_vfio_pci: Add support for VFIO live migration")
Fixes: a22099ed7936f ("hisi_acc_vfio_pci: fix VF reset timeout issue")
Signed-off-by: Longfang Liu <liulongfang@xxxxxxxxxx>
---
 .../vfio/pci/hisilicon/hisi_acc_vfio_pci.c    | 19 ++++++++++++-------
 1 file changed, 12 insertions(+), 7 deletions(-)

diff --git a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
index 86362ec424a5..8ff69c8d1ff7 100644
--- a/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
+++ b/drivers/vfio/pci/hisilicon/hisi_acc_vfio_pci.c
@@ -1154,9 +1154,14 @@ static void hisi_acc_vf_pci_reset_prepare(struct pci_dev *pdev)
 {
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
 	struct hisi_qm *qm = hisi_acc_vdev->pf_qm;
-	struct device *dev = &qm->pdev->dev;
+	struct device *dev = &pdev->dev;
 	u32 delay = 0;
 
+	if (!hisi_acc_vdev->core_device.vdev.mig_ops) {
+		dev_err(dev, "device not support migration\n");
+		return;
+	}
+
 	/* All reset requests need to be queued for processing */
 	while (test_and_set_bit(QM_RESETTING, &qm->misc_ctl)) {
 		msleep(1);
@@ -1174,12 +1179,14 @@ static void hisi_acc_vf_pci_aer_reset_done(struct pci_dev *pdev)
 	struct hisi_acc_vf_core_device *hisi_acc_vdev = hisi_acc_drvdata(pdev);
 	struct hisi_qm *qm = hisi_acc_vdev->pf_qm;
 
-	if (hisi_acc_vdev->set_reset_flag)
-		clear_bit(QM_RESETTING, &qm->misc_ctl);
-
 	if (!hisi_acc_vdev->core_device.vdev.mig_ops)
 		return;
 
+	if (hisi_acc_vdev->set_reset_flag) {
+		clear_bit(QM_RESETTING, &qm->misc_ctl);
+		hisi_acc_vdev->set_reset_flag = false;
+	}
+
 	mutex_lock(&hisi_acc_vdev->state_mutex);
 	hisi_acc_vf_reset(hisi_acc_vdev);
 	mutex_unlock(&hisi_acc_vdev->state_mutex);
@@ -1670,13 +1677,11 @@ static int hisi_acc_vfio_pci_probe(struct pci_dev *pdev, const struct pci_device
 	struct hisi_acc_vf_core_device *hisi_acc_vdev;
 	const struct vfio_device_ops *ops = &hisi_acc_vfio_pci_ops;
 	struct hisi_qm *pf_qm;
-	int vf_id;
 	int ret;
 
 	pf_qm = hisi_acc_get_pf_qm(pdev);
 	if (pf_qm && pf_qm->ver >= QM_HW_V3) {
-		vf_id = pci_iov_vf_id(pdev);
-		if (vf_id >= 0)
+		if (pdev->is_virtfn)
 			ops = &hisi_acc_vfio_pci_migrn_ops;
 		else
 			pci_warn(pdev, "migration support failed, continue with generic interface\n");
-- 
2.43.0