drivers/vfio: EEH support for VFIO PCI device

The patch adds new IOCTL commands for sPAPR VFIO container device
to support EEH functionality for PCI devices, which have been passed
through from host to somebody else via VFIO.

Signed-off-by: Gavin Shan <gwshan@linux.vnet.ibm.com>
Acked-by: Alexander Graf <agraf@suse.de>
Acked-by: Alex Williamson <alex.williamson@redhat.com>
Signed-off-by: Benjamin Herrenschmidt <benh@kernel.crashing.org>

4 files changed, 118 insertions, 5 deletions

diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile
index 72bfabc..50e30bc 100644
--- a/drivers/vfio/Makefile
+++ b/drivers/vfio/Makefile
@@ -1,4 +1,5 @@
 obj-$(CONFIG_VFIO) += vfio.o
 obj-$(CONFIG_VFIO_IOMMU_TYPE1) += vfio_iommu_type1.o
 obj-$(CONFIG_VFIO_IOMMU_SPAPR_TCE) += vfio_iommu_spapr_tce.o
+obj-$(CONFIG_EEH) += vfio_spapr_eeh.o
 obj-$(CONFIG_VFIO_PCI) += pci/
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 010e0f8..e2ee80f 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -157,8 +157,10 @@ static void vfio_pci_release(void *device_data)
 {
 	struct vfio_pci_device *vdev = device_data;
 
-	if (atomic_dec_and_test(&vdev->refcnt))
+	if (atomic_dec_and_test(&vdev->refcnt)) {
+		vfio_spapr_pci_eeh_release(vdev->pdev);
 		vfio_pci_disable(vdev);
+	}
 
 	module_put(THIS_MODULE);
 }
@@ -166,19 +168,27 @@ static void vfio_pci_release(void *device_data)
 static int vfio_pci_open(void *device_data)
 {
 	struct vfio_pci_device *vdev = device_data;
+	int ret;
 
 	if (!try_module_get(THIS_MODULE))
 		return -ENODEV;
 
 	if (atomic_inc_return(&vdev->refcnt) == 1) {
-		int ret = vfio_pci_enable(vdev);
+		ret = vfio_pci_enable(vdev);
+		if (ret)
+			goto error;
+
+		ret = vfio_spapr_pci_eeh_open(vdev->pdev);
 		if (ret) {
-			module_put(THIS_MODULE);
-			return ret;
+			vfio_pci_disable(vdev);
+			goto error;
 		}
 	}
 
 	return 0;
+error:
+	module_put(THIS_MODULE);
+	return ret;
 }
 
 static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index a84788b..730b4ef 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -156,7 +156,16 @@ static long tce_iommu_ioctl(void *iommu_data,
 
 	switch (cmd) {
 	case VFIO_CHECK_EXTENSION:
-		return (arg == VFIO_SPAPR_TCE_IOMMU) ? 1 : 0;
+		switch (arg) {
+		case VFIO_SPAPR_TCE_IOMMU:
+			ret = 1;
+			break;
+		default:
+			ret = vfio_spapr_iommu_eeh_ioctl(NULL, cmd, arg);
+			break;
+		}
+
+		return (ret < 0) ? 0 : ret;
 
 	case VFIO_IOMMU_SPAPR_TCE_GET_INFO: {
 		struct vfio_iommu_spapr_tce_info info;
@@ -283,6 +292,12 @@ static long tce_iommu_ioctl(void *iommu_data,
 		tce_iommu_disable(container);
 		mutex_unlock(&container->lock);
 		return 0;
+	case VFIO_EEH_PE_OP:
+		if (!container->tbl || !container->tbl->it_group)
+			return -ENODEV;
+
+		return vfio_spapr_iommu_eeh_ioctl(container->tbl->it_group,
+						  cmd, arg);
 	}
 
 	return -ENOTTY;
diff --git a/drivers/vfio/vfio_spapr_eeh.c b/drivers/vfio/vfio_spapr_eeh.c
new file mode 100644
index 0000000..f834b4c
--- /dev/null
+++ b/drivers/vfio/vfio_spapr_eeh.c
@@ -0,0 +1,87 @@
+/*
+ * EEH functionality support for VFIO devices. The feature is only
+ * available on sPAPR compatible platforms.
+ *
+ * Copyright Gavin Shan, IBM Corporation 2014.
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License version 2 as
+ * published by the Free Software Foundation.
+ */
+
+#include <linux/uaccess.h>
+#include <linux/vfio.h>
+#include <asm/eeh.h>
+
+/* We might build address mapping here for "fast" path later */
+int vfio_spapr_pci_eeh_open(struct pci_dev *pdev)
+{
+	return eeh_dev_open(pdev);
+}
+
+void vfio_spapr_pci_eeh_release(struct pci_dev *pdev)
+{
+	eeh_dev_release(pdev);
+}
+
+long vfio_spapr_iommu_eeh_ioctl(struct iommu_group *group,
+				unsigned int cmd, unsigned long arg)
+{
+	struct eeh_pe *pe;
+	struct vfio_eeh_pe_op op;
+	unsigned long minsz;
+	long ret = -EINVAL;
+
+	switch (cmd) {
+	case VFIO_CHECK_EXTENSION:
+		if (arg == VFIO_EEH)
+			ret = eeh_enabled() ? 1 : 0;
+		else
+			ret = 0;
+		break;
+	case VFIO_EEH_PE_OP:
+		pe = eeh_iommu_group_to_pe(group);
+		if (!pe)
+			return -ENODEV;
+
+		minsz = offsetofend(struct vfio_eeh_pe_op, op);
+		if (copy_from_user(&op, (void __user *)arg, minsz))
+			return -EFAULT;
+		if (op.argsz < minsz || op.flags)
+			return -EINVAL;
+
+		switch (op.op) {
+		case VFIO_EEH_PE_DISABLE:
+			ret = eeh_pe_set_option(pe, EEH_OPT_DISABLE);
+			break;
+		case VFIO_EEH_PE_ENABLE:
+			ret = eeh_pe_set_option(pe, EEH_OPT_ENABLE);
+			break;
+		case VFIO_EEH_PE_UNFREEZE_IO:
+			ret = eeh_pe_set_option(pe, EEH_OPT_THAW_MMIO);
+			break;
+		case VFIO_EEH_PE_UNFREEZE_DMA:
+			ret = eeh_pe_set_option(pe, EEH_OPT_THAW_DMA);
+			break;
+		case VFIO_EEH_PE_GET_STATE:
+			ret = eeh_pe_get_state(pe);
+			break;
+		case VFIO_EEH_PE_RESET_DEACTIVATE:
+			ret = eeh_pe_reset(pe, EEH_RESET_DEACTIVATE);
+			break;
+		case VFIO_EEH_PE_RESET_HOT:
+			ret = eeh_pe_reset(pe, EEH_RESET_HOT);
+			break;
+		case VFIO_EEH_PE_RESET_FUNDAMENTAL:
+			ret = eeh_pe_reset(pe, EEH_RESET_FUNDAMENTAL);
+			break;
+		case VFIO_EEH_PE_CONFIGURE:
+			ret = eeh_pe_configure(pe);
+			break;
+		default:
+			ret = -EINVAL;
+		}
+	}
+
+	return ret;
+}