summaryrefslogtreecommitdiffstats
path: root/drivers/vfio
diff options
context:
space:
mode:
Diffstat (limited to 'drivers/vfio')
-rw-r--r--drivers/vfio/Kconfig2
-rw-r--r--drivers/vfio/mdev/Kconfig1
-rw-r--r--drivers/vfio/mdev/Makefile1
-rw-r--r--drivers/vfio/mdev/mdev_core.c36
-rw-r--r--drivers/vfio/mdev/mdev_private.h2
-rw-r--r--drivers/vfio/mdev/mdev_sysfs.c2
-rw-r--r--drivers/vfio/pci/Kconfig1
-rw-r--r--drivers/vfio/pci/Makefile1
-rw-r--r--drivers/vfio/pci/vfio_pci.c27
-rw-r--r--drivers/vfio/pci/vfio_pci_config.c29
-rw-r--r--drivers/vfio/pci/vfio_pci_nvlink2.c2
-rw-r--r--drivers/vfio/platform/Kconfig1
-rw-r--r--drivers/vfio/platform/reset/Kconfig1
-rw-r--r--drivers/vfio/platform/reset/vfio_platform_amdxgbe.c5
-rw-r--r--drivers/vfio/platform/vfio_platform_common.c12
-rw-r--r--drivers/vfio/vfio.c59
-rw-r--r--drivers/vfio/vfio_iommu_spapr_tce.c5
-rw-r--r--drivers/vfio/vfio_iommu_type1.c156
18 files changed, 233 insertions, 110 deletions
diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig
index 9de5ed38da83..e5a7a454fe17 100644
--- a/drivers/vfio/Kconfig
+++ b/drivers/vfio/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config VFIO_IOMMU_TYPE1
tristate
depends on VFIO
@@ -22,7 +23,6 @@ menuconfig VFIO
tristate "VFIO Non-Privileged userspace driver framework"
depends on IOMMU_API
select VFIO_IOMMU_TYPE1 if (X86 || S390 || ARM || ARM64)
- select ANON_INODES
help
VFIO provides a framework for secure userspace device drivers.
See Documentation/vfio.txt for more details.
diff --git a/drivers/vfio/mdev/Kconfig b/drivers/vfio/mdev/Kconfig
index 14fdb106a827..ba94a076887f 100644
--- a/drivers/vfio/mdev/Kconfig
+++ b/drivers/vfio/mdev/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config VFIO_MDEV
tristate "Mediated device driver framework"
diff --git a/drivers/vfio/mdev/Makefile b/drivers/vfio/mdev/Makefile
index fa2d5ea466ee..101516fdf375 100644
--- a/drivers/vfio/mdev/Makefile
+++ b/drivers/vfio/mdev/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
mdev-y := mdev_core.o mdev_sysfs.o mdev_driver.o
diff --git a/drivers/vfio/mdev/mdev_core.c b/drivers/vfio/mdev/mdev_core.c
index b96fedc77ee5..3cc1a05fde1c 100644
--- a/drivers/vfio/mdev/mdev_core.c
+++ b/drivers/vfio/mdev/mdev_core.c
@@ -88,7 +88,7 @@ static void mdev_release_parent(struct kref *kref)
put_device(dev);
}
-static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
+static struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
{
if (parent)
kref_get(&parent->ref);
@@ -96,7 +96,7 @@ static inline struct mdev_parent *mdev_get_parent(struct mdev_parent *parent)
return parent;
}
-static inline void mdev_put_parent(struct mdev_parent *parent)
+static void mdev_put_parent(struct mdev_parent *parent)
{
if (parent)
kref_put(&parent->ref, mdev_release_parent);
@@ -141,7 +141,7 @@ static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
*/
ret = parent->ops->remove(mdev);
if (ret && !force_remove)
- return -EBUSY;
+ return ret;
sysfs_remove_groups(&mdev->dev.kobj, parent->ops->mdev_attr_groups);
return 0;
@@ -149,10 +149,10 @@ static int mdev_device_remove_ops(struct mdev_device *mdev, bool force_remove)
static int mdev_device_remove_cb(struct device *dev, void *data)
{
- if (!dev_is_mdev(dev))
- return 0;
+ if (dev_is_mdev(dev))
+ mdev_device_remove(dev, true);
- return mdev_device_remove(dev, data ? *(bool *)data : true);
+ return 0;
}
/*
@@ -181,6 +181,7 @@ int mdev_register_device(struct device *dev, const struct mdev_parent_ops *ops)
/* Check for duplicate */
parent = __find_parent_device(dev);
if (parent) {
+ parent = NULL;
ret = -EEXIST;
goto add_dev_err;
}
@@ -239,7 +240,6 @@ EXPORT_SYMBOL(mdev_register_device);
void mdev_unregister_device(struct device *dev)
{
struct mdev_parent *parent;
- bool force_remove = true;
mutex_lock(&parent_list_lock);
parent = __find_parent_device(dev);
@@ -253,8 +253,7 @@ void mdev_unregister_device(struct device *dev)
list_del(&parent->next);
class_compat_remove_link(mdev_bus_compat_class, dev, NULL);
- device_for_each_child(dev, (void *)&force_remove,
- mdev_device_remove_cb);
+ device_for_each_child(dev, NULL, mdev_device_remove_cb);
parent_remove_sysfs_files(parent);
@@ -310,7 +309,6 @@ int mdev_device_create(struct kobject *kobj,
mutex_unlock(&mdev_list_lock);
mdev->parent = parent;
- kref_init(&mdev->ref);
mdev->dev.parent = dev;
mdev->dev.bus = &mdev_bus_type;
@@ -390,6 +388,24 @@ int mdev_device_remove(struct device *dev, bool force_remove)
return 0;
}
+int mdev_set_iommu_device(struct device *dev, struct device *iommu_device)
+{
+ struct mdev_device *mdev = to_mdev_device(dev);
+
+ mdev->iommu_device = iommu_device;
+
+ return 0;
+}
+EXPORT_SYMBOL(mdev_set_iommu_device);
+
+struct device *mdev_get_iommu_device(struct device *dev)
+{
+ struct mdev_device *mdev = to_mdev_device(dev);
+
+ return mdev->iommu_device;
+}
+EXPORT_SYMBOL(mdev_get_iommu_device);
+
static int __init mdev_init(void)
{
return mdev_bus_register();
diff --git a/drivers/vfio/mdev/mdev_private.h b/drivers/vfio/mdev/mdev_private.h
index 379758c52b1b..36cbbdb754de 100644
--- a/drivers/vfio/mdev/mdev_private.h
+++ b/drivers/vfio/mdev/mdev_private.h
@@ -30,9 +30,9 @@ struct mdev_device {
struct mdev_parent *parent;
guid_t uuid;
void *driver_data;
- struct kref ref;
struct list_head next;
struct kobject *type_kobj;
+ struct device *iommu_device;
bool active;
};
diff --git a/drivers/vfio/mdev/mdev_sysfs.c b/drivers/vfio/mdev/mdev_sysfs.c
index 5193a0e0ce5a..cbf94b8165ea 100644
--- a/drivers/vfio/mdev/mdev_sysfs.c
+++ b/drivers/vfio/mdev/mdev_sysfs.c
@@ -280,7 +280,7 @@ type_link_failed:
void mdev_remove_sysfs_files(struct device *dev, struct mdev_type *type)
{
+ sysfs_remove_files(&dev->kobj, mdev_device_attrs);
sysfs_remove_link(&dev->kobj, "mdev_type");
sysfs_remove_link(type->devices_kobj, dev_name(dev));
- sysfs_remove_files(&dev->kobj, mdev_device_attrs);
}
diff --git a/drivers/vfio/pci/Kconfig b/drivers/vfio/pci/Kconfig
index d0f8e4f5a039..ac3c1dd3edef 100644
--- a/drivers/vfio/pci/Kconfig
+++ b/drivers/vfio/pci/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config VFIO_PCI
tristate "VFIO support for PCI devices"
depends on VFIO && PCI && EVENTFD
diff --git a/drivers/vfio/pci/Makefile b/drivers/vfio/pci/Makefile
index 9662c063a6b1..f027f8a0e89c 100644
--- a/drivers/vfio/pci/Makefile
+++ b/drivers/vfio/pci/Makefile
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
vfio-pci-y := vfio_pci.o vfio_pci_intrs.o vfio_pci_rdwr.o vfio_pci_config.o
vfio-pci-$(CONFIG_VFIO_PCI_IGD) += vfio_pci_igd.o
diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index a25659b5a5d1..cab71da46f4a 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -12,6 +12,7 @@
*/
#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+#define dev_fmt pr_fmt
#include <linux/device.h>
#include <linux/eventfd.h>
@@ -287,12 +288,11 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
pci_save_state(pdev);
vdev->pci_saved_state = pci_store_saved_state(pdev);
if (!vdev->pci_saved_state)
- pr_debug("%s: Couldn't store %s saved state\n",
- __func__, dev_name(&pdev->dev));
+ pci_dbg(pdev, "%s: Couldn't store saved state\n", __func__);
if (likely(!nointxmask)) {
if (vfio_pci_nointx(pdev)) {
- dev_info(&pdev->dev, "Masking broken INTx support\n");
+ pci_info(pdev, "Masking broken INTx support\n");
vdev->nointx = true;
pci_intx(pdev, 0);
} else
@@ -336,8 +336,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
IS_ENABLED(CONFIG_VFIO_PCI_IGD)) {
ret = vfio_pci_igd_init(vdev);
if (ret) {
- dev_warn(&vdev->pdev->dev,
- "Failed to setup Intel IGD regions\n");
+ pci_warn(pdev, "Failed to setup Intel IGD regions\n");
goto disable_exit;
}
}
@@ -346,8 +345,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
ret = vfio_pci_nvdia_v100_nvlink2_init(vdev);
if (ret && ret != -ENODEV) {
- dev_warn(&vdev->pdev->dev,
- "Failed to setup NVIDIA NV2 RAM region\n");
+ pci_warn(pdev, "Failed to setup NVIDIA NV2 RAM region\n");
goto disable_exit;
}
}
@@ -356,8 +354,7 @@ static int vfio_pci_enable(struct vfio_pci_device *vdev)
IS_ENABLED(CONFIG_VFIO_PCI_NVLINK2)) {
ret = vfio_pci_ibm_npu2_init(vdev);
if (ret && ret != -ENODEV) {
- dev_warn(&vdev->pdev->dev,
- "Failed to setup NVIDIA NV2 ATSD region\n");
+ pci_warn(pdev, "Failed to setup NVIDIA NV2 ATSD region\n");
goto disable_exit;
}
}
@@ -429,8 +426,7 @@ static void vfio_pci_disable(struct vfio_pci_device *vdev)
* is just busy work.
*/
if (pci_load_and_free_saved_state(pdev, &vdev->pci_saved_state)) {
- pr_info("%s: Couldn't reload %s saved state\n",
- __func__, dev_name(&pdev->dev));
+ pci_info(pdev, "%s: Couldn't reload saved state\n", __func__);
if (!vdev->reset_works)
goto out;
@@ -1255,17 +1251,18 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
static void vfio_pci_request(void *device_data, unsigned int count)
{
struct vfio_pci_device *vdev = device_data;
+ struct pci_dev *pdev = vdev->pdev;
mutex_lock(&vdev->igate);
if (vdev->req_trigger) {
if (!(count % 10))
- dev_notice_ratelimited(&vdev->pdev->dev,
+ pci_notice_ratelimited(pdev,
"Relaying device request to user (#%u)\n",
count);
eventfd_signal(vdev->req_trigger, 1);
} else if (count == 0) {
- dev_warn(&vdev->pdev->dev,
+ pci_warn(pdev,
"No device request channel registered, blocked until released by user\n");
}
@@ -1661,11 +1658,11 @@ static void __init vfio_pci_fill_ids(void)
rc = pci_add_dynid(&vfio_pci_driver, vendor, device,
subvendor, subdevice, class, class_mask, 0);
if (rc)
- pr_warn("failed to add dynamic id [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x (%d)\n",
+ pr_warn("failed to add dynamic id [%04x:%04x[%04x:%04x]] class %#08x/%08x (%d)\n",
vendor, device, subvendor, subdevice,
class, class_mask, rc);
else
- pr_info("add [%04hx:%04hx[%04hx:%04hx]] class %#08x/%08x\n",
+ pr_info("add [%04x:%04x[%04x:%04x]] class %#08x/%08x\n",
vendor, device, subvendor, subdevice,
class, class_mask);
}
diff --git a/drivers/vfio/pci/vfio_pci_config.c b/drivers/vfio/pci/vfio_pci_config.c
index e82b51114687..52963a904790 100644
--- a/drivers/vfio/pci/vfio_pci_config.c
+++ b/drivers/vfio/pci/vfio_pci_config.c
@@ -412,8 +412,7 @@ static void vfio_bar_restore(struct vfio_pci_device *vdev)
if (pdev->is_virtfn)
return;
- pr_info("%s: %s reset recovery - restoring bars\n",
- __func__, dev_name(&pdev->dev));
+ pci_info(pdev, "%s: reset recovery - restoring BARs\n", __func__);
for (i = PCI_BASE_ADDRESS_0; i <= PCI_BASE_ADDRESS_5; i += 4, rbar++)
pci_user_write_config_dword(pdev, i, *rbar);
@@ -1298,8 +1297,8 @@ static int vfio_cap_len(struct vfio_pci_device *vdev, u8 cap, u8 pos)
else
return PCI_SATA_SIZEOF_SHORT;
default:
- pr_warn("%s: %s unknown length for pci cap 0x%x@0x%x\n",
- dev_name(&pdev->dev), __func__, cap, pos);
+ pci_warn(pdev, "%s: unknown length for PCI cap %#x@%#x\n",
+ __func__, cap, pos);
}
return 0;
@@ -1372,8 +1371,8 @@ static int vfio_ext_cap_len(struct vfio_pci_device *vdev, u16 ecap, u16 epos)
}
return PCI_TPH_BASE_SIZEOF;
default:
- pr_warn("%s: %s unknown length for pci ecap 0x%x@0x%x\n",
- dev_name(&pdev->dev), __func__, ecap, epos);
+ pci_warn(pdev, "%s: unknown length for PCI ecap %#x@%#x\n",
+ __func__, ecap, epos);
}
return 0;
@@ -1474,8 +1473,8 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
}
if (!len) {
- pr_info("%s: %s hiding cap 0x%x\n",
- __func__, dev_name(&pdev->dev), cap);
+ pci_info(pdev, "%s: hiding cap %#x@%#x\n", __func__,
+ cap, pos);
*prev = next;
pos = next;
continue;
@@ -1486,9 +1485,8 @@ static int vfio_cap_init(struct vfio_pci_device *vdev)
if (likely(map[pos + i] == PCI_CAP_ID_INVALID))
continue;
- pr_warn("%s: %s pci config conflict @0x%x, was cap 0x%x now cap 0x%x\n",
- __func__, dev_name(&pdev->dev),
- pos + i, map[pos + i], cap);
+ pci_warn(pdev, "%s: PCI config conflict @%#x, was cap %#x now cap %#x\n",
+ __func__, pos + i, map[pos + i], cap);
}
BUILD_BUG_ON(PCI_CAP_ID_MAX >= PCI_CAP_ID_INVALID_VIRT);
@@ -1549,8 +1547,8 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
}
if (!len) {
- pr_info("%s: %s hiding ecap 0x%x@0x%x\n",
- __func__, dev_name(&pdev->dev), ecap, epos);
+ pci_info(pdev, "%s: hiding ecap %#x@%#x\n",
+ __func__, ecap, epos);
/* If not the first in the chain, we can skip over it */
if (prev) {
@@ -1572,9 +1570,8 @@ static int vfio_ecap_init(struct vfio_pci_device *vdev)
if (likely(map[epos + i] == PCI_CAP_ID_INVALID))
continue;
- pr_warn("%s: %s pci config conflict @0x%x, was ecap 0x%x now ecap 0x%x\n",
- __func__, dev_name(&pdev->dev),
- epos + i, map[epos + i], ecap);
+ pci_warn(pdev, "%s: PCI config conflict @%#x, was ecap %#x now ecap %#x\n",
+ __func__, epos + i, map[epos + i], ecap);
}
/*
diff --git a/drivers/vfio/pci/vfio_pci_nvlink2.c b/drivers/vfio/pci/vfio_pci_nvlink2.c
index 32f695ffe128..50fe3c4f7feb 100644
--- a/drivers/vfio/pci/vfio_pci_nvlink2.c
+++ b/drivers/vfio/pci/vfio_pci_nvlink2.c
@@ -472,6 +472,8 @@ int vfio_pci_ibm_npu2_init(struct vfio_pci_device *vdev)
return 0;
free_exit:
+ if (data->base)
+ memunmap(data->base);
kfree(data);
return ret;
diff --git a/drivers/vfio/platform/Kconfig b/drivers/vfio/platform/Kconfig
index bb30128782aa..dc1a3c44f2c6 100644
--- a/drivers/vfio/platform/Kconfig
+++ b/drivers/vfio/platform/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config VFIO_PLATFORM
tristate "VFIO support for platform devices"
depends on VFIO && EVENTFD && (ARM || ARM64)
diff --git a/drivers/vfio/platform/reset/Kconfig b/drivers/vfio/platform/reset/Kconfig
index 392e3c09def0..1edbe9ee7356 100644
--- a/drivers/vfio/platform/reset/Kconfig
+++ b/drivers/vfio/platform/reset/Kconfig
@@ -1,3 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
config VFIO_PLATFORM_CALXEDAXGMAC_RESET
tristate "VFIO support for calxeda xgmac reset"
depends on VFIO_PLATFORM
diff --git a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
index 3ddb2704221d..fe95964bc3be 100644
--- a/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
+++ b/drivers/vfio/platform/reset/vfio_platform_amdxgbe.c
@@ -89,7 +89,8 @@ static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
} while ((pcs_value & MDIO_CTRL1_RESET) && --count);
if (pcs_value & MDIO_CTRL1_RESET)
- pr_warn("%s XGBE PHY reset timeout\n", __func__);
+ dev_warn(vdev->device, "%s: XGBE PHY reset timeout\n",
+ __func__);
/* disable auto-negotiation */
value = xmdio_read(xpcs_regs->ioaddr, MDIO_MMD_AN, MDIO_CTRL1);
@@ -114,7 +115,7 @@ static int vfio_platform_amdxgbe_reset(struct vfio_platform_device *vdev)
usleep_range(500, 600);
if (!count)
- pr_warn("%s MAC SW reset failed\n", __func__);
+ dev_warn(vdev->device, "%s: MAC SW reset failed\n", __func__);
return 0;
}
diff --git a/drivers/vfio/platform/vfio_platform_common.c b/drivers/vfio/platform/vfio_platform_common.c
index c0cd824be2b7..2a45b36bcf58 100644
--- a/drivers/vfio/platform/vfio_platform_common.c
+++ b/drivers/vfio/platform/vfio_platform_common.c
@@ -12,6 +12,8 @@
* GNU General Public License for more details.
*/
+#define dev_fmt(fmt) "VFIO: " fmt
+
#include <linux/device.h>
#include <linux/acpi.h>
#include <linux/iommu.h>
@@ -63,7 +65,7 @@ static int vfio_platform_acpi_probe(struct vfio_platform_device *vdev,
adev = ACPI_COMPANION(dev);
if (!adev) {
- pr_err("VFIO: ACPI companion device not found for %s\n",
+ dev_err(dev, "ACPI companion device not found for %s\n",
vdev->name);
return -ENODEV;
}
@@ -638,7 +640,7 @@ static int vfio_platform_of_probe(struct vfio_platform_device *vdev,
ret = device_property_read_string(dev, "compatible",
&vdev->compat);
if (ret)
- pr_err("VFIO: Cannot retrieve compat for %s\n", vdev->name);
+ dev_err(dev, "Cannot retrieve compat for %s\n", vdev->name);
return ret;
}
@@ -680,14 +682,14 @@ int vfio_platform_probe_common(struct vfio_platform_device *vdev,
ret = vfio_platform_get_reset(vdev);
if (ret && vdev->reset_required) {
- pr_err("VFIO: No reset function found for device %s\n",
- vdev->name);
+ dev_err(dev, "No reset function found for device %s\n",
+ vdev->name);
return ret;
}
group = vfio_iommu_group_get(dev);
if (!group) {
- pr_err("VFIO: No IOMMU group for device %s\n", vdev->name);
+ dev_err(dev, "No IOMMU group for device %s\n", vdev->name);
ret = -EINVAL;
goto put_reset;
}
diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c
index a3030cdf3c18..82fcf07fa9ea 100644
--- a/drivers/vfio/vfio.c
+++ b/drivers/vfio/vfio.c
@@ -34,6 +34,7 @@
#include <linux/uaccess.h>
#include <linux/vfio.h>
#include <linux/wait.h>
+#include <linux/sched/signal.h>
#define DRIVER_VERSION "0.3"
#define DRIVER_AUTHOR "Alex Williamson <alex.williamson@redhat.com>"
@@ -704,8 +705,8 @@ static int vfio_group_nb_add_dev(struct vfio_group *group, struct device *dev)
return 0;
/* TODO Prevent device auto probing */
- WARN(1, "Device %s added to live group %d!\n", dev_name(dev),
- iommu_group_id(group->iommu_group));
+ dev_WARN(dev, "Device added to live group %d!\n",
+ iommu_group_id(group->iommu_group));
return 0;
}
@@ -748,25 +749,22 @@ static int vfio_iommu_group_notifier(struct notifier_block *nb,
*/
break;
case IOMMU_GROUP_NOTIFY_BIND_DRIVER:
- pr_debug("%s: Device %s, group %d binding to driver\n",
- __func__, dev_name(dev),
- iommu_group_id(group->iommu_group));
+ dev_dbg(dev, "%s: group %d binding to driver\n", __func__,
+ iommu_group_id(group->iommu_group));
break;
case IOMMU_GROUP_NOTIFY_BOUND_DRIVER:
- pr_debug("%s: Device %s, group %d bound to driver %s\n",
- __func__, dev_name(dev),
- iommu_group_id(group->iommu_group), dev->driver->name);
+ dev_dbg(dev, "%s: group %d bound to driver %s\n", __func__,
+ iommu_group_id(group->iommu_group), dev->driver->name);
BUG_ON(vfio_group_nb_verify(group, dev));
break;
case IOMMU_GROUP_NOTIFY_UNBIND_DRIVER:
- pr_debug("%s: Device %s, group %d unbinding from driver %s\n",
- __func__, dev_name(dev),
- iommu_group_id(group->iommu_group), dev->driver->name);
+ dev_dbg(dev, "%s: group %d unbinding from driver %s\n",
+ __func__, iommu_group_id(group->iommu_group),
+ dev->driver->name);
break;
case IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER:
- pr_debug("%s: Device %s, group %d unbound from driver\n",
- __func__, dev_name(dev),
- iommu_group_id(group->iommu_group));
+ dev_dbg(dev, "%s: group %d unbound from driver\n", __func__,
+ iommu_group_id(group->iommu_group));
/*
* XXX An unbound device in a live group is ok, but we'd
* really like to avoid the above BUG_ON by preventing other
@@ -830,8 +828,8 @@ int vfio_add_group_dev(struct device *dev,
device = vfio_group_get_device(group, dev);
if (device) {
- WARN(1, "Device %s already exists on group %d\n",
- dev_name(dev), iommu_group_id(iommu_group));
+ dev_WARN(dev, "Device already exists on group %d\n",
+ iommu_group_id(iommu_group));
vfio_device_put(device);
vfio_group_put(group);
return -EBUSY;
@@ -904,30 +902,17 @@ void *vfio_device_data(struct vfio_device *device)
}
EXPORT_SYMBOL_GPL(vfio_device_data);
-/* Given a referenced group, check if it contains the device */
-static bool vfio_dev_present(struct vfio_group *group, struct device *dev)
-{
- struct vfio_device *device;
-
- device = vfio_group_get_device(group, dev);
- if (!device)
- return false;
-
- vfio_device_put(device);
- return true;
-}
-
/*
* Decrement the device reference count and wait for the device to be
* removed. Open file descriptors for the device... */
void *vfio_del_group_dev(struct device *dev)
{
+ DEFINE_WAIT_FUNC(wait, woken_wake_function);
struct vfio_device *device = dev_get_drvdata(dev);
struct vfio_group *group = device->group;
void *device_data = device->device_data;
struct vfio_unbound_dev *unbound;
unsigned int i = 0;
- long ret;
bool interrupted = false;
/*
@@ -964,6 +949,8 @@ void *vfio_del_group_dev(struct device *dev)
* interval with counter to allow the driver to take escalating
* measures to release the device if it has the ability to do so.
*/
+ add_wait_queue(&vfio.release_q, &wait);
+
do {
device = vfio_group_get_device(group, dev);
if (!device)
@@ -975,12 +962,10 @@ void *vfio_del_group_dev(struct device *dev)
vfio_device_put(device);
if (interrupted) {
- ret = wait_event_timeout(vfio.release_q,
- !vfio_dev_present(group, dev), HZ * 10);
+ wait_woken(&wait, TASK_UNINTERRUPTIBLE, HZ * 10);
} else {
- ret = wait_event_interruptible_timeout(vfio.release_q,
- !vfio_dev_present(group, dev), HZ * 10);
- if (ret == -ERESTARTSYS) {
+ wait_woken(&wait, TASK_INTERRUPTIBLE, HZ * 10);
+ if (signal_pending(current)) {
interrupted = true;
dev_warn(dev,
"Device is currently in use, task"
@@ -989,8 +974,10 @@ void *vfio_del_group_dev(struct device *dev)
current->comm, task_pid_nr(current));
}
}
- } while (ret <= 0);
+ } while (1);
+
+ remove_wait_queue(&vfio.release_q, &wait);
/*
* In order to support multiple devices per group, devices can be
* plucked from the group while other devices in the group are still
diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c
index 8dbb270998f4..40ddc0c5f677 100644
--- a/drivers/vfio/vfio_iommu_spapr_tce.c
+++ b/drivers/vfio/vfio_iommu_spapr_tce.c
@@ -532,7 +532,8 @@ static int tce_iommu_use_page(unsigned long tce, unsigned long *hpa)
enum dma_data_direction direction = iommu_tce_direction(tce);
if (get_user_pages_fast(tce & PAGE_MASK, 1,
- direction != DMA_TO_DEVICE, &page) != 1)
+ direction != DMA_TO_DEVICE ? FOLL_WRITE : 0,
+ &page) != 1)
return -EFAULT;
*hpa = __pa((unsigned long) page_address(page));
@@ -1398,7 +1399,7 @@ unlock_exit:
mutex_unlock(&container->lock);
}
-const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
+static const struct vfio_iommu_driver_ops tce_iommu_driver_ops = {
.name = "iommu-vfio-powerpc",
.owner = THIS_MODULE,
.open = tce_iommu_open,
diff --git a/drivers/vfio/vfio_iommu_type1.c b/drivers/vfio/vfio_iommu_type1.c
index 73652e21efec..3ddc375e7063 100644
--- a/drivers/vfio/vfio_iommu_type1.c
+++ b/drivers/vfio/vfio_iommu_type1.c
@@ -58,12 +58,18 @@ module_param_named(disable_hugepages,
MODULE_PARM_DESC(disable_hugepages,
"Disable VFIO IOMMU support for IOMMU hugepages.");
+static unsigned int dma_entry_limit __read_mostly = U16_MAX;
+module_param_named(dma_entry_limit, dma_entry_limit, uint, 0644);
+MODULE_PARM_DESC(dma_entry_limit,
+ "Maximum number of user DMA mappings per container (65535).");
+
struct vfio_iommu {
struct list_head domain_list;
struct vfio_domain *external_domain; /* domain for external user */
struct mutex lock;
struct rb_root dma_list;
struct blocking_notifier_head notifier;
+ unsigned int dma_avail;
bool v2;
bool nesting;
};
@@ -91,6 +97,7 @@ struct vfio_dma {
struct vfio_group {
struct iommu_group *iommu_group;
struct list_head next;
+ bool mdev_group; /* An mdev group */
};
/*
@@ -351,7 +358,8 @@ static int vaddr_get_pfn(struct mm_struct *mm, unsigned long vaddr,
down_read(&mm->mmap_sem);
if (mm == current->mm) {
- ret = get_user_pages_longterm(vaddr, 1, flags, page, vmas);
+ ret = get_user_pages(vaddr, 1, flags | FOLL_LONGTERM, page,
+ vmas);
} else {
ret = get_user_pages_remote(NULL, mm, vaddr, 1, flags, page,
vmas, NULL);
@@ -558,7 +566,7 @@ static int vfio_iommu_type1_pin_pages(void *iommu_data,
mutex_lock(&iommu->lock);
/* Fail if notifier list is empty */
- if ((!iommu->external_domain) || (!iommu->notifier.head)) {
+ if (!iommu->notifier.head) {
ret = -EINVAL;
goto pin_done;
}
@@ -640,11 +648,6 @@ static int vfio_iommu_type1_unpin_pages(void *iommu_data,
mutex_lock(&iommu->lock);
- if (!iommu->external_domain) {
- mutex_unlock(&iommu->lock);
- return -EINVAL;
- }
-
do_accounting = !IS_IOMMU_CAP_DOMAIN_IN_CONTAINER(iommu);
for (i = 0; i < npage; i++) {
struct vfio_dma *dma;
@@ -836,6 +839,7 @@ static void vfio_remove_dma(struct vfio_iommu *iommu, struct vfio_dma *dma)
vfio_unlink_dma(iommu, dma);
put_task_struct(dma->task);
kfree(dma);
+ iommu->dma_avail++;
}
static unsigned long vfio_pgsize_bitmap(struct vfio_iommu *iommu)
@@ -1081,12 +1085,18 @@ static int vfio_dma_do_map(struct vfio_iommu *iommu,
goto out_unlock;
}
+ if (!iommu->dma_avail) {
+ ret = -ENOSPC;
+ goto out_unlock;
+ }
+
dma = kzalloc(sizeof(*dma), GFP_KERNEL);
if (!dma) {
ret = -ENOMEM;
goto out_unlock;
}
+ iommu->dma_avail--;
dma->iova = iova;
dma->vaddr = vaddr;
dma->prot = prot;
@@ -1298,13 +1308,109 @@ static bool vfio_iommu_has_sw_msi(struct iommu_group *group, phys_addr_t *base)
return ret;
}
+static struct device *vfio_mdev_get_iommu_device(struct device *dev)
+{
+ struct device *(*fn)(struct device *dev);
+ struct device *iommu_device;
+
+ fn = symbol_get(mdev_get_iommu_device);
+ if (fn) {
+ iommu_device = fn(dev);
+ symbol_put(mdev_get_iommu_device);
+
+ return iommu_device;
+ }
+
+ return NULL;
+}
+
+static int vfio_mdev_attach_domain(struct device *dev, void *data)
+{
+ struct iommu_domain *domain = data;
+ struct device *iommu_device;
+
+ iommu_device = vfio_mdev_get_iommu_device(dev);
+ if (iommu_device) {
+ if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX))
+ return iommu_aux_attach_device(domain, iommu_device);
+ else
+ return iommu_attach_device(domain, iommu_device);
+ }
+
+ return -EINVAL;
+}
+
+static int vfio_mdev_detach_domain(struct device *dev, void *data)
+{
+ struct iommu_domain *domain = data;
+ struct device *iommu_device;
+
+ iommu_device = vfio_mdev_get_iommu_device(dev);
+ if (iommu_device) {
+ if (iommu_dev_feature_enabled(iommu_device, IOMMU_DEV_FEAT_AUX))
+ iommu_aux_detach_device(domain, iommu_device);
+ else
+ iommu_detach_device(domain, iommu_device);
+ }
+
+ return 0;
+}
+
+static int vfio_iommu_attach_group(struct vfio_domain *domain,
+ struct vfio_group *group)
+{
+ if (group->mdev_group)
+ return iommu_group_for_each_dev(group->iommu_group,
+ domain->domain,
+ vfio_mdev_attach_domain);
+ else
+ return iommu_attach_group(domain->domain, group->iommu_group);
+}
+
+static void vfio_iommu_detach_group(struct vfio_domain *domain,
+ struct vfio_group *group)
+{
+ if (group->mdev_group)
+ iommu_group_for_each_dev(group->iommu_group, domain->domain,
+ vfio_mdev_detach_domain);
+ else
+ iommu_detach_group(domain->domain, group->iommu_group);
+}
+
+static bool vfio_bus_is_mdev(struct bus_type *bus)
+{
+ struct bus_type *mdev_bus;
+ bool ret = false;
+
+ mdev_bus = symbol_get(mdev_bus_type);
+ if (mdev_bus) {
+ ret = (bus == mdev_bus);
+ symbol_put(mdev_bus_type);
+ }
+
+ return ret;
+}
+
+static int vfio_mdev_iommu_device(struct device *dev, void *data)
+{
+ struct device **old = data, *new;
+
+ new = vfio_mdev_get_iommu_device(dev);
+ if (!new || (*old && *old != new))
+ return -EINVAL;
+
+ *old = new;
+
+ return 0;
+}
+
static int vfio_iommu_type1_attach_group(void *iommu_data,
struct iommu_group *iommu_group)
{
struct vfio_iommu *iommu = iommu_data;
struct vfio_group *group;
struct vfio_domain *domain, *d;
- struct bus_type *bus = NULL, *mdev_bus;
+ struct bus_type *bus = NULL;
int ret;
bool resv_msi, msi_remap;
phys_addr_t resv_msi_base;
@@ -1339,23 +1445,30 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
if (ret)
goto out_free;
- mdev_bus = symbol_get(mdev_bus_type);
+ if (vfio_bus_is_mdev(bus)) {
+ struct device *iommu_device = NULL;
- if (mdev_bus) {
- if ((bus == mdev_bus) && !iommu_present(bus)) {
- symbol_put(mdev_bus_type);
+ group->mdev_group = true;
+
+ /* Determine the isolation type */
+ ret = iommu_group_for_each_dev(iommu_group, &iommu_device,
+ vfio_mdev_iommu_device);
+ if (ret || !iommu_device) {
if (!iommu->external_domain) {
INIT_LIST_HEAD(&domain->group_list);
iommu->external_domain = domain;
- } else
+ } else {
kfree(domain);
+ }
list_add(&group->next,
&iommu->external_domain->group_list);
mutex_unlock(&iommu->lock);
+
return 0;
}
- symbol_put(mdev_bus_type);
+
+ bus = iommu_device->bus;
}
domain->domain = iommu_domain_alloc(bus);
@@ -1373,7 +1486,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
goto out_domain;
}
- ret = iommu_attach_group(domain->domain, iommu_group);
+ ret = vfio_iommu_attach_group(domain, group);
if (ret)
goto out_domain;
@@ -1405,8 +1518,8 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
list_for_each_entry(d, &iommu->domain_list, next) {
if (d->domain->ops == domain->domain->ops &&
d->prot == domain->prot) {
- iommu_detach_group(domain->domain, iommu_group);
- if (!iommu_attach_group(d->domain, iommu_group)) {
+ vfio_iommu_detach_group(domain, group);
+ if (!vfio_iommu_attach_group(d, group)) {
list_add(&group->next, &d->group_list);
iommu_domain_free(domain->domain);
kfree(domain);
@@ -1414,7 +1527,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
return 0;
}
- ret = iommu_attach_group(domain->domain, iommu_group);
+ ret = vfio_iommu_attach_group(domain, group);
if (ret)
goto out_domain;
}
@@ -1440,7 +1553,7 @@ static int vfio_iommu_type1_attach_group(void *iommu_data,
return 0;
out_detach:
- iommu_detach_group(domain->domain, iommu_group);
+ vfio_iommu_detach_group(domain, group);
out_domain:
iommu_domain_free(domain->domain);
out_free:
@@ -1531,7 +1644,7 @@ static void vfio_iommu_type1_detach_group(void *iommu_data,
if (!group)
continue;
- iommu_detach_group(domain->domain, iommu_group);
+ vfio_iommu_detach_group(domain, group);
list_del(&group->next);
kfree(group);
/*
@@ -1583,6 +1696,7 @@ static void *vfio_iommu_type1_open(unsigned long arg)
INIT_LIST_HEAD(&iommu->domain_list);
iommu->dma_list = RB_ROOT;
+ iommu->dma_avail = dma_entry_limit;
mutex_init(&iommu->lock);
BLOCKING_INIT_NOTIFIER_HEAD(&iommu->notifier);
@@ -1596,7 +1710,7 @@ static void vfio_release_domain(struct vfio_domain *domain, bool external)
list_for_each_entry_safe(group, group_tmp,
&domain->group_list, next) {
if (!external)
- iommu_detach_group(domain->domain, group->iommu_group);
+ vfio_iommu_detach_group(domain, group);
list_del(&group->next);
kfree(group);
}
generated by cgit v1.2.3-55-g7522 (git 2.39.0) at 2025-05-18 20:13:37 +0200