[PATCH openEuler-21.09 18/38] vfio/pci: provide customized live migration VFIO driver framework

4 Sep 2021

From: Longfang Liu liulongfang@huawei.com
driver inclusion
category: feature
bugzilla: https://gitee.com/openeuler/kernel/issues/I473Q4?from=project-issue
----------------------------------------------------------------------
vfio_pci_vendor_driver_ops includes these parts:
(1) .probe() and .remove() interface to be called by vfio_pci_probe()
and vfio_pci_remove().
(2) pointer to struct vfio_device_ops. It will be registered as ops of vfio
device if .probe() succeeds.
(3) vendor modules call macro module_vfio_pci_register_vendor_handler to
generate module_init and module_exit.
(4) export functions vfio_pci_vendor_data(), vfio_pci_irq_type(),
vfio_pci_num_regions(), vfio_pci_pdev(), and functions in vfio_pci_ops,
so they are able to be called from outside modules and make them a kind of
inherited by vfio_device_ops provided by vendor modules
(5) allows a simpler VFIO_DEVICE_GET_INFO ioctl in vendor driver,
let vfio_pci know number of vendor regions and vendor irqs
(6) allows vendor driver to read/write to bars directly which is useful
in security checking condition.
(7) allows vendor driver triggers this VFIO_IRQ_TYPE_REMAP_BAR_REGION
when it wants to notify userspace to remap PCI BARs.
Signed-off-by: Longfang Liu liulongfang@huawei.com
Reviewed-by: Hao Fang fanghao11@huawei.com
Reviewed-by: Mingqiang Ling lingmingqiang@huawei.com
Signed-off-by: Zheng Zengkai zhengzengkai@huawei.com
---
 drivers/vfio/pci/vfio_pci.c         | 183 ++++++++++++++++++++++++++--
 drivers/vfio/pci/vfio_pci_private.h |   9 ++
 drivers/vfio/pci/vfio_pci_rdwr.c    |  10 ++
 include/linux/vfio.h                |  52 ++++++++
 4 files changed, 243 insertions(+), 11 deletions(-)

diff --git a/drivers/vfio/pci/vfio_pci.c b/drivers/vfio/pci/vfio_pci.c
index 42612e193a00..df018a4554b6 100644
--- a/drivers/vfio/pci/vfio_pci.c
+++ b/drivers/vfio/pci/vfio_pci.c
@@ -74,6 +74,61 @@ static inline bool vfio_vga_disabled(void)
 #endif
 }
+static struct vfio_pci {
+	struct mutex		vendor_drivers_lock;
+	struct list_head	vendor_drivers_list;
+} vfio_pci;
+
+struct pci_dev *vfio_pci_pdev(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	return vdev->pdev;
+}
+EXPORT_SYMBOL_GPL(vfio_pci_pdev);
+
+int vfio_pci_num_regions(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	return vdev->num_regions;
+}
+EXPORT_SYMBOL_GPL(vfio_pci_num_regions);
+
+int vfio_pci_irq_type(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	return vdev->irq_type;
+}
+EXPORT_SYMBOL_GPL(vfio_pci_irq_type);
+
+void *vfio_pci_vendor_data(void *device_data)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	return vdev->vendor_data;
+}
+EXPORT_SYMBOL_GPL(vfio_pci_vendor_data);
+
+int vfio_pci_set_vendor_regions(void *device_data, int num_vendor_regions)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	vdev->num_vendor_regions = num_vendor_regions;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_pci_set_vendor_regions);
+
+int vfio_pci_set_vendor_irqs(void *device_data, int num_vendor_irqs)
+{
+	struct vfio_pci_device *vdev = device_data;
+
+	vdev->num_vendor_irqs = num_vendor_irqs;
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vfio_pci_set_vendor_irqs);
+
 static bool vfio_pci_dev_in_denylist(struct pci_dev *pdev)
 {
    switch (pdev->vendor) {
@@ -914,7 +969,7 @@ static void vfio_pci_vf_token_user_add(struct vfio_pci_device *vdev, int val)
    vfio_device_put(pf_dev);
 }
-static void vfio_pci_release(void *device_data)
+void vfio_pci_release(void *device_data)
 {
    struct vfio_pci_device *vdev = device_data;
@@ -941,8 +996,9 @@ static void vfio_pci_release(void *device_data)
module_put(THIS_MODULE);
 }
+EXPORT_SYMBOL_GPL(vfio_pci_release);
-static int vfio_pci_open(void *device_data)
+int vfio_pci_open(void *device_data)
 {
    struct vfio_pci_device *vdev = device_data;
    int ret = 0;
@@ -967,6 +1023,7 @@ static int vfio_pci_open(void *device_data)
    	module_put(THIS_MODULE);
    return ret;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_open);
static int vfio_pci_get_irq_count(struct vfio_pci_device *vdev, int irq_type)
 {
@@ -1161,7 +1218,7 @@ struct vfio_devices {
    int max_index;
 };
-static long vfio_pci_ioctl(void *device_data,
+long vfio_pci_ioctl(void *device_data,
    		   unsigned int cmd, unsigned long arg)
 {
    struct vfio_pci_device *vdev = device_data;
@@ -1193,8 +1250,10 @@ static long vfio_pci_ioctl(void *device_data,
    	if (vdev->reset_works)
    		info.flags |= VFIO_DEVICE_FLAGS_RESET;
-		info.num_regions = VFIO_PCI_NUM_REGIONS + vdev->num_regions;
-		info.num_irqs = VFIO_PCI_NUM_IRQS + vdev->num_ext_irqs;
+		info.num_regions = VFIO_PCI_NUM_REGIONS + vdev->num_regions +
+						   vdev->num_vendor_regions;
+		info.num_irqs = VFIO_PCI_NUM_IRQS + vdev->num_ext_irqs +
+						vdev->num_vendor_irqs;
if (IS_ENABLED(CONFIG_VFIO_PCI_ZDEV)) {
    		int ret = vfio_pci_info_zdev_add_caps(vdev, &caps);
@@ -1819,6 +1878,7 @@ static long vfio_pci_ioctl(void *device_data,
return -ENOTTY;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_ioctl);
static ssize_t vfio_pci_rw(void *device_data, char __user *buf,
    		   size_t count, loff_t *ppos, bool iswrite)
@@ -1852,7 +1912,7 @@ static ssize_t vfio_pci_rw(void *device_data, char __user *buf,
    return -EINVAL;
 }
-static ssize_t vfio_pci_read(void *device_data, char __user *buf,
+ssize_t vfio_pci_read(void *device_data, char __user *buf,
    		     size_t count, loff_t *ppos)
 {
    if (!count)
@@ -1860,8 +1920,9 @@ static ssize_t vfio_pci_read(void *device_data, char __user *buf,
return vfio_pci_rw(device_data, buf, count, ppos, false);
 }
+EXPORT_SYMBOL_GPL(vfio_pci_read);
-static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
+ssize_t vfio_pci_write(void *device_data, const char __user *buf,
    		      size_t count, loff_t *ppos)
 {
    if (!count)
@@ -1869,6 +1930,7 @@ static ssize_t vfio_pci_write(void *device_data, const char __user *buf,
return vfio_pci_rw(device_data, (char __user *)buf, count, ppos, true);
 }
+EXPORT_SYMBOL_GPL(vfio_pci_write);
/* Return 1 on zap and vma_lock acquired, 0 on contention (only with @try) */
 static int vfio_pci_zap_and_vma_lock(struct vfio_pci_device *vdev, bool try)
@@ -2064,7 +2126,7 @@ static const struct vm_operations_struct vfio_pci_mmap_ops = {
    .fault = vfio_pci_mmap_fault,
 };
-static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
+int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
 {
    struct vfio_pci_device *vdev = device_data;
    struct pci_dev *pdev = vdev->pdev;
@@ -2133,8 +2195,9 @@ static int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma)
return 0;
 }
+EXPORT_SYMBOL_GPL(vfio_pci_mmap);
-static void vfio_pci_request(void *device_data, unsigned int count)
+void vfio_pci_request(void *device_data, unsigned int count)
 {
    struct vfio_pci_device *vdev = device_data;
    struct pci_dev *pdev = vdev->pdev;
@@ -2154,6 +2217,7 @@ static void vfio_pci_request(void *device_data, unsigned int count)
mutex_unlock(&vdev->igate);
 }
+EXPORT_SYMBOL_GPL(vfio_pci_request);
static int vfio_pci_validate_vf_token(struct vfio_pci_device *vdev,
    			      bool vf_token, uuid_t *uuid)
@@ -2250,7 +2314,7 @@ static int vfio_pci_validate_vf_token(struct vfio_pci_device *vdev,
#define VF_TOKEN_ARG "vf_token="
-static int vfio_pci_match(void *device_data, char *buf)
+int vfio_pci_match(void *device_data, char *buf)
 {
    struct vfio_pci_device *vdev = device_data;
    bool vf_token = false;
@@ -2298,6 +2362,7 @@ static int vfio_pci_match(void *device_data, char *buf)
return 1; /* Match */
 }
+EXPORT_SYMBOL_GPL(vfio_pci_match);
static const struct vfio_device_ops vfio_pci_ops = {
    .name		= "vfio-pci",
@@ -2404,6 +2469,35 @@ static void vfio_pci_vga_uninit(struct vfio_pci_device *vdev)
    				      VGA_RSRC_LEGACY_MEM);
 }
+static int probe_vendor_drivers(struct vfio_pci_device *vdev)
+{
+	struct vfio_pci_vendor_driver *driver;
+	int ret = -ENODEV;
+
+	request_module("vfio-pci:%x-%x", vdev->pdev->vendor,
+					 vdev->pdev->device);
+
+	mutex_lock(&vfio_pci.vendor_drivers_lock);
+	list_for_each_entry(driver, &vfio_pci.vendor_drivers_list, next) {
+		void *data;
+
+		if (!try_module_get(driver->ops->owner))
+			continue;
+
+		data = driver->ops->probe(vdev->pdev);
+		if (IS_ERR(data)) {
+			module_put(driver->ops->owner);
+			continue;
+		}
+		vdev->vendor_driver = driver;
+		vdev->vendor_data = data;
+		ret = 0;
+		break;
+	}
+	mutex_unlock(&vfio_pci.vendor_drivers_lock);
+	return ret;
+}
+
 static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
 {
    struct vfio_pci_device *vdev;
@@ -2477,7 +2571,11 @@ static int vfio_pci_probe(struct pci_dev *pdev, const struct pci_device_id *id)
    	vfio_pci_set_power_state(vdev, PCI_D3hot);
    }
-	ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
+	if (probe_vendor_drivers(vdev))
+		ret = vfio_add_group_dev(&pdev->dev, &vfio_pci_ops, vdev);
+	else
+		ret = vfio_add_group_dev(&pdev->dev,
+				vdev->vendor_driver->ops->device_ops, vdev);
    if (ret)
    	goto out_power;
    return 0;
@@ -2517,6 +2615,12 @@ static void vfio_pci_remove(struct pci_dev *pdev)
    	vfio_pci_set_power_state(vdev, PCI_D0);
mutex_destroy(&vdev->ioeventfds_lock);
+
+	if (vdev->vendor_driver) {
+		vdev->vendor_driver->ops->remove(vdev->vendor_data);
+		module_put(vdev->vendor_driver->ops->owner);
+	}
+
    kfree(vdev->region);
    kfree(vdev->pm_save);
    kfree(vdev);
@@ -2868,6 +2972,9 @@ static int __init vfio_pci_init(void)
    if (ret)
    	return ret;
+	mutex_init(&vfio_pci.vendor_drivers_lock);
+	INIT_LIST_HEAD(&vfio_pci.vendor_drivers_list);
+
    /* Register and scan for devices */
    ret = pci_register_driver(&vfio_pci_driver);
    if (ret)
@@ -2885,6 +2992,60 @@ static int __init vfio_pci_init(void)
    return ret;
 }
+int __vfio_pci_register_vendor_driver(struct vfio_pci_vendor_driver_ops *ops)
+{
+	struct vfio_pci_vendor_driver *driver, *tmp;
+
+	if (!ops || !ops->device_ops)
+		return -EINVAL;
+
+	driver = kzalloc(sizeof(*driver), GFP_KERNEL);
+	if (!driver)
+		return -ENOMEM;
+
+	driver->ops = ops;
+
+	mutex_lock(&vfio_pci.vendor_drivers_lock);
+
+	/* Check for duplicates */
+	list_for_each_entry(tmp, &vfio_pci.vendor_drivers_list, next) {
+		if (tmp->ops->device_ops == ops->device_ops) {
+			mutex_unlock(&vfio_pci.vendor_drivers_lock);
+			kfree(driver);
+			return -EINVAL;
+		}
+	}
+
+	list_add(&driver->next, &vfio_pci.vendor_drivers_list);
+
+	mutex_unlock(&vfio_pci.vendor_drivers_lock);
+
+	if (!try_module_get(THIS_MODULE))
+		return -ENODEV;
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(__vfio_pci_register_vendor_driver);
+
+void vfio_pci_unregister_vendor_driver(struct vfio_device_ops *device_ops)
+{
+	struct vfio_pci_vendor_driver *driver, *tmp;
+
+	mutex_lock(&vfio_pci.vendor_drivers_lock);
+	list_for_each_entry_safe(driver, tmp,
+				 &vfio_pci.vendor_drivers_list, next) {
+		if (driver->ops->device_ops == device_ops) {
+			list_del(&driver->next);
+			mutex_unlock(&vfio_pci.vendor_drivers_lock);
+			kfree(driver);
+			module_put(THIS_MODULE);
+			return;
+		}
+	}
+	mutex_unlock(&vfio_pci.vendor_drivers_lock);
+}
+EXPORT_SYMBOL_GPL(vfio_pci_unregister_vendor_driver);
+
 module_init(vfio_pci_init);
 module_exit(vfio_pci_cleanup);
diff --git a/drivers/vfio/pci/vfio_pci_private.h b/drivers/vfio/pci/vfio_pci_private.h
index 5944f96ced0c..318328602874 100644
--- a/drivers/vfio/pci/vfio_pci_private.h
+++ b/drivers/vfio/pci/vfio_pci_private.h
@@ -112,6 +112,11 @@ struct vfio_pci_mmap_vma {
    struct list_head	vma_next;
 };
+struct vfio_pci_vendor_driver {
+	const struct vfio_pci_vendor_driver_ops *ops;
+	struct list_head                        next;
+};
+
 struct vfio_pci_device {
    struct pci_dev		*pdev;
    void __iomem		*barmap[PCI_STD_NUM_BARS];
@@ -127,6 +132,8 @@ struct vfio_pci_device {
    struct vfio_ext_irq	*ext_irqs;
    int			num_ext_irqs;
    int			num_regions;
+	int			num_vendor_regions;
+	int			num_vendor_irqs;
    struct vfio_pci_region	*region;
    u8			msi_qmax;
    u8			msix_bar;
@@ -163,6 +170,8 @@ struct vfio_pci_device {
    struct mutex		vma_lock;
    struct list_head	vma_list;
    struct rw_semaphore	memory_lock;
+	void			*vendor_data;
+	struct vfio_pci_vendor_driver	*vendor_driver;
 };
#define is_intx(vdev) (vdev->irq_type == VFIO_PCI_INTX_IRQ_INDEX)
diff --git a/drivers/vfio/pci/vfio_pci_rdwr.c b/drivers/vfio/pci/vfio_pci_rdwr.c
index 78c494fe35cc..43c11b5f5486 100644
--- a/drivers/vfio/pci/vfio_pci_rdwr.c
+++ b/drivers/vfio/pci/vfio_pci_rdwr.c
@@ -224,6 +224,16 @@ static int vfio_pci_setup_barmap(struct vfio_pci_device *vdev, int bar)
    return 0;
 }
+void __iomem *vfio_pci_get_barmap(void *device_data, int bar)
+{
+	int ret;
+	struct vfio_pci_device *vdev = device_data;
+
+	ret = vfio_pci_setup_barmap(vdev, bar);
+	return ret ? ERR_PTR(ret) : vdev->barmap[bar];
+}
+EXPORT_SYMBOL_GPL(vfio_pci_get_barmap);
+
 ssize_t vfio_pci_bar_rw(struct vfio_pci_device *vdev, char __user *buf,
    		size_t count, loff_t *ppos, bool iswrite)
 {
diff --git a/include/linux/vfio.h b/include/linux/vfio.h
index 38d3c6a8dc7e..c3819fadf7c8 100644
--- a/include/linux/vfio.h
+++ b/include/linux/vfio.h
@@ -214,4 +214,56 @@ extern int vfio_virqfd_enable(void *opaque,
    		      void *data, struct virqfd **pvirqfd, int fd);
 extern void vfio_virqfd_disable(struct virqfd **pvirqfd);
+extern int vfio_pci_num_regions(void *device_data);
+extern struct pci_dev *vfio_pci_pdev(void *device_data);
+extern long vfio_pci_ioctl(void *device_data,
+			  unsigned int cmd, unsigned long arg);
+extern ssize_t vfio_pci_read(void *device_data, char __user *buf,
+			     size_t count, loff_t *ppos);
+extern ssize_t vfio_pci_write(void *device_data, const char __user *buf,
+			      size_t count, loff_t *ppos);
+extern int vfio_pci_mmap(void *device_data, struct vm_area_struct *vma);
+extern void vfio_pci_request(void *device_data, unsigned int count);
+extern int vfio_pci_open(void *device_data);
+extern void vfio_pci_release(void *device_data);
+extern void *vfio_pci_vendor_data(void *device_data);
+extern int vfio_pci_set_vendor_regions(void *device_data,
+					int num_vendor_regions);
+
+struct vfio_pci_vendor_driver_ops {
+	char			*name;
+	struct module		*owner;
+	void			*(*probe)(struct pci_dev *pdev);
+	void			(*remove)(void *vendor_data);
+	struct vfio_device_ops *device_ops;
+};
+int __vfio_pci_register_vendor_driver(struct vfio_pci_vendor_driver_ops *ops);
+void vfio_pci_unregister_vendor_driver(struct vfio_device_ops *device_ops);
+
+#define vfio_pci_register_vendor_driver(__name, __probe, __remove,	\
+					__device_ops)			\
+static struct vfio_pci_vendor_driver_ops  __ops ## _node = {		\
+	.owner		= THIS_MODULE,					\
+	.name		= __name,					\
+	.probe		= __probe,					\
+	.remove		= __remove,					\
+	.device_ops	= __device_ops,					\
+};									\
+__vfio_pci_register_vendor_driver(&__ops ## _node)
+
+#define module_vfio_pci_register_vendor_handler(name, probe, remove,	\
+						device_ops)		\
+static int __init device_ops ## _module_init(void)			\
+{									\
+	vfio_pci_register_vendor_driver(name, probe, remove,		\
+					device_ops);			\
+	return 0;							\
+};									\
+static void __exit device_ops ## _module_exit(void)			\
+{									\
+	vfio_pci_unregister_vendor_driver(device_ops);			\
+};									\
+module_init(device_ops ## _module_init);				\
+module_exit(device_ops ## _module_exit)
+
 #endif /* VFIO_H */
-- 
2.20.1

    

2024

2023

2022

2021

2020

2019

[PATCH openEuler-21.09 18/38] vfio/pci: provide customized live migration VFIO driver framework