From c0560f51cf77472f4ed113539b0a02ca6cda7961 Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Tue, 24 Mar 2020 09:27:56 -0600 Subject: vfio: allow external user to get vfio group from device external user calls vfio_group_get_external_user_from_dev() with a device pointer to get the VFIO group associated with this device. The VFIO group is checked to be vialbe and have IOMMU set. Then container user counter is increased and VFIO group reference is hold to prevent the VFIO group from disposal before external user exits. when the external user finishes using of the VFIO group, it calls vfio_group_put_external_user() to dereference the VFIO group and the container user counter. Suggested-by: Alex Williamson Signed-off-by: Yan Zhao Signed-off-by: Alex Williamson --- include/linux/vfio.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e42a711a2800..fb71e0ac0e76 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -94,6 +94,8 @@ extern void vfio_unregister_iommu_driver( */ extern struct vfio_group *vfio_group_get_external_user(struct file *filep); extern void vfio_group_put_external_user(struct vfio_group *group); +extern struct vfio_group *vfio_group_get_external_user_from_dev(struct device + *dev); extern bool vfio_external_group_match_file(struct vfio_group *group, struct file *filep); extern int vfio_external_user_iommu_id(struct vfio_group *group); -- cgit From 8d46c0cca5f4dc0538173d62cd36b1119b5105bc Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Tue, 24 Mar 2020 09:27:57 -0600 Subject: vfio: introduce vfio_dma_rw to read/write a range of IOVAs vfio_dma_rw will read/write a range of user space memory pointed to by IOVA into/from a kernel buffer without enforcing pinning the user space memory. TODO: mark the IOVAs to user space memory dirty if they are written in vfio_dma_rw(). Cc: Kevin Tian Signed-off-by: Yan Zhao Signed-off-by: Alex Williamson --- include/linux/vfio.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index fb71e0ac0e76..34b2fdf4de6e 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -82,6 +82,8 @@ struct vfio_iommu_driver_ops { struct notifier_block *nb); int (*unregister_notifier)(void *iommu_data, struct notifier_block *nb); + int (*dma_rw)(void *iommu_data, dma_addr_t user_iova, + void *data, size_t count, bool write); }; extern int vfio_register_iommu_driver(const struct vfio_iommu_driver_ops *ops); @@ -109,6 +111,9 @@ extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage); +extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova, + void *data, size_t len, bool write); + /* each type has independent events */ enum vfio_notify_type { VFIO_IOMMU_NOTIFY = 0, -- cgit From 40280cf7e8ca7d31bb0a9d626f36f458fec32815 Mon Sep 17 00:00:00 2001 From: Yan Zhao Date: Tue, 24 Mar 2020 09:27:57 -0600 Subject: vfio: avoid inefficient operations on VFIO group in vfio_pin/unpin_pages vfio_group_pin_pages() and vfio_group_unpin_pages() are introduced to avoid inefficient search/check/ref/deref opertions associated with VFIO group as those in each calling into vfio_pin_pages() and vfio_unpin_pages(). VFIO group is taken as arg directly. The callers combine search/check/ref/deref operations associated with VFIO group by calling vfio_group_get_external_user()/vfio_group_get_external_user_from_dev() beforehand, and vfio_group_put_external_user() afterwards. Suggested-by: Alex Williamson Signed-off-by: Yan Zhao Signed-off-by: Alex Williamson --- include/linux/vfio.h | 6 ++++++ 1 file changed, 6 insertions(+) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 34b2fdf4de6e..be2bd358b952 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -111,6 +111,12 @@ extern int vfio_pin_pages(struct device *dev, unsigned long *user_pfn, extern int vfio_unpin_pages(struct device *dev, unsigned long *user_pfn, int npage); +extern int vfio_group_pin_pages(struct vfio_group *group, + unsigned long *user_iova_pfn, int npage, + int prot, unsigned long *phys_pfn); +extern int vfio_group_unpin_pages(struct vfio_group *group, + unsigned long *user_iova_pfn, int npage); + extern int vfio_dma_rw(struct vfio_group *group, dma_addr_t user_iova, void *data, size_t len, bool write); -- cgit From 5f3874c2a2310d9bd6969ca6764961d27a843b9d Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 24 Mar 2020 09:28:25 -0600 Subject: vfio: Include optional device match in vfio_device_ops callbacks Allow bus drivers to provide their own callback to match a device to the user provided string. Reviewed-by: Cornelia Huck Reviewed-by: Kevin Tian Signed-off-by: Alex Williamson --- include/linux/vfio.h | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'include') diff --git a/include/linux/vfio.h b/include/linux/vfio.h index e42a711a2800..029694b977f2 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -26,6 +26,9 @@ * operations documented below * @mmap: Perform mmap(2) on a region of the device file descriptor * @request: Request for the bus driver to release the device + * @match: Optional device name match callback (return: 0 for no-match, >0 for + * match, -errno for abort (ex. match with insufficient or incorrect + * additional args) */ struct vfio_device_ops { char *name; @@ -39,6 +42,7 @@ struct vfio_device_ops { unsigned long arg); int (*mmap)(void *device_data, struct vm_area_struct *vma); void (*request)(void *device_data, unsigned int count); + int (*match)(void *device_data, char *buf); }; extern struct iommu_group *vfio_iommu_group_get(struct device *dev); -- cgit From 43eeeecc8ed5fa05652d68032a8bfb1308ee9baa Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 24 Mar 2020 09:28:27 -0600 Subject: vfio: Introduce VFIO_DEVICE_FEATURE ioctl and first user The VFIO_DEVICE_FEATURE ioctl is meant to be a general purpose, device agnostic ioctl for setting, retrieving, and probing device features. This implementation provides a 16-bit field for specifying a feature index, where the data porition of the ioctl is determined by the semantics for the given feature. Additional flag bits indicate the direction and nature of the operation; SET indicates user data is provided into the device feature, GET indicates the device feature is written out into user data. The PROBE flag augments determining whether the given feature is supported, and if provided, whether the given operation on the feature is supported. The first user of this ioctl is for setting the vfio-pci VF token, where the user provides a shared secret key (UUID) on a SR-IOV PF device, which users must provide when opening associated VF devices. Reviewed-by: Cornelia Huck Reviewed-by: Kevin Tian Signed-off-by: Alex Williamson --- include/uapi/linux/vfio.h | 37 +++++++++++++++++++++++++++++++++++++ 1 file changed, 37 insertions(+) (limited to 'include') diff --git a/include/uapi/linux/vfio.h b/include/uapi/linux/vfio.h index 9e843a147ead..015516bcfaa3 100644 --- a/include/uapi/linux/vfio.h +++ b/include/uapi/linux/vfio.h @@ -707,6 +707,43 @@ struct vfio_device_ioeventfd { #define VFIO_DEVICE_IOEVENTFD _IO(VFIO_TYPE, VFIO_BASE + 16) +/** + * VFIO_DEVICE_FEATURE - _IORW(VFIO_TYPE, VFIO_BASE + 17, + * struct vfio_device_feature) + * + * Get, set, or probe feature data of the device. The feature is selected + * using the FEATURE_MASK portion of the flags field. Support for a feature + * can be probed by setting both the FEATURE_MASK and PROBE bits. A probe + * may optionally include the GET and/or SET bits to determine read vs write + * access of the feature respectively. Probing a feature will return success + * if the feature is supported and all of the optionally indicated GET/SET + * methods are supported. The format of the data portion of the structure is + * specific to the given feature. The data portion is not required for + * probing. GET and SET are mutually exclusive, except for use with PROBE. + * + * Return 0 on success, -errno on failure. + */ +struct vfio_device_feature { + __u32 argsz; + __u32 flags; +#define VFIO_DEVICE_FEATURE_MASK (0xffff) /* 16-bit feature index */ +#define VFIO_DEVICE_FEATURE_GET (1 << 16) /* Get feature into data[] */ +#define VFIO_DEVICE_FEATURE_SET (1 << 17) /* Set feature from data[] */ +#define VFIO_DEVICE_FEATURE_PROBE (1 << 18) /* Probe feature support */ + __u8 data[]; +}; + +#define VFIO_DEVICE_FEATURE _IO(VFIO_TYPE, VFIO_BASE + 17) + +/* + * Provide support for setting a PCI VF Token, which is used as a shared + * secret between PF and VF drivers. This feature may only be set on a + * PCI SR-IOV PF when SR-IOV is enabled on the PF and there are no existing + * open VFs. Data provided when setting this feature is a 16-byte array + * (__u8 b[16]), representing a UUID. + */ +#define VFIO_DEVICE_FEATURE_PCI_VF_TOKEN (0) + /* -------- API for Type1 VFIO IOMMU -------- */ /** -- cgit