Currently querying and setting capabilities is restricted to a single capability and contained within the virtio PCI driver. However, each device type has generic and device specific capabilities, that may be queried and set. In subsequent patches virtio_net will query and set flow filter capabilities. Move the admin related definitions to a new header file. It needs to be abstracted away from the PCI specifics to be used by upper layer drivers. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit Reviewed-by: Yishai Hadas --- drivers/virtio/virtio.c | 82 ++++++++++++++++ drivers/virtio/virtio_pci_common.h | 1 - drivers/virtio/virtio_pci_modern.c | 145 +++++++++++++++++------------ include/linux/virtio.h | 14 +++ include/linux/virtio_admin.h | 68 ++++++++++++++ include/uapi/linux/virtio_pci.h | 7 +- 6 files changed, 255 insertions(+), 62 deletions(-) create mode 100644 include/linux/virtio_admin.h diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index a09eb4d62f82..6bc268c11100 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -706,6 +706,88 @@ int virtio_device_reset_done(struct virtio_device *dev) } EXPORT_SYMBOL_GPL(virtio_device_reset_done); +/** + * virtio_device_cap_id_list_query - Query the list of available capability IDs + * @vdev: the virtio device + * @data: pointer to store the capability ID list result + * + * This function queries the virtio device for the list of available capability + * IDs that can be used with virtio_device_cap_get() and virtio_device_cap_set(). + * The result is stored in the provided data structure. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or capability queries, or a negative error code on other failures. + */ +int +virtio_device_cap_id_list_query(struct virtio_device *vdev, + struct virtio_admin_cmd_query_cap_id_result *data) +{ + const struct virtio_admin_ops *admin = vdev->admin_ops; + + if (!admin || !admin->cap_id_list_query) + return -EOPNOTSUPP; + + return admin->cap_id_list_query(vdev, data); +} +EXPORT_SYMBOL_GPL(virtio_device_cap_id_list_query); + +/** + * virtio_device_cap_get - Get a capability from a virtio device + * @vdev: the virtio device + * @id: capability ID to retrieve + * @caps: buffer to store the capability data + * @cap_size: size of the capability buffer in bytes + * + * This function retrieves a specific capability from the virtio device. + * The capability data is stored in the provided buffer. The caller must + * ensure the buffer is large enough to hold the capability data. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or capability retrieval, or a negative error code on other failures. + */ +int virtio_device_cap_get(struct virtio_device *vdev, + u16 id, + void *caps, + size_t cap_size) +{ + const struct virtio_admin_ops *admin = vdev->admin_ops; + + if (!admin || !admin->cap_get) + return -EOPNOTSUPP; + + return admin->cap_get(vdev, id, caps, cap_size); +} +EXPORT_SYMBOL_GPL(virtio_device_cap_get); + +/** + * virtio_device_cap_set - Set a capability on a virtio device + * @vdev: the virtio device + * @id: capability ID to set + * @caps: buffer containing the capability data to set + * @cap_size: size of the capability data in bytes + * + * This function sets a specific capability on the virtio device. + * The capability data is read from the provided buffer and applied + * to the device. The device may validate the capability data before + * applying it. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or capability setting, or a negative error code on other failures. + */ +int virtio_device_cap_set(struct virtio_device *vdev, + u16 id, + const void *caps, + size_t cap_size) +{ + const struct virtio_admin_ops *admin = vdev->admin_ops; + + if (!admin || !admin->cap_set) + return -EOPNOTSUPP; + + return admin->cap_set(vdev, id, caps, cap_size); +} +EXPORT_SYMBOL_GPL(virtio_device_cap_set); + static int virtio_init(void) { BUILD_BUG_ON(offsetof(struct virtio_device, features) != diff --git a/drivers/virtio/virtio_pci_common.h b/drivers/virtio/virtio_pci_common.h index 8cd01de27baf..fc26e035e7a6 100644 --- a/drivers/virtio/virtio_pci_common.h +++ b/drivers/virtio/virtio_pci_common.h @@ -48,7 +48,6 @@ struct virtio_pci_admin_vq { /* Protects virtqueue access. */ spinlock_t lock; u64 supported_cmds; - u64 supported_caps; u8 max_dev_parts_objects; struct ida dev_parts_ida; /* Name of the admin queue: avq.$vq_index. */ diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index dd0e65f71d41..c8bbd807371d 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -19,6 +19,7 @@ #define VIRTIO_PCI_NO_LEGACY #define VIRTIO_RING_NO_LEGACY #include "virtio_pci_common.h" +#include #define VIRTIO_AVQ_SGS_MAX 4 @@ -232,103 +233,123 @@ static void virtio_pci_admin_cmd_list_init(struct virtio_device *virtio_dev) kfree(data); } -static void -virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev) +static int vp_modern_admin_cmd_cap_get(struct virtio_device *virtio_dev, + u16 id, + void *caps, + size_t cap_size) { - struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev); - struct virtio_admin_cmd_cap_get_data *get_data; - struct virtio_admin_cmd_cap_set_data *set_data; - struct virtio_dev_parts_cap *result; + struct virtio_admin_cmd_cap_get_data *data __free(kfree) = NULL; struct virtio_admin_cmd cmd = {}; struct scatterlist result_sg; struct scatterlist data_sg; - u8 resource_objects_limit; - u16 set_data_size; - int ret; - get_data = kzalloc(sizeof(*get_data), GFP_KERNEL); - if (!get_data) - return; - - result = kzalloc(sizeof(*result), GFP_KERNEL); - if (!result) - goto end; + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; - get_data->id = cpu_to_le16(VIRTIO_DEV_PARTS_CAP); - sg_init_one(&data_sg, get_data, sizeof(*get_data)); - sg_init_one(&result_sg, result, sizeof(*result)); + data->id = cpu_to_le16(id); + sg_init_one(&data_sg, data, sizeof(*data)); + sg_init_one(&result_sg, caps, cap_size); cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DEVICE_CAP_GET); cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); cmd.data_sg = &data_sg; cmd.result_sg = &result_sg; - ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); - if (ret) - goto err_get; - set_data_size = sizeof(*set_data) + sizeof(*result); - set_data = kzalloc(set_data_size, GFP_KERNEL); - if (!set_data) - goto err_get; + return vp_modern_admin_cmd_exec(virtio_dev, &cmd); +} - set_data->id = cpu_to_le16(VIRTIO_DEV_PARTS_CAP); +static int vp_modern_admin_cmd_cap_set(struct virtio_device *virtio_dev, + u16 id, + const void *caps, + size_t cap_size) +{ + struct virtio_admin_cmd_cap_set_data *data __free(kfree) = NULL; + struct virtio_admin_cmd cmd = {}; + struct scatterlist data_sg; + size_t data_size; + + data_size = sizeof(*data) + cap_size; + data = kzalloc(data_size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->id = cpu_to_le16(id); + memcpy(data->cap_specific_data, caps, cap_size); + sg_init_one(&data_sg, data, data_size); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DRIVER_CAP_SET); + cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); + cmd.data_sg = &data_sg; + cmd.result_sg = NULL; + + return vp_modern_admin_cmd_exec(virtio_dev, &cmd); +} + +static void +virtio_pci_admin_cmd_dev_parts_objects_enable(struct virtio_device *virtio_dev) +{ + struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev); + struct virtio_dev_parts_cap *dev_parts; + u8 resource_objects_limit; + int ret; + + dev_parts = kzalloc(sizeof(*dev_parts), GFP_KERNEL); + if (!dev_parts) + return; + + ret = vp_modern_admin_cmd_cap_get(virtio_dev, VIRTIO_DEV_PARTS_CAP, + dev_parts, sizeof(*dev_parts)); + if (ret) + goto err; /* Set the limit to the minimum value between the GET and SET values * supported by the device. Since the obj_id for VIRTIO_DEV_PARTS_CAP * is a globally unique value per PF, there is no possibility of * overlap between GET and SET operations. */ - resource_objects_limit = min(result->get_parts_resource_objects_limit, - result->set_parts_resource_objects_limit); - result->get_parts_resource_objects_limit = resource_objects_limit; - result->set_parts_resource_objects_limit = resource_objects_limit; - memcpy(set_data->cap_specific_data, result, sizeof(*result)); - sg_init_one(&data_sg, set_data, set_data_size); - cmd.data_sg = &data_sg; - cmd.result_sg = NULL; - cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_DRIVER_CAP_SET); - ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + resource_objects_limit = min(dev_parts->get_parts_resource_objects_limit, + dev_parts->set_parts_resource_objects_limit); + dev_parts->get_parts_resource_objects_limit = resource_objects_limit; + dev_parts->set_parts_resource_objects_limit = resource_objects_limit; + + ret = vp_modern_admin_cmd_cap_set(virtio_dev, VIRTIO_DEV_PARTS_CAP, + dev_parts, sizeof(*dev_parts)); if (ret) - goto err_set; + goto err; /* Allocate IDR to manage the dev caps objects */ ida_init(&vp_dev->admin_vq.dev_parts_ida); vp_dev->admin_vq.max_dev_parts_objects = resource_objects_limit; -err_set: - kfree(set_data); -err_get: - kfree(result); -end: - kfree(get_data); +err: + kfree(dev_parts); } -static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev) +static int vp_modern_admin_cap_id_list_query(struct virtio_device *virtio_dev, + struct virtio_admin_cmd_query_cap_id_result *data) { - struct virtio_pci_device *vp_dev = to_vp_device(virtio_dev); - struct virtio_admin_cmd_query_cap_id_result *data; struct virtio_admin_cmd cmd = {}; struct scatterlist result_sg; - int ret; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return; sg_init_one(&result_sg, data, sizeof(*data)); cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_CAP_ID_LIST_QUERY); cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SELF); cmd.result_sg = &result_sg; - ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); - if (ret) - goto end; + return vp_modern_admin_cmd_exec(virtio_dev, &cmd); +} - /* Max number of caps fits into a single u64 */ - BUILD_BUG_ON(sizeof(data->supported_caps) > sizeof(u64)); +static void virtio_pci_admin_cmd_cap_init(struct virtio_device *virtio_dev) +{ + struct virtio_admin_cmd_query_cap_id_result *data; - vp_dev->admin_vq.supported_caps = le64_to_cpu(data->supported_caps[0]); + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return; + + if (vp_modern_admin_cap_id_list_query(virtio_dev, data)) + goto end; - if (!(vp_dev->admin_vq.supported_caps & (1 << VIRTIO_DEV_PARTS_CAP))) + if (!(VIRTIO_CAP_IN_LIST(data, VIRTIO_DEV_PARTS_CAP))) goto end; virtio_pci_admin_cmd_dev_parts_objects_enable(virtio_dev); @@ -1264,6 +1285,11 @@ static const struct virtio_config_ops virtio_pci_config_ops = { .enable_vq_after_reset = vp_modern_enable_vq_after_reset, }; +static const struct virtio_admin_ops virtio_pci_admin_ops = { + .cap_id_list_query = vp_modern_admin_cap_id_list_query, + .cap_get = vp_modern_admin_cmd_cap_get, + .cap_set = vp_modern_admin_cmd_cap_set, +}; /* the PCI probing function */ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) { @@ -1282,6 +1308,7 @@ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) else vp_dev->vdev.config = &virtio_pci_config_nodev_ops; + vp_dev->vdev.admin_ops = &virtio_pci_admin_ops; vp_dev->config_vector = vp_config_vector; vp_dev->setup_vq = setup_vq; vp_dev->del_vq = del_vq; diff --git a/include/linux/virtio.h b/include/linux/virtio.h index db31fc6f4f1f..7ab4ea75ad44 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -12,6 +12,7 @@ #include #include #include +#include /** * struct virtqueue - a queue to register buffers for sending or receiving. @@ -141,6 +142,7 @@ struct virtio_admin_cmd { * @id: the device type identification (used to match it with a driver). * @config: the configuration ops for this device. * @vringh_config: configuration ops for host vrings. + * @admin_ops: administration operations for this device. * @vqs: the list of virtqueues for this device. * @features: the 64 lower features supported by both driver and device. * @features_array: the full features space supported by both driver and @@ -161,6 +163,7 @@ struct virtio_device { struct virtio_device_id id; const struct virtio_config_ops *config; const struct vringh_config_ops *vringh_config; + const struct virtio_admin_ops *admin_ops; struct list_head vqs; VIRTIO_DECLARE_FEATURES(features); void *priv; @@ -195,6 +198,17 @@ int virtio_device_restore(struct virtio_device *dev); void virtio_reset_device(struct virtio_device *dev); int virtio_device_reset_prepare(struct virtio_device *dev); int virtio_device_reset_done(struct virtio_device *dev); +int +virtio_device_cap_id_list_query(struct virtio_device *vdev, + struct virtio_admin_cmd_query_cap_id_result *data); +int virtio_device_cap_get(struct virtio_device *vdev, + u16 id, + void *caps, + size_t cap_size); +int virtio_device_cap_set(struct virtio_device *vdev, + u16 id, + const void *caps, + size_t cap_size); size_t virtio_max_dma_size(const struct virtio_device *vdev); diff --git a/include/linux/virtio_admin.h b/include/linux/virtio_admin.h new file mode 100644 index 000000000000..bbf543d20be4 --- /dev/null +++ b/include/linux/virtio_admin.h @@ -0,0 +1,68 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Header file for virtio admin operations + */ +#include + +#ifndef _LINUX_VIRTIO_ADMIN_H +#define _LINUX_VIRTIO_ADMIN_H + +struct virtio_device; + +/** + * VIRTIO_CAP_IN_LIST - Check if a capability is supported in the capability list + * @cap_list: Pointer to capability list structure containing supported_caps array + * @cap: Capability ID to check + * + * The cap_list contains a supported_caps array of little-endian 64-bit integers + * where each bit represents a capability. Bit 0 of the first element represents + * capability ID 0, bit 1 represents capability ID 1, and so on. + * + * Return: 1 if capability is supported, 0 otherwise + */ +#define VIRTIO_CAP_IN_LIST(cap_list, cap) \ + (!!(1 & (le64_to_cpu(cap_list->supported_caps[cap / 64]) >> cap % 64))) + +/** + * struct virtio_admin_ops - Operations for virtio admin functionality + * + * This structure contains function pointers for performing administrative + * operations on virtio devices. All data and caps pointers must be allocated + * on the heap by the caller. + */ +struct virtio_admin_ops { + /** + * @cap_id_list_query: Query the list of supported capability IDs + * @vdev: The virtio device to query + * @data: Pointer to result structure (must be heap allocated) + * Return: 0 on success, negative error code on failure + */ + int (*cap_id_list_query)(struct virtio_device *vdev, + struct virtio_admin_cmd_query_cap_id_result *data); + /** + * @cap_get: Get capability data for a specific capability ID + * @vdev: The virtio device + * @id: Capability ID to retrieve + * @caps: Pointer to capability data structure (must be heap allocated) + * @cap_size: Size of the capability data structure + * Return: 0 on success, negative error code on failure + */ + int (*cap_get)(struct virtio_device *vdev, + u16 id, + void *caps, + size_t cap_size); + /** + * @cap_set: Set capability data for a specific capability ID + * @vdev: The virtio device + * @id: Capability ID to set + * @caps: Pointer to capability data structure (must be heap allocated) + * @cap_size: Size of the capability data structure + * Return: 0 on success, negative error code on failure + */ + int (*cap_set)(struct virtio_device *vdev, + u16 id, + const void *caps, + size_t cap_size); +}; + +#endif /* _LINUX_VIRTIO_ADMIN_H */ diff --git a/include/uapi/linux/virtio_pci.h b/include/uapi/linux/virtio_pci.h index c691ac210ce2..0d5ca0cff629 100644 --- a/include/uapi/linux/virtio_pci.h +++ b/include/uapi/linux/virtio_pci.h @@ -315,15 +315,18 @@ struct virtio_admin_cmd_notify_info_result { #define VIRTIO_DEV_PARTS_CAP 0x0000 +/* Update this value to largest implemented cap number. */ +#define VIRTIO_ADMIN_MAX_CAP 0x0fff + struct virtio_dev_parts_cap { __u8 get_parts_resource_objects_limit; __u8 set_parts_resource_objects_limit; }; -#define MAX_CAP_ID __KERNEL_DIV_ROUND_UP(VIRTIO_DEV_PARTS_CAP + 1, 64) +#define VIRTIO_ADMIN_CAP_ID_ARRAY_SIZE __KERNEL_DIV_ROUND_UP(VIRTIO_ADMIN_MAX_CAP, 64) struct virtio_admin_cmd_query_cap_id_result { - __le64 supported_caps[MAX_CAP_ID]; + __le64 supported_caps[VIRTIO_ADMIN_CAP_ID_ARRAY_SIZE]; }; struct virtio_admin_cmd_cap_get_data { -- 2.45.0 Object create and destroy were implemented specifically for dev parts device objects. Create general purpose APIs for use by upper layer drivers. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit Reviewed-by: Yishai Hadas --- drivers/vfio/pci/virtio/migrate.c | 8 +- drivers/virtio/virtio.c | 59 ++++++++++ drivers/virtio/virtio_pci_modern.c | 175 +++++++++++++++++------------ include/linux/virtio.h | 8 ++ include/linux/virtio_admin.h | 32 ++++++ include/linux/virtio_pci_admin.h | 7 +- 6 files changed, 212 insertions(+), 77 deletions(-) diff --git a/drivers/vfio/pci/virtio/migrate.c b/drivers/vfio/pci/virtio/migrate.c index ba92bb4e9af9..a2aa0e32f593 100644 --- a/drivers/vfio/pci/virtio/migrate.c +++ b/drivers/vfio/pci/virtio/migrate.c @@ -152,15 +152,15 @@ static int virtiovf_pci_alloc_obj_id(struct virtiovf_pci_core_device *virtvdev, u8 type, u32 *obj_id) { - return virtio_pci_admin_obj_create(virtvdev->core_device.pdev, - VIRTIO_RESOURCE_OBJ_DEV_PARTS, type, obj_id); + return virtio_pci_admin_dev_parts_obj_create(virtvdev->core_device.pdev, + type, obj_id); } static void virtiovf_pci_free_obj_id(struct virtiovf_pci_core_device *virtvdev, u32 obj_id) { - virtio_pci_admin_obj_destroy(virtvdev->core_device.pdev, - VIRTIO_RESOURCE_OBJ_DEV_PARTS, obj_id); + virtio_pci_admin_dev_parts_obj_destroy(virtvdev->core_device.pdev, + obj_id); } static struct virtiovf_data_buffer * diff --git a/drivers/virtio/virtio.c b/drivers/virtio/virtio.c index 6bc268c11100..62233ab4501b 100644 --- a/drivers/virtio/virtio.c +++ b/drivers/virtio/virtio.c @@ -788,6 +788,65 @@ int virtio_device_cap_set(struct virtio_device *vdev, } EXPORT_SYMBOL_GPL(virtio_device_cap_set); +/** + * virtio_device_object_create - Create an object on a virtio device + * @vdev: the virtio device + * @obj_type: type of object to create + * @obj_id: ID for the new object + * @obj_specific_data: object-specific data for creation + * @obj_specific_data_size: size of the object-specific data in bytes + * + * Creates a new object on the virtio device with the specified type and ID. + * The object may require object-specific data for proper initialization. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or object creation, or a negative error code on other failures. + */ +int virtio_device_object_create(struct virtio_device *vdev, + u16 obj_type, + u32 obj_id, + const void *obj_specific_data, + size_t obj_specific_data_size) +{ + const struct virtio_admin_ops *admin = vdev->admin_ops; + + if (!admin || !admin->object_create) + return -EOPNOTSUPP; + + /* All users of this interface use the self group with member id 0 */ + return admin->object_create(vdev, obj_type, obj_id, + VIRTIO_ADMIN_GROUP_TYPE_SELF, 0, + obj_specific_data, obj_specific_data_size); +} +EXPORT_SYMBOL_GPL(virtio_device_object_create); + +/** + * virtio_device_object_destroy - Destroy an object on a virtio device + * @vdev: the virtio device + * @obj_type: type of object to destroy + * @obj_id: ID of the object to destroy + * + * Destroys a existing object on the virtio device with the specified type + * and ID. + * + * Return: 0 on success, -EOPNOTSUPP if the device doesn't support admin + * operations or object destruction, or a negative error code on other failures. + */ +int virtio_device_object_destroy(struct virtio_device *vdev, + u16 obj_type, + u32 obj_id) +{ + const struct virtio_admin_ops *admin = vdev->admin_ops; + + if (!admin || !admin->object_destroy) + return -EOPNOTSUPP; + + /* All users of this interface use the self group with member id 0 */ + return admin->object_destroy(vdev, obj_type, obj_id, + VIRTIO_ADMIN_GROUP_TYPE_SELF, 0); +} +EXPORT_SYMBOL_GPL(virtio_device_object_destroy); + static int virtio_init(void) { BUILD_BUG_ON(offsetof(struct virtio_device, features) != diff --git a/drivers/virtio/virtio_pci_modern.c b/drivers/virtio/virtio_pci_modern.c index c8bbd807371d..ef787a6334c8 100644 --- a/drivers/virtio/virtio_pci_modern.c +++ b/drivers/virtio/virtio_pci_modern.c @@ -967,28 +967,61 @@ int virtio_pci_admin_mode_set(struct pci_dev *pdev, u8 flags) } EXPORT_SYMBOL_GPL(virtio_pci_admin_mode_set); -/* - * virtio_pci_admin_obj_create - Creates an object for a given type and operation, - * following the max objects that can be created for that request. - * @pdev: VF pci_dev - * @obj_type: Object type - * @operation_type: Operation type - * @obj_id: Output unique object id +static int vp_modern_admin_cmd_obj_create(struct virtio_device *virtio_dev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id, + const void *obj_specific_data, + size_t obj_specific_data_size) +{ + size_t data_size = sizeof(struct virtio_admin_cmd_resource_obj_create_data); + struct virtio_admin_cmd_resource_obj_create_data *obj_create_data; + struct virtio_admin_cmd cmd = {}; + void *data __free(kfree) = NULL; + struct scatterlist data_sg; + + data_size += (obj_specific_data_size); + data = kzalloc(data_size, GFP_KERNEL); + if (!data) + return -ENOMEM; + + obj_create_data = data; + obj_create_data->hdr.type = cpu_to_le16(obj_type); + obj_create_data->hdr.id = cpu_to_le32(obj_id); + memcpy(obj_create_data->resource_obj_specific_data, obj_specific_data, + obj_specific_data_size); + sg_init_one(&data_sg, data, data_size); + + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_CREATE); + cmd.group_type = cpu_to_le16(group_type); + cmd.group_member_id = cpu_to_le64(group_member_id); + cmd.data_sg = &data_sg; + + return vp_modern_admin_cmd_exec(virtio_dev, &cmd); +} + +/** + * virtio_pci_admin_dev_parts_obj_create - Create a device parts object + * @pdev: VF PCI device + * @operation_type: operation type (GET or SET) + * @obj_id: pointer to store the output unique object ID * - * Note: caller must serialize access for the given device. - * Returns 0 on success, or negative on failure. + * This function creates a device parts object for the specified VF PCI device. + * The object is associated with the SRIOV group and can be used for GET or SET + * operations. The caller must serialize access for the given device. + * + * Return: 0 on success, -ENODEV if the virtio device is not found, + * -EINVAL if the operation type is invalid, -EOPNOTSUPP if device parts + * objects are not supported, or a negative error code on other failures. */ -int virtio_pci_admin_obj_create(struct pci_dev *pdev, u16 obj_type, u8 operation_type, - u32 *obj_id) +int virtio_pci_admin_dev_parts_obj_create(struct pci_dev *pdev, + u8 operation_type, + u32 *obj_id) { struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev); - u16 data_size = sizeof(struct virtio_admin_cmd_resource_obj_create_data); - struct virtio_admin_cmd_resource_obj_create_data *obj_create_data; struct virtio_resource_obj_dev_parts obj_dev_parts = {}; struct virtio_pci_admin_vq *avq; - struct virtio_admin_cmd cmd = {}; - struct scatterlist data_sg; - void *data; int id = -1; int vf_id; int ret; @@ -1000,9 +1033,6 @@ int virtio_pci_admin_obj_create(struct pci_dev *pdev, u16 obj_type, u8 operation if (vf_id < 0) return vf_id; - if (obj_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS) - return -EOPNOTSUPP; - if (operation_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_GET && operation_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS_TYPE_SET) return -EINVAL; @@ -1016,52 +1046,66 @@ int virtio_pci_admin_obj_create(struct pci_dev *pdev, u16 obj_type, u8 operation if (id < 0) return id; - *obj_id = id; - data_size += sizeof(obj_dev_parts); - data = kzalloc(data_size, GFP_KERNEL); - if (!data) { - ret = -ENOMEM; - goto end; - } - - obj_create_data = data; - obj_create_data->hdr.type = cpu_to_le16(obj_type); - obj_create_data->hdr.id = cpu_to_le32(*obj_id); obj_dev_parts.type = operation_type; - memcpy(obj_create_data->resource_obj_specific_data, &obj_dev_parts, - sizeof(obj_dev_parts)); - sg_init_one(&data_sg, data, data_size); - cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_CREATE); - cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); - cmd.group_member_id = cpu_to_le64(vf_id + 1); - cmd.data_sg = &data_sg; - ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + ret = vp_modern_admin_cmd_obj_create(virtio_dev, + VIRTIO_RESOURCE_OBJ_DEV_PARTS, + id, + VIRTIO_ADMIN_GROUP_TYPE_SRIOV, + vf_id + 1, + &obj_dev_parts, + sizeof(obj_dev_parts)); - kfree(data); -end: if (ret) ida_free(&avq->dev_parts_ida, id); + else + *obj_id = id; return ret; } -EXPORT_SYMBOL_GPL(virtio_pci_admin_obj_create); +EXPORT_SYMBOL_GPL(virtio_pci_admin_dev_parts_obj_create); -/* - * virtio_pci_admin_obj_destroy - Destroys an object of a given type and id - * @pdev: VF pci_dev - * @obj_type: Object type - * @id: Object id +static int vp_modern_admin_cmd_obj_destroy(struct virtio_device *virtio_dev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id) +{ + struct virtio_admin_cmd_resource_obj_cmd_hdr *data __free(kfree) = NULL; + struct virtio_admin_cmd cmd = {}; + struct scatterlist data_sg; + + data = kzalloc(sizeof(*data), GFP_KERNEL); + if (!data) + return -ENOMEM; + + data->type = cpu_to_le16(obj_type); + data->id = cpu_to_le32(obj_id); + sg_init_one(&data_sg, data, sizeof(*data)); + cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_DESTROY); + cmd.group_type = cpu_to_le16(group_type); + cmd.group_member_id = cpu_to_le64(group_member_id); + cmd.data_sg = &data_sg; + + return vp_modern_admin_cmd_exec(virtio_dev, &cmd); +} + +/** + * virtio_pci_admin_dev_parts_obj_destroy - Destroy a device parts object + * @pdev: VF PCI device + * @obj_id: ID of the object to destroy * - * Note: caller must serialize access for the given device. - * Returns 0 on success, or negative on failure. + * This function destroys a device parts object with the specified ID for the + * given VF PCI device. The object must have been previously created using + * virtio_pci_admin_dev_parts_obj_create(). The caller must serialize access + * for the given device. + * + * Return: 0 on success, -ENODEV if the virtio device is not found, + * or a negative error code on other failures. */ -int virtio_pci_admin_obj_destroy(struct pci_dev *pdev, u16 obj_type, u32 id) +int virtio_pci_admin_dev_parts_obj_destroy(struct pci_dev *pdev, u32 obj_id) { struct virtio_device *virtio_dev = virtio_pci_vf_get_pf_dev(pdev); - struct virtio_admin_cmd_resource_obj_cmd_hdr *data; struct virtio_pci_device *vp_dev; - struct virtio_admin_cmd cmd = {}; - struct scatterlist data_sg; int vf_id; int ret; @@ -1072,30 +1116,19 @@ int virtio_pci_admin_obj_destroy(struct pci_dev *pdev, u16 obj_type, u32 id) if (vf_id < 0) return vf_id; - if (obj_type != VIRTIO_RESOURCE_OBJ_DEV_PARTS) - return -EINVAL; - - data = kzalloc(sizeof(*data), GFP_KERNEL); - if (!data) - return -ENOMEM; - - data->type = cpu_to_le16(obj_type); - data->id = cpu_to_le32(id); - sg_init_one(&data_sg, data, sizeof(*data)); - cmd.opcode = cpu_to_le16(VIRTIO_ADMIN_CMD_RESOURCE_OBJ_DESTROY); - cmd.group_type = cpu_to_le16(VIRTIO_ADMIN_GROUP_TYPE_SRIOV); - cmd.group_member_id = cpu_to_le64(vf_id + 1); - cmd.data_sg = &data_sg; - ret = vp_modern_admin_cmd_exec(virtio_dev, &cmd); + ret = vp_modern_admin_cmd_obj_destroy(virtio_dev, + VIRTIO_RESOURCE_OBJ_DEV_PARTS, + obj_id, + VIRTIO_ADMIN_GROUP_TYPE_SRIOV, + vf_id + 1); if (!ret) { vp_dev = to_vp_device(virtio_dev); - ida_free(&vp_dev->admin_vq.dev_parts_ida, id); + ida_free(&vp_dev->admin_vq.dev_parts_ida, obj_id); } - kfree(data); return ret; } -EXPORT_SYMBOL_GPL(virtio_pci_admin_obj_destroy); +EXPORT_SYMBOL_GPL(virtio_pci_admin_dev_parts_obj_destroy); /* * virtio_pci_admin_dev_parts_metadata_get - Gets the metadata of the device parts @@ -1289,6 +1322,8 @@ static const struct virtio_admin_ops virtio_pci_admin_ops = { .cap_id_list_query = vp_modern_admin_cap_id_list_query, .cap_get = vp_modern_admin_cmd_cap_get, .cap_set = vp_modern_admin_cmd_cap_set, + .object_create = vp_modern_admin_cmd_obj_create, + .object_destroy = vp_modern_admin_cmd_obj_destroy, }; /* the PCI probing function */ int virtio_pci_modern_probe(struct virtio_pci_device *vp_dev) diff --git a/include/linux/virtio.h b/include/linux/virtio.h index 7ab4ea75ad44..543ba266d24c 100644 --- a/include/linux/virtio.h +++ b/include/linux/virtio.h @@ -209,6 +209,14 @@ int virtio_device_cap_set(struct virtio_device *vdev, u16 id, const void *caps, size_t cap_size); +int virtio_device_object_create(struct virtio_device *virtio_dev, + u16 obj_type, + u32 obj_id, + const void *obj_specific_data, + size_t obj_specific_data_size); +int virtio_device_object_destroy(struct virtio_device *virtio_dev, + u16 obj_type, + u32 obj_id); size_t virtio_max_dma_size(const struct virtio_device *vdev); diff --git a/include/linux/virtio_admin.h b/include/linux/virtio_admin.h index bbf543d20be4..cc6b82461c9f 100644 --- a/include/linux/virtio_admin.h +++ b/include/linux/virtio_admin.h @@ -63,6 +63,38 @@ struct virtio_admin_ops { u16 id, const void *caps, size_t cap_size); + /** + * @object_create: Create a new object of specified type + * @virtio_dev: The virtio device + * @obj_type: Type of object to create + * @obj_id: ID to assign to the created object + * @group_type: Type of group the object belongs to + * @group_member_id: Member ID within the group + * @obj_specific_data: Object-specific data (must be heap allocated) + * @obj_specific_data_size: Size of the object-specific data + * Returns: 0 on success, negative error code on failure + */ + int (*object_create)(struct virtio_device *virtio_dev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id, + const void *obj_specific_data, + size_t obj_specific_data_size); + /** + * @object_destroy: Destroy an existing object + * @virtio_dev: The virtio device + * @obj_type: Type of object to destroy + * @obj_id: ID of the object to destroy + * @group_type: Type of group the object belongs to + * @group_member_id: Member ID within the group + * Returns: 0 on success, negative error code on failure + */ + int (*object_destroy)(struct virtio_device *virtio_dev, + u16 obj_type, + u32 obj_id, + u16 group_type, + u64 group_member_id); }; #endif /* _LINUX_VIRTIO_ADMIN_H */ diff --git a/include/linux/virtio_pci_admin.h b/include/linux/virtio_pci_admin.h index dffc92c17ad2..da9b8495bce4 100644 --- a/include/linux/virtio_pci_admin.h +++ b/include/linux/virtio_pci_admin.h @@ -22,9 +22,10 @@ int virtio_pci_admin_legacy_io_notify_info(struct pci_dev *pdev, bool virtio_pci_admin_has_dev_parts(struct pci_dev *pdev); int virtio_pci_admin_mode_set(struct pci_dev *pdev, u8 mode); -int virtio_pci_admin_obj_create(struct pci_dev *pdev, u16 obj_type, u8 operation_type, - u32 *obj_id); -int virtio_pci_admin_obj_destroy(struct pci_dev *pdev, u16 obj_type, u32 id); +int virtio_pci_admin_dev_parts_obj_create(struct pci_dev *pdev, + u8 operation_type, + u32 *obj_id); +int virtio_pci_admin_dev_parts_obj_destroy(struct pci_dev *pdev, u32 obj_id); int virtio_pci_admin_dev_parts_metadata_get(struct pci_dev *pdev, u16 obj_type, u32 id, u8 metadata_type, u32 *out); int virtio_pci_admin_dev_parts_get(struct pci_dev *pdev, u16 obj_type, u32 id, -- 2.45.0 The flow filter implementaion requires minimal changes to the existing virtio_net implementation. It's cleaner to separate it into another file. In order to do so, move virtio_net.c into the new virtio_net directory, and create a makefile for it. Note the name is changed to virtio_net_main.c, so the module can retain the name virtio_net. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- MAINTAINERS | 2 +- drivers/net/Makefile | 2 +- drivers/net/virtio_net/Makefile | 8 ++++++++ .../net/{virtio_net.c => virtio_net/virtio_net_main.c} | 0 4 files changed, 10 insertions(+), 2 deletions(-) create mode 100644 drivers/net/virtio_net/Makefile rename drivers/net/{virtio_net.c => virtio_net/virtio_net_main.c} (100%) diff --git a/MAINTAINERS b/MAINTAINERS index a8a770714101..09d26c4225a9 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -26685,7 +26685,7 @@ F: Documentation/devicetree/bindings/virtio/ F: Documentation/driver-api/virtio/ F: drivers/block/virtio_blk.c F: drivers/crypto/virtio/ -F: drivers/net/virtio_net.c +F: drivers/net/virtio_net/ F: drivers/vdpa/ F: drivers/virtio/ F: include/linux/vdpa.h diff --git a/drivers/net/Makefile b/drivers/net/Makefile index 73bc63ecd65f..cf28992658a6 100644 --- a/drivers/net/Makefile +++ b/drivers/net/Makefile @@ -33,7 +33,7 @@ obj-$(CONFIG_NET_TEAM) += team/ obj-$(CONFIG_TUN) += tun.o obj-$(CONFIG_TAP) += tap.o obj-$(CONFIG_VETH) += veth.o -obj-$(CONFIG_VIRTIO_NET) += virtio_net.o +obj-$(CONFIG_VIRTIO_NET) += virtio_net/ obj-$(CONFIG_VXLAN) += vxlan/ obj-$(CONFIG_GENEVE) += geneve.o obj-$(CONFIG_BAREUDP) += bareudp.o diff --git a/drivers/net/virtio_net/Makefile b/drivers/net/virtio_net/Makefile new file mode 100644 index 000000000000..c0a4725ddd69 --- /dev/null +++ b/drivers/net/virtio_net/Makefile @@ -0,0 +1,8 @@ +# SPDX-License-Identifier: GPL-2.0-only +# +# Makefile for the VirtIO Net driver +# + +obj-$(CONFIG_VIRTIO_NET) += virtio_net.o + +virtio_net-objs := virtio_net_main.o diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net/virtio_net_main.c similarity index 100% rename from drivers/net/virtio_net.c rename to drivers/net/virtio_net/virtio_net_main.c -- 2.45.0 When probing a virtnet device, attempt to read the flow filter capabilities. In order to use the feature the caps must also be set. For now setting what was read is sufficient. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/Makefile | 2 +- drivers/net/virtio_net/virtio_net_ff.c | 145 +++++++++++++++++++++++ drivers/net/virtio_net/virtio_net_ff.h | 22 ++++ drivers/net/virtio_net/virtio_net_main.c | 7 ++ include/linux/virtio_admin.h | 1 + include/uapi/linux/virtio_net_ff.h | 55 +++++++++ 6 files changed, 231 insertions(+), 1 deletion(-) create mode 100644 drivers/net/virtio_net/virtio_net_ff.c create mode 100644 drivers/net/virtio_net/virtio_net_ff.h create mode 100644 include/uapi/linux/virtio_net_ff.h diff --git a/drivers/net/virtio_net/Makefile b/drivers/net/virtio_net/Makefile index c0a4725ddd69..c41a587ffb5b 100644 --- a/drivers/net/virtio_net/Makefile +++ b/drivers/net/virtio_net/Makefile @@ -5,4 +5,4 @@ obj-$(CONFIG_VIRTIO_NET) += virtio_net.o -virtio_net-objs := virtio_net_main.o +virtio_net-objs := virtio_net_main.o virtio_net_ff.o diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c new file mode 100644 index 000000000000..61cb45331c97 --- /dev/null +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -0,0 +1,145 @@ +// SPDX-License-Identifier: GPL-2.0-only + +#include +#include +#include +#include +#include "virtio_net_ff.h" + +static size_t get_mask_size(u16 type) +{ + switch (type) { + case VIRTIO_NET_FF_MASK_TYPE_ETH: + return sizeof(struct ethhdr); + case VIRTIO_NET_FF_MASK_TYPE_IPV4: + return sizeof(struct iphdr); + case VIRTIO_NET_FF_MASK_TYPE_IPV6: + return sizeof(struct ipv6hdr); + case VIRTIO_NET_FF_MASK_TYPE_TCP: + return sizeof(struct tcphdr); + case VIRTIO_NET_FF_MASK_TYPE_UDP: + return sizeof(struct udphdr); + } + + return 0; +} + +void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev) +{ + struct virtio_admin_cmd_query_cap_id_result *cap_id_list __free(kfree) = NULL; + size_t ff_mask_size = sizeof(struct virtio_net_ff_cap_mask_data) + + sizeof(struct virtio_net_ff_selector) * + VIRTIO_NET_FF_MASK_TYPE_MAX; + struct virtio_net_ff_selector *sel; + int err; + int i; + + cap_id_list = kzalloc(sizeof(*cap_id_list), GFP_KERNEL); + if (!cap_id_list) + return; + + err = virtio_device_cap_id_list_query(vdev, cap_id_list); + if (err) + return; + + if (!(VIRTIO_CAP_IN_LIST(cap_id_list, + VIRTIO_NET_FF_RESOURCE_CAP) && + VIRTIO_CAP_IN_LIST(cap_id_list, + VIRTIO_NET_FF_SELECTOR_CAP) && + VIRTIO_CAP_IN_LIST(cap_id_list, + VIRTIO_NET_FF_ACTION_CAP))) + return; + + ff->ff_caps = kzalloc(sizeof(*ff->ff_caps), GFP_KERNEL); + if (!ff->ff_caps) + return; + + err = virtio_device_cap_get(vdev, + VIRTIO_NET_FF_RESOURCE_CAP, + ff->ff_caps, + sizeof(*ff->ff_caps)); + + if (err) + goto err_ff; + + /* VIRTIO_NET_FF_MASK_TYPE start at 1 */ + for (i = 1; i <= VIRTIO_NET_FF_MASK_TYPE_MAX; i++) + ff_mask_size += get_mask_size(i); + + ff->ff_mask = kzalloc(ff_mask_size, GFP_KERNEL); + if (!ff->ff_mask) + goto err_ff; + + err = virtio_device_cap_get(vdev, + VIRTIO_NET_FF_SELECTOR_CAP, + ff->ff_mask, + ff_mask_size); + + if (err) + goto err_ff_mask; + + ff->ff_actions = kzalloc(sizeof(*ff->ff_actions) + + VIRTIO_NET_FF_ACTION_MAX, + GFP_KERNEL); + if (!ff->ff_actions) + goto err_ff_mask; + + err = virtio_device_cap_get(vdev, + VIRTIO_NET_FF_ACTION_CAP, + ff->ff_actions, + sizeof(*ff->ff_actions) + VIRTIO_NET_FF_ACTION_MAX); + + if (err) + goto err_ff_action; + + err = virtio_device_cap_set(vdev, + VIRTIO_NET_FF_RESOURCE_CAP, + ff->ff_caps, + sizeof(*ff->ff_caps)); + if (err) + goto err_ff_action; + + ff_mask_size = sizeof(struct virtio_net_ff_cap_mask_data); + sel = &ff->ff_mask->selectors[0]; + + for (int i = 0; i < ff->ff_mask->count; i++) { + ff_mask_size += sizeof(struct virtio_net_ff_selector) + sel->length; + sel = (struct virtio_net_ff_selector *)((u8 *)sel + sizeof(*sel) + sel->length); + } + + err = virtio_device_cap_set(vdev, + VIRTIO_NET_FF_SELECTOR_CAP, + ff->ff_mask, + ff_mask_size); + if (err) + goto err_ff_action; + + err = virtio_device_cap_set(vdev, + VIRTIO_NET_FF_ACTION_CAP, + ff->ff_actions, + sizeof(*ff->ff_actions) + VIRTIO_NET_FF_ACTION_MAX); + if (err) + goto err_ff_action; + + ff->vdev = vdev; + ff->ff_supported = true; + + return; + +err_ff_action: + kfree(ff->ff_actions); +err_ff_mask: + kfree(ff->ff_mask); +err_ff: + kfree(ff->ff_caps); +} + +void virtnet_ff_cleanup(struct virtnet_ff *ff) +{ + if (!ff->ff_supported) + return; + + kfree(ff->ff_actions); + kfree(ff->ff_mask); + kfree(ff->ff_caps); +} diff --git a/drivers/net/virtio_net/virtio_net_ff.h b/drivers/net/virtio_net/virtio_net_ff.h new file mode 100644 index 000000000000..4aac0bd08b63 --- /dev/null +++ b/drivers/net/virtio_net/virtio_net_ff.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0-only + * + * Header file for virtio_net flow filters + */ +#include + +#ifndef _VIRTIO_NET_FF_H +#define _VIRTIO_NET_FF_H + +struct virtnet_ff { + struct virtio_device *vdev; + bool ff_supported; + struct virtio_net_ff_cap_data *ff_caps; + struct virtio_net_ff_cap_mask_data *ff_mask; + struct virtio_net_ff_actions *ff_actions; +}; + +void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev); + +void virtnet_ff_cleanup(struct virtnet_ff *ff); + +#endif /* _VIRTIO_NET_FF_H */ diff --git a/drivers/net/virtio_net/virtio_net_main.c b/drivers/net/virtio_net/virtio_net_main.c index 7da5a37917e9..ebf3e5db0d64 100644 --- a/drivers/net/virtio_net/virtio_net_main.c +++ b/drivers/net/virtio_net/virtio_net_main.c @@ -26,6 +26,7 @@ #include #include #include +#include "virtio_net_ff.h" static int napi_weight = NAPI_POLL_WEIGHT; module_param(napi_weight, int, 0444); @@ -493,6 +494,8 @@ struct virtnet_info { struct failover *failover; u64 device_stats_cap; + + struct virtnet_ff ff; }; struct padded_vnet_hdr { @@ -7116,6 +7119,8 @@ static int virtnet_probe(struct virtio_device *vdev) } vi->guest_offloads_capable = vi->guest_offloads; + virtnet_ff_init(&vi->ff, vi->vdev); + rtnl_unlock(); err = virtnet_cpu_notif_add(vi); @@ -7131,6 +7136,7 @@ static int virtnet_probe(struct virtio_device *vdev) free_unregister_netdev: unregister_netdev(dev); + virtnet_ff_cleanup(&vi->ff); free_failover: net_failover_destroy(vi->failover); free_vqs: @@ -7180,6 +7186,7 @@ static void virtnet_remove(struct virtio_device *vdev) virtnet_free_irq_moder(vi); unregister_netdev(vi->dev); + virtnet_ff_cleanup(&vi->ff); net_failover_destroy(vi->failover); diff --git a/include/linux/virtio_admin.h b/include/linux/virtio_admin.h index cc6b82461c9f..f8f1369d1175 100644 --- a/include/linux/virtio_admin.h +++ b/include/linux/virtio_admin.h @@ -3,6 +3,7 @@ * Header file for virtio admin operations */ #include +#include #ifndef _LINUX_VIRTIO_ADMIN_H #define _LINUX_VIRTIO_ADMIN_H diff --git a/include/uapi/linux/virtio_net_ff.h b/include/uapi/linux/virtio_net_ff.h new file mode 100644 index 000000000000..a35533bf8377 --- /dev/null +++ b/include/uapi/linux/virtio_net_ff.h @@ -0,0 +1,55 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note + * + * Header file for virtio_net flow filters + */ +#ifndef _LINUX_VIRTIO_NET_FF_H +#define _LINUX_VIRTIO_NET_FF_H + +#include +#include + +#define VIRTIO_NET_FF_RESOURCE_CAP 0x800 +#define VIRTIO_NET_FF_SELECTOR_CAP 0x801 +#define VIRTIO_NET_FF_ACTION_CAP 0x802 + +struct virtio_net_ff_cap_data { + __le32 groups_limit; + __le32 classifiers_limit; + __le32 rules_limit; + __le32 rules_per_group_limit; + __u8 last_rule_priority; + __u8 selectors_per_classifier_limit; +}; + +struct virtio_net_ff_selector { + __u8 type; + __u8 flags; + __u8 reserved[2]; + __u8 length; + __u8 reserved1[3]; + __u8 mask[]; +}; + +#define VIRTIO_NET_FF_MASK_TYPE_ETH 1 +#define VIRTIO_NET_FF_MASK_TYPE_IPV4 2 +#define VIRTIO_NET_FF_MASK_TYPE_IPV6 3 +#define VIRTIO_NET_FF_MASK_TYPE_TCP 4 +#define VIRTIO_NET_FF_MASK_TYPE_UDP 5 +#define VIRTIO_NET_FF_MASK_TYPE_MAX VIRTIO_NET_FF_MASK_TYPE_UDP + +struct virtio_net_ff_cap_mask_data { + __u8 count; + __u8 reserved[7]; + struct virtio_net_ff_selector selectors[]; +}; +#define VIRTIO_NET_FF_MASK_F_PARTIAL_MASK (1 << 0) + +#define VIRTIO_NET_FF_ACTION_DROP 1 +#define VIRTIO_NET_FF_ACTION_RX_VQ 2 +#define VIRTIO_NET_FF_ACTION_MAX VIRTIO_NET_FF_ACTION_RX_VQ +struct virtio_net_ff_actions { + __u8 count; + __u8 reserved[7]; + __u8 actions[]; +}; +#endif -- 2.45.0 All ethtool steering rules will go in one group, create it during initialization. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/virtio_net_ff.c | 25 +++++++++++++++++++++++++ include/uapi/linux/virtio_net_ff.h | 7 +++++++ 2 files changed, 32 insertions(+) diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c index 61cb45331c97..0036c2db9f77 100644 --- a/drivers/net/virtio_net/virtio_net_ff.c +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -6,6 +6,9 @@ #include #include "virtio_net_ff.h" +#define VIRTNET_FF_ETHTOOL_GROUP_PRIORITY 1 +#define VIRTNET_FF_MAX_GROUPS 1 + static size_t get_mask_size(u16 type) { switch (type) { @@ -30,6 +33,7 @@ void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev) size_t ff_mask_size = sizeof(struct virtio_net_ff_cap_mask_data) + sizeof(struct virtio_net_ff_selector) * VIRTIO_NET_FF_MASK_TYPE_MAX; + struct virtio_net_resource_obj_ff_group ethtool_group = {}; struct virtio_net_ff_selector *sel; int err; int i; @@ -92,6 +96,12 @@ void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev) if (err) goto err_ff_action; + if (le32_to_cpu(ff->ff_caps->groups_limit) < VIRTNET_FF_MAX_GROUPS) { + err = -ENOSPC; + goto err_ff_action; + } + ff->ff_caps->groups_limit = cpu_to_le32(VIRTNET_FF_MAX_GROUPS); + err = virtio_device_cap_set(vdev, VIRTIO_NET_FF_RESOURCE_CAP, ff->ff_caps, @@ -121,6 +131,17 @@ void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev) if (err) goto err_ff_action; + ethtool_group.group_priority = cpu_to_le16(VIRTNET_FF_ETHTOOL_GROUP_PRIORITY); + + /* Use priority for the object ID. */ + err = virtio_device_object_create(vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_GROUP, + VIRTNET_FF_ETHTOOL_GROUP_PRIORITY, + ðtool_group, + sizeof(ethtool_group)); + if (err) + goto err_ff_action; + ff->vdev = vdev; ff->ff_supported = true; @@ -139,6 +160,10 @@ void virtnet_ff_cleanup(struct virtnet_ff *ff) if (!ff->ff_supported) return; + virtio_device_object_destroy(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_GROUP, + VIRTNET_FF_ETHTOOL_GROUP_PRIORITY); + kfree(ff->ff_actions); kfree(ff->ff_mask); kfree(ff->ff_caps); diff --git a/include/uapi/linux/virtio_net_ff.h b/include/uapi/linux/virtio_net_ff.h index a35533bf8377..662693e1fefd 100644 --- a/include/uapi/linux/virtio_net_ff.h +++ b/include/uapi/linux/virtio_net_ff.h @@ -12,6 +12,8 @@ #define VIRTIO_NET_FF_SELECTOR_CAP 0x801 #define VIRTIO_NET_FF_ACTION_CAP 0x802 +#define VIRTIO_NET_RESOURCE_OBJ_FF_GROUP 0x0200 + struct virtio_net_ff_cap_data { __le32 groups_limit; __le32 classifiers_limit; @@ -52,4 +54,9 @@ struct virtio_net_ff_actions { __u8 reserved[7]; __u8 actions[]; }; + +struct virtio_net_resource_obj_ff_group { + __le16 group_priority; +}; + #endif -- 2.45.0 Filtering a flow requires a classifier to match the packets, and a rule to filter on the matches. A classifier consists of one or more selectors. There is one selector per header type. A selector must only use fields set in the selector capabality. If partial matching is supported, the classifier mask for a particular field can be a subset of the mask for that field in the capability. The rule consists of a priority, an action and a key. The key is a byte array containing headers corresponding to the selectors in the classifier. This patch implements ethtool rules for ethernet headers. Example: $ ethtool -U ens9 flow-type ether dst 08:11:22:33:44:54 action 30 Added rule with ID 1 The rule in the example directs received packets with the specified destination MAC address to rq 30. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/virtio_net_ff.c | 423 +++++++++++++++++++++++ drivers/net/virtio_net/virtio_net_ff.h | 14 + drivers/net/virtio_net/virtio_net_main.c | 16 + include/uapi/linux/virtio_net_ff.h | 20 ++ 4 files changed, 473 insertions(+) diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c index 0036c2db9f77..e3c34bfd1d55 100644 --- a/drivers/net/virtio_net/virtio_net_ff.c +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -9,6 +9,418 @@ #define VIRTNET_FF_ETHTOOL_GROUP_PRIORITY 1 #define VIRTNET_FF_MAX_GROUPS 1 +struct virtnet_ethtool_rule { + struct ethtool_rx_flow_spec flow_spec; + u32 classifier_id; +}; + +/* New fields must be added before the classifier struct */ +struct virtnet_classifier { + size_t size; + u32 id; + struct virtio_net_resource_obj_ff_classifier classifier; +}; + +static bool check_mask_vs_cap(const void *m, const void *c, + u16 len, bool partial) +{ + const u8 *mask = m; + const u8 *cap = c; + int i; + + for (i = 0; i < len; i++) { + if (partial && ((mask[i] & cap[i]) != mask[i])) + return false; + if (!partial && mask[i] != cap[i]) + return false; + } + + return true; +} + +static +struct virtio_net_ff_selector *get_selector_cap(const struct virtnet_ff *ff, + u8 selector_type) +{ + struct virtio_net_ff_selector *sel; + u8 *buf; + int i; + + buf = (u8 *)&ff->ff_mask->selectors; + sel = (struct virtio_net_ff_selector *)buf; + + for (i = 0; i < ff->ff_mask->count; i++) { + if (sel->type == selector_type) + return sel; + + buf += sizeof(struct virtio_net_ff_selector) + sel->length; + sel = (struct virtio_net_ff_selector *)buf; + } + + return NULL; +} + +static bool validate_eth_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct ethhdr *cap, *mask; + struct ethhdr zeros = {0}; + + cap = (struct ethhdr *)&sel_cap->mask; + mask = (struct ethhdr *)&sel->mask; + + if (memcmp(&zeros.h_dest, mask->h_dest, sizeof(zeros.h_dest)) && + !check_mask_vs_cap(mask->h_dest, cap->h_dest, + sizeof(mask->h_dest), partial_mask)) + return false; + + if (memcmp(&zeros.h_source, mask->h_source, sizeof(zeros.h_source)) && + !check_mask_vs_cap(mask->h_source, cap->h_source, + sizeof(mask->h_source), partial_mask)) + return false; + + if (mask->h_proto && + !check_mask_vs_cap(&mask->h_proto, &cap->h_proto, + sizeof(__be16), partial_mask)) + return false; + + return true; +} + +static bool validate_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel) +{ + struct virtio_net_ff_selector *sel_cap = get_selector_cap(ff, sel->type); + + if (!sel_cap) + return false; + + switch (sel->type) { + case VIRTIO_NET_FF_MASK_TYPE_ETH: + return validate_eth_mask(ff, sel, sel_cap); + } + + return false; +} + +static int setup_classifier(struct virtnet_ff *ff, struct virtnet_classifier *c) +{ + int err; + + err = xa_alloc(&ff->classifiers, &c->id, c, + XA_LIMIT(0, le32_to_cpu(ff->ff_caps->classifiers_limit) - 1), + GFP_KERNEL); + if (err) + return err; + + err = virtio_device_object_create(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER, + c->id, + &c->classifier, + c->size); + if (err) + goto err_xarray; + + return 0; + +err_xarray: + xa_erase(&ff->classifiers, c->id); + + return err; +} + +static void destroy_classifier(struct virtnet_ff *ff, + u32 classifier_id) +{ + struct virtnet_classifier *c; + + c = xa_load(&ff->classifiers, classifier_id); + if (c) { + virtio_device_object_destroy(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER, + c->id); + + xa_erase(&ff->classifiers, c->id); + kfree(c); + } +} + +static void destroy_ethtool_rule(struct virtnet_ff *ff, + struct virtnet_ethtool_rule *eth_rule) +{ + ff->ethtool.num_rules--; + + virtio_device_object_destroy(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_RULE, + eth_rule->flow_spec.location); + + xa_erase(&ff->ethtool.rules, eth_rule->flow_spec.location); + destroy_classifier(ff, eth_rule->classifier_id); + kfree(eth_rule); +} + +static int insert_rule(struct virtnet_ff *ff, + struct virtnet_ethtool_rule *eth_rule, + u32 classifier_id, + const u8 *key, + size_t key_size) +{ + struct ethtool_rx_flow_spec *fs = ð_rule->flow_spec; + struct virtio_net_resource_obj_ff_rule *ff_rule; + int err; + + ff_rule = kzalloc(sizeof(*ff_rule) + key_size, GFP_KERNEL); + if (!ff_rule) { + err = -ENOMEM; + goto err_eth_rule; + } + /* + * Intentionally leave the priority as 0. All rules have the same + * priority. + */ + ff_rule->group_id = cpu_to_le32(VIRTNET_FF_ETHTOOL_GROUP_PRIORITY); + ff_rule->classifier_id = cpu_to_le32(classifier_id); + ff_rule->key_length = (u8)key_size; + ff_rule->action = fs->ring_cookie == RX_CLS_FLOW_DISC ? + VIRTIO_NET_FF_ACTION_DROP : + VIRTIO_NET_FF_ACTION_RX_VQ; + ff_rule->vq_index = fs->ring_cookie != RX_CLS_FLOW_DISC ? + cpu_to_le16(fs->ring_cookie) : 0; + memcpy(&ff_rule->keys, key, key_size); + + err = virtio_device_object_create(ff->vdev, + VIRTIO_NET_RESOURCE_OBJ_FF_RULE, + fs->location, + ff_rule, + sizeof(*ff_rule) + key_size); + if (err) + goto err_ff_rule; + + eth_rule->classifier_id = classifier_id; + ff->ethtool.num_rules++; + kfree(ff_rule); + + return 0; + +err_ff_rule: + kfree(ff_rule); +err_eth_rule: + xa_erase(&ff->ethtool.rules, eth_rule->flow_spec.location); + kfree(eth_rule); + + return err; +} + +static u32 flow_type_mask(u32 flow_type) +{ + return flow_type & ~(FLOW_EXT | FLOW_MAC_EXT | FLOW_RSS); +} + +static bool supported_flow_type(const struct ethtool_rx_flow_spec *fs) +{ + switch (fs->flow_type) { + case ETHER_FLOW: + return true; + } + + return false; +} + +static int validate_flow_input(struct virtnet_ff *ff, + const struct ethtool_rx_flow_spec *fs, + u16 curr_queue_pairs) +{ + /* Force users to use RX_CLS_LOC_ANY - don't allow specific locations */ + if (fs->location != RX_CLS_LOC_ANY) + return -EOPNOTSUPP; + + if (fs->ring_cookie != RX_CLS_FLOW_DISC && + fs->ring_cookie >= curr_queue_pairs) + return -EINVAL; + + if (fs->flow_type != flow_type_mask(fs->flow_type)) + return -EOPNOTSUPP; + + if (!supported_flow_type(fs)) + return -EOPNOTSUPP; + + return 0; +} + +static void calculate_flow_sizes(struct ethtool_rx_flow_spec *fs, + size_t *key_size, size_t *classifier_size, + int *num_hdrs) +{ + *num_hdrs = 1; + *key_size = sizeof(struct ethhdr); + /* + * The classifier size is the size of the classifier header, a selector + * header for each type of header in the match criteria, and each header + * providing the mask for matching against. + */ + *classifier_size = *key_size + + sizeof(struct virtio_net_resource_obj_ff_classifier) + + sizeof(struct virtio_net_ff_selector) * (*num_hdrs); +} + +static void setup_eth_hdr_key_mask(struct virtio_net_ff_selector *selector, + u8 *key, + const struct ethtool_rx_flow_spec *fs) +{ + struct ethhdr *eth_m = (struct ethhdr *)&selector->mask; + struct ethhdr *eth_k = (struct ethhdr *)key; + + selector->type = VIRTIO_NET_FF_MASK_TYPE_ETH; + selector->length = sizeof(struct ethhdr); + + memcpy(eth_m, &fs->m_u.ether_spec, sizeof(*eth_m)); + memcpy(eth_k, &fs->h_u.ether_spec, sizeof(*eth_k)); +} + +static int +validate_classifier_selectors(struct virtnet_ff *ff, + struct virtio_net_resource_obj_ff_classifier *classifier, + int num_hdrs) +{ + struct virtio_net_ff_selector *selector = classifier->selectors; + + for (int i = 0; i < num_hdrs; i++) { + if (!validate_mask(ff, selector)) + return -EINVAL; + + selector = (struct virtio_net_ff_selector *)(((u8 *)selector) + + sizeof(*selector) + selector->length); + } + + return 0; +} + +static int build_and_insert(struct virtnet_ff *ff, + struct virtnet_ethtool_rule *eth_rule) +{ + struct virtio_net_resource_obj_ff_classifier *classifier; + struct ethtool_rx_flow_spec *fs = ð_rule->flow_spec; + struct virtio_net_ff_selector *selector; + struct virtnet_classifier *c; + size_t classifier_size; + size_t key_size; + int num_hdrs; + u8 *key; + int err; + + calculate_flow_sizes(fs, &key_size, &classifier_size, &num_hdrs); + + key = kzalloc(key_size, GFP_KERNEL); + if (!key) + return -ENOMEM; + + /* + * virtio_net_ff_obj_ff_classifier is already included in the + * classifier_size. + */ + c = kzalloc(classifier_size + + sizeof(struct virtnet_classifier) - + sizeof(struct virtio_net_resource_obj_ff_classifier), + GFP_KERNEL); + if (!c) { + kfree(key); + return -ENOMEM; + } + + c->size = classifier_size; + classifier = &c->classifier; + classifier->count = num_hdrs; + selector = &classifier->selectors[0]; + + setup_eth_hdr_key_mask(selector, key, fs); + + err = validate_classifier_selectors(ff, classifier, num_hdrs); + if (err) + goto err_key; + + err = setup_classifier(ff, c); + if (err) + goto err_classifier; + + err = insert_rule(ff, eth_rule, c->id, key, key_size); + if (err) { + destroy_classifier(ff, c->id); + goto err_key; + } + + return 0; + +err_classifier: + kfree(c); +err_key: + kfree(key); + + return err; +} + +int virtnet_ethtool_flow_insert(struct virtnet_ff *ff, + struct ethtool_rx_flow_spec *fs, + u16 curr_queue_pairs) +{ + struct virtnet_ethtool_rule *eth_rule; + int err; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + err = validate_flow_input(ff, fs, curr_queue_pairs); + if (err) + return err; + + eth_rule = kzalloc(sizeof(*eth_rule), GFP_KERNEL); + if (!eth_rule) + return -ENOMEM; + + err = xa_alloc(&ff->ethtool.rules, &fs->location, eth_rule, + XA_LIMIT(0, le32_to_cpu(ff->ff_caps->rules_limit) - 1), + GFP_KERNEL); + if (err) + goto err_rule; + + eth_rule->flow_spec = *fs; + + err = build_and_insert(ff, eth_rule); + if (err) + goto err_xa; + + return err; + +err_xa: + xa_erase(&ff->ethtool.rules, eth_rule->flow_spec.location); + +err_rule: + fs->location = RX_CLS_LOC_ANY; + kfree(eth_rule); + + return err; +} + +int virtnet_ethtool_flow_remove(struct virtnet_ff *ff, int location) +{ + struct virtnet_ethtool_rule *eth_rule; + int err = 0; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + eth_rule = xa_load(&ff->ethtool.rules, location); + if (!eth_rule) { + err = -ENOENT; + goto out; + } + + destroy_ethtool_rule(ff, eth_rule); +out: + return err; +} + static size_t get_mask_size(u16 type) { switch (type) { @@ -142,6 +554,8 @@ void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev) if (err) goto err_ff_action; + xa_init_flags(&ff->classifiers, XA_FLAGS_ALLOC); + xa_init_flags(&ff->ethtool.rules, XA_FLAGS_ALLOC); ff->vdev = vdev; ff->ff_supported = true; @@ -157,9 +571,18 @@ void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev) void virtnet_ff_cleanup(struct virtnet_ff *ff) { + struct virtnet_ethtool_rule *eth_rule; + unsigned long i; + if (!ff->ff_supported) return; + xa_for_each(&ff->ethtool.rules, i, eth_rule) + destroy_ethtool_rule(ff, eth_rule); + + xa_destroy(&ff->ethtool.rules); + xa_destroy(&ff->classifiers); + virtio_device_object_destroy(ff->vdev, VIRTIO_NET_RESOURCE_OBJ_FF_GROUP, VIRTNET_FF_ETHTOOL_GROUP_PRIORITY); diff --git a/drivers/net/virtio_net/virtio_net_ff.h b/drivers/net/virtio_net/virtio_net_ff.h index 4aac0bd08b63..94b575fbd9ed 100644 --- a/drivers/net/virtio_net/virtio_net_ff.h +++ b/drivers/net/virtio_net/virtio_net_ff.h @@ -3,20 +3,34 @@ * Header file for virtio_net flow filters */ #include +#include #ifndef _VIRTIO_NET_FF_H #define _VIRTIO_NET_FF_H +struct virtnet_ethtool_ff { + struct xarray rules; + int num_rules; +}; + struct virtnet_ff { struct virtio_device *vdev; bool ff_supported; struct virtio_net_ff_cap_data *ff_caps; struct virtio_net_ff_cap_mask_data *ff_mask; struct virtio_net_ff_actions *ff_actions; + struct xarray classifiers; + int num_classifiers; + struct virtnet_ethtool_ff ethtool; }; void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev); void virtnet_ff_cleanup(struct virtnet_ff *ff); +int virtnet_ethtool_flow_insert(struct virtnet_ff *ff, + struct ethtool_rx_flow_spec *fs, + u16 curr_queue_pairs); +int virtnet_ethtool_flow_remove(struct virtnet_ff *ff, int location); + #endif /* _VIRTIO_NET_FF_H */ diff --git a/drivers/net/virtio_net/virtio_net_main.c b/drivers/net/virtio_net/virtio_net_main.c index ebf3e5db0d64..808988cdf265 100644 --- a/drivers/net/virtio_net/virtio_net_main.c +++ b/drivers/net/virtio_net/virtio_net_main.c @@ -5619,6 +5619,21 @@ static u32 virtnet_get_rx_ring_count(struct net_device *dev) return vi->curr_queue_pairs; } +static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) +{ + struct virtnet_info *vi = netdev_priv(dev); + + switch (info->cmd) { + case ETHTOOL_SRXCLSRLINS: + return virtnet_ethtool_flow_insert(&vi->ff, &info->fs, + vi->curr_queue_pairs); + case ETHTOOL_SRXCLSRLDEL: + return virtnet_ethtool_flow_remove(&vi->ff, info->fs.location); + } + + return -EOPNOTSUPP; +} + static const struct ethtool_ops virtnet_ethtool_ops = { .supported_coalesce_params = ETHTOOL_COALESCE_MAX_FRAMES | ETHTOOL_COALESCE_USECS | ETHTOOL_COALESCE_USE_ADAPTIVE_RX, @@ -5645,6 +5660,7 @@ static const struct ethtool_ops virtnet_ethtool_ops = { .get_rxfh_fields = virtnet_get_hashflow, .set_rxfh_fields = virtnet_set_hashflow, .get_rx_ring_count = virtnet_get_rx_ring_count, + .set_rxnfc = virtnet_set_rxnfc, }; static void virtnet_get_queue_stats_rx(struct net_device *dev, int i, diff --git a/include/uapi/linux/virtio_net_ff.h b/include/uapi/linux/virtio_net_ff.h index 662693e1fefd..f258964322f4 100644 --- a/include/uapi/linux/virtio_net_ff.h +++ b/include/uapi/linux/virtio_net_ff.h @@ -13,6 +13,8 @@ #define VIRTIO_NET_FF_ACTION_CAP 0x802 #define VIRTIO_NET_RESOURCE_OBJ_FF_GROUP 0x0200 +#define VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER 0x0201 +#define VIRTIO_NET_RESOURCE_OBJ_FF_RULE 0x0202 struct virtio_net_ff_cap_data { __le32 groups_limit; @@ -59,4 +61,22 @@ struct virtio_net_resource_obj_ff_group { __le16 group_priority; }; +struct virtio_net_resource_obj_ff_classifier { + __u8 count; + __u8 reserved[7]; + struct virtio_net_ff_selector selectors[]; +}; + +struct virtio_net_resource_obj_ff_rule { + __le32 group_id; + __le32 classifier_id; + __u8 rule_priority; + __u8 key_length; /* length of key in bytes */ + __u8 action; + __u8 reserved; + __le16 vq_index; + __u8 reserved1[2]; + __u8 keys[]; +}; + #endif -- 2.45.0 Classifiers can be used by more than one rule. If there is an exisitng classifier, use it instead of creating a new one. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/virtio_net_ff.c | 39 ++++++++++++++++++-------- 1 file changed, 27 insertions(+), 12 deletions(-) diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c index e3c34bfd1d55..30c5ded57ab5 100644 --- a/drivers/net/virtio_net/virtio_net_ff.c +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -17,6 +17,7 @@ struct virtnet_ethtool_rule { /* New fields must be added before the classifier struct */ struct virtnet_classifier { size_t size; + refcount_t refcount; u32 id; struct virtio_net_resource_obj_ff_classifier classifier; }; @@ -105,11 +106,24 @@ static bool validate_mask(const struct virtnet_ff *ff, return false; } -static int setup_classifier(struct virtnet_ff *ff, struct virtnet_classifier *c) +static int setup_classifier(struct virtnet_ff *ff, + struct virtnet_classifier **c) { + struct virtnet_classifier *tmp; + unsigned long i; int err; - err = xa_alloc(&ff->classifiers, &c->id, c, + xa_for_each(&ff->classifiers, i, tmp) { + if ((*c)->size == tmp->size && + !memcmp(&tmp->classifier, &(*c)->classifier, tmp->size)) { + refcount_inc(&tmp->refcount); + kfree(*c); + *c = tmp; + goto out; + } + } + + err = xa_alloc(&ff->classifiers, &(*c)->id, *c, XA_LIMIT(0, le32_to_cpu(ff->ff_caps->classifiers_limit) - 1), GFP_KERNEL); if (err) @@ -117,27 +131,28 @@ static int setup_classifier(struct virtnet_ff *ff, struct virtnet_classifier *c) err = virtio_device_object_create(ff->vdev, VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER, - c->id, - &c->classifier, - c->size); + (*c)->id, + &(*c)->classifier, + (*c)->size); if (err) goto err_xarray; + refcount_set(&(*c)->refcount, 1); +out: return 0; err_xarray: - xa_erase(&ff->classifiers, c->id); + xa_erase(&ff->classifiers, (*c)->id); return err; } -static void destroy_classifier(struct virtnet_ff *ff, - u32 classifier_id) +static void try_destroy_classifier(struct virtnet_ff *ff, u32 classifier_id) { struct virtnet_classifier *c; c = xa_load(&ff->classifiers, classifier_id); - if (c) { + if (c && refcount_dec_and_test(&c->refcount)) { virtio_device_object_destroy(ff->vdev, VIRTIO_NET_RESOURCE_OBJ_FF_CLASSIFIER, c->id); @@ -157,7 +172,7 @@ static void destroy_ethtool_rule(struct virtnet_ff *ff, eth_rule->flow_spec.location); xa_erase(&ff->ethtool.rules, eth_rule->flow_spec.location); - destroy_classifier(ff, eth_rule->classifier_id); + try_destroy_classifier(ff, eth_rule->classifier_id); kfree(eth_rule); } @@ -340,13 +355,13 @@ static int build_and_insert(struct virtnet_ff *ff, if (err) goto err_key; - err = setup_classifier(ff, c); + err = setup_classifier(ff, &c); if (err) goto err_classifier; err = insert_rule(ff, eth_rule, c->id, key, key_size); if (err) { - destroy_classifier(ff, c->id); + try_destroy_classifier(ff, c->id); goto err_key; } -- 2.45.0 Add support for IP_USER type rules from ethtool. Example: $ ethtool -U ens9 flow-type ip4 src-ip 192.168.51.101 action -1 Added rule with ID 1 The example rule will drop packets with the source IP specified. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/virtio_net_ff.c | 127 +++++++++++++++++++++++-- 1 file changed, 119 insertions(+), 8 deletions(-) diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c index 30c5ded57ab5..0374676d1342 100644 --- a/drivers/net/virtio_net/virtio_net_ff.c +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -90,6 +90,34 @@ static bool validate_eth_mask(const struct virtnet_ff *ff, return true; } +static bool validate_ip4_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct iphdr *cap, *mask; + + cap = (struct iphdr *)&sel_cap->mask; + mask = (struct iphdr *)&sel->mask; + + if (mask->saddr && + !check_mask_vs_cap(&mask->saddr, &cap->saddr, + sizeof(__be32), partial_mask)) + return false; + + if (mask->daddr && + !check_mask_vs_cap(&mask->daddr, &cap->daddr, + sizeof(__be32), partial_mask)) + return false; + + if (mask->protocol && + !check_mask_vs_cap(&mask->protocol, &cap->protocol, + sizeof(u8), partial_mask)) + return false; + + return true; +} + static bool validate_mask(const struct virtnet_ff *ff, const struct virtio_net_ff_selector *sel) { @@ -101,11 +129,36 @@ static bool validate_mask(const struct virtnet_ff *ff, switch (sel->type) { case VIRTIO_NET_FF_MASK_TYPE_ETH: return validate_eth_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_IPV4: + return validate_ip4_mask(ff, sel, sel_cap); } return false; } +static void parse_ip4(struct iphdr *mask, struct iphdr *key, + const struct ethtool_rx_flow_spec *fs) +{ + const struct ethtool_usrip4_spec *l3_mask = &fs->m_u.usr_ip4_spec; + const struct ethtool_usrip4_spec *l3_val = &fs->h_u.usr_ip4_spec; + + mask->saddr = l3_mask->ip4src; + mask->daddr = l3_mask->ip4dst; + key->saddr = l3_val->ip4src; + key->daddr = l3_val->ip4dst; + + if (mask->protocol) { + mask->protocol = l3_mask->proto; + key->protocol = l3_val->proto; + } +} + +static bool has_ipv4(u32 flow_type) +{ + return flow_type == IP_USER_FLOW; +} + static int setup_classifier(struct virtnet_ff *ff, struct virtnet_classifier **c) { @@ -237,6 +290,7 @@ static bool supported_flow_type(const struct ethtool_rx_flow_spec *fs) { switch (fs->flow_type) { case ETHER_FLOW: + case IP_USER_FLOW: return true; } @@ -260,16 +314,27 @@ static int validate_flow_input(struct virtnet_ff *ff, if (!supported_flow_type(fs)) return -EOPNOTSUPP; - return 0; } static void calculate_flow_sizes(struct ethtool_rx_flow_spec *fs, - size_t *key_size, size_t *classifier_size, - int *num_hdrs) + size_t *key_size, size_t *classifier_size, + int *num_hdrs) { + size_t size = sizeof(struct ethhdr); + *num_hdrs = 1; *key_size = sizeof(struct ethhdr); + + if (fs->flow_type == ETHER_FLOW) + goto done; + + (*num_hdrs)++; + if (has_ipv4(fs->flow_type)) + size += sizeof(struct iphdr); + +done: + *key_size = size; /* * The classifier size is the size of the classifier header, a selector * header for each type of header in the match criteria, and each header @@ -281,8 +346,9 @@ static void calculate_flow_sizes(struct ethtool_rx_flow_spec *fs, } static void setup_eth_hdr_key_mask(struct virtio_net_ff_selector *selector, - u8 *key, - const struct ethtool_rx_flow_spec *fs) + u8 *key, + const struct ethtool_rx_flow_spec *fs, + int num_hdrs) { struct ethhdr *eth_m = (struct ethhdr *)&selector->mask; struct ethhdr *eth_k = (struct ethhdr *)key; @@ -290,8 +356,33 @@ static void setup_eth_hdr_key_mask(struct virtio_net_ff_selector *selector, selector->type = VIRTIO_NET_FF_MASK_TYPE_ETH; selector->length = sizeof(struct ethhdr); - memcpy(eth_m, &fs->m_u.ether_spec, sizeof(*eth_m)); - memcpy(eth_k, &fs->h_u.ether_spec, sizeof(*eth_k)); + if (num_hdrs > 1) { + eth_m->h_proto = cpu_to_be16(0xffff); + eth_k->h_proto = cpu_to_be16(ETH_P_IP); + } else { + memcpy(eth_m, &fs->m_u.ether_spec, sizeof(*eth_m)); + memcpy(eth_k, &fs->h_u.ether_spec, sizeof(*eth_k)); + } +} + +static int setup_ip_key_mask(struct virtio_net_ff_selector *selector, + u8 *key, + const struct ethtool_rx_flow_spec *fs) +{ + struct iphdr *v4_m = (struct iphdr *)&selector->mask; + struct iphdr *v4_k = (struct iphdr *)key; + + selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV4; + selector->length = sizeof(struct iphdr); + + if (fs->h_u.usr_ip4_spec.l4_4_bytes || + fs->h_u.usr_ip4_spec.tos || + fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4) + return -EOPNOTSUPP; + + parse_ip4(v4_m, v4_k, fs); + + return 0; } static int @@ -312,6 +403,17 @@ validate_classifier_selectors(struct virtnet_ff *ff, return 0; } +static +struct virtio_net_ff_selector *next_selector(struct virtio_net_ff_selector *sel) +{ + void *nextsel; + + nextsel = (u8 *)sel + sizeof(struct virtio_net_ff_selector) + + sel->length; + + return nextsel; +} + static int build_and_insert(struct virtnet_ff *ff, struct virtnet_ethtool_rule *eth_rule) { @@ -349,8 +451,17 @@ static int build_and_insert(struct virtnet_ff *ff, classifier->count = num_hdrs; selector = &classifier->selectors[0]; - setup_eth_hdr_key_mask(selector, key, fs); + setup_eth_hdr_key_mask(selector, key, fs, num_hdrs); + if (num_hdrs == 1) + goto validate; + + selector = next_selector(selector); + + err = setup_ip_key_mask(selector, key + sizeof(struct ethhdr), fs); + if (err) + goto err_classifier; +validate: err = validate_classifier_selectors(ff, classifier, num_hdrs); if (err) goto err_key; -- 2.45.0 Implement support for IPV6_USER_FLOW type rules. Example: $ ethtool -U ens9 flow-type ip6 src-ip fe80::2 dst-ip fe80::4 action 3 Added rule with ID 0 The example rule will forward packets with the specified soure and destination IP addresses to RX ring 3. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/virtio_net_ff.c | 89 +++++++++++++++++++++++--- 1 file changed, 81 insertions(+), 8 deletions(-) diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c index 0374676d1342..ce59fb36dae9 100644 --- a/drivers/net/virtio_net/virtio_net_ff.c +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -118,6 +118,34 @@ static bool validate_ip4_mask(const struct virtnet_ff *ff, return true; } +static bool validate_ip6_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct ipv6hdr *cap, *mask; + + cap = (struct ipv6hdr *)&sel_cap->mask; + mask = (struct ipv6hdr *)&sel->mask; + + if (!ipv6_addr_any(&mask->saddr) && + !check_mask_vs_cap(&mask->saddr, &cap->saddr, + sizeof(cap->saddr), partial_mask)) + return false; + + if (!ipv6_addr_any(&mask->daddr) && + !check_mask_vs_cap(&mask->daddr, &cap->daddr, + sizeof(cap->daddr), partial_mask)) + return false; + + if (mask->nexthdr && + !check_mask_vs_cap(&mask->nexthdr, &cap->nexthdr, + sizeof(cap->nexthdr), partial_mask)) + return false; + + return true; +} + static bool validate_mask(const struct virtnet_ff *ff, const struct virtio_net_ff_selector *sel) { @@ -132,6 +160,9 @@ static bool validate_mask(const struct virtnet_ff *ff, case VIRTIO_NET_FF_MASK_TYPE_IPV4: return validate_ip4_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_IPV6: + return validate_ip6_mask(ff, sel, sel_cap); } return false; @@ -154,11 +185,38 @@ static void parse_ip4(struct iphdr *mask, struct iphdr *key, } } +static void parse_ip6(struct ipv6hdr *mask, struct ipv6hdr *key, + const struct ethtool_rx_flow_spec *fs) +{ + const struct ethtool_usrip6_spec *l3_mask = &fs->m_u.usr_ip6_spec; + const struct ethtool_usrip6_spec *l3_val = &fs->h_u.usr_ip6_spec; + + if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6src)) { + memcpy(&mask->saddr, l3_mask->ip6src, sizeof(mask->saddr)); + memcpy(&key->saddr, l3_val->ip6src, sizeof(key->saddr)); + } + + if (!ipv6_addr_any((struct in6_addr *)l3_mask->ip6dst)) { + memcpy(&mask->daddr, l3_mask->ip6dst, sizeof(mask->daddr)); + memcpy(&key->daddr, l3_val->ip6dst, sizeof(key->daddr)); + } + + if (l3_mask->l4_proto) { + mask->nexthdr = l3_mask->l4_proto; + key->nexthdr = l3_val->l4_proto; + } +} + static bool has_ipv4(u32 flow_type) { return flow_type == IP_USER_FLOW; } +static bool has_ipv6(u32 flow_type) +{ + return flow_type == IPV6_USER_FLOW; +} + static int setup_classifier(struct virtnet_ff *ff, struct virtnet_classifier **c) { @@ -291,6 +349,7 @@ static bool supported_flow_type(const struct ethtool_rx_flow_spec *fs) switch (fs->flow_type) { case ETHER_FLOW: case IP_USER_FLOW: + case IPV6_USER_FLOW: return true; } @@ -332,7 +391,8 @@ static void calculate_flow_sizes(struct ethtool_rx_flow_spec *fs, (*num_hdrs)++; if (has_ipv4(fs->flow_type)) size += sizeof(struct iphdr); - + else if (has_ipv6(fs->flow_type)) + size += sizeof(struct ipv6hdr); done: *key_size = size; /* @@ -369,18 +429,31 @@ static int setup_ip_key_mask(struct virtio_net_ff_selector *selector, u8 *key, const struct ethtool_rx_flow_spec *fs) { + struct ipv6hdr *v6_m = (struct ipv6hdr *)&selector->mask; struct iphdr *v4_m = (struct iphdr *)&selector->mask; + struct ipv6hdr *v6_k = (struct ipv6hdr *)key; struct iphdr *v4_k = (struct iphdr *)key; - selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV4; - selector->length = sizeof(struct iphdr); + if (has_ipv6(fs->flow_type)) { + selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV6; + selector->length = sizeof(struct ipv6hdr); - if (fs->h_u.usr_ip4_spec.l4_4_bytes || - fs->h_u.usr_ip4_spec.tos || - fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4) - return -EOPNOTSUPP; + if (fs->h_u.usr_ip6_spec.l4_4_bytes || + fs->h_u.usr_ip6_spec.tclass) + return -EOPNOTSUPP; - parse_ip4(v4_m, v4_k, fs); + parse_ip6(v6_m, v6_k, fs); + } else { + selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV4; + selector->length = sizeof(struct iphdr); + + if (fs->h_u.usr_ip4_spec.l4_4_bytes || + fs->h_u.usr_ip4_spec.tos || + fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4) + return -EOPNOTSUPP; + + parse_ip4(v4_m, v4_k, fs); + } return 0; } -- 2.45.0 Implement TCP and UDP V4/V6 ethtool flow types. Examples: $ ethtool -U ens9 flow-type udp4 dst-ip 192.168.5.2 dst-port\ 4321 action 20 Added rule with ID 4 This example directs IPv4 UDP traffic with the specified address and port to queue 20. $ ethtool -U ens9 flow-type tcp6 src-ip 2001:db8::1 src-port 1234 dst-ip\ 2001:db8::2 dst-port 4321 action 12 Added rule with ID 5 This example directs IPv6 TCP traffic with the specified address and port to queue 12. Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/virtio_net_ff.c | 207 +++++++++++++++++++++++-- 1 file changed, 198 insertions(+), 9 deletions(-) diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c index ce59fb36dae9..d4a34958cc42 100644 --- a/drivers/net/virtio_net/virtio_net_ff.c +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -146,6 +146,52 @@ static bool validate_ip6_mask(const struct virtnet_ff *ff, return true; } +static bool validate_tcp_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct tcphdr *cap, *mask; + + cap = (struct tcphdr *)&sel_cap->mask; + mask = (struct tcphdr *)&sel->mask; + + if (mask->source && + !check_mask_vs_cap(&mask->source, &cap->source, + sizeof(cap->source), partial_mask)) + return false; + + if (mask->dest && + !check_mask_vs_cap(&mask->dest, &cap->dest, + sizeof(cap->dest), partial_mask)) + return false; + + return true; +} + +static bool validate_udp_mask(const struct virtnet_ff *ff, + const struct virtio_net_ff_selector *sel, + const struct virtio_net_ff_selector *sel_cap) +{ + bool partial_mask = !!(sel_cap->flags & VIRTIO_NET_FF_MASK_F_PARTIAL_MASK); + struct udphdr *cap, *mask; + + cap = (struct udphdr *)&sel_cap->mask; + mask = (struct udphdr *)&sel->mask; + + if (mask->source && + !check_mask_vs_cap(&mask->source, &cap->source, + sizeof(cap->source), partial_mask)) + return false; + + if (mask->dest && + !check_mask_vs_cap(&mask->dest, &cap->dest, + sizeof(cap->dest), partial_mask)) + return false; + + return true; +} + static bool validate_mask(const struct virtnet_ff *ff, const struct virtio_net_ff_selector *sel) { @@ -163,11 +209,45 @@ static bool validate_mask(const struct virtnet_ff *ff, case VIRTIO_NET_FF_MASK_TYPE_IPV6: return validate_ip6_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_TCP: + return validate_tcp_mask(ff, sel, sel_cap); + + case VIRTIO_NET_FF_MASK_TYPE_UDP: + return validate_udp_mask(ff, sel, sel_cap); } return false; } +static void set_tcp(struct tcphdr *mask, struct tcphdr *key, + __be16 psrc_m, __be16 psrc_k, + __be16 pdst_m, __be16 pdst_k) +{ + if (psrc_m) { + mask->source = psrc_m; + key->source = psrc_k; + } + if (pdst_m) { + mask->dest = pdst_m; + key->dest = pdst_k; + } +} + +static void set_udp(struct udphdr *mask, struct udphdr *key, + __be16 psrc_m, __be16 psrc_k, + __be16 pdst_m, __be16 pdst_k) +{ + if (psrc_m) { + mask->source = psrc_m; + key->source = psrc_k; + } + if (pdst_m) { + mask->dest = pdst_m; + key->dest = pdst_k; + } +} + static void parse_ip4(struct iphdr *mask, struct iphdr *key, const struct ethtool_rx_flow_spec *fs) { @@ -209,12 +289,26 @@ static void parse_ip6(struct ipv6hdr *mask, struct ipv6hdr *key, static bool has_ipv4(u32 flow_type) { - return flow_type == IP_USER_FLOW; + return flow_type == TCP_V4_FLOW || + flow_type == UDP_V4_FLOW || + flow_type == IP_USER_FLOW; } static bool has_ipv6(u32 flow_type) { - return flow_type == IPV6_USER_FLOW; + return flow_type == TCP_V6_FLOW || + flow_type == UDP_V6_FLOW || + flow_type == IPV6_USER_FLOW; +} + +static bool has_tcp(u32 flow_type) +{ + return flow_type == TCP_V4_FLOW || flow_type == TCP_V6_FLOW; +} + +static bool has_udp(u32 flow_type) +{ + return flow_type == UDP_V4_FLOW || flow_type == UDP_V6_FLOW; } static int setup_classifier(struct virtnet_ff *ff, @@ -350,6 +444,10 @@ static bool supported_flow_type(const struct ethtool_rx_flow_spec *fs) case ETHER_FLOW: case IP_USER_FLOW: case IPV6_USER_FLOW: + case TCP_V4_FLOW: + case TCP_V6_FLOW: + case UDP_V4_FLOW: + case UDP_V6_FLOW: return true; } @@ -393,6 +491,12 @@ static void calculate_flow_sizes(struct ethtool_rx_flow_spec *fs, size += sizeof(struct iphdr); else if (has_ipv6(fs->flow_type)) size += sizeof(struct ipv6hdr); + + if (has_tcp(fs->flow_type) || has_udp(fs->flow_type)) { + (*num_hdrs)++; + size += has_tcp(fs->flow_type) ? sizeof(struct tcphdr) : + sizeof(struct udphdr); + } done: *key_size = size; /* @@ -427,7 +531,8 @@ static void setup_eth_hdr_key_mask(struct virtio_net_ff_selector *selector, static int setup_ip_key_mask(struct virtio_net_ff_selector *selector, u8 *key, - const struct ethtool_rx_flow_spec *fs) + const struct ethtool_rx_flow_spec *fs, + int num_hdrs) { struct ipv6hdr *v6_m = (struct ipv6hdr *)&selector->mask; struct iphdr *v4_m = (struct iphdr *)&selector->mask; @@ -438,21 +543,93 @@ static int setup_ip_key_mask(struct virtio_net_ff_selector *selector, selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV6; selector->length = sizeof(struct ipv6hdr); - if (fs->h_u.usr_ip6_spec.l4_4_bytes || - fs->h_u.usr_ip6_spec.tclass) + if (num_hdrs == 2 && (fs->h_u.usr_ip6_spec.l4_4_bytes || + fs->h_u.usr_ip6_spec.tclass)) return -EOPNOTSUPP; parse_ip6(v6_m, v6_k, fs); + + if (num_hdrs > 2) { + v6_m->nexthdr = 0xff; + if (has_tcp(fs->flow_type)) + v6_k->nexthdr = IPPROTO_TCP; + else + v6_k->nexthdr = IPPROTO_UDP; + } } else { selector->type = VIRTIO_NET_FF_MASK_TYPE_IPV4; selector->length = sizeof(struct iphdr); - if (fs->h_u.usr_ip4_spec.l4_4_bytes || - fs->h_u.usr_ip4_spec.tos || - fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4) + if (num_hdrs == 2 && + (fs->h_u.usr_ip4_spec.l4_4_bytes || + fs->h_u.usr_ip4_spec.tos || + fs->h_u.usr_ip4_spec.ip_ver != ETH_RX_NFC_IP4)) return -EOPNOTSUPP; parse_ip4(v4_m, v4_k, fs); + + if (num_hdrs > 2) { + v4_m->protocol = 0xff; + if (has_tcp(fs->flow_type)) + v4_k->protocol = IPPROTO_TCP; + else + v4_k->protocol = IPPROTO_UDP; + } + } + + return 0; +} + +static int setup_transport_key_mask(struct virtio_net_ff_selector *selector, + u8 *key, + struct ethtool_rx_flow_spec *fs) +{ + struct tcphdr *tcp_m = (struct tcphdr *)&selector->mask; + struct udphdr *udp_m = (struct udphdr *)&selector->mask; + const struct ethtool_tcpip6_spec *v6_l4_mask; + const struct ethtool_tcpip4_spec *v4_l4_mask; + const struct ethtool_tcpip6_spec *v6_l4_key; + const struct ethtool_tcpip4_spec *v4_l4_key; + struct tcphdr *tcp_k = (struct tcphdr *)key; + struct udphdr *udp_k = (struct udphdr *)key; + + if (has_tcp(fs->flow_type)) { + selector->type = VIRTIO_NET_FF_MASK_TYPE_TCP; + selector->length = sizeof(struct tcphdr); + + if (has_ipv6(fs->flow_type)) { + v6_l4_mask = &fs->m_u.tcp_ip6_spec; + v6_l4_key = &fs->h_u.tcp_ip6_spec; + + set_tcp(tcp_m, tcp_k, v6_l4_mask->psrc, v6_l4_key->psrc, + v6_l4_mask->pdst, v6_l4_key->pdst); + } else { + v4_l4_mask = &fs->m_u.tcp_ip4_spec; + v4_l4_key = &fs->h_u.tcp_ip4_spec; + + set_tcp(tcp_m, tcp_k, v4_l4_mask->psrc, v4_l4_key->psrc, + v4_l4_mask->pdst, v4_l4_key->pdst); + } + + } else if (has_udp(fs->flow_type)) { + selector->type = VIRTIO_NET_FF_MASK_TYPE_UDP; + selector->length = sizeof(struct udphdr); + + if (has_ipv6(fs->flow_type)) { + v6_l4_mask = &fs->m_u.udp_ip6_spec; + v6_l4_key = &fs->h_u.udp_ip6_spec; + + set_udp(udp_m, udp_k, v6_l4_mask->psrc, v6_l4_key->psrc, + v6_l4_mask->pdst, v6_l4_key->pdst); + } else { + v4_l4_mask = &fs->m_u.udp_ip4_spec; + v4_l4_key = &fs->h_u.udp_ip4_spec; + + set_udp(udp_m, udp_k, v4_l4_mask->psrc, v4_l4_key->psrc, + v4_l4_mask->pdst, v4_l4_key->pdst); + } + } else { + return -EOPNOTSUPP; } return 0; @@ -495,6 +672,7 @@ static int build_and_insert(struct virtnet_ff *ff, struct virtio_net_ff_selector *selector; struct virtnet_classifier *c; size_t classifier_size; + size_t key_offset; size_t key_size; int num_hdrs; u8 *key; @@ -528,9 +706,20 @@ static int build_and_insert(struct virtnet_ff *ff, if (num_hdrs == 1) goto validate; + key_offset = selector->length; + selector = next_selector(selector); + + err = setup_ip_key_mask(selector, key + key_offset, fs, num_hdrs); + if (err) + goto err_classifier; + + if (num_hdrs == 2) + goto validate; + + key_offset += selector->length; selector = next_selector(selector); - err = setup_ip_key_mask(selector, key + sizeof(struct ethhdr), fs); + err = setup_transport_key_mask(selector, key + key_offset, fs); if (err) goto err_classifier; -- 2.45.0 - Get total number of rules. There's no user interface for this. It is used to allocate an appropriately sized buffer for getting all the rules. - Get specific rule $ ethtool -u ens9 rule 0 Filter: 0 Rule Type: UDP over IPv4 Src IP addr: 0.0.0.0 mask: 255.255.255.255 Dest IP addr: 192.168.5.2 mask: 0.0.0.0 TOS: 0x0 mask: 0xff Src port: 0 mask: 0xffff Dest port: 4321 mask: 0x0 Action: Direct to queue 16 - Get all rules: $ ethtool -u ens9 31 RX rings available Total 2 rules Filter: 0 Rule Type: UDP over IPv4 Src IP addr: 0.0.0.0 mask: 255.255.255.255 Dest IP addr: 192.168.5.2 mask: 0.0.0.0 ... Filter: 1 Flow Type: Raw Ethernet Src MAC addr: 00:00:00:00:00:00 mask: FF:FF:FF:FF:FF:FF Dest MAC addr: 08:11:22:33:44:54 mask: 00:00:00:00:00:00 Signed-off-by: Daniel Jurgens Reviewed-by: Parav Pandit Reviewed-by: Shahar Shitrit --- drivers/net/virtio_net/virtio_net_ff.c | 48 ++++++++++++++++++++++++ drivers/net/virtio_net/virtio_net_ff.h | 6 +++ drivers/net/virtio_net/virtio_net_main.c | 23 ++++++++++++ 3 files changed, 77 insertions(+) diff --git a/drivers/net/virtio_net/virtio_net_ff.c b/drivers/net/virtio_net/virtio_net_ff.c index d4a34958cc42..5488300a4fc3 100644 --- a/drivers/net/virtio_net/virtio_net_ff.c +++ b/drivers/net/virtio_net/virtio_net_ff.c @@ -809,6 +809,54 @@ int virtnet_ethtool_flow_remove(struct virtnet_ff *ff, int location) return err; } +int virtnet_ethtool_get_flow_count(struct virtnet_ff *ff, + struct ethtool_rxnfc *info) +{ + if (!ff->ff_supported) + return -EOPNOTSUPP; + + info->rule_cnt = ff->ethtool.num_rules; + info->data = le32_to_cpu(ff->ff_caps->rules_limit) | RX_CLS_LOC_SPECIAL; + + return 0; +} + +int virtnet_ethtool_get_flow(struct virtnet_ff *ff, + struct ethtool_rxnfc *info) +{ + struct virtnet_ethtool_rule *eth_rule; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + eth_rule = xa_load(&ff->ethtool.rules, info->fs.location); + if (!eth_rule) + return -ENOENT; + + info->fs = eth_rule->flow_spec; + + return 0; +} + +int +virtnet_ethtool_get_all_flows(struct virtnet_ff *ff, + struct ethtool_rxnfc *info, u32 *rule_locs) +{ + struct virtnet_ethtool_rule *eth_rule; + unsigned long i = 0; + int idx = 0; + + if (!ff->ff_supported) + return -EOPNOTSUPP; + + xa_for_each(&ff->ethtool.rules, i, eth_rule) + rule_locs[idx++] = i; + + info->data = le32_to_cpu(ff->ff_caps->rules_limit); + + return 0; +} + static size_t get_mask_size(u16 type) { switch (type) { diff --git a/drivers/net/virtio_net/virtio_net_ff.h b/drivers/net/virtio_net/virtio_net_ff.h index 94b575fbd9ed..4bb41e64cc59 100644 --- a/drivers/net/virtio_net/virtio_net_ff.h +++ b/drivers/net/virtio_net/virtio_net_ff.h @@ -28,6 +28,12 @@ void virtnet_ff_init(struct virtnet_ff *ff, struct virtio_device *vdev); void virtnet_ff_cleanup(struct virtnet_ff *ff); +int virtnet_ethtool_get_flow_count(struct virtnet_ff *ff, + struct ethtool_rxnfc *info); +int virtnet_ethtool_get_all_flows(struct virtnet_ff *ff, + struct ethtool_rxnfc *info, u32 *rule_locs); +int virtnet_ethtool_get_flow(struct virtnet_ff *ff, + struct ethtool_rxnfc *info); int virtnet_ethtool_flow_insert(struct virtnet_ff *ff, struct ethtool_rx_flow_spec *fs, u16 curr_queue_pairs); diff --git a/drivers/net/virtio_net/virtio_net_main.c b/drivers/net/virtio_net/virtio_net_main.c index 808988cdf265..e8336925c912 100644 --- a/drivers/net/virtio_net/virtio_net_main.c +++ b/drivers/net/virtio_net/virtio_net_main.c @@ -5619,6 +5619,28 @@ static u32 virtnet_get_rx_ring_count(struct net_device *dev) return vi->curr_queue_pairs; } +static int virtnet_get_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info, u32 *rule_locs) +{ + struct virtnet_info *vi = netdev_priv(dev); + int rc = 0; + + switch (info->cmd) { + case ETHTOOL_GRXCLSRLCNT: + rc = virtnet_ethtool_get_flow_count(&vi->ff, info); + break; + case ETHTOOL_GRXCLSRULE: + rc = virtnet_ethtool_get_flow(&vi->ff, info); + break; + case ETHTOOL_GRXCLSRLALL: + rc = virtnet_ethtool_get_all_flows(&vi->ff, info, rule_locs); + break; + default: + rc = -EOPNOTSUPP; + } + + return rc; +} + static int virtnet_set_rxnfc(struct net_device *dev, struct ethtool_rxnfc *info) { struct virtnet_info *vi = netdev_priv(dev); @@ -5660,6 +5682,7 @@ static const struct ethtool_ops virtnet_ethtool_ops = { .get_rxfh_fields = virtnet_get_hashflow, .set_rxfh_fields = virtnet_set_hashflow, .get_rx_ring_count = virtnet_get_rx_ring_count, + .get_rxnfc = virtnet_get_rxnfc, .set_rxnfc = virtnet_set_rxnfc, }; -- 2.45.0