Merge tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost

Pull virtio updates from Michael Tsirkin:

 - resume support in vdpa/solidrun

 - structure size optimizations in virtio_pci

 - new pds_vdpa driver

 - immediate initialization mechanism for vdpa/ifcvf

 - interrupt bypass for vdpa/mlx5

 - multiple worker support for vhost

 - viirtio net in Intel F2000X-PL support for vdpa/ifcvf

 - fixes, cleanups all over the place

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost: (48 commits)
  vhost: Make parameter name match of vhost_get_vq_desc()
  vduse: fix NULL pointer dereference
  vhost: Allow worker switching while work is queueing
  vhost_scsi: add support for worker ioctls
  vhost: allow userspace to create workers
  vhost: replace single worker pointer with xarray
  vhost: add helper to parse userspace vring state/file
  vhost: remove vhost_work_queue
  vhost_scsi: flush IO vqs then send TMF rsp
  vhost_scsi: convert to vhost_vq_work_queue
  vhost_scsi: make SCSI cmd completion per vq
  vhost_sock: convert to vhost_vq_work_queue
  vhost: convert poll work to be vq based
  vhost: take worker or vq for flushing
  vhost: take worker or vq instead of dev for queueing
  vhost, vhost_net: add helper to check if vq has work
  vhost: add vhost_worker pointer to vhost_virtqueue
  vhost: dynamically allocate vhost_worker
  vhost: create worker at end of vhost_dev_set_owner
  virtio_bt: call scheduler when we free unused buffs
  ...

6 files changed, 305 insertions, 21 deletions

diff --git a/include/linux/pds/pds_adminq.h b/include/linux/pds/pds_adminq.h
index 98a60ce87b92..bcba7fda3cc9 100644
--- a/include/linux/pds/pds_adminq.h
+++ b/include/linux/pds/pds_adminq.h
@@ -222,6 +222,27 @@ enum pds_core_lif_type {
 	PDS_CORE_LIF_TYPE_DEFAULT = 0,
 };
 
+#define PDS_CORE_IFNAMSIZ		16
+
+/**
+ * enum pds_core_logical_qtype - Logical Queue Types
+ * @PDS_CORE_QTYPE_ADMINQ:    Administrative Queue
+ * @PDS_CORE_QTYPE_NOTIFYQ:   Notify Queue
+ * @PDS_CORE_QTYPE_RXQ:       Receive Queue
+ * @PDS_CORE_QTYPE_TXQ:       Transmit Queue
+ * @PDS_CORE_QTYPE_EQ:        Event Queue
+ * @PDS_CORE_QTYPE_MAX:       Max queue type supported
+ */
+enum pds_core_logical_qtype {
+	PDS_CORE_QTYPE_ADMINQ  = 0,
+	PDS_CORE_QTYPE_NOTIFYQ = 1,
+	PDS_CORE_QTYPE_RXQ     = 2,
+	PDS_CORE_QTYPE_TXQ     = 3,
+	PDS_CORE_QTYPE_EQ      = 4,
+
+	PDS_CORE_QTYPE_MAX     = 16   /* don't change - used in struct size */
+};
+
 /**
  * union pds_core_lif_config - LIF configuration
  * @state:	    LIF state (enum pds_core_lif_state)
@@ -584,6 +605,219 @@ struct pds_core_q_init_comp {
 	u8     color;
 };
 
+/*
+ * enum pds_vdpa_cmd_opcode - vDPA Device commands
+ */
+enum pds_vdpa_cmd_opcode {
+	PDS_VDPA_CMD_INIT		= 48,
+	PDS_VDPA_CMD_IDENT		= 49,
+	PDS_VDPA_CMD_RESET		= 51,
+	PDS_VDPA_CMD_VQ_RESET		= 52,
+	PDS_VDPA_CMD_VQ_INIT		= 53,
+	PDS_VDPA_CMD_STATUS_UPDATE	= 54,
+	PDS_VDPA_CMD_SET_FEATURES	= 55,
+	PDS_VDPA_CMD_SET_ATTR		= 56,
+};
+
+/**
+ * struct pds_vdpa_cmd - generic command
+ * @opcode:	Opcode
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ */
+struct pds_vdpa_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+};
+
+/**
+ * struct pds_vdpa_init_cmd - INIT command
+ * @opcode:	Opcode PDS_VDPA_CMD_INIT
+ * @vdpa_index: Index for vdpa subdevice
+ * @vf_id:	VF id
+ */
+struct pds_vdpa_init_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+};
+
+/**
+ * struct pds_vdpa_ident - vDPA identification data
+ * @hw_features:	vDPA features supported by device
+ * @max_vqs:		max queues available (2 queues for a single queuepair)
+ * @max_qlen:		log(2) of maximum number of descriptors
+ * @min_qlen:		log(2) of minimum number of descriptors
+ *
+ * This struct is used in a DMA block that is set up for the PDS_VDPA_CMD_IDENT
+ * transaction.  Set up the DMA block and send the address in the IDENT cmd
+ * data, the DSC will write the ident information, then we can remove the DMA
+ * block after reading the answer.  If the completion status is 0, then there
+ * is valid information, else there was an error and the data should be invalid.
+ */
+struct pds_vdpa_ident {
+	__le64 hw_features;
+	__le16 max_vqs;
+	__le16 max_qlen;
+	__le16 min_qlen;
+};
+
+/**
+ * struct pds_vdpa_ident_cmd - IDENT command
+ * @opcode:	Opcode PDS_VDPA_CMD_IDENT
+ * @rsvd:       Word boundary padding
+ * @vf_id:	VF id
+ * @len:	length of ident info DMA space
+ * @ident_pa:	address for DMA of ident info (struct pds_vdpa_ident)
+ *			only used for this transaction, then forgotten by DSC
+ */
+struct pds_vdpa_ident_cmd {
+	u8     opcode;
+	u8     rsvd;
+	__le16 vf_id;
+	__le32 len;
+	__le64 ident_pa;
+};
+
+/**
+ * struct pds_vdpa_status_cmd - STATUS_UPDATE command
+ * @opcode:	Opcode PDS_VDPA_CMD_STATUS_UPDATE
+ * @vdpa_index: Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @status:	new status bits
+ */
+struct pds_vdpa_status_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	u8     status;
+};
+
+/**
+ * enum pds_vdpa_attr - List of VDPA device attributes
+ * @PDS_VDPA_ATTR_MAC:          MAC address
+ * @PDS_VDPA_ATTR_MAX_VQ_PAIRS: Max virtqueue pairs
+ */
+enum pds_vdpa_attr {
+	PDS_VDPA_ATTR_MAC          = 1,
+	PDS_VDPA_ATTR_MAX_VQ_PAIRS = 2,
+};
+
+/**
+ * struct pds_vdpa_setattr_cmd - SET_ATTR command
+ * @opcode:		Opcode PDS_VDPA_CMD_SET_ATTR
+ * @vdpa_index:		Index for vdpa subdevice
+ * @vf_id:		VF id
+ * @attr:		attribute to be changed (enum pds_vdpa_attr)
+ * @pad:		Word boundary padding
+ * @mac:		new mac address to be assigned as vdpa device address
+ * @max_vq_pairs:	new limit of virtqueue pairs
+ */
+struct pds_vdpa_setattr_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	u8     attr;
+	u8     pad[3];
+	union {
+		u8 mac[6];
+		__le16 max_vq_pairs;
+	} __packed;
+};
+
+/**
+ * struct pds_vdpa_vq_init_cmd - queue init command
+ * @opcode: Opcode PDS_VDPA_CMD_VQ_INIT
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @qid:	Queue id (bit0 clear = rx, bit0 set = tx, qid=N is ctrlq)
+ * @len:	log(2) of max descriptor count
+ * @desc_addr:	DMA address of descriptor area
+ * @avail_addr:	DMA address of available descriptors (aka driver area)
+ * @used_addr:	DMA address of used descriptors (aka device area)
+ * @intr_index:	interrupt index
+ * @avail_index:	initial device position in available ring
+ * @used_index:	initial device position in used ring
+ */
+struct pds_vdpa_vq_init_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	__le16 qid;
+	__le16 len;
+	__le64 desc_addr;
+	__le64 avail_addr;
+	__le64 used_addr;
+	__le16 intr_index;
+	__le16 avail_index;
+	__le16 used_index;
+};
+
+/**
+ * struct pds_vdpa_vq_init_comp - queue init completion
+ * @status:	Status of the command (enum pds_core_status_code)
+ * @hw_qtype:	HW queue type, used in doorbell selection
+ * @hw_qindex:	HW queue index, used in doorbell selection
+ * @rsvd:	Word boundary padding
+ * @color:	Color bit
+ */
+struct pds_vdpa_vq_init_comp {
+	u8     status;
+	u8     hw_qtype;
+	__le16 hw_qindex;
+	u8     rsvd[11];
+	u8     color;
+};
+
+/**
+ * struct pds_vdpa_vq_reset_cmd - queue reset command
+ * @opcode:	Opcode PDS_VDPA_CMD_VQ_RESET
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @qid:	Queue id
+ */
+struct pds_vdpa_vq_reset_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	__le16 qid;
+};
+
+/**
+ * struct pds_vdpa_vq_reset_comp - queue reset completion
+ * @status:	Status of the command (enum pds_core_status_code)
+ * @rsvd0:	Word boundary padding
+ * @avail_index:	current device position in available ring
+ * @used_index:	current device position in used ring
+ * @rsvd:	Word boundary padding
+ * @color:	Color bit
+ */
+struct pds_vdpa_vq_reset_comp {
+	u8     status;
+	u8     rsvd0;
+	__le16 avail_index;
+	__le16 used_index;
+	u8     rsvd[9];
+	u8     color;
+};
+
+/**
+ * struct pds_vdpa_set_features_cmd - set hw features
+ * @opcode: Opcode PDS_VDPA_CMD_SET_FEATURES
+ * @vdpa_index:	Index for vdpa subdevice
+ * @vf_id:	VF id
+ * @rsvd:       Word boundary padding
+ * @features:	Feature bit mask
+ */
+struct pds_vdpa_set_features_cmd {
+	u8     opcode;
+	u8     vdpa_index;
+	__le16 vf_id;
+	__le32 rsvd;
+	__le64 features;
+};
+
 union pds_core_adminq_cmd {
 	u8     opcode;
 	u8     bytes[64];
@@ -600,6 +834,16 @@ union pds_core_adminq_cmd {
 
 	struct pds_core_q_identify_cmd    q_ident;
 	struct pds_core_q_init_cmd        q_init;
+
+	struct pds_vdpa_cmd		  vdpa;
+	struct pds_vdpa_init_cmd	  vdpa_init;
+	struct pds_vdpa_ident_cmd	  vdpa_ident;
+	struct pds_vdpa_status_cmd	  vdpa_status;
+	struct pds_vdpa_setattr_cmd	  vdpa_setattr;
+	struct pds_vdpa_set_features_cmd  vdpa_set_features;
+	struct pds_vdpa_vq_init_cmd	  vdpa_vq_init;
+	struct pds_vdpa_vq_reset_cmd	  vdpa_vq_reset;
+
 };
 
 union pds_core_adminq_comp {
@@ -621,6 +865,9 @@ union pds_core_adminq_comp {
 
 	struct pds_core_q_identify_comp   q_ident;
 	struct pds_core_q_init_comp       q_init;
+
+	struct pds_vdpa_vq_init_comp	  vdpa_vq_init;
+	struct pds_vdpa_vq_reset_comp	  vdpa_vq_reset;
 };
 
 #ifndef __CHECKER__
diff --git a/include/linux/pds/pds_common.h b/include/linux/pds/pds_common.h
index 060331486d50..435c8e8161c2 100644
--- a/include/linux/pds/pds_common.h
+++ b/include/linux/pds/pds_common.h
@@ -39,26 +39,7 @@ enum pds_core_vif_types {
 #define PDS_DEV_TYPE_RDMA_STR	"RDMA"
 #define PDS_DEV_TYPE_LM_STR	"LM"
 
-#define PDS_CORE_IFNAMSIZ		16
-
-/**
- * enum pds_core_logical_qtype - Logical Queue Types
- * @PDS_CORE_QTYPE_ADMINQ:    Administrative Queue
- * @PDS_CORE_QTYPE_NOTIFYQ:   Notify Queue
- * @PDS_CORE_QTYPE_RXQ:       Receive Queue
- * @PDS_CORE_QTYPE_TXQ:       Transmit Queue
- * @PDS_CORE_QTYPE_EQ:        Event Queue
- * @PDS_CORE_QTYPE_MAX:       Max queue type supported
- */
-enum pds_core_logical_qtype {
-	PDS_CORE_QTYPE_ADMINQ  = 0,
-	PDS_CORE_QTYPE_NOTIFYQ = 1,
-	PDS_CORE_QTYPE_RXQ     = 2,
-	PDS_CORE_QTYPE_TXQ     = 3,
-	PDS_CORE_QTYPE_EQ      = 4,
-
-	PDS_CORE_QTYPE_MAX     = 16   /* don't change - used in struct size */
-};
+#define PDS_VDPA_DEV_NAME	PDS_CORE_DRV_NAME "." PDS_DEV_TYPE_VDPA_STR
 
 int pdsc_register_notify(struct notifier_block *nb);
 void pdsc_unregister_notify(struct notifier_block *nb);
diff --git a/include/linux/virtio.h b/include/linux/virtio.h
index b93238db94e3..de6041deee37 100644
--- a/include/linux/virtio.h
+++ b/include/linux/virtio.h
@@ -103,6 +103,7 @@ int virtqueue_resize(struct virtqueue *vq, u32 num,
  * @config_enabled: configuration change reporting enabled
  * @config_change_pending: configuration change reported while disabled
  * @config_lock: protects configuration change reporting
+ * @vqs_list_lock: protects @vqs.
  * @dev: underlying device.
  * @id: the device type identification (used to match it with a driver).
  * @config: the configuration ops for this device.
@@ -117,7 +118,7 @@ struct virtio_device {
 	bool config_enabled;
 	bool config_change_pending;
 	spinlock_t config_lock;
-	spinlock_t vqs_list_lock; /* Protects VQs list access */
+	spinlock_t vqs_list_lock;
 	struct device dev;
 	struct virtio_device_id id;
 	const struct virtio_config_ops *config;
@@ -160,6 +161,8 @@ size_t virtio_max_dma_size(const struct virtio_device *vdev);
  * @feature_table_size: number of entries in the feature table array.
  * @feature_table_legacy: same as feature_table but when working in legacy mode.
  * @feature_table_size_legacy: number of entries in feature table legacy array.
+ * @validate: the function to call to validate features and config space.
+ *            Returns 0 or -errno.
  * @probe: the function to call when a device is found.  Returns 0 or -errno.
  * @scan: optional function to call after successful probe; intended
  *    for virtio-scsi to invoke a scan.
diff --git a/include/linux/virtio_pci_modern.h b/include/linux/virtio_pci_modern.h
index c4eeb79b0139..067ac1d789bc 100644
--- a/include/linux/virtio_pci_modern.h
+++ b/include/linux/virtio_pci_modern.h
@@ -38,6 +38,12 @@ struct virtio_pci_modern_device {
 	int modern_bars;
 
 	struct virtio_device_id id;
+
+	/* optional check for vendor virtio device, returns dev_id or -ERRNO */
+	int (*device_id_check)(struct pci_dev *pdev);
+
+	/* optional mask for devices with limited DMA space */
+	u64 dma_mask;
 };
 
 /*
diff --git a/include/uapi/linux/vhost.h b/include/uapi/linux/vhost.h
index 92e1b700b51c..f5c48b61ab62 100644
--- a/include/uapi/linux/vhost.h
+++ b/include/uapi/linux/vhost.h
@@ -45,6 +45,25 @@
 #define VHOST_SET_LOG_BASE _IOW(VHOST_VIRTIO, 0x04, __u64)
 /* Specify an eventfd file descriptor to signal on log write. */
 #define VHOST_SET_LOG_FD _IOW(VHOST_VIRTIO, 0x07, int)
+/* By default, a device gets one vhost_worker that its virtqueues share. This
+ * command allows the owner of the device to create an additional vhost_worker
+ * for the device. It can later be bound to 1 or more of its virtqueues using
+ * the VHOST_ATTACH_VRING_WORKER command.
+ *
+ * This must be called after VHOST_SET_OWNER and the caller must be the owner
+ * of the device. The new thread will inherit caller's cgroups and namespaces,
+ * and will share the caller's memory space. The new thread will also be
+ * counted against the caller's RLIMIT_NPROC value.
+ *
+ * The worker's ID used in other commands will be returned in
+ * vhost_worker_state.
+ */
+#define VHOST_NEW_WORKER _IOR(VHOST_VIRTIO, 0x8, struct vhost_worker_state)
+/* Free a worker created with VHOST_NEW_WORKER if it's not attached to any
+ * virtqueue. If userspace is not able to call this for workers its created,
+ * the kernel will free all the device's workers when the device is closed.
+ */
+#define VHOST_FREE_WORKER _IOW(VHOST_VIRTIO, 0x9, struct vhost_worker_state)
 
 /* Ring setup. */
 /* Set number of descriptors in ring. This parameter can not
@@ -70,6 +89,18 @@
 #define VHOST_VRING_BIG_ENDIAN 1
 #define VHOST_SET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x13, struct vhost_vring_state)
 #define VHOST_GET_VRING_ENDIAN _IOW(VHOST_VIRTIO, 0x14, struct vhost_vring_state)
+/* Attach a vhost_worker created with VHOST_NEW_WORKER to one of the device's
+ * virtqueues.
+ *
+ * This will replace the virtqueue's existing worker. If the replaced worker
+ * is no longer attached to any virtqueues, it can be freed with
+ * VHOST_FREE_WORKER.
+ */
+#define VHOST_ATTACH_VRING_WORKER _IOW(VHOST_VIRTIO, 0x15,		\
+				       struct vhost_vring_worker)
+/* Return the vring worker's ID */
+#define VHOST_GET_VRING_WORKER _IOWR(VHOST_VIRTIO, 0x16,		\
+				     struct vhost_vring_worker)
 
 /* The following ioctls use eventfd file descriptors to signal and poll
  * for events. */
diff --git a/include/uapi/linux/vhost_types.h b/include/uapi/linux/vhost_types.h
index c5690a8992d8..d3aad12ad1fa 100644
--- a/include/uapi/linux/vhost_types.h
+++ b/include/uapi/linux/vhost_types.h
@@ -47,6 +47,22 @@ struct vhost_vring_addr {
 	__u64 log_guest_addr;
 };
 
+struct vhost_worker_state {
+	/*
+	 * For VHOST_NEW_WORKER the kernel will return the new vhost_worker id.
+	 * For VHOST_FREE_WORKER this must be set to the id of the vhost_worker
+	 * to free.
+	 */
+	unsigned int worker_id;
+};
+
+struct vhost_vring_worker {
+	/* vring index */
+	unsigned int index;
+	/* The id of the vhost_worker returned from VHOST_NEW_WORKER */
+	unsigned int worker_id;
+};
+
 /* no alignment requirement */
 struct vhost_iotlb_msg {
 	__u64 iova;