3 files changed, 397 insertions, 0 deletions
diff --git a/vdpa/include/uapi/linux/vdpa.h b/vdpa/include/uapi/linux/vdpa.h
new file mode 100644
index 0000000..0561852
--- /dev/null
+++ b/vdpa/include/uapi/linux/vdpa.h
@@ -0,0 +1,65 @@
+/* SPDX-License-Identifier: GPL-2.0+ WITH Linux-syscall-note */
+/*
+ * vdpa device management interface
+ * Copyright (c) 2020 Mellanox Technologies Ltd. All rights reserved.
+ */
+
+#ifndef _LINUX_VDPA_H_
+#define _LINUX_VDPA_H_
+
+#define VDPA_GENL_NAME "vdpa"
+#define VDPA_GENL_VERSION 0x1
+
+enum vdpa_command {
+	VDPA_CMD_UNSPEC,
+	VDPA_CMD_MGMTDEV_NEW,
+	VDPA_CMD_MGMTDEV_GET,		/* can dump */
+	VDPA_CMD_DEV_NEW,
+	VDPA_CMD_DEV_DEL,
+	VDPA_CMD_DEV_GET,		/* can dump */
+	VDPA_CMD_DEV_CONFIG_GET,	/* can dump */
+	VDPA_CMD_DEV_VSTATS_GET,
+};
+
+enum vdpa_attr {
+	VDPA_ATTR_UNSPEC,
+
+	/* Pad attribute for 64b alignment */
+	VDPA_ATTR_PAD = VDPA_ATTR_UNSPEC,
+
+	/* bus name (optional) + dev name together make the parent device handle */
+	VDPA_ATTR_MGMTDEV_BUS_NAME,		/* string */
+	VDPA_ATTR_MGMTDEV_DEV_NAME,		/* string */
+	VDPA_ATTR_MGMTDEV_SUPPORTED_CLASSES,	/* u64 */
+
+	VDPA_ATTR_DEV_NAME,			/* string */
+	VDPA_ATTR_DEV_ID,			/* u32 */
+	VDPA_ATTR_DEV_VENDOR_ID,		/* u32 */
+	VDPA_ATTR_DEV_MAX_VQS,			/* u32 */
+	VDPA_ATTR_DEV_MAX_VQ_SIZE,		/* u16 */
+	VDPA_ATTR_DEV_MIN_VQ_SIZE,		/* u16 */
+
+	VDPA_ATTR_DEV_NET_CFG_MACADDR,		/* binary */
+	VDPA_ATTR_DEV_NET_STATUS,		/* u8 */
+	VDPA_ATTR_DEV_NET_CFG_MAX_VQP,		/* u16 */
+	VDPA_ATTR_DEV_NET_CFG_MTU,		/* u16 */
+
+	VDPA_ATTR_DEV_NEGOTIATED_FEATURES,	/* u64 */
+	VDPA_ATTR_DEV_MGMTDEV_MAX_VQS,		/* u32 */
+	/* virtio features that are supported by the vDPA management device */
+	VDPA_ATTR_DEV_SUPPORTED_FEATURES,	/* u64 */
+
+	VDPA_ATTR_DEV_QUEUE_INDEX,              /* u32 */
+	VDPA_ATTR_DEV_VENDOR_ATTR_NAME,		/* string */
+	VDPA_ATTR_DEV_VENDOR_ATTR_VALUE,        /* u64 */
+
+	VDPA_ATTR_DEV_FEATURES,                 /* u64 */
+
+	/* virtio features that are supported by the vDPA device */
+	VDPA_ATTR_VDPA_DEV_SUPPORTED_FEATURES,	/* u64 */
+
+	/* new attributes must be added above here */
+	VDPA_ATTR_MAX,
+};
+
+#endif
diff --git a/vdpa/include/uapi/linux/virtio_ids.h b/vdpa/include/uapi/linux/virtio_ids.h
new file mode 100644
index 0000000..7aa2eb7
--- /dev/null
+++ b/vdpa/include/uapi/linux/virtio_ids.h
@@ -0,0 +1,84 @@
+#ifndef _LINUX_VIRTIO_IDS_H
+#define _LINUX_VIRTIO_IDS_H
+/*
+ * Virtio IDs
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE. */
+
+#define VIRTIO_ID_NET			1 /* virtio net */
+#define VIRTIO_ID_BLOCK			2 /* virtio block */
+#define VIRTIO_ID_CONSOLE		3 /* virtio console */
+#define VIRTIO_ID_RNG			4 /* virtio rng */
+#define VIRTIO_ID_BALLOON		5 /* virtio balloon */
+#define VIRTIO_ID_IOMEM			6 /* virtio ioMemory */
+#define VIRTIO_ID_RPMSG			7 /* virtio remote processor messaging */
+#define VIRTIO_ID_SCSI			8 /* virtio scsi */
+#define VIRTIO_ID_9P			9 /* 9p virtio console */
+#define VIRTIO_ID_MAC80211_WLAN		10 /* virtio WLAN MAC */
+#define VIRTIO_ID_RPROC_SERIAL		11 /* virtio remoteproc serial link */
+#define VIRTIO_ID_CAIF			12 /* Virtio caif */
+#define VIRTIO_ID_MEMORY_BALLOON	13 /* virtio memory balloon */
+#define VIRTIO_ID_GPU			16 /* virtio GPU */
+#define VIRTIO_ID_CLOCK			17 /* virtio clock/timer */
+#define VIRTIO_ID_INPUT			18 /* virtio input */
+#define VIRTIO_ID_VSOCK			19 /* virtio vsock transport */
+#define VIRTIO_ID_CRYPTO		20 /* virtio crypto */
+#define VIRTIO_ID_SIGNAL_DIST		21 /* virtio signal distribution device */
+#define VIRTIO_ID_PSTORE		22 /* virtio pstore device */
+#define VIRTIO_ID_IOMMU			23 /* virtio IOMMU */
+#define VIRTIO_ID_MEM			24 /* virtio mem */
+#define VIRTIO_ID_SOUND			25 /* virtio sound */
+#define VIRTIO_ID_FS			26 /* virtio filesystem */
+#define VIRTIO_ID_PMEM			27 /* virtio pmem */
+#define VIRTIO_ID_RPMB			28 /* virtio rpmb */
+#define VIRTIO_ID_MAC80211_HWSIM	29 /* virtio mac80211-hwsim */
+#define VIRTIO_ID_VIDEO_ENCODER		30 /* virtio video encoder */
+#define VIRTIO_ID_VIDEO_DECODER		31 /* virtio video decoder */
+#define VIRTIO_ID_SCMI			32 /* virtio SCMI */
+#define VIRTIO_ID_NITRO_SEC_MOD		33 /* virtio nitro secure module*/
+#define VIRTIO_ID_I2C_ADAPTER		34 /* virtio i2c adapter */
+#define VIRTIO_ID_WATCHDOG		35 /* virtio watchdog */
+#define VIRTIO_ID_CAN			36 /* virtio can */
+#define VIRTIO_ID_DMABUF		37 /* virtio dmabuf */
+#define VIRTIO_ID_PARAM_SERV		38 /* virtio parameter server */
+#define VIRTIO_ID_AUDIO_POLICY		39 /* virtio audio policy */
+#define VIRTIO_ID_BT			40 /* virtio bluetooth */
+#define VIRTIO_ID_GPIO			41 /* virtio gpio */
+
+/*
+ * Virtio Transitional IDs
+ */
+
+#define VIRTIO_TRANS_ID_NET		0x1000 /* transitional virtio net */
+#define VIRTIO_TRANS_ID_BLOCK		0x1001 /* transitional virtio block */
+#define VIRTIO_TRANS_ID_BALLOON		0x1002 /* transitional virtio balloon */
+#define VIRTIO_TRANS_ID_CONSOLE		0x1003 /* transitional virtio console */
+#define VIRTIO_TRANS_ID_SCSI		0x1004 /* transitional virtio SCSI */
+#define VIRTIO_TRANS_ID_RNG		0x1005 /* transitional virtio rng */
+#define VIRTIO_TRANS_ID_9P		0x1009 /* transitional virtio 9p console */
+
+#endif /* _LINUX_VIRTIO_IDS_H */
diff --git a/vdpa/include/uapi/linux/virtio_ring.h b/vdpa/include/uapi/linux/virtio_ring.h
new file mode 100644
index 0000000..0e827fb
--- /dev/null
+++ b/vdpa/include/uapi/linux/virtio_ring.h
@@ -0,0 +1,248 @@
+#ifndef _LINUX_VIRTIO_RING_H
+#define _LINUX_VIRTIO_RING_H
+/* An interface for efficient virtio implementation, currently for use by KVM,
+ * but hopefully others soon.  Do NOT change this since it will
+ * break existing servers and clients.
+ *
+ * This header is BSD licensed so anyone can use the definitions to implement
+ * compatible drivers/servers.
+ *
+ * Redistribution and use in source and binary forms, with or without
+ * modification, are permitted provided that the following conditions
+ * are met:
+ * 1. Redistributions of source code must retain the above copyright
+ *    notice, this list of conditions and the following disclaimer.
+ * 2. Redistributions in binary form must reproduce the above copyright
+ *    notice, this list of conditions and the following disclaimer in the
+ *    documentation and/or other materials provided with the distribution.
+ * 3. Neither the name of IBM nor the names of its contributors
+ *    may be used to endorse or promote products derived from this software
+ *    without specific prior written permission.
+ * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS ``AS IS'' AND
+ * ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE
+ * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE
+ * ARE DISCLAIMED.  IN NO EVENT SHALL IBM OR CONTRIBUTORS BE LIABLE
+ * FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR CONSEQUENTIAL
+ * DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS
+ * OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION)
+ * HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT
+ * LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY
+ * OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF
+ * SUCH DAMAGE.
+ *
+ * Copyright Rusty Russell IBM Corporation 2007. */
+#include <stdint.h>
+#include <linux/types.h>
+#include <linux/virtio_types.h>
+
+/* This marks a buffer as continuing via the next field. */
+#define VRING_DESC_F_NEXT	1
+/* This marks a buffer as write-only (otherwise read-only). */
+#define VRING_DESC_F_WRITE	2
+/* This means the buffer contains a list of buffer descriptors. */
+#define VRING_DESC_F_INDIRECT	4
+
+/*
+ * Mark a descriptor as available or used in packed ring.
+ * Notice: they are defined as shifts instead of shifted values.
+ */
+#define VRING_PACKED_DESC_F_AVAIL	7
+#define VRING_PACKED_DESC_F_USED	15
+
+/* The Host uses this in used->flags to advise the Guest: don't kick me when
+ * you add a buffer.  It's unreliable, so it's simply an optimization.  Guest
+ * will still kick if it's out of buffers. */
+#define VRING_USED_F_NO_NOTIFY	1
+/* The Guest uses this in avail->flags to advise the Host: don't interrupt me
+ * when you consume a buffer.  It's unreliable, so it's simply an
+ * optimization.  */
+#define VRING_AVAIL_F_NO_INTERRUPT	1
+
+/* Enable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_ENABLE	0x0
+/* Disable events in packed ring. */
+#define VRING_PACKED_EVENT_FLAG_DISABLE	0x1
+/*
+ * Enable events for a specific descriptor in packed ring.
+ * (as specified by Descriptor Ring Change Event Offset/Wrap Counter).
+ * Only valid if VIRTIO_RING_F_EVENT_IDX has been negotiated.
+ */
+#define VRING_PACKED_EVENT_FLAG_DESC	0x2
+
+/*
+ * Wrap counter bit shift in event suppression structure
+ * of packed ring.
+ */
+#define VRING_PACKED_EVENT_F_WRAP_CTR	15
+
+/* We support indirect buffer descriptors */
+#define VIRTIO_RING_F_INDIRECT_DESC	28
+
+/* The Guest publishes the used index for which it expects an interrupt
+ * at the end of the avail ring. Host should ignore the avail->flags field. */
+/* The Host publishes the avail index for which it expects a kick
+ * at the end of the used ring. Guest should ignore the used->flags field. */
+#define VIRTIO_RING_F_EVENT_IDX		29
+
+/* Alignment requirements for vring elements.
+ * When using pre-virtio 1.0 layout, these fall out naturally.
+ */
+#define VRING_AVAIL_ALIGN_SIZE 2
+#define VRING_USED_ALIGN_SIZE 4
+#define VRING_DESC_ALIGN_SIZE 16
+
+/**
+ * struct vring_desc - Virtio ring descriptors,
+ * 16 bytes long. These can chain together via @next.
+ *
+ * @addr: buffer address (guest-physical)
+ * @len: buffer length
+ * @flags: descriptor flags
+ * @next: index of the next descriptor in the chain,
+ *        if the VRING_DESC_F_NEXT flag is set. We chain unused
+ *        descriptors via this, too.
+ */
+struct vring_desc {
+	__virtio64 addr;
+	__virtio32 len;
+	__virtio16 flags;
+	__virtio16 next;
+};
+
+struct vring_avail {
+	__virtio16 flags;
+	__virtio16 idx;
+	__virtio16 ring[];
+};
+
+/* u32 is used here for ids for padding reasons. */
+struct vring_used_elem {
+	/* Index of start of used descriptor chain. */
+	__virtio32 id;
+	/* Total length of the descriptor chain which was used (written to) */
+	__virtio32 len;
+};
+
+typedef struct vring_used_elem __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+	vring_used_elem_t;
+
+struct vring_used {
+	__virtio16 flags;
+	__virtio16 idx;
+	vring_used_elem_t ring[];
+};
+
+/*
+ * The ring element addresses are passed between components with different
+ * alignments assumptions. Thus, we might need to decrease the compiler-selected
+ * alignment, and so must use a typedef to make sure the aligned attribute
+ * actually takes hold:
+ *
+ * https://gcc.gnu.org/onlinedocs//gcc/Common-Type-Attributes.html#Common-Type-Attributes
+ *
+ * When used on a struct, or struct member, the aligned attribute can only
+ * increase the alignment; in order to decrease it, the packed attribute must
+ * be specified as well. When used as part of a typedef, the aligned attribute
+ * can both increase and decrease alignment, and specifying the packed
+ * attribute generates a warning.
+ */
+typedef struct vring_desc __attribute__((aligned(VRING_DESC_ALIGN_SIZE)))
+	vring_desc_t;
+typedef struct vring_avail __attribute__((aligned(VRING_AVAIL_ALIGN_SIZE)))
+	vring_avail_t;
+typedef struct vring_used __attribute__((aligned(VRING_USED_ALIGN_SIZE)))
+	vring_used_t;
+
+struct vring {
+	unsigned int num;
+
+	vring_desc_t *desc;
+
+	vring_avail_t *avail;
+
+	vring_used_t *used;
+};
+
+#ifndef VIRTIO_RING_NO_LEGACY
+
+/* The standard layout for the ring is a continuous chunk of memory which looks
+ * like this.  We assume num is a power of 2.
+ *
+ * struct vring
+ * {
+ *	// The actual descriptors (16 bytes each)
+ *	struct vring_desc desc[num];
+ *
+ *	// A ring of available descriptor heads with free-running index.
+ *	__virtio16 avail_flags;
+ *	__virtio16 avail_idx;
+ *	__virtio16 available[num];
+ *	__virtio16 used_event_idx;
+ *
+ *	// Padding to the next align boundary.
+ *	char pad[];
+ *
+ *	// A ring of used descriptor heads with free-running index.
+ *	__virtio16 used_flags;
+ *	__virtio16 used_idx;
+ *	struct vring_used_elem used[num];
+ *	__virtio16 avail_event_idx;
+ * };
+ */
+/* We publish the used event index at the end of the available ring, and vice
+ * versa. They are at the end for backwards compatibility. */
+#define vring_used_event(vr) ((vr)->avail->ring[(vr)->num])
+#define vring_avail_event(vr) (*(__virtio16 *)&(vr)->used->ring[(vr)->num])
+
+static __inline__ void vring_init(struct vring *vr, unsigned int num, void *p,
+			      unsigned long align)
+{
+	vr->num = num;
+	vr->desc = p;
+	vr->avail = (struct vring_avail *)((char *)p + num * sizeof(struct vring_desc));
+	vr->used = (void *)(((uintptr_t)&vr->avail->ring[num] + sizeof(__virtio16)
+		+ align-1) & ~(align - 1));
+}
+
+static __inline__ unsigned vring_size(unsigned int num, unsigned long align)
+{
+	return ((sizeof(struct vring_desc) * num + sizeof(__virtio16) * (3 + num)
+		 + align - 1) & ~(align - 1))
+		+ sizeof(__virtio16) * 3 + sizeof(struct vring_used_elem) * num;
+}
+
+#endif /* VIRTIO_RING_NO_LEGACY */
+
+/* The following is used with USED_EVENT_IDX and AVAIL_EVENT_IDX */
+/* Assuming a given event_idx value from the other side, if
+ * we have just incremented index from old to new_idx,
+ * should we trigger an event? */
+static __inline__ int vring_need_event(__u16 event_idx, __u16 new_idx, __u16 old)
+{
+	/* Note: Xen has similar logic for notification hold-off
+	 * in include/xen/interface/io/ring.h with req_event and req_prod
+	 * corresponding to event_idx + 1 and new_idx respectively.
+	 * Note also that req_event and req_prod in Xen start at 1,
+	 * event indexes in virtio start at 0. */
+	return (__u16)(new_idx - event_idx - 1) < (__u16)(new_idx - old);
+}
+
+struct vring_packed_desc_event {
+	/* Descriptor Ring Change Event Offset/Wrap Counter. */
+	__le16 off_wrap;
+	/* Descriptor Ring Change Event Flags. */
+	__le16 flags;
+};
+
+struct vring_packed_desc {
+	/* Buffer Address. */
+	__le64 addr;
+	/* Buffer Length. */
+	__le32 len;
+	/* Buffer ID. */
+	__le16 id;
+	/* The flags depending on descriptor type. */
+	__le16 flags;
+};
+
+#endif /* _LINUX_VIRTIO_RING_H */