virtio: fixes, vdpa

Some bug fixes.
 The new vdpa subsystem with two first drivers.
 
 Signed-off-by: Michael S. Tsirkin <mst@redhat.com>
 -----BEGIN PGP SIGNATURE-----
 
 iQFDBAABCAAtFiEEXQn9CHHI+FuUyooNKB8NuNKNVGkFAl6MS7wPHG1zdEByZWRo
 YXQuY29tAAoJECgfDbjSjVRpGp8H/2H49Gya1cfVbGU13qgmBSQqQXC8hS3iNLuG
 ltRgU+jafJT//kvkdm3/DUzfK3eRUWUfqZLKEbAQDtMY0OGHi/KGEBYVLDde7Zxt
 Lg4VnwBhkYDR/f01ZZDbHxzj9JAr83i28nILjLIqf3a1BX4zf203+ZE0/JM8a7wL
 dOPoH7NAfyz5ul2F67bR1IOF8vC6TidpavzR2+HC/MocHYXb6Bgfvt+i4EcrfuMf
 9lnBfajgklKr9sNJniwvvR1pWVg+YyG3VeC6T8tIC/xzbCmIoNT+5b3q2XPSIHq1
 EuQTeXH9CBFXS0qcFlq2ktR1xd1Lx95hKwZpqLwLFDmfgjhV2QU=
 =/84P
 -----END PGP SIGNATURE-----

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

Pull virtio updates from Michael Tsirkin:

 - Some bug fixes

 - The new vdpa subsystem with two first drivers

* tag 'for_linus' of git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost:
  virtio-balloon: Revert "virtio-balloon: Switch back to OOM handler for VIRTIO_BALLOON_F_DEFLATE_ON_OOM"
  vdpa: move to drivers/vdpa
  virtio: Intel IFC VF driver for VDPA
  vdpasim: vDPA device simulator
  vhost: introduce vDPA-based backend
  virtio: introduce a vDPA based transport
  vDPA: introduce vDPA bus
  vringh: IOTLB support
  vhost: factor out IOTLB
  vhost: allow per device message handler
  vhost: refine vhost and vringh kconfig
  virtio-balloon: Switch back to OOM handler for VIRTIO_BALLOON_F_DEFLATE_ON_OOM
  virtio-net: Introduce hash report feature
  virtio-net: Introduce RSS receive steering feature
  virtio-net: Introduce extended RSC feature
  tools/virtio: option to build an out of tree module

MAINTAINERS

@@ -17870,10 +17870,12 @@ L:	virtualization@lists.linux-foundation.org
 S:	Maintained
 F:	Documentation/devicetree/bindings/virtio/
 F:	drivers/virtio/
+F:	drivers/vdpa/
 F:	tools/virtio/
 F:	drivers/net/virtio_net.c
 F:	drivers/block/virtio_blk.c
 F:	include/linux/virtio*.h
+F:	include/linux/vdpa.h
 F:	include/uapi/linux/virtio_*.h
 F:	drivers/crypto/virtio/
 F:	mm/balloon_compaction.c
@@ -17941,6 +17943,7 @@ T:	git git://git.kernel.org/pub/scm/linux/kernel/git/mst/vhost.git
 S:	Maintained
 F:	drivers/vhost/
 F:	include/uapi/linux/vhost.h
+F:	include/linux/vhost_iotlb.h
 
 VIRTIO INPUT DRIVER
 M:	Gerd Hoffmann <kraxel@redhat.com>

arch/arm64/kvm/Kconfig

@@ -64,6 +64,4 @@ config KVM_ARM_PMU
 config KVM_INDIRECT_VECTORS
        def_bool KVM && (HARDEN_BRANCH_PREDICTOR || HARDEN_EL2_VECTORS)
 
-source "drivers/vhost/Kconfig"
-
 endif # VIRTUALIZATION

arch/mips/kvm/Kconfig

@@ -72,6 +72,4 @@ config KVM_MIPS_DEBUG_COP0_COUNTERS
 
 	  If unsure, say N.
 
-source "drivers/vhost/Kconfig"
-
 endif # VIRTUALIZATION

arch/powerpc/kvm/Kconfig

@@ -204,6 +204,4 @@ config KVM_XIVE
 	default y
 	depends on KVM_XICS && PPC_XIVE_NATIVE && KVM_BOOK3S_HV_POSSIBLE
 
-source "drivers/vhost/Kconfig"
-
 endif # VIRTUALIZATION

arch/s390/kvm/Kconfig

@@ -55,8 +55,4 @@ config KVM_S390_UCONTROL
 
 	  If unsure, say N.
 
-# OK, it's a little counter-intuitive to do this, but it puts it neatly under
-# the virtualization menu.
-source "drivers/vhost/Kconfig"
-
 endif # VIRTUALIZATION

arch/x86/kvm/Kconfig

@@ -107,8 +107,4 @@ config KVM_MMU_AUDIT
 	 This option adds a R/W kVM module parameter 'mmu_audit', which allows
 	 auditing of KVM MMU events at runtime.
 
-# OK, it's a little counter-intuitive to do this, but it puts it neatly under
-# the virtualization menu.
-source "drivers/vhost/Kconfig"
-
 endif # VIRTUALIZATION

drivers/Kconfig

@@ -138,6 +138,10 @@ source "drivers/virt/Kconfig"
 
 source "drivers/virtio/Kconfig"
 
+source "drivers/vdpa/Kconfig"
+
+source "drivers/vhost/Kconfig"
+
 source "drivers/hv/Kconfig"
 
 source "drivers/xen/Kconfig"

drivers/Makefile

@@ -42,6 +42,7 @@ obj-$(CONFIG_DMADEVICES)	+= dma/
 obj-y				+= soc/
 
 obj-$(CONFIG_VIRTIO)		+= virtio/
+obj-$(CONFIG_VDPA)		+= vdpa/
 obj-$(CONFIG_XEN)		+= xen/
 
 # regulators early, since some subsystems rely on them to initialize

drivers/misc/mic/Kconfig

@@ -133,8 +133,4 @@ config VOP
 	  OS and tools for MIC to use with this driver are available from
 	  <http://software.intel.com/en-us/mic-developer>.
 
-if VOP
-source "drivers/vhost/Kconfig.vringh"
-endif
-
 endmenu

drivers/net/caif/Kconfig

@@ -58,8 +58,4 @@ config CAIF_VIRTIO
 	---help---
 	  The CAIF driver for CAIF over Virtio.
 
-if CAIF_VIRTIO
-source "drivers/vhost/Kconfig.vringh"
-endif
-
 endif # CAIF_DRIVERS

drivers/vdpa/Kconfig

@@ -0,0 +1,37 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config VDPA
+	tristate
+	help
+	  Enable this module to support vDPA device that uses a
+	  datapath which complies with virtio specifications with
+	  vendor specific control path.
+
+menuconfig VDPA_MENU
+	bool "VDPA drivers"
+	default n
+
+if VDPA_MENU
+
+config VDPA_SIM
+	tristate "vDPA device simulator"
+	depends on RUNTIME_TESTING_MENU
+	select VDPA
+	select VHOST_RING
+	default n
+	help
+	  vDPA networking device simulator which loop TX traffic back
+	  to RX. This device is used for testing, prototyping and
+	  development of vDPA.
+
+config IFCVF
+	tristate "Intel IFC VF VDPA driver"
+	depends on PCI_MSI
+	select VDPA
+	default n
+	help
+	  This kernel module can drive Intel IFC VF NIC to offload
+	  virtio dataplane traffic to hardware.
+	  To compile this driver as a module, choose M here: the module will
+	  be called ifcvf.
+
+endif # VDPA_MENU

drivers/vdpa/Makefile

@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_VDPA) += vdpa.o
+obj-$(CONFIG_VDPA_SIM) += vdpa_sim/
+obj-$(CONFIG_IFCVF)    += ifcvf/

drivers/vdpa/ifcvf/Makefile

@@ -0,0 +1,3 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_IFCVF) += ifcvf.o
+ifcvf-$(CONFIG_IFCVF) += ifcvf_main.o ifcvf_base.o

drivers/vdpa/ifcvf/ifcvf_base.c

@@ -0,0 +1,389 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel IFC VF NIC driver for virtio dataplane offloading
+ *
+ * Copyright (C) 2020 Intel Corporation.
+ *
+ * Author: Zhu Lingshan <lingshan.zhu@intel.com>
+ *
+ */
+
+#include "ifcvf_base.h"
+
+static inline u8 ifc_ioread8(u8 __iomem *addr)
+{
+	return ioread8(addr);
+}
+static inline u16 ifc_ioread16 (__le16 __iomem *addr)
+{
+	return ioread16(addr);
+}
+
+static inline u32 ifc_ioread32(__le32 __iomem *addr)
+{
+	return ioread32(addr);
+}
+
+static inline void ifc_iowrite8(u8 value, u8 __iomem *addr)
+{
+	iowrite8(value, addr);
+}
+
+static inline void ifc_iowrite16(u16 value, __le16 __iomem *addr)
+{
+	iowrite16(value, addr);
+}
+
+static inline void ifc_iowrite32(u32 value, __le32 __iomem *addr)
+{
+	iowrite32(value, addr);
+}
+
+static void ifc_iowrite64_twopart(u64 val,
+				  __le32 __iomem *lo, __le32 __iomem *hi)
+{
+	ifc_iowrite32((u32)val, lo);
+	ifc_iowrite32(val >> 32, hi);
+}
+
+struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw)
+{
+	return container_of(hw, struct ifcvf_adapter, vf);
+}
+
+static void __iomem *get_cap_addr(struct ifcvf_hw *hw,
+				  struct virtio_pci_cap *cap)
+{
+	struct ifcvf_adapter *ifcvf;
+	struct pci_dev *pdev;
+	u32 length, offset;
+	u8 bar;
+
+	length = le32_to_cpu(cap->length);
+	offset = le32_to_cpu(cap->offset);
+	bar = cap->bar;
+
+	ifcvf= vf_to_adapter(hw);
+	pdev = ifcvf->pdev;
+
+	if (bar >= IFCVF_PCI_MAX_RESOURCE) {
+		IFCVF_DBG(pdev,
+			  "Invalid bar number %u to get capabilities\n", bar);
+		return NULL;
+	}
+
+	if (offset + length > pci_resource_len(pdev, bar)) {
+		IFCVF_DBG(pdev,
+			  "offset(%u) + len(%u) overflows bar%u's capability\n",
+			  offset, length, bar);
+		return NULL;
+	}
+
+	return hw->base[bar] + offset;
+}
+
+static int ifcvf_read_config_range(struct pci_dev *dev,
+				   uint32_t *val, int size, int where)
+{
+	int ret, i;
+
+	for (i = 0; i < size; i += 4) {
+		ret = pci_read_config_dword(dev, where + i, val + i / 4);
+		if (ret < 0)
+			return ret;
+	}
+
+	return 0;
+}
+
+int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *pdev)
+{
+	struct virtio_pci_cap cap;
+	u16 notify_off;
+	int ret;
+	u8 pos;
+	u32 i;
+
+	ret = pci_read_config_byte(pdev, PCI_CAPABILITY_LIST, &pos);
+	if (ret < 0) {
+		IFCVF_ERR(pdev, "Failed to read PCI capability list\n");
+		return -EIO;
+	}
+
+	while (pos) {
+		ret = ifcvf_read_config_range(pdev, (u32 *)&cap,
+					      sizeof(cap), pos);
+		if (ret < 0) {
+			IFCVF_ERR(pdev,
+				  "Failed to get PCI capability at %x\n", pos);
+			break;
+		}
+
+		if (cap.cap_vndr != PCI_CAP_ID_VNDR)
+			goto next;
+
+		switch (cap.cfg_type) {
+		case VIRTIO_PCI_CAP_COMMON_CFG:
+			hw->common_cfg = get_cap_addr(hw, &cap);
+			IFCVF_DBG(pdev, "hw->common_cfg = %p\n",
+				  hw->common_cfg);
+			break;
+		case VIRTIO_PCI_CAP_NOTIFY_CFG:
+			pci_read_config_dword(pdev, pos + sizeof(cap),
+					      &hw->notify_off_multiplier);
+			hw->notify_bar = cap.bar;
+			hw->notify_base = get_cap_addr(hw, &cap);
+			IFCVF_DBG(pdev, "hw->notify_base = %p\n",
+				  hw->notify_base);
+			break;
+		case VIRTIO_PCI_CAP_ISR_CFG:
+			hw->isr = get_cap_addr(hw, &cap);
+			IFCVF_DBG(pdev, "hw->isr = %p\n", hw->isr);
+			break;
+		case VIRTIO_PCI_CAP_DEVICE_CFG:
+			hw->net_cfg = get_cap_addr(hw, &cap);
+			IFCVF_DBG(pdev, "hw->net_cfg = %p\n", hw->net_cfg);
+			break;
+		}
+
+next:
+		pos = cap.cap_next;
+	}
+
+	if (hw->common_cfg == NULL || hw->notify_base == NULL ||
+	    hw->isr == NULL || hw->net_cfg == NULL) {
+		IFCVF_ERR(pdev, "Incomplete PCI capabilities\n");
+		return -EIO;
+	}
+
+	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
+		ifc_iowrite16(i, &hw->common_cfg->queue_select);
+		notify_off = ifc_ioread16(&hw->common_cfg->queue_notify_off);
+		hw->vring[i].notify_addr = hw->notify_base +
+			notify_off * hw->notify_off_multiplier;
+	}
+
+	hw->lm_cfg = hw->base[IFCVF_LM_BAR];
+
+	IFCVF_DBG(pdev,
+		  "PCI capability mapping: common cfg: %p, notify base: %p\n, isr cfg: %p, device cfg: %p, multiplier: %u\n",
+		  hw->common_cfg, hw->notify_base, hw->isr,
+		  hw->net_cfg, hw->notify_off_multiplier);
+
+	return 0;
+}
+
+u8 ifcvf_get_status(struct ifcvf_hw *hw)
+{
+	return ifc_ioread8(&hw->common_cfg->device_status);
+}
+
+void ifcvf_set_status(struct ifcvf_hw *hw, u8 status)
+{
+	ifc_iowrite8(status, &hw->common_cfg->device_status);
+}
+
+void ifcvf_reset(struct ifcvf_hw *hw)
+{
+	ifcvf_set_status(hw, 0);
+	/* flush set_status, make sure VF is stopped, reset */
+	ifcvf_get_status(hw);
+}
+
+static void ifcvf_add_status(struct ifcvf_hw *hw, u8 status)
+{
+	if (status != 0)
+		status |= ifcvf_get_status(hw);
+
+	ifcvf_set_status(hw, status);
+	ifcvf_get_status(hw);
+}
+
+u64 ifcvf_get_features(struct ifcvf_hw *hw)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
+	u32 features_lo, features_hi;
+
+	ifc_iowrite32(0, &cfg->device_feature_select);
+	features_lo = ifc_ioread32(&cfg->device_feature);
+
+	ifc_iowrite32(1, &cfg->device_feature_select);
+	features_hi = ifc_ioread32(&cfg->device_feature);
+
+	return ((u64)features_hi << 32) | features_lo;
+}
+
+void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+			   void *dst, int length)
+{
+	u8 old_gen, new_gen, *p;
+	int i;
+
+	WARN_ON(offset + length > sizeof(struct virtio_net_config));
+	do {
+		old_gen = ifc_ioread8(&hw->common_cfg->config_generation);
+		p = dst;
+		for (i = 0; i < length; i++)
+			*p++ = ifc_ioread8(hw->net_cfg + offset + i);
+
+		new_gen = ifc_ioread8(&hw->common_cfg->config_generation);
+	} while (old_gen != new_gen);
+}
+
+void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+			    const void *src, int length)
+{
+	const u8 *p;
+	int i;
+
+	p = src;
+	WARN_ON(offset + length > sizeof(struct virtio_net_config));
+	for (i = 0; i < length; i++)
+		ifc_iowrite8(*p++, hw->net_cfg + offset + i);
+}
+
+static void ifcvf_set_features(struct ifcvf_hw *hw, u64 features)
+{
+	struct virtio_pci_common_cfg __iomem *cfg = hw->common_cfg;
+
+	ifc_iowrite32(0, &cfg->guest_feature_select);
+	ifc_iowrite32((u32)features, &cfg->guest_feature);
+
+	ifc_iowrite32(1, &cfg->guest_feature_select);
+	ifc_iowrite32(features >> 32, &cfg->guest_feature);
+}
+
+static int ifcvf_config_features(struct ifcvf_hw *hw)
+{
+	struct ifcvf_adapter *ifcvf;
+
+	ifcvf = vf_to_adapter(hw);
+	ifcvf_set_features(hw, hw->req_features);
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_FEATURES_OK);
+
+	if (!(ifcvf_get_status(hw) & VIRTIO_CONFIG_S_FEATURES_OK)) {
+		IFCVF_ERR(ifcvf->pdev, "Failed to set FEATURES_OK status\n");
+		return -EIO;
+	}
+
+	return 0;
+}
+
+u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid)
+{
+	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
+	void __iomem *avail_idx_addr;
+	u16 last_avail_idx;
+	u32 q_pair_id;
+
+	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
+	q_pair_id = qid / (IFCVF_MAX_QUEUE_PAIRS * 2);
+	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
+	last_avail_idx = ifc_ioread16(avail_idx_addr);
+
+	return last_avail_idx;
+}
+
+int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num)
+{
+	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
+	void __iomem *avail_idx_addr;
+	u32 q_pair_id;
+
+	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
+	q_pair_id = qid / (IFCVF_MAX_QUEUE_PAIRS * 2);
+	avail_idx_addr = &ifcvf_lm->vring_lm_cfg[q_pair_id].idx_addr[qid % 2];
+	hw->vring[qid].last_avail_idx = num;
+	ifc_iowrite16(num, avail_idx_addr);
+
+	return 0;
+}
+
+static int ifcvf_hw_enable(struct ifcvf_hw *hw)
+{
+	struct ifcvf_lm_cfg __iomem *ifcvf_lm;
+	struct virtio_pci_common_cfg __iomem *cfg;
+	struct ifcvf_adapter *ifcvf;
+	u32 i;
+
+	ifcvf_lm = (struct ifcvf_lm_cfg __iomem *)hw->lm_cfg;
+	ifcvf = vf_to_adapter(hw);
+	cfg = hw->common_cfg;
+	ifc_iowrite16(IFCVF_MSI_CONFIG_OFF, &cfg->msix_config);
+
+	if (ifc_ioread16(&cfg->msix_config) == VIRTIO_MSI_NO_VECTOR) {
+		IFCVF_ERR(ifcvf->pdev, "No msix vector for device config\n");
+		return -EINVAL;
+	}
+
+	for (i = 0; i < hw->nr_vring; i++) {
+		if (!hw->vring[i].ready)
+			break;
+
+		ifc_iowrite16(i, &cfg->queue_select);
+		ifc_iowrite64_twopart(hw->vring[i].desc, &cfg->queue_desc_lo,
+				     &cfg->queue_desc_hi);
+		ifc_iowrite64_twopart(hw->vring[i].avail, &cfg->queue_avail_lo,
+				      &cfg->queue_avail_hi);
+		ifc_iowrite64_twopart(hw->vring[i].used, &cfg->queue_used_lo,
+				     &cfg->queue_used_hi);
+		ifc_iowrite16(hw->vring[i].size, &cfg->queue_size);
+		ifc_iowrite16(i + IFCVF_MSI_QUEUE_OFF, &cfg->queue_msix_vector);
+
+		if (ifc_ioread16(&cfg->queue_msix_vector) ==
+		    VIRTIO_MSI_NO_VECTOR) {
+			IFCVF_ERR(ifcvf->pdev,
+				  "No msix vector for queue %u\n", i);
+			return -EINVAL;
+		}
+
+		ifcvf_set_vq_state(hw, i, hw->vring[i].last_avail_idx);
+		ifc_iowrite16(1, &cfg->queue_enable);
+	}
+
+	return 0;
+}
+
+static void ifcvf_hw_disable(struct ifcvf_hw *hw)
+{
+	struct virtio_pci_common_cfg __iomem *cfg;
+	u32 i;
+
+	cfg = hw->common_cfg;
+	ifc_iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->msix_config);
+
+	for (i = 0; i < hw->nr_vring; i++) {
+		ifc_iowrite16(i, &cfg->queue_select);
+		ifc_iowrite16(VIRTIO_MSI_NO_VECTOR, &cfg->queue_msix_vector);
+	}
+
+	ifc_ioread16(&cfg->queue_msix_vector);
+}
+
+int ifcvf_start_hw(struct ifcvf_hw *hw)
+{
+	ifcvf_reset(hw);
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_ACKNOWLEDGE);
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER);
+
+	if (ifcvf_config_features(hw) < 0)
+		return -EINVAL;
+
+	if (ifcvf_hw_enable(hw) < 0)
+		return -EINVAL;
+
+	ifcvf_add_status(hw, VIRTIO_CONFIG_S_DRIVER_OK);
+
+	return 0;
+}
+
+void ifcvf_stop_hw(struct ifcvf_hw *hw)
+{
+	ifcvf_hw_disable(hw);
+	ifcvf_reset(hw);
+}
+
+void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid)
+{
+	ifc_iowrite16(qid, hw->vring[qid].notify_addr);
+}

drivers/vdpa/ifcvf/ifcvf_base.h

@@ -0,0 +1,118 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Intel IFC VF NIC driver for virtio dataplane offloading
+ *
+ * Copyright (C) 2020 Intel Corporation.
+ *
+ * Author: Zhu Lingshan <lingshan.zhu@intel.com>
+ *
+ */
+
+#ifndef _IFCVF_H_
+#define _IFCVF_H_
+
+#include <linux/pci.h>
+#include <linux/pci_regs.h>
+#include <linux/vdpa.h>
+#include <uapi/linux/virtio_net.h>
+#include <uapi/linux/virtio_config.h>
+#include <uapi/linux/virtio_pci.h>
+
+#define IFCVF_VENDOR_ID		0x1AF4
+#define IFCVF_DEVICE_ID		0x1041
+#define IFCVF_SUBSYS_VENDOR_ID	0x8086
+#define IFCVF_SUBSYS_DEVICE_ID	0x001A
+
+#define IFCVF_SUPPORTED_FEATURES \
+		((1ULL << VIRTIO_NET_F_MAC)			| \
+		 (1ULL << VIRTIO_F_ANY_LAYOUT)			| \
+		 (1ULL << VIRTIO_F_VERSION_1)			| \
+		 (1ULL << VIRTIO_F_ORDER_PLATFORM)		| \
+		 (1ULL << VIRTIO_F_IOMMU_PLATFORM)		| \
+		 (1ULL << VIRTIO_NET_F_MRG_RXBUF))
+
+/* Only one queue pair for now. */
+#define IFCVF_MAX_QUEUE_PAIRS	1
+
+#define IFCVF_QUEUE_ALIGNMENT	PAGE_SIZE
+#define IFCVF_QUEUE_MAX		32768
+#define IFCVF_MSI_CONFIG_OFF	0
+#define IFCVF_MSI_QUEUE_OFF	1
+#define IFCVF_PCI_MAX_RESOURCE	6
+
+#define IFCVF_LM_CFG_SIZE		0x40
+#define IFCVF_LM_RING_STATE_OFFSET	0x20
+#define IFCVF_LM_BAR			4
+
+#define IFCVF_ERR(pdev, fmt, ...)	dev_err(&pdev->dev, fmt, ##__VA_ARGS__)
+#define IFCVF_DBG(pdev, fmt, ...)	dev_dbg(&pdev->dev, fmt, ##__VA_ARGS__)
+#define IFCVF_INFO(pdev, fmt, ...)	dev_info(&pdev->dev, fmt, ##__VA_ARGS__)
+
+#define ifcvf_private_to_vf(adapter) \
+	(&((struct ifcvf_adapter *)adapter)->vf)
+
+#define IFCVF_MAX_INTR (IFCVF_MAX_QUEUE_PAIRS * 2 + 1)
+
+struct vring_info {
+	u64 desc;
+	u64 avail;
+	u64 used;
+	u16 size;
+	u16 last_avail_idx;
+	bool ready;
+	void __iomem *notify_addr;
+	u32 irq;
+	struct vdpa_callback cb;
+	char msix_name[256];
+};
+
+struct ifcvf_hw {
+	u8 __iomem *isr;
+	/* Live migration */
+	u8 __iomem *lm_cfg;
+	u16 nr_vring;
+	/* Notification bar number */
+	u8 notify_bar;
+	/* Notificaiton bar address */
+	void __iomem *notify_base;
+	u32 notify_off_multiplier;
+	u64 req_features;
+	struct virtio_pci_common_cfg __iomem *common_cfg;
+	void __iomem *net_cfg;
+	struct vring_info vring[IFCVF_MAX_QUEUE_PAIRS * 2];
+	void __iomem * const *base;
+};
+
+struct ifcvf_adapter {
+	struct vdpa_device vdpa;
+	struct pci_dev *pdev;
+	struct ifcvf_hw vf;
+};
+
+struct ifcvf_vring_lm_cfg {
+	u32 idx_addr[2];
+	u8 reserved[IFCVF_LM_CFG_SIZE - 8];
+};
+
+struct ifcvf_lm_cfg {
+	u8 reserved[IFCVF_LM_RING_STATE_OFFSET];
+	struct ifcvf_vring_lm_cfg vring_lm_cfg[IFCVF_MAX_QUEUE_PAIRS];
+};
+
+int ifcvf_init_hw(struct ifcvf_hw *hw, struct pci_dev *dev);
+int ifcvf_start_hw(struct ifcvf_hw *hw);
+void ifcvf_stop_hw(struct ifcvf_hw *hw);
+void ifcvf_notify_queue(struct ifcvf_hw *hw, u16 qid);
+void ifcvf_read_net_config(struct ifcvf_hw *hw, u64 offset,
+			   void *dst, int length);
+void ifcvf_write_net_config(struct ifcvf_hw *hw, u64 offset,
+			    const void *src, int length);
+u8 ifcvf_get_status(struct ifcvf_hw *hw);
+void ifcvf_set_status(struct ifcvf_hw *hw, u8 status);
+void io_write64_twopart(u64 val, u32 *lo, u32 *hi);
+void ifcvf_reset(struct ifcvf_hw *hw);
+u64 ifcvf_get_features(struct ifcvf_hw *hw);
+u64 ifcvf_get_vq_state(struct ifcvf_hw *hw, u16 qid);
+int ifcvf_set_vq_state(struct ifcvf_hw *hw, u16 qid, u64 num);
+struct ifcvf_adapter *vf_to_adapter(struct ifcvf_hw *hw);
+#endif /* _IFCVF_H_ */

drivers/vdpa/ifcvf/ifcvf_main.c

@@ -0,0 +1,435 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Intel IFC VF NIC driver for virtio dataplane offloading
+ *
+ * Copyright (C) 2020 Intel Corporation.
+ *
+ * Author: Zhu Lingshan <lingshan.zhu@intel.com>
+ *
+ */
+
+#include <linux/interrupt.h>
+#include <linux/module.h>
+#include <linux/pci.h>
+#include <linux/sysfs.h>
+#include "ifcvf_base.h"
+
+#define VERSION_STRING  "0.1"
+#define DRIVER_AUTHOR   "Intel Corporation"
+#define IFCVF_DRIVER_NAME       "ifcvf"
+
+static irqreturn_t ifcvf_intr_handler(int irq, void *arg)
+{
+	struct vring_info *vring = arg;
+
+	if (vring->cb.callback)
+		return vring->cb.callback(vring->cb.private);
+
+	return IRQ_HANDLED;
+}
+
+static int ifcvf_start_datapath(void *private)
+{
+	struct ifcvf_hw *vf = ifcvf_private_to_vf(private);
+	struct ifcvf_adapter *ifcvf;
+	u8 status;
+	int ret;
+
+	ifcvf = vf_to_adapter(vf);
+	vf->nr_vring = IFCVF_MAX_QUEUE_PAIRS * 2;
+	ret = ifcvf_start_hw(vf);
+	if (ret < 0) {
+		status = ifcvf_get_status(vf);
+		status |= VIRTIO_CONFIG_S_FAILED;
+		ifcvf_set_status(vf, status);
+	}
+
+	return ret;
+}
+
+static int ifcvf_stop_datapath(void *private)
+{
+	struct ifcvf_hw *vf = ifcvf_private_to_vf(private);
+	int i;
+
+	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++)
+		vf->vring[i].cb.callback = NULL;
+
+	ifcvf_stop_hw(vf);
+
+	return 0;
+}
+
+static void ifcvf_reset_vring(struct ifcvf_adapter *adapter)
+{
+	struct ifcvf_hw *vf = ifcvf_private_to_vf(adapter);
+	int i;
+
+	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
+		vf->vring[i].last_avail_idx = 0;
+		vf->vring[i].desc = 0;
+		vf->vring[i].avail = 0;
+		vf->vring[i].used = 0;
+		vf->vring[i].ready = 0;
+		vf->vring[i].cb.callback = NULL;
+		vf->vring[i].cb.private = NULL;
+	}
+
+	ifcvf_reset(vf);
+}
+
+static struct ifcvf_adapter *vdpa_to_adapter(struct vdpa_device *vdpa_dev)
+{
+	return container_of(vdpa_dev, struct ifcvf_adapter, vdpa);
+}
+
+static struct ifcvf_hw *vdpa_to_vf(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_adapter *adapter = vdpa_to_adapter(vdpa_dev);
+
+	return &adapter->vf;
+}
+
+static u64 ifcvf_vdpa_get_features(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+	u64 features;
+
+	features = ifcvf_get_features(vf) & IFCVF_SUPPORTED_FEATURES;
+
+	return features;
+}
+
+static int ifcvf_vdpa_set_features(struct vdpa_device *vdpa_dev, u64 features)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->req_features = features;
+
+	return 0;
+}
+
+static u8 ifcvf_vdpa_get_status(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return ifcvf_get_status(vf);
+}
+
+static void ifcvf_vdpa_set_status(struct vdpa_device *vdpa_dev, u8 status)
+{
+	struct ifcvf_adapter *adapter;
+	struct ifcvf_hw *vf;
+
+	vf  = vdpa_to_vf(vdpa_dev);
+	adapter = dev_get_drvdata(vdpa_dev->dev.parent);
+
+	if (status == 0) {
+		ifcvf_stop_datapath(adapter);
+		ifcvf_reset_vring(adapter);
+		return;
+	}
+
+	if (status & VIRTIO_CONFIG_S_DRIVER_OK) {
+		if (ifcvf_start_datapath(adapter) < 0)
+			IFCVF_ERR(adapter->pdev,
+				  "Failed to set ifcvf vdpa  status %u\n",
+				  status);
+	}
+
+	ifcvf_set_status(vf, status);
+}
+
+static u16 ifcvf_vdpa_get_vq_num_max(struct vdpa_device *vdpa_dev)
+{
+	return IFCVF_QUEUE_MAX;
+}
+
+static u64 ifcvf_vdpa_get_vq_state(struct vdpa_device *vdpa_dev, u16 qid)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return ifcvf_get_vq_state(vf, qid);
+}
+
+static int ifcvf_vdpa_set_vq_state(struct vdpa_device *vdpa_dev, u16 qid,
+				   u64 num)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return ifcvf_set_vq_state(vf, qid, num);
+}
+
+static void ifcvf_vdpa_set_vq_cb(struct vdpa_device *vdpa_dev, u16 qid,
+				 struct vdpa_callback *cb)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].cb = *cb;
+}
+
+static void ifcvf_vdpa_set_vq_ready(struct vdpa_device *vdpa_dev,
+				    u16 qid, bool ready)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].ready = ready;
+}
+
+static bool ifcvf_vdpa_get_vq_ready(struct vdpa_device *vdpa_dev, u16 qid)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return vf->vring[qid].ready;
+}
+
+static void ifcvf_vdpa_set_vq_num(struct vdpa_device *vdpa_dev, u16 qid,
+				  u32 num)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].size = num;
+}
+
+static int ifcvf_vdpa_set_vq_address(struct vdpa_device *vdpa_dev, u16 qid,
+				     u64 desc_area, u64 driver_area,
+				     u64 device_area)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	vf->vring[qid].desc = desc_area;
+	vf->vring[qid].avail = driver_area;
+	vf->vring[qid].used = device_area;
+
+	return 0;
+}
+
+static void ifcvf_vdpa_kick_vq(struct vdpa_device *vdpa_dev, u16 qid)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	ifcvf_notify_queue(vf, qid);
+}
+
+static u32 ifcvf_vdpa_get_generation(struct vdpa_device *vdpa_dev)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	return ioread8(&vf->common_cfg->config_generation);
+}
+
+static u32 ifcvf_vdpa_get_device_id(struct vdpa_device *vdpa_dev)
+{
+	return VIRTIO_ID_NET;
+}
+
+static u32 ifcvf_vdpa_get_vendor_id(struct vdpa_device *vdpa_dev)
+{
+	return IFCVF_SUBSYS_VENDOR_ID;
+}
+
+static u16 ifcvf_vdpa_get_vq_align(struct vdpa_device *vdpa_dev)
+{
+	return IFCVF_QUEUE_ALIGNMENT;
+}
+
+static void ifcvf_vdpa_get_config(struct vdpa_device *vdpa_dev,
+				  unsigned int offset,
+				  void *buf, unsigned int len)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	WARN_ON(offset + len > sizeof(struct virtio_net_config));
+	ifcvf_read_net_config(vf, offset, buf, len);
+}
+
+static void ifcvf_vdpa_set_config(struct vdpa_device *vdpa_dev,
+				  unsigned int offset, const void *buf,
+				  unsigned int len)
+{
+	struct ifcvf_hw *vf = vdpa_to_vf(vdpa_dev);
+
+	WARN_ON(offset + len > sizeof(struct virtio_net_config));
+	ifcvf_write_net_config(vf, offset, buf, len);
+}
+
+static void ifcvf_vdpa_set_config_cb(struct vdpa_device *vdpa_dev,
+				     struct vdpa_callback *cb)
+{
+	/* We don't support config interrupt */
+}
+
+/*
+ * IFCVF currently does't have on-chip IOMMU, so not
+ * implemented set_map()/dma_map()/dma_unmap()
+ */
+static const struct vdpa_config_ops ifc_vdpa_ops = {
+	.get_features	= ifcvf_vdpa_get_features,
+	.set_features	= ifcvf_vdpa_set_features,
+	.get_status	= ifcvf_vdpa_get_status,
+	.set_status	= ifcvf_vdpa_set_status,
+	.get_vq_num_max	= ifcvf_vdpa_get_vq_num_max,
+	.get_vq_state	= ifcvf_vdpa_get_vq_state,
+	.set_vq_state	= ifcvf_vdpa_set_vq_state,
+	.set_vq_cb	= ifcvf_vdpa_set_vq_cb,
+	.set_vq_ready	= ifcvf_vdpa_set_vq_ready,
+	.get_vq_ready	= ifcvf_vdpa_get_vq_ready,
+	.set_vq_num	= ifcvf_vdpa_set_vq_num,
+	.set_vq_address	= ifcvf_vdpa_set_vq_address,
+	.kick_vq	= ifcvf_vdpa_kick_vq,
+	.get_generation	= ifcvf_vdpa_get_generation,
+	.get_device_id	= ifcvf_vdpa_get_device_id,
+	.get_vendor_id	= ifcvf_vdpa_get_vendor_id,
+	.get_vq_align	= ifcvf_vdpa_get_vq_align,
+	.get_config	= ifcvf_vdpa_get_config,
+	.set_config	= ifcvf_vdpa_set_config,
+	.set_config_cb  = ifcvf_vdpa_set_config_cb,
+};
+
+static int ifcvf_request_irq(struct ifcvf_adapter *adapter)
+{
+	struct pci_dev *pdev = adapter->pdev;
+	struct ifcvf_hw *vf = &adapter->vf;
+	int vector, i, ret, irq;
+
+
+	for (i = 0; i < IFCVF_MAX_QUEUE_PAIRS * 2; i++) {
+		snprintf(vf->vring[i].msix_name, 256, "ifcvf[%s]-%d\n",
+			 pci_name(pdev), i);
+		vector = i + IFCVF_MSI_QUEUE_OFF;
+		irq = pci_irq_vector(pdev, vector);
+		ret = devm_request_irq(&pdev->dev, irq,
+				       ifcvf_intr_handler, 0,
+				       vf->vring[i].msix_name,
+				       &vf->vring[i]);
+		if (ret) {
+			IFCVF_ERR(pdev,
+				  "Failed to request irq for vq %d\n", i);
+			return ret;
+		}
+		vf->vring[i].irq = irq;
+	}
+
+	return 0;
+}
+
+static void ifcvf_free_irq_vectors(void *data)
+{
+	pci_free_irq_vectors(data);
+}
+
+static int ifcvf_probe(struct pci_dev *pdev, const struct pci_device_id *id)
+{
+	struct device *dev = &pdev->dev;
+	struct ifcvf_adapter *adapter;
+	struct ifcvf_hw *vf;
+	int ret;
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to enable device\n");
+		return ret;
+	}
+
+	ret = pcim_iomap_regions(pdev, BIT(0) | BIT(2) | BIT(4),
+				 IFCVF_DRIVER_NAME);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request MMIO region\n");
+		return ret;
+	}
+
+	ret = pci_set_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (ret) {
+		IFCVF_ERR(pdev, "No usable DMA confiugration\n");
+		return ret;
+	}
+
+	ret = pci_set_consistent_dma_mask(pdev, DMA_BIT_MASK(64));
+	if (ret) {
+		IFCVF_ERR(pdev,
+			  "No usable coherent DMA confiugration\n");
+		return ret;
+	}
+
+	ret = pci_alloc_irq_vectors(pdev, IFCVF_MAX_INTR,
+				    IFCVF_MAX_INTR, PCI_IRQ_MSIX);
+	if (ret < 0) {
+		IFCVF_ERR(pdev, "Failed to alloc irq vectors\n");
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(dev, ifcvf_free_irq_vectors, pdev);
+	if (ret) {
+		IFCVF_ERR(pdev,
+			  "Failed for adding devres for freeing irq vectors\n");
+		return ret;
+	}
+
+	adapter = vdpa_alloc_device(struct ifcvf_adapter, vdpa,
+				    dev, &ifc_vdpa_ops);
+	if (adapter == NULL) {
+		IFCVF_ERR(pdev, "Failed to allocate vDPA structure");
+		return -ENOMEM;
+	}
+
+	pci_set_master(pdev);
+	pci_set_drvdata(pdev, adapter);
+
+	vf = &adapter->vf;
+	vf->base = pcim_iomap_table(pdev);
+
+	adapter->pdev = pdev;
+	adapter->vdpa.dma_dev = &pdev->dev;
+
+	ret = ifcvf_request_irq(adapter);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to request MSI-X irq\n");
+		goto err;
+	}
+
+	ret = ifcvf_init_hw(vf, pdev);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to init IFCVF hw\n");
+		goto err;
+	}
+
+	ret = vdpa_register_device(&adapter->vdpa);
+	if (ret) {
+		IFCVF_ERR(pdev, "Failed to register ifcvf to vdpa bus");
+		goto err;
+	}
+
+	return 0;
+
+err:
+	put_device(&adapter->vdpa.dev);
+	return ret;
+}
+
+static void ifcvf_remove(struct pci_dev *pdev)
+{
+	struct ifcvf_adapter *adapter = pci_get_drvdata(pdev);
+
+	vdpa_unregister_device(&adapter->vdpa);
+}
+
+static struct pci_device_id ifcvf_pci_ids[] = {
+	{ PCI_DEVICE_SUB(IFCVF_VENDOR_ID,
+		IFCVF_DEVICE_ID,
+		IFCVF_SUBSYS_VENDOR_ID,
+		IFCVF_SUBSYS_DEVICE_ID) },
+	{ 0 },
+};
+MODULE_DEVICE_TABLE(pci, ifcvf_pci_ids);
+
+static struct pci_driver ifcvf_driver = {
+	.name     = IFCVF_DRIVER_NAME,
+	.id_table = ifcvf_pci_ids,
+	.probe    = ifcvf_probe,
+	.remove   = ifcvf_remove,
+};
+
+module_pci_driver(ifcvf_driver);
+
+MODULE_LICENSE("GPL v2");
+MODULE_VERSION(VERSION_STRING);

drivers/vdpa/vdpa.c

@@ -0,0 +1,180 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * vDPA bus.
+ *
+ * Copyright (c) 2020, Red Hat. All rights reserved.
+ *     Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/idr.h>
+#include <linux/slab.h>
+#include <linux/vdpa.h>
+
+static DEFINE_IDA(vdpa_index_ida);
+
+static int vdpa_dev_probe(struct device *d)
+{
+	struct vdpa_device *vdev = dev_to_vdpa(d);
+	struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver);
+	int ret = 0;
+
+	if (drv && drv->probe)
+		ret = drv->probe(vdev);
+
+	return ret;
+}
+
+static int vdpa_dev_remove(struct device *d)
+{
+	struct vdpa_device *vdev = dev_to_vdpa(d);
+	struct vdpa_driver *drv = drv_to_vdpa(vdev->dev.driver);
+
+	if (drv && drv->remove)
+		drv->remove(vdev);
+
+	return 0;
+}
+
+static struct bus_type vdpa_bus = {
+	.name  = "vdpa",
+	.probe = vdpa_dev_probe,
+	.remove = vdpa_dev_remove,
+};
+
+static void vdpa_release_dev(struct device *d)
+{
+	struct vdpa_device *vdev = dev_to_vdpa(d);
+	const struct vdpa_config_ops *ops = vdev->config;
+
+	if (ops->free)
+		ops->free(vdev);
+
+	ida_simple_remove(&vdpa_index_ida, vdev->index);
+	kfree(vdev);
+}
+
+/**
+ * __vdpa_alloc_device - allocate and initilaize a vDPA device
+ * This allows driver to some prepartion after device is
+ * initialized but before registered.
+ * @parent: the parent device
+ * @config: the bus operations that is supported by this device
+ * @size: size of the parent structure that contains private data
+ *
+ * Drvier should use vdap_alloc_device() wrapper macro instead of
+ * using this directly.
+ *
+ * Returns an error when parent/config/dma_dev is not set or fail to get
+ * ida.
+ */
+struct vdpa_device *__vdpa_alloc_device(struct device *parent,
+					const struct vdpa_config_ops *config,
+					size_t size)
+{
+	struct vdpa_device *vdev;
+	int err = -EINVAL;
+
+	if (!config)
+		goto err;
+
+	if (!!config->dma_map != !!config->dma_unmap)
+		goto err;
+
+	err = -ENOMEM;
+	vdev = kzalloc(size, GFP_KERNEL);
+	if (!vdev)
+		goto err;
+
+	err = ida_simple_get(&vdpa_index_ida, 0, 0, GFP_KERNEL);
+	if (err < 0)
+		goto err_ida;
+
+	vdev->dev.bus = &vdpa_bus;
+	vdev->dev.parent = parent;
+	vdev->dev.release = vdpa_release_dev;
+	vdev->index = err;
+	vdev->config = config;
+
+	err = dev_set_name(&vdev->dev, "vdpa%u", vdev->index);
+	if (err)
+		goto err_name;
+
+	device_initialize(&vdev->dev);
+
+	return vdev;
+
+err_name:
+	ida_simple_remove(&vdpa_index_ida, vdev->index);
+err_ida:
+	kfree(vdev);
+err:
+	return ERR_PTR(err);
+}
+EXPORT_SYMBOL_GPL(__vdpa_alloc_device);
+
+/**
+ * vdpa_register_device - register a vDPA device
+ * Callers must have a succeed call of vdpa_init_device() before.
+ * @vdev: the vdpa device to be registered to vDPA bus
+ *
+ * Returns an error when fail to add to vDPA bus
+ */
+int vdpa_register_device(struct vdpa_device *vdev)
+{
+	return device_add(&vdev->dev);
+}
+EXPORT_SYMBOL_GPL(vdpa_register_device);
+
+/**
+ * vdpa_unregister_device - unregister a vDPA device
+ * @vdev: the vdpa device to be unregisted from vDPA bus
+ */
+void vdpa_unregister_device(struct vdpa_device *vdev)
+{
+	device_unregister(&vdev->dev);
+}
+EXPORT_SYMBOL_GPL(vdpa_unregister_device);
+
+/**
+ * __vdpa_register_driver - register a vDPA device driver
+ * @drv: the vdpa device driver to be registered
+ * @owner: module owner of the driver
+ *
+ * Returns an err when fail to do the registration
+ */
+int __vdpa_register_driver(struct vdpa_driver *drv, struct module *owner)
+{
+	drv->driver.bus = &vdpa_bus;
+	drv->driver.owner = owner;
+
+	return driver_register(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(__vdpa_register_driver);
+
+/**
+ * vdpa_unregister_driver - unregister a vDPA device driver
+ * @drv: the vdpa device driver to be unregistered
+ */
+void vdpa_unregister_driver(struct vdpa_driver *drv)
+{
+	driver_unregister(&drv->driver);
+}
+EXPORT_SYMBOL_GPL(vdpa_unregister_driver);
+
+static int vdpa_init(void)
+{
+	return bus_register(&vdpa_bus);
+}
+
+static void __exit vdpa_exit(void)
+{
+	bus_unregister(&vdpa_bus);
+	ida_destroy(&vdpa_index_ida);
+}
+core_initcall(vdpa_init);
+module_exit(vdpa_exit);
+
+MODULE_AUTHOR("Jason Wang <jasowang@redhat.com>");
+MODULE_LICENSE("GPL v2");

drivers/vdpa/vdpa_sim/Makefile

@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_VDPA_SIM) += vdpa_sim.o

drivers/vdpa/vdpa_sim/vdpa_sim.c

@@ -0,0 +1,629 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VDPA networking device simulator.
+ *
+ * Copyright (c) 2020, Red Hat Inc. All rights reserved.
+ *     Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/fs.h>
+#include <linux/poll.h>
+#include <linux/slab.h>
+#include <linux/sched.h>
+#include <linux/wait.h>
+#include <linux/uuid.h>
+#include <linux/iommu.h>
+#include <linux/dma-mapping.h>
+#include <linux/sysfs.h>
+#include <linux/file.h>
+#include <linux/etherdevice.h>
+#include <linux/vringh.h>
+#include <linux/vdpa.h>
+#include <linux/vhost_iotlb.h>
+#include <uapi/linux/virtio_config.h>
+#include <uapi/linux/virtio_net.h>
+
+#define DRV_VERSION  "0.1"
+#define DRV_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define DRV_DESC     "vDPA Device Simulator"
+#define DRV_LICENSE  "GPL v2"
+
+struct vdpasim_virtqueue {
+	struct vringh vring;
+	struct vringh_kiov iov;
+	unsigned short head;
+	bool ready;
+	u64 desc_addr;
+	u64 device_addr;
+	u64 driver_addr;
+	u32 num;
+	void *private;
+	irqreturn_t (*cb)(void *data);
+};
+
+#define VDPASIM_QUEUE_ALIGN PAGE_SIZE
+#define VDPASIM_QUEUE_MAX 256
+#define VDPASIM_DEVICE_ID 0x1
+#define VDPASIM_VENDOR_ID 0
+#define VDPASIM_VQ_NUM 0x2
+#define VDPASIM_NAME "vdpasim-netdev"
+
+static u64 vdpasim_features = (1ULL << VIRTIO_F_ANY_LAYOUT) |
+			      (1ULL << VIRTIO_F_VERSION_1)  |
+			      (1ULL << VIRTIO_F_IOMMU_PLATFORM);
+
+/* State of each vdpasim device */
+struct vdpasim {
+	struct vdpa_device vdpa;
+	struct vdpasim_virtqueue vqs[2];
+	struct work_struct work;
+	/* spinlock to synchronize virtqueue state */
+	spinlock_t lock;
+	struct virtio_net_config config;
+	struct vhost_iotlb *iommu;
+	void *buffer;
+	u32 status;
+	u32 generation;
+	u64 features;
+};
+
+static struct vdpasim *vdpasim_dev;
+
+static struct vdpasim *vdpa_to_sim(struct vdpa_device *vdpa)
+{
+	return container_of(vdpa, struct vdpasim, vdpa);
+}
+
+static struct vdpasim *dev_to_sim(struct device *dev)
+{
+	struct vdpa_device *vdpa = dev_to_vdpa(dev);
+
+	return vdpa_to_sim(vdpa);
+}
+
+static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
+{
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+	int ret;
+
+	ret = vringh_init_iotlb(&vq->vring, vdpasim_features,
+				VDPASIM_QUEUE_MAX, false,
+				(struct vring_desc *)(uintptr_t)vq->desc_addr,
+				(struct vring_avail *)
+				(uintptr_t)vq->driver_addr,
+				(struct vring_used *)
+				(uintptr_t)vq->device_addr);
+}
+
+static void vdpasim_vq_reset(struct vdpasim_virtqueue *vq)
+{
+	vq->ready = 0;
+	vq->desc_addr = 0;
+	vq->driver_addr = 0;
+	vq->device_addr = 0;
+	vq->cb = NULL;
+	vq->private = NULL;
+	vringh_init_iotlb(&vq->vring, vdpasim_features, VDPASIM_QUEUE_MAX,
+			  false, NULL, NULL, NULL);
+}
+
+static void vdpasim_reset(struct vdpasim *vdpasim)
+{
+	int i;
+
+	for (i = 0; i < VDPASIM_VQ_NUM; i++)
+		vdpasim_vq_reset(&vdpasim->vqs[i]);
+
+	vhost_iotlb_reset(vdpasim->iommu);
+
+	vdpasim->features = 0;
+	vdpasim->status = 0;
+	++vdpasim->generation;
+}
+
+static void vdpasim_work(struct work_struct *work)
+{
+	struct vdpasim *vdpasim = container_of(work, struct
+						 vdpasim, work);
+	struct vdpasim_virtqueue *txq = &vdpasim->vqs[1];
+	struct vdpasim_virtqueue *rxq = &vdpasim->vqs[0];
+	size_t read, write, total_write;
+	int err;
+	int pkts = 0;
+
+	spin_lock(&vdpasim->lock);
+
+	if (!(vdpasim->status & VIRTIO_CONFIG_S_DRIVER_OK))
+		goto out;
+
+	if (!txq->ready || !rxq->ready)
+		goto out;
+
+	while (true) {
+		total_write = 0;
+		err = vringh_getdesc_iotlb(&txq->vring, &txq->iov, NULL,
+					   &txq->head, GFP_ATOMIC);
+		if (err <= 0)
+			break;
+
+		err = vringh_getdesc_iotlb(&rxq->vring, NULL, &rxq->iov,
+					   &rxq->head, GFP_ATOMIC);
+		if (err <= 0) {
+			vringh_complete_iotlb(&txq->vring, txq->head, 0);
+			break;
+		}
+
+		while (true) {
+			read = vringh_iov_pull_iotlb(&txq->vring, &txq->iov,
+						     vdpasim->buffer,
+						     PAGE_SIZE);
+			if (read <= 0)
+				break;
+
+			write = vringh_iov_push_iotlb(&rxq->vring, &rxq->iov,
+						      vdpasim->buffer, read);
+			if (write <= 0)
+				break;
+
+			total_write += write;
+		}
+
+		/* Make sure data is wrote before advancing index */
+		smp_wmb();
+
+		vringh_complete_iotlb(&txq->vring, txq->head, 0);
+		vringh_complete_iotlb(&rxq->vring, rxq->head, total_write);
+
+		/* Make sure used is visible before rasing the interrupt. */
+		smp_wmb();
+
+		local_bh_disable();
+		if (txq->cb)
+			txq->cb(txq->private);
+		if (rxq->cb)
+			rxq->cb(rxq->private);
+		local_bh_enable();
+
+		if (++pkts > 4) {
+			schedule_work(&vdpasim->work);
+			goto out;
+		}
+	}
+
+out:
+	spin_unlock(&vdpasim->lock);
+}
+
+static int dir_to_perm(enum dma_data_direction dir)
+{
+	int perm = -EFAULT;
+
+	switch (dir) {
+	case DMA_FROM_DEVICE:
+		perm = VHOST_MAP_WO;
+		break;
+	case DMA_TO_DEVICE:
+		perm = VHOST_MAP_RO;
+		break;
+	case DMA_BIDIRECTIONAL:
+		perm = VHOST_MAP_RW;
+		break;
+	default:
+		break;
+	}
+
+	return perm;
+}
+
+static dma_addr_t vdpasim_map_page(struct device *dev, struct page *page,
+				   unsigned long offset, size_t size,
+				   enum dma_data_direction dir,
+				   unsigned long attrs)
+{
+	struct vdpasim *vdpasim = dev_to_sim(dev);
+	struct vhost_iotlb *iommu = vdpasim->iommu;
+	u64 pa = (page_to_pfn(page) << PAGE_SHIFT) + offset;
+	int ret, perm = dir_to_perm(dir);
+
+	if (perm < 0)
+		return DMA_MAPPING_ERROR;
+
+	/* For simplicity, use identical mapping to avoid e.g iova
+	 * allocator.
+	 */
+	ret = vhost_iotlb_add_range(iommu, pa, pa + size - 1,
+				    pa, dir_to_perm(dir));
+	if (ret)
+		return DMA_MAPPING_ERROR;
+
+	return (dma_addr_t)(pa);
+}
+
+static void vdpasim_unmap_page(struct device *dev, dma_addr_t dma_addr,
+			       size_t size, enum dma_data_direction dir,
+			       unsigned long attrs)
+{
+	struct vdpasim *vdpasim = dev_to_sim(dev);
+	struct vhost_iotlb *iommu = vdpasim->iommu;
+
+	vhost_iotlb_del_range(iommu, (u64)dma_addr,
+			      (u64)dma_addr + size - 1);
+}
+
+static void *vdpasim_alloc_coherent(struct device *dev, size_t size,
+				    dma_addr_t *dma_addr, gfp_t flag,
+				    unsigned long attrs)
+{
+	struct vdpasim *vdpasim = dev_to_sim(dev);
+	struct vhost_iotlb *iommu = vdpasim->iommu;
+	void *addr = kmalloc(size, flag);
+	int ret;
+
+	if (!addr)
+		*dma_addr = DMA_MAPPING_ERROR;
+	else {
+		u64 pa = virt_to_phys(addr);
+
+		ret = vhost_iotlb_add_range(iommu, (u64)pa,
+					    (u64)pa + size - 1,
+					    pa, VHOST_MAP_RW);
+		if (ret) {
+			*dma_addr = DMA_MAPPING_ERROR;
+			kfree(addr);
+			addr = NULL;
+		} else
+			*dma_addr = (dma_addr_t)pa;
+	}
+
+	return addr;
+}
+
+static void vdpasim_free_coherent(struct device *dev, size_t size,
+				  void *vaddr, dma_addr_t dma_addr,
+				  unsigned long attrs)
+{
+	struct vdpasim *vdpasim = dev_to_sim(dev);
+	struct vhost_iotlb *iommu = vdpasim->iommu;
+
+	vhost_iotlb_del_range(iommu, (u64)dma_addr,
+			      (u64)dma_addr + size - 1);
+	kfree(phys_to_virt((uintptr_t)dma_addr));
+}
+
+static const struct dma_map_ops vdpasim_dma_ops = {
+	.map_page = vdpasim_map_page,
+	.unmap_page = vdpasim_unmap_page,
+	.alloc = vdpasim_alloc_coherent,
+	.free = vdpasim_free_coherent,
+};
+
+static const struct vdpa_config_ops vdpasim_net_config_ops;
+
+static struct vdpasim *vdpasim_create(void)
+{
+	struct virtio_net_config *config;
+	struct vdpasim *vdpasim;
+	struct device *dev;
+	int ret = -ENOMEM;
+
+	vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL,
+				    &vdpasim_net_config_ops);
+	if (!vdpasim)
+		goto err_alloc;
+
+	INIT_WORK(&vdpasim->work, vdpasim_work);
+	spin_lock_init(&vdpasim->lock);
+
+	dev = &vdpasim->vdpa.dev;
+	dev->coherent_dma_mask = DMA_BIT_MASK(64);
+	set_dma_ops(dev, &vdpasim_dma_ops);
+
+	vdpasim->iommu = vhost_iotlb_alloc(2048, 0);
+	if (!vdpasim->iommu)
+		goto err_iommu;
+
+	vdpasim->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
+	if (!vdpasim->buffer)
+		goto err_iommu;
+
+	config = &vdpasim->config;
+	config->mtu = 1500;
+	config->status = VIRTIO_NET_S_LINK_UP;
+	eth_random_addr(config->mac);
+
+	vringh_set_iotlb(&vdpasim->vqs[0].vring, vdpasim->iommu);
+	vringh_set_iotlb(&vdpasim->vqs[1].vring, vdpasim->iommu);
+
+	vdpasim->vdpa.dma_dev = dev;
+	ret = vdpa_register_device(&vdpasim->vdpa);
+	if (ret)
+		goto err_iommu;
+
+	return vdpasim;
+
+err_iommu:
+	put_device(dev);
+err_alloc:
+	return ERR_PTR(ret);
+}
+
+static int vdpasim_set_vq_address(struct vdpa_device *vdpa, u16 idx,
+				  u64 desc_area, u64 driver_area,
+				  u64 device_area)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+
+	vq->desc_addr = desc_area;
+	vq->driver_addr = driver_area;
+	vq->device_addr = device_area;
+
+	return 0;
+}
+
+static void vdpasim_set_vq_num(struct vdpa_device *vdpa, u16 idx, u32 num)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+
+	vq->num = num;
+}
+
+static void vdpasim_kick_vq(struct vdpa_device *vdpa, u16 idx)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+
+	if (vq->ready)
+		schedule_work(&vdpasim->work);
+}
+
+static void vdpasim_set_vq_cb(struct vdpa_device *vdpa, u16 idx,
+			      struct vdpa_callback *cb)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+
+	vq->cb = cb->callback;
+	vq->private = cb->private;
+}
+
+static void vdpasim_set_vq_ready(struct vdpa_device *vdpa, u16 idx, bool ready)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+
+	spin_lock(&vdpasim->lock);
+	vq->ready = ready;
+	if (vq->ready)
+		vdpasim_queue_ready(vdpasim, idx);
+	spin_unlock(&vdpasim->lock);
+}
+
+static bool vdpasim_get_vq_ready(struct vdpa_device *vdpa, u16 idx)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+
+	return vq->ready;
+}
+
+static int vdpasim_set_vq_state(struct vdpa_device *vdpa, u16 idx, u64 state)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+	struct vringh *vrh = &vq->vring;
+
+	spin_lock(&vdpasim->lock);
+	vrh->last_avail_idx = state;
+	spin_unlock(&vdpasim->lock);
+
+	return 0;
+}
+
+static u64 vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
+	struct vringh *vrh = &vq->vring;
+
+	return vrh->last_avail_idx;
+}
+
+static u16 vdpasim_get_vq_align(struct vdpa_device *vdpa)
+{
+	return VDPASIM_QUEUE_ALIGN;
+}
+
+static u64 vdpasim_get_features(struct vdpa_device *vdpa)
+{
+	return vdpasim_features;
+}
+
+static int vdpasim_set_features(struct vdpa_device *vdpa, u64 features)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	/* DMA mapping must be done by driver */
+	if (!(features & (1ULL << VIRTIO_F_IOMMU_PLATFORM)))
+		return -EINVAL;
+
+	vdpasim->features = features & vdpasim_features;
+
+	return 0;
+}
+
+static void vdpasim_set_config_cb(struct vdpa_device *vdpa,
+				  struct vdpa_callback *cb)
+{
+	/* We don't support config interrupt */
+}
+
+static u16 vdpasim_get_vq_num_max(struct vdpa_device *vdpa)
+{
+	return VDPASIM_QUEUE_MAX;
+}
+
+static u32 vdpasim_get_device_id(struct vdpa_device *vdpa)
+{
+	return VDPASIM_DEVICE_ID;
+}
+
+static u32 vdpasim_get_vendor_id(struct vdpa_device *vdpa)
+{
+	return VDPASIM_VENDOR_ID;
+}
+
+static u8 vdpasim_get_status(struct vdpa_device *vdpa)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	u8 status;
+
+	spin_lock(&vdpasim->lock);
+	status = vdpasim->status;
+	spin_unlock(&vdpasim->lock);
+
+	return vdpasim->status;
+}
+
+static void vdpasim_set_status(struct vdpa_device *vdpa, u8 status)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	spin_lock(&vdpasim->lock);
+	vdpasim->status = status;
+	if (status == 0)
+		vdpasim_reset(vdpasim);
+	spin_unlock(&vdpasim->lock);
+}
+
+static void vdpasim_get_config(struct vdpa_device *vdpa, unsigned int offset,
+			     void *buf, unsigned int len)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	if (offset + len < sizeof(struct virtio_net_config))
+		memcpy(buf, &vdpasim->config + offset, len);
+}
+
+static void vdpasim_set_config(struct vdpa_device *vdpa, unsigned int offset,
+			     const void *buf, unsigned int len)
+{
+	/* No writable config supportted by vdpasim */
+}
+
+static u32 vdpasim_get_generation(struct vdpa_device *vdpa)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	return vdpasim->generation;
+}
+
+static int vdpasim_set_map(struct vdpa_device *vdpa,
+			   struct vhost_iotlb *iotlb)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+	struct vhost_iotlb_map *map;
+	u64 start = 0ULL, last = 0ULL - 1;
+	int ret;
+
+	vhost_iotlb_reset(vdpasim->iommu);
+
+	for (map = vhost_iotlb_itree_first(iotlb, start, last); map;
+	     map = vhost_iotlb_itree_next(map, start, last)) {
+		ret = vhost_iotlb_add_range(vdpasim->iommu, map->start,
+					    map->last, map->addr, map->perm);
+		if (ret)
+			goto err;
+	}
+	return 0;
+
+err:
+	vhost_iotlb_reset(vdpasim->iommu);
+	return ret;
+}
+
+static int vdpasim_dma_map(struct vdpa_device *vdpa, u64 iova, u64 size,
+			   u64 pa, u32 perm)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	return vhost_iotlb_add_range(vdpasim->iommu, iova,
+				     iova + size - 1, pa, perm);
+}
+
+static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	vhost_iotlb_del_range(vdpasim->iommu, iova, iova + size - 1);
+
+	return 0;
+}
+
+static void vdpasim_free(struct vdpa_device *vdpa)
+{
+	struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
+
+	cancel_work_sync(&vdpasim->work);
+	kfree(vdpasim->buffer);
+	if (vdpasim->iommu)
+		vhost_iotlb_free(vdpasim->iommu);
+}
+
+static const struct vdpa_config_ops vdpasim_net_config_ops = {
+	.set_vq_address         = vdpasim_set_vq_address,
+	.set_vq_num             = vdpasim_set_vq_num,
+	.kick_vq                = vdpasim_kick_vq,
+	.set_vq_cb              = vdpasim_set_vq_cb,
+	.set_vq_ready           = vdpasim_set_vq_ready,
+	.get_vq_ready           = vdpasim_get_vq_ready,
+	.set_vq_state           = vdpasim_set_vq_state,
+	.get_vq_state           = vdpasim_get_vq_state,
+	.get_vq_align           = vdpasim_get_vq_align,
+	.get_features           = vdpasim_get_features,
+	.set_features           = vdpasim_set_features,
+	.set_config_cb          = vdpasim_set_config_cb,
+	.get_vq_num_max         = vdpasim_get_vq_num_max,
+	.get_device_id          = vdpasim_get_device_id,
+	.get_vendor_id          = vdpasim_get_vendor_id,
+	.get_status             = vdpasim_get_status,
+	.set_status             = vdpasim_set_status,
+	.get_config             = vdpasim_get_config,
+	.set_config             = vdpasim_set_config,
+	.get_generation         = vdpasim_get_generation,
+	.set_map                = vdpasim_set_map,
+	.dma_map                = vdpasim_dma_map,
+	.dma_unmap              = vdpasim_dma_unmap,
+	.free                   = vdpasim_free,
+};
+
+static int __init vdpasim_dev_init(void)
+{
+	vdpasim_dev = vdpasim_create();
+
+	if (!IS_ERR(vdpasim_dev))
+		return 0;
+
+	return PTR_ERR(vdpasim_dev);
+}
+
+static void __exit vdpasim_dev_exit(void)
+{
+	struct vdpa_device *vdpa = &vdpasim_dev->vdpa;
+
+	vdpa_unregister_device(vdpa);
+}
+
+module_init(vdpasim_dev_init)
+module_exit(vdpasim_dev_exit)
+
+MODULE_VERSION(DRV_VERSION);
+MODULE_LICENSE(DRV_LICENSE);
+MODULE_AUTHOR(DRV_AUTHOR);
+MODULE_DESCRIPTION(DRV_DESC);

drivers/vhost/Kconfig

@@ -1,4 +1,29 @@
 # SPDX-License-Identifier: GPL-2.0-only
+config VHOST_IOTLB
+	tristate
+	help
+	  Generic IOTLB implementation for vhost and vringh.
+
+config VHOST_RING
+	tristate
+	select VHOST_IOTLB
+	help
+	  This option is selected by any driver which needs to access
+	  the host side of a virtio ring.
+
+config VHOST
+	tristate
+	select VHOST_IOTLB
+	help
+	  This option is selected by any driver which needs to access
+	  the core of vhost.
+
+menuconfig VHOST_MENU
+	bool "VHOST drivers"
+	default y
+
+if VHOST_MENU
+
 config VHOST_NET
 	tristate "Host kernel accelerator for virtio net"
 	depends on NET && EVENTFD && (TUN || !TUN) && (TAP || !TAP)
@@ -23,8 +48,8 @@ config VHOST_SCSI
 config VHOST_VSOCK
 	tristate "vhost virtio-vsock driver"
 	depends on VSOCKETS && EVENTFD
-	select VIRTIO_VSOCKETS_COMMON
 	select VHOST
+	select VIRTIO_VSOCKETS_COMMON
 	default n
 	---help---
 	This kernel module can be loaded in the host kernel to provide AF_VSOCK
@@ -34,11 +59,17 @@ config VHOST_VSOCK
 	To compile this driver as a module, choose M here: the module will be called
 	vhost_vsock.
 
-config VHOST
+config VHOST_VDPA
-	tristate
+	tristate "Vhost driver for vDPA-based backend"
-	---help---
+	depends on EVENTFD
-	  This option is selected by any driver which needs to access
+	select VHOST
-	  the core of vhost.
+	select VDPA
+	help
+	  This kernel module can be loaded in host kernel to accelerate
+	  guest virtio devices with the vDPA-based backends.
+
+	  To compile this driver as a module, choose M here: the module
+	  will be called vhost_vdpa.
 
 config VHOST_CROSS_ENDIAN_LEGACY
 	bool "Cross-endian support for vhost"
@@ -54,3 +85,5 @@ config VHOST_CROSS_ENDIAN_LEGACY
 	  adds some overhead, it is disabled by default.
 
 	  If unsure, say "N".
+
+endif

drivers/vhost/Kconfig.vringh

@@ -1,6 +0,0 @@
-# SPDX-License-Identifier: GPL-2.0-only
-config VHOST_RING
-	tristate
-	---help---
-	  This option is selected by any driver which needs to access
-	  the host side of a virtio ring.

drivers/vhost/Makefile

@@ -10,4 +10,10 @@ vhost_vsock-y := vsock.o
 
 obj-$(CONFIG_VHOST_RING) += vringh.o
 
+obj-$(CONFIG_VHOST_VDPA) += vhost_vdpa.o
+vhost_vdpa-y := vdpa.o
+
 obj-$(CONFIG_VHOST)	+= vhost.o
+
+obj-$(CONFIG_VHOST_IOTLB) += vhost_iotlb.o
+vhost_iotlb-y := iotlb.o

drivers/vhost/iotlb.c

@@ -0,0 +1,177 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/* Copyright (C) 2020 Red Hat, Inc.
+ * Author: Jason Wang <jasowang@redhat.com>
+ *
+ * IOTLB implementation for vhost.
+ */
+#include <linux/slab.h>
+#include <linux/vhost_iotlb.h>
+#include <linux/module.h>
+
+#define MOD_VERSION  "0.1"
+#define MOD_DESC     "VHOST IOTLB"
+#define MOD_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define MOD_LICENSE  "GPL v2"
+
+#define START(map) ((map)->start)
+#define LAST(map) ((map)->last)
+
+INTERVAL_TREE_DEFINE(struct vhost_iotlb_map,
+		     rb, __u64, __subtree_last,
+		     START, LAST, static inline, vhost_iotlb_itree);
+
+/**
+ * vhost_iotlb_map_free - remove a map node and free it
+ * @iotlb: the IOTLB
+ * @map: the map that want to be remove and freed
+ */
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map)
+{
+	vhost_iotlb_itree_remove(map, &iotlb->root);
+	list_del(&map->link);
+	kfree(map);
+	iotlb->nmaps--;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_map_free);
+
+/**
+ * vhost_iotlb_add_range - add a new range to vhost IOTLB
+ * @iotlb: the IOTLB
+ * @start: start of the IOVA range
+ * @last: last of IOVA range
+ * @addr: the address that is mapped to @start
+ * @perm: access permission of this range
+ *
+ * Returns an error last is smaller than start or memory allocation
+ * fails
+ */
+int vhost_iotlb_add_range(struct vhost_iotlb *iotlb,
+			  u64 start, u64 last,
+			  u64 addr, unsigned int perm)
+{
+	struct vhost_iotlb_map *map;
+
+	if (last < start)
+		return -EFAULT;
+
+	if (iotlb->limit &&
+	    iotlb->nmaps == iotlb->limit &&
+	    iotlb->flags & VHOST_IOTLB_FLAG_RETIRE) {
+		map = list_first_entry(&iotlb->list, typeof(*map), link);
+		vhost_iotlb_map_free(iotlb, map);
+	}
+
+	map = kmalloc(sizeof(*map), GFP_ATOMIC);
+	if (!map)
+		return -ENOMEM;
+
+	map->start = start;
+	map->size = last - start + 1;
+	map->last = last;
+	map->addr = addr;
+	map->perm = perm;
+
+	iotlb->nmaps++;
+	vhost_iotlb_itree_insert(map, &iotlb->root);
+
+	INIT_LIST_HEAD(&map->link);
+	list_add_tail(&map->link, &iotlb->list);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_add_range);
+
+/**
+ * vring_iotlb_del_range - delete overlapped ranges from vhost IOTLB
+ * @iotlb: the IOTLB
+ * @start: start of the IOVA range
+ * @last: last of IOVA range
+ */
+void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last)
+{
+	struct vhost_iotlb_map *map;
+
+	while ((map = vhost_iotlb_itree_iter_first(&iotlb->root,
+						   start, last)))
+		vhost_iotlb_map_free(iotlb, map);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_del_range);
+
+/**
+ * vhost_iotlb_alloc - add a new vhost IOTLB
+ * @limit: maximum number of IOTLB entries
+ * @flags: VHOST_IOTLB_FLAG_XXX
+ *
+ * Returns an error is memory allocation fails
+ */
+struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags)
+{
+	struct vhost_iotlb *iotlb = kzalloc(sizeof(*iotlb), GFP_KERNEL);
+
+	if (!iotlb)
+		return NULL;
+
+	iotlb->root = RB_ROOT_CACHED;
+	iotlb->limit = limit;
+	iotlb->nmaps = 0;
+	iotlb->flags = flags;
+	INIT_LIST_HEAD(&iotlb->list);
+
+	return iotlb;
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_alloc);
+
+/**
+ * vhost_iotlb_reset - reset vhost IOTLB (free all IOTLB entries)
+ * @iotlb: the IOTLB to be reset
+ */
+void vhost_iotlb_reset(struct vhost_iotlb *iotlb)
+{
+	vhost_iotlb_del_range(iotlb, 0ULL, 0ULL - 1);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_reset);
+
+/**
+ * vhost_iotlb_free - reset and free vhost IOTLB
+ * @iotlb: the IOTLB to be freed
+ */
+void vhost_iotlb_free(struct vhost_iotlb *iotlb)
+{
+	if (iotlb) {
+		vhost_iotlb_reset(iotlb);
+		kfree(iotlb);
+	}
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_free);
+
+/**
+ * vhost_iotlb_itree_first - return the first overlapped range
+ * @iotlb: the IOTLB
+ * @start: start of IOVA range
+ * @end: end of IOVA range
+ */
+struct vhost_iotlb_map *
+vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last)
+{
+	return vhost_iotlb_itree_iter_first(&iotlb->root, start, last);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_itree_first);
+
+/**
+ * vhost_iotlb_itree_first - return the next overlapped range
+ * @iotlb: the IOTLB
+ * @start: start of IOVA range
+ * @end: end of IOVA range
+ */
+struct vhost_iotlb_map *
+vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last)
+{
+	return vhost_iotlb_itree_iter_next(map, start, last);
+}
+EXPORT_SYMBOL_GPL(vhost_iotlb_itree_next);
+
+MODULE_VERSION(MOD_VERSION);
+MODULE_DESCRIPTION(MOD_DESC);
+MODULE_AUTHOR(MOD_AUTHOR);
+MODULE_LICENSE(MOD_LICENSE);

drivers/vhost/net.c

@@ -1324,7 +1324,8 @@ static int vhost_net_open(struct inode *inode, struct file *f)
 	}
 	vhost_dev_init(dev, vqs, VHOST_NET_VQ_MAX,
 		       UIO_MAXIOV + VHOST_NET_BATCH,
-		       VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT);
+		       VHOST_NET_PKT_WEIGHT, VHOST_NET_WEIGHT,
+		       NULL);
 
 	vhost_poll_init(n->poll + VHOST_NET_VQ_TX, handle_tx_net, EPOLLOUT, dev);
 	vhost_poll_init(n->poll + VHOST_NET_VQ_RX, handle_rx_net, EPOLLIN, dev);
@@ -1586,7 +1587,7 @@ static long vhost_net_reset_owner(struct vhost_net *n)
 	struct socket *tx_sock = NULL;
 	struct socket *rx_sock = NULL;
 	long err;
-	struct vhost_umem *umem;
+	struct vhost_iotlb *umem;
 
 	mutex_lock(&n->dev.mutex);
 	err = vhost_dev_check_owner(&n->dev);

drivers/vhost/scsi.c

@@ -1628,7 +1628,7 @@ static int vhost_scsi_open(struct inode *inode, struct file *f)
 		vs->vqs[i].vq.handle_kick = vhost_scsi_handle_kick;
 	}
 	vhost_dev_init(&vs->dev, vqs, VHOST_SCSI_MAX_VQ, UIO_MAXIOV,
-		       VHOST_SCSI_WEIGHT, 0);
+		       VHOST_SCSI_WEIGHT, 0, NULL);
 
 	vhost_scsi_init_inflight(vs, NULL);
 

drivers/vhost/vdpa.c

@@ -0,0 +1,883 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (C) 2018-2020 Intel Corporation.
+ * Copyright (C) 2020 Red Hat, Inc.
+ *
+ * Author: Tiwei Bie <tiwei.bie@intel.com>
+ *         Jason Wang <jasowang@redhat.com>
+ *
+ * Thanks Michael S. Tsirkin for the valuable comments and
+ * suggestions.  And thanks to Cunming Liang and Zhihong Wang for all
+ * their supports.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/iommu.h>
+#include <linux/uuid.h>
+#include <linux/vdpa.h>
+#include <linux/nospec.h>
+#include <linux/vhost.h>
+#include <linux/virtio_net.h>
+
+#include "vhost.h"
+
+enum {
+	VHOST_VDPA_FEATURES =
+		(1ULL << VIRTIO_F_NOTIFY_ON_EMPTY) |
+		(1ULL << VIRTIO_F_ANY_LAYOUT) |
+		(1ULL << VIRTIO_F_VERSION_1) |
+		(1ULL << VIRTIO_F_IOMMU_PLATFORM) |
+		(1ULL << VIRTIO_F_RING_PACKED) |
+		(1ULL << VIRTIO_F_ORDER_PLATFORM) |
+		(1ULL << VIRTIO_RING_F_INDIRECT_DESC) |
+		(1ULL << VIRTIO_RING_F_EVENT_IDX),
+
+	VHOST_VDPA_NET_FEATURES = VHOST_VDPA_FEATURES |
+		(1ULL << VIRTIO_NET_F_CSUM) |
+		(1ULL << VIRTIO_NET_F_GUEST_CSUM) |
+		(1ULL << VIRTIO_NET_F_MTU) |
+		(1ULL << VIRTIO_NET_F_MAC) |
+		(1ULL << VIRTIO_NET_F_GUEST_TSO4) |
+		(1ULL << VIRTIO_NET_F_GUEST_TSO6) |
+		(1ULL << VIRTIO_NET_F_GUEST_ECN) |
+		(1ULL << VIRTIO_NET_F_GUEST_UFO) |
+		(1ULL << VIRTIO_NET_F_HOST_TSO4) |
+		(1ULL << VIRTIO_NET_F_HOST_TSO6) |
+		(1ULL << VIRTIO_NET_F_HOST_ECN) |
+		(1ULL << VIRTIO_NET_F_HOST_UFO) |
+		(1ULL << VIRTIO_NET_F_MRG_RXBUF) |
+		(1ULL << VIRTIO_NET_F_STATUS) |
+		(1ULL << VIRTIO_NET_F_SPEED_DUPLEX),
+};
+
+/* Currently, only network backend w/o multiqueue is supported. */
+#define VHOST_VDPA_VQ_MAX	2
+
+#define VHOST_VDPA_DEV_MAX (1U << MINORBITS)
+
+struct vhost_vdpa {
+	struct vhost_dev vdev;
+	struct iommu_domain *domain;
+	struct vhost_virtqueue *vqs;
+	struct completion completion;
+	struct vdpa_device *vdpa;
+	struct device dev;
+	struct cdev cdev;
+	atomic_t opened;
+	int nvqs;
+	int virtio_id;
+	int minor;
+};
+
+static DEFINE_IDA(vhost_vdpa_ida);
+
+static dev_t vhost_vdpa_major;
+
+static const u64 vhost_vdpa_features[] = {
+	[VIRTIO_ID_NET] = VHOST_VDPA_NET_FEATURES,
+};
+
+static void handle_vq_kick(struct vhost_work *work)
+{
+	struct vhost_virtqueue *vq = container_of(work, struct vhost_virtqueue,
+						  poll.work);
+	struct vhost_vdpa *v = container_of(vq->dev, struct vhost_vdpa, vdev);
+	const struct vdpa_config_ops *ops = v->vdpa->config;
+
+	ops->kick_vq(v->vdpa, vq - v->vqs);
+}
+
+static irqreturn_t vhost_vdpa_virtqueue_cb(void *private)
+{
+	struct vhost_virtqueue *vq = private;
+	struct eventfd_ctx *call_ctx = vq->call_ctx;
+
+	if (call_ctx)
+		eventfd_signal(call_ctx, 1);
+
+	return IRQ_HANDLED;
+}
+
+static void vhost_vdpa_reset(struct vhost_vdpa *v)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	ops->set_status(vdpa, 0);
+}
+
+static long vhost_vdpa_get_device_id(struct vhost_vdpa *v, u8 __user *argp)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	u32 device_id;
+
+	device_id = ops->get_device_id(vdpa);
+
+	if (copy_to_user(argp, &device_id, sizeof(device_id)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long vhost_vdpa_get_status(struct vhost_vdpa *v, u8 __user *statusp)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	u8 status;
+
+	status = ops->get_status(vdpa);
+
+	if (copy_to_user(statusp, &status, sizeof(status)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long vhost_vdpa_set_status(struct vhost_vdpa *v, u8 __user *statusp)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	u8 status;
+
+	if (copy_from_user(&status, statusp, sizeof(status)))
+		return -EFAULT;
+
+	/*
+	 * Userspace shouldn't remove status bits unless reset the
+	 * status to 0.
+	 */
+	if (status != 0 && (ops->get_status(vdpa) & ~status) != 0)
+		return -EINVAL;
+
+	ops->set_status(vdpa, status);
+
+	return 0;
+}
+
+static int vhost_vdpa_config_validate(struct vhost_vdpa *v,
+				      struct vhost_vdpa_config *c)
+{
+	long size = 0;
+
+	switch (v->virtio_id) {
+	case VIRTIO_ID_NET:
+		size = sizeof(struct virtio_net_config);
+		break;
+	}
+
+	if (c->len == 0)
+		return -EINVAL;
+
+	if (c->len > size - c->off)
+		return -E2BIG;
+
+	return 0;
+}
+
+static long vhost_vdpa_get_config(struct vhost_vdpa *v,
+				  struct vhost_vdpa_config __user *c)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct vhost_vdpa_config config;
+	unsigned long size = offsetof(struct vhost_vdpa_config, buf);
+	u8 *buf;
+
+	if (copy_from_user(&config, c, size))
+		return -EFAULT;
+	if (vhost_vdpa_config_validate(v, &config))
+		return -EINVAL;
+	buf = kvzalloc(config.len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	ops->get_config(vdpa, config.off, buf, config.len);
+
+	if (copy_to_user(c->buf, buf, config.len)) {
+		kvfree(buf);
+		return -EFAULT;
+	}
+
+	kvfree(buf);
+	return 0;
+}
+
+static long vhost_vdpa_set_config(struct vhost_vdpa *v,
+				  struct vhost_vdpa_config __user *c)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct vhost_vdpa_config config;
+	unsigned long size = offsetof(struct vhost_vdpa_config, buf);
+	u8 *buf;
+
+	if (copy_from_user(&config, c, size))
+		return -EFAULT;
+	if (vhost_vdpa_config_validate(v, &config))
+		return -EINVAL;
+	buf = kvzalloc(config.len, GFP_KERNEL);
+	if (!buf)
+		return -ENOMEM;
+
+	if (copy_from_user(buf, c->buf, config.len)) {
+		kvfree(buf);
+		return -EFAULT;
+	}
+
+	ops->set_config(vdpa, config.off, buf, config.len);
+
+	kvfree(buf);
+	return 0;
+}
+
+static long vhost_vdpa_get_features(struct vhost_vdpa *v, u64 __user *featurep)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	u64 features;
+
+	features = ops->get_features(vdpa);
+	features &= vhost_vdpa_features[v->virtio_id];
+
+	if (copy_to_user(featurep, &features, sizeof(features)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long vhost_vdpa_set_features(struct vhost_vdpa *v, u64 __user *featurep)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	u64 features;
+
+	/*
+	 * It's not allowed to change the features after they have
+	 * been negotiated.
+	 */
+	if (ops->get_status(vdpa) & VIRTIO_CONFIG_S_FEATURES_OK)
+		return -EBUSY;
+
+	if (copy_from_user(&features, featurep, sizeof(features)))
+		return -EFAULT;
+
+	if (features & ~vhost_vdpa_features[v->virtio_id])
+		return -EINVAL;
+
+	if (ops->set_features(vdpa, features))
+		return -EINVAL;
+
+	return 0;
+}
+
+static long vhost_vdpa_get_vring_num(struct vhost_vdpa *v, u16 __user *argp)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	u16 num;
+
+	num = ops->get_vq_num_max(vdpa);
+
+	if (copy_to_user(argp, &num, sizeof(num)))
+		return -EFAULT;
+
+	return 0;
+}
+
+static long vhost_vdpa_vring_ioctl(struct vhost_vdpa *v, unsigned int cmd,
+				   void __user *argp)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct vdpa_callback cb;
+	struct vhost_virtqueue *vq;
+	struct vhost_vring_state s;
+	u8 status;
+	u32 idx;
+	long r;
+
+	r = get_user(idx, (u32 __user *)argp);
+	if (r < 0)
+		return r;
+
+	if (idx >= v->nvqs)
+		return -ENOBUFS;
+
+	idx = array_index_nospec(idx, v->nvqs);
+	vq = &v->vqs[idx];
+
+	status = ops->get_status(vdpa);
+
+	if (cmd == VHOST_VDPA_SET_VRING_ENABLE) {
+		if (copy_from_user(&s, argp, sizeof(s)))
+			return -EFAULT;
+		ops->set_vq_ready(vdpa, idx, s.num);
+		return 0;
+	}
+
+	if (cmd == VHOST_GET_VRING_BASE)
+		vq->last_avail_idx = ops->get_vq_state(v->vdpa, idx);
+
+	r = vhost_vring_ioctl(&v->vdev, cmd, argp);
+	if (r)
+		return r;
+
+	switch (cmd) {
+	case VHOST_SET_VRING_ADDR:
+		if (ops->set_vq_address(vdpa, idx,
+					(u64)(uintptr_t)vq->desc,
+					(u64)(uintptr_t)vq->avail,
+					(u64)(uintptr_t)vq->used))
+			r = -EINVAL;
+		break;
+
+	case VHOST_SET_VRING_BASE:
+		if (ops->set_vq_state(vdpa, idx, vq->last_avail_idx))
+			r = -EINVAL;
+		break;
+
+	case VHOST_SET_VRING_CALL:
+		if (vq->call_ctx) {
+			cb.callback = vhost_vdpa_virtqueue_cb;
+			cb.private = vq;
+		} else {
+			cb.callback = NULL;
+			cb.private = NULL;
+		}
+		ops->set_vq_cb(vdpa, idx, &cb);
+		break;
+
+	case VHOST_SET_VRING_NUM:
+		ops->set_vq_num(vdpa, idx, vq->num);
+		break;
+	}
+
+	return r;
+}
+
+static long vhost_vdpa_unlocked_ioctl(struct file *filep,
+				      unsigned int cmd, unsigned long arg)
+{
+	struct vhost_vdpa *v = filep->private_data;
+	struct vhost_dev *d = &v->vdev;
+	void __user *argp = (void __user *)arg;
+	long r;
+
+	mutex_lock(&d->mutex);
+
+	switch (cmd) {
+	case VHOST_VDPA_GET_DEVICE_ID:
+		r = vhost_vdpa_get_device_id(v, argp);
+		break;
+	case VHOST_VDPA_GET_STATUS:
+		r = vhost_vdpa_get_status(v, argp);
+		break;
+	case VHOST_VDPA_SET_STATUS:
+		r = vhost_vdpa_set_status(v, argp);
+		break;
+	case VHOST_VDPA_GET_CONFIG:
+		r = vhost_vdpa_get_config(v, argp);
+		break;
+	case VHOST_VDPA_SET_CONFIG:
+		r = vhost_vdpa_set_config(v, argp);
+		break;
+	case VHOST_GET_FEATURES:
+		r = vhost_vdpa_get_features(v, argp);
+		break;
+	case VHOST_SET_FEATURES:
+		r = vhost_vdpa_set_features(v, argp);
+		break;
+	case VHOST_VDPA_GET_VRING_NUM:
+		r = vhost_vdpa_get_vring_num(v, argp);
+		break;
+	case VHOST_SET_LOG_BASE:
+	case VHOST_SET_LOG_FD:
+		r = -ENOIOCTLCMD;
+		break;
+	default:
+		r = vhost_dev_ioctl(&v->vdev, cmd, argp);
+		if (r == -ENOIOCTLCMD)
+			r = vhost_vdpa_vring_ioctl(v, cmd, argp);
+		break;
+	}
+
+	mutex_unlock(&d->mutex);
+	return r;
+}
+
+static void vhost_vdpa_iotlb_unmap(struct vhost_vdpa *v, u64 start, u64 last)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vhost_iotlb *iotlb = dev->iotlb;
+	struct vhost_iotlb_map *map;
+	struct page *page;
+	unsigned long pfn, pinned;
+
+	while ((map = vhost_iotlb_itree_first(iotlb, start, last)) != NULL) {
+		pinned = map->size >> PAGE_SHIFT;
+		for (pfn = map->addr >> PAGE_SHIFT;
+		     pinned > 0; pfn++, pinned--) {
+			page = pfn_to_page(pfn);
+			if (map->perm & VHOST_ACCESS_WO)
+				set_page_dirty_lock(page);
+			unpin_user_page(page);
+		}
+		atomic64_sub(map->size >> PAGE_SHIFT, &dev->mm->pinned_vm);
+		vhost_iotlb_map_free(iotlb, map);
+	}
+}
+
+static void vhost_vdpa_iotlb_free(struct vhost_vdpa *v)
+{
+	struct vhost_dev *dev = &v->vdev;
+
+	vhost_vdpa_iotlb_unmap(v, 0ULL, 0ULL - 1);
+	kfree(dev->iotlb);
+	dev->iotlb = NULL;
+}
+
+static int perm_to_iommu_flags(u32 perm)
+{
+	int flags = 0;
+
+	switch (perm) {
+	case VHOST_ACCESS_WO:
+		flags |= IOMMU_WRITE;
+		break;
+	case VHOST_ACCESS_RO:
+		flags |= IOMMU_READ;
+		break;
+	case VHOST_ACCESS_RW:
+		flags |= (IOMMU_WRITE | IOMMU_READ);
+		break;
+	default:
+		WARN(1, "invalidate vhost IOTLB permission\n");
+		break;
+	}
+
+	return flags | IOMMU_CACHE;
+}
+
+static int vhost_vdpa_map(struct vhost_vdpa *v,
+			  u64 iova, u64 size, u64 pa, u32 perm)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	int r = 0;
+
+	r = vhost_iotlb_add_range(dev->iotlb, iova, iova + size - 1,
+				  pa, perm);
+	if (r)
+		return r;
+
+	if (ops->dma_map)
+		r = ops->dma_map(vdpa, iova, size, pa, perm);
+	else if (ops->set_map)
+		r = ops->set_map(vdpa, dev->iotlb);
+	else
+		r = iommu_map(v->domain, iova, pa, size,
+			      perm_to_iommu_flags(perm));
+
+	return r;
+}
+
+static void vhost_vdpa_unmap(struct vhost_vdpa *v, u64 iova, u64 size)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	vhost_vdpa_iotlb_unmap(v, iova, iova + size - 1);
+
+	if (ops->dma_map)
+		ops->dma_unmap(vdpa, iova, size);
+	else if (ops->set_map)
+		ops->set_map(vdpa, dev->iotlb);
+	else
+		iommu_unmap(v->domain, iova, size);
+}
+
+static int vhost_vdpa_process_iotlb_update(struct vhost_vdpa *v,
+					   struct vhost_iotlb_msg *msg)
+{
+	struct vhost_dev *dev = &v->vdev;
+	struct vhost_iotlb *iotlb = dev->iotlb;
+	struct page **page_list;
+	unsigned long list_size = PAGE_SIZE / sizeof(struct page *);
+	unsigned int gup_flags = FOLL_LONGTERM;
+	unsigned long npages, cur_base, map_pfn, last_pfn = 0;
+	unsigned long locked, lock_limit, pinned, i;
+	u64 iova = msg->iova;
+	int ret = 0;
+
+	if (vhost_iotlb_itree_first(iotlb, msg->iova,
+				    msg->iova + msg->size - 1))
+		return -EEXIST;
+
+	page_list = (struct page **) __get_free_page(GFP_KERNEL);
+	if (!page_list)
+		return -ENOMEM;
+
+	if (msg->perm & VHOST_ACCESS_WO)
+		gup_flags |= FOLL_WRITE;
+
+	npages = PAGE_ALIGN(msg->size + (iova & ~PAGE_MASK)) >> PAGE_SHIFT;
+	if (!npages)
+		return -EINVAL;
+
+	down_read(&dev->mm->mmap_sem);
+
+	locked = atomic64_add_return(npages, &dev->mm->pinned_vm);
+	lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT;
+
+	if (locked > lock_limit) {
+		ret = -ENOMEM;
+		goto out;
+	}
+
+	cur_base = msg->uaddr & PAGE_MASK;
+	iova &= PAGE_MASK;
+
+	while (npages) {
+		pinned = min_t(unsigned long, npages, list_size);
+		ret = pin_user_pages(cur_base, pinned,
+				     gup_flags, page_list, NULL);
+		if (ret != pinned)
+			goto out;
+
+		if (!last_pfn)
+			map_pfn = page_to_pfn(page_list[0]);
+
+		for (i = 0; i < ret; i++) {
+			unsigned long this_pfn = page_to_pfn(page_list[i]);
+			u64 csize;
+
+			if (last_pfn && (this_pfn != last_pfn + 1)) {
+				/* Pin a contiguous chunk of memory */
+				csize = (last_pfn - map_pfn + 1) << PAGE_SHIFT;
+				if (vhost_vdpa_map(v, iova, csize,
+						   map_pfn << PAGE_SHIFT,
+						   msg->perm))
+					goto out;
+				map_pfn = this_pfn;
+				iova += csize;
+			}
+
+			last_pfn = this_pfn;
+		}
+
+		cur_base += ret << PAGE_SHIFT;
+		npages -= ret;
+	}
+
+	/* Pin the rest chunk */
+	ret = vhost_vdpa_map(v, iova, (last_pfn - map_pfn + 1) << PAGE_SHIFT,
+			     map_pfn << PAGE_SHIFT, msg->perm);
+out:
+	if (ret) {
+		vhost_vdpa_unmap(v, msg->iova, msg->size);
+		atomic64_sub(npages, &dev->mm->pinned_vm);
+	}
+	up_read(&dev->mm->mmap_sem);
+	free_page((unsigned long)page_list);
+	return ret;
+}
+
+static int vhost_vdpa_process_iotlb_msg(struct vhost_dev *dev,
+					struct vhost_iotlb_msg *msg)
+{
+	struct vhost_vdpa *v = container_of(dev, struct vhost_vdpa, vdev);
+	int r = 0;
+
+	r = vhost_dev_check_owner(dev);
+	if (r)
+		return r;
+
+	switch (msg->type) {
+	case VHOST_IOTLB_UPDATE:
+		r = vhost_vdpa_process_iotlb_update(v, msg);
+		break;
+	case VHOST_IOTLB_INVALIDATE:
+		vhost_vdpa_unmap(v, msg->iova, msg->size);
+		break;
+	default:
+		r = -EINVAL;
+		break;
+	}
+
+	return r;
+}
+
+static ssize_t vhost_vdpa_chr_write_iter(struct kiocb *iocb,
+					 struct iov_iter *from)
+{
+	struct file *file = iocb->ki_filp;
+	struct vhost_vdpa *v = file->private_data;
+	struct vhost_dev *dev = &v->vdev;
+
+	return vhost_chr_write_iter(dev, from);
+}
+
+static int vhost_vdpa_alloc_domain(struct vhost_vdpa *v)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct device *dma_dev = vdpa_get_dma_dev(vdpa);
+	struct bus_type *bus;
+	int ret;
+
+	/* Device want to do DMA by itself */
+	if (ops->set_map || ops->dma_map)
+		return 0;
+
+	bus = dma_dev->bus;
+	if (!bus)
+		return -EFAULT;
+
+	if (!iommu_capable(bus, IOMMU_CAP_CACHE_COHERENCY))
+		return -ENOTSUPP;
+
+	v->domain = iommu_domain_alloc(bus);
+	if (!v->domain)
+		return -EIO;
+
+	ret = iommu_attach_device(v->domain, dma_dev);
+	if (ret)
+		goto err_attach;
+
+	return 0;
+
+err_attach:
+	iommu_domain_free(v->domain);
+	return ret;
+}
+
+static void vhost_vdpa_free_domain(struct vhost_vdpa *v)
+{
+	struct vdpa_device *vdpa = v->vdpa;
+	struct device *dma_dev = vdpa_get_dma_dev(vdpa);
+
+	if (v->domain) {
+		iommu_detach_device(v->domain, dma_dev);
+		iommu_domain_free(v->domain);
+	}
+
+	v->domain = NULL;
+}
+
+static int vhost_vdpa_open(struct inode *inode, struct file *filep)
+{
+	struct vhost_vdpa *v;
+	struct vhost_dev *dev;
+	struct vhost_virtqueue **vqs;
+	int nvqs, i, r, opened;
+
+	v = container_of(inode->i_cdev, struct vhost_vdpa, cdev);
+	if (!v)
+		return -ENODEV;
+
+	opened = atomic_cmpxchg(&v->opened, 0, 1);
+	if (opened)
+		return -EBUSY;
+
+	nvqs = v->nvqs;
+	vhost_vdpa_reset(v);
+
+	vqs = kmalloc_array(nvqs, sizeof(*vqs), GFP_KERNEL);
+	if (!vqs) {
+		r = -ENOMEM;
+		goto err;
+	}
+
+	dev = &v->vdev;
+	for (i = 0; i < nvqs; i++) {
+		vqs[i] = &v->vqs[i];
+		vqs[i]->handle_kick = handle_vq_kick;
+	}
+	vhost_dev_init(dev, vqs, nvqs, 0, 0, 0,
+		       vhost_vdpa_process_iotlb_msg);
+
+	dev->iotlb = vhost_iotlb_alloc(0, 0);
+	if (!dev->iotlb) {
+		r = -ENOMEM;
+		goto err_init_iotlb;
+	}
+
+	r = vhost_vdpa_alloc_domain(v);
+	if (r)
+		goto err_init_iotlb;
+
+	filep->private_data = v;
+
+	return 0;
+
+err_init_iotlb:
+	vhost_dev_cleanup(&v->vdev);
+err:
+	atomic_dec(&v->opened);
+	return r;
+}
+
+static int vhost_vdpa_release(struct inode *inode, struct file *filep)
+{
+	struct vhost_vdpa *v = filep->private_data;
+	struct vhost_dev *d = &v->vdev;
+
+	mutex_lock(&d->mutex);
+	filep->private_data = NULL;
+	vhost_vdpa_reset(v);
+	vhost_dev_stop(&v->vdev);
+	vhost_vdpa_iotlb_free(v);
+	vhost_vdpa_free_domain(v);
+	vhost_dev_cleanup(&v->vdev);
+	kfree(v->vdev.vqs);
+	mutex_unlock(&d->mutex);
+
+	atomic_dec(&v->opened);
+	complete(&v->completion);
+
+	return 0;
+}
+
+static const struct file_operations vhost_vdpa_fops = {
+	.owner		= THIS_MODULE,
+	.open		= vhost_vdpa_open,
+	.release	= vhost_vdpa_release,
+	.write_iter	= vhost_vdpa_chr_write_iter,
+	.unlocked_ioctl	= vhost_vdpa_unlocked_ioctl,
+	.compat_ioctl	= compat_ptr_ioctl,
+};
+
+static void vhost_vdpa_release_dev(struct device *device)
+{
+	struct vhost_vdpa *v =
+	       container_of(device, struct vhost_vdpa, dev);
+
+	ida_simple_remove(&vhost_vdpa_ida, v->minor);
+	kfree(v->vqs);
+	kfree(v);
+}
+
+static int vhost_vdpa_probe(struct vdpa_device *vdpa)
+{
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct vhost_vdpa *v;
+	int minor, nvqs = VHOST_VDPA_VQ_MAX;
+	int r;
+
+	/* Currently, we only accept the network devices. */
+	if (ops->get_device_id(vdpa) != VIRTIO_ID_NET)
+		return -ENOTSUPP;
+
+	v = kzalloc(sizeof(*v), GFP_KERNEL | __GFP_RETRY_MAYFAIL);
+	if (!v)
+		return -ENOMEM;
+
+	minor = ida_simple_get(&vhost_vdpa_ida, 0,
+			       VHOST_VDPA_DEV_MAX, GFP_KERNEL);
+	if (minor < 0) {
+		kfree(v);
+		return minor;
+	}
+
+	atomic_set(&v->opened, 0);
+	v->minor = minor;
+	v->vdpa = vdpa;
+	v->nvqs = nvqs;
+	v->virtio_id = ops->get_device_id(vdpa);
+
+	device_initialize(&v->dev);
+	v->dev.release = vhost_vdpa_release_dev;
+	v->dev.parent = &vdpa->dev;
+	v->dev.devt = MKDEV(MAJOR(vhost_vdpa_major), minor);
+	v->vqs = kmalloc_array(nvqs, sizeof(struct vhost_virtqueue),
+			       GFP_KERNEL);
+	if (!v->vqs) {
+		r = -ENOMEM;
+		goto err;
+	}
+
+	r = dev_set_name(&v->dev, "vhost-vdpa-%u", minor);
+	if (r)
+		goto err;
+
+	cdev_init(&v->cdev, &vhost_vdpa_fops);
+	v->cdev.owner = THIS_MODULE;
+
+	r = cdev_device_add(&v->cdev, &v->dev);
+	if (r)
+		goto err;
+
+	init_completion(&v->completion);
+	vdpa_set_drvdata(vdpa, v);
+
+	return 0;
+
+err:
+	put_device(&v->dev);
+	return r;
+}
+
+static void vhost_vdpa_remove(struct vdpa_device *vdpa)
+{
+	struct vhost_vdpa *v = vdpa_get_drvdata(vdpa);
+	int opened;
+
+	cdev_device_del(&v->cdev, &v->dev);
+
+	do {
+		opened = atomic_cmpxchg(&v->opened, 0, 1);
+		if (!opened)
+			break;
+		wait_for_completion(&v->completion);
+	} while (1);
+
+	put_device(&v->dev);
+}
+
+static struct vdpa_driver vhost_vdpa_driver = {
+	.driver = {
+		.name	= "vhost_vdpa",
+	},
+	.probe	= vhost_vdpa_probe,
+	.remove	= vhost_vdpa_remove,
+};
+
+static int __init vhost_vdpa_init(void)
+{
+	int r;
+
+	r = alloc_chrdev_region(&vhost_vdpa_major, 0, VHOST_VDPA_DEV_MAX,
+				"vhost-vdpa");
+	if (r)
+		goto err_alloc_chrdev;
+
+	r = vdpa_register_driver(&vhost_vdpa_driver);
+	if (r)
+		goto err_vdpa_register_driver;
+
+	return 0;
+
+err_vdpa_register_driver:
+	unregister_chrdev_region(vhost_vdpa_major, VHOST_VDPA_DEV_MAX);
+err_alloc_chrdev:
+	return r;
+}
+module_init(vhost_vdpa_init);
+
+static void __exit vhost_vdpa_exit(void)
+{
+	vdpa_unregister_driver(&vhost_vdpa_driver);
+	unregister_chrdev_region(vhost_vdpa_major, VHOST_VDPA_DEV_MAX);
+}
+module_exit(vhost_vdpa_exit);
+
+MODULE_VERSION("0.0.1");
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Intel Corporation");
+MODULE_DESCRIPTION("vDPA-based vhost backend for virtio");

drivers/vhost/vhost.c

@@ -50,10 +50,6 @@ enum {
 #define vhost_used_event(vq) ((__virtio16 __user *)&vq->avail->ring[vq->num])
 #define vhost_avail_event(vq) ((__virtio16 __user *)&vq->used->ring[vq->num])
 
-INTERVAL_TREE_DEFINE(struct vhost_umem_node,
-		     rb, __u64, __subtree_last,
-		     START, LAST, static inline, vhost_umem_interval_tree);
-
 #ifdef CONFIG_VHOST_CROSS_ENDIAN_LEGACY
 static void vhost_disable_cross_endian(struct vhost_virtqueue *vq)
 {
@@ -457,7 +453,9 @@ static size_t vhost_get_desc_size(struct vhost_virtqueue *vq,
 
 void vhost_dev_init(struct vhost_dev *dev,
 		    struct vhost_virtqueue **vqs, int nvqs,
-		    int iov_limit, int weight, int byte_weight)
+		    int iov_limit, int weight, int byte_weight,
+		    int (*msg_handler)(struct vhost_dev *dev,
+				       struct vhost_iotlb_msg *msg))
 {
 	struct vhost_virtqueue *vq;
 	int i;
@@ -473,6 +471,7 @@ void vhost_dev_init(struct vhost_dev *dev,
 	dev->iov_limit = iov_limit;
 	dev->weight = weight;
 	dev->byte_weight = byte_weight;
+	dev->msg_handler = msg_handler;
 	init_llist_head(&dev->work_list);
 	init_waitqueue_head(&dev->wait);
 	INIT_LIST_HEAD(&dev->read_list);
@@ -581,21 +580,25 @@ long vhost_dev_set_owner(struct vhost_dev *dev)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_set_owner);
 
-struct vhost_umem *vhost_dev_reset_owner_prepare(void)
+static struct vhost_iotlb *iotlb_alloc(void)
 {
-	return kvzalloc(sizeof(struct vhost_umem), GFP_KERNEL);
+	return vhost_iotlb_alloc(max_iotlb_entries,
+				 VHOST_IOTLB_FLAG_RETIRE);
+}
+
+struct vhost_iotlb *vhost_dev_reset_owner_prepare(void)
+{
+	return iotlb_alloc();
 }
 EXPORT_SYMBOL_GPL(vhost_dev_reset_owner_prepare);
 
 /* Caller should have device mutex */
-void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_umem *umem)
+void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *umem)
 {
 	int i;
 
 	vhost_dev_cleanup(dev);
 
-	/* Restore memory to default empty mapping. */
-	INIT_LIST_HEAD(&umem->umem_list);
 	dev->umem = umem;
 	/* We don't need VQ locks below since vhost_dev_cleanup makes sure
 	 * VQs aren't running.
@@ -618,28 +621,6 @@ void vhost_dev_stop(struct vhost_dev *dev)
 }
 EXPORT_SYMBOL_GPL(vhost_dev_stop);
 
-static void vhost_umem_free(struct vhost_umem *umem,
-			    struct vhost_umem_node *node)
-{
-	vhost_umem_interval_tree_remove(node, &umem->umem_tree);
-	list_del(&node->link);
-	kfree(node);
-	umem->numem--;
-}
-
-static void vhost_umem_clean(struct vhost_umem *umem)
-{
-	struct vhost_umem_node *node, *tmp;
-
-	if (!umem)
-		return;
-
-	list_for_each_entry_safe(node, tmp, &umem->umem_list, link)
-		vhost_umem_free(umem, node);
-
-	kvfree(umem);
-}
-
 static void vhost_clear_msg(struct vhost_dev *dev)
 {
 	struct vhost_msg_node *node, *n;
@@ -677,9 +658,9 @@ void vhost_dev_cleanup(struct vhost_dev *dev)
 		eventfd_ctx_put(dev->log_ctx);
 	dev->log_ctx = NULL;
 	/* No one will access memory at this point */
-	vhost_umem_clean(dev->umem);
+	vhost_iotlb_free(dev->umem);
 	dev->umem = NULL;
-	vhost_umem_clean(dev->iotlb);
+	vhost_iotlb_free(dev->iotlb);
 	dev->iotlb = NULL;
 	vhost_clear_msg(dev);
 	wake_up_interruptible_poll(&dev->wait, EPOLLIN | EPOLLRDNORM);
@@ -715,27 +696,26 @@ static bool vhost_overflow(u64 uaddr, u64 size)
 }
 
 /* Caller should have vq mutex and device mutex. */
-static bool vq_memory_access_ok(void __user *log_base, struct vhost_umem *umem,
+static bool vq_memory_access_ok(void __user *log_base, struct vhost_iotlb *umem,
 				int log_all)
 {
-	struct vhost_umem_node *node;
+	struct vhost_iotlb_map *map;
 
 	if (!umem)
 		return false;
 
-	list_for_each_entry(node, &umem->umem_list, link) {
+	list_for_each_entry(map, &umem->list, link) {
-		unsigned long a = node->userspace_addr;
+		unsigned long a = map->addr;
 
-		if (vhost_overflow(node->userspace_addr, node->size))
+		if (vhost_overflow(map->addr, map->size))
 			return false;
 
 
-		if (!access_ok((void __user *)a,
+		if (!access_ok((void __user *)a, map->size))
-				    node->size))
 			return false;
 		else if (log_all && !log_access_ok(log_base,
-						   node->start,
+						   map->start,
-						   node->size))
+						   map->size))
 			return false;
 	}
 	return true;
@@ -745,17 +725,17 @@ static inline void __user *vhost_vq_meta_fetch(struct vhost_virtqueue *vq,
 					       u64 addr, unsigned int size,
 					       int type)
 {
-	const struct vhost_umem_node *node = vq->meta_iotlb[type];
+	const struct vhost_iotlb_map *map = vq->meta_iotlb[type];
 
-	if (!node)
+	if (!map)
 		return NULL;
 
-	return (void *)(uintptr_t)(node->userspace_addr + addr - node->start);
+	return (void *)(uintptr_t)(map->addr + addr - map->start);
 }
 
 /* Can we switch to this memory table? */
 /* Caller should have device mutex but not vq mutex */
-static bool memory_access_ok(struct vhost_dev *d, struct vhost_umem *umem,
+static bool memory_access_ok(struct vhost_dev *d, struct vhost_iotlb *umem,
 			     int log_all)
 {
 	int i;
@@ -1020,47 +1000,6 @@ static inline int vhost_get_desc(struct vhost_virtqueue *vq,
 	return vhost_copy_from_user(vq, desc, vq->desc + idx, sizeof(*desc));
 }
 
-static int vhost_new_umem_range(struct vhost_umem *umem,
-				u64 start, u64 size, u64 end,
-				u64 userspace_addr, int perm)
-{
-	struct vhost_umem_node *tmp, *node;
-
-	if (!size)
-		return -EFAULT;
-
-	node = kmalloc(sizeof(*node), GFP_ATOMIC);
-	if (!node)
-		return -ENOMEM;
-
-	if (umem->numem == max_iotlb_entries) {
-		tmp = list_first_entry(&umem->umem_list, typeof(*tmp), link);
-		vhost_umem_free(umem, tmp);
-	}
-
-	node->start = start;
-	node->size = size;
-	node->last = end;
-	node->userspace_addr = userspace_addr;
-	node->perm = perm;
-	INIT_LIST_HEAD(&node->link);
-	list_add_tail(&node->link, &umem->umem_list);
-	vhost_umem_interval_tree_insert(node, &umem->umem_tree);
-	umem->numem++;
-
-	return 0;
-}
-
-static void vhost_del_umem_range(struct vhost_umem *umem,
-				 u64 start, u64 end)
-{
-	struct vhost_umem_node *node;
-
-	while ((node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
-							   start, end)))
-		vhost_umem_free(umem, node);
-}
-
 static void vhost_iotlb_notify_vq(struct vhost_dev *d,
 				  struct vhost_iotlb_msg *msg)
 {
@@ -1117,9 +1056,9 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 			break;
 		}
 		vhost_vq_meta_reset(dev);
-		if (vhost_new_umem_range(dev->iotlb, msg->iova, msg->size,
+		if (vhost_iotlb_add_range(dev->iotlb, msg->iova,
-					 msg->iova + msg->size - 1,
+					  msg->iova + msg->size - 1,
-					 msg->uaddr, msg->perm)) {
+					  msg->uaddr, msg->perm)) {
 			ret = -ENOMEM;
 			break;
 		}
@@ -1131,8 +1070,8 @@ static int vhost_process_iotlb_msg(struct vhost_dev *dev,
 			break;
 		}
 		vhost_vq_meta_reset(dev);
-		vhost_del_umem_range(dev->iotlb, msg->iova,
+		vhost_iotlb_del_range(dev->iotlb, msg->iova,
-				     msg->iova + msg->size - 1);
+				      msg->iova + msg->size - 1);
 		break;
 	default:
 		ret = -EINVAL;
@@ -1178,7 +1117,12 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 		ret = -EINVAL;
 		goto done;
 	}
-	if (vhost_process_iotlb_msg(dev, &msg)) {
+
+	if (dev->msg_handler)
+		ret = dev->msg_handler(dev, &msg);
+	else
+		ret = vhost_process_iotlb_msg(dev, &msg);
+	if (ret) {
 		ret = -EFAULT;
 		goto done;
 	}
@@ -1311,44 +1255,42 @@ static bool vq_access_ok(struct vhost_virtqueue *vq, unsigned int num,
 }
 
 static void vhost_vq_meta_update(struct vhost_virtqueue *vq,
-				 const struct vhost_umem_node *node,
+				 const struct vhost_iotlb_map *map,
 				 int type)
 {
 	int access = (type == VHOST_ADDR_USED) ?
 		     VHOST_ACCESS_WO : VHOST_ACCESS_RO;
 
-	if (likely(node->perm & access))
+	if (likely(map->perm & access))
-		vq->meta_iotlb[type] = node;
+		vq->meta_iotlb[type] = map;
 }
 
 static bool iotlb_access_ok(struct vhost_virtqueue *vq,
 			    int access, u64 addr, u64 len, int type)
 {
-	const struct vhost_umem_node *node;
+	const struct vhost_iotlb_map *map;
-	struct vhost_umem *umem = vq->iotlb;
+	struct vhost_iotlb *umem = vq->iotlb;
 	u64 s = 0, size, orig_addr = addr, last = addr + len - 1;
 
 	if (vhost_vq_meta_fetch(vq, addr, len, type))
 		return true;
 
 	while (len > s) {
-		node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
+		map = vhost_iotlb_itree_first(umem, addr, last);
-							   addr,
+		if (map == NULL || map->start > addr) {
-							   last);
-		if (node == NULL || node->start > addr) {
 			vhost_iotlb_miss(vq, addr, access);
 			return false;
-		} else if (!(node->perm & access)) {
+		} else if (!(map->perm & access)) {
 			/* Report the possible access violation by
 			 * request another translation from userspace.
 			 */
 			return false;
 		}
 
-		size = node->size - addr + node->start;
+		size = map->size - addr + map->start;
 
 		if (orig_addr == addr && size >= len)
-			vhost_vq_meta_update(vq, node, type);
+			vhost_vq_meta_update(vq, map, type);
 
 		s += size;
 		addr += size;
@@ -1364,12 +1306,12 @@ int vq_meta_prefetch(struct vhost_virtqueue *vq)
 	if (!vq->iotlb)
 		return 1;
 
-	return iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->desc,
+	return iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->desc,
 			       vhost_get_desc_size(vq, num), VHOST_ADDR_DESC) &&
-	       iotlb_access_ok(vq, VHOST_ACCESS_RO, (u64)(uintptr_t)vq->avail,
+	       iotlb_access_ok(vq, VHOST_MAP_RO, (u64)(uintptr_t)vq->avail,
 			       vhost_get_avail_size(vq, num),
 			       VHOST_ADDR_AVAIL) &&
-	       iotlb_access_ok(vq, VHOST_ACCESS_WO, (u64)(uintptr_t)vq->used,
+	       iotlb_access_ok(vq, VHOST_MAP_WO, (u64)(uintptr_t)vq->used,
 			       vhost_get_used_size(vq, num), VHOST_ADDR_USED);
 }
 EXPORT_SYMBOL_GPL(vq_meta_prefetch);
@@ -1408,25 +1350,11 @@ bool vhost_vq_access_ok(struct vhost_virtqueue *vq)
 }
 EXPORT_SYMBOL_GPL(vhost_vq_access_ok);
 
-static struct vhost_umem *vhost_umem_alloc(void)
-{
-	struct vhost_umem *umem = kvzalloc(sizeof(*umem), GFP_KERNEL);
-
-	if (!umem)
-		return NULL;
-
-	umem->umem_tree = RB_ROOT_CACHED;
-	umem->numem = 0;
-	INIT_LIST_HEAD(&umem->umem_list);
-
-	return umem;
-}
-
 static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 {
 	struct vhost_memory mem, *newmem;
 	struct vhost_memory_region *region;
-	struct vhost_umem *newumem, *oldumem;
+	struct vhost_iotlb *newumem, *oldumem;
 	unsigned long size = offsetof(struct vhost_memory, regions);
 	int i;
 
@@ -1448,7 +1376,7 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 		return -EFAULT;
 	}
 
-	newumem = vhost_umem_alloc();
+	newumem = iotlb_alloc();
 	if (!newumem) {
 		kvfree(newmem);
 		return -ENOMEM;
@@ -1457,13 +1385,12 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 	for (region = newmem->regions;
 	     region < newmem->regions + mem.nregions;
 	     region++) {
-		if (vhost_new_umem_range(newumem,
+		if (vhost_iotlb_add_range(newumem,
-					 region->guest_phys_addr,
+					  region->guest_phys_addr,
-					 region->memory_size,
+					  region->guest_phys_addr +
-					 region->guest_phys_addr +
+					  region->memory_size - 1,
-					 region->memory_size - 1,
+					  region->userspace_addr,
-					 region->userspace_addr,
+					  VHOST_MAP_RW))
-					 VHOST_ACCESS_RW))
 			goto err;
 	}
 
@@ -1481,11 +1408,11 @@ static long vhost_set_memory(struct vhost_dev *d, struct vhost_memory __user *m)
 	}
 
 	kvfree(newmem);
-	vhost_umem_clean(oldumem);
+	vhost_iotlb_free(oldumem);
 	return 0;
 
 err:
-	vhost_umem_clean(newumem);
+	vhost_iotlb_free(newumem);
 	kvfree(newmem);
 	return -EFAULT;
 }
@@ -1726,10 +1653,10 @@ EXPORT_SYMBOL_GPL(vhost_vring_ioctl);
 
 int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
 {
-	struct vhost_umem *niotlb, *oiotlb;
+	struct vhost_iotlb *niotlb, *oiotlb;
 	int i;
 
-	niotlb = vhost_umem_alloc();
+	niotlb = iotlb_alloc();
 	if (!niotlb)
 		return -ENOMEM;
 
@@ -1745,7 +1672,7 @@ int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled)
 		mutex_unlock(&vq->mutex);
 	}
 
-	vhost_umem_clean(oiotlb);
+	vhost_iotlb_free(oiotlb);
 
 	return 0;
 }
@@ -1875,8 +1802,8 @@ static int log_write(void __user *log_base,
 
 static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
 {
-	struct vhost_umem *umem = vq->umem;
+	struct vhost_iotlb *umem = vq->umem;
-	struct vhost_umem_node *u;
+	struct vhost_iotlb_map *u;
 	u64 start, end, l, min;
 	int r;
 	bool hit = false;
@@ -1886,16 +1813,15 @@ static int log_write_hva(struct vhost_virtqueue *vq, u64 hva, u64 len)
 		/* More than one GPAs can be mapped into a single HVA. So
 		 * iterate all possible umems here to be safe.
 		 */
-		list_for_each_entry(u, &umem->umem_list, link) {
+		list_for_each_entry(u, &umem->list, link) {
-			if (u->userspace_addr > hva - 1 + len ||
+			if (u->addr > hva - 1 + len ||
-			    u->userspace_addr - 1 + u->size < hva)
+			    u->addr - 1 + u->size < hva)
 				continue;
-			start = max(u->userspace_addr, hva);
+			start = max(u->addr, hva);
-			end = min(u->userspace_addr - 1 + u->size,
+			end = min(u->addr - 1 + u->size, hva - 1 + len);
-				  hva - 1 + len);
 			l = end - start + 1;
 			r = log_write(vq->log_base,
-				      u->start + start - u->userspace_addr,
+				      u->start + start - u->addr,
 				      l);
 			if (r < 0)
 				return r;
@@ -2046,9 +1972,9 @@ EXPORT_SYMBOL_GPL(vhost_vq_init_access);
 static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 			  struct iovec iov[], int iov_size, int access)
 {
-	const struct vhost_umem_node *node;
+	const struct vhost_iotlb_map *map;
 	struct vhost_dev *dev = vq->dev;
-	struct vhost_umem *umem = dev->iotlb ? dev->iotlb : dev->umem;
+	struct vhost_iotlb *umem = dev->iotlb ? dev->iotlb : dev->umem;
 	struct iovec *_iov;
 	u64 s = 0;
 	int ret = 0;
@@ -2060,25 +1986,24 @@ static int translate_desc(struct vhost_virtqueue *vq, u64 addr, u32 len,
 			break;
 		}
 
-		node = vhost_umem_interval_tree_iter_first(&umem->umem_tree,
+		map = vhost_iotlb_itree_first(umem, addr, addr + len - 1);
-							addr, addr + len - 1);
+		if (map == NULL || map->start > addr) {
-		if (node == NULL || node->start > addr) {
 			if (umem != dev->iotlb) {
 				ret = -EFAULT;
 				break;
 			}
 			ret = -EAGAIN;
 			break;
-		} else if (!(node->perm & access)) {
+		} else if (!(map->perm & access)) {
 			ret = -EPERM;
 			break;
 		}
 
 		_iov = iov + ret;
-		size = node->size - addr + node->start;
+		size = map->size - addr + map->start;
 		_iov->iov_len = min((u64)len - s, size);
 		_iov->iov_base = (void __user *)(unsigned long)
-			(node->userspace_addr + addr - node->start);
+				 (map->addr + addr - map->start);
 		s += size;
 		addr += size;
 		++ret;

drivers/vhost/vhost.h

@@ -12,6 +12,7 @@
 #include <linux/virtio_config.h>
 #include <linux/virtio_ring.h>
 #include <linux/atomic.h>
+#include <linux/vhost_iotlb.h>
 
 struct vhost_work;
 typedef void (*vhost_work_fn_t)(struct vhost_work *work);
@@ -52,27 +53,6 @@ struct vhost_log {
 	u64 len;
 };
 
-#define START(node) ((node)->start)
-#define LAST(node) ((node)->last)
-
-struct vhost_umem_node {
-	struct rb_node rb;
-	struct list_head link;
-	__u64 start;
-	__u64 last;
-	__u64 size;
-	__u64 userspace_addr;
-	__u32 perm;
-	__u32 flags_padding;
-	__u64 __subtree_last;
-};
-
-struct vhost_umem {
-	struct rb_root_cached umem_tree;
-	struct list_head umem_list;
-	int numem;
-};
-
 enum vhost_uaddr_type {
 	VHOST_ADDR_DESC = 0,
 	VHOST_ADDR_AVAIL = 1,
@@ -90,7 +70,7 @@ struct vhost_virtqueue {
 	struct vring_desc __user *desc;
 	struct vring_avail __user *avail;
 	struct vring_used __user *used;
-	const struct vhost_umem_node *meta_iotlb[VHOST_NUM_ADDRS];
+	const struct vhost_iotlb_map *meta_iotlb[VHOST_NUM_ADDRS];
 	struct file *kick;
 	struct eventfd_ctx *call_ctx;
 	struct eventfd_ctx *error_ctx;
@@ -128,8 +108,8 @@ struct vhost_virtqueue {
 	struct iovec *indirect;
 	struct vring_used_elem *heads;
 	/* Protected by virtqueue mutex. */
-	struct vhost_umem *umem;
+	struct vhost_iotlb *umem;
-	struct vhost_umem *iotlb;
+	struct vhost_iotlb *iotlb;
 	void *private_data;
 	u64 acked_features;
 	u64 acked_backend_features;
@@ -164,8 +144,8 @@ struct vhost_dev {
 	struct eventfd_ctx *log_ctx;
 	struct llist_head work_list;
 	struct task_struct *worker;
-	struct vhost_umem *umem;
+	struct vhost_iotlb *umem;
-	struct vhost_umem *iotlb;
+	struct vhost_iotlb *iotlb;
 	spinlock_t iotlb_lock;
 	struct list_head read_list;
 	struct list_head pending_list;
@@ -174,16 +154,20 @@ struct vhost_dev {
 	int weight;
 	int byte_weight;
 	u64 kcov_handle;
+	int (*msg_handler)(struct vhost_dev *dev,
+			   struct vhost_iotlb_msg *msg);
 };
 
 bool vhost_exceeds_weight(struct vhost_virtqueue *vq, int pkts, int total_len);
 void vhost_dev_init(struct vhost_dev *, struct vhost_virtqueue **vqs,
-		    int nvqs, int iov_limit, int weight, int byte_weight);
+		    int nvqs, int iov_limit, int weight, int byte_weight,
+		    int (*msg_handler)(struct vhost_dev *dev,
+				       struct vhost_iotlb_msg *msg));
 long vhost_dev_set_owner(struct vhost_dev *dev);
 bool vhost_dev_has_owner(struct vhost_dev *dev);
 long vhost_dev_check_owner(struct vhost_dev *);
-struct vhost_umem *vhost_dev_reset_owner_prepare(void);
+struct vhost_iotlb *vhost_dev_reset_owner_prepare(void);
-void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *);
+void vhost_dev_reset_owner(struct vhost_dev *dev, struct vhost_iotlb *iotlb);
 void vhost_dev_cleanup(struct vhost_dev *);
 void vhost_dev_stop(struct vhost_dev *);
 long vhost_dev_ioctl(struct vhost_dev *, unsigned int ioctl, void __user *argp);
@@ -229,6 +213,9 @@ ssize_t vhost_chr_write_iter(struct vhost_dev *dev,
 			     struct iov_iter *from);
 int vhost_init_device_iotlb(struct vhost_dev *d, bool enabled);
 
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map);
+
 #define vq_err(vq, fmt, ...) do {                                  \
 		pr_debug(pr_fmt(fmt), ##__VA_ARGS__);       \
 		if ((vq)->error_ctx)                               \

drivers/vhost/vringh.c

@@ -13,6 +13,9 @@
 #include <linux/uaccess.h>
 #include <linux/slab.h>
 #include <linux/export.h>
+#include <linux/bvec.h>
+#include <linux/highmem.h>
+#include <linux/vhost_iotlb.h>
 #include <uapi/linux/virtio_config.h>
 
 static __printf(1,2) __cold void vringh_bad(const char *fmt, ...)
@@ -71,9 +74,11 @@ static inline int __vringh_get_head(const struct vringh *vrh,
 }
 
 /* Copy some bytes to/from the iovec.  Returns num copied. */
-static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov,
+static inline ssize_t vringh_iov_xfer(struct vringh *vrh,
+				      struct vringh_kiov *iov,
 				      void *ptr, size_t len,
-				      int (*xfer)(void *addr, void *ptr,
+				      int (*xfer)(const struct vringh *vrh,
+						  void *addr, void *ptr,
 						  size_t len))
 {
 	int err, done = 0;
@@ -82,7 +87,7 @@ static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov,
 		size_t partlen;
 
 		partlen = min(iov->iov[iov->i].iov_len, len);
-		err = xfer(iov->iov[iov->i].iov_base, ptr, partlen);
+		err = xfer(vrh, iov->iov[iov->i].iov_base, ptr, partlen);
 		if (err)
 			return err;
 		done += partlen;
@@ -96,6 +101,7 @@ static inline ssize_t vringh_iov_xfer(struct vringh_kiov *iov,
 			/* Fix up old iov element then increment. */
 			iov->iov[iov->i].iov_len = iov->consumed;
 			iov->iov[iov->i].iov_base -= iov->consumed;
+
 			
 			iov->consumed = 0;
 			iov->i++;
@@ -227,7 +233,8 @@ static int slow_copy(struct vringh *vrh, void *dst, const void *src,
 				      u64 addr,
 				      struct vringh_range *r),
 		     struct vringh_range *range,
-		     int (*copy)(void *dst, const void *src, size_t len))
+		     int (*copy)(const struct vringh *vrh,
+				 void *dst, const void *src, size_t len))
 {
 	size_t part, len = sizeof(struct vring_desc);
 
@@ -241,7 +248,7 @@ static int slow_copy(struct vringh *vrh, void *dst, const void *src,
 		if (!rcheck(vrh, addr, &part, range, getrange))
 			return -EINVAL;
 
-		err = copy(dst, src, part);
+		err = copy(vrh, dst, src, part);
 		if (err)
 			return err;
 
@@ -262,7 +269,8 @@ __vringh_iov(struct vringh *vrh, u16 i,
 					     struct vringh_range *)),
 	     bool (*getrange)(struct vringh *, u64, struct vringh_range *),
 	     gfp_t gfp,
-	     int (*copy)(void *dst, const void *src, size_t len))
+	     int (*copy)(const struct vringh *vrh,
+			 void *dst, const void *src, size_t len))
 {
 	int err, count = 0, up_next, desc_max;
 	struct vring_desc desc, *descs;
@@ -291,7 +299,7 @@ __vringh_iov(struct vringh *vrh, u16 i,
 			err = slow_copy(vrh, &desc, &descs[i], rcheck, getrange,
 					&slowrange, copy);
 		else
-			err = copy(&desc, &descs[i], sizeof(desc));
+			err = copy(vrh, &desc, &descs[i], sizeof(desc));
 		if (unlikely(err))
 			goto fail;
 
@@ -404,7 +412,8 @@ static inline int __vringh_complete(struct vringh *vrh,
 				    unsigned int num_used,
 				    int (*putu16)(const struct vringh *vrh,
 						  __virtio16 *p, u16 val),
-				    int (*putused)(struct vring_used_elem *dst,
+				    int (*putused)(const struct vringh *vrh,
+						   struct vring_used_elem *dst,
 						   const struct vring_used_elem
 						   *src, unsigned num))
 {
@@ -420,12 +429,12 @@ static inline int __vringh_complete(struct vringh *vrh,
 	/* Compiler knows num_used == 1 sometimes, hence extra check */
 	if (num_used > 1 && unlikely(off + num_used >= vrh->vring.num)) {
 		u16 part = vrh->vring.num - off;
-		err = putused(&used_ring->ring[off], used, part);
+		err = putused(vrh, &used_ring->ring[off], used, part);
 		if (!err)
-			err = putused(&used_ring->ring[0], used + part,
+			err = putused(vrh, &used_ring->ring[0], used + part,
 				      num_used - part);
 	} else
-		err = putused(&used_ring->ring[off], used, num_used);
+		err = putused(vrh, &used_ring->ring[off], used, num_used);
 
 	if (err) {
 		vringh_bad("Failed to write %u used entries %u at %p",
@@ -564,13 +573,15 @@ static inline int putu16_user(const struct vringh *vrh, __virtio16 *p, u16 val)
 	return put_user(v, (__force __virtio16 __user *)p);
 }
 
-static inline int copydesc_user(void *dst, const void *src, size_t len)
+static inline int copydesc_user(const struct vringh *vrh,
+				void *dst, const void *src, size_t len)
 {
 	return copy_from_user(dst, (__force void __user *)src, len) ?
 		-EFAULT : 0;
 }
 
-static inline int putused_user(struct vring_used_elem *dst,
+static inline int putused_user(const struct vringh *vrh,
+			       struct vring_used_elem *dst,
 			       const struct vring_used_elem *src,
 			       unsigned int num)
 {
@@ -578,13 +589,15 @@ static inline int putused_user(struct vring_used_elem *dst,
 			    sizeof(*dst) * num) ? -EFAULT : 0;
 }
 
-static inline int xfer_from_user(void *src, void *dst, size_t len)
+static inline int xfer_from_user(const struct vringh *vrh, void *src,
+				 void *dst, size_t len)
 {
 	return copy_from_user(dst, (__force void __user *)src, len) ?
 		-EFAULT : 0;
 }
 
-static inline int xfer_to_user(void *dst, void *src, size_t len)
+static inline int xfer_to_user(const struct vringh *vrh,
+			       void *dst, void *src, size_t len)
 {
 	return copy_to_user((__force void __user *)dst, src, len) ?
 		-EFAULT : 0;
@@ -706,7 +719,7 @@ EXPORT_SYMBOL(vringh_getdesc_user);
  */
 ssize_t vringh_iov_pull_user(struct vringh_iov *riov, void *dst, size_t len)
 {
-	return vringh_iov_xfer((struct vringh_kiov *)riov,
+	return vringh_iov_xfer(NULL, (struct vringh_kiov *)riov,
 			       dst, len, xfer_from_user);
 }
 EXPORT_SYMBOL(vringh_iov_pull_user);
@@ -722,7 +735,7 @@ EXPORT_SYMBOL(vringh_iov_pull_user);
 ssize_t vringh_iov_push_user(struct vringh_iov *wiov,
 			     const void *src, size_t len)
 {
-	return vringh_iov_xfer((struct vringh_kiov *)wiov,
+	return vringh_iov_xfer(NULL, (struct vringh_kiov *)wiov,
 			       (void *)src, len, xfer_to_user);
 }
 EXPORT_SYMBOL(vringh_iov_push_user);
@@ -832,13 +845,15 @@ static inline int putu16_kern(const struct vringh *vrh, __virtio16 *p, u16 val)
 	return 0;
 }
 
-static inline int copydesc_kern(void *dst, const void *src, size_t len)
+static inline int copydesc_kern(const struct vringh *vrh,
+				void *dst, const void *src, size_t len)
 {
 	memcpy(dst, src, len);
 	return 0;
 }
 
-static inline int putused_kern(struct vring_used_elem *dst,
+static inline int putused_kern(const struct vringh *vrh,
+			       struct vring_used_elem *dst,
 			       const struct vring_used_elem *src,
 			       unsigned int num)
 {
@@ -846,13 +861,15 @@ static inline int putused_kern(struct vring_used_elem *dst,
 	return 0;
 }
 
-static inline int xfer_kern(void *src, void *dst, size_t len)
+static inline int xfer_kern(const struct vringh *vrh, void *src,
+			    void *dst, size_t len)
 {
 	memcpy(dst, src, len);
 	return 0;
 }
 
-static inline int kern_xfer(void *dst, void *src, size_t len)
+static inline int kern_xfer(const struct vringh *vrh, void *dst,
+			    void *src, size_t len)
 {
 	memcpy(dst, src, len);
 	return 0;
@@ -949,7 +966,7 @@ EXPORT_SYMBOL(vringh_getdesc_kern);
  */
 ssize_t vringh_iov_pull_kern(struct vringh_kiov *riov, void *dst, size_t len)
 {
-	return vringh_iov_xfer(riov, dst, len, xfer_kern);
+	return vringh_iov_xfer(NULL, riov, dst, len, xfer_kern);
 }
 EXPORT_SYMBOL(vringh_iov_pull_kern);
 
@@ -964,7 +981,7 @@ EXPORT_SYMBOL(vringh_iov_pull_kern);
 ssize_t vringh_iov_push_kern(struct vringh_kiov *wiov,
 			     const void *src, size_t len)
 {
-	return vringh_iov_xfer(wiov, (void *)src, len, kern_xfer);
+	return vringh_iov_xfer(NULL, wiov, (void *)src, len, kern_xfer);
 }
 EXPORT_SYMBOL(vringh_iov_push_kern);
 
@@ -1042,4 +1059,362 @@ int vringh_need_notify_kern(struct vringh *vrh)
 }
 EXPORT_SYMBOL(vringh_need_notify_kern);
 
+static int iotlb_translate(const struct vringh *vrh,
+			   u64 addr, u64 len, struct bio_vec iov[],
+			   int iov_size, u32 perm)
+{
+	struct vhost_iotlb_map *map;
+	struct vhost_iotlb *iotlb = vrh->iotlb;
+	int ret = 0;
+	u64 s = 0;
+
+	while (len > s) {
+		u64 size, pa, pfn;
+
+		if (unlikely(ret >= iov_size)) {
+			ret = -ENOBUFS;
+			break;
+		}
+
+		map = vhost_iotlb_itree_first(iotlb, addr,
+					      addr + len - 1);
+		if (!map || map->start > addr) {
+			ret = -EINVAL;
+			break;
+		} else if (!(map->perm & perm)) {
+			ret = -EPERM;
+			break;
+		}
+
+		size = map->size - addr + map->start;
+		pa = map->addr + addr - map->start;
+		pfn = pa >> PAGE_SHIFT;
+		iov[ret].bv_page = pfn_to_page(pfn);
+		iov[ret].bv_len = min(len - s, size);
+		iov[ret].bv_offset = pa & (PAGE_SIZE - 1);
+		s += size;
+		addr += size;
+		++ret;
+	}
+
+	return ret;
+}
+
+static inline int copy_from_iotlb(const struct vringh *vrh, void *dst,
+				  void *src, size_t len)
+{
+	struct iov_iter iter;
+	struct bio_vec iov[16];
+	int ret;
+
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)src,
+			      len, iov, 16, VHOST_MAP_RO);
+	if (ret < 0)
+		return ret;
+
+	iov_iter_bvec(&iter, READ, iov, ret, len);
+
+	ret = copy_from_iter(dst, len, &iter);
+
+	return ret;
+}
+
+static inline int copy_to_iotlb(const struct vringh *vrh, void *dst,
+				void *src, size_t len)
+{
+	struct iov_iter iter;
+	struct bio_vec iov[16];
+	int ret;
+
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)dst,
+			      len, iov, 16, VHOST_MAP_WO);
+	if (ret < 0)
+		return ret;
+
+	iov_iter_bvec(&iter, WRITE, iov, ret, len);
+
+	return copy_to_iter(src, len, &iter);
+}
+
+static inline int getu16_iotlb(const struct vringh *vrh,
+			       u16 *val, const __virtio16 *p)
+{
+	struct bio_vec iov;
+	void *kaddr, *from;
+	int ret;
+
+	/* Atomic read is needed for getu16 */
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p),
+			      &iov, 1, VHOST_MAP_RO);
+	if (ret < 0)
+		return ret;
+
+	kaddr = kmap_atomic(iov.bv_page);
+	from = kaddr + iov.bv_offset;
+	*val = vringh16_to_cpu(vrh, READ_ONCE(*(__virtio16 *)from));
+	kunmap_atomic(kaddr);
+
+	return 0;
+}
+
+static inline int putu16_iotlb(const struct vringh *vrh,
+			       __virtio16 *p, u16 val)
+{
+	struct bio_vec iov;
+	void *kaddr, *to;
+	int ret;
+
+	/* Atomic write is needed for putu16 */
+	ret = iotlb_translate(vrh, (u64)(uintptr_t)p, sizeof(*p),
+			      &iov, 1, VHOST_MAP_WO);
+	if (ret < 0)
+		return ret;
+
+	kaddr = kmap_atomic(iov.bv_page);
+	to = kaddr + iov.bv_offset;
+	WRITE_ONCE(*(__virtio16 *)to, cpu_to_vringh16(vrh, val));
+	kunmap_atomic(kaddr);
+
+	return 0;
+}
+
+static inline int copydesc_iotlb(const struct vringh *vrh,
+				 void *dst, const void *src, size_t len)
+{
+	int ret;
+
+	ret = copy_from_iotlb(vrh, dst, (void *)src, len);
+	if (ret != len)
+		return -EFAULT;
+
+	return 0;
+}
+
+static inline int xfer_from_iotlb(const struct vringh *vrh, void *src,
+				  void *dst, size_t len)
+{
+	int ret;
+
+	ret = copy_from_iotlb(vrh, dst, src, len);
+	if (ret != len)
+		return -EFAULT;
+
+	return 0;
+}
+
+static inline int xfer_to_iotlb(const struct vringh *vrh,
+			       void *dst, void *src, size_t len)
+{
+	int ret;
+
+	ret = copy_to_iotlb(vrh, dst, src, len);
+	if (ret != len)
+		return -EFAULT;
+
+	return 0;
+}
+
+static inline int putused_iotlb(const struct vringh *vrh,
+				struct vring_used_elem *dst,
+				const struct vring_used_elem *src,
+				unsigned int num)
+{
+	int size = num * sizeof(*dst);
+	int ret;
+
+	ret = copy_to_iotlb(vrh, dst, (void *)src, num * sizeof(*dst));
+	if (ret != size)
+		return -EFAULT;
+
+	return 0;
+}
+
+/**
+ * vringh_init_iotlb - initialize a vringh for a ring with IOTLB.
+ * @vrh: the vringh to initialize.
+ * @features: the feature bits for this ring.
+ * @num: the number of elements.
+ * @weak_barriers: true if we only need memory barriers, not I/O.
+ * @desc: the userpace descriptor pointer.
+ * @avail: the userpace avail pointer.
+ * @used: the userpace used pointer.
+ *
+ * Returns an error if num is invalid.
+ */
+int vringh_init_iotlb(struct vringh *vrh, u64 features,
+		      unsigned int num, bool weak_barriers,
+		      struct vring_desc *desc,
+		      struct vring_avail *avail,
+		      struct vring_used *used)
+{
+	return vringh_init_kern(vrh, features, num, weak_barriers,
+				desc, avail, used);
+}
+EXPORT_SYMBOL(vringh_init_iotlb);
+
+/**
+ * vringh_set_iotlb - initialize a vringh for a ring with IOTLB.
+ * @vrh: the vring
+ * @iotlb: iotlb associated with this vring
+ */
+void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb)
+{
+	vrh->iotlb = iotlb;
+}
+EXPORT_SYMBOL(vringh_set_iotlb);
+
+/**
+ * vringh_getdesc_iotlb - get next available descriptor from ring with
+ * IOTLB.
+ * @vrh: the kernelspace vring.
+ * @riov: where to put the readable descriptors (or NULL)
+ * @wiov: where to put the writable descriptors (or NULL)
+ * @head: head index we received, for passing to vringh_complete_iotlb().
+ * @gfp: flags for allocating larger riov/wiov.
+ *
+ * Returns 0 if there was no descriptor, 1 if there was, or -errno.
+ *
+ * Note that on error return, you can tell the difference between an
+ * invalid ring and a single invalid descriptor: in the former case,
+ * *head will be vrh->vring.num.  You may be able to ignore an invalid
+ * descriptor, but there's not much you can do with an invalid ring.
+ *
+ * Note that you may need to clean up riov and wiov, even on error!
+ */
+int vringh_getdesc_iotlb(struct vringh *vrh,
+			 struct vringh_kiov *riov,
+			 struct vringh_kiov *wiov,
+			 u16 *head,
+			 gfp_t gfp)
+{
+	int err;
+
+	err = __vringh_get_head(vrh, getu16_iotlb, &vrh->last_avail_idx);
+	if (err < 0)
+		return err;
+
+	/* Empty... */
+	if (err == vrh->vring.num)
+		return 0;
+
+	*head = err;
+	err = __vringh_iov(vrh, *head, riov, wiov, no_range_check, NULL,
+			   gfp, copydesc_iotlb);
+	if (err)
+		return err;
+
+	return 1;
+}
+EXPORT_SYMBOL(vringh_getdesc_iotlb);
+
+/**
+ * vringh_iov_pull_iotlb - copy bytes from vring_iov.
+ * @vrh: the vring.
+ * @riov: the riov as passed to vringh_getdesc_iotlb() (updated as we consume)
+ * @dst: the place to copy.
+ * @len: the maximum length to copy.
+ *
+ * Returns the bytes copied <= len or a negative errno.
+ */
+ssize_t vringh_iov_pull_iotlb(struct vringh *vrh,
+			      struct vringh_kiov *riov,
+			      void *dst, size_t len)
+{
+	return vringh_iov_xfer(vrh, riov, dst, len, xfer_from_iotlb);
+}
+EXPORT_SYMBOL(vringh_iov_pull_iotlb);
+
+/**
+ * vringh_iov_push_iotlb - copy bytes into vring_iov.
+ * @vrh: the vring.
+ * @wiov: the wiov as passed to vringh_getdesc_iotlb() (updated as we consume)
+ * @dst: the place to copy.
+ * @len: the maximum length to copy.
+ *
+ * Returns the bytes copied <= len or a negative errno.
+ */
+ssize_t vringh_iov_push_iotlb(struct vringh *vrh,
+			      struct vringh_kiov *wiov,
+			      const void *src, size_t len)
+{
+	return vringh_iov_xfer(vrh, wiov, (void *)src, len, xfer_to_iotlb);
+}
+EXPORT_SYMBOL(vringh_iov_push_iotlb);
+
+/**
+ * vringh_abandon_iotlb - we've decided not to handle the descriptor(s).
+ * @vrh: the vring.
+ * @num: the number of descriptors to put back (ie. num
+ *	 vringh_get_iotlb() to undo).
+ *
+ * The next vringh_get_iotlb() will return the old descriptor(s) again.
+ */
+void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num)
+{
+	/* We only update vring_avail_event(vr) when we want to be notified,
+	 * so we haven't changed that yet.
+	 */
+	vrh->last_avail_idx -= num;
+}
+EXPORT_SYMBOL(vringh_abandon_iotlb);
+
+/**
+ * vringh_complete_iotlb - we've finished with descriptor, publish it.
+ * @vrh: the vring.
+ * @head: the head as filled in by vringh_getdesc_iotlb.
+ * @len: the length of data we have written.
+ *
+ * You should check vringh_need_notify_iotlb() after one or more calls
+ * to this function.
+ */
+int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len)
+{
+	struct vring_used_elem used;
+
+	used.id = cpu_to_vringh32(vrh, head);
+	used.len = cpu_to_vringh32(vrh, len);
+
+	return __vringh_complete(vrh, &used, 1, putu16_iotlb, putused_iotlb);
+}
+EXPORT_SYMBOL(vringh_complete_iotlb);
+
+/**
+ * vringh_notify_enable_iotlb - we want to know if something changes.
+ * @vrh: the vring.
+ *
+ * This always enables notifications, but returns false if there are
+ * now more buffers available in the vring.
+ */
+bool vringh_notify_enable_iotlb(struct vringh *vrh)
+{
+	return __vringh_notify_enable(vrh, getu16_iotlb, putu16_iotlb);
+}
+EXPORT_SYMBOL(vringh_notify_enable_iotlb);
+
+/**
+ * vringh_notify_disable_iotlb - don't tell us if something changes.
+ * @vrh: the vring.
+ *
+ * This is our normal running state: we disable and then only enable when
+ * we're going to sleep.
+ */
+void vringh_notify_disable_iotlb(struct vringh *vrh)
+{
+	__vringh_notify_disable(vrh, putu16_iotlb);
+}
+EXPORT_SYMBOL(vringh_notify_disable_iotlb);
+
+/**
+ * vringh_need_notify_iotlb - must we tell the other side about used buffers?
+ * @vrh: the vring we've called vringh_complete_iotlb() on.
+ *
+ * Returns -errno or 0 if we don't need to tell the other side, 1 if we do.
+ */
+int vringh_need_notify_iotlb(struct vringh *vrh)
+{
+	return __vringh_need_notify(vrh, getu16_iotlb);
+}
+EXPORT_SYMBOL(vringh_need_notify_iotlb);
+
+
 MODULE_LICENSE("GPL");

drivers/vhost/vsock.c

@@ -621,7 +621,7 @@ static int vhost_vsock_dev_open(struct inode *inode, struct file *file)
 
 	vhost_dev_init(&vsock->dev, vqs, ARRAY_SIZE(vsock->vqs),
 		       UIO_MAXIOV, VHOST_VSOCK_PKT_WEIGHT,
-		       VHOST_VSOCK_WEIGHT);
+		       VHOST_VSOCK_WEIGHT, NULL);
 
 	file->private_data = vsock;
 	spin_lock_init(&vsock->send_pkt_list_lock);

drivers/virtio/Kconfig

@@ -43,6 +43,19 @@ config VIRTIO_PCI_LEGACY
 
 	  If unsure, say Y.
 
+config VIRTIO_VDPA
+	tristate "vDPA driver for virtio devices"
+	select VDPA
+	select VIRTIO
+	help
+	  This driver provides support for virtio based paravirtual
+	  device driver over vDPA bus. For this to be useful, you need
+	  an appropriate vDPA device implementation that operates on a
+	  physical device to allow the datapath of virtio to be
+	  offloaded to hardware.
+
+	  If unsure, say M.
+
 config VIRTIO_PMEM
 	tristate "Support for virtio pmem driver"
 	depends on VIRTIO

drivers/virtio/Makefile

@@ -6,3 +6,4 @@ virtio_pci-y := virtio_pci_modern.o virtio_pci_common.o
 virtio_pci-$(CONFIG_VIRTIO_PCI_LEGACY) += virtio_pci_legacy.o
 obj-$(CONFIG_VIRTIO_BALLOON) += virtio_balloon.o
 obj-$(CONFIG_VIRTIO_INPUT) += virtio_input.o
+obj-$(CONFIG_VIRTIO_VDPA) += virtio_vdpa.o

drivers/virtio/virtio_vdpa.c

@@ -0,0 +1,396 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * VIRTIO based driver for vDPA device
+ *
+ * Copyright (c) 2020, Red Hat. All rights reserved.
+ *     Author: Jason Wang <jasowang@redhat.com>
+ *
+ */
+
+#include <linux/init.h>
+#include <linux/module.h>
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/uuid.h>
+#include <linux/virtio.h>
+#include <linux/vdpa.h>
+#include <linux/virtio_config.h>
+#include <linux/virtio_ring.h>
+
+#define MOD_VERSION  "0.1"
+#define MOD_AUTHOR   "Jason Wang <jasowang@redhat.com>"
+#define MOD_DESC     "vDPA bus driver for virtio devices"
+#define MOD_LICENSE  "GPL v2"
+
+struct virtio_vdpa_device {
+	struct virtio_device vdev;
+	struct vdpa_device *vdpa;
+	u64 features;
+
+	/* The lock to protect virtqueue list */
+	spinlock_t lock;
+	/* List of virtio_vdpa_vq_info */
+	struct list_head virtqueues;
+};
+
+struct virtio_vdpa_vq_info {
+	/* the actual virtqueue */
+	struct virtqueue *vq;
+
+	/* the list node for the virtqueues list */
+	struct list_head node;
+};
+
+static inline struct virtio_vdpa_device *
+to_virtio_vdpa_device(struct virtio_device *dev)
+{
+	return container_of(dev, struct virtio_vdpa_device, vdev);
+}
+
+static struct vdpa_device *vd_get_vdpa(struct virtio_device *vdev)
+{
+	return to_virtio_vdpa_device(vdev)->vdpa;
+}
+
+static void virtio_vdpa_get(struct virtio_device *vdev, unsigned offset,
+			    void *buf, unsigned len)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	ops->get_config(vdpa, offset, buf, len);
+}
+
+static void virtio_vdpa_set(struct virtio_device *vdev, unsigned offset,
+			    const void *buf, unsigned len)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	ops->set_config(vdpa, offset, buf, len);
+}
+
+static u32 virtio_vdpa_generation(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	if (ops->get_generation)
+		return ops->get_generation(vdpa);
+
+	return 0;
+}
+
+static u8 virtio_vdpa_get_status(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return ops->get_status(vdpa);
+}
+
+static void virtio_vdpa_set_status(struct virtio_device *vdev, u8 status)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return ops->set_status(vdpa, status);
+}
+
+static void virtio_vdpa_reset(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return ops->set_status(vdpa, 0);
+}
+
+static bool virtio_vdpa_notify(struct virtqueue *vq)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vq->vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	ops->kick_vq(vdpa, vq->index);
+
+	return true;
+}
+
+static irqreturn_t virtio_vdpa_config_cb(void *private)
+{
+	struct virtio_vdpa_device *vd_dev = private;
+
+	virtio_config_changed(&vd_dev->vdev);
+
+	return IRQ_HANDLED;
+}
+
+static irqreturn_t virtio_vdpa_virtqueue_cb(void *private)
+{
+	struct virtio_vdpa_vq_info *info = private;
+
+	return vring_interrupt(0, info->vq);
+}
+
+static struct virtqueue *
+virtio_vdpa_setup_vq(struct virtio_device *vdev, unsigned int index,
+		     void (*callback)(struct virtqueue *vq),
+		     const char *name, bool ctx)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct virtio_vdpa_vq_info *info;
+	struct vdpa_callback cb;
+	struct virtqueue *vq;
+	u64 desc_addr, driver_addr, device_addr;
+	unsigned long flags;
+	u32 align, num;
+	int err;
+
+	if (!name)
+		return NULL;
+
+	/* Queue shouldn't already be set up. */
+	if (ops->get_vq_ready(vdpa, index))
+		return ERR_PTR(-ENOENT);
+
+	/* Allocate and fill out our active queue description */
+	info = kmalloc(sizeof(*info), GFP_KERNEL);
+	if (!info)
+		return ERR_PTR(-ENOMEM);
+
+	num = ops->get_vq_num_max(vdpa);
+	if (num == 0) {
+		err = -ENOENT;
+		goto error_new_virtqueue;
+	}
+
+	/* Create the vring */
+	align = ops->get_vq_align(vdpa);
+	vq = vring_create_virtqueue(index, num, align, vdev,
+				    true, true, ctx,
+				    virtio_vdpa_notify, callback, name);
+	if (!vq) {
+		err = -ENOMEM;
+		goto error_new_virtqueue;
+	}
+
+	/* Setup virtqueue callback */
+	cb.callback = virtio_vdpa_virtqueue_cb;
+	cb.private = info;
+	ops->set_vq_cb(vdpa, index, &cb);
+	ops->set_vq_num(vdpa, index, virtqueue_get_vring_size(vq));
+
+	desc_addr = virtqueue_get_desc_addr(vq);
+	driver_addr = virtqueue_get_avail_addr(vq);
+	device_addr = virtqueue_get_used_addr(vq);
+
+	if (ops->set_vq_address(vdpa, index,
+				desc_addr, driver_addr,
+				device_addr)) {
+		err = -EINVAL;
+		goto err_vq;
+	}
+
+	ops->set_vq_ready(vdpa, index, 1);
+
+	vq->priv = info;
+	info->vq = vq;
+
+	spin_lock_irqsave(&vd_dev->lock, flags);
+	list_add(&info->node, &vd_dev->virtqueues);
+	spin_unlock_irqrestore(&vd_dev->lock, flags);
+
+	return vq;
+
+err_vq:
+	vring_del_virtqueue(vq);
+error_new_virtqueue:
+	ops->set_vq_ready(vdpa, index, 0);
+	/* VDPA driver should make sure vq is stopeed here */
+	WARN_ON(ops->get_vq_ready(vdpa, index));
+	kfree(info);
+	return ERR_PTR(err);
+}
+
+static void virtio_vdpa_del_vq(struct virtqueue *vq)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vq->vdev);
+	struct vdpa_device *vdpa = vd_dev->vdpa;
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct virtio_vdpa_vq_info *info = vq->priv;
+	unsigned int index = vq->index;
+	unsigned long flags;
+
+	spin_lock_irqsave(&vd_dev->lock, flags);
+	list_del(&info->node);
+	spin_unlock_irqrestore(&vd_dev->lock, flags);
+
+	/* Select and deactivate the queue */
+	ops->set_vq_ready(vdpa, index, 0);
+	WARN_ON(ops->get_vq_ready(vdpa, index));
+
+	vring_del_virtqueue(vq);
+
+	kfree(info);
+}
+
+static void virtio_vdpa_del_vqs(struct virtio_device *vdev)
+{
+	struct virtqueue *vq, *n;
+
+	list_for_each_entry_safe(vq, n, &vdev->vqs, list)
+		virtio_vdpa_del_vq(vq);
+}
+
+static int virtio_vdpa_find_vqs(struct virtio_device *vdev, unsigned nvqs,
+				struct virtqueue *vqs[],
+				vq_callback_t *callbacks[],
+				const char * const names[],
+				const bool *ctx,
+				struct irq_affinity *desc)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct vdpa_callback cb;
+	int i, err, queue_idx = 0;
+
+	for (i = 0; i < nvqs; ++i) {
+		if (!names[i]) {
+			vqs[i] = NULL;
+			continue;
+		}
+
+		vqs[i] = virtio_vdpa_setup_vq(vdev, queue_idx++,
+					      callbacks[i], names[i], ctx ?
+					      ctx[i] : false);
+		if (IS_ERR(vqs[i])) {
+			err = PTR_ERR(vqs[i]);
+			goto err_setup_vq;
+		}
+	}
+
+	cb.callback = virtio_vdpa_config_cb;
+	cb.private = vd_dev;
+	ops->set_config_cb(vdpa, &cb);
+
+	return 0;
+
+err_setup_vq:
+	virtio_vdpa_del_vqs(vdev);
+	return err;
+}
+
+static u64 virtio_vdpa_get_features(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	return ops->get_features(vdpa);
+}
+
+static int virtio_vdpa_finalize_features(struct virtio_device *vdev)
+{
+	struct vdpa_device *vdpa = vd_get_vdpa(vdev);
+	const struct vdpa_config_ops *ops = vdpa->config;
+
+	/* Give virtio_ring a chance to accept features. */
+	vring_transport_features(vdev);
+
+	return ops->set_features(vdpa, vdev->features);
+}
+
+static const char *virtio_vdpa_bus_name(struct virtio_device *vdev)
+{
+	struct virtio_vdpa_device *vd_dev = to_virtio_vdpa_device(vdev);
+	struct vdpa_device *vdpa = vd_dev->vdpa;
+
+	return dev_name(&vdpa->dev);
+}
+
+static const struct virtio_config_ops virtio_vdpa_config_ops = {
+	.get		= virtio_vdpa_get,
+	.set		= virtio_vdpa_set,
+	.generation	= virtio_vdpa_generation,
+	.get_status	= virtio_vdpa_get_status,
+	.set_status	= virtio_vdpa_set_status,
+	.reset		= virtio_vdpa_reset,
+	.find_vqs	= virtio_vdpa_find_vqs,
+	.del_vqs	= virtio_vdpa_del_vqs,
+	.get_features	= virtio_vdpa_get_features,
+	.finalize_features = virtio_vdpa_finalize_features,
+	.bus_name	= virtio_vdpa_bus_name,
+};
+
+static void virtio_vdpa_release_dev(struct device *_d)
+{
+	struct virtio_device *vdev =
+	       container_of(_d, struct virtio_device, dev);
+	struct virtio_vdpa_device *vd_dev =
+	       container_of(vdev, struct virtio_vdpa_device, vdev);
+
+	kfree(vd_dev);
+}
+
+static int virtio_vdpa_probe(struct vdpa_device *vdpa)
+{
+	const struct vdpa_config_ops *ops = vdpa->config;
+	struct virtio_vdpa_device *vd_dev, *reg_dev = NULL;
+	int ret = -EINVAL;
+
+	vd_dev = kzalloc(sizeof(*vd_dev), GFP_KERNEL);
+	if (!vd_dev)
+		return -ENOMEM;
+
+	vd_dev->vdev.dev.parent = vdpa_get_dma_dev(vdpa);
+	vd_dev->vdev.dev.release = virtio_vdpa_release_dev;
+	vd_dev->vdev.config = &virtio_vdpa_config_ops;
+	vd_dev->vdpa = vdpa;
+	INIT_LIST_HEAD(&vd_dev->virtqueues);
+	spin_lock_init(&vd_dev->lock);
+
+	vd_dev->vdev.id.device = ops->get_device_id(vdpa);
+	if (vd_dev->vdev.id.device == 0)
+		goto err;
+
+	vd_dev->vdev.id.vendor = ops->get_vendor_id(vdpa);
+	ret = register_virtio_device(&vd_dev->vdev);
+	reg_dev = vd_dev;
+	if (ret)
+		goto err;
+
+	vdpa_set_drvdata(vdpa, vd_dev);
+
+	return 0;
+
+err:
+	if (reg_dev)
+		put_device(&vd_dev->vdev.dev);
+	else
+		kfree(vd_dev);
+	return ret;
+}
+
+static void virtio_vdpa_remove(struct vdpa_device *vdpa)
+{
+	struct virtio_vdpa_device *vd_dev = vdpa_get_drvdata(vdpa);
+
+	unregister_virtio_device(&vd_dev->vdev);
+}
+
+static struct vdpa_driver virtio_vdpa_driver = {
+	.driver = {
+		.name	= "virtio_vdpa",
+	},
+	.probe	= virtio_vdpa_probe,
+	.remove = virtio_vdpa_remove,
+};
+
+module_vdpa_driver(virtio_vdpa_driver);
+
+MODULE_VERSION(MOD_VERSION);
+MODULE_LICENSE(MOD_LICENSE);
+MODULE_AUTHOR(MOD_AUTHOR);
+MODULE_DESCRIPTION(MOD_DESC);

include/linux/vdpa.h

@@ -0,0 +1,253 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VDPA_H
+#define _LINUX_VDPA_H
+
+#include <linux/kernel.h>
+#include <linux/device.h>
+#include <linux/interrupt.h>
+#include <linux/vhost_iotlb.h>
+
+/**
+ * vDPA callback definition.
+ * @callback: interrupt callback function
+ * @private: the data passed to the callback function
+ */
+struct vdpa_callback {
+	irqreturn_t (*callback)(void *data);
+	void *private;
+};
+
+/**
+ * vDPA device - representation of a vDPA device
+ * @dev: underlying device
+ * @dma_dev: the actual device that is performing DMA
+ * @config: the configuration ops for this device.
+ * @index: device index
+ */
+struct vdpa_device {
+	struct device dev;
+	struct device *dma_dev;
+	const struct vdpa_config_ops *config;
+	unsigned int index;
+};
+
+/**
+ * vDPA_config_ops - operations for configuring a vDPA device.
+ * Note: vDPA device drivers are required to implement all of the
+ * operations unless it is mentioned to be optional in the following
+ * list.
+ *
+ * @set_vq_address:		Set the address of virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				@desc_area: address of desc area
+ *				@driver_area: address of driver area
+ *				@device_area: address of device area
+ *				Returns integer: success (0) or error (< 0)
+ * @set_vq_num:			Set the size of virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				@num: the size of virtqueue
+ * @kick_vq:			Kick the virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ * @set_vq_cb:			Set the interrupt callback function for
+ *				a virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				@cb: virtio-vdev interrupt callback structure
+ * @set_vq_ready:		Set ready status for a virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				@ready: ready (true) not ready(false)
+ * @get_vq_ready:		Get ready status for a virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				Returns boolean: ready (true) or not (false)
+ * @set_vq_state:		Set the state for a virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				@state: virtqueue state (last_avail_idx)
+ *				Returns integer: success (0) or error (< 0)
+ * @get_vq_state:		Get the state for a virtqueue
+ *				@vdev: vdpa device
+ *				@idx: virtqueue index
+ *				Returns virtqueue state (last_avail_idx)
+ * @get_vq_align:		Get the virtqueue align requirement
+ *				for the device
+ *				@vdev: vdpa device
+ *				Returns virtqueue algin requirement
+ * @get_features:		Get virtio features supported by the device
+ *				@vdev: vdpa device
+ *				Returns the virtio features support by the
+ *				device
+ * @set_features:		Set virtio features supported by the driver
+ *				@vdev: vdpa device
+ *				@features: feature support by the driver
+ *				Returns integer: success (0) or error (< 0)
+ * @set_config_cb:		Set the config interrupt callback
+ *				@vdev: vdpa device
+ *				@cb: virtio-vdev interrupt callback structure
+ * @get_vq_num_max:		Get the max size of virtqueue
+ *				@vdev: vdpa device
+ *				Returns u16: max size of virtqueue
+ * @get_device_id:		Get virtio device id
+ *				@vdev: vdpa device
+ *				Returns u32: virtio device id
+ * @get_vendor_id:		Get id for the vendor that provides this device
+ *				@vdev: vdpa device
+ *				Returns u32: virtio vendor id
+ * @get_status:			Get the device status
+ *				@vdev: vdpa device
+ *				Returns u8: virtio device status
+ * @set_status:			Set the device status
+ *				@vdev: vdpa device
+ *				@status: virtio device status
+ * @get_config:			Read from device specific configuration space
+ *				@vdev: vdpa device
+ *				@offset: offset from the beginning of
+ *				configuration space
+ *				@buf: buffer used to read to
+ *				@len: the length to read from
+ *				configuration space
+ * @set_config:			Write to device specific configuration space
+ *				@vdev: vdpa device
+ *				@offset: offset from the beginning of
+ *				configuration space
+ *				@buf: buffer used to write from
+ *				@len: the length to write to
+ *				configuration space
+ * @get_generation:		Get device config generation (optional)
+ *				@vdev: vdpa device
+ *				Returns u32: device generation
+ * @set_map:			Set device memory mapping (optional)
+ *				Needed for device that using device
+ *				specific DMA translation (on-chip IOMMU)
+ *				@vdev: vdpa device
+ *				@iotlb: vhost memory mapping to be
+ *				used by the vDPA
+ *				Returns integer: success (0) or error (< 0)
+ * @dma_map:			Map an area of PA to IOVA (optional)
+ *				Needed for device that using device
+ *				specific DMA translation (on-chip IOMMU)
+ *				and preferring incremental map.
+ *				@vdev: vdpa device
+ *				@iova: iova to be mapped
+ *				@size: size of the area
+ *				@pa: physical address for the map
+ *				@perm: device access permission (VHOST_MAP_XX)
+ *				Returns integer: success (0) or error (< 0)
+ * @dma_unmap:			Unmap an area of IOVA (optional but
+ *				must be implemented with dma_map)
+ *				Needed for device that using device
+ *				specific DMA translation (on-chip IOMMU)
+ *				and preferring incremental unmap.
+ *				@vdev: vdpa device
+ *				@iova: iova to be unmapped
+ *				@size: size of the area
+ *				Returns integer: success (0) or error (< 0)
+ * @free:			Free resources that belongs to vDPA (optional)
+ *				@vdev: vdpa device
+ */
+struct vdpa_config_ops {
+	/* Virtqueue ops */
+	int (*set_vq_address)(struct vdpa_device *vdev,
+			      u16 idx, u64 desc_area, u64 driver_area,
+			      u64 device_area);
+	void (*set_vq_num)(struct vdpa_device *vdev, u16 idx, u32 num);
+	void (*kick_vq)(struct vdpa_device *vdev, u16 idx);
+	void (*set_vq_cb)(struct vdpa_device *vdev, u16 idx,
+			  struct vdpa_callback *cb);
+	void (*set_vq_ready)(struct vdpa_device *vdev, u16 idx, bool ready);
+	bool (*get_vq_ready)(struct vdpa_device *vdev, u16 idx);
+	int (*set_vq_state)(struct vdpa_device *vdev, u16 idx, u64 state);
+	u64 (*get_vq_state)(struct vdpa_device *vdev, u16 idx);
+
+	/* Device ops */
+	u16 (*get_vq_align)(struct vdpa_device *vdev);
+	u64 (*get_features)(struct vdpa_device *vdev);
+	int (*set_features)(struct vdpa_device *vdev, u64 features);
+	void (*set_config_cb)(struct vdpa_device *vdev,
+			      struct vdpa_callback *cb);
+	u16 (*get_vq_num_max)(struct vdpa_device *vdev);
+	u32 (*get_device_id)(struct vdpa_device *vdev);
+	u32 (*get_vendor_id)(struct vdpa_device *vdev);
+	u8 (*get_status)(struct vdpa_device *vdev);
+	void (*set_status)(struct vdpa_device *vdev, u8 status);
+	void (*get_config)(struct vdpa_device *vdev, unsigned int offset,
+			   void *buf, unsigned int len);
+	void (*set_config)(struct vdpa_device *vdev, unsigned int offset,
+			   const void *buf, unsigned int len);
+	u32 (*get_generation)(struct vdpa_device *vdev);
+
+	/* DMA ops */
+	int (*set_map)(struct vdpa_device *vdev, struct vhost_iotlb *iotlb);
+	int (*dma_map)(struct vdpa_device *vdev, u64 iova, u64 size,
+		       u64 pa, u32 perm);
+	int (*dma_unmap)(struct vdpa_device *vdev, u64 iova, u64 size);
+
+	/* Free device resources */
+	void (*free)(struct vdpa_device *vdev);
+};
+
+struct vdpa_device *__vdpa_alloc_device(struct device *parent,
+					const struct vdpa_config_ops *config,
+					size_t size);
+
+#define vdpa_alloc_device(dev_struct, member, parent, config)   \
+			  container_of(__vdpa_alloc_device( \
+				       parent, config, \
+				       sizeof(dev_struct) + \
+				       BUILD_BUG_ON_ZERO(offsetof( \
+				       dev_struct, member))), \
+				       dev_struct, member)
+
+int vdpa_register_device(struct vdpa_device *vdev);
+void vdpa_unregister_device(struct vdpa_device *vdev);
+
+/**
+ * vdpa_driver - operations for a vDPA driver
+ * @driver: underlying device driver
+ * @probe: the function to call when a device is found.  Returns 0 or -errno.
+ * @remove: the function to call when a device is removed.
+ */
+struct vdpa_driver {
+	struct device_driver driver;
+	int (*probe)(struct vdpa_device *vdev);
+	void (*remove)(struct vdpa_device *vdev);
+};
+
+#define vdpa_register_driver(drv) \
+	__vdpa_register_driver(drv, THIS_MODULE)
+int __vdpa_register_driver(struct vdpa_driver *drv, struct module *owner);
+void vdpa_unregister_driver(struct vdpa_driver *drv);
+
+#define module_vdpa_driver(__vdpa_driver) \
+	module_driver(__vdpa_driver, vdpa_register_driver,	\
+		      vdpa_unregister_driver)
+
+static inline struct vdpa_driver *drv_to_vdpa(struct device_driver *driver)
+{
+	return container_of(driver, struct vdpa_driver, driver);
+}
+
+static inline struct vdpa_device *dev_to_vdpa(struct device *_dev)
+{
+	return container_of(_dev, struct vdpa_device, dev);
+}
+
+static inline void *vdpa_get_drvdata(const struct vdpa_device *vdev)
+{
+	return dev_get_drvdata(&vdev->dev);
+}
+
+static inline void vdpa_set_drvdata(struct vdpa_device *vdev, void *data)
+{
+	dev_set_drvdata(&vdev->dev, data);
+}
+
+static inline struct device *vdpa_get_dma_dev(struct vdpa_device *vdev)
+{
+	return vdev->dma_dev;
+}
+#endif /* _LINUX_VDPA_H */

include/linux/vhost_iotlb.h

@@ -0,0 +1,47 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _LINUX_VHOST_IOTLB_H
+#define _LINUX_VHOST_IOTLB_H
+
+#include <linux/interval_tree_generic.h>
+
+struct vhost_iotlb_map {
+	struct rb_node rb;
+	struct list_head link;
+	u64 start;
+	u64 last;
+	u64 size;
+	u64 addr;
+#define VHOST_MAP_RO 0x1
+#define VHOST_MAP_WO 0x2
+#define VHOST_MAP_RW 0x3
+	u32 perm;
+	u32 flags_padding;
+	u64 __subtree_last;
+};
+
+#define VHOST_IOTLB_FLAG_RETIRE 0x1
+
+struct vhost_iotlb {
+	struct rb_root_cached root;
+	struct list_head list;
+	unsigned int limit;
+	unsigned int nmaps;
+	unsigned int flags;
+};
+
+int vhost_iotlb_add_range(struct vhost_iotlb *iotlb, u64 start, u64 last,
+			  u64 addr, unsigned int perm);
+void vhost_iotlb_del_range(struct vhost_iotlb *iotlb, u64 start, u64 last);
+
+struct vhost_iotlb *vhost_iotlb_alloc(unsigned int limit, unsigned int flags);
+void vhost_iotlb_free(struct vhost_iotlb *iotlb);
+void vhost_iotlb_reset(struct vhost_iotlb *iotlb);
+
+struct vhost_iotlb_map *
+vhost_iotlb_itree_first(struct vhost_iotlb *iotlb, u64 start, u64 last);
+struct vhost_iotlb_map *
+vhost_iotlb_itree_next(struct vhost_iotlb_map *map, u64 start, u64 last);
+
+void vhost_iotlb_map_free(struct vhost_iotlb *iotlb,
+			  struct vhost_iotlb_map *map);
+#endif

include/linux/vringh.h

@@ -14,6 +14,8 @@
 #include <linux/virtio_byteorder.h>
 #include <linux/uio.h>
 #include <linux/slab.h>
+#include <linux/dma-direction.h>
+#include <linux/vhost_iotlb.h>
 #include <asm/barrier.h>
 
 /* virtio_ring with information needed for host access. */
@@ -39,6 +41,9 @@ struct vringh {
 	/* The vring (note: it may contain user pointers!) */
 	struct vring vring;
 
+	/* IOTLB for this vring */
+	struct vhost_iotlb *iotlb;
+
 	/* The function to call to notify the guest about added buffers */
 	void (*notify)(struct vringh *);
 };
@@ -248,4 +253,35 @@ static inline __virtio64 cpu_to_vringh64(const struct vringh *vrh, u64 val)
 {
 	return __cpu_to_virtio64(vringh_is_little_endian(vrh), val);
 }
+
+void vringh_set_iotlb(struct vringh *vrh, struct vhost_iotlb *iotlb);
+
+int vringh_init_iotlb(struct vringh *vrh, u64 features,
+		      unsigned int num, bool weak_barriers,
+		      struct vring_desc *desc,
+		      struct vring_avail *avail,
+		      struct vring_used *used);
+
+int vringh_getdesc_iotlb(struct vringh *vrh,
+			 struct vringh_kiov *riov,
+			 struct vringh_kiov *wiov,
+			 u16 *head,
+			 gfp_t gfp);
+
+ssize_t vringh_iov_pull_iotlb(struct vringh *vrh,
+			      struct vringh_kiov *riov,
+			      void *dst, size_t len);
+ssize_t vringh_iov_push_iotlb(struct vringh *vrh,
+			      struct vringh_kiov *wiov,
+			      const void *src, size_t len);
+
+void vringh_abandon_iotlb(struct vringh *vrh, unsigned int num);
+
+int vringh_complete_iotlb(struct vringh *vrh, u16 head, u32 len);
+
+bool vringh_notify_enable_iotlb(struct vringh *vrh);
+void vringh_notify_disable_iotlb(struct vringh *vrh);
+
+int vringh_need_notify_iotlb(struct vringh *vrh);
+
 #endif /* _LINUX_VRINGH_H */

include/uapi/linux/vhost.h

@@ -116,4 +116,28 @@
 #define VHOST_VSOCK_SET_GUEST_CID	_IOW(VHOST_VIRTIO, 0x60, __u64)
 #define VHOST_VSOCK_SET_RUNNING		_IOW(VHOST_VIRTIO, 0x61, int)
 
+/* VHOST_VDPA specific defines */
+
+/* Get the device id. The device ids follow the same definition of
+ * the device id defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_DEVICE_ID	_IOR(VHOST_VIRTIO, 0x70, __u32)
+/* Get and set the status. The status bits follow the same definition
+ * of the device status defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_STATUS		_IOR(VHOST_VIRTIO, 0x71, __u8)
+#define VHOST_VDPA_SET_STATUS		_IOW(VHOST_VIRTIO, 0x72, __u8)
+/* Get and set the device config. The device config follows the same
+ * definition of the device config defined in virtio-spec.
+ */
+#define VHOST_VDPA_GET_CONFIG		_IOR(VHOST_VIRTIO, 0x73, \
+					     struct vhost_vdpa_config)
+#define VHOST_VDPA_SET_CONFIG		_IOW(VHOST_VIRTIO, 0x74, \
+					     struct vhost_vdpa_config)
+/* Enable/disable the ring. */
+#define VHOST_VDPA_SET_VRING_ENABLE	_IOW(VHOST_VIRTIO, 0x75, \
+					     struct vhost_vring_state)
+/* Get the max ring size. */
+#define VHOST_VDPA_GET_VRING_NUM	_IOR(VHOST_VIRTIO, 0x76, __u16)
+
 #endif

include/uapi/linux/vhost_types.h

@@ -119,6 +119,14 @@ struct vhost_scsi_target {
 	unsigned short reserved;
 };
 
+/* VHOST_VDPA specific definitions */
+
+struct vhost_vdpa_config {
+	__u32 off;
+	__u32 len;
+	__u8 buf[0];
+};
+
 /* Feature bits */
 /* Log all write descriptors. Can be changed while device is active. */
 #define VHOST_F_LOG_ALL 26

include/uapi/linux/virtio_net.h

@@ -57,6 +57,9 @@
 					 * Steering */
 #define VIRTIO_NET_F_CTRL_MAC_ADDR 23	/* Set MAC address */
 
+#define VIRTIO_NET_F_HASH_REPORT  57	/* Supports hash report */
+#define VIRTIO_NET_F_RSS	  60	/* Supports RSS RX steering */
+#define VIRTIO_NET_F_RSC_EXT	  61	/* extended coalescing info */
 #define VIRTIO_NET_F_STANDBY	  62	/* Act as standby for another device
 					 * with the same MAC.
 					 */
@@ -69,6 +72,17 @@
 #define VIRTIO_NET_S_LINK_UP	1	/* Link is up */
 #define VIRTIO_NET_S_ANNOUNCE	2	/* Announcement is needed */
 
+/* supported/enabled hash types */
+#define VIRTIO_NET_RSS_HASH_TYPE_IPv4          (1 << 0)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCPv4         (1 << 1)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDPv4         (1 << 2)
+#define VIRTIO_NET_RSS_HASH_TYPE_IPv6          (1 << 3)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCPv6         (1 << 4)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDPv6         (1 << 5)
+#define VIRTIO_NET_RSS_HASH_TYPE_IP_EX         (1 << 6)
+#define VIRTIO_NET_RSS_HASH_TYPE_TCP_EX        (1 << 7)
+#define VIRTIO_NET_RSS_HASH_TYPE_UDP_EX        (1 << 8)
+
 struct virtio_net_config {
 	/* The config defining mac address (if VIRTIO_NET_F_MAC) */
 	__u8 mac[ETH_ALEN];
@@ -92,6 +106,12 @@ struct virtio_net_config {
 	 * Any other value stands for unknown.
 	 */
 	__u8 duplex;
+	/* maximum size of RSS key */
+	__u8 rss_max_key_size;
+	/* maximum number of indirection table entries */
+	__le16 rss_max_indirection_table_length;
+	/* bitmask of supported VIRTIO_NET_RSS_HASH_ types */
+	__le32 supported_hash_types;
 } __attribute__((packed));
 
 /*
@@ -104,6 +124,7 @@ struct virtio_net_config {
 struct virtio_net_hdr_v1 {
 #define VIRTIO_NET_HDR_F_NEEDS_CSUM	1	/* Use csum_start, csum_offset */
 #define VIRTIO_NET_HDR_F_DATA_VALID	2	/* Csum is valid */
+#define VIRTIO_NET_HDR_F_RSC_INFO	4	/* rsc info in csum_ fields */
 	__u8 flags;
 #define VIRTIO_NET_HDR_GSO_NONE		0	/* Not a GSO frame */
 #define VIRTIO_NET_HDR_GSO_TCPV4	1	/* GSO frame, IPv4 TCP (TSO) */
@@ -113,11 +134,46 @@ struct virtio_net_hdr_v1 {
 	__u8 gso_type;
 	__virtio16 hdr_len;	/* Ethernet + IP + tcp/udp hdrs */
 	__virtio16 gso_size;	/* Bytes to append to hdr_len per frame */
-	__virtio16 csum_start;	/* Position to start checksumming from */
+	union {
-	__virtio16 csum_offset;	/* Offset after that to place checksum */
+		struct {
+			__virtio16 csum_start;
+			__virtio16 csum_offset;
+		};
+		/* Checksum calculation */
+		struct {
+			/* Position to start checksumming from */
+			__virtio16 start;
+			/* Offset after that to place checksum */
+			__virtio16 offset;
+		} csum;
+		/* Receive Segment Coalescing */
+		struct {
+			/* Number of coalesced segments */
+			__le16 segments;
+			/* Number of duplicated acks */
+			__le16 dup_acks;
+		} rsc;
+	};
 	__virtio16 num_buffers;	/* Number of merged rx buffers */
 };
 
+struct virtio_net_hdr_v1_hash {
+	struct virtio_net_hdr_v1 hdr;
+	__le32 hash_value;
+#define VIRTIO_NET_HASH_REPORT_NONE            0
+#define VIRTIO_NET_HASH_REPORT_IPv4            1
+#define VIRTIO_NET_HASH_REPORT_TCPv4           2
+#define VIRTIO_NET_HASH_REPORT_UDPv4           3
+#define VIRTIO_NET_HASH_REPORT_IPv6            4
+#define VIRTIO_NET_HASH_REPORT_TCPv6           5
+#define VIRTIO_NET_HASH_REPORT_UDPv6           6
+#define VIRTIO_NET_HASH_REPORT_IPv6_EX         7
+#define VIRTIO_NET_HASH_REPORT_TCPv6_EX        8
+#define VIRTIO_NET_HASH_REPORT_UDPv6_EX        9
+	__le16 hash_report;
+	__le16 padding;
+};
+
 #ifndef VIRTIO_NET_NO_LEGACY
 /* This header comes first in the scatter-gather list.
  * For legacy virtio, if VIRTIO_F_ANY_LAYOUT is not negotiated, it must
@@ -228,7 +284,9 @@ struct virtio_net_ctrl_mac {
 
 /*
  * Control Receive Flow Steering
- *
+ */
+#define VIRTIO_NET_CTRL_MQ   4
+/*
  * The command VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET
  * enables Receive Flow Steering, specifying the number of the transmit and
  * receive queues that will be used. After the command is consumed and acked by
@@ -241,11 +299,47 @@ struct virtio_net_ctrl_mq {
 	__virtio16 virtqueue_pairs;
 };
 
-#define VIRTIO_NET_CTRL_MQ   4
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET        0
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MIN        1
  #define VIRTIO_NET_CTRL_MQ_VQ_PAIRS_MAX        0x8000
 
+/*
+ * The command VIRTIO_NET_CTRL_MQ_RSS_CONFIG has the same effect as
+ * VIRTIO_NET_CTRL_MQ_VQ_PAIRS_SET does and additionally configures
+ * the receive steering to use a hash calculated for incoming packet
+ * to decide on receive virtqueue to place the packet. The command
+ * also provides parameters to calculate a hash and receive virtqueue.
+ */
+struct virtio_net_rss_config {
+	__le32 hash_types;
+	__le16 indirection_table_mask;
+	__le16 unclassified_queue;
+	__le16 indirection_table[1/* + indirection_table_mask */];
+	__le16 max_tx_vq;
+	__u8 hash_key_length;
+	__u8 hash_key_data[/* hash_key_length */];
+};
+
+ #define VIRTIO_NET_CTRL_MQ_RSS_CONFIG          1
+
+/*
+ * The command VIRTIO_NET_CTRL_MQ_HASH_CONFIG requests the device
+ * to include in the virtio header of the packet the value of the
+ * calculated hash and the report type of hash. It also provides
+ * parameters for hash calculation. The command requires feature
+ * VIRTIO_NET_F_HASH_REPORT to be negotiated to extend the
+ * layout of virtio header as defined in virtio_net_hdr_v1_hash.
+ */
+struct virtio_net_hash_config {
+	__le32 hash_types;
+	/* for compatibility with virtio_net_rss_config */
+	__le16 reserved[4];
+	__u8 hash_key_length;
+	__u8 hash_key_data[/* hash_key_length */];
+};
+
+ #define VIRTIO_NET_CTRL_MQ_HASH_CONFIG         2
+
 /*
  * Control network offloads
  *

tools/virtio/Makefile

@@ -8,7 +8,32 @@ CFLAGS += -g -O2 -Werror -Wall -I. -I../include/ -I ../../usr/include/ -Wno-poin
 vpath %.c ../../drivers/virtio ../../drivers/vhost
 mod:
 	${MAKE} -C `pwd`/../.. M=`pwd`/vhost_test V=${V}
-.PHONY: all test mod clean
+
+#oot: build vhost as an out of tree module for a distro kernel
+#no effort is taken to make it actually build or work, but tends to mostly work
+#if the distro kernel is very close to upstream
+#unsupported! this is a development tool only, don't use the
+#resulting modules in production!
+OOT_KSRC=/lib/modules/$$(uname -r)/build
+OOT_VHOST=`pwd`/../../drivers/vhost
+#Everyone depends on vhost
+#Tweak the below to enable more modules
+OOT_CONFIGS=\
+	CONFIG_VHOST=m \
+	CONFIG_VHOST_NET=n \
+	CONFIG_VHOST_SCSI=n \
+	CONFIG_VHOST_VSOCK=n
+OOT_BUILD=KCFLAGS="-I "${OOT_VHOST} ${MAKE} -C ${OOT_KSRC} V=${V}
+oot-build:
+	echo "UNSUPPORTED! Don't use the resulting modules in production!"
+	${OOT_BUILD} M=`pwd`/vhost_test
+	${OOT_BUILD} M=${OOT_VHOST} ${OOT_CONFIGS}
+
+oot-clean: oot-build
+oot: oot-build
+oot-clean: OOT_BUILD+=clean
+
+.PHONY: all test mod clean vhost oot oot-clean oot-build
 clean:
 	${RM} *.o vringh_test virtio_test vhost_test/*.o vhost_test/.*.cmd \
               vhost_test/Module.symvers vhost_test/modules.order *.d