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

+# 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

+# 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

+# 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

+// 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

+/* 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/vdpa.c

+// 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

+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_VDPA_SIM) += vdpa_sim.o

drivers/vhost/Kconfig

 # 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
-	tristate
-	---help---
-	  This option is selected by any driver which needs to access
-	  the core of vhost.
+config VHOST_VDPA
+	tristate "Vhost driver for vDPA-based backend"
+	depends on EVENTFD
+	select 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

-# 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

+// 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/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_umem *iotlb;
+	struct vhost_iotlb *umem;
+	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_umem *iotlb;
+	struct vhost_iotlb *umem;
+	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);
-void vhost_dev_reset_owner(struct vhost_dev *, struct vhost_umem *);
+struct vhost_iotlb *vhost_dev_reset_owner_prepare(void);
+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/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

+// 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

+/* 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

+/* 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