Commit 9bb71526 authored by Linus Torvalds's avatar Linus Torvalds

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
parents ae46d2aa 835a6a64
......@@ -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>
......
......@@ -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
......@@ -72,6 +72,4 @@ config KVM_MIPS_DEBUG_COP0_COUNTERS
If unsure, say N.
source "drivers/vhost/Kconfig"
endif # VIRTUALIZATION
......@@ -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
......@@ -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
......@@ -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
......@@ -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"
......
......@@ -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
......
......@@ -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
......@@ -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
# 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
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_VDPA) += vdpa.o
obj-$(CONFIG_VDPA_SIM) += vdpa_sim/
obj-$(CONFIG_IFCVF) += ifcvf/
# SPDX-License-Identifier: GPL-2.0
obj-$(CONFIG_IFCVF) += ifcvf.o
ifcvf-$(CONFIG_IFCVF) += ifcvf_main.o ifcvf_base.o
// 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);
}
/* 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_ */
This diff is collapsed.
// 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);