OpenCloudOS-Kernel/drivers/vdpa/vdpa_sim/vdpa_sim.c

813 lines
20 KiB
C
Raw Normal View History

// 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/slab.h>
#include <linux/sched.h>
#include <linux/dma-map-ops.h>
#include <linux/etherdevice.h>
#include <linux/vringh.h>
#include <linux/vdpa.h>
#include <linux/virtio_byteorder.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"
static int batch_mapping = 1;
module_param(batch_mapping, int, 0444);
MODULE_PARM_DESC(batch_mapping, "Batched mapping 1 -Enable; 0 - Disable");
static int max_iotlb_entries = 2048;
module_param(max_iotlb_entries, int, 0444);
MODULE_PARM_DESC(max_iotlb_entries,
"Maximum number of iotlb entries. 0 means unlimited. (default: 2048)");
static char *macaddr;
module_param(macaddr, charp, 0);
MODULE_PARM_DESC(macaddr, "Ethernet MAC address");
u8 macaddr_buf[ETH_ALEN];
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_VENDOR_ID 0
#define VDPASIM_VQ_NUM 0x2
#define VDPASIM_NAME "vdpasim-netdev"
#define VDPASIM_FEATURES ((1ULL << VIRTIO_F_ANY_LAYOUT) | \
(1ULL << VIRTIO_F_VERSION_1) | \
(1ULL << VIRTIO_F_ACCESS_PLATFORM))
#define VDPASIM_NET_FEATURES (VDPASIM_FEATURES | \
(1ULL << VIRTIO_NET_F_MAC))
struct vdpasim;
struct vdpasim_dev_attr {
u64 supported_features;
size_t config_size;
int nvqs;
u32 id;
work_func_t work_fn;
void (*get_config)(struct vdpasim *vdpasim, void *config);
void (*set_config)(struct vdpasim *vdpasim, const void *config);
};
/* State of each vdpasim device */
struct vdpasim {
struct vdpa_device vdpa;
struct vdpasim_virtqueue *vqs;
struct work_struct work;
struct vdpasim_dev_attr dev_attr;
/* spinlock to synchronize virtqueue state */
spinlock_t lock;
/* virtio config according to device type */
void *config;
struct vhost_iotlb *iommu;
void *buffer;
u32 status;
u32 generation;
u64 features;
/* spinlock to synchronize iommu table */
spinlock_t iommu_lock;
};
/* TODO: cross-endian support */
static inline bool vdpasim_is_little_endian(struct vdpasim *vdpasim)
{
return virtio_legacy_is_little_endian() ||
(vdpasim->features & (1ULL << VIRTIO_F_VERSION_1));
}
static inline u16 vdpasim16_to_cpu(struct vdpasim *vdpasim, __virtio16 val)
{
return __virtio16_to_cpu(vdpasim_is_little_endian(vdpasim), val);
}
static inline __virtio16 cpu_to_vdpasim16(struct vdpasim *vdpasim, u16 val)
{
return __cpu_to_virtio16(vdpasim_is_little_endian(vdpasim), val);
}
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_vq_notify(struct vringh *vring)
{
struct vdpasim_virtqueue *vq =
container_of(vring, struct vdpasim_virtqueue, vring);
if (!vq->cb)
return;
vq->cb(vq->private);
}
static void vdpasim_queue_ready(struct vdpasim *vdpasim, unsigned int idx)
{
struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_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);
vq->vring.notify = vdpasim_vq_notify;
}
static void vdpasim_vq_reset(struct vdpasim *vdpasim,
struct vdpasim_virtqueue *vq)
{
vq->ready = false;
vq->desc_addr = 0;
vq->driver_addr = 0;
vq->device_addr = 0;
vq->cb = NULL;
vq->private = NULL;
vringh_init_iotlb(&vq->vring, vdpasim->dev_attr.supported_features,
VDPASIM_QUEUE_MAX, false, NULL, NULL, NULL);
vq->vring.notify = NULL;
}
static void vdpasim_reset(struct vdpasim *vdpasim)
{
int i;
for (i = 0; i < vdpasim->dev_attr.nvqs; i++)
vdpasim_vq_reset(vdpasim, &vdpasim->vqs[i]);
spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_reset(vdpasim->iommu);
spin_unlock(&vdpasim->iommu_lock);
vdpasim->features = 0;
vdpasim->status = 0;
++vdpasim->generation;
}
static void vdpasim_net_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];
ssize_t read, write;
size_t total_write;
int pkts = 0;
int err;
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 (vringh_need_notify_iotlb(&txq->vring) > 0)
vringh_notify(&txq->vring);
if (vringh_need_notify_iotlb(&rxq->vring) > 0)
vringh_notify(&rxq->vring);
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.
*/
spin_lock(&vdpasim->iommu_lock);
ret = vhost_iotlb_add_range(iommu, pa, pa + size - 1,
pa, dir_to_perm(dir));
spin_unlock(&vdpasim->iommu_lock);
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;
spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_del_range(iommu, (u64)dma_addr,
(u64)dma_addr + size - 1);
spin_unlock(&vdpasim->iommu_lock);
}
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;
spin_lock(&vdpasim->iommu_lock);
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;
}
spin_unlock(&vdpasim->iommu_lock);
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;
spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_del_range(iommu, (u64)dma_addr,
(u64)dma_addr + size - 1);
spin_unlock(&vdpasim->iommu_lock);
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_config_ops;
static const struct vdpa_config_ops vdpasim_batch_config_ops;
static struct vdpasim *vdpasim_create(struct vdpasim_dev_attr *dev_attr)
{
const struct vdpa_config_ops *ops;
struct vdpasim *vdpasim;
struct device *dev;
int i, ret = -ENOMEM;
if (batch_mapping)
ops = &vdpasim_batch_config_ops;
else
ops = &vdpasim_config_ops;
vdpasim = vdpa_alloc_device(struct vdpasim, vdpa, NULL, ops,
dev_attr->nvqs);
if (!vdpasim)
goto err_alloc;
vdpasim->dev_attr = *dev_attr;
INIT_WORK(&vdpasim->work, dev_attr->work_fn);
spin_lock_init(&vdpasim->lock);
spin_lock_init(&vdpasim->iommu_lock);
dev = &vdpasim->vdpa.dev;
vdpa_sim: Fix DMA mask Since commit f959dcd6ddfd ("dma-direct: Fix potential NULL pointer dereference") an error is reported when we load vdpa_sim and virtio-vdpa: [ 129.351207] net eth0: Unexpected TXQ (0) queue failure: -12 It seems that dma_mask is not initialized. This patch initializes dma_mask() and calls dma_set_mask_and_coherent() to fix the problem. Full log: [ 128.548628] ------------[ cut here ]------------ [ 128.553268] WARNING: CPU: 23 PID: 1105 at kernel/dma/mapping.c:149 dma_map_page_attrs+0x14c/0x1d0 [ 128.562139] Modules linked in: virtio_net net_failover failover virtio_vdpa vdpa_sim vringh vhost_iotlb vdpa xt_CHECKSUM xt_MASQUERADE xt_conntrack ipt_REJECT nf_reject_ipv4 nft_compat nft_counter nft_chain_nat nf_nat nf_conntrack nf_defrag_ipv6 nf_defrag_ipv4 nf_tables nfnetlink tun bridge stp llc iscsi_tcp libiscsi_tcp libiscsi scsi_transport_iscsi rfkill intel_rapl_msr intel_rapl_common isst_if_common sunrpc skx_edac nfit libnvdimm x86_pkg_temp_thermal intel_powerclamp coretemp kvm_intel ipmi_ssif kvm mgag200 i2c_algo_bit irqbypass drm_kms_helper crct10dif_pclmul crc32_pclmul syscopyarea ghash_clmulni_intel iTCO_wdt sysfillrect iTCO_vendor_support sysimgblt rapl fb_sys_fops dcdbas intel_cstate drm acpi_ipmi ipmi_si mei_me dell_smbios intel_uncore ipmi_devintf mei i2c_i801 dell_wmi_descriptor wmi_bmof pcspkr lpc_ich i2c_smbus ipmi_msghandler acpi_power_meter ip_tables xfs libcrc32c sd_mod t10_pi sg ahci libahci libata megaraid_sas tg3 crc32c_intel wmi dm_mirror dm_region_hash dm_log [ 128.562188] dm_mod [ 128.651334] CPU: 23 PID: 1105 Comm: NetworkManager Tainted: G S I 5.10.0-rc1+ #59 [ 128.659939] Hardware name: Dell Inc. PowerEdge R440/04JN2K, BIOS 2.8.1 06/30/2020 [ 128.667419] RIP: 0010:dma_map_page_attrs+0x14c/0x1d0 [ 128.672384] Code: 1c 25 28 00 00 00 0f 85 97 00 00 00 48 83 c4 10 5b 5d 41 5c 41 5d c3 4c 89 da eb d7 48 89 f2 48 2b 50 18 48 89 d0 eb 8d 0f 0b <0f> 0b 48 c7 c0 ff ff ff ff eb c3 48 89 d9 48 8b 40 40 e8 2d a0 aa [ 128.691131] RSP: 0018:ffffae0f0151f3c8 EFLAGS: 00010246 [ 128.696357] RAX: ffffffffc06b7400 RBX: 00000000000005fa RCX: 0000000000000000 [ 128.703488] RDX: 0000000000000040 RSI: ffffcee3c7861200 RDI: ffff9e2bc16cd000 [ 128.710620] RBP: 0000000000000000 R08: 0000000000000002 R09: 0000000000000000 [ 128.717754] R10: 0000000000000002 R11: 0000000000000000 R12: ffff9e472cb291f8 [ 128.724886] R13: ffff9e2bc14da780 R14: ffff9e472bc20000 R15: ffff9e2bc1b14940 [ 128.732020] FS: 00007f887bae23c0(0000) GS:ffff9e4ac01c0000(0000) knlGS:0000000000000000 [ 128.740105] CS: 0010 DS: 0000 ES: 0000 CR0: 0000000080050033 [ 128.745852] CR2: 0000562bc09de998 CR3: 00000003c156c006 CR4: 00000000007706e0 [ 128.752982] DR0: 0000000000000000 DR1: 0000000000000000 DR2: 0000000000000000 [ 128.760114] DR3: 0000000000000000 DR6: 00000000fffe0ff0 DR7: 0000000000000400 [ 128.767247] PKRU: 55555554 [ 128.769961] Call Trace: [ 128.772418] virtqueue_add+0x81e/0xb00 [ 128.776176] virtqueue_add_inbuf_ctx+0x26/0x30 [ 128.780625] try_fill_recv+0x3a2/0x6e0 [virtio_net] [ 128.785509] virtnet_open+0xf9/0x180 [virtio_net] [ 128.790217] __dev_open+0xe8/0x180 [ 128.793620] __dev_change_flags+0x1a7/0x210 [ 128.797808] dev_change_flags+0x21/0x60 [ 128.801646] do_setlink+0x328/0x10e0 [ 128.805227] ? __nla_validate_parse+0x121/0x180 [ 128.809757] ? __nla_parse+0x21/0x30 [ 128.813338] ? inet6_validate_link_af+0x5c/0xf0 [ 128.817871] ? cpumask_next+0x17/0x20 [ 128.821535] ? __snmp6_fill_stats64.isra.54+0x6b/0x110 [ 128.826676] ? __nla_validate_parse+0x47/0x180 [ 128.831120] __rtnl_newlink+0x541/0x8e0 [ 128.834962] ? __nla_reserve+0x38/0x50 [ 128.838713] ? security_sock_rcv_skb+0x2a/0x40 [ 128.843158] ? netlink_deliver_tap+0x2c/0x1e0 [ 128.847518] ? netlink_attachskb+0x1d8/0x220 [ 128.851793] ? skb_queue_tail+0x1b/0x50 [ 128.855641] ? fib6_clean_node+0x43/0x170 [ 128.859652] ? _cond_resched+0x15/0x30 [ 128.863406] ? kmem_cache_alloc_trace+0x3a3/0x420 [ 128.868110] rtnl_newlink+0x43/0x60 [ 128.871602] rtnetlink_rcv_msg+0x12c/0x380 [ 128.875701] ? rtnl_calcit.isra.39+0x110/0x110 [ 128.880147] netlink_rcv_skb+0x50/0x100 [ 128.883987] netlink_unicast+0x1a5/0x280 [ 128.887913] netlink_sendmsg+0x23d/0x470 [ 128.891839] sock_sendmsg+0x5b/0x60 [ 128.895331] ____sys_sendmsg+0x1ef/0x260 [ 128.899255] ? copy_msghdr_from_user+0x5c/0x90 [ 128.903702] ___sys_sendmsg+0x7c/0xc0 [ 128.907369] ? dev_forward_change+0x130/0x130 [ 128.911731] ? sysctl_head_finish.part.29+0x24/0x40 [ 128.916616] ? new_sync_write+0x11f/0x1b0 [ 128.920628] ? mntput_no_expire+0x47/0x240 [ 128.924727] __sys_sendmsg+0x57/0xa0 [ 128.928309] do_syscall_64+0x33/0x40 [ 128.931887] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 128.936937] RIP: 0033:0x7f88792e3857 [ 128.940518] Code: c3 66 90 41 54 41 89 d4 55 48 89 f5 53 89 fb 48 83 ec 10 e8 0b ed ff ff 44 89 e2 48 89 ee 89 df 41 89 c0 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 44 89 c7 48 89 44 24 08 e8 44 ed ff ff 48 [ 128.959263] RSP: 002b:00007ffdca60dea0 EFLAGS: 00000293 ORIG_RAX: 000000000000002e [ 128.966827] RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007f88792e3857 [ 128.973960] RDX: 0000000000000000 RSI: 00007ffdca60def0 RDI: 000000000000000c [ 128.981095] RBP: 00007ffdca60def0 R08: 0000000000000000 R09: 0000000000000000 [ 128.988224] R10: 0000000000000001 R11: 0000000000000293 R12: 0000000000000000 [ 128.995357] R13: 0000000000000000 R14: 00007ffdca60e0a8 R15: 00007ffdca60e09c [ 129.002492] CPU: 23 PID: 1105 Comm: NetworkManager Tainted: G S I 5.10.0-rc1+ #59 [ 129.011093] Hardware name: Dell Inc. PowerEdge R440/04JN2K, BIOS 2.8.1 06/30/2020 [ 129.018571] Call Trace: [ 129.021027] dump_stack+0x57/0x6a [ 129.024346] __warn.cold.14+0xe/0x3d [ 129.027925] ? dma_map_page_attrs+0x14c/0x1d0 [ 129.032283] report_bug+0xbd/0xf0 [ 129.035602] handle_bug+0x44/0x80 [ 129.038922] exc_invalid_op+0x13/0x60 [ 129.042589] asm_exc_invalid_op+0x12/0x20 [ 129.046602] RIP: 0010:dma_map_page_attrs+0x14c/0x1d0 [ 129.051566] Code: 1c 25 28 00 00 00 0f 85 97 00 00 00 48 83 c4 10 5b 5d 41 5c 41 5d c3 4c 89 da eb d7 48 89 f2 48 2b 50 18 48 89 d0 eb 8d 0f 0b <0f> 0b 48 c7 c0 ff ff ff ff eb c3 48 89 d9 48 8b 40 40 e8 2d a0 aa [ 129.070311] RSP: 0018:ffffae0f0151f3c8 EFLAGS: 00010246 [ 129.075536] RAX: ffffffffc06b7400 RBX: 00000000000005fa RCX: 0000000000000000 [ 129.082669] RDX: 0000000000000040 RSI: ffffcee3c7861200 RDI: ffff9e2bc16cd000 [ 129.089803] RBP: 0000000000000000 R08: 0000000000000002 R09: 0000000000000000 [ 129.096936] R10: 0000000000000002 R11: 0000000000000000 R12: ffff9e472cb291f8 [ 129.104068] R13: ffff9e2bc14da780 R14: ffff9e472bc20000 R15: ffff9e2bc1b14940 [ 129.111200] virtqueue_add+0x81e/0xb00 [ 129.114952] virtqueue_add_inbuf_ctx+0x26/0x30 [ 129.119399] try_fill_recv+0x3a2/0x6e0 [virtio_net] [ 129.124280] virtnet_open+0xf9/0x180 [virtio_net] [ 129.128984] __dev_open+0xe8/0x180 [ 129.132390] __dev_change_flags+0x1a7/0x210 [ 129.136575] dev_change_flags+0x21/0x60 [ 129.140415] do_setlink+0x328/0x10e0 [ 129.143994] ? __nla_validate_parse+0x121/0x180 [ 129.148528] ? __nla_parse+0x21/0x30 [ 129.152107] ? inet6_validate_link_af+0x5c/0xf0 [ 129.156639] ? cpumask_next+0x17/0x20 [ 129.160306] ? __snmp6_fill_stats64.isra.54+0x6b/0x110 [ 129.165443] ? __nla_validate_parse+0x47/0x180 [ 129.169890] __rtnl_newlink+0x541/0x8e0 [ 129.173731] ? __nla_reserve+0x38/0x50 [ 129.177483] ? security_sock_rcv_skb+0x2a/0x40 [ 129.181928] ? netlink_deliver_tap+0x2c/0x1e0 [ 129.186286] ? netlink_attachskb+0x1d8/0x220 [ 129.190560] ? skb_queue_tail+0x1b/0x50 [ 129.194401] ? fib6_clean_node+0x43/0x170 [ 129.198411] ? _cond_resched+0x15/0x30 [ 129.202163] ? kmem_cache_alloc_trace+0x3a3/0x420 [ 129.206869] rtnl_newlink+0x43/0x60 [ 129.210361] rtnetlink_rcv_msg+0x12c/0x380 [ 129.214462] ? rtnl_calcit.isra.39+0x110/0x110 [ 129.218908] netlink_rcv_skb+0x50/0x100 [ 129.222747] netlink_unicast+0x1a5/0x280 [ 129.226672] netlink_sendmsg+0x23d/0x470 [ 129.230599] sock_sendmsg+0x5b/0x60 [ 129.234090] ____sys_sendmsg+0x1ef/0x260 [ 129.238015] ? copy_msghdr_from_user+0x5c/0x90 [ 129.242461] ___sys_sendmsg+0x7c/0xc0 [ 129.246128] ? dev_forward_change+0x130/0x130 [ 129.250487] ? sysctl_head_finish.part.29+0x24/0x40 [ 129.255368] ? new_sync_write+0x11f/0x1b0 [ 129.259381] ? mntput_no_expire+0x47/0x240 [ 129.263478] __sys_sendmsg+0x57/0xa0 [ 129.267058] do_syscall_64+0x33/0x40 [ 129.270639] entry_SYSCALL_64_after_hwframe+0x44/0xa9 [ 129.275689] RIP: 0033:0x7f88792e3857 [ 129.279268] Code: c3 66 90 41 54 41 89 d4 55 48 89 f5 53 89 fb 48 83 ec 10 e8 0b ed ff ff 44 89 e2 48 89 ee 89 df 41 89 c0 b8 2e 00 00 00 0f 05 <48> 3d 00 f0 ff ff 77 35 44 89 c7 48 89 44 24 08 e8 44 ed ff ff 48 [ 129.298015] RSP: 002b:00007ffdca60dea0 EFLAGS: 00000293 ORIG_RAX: 000000000000002e [ 129.305581] RAX: ffffffffffffffda RBX: 000000000000000c RCX: 00007f88792e3857 [ 129.312712] RDX: 0000000000000000 RSI: 00007ffdca60def0 RDI: 000000000000000c [ 129.319846] RBP: 00007ffdca60def0 R08: 0000000000000000 R09: 0000000000000000 [ 129.326978] R10: 0000000000000001 R11: 0000000000000293 R12: 0000000000000000 [ 129.334109] R13: 0000000000000000 R14: 00007ffdca60e0a8 R15: 00007ffdca60e09c [ 129.341249] ---[ end trace c551e8028fbaf59d ]--- [ 129.351207] net eth0: Unexpected TXQ (0) queue failure: -12 [ 129.360445] net eth0: Unexpected TXQ (0) queue failure: -12 [ 129.824428] net eth0: Unexpected TXQ (0) queue failure: -12 Fixes: 2c53d0f64c06 ("vdpasim: vDPA device simulator") Signed-off-by: Laurent Vivier <lvivier@redhat.com> Link: https://lore.kernel.org/r/20201027175914.689278-1-lvivier@redhat.com Signed-off-by: Michael S. Tsirkin <mst@redhat.com> Cc: stable@vger.kernel.org Acked-by: Jason Wang <jasowang@redhat.com>
2020-10-28 01:59:14 +08:00
dev->dma_mask = &dev->coherent_dma_mask;
if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(64)))
goto err_iommu;
set_dma_ops(dev, &vdpasim_dma_ops);
vdpasim->config = kzalloc(dev_attr->config_size, GFP_KERNEL);
if (!vdpasim->config)
goto err_iommu;
vdpasim->vqs = kcalloc(dev_attr->nvqs, sizeof(struct vdpasim_virtqueue),
GFP_KERNEL);
if (!vdpasim->vqs)
goto err_iommu;
vdpasim->iommu = vhost_iotlb_alloc(max_iotlb_entries, 0);
if (!vdpasim->iommu)
goto err_iommu;
vdpasim->buffer = kmalloc(PAGE_SIZE, GFP_KERNEL);
if (!vdpasim->buffer)
goto err_iommu;
if (macaddr) {
mac_pton(macaddr, macaddr_buf);
if (!is_valid_ether_addr(macaddr_buf)) {
ret = -EADDRNOTAVAIL;
goto err_iommu;
}
} else {
eth_random_addr(macaddr_buf);
}
for (i = 0; i < dev_attr->nvqs; i++)
vringh_set_iotlb(&vdpasim->vqs[i].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,
const struct vdpa_vq_state *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->avail_index;
spin_unlock(&vdpasim->lock);
return 0;
}
static int vdpasim_get_vq_state(struct vdpa_device *vdpa, u16 idx,
struct vdpa_vq_state *state)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
struct vdpasim_virtqueue *vq = &vdpasim->vqs[idx];
struct vringh *vrh = &vq->vring;
state->avail_index = vrh->last_avail_idx;
return 0;
}
static u32 vdpasim_get_vq_align(struct vdpa_device *vdpa)
{
return VDPASIM_QUEUE_ALIGN;
}
static u64 vdpasim_get_features(struct vdpa_device *vdpa)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
return vdpasim->dev_attr.supported_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_ACCESS_PLATFORM)))
return -EINVAL;
vdpasim->features = features & vdpasim->dev_attr.supported_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)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
return vdpasim->dev_attr.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 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 > vdpasim->dev_attr.config_size)
return;
if (vdpasim->dev_attr.get_config)
vdpasim->dev_attr.get_config(vdpasim, vdpasim->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)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
if (offset + len > vdpasim->dev_attr.config_size)
return;
memcpy(vdpasim->config + offset, buf, len);
if (vdpasim->dev_attr.set_config)
vdpasim->dev_attr.set_config(vdpasim, vdpasim->config);
}
static u32 vdpasim_get_generation(struct vdpa_device *vdpa)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
return vdpasim->generation;
}
static struct vdpa_iova_range vdpasim_get_iova_range(struct vdpa_device *vdpa)
{
struct vdpa_iova_range range = {
.first = 0ULL,
.last = ULLONG_MAX,
};
return range;
}
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;
spin_lock(&vdpasim->iommu_lock);
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;
}
spin_unlock(&vdpasim->iommu_lock);
return 0;
err:
vhost_iotlb_reset(vdpasim->iommu);
spin_unlock(&vdpasim->iommu_lock);
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);
int ret;
spin_lock(&vdpasim->iommu_lock);
ret = vhost_iotlb_add_range(vdpasim->iommu, iova, iova + size - 1, pa,
perm);
spin_unlock(&vdpasim->iommu_lock);
return ret;
}
static int vdpasim_dma_unmap(struct vdpa_device *vdpa, u64 iova, u64 size)
{
struct vdpasim *vdpasim = vdpa_to_sim(vdpa);
spin_lock(&vdpasim->iommu_lock);
vhost_iotlb_del_range(vdpasim->iommu, iova, iova + size - 1);
spin_unlock(&vdpasim->iommu_lock);
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);
kfree(vdpasim->vqs);
kfree(vdpasim->config);
}
static const struct vdpa_config_ops vdpasim_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,
.get_iova_range = vdpasim_get_iova_range,
.dma_map = vdpasim_dma_map,
.dma_unmap = vdpasim_dma_unmap,
.free = vdpasim_free,
};
static const struct vdpa_config_ops vdpasim_batch_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,
.get_iova_range = vdpasim_get_iova_range,
.set_map = vdpasim_set_map,
.free = vdpasim_free,
};
static void vdpasim_net_get_config(struct vdpasim *vdpasim, void *config)
{
struct virtio_net_config *net_config =
(struct virtio_net_config *)config;
net_config->mtu = cpu_to_vdpasim16(vdpasim, 1500);
net_config->status = cpu_to_vdpasim16(vdpasim, VIRTIO_NET_S_LINK_UP);
memcpy(net_config->mac, macaddr_buf, ETH_ALEN);
}
static int __init vdpasim_dev_init(void)
{
struct vdpasim_dev_attr dev_attr = {};
dev_attr.id = VIRTIO_ID_NET;
dev_attr.supported_features = VDPASIM_NET_FEATURES;
dev_attr.nvqs = VDPASIM_VQ_NUM;
dev_attr.config_size = sizeof(struct virtio_net_config);
dev_attr.get_config = vdpasim_net_get_config;
dev_attr.work_fn = vdpasim_net_work;
vdpasim_dev = vdpasim_create(&dev_attr);
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);