renegade-project/linux-next
2
0
Fork 0
mirror of https://github.com/edk2-porting/linux-next.git synced 2024-12-22 20:23:57 +08:00
Code
3c6d405666
linux-next/samples/vfio-mdev/mtty.c
Christoph Hellwig c68ea0d00a vfio: simplify iommu group allocation for mediated devices 
Reuse the logic in vfio_noiommu_group_alloc to allocate a fake
single-device iommu group for mediated devices by factoring out a common
function, and replacing the noiommu boolean field in struct vfio_group
with an enum to distinguish the three different kinds of groups.

Signed-off-by: Christoph Hellwig <hch@lst.de>
Reviewed-by: Kevin Tian <kevin.tian@intel.com>
Link: https://lore.kernel.org/r/20210924155705.4258-8-hch@lst.de
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>
2021-09-30 12:46:44 -06:00

1427 lines
32 KiB
C
Raw Blame History

// SPDX-License-Identifier: GPL-2.0-only
/*
* Mediated virtual PCI serial host device driver
*
* Copyright (c) 2016, NVIDIA CORPORATION. All rights reserved.
* Author: Neo Jia <cjia@nvidia.com>
* Kirti Wankhede <kwankhede@nvidia.com>
*
* Sample driver that creates mdev device that simulates serial port over PCI
* card.
*/
#include <linux/init.h>
#include <linux/module.h>
#include <linux/device.h>
#include <linux/kernel.h>
#include <linux/fs.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/cdev.h>
#include <linux/sched.h>
#include <linux/wait.h>
#include <linux/uuid.h>
#include <linux/vfio.h>
#include <linux/iommu.h>
#include <linux/sysfs.h>
#include <linux/ctype.h>
#include <linux/file.h>
#include <linux/mdev.h>
#include <linux/pci.h>
#include <linux/serial.h>
#include <uapi/linux/serial_reg.h>
#include <linux/eventfd.h>
/*
* #defines
*/
#define VERSION_STRING "0.1"
#define DRIVER_AUTHOR "NVIDIA Corporation"
#define MTTY_CLASS_NAME "mtty"
#define MTTY_NAME "mtty"
#define MTTY_STRING_LEN 16
#define MTTY_CONFIG_SPACE_SIZE 0xff
#define MTTY_IO_BAR_SIZE 0x8
#define MTTY_MMIO_BAR_SIZE 0x100000
#define STORE_LE16(addr, val) (*(u16 *)addr = val)
#define STORE_LE32(addr, val) (*(u32 *)addr = val)
#define MAX_FIFO_SIZE 16
#define CIRCULAR_BUF_INC_IDX(idx) (idx = (idx + 1) & (MAX_FIFO_SIZE - 1))
#define MTTY_VFIO_PCI_OFFSET_SHIFT 40
#define MTTY_VFIO_PCI_OFFSET_TO_INDEX(off) (off >> MTTY_VFIO_PCI_OFFSET_SHIFT)
#define MTTY_VFIO_PCI_INDEX_TO_OFFSET(index) \
((u64)(index) << MTTY_VFIO_PCI_OFFSET_SHIFT)
#define MTTY_VFIO_PCI_OFFSET_MASK \
(((u64)(1) << MTTY_VFIO_PCI_OFFSET_SHIFT) - 1)
#define MAX_MTTYS 24
/*
* Global Structures
*/
static struct mtty_dev {
dev_t vd_devt;
struct class *vd_class;
struct cdev vd_cdev;
struct idr vd_idr;
struct device dev;
} mtty_dev;
struct mdev_region_info {
u64 start;
u64 phys_start;
u32 size;
u64 vfio_offset;
};
#if defined(DEBUG_REGS)
static const char *wr_reg[] = {
"TX",
"IER",
"FCR",
"LCR",
"MCR",
"LSR",
"MSR",
"SCR"
};
static const char *rd_reg[] = {
"RX",
"IER",
"IIR",
"LCR",
"MCR",
"LSR",
"MSR",
"SCR"
};
#endif
/* loop back buffer */
struct rxtx {
u8 fifo[MAX_FIFO_SIZE];
u8 head, tail;
u8 count;
};
struct serial_port {
u8 uart_reg[8]; /* 8 registers */
struct rxtx rxtx; /* loop back buffer */
bool dlab;
bool overrun;
u16 divisor;
u8 fcr; /* FIFO control register */
u8 max_fifo_size;
u8 intr_trigger_level; /* interrupt trigger level */
};
/* State of each mdev device */
struct mdev_state {
struct vfio_device vdev;
int irq_fd;
struct eventfd_ctx *intx_evtfd;
struct eventfd_ctx *msi_evtfd;
int irq_index;
u8 *vconfig;
struct mutex ops_lock;
struct mdev_device *mdev;
struct mdev_region_info region_info[VFIO_PCI_NUM_REGIONS];
u32 bar_mask[VFIO_PCI_NUM_REGIONS];
struct list_head next;
struct serial_port s[2];
struct mutex rxtx_lock;
struct vfio_device_info dev_info;
int nr_ports;
};
static atomic_t mdev_avail_ports = ATOMIC_INIT(MAX_MTTYS);
static const struct file_operations vd_fops = {
.owner = THIS_MODULE,
};
static const struct vfio_device_ops mtty_dev_ops;
/* function prototypes */
static int mtty_trigger_interrupt(struct mdev_state *mdev_state);
/* Helper functions */
static void dump_buffer(u8 *buf, uint32_t count)
{
#if defined(DEBUG)
int i;
pr_info("Buffer:\n");
for (i = 0; i < count; i++) {
pr_info("%2x ", *(buf + i));
if ((i + 1) % 16 == 0)
pr_info("\n");
}
#endif
}
static void mtty_create_config_space(struct mdev_state *mdev_state)
{
/* PCI dev ID */
STORE_LE32((u32 *) &mdev_state->vconfig[0x0], 0x32534348);
/* Control: I/O+, Mem-, BusMaster- */
STORE_LE16((u16 *) &mdev_state->vconfig[0x4], 0x0001);
/* Status: capabilities list absent */
STORE_LE16((u16 *) &mdev_state->vconfig[0x6], 0x0200);
/* Rev ID */
mdev_state->vconfig[0x8] = 0x10;
/* programming interface class : 16550-compatible serial controller */
mdev_state->vconfig[0x9] = 0x02;
/* Sub class : 00 */
mdev_state->vconfig[0xa] = 0x00;
/* Base class : Simple Communication controllers */
mdev_state->vconfig[0xb] = 0x07;
/* base address registers */
/* BAR0: IO space */
STORE_LE32((u32 *) &mdev_state->vconfig[0x10], 0x000001);
mdev_state->bar_mask[0] = ~(MTTY_IO_BAR_SIZE) + 1;
if (mdev_state->nr_ports == 2) {
/* BAR1: IO space */
STORE_LE32((u32 *) &mdev_state->vconfig[0x14], 0x000001);
mdev_state->bar_mask[1] = ~(MTTY_IO_BAR_SIZE) + 1;
}
/* Subsystem ID */
STORE_LE32((u32 *) &mdev_state->vconfig[0x2c], 0x32534348);
mdev_state->vconfig[0x34] = 0x00; /* Cap Ptr */
mdev_state->vconfig[0x3d] = 0x01; /* interrupt pin (INTA#) */
/* Vendor specific data */
mdev_state->vconfig[0x40] = 0x23;
mdev_state->vconfig[0x43] = 0x80;
mdev_state->vconfig[0x44] = 0x23;
mdev_state->vconfig[0x48] = 0x23;
mdev_state->vconfig[0x4c] = 0x23;
mdev_state->vconfig[0x60] = 0x50;
mdev_state->vconfig[0x61] = 0x43;
mdev_state->vconfig[0x62] = 0x49;
mdev_state->vconfig[0x63] = 0x20;
mdev_state->vconfig[0x64] = 0x53;
mdev_state->vconfig[0x65] = 0x65;
mdev_state->vconfig[0x66] = 0x72;
mdev_state->vconfig[0x67] = 0x69;
mdev_state->vconfig[0x68] = 0x61;
mdev_state->vconfig[0x69] = 0x6c;
mdev_state->vconfig[0x6a] = 0x2f;
mdev_state->vconfig[0x6b] = 0x55;
mdev_state->vconfig[0x6c] = 0x41;
mdev_state->vconfig[0x6d] = 0x52;
mdev_state->vconfig[0x6e] = 0x54;
}
static void handle_pci_cfg_write(struct mdev_state *mdev_state, u16 offset,
u8 *buf, u32 count)
{
u32 cfg_addr, bar_mask, bar_index = 0;
switch (offset) {
case 0x04: /* device control */
case 0x06: /* device status */
/* do nothing */
break;
case 0x3c: /* interrupt line */
mdev_state->vconfig[0x3c] = buf[0];
break;
case 0x3d:
/*
* Interrupt Pin is hardwired to INTA.
* This field is write protected by hardware
*/
break;
case 0x10: /* BAR0 */
case 0x14: /* BAR1 */
if (offset == 0x10)
bar_index = 0;
else if (offset == 0x14)
bar_index = 1;
if ((mdev_state->nr_ports == 1) && (bar_index == 1)) {
STORE_LE32(&mdev_state->vconfig[offset], 0);
break;
}
cfg_addr = *(u32 *)buf;
pr_info("BAR%d addr 0x%x\n", bar_index, cfg_addr);
if (cfg_addr == 0xffffffff) {
bar_mask = mdev_state->bar_mask[bar_index];
cfg_addr = (cfg_addr & bar_mask);
}
cfg_addr |= (mdev_state->vconfig[offset] & 0x3ul);
STORE_LE32(&mdev_state->vconfig[offset], cfg_addr);
break;
case 0x18: /* BAR2 */
case 0x1c: /* BAR3 */
case 0x20: /* BAR4 */
STORE_LE32(&mdev_state->vconfig[offset], 0);
break;
default:
pr_info("PCI config write @0x%x of %d bytes not handled\n",
offset, count);
break;
}
}
static void handle_bar_write(unsigned int index, struct mdev_state *mdev_state,
u16 offset, u8 *buf, u32 count)
{
u8 data = *buf;
/* Handle data written by guest */
switch (offset) {
case UART_TX:
/* if DLAB set, data is LSB of divisor */
if (mdev_state->s[index].dlab) {
mdev_state->s[index].divisor |= data;
break;
}
mutex_lock(&mdev_state->rxtx_lock);
/* save in TX buffer */
if (mdev_state->s[index].rxtx.count <
mdev_state->s[index].max_fifo_size) {
mdev_state->s[index].rxtx.fifo[
mdev_state->s[index].rxtx.head] = data;
mdev_state->s[index].rxtx.count++;
CIRCULAR_BUF_INC_IDX(mdev_state->s[index].rxtx.head);
mdev_state->s[index].overrun = false;
/*
* Trigger interrupt if receive data interrupt is
* enabled and fifo reached trigger level
*/
if ((mdev_state->s[index].uart_reg[UART_IER] &
UART_IER_RDI) &&
(mdev_state->s[index].rxtx.count ==
mdev_state->s[index].intr_trigger_level)) {
/* trigger interrupt */
#if defined(DEBUG_INTR)
pr_err("Serial port %d: Fifo level trigger\n",
index);
#endif
mtty_trigger_interrupt(mdev_state);
}
} else {
#if defined(DEBUG_INTR)
pr_err("Serial port %d: Buffer Overflow\n", index);
#endif
mdev_state->s[index].overrun = true;
/*
* Trigger interrupt if receiver line status interrupt
* is enabled
*/
if (mdev_state->s[index].uart_reg[UART_IER] &
UART_IER_RLSI)
mtty_trigger_interrupt(mdev_state);
}
mutex_unlock(&mdev_state->rxtx_lock);
break;
case UART_IER:
/* if DLAB set, data is MSB of divisor */
if (mdev_state->s[index].dlab)
mdev_state->s[index].divisor |= (u16)data << 8;
else {
mdev_state->s[index].uart_reg[offset] = data;
mutex_lock(&mdev_state->rxtx_lock);
if ((data & UART_IER_THRI) &&
(mdev_state->s[index].rxtx.head ==
mdev_state->s[index].rxtx.tail)) {
#if defined(DEBUG_INTR)
pr_err("Serial port %d: IER_THRI write\n",
index);
#endif
mtty_trigger_interrupt(mdev_state);
}
mutex_unlock(&mdev_state->rxtx_lock);
}
break;
case UART_FCR:
mdev_state->s[index].fcr = data;
mutex_lock(&mdev_state->rxtx_lock);
if (data & (UART_FCR_CLEAR_RCVR | UART_FCR_CLEAR_XMIT)) {
/* clear loop back FIFO */
mdev_state->s[index].rxtx.count = 0;
mdev_state->s[index].rxtx.head = 0;
mdev_state->s[index].rxtx.tail = 0;
}
mutex_unlock(&mdev_state->rxtx_lock);
switch (data & UART_FCR_TRIGGER_MASK) {
case UART_FCR_TRIGGER_1:
mdev_state->s[index].intr_trigger_level = 1;
break;
case UART_FCR_TRIGGER_4:
mdev_state->s[index].intr_trigger_level = 4;
break;
case UART_FCR_TRIGGER_8:
mdev_state->s[index].intr_trigger_level = 8;
break;
case UART_FCR_TRIGGER_14:
mdev_state->s[index].intr_trigger_level = 14;
break;
}
/*
* Set trigger level to 1 otherwise or implement timer with
* timeout of 4 characters and on expiring that timer set
* Recevice data timeout in IIR register
*/
mdev_state->s[index].intr_trigger_level = 1;
if (data & UART_FCR_ENABLE_FIFO)
mdev_state->s[index].max_fifo_size = MAX_FIFO_SIZE;
else {
mdev_state->s[index].max_fifo_size = 1;
mdev_state->s[index].intr_trigger_level = 1;
}
break;
case UART_LCR:
if (data & UART_LCR_DLAB) {
mdev_state->s[index].dlab = true;
mdev_state->s[index].divisor = 0;
} else
mdev_state->s[index].dlab = false;
mdev_state->s[index].uart_reg[offset] = data;
break;
case UART_MCR:
mdev_state->s[index].uart_reg[offset] = data;
if ((mdev_state->s[index].uart_reg[UART_IER] & UART_IER_MSI) &&
(data & UART_MCR_OUT2)) {
#if defined(DEBUG_INTR)
pr_err("Serial port %d: MCR_OUT2 write\n", index);
#endif
mtty_trigger_interrupt(mdev_state);
}
if ((mdev_state->s[index].uart_reg[UART_IER] & UART_IER_MSI) &&
(data & (UART_MCR_RTS | UART_MCR_DTR))) {
#if defined(DEBUG_INTR)
pr_err("Serial port %d: MCR RTS/DTR write\n", index);
#endif
mtty_trigger_interrupt(mdev_state);
}
break;
case UART_LSR:
case UART_MSR:
/* do nothing */
break;
case UART_SCR:
mdev_state->s[index].uart_reg[offset] = data;
break;
default:
break;
}
}
static void handle_bar_read(unsigned int index, struct mdev_state *mdev_state,
u16 offset, u8 *buf, u32 count)
{
/* Handle read requests by guest */
switch (offset) {
case UART_RX:
/* if DLAB set, data is LSB of divisor */
if (mdev_state->s[index].dlab) {
*buf = (u8)mdev_state->s[index].divisor;
break;
}
mutex_lock(&mdev_state->rxtx_lock);
/* return data in tx buffer */
if (mdev_state->s[index].rxtx.head !=
mdev_state->s[index].rxtx.tail) {
*buf = mdev_state->s[index].rxtx.fifo[
mdev_state->s[index].rxtx.tail];
mdev_state->s[index].rxtx.count--;
CIRCULAR_BUF_INC_IDX(mdev_state->s[index].rxtx.tail);
}
if (mdev_state->s[index].rxtx.head ==
mdev_state->s[index].rxtx.tail) {
/*
* Trigger interrupt if tx buffer empty interrupt is
* enabled and fifo is empty
*/
#if defined(DEBUG_INTR)
pr_err("Serial port %d: Buffer Empty\n", index);
#endif
if (mdev_state->s[index].uart_reg[UART_IER] &
UART_IER_THRI)
mtty_trigger_interrupt(mdev_state);
}
mutex_unlock(&mdev_state->rxtx_lock);
break;
case UART_IER:
if (mdev_state->s[index].dlab) {
*buf = (u8)(mdev_state->s[index].divisor >> 8);
break;
}
*buf = mdev_state->s[index].uart_reg[offset] & 0x0f;
break;
case UART_IIR:
{
u8 ier = mdev_state->s[index].uart_reg[UART_IER];
*buf = 0;
mutex_lock(&mdev_state->rxtx_lock);
/* Interrupt priority 1: Parity, overrun, framing or break */
if ((ier & UART_IER_RLSI) && mdev_state->s[index].overrun)
*buf |= UART_IIR_RLSI;
/* Interrupt priority 2: Fifo trigger level reached */
if ((ier & UART_IER_RDI) &&
(mdev_state->s[index].rxtx.count >=
mdev_state->s[index].intr_trigger_level))
*buf |= UART_IIR_RDI;
/* Interrupt priotiry 3: transmitter holding register empty */
if ((ier & UART_IER_THRI) &&
(mdev_state->s[index].rxtx.head ==
mdev_state->s[index].rxtx.tail))
*buf |= UART_IIR_THRI;
/* Interrupt priotiry 4: Modem status: CTS, DSR, RI or DCD */
if ((ier & UART_IER_MSI) &&
(mdev_state->s[index].uart_reg[UART_MCR] &
(UART_MCR_RTS | UART_MCR_DTR)))
*buf |= UART_IIR_MSI;
/* bit0: 0=> interrupt pending, 1=> no interrupt is pending */
if (*buf == 0)
*buf = UART_IIR_NO_INT;
/* set bit 6 & 7 to be 16550 compatible */
*buf |= 0xC0;
mutex_unlock(&mdev_state->rxtx_lock);
}
break;
case UART_LCR:
case UART_MCR:
*buf = mdev_state->s[index].uart_reg[offset];
break;
case UART_LSR:
{
u8 lsr = 0;
mutex_lock(&mdev_state->rxtx_lock);
/* atleast one char in FIFO */
if (mdev_state->s[index].rxtx.head !=
mdev_state->s[index].rxtx.tail)
lsr |= UART_LSR_DR;
/* if FIFO overrun */
if (mdev_state->s[index].overrun)
lsr |= UART_LSR_OE;
/* transmit FIFO empty and tramsitter empty */
if (mdev_state->s[index].rxtx.head ==
mdev_state->s[index].rxtx.tail)
lsr |= UART_LSR_TEMT | UART_LSR_THRE;
mutex_unlock(&mdev_state->rxtx_lock);
*buf = lsr;
break;
}
case UART_MSR:
*buf = UART_MSR_DSR | UART_MSR_DDSR | UART_MSR_DCD;
mutex_lock(&mdev_state->rxtx_lock);
/* if AFE is 1 and FIFO have space, set CTS bit */
if (mdev_state->s[index].uart_reg[UART_MCR] &
UART_MCR_AFE) {
if (mdev_state->s[index].rxtx.count <
mdev_state->s[index].max_fifo_size)
*buf |= UART_MSR_CTS | UART_MSR_DCTS;
} else
*buf |= UART_MSR_CTS | UART_MSR_DCTS;
mutex_unlock(&mdev_state->rxtx_lock);
break;
case UART_SCR:
*buf = mdev_state->s[index].uart_reg[offset];
break;
default:
break;
}
}
static void mdev_read_base(struct mdev_state *mdev_state)
{
int index, pos;
u32 start_lo, start_hi;
u32 mem_type;
pos = PCI_BASE_ADDRESS_0;
for (index = 0; index <= VFIO_PCI_BAR5_REGION_INDEX; index++) {
if (!mdev_state->region_info[index].size)
continue;
start_lo = (*(u32 *)(mdev_state->vconfig + pos)) &
PCI_BASE_ADDRESS_MEM_MASK;
mem_type = (*(u32 *)(mdev_state->vconfig + pos)) &
PCI_BASE_ADDRESS_MEM_TYPE_MASK;
switch (mem_type) {
case PCI_BASE_ADDRESS_MEM_TYPE_64:
start_hi = (*(u32 *)(mdev_state->vconfig + pos + 4));
pos += 4;
break;
case PCI_BASE_ADDRESS_MEM_TYPE_32:
case PCI_BASE_ADDRESS_MEM_TYPE_1M:
/* 1M mem BAR treated as 32-bit BAR */
default:
/* mem unknown type treated as 32-bit BAR */
start_hi = 0;
break;
}
pos += 4;
mdev_state->region_info[index].start = ((u64)start_hi << 32) |
start_lo;
}
}
static ssize_t mdev_access(struct mdev_state *mdev_state, u8 *buf, size_t count,
loff_t pos, bool is_write)
{
unsigned int index;
loff_t offset;
int ret = 0;
if (!buf)
return -EINVAL;
mutex_lock(&mdev_state->ops_lock);
index = MTTY_VFIO_PCI_OFFSET_TO_INDEX(pos);
offset = pos & MTTY_VFIO_PCI_OFFSET_MASK;
switch (index) {
case VFIO_PCI_CONFIG_REGION_INDEX:
#if defined(DEBUG)
pr_info("%s: PCI config space %s at offset 0x%llx\n",
__func__, is_write ? "write" : "read", offset);
#endif
if (is_write) {
dump_buffer(buf, count);
handle_pci_cfg_write(mdev_state, offset, buf, count);
} else {
memcpy(buf, (mdev_state->vconfig + offset), count);
dump_buffer(buf, count);
}
break;
case VFIO_PCI_BAR0_REGION_INDEX ... VFIO_PCI_BAR5_REGION_INDEX:
if (!mdev_state->region_info[index].start)
mdev_read_base(mdev_state);
if (is_write) {
dump_buffer(buf, count);
#if defined(DEBUG_REGS)
pr_info("%s: BAR%d WR @0x%llx %s val:0x%02x dlab:%d\n",
__func__, index, offset, wr_reg[offset],
*buf, mdev_state->s[index].dlab);
#endif
handle_bar_write(index, mdev_state, offset, buf, count);
} else {
handle_bar_read(index, mdev_state, offset, buf, count);
dump_buffer(buf, count);
#if defined(DEBUG_REGS)
pr_info("%s: BAR%d RD @0x%llx %s val:0x%02x dlab:%d\n",
__func__, index, offset, rd_reg[offset],
*buf, mdev_state->s[index].dlab);
#endif
}
break;
default:
ret = -1;
goto accessfailed;
}
ret = count;
accessfailed:
mutex_unlock(&mdev_state->ops_lock);
return ret;
}
static int mtty_probe(struct mdev_device *mdev)
{
struct mdev_state *mdev_state;
int nr_ports = mdev_get_type_group_id(mdev) + 1;
int avail_ports = atomic_read(&mdev_avail_ports);
int ret;
do {
if (avail_ports < nr_ports)
return -ENOSPC;
} while (!atomic_try_cmpxchg(&mdev_avail_ports,
&avail_ports, avail_ports - nr_ports));
mdev_state = kzalloc(sizeof(struct mdev_state), GFP_KERNEL);
if (mdev_state == NULL) {
ret = -ENOMEM;
goto err_nr_ports;
}
vfio_init_group_dev(&mdev_state->vdev, &mdev->dev, &mtty_dev_ops);
mdev_state->nr_ports = nr_ports;
mdev_state->irq_index = -1;
mdev_state->s[0].max_fifo_size = MAX_FIFO_SIZE;
mdev_state->s[1].max_fifo_size = MAX_FIFO_SIZE;
mutex_init(&mdev_state->rxtx_lock);
mdev_state->vconfig = kzalloc(MTTY_CONFIG_SPACE_SIZE, GFP_KERNEL);
if (mdev_state->vconfig == NULL) {
ret = -ENOMEM;
goto err_state;
}
mutex_init(&mdev_state->ops_lock);
mdev_state->mdev = mdev;
mtty_create_config_space(mdev_state);
ret = vfio_register_emulated_iommu_dev(&mdev_state->vdev);
if (ret)
goto err_vconfig;
dev_set_drvdata(&mdev->dev, mdev_state);
return 0;
err_vconfig:
kfree(mdev_state->vconfig);
err_state:
vfio_uninit_group_dev(&mdev_state->vdev);
kfree(mdev_state);
err_nr_ports:
atomic_add(nr_ports, &mdev_avail_ports);
return ret;
}
static void mtty_remove(struct mdev_device *mdev)
{
struct mdev_state *mdev_state = dev_get_drvdata(&mdev->dev);
int nr_ports = mdev_state->nr_ports;
vfio_unregister_group_dev(&mdev_state->vdev);
kfree(mdev_state->vconfig);
vfio_uninit_group_dev(&mdev_state->vdev);
kfree(mdev_state);
atomic_add(nr_ports, &mdev_avail_ports);
}
static int mtty_reset(struct mdev_state *mdev_state)
{
pr_info("%s: called\n", __func__);
return 0;
}
static ssize_t mtty_read(struct vfio_device *vdev, char __user *buf,
size_t count, loff_t *ppos)
{
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
unsigned int done = 0;
int ret;
while (count) {
size_t filled;
if (count >= 4 && !(*ppos % 4)) {
u32 val;
ret = mdev_access(mdev_state, (u8 *)&val, sizeof(val),
*ppos, false);
if (ret <= 0)
goto read_err;
if (copy_to_user(buf, &val, sizeof(val)))
goto read_err;
filled = 4;
} else if (count >= 2 && !(*ppos % 2)) {
u16 val;
ret = mdev_access(mdev_state, (u8 *)&val, sizeof(val),
*ppos, false);
if (ret <= 0)
goto read_err;
if (copy_to_user(buf, &val, sizeof(val)))
goto read_err;
filled = 2;
} else {
u8 val;
ret = mdev_access(mdev_state, (u8 *)&val, sizeof(val),
*ppos, false);
if (ret <= 0)
goto read_err;
if (copy_to_user(buf, &val, sizeof(val)))
goto read_err;
filled = 1;
}
count -= filled;
done += filled;
*ppos += filled;
buf += filled;
}
return done;
read_err:
return -EFAULT;
}
static ssize_t mtty_write(struct vfio_device *vdev, const char __user *buf,
size_t count, loff_t *ppos)
{
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
unsigned int done = 0;
int ret;
while (count) {
size_t filled;
if (count >= 4 && !(*ppos % 4)) {
u32 val;
if (copy_from_user(&val, buf, sizeof(val)))
goto write_err;
ret = mdev_access(mdev_state, (u8 *)&val, sizeof(val),
*ppos, true);
if (ret <= 0)
goto write_err;
filled = 4;
} else if (count >= 2 && !(*ppos % 2)) {
u16 val;
if (copy_from_user(&val, buf, sizeof(val)))
goto write_err;
ret = mdev_access(mdev_state, (u8 *)&val, sizeof(val),
*ppos, true);
if (ret <= 0)
goto write_err;
filled = 2;
} else {
u8 val;
if (copy_from_user(&val, buf, sizeof(val)))
goto write_err;
ret = mdev_access(mdev_state, (u8 *)&val, sizeof(val),
*ppos, true);
if (ret <= 0)
goto write_err;
filled = 1;
}
count -= filled;
done += filled;
*ppos += filled;
buf += filled;
}
return done;
write_err:
return -EFAULT;
}
static int mtty_set_irqs(struct mdev_state *mdev_state, uint32_t flags,
unsigned int index, unsigned int start,
unsigned int count, void *data)
{
int ret = 0;
mutex_lock(&mdev_state->ops_lock);
switch (index) {
case VFIO_PCI_INTX_IRQ_INDEX:
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_MASK:
case VFIO_IRQ_SET_ACTION_UNMASK:
break;
case VFIO_IRQ_SET_ACTION_TRIGGER:
{
if (flags & VFIO_IRQ_SET_DATA_NONE) {
pr_info("%s: disable INTx\n", __func__);
if (mdev_state->intx_evtfd)
eventfd_ctx_put(mdev_state->intx_evtfd);
break;
}
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int fd = *(int *)data;
if (fd > 0) {
struct eventfd_ctx *evt;
evt = eventfd_ctx_fdget(fd);
if (IS_ERR(evt)) {
ret = PTR_ERR(evt);
break;
}
mdev_state->intx_evtfd = evt;
mdev_state->irq_fd = fd;
mdev_state->irq_index = index;
break;
}
}
break;
}
}
break;
case VFIO_PCI_MSI_IRQ_INDEX:
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_MASK:
case VFIO_IRQ_SET_ACTION_UNMASK:
break;
case VFIO_IRQ_SET_ACTION_TRIGGER:
if (flags & VFIO_IRQ_SET_DATA_NONE) {
if (mdev_state->msi_evtfd)
eventfd_ctx_put(mdev_state->msi_evtfd);
pr_info("%s: disable MSI\n", __func__);
mdev_state->irq_index = VFIO_PCI_INTX_IRQ_INDEX;
break;
}
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int fd = *(int *)data;
struct eventfd_ctx *evt;
if (fd <= 0)
break;
if (mdev_state->msi_evtfd)
break;
evt = eventfd_ctx_fdget(fd);
if (IS_ERR(evt)) {
ret = PTR_ERR(evt);
break;
}
mdev_state->msi_evtfd = evt;
mdev_state->irq_fd = fd;
mdev_state->irq_index = index;
}
break;
}
break;
case VFIO_PCI_MSIX_IRQ_INDEX:
pr_info("%s: MSIX_IRQ\n", __func__);
break;
case VFIO_PCI_ERR_IRQ_INDEX:
pr_info("%s: ERR_IRQ\n", __func__);
break;
case VFIO_PCI_REQ_IRQ_INDEX:
pr_info("%s: REQ_IRQ\n", __func__);
break;
}
mutex_unlock(&mdev_state->ops_lock);
return ret;
}
static int mtty_trigger_interrupt(struct mdev_state *mdev_state)
{
int ret = -1;
if ((mdev_state->irq_index == VFIO_PCI_MSI_IRQ_INDEX) &&
(!mdev_state->msi_evtfd))
return -EINVAL;
else if ((mdev_state->irq_index == VFIO_PCI_INTX_IRQ_INDEX) &&
(!mdev_state->intx_evtfd)) {
pr_info("%s: Intr eventfd not found\n", __func__);
return -EINVAL;
}
if (mdev_state->irq_index == VFIO_PCI_MSI_IRQ_INDEX)
ret = eventfd_signal(mdev_state->msi_evtfd, 1);
else
ret = eventfd_signal(mdev_state->intx_evtfd, 1);
#if defined(DEBUG_INTR)
pr_info("Intx triggered\n");
#endif
if (ret != 1)
pr_err("%s: eventfd signal failed (%d)\n", __func__, ret);
return ret;
}
static int mtty_get_region_info(struct mdev_state *mdev_state,
struct vfio_region_info *region_info,
u16 *cap_type_id, void **cap_type)
{
unsigned int size = 0;
u32 bar_index;
bar_index = region_info->index;
if (bar_index >= VFIO_PCI_NUM_REGIONS)
return -EINVAL;
mutex_lock(&mdev_state->ops_lock);
switch (bar_index) {
case VFIO_PCI_CONFIG_REGION_INDEX:
size = MTTY_CONFIG_SPACE_SIZE;
break;
case VFIO_PCI_BAR0_REGION_INDEX:
size = MTTY_IO_BAR_SIZE;
break;
case VFIO_PCI_BAR1_REGION_INDEX:
if (mdev_state->nr_ports == 2)
size = MTTY_IO_BAR_SIZE;
break;
default:
size = 0;
break;
}
mdev_state->region_info[bar_index].size = size;
mdev_state->region_info[bar_index].vfio_offset =
MTTY_VFIO_PCI_INDEX_TO_OFFSET(bar_index);
region_info->size = size;
region_info->offset = MTTY_VFIO_PCI_INDEX_TO_OFFSET(bar_index);
region_info->flags = VFIO_REGION_INFO_FLAG_READ |
VFIO_REGION_INFO_FLAG_WRITE;
mutex_unlock(&mdev_state->ops_lock);
return 0;
}
static int mtty_get_irq_info(struct vfio_irq_info *irq_info)
{
switch (irq_info->index) {
case VFIO_PCI_INTX_IRQ_INDEX:
case VFIO_PCI_MSI_IRQ_INDEX:
case VFIO_PCI_REQ_IRQ_INDEX:
break;
default:
return -EINVAL;
}
irq_info->flags = VFIO_IRQ_INFO_EVENTFD;
irq_info->count = 1;
if (irq_info->index == VFIO_PCI_INTX_IRQ_INDEX)
irq_info->flags |= (VFIO_IRQ_INFO_MASKABLE |
VFIO_IRQ_INFO_AUTOMASKED);
else
irq_info->flags |= VFIO_IRQ_INFO_NORESIZE;
return 0;
}
static int mtty_get_device_info(struct vfio_device_info *dev_info)
{
dev_info->flags = VFIO_DEVICE_FLAGS_PCI;
dev_info->num_regions = VFIO_PCI_NUM_REGIONS;
dev_info->num_irqs = VFIO_PCI_NUM_IRQS;
return 0;
}
static long mtty_ioctl(struct vfio_device *vdev, unsigned int cmd,
unsigned long arg)
{
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
int ret = 0;
unsigned long minsz;
switch (cmd) {
case VFIO_DEVICE_GET_INFO:
{
struct vfio_device_info info;
minsz = offsetofend(struct vfio_device_info, num_irqs);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
return -EINVAL;
ret = mtty_get_device_info(&info);
if (ret)
return ret;
memcpy(&mdev_state->dev_info, &info, sizeof(info));
if (copy_to_user((void __user *)arg, &info, minsz))
return -EFAULT;
return 0;
}
case VFIO_DEVICE_GET_REGION_INFO:
{
struct vfio_region_info info;
u16 cap_type_id = 0;
void *cap_type = NULL;
minsz = offsetofend(struct vfio_region_info, offset);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
return -EINVAL;
ret = mtty_get_region_info(mdev_state, &info, &cap_type_id,
&cap_type);
if (ret)
return ret;
if (copy_to_user((void __user *)arg, &info, minsz))
return -EFAULT;
return 0;
}
case VFIO_DEVICE_GET_IRQ_INFO:
{
struct vfio_irq_info info;
minsz = offsetofend(struct vfio_irq_info, count);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if ((info.argsz < minsz) ||
(info.index >= mdev_state->dev_info.num_irqs))
return -EINVAL;
ret = mtty_get_irq_info(&info);
if (ret)
return ret;
if (copy_to_user((void __user *)arg, &info, minsz))
return -EFAULT;
return 0;
}
case VFIO_DEVICE_SET_IRQS:
{
struct vfio_irq_set hdr;
u8 *data = NULL, *ptr = NULL;
size_t data_size = 0;
minsz = offsetofend(struct vfio_irq_set, count);
if (copy_from_user(&hdr, (void __user *)arg, minsz))
return -EFAULT;
ret = vfio_set_irqs_validate_and_prepare(&hdr,
mdev_state->dev_info.num_irqs,
VFIO_PCI_NUM_IRQS,
&data_size);
if (ret)
return ret;
if (data_size) {
ptr = data = memdup_user((void __user *)(arg + minsz),
data_size);
if (IS_ERR(data))
return PTR_ERR(data);
}
ret = mtty_set_irqs(mdev_state, hdr.flags, hdr.index, hdr.start,
hdr.count, data);
kfree(ptr);
return ret;
}
case VFIO_DEVICE_RESET:
return mtty_reset(mdev_state);
}
return -ENOTTY;
}
static ssize_t
sample_mtty_dev_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
return sprintf(buf, "This is phy device\n");
}
static DEVICE_ATTR_RO(sample_mtty_dev);
static struct attribute *mtty_dev_attrs[] = {
&dev_attr_sample_mtty_dev.attr,
NULL,
};
static const struct attribute_group mtty_dev_group = {
.name = "mtty_dev",
.attrs = mtty_dev_attrs,
};
static const struct attribute_group *mtty_dev_groups[] = {
&mtty_dev_group,
NULL,
};
static ssize_t
sample_mdev_dev_show(struct device *dev, struct device_attribute *attr,
char *buf)
{
if (mdev_from_dev(dev))
return sprintf(buf, "This is MDEV %s\n", dev_name(dev));
return sprintf(buf, "\n");
}
static DEVICE_ATTR_RO(sample_mdev_dev);
static struct attribute *mdev_dev_attrs[] = {
&dev_attr_sample_mdev_dev.attr,
NULL,
};
static const struct attribute_group mdev_dev_group = {
.name = "vendor",
.attrs = mdev_dev_attrs,
};
static const struct attribute_group *mdev_dev_groups[] = {
&mdev_dev_group,
NULL,
};
static ssize_t name_show(struct mdev_type *mtype,
struct mdev_type_attribute *attr, char *buf)
{
static const char *name_str[2] = { "Single port serial",
"Dual port serial" };
return sysfs_emit(buf, "%s\n",
name_str[mtype_get_type_group_id(mtype)]);
}
static MDEV_TYPE_ATTR_RO(name);
static ssize_t available_instances_show(struct mdev_type *mtype,
struct mdev_type_attribute *attr,
char *buf)
{
unsigned int ports = mtype_get_type_group_id(mtype) + 1;
return sprintf(buf, "%d\n", atomic_read(&mdev_avail_ports) / ports);
}
static MDEV_TYPE_ATTR_RO(available_instances);
static ssize_t device_api_show(struct mdev_type *mtype,
struct mdev_type_attribute *attr, char *buf)
{
return sprintf(buf, "%s\n", VFIO_DEVICE_API_PCI_STRING);
}
static MDEV_TYPE_ATTR_RO(device_api);
static struct attribute *mdev_types_attrs[] = {
&mdev_type_attr_name.attr,
&mdev_type_attr_device_api.attr,
&mdev_type_attr_available_instances.attr,
NULL,
};
static struct attribute_group mdev_type_group1 = {
.name = "1",
.attrs = mdev_types_attrs,
};
static struct attribute_group mdev_type_group2 = {
.name = "2",
.attrs = mdev_types_attrs,
};
static struct attribute_group *mdev_type_groups[] = {
&mdev_type_group1,
&mdev_type_group2,
NULL,
};
static const struct vfio_device_ops mtty_dev_ops = {
.name = "vfio-mtty",
.read = mtty_read,
.write = mtty_write,
.ioctl = mtty_ioctl,
};
static struct mdev_driver mtty_driver = {
.driver = {
.name = "mtty",
.owner = THIS_MODULE,
.mod_name = KBUILD_MODNAME,
.dev_groups = mdev_dev_groups,
},
.probe = mtty_probe,
.remove = mtty_remove,
};
static const struct mdev_parent_ops mdev_fops = {
.owner = THIS_MODULE,
.device_driver = &mtty_driver,
.dev_attr_groups = mtty_dev_groups,
.supported_type_groups = mdev_type_groups,
};
static void mtty_device_release(struct device *dev)
{
dev_dbg(dev, "mtty: released\n");
}
static int __init mtty_dev_init(void)
{
int ret = 0;
pr_info("mtty_dev: %s\n", __func__);
memset(&mtty_dev, 0, sizeof(mtty_dev));
idr_init(&mtty_dev.vd_idr);
ret = alloc_chrdev_region(&mtty_dev.vd_devt, 0, MINORMASK + 1,
MTTY_NAME);
if (ret < 0) {
pr_err("Error: failed to register mtty_dev, err:%d\n", ret);
return ret;
}
cdev_init(&mtty_dev.vd_cdev, &vd_fops);
cdev_add(&mtty_dev.vd_cdev, mtty_dev.vd_devt, MINORMASK + 1);
pr_info("major_number:%d\n", MAJOR(mtty_dev.vd_devt));
ret = mdev_register_driver(&mtty_driver);
if (ret)
goto err_cdev;
mtty_dev.vd_class = class_create(THIS_MODULE, MTTY_CLASS_NAME);
if (IS_ERR(mtty_dev.vd_class)) {
pr_err("Error: failed to register mtty_dev class\n");
ret = PTR_ERR(mtty_dev.vd_class);
goto err_driver;
}
mtty_dev.dev.class = mtty_dev.vd_class;
mtty_dev.dev.release = mtty_device_release;
dev_set_name(&mtty_dev.dev, "%s", MTTY_NAME);
ret = device_register(&mtty_dev.dev);
if (ret)
goto err_class;
ret = mdev_register_device(&mtty_dev.dev, &mdev_fops);
if (ret)
goto err_device;
return 0;
err_device:
device_unregister(&mtty_dev.dev);
err_class:
class_destroy(mtty_dev.vd_class);
err_driver:
mdev_unregister_driver(&mtty_driver);
err_cdev:
cdev_del(&mtty_dev.vd_cdev);
unregister_chrdev_region(mtty_dev.vd_devt, MINORMASK + 1);
return ret;
}
static void __exit mtty_dev_exit(void)
{
mtty_dev.dev.bus = NULL;
mdev_unregister_device(&mtty_dev.dev);
device_unregister(&mtty_dev.dev);
idr_destroy(&mtty_dev.vd_idr);
mdev_unregister_driver(&mtty_driver);
cdev_del(&mtty_dev.vd_cdev);
unregister_chrdev_region(mtty_dev.vd_devt, MINORMASK + 1);
class_destroy(mtty_dev.vd_class);
mtty_dev.vd_class = NULL;
pr_info("mtty_dev: Unloaded!\n");
}
module_init(mtty_dev_init)
module_exit(mtty_dev_exit)
MODULE_LICENSE("GPL v2");
MODULE_INFO(supported, "Test driver that simulate serial port over PCI");
MODULE_VERSION(VERSION_STRING);
MODULE_AUTHOR(DRIVER_AUTHOR);
View Git Blame Copy Permalink