Piecuu/linux-samsung-r9q2
1
0
Fork 0
Code Issues Pull requests Projects Releases Packages Wiki Activity

VFIO updates for v6.7

Browse source 
- Add support for "chunk mode" in the mlx5-vfio-pci variant driver,
    which allows both larger device image sizes for migration, beyond
    the previous 4GB limit, and also read-ahead support for improved
    migration performance. (Yishai Hadas)
 
  - A new bus master control interface for the CDX bus driver where
    there is no in-band mechanism to toggle device DMA as there is
    through config space on PCI devices. (Nipun Gupta)
 
  - Add explicit alignment directives to vfio data structures to
    reduce the chance of breaking 32-bit userspace.  In most cases
    this is transparent and the remaining cases where data structures
    are padded work within the existing rules for extending data
    structures within vfio.  (Stefan Hajnoczi)
 
  - Resolve a bug in the cdx bus driver noted when compiled with clang
    where missing parenthesis result in the wrong operation.
    (Nathan Chancellor)
 
  - Resolve errors reported by smatch for a function when dealing
    with invalid inputs. (Alex Williamson)
 
  - Add migration support to the mtty vfio/mdev sample driver for
    testing and integration purposes, allowing CI of migration without
    specific hardware requirements.  Also resolve many of the short-
    comings of this driver relative to implementation of the vfio
    interrupt ioctl along the way. (Alex Williamson)
 -----BEGIN PGP SIGNATURE-----
 
 iQJPBAABCAA5FiEEQvbATlQL0amee4qQI5ubbjuwiyIFAmVALFYbHGFsZXgud2ls
 bGlhbXNvbkByZWRoYXQuY29tAAoJECObm247sIsigekP/3IbfI8XPUheSE/4f790
 TAaot7GBvXs7pBGF0ewtVGn/Lo1p3gWDdbGoJNWNoHGUnzCHBkewpCA0cd2xmn4Y
 fJTax1WbBdagmMQ7gGFC2x06JgWHZqSX43rD4ZhQDVgv4LhxBJ/eTAdEZocFIKTL
 a7F/2VH7EaGnybOCOwBDMA8lBr3DJ2eiU25kBYCLRzT61GIwlkurYI7TIX2AcHmW
 iWA7OwJ8YDzVd6IGBad003hDm0MRmkgGvdSR8rHj0Bnz7tSS6UcsNGu0OsUzJdxF
 h6SCaK2w8eKjVaU/OmRZrteq1lwryUbuY1Gdceazj0fcvsMnP19k3nWadSZ2+/mv
 fqC60ahjfN0cIwVeV1GHcGeJI2ImNmCO/Uup7Y+bH9FSc5TQuKK90FRlYmHveUY7
 XEkmi8rcpwEvcrOHT8uZxSRyi6lbjo7i88DWPJ1ByyM82l1rg2ktNI1KEOsvQOdV
 QteFdD3e8mHQYwTAI4MbhWPRvJsN+RM05UKrTvpFHwa4eUqfaJQ0SJktbZIlm/XB
 8UFPF+h6iUFuqJwAH4zlEvDyjMZlAkp9redlKklyGPUreW8MOo/1yoOl7Q5dgibj
 +ZTy7IJjrGXrTpeL1QohBl3BHrGMM2O3rYubkXKZIOU38MdXXn4xzDY+w+fNwB5l
 c/oIN2i1TIUr4Ub0BfI7Fxk7
 =3kXB
 -----END PGP SIGNATURE-----

Merge tag 'vfio-v6.7-rc1' of https://github.com/awilliam/linux-vfio

Pull VFIO updates from Alex Williamson:

 - Add support for "chunk mode" in the mlx5-vfio-pci variant driver,
   which allows both larger device image sizes for migration, beyond the
   previous 4GB limit, and also read-ahead support for improved
   migration performance (Yishai Hadas)

 - A new bus master control interface for the CDX bus driver where there
   is no in-band mechanism to toggle device DMA as there is through
   config space on PCI devices (Nipun Gupta)

 - Add explicit alignment directives to vfio data structures to reduce
   the chance of breaking 32-bit userspace. In most cases this is
   transparent and the remaining cases where data structures are padded
   work within the existing rules for extending data structures within
   vfio (Stefan Hajnoczi)

 - Resolve a bug in the cdx bus driver noted when compiled with clang
   where missing parenthesis result in the wrong operation (Nathan
   Chancellor)

 - Resolve errors reported by smatch for a function when dealing with
   invalid inputs (Alex Williamson)

 - Add migration support to the mtty vfio/mdev sample driver for testing
   and integration purposes, allowing CI of migration without specific
   hardware requirements. Also resolve many of the short- comings of
   this driver relative to implementation of the vfio interrupt ioctl
   along the way (Alex Williamson)

* tag 'vfio-v6.7-rc1' of https://github.com/awilliam/linux-vfio:
  vfio/mtty: Enable migration support
  vfio/mtty: Overhaul mtty interrupt handling
  vfio: Fix smatch errors in vfio_combine_iova_ranges()
  vfio/cdx: Add parentheses between bitwise AND expression and logical NOT
  vfio/mlx5: Activate the chunk mode functionality
  vfio/mlx5: Add support for READING in chunk mode
  vfio/mlx5: Add support for SAVING in chunk mode
  vfio/mlx5: Pre-allocate chunks for the STOP_COPY phase
  vfio/mlx5: Rename some stuff to match chunk mode
  vfio/mlx5: Enable querying state size which is > 4GB
  vfio/mlx5: Refactor the SAVE callback to activate a work only upon an error
  vfio/mlx5: Wake up the reader post of disabling the SAVING migration file
  vfio: use __aligned_u64 in struct vfio_device_ioeventfd
  vfio: use __aligned_u64 in struct vfio_device_gfx_plane_info
  vfio: trivially use __aligned_u64 for ioctl structs
  vfio-cdx: add bus mastering device feature support
  vfio: add bus master feature to device feature ioctl
  cdx: add support for bus mastering
This commit is contained in:
Linus Torvalds 2023-11-01 13:55:40 -10:00
commit deefd5024f
16 changed files with 1298 additions and 192 deletions
Download patch file Download diff file Expand all files Collapse all files

2
samples/vfio-mdev/mbochs.c
View file

@ -1262,7 +1262,7 @@ static long mbochs_ioctl(struct vfio_device *vdev, unsigned int cmd,
case VFIO_DEVICE_QUERY_GFX_PLANE:
{
struct vfio_device_gfx_plane_info plane;
struct vfio_device_gfx_plane_info plane = {};
minsz = offsetofend(struct vfio_device_gfx_plane_info,
region_index);

2
samples/vfio-mdev/mdpy.c
View file

@ -591,7 +591,7 @@ static long mdpy_ioctl(struct vfio_device *vdev, unsigned int cmd,
case VFIO_DEVICE_QUERY_GFX_PLANE:
{
struct vfio_device_gfx_plane_info plane;
struct vfio_device_gfx_plane_info plane = {};
minsz = offsetofend(struct vfio_device_gfx_plane_info,
region_index);

827
samples/vfio-mdev/mtty.c
View file

@ -29,6 +29,8 @@
#include <linux/serial.h>
#include <uapi/linux/serial_reg.h>
#include <linux/eventfd.h>
#include <linux/anon_inodes.h>
/*
* #defines
*/
@ -124,10 +126,32 @@ struct serial_port {
u8 intr_trigger_level; /* interrupt trigger level */
};
struct mtty_data {
u64 magic;
#define MTTY_MAGIC 0x7e9d09898c3e2c4e /* Nothing clever, just random */
u32 major_ver;
#define MTTY_MAJOR_VER 1
u32 minor_ver;
#define MTTY_MINOR_VER 0
u32 nr_ports;
u32 flags;
struct serial_port ports[2];
};
struct mdev_state;
struct mtty_migration_file {
struct file *filp;
struct mutex lock;
struct mdev_state *mdev_state;
struct mtty_data data;
ssize_t filled_size;
u8 disabled:1;
};
/* 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;
@ -141,6 +165,13 @@ struct mdev_state {
struct mutex rxtx_lock;
struct vfio_device_info dev_info;
int nr_ports;
enum vfio_device_mig_state state;
struct mutex state_mutex;
struct mutex reset_mutex;
struct mtty_migration_file *saving_migf;
struct mtty_migration_file *resuming_migf;
u8 deferred_reset:1;
u8 intx_mask:1;
};
static struct mtty_type {
@ -166,10 +197,6 @@ static const struct file_operations vd_fops = {
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)
@ -186,6 +213,36 @@ static void dump_buffer(u8 *buf, uint32_t count)
#endif
}
static bool is_intx(struct mdev_state *mdev_state)
{
return mdev_state->irq_index == VFIO_PCI_INTX_IRQ_INDEX;
}
static bool is_msi(struct mdev_state *mdev_state)
{
return mdev_state->irq_index == VFIO_PCI_MSI_IRQ_INDEX;
}
static bool is_noirq(struct mdev_state *mdev_state)
{
return !is_intx(mdev_state) && !is_msi(mdev_state);
}
static void mtty_trigger_interrupt(struct mdev_state *mdev_state)
{
lockdep_assert_held(&mdev_state->ops_lock);
if (is_msi(mdev_state)) {
if (mdev_state->msi_evtfd)
eventfd_signal(mdev_state->msi_evtfd, 1);
} else if (is_intx(mdev_state)) {
if (mdev_state->intx_evtfd && !mdev_state->intx_mask) {
eventfd_signal(mdev_state->intx_evtfd, 1);
mdev_state->intx_mask = true;
}
}
}
static void mtty_create_config_space(struct mdev_state *mdev_state)
{
/* PCI dev ID */
@ -717,6 +774,543 @@ accessfailed:
return ret;
}
static size_t mtty_data_size(struct mdev_state *mdev_state)
{
return offsetof(struct mtty_data, ports) +
(mdev_state->nr_ports * sizeof(struct serial_port));
}
static void mtty_disable_file(struct mtty_migration_file *migf)
{
mutex_lock(&migf->lock);
migf->disabled = true;
migf->filled_size = 0;
migf->filp->f_pos = 0;
mutex_unlock(&migf->lock);
}
static void mtty_disable_files(struct mdev_state *mdev_state)
{
if (mdev_state->saving_migf) {
mtty_disable_file(mdev_state->saving_migf);
fput(mdev_state->saving_migf->filp);
mdev_state->saving_migf = NULL;
}
if (mdev_state->resuming_migf) {
mtty_disable_file(mdev_state->resuming_migf);
fput(mdev_state->resuming_migf->filp);
mdev_state->resuming_migf = NULL;
}
}
static void mtty_state_mutex_unlock(struct mdev_state *mdev_state)
{
again:
mutex_lock(&mdev_state->reset_mutex);
if (mdev_state->deferred_reset) {
mdev_state->deferred_reset = false;
mutex_unlock(&mdev_state->reset_mutex);
mdev_state->state = VFIO_DEVICE_STATE_RUNNING;
mtty_disable_files(mdev_state);
goto again;
}
mutex_unlock(&mdev_state->state_mutex);
mutex_unlock(&mdev_state->reset_mutex);
}
static int mtty_release_migf(struct inode *inode, struct file *filp)
{
struct mtty_migration_file *migf = filp->private_data;
mtty_disable_file(migf);
mutex_destroy(&migf->lock);
kfree(migf);
return 0;
}
static long mtty_precopy_ioctl(struct file *filp, unsigned int cmd,
unsigned long arg)
{
struct mtty_migration_file *migf = filp->private_data;
struct mdev_state *mdev_state = migf->mdev_state;
loff_t *pos = &filp->f_pos;
struct vfio_precopy_info info = {};
unsigned long minsz;
int ret;
if (cmd != VFIO_MIG_GET_PRECOPY_INFO)
return -ENOTTY;
minsz = offsetofend(struct vfio_precopy_info, dirty_bytes);
if (copy_from_user(&info, (void __user *)arg, minsz))
return -EFAULT;
if (info.argsz < minsz)
return -EINVAL;
mutex_lock(&mdev_state->state_mutex);
if (mdev_state->state != VFIO_DEVICE_STATE_PRE_COPY &&
mdev_state->state != VFIO_DEVICE_STATE_PRE_COPY_P2P) {
ret = -EINVAL;
goto unlock;
}
mutex_lock(&migf->lock);
if (migf->disabled) {
mutex_unlock(&migf->lock);
ret = -ENODEV;
goto unlock;
}
if (*pos > migf->filled_size) {
mutex_unlock(&migf->lock);
ret = -EINVAL;
goto unlock;
}
info.dirty_bytes = 0;
info.initial_bytes = migf->filled_size - *pos;
mutex_unlock(&migf->lock);
ret = copy_to_user((void __user *)arg, &info, minsz) ? -EFAULT : 0;
unlock:
mtty_state_mutex_unlock(mdev_state);
return ret;
}
static ssize_t mtty_save_read(struct file *filp, char __user *buf,
size_t len, loff_t *pos)
{
struct mtty_migration_file *migf = filp->private_data;
ssize_t ret = 0;
if (pos)
return -ESPIPE;
pos = &filp->f_pos;
mutex_lock(&migf->lock);
dev_dbg(migf->mdev_state->vdev.dev, "%s ask %zu\n", __func__, len);
if (migf->disabled) {
ret = -ENODEV;
goto out_unlock;
}
if (*pos > migf->filled_size) {
ret = -EINVAL;
goto out_unlock;
}
len = min_t(size_t, migf->filled_size - *pos, len);
if (len) {
if (copy_to_user(buf, (void *)&migf->data + *pos, len)) {
ret = -EFAULT;
goto out_unlock;
}
*pos += len;
ret = len;
}
out_unlock:
dev_dbg(migf->mdev_state->vdev.dev, "%s read %zu\n", __func__, ret);
mutex_unlock(&migf->lock);
return ret;
}
static const struct file_operations mtty_save_fops = {
.owner = THIS_MODULE,
.read = mtty_save_read,
.unlocked_ioctl = mtty_precopy_ioctl,
.compat_ioctl = compat_ptr_ioctl,
.release = mtty_release_migf,
.llseek = no_llseek,
};
static void mtty_save_state(struct mdev_state *mdev_state)
{
struct mtty_migration_file *migf = mdev_state->saving_migf;
int i;
mutex_lock(&migf->lock);
for (i = 0; i < mdev_state->nr_ports; i++) {
memcpy(&migf->data.ports[i],
&mdev_state->s[i], sizeof(struct serial_port));
migf->filled_size += sizeof(struct serial_port);
}
dev_dbg(mdev_state->vdev.dev,
"%s filled to %zu\n", __func__, migf->filled_size);
mutex_unlock(&migf->lock);
}
static int mtty_load_state(struct mdev_state *mdev_state)
{
struct mtty_migration_file *migf = mdev_state->resuming_migf;
int i;
mutex_lock(&migf->lock);
/* magic and version already tested by resume write fn */
if (migf->filled_size < mtty_data_size(mdev_state)) {
dev_dbg(mdev_state->vdev.dev, "%s expected %zu, got %zu\n",
__func__, mtty_data_size(mdev_state),
migf->filled_size);
mutex_unlock(&migf->lock);
return -EINVAL;
}
for (i = 0; i < mdev_state->nr_ports; i++)
memcpy(&mdev_state->s[i],
&migf->data.ports[i], sizeof(struct serial_port));
mutex_unlock(&migf->lock);
return 0;
}
static struct mtty_migration_file *
mtty_save_device_data(struct mdev_state *mdev_state,
enum vfio_device_mig_state state)
{
struct mtty_migration_file *migf = mdev_state->saving_migf;
struct mtty_migration_file *ret = NULL;
if (migf) {
if (state == VFIO_DEVICE_STATE_STOP_COPY)
goto fill_data;
return ret;
}
migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT);
if (!migf)
return ERR_PTR(-ENOMEM);
migf->filp = anon_inode_getfile("mtty_mig", &mtty_save_fops,
migf, O_RDONLY);
if (IS_ERR(migf->filp)) {
int rc = PTR_ERR(migf->filp);
kfree(migf);
return ERR_PTR(rc);
}
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
migf->mdev_state = mdev_state;
migf->data.magic = MTTY_MAGIC;
migf->data.major_ver = MTTY_MAJOR_VER;
migf->data.minor_ver = MTTY_MINOR_VER;
migf->data.nr_ports = mdev_state->nr_ports;
migf->filled_size = offsetof(struct mtty_data, ports);
dev_dbg(mdev_state->vdev.dev, "%s filled header to %zu\n",
__func__, migf->filled_size);
ret = mdev_state->saving_migf = migf;
fill_data:
if (state == VFIO_DEVICE_STATE_STOP_COPY)
mtty_save_state(mdev_state);
return ret;
}
static ssize_t mtty_resume_write(struct file *filp, const char __user *buf,
size_t len, loff_t *pos)
{
struct mtty_migration_file *migf = filp->private_data;
struct mdev_state *mdev_state = migf->mdev_state;
loff_t requested_length;
ssize_t ret = 0;
if (pos)
return -ESPIPE;
pos = &filp->f_pos;
if (*pos < 0 ||
check_add_overflow((loff_t)len, *pos, &requested_length))
return -EINVAL;
if (requested_length > mtty_data_size(mdev_state))
return -ENOMEM;
mutex_lock(&migf->lock);
if (migf->disabled) {
ret = -ENODEV;
goto out_unlock;
}
if (copy_from_user((void *)&migf->data + *pos, buf, len)) {
ret = -EFAULT;
goto out_unlock;
}
*pos += len;
ret = len;
dev_dbg(migf->mdev_state->vdev.dev, "%s received %zu, total %zu\n",
__func__, len, migf->filled_size + len);
if (migf->filled_size < offsetof(struct mtty_data, ports) &&
migf->filled_size + len >= offsetof(struct mtty_data, ports)) {
if (migf->data.magic != MTTY_MAGIC || migf->data.flags ||
migf->data.major_ver != MTTY_MAJOR_VER ||
migf->data.minor_ver != MTTY_MINOR_VER ||
migf->data.nr_ports != mdev_state->nr_ports) {
dev_dbg(migf->mdev_state->vdev.dev,
"%s failed validation\n", __func__);
ret = -EFAULT;
} else {
dev_dbg(migf->mdev_state->vdev.dev,
"%s header validated\n", __func__);
}
}
migf->filled_size += len;
out_unlock:
mutex_unlock(&migf->lock);
return ret;
}
static const struct file_operations mtty_resume_fops = {
.owner = THIS_MODULE,
.write = mtty_resume_write,
.release = mtty_release_migf,
.llseek = no_llseek,
};
static struct mtty_migration_file *
mtty_resume_device_data(struct mdev_state *mdev_state)
{
struct mtty_migration_file *migf;
int ret;
migf = kzalloc(sizeof(*migf), GFP_KERNEL_ACCOUNT);
if (!migf)
return ERR_PTR(-ENOMEM);
migf->filp = anon_inode_getfile("mtty_mig", &mtty_resume_fops,
migf, O_WRONLY);
if (IS_ERR(migf->filp)) {
ret = PTR_ERR(migf->filp);
kfree(migf);
return ERR_PTR(ret);
}
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
migf->mdev_state = mdev_state;
mdev_state->resuming_migf = migf;
return migf;
}
static struct file *mtty_step_state(struct mdev_state *mdev_state,
enum vfio_device_mig_state new)
{
enum vfio_device_mig_state cur = mdev_state->state;
dev_dbg(mdev_state->vdev.dev, "%s: %d -> %d\n", __func__, cur, new);
/*
* The following state transitions are no-op considering
* mtty does not do DMA nor require any explicit start/stop.
*
* RUNNING -> RUNNING_P2P
* RUNNING_P2P -> RUNNING
* RUNNING_P2P -> STOP
* PRE_COPY -> PRE_COPY_P2P
* PRE_COPY_P2P -> PRE_COPY
* STOP -> RUNNING_P2P
*/
if ((cur == VFIO_DEVICE_STATE_RUNNING &&
new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
(cur == VFIO_DEVICE_STATE_RUNNING_P2P &&
(new == VFIO_DEVICE_STATE_RUNNING ||
new == VFIO_DEVICE_STATE_STOP)) ||
(cur == VFIO_DEVICE_STATE_PRE_COPY &&
new == VFIO_DEVICE_STATE_PRE_COPY_P2P) ||
(cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
new == VFIO_DEVICE_STATE_PRE_COPY) ||
(cur == VFIO_DEVICE_STATE_STOP &&
new == VFIO_DEVICE_STATE_RUNNING_P2P))
return NULL;
/*
* The following state transitions simply close migration files,
* with the exception of RESUMING -> STOP, which needs to load
* the state first.
*
* RESUMING -> STOP
* PRE_COPY -> RUNNING
* PRE_COPY_P2P -> RUNNING_P2P
* STOP_COPY -> STOP
*/
if (cur == VFIO_DEVICE_STATE_RESUMING &&
new == VFIO_DEVICE_STATE_STOP) {
int ret;
ret = mtty_load_state(mdev_state);
if (ret)
return ERR_PTR(ret);
mtty_disable_files(mdev_state);
return NULL;
}
if ((cur == VFIO_DEVICE_STATE_PRE_COPY &&
new == VFIO_DEVICE_STATE_RUNNING) ||
(cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
(cur == VFIO_DEVICE_STATE_STOP_COPY &&
new == VFIO_DEVICE_STATE_STOP)) {
mtty_disable_files(mdev_state);
return NULL;
}
/*
* The following state transitions return migration files.
*
* RUNNING -> PRE_COPY
* RUNNING_P2P -> PRE_COPY_P2P
* STOP -> STOP_COPY
* STOP -> RESUMING
* PRE_COPY_P2P -> STOP_COPY
*/
if ((cur == VFIO_DEVICE_STATE_RUNNING &&
new == VFIO_DEVICE_STATE_PRE_COPY) ||
(cur == VFIO_DEVICE_STATE_RUNNING_P2P &&
new == VFIO_DEVICE_STATE_PRE_COPY_P2P) ||
(cur == VFIO_DEVICE_STATE_STOP &&
new == VFIO_DEVICE_STATE_STOP_COPY) ||
(cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
new == VFIO_DEVICE_STATE_STOP_COPY)) {
struct mtty_migration_file *migf;
migf = mtty_save_device_data(mdev_state, new);
if (IS_ERR(migf))
return ERR_CAST(migf);
if (migf) {
get_file(migf->filp);
return migf->filp;
}
return NULL;
}
if (cur == VFIO_DEVICE_STATE_STOP &&
new == VFIO_DEVICE_STATE_RESUMING) {
struct mtty_migration_file *migf;
migf = mtty_resume_device_data(mdev_state);
if (IS_ERR(migf))
return ERR_CAST(migf);
get_file(migf->filp);
return migf->filp;
}
/* vfio_mig_get_next_state() does not use arcs other than the above */
WARN_ON(true);
return ERR_PTR(-EINVAL);
}
static struct file *mtty_set_state(struct vfio_device *vdev,
enum vfio_device_mig_state new_state)
{
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
struct file *ret = NULL;
dev_dbg(vdev->dev, "%s -> %d\n", __func__, new_state);
mutex_lock(&mdev_state->state_mutex);
while (mdev_state->state != new_state) {
enum vfio_device_mig_state next_state;
int rc = vfio_mig_get_next_state(vdev, mdev_state->state,
new_state, &next_state);
if (rc) {
ret = ERR_PTR(rc);
break;
}
ret = mtty_step_state(mdev_state, next_state);
if (IS_ERR(ret))
break;
mdev_state->state = next_state;
if (WARN_ON(ret && new_state != next_state)) {
fput(ret);
ret = ERR_PTR(-EINVAL);
break;
}
}
mtty_state_mutex_unlock(mdev_state);
return ret;
}
static int mtty_get_state(struct vfio_device *vdev,
enum vfio_device_mig_state *current_state)
{
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
mutex_lock(&mdev_state->state_mutex);
*current_state = mdev_state->state;
mtty_state_mutex_unlock(mdev_state);
return 0;
}
static int mtty_get_data_size(struct vfio_device *vdev,
unsigned long *stop_copy_length)
{
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
*stop_copy_length = mtty_data_size(mdev_state);
return 0;
}
static const struct vfio_migration_ops mtty_migration_ops = {
.migration_set_state = mtty_set_state,
.migration_get_state = mtty_get_state,
.migration_get_data_size = mtty_get_data_size,
};
static int mtty_log_start(struct vfio_device *vdev,
struct rb_root_cached *ranges,
u32 nnodes, u64 *page_size)
{
return 0;
}
static int mtty_log_stop(struct vfio_device *vdev)
{
return 0;
}
static int mtty_log_read_and_clear(struct vfio_device *vdev,
unsigned long iova, unsigned long length,
struct iova_bitmap *dirty)
{
return 0;
}
static const struct vfio_log_ops mtty_log_ops = {
.log_start = mtty_log_start,
.log_stop = mtty_log_stop,
.log_read_and_clear = mtty_log_read_and_clear,
};
static int mtty_init_dev(struct vfio_device *vdev)
{
struct mdev_state *mdev_state =
@ -749,6 +1343,16 @@ static int mtty_init_dev(struct vfio_device *vdev)
mutex_init(&mdev_state->ops_lock);
mdev_state->mdev = mdev;
mtty_create_config_space(mdev_state);
mutex_init(&mdev_state->state_mutex);
mutex_init(&mdev_state->reset_mutex);
vdev->migration_flags = VFIO_MIGRATION_STOP_COPY |
VFIO_MIGRATION_P2P |
VFIO_MIGRATION_PRE_COPY;
vdev->mig_ops = &mtty_migration_ops;
vdev->log_ops = &mtty_log_ops;
mdev_state->state = VFIO_DEVICE_STATE_RUNNING;
return 0;
err_nr_ports:
@ -782,6 +1386,8 @@ static void mtty_release_dev(struct vfio_device *vdev)
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
mutex_destroy(&mdev_state->reset_mutex);
mutex_destroy(&mdev_state->state_mutex);
atomic_add(mdev_state->nr_ports, &mdev_avail_ports);
kfree(mdev_state->vconfig);
}
@ -798,6 +1404,15 @@ static int mtty_reset(struct mdev_state *mdev_state)
{
pr_info("%s: called\n", __func__);
mutex_lock(&mdev_state->reset_mutex);
mdev_state->deferred_reset = true;
if (!mutex_trylock(&mdev_state->state_mutex)) {
mutex_unlock(&mdev_state->reset_mutex);
return 0;
}
mutex_unlock(&mdev_state->reset_mutex);
mtty_state_mutex_unlock(mdev_state);
return 0;
}
@ -921,6 +1536,25 @@ write_err:
return -EFAULT;
}
static void mtty_disable_intx(struct mdev_state *mdev_state)
{
if (mdev_state->intx_evtfd) {
eventfd_ctx_put(mdev_state->intx_evtfd);
mdev_state->intx_evtfd = NULL;
mdev_state->intx_mask = false;
mdev_state->irq_index = -1;
}
}
static void mtty_disable_msi(struct mdev_state *mdev_state)
{
if (mdev_state->msi_evtfd) {
eventfd_ctx_put(mdev_state->msi_evtfd);
mdev_state->msi_evtfd = NULL;
mdev_state->irq_index = -1;
}
}
static int mtty_set_irqs(struct mdev_state *mdev_state, uint32_t flags,
unsigned int index, unsigned int start,
unsigned int count, void *data)
@ -932,59 +1566,113 @@ static int mtty_set_irqs(struct mdev_state *mdev_state, uint32_t flags,
case VFIO_PCI_INTX_IRQ_INDEX:
switch (flags & VFIO_IRQ_SET_ACTION_TYPE_MASK) {
case VFIO_IRQ_SET_ACTION_MASK:
if (!is_intx(mdev_state) || start != 0 || count != 1) {
ret = -EINVAL;
break;
}
if (flags & VFIO_IRQ_SET_DATA_NONE) {
mdev_state->intx_mask = true;
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t mask = *(uint8_t *)data;
if (mask)
mdev_state->intx_mask = true;
} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
ret = -ENOTTY; /* No support for mask fd */
}
break;
case VFIO_IRQ_SET_ACTION_UNMASK:
if (!is_intx(mdev_state) || start != 0 || count != 1) {
ret = -EINVAL;
break;
}
if (flags & VFIO_IRQ_SET_DATA_NONE) {
mdev_state->intx_mask = false;
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t mask = *(uint8_t *)data;
if (mask)
mdev_state->intx_mask = false;
} else if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
ret = -ENOTTY; /* No support for unmask fd */
}
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);
if (is_intx(mdev_state) && !count &&
(flags & VFIO_IRQ_SET_DATA_NONE)) {
mtty_disable_intx(mdev_state);
break;
}
if (!(is_intx(mdev_state) || is_noirq(mdev_state)) ||
start != 0 || count != 1) {
ret = -EINVAL;
break;
}
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int fd = *(int *)data;
struct eventfd_ctx *evt;
if (fd > 0) {
struct eventfd_ctx *evt;
mtty_disable_intx(mdev_state);
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;
if (fd < 0)
break;
evt = eventfd_ctx_fdget(fd);
if (IS_ERR(evt)) {
ret = PTR_ERR(evt);
break;
}
mdev_state->intx_evtfd = evt;
mdev_state->irq_index = index;
break;
}
if (!is_intx(mdev_state)) {
ret = -EINVAL;
break;
}
if (flags & VFIO_IRQ_SET_DATA_NONE) {
mtty_trigger_interrupt(mdev_state);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t trigger = *(uint8_t *)data;
if (trigger)
mtty_trigger_interrupt(mdev_state);
}
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:
ret = -ENOTTY;
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;
if (is_msi(mdev_state) && !count &&
(flags & VFIO_IRQ_SET_DATA_NONE)) {
mtty_disable_msi(mdev_state);
break;
}
if (!(is_msi(mdev_state) || is_noirq(mdev_state)) ||
start != 0 || count != 1) {
ret = -EINVAL;
break;
}
if (flags & VFIO_IRQ_SET_DATA_EVENTFD) {
int fd = *(int *)data;
struct eventfd_ctx *evt;
if (fd <= 0)
break;
mtty_disable_msi(mdev_state);
if (mdev_state->msi_evtfd)
if (fd < 0)
break;
evt = eventfd_ctx_fdget(fd);
@ -993,20 +1681,37 @@ static int mtty_set_irqs(struct mdev_state *mdev_state, uint32_t flags,
break;
}
mdev_state->msi_evtfd = evt;
mdev_state->irq_fd = fd;
mdev_state->irq_index = index;
break;
}
if (!is_msi(mdev_state)) {
ret = -EINVAL;
break;
}
if (flags & VFIO_IRQ_SET_DATA_NONE) {
mtty_trigger_interrupt(mdev_state);
} else if (flags & VFIO_IRQ_SET_DATA_BOOL) {
uint8_t trigger = *(uint8_t *)data;
if (trigger)
mtty_trigger_interrupt(mdev_state);
}
break;
}
break;
}
break;
case VFIO_PCI_MSIX_IRQ_INDEX:
pr_info("%s: MSIX_IRQ\n", __func__);
dev_dbg(mdev_state->vdev.dev, "%s: MSIX_IRQ\n", __func__);
ret = -ENOTTY;
break;
case VFIO_PCI_ERR_IRQ_INDEX:
pr_info("%s: ERR_IRQ\n", __func__);
dev_dbg(mdev_state->vdev.dev, "%s: ERR_IRQ\n", __func__);
ret = -ENOTTY;
break;
case VFIO_PCI_REQ_IRQ_INDEX:
pr_info("%s: REQ_IRQ\n", __func__);
dev_dbg(mdev_state->vdev.dev, "%s: REQ_IRQ\n", __func__);
ret = -ENOTTY;
break;
}
@ -1014,33 +1719,6 @@ static int mtty_set_irqs(struct mdev_state *mdev_state, uint32_t flags,
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)
@ -1084,22 +1762,16 @@ static int mtty_get_region_info(struct mdev_state *mdev_state,
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:
if (irq_info->index != VFIO_PCI_INTX_IRQ_INDEX &&
irq_info->index != VFIO_PCI_MSI_IRQ_INDEX)
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);
irq_info->flags |= VFIO_IRQ_INFO_MASKABLE |
VFIO_IRQ_INFO_AUTOMASKED;
else
irq_info->flags |= VFIO_IRQ_INFO_NORESIZE;
@ -1262,6 +1934,16 @@ static unsigned int mtty_get_available(struct mdev_type *mtype)
return atomic_read(&mdev_avail_ports) / type->nr_ports;
}
static void mtty_close(struct vfio_device *vdev)
{
struct mdev_state *mdev_state =
container_of(vdev, struct mdev_state, vdev);
mtty_disable_files(mdev_state);
mtty_disable_intx(mdev_state);
mtty_disable_msi(mdev_state);
}
static const struct vfio_device_ops mtty_dev_ops = {
.name = "vfio-mtty",
.init = mtty_init_dev,
@ -1273,6 +1955,7 @@ static const struct vfio_device_ops mtty_dev_ops = {
.unbind_iommufd = vfio_iommufd_emulated_unbind,
.attach_ioas = vfio_iommufd_emulated_attach_ioas,
.detach_ioas = vfio_iommufd_emulated_detach_ioas,
.close_device = mtty_close,
};
static struct mdev_driver mtty_driver = {