@@ -14,18 +14,36 @@ _mlx5vf_free_page_tracker_resources(struct mlx5vf_pci_core_device *mvdev);
int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod)
{
+ struct mlx5_vf_migration_file *migf = mvdev->saving_migf;
u32 out[MLX5_ST_SZ_DW(suspend_vhca_out)] = {};
u32 in[MLX5_ST_SZ_DW(suspend_vhca_in)] = {};
+ int err;
lockdep_assert_held(&mvdev->state_mutex);
if (mvdev->mdev_detach)
return -ENOTCONN;
+ /*
+ * In case PRE_COPY is used, saving_migf is exposed while the device is
+ * running. Make sure to run only once there is no active save command.
+ * Running both in parallel, might end-up with a failure in the save
+ * command once it will try to turn on 'tracking' on a suspended device.
+ */
+ if (migf) {
+ err = wait_for_completion_interruptible(&migf->save_comp);
+ if (err)
+ return err;
+ }
+
MLX5_SET(suspend_vhca_in, in, opcode, MLX5_CMD_OP_SUSPEND_VHCA);
MLX5_SET(suspend_vhca_in, in, vhca_id, mvdev->vhca_id);
MLX5_SET(suspend_vhca_in, in, op_mod, op_mod);
- return mlx5_cmd_exec_inout(mvdev->mdev, suspend_vhca, in, out);
+ err = mlx5_cmd_exec_inout(mvdev->mdev, suspend_vhca, in, out);
+ if (migf)
+ complete(&migf->save_comp);
+
+ return err;
}
int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod)
@@ -45,7 +63,7 @@ int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod)
}
int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
- size_t *state_size)
+ size_t *state_size, u8 query_flags)
{
u32 out[MLX5_ST_SZ_DW(query_vhca_migration_state_out)] = {};
u32 in[MLX5_ST_SZ_DW(query_vhca_migration_state_in)] = {};
@@ -59,6 +77,8 @@ int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
MLX5_CMD_OP_QUERY_VHCA_MIGRATION_STATE);
MLX5_SET(query_vhca_migration_state_in, in, vhca_id, mvdev->vhca_id);
MLX5_SET(query_vhca_migration_state_in, in, op_mod, 0);
+ MLX5_SET(query_vhca_migration_state_in, in, incremental,
+ query_flags & MLX5VF_QUERY_INC);
ret = mlx5_cmd_exec_inout(mvdev->mdev, query_vhca_migration_state, in,
out);
@@ -342,6 +362,56 @@ mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
return ERR_PTR(ret);
}
+void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf)
+{
+ spin_lock_irq(&buf->migf->list_lock);
+ list_add_tail(&buf->buf_elm, &buf->migf->avail_list);
+ spin_unlock_irq(&buf->migf->list_lock);
+}
+
+struct mlx5_vhca_data_buffer *
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
+ size_t length, enum dma_data_direction dma_dir)
+{
+ struct mlx5_vhca_data_buffer *buf, *temp_buf;
+ struct list_head free_list;
+
+ lockdep_assert_held(&migf->mvdev->state_mutex);
+ if (migf->mvdev->mdev_detach)
+ return ERR_PTR(-ENOTCONN);
+
+ INIT_LIST_HEAD(&free_list);
+
+ spin_lock_irq(&migf->list_lock);
+ list_for_each_entry_safe(buf, temp_buf, &migf->avail_list, buf_elm) {
+ if (buf->dma_dir == dma_dir) {
+ list_del_init(&buf->buf_elm);
+ if (buf->allocated_length >= length) {
+ spin_unlock_irq(&migf->list_lock);
+ goto found;
+ }
+ /*
+ * Prevent holding redundant buffers. Put in a free
+ * list and call at the end not under the spin lock
+ * (&migf->list_lock) to mlx5vf_free_data_buffer which
+ * might sleep.
+ */
+ list_add(&buf->buf_elm, &free_list);
+ }
+ }
+ spin_unlock_irq(&migf->list_lock);
+ buf = mlx5vf_alloc_data_buffer(migf, length, dma_dir);
+
+found:
+ while ((temp_buf = list_first_entry_or_null(&free_list,
+ struct mlx5_vhca_data_buffer, buf_elm))) {
+ list_del(&temp_buf->buf_elm);
+ mlx5vf_free_data_buffer(temp_buf);
+ }
+
+ return buf;
+}
+
void mlx5vf_mig_file_cleanup_cb(struct work_struct *_work)
{
struct mlx5vf_async_data *async_data = container_of(_work,
@@ -351,7 +421,7 @@ void mlx5vf_mig_file_cleanup_cb(struct work_struct *_work)
mutex_lock(&migf->lock);
if (async_data->status) {
- migf->buf = async_data->buf;
+ mlx5vf_put_data_buffer(async_data->buf);
migf->state = MLX5_MIGF_STATE_ERROR;
wake_up_interruptible(&migf->poll_wait);
}
@@ -369,15 +439,19 @@ static void mlx5vf_save_callback(int status, struct mlx5_async_work *context)
struct mlx5_vf_migration_file, async_data);
if (!status) {
+ size_t image_size;
unsigned long flags;
- async_data->buf->length =
- MLX5_GET(save_vhca_state_out, async_data->out,
- actual_image_size);
+ image_size = MLX5_GET(save_vhca_state_out, async_data->out,
+ actual_image_size);
+ async_data->buf->length = image_size;
+ async_data->buf->start_pos = migf->max_pos;
+ migf->max_pos += async_data->buf->length;
spin_lock_irqsave(&migf->list_lock, flags);
list_add_tail(&async_data->buf->buf_elm, &migf->buf_list);
spin_unlock_irqrestore(&migf->list_lock, flags);
- migf->state = MLX5_MIGF_STATE_COMPLETE;
+ if (async_data->last_chunk)
+ migf->state = MLX5_MIGF_STATE_COMPLETE;
wake_up_interruptible(&migf->poll_wait);
}
@@ -391,7 +465,8 @@ static void mlx5vf_save_callback(int status, struct mlx5_async_work *context)
int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
struct mlx5_vf_migration_file *migf,
- struct mlx5_vhca_data_buffer *buf)
+ struct mlx5_vhca_data_buffer *buf, bool inc,
+ bool track)
{
u32 out_size = MLX5_ST_SZ_BYTES(save_vhca_state_out);
u32 in[MLX5_ST_SZ_DW(save_vhca_state_in)] = {};
@@ -412,9 +487,12 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
MLX5_SET(save_vhca_state_in, in, vhca_id, mvdev->vhca_id);
MLX5_SET(save_vhca_state_in, in, mkey, buf->mkey);
MLX5_SET(save_vhca_state_in, in, size, buf->allocated_length);
+ MLX5_SET(save_vhca_state_in, in, incremental, inc);
+ MLX5_SET(save_vhca_state_in, in, set_track, track);
async_data = &migf->async_data;
async_data->buf = buf;
+ async_data->last_chunk = !track;
async_data->out = kvzalloc(out_size, GFP_KERNEL);
if (!async_data->out) {
err = -ENOMEM;
@@ -497,6 +575,8 @@ void mlx5fv_cmd_clean_migf_resources(struct mlx5_vf_migration_file *migf)
migf->buf = NULL;
}
+ list_splice(&migf->avail_list, &migf->buf_list);
+
while ((entry = list_first_entry_or_null(&migf->buf_list,
struct mlx5_vhca_data_buffer, buf_elm))) {
list_del(&entry->buf_elm);
@@ -38,6 +38,7 @@ struct mlx5vf_async_data {
struct work_struct work;
struct mlx5_vhca_data_buffer *buf;
int status;
+ u8 last_chunk:1;
void *out;
};
@@ -47,9 +48,11 @@ struct mlx5_vf_migration_file {
enum mlx5_vf_migf_state state;
u32 pdn;
+ loff_t max_pos;
struct mlx5_vhca_data_buffer *buf;
spinlock_t list_lock;
struct list_head buf_list;
+ struct list_head avail_list;
struct mlx5vf_pci_core_device *mvdev;
wait_queue_head_t poll_wait;
struct completion save_comp;
@@ -129,10 +132,14 @@ struct mlx5vf_pci_core_device {
struct mlx5_core_dev *mdev;
};
+enum {
+ MLX5VF_QUERY_INC = (1UL << 0),
+};
+
int mlx5vf_cmd_suspend_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
int mlx5vf_cmd_resume_vhca(struct mlx5vf_pci_core_device *mvdev, u16 op_mod);
int mlx5vf_cmd_query_vhca_migration_state(struct mlx5vf_pci_core_device *mvdev,
- size_t *state_size);
+ size_t *state_size, u8 query_flags);
void mlx5vf_cmd_set_migratable(struct mlx5vf_pci_core_device *mvdev,
const struct vfio_migration_ops *mig_ops,
const struct vfio_log_ops *log_ops);
@@ -140,7 +147,8 @@ void mlx5vf_cmd_remove_migratable(struct mlx5vf_pci_core_device *mvdev);
void mlx5vf_cmd_close_migratable(struct mlx5vf_pci_core_device *mvdev);
int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
struct mlx5_vf_migration_file *migf,
- struct mlx5_vhca_data_buffer *buf);
+ struct mlx5_vhca_data_buffer *buf, bool inc,
+ bool track);
int mlx5vf_cmd_load_vhca_state(struct mlx5vf_pci_core_device *mvdev,
struct mlx5_vf_migration_file *migf,
struct mlx5_vhca_data_buffer *buf);
@@ -151,6 +159,10 @@ struct mlx5_vhca_data_buffer *
mlx5vf_alloc_data_buffer(struct mlx5_vf_migration_file *migf,
size_t length, enum dma_data_direction dma_dir);
void mlx5vf_free_data_buffer(struct mlx5_vhca_data_buffer *buf);
+struct mlx5_vhca_data_buffer *
+mlx5vf_get_data_buffer(struct mlx5_vf_migration_file *migf,
+ size_t length, enum dma_data_direction dma_dir);
+void mlx5vf_put_data_buffer(struct mlx5_vhca_data_buffer *buf);
int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
unsigned int npages);
void mlx5vf_state_mutex_unlock(struct mlx5vf_pci_core_device *mvdev);
@@ -195,6 +195,7 @@ static ssize_t mlx5vf_buf_read(struct mlx5_vhca_data_buffer *vhca_buf,
if (*pos >= vhca_buf->start_pos + vhca_buf->length) {
spin_lock_irq(&vhca_buf->migf->list_lock);
list_del_init(&vhca_buf->buf_elm);
+ list_add_tail(&vhca_buf->buf_elm, &vhca_buf->migf->avail_list);
spin_unlock_irq(&vhca_buf->migf->list_lock);
}
@@ -283,6 +284,16 @@ static __poll_t mlx5vf_save_poll(struct file *filp,
return pollflags;
}
+/*
+ * FD is exposed and user can use it after receiving an error.
+ * Mark migf in error, and wake the user.
+ */
+static void mlx5vf_mark_err(struct mlx5_vf_migration_file *migf)
+{
+ migf->state = MLX5_MIGF_STATE_ERROR;
+ wake_up_interruptible(&migf->poll_wait);
+}
+
static const struct file_operations mlx5vf_save_fops = {
.owner = THIS_MODULE,
.read = mlx5vf_save_read,
@@ -291,8 +302,42 @@ static const struct file_operations mlx5vf_save_fops = {
.llseek = no_llseek,
};
+static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev)
+{
+ struct mlx5_vf_migration_file *migf = mvdev->saving_migf;
+ struct mlx5_vhca_data_buffer *buf;
+ size_t length;
+ int ret;
+
+ if (migf->state == MLX5_MIGF_STATE_ERROR)
+ return -ENODEV;
+
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length,
+ MLX5VF_QUERY_INC);
+ if (ret)
+ goto err;
+
+ buf = mlx5vf_get_data_buffer(migf, length, DMA_FROM_DEVICE);
+ if (IS_ERR(buf)) {
+ ret = PTR_ERR(buf);
+ goto err;
+ }
+
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, true, false);
+ if (ret)
+ goto err_save;
+
+ return 0;
+
+err_save:
+ mlx5vf_put_data_buffer(buf);
+err:
+ mlx5vf_mark_err(migf);
+ return ret;
+}
+
static struct mlx5_vf_migration_file *
-mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
+mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
{
struct mlx5_vf_migration_file *migf;
struct mlx5_vhca_data_buffer *buf;
@@ -323,8 +368,9 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
mlx5_cmd_init_async_ctx(mvdev->mdev, &migf->async_ctx);
INIT_WORK(&migf->async_data.work, mlx5vf_mig_file_cleanup_cb);
INIT_LIST_HEAD(&migf->buf_list);
+ INIT_LIST_HEAD(&migf->avail_list);
spin_lock_init(&migf->list_lock);
- ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length);
+ ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, 0);
if (ret)
goto out_pd;
@@ -334,7 +380,7 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev)
goto out_pd;
}
- ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf);
+ ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, false, track);
if (ret)
goto out_save;
return migf;
@@ -457,6 +503,7 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
stream_open(migf->filp->f_inode, migf->filp);
mutex_init(&migf->lock);
INIT_LIST_HEAD(&migf->buf_list);
+ INIT_LIST_HEAD(&migf->avail_list);
spin_lock_init(&migf->list_lock);
return migf;
out_pd:
@@ -509,7 +556,8 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return NULL;
}
- if (cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) {
+ if ((cur == VFIO_DEVICE_STATE_RUNNING && new == VFIO_DEVICE_STATE_RUNNING_P2P) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_PRE_COPY_P2P)) {
ret = mlx5vf_cmd_suspend_vhca(mvdev,
MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_INITIATOR);
if (ret)
@@ -517,7 +565,8 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return NULL;
}
- if (cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) {
+ if ((cur == VFIO_DEVICE_STATE_RUNNING_P2P && new == VFIO_DEVICE_STATE_RUNNING) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_PRE_COPY)) {
ret = mlx5vf_cmd_resume_vhca(mvdev,
MLX5_RESUME_VHCA_IN_OP_MOD_RESUME_INITIATOR);
if (ret)
@@ -528,7 +577,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_STOP_COPY) {
struct mlx5_vf_migration_file *migf;
- migf = mlx5vf_pci_save_device_data(mvdev);
+ migf = mlx5vf_pci_save_device_data(mvdev, false);
if (IS_ERR(migf))
return ERR_CAST(migf);
get_file(migf->filp);
@@ -536,7 +585,10 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return migf->filp;
}
- if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP)) {
+ if ((cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) ||
+ (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P &&
+ new == VFIO_DEVICE_STATE_RUNNING_P2P)) {
mlx5vf_disable_fds(mvdev);
return NULL;
}
@@ -562,6 +614,28 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
return NULL;
}
+ 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)) {
+ struct mlx5_vf_migration_file *migf;
+
+ migf = mlx5vf_pci_save_device_data(mvdev, true);
+ if (IS_ERR(migf))
+ return ERR_CAST(migf);
+ get_file(migf->filp);
+ mvdev->saving_migf = migf;
+ return migf->filp;
+ }
+
+ if (cur == VFIO_DEVICE_STATE_PRE_COPY_P2P && new == VFIO_DEVICE_STATE_STOP_COPY) {
+ ret = mlx5vf_cmd_suspend_vhca(mvdev,
+ MLX5_SUSPEND_VHCA_IN_OP_MOD_SUSPEND_RESPONDER);
+ if (ret)
+ return ERR_PTR(ret);
+ ret = mlx5vf_pci_save_device_inc_data(mvdev);
+ return ret ? ERR_PTR(ret) : NULL;
+ }
+
/*
* vfio_mig_get_next_state() does not use arcs other than the above
*/
@@ -630,7 +704,7 @@ static int mlx5vf_pci_get_data_size(struct vfio_device *vdev,
mutex_lock(&mvdev->state_mutex);
ret = mlx5vf_cmd_query_vhca_migration_state(mvdev,
- &state_size);
+ &state_size, 0);
if (!ret)
*stop_copy_length = state_size;
mlx5vf_state_mutex_unlock(mvdev);