vfio/mlx5: Consider temporary end of stream as part of PRE_COPY

During PRE_COPY the migration data FD may have a temporary "end of
stream" that is reached when the initial_bytes were read and no other
dirty data exists yet.

For instance, this may indicate that the device is idle and not
currently dirtying any internal state. When read() is done on this
temporary end of stream the kernel driver should return ENOMSG from
read(). Userspace can wait for more data or consider moving to
STOP_COPY.

To not block the user upon read() and let it get ENOMSG we add a new
state named MLX5_MIGF_STATE_PRE_COPY on the migration file.

In addition, we add the MLX5_MIGF_STATE_SAVE_LAST state to block the
read() once we call the last SAVE upon moving to STOP_COPY.

Any further error will be marked with MLX5_MIGF_STATE_ERROR and the user
won't be blocked.

Reviewed-by: Jason Gunthorpe <jgg@nvidia.com>
Signed-off-by: Yishai Hadas <yishaih@nvidia.com>
Link: https://lore.kernel.org/r/20221206083438.37807-12-yishaih@nvidia.com
Signed-off-by: Alex Williamson <alex.williamson@redhat.com>

diff --git a/drivers/vfio/pci/mlx5/cmd.c b/drivers/vfio/pci/mlx5/cmd.c
index 12e74ec..f6293da 100644 (file)
--- a/drivers/vfio/pci/mlx5/cmd.c
+++ b/drivers/vfio/pci/mlx5/cmd.c
@@ -501,8 +501,8 @@ static void mlx5vf_save_callback(int status, struct mlx5_async_work *context)
                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);
-               if (async_data->last_chunk)
-                       migf->state = MLX5_MIGF_STATE_COMPLETE;
+               migf->state = async_data->last_chunk ?
+                       MLX5_MIGF_STATE_COMPLETE : MLX5_MIGF_STATE_PRE_COPY;
                wake_up_interruptible(&migf->poll_wait);
        }
 
@@ -561,6 +561,9 @@ int mlx5vf_cmd_save_vhca_state(struct mlx5vf_pci_core_device *mvdev,
                }
        }
 
+       if (async_data->last_chunk)
+               migf->state = MLX5_MIGF_STATE_SAVE_LAST;
+
        async_data->header_buf = header_buf;
        get_file(migf->filp);
        err = mlx5_cmd_exec_cb(&migf->async_ctx, in, sizeof(in),

diff --git a/drivers/vfio/pci/mlx5/cmd.h b/drivers/vfio/pci/mlx5/cmd.h
index 3e36ccc..d048f23 100644 (file)
--- a/drivers/vfio/pci/mlx5/cmd.h
+++ b/drivers/vfio/pci/mlx5/cmd.h
@@ -17,6 +17,8 @@
 
 enum mlx5_vf_migf_state {
        MLX5_MIGF_STATE_ERROR = 1,
+       MLX5_MIGF_STATE_PRE_COPY,
+       MLX5_MIGF_STATE_SAVE_LAST,
        MLX5_MIGF_STATE_COMPLETE,
 };
 

diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index 2c8ac76..44b1543 100644 (file)
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -219,6 +219,7 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
                if (wait_event_interruptible(migf->poll_wait,
                                !list_empty(&migf->buf_list) ||
                                migf->state == MLX5_MIGF_STATE_ERROR ||
+                               migf->state == MLX5_MIGF_STATE_PRE_COPY ||
                                migf->state == MLX5_MIGF_STATE_COMPLETE))
                        return -ERESTARTSYS;
        }
@@ -236,6 +237,12 @@ static ssize_t mlx5vf_save_read(struct file *filp, char __user *buf, size_t len,
                                                         &end_of_data);
                if (first_loop_call) {
                        first_loop_call = false;
+                       /* Temporary end of file as part of PRE_COPY */
+                       if (end_of_data && migf->state == MLX5_MIGF_STATE_PRE_COPY) {
+                               done = -ENOMSG;
+                               goto out_unlock;
+                       }
+
                        if (end_of_data && migf->state != MLX5_MIGF_STATE_COMPLETE) {
                                if (filp->f_flags & O_NONBLOCK) {
                                        done = -EAGAIN;