1 files changed, 91 insertions, 177 deletions

diff --git a/drivers/vfio/pci/mlx5/main.c b/drivers/vfio/pci/mlx5/main.c
index fe09a8c8af95..93f894fe60d2 100644
--- a/drivers/vfio/pci/mlx5/main.c
+++ b/drivers/vfio/pci/mlx5/main.c
@@ -34,81 +34,6 @@ static struct mlx5vf_pci_core_device *mlx5vf_drvdata(struct pci_dev *pdev)
 			    core_device);
 }
 
-struct page *
-mlx5vf_get_migration_page(struct mlx5_vhca_data_buffer *buf,
-			  unsigned long offset)
-{
-	unsigned long cur_offset = 0;
-	struct scatterlist *sg;
-	unsigned int i;
-
-	/* All accesses are sequential */
-	if (offset < buf->last_offset || !buf->last_offset_sg) {
-		buf->last_offset = 0;
-		buf->last_offset_sg = buf->table.sgt.sgl;
-		buf->sg_last_entry = 0;
-	}
-
-	cur_offset = buf->last_offset;
-
-	for_each_sg(buf->last_offset_sg, sg,
-			buf->table.sgt.orig_nents - buf->sg_last_entry, i) {
-		if (offset < sg->length + cur_offset) {
-			buf->last_offset_sg = sg;
-			buf->sg_last_entry += i;
-			buf->last_offset = cur_offset;
-			return nth_page(sg_page(sg),
-					(offset - cur_offset) / PAGE_SIZE);
-		}
-		cur_offset += sg->length;
-	}
-	return NULL;
-}
-
-int mlx5vf_add_migration_pages(struct mlx5_vhca_data_buffer *buf,
-			       unsigned int npages)
-{
-	unsigned int to_alloc = npages;
-	struct page **page_list;
-	unsigned long filled;
-	unsigned int to_fill;
-	int ret;
-
-	to_fill = min_t(unsigned int, npages, PAGE_SIZE / sizeof(*page_list));
-	page_list = kvzalloc(to_fill * sizeof(*page_list), GFP_KERNEL_ACCOUNT);
-	if (!page_list)
-		return -ENOMEM;
-
-	do {
-		filled = alloc_pages_bulk_array(GFP_KERNEL_ACCOUNT, to_fill,
-						page_list);
-		if (!filled) {
-			ret = -ENOMEM;
-			goto err;
-		}
-		to_alloc -= filled;
-		ret = sg_alloc_append_table_from_pages(
-			&buf->table, page_list, filled, 0,
-			filled << PAGE_SHIFT, UINT_MAX, SG_MAX_SINGLE_ALLOC,
-			GFP_KERNEL_ACCOUNT);
-
-		if (ret)
-			goto err;
-		buf->allocated_length += filled * PAGE_SIZE;
-		/* clean input for another bulk allocation */
-		memset(page_list, 0, filled * sizeof(*page_list));
-		to_fill = min_t(unsigned int, to_alloc,
-				PAGE_SIZE / sizeof(*page_list));
-	} while (to_alloc > 0);
-
-	kvfree(page_list);
-	return 0;
-
-err:
-	kvfree(page_list);
-	return ret;
-}
-
 static void mlx5vf_disable_fd(struct mlx5_vf_migration_file *migf)
 {
 	mutex_lock(&migf->lock);
@@ -352,6 +277,7 @@ static struct mlx5_vhca_data_buffer *
 mlx5vf_mig_file_get_stop_copy_buf(struct mlx5_vf_migration_file *migf,
 				  u8 index, size_t required_length)
 {
+	u32 npages = DIV_ROUND_UP(required_length, PAGE_SIZE);
 	struct mlx5_vhca_data_buffer *buf = migf->buf[index];
 	u8 chunk_num;
 
@@ -359,12 +285,11 @@ mlx5vf_mig_file_get_stop_copy_buf(struct mlx5_vf_migration_file *migf,
 	chunk_num = buf->stop_copy_chunk_num;
 	buf->migf->buf[index] = NULL;
 	/* Checking whether the pre-allocated buffer can fit */
-	if (buf->allocated_length >= required_length)
+	if (buf->npages >= npages)
 		return buf;
 
 	mlx5vf_put_data_buffer(buf);
-	buf = mlx5vf_get_data_buffer(buf->migf, required_length,
-				     DMA_FROM_DEVICE);
+	buf = mlx5vf_get_data_buffer(buf->migf, npages, DMA_FROM_DEVICE);
 	if (IS_ERR(buf))
 		return buf;
 
@@ -417,7 +342,8 @@ static int mlx5vf_add_stop_copy_header(struct mlx5_vf_migration_file *migf,
 	u8 *to_buff;
 	int ret;
 
-	header_buf = mlx5vf_get_data_buffer(migf, size, DMA_NONE);
+	header_buf = mlx5vf_get_data_buffer(migf, DIV_ROUND_UP(size, PAGE_SIZE),
+					    DMA_NONE);
 	if (IS_ERR(header_buf))
 		return PTR_ERR(header_buf);
 
@@ -432,7 +358,7 @@ static int mlx5vf_add_stop_copy_header(struct mlx5_vf_migration_file *migf,
 	to_buff = kmap_local_page(page);
 	memcpy(to_buff, &header, sizeof(header));
 	header_buf->length = sizeof(header);
-	data.stop_copy_size = cpu_to_le64(migf->buf[0]->allocated_length);
+	data.stop_copy_size = cpu_to_le64(migf->buf[0]->npages * PAGE_SIZE);
 	memcpy(to_buff + sizeof(header), &data, sizeof(data));
 	header_buf->length += sizeof(data);
 	kunmap_local(to_buff);
@@ -481,15 +407,20 @@ static int mlx5vf_prep_stop_copy(struct mlx5vf_pci_core_device *mvdev,
 
 	num_chunks = mvdev->chunk_mode ? MAX_NUM_CHUNKS : 1;
 	for (i = 0; i < num_chunks; i++) {
-		buf = mlx5vf_get_data_buffer(migf, inc_state_size, DMA_FROM_DEVICE);
+		buf = mlx5vf_get_data_buffer(
+			migf, DIV_ROUND_UP(inc_state_size, PAGE_SIZE),
+			DMA_FROM_DEVICE);
 		if (IS_ERR(buf)) {
 			ret = PTR_ERR(buf);
 			goto err;
 		}
 
 		migf->buf[i] = buf;
-		buf = mlx5vf_get_data_buffer(migf,
-				sizeof(struct mlx5_vf_migration_header), DMA_NONE);
+		buf = mlx5vf_get_data_buffer(
+			migf,
+			DIV_ROUND_UP(sizeof(struct mlx5_vf_migration_header),
+				     PAGE_SIZE),
+			DMA_NONE);
 		if (IS_ERR(buf)) {
 			ret = PTR_ERR(buf);
 			goto err;
@@ -597,7 +528,8 @@ static long mlx5vf_precopy_ioctl(struct file *filp, unsigned int cmd,
 	 * We finished transferring the current state and the device has a
 	 * dirty state, save a new state to be ready for.
 	 */
-	buf = mlx5vf_get_data_buffer(migf, inc_length, DMA_FROM_DEVICE);
+	buf = mlx5vf_get_data_buffer(migf, DIV_ROUND_UP(inc_length, PAGE_SIZE),
+				     DMA_FROM_DEVICE);
 	if (IS_ERR(buf)) {
 		ret = PTR_ERR(buf);
 		mlx5vf_mark_err(migf);
@@ -631,7 +563,6 @@ static const struct file_operations mlx5vf_save_fops = {
 	.unlocked_ioctl = mlx5vf_precopy_ioctl,
 	.compat_ioctl = compat_ptr_ioctl,
 	.release = mlx5vf_release_file,
-	.llseek = no_llseek,
 };
 
 static int mlx5vf_pci_save_device_inc_data(struct mlx5vf_pci_core_device *mvdev)
@@ -685,14 +616,11 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
 					O_RDONLY);
 	if (IS_ERR(migf->filp)) {
 		ret = PTR_ERR(migf->filp);
-		goto end;
+		kfree(migf);
+		return ERR_PTR(ret);
 	}
 
 	migf->mvdev = mvdev;
-	ret = mlx5vf_cmd_alloc_pd(migf);
-	if (ret)
-		goto out_free;
-
 	stream_open(migf->filp->f_inode, migf->filp);
 	mutex_init(&migf->lock);
 	init_waitqueue_head(&migf->poll_wait);
@@ -708,6 +636,11 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
 	INIT_LIST_HEAD(&migf->buf_list);
 	INIT_LIST_HEAD(&migf->avail_list);
 	spin_lock_init(&migf->list_lock);
+
+	ret = mlx5vf_cmd_alloc_pd(migf);
+	if (ret)
+		goto out;
+
 	ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &length, &full_size, 0);
 	if (ret)
 		goto out_pd;
@@ -718,8 +651,8 @@ mlx5vf_pci_save_device_data(struct mlx5vf_pci_core_device *mvdev, bool track)
 
 	if (track) {
 		/* leave the allocated buffer ready for the stop-copy phase */
-		buf = mlx5vf_alloc_data_buffer(migf,
-			migf->buf[0]->allocated_length, DMA_FROM_DEVICE);
+		buf = mlx5vf_alloc_data_buffer(migf, migf->buf[0]->npages,
+					       DMA_FROM_DEVICE);
 		if (IS_ERR(buf)) {
 			ret = PTR_ERR(buf);
 			goto out_pd;
@@ -737,10 +670,8 @@ out_save:
 	mlx5vf_free_data_buffer(buf);
 out_pd:
 	mlx5fv_cmd_clean_migf_resources(migf);
-out_free:
+out:
 	fput(migf->filp);
-end:
-	kfree(migf);
 	return ERR_PTR(ret);
 }
 
@@ -777,36 +708,6 @@ mlx5vf_append_page_to_mig_buf(struct mlx5_vhca_data_buffer *vhca_buf,
 	return 0;
 }
 
-static int
-mlx5vf_resume_read_image_no_header(struct mlx5_vhca_data_buffer *vhca_buf,
-				   loff_t requested_length,
-				   const char __user **buf, size_t *len,
-				   loff_t *pos, ssize_t *done)
-{
-	int ret;
-
-	if (requested_length > MAX_LOAD_SIZE)
-		return -ENOMEM;
-
-	if (vhca_buf->allocated_length < requested_length) {
-		ret = mlx5vf_add_migration_pages(
-			vhca_buf,
-			DIV_ROUND_UP(requested_length - vhca_buf->allocated_length,
-				     PAGE_SIZE));
-		if (ret)
-			return ret;
-	}
-
-	while (*len) {
-		ret = mlx5vf_append_page_to_mig_buf(vhca_buf, buf, len, pos,
-						    done);
-		if (ret)
-			return ret;
-	}
-
-	return 0;
-}
-
 static ssize_t
 mlx5vf_resume_read_image(struct mlx5_vf_migration_file *migf,
 			 struct mlx5_vhca_data_buffer *vhca_buf,
@@ -992,11 +893,14 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
 				goto out_unlock;
 			break;
 		case MLX5_VF_LOAD_STATE_PREP_HEADER_DATA:
-			if (vhca_buf_header->allocated_length < migf->record_size) {
+		{
+			u32 npages = DIV_ROUND_UP(migf->record_size, PAGE_SIZE);
+
+			if (vhca_buf_header->npages < npages) {
 				mlx5vf_free_data_buffer(vhca_buf_header);
 
-				migf->buf_header[0] = mlx5vf_alloc_data_buffer(migf,
-						migf->record_size, DMA_NONE);
+				migf->buf_header[0] = mlx5vf_alloc_data_buffer(
+					migf, npages, DMA_NONE);
 				if (IS_ERR(migf->buf_header[0])) {
 					ret = PTR_ERR(migf->buf_header[0]);
 					migf->buf_header[0] = NULL;
@@ -1009,6 +913,7 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
 			vhca_buf_header->start_pos = migf->max_pos;
 			migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER_DATA;
 			break;
+		}
 		case MLX5_VF_LOAD_STATE_READ_HEADER_DATA:
 			ret = mlx5vf_resume_read_header_data(migf, vhca_buf_header,
 							&buf, &len, pos, &done);
@@ -1019,12 +924,13 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
 		{
 			u64 size = max(migf->record_size,
 				       migf->stop_copy_prep_size);
+			u32 npages = DIV_ROUND_UP(size, PAGE_SIZE);
 
-			if (vhca_buf->allocated_length < size) {
+			if (vhca_buf->npages < npages) {
 				mlx5vf_free_data_buffer(vhca_buf);
 
-				migf->buf[0] = mlx5vf_alloc_data_buffer(migf,
-							size, DMA_TO_DEVICE);
+				migf->buf[0] = mlx5vf_alloc_data_buffer(
+					migf, npages, DMA_TO_DEVICE);
 				if (IS_ERR(migf->buf[0])) {
 					ret = PTR_ERR(migf->buf[0]);
 					migf->buf[0] = NULL;
@@ -1038,13 +944,6 @@ static ssize_t mlx5vf_resume_write(struct file *filp, const char __user *buf,
 			migf->load_state = MLX5_VF_LOAD_STATE_READ_IMAGE;
 			break;
 		}
-		case MLX5_VF_LOAD_STATE_READ_IMAGE_NO_HEADER:
-			ret = mlx5vf_resume_read_image_no_header(vhca_buf,
-						requested_length,
-						&buf, &len, pos, &done);
-			if (ret)
-				goto out_unlock;
-			break;
 		case MLX5_VF_LOAD_STATE_READ_IMAGE:
 			ret = mlx5vf_resume_read_image(migf, vhca_buf,
 						migf->record_size,
@@ -1081,7 +980,6 @@ static const struct file_operations mlx5vf_resume_fops = {
 	.owner = THIS_MODULE,
 	.write = mlx5vf_resume_write,
 	.release = mlx5vf_release_file,
-	.llseek = no_llseek,
 };
 
 static struct mlx5_vf_migration_file *
@@ -1099,13 +997,19 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
 					O_WRONLY);
 	if (IS_ERR(migf->filp)) {
 		ret = PTR_ERR(migf->filp);
-		goto end;
+		kfree(migf);
+		return ERR_PTR(ret);
 	}
 
+	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);
 	migf->mvdev = mvdev;
 	ret = mlx5vf_cmd_alloc_pd(migf);
 	if (ret)
-		goto out_free;
+		goto out;
 
 	buf = mlx5vf_alloc_data_buffer(migf, 0, DMA_TO_DEVICE);
 	if (IS_ERR(buf)) {
@@ -1114,39 +1018,31 @@ mlx5vf_pci_resume_device_data(struct mlx5vf_pci_core_device *mvdev)
 	}
 
 	migf->buf[0] = buf;
-	if (MLX5VF_PRE_COPY_SUPP(mvdev)) {
-		buf = mlx5vf_alloc_data_buffer(migf,
-			sizeof(struct mlx5_vf_migration_header), DMA_NONE);
-		if (IS_ERR(buf)) {
-			ret = PTR_ERR(buf);
-			goto out_buf;
-		}
-
-		migf->buf_header[0] = buf;
-		migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER;
-	} else {
-		/* Initial state will be to read the image */
-		migf->load_state = MLX5_VF_LOAD_STATE_READ_IMAGE_NO_HEADER;
+	buf = mlx5vf_alloc_data_buffer(
+		migf,
+		DIV_ROUND_UP(sizeof(struct mlx5_vf_migration_header),
+			     PAGE_SIZE),
+		DMA_NONE);
+	if (IS_ERR(buf)) {
+		ret = PTR_ERR(buf);
+		goto out_buf;
 	}
 
-	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);
+	migf->buf_header[0] = buf;
+	migf->load_state = MLX5_VF_LOAD_STATE_READ_HEADER;
+
 	return migf;
 out_buf:
 	mlx5vf_free_data_buffer(migf->buf[0]);
 out_pd:
 	mlx5vf_cmd_dealloc_pd(migf);
-out_free:
+out:
 	fput(migf->filp);
-end:
-	kfree(migf);
 	return ERR_PTR(ret);
 }
 
-void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
+void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev,
+			enum mlx5_vf_migf_state *last_save_state)
 {
 	if (mvdev->resuming_migf) {
 		mlx5vf_disable_fd(mvdev->resuming_migf);
@@ -1157,6 +1053,8 @@ void mlx5vf_disable_fds(struct mlx5vf_pci_core_device *mvdev)
 	if (mvdev->saving_migf) {
 		mlx5_cmd_cleanup_async_ctx(&mvdev->saving_migf->async_ctx);
 		cancel_work_sync(&mvdev->saving_migf->async_data.work);
+		if (last_save_state)
+			*last_save_state = mvdev->saving_migf->state;
 		mlx5vf_disable_fd(mvdev->saving_migf);
 		wake_up_interruptible(&mvdev->saving_migf->poll_wait);
 		mlx5fv_cmd_clean_migf_resources(mvdev->saving_migf);
@@ -1217,12 +1115,35 @@ 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) ||
-	    (cur == VFIO_DEVICE_STATE_PRE_COPY && new == VFIO_DEVICE_STATE_RUNNING) ||
+	if (cur == VFIO_DEVICE_STATE_STOP_COPY && new == VFIO_DEVICE_STATE_STOP) {
+		mlx5vf_disable_fds(mvdev, NULL);
+		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)) {
-		mlx5vf_disable_fds(mvdev);
-		return NULL;
+		struct mlx5_vf_migration_file *migf = mvdev->saving_migf;
+		struct mlx5_vhca_data_buffer *buf;
+		enum mlx5_vf_migf_state state;
+		size_t size;
+
+		ret = mlx5vf_cmd_query_vhca_migration_state(mvdev, &size, NULL,
+					MLX5VF_QUERY_INC | MLX5VF_QUERY_CLEANUP);
+		if (ret)
+			return ERR_PTR(ret);
+		buf = mlx5vf_get_data_buffer(migf,
+				DIV_ROUND_UP(size, PAGE_SIZE), DMA_FROM_DEVICE);
+		if (IS_ERR(buf))
+			return ERR_CAST(buf);
+		/* pre_copy cleanup */
+		ret = mlx5vf_cmd_save_vhca_state(mvdev, migf, buf, false, false);
+		if (ret) {
+			mlx5vf_put_data_buffer(buf);
+			return ERR_PTR(ret);
+		}
+		mlx5vf_disable_fds(mvdev, &state);
+		return (state != MLX5_MIGF_STATE_ERROR) ? NULL : ERR_PTR(-EIO);
 	}
 
 	if (cur == VFIO_DEVICE_STATE_STOP && new == VFIO_DEVICE_STATE_RESUMING) {
@@ -1237,14 +1158,7 @@ mlx5vf_pci_step_device_state_locked(struct mlx5vf_pci_core_device *mvdev,
 	}
 
 	if (cur == VFIO_DEVICE_STATE_RESUMING && new == VFIO_DEVICE_STATE_STOP) {
-		if (!MLX5VF_PRE_COPY_SUPP(mvdev)) {
-			ret = mlx5vf_cmd_load_vhca_state(mvdev,
-							 mvdev->resuming_migf,
-							 mvdev->resuming_migf->buf[0]);
-			if (ret)
-				return ERR_PTR(ret);
-		}
-		mlx5vf_disable_fds(mvdev);
+		mlx5vf_disable_fds(mvdev, NULL);
 		return NULL;
 	}
 
@@ -1289,7 +1203,7 @@ again:
 		mvdev->deferred_reset = false;
 		spin_unlock(&mvdev->reset_lock);
 		mvdev->mig_state = VFIO_DEVICE_STATE_RUNNING;
-		mlx5vf_disable_fds(mvdev);
+		mlx5vf_disable_fds(mvdev, NULL);
 		goto again;
 	}
 	mutex_unlock(&mvdev->state_mutex);
@@ -1517,7 +1431,7 @@ static struct pci_driver mlx5vf_pci_driver = {
 
 module_pci_driver(mlx5vf_pci_driver);
 
-MODULE_IMPORT_NS(IOMMUFD);
+MODULE_IMPORT_NS("IOMMUFD");
 MODULE_LICENSE("GPL");
 MODULE_AUTHOR("Max Gurtovoy <mgurtovoy@nvidia.com>");
 MODULE_AUTHOR("Yishai Hadas <yishaih@nvidia.com>");