Re: [PATCH RFC v2 10/15] vfio/nvgrace-egm: Clear Memory before handing out to VM

[Alex Williamson]

On Mon, 23 Feb 2026 15:55:09 +0000
<ankita@xxxxxxxxxx> wrote:

> From: Ankit Agrawal <ankita@xxxxxxxxxx>
> 
> The EGM region is invisible to the host Linux kernel and it does not
> manage the region. The EGM module manages the EGM memory and thus is
> responsible to clear out the region before handing out to the VM.
> 
> Clear EGM region on EGM chardev open. To avoid CPU lockup logs,
> zap the region in 1G chunks.
> 
> Suggested-by: Vikram Sethi <vsethi@xxxxxxxxxx>
> Signed-off-by: Ankit Agrawal <ankita@xxxxxxxxxx>
> ---
>  drivers/vfio/pci/nvgrace-gpu/egm.c | 43 ++++++++++++++++++++++++++++++
>  1 file changed, 43 insertions(+)
> 
> diff --git a/drivers/vfio/pci/nvgrace-gpu/egm.c b/drivers/vfio/pci/nvgrace-gpu/egm.c
> index 5786ebe374a5..de7771a4145d 100644
> --- a/drivers/vfio/pci/nvgrace-gpu/egm.c
> +++ b/drivers/vfio/pci/nvgrace-gpu/egm.c
> @@ -15,6 +15,7 @@ static DEFINE_XARRAY(egm_chardevs);
>  struct chardev {
>  	struct device device;
>  	struct cdev cdev;
> +	atomic_t open_count;
>  };
>  
>  static struct nvgrace_egm_dev *
> @@ -30,6 +31,42 @@ static int nvgrace_egm_open(struct inode *inode, struct file *file)
>  {
>  	struct chardev *egm_chardev =
>  		container_of(inode->i_cdev, struct chardev, cdev);
> +	struct nvgrace_egm_dev *egm_dev =
> +		egm_chardev_to_nvgrace_egm_dev(egm_chardev);
> +	void *memaddr;
> +
> +	if (atomic_cmpxchg(&egm_chardev->open_count, 0, 1) != 0)
> +		return -EBUSY;
> +
> +	/*
> +	 * nvgrace-egm module is responsible to manage the EGM memory as
> +	 * the host kernel has no knowledge of it. Clear the region before
> +	 * handing over to userspace.
> +	 */
> +	memaddr = memremap(egm_dev->egmphys, egm_dev->egmlength, MEMREMAP_WB);
> +	if (!memaddr) {
> +		atomic_dec(&egm_chardev->open_count);
> +		return -ENOMEM;
> +	}
> +
> +	/*
> +	 * Clear in chunks of 1G to avoid CPU lockup logs.
> +	 */
> +	{
> +		size_t remaining = egm_dev->egmlength;
> +		u8 *chunk_addr = (u8 *)memaddr;
> +		size_t chunk_size;

Declare at the start of the function and remove this scope hack.

> +
> +		while (remaining > 0) {
> +			chunk_size = min(remaining, SZ_1G);

min_t(size_t,,);

> +			memset(chunk_addr, 0, chunk_size);
> +			cond_resched();
> +			chunk_addr += chunk_size;
> +			remaining -= chunk_size;
> +		}
> +	}

Aren't we going to want to do this asynchronously or run multiple
threads to avoid stalling VM launch? 

> +
> +	memunmap(memaddr);
>  
>  	file->private_data = egm_chardev;
>  
> @@ -38,8 +75,13 @@ static int nvgrace_egm_open(struct inode *inode, struct file *file)
>  
>  static int nvgrace_egm_release(struct inode *inode, struct file *file)
>  {
> +	struct chardev *egm_chardev =
> +		container_of(inode->i_cdev, struct chardev, cdev);
> +
>  	file->private_data = NULL;
>  
> +	atomic_dec(&egm_chardev->open_count);
> +
>  	return 0;
>  }
>  
> @@ -108,6 +150,7 @@ setup_egm_chardev(struct nvgrace_egm_dev *egm_dev)
>  	egm_chardev->device.parent = &egm_dev->aux_dev.dev;
>  	cdev_init(&egm_chardev->cdev, &file_ops);
>  	egm_chardev->cdev.owner = THIS_MODULE;
> +	atomic_set(&egm_chardev->open_count, 0);

Already zero from kzalloc.  Thanks,

Alex

>  
>  	ret = dev_set_name(&egm_chardev->device, "egm%lld", egm_dev->egmpxm);
>  	if (ret)