linux-kernel - Re: [PATCH v6 4/6] vfio/nvgrace-gpu: split the code to wait for GPU ready

lists.openwall.net		lists / announce owl-users owl-dev john-users john-dev passwdqc-users yescrypt popa3d-users / oss-security kernel-hardening musl sabotage tlsify passwords / crypt-dev xvendor / Bugtraq Full-Disclosure linux-kernel linux-netdev linux-ext4 linux-hardening linux-cve-announce PHC
Open Source and information security mailing list archives

Hash Suite: Windows password security audit tool. GUI, reports in PDF.

[<prev] [next>] [<thread-prev] [thread-next>] [day] [month] [year] [list]

Message-ID: <20251125223001.7d05d834.zhiw@nvidia.com>
Date: Tue, 25 Nov 2025 22:30:01 +0200
From: Zhi Wang <zhiw@...dia.com>
To: <ankita@...dia.com>
CC: <jgg@...pe.ca>, <yishaih@...dia.com>, <skolothumtho@...dia.com>,
	<kevin.tian@...el.com>, <alex@...zbot.org>, <aniketa@...dia.com>,
	<vsethi@...dia.com>, <mochs@...dia.com>, <Yunxiang.Li@....com>,
	<yi.l.liu@...el.com>, <zhangdongdong@...incomputing.com>,
	<avihaih@...dia.com>, <bhelgaas@...gle.com>, <peterx@...hat.com>,
	<pstanner@...hat.com>, <apopple@...dia.com>, <kvm@...r.kernel.org>,
	<linux-kernel@...r.kernel.org>, <cjia@...dia.com>, <kwankhede@...dia.com>,
	<targupta@...dia.com>, <danw@...dia.com>, <dnigam@...dia.com>,
	<kjaju@...dia.com>
Subject: Re: [PATCH v6 4/6] vfio/nvgrace-gpu: split the code to wait for GPU
 ready

On Tue, 25 Nov 2025 17:30:11 +0000
<ankita@...dia.com> wrote:

Looking good to me.

Reviewed-by: Zhi Wang <zhiw@...dia.com>

> From: Ankit Agrawal <ankita@...dia.com>
> 
> Split the function that check for the GPU device being ready on
> the probe.
> 
> Move the code to wait for the GPU to be ready through BAR0 register
> reads to a separate function. This would help reuse the code.
> 
> Reviewed-by: Shameer Kolothum <skolothumtho@...dia.com>
> Signed-off-by: Ankit Agrawal <ankita@...dia.com>
> ---
>  drivers/vfio/pci/nvgrace-gpu/main.c | 29
> +++++++++++++++++------------ 1 file changed, 17 insertions(+), 12
> deletions(-)
> 
> diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c
> b/drivers/vfio/pci/nvgrace-gpu/main.c index
> 8a982310b188..2b736cb82f38 100644 ---
> a/drivers/vfio/pci/nvgrace-gpu/main.c +++
> b/drivers/vfio/pci/nvgrace-gpu/main.c @@ -130,6 +130,20 @@ static
> void nvgrace_gpu_close_device(struct vfio_device *core_vdev)
> vfio_pci_core_close_device(core_vdev); }
>  
> +static int nvgrace_gpu_wait_device_ready(void __iomem *io)
> +{
> +	unsigned long timeout = jiffies +
> msecs_to_jiffies(POLL_TIMEOUT_MS); +
> +	do {
> +		if ((ioread32(io + C2C_LINK_BAR0_OFFSET) ==
> STATUS_READY) &&
> +		    (ioread32(io + HBM_TRAINING_BAR0_OFFSET) ==
> STATUS_READY))
> +			return 0;
> +		msleep(POLL_QUANTUM_MS);
> +	} while (!time_after(jiffies, timeout));
> +
> +	return -ETIME;
> +}
> +
>  static unsigned long addr_to_pgoff(struct vm_area_struct *vma,
>  				   unsigned long addr)
>  {
> @@ -933,9 +947,8 @@ static bool nvgrace_gpu_has_mig_hw_bug(struct
> pci_dev *pdev)
>   * Ensure that the BAR0 region is enabled before accessing the
>   * registers.
>   */
> -static int nvgrace_gpu_wait_device_ready(struct pci_dev *pdev)
> +static int nvgrace_gpu_probe_check_device_ready(struct pci_dev *pdev)
>  {
> -	unsigned long timeout = jiffies +
> msecs_to_jiffies(POLL_TIMEOUT_MS); void __iomem *io;
>  	int ret = -ETIME;
>  
> @@ -953,16 +966,8 @@ static int nvgrace_gpu_wait_device_ready(struct
> pci_dev *pdev) goto iomap_exit;
>  	}
>  
> -	do {
> -		if ((ioread32(io + C2C_LINK_BAR0_OFFSET) ==
> STATUS_READY) &&
> -		    (ioread32(io + HBM_TRAINING_BAR0_OFFSET) ==
> STATUS_READY)) {
> -			ret = 0;
> -			goto reg_check_exit;
> -		}
> -		msleep(POLL_QUANTUM_MS);
> -	} while (!time_after(jiffies, timeout));
> +	ret = nvgrace_gpu_wait_device_ready(io);
>  
> -reg_check_exit:
>  	pci_iounmap(pdev, io);
>  iomap_exit:
>  	pci_release_selected_regions(pdev, 1 << 0);
> @@ -979,7 +984,7 @@ static int nvgrace_gpu_probe(struct pci_dev *pdev,
>  	u64 memphys, memlength;
>  	int ret;
>  
> -	ret = nvgrace_gpu_wait_device_ready(pdev);
> +	ret = nvgrace_gpu_probe_check_device_ready(pdev);
>  	if (ret)
>  		return ret;
>