[PATCH v5 6/7] vfio/nvgrace-gpu: Inform devmem unmapped after reset

ankita@nvidia.com posted 7 patches 1 week ago
There is a newer version of this series
[PATCH v5 6/7] vfio/nvgrace-gpu: Inform devmem unmapped after reset
Posted by ankita@nvidia.com 1 week ago
From: Ankit Agrawal <ankita@nvidia.com>

Introduce a new flag reset_done to notify that the GPU has just
been reset and the mapping to the GPU memory is zapped.

Implement the reset_done handler to set this new variable. It
will be used later in the patches to wait for the GPU memory
to be ready before doing any mapping or access.

Suggested-by: Alex Williamson <alex@shazbot.org>
Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
---
 drivers/vfio/pci/nvgrace-gpu/main.c | 21 ++++++++++++++++++++-
 1 file changed, 20 insertions(+), 1 deletion(-)

diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index 3e45b8bd1a89..bef9f25bf8f3 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -58,6 +58,8 @@ struct nvgrace_gpu_pci_core_device {
 	/* Lock to control device memory kernel mapping */
 	struct mutex remap_lock;
 	bool has_mig_hw_bug;
+	/* GPU has just been reset */
+	bool reset_done;
 };
 
 static void nvgrace_gpu_init_fake_bar_emu_regs(struct vfio_device *core_vdev)
@@ -1048,12 +1050,29 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, nvgrace_gpu_vfio_pci_table);
 
+static void nvgrace_gpu_vfio_pci_reset_done(struct pci_dev *pdev)
+{
+	struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev);
+	struct nvgrace_gpu_pci_core_device *nvdev =
+		container_of(core_device, struct nvgrace_gpu_pci_core_device,
+			     core_device);
+
+	lockdep_assert_held_write(&core_device->memory_lock);
+
+	nvdev->reset_done = true;
+}
+
+static const struct pci_error_handlers nvgrace_gpu_vfio_pci_err_handlers = {
+	.reset_done = nvgrace_gpu_vfio_pci_reset_done,
+	.error_detected = vfio_pci_core_aer_err_detected,
+};
+
 static struct pci_driver nvgrace_gpu_vfio_pci_driver = {
 	.name = KBUILD_MODNAME,
 	.id_table = nvgrace_gpu_vfio_pci_table,
 	.probe = nvgrace_gpu_probe,
 	.remove = nvgrace_gpu_remove,
-	.err_handler = &vfio_pci_core_err_handlers,
+	.err_handler = &nvgrace_gpu_vfio_pci_err_handlers,
 	.driver_managed_dma = true,
 };
 
-- 
2.34.1
Re: [PATCH v5 6/7] vfio/nvgrace-gpu: Inform devmem unmapped after reset
Posted by Jason Gunthorpe 1 week ago
On Mon, Nov 24, 2025 at 11:59:25AM +0000, ankita@nvidia.com wrote:
> @@ -1048,12 +1050,29 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = {
>  
>  MODULE_DEVICE_TABLE(pci, nvgrace_gpu_vfio_pci_table);
>  
> +static void nvgrace_gpu_vfio_pci_reset_done(struct pci_dev *pdev)
> +{
> +	struct vfio_pci_core_device *core_device = dev_get_drvdata(&pdev->dev);
> +	struct nvgrace_gpu_pci_core_device *nvdev =
> +		container_of(core_device, struct nvgrace_gpu_pci_core_device,
> +			     core_device);
> +
> +	lockdep_assert_held_write(&core_device->memory_lock);
> +
> +	nvdev->reset_done = true;
> +}

Seems surprising/wrong at least needs a comment. What on earth is
ensuring that lockdep within a PCI callback??

>  static struct pci_driver nvgrace_gpu_vfio_pci_driver = {
>  	.name = KBUILD_MODNAME,
>  	.id_table = nvgrace_gpu_vfio_pci_table,
>  	.probe = nvgrace_gpu_probe,
>  	.remove = nvgrace_gpu_remove,
> -	.err_handler = &vfio_pci_core_err_handlers,
> +	.err_handler = &nvgrace_gpu_vfio_pci_err_handlers,

Jason