vfio/nvgrace-gpu: Inform devmem unmapped after reset

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.

Cc: Jason Gunthorpe <jgg@ziepe.ca>
Reviewed-by: Shameer Kolothum <skolothumtho@nvidia.com>
Suggested-by: Alex Williamson <alex@shazbot.org>
Signed-off-by: Ankit Agrawal <ankita@nvidia.com>
Link: https://lore.kernel.org/r/20251127170632.3477-6-ankita@nvidia.com
Signed-off-by: Alex Williamson <alex@shazbot.org>

1 files changed, 25 insertions, 1 deletions

diff --git a/drivers/vfio/pci/nvgrace-gpu/main.c b/drivers/vfio/pci/nvgrace-gpu/main.c
index 5f122929dd44..df360e12b299 100644
--- a/drivers/vfio/pci/nvgrace-gpu/main.c
+++ b/drivers/vfio/pci/nvgrace-gpu/main.c
@@ -59,6 +59,8 @@ 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)
@@ -1067,12 +1069,34 @@ static const struct pci_device_id nvgrace_gpu_vfio_pci_table[] = {
 
 MODULE_DEVICE_TABLE(pci, nvgrace_gpu_vfio_pci_table);
 
+/*
+ * The GPU reset is required to be serialized against the *first* mapping
+ * faults and read/writes accesses to prevent potential RAS events logging.
+ *
+ * First fault or access after a reset needs to poll device readiness,
+ * flag that a reset has occurred.
+ */
+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);
+
+	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,
 };