vfio: selftests: Add memcpy chunking to vfio_pci_driver_memcpy()

Add a chunking loop to vfio_pci_driver_memcpy() so that it breaks up
large memcpy requests into max_memcpy_size-sized chunks. This allows
callers to request any size without worrying about per-driver limits.
The memcpy_start()/memcpy_wait() semantics are unchanged.

Update the test to use 4x max_memcpy_size so it exercises the new
chunking path (4 iterations) while keeping execution fast for drivers
with small DMA transfer sizes.

Reviewed-by: David Matlack <dmatlack@google.com>
Signed-off-by: Alex Williamson <alex.williamson@nvidia.com>
Signed-off-by: Rubin Du <rubind@nvidia.com>
Link: https://lore.kernel.org/r/20260609232855.3808971-2-rubind@nvidia.com
Signed-off-by: Alex Williamson <alex@shazbot.org>

1 files changed, 16 insertions, 2 deletions

diff --git a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c
index 6827f4a6febe..e6c5b9c703f4 100644
--- a/tools/testing/selftests/vfio/lib/vfio_pci_driver.c
+++ b/tools/testing/selftests/vfio/lib/vfio_pci_driver.c
@@ -106,7 +106,21 @@ int vfio_pci_driver_memcpy_wait(struct vfio_pci_device *device)
 int vfio_pci_driver_memcpy(struct vfio_pci_device *device,
 			   iova_t src, iova_t dst, u64 size)
 {
-	vfio_pci_driver_memcpy_start(device, src, dst, size, 1);
+	struct vfio_pci_driver *driver = &device->driver;
+	u64 offset = 0;
+
+	while (offset < size) {
+		u64 chunk = min(size - offset, driver->max_memcpy_size);
+		int ret;
+
+		vfio_pci_driver_memcpy_start(device, src + offset,
+					     dst + offset, chunk, 1);
+		ret = vfio_pci_driver_memcpy_wait(device);
+		if (ret)
+			return ret;
+
+		offset += chunk;
+	}
 
-	return vfio_pci_driver_memcpy_wait(device);
+	return 0;
 }