mirror of
https://git.kernel.org/pub/scm/linux/kernel/git/torvalds/linux.git
synced 2025-12-27 12:21:22 -05:00
0810d5ad88
Using the DRM GPU scheduler infrastructure, with a scheduler for each core. Userspace can decide for a series of tasks to be executed sequentially in the same core, so SRAM locality can be taken advantage of. The job submission code was initially based on Panfrost. v2: - Remove hardcoded number of cores - Misc. style fixes (Jeffrey Hugo) - Repack IOCTL struct (Jeffrey Hugo) v3: - Adapt to a split of the register block in the DT bindings (Nicolas Frattaroli) - Make use of GPL-2.0-only for the copyright notice (Jeff Hugo) - Use drm_* logging functions (Thomas Zimmermann) - Rename reg i/o macros (Thomas Zimmermann) - Add padding to ioctls and check for zero (Jeff Hugo) - Improve error handling (Nicolas Frattaroli) v6: - Use mutexes guard (Markus Elfring) - Use u64_to_user_ptr (Jeff Hugo) - Drop rocket_fence (Rob Herring) v7: - Assign its own IOMMU domain to each client, for isolation (Daniel Stone and Robin Murphy) v8: - Use reset lines to reset the cores (Robin Murphy) - Use the macros to compute the values for the bitfields (Robin Murphy) - More descriptive name for the IRQ (Robin Murphy) - Simplify job interrupt handing (Robin Murphy) - Correctly acquire a reference to the IOMMU (Robin Murphy) - Specify the size of the embedded structs in the IOCTLs for future extensibility (Rob Herring) - Expose only 32 bits for the address of the regcmd BO (Robin Murphy) Tested-by: Heiko Stuebner <heiko@sntech.de> Reviewed-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com> Signed-off-by: Tomeu Vizoso <tomeu@tomeuvizoso.net> Signed-off-by: Jeff Hugo <jeff.hugo@oss.qualcomm.com> Link: https://lore.kernel.org/r/20250721-6-10-rocket-v9-4-77ebd484941e@tomeuvizoso.net
61 lines
1.4 KiB
C
61 lines
1.4 KiB
C
// SPDX-License-Identifier: GPL-2.0-only
|
|
/* Copyright 2024-2025 Tomeu Vizoso <tomeu@tomeuvizoso.net> */
|
|
|
|
#include <drm/drm_drv.h>
|
|
#include <linux/array_size.h>
|
|
#include <linux/clk.h>
|
|
#include <linux/dma-mapping.h>
|
|
#include <linux/platform_device.h>
|
|
#include <linux/of.h>
|
|
|
|
#include "rocket_device.h"
|
|
|
|
struct rocket_device *rocket_device_init(struct platform_device *pdev,
|
|
const struct drm_driver *rocket_drm_driver)
|
|
{
|
|
struct device *dev = &pdev->dev;
|
|
struct device_node *core_node;
|
|
struct rocket_device *rdev;
|
|
struct drm_device *ddev;
|
|
unsigned int num_cores = 0;
|
|
int err;
|
|
|
|
rdev = devm_drm_dev_alloc(dev, rocket_drm_driver, struct rocket_device, ddev);
|
|
if (IS_ERR(rdev))
|
|
return rdev;
|
|
|
|
ddev = &rdev->ddev;
|
|
dev_set_drvdata(dev, rdev);
|
|
|
|
for_each_compatible_node(core_node, NULL, "rockchip,rk3588-rknn-core")
|
|
if (of_device_is_available(core_node))
|
|
num_cores++;
|
|
|
|
rdev->cores = devm_kcalloc(dev, num_cores, sizeof(*rdev->cores), GFP_KERNEL);
|
|
if (!rdev->cores)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
dma_set_max_seg_size(dev, UINT_MAX);
|
|
|
|
err = dma_set_mask_and_coherent(dev, DMA_BIT_MASK(40));
|
|
if (err)
|
|
return ERR_PTR(err);
|
|
|
|
err = devm_mutex_init(dev, &rdev->sched_lock);
|
|
if (err)
|
|
return ERR_PTR(-ENOMEM);
|
|
|
|
err = drm_dev_register(ddev, 0);
|
|
if (err)
|
|
return ERR_PTR(err);
|
|
|
|
return rdev;
|
|
}
|
|
|
|
void rocket_device_fini(struct rocket_device *rdev)
|
|
{
|
|
WARN_ON(rdev->num_cores > 0);
|
|
|
|
drm_dev_unregister(&rdev->ddev);
|
|
}
|