mirror of
git://nv-tegra.nvidia.com/linux-nvgpu.git
synced 2025-12-23 09:57:08 +03:00
733fb79b39
Add support for pre-allocation of job tracking resources w/ new (extended) ioctl. Goal is to avoid dynamic memory allocation in the submit path. This patch does the following: 1) Intoduces a new ioctl, NVGPU_IOCTL_CHANNEL_ALLOC_GPFIFO_EX, which enables pre-allocation of tracking resources per job: a) 2x priv_cmd_entry b) 2x gk20a_fence 2) Implements circular ring buffer for job tracking to avoid lock contention between producer (submitter) and consumer (clean-up) Bug 1795076 Change-Id: I6b52e5c575871107ff380f9a5790f440a6969347 Signed-off-by: Sachit Kadle <skadle@nvidia.com> Reviewed-on: http://git-master/r/1203300 (cherry picked from commit 9fd270c22b860935dffe244753dabd87454bef39) Reviewed-on: http://git-master/r/1223934 Reviewed-by: mobile promotions <svcmobile_promotions@nvidia.com> Tested-by: mobile promotions <svcmobile_promotions@nvidia.com>
90 lines
2.4 KiB
C
90 lines
2.4 KiB
C
/*
|
|
* drivers/video/tegra/host/gk20a/fence_gk20a.h
|
|
*
|
|
* GK20A Fences
|
|
*
|
|
* Copyright (c) 2014-2016, NVIDIA CORPORATION. All rights reserved.
|
|
*
|
|
* This program is free software; you can redistribute it and/or modify it
|
|
* under the terms and conditions of the GNU General Public License,
|
|
* version 2, as published by the Free Software Foundation.
|
|
*
|
|
* This program is distributed in the hope it will be useful, but WITHOUT
|
|
* ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
|
|
* FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for
|
|
* more details.
|
|
*/
|
|
#ifndef _GK20A_FENCE_H_
|
|
#define _GK20A_FENCE_H_
|
|
|
|
#include <linux/types.h>
|
|
#include <linux/kref.h>
|
|
#include <linux/wait.h>
|
|
|
|
struct platform_device;
|
|
struct sync_timeline;
|
|
struct sync_fence;
|
|
struct gk20a_semaphore;
|
|
struct channel_gk20a;
|
|
|
|
struct gk20a_fence_ops;
|
|
|
|
struct gk20a_fence {
|
|
/* Valid for all fence types: */
|
|
bool valid;
|
|
struct kref ref;
|
|
bool wfi;
|
|
struct sync_fence *sync_fence;
|
|
const struct gk20a_fence_ops *ops;
|
|
|
|
/* Valid for fences created from semaphores: */
|
|
struct gk20a_semaphore *semaphore;
|
|
wait_queue_head_t *semaphore_wq;
|
|
|
|
/* Valid for fences created from syncpoints: */
|
|
struct platform_device *host1x_pdev;
|
|
u32 syncpt_id;
|
|
u32 syncpt_value;
|
|
|
|
/* Valid for fences part of a pre-allocated fence pool */
|
|
struct gk20a_allocator *allocator;
|
|
};
|
|
|
|
/* Fences can be created from semaphores or syncpoint (id, value) pairs */
|
|
int gk20a_fence_from_semaphore(
|
|
struct gk20a_fence *fence_out,
|
|
struct sync_timeline *timeline,
|
|
struct gk20a_semaphore *semaphore,
|
|
wait_queue_head_t *semaphore_wq,
|
|
struct sync_fence *dependency,
|
|
bool wfi, bool need_sync_fence);
|
|
|
|
int gk20a_fence_from_syncpt(
|
|
struct gk20a_fence *fence_out,
|
|
struct platform_device *host1x_pdev,
|
|
u32 id, u32 value, bool wfi,
|
|
bool need_sync_fence);
|
|
|
|
int gk20a_alloc_fence_pool(
|
|
struct channel_gk20a *c,
|
|
int size);
|
|
|
|
void gk20a_free_fence_pool(
|
|
struct channel_gk20a *c);
|
|
|
|
struct gk20a_fence *gk20a_alloc_fence(
|
|
struct channel_gk20a *c);
|
|
|
|
void gk20a_init_fence(struct gk20a_fence *f,
|
|
const struct gk20a_fence_ops *ops,
|
|
struct sync_fence *sync_fence, bool wfi);
|
|
|
|
/* Fence operations */
|
|
void gk20a_fence_put(struct gk20a_fence *f);
|
|
struct gk20a_fence *gk20a_fence_get(struct gk20a_fence *f);
|
|
int gk20a_fence_wait(struct gk20a_fence *f, int timeout);
|
|
bool gk20a_fence_is_expired(struct gk20a_fence *f);
|
|
int gk20a_fence_install_fd(struct gk20a_fence *f);
|
|
|
|
#endif
|