From 9d77db3c730780c8ef5ccd4b66403ff5675cfe4e Mon Sep 17 00:00:00 2001
From: hc <hc@nodka.com>
Date: Mon, 13 May 2024 10:30:14 +0000
Subject: [PATCH] modify sin led gpio
---
kernel/drivers/gpu/drm/v3d/v3d_gem.c | 788 +++++++++++++++++++++++++++++++++++++------------------
1 files changed, 525 insertions(+), 263 deletions(-)
diff --git a/kernel/drivers/gpu/drm/v3d/v3d_gem.c b/kernel/drivers/gpu/drm/v3d/v3d_gem.c
index 5ce2409..64fe63c 100644
--- a/kernel/drivers/gpu/drm/v3d/v3d_gem.c
+++ b/kernel/drivers/gpu/drm/v3d/v3d_gem.c
@@ -1,16 +1,19 @@
// SPDX-License-Identifier: GPL-2.0+
/* Copyright (C) 2014-2018 Broadcom */
-#include <drm/drmP.h>
-#include <drm/drm_syncobj.h>
+#include <linux/device.h>
+#include <linux/dma-mapping.h>
+#include <linux/io.h>
#include <linux/module.h>
#include <linux/platform_device.h>
#include <linux/pm_runtime.h>
-#include <linux/device.h>
-#include <linux/io.h>
+#include <linux/reset.h>
#include <linux/sched/signal.h>
+#include <linux/uaccess.h>
-#include "uapi/drm/v3d_drm.h"
+#include <drm/drm_syncobj.h>
+#include <uapi/drm/v3d_drm.h>
+
#include "v3d_drv.h"
#include "v3d_regs.h"
#include "v3d_trace.h"
@@ -24,7 +27,8 @@
* type. If you want the default behavior, you can still put
* "2" in the indirect texture state's output_type field.
*/
- V3D_CORE_WRITE(core, V3D_CTL_MISCCFG, V3D_MISCCFG_OVRTMUOUT);
+ if (v3d->ver < 40)
+ V3D_CORE_WRITE(core, V3D_CTL_MISCCFG, V3D_MISCCFG_OVRTMUOUT);
/* Whenever we flush the L2T cache, we always want to flush
* the whole thing.
@@ -69,7 +73,7 @@
}
static void
-v3d_reset_v3d(struct v3d_dev *v3d)
+v3d_reset_by_bridge(struct v3d_dev *v3d)
{
int version = V3D_BRIDGE_READ(V3D_TOP_GR_BRIDGE_REVISION);
@@ -89,6 +93,15 @@
V3D_TOP_GR_BRIDGE_SW_INIT_1_V3D_CLK_108_SW_INIT);
V3D_BRIDGE_WRITE(V3D_TOP_GR_BRIDGE_SW_INIT_1, 0);
}
+}
+
+static void
+v3d_reset_v3d(struct v3d_dev *v3d)
+{
+ if (v3d->reset)
+ reset_control_reset(v3d->reset);
+ else
+ v3d_reset_by_bridge(v3d);
v3d_init_hw_state(v3d);
}
@@ -98,7 +111,9 @@
{
struct drm_device *dev = &v3d->drm;
- DRM_ERROR("Resetting GPU.\n");
+ DRM_DEV_ERROR(dev->dev, "Resetting GPU for hang.\n");
+ DRM_DEV_ERROR(dev->dev, "V3D_ERR_STAT: 0x%08x\n",
+ V3D_CORE_READ(0, V3D_ERR_STAT));
trace_v3d_reset_begin(dev);
/* XXX: only needed for safe powerdown, not reset. */
@@ -130,38 +145,73 @@
}
}
-/* Invalidates the (read-only) L2 cache. */
+/* Invalidates the (read-only) L2C cache. This was the L2 cache for
+ * uniforms and instructions on V3D 3.2.
+ */
static void
-v3d_invalidate_l2(struct v3d_dev *v3d, int core)
+v3d_invalidate_l2c(struct v3d_dev *v3d, int core)
{
+ if (v3d->ver > 32)
+ return;
+
V3D_CORE_WRITE(core, V3D_CTL_L2CACTL,
V3D_L2CACTL_L2CCLR |
V3D_L2CACTL_L2CENA);
-}
-
-static void
-v3d_invalidate_l1td(struct v3d_dev *v3d, int core)
-{
- V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL, V3D_L2TCACTL_TMUWCF);
- if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
- V3D_L2TCACTL_L2TFLS), 100)) {
- DRM_ERROR("Timeout waiting for L1T write combiner flush\n");
- }
}
/* Invalidates texture L2 cachelines */
static void
v3d_flush_l2t(struct v3d_dev *v3d, int core)
{
- v3d_invalidate_l1td(v3d, core);
-
+ /* While there is a busy bit (V3D_L2TCACTL_L2TFLS), we don't
+ * need to wait for completion before dispatching the job --
+ * L2T accesses will be stalled until the flush has completed.
+ * However, we do need to make sure we don't try to trigger a
+ * new flush while the L2_CLEAN queue is trying to
+ * synchronously clean after a job.
+ */
+ mutex_lock(&v3d->cache_clean_lock);
V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL,
V3D_L2TCACTL_L2TFLS |
V3D_SET_FIELD(V3D_L2TCACTL_FLM_FLUSH, V3D_L2TCACTL_FLM));
+ mutex_unlock(&v3d->cache_clean_lock);
+}
+
+/* Cleans texture L1 and L2 cachelines (writing back dirty data).
+ *
+ * For cleaning, which happens from the CACHE_CLEAN queue after CSD has
+ * executed, we need to make sure that the clean is done before
+ * signaling job completion. So, we synchronously wait before
+ * returning, and we make sure that L2 invalidates don't happen in the
+ * meantime to confuse our are-we-done checks.
+ */
+void
+v3d_clean_caches(struct v3d_dev *v3d)
+{
+ struct drm_device *dev = &v3d->drm;
+ int core = 0;
+
+ trace_v3d_cache_clean_begin(dev);
+
+ V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL, V3D_L2TCACTL_TMUWCF);
+ if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
+ V3D_L2TCACTL_TMUWCF), 100)) {
+ DRM_ERROR("Timeout waiting for TMU write combiner flush\n");
+ }
+
+ mutex_lock(&v3d->cache_clean_lock);
+ V3D_CORE_WRITE(core, V3D_CTL_L2TCACTL,
+ V3D_L2TCACTL_L2TFLS |
+ V3D_SET_FIELD(V3D_L2TCACTL_FLM_CLEAN, V3D_L2TCACTL_FLM));
+
if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
V3D_L2TCACTL_L2TFLS), 100)) {
- DRM_ERROR("Timeout waiting for L2T flush\n");
+ DRM_ERROR("Timeout waiting for L2T clean\n");
}
+
+ mutex_unlock(&v3d->cache_clean_lock);
+
+ trace_v3d_cache_clean_end(dev);
}
/* Invalidates the slice caches. These are read-only caches. */
@@ -175,66 +225,18 @@
V3D_SET_FIELD(0xf, V3D_SLCACTL_ICC));
}
-/* Invalidates texture L2 cachelines */
-static void
-v3d_invalidate_l2t(struct v3d_dev *v3d, int core)
-{
- V3D_CORE_WRITE(core,
- V3D_CTL_L2TCACTL,
- V3D_L2TCACTL_L2TFLS |
- V3D_SET_FIELD(V3D_L2TCACTL_FLM_CLEAR, V3D_L2TCACTL_FLM));
- if (wait_for(!(V3D_CORE_READ(core, V3D_CTL_L2TCACTL) &
- V3D_L2TCACTL_L2TFLS), 100)) {
- DRM_ERROR("Timeout waiting for L2T invalidate\n");
- }
-}
-
void
v3d_invalidate_caches(struct v3d_dev *v3d)
{
+ /* Invalidate the caches from the outside in. That way if
+ * another CL's concurrent use of nearby memory were to pull
+ * an invalidated cacheline back in, we wouldn't leave stale
+ * data in the inner cache.
+ */
v3d_flush_l3(v3d);
-
- v3d_invalidate_l2(v3d, 0);
- v3d_invalidate_slices(v3d, 0);
+ v3d_invalidate_l2c(v3d, 0);
v3d_flush_l2t(v3d, 0);
-}
-
-void
-v3d_flush_caches(struct v3d_dev *v3d)
-{
- v3d_invalidate_l1td(v3d, 0);
- v3d_invalidate_l2t(v3d, 0);
-}
-
-static void
-v3d_attach_object_fences(struct v3d_exec_info *exec)
-{
- struct dma_fence *out_fence = &exec->render.base.s_fence->finished;
- struct v3d_bo *bo;
- int i;
-
- for (i = 0; i < exec->bo_count; i++) {
- bo = to_v3d_bo(&exec->bo[i]->base);
-
- /* XXX: Use shared fences for read-only objects. */
- reservation_object_add_excl_fence(bo->resv, out_fence);
- }
-}
-
-static void
-v3d_unlock_bo_reservations(struct drm_device *dev,
- struct v3d_exec_info *exec,
- struct ww_acquire_ctx *acquire_ctx)
-{
- int i;
-
- for (i = 0; i < exec->bo_count; i++) {
- struct v3d_bo *bo = to_v3d_bo(&exec->bo[i]->base);
-
- ww_mutex_unlock(&bo->resv->lock);
- }
-
- ww_acquire_fini(acquire_ctx);
+ v3d_invalidate_slices(v3d, 0);
}
/* Takes the reservation lock on all the BOs being referenced, so that
@@ -245,69 +247,21 @@
* to v3d, so we don't attach dma-buf fences to them.
*/
static int
-v3d_lock_bo_reservations(struct drm_device *dev,
- struct v3d_exec_info *exec,
+v3d_lock_bo_reservations(struct v3d_job *job,
struct ww_acquire_ctx *acquire_ctx)
{
- int contended_lock = -1;
int i, ret;
- struct v3d_bo *bo;
- ww_acquire_init(acquire_ctx, &reservation_ww_class);
+ ret = drm_gem_lock_reservations(job->bo, job->bo_count, acquire_ctx);
+ if (ret)
+ return ret;
-retry:
- if (contended_lock != -1) {
- bo = to_v3d_bo(&exec->bo[contended_lock]->base);
- ret = ww_mutex_lock_slow_interruptible(&bo->resv->lock,
- acquire_ctx);
+ for (i = 0; i < job->bo_count; i++) {
+ ret = drm_gem_fence_array_add_implicit(&job->deps,
+ job->bo[i], true);
if (ret) {
- ww_acquire_done(acquire_ctx);
- return ret;
- }
- }
-
- for (i = 0; i < exec->bo_count; i++) {
- if (i == contended_lock)
- continue;
-
- bo = to_v3d_bo(&exec->bo[i]->base);
-
- ret = ww_mutex_lock_interruptible(&bo->resv->lock, acquire_ctx);
- if (ret) {
- int j;
-
- for (j = 0; j < i; j++) {
- bo = to_v3d_bo(&exec->bo[j]->base);
- ww_mutex_unlock(&bo->resv->lock);
- }
-
- if (contended_lock != -1 && contended_lock >= i) {
- bo = to_v3d_bo(&exec->bo[contended_lock]->base);
-
- ww_mutex_unlock(&bo->resv->lock);
- }
-
- if (ret == -EDEADLK) {
- contended_lock = i;
- goto retry;
- }
-
- ww_acquire_done(acquire_ctx);
- return ret;
- }
- }
-
- ww_acquire_done(acquire_ctx);
-
- /* Reserve space for our shared (read-only) fence references,
- * before we commit the CL to the hardware.
- */
- for (i = 0; i < exec->bo_count; i++) {
- bo = to_v3d_bo(&exec->bo[i]->base);
-
- ret = reservation_object_reserve_shared(bo->resv);
- if (ret) {
- v3d_unlock_bo_reservations(dev, exec, acquire_ctx);
+ drm_gem_unlock_reservations(job->bo, job->bo_count,
+ acquire_ctx);
return ret;
}
}
@@ -316,11 +270,11 @@
}
/**
- * v3d_cl_lookup_bos() - Sets up exec->bo[] with the GEM objects
+ * v3d_lookup_bos() - Sets up job->bo[] with the GEM objects
* referenced by the job.
* @dev: DRM device
* @file_priv: DRM file for this fd
- * @exec: V3D job being set up
+ * @job: V3D job being set up
*
* The command validator needs to reference BOs by their index within
* the submitted job's BO list. This does the validation of the job's
@@ -330,18 +284,19 @@
* failure, because that will happen at v3d_exec_cleanup() time.
*/
static int
-v3d_cl_lookup_bos(struct drm_device *dev,
- struct drm_file *file_priv,
- struct drm_v3d_submit_cl *args,
- struct v3d_exec_info *exec)
+v3d_lookup_bos(struct drm_device *dev,
+ struct drm_file *file_priv,
+ struct v3d_job *job,
+ u64 bo_handles,
+ u32 bo_count)
{
u32 *handles;
int ret = 0;
int i;
- exec->bo_count = args->bo_handle_count;
+ job->bo_count = bo_count;
- if (!exec->bo_count) {
+ if (!job->bo_count) {
/* See comment on bo_index for why we have to check
* this.
*/
@@ -349,15 +304,15 @@
return -EINVAL;
}
- exec->bo = kvmalloc_array(exec->bo_count,
- sizeof(struct drm_gem_cma_object *),
- GFP_KERNEL | __GFP_ZERO);
- if (!exec->bo) {
+ job->bo = kvmalloc_array(job->bo_count,
+ sizeof(struct drm_gem_cma_object *),
+ GFP_KERNEL | __GFP_ZERO);
+ if (!job->bo) {
DRM_DEBUG("Failed to allocate validated BO pointers\n");
return -ENOMEM;
}
- handles = kvmalloc_array(exec->bo_count, sizeof(u32), GFP_KERNEL);
+ handles = kvmalloc_array(job->bo_count, sizeof(u32), GFP_KERNEL);
if (!handles) {
ret = -ENOMEM;
DRM_DEBUG("Failed to allocate incoming GEM handles\n");
@@ -365,15 +320,15 @@
}
if (copy_from_user(handles,
- (void __user *)(uintptr_t)args->bo_handles,
- exec->bo_count * sizeof(u32))) {
+ (void __user *)(uintptr_t)bo_handles,
+ job->bo_count * sizeof(u32))) {
ret = -EFAULT;
DRM_DEBUG("Failed to copy in GEM handles\n");
goto fail;
}
spin_lock(&file_priv->table_lock);
- for (i = 0; i < exec->bo_count; i++) {
+ for (i = 0; i < job->bo_count; i++) {
struct drm_gem_object *bo = idr_find(&file_priv->object_idr,
handles[i]);
if (!bo) {
@@ -384,7 +339,7 @@
goto fail;
}
drm_gem_object_get(bo);
- exec->bo[i] = to_v3d_bo(bo);
+ job->bo[i] = bo;
}
spin_unlock(&file_priv->table_lock);
@@ -394,39 +349,50 @@
}
static void
-v3d_exec_cleanup(struct kref *ref)
+v3d_job_free(struct kref *ref)
{
- struct v3d_exec_info *exec = container_of(ref, struct v3d_exec_info,
- refcount);
- struct v3d_dev *v3d = exec->v3d;
- unsigned int i;
- struct v3d_bo *bo, *save;
+ struct v3d_job *job = container_of(ref, struct v3d_job, refcount);
+ unsigned long index;
+ struct dma_fence *fence;
+ int i;
- dma_fence_put(exec->bin.in_fence);
- dma_fence_put(exec->render.in_fence);
-
- dma_fence_put(exec->bin.done_fence);
- dma_fence_put(exec->render.done_fence);
-
- dma_fence_put(exec->bin_done_fence);
-
- for (i = 0; i < exec->bo_count; i++)
- drm_gem_object_put_unlocked(&exec->bo[i]->base);
- kvfree(exec->bo);
-
- list_for_each_entry_safe(bo, save, &exec->unref_list, unref_head) {
- drm_gem_object_put_unlocked(&bo->base);
+ for (i = 0; i < job->bo_count; i++) {
+ if (job->bo[i])
+ drm_gem_object_put(job->bo[i]);
}
+ kvfree(job->bo);
- pm_runtime_mark_last_busy(v3d->dev);
- pm_runtime_put_autosuspend(v3d->dev);
+ xa_for_each(&job->deps, index, fence) {
+ dma_fence_put(fence);
+ }
+ xa_destroy(&job->deps);
- kfree(exec);
+ dma_fence_put(job->irq_fence);
+ dma_fence_put(job->done_fence);
+
+ pm_runtime_mark_last_busy(job->v3d->drm.dev);
+ pm_runtime_put_autosuspend(job->v3d->drm.dev);
+
+ kfree(job);
}
-void v3d_exec_put(struct v3d_exec_info *exec)
+static void
+v3d_render_job_free(struct kref *ref)
{
- kref_put(&exec->refcount, v3d_exec_cleanup);
+ struct v3d_render_job *job = container_of(ref, struct v3d_render_job,
+ base.refcount);
+ struct v3d_bo *bo, *save;
+
+ list_for_each_entry_safe(bo, save, &job->unref_list, unref_head) {
+ drm_gem_object_put(&bo->base.base);
+ }
+
+ v3d_job_free(ref);
+}
+
+void v3d_job_put(struct v3d_job *job)
+{
+ kref_put(&job->refcount, job->free);
}
int
@@ -435,8 +401,6 @@
{
int ret;
struct drm_v3d_wait_bo *args = data;
- struct drm_gem_object *gem_obj;
- struct v3d_bo *bo;
ktime_t start = ktime_get();
u64 delta_ns;
unsigned long timeout_jiffies =
@@ -445,21 +409,8 @@
if (args->pad != 0)
return -EINVAL;
- gem_obj = drm_gem_object_lookup(file_priv, args->handle);
- if (!gem_obj) {
- DRM_DEBUG("Failed to look up GEM BO %d\n", args->handle);
- return -EINVAL;
- }
- bo = to_v3d_bo(gem_obj);
-
- ret = reservation_object_wait_timeout_rcu(bo->resv,
- true, true,
- timeout_jiffies);
-
- if (ret == 0)
- ret = -ETIME;
- else if (ret > 0)
- ret = 0;
+ ret = drm_gem_dma_resv_wait(file_priv, args->handle,
+ true, timeout_jiffies);
/* Decrement the user's timeout, in case we got interrupted
* such that the ioctl will be restarted.
@@ -474,9 +425,88 @@
if (ret == -ETIME && args->timeout_ns)
ret = -EAGAIN;
- drm_gem_object_put_unlocked(gem_obj);
-
return ret;
+}
+
+static int
+v3d_job_init(struct v3d_dev *v3d, struct drm_file *file_priv,
+ struct v3d_job *job, void (*free)(struct kref *ref),
+ u32 in_sync)
+{
+ struct dma_fence *in_fence = NULL;
+ int ret;
+
+ job->v3d = v3d;
+ job->free = free;
+
+ ret = pm_runtime_get_sync(v3d->drm.dev);
+ if (ret < 0)
+ return ret;
+
+ xa_init_flags(&job->deps, XA_FLAGS_ALLOC);
+
+ ret = drm_syncobj_find_fence(file_priv, in_sync, 0, 0, &in_fence);
+ if (ret == -EINVAL)
+ goto fail;
+
+ ret = drm_gem_fence_array_add(&job->deps, in_fence);
+ if (ret)
+ goto fail;
+
+ kref_init(&job->refcount);
+
+ return 0;
+fail:
+ xa_destroy(&job->deps);
+ pm_runtime_put_autosuspend(v3d->drm.dev);
+ return ret;
+}
+
+static int
+v3d_push_job(struct v3d_file_priv *v3d_priv,
+ struct v3d_job *job, enum v3d_queue queue)
+{
+ int ret;
+
+ ret = drm_sched_job_init(&job->base, &v3d_priv->sched_entity[queue],
+ v3d_priv);
+ if (ret)
+ return ret;
+
+ job->done_fence = dma_fence_get(&job->base.s_fence->finished);
+
+ /* put by scheduler job completion */
+ kref_get(&job->refcount);
+
+ drm_sched_entity_push_job(&job->base, &v3d_priv->sched_entity[queue]);
+
+ return 0;
+}
+
+static void
+v3d_attach_fences_and_unlock_reservation(struct drm_file *file_priv,
+ struct v3d_job *job,
+ struct ww_acquire_ctx *acquire_ctx,
+ u32 out_sync,
+ struct dma_fence *done_fence)
+{
+ struct drm_syncobj *sync_out;
+ int i;
+
+ for (i = 0; i < job->bo_count; i++) {
+ /* XXX: Use shared fences for read-only objects. */
+ dma_resv_add_excl_fence(job->bo[i]->resv,
+ job->done_fence);
+ }
+
+ drm_gem_unlock_reservations(job->bo, job->bo_count, acquire_ctx);
+
+ /* Update the return sync object for the job */
+ sync_out = drm_syncobj_find(file_priv, out_sync);
+ if (sync_out) {
+ drm_syncobj_replace_fence(sync_out, done_fence);
+ drm_syncobj_put(sync_out);
+ }
}
/**
@@ -498,106 +528,336 @@
struct v3d_dev *v3d = to_v3d_dev(dev);
struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
struct drm_v3d_submit_cl *args = data;
- struct v3d_exec_info *exec;
+ struct v3d_bin_job *bin = NULL;
+ struct v3d_render_job *render;
+ struct v3d_job *clean_job = NULL;
+ struct v3d_job *last_job;
struct ww_acquire_ctx acquire_ctx;
- struct drm_syncobj *sync_out;
int ret = 0;
- if (args->pad != 0) {
- DRM_INFO("pad must be zero: %d\n", args->pad);
+ trace_v3d_submit_cl_ioctl(&v3d->drm, args->rcl_start, args->rcl_end);
+
+ if (args->flags != 0 &&
+ args->flags != DRM_V3D_SUBMIT_CL_FLUSH_CACHE) {
+ DRM_INFO("invalid flags: %d\n", args->flags);
return -EINVAL;
}
- exec = kcalloc(1, sizeof(*exec), GFP_KERNEL);
- if (!exec)
+ render = kcalloc(1, sizeof(*render), GFP_KERNEL);
+ if (!render)
return -ENOMEM;
- ret = pm_runtime_get_sync(v3d->dev);
- if (ret < 0) {
- kfree(exec);
+ render->start = args->rcl_start;
+ render->end = args->rcl_end;
+ INIT_LIST_HEAD(&render->unref_list);
+
+ ret = v3d_job_init(v3d, file_priv, &render->base,
+ v3d_render_job_free, args->in_sync_rcl);
+ if (ret) {
+ kfree(render);
return ret;
}
- kref_init(&exec->refcount);
+ if (args->bcl_start != args->bcl_end) {
+ bin = kcalloc(1, sizeof(*bin), GFP_KERNEL);
+ if (!bin) {
+ v3d_job_put(&render->base);
+ return -ENOMEM;
+ }
- ret = drm_syncobj_find_fence(file_priv, args->in_sync_bcl,
- &exec->bin.in_fence);
- if (ret == -EINVAL)
- goto fail;
+ ret = v3d_job_init(v3d, file_priv, &bin->base,
+ v3d_job_free, args->in_sync_bcl);
+ if (ret) {
+ v3d_job_put(&render->base);
+ kfree(bin);
+ return ret;
+ }
- ret = drm_syncobj_find_fence(file_priv, args->in_sync_rcl,
- &exec->render.in_fence);
- if (ret == -EINVAL)
- goto fail;
+ bin->start = args->bcl_start;
+ bin->end = args->bcl_end;
+ bin->qma = args->qma;
+ bin->qms = args->qms;
+ bin->qts = args->qts;
+ bin->render = render;
+ }
- exec->qma = args->qma;
- exec->qms = args->qms;
- exec->qts = args->qts;
- exec->bin.exec = exec;
- exec->bin.start = args->bcl_start;
- exec->bin.end = args->bcl_end;
- exec->render.exec = exec;
- exec->render.start = args->rcl_start;
- exec->render.end = args->rcl_end;
- exec->v3d = v3d;
- INIT_LIST_HEAD(&exec->unref_list);
+ if (args->flags & DRM_V3D_SUBMIT_CL_FLUSH_CACHE) {
+ clean_job = kcalloc(1, sizeof(*clean_job), GFP_KERNEL);
+ if (!clean_job) {
+ ret = -ENOMEM;
+ goto fail;
+ }
- ret = v3d_cl_lookup_bos(dev, file_priv, args, exec);
+ ret = v3d_job_init(v3d, file_priv, clean_job, v3d_job_free, 0);
+ if (ret) {
+ kfree(clean_job);
+ clean_job = NULL;
+ goto fail;
+ }
+
+ last_job = clean_job;
+ } else {
+ last_job = &render->base;
+ }
+
+ ret = v3d_lookup_bos(dev, file_priv, last_job,
+ args->bo_handles, args->bo_handle_count);
if (ret)
goto fail;
- ret = v3d_lock_bo_reservations(dev, exec, &acquire_ctx);
+ ret = v3d_lock_bo_reservations(last_job, &acquire_ctx);
if (ret)
goto fail;
mutex_lock(&v3d->sched_lock);
- if (exec->bin.start != exec->bin.end) {
- ret = drm_sched_job_init(&exec->bin.base,
- &v3d_priv->sched_entity[V3D_BIN],
- v3d_priv);
+ if (bin) {
+ ret = v3d_push_job(v3d_priv, &bin->base, V3D_BIN);
if (ret)
goto fail_unreserve;
- exec->bin_done_fence =
- dma_fence_get(&exec->bin.base.s_fence->finished);
-
- kref_get(&exec->refcount); /* put by scheduler job completion */
- drm_sched_entity_push_job(&exec->bin.base,
- &v3d_priv->sched_entity[V3D_BIN]);
+ ret = drm_gem_fence_array_add(&render->base.deps,
+ dma_fence_get(bin->base.done_fence));
+ if (ret)
+ goto fail_unreserve;
}
- ret = drm_sched_job_init(&exec->render.base,
- &v3d_priv->sched_entity[V3D_RENDER],
- v3d_priv);
+ ret = v3d_push_job(v3d_priv, &render->base, V3D_RENDER);
if (ret)
goto fail_unreserve;
- kref_get(&exec->refcount); /* put by scheduler job completion */
- drm_sched_entity_push_job(&exec->render.base,
- &v3d_priv->sched_entity[V3D_RENDER]);
- mutex_unlock(&v3d->sched_lock);
-
- v3d_attach_object_fences(exec);
-
- v3d_unlock_bo_reservations(dev, exec, &acquire_ctx);
-
- /* Update the return sync object for the */
- sync_out = drm_syncobj_find(file_priv, args->out_sync);
- if (sync_out) {
- drm_syncobj_replace_fence(sync_out,
- &exec->render.base.s_fence->finished);
- drm_syncobj_put(sync_out);
+ if (clean_job) {
+ struct dma_fence *render_fence =
+ dma_fence_get(render->base.done_fence);
+ ret = drm_gem_fence_array_add(&clean_job->deps, render_fence);
+ if (ret)
+ goto fail_unreserve;
+ ret = v3d_push_job(v3d_priv, clean_job, V3D_CACHE_CLEAN);
+ if (ret)
+ goto fail_unreserve;
}
- v3d_exec_put(exec);
+ mutex_unlock(&v3d->sched_lock);
+
+ v3d_attach_fences_and_unlock_reservation(file_priv,
+ last_job,
+ &acquire_ctx,
+ args->out_sync,
+ last_job->done_fence);
+
+ if (bin)
+ v3d_job_put(&bin->base);
+ v3d_job_put(&render->base);
+ if (clean_job)
+ v3d_job_put(clean_job);
return 0;
fail_unreserve:
mutex_unlock(&v3d->sched_lock);
- v3d_unlock_bo_reservations(dev, exec, &acquire_ctx);
+ drm_gem_unlock_reservations(last_job->bo,
+ last_job->bo_count, &acquire_ctx);
fail:
- v3d_exec_put(exec);
+ if (bin)
+ v3d_job_put(&bin->base);
+ v3d_job_put(&render->base);
+ if (clean_job)
+ v3d_job_put(clean_job);
+
+ return ret;
+}
+
+/**
+ * v3d_submit_tfu_ioctl() - Submits a TFU (texture formatting) job to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * Userspace provides the register setup for the TFU, which we don't
+ * need to validate since the TFU is behind the MMU.
+ */
+int
+v3d_submit_tfu_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file_priv)
+{
+ struct v3d_dev *v3d = to_v3d_dev(dev);
+ struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+ struct drm_v3d_submit_tfu *args = data;
+ struct v3d_tfu_job *job;
+ struct ww_acquire_ctx acquire_ctx;
+ int ret = 0;
+
+ trace_v3d_submit_tfu_ioctl(&v3d->drm, args->iia);
+
+ job = kcalloc(1, sizeof(*job), GFP_KERNEL);
+ if (!job)
+ return -ENOMEM;
+
+ ret = v3d_job_init(v3d, file_priv, &job->base,
+ v3d_job_free, args->in_sync);
+ if (ret) {
+ kfree(job);
+ return ret;
+ }
+
+ job->base.bo = kcalloc(ARRAY_SIZE(args->bo_handles),
+ sizeof(*job->base.bo), GFP_KERNEL);
+ if (!job->base.bo) {
+ v3d_job_put(&job->base);
+ return -ENOMEM;
+ }
+
+ job->args = *args;
+
+ spin_lock(&file_priv->table_lock);
+ for (job->base.bo_count = 0;
+ job->base.bo_count < ARRAY_SIZE(args->bo_handles);
+ job->base.bo_count++) {
+ struct drm_gem_object *bo;
+
+ if (!args->bo_handles[job->base.bo_count])
+ break;
+
+ bo = idr_find(&file_priv->object_idr,
+ args->bo_handles[job->base.bo_count]);
+ if (!bo) {
+ DRM_DEBUG("Failed to look up GEM BO %d: %d\n",
+ job->base.bo_count,
+ args->bo_handles[job->base.bo_count]);
+ ret = -ENOENT;
+ spin_unlock(&file_priv->table_lock);
+ goto fail;
+ }
+ drm_gem_object_get(bo);
+ job->base.bo[job->base.bo_count] = bo;
+ }
+ spin_unlock(&file_priv->table_lock);
+
+ ret = v3d_lock_bo_reservations(&job->base, &acquire_ctx);
+ if (ret)
+ goto fail;
+
+ mutex_lock(&v3d->sched_lock);
+ ret = v3d_push_job(v3d_priv, &job->base, V3D_TFU);
+ if (ret)
+ goto fail_unreserve;
+ mutex_unlock(&v3d->sched_lock);
+
+ v3d_attach_fences_and_unlock_reservation(file_priv,
+ &job->base, &acquire_ctx,
+ args->out_sync,
+ job->base.done_fence);
+
+ v3d_job_put(&job->base);
+
+ return 0;
+
+fail_unreserve:
+ mutex_unlock(&v3d->sched_lock);
+ drm_gem_unlock_reservations(job->base.bo, job->base.bo_count,
+ &acquire_ctx);
+fail:
+ v3d_job_put(&job->base);
+
+ return ret;
+}
+
+/**
+ * v3d_submit_csd_ioctl() - Submits a CSD (texture formatting) job to the V3D.
+ * @dev: DRM device
+ * @data: ioctl argument
+ * @file_priv: DRM file for this fd
+ *
+ * Userspace provides the register setup for the CSD, which we don't
+ * need to validate since the CSD is behind the MMU.
+ */
+int
+v3d_submit_csd_ioctl(struct drm_device *dev, void *data,
+ struct drm_file *file_priv)
+{
+ struct v3d_dev *v3d = to_v3d_dev(dev);
+ struct v3d_file_priv *v3d_priv = file_priv->driver_priv;
+ struct drm_v3d_submit_csd *args = data;
+ struct v3d_csd_job *job;
+ struct v3d_job *clean_job;
+ struct ww_acquire_ctx acquire_ctx;
+ int ret;
+
+ trace_v3d_submit_csd_ioctl(&v3d->drm, args->cfg[5], args->cfg[6]);
+
+ if (!v3d_has_csd(v3d)) {
+ DRM_DEBUG("Attempting CSD submit on non-CSD hardware\n");
+ return -EINVAL;
+ }
+
+ job = kcalloc(1, sizeof(*job), GFP_KERNEL);
+ if (!job)
+ return -ENOMEM;
+
+ ret = v3d_job_init(v3d, file_priv, &job->base,
+ v3d_job_free, args->in_sync);
+ if (ret) {
+ kfree(job);
+ return ret;
+ }
+
+ clean_job = kcalloc(1, sizeof(*clean_job), GFP_KERNEL);
+ if (!clean_job) {
+ v3d_job_put(&job->base);
+ kfree(job);
+ return -ENOMEM;
+ }
+
+ ret = v3d_job_init(v3d, file_priv, clean_job, v3d_job_free, 0);
+ if (ret) {
+ v3d_job_put(&job->base);
+ kfree(clean_job);
+ return ret;
+ }
+
+ job->args = *args;
+
+ ret = v3d_lookup_bos(dev, file_priv, clean_job,
+ args->bo_handles, args->bo_handle_count);
+ if (ret)
+ goto fail;
+
+ ret = v3d_lock_bo_reservations(clean_job, &acquire_ctx);
+ if (ret)
+ goto fail;
+
+ mutex_lock(&v3d->sched_lock);
+ ret = v3d_push_job(v3d_priv, &job->base, V3D_CSD);
+ if (ret)
+ goto fail_unreserve;
+
+ ret = drm_gem_fence_array_add(&clean_job->deps,
+ dma_fence_get(job->base.done_fence));
+ if (ret)
+ goto fail_unreserve;
+
+ ret = v3d_push_job(v3d_priv, clean_job, V3D_CACHE_CLEAN);
+ if (ret)
+ goto fail_unreserve;
+ mutex_unlock(&v3d->sched_lock);
+
+ v3d_attach_fences_and_unlock_reservation(file_priv,
+ clean_job,
+ &acquire_ctx,
+ args->out_sync,
+ clean_job->done_fence);
+
+ v3d_job_put(&job->base);
+ v3d_job_put(clean_job);
+
+ return 0;
+
+fail_unreserve:
+ mutex_unlock(&v3d->sched_lock);
+ drm_gem_unlock_reservations(clean_job->bo, clean_job->bo_count,
+ &acquire_ctx);
+fail:
+ v3d_job_put(&job->base);
+ v3d_job_put(clean_job);
return ret;
}
@@ -617,6 +877,7 @@
mutex_init(&v3d->bo_lock);
mutex_init(&v3d->reset_lock);
mutex_init(&v3d->sched_lock);
+ mutex_init(&v3d->cache_clean_lock);
/* Note: We don't allocate address 0. Various bits of HW
* treat 0 as special, such as the occlusion query counters
@@ -624,12 +885,12 @@
*/
drm_mm_init(&v3d->mm, 1, pt_size / sizeof(u32) - 1);
- v3d->pt = dma_alloc_wc(v3d->dev, pt_size,
+ v3d->pt = dma_alloc_wc(v3d->drm.dev, pt_size,
&v3d->pt_paddr,
GFP_KERNEL | __GFP_NOWARN | __GFP_ZERO);
if (!v3d->pt) {
drm_mm_takedown(&v3d->mm);
- dev_err(v3d->dev,
+ dev_err(v3d->drm.dev,
"Failed to allocate page tables. "
"Please ensure you have CMA enabled.\n");
return -ENOMEM;
@@ -641,7 +902,7 @@
ret = v3d_sched_init(v3d);
if (ret) {
drm_mm_takedown(&v3d->mm);
- dma_free_coherent(v3d->dev, 4096 * 1024, (void *)v3d->pt,
+ dma_free_coherent(v3d->drm.dev, 4096 * 1024, (void *)v3d->pt,
v3d->pt_paddr);
}
@@ -655,7 +916,7 @@
v3d_sched_fini(v3d);
- /* Waiting for exec to finish would need to be done before
+ /* Waiting for jobs to finish would need to be done before
* unregistering V3D.
*/
WARN_ON(v3d->bin_job);
@@ -663,5 +924,6 @@
drm_mm_takedown(&v3d->mm);
- dma_free_coherent(v3d->dev, 4096 * 1024, (void *)v3d->pt, v3d->pt_paddr);
+ dma_free_coherent(v3d->drm.dev, 4096 * 1024, (void *)v3d->pt,
+ v3d->pt_paddr);
}
--
Gitblit v1.6.2