linux/drivers/gpu/drm/i915/selftests/mock_gem_device.c

272 lines
6.9 KiB
C
Raw Normal View History

/*
* Copyright © 2016 Intel Corporation
*
* Permission is hereby granted, free of charge, to any person obtaining a
* copy of this software and associated documentation files (the "Software"),
* to deal in the Software without restriction, including without limitation
* the rights to use, copy, modify, merge, publish, distribute, sublicense,
* and/or sell copies of the Software, and to permit persons to whom the
* Software is furnished to do so, subject to the following conditions:
*
* The above copyright notice and this permission notice (including the next
* paragraph) shall be included in all copies or substantial portions of the
* Software.
*
* THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, EXPRESS OR
* IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF MERCHANTABILITY,
* FITNESS FOR A PARTICULAR PURPOSE AND NONINFRINGEMENT. IN NO EVENT SHALL
* THE AUTHORS OR COPYRIGHT HOLDERS BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER
* LIABILITY, WHETHER IN AN ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING
* FROM, OUT OF OR IN CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS
* IN THE SOFTWARE.
*
*/
#include <linux/pm_domain.h>
#include <linux/pm_runtime.h>
#include "mock_engine.h"
#include "mock_context.h"
#include "mock_request.h"
#include "mock_gem_device.h"
#include "mock_gem_object.h"
#include "mock_gtt.h"
#include "mock_uncore.h"
void mock_device_flush(struct drm_i915_private *i915)
{
struct intel_engine_cs *engine;
enum intel_engine_id id;
lockdep_assert_held(&i915->drm.struct_mutex);
for_each_engine(engine, i915, id)
mock_engine_flush(engine);
i915_retire_requests(i915);
drm/i915: Retire requests along rings In the next patch, rings are the central timeline as requests may jump between engines. Therefore in the future as we retire in order along the engine timeline, we may retire out-of-order within a ring (as the ring now occurs along multiple engines), leading to much hilarity in miscomputing the position of ring->head. As an added bonus, retiring along the ring reduces the penalty of having one execlists client do cleanup for another (old legacy submission shares a ring between all clients). The downside is that slow and irregular (off the critical path) process of cleaning up stale requests after userspace becomes a modicum less efficient. In the long run, it will become apparent that the ordered ring->request_list matches the ring->timeline, a fun challenge for the future will be unifying the two lists to avoid duplication! v2: We need both engine-order and ring-order processing to maintain our knowledge of where individual rings have completed upto as well as knowing what was last executing on any engine. And finally by decoupling retiring the contexts on the engine and the timelines along the rings, we do have to keep a reference to the context on each request (previously it was guaranteed by the context being pinned). v3: Not just a reference to the context, but we need to keep it pinned as we manipulate the rings; i.e. we need a pin for both the manipulation of the engine state during its retirements, and a separate pin for the manipulation of the ring state. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180430131503.5375-3-chris@chris-wilson.co.uk
2018-04-30 13:15:02 +00:00
GEM_BUG_ON(i915->gt.active_requests);
}
static void mock_device_release(struct drm_device *dev)
{
struct drm_i915_private *i915 = to_i915(dev);
struct intel_engine_cs *engine;
enum intel_engine_id id;
mutex_lock(&i915->drm.struct_mutex);
mock_device_flush(i915);
i915_gem_contexts_lost(i915);
mutex_unlock(&i915->drm.struct_mutex);
cancel_delayed_work_sync(&i915->gt.retire_work);
cancel_delayed_work_sync(&i915->gt.idle_work);
i915_gem_drain_workqueue(i915);
mutex_lock(&i915->drm.struct_mutex);
for_each_engine(engine, i915, id)
mock_engine_free(engine);
i915_gem_contexts_fini(i915);
mutex_unlock(&i915->drm.struct_mutex);
drain_workqueue(i915->wq);
i915_gem_drain_freed_objects(i915);
mutex_lock(&i915->drm.struct_mutex);
mock_fini_ggtt(i915);
mutex_unlock(&i915->drm.struct_mutex);
WARN_ON(!list_empty(&i915->gt.timelines));
destroy_workqueue(i915->wq);
kmem_cache_destroy(i915->priorities);
kmem_cache_destroy(i915->dependencies);
kmem_cache_destroy(i915->requests);
kmem_cache_destroy(i915->vmas);
kmem_cache_destroy(i915->objects);
i915_gemfs_fini(i915);
drm_mode_config_cleanup(&i915->drm);
drm_dev_fini(&i915->drm);
put_device(&i915->drm.pdev->dev);
}
static struct drm_driver mock_driver = {
.name = "mock",
.driver_features = DRIVER_GEM,
.release = mock_device_release,
.gem_close_object = i915_gem_close_object,
.gem_free_object_unlocked = i915_gem_free_object,
};
static void release_dev(struct device *dev)
{
struct pci_dev *pdev = to_pci_dev(dev);
kfree(pdev);
}
static void mock_retire_work_handler(struct work_struct *work)
{
}
static void mock_idle_work_handler(struct work_struct *work)
{
}
static int pm_domain_resume(struct device *dev)
{
return pm_generic_runtime_resume(dev);
}
static int pm_domain_suspend(struct device *dev)
{
return pm_generic_runtime_suspend(dev);
}
static struct dev_pm_domain pm_domain = {
.ops = {
.runtime_suspend = pm_domain_suspend,
.runtime_resume = pm_domain_resume,
},
};
struct drm_i915_private *mock_gem_device(void)
{
struct drm_i915_private *i915;
struct pci_dev *pdev;
int err;
pdev = kzalloc(sizeof(*pdev) + sizeof(*i915), GFP_KERNEL);
if (!pdev)
goto err;
device_initialize(&pdev->dev);
pdev->class = PCI_BASE_CLASS_DISPLAY << 16;
pdev->dev.release = release_dev;
dev_set_name(&pdev->dev, "mock");
dma_coerce_mask_and_coherent(&pdev->dev, DMA_BIT_MASK(32));
#if IS_ENABLED(CONFIG_IOMMU_API) && defined(CONFIG_INTEL_IOMMU)
/* hack to disable iommu for the fake device; force identity mapping */
pdev->dev.archdata.iommu = (void *)-1;
#endif
dev_pm_domain_set(&pdev->dev, &pm_domain);
pm_runtime_enable(&pdev->dev);
pm_runtime_dont_use_autosuspend(&pdev->dev);
if (pm_runtime_enabled(&pdev->dev))
WARN_ON(pm_runtime_get_sync(&pdev->dev));
i915 = (struct drm_i915_private *)(pdev + 1);
pci_set_drvdata(pdev, i915);
err = drm_dev_init(&i915->drm, &mock_driver, &pdev->dev);
if (err) {
pr_err("Failed to initialise mock GEM device: err=%d\n", err);
goto put_device;
}
i915->drm.pdev = pdev;
i915->drm.dev_private = i915;
/* Using the global GTT may ask questions about KMS users, so prepare */
drm_mode_config_init(&i915->drm);
mkwrite_device_info(i915)->gen = -1;
mkwrite_device_info(i915)->page_sizes =
I915_GTT_PAGE_SIZE_4K |
I915_GTT_PAGE_SIZE_64K |
I915_GTT_PAGE_SIZE_2M;
mock_uncore_init(i915);
drm/i915/selftests: Yet another forgotten mock_i915->mm initialiser Move all of the i915->mm initialisation to a private function that can be reused by the mock i915 device to save forgetting any more steps. For example, <7>[ 1542.046332] [IGT] drv_selftest: starting subtest mock_objects <4>[ 1542.123924] Setting dangerous option mock_selftests - tainting kernel <6>[ 1542.167941] i915: Performing mock selftests with st_random_seed=0x246f5ab5 st_timeout=1000 <4>[ 1542.178012] INFO: trying to register non-static key. <4>[ 1542.178027] the code is fine but needs lockdep annotation. <4>[ 1542.178032] turning off the locking correctness validator. <4>[ 1542.178041] CPU: 3 PID: 6008 Comm: kworker/3:7 Tainted: G U 4.14.0-rc8-CI-CI_DRM_3332+ #1 <4>[ 1542.178049] Hardware name: /NUC6CAYB, BIOS AYAPLCEL.86A.0040.2017.0619.1722 06/19/2017 <4>[ 1542.178144] Workqueue: events __i915_gem_free_work [i915] <4>[ 1542.178152] Call Trace: <4>[ 1542.178163] dump_stack+0x68/0x9f <4>[ 1542.178170] register_lock_class+0x3fd/0x580 <4>[ 1542.178177] ? unwind_next_frame+0x14/0x20 <4>[ 1542.178184] ? __save_stack_trace+0x73/0xd0 <4>[ 1542.178191] __lock_acquire+0xa4/0x1b00 <4>[ 1542.178254] ? __i915_gem_free_work+0x28/0xa0 [i915] <4>[ 1542.178261] ? __lock_acquire+0x4ab/0x1b00 <4>[ 1542.178268] lock_acquire+0xb0/0x200 <4>[ 1542.178273] ? lock_acquire+0xb0/0x200 <4>[ 1542.178336] ? __i915_gem_free_work+0x28/0xa0 [i915] <4>[ 1542.178344] _raw_spin_lock+0x32/0x50 <4>[ 1542.178405] ? __i915_gem_free_work+0x28/0xa0 [i915] <4>[ 1542.178468] __i915_gem_free_work+0x28/0xa0 [i915] <4>[ 1542.178476] process_one_work+0x221/0x650 <4>[ 1542.178483] worker_thread+0x4e/0x3c0 <4>[ 1542.178489] kthread+0x114/0x150 <4>[ 1542.178494] ? process_one_work+0x650/0x650 <4>[ 1542.178499] ? kthread_create_on_node+0x40/0x40 <4>[ 1542.178506] ret_from_fork+0x27/0x40 v2: Fish out i915->mm.object_stat_lock which was being inited over in i915_drv.c (Matthew) Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Matthew Auld <matthew.auld@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171110232447.21618-1-chris@chris-wilson.co.uk Reviewed-by: Matthew Auld <matthew.auld@intel.com>
2017-11-10 23:24:47 +00:00
i915_gem_init__mm(i915);
init_waitqueue_head(&i915->gpu_error.wait_queue);
init_waitqueue_head(&i915->gpu_error.reset_queue);
i915->wq = alloc_ordered_workqueue("mock", 0);
if (!i915->wq)
goto err_drv;
mock_init_contexts(i915);
INIT_DELAYED_WORK(&i915->gt.retire_work, mock_retire_work_handler);
INIT_DELAYED_WORK(&i915->gt.idle_work, mock_idle_work_handler);
i915->gt.awake = true;
i915->objects = KMEM_CACHE(mock_object, SLAB_HWCACHE_ALIGN);
if (!i915->objects)
goto err_wq;
i915->vmas = KMEM_CACHE(i915_vma, SLAB_HWCACHE_ALIGN);
if (!i915->vmas)
goto err_objects;
i915->requests = KMEM_CACHE(mock_request,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT |
SLAB_TYPESAFE_BY_RCU);
if (!i915->requests)
goto err_vmas;
i915->dependencies = KMEM_CACHE(i915_dependency,
SLAB_HWCACHE_ALIGN |
SLAB_RECLAIM_ACCOUNT);
if (!i915->dependencies)
goto err_requests;
i915->priorities = KMEM_CACHE(i915_priolist, SLAB_HWCACHE_ALIGN);
if (!i915->priorities)
goto err_dependencies;
INIT_LIST_HEAD(&i915->gt.timelines);
INIT_LIST_HEAD(&i915->gt.active_rings);
drm/i915: Lazily unbind vma on close When userspace is passing around swapbuffers using DRI, we frequently have to open and close the same object in the foreign address space. This shows itself as the same object being rebound at roughly 30fps (with a second object also being rebound at 30fps), which involves us having to rewrite the page tables and maintain the drm_mm range manager every time. However, since the object still exists and it is only the local handle that disappears, if we are lazy and do not unbind the VMA immediately when the local user closes the object but defer it until the GPU is idle, then we can reuse the same VMA binding. We still have to be careful to mark the handle and lookup tables as closed to maintain the uABI, just allowing the underlying VMA to be resurrected if the user is able to access the same object from the same context again. If the object itself is destroyed (neither userspace keeping a handle to it), the VMA will be reaped immediately as usual. In the future, this will be even more useful as instantiating a new VMA for use on the GPU will become heavier. A nuisance indeed, so nip it in the bud. v2: s/__i915_vma_final_close/i915_vma_destroy/ etc. v3: Leave a hint as to why we deferred the unbind on close. Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20180503195115.22309-1-chris@chris-wilson.co.uk
2018-05-03 19:51:14 +00:00
INIT_LIST_HEAD(&i915->gt.closed_vma);
mutex_lock(&i915->drm.struct_mutex);
mock_init_ggtt(i915);
mkwrite_device_info(i915)->ring_mask = BIT(0);
i915->kernel_context = mock_context(i915, NULL);
if (!i915->kernel_context)
goto err_unlock;
i915->engine[RCS] = mock_engine(i915, "mock", RCS);
if (!i915->engine[RCS])
goto err_context;
mutex_unlock(&i915->drm.struct_mutex);
WARN_ON(i915_gemfs_init(i915));
return i915;
err_context:
i915_gem_contexts_fini(i915);
err_unlock:
mutex_unlock(&i915->drm.struct_mutex);
kmem_cache_destroy(i915->priorities);
err_dependencies:
kmem_cache_destroy(i915->dependencies);
err_requests:
kmem_cache_destroy(i915->requests);
err_vmas:
kmem_cache_destroy(i915->vmas);
err_objects:
kmem_cache_destroy(i915->objects);
err_wq:
destroy_workqueue(i915->wq);
err_drv:
drm_mode_config_cleanup(&i915->drm);
drm_dev_fini(&i915->drm);
put_device:
put_device(&pdev->dev);
err:
return NULL;
}