Hi Felix & Harish,
maybe explain why I found that odd: dma_fence_add_callback() sets the
DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT flag before adding the callback.
So the flag should always be set when there are callbacks.
Did I miss anything?
Regards,
Christian.
Am 29.01.2018 um 00:55 schrieb Felix Kuehling:
> [+Harish, forgot to acknowledge him in the commit description, will fix
> that in v2]
>
> Harish, please see Christian's question below in amd_kfd_fence_signal.
> Did I understand this correctly?
>
> Regards,
> Â Felix
>
> On 2018-01-28 06:42 PM, Felix Kuehling wrote:
>> On 2018-01-27 04:16 AM, Christian König wrote:
>>> Am 27.01.2018 um 02:09 schrieb Felix Kuehling:
>> [snip]
>>>> +struct amdgpu_amdkfd_fence *amdgpu_amdkfd_fence_create(u64 context,
>>>> +Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â void *mm)
>>>> +{
>>>> +Â Â Â struct amdgpu_amdkfd_fence *fence = NULL;
>>>> +
>>>> +Â Â Â fence = kzalloc(sizeof(*fence), GFP_KERNEL);
>>>> +Â Â Â if (fence == NULL)
>>>> +Â Â Â Â Â Â Â return NULL;
>>>> +
>>>> +Â Â Â /* mm_struct mm is used as void pointer to identify the parent
>>>> +Â Â Â Â * KFD process. Don't dereference it. Fence and any threads using
>>>> +Â Â Â Â * mm is guranteed to be released before process termination.
>>>> +Â Â Â Â */
>>>> +Â Â Â fence->mm = mm;
>>> That won't work. Fences can live much longer than any process who
>>> created them.
>>>
>>> I've already found a fence in a BO still living hours after the
>>> process was killed and the pid long recycled.
>>>
>>> I suggest to make fence->mm a real mm_struct pointer with reference
>>> counting and then set it to NULL and drop the reference in
>>> enable_signaling.
>> I agree. But enable_signaling may be too early to drop the reference.
>> amd_kfd_fence_check_mm could still be called later from
>> amdgpu_ttm_bo_eviction_valuable, as long as the fence hasn't signaled yet.
>>
>> The safe place is problably in amd_kfd_fence_release.
>>
>>>> +Â Â Â get_task_comm(fence->timeline_name, current);
>>>> +Â Â Â spin_lock_init(&fence->lock);
>>>> +
>>>> +Â Â Â dma_fence_init(&fence->base, &amd_kfd_fence_ops, &fence->lock,
>>>> +Â Â Â Â Â Â Â Â Â Â context, atomic_inc_return(&fence_seq));
>>>> +
>>>> +Â Â Â return fence;
>>>> +}
>>>> +
>>>> +struct amdgpu_amdkfd_fence *to_amdgpu_amdkfd_fence(struct dma_fence *f)
>>>> +{
>>>> +Â Â Â struct amdgpu_amdkfd_fence *fence;
>>>> +
>>>> +Â Â Â if (!f)
>>>> +Â Â Â Â Â Â Â return NULL;
>>>> +
>>>> +Â Â Â fence = container_of(f, struct amdgpu_amdkfd_fence, base);
>>>> +Â Â Â if (fence && f->ops == &amd_kfd_fence_ops)
>>>> +Â Â Â Â Â Â Â return fence;
>>>> +
>>>> +Â Â Â return NULL;
>>>> +}
>>>> +
>>>> +static const char *amd_kfd_fence_get_driver_name(struct dma_fence *f)
>>>> +{
>>>> +Â Â Â return "amdgpu_amdkfd_fence";
>>>> +}
>>>> +
>>>> +static const char *amd_kfd_fence_get_timeline_name(struct dma_fence *f)
>>>> +{
>>>> +Â Â Â struct amdgpu_amdkfd_fence *fence = to_amdgpu_amdkfd_fence(f);
>>>> +
>>>> +Â Â Â return fence->timeline_name;
>>>> +}
>>>> +
>>>> +/**
>>>> + * amd_kfd_fence_enable_signaling - This gets called when TTM wants
>>>> to evict
>>>> + *Â a KFD BO and schedules a job to move the BO.
>>>> + *Â If fence is already signaled return true.
>>>> + *Â If fence is not signaled schedule a evict KFD process work item.
>>>> + */
>>>> +static bool amd_kfd_fence_enable_signaling(struct dma_fence *f)
>>>> +{
>>>> +Â Â Â struct amdgpu_amdkfd_fence *fence = to_amdgpu_amdkfd_fence(f);
>>>> +
>>>> +Â Â Â if (!fence)
>>>> +Â Â Â Â Â Â Â return false;
>>>> +
>>>> +Â Â Â if (dma_fence_is_signaled(f))
>>>> +Â Â Â Â Â Â Â return true;
>>>> +
>>>> +Â Â Â if (!kgd2kfd->schedule_evict_and_restore_process(
>>>> +Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â (struct mm_struct *)fence->mm, f))
>>>> +Â Â Â Â Â Â Â return true;
>>>> +
>>>> +Â Â Â return false;
>>>> +}
>>>> +
>>>> +static int amd_kfd_fence_signal(struct dma_fence *f)
>>>> +{
>>>> +Â Â Â unsigned long flags;
>>>> +Â Â Â int ret;
>>>> +
>>>> +Â Â Â spin_lock_irqsave(f->lock, flags);
>>>> +Â Â Â /* Set enabled bit so cb will called */
>>>> +Â Â Â set_bit(DMA_FENCE_FLAG_ENABLE_SIGNAL_BIT, &f->flags);
>>> Mhm, why is that necessary?
>> This only gets called from fence_release below. I think this is to avoid
>> needlessly scheduling an eviction/restore cycle when an eviction fence
>> gets destroyed that hasn't been triggered before, probably during
>> process termination.
>>
>> Harish, do you remember any other reason for this?
>>
>>>> +Â Â Â ret = dma_fence_signal_locked(f);
>>>> +Â Â Â spin_unlock_irqrestore(f->lock, flags);
>>>> +
>>>> +Â Â Â return ret;
>>>> +}
>>>> +
>>>> +/**
>>>> + * amd_kfd_fence_release - callback that fence can be freed
>>>> + *
>>>> + * @fence: fence
>>>> + *
>>>> + * This function is called when the reference count becomes zero.
>>>> + * It just RCU schedules freeing up the fence.
>>>> + */
>>>> +static void amd_kfd_fence_release(struct dma_fence *f)
>>>> +{
>>>> +Â Â Â struct amdgpu_amdkfd_fence *fence = to_amdgpu_amdkfd_fence(f);
>>>> +Â Â Â /* Unconditionally signal the fence. The process is getting
>>>> +Â Â Â Â * terminated.
>>>> +Â Â Â Â */
>>>> +Â Â Â if (WARN_ON(!fence))
>>>> +Â Â Â Â Â Â Â return; /* Not an amdgpu_amdkfd_fence */
>>>> +
>>>> +Â Â Â amd_kfd_fence_signal(f);
>>>> +Â Â Â kfree_rcu(f, rcu);
>>>> +}
>>>> +
>>>> +/**
>>>> + * amd_kfd_fence_check_mm - Check if @mm is same as that of the
>>>> fence @f
>>>> + *Â if same return TRUE else return FALSE.
>>>> + *
>>>> + * @f: [IN] fence
>>>> + * @mm: [IN] mm that needs to be verified
>>>> + */
>>>> +bool amd_kfd_fence_check_mm(struct dma_fence *f, void *mm)
>>>> +{
>>>> +Â Â Â struct amdgpu_amdkfd_fence *fence = to_amdgpu_amdkfd_fence(f);
>>>> +
>>>> +Â Â Â if (!fence)
>>>> +Â Â Â Â Â Â Â return false;
>>>> +Â Â Â else if (fence->mm == mm)
>>>> +Â Â Â Â Â Â Â return true;
>>>> +
>>>> +Â Â Â return false;
>>>> +}
>>>> +
>>>> +const struct dma_fence_ops amd_kfd_fence_ops = {
>>>> +Â Â Â .get_driver_name = amd_kfd_fence_get_driver_name,
>>>> +Â Â Â .get_timeline_name = amd_kfd_fence_get_timeline_name,
>>>> +Â Â Â .enable_signaling = amd_kfd_fence_enable_signaling,
>>>> +Â Â Â .signaled = NULL,
>>>> +Â Â Â .wait = dma_fence_default_wait,
>>>> +Â Â Â .release = amd_kfd_fence_release,
>>>> +};
>>>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
>>>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
>>>> index 65d5a4e..ca00dd2 100644
>>>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
>>>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ring.h
>>>> @@ -36,8 +36,9 @@
>>>> Â #define AMDGPU_MAX_UVD_ENC_RINGSÂ Â Â 2
>>>> Â Â /* some special values for the owner field */
>>>> -#define AMDGPU_FENCE_OWNER_UNDEFINEDÂ Â Â ((void*)0ul)
>>>> -#define AMDGPU_FENCE_OWNER_VMÂ Â Â Â Â Â Â ((void*)1ul)
>>>> +#define AMDGPU_FENCE_OWNER_UNDEFINEDÂ Â Â ((void *)0ul)
>>>> +#define AMDGPU_FENCE_OWNER_VMÂ Â Â Â Â Â Â ((void *)1ul)
>>>> +#define AMDGPU_FENCE_OWNER_KFDÂ Â Â Â Â Â Â ((void *)2ul)
>>>> Â Â #define AMDGPU_FENCE_FLAG_64BITÂ Â Â Â Â Â Â Â (1 << 0)
>>>> Â #define AMDGPU_FENCE_FLAG_INTÂ Â Â Â Â Â Â Â Â Â (1 << 1)
>>>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
>>>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
>>>> index df65c66..0cb31d9 100644
>>>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
>>>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_sync.c
>>>> @@ -31,6 +31,7 @@
>>>> Â #include <drm/drmP.h>
>>>> Â #include "amdgpu.h"
>>>> Â #include "amdgpu_trace.h"
>>>> +#include "amdgpu_amdkfd.h"
>>>> Â Â struct amdgpu_sync_entry {
>>>>      struct hlist_node   node;
>>>> @@ -86,10 +87,18 @@ static bool amdgpu_sync_same_dev(struct
>>>> amdgpu_device *adev,
>>>> Â static void *amdgpu_sync_get_owner(struct dma_fence *f)
>>>> Â {
>>>> Â Â Â Â Â struct drm_sched_fence *s_fence = to_drm_sched_fence(f);
>>>> +Â Â Â struct amdgpu_amdkfd_fence *kfd_fence;
>>>> +
>>>> +Â Â Â if (!f)
>>>> +Â Â Â Â Â Â Â return AMDGPU_FENCE_OWNER_UNDEFINED;
>>> When you add the extra NULL check here then please move the
>>> to_drm_sched_fence() after it as well.
>> Yeah, makes sense.
>>
>> Regards,
>> Â Felix
>>
>>> Christian.
>>>
>>>> Â Â Â Â Â Â if (s_fence)
>>>> Â Â Â Â Â Â Â Â Â return s_fence->owner;
>>>> Â +Â Â Â kfd_fence = to_amdgpu_amdkfd_fence(f);
>>>> +Â Â Â if (kfd_fence)
>>>> +Â Â Â Â Â Â Â return AMDGPU_FENCE_OWNER_KFD;
>>>> +
>>>> Â Â Â Â Â return AMDGPU_FENCE_OWNER_UNDEFINED;
>>>> Â }
>>>> Â @@ -204,11 +213,18 @@ int amdgpu_sync_resv(struct amdgpu_device *adev,
>>>> Â Â Â Â Â for (i = 0; i < flist->shared_count; ++i) {
>>>> Â Â Â Â Â Â Â Â Â f = rcu_dereference_protected(flist->shared[i],
>>>> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â reservation_object_held(resv));
>>>> +Â Â Â Â Â Â Â /* We only want to trigger KFD eviction fences on
>>>> +Â Â Â Â Â Â Â Â * evict or move jobs. Skip KFD fences otherwise.
>>>> +Â Â Â Â Â Â Â Â */
>>>> +Â Â Â Â Â Â Â fence_owner = amdgpu_sync_get_owner(f);
>>>> +Â Â Â Â Â Â Â if (fence_owner == AMDGPU_FENCE_OWNER_KFD &&
>>>> +Â Â Â Â Â Â Â Â Â Â Â owner != AMDGPU_FENCE_OWNER_UNDEFINED)
>>>> +Â Â Â Â Â Â Â Â Â Â Â continue;
>>>> +
>>>> Â Â Â Â Â Â Â Â Â if (amdgpu_sync_same_dev(adev, f)) {
>>>> Â Â Â Â Â Â Â Â Â Â Â Â Â /* VM updates are only interesting
>>>> Â Â Â Â Â Â Â Â Â Â Â Â Â Â * for other VM updates and moves.
>>>> Â Â Â Â Â Â Â Â Â Â Â Â Â Â */
>>>> -Â Â Â Â Â Â Â Â Â Â Â fence_owner = amdgpu_sync_get_owner(f);
>>>> Â Â Â Â Â Â Â Â Â Â Â Â Â if ((owner != AMDGPU_FENCE_OWNER_UNDEFINED) &&
>>>> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â (fence_owner != AMDGPU_FENCE_OWNER_UNDEFINED) &&
>>>> Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â ((owner == AMDGPU_FENCE_OWNER_VM) !=
>>>> diff --git a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>>>> b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>>>> index e4bb435..c3f33d3 100644
>>>> --- a/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>>>> +++ b/drivers/gpu/drm/amd/amdgpu/amdgpu_ttm.c
>>>> @@ -46,6 +46,7 @@
>>>> Â #include "amdgpu.h"
>>>> Â #include "amdgpu_object.h"
>>>> Â #include "amdgpu_trace.h"
>>>> +#include "amdgpu_amdkfd.h"
>>>> Â #include "bif/bif_4_1_d.h"
>>>> Â Â #define DRM_FILE_PAGE_OFFSET (0x100000000ULL >> PAGE_SHIFT)
>>>> @@ -1170,6 +1171,23 @@ static bool
>>>> amdgpu_ttm_bo_eviction_valuable(struct ttm_buffer_object *bo,
>>>> Â {
>>>> Â Â Â Â Â unsigned long num_pages = bo->mem.num_pages;
>>>> Â Â Â Â Â struct drm_mm_node *node = bo->mem.mm_node;
>>>> +Â Â Â struct reservation_object_list *flist;
>>>> +Â Â Â struct dma_fence *f;
>>>> +Â Â Â int i;
>>>> +
>>>> +Â Â Â /* If bo is a KFD BO, check if the bo belongs to the current
>>>> process.
>>>> +Â Â Â Â * If true, then return false as any KFD process needs all its
>>>> BOs to
>>>> +Â Â Â Â * be resident to run successfully
>>>> +Â Â Â Â */
>>>> +Â Â Â flist = reservation_object_get_list(bo->resv);
>>>> +Â Â Â if (flist) {
>>>> +Â Â Â Â Â Â Â for (i = 0; i < flist->shared_count; ++i) {
>>>> +Â Â Â Â Â Â Â Â Â Â Â f = rcu_dereference_protected(flist->shared[i],
>>>> +Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â reservation_object_held(bo->resv));
>>>> +Â Â Â Â Â Â Â Â Â Â Â if (amd_kfd_fence_check_mm(f, current->mm))
>>>> +Â Â Â Â Â Â Â Â Â Â Â Â Â Â Â return false;
>>>> +Â Â Â Â Â Â Â }
>>>> +Â Â Â }
>>>> Â Â Â Â Â Â switch (bo->mem.mem_type) {
>>>> Â Â Â Â Â case TTM_PL_TT:
>>>> diff --git a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
>>>> b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
>>>> index 94eab54..9e35249 100644
>>>> --- a/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
>>>> +++ b/drivers/gpu/drm/amd/include/kgd_kfd_interface.h
>>>> @@ -30,6 +30,7 @@
>>>> Â Â #include <linux/types.h>
>>>> Â #include <linux/bitmap.h>
>>>> +#include <linux/dma-fence.h>
>>>> Â Â struct pci_dev;
>>>> Â @@ -286,6 +287,9 @@ struct kfd2kgd_calls {
>>>> Â Â *
>>>> Â Â * @resume: Notifies amdkfd about a resume action done to a kgd device
>>>> Â Â *
>>>> + * @schedule_evict_and_restore_process: Schedules work queue that
>>>> will prepare
>>>> + * for safe eviction of KFD BOs that belong to the specified process.
>>>> + *
>>>> Â Â * This structure contains function callback pointers so the kgd
>>>> driver
>>>> Â Â * will notify to the amdkfd about certain status changes.
>>>> Â Â *
>>>> @@ -300,6 +304,8 @@ struct kgd2kfd_calls {
>>>> Â Â Â Â Â void (*interrupt)(struct kfd_dev *kfd, const void *ih_ring_entry);
>>>> Â Â Â Â Â void (*suspend)(struct kfd_dev *kfd);
>>>> Â Â Â Â Â int (*resume)(struct kfd_dev *kfd);
>>>> +Â Â Â int (*schedule_evict_and_restore_process)(struct mm_struct *mm,
>>>> +Â Â Â Â Â Â Â Â Â Â Â struct dma_fence *fence);
>>>> Â };
>>>> Â Â int kgd2kfd_init(unsigned interface_version,
> _______________________________________________
> amd-gfx mailing list
> amd-gfx at lists.freedesktop.org
> https://lists.freedesktop.org/mailman/listinfo/amd-gfx
