[PATCH] drm/xe/guc: Add more GuC CT states
Riana Tauro
riana.tauro at intel.com
Wed Dec 27 06:52:07 UTC 2023
On 12/22/2023 11:22 AM, Matthew Brost wrote:
> On Fri, Dec 22, 2023 at 05:47:17AM +0000, Matthew Brost wrote:
>> On Thu, Dec 21, 2023 at 01:56:33PM -0800, Daniele Ceraolo Spurio wrote:
>>>
>>>
>>> On 12/19/2023 9:28 AM, Matthew Brost wrote:
>>>> The Guc CT has more than enabled / disables states rather it has 4. The
>>>> 4 states are not initialized, disabled, drop messages, and enabled.
>>>> Change the code to reflect this. These states will enable proper return
>>>> codes from functions and therefore enable proper error messages.
>>>
>>> Can you explain a bit more in which situation we expect to drop messages and
>>> handle it? AFAICS not all callers waiting for a G2H reply can cope with the
>>
>> Anything that requires a G2H reply must be able to cope with it getting
>> dropped as the GuC can hang at any moment. Certainly all of submission
>> is designed this way, so is TLB invalidations. More on that below. With
>> everything being able to cope with lost G2H their is not a point to
>> continue to process G2H once a reset has started (or send H2G either).
>>
>>> reply not coming; e.g. it looks like xe_gt_tlb_invalidation_wait() will
>>
>> During a GT reset xe_gt_tlb_invalidation_reset() is called which will
>> signal all waiters for invalidations avoiding timeouts.
>>
>> So the flow roughly is:
>>
>> Set CT channel to drop messages
>> Stop all submissions
>> Do reset
>> Signal TLB invalidation waiters.
>>
>
> Ah, forgot a key detail here. Setting CT channel to drop message before
> do the reset is key here - we don't want a G2H being processed to race
> with cleaning up lost G2H in there reset step.
>
> Matt
>
>>> timeout and throw an error (which IMO is already an issue, because the reply
>>> might be lost due to reset). I know that currently in all cases in which we
>>> stop communication we do a reset, so the situation ends up ok, but there is
>>> a pending series to remove the reset in the runtime suspend/resume scenario
>>> (https://patchwork.freedesktop.org/series/122772/) in which case IMO we
>>
>> This path we would want to put the GuC communication into a state where
>> if messages send / recv this triggers an error. (-ENODEV). We don't
>> expect to suspend the device and then send / recv messages. That is the
>> point of this patch - it is fine drop messages during a reset, not if
>> during suspend or if CT has not yet been initialized.
Hi Matthew
During D3hot->D0 , currently GuC is reloaded during resume. This pending
patch https://patchwork.freedesktop.org/series/122772/ only
suspends/resumes CTB communication instead of reload .
Which states should be used in this case?
Thanks
Riana
>>
>> Proper error messages will added based on these new states.
>>
>>> don't want to drop messages but do a flush instead.
>>>
>>
>> See above. Also unsure what you mean by flush here? Do you mean the G2H
>> worker? I think that creates some dma-fencing (or lockdep) nightmares if
>> we do that.
>>
>> Matt
>>
>>> Daniele
>>>
>>>>
>>>> Cc: Michal Wajdeczko <michal.wajdeczko at intel.com>
>>>> Cc: Tejas Upadhyay <tejas.upadhyay at intel.com>
>>>> Signed-off-by: Matthew Brost <matthew.brost at intel.com>
>>>> ---
>>>> drivers/gpu/drm/xe/xe_guc.c | 4 +-
>>>> drivers/gpu/drm/xe/xe_guc_ct.c | 55 ++++++++++++++++++++--------
>>>> drivers/gpu/drm/xe/xe_guc_ct.h | 8 +++-
>>>> drivers/gpu/drm/xe/xe_guc_ct_types.h | 18 ++++++++-
>>>> 4 files changed, 64 insertions(+), 21 deletions(-)
>>>>
>>>> diff --git a/drivers/gpu/drm/xe/xe_guc.c b/drivers/gpu/drm/xe/xe_guc.c
>>>> index 482cb0df9f15..9b0fa8b1eb48 100644
>>>> --- a/drivers/gpu/drm/xe/xe_guc.c
>>>> +++ b/drivers/gpu/drm/xe/xe_guc.c
>>>> @@ -645,7 +645,7 @@ int xe_guc_mmio_send_recv(struct xe_guc *guc, const u32 *request,
>>>> BUILD_BUG_ON(VF_SW_FLAG_COUNT != MED_VF_SW_FLAG_COUNT);
>>>> - xe_assert(xe, !guc->ct.enabled);
>>>> + xe_assert(xe, !xe_guc_ct_enabled(&guc->ct));
>>>> xe_assert(xe, len);
>>>> xe_assert(xe, len <= VF_SW_FLAG_COUNT);
>>>> xe_assert(xe, len <= MED_VF_SW_FLAG_COUNT);
>>>> @@ -827,7 +827,7 @@ int xe_guc_stop(struct xe_guc *guc)
>>>> {
>>>> int ret;
>>>> - xe_guc_ct_disable(&guc->ct);
>>>> + xe_guc_ct_drop_messages(&guc->ct);
>>>> ret = xe_guc_submit_stop(guc);
>>>> if (ret)
>>>> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.c b/drivers/gpu/drm/xe/xe_guc_ct.c
>>>> index 24a33fa36496..22d655a8bf9a 100644
>>>> --- a/drivers/gpu/drm/xe/xe_guc_ct.c
>>>> +++ b/drivers/gpu/drm/xe/xe_guc_ct.c
>>>> @@ -278,12 +278,25 @@ static int guc_ct_control_toggle(struct xe_guc_ct *ct, bool enable)
>>>> return ret > 0 ? -EPROTO : ret;
>>>> }
>>>> +static void xe_guc_ct_set_state(struct xe_guc_ct *ct,
>>>> + enum xe_guc_ct_state state)
>>>> +{
>>>> + mutex_lock(&ct->lock); /* Serialise dequeue_one_g2h() */
>>>> + spin_lock_irq(&ct->fast_lock); /* Serialise CT fast-path */
>>>> +
>>>> + ct->g2h_outstanding = 0;
>>>> + ct->state = state;
>>>> +
>>>> + spin_unlock_irq(&ct->fast_lock);
>>>> + mutex_unlock(&ct->lock);
>>>> +}
>>>> +
>>>> int xe_guc_ct_enable(struct xe_guc_ct *ct)
>>>> {
>>>> struct xe_device *xe = ct_to_xe(ct);
>>>> int err;
>>>> - xe_assert(xe, !ct->enabled);
>>>> + xe_assert(xe, !xe_guc_ct_enabled(ct));
>>>> guc_ct_ctb_h2g_init(xe, &ct->ctbs.h2g, &ct->bo->vmap);
>>>> guc_ct_ctb_g2h_init(xe, &ct->ctbs.g2h, &ct->bo->vmap);
>>>> @@ -300,12 +313,7 @@ int xe_guc_ct_enable(struct xe_guc_ct *ct)
>>>> if (err)
>>>> goto err_out;
>>>> - mutex_lock(&ct->lock);
>>>> - spin_lock_irq(&ct->fast_lock);
>>>> - ct->g2h_outstanding = 0;
>>>> - ct->enabled = true;
>>>> - spin_unlock_irq(&ct->fast_lock);
>>>> - mutex_unlock(&ct->lock);
>>>> + xe_guc_ct_set_state(ct, XE_GUC_CT_STATE_ENABLED);
>>>> smp_mb();
>>>> wake_up_all(&ct->wq);
>>>> @@ -321,12 +329,12 @@ int xe_guc_ct_enable(struct xe_guc_ct *ct)
>>>> void xe_guc_ct_disable(struct xe_guc_ct *ct)
>>>> {
>>>> - mutex_lock(&ct->lock); /* Serialise dequeue_one_g2h() */
>>>> - spin_lock_irq(&ct->fast_lock); /* Serialise CT fast-path */
>>>> - ct->enabled = false; /* Finally disable CT communication */
>>>> - spin_unlock_irq(&ct->fast_lock);
>>>> - mutex_unlock(&ct->lock);
>>>> + xe_guc_ct_set_state(ct, XE_GUC_CT_STATE_DISABLED);
>>>> +}
>>>> +void xe_guc_ct_drop_messages(struct xe_guc_ct *ct)
>>>> +{
>>>> + xe_guc_ct_set_state(ct, XE_GUC_CT_STATE_DROP_MESSAGES);
>>>> xa_destroy(&ct->fence_lookup);
>>>> }
>>>> @@ -493,11 +501,19 @@ static int __guc_ct_send_locked(struct xe_guc_ct *ct, const u32 *action,
>>>> goto out;
>>>> }
>>>> - if (unlikely(!ct->enabled)) {
>>>> + if (ct->state == XE_GUC_CT_STATE_NOT_INITIALIZED ||
>>>> + ct->state == XE_GUC_CT_STATE_DISABLED) {
>>>> ret = -ENODEV;
>>>> goto out;
>>>> }
>>>> + if (ct->state == XE_GUC_CT_STATE_DROP_MESSAGES) {
>>>> + ret = -ECANCELED;
>>>> + goto out;
>>>> + }
>>>> +
>>>> + xe_assert(xe, xe_guc_ct_enabled(ct));
>>>> +
>>>> if (g2h_fence) {
>>>> g2h_len = GUC_CTB_HXG_MSG_MAX_LEN;
>>>> num_g2h = 1;
>>>> @@ -682,7 +698,8 @@ static bool retry_failure(struct xe_guc_ct *ct, int ret)
>>>> return false;
>>>> #define ct_alive(ct) \
>>>> - (ct->enabled && !ct->ctbs.h2g.info.broken && !ct->ctbs.g2h.info.broken)
>>>> + (xe_guc_ct_enabled(ct) && !ct->ctbs.h2g.info.broken && \
>>>> + !ct->ctbs.g2h.info.broken)
>>>> if (!wait_event_interruptible_timeout(ct->wq, ct_alive(ct), HZ * 5))
>>>> return false;
>>>> #undef ct_alive
>>>> @@ -941,12 +958,18 @@ static int g2h_read(struct xe_guc_ct *ct, u32 *msg, bool fast_path)
>>>> lockdep_assert_held(&ct->fast_lock);
>>>> - if (!ct->enabled)
>>>> + if (ct->state == XE_GUC_CT_STATE_NOT_INITIALIZED ||
>>>> + ct->state == XE_GUC_CT_STATE_DISABLED)
>>>> return -ENODEV;
>>>> + if (ct->state == XE_GUC_CT_STATE_DROP_MESSAGES)
>>>> + return -ECANCELED;
>>>> +
>>>> if (g2h->info.broken)
>>>> return -EPIPE;
>>>> + xe_assert(xe, xe_guc_ct_enabled(ct));
>>>> +
>>>> /* Calculate DW available to read */
>>>> tail = desc_read(xe, g2h, tail);
>>>> avail = tail - g2h->info.head;
>>>> @@ -1245,7 +1268,7 @@ struct xe_guc_ct_snapshot *xe_guc_ct_snapshot_capture(struct xe_guc_ct *ct,
>>>> return NULL;
>>>> }
>>>> - if (ct->enabled) {
>>>> + if (xe_guc_ct_enabled(ct)) {
>>>> snapshot->ct_enabled = true;
>>>> snapshot->g2h_outstanding = READ_ONCE(ct->g2h_outstanding);
>>>> guc_ctb_snapshot_capture(xe, &ct->ctbs.h2g,
>>>> diff --git a/drivers/gpu/drm/xe/xe_guc_ct.h b/drivers/gpu/drm/xe/xe_guc_ct.h
>>>> index f15f8a4857e0..214a6a357519 100644
>>>> --- a/drivers/gpu/drm/xe/xe_guc_ct.h
>>>> +++ b/drivers/gpu/drm/xe/xe_guc_ct.h
>>>> @@ -13,6 +13,7 @@ struct drm_printer;
>>>> int xe_guc_ct_init(struct xe_guc_ct *ct);
>>>> int xe_guc_ct_enable(struct xe_guc_ct *ct);
>>>> void xe_guc_ct_disable(struct xe_guc_ct *ct);
>>>> +void xe_guc_ct_drop_messages(struct xe_guc_ct *ct);
>>>> void xe_guc_ct_fast_path(struct xe_guc_ct *ct);
>>>> struct xe_guc_ct_snapshot *
>>>> @@ -22,10 +23,15 @@ void xe_guc_ct_snapshot_print(struct xe_guc_ct_snapshot *snapshot,
>>>> void xe_guc_ct_snapshot_free(struct xe_guc_ct_snapshot *snapshot);
>>>> void xe_guc_ct_print(struct xe_guc_ct *ct, struct drm_printer *p, bool atomic);
>>>> +static inline bool xe_guc_ct_enabled(struct xe_guc_ct *ct)
>>>> +{
>>>> + return ct->state == XE_GUC_CT_STATE_ENABLED;
>>>> +}
>>>> +
>>>> static inline void xe_guc_ct_irq_handler(struct xe_guc_ct *ct)
>>>> {
>>>> wake_up_all(&ct->wq);
>>>> - if (ct->enabled)
>>>> + if (xe_guc_ct_enabled(ct))
>>>> queue_work(system_unbound_wq, &ct->g2h_worker);
>>>> xe_guc_ct_fast_path(ct);
>>>> }
>>>> diff --git a/drivers/gpu/drm/xe/xe_guc_ct_types.h b/drivers/gpu/drm/xe/xe_guc_ct_types.h
>>>> index d814d4ee3fc6..e36c7029dffe 100644
>>>> --- a/drivers/gpu/drm/xe/xe_guc_ct_types.h
>>>> +++ b/drivers/gpu/drm/xe/xe_guc_ct_types.h
>>>> @@ -72,6 +72,20 @@ struct xe_guc_ct_snapshot {
>>>> struct guc_ctb_snapshot h2g;
>>>> };
>>>> +/**
>>>> + * enum xe_guc_ct_state - CT state
>>>> + * @XE_GUC_CT_STATE_NOT_INITIALIZED: CT suspended, messages not expected in this state
>>>> + * @XE_GUC_CT_STATE_DISABLED: CT disabled, messages not expected in this state
>>>> + * @XE_GUC_CT_STATE_DROP_MESSAGES: CT drops messages without errors
>>>> + * @XE_GUC_CT_STATE_ENABLED: CT enabled, messages sent / recieved in this state
>>>> + */
>>>> +enum xe_guc_ct_state {
>>>> + XE_GUC_CT_STATE_NOT_INITIALIZED = 0,
>>>> + XE_GUC_CT_STATE_DISABLED,
>>>> + XE_GUC_CT_STATE_DROP_MESSAGES,
>>>> + XE_GUC_CT_STATE_ENABLED,
>>>> +};
>>>> +
>>>> /**
>>>> * struct xe_guc_ct - GuC command transport (CT) layer
>>>> *
>>>> @@ -96,8 +110,8 @@ struct xe_guc_ct {
>>>> u32 g2h_outstanding;
>>>> /** @g2h_worker: worker to process G2H messages */
>>>> struct work_struct g2h_worker;
>>>> - /** @enabled: CT enabled */
>>>> - bool enabled;
>>>> + /** @state: CT state */
>>>> + enum xe_guc_ct_state state;;
>>>> /** @fence_seqno: G2H fence seqno - 16 bits used by CT */
>>>> u32 fence_seqno;
>>>> /** @fence_lookup: G2H fence lookup */
>>>
More information about the Intel-xe
mailing list