#include "intel_reset.h"
#include "uc/intel_guc.h"
-#include "uc/intel_guc_submission.h"
#define RESET_MAX_RETRIES 3
intel_uncore_rmw_fw(uncore, reg, clr, 0);
}
-static void skip_context(struct i915_request *rq)
-{
- struct intel_context *hung_ctx = rq->context;
-
- list_for_each_entry_from_rcu(rq, &hung_ctx->timeline->requests, link) {
- if (!i915_request_is_active(rq))
- return;
-
- if (rq->context == hung_ctx) {
- i915_request_set_error_once(rq, -EIO);
- __i915_request_skip(rq);
- }
- }
-}
-
static void client_mark_guilty(struct i915_gem_context *ctx, bool banned)
{
struct drm_i915_file_private *file_priv = ctx->file_priv;
bool banned;
int i;
- if (intel_context_is_closed(rq->context)) {
- intel_context_set_banned(rq->context);
+ if (intel_context_is_closed(rq->context))
return true;
- }
rcu_read_lock();
ctx = rcu_dereference(rq->context->gem_context);
banned = !i915_gem_context_is_recoverable(ctx);
if (time_before(jiffies, prev_hang + CONTEXT_FAST_HANG_JIFFIES))
banned = true;
- if (banned) {
+ if (banned)
drm_dbg(&ctx->i915->drm, "context %s: guilty %d, banned\n",
ctx->name, atomic_read(&ctx->guilty_count));
- intel_context_set_banned(rq->context);
- }
client_mark_guilty(ctx, banned);
void __i915_request_reset(struct i915_request *rq, bool guilty)
{
+ bool banned = false;
+
RQ_TRACE(rq, "guilty? %s\n", yesno(guilty));
GEM_BUG_ON(__i915_request_is_complete(rq));
if (guilty) {
i915_request_set_error_once(rq, -EIO);
__i915_request_skip(rq);
- if (mark_guilty(rq) && !intel_engine_uses_guc(rq->engine))
- skip_context(rq);
+ banned = mark_guilty(rq);
} else {
i915_request_set_error_once(rq, -EAGAIN);
mark_innocent(rq);
}
rcu_read_unlock();
+
+ if (banned)
+ intel_context_ban(rq->context, rq);
}
static bool i915_in_reset(struct pci_dev *pdev)
#define SCHED_STATE_WAIT_FOR_DEREGISTER_TO_REGISTER BIT(0)
#define SCHED_STATE_DESTROYED BIT(1)
#define SCHED_STATE_PENDING_DISABLE BIT(2)
+#define SCHED_STATE_BANNED BIT(3)
static inline void init_sched_state(struct intel_context *ce)
{
/* Only should be called from guc_lrc_desc_pin() */
ce->guc_state.sched_state &= ~SCHED_STATE_PENDING_DISABLE;
}
+static inline bool context_banned(struct intel_context *ce)
+{
+ return ce->guc_state.sched_state & SCHED_STATE_BANNED;
+}
+
+static inline void set_context_banned(struct intel_context *ce)
+{
+ lockdep_assert_held(&ce->guc_state.lock);
+ ce->guc_state.sched_state |= SCHED_STATE_BANNED;
+}
+
+static inline void clr_context_banned(struct intel_context *ce)
+{
+ lockdep_assert_held(&ce->guc_state.lock);
+ ce->guc_state.sched_state &= ~SCHED_STATE_BANNED;
+}
+
static inline bool context_guc_id_invalid(struct intel_context *ce)
{
return ce->guc_id == GUC_INVALID_LRC_ID;
static int guc_add_request(struct intel_guc *guc, struct i915_request *rq)
{
- int err;
+ int err = 0;
struct intel_context *ce = rq->context;
u32 action[3];
int len = 0;
u32 g2h_len_dw = 0;
bool enabled;
+ /*
+ * Corner case where requests were sitting in the priority list or a
+ * request resubmitted after the context was banned.
+ */
+ if (unlikely(intel_context_is_banned(ce))) {
+ i915_request_put(i915_request_mark_eio(rq));
+ intel_engine_signal_breadcrumbs(ce->engine);
+ goto out;
+ }
+
GEM_BUG_ON(!atomic_read(&ce->guc_id_ref));
GEM_BUG_ON(context_guc_id_invalid(ce));
clr_context_pending_enable(ce);
intel_context_put(ce);
}
+ if (likely(!err))
+ trace_i915_request_guc_submit(rq);
out:
return err;
guc->stalled_request = last;
return false;
}
- trace_i915_request_guc_submit(last);
}
guc->stalled_request = NULL;
static void __guc_context_destroy(struct intel_context *ce);
static void release_guc_id(struct intel_guc *guc, struct intel_context *ce);
static void guc_signal_context_fence(struct intel_context *ce);
+static void guc_cancel_context_requests(struct intel_context *ce);
static void scrub_guc_desc_for_outstanding_g2h(struct intel_guc *guc)
{
struct intel_context *ce;
unsigned long index, flags;
- bool pending_disable, pending_enable, deregister, destroyed;
+ bool pending_disable, pending_enable, deregister, destroyed, banned;
xa_for_each(&guc->context_lookup, index, ce) {
/* Flush context */
pending_enable = context_pending_enable(ce);
pending_disable = context_pending_disable(ce);
deregister = context_wait_for_deregister_to_register(ce);
+ banned = context_banned(ce);
init_sched_state(ce);
if (pending_enable || destroyed || deregister) {
/* Not mutualy exclusive with above if statement. */
if (pending_disable) {
guc_signal_context_fence(ce);
+ if (banned) {
+ guc_cancel_context_requests(ce);
+ intel_engine_signal_breadcrumbs(ce->engine);
+ }
intel_context_sched_disable_unpin(ce);
atomic_dec(&guc->outstanding_submission_g2h);
intel_context_put(ce);
{
struct intel_engine_cs *engine = __context_to_physical_engine(ce);
+ if (intel_context_is_banned(ce))
+ return;
+
GEM_BUG_ON(!intel_context_is_pinned(ce));
/*
struct i915_request *rq;
u32 head;
+ intel_context_get(ce);
+
/*
* GuC will implicitly mark the context as non-schedulable
* when it sends the reset notification. Make sure our state
out_replay:
guc_reset_state(ce, head, stalled);
__unwind_incomplete_requests(ce);
+ intel_context_put(ce);
}
void intel_guc_submission_reset(struct intel_guc *guc, bool stalled)
ret = guc_add_request(guc, rq);
if (ret == -EBUSY)
guc->stalled_request = rq;
- else
- trace_i915_request_guc_submit(rq);
if (unlikely(ret == -EPIPE))
disable_submission(guc);
return ce->guc_id;
}
+static void __guc_context_set_preemption_timeout(struct intel_guc *guc,
+ u16 guc_id,
+ u32 preemption_timeout)
+{
+ u32 action[] = {
+ INTEL_GUC_ACTION_SET_CONTEXT_PREEMPTION_TIMEOUT,
+ guc_id,
+ preemption_timeout
+ };
+
+ intel_guc_send_busy_loop(guc, action, ARRAY_SIZE(action), 0, true);
+}
+
+static void guc_context_ban(struct intel_context *ce, struct i915_request *rq)
+{
+ struct intel_guc *guc = ce_to_guc(ce);
+ struct intel_runtime_pm *runtime_pm =
+ &ce->engine->gt->i915->runtime_pm;
+ intel_wakeref_t wakeref;
+ unsigned long flags;
+
+ guc_flush_submissions(guc);
+
+ spin_lock_irqsave(&ce->guc_state.lock, flags);
+ set_context_banned(ce);
+
+ if (submission_disabled(guc) ||
+ (!context_enabled(ce) && !context_pending_disable(ce))) {
+ spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+ guc_cancel_context_requests(ce);
+ intel_engine_signal_breadcrumbs(ce->engine);
+ } else if (!context_pending_disable(ce)) {
+ u16 guc_id;
+
+ /*
+ * We add +2 here as the schedule disable complete CTB handler
+ * calls intel_context_sched_disable_unpin (-2 to pin_count).
+ */
+ atomic_add(2, &ce->pin_count);
+
+ guc_id = prep_context_pending_disable(ce);
+ spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+ /*
+ * In addition to disabling scheduling, set the preemption
+ * timeout to the minimum value (1 us) so the banned context
+ * gets kicked off the HW ASAP.
+ */
+ with_intel_runtime_pm(runtime_pm, wakeref) {
+ __guc_context_set_preemption_timeout(guc, guc_id, 1);
+ __guc_context_sched_disable(guc, ce, guc_id);
+ }
+ } else {
+ if (!context_guc_id_invalid(ce))
+ with_intel_runtime_pm(runtime_pm, wakeref)
+ __guc_context_set_preemption_timeout(guc,
+ ce->guc_id,
+ 1);
+ spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+ }
+}
+
static void guc_context_sched_disable(struct intel_context *ce)
{
struct intel_guc *guc = ce_to_guc(ce);
- struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
unsigned long flags;
- u16 guc_id;
+ struct intel_runtime_pm *runtime_pm = &ce->engine->gt->i915->runtime_pm;
intel_wakeref_t wakeref;
+ u16 guc_id;
+ bool enabled;
if (submission_disabled(guc) || context_guc_id_invalid(ce) ||
!lrc_desc_registered(guc, ce->guc_id)) {
spin_lock_irqsave(&ce->guc_state.lock, flags);
/*
- * We have to check if the context has been pinned again as another pin
- * operation is allowed to pass this function. Checking the pin count,
- * within ce->guc_state.lock, synchronizes this function with
+ * We have to check if the context has been disabled by another thread.
+ * We also have to check if the context has been pinned again as another
+ * pin operation is allowed to pass this function. Checking the pin
+ * count, within ce->guc_state.lock, synchronizes this function with
* guc_request_alloc ensuring a request doesn't slip through the
* 'context_pending_disable' fence. Checking within the spin lock (can't
* sleep) ensures another process doesn't pin this context and generate
* a request before we set the 'context_pending_disable' flag here.
*/
+ enabled = context_enabled(ce);
+ if (unlikely(!enabled || submission_disabled(guc))) {
+ if (enabled)
+ clr_context_enabled(ce);
+ spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+ goto unpin;
+ }
if (unlikely(atomic_add_unless(&ce->pin_count, -2, 2))) {
spin_unlock_irqrestore(&ce->guc_state.lock, flags);
return;
.unpin = guc_context_unpin,
.post_unpin = guc_context_post_unpin,
+ .ban = guc_context_ban,
+
.enter = intel_context_enter_engine,
.exit = intel_context_exit_engine,
.unpin = guc_context_unpin,
.post_unpin = guc_context_post_unpin,
+ .ban = guc_context_ban,
+
.enter = guc_virtual_context_enter,
.exit = guc_virtual_context_exit,
if (context_pending_enable(ce)) {
clr_context_pending_enable(ce);
} else if (context_pending_disable(ce)) {
+ bool banned;
+
/*
* Unpin must be done before __guc_signal_context_fence,
* otherwise a race exists between the requests getting
intel_context_sched_disable_unpin(ce);
spin_lock_irqsave(&ce->guc_state.lock, flags);
+ banned = context_banned(ce);
+ clr_context_banned(ce);
clr_context_pending_disable(ce);
__guc_signal_context_fence(ce);
spin_unlock_irqrestore(&ce->guc_state.lock, flags);
+
+ if (banned) {
+ guc_cancel_context_requests(ce);
+ intel_engine_signal_breadcrumbs(ce->engine);
+ }
}
decr_outstanding_submission_g2h(guc);
struct intel_context *ce)
{
trace_intel_context_reset(ce);
- capture_error_state(guc, ce);
- guc_context_replay(ce);
+
+ if (likely(!intel_context_is_banned(ce))) {
+ capture_error_state(guc, ce);
+ guc_context_replay(ce);
+ }
}
int intel_guc_context_reset_process_msg(struct intel_guc *guc,
projects / kernel.git / commitdiff