drm/i915: Improve user experience and driver robustness under SIGINT or similar

We have long standing customer complaints that pressing Ctrl-C (or to the
effect of) causes engine resets with otherwise well behaving programs.

Not only is logging engine resets during normal operation not desirable
since it creates support incidents, but more fundamentally we should avoid
going the engine reset path when we can since any engine reset introduces
a chance of harming an innocent context.

Reason for this undesirable behaviour is that the driver currently does
not distinguish between banned contexts and non-persistent contexts which
have been closed.

To fix this we add the distinction between the two reasons for revoking
contexts, which then allows the strict timeout only be applied to banned,
while innocent contexts (well behaving) can preempt cleanly and exit
without triggering the engine reset path.

Note that the added context exiting category applies both to closed non-
persistent context, and any exiting context when hangcheck has been
disabled by the user.

At the same time we rename the backend operation from 'ban' to 'revoke'
which more accurately describes the actual semantics. (There is no ban at
the backend level since banning is a concept driven by the scheduling
frontend. Backends are simply able to revoke a running context so that
is the more appropriate name chosen.)

Signed-off-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Andrzej Hajda <andrzej.hajda@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20220527072452.2225610-1-tvrtko.ursulin@linux.intel.com

1 files changed, 15 insertions, 8 deletions

diff --git a/drivers/gpu/drm/i915/gem/i915_gem_context.c b/drivers/gpu/drm/i915/gem/i915_gem_context.c
index a3bb73f5d53b..e116f82fc37c 100644
--- a/drivers/gpu/drm/i915/gem/i915_gem_context.c
+++ b/drivers/gpu/drm/i915/gem/i915_gem_context.c
@@ -1367,7 +1367,8 @@ static struct intel_engine_cs *active_engine(struct intel_context *ce)
 	return engine;
 }
 
-static void kill_engines(struct i915_gem_engines *engines, bool ban)
+static void
+kill_engines(struct i915_gem_engines *engines, bool exit, bool persistent)
 {
 	struct i915_gem_engines_iter it;
 	struct intel_context *ce;
@@ -1381,9 +1382,15 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
 	 */
 	for_each_gem_engine(ce, engines, it) {
 		struct intel_engine_cs *engine;
+		bool skip = false;
 
-		if (ban && intel_context_ban(ce, NULL))
-			continue;
+		if (exit)
+			skip = intel_context_set_exiting(ce);
+		else if (!persistent)
+			skip = intel_context_exit_nonpersistent(ce, NULL);
+
+		if (skip)
+			continue; /* Already marked. */
 
 		/*
 		 * Check the current active state of this context; if we
@@ -1395,7 +1402,7 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
 		engine = active_engine(ce);
 
 		/* First attempt to gracefully cancel the context */
-		if (engine && !__cancel_engine(engine) && ban)
+		if (engine && !__cancel_engine(engine) && (exit || !persistent))
 			/*
 			 * If we are unable to send a preemptive pulse to bump
 			 * the context from the GPU, we have to resort to a full
@@ -1407,8 +1414,6 @@ static void kill_engines(struct i915_gem_engines *engines, bool ban)
 
 static void kill_context(struct i915_gem_context *ctx)
 {
-	bool ban = (!i915_gem_context_is_persistent(ctx) ||
-		    !ctx->i915->params.enable_hangcheck);
 	struct i915_gem_engines *pos, *next;
 
 	spin_lock_irq(&ctx->stale.lock);
@@ -1421,7 +1426,8 @@ static void kill_context(struct i915_gem_context *ctx)
 
 		spin_unlock_irq(&ctx->stale.lock);
 
-		kill_engines(pos, ban);
+		kill_engines(pos, !ctx->i915->params.enable_hangcheck,
+			     i915_gem_context_is_persistent(ctx));
 
 		spin_lock_irq(&ctx->stale.lock);
 		GEM_BUG_ON(i915_sw_fence_signaled(&pos->fence));
@@ -1467,7 +1473,8 @@ static void engines_idle_release(struct i915_gem_context *ctx,
 
 kill:
 	if (list_empty(&engines->link)) /* raced, already closed */
-		kill_engines(engines, true);
+		kill_engines(engines, true,
+			     i915_gem_context_is_persistent(ctx));
 
 	i915_sw_fence_commit(&engines->fence);
 }