drm/i915/execlists: Track inflight CCID

The presumption is that by using a circular counter that is twice as
large as the maximum ELSP submission, we would never reuse the same CCID
for two inflight contexts.

However, if we continually preempt an active context such that it always
remains inflight, it can be resubmitted with an arbitrary number of
paired contexts. As each of its paired contexts will use a new CCID,
eventually it will wrap and submit two ELSP with the same CCID.

Rather than use a simple circular counter, switch over to a small bitmap
of inflight ids so we can avoid reusing one that is still potentially
active.

Closes: https://gitlab.freedesktop.org/drm/intel/-/issues/1796
Fixes: 2935ed5339c4 ("drm/i915: Remove logical HW ID")
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Cc: <stable@vger.kernel.org> # v5.5+
Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20200428184751.11257-2-chris@chris-wilson.co.uk
(cherry picked from commit 5c4a53e3b1cbc38d0906e382f1037290658759bb)
(cherry picked from commit 134711240307d5586ae8e828d2699db70a8b74f2)
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>

1 files changed, 22 insertions, 7 deletions

diff --git a/drivers/gpu/drm/i915/gt/intel_lrc.c b/drivers/gpu/drm/i915/gt/intel_lrc.c
index e8b02f84aa3d..77420372d813 100644
--- a/drivers/gpu/drm/i915/gt/intel_lrc.c
+++ b/drivers/gpu/drm/i915/gt/intel_lrc.c
@@ -1239,13 +1239,17 @@ __execlists_schedule_in(struct i915_request *rq)
 
 	if (ce->tag) {
 		/* Use a fixed tag for OA and friends */
+		GEM_BUG_ON(ce->tag <= BITS_PER_LONG);
 		ce->lrc.ccid = ce->tag;
 	} else {
 		/* We don't need a strict matching tag, just different values */
-		ce->lrc.ccid =
-			(++engine->context_tag % NUM_CONTEXT_TAG) <<
-			(GEN11_SW_CTX_ID_SHIFT - 32);
-		BUILD_BUG_ON(NUM_CONTEXT_TAG > GEN12_MAX_CONTEXT_HW_ID);
+		unsigned int tag = ffs(engine->context_tag);
+
+		GEM_BUG_ON(tag == 0 || tag >= BITS_PER_LONG);
+		clear_bit(tag - 1, &engine->context_tag);
+		ce->lrc.ccid = tag << (GEN11_SW_CTX_ID_SHIFT - 32);
+
+		BUILD_BUG_ON(BITS_PER_LONG > GEN12_MAX_CONTEXT_HW_ID);
 	}
 
 	ce->lrc.ccid |= engine->execlists.ccid;
@@ -1289,7 +1293,8 @@ static void kick_siblings(struct i915_request *rq, struct intel_context *ce)
 
 static inline void
 __execlists_schedule_out(struct i915_request *rq,
-			 struct intel_engine_cs * const engine)
+			 struct intel_engine_cs * const engine,
+			 unsigned int ccid)
 {
 	struct intel_context * const ce = rq->context;
 
@@ -1307,6 +1312,14 @@ __execlists_schedule_out(struct i915_request *rq,
 	    i915_request_completed(rq))
 		intel_engine_add_retire(engine, ce->timeline);
 
+	ccid >>= GEN11_SW_CTX_ID_SHIFT - 32;
+	ccid &= GEN12_MAX_CONTEXT_HW_ID;
+	if (ccid < BITS_PER_LONG) {
+		GEM_BUG_ON(ccid == 0);
+		GEM_BUG_ON(test_bit(ccid - 1, &engine->context_tag));
+		set_bit(ccid - 1, &engine->context_tag);
+	}
+
 	intel_context_update_runtime(ce);
 	intel_engine_context_out(engine);
 	execlists_context_status_change(rq, INTEL_CONTEXT_SCHEDULE_OUT);
@@ -1332,15 +1345,17 @@ execlists_schedule_out(struct i915_request *rq)
 {
 	struct intel_context * const ce = rq->context;
 	struct intel_engine_cs *cur, *old;
+	u32 ccid;
 
 	trace_i915_request_out(rq);
 
+	ccid = rq->context->lrc.ccid;
 	old = READ_ONCE(ce->inflight);
 	do
 		cur = ptr_unmask_bits(old, 2) ? ptr_dec(old) : NULL;
 	while (!try_cmpxchg(&ce->inflight, &old, cur));
 	if (!cur)
-		__execlists_schedule_out(rq, old);
+		__execlists_schedule_out(rq, old, ccid);
 
 	i915_request_put(rq);
 }
@@ -3556,7 +3571,7 @@ static void enable_execlists(struct intel_engine_cs *engine)
 
 	enable_error_interrupt(engine);
 
-	engine->context_tag = 0;
+	engine->context_tag = GENMASK(BITS_PER_LONG - 2, 0);
 }
 
 static bool unexpected_starting_state(struct intel_engine_cs *engine)