@@ -1321,7 +1321,7 @@ static u64 execlists_update_context(struct i915_request *rq)
{
struct intel_context *ce = rq->context;
u64 desc = ce->lrc_desc;
- u32 tail;
+ u32 tail, prev;
/*
* WaIdleLiteRestore:bdw,skl
@@ -1334,9 +1334,15 @@ static u64 execlists_update_context(struct i915_request *rq)
* subsequent resubmissions (for lite restore). Should that fail us,
* and we try and submit the same tail again, force the context
* reload.
+ *
+ * If we need to return to a preempted context, we need to skip the
+ * lite-restore and force it to reload the RING_TAIL. Otherwise, the
+ * HW has a tendency to ignore us rewinding the TAIL to the end of
+ * an earlier request.
*/
tail = intel_ring_set_tail(rq->ring, rq->tail);
- if (unlikely(ce->lrc_reg_state[CTX_RING_TAIL] == tail))
+ prev = ce->lrc_reg_state[CTX_RING_TAIL];
+ if (unlikely(intel_ring_direction(rq->ring, tail, prev) <= 0))
desc |= CTX_DESC_FORCE_RESTORE;
ce->lrc_reg_state[CTX_RING_TAIL] = tail;
rq->tail = rq->wa_tail;
@@ -1854,14 +1860,6 @@ static void execlists_dequeue(struct intel_engine_cs *engine)
*/
__unwind_incomplete_requests(engine);
- /*
- * If we need to return to the preempted context, we
- * need to skip the lite-restore and force it to
- * reload the RING_TAIL. Otherwise, the HW has a
- * tendency to ignore us rewinding the TAIL to the
- * end of an earlier request.
- */
- last->context->lrc_desc |= CTX_DESC_FORCE_RESTORE;
last = NULL;
} else if (need_timeslice(engine, last) &&
timer_expired(&engine->execlists.timer)) {
@@ -143,6 +143,7 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
kref_init(&ring->ref);
ring->size = size;
+ ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
/*
* Workaround an erratum on the i830 which causes a hang if
@@ -56,6 +56,14 @@ static inline u32 intel_ring_wrap(const struct intel_ring *ring, u32 pos)
return pos & (ring->size - 1);
}
+static inline int intel_ring_direction(const struct intel_ring *ring,
+ u32 next, u32 prev)
+{
+ typecheck(typeof(ring->size), next);
+ typecheck(typeof(ring->size), prev);
+ return (next - prev) << ring->wrap;
+}
+
static inline bool
intel_ring_offset_valid(const struct intel_ring *ring,
unsigned int pos)
@@ -45,6 +45,7 @@ struct intel_ring {
u32 space;
u32 size;
+ u32 wrap;
u32 effective_size;
};
If we rewind the RING_TAIL on a context, due to a preemption event, we must force the context restore for the RING_TAIL update to be properly handled. Rather than note which preemption events may cause us to rewind the tail, compare the new request's tail with the previously submitted RING_TAIL, as it turns out that timeslicing was causing unexpected rewinds. <idle>-0 0d.s2 1280851190us : __execlists_submission_tasklet: 0000:00:02.0 rcs0: expired last=130:4698, prio=3, hint=3 <idle>-0 0d.s2 1280851192us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 66:119966, current 119964 <idle>-0 0d.s2 1280851195us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4698, current 4695 ^---- Note we unwind 2 requests from the same context <idle>-0 0d.s2 1280851198us : __i915_request_unsubmit: 0000:00:02.0 rcs0: fence 130:4696, current 4695 <idle>-0 0d.s2 1280851208us : __i915_request_submit: 0000:00:02.0 rcs0: fence 130:4696, current 4695 <idle>-0 0d.s2 1280851213us : __i915_request_submit: 0000:00:02.0 rcs0: fence 134:1508, current 1506 ^---- But to apply the new timeslice, we have to replay the first request before he new client can start <idle>-0 0d.s2 1280851219us : trace_ports: 0000:00:02.0 rcs0: submit { 130:4696*, 134:1508 } synmark2-5425 2..s. 1280851239us : process_csb: 0000:00:02.0 rcs0: cs-irq head=5, tail=0 synmark2-5425 2..s. 1280851240us : process_csb: 0000:00:02.0 rcs0: csb[0]: status=0x00008002:0x00000000 ^---- Preemption event for the ELSP update; note the lite-restore synmark2-5425 2..s. 1280851243us : trace_ports: 0000:00:02.0 rcs0: preempted { 130:4698, 66:119966 } synmark2-5425 2..s. 1280851246us : trace_ports: 0000:00:02.0 rcs0: promote { 130:4696*, 134:1508 } synmark2-5425 2.... 1280851462us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4700, current 4695 synmark2-5425 2.... 1280852111us : __i915_request_commit: 0000:00:02.0 rcs0: fence 130:4702, current 4695 synmark2-5425 2.Ns1 1280852296us : process_csb: 0000:00:02.0 rcs0: cs-irq head=0, tail=2 synmark2-5425 2.Ns1 1280852297us : process_csb: 0000:00:02.0 rcs0: csb[1]: status=0x00000814:0x00000000 synmark2-5425 2.Ns1 1280852299us : trace_ports: 0000:00:02.0 rcs0: completed { 130:4696!, 134:1508 } synmark2-5425 2.Ns1 1280852301us : process_csb: 0000:00:02.0 rcs0: csb[2]: status=0x00000818:0x00000040 synmark2-5425 2.Ns1 1280852302us : trace_ports: 0000:00:02.0 rcs0: completed { 134:1508, 0:0 } synmark2-5425 2.Ns1 1280852313us : process_csb: process_csb:2336 GEM_BUG_ON(!i915_request_completed(*execlists->active) && !reset_in_progress(execlists)) Fixes: 8ee36e048c98 ("drm/i915/execlists: Minimalistic timeslicing") Referenecs: 82c69bf58650 ("drm/i915/gt: Detect if we miss WaIdleLiteRestore") Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Cc: Mika Kuoppala <mika.kuoppala@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Cc: <stable@vger.kernel.org> # v5.4+ --- drivers/gpu/drm/i915/gt/intel_lrc.c | 18 ++++++++---------- drivers/gpu/drm/i915/gt/intel_ring.c | 1 + drivers/gpu/drm/i915/gt/intel_ring.h | 8 ++++++++ drivers/gpu/drm/i915/gt/intel_ring_types.h | 1 + 4 files changed, 18 insertions(+), 10 deletions(-)