Commit d8f50531 authored by Mika Kuoppala's avatar Mika Kuoppala

drm/i915/icl: Forcibly evict stale csb entries

Gen11 fails to deliver wrt global observation point on
tail/entry updates and we sometimes see old entry.

Use clflush to forcibly evict our possibly stale copy
of the cacheline in hopes that we get fresh one from gpu.
Obviously there is something amiss in the coherency protocol so
this can be consired as a workaround until real cause
is found.

The working hardware will do the evict without our cue anyways,
so the cost in there should be ameliorated by that fact.

v2: for next pass, s/flush/evict, add reset (Chris)

References: https://bugzilla.freedesktop.org/show_bug.cgi?id=108315
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: default avatarMika Kuoppala <mika.kuoppala@linux.intel.com>
Reviewed-by: default avatarChris Wilson <chris@chris-wilson.co.uk>
Link: https://patchwork.freedesktop.org/patch/msgid/20181205134612.24822-1-mika.kuoppala@linux.intel.com
parent 490b8c65
...@@ -770,6 +770,13 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists) ...@@ -770,6 +770,13 @@ execlists_cancel_port_requests(struct intel_engine_execlists * const execlists)
execlists_clear_all_active(execlists); execlists_clear_all_active(execlists);
} }
static inline void
invalidate_csb_entries(const u32 *first, const u32 *last)
{
clflush((void *)first);
clflush((void *)last);
}
static void reset_csb_pointers(struct intel_engine_execlists *execlists) static void reset_csb_pointers(struct intel_engine_execlists *execlists)
{ {
const unsigned int reset_value = GEN8_CSB_ENTRIES - 1; const unsigned int reset_value = GEN8_CSB_ENTRIES - 1;
...@@ -785,6 +792,9 @@ static void reset_csb_pointers(struct intel_engine_execlists *execlists) ...@@ -785,6 +792,9 @@ static void reset_csb_pointers(struct intel_engine_execlists *execlists)
*/ */
execlists->csb_head = reset_value; execlists->csb_head = reset_value;
WRITE_ONCE(*execlists->csb_write, reset_value); WRITE_ONCE(*execlists->csb_write, reset_value);
invalidate_csb_entries(&execlists->csb_status[0],
&execlists->csb_status[GEN8_CSB_ENTRIES - 1]);
} }
static void nop_submission_tasklet(unsigned long data) static void nop_submission_tasklet(unsigned long data)
...@@ -1020,6 +1030,19 @@ static void process_csb(struct intel_engine_cs *engine) ...@@ -1020,6 +1030,19 @@ static void process_csb(struct intel_engine_cs *engine)
} while (head != tail); } while (head != tail);
execlists->csb_head = head; execlists->csb_head = head;
/*
* Gen11 has proven to fail wrt global observation point between
* entry and tail update, failing on the ordering and thus
* we see an old entry in the context status buffer.
*
* Forcibly evict out entries for the next gpu csb update,
* to increase the odds that we get a fresh entries with non
* working hardware. The cost for doing so comes out mostly with
* the wash as hardware, working or not, will need to do the
* invalidation before.
*/
invalidate_csb_entries(&buf[0], &buf[GEN8_CSB_ENTRIES - 1]);
} }
static void __execlists_submission_tasklet(struct intel_engine_cs *const engine) static void __execlists_submission_tasklet(struct intel_engine_cs *const engine)
......
Markdown is supported
0%
or
You are about to add 0 people to the discussion. Proceed with caution.
Finish editing this message first!
Please register or to comment