summaryrefslogtreecommitdiff
path: root/drivers/gpu/drm/i915/intel_ringbuffer.h
diff options
context:
space:
mode:
authorChris Wilson <chris@chris-wilson.co.uk>2017-11-20 23:55:01 +0300
committerChris Wilson <chris@chris-wilson.co.uk>2017-11-21 00:54:58 +0300
commit79e6770cb1f5e32eb49590edbb794a97d0113aed (patch)
treec62d7a3feac949fcc25906753ca3917eed38091b /drivers/gpu/drm/i915/intel_ringbuffer.h
parentfb5c551ad510e4a408c105670f89c725ebbfe6c8 (diff)
downloadlinux-79e6770cb1f5e32eb49590edbb794a97d0113aed.tar.xz
drm/i915: Remove obsolete ringbuffer emission for gen8+
Since removing the module parameter to force selection of ringbuffer emission for gen8, the code is defunct. Remove it. To put the difference into perspective, a couple of microbenchmarks (bdw i7-5557u, 20170324): ring execlists exec continuous nops on all rings: 1.491us 2.223us exec sequential nops on each ring: 12.508us 53.682us single nop + sync: 9.272us 30.291us vblank_mode=0 glxgears: ~11000fps ~9000fps Since the earlier submission, gen8 ringbuffer submission has fallen further and further behind in features. So while ringbuffer may hold the throughput crown, in terms of interactive latency, execlists is much better. Alas, we have no convenient metrics for such, other than demonstrating things we can do with execlists but can not using legacy ringbuffer submission. We have made a few improvements to lowlevel execlists throughput, and ringbuffer currently panics on boot! (bdw i7-5557u, 20171026): ring execlists exec continuous nops on all rings: n/a 1.921us exec sequential nops on each ring: n/a 44.621us single nop + sync: n/a 21.953us vblank_mode=0 glxgears: n/a ~18500fps References: https://bugs.freedesktop.org/show_bug.cgi?id=87725 Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk> Once-upon-a-time-Reviewed-by: Joonas Lahtinen <joonas.lahtinen@linux.intel.com> Reviewed-by: Mika Kuoppala <mika.kuoppala@linux.intel.com> Link: https://patchwork.freedesktop.org/patch/msgid/20171120205504.21892-2-chris@chris-wilson.co.uk
Diffstat (limited to 'drivers/gpu/drm/i915/intel_ringbuffer.h')
-rw-r--r--drivers/gpu/drm/i915/intel_ringbuffer.h25
1 files changed, 6 insertions, 19 deletions
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index e437a9556c08..80cd7812ce02 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -46,16 +46,6 @@ struct intel_hw_status_page {
/* seqno size is actually only a uint32, but since we plan to use MI_FLUSH_DW to
* do the writes, and that must have qw aligned offsets, simply pretend it's 8b.
*/
-#define gen8_semaphore_seqno_size sizeof(uint64_t)
-#define GEN8_SEMAPHORE_OFFSET(__from, __to) \
- (((__from) * I915_NUM_ENGINES + (__to)) * gen8_semaphore_seqno_size)
-#define GEN8_SIGNAL_OFFSET(__ring, to) \
- (dev_priv->semaphore->node.start + \
- GEN8_SEMAPHORE_OFFSET((__ring)->id, (to)))
-#define GEN8_WAIT_OFFSET(__ring, from) \
- (dev_priv->semaphore->node.start + \
- GEN8_SEMAPHORE_OFFSET(from, (__ring)->id))
-
enum intel_engine_hangcheck_action {
ENGINE_IDLE = 0,
ENGINE_WAIT,
@@ -467,18 +457,15 @@ struct intel_engine_cs {
* ie. transpose of f(x, y)
*/
struct {
- union {
#define GEN6_SEMAPHORE_LAST VECS_HW
#define GEN6_NUM_SEMAPHORES (GEN6_SEMAPHORE_LAST + 1)
#define GEN6_SEMAPHORES_MASK GENMASK(GEN6_SEMAPHORE_LAST, 0)
- struct {
- /* our mbox written by others */
- u32 wait[GEN6_NUM_SEMAPHORES];
- /* mboxes this ring signals to */
- i915_reg_t signal[GEN6_NUM_SEMAPHORES];
- } mbox;
- u64 signal_ggtt[I915_NUM_ENGINES];
- };
+ struct {
+ /* our mbox written by others */
+ u32 wait[GEN6_NUM_SEMAPHORES];
+ /* mboxes this ring signals to */
+ i915_reg_t signal[GEN6_NUM_SEMAPHORES];
+ } mbox;
/* AKA wait() */
int (*sync_to)(struct drm_i915_gem_request *req,