drm/i915/execlists: Pack the count into the low bits of the port.request
add/remove: 1/1 grow/shrink: 5/4 up/down: 391/-578 (-187)
function old new delta
execlists_submit_ports 262 471 +209
port_assign.isra - 136 +136
capture 6344 6359 +15
reset_common_ring 438 452 +14
execlists_submit_request 228 238 +10
gen8_init_common_ring 334 341 +7
intel_engine_is_idle 106 105 -1
i915_engine_info 2314 2290 -24
__i915_gem_set_wedged_BKL 485 411 -74
intel_lrc_irq_handler 1789 1604 -185
execlists_update_context 294 - -294
The most important change there is the improve to the
intel_lrc_irq_handler and excclist_submit_ports (net improvement since
execlists_update_context is now inlined).
v2: Use the port_api() for guc as well (even though currently we do not
pack any counters in there, yet) and hide all port->request_count inside
the helpers.
Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Mika Kuoppala <mika.kuoppala@intel.com>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: http://patchwork.freedesktop.org/patch/msgid/20170517121007.27224-5-chris@chris-wilson.co.uk
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index ec16fb6..162f0a9 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -368,8 +368,15 @@ struct intel_engine_cs {
/* Execlists */
struct tasklet_struct irq_tasklet;
struct execlist_port {
- struct drm_i915_gem_request *request;
- unsigned int count;
+ struct drm_i915_gem_request *request_count;
+#define EXECLIST_COUNT_BITS 2
+#define port_request(p) ptr_mask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_count(p) ptr_unmask_bits((p)->request_count, EXECLIST_COUNT_BITS)
+#define port_pack(rq, count) ptr_pack_bits(rq, count, EXECLIST_COUNT_BITS)
+#define port_unpack(p, count) ptr_unpack_bits((p)->request_count, count, EXECLIST_COUNT_BITS)
+#define port_set(p, packed) ((p)->request_count = (packed))
+#define port_isset(p) ((p)->request_count)
+#define port_index(p, e) ((p) - (e)->execlist_port)
GEM_DEBUG_DECL(u32 context_id);
} execlist_port[2];
struct rb_root execlist_queue;