diff mbox

drm/i915: add irq_barrier operation for synchronising reads

Message ID 1418901522-14819-1-git-send-email-david.s.gordon@intel.com (mailing list archive)
State New, archived
Headers show

Commit Message

Dave Gordon Dec. 18, 2014, 11:18 a.m. UTC
On some generations of chips, it is necessary to read an MMIO register
before getting the sequence number from the status page in main memory,
in order to ensure coherency; and on all generations this should be
either helpful or harmless.

In general, we want this operation to be the cheapest possible, since
we require only the side-effect of DMA completion and don't interpret
the result of the read, and don't require any coordination with other
threads, power domains, or anything else.

However, finding a suitable register may be problematic; on GEN6 chips
the ACTHD register was used, but on VLV et al access to this register
requires FORCEWAKE and therefore many complications involving spinlocks
and polling.

So this commit introduces this synchronising operation as a distinct
vfunc in the engine structure, so that it can be GEN- or chip-specific
if needed.

And there are three implementations; a dummy one, for chips where no
synchronising read is needed, a gen6(+) version that issues a posting
read (to TAIL), and a VLV-specific one that issues a raw read instead,
avoiding touching FORCEWAKE and GTFIFO and other such complications.

We then change gen6_ring_get_seqno() to use this new irq_barrier rather
than a POSTING_READ of ACTHD. Note that both older (pre-GEN6) and newer
(GEN8+) devices running in LRC mode do not currently include any posting
read in their own get_seqno() implementations, so this change only
makes a difference on VLV (and not CHV+).

Signed-off-by: Dave Gordon <david.s.gordon@intel.com>
---
 drivers/gpu/drm/i915/intel_ringbuffer.c |   37 +++++++++++++++++++++++++++++--
 drivers/gpu/drm/i915/intel_ringbuffer.h |    1 +
 2 files changed, 36 insertions(+), 2 deletions(-)

Comments

Shuang He Dec. 18, 2014, 4:57 p.m. UTC | #1
Tested-By: PRC QA PRTS (Patch Regression Test System Contact: shuang.he@intel.com)
-------------------------------------Summary-------------------------------------
Platform          Delta          drm-intel-nightly          Series Applied
PNV                 -1              364/364              363/364
ILK              +1-1              364/366              364/366
SNB                 -1              448/450              447/450
IVB                 -1              497/498              496/498
BYT                 -1              289/289              288/289
HSW                 -1              563/564              562/564
BDW                 -1              416/417              415/417
-------------------------------------Detailed-------------------------------------
Platform  Test                                drm-intel-nightly          Series Applied
 PNV  igt_gem_exec_blt      NRUN(3, M23M7M25)PASS(1, M25)      NRUN(1, M25)
 ILK  igt_gem_exec_blt      NRUN(3, M37M26)PASS(1, M26)      NRUN(1, M37)
 ILK  igt_kms_flip_bcs-flip-vs-modeset-interruptible      DMESG_WARN(1, M26)PASS(7, M37M26)      PASS(1, M37)
 SNB  igt_gem_exec_blt      NRUN(3, M35M22)PASS(1, M35)      NRUN(1, M35)
 IVB  igt_gem_exec_blt      NRUN(3, M34M21M4)PASS(1, M34)      NRUN(1, M4)
 BYT  igt_gem_exec_blt      NRUN(3, M48M49M50)PASS(1, M48)      NRUN(1, M50)
 HSW  igt_gem_exec_blt      NRUN(3, M40M20M19)PASS(1, M40)      NRUN(1, M19)
 BDW  igt_gem_exec_blt      NRUN(3, M30M28)PASS(1, M28)      NRUN(1, M30)
Note: You need to pay more attention to line start with '*'
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 12a36f0..ed8034b 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -1209,6 +1209,28 @@  pc_render_add_request(struct intel_engine_cs *ring)
 	return 0;
 }
 
+static void
+dummy_irq_barrier(struct intel_engine_cs *ring)
+{
+}
+
+static void
+gen6_irq_barrier(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+	POSTING_READ(RING_TAIL(ring->mmio_base));
+}
+
+#define __raw_i915_read32(dev_priv__, reg__)	readl((dev_priv__)->regs + (reg__))
+#define RAW_POSTING_READ(reg__)			(void)__raw_i915_read32(dev_priv, reg__)
+
+static void
+vlv_irq_barrier(struct intel_engine_cs *ring)
+{
+	struct drm_i915_private *dev_priv = to_i915(ring->dev);
+	RAW_POSTING_READ(RING_TAIL(ring->mmio_base));
+}
+
 static u32
 gen6_ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
 {
@@ -1216,8 +1238,7 @@  gen6_ring_get_seqno(struct intel_engine_cs *ring, bool lazy_coherency)
 	 * ivb (and maybe also on snb) by reading from a CS register (like
 	 * ACTHD) before reading the status page. */
 	if (!lazy_coherency) {
-		struct drm_i915_private *dev_priv = ring->dev->dev_private;
-		POSTING_READ(RING_ACTHD(ring->mmio_base));
+		ring->irq_barrier(ring);
 	}
 
 	return intel_read_status_page(ring, I915_GEM_HWS_INDEX);
@@ -2375,6 +2396,7 @@  int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->irq_get = gen8_ring_get_irq;
 		ring->irq_put = gen8_ring_put_irq;
 		ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
+		ring->irq_barrier = gen6_irq_barrier;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		if (i915_semaphore_is_enabled(dev)) {
@@ -2391,6 +2413,10 @@  int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->irq_get = gen6_ring_get_irq;
 		ring->irq_put = gen6_ring_put_irq;
 		ring->irq_enable_mask = GT_RENDER_USER_INTERRUPT;
+		if (IS_VALLEYVIEW(dev) && !IS_GEN8(dev))
+			ring->irq_barrier = vlv_irq_barrier;
+		else
+			ring->irq_barrier = gen6_irq_barrier;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		if (i915_semaphore_is_enabled(dev)) {
@@ -2417,6 +2443,7 @@  int intel_init_render_ring_buffer(struct drm_device *dev)
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->flush = gen4_render_ring_flush;
+		ring->irq_barrier = dummy_irq_barrier;
 		ring->get_seqno = pc_render_get_seqno;
 		ring->set_seqno = pc_render_set_seqno;
 		ring->irq_get = gen5_ring_get_irq;
@@ -2429,6 +2456,7 @@  int intel_init_render_ring_buffer(struct drm_device *dev)
 			ring->flush = gen2_render_ring_flush;
 		else
 			ring->flush = gen4_render_ring_flush;
+		ring->irq_barrier = dummy_irq_barrier;
 		ring->get_seqno = ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		if (IS_GEN2(dev)) {
@@ -2505,6 +2533,7 @@  int intel_init_bsd_ring_buffer(struct drm_device *dev)
 			ring->write_tail = gen6_bsd_ring_write_tail;
 		ring->flush = gen6_bsd_ring_flush;
 		ring->add_request = gen6_add_request;
+		ring->irq_barrier = gen6_irq_barrier;
 		ring->get_seqno = gen6_ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		if (INTEL_INFO(dev)->gen >= 8) {
@@ -2544,6 +2573,7 @@  int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->mmio_base = BSD_RING_BASE;
 		ring->flush = bsd_ring_flush;
 		ring->add_request = i9xx_add_request;
+		ring->irq_barrier = dummy_irq_barrier;
 		ring->get_seqno = ring_get_seqno;
 		ring->set_seqno = ring_set_seqno;
 		if (IS_GEN5(dev)) {
@@ -2583,6 +2613,7 @@  int intel_init_bsd2_ring_buffer(struct drm_device *dev)
 	ring->mmio_base = GEN8_BSD2_RING_BASE;
 	ring->flush = gen6_bsd_ring_flush;
 	ring->add_request = gen6_add_request;
+	ring->irq_barrier = gen6_irq_barrier;
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;
 	ring->irq_enable_mask =
@@ -2613,6 +2644,7 @@  int intel_init_blt_ring_buffer(struct drm_device *dev)
 	ring->write_tail = ring_write_tail;
 	ring->flush = gen6_ring_flush;
 	ring->add_request = gen6_add_request;
+	ring->irq_barrier = gen6_irq_barrier;
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;
 	if (INTEL_INFO(dev)->gen >= 8) {
@@ -2670,6 +2702,7 @@  int intel_init_vebox_ring_buffer(struct drm_device *dev)
 	ring->write_tail = ring_write_tail;
 	ring->flush = gen6_ring_flush;
 	ring->add_request = gen6_add_request;
+	ring->irq_barrier = gen6_irq_barrier;
 	ring->get_seqno = gen6_ring_get_seqno;
 	ring->set_seqno = ring_set_seqno;
 
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 6dbb6f4..f686929 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -163,6 +163,7 @@  struct  intel_engine_cs {
 	 * seen value is good enough. Note that the seqno will always be
 	 * monotonic, even if not coherent.
 	 */
+	void		(*irq_barrier)(struct intel_engine_cs *ring);
 	u32		(*get_seqno)(struct intel_engine_cs *ring,
 				     bool lazy_coherency);
 	void		(*set_seqno)(struct intel_engine_cs *ring,