[PATCH v5] drm/i915/icl: Enhanced execution list support

[Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>]

From: Thomas Daniel <thomas.daniel@intel.com>

Enhanced Execlists is an upgraded version of execlists which supports
up to 8 ports. The lrcs to be submitted are written to a submit queue,
which is then loaded on the HW. When writing to the ELSP register, the
lrcs are written cyclically in the queue from position 0 to position 7.
Alternatively, it is possible to write directly in the individual
positions of the queue using the ELSQ registers. To be able to re-use
all the existing code we're using the latter method and we're currently
limiting ourself to only using 2 elements.

The preemption flow is sligthly different with enhanced execlists, so
this patch turns preemption off temporarily for Gen11+ while we wait for
the new mechanism to land.

v2: Rebase.
v3: Switch from !IS_GEN11 to GEN < 11 (Daniele Ceraolo Spurio).
v4: Use the elsq registers instead of elsp. (Daniele Ceraolo Spurio)
v5: Reword commit, rename regs to be closer to specs, turn off
    preemption (Daniele), reuse engine->execlists.elsp (Chris)

Cc: Chris Wilson <chris@chris-wilson.co.uk>
Signed-off-by: Thomas Daniel <thomas.daniel@intel.com>
Signed-off-by: Rodrigo Vivi <rodrigo.vivi@intel.com>
Signed-off-by: Daniele Ceraolo Spurio <daniele.ceraolospurio@intel.com>
---
 drivers/gpu/drm/i915/i915_drv.h         |  5 ++++-
 drivers/gpu/drm/i915/intel_lrc.c        | 35 ++++++++++++++++++++++++++++-----
 drivers/gpu/drm/i915/intel_lrc.h        |  3 +++
 drivers/gpu/drm/i915/intel_ringbuffer.h |  6 ++++--
 4 files changed, 41 insertions(+), 8 deletions(-)

diff --git a/drivers/gpu/drm/i915/i915_drv.h b/drivers/gpu/drm/i915/i915_drv.h
index c42015b..3163543 100644
--- a/drivers/gpu/drm/i915/i915_drv.h
+++ b/drivers/gpu/drm/i915/i915_drv.h
@@ -2738,8 +2738,11 @@ static inline unsigned int i915_sg_segment_size(void)
 
 #define HAS_LOGICAL_RING_CONTEXTS(dev_priv) \
 		((dev_priv)->info.has_logical_ring_contexts)
+
+/* XXX: Preemption disabled for Gen11+ until support for new flow lands */
 #define HAS_LOGICAL_RING_PREEMPTION(dev_priv) \
-		((dev_priv)->info.has_logical_ring_preemption)
+		((dev_priv)->info.has_logical_ring_preemption && \
+		 INTEL_GEN(dev_priv) < 11)
 
 #define HAS_EXECLISTS(dev_priv) HAS_LOGICAL_RING_CONTEXTS(dev_priv)
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index ff25f20..67ad7c9 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -428,11 +428,24 @@ static inline void elsp_write(u64 desc, u32 __iomem *elsp)
 	writel(lower_32_bits(desc), elsp);
 }
 
+static inline void elsqc_write(u64 desc, u32 __iomem *elsqc, u32 port)
+{
+	writel(lower_32_bits(desc), elsqc + port * 2);
+	writel(upper_32_bits(desc), elsqc + port * 2 + 1);
+}
+
 static void execlists_submit_ports(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *dev_priv = engine->i915;
 	struct execlist_port *port = engine->execlists.port;
 	unsigned int n;
 
+	/*
+	 * Gen11+ note: the submit queue is not cleared after being submitted
+	 * to the HW so we need to make sure we always clean it up. This is
+	 * currently ensured by the fact that we always write the same number
+	 * of elsq entries, keep this in mind before changing the loop below.
+	 */
 	for (n = execlists_num_ports(&engine->execlists); n--; ) {
 		struct drm_i915_gem_request *rq;
 		unsigned int count;
@@ -456,8 +469,16 @@ static void execlists_submit_ports(struct intel_engine_cs *engine)
 			desc = 0;
 		}
 
-		elsp_write(desc, engine->execlists.elsp);
+		if (INTEL_GEN(dev_priv) >= 11)
+			elsqc_write(desc, engine->execlists.els, n);
+		else
+			elsp_write(desc, engine->execlists.els);
 	}
+
+	/* for gen11+ we need to manually load the submit queue */
+	if (INTEL_GEN(dev_priv) >= 11)
+		I915_WRITE_FW(RING_EXECLIST_CONTROL(engine), EL_CTRL_LOAD);
+
 	execlists_clear_active(&engine->execlists, EXECLISTS_ACTIVE_HWACK);
 }
 
@@ -506,9 +527,9 @@ static void inject_preempt_context(struct intel_engine_cs *engine)
 
 	GEM_TRACE("%s\n", engine->name);
 	for (n = execlists_num_ports(&engine->execlists); --n; )
-		elsp_write(0, engine->execlists.elsp);
+		elsp_write(0, engine->execlists.els);
 
-	elsp_write(ce->lrc_desc, engine->execlists.elsp);
+	elsp_write(ce->lrc_desc, engine->execlists.els);
 	execlists_clear_active(&engine->execlists, EXECLISTS_ACTIVE_HWACK);
 }
 
@@ -2016,8 +2037,12 @@ static int logical_ring_init(struct intel_engine_cs *engine)
 	if (ret)
 		goto error;
 
-	engine->execlists.elsp =
-		engine->i915->regs + i915_mmio_reg_offset(RING_ELSP(engine));
+	if (INTEL_GEN(engine->i915) >= 11)
+		engine->execlists.els = engine->i915->regs +
+			i915_mmio_reg_offset(RING_EXECLIST_SQ_CONTENTS(engine));
+	else
+		engine->execlists.els = engine->i915->regs +
+			i915_mmio_reg_offset(RING_ELSP(engine));
 
 	return 0;
 
diff --git a/drivers/gpu/drm/i915/intel_lrc.h b/drivers/gpu/drm/i915/intel_lrc.h
index 6d4f9b9..3ab4266 100644
--- a/drivers/gpu/drm/i915/intel_lrc.h
+++ b/drivers/gpu/drm/i915/intel_lrc.h
@@ -38,6 +38,9 @@
 #define	  CTX_CTRL_ENGINE_CTX_RESTORE_INHIBIT	(1 << 0)
 #define   CTX_CTRL_RS_CTX_ENABLE                (1 << 1)
 #define RING_CONTEXT_STATUS_BUF_BASE(engine)	_MMIO((engine)->mmio_base + 0x370)
+#define RING_EXECLIST_SQ_CONTENTS(engine)	_MMIO((engine)->mmio_base + 0x510)
+#define RING_EXECLIST_CONTROL(engine)		_MMIO((engine)->mmio_base + 0x550)
+#define	  EL_CTRL_LOAD				(1 << 0)
 #define RING_CONTEXT_STATUS_BUF_LO(engine, i)	_MMIO((engine)->mmio_base + 0x370 + (i) * 8)
 #define RING_CONTEXT_STATUS_BUF_HI(engine, i)	_MMIO((engine)->mmio_base + 0x370 + (i) * 8 + 4)
 #define RING_CONTEXT_STATUS_PTR(engine)		_MMIO((engine)->mmio_base + 0x3a0)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index c5ff203..d36bb73 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -200,9 +200,11 @@ struct intel_engine_execlists {
 	bool no_priolist;
 
 	/**
-	 * @elsp: the ExecList Submission Port register
+	 * @els: gen-specific execlist submission register
+	 * set to the ExecList Submission Port (elsp) register pre-Gen11 and to
+	 * the ExecList Submission Queue Contents register array for Gen11+
 	 */
-	u32 __iomem *elsp;
+	u32 __iomem *els;
 
 	/**
 	 * @port: execlist port states
-- 
1.9.1

_______________________________________________
Intel-gfx mailing list
Intel-gfx@lists.freedesktop.org
https://lists.freedesktop.org/mailman/listinfo/intel-gfx