drm/i915/execlists: Unify CSB access pointers

Following the removal of the last workarounds, the only CSB mmio access
is for the old vGPU interface. The mmio registers presented by vGPU do
not require forcewake and can be treated as ordinary volatile memory,
i.e. they behave just like the HWSP access just at a different location.
We can reduce the CSB access to a set of read/write/buffer pointers and
treat the various paths identically and not worry about forcewake.
(Forcewake is nightmare for worstcase latency, and we want to process
this all with irqsoff -- no latency allowed!)

v2: Comments, comments, comments. Well, 2 bonus comments.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
Cc: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Reviewed-by: Tvrtko Ursulin <tvrtko.ursulin@intel.com>
Link: https://patchwork.freedesktop.org/patch/msgid/20180628201211.13837-5-chris@chris-wilson.co.uk

1 files changed, 65 insertions, 68 deletions

diff --git a/drivers/gpu/drm/i915/intel_lrc.c b/drivers/gpu/drm/i915/intel_lrc.c
index c8d3d41011ce..81f000c245ab 100644
--- a/drivers/gpu/drm/i915/intel_lrc.c
+++ b/drivers/gpu/drm/i915/intel_lrc.c
@@ -137,6 +137,7 @@
 #include <drm/i915_drm.h>
 #include "i915_drv.h"
 #include "i915_gem_render_state.h"
+#include "i915_vgpu.h"
 #include "intel_lrc_reg.h"
 #include "intel_mocs.h"
 #include "intel_workarounds.h"
@@ -954,44 +955,40 @@ static void process_csb(struct intel_engine_cs *engine)
 {
 	struct intel_engine_execlists * const execlists = &engine->execlists;
 	struct execlist_port *port = execlists->port;
-	struct drm_i915_private *i915 = engine->i915;
-
-	/* The HWSP contains a (cacheable) mirror of the CSB */
-	const u32 *buf =
-		&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
-	unsigned int head, tail;
-	bool fw = false;
+	const u32 * const buf = execlists->csb_status;
+	u8 head, tail;
 
 	/* Clear before reading to catch new interrupts */
 	clear_bit(ENGINE_IRQ_EXECLIST, &engine->irq_posted);
 	smp_mb__after_atomic();
 
-	if (unlikely(execlists->csb_use_mmio)) {
-		intel_uncore_forcewake_get(i915, execlists->fw_domains);
-		fw = true;
-
-		buf = (u32 * __force)
-			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
-
-		head = readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-		tail = GEN8_CSB_WRITE_PTR(head);
-		head = GEN8_CSB_READ_PTR(head);
-		execlists->csb_head = head;
-	} else {
-		const int write_idx =
-			intel_hws_csb_write_index(i915) -
-			I915_HWS_CSB_BUF0_INDEX;
+	/*
+	 * Note that csb_write, csb_status may be either in HWSP or mmio.
+	 * When reading from the csb_write mmio register, we have to be
+	 * careful to only use the GEN8_CSB_WRITE_PTR portion, which is
+	 * the low 4bits. As it happens we know the next 4bits are always
+	 * zero and so we can simply masked off the low u8 of the register
+	 * and treat it identically to reading from the HWSP (without having
+	 * to use explicit shifting and masking, and probably bifurcating
+	 * the code to handle the legacy mmio read).
+	 */
+	head = execlists->csb_head;
+	tail = READ_ONCE(*execlists->csb_write);
+	GEM_TRACE("%s cs-irq head=%d, tail=%d\n", engine->name, head, tail);
+	if (unlikely(head == tail))
+		return;
 
-		head = execlists->csb_head;
-		tail = READ_ONCE(buf[write_idx]);
-		rmb(); /* Hopefully paired with a wmb() in HW */
-	}
-	GEM_TRACE("%s cs-irq head=%d [%d%s], tail=%d [%d%s]\n",
-		  engine->name,
-		  head, GEN8_CSB_READ_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?",
-		  tail, GEN8_CSB_WRITE_PTR(readl(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)))), fw ? "" : "?");
+	/*
+	 * Hopefully paired with a wmb() in HW!
+	 *
+	 * We must complete the read of the write pointer before any reads
+	 * from the CSB, so that we do not see stale values. Without an rmb
+	 * (lfence) the HW may speculatively perform the CSB[] reads *before*
+	 * we perform the READ_ONCE(*csb_write).
+	 */
+	rmb();
 
-	while (head != tail) {
+	do {
 		struct i915_request *rq;
 		unsigned int status;
 		unsigned int count;
@@ -1017,12 +1014,12 @@ static void process_csb(struct intel_engine_cs *engine)
 		 * status notifier.
 		 */
 
-		status = READ_ONCE(buf[2 * head]); /* maybe mmio! */
 		GEM_TRACE("%s csb[%d]: status=0x%08x:0x%08x, active=0x%x\n",
 			  engine->name, head,
-			  status, buf[2*head + 1],
+			  buf[2 * head + 0], buf[2 * head + 1],
 			  execlists->active);
 
+		status = buf[2 * head];
 		if (status & (GEN8_CTX_STATUS_IDLE_ACTIVE |
 			      GEN8_CTX_STATUS_PREEMPTED))
 			execlists_set_active(execlists,
@@ -1104,16 +1101,11 @@ static void process_csb(struct intel_engine_cs *engine)
 		} else {
 			port_set(port, port_pack(rq, count));
 		}
-	}
-
-	if (head != execlists->csb_head) {
-		execlists->csb_head = head;
-		writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
-		       i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine)));
-	}
+	} while (head != tail);
 
-	if (unlikely(fw))
-		intel_uncore_forcewake_put(i915, execlists->fw_domains);
+	writel(_MASKED_FIELD(GEN8_CSB_READ_PTR_MASK, head << 8),
+	       execlists->csb_read);
+	execlists->csb_head = head;
 }
 
 /*
@@ -2431,28 +2423,11 @@ logical_ring_default_irqs(struct intel_engine_cs *engine)
 static void
 logical_ring_setup(struct intel_engine_cs *engine)
 {
-	struct drm_i915_private *dev_priv = engine->i915;
-	enum forcewake_domains fw_domains;
-
 	intel_engine_setup_common(engine);
 
 	/* Intentionally left blank. */
 	engine->buffer = NULL;
 
-	fw_domains = intel_uncore_forcewake_for_reg(dev_priv,
-						    RING_ELSP(engine),
-						    FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_PTR(engine),
-						     FW_REG_READ | FW_REG_WRITE);
-
-	fw_domains |= intel_uncore_forcewake_for_reg(dev_priv,
-						     RING_CONTEXT_STATUS_BUF_BASE(engine),
-						     FW_REG_READ);
-
-	engine->execlists.fw_domains = fw_domains;
-
 	tasklet_init(&engine->execlists.tasklet,
 		     execlists_submission_tasklet, (unsigned long)engine);
 
@@ -2460,34 +2435,56 @@ logical_ring_setup(struct intel_engine_cs *engine)
 	logical_ring_default_irqs(engine);
 }
 
+static bool csb_force_mmio(struct drm_i915_private *i915)
+{
+	/* Older GVT emulation depends upon intercepting CSB mmio */
+	return intel_vgpu_active(i915) && !intel_vgpu_has_hwsp_emulation(i915);
+}
+
 static int logical_ring_init(struct intel_engine_cs *engine)
 {
+	struct drm_i915_private *i915 = engine->i915;
+	struct intel_engine_execlists * const execlists = &engine->execlists;
 	int ret;
 
 	ret = intel_engine_init_common(engine);
 	if (ret)
 		goto error;
 
-	if (HAS_LOGICAL_RING_ELSQ(engine->i915)) {
-		engine->execlists.submit_reg = engine->i915->regs +
+	if (HAS_LOGICAL_RING_ELSQ(i915)) {
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_SQ_CONTENTS(engine));
-		engine->execlists.ctrl_reg = engine->i915->regs +
+		execlists->ctrl_reg = i915->regs +
 			i915_mmio_reg_offset(RING_EXECLIST_CONTROL(engine));
 	} else {
-		engine->execlists.submit_reg = engine->i915->regs +
+		execlists->submit_reg = i915->regs +
 			i915_mmio_reg_offset(RING_ELSP(engine));
 	}
 
-	engine->execlists.preempt_complete_status = ~0u;
-	if (engine->i915->preempt_context) {
+	execlists->preempt_complete_status = ~0u;
+	if (i915->preempt_context) {
 		struct intel_context *ce =
-			to_intel_context(engine->i915->preempt_context, engine);
+			to_intel_context(i915->preempt_context, engine);
 
-		engine->execlists.preempt_complete_status =
+		execlists->preempt_complete_status =
 			upper_32_bits(ce->lrc_desc);
 	}
 
-	engine->execlists.csb_head = GEN8_CSB_ENTRIES - 1;
+	execlists->csb_head = GEN8_CSB_ENTRIES - 1;
+	execlists->csb_read =
+		i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_PTR(engine));
+	if (csb_force_mmio(i915)) {
+		execlists->csb_status = (u32 __force *)
+			(i915->regs + i915_mmio_reg_offset(RING_CONTEXT_STATUS_BUF_LO(engine, 0)));
+
+		execlists->csb_write = (u32 __force *)execlists->csb_read;
+	} else {
+		execlists->csb_status =
+			&engine->status_page.page_addr[I915_HWS_CSB_BUF0_INDEX];
+
+		execlists->csb_write =
+			&engine->status_page.page_addr[intel_hws_csb_write_index(i915)];
+	}
 
 	return 0;