intel-gfx.lists.freedesktop.org archive mirror
 help / color / mirror / Atom feed
From: Chris Wilson <chris@chris-wilson.co.uk>
To: intel-gfx@lists.freedesktop.org
Cc: Chris Wilson <chris@chris-wilson.co.uk>
Subject: [Intel-gfx] [PATCH 07/36] drm/i915/gt: Support creation of 'internal' rings
Date: Mon,  1 Jun 2020 08:24:17 +0100	[thread overview]
Message-ID: <20200601072446.19548-7-chris@chris-wilson.co.uk> (raw)
In-Reply-To: <20200601072446.19548-1-chris@chris-wilson.co.uk>

To support legacy ring buffer scheduling, we want a virtual ringbuffer
for each client. These rings are purely for holding the requests as they
are being constructed on the CPU and never accessed by the GPU, so they
should not be bound into the GGTT, and we can use plain old WB mapped
pages.

As they are not bound, we need to nerf a few assumptions that a rq->ring
is in the GGTT.

Signed-off-by: Chris Wilson <chris@chris-wilson.co.uk>
---
 drivers/gpu/drm/i915/gt/intel_context.c    |  2 +-
 drivers/gpu/drm/i915/gt/intel_engine_cs.c  | 17 ++----
 drivers/gpu/drm/i915/gt/intel_ring.c       | 63 ++++++++++++++--------
 drivers/gpu/drm/i915/gt/intel_ring.h       | 12 ++++-
 drivers/gpu/drm/i915/gt/intel_ring_types.h |  2 +
 5 files changed, 57 insertions(+), 39 deletions(-)

diff --git a/drivers/gpu/drm/i915/gt/intel_context.c b/drivers/gpu/drm/i915/gt/intel_context.c
index e4aece20bc80..fd71977c010a 100644
--- a/drivers/gpu/drm/i915/gt/intel_context.c
+++ b/drivers/gpu/drm/i915/gt/intel_context.c
@@ -127,7 +127,7 @@ int __intel_context_do_pin(struct intel_context *ce)
 			goto err_active;
 
 		CE_TRACE(ce, "pin ring:{start:%08x, head:%04x, tail:%04x}\n",
-			 i915_ggtt_offset(ce->ring->vma),
+			 intel_ring_address(ce->ring),
 			 ce->ring->head, ce->ring->tail);
 
 		smp_mb__before_atomic(); /* flush pin before it is visible */
diff --git a/drivers/gpu/drm/i915/gt/intel_engine_cs.c b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
index c8c14981eb5d..64e13c074708 100644
--- a/drivers/gpu/drm/i915/gt/intel_engine_cs.c
+++ b/drivers/gpu/drm/i915/gt/intel_engine_cs.c
@@ -1261,7 +1261,7 @@ static int print_ring(char *buf, int sz, struct i915_request *rq)
 
 		len = scnprintf(buf, sz,
 				"ring:{start:%08x, hwsp:%08x, seqno:%08x, runtime:%llums}, ",
-				i915_ggtt_offset(rq->ring->vma),
+				intel_ring_address(rq->ring),
 				tl ? tl->hwsp_offset : 0,
 				hwsp_seqno(rq),
 				DIV_ROUND_CLOSEST_ULL(intel_context_get_total_runtime_ns(rq->context),
@@ -1542,7 +1542,7 @@ void intel_engine_dump(struct intel_engine_cs *engine,
 		print_request(m, rq, "\t\tactive ");
 
 		drm_printf(m, "\t\tring->start:  0x%08x\n",
-			   i915_ggtt_offset(rq->ring->vma));
+			   intel_ring_address(rq->ring));
 		drm_printf(m, "\t\tring->head:   0x%08x\n",
 			   rq->ring->head);
 		drm_printf(m, "\t\tring->tail:   0x%08x\n",
@@ -1621,13 +1621,6 @@ ktime_t intel_engine_get_busy_time(struct intel_engine_cs *engine)
 	return total;
 }
 
-static bool match_ring(struct i915_request *rq)
-{
-	u32 ring = ENGINE_READ(rq->engine, RING_START);
-
-	return ring == i915_ggtt_offset(rq->ring->vma);
-}
-
 struct i915_request *
 intel_engine_find_active_request(struct intel_engine_cs *engine)
 {
@@ -1667,11 +1660,7 @@ intel_engine_find_active_request(struct intel_engine_cs *engine)
 			continue;
 
 		if (!i915_request_started(request))
-			continue;
-
-		/* More than one preemptible request may match! */
-		if (!match_ring(request))
-			continue;
+			break;
 
 		active = request;
 		break;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.c b/drivers/gpu/drm/i915/gt/intel_ring.c
index 8cda1b7e17ba..438637996ab5 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.c
+++ b/drivers/gpu/drm/i915/gt/intel_ring.c
@@ -24,33 +24,42 @@ unsigned int intel_ring_update_space(struct intel_ring *ring)
 int intel_ring_pin(struct intel_ring *ring)
 {
 	struct i915_vma *vma = ring->vma;
-	unsigned int flags;
 	void *addr;
 	int ret;
 
 	if (atomic_fetch_inc(&ring->pin_count))
 		return 0;
 
-	/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
-	flags = PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
+	if (!(ring->flags & INTEL_RING_CREATE_INTERNAL)) {
+		unsigned int pin;
 
-	if (vma->obj->stolen)
-		flags |= PIN_MAPPABLE;
-	else
-		flags |= PIN_HIGH;
+		/* Ring wraparound at offset 0 sometimes hangs. No idea why. */
+		pin |= PIN_OFFSET_BIAS | i915_ggtt_pin_bias(vma);
 
-	ret = i915_ggtt_pin(vma, 0, flags);
-	if (unlikely(ret))
-		goto err_unpin;
+		if (vma->obj->stolen)
+			pin |= PIN_MAPPABLE;
+		else
+			pin |= PIN_HIGH;
 
-	if (i915_vma_is_map_and_fenceable(vma))
-		addr = (void __force *)i915_vma_pin_iomap(vma);
-	else
-		addr = i915_gem_object_pin_map(vma->obj,
-					       i915_coherent_map_type(vma->vm->i915));
-	if (IS_ERR(addr)) {
-		ret = PTR_ERR(addr);
-		goto err_ring;
+		ret = i915_ggtt_pin(vma, 0, pin);
+		if (unlikely(ret))
+			goto err_unpin;
+
+		if (i915_vma_is_map_and_fenceable(vma))
+			addr = (void __force *)i915_vma_pin_iomap(vma);
+		else
+			addr = i915_gem_object_pin_map(vma->obj,
+						       i915_coherent_map_type(vma->vm->i915));
+		if (IS_ERR(addr)) {
+			ret = PTR_ERR(addr);
+			goto err_ring;
+		}
+	} else {
+		addr = i915_gem_object_pin_map(vma->obj, I915_MAP_WB);
+		if (IS_ERR(addr)) {
+			ret = PTR_ERR(addr);
+			goto err_ring;
+		}
 	}
 
 	i915_vma_make_unshrinkable(vma);
@@ -91,10 +100,12 @@ void intel_ring_unpin(struct intel_ring *ring)
 		i915_gem_object_unpin_map(vma->obj);
 
 	i915_vma_make_purgeable(vma);
-	i915_vma_unpin(vma);
+	if (!(ring->flags & INTEL_RING_CREATE_INTERNAL))
+		i915_vma_unpin(vma);
 }
 
-static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
+static struct i915_vma *
+create_ring_vma(struct i915_ggtt *ggtt, int size, unsigned int flags)
 {
 	struct i915_address_space *vm = &ggtt->vm;
 	struct drm_i915_private *i915 = vm->i915;
@@ -102,7 +113,8 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
 	struct i915_vma *vma;
 
 	obj = ERR_PTR(-ENODEV);
-	if (i915_ggtt_has_aperture(ggtt))
+	if (!(flags & INTEL_RING_CREATE_INTERNAL) &&
+	    i915_ggtt_has_aperture(ggtt))
 		obj = i915_gem_object_create_stolen(i915, size);
 	if (IS_ERR(obj))
 		obj = i915_gem_object_create_internal(i915, size);
@@ -128,12 +140,14 @@ static struct i915_vma *create_ring_vma(struct i915_ggtt *ggtt, int size)
 }
 
 struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size)
+intel_engine_create_ring(struct intel_engine_cs *engine, unsigned int size)
 {
 	struct drm_i915_private *i915 = engine->i915;
+	unsigned int flags = size & GENMASK(11, 0);
 	struct intel_ring *ring;
 	struct i915_vma *vma;
 
+	size ^= flags;
 	GEM_BUG_ON(!is_power_of_2(size));
 	GEM_BUG_ON(RING_CTL_SIZE(size) & ~RING_NR_PAGES);
 
@@ -142,8 +156,10 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 		return ERR_PTR(-ENOMEM);
 
 	kref_init(&ring->ref);
+
 	ring->size = size;
 	ring->wrap = BITS_PER_TYPE(ring->size) - ilog2(size);
+	ring->flags = flags;
 
 	/*
 	 * Workaround an erratum on the i830 which causes a hang if
@@ -156,11 +172,12 @@ intel_engine_create_ring(struct intel_engine_cs *engine, int size)
 
 	intel_ring_update_space(ring);
 
-	vma = create_ring_vma(engine->gt->ggtt, size);
+	vma = create_ring_vma(engine->gt->ggtt, size, flags);
 	if (IS_ERR(vma)) {
 		kfree(ring);
 		return ERR_CAST(vma);
 	}
+
 	ring->vma = vma;
 
 	return ring;
diff --git a/drivers/gpu/drm/i915/gt/intel_ring.h b/drivers/gpu/drm/i915/gt/intel_ring.h
index cc0ebca65167..d022fa209325 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring.h
@@ -9,12 +9,14 @@
 
 #include "i915_gem.h" /* GEM_BUG_ON */
 #include "i915_request.h"
+#include "i915_vma.h"
 #include "intel_ring_types.h"
 
 struct intel_engine_cs;
 
 struct intel_ring *
-intel_engine_create_ring(struct intel_engine_cs *engine, int size);
+intel_engine_create_ring(struct intel_engine_cs *engine, unsigned int size);
+#define INTEL_RING_CREATE_INTERNAL BIT(0)
 
 u32 *intel_ring_begin(struct i915_request *rq, unsigned int num_dwords);
 int intel_ring_cacheline_align(struct i915_request *rq);
@@ -137,4 +139,12 @@ __intel_ring_space(unsigned int head, unsigned int tail, unsigned int size)
 	return (head - tail - CACHELINE_BYTES) & (size - 1);
 }
 
+static inline u32 intel_ring_address(const struct intel_ring *ring)
+{
+	if (ring->flags & INTEL_RING_CREATE_INTERNAL)
+		return -1;
+
+	return i915_ggtt_offset(ring->vma);
+}
+
 #endif /* INTEL_RING_H */
diff --git a/drivers/gpu/drm/i915/gt/intel_ring_types.h b/drivers/gpu/drm/i915/gt/intel_ring_types.h
index 1a189ea00fd8..d927deafcb33 100644
--- a/drivers/gpu/drm/i915/gt/intel_ring_types.h
+++ b/drivers/gpu/drm/i915/gt/intel_ring_types.h
@@ -47,6 +47,8 @@ struct intel_ring {
 	u32 size;
 	u32 wrap;
 	u32 effective_size;
+
+	unsigned long flags;
 };
 
 #endif /* INTEL_RING_TYPES_H */
-- 
2.20.1

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

  parent reply	other threads:[~2020-06-01  7:25 UTC|newest]

Thread overview: 53+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2020-06-01  7:24 [Intel-gfx] [PATCH 01/36] drm/i915: Handle very early engine initialisation failure Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 02/36] drm/i915/gt: Split low level gen2-7 CS emitters Chris Wilson
2020-06-02  9:04   ` Mika Kuoppala
2020-06-01  7:24 ` [Intel-gfx] [PATCH 03/36] drm/i915/gt: Move legacy context wa to intel_workarounds Chris Wilson
2020-06-02  9:05   ` Mika Kuoppala
2020-06-01  7:24 ` [Intel-gfx] [PATCH 04/36] drm/i915: Trim the ironlake+ irq handler Chris Wilson
2020-06-01 11:49   ` Mika Kuoppala
2020-06-01 12:00     ` Chris Wilson
2020-06-01 12:08       ` Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 05/36] Restore "drm/i915: drop engine_pin/unpin_breadcrumbs_irq" Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 06/36] drm/i915/gt: Couple tasklet scheduling for all CS interrupts Chris Wilson
2020-06-01  7:24 ` Chris Wilson [this message]
2020-06-01  7:24 ` [Intel-gfx] [PATCH 08/36] drm/i915/gt: Use client timeline address for seqno writes Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 09/36] drm/i915: Support inter-engine semaphores on gen6/7 Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 10/36] drm/i915/gt: Infrastructure for ring scheduling Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 11/36] drm/i915/gt: Enable busy-stats for ring-scheduler Chris Wilson
2020-06-01  8:03   ` [Intel-gfx] [PATCH] " Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 12/36] drm/i915/gt: Track if an engine requires forcewake w/a Chris Wilson
2020-06-01 12:17   ` Mika Kuoppala
2020-06-01  7:24 ` [Intel-gfx] [PATCH 13/36] drm/i915: Relinquish forcewake immediately after manual grouping Chris Wilson
2020-06-01 12:20   ` Mika Kuoppala
2020-06-01  7:24 ` [Intel-gfx] [PATCH 14/36] drm/i915/gt: Implement ring scheduler for gen6/7 Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 15/36] drm/i915/gt: Enable ring scheduling " Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 16/36] drm/i915/gem: Mark the buffer pool as active for the cmdparser Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 17/36] drm/i915/gem: Async GPU relocations only Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 18/36] drm/i915: Add list_for_each_entry_safe_continue_reverse Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 19/36] drm/i915/gem: Separate reloc validation into an earlier step Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 20/36] drm/i915/gem: Lift GPU relocation allocation Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 21/36] drm/i915/gem: Build the reloc request first Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 22/36] drm/i915/gem: Add all GPU reloc awaits/signals en masse Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 23/36] dma-buf: Proxy fence, an unsignaled fence placeholder Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 24/36] drm/i915: Unpeel awaits on a proxy fence Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 25/36] drm/i915/gem: Make relocations atomic within execbuf Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 26/36] drm/syncobj: Allow use of dma-fence-proxy Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 27/36] drm/i915/gem: Teach execbuf how to wait on future syncobj Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 28/36] drm/i915/gem: Allow combining submit-fences with syncobj Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 29/36] drm/i915/gt: Declare when we enabled timeslicing Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 30/36] drm/i915: Drop I915_IDLE_ENGINES_TIMEOUT Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 31/36] drm/i915: Always defer fenced work to the worker Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 32/36] drm/i915/gem: Assign context id for async work Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 33/36] drm/i915: Export a preallocate variant of i915_active_acquire() Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 34/36] drm/i915/gem: Separate the ww_mutex walker into its own list Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 35/36] drm/i915/gem: Asynchronous GTT unbinding Chris Wilson
2020-06-01  7:24 ` [Intel-gfx] [PATCH 36/36] drm/i915/gem: Bind the fence async for execbuf Chris Wilson
2020-06-01  7:34 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/36] drm/i915: Handle very early engine initialisation failure Patchwork
2020-06-01  7:36 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-06-01  7:56 ` [Intel-gfx] ✗ Fi.CI.BAT: failure " Patchwork
2020-06-01  8:30 ` [Intel-gfx] ✗ Fi.CI.CHECKPATCH: warning for series starting with [01/36] drm/i915: Handle very early engine initialisation failure (rev2) Patchwork
2020-06-01  8:31 ` [Intel-gfx] ✗ Fi.CI.SPARSE: " Patchwork
2020-06-01  8:51 ` [Intel-gfx] ✓ Fi.CI.BAT: success " Patchwork
2020-06-01 11:00 ` [Intel-gfx] ✗ Fi.CI.IGT: failure " Patchwork
2020-06-01 11:39   ` Chris Wilson
2020-06-01 11:31 ` [Intel-gfx] [PATCH 01/36] drm/i915: Handle very early engine initialisation failure Mika Kuoppala

Reply instructions:

You may reply publicly to this message via plain-text email
using any one of the following methods:

* Save the following mbox file, import it into your mail client,
  and reply-to-all from there: mbox

  Avoid top-posting and favor interleaved quoting:
  https://en.wikipedia.org/wiki/Posting_style#Interleaved_style

* Reply using the --to, --cc, and --in-reply-to
  switches of git-send-email(1):

  git send-email \
    --in-reply-to=20200601072446.19548-7-chris@chris-wilson.co.uk \
    --to=chris@chris-wilson.co.uk \
    --cc=intel-gfx@lists.freedesktop.org \
    /path/to/YOUR_REPLY

  https://kernel.org/pub/software/scm/git/docs/git-send-email.html

* If your mail client supports setting the In-Reply-To header
  via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).