diff mbox

[02/18] drm/i915: Semaphore MBOX update generalization

Message ID 1367110769-1306-3-git-send-email-ben@bwidawsk.net (mailing list archive)
State New, archived
Headers show

Commit Message

Ben Widawsky April 28, 2013, 12:59 a.m. UTC 
This replaces the existing MBOX update code with a more generalized
calculation for emitting mbox updates. We also create a sentinel for
doing the updates so we can more abstractly deal with the rings.

When doing MBOX updates the code must be aware of the /other/ rings.
Until now the platforms which supported semaphores had a fixed number of
rings and so it made sense for the code to be very specialized
(hardcoded).

The patch does contain a functional change, but should have no
behavioral changes.

Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
---
 drivers/gpu/drm/i915/i915_reg.h         |  1 +
 drivers/gpu/drm/i915/intel_ringbuffer.c | 38 +++++++++++++++++++++------------
 drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
 3 files changed, 26 insertions(+), 15 deletions(-)

Comments

Lespiau, Damien May 7, 2013, 3:34 p.m. UTC | #1 
On Sat, Apr 27, 2013 at 05:59:13PM -0700, Ben Widawsky wrote:
> This replaces the existing MBOX update code with a more generalized
> calculation for emitting mbox updates. We also create a sentinel for
> doing the updates so we can more abstractly deal with the rings.
> 
> When doing MBOX updates the code must be aware of the /other/ rings.
> Until now the platforms which supported semaphores had a fixed number of
> rings and so it made sense for the code to be very specialized
> (hardcoded).
> 
> The patch does contain a functional change, but should have no
> behavioral changes.
> 
> Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> ---
>  drivers/gpu/drm/i915/i915_reg.h         |  1 +
>  drivers/gpu/drm/i915/intel_ringbuffer.c | 38 +++++++++++++++++++++------------
>  drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
>  3 files changed, 26 insertions(+), 15 deletions(-)
> 
> diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> index 767aa32..5be4a75 100644
> --- a/drivers/gpu/drm/i915/i915_reg.h
> +++ b/drivers/gpu/drm/i915/i915_reg.h
> @@ -568,6 +568,7 @@
>  #define GEN6_VRSYNC (RING_SYNC_1(GEN6_BSD_RING_BASE))
>  #define GEN6_VBSYNC (RING_SYNC_0(GEN6_BSD_RING_BASE))
>  #define GEN6_BRSYNC (RING_SYNC_0(BLT_RING_BASE))
> +#define GEN6_NOSYNC 0
>  #define GEN6_BVSYNC (RING_SYNC_1(BLT_RING_BASE))
>  #define RING_MAX_IDLE(base)	((base)+0x54)
>  #define RING_HWS_PGA(base)	((base)+0x80)
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> index 38751a7..0f97547 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> @@ -578,9 +578,11 @@ static void
>  update_mboxes(struct intel_ring_buffer *ring,
>  	      u32 mmio_offset)
>  {
> +#define MBOX_UPDATE_DWORDS 4
>  	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
>  	intel_ring_emit(ring, mmio_offset);
>  	intel_ring_emit(ring, ring->outstanding_lazy_request);
> +	intel_ring_emit(ring, MI_NOOP);

Not sure why you are adding a MI_NOOP here, mind documenting this?

>  }
>  
>  /**
> @@ -595,19 +597,24 @@ update_mboxes(struct intel_ring_buffer *ring,
>  static int
>  gen6_add_request(struct intel_ring_buffer *ring)
>  {
> -	u32 mbox1_reg;
> -	u32 mbox2_reg;
> -	int ret;
> +	struct drm_device *dev = ring->dev;
> +	struct drm_i915_private *dev_priv = dev->dev_private;
> +	struct intel_ring_buffer *useless;
> +	int i, ret;
>  
> -	ret = intel_ring_begin(ring, 10);
> +	ret = intel_ring_begin(ring, ((I915_NUM_RINGS-1) *
> +				      MBOX_UPDATE_DWORDS) +
> +				      4);
>  	if (ret)
>  		return ret;
> +#undef MBOX_UPDATE_DWORDS
>  
> -	mbox1_reg = ring->signal_mbox[0];
> -	mbox2_reg = ring->signal_mbox[1];
> +	for_each_ring(useless, dev_priv, i) {
> +		u32 mbox_reg = ring->signal_mbox[i];
> +		if (mbox_reg != GEN6_NOSYNC)
> +			update_mboxes(ring, mbox_reg);
> +	}
>  
> -	update_mboxes(ring, mbox1_reg);
> -	update_mboxes(ring, mbox2_reg);
>  	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
>  	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
>  	intel_ring_emit(ring, ring->outstanding_lazy_request);
> @@ -1669,8 +1676,9 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
>  		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
>  		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
>  		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
> -		ring->signal_mbox[0] = GEN6_VRSYNC;
> -		ring->signal_mbox[1] = GEN6_BRSYNC;
> +		ring->signal_mbox[RCS] = GEN6_NOSYNC;
> +		ring->signal_mbox[VCS] = GEN6_VRSYNC;
> +		ring->signal_mbox[BCS] = GEN6_BRSYNC;
>  	} else if (IS_GEN5(dev)) {
>  		ring->add_request = pc_render_add_request;
>  		ring->flush = gen4_render_ring_flush;
> @@ -1828,8 +1836,9 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
>  		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
>  		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
>  		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
> -		ring->signal_mbox[0] = GEN6_RVSYNC;
> -		ring->signal_mbox[1] = GEN6_BVSYNC;
> +		ring->signal_mbox[RCS] = GEN6_RVSYNC;
> +		ring->signal_mbox[VCS] = GEN6_NOSYNC;
> +		ring->signal_mbox[BCS] = GEN6_BVSYNC;
>  	} else {
>  		ring->mmio_base = BSD_RING_BASE;
>  		ring->flush = bsd_ring_flush;
> @@ -1874,8 +1883,9 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
>  	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
>  	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
>  	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
> -	ring->signal_mbox[0] = GEN6_RBSYNC;
> -	ring->signal_mbox[1] = GEN6_VBSYNC;
> +	ring->signal_mbox[RCS] = GEN6_RBSYNC;
> +	ring->signal_mbox[VCS] = GEN6_VBSYNC;
> +	ring->signal_mbox[BCS] = GEN6_NOSYNC;
>  	ring->init = init_ring_common;
>  
>  	return intel_init_ring_buffer(dev, ring);
> diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> index 785df13..f1aef0d 100644
> --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> @@ -103,7 +103,7 @@ struct  intel_ring_buffer {
>  				   u32 seqno);
>  
>  	u32		semaphore_register[I915_NUM_RINGS]; /*our mbox written by others */
> -	u32		signal_mbox[2]; /* mboxes this ring signals to */
> +	u32		signal_mbox[I915_NUM_RINGS]; /* mboxes this ring signals to + sentinel */
>  	/**
>  	 * List of objects currently involved in rendering from the
>  	 * ringbuffer.
> -- 
> 1.8.2.1
> 
> _______________________________________________
> Intel-gfx mailing list
> Intel-gfx@lists.freedesktop.org
> http://lists.freedesktop.org/mailman/listinfo/intel-gfx
Ben Widawsky May 8, 2013, 5:17 a.m. UTC | #2 
On Tue, May 07, 2013 at 04:34:46PM +0100, Damien Lespiau wrote:
> On Sat, Apr 27, 2013 at 05:59:13PM -0700, Ben Widawsky wrote:
> > This replaces the existing MBOX update code with a more generalized
> > calculation for emitting mbox updates. We also create a sentinel for
> > doing the updates so we can more abstractly deal with the rings.
> > 
> > When doing MBOX updates the code must be aware of the /other/ rings.
> > Until now the platforms which supported semaphores had a fixed number of
> > rings and so it made sense for the code to be very specialized
> > (hardcoded).
> > 
> > The patch does contain a functional change, but should have no
> > behavioral changes.
> > 
> > Signed-off-by: Ben Widawsky <ben@bwidawsk.net>
> > ---
> >  drivers/gpu/drm/i915/i915_reg.h         |  1 +
> >  drivers/gpu/drm/i915/intel_ringbuffer.c | 38 +++++++++++++++++++++------------
> >  drivers/gpu/drm/i915/intel_ringbuffer.h |  2 +-
> >  3 files changed, 26 insertions(+), 15 deletions(-)
> > 
> > diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
> > index 767aa32..5be4a75 100644
> > --- a/drivers/gpu/drm/i915/i915_reg.h
> > +++ b/drivers/gpu/drm/i915/i915_reg.h
> > @@ -568,6 +568,7 @@
> >  #define GEN6_VRSYNC (RING_SYNC_1(GEN6_BSD_RING_BASE))
> >  #define GEN6_VBSYNC (RING_SYNC_0(GEN6_BSD_RING_BASE))
> >  #define GEN6_BRSYNC (RING_SYNC_0(BLT_RING_BASE))
> > +#define GEN6_NOSYNC 0
> >  #define GEN6_BVSYNC (RING_SYNC_1(BLT_RING_BASE))
> >  #define RING_MAX_IDLE(base)	((base)+0x54)
> >  #define RING_HWS_PGA(base)	((base)+0x80)
> > diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > index 38751a7..0f97547 100644
> > --- a/drivers/gpu/drm/i915/intel_ringbuffer.c
> > +++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
> > @@ -578,9 +578,11 @@ static void
> >  update_mboxes(struct intel_ring_buffer *ring,
> >  	      u32 mmio_offset)
> >  {
> > +#define MBOX_UPDATE_DWORDS 4
> >  	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
> >  	intel_ring_emit(ring, mmio_offset);
> >  	intel_ring_emit(ring, ring->outstanding_lazy_request);
> > +	intel_ring_emit(ring, MI_NOOP);
> 
> Not sure why you are adding a MI_NOOP here, mind documenting this?
> 

Sure. The key is that we move to for_each_ring and the number of rings
we must update move from even to odd...
How's this:
/* In order to be able to do semaphore MBOX updates for varying number
 * of rings, it's easiest if we round up each individual update to a
 * multiple of 2 (since ring updates must always be a multiple of 2)
 * even though the actual update only requires 3 dwords.
 */

> >  }
> >  
> >  /**
> > @@ -595,19 +597,24 @@ update_mboxes(struct intel_ring_buffer *ring,
> >  static int
> >  gen6_add_request(struct intel_ring_buffer *ring)
> >  {
> > -	u32 mbox1_reg;
> > -	u32 mbox2_reg;
> > -	int ret;
> > +	struct drm_device *dev = ring->dev;
> > +	struct drm_i915_private *dev_priv = dev->dev_private;
> > +	struct intel_ring_buffer *useless;
> > +	int i, ret;
> >  
> > -	ret = intel_ring_begin(ring, 10);
> > +	ret = intel_ring_begin(ring, ((I915_NUM_RINGS-1) *
> > +				      MBOX_UPDATE_DWORDS) +
> > +				      4);
> >  	if (ret)
> >  		return ret;
> > +#undef MBOX_UPDATE_DWORDS
> >  
> > -	mbox1_reg = ring->signal_mbox[0];
> > -	mbox2_reg = ring->signal_mbox[1];
> > +	for_each_ring(useless, dev_priv, i) {
> > +		u32 mbox_reg = ring->signal_mbox[i];
> > +		if (mbox_reg != GEN6_NOSYNC)
> > +			update_mboxes(ring, mbox_reg);
> > +	}
> >  
> > -	update_mboxes(ring, mbox1_reg);
> > -	update_mboxes(ring, mbox2_reg);
> >  	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
> >  	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
> >  	intel_ring_emit(ring, ring->outstanding_lazy_request);
> > @@ -1669,8 +1676,9 @@ int intel_init_render_ring_buffer(struct drm_device *dev)
> >  		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
> >  		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
> >  		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
> > -		ring->signal_mbox[0] = GEN6_VRSYNC;
> > -		ring->signal_mbox[1] = GEN6_BRSYNC;
> > +		ring->signal_mbox[RCS] = GEN6_NOSYNC;
> > +		ring->signal_mbox[VCS] = GEN6_VRSYNC;
> > +		ring->signal_mbox[BCS] = GEN6_BRSYNC;
> >  	} else if (IS_GEN5(dev)) {
> >  		ring->add_request = pc_render_add_request;
> >  		ring->flush = gen4_render_ring_flush;
> > @@ -1828,8 +1836,9 @@ int intel_init_bsd_ring_buffer(struct drm_device *dev)
> >  		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
> >  		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
> >  		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
> > -		ring->signal_mbox[0] = GEN6_RVSYNC;
> > -		ring->signal_mbox[1] = GEN6_BVSYNC;
> > +		ring->signal_mbox[RCS] = GEN6_RVSYNC;
> > +		ring->signal_mbox[VCS] = GEN6_NOSYNC;
> > +		ring->signal_mbox[BCS] = GEN6_BVSYNC;
> >  	} else {
> >  		ring->mmio_base = BSD_RING_BASE;
> >  		ring->flush = bsd_ring_flush;
> > @@ -1874,8 +1883,9 @@ int intel_init_blt_ring_buffer(struct drm_device *dev)
> >  	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
> >  	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
> >  	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
> > -	ring->signal_mbox[0] = GEN6_RBSYNC;
> > -	ring->signal_mbox[1] = GEN6_VBSYNC;
> > +	ring->signal_mbox[RCS] = GEN6_RBSYNC;
> > +	ring->signal_mbox[VCS] = GEN6_VBSYNC;
> > +	ring->signal_mbox[BCS] = GEN6_NOSYNC;
> >  	ring->init = init_ring_common;
> >  
> >  	return intel_init_ring_buffer(dev, ring);
> > diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
> > index 785df13..f1aef0d 100644
> > --- a/drivers/gpu/drm/i915/intel_ringbuffer.h
> > +++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
> > @@ -103,7 +103,7 @@ struct  intel_ring_buffer {
> >  				   u32 seqno);
> >  
> >  	u32		semaphore_register[I915_NUM_RINGS]; /*our mbox written by others */
> > -	u32		signal_mbox[2]; /* mboxes this ring signals to */
> > +	u32		signal_mbox[I915_NUM_RINGS]; /* mboxes this ring signals to + sentinel */
> >  	/**
> >  	 * List of objects currently involved in rendering from the
> >  	 * ringbuffer.
> > -- 
> > 1.8.2.1
> > 
> > _______________________________________________
> > Intel-gfx mailing list
> > Intel-gfx@lists.freedesktop.org
> > http://lists.freedesktop.org/mailman/listinfo/intel-gfx
diff mbox

Patch

diff --git a/drivers/gpu/drm/i915/i915_reg.h b/drivers/gpu/drm/i915/i915_reg.h
index 767aa32..5be4a75 100644
--- a/drivers/gpu/drm/i915/i915_reg.h
+++ b/drivers/gpu/drm/i915/i915_reg.h
@@ -568,6 +568,7 @@ 
 #define GEN6_VRSYNC (RING_SYNC_1(GEN6_BSD_RING_BASE))
 #define GEN6_VBSYNC (RING_SYNC_0(GEN6_BSD_RING_BASE))
 #define GEN6_BRSYNC (RING_SYNC_0(BLT_RING_BASE))
+#define GEN6_NOSYNC 0
 #define GEN6_BVSYNC (RING_SYNC_1(BLT_RING_BASE))
 #define RING_MAX_IDLE(base)	((base)+0x54)
 #define RING_HWS_PGA(base)	((base)+0x80)
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.c b/drivers/gpu/drm/i915/intel_ringbuffer.c
index 38751a7..0f97547 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.c
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.c
@@ -578,9 +578,11 @@  static void
 update_mboxes(struct intel_ring_buffer *ring,
 	      u32 mmio_offset)
 {
+#define MBOX_UPDATE_DWORDS 4
 	intel_ring_emit(ring, MI_LOAD_REGISTER_IMM(1));
 	intel_ring_emit(ring, mmio_offset);
 	intel_ring_emit(ring, ring->outstanding_lazy_request);
+	intel_ring_emit(ring, MI_NOOP);
 }
 
 /**
@@ -595,19 +597,24 @@  update_mboxes(struct intel_ring_buffer *ring,
 static int
 gen6_add_request(struct intel_ring_buffer *ring)
 {
-	u32 mbox1_reg;
-	u32 mbox2_reg;
-	int ret;
+	struct drm_device *dev = ring->dev;
+	struct drm_i915_private *dev_priv = dev->dev_private;
+	struct intel_ring_buffer *useless;
+	int i, ret;
 
-	ret = intel_ring_begin(ring, 10);
+	ret = intel_ring_begin(ring, ((I915_NUM_RINGS-1) *
+				      MBOX_UPDATE_DWORDS) +
+				      4);
 	if (ret)
 		return ret;
+#undef MBOX_UPDATE_DWORDS
 
-	mbox1_reg = ring->signal_mbox[0];
-	mbox2_reg = ring->signal_mbox[1];
+	for_each_ring(useless, dev_priv, i) {
+		u32 mbox_reg = ring->signal_mbox[i];
+		if (mbox_reg != GEN6_NOSYNC)
+			update_mboxes(ring, mbox_reg);
+	}
 
-	update_mboxes(ring, mbox1_reg);
-	update_mboxes(ring, mbox2_reg);
 	intel_ring_emit(ring, MI_STORE_DWORD_INDEX);
 	intel_ring_emit(ring, I915_GEM_HWS_INDEX << MI_STORE_DWORD_INDEX_SHIFT);
 	intel_ring_emit(ring, ring->outstanding_lazy_request);
@@ -1669,8 +1676,9 @@  int intel_init_render_ring_buffer(struct drm_device *dev)
 		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_RV;
 		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_RB;
-		ring->signal_mbox[0] = GEN6_VRSYNC;
-		ring->signal_mbox[1] = GEN6_BRSYNC;
+		ring->signal_mbox[RCS] = GEN6_NOSYNC;
+		ring->signal_mbox[VCS] = GEN6_VRSYNC;
+		ring->signal_mbox[BCS] = GEN6_BRSYNC;
 	} else if (IS_GEN5(dev)) {
 		ring->add_request = pc_render_add_request;
 		ring->flush = gen4_render_ring_flush;
@@ -1828,8 +1836,9 @@  int intel_init_bsd_ring_buffer(struct drm_device *dev)
 		ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_VR;
 		ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_INVALID;
 		ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_VB;
-		ring->signal_mbox[0] = GEN6_RVSYNC;
-		ring->signal_mbox[1] = GEN6_BVSYNC;
+		ring->signal_mbox[RCS] = GEN6_RVSYNC;
+		ring->signal_mbox[VCS] = GEN6_NOSYNC;
+		ring->signal_mbox[BCS] = GEN6_BVSYNC;
 	} else {
 		ring->mmio_base = BSD_RING_BASE;
 		ring->flush = bsd_ring_flush;
@@ -1874,8 +1883,9 @@  int intel_init_blt_ring_buffer(struct drm_device *dev)
 	ring->semaphore_register[RCS] = MI_SEMAPHORE_SYNC_BR;
 	ring->semaphore_register[VCS] = MI_SEMAPHORE_SYNC_BV;
 	ring->semaphore_register[BCS] = MI_SEMAPHORE_SYNC_INVALID;
-	ring->signal_mbox[0] = GEN6_RBSYNC;
-	ring->signal_mbox[1] = GEN6_VBSYNC;
+	ring->signal_mbox[RCS] = GEN6_RBSYNC;
+	ring->signal_mbox[VCS] = GEN6_VBSYNC;
+	ring->signal_mbox[BCS] = GEN6_NOSYNC;
 	ring->init = init_ring_common;
 
 	return intel_init_ring_buffer(dev, ring);
diff --git a/drivers/gpu/drm/i915/intel_ringbuffer.h b/drivers/gpu/drm/i915/intel_ringbuffer.h
index 785df13..f1aef0d 100644
--- a/drivers/gpu/drm/i915/intel_ringbuffer.h
+++ b/drivers/gpu/drm/i915/intel_ringbuffer.h
@@ -103,7 +103,7 @@  struct  intel_ring_buffer {
 				   u32 seqno);
 
 	u32		semaphore_register[I915_NUM_RINGS]; /*our mbox written by others */
-	u32		signal_mbox[2]; /* mboxes this ring signals to */
+	u32		signal_mbox[I915_NUM_RINGS]; /* mboxes this ring signals to + sentinel */
 	/**
 	 * List of objects currently involved in rendering from the
 	 * ringbuffer.