openwrtv3/target/linux/brcm2708/patches-4.4/0456-drm-vc4-Implement-precise-vblank-timestamping.patch

From d1a9a03cbe1110756a63d4a3747e22eb8417f75e Mon Sep 17 00:00:00 2001
From: Mario Kleiner <mario.kleiner.de@gmail.com>
Date: Thu, 23 Jun 2016 08:17:50 +0200
Subject: [PATCH] drm/vc4: Implement precise vblank timestamping.

Precise vblank timestamping is implemented via the
usual scanout position based method. On VC4 the
pixelvalves PV do not have a scanout position
register. Only the hardware video scaler HVS has a
similar register which describes which scanline for
the output is currently composited and stored in the
HVS fifo for later consumption by the PV.

This causes a problem in that the HVS runs at a much
faster clock (system clock / audio gate) than the PV
which runs at video mode dot clock, so the unless the
fifo between HVS and PV is full, the HVS will progress
faster in its observable read line position than video
scan rate, so the HVS position reading can't be directly
translated into a scanout position for timestamp correction.

Additionally when the PV is in vblank, it doesn't consume
from the fifo, so the fifo gets full very quickly and then
the HVS stops compositing until the PV enters active scanout
and starts consuming scanlines from the fifo again, making
new space for the HVS to composite.

Therefore a simple translation of HVS read position into
elapsed time since (or to) start of active scanout does
not work, but for the most interesting cases we can still
get useful and sufficiently accurate results:

1. The PV enters active scanout of a new frame with the
   fifo of the HVS completely full, and the HVS can refill
   any fifo line which gets consumed and thereby freed up by
   the PV during active scanout very quickly. Therefore the
   PV and HVS work effectively in lock-step during active
   scanout with the fifo never having more than 1 scanline
   freed up by the PV before it gets refilled. The PV's
   real scanout position is therefore trailing the HVS
   compositing position as scanoutpos = hvspos - fifosize
   and we can get the true scanoutpos as HVS readpos minus
   fifo size, so precise timestamping works while in active
   scanout, except for the last few scanlines of the frame,
   when the HVS reaches end of frame, stops compositing and
   the PV catches up and drains the fifo. This special case
   would only introduce minor errors though.

2. If we are in vblank, then we can only guess something
   reasonable. If called from vblank irq, we assume the irq is
   usually dispatched with minimum delay, so we can take a
   timestamp taken at entry into the vblank irq handler as a
   baseline and then add a full vblank duration until the
   guessed start of active scanout. As irq dispatch is usually
   pretty low latency this works with relatively low jitter and
   good results.

   If we aren't called from vblank then we could be anywhere
   within the vblank interval, so we return a neutral result,
   simply the current system timestamp, and hope for the best.

Measurement shows the generated timestamps to be rather precise,
and at least never off more than 1 vblank duration worst-case.

Limitations: Doesn't work well yet for interlaced video modes,
             therefore disabled in interlaced mode for now.

v2: Use the DISPBASE registers to determine the FIFO size (changes
    by anholt)

Signed-off-by: Mario Kleiner <mario.kleiner.de@gmail.com>
Signed-off-by: Eric Anholt <eric@anholt.net>
Reviewed-and-tested-by: Mario Kleiner <mario.kleiner.de@gmail.com> (v2)
(cherry picked from commit 1bf59f1dcbe25272f6b5d870054647e58a8a9c55)
---
 drivers/gpu/drm/vc4/vc4_crtc.c | 162 +++++++++++++++++++++++++++++++++++++++++
 drivers/gpu/drm/vc4/vc4_drv.c  |   2 +
 drivers/gpu/drm/vc4/vc4_drv.h  |   7 ++
 drivers/gpu/drm/vc4/vc4_regs.h |  22 +++++-
 4 files changed, 192 insertions(+), 1 deletion(-)

--- a/drivers/gpu/drm/vc4/vc4_crtc.c
+++ b/drivers/gpu/drm/vc4/vc4_crtc.c
@@ -47,12 +47,17 @@ struct vc4_crtc {
 	const struct vc4_crtc_data *data;
 	void __iomem *regs;
 
+	/* Timestamp at start of vblank irq - unaffected by lock delays. */
+	ktime_t t_vblank;
+
 	/* Which HVS channel we're using for our CRTC. */
 	int channel;
 
 	u8 lut_r[256];
 	u8 lut_g[256];
 	u8 lut_b[256];
+	/* Size in pixels of the COB memory allocated to this CRTC. */
+	u32 cob_size;
 
 	struct drm_pending_vblank_event *event;
 };
@@ -134,6 +139,144 @@ int vc4_crtc_debugfs_regs(struct seq_fil
 }
 #endif
 
+int vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
+			    unsigned int flags, int *vpos, int *hpos,
+			    ktime_t *stime, ktime_t *etime,
+			    const struct drm_display_mode *mode)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc = vc4->crtc[crtc_id];
+	u32 val;
+	int fifo_lines;
+	int vblank_lines;
+	int ret = 0;
+
+	/*
+	 * XXX Doesn't work well in interlaced mode yet, partially due
+	 * to problems in vc4 kms or drm core interlaced mode handling,
+	 * so disable for now in interlaced mode.
+	 */
+	if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+		return ret;
+
+	/* preempt_disable_rt() should go right here in PREEMPT_RT patchset. */
+
+	/* Get optional system timestamp before query. */
+	if (stime)
+		*stime = ktime_get();
+
+	/*
+	 * Read vertical scanline which is currently composed for our
+	 * pixelvalve by the HVS, and also the scaler status.
+	 */
+	val = HVS_READ(SCALER_DISPSTATX(vc4_crtc->channel));
+
+	/* Get optional system timestamp after query. */
+	if (etime)
+		*etime = ktime_get();
+
+	/* preempt_enable_rt() should go right here in PREEMPT_RT patchset. */
+
+	/* Vertical position of hvs composed scanline. */
+	*vpos = VC4_GET_FIELD(val, SCALER_DISPSTATX_LINE);
+
+	/* No hpos info available. */
+	if (hpos)
+		*hpos = 0;
+
+	/* This is the offset we need for translating hvs -> pv scanout pos. */
+	fifo_lines = vc4_crtc->cob_size / mode->crtc_hdisplay;
+
+	if (fifo_lines > 0)
+		ret |= DRM_SCANOUTPOS_VALID;
+
+	/* HVS more than fifo_lines into frame for compositing? */
+	if (*vpos > fifo_lines) {
+		/*
+		 * We are in active scanout and can get some meaningful results
+		 * from HVS. The actual PV scanout can not trail behind more
+		 * than fifo_lines as that is the fifo's capacity. Assume that
+		 * in active scanout the HVS and PV work in lockstep wrt. HVS
+		 * refilling the fifo and PV consuming from the fifo, ie.
+		 * whenever the PV consumes and frees up a scanline in the
+		 * fifo, the HVS will immediately refill it, therefore
+		 * incrementing vpos. Therefore we choose HVS read position -
+		 * fifo size in scanlines as a estimate of the real scanout
+		 * position of the PV.
+		 */
+		*vpos -= fifo_lines + 1;
+		if (mode->flags & DRM_MODE_FLAG_INTERLACE)
+			*vpos /= 2;
+
+		ret |= DRM_SCANOUTPOS_ACCURATE;
+		return ret;
+	}
+
+	/*
+	 * Less: This happens when we are in vblank and the HVS, after getting
+	 * the VSTART restart signal from the PV, just started refilling its
+	 * fifo with new lines from the top-most lines of the new framebuffers.
+	 * The PV does not scan out in vblank, so does not remove lines from
+	 * the fifo, so the fifo will be full quickly and the HVS has to pause.
+	 * We can't get meaningful readings wrt. scanline position of the PV
+	 * and need to make things up in a approximative but consistent way.
+	 */
+	ret |= DRM_SCANOUTPOS_IN_VBLANK;
+	vblank_lines = mode->crtc_vtotal - mode->crtc_vdisplay;
+
+	if (flags & DRM_CALLED_FROM_VBLIRQ) {
+		/*
+		 * Assume the irq handler got called close to first
+		 * line of vblank, so PV has about a full vblank
+		 * scanlines to go, and as a base timestamp use the
+		 * one taken at entry into vblank irq handler, so it
+		 * is not affected by random delays due to lock
+		 * contention on event_lock or vblank_time lock in
+		 * the core.
+		 */
+		*vpos = -vblank_lines;
+
+		if (stime)
+			*stime = vc4_crtc->t_vblank;
+		if (etime)
+			*etime = vc4_crtc->t_vblank;
+
+		/*
+		 * If the HVS fifo is not yet full then we know for certain
+		 * we are at the very beginning of vblank, as the hvs just
+		 * started refilling, and the stime and etime timestamps
+		 * truly correspond to start of vblank.
+		 */
+		if ((val & SCALER_DISPSTATX_FULL) != SCALER_DISPSTATX_FULL)
+			ret |= DRM_SCANOUTPOS_ACCURATE;
+	} else {
+		/*
+		 * No clue where we are inside vblank. Return a vpos of zero,
+		 * which will cause calling code to just return the etime
+		 * timestamp uncorrected. At least this is no worse than the
+		 * standard fallback.
+		 */
+		*vpos = 0;
+	}
+
+	return ret;
+}
+
+int vc4_crtc_get_vblank_timestamp(struct drm_device *dev, unsigned int crtc_id,
+				  int *max_error, struct timeval *vblank_time,
+				  unsigned flags)
+{
+	struct vc4_dev *vc4 = to_vc4_dev(dev);
+	struct vc4_crtc *vc4_crtc = vc4->crtc[crtc_id];
+	struct drm_crtc *crtc = &vc4_crtc->base;
+	struct drm_crtc_state *state = crtc->state;
+
+	/* Helper routine in DRM core does all the work: */
+	return drm_calc_vbltimestamp_from_scanoutpos(dev, crtc_id, max_error,
+						     vblank_time, flags,
+						     &state->adjusted_mode);
+}
+
 static void vc4_crtc_destroy(struct drm_crtc *crtc)
 {
 	drm_crtc_cleanup(crtc);
@@ -535,6 +678,7 @@ static irqreturn_t vc4_crtc_irq_handler(
 	irqreturn_t ret = IRQ_NONE;
 
 	if (stat & PV_INT_VFP_START) {
+		vc4_crtc->t_vblank = ktime_get();
 		CRTC_WRITE(PV_INTSTAT, PV_INT_VFP_START);
 		drm_crtc_handle_vblank(&vc4_crtc->base);
 		vc4_crtc_handle_page_flip(vc4_crtc);
@@ -759,6 +903,22 @@ static void vc4_set_crtc_possible_masks(
 	}
 }
 
+static void
+vc4_crtc_get_cob_allocation(struct vc4_crtc *vc4_crtc)
+{
+	struct drm_device *drm = vc4_crtc->base.dev;
+	struct vc4_dev *vc4 = to_vc4_dev(drm);
+	u32 dispbase = HVS_READ(SCALER_DISPBASEX(vc4_crtc->channel));
+	/* Top/base are supposed to be 4-pixel aligned, but the
+	 * Raspberry Pi firmware fills the low bits (which are
+	 * presumably ignored).
+	 */
+	u32 top = VC4_GET_FIELD(dispbase, SCALER_DISPBASEX_TOP) & ~3;
+	u32 base = VC4_GET_FIELD(dispbase, SCALER_DISPBASEX_BASE) & ~3;
+
+	vc4_crtc->cob_size = top - base + 4;
+}
+
 static int vc4_crtc_bind(struct device *dev, struct device *master, void *data)
 {
 	struct platform_device *pdev = to_platform_device(dev);
@@ -835,6 +995,8 @@ static int vc4_crtc_bind(struct device *
 		crtc->cursor = cursor_plane;
 	}
 
+	vc4_crtc_get_cob_allocation(vc4_crtc);
+
 	CRTC_WRITE(PV_INTEN, 0);
 	CRTC_WRITE(PV_INTSTAT, PV_INT_VFP_START);
 	ret = devm_request_irq(dev, platform_get_irq(pdev, 0),
--- a/drivers/gpu/drm/vc4/vc4_drv.c
+++ b/drivers/gpu/drm/vc4/vc4_drv.c
@@ -116,6 +116,8 @@ static struct drm_driver vc4_drm_driver
 	.enable_vblank = vc4_enable_vblank,
 	.disable_vblank = vc4_disable_vblank,
 	.get_vblank_counter = drm_vblank_no_hw_counter,
+	.get_scanout_position = vc4_crtc_get_scanoutpos,
+	.get_vblank_timestamp = vc4_crtc_get_vblank_timestamp,
 
 #if defined(CONFIG_DEBUG_FS)
 	.debugfs_init = vc4_debugfs_init,
--- a/drivers/gpu/drm/vc4/vc4_drv.h
+++ b/drivers/gpu/drm/vc4/vc4_drv.h
@@ -419,6 +419,13 @@ int vc4_enable_vblank(struct drm_device
 void vc4_disable_vblank(struct drm_device *dev, unsigned int crtc_id);
 void vc4_cancel_page_flip(struct drm_crtc *crtc, struct drm_file *file);
 int vc4_crtc_debugfs_regs(struct seq_file *m, void *arg);
+int vc4_crtc_get_scanoutpos(struct drm_device *dev, unsigned int crtc_id,
+			    unsigned int flags, int *vpos, int *hpos,
+			    ktime_t *stime, ktime_t *etime,
+			    const struct drm_display_mode *mode);
+int vc4_crtc_get_vblank_timestamp(struct drm_device *dev, unsigned int crtc_id,
+				  int *max_error, struct timeval *vblank_time,
+				  unsigned flags);
 
 /* vc4_debugfs.c */
 int vc4_debugfs_init(struct drm_minor *minor);
--- a/drivers/gpu/drm/vc4/vc4_regs.h
+++ b/drivers/gpu/drm/vc4/vc4_regs.h
@@ -368,7 +368,6 @@
 # define SCALER_DISPBKGND_FILL			BIT(24)
 
 #define SCALER_DISPSTAT0                        0x00000048
-#define SCALER_DISPBASE0                        0x0000004c
 # define SCALER_DISPSTATX_MODE_MASK		VC4_MASK(31, 30)
 # define SCALER_DISPSTATX_MODE_SHIFT		30
 # define SCALER_DISPSTATX_MODE_DISABLED		0
@@ -377,6 +376,24 @@
 # define SCALER_DISPSTATX_MODE_EOF		3
 # define SCALER_DISPSTATX_FULL			BIT(29)
 # define SCALER_DISPSTATX_EMPTY			BIT(28)
+# define SCALER_DISPSTATX_FRAME_COUNT_MASK	VC4_MASK(17, 12)
+# define SCALER_DISPSTATX_FRAME_COUNT_SHIFT	12
+# define SCALER_DISPSTATX_LINE_MASK		VC4_MASK(11, 0)
+# define SCALER_DISPSTATX_LINE_SHIFT		0
+
+#define SCALER_DISPBASE0                        0x0000004c
+/* Last pixel in the COB (display FIFO memory) allocated to this HVS
+ * channel.  Must be 4-pixel aligned (and thus 4 pixels less than the
+ * next COB base).
+ */
+# define SCALER_DISPBASEX_TOP_MASK		VC4_MASK(31, 16)
+# define SCALER_DISPBASEX_TOP_SHIFT		16
+/* First pixel in the COB (display FIFO memory) allocated to this HVS
+ * channel.  Must be 4-pixel aligned.
+ */
+# define SCALER_DISPBASEX_BASE_MASK		VC4_MASK(15, 0)
+# define SCALER_DISPBASEX_BASE_SHIFT		0
+
 #define SCALER_DISPCTRL1                        0x00000050
 #define SCALER_DISPBKGND1                       0x00000054
 #define SCALER_DISPBKGNDX(x)			(SCALER_DISPBKGND0 +        \
@@ -387,6 +404,9 @@
 						 (x) * (SCALER_DISPSTAT1 - \
 							SCALER_DISPSTAT0))
 #define SCALER_DISPBASE1                        0x0000005c
+#define SCALER_DISPBASEX(x)			(SCALER_DISPBASE0 +        \
+						 (x) * (SCALER_DISPBASE1 - \
+							SCALER_DISPBASE0))
 #define SCALER_DISPCTRL2                        0x00000060
 #define SCALER_DISPCTRLX(x)			(SCALER_DISPCTRL0 +        \
 						 (x) * (SCALER_DISPCTRL1 - \