[PATCH v4 5/5] drm/vc4: dsi: Recover from a timed-out transfer

[Henry Zhang]

When a transfer times out, vc4_dsi_host_transfer() disables the
command, resets the FIFOs and returns -ETIMEDOUT. That is not always
enough: after an LP receive timeout during a read (the peripheral did
not complete the bus turnaround), every following transfer times out
as well, with no interrupt and STAT reading back 0. Only a modeset,
which goes through post_disable/pre_enable, brings the block back.

Reset the DSI block and its analog front end after a timeout and restore
the configuration programmed in pre_enable, in the same order as
pre_enable: the block is ungated and the AFE released only after the
timings are programmed. Keep the interrupt handler out with
disable_irq() until the block is restored and INT_STAT is cleared, so
that neither a late completion interrupt of the timed-out transfer nor
an error interrupt raised during the reset can complete the next
transfer or run in the middle of the reset. Also mask the interrupts
until the AFE is out of reset: the error interrupts otherwise fire
continuously while it is held in reset. The timed-out message is not
resent, as it may already have been executed by the peripheral; the
error is returned and the caller decides whether to retry.

Only do this while the block is enabled. Between post_disable and
pre_enable the clocks are off and there is nothing to restore; a
transfer then times out as before. The transfer lock keeps the
recovery from running in the middle of pre_enable or post_disable.

This does not prevent the timeouts themselves. With video running,
vc4 does not keep commands within vertical blanking, and transfers can
still time out, sometimes several in a row after a reset. That is a
separate issue.

Signed-off-by: Henry Zhang <henryzhang62@xxxxxxxxx>
---
 drivers/gpu/drm/vc4/vc4_dsi.c | 136 ++++++++++++++++++++++++++++++++--
 1 file changed, 129 insertions(+), 7 deletions(-)

diff --git a/drivers/gpu/drm/vc4/vc4_dsi.c b/drivers/gpu/drm/vc4/vc4_dsi.c
index 3ee6e8e86..6edda74e1 100644
--- a/drivers/gpu/drm/vc4/vc4_dsi.c
+++ b/drivers/gpu/drm/vc4/vc4_dsi.c
@@ -601,8 +601,11 @@ struct vc4_dsi {
 	 * bridge enable/disable paths, which reprogram the block.
 	 */
 	struct mutex transfer_lock;
+	/* The block is powered and configured. Protected by transfer_lock. */
+	bool enabled;
 	struct completion xfer_completion;
 	int xfer_result;
+	int irq;
 
 	struct debugfs_regset32 regset;
 };
@@ -826,6 +829,8 @@ static void vc4_dsi_bridge_post_disable(struct drm_bridge *bridge,
 
 	guard(mutex)(&dsi->transfer_lock);
 
+	dsi->enabled = false;
+
 	clk_disable_unprepare(dsi->pll_phy_clock);
 	clk_disable_unprepare(dsi->escape_clock);
 	clk_disable_unprepare(dsi->pixel_clock);
@@ -1151,6 +1156,8 @@ static void vc4_dsi_bridge_pre_enable(struct drm_bridge *bridge,
 		DSI_PORT_WRITE(DISP0_CTRL,
 			       DSI_DISP0_COMMAND_MODE);
 	}
+
+	dsi->enabled = true;
 }
 
 static void vc4_dsi_bridge_enable(struct drm_bridge *bridge,
@@ -1184,10 +1191,9 @@ static int vc4_dsi_bridge_attach(struct drm_bridge *bridge,
 				 &dsi->bridge, flags);
 }
 
-static ssize_t vc4_dsi_host_transfer(struct mipi_dsi_host *host,
-				     const struct mipi_dsi_msg *msg)
+static ssize_t vc4_dsi_transfer(struct vc4_dsi *dsi,
+				const struct mipi_dsi_msg *msg)
 {
-	struct vc4_dsi *dsi = host_to_dsi(host);
 	struct drm_device *drm = dsi->bridge.dev;
 	struct mipi_dsi_packet packet;
 	u32 pkth = 0, pktc = 0;
@@ -1195,8 +1201,6 @@ static ssize_t vc4_dsi_host_transfer(struct mipi_dsi_host *host,
 	bool is_long = mipi_dsi_packet_format_is_long(msg->type);
 	u32 cmd_fifo_len = 0, pix_fifo_len = 0;
 
-	guard(mutex)(&dsi->transfer_lock);
-
 	mipi_dsi_create_packet(&packet, msg);
 
 	pkth |= VC4_SET_FIELD(packet.header[0], DSI_TXPKT1H_BC_DT);
@@ -1374,6 +1378,120 @@ static ssize_t vc4_dsi_host_transfer(struct mipi_dsi_host *host,
 	return ret;
 }
 
+/*
+ * Reset the DSI block and its analog front end, then restore the
+ * configuration done in pre_enable. Resetting the FIFOs alone does not
+ * clear the state the block can be left in after a transfer timed out
+ * (e.g. on an LP receive timeout): every following transfer then times
+ * out as well, until the next modeset.
+ */
+static void vc4_dsi_reset_and_restore(struct vc4_dsi *dsi)
+{
+	u32 en = dsi->variant->port ? DSI1_CTRL_EN : DSI0_CTRL_CTRL0;
+	u32 ctrl = DSI_PORT_READ(CTRL);
+	u32 afec0 = DSI_PORT_READ(PHY_AFEC0);
+	u32 afec1 = DSI_PORT_READ(PHY_AFEC1);
+	u32 disp0 = DSI_PORT_READ(DISP0_CTRL) & ~DSI_DISP0_ENABLE;
+	u32 disp1 = DSI_PORT_READ(DISP1_CTRL);
+	u32 hstx_to = DSI_PORT_READ(HSTX_TO_CNT);
+	u32 lprx_to = DSI_PORT_READ(LPRX_TO_CNT);
+	u32 ta_to = DSI_PORT_READ(TA_TO_CNT);
+	u32 pr_to = DSI_PORT_READ(PR_TO_CNT);
+	u32 phyc = DSI_PORT_READ(PHYC);
+	u32 clt0 = DSI_PORT_READ(HS_CLT0);
+	u32 clt1 = DSI_PORT_READ(HS_CLT1);
+	u32 clt2 = DSI_PORT_READ(HS_CLT2);
+	u32 dlt3 = DSI_PORT_READ(HS_DLT3);
+	u32 dlt4 = DSI_PORT_READ(HS_DLT4);
+	u32 dlt5 = DSI_PORT_READ(HS_DLT5);
+	u32 dlt6 = DSI_PORT_READ(HS_DLT6);
+	u32 dlt7 = DSI_PORT_READ(HS_DLT7);
+
+	/*
+	 * Mask the interrupts while the block and its AFE are in reset: the
+	 * error interrupts would otherwise fire continuously.
+	 */
+	DSI_PORT_WRITE(INT_EN, 0);
+	DSI_PORT_WRITE(DISP0_CTRL, disp0);
+	DSI_PORT_WRITE(TXPKT1C, 0);
+	DSI_PORT_WRITE(CTRL, DSI_CTRL_SOFT_RESET_CFG |
+		       DSI_PORT_BIT(CTRL_RESET_FIFOS));
+	DSI_PORT_WRITE(PHY_AFEC0, afec0 | DSI_PORT_BIT(PHY_AFEC0_RESET));
+	/* AFEC reset hold time */
+	mdelay(1);
+
+	/*
+	 * Same order as pre_enable: the block stays gated and the AFE in
+	 * reset until the timings are programmed.
+	 */
+	DSI_PORT_WRITE(CTRL, ctrl & ~(DSI_CTRL_CAL_BYTE | en));
+	DSI_PORT_WRITE(STAT, DSI_PORT_READ(STAT));
+	DSI_PORT_WRITE(PHY_AFEC1, afec1);
+	DSI_PORT_WRITE(HS_CLT0, clt0);
+	DSI_PORT_WRITE(HS_CLT1, clt1);
+	DSI_PORT_WRITE(HS_CLT2, clt2);
+	DSI_PORT_WRITE(HS_DLT3, dlt3);
+	DSI_PORT_WRITE(HS_DLT4, dlt4);
+	DSI_PORT_WRITE(HS_DLT5, dlt5);
+	DSI_PORT_WRITE(HS_DLT6, dlt6);
+	DSI_PORT_WRITE(HS_DLT7, dlt7);
+	DSI_PORT_WRITE(PHYC, phyc);
+	DSI_PORT_WRITE(CTRL, ctrl & ~en);
+	DSI_PORT_WRITE(HSTX_TO_CNT, hstx_to);
+	DSI_PORT_WRITE(LPRX_TO_CNT, lprx_to);
+	DSI_PORT_WRITE(TA_TO_CNT, ta_to);
+	DSI_PORT_WRITE(PR_TO_CNT, pr_to);
+	DSI_PORT_WRITE(DISP1_CTRL, disp1);
+	/* Ungate the block. */
+	DSI_PORT_WRITE(CTRL, ctrl);
+	/* Bring AFE out of reset. */
+	DSI_PORT_WRITE(PHY_AFEC0, afec0 & ~DSI_PORT_BIT(PHY_AFEC0_RESET));
+	DSI_PORT_WRITE(DISP0_CTRL, disp0);
+
+	DSI_PORT_WRITE(INT_STAT, DSI_PORT_READ(INT_STAT));
+	DSI_PORT_WRITE(INT_EN, DSI_PORT_BIT(INTERRUPTS_ALWAYS_ENABLED));
+}
+
+static ssize_t vc4_dsi_host_transfer(struct mipi_dsi_host *host,
+				     const struct mipi_dsi_msg *msg)
+{
+	struct vc4_dsi *dsi = host_to_dsi(host);
+	u32 disp0_ctrl;
+	ssize_t ret;
+
+	guard(mutex)(&dsi->transfer_lock);
+
+	ret = vc4_dsi_transfer(dsi, msg);
+	/* Only a running block can be reset and restored. */
+	if (ret != -ETIMEDOUT || !dsi->enabled)
+		return ret;
+
+	/*
+	 * Leave the block usable for the next transfer. The message is not
+	 * resent: it may already have reached the peripheral, and only the
+	 * caller knows whether it is safe to repeat.
+	 */
+	disp0_ctrl = DSI_PORT_READ(DISP0_CTRL);
+	dev_warn(&dsi->pdev->dev,
+		 "transfer timed out (stat 0x%08x), resetting DSI\n",
+		 DSI_PORT_READ(STAT));
+	/*
+	 * Keep the interrupt handler out until the block is restored and
+	 * INT_STAT is cleared. The error interrupts are still enabled, and
+	 * a handler running during the reset could complete the next
+	 * transfer, or race with the register writes on DSI1 of the
+	 * BCM2835, where both go through the DMA workaround. disable_irq()
+	 * also waits for a late completion interrupt of the timed-out
+	 * transfer.
+	 */
+	disable_irq(dsi->irq);
+	vc4_dsi_reset_and_restore(dsi);
+	DSI_PORT_WRITE(DISP0_CTRL, disp0_ctrl);
+	enable_irq(dsi->irq);
+
+	return ret;
+}
+
 static const struct component_ops vc4_dsi_ops;
 static int vc4_dsi_host_attach(struct mipi_dsi_host *host,
 			       struct mipi_dsi_device *device)
@@ -1743,14 +1861,18 @@ static int vc4_dsi_bind(struct device *dev, struct device *master, void *data)
 	/* Clear any existing interrupt state. */
 	DSI_PORT_WRITE(INT_STAT, DSI_PORT_READ(INT_STAT));
 
+	dsi->irq = platform_get_irq(pdev, 0);
+	if (dsi->irq < 0)
+		return dsi->irq;
+
 	if (dsi->reg_dma_mem)
-		ret = devm_request_threaded_irq(dev, platform_get_irq(pdev, 0),
+		ret = devm_request_threaded_irq(dev, dsi->irq,
 						vc4_dsi_irq_defer_to_thread_handler,
 						vc4_dsi_irq_handler,
 						IRQF_ONESHOT,
 						"vc4 dsi", dsi);
 	else
-		ret = devm_request_irq(dev, platform_get_irq(pdev, 0),
+		ret = devm_request_irq(dev, dsi->irq,
 				       vc4_dsi_irq_handler, 0, "vc4 dsi", dsi);
 	if (ret) {
 		if (ret != -EPROBE_DEFER)
-- 
2.47.3