Merge tag 'mailbox-v5.7' of git://git.linaro.org/landing-teams/working/fujitsu/integration

Pull mailbox updates from Jassi Brar:

 - imx: add support for i.MX8/8X to existing driver

 - mediatek: drop the atomix execution feature, add flush

 - allwinner: new 'msgbox' controller driver

 - armada: misc: drop redundant error print

 - bcm: misc: catch error in probe and snprintf buffer overflow

* tag 'mailbox-v5.7' of git://git.linaro.org/landing-teams/working/fujitsu/integration:
  mailbox: imx: add SCU MU support
  mailbox: imx: restructure code to make easy for new MU
  dt-bindings: mailbox: imx-mu: add SCU MU support
  mailbox: mediatek: remove implementation related to atomic_exec
  mailbox: mediatek: implement flush function
  dt-binding: gce: remove atomic_exec in mboxes property
  maillbox: bcm-flexrm-mailbox: handle cmpl_pool dma allocation failure
  mailbox: sun6i-msgbox: Add a new mailbox driver
  dt-bindings: mailbox: Add a binding for the sun6i msgbox
  mailbox: bcm-pdc: Use scnprintf() for avoiding potential buffer overflow
  mailbox:armada-37xx-rwtm:remove duplicate print in armada_37xx_mbox_probe()

8 files changed, 647 insertions, 136 deletions

diff --git a/drivers/mailbox/Kconfig b/drivers/mailbox/Kconfig
index ab4eb750bbdd..5a577a6734cf 100644
--- a/drivers/mailbox/Kconfig
+++ b/drivers/mailbox/Kconfig
@@ -227,4 +227,13 @@ config ZYNQMP_IPI_MBOX
 	  message to the IPI buffer and will access the IPI control
 	  registers to kick the other processor or enquire status.
 
+config SUN6I_MSGBOX
+	tristate "Allwinner sun6i/sun8i/sun9i/sun50i Message Box"
+	depends on ARCH_SUNXI || COMPILE_TEST
+	default ARCH_SUNXI
+	help
+	  Mailbox implementation for the hardware message box present in
+	  various Allwinner SoCs. This mailbox is used for communication
+	  between the application CPUs and the power management coprocessor.
+
 endif
diff --git a/drivers/mailbox/Makefile b/drivers/mailbox/Makefile
index c22fad6f696b..2e4364ef5c47 100644
--- a/drivers/mailbox/Makefile
+++ b/drivers/mailbox/Makefile
@@ -48,3 +48,5 @@ obj-$(CONFIG_STM32_IPCC) 	+= stm32-ipcc.o
 obj-$(CONFIG_MTK_CMDQ_MBOX)	+= mtk-cmdq-mailbox.o
 
 obj-$(CONFIG_ZYNQMP_IPI_MBOX)	+= zynqmp-ipi-mailbox.o
+
+obj-$(CONFIG_SUN6I_MSGBOX)	+= sun6i-msgbox.o
diff --git a/drivers/mailbox/armada-37xx-rwtm-mailbox.c b/drivers/mailbox/armada-37xx-rwtm-mailbox.c
index 02b7b28e6969..9f2ce7f03c67 100644
--- a/drivers/mailbox/armada-37xx-rwtm-mailbox.c
+++ b/drivers/mailbox/armada-37xx-rwtm-mailbox.c
@@ -156,16 +156,12 @@ static int armada_37xx_mbox_probe(struct platform_device *pdev)
 		return -ENOMEM;
 
 	mbox->base = devm_platform_ioremap_resource(pdev, 0);
-	if (IS_ERR(mbox->base)) {
-		dev_err(&pdev->dev, "ioremap failed\n");
+	if (IS_ERR(mbox->base))
 		return PTR_ERR(mbox->base);
-	}
 
 	mbox->irq = platform_get_irq(pdev, 0);
-	if (mbox->irq < 0) {
-		dev_err(&pdev->dev, "Cannot get irq\n");
+	if (mbox->irq < 0)
 		return mbox->irq;
-	}
 
 	mbox->dev = &pdev->dev;
 
diff --git a/drivers/mailbox/bcm-flexrm-mailbox.c b/drivers/mailbox/bcm-flexrm-mailbox.c
index 8ee9db274802..bee33abb5308 100644
--- a/drivers/mailbox/bcm-flexrm-mailbox.c
+++ b/drivers/mailbox/bcm-flexrm-mailbox.c
@@ -1599,6 +1599,7 @@ static int flexrm_mbox_probe(struct platform_device *pdev)
 					  1 << RING_CMPL_ALIGN_ORDER, 0);
 	if (!mbox->cmpl_pool) {
 		ret = -ENOMEM;
+		goto fail_destroy_bd_pool;
 	}
 
 	/* Allocate platform MSIs for each ring */
@@ -1661,6 +1662,7 @@ fail_free_debugfs_root:
 	platform_msi_domain_free_irqs(dev);
 fail_destroy_cmpl_pool:
 	dma_pool_destroy(mbox->cmpl_pool);
+fail_destroy_bd_pool:
 	dma_pool_destroy(mbox->bd_pool);
 fail:
 	return ret;
diff --git a/drivers/mailbox/bcm-pdc-mailbox.c b/drivers/mailbox/bcm-pdc-mailbox.c
index fcb3b18a0678..c10a9318a4b7 100644
--- a/drivers/mailbox/bcm-pdc-mailbox.c
+++ b/drivers/mailbox/bcm-pdc-mailbox.c
@@ -436,33 +436,33 @@ static ssize_t pdc_debugfs_read(struct file *filp, char __user *ubuf,
 
 	pdcs = filp->private_data;
 	out_offset = 0;
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "SPU %u stats:\n", pdcs->pdc_idx);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "PDC requests....................%u\n",
 			       pdcs->pdc_requests);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "PDC responses...................%u\n",
 			       pdcs->pdc_replies);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "Tx not done.....................%u\n",
 			       pdcs->last_tx_not_done);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "Tx ring full....................%u\n",
 			       pdcs->tx_ring_full);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "Rx ring full....................%u\n",
 			       pdcs->rx_ring_full);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "Tx desc write fail. Ring full...%u\n",
 			       pdcs->txnobuf);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "Rx desc write fail. Ring full...%u\n",
 			       pdcs->rxnobuf);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "Receive overflow................%u\n",
 			       pdcs->rx_oflow);
-	out_offset += snprintf(buf + out_offset, out_count - out_offset,
+	out_offset += scnprintf(buf + out_offset, out_count - out_offset,
 			       "Num frags in rx ring............%u\n",
 			       NRXDACTIVE(pdcs->rxin, pdcs->last_rx_curr,
 					  pdcs->nrxpost));
diff --git a/drivers/mailbox/imx-mailbox.c b/drivers/mailbox/imx-mailbox.c
index 2cdcdc5f1119..7906624a731c 100644
--- a/drivers/mailbox/imx-mailbox.c
+++ b/drivers/mailbox/imx-mailbox.c
@@ -4,8 +4,10 @@
  */
 
 #include <linux/clk.h>
+#include <linux/firmware/imx/ipc.h>
 #include <linux/interrupt.h>
 #include <linux/io.h>
+#include <linux/iopoll.h>
 #include <linux/kernel.h>
 #include <linux/mailbox_controller.h>
 #include <linux/module.h>
@@ -27,6 +29,8 @@
 #define IMX_MU_xCR_GIRn(x)	BIT(16 + (3 - (x)))
 
 #define IMX_MU_CHANS		16
+/* TX0/RX0/RXDB[0-3] */
+#define IMX_MU_SCU_CHANS	6
 #define IMX_MU_CHAN_NAME_SIZE	20
 
 enum imx_mu_chan_type {
@@ -36,11 +40,9 @@ enum imx_mu_chan_type {
 	IMX_MU_TYPE_RXDB,	/* Rx doorbell */
 };
 
-struct imx_mu_dcfg {
-	u32	xTR[4];		/* Transmit Registers */
-	u32	xRR[4];		/* Receive Registers */
-	u32	xSR;		/* Status Register */
-	u32	xCR;		/* Control Register */
+struct imx_sc_rpc_msg_max {
+	struct imx_sc_rpc_msg hdr;
+	u32 data[7];
 };
 
 struct imx_mu_con_priv {
@@ -67,18 +69,14 @@ struct imx_mu_priv {
 	bool			side_b;
 };
 
-static const struct imx_mu_dcfg imx_mu_cfg_imx6sx = {
-	.xTR	= {0x0, 0x4, 0x8, 0xc},
-	.xRR	= {0x10, 0x14, 0x18, 0x1c},
-	.xSR	= 0x20,
-	.xCR	= 0x24,
-};
-
-static const struct imx_mu_dcfg imx_mu_cfg_imx7ulp = {
-	.xTR	= {0x20, 0x24, 0x28, 0x2c},
-	.xRR	= {0x40, 0x44, 0x48, 0x4c},
-	.xSR	= 0x60,
-	.xCR	= 0x64,
+struct imx_mu_dcfg {
+	int (*tx)(struct imx_mu_priv *priv, struct imx_mu_con_priv *cp, void *data);
+	int (*rx)(struct imx_mu_priv *priv, struct imx_mu_con_priv *cp);
+	void (*init)(struct imx_mu_priv *priv);
+	u32	xTR[4];		/* Transmit Registers */
+	u32	xRR[4];		/* Receive Registers */
+	u32	xSR;		/* Status Register */
+	u32	xCR;		/* Control Register */
 };
 
 static struct imx_mu_priv *to_imx_mu_priv(struct mbox_controller *mbox)
@@ -111,6 +109,117 @@ static u32 imx_mu_xcr_rmw(struct imx_mu_priv *priv, u32 set, u32 clr)
 	return val;
 }
 
+static int imx_mu_generic_tx(struct imx_mu_priv *priv,
+			     struct imx_mu_con_priv *cp,
+			     void *data)
+{
+	u32 *arg = data;
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_TX:
+		imx_mu_write(priv, *arg, priv->dcfg->xTR[cp->idx]);
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_TIEn(cp->idx), 0);
+		break;
+	case IMX_MU_TYPE_TXDB:
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIRn(cp->idx), 0);
+		tasklet_schedule(&cp->txdb_tasklet);
+		break;
+	default:
+		dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int imx_mu_generic_rx(struct imx_mu_priv *priv,
+			     struct imx_mu_con_priv *cp)
+{
+	u32 dat;
+
+	dat = imx_mu_read(priv, priv->dcfg->xRR[cp->idx]);
+	mbox_chan_received_data(cp->chan, (void *)&dat);
+
+	return 0;
+}
+
+static int imx_mu_scu_tx(struct imx_mu_priv *priv,
+			 struct imx_mu_con_priv *cp,
+			 void *data)
+{
+	struct imx_sc_rpc_msg_max *msg = data;
+	u32 *arg = data;
+	int i, ret;
+	u32 xsr;
+
+	switch (cp->type) {
+	case IMX_MU_TYPE_TX:
+		if (msg->hdr.size > sizeof(*msg)) {
+			/*
+			 * The real message size can be different to
+			 * struct imx_sc_rpc_msg_max size
+			 */
+			dev_err(priv->dev, "Exceed max msg size (%zu) on TX, got: %i\n", sizeof(*msg), msg->hdr.size);
+			return -EINVAL;
+		}
+
+		for (i = 0; i < 4 && i < msg->hdr.size; i++)
+			imx_mu_write(priv, *arg++, priv->dcfg->xTR[i % 4]);
+		for (; i < msg->hdr.size; i++) {
+			ret = readl_poll_timeout(priv->base + priv->dcfg->xSR,
+						 xsr,
+						 xsr & IMX_MU_xSR_TEn(i % 4),
+						 0, 100);
+			if (ret) {
+				dev_err(priv->dev, "Send data index: %d timeout\n", i);
+				return ret;
+			}
+			imx_mu_write(priv, *arg++, priv->dcfg->xTR[i % 4]);
+		}
+
+		imx_mu_xcr_rmw(priv, IMX_MU_xCR_TIEn(cp->idx), 0);
+		break;
+	default:
+		dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int imx_mu_scu_rx(struct imx_mu_priv *priv,
+			 struct imx_mu_con_priv *cp)
+{
+	struct imx_sc_rpc_msg_max msg;
+	u32 *data = (u32 *)&msg;
+	int i, ret;
+	u32 xsr;
+
+	imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_RIEn(0));
+	*data++ = imx_mu_read(priv, priv->dcfg->xRR[0]);
+
+	if (msg.hdr.size > sizeof(msg)) {
+		dev_err(priv->dev, "Exceed max msg size (%zu) on RX, got: %i\n",
+			sizeof(msg), msg.hdr.size);
+		return -EINVAL;
+	}
+
+	for (i = 1; i < msg.hdr.size; i++) {
+		ret = readl_poll_timeout(priv->base + priv->dcfg->xSR, xsr,
+					 xsr & IMX_MU_xSR_RFn(i % 4), 0, 100);
+		if (ret) {
+			dev_err(priv->dev, "timeout read idx %d\n", i);
+			return ret;
+		}
+		*data++ = imx_mu_read(priv, priv->dcfg->xRR[i % 4]);
+	}
+
+	imx_mu_xcr_rmw(priv, IMX_MU_xCR_RIEn(0), 0);
+	mbox_chan_received_data(cp->chan, (void *)&msg);
+
+	return 0;
+}
+
 static void imx_mu_txdb_tasklet(unsigned long data)
 {
 	struct imx_mu_con_priv *cp = (struct imx_mu_con_priv *)data;
@@ -123,7 +232,7 @@ static irqreturn_t imx_mu_isr(int irq, void *p)
 	struct mbox_chan *chan = p;
 	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
 	struct imx_mu_con_priv *cp = chan->con_priv;
-	u32 val, ctrl, dat;
+	u32 val, ctrl;
 
 	ctrl = imx_mu_read(priv, priv->dcfg->xCR);
 	val = imx_mu_read(priv, priv->dcfg->xSR);
@@ -152,8 +261,7 @@ static irqreturn_t imx_mu_isr(int irq, void *p)
 		imx_mu_xcr_rmw(priv, 0, IMX_MU_xCR_TIEn(cp->idx));
 		mbox_chan_txdone(chan, 0);
 	} else if (val == IMX_MU_xSR_RFn(cp->idx)) {
-		dat = imx_mu_read(priv, priv->dcfg->xRR[cp->idx]);
-		mbox_chan_received_data(chan, (void *)&dat);
+		priv->dcfg->rx(priv, cp);
 	} else if (val == IMX_MU_xSR_GIPn(cp->idx)) {
 		imx_mu_write(priv, IMX_MU_xSR_GIPn(cp->idx), priv->dcfg->xSR);
 		mbox_chan_received_data(chan, NULL);
@@ -169,23 +277,8 @@ static int imx_mu_send_data(struct mbox_chan *chan, void *data)
 {
 	struct imx_mu_priv *priv = to_imx_mu_priv(chan->mbox);
 	struct imx_mu_con_priv *cp = chan->con_priv;
-	u32 *arg = data;
 
-	switch (cp->type) {
-	case IMX_MU_TYPE_TX:
-		imx_mu_write(priv, *arg, priv->dcfg->xTR[cp->idx]);
-		imx_mu_xcr_rmw(priv, IMX_MU_xCR_TIEn(cp->idx), 0);
-		break;
-	case IMX_MU_TYPE_TXDB:
-		imx_mu_xcr_rmw(priv, IMX_MU_xCR_GIRn(cp->idx), 0);
-		tasklet_schedule(&cp->txdb_tasklet);
-		break;
-	default:
-		dev_warn_ratelimited(priv->dev, "Send data on wrong channel type: %d\n", cp->type);
-		return -EINVAL;
-	}
-
-	return 0;
+	return priv->dcfg->tx(priv, cp, data);
 }
 
 static int imx_mu_startup(struct mbox_chan *chan)
@@ -256,6 +349,42 @@ static const struct mbox_chan_ops imx_mu_ops = {
 	.shutdown = imx_mu_shutdown,
 };
 
+static struct mbox_chan *imx_mu_scu_xlate(struct mbox_controller *mbox,
+					  const struct of_phandle_args *sp)
+{
+	u32 type, idx, chan;
+
+	if (sp->args_count != 2) {
+		dev_err(mbox->dev, "Invalid argument count %d\n", sp->args_count);
+		return ERR_PTR(-EINVAL);
+	}
+
+	type = sp->args[0]; /* channel type */
+	idx = sp->args[1]; /* index */
+
+	switch (type) {
+	case IMX_MU_TYPE_TX:
+	case IMX_MU_TYPE_RX:
+		if (idx != 0)
+			dev_err(mbox->dev, "Invalid chan idx: %d\n", idx);
+		chan = type;
+		break;
+	case IMX_MU_TYPE_RXDB:
+		chan = 2 + idx;
+		break;
+	default:
+		dev_err(mbox->dev, "Invalid chan type: %d\n", type);
+		return NULL;
+	}
+
+	if (chan >= mbox->num_chans) {
+		dev_err(mbox->dev, "Not supported channel number: %d. (type: %d, idx: %d)\n", chan, type, idx);
+		return ERR_PTR(-EINVAL);
+	}
+
+	return &mbox->chans[chan];
+}
+
 static struct mbox_chan * imx_mu_xlate(struct mbox_controller *mbox,
 				       const struct of_phandle_args *sp)
 {
@@ -280,6 +409,22 @@ static struct mbox_chan * imx_mu_xlate(struct mbox_controller *mbox,
 
 static void imx_mu_init_generic(struct imx_mu_priv *priv)
 {
+	unsigned int i;
+
+	for (i = 0; i < IMX_MU_CHANS; i++) {
+		struct imx_mu_con_priv *cp = &priv->con_priv[i];
+
+		cp->idx = i % 4;
+		cp->type = i >> 2;
+		cp->chan = &priv->mbox_chans[i];
+		priv->mbox_chans[i].con_priv = cp;
+		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
+			 "imx_mu_chan[%i-%i]", cp->type, cp->idx);
+	}
+
+	priv->mbox.num_chans = IMX_MU_CHANS;
+	priv->mbox.of_xlate = imx_mu_xlate;
+
 	if (priv->side_b)
 		return;
 
@@ -287,13 +432,34 @@ static void imx_mu_init_generic(struct imx_mu_priv *priv)
 	imx_mu_write(priv, 0, priv->dcfg->xCR);
 }
 
+static void imx_mu_init_scu(struct imx_mu_priv *priv)
+{
+	unsigned int i;
+
+	for (i = 0; i < IMX_MU_SCU_CHANS; i++) {
+		struct imx_mu_con_priv *cp = &priv->con_priv[i];
+
+		cp->idx = i < 2 ? 0 : i - 2;
+		cp->type = i < 2 ? i : IMX_MU_TYPE_RXDB;
+		cp->chan = &priv->mbox_chans[i];
+		priv->mbox_chans[i].con_priv = cp;
+		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
+			 "imx_mu_chan[%i-%i]", cp->type, cp->idx);
+	}
+
+	priv->mbox.num_chans = IMX_MU_SCU_CHANS;
+	priv->mbox.of_xlate = imx_mu_scu_xlate;
+
+	/* Set default MU configuration */
+	imx_mu_write(priv, 0, priv->dcfg->xCR);
+}
+
 static int imx_mu_probe(struct platform_device *pdev)
 {
 	struct device *dev = &pdev->dev;
 	struct device_node *np = dev->of_node;
 	struct imx_mu_priv *priv;
 	const struct imx_mu_dcfg *dcfg;
-	unsigned int i;
 	int ret;
 
 	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
@@ -329,32 +495,19 @@ static int imx_mu_probe(struct platform_device *pdev)
 		return ret;
 	}
 
-	for (i = 0; i < IMX_MU_CHANS; i++) {
-		struct imx_mu_con_priv *cp = &priv->con_priv[i];
-
-		cp->idx = i % 4;
-		cp->type = i >> 2;
-		cp->chan = &priv->mbox_chans[i];
-		priv->mbox_chans[i].con_priv = cp;
-		snprintf(cp->irq_desc, sizeof(cp->irq_desc),
-			 "imx_mu_chan[%i-%i]", cp->type, cp->idx);
-	}
-
 	priv->side_b = of_property_read_bool(np, "fsl,mu-side-b");
 
+	priv->dcfg->init(priv);
+
 	spin_lock_init(&priv->xcr_lock);
 
 	priv->mbox.dev = dev;
 	priv->mbox.ops = &imx_mu_ops;
 	priv->mbox.chans = priv->mbox_chans;
-	priv->mbox.num_chans = IMX_MU_CHANS;
-	priv->mbox.of_xlate = imx_mu_xlate;
 	priv->mbox.txdone_irq = true;
 
 	platform_set_drvdata(pdev, priv);
 
-	imx_mu_init_generic(priv);
-
 	return devm_mbox_controller_register(dev, &priv->mbox);
 }
 
@@ -367,9 +520,40 @@ static int imx_mu_remove(struct platform_device *pdev)
 	return 0;
 }
 
+static const struct imx_mu_dcfg imx_mu_cfg_imx6sx = {
+	.tx	= imx_mu_generic_tx,
+	.rx	= imx_mu_generic_rx,
+	.init	= imx_mu_init_generic,
+	.xTR	= {0x0, 0x4, 0x8, 0xc},
+	.xRR	= {0x10, 0x14, 0x18, 0x1c},
+	.xSR	= 0x20,
+	.xCR	= 0x24,
+};
+
+static const struct imx_mu_dcfg imx_mu_cfg_imx7ulp = {
+	.tx	= imx_mu_generic_tx,
+	.rx	= imx_mu_generic_rx,
+	.init	= imx_mu_init_generic,
+	.xTR	= {0x20, 0x24, 0x28, 0x2c},
+	.xRR	= {0x40, 0x44, 0x48, 0x4c},
+	.xSR	= 0x60,
+	.xCR	= 0x64,
+};
+
+static const struct imx_mu_dcfg imx_mu_cfg_imx8_scu = {
+	.tx	= imx_mu_scu_tx,
+	.rx	= imx_mu_scu_rx,
+	.init	= imx_mu_init_scu,
+	.xTR	= {0x0, 0x4, 0x8, 0xc},
+	.xRR	= {0x10, 0x14, 0x18, 0x1c},
+	.xSR	= 0x20,
+	.xCR	= 0x24,
+};
+
 static const struct of_device_id imx_mu_dt_ids[] = {
 	{ .compatible = "fsl,imx7ulp-mu", .data = &imx_mu_cfg_imx7ulp },
 	{ .compatible = "fsl,imx6sx-mu", .data = &imx_mu_cfg_imx6sx },
+	{ .compatible = "fsl,imx8-mu-scu", .data = &imx_mu_cfg_imx8_scu },
 	{ },
 };
 MODULE_DEVICE_TABLE(of, imx_mu_dt_ids);
diff --git a/drivers/mailbox/mtk-cmdq-mailbox.c b/drivers/mailbox/mtk-cmdq-mailbox.c
index 9a6ce9f5a7db..b24822ad8409 100644
--- a/drivers/mailbox/mtk-cmdq-mailbox.c
+++ b/drivers/mailbox/mtk-cmdq-mailbox.c
@@ -56,7 +56,6 @@ struct cmdq_thread {
 	void __iomem		*base;
 	struct list_head	task_busy_list;
 	u32			priority;
-	bool			atomic_exec;
 };
 
 struct cmdq_task {
@@ -162,48 +161,11 @@ static void cmdq_task_insert_into_thread(struct cmdq_task *task)
 	cmdq_thread_invalidate_fetched_data(thread);
 }
 
-static bool cmdq_command_is_wfe(u64 cmd)
-{
-	u64 wfe_option = CMDQ_WFE_UPDATE | CMDQ_WFE_WAIT | CMDQ_WFE_WAIT_VALUE;
-	u64 wfe_op = (u64)(CMDQ_CODE_WFE << CMDQ_OP_CODE_SHIFT) << 32;
-	u64 wfe_mask = (u64)CMDQ_OP_CODE_MASK << 32 | 0xffffffff;
-
-	return ((cmd & wfe_mask) == (wfe_op | wfe_option));
-}
-
-/* we assume tasks in the same display GCE thread are waiting the same event. */
-static void cmdq_task_remove_wfe(struct cmdq_task *task)
-{
-	struct device *dev = task->cmdq->mbox.dev;
-	u64 *base = task->pkt->va_base;
-	int i;
-
-	dma_sync_single_for_cpu(dev, task->pa_base, task->pkt->cmd_buf_size,
-				DMA_TO_DEVICE);
-	for (i = 0; i < CMDQ_NUM_CMD(task->pkt); i++)
-		if (cmdq_command_is_wfe(base[i]))
-			base[i] = (u64)CMDQ_JUMP_BY_OFFSET << 32 |
-				  CMDQ_JUMP_PASS;
-	dma_sync_single_for_device(dev, task->pa_base, task->pkt->cmd_buf_size,
-				   DMA_TO_DEVICE);
-}
-
 static bool cmdq_thread_is_in_wfe(struct cmdq_thread *thread)
 {
 	return readl(thread->base + CMDQ_THR_WAIT_TOKEN) & CMDQ_THR_IS_WAITING;
 }
 
-static void cmdq_thread_wait_end(struct cmdq_thread *thread,
-				 unsigned long end_pa)
-{
-	struct device *dev = thread->chan->mbox->dev;
-	unsigned long curr_pa;
-
-	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_CURR_ADDR,
-			curr_pa, curr_pa == end_pa, 1, 20))
-		dev_err(dev, "GCE thread cannot run to end.\n");
-}
-
 static void cmdq_task_exec_done(struct cmdq_task *task, enum cmdq_cb_status sta)
 {
 	struct cmdq_task_cb *cb = &task->pkt->async_cb;
@@ -383,36 +345,15 @@ static int cmdq_mbox_send_data(struct mbox_chan *chan, void *data)
 		WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
 		curr_pa = readl(thread->base + CMDQ_THR_CURR_ADDR);
 		end_pa = readl(thread->base + CMDQ_THR_END_ADDR);
-
-		/*
-		 * Atomic execution should remove the following wfe, i.e. only
-		 * wait event at first task, and prevent to pause when running.
-		 */
-		if (thread->atomic_exec) {
-			/* GCE is executing if command is not WFE */
-			if (!cmdq_thread_is_in_wfe(thread)) {
-				cmdq_thread_resume(thread);
-				cmdq_thread_wait_end(thread, end_pa);
-				WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
-				/* set to this task directly */
-				writel(task->pa_base,
-				       thread->base + CMDQ_THR_CURR_ADDR);
-			} else {
-				cmdq_task_insert_into_thread(task);
-				cmdq_task_remove_wfe(task);
-				smp_mb(); /* modify jump before enable thread */
-			}
+		/* check boundary */
+		if (curr_pa == end_pa - CMDQ_INST_SIZE ||
+		    curr_pa == end_pa) {
+			/* set to this task directly */
+			writel(task->pa_base,
+			       thread->base + CMDQ_THR_CURR_ADDR);
 		} else {
-			/* check boundary */
-			if (curr_pa == end_pa - CMDQ_INST_SIZE ||
-			    curr_pa == end_pa) {
-				/* set to this task directly */
-				writel(task->pa_base,
-				       thread->base + CMDQ_THR_CURR_ADDR);
-			} else {
-				cmdq_task_insert_into_thread(task);
-				smp_mb(); /* modify jump before enable thread */
-			}
+			cmdq_task_insert_into_thread(task);
+			smp_mb(); /* modify jump before enable thread */
 		}
 		writel(task->pa_base + pkt->cmd_buf_size,
 		       thread->base + CMDQ_THR_END_ADDR);
@@ -432,10 +373,62 @@ static void cmdq_mbox_shutdown(struct mbox_chan *chan)
 {
 }
 
+static int cmdq_mbox_flush(struct mbox_chan *chan, unsigned long timeout)
+{
+	struct cmdq_thread *thread = (struct cmdq_thread *)chan->con_priv;
+	struct cmdq_task_cb *cb;
+	struct cmdq_cb_data data;
+	struct cmdq *cmdq = dev_get_drvdata(chan->mbox->dev);
+	struct cmdq_task *task, *tmp;
+	unsigned long flags;
+	u32 enable;
+
+	spin_lock_irqsave(&thread->chan->lock, flags);
+	if (list_empty(&thread->task_busy_list))
+		goto out;
+
+	WARN_ON(cmdq_thread_suspend(cmdq, thread) < 0);
+	if (!cmdq_thread_is_in_wfe(thread))
+		goto wait;
+
+	list_for_each_entry_safe(task, tmp, &thread->task_busy_list,
+				 list_entry) {
+		cb = &task->pkt->async_cb;
+		if (cb->cb) {
+			data.sta = CMDQ_CB_ERROR;
+			data.data = cb->data;
+			cb->cb(data);
+		}
+		list_del(&task->list_entry);
+		kfree(task);
+	}
+
+	cmdq_thread_resume(thread);
+	cmdq_thread_disable(cmdq, thread);
+	clk_disable(cmdq->clock);
+
+out:
+	spin_unlock_irqrestore(&thread->chan->lock, flags);
+	return 0;
+
+wait:
+	cmdq_thread_resume(thread);
+	spin_unlock_irqrestore(&thread->chan->lock, flags);
+	if (readl_poll_timeout_atomic(thread->base + CMDQ_THR_ENABLE_TASK,
+				      enable, enable == 0, 1, timeout)) {
+		dev_err(cmdq->mbox.dev, "Fail to wait GCE thread 0x%x done\n",
+			(u32)(thread->base - cmdq->base));
+
+		return -EFAULT;
+	}
+	return 0;
+}
+
 static const struct mbox_chan_ops cmdq_mbox_chan_ops = {
 	.send_data = cmdq_mbox_send_data,
 	.startup = cmdq_mbox_startup,
 	.shutdown = cmdq_mbox_shutdown,
+	.flush = cmdq_mbox_flush,
 };
 
 static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
@@ -449,7 +442,6 @@ static struct mbox_chan *cmdq_xlate(struct mbox_controller *mbox,
 
 	thread = (struct cmdq_thread *)mbox->chans[ind].con_priv;
 	thread->priority = sp->args[1];
-	thread->atomic_exec = (sp->args[2] != 0);
 	thread->chan = &mbox->chans[ind];
 
 	return &mbox->chans[ind];
diff --git a/drivers/mailbox/sun6i-msgbox.c b/drivers/mailbox/sun6i-msgbox.c
new file mode 100644
index 000000000000..ccecf2e5941d
--- /dev/null
+++ b/drivers/mailbox/sun6i-msgbox.c
@@ -0,0 +1,326 @@
+// SPDX-License-Identifier: GPL-2.0
+//
+// Copyright (c) 2017-2019 Samuel Holland <samuel@sholland.org>
+
+#include <linux/bitops.h>
+#include <linux/clk.h>
+#include <linux/device.h>
+#include <linux/err.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/kernel.h>
+#include <linux/mailbox_controller.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/of_irq.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+#include <linux/spinlock.h>
+
+#define NUM_CHANS		8
+
+#define CTRL_REG(n)		(0x0000 + 0x4 * ((n) / 4))
+#define CTRL_RX(n)		BIT(0 + 8 * ((n) % 4))
+#define CTRL_TX(n)		BIT(4 + 8 * ((n) % 4))
+
+#define REMOTE_IRQ_EN_REG	0x0040
+#define REMOTE_IRQ_STAT_REG	0x0050
+#define LOCAL_IRQ_EN_REG	0x0060
+#define LOCAL_IRQ_STAT_REG	0x0070
+
+#define RX_IRQ(n)		BIT(0 + 2 * (n))
+#define RX_IRQ_MASK		0x5555
+#define TX_IRQ(n)		BIT(1 + 2 * (n))
+#define TX_IRQ_MASK		0xaaaa
+
+#define FIFO_STAT_REG(n)	(0x0100 + 0x4 * (n))
+#define FIFO_STAT_MASK		GENMASK(0, 0)
+
+#define MSG_STAT_REG(n)		(0x0140 + 0x4 * (n))
+#define MSG_STAT_MASK		GENMASK(2, 0)
+
+#define MSG_DATA_REG(n)		(0x0180 + 0x4 * (n))
+
+#define mbox_dbg(mbox, ...)	dev_dbg((mbox)->controller.dev, __VA_ARGS__)
+
+struct sun6i_msgbox {
+	struct mbox_controller controller;
+	struct clk *clk;
+	spinlock_t lock;
+	void __iomem *regs;
+};
+
+static bool sun6i_msgbox_last_tx_done(struct mbox_chan *chan);
+static bool sun6i_msgbox_peek_data(struct mbox_chan *chan);
+
+static inline int channel_number(struct mbox_chan *chan)
+{
+	return chan - chan->mbox->chans;
+}
+
+static inline struct sun6i_msgbox *to_sun6i_msgbox(struct mbox_chan *chan)
+{
+	return chan->con_priv;
+}
+
+static irqreturn_t sun6i_msgbox_irq(int irq, void *dev_id)
+{
+	struct sun6i_msgbox *mbox = dev_id;
+	uint32_t status;
+	int n;
+
+	/* Only examine channels that are currently enabled. */
+	status = readl(mbox->regs + LOCAL_IRQ_EN_REG) &
+		 readl(mbox->regs + LOCAL_IRQ_STAT_REG);
+
+	if (!(status & RX_IRQ_MASK))
+		return IRQ_NONE;
+
+	for (n = 0; n < NUM_CHANS; ++n) {
+		struct mbox_chan *chan = &mbox->controller.chans[n];
+
+		if (!(status & RX_IRQ(n)))
+			continue;
+
+		while (sun6i_msgbox_peek_data(chan)) {
+			uint32_t msg = readl(mbox->regs + MSG_DATA_REG(n));
+
+			mbox_dbg(mbox, "Channel %d received 0x%08x\n", n, msg);
+			mbox_chan_received_data(chan, &msg);
+		}
+
+		/* The IRQ can be cleared only once the FIFO is empty. */
+		writel(RX_IRQ(n), mbox->regs + LOCAL_IRQ_STAT_REG);
+	}
+
+	return IRQ_HANDLED;
+}
+
+static int sun6i_msgbox_send_data(struct mbox_chan *chan, void *data)
+{
+	struct sun6i_msgbox *mbox = to_sun6i_msgbox(chan);
+	int n = channel_number(chan);
+	uint32_t msg = *(uint32_t *)data;
+
+	/* Using a channel backwards gets the hardware into a bad state. */
+	if (WARN_ON_ONCE(!(readl(mbox->regs + CTRL_REG(n)) & CTRL_TX(n))))
+		return 0;
+
+	writel(msg, mbox->regs + MSG_DATA_REG(n));
+	mbox_dbg(mbox, "Channel %d sent 0x%08x\n", n, msg);
+
+	return 0;
+}
+
+static int sun6i_msgbox_startup(struct mbox_chan *chan)
+{
+	struct sun6i_msgbox *mbox = to_sun6i_msgbox(chan);
+	int n = channel_number(chan);
+
+	/* The coprocessor is responsible for setting channel directions. */
+	if (readl(mbox->regs + CTRL_REG(n)) & CTRL_RX(n)) {
+		/* Flush the receive FIFO. */
+		while (sun6i_msgbox_peek_data(chan))
+			readl(mbox->regs + MSG_DATA_REG(n));
+		writel(RX_IRQ(n), mbox->regs + LOCAL_IRQ_STAT_REG);
+
+		/* Enable the receive IRQ. */
+		spin_lock(&mbox->lock);
+		writel(readl(mbox->regs + LOCAL_IRQ_EN_REG) | RX_IRQ(n),
+		       mbox->regs + LOCAL_IRQ_EN_REG);
+		spin_unlock(&mbox->lock);
+	}
+
+	mbox_dbg(mbox, "Channel %d startup complete\n", n);
+
+	return 0;
+}
+
+static void sun6i_msgbox_shutdown(struct mbox_chan *chan)
+{
+	struct sun6i_msgbox *mbox = to_sun6i_msgbox(chan);
+	int n = channel_number(chan);
+
+	if (readl(mbox->regs + CTRL_REG(n)) & CTRL_RX(n)) {
+		/* Disable the receive IRQ. */
+		spin_lock(&mbox->lock);
+		writel(readl(mbox->regs + LOCAL_IRQ_EN_REG) & ~RX_IRQ(n),
+		       mbox->regs + LOCAL_IRQ_EN_REG);
+		spin_unlock(&mbox->lock);
+
+		/* Attempt to flush the FIFO until the IRQ is cleared. */
+		do {
+			while (sun6i_msgbox_peek_data(chan))
+				readl(mbox->regs + MSG_DATA_REG(n));
+			writel(RX_IRQ(n), mbox->regs + LOCAL_IRQ_STAT_REG);
+		} while (readl(mbox->regs + LOCAL_IRQ_STAT_REG) & RX_IRQ(n));
+	}
+
+	mbox_dbg(mbox, "Channel %d shutdown complete\n", n);
+}
+
+static bool sun6i_msgbox_last_tx_done(struct mbox_chan *chan)
+{
+	struct sun6i_msgbox *mbox = to_sun6i_msgbox(chan);
+	int n = channel_number(chan);
+
+	/*
+	 * The hardware allows snooping on the remote user's IRQ statuses.
+	 * We consider a message to be acknowledged only once the receive IRQ
+	 * for that channel is cleared. Since the receive IRQ for a channel
+	 * cannot be cleared until the FIFO for that channel is empty, this
+	 * ensures that the message has actually been read. It also gives the
+	 * recipient an opportunity to perform minimal processing before
+	 * acknowledging the message.
+	 */
+	return !(readl(mbox->regs + REMOTE_IRQ_STAT_REG) & RX_IRQ(n));
+}
+
+static bool sun6i_msgbox_peek_data(struct mbox_chan *chan)
+{
+	struct sun6i_msgbox *mbox = to_sun6i_msgbox(chan);
+	int n = channel_number(chan);
+
+	return readl(mbox->regs + MSG_STAT_REG(n)) & MSG_STAT_MASK;
+}
+
+static const struct mbox_chan_ops sun6i_msgbox_chan_ops = {
+	.send_data    = sun6i_msgbox_send_data,
+	.startup      = sun6i_msgbox_startup,
+	.shutdown     = sun6i_msgbox_shutdown,
+	.last_tx_done = sun6i_msgbox_last_tx_done,
+	.peek_data    = sun6i_msgbox_peek_data,
+};
+
+static int sun6i_msgbox_probe(struct platform_device *pdev)
+{
+	struct device *dev = &pdev->dev;
+	struct mbox_chan *chans;
+	struct reset_control *reset;
+	struct resource *res;
+	struct sun6i_msgbox *mbox;
+	int i, ret;
+
+	mbox = devm_kzalloc(dev, sizeof(*mbox), GFP_KERNEL);
+	if (!mbox)
+		return -ENOMEM;
+
+	chans = devm_kcalloc(dev, NUM_CHANS, sizeof(*chans), GFP_KERNEL);
+	if (!chans)
+		return -ENOMEM;
+
+	for (i = 0; i < NUM_CHANS; ++i)
+		chans[i].con_priv = mbox;
+
+	mbox->clk = devm_clk_get(dev, NULL);
+	if (IS_ERR(mbox->clk)) {
+		ret = PTR_ERR(mbox->clk);
+		dev_err(dev, "Failed to get clock: %d\n", ret);
+		return ret;
+	}
+
+	ret = clk_prepare_enable(mbox->clk);
+	if (ret) {
+		dev_err(dev, "Failed to enable clock: %d\n", ret);
+		return ret;
+	}
+
+	reset = devm_reset_control_get_exclusive(dev, NULL);
+	if (IS_ERR(reset)) {
+		ret = PTR_ERR(reset);
+		dev_err(dev, "Failed to get reset control: %d\n", ret);
+		goto err_disable_unprepare;
+	}
+
+	/*
+	 * NOTE: We rely on platform firmware to preconfigure the channel
+	 * directions, and we share this hardware block with other firmware
+	 * that runs concurrently with Linux (e.g. a trusted monitor).
+	 *
+	 * Therefore, we do *not* assert the reset line if probing fails or
+	 * when removing the device.
+	 */
+	ret = reset_control_deassert(reset);
+	if (ret) {
+		dev_err(dev, "Failed to deassert reset: %d\n", ret);
+		goto err_disable_unprepare;
+	}
+
+	res = platform_get_resource(pdev, IORESOURCE_MEM, 0);
+	if (!res) {
+		ret = -ENODEV;
+		goto err_disable_unprepare;
+	}
+
+	mbox->regs = devm_ioremap_resource(&pdev->dev, res);
+	if (IS_ERR(mbox->regs)) {
+		ret = PTR_ERR(mbox->regs);
+		dev_err(dev, "Failed to map MMIO resource: %d\n", ret);
+		goto err_disable_unprepare;
+	}
+
+	/* Disable all IRQs for this end of the msgbox. */
+	writel(0, mbox->regs + LOCAL_IRQ_EN_REG);
+
+	ret = devm_request_irq(dev, irq_of_parse_and_map(dev->of_node, 0),
+			       sun6i_msgbox_irq, 0, dev_name(dev), mbox);
+	if (ret) {
+		dev_err(dev, "Failed to register IRQ handler: %d\n", ret);
+		goto err_disable_unprepare;
+	}
+
+	mbox->controller.dev           = dev;
+	mbox->controller.ops           = &sun6i_msgbox_chan_ops;
+	mbox->controller.chans         = chans;
+	mbox->controller.num_chans     = NUM_CHANS;
+	mbox->controller.txdone_irq    = false;
+	mbox->controller.txdone_poll   = true;
+	mbox->controller.txpoll_period = 5;
+
+	spin_lock_init(&mbox->lock);
+	platform_set_drvdata(pdev, mbox);
+
+	ret = mbox_controller_register(&mbox->controller);
+	if (ret) {
+		dev_err(dev, "Failed to register controller: %d\n", ret);
+		goto err_disable_unprepare;
+	}
+
+	return 0;
+
+err_disable_unprepare:
+	clk_disable_unprepare(mbox->clk);
+
+	return ret;
+}
+
+static int sun6i_msgbox_remove(struct platform_device *pdev)
+{
+	struct sun6i_msgbox *mbox = platform_get_drvdata(pdev);
+
+	mbox_controller_unregister(&mbox->controller);
+	/* See the comment in sun6i_msgbox_probe about the reset line. */
+	clk_disable_unprepare(mbox->clk);
+
+	return 0;
+}
+
+static const struct of_device_id sun6i_msgbox_of_match[] = {
+	{ .compatible = "allwinner,sun6i-a31-msgbox", },
+	{},
+};
+MODULE_DEVICE_TABLE(of, sun6i_msgbox_of_match);
+
+static struct platform_driver sun6i_msgbox_driver = {
+	.driver = {
+		.name = "sun6i-msgbox",
+		.of_match_table = sun6i_msgbox_of_match,
+	},
+	.probe  = sun6i_msgbox_probe,
+	.remove = sun6i_msgbox_remove,
+};
+module_platform_driver(sun6i_msgbox_driver);
+
+MODULE_AUTHOR("Samuel Holland <samuel@sholland.org>");
+MODULE_DESCRIPTION("Allwinner sun6i/sun8i/sun9i/sun50i Message Box");
+MODULE_LICENSE("GPL v2");