Merge branch 'for-4.10/firmware' into for-4.10/reset

19 files changed, 5327 insertions, 0 deletions

diff --git a/Documentation/devicetree/bindings/firmware/nvidia,tegra186-bpmp.txt b/Documentation/devicetree/bindings/firmware/nvidia,tegra186-bpmp.txt
new file mode 100644
index 000000000000..e821e16ad65b
--- /dev/null
+++ b/Documentation/devicetree/bindings/firmware/nvidia,tegra186-bpmp.txt
@@ -0,0 +1,108 @@
+NVIDIA Tegra Boot and Power Management Processor (BPMP)
+
+The BPMP is a specific processor in Tegra chip, which is designed for
+booting process handling and offloading the power management, clock
+management, and reset control tasks from the CPU. The binding document
+defines the resources that would be used by the BPMP firmware driver,
+which can create the interprocessor communication (IPC) between the CPU
+and BPMP.
+
+Required properties:
+- name : Should be bpmp
+- compatible
+    Array of strings
+    One of:
+    - "nvidia,tegra186-bpmp"
+- mboxes : The phandle of mailbox controller and the mailbox specifier.
+- shmem : List of the phandle of the TX and RX shared memory area that
+	  the IPC between CPU and BPMP is based on.
+- #clock-cells : Should be 1.
+- #power-domain-cells : Should be 1.
+- #reset-cells : Should be 1.
+
+This node is a mailbox consumer. See the following files for details of
+the mailbox subsystem, and the specifiers implemented by the relevant
+provider(s):
+
+- .../mailbox/mailbox.txt
+- .../mailbox/nvidia,tegra186-hsp.txt
+
+This node is a clock, power domain, and reset provider. See the following
+files for general documentation of those features, and the specifiers
+implemented by this node:
+
+- .../clock/clock-bindings.txt
+- <dt-bindings/clock/tegra186-clock.h>
+- ../power/power_domain.txt
+- <dt-bindings/power/tegra186-powergate.h>
+- .../reset/reset.txt
+- <dt-bindings/reset/tegra186-reset.h>
+
+The BPMP implements some services which must be represented by separate nodes.
+For example, it can provide access to certain I2C controllers, and the I2C
+bindings represent each I2C controller as a device tree node. Such nodes should
+be nested directly inside the main BPMP node.
+
+Software can determine whether a child node of the BPMP node represents a device
+by checking for a compatible property. Any node with a compatible property
+represents a device that can be instantiated. Nodes without a compatible
+property may be used to provide configuration information regarding the BPMP
+itself, although no such configuration nodes are currently defined by this
+binding.
+
+The BPMP firmware defines no single global name-/numbering-space for such
+services. Put another way, the numbering scheme for I2C buses is distinct from
+the numbering scheme for any other service the BPMP may provide (e.g. a future
+hypothetical SPI bus service). As such, child device nodes will have no reg
+property, and the BPMP node will have no #address-cells or #size-cells property.
+
+The shared memory bindings for BPMP
+-----------------------------------
+
+The shared memory area for the IPC TX and RX between CPU and BPMP are
+predefined and work on top of sysram, which is an SRAM inside the chip.
+
+See ".../sram/sram.txt" for the bindings.
+
+Example:
+
+hsp_top0: hsp@03c00000 {
+	...
+	#mbox-cells = <2>;
+};
+
+sysram@30000000 {
+	compatible = "nvidia,tegra186-sysram", "mmio-sram";
+	reg = <0x0 0x30000000 0x0 0x50000>;
+	#address-cells = <2>;
+	#size-cells = <2>;
+	ranges = <0 0x0 0x0 0x30000000 0x0 0x50000>;
+
+	cpu_bpmp_tx: shmem@4e000 {
+		compatible = "nvidia,tegra186-bpmp-shmem";
+		reg = <0x0 0x4e000 0x0 0x1000>;
+		label = "cpu-bpmp-tx";
+		pool;
+	};
+
+	cpu_bpmp_rx: shmem@4f000 {
+		compatible = "nvidia,tegra186-bpmp-shmem";
+		reg = <0x0 0x4f000 0x0 0x1000>;
+		label = "cpu-bpmp-rx";
+		pool;
+	};
+};
+
+bpmp {
+	compatible = "nvidia,tegra186-bpmp";
+	mboxes = <&hsp_top0 TEGRA_HSP_MBOX_TYPE_DB TEGRA_HSP_DB_MASTER_BPMP>;
+	shmem = <&cpu_bpmp_tx &cpu_bpmp_rx>;
+	#clock-cells = <1>;
+	#power-domain-cells = <1>;
+	#reset-cells = <1>;
+
+	i2c {
+		compatible = "...";
+		...
+	};
+};
diff --git a/Documentation/devicetree/bindings/mailbox/nvidia,tegra186-hsp.txt b/Documentation/devicetree/bindings/mailbox/nvidia,tegra186-hsp.txt
new file mode 100644
index 000000000000..b99d25fc2f26
--- /dev/null
+++ b/Documentation/devicetree/bindings/mailbox/nvidia,tegra186-hsp.txt
@@ -0,0 +1,52 @@
+NVIDIA Tegra Hardware Synchronization Primitives (HSP)
+
+The HSP modules are used for the processors to share resources and communicate
+together. It provides a set of hardware synchronization primitives for
+interprocessor communication. So the interprocessor communication (IPC)
+protocols can use hardware synchronization primitives, when operating between
+two processors not in an SMP relationship.
+
+The features that HSP supported are shared mailboxes, shared semaphores,
+arbitrated semaphores and doorbells.
+
+Required properties:
+- name : Should be hsp
+- compatible
+    Array of strings.
+    one of:
+    - "nvidia,tegra186-hsp"
+- reg : Offset and length of the register set for the device.
+- interrupt-names
+    Array of strings.
+    Contains a list of names for the interrupts described by the interrupt
+    property. May contain the following entries, in any order:
+    - "doorbell"
+    Users of this binding MUST look up entries in the interrupt property
+    by name, using this interrupt-names property to do so.
+- interrupts
+    Array of interrupt specifiers.
+    Must contain one entry per entry in the interrupt-names property,
+    in a matching order.
+- #mbox-cells : Should be 2.
+
+The mbox specifier of the "mboxes" property in the client node should
+contain two data. The first one should be the HSP type and the second
+one should be the ID that the client is going to use. Those information
+can be found in the following file.
+
+- <dt-bindings/mailbox/tegra186-hsp.h>.
+
+Example:
+
+hsp_top0: hsp@3c00000 {
+	compatible = "nvidia,tegra186-hsp";
+	reg = <0x0 0x03c00000 0x0 0xa0000>;
+	interrupts = <GIC_SPI 176 IRQ_TYPE_LEVEL_HIGH>;
+	interrupt-names = "doorbell";
+	#mbox-cells = <2>;
+};
+
+client {
+	...
+	mboxes = <&hsp_top0 TEGRA_HSP_MBOX_TYPE_DB TEGRA_HSP_DB_MASTER_XXX>;
+};
diff --git a/drivers/firmware/Kconfig b/drivers/firmware/Kconfig
index bca172d42c74..9968de04d1d5 100644
--- a/drivers/firmware/Kconfig
+++ b/drivers/firmware/Kconfig
@@ -210,5 +210,6 @@ source "drivers/firmware/broadcom/Kconfig"
 source "drivers/firmware/google/Kconfig"
 source "drivers/firmware/efi/Kconfig"
 source "drivers/firmware/meson/Kconfig"
+source "drivers/firmware/tegra/Kconfig"
 
 endmenu
diff --git a/drivers/firmware/Makefile b/drivers/firmware/Makefile
index 898ac41fa8b3..2afe75c52ac2 100644
--- a/drivers/firmware/Makefile
+++ b/drivers/firmware/Makefile
@@ -26,3 +26,4 @@ obj-y				+= meson/
 obj-$(CONFIG_GOOGLE_FIRMWARE)	+= google/
 obj-$(CONFIG_EFI)		+= efi/
 obj-$(CONFIG_UEFI_CPER)		+= efi/
+obj-y				+= tegra/
diff --git a/drivers/firmware/tegra/Kconfig b/drivers/firmware/tegra/Kconfig
new file mode 100644
index 000000000000..ff2730d5c468
--- /dev/null
+++ b/drivers/firmware/tegra/Kconfig
@@ -0,0 +1,25 @@
+menu "Tegra firmware driver"
+
+config TEGRA_IVC
+	bool "Tegra IVC protocol"
+	depends on ARCH_TEGRA
+	help
+	  IVC (Inter-VM Communication) protocol is part of the IPC
+	  (Inter Processor Communication) framework on Tegra. It maintains the
+	  data and the different commuication channels in SysRAM or RAM and
+	  keeps the content is synchronization between host CPU and remote
+	  processors.
+
+config TEGRA_BPMP
+	bool "Tegra BPMP driver"
+	depends on ARCH_TEGRA && TEGRA_HSP_MBOX && TEGRA_IVC
+	help
+	  BPMP (Boot and Power Management Processor) is designed to off-loading
+	  the PM functions which include clock/DVFS/thermal/power from the CPU.
+	  It needs HSP as the HW synchronization and notification module and
+	  IVC module as the message communication protocol.
+
+	  This driver manages the IPC interface between host CPU and the
+	  firmware running on BPMP.
+
+endmenu
diff --git a/drivers/firmware/tegra/Makefile b/drivers/firmware/tegra/Makefile
new file mode 100644
index 000000000000..e34a2f79e1ad
--- /dev/null
+++ b/drivers/firmware/tegra/Makefile
@@ -0,0 +1,2 @@
+obj-$(CONFIG_TEGRA_BPMP)	+= bpmp.o
+obj-$(CONFIG_TEGRA_IVC)		+= ivc.o
diff --git a/drivers/firmware/tegra/bpmp.c b/drivers/firmware/tegra/bpmp.c
new file mode 100644
index 000000000000..4ff02d310868
--- /dev/null
+++ b/drivers/firmware/tegra/bpmp.c
@@ -0,0 +1,868 @@
+/*
+ * Copyright (c) 2016, NVIDIA CORPORATION.  All rights reserved.
+ *
+ * This program is free software; you can redistribute it and/or modify it
+ * under the terms and conditions of the GNU General Public License,
+ * version 2, as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope it will be useful, but WITHOUT
+ * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or
+ * FITNESS FOR A PARTICULAR PURPOSE.  See the GNU General Public License for
+ * more details.
+ */
+
+#include <linux/clk/tegra.h>
+#include <linux/genalloc.h>
+#include <linux/mailbox_client.h>
+#include <linux/of.h>
+#include <linux/of_address.h>
+#include <linux/of_device.h>
+#include <linux/platform_device.h>
+#include <linux/semaphore.h>
+
+#include <soc/tegra/bpmp.h>
+#include <soc/tegra/bpmp-abi.h>
+#include <soc/tegra/ivc.h>
+
+#define MSG_ACK		BIT(0)
+#define MSG_RING	BIT(1)
+
+static inline struct tegra_bpmp *
+mbox_client_to_bpmp(struct mbox_client *client)
+{
+	return container_of(client, struct tegra_bpmp, mbox.client);
+}
+
+struct tegra_bpmp *tegra_bpmp_get(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct tegra_bpmp *bpmp;
+	struct device_node *np;
+
+	np = of_parse_phandle(dev->of_node, "nvidia,bpmp", 0);
+	if (!np)
+		return ERR_PTR(-ENOENT);
+
+	pdev = of_find_device_by_node(np);
+	if (!pdev) {
+		bpmp = ERR_PTR(-ENODEV);
+		goto put;
+	}
+
+	bpmp = platform_get_drvdata(pdev);
+	if (!bpmp) {
+		bpmp = ERR_PTR(-EPROBE_DEFER);
+		put_device(&pdev->dev);
+		goto put;
+	}
+
+put:
+	of_node_put(np);
+	return bpmp;
+}
+EXPORT_SYMBOL_GPL(tegra_bpmp_get);
+
+void tegra_bpmp_put(struct tegra_bpmp *bpmp)
+{
+	if (bpmp)
+		put_device(bpmp->dev);
+}
+EXPORT_SYMBOL_GPL(tegra_bpmp_put);
+
+static int tegra_bpmp_channel_get_index(struct tegra_bpmp_channel *channel)
+{
+	return channel - channel->bpmp->channels;
+}
+
+static int
+tegra_bpmp_channel_get_thread_index(struct tegra_bpmp_channel *channel)
+{
+	struct tegra_bpmp *bpmp = channel->bpmp;
+	unsigned int offset, count;
+	int index;
+
+	offset = bpmp->soc->channels.thread.offset;
+	count = bpmp->soc->channels.thread.count;
+
+	index = tegra_bpmp_channel_get_index(channel);
+	if (index < 0)
+		return index;
+
+	if (index < offset || index >= offset + count)
+		return -EINVAL;
+
+	return index - offset;
+}
+
+static struct tegra_bpmp_channel *
+tegra_bpmp_channel_get_thread(struct tegra_bpmp *bpmp, unsigned int index)
+{
+	unsigned int offset = bpmp->soc->channels.thread.offset;
+	unsigned int count = bpmp->soc->channels.thread.count;
+
+	if (index >= count)
+		return NULL;
+
+	return &bpmp->channels[offset + index];
+}
+
+static struct tegra_bpmp_channel *
+tegra_bpmp_channel_get_tx(struct tegra_bpmp *bpmp)
+{
+	unsigned int offset = bpmp->soc->channels.cpu_tx.offset;
+
+	return &bpmp->channels[offset + smp_processor_id()];
+}
+
+static struct tegra_bpmp_channel *
+tegra_bpmp_channel_get_rx(struct tegra_bpmp *bpmp)
+{
+	unsigned int offset = bpmp->soc->channels.cpu_rx.offset;
+
+	return &bpmp->channels[offset];
+}
+
+static bool tegra_bpmp_message_valid(const struct tegra_bpmp_message *msg)
+{
+	return (msg->tx.size <= MSG_DATA_MIN_SZ) &&
+	       (msg->rx.size <= MSG_DATA_MIN_SZ) &&
+	       (msg->tx.size == 0 || msg->tx.data) &&
+	       (msg->rx.size == 0 || msg->rx.data);
+}
+
+static bool tegra_bpmp_master_acked(struct tegra_bpmp_channel *channel)
+{
+	void *frame;
+
+	frame = tegra_ivc_read_get_next_frame(channel->ivc);
+	if (IS_ERR(frame)) {
+		channel->ib = NULL;
+		return false;
+	}
+
+	channel->ib = frame;
+
+	return true;
+}
+
+static int tegra_bpmp_wait_ack(struct tegra_bpmp_channel *channel)
+{
+	unsigned long timeout = channel->bpmp->soc->channels.cpu_tx.timeout;
+	ktime_t end;
+
+	end = ktime_add_us(ktime_get(), timeout);
+
+	do {
+		if (tegra_bpmp_master_acked(channel))
+			return 0;
+	} while (ktime_before(ktime_get(), end));
+
+	return -ETIMEDOUT;
+}
+
+static bool tegra_bpmp_master_free(struct tegra_bpmp_channel *channel)
+{
+	void *frame;
+
+	frame = tegra_ivc_write_get_next_frame(channel->ivc);
+	if (IS_ERR(frame)) {
+		channel->ob = NULL;
+		return false;
+	}
+
+	channel->ob = frame;
+
+	return true;
+}
+
+static int tegra_bpmp_wait_master_free(struct tegra_bpmp_channel *channel)
+{
+	unsigned long timeout = channel->bpmp->soc->channels.cpu_tx.timeout;
+	ktime_t start, now;
+
+	start = ns_to_ktime(local_clock());
+
+	do {
+		if (tegra_bpmp_master_free(channel))
+			return 0;
+
+		now = ns_to_ktime(local_clock());
+	} while (ktime_us_delta(now, start) < timeout);
+
+	return -ETIMEDOUT;
+}
+
+static ssize_t __tegra_bpmp_channel_read(struct tegra_bpmp_channel *channel,
+					 void *data, size_t size)
+{
+	if (data && size > 0)
+		memcpy(data, channel->ib->data, size);
+
+	return tegra_ivc_read_advance(channel->ivc);
+}
+
+static ssize_t tegra_bpmp_channel_read(struct tegra_bpmp_channel *channel,
+				       void *data, size_t size)
+{
+	struct tegra_bpmp *bpmp = channel->bpmp;
+	unsigned long flags;
+	ssize_t err;
+	int index;
+
+	index = tegra_bpmp_channel_get_thread_index(channel);
+	if (index < 0)
+		return index;
+
+	spin_lock_irqsave(&bpmp->lock, flags);
+	err = __tegra_bpmp_channel_read(channel, data, size);
+	clear_bit(index, bpmp->threaded.allocated);
+	spin_unlock_irqrestore(&bpmp->lock, flags);
+
+	up(&bpmp->threaded.lock);
+
+	return err;
+}
+
+static ssize_t __tegra_bpmp_channel_write(struct tegra_bpmp_channel *channel,
+					  unsigned int mrq, unsigned long flags,
+					  const void *data, size_t size)
+{
+	channel->ob->code = mrq;
+	channel->ob->flags = flags;
+
+	if (data && size > 0)
+		memcpy(channel->ob->data, data, size);
+
+	return tegra_ivc_write_advance(channel->ivc);
+}
+
+static struct tegra_bpmp_channel *
+tegra_bpmp_write_threaded(struct tegra_bpmp *bpmp, unsigned int mrq,
+			  const void *data, size_t size)
+{
+	unsigned long timeout = bpmp->soc->channels.thread.timeout;
+	unsigned int count = bpmp->soc->channels.thread.count;
+	struct tegra_bpmp_channel *channel;
+	unsigned long flags;
+	unsigned int index;
+	int err;
+
+	err = down_timeout(&bpmp->threaded.lock, usecs_to_jiffies(timeout));
+	if (err < 0)
+		return ERR_PTR(err);
+
+	spin_lock_irqsave(&bpmp->lock, flags);
+
+	index = find_first_zero_bit(bpmp->threaded.allocated, count);
+	if (index == count) {
+		channel = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	channel = tegra_bpmp_channel_get_thread(bpmp, index);
+	if (!channel) {
+		channel = ERR_PTR(-EINVAL);
+		goto unlock;
+	}
+
+	if (!tegra_bpmp_master_free(channel)) {
+		channel = ERR_PTR(-EBUSY);
+		goto unlock;
+	}
+
+	set_bit(index, bpmp->threaded.allocated);
+
+	err = __tegra_bpmp_channel_write(channel, mrq, MSG_ACK | MSG_RING,
+					 data, size);
+	if (err < 0) {
+		clear_bit(index, bpmp->threaded.allocated);
+		goto unlock;
+	}
+
+	set_bit(index, bpmp->threaded.busy);
+
+unlock:
+	spin_unlock_irqrestore(&bpmp->lock, flags);
+	return channel;
+}
+
+static ssize_t tegra_bpmp_channel_write(struct tegra_bpmp_channel *channel,
+					unsigned int mrq, unsigned long flags,
+					const void *data, size_t size)
+{
+	int err;
+
+	err = tegra_bpmp_wait_master_free(channel);
+	if (err < 0)
+		return err;
+
+	return __tegra_bpmp_channel_write(channel, mrq, flags, data, size);
+}
+
+int tegra_bpmp_transfer_atomic(struct tegra_bpmp *bpmp,
+			       struct tegra_bpmp_message *msg)
+{
+	struct tegra_bpmp_channel *channel;
+	int err;
+
+	if (WARN_ON(!irqs_disabled()))
+		return -EPERM;
+
+	if (!tegra_bpmp_message_valid(msg))
+		return -EINVAL;
+
+	channel = tegra_bpmp_channel_get_tx(bpmp);
+
+	err = tegra_bpmp_channel_write(channel, msg->mrq, MSG_ACK,
+				       msg->tx.data, msg->tx.size);
+	if (err < 0)
+		return err;
+
+	err = mbox_send_message(bpmp->mbox.channel, NULL);
+	if (err < 0)
+		return err;
+
+	mbox_client_txdone(bpmp->mbox.channel, 0);
+
+	err = tegra_bpmp_wait_ack(channel);
+	if (err < 0)
+		return err;
+
+	return __tegra_bpmp_channel_read(channel, msg->rx.data, msg->rx.size);
+}
+EXPORT_SYMBOL_GPL(tegra_bpmp_transfer_atomic);
+
+int tegra_bpmp_transfer(struct tegra_bpmp *bpmp,
+			struct tegra_bpmp_message *msg)
+{
+	struct tegra_bpmp_channel *channel;
+	unsigned long timeout;
+	int err;
+
+	if (WARN_ON(irqs_disabled()))
+		return -EPERM;
+
+	if (!tegra_bpmp_message_valid(msg))
+		return -EINVAL;
+
+	channel = tegra_bpmp_write_threaded(bpmp, msg->mrq, msg->tx.data,
+					    msg->tx.size);
+	if (IS_ERR(channel))
+		return PTR_ERR(channel);
+
+	err = mbox_send_message(bpmp->mbox.channel, NULL);
+	if (err < 0)
+		return err;
+
+	mbox_client_txdone(bpmp->mbox.channel, 0);
+
+	timeout = usecs_to_jiffies(bpmp->soc->channels.thread.timeout);
+
+	err = wait_for_completion_timeout(&channel->completion, timeout);
+	if (err == 0)
+		return -ETIMEDOUT;
+
+	return tegra_bpmp_channel_read(channel, msg->rx.data, msg->rx.size);
+}
+EXPORT_SYMBOL_GPL(tegra_bpmp_transfer);
+
+static struct tegra_bpmp_mrq *tegra_bpmp_find_mrq(struct tegra_bpmp *bpmp,
+						  unsigned int mrq)
+{
+	struct tegra_bpmp_mrq *entry;
+
+	list_for_each_entry(entry, &bpmp->mrqs, list)
+		if (entry->mrq == mrq)
+			return entry;
+
+	return NULL;
+}
+
+static void tegra_bpmp_mrq_return(struct tegra_bpmp_channel *channel,
+				  int code, const void *data, size_t size)
+{
+	unsigned long flags = channel->ib->flags;
+	struct tegra_bpmp *bpmp = channel->bpmp;
+	struct tegra_bpmp_mb_data *frame;
+	int err;
+
+	if (WARN_ON(size > MSG_DATA_MIN_SZ))
+		return;
+
+	err = tegra_ivc_read_advance(channel->ivc);
+	if (WARN_ON(err < 0))
+		return;
+
+	if ((flags & MSG_ACK) == 0)
+		return;
+
+	frame = tegra_ivc_write_get_next_frame(channel->ivc);
+	if (WARN_ON(IS_ERR(frame)))
+		return;
+
+	frame->code = code;
+
+	if (data && size > 0)
+		memcpy(frame->data, data, size);
+
+	err = tegra_ivc_write_advance(channel->ivc);
+	if (WARN_ON(err < 0))
+		return;
+
+	if (flags & MSG_RING) {
+		err = mbox_send_message(bpmp->mbox.channel, NULL);
+		if (WARN_ON(err < 0))
+			return;
+
+		mbox_client_txdone(bpmp->mbox.channel, 0);
+	}
+}
+
+static void tegra_bpmp_handle_mrq(struct tegra_bpmp *bpmp,
+				  unsigned int mrq,
+				  struct tegra_bpmp_channel *channel)
+{
+	struct tegra_bpmp_mrq *entry;
+	u32 zero = 0;
+
+	spin_lock(&bpmp->lock);
+
+	entry = tegra_bpmp_find_mrq(bpmp, mrq);
+	if (!entry) {
+		spin_unlock(&bpmp->lock);
+		tegra_bpmp_mrq_return(channel, -EINVAL, &zero, sizeof(zero));
+		return;
+	}
+
+	entry->handler(mrq, channel, entry->data);
+
+	spin_unlock(&bpmp->lock);
+}
+
+int tegra_bpmp_request_mrq(struct tegra_bpmp *bpmp, unsigned int mrq,
+			   tegra_bpmp_mrq_handler_t handler, void *data)
+{
+	struct tegra_bpmp_mrq *entry;
+	unsigned long flags;
+
+	if (!handler)
+		return -EINVAL;
+
+	entry = devm_kzalloc(bpmp->dev, sizeof(*entry), GFP_KERNEL);
+	if (!entry)
+		return -ENOMEM;
+
+	spin_lock_irqsave(&bpmp->lock, flags);
+
+	entry->mrq = mrq;
+	entry->handler = handler;
+	entry->data = data;
+	list_add(&entry->list, &bpmp->mrqs);
+
+	spin_unlock_irqrestore(&bpmp->lock, flags);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(tegra_bpmp_request_mrq);
+
+void tegra_bpmp_free_mrq(struct tegra_bpmp *bpmp, unsigned int mrq, void *data)
+{
+	struct tegra_bpmp_mrq *entry;
+	unsigned long flags;
+
+	spin_lock_irqsave(&bpmp->lock, flags);
+
+	entry = tegra_bpmp_find_mrq(bpmp, mrq);
+	if (!entry)
+		goto unlock;
+
+	list_del(&entry->list);
+	devm_kfree(bpmp->dev, entry);
+
+unlock:
+	spin_unlock_irqrestore(&bpmp->lock, flags);
+}
+EXPORT_SYMBOL_GPL(tegra_bpmp_free_mrq);
+
+static void tegra_bpmp_mrq_handle_ping(unsigned int mrq,
+				       struct tegra_bpmp_channel *channel,
+				       void *data)
+{
+	struct mrq_ping_request *request;
+	struct mrq_ping_response response;
+
+	request = (struct mrq_ping_request *)channel->ib->data;
+
+	memset(&response, 0, sizeof(response));
+	response.reply = request->challenge << 1;
+
+	tegra_bpmp_mrq_return(channel, 0, &response, sizeof(response));
+}
+
+static int tegra_bpmp_ping(struct tegra_bpmp *bpmp)
+{
+	struct mrq_ping_response response;
+	struct mrq_ping_request request;
+	struct tegra_bpmp_message msg;
+	unsigned long flags;
+	ktime_t start, end;
+	int err;
+
+	memset(&request, 0, sizeof(request));
+	request.challenge = 1;
+
+	memset(&response, 0, sizeof(response));
+
+	memset(&msg, 0, sizeof(msg));
+	msg.mrq = MRQ_PING;
+	msg.tx.data = &request;
+	msg.tx.size = sizeof(request);
+	msg.rx.data = &response;
+	msg.rx.size = sizeof(response);
+
+	local_irq_save(flags);
+	start = ktime_get();
+	err = tegra_bpmp_transfer_atomic(bpmp, &msg);
+	end = ktime_get();
+	local_irq_restore(flags);
+
+	if (!err)
+		dev_dbg(bpmp->dev,
+			"ping ok: challenge: %u, response: %u, time: %lld\n",
+			request.challenge, response.reply,
+			ktime_to_us(ktime_sub(end, start)));
+
+	return err;
+}
+
+static int tegra_bpmp_get_firmware_tag(struct tegra_bpmp *bpmp, char *tag,
+				       size_t size)
+{
+	struct mrq_query_tag_request request;
+	struct tegra_bpmp_message msg;
+	unsigned long flags;
+	dma_addr_t phys;
+	void *virt;
+	int err;
+
+	virt = dma_alloc_coherent(bpmp->dev, MSG_DATA_MIN_SZ, &phys,
+				  GFP_KERNEL | GFP_DMA32);
+	if (!virt)
+		return -ENOMEM;
+
+	memset(&request, 0, sizeof(request));
+	request.addr = phys;
+
+	memset(&msg, 0, sizeof(msg));
+	msg.mrq = MRQ_QUERY_TAG;
+	msg.tx.data = &request;
+	msg.tx.size = sizeof(request);
+
+	local_irq_save(flags);
+	err = tegra_bpmp_transfer_atomic(bpmp, &msg);
+	local_irq_restore(flags);
+
+	if (err == 0)
+		strlcpy(tag, virt, size);
+
+	dma_free_coherent(bpmp->dev, MSG_DATA_MIN_SZ, virt, phys);
+
+	return err;
+}
+
+static void tegra_bpmp_channel_signal(struct tegra_bpmp_channel *channel)
+{
+	unsigned long flags = channel->ob->flags;
+
+	if ((flags & MSG_RING) == 0)
+		return;
+
+	complete(&channel->completion);
+}
+
+static void tegra_bpmp_handle_rx(struct mbox_client *client, void *data)
+{
+	struct tegra_bpmp *bpmp = mbox_client_to_bpmp(client);
+	struct tegra_bpmp_channel *channel;
+	unsigned int i, count;
+	unsigned long *busy;
+
+	channel = tegra_bpmp_channel_get_rx(bpmp);
+	count = bpmp->soc->channels.thread.count;
+	busy = bpmp->threaded.busy;
+
+	if (tegra_bpmp_master_acked(channel))
+		tegra_bpmp_handle_mrq(bpmp, channel->ib->code, channel);
+
+	spin_lock(&bpmp->lock);
+
+	for_each_set_bit(i, busy, count) {
+		struct tegra_bpmp_channel *channel;
+
+		channel = tegra_bpmp_channel_get_thread(bpmp, i);
+		if (!channel)
+			continue;
+
+		if (tegra_bpmp_master_acked(channel)) {
+			tegra_bpmp_channel_signal(channel);
+			clear_bit(i, busy);
+		}
+	}
+
+	spin_unlock(&bpmp->lock);
+}
+
+static void tegra_bpmp_ivc_notify(struct tegra_ivc *ivc, void *data)
+{
+	struct tegra_bpmp *bpmp = data;
+	int err;
+
+	if (WARN_ON(bpmp->mbox.channel == NULL))
+		return;
+
+	err = mbox_send_message(bpmp->mbox.channel, NULL);
+	if (err < 0)
+		return;
+
+	mbox_client_txdone(bpmp->mbox.channel, 0);
+}
+
+static int tegra_bpmp_channel_init(struct tegra_bpmp_channel *channel,
+				   struct tegra_bpmp *bpmp,
+				   unsigned int index)
+{
+	size_t message_size, queue_size;
+	unsigned int offset;
+	int err;
+
+	channel->ivc = devm_kzalloc(bpmp->dev, sizeof(*channel->ivc),
+				    GFP_KERNEL);
+	if (!channel->ivc)
+		return -ENOMEM;
+
+	message_size = tegra_ivc_align(MSG_MIN_SZ);
+	queue_size = tegra_ivc_total_queue_size(message_size);
+	offset = queue_size * index;
+
+	err = tegra_ivc_init(channel->ivc, NULL,
+			     bpmp->rx.virt + offset, bpmp->rx.phys + offset,
+			     bpmp->tx.virt + offset, bpmp->tx.phys + offset,
+			     1, message_size, tegra_bpmp_ivc_notify,
+			     bpmp);
+	if (err < 0) {
+		dev_err(bpmp->dev, "failed to setup IVC for channel %u: %d\n",
+			index, err);
+		return err;
+	}
+
+	init_completion(&channel->completion);
+	channel->bpmp = bpmp;
+
+	return 0;
+}
+
+static void tegra_bpmp_channel_reset(struct tegra_bpmp_channel *channel)
+{
+	/* reset the channel state */
+	tegra_ivc_reset(channel->ivc);
+
+	/* sync the channel state with BPMP */
+	while (tegra_ivc_notified(channel->ivc))
+		;
+}
+
+static void tegra_bpmp_channel_cleanup(struct tegra_bpmp_channel *channel)
+{
+	tegra_ivc_cleanup(channel->ivc);
+}
+
+static int tegra_bpmp_probe(struct platform_device *pdev)
+{
+	struct tegra_bpmp_channel *channel;
+	struct tegra_bpmp *bpmp;
+	unsigned int i;
+	char tag[32];
+	size_t size;
+	int err;
+
+	bpmp = devm_kzalloc(&pdev->dev, sizeof(*bpmp), GFP_KERNEL);
+	if (!bpmp)
+		return -ENOMEM;
+
+	bpmp->soc = of_device_get_match_data(&pdev->dev);
+	bpmp->dev = &pdev->dev;
+
+	bpmp->tx.pool = of_gen_pool_get(pdev->dev.of_node, "shmem", 0);
+	if (!bpmp->tx.pool) {
+		dev_err(&pdev->dev, "TX shmem pool not found\n");
+		return -ENOMEM;
+	}
+
+	bpmp->tx.virt = gen_pool_dma_alloc(bpmp->tx.pool, 4096, &bpmp->tx.phys);
+	if (!bpmp->tx.virt) {
+		dev_err(&pdev->dev, "failed to allocate from TX pool\n");
+		return -ENOMEM;
+	}
+
+	bpmp->rx.pool = of_gen_pool_get(pdev->dev.of_node, "shmem", 1);
+	if (!bpmp->rx.pool) {
+		dev_err(&pdev->dev, "RX shmem pool not found\n");
+		err = -ENOMEM;
+		goto free_tx;
+	}
+
+	bpmp->rx.virt = gen_pool_dma_alloc(bpmp->rx.pool, 4096, &bpmp->rx.phys);
+	if (!bpmp->rx.pool) {
+		dev_err(&pdev->dev, "failed to allocate from RX pool\n");
+		err = -ENOMEM;
+		goto free_tx;
+	}
+
+	INIT_LIST_HEAD(&bpmp->mrqs);
+	spin_lock_init(&bpmp->lock);
+
+	bpmp->threaded.count = bpmp->soc->channels.thread.count;
+	sema_init(&bpmp->threaded.lock, bpmp->threaded.count);
+
+	size = BITS_TO_LONGS(bpmp->threaded.count) * sizeof(long);
+
+	bpmp->threaded.allocated = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+	if (!bpmp->threaded.allocated) {
+		err = -ENOMEM;
+		goto free_rx;
+	}
+
+	bpmp->threaded.busy = devm_kzalloc(&pdev->dev, size, GFP_KERNEL);
+	if (!bpmp->threaded.busy) {
+		err = -ENOMEM;
+		goto free_rx;
+	}
+
+	bpmp->num_channels = bpmp->soc->channels.cpu_tx.count +
+			     bpmp->soc->channels.thread.count +
+			     bpmp->soc->channels.cpu_rx.count;
+
+	bpmp->channels = devm_kcalloc(&pdev->dev, bpmp->num_channels,
+				      sizeof(*channel), GFP_KERNEL);
+	if (!bpmp->channels) {
+		err = -ENOMEM;
+		goto free_rx;