Merge tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-nextgrafted

Pull networking updates from Jakub Kicinski:
 "Core:

   - Add dedicated kmem_cache for typical/small skb->head, avoid having
     to access struct page at kfree time, and improve memory use.

   - Introduce sysctl to set default RPS configuration for new netdevs.

   - Define Netlink protocol specification format which can be used to
     describe messages used by each family and auto-generate parsers.
     Add tools for generating kernel data structures and uAPI headers.

   - Expose all net/core sysctls inside netns.

   - Remove 4s sleep in netpoll if carrier is instantly detected on
     boot.

   - Add configurable limit of MDB entries per port, and port-vlan.

   - Continue populating drop reasons throughout the stack.

   - Retire a handful of legacy Qdiscs and classifiers.

  Protocols:

   - Support IPv4 big TCP (TSO frames larger than 64kB).

   - Add IP_LOCAL_PORT_RANGE socket option, to control local port range
     on socket by socket basis.

   - Track and report in procfs number of MPTCP sockets used.

   - Support mixing IPv4 and IPv6 flows in the in-kernel MPTCP path
     manager.

   - IPv6: don't check net.ipv6.route.max_size and rely on garbage
     collection to free memory (similarly to IPv4).

   - Support Penultimate Segment Pop (PSP) flavor in SRv6 (RFC8986).

   - ICMP: add per-rate limit counters.

   - Add support for user scanning requests in ieee802154.

   - Remove static WEP support.

   - Support minimal Wi-Fi 7 Extremely High Throughput (EHT) rate
     reporting.

   - WiFi 7 EHT channel puncturing support (client & AP).

  BPF:

   - Add a rbtree data structure following the "next-gen data structure"
     precedent set by recently added linked list, that is, by using
     kfunc + kptr instead of adding a new BPF map type.

   - Expose XDP hints via kfuncs with initial support for RX hash and
     timestamp metadata.

   - Add BPF_F_NO_TUNNEL_KEY extension to bpf_skb_set_tunnel_key to
     better support decap on GRE tunnel devices not operating in collect
     metadata.

   - Improve x86 JIT's codegen for PROBE_MEM runtime error checks.

   - Remove the need for trace_printk_lock for bpf_trace_printk and
     bpf_trace_vprintk helpers.

   - Extend libbpf's bpf_tracing.h support for tracing arguments of
     kprobes/uprobes and syscall as a special case.

   - Significantly reduce the search time for module symbols by
     livepatch and BPF.

   - Enable cpumasks to be used as kptrs, which is useful for tracing
     programs tracking which tasks end up running on which CPUs in
     different time intervals.

   - Add support for BPF trampoline on s390x and riscv64.

   - Add capability to export the XDP features supported by the NIC.

   - Add __bpf_kfunc tag for marking kernel functions as kfuncs.

   - Add cgroup.memory=nobpf kernel parameter option to disable BPF
     memory accounting for container environments.

  Netfilter:

   - Remove the CLUSTERIP target. It has been marked as obsolete for
     years, and we still have WARN splats wrt races of the out-of-band
     /proc interface installed by this target.

   - Add 'destroy' commands to nf_tables. They are identical to the
     existing 'delete' commands, but do not return an error if the
     referenced object (set, chain, rule...) did not exist.

  Driver API:

   - Improve cpumask_local_spread() locality to help NICs set the right
     IRQ affinity on AMD platforms.

   - Separate C22 and C45 MDIO bus transactions more clearly.

   - Introduce new DCB table to control DSCP rewrite on egress.

   - Support configuration of Physical Layer Collision Avoidance (PLCA)
     Reconciliation Sublayer (RS) (802.3cg-2019). Modern version of
     shared medium Ethernet.

   - Support for MAC Merge layer (IEEE 802.3-2018 clause 99). Allowing
     preemption of low priority frames by high priority frames.

   - Add support for controlling MACSec offload using netlink SET.

   - Rework devlink instance refcounts to allow registration and
     de-registration under the instance lock. Split the code into
     multiple files, drop some of the unnecessarily granular locks and
     factor out common parts of netlink operation handling.

   - Add TX frame aggregation parameters (for USB drivers).

   - Add a new attr TCA_EXT_WARN_MSG to report TC (offload) warning
     messages with notifications for debug.

   - Allow offloading of UDP NEW connections via act_ct.

   - Add support for per action HW stats in TC.

   - Support hardware miss to TC action (continue processing in SW from
     a specific point in the action chain).

   - Warn if old Wireless Extension user space interface is used with
     modern cfg80211/mac80211 drivers. Do not support Wireless
     Extensions for Wi-Fi 7 devices at all. Everyone should switch to
     using nl80211 interface instead.

   - Improve the CAN bit timing configuration. Use extack to return
     error messages directly to user space, update the SJW handling,
     including the definition of a new default value that will benefit
     CAN-FD controllers, by increasing their oscillator tolerance.

  New hardware / drivers:

   - Ethernet:
      - nVidia BlueField-3 support (control traffic driver)
      - Ethernet support for imx93 SoCs
      - Motorcomm yt8531 gigabit Ethernet PHY
      - onsemi NCN26000 10BASE-T1S PHY (with support for PLCA)
      - Microchip LAN8841 PHY (incl. cable diagnostics and PTP)
      - Amlogic gxl MDIO mux

   - WiFi:
      - RealTek RTL8188EU (rtl8xxxu)
      - Qualcomm Wi-Fi 7 devices (ath12k)

   - CAN:
      - Renesas R-Car V4H

  Drivers:

   - Bluetooth:
      - Set Per Platform Antenna Gain (PPAG) for Intel controllers.

   - Ethernet NICs:
      - Intel (1G, igc):
         - support TSN / Qbv / packet scheduling features of i226 model
      - Intel (100G, ice):
         - use GNSS subsystem instead of TTY
         - multi-buffer XDP support
         - extend support for GPIO pins to E823 devices
      - nVidia/Mellanox:
         - update the shared buffer configuration on PFC commands
         - implement PTP adjphase function for HW offset control
         - TC support for Geneve and GRE with VF tunnel offload
         - more efficient crypto key management method
         - multi-port eswitch support
      - Netronome/Corigine:
         - add DCB IEEE support
         - support IPsec offloading for NFP3800
      - Freescale/NXP (enetc):
         - support XDP_REDIRECT for XDP non-linear buffers
         - improve reconfig, avoid link flap and waiting for idle
         - support MAC Merge layer
      - Other NICs:
         - sfc/ef100: add basic devlink support for ef100
         - ionic: rx_push mode operation (writing descriptors via MMIO)
         - bnxt: use the auxiliary bus abstraction for RDMA
         - r8169: disable ASPM and reset bus in case of tx timeout
         - cpsw: support QSGMII mode for J721e CPSW9G
         - cpts: support pulse-per-second output
         - ngbe: add an mdio bus driver
         - usbnet: optimize usbnet_bh() by avoiding unnecessary queuing
         - r8152: handle devices with FW with NCM support
         - amd-xgbe: support 10Mbps, 2.5GbE speeds and rx-adaptation
         - virtio-net: support multi buffer XDP
         - virtio/vsock: replace virtio_vsock_pkt with sk_buff
         - tsnep: XDP support

   - Ethernet high-speed switches:
      - nVidia/Mellanox (mlxsw):
         - add support for latency TLV (in FW control messages)
      - Microchip (sparx5):
         - separate explicit and implicit traffic forwarding rules, make
           the implicit rules always active
         - add support for egress DSCP rewrite
         - IS0 VCAP support (Ingress Classification)
         - IS2 VCAP filters (protos, L3 addrs, L4 ports, flags, ToS
           etc.)
         - ES2 VCAP support (Egress Access Control)
         - support for Per-Stream Filtering and Policing (802.1Q,
           8.6.5.1)

   - Ethernet embedded switches:
      - Marvell (mv88e6xxx):
         - add MAB (port auth) offload support
         - enable PTP receive for mv88e6390
      - NXP (ocelot):
         - support MAC Merge layer
         - support for the the vsc7512 internal copper phys
      - Microchip:
         - lan9303: convert to PHYLINK
         - lan966x: support TC flower filter statistics
         - lan937x: PTP support for KSZ9563/KSZ8563 and LAN937x
         - lan937x: support Credit Based Shaper configuration
         - ksz9477: support Energy Efficient Ethernet
      - other:
         - qca8k: convert to regmap read/write API, use bulk operations
         - rswitch: Improve TX timestamp accuracy

   - Intel WiFi (iwlwifi):
      - EHT (Wi-Fi 7) rate reporting
      - STEP equalizer support: transfer some STEP (connection to radio
        on platforms with integrated wifi) related parameters from the
        BIOS to the firmware.

   - Qualcomm 802.11ax WiFi (ath11k):
      - IPQ5018 support
      - Fine Timing Measurement (FTM) responder role support
      - channel 177 support

   - MediaTek WiFi (mt76):
      - per-PHY LED support
      - mt7996: EHT (Wi-Fi 7) support
      - Wireless Ethernet Dispatch (WED) reset support
      - switch to using page pool allocator

   - RealTek WiFi (rtw89):
      - support new version of Bluetooth co-existance

   - Mobile:
      - rmnet: support TX aggregation"

* tag 'net-next-6.3' of git://git.kernel.org/pub/scm/linux/kernel/git/netdev/net-next: (1872 commits)
  page_pool: add a comment explaining the fragment counter usage
  net: ethtool: fix __ethtool_dev_mm_supported() implementation
  ethtool: pse-pd: Fix double word in comments
  xsk: add linux/vmalloc.h to xsk.c
  sefltests: netdevsim: wait for devlink instance after netns removal
  selftest: fib_tests: Always cleanup before exit
  net/mlx5e: Align IPsec ASO result memory to be as required by hardware
  net/mlx5e: TC, Set CT miss to the specific ct action instance
  net/mlx5e: Rename CHAIN_TO_REG to MAPPED_OBJ_TO_REG
  net/mlx5: Refactor tc miss handling to a single function
  net/mlx5: Kconfig: Make tc offload depend on tc skb extension
  net/sched: flower: Support hardware miss to tc action
  net/sched: flower: Move filter handle initialization earlier
  net/sched: cls_api: Support hardware miss to tc action
  net/sched: Rename user cookie and act cookie
  sfc: fix builds without CONFIG_RTC_LIB
  sfc: clean up some inconsistent indentings
  net/mlx4_en: Introduce flexible array to silence overflow warning
  net: lan966x: Fix possible deadlock inside PTP
  net/ulp: Remove redundant ->clone() test in inet_clone_ulp().
  ...

1 files changed, 574 insertions, 0 deletions

diff --git a/drivers/soc/qcom/qcom_aoss.c b/drivers/soc/qcom/qcom_aoss.c
new file mode 100644
index 000000000..18c856056
--- /dev/null
+++ b/drivers/soc/qcom/qcom_aoss.c
@@ -0,0 +1,574 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Copyright (c) 2019, Linaro Ltd
+ */
+#include <linux/clk-provider.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/mailbox_client.h>
+#include <linux/module.h>
+#include <linux/of_platform.h>
+#include <linux/platform_device.h>
+#include <linux/thermal.h>
+#include <linux/slab.h>
+#include <linux/soc/qcom/qcom_aoss.h>
+
+#define QMP_DESC_MAGIC			0x0
+#define QMP_DESC_VERSION		0x4
+#define QMP_DESC_FEATURES		0x8
+
+/* AOP-side offsets */
+#define QMP_DESC_UCORE_LINK_STATE	0xc
+#define QMP_DESC_UCORE_LINK_STATE_ACK	0x10
+#define QMP_DESC_UCORE_CH_STATE		0x14
+#define QMP_DESC_UCORE_CH_STATE_ACK	0x18
+#define QMP_DESC_UCORE_MBOX_SIZE	0x1c
+#define QMP_DESC_UCORE_MBOX_OFFSET	0x20
+
+/* Linux-side offsets */
+#define QMP_DESC_MCORE_LINK_STATE	0x24
+#define QMP_DESC_MCORE_LINK_STATE_ACK	0x28
+#define QMP_DESC_MCORE_CH_STATE		0x2c
+#define QMP_DESC_MCORE_CH_STATE_ACK	0x30
+#define QMP_DESC_MCORE_MBOX_SIZE	0x34
+#define QMP_DESC_MCORE_MBOX_OFFSET	0x38
+
+#define QMP_STATE_UP			GENMASK(15, 0)
+#define QMP_STATE_DOWN			GENMASK(31, 16)
+
+#define QMP_MAGIC			0x4d41494c /* mail */
+#define QMP_VERSION			1
+
+/* 64 bytes is enough to store the requests and provides padding to 4 bytes */
+#define QMP_MSG_LEN			64
+
+#define QMP_NUM_COOLING_RESOURCES	2
+
+static bool qmp_cdev_max_state = 1;
+
+struct qmp_cooling_device {
+	struct thermal_cooling_device *cdev;
+	struct qmp *qmp;
+	char *name;
+	bool state;
+};
+
+/**
+ * struct qmp - driver state for QMP implementation
+ * @msgram: iomem referencing the message RAM used for communication
+ * @dev: reference to QMP device
+ * @mbox_client: mailbox client used to ring the doorbell on transmit
+ * @mbox_chan: mailbox channel used to ring the doorbell on transmit
+ * @offset: offset within @msgram where messages should be written
+ * @size: maximum size of the messages to be transmitted
+ * @event: wait_queue for synchronization with the IRQ
+ * @tx_lock: provides synchronization between multiple callers of qmp_send()
+ * @qdss_clk: QDSS clock hw struct
+ * @cooling_devs: thermal cooling devices
+ */
+struct qmp {
+	void __iomem *msgram;
+	struct device *dev;
+
+	struct mbox_client mbox_client;
+	struct mbox_chan *mbox_chan;
+
+	size_t offset;
+	size_t size;
+
+	wait_queue_head_t event;
+
+	struct mutex tx_lock;
+
+	struct clk_hw qdss_clk;
+	struct qmp_cooling_device *cooling_devs;
+};
+
+static void qmp_kick(struct qmp *qmp)
+{
+	mbox_send_message(qmp->mbox_chan, NULL);
+	mbox_client_txdone(qmp->mbox_chan, 0);
+}
+
+static bool qmp_magic_valid(struct qmp *qmp)
+{
+	return readl(qmp->msgram + QMP_DESC_MAGIC) == QMP_MAGIC;
+}
+
+static bool qmp_link_acked(struct qmp *qmp)
+{
+	return readl(qmp->msgram + QMP_DESC_MCORE_LINK_STATE_ACK) == QMP_STATE_UP;
+}
+
+static bool qmp_mcore_channel_acked(struct qmp *qmp)
+{
+	return readl(qmp->msgram + QMP_DESC_MCORE_CH_STATE_ACK) == QMP_STATE_UP;
+}
+
+static bool qmp_ucore_channel_up(struct qmp *qmp)
+{
+	return readl(qmp->msgram + QMP_DESC_UCORE_CH_STATE) == QMP_STATE_UP;
+}
+
+static int qmp_open(struct qmp *qmp)
+{
+	int ret;
+	u32 val;
+
+	if (!qmp_magic_valid(qmp)) {
+		dev_err(qmp->dev, "QMP magic doesn't match\n");
+		return -EINVAL;
+	}
+
+	val = readl(qmp->msgram + QMP_DESC_VERSION);
+	if (val != QMP_VERSION) {
+		dev_err(qmp->dev, "unsupported QMP version %d\n", val);
+		return -EINVAL;
+	}
+
+	qmp->offset = readl(qmp->msgram + QMP_DESC_MCORE_MBOX_OFFSET);
+	qmp->size = readl(qmp->msgram + QMP_DESC_MCORE_MBOX_SIZE);
+	if (!qmp->size) {
+		dev_err(qmp->dev, "invalid mailbox size\n");
+		return -EINVAL;
+	}
+
+	/* Ack remote core's link state */
+	val = readl(qmp->msgram + QMP_DESC_UCORE_LINK_STATE);
+	writel(val, qmp->msgram + QMP_DESC_UCORE_LINK_STATE_ACK);
+
+	/* Set local core's link state to up */
+	writel(QMP_STATE_UP, qmp->msgram + QMP_DESC_MCORE_LINK_STATE);
+
+	qmp_kick(qmp);
+
+	ret = wait_event_timeout(qmp->event, qmp_link_acked(qmp), HZ);
+	if (!ret) {
+		dev_err(qmp->dev, "ucore didn't ack link\n");
+		goto timeout_close_link;
+	}
+
+	writel(QMP_STATE_UP, qmp->msgram + QMP_DESC_MCORE_CH_STATE);
+
+	qmp_kick(qmp);
+
+	ret = wait_event_timeout(qmp->event, qmp_ucore_channel_up(qmp), HZ);
+	if (!ret) {
+		dev_err(qmp->dev, "ucore didn't open channel\n");
+		goto timeout_close_channel;
+	}
+
+	/* Ack remote core's channel state */
+	writel(QMP_STATE_UP, qmp->msgram + QMP_DESC_UCORE_CH_STATE_ACK);
+
+	qmp_kick(qmp);
+
+	ret = wait_event_timeout(qmp->event, qmp_mcore_channel_acked(qmp), HZ);
+	if (!ret) {
+		dev_err(qmp->dev, "ucore didn't ack channel\n");
+		goto timeout_close_channel;
+	}
+
+	return 0;
+
+timeout_close_channel:
+	writel(QMP_STATE_DOWN, qmp->msgram + QMP_DESC_MCORE_CH_STATE);
+
+timeout_close_link:
+	writel(QMP_STATE_DOWN, qmp->msgram + QMP_DESC_MCORE_LINK_STATE);
+	qmp_kick(qmp);
+
+	return -ETIMEDOUT;
+}
+
+static void qmp_close(struct qmp *qmp)
+{
+	writel(QMP_STATE_DOWN, qmp->msgram + QMP_DESC_MCORE_CH_STATE);
+	writel(QMP_STATE_DOWN, qmp->msgram + QMP_DESC_MCORE_LINK_STATE);
+	qmp_kick(qmp);
+}
+
+static irqreturn_t qmp_intr(int irq, void *data)
+{
+	struct qmp *qmp = data;
+
+	wake_up_all(&qmp->event);
+
+	return IRQ_HANDLED;
+}
+
+static bool qmp_message_empty(struct qmp *qmp)
+{
+	return readl(qmp->msgram + qmp->offset) == 0;
+}
+
+/**
+ * qmp_send() - send a message to the AOSS
+ * @qmp: qmp context
+ * @data: message to be sent
+ * @len: length of the message
+ *
+ * Transmit @data to AOSS and wait for the AOSS to acknowledge the message.
+ * @len must be a multiple of 4 and not longer than the mailbox size. Access is
+ * synchronized by this implementation.
+ *
+ * Return: 0 on success, negative errno on failure
+ */
+int qmp_send(struct qmp *qmp, const void *data, size_t len)
+{
+	long time_left;
+	int ret;
+
+	if (WARN_ON(IS_ERR_OR_NULL(qmp) || !data))
+		return -EINVAL;
+
+	if (WARN_ON(len + sizeof(u32) > qmp->size))
+		return -EINVAL;
+
+	if (WARN_ON(len % sizeof(u32)))
+		return -EINVAL;
+
+	mutex_lock(&qmp->tx_lock);
+
+	/* The message RAM only implements 32-bit accesses */
+	__iowrite32_copy(qmp->msgram + qmp->offset + sizeof(u32),
+			 data, len / sizeof(u32));
+	writel(len, qmp->msgram + qmp->offset);
+
+	/* Read back len to confirm data written in message RAM */
+	readl(qmp->msgram + qmp->offset);
+	qmp_kick(qmp);
+
+	time_left = wait_event_interruptible_timeout(qmp->event,
+						     qmp_message_empty(qmp), HZ);
+	if (!time_left) {
+		dev_err(qmp->dev, "ucore did not ack channel\n");
+		ret = -ETIMEDOUT;
+
+		/* Clear message from buffer */
+		writel(0, qmp->msgram + qmp->offset);
+	} else {
+		ret = 0;
+	}
+
+	mutex_unlock(&qmp->tx_lock);
+
+	return ret;
+}
+EXPORT_SYMBOL(qmp_send);
+
+static int qmp_qdss_clk_prepare(struct clk_hw *hw)
+{
+	static const char buf[QMP_MSG_LEN] = "{class: clock, res: qdss, val: 1}";
+	struct qmp *qmp = container_of(hw, struct qmp, qdss_clk);
+
+	return qmp_send(qmp, buf, sizeof(buf));
+}
+
+static void qmp_qdss_clk_unprepare(struct clk_hw *hw)
+{
+	static const char buf[QMP_MSG_LEN] = "{class: clock, res: qdss, val: 0}";
+	struct qmp *qmp = container_of(hw, struct qmp, qdss_clk);
+
+	qmp_send(qmp, buf, sizeof(buf));
+}
+
+static const struct clk_ops qmp_qdss_clk_ops = {
+	.prepare = qmp_qdss_clk_prepare,
+	.unprepare = qmp_qdss_clk_unprepare,
+};
+
+static int qmp_qdss_clk_add(struct qmp *qmp)
+{
+	static const struct clk_init_data qdss_init = {
+		.ops = &qmp_qdss_clk_ops,
+		.name = "qdss",
+	};
+	int ret;
+
+	qmp->qdss_clk.init = &qdss_init;
+	ret = clk_hw_register(qmp->dev, &qmp->qdss_clk);
+	if (ret < 0) {
+		dev_err(qmp->dev, "failed to register qdss clock\n");
+		return ret;
+	}
+
+	ret = of_clk_add_hw_provider(qmp->dev->of_node, of_clk_hw_simple_get,
+				     &qmp->qdss_clk);
+	if (ret < 0) {
+		dev_err(qmp->dev, "unable to register of clk hw provider\n");
+		clk_hw_unregister(&qmp->qdss_clk);
+	}
+
+	return ret;
+}
+
+static void qmp_qdss_clk_remove(struct qmp *qmp)
+{
+	of_clk_del_provider(qmp->dev->of_node);
+	clk_hw_unregister(&qmp->qdss_clk);
+}
+
+static int qmp_cdev_get_max_state(struct thermal_cooling_device *cdev,
+				  unsigned long *state)
+{
+	*state = qmp_cdev_max_state;
+	return 0;
+}
+
+static int qmp_cdev_get_cur_state(struct thermal_cooling_device *cdev,
+				  unsigned long *state)
+{
+	struct qmp_cooling_device *qmp_cdev = cdev->devdata;
+
+	*state = qmp_cdev->state;
+	return 0;
+}
+
+static int qmp_cdev_set_cur_state(struct thermal_cooling_device *cdev,
+				  unsigned long state)
+{
+	struct qmp_cooling_device *qmp_cdev = cdev->devdata;
+	char buf[QMP_MSG_LEN] = {};
+	bool cdev_state;
+	int ret;
+
+	/* Normalize state */
+	cdev_state = !!state;
+
+	if (qmp_cdev->state == state)
+		return 0;
+
+	snprintf(buf, sizeof(buf),
+		 "{class: volt_flr, event:zero_temp, res:%s, value:%s}",
+			qmp_cdev->name,
+			cdev_state ? "on" : "off");
+
+	ret = qmp_send(qmp_cdev->qmp, buf, sizeof(buf));
+
+	if (!ret)
+		qmp_cdev->state = cdev_state;
+
+	return ret;
+}
+
+static const struct thermal_cooling_device_ops qmp_cooling_device_ops = {
+	.get_max_state = qmp_cdev_get_max_state,
+	.get_cur_state = qmp_cdev_get_cur_state,
+	.set_cur_state = qmp_cdev_set_cur_state,
+};
+
+static int qmp_cooling_device_add(struct qmp *qmp,
+				  struct qmp_cooling_device *qmp_cdev,
+				  struct device_node *node)
+{
+	char *cdev_name = (char *)node->name;
+
+	qmp_cdev->qmp = qmp;
+	qmp_cdev->state = !qmp_cdev_max_state;
+	qmp_cdev->name = cdev_name;
+	qmp_cdev->cdev = devm_thermal_of_cooling_device_register
+				(qmp->dev, node,
+				cdev_name,
+				qmp_cdev, &qmp_cooling_device_ops);
+
+	if (IS_ERR(qmp_cdev->cdev))
+		dev_err(qmp->dev, "unable to register %s cooling device\n",
+			cdev_name);
+
+	return PTR_ERR_OR_ZERO(qmp_cdev->cdev);
+}
+
+static int qmp_cooling_devices_register(struct qmp *qmp)
+{
+	struct device_node *np, *child;
+	int count = 0;
+	int ret;
+
+	np = qmp->dev->of_node;
+
+	qmp->cooling_devs = devm_kcalloc(qmp->dev, QMP_NUM_COOLING_RESOURCES,
+					 sizeof(*qmp->cooling_devs),
+					 GFP_KERNEL);
+
+	if (!qmp->cooling_devs)
+		return -ENOMEM;
+
+	for_each_available_child_of_node(np, child) {
+		if (!of_find_property(child, "#cooling-cells", NULL))
+			continue;
+		ret = qmp_cooling_device_add(qmp, &qmp->cooling_devs[count++],
+					     child);
+		if (ret) {
+			of_node_put(child);
+			goto unroll;
+		}
+	}
+
+	if (!count)
+		devm_kfree(qmp->dev, qmp->cooling_devs);
+
+	return 0;
+
+unroll:
+	while (--count >= 0)
+		thermal_cooling_device_unregister
+			(qmp->cooling_devs[count].cdev);
+	devm_kfree(qmp->dev, qmp->cooling_devs);
+
+	return ret;
+}
+
+static void qmp_cooling_devices_remove(struct qmp *qmp)
+{
+	int i;
+
+	for (i = 0; i < QMP_NUM_COOLING_RESOURCES; i++)
+		thermal_cooling_device_unregister(qmp->cooling_devs[i].cdev);
+}
+
+/**
+ * qmp_get() - get a qmp handle from a device
+ * @dev: client device pointer
+ *
+ * Return: handle to qmp device on success, ERR_PTR() on failure
+ */
+struct qmp *qmp_get(struct device *dev)
+{
+	struct platform_device *pdev;
+	struct device_node *np;
+	struct qmp *qmp;
+
+	if (!dev || !dev->of_node)
+		return ERR_PTR(-EINVAL);
+
+	np = of_parse_phandle(dev->of_node, "qcom,qmp", 0);
+	if (!np)
+		return ERR_PTR(-ENODEV);
+
+	pdev = of_find_device_by_node(np);
+	of_node_put(np);
+	if (!pdev)
+		return ERR_PTR(-EINVAL);
+
+	qmp = platform_get_drvdata(pdev);
+
+	if (!qmp) {
+		put_device(&pdev->dev);
+		return ERR_PTR(-EPROBE_DEFER);
+	}
+	return qmp;
+}
+EXPORT_SYMBOL(qmp_get);
+
+/**
+ * qmp_put() - release a qmp handle
+ * @qmp: qmp handle obtained from qmp_get()
+ */
+void qmp_put(struct qmp *qmp)
+{
+	/*
+	 * Match get_device() inside of_find_device_by_node() in
+	 * qmp_get()
+	 */
+	if (!IS_ERR_OR_NULL(qmp))
+		put_device(qmp->dev);
+}
+EXPORT_SYMBOL(qmp_put);
+
+static int qmp_probe(struct platform_device *pdev)
+{
+	struct qmp *qmp;
+	int irq;
+	int ret;
+
+	qmp = devm_kzalloc(&pdev->dev, sizeof(*qmp), GFP_KERNEL);
+	if (!qmp)
+		return -ENOMEM;
+
+	qmp->dev = &pdev->dev;
+	init_waitqueue_head(&qmp->event);
+	mutex_init(&qmp->tx_lock);
+
+	qmp->msgram = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(qmp->msgram))
+		return PTR_ERR(qmp->msgram);
+
+	qmp->mbox_client.dev = &pdev->dev;
+	qmp->mbox_client.knows_txdone = true;
+	qmp->mbox_chan = mbox_request_channel(&qmp->mbox_client, 0);
+	if (IS_ERR(qmp->mbox_chan)) {
+		dev_err(&pdev->dev, "failed to acquire ipc mailbox\n");
+		return PTR_ERR(qmp->mbox_chan);
+	}
+
+	irq = platform_get_irq(pdev, 0);
+	ret = devm_request_irq(&pdev->dev, irq, qmp_intr, 0,
+			       "aoss-qmp", qmp);
+	if (ret < 0) {
+		dev_err(&pdev->dev, "failed to request interrupt\n");
+		goto err_free_mbox;
+	}
+
+	ret = qmp_open(qmp);
+	if (ret < 0)
+		goto err_free_mbox;
+
+	ret = qmp_qdss_clk_add(qmp);
+	if (ret)
+		goto err_close_qmp;
+
+	ret = qmp_cooling_devices_register(qmp);
+	if (ret)
+		dev_err(&pdev->dev, "failed to register aoss cooling devices\n");
+
+	platform_set_drvdata(pdev, qmp);
+
+	return 0;
+
+err_close_qmp:
+	qmp_close(qmp);
+err_free_mbox:
+	mbox_free_channel(qmp->mbox_chan);
+
+	return ret;
+}
+
+static int qmp_remove(struct platform_device *pdev)
+{
+	struct qmp *qmp = platform_get_drvdata(pdev);
+
+	qmp_qdss_clk_remove(qmp);
+	qmp_cooling_devices_remove(qmp);
+
+	qmp_close(qmp);
+	mbox_free_channel(qmp->mbox_chan);
+
+	return 0;
+}
+
+static const struct of_device_id qmp_dt_match[] = {
+	{ .compatible = "qcom,sc7180-aoss-qmp", },
+	{ .compatible = "qcom,sc7280-aoss-qmp", },
+	{ .compatible = "qcom,sdm845-aoss-qmp", },
+	{ .compatible = "qcom,sm8150-aoss-qmp", },
+	{ .compatible = "qcom,sm8250-aoss-qmp", },
+	{ .compatible = "qcom,sm8350-aoss-qmp", },
+	{ .compatible = "qcom,aoss-qmp", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, qmp_dt_match);
+
+static struct platform_driver qmp_driver = {
+	.driver = {
+		.name		= "qcom_aoss_qmp",
+		.of_match_table	= qmp_dt_match,
+		.suppress_bind_attrs = true,
+	},
+	.probe = qmp_probe,
+	.remove	= qmp_remove,
+};
+module_platform_driver(qmp_driver);
+
+MODULE_DESCRIPTION("Qualcomm AOSS QMP driver");
+MODULE_LICENSE("GPL v2");