Adding upstream version 6.1.76.upstream/6.1.76

Signed-off-by: Daniel Baumann <daniel.baumann@progress-linux.org>

4 files changed, 1278 insertions, 0 deletions

diff --git a/drivers/hwtracing/ptt/Kconfig b/drivers/hwtracing/ptt/Kconfig
new file mode 100644
index 000000000..6d46a09ff
--- /dev/null
+++ b/drivers/hwtracing/ptt/Kconfig
@@ -0,0 +1,12 @@
+# SPDX-License-Identifier: GPL-2.0-only
+config HISI_PTT
+	tristate "HiSilicon PCIe Tune and Trace Device"
+	depends on ARM64 || (COMPILE_TEST && 64BIT)
+	depends on PCI && HAS_DMA && HAS_IOMEM && PERF_EVENTS
+	help
+	  HiSilicon PCIe Tune and Trace device exists as a PCIe RCiEP
+	  device, and it provides support for PCIe traffic tuning and
+	  tracing TLP headers to the memory.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called hisi_ptt.
diff --git a/drivers/hwtracing/ptt/Makefile b/drivers/hwtracing/ptt/Makefile
new file mode 100644
index 000000000..908c09a98
--- /dev/null
+++ b/drivers/hwtracing/ptt/Makefile
@@ -0,0 +1,2 @@
+# SPDX-License-Identifier: GPL-2.0
+obj-$(CONFIG_HISI_PTT) += hisi_ptt.o
diff --git a/drivers/hwtracing/ptt/hisi_ptt.c b/drivers/hwtracing/ptt/hisi_ptt.c
new file mode 100644
index 000000000..8d8fa8e8a
--- /dev/null
+++ b/drivers/hwtracing/ptt/hisi_ptt.c
@@ -0,0 +1,1062 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for HiSilicon PCIe tune and trace device
+ *
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ * Author: Yicong Yang <yangyicong@hisilicon.com>
+ */
+
+#include <linux/bitfield.h>
+#include <linux/bitops.h>
+#include <linux/cpuhotplug.h>
+#include <linux/delay.h>
+#include <linux/dma-mapping.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iommu.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/sysfs.h>
+#include <linux/vmalloc.h>
+
+#include "hisi_ptt.h"
+
+/* Dynamic CPU hotplug state used by PTT */
+static enum cpuhp_state hisi_ptt_pmu_online;
+
+static bool hisi_ptt_wait_tuning_finish(struct hisi_ptt *hisi_ptt)
+{
+	u32 val;
+
+	return !readl_poll_timeout(hisi_ptt->iobase + HISI_PTT_TUNING_INT_STAT,
+				   val, !(val & HISI_PTT_TUNING_INT_STAT_MASK),
+				   HISI_PTT_WAIT_POLL_INTERVAL_US,
+				   HISI_PTT_WAIT_TUNE_TIMEOUT_US);
+}
+
+static ssize_t hisi_ptt_tune_attr_show(struct device *dev,
+				       struct device_attribute *attr,
+				       char *buf)
+{
+	struct hisi_ptt *hisi_ptt = to_hisi_ptt(dev_get_drvdata(dev));
+	struct dev_ext_attribute *ext_attr;
+	struct hisi_ptt_tune_desc *desc;
+	u32 reg;
+	u16 val;
+
+	ext_attr = container_of(attr, struct dev_ext_attribute, attr);
+	desc = ext_attr->var;
+
+	mutex_lock(&hisi_ptt->tune_lock);
+
+	reg = readl(hisi_ptt->iobase + HISI_PTT_TUNING_CTRL);
+	reg &= ~(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB);
+	reg |= FIELD_PREP(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB,
+			  desc->event_code);
+	writel(reg, hisi_ptt->iobase + HISI_PTT_TUNING_CTRL);
+
+	/* Write all 1 to indicates it's the read process */
+	writel(~0U, hisi_ptt->iobase + HISI_PTT_TUNING_DATA);
+
+	if (!hisi_ptt_wait_tuning_finish(hisi_ptt)) {
+		mutex_unlock(&hisi_ptt->tune_lock);
+		return -ETIMEDOUT;
+	}
+
+	reg = readl(hisi_ptt->iobase + HISI_PTT_TUNING_DATA);
+	reg &= HISI_PTT_TUNING_DATA_VAL_MASK;
+	val = FIELD_GET(HISI_PTT_TUNING_DATA_VAL_MASK, reg);
+
+	mutex_unlock(&hisi_ptt->tune_lock);
+	return sysfs_emit(buf, "%u\n", val);
+}
+
+static ssize_t hisi_ptt_tune_attr_store(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct hisi_ptt *hisi_ptt = to_hisi_ptt(dev_get_drvdata(dev));
+	struct dev_ext_attribute *ext_attr;
+	struct hisi_ptt_tune_desc *desc;
+	u32 reg;
+	u16 val;
+
+	ext_attr = container_of(attr, struct dev_ext_attribute, attr);
+	desc = ext_attr->var;
+
+	if (kstrtou16(buf, 10, &val))
+		return -EINVAL;
+
+	mutex_lock(&hisi_ptt->tune_lock);
+
+	reg = readl(hisi_ptt->iobase + HISI_PTT_TUNING_CTRL);
+	reg &= ~(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB);
+	reg |= FIELD_PREP(HISI_PTT_TUNING_CTRL_CODE | HISI_PTT_TUNING_CTRL_SUB,
+			  desc->event_code);
+	writel(reg, hisi_ptt->iobase + HISI_PTT_TUNING_CTRL);
+	writel(FIELD_PREP(HISI_PTT_TUNING_DATA_VAL_MASK, val),
+	       hisi_ptt->iobase + HISI_PTT_TUNING_DATA);
+
+	if (!hisi_ptt_wait_tuning_finish(hisi_ptt)) {
+		mutex_unlock(&hisi_ptt->tune_lock);
+		return -ETIMEDOUT;
+	}
+
+	mutex_unlock(&hisi_ptt->tune_lock);
+	return count;
+}
+
+#define HISI_PTT_TUNE_ATTR(_name, _val, _show, _store)			\
+	static struct hisi_ptt_tune_desc _name##_desc = {		\
+		.name = #_name,						\
+		.event_code = (_val),					\
+	};								\
+	static struct dev_ext_attribute hisi_ptt_##_name##_attr = {	\
+		.attr	= __ATTR(_name, 0600, _show, _store),		\
+		.var	= &_name##_desc,				\
+	}
+
+#define HISI_PTT_TUNE_ATTR_COMMON(_name, _val)		\
+	HISI_PTT_TUNE_ATTR(_name, _val,			\
+			   hisi_ptt_tune_attr_show,	\
+			   hisi_ptt_tune_attr_store)
+
+/*
+ * The value of the tuning event are composed of two parts: main event code
+ * in BIT[0,15] and subevent code in BIT[16,23]. For example, qox_tx_cpl is
+ * a subevent of 'Tx path QoS control' which for tuning the weight of Tx
+ * completion TLPs. See hisi_ptt.rst documentation for more information.
+ */
+#define HISI_PTT_TUNE_QOS_TX_CPL		(0x4 | (3 << 16))
+#define HISI_PTT_TUNE_QOS_TX_NP			(0x4 | (4 << 16))
+#define HISI_PTT_TUNE_QOS_TX_P			(0x4 | (5 << 16))
+#define HISI_PTT_TUNE_RX_ALLOC_BUF_LEVEL	(0x5 | (6 << 16))
+#define HISI_PTT_TUNE_TX_ALLOC_BUF_LEVEL	(0x5 | (7 << 16))
+
+HISI_PTT_TUNE_ATTR_COMMON(qos_tx_cpl, HISI_PTT_TUNE_QOS_TX_CPL);
+HISI_PTT_TUNE_ATTR_COMMON(qos_tx_np, HISI_PTT_TUNE_QOS_TX_NP);
+HISI_PTT_TUNE_ATTR_COMMON(qos_tx_p, HISI_PTT_TUNE_QOS_TX_P);
+HISI_PTT_TUNE_ATTR_COMMON(rx_alloc_buf_level, HISI_PTT_TUNE_RX_ALLOC_BUF_LEVEL);
+HISI_PTT_TUNE_ATTR_COMMON(tx_alloc_buf_level, HISI_PTT_TUNE_TX_ALLOC_BUF_LEVEL);
+
+static struct attribute *hisi_ptt_tune_attrs[] = {
+	&hisi_ptt_qos_tx_cpl_attr.attr.attr,
+	&hisi_ptt_qos_tx_np_attr.attr.attr,
+	&hisi_ptt_qos_tx_p_attr.attr.attr,
+	&hisi_ptt_rx_alloc_buf_level_attr.attr.attr,
+	&hisi_ptt_tx_alloc_buf_level_attr.attr.attr,
+	NULL,
+};
+
+static struct attribute_group hisi_ptt_tune_group = {
+	.name	= "tune",
+	.attrs	= hisi_ptt_tune_attrs,
+};
+
+static u16 hisi_ptt_get_filter_val(u16 devid, bool is_port)
+{
+	if (is_port)
+		return BIT(HISI_PCIE_CORE_PORT_ID(devid & 0xff));
+
+	return devid;
+}
+
+static bool hisi_ptt_wait_trace_hw_idle(struct hisi_ptt *hisi_ptt)
+{
+	u32 val;
+
+	return !readl_poll_timeout_atomic(hisi_ptt->iobase + HISI_PTT_TRACE_STS,
+					  val, val & HISI_PTT_TRACE_IDLE,
+					  HISI_PTT_WAIT_POLL_INTERVAL_US,
+					  HISI_PTT_WAIT_TRACE_TIMEOUT_US);
+}
+
+static void hisi_ptt_wait_dma_reset_done(struct hisi_ptt *hisi_ptt)
+{
+	u32 val;
+
+	readl_poll_timeout_atomic(hisi_ptt->iobase + HISI_PTT_TRACE_WR_STS,
+				  val, !val, HISI_PTT_RESET_POLL_INTERVAL_US,
+				  HISI_PTT_RESET_TIMEOUT_US);
+}
+
+static void hisi_ptt_trace_end(struct hisi_ptt *hisi_ptt)
+{
+	writel(0, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+	hisi_ptt->trace_ctrl.started = false;
+}
+
+static int hisi_ptt_trace_start(struct hisi_ptt *hisi_ptt)
+{
+	struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl;
+	u32 val;
+	int i;
+
+	/* Check device idle before start trace */
+	if (!hisi_ptt_wait_trace_hw_idle(hisi_ptt)) {
+		pci_err(hisi_ptt->pdev, "Failed to start trace, the device is still busy\n");
+		return -EBUSY;
+	}
+
+	ctrl->started = true;
+
+	/* Reset the DMA before start tracing */
+	val = readl(hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+	val |= HISI_PTT_TRACE_CTRL_RST;
+	writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+
+	hisi_ptt_wait_dma_reset_done(hisi_ptt);
+
+	val = readl(hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+	val &= ~HISI_PTT_TRACE_CTRL_RST;
+	writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+
+	/* Reset the index of current buffer */
+	hisi_ptt->trace_ctrl.buf_index = 0;
+
+	/* Zero the trace buffers */
+	for (i = 0; i < HISI_PTT_TRACE_BUF_CNT; i++)
+		memset(ctrl->trace_buf[i].addr, 0, HISI_PTT_TRACE_BUF_SIZE);
+
+	/* Clear the interrupt status */
+	writel(HISI_PTT_TRACE_INT_STAT_MASK, hisi_ptt->iobase + HISI_PTT_TRACE_INT_STAT);
+	writel(0, hisi_ptt->iobase + HISI_PTT_TRACE_INT_MASK);
+
+	/* Set the trace control register */
+	val = FIELD_PREP(HISI_PTT_TRACE_CTRL_TYPE_SEL, ctrl->type);
+	val |= FIELD_PREP(HISI_PTT_TRACE_CTRL_RXTX_SEL, ctrl->direction);
+	val |= FIELD_PREP(HISI_PTT_TRACE_CTRL_DATA_FORMAT, ctrl->format);
+	val |= FIELD_PREP(HISI_PTT_TRACE_CTRL_TARGET_SEL, hisi_ptt->trace_ctrl.filter);
+	if (!hisi_ptt->trace_ctrl.is_port)
+		val |= HISI_PTT_TRACE_CTRL_FILTER_MODE;
+
+	/* Start the Trace */
+	val |= HISI_PTT_TRACE_CTRL_EN;
+	writel(val, hisi_ptt->iobase + HISI_PTT_TRACE_CTRL);
+
+	return 0;
+}
+
+static int hisi_ptt_update_aux(struct hisi_ptt *hisi_ptt, int index, bool stop)
+{
+	struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl;
+	struct perf_output_handle *handle = &ctrl->handle;
+	struct perf_event *event = handle->event;
+	struct hisi_ptt_pmu_buf *buf;
+	size_t size;
+	void *addr;
+
+	buf = perf_get_aux(handle);
+	if (!buf || !handle->size)
+		return -EINVAL;
+
+	addr = ctrl->trace_buf[ctrl->buf_index].addr;
+
+	/*
+	 * If we're going to stop, read the size of already traced data from
+	 * HISI_PTT_TRACE_WR_STS. Otherwise we're coming from the interrupt,
+	 * the data size is always HISI_PTT_TRACE_BUF_SIZE.
+	 */
+	if (stop) {
+		u32 reg;
+
+		reg = readl(hisi_ptt->iobase + HISI_PTT_TRACE_WR_STS);
+		size = FIELD_GET(HISI_PTT_TRACE_WR_STS_WRITE, reg);
+	} else {
+		size = HISI_PTT_TRACE_BUF_SIZE;
+	}
+
+	memcpy(buf->base + buf->pos, addr, size);
+	buf->pos += size;
+
+	/*
+	 * Just commit the traced data if we're going to stop. Otherwise if the
+	 * resident AUX buffer cannot contain the data of next trace buffer,
+	 * apply a new one.
+	 */
+	if (stop) {
+		perf_aux_output_end(handle, buf->pos);
+	} else if (buf->length - buf->pos < HISI_PTT_TRACE_BUF_SIZE) {
+		perf_aux_output_end(handle, buf->pos);
+
+		buf = perf_aux_output_begin(handle, event);
+		if (!buf)
+			return -EINVAL;
+
+		buf->pos = handle->head % buf->length;
+		if (buf->length - buf->pos < HISI_PTT_TRACE_BUF_SIZE) {
+			perf_aux_output_end(handle, 0);
+			return -EINVAL;
+		}
+	}
+
+	return 0;
+}
+
+static irqreturn_t hisi_ptt_isr(int irq, void *context)
+{
+	struct hisi_ptt *hisi_ptt = context;
+	u32 status, buf_idx;
+
+	status = readl(hisi_ptt->iobase + HISI_PTT_TRACE_INT_STAT);
+	if (!(status & HISI_PTT_TRACE_INT_STAT_MASK))
+		return IRQ_NONE;
+
+	buf_idx = ffs(status) - 1;
+
+	/* Clear the interrupt status of buffer @buf_idx */
+	writel(status, hisi_ptt->iobase + HISI_PTT_TRACE_INT_STAT);
+
+	/*
+	 * Update the AUX buffer and cache the current buffer index,
+	 * as we need to know this and save the data when the trace
+	 * is ended out of the interrupt handler. End the trace
+	 * if the updating fails.
+	 */
+	if (hisi_ptt_update_aux(hisi_ptt, buf_idx, false))
+		hisi_ptt_trace_end(hisi_ptt);
+	else
+		hisi_ptt->trace_ctrl.buf_index = (buf_idx + 1) % HISI_PTT_TRACE_BUF_CNT;
+
+	return IRQ_HANDLED;
+}
+
+static void hisi_ptt_irq_free_vectors(void *pdev)
+{
+	pci_free_irq_vectors(pdev);
+}
+
+static int hisi_ptt_register_irq(struct hisi_ptt *hisi_ptt)
+{
+	struct pci_dev *pdev = hisi_ptt->pdev;
+	int ret;
+
+	ret = pci_alloc_irq_vectors(pdev, 1, 1, PCI_IRQ_MSI);
+	if (ret < 0) {
+		pci_err(pdev, "failed to allocate irq vector, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(&pdev->dev, hisi_ptt_irq_free_vectors, pdev);
+	if (ret < 0)
+		return ret;
+
+	hisi_ptt->trace_irq = pci_irq_vector(pdev, HISI_PTT_TRACE_DMA_IRQ);
+	ret = devm_request_irq(&pdev->dev, hisi_ptt->trace_irq, hisi_ptt_isr,
+				IRQF_NOBALANCING | IRQF_NO_THREAD, DRV_NAME,
+				hisi_ptt);
+	if (ret) {
+		pci_err(pdev, "failed to request irq %d, ret = %d\n",
+			hisi_ptt->trace_irq, ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static int hisi_ptt_init_filters(struct pci_dev *pdev, void *data)
+{
+	struct pci_dev *root_port = pcie_find_root_port(pdev);
+	struct hisi_ptt_filter_desc *filter;
+	struct hisi_ptt *hisi_ptt = data;
+	u32 port_devid;
+
+	if (!root_port)
+		return 0;
+
+	port_devid = PCI_DEVID(root_port->bus->number, root_port->devfn);
+	if (port_devid < hisi_ptt->lower_bdf ||
+	    port_devid > hisi_ptt->upper_bdf)
+		return 0;
+
+	/*
+	 * We won't fail the probe if filter allocation failed here. The filters
+	 * should be partial initialized and users would know which filter fails
+	 * through the log. Other functions of PTT device are still available.
+	 */
+	filter = kzalloc(sizeof(*filter), GFP_KERNEL);
+	if (!filter) {
+		pci_err(hisi_ptt->pdev, "failed to add filter %s\n", pci_name(pdev));
+		return -ENOMEM;
+	}
+
+	filter->devid = PCI_DEVID(pdev->bus->number, pdev->devfn);
+
+	if (pci_pcie_type(pdev) == PCI_EXP_TYPE_ROOT_PORT) {
+		filter->is_port = true;
+		list_add_tail(&filter->list, &hisi_ptt->port_filters);
+
+		/* Update the available port mask */
+		hisi_ptt->port_mask |= hisi_ptt_get_filter_val(filter->devid, true);
+	} else {
+		list_add_tail(&filter->list, &hisi_ptt->req_filters);
+	}
+
+	return 0;
+}
+
+static void hisi_ptt_release_filters(void *data)
+{
+	struct hisi_ptt_filter_desc *filter, *tmp;
+	struct hisi_ptt *hisi_ptt = data;
+
+	list_for_each_entry_safe(filter, tmp, &hisi_ptt->req_filters, list) {
+		list_del(&filter->list);
+		kfree(filter);
+	}
+
+	list_for_each_entry_safe(filter, tmp, &hisi_ptt->port_filters, list) {
+		list_del(&filter->list);
+		kfree(filter);
+	}
+}
+
+static int hisi_ptt_config_trace_buf(struct hisi_ptt *hisi_ptt)
+{
+	struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl;
+	struct device *dev = &hisi_ptt->pdev->dev;
+	int i;
+
+	ctrl->trace_buf = devm_kcalloc(dev, HISI_PTT_TRACE_BUF_CNT,
+				       sizeof(*ctrl->trace_buf), GFP_KERNEL);
+	if (!ctrl->trace_buf)
+		return -ENOMEM;
+
+	for (i = 0; i < HISI_PTT_TRACE_BUF_CNT; ++i) {
+		ctrl->trace_buf[i].addr = dmam_alloc_coherent(dev, HISI_PTT_TRACE_BUF_SIZE,
+							     &ctrl->trace_buf[i].dma,
+							     GFP_KERNEL);
+		if (!ctrl->trace_buf[i].addr)
+			return -ENOMEM;
+	}
+
+	/* Configure the trace DMA buffer */
+	for (i = 0; i < HISI_PTT_TRACE_BUF_CNT; i++) {
+		writel(lower_32_bits(ctrl->trace_buf[i].dma),
+		       hisi_ptt->iobase + HISI_PTT_TRACE_ADDR_BASE_LO_0 +
+		       i * HISI_PTT_TRACE_ADDR_STRIDE);
+		writel(upper_32_bits(ctrl->trace_buf[i].dma),
+		       hisi_ptt->iobase + HISI_PTT_TRACE_ADDR_BASE_HI_0 +
+		       i * HISI_PTT_TRACE_ADDR_STRIDE);
+	}
+	writel(HISI_PTT_TRACE_BUF_SIZE, hisi_ptt->iobase + HISI_PTT_TRACE_ADDR_SIZE);
+
+	return 0;
+}
+
+static int hisi_ptt_init_ctrls(struct hisi_ptt *hisi_ptt)
+{
+	struct pci_dev *pdev = hisi_ptt->pdev;
+	struct pci_bus *bus;
+	int ret;
+	u32 reg;
+
+	INIT_LIST_HEAD(&hisi_ptt->port_filters);
+	INIT_LIST_HEAD(&hisi_ptt->req_filters);
+
+	ret = hisi_ptt_config_trace_buf(hisi_ptt);
+	if (ret)
+		return ret;
+
+	/*
+	 * The device range register provides the information about the root
+	 * ports which the RCiEP can control and trace. The RCiEP and the root
+	 * ports which it supports are on the same PCIe core, with same domain
+	 * number but maybe different bus number. The device range register
+	 * will tell us which root ports we can support, Bit[31:16] indicates
+	 * the upper BDF numbers of the root port, while Bit[15:0] indicates
+	 * the lower.
+	 */
+	reg = readl(hisi_ptt->iobase + HISI_PTT_DEVICE_RANGE);
+	hisi_ptt->upper_bdf = FIELD_GET(HISI_PTT_DEVICE_RANGE_UPPER, reg);
+	hisi_ptt->lower_bdf = FIELD_GET(HISI_PTT_DEVICE_RANGE_LOWER, reg);
+
+	bus = pci_find_bus(pci_domain_nr(pdev->bus), PCI_BUS_NUM(hisi_ptt->upper_bdf));
+	if (bus)
+		pci_walk_bus(bus, hisi_ptt_init_filters, hisi_ptt);
+
+	ret = devm_add_action_or_reset(&pdev->dev, hisi_ptt_release_filters, hisi_ptt);
+	if (ret)
+		return ret;
+
+	hisi_ptt->trace_ctrl.on_cpu = -1;
+	return 0;
+}
+
+static ssize_t cpumask_show(struct device *dev, struct device_attribute *attr,
+			    char *buf)
+{
+	struct hisi_ptt *hisi_ptt = to_hisi_ptt(dev_get_drvdata(dev));
+	const cpumask_t *cpumask = cpumask_of_node(dev_to_node(&hisi_ptt->pdev->dev));
+
+	return cpumap_print_to_pagebuf(true, buf, cpumask);
+}
+static DEVICE_ATTR_RO(cpumask);
+
+static struct attribute *hisi_ptt_cpumask_attrs[] = {
+	&dev_attr_cpumask.attr,
+	NULL
+};
+
+static const struct attribute_group hisi_ptt_cpumask_attr_group = {
+	.attrs = hisi_ptt_cpumask_attrs,
+};
+
+/*
+ * Bit 19 indicates the filter type, 1 for Root Port filter and 0 for Requester
+ * filter. Bit[15:0] indicates the filter value, for Root Port filter it's
+ * a bit mask of desired ports and for Requester filter it's the Requester ID
+ * of the desired PCIe function. Bit[18:16] is reserved for extension.
+ *
+ * See hisi_ptt.rst documentation for detailed information.
+ */
+PMU_FORMAT_ATTR(filter,		"config:0-19");
+PMU_FORMAT_ATTR(direction,	"config:20-23");
+PMU_FORMAT_ATTR(type,		"config:24-31");
+PMU_FORMAT_ATTR(format,		"config:32-35");
+
+static struct attribute *hisi_ptt_pmu_format_attrs[] = {
+	&format_attr_filter.attr,
+	&format_attr_direction.attr,
+	&format_attr_type.attr,
+	&format_attr_format.attr,
+	NULL
+};
+
+static struct attribute_group hisi_ptt_pmu_format_group = {
+	.name = "format",
+	.attrs = hisi_ptt_pmu_format_attrs,
+};
+
+static const struct attribute_group *hisi_ptt_pmu_groups[] = {
+	&hisi_ptt_cpumask_attr_group,
+	&hisi_ptt_pmu_format_group,
+	&hisi_ptt_tune_group,
+	NULL
+};
+
+static int hisi_ptt_trace_valid_direction(u32 val)
+{
+	/*
+	 * The direction values have different effects according to the data
+	 * format (specified in the parentheses). TLP set A/B means different
+	 * set of TLP types. See hisi_ptt.rst documentation for more details.
+	 */
+	static const u32 hisi_ptt_trace_available_direction[] = {
+		0,	/* inbound(4DW) or reserved(8DW) */
+		1,	/* outbound(4DW) */
+		2,	/* {in, out}bound(4DW) or inbound(8DW), TLP set A */
+		3,	/* {in, out}bound(4DW) or inbound(8DW), TLP set B */
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hisi_ptt_trace_available_direction); i++) {
+		if (val == hisi_ptt_trace_available_direction[i])
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int hisi_ptt_trace_valid_type(u32 val)
+{
+	/* Different types can be set simultaneously */
+	static const u32 hisi_ptt_trace_available_type[] = {
+		1,	/* posted_request */
+		2,	/* non-posted_request */
+		4,	/* completion */
+	};
+	int i;
+
+	if (!val)
+		return -EINVAL;
+
+	/*
+	 * Walk the available list and clear the valid bits of
+	 * the config. If there is any resident bit after the
+	 * walk then the config is invalid.
+	 */
+	for (i = 0; i < ARRAY_SIZE(hisi_ptt_trace_available_type); i++)
+		val &= ~hisi_ptt_trace_available_type[i];
+
+	if (val)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int hisi_ptt_trace_valid_format(u32 val)
+{
+	static const u32 hisi_ptt_trace_availble_format[] = {
+		0,	/* 4DW */
+		1,	/* 8DW */
+	};
+	int i;
+
+	for (i = 0; i < ARRAY_SIZE(hisi_ptt_trace_availble_format); i++) {
+		if (val == hisi_ptt_trace_availble_format[i])
+			return 0;
+	}
+
+	return -EINVAL;
+}
+
+static int hisi_ptt_trace_valid_filter(struct hisi_ptt *hisi_ptt, u64 config)
+{
+	unsigned long val, port_mask = hisi_ptt->port_mask;
+	struct hisi_ptt_filter_desc *filter;
+
+	hisi_ptt->trace_ctrl.is_port = FIELD_GET(HISI_PTT_PMU_FILTER_IS_PORT, config);
+	val = FIELD_GET(HISI_PTT_PMU_FILTER_VAL_MASK, config);
+
+	/*
+	 * Port filters are defined as bit mask. For port filters, check
+	 * the bits in the @val are within the range of hisi_ptt->port_mask
+	 * and whether it's empty or not, otherwise user has specified
+	 * some unsupported root ports.
+	 *
+	 * For Requester ID filters, walk the available filter list to see
+	 * whether we have one matched.
+	 */
+	if (!hisi_ptt->trace_ctrl.is_port) {
+		list_for_each_entry(filter, &hisi_ptt->req_filters, list) {
+			if (val == hisi_ptt_get_filter_val(filter->devid, filter->is_port))
+				return 0;
+		}
+	} else if (bitmap_subset(&val, &port_mask, BITS_PER_LONG)) {
+		return 0;
+	}
+
+	return -EINVAL;
+}
+
+static void hisi_ptt_pmu_init_configs(struct hisi_ptt *hisi_ptt, struct perf_event *event)
+{
+	struct hisi_ptt_trace_ctrl *ctrl = &hisi_ptt->trace_ctrl;
+	u32 val;
+
+	val = FIELD_GET(HISI_PTT_PMU_FILTER_VAL_MASK, event->attr.config);
+	hisi_ptt->trace_ctrl.filter = val;
+
+	val = FIELD_GET(HISI_PTT_PMU_DIRECTION_MASK, event->attr.config);
+	ctrl->direction = val;
+
+	val = FIELD_GET(HISI_PTT_PMU_TYPE_MASK, event->attr.config);
+	ctrl->type = val;
+
+	val = FIELD_GET(HISI_PTT_PMU_FORMAT_MASK, event->attr.config);
+	ctrl->format = val;
+}
+
+static int hisi_ptt_pmu_event_init(struct perf_event *event)
+{
+	struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu);
+	int ret;
+	u32 val;
+
+	if (event->cpu < 0) {
+		dev_dbg(event->pmu->dev, "Per-task mode not supported\n");
+		return -EOPNOTSUPP;
+	}
+
+	if (event->attach_state & PERF_ATTACH_TASK)
+		return -EOPNOTSUPP;
+
+	if (event->attr.type != hisi_ptt->hisi_ptt_pmu.type)
+		return -ENOENT;
+
+	ret = hisi_ptt_trace_valid_filter(hisi_ptt, event->attr.config);
+	if (ret < 0)
+		return ret;
+
+	val = FIELD_GET(HISI_PTT_PMU_DIRECTION_MASK, event->attr.config);
+	ret = hisi_ptt_trace_valid_direction(val);
+	if (ret < 0)
+		return ret;
+
+	val = FIELD_GET(HISI_PTT_PMU_TYPE_MASK, event->attr.config);
+	ret = hisi_ptt_trace_valid_type(val);
+	if (ret < 0)
+		return ret;
+
+	val = FIELD_GET(HISI_PTT_PMU_FORMAT_MASK, event->attr.config);
+	return hisi_ptt_trace_valid_format(val);
+}
+
+static void *hisi_ptt_pmu_setup_aux(struct perf_event *event, void **pages,
+				    int nr_pages, bool overwrite)
+{
+	struct hisi_ptt_pmu_buf *buf;
+	struct page **pagelist;
+	int i;
+
+	if (overwrite) {
+		dev_warn(event->pmu->dev, "Overwrite mode is not supported\n");
+		return NULL;
+	}
+
+	/* If the pages size less than buffers, we cannot start trace */
+	if (nr_pages < HISI_PTT_TRACE_TOTAL_BUF_SIZE / PAGE_SIZE)
+		return NULL;
+
+	buf = kzalloc(sizeof(*buf), GFP_KERNEL);
+	if (!buf)
+		return NULL;
+
+	pagelist = kcalloc(nr_pages, sizeof(*pagelist), GFP_KERNEL);
+	if (!pagelist)
+		goto err;
+
+	for (i = 0; i < nr_pages; i++)
+		pagelist[i] = virt_to_page(pages[i]);
+
+	buf->base = vmap(pagelist, nr_pages, VM_MAP, PAGE_KERNEL);
+	if (!buf->base) {
+		kfree(pagelist);
+		goto err;
+	}
+
+	buf->nr_pages = nr_pages;
+	buf->length = nr_pages * PAGE_SIZE;
+	buf->pos = 0;
+
+	kfree(pagelist);
+	return buf;
+err:
+	kfree(buf);
+	return NULL;
+}
+
+static void hisi_ptt_pmu_free_aux(void *aux)
+{
+	struct hisi_ptt_pmu_buf *buf = aux;
+
+	vunmap(buf->base);
+	kfree(buf);
+}
+
+static void hisi_ptt_pmu_start(struct perf_event *event, int flags)
+{
+	struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu);
+	struct perf_output_handle *handle = &hisi_ptt->trace_ctrl.handle;
+	struct hw_perf_event *hwc = &event->hw;
+	struct device *dev = event->pmu->dev;
+	struct hisi_ptt_pmu_buf *buf;
+	int cpu = event->cpu;
+	int ret;
+
+	hwc->state = 0;
+
+	/* Serialize the perf process if user specified several CPUs */
+	spin_lock(&hisi_ptt->pmu_lock);
+	if (hisi_ptt->trace_ctrl.started) {
+		dev_dbg(dev, "trace has already started\n");
+		goto stop;
+	}
+
+	/*
+	 * Handle the interrupt on the same cpu which starts the trace to avoid
+	 * context mismatch. Otherwise we'll trigger the WARN from the perf
+	 * core in event_function_local(). If CPU passed is offline we'll fail
+	 * here, just log it since we can do nothing here.
+	 */
+	ret = irq_set_affinity(hisi_ptt->trace_irq, cpumask_of(cpu));
+	if (ret)
+		dev_warn(dev, "failed to set the affinity of trace interrupt\n");
+
+	hisi_ptt->trace_ctrl.on_cpu = cpu;
+
+	buf = perf_aux_output_begin(handle, event);
+	if (!buf) {
+		dev_dbg(dev, "aux output begin failed\n");
+		goto stop;
+	}
+
+	buf->pos = handle->head % buf->length;
+
+	hisi_ptt_pmu_init_configs(hisi_ptt, event);
+
+	ret = hisi_ptt_trace_start(hisi_ptt);
+	if (ret) {
+		dev_dbg(dev, "trace start failed, ret = %d\n", ret);
+		perf_aux_output_end(handle, 0);
+		goto stop;
+	}
+
+	spin_unlock(&hisi_ptt->pmu_lock);
+	return;
+stop:
+	event->hw.state |= PERF_HES_STOPPED;
+	spin_unlock(&hisi_ptt->pmu_lock);
+}
+
+static void hisi_ptt_pmu_stop(struct perf_event *event, int flags)
+{
+	struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+
+	if (hwc->state & PERF_HES_STOPPED)
+		return;
+
+	spin_lock(&hisi_ptt->pmu_lock);
+	if (hisi_ptt->trace_ctrl.started) {
+		hisi_ptt_trace_end(hisi_ptt);
+
+		if (!hisi_ptt_wait_trace_hw_idle(hisi_ptt))
+			dev_warn(event->pmu->dev, "Device is still busy\n");
+
+		hisi_ptt_update_aux(hisi_ptt, hisi_ptt->trace_ctrl.buf_index, true);
+	}
+	spin_unlock(&hisi_ptt->pmu_lock);
+
+	hwc->state |= PERF_HES_STOPPED;
+	perf_event_update_userpage(event);
+	hwc->state |= PERF_HES_UPTODATE;
+}
+
+static int hisi_ptt_pmu_add(struct perf_event *event, int flags)
+{
+	struct hisi_ptt *hisi_ptt = to_hisi_ptt(event->pmu);
+	struct hw_perf_event *hwc = &event->hw;
+	int cpu = event->cpu;
+
+	/* Only allow the cpus on the device's node to add the event */
+	if (!cpumask_test_cpu(cpu, cpumask_of_node(dev_to_node(&hisi_ptt->pdev->dev))))
+		return 0;
+
+	hwc->state = PERF_HES_STOPPED | PERF_HES_UPTODATE;
+
+	if (flags & PERF_EF_START) {
+		hisi_ptt_pmu_start(event, PERF_EF_RELOAD);
+		if (hwc->state & PERF_HES_STOPPED)
+			return -EINVAL;
+	}
+
+	return 0;
+}
+
+static void hisi_ptt_pmu_del(struct perf_event *event, int flags)
+{
+	hisi_ptt_pmu_stop(event, PERF_EF_UPDATE);
+}
+
+static void hisi_ptt_pmu_read(struct perf_event *event)
+{
+}
+
+static void hisi_ptt_remove_cpuhp_instance(void *hotplug_node)
+{
+	cpuhp_state_remove_instance_nocalls(hisi_ptt_pmu_online, hotplug_node);
+}
+
+static void hisi_ptt_unregister_pmu(void *pmu)
+{
+	perf_pmu_unregister(pmu);
+}
+
+static int hisi_ptt_register_pmu(struct hisi_ptt *hisi_ptt)
+{
+	u16 core_id, sicl_id;
+	char *pmu_name;
+	u32 reg;
+	int ret;
+
+	ret = cpuhp_state_add_instance_nocalls(hisi_ptt_pmu_online,
+					       &hisi_ptt->hotplug_node);
+	if (ret)
+		return ret;
+
+	ret = devm_add_action_or_reset(&hisi_ptt->pdev->dev,
+				       hisi_ptt_remove_cpuhp_instance,
+				       &hisi_ptt->hotplug_node);
+	if (ret)
+		return ret;
+
+	mutex_init(&hisi_ptt->tune_lock);
+	spin_lock_init(&hisi_ptt->pmu_lock);
+
+	hisi_ptt->hisi_ptt_pmu = (struct pmu) {
+		.module		= THIS_MODULE,
+		.capabilities	= PERF_PMU_CAP_EXCLUSIVE | PERF_PMU_CAP_ITRACE,
+		.task_ctx_nr	= perf_sw_context,
+		.attr_groups	= hisi_ptt_pmu_groups,
+		.event_init	= hisi_ptt_pmu_event_init,
+		.setup_aux	= hisi_ptt_pmu_setup_aux,
+		.free_aux	= hisi_ptt_pmu_free_aux,
+		.start		= hisi_ptt_pmu_start,
+		.stop		= hisi_ptt_pmu_stop,
+		.add		= hisi_ptt_pmu_add,
+		.del		= hisi_ptt_pmu_del,
+		.read		= hisi_ptt_pmu_read,
+	};
+
+	reg = readl(hisi_ptt->iobase + HISI_PTT_LOCATION);
+	core_id = FIELD_GET(HISI_PTT_CORE_ID, reg);
+	sicl_id = FIELD_GET(HISI_PTT_SICL_ID, reg);
+
+	pmu_name = devm_kasprintf(&hisi_ptt->pdev->dev, GFP_KERNEL, "hisi_ptt%u_%u",
+				  sicl_id, core_id);
+	if (!pmu_name)
+		return -ENOMEM;
+
+	ret = perf_pmu_register(&hisi_ptt->hisi_ptt_pmu, pmu_name, -1);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(&hisi_ptt->pdev->dev,
+					hisi_ptt_unregister_pmu,
+					&hisi_ptt->hisi_ptt_pmu);
+}
+
+/*
+ * The DMA of PTT trace can only use direct mappings due to some
+ * hardware restriction. Check whether there is no IOMMU or the
+ * policy of the IOMMU domain is passthrough, otherwise the trace
+ * cannot work.
+ *
+ * The PTT device is supposed to behind an ARM SMMUv3, which
+ * should have passthrough the device by a quirk.
+ */
+static int hisi_ptt_check_iommu_mapping(struct pci_dev *pdev)
+{
+	struct iommu_domain *iommu_domain;
+
+	iommu_domain = iommu_get_domain_for_dev(&pdev->dev);
+	if (!iommu_domain || iommu_domain->type == IOMMU_DOMAIN_IDENTITY)
+		return 0;
+
+	return -EOPNOTSUPP;
+}
+
+static int hisi_ptt_probe(struct pci_dev *pdev,
+			  const struct pci_device_id *id)
+{
+	struct hisi_ptt *hisi_ptt;
+	int ret;
+
+	ret = hisi_ptt_check_iommu_mapping(pdev);
+	if (ret) {
+		pci_err(pdev, "requires direct DMA mappings\n");
+		return ret;
+	}
+
+	hisi_ptt = devm_kzalloc(&pdev->dev, sizeof(*hisi_ptt), GFP_KERNEL);
+	if (!hisi_ptt)
+		return -ENOMEM;
+
+	hisi_ptt->pdev = pdev;
+	pci_set_drvdata(pdev, hisi_ptt);
+
+	ret = pcim_enable_device(pdev);
+	if (ret) {
+		pci_err(pdev, "failed to enable device, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = pcim_iomap_regions(pdev, BIT(2), DRV_NAME);
+	if (ret) {
+		pci_err(pdev, "failed to remap io memory, ret = %d\n", ret);
+		return ret;
+	}
+
+	hisi_ptt->iobase = pcim_iomap_table(pdev)[2];
+
+	ret = dma_set_coherent_mask(&pdev->dev, DMA_BIT_MASK(64));
+	if (ret) {
+		pci_err(pdev, "failed to set 64 bit dma mask, ret = %d\n", ret);
+		return ret;
+	}
+
+	pci_set_master(pdev);
+
+	ret = hisi_ptt_register_irq(hisi_ptt);
+	if (ret)
+		return ret;
+
+	ret = hisi_ptt_init_ctrls(hisi_ptt);
+	if (ret) {
+		pci_err(pdev, "failed to init controls, ret = %d\n", ret);
+		return ret;
+	}
+
+	ret = hisi_ptt_register_pmu(hisi_ptt);
+	if (ret) {
+		pci_err(pdev, "failed to register PMU device, ret = %d", ret);
+		return ret;
+	}
+
+	return 0;
+}
+
+static const struct pci_device_id hisi_ptt_id_tbl[] = {
+	{ PCI_DEVICE(PCI_VENDOR_ID_HUAWEI, 0xa12e) },
+	{ }
+};
+MODULE_DEVICE_TABLE(pci, hisi_ptt_id_tbl);
+
+static struct pci_driver hisi_ptt_driver = {
+	.name = DRV_NAME,
+	.id_table = hisi_ptt_id_tbl,
+	.probe = hisi_ptt_probe,
+};
+
+static int hisi_ptt_cpu_teardown(unsigned int cpu, struct hlist_node *node)
+{
+	struct hisi_ptt *hisi_ptt;
+	struct device *dev;
+	int target, src;
+
+	hisi_ptt = hlist_entry_safe(node, struct hisi_ptt, hotplug_node);
+	src = hisi_ptt->trace_ctrl.on_cpu;
+	dev = hisi_ptt->hisi_ptt_pmu.dev;
+
+	if (!hisi_ptt->trace_ctrl.started || src != cpu)
+		return 0;
+
+	target = cpumask_any_but(cpumask_of_node(dev_to_node(&hisi_ptt->pdev->dev)), cpu);
+	if (target >= nr_cpu_ids) {
+		dev_err(dev, "no available cpu for perf context migration\n");
+		return 0;
+	}
+
+	perf_pmu_migrate_context(&hisi_ptt->hisi_ptt_pmu, src, target);
+
+	/*
+	 * Also make sure the interrupt bind to the migrated CPU as well. Warn
+	 * the user on failure here.
+	 */
+	if (irq_set_affinity(hisi_ptt->trace_irq, cpumask_of(target)))
+		dev_warn(dev, "failed to set the affinity of trace interrupt\n");
+
+	hisi_ptt->trace_ctrl.on_cpu = target;
+	return 0;
+}
+
+static int __init hisi_ptt_init(void)
+{
+	int ret;
+
+	ret = cpuhp_setup_state_multi(CPUHP_AP_ONLINE_DYN, DRV_NAME, NULL,
+				      hisi_ptt_cpu_teardown);
+	if (ret < 0)
+		return ret;
+	hisi_ptt_pmu_online = ret;
+
+	ret = pci_register_driver(&hisi_ptt_driver);
+	if (ret)
+		cpuhp_remove_multi_state(hisi_ptt_pmu_online);
+
+	return ret;
+}
+module_init(hisi_ptt_init);
+
+static void __exit hisi_ptt_exit(void)
+{
+	pci_unregister_driver(&hisi_ptt_driver);
+	cpuhp_remove_multi_state(hisi_ptt_pmu_online);
+}
+module_exit(hisi_ptt_exit);
+
+MODULE_LICENSE("GPL");
+MODULE_AUTHOR("Yicong Yang <yangyicong@hisilicon.com>");
+MODULE_DESCRIPTION("Driver for HiSilicon PCIe tune and trace device");
diff --git a/drivers/hwtracing/ptt/hisi_ptt.h b/drivers/hwtracing/ptt/hisi_ptt.h
new file mode 100644
index 000000000..948a4c423
--- /dev/null
+++ b/drivers/hwtracing/ptt/hisi_ptt.h
@@ -0,0 +1,202 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Driver for HiSilicon PCIe tune and trace device
+ *
+ * Copyright (c) 2022 HiSilicon Technologies Co., Ltd.
+ * Author: Yicong Yang <yangyicong@hisilicon.com>
+ */
+
+#ifndef _HISI_PTT_H
+#define _HISI_PTT_H
+
+#include <linux/bits.h>
+#include <linux/cpumask.h>
+#include <linux/list.h>
+#include <linux/mutex.h>
+#include <linux/pci.h>
+#include <linux/perf_event.h>
+#include <linux/spinlock.h>
+#include <linux/types.h>
+
+#define DRV_NAME "hisi_ptt"
+
+/*
+ * The definition of the device registers and register fields.
+ */
+#define HISI_PTT_TUNING_CTRL		0x0000
+#define   HISI_PTT_TUNING_CTRL_CODE	GENMASK(15, 0)
+#define   HISI_PTT_TUNING_CTRL_SUB	GENMASK(23, 16)
+#define HISI_PTT_TUNING_DATA		0x0004
+#define   HISI_PTT_TUNING_DATA_VAL_MASK	GENMASK(15, 0)
+#define HISI_PTT_TRACE_ADDR_SIZE	0x0800
+#define HISI_PTT_TRACE_ADDR_BASE_LO_0	0x0810
+#define HISI_PTT_TRACE_ADDR_BASE_HI_0	0x0814
+#define HISI_PTT_TRACE_ADDR_STRIDE	0x8
+#define HISI_PTT_TRACE_CTRL		0x0850
+#define   HISI_PTT_TRACE_CTRL_EN	BIT(0)
+#define   HISI_PTT_TRACE_CTRL_RST	BIT(1)
+#define   HISI_PTT_TRACE_CTRL_RXTX_SEL	GENMASK(3, 2)
+#define   HISI_PTT_TRACE_CTRL_TYPE_SEL	GENMASK(7, 4)
+#define   HISI_PTT_TRACE_CTRL_DATA_FORMAT	BIT(14)
+#define   HISI_PTT_TRACE_CTRL_FILTER_MODE	BIT(15)
+#define   HISI_PTT_TRACE_CTRL_TARGET_SEL	GENMASK(31, 16)
+#define HISI_PTT_TRACE_INT_STAT		0x0890
+#define   HISI_PTT_TRACE_INT_STAT_MASK	GENMASK(3, 0)
+#define HISI_PTT_TRACE_INT_MASK		0x0894
+#define HISI_PTT_TUNING_INT_STAT	0x0898
+#define   HISI_PTT_TUNING_INT_STAT_MASK	BIT(0)
+#define HISI_PTT_TRACE_WR_STS		0x08a0
+#define   HISI_PTT_TRACE_WR_STS_WRITE	GENMASK(27, 0)
+#define   HISI_PTT_TRACE_WR_STS_BUFFER	GENMASK(29, 28)
+#define HISI_PTT_TRACE_STS		0x08b0
+#define   HISI_PTT_TRACE_IDLE		BIT(0)
+#define HISI_PTT_DEVICE_RANGE		0x0fe0
+#define   HISI_PTT_DEVICE_RANGE_UPPER	GENMASK(31, 16)
+#define   HISI_PTT_DEVICE_RANGE_LOWER	GENMASK(15, 0)
+#define HISI_PTT_LOCATION		0x0fe8
+#define   HISI_PTT_CORE_ID		GENMASK(15, 0)
+#define   HISI_PTT_SICL_ID		GENMASK(31, 16)
+
+/* Parameters of PTT trace DMA part. */
+#define HISI_PTT_TRACE_DMA_IRQ			0
+#define HISI_PTT_TRACE_BUF_CNT			4
+#define HISI_PTT_TRACE_BUF_SIZE			SZ_4M
+#define HISI_PTT_TRACE_TOTAL_BUF_SIZE		(HISI_PTT_TRACE_BUF_SIZE * \
+						 HISI_PTT_TRACE_BUF_CNT)
+/* Wait time for hardware DMA to reset */
+#define HISI_PTT_RESET_TIMEOUT_US	10UL
+#define HISI_PTT_RESET_POLL_INTERVAL_US	1UL
+/* Poll timeout and interval for waiting hardware work to finish */
+#define HISI_PTT_WAIT_TUNE_TIMEOUT_US	1000000UL
+#define HISI_PTT_WAIT_TRACE_TIMEOUT_US	100UL
+#define HISI_PTT_WAIT_POLL_INTERVAL_US	10UL
+
+#define HISI_PCIE_CORE_PORT_ID(devfn)	((PCI_SLOT(devfn) & 0x7) << 1)
+
+/* Definition of the PMU configs */
+#define HISI_PTT_PMU_FILTER_IS_PORT	BIT(19)
+#define HISI_PTT_PMU_FILTER_VAL_MASK	GENMASK(15, 0)
+#define HISI_PTT_PMU_DIRECTION_MASK	GENMASK(23, 20)
+#define HISI_PTT_PMU_TYPE_MASK		GENMASK(31, 24)
+#define HISI_PTT_PMU_FORMAT_MASK	GENMASK(35, 32)
+
+/**
+ * struct hisi_ptt_tune_desc - Describe tune event for PTT tune
+ * @hisi_ptt:   PTT device this tune event belongs to
+ * @name:       name of this event
+ * @event_code: code of the event
+ */
+struct hisi_ptt_tune_desc {
+	struct hisi_ptt *hisi_ptt;
+	const char *name;
+	u32 event_code;
+};
+
+/**
+ * struct hisi_ptt_dma_buffer - Describe a single trace buffer of PTT trace.
+ *                              The detail of the data format is described
+ *                              in the documentation of PTT device.
+ * @dma:   DMA address of this buffer visible to the device
+ * @addr:  virtual address of this buffer visible to the cpu
+ */
+struct hisi_ptt_dma_buffer {
+	dma_addr_t dma;
+	void *addr;
+};
+
+/**
+ * struct hisi_ptt_trace_ctrl - Control and status of PTT trace
+ * @trace_buf: array of the trace buffers for holding the trace data.
+ *             the length will be HISI_PTT_TRACE_BUF_CNT.
+ * @handle:    perf output handle of current trace session
+ * @buf_index: the index of current using trace buffer
+ * @on_cpu:    current tracing cpu
+ * @started:   current trace status, true for started
+ * @is_port:   whether we're tracing root port or not
+ * @direction: direction of the TLP headers to trace
+ * @filter:    filter value for tracing the TLP headers
+ * @format:    format of the TLP headers to trace
+ * @type:      type of the TLP headers to trace
+ */
+struct hisi_ptt_trace_ctrl {
+	struct hisi_ptt_dma_buffer *trace_buf;
+	struct perf_output_handle handle;
+	u32 buf_index;
+	int on_cpu;
+	bool started;
+	bool is_port;
+	u32 direction:2;
+	u32 filter:16;
+	u32 format:1;
+	u32 type:4;
+};
+
+/**
+ * struct hisi_ptt_filter_desc - Descriptor of the PTT trace filter
+ * @list:    entry of this descriptor in the filter list
+ * @is_port: the PCI device of the filter is a Root Port or not
+ * @devid:   the PCI device's devid of the filter
+ */
+struct hisi_ptt_filter_desc {
+	struct list_head list;
+	bool is_port;
+	u16 devid;
+};
+
+/**
+ * struct hisi_ptt_pmu_buf - Descriptor of the AUX buffer of PTT trace
+ * @length:   size of the AUX buffer
+ * @nr_pages: number of pages of the AUX buffer
+ * @base:     start address of AUX buffer
+ * @pos:      position in the AUX buffer to commit traced data
+ */
+struct hisi_ptt_pmu_buf {
+	size_t length;
+	int nr_pages;
+	void *base;
+	long pos;
+};
+
+/**
+ * struct hisi_ptt - Per PTT device data
+ * @trace_ctrl:   the control information of PTT trace
+ * @hotplug_node: node for register cpu hotplug event
+ * @hisi_ptt_pmu: the pum device of trace
+ * @iobase:       base IO address of the device
+ * @pdev:         pci_dev of this PTT device
+ * @tune_lock:    lock to serialize the tune process
+ * @pmu_lock:     lock to serialize the perf process
+ * @trace_irq:    interrupt number used by trace
+ * @upper_bdf:    the upper BDF range of the PCI devices managed by this PTT device
+ * @lower_bdf:    the lower BDF range of the PCI devices managed by this PTT device
+ * @port_filters: the filter list of root ports
+ * @req_filters:  the filter list of requester ID
+ * @port_mask:    port mask of the managed root ports
+ */
+struct hisi_ptt {
+	struct hisi_ptt_trace_ctrl trace_ctrl;
+	struct hlist_node hotplug_node;
+	struct pmu hisi_ptt_pmu;
+	void __iomem *iobase;
+	struct pci_dev *pdev;
+	struct mutex tune_lock;
+	spinlock_t pmu_lock;
+	int trace_irq;
+	u32 upper_bdf;
+	u32 lower_bdf;
+
+	/*
+	 * The trace TLP headers can either be filtered by certain
+	 * root port, or by the requester ID. Organize the filters
+	 * by @port_filters and @req_filters here. The mask of all
+	 * the valid ports is also cached for doing sanity check
+	 * of user input.
+	 */
+	struct list_head port_filters;
+	struct list_head req_filters;
+	u16 port_mask;
+};
+
+#define to_hisi_ptt(pmu) container_of(pmu, struct hisi_ptt, hisi_ptt_pmu)
+
+#endif /* _HISI_PTT_H */