[PATCH v8 03/12] peci: Add support for PECI bus driver core

[Jae Hyun Yoo]

This commit adds driver implementation for PECI bus core into linux
driver framework.

Cc: Greg Kroah-Hartman <gregkh@xxxxxxxxxxxxxxxxxxx>
Cc: Philippe Ombredanne <pombredanne@xxxxxxxx>
Cc: Gavin Schenk <g.schenk@xxxxxxxxxxxx>
Cc: Vinod Koul <vkoul@xxxxxxxxxx>
Cc: Thomas Gleixner <tglx@xxxxxxxxxxxxx>
Cc: Sagar Dharia <sdharia@xxxxxxxxxxxxxx>
Cc: David Kershner <david.kershner@xxxxxxxxxx>
Cc: Johan Hovold <johan@xxxxxxxxxx>
Cc: Uwe Kleine-Konig <u.kleine-koenig@xxxxxxxxxxxxxx>
Cc: Viresh Kumar <viresh.kumar@xxxxxxxxxx>
Cc: Randy Dunlap <rdunlap@xxxxxxxxxxxxx>
Cc: Cyrille Pitchen <cyrille.pitchen@xxxxxxxxxxxxxxxxxx>
Cc: Juergen Gross <jgross@xxxxxxxx>
Cc: Alan Cox <alan@xxxxxxxxxxxxxxx>
Cc: Andrew Lunn <andrew@xxxxxxx>
Cc: Andy Shevchenko <andriy.shevchenko@xxxxxxxxx>
Cc: Arnd Bergmann <arnd@xxxxxxxx>
Cc: Benjamin Herrenschmidt <benh@xxxxxxxxxxxxxxxxxxx>
Cc: Fengguang Wu <fengguang.wu@xxxxxxxxx>
Cc: Jason M Biils <jason.m.bills@xxxxxxxxxxxxxxx>
Cc: Julia Cartwright <juliac@xxxxxxxxxxxx>
Signed-off-by: Jae Hyun Yoo <jae.hyun.yoo@xxxxxxxxxxxxxxx>
Signed-off-by: Fengguang Wu <fengguang.wu@xxxxxxxxx>
Reviewed-by: Haiyue Wang <haiyue.wang@xxxxxxxxxxxxxxx>
Reviewed-by: James Feist <james.feist@xxxxxxxxxxxxxxx>
Reviewed-by: Vernon Mauery <vernon.mauery@xxxxxxxxxxxxxxx>
---
 drivers/Kconfig                 |    2 +
 drivers/Makefile                |    1 +
 drivers/peci/Kconfig            |   12 +
 drivers/peci/Makefile           |    6 +
 drivers/peci/peci-core.c        | 1440 +++++++++++++++++++++++++++++++
 include/linux/peci.h            |  104 +++
 include/uapi/linux/peci-ioctl.h |  265 ++++++
 7 files changed, 1830 insertions(+)
 create mode 100644 drivers/peci/Kconfig
 create mode 100644 drivers/peci/Makefile
 create mode 100644 drivers/peci/peci-core.c
 create mode 100644 include/linux/peci.h
 create mode 100644 include/uapi/linux/peci-ioctl.h

diff --git a/drivers/Kconfig b/drivers/Kconfig
index ab4d43923c4d..c633db2b41fb 100644
--- a/drivers/Kconfig
+++ b/drivers/Kconfig
@@ -219,4 +219,6 @@ source "drivers/siox/Kconfig"
 
 source "drivers/slimbus/Kconfig"
 
+source "drivers/peci/Kconfig"
+
 endmenu
diff --git a/drivers/Makefile b/drivers/Makefile
index 578f469f72fb..63c9b425e6e1 100644
--- a/drivers/Makefile
+++ b/drivers/Makefile
@@ -186,3 +186,4 @@ obj-$(CONFIG_MULTIPLEXER)	+= mux/
 obj-$(CONFIG_UNISYS_VISORBUS)	+= visorbus/
 obj-$(CONFIG_SIOX)		+= siox/
 obj-$(CONFIG_GNSS)		+= gnss/
+obj-$(CONFIG_PECI)		+= peci/
diff --git a/drivers/peci/Kconfig b/drivers/peci/Kconfig
new file mode 100644
index 000000000000..4ccacb22a356
--- /dev/null
+++ b/drivers/peci/Kconfig
@@ -0,0 +1,12 @@
+#
+# Platform Environment Control Interface (PECI) subsystem configuration
+#
+
+config PECI
+	bool "PECI support"
+	select RT_MUTEXES
+	select CRC8
+	help
+	  The Platform Environment Control Interface (PECI) is a one-wire bus
+	  interface that provides a communication channel from Intel processors
+	  and chipset components to external monitoring or control devices.
diff --git a/drivers/peci/Makefile b/drivers/peci/Makefile
new file mode 100644
index 000000000000..9e8615e0d3ff
--- /dev/null
+++ b/drivers/peci/Makefile
@@ -0,0 +1,6 @@
+#
+# Makefile for the PECI core and bus drivers.
+#
+
+# Core functionality
+obj-$(CONFIG_PECI)		+= peci-core.o
diff --git a/drivers/peci/peci-core.c b/drivers/peci/peci-core.c
new file mode 100644
index 000000000000..7a99e823c14b
--- /dev/null
+++ b/drivers/peci/peci-core.c
@@ -0,0 +1,1440 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2018 Intel Corporation
+
+#include <linux/bitfield.h>
+#include <linux/crc8.h>
+#include <linux/delay.h>
+#include <linux/fs.h>
+#include <linux/module.h>
+#include <linux/of_device.h>
+#include <linux/peci.h>
+#include <linux/pm_domain.h>
+#include <linux/pm_runtime.h>
+#include <linux/slab.h>
+#include <linux/uaccess.h>
+
+/* Mask for getting minor revision number from DIB */
+#define MINOR_REV_NUM_MASK GENMASK(11, 8)
+
+/* CRC8 table for Assure Write Frame Check */
+#define PECI_CRC8_POLYNOMIAL 0x07
+DECLARE_CRC8_TABLE(peci_crc8_table);
+
+static struct device_type peci_adapter_type;
+static struct device_type peci_client_type;
+
+/* Max number of peci cdev */
+#define PECI_CDEV_MAX    16
+
+static dev_t peci_devt;
+static bool is_registered;
+
+static DEFINE_MUTEX(core_lock);
+static DEFINE_IDR(peci_adapter_idr);
+
+static struct peci_adapter *peci_get_adapter(int nr)
+{
+	struct peci_adapter *adapter;
+
+	mutex_lock(&core_lock);
+	adapter = idr_find(&peci_adapter_idr, nr);
+	if (!adapter)
+		goto out_unlock;
+
+	if (try_module_get(adapter->owner))
+		get_device(&adapter->dev);
+	else
+		adapter = NULL;
+
+out_unlock:
+	mutex_unlock(&core_lock);
+	return adapter;
+}
+
+static void peci_put_adapter(struct peci_adapter *adapter)
+{
+	if (!adapter)
+		return;
+
+	put_device(&adapter->dev);
+	module_put(adapter->owner);
+}
+
+static ssize_t name_show(struct device *dev,
+			 struct device_attribute *attr,
+			 char *buf)
+{
+	return sprintf(buf, "%s\n", dev->type == &peci_client_type ?
+		       to_peci_client(dev)->name : to_peci_adapter(dev)->name);
+}
+static DEVICE_ATTR_RO(name);
+
+static void peci_client_dev_release(struct device *dev)
+{
+	struct peci_client *client = to_peci_client(dev);
+
+	dev_dbg(dev, "%s: %s\n", __func__, client->name);
+	peci_put_adapter(client->adapter);
+	kfree(client);
+}
+
+static struct attribute *peci_device_attrs[] = {
+	&dev_attr_name.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(peci_device);
+
+static struct device_type peci_client_type = {
+	.groups		= peci_device_groups,
+	.release	= peci_client_dev_release,
+};
+
+struct peci_client *peci_verify_client(struct device *dev)
+{
+	return (dev->type == &peci_client_type)
+			? to_peci_client(dev)
+			: NULL;
+}
+EXPORT_SYMBOL_GPL(peci_verify_client);
+
+static u8 peci_aw_fcs(u8 *data, int len)
+{
+	return crc8(peci_crc8_table, data, (size_t)len, 0);
+}
+
+static int __peci_xfer(struct peci_adapter *adapter, struct peci_xfer_msg *msg,
+		       bool do_retry, bool has_aw_fcs)
+{
+	ktime_t start, end;
+	s64 elapsed_ms;
+	int rc = 0;
+
+	/**
+	 * For some commands, the PECI originator may need to retry a command if
+	 * the processor PECI client responds with a 0x8x completion code. In
+	 * each instance, the processor PECI client may have started the
+	 * operation but not completed it yet. When the 'retry' bit is set, the
+	 * PECI client will ignore a new request if it exactly matches a
+	 * previous valid request.
+	 */
+
+	if (do_retry)
+		start = ktime_get();
+
+	do {
+		rc = adapter->xfer(adapter, msg);
+
+		if (!do_retry || rc)
+			break;
+
+		if (msg->rx_buf[0] == DEV_PECI_CC_SUCCESS)
+			break;
+
+		/* Retry is needed when completion code is 0x8x */
+		if ((msg->rx_buf[0] & DEV_PECI_CC_RETRY_CHECK_MASK) !=
+		    DEV_PECI_CC_NEED_RETRY) {
+			rc = -EIO;
+			break;
+		}
+
+		/* Set the retry bit to indicate a retry attempt */
+		msg->tx_buf[1] |= DEV_PECI_RETRY_BIT;
+
+		/* Recalculate the AW FCS if it has one */
+		if (has_aw_fcs)
+			msg->tx_buf[msg->tx_len - 1] = 0x80 ^
+						peci_aw_fcs((u8 *)msg,
+							    2 + msg->tx_len);
+
+		/**
+		 * Retry for at least 250ms before returning an error.
+		 * Retry interval guideline:
+		 *   No minimum < Retry Interval < No maximum
+		 *                (recommend 10ms)
+		 */
+		end = ktime_get();
+		elapsed_ms = ktime_to_ms(ktime_sub(end, start));
+		if (elapsed_ms >= DEV_PECI_RETRY_TIME_MS) {
+			dev_dbg(&adapter->dev, "Timeout retrying xfer!\n");
+			rc = -ETIMEDOUT;
+			break;
+		}
+
+		usleep_range((DEV_PECI_RETRY_INTERVAL_USEC >> 2) + 1,
+			     DEV_PECI_RETRY_INTERVAL_USEC);
+	} while (true);
+
+	if (rc)
+		dev_dbg(&adapter->dev, "xfer error, rc: %d\n", rc);
+
+	return rc;
+}
+
+static int peci_xfer(struct peci_adapter *adapter, struct peci_xfer_msg *msg)
+{
+	return __peci_xfer(adapter, msg, false, false);
+}
+
+static int peci_xfer_with_retries(struct peci_adapter *adapter,
+				  struct peci_xfer_msg *msg,
+				  bool has_aw_fcs)
+{
+	return __peci_xfer(adapter, msg, true, has_aw_fcs);
+}
+
+static int peci_scan_cmd_mask(struct peci_adapter *adapter)
+{
+	struct peci_xfer_msg msg;
+	int rc = 0;
+	u32 dib;
+
+	/* Update command mask just once */
+	if (adapter->cmd_mask & BIT(PECI_CMD_XFER))
+		return 0;
+
+	msg.addr      = PECI_BASE_ADDR;
+	msg.tx_len    = GET_DIB_WR_LEN;
+	msg.rx_len    = GET_DIB_RD_LEN;
+	msg.tx_buf[0] = GET_DIB_PECI_CMD;
+
+	rc = peci_xfer(adapter, &msg);
+	if (rc)
+		return rc;
+
+	dib = le32_to_cpup((__le32 *)msg.rx_buf);
+
+	/* Check special case for Get DIB command */
+	if (dib == 0x00) {
+		dev_dbg(&adapter->dev, "DIB read as 0x00\n");
+		return -EIO;
+	}
+
+	/**
+	 * Setting up the supporting commands based on minor revision number.
+	 * See PECI Spec Table 3-1.
+	 */
+	switch (FIELD_GET(MINOR_REV_NUM_MASK, dib)) {
+	case 6:
+		adapter->cmd_mask |= BIT(PECI_CMD_WR_IA_MSR);
+		/* fallthrough */
+	case 5:
+		adapter->cmd_mask |= BIT(PECI_CMD_WR_PCI_CFG);
+		/* fallthrough */
+	case 4:
+		adapter->cmd_mask |= BIT(PECI_CMD_RD_PCI_CFG);
+		/* fallthrough */
+	case 3:
+		adapter->cmd_mask |= BIT(PECI_CMD_RD_PCI_CFG_LOCAL);
+		adapter->cmd_mask |= BIT(PECI_CMD_WR_PCI_CFG_LOCAL);
+		/* fallthrough */
+	case 2:
+		adapter->cmd_mask |= BIT(PECI_CMD_RD_IA_MSR);
+		/* fallthrough */
+	case 1:
+		adapter->cmd_mask |= BIT(PECI_CMD_RD_PKG_CFG);
+		adapter->cmd_mask |= BIT(PECI_CMD_WR_PKG_CFG);
+	}
+
+	adapter->cmd_mask |= BIT(PECI_CMD_XFER);
+	adapter->cmd_mask |= BIT(PECI_CMD_GET_TEMP);
+	adapter->cmd_mask |= BIT(PECI_CMD_GET_DIB);
+	adapter->cmd_mask |= BIT(PECI_CMD_PING);
+
+	return rc;
+}
+
+static int peci_cmd_support(struct peci_adapter *adapter, enum peci_cmd cmd)
+{
+	if (!(adapter->cmd_mask & BIT(PECI_CMD_PING)) &&
+	    peci_scan_cmd_mask(adapter) < 0) {
+		dev_dbg(&adapter->dev, "Failed to scan command mask\n");
+		return -EIO;
+	}
+
+	if (!(adapter->cmd_mask & BIT(cmd))) {
+		dev_dbg(&adapter->dev, "Command %d is not supported\n", cmd);
+		return -EINVAL;
+	}
+
+	return 0;
+}
+
+static int peci_ioctl_xfer(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_xfer_msg *msg = vmsg;
+
+	return peci_xfer(adapter, msg);
+}
+
+static int peci_ioctl_ping(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_ping_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+
+	msg.addr   = umsg->addr;
+	msg.tx_len = 0;
+	msg.rx_len = 0;
+
+	return peci_xfer(adapter, &msg);
+}
+
+static int peci_ioctl_get_dib(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_get_dib_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	int rc;
+
+	msg.addr      = umsg->addr;
+	msg.tx_len    = GET_DIB_WR_LEN;
+	msg.rx_len    = GET_DIB_RD_LEN;
+	msg.tx_buf[0] = GET_DIB_PECI_CMD;
+
+	rc = peci_xfer(adapter, &msg);
+	if (rc)
+		return rc;
+
+	umsg->dib = le32_to_cpup((__le32 *)msg.rx_buf);
+
+	return 0;
+}
+
+static int peci_ioctl_get_temp(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_get_temp_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	int rc;
+
+	msg.addr      = umsg->addr;
+	msg.tx_len    = GET_TEMP_WR_LEN;
+	msg.rx_len    = GET_TEMP_RD_LEN;
+	msg.tx_buf[0] = GET_TEMP_PECI_CMD;
+
+	rc = peci_xfer(adapter, &msg);
+	if (rc)
+		return rc;
+
+	umsg->temp_raw = le16_to_cpup((__le16 *)msg.rx_buf);
+
+	return 0;
+}
+
+static int peci_ioctl_rd_pkg_cfg(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_rd_pkg_cfg_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	int rc = 0;
+
+	/* Per the PECI spec, the read length must be a byte, word, or dword */
+	if (umsg->rx_len != 1 && umsg->rx_len != 2 && umsg->rx_len != 4) {
+		dev_dbg(&adapter->dev, "Invalid read length, rx_len: %d\n",
+			umsg->rx_len);
+		return -EINVAL;
+	}
+
+	msg.addr = umsg->addr;
+	msg.tx_len = RDPKGCFG_WRITE_LEN;
+	/* read lengths of 1 and 2 result in an error, so only use 4 for now */
+	msg.rx_len = RDPKGCFG_READ_LEN_BASE + umsg->rx_len;
+	msg.tx_buf[0] = RDPKGCFG_PECI_CMD;
+	msg.tx_buf[1] = 0x00;         /* request byte for Host ID | Retry bit */
+				      /* Host ID is 0 for PECI 3.0 */
+	msg.tx_buf[2] = umsg->index;            /* RdPkgConfig index */
+	msg.tx_buf[3] = (u8)umsg->param;        /* LSB - Config parameter */
+	msg.tx_buf[4] = (u8)(umsg->param >> 8); /* MSB - Config parameter */
+
+	rc = peci_xfer_with_retries(adapter, &msg, false);
+	if (!rc)
+		memcpy(umsg->pkg_config, &msg.rx_buf[1], umsg->rx_len);
+
+	return rc;
+}
+
+static int peci_ioctl_wr_pkg_cfg(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_wr_pkg_cfg_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	int rc = 0, i;
+
+	/* Per the PECI spec, the write length must be a dword */
+	if (umsg->tx_len != 4) {
+		dev_dbg(&adapter->dev, "Invalid write length, tx_len: %d\n",
+			umsg->tx_len);
+		return -EINVAL;
+	}
+
+	msg.addr = umsg->addr;
+	msg.tx_len = WRPKGCFG_WRITE_LEN_BASE + umsg->tx_len;
+	/* read lengths of 1 and 2 result in an error, so only use 4 for now */
+	msg.rx_len = WRPKGCFG_READ_LEN;
+	msg.tx_buf[0] = WRPKGCFG_PECI_CMD;
+	msg.tx_buf[1] = 0x00;         /* request byte for Host ID | Retry bit */
+				      /* Host ID is 0 for PECI 3.0 */
+	msg.tx_buf[2] = umsg->index;            /* RdPkgConfig index */
+	msg.tx_buf[3] = (u8)umsg->param;        /* LSB - Config parameter */
+	msg.tx_buf[4] = (u8)(umsg->param >> 8); /* MSB - Config parameter */
+	for (i = 0; i < umsg->tx_len; i++)
+		msg.tx_buf[5 + i] = (u8)(umsg->value >> (i << 3));
+
+	/* Add an Assure Write Frame Check Sequence byte */
+	msg.tx_buf[5 + i] = 0x80 ^
+			    peci_aw_fcs((u8 *)&msg, 8 + umsg->tx_len);
+
+	rc = peci_xfer_with_retries(adapter, &msg, true);
+
+	return rc;
+}
+
+static int peci_ioctl_rd_ia_msr(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_rd_ia_msr_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	int rc = 0;
+
+	msg.addr = umsg->addr;
+	msg.tx_len = RDIAMSR_WRITE_LEN;
+	msg.rx_len = RDIAMSR_READ_LEN;
+	msg.tx_buf[0] = RDIAMSR_PECI_CMD;
+	msg.tx_buf[1] = 0x00;
+	msg.tx_buf[2] = umsg->thread_id;
+	msg.tx_buf[3] = (u8)umsg->address;
+	msg.tx_buf[4] = (u8)(umsg->address >> 8);
+
+	rc = peci_xfer_with_retries(adapter, &msg, false);
+	if (!rc)
+		memcpy(&umsg->value, &msg.rx_buf[1], sizeof(uint64_t));
+
+	return rc;
+}
+
+static int peci_ioctl_rd_pci_cfg(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_rd_pci_cfg_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	u32 address;
+	int rc = 0;
+
+	address = umsg->reg;                  /* [11:0]  - Register */
+	address |= (u32)umsg->function << 12; /* [14:12] - Function */
+	address |= (u32)umsg->device << 15;   /* [19:15] - Device   */
+	address |= (u32)umsg->bus << 20;      /* [27:20] - Bus      */
+					      /* [31:28] - Reserved */
+	msg.addr = umsg->addr;
+	msg.tx_len = RDPCICFG_WRITE_LEN;
+	msg.rx_len = RDPCICFG_READ_LEN;
+	msg.tx_buf[0] = RDPCICFG_PECI_CMD;
+	msg.tx_buf[1] = 0x00;         /* request byte for Host ID | Retry bit */
+				      /* Host ID is 0 for PECI 3.0 */
+	msg.tx_buf[2] = (u8)address;         /* LSB - PCI Config Address */
+	msg.tx_buf[3] = (u8)(address >> 8);  /* PCI Config Address */
+	msg.tx_buf[4] = (u8)(address >> 16); /* PCI Config Address */
+	msg.tx_buf[5] = (u8)(address >> 24); /* MSB - PCI Config Address */
+
+	rc = peci_xfer_with_retries(adapter, &msg, false);
+	if (!rc)
+		memcpy(umsg->pci_config, &msg.rx_buf[1], 4);
+
+	return rc;
+}
+
+static int peci_ioctl_rd_pci_cfg_local(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_rd_pci_cfg_local_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	u32 address;
+	int rc = 0;
+
+	/* Per the PECI spec, the read length must be a byte, word, or dword */
+	if (umsg->rx_len != 1 && umsg->rx_len != 2 && umsg->rx_len != 4) {
+		dev_dbg(&adapter->dev, "Invalid read length, rx_len: %d\n",
+			umsg->rx_len);
+		return -EINVAL;
+	}
+
+	address = umsg->reg;                  /* [11:0]  - Register */
+	address |= (u32)umsg->function << 12; /* [14:12] - Function */
+	address |= (u32)umsg->device << 15;   /* [19:15] - Device   */
+	address |= (u32)umsg->bus << 20;      /* [23:20] - Bus      */
+
+	msg.addr = umsg->addr;
+	msg.tx_len = RDPCICFGLOCAL_WRITE_LEN;
+	msg.rx_len = RDPCICFGLOCAL_READ_LEN_BASE + umsg->rx_len;
+	msg.tx_buf[0] = RDPCICFGLOCAL_PECI_CMD;
+	msg.tx_buf[1] = 0x00;         /* request byte for Host ID | Retry bit */
+				      /* Host ID is 0 for PECI 3.0 */
+	msg.tx_buf[2] = (u8)address;       /* LSB - PCI Configuration Address */
+	msg.tx_buf[3] = (u8)(address >> 8);  /* PCI Configuration Address */
+	msg.tx_buf[4] = (u8)(address >> 16); /* PCI Configuration Address */
+
+	rc = peci_xfer_with_retries(adapter, &msg, false);
+	if (!rc)
+		memcpy(umsg->pci_config, &msg.rx_buf[1], umsg->rx_len);
+
+	return rc;
+}
+
+static int peci_ioctl_wr_pci_cfg_local(struct peci_adapter *adapter, void *vmsg)
+{
+	struct peci_wr_pci_cfg_local_msg *umsg = vmsg;
+	struct peci_xfer_msg msg;
+	int rc = 0, i;
+	u32 address;
+
+	/* Per the PECI spec, the write length must be a byte, word, or dword */
+	if (umsg->tx_len != 1 && umsg->tx_len != 2 && umsg->tx_len != 4) {
+		dev_dbg(&adapter->dev, "Invalid write length, tx_len: %d\n",
+			umsg->tx_len);
+		return -EINVAL;
+	}
+
+	address = umsg->reg;                  /* [11:0]  - Register */
+	address |= (u32)umsg->function << 12; /* [14:12] - Function */
+	address |= (u32)umsg->device << 15;   /* [19:15] - Device   */
+	address |= (u32)umsg->bus << 20;      /* [23:20] - Bus      */
+
+	msg.addr = umsg->addr;
+	msg.tx_len = WRPCICFGLOCAL_WRITE_LEN_BASE + umsg->tx_len;
+	msg.rx_len = WRPCICFGLOCAL_READ_LEN;
+	msg.tx_buf[0] = WRPCICFGLOCAL_PECI_CMD;
+	msg.tx_buf[1] = 0x00;         /* request byte for Host ID | Retry bit */
+				      /* Host ID is 0 for PECI 3.0 */
+	msg.tx_buf[2] = (u8)address;       /* LSB - PCI Configuration Address */
+	msg.tx_buf[3] = (u8)(address >> 8);  /* PCI Configuration Address */
+	msg.tx_buf[4] = (u8)(address >> 16); /* PCI Configuration Address */
+	for (i = 0; i < umsg->tx_len; i++)
+		msg.tx_buf[5 + i] = (u8)(umsg->value >> (i << 3));
+
+	/* Add an Assure Write Frame Check Sequence byte */
+	msg.tx_buf[5 + i] = 0x80 ^
+			    peci_aw_fcs((u8 *)&msg, 8 + umsg->tx_len);
+
+	rc = peci_xfer_with_retries(adapter, &msg, true);
+
+	return rc;
+}
+
+typedef int (*peci_ioctl_fn_type)(struct peci_adapter *, void *);
+
+static const peci_ioctl_fn_type peci_ioctl_fn[PECI_CMD_MAX] = {
+	peci_ioctl_xfer,
+	peci_ioctl_ping,
+	peci_ioctl_get_dib,
+	peci_ioctl_get_temp,
+	peci_ioctl_rd_pkg_cfg,
+	peci_ioctl_wr_pkg_cfg,
+	peci_ioctl_rd_ia_msr,
+	NULL, /* Reserved */
+	peci_ioctl_rd_pci_cfg,
+	NULL, /* Reserved */
+	peci_ioctl_rd_pci_cfg_local,
+	peci_ioctl_wr_pci_cfg_local,
+};
+
+int peci_command(struct peci_adapter *adapter, enum peci_cmd cmd, void *vmsg)
+{
+	int rc = 0;
+
+	if (cmd >= PECI_CMD_MAX || cmd < PECI_CMD_XFER)
+		return -EINVAL;
+
+	dev_dbg(&adapter->dev, "%s, cmd=0x%02x\n", __func__, cmd);
+
+	if (!peci_ioctl_fn[cmd])
+		return -EINVAL;
+
+	rt_mutex_lock(&adapter->bus_lock);
+
+	rc = peci_cmd_support(adapter, cmd);
+	if (!rc)
+		rc = peci_ioctl_fn[cmd](adapter, vmsg);
+
+	rt_mutex_unlock(&adapter->bus_lock);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(peci_command);
+
+static long peci_ioctl(struct file *file, unsigned int iocmd, unsigned long arg)
+{
+	struct peci_adapter *adapter = file->private_data;
+	void __user *argp = (void __user *)arg;
+	unsigned int msg_len;
+	enum peci_cmd cmd;
+	int rc = 0;
+	u8 *msg;
+
+	if (!capable(CAP_SYS_ADMIN))
+		return -EPERM;
+
+	dev_dbg(&adapter->dev, "ioctl, cmd=0x%x, arg=0x%lx\n", iocmd, arg);
+
+	switch (iocmd) {
+	case PECI_IOC_XFER:
+	case PECI_IOC_PING:
+	case PECI_IOC_GET_DIB:
+	case PECI_IOC_GET_TEMP:
+	case PECI_IOC_RD_PKG_CFG:
+	case PECI_IOC_WR_PKG_CFG:
+	case PECI_IOC_RD_IA_MSR:
+	case PECI_IOC_RD_PCI_CFG:
+	case PECI_IOC_RD_PCI_CFG_LOCAL:
+	case PECI_IOC_WR_PCI_CFG_LOCAL:
+		cmd = _IOC_NR(iocmd);
+		msg_len = _IOC_SIZE(iocmd);
+		break;
+
+	default:
+		dev_dbg(&adapter->dev, "Invalid ioctl cmd : 0x%x\n", iocmd);
+		return -ENOTTY;
+	}
+
+	if (!access_ok(VERIFY_WRITE, argp, msg_len))
+		return -EFAULT;
+
+	msg = memdup_user(argp, msg_len);
+	if (IS_ERR(msg))
+		return PTR_ERR(msg);
+
+	rc = peci_command(adapter, cmd, msg);
+
+	if (!rc && copy_to_user(argp, msg, msg_len))
+		rc = -EFAULT;
+
+	kfree(msg);
+	return (long)rc;
+}
+
+static int peci_open(struct inode *inode, struct file *file)
+{
+	unsigned int minor = iminor(inode);
+	struct peci_adapter *adapter;
+
+	adapter = peci_get_adapter(minor);
+	if (!adapter)
+		return -ENODEV;
+
+	file->private_data = adapter;
+
+	return 0;
+}
+
+static int peci_release(struct inode *inode, struct file *file)
+{
+	struct peci_adapter *adapter = file->private_data;
+
+	peci_put_adapter(adapter);
+	file->private_data = NULL;
+
+	return 0;
+}
+
+static const struct file_operations peci_fops = {
+	.owner          = THIS_MODULE,
+	.unlocked_ioctl = peci_ioctl,
+	.open           = peci_open,
+	.release        = peci_release,
+};
+
+static int peci_detect(struct peci_adapter *adapter, u8 addr)
+{
+	struct peci_ping_msg msg;
+
+	msg.addr = addr;
+
+	return peci_command(adapter, PECI_CMD_PING, &msg);
+}
+
+static const struct of_device_id *
+peci_of_match_device(const struct of_device_id *matches,
+		     struct peci_client *client)
+{
+#if IS_ENABLED(CONFIG_OF)
+	if (!(client && matches))
+		return NULL;
+
+	return of_match_device(matches, &client->dev);
+#else
+	return NULL;
+#endif
+}
+
+static const struct peci_device_id *
+peci_match_id(const struct peci_device_id *id, struct peci_client *client)
+{
+	if (!(id && client))
+		return NULL;
+
+	while (id->name[0]) {
+		if (!strncmp(client->name, id->name, PECI_NAME_SIZE))
+			return id;
+		id++;
+	}
+
+	return NULL;
+}
+
+static int peci_device_match(struct device *dev, struct device_driver *drv)
+{
+	struct peci_client *client = peci_verify_client(dev);
+	struct peci_driver *driver;
+
+	/* Attempt an OF style match */
+	if (peci_of_match_device(drv->of_match_table, client))
+		return 1;
+
+	driver = to_peci_driver(drv);
+
+	/* Finally an ID match */
+	if (peci_match_id(driver->id_table, client))
+		return 1;
+
+	return 0;
+}
+
+static int peci_device_probe(struct device *dev)
+{
+	struct peci_client *client = peci_verify_client(dev);
+	struct peci_driver *driver;
+	int status = -EINVAL;
+
+	if (!client)
+		return 0;
+
+	driver = to_peci_driver(dev->driver);
+
+	if (!driver->id_table &&
+	    !peci_of_match_device(dev->driver->of_match_table, client))
+		return -ENODEV;
+
+	dev_dbg(dev, "%s: name:%s\n", __func__, client->name);
+
+	status = dev_pm_domain_attach(&client->dev, true);
+	if (status == -EPROBE_DEFER)
+		return status;
+
+	if (driver->probe)
+		status = driver->probe(client);
+	else
+		status = -EINVAL;
+
+	if (status)
+		goto err_detach_pm_domain;
+
+	return 0;
+
+err_detach_pm_domain:
+	dev_pm_domain_detach(&client->dev, true);
+	return status;
+}
+
+static int peci_device_remove(struct device *dev)
+{
+	struct peci_client *client = peci_verify_client(dev);
+	struct peci_driver *driver;
+	int status = 0;
+
+	if (!client || !dev->driver)
+		return 0;
+
+	driver = to_peci_driver(dev->driver);
+	if (driver->remove) {
+		dev_dbg(dev, "%s: name:%s\n", __func__, client->name);
+		status = driver->remove(client);
+	}
+
+	dev_pm_domain_detach(&client->dev, true);
+
+	return status;
+}
+
+static void peci_device_shutdown(struct device *dev)
+{
+	struct peci_client *client = peci_verify_client(dev);
+	struct peci_driver *driver;
+
+	if (!client || !dev->driver)
+		return;
+
+	dev_dbg(dev, "%s: name:%s\n", __func__, client->name);
+
+	driver = to_peci_driver(dev->driver);
+	if (driver->shutdown)
+		driver->shutdown(client);
+}
+
+static struct bus_type peci_bus_type = {
+	.name		= "peci",
+	.match		= peci_device_match,
+	.probe		= peci_device_probe,
+	.remove		= peci_device_remove,
+	.shutdown	= peci_device_shutdown,
+};
+
+static int peci_check_addr_validity(u8 addr)
+{
+	if (addr < PECI_BASE_ADDR && addr > PECI_BASE_ADDR + PECI_OFFSET_MAX)
+		return -EINVAL;
+
+	return 0;
+}
+
+static int peci_check_client_busy(struct device *dev, void *client_new_p)
+{
+	struct peci_client *client = peci_verify_client(dev);
+	struct peci_client *client_new = client_new_p;
+
+	if (client && client->addr == client_new->addr)
+		return -EBUSY;
+
+	return 0;
+}
+
+int peci_get_cpu_id(struct peci_adapter *adapter, u8 addr, u32 *cpu_id)
+{
+	struct peci_rd_pkg_cfg_msg msg;
+	int rc;
+
+	msg.addr = addr;
+	msg.index = MBX_INDEX_CPU_ID;
+	msg.param = PKG_ID_CPU_ID;
+	msg.rx_len = 4;
+
+	rc = peci_command(adapter, PECI_CMD_RD_PKG_CFG, &msg);
+	if (!rc)
+		*cpu_id = le32_to_cpup((__le32 *)msg.pkg_config);
+
+	return rc;
+}
+EXPORT_SYMBOL_GPL(peci_get_cpu_id);
+
+static struct peci_client *peci_new_device(struct peci_adapter *adapter,
+					   struct peci_board_info const *info)
+{
+	struct peci_client *client;
+	int rc;
+
+	/* Increase reference count for the adapter assigned */
+	if (!peci_get_adapter(adapter->nr))
+		return NULL;
+
+	client = kzalloc(sizeof(*client), GFP_KERNEL);
+	if (!client)
+		goto err_put_adapter;
+
+	client->adapter = adapter;
+	client->addr = info->addr;
+	strlcpy(client->name, info->type, sizeof(client->name));
+
+	rc = peci_check_addr_validity(client->addr);
+	if (rc) {
+		dev_err(&adapter->dev, "Invalid PECI CPU address 0x%02hx\n",
+			client->addr);
+		goto err_free_client_silent;
+	}
+
+	/* Check online status of client */
+	rc = peci_detect(adapter, client->addr);
+	if (rc)
+		goto err_free_client;
+
+	rc = device_for_each_child(&adapter->dev, client,
+				   peci_check_client_busy);
+	if (rc)
+		goto err_free_client;
+
+	client->dev.parent = &client->adapter->dev;
+	client->dev.bus = &peci_bus_type;
+	client->dev.type = &peci_client_type;
+	client->dev.of_node = info->of_node;
+	dev_set_name(&client->dev, "%d-%02x", adapter->nr, client->addr);
+
+	rc = device_register(&client->dev);
+	if (rc)
+		goto err_free_client;
+
+	dev_dbg(&adapter->dev, "client [%s] registered with bus id %s\n",
+		client->name, dev_name(&client->dev));
+
+	return client;
+
+err_free_client:
+	dev_err(&adapter->dev,
+		"Failed to register peci client %s at 0x%02x (%d)\n",
+		client->name, client->addr, rc);
+err_free_client_silent:
+	kfree(client);
+err_put_adapter:
+	peci_put_adapter(adapter);
+	return NULL;
+}
+
+static void peci_unregister_device(struct peci_client *client)
+{
+	if (!client)
+		return;
+
+	if (client->dev.of_node)
+		of_node_clear_flag(client->dev.of_node, OF_POPULATED);
+
+	device_unregister(&client->dev);
+}
+
+static int peci_unregister_client(struct device *dev, void *dummy)
+{
+	struct peci_client *client = peci_verify_client(dev);
+
+	peci_unregister_device(client);
+
+	return 0;
+}
+
+static void peci_adapter_dev_release(struct device *dev)
+{
+	struct peci_adapter *adapter = to_peci_adapter(dev);
+
+	dev_dbg(dev, "%s: %s\n", __func__, adapter->name);
+	mutex_destroy(&adapter->userspace_clients_lock);
+	rt_mutex_destroy(&adapter->bus_lock);
+	kfree(adapter);
+}
+
+static ssize_t peci_sysfs_new_device(struct device *dev,
+				     struct device_attribute *attr,
+				     const char *buf, size_t count)
+{
+	struct peci_adapter *adapter = to_peci_adapter(dev);
+	struct peci_board_info info = {};
+	struct peci_client *client;
+	char *blank, end;
+	int rc;
+
+	/* Parse device type */
+	blank = strchr(buf, ' ');
+	if (!blank) {
+		dev_err(dev, "%s: Missing parameters\n", "new_device");
+		return -EINVAL;
+	}
+	if (blank - buf > PECI_NAME_SIZE - 1) {
+		dev_err(dev, "%s: Invalid device type\n", "new_device");
+		return -EINVAL;
+	}
+	memcpy(info.type, buf, blank - buf);
+
+	/* Parse remaining parameters, reject extra parameters */
+	rc = sscanf(++blank, "%hi%c", &info.addr, &end);
+	if (rc < 1) {
+		dev_err(dev, "%s: Can't parse client address\n", "new_device");
+		return -EINVAL;
+	}
+	if (rc > 1  && end != '\n') {
+		dev_err(dev, "%s: Extra parameters\n", "new_device");
+		return -EINVAL;
+	}
+
+	client = peci_new_device(adapter, &info);
+	if (!client)
+		return -EINVAL;
+
+	/* Keep track of the added device */
+	mutex_lock(&adapter->userspace_clients_lock);
+	list_add_tail(&client->detected, &adapter->userspace_clients);
+	mutex_unlock(&adapter->userspace_clients_lock);
+	dev_info(dev, "%s: Instantiated device %s at 0x%02hx\n", "new_device",
+		 info.type, info.addr);
+
+	return count;
+}
+static DEVICE_ATTR(new_device, 0200, NULL, peci_sysfs_new_device);
+
+static ssize_t peci_sysfs_delete_device(struct device *dev,
+					struct device_attribute *attr,
+					const char *buf, size_t count)
+{
+	struct peci_adapter *adapter = to_peci_adapter(dev);
+	struct peci_client *client, *next;
+	struct peci_board_info info = {};
+	struct peci_driver *driver;
+	char *blank, end;
+	int rc;
+
+	/* Parse device type */
+	blank = strchr(buf, ' ');
+	if (!blank) {
+		dev_err(dev, "%s: Missing parameters\n", "delete_device");
+		return -EINVAL;
+	}
+	if (blank - buf > PECI_NAME_SIZE - 1) {
+		dev_err(dev, "%s: Invalid device type\n", "delete_device");
+		return -EINVAL;
+	}
+	memcpy(info.type, buf, blank - buf);
+
+	/* Parse remaining parameters, reject extra parameters */
+	rc = sscanf(++blank, "%hi%c", &info.addr, &end);
+	if (rc < 1) {
+		dev_err(dev, "%s: Can't parse client address\n",
+			"delete_device");
+		return -EINVAL;
+	}
+	if (rc > 1  && end != '\n') {
+		dev_err(dev, "%s: Extra parameters\n", "delete_device");
+		return -EINVAL;
+	}
+
+	/* Make sure the device was added through sysfs */
+	rc = -ENOENT;
+	mutex_lock(&adapter->userspace_clients_lock);
+	list_for_each_entry_safe(client, next, &adapter->userspace_clients,
+				 detected) {
+		driver = to_peci_driver(client->dev.driver);
+
+		if (client->addr == info.addr &&
+		    !strncmp(client->name, info.type, PECI_NAME_SIZE)) {
+			dev_info(dev, "%s: Deleting device %s at 0x%02hx\n",
+				 "delete_device", client->name, client->addr);
+			list_del(&client->detected);
+			peci_unregister_device(client);
+			rc = count;
+			break;
+		}
+	}
+	mutex_unlock(&adapter->userspace_clients_lock);
+
+	if (rc < 0)
+		dev_err(dev, "%s: Can't find device in list\n",
+			"delete_device");
+
+	return rc;
+}
+static DEVICE_ATTR_IGNORE_LOCKDEP(delete_device, 0200, NULL,
+				  peci_sysfs_delete_device);
+
+static struct attribute *peci_adapter_attrs[] = {
+	&dev_attr_name.attr,
+	&dev_attr_new_device.attr,
+	&dev_attr_delete_device.attr,
+	NULL
+};
+ATTRIBUTE_GROUPS(peci_adapter);
+
+static struct device_type peci_adapter_type = {
+	.groups		= peci_adapter_groups,
+	.release	= peci_adapter_dev_release,
+};
+
+struct peci_adapter *peci_verify_adapter(struct device *dev)
+{
+	return (dev->type == &peci_adapter_type)
+			? to_peci_adapter(dev)
+			: NULL;
+}
+EXPORT_SYMBOL_GPL(peci_verify_adapter);
+
+#if IS_ENABLED(CONFIG_OF)
+static struct peci_client *peci_of_register_device(struct peci_adapter *adapter,
+						   struct device_node *node)
+{
+	struct peci_board_info info = {};
+	struct peci_client *result;
+	const __be32 *addr_be;
+	int len;
+
+	dev_dbg(&adapter->dev, "register %pOF\n", node);
+
+	if (of_modalias_node(node, info.type, sizeof(info.type)) < 0) {
+		dev_err(&adapter->dev, "modalias failure on %pOF\n", node);
+		return ERR_PTR(-EINVAL);
+	}
+
+	addr_be = of_get_property(node, "reg", &len);
+	if (!addr_be || len < sizeof(*addr_be)) {
+		dev_err(&adapter->dev, "invalid reg on %pOF\n", node);
+		return ERR_PTR(-EINVAL);
+	}
+
+	info.addr = be32_to_cpup(addr_be);
+	info.of_node = of_node_get(node);
+
+	result = peci_new_device(adapter, &info);
+	if (!result)
+		result = ERR_PTR(-EINVAL);
+
+	of_node_put(node);
+	return result;
+}
+
+static void peci_of_register_devices(struct peci_adapter *adapter)
+{
+	struct device_node *bus, *node;
+	struct peci_client *client;
+
+	/* Only register child devices if the adapter has a node pointer set */
+	if (!adapter->dev.of_node)
+		return;
+
+	bus = of_get_child_by_name(adapter->dev.of_node, "peci-bus");
+	if (!bus)
+		bus = of_node_get(adapter->dev.of_node);
+
+	for_each_available_child_of_node(bus, node) {
+		if (of_node_test_and_set_flag(node, OF_POPULATED))
+			continue;
+
+		client = peci_of_register_device(adapter, node);
+		if (IS_ERR(client)) {
+			dev_warn(&adapter->dev,
+				 "Failed to create PECI device for %pOF\n",
+				 node);
+			of_node_clear_flag(node, OF_POPULATED);
+		}
+	}
+
+	of_node_put(bus);
+}
+#else
+static void peci_of_register_devices(struct peci_adapter *adapter) { }
+#endif /* CONFIG_OF */
+
+#if IS_ENABLED(CONFIG_OF_DYNAMIC)
+static int peci_of_match_node(struct device *dev, void *data)
+{
+	return dev->of_node == data;
+}
+
+/* must call put_device() when done with returned peci_client device */
+static struct peci_client *peci_of_find_device(struct device_node *node)
+{
+	struct peci_client *client;
+	struct device *dev;
+
+	dev = bus_find_device(&peci_bus_type, NULL, node, peci_of_match_node);
+	if (!dev)
+		return NULL;
+
+	client = peci_verify_client(dev);
+	if (!client)
+		put_device(dev);
+
+	return client;
+}
+
+/* must call put_device() when done with returned peci_adapter device */
+static struct peci_adapter *peci_of_find_adapter(struct device_node *node)
+{
+	struct peci_adapter *adapter;
+	struct device *dev;
+
+	dev = bus_find_device(&peci_bus_type, NULL, node, peci_of_match_node);
+	if (!dev)
+		return NULL;
+
+	adapter = peci_verify_adapter(dev);
+	if (!adapter)
+		put_device(dev);
+
+	return adapter;
+}
+
+static int peci_of_notify(struct notifier_block *nb,
+			  unsigned long action,
+			  void *arg)
+{
+	struct of_reconfig_data *rd = arg;
+	struct peci_adapter *adapter;
+	struct peci_client *client;
+
+	switch (of_reconfig_get_state_change(action, rd)) {
+	case OF_RECONFIG_CHANGE_ADD:
+		adapter = peci_of_find_adapter(rd->dn->parent);
+		if (!adapter)
+			return NOTIFY_OK;	/* not for us */
+
+		if (of_node_test_and_set_flag(rd->dn, OF_POPULATED)) {
+			put_device(&adapter->dev);
+			return NOTIFY_OK;
+		}
+
+		client = peci_of_register_device(adapter, rd->dn);
+		put_device(&adapter->dev);
+
+		if (IS_ERR(client)) {
+			dev_err(&adapter->dev,
+				"failed to create client for '%pOF'\n", rd->dn);
+			of_node_clear_flag(rd->dn, OF_POPULATED);
+			return notifier_from_errno(PTR_ERR(client));
+		}
+		break;
+	case OF_RECONFIG_CHANGE_REMOVE:
+		/* already depopulated? */
+		if (!of_node_check_flag(rd->dn, OF_POPULATED))
+			return NOTIFY_OK;
+
+		/* find our device by node */
+		client = peci_of_find_device(rd->dn);
+		if (!client)
+			return NOTIFY_OK;	/* no? not meant for us */
+
+		/* unregister takes one ref away */
+		peci_unregister_device(client);
+
+		/* and put the reference of the find */
+		put_device(&client->dev);
+		break;
+	}
+
+	return NOTIFY_OK;
+}
+
+static struct notifier_block peci_of_notifier = {
+	.notifier_call = peci_of_notify,
+};
+#else
+extern struct notifier_block peci_of_notifier;
+#endif /* CONFIG_OF_DYNAMIC */
+
+struct peci_adapter *peci_alloc_adapter(struct device *dev, unsigned int size)
+{
+	struct peci_adapter *adapter;
+
+	if (!dev)
+		return NULL;
+
+	adapter = kzalloc(size + sizeof(*adapter), GFP_KERNEL);
+	if (!adapter)
+		return NULL;
+
+	device_initialize(&adapter->dev);
+	adapter->dev.parent = dev;
+	adapter->dev.bus = &peci_bus_type;
+	adapter->dev.type = &peci_adapter_type;
+	peci_set_adapdata(adapter, &adapter[1]);
+
+	return adapter;
+}
+EXPORT_SYMBOL_GPL(peci_alloc_adapter);
+
+static int peci_register_adapter(struct peci_adapter *adapter)
+{
+	int rc = -EINVAL;
+
+	/* Can't register until after driver model init */
+	if (WARN_ON(!is_registered))
+		goto err_free_idr;
+
+	if (WARN(!adapter->name[0], "peci adapter has no name"))
+		goto err_free_idr;
+
+	if (WARN(!adapter->xfer, "peci adapter has no xfer function\n"))
+		goto err_free_idr;
+
+	rt_mutex_init(&adapter->bus_lock);
+	mutex_init(&adapter->userspace_clients_lock);
+	INIT_LIST_HEAD(&adapter->userspace_clients);
+
+	dev_set_name(&adapter->dev, "peci%d", adapter->nr);
+
+	/* cdev */
+	cdev_init(&adapter->cdev, &peci_fops);
+	adapter->cdev.owner = THIS_MODULE;
+	adapter->dev.devt = MKDEV(MAJOR(peci_devt), adapter->nr);
+	rc = cdev_add(&adapter->cdev, adapter->dev.devt, 1);
+	if (rc) {
+		pr_err("adapter '%s': can't add cdev (%d)\n",
+		       adapter->name, rc);
+		goto err_free_idr;
+	}
+	rc = device_add(&adapter->dev);
+	if (rc) {
+		pr_err("adapter '%s': can't add device (%d)\n",
+		       adapter->name, rc);
+		goto err_del_cdev;
+	}
+
+	dev_dbg(&adapter->dev, "adapter [%s] registered\n", adapter->name);
+
+	pm_runtime_no_callbacks(&adapter->dev);
+	pm_suspend_ignore_children(&adapter->dev, true);
+	pm_runtime_enable(&adapter->dev);
+
+	/* create pre-declared device nodes */
+	peci_of_register_devices(adapter);
+
+	return 0;
+
+err_del_cdev:
+	cdev_del(&adapter->cdev);
+err_free_idr:
+	mutex_lock(&core_lock);
+	idr_remove(&peci_adapter_idr, adapter->nr);
+	mutex_unlock(&core_lock);
+	return rc;
+}
+
+static int peci_add_numbered_adapter(struct peci_adapter *adapter)
+{
+	int id;
+
+	mutex_lock(&core_lock);
+	id = idr_alloc(&peci_adapter_idr, adapter,
+		       adapter->nr, adapter->nr + 1, GFP_KERNEL);
+	mutex_unlock(&core_lock);
+	if (WARN(id < 0, "couldn't get idr"))
+		return id == -ENOSPC ? -EBUSY : id;
+
+	return peci_register_adapter(adapter);
+}
+
+int peci_add_adapter(struct peci_adapter *adapter)
+{
+	struct device *dev = &adapter->dev;
+	int id;
+
+	if (dev->of_node) {
+		id = of_alias_get_id(dev->of_node, "peci");
+		if (id >= 0) {
+			adapter->nr = id;
+			return peci_add_numbered_adapter(adapter);
+		}
+	}
+
+	mutex_lock(&core_lock);
+	id = idr_alloc(&peci_adapter_idr, adapter, 0, 0, GFP_KERNEL);
+	mutex_unlock(&core_lock);
+	if (WARN(id < 0, "couldn't get idr"))
+		return id;
+
+	adapter->nr = id;
+
+	return peci_register_adapter(adapter);
+}
+EXPORT_SYMBOL_GPL(peci_add_adapter);
+
+void peci_del_adapter(struct peci_adapter *adapter)
+{
+	struct peci_client *client, *next;
+	struct peci_adapter *found;
+	int nr;
+
+	/* First make sure that this adapter was ever added */
+	mutex_lock(&core_lock);
+	found = idr_find(&peci_adapter_idr, adapter->nr);
+	mutex_unlock(&core_lock);
+
+	if (found != adapter)
+		return;
+
+	/* Remove devices instantiated from sysfs */
+	mutex_lock(&adapter->userspace_clients_lock);
+	list_for_each_entry_safe(client, next, &adapter->userspace_clients,
+				 detected) {
+		dev_dbg(&adapter->dev, "Removing %s at 0x%x\n", client->name,
+			client->addr);
+		list_del(&client->detected);
+		peci_unregister_device(client);
+	}
+	mutex_unlock(&adapter->userspace_clients_lock);
+
+	/**
+	 * Detach any active clients. This can't fail, thus we do not
+	 * check the returned value.
+	 */
+	device_for_each_child(&adapter->dev, NULL, peci_unregister_client);
+
+	/* device name is gone after device_unregister */
+	dev_dbg(&adapter->dev, "adapter [%s] unregistered\n", adapter->name);
+
+	/* free cdev */
+	cdev_del(&adapter->cdev);
+
+	pm_runtime_disable(&adapter->dev);
+
+	nr = adapter->nr;
+
+	device_unregister(&adapter->dev);
+
+	/* free bus id */
+	mutex_lock(&core_lock);
+	idr_remove(&peci_adapter_idr, nr);
+	mutex_unlock(&core_lock);
+}
+EXPORT_SYMBOL_GPL(peci_del_adapter);
+
+/**
+ * A peci_driver is used with one or more peci_client (device) nodes to access
+ * peci clients, on a bus instance associated with some peci_adapter.
+ */
+int peci_register_driver(struct module *owner, struct peci_driver *driver)
+{
+	int rc;
+
+	/* Can't register until after driver model init */
+	if (WARN_ON(!is_registered))
+		return -EAGAIN;
+
+	/* add the driver to the list of peci drivers in the driver core */
+	driver->driver.owner = owner;
+	driver->driver.bus = &peci_bus_type;
+
+	/**
+	 * When registration returns, the driver core
+	 * will have called probe() for all matching-but-unbound devices.
+	 */
+	rc = driver_register(&driver->driver);
+	if (rc)
+		return rc;
+
+	pr_debug("driver [%s] registered\n", driver->driver.name);
+
+	return 0;
+}
+EXPORT_SYMBOL_GPL(peci_register_driver);
+
+void peci_del_driver(struct peci_driver *driver)
+{
+	driver_unregister(&driver->driver);
+	pr_debug("driver [%s] unregistered\n", driver->driver.name);
+}
+EXPORT_SYMBOL_GPL(peci_del_driver);
+
+static int __init peci_init(void)
+{
+	int ret;
+
+	ret = bus_register(&peci_bus_type);
+	if (ret < 0) {
+		pr_err("peci: Failed to register PECI bus type!\n");
+		return ret;
+	}
+
+	ret = alloc_chrdev_region(&peci_devt, 0, PECI_CDEV_MAX, "peci");
+	if (ret < 0) {
+		pr_err("peci: Failed to allocate chr dev region!\n");
+		bus_unregister(&peci_bus_type);
+		return ret;
+	}
+
+	crc8_populate_msb(peci_crc8_table, PECI_CRC8_POLYNOMIAL);
+
+	if (IS_ENABLED(CONFIG_OF_DYNAMIC))
+		WARN_ON(of_reconfig_notifier_register(&peci_of_notifier));
+
+	is_registered = true;
+
+	return 0;
+}
+
+static void __exit peci_exit(void)
+{
+	if (IS_ENABLED(CONFIG_OF_DYNAMIC))
+		WARN_ON(of_reconfig_notifier_unregister(&peci_of_notifier));
+
+	unregister_chrdev_region(peci_devt, PECI_CDEV_MAX);
+	bus_unregister(&peci_bus_type);
+}
+
+postcore_initcall(peci_init);
+module_exit(peci_exit);
+
+MODULE_AUTHOR("Jason M Biils <jason.m.bills@xxxxxxxxxxxxxxx>");
+MODULE_AUTHOR("Jae Hyun Yoo <jae.hyun.yoo@xxxxxxxxxxxxxxx>");
+MODULE_DESCRIPTION("PECI bus core module");
+MODULE_LICENSE("GPL v2");
diff --git a/include/linux/peci.h b/include/linux/peci.h
new file mode 100644
index 000000000000..425c9cdab6dc
--- /dev/null
+++ b/include/linux/peci.h
@@ -0,0 +1,104 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef __LINUX_PECI_H
+#define __LINUX_PECI_H
+
+#include <linux/cdev.h>
+#include <linux/device.h>
+#include <linux/peci-ioctl.h>
+#include <linux/rtmutex.h>
+
+#define PECI_NAME_SIZE   32
+
+struct peci_board_info {
+	char			type[PECI_NAME_SIZE];
+	unsigned short		addr;	/* CPU client address */
+	struct device_node	*of_node;
+};
+
+struct peci_adapter {
+	struct module		*owner;
+	struct rt_mutex		bus_lock;
+	struct device		dev;
+	struct cdev		cdev;
+	int			nr;
+	char			name[PECI_NAME_SIZE];
+	struct mutex		userspace_clients_lock; /* clients list mutex */
+	struct list_head	userspace_clients;
+	int			(*xfer)(struct peci_adapter *adapter,
+					struct peci_xfer_msg *msg);
+	uint			cmd_mask;
+};
+
+static inline struct peci_adapter *to_peci_adapter(void *d)
+{
+	return container_of(d, struct peci_adapter, dev);
+}
+
+static inline void *peci_get_adapdata(const struct peci_adapter *adapter)
+{
+	return dev_get_drvdata(&adapter->dev);
+}
+
+static inline void peci_set_adapdata(struct peci_adapter *adapter, void *data)
+{
+	dev_set_drvdata(&adapter->dev, data);
+}
+
+struct peci_client {
+	struct device		dev;		/* the device structure */
+	struct peci_adapter	*adapter;	/* the adapter we sit on */
+	u8			addr;		/* CPU client address */
+	char			name[PECI_NAME_SIZE];
+	struct list_head	detected;
+};
+
+static inline struct peci_client *to_peci_client(void *d)
+{
+	return container_of(d, struct peci_client, dev);
+}
+
+struct peci_device_id {
+	char		name[PECI_NAME_SIZE];
+	unsigned long	driver_data;	/* Data private to the driver */
+};
+
+struct peci_driver {
+	int				(*probe)(struct peci_client *client);
+	int				(*remove)(struct peci_client *client);
+	void				(*shutdown)(struct peci_client *client);
+	struct device_driver		driver;
+	const struct peci_device_id	*id_table;
+};
+
+static inline struct peci_driver *to_peci_driver(void *d)
+{
+	return container_of(d, struct peci_driver, driver);
+}
+
+/**
+ * module_peci_driver() - Helper macro for registering a modular PECI driver
+ * @__peci_driver: peci_driver struct
+ *
+ * Helper macro for PECI drivers which do not do anything special in module
+ * init/exit. This eliminates a lot of boilerplate. Each module may only
+ * use this macro once, and calling it replaces module_init() and module_exit()
+ */
+#define module_peci_driver(__peci_driver) \
+	module_driver(__peci_driver, peci_add_driver, peci_del_driver)
+
+/* use a define to avoid include chaining to get THIS_MODULE */
+#define peci_add_driver(driver) peci_register_driver(THIS_MODULE, driver)
+
+int  peci_register_driver(struct module *owner, struct peci_driver *drv);
+void peci_del_driver(struct peci_driver *driver);
+struct peci_client *peci_verify_client(struct device *dev);
+struct peci_adapter *peci_alloc_adapter(struct device *dev, unsigned int size);
+int  peci_add_adapter(struct peci_adapter *adapter);
+void peci_del_adapter(struct peci_adapter *adapter);
+struct peci_adapter *peci_verify_adapter(struct device *dev);
+int  peci_command(struct peci_adapter *adpater, enum peci_cmd cmd, void *vmsg);
+int  peci_get_cpu_id(struct peci_adapter *adapter, u8 addr, u32 *cpu_id);
+
+#endif /* __LINUX_PECI_H */
diff --git a/include/uapi/linux/peci-ioctl.h b/include/uapi/linux/peci-ioctl.h
new file mode 100644
index 000000000000..b30d797c3b6e
--- /dev/null
+++ b/include/uapi/linux/peci-ioctl.h
@@ -0,0 +1,265 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/* Copyright (c) 2018 Intel Corporation */
+
+#ifndef __PECI_IOCTL_H
+#define __PECI_IOCTL_H
+
+#include <linux/ioctl.h>
+#include <linux/types.h>
+
+/* Base Address of 48d */
+#define PECI_BASE_ADDR  0x30  /* The PECI client's default address of 0x30 */
+#define PECI_OFFSET_MAX 8     /* Max numver of CPU clients */
+
+/* PCI Access */
+#define MAX_PCI_READ_LEN 24   /* Number of bytes of the PCI Space read */
+
+#define PCI_BUS0_CPU0      0x00
+#define PCI_BUS0_CPU1      0x80
+#define PCI_CPUBUSNO_BUS   0x00
+#define PCI_CPUBUSNO_DEV   0x08
+#define PCI_CPUBUSNO_FUNC  0x02
+#define PCI_CPUBUSNO       0xcc
+#define PCI_CPUBUSNO_1     0xd0
+#define PCI_CPUBUSNO_VALID 0xd4
+
+/* Package Identifier Read Parameter Value */
+#define PKG_ID_CPU_ID               0x0000  /* CPUID Info */
+#define PKG_ID_PLATFORM_ID          0x0001  /* Platform ID */
+#define PKG_ID_UNCORE_ID            0x0002  /* Uncore Device ID */
+#define PKG_ID_MAX_THREAD_ID        0x0003  /* Max Thread ID */
+#define PKG_ID_MICROCODE_REV        0x0004  /* CPU Microcode Update Revision */
+#define PKG_ID_MACHINE_CHECK_STATUS 0x0005  /* Machine Check Status */
+
+/* RdPkgConfig Index */
+#define MBX_INDEX_CPU_ID            0   /* Package Identifier Read */
+#define MBX_INDEX_VR_DEBUG          1   /* VR Debug */
+#define MBX_INDEX_PKG_TEMP_READ     2   /* Package Temperature Read */
+#define MBX_INDEX_ENERGY_COUNTER    3   /* Energy counter */
+#define MBX_INDEX_ENERGY_STATUS     4   /* DDR Energy Status */
+#define MBX_INDEX_WAKE_MODE_BIT     5   /* "Wake on PECI" Mode bit */
+#define MBX_INDEX_EPI               6   /* Efficient Performance Indication */
+#define MBX_INDEX_PKG_RAPL_PERF     8   /* Pkg RAPL Performance Status Read */
+#define MBX_INDEX_PER_CORE_DTS_TEMP 9   /* Per Core DTS Temperature Read */
+#define MBX_INDEX_DTS_MARGIN        10  /* DTS thermal margin */
+#define MBX_INDEX_SKT_PWR_THRTL_DUR 11  /* Socket Power Throttled Duration */
+#define MBX_INDEX_CFG_TDP_CONTROL   12  /* TDP Config Control */
+#define MBX_INDEX_CFG_TDP_LEVELS    13  /* TDP Config Levels */
+#define MBX_INDEX_DDR_DIMM_TEMP     14  /* DDR DIMM Temperature */
+#define MBX_INDEX_CFG_ICCMAX        15  /* Configurable ICCMAX */
+#define MBX_INDEX_TEMP_TARGET       16  /* Temperature Target Read */
+#define MBX_INDEX_CURR_CFG_LIMIT    17  /* Current Config Limit */
+#define MBX_INDEX_DIMM_TEMP_READ    20  /* Package Thermal Status Read */
+#define MBX_INDEX_DRAM_IMC_TMP_READ 22  /* DRAM IMC Temperature Read */
+#define MBX_INDEX_DDR_CH_THERM_STAT 23  /* DDR Channel Thermal Status */
+#define MBX_INDEX_PKG_POWER_LIMIT1  26  /* Package Power Limit1 */
+#define MBX_INDEX_PKG_POWER_LIMIT2  27  /* Package Power Limit2 */
+#define MBX_INDEX_TDP               28  /* Thermal design power minimum */
+#define MBX_INDEX_TDP_HIGH          29  /* Thermal design power maximum */
+#define MBX_INDEX_TDP_UNITS         30  /* Units for power/energy registers */
+#define MBX_INDEX_RUN_TIME          31  /* Accumulated Run Time */
+#define MBX_INDEX_CONSTRAINED_TIME  32  /* Thermally Constrained Time Read */
+#define MBX_INDEX_TURBO_RATIO       33  /* Turbo Activation Ratio */
+#define MBX_INDEX_DDR_RAPL_PL1      34  /* DDR RAPL PL1 */
+#define MBX_INDEX_DDR_PWR_INFO_HIGH 35  /* DRAM Power Info Read (high) */
+#define MBX_INDEX_DDR_PWR_INFO_LOW  36  /* DRAM Power Info Read (low) */
+#define MBX_INDEX_DDR_RAPL_PL2      37  /* DDR RAPL PL2 */
+#define MBX_INDEX_DDR_RAPL_STATUS   38  /* DDR RAPL Performance Status */
+#define MBX_INDEX_DDR_HOT_ABSOLUTE  43  /* DDR Hottest Dimm Absolute Temp */
+#define MBX_INDEX_DDR_HOT_RELATIVE  44  /* DDR Hottest Dimm Relative Temp */
+#define MBX_INDEX_DDR_THROTTLE_TIME 45  /* DDR Throttle Time */
+#define MBX_INDEX_DDR_THERM_STATUS  46  /* DDR Thermal Status */
+#define MBX_INDEX_TIME_AVG_TEMP     47  /* Package time-averaged temperature */
+#define MBX_INDEX_TURBO_RATIO_LIMIT 49  /* Turbo Ratio Limit Read */
+#define MBX_INDEX_HWP_AUTO_OOB      53  /* HWP Autonomous Out-of-band */
+#define MBX_INDEX_DDR_WARM_BUDGET   55  /* DDR Warm Power Budget */
+#define MBX_INDEX_DDR_HOT_BUDGET    56  /* DDR Hot Power Budget */
+#define MBX_INDEX_PKG_PSYS_PWR_LIM3 57  /* Package/Psys Power Limit3 */
+#define MBX_INDEX_PKG_PSYS_PWR_LIM1 58  /* Package/Psys Power Limit1 */
+#define MBX_INDEX_PKG_PSYS_PWR_LIM2 59  /* Package/Psys Power Limit2 */
+#define MBX_INDEX_PKG_PSYS_PWR_LIM4 60  /* Package/Psys Power Limit4 */
+#define MBX_INDEX_PERF_LIMIT_REASON 65  /* Performance Limit Reasons */
+
+/* WrPkgConfig Index */
+#define MBX_INDEX_DIMM_AMBIENT      19
+#define MBX_INDEX_DIMM_TEMP         24
+
+/* Device Specific Completion Code (CC) Definition */
+#define DEV_PECI_CC_SUCCESS          0x40
+#define DEV_PECI_CC_TIMEOUT          0x80
+#define DEV_PECI_CC_OUT_OF_RESOURCE  0x81
+#define DEV_PECI_CC_UNAVAIL_RESOURCE 0x82
+#define DEV_PECI_CC_INVALID_REQ      0x90
+
+/* Completion Code mask to check retry needs */
+#define DEV_PECI_CC_RETRY_CHECK_MASK 0xf0
+#define DEV_PECI_CC_NEED_RETRY       0x80
+
+/* Skylake EDS says to retry for 250ms */
+#define DEV_PECI_RETRY_TIME_MS       250
+#define DEV_PECI_RETRY_INTERVAL_USEC 10000
+#define DEV_PECI_RETRY_BIT           0x01
+
+#define GET_TEMP_WR_LEN   1
+#define GET_TEMP_RD_LEN   2
+#define GET_TEMP_PECI_CMD 0x01
+
+#define GET_DIB_WR_LEN   1
+#define GET_DIB_RD_LEN   8
+#define GET_DIB_PECI_CMD 0xf7
+
+#define RDPKGCFG_WRITE_LEN     5
+#define RDPKGCFG_READ_LEN_BASE 1
+#define RDPKGCFG_PECI_CMD      0xa1
+
+#define WRPKGCFG_WRITE_LEN_BASE 6
+#define WRPKGCFG_READ_LEN       1
+#define WRPKGCFG_PECI_CMD       0xa5
+
+#define RDIAMSR_WRITE_LEN 5
+#define RDIAMSR_READ_LEN  9
+#define RDIAMSR_PECI_CMD  0xb1
+
+#define WRIAMSR_PECI_CMD  0xb5
+
+#define RDPCICFG_WRITE_LEN 6
+#define RDPCICFG_READ_LEN  5
+#define RDPCICFG_PECI_CMD  0x61
+
+#define WRPCICFG_PECI_CMD  0x65
+
+#define RDPCICFGLOCAL_WRITE_LEN     5
+#define RDPCICFGLOCAL_READ_LEN_BASE 1
+#define RDPCICFGLOCAL_PECI_CMD      0xe1
+
+#define WRPCICFGLOCAL_WRITE_LEN_BASE 6
+#define WRPCICFGLOCAL_READ_LEN       1
+#define WRPCICFGLOCAL_PECI_CMD       0xe5
+
+#define PECI_BUFFER_SIZE 32
+
+enum peci_cmd {
+	PECI_CMD_XFER = 0,
+	PECI_CMD_PING,
+	PECI_CMD_GET_DIB,
+	PECI_CMD_GET_TEMP,
+	PECI_CMD_RD_PKG_CFG,
+	PECI_CMD_WR_PKG_CFG,
+	PECI_CMD_RD_IA_MSR,
+	PECI_CMD_WR_IA_MSR,
+	PECI_CMD_RD_PCI_CFG,
+	PECI_CMD_WR_PCI_CFG,
+	PECI_CMD_RD_PCI_CFG_LOCAL,
+	PECI_CMD_WR_PCI_CFG_LOCAL,
+	PECI_CMD_MAX
+};
+
+struct peci_xfer_msg {
+	__u8 addr;
+	__u8 tx_len;
+	__u8 rx_len;
+	__u8 tx_buf[PECI_BUFFER_SIZE];
+	__u8 rx_buf[PECI_BUFFER_SIZE];
+} __attribute__((__packed__));
+
+struct peci_ping_msg {
+	__u8 addr;
+} __attribute__((__packed__));
+
+struct peci_get_dib_msg {
+	__u8  addr;
+	__u32 dib;
+} __attribute__((__packed__));
+
+struct peci_get_temp_msg {
+	__u8  addr;
+	__s16 temp_raw;
+} __attribute__((__packed__));
+
+struct peci_rd_pkg_cfg_msg {
+	__u8  addr;
+	__u8  index;
+	__u16 param;
+	__u8  rx_len;
+	__u8  pkg_config[4];
+} __attribute__((__packed__));
+
+struct peci_wr_pkg_cfg_msg {
+	__u8  addr;
+	__u8  index;
+	__u16 param;
+	__u8  tx_len;
+	__u32 value;
+} __attribute__((__packed__));
+
+struct peci_rd_ia_msr_msg {
+	__u8  addr;
+	__u8  thread_id;
+	__u16 address;
+	__u64 value;
+} __attribute__((__packed__));
+
+struct peci_rd_pci_cfg_msg {
+	__u8  addr;
+	__u8  bus;
+	__u8  device;
+	__u8  function;
+	__u16 reg;
+	__u8  pci_config[4];
+} __attribute__((__packed__));
+
+struct peci_rd_pci_cfg_local_msg {
+	__u8  addr;
+	__u8  bus;
+	__u8  device;
+	__u8  function;
+	__u16 reg;
+	__u8  rx_len;
+	__u8  pci_config[4];
+} __attribute__((__packed__));
+
+struct peci_wr_pci_cfg_local_msg {
+	__u8  addr;
+	__u8  bus;
+	__u8  device;
+	__u8  function;
+	__u16 reg;
+	__u8  tx_len;
+	__u32 value;
+} __attribute__((__packed__));
+
+#define PECI_IOC_BASE  0xb7
+
+#define PECI_IOC_XFER \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_XFER, struct peci_xfer_msg)
+
+#define PECI_IOC_PING \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_PING, struct peci_ping_msg)
+
+#define PECI_IOC_GET_DIB \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_GET_DIB, struct peci_get_dib_msg)
+
+#define PECI_IOC_GET_TEMP \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_GET_TEMP, struct peci_get_temp_msg)
+
+#define PECI_IOC_RD_PKG_CFG \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_RD_PKG_CFG, struct peci_rd_pkg_cfg_msg)
+
+#define PECI_IOC_WR_PKG_CFG \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_WR_PKG_CFG, struct peci_wr_pkg_cfg_msg)
+
+#define PECI_IOC_RD_IA_MSR \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_RD_IA_MSR, struct peci_rd_ia_msr_msg)
+
+#define PECI_IOC_RD_PCI_CFG \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_RD_PCI_CFG, struct peci_rd_pci_cfg_msg)
+
+#define PECI_IOC_RD_PCI_CFG_LOCAL \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_RD_PCI_CFG_LOCAL, \
+	      struct peci_rd_pci_cfg_local_msg)
+
+#define PECI_IOC_WR_PCI_CFG_LOCAL \
+	_IOWR(PECI_IOC_BASE, PECI_CMD_WR_PCI_CFG_LOCAL, \
+	      struct peci_wr_pci_cfg_local_msg)
+
+#endif /* __PECI_IOCTL_H */
-- 
2.18.0