x86/kprobes: Fix crash when probing CS CALL instructionsgrafted

When using eBPF to probe CS CALL instructions within a function,
a crash can be triggered.

The eBPF tool probes offset 257 of the __hrtimer_run_queues()
function:

<__hrtimer_run_queues+249>:  nopl   0x0(%rax,%rax,1)
<__hrtimer_run_queues+254>:  mov    %r14,%rdi
<__hrtimer_run_queues+257>:  cs call <__x86_indirect_thunk_r12>
<__hrtimer_run_queues+263>:  mov    %eax,%r12d
<__hrtimer_run_queues+266>:  xchg   %ax,%ax
<__hrtimer_run_queues+268>:  mov    %r13,%rdi

Which triggers this crash:

  BUG: unable to handle page fault for address: 00000000000f41c9
  #PF: supervisor write access in kernel mode
  #PF: error_code(0x0002) - not-present page
  PGD 0 P4D 0
  Oops: 0002 [#1] SMP NOPTI
  CPU: 1 PID: 0 Comm: swapper/1 Kdump: loaded Tainted: P
  RIP: 0010:__hrtimer_run_queues+0x106/0x230

Note that __hrtimer_run_queues+0x106 is __hrtimer_run_queues+262, which is
at the 6th byte of the above CS CALL instruction. Since the CS CALL
instruction occupies 6 bytes, the exception occurred in the middle of that
call instruction.

The root cause is that when using eBPF tools to probe in the middle of a
function, a kprobe with INT3 is used as the underlying implementation.

During single-step emulation of the original CALL instruction,
int3_emulate_call() assumes that the probed CALL instruction is 5 bytes
long. However, the actual CS-prefixed CALL instruction occupies 6 bytes,
so it constructs an incorrect exception return address. When the CPU
returns from the kprobe handler, the next instruction to be executed is at
the address of the last byte of that CS CALL instruction. Coincidentally,
starting from that address, the CPU fetches and decodes a completely
different instruction, which ultimately triggers a kernel crash.

Fix the issue by using the actual instruction length obtained from
the instruction decoder when constructing the exception return
address, rather than relying on the hardcoded CALL_INSN_SIZE macro.

[ mingo: Refined the changelog ]

Fixes: 6256e668b7af ("x86/kprobes: Use int3 instead of debug trap for single-step")
Suggested-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Signed-off-by: Jinke Han <jinkehan@didiglobal.com>
Signed-off-by: Ingo Molnar <mingo@kernel.org>
Reviewed-by: Masami Hiramatsu (Google) <mhiramat@kernel.org>
Acked-by: Yafang Shao <laoar.shao@gmail.com>
Acked-by: Borislav Petkov <bp@alien8.de>
Cc: Peter Zijlstra <peterz@infradead.org>
Link: https://patch.msgid.link/20260908073742.GA10517@didi-ThinkCentre-M920t-N000

12 files changed, 2508 insertions, 0 deletions

diff --git a/drivers/peci/Kconfig b/drivers/peci/Kconfig
new file mode 100644
index 000000000..89872ad83
--- /dev/null
+++ b/drivers/peci/Kconfig
@@ -0,0 +1,36 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+menuconfig PECI
+	tristate "PECI support"
+	help
+	  The Platform Environment Control Interface (PECI) is an interface
+	  that provides a communication channel to Intel processors and
+	  chipset components from external monitoring or control devices.
+
+	  If you are building a Baseboard Management Controller (BMC) kernel
+	  for Intel platform say Y here and also to the specific driver for
+	  your adapter(s) below. If unsure say N.
+
+	  This support is also available as a module. If so, the module
+	  will be called peci.
+
+if PECI
+
+config PECI_CPU
+	tristate "PECI CPU"
+	select AUXILIARY_BUS
+	help
+	  This option enables peci-cpu driver for Intel processors. It is
+	  responsible for creating auxiliary devices that can subsequently
+	  be used by other drivers in order to perform various
+	  functionalities such as e.g. temperature monitoring.
+
+	  Additional drivers must be enabled in order to use the functionality
+	  of the device.
+
+	  This driver can also be built as a module. If so, the module
+	  will be called peci-cpu.
+
+source "drivers/peci/controller/Kconfig"
+
+endif # PECI
diff --git a/drivers/peci/Makefile b/drivers/peci/Makefile
new file mode 100644
index 000000000..7de18137e
--- /dev/null
+++ b/drivers/peci/Makefile
@@ -0,0 +1,10 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+# Core functionality
+peci-y := core.o request.o device.o sysfs.o
+obj-$(CONFIG_PECI) += peci.o
+peci-cpu-y := cpu.o
+obj-$(CONFIG_PECI_CPU) += peci-cpu.o
+
+# Hardware specific bus drivers
+obj-y += controller/
diff --git a/drivers/peci/controller/Kconfig b/drivers/peci/controller/Kconfig
new file mode 100644
index 000000000..4f9c245ad
--- /dev/null
+++ b/drivers/peci/controller/Kconfig
@@ -0,0 +1,34 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+config PECI_ASPEED
+	tristate "ASPEED PECI support"
+	depends on ARCH_ASPEED || COMPILE_TEST
+	depends on OF
+	depends on HAS_IOMEM
+	depends on COMMON_CLK
+	help
+	  This option enables PECI controller driver for ASPEED AST2400,
+	  AST2500 and AST2600 SoCs. It allows BMC to discover devices
+	  connected to it, and communicate with them using PECI protocol.
+
+	  Say Y here if your system runs on ASPEED SoC and you are using it
+	  as BMC for Intel platform.
+
+	  This driver can also be built as a module. If so, the module will
+	  be called peci-aspeed.
+
+config PECI_NPCM
+	tristate "Nuvoton NPCM PECI support"
+	depends on ARCH_NPCM || COMPILE_TEST
+	depends on OF
+	select REGMAP_MMIO
+	help
+	  This option enables PECI controller driver for Nuvoton NPCM7XX
+	  and NPCM8XX SoCs. It allows BMC to discover devices connected
+	  to it and communicate with them using PECI protocol.
+
+	  Say Y here if you want support for the Platform Environment Control
+	  Interface (PECI) bus adapter driver on the Nuvoton NPCM SoCs.
+
+	  This support is also available as a module. If so, the module
+	  will be called peci-npcm.
diff --git a/drivers/peci/controller/Makefile b/drivers/peci/controller/Makefile
new file mode 100644
index 000000000..e247449bb
--- /dev/null
+++ b/drivers/peci/controller/Makefile
@@ -0,0 +1,4 @@
+# SPDX-License-Identifier: GPL-2.0-only
+
+obj-$(CONFIG_PECI_ASPEED)	+= peci-aspeed.o
+obj-$(CONFIG_PECI_NPCM)		+= peci-npcm.o
diff --git a/drivers/peci/controller/peci-aspeed.c b/drivers/peci/controller/peci-aspeed.c
new file mode 100644
index 000000000..a0c99ecf7
--- /dev/null
+++ b/drivers/peci/controller/peci-aspeed.c
@@ -0,0 +1,602 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2012-2017 ASPEED Technology Inc.
+// Copyright (c) 2018-2021 Intel Corporation
+
+#include <linux/unaligned.h>
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/clkdev.h>
+#include <linux/clk-provider.h>
+#include <linux/delay.h>
+#include <linux/interrupt.h>
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/jiffies.h>
+#include <linux/math.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/peci.h>
+#include <linux/platform_device.h>
+#include <linux/reset.h>
+
+/* ASPEED PECI Registers */
+/* Control Register */
+#define ASPEED_PECI_CTRL			0x00
+#define   ASPEED_PECI_CTRL_SAMPLING_MASK	GENMASK(19, 16)
+#define   ASPEED_PECI_CTRL_RD_MODE_MASK		GENMASK(13, 12)
+#define     ASPEED_PECI_CTRL_RD_MODE_DBG	BIT(13)
+#define     ASPEED_PECI_CTRL_RD_MODE_COUNT	BIT(12)
+#define   ASPEED_PECI_CTRL_CLK_SRC_HCLK		BIT(11)
+#define   ASPEED_PECI_CTRL_CLK_DIV_MASK		GENMASK(10, 8)
+#define   ASPEED_PECI_CTRL_INVERT_OUT		BIT(7)
+#define   ASPEED_PECI_CTRL_INVERT_IN		BIT(6)
+#define   ASPEED_PECI_CTRL_BUS_CONTENTION_EN	BIT(5)
+#define   ASPEED_PECI_CTRL_PECI_EN		BIT(4)
+#define   ASPEED_PECI_CTRL_PECI_CLK_EN		BIT(0)
+
+/* Timing Negotiation Register */
+#define ASPEED_PECI_TIMING_NEGOTIATION		0x04
+#define   ASPEED_PECI_T_NEGO_MSG_MASK		GENMASK(15, 8)
+#define   ASPEED_PECI_T_NEGO_ADDR_MASK		GENMASK(7, 0)
+
+/* Command Register */
+#define ASPEED_PECI_CMD				0x08
+#define   ASPEED_PECI_CMD_PIN_MONITORING	BIT(31)
+#define   ASPEED_PECI_CMD_STS_MASK		GENMASK(27, 24)
+#define     ASPEED_PECI_CMD_STS_ADDR_T_NEGO	0x3
+#define   ASPEED_PECI_CMD_IDLE_MASK		\
+	  (ASPEED_PECI_CMD_STS_MASK | ASPEED_PECI_CMD_PIN_MONITORING)
+#define   ASPEED_PECI_CMD_FIRE			BIT(0)
+
+/* Read/Write Length Register */
+#define ASPEED_PECI_RW_LENGTH			0x0c
+#define   ASPEED_PECI_AW_FCS_EN			BIT(31)
+#define   ASPEED_PECI_RD_LEN_MASK		GENMASK(23, 16)
+#define   ASPEED_PECI_WR_LEN_MASK		GENMASK(15, 8)
+#define   ASPEED_PECI_TARGET_ADDR_MASK		GENMASK(7, 0)
+
+/* Expected FCS Data Register */
+#define ASPEED_PECI_EXPECTED_FCS		0x10
+#define   ASPEED_PECI_EXPECTED_RD_FCS_MASK	GENMASK(23, 16)
+#define   ASPEED_PECI_EXPECTED_AW_FCS_AUTO_MASK	GENMASK(15, 8)
+#define   ASPEED_PECI_EXPECTED_WR_FCS_MASK	GENMASK(7, 0)
+
+/* Captured FCS Data Register */
+#define ASPEED_PECI_CAPTURED_FCS		0x14
+#define   ASPEED_PECI_CAPTURED_RD_FCS_MASK	GENMASK(23, 16)
+#define   ASPEED_PECI_CAPTURED_WR_FCS_MASK	GENMASK(7, 0)
+
+/* Interrupt Register */
+#define ASPEED_PECI_INT_CTRL			0x18
+#define   ASPEED_PECI_TIMING_NEGO_SEL_MASK	GENMASK(31, 30)
+#define     ASPEED_PECI_1ST_BIT_OF_ADDR_NEGO	0
+#define     ASPEED_PECI_2ND_BIT_OF_ADDR_NEGO	1
+#define     ASPEED_PECI_MESSAGE_NEGO		2
+#define   ASPEED_PECI_INT_MASK			GENMASK(4, 0)
+#define     ASPEED_PECI_INT_BUS_TIMEOUT		BIT(4)
+#define     ASPEED_PECI_INT_BUS_CONTENTION	BIT(3)
+#define     ASPEED_PECI_INT_WR_FCS_BAD		BIT(2)
+#define     ASPEED_PECI_INT_WR_FCS_ABORT	BIT(1)
+#define     ASPEED_PECI_INT_CMD_DONE		BIT(0)
+
+/* Interrupt Status Register */
+#define ASPEED_PECI_INT_STS			0x1c
+#define   ASPEED_PECI_INT_TIMING_RESULT_MASK	GENMASK(29, 16)
+	  /* bits[4..0]: Same bit fields in the 'Interrupt Register' */
+
+/* Rx/Tx Data Buffer Registers */
+#define ASPEED_PECI_WR_DATA0			0x20
+#define ASPEED_PECI_WR_DATA1			0x24
+#define ASPEED_PECI_WR_DATA2			0x28
+#define ASPEED_PECI_WR_DATA3			0x2c
+#define ASPEED_PECI_RD_DATA0			0x30
+#define ASPEED_PECI_RD_DATA1			0x34
+#define ASPEED_PECI_RD_DATA2			0x38
+#define ASPEED_PECI_RD_DATA3			0x3c
+#define ASPEED_PECI_WR_DATA4			0x40
+#define ASPEED_PECI_WR_DATA5			0x44
+#define ASPEED_PECI_WR_DATA6			0x48
+#define ASPEED_PECI_WR_DATA7			0x4c
+#define ASPEED_PECI_RD_DATA4			0x50
+#define ASPEED_PECI_RD_DATA5			0x54
+#define ASPEED_PECI_RD_DATA6			0x58
+#define ASPEED_PECI_RD_DATA7			0x5c
+#define   ASPEED_PECI_DATA_BUF_SIZE_MAX		32
+
+/* Timing Negotiation */
+#define ASPEED_PECI_CLK_FREQUENCY_MIN		2000
+#define ASPEED_PECI_CLK_FREQUENCY_DEFAULT	1000000
+#define ASPEED_PECI_CLK_FREQUENCY_MAX		2000000
+#define ASPEED_PECI_RD_SAMPLING_POINT_DEFAULT	8
+/* Timeout */
+#define ASPEED_PECI_IDLE_CHECK_TIMEOUT_US	(50 * USEC_PER_MSEC)
+#define ASPEED_PECI_IDLE_CHECK_INTERVAL_US	(10 * USEC_PER_MSEC)
+#define ASPEED_PECI_CMD_TIMEOUT_MS_DEFAULT	1000
+#define ASPEED_PECI_CMD_TIMEOUT_MS_MAX		1000
+
+#define ASPEED_PECI_CLK_DIV1(msg_timing) (4 * (msg_timing) + 1)
+#define ASPEED_PECI_CLK_DIV2(clk_div_exp) BIT(clk_div_exp)
+#define ASPEED_PECI_CLK_DIV(msg_timing, clk_div_exp) \
+	(4 * ASPEED_PECI_CLK_DIV1(msg_timing) * ASPEED_PECI_CLK_DIV2(clk_div_exp))
+
+struct aspeed_peci {
+	struct peci_controller *controller;
+	struct device *dev;
+	void __iomem *base;
+	struct reset_control *rst;
+	int irq;
+	spinlock_t lock; /* to sync completion status handling */
+	struct completion xfer_complete;
+	struct clk *clk;
+	u32 clk_frequency;
+	u32 status;
+	u32 cmd_timeout_ms;
+};
+
+struct clk_aspeed_peci {
+	struct clk_hw hw;
+	struct aspeed_peci *aspeed_peci;
+};
+
+static void aspeed_peci_controller_enable(struct aspeed_peci *priv)
+{
+	u32 val = readl(priv->base + ASPEED_PECI_CTRL);
+
+	val |= ASPEED_PECI_CTRL_PECI_CLK_EN;
+	val |= ASPEED_PECI_CTRL_PECI_EN;
+
+	writel(val, priv->base + ASPEED_PECI_CTRL);
+}
+
+static void aspeed_peci_init_regs(struct aspeed_peci *priv)
+{
+	u32 val;
+
+	/* Clear interrupts */
+	writel(ASPEED_PECI_INT_MASK, priv->base + ASPEED_PECI_INT_STS);
+
+	/* Set timing negotiation mode and enable interrupts */
+	val = FIELD_PREP(ASPEED_PECI_TIMING_NEGO_SEL_MASK, ASPEED_PECI_1ST_BIT_OF_ADDR_NEGO);
+	val |= ASPEED_PECI_INT_MASK;
+	writel(val, priv->base + ASPEED_PECI_INT_CTRL);
+
+	val = FIELD_PREP(ASPEED_PECI_CTRL_SAMPLING_MASK, ASPEED_PECI_RD_SAMPLING_POINT_DEFAULT);
+	writel(val, priv->base + ASPEED_PECI_CTRL);
+}
+
+static int aspeed_peci_check_idle(struct aspeed_peci *priv)
+{
+	u32 cmd_sts = readl(priv->base + ASPEED_PECI_CMD);
+	int ret;
+
+	/*
+	 * Under normal circumstances, we expect to be idle here.
+	 * In case there were any errors/timeouts that led to the situation
+	 * where the hardware is not in idle state - we need to reset and
+	 * reinitialize it to avoid potential controller hang.
+	 */
+	if (FIELD_GET(ASPEED_PECI_CMD_STS_MASK, cmd_sts)) {
+		ret = reset_control_assert(priv->rst);
+		if (ret) {
+			dev_err(priv->dev, "cannot assert reset control\n");
+			return ret;
+		}
+
+		ret = reset_control_deassert(priv->rst);
+		if (ret) {
+			dev_err(priv->dev, "cannot deassert reset control\n");
+			return ret;
+		}
+
+		aspeed_peci_init_regs(priv);
+
+		ret = clk_set_rate(priv->clk, priv->clk_frequency);
+		if (ret < 0) {
+			dev_err(priv->dev, "cannot set clock frequency\n");
+			return ret;
+		}
+
+		aspeed_peci_controller_enable(priv);
+	}
+
+	return readl_poll_timeout(priv->base + ASPEED_PECI_CMD,
+				  cmd_sts,
+				  !(cmd_sts & ASPEED_PECI_CMD_IDLE_MASK),
+				  ASPEED_PECI_IDLE_CHECK_INTERVAL_US,
+				  ASPEED_PECI_IDLE_CHECK_TIMEOUT_US);
+}
+
+static int aspeed_peci_xfer(struct peci_controller *controller,
+			    u8 addr, struct peci_request *req)
+{
+	struct aspeed_peci *priv = dev_get_drvdata(controller->dev.parent);
+	unsigned long timeout = msecs_to_jiffies(priv->cmd_timeout_ms);
+	u32 peci_head;
+	int ret, i;
+
+	if (req->tx.len > ASPEED_PECI_DATA_BUF_SIZE_MAX ||
+	    req->rx.len > ASPEED_PECI_DATA_BUF_SIZE_MAX)
+		return -EINVAL;
+
+	/* Check command sts and bus idle state */
+	ret = aspeed_peci_check_idle(priv);
+	if (ret)
+		return ret; /* -ETIMEDOUT */
+
+	spin_lock_irq(&priv->lock);
+	reinit_completion(&priv->xfer_complete);
+
+	peci_head = FIELD_PREP(ASPEED_PECI_TARGET_ADDR_MASK, addr) |
+		    FIELD_PREP(ASPEED_PECI_WR_LEN_MASK, req->tx.len) |
+		    FIELD_PREP(ASPEED_PECI_RD_LEN_MASK, req->rx.len);
+
+	writel(peci_head, priv->base + ASPEED_PECI_RW_LENGTH);
+
+	for (i = 0; i < req->tx.len; i += 4) {
+		u32 reg = (i < 16 ? ASPEED_PECI_WR_DATA0 : ASPEED_PECI_WR_DATA4) + i % 16;
+
+		writel(get_unaligned_le32(&req->tx.buf[i]), priv->base + reg);
+	}
+
+#if IS_ENABLED(CONFIG_DYNAMIC_DEBUG)
+	dev_dbg(priv->dev, "HEAD : %#08x\n", peci_head);
+	print_hex_dump_bytes("TX : ", DUMP_PREFIX_NONE, req->tx.buf, req->tx.len);
+#endif
+
+	priv->status = 0;
+	writel(ASPEED_PECI_CMD_FIRE, priv->base + ASPEED_PECI_CMD);
+	spin_unlock_irq(&priv->lock);
+
+	ret = wait_for_completion_interruptible_timeout(&priv->xfer_complete, timeout);
+	if (ret < 0)
+		return ret;
+
+	if (ret == 0) {
+		dev_dbg(priv->dev, "timeout waiting for a response\n");
+		return -ETIMEDOUT;
+	}
+
+	spin_lock_irq(&priv->lock);
+
+	if (priv->status != ASPEED_PECI_INT_CMD_DONE) {
+		spin_unlock_irq(&priv->lock);
+		dev_dbg(priv->dev, "no valid response, status: %#02x\n", priv->status);
+		return -EIO;
+	}
+
+	spin_unlock_irq(&priv->lock);
+
+	/*
+	 * We need to use dword reads for register access, make sure that the
+	 * buffer size is multiple of 4-bytes.
+	 */
+	BUILD_BUG_ON(PECI_REQUEST_MAX_BUF_SIZE % 4);
+
+	for (i = 0; i < req->rx.len; i += 4) {
+		u32 reg = (i < 16 ? ASPEED_PECI_RD_DATA0 : ASPEED_PECI_RD_DATA4) + i % 16;
+		u32 rx_data = readl(priv->base + reg);
+
+		put_unaligned_le32(rx_data, &req->rx.buf[i]);
+	}
+
+#if IS_ENABLED(CONFIG_DYNAMIC_DEBUG)
+	print_hex_dump_bytes("RX : ", DUMP_PREFIX_NONE, req->rx.buf, req->rx.len);
+#endif
+	return 0;
+}
+
+static irqreturn_t aspeed_peci_irq_handler(int irq, void *arg)
+{
+	struct aspeed_peci *priv = arg;
+	u32 status;
+
+	spin_lock(&priv->lock);
+	status = readl(priv->base + ASPEED_PECI_INT_STS);
+	writel(status, priv->base + ASPEED_PECI_INT_STS);
+	priv->status |= (status & ASPEED_PECI_INT_MASK);
+
+	/*
+	 * All commands should be ended up with a ASPEED_PECI_INT_CMD_DONE bit
+	 * set even in an error case.
+	 */
+	if (status & ASPEED_PECI_INT_CMD_DONE)
+		complete(&priv->xfer_complete);
+
+	writel(0, priv->base + ASPEED_PECI_CMD);
+
+	spin_unlock(&priv->lock);
+
+	return IRQ_HANDLED;
+}
+
+static void clk_aspeed_peci_find_div_values(unsigned long rate, int *msg_timing, int *clk_div_exp)
+{
+	unsigned long best_diff = ~0ul, diff;
+	int msg_timing_temp, clk_div_exp_temp, i, j;
+
+	for (i = 1; i <= 255; i++)
+		for (j = 0; j < 8; j++) {
+			diff = abs(rate - ASPEED_PECI_CLK_DIV1(i) * ASPEED_PECI_CLK_DIV2(j));
+			if (diff < best_diff) {
+				msg_timing_temp = i;
+				clk_div_exp_temp = j;
+				best_diff = diff;
+			}
+		}
+
+	*msg_timing = msg_timing_temp;
+	*clk_div_exp = clk_div_exp_temp;
+}
+
+static int clk_aspeed_peci_get_div(unsigned long rate, const unsigned long *prate)
+{
+	unsigned long this_rate = *prate / (4 * rate);
+	int msg_timing, clk_div_exp;
+
+	clk_aspeed_peci_find_div_values(this_rate, &msg_timing, &clk_div_exp);
+
+	return ASPEED_PECI_CLK_DIV(msg_timing, clk_div_exp);
+}
+
+static int clk_aspeed_peci_set_rate(struct clk_hw *hw, unsigned long rate,
+				    unsigned long prate)
+{
+	struct clk_aspeed_peci *peci_clk = container_of(hw, struct clk_aspeed_peci, hw);
+	struct aspeed_peci *aspeed_peci = peci_clk->aspeed_peci;
+	unsigned long this_rate = prate / (4 * rate);
+	int clk_div_exp, msg_timing;
+	u32 val;
+
+	clk_aspeed_peci_find_div_values(this_rate, &msg_timing, &clk_div_exp);
+
+	val = readl(aspeed_peci->base + ASPEED_PECI_CTRL);
+	val &= ~ASPEED_PECI_CTRL_CLK_DIV_MASK;
+	val |= FIELD_PREP(ASPEED_PECI_CTRL_CLK_DIV_MASK, clk_div_exp);
+	writel(val, aspeed_peci->base + ASPEED_PECI_CTRL);
+
+	val = FIELD_PREP(ASPEED_PECI_T_NEGO_MSG_MASK, msg_timing);
+	val |= FIELD_PREP(ASPEED_PECI_T_NEGO_ADDR_MASK, msg_timing);
+	writel(val, aspeed_peci->base + ASPEED_PECI_TIMING_NEGOTIATION);
+
+	return 0;
+}
+
+static int clk_aspeed_peci_determine_rate(struct clk_hw *hw,
+					  struct clk_rate_request *req)
+{
+	int div = clk_aspeed_peci_get_div(req->rate, &req->best_parent_rate);
+
+	req->rate = DIV_ROUND_UP_ULL(req->best_parent_rate, div);
+
+	return 0;
+}
+
+static unsigned long clk_aspeed_peci_recalc_rate(struct clk_hw *hw, unsigned long prate)
+{
+	struct clk_aspeed_peci *peci_clk = container_of(hw, struct clk_aspeed_peci, hw);
+	struct aspeed_peci *aspeed_peci = peci_clk->aspeed_peci;
+	int div, msg_timing, addr_timing, clk_div_exp;
+	u32 reg;
+
+	reg = readl(aspeed_peci->base + ASPEED_PECI_TIMING_NEGOTIATION);
+	msg_timing = FIELD_GET(ASPEED_PECI_T_NEGO_MSG_MASK, reg);
+	addr_timing = FIELD_GET(ASPEED_PECI_T_NEGO_ADDR_MASK, reg);
+
+	if (msg_timing != addr_timing)
+		return 0;
+
+	reg = readl(aspeed_peci->base + ASPEED_PECI_CTRL);
+	clk_div_exp = FIELD_GET(ASPEED_PECI_CTRL_CLK_DIV_MASK, reg);
+
+	div = ASPEED_PECI_CLK_DIV(msg_timing, clk_div_exp);
+
+	return DIV_ROUND_UP_ULL(prate, div);
+}
+
+static const struct clk_ops clk_aspeed_peci_ops = {
+	.set_rate = clk_aspeed_peci_set_rate,
+	.determine_rate = clk_aspeed_peci_determine_rate,
+	.recalc_rate = clk_aspeed_peci_recalc_rate,
+};
+
+/*
+ * PECI HW contains a clock divider which is a combination of:
+ *  div0: 4 (fixed divider)
+ *  div1: x + 1
+ *  div2: 1 << y
+ * In other words, out_clk = in_clk / (div0 * div1 * div2)
+ * The resulting frequency is used by PECI Controller to drive the PECI bus to
+ * negotiate optimal transfer rate.
+ */
+static struct clk *devm_aspeed_peci_register_clk_div(struct device *dev, struct clk *parent,
+						     struct aspeed_peci *priv)
+{
+	struct clk_aspeed_peci *peci_clk;
+	struct clk_init_data init;
+	const char *parent_name;
+	char name[32];
+	int ret;
+
+	snprintf(name, sizeof(name), "%s_div", dev_name(dev));
+
+	parent_name = __clk_get_name(parent);
+
+	init.ops = &clk_aspeed_peci_ops;
+	init.name = name;
+	init.parent_names = (const char* []) { parent_name };
+	init.num_parents = 1;
+	init.flags = 0;
+
+	peci_clk = devm_kzalloc(dev, sizeof(struct clk_aspeed_peci), GFP_KERNEL);
+	if (!peci_clk)
+		return ERR_PTR(-ENOMEM);
+
+	peci_clk->hw.init = &init;
+	peci_clk->aspeed_peci = priv;
+
+	ret = devm_clk_hw_register(dev, &peci_clk->hw);
+	if (ret)
+		return ERR_PTR(ret);
+
+	return peci_clk->hw.clk;
+}
+
+static void aspeed_peci_property_sanitize(struct device *dev, const char *propname,
+					  u32 min, u32 max, u32 default_val, u32 *propval)
+{
+	u32 val;
+	int ret;
+
+	ret = device_property_read_u32(dev, propname, &val);
+	if (ret) {
+		val = default_val;
+	} else if (val > max || val < min) {
+		dev_warn(dev, "invalid %s: %u, falling back to: %u\n",
+			 propname, val, default_val);
+
+		val = default_val;
+	}
+
+	*propval = val;
+}
+
+static void aspeed_peci_property_setup(struct aspeed_peci *priv)
+{
+	aspeed_peci_property_sanitize(priv->dev, "clock-frequency",
+				      ASPEED_PECI_CLK_FREQUENCY_MIN, ASPEED_PECI_CLK_FREQUENCY_MAX,
+				      ASPEED_PECI_CLK_FREQUENCY_DEFAULT, &priv->clk_frequency);
+	aspeed_peci_property_sanitize(priv->dev, "cmd-timeout-ms",
+				      1, ASPEED_PECI_CMD_TIMEOUT_MS_MAX,
+				      ASPEED_PECI_CMD_TIMEOUT_MS_DEFAULT, &priv->cmd_timeout_ms);
+}
+
+static const struct peci_controller_ops aspeed_ops = {
+	.xfer = aspeed_peci_xfer,
+};
+
+static void aspeed_peci_reset_control_release(void *data)
+{
+	reset_control_assert(data);
+}
+
+static int devm_aspeed_peci_reset_control_deassert(struct device *dev, struct reset_control *rst)
+{
+	int ret;
+
+	ret = reset_control_deassert(rst);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, aspeed_peci_reset_control_release, rst);
+}
+
+static void aspeed_peci_clk_release(void *data)
+{
+	clk_disable_unprepare(data);
+}
+
+static int devm_aspeed_peci_clk_enable(struct device *dev, struct clk *clk)
+{
+	int ret;
+
+	ret = clk_prepare_enable(clk);
+	if (ret)
+		return ret;
+
+	return devm_add_action_or_reset(dev, aspeed_peci_clk_release, clk);
+}
+
+static int aspeed_peci_probe(struct platform_device *pdev)
+{
+	struct peci_controller *controller;
+	struct aspeed_peci *priv;
+	struct clk *ref_clk;
+	int ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = &pdev->dev;
+	dev_set_drvdata(priv->dev, priv);
+
+	priv->base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(priv->base))
+		return PTR_ERR(priv->base);
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0)
+		return priv->irq;
+
+	ret = devm_request_irq(&pdev->dev, priv->irq, aspeed_peci_irq_handler,
+			       0, "peci-aspeed", priv);
+	if (ret)
+		return ret;
+
+	init_completion(&priv->xfer_complete);
+	spin_lock_init(&priv->lock);
+
+	priv->rst = devm_reset_control_get(&pdev->dev, NULL);
+	if (IS_ERR(priv->rst))
+		return dev_err_probe(priv->dev, PTR_ERR(priv->rst),
+				     "failed to get reset control\n");
+
+	ret = devm_aspeed_peci_reset_control_deassert(priv->dev, priv->rst);
+	if (ret)
+		return dev_err_probe(priv->dev, ret, "cannot deassert reset control\n");
+
+	aspeed_peci_property_setup(priv);
+
+	aspeed_peci_init_regs(priv);
+
+	ref_clk = devm_clk_get(priv->dev, NULL);
+	if (IS_ERR(ref_clk))
+		return dev_err_probe(priv->dev, PTR_ERR(ref_clk), "failed to get ref clock\n");
+
+	priv->clk = devm_aspeed_peci_register_clk_div(priv->dev, ref_clk, priv);
+	if (IS_ERR(priv->clk))
+		return dev_err_probe(priv->dev, PTR_ERR(priv->clk), "cannot register clock\n");
+
+	ret = clk_set_rate(priv->clk, priv->clk_frequency);
+	if (ret < 0)
+		return dev_err_probe(priv->dev, ret, "cannot set clock frequency\n");
+
+	ret = devm_aspeed_peci_clk_enable(priv->dev, priv->clk);
+	if (ret)
+		return dev_err_probe(priv->dev, ret, "failed to enable clock\n");
+
+	aspeed_peci_controller_enable(priv);
+
+	controller = devm_peci_controller_add(priv->dev, &aspeed_ops);
+	if (IS_ERR(controller))
+		return dev_err_probe(priv->dev, PTR_ERR(controller),
+				     "failed to add aspeed peci controller\n");
+
+	priv->controller = controller;
+
+	return 0;
+}
+
+static const struct of_device_id aspeed_peci_of_table[] = {
+	{ .compatible = "aspeed,ast2400-peci", },
+	{ .compatible = "aspeed,ast2500-peci", },
+	{ .compatible = "aspeed,ast2600-peci", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, aspeed_peci_of_table);
+
+static struct platform_driver aspeed_peci_driver = {
+	.probe  = aspeed_peci_probe,
+	.driver = {
+		.name           = "peci-aspeed",
+		.of_match_table = aspeed_peci_of_table,
+	},
+};
+module_platform_driver(aspeed_peci_driver);
+
+MODULE_AUTHOR("Ryan Chen <ryan_chen@aspeedtech.com>");
+MODULE_AUTHOR("Jae Hyun Yoo <jae.hyun.yoo@linux.intel.com>");
+MODULE_DESCRIPTION("ASPEED PECI driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("PECI");
diff --git a/drivers/peci/controller/peci-npcm.c b/drivers/peci/controller/peci-npcm.c
new file mode 100644
index 000000000..931868991
--- /dev/null
+++ b/drivers/peci/controller/peci-npcm.c
@@ -0,0 +1,297 @@
+// SPDX-License-Identifier: GPL-2.0
+// Copyright (c) 2019 Nuvoton Technology corporation
+
+#include <linux/bitfield.h>
+#include <linux/clk.h>
+#include <linux/interrupt.h>
+#include <linux/jiffies.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/peci.h>
+#include <linux/platform_device.h>
+#include <linux/regmap.h>
+#include <linux/reset.h>
+
+/* NPCM GCR module */
+#define NPCM_INTCR3_OFFSET	0x9C
+#define NPCM_INTCR3_PECIVSEL	BIT(19)
+
+/* NPCM PECI Registers */
+#define NPCM_PECI_CTL_STS	0x00
+#define NPCM_PECI_RD_LENGTH	0x04
+#define NPCM_PECI_ADDR		0x08
+#define NPCM_PECI_CMD		0x0C
+#define NPCM_PECI_CTL2		0x10
+#define NPCM_PECI_WR_LENGTH	0x1C
+#define NPCM_PECI_PDDR		0x2C
+#define NPCM_PECI_DAT_INOUT(n)	(0x100 + ((n) * 4))
+
+#define NPCM_PECI_MAX_REG	0x200
+
+/* NPCM_PECI_CTL_STS - 0x00 : Control Register */
+#define NPCM_PECI_CTRL_DONE_INT_EN	BIT(6)
+#define NPCM_PECI_CTRL_ABRT_ERR		BIT(4)
+#define NPCM_PECI_CTRL_CRC_ERR		BIT(3)
+#define NPCM_PECI_CTRL_DONE		BIT(1)
+#define NPCM_PECI_CTRL_START_BUSY	BIT(0)
+
+/* NPCM_PECI_RD_LENGTH - 0x04 : Command Register */
+#define NPCM_PECI_RD_LEN_MASK		GENMASK(6, 0)
+
+/* NPCM_PECI_CMD - 0x10 : Command Register */
+#define NPCM_PECI_CTL2_MASK		GENMASK(7, 6)
+
+/* NPCM_PECI_WR_LENGTH - 0x1C : Command Register */
+#define NPCM_PECI_WR_LEN_MASK		GENMASK(6, 0)
+
+/* NPCM_PECI_PDDR - 0x2C : Command Register */
+#define NPCM_PECI_PDDR_MASK		GENMASK(4, 0)
+
+#define NPCM_PECI_INT_MASK		(NPCM_PECI_CTRL_ABRT_ERR | \
+					 NPCM_PECI_CTRL_CRC_ERR  | \
+					 NPCM_PECI_CTRL_DONE)
+
+#define NPCM_PECI_IDLE_CHECK_TIMEOUT_USEC	(50 * USEC_PER_MSEC)
+#define NPCM_PECI_IDLE_CHECK_INTERVAL_USEC	(10 * USEC_PER_MSEC)
+#define NPCM_PECI_CMD_TIMEOUT_MS_DEFAULT	1000
+#define NPCM_PECI_CMD_TIMEOUT_MS_MAX		60000
+#define NPCM_PECI_HOST_NEG_BIT_RATE_DEFAULT	15
+#define NPCM_PECI_PULL_DOWN_DEFAULT		0
+
+struct npcm_peci {
+	u32			cmd_timeout_ms;
+	struct completion	xfer_complete;
+	struct regmap		*regmap;
+	u32			status;
+	spinlock_t		lock; /* to sync completion status handling */
+	struct peci_controller *controller;
+	struct device		*dev;
+	struct clk		*clk;
+	int			irq;
+};
+
+static int npcm_peci_xfer(struct peci_controller *controller, u8 addr, struct peci_request *req)
+{
+	struct npcm_peci *priv = dev_get_drvdata(controller->dev.parent);
+	unsigned long timeout = msecs_to_jiffies(priv->cmd_timeout_ms);
+	unsigned int msg_rd;
+	u32 cmd_sts;
+	int i, ret;
+
+	/* Check command sts and bus idle state */
+	ret = regmap_read_poll_timeout(priv->regmap, NPCM_PECI_CTL_STS, cmd_sts,
+				       !(cmd_sts & NPCM_PECI_CTRL_START_BUSY),
+				       NPCM_PECI_IDLE_CHECK_INTERVAL_USEC,
+				       NPCM_PECI_IDLE_CHECK_TIMEOUT_USEC);
+	if (ret)
+		return ret; /* -ETIMEDOUT */
+
+	spin_lock_irq(&priv->lock);
+	reinit_completion(&priv->xfer_complete);
+
+	regmap_write(priv->regmap, NPCM_PECI_ADDR, addr);
+	regmap_write(priv->regmap, NPCM_PECI_RD_LENGTH, NPCM_PECI_WR_LEN_MASK & req->rx.len);
+	regmap_write(priv->regmap, NPCM_PECI_WR_LENGTH, NPCM_PECI_WR_LEN_MASK & req->tx.len);
+
+	if (req->tx.len) {
+		regmap_write(priv->regmap, NPCM_PECI_CMD, req->tx.buf[0]);
+
+		for (i = 0; i < (req->tx.len - 1); i++)
+			regmap_write(priv->regmap, NPCM_PECI_DAT_INOUT(i), req->tx.buf[i + 1]);
+	}
+
+#if IS_ENABLED(CONFIG_DYNAMIC_DEBUG)
+	dev_dbg(priv->dev, "addr : %#02x, tx.len : %#02x, rx.len : %#02x\n",
+		addr, req->tx.len, req->rx.len);
+	print_hex_dump_bytes("TX : ", DUMP_PREFIX_NONE, req->tx.buf, req->tx.len);
+#endif
+
+	priv->status = 0;
+	regmap_update_bits(priv->regmap, NPCM_PECI_CTL_STS, NPCM_PECI_CTRL_START_BUSY,
+			   NPCM_PECI_CTRL_START_BUSY);
+
+	spin_unlock_irq(&priv->lock);
+
+	ret = wait_for_completion_interruptible_timeout(&priv->xfer_complete, timeout);
+	if (ret < 0)
+		return ret;
+
+	if (ret == 0) {
+		dev_dbg(priv->dev, "timeout waiting for a response\n");
+		return -ETIMEDOUT;
+	}
+
+	spin_lock_irq(&priv->lock);
+
+	if (priv->status != NPCM_PECI_CTRL_DONE) {
+		spin_unlock_irq(&priv->lock);
+		dev_dbg(priv->dev, "no valid response, status: %#02x\n", priv->status);
+		return -EIO;
+	}
+
+	regmap_write(priv->regmap, NPCM_PECI_CMD, 0);
+
+	for (i = 0; i < req->rx.len; i++) {
+		regmap_read(priv->regmap, NPCM_PECI_DAT_INOUT(i), &msg_rd);
+		req->rx.buf[i] = (u8)msg_rd;
+	}
+
+	spin_unlock_irq(&priv->lock);
+
+#if IS_ENABLED(CONFIG_DYNAMIC_DEBUG)
+	print_hex_dump_bytes("RX : ", DUMP_PREFIX_NONE, req->rx.buf, req->rx.len);
+#endif
+	return 0;
+}
+
+static irqreturn_t npcm_peci_irq_handler(int irq, void *arg)
+{
+	struct npcm_peci *priv = arg;
+	u32 status_ack = 0;
+	u32 status;
+
+	spin_lock(&priv->lock);
+	regmap_read(priv->regmap, NPCM_PECI_CTL_STS, &status);
+	priv->status |= (status & NPCM_PECI_INT_MASK);
+
+	if (status & NPCM_PECI_CTRL_CRC_ERR)
+		status_ack |= NPCM_PECI_CTRL_CRC_ERR;
+
+	if (status & NPCM_PECI_CTRL_ABRT_ERR)
+		status_ack |= NPCM_PECI_CTRL_ABRT_ERR;
+
+	/*
+	 * All commands should be ended up with a NPCM_PECI_CTRL_DONE
+	 * bit set even in an error case.
+	 */
+	if (status & NPCM_PECI_CTRL_DONE) {
+		status_ack |= NPCM_PECI_CTRL_DONE;
+		complete(&priv->xfer_complete);
+	}
+
+	regmap_write_bits(priv->regmap, NPCM_PECI_CTL_STS, NPCM_PECI_INT_MASK, status_ack);
+
+	spin_unlock(&priv->lock);
+	return IRQ_HANDLED;
+}
+
+static int npcm_peci_init_ctrl(struct npcm_peci *priv)
+{
+	u32 cmd_sts;
+	int ret;
+
+	priv->clk = devm_clk_get_enabled(priv->dev, NULL);
+	if (IS_ERR(priv->clk)) {
+		dev_err(priv->dev, "failed to get ref clock\n");
+		return PTR_ERR(priv->clk);
+	}
+
+	ret = device_property_read_u32(priv->dev, "cmd-timeout-ms", &priv->cmd_timeout_ms);
+	if (ret) {
+		priv->cmd_timeout_ms = NPCM_PECI_CMD_TIMEOUT_MS_DEFAULT;
+	} else if (priv->cmd_timeout_ms > NPCM_PECI_CMD_TIMEOUT_MS_MAX ||
+		   priv->cmd_timeout_ms == 0) {
+		dev_warn(priv->dev, "invalid cmd-timeout-ms: %u, falling back to: %u\n",
+			 priv->cmd_timeout_ms, NPCM_PECI_CMD_TIMEOUT_MS_DEFAULT);
+
+		priv->cmd_timeout_ms = NPCM_PECI_CMD_TIMEOUT_MS_DEFAULT;
+	}
+
+	regmap_update_bits(priv->regmap, NPCM_PECI_CTL2, NPCM_PECI_CTL2_MASK,
+			   NPCM_PECI_PULL_DOWN_DEFAULT << 6);
+
+	regmap_update_bits(priv->regmap, NPCM_PECI_PDDR, NPCM_PECI_PDDR_MASK,
+			   NPCM_PECI_HOST_NEG_BIT_RATE_DEFAULT);
+
+	ret = regmap_read_poll_timeout(priv->regmap, NPCM_PECI_CTL_STS, cmd_sts,
+				       !(cmd_sts & NPCM_PECI_CTRL_START_BUSY),
+				       NPCM_PECI_IDLE_CHECK_INTERVAL_USEC,
+				       NPCM_PECI_IDLE_CHECK_TIMEOUT_USEC);
+	if (ret)
+		return ret; /* -ETIMEDOUT */
+
+	/* PECI interrupt enable */
+	regmap_update_bits(priv->regmap, NPCM_PECI_CTL_STS, NPCM_PECI_CTRL_DONE_INT_EN,
+			   NPCM_PECI_CTRL_DONE_INT_EN);
+
+	return 0;
+}
+
+static const struct regmap_config npcm_peci_regmap_config = {
+	.reg_bits = 8,
+	.val_bits = 8,
+	.max_register = NPCM_PECI_MAX_REG,
+};
+
+static const struct peci_controller_ops npcm_ops = {
+	.xfer = npcm_peci_xfer,
+};
+
+static int npcm_peci_probe(struct platform_device *pdev)
+{
+	struct peci_controller *controller;
+	struct npcm_peci *priv;
+	void __iomem *base;
+	int ret;
+
+	priv = devm_kzalloc(&pdev->dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	priv->dev = &pdev->dev;
+	dev_set_drvdata(&pdev->dev, priv);
+
+	base = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(base))
+		return PTR_ERR(base);
+
+	priv->regmap = devm_regmap_init_mmio(&pdev->dev, base, &npcm_peci_regmap_config);
+	if (IS_ERR(priv->regmap))
+		return PTR_ERR(priv->regmap);
+
+	priv->irq = platform_get_irq(pdev, 0);
+	if (priv->irq < 0)
+		return priv->irq;
+
+	ret = devm_request_irq(&pdev->dev, priv->irq, npcm_peci_irq_handler,
+			       0, "peci-npcm-irq", priv);
+	if (ret)
+		return ret;
+
+	init_completion(&priv->xfer_complete);
+	spin_lock_init(&priv->lock);
+
+	ret = npcm_peci_init_ctrl(priv);
+	if (ret)
+		return ret;
+
+	controller = devm_peci_controller_add(priv->dev, &npcm_ops);
+	if (IS_ERR(controller))
+		return dev_err_probe(priv->dev, PTR_ERR(controller),
+				     "failed to add npcm peci controller\n");
+
+	priv->controller = controller;
+
+	return 0;
+}
+
+static const struct of_device_id npcm_peci_of_table[] = {
+	{ .compatible = "nuvoton,npcm750-peci", },
+	{ .compatible = "nuvoton,npcm845-peci", },
+	{ }
+};
+MODULE_DEVICE_TABLE(of, npcm_peci_of_table);
+
+static struct platform_driver npcm_peci_driver = {
+	.probe  = npcm_peci_probe,
+	.driver = {
+		.name           = KBUILD_MODNAME,
+		.of_match_table = npcm_peci_of_table,
+	},
+};
+module_platform_driver(npcm_peci_driver);
+
+MODULE_AUTHOR("Tomer Maimon <tomer.maimon@nuvoton.com>");
+MODULE_DESCRIPTION("NPCM PECI driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("PECI");
diff --git a/drivers/peci/core.c b/drivers/peci/core.c
new file mode 100644
index 000000000..e14995b1b
--- /dev/null
+++ b/drivers/peci/core.c
@@ -0,0 +1,235 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2018-2021 Intel Corporation
+
+#include <linux/bug.h>
+#include <linux/device.h>
+#include <linux/export.h>
+#include <linux/idr.h>
+#include <linux/module.h>
+#include <linux/of.h>
+#include <linux/peci.h>
+#include <linux/pm_runtime.h>
+#include <linux/property.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+static DEFINE_IDA(peci_controller_ida);
+
+static void peci_controller_dev_release(struct device *dev)
+{
+	struct peci_controller *controller = to_peci_controller(dev);
+
+	mutex_destroy(&controller->bus_lock);
+	ida_free(&peci_controller_ida, controller->id);
+	kfree(controller);
+}
+
+const struct device_type peci_controller_type = {
+	.release	= peci_controller_dev_release,
+};
+
+int peci_controller_scan_devices(struct peci_controller *controller)
+{
+	int ret;
+	u8 addr;
+
+	for (addr = PECI_BASE_ADDR; addr < PECI_BASE_ADDR + PECI_DEVICE_NUM_MAX; addr++) {
+		ret = peci_device_create(controller, addr);
+		if (ret)
+			return ret;
+	}
+
+	return 0;
+}
+
+static struct peci_controller *peci_controller_alloc(struct device *dev,
+						     const struct peci_controller_ops *ops)
+{
+	struct peci_controller *controller;
+	int ret;
+
+	if (!ops->xfer)
+		return ERR_PTR(-EINVAL);
+
+	controller = kzalloc_obj(*controller);
+	if (!controller)
+		return ERR_PTR(-ENOMEM);
+
+	ret = ida_alloc_max(&peci_controller_ida, U8_MAX, GFP_KERNEL);
+	if (ret < 0)
+		goto err;
+	controller->id = ret;
+
+	controller->ops = ops;
+
+	controller->dev.parent = dev;
+	controller->dev.bus = &peci_bus_type;
+	controller->dev.type = &peci_controller_type;
+
+	device_initialize(&controller->dev);
+
+	mutex_init(&controller->bus_lock);
+
+	return controller;
+
+err:
+	kfree(controller);
+	return ERR_PTR(ret);
+}
+
+static int unregister_child(struct device *dev, void *dummy)
+{
+	peci_device_destroy(to_peci_device(dev));
+
+	return 0;
+}
+
+static void unregister_controller(void *_controller)
+{
+	struct peci_controller *controller = _controller;
+
+	/*
+	 * Detach any active PECI devices. This can't fail, thus we do not
+	 * check the returned value.
+	 */
+	device_for_each_child_reverse(&controller->dev, NULL, unregister_child);
+
+	device_unregister(&controller->dev);
+
+	fwnode_handle_put(controller->dev.fwnode);
+
+	pm_runtime_disable(&controller->dev);
+}
+
+/**
+ * devm_peci_controller_add() - add PECI controller
+ * @dev: device for devm operations
+ * @ops: pointer to controller specific methods
+ *
+ * In final stage of its probe(), peci_controller driver calls
+ * devm_peci_controller_add() to register itself with the PECI bus.
+ *
+ * Return: Pointer to the newly allocated controller or ERR_PTR() in case of failure.
+ */
+struct peci_controller *devm_peci_controller_add(struct device *dev,
+						 const struct peci_controller_ops *ops)
+{
+	struct peci_controller *controller;
+	int ret;
+
+	controller = peci_controller_alloc(dev, ops);
+	if (IS_ERR(controller))
+		return controller;
+
+	ret = dev_set_name(&controller->dev, "peci-%d", controller->id);
+	if (ret)
+		goto err_put;
+
+	pm_runtime_no_callbacks(&controller->dev);
+	pm_suspend_ignore_children(&controller->dev, true);
+	pm_runtime_enable(&controller->dev);
+
+	device_set_node(&controller->dev, fwnode_handle_get(dev_fwnode(dev)));
+
+	ret = device_add(&controller->dev);
+	if (ret)
+		goto err_fwnode;
+
+	ret = devm_add_action_or_reset(dev, unregister_controller, controller);
+	if (ret)
+		return ERR_PTR(ret);
+
+	/*
+	 * Ignoring retval since failures during scan are non-critical for
+	 * controller itself.
+	 */
+	peci_controller_scan_devices(controller);
+
+	return controller;
+
+err_fwnode:
+	fwnode_handle_put(controller->dev.fwnode);
+
+	pm_runtime_disable(&controller->dev);
+
+err_put:
+	put_device(&controller->dev);
+
+	return ERR_PTR(ret);
+}
+EXPORT_SYMBOL_NS_GPL(devm_peci_controller_add, "PECI");
+
+static const struct peci_device_id *
+peci_bus_match_device_id(const struct peci_device_id *id, struct peci_device *device)
+{
+	while (id->x86_vfm != 0) {
+		if (id->x86_vfm == device->info.x86_vfm)
+			return id;
+		id++;
+	}
+
+	return NULL;
+}
+
+static int peci_bus_device_match(struct device *dev, const struct device_driver *drv)
+{
+	struct peci_device *device = to_peci_device(dev);
+	const struct peci_driver *peci_drv = to_peci_driver(drv);
+
+	if (dev->type != &peci_device_type)
+		return 0;
+
+	return !!peci_bus_match_device_id(peci_drv->id_table, device);
+}
+
+static int peci_bus_device_probe(struct device *dev)
+{
+	struct peci_device *device = to_peci_device(dev);
+	struct peci_driver *driver = to_peci_driver(dev->driver);
+
+	return driver->probe(device, peci_bus_match_device_id(driver->id_table, device));
+}
+
+static void peci_bus_device_remove(struct device *dev)
+{
+	struct peci_device *device = to_peci_device(dev);
+	struct peci_driver *driver = to_peci_driver(dev->driver);
+
+	if (driver->remove)
+		driver->remove(device);
+}
+
+const struct bus_type peci_bus_type = {
+	.name		= "peci",
+	.match		= peci_bus_device_match,
+	.probe		= peci_bus_device_probe,
+	.remove		= peci_bus_device_remove,
+	.bus_groups	= peci_bus_groups,
+};
+
+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;
+	}
+
+	return 0;
+}
+module_init(peci_init);
+
+static void __exit peci_exit(void)
+{
+	bus_unregister(&peci_bus_type);
+}
+module_exit(peci_exit);
+
+MODULE_AUTHOR("Jason M Bills <jason.m.bills@linux.intel.com>");
+MODULE_AUTHOR("Jae Hyun Yoo <jae.hyun.yoo@linux.intel.com>");
+MODULE_AUTHOR("Iwona Winiarska <iwona.winiarska@intel.com>");
+MODULE_DESCRIPTION("PECI bus core module");
+MODULE_LICENSE("GPL");
diff --git a/drivers/peci/cpu.c b/drivers/peci/cpu.c
new file mode 100644
index 000000000..c9fc06c9f
--- /dev/null
+++ b/drivers/peci/cpu.c
@@ -0,0 +1,344 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2021 Intel Corporation
+
+#include <linux/auxiliary_bus.h>
+#include <linux/module.h>
+#include <linux/peci.h>
+#include <linux/peci-cpu.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+/**
+ * peci_temp_read() - read the maximum die temperature from PECI target device
+ * @device: PECI device to which request is going to be sent
+ * @temp_raw: where to store the read temperature
+ *
+ * It uses GetTemp PECI command.
+ *
+ * Return: 0 if succeeded, other values in case errors.
+ */
+int peci_temp_read(struct peci_device *device, s16 *temp_raw)
+{
+	struct peci_request *req;
+
+	req = peci_xfer_get_temp(device);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	*temp_raw = peci_request_temp_read(req);
+
+	peci_request_free(req);
+
+	return 0;
+}
+EXPORT_SYMBOL_NS_GPL(peci_temp_read, "PECI_CPU");
+
+/**
+ * peci_pcs_read() - read PCS register
+ * @device: PECI device to which request is going to be sent
+ * @index: PCS index
+ * @param: PCS parameter
+ * @data: where to store the read data
+ *
+ * It uses RdPkgConfig PECI command.
+ *
+ * Return: 0 if succeeded, other values in case errors.
+ */
+int peci_pcs_read(struct peci_device *device, u8 index, u16 param, u32 *data)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_xfer_pkg_cfg_readl(device, index, param);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = peci_request_status(req);
+	if (ret)
+		goto out_req_free;
+
+	*data = peci_request_data_readl(req);
+out_req_free:
+	peci_request_free(req);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(peci_pcs_read, "PECI_CPU");
+
+/**
+ * peci_pci_local_read() - read 32-bit memory location using raw address
+ * @device: PECI device to which request is going to be sent
+ * @bus: bus
+ * @dev: device
+ * @func: function
+ * @reg: register
+ * @data: where to store the read data
+ *
+ * It uses RdPCIConfigLocal PECI command.
+ *
+ * Return: 0 if succeeded, other values in case errors.
+ */
+int peci_pci_local_read(struct peci_device *device, u8 bus, u8 dev, u8 func,
+			u16 reg, u32 *data)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_xfer_pci_cfg_local_readl(device, bus, dev, func, reg);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = peci_request_status(req);
+	if (ret)
+		goto out_req_free;
+
+	*data = peci_request_data_readl(req);
+out_req_free:
+	peci_request_free(req);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(peci_pci_local_read, "PECI_CPU");
+
+/**
+ * peci_ep_pci_local_read() - read 32-bit memory location using raw address
+ * @device: PECI device to which request is going to be sent
+ * @seg: PCI segment
+ * @bus: bus
+ * @dev: device
+ * @func: function
+ * @reg: register
+ * @data: where to store the read data
+ *
+ * Like &peci_pci_local_read, but it uses RdEndpointConfig PECI command.
+ *
+ * Return: 0 if succeeded, other values in case errors.
+ */
+int peci_ep_pci_local_read(struct peci_device *device, u8 seg,
+			   u8 bus, u8 dev, u8 func, u16 reg, u32 *data)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_xfer_ep_pci_cfg_local_readl(device, seg, bus, dev, func, reg);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = peci_request_status(req);
+	if (ret)
+		goto out_req_free;
+
+	*data = peci_request_data_readl(req);
+out_req_free:
+	peci_request_free(req);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(peci_ep_pci_local_read, "PECI_CPU");
+
+/**
+ * peci_mmio_read() - read 32-bit memory location using 64-bit bar offset address
+ * @device: PECI device to which request is going to be sent
+ * @bar: PCI bar
+ * @seg: PCI segment
+ * @bus: bus
+ * @dev: device
+ * @func: function
+ * @address: 64-bit MMIO address
+ * @data: where to store the read data
+ *
+ * It uses RdEndpointConfig PECI command.
+ *
+ * Return: 0 if succeeded, other values in case errors.
+ */
+int peci_mmio_read(struct peci_device *device, u8 bar, u8 seg,
+		   u8 bus, u8 dev, u8 func, u64 address, u32 *data)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_xfer_ep_mmio64_readl(device, bar, seg, bus, dev, func, address);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = peci_request_status(req);
+	if (ret)
+		goto out_req_free;
+
+	*data = peci_request_data_readl(req);
+out_req_free:
+	peci_request_free(req);
+
+	return ret;
+}
+EXPORT_SYMBOL_NS_GPL(peci_mmio_read, "PECI_CPU");
+
+static const char * const peci_adev_types[] = {
+	"cputemp",
+	"dimmtemp",
+};
+
+struct peci_cpu {
+	struct peci_device *device;
+	const struct peci_device_id *id;
+};
+
+static void adev_release(struct device *dev)
+{
+	struct auxiliary_device *adev = to_auxiliary_dev(dev);
+
+	kfree(adev->name);
+	kfree(adev);
+}
+
+static struct auxiliary_device *adev_alloc(struct peci_cpu *priv, int idx)
+{
+	struct peci_controller *controller = to_peci_controller(priv->device->dev.parent);
+	struct auxiliary_device *adev;
+	const char *name;
+	int ret;
+
+	adev = kzalloc_obj(*adev);
+	if (!adev)
+		return ERR_PTR(-ENOMEM);
+
+	name = kasprintf(GFP_KERNEL, "%s.%s", peci_adev_types[idx], (const char *)priv->id->data);
+	if (!name) {
+		ret = -ENOMEM;
+		goto free_adev;
+	}
+
+	adev->name = name;
+	adev->dev.parent = &priv->device->dev;
+	adev->dev.release = adev_release;
+	adev->id = (controller->id << 16) | (priv->device->addr);
+
+	ret = auxiliary_device_init(adev);
+	if (ret)
+		goto free_name;
+
+	return adev;
+
+free_name:
+	kfree(name);
+free_adev:
+	kfree(adev);
+	return ERR_PTR(ret);
+}
+
+static void unregister_adev(void *_adev)
+{
+	struct auxiliary_device *adev = _adev;
+
+	auxiliary_device_delete(adev);
+	auxiliary_device_uninit(adev);
+}
+
+static int devm_adev_add(struct device *dev, int idx)
+{
+	struct peci_cpu *priv = dev_get_drvdata(dev);
+	struct auxiliary_device *adev;
+	int ret;
+
+	adev = adev_alloc(priv, idx);
+	if (IS_ERR(adev))
+		return PTR_ERR(adev);
+
+	ret = auxiliary_device_add(adev);
+	if (ret) {
+		auxiliary_device_uninit(adev);
+		return ret;
+	}
+
+	ret = devm_add_action_or_reset(&priv->device->dev, unregister_adev, adev);
+	if (ret)
+		return ret;
+
+	return 0;
+}
+
+static void peci_cpu_add_adevices(struct peci_cpu *priv)
+{
+	struct device *dev = &priv->device->dev;
+	int ret, i;
+
+	for (i = 0; i < ARRAY_SIZE(peci_adev_types); i++) {
+		ret = devm_adev_add(dev, i);
+		if (ret) {
+			dev_warn(dev, "Failed to register PECI auxiliary: %s, ret = %d\n",
+				 peci_adev_types[i], ret);
+			continue;
+		}
+	}
+}
+
+static int
+peci_cpu_probe(struct peci_device *device, const struct peci_device_id *id)
+{
+	struct device *dev = &device->dev;
+	struct peci_cpu *priv;
+
+	priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL);
+	if (!priv)
+		return -ENOMEM;
+
+	dev_set_drvdata(dev, priv);
+	priv->device = device;
+	priv->id = id;
+
+	peci_cpu_add_adevices(priv);
+
+	return 0;
+}
+
+static const struct peci_device_id peci_cpu_device_ids[] = {
+	{ /* Haswell Xeon */
+		.x86_vfm = INTEL_HASWELL_X,
+		.data	= "hsx",
+	},
+	{ /* Broadwell Xeon */
+		.x86_vfm = INTEL_BROADWELL_X,
+		.data	= "bdx",
+	},
+	{ /* Broadwell Xeon D */
+		.x86_vfm = INTEL_BROADWELL_D,
+		.data	= "bdxd",
+	},
+	{ /* Skylake Xeon */
+		.x86_vfm = INTEL_SKYLAKE_X,
+		.data	= "skx",
+	},
+	{ /* Icelake Xeon */
+		.x86_vfm = INTEL_ICELAKE_X,
+		.data	= "icx",
+	},
+	{ /* Icelake Xeon D */
+		.x86_vfm = INTEL_ICELAKE_D,
+		.data	= "icxd",
+	},
+	{ /* Sapphire Rapids Xeon */
+		.x86_vfm = INTEL_SAPPHIRERAPIDS_X,
+		.data	= "spr",
+	},
+	{ /* Emerald Rapids Xeon */
+		.x86_vfm  = INTEL_EMERALDRAPIDS_X,
+		.data  = "emr",
+	},
+	{ }
+};
+MODULE_DEVICE_TABLE(peci, peci_cpu_device_ids);
+
+static struct peci_driver peci_cpu_driver = {
+	.probe		= peci_cpu_probe,
+	.id_table	= peci_cpu_device_ids,
+	.driver		= {
+		.name		= "peci-cpu",
+	},
+};
+module_peci_driver(peci_cpu_driver);
+
+MODULE_AUTHOR("Iwona Winiarska <iwona.winiarska@intel.com>");
+MODULE_DESCRIPTION("PECI CPU driver");
+MODULE_LICENSE("GPL");
+MODULE_IMPORT_NS("PECI");
diff --git a/drivers/peci/device.c b/drivers/peci/device.c
new file mode 100644
index 000000000..2b9610216
--- /dev/null
+++ b/drivers/peci/device.c
@@ -0,0 +1,251 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2018-2021 Intel Corporation
+
+#include <linux/bitfield.h>
+#include <linux/peci.h>
+#include <linux/peci-cpu.h>
+#include <linux/slab.h>
+
+#include "internal.h"
+
+/*
+ * PECI device can be removed using sysfs, but the removal can also happen as
+ * a result of controller being removed.
+ * Mutex is used to protect PECI device from being double-deleted.
+ */
+static DEFINE_MUTEX(peci_device_del_lock);
+
+#define REVISION_NUM_MASK GENMASK(15, 8)
+static int peci_get_revision(struct peci_device *device, u8 *revision)
+{
+	struct peci_request *req;
+	u64 dib;
+
+	req = peci_xfer_get_dib(device);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	/*
+	 * PECI device may be in a state where it is unable to return a proper
+	 * DIB, in which case it returns 0 as DIB value.
+	 * Let's treat this as an error to avoid carrying on with the detection
+	 * using invalid revision.
+	 */
+	dib = peci_request_dib_read(req);
+	if (dib == 0) {
+		peci_request_free(req);
+		return -EIO;
+	}
+
+	*revision = FIELD_GET(REVISION_NUM_MASK, dib);
+
+	peci_request_free(req);
+
+	return 0;
+}
+
+static int peci_get_cpu_id(struct peci_device *device, u32 *cpu_id)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_xfer_pkg_cfg_readl(device, PECI_PCS_PKG_ID, PECI_PKG_ID_CPU_ID);
+	if (IS_ERR(req))
+		return PTR_ERR(req);
+
+	ret = peci_request_status(req);
+	if (ret)
+		goto out_req_free;
+
+	*cpu_id = peci_request_data_readl(req);
+out_req_free:
+	peci_request_free(req);
+
+	return ret;
+}
+
+static unsigned int peci_x86_cpu_family(unsigned int sig)
+{
+	unsigned int x86;
+
+	x86 = (sig >> 8) & 0xf;
+
+	if (x86 == 0xf)
+		x86 += (sig >> 20) & 0xff;
+
+	return x86;
+}
+
+static unsigned int peci_x86_cpu_model(unsigned int sig)
+{
+	unsigned int fam, model;
+
+	fam = peci_x86_cpu_family(sig);
+
+	model = (sig >> 4) & 0xf;
+
+	if (fam >= 0x6)
+		model += ((sig >> 16) & 0xf) << 4;
+
+	return model;
+}
+
+static int peci_device_info_init(struct peci_device *device)
+{
+	u8 revision;
+	u32 cpu_id;
+	int ret;
+
+	ret = peci_get_cpu_id(device, &cpu_id);
+	if (ret)
+		return ret;
+
+	device->info.x86_vfm = IFM(peci_x86_cpu_family(cpu_id), peci_x86_cpu_model(cpu_id));
+
+	ret = peci_get_revision(device, &revision);
+	if (ret)
+		return ret;
+	device->info.peci_revision = revision;
+
+	device->info.socket_id = device->addr - PECI_BASE_ADDR;
+
+	return 0;
+}
+
+static int peci_detect(struct peci_controller *controller, u8 addr)
+{
+	/*
+	 * PECI Ping is a command encoded by tx_len = 0, rx_len = 0.
+	 * We expect correct Write FCS if the device at the target address
+	 * is able to respond.
+	 */
+	struct peci_request req = { 0 };
+	int ret;
+
+	mutex_lock(&controller->bus_lock);
+	ret = controller->ops->xfer(controller, addr, &req);
+	mutex_unlock(&controller->bus_lock);
+
+	return ret;
+}
+
+static bool peci_addr_valid(u8 addr)
+{
+	return addr >= PECI_BASE_ADDR && addr < PECI_BASE_ADDR + PECI_DEVICE_NUM_MAX;
+}
+
+static int peci_dev_exists(struct device *dev, void *data)
+{
+	struct peci_device *device = to_peci_device(dev);
+	u8 *addr = data;
+
+	if (device->addr == *addr)
+		return -EBUSY;
+
+	return 0;
+}
+
+int peci_device_create(struct peci_controller *controller, u8 addr)
+{
+	struct peci_device *device;
+	int ret;
+
+	if (!peci_addr_valid(addr))
+		return -EINVAL;
+
+	/* Check if we have already detected this device before. */
+	ret = device_for_each_child(&controller->dev, &addr, peci_dev_exists);
+	if (ret)
+		return 0;
+
+	ret = peci_detect(controller, addr);
+	if (ret) {
+		/*
+		 * Device not present or host state doesn't allow successful
+		 * detection at this time.
+		 */
+		if (ret == -EIO || ret == -ETIMEDOUT)
+			return 0;
+
+		return ret;
+	}
+
+	device = kzalloc_obj(*device);
+	if (!device)
+		return -ENOMEM;
+
+	device_initialize(&device->dev);
+
+	device->addr = addr;
+	device->dev.parent = &controller->dev;
+	device->dev.bus = &peci_bus_type;
+	device->dev.type = &peci_device_type;
+
+	ret = peci_device_info_init(device);
+	if (ret)
+		goto err_put;
+
+	ret = dev_set_name(&device->dev, "%d-%02x", controller->id, device->addr);
+	if (ret)
+		goto err_put;
+
+	ret = device_add(&device->dev);
+	if (ret)
+		goto err_put;
+
+	return 0;
+
+err_put:
+	put_device(&device->dev);
+
+	return ret;
+}
+
+void peci_device_destroy(struct peci_device *device)
+{
+	mutex_lock(&peci_device_del_lock);
+	if (!device->deleted) {
+		device_unregister(&device->dev);
+		device->deleted = true;
+	}
+	mutex_unlock(&peci_device_del_lock);
+}
+
+int __peci_driver_register(struct peci_driver *driver, struct module *owner,
+			   const char *mod_name)
+{
+	driver->driver.bus = &peci_bus_type;
+	driver->driver.owner = owner;
+	driver->driver.mod_name = mod_name;
+
+	if (!driver->probe) {
+		pr_err("peci: trying to register driver without probe callback\n");
+		return -EINVAL;
+	}
+
+	if (!driver->id_table) {
+		pr_err("peci: trying to register driver without device id table\n");
+		return -EINVAL;
+	}
+
+	return driver_register(&driver->driver);
+}
+EXPORT_SYMBOL_NS_GPL(__peci_driver_register, "PECI");
+
+void peci_driver_unregister(struct peci_driver *driver)
+{
+	driver_unregister(&driver->driver);
+}
+EXPORT_SYMBOL_NS_GPL(peci_driver_unregister, "PECI");
+
+static void peci_device_release(struct device *dev)
+{
+	struct peci_device *device = to_peci_device(dev);
+
+	kfree(device);
+}
+
+const struct device_type peci_device_type = {
+	.groups		= peci_device_groups,
+	.release	= peci_device_release,
+};
diff --git a/drivers/peci/internal.h b/drivers/peci/internal.h
new file mode 100644
index 000000000..99924a118
--- /dev/null
+++ b/drivers/peci/internal.h
@@ -0,0 +1,131 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/* Copyright (c) 2018-2021 Intel Corporation */
+
+#ifndef __PECI_INTERNAL_H
+#define __PECI_INTERNAL_H
+
+#include <linux/device.h>
+#include <linux/types.h>
+
+struct peci_controller;
+struct attribute_group;
+struct peci_device;
+struct peci_request;
+
+/* PECI CPU address range 0x30-0x37 */
+#define PECI_BASE_ADDR		0x30
+#define PECI_DEVICE_NUM_MAX	8
+
+struct peci_request *peci_request_alloc(struct peci_device *device, u8 tx_len, u8 rx_len);
+void peci_request_free(struct peci_request *req);
+
+int peci_request_status(struct peci_request *req);
+
+u64 peci_request_dib_read(struct peci_request *req);
+s16 peci_request_temp_read(struct peci_request *req);
+
+u8 peci_request_data_readb(struct peci_request *req);
+u16 peci_request_data_readw(struct peci_request *req);
+u32 peci_request_data_readl(struct peci_request *req);
+u64 peci_request_data_readq(struct peci_request *req);
+
+struct peci_request *peci_xfer_get_dib(struct peci_device *device);
+struct peci_request *peci_xfer_get_temp(struct peci_device *device);
+
+struct peci_request *peci_xfer_pkg_cfg_readb(struct peci_device *device, u8 index, u16 param);
+struct peci_request *peci_xfer_pkg_cfg_readw(struct peci_device *device, u8 index, u16 param);
+struct peci_request *peci_xfer_pkg_cfg_readl(struct peci_device *device, u8 index, u16 param);
+struct peci_request *peci_xfer_pkg_cfg_readq(struct peci_device *device, u8 index, u16 param);
+
+struct peci_request *peci_xfer_pci_cfg_local_readb(struct peci_device *device,
+						   u8 bus, u8 dev, u8 func, u16 reg);
+struct peci_request *peci_xfer_pci_cfg_local_readw(struct peci_device *device,
+						   u8 bus, u8 dev, u8 func, u16 reg);
+struct peci_request *peci_xfer_pci_cfg_local_readl(struct peci_device *device,
+						   u8 bus, u8 dev, u8 func, u16 reg);
+
+struct peci_request *peci_xfer_ep_pci_cfg_local_readb(struct peci_device *device, u8 seg,
+						      u8 bus, u8 dev, u8 func, u16 reg);
+struct peci_request *peci_xfer_ep_pci_cfg_local_readw(struct peci_device *device, u8 seg,
+						      u8 bus, u8 dev, u8 func, u16 reg);
+struct peci_request *peci_xfer_ep_pci_cfg_local_readl(struct peci_device *device, u8 seg,
+						      u8 bus, u8 dev, u8 func, u16 reg);
+
+struct peci_request *peci_xfer_ep_pci_cfg_readb(struct peci_device *device, u8 seg,
+						u8 bus, u8 dev, u8 func, u16 reg);
+struct peci_request *peci_xfer_ep_pci_cfg_readw(struct peci_device *device, u8 seg,
+						u8 bus, u8 dev, u8 func, u16 reg);
+struct peci_request *peci_xfer_ep_pci_cfg_readl(struct peci_device *device, u8 seg,
+						u8 bus, u8 dev, u8 func, u16 reg);
+
+struct peci_request *peci_xfer_ep_mmio32_readl(struct peci_device *device, u8 bar, u8 seg,
+					       u8 bus, u8 dev, u8 func, u64 offset);
+
+struct peci_request *peci_xfer_ep_mmio64_readl(struct peci_device *device, u8 bar, u8 seg,
+					       u8 bus, u8 dev, u8 func, u64 offset);
+/**
+ * struct peci_device_id - PECI device data to match
+ * @data: pointer to driver private data specific to device
+ * @x86_vfm: device vendor-family-model
+ */
+struct peci_device_id {
+	const void *data;
+	u32 x86_vfm;
+};
+
+extern const struct device_type peci_device_type;
+extern const struct attribute_group *peci_device_groups[];
+
+int peci_device_create(struct peci_controller *controller, u8 addr);
+void peci_device_destroy(struct peci_device *device);
+
+extern const struct bus_type peci_bus_type;
+extern const struct attribute_group *peci_bus_groups[];
+
+/**
+ * struct peci_driver - PECI driver
+ * @driver: inherit device driver
+ * @probe: probe callback
+ * @remove: remove callback
+ * @id_table: PECI device match table to decide which device to bind
+ */
+struct peci_driver {
+	struct device_driver driver;
+	int (*probe)(struct peci_device *device, const struct peci_device_id *id);
+	void (*remove)(struct peci_device *device);
+	const struct peci_device_id *id_table;
+};
+
+#define to_peci_driver(__drv)	container_of_const(__drv, struct peci_driver, driver)
+
+int __peci_driver_register(struct peci_driver *driver, struct module *owner,
+			   const char *mod_name);
+/**
+ * peci_driver_register() - register PECI driver
+ * @driver: the driver to be registered
+ *
+ * PECI drivers that don't need to do anything special in module init should
+ * use the convenience "module_peci_driver" macro instead
+ *
+ * Return: zero on success, else a negative error code.
+ */
+#define peci_driver_register(driver) \
+	__peci_driver_register(driver, THIS_MODULE, KBUILD_MODNAME)
+void peci_driver_unregister(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_driver_register, peci_driver_unregister)
+
+extern const struct device_type peci_controller_type;
+
+int peci_controller_scan_devices(struct peci_controller *controller);
+
+#endif /* __PECI_INTERNAL_H */
diff --git a/drivers/peci/request.c b/drivers/peci/request.c
new file mode 100644
index 000000000..db2cc30a4
--- /dev/null
+++ b/drivers/peci/request.c
@@ -0,0 +1,482 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2021 Intel Corporation
+
+#include <linux/bug.h>
+#include <linux/export.h>
+#include <linux/pci.h>
+#include <linux/peci.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+
+#include <linux/unaligned.h>
+
+#include "internal.h"
+
+#define PECI_GET_DIB_CMD		0xf7
+#define  PECI_GET_DIB_WR_LEN		1
+#define  PECI_GET_DIB_RD_LEN		8
+
+#define PECI_GET_TEMP_CMD		0x01
+#define  PECI_GET_TEMP_WR_LEN		1
+#define  PECI_GET_TEMP_RD_LEN		2
+
+#define PECI_RDPKGCFG_CMD		0xa1
+#define  PECI_RDPKGCFG_WR_LEN		5
+#define  PECI_RDPKGCFG_RD_LEN_BASE	1
+#define PECI_WRPKGCFG_CMD		0xa5
+#define  PECI_WRPKGCFG_WR_LEN_BASE	6
+#define  PECI_WRPKGCFG_RD_LEN		1
+
+#define PECI_RDIAMSR_CMD		0xb1
+#define  PECI_RDIAMSR_WR_LEN		5
+#define  PECI_RDIAMSR_RD_LEN		9
+#define PECI_WRIAMSR_CMD		0xb5
+#define PECI_RDIAMSREX_CMD		0xd1
+#define  PECI_RDIAMSREX_WR_LEN		6
+#define  PECI_RDIAMSREX_RD_LEN		9
+
+#define PECI_RDPCICFG_CMD		0x61
+#define  PECI_RDPCICFG_WR_LEN		6
+#define  PECI_RDPCICFG_RD_LEN		5
+#define  PECI_RDPCICFG_RD_LEN_MAX	24
+#define PECI_WRPCICFG_CMD		0x65
+
+#define PECI_RDPCICFGLOCAL_CMD			0xe1
+#define  PECI_RDPCICFGLOCAL_WR_LEN		5
+#define  PECI_RDPCICFGLOCAL_RD_LEN_BASE		1
+#define PECI_WRPCICFGLOCAL_CMD			0xe5
+#define  PECI_WRPCICFGLOCAL_WR_LEN_BASE		6
+#define  PECI_WRPCICFGLOCAL_RD_LEN		1
+
+#define PECI_ENDPTCFG_TYPE_LOCAL_PCI		0x03
+#define PECI_ENDPTCFG_TYPE_PCI			0x04
+#define PECI_ENDPTCFG_TYPE_MMIO			0x05
+#define PECI_ENDPTCFG_ADDR_TYPE_PCI		0x04
+#define PECI_ENDPTCFG_ADDR_TYPE_MMIO_D		0x05
+#define PECI_ENDPTCFG_ADDR_TYPE_MMIO_Q		0x06
+#define PECI_RDENDPTCFG_CMD			0xc1
+#define  PECI_RDENDPTCFG_PCI_WR_LEN		12
+#define  PECI_RDENDPTCFG_MMIO_WR_LEN_BASE	10
+#define  PECI_RDENDPTCFG_MMIO_D_WR_LEN		14
+#define  PECI_RDENDPTCFG_MMIO_Q_WR_LEN		18
+#define  PECI_RDENDPTCFG_RD_LEN_BASE		1
+#define PECI_WRENDPTCFG_CMD			0xc5
+#define  PECI_WRENDPTCFG_PCI_WR_LEN_BASE	13
+#define  PECI_WRENDPTCFG_MMIO_D_WR_LEN_BASE	15
+#define  PECI_WRENDPTCFG_MMIO_Q_WR_LEN_BASE	19
+#define  PECI_WRENDPTCFG_RD_LEN			1
+
+/* Device Specific Completion Code (CC) Definition */
+#define PECI_CC_SUCCESS				0x40
+#define PECI_CC_NEED_RETRY			0x80
+#define PECI_CC_OUT_OF_RESOURCE			0x81
+#define PECI_CC_UNAVAIL_RESOURCE		0x82
+#define PECI_CC_INVALID_REQ			0x90
+#define PECI_CC_MCA_ERROR			0x91
+#define PECI_CC_CATASTROPHIC_MCA_ERROR		0x93
+#define PECI_CC_FATAL_MCA_ERROR			0x94
+#define PECI_CC_PARITY_ERR_GPSB_OR_PMSB		0x98
+#define PECI_CC_PARITY_ERR_GPSB_OR_PMSB_IERR	0x9B
+#define PECI_CC_PARITY_ERR_GPSB_OR_PMSB_MCA	0x9C
+
+#define PECI_RETRY_BIT			BIT(0)
+
+#define PECI_RETRY_TIMEOUT		msecs_to_jiffies(700)
+#define PECI_RETRY_INTERVAL_MIN		msecs_to_jiffies(1)
+#define PECI_RETRY_INTERVAL_MAX		msecs_to_jiffies(128)
+
+static u8 peci_request_data_cc(struct peci_request *req)
+{
+	return req->rx.buf[0];
+}
+
+/**
+ * peci_request_status() - return -errno based on PECI completion code
+ * @req: the PECI request that contains response data with completion code
+ *
+ * It can't be used for Ping(), GetDIB() and GetTemp() - for those commands we
+ * don't expect completion code in the response.
+ *
+ * Return: -errno
+ */
+int peci_request_status(struct peci_request *req)
+{
+	u8 cc = peci_request_data_cc(req);
+
+	if (cc != PECI_CC_SUCCESS)
+		dev_dbg(&req->device->dev, "ret: %#02x\n", cc);
+
+	switch (cc) {
+	case PECI_CC_SUCCESS:
+		return 0;
+	case PECI_CC_NEED_RETRY:
+	case PECI_CC_OUT_OF_RESOURCE:
+	case PECI_CC_UNAVAIL_RESOURCE:
+		return -EAGAIN;
+	case PECI_CC_INVALID_REQ:
+		return -EINVAL;
+	case PECI_CC_MCA_ERROR:
+	case PECI_CC_CATASTROPHIC_MCA_ERROR:
+	case PECI_CC_FATAL_MCA_ERROR:
+	case PECI_CC_PARITY_ERR_GPSB_OR_PMSB:
+	case PECI_CC_PARITY_ERR_GPSB_OR_PMSB_IERR:
+	case PECI_CC_PARITY_ERR_GPSB_OR_PMSB_MCA:
+		return -EIO;
+	}
+
+	WARN_ONCE(1, "Unknown PECI completion code: %#02x\n", cc);
+
+	return -EIO;
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_status, "PECI");
+
+static int peci_request_xfer(struct peci_request *req)
+{
+	struct peci_device *device = req->device;
+	struct peci_controller *controller = to_peci_controller(device->dev.parent);
+	int ret;
+
+	mutex_lock(&controller->bus_lock);
+	ret = controller->ops->xfer(controller, device->addr, req);
+	mutex_unlock(&controller->bus_lock);
+
+	return ret;
+}
+
+static int peci_request_xfer_retry(struct peci_request *req)
+{
+	long wait_interval = PECI_RETRY_INTERVAL_MIN;
+	struct peci_device *device = req->device;
+	struct peci_controller *controller = to_peci_controller(device->dev.parent);
+	unsigned long start = jiffies;
+	int ret;
+
+	/* Don't try to use it for ping */
+	if (WARN_ON(req->tx.len == 0))
+		return 0;
+
+	do {
+		ret = peci_request_xfer(req);
+		if (ret) {
+			dev_dbg(&controller->dev, "xfer error: %d\n", ret);
+			return ret;
+		}
+
+		if (peci_request_status(req) != -EAGAIN)
+			return 0;
+
+		/* Set the retry bit to indicate a retry attempt */
+		req->tx.buf[1] |= PECI_RETRY_BIT;
+
+		if (schedule_timeout_interruptible(wait_interval))
+			return -ERESTARTSYS;
+
+		wait_interval = min_t(long, wait_interval * 2, PECI_RETRY_INTERVAL_MAX);
+	} while (time_before(jiffies, start + PECI_RETRY_TIMEOUT));
+
+	dev_dbg(&controller->dev, "request timed out\n");
+
+	return -ETIMEDOUT;
+}
+
+/**
+ * peci_request_alloc() - allocate &struct peci_requests
+ * @device: PECI device to which request is going to be sent
+ * @tx_len: TX length
+ * @rx_len: RX length
+ *
+ * Return: A pointer to a newly allocated &struct peci_request on success or NULL otherwise.
+ */
+struct peci_request *peci_request_alloc(struct peci_device *device, u8 tx_len, u8 rx_len)
+{
+	struct peci_request *req;
+
+	/*
+	 * TX and RX buffers are fixed length members of peci_request, this is
+	 * just a warn for developers to make sure to expand the buffers (or
+	 * change the allocation method) if we go over the current limit.
+	 */
+	if (WARN_ON_ONCE(tx_len > PECI_REQUEST_MAX_BUF_SIZE || rx_len > PECI_REQUEST_MAX_BUF_SIZE))
+		return NULL;
+	/*
+	 * PECI controllers that we are using now don't support DMA, this
+	 * should be converted to DMA API once support for controllers that do
+	 * allow it is added to avoid an extra copy.
+	 */
+	req = kzalloc_obj(*req);
+	if (!req)
+		return NULL;
+
+	req->device = device;
+	req->tx.len = tx_len;
+	req->rx.len = rx_len;
+
+	return req;
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_alloc, "PECI");
+
+/**
+ * peci_request_free() - free peci_request
+ * @req: the PECI request to be freed
+ */
+void peci_request_free(struct peci_request *req)
+{
+	kfree(req);
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_free, "PECI");
+
+struct peci_request *peci_xfer_get_dib(struct peci_device *device)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_request_alloc(device, PECI_GET_DIB_WR_LEN, PECI_GET_DIB_RD_LEN);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	req->tx.buf[0] = PECI_GET_DIB_CMD;
+
+	ret = peci_request_xfer(req);
+	if (ret) {
+		peci_request_free(req);
+		return ERR_PTR(ret);
+	}
+
+	return req;
+}
+EXPORT_SYMBOL_NS_GPL(peci_xfer_get_dib, "PECI");
+
+struct peci_request *peci_xfer_get_temp(struct peci_device *device)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_request_alloc(device, PECI_GET_TEMP_WR_LEN, PECI_GET_TEMP_RD_LEN);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	req->tx.buf[0] = PECI_GET_TEMP_CMD;
+
+	ret = peci_request_xfer(req);
+	if (ret) {
+		peci_request_free(req);
+		return ERR_PTR(ret);
+	}
+
+	return req;
+}
+EXPORT_SYMBOL_NS_GPL(peci_xfer_get_temp, "PECI");
+
+static struct peci_request *
+__pkg_cfg_read(struct peci_device *device, u8 index, u16 param, u8 len)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_request_alloc(device, PECI_RDPKGCFG_WR_LEN, PECI_RDPKGCFG_RD_LEN_BASE + len);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	req->tx.buf[0] = PECI_RDPKGCFG_CMD;
+	req->tx.buf[1] = 0;
+	req->tx.buf[2] = index;
+	put_unaligned_le16(param, &req->tx.buf[3]);
+
+	ret = peci_request_xfer_retry(req);
+	if (ret) {
+		peci_request_free(req);
+		return ERR_PTR(ret);
+	}
+
+	return req;
+}
+
+static u32 __get_pci_addr(u8 bus, u8 dev, u8 func, u16 reg)
+{
+	return reg | PCI_DEVID(bus, PCI_DEVFN(dev, func)) << 12;
+}
+
+static struct peci_request *
+__pci_cfg_local_read(struct peci_device *device, u8 bus, u8 dev, u8 func, u16 reg, u8 len)
+{
+	struct peci_request *req;
+	u32 pci_addr;
+	int ret;
+
+	req = peci_request_alloc(device, PECI_RDPCICFGLOCAL_WR_LEN,
+				 PECI_RDPCICFGLOCAL_RD_LEN_BASE + len);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	pci_addr = __get_pci_addr(bus, dev, func, reg);
+
+	req->tx.buf[0] = PECI_RDPCICFGLOCAL_CMD;
+	req->tx.buf[1] = 0;
+	put_unaligned_le24(pci_addr, &req->tx.buf[2]);
+
+	ret = peci_request_xfer_retry(req);
+	if (ret) {
+		peci_request_free(req);
+		return ERR_PTR(ret);
+	}
+
+	return req;
+}
+
+static struct peci_request *
+__ep_pci_cfg_read(struct peci_device *device, u8 msg_type, u8 seg,
+		  u8 bus, u8 dev, u8 func, u16 reg, u8 len)
+{
+	struct peci_request *req;
+	u32 pci_addr;
+	int ret;
+
+	req = peci_request_alloc(device, PECI_RDENDPTCFG_PCI_WR_LEN,
+				 PECI_RDENDPTCFG_RD_LEN_BASE + len);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	pci_addr = __get_pci_addr(bus, dev, func, reg);
+
+	req->tx.buf[0] = PECI_RDENDPTCFG_CMD;
+	req->tx.buf[1] = 0;
+	req->tx.buf[2] = msg_type;
+	req->tx.buf[3] = 0;
+	req->tx.buf[4] = 0;
+	req->tx.buf[5] = 0;
+	req->tx.buf[6] = PECI_ENDPTCFG_ADDR_TYPE_PCI;
+	req->tx.buf[7] = seg; /* PCI Segment */
+	put_unaligned_le32(pci_addr, &req->tx.buf[8]);
+
+	ret = peci_request_xfer_retry(req);
+	if (ret) {
+		peci_request_free(req);
+		return ERR_PTR(ret);
+	}
+
+	return req;
+}
+
+static struct peci_request *
+__ep_mmio_read(struct peci_device *device, u8 bar, u8 addr_type, u8 seg,
+	       u8 bus, u8 dev, u8 func, u64 offset, u8 tx_len, u8 len)
+{
+	struct peci_request *req;
+	int ret;
+
+	req = peci_request_alloc(device, tx_len, PECI_RDENDPTCFG_RD_LEN_BASE + len);
+	if (!req)
+		return ERR_PTR(-ENOMEM);
+
+	req->tx.buf[0] = PECI_RDENDPTCFG_CMD;
+	req->tx.buf[1] = 0;
+	req->tx.buf[2] = PECI_ENDPTCFG_TYPE_MMIO;
+	req->tx.buf[3] = 0; /* Endpoint ID */
+	req->tx.buf[4] = 0; /* Reserved */
+	req->tx.buf[5] = bar;
+	req->tx.buf[6] = addr_type;
+	req->tx.buf[7] = seg; /* PCI Segment */
+	req->tx.buf[8] = PCI_DEVFN(dev, func);
+	req->tx.buf[9] = bus; /* PCI Bus */
+
+	if (addr_type == PECI_ENDPTCFG_ADDR_TYPE_MMIO_D)
+		put_unaligned_le32(offset, &req->tx.buf[10]);
+	else
+		put_unaligned_le64(offset, &req->tx.buf[10]);
+
+	ret = peci_request_xfer_retry(req);
+	if (ret) {
+		peci_request_free(req);
+		return ERR_PTR(ret);
+	}
+
+	return req;
+}
+
+u8 peci_request_data_readb(struct peci_request *req)
+{
+	return req->rx.buf[1];
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_data_readb, "PECI");
+
+u16 peci_request_data_readw(struct peci_request *req)
+{
+	return get_unaligned_le16(&req->rx.buf[1]);
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_data_readw, "PECI");
+
+u32 peci_request_data_readl(struct peci_request *req)
+{
+	return get_unaligned_le32(&req->rx.buf[1]);
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_data_readl, "PECI");
+
+u64 peci_request_data_readq(struct peci_request *req)
+{
+	return get_unaligned_le64(&req->rx.buf[1]);
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_data_readq, "PECI");
+
+u64 peci_request_dib_read(struct peci_request *req)
+{
+	return get_unaligned_le64(&req->rx.buf[0]);
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_dib_read, "PECI");
+
+s16 peci_request_temp_read(struct peci_request *req)
+{
+	return get_unaligned_le16(&req->rx.buf[0]);
+}
+EXPORT_SYMBOL_NS_GPL(peci_request_temp_read, "PECI");
+
+#define __read_pkg_config(x, type) \
+struct peci_request *peci_xfer_pkg_cfg_##x(struct peci_device *device, u8 index, u16 param) \
+{ \
+	return __pkg_cfg_read(device, index, param, sizeof(type)); \
+} \
+EXPORT_SYMBOL_NS_GPL(peci_xfer_pkg_cfg_##x, "PECI")
+
+__read_pkg_config(readb, u8);
+__read_pkg_config(readw, u16);
+__read_pkg_config(readl, u32);
+__read_pkg_config(readq, u64);
+
+#define __read_pci_config_local(x, type) \
+struct peci_request * \
+peci_xfer_pci_cfg_local_##x(struct peci_device *device, u8 bus, u8 dev, u8 func, u16 reg) \
+{ \
+	return __pci_cfg_local_read(device, bus, dev, func, reg, sizeof(type)); \
+} \
+EXPORT_SYMBOL_NS_GPL(peci_xfer_pci_cfg_local_##x, "PECI")
+
+__read_pci_config_local(readb, u8);
+__read_pci_config_local(readw, u16);
+__read_pci_config_local(readl, u32);
+
+#define __read_ep_pci_config(x, msg_type, type) \
+struct peci_request * \
+peci_xfer_ep_pci_cfg_##x(struct peci_device *device, u8 seg, u8 bus, u8 dev, u8 func, u16 reg) \
+{ \
+	return __ep_pci_cfg_read(device, msg_type, seg, bus, dev, func, reg, sizeof(type)); \
+} \
+EXPORT_SYMBOL_NS_GPL(peci_xfer_ep_pci_cfg_##x, "PECI")
+
+__read_ep_pci_config(local_readb, PECI_ENDPTCFG_TYPE_LOCAL_PCI, u8);
+__read_ep_pci_config(local_readw, PECI_ENDPTCFG_TYPE_LOCAL_PCI, u16);
+__read_ep_pci_config(local_readl, PECI_ENDPTCFG_TYPE_LOCAL_PCI, u32);
+__read_ep_pci_config(readb, PECI_ENDPTCFG_TYPE_PCI, u8);
+__read_ep_pci_config(readw, PECI_ENDPTCFG_TYPE_PCI, u16);
+__read_ep_pci_config(readl, PECI_ENDPTCFG_TYPE_PCI, u32);
+
+#define __read_ep_mmio(x, y, addr_type, type1, type2) \
+struct peci_request *peci_xfer_ep_mmio##y##_##x(struct peci_device *device, u8 bar, u8 seg, \
+					   u8 bus, u8 dev, u8 func, u64 offset) \
+{ \
+	return __ep_mmio_read(device, bar, addr_type, seg, bus, dev, func, \
+			      offset, PECI_RDENDPTCFG_MMIO_WR_LEN_BASE + sizeof(type1), \
+			      sizeof(type2)); \
+} \
+EXPORT_SYMBOL_NS_GPL(peci_xfer_ep_mmio##y##_##x, "PECI")
+
+__read_ep_mmio(readl, 32, PECI_ENDPTCFG_ADDR_TYPE_MMIO_D, u32, u32);
+__read_ep_mmio(readl, 64, PECI_ENDPTCFG_ADDR_TYPE_MMIO_Q, u64, u32);
diff --git a/drivers/peci/sysfs.c b/drivers/peci/sysfs.c
new file mode 100644
index 000000000..c04244075
--- /dev/null
+++ b/drivers/peci/sysfs.c
@@ -0,0 +1,82 @@
+// SPDX-License-Identifier: GPL-2.0-only
+// Copyright (c) 2021 Intel Corporation
+
+#include <linux/device.h>
+#include <linux/kernel.h>
+#include <linux/peci.h>
+
+#include "internal.h"
+
+static int rescan_controller(struct device *dev, void *data)
+{
+	if (dev->type != &peci_controller_type)
+		return 0;
+
+	return peci_controller_scan_devices(to_peci_controller(dev));
+}
+
+static ssize_t rescan_store(const struct bus_type *bus, const char *buf, size_t count)
+{
+	bool res;
+	int ret;
+
+	ret = kstrtobool(buf, &res);
+	if (ret)
+		return ret;
+
+	if (!res)
+		return count;
+
+	ret = bus_for_each_dev(&peci_bus_type, NULL, NULL, rescan_controller);
+	if (ret)
+		return ret;
+
+	return count;
+}
+static BUS_ATTR_WO(rescan);
+
+static struct attribute *peci_bus_attrs[] = {
+	&bus_attr_rescan.attr,
+	NULL
+};
+
+static const struct attribute_group peci_bus_group = {
+	.attrs = peci_bus_attrs,
+};
+
+const struct attribute_group *peci_bus_groups[] = {
+	&peci_bus_group,
+	NULL
+};
+
+static ssize_t remove_store(struct device *dev, struct device_attribute *attr,
+			    const char *buf, size_t count)
+{
+	struct peci_device *device = to_peci_device(dev);
+	bool res;
+	int ret;
+
+	ret = kstrtobool(buf, &res);
+	if (ret)
+		return ret;
+
+	if (res && device_remove_file_self(dev, attr))
+		peci_device_destroy(device);
+
+	return count;
+}
+static DEVICE_ATTR_IGNORE_LOCKDEP(remove, 0200, NULL, remove_store);
+
+static struct attribute *peci_device_attrs[] = {
+	&dev_attr_remove.attr,
+	NULL
+};
+
+static const struct attribute_group peci_device_group = {
+	.attrs = peci_device_attrs,
+};
+
+const struct attribute_group *peci_device_groups[] = {
+	&peci_device_group,
+	NULL
+};