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

1 files changed, 168 insertions, 0 deletions

diff --git a/drivers/spmi/spmi-apple-controller.c b/drivers/spmi/spmi-apple-controller.c
new file mode 100644
index 000000000..376cf682c
--- /dev/null
+++ b/drivers/spmi/spmi-apple-controller.c
@@ -0,0 +1,168 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Apple SoC SPMI device driver
+ *
+ * Copyright The Asahi Linux Contributors
+ *
+ * Inspired by:
+ *		OpenBSD support Copyright (c) 2021 Mark Kettenis <kettenis@openbsd.org>
+ *		Correllium support Copyright (C) 2021 Corellium LLC
+ *		hisi-spmi-controller.c
+ *		spmi-pmic-arb.c Copyright (c) 2021, The Linux Foundation.
+ */
+
+#include <linux/io.h>
+#include <linux/iopoll.h>
+#include <linux/module.h>
+#include <linux/platform_device.h>
+#include <linux/spmi.h>
+
+/* SPMI Controller Registers */
+#define SPMI_STATUS_REG 0
+#define SPMI_CMD_REG 0x4
+#define SPMI_RSP_REG 0x8
+
+#define SPMI_RX_FIFO_EMPTY BIT(24)
+
+#define REG_POLL_INTERVAL_US 10000
+#define REG_POLL_TIMEOUT_US (REG_POLL_INTERVAL_US * 5)
+
+struct apple_spmi {
+	void __iomem *regs;
+};
+
+#define poll_reg(spmi, reg, val, cond) \
+	readl_poll_timeout((spmi)->regs + (reg), (val), (cond), \
+			   REG_POLL_INTERVAL_US, REG_POLL_TIMEOUT_US)
+
+static inline u32 apple_spmi_pack_cmd(u8 opc, u8 sid, u16 saddr, size_t len)
+{
+	return opc | sid << 8 | saddr << 16 | (len - 1) | (1 << 15);
+}
+
+/* Wait for Rx FIFO to have something */
+static int apple_spmi_wait_rx_not_empty(struct spmi_controller *ctrl)
+{
+	struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
+	int ret;
+	u32 status;
+
+	ret = poll_reg(spmi, SPMI_STATUS_REG, status, !(status & SPMI_RX_FIFO_EMPTY));
+	if (ret) {
+		dev_err(&ctrl->dev,
+			"failed to wait for RX FIFO not empty\n");
+		return ret;
+	}
+
+	return 0;
+}
+
+static int spmi_read_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
+			 u16 saddr, u8 *buf, size_t len)
+{
+	struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
+	u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
+	u32 rsp;
+	size_t len_read = 0;
+	u8 i;
+	int ret;
+
+	writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+
+	ret = apple_spmi_wait_rx_not_empty(ctrl);
+	if (ret)
+		return ret;
+
+	/* Discard SPMI reply status */
+	readl(spmi->regs + SPMI_RSP_REG);
+
+	/* Read SPMI data reply */
+	while (len_read < len) {
+		rsp = readl(spmi->regs + SPMI_RSP_REG);
+		i = 0;
+		while ((len_read < len) && (i < 4)) {
+			buf[len_read++] = ((0xff << (8 * i)) & rsp) >> (8 * i);
+			i += 1;
+		}
+	}
+
+	return 0;
+}
+
+static int spmi_write_cmd(struct spmi_controller *ctrl, u8 opc, u8 sid,
+			  u16 saddr, const u8 *buf, size_t len)
+{
+	struct apple_spmi *spmi = spmi_controller_get_drvdata(ctrl);
+	u32 spmi_cmd = apple_spmi_pack_cmd(opc, sid, saddr, len);
+	size_t i = 0, j;
+	int ret;
+
+	writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+
+	while (i < len) {
+		j = 0;
+		spmi_cmd = 0;
+		while ((j < 4) & (i < len))
+			spmi_cmd |= buf[i++] << (j++ * 8);
+
+		writel(spmi_cmd, spmi->regs + SPMI_CMD_REG);
+	}
+
+	ret = apple_spmi_wait_rx_not_empty(ctrl);
+	if (ret)
+		return ret;
+
+	/* Discard */
+	readl(spmi->regs + SPMI_RSP_REG);
+
+	return 0;
+}
+
+static int apple_spmi_probe(struct platform_device *pdev)
+{
+	struct apple_spmi *spmi;
+	struct spmi_controller *ctrl;
+	int ret;
+
+	ctrl = devm_spmi_controller_alloc(&pdev->dev, sizeof(*spmi));
+	if (IS_ERR(ctrl))
+		return -ENOMEM;
+
+	spmi = spmi_controller_get_drvdata(ctrl);
+
+	spmi->regs = devm_platform_ioremap_resource(pdev, 0);
+	if (IS_ERR(spmi->regs))
+		return PTR_ERR(spmi->regs);
+
+	ctrl->dev.of_node = pdev->dev.of_node;
+
+	ctrl->read_cmd = spmi_read_cmd;
+	ctrl->write_cmd = spmi_write_cmd;
+
+	ret = devm_spmi_controller_add(&pdev->dev, ctrl);
+	if (ret)
+		return dev_err_probe(&pdev->dev, ret,
+				     "spmi_controller_add failed\n");
+
+	return 0;
+}
+
+static const struct of_device_id apple_spmi_match_table[] = {
+	{ .compatible = "apple,t8103-spmi", },
+	{ .compatible = "apple,spmi", },
+	{}
+};
+MODULE_DEVICE_TABLE(of, apple_spmi_match_table);
+
+static struct platform_driver apple_spmi_driver = {
+	.probe		= apple_spmi_probe,
+	.driver		= {
+		.name	= "apple-spmi",
+		.of_match_table = apple_spmi_match_table,
+	},
+};
+module_platform_driver(apple_spmi_driver);
+
+MODULE_AUTHOR("Jean-Francois Bortolotti <jeff@borto.fr>");
+MODULE_DESCRIPTION("Apple SoC SPMI driver");
+MODULE_LICENSE("GPL");