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, 137 insertions, 0 deletions

diff --git a/drivers/net/phy/ste10Xp.c b/drivers/net/phy/ste10Xp.c
new file mode 100644
index 000000000..d4835d4c5
--- /dev/null
+++ b/drivers/net/phy/ste10Xp.c
@@ -0,0 +1,137 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * drivers/net/phy/ste10Xp.c
+ *
+ * Driver for STMicroelectronics STe10Xp PHYs
+ *
+ * Author: Giuseppe Cavallaro <peppe.cavallaro@st.com>
+ *
+ * Copyright (c) 2008 STMicroelectronics Limited
+ */
+
+#include <linux/module.h>
+#include <linux/init.h>
+#include <linux/sched.h>
+#include <linux/kernel.h>
+#include <linux/moduleparam.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/ethtool.h>
+#include <linux/mii.h>
+#include <linux/phy.h>
+
+#define MII_XCIIS	0x11	/* Configuration Info IRQ & Status Reg */
+#define MII_XIE		0x12	/* Interrupt Enable Register */
+#define MII_XIE_DEFAULT_MASK 0x0070 /* ANE complete, Remote Fault, Link Down */
+
+#define STE101P_PHY_ID		0x00061c50
+#define STE100P_PHY_ID		0x1c040011
+
+static int ste10Xp_config_init(struct phy_device *phydev)
+{
+	int value, err;
+
+	/* Software Reset PHY */
+	value = phy_read(phydev, MII_BMCR);
+	if (value < 0)
+		return value;
+
+	value |= BMCR_RESET;
+	err = phy_write(phydev, MII_BMCR, value);
+	if (err < 0)
+		return err;
+
+	do {
+		value = phy_read(phydev, MII_BMCR);
+	} while (value & BMCR_RESET);
+
+	return 0;
+}
+
+static int ste10Xp_ack_interrupt(struct phy_device *phydev)
+{
+	int err = phy_read(phydev, MII_XCIIS);
+
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int ste10Xp_config_intr(struct phy_device *phydev)
+{
+	int err;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		/* clear any pending interrupts */
+		err = ste10Xp_ack_interrupt(phydev);
+		if (err)
+			return err;
+
+		/* Enable all STe101P interrupts (PR12) */
+		err = phy_write(phydev, MII_XIE, MII_XIE_DEFAULT_MASK);
+	} else {
+		err = phy_write(phydev, MII_XIE, 0);
+		if (err)
+			return err;
+
+		err = ste10Xp_ack_interrupt(phydev);
+	}
+
+	return err;
+}
+
+static irqreturn_t ste10Xp_handle_interrupt(struct phy_device *phydev)
+{
+	int irq_status;
+
+	irq_status = phy_read(phydev, MII_XCIIS);
+	if (irq_status < 0) {
+		phy_error(phydev);
+		return IRQ_NONE;
+	}
+
+	if (!(irq_status & MII_XIE_DEFAULT_MASK))
+		return IRQ_NONE;
+
+	phy_trigger_machine(phydev);
+
+	return IRQ_HANDLED;
+}
+
+static struct phy_driver ste10xp_pdriver[] = {
+{
+	.phy_id = STE101P_PHY_ID,
+	.phy_id_mask = 0xfffffff0,
+	.name = "STe101p",
+	/* PHY_BASIC_FEATURES */
+	.config_init = ste10Xp_config_init,
+	.config_intr = ste10Xp_config_intr,
+	.handle_interrupt = ste10Xp_handle_interrupt,
+	.suspend = genphy_suspend,
+	.resume = genphy_resume,
+}, {
+	.phy_id = STE100P_PHY_ID,
+	.phy_id_mask = 0xffffffff,
+	.name = "STe100p",
+	/* PHY_BASIC_FEATURES */
+	.config_init = ste10Xp_config_init,
+	.config_intr = ste10Xp_config_intr,
+	.handle_interrupt = ste10Xp_handle_interrupt,
+	.suspend = genphy_suspend,
+	.resume = genphy_resume,
+} };
+
+module_phy_driver(ste10xp_pdriver);
+
+static const struct mdio_device_id __maybe_unused ste10Xp_tbl[] = {
+	{ STE101P_PHY_ID, 0xfffffff0 },
+	{ STE100P_PHY_ID, 0xffffffff },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, ste10Xp_tbl);
+
+MODULE_DESCRIPTION("STMicroelectronics STe10Xp PHY driver");
+MODULE_AUTHOR("Giuseppe Cavallaro <peppe.cavallaro@st.com>");
+MODULE_LICENSE("GPL");