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, 154 insertions, 0 deletions

diff --git a/drivers/net/phy/cicada.c b/drivers/net/phy/cicada.c
new file mode 100644
index 000000000..d87cf8b94
--- /dev/null
+++ b/drivers/net/phy/cicada.c
@@ -0,0 +1,154 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * drivers/net/phy/cicada.c
+ *
+ * Driver for Cicada PHYs
+ *
+ * Author: Andy Fleming
+ *
+ * Copyright (c) 2004 Freescale Semiconductor, Inc.
+ */
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/unistd.h>
+#include <linux/interrupt.h>
+#include <linux/init.h>
+#include <linux/delay.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/spinlock.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/ethtool.h>
+#include <linux/phy.h>
+
+#include <linux/io.h>
+#include <asm/irq.h>
+#include <linux/uaccess.h>
+
+/* Cicada Extended Control Register 1 */
+#define MII_CIS8201_EXT_CON1           0x17
+#define MII_CIS8201_EXTCON1_INIT       0x0000
+
+/* Cicada Interrupt Mask Register */
+#define MII_CIS8201_IMASK		0x19
+#define MII_CIS8201_IMASK_IEN		0x8000
+#define MII_CIS8201_IMASK_SPEED	0x4000
+#define MII_CIS8201_IMASK_LINK		0x2000
+#define MII_CIS8201_IMASK_DUPLEX	0x1000
+#define MII_CIS8201_IMASK_MASK		0xf000
+
+/* Cicada Interrupt Status Register */
+#define MII_CIS8201_ISTAT		0x1a
+#define MII_CIS8201_ISTAT_STATUS	0x8000
+#define MII_CIS8201_ISTAT_SPEED	0x4000
+#define MII_CIS8201_ISTAT_LINK		0x2000
+#define MII_CIS8201_ISTAT_DUPLEX	0x1000
+
+/* Cicada Auxiliary Control/Status Register */
+#define MII_CIS8201_AUX_CONSTAT        0x1c
+#define MII_CIS8201_AUXCONSTAT_INIT    0x0004
+#define MII_CIS8201_AUXCONSTAT_DUPLEX  0x0020
+#define MII_CIS8201_AUXCONSTAT_SPEED   0x0018
+#define MII_CIS8201_AUXCONSTAT_GBIT    0x0010
+#define MII_CIS8201_AUXCONSTAT_100     0x0008
+
+MODULE_DESCRIPTION("Cicadia PHY driver");
+MODULE_AUTHOR("Andy Fleming");
+MODULE_LICENSE("GPL");
+
+static int cis820x_config_init(struct phy_device *phydev)
+{
+	int err;
+
+	err = phy_write(phydev, MII_CIS8201_AUX_CONSTAT,
+			MII_CIS8201_AUXCONSTAT_INIT);
+
+	if (err < 0)
+		return err;
+
+	err = phy_write(phydev, MII_CIS8201_EXT_CON1,
+			MII_CIS8201_EXTCON1_INIT);
+
+	return err;
+}
+
+static int cis820x_ack_interrupt(struct phy_device *phydev)
+{
+	int err = phy_read(phydev, MII_CIS8201_ISTAT);
+
+	return (err < 0) ? err : 0;
+}
+
+static int cis820x_config_intr(struct phy_device *phydev)
+{
+	int err;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		err = cis820x_ack_interrupt(phydev);
+		if (err)
+			return err;
+
+		err = phy_write(phydev, MII_CIS8201_IMASK,
+				MII_CIS8201_IMASK_MASK);
+	} else {
+		err = phy_write(phydev, MII_CIS8201_IMASK, 0);
+		if (err)
+			return err;
+
+		err = cis820x_ack_interrupt(phydev);
+	}
+
+	return err;
+}
+
+static irqreturn_t cis820x_handle_interrupt(struct phy_device *phydev)
+{
+	int irq_status;
+
+	irq_status = phy_read(phydev, MII_CIS8201_ISTAT);
+	if (irq_status < 0) {
+		phy_error(phydev);
+		return IRQ_NONE;
+	}
+
+	if (!(irq_status & MII_CIS8201_IMASK_MASK))
+		return IRQ_NONE;
+
+	phy_trigger_machine(phydev);
+
+	return IRQ_HANDLED;
+}
+
+/* Cicada 8201, a.k.a Vitesse VSC8201 */
+static struct phy_driver cis820x_driver[] = {
+{
+	.phy_id		= 0x000fc410,
+	.name		= "Cicada Cis8201",
+	.phy_id_mask	= 0x000ffff0,
+	/* PHY_GBIT_FEATURES */
+	.config_init	= &cis820x_config_init,
+	.config_intr	= &cis820x_config_intr,
+	.handle_interrupt = &cis820x_handle_interrupt,
+}, {
+	.phy_id		= 0x000fc440,
+	.name		= "Cicada Cis8204",
+	.phy_id_mask	= 0x000fffc0,
+	/* PHY_GBIT_FEATURES */
+	.config_init	= &cis820x_config_init,
+	.config_intr	= &cis820x_config_intr,
+	.handle_interrupt = &cis820x_handle_interrupt,
+} };
+
+module_phy_driver(cis820x_driver);
+
+static const struct mdio_device_id __maybe_unused cicada_tbl[] = {
+	{ 0x000fc410, 0x000ffff0 },
+	{ 0x000fc440, 0x000fffc0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, cicada_tbl);