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, 163 insertions, 0 deletions

diff --git a/drivers/net/phy/qsemi.c b/drivers/net/phy/qsemi.c
new file mode 100644
index 000000000..7b70ba6ca
--- /dev/null
+++ b/drivers/net/phy/qsemi.c
@@ -0,0 +1,163 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * drivers/net/phy/qsemi.c
+ *
+ * Driver for Quality Semiconductor 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 <asm/io.h>
+#include <asm/irq.h>
+#include <linux/uaccess.h>
+
+/* ------------------------------------------------------------------------- */
+/* The Quality Semiconductor QS6612 is used on the RPX CLLF                  */
+
+/* register definitions */
+
+#define MII_QS6612_MCR		17  /* Mode Control Register      */
+#define MII_QS6612_FTR		27  /* Factory Test Register      */
+#define MII_QS6612_MCO		28  /* Misc. Control Register     */
+#define MII_QS6612_ISR		29  /* Interrupt Source Register  */
+#define MII_QS6612_IMR		30  /* Interrupt Mask Register    */
+#define MII_QS6612_IMR_INIT	0x003a
+#define MII_QS6612_PCR		31  /* 100BaseTx PHY Control Reg. */
+
+#define QS6612_PCR_AN_COMPLETE	0x1000
+#define QS6612_PCR_RLBEN	0x0200
+#define QS6612_PCR_DCREN	0x0100
+#define QS6612_PCR_4B5BEN	0x0040
+#define QS6612_PCR_TX_ISOLATE	0x0020
+#define QS6612_PCR_MLT3_DIS	0x0002
+#define QS6612_PCR_SCRM_DESCRM	0x0001
+
+MODULE_DESCRIPTION("Quality Semiconductor PHY driver");
+MODULE_AUTHOR("Andy Fleming");
+MODULE_LICENSE("GPL");
+
+/* Returns 0, unless there's a write error */
+static int qs6612_config_init(struct phy_device *phydev)
+{
+	/* The PHY powers up isolated on the RPX,
+	 * so send a command to allow operation.
+	 * XXX - My docs indicate this should be 0x0940
+	 * ...or something.  The current value sets three
+	 * reserved bits, bit 11, which specifies it should be
+	 * set to one, bit 10, which specifies it should be set
+	 * to 0, and bit 7, which doesn't specify.  However, my
+	 * docs are preliminary, and I will leave it like this
+	 * until someone more knowledgable corrects me or it.
+	 * -- Andy Fleming
+	 */
+	return phy_write(phydev, MII_QS6612_PCR, 0x0dc0);
+}
+
+static int qs6612_ack_interrupt(struct phy_device *phydev)
+{
+	int err;
+
+	/* The Interrupt Source register is not self-clearing, bits 4 and 5 are
+	 * cleared when MII_BMSR is read and bits 1 and 3 are cleared when
+	 * MII_EXPANSION is read
+	 */
+	err = phy_read(phydev, MII_QS6612_ISR);
+
+	if (err < 0)
+		return err;
+
+	err = phy_read(phydev, MII_BMSR);
+
+	if (err < 0)
+		return err;
+
+	err = phy_read(phydev, MII_EXPANSION);
+
+	if (err < 0)
+		return err;
+
+	return 0;
+}
+
+static int qs6612_config_intr(struct phy_device *phydev)
+{
+	int err;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		/* clear any interrupts before enabling them */
+		err = qs6612_ack_interrupt(phydev);
+		if (err)
+			return err;
+
+		err = phy_write(phydev, MII_QS6612_IMR,
+				MII_QS6612_IMR_INIT);
+	} else {
+		err = phy_write(phydev, MII_QS6612_IMR, 0);
+		if (err)
+			return err;
+
+		/* clear any leftover interrupts */
+		err = qs6612_ack_interrupt(phydev);
+	}
+
+	return err;
+
+}
+
+static irqreturn_t qs6612_handle_interrupt(struct phy_device *phydev)
+{
+	int irq_status;
+
+	irq_status = phy_read(phydev, MII_QS6612_ISR);
+	if (irq_status < 0) {
+		phy_error(phydev);
+		return IRQ_NONE;
+	}
+
+	if (!(irq_status & MII_QS6612_IMR_INIT))
+		return IRQ_NONE;
+
+	/* the interrupt source register is not self-clearing */
+	qs6612_ack_interrupt(phydev);
+
+	phy_trigger_machine(phydev);
+
+	return IRQ_HANDLED;
+}
+
+static struct phy_driver qs6612_driver[] = { {
+	.phy_id		= 0x00181440,
+	.name		= "QS6612",
+	.phy_id_mask	= 0xfffffff0,
+	/* PHY_BASIC_FEATURES */
+	.config_init	= qs6612_config_init,
+	.config_intr	= qs6612_config_intr,
+	.handle_interrupt = qs6612_handle_interrupt,
+} };
+
+module_phy_driver(qs6612_driver);
+
+static const struct mdio_device_id __maybe_unused qs6612_tbl[] = {
+	{ 0x00181440, 0xfffffff0 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, qs6612_tbl);