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, 102 insertions, 0 deletions

diff --git a/drivers/net/phy/bcm63xx.c b/drivers/net/phy/bcm63xx.c
new file mode 100644
index 000000000..b46a736a3
--- /dev/null
+++ b/drivers/net/phy/bcm63xx.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ *	Driver for Broadcom 63xx SOCs integrated PHYs
+ */
+#include "bcm-phy-lib.h"
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define MII_BCM63XX_IR		0x1a	/* interrupt register */
+#define MII_BCM63XX_IR_EN	0x4000	/* global interrupt enable */
+#define MII_BCM63XX_IR_DUPLEX	0x0800	/* duplex changed */
+#define MII_BCM63XX_IR_SPEED	0x0400	/* speed changed */
+#define MII_BCM63XX_IR_LINK	0x0200	/* link changed */
+#define MII_BCM63XX_IR_GMASK	0x0100	/* global interrupt mask */
+
+MODULE_DESCRIPTION("Broadcom 63xx internal PHY driver");
+MODULE_AUTHOR("Maxime Bizon <mbizon@freebox.fr>");
+MODULE_LICENSE("GPL");
+
+static int bcm63xx_config_intr(struct phy_device *phydev)
+{
+	int reg, err;
+
+	reg = phy_read(phydev, MII_BCM63XX_IR);
+	if (reg < 0)
+		return reg;
+
+	if (phydev->interrupts == PHY_INTERRUPT_ENABLED) {
+		err = bcm_phy_ack_intr(phydev);
+		if (err)
+			return err;
+
+		reg &= ~MII_BCM63XX_IR_GMASK;
+		err = phy_write(phydev, MII_BCM63XX_IR, reg);
+	} else {
+		reg |= MII_BCM63XX_IR_GMASK;
+		err = phy_write(phydev, MII_BCM63XX_IR, reg);
+		if (err)
+			return err;
+
+		err = bcm_phy_ack_intr(phydev);
+	}
+
+	return err;
+}
+
+static int bcm63xx_config_init(struct phy_device *phydev)
+{
+	int reg, err;
+
+	/* ASYM_PAUSE bit is marked RO in datasheet, so don't cheat */
+	linkmode_set_bit(ETHTOOL_LINK_MODE_Pause_BIT, phydev->supported);
+
+	reg = phy_read(phydev, MII_BCM63XX_IR);
+	if (reg < 0)
+		return reg;
+
+	/* Mask interrupts globally.  */
+	reg |= MII_BCM63XX_IR_GMASK;
+	err = phy_write(phydev, MII_BCM63XX_IR, reg);
+	if (err < 0)
+		return err;
+
+	/* Unmask events we are interested in  */
+	reg = ~(MII_BCM63XX_IR_DUPLEX |
+		MII_BCM63XX_IR_SPEED |
+		MII_BCM63XX_IR_LINK) |
+		MII_BCM63XX_IR_EN;
+	return phy_write(phydev, MII_BCM63XX_IR, reg);
+}
+
+static struct phy_driver bcm63xx_driver[] = {
+{
+	.phy_id		= 0x00406000,
+	.phy_id_mask	= 0xfffffc00,
+	.name		= "Broadcom BCM63XX (1)",
+	/* PHY_BASIC_FEATURES */
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm63xx_config_init,
+	.config_intr	= bcm63xx_config_intr,
+	.handle_interrupt = bcm_phy_handle_interrupt,
+}, {
+	/* same phy as above, with just a different OUI */
+	.phy_id		= 0x002bdc00,
+	.phy_id_mask	= 0xfffffc00,
+	.name		= "Broadcom BCM63XX (2)",
+	/* PHY_BASIC_FEATURES */
+	.flags		= PHY_IS_INTERNAL,
+	.config_init	= bcm63xx_config_init,
+	.config_intr	= bcm63xx_config_intr,
+	.handle_interrupt = bcm_phy_handle_interrupt,
+} };
+
+module_phy_driver(bcm63xx_driver);
+
+static const struct mdio_device_id __maybe_unused bcm63xx_tbl[] = {
+	{ 0x00406000, 0xfffffc00 },
+	{ 0x002bdc00, 0xfffffc00 },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, bcm63xx_tbl);