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, 96 insertions, 0 deletions

diff --git a/drivers/net/phy/teranetics.c b/drivers/net/phy/teranetics.c
new file mode 100644
index 000000000..46c5ff7d7
--- /dev/null
+++ b/drivers/net/phy/teranetics.c
@@ -0,0 +1,96 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Driver for Teranetics PHY
+ *
+ * Author: Shaohui Xie <Shaohui.Xie@freescale.com>
+ *
+ * Copyright 2015 Freescale Semiconductor, Inc.
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/mii.h>
+#include <linux/ethtool.h>
+#include <linux/mdio.h>
+#include <linux/phy.h>
+
+MODULE_DESCRIPTION("Teranetics PHY driver");
+MODULE_AUTHOR("Shaohui Xie <Shaohui.Xie@freescale.com>");
+MODULE_LICENSE("GPL v2");
+
+#define PHY_ID_TN2020	0x00a19410
+#define MDIO_PHYXS_LNSTAT_SYNC0	0x0001
+#define MDIO_PHYXS_LNSTAT_SYNC1	0x0002
+#define MDIO_PHYXS_LNSTAT_SYNC2	0x0004
+#define MDIO_PHYXS_LNSTAT_SYNC3	0x0008
+#define MDIO_PHYXS_LNSTAT_ALIGN 0x1000
+
+#define MDIO_PHYXS_LANE_READY	(MDIO_PHYXS_LNSTAT_SYNC0 | \
+				MDIO_PHYXS_LNSTAT_SYNC1 | \
+				MDIO_PHYXS_LNSTAT_SYNC2 | \
+				MDIO_PHYXS_LNSTAT_SYNC3 | \
+				MDIO_PHYXS_LNSTAT_ALIGN)
+
+static int teranetics_aneg_done(struct phy_device *phydev)
+{
+	/* auto negotiation state can only be checked when using copper
+	 * port, if using fiber port, just lie it's done.
+	 */
+	if (!phy_read_mmd(phydev, MDIO_MMD_VEND1, 93))
+		return genphy_c45_aneg_done(phydev);
+
+	return 1;
+}
+
+static int teranetics_read_status(struct phy_device *phydev)
+{
+	int reg;
+
+	phydev->link = 1;
+
+	phydev->speed = SPEED_10000;
+	phydev->duplex = DUPLEX_FULL;
+
+	if (!phy_read_mmd(phydev, MDIO_MMD_VEND1, 93)) {
+		reg = phy_read_mmd(phydev, MDIO_MMD_PHYXS, MDIO_PHYXS_LNSTAT);
+		if (reg < 0 ||
+		    !((reg & MDIO_PHYXS_LANE_READY) == MDIO_PHYXS_LANE_READY)) {
+			phydev->link = 0;
+			return 0;
+		}
+
+		reg = phy_read_mmd(phydev, MDIO_MMD_AN, MDIO_STAT1);
+		if (reg < 0 || !(reg & MDIO_STAT1_LSTATUS))
+			phydev->link = 0;
+	}
+
+	return 0;
+}
+
+static int teranetics_match_phy_device(struct phy_device *phydev,
+				       const struct phy_driver *phydrv)
+{
+	return phydev->c45_ids.device_ids[3] == PHY_ID_TN2020;
+}
+
+static struct phy_driver teranetics_driver[] = {
+{
+	.phy_id		= PHY_ID_TN2020,
+	.phy_id_mask	= 0xffffffff,
+	.name		= "Teranetics TN2020",
+	.features       = PHY_10GBIT_FEATURES,
+	.aneg_done	= teranetics_aneg_done,
+	.config_aneg    = gen10g_config_aneg,
+	.read_status	= teranetics_read_status,
+	.match_phy_device = teranetics_match_phy_device,
+},
+};
+
+module_phy_driver(teranetics_driver);
+
+static const struct mdio_device_id __maybe_unused teranetics_tbl[] = {
+	{ PHY_ID_TN2020, 0xffffffff },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, teranetics_tbl);