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, 98 insertions, 0 deletions

diff --git a/drivers/net/phy/uPD60620.c b/drivers/net/phy/uPD60620.c
new file mode 100644
index 000000000..900cb756c
--- /dev/null
+++ b/drivers/net/phy/uPD60620.c
@@ -0,0 +1,98 @@
+// SPDX-License-Identifier: GPL-2.0+
+/*
+ * Driver for the Renesas PHY uPD60620.
+ *
+ * Copyright (C) 2015 Softing Industrial Automation GmbH
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/phy.h>
+
+#define UPD60620_PHY_ID    0xb8242824
+
+/* Extended Registers and values */
+/* PHY Special Control/Status    */
+#define PHY_PHYSCR         0x1F      /* PHY.31 */
+#define PHY_PHYSCR_10MB    0x0004    /* PHY speed = 10mb */
+#define PHY_PHYSCR_100MB   0x0008    /* PHY speed = 100mb */
+#define PHY_PHYSCR_DUPLEX  0x0010    /* PHY Duplex */
+
+/* PHY Special Modes */
+#define PHY_SPM            0x12      /* PHY.18 */
+
+/* Init PHY */
+
+static int upd60620_config_init(struct phy_device *phydev)
+{
+	/* Enable support for passive HUBs (could be a strap option) */
+	/* PHYMODE: All speeds, HD in parallel detect */
+	return phy_write(phydev, PHY_SPM, 0x0180 | phydev->mdio.addr);
+}
+
+/* Get PHY status from common registers */
+
+static int upd60620_read_status(struct phy_device *phydev)
+{
+	int phy_state;
+
+	/* Read negotiated state */
+	phy_state = phy_read(phydev, MII_BMSR);
+	if (phy_state < 0)
+		return phy_state;
+
+	phydev->link = 0;
+	linkmode_zero(phydev->lp_advertising);
+	phydev->pause = 0;
+	phydev->asym_pause = 0;
+
+	if (phy_state & (BMSR_ANEGCOMPLETE | BMSR_LSTATUS)) {
+		phy_state = phy_read(phydev, PHY_PHYSCR);
+		if (phy_state < 0)
+			return phy_state;
+
+		if (phy_state & (PHY_PHYSCR_10MB | PHY_PHYSCR_100MB)) {
+			phydev->link = 1;
+			phydev->speed = SPEED_10;
+			phydev->duplex = DUPLEX_HALF;
+
+			if (phy_state & PHY_PHYSCR_100MB)
+				phydev->speed = SPEED_100;
+			if (phy_state & PHY_PHYSCR_DUPLEX)
+				phydev->duplex = DUPLEX_FULL;
+
+			phy_state = phy_read(phydev, MII_LPA);
+			if (phy_state < 0)
+				return phy_state;
+
+			mii_lpa_to_linkmode_lpa_t(phydev->lp_advertising,
+						  phy_state);
+
+			phy_resolve_aneg_pause(phydev);
+		}
+	}
+	return 0;
+}
+
+MODULE_DESCRIPTION("Renesas uPD60620 PHY driver");
+MODULE_AUTHOR("Bernd Edlinger <bernd.edlinger@hotmail.de>");
+MODULE_LICENSE("GPL");
+
+static struct phy_driver upd60620_driver[1] = { {
+	.phy_id         = UPD60620_PHY_ID,
+	.phy_id_mask    = 0xfffffffe,
+	.name           = "Renesas uPD60620",
+	/* PHY_BASIC_FEATURES */
+	.flags          = 0,
+	.config_init    = upd60620_config_init,
+	.read_status    = upd60620_read_status,
+} };
+
+module_phy_driver(upd60620_driver);
+
+static const struct mdio_device_id __maybe_unused upd60620_tbl[] = {
+	{ UPD60620_PHY_ID, 0xfffffffe },
+	{ }
+};
+
+MODULE_DEVICE_TABLE(mdio, upd60620_tbl);