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, 129 insertions, 0 deletions

diff --git a/drivers/usb/dwc3/ulpi.c b/drivers/usb/dwc3/ulpi.c
new file mode 100644
index 000000000..a256b7f5d
--- /dev/null
+++ b/drivers/usb/dwc3/ulpi.c
@@ -0,0 +1,129 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * ulpi.c - DesignWare USB3 Controller's ULPI PHY interface
+ *
+ * Copyright (C) 2015 Intel Corporation
+ *
+ * Author: Heikki Krogerus <heikki.krogerus@linux.intel.com>
+ */
+
+#include <linux/delay.h>
+#include <linux/time64.h>
+#include <linux/ulpi/regs.h>
+#include <linux/ulpi/driver.h>
+
+#include "core.h"
+#include "io.h"
+
+#define USB_VENDOR_MICROCHIP 0x0424
+
+#define DWC3_ULPI_ADDR(a) \
+		((a >= ULPI_EXT_VENDOR_SPECIFIC) ? \
+		DWC3_GUSB2PHYACC_ADDR(ULPI_ACCESS_EXTENDED) | \
+		DWC3_GUSB2PHYACC_EXTEND_ADDR(a) : DWC3_GUSB2PHYACC_ADDR(a))
+
+#define DWC3_ULPI_BASE_DELAY	DIV_ROUND_UP(NSEC_PER_SEC, 60000000L)
+
+static int dwc3_ulpi_busyloop(struct dwc3 *dwc, u8 addr, bool read)
+{
+	unsigned long ns = 5L * DWC3_ULPI_BASE_DELAY;
+	unsigned int count = 10000;
+	u32 reg;
+
+	if (addr >= ULPI_EXT_VENDOR_SPECIFIC)
+		ns += DWC3_ULPI_BASE_DELAY;
+
+	if (read)
+		ns += DWC3_ULPI_BASE_DELAY;
+
+	reg = dwc3_readl(dwc, DWC3_GUSB2PHYCFG(0));
+	if (reg & DWC3_GUSB2PHYCFG_SUSPHY)
+		usleep_range(1000, 1200);
+
+	while (count--) {
+		ndelay(ns);
+		reg = dwc3_readl(dwc, DWC3_GUSB2PHYACC(0));
+		if (reg & DWC3_GUSB2PHYACC_DONE)
+			return 0;
+		cpu_relax();
+	}
+
+	return -ETIMEDOUT;
+}
+
+static int dwc3_ulpi_read(struct device *dev, u8 addr)
+{
+	struct dwc3 *dwc = dev_get_drvdata(dev);
+	u32 reg;
+	int ret;
+
+	reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr);
+	dwc3_writel(dwc, DWC3_GUSB2PHYACC(0), reg);
+
+	ret = dwc3_ulpi_busyloop(dwc, addr, true);
+	if (ret)
+		return ret;
+
+	reg = dwc3_readl(dwc, DWC3_GUSB2PHYACC(0));
+
+	return DWC3_GUSB2PHYACC_DATA(reg);
+}
+
+static int dwc3_ulpi_write(struct device *dev, u8 addr, u8 val)
+{
+	struct dwc3 *dwc = dev_get_drvdata(dev);
+	u32 reg;
+
+	reg = DWC3_GUSB2PHYACC_NEWREGREQ | DWC3_ULPI_ADDR(addr);
+	reg |= DWC3_GUSB2PHYACC_WRITE | val;
+	dwc3_writel(dwc, DWC3_GUSB2PHYACC(0), reg);
+
+	return dwc3_ulpi_busyloop(dwc, addr, false);
+}
+
+static const struct ulpi_ops dwc3_ulpi_ops = {
+	.read = dwc3_ulpi_read,
+	.write = dwc3_ulpi_write,
+};
+
+static void dwc3_ulpi_detect_config(struct dwc3 *dwc)
+{
+	struct ulpi *ulpi = dwc->ulpi;
+
+	switch (ulpi->id.vendor) {
+	case USB_VENDOR_MICROCHIP:
+		switch (ulpi->id.product) {
+		case 0x0009:
+			/* Microchip USB3340 ULPI PHY */
+			dwc->enable_usb2_transceiver_delay = true;
+			break;
+		default:
+			break;
+		}
+		break;
+	default:
+		break;
+	}
+}
+
+int dwc3_ulpi_init(struct dwc3 *dwc)
+{
+	/* Register the interface */
+	dwc->ulpi = ulpi_register_interface(dwc->dev, &dwc3_ulpi_ops);
+	if (IS_ERR(dwc->ulpi)) {
+		dev_err(dwc->dev, "failed to register ULPI interface");
+		return PTR_ERR(dwc->ulpi);
+	}
+
+	dwc3_ulpi_detect_config(dwc);
+
+	return 0;
+}
+
+void dwc3_ulpi_exit(struct dwc3 *dwc)
+{
+	if (dwc->ulpi) {
+		ulpi_unregister_interface(dwc->ulpi);
+		dwc->ulpi = NULL;
+	}
+}