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, 101 insertions, 0 deletions

diff --git a/drivers/dma/dw/internal.h b/drivers/dma/dw/internal.h
new file mode 100644
index 000000000..f1bd06a20
--- /dev/null
+++ b/drivers/dma/dw/internal.h
@@ -0,0 +1,101 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Driver for the Synopsys DesignWare DMA Controller
+ *
+ * Copyright (C) 2013 Intel Corporation
+ */
+
+#ifndef _DMA_DW_INTERNAL_H
+#define _DMA_DW_INTERNAL_H
+
+#include <linux/dma/dw.h>
+
+#include "regs.h"
+
+int do_dma_probe(struct dw_dma_chip *chip);
+int do_dma_remove(struct dw_dma_chip *chip);
+
+void do_dw_dma_on(struct dw_dma *dw);
+void do_dw_dma_off(struct dw_dma *dw);
+
+int do_dw_dma_disable(struct dw_dma_chip *chip);
+int do_dw_dma_enable(struct dw_dma_chip *chip);
+
+extern bool dw_dma_filter(struct dma_chan *chan, void *param);
+
+#ifdef CONFIG_ACPI
+void dw_dma_acpi_controller_register(struct dw_dma *dw);
+void dw_dma_acpi_controller_free(struct dw_dma *dw);
+#else /* !CONFIG_ACPI */
+static inline void dw_dma_acpi_controller_register(struct dw_dma *dw) {}
+static inline void dw_dma_acpi_controller_free(struct dw_dma *dw) {}
+#endif /* !CONFIG_ACPI */
+
+struct platform_device;
+
+#ifdef CONFIG_OF
+struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev);
+void dw_dma_of_controller_register(struct dw_dma *dw);
+void dw_dma_of_controller_free(struct dw_dma *dw);
+#else
+static inline struct dw_dma_platform_data *dw_dma_parse_dt(struct platform_device *pdev)
+{
+	return NULL;
+}
+static inline void dw_dma_of_controller_register(struct dw_dma *dw) {}
+static inline void dw_dma_of_controller_free(struct dw_dma *dw) {}
+#endif
+
+struct dw_dma_chip_pdata {
+	const struct dw_dma_platform_data *pdata;
+	int (*probe)(struct dw_dma_chip *chip);
+	int (*remove)(struct dw_dma_chip *chip);
+	struct dw_dma_chip *chip;
+	u8 m_master;
+	u8 p_master;
+};
+
+static __maybe_unused const struct dw_dma_chip_pdata dw_dma_chip_pdata = {
+	.probe = dw_dma_probe,
+	.remove = dw_dma_remove,
+	.m_master = 0,
+	.p_master = 1,
+};
+
+static const struct dw_dma_platform_data idma32_pdata = {
+	.nr_channels = 8,
+	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
+	.chan_priority = CHAN_PRIORITY_ASCENDING,
+	.block_size = 131071,
+	.nr_masters = 1,
+	.data_width = {4},
+	.multi_block = {1, 1, 1, 1, 1, 1, 1, 1},
+};
+
+static __maybe_unused const struct dw_dma_chip_pdata idma32_chip_pdata = {
+	.pdata = &idma32_pdata,
+	.probe = idma32_dma_probe,
+	.remove = idma32_dma_remove,
+	.m_master = 0,
+	.p_master = 0,
+};
+
+static const struct dw_dma_platform_data xbar_pdata = {
+	.nr_channels = 8,
+	.chan_allocation_order = CHAN_ALLOCATION_ASCENDING,
+	.chan_priority = CHAN_PRIORITY_ASCENDING,
+	.block_size = 131071,
+	.nr_masters = 1,
+	.data_width = {4},
+	.quirks = DW_DMA_QUIRK_XBAR_PRESENT,
+};
+
+static __maybe_unused const struct dw_dma_chip_pdata xbar_chip_pdata = {
+	.pdata = &xbar_pdata,
+	.probe = idma32_dma_probe,
+	.remove = idma32_dma_remove,
+	.m_master = 0,
+	.p_master = 0,
+};
+
+#endif /* _DMA_DW_INTERNAL_H */