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/clk/davinci/psc.h b/drivers/clk/davinci/psc.h
new file mode 100644
index 000000000..742672843
--- /dev/null
+++ b/drivers/clk/davinci/psc.h
@@ -0,0 +1,102 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Clock driver for TI Davinci PSC controllers
+ *
+ * Copyright (C) 2018 David Lechner <david@lechnology.com>
+ */
+
+#ifndef __CLK_DAVINCI_PSC_H__
+#define __CLK_DAVINCI_PSC_H__
+
+#include <linux/clk-provider.h>
+#include <linux/types.h>
+
+/* PSC quirk flags */
+#define LPSC_ALWAYS_ENABLED	BIT(0) /* never disable this clock */
+#define LPSC_SET_RATE_PARENT	BIT(1) /* propagate set_rate to parent clock */
+#define LPSC_FORCE		BIT(2) /* requires MDCTL FORCE bit */
+#define LPSC_LOCAL_RESET	BIT(3) /* acts as reset provider */
+
+struct davinci_lpsc_clkdev_info {
+	const char *con_id;
+	const char *dev_id;
+};
+
+#define LPSC_CLKDEV(c, d) {	\
+	.con_id = (c),		\
+	.dev_id = (d)		\
+}
+
+#define LPSC_CLKDEV1(n, c, d) \
+static const struct davinci_lpsc_clkdev_info n[] __initconst = {	\
+	LPSC_CLKDEV((c), (d)),						\
+	{ }								\
+}
+
+#define LPSC_CLKDEV2(n, c1, d1, c2, d2) \
+static const struct davinci_lpsc_clkdev_info n[] __initconst = {	\
+	LPSC_CLKDEV((c1), (d1)),					\
+	LPSC_CLKDEV((c2), (d2)),					\
+	{ }								\
+}
+
+#define LPSC_CLKDEV3(n, c1, d1, c2, d2, c3, d3) \
+static const struct davinci_lpsc_clkdev_info n[] __initconst = {	\
+	LPSC_CLKDEV((c1), (d1)),					\
+	LPSC_CLKDEV((c2), (d2)),					\
+	LPSC_CLKDEV((c3), (d3)),					\
+	{ }								\
+}
+
+/**
+ * davinci_lpsc_clk_info - LPSC module-specific clock information
+ * @name: the clock name
+ * @parent: the parent clock name
+ * @cdevs: optional array of clkdev lookup table info
+ * @md: the local module domain (LPSC id)
+ * @pd: the power domain id
+ * @flags: bitmask of LPSC_* flags
+ */
+struct davinci_lpsc_clk_info {
+	const char *name;
+	const char *parent;
+	const struct davinci_lpsc_clkdev_info *cdevs;
+	u32 md;
+	u32 pd;
+	unsigned long flags;
+};
+
+#define LPSC(m, d, n, p, c, f)	\
+{				\
+	.name	= #n,		\
+	.parent	= #p,		\
+	.cdevs	= (c),		\
+	.md	= (m),		\
+	.pd	= (d),		\
+	.flags	= (f),		\
+}
+
+int davinci_psc_register_clocks(struct device *dev,
+				const struct davinci_lpsc_clk_info *info,
+				u8 num_clks,
+				void __iomem *base);
+
+int of_davinci_psc_clk_init(struct device *dev,
+			    const struct davinci_lpsc_clk_info *info,
+			    u8 num_clks,
+			    void __iomem *base);
+
+/* Device-specific data */
+
+struct davinci_psc_init_data {
+	struct clk_bulk_data *parent_clks;
+	int num_parent_clks;
+	int (*psc_init)(struct device *dev, void __iomem *base);
+};
+
+extern const struct davinci_psc_init_data da850_psc0_init_data;
+extern const struct davinci_psc_init_data da850_psc1_init_data;
+extern const struct davinci_psc_init_data of_da850_psc0_init_data;
+extern const struct davinci_psc_init_data of_da850_psc1_init_data;
+
+#endif /* __CLK_DAVINCI_PSC_H__ */