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, 80 insertions, 0 deletions

diff --git a/drivers/i3c/internals.h b/drivers/i3c/internals.h
new file mode 100644
index 000000000..86a36b951
--- /dev/null
+++ b/drivers/i3c/internals.h
@@ -0,0 +1,80 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 2018 Cadence Design Systems Inc.
+ *
+ * Author: Boris Brezillon <boris.brezillon@bootlin.com>
+ */
+
+#ifndef I3C_INTERNALS_H
+#define I3C_INTERNALS_H
+
+#include <linux/i3c/master.h>
+#include <linux/io.h>
+
+int __must_check i3c_bus_rpm_get(struct i3c_bus *bus);
+void i3c_bus_rpm_put(struct i3c_bus *bus);
+bool i3c_bus_rpm_ibi_allowed(struct i3c_bus *bus);
+
+void i3c_bus_normaluse_lock(struct i3c_bus *bus);
+void i3c_bus_normaluse_unlock(struct i3c_bus *bus);
+
+int i3c_dev_setdasa_locked(struct i3c_dev_desc *dev);
+int i3c_dev_do_xfers_locked(struct i3c_dev_desc *dev,
+			    struct i3c_xfer *xfers,
+			    int nxfers, enum i3c_xfer_mode mode);
+int i3c_dev_disable_ibi_locked(struct i3c_dev_desc *dev);
+int i3c_dev_enable_ibi_locked(struct i3c_dev_desc *dev);
+int i3c_dev_request_ibi_locked(struct i3c_dev_desc *dev,
+			       const struct i3c_ibi_setup *req);
+void i3c_dev_free_ibi_locked(struct i3c_dev_desc *dev);
+
+/**
+ * i3c_writel_fifo - Write data buffer to 32bit FIFO
+ * @addr: FIFO Address to write to
+ * @buf: Pointer to the data bytes to write
+ * @nbytes: Number of bytes to write
+ */
+static inline void i3c_writel_fifo(void __iomem *addr, const void *buf,
+				   int nbytes)
+{
+	writesl(addr, buf, nbytes / 4);
+	if (nbytes & 3) {
+		u32 tmp = 0;
+
+		memcpy(&tmp, buf + (nbytes & ~3), nbytes & 3);
+		/*
+		 * writesl() instead of writel() to keep FIFO
+		 * byteorder on big-endian targets
+		 */
+		writesl(addr, &tmp, 1);
+	}
+}
+
+/**
+ * i3c_readl_fifo - Read data buffer from 32bit FIFO
+ * @addr: FIFO Address to read from
+ * @buf: Pointer to the buffer to store read bytes
+ * @nbytes: Number of bytes to read
+ */
+static inline void i3c_readl_fifo(const void __iomem *addr, void *buf,
+				  int nbytes)
+{
+	readsl(addr, buf, nbytes / 4);
+	if (nbytes & 3) {
+		u32 tmp;
+
+		/*
+		 * readsl() instead of readl() to keep FIFO
+		 * byteorder on big-endian targets
+		 */
+		readsl(addr, &tmp, 1);
+		memcpy(buf + (nbytes & ~3), &tmp, nbytes & 3);
+	}
+}
+
+static inline struct i3c_master_controller *i3c_bus_to_i3c_master(struct i3c_bus *i3cbus)
+{
+	return container_of(i3cbus, struct i3c_master_controller, bus);
+}
+
+#endif /* I3C_INTERNAL_H */