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, 162 insertions, 0 deletions

diff --git a/arch/mips/lib/bitops.c b/arch/mips/lib/bitops.c
new file mode 100644
index 000000000..00aee98e9
--- /dev/null
+++ b/arch/mips/lib/bitops.c
@@ -0,0 +1,162 @@
+/*
+ * This file is subject to the terms and conditions of the GNU General Public
+ * License.  See the file "COPYING" in the main directory of this archive
+ * for more details.
+ *
+ * Copyright (c) 1994-1997, 99, 2000, 06, 07 Ralf Baechle (ralf@linux-mips.org)
+ * Copyright (c) 1999, 2000  Silicon Graphics, Inc.
+ */
+#include <linux/bitops.h>
+#include <linux/bits.h>
+#include <linux/irqflags.h>
+#include <linux/export.h>
+
+
+/**
+ * __mips_set_bit - Atomically set a bit in memory.  This is called by
+ * set_bit() if it cannot find a faster solution.
+ * @nr: the bit to set
+ * @addr: the address to start counting from
+ */
+void __mips_set_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
+	unsigned long mask;
+	unsigned long flags;
+
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	*a |= mask;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__mips_set_bit);
+
+
+/**
+ * __mips_clear_bit - Clears a bit in memory.  This is called by clear_bit() if
+ * it cannot find a faster solution.
+ * @nr: Bit to clear
+ * @addr: Address to start counting from
+ */
+void __mips_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
+	unsigned long mask;
+	unsigned long flags;
+
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	*a &= ~mask;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__mips_clear_bit);
+
+
+/**
+ * __mips_change_bit - Toggle a bit in memory.	This is called by change_bit()
+ * if it cannot find a faster solution.
+ * @nr: Bit to change
+ * @addr: Address to start counting from
+ */
+void __mips_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
+	unsigned long mask;
+	unsigned long flags;
+
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	*a ^= mask;
+	raw_local_irq_restore(flags);
+}
+EXPORT_SYMBOL(__mips_change_bit);
+
+
+/**
+ * __mips_test_and_set_bit_lock - Set a bit and return its old value.  This is
+ * called by test_and_set_bit_lock() if it cannot find a faster solution.
+ * @nr: Bit to set
+ * @addr: Address to count from
+ */
+int __mips_test_and_set_bit_lock(unsigned long nr,
+				 volatile unsigned long *addr)
+{
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
+	unsigned long mask;
+	unsigned long flags;
+	int res;
+
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	res = (mask & *a) != 0;
+	*a |= mask;
+	raw_local_irq_restore(flags);
+	return res;
+}
+EXPORT_SYMBOL(__mips_test_and_set_bit_lock);
+
+
+/**
+ * __mips_test_and_clear_bit - Clear a bit and return its old value.  This is
+ * called by test_and_clear_bit() if it cannot find a faster solution.
+ * @nr: Bit to clear
+ * @addr: Address to count from
+ */
+int __mips_test_and_clear_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
+	unsigned long mask;
+	unsigned long flags;
+	int res;
+
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	res = (mask & *a) != 0;
+	*a &= ~mask;
+	raw_local_irq_restore(flags);
+	return res;
+}
+EXPORT_SYMBOL(__mips_test_and_clear_bit);
+
+
+/**
+ * __mips_test_and_change_bit - Change a bit and return its old value.	This is
+ * called by test_and_change_bit() if it cannot find a faster solution.
+ * @nr: Bit to change
+ * @addr: Address to count from
+ */
+int __mips_test_and_change_bit(unsigned long nr, volatile unsigned long *addr)
+{
+	volatile unsigned long *a = &addr[BIT_WORD(nr)];
+	unsigned int bit = nr % BITS_PER_LONG;
+	unsigned long mask;
+	unsigned long flags;
+	int res;
+
+	mask = 1UL << bit;
+	raw_local_irq_save(flags);
+	res = (mask & *a) != 0;
+	*a ^= mask;
+	raw_local_irq_restore(flags);
+	return res;
+}
+EXPORT_SYMBOL(__mips_test_and_change_bit);
+
+bool __mips_xor_is_negative_byte(unsigned long mask,
+		volatile unsigned long *addr)
+{
+	unsigned long flags;
+	unsigned long data;
+
+	raw_local_irq_save(flags);
+	data = *addr;
+	*addr = data ^ mask;
+	raw_local_irq_restore(flags);
+
+	return (data & BIT(7)) != 0;
+}