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/arch/riscv/mm/extable.c b/arch/riscv/mm/extable.c
new file mode 100644
index 000000000..dd1530af3
--- /dev/null
+++ b/arch/riscv/mm/extable.c
@@ -0,0 +1,102 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * Copyright (C) 2009 Sunplus Core Technology Co., Ltd.
+ *  Lennox Wu <lennox.wu@sunplusct.com>
+ *  Chen Liqin <liqin.chen@sunplusct.com>
+ * Copyright (C) 2013 Regents of the University of California
+ */
+
+
+#include <linux/bitfield.h>
+#include <linux/extable.h>
+#include <linux/module.h>
+#include <linux/uaccess.h>
+#include <asm/asm-extable.h>
+#include <asm/ptrace.h>
+
+static inline unsigned long
+get_ex_fixup(const struct exception_table_entry *ex)
+{
+	return ((unsigned long)&ex->fixup + ex->fixup);
+}
+
+static bool ex_handler_fixup(const struct exception_table_entry *ex,
+			     struct pt_regs *regs)
+{
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+static inline unsigned long regs_get_gpr(struct pt_regs *regs, unsigned int offset)
+{
+	if (unlikely(!offset || offset > MAX_REG_OFFSET))
+		return 0;
+
+	return *(unsigned long *)((unsigned long)regs + offset);
+}
+
+static inline void regs_set_gpr(struct pt_regs *regs, unsigned int offset,
+				unsigned long val)
+{
+	if (unlikely(offset > MAX_REG_OFFSET))
+		return;
+
+	if (offset)
+		*(unsigned long *)((unsigned long)regs + offset) = val;
+}
+
+static bool ex_handler_uaccess_err_zero(const struct exception_table_entry *ex,
+					struct pt_regs *regs)
+{
+	int reg_err = FIELD_GET(EX_DATA_REG_ERR, ex->data);
+	int reg_zero = FIELD_GET(EX_DATA_REG_ZERO, ex->data);
+
+	regs_set_gpr(regs, reg_err * sizeof(unsigned long), -EFAULT);
+	regs_set_gpr(regs, reg_zero * sizeof(unsigned long), 0);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+static bool
+ex_handler_load_unaligned_zeropad(const struct exception_table_entry *ex,
+				  struct pt_regs *regs)
+{
+	int reg_data = FIELD_GET(EX_DATA_REG_DATA, ex->data);
+	int reg_addr = FIELD_GET(EX_DATA_REG_ADDR, ex->data);
+	unsigned long data, addr, offset;
+
+	addr = regs_get_gpr(regs, reg_addr * sizeof(unsigned long));
+
+	offset = addr & 0x7UL;
+	addr &= ~0x7UL;
+
+	data = *(unsigned long *)addr >> (offset * 8);
+
+	regs_set_gpr(regs, reg_data * sizeof(unsigned long), data);
+
+	regs->epc = get_ex_fixup(ex);
+	return true;
+}
+
+bool fixup_exception(struct pt_regs *regs)
+{
+	const struct exception_table_entry *ex;
+
+	ex = search_exception_tables(regs->epc);
+	if (!ex)
+		return false;
+
+	switch (ex->type) {
+	case EX_TYPE_FIXUP:
+		return ex_handler_fixup(ex, regs);
+	case EX_TYPE_BPF:
+		return ex_handler_bpf(ex, regs);
+	case EX_TYPE_UACCESS_ERR_ZERO:
+		return ex_handler_uaccess_err_zero(ex, regs);
+	case EX_TYPE_LOAD_UNALIGNED_ZEROPAD:
+		return ex_handler_load_unaligned_zeropad(ex, regs);
+	}
+
+	BUG();
+}