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, 70 insertions, 0 deletions

diff --git a/lib/crypto/chacha.c b/lib/crypto/chacha.c
new file mode 100644
index 000000000..86e5d382a
--- /dev/null
+++ b/lib/crypto/chacha.c
@@ -0,0 +1,70 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ * The ChaCha stream cipher (RFC7539)
+ *
+ * Copyright (C) 2015 Martin Willi
+ */
+
+#include <crypto/chacha.h>
+#include <crypto/utils.h>
+#include <linux/export.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+
+static void __maybe_unused
+chacha_crypt_generic(struct chacha_state *state, u8 *dst, const u8 *src,
+		     unsigned int bytes, int nrounds)
+{
+	/* aligned to potentially speed up crypto_xor() */
+	u8 stream[CHACHA_BLOCK_SIZE] __aligned(sizeof(long));
+
+	while (bytes >= CHACHA_BLOCK_SIZE) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, CHACHA_BLOCK_SIZE);
+		bytes -= CHACHA_BLOCK_SIZE;
+		dst += CHACHA_BLOCK_SIZE;
+		src += CHACHA_BLOCK_SIZE;
+	}
+	if (bytes) {
+		chacha_block_generic(state, stream, nrounds);
+		crypto_xor_cpy(dst, src, stream, bytes);
+	}
+}
+
+#ifdef CONFIG_CRYPTO_LIB_CHACHA_ARCH
+#include "chacha.h" /* $(SRCARCH)/chacha.h */
+#else
+#define chacha_crypt_arch chacha_crypt_generic
+#define hchacha_block_arch hchacha_block_generic
+#endif
+
+void chacha_crypt(struct chacha_state *state, u8 *dst, const u8 *src,
+		  unsigned int bytes, int nrounds)
+{
+	chacha_crypt_arch(state, dst, src, bytes, nrounds);
+}
+EXPORT_SYMBOL_GPL(chacha_crypt);
+
+void hchacha_block(const struct chacha_state *state,
+		   u32 out[HCHACHA_OUT_WORDS], int nrounds)
+{
+	hchacha_block_arch(state, out, nrounds);
+}
+EXPORT_SYMBOL_GPL(hchacha_block);
+
+#ifdef chacha_mod_init_arch
+static int __init chacha_mod_init(void)
+{
+	chacha_mod_init_arch();
+	return 0;
+}
+subsys_initcall(chacha_mod_init);
+
+static void __exit chacha_mod_exit(void)
+{
+}
+module_exit(chacha_mod_exit);
+#endif
+
+MODULE_DESCRIPTION("ChaCha stream cipher (RFC7539)");
+MODULE_LICENSE("GPL");