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, 71 insertions, 0 deletions

diff --git a/drivers/crypto/qce/sha.h b/drivers/crypto/qce/sha.h
new file mode 100644
index 000000000..cb822fc33
--- /dev/null
+++ b/drivers/crypto/qce/sha.h
@@ -0,0 +1,71 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _SHA_H_
+#define _SHA_H_
+
+#include <crypto/scatterwalk.h>
+#include <crypto/sha2.h>
+
+#include "common.h"
+#include "core.h"
+
+#define QCE_SHA_MAX_BLOCKSIZE		SHA256_BLOCK_SIZE
+#define QCE_SHA_MAX_DIGESTSIZE		SHA256_DIGEST_SIZE
+
+struct qce_sha_ctx {
+	u8 authkey[QCE_SHA_MAX_BLOCKSIZE];
+};
+
+/**
+ * struct qce_sha_reqctx - holds private ahash objects per request
+ * @buf: used during update, import and export
+ * @tmpbuf: buffer for internal use
+ * @digest: calculated digest buffer
+ * @buflen: length of the buffer
+ * @flags: operation flags
+ * @src_orig: original request sg list
+ * @nbytes_orig: original request number of bytes
+ * @src_nents: source number of entries
+ * @byte_count: byte count
+ * @count: save count in states during update, import and export
+ * @first_blk: is it the first block
+ * @last_blk: is it the last block
+ * @sg: used to chain sg lists
+ * @authkey: pointer to auth key in sha ctx
+ * @authklen: auth key length
+ * @result_sg: scatterlist used for result buffer
+ */
+struct qce_sha_reqctx {
+	u8 buf[QCE_SHA_MAX_BLOCKSIZE];
+	u8 tmpbuf[QCE_SHA_MAX_BLOCKSIZE];
+	u8 digest[QCE_SHA_MAX_DIGESTSIZE];
+	unsigned int buflen;
+	unsigned long flags;
+	struct scatterlist *src_orig;
+	unsigned int nbytes_orig;
+	int src_nents;
+	__be32 byte_count[2];
+	u64 count;
+	bool first_blk;
+	bool last_blk;
+	struct scatterlist sg[2];
+	u8 *authkey;
+	unsigned int authklen;
+	struct scatterlist result_sg;
+};
+
+static inline struct qce_alg_template *to_ahash_tmpl(struct crypto_tfm *tfm)
+{
+	struct crypto_ahash *ahash = __crypto_ahash_cast(tfm);
+	struct ahash_alg *alg = container_of(crypto_hash_alg_common(ahash),
+					     struct ahash_alg, halg);
+
+	return container_of(alg, struct qce_alg_template, alg.ahash);
+}
+
+extern const struct qce_algo_ops ahash_ops;
+
+#endif /* _SHA_H_ */