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, 53 insertions, 0 deletions

diff --git a/net/ceph/crypto.h b/net/ceph/crypto.h
new file mode 100644
index 000000000..3a2ade15a
--- /dev/null
+++ b/net/ceph/crypto.h
@@ -0,0 +1,53 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+#ifndef _FS_CEPH_CRYPTO_H
+#define _FS_CEPH_CRYPTO_H
+
+#include <crypto/sha2.h>
+#include <linux/ceph/types.h>
+#include <linux/ceph/buffer.h>
+
+#define CEPH_MAX_KEY_LEN		32
+#define CEPH_MAX_CON_SECRET_LEN		64
+
+/*
+ * cryptographic secret
+ */
+struct ceph_crypto_key {
+	int type;
+	struct ceph_timespec created;
+	int len;
+	void *key;
+
+	union {
+		struct crypto_sync_skcipher *aes_tfm;
+		struct {
+			struct hmac_sha256_key hmac_key;
+			const struct krb5_enctype *krb5_type;
+			struct crypto_aead *krb5_tfms[3];
+		};
+	};
+};
+
+int ceph_crypto_key_prepare(struct ceph_crypto_key *key,
+			    const u32 *key_usages, int key_usage_cnt);
+int ceph_crypto_key_clone(struct ceph_crypto_key *dst,
+			  const struct ceph_crypto_key *src);
+int ceph_crypto_key_decode(struct ceph_crypto_key *key, void **p, void *end);
+int ceph_crypto_key_unarmor(struct ceph_crypto_key *key, const char *in);
+void ceph_crypto_key_destroy(struct ceph_crypto_key *key);
+
+/* crypto.c */
+int ceph_crypt(const struct ceph_crypto_key *key, int usage_slot, bool encrypt,
+	       void *buf, int buf_len, int in_len, int *pout_len);
+int ceph_crypt_data_offset(const struct ceph_crypto_key *key);
+int ceph_crypt_buflen(const struct ceph_crypto_key *key, int data_len);
+void ceph_hmac_sha256(const struct ceph_crypto_key *key, const void *buf,
+		      int buf_len, u8 hmac[SHA256_DIGEST_SIZE]);
+int ceph_crypto_init(void);
+void ceph_crypto_shutdown(void);
+
+/* armor.c */
+int ceph_armor(char *dst, const char *src, const char *end);
+int ceph_unarmor(char *dst, const char *src, const char *end);
+
+#endif