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, 94 insertions, 0 deletions

diff --git a/drivers/crypto/qce/common.h b/drivers/crypto/qce/common.h
new file mode 100644
index 000000000..9cd2e6ed8
--- /dev/null
+++ b/drivers/crypto/qce/common.h
@@ -0,0 +1,94 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright (c) 2010-2014, The Linux Foundation. All rights reserved.
+ */
+
+#ifndef _COMMON_H_
+#define _COMMON_H_
+
+#include <linux/crypto.h>
+#include <linux/types.h>
+#include <crypto/aes.h>
+#include <crypto/hash.h>
+#include <crypto/internal/skcipher.h>
+#include <crypto/internal/aead.h>
+
+/* xts du size */
+#define QCE_SECTOR_SIZE			512
+
+/* key size in bytes */
+#define QCE_SHA_HMAC_KEY_SIZE		64
+#define QCE_MAX_CIPHER_KEY_SIZE		AES_KEYSIZE_256
+
+/* IV length in bytes */
+#define QCE_AES_IV_LENGTH		AES_BLOCK_SIZE
+/* max of AES_BLOCK_SIZE */
+#define QCE_MAX_IV_SIZE			AES_BLOCK_SIZE
+
+/* maximum nonce bytes  */
+#define QCE_MAX_NONCE			16
+#define QCE_MAX_NONCE_WORDS		(QCE_MAX_NONCE / sizeof(u32))
+
+/* burst size alignment requirement */
+#define QCE_MAX_ALIGN_SIZE		64
+
+/* cipher algorithms */
+#define QCE_ALG_AES			BIT(2)
+
+/* hash and hmac algorithms */
+#define QCE_HASH_SHA256			BIT(4)
+#define QCE_HASH_SHA256_HMAC		BIT(6)
+#define QCE_HASH_AES_CMAC		BIT(7)
+
+/* cipher modes */
+#define QCE_MODE_CBC			BIT(8)
+#define QCE_MODE_ECB			BIT(9)
+#define QCE_MODE_CTR			BIT(10)
+#define QCE_MODE_XTS			BIT(11)
+#define QCE_MODE_CCM			BIT(12)
+#define QCE_MODE_MASK			GENMASK(12, 8)
+
+#define QCE_MODE_CCM_RFC4309		BIT(13)
+
+/* cipher encryption/decryption operations */
+#define QCE_ENCRYPT			BIT(30)
+#define QCE_DECRYPT			BIT(31)
+
+#define IS_AES(flags)			(flags & QCE_ALG_AES)
+
+#define IS_SHA256(flags)		(flags & QCE_HASH_SHA256)
+#define IS_SHA256_HMAC(flags)		(flags & QCE_HASH_SHA256_HMAC)
+#define IS_CMAC(flags)			(flags & QCE_HASH_AES_CMAC)
+#define IS_SHA(flags)			IS_SHA256(flags)
+#define IS_SHA_HMAC(flags)		IS_SHA256_HMAC(flags)
+
+#define IS_CBC(mode)			(mode & QCE_MODE_CBC)
+#define IS_CTR(mode)			(mode & QCE_MODE_CTR)
+#define IS_XTS(mode)			(mode & QCE_MODE_XTS)
+#define IS_CCM(mode)			(mode & QCE_MODE_CCM)
+#define IS_CCM_RFC4309(mode)		((mode) & QCE_MODE_CCM_RFC4309)
+
+#define IS_ENCRYPT(dir)			(dir & QCE_ENCRYPT)
+#define IS_DECRYPT(dir)			(dir & QCE_DECRYPT)
+
+struct qce_alg_template {
+	struct list_head entry;
+	u32 crypto_alg_type;
+	unsigned long alg_flags;
+	const u32 *std_iv;
+	union {
+		struct skcipher_alg skcipher;
+		struct ahash_alg ahash;
+		struct aead_alg aead;
+	} alg;
+	struct qce_device *qce;
+	const u8 *hash_zero;
+	const u32 digest_size;
+};
+
+void qce_cpu_to_be32p_array(__be32 *dst, const u8 *src, unsigned int len);
+int qce_check_status(struct qce_device *qce, u32 *status);
+void qce_get_version(struct qce_device *qce, u32 *major, u32 *minor, u32 *step);
+int qce_start(struct crypto_async_request *async_req, u32 type);
+
+#endif /* _COMMON_H_ */