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, 147 insertions, 0 deletions

diff --git a/fs/smb/server/oplock.h b/fs/smb/server/oplock.h
new file mode 100644
index 000000000..b08d21758
--- /dev/null
+++ b/fs/smb/server/oplock.h
@@ -0,0 +1,147 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ *   Copyright (C) 2016 Namjae Jeon <linkinjeon@kernel.org>
+ *   Copyright (C) 2018 Samsung Electronics Co., Ltd.
+ */
+
+#ifndef __KSMBD_OPLOCK_H
+#define __KSMBD_OPLOCK_H
+
+#include "smb_common.h"
+
+#define OPLOCK_WAIT_TIME	(35 * HZ)
+
+/* Oplock states */
+#define OPLOCK_STATE_NONE	0x00
+#define OPLOCK_ACK_WAIT		0x01
+#define OPLOCK_CLOSING		0x02
+
+#define OPLOCK_WRITE_TO_READ		0x01
+#define OPLOCK_READ_HANDLE_TO_READ	0x02
+#define OPLOCK_WRITE_TO_NONE		0x04
+#define OPLOCK_READ_TO_NONE		0x08
+
+struct lease_ctx_info {
+	__u8			lease_key[SMB2_LEASE_KEY_SIZE];
+	__le32			req_state;
+	__le32			flags;
+	__le64			duration;
+	__u8			parent_lease_key[SMB2_LEASE_KEY_SIZE];
+	__le16			epoch;
+	int			version;
+	bool			is_dir;
+};
+
+struct lease_table {
+	char			client_guid[SMB2_CLIENT_GUID_SIZE];
+	struct ksmbd_conn	*conn;
+	struct list_head	lease_list;
+	struct list_head	l_entry;
+	spinlock_t		lb_lock;
+};
+
+struct lease {
+	__u8			lease_key[SMB2_LEASE_KEY_SIZE];
+	__le32			state;
+	__le32			new_state;
+	__le32			flags;
+	__le64			duration;
+	__u8			parent_lease_key[SMB2_LEASE_KEY_SIZE];
+	int			version;
+	unsigned short		epoch;
+	bool			is_dir;
+	bool			reuse_epoch;
+	struct ksmbd_inode	*ci;
+	struct lease_table	*l_lb;
+	struct list_head	l_entry;
+	struct list_head	open_list;
+	spinlock_t		lock;
+	atomic_t		refcount;
+};
+
+struct oplock_info {
+	struct ksmbd_conn	*conn;
+	struct ksmbd_session	*sess;
+	struct ksmbd_work	*work;
+	struct ksmbd_file	*o_fp;
+	int                     level;
+	int                     op_state;
+	spinlock_t		state_lock;
+	unsigned long		pending_break;
+	u64			fid;
+	atomic_t		breaking_cnt;
+	atomic_t		refcount;
+	__u16                   Tid;
+	bool			is_lease;
+	bool			open_trunc;	/* truncate on open */
+	struct lease		*o_lease;
+	struct list_head        op_entry;
+	struct list_head        lease_entry;
+	wait_queue_head_t	oplock_q; /* Other server threads */
+	wait_queue_head_t	oplock_brk; /* oplock breaking wait */
+	struct rcu_head		rcu;
+};
+
+struct lease_break_info {
+	__le32			curr_state;
+	__le32			new_state;
+	__le16			epoch;
+	char			lease_key[SMB2_LEASE_KEY_SIZE];
+};
+
+struct oplock_break_info {
+	int level;
+	int open_trunc;
+	int fid;
+};
+
+int smb_grant_oplock(struct ksmbd_work *work, int req_op_level,
+		     u64 pid, struct ksmbd_file *fp, __u16 tid,
+		     struct lease_ctx_info *lctx, int share_ret, bool replay);
+void smb_break_all_levII_oplock(struct ksmbd_work *work,
+					struct ksmbd_file *fp, int is_trunc);
+void smb_break_all_levII_oplock_rename(struct ksmbd_work *work, struct ksmbd_file *fp);
+void smb_break_all_levII_oplock_no_interim(struct ksmbd_work *work,
+					   struct ksmbd_file *fp, int is_trunc);
+void smb_break_all_levII_oplock_for_delete(struct ksmbd_work *work,
+					   struct ksmbd_file *fp);
+int opinfo_write_to_read(struct oplock_info *opinfo);
+int opinfo_read_handle_to_read(struct oplock_info *opinfo);
+int opinfo_write_to_none(struct oplock_info *opinfo);
+int opinfo_read_to_none(struct oplock_info *opinfo);
+void close_id_del_oplock(struct ksmbd_file *fp);
+void smb_break_all_oplock(struct ksmbd_work *work, struct ksmbd_file *fp);
+struct oplock_info *opinfo_get(struct ksmbd_file *fp);
+void opinfo_put(struct oplock_info *opinfo);
+
+/* Lease related functions */
+void create_lease_buf(u8 *rbuf, struct lease *lease);
+struct lease_ctx_info *parse_lease_state(void *open_req);
+__u8 smb2_map_lease_to_oplock(__le32 lease_state);
+void lease_update_oplock_levels(struct lease *lease);
+int lease_read_to_write(struct oplock_info *opinfo);
+
+/* Durable related functions */
+void create_durable_rsp_buf(char *cc);
+void create_durable_v2_rsp_buf(char *cc, struct ksmbd_file *fp);
+void create_mxac_rsp_buf(char *cc, int maximal_access);
+void create_disk_id_rsp_buf(char *cc, __u64 file_id, __u64 vol_id);
+void create_posix_rsp_buf(char *cc, struct ksmbd_file *fp);
+void create_aapl_rsp_buf(char *cc, __u64 vol_caps, __u64 req_bitmap,
+			 bool readdir_attr_v2);
+struct create_context *smb2_find_context_vals(void *open_req, const char *tag, int tag_len);
+struct oplock_info *lookup_lease_in_table(struct ksmbd_conn *conn,
+					  char *lease_key);
+int find_same_lease_key(struct ksmbd_conn *conn, struct ksmbd_inode *ci,
+			struct lease_ctx_info *lctx);
+void destroy_lease_table(struct ksmbd_conn *conn);
+void smb_send_parent_lease_break_noti(struct ksmbd_file *fp,
+				      struct lease_ctx_info *lctx);
+void smb_lazy_parent_lease_break_close(struct ksmbd_file *fp);
+int smb2_check_durable_oplock(struct ksmbd_conn *conn,
+			      struct ksmbd_share_config *share,
+			      struct ksmbd_file *fp,
+			      struct lease_ctx_info *lctx,
+			      struct ksmbd_user *user,
+			      char *name);
+#endif /* __KSMBD_OPLOCK_H */