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, 139 insertions, 0 deletions

diff --git a/fs/nfsd/export.h b/fs/nfsd/export.h
new file mode 100644
index 000000000..d2b09cd76
--- /dev/null
+++ b/fs/nfsd/export.h
@@ -0,0 +1,139 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Copyright (C) 1995-1997 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef NFSD_EXPORT_H
+#define NFSD_EXPORT_H
+
+#include <linux/sunrpc/cache.h>
+#include <linux/percpu_counter.h>
+#include <uapi/linux/nfsd/export.h>
+#include <linux/nfs4.h>
+
+struct knfsd_fh;
+struct svc_fh;
+struct svc_rqst;
+
+/*
+ * FS Locations
+ */
+
+#define MAX_FS_LOCATIONS	128
+
+struct nfsd4_fs_location {
+	char *hosts; /* colon separated list of hosts */
+	char *path;  /* slash separated list of path components */
+};
+
+struct nfsd4_fs_locations {
+	uint32_t locations_count;
+	struct nfsd4_fs_location *locations;
+/* If we're not actually serving this data ourselves (only providing a
+ * list of replicas that do serve it) then we set "migrated": */
+	int migrated;
+};
+
+/*
+ * We keep an array of pseudoflavors with the export, in order from most
+ * to least preferred.  For the foreseeable future, we don't expect more
+ * than the eight pseudoflavors null, unix, krb5, krb5i, krb5p, skpm3,
+ * spkm3i, and spkm3p (and using all 8 at once should be rare).
+ */
+#define MAX_SECINFO_LIST	8
+#define EX_UUID_LEN		16
+
+struct exp_flavor_info {
+	u32	pseudoflavor;
+	u32	flags;
+};
+
+/* Per-export stats */
+enum {
+	EXP_STATS_FH_STALE,
+	EXP_STATS_IO_READ,
+	EXP_STATS_IO_WRITE,
+	EXP_STATS_COUNTERS_NUM
+};
+
+struct export_stats {
+	time64_t		start_time;
+	struct percpu_counter	counter[EXP_STATS_COUNTERS_NUM];
+};
+
+struct svc_export {
+	struct cache_head	h;
+	struct auth_domain *	ex_client;
+	int			ex_flags;
+	int			ex_fsid;
+	struct path		ex_path;
+	kuid_t			ex_anon_uid;
+	kgid_t			ex_anon_gid;
+	unsigned char *		ex_uuid; /* 16 byte fsid */
+	struct nfsd4_fs_locations ex_fslocs;
+	uint32_t		ex_nflavors;
+	struct exp_flavor_info	ex_flavors[MAX_SECINFO_LIST];
+	u32			ex_layout_types;
+	struct nfsd4_deviceid_map *ex_devid_map;
+	struct cache_detail	*cd;
+	struct rcu_head		ex_rcu;
+	unsigned long		ex_xprtsec_modes;
+	struct export_stats	*ex_stats;
+};
+
+/* an "export key" (expkey) maps a filehandlefragement to an
+ * svc_export for a given client.  There can be several per export,
+ * for the different fsid types.
+ */
+struct svc_expkey {
+	struct cache_head	h;
+
+	struct auth_domain *	ek_client;
+	u8			ek_fsidtype;
+	u32			ek_fsid[6];
+
+	struct path		ek_path;
+	struct rcu_head		ek_rcu;
+};
+
+#define EX_ISSYNC(exp)		(!((exp)->ex_flags & NFSEXP_ASYNC))
+#define EX_NOHIDE(exp)		((exp)->ex_flags & NFSEXP_NOHIDE)
+#define EX_WGATHER(exp)		((exp)->ex_flags & NFSEXP_GATHERED_WRITES)
+
+struct svc_cred;
+int nfsexp_flags(struct svc_cred *cred, struct svc_export *exp);
+__be32 check_xprtsec_policy(struct svc_export *exp, struct svc_rqst *rqstp);
+__be32 check_security_flavor(struct svc_export *exp, struct svc_rqst *rqstp,
+			     bool may_bypass_gss);
+__be32 check_nfsd_access(struct svc_export *exp, struct svc_rqst *rqstp,
+			 bool may_bypass_gss);
+
+/*
+ * Function declarations
+ */
+int			nfsd_export_init(struct net *);
+void			nfsd_export_shutdown(struct net *);
+void			nfsd_export_flush(struct net *);
+struct svc_export *	rqst_exp_get_by_name(struct svc_rqst *,
+					     const struct path *);
+struct svc_export *	rqst_exp_parent(struct svc_rqst *,
+					struct path *);
+struct svc_export *	rqst_find_fsidzero_export(struct svc_rqst *);
+int			exp_rootfh(struct net *, struct auth_domain *,
+					char *path, struct knfsd_fh *, int maxsize);
+__be32			exp_pseudoroot(struct svc_rqst *, struct svc_fh *);
+
+static inline void exp_put(struct svc_export *exp)
+{
+	cache_put(&exp->h, exp->cd);
+}
+
+static inline struct svc_export *exp_get(struct svc_export *exp)
+{
+	cache_get(&exp->h);
+	return exp;
+}
+struct svc_export *rqst_exp_find(struct cache_req *reqp, struct net *net,
+				 struct auth_domain *cl, struct auth_domain *gsscl,
+				 int fsid_type, u32 *fsidv);
+
+#endif /* NFSD_EXPORT_H */