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, 140 insertions, 0 deletions

diff --git a/fs/nfsd/stats.h b/fs/nfsd/stats.h
new file mode 100644
index 000000000..aabfbb1a9
--- /dev/null
+++ b/fs/nfsd/stats.h
@@ -0,0 +1,140 @@
+/* SPDX-License-Identifier: GPL-2.0 */
+/*
+ * Statistics for NFS server.
+ *
+ * Copyright (C) 1995, 1996 Olaf Kirch <okir@monad.swb.de>
+ */
+#ifndef _NFSD_STATS_H
+#define _NFSD_STATS_H
+
+#include <uapi/linux/nfsd/stats.h>
+#include <linux/percpu_counter.h>
+
+#include "export.h"
+#include "netns.h"
+
+struct proc_dir_entry *nfsd_proc_stat_init(struct net *net);
+void nfsd_proc_stat_shutdown(struct net *net);
+
+/**
+ * nfsd_stats_rc_hits_inc - Count a duplicate reply cache hit
+ * @nn: target network namespace
+ *
+ * These reply cache counters are updated once per RPC. Readers use
+ * percpu_counter_sum_positive(), so local batching does not affect
+ * read accuracy.
+ */
+static inline void nfsd_stats_rc_hits_inc(struct nfsd_net *nn)
+{
+	percpu_counter_add_local(&nn->counter[NFSD_STATS_RC_HITS], 1);
+}
+
+/**
+ * nfsd_stats_rc_misses_inc - Count a duplicate reply cache miss
+ * @nn: target network namespace
+ *
+ * See nfsd_stats_rc_hits_inc() for batching rationale.
+ */
+static inline void nfsd_stats_rc_misses_inc(struct nfsd_net *nn)
+{
+	percpu_counter_add_local(&nn->counter[NFSD_STATS_RC_MISSES], 1);
+}
+
+/**
+ * nfsd_stats_rc_nocache_inc - Count a request not cached in the reply cache
+ * @nn: target network namespace
+ *
+ * See nfsd_stats_rc_hits_inc() for batching rationale.
+ */
+static inline void nfsd_stats_rc_nocache_inc(struct nfsd_net *nn)
+{
+	percpu_counter_add_local(&nn->counter[NFSD_STATS_RC_NOCACHE], 1);
+}
+
+static inline void nfsd_stats_fh_stale_inc(struct nfsd_net *nn,
+					   struct svc_export *exp)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_FH_STALE]);
+	if (exp && exp->ex_stats)
+		percpu_counter_inc(&exp->ex_stats->counter[EXP_STATS_FH_STALE]);
+}
+
+/**
+ * nfsd_stats_io_read_add - Count number of bytes for an NFS READ
+ * @nn: target network namespace
+ * @exp: target export
+ * @amount: byte count
+ *
+ * These counters are updated on every READ request. Readers use
+ * percpu_counter_sum_positive(), so local batching does not affect
+ * read accuracy.
+ */
+static inline void nfsd_stats_io_read_add(struct nfsd_net *nn,
+					  struct svc_export *exp, s64 amount)
+{
+	percpu_counter_add_local(&nn->counter[NFSD_STATS_IO_READ], amount);
+	if (exp && exp->ex_stats)
+		percpu_counter_add_local(&exp->ex_stats->counter[EXP_STATS_IO_READ],
+					 amount);
+}
+
+/**
+ * nfsd_stats_io_write_add - Count number of bytes for an NFS WRITE
+ * @nn: target network namespace
+ * @exp: target export
+ * @amount: byte count
+ *
+ * These counters are updated on every WRITE request. Readers use
+ * percpu_counter_sum_positive(), so local batching does not affect
+ * read accuracy.
+ */
+static inline void nfsd_stats_io_write_add(struct nfsd_net *nn,
+					   struct svc_export *exp, s64 amount)
+{
+	percpu_counter_add_local(&nn->counter[NFSD_STATS_IO_WRITE], amount);
+	if (exp && exp->ex_stats)
+		percpu_counter_add_local(&exp->ex_stats->counter[EXP_STATS_IO_WRITE],
+					 amount);
+}
+
+static inline void nfsd_stats_payload_misses_inc(struct nfsd_net *nn)
+{
+	percpu_counter_inc(&nn->counter[NFSD_STATS_PAYLOAD_MISSES]);
+}
+
+/**
+ * nfsd_stats_drc_mem_usage_add - Add memory used by a cache item
+ * @nn: target network namespace
+ * @amount: byte count
+ *
+ * percpu_counter_add_local() keeps updates on the per-CPU fast
+ * path. The sole reader, percpu_counter_sum_positive(), sums the
+ * per-CPU deltas, so batching locally does not lose accuracy.
+ */
+static inline void nfsd_stats_drc_mem_usage_add(struct nfsd_net *nn, s64 amount)
+{
+	percpu_counter_add_local(&nn->counter[NFSD_STATS_DRC_MEM_USAGE],
+				 amount);
+}
+
+/**
+ * nfsd_stats_drc_mem_usage_sub - Subtract memory used by a cache item
+ * @nn: target network namespace
+ * @amount: byte count
+ *
+ * See nfsd_stats_drc_mem_usage_add() for batching rationale.
+ */
+static inline void nfsd_stats_drc_mem_usage_sub(struct nfsd_net *nn, s64 amount)
+{
+	percpu_counter_sub_local(&nn->counter[NFSD_STATS_DRC_MEM_USAGE],
+				 amount);
+}
+
+#ifdef CONFIG_NFSD_V4
+static inline void nfsd_stats_cb_op_inc(struct nfsd_net *nn, u32 opcode)
+{
+	if (opcode >= OP_CB_GETATTR && opcode <= OP_CB_OFFLOAD)
+		percpu_counter_inc(&nn->cb_counter[opcode]);
+}
+#endif
+#endif /* _NFSD_STATS_H */