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, 112 insertions, 0 deletions

diff --git a/net/mac80211/rate.h b/net/mac80211/rate.h
new file mode 100644
index 000000000..5e4bde598
--- /dev/null
+++ b/net/mac80211/rate.h
@@ -0,0 +1,112 @@
+/* SPDX-License-Identifier: GPL-2.0-only */
+/*
+ * Copyright 2002-2005, Instant802 Networks, Inc.
+ * Copyright 2005, Devicescape Software, Inc.
+ * Copyright (c) 2006 Jiri Benc <jbenc@suse.cz>
+ * Copyright (C) 2022, 2024 Intel Corporation
+ */
+
+#ifndef IEEE80211_RATE_H
+#define IEEE80211_RATE_H
+
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/types.h>
+#include <net/mac80211.h>
+#include "ieee80211_i.h"
+#include "sta_info.h"
+#include "driver-ops.h"
+
+struct rate_control_ref {
+	const struct rate_control_ops *ops;
+	void *priv;
+};
+
+void rate_control_get_rate(struct ieee80211_sub_if_data *sdata,
+			   struct sta_info *sta,
+			   struct ieee80211_tx_rate_control *txrc);
+
+void rate_control_tx_status(struct ieee80211_local *local,
+			    struct ieee80211_tx_status *st);
+
+void rate_control_rate_init(struct link_sta_info *link_sta);
+void rate_control_rate_init_all_links(struct sta_info *sta);
+void rate_control_rate_update(struct ieee80211_local *local,
+			      struct ieee80211_supported_band *sband,
+			      struct link_sta_info *link_sta,
+			      u32 changed);
+
+static inline void *rate_control_alloc_sta(struct rate_control_ref *ref,
+					   struct sta_info *sta, gfp_t gfp)
+{
+	spin_lock_init(&sta->rate_ctrl_lock);
+	return ref->ops->alloc_sta(ref->priv, &sta->sta, gfp);
+}
+
+static inline void rate_control_free_sta(struct sta_info *sta)
+{
+	struct rate_control_ref *ref = sta->rate_ctrl;
+	struct ieee80211_sta *ista = &sta->sta;
+	void *priv_sta = sta->rate_ctrl_priv;
+
+	ref->ops->free_sta(ref->priv, ista, priv_sta);
+}
+
+static inline void rate_control_add_sta_debugfs(struct sta_info *sta)
+{
+#ifdef CONFIG_MAC80211_DEBUGFS
+	struct rate_control_ref *ref = sta->rate_ctrl;
+	if (ref && sta->debugfs_dir && ref->ops->add_sta_debugfs)
+		ref->ops->add_sta_debugfs(ref->priv, sta->rate_ctrl_priv,
+					  sta->debugfs_dir);
+#endif
+}
+
+extern const struct debugfs_short_fops rcname_ops;
+
+static inline void rate_control_add_debugfs(struct ieee80211_local *local)
+{
+#ifdef CONFIG_MAC80211_DEBUGFS
+	struct dentry *debugfsdir;
+
+	if (!local->rate_ctrl)
+		return;
+
+	if (!local->rate_ctrl->ops->add_debugfs)
+		return;
+
+	debugfsdir = debugfs_create_dir("rc", local->hw.wiphy->debugfsdir);
+	local->debugfs.rcdir = debugfsdir;
+	debugfs_create_file("name", 0400, debugfsdir,
+			    local->rate_ctrl, &rcname_ops);
+
+	local->rate_ctrl->ops->add_debugfs(&local->hw, local->rate_ctrl->priv,
+					   debugfsdir);
+#endif
+}
+
+void ieee80211_check_rate_mask(struct ieee80211_link_data *link);
+
+/* Get a reference to the rate control algorithm. If `name' is NULL, get the
+ * first available algorithm. */
+int ieee80211_init_rate_ctrl_alg(struct ieee80211_local *local,
+				 const char *name);
+void rate_control_deinitialize(struct ieee80211_local *local);
+
+
+/* Rate control algorithms */
+#ifdef CONFIG_MAC80211_RC_MINSTREL
+int rc80211_minstrel_init(void);
+void rc80211_minstrel_exit(void);
+#else
+static inline int rc80211_minstrel_init(void)
+{
+	return 0;
+}
+static inline void rc80211_minstrel_exit(void)
+{
+}
+#endif
+
+
+#endif /* IEEE80211_RATE_H */