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, 200 insertions, 0 deletions

diff --git a/net/mac80211/pm.c b/net/mac80211/pm.c
new file mode 100644
index 000000000..5a508d99e
--- /dev/null
+++ b/net/mac80211/pm.c
@@ -0,0 +1,200 @@
+// SPDX-License-Identifier: GPL-2.0
+/*
+ * Portions
+ * Copyright (C) 2020-2021, 2023-2024 Intel Corporation
+ */
+#include <net/mac80211.h>
+#include <net/rtnetlink.h>
+
+#include "ieee80211_i.h"
+#include "mesh.h"
+#include "driver-ops.h"
+#include "led.h"
+
+static void ieee80211_sched_scan_cancel(struct ieee80211_local *local)
+{
+	if (ieee80211_request_sched_scan_stop(local))
+		return;
+	cfg80211_sched_scan_stopped_locked(local->hw.wiphy, 0);
+}
+
+int __ieee80211_suspend(struct ieee80211_hw *hw, struct cfg80211_wowlan *wowlan)
+{
+	struct ieee80211_local *local = hw_to_local(hw);
+	struct ieee80211_sub_if_data *sdata;
+	struct sta_info *sta;
+
+	if (!local->open_count)
+		goto suspend;
+
+	local->suspending = true;
+	mb(); /* make suspending visible before any cancellation */
+
+	ieee80211_scan_cancel(local);
+
+	ieee80211_dfs_cac_cancel(local, NULL);
+
+	ieee80211_roc_purge(local, NULL);
+
+	ieee80211_del_virtual_monitor(local);
+
+	if (ieee80211_hw_check(hw, AMPDU_AGGREGATION) &&
+	    !(wowlan && wowlan->any)) {
+		lockdep_assert_wiphy(local->hw.wiphy);
+		list_for_each_entry(sta, &local->sta_list, list) {
+			set_sta_flag(sta, WLAN_STA_BLOCK_BA);
+			ieee80211_sta_tear_down_BA_sessions(
+					sta, AGG_STOP_LOCAL_REQUEST);
+		}
+	}
+
+	/* keep sched_scan only in case of 'any' trigger */
+	if (!(wowlan && wowlan->any))
+		ieee80211_sched_scan_cancel(local);
+
+	ieee80211_stop_queues_by_reason(hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_SUSPEND,
+					false);
+
+	/* flush out all packets */
+	synchronize_net();
+
+	ieee80211_flush_queues(local, NULL, true);
+
+	local->quiescing = true;
+	/* make quiescing visible to timers everywhere */
+	mb();
+
+	flush_workqueue(local->workqueue);
+
+	/* Don't try to run timers while suspended. */
+	timer_delete_sync(&local->sta_cleanup);
+
+	 /*
+	 * Note that this particular timer doesn't need to be
+	 * restarted at resume.
+	 */
+	wiphy_work_cancel(local->hw.wiphy, &local->dynamic_ps_enable_work);
+	timer_delete_sync(&local->dynamic_ps_timer);
+
+	local->wowlan = wowlan;
+	if (local->wowlan) {
+		int err;
+
+		/* Drivers don't expect to suspend while some operations like
+		 * authenticating or associating are in progress. It doesn't
+		 * make sense anyway to accept that, since the authentication
+		 * or association would never finish since the driver can't do
+		 * that on its own.
+		 * Thus, clean up in-progress auth/assoc first.
+		 */
+		list_for_each_entry(sdata, &local->interfaces, list) {
+			if (!ieee80211_sdata_running(sdata))
+				continue;
+			if (sdata->vif.type != NL80211_IFTYPE_STATION)
+				continue;
+			ieee80211_mgd_quiesce(sdata);
+			/* If suspended during TX in progress, and wowlan
+			 * is enabled (connection will be active) there
+			 * can be a race where the driver is put out
+			 * of power-save due to TX and during suspend
+			 * dynamic_ps_timer is cancelled and TX packet
+			 * is flushed, leaving the driver in ACTIVE even
+			 * after resuming until dynamic_ps_timer puts
+			 * driver back in DOZE.
+			 */
+			if (sdata->u.mgd.associated &&
+			    sdata->u.mgd.powersave &&
+			     !(local->hw.conf.flags & IEEE80211_CONF_PS)) {
+				local->hw.conf.flags |= IEEE80211_CONF_PS;
+				ieee80211_hw_config(local, -1,
+						    IEEE80211_CONF_CHANGE_PS);
+			}
+		}
+
+		err = drv_suspend(local, wowlan);
+		if (err < 0) {
+			local->quiescing = false;
+			local->wowlan = false;
+			if (ieee80211_hw_check(hw, AMPDU_AGGREGATION)) {
+				lockdep_assert_wiphy(local->hw.wiphy);
+				list_for_each_entry(sta,
+						    &local->sta_list, list) {
+					clear_sta_flag(sta, WLAN_STA_BLOCK_BA);
+				}
+			}
+			ieee80211_wake_queues_by_reason(hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_SUSPEND,
+					false);
+			return err;
+		} else if (err > 0) {
+			WARN_ON(err != 1);
+			/* cfg80211 will call back into mac80211 to disconnect
+			 * all interfaces, allow that to proceed properly
+			 */
+			ieee80211_wake_queues_by_reason(hw,
+					IEEE80211_MAX_QUEUE_MAP,
+					IEEE80211_QUEUE_STOP_REASON_SUSPEND,
+					false);
+			return err;
+		} else {
+			goto suspend;
+		}
+	}
+
+	/* remove all interfaces that were created in the driver */
+	list_for_each_entry(sdata, &local->interfaces, list) {
+		if (!ieee80211_sdata_running(sdata))
+			continue;
+		switch (sdata->vif.type) {
+		case NL80211_IFTYPE_AP_VLAN:
+		case NL80211_IFTYPE_MONITOR:
+			continue;
+		case NL80211_IFTYPE_STATION:
+			ieee80211_mgd_quiesce(sdata);
+			break;
+		default:
+			break;
+		}
+
+		wiphy_delayed_work_flush(local->hw.wiphy,
+					 &sdata->dec_tailroom_needed_wk);
+		drv_remove_interface(local, sdata);
+	}
+
+	/*
+	 * We disconnected on all interfaces before suspend, all channel
+	 * contexts should be released.
+	 */
+	WARN_ON(!list_empty(&local->chanctx_list));
+
+	/* stop hardware - this must stop RX */
+	ieee80211_stop_device(local, true);
+
+ suspend:
+	local->suspended = true;
+	/* need suspended to be visible before quiescing is false */
+	barrier();
+	local->quiescing = false;
+	local->suspending = false;
+
+	return 0;
+}
+
+/*
+ * __ieee80211_resume() is a static inline which just calls
+ * ieee80211_reconfig(), which is also needed for hardware
+ * hang/firmware failure/etc. recovery.
+ */
+
+void ieee80211_report_wowlan_wakeup(struct ieee80211_vif *vif,
+				    struct cfg80211_wowlan_wakeup *wakeup,
+				    gfp_t gfp)
+{
+	struct ieee80211_sub_if_data *sdata = vif_to_sdata(vif);
+
+	cfg80211_report_wowlan_wakeup(&sdata->wdev, wakeup, gfp);
+}
+EXPORT_SYMBOL(ieee80211_report_wowlan_wakeup);