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, 148 insertions, 0 deletions

diff --git a/net/ieee802154/netlink.c b/net/ieee802154/netlink.c
new file mode 100644
index 000000000..cacad2134
--- /dev/null
+++ b/net/ieee802154/netlink.c
@@ -0,0 +1,148 @@
+// SPDX-License-Identifier: GPL-2.0-only
+/*
+ * Netlink interface for IEEE 802.15.4 stack
+ *
+ * Copyright 2007, 2008 Siemens AG
+ *
+ * Written by:
+ * Sergey Lapin <slapin@ossfans.org>
+ * Dmitry Eremin-Solenikov <dbaryshkov@gmail.com>
+ * Maxim Osipov <maxim.osipov@siemens.com>
+ */
+
+#include <linux/kernel.h>
+#include <linux/gfp.h>
+#include <net/genetlink.h>
+#include <linux/nl802154.h>
+
+#include "ieee802154.h"
+
+static unsigned int ieee802154_seq_num;
+static DEFINE_SPINLOCK(ieee802154_seq_lock);
+
+/* Requests to userspace */
+struct sk_buff *ieee802154_nl_create(int flags, u8 req)
+{
+	void *hdr;
+	struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+	unsigned long f;
+
+	if (!msg)
+		return NULL;
+
+	spin_lock_irqsave(&ieee802154_seq_lock, f);
+	hdr = genlmsg_put(msg, 0, ieee802154_seq_num++,
+			  &nl802154_family, flags, req);
+	spin_unlock_irqrestore(&ieee802154_seq_lock, f);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return NULL;
+	}
+
+	return msg;
+}
+
+int ieee802154_nl_mcast(struct sk_buff *msg, unsigned int group)
+{
+	struct nlmsghdr *nlh = nlmsg_hdr(msg);
+	void *hdr = genlmsg_data(nlmsg_data(nlh));
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_multicast(&nl802154_family, msg, 0, group, GFP_ATOMIC);
+}
+
+struct sk_buff *ieee802154_nl_new_reply(struct genl_info *info,
+					int flags, u8 req)
+{
+	void *hdr;
+	struct sk_buff *msg = nlmsg_new(NLMSG_DEFAULT_SIZE, GFP_ATOMIC);
+
+	if (!msg)
+		return NULL;
+
+	hdr = genlmsg_put_reply(msg, info,
+				&nl802154_family, flags, req);
+	if (!hdr) {
+		nlmsg_free(msg);
+		return NULL;
+	}
+
+	return msg;
+}
+
+int ieee802154_nl_reply(struct sk_buff *msg, struct genl_info *info)
+{
+	struct nlmsghdr *nlh = nlmsg_hdr(msg);
+	void *hdr = genlmsg_data(nlmsg_data(nlh));
+
+	genlmsg_end(msg, hdr);
+
+	return genlmsg_reply(msg, info);
+}
+
+static const struct genl_small_ops ieee802154_ops[] = {
+	/* see nl-phy.c */
+	IEEE802154_DUMP(IEEE802154_LIST_PHY, ieee802154_list_phy,
+			ieee802154_dump_phy),
+	IEEE802154_OP(IEEE802154_ADD_IFACE, ieee802154_add_iface),
+	IEEE802154_OP(IEEE802154_DEL_IFACE, ieee802154_del_iface),
+	/* see nl-mac.c */
+	IEEE802154_OP(IEEE802154_ASSOCIATE_REQ, ieee802154_associate_req),
+	IEEE802154_OP(IEEE802154_ASSOCIATE_RESP, ieee802154_associate_resp),
+	IEEE802154_OP(IEEE802154_DISASSOCIATE_REQ, ieee802154_disassociate_req),
+	IEEE802154_OP(IEEE802154_SCAN_REQ, ieee802154_scan_req),
+	IEEE802154_OP(IEEE802154_START_REQ, ieee802154_start_req),
+	IEEE802154_DUMP(IEEE802154_LIST_IFACE, ieee802154_list_iface,
+			ieee802154_dump_iface),
+	IEEE802154_OP(IEEE802154_SET_MACPARAMS, ieee802154_set_macparams),
+	IEEE802154_OP(IEEE802154_LLSEC_GETPARAMS, ieee802154_llsec_getparams),
+	IEEE802154_OP(IEEE802154_LLSEC_SETPARAMS, ieee802154_llsec_setparams),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_KEY, NULL,
+			     ieee802154_llsec_dump_keys),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_KEY, ieee802154_llsec_add_key),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_KEY, ieee802154_llsec_del_key),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_DEV, NULL,
+			     ieee802154_llsec_dump_devs),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_DEV, ieee802154_llsec_add_dev),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_DEV, ieee802154_llsec_del_dev),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_DEVKEY, NULL,
+			     ieee802154_llsec_dump_devkeys),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_DEVKEY, ieee802154_llsec_add_devkey),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_DEVKEY, ieee802154_llsec_del_devkey),
+	IEEE802154_DUMP_PRIV(IEEE802154_LLSEC_LIST_SECLEVEL, NULL,
+			     ieee802154_llsec_dump_seclevels),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_ADD_SECLEVEL,
+			      ieee802154_llsec_add_seclevel),
+	IEEE802154_OP_RELAXED(IEEE802154_LLSEC_DEL_SECLEVEL,
+			      ieee802154_llsec_del_seclevel),
+};
+
+static const struct genl_multicast_group ieee802154_mcgrps[] = {
+	[IEEE802154_COORD_MCGRP] = { .name = IEEE802154_MCAST_COORD_NAME, },
+	[IEEE802154_BEACON_MCGRP] = { .name = IEEE802154_MCAST_BEACON_NAME, },
+};
+
+struct genl_family nl802154_family __ro_after_init = {
+	.hdrsize	= 0,
+	.name		= IEEE802154_NL_NAME,
+	.version	= 1,
+	.maxattr	= IEEE802154_ATTR_MAX,
+	.policy		= ieee802154_policy,
+	.module		= THIS_MODULE,
+	.small_ops	= ieee802154_ops,
+	.n_small_ops	= ARRAY_SIZE(ieee802154_ops),
+	.resv_start_op	= IEEE802154_LLSEC_DEL_SECLEVEL + 1,
+	.mcgrps		= ieee802154_mcgrps,
+	.n_mcgrps	= ARRAY_SIZE(ieee802154_mcgrps),
+};
+
+int __init ieee802154_nl_init(void)
+{
+	return genl_register_family(&nl802154_family);
+}
+
+void ieee802154_nl_exit(void)
+{
+	genl_unregister_family(&nl802154_family);
+}