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, 364 insertions, 0 deletions

diff --git a/include/net/l3mdev.h b/include/net/l3mdev.h
new file mode 100644
index 000000000..710e98665
--- /dev/null
+++ b/include/net/l3mdev.h
@@ -0,0 +1,364 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+/*
+ * include/net/l3mdev.h - L3 master device API
+ * Copyright (c) 2015 Cumulus Networks
+ * Copyright (c) 2015 David Ahern <dsa@cumulusnetworks.com>
+ */
+#ifndef _NET_L3MDEV_H_
+#define _NET_L3MDEV_H_
+
+#include <net/dst.h>
+#include <net/fib_rules.h>
+
+enum l3mdev_type {
+	L3MDEV_TYPE_UNSPEC,
+	L3MDEV_TYPE_VRF,
+	__L3MDEV_TYPE_MAX
+};
+
+#define L3MDEV_TYPE_MAX (__L3MDEV_TYPE_MAX - 1)
+
+typedef int (*lookup_by_table_id_t)(struct net *net, u32 table_d);
+
+/**
+ * struct l3mdev_ops - l3mdev operations
+ *
+ * @l3mdev_fib_table: Get FIB table id to use for lookups
+ *
+ * @l3mdev_l3_rcv:    Hook in L3 receive path
+ *
+ * @l3mdev_l3_out:    Hook in L3 output path
+ *
+ * @l3mdev_link_scope_lookup: IPv6 lookup for linklocal and mcast destinations
+ */
+
+struct l3mdev_ops {
+	u32		(*l3mdev_fib_table)(const struct net_device *dev);
+	struct sk_buff * (*l3mdev_l3_rcv)(struct net_device *dev,
+					  struct sk_buff *skb, u16 proto);
+	struct sk_buff * (*l3mdev_l3_out)(struct net_device *dev,
+					  struct sock *sk, struct sk_buff *skb,
+					  u16 proto);
+
+	/* IPv6 ops */
+	struct dst_entry * (*l3mdev_link_scope_lookup)(const struct net_device *dev,
+						 struct flowi6 *fl6);
+};
+
+#ifdef CONFIG_NET_L3_MASTER_DEV
+
+int l3mdev_table_lookup_register(enum l3mdev_type l3type,
+				 lookup_by_table_id_t fn);
+
+void l3mdev_table_lookup_unregister(enum l3mdev_type l3type,
+				    lookup_by_table_id_t fn);
+
+int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net,
+				      u32 table_id);
+
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg);
+
+static inline
+bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex)
+{
+	return !(fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF) &&
+	       fl->flowi_l3mdev == iifindex;
+}
+
+static inline
+bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex)
+{
+	return fl->flowi_flags & FLOWI_FLAG_L3MDEV_OIF &&
+	       fl->flowi_l3mdev == oifindex;
+}
+
+void l3mdev_update_flow(struct net *net, struct flowi *fl);
+
+int l3mdev_master_ifindex_rcu(const struct net_device *dev);
+static inline int l3mdev_master_ifindex(struct net_device *dev)
+{
+	int ifindex;
+
+	rcu_read_lock();
+	ifindex = l3mdev_master_ifindex_rcu(dev);
+	rcu_read_unlock();
+
+	return ifindex;
+}
+
+static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+	int rc = 0;
+
+	if (ifindex) {
+		rcu_read_lock();
+
+		dev = dev_get_by_index_rcu(net, ifindex);
+		if (dev)
+			rc = l3mdev_master_ifindex_rcu(dev);
+
+		rcu_read_unlock();
+	}
+
+	return rc;
+}
+
+static inline
+struct net_device *l3mdev_master_dev_rcu(const struct net_device *_dev)
+{
+	/* netdev_master_upper_dev_get_rcu calls
+	 * list_first_or_null_rcu to walk the upper dev list.
+	 * list_first_or_null_rcu does not handle a const arg. We aren't
+	 * making changes, just want the master device from that list so
+	 * typecast to remove the const
+	 */
+	struct net_device *dev = (struct net_device *)_dev;
+	struct net_device *master;
+
+	if (!dev)
+		return NULL;
+
+	if (netif_is_l3_master(dev))
+		master = dev;
+	else if (netif_is_l3_slave(dev))
+		master = netdev_master_upper_dev_get_rcu(dev);
+	else
+		master = NULL;
+
+	return master;
+}
+
+int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex);
+static inline
+int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex)
+{
+	rcu_read_lock();
+	ifindex = l3mdev_master_upper_ifindex_by_index_rcu(net, ifindex);
+	rcu_read_unlock();
+
+	return ifindex;
+}
+
+u32 l3mdev_fib_table_rcu(const struct net_device *dev);
+u32 l3mdev_fib_table_by_index(struct net *net, int ifindex);
+static inline u32 l3mdev_fib_table(const struct net_device *dev)
+{
+	u32 tb_id;
+
+	rcu_read_lock();
+	tb_id = l3mdev_fib_table_rcu(dev);
+	rcu_read_unlock();
+
+	return tb_id;
+}
+
+static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
+{
+	struct net_device *dev;
+	bool rc = false;
+
+	if (ifindex == 0)
+		return false;
+
+	rcu_read_lock();
+
+	dev = dev_get_by_index_rcu(net, ifindex);
+	if (dev)
+		rc = netif_is_l3_master(dev);
+
+	rcu_read_unlock();
+
+	return rc;
+}
+
+struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6);
+
+static inline
+struct sk_buff *l3mdev_l3_rcv(struct sk_buff *skb, u16 proto)
+{
+	struct net_device *master = NULL;
+
+	if (netif_is_l3_slave(skb->dev))
+		master = netdev_master_upper_dev_get_rcu(skb->dev);
+	else if (netif_is_l3_master(skb->dev) ||
+		 netif_has_l3_rx_handler(skb->dev))
+		master = skb->dev;
+
+	if (master && master->l3mdev_ops->l3mdev_l3_rcv)
+		skb = master->l3mdev_ops->l3mdev_l3_rcv(master, skb, proto);
+
+	return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
+{
+	return l3mdev_l3_rcv(skb, AF_INET);
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
+{
+	return l3mdev_l3_rcv(skb, AF_INET6);
+}
+
+static inline
+struct sk_buff *l3mdev_l3_out(struct sock *sk, struct sk_buff *skb, u16 proto)
+{
+	struct net_device *dev;
+
+	rcu_read_lock();
+	dev = skb_dst_dev_rcu(skb);
+	if (netif_is_l3_slave(dev)) {
+		struct net_device *master;
+
+		master = netdev_master_upper_dev_get_rcu(dev);
+		if (master && master->l3mdev_ops->l3mdev_l3_out)
+			skb = master->l3mdev_ops->l3mdev_l3_out(master, sk,
+								skb, proto);
+	}
+	rcu_read_unlock();
+
+	return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb)
+{
+	return l3mdev_l3_out(sk, skb, AF_INET);
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb)
+{
+	return l3mdev_l3_out(sk, skb, AF_INET6);
+}
+#else
+
+static inline int l3mdev_master_ifindex_rcu(const struct net_device *dev)
+{
+	return 0;
+}
+static inline int l3mdev_master_ifindex(struct net_device *dev)
+{
+	return 0;
+}
+
+static inline int l3mdev_master_ifindex_by_index(struct net *net, int ifindex)
+{
+	return 0;
+}
+
+static inline
+int l3mdev_master_upper_ifindex_by_index_rcu(struct net *net, int ifindex)
+{
+	return 0;
+}
+static inline
+int l3mdev_master_upper_ifindex_by_index(struct net *net, int ifindex)
+{
+	return 0;
+}
+
+static inline
+struct net_device *l3mdev_master_dev_rcu(const struct net_device *dev)
+{
+	return NULL;
+}
+
+static inline u32 l3mdev_fib_table_rcu(const struct net_device *dev)
+{
+	return 0;
+}
+static inline u32 l3mdev_fib_table(const struct net_device *dev)
+{
+	return 0;
+}
+static inline u32 l3mdev_fib_table_by_index(struct net *net, int ifindex)
+{
+	return 0;
+}
+
+static inline bool netif_index_is_l3_master(struct net *net, int ifindex)
+{
+	return false;
+}
+
+static inline
+struct dst_entry *l3mdev_link_scope_lookup(struct net *net, struct flowi6 *fl6)
+{
+	return NULL;
+}
+
+static inline
+struct sk_buff *l3mdev_ip_rcv(struct sk_buff *skb)
+{
+	return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_rcv(struct sk_buff *skb)
+{
+	return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip_out(struct sock *sk, struct sk_buff *skb)
+{
+	return skb;
+}
+
+static inline
+struct sk_buff *l3mdev_ip6_out(struct sock *sk, struct sk_buff *skb)
+{
+	return skb;
+}
+
+static inline
+int l3mdev_table_lookup_register(enum l3mdev_type l3type,
+				 lookup_by_table_id_t fn)
+{
+	return -EOPNOTSUPP;
+}
+
+static inline
+void l3mdev_table_lookup_unregister(enum l3mdev_type l3type,
+				    lookup_by_table_id_t fn)
+{
+}
+
+static inline
+int l3mdev_ifindex_lookup_by_table_id(enum l3mdev_type l3type, struct net *net,
+				      u32 table_id)
+{
+	return -ENODEV;
+}
+
+static inline
+int l3mdev_fib_rule_match(struct net *net, struct flowi *fl,
+			  struct fib_lookup_arg *arg)
+{
+	return 1;
+}
+
+static inline
+bool l3mdev_fib_rule_iif_match(const struct flowi *fl, int iifindex)
+{
+	return false;
+}
+
+static inline
+bool l3mdev_fib_rule_oif_match(const struct flowi *fl, int oifindex)
+{
+	return false;
+}
+
+static inline
+void l3mdev_update_flow(struct net *net, struct flowi *fl)
+{
+}
+#endif
+
+#endif /* _NET_L3MDEV_H_ */