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, 172 insertions, 0 deletions

diff --git a/net/ethtool/eee.c b/net/ethtool/eee.c
new file mode 100644
index 000000000..50d6fcd36
--- /dev/null
+++ b/net/ethtool/eee.c
@@ -0,0 +1,172 @@
+// SPDX-License-Identifier: GPL-2.0-only
+
+#include "bitset.h"
+#include "common.h"
+#include "netlink.h"
+
+struct eee_req_info {
+	struct ethnl_req_info		base;
+};
+
+struct eee_reply_data {
+	struct ethnl_reply_data		base;
+	struct ethtool_keee		eee;
+};
+
+#define EEE_REPDATA(__reply_base) \
+	container_of(__reply_base, struct eee_reply_data, base)
+
+const struct nla_policy ethnl_eee_get_policy[] = {
+	[ETHTOOL_A_EEE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
+};
+
+static int eee_prepare_data(const struct ethnl_req_info *req_base,
+			    struct ethnl_reply_data *reply_base,
+			    const struct genl_info *info)
+{
+	struct eee_reply_data *data = EEE_REPDATA(reply_base);
+	struct net_device *dev = reply_base->dev;
+	struct ethtool_keee *eee = &data->eee;
+	int ret;
+
+	if (!dev->ethtool_ops->get_eee)
+		return -EOPNOTSUPP;
+	ret = ethnl_ops_begin(dev);
+	if (ret < 0)
+		return ret;
+	ret = dev->ethtool_ops->get_eee(dev, eee);
+	ethnl_ops_complete(dev);
+
+	return ret;
+}
+
+static int eee_reply_size(const struct ethnl_req_info *req_base,
+			  const struct ethnl_reply_data *reply_base)
+{
+	bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS;
+	const struct eee_reply_data *data = EEE_REPDATA(reply_base);
+	const struct ethtool_keee *eee = &data->eee;
+	int len = 0;
+	int ret;
+
+	/* MODES_OURS */
+	ret = ethnl_bitset_size(eee->advertised, eee->supported,
+				__ETHTOOL_LINK_MODE_MASK_NBITS,
+				link_mode_names, compact);
+	if (ret < 0)
+		return ret;
+	len += ret;
+	/* MODES_PEERS */
+	ret = ethnl_bitset_size(eee->lp_advertised, NULL,
+				__ETHTOOL_LINK_MODE_MASK_NBITS,
+				link_mode_names, compact);
+	if (ret < 0)
+		return ret;
+	len += ret;
+
+	len += nla_total_size(sizeof(u8)) +	/* _EEE_ACTIVE */
+	       nla_total_size(sizeof(u8)) +	/* _EEE_ENABLED */
+	       nla_total_size(sizeof(u8)) +	/* _EEE_TX_LPI_ENABLED */
+	       nla_total_size(sizeof(u32));	/* _EEE_TX_LPI_TIMER */
+
+	return len;
+}
+
+static int eee_fill_reply(struct sk_buff *skb,
+			  const struct ethnl_req_info *req_base,
+			  const struct ethnl_reply_data *reply_base)
+{
+	bool compact = req_base->flags & ETHTOOL_FLAG_COMPACT_BITSETS;
+	const struct eee_reply_data *data = EEE_REPDATA(reply_base);
+	const struct ethtool_keee *eee = &data->eee;
+	int ret;
+
+	ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_OURS,
+			       eee->advertised, eee->supported,
+			       __ETHTOOL_LINK_MODE_MASK_NBITS,
+			       link_mode_names, compact);
+	if (ret < 0)
+		return ret;
+	ret = ethnl_put_bitset(skb, ETHTOOL_A_EEE_MODES_PEER,
+			       eee->lp_advertised, NULL,
+			       __ETHTOOL_LINK_MODE_MASK_NBITS,
+			       link_mode_names, compact);
+	if (ret < 0)
+		return ret;
+
+	if (nla_put_u8(skb, ETHTOOL_A_EEE_ACTIVE, eee->eee_active) ||
+	    nla_put_u8(skb, ETHTOOL_A_EEE_ENABLED, eee->eee_enabled) ||
+	    nla_put_u8(skb, ETHTOOL_A_EEE_TX_LPI_ENABLED,
+		       eee->tx_lpi_enabled) ||
+	    nla_put_u32(skb, ETHTOOL_A_EEE_TX_LPI_TIMER, eee->tx_lpi_timer))
+		return -EMSGSIZE;
+
+	return 0;
+}
+
+/* EEE_SET */
+
+const struct nla_policy ethnl_eee_set_policy[] = {
+	[ETHTOOL_A_EEE_HEADER]		=
+		NLA_POLICY_NESTED(ethnl_header_policy),
+	[ETHTOOL_A_EEE_MODES_OURS]	= { .type = NLA_NESTED },
+	[ETHTOOL_A_EEE_ENABLED]		= { .type = NLA_U8 },
+	[ETHTOOL_A_EEE_TX_LPI_ENABLED]	= { .type = NLA_U8 },
+	[ETHTOOL_A_EEE_TX_LPI_TIMER]	= { .type = NLA_U32 },
+};
+
+static int
+ethnl_set_eee_validate(struct ethnl_req_info *req_info, struct genl_info *info)
+{
+	const struct ethtool_ops *ops = req_info->dev->ethtool_ops;
+
+	return ops->get_eee && ops->set_eee ? 1 : -EOPNOTSUPP;
+}
+
+static int
+ethnl_set_eee(struct ethnl_req_info *req_info, struct genl_info *info)
+{
+	struct net_device *dev = req_info->dev;
+	struct nlattr **tb = info->attrs;
+	struct ethtool_keee eee = {};
+	bool mod = false;
+	int ret;
+
+	ret = dev->ethtool_ops->get_eee(dev, &eee);
+	if (ret < 0)
+		return ret;
+
+	ret = ethnl_update_bitset(eee.advertised,
+				  __ETHTOOL_LINK_MODE_MASK_NBITS,
+				  tb[ETHTOOL_A_EEE_MODES_OURS],
+				  link_mode_names, info->extack, &mod);
+	if (ret < 0)
+		return ret;
+	ethnl_update_bool(&eee.eee_enabled, tb[ETHTOOL_A_EEE_ENABLED], &mod);
+	ethnl_update_bool(&eee.tx_lpi_enabled, tb[ETHTOOL_A_EEE_TX_LPI_ENABLED],
+			  &mod);
+	ethnl_update_u32(&eee.tx_lpi_timer, tb[ETHTOOL_A_EEE_TX_LPI_TIMER],
+			 &mod);
+	if (!mod)
+		return 0;
+
+	ret = dev->ethtool_ops->set_eee(dev, &eee);
+	return ret < 0 ? ret : 1;
+}
+
+const struct ethnl_request_ops ethnl_eee_request_ops = {
+	.request_cmd		= ETHTOOL_MSG_EEE_GET,
+	.reply_cmd		= ETHTOOL_MSG_EEE_GET_REPLY,
+	.hdr_attr		= ETHTOOL_A_EEE_HEADER,
+	.req_info_size		= sizeof(struct eee_req_info),
+	.reply_data_size	= sizeof(struct eee_reply_data),
+
+	.prepare_data		= eee_prepare_data,
+	.reply_size		= eee_reply_size,
+	.fill_reply		= eee_fill_reply,
+
+	.set_validate		= ethnl_set_eee_validate,
+	.set			= ethnl_set_eee,
+	.set_ntf_cmd		= ETHTOOL_MSG_EEE_NTF,
+};