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

3 files changed, 199 insertions, 0 deletions

diff --git a/net/ife/Kconfig b/net/ife/Kconfig
new file mode 100644
index 000000000..de36a5b91
--- /dev/null
+++ b/net/ife/Kconfig
@@ -0,0 +1,16 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# IFE subsystem configuration
+#
+
+menuconfig NET_IFE
+	tristate "Inter-FE based on IETF ForCES InterFE LFB"
+	default n
+	help
+	  Say Y here to add support of IFE encapsulation protocol
+	  For details refer to netdev01 paper:
+	  "Distributing Linux Traffic Control Classifier-Action Subsystem"
+	   Authors: Jamal Hadi Salim and Damascene M. Joachimpillai
+
+	  To compile this support as a module, choose M here: the module will
+	  be called ife.
diff --git a/net/ife/Makefile b/net/ife/Makefile
new file mode 100644
index 000000000..1258fcb07
--- /dev/null
+++ b/net/ife/Makefile
@@ -0,0 +1,6 @@
+# SPDX-License-Identifier: GPL-2.0-only
+#
+# Makefile for the IFE encapsulation protocol
+#
+
+obj-$(CONFIG_NET_IFE) += ife.o
diff --git a/net/ife/ife.c b/net/ife/ife.c
new file mode 100644
index 000000000..2ddf725d3
--- /dev/null
+++ b/net/ife/ife.c
@@ -0,0 +1,177 @@
+/*
+ * net/ife/ife.c - Inter-FE protocol based on ForCES WG InterFE LFB
+ * Copyright (c) 2015 Jamal Hadi Salim <jhs@mojatatu.com>
+ * Copyright (c) 2017 Yotam Gigi <yotamg@mellanox.com>
+ *
+ * Refer to: draft-ietf-forces-interfelfb-03 and netdev01 paper:
+ * "Distributing Linux Traffic Control Classifier-Action Subsystem"
+ * Authors: Jamal Hadi Salim and Damascene M. Joachimpillai
+ *
+ * This program is free software; you can redistribute it and/or modify
+ * it under the terms of the GNU General Public License as published by
+ * the Free Software Foundation.
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/module.h>
+#include <linux/init.h>
+#include <net/net_namespace.h>
+#include <net/netlink.h>
+#include <net/pkt_sched.h>
+#include <linux/etherdevice.h>
+#include <net/ife.h>
+
+struct ifeheadr {
+	__be16 metalen;
+	u8 tlv_data[];
+};
+
+void *ife_encode(struct sk_buff *skb, u16 metalen)
+{
+	/* OUTERHDR:TOTMETALEN:{TLVHDR:Metadatum:TLVHDR..}:ORIGDATA
+	 * where ORIGDATA = original ethernet header ...
+	 */
+	int hdrm = metalen + IFE_METAHDRLEN;
+	int total_push = hdrm + ETH_HLEN;
+	struct ifeheadr *ifehdr;
+	struct ethhdr *iethh;	/* inner ether header */
+	int skboff = 0;
+	int err;
+
+	err = skb_cow_head(skb, total_push);
+	if (unlikely(err))
+		return NULL;
+
+	iethh = (struct ethhdr *) skb->data;
+
+	__skb_push(skb, total_push);
+	memcpy(skb->data, iethh, ETH_HLEN);
+	skb_reset_mac_header(skb);
+	skboff += ETH_HLEN;
+
+	/* total metadata length */
+	ifehdr = (struct ifeheadr *) (skb->data + skboff);
+	metalen += IFE_METAHDRLEN;
+	ifehdr->metalen = htons(metalen);
+
+	return ifehdr->tlv_data;
+}
+EXPORT_SYMBOL_GPL(ife_encode);
+
+void *ife_decode(struct sk_buff *skb, u16 *metalen)
+{
+	struct ifeheadr *ifehdr;
+	int total_pull;
+	u16 ifehdrln;
+
+	if (!pskb_may_pull(skb, ETH_HLEN + IFE_METAHDRLEN))
+		return NULL;
+
+	ifehdr = (struct ifeheadr *)(skb->data + ETH_HLEN);
+	ifehdrln = ntohs(ifehdr->metalen);
+	total_pull = ETH_HLEN + ifehdrln;
+
+	if (unlikely(ifehdrln < 2))
+		return NULL;
+
+	if (unlikely(!pskb_may_pull(skb, total_pull + ETH_HLEN)))
+		return NULL;
+
+	ifehdr = (struct ifeheadr *)(skb->data + ETH_HLEN);
+	skb_set_mac_header(skb, total_pull);
+	__skb_pull(skb, total_pull);
+	*metalen = ifehdrln - IFE_METAHDRLEN;
+
+	return &ifehdr->tlv_data;
+}
+EXPORT_SYMBOL_GPL(ife_decode);
+
+struct meta_tlvhdr {
+	__be16 type;
+	__be16 len;
+};
+
+static bool __ife_tlv_meta_valid(const unsigned char *skbdata,
+				 const unsigned char *ifehdr_end)
+{
+	const struct meta_tlvhdr *tlv;
+	u16 tlvlen;
+
+	if (unlikely(skbdata + sizeof(*tlv) > ifehdr_end))
+		return false;
+
+	tlv = (const struct meta_tlvhdr *)skbdata;
+	tlvlen = ntohs(tlv->len);
+
+	/* tlv length field is inc header, check on minimum */
+	if (tlvlen < NLA_HDRLEN)
+		return false;
+
+	/* overflow by NLA_ALIGN check */
+	if (NLA_ALIGN(tlvlen) < tlvlen)
+		return false;
+
+	if (unlikely(skbdata + NLA_ALIGN(tlvlen) > ifehdr_end))
+		return false;
+
+	return true;
+}
+
+/* Caller takes care of presenting data in network order
+ */
+void *ife_tlv_meta_decode(void *skbdata, const void *ifehdr_end, u16 *attrtype,
+			  u16 *dlen, u16 *totlen)
+{
+	struct meta_tlvhdr *tlv;
+
+	if (!__ife_tlv_meta_valid(skbdata, ifehdr_end))
+		return NULL;
+
+	tlv = (struct meta_tlvhdr *)skbdata;
+	*dlen = ntohs(tlv->len) - NLA_HDRLEN;
+	*attrtype = ntohs(tlv->type);
+
+	if (totlen)
+		*totlen = nla_total_size(*dlen);
+
+	return skbdata + sizeof(struct meta_tlvhdr);
+}
+EXPORT_SYMBOL_GPL(ife_tlv_meta_decode);
+
+void *ife_tlv_meta_next(void *skbdata)
+{
+	struct meta_tlvhdr *tlv = (struct meta_tlvhdr *) skbdata;
+	u16 tlvlen = ntohs(tlv->len);
+
+	tlvlen = NLA_ALIGN(tlvlen);
+
+	return skbdata + tlvlen;
+}
+EXPORT_SYMBOL_GPL(ife_tlv_meta_next);
+
+/* Caller takes care of presenting data in network order
+ */
+int ife_tlv_meta_encode(void *skbdata, u16 attrtype, u16 dlen, const void *dval)
+{
+	__be32 *tlv = (__be32 *) (skbdata);
+	u16 totlen = nla_total_size(dlen);	/*alignment + hdr */
+	char *dptr = (char *) tlv + NLA_HDRLEN;
+	u32 htlv = attrtype << 16 | (dlen + NLA_HDRLEN);
+
+	*tlv = htonl(htlv);
+	memset(dptr, 0, totlen - NLA_HDRLEN);
+	memcpy(dptr, dval, dlen);
+
+	return totlen;
+}
+EXPORT_SYMBOL_GPL(ife_tlv_meta_encode);
+
+MODULE_AUTHOR("Jamal Hadi Salim <jhs@mojatatu.com>");
+MODULE_AUTHOR("Yotam Gigi <yotam.gi@gmail.com>");
+MODULE_DESCRIPTION("Inter-FE LFB action");
+MODULE_LICENSE("GPL");