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, 287 insertions, 0 deletions

diff --git a/net/ipv4/gre_offload.c b/net/ipv4/gre_offload.c
new file mode 100644
index 000000000..5028c72d4
--- /dev/null
+++ b/net/ipv4/gre_offload.c
@@ -0,0 +1,287 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/*
+ *	IPV4 GSO/GRO offload support
+ *	Linux INET implementation
+ *
+ *	GRE GSO support
+ */
+
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <net/protocol.h>
+#include <net/gre.h>
+#include <net/gro.h>
+#include <net/gso.h>
+
+static struct sk_buff *gre_gso_segment(struct sk_buff *skb,
+				       netdev_features_t features)
+{
+	int tnl_hlen = skb_inner_mac_header(skb) - skb_transport_header(skb);
+	bool need_csum, offload_csum, gso_partial, need_ipsec;
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	u16 mac_offset = skb->mac_header;
+	__be16 protocol = skb->protocol;
+	u16 mac_len = skb->mac_len;
+	int gre_offset, outer_hlen;
+
+	if (!skb->encapsulation)
+		goto out;
+
+	if (unlikely(tnl_hlen < sizeof(struct gre_base_hdr)))
+		goto out;
+
+	if (unlikely(!pskb_may_pull(skb, tnl_hlen)))
+		goto out;
+
+	/* setup inner skb. */
+	skb->encapsulation = 0;
+	SKB_GSO_CB(skb)->encap_level = 0;
+	__skb_pull(skb, tnl_hlen);
+	skb_reset_mac_header(skb);
+	skb_set_network_header(skb, skb_inner_network_offset(skb));
+	skb->mac_len = skb_inner_network_offset(skb);
+	skb->protocol = skb->inner_protocol;
+
+	need_csum = !!(skb_shinfo(skb)->gso_type & SKB_GSO_GRE_CSUM);
+	skb->encap_hdr_csum = need_csum;
+
+	features &= skb->dev->hw_enc_features;
+	if (need_csum)
+		features &= ~NETIF_F_SCTP_CRC;
+
+	need_ipsec = skb_dst(skb) && dst_xfrm(skb_dst(skb));
+	/* Try to offload checksum if possible */
+	offload_csum = !!(need_csum && !need_ipsec &&
+			  (skb->dev->features & NETIF_F_HW_CSUM));
+
+	/* segment inner packet. */
+	segs = skb_mac_gso_segment(skb, features);
+	if (IS_ERR_OR_NULL(segs)) {
+		skb_gso_error_unwind(skb, protocol, tnl_hlen, mac_offset,
+				     mac_len);
+		goto out;
+	}
+
+	gso_partial = !!(skb_shinfo(segs)->gso_type & SKB_GSO_PARTIAL);
+
+	outer_hlen = skb_tnl_header_len(skb);
+	gre_offset = outer_hlen - tnl_hlen;
+	skb = segs;
+	do {
+		struct gre_base_hdr *greh;
+		__sum16 *pcsum;
+
+		/* Set up inner headers if we are offloading inner checksum */
+		if (skb->ip_summed == CHECKSUM_PARTIAL) {
+			skb_reset_inner_headers(skb);
+			skb->encapsulation = 1;
+		}
+
+		skb->mac_len = mac_len;
+		skb->protocol = protocol;
+
+		__skb_push(skb, outer_hlen);
+		skb_reset_mac_header(skb);
+		skb_set_network_header(skb, mac_len);
+		skb_set_transport_header(skb, gre_offset);
+
+		if (!need_csum)
+			continue;
+
+		greh = (struct gre_base_hdr *)skb_transport_header(skb);
+		pcsum = (__sum16 *)(greh + 1);
+
+		if (gso_partial && skb_is_gso(skb)) {
+			unsigned int partial_adj;
+
+			/* Adjust checksum to account for the fact that
+			 * the partial checksum is based on actual size
+			 * whereas headers should be based on MSS size.
+			 */
+			partial_adj = skb->len + skb_headroom(skb) -
+				      SKB_GSO_CB(skb)->data_offset -
+				      skb_shinfo(skb)->gso_size;
+			*pcsum = ~csum_fold((__force __wsum)htonl(partial_adj));
+		} else {
+			*pcsum = 0;
+		}
+
+		*(pcsum + 1) = 0;
+		if (skb->encapsulation || !offload_csum) {
+			*pcsum = gso_make_checksum(skb, 0);
+		} else {
+			skb->ip_summed = CHECKSUM_PARTIAL;
+			skb->csum_start = skb_transport_header(skb) - skb->head;
+			skb->csum_offset = sizeof(*greh);
+		}
+	} while ((skb = skb->next));
+out:
+	return segs;
+}
+
+static struct sk_buff *gre_gro_receive(struct list_head *head,
+				       struct sk_buff *skb)
+{
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
+	const struct gre_base_hdr *greh;
+	unsigned int hlen, grehlen;
+	unsigned int off;
+	int flush = 1;
+	struct packet_offload *ptype;
+	__be16 type;
+
+	if (NAPI_GRO_CB(skb)->encap_mark)
+		goto out;
+
+	NAPI_GRO_CB(skb)->encap_mark = 1;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*greh);
+	greh = skb_gro_header(skb, hlen, off);
+	if (unlikely(!greh))
+		goto out;
+
+	/* Only support version 0 and K (key), C (csum) flags. Note that
+	 * although the support for the S (seq#) flag can be added easily
+	 * for GRO, this is problematic for GSO hence can not be enabled
+	 * here because a GRO pkt may end up in the forwarding path, thus
+	 * requiring GSO support to break it up correctly.
+	 */
+	if ((greh->flags & ~(GRE_KEY|GRE_CSUM)) != 0)
+		goto out;
+
+	/* We can only support GRE_CSUM if we can track the location of
+	 * the GRE header.  In the case of FOU/GUE we cannot because the
+	 * outer UDP header displaces the GRE header leaving us in a state
+	 * of limbo.
+	 */
+	if ((greh->flags & GRE_CSUM) && NAPI_GRO_CB(skb)->is_fou)
+		goto out;
+
+	type = greh->protocol;
+
+	ptype = gro_find_receive_by_type(type);
+	if (!ptype)
+		goto out;
+
+	grehlen = GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	hlen = off + grehlen;
+	if (!skb_gro_may_pull(skb, hlen)) {
+		greh = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!greh))
+			goto out;
+	}
+
+	/* Don't bother verifying checksum if we're going to flush anyway. */
+	if ((greh->flags & GRE_CSUM) && !NAPI_GRO_CB(skb)->flush) {
+		if (skb_gro_checksum_simple_validate(skb))
+			goto out;
+
+		skb_gro_checksum_try_convert(skb, IPPROTO_GRE,
+					     null_compute_pseudo);
+	}
+
+	list_for_each_entry(p, head, list) {
+		const struct gre_base_hdr *greh2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		/* The following checks are needed to ensure only pkts
+		 * from the same tunnel are considered for aggregation.
+		 * The criteria for "the same tunnel" includes:
+		 * 1) same version (we only support version 0 here)
+		 * 2) same protocol (we only support ETH_P_IP for now)
+		 * 3) same set of flags
+		 * 4) same key if the key field is present.
+		 */
+		greh2 = (struct gre_base_hdr *)(p->data + off);
+
+		if (greh2->flags != greh->flags ||
+		    greh2->protocol != greh->protocol) {
+			NAPI_GRO_CB(p)->same_flow = 0;
+			continue;
+		}
+		if (greh->flags & GRE_KEY) {
+			/* compare keys */
+			if (*(__be32 *)(greh2+1) != *(__be32 *)(greh+1)) {
+				NAPI_GRO_CB(p)->same_flow = 0;
+				continue;
+			}
+		}
+	}
+
+	skb_gro_pull(skb, grehlen);
+
+	/* Adjusted NAPI_GRO_CB(skb)->csum after skb_gro_pull()*/
+	skb_gro_postpull_rcsum(skb, greh, grehlen);
+
+	pp = call_gro_receive(ptype->callbacks.gro_receive, head, skb);
+	flush = 0;
+
+out:
+	skb_gro_flush_final(skb, pp, flush);
+
+	return pp;
+}
+
+static int gre_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct gre_base_hdr *greh = (struct gre_base_hdr *)(skb->data + nhoff);
+	struct packet_offload *ptype;
+	unsigned int grehlen = sizeof(*greh);
+	int err = -ENOENT;
+	__be16 type;
+
+	skb->encapsulation = 1;
+	skb_shinfo(skb)->gso_type = SKB_GSO_GRE;
+
+	type = greh->protocol;
+	if (greh->flags & GRE_KEY)
+		grehlen += GRE_HEADER_SECTION;
+
+	if (greh->flags & GRE_CSUM)
+		grehlen += GRE_HEADER_SECTION;
+
+	ptype = gro_find_complete_by_type(type);
+	if (ptype)
+		err = ptype->callbacks.gro_complete(skb, nhoff + grehlen);
+
+	skb_set_inner_mac_header(skb, nhoff + grehlen);
+
+	return err;
+}
+
+static const struct net_offload gre_offload = {
+	.callbacks = {
+		.gso_segment = gre_gso_segment,
+		.gro_receive = gre_gro_receive,
+		.gro_complete = gre_gro_complete,
+	},
+};
+
+static int __init gre_offload_init(void)
+{
+	int err;
+
+	err = inet_add_offload(&gre_offload, IPPROTO_GRE);
+#if IS_ENABLED(CONFIG_IPV6)
+	if (err)
+		return err;
+
+	err = inet6_add_offload(&gre_offload, IPPROTO_GRE);
+	if (err)
+		inet_del_offload(&gre_offload, IPPROTO_GRE);
+#endif
+
+	return err;
+}
+device_initcall(gre_offload_init);