Merge tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-tracegrafted

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

   Currently if a boot instance creation fails, instead of printing out
   the name of the instance that failed, it prints "(null)". That is
   because it prints "cur_str" that had already been processed by
   strsep(). Print the saved name instead.

   While at it, print the error code of the failure.

 - Fix use-after-free for same named historgrams

   Histograms can be named so that they can be used in multiple events.
   But if the named histogram has a variable attached, the second event
   that uses the named histogram which duplicates it and needs to free
   the original after duplication leaves the old variable in place and
   still visible. If another histogram uses than variable, it will use
   the stale one which will try to reference the freed duplicate
   histogram and crash the kernel.

   Free the duplicate variables along with the duplicated histogram
   data.

 - Check return value of kthread_run() in event self test

   The events self tests uses a kthread for testing but does not check
   if it succeeded in creating a kthread. If the kthread creation were
   to fail, the code will still try to call kthread_stop() on the error
   returned.

 - Fix race between reading trace_pipe and updating subbuffer size

   If a user is reading the trace_pipe file at the same time they update
   the ring buffer sub-buffer size, can cause the trace_pipe read to
   read stale data. Add trace_access_lock() around updating the ring
   buffer sub-buffer size.

 - Fix eventfs_inode on failure path in creation of the events directory

   In the creation of the "events" directory, if after allocating the
   eventfs_inode a failure is detected, it calls cleanup_ei() which
   calls free_ei(). The free_ei() will test if eventfs_inode being freed
   has no children. It is a bug if it does. But on the failure case of
   the creation of the "events" directory, the children lists have not
   yet been initialized and the free will trigger a warning because
   list_empty() on an uninitialized list returns false.

   Move the initialization into init_ei() where it makes more sense and
   makes sure that a created eventfs_inode has its lists initialized
   upon creation.

 - Check return value of kthread_run() in ftrace direct sample code

   The sample code that shows how to use the ftrace direct calls does
   not test the return of kthread_run() to see if it succeeds. Return a
   failure if the kthread_run() doesn't succeed.

 - Clear user events state on fork in case of alloc failure

   On fork, the child gets a pointer to the parent's user events state.
   It makes a copy of it then updates the child's pointer to it. But if
   the allocation fails, the duplication function leaves the child with
   a pointer to its parent's descriptor. When the child cleans up its
   data, it will free the parent's descriptor while the parent is still
   using it.

   In the duplication function, set the child's user_event_mm to NULL
   before testing if the allocation succeeded, and when it exits it will
   not free the parent's descriptor.

 - Fix retry exhaustion in simple ring buffer reader swap

   simple_ring_buffer_swap_reader_page() starts with retry set to 8 and
   post-decrements it only after a failed link replacement. On the final
   attempt, a successful replacement leaves retry at zero, while a
   failed replacement leaves it at -1.

   But the check for success expects the retry value to be non-zero and
   exits with an error on zero. This is the opposite result. Fix it.

 - Fail nicely when the remote swap_reader_page() returns an error

   Currently, if the swap_reader_page() of a remote buffer fails, it
   triggers a WARN_ON_ONCE() and continues normally. Instead, have it
   exit with an error and a pr_warn() print instead of a full WARNING.

* tag 'trace-v7.3-2' of git://git.kernel.org/pub/scm/linux/kernel/git/trace/linux-trace:
  ring-buffer: Stop remote reader update when page swap fails
  tracing: Fix retry exhaustion in simple ring buffer reader swap
  tracing/user_events: Clear copied tracing state before fork duplication
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-multi-modify
  samples/ftrace: Fix kthread_stop() on ERR_PTR in ftrace-direct-modify
  eventfs: Initialize ei->children and ei->list in init_ei()
  tracing: Fix use-after-free in trace_pipe read on sub-buffer order change
  tracing: Fix crash passing ERR_PTR to kthread_stop()
  tracing: Fix use-after-free with same-name named triggers
  tracing: Fix logged instance name on creation failure

1 files changed, 622 insertions, 0 deletions

diff --git a/include/net/gro.h b/include/net/gro.h
new file mode 100644
index 000000000..2300b6da0
--- /dev/null
+++ b/include/net/gro.h
@@ -0,0 +1,622 @@
+/* SPDX-License-Identifier: GPL-2.0-or-later */
+
+#ifndef _NET_GRO_H
+#define _NET_GRO_H
+
+#include <linux/indirect_call_wrapper.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <net/ip6_checksum.h>
+#include <linux/skbuff.h>
+#include <net/udp.h>
+#include <net/hotdata.h>
+
+/* This should be increased if a protocol with a bigger head is added. */
+#define GRO_MAX_HEAD (MAX_HEADER + 128)
+
+struct napi_gro_cb {
+	union {
+		struct {
+			/* Virtual address of skb_shinfo(skb)->frags[0].page + offset. */
+			void	*frag0;
+
+			/* Length of frag0. */
+			unsigned int frag0_len;
+		};
+
+		struct {
+			/* used in skb_gro_receive() slow path */
+			struct sk_buff *last;
+
+			/* jiffies when first packet was created/queued */
+			unsigned long age;
+		};
+	};
+
+	/* This indicates where we are processing relative to skb->data. */
+	int	data_offset;
+
+	/* This is non-zero if the packet cannot be merged with the new skb. */
+	u16	flush;
+
+	/* Number of segments aggregated. */
+	u16	count;
+
+	/* Used in ipv6_gro_receive() and foo-over-udp and esp-in-udp */
+	u16	proto;
+
+	u16	pad;
+
+/* Used in napi_gro_cb::free */
+#define NAPI_GRO_FREE             1
+#define NAPI_GRO_FREE_STOLEN_HEAD 2
+	/* portion of the cb set to zero at every gro iteration */
+	struct_group(zeroed,
+
+		/* Start offset for remote checksum offload */
+		u16	gro_remcsum_start;
+
+		/* This is non-zero if the packet may be of the same flow. */
+		u8	same_flow:1;
+
+		/* Used in tunnel GRO receive */
+		u8	encap_mark:1;
+
+		/* GRO checksum is valid */
+		u8	csum_valid:1;
+
+		/* Number of checksums via CHECKSUM_UNNECESSARY */
+		u8	csum_cnt:3;
+
+		/* Free the skb? */
+		u8	free:2;
+
+		/* Used in GRE, set in fou/gue_gro_receive */
+		u8	is_fou:1;
+
+		/* Used to determine if ipid_offset can be ignored */
+		u8	ip_fixedid:2;
+
+		/* Number of gro_receive callbacks this packet already went through */
+		u8 recursion_counter:4;
+
+		/* GRO is done by frag_list pointer chaining. */
+		u8	is_flist:1;
+	);
+
+	/* used to support CHECKSUM_COMPLETE for tunneling protocols */
+	__wsum	csum;
+
+	/* L3 offsets */
+	union {
+		struct {
+			u16 network_offset;
+			u16 inner_network_offset;
+		};
+		u16 network_offsets[2];
+	};
+};
+
+#define NAPI_GRO_CB(skb) ((struct napi_gro_cb *)(skb)->cb)
+
+#define GRO_RECURSION_LIMIT 15
+static inline int gro_recursion_inc_test(struct sk_buff *skb)
+{
+	return ++NAPI_GRO_CB(skb)->recursion_counter == GRO_RECURSION_LIMIT;
+}
+
+typedef struct sk_buff *(*gro_receive_t)(struct list_head *, struct sk_buff *);
+static inline struct sk_buff *call_gro_receive(gro_receive_t cb,
+					       struct list_head *head,
+					       struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(head, skb);
+}
+
+typedef struct sk_buff *(*gro_receive_sk_t)(struct sock *, struct list_head *,
+					    struct sk_buff *);
+static inline struct sk_buff *call_gro_receive_sk(gro_receive_sk_t cb,
+						  struct sock *sk,
+						  struct list_head *head,
+						  struct sk_buff *skb)
+{
+	if (unlikely(gro_recursion_inc_test(skb))) {
+		NAPI_GRO_CB(skb)->flush |= 1;
+		return NULL;
+	}
+
+	return cb(sk, head, skb);
+}
+
+static inline unsigned int skb_gro_offset(const struct sk_buff *skb)
+{
+	return NAPI_GRO_CB(skb)->data_offset;
+}
+
+static inline unsigned int skb_gro_len(const struct sk_buff *skb)
+{
+	return skb->len - NAPI_GRO_CB(skb)->data_offset;
+}
+
+static inline void skb_gro_pull(struct sk_buff *skb, unsigned int len)
+{
+	NAPI_GRO_CB(skb)->data_offset += len;
+}
+
+static inline void *skb_gro_header_fast(const struct sk_buff *skb,
+					unsigned int offset)
+{
+	return NAPI_GRO_CB(skb)->frag0 + offset;
+}
+
+static inline bool skb_gro_may_pull(const struct sk_buff *skb,
+				    unsigned int hlen)
+{
+	return likely(hlen <= NAPI_GRO_CB(skb)->frag0_len);
+}
+
+static inline void *skb_gro_header_slow(struct sk_buff *skb, unsigned int hlen,
+					unsigned int offset)
+{
+	if (!pskb_may_pull(skb, hlen))
+		return NULL;
+
+	return skb->data + offset;
+}
+
+static inline void *skb_gro_header(struct sk_buff *skb, unsigned int hlen,
+				   unsigned int offset)
+{
+	void *ptr;
+
+	ptr = skb_gro_header_fast(skb, offset);
+	if (!skb_gro_may_pull(skb, hlen))
+		ptr = skb_gro_header_slow(skb, hlen, offset);
+	return ptr;
+}
+
+static inline int skb_gro_receive_network_offset(const struct sk_buff *skb)
+{
+	return NAPI_GRO_CB(skb)->network_offsets[NAPI_GRO_CB(skb)->encap_mark];
+}
+
+static inline void *skb_gro_network_header(const struct sk_buff *skb)
+{
+	if (skb_gro_may_pull(skb, skb_gro_offset(skb)))
+		return skb_gro_header_fast(skb, skb_gro_receive_network_offset(skb));
+
+	return skb->data + skb_gro_receive_network_offset(skb);
+}
+
+static inline __wsum inet_gro_compute_pseudo(const struct sk_buff *skb,
+					     int proto)
+{
+	const struct iphdr *iph = skb_gro_network_header(skb);
+
+	return csum_tcpudp_nofold(iph->saddr, iph->daddr,
+				  skb_gro_len(skb), proto, 0);
+}
+
+static inline void skb_gro_postpull_rcsum(struct sk_buff *skb,
+					const void *start, unsigned int len)
+{
+	if (NAPI_GRO_CB(skb)->csum_valid)
+		NAPI_GRO_CB(skb)->csum = wsum_negate(csum_partial(start, len,
+						wsum_negate(NAPI_GRO_CB(skb)->csum)));
+}
+
+/* GRO checksum functions. These are logical equivalents of the normal
+ * checksum functions (in skbuff.h) except that they operate on the GRO
+ * offsets and fields in sk_buff.
+ */
+
+__sum16 __skb_gro_checksum_complete(struct sk_buff *skb);
+
+static inline bool skb_at_gro_remcsum_start(struct sk_buff *skb)
+{
+	return (NAPI_GRO_CB(skb)->gro_remcsum_start == skb_gro_offset(skb));
+}
+
+static inline bool __skb_gro_checksum_validate_needed(struct sk_buff *skb,
+						      bool zero_okay,
+						      __sum16 check)
+{
+	return ((skb->ip_summed != CHECKSUM_PARTIAL ||
+		skb_checksum_start_offset(skb) <
+		 skb_gro_offset(skb)) &&
+		!skb_at_gro_remcsum_start(skb) &&
+		NAPI_GRO_CB(skb)->csum_cnt == 0 &&
+		(!zero_okay || check));
+}
+
+static inline __sum16 __skb_gro_checksum_validate_complete(struct sk_buff *skb,
+							   __wsum psum)
+{
+	if (NAPI_GRO_CB(skb)->csum_valid &&
+	    !csum_fold(csum_add(psum, NAPI_GRO_CB(skb)->csum)))
+		return 0;
+
+	NAPI_GRO_CB(skb)->csum = psum;
+
+	return __skb_gro_checksum_complete(skb);
+}
+
+static inline void skb_gro_incr_csum_unnecessary(struct sk_buff *skb)
+{
+	if (NAPI_GRO_CB(skb)->csum_cnt > 0) {
+		/* Consume a checksum from CHECKSUM_UNNECESSARY */
+		NAPI_GRO_CB(skb)->csum_cnt--;
+	} else {
+		/* Update skb for CHECKSUM_UNNECESSARY and csum_level when we
+		 * verified a new top level checksum or an encapsulated one
+		 * during GRO. This saves work if we fallback to normal path.
+		 */
+		__skb_incr_checksum_unnecessary(skb);
+	}
+}
+
+#define __skb_gro_checksum_validate(skb, proto, zero_okay, check,	\
+				    compute_pseudo)			\
+({									\
+	__sum16 __ret = 0;						\
+	if (__skb_gro_checksum_validate_needed(skb, zero_okay, check))	\
+		__ret = __skb_gro_checksum_validate_complete(skb,	\
+				compute_pseudo(skb, proto));		\
+	if (!__ret)							\
+		skb_gro_incr_csum_unnecessary(skb);			\
+	__ret;								\
+})
+
+#define skb_gro_checksum_validate(skb, proto, compute_pseudo)		\
+	__skb_gro_checksum_validate(skb, proto, false, 0, compute_pseudo)
+
+#define skb_gro_checksum_validate_zero_check(skb, proto, check,		\
+					     compute_pseudo)		\
+	__skb_gro_checksum_validate(skb, proto, true, check, compute_pseudo)
+
+#define skb_gro_checksum_simple_validate(skb)				\
+	__skb_gro_checksum_validate(skb, 0, false, 0, null_compute_pseudo)
+
+static inline bool __skb_gro_checksum_convert_check(struct sk_buff *skb)
+{
+	return (NAPI_GRO_CB(skb)->csum_cnt == 0 &&
+		!NAPI_GRO_CB(skb)->csum_valid);
+}
+
+static inline void __skb_gro_checksum_convert(struct sk_buff *skb,
+					      __wsum pseudo)
+{
+	NAPI_GRO_CB(skb)->csum = ~pseudo;
+	NAPI_GRO_CB(skb)->csum_valid = 1;
+}
+
+#define skb_gro_checksum_try_convert(skb, proto, compute_pseudo)	\
+do {									\
+	if (__skb_gro_checksum_convert_check(skb))			\
+		__skb_gro_checksum_convert(skb, 			\
+					   compute_pseudo(skb, proto));	\
+} while (0)
+
+struct gro_remcsum {
+	int offset;
+	__wsum delta;
+};
+
+static inline void skb_gro_remcsum_init(struct gro_remcsum *grc)
+{
+	grc->offset = 0;
+	grc->delta = 0;
+}
+
+static inline void *skb_gro_remcsum_process(struct sk_buff *skb, void *ptr,
+					    unsigned int off, size_t hdrlen,
+					    int start, int offset,
+					    struct gro_remcsum *grc,
+					    bool nopartial)
+{
+	__wsum delta;
+	size_t plen = hdrlen + max_t(size_t, offset + sizeof(u16), start);
+
+	BUG_ON(!NAPI_GRO_CB(skb)->csum_valid);
+
+	if (!nopartial) {
+		NAPI_GRO_CB(skb)->gro_remcsum_start = off + hdrlen + start;
+		return ptr;
+	}
+
+	ptr = skb_gro_header(skb, off + plen, off);
+	if (!ptr)
+		return NULL;
+
+	delta = remcsum_adjust(ptr + hdrlen, NAPI_GRO_CB(skb)->csum,
+			       start, offset);
+
+	/* Adjust skb->csum since we changed the packet */
+	NAPI_GRO_CB(skb)->csum = csum_add(NAPI_GRO_CB(skb)->csum, delta);
+
+	grc->offset = off + hdrlen + offset;
+	grc->delta = delta;
+
+	return ptr;
+}
+
+static inline void skb_gro_remcsum_cleanup(struct sk_buff *skb,
+					   struct gro_remcsum *grc)
+{
+	void *ptr;
+	size_t plen = grc->offset + sizeof(u16);
+
+	if (!grc->delta)
+		return;
+
+	ptr = skb_gro_header(skb, plen, grc->offset);
+	if (!ptr)
+		return;
+
+	remcsum_unadjust((__sum16 *)ptr, grc->delta);
+}
+
+#ifdef CONFIG_XFRM_OFFLOAD
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
+{
+	if (PTR_ERR(pp) != -EINPROGRESS)
+		NAPI_GRO_CB(skb)->flush |= flush;
+}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff *pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	if (PTR_ERR(pp) != -EINPROGRESS) {
+		NAPI_GRO_CB(skb)->flush |= flush;
+		skb_gro_remcsum_cleanup(skb, grc);
+		skb->remcsum_offload = 0;
+	}
+}
+#else
+static inline void skb_gro_flush_final(struct sk_buff *skb, struct sk_buff *pp, int flush)
+{
+	NAPI_GRO_CB(skb)->flush |= flush;
+}
+static inline void skb_gro_flush_final_remcsum(struct sk_buff *skb,
+					       struct sk_buff *pp,
+					       int flush,
+					       struct gro_remcsum *grc)
+{
+	NAPI_GRO_CB(skb)->flush |= flush;
+	skb_gro_remcsum_cleanup(skb, grc);
+	skb->remcsum_offload = 0;
+}
+#endif
+
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *ipv6_gro_receive(struct list_head *,
+							   struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(int ipv6_gro_complete(struct sk_buff *, int));
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *inet_gro_receive(struct list_head *,
+							   struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(int inet_gro_complete(struct sk_buff *, int));
+
+INDIRECT_CALLABLE_DECLARE(struct sk_buff *udp4_gro_receive(struct list_head *,
+							   struct sk_buff *));
+INDIRECT_CALLABLE_DECLARE(int udp4_gro_complete(struct sk_buff *, int));
+
+struct sk_buff *udp6_gro_receive(struct list_head *, struct sk_buff *);
+int udp6_gro_complete(struct sk_buff *, int);
+
+#define indirect_call_gro_receive_inet(cb, f2, f1, head, skb)	\
+({								\
+	unlikely(gro_recursion_inc_test(skb)) ?			\
+		NAPI_GRO_CB(skb)->flush |= 1, NULL :		\
+		INDIRECT_CALL_INET(cb, f2, f1, head, skb);	\
+})
+
+struct sk_buff *udp_gro_receive(struct list_head *head, struct sk_buff *skb,
+				struct udphdr *uh, struct sock *sk);
+int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup);
+
+static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb)
+{
+	struct udphdr *uh;
+	unsigned int hlen, off;
+
+	off  = skb_gro_offset(skb);
+	hlen = off + sizeof(*uh);
+	uh   = skb_gro_header(skb, hlen, off);
+
+	return uh;
+}
+
+static inline __wsum ip6_gro_compute_pseudo(const struct sk_buff *skb,
+					    int proto)
+{
+	const struct ipv6hdr *iph = skb_gro_network_header(skb);
+
+	return ~csum_unfold(csum_ipv6_magic(&iph->saddr, &iph->daddr,
+					    skb_gro_len(skb), proto, 0));
+}
+
+static inline int inet_gro_flush(const struct iphdr *iph, const struct iphdr *iph2,
+				 struct sk_buff *p, bool inner)
+{
+	const u32 id = ntohl(*(__be32 *)&iph->id);
+	const u32 id2 = ntohl(*(__be32 *)&iph2->id);
+	const u16 ipid_offset = (id >> 16) - (id2 >> 16);
+	const u16 count = NAPI_GRO_CB(p)->count;
+
+	/* All fields must match except length and checksum. */
+	if ((iph->ttl ^ iph2->ttl) | (iph->tos ^ iph2->tos) | ((id ^ id2) & IP_DF))
+		return true;
+
+	/* When we receive our second frame we can make a decision on if we
+	 * continue this flow as an atomic flow with a fixed ID or if we use
+	 * an incrementing ID.
+	 */
+	if (count == 1 && !ipid_offset)
+		NAPI_GRO_CB(p)->ip_fixedid |= 1 << inner;
+
+	return ipid_offset ^ (count * !(NAPI_GRO_CB(p)->ip_fixedid & (1 << inner)));
+}
+
+static inline int ipv6_gro_flush(const struct ipv6hdr *iph, const struct ipv6hdr *iph2)
+{
+	/* <Version:4><Traffic_Class:8><Flow_Label:20> */
+	__be32 first_word = *(__be32 *)iph ^ *(__be32 *)iph2;
+
+	/* Flush if Traffic Class fields are different. */
+	return !!((first_word & htonl(0x0FF00000)) |
+		(__force __be32)(iph->hop_limit ^ iph2->hop_limit));
+}
+
+static inline int __gro_receive_network_flush(const void *th, const void *th2,
+					      struct sk_buff *p, const u16 diff,
+					      bool inner)
+{
+	const void *nh = th - diff;
+	const void *nh2 = th2 - diff;
+
+	if (((struct iphdr *)nh)->version == 6)
+		return ipv6_gro_flush(nh, nh2);
+	else
+		return inet_gro_flush(nh, nh2, p, inner);
+}
+
+static inline int gro_receive_network_flush(const void *th, const void *th2,
+					    struct sk_buff *p)
+{
+	int off = skb_transport_offset(p);
+	int flush;
+
+	flush = __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->network_offset, false);
+	if (NAPI_GRO_CB(p)->encap_mark)
+		flush |= __gro_receive_network_flush(th, th2, p, off - NAPI_GRO_CB(p)->inner_network_offset, true);
+
+	return flush;
+}
+
+int skb_gro_receive(struct sk_buff *p, struct sk_buff *skb);
+int skb_gro_receive_list(struct sk_buff *p, struct sk_buff *skb);
+void __gro_flush(struct gro_node *gro, bool flush_old);
+
+static inline void gro_flush(struct gro_node *gro, bool flush_old)
+{
+	if (!gro->bitmask)
+		return;
+
+	__gro_flush(gro, flush_old);
+}
+
+static inline void napi_gro_flush(struct napi_struct *napi, bool flush_old)
+{
+	gro_flush(&napi->gro, flush_old);
+}
+
+/* Pass the currently batched GRO_NORMAL SKBs up to the stack. */
+static inline void gro_normal_list(struct gro_node *gro)
+{
+	if (!gro->rx_count)
+		return;
+	netif_receive_skb_list_internal(&gro->rx_list);
+	INIT_LIST_HEAD(&gro->rx_list);
+	gro->rx_count = 0;
+}
+
+static inline void gro_flush_normal(struct gro_node *gro, bool flush_old)
+{
+	gro_flush(gro, flush_old);
+	gro_normal_list(gro);
+}
+
+/* Queue one GRO_NORMAL SKB up for list processing. If batch size exceeded,
+ * pass the whole batch up to the stack.
+ */
+static inline void gro_normal_one(struct gro_node *gro, struct sk_buff *skb,
+				  int segs)
+{
+	list_add_tail(&skb->list, &gro->rx_list);
+	gro->rx_count += segs;
+	if (gro->rx_count >= READ_ONCE(net_hotdata.gro_normal_batch))
+		gro_normal_list(gro);
+}
+
+void gro_init(struct gro_node *gro);
+void gro_cleanup(struct gro_node *gro);
+
+/* This function is the alternative of 'inet_iif' and 'inet_sdif'
+ * functions in case we can not rely on fields of IPCB.
+ *
+ * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized.
+ * The caller must hold the RCU read lock.
+ */
+static inline void inet_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif)
+{
+	*iif = inet_iif(skb) ?: skb->dev->ifindex;
+	*sdif = 0;
+
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (netif_is_l3_slave(skb->dev)) {
+		struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev);
+
+		*sdif = *iif;
+		*iif = master ? master->ifindex : 0;
+	}
+#endif
+}
+
+/* This function is the alternative of 'inet6_iif' and 'inet6_sdif'
+ * functions in case we can not rely on fields of IP6CB.
+ *
+ * The caller must verify skb_valid_dst(skb) is false and skb->dev is initialized.
+ * The caller must hold the RCU read lock.
+ */
+static inline void inet6_get_iif_sdif(const struct sk_buff *skb, int *iif, int *sdif)
+{
+	/* using skb->dev->ifindex because skb_dst(skb) is not initialized */
+	*iif = skb->dev->ifindex;
+	*sdif = 0;
+
+#if IS_ENABLED(CONFIG_NET_L3_MASTER_DEV)
+	if (netif_is_l3_slave(skb->dev)) {
+		struct net_device *master = netdev_master_upper_dev_get_rcu(skb->dev);
+
+		*sdif = *iif;
+		*iif = master ? master->ifindex : 0;
+	}
+#endif
+}
+
+struct packet_offload *gro_find_receive_by_type(__be16 type);
+struct packet_offload *gro_find_complete_by_type(__be16 type);
+
+static inline struct tcphdr *tcp_gro_pull_header(struct sk_buff *skb)
+{
+	unsigned int thlen, hlen, off;
+	struct tcphdr *th;
+
+	off = skb_gro_offset(skb);
+	hlen = off + sizeof(*th);
+	th = skb_gro_header(skb, hlen, off);
+	if (unlikely(!th))
+		return NULL;
+
+	thlen = th->doff * 4;
+	if (unlikely(thlen < sizeof(*th)))
+		return NULL;
+
+	hlen = off + thlen;
+	if (!skb_gro_may_pull(skb, hlen)) {
+		th = skb_gro_header_slow(skb, hlen, off);
+		if (unlikely(!th))
+			return NULL;
+	}
+
+	skb_gro_pull(skb, thlen);
+
+	return th;
+}
+
+#endif /* _NET_GRO_H */