Fixed MTP to work with TWRP

net/core/Makefile

@@ -0,0 +1,25 @@
+#
+# Makefile for the Linux networking core.
+#
+
+obj-y := sock.o request_sock.o skbuff.o iovec.o datagram.o stream.o scm.o \
+	 gen_stats.o gen_estimator.o net_namespace.o secure_seq.o flow_dissector.o
+
+obj-$(CONFIG_SYSCTL) += sysctl_net_core.o
+
+obj-y		     += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \
+			neighbour.o rtnetlink.o utils.o link_watch.o filter.o \
+			sock_diag.o dev_ioctl.o tso.o
+
+obj-$(CONFIG_XFRM) += flow.o
+obj-y += net-sysfs.o
+obj-$(CONFIG_PROC_FS) += net-procfs.o
+obj-$(CONFIG_NET_PKTGEN) += pktgen.o
+obj-$(CONFIG_NETPOLL) += netpoll.o
+obj-$(CONFIG_FIB_RULES) += fib_rules.o
+obj-$(CONFIG_TRACEPOINTS) += net-traces.o
+obj-$(CONFIG_NET_DROP_MONITOR) += drop_monitor.o
+obj-$(CONFIG_NETWORK_PHY_TIMESTAMPING) += timestamping.o
+obj-$(CONFIG_NET_PTP_CLASSIFY) += ptp_classifier.o
+obj-$(CONFIG_CGROUP_NET_PRIO) += netprio_cgroup.o
+obj-$(CONFIG_CGROUP_NET_CLASSID) += netclassid_cgroup.o

net/core/datagram.c

@@ -0,0 +1,888 @@
+/*
+ *	SUCS NET3:
+ *
+ *	Generic datagram handling routines. These are generic for all
+ *	protocols. Possibly a generic IP version on top of these would
+ *	make sense. Not tonight however 8-).
+ *	This is used because UDP, RAW, PACKET, DDP, IPX, AX.25 and
+ *	NetROM layer all have identical poll code and mostly
+ *	identical recvmsg() code. So we share it here. The poll was
+ *	shared before but buried in udp.c so I moved it.
+ *
+ *	Authors:	Alan Cox <alan@lxorguk.ukuu.org.uk>. (datagram_poll() from old
+ *						     udp.c code)
+ *
+ *	Fixes:
+ *		Alan Cox	:	NULL return from skb_peek_copy()
+ *					understood
+ *		Alan Cox	:	Rewrote skb_read_datagram to avoid the
+ *					skb_peek_copy stuff.
+ *		Alan Cox	:	Added support for SOCK_SEQPACKET.
+ *					IPX can no longer use the SO_TYPE hack
+ *					but AX.25 now works right, and SPX is
+ *					feasible.
+ *		Alan Cox	:	Fixed write poll of non IP protocol
+ *					crash.
+ *		Florian  La Roche:	Changed for my new skbuff handling.
+ *		Darryl Miles	:	Fixed non-blocking SOCK_SEQPACKET.
+ *		Linus Torvalds	:	BSD semantic fixes.
+ *		Alan Cox	:	Datagram iovec handling
+ *		Darryl Miles	:	Fixed non-blocking SOCK_STREAM.
+ *		Alan Cox	:	POSIXisms
+ *		Pete Wyckoff    :       Unconnected accept() fix.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <asm/uaccess.h>
+#include <linux/mm.h>
+#include <linux/interrupt.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/inet.h>
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/poll.h>
+#include <linux/highmem.h>
+#include <linux/spinlock.h>
+#include <linux/slab.h>
+#include <linux/pagemap.h>
+
+#include <net/protocol.h>
+#include <linux/skbuff.h>
+
+#include <net/checksum.h>
+#include <net/sock.h>
+#include <net/tcp_states.h>
+#include <trace/events/skb.h>
+#include <net/busy_poll.h>
+
+/*
+ *	Is a socket 'connection oriented' ?
+ */
+static inline int connection_based(struct sock *sk)
+{
+	return sk->sk_type == SOCK_SEQPACKET || sk->sk_type == SOCK_STREAM;
+}
+
+static int receiver_wake_function(wait_queue_t *wait, unsigned int mode, int sync,
+				  void *key)
+{
+	unsigned long bits = (unsigned long)key;
+
+	/*
+	 * Avoid a wakeup if event not interesting for us
+	 */
+	if (bits && !(bits & (POLLIN | POLLERR)))
+		return 0;
+	return autoremove_wake_function(wait, mode, sync, key);
+}
+/*
+ * Wait for the last received packet to be different from skb
+ */
+static int wait_for_more_packets(struct sock *sk, int *err, long *timeo_p,
+				 const struct sk_buff *skb)
+{
+	int error;
+	DEFINE_WAIT_FUNC(wait, receiver_wake_function);
+
+	prepare_to_wait_exclusive(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+
+	/* Socket errors? */
+	error = sock_error(sk);
+	if (error)
+		goto out_err;
+
+	if (sk->sk_receive_queue.prev != skb)
+		goto out;
+
+	/* Socket shut down? */
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		goto out_noerr;
+
+	/* Sequenced packets can come disconnected.
+	 * If so we report the problem
+	 */
+	error = -ENOTCONN;
+	if (connection_based(sk) &&
+	    !(sk->sk_state == TCP_ESTABLISHED || sk->sk_state == TCP_LISTEN))
+		goto out_err;
+
+	/* handle signals */
+	if (signal_pending(current))
+		goto interrupted;
+
+	error = 0;
+	*timeo_p = schedule_timeout(*timeo_p);
+out:
+	finish_wait(sk_sleep(sk), &wait);
+	return error;
+interrupted:
+	error = sock_intr_errno(*timeo_p);
+out_err:
+	*err = error;
+	goto out;
+out_noerr:
+	*err = 0;
+	error = 1;
+	goto out;
+}
+
+/**
+ *	__skb_recv_datagram - Receive a datagram skbuff
+ *	@sk: socket
+ *	@flags: MSG_ flags
+ *	@peeked: returns non-zero if this packet has been seen before
+ *	@off: an offset in bytes to peek skb from. Returns an offset
+ *	      within an skb where data actually starts
+ *	@err: error code returned
+ *
+ *	Get a datagram skbuff, understands the peeking, nonblocking wakeups
+ *	and possible races. This replaces identical code in packet, raw and
+ *	udp, as well as the IPX AX.25 and Appletalk. It also finally fixes
+ *	the long standing peek and read race for datagram sockets. If you
+ *	alter this routine remember it must be re-entrant.
+ *
+ *	This function will lock the socket if a skb is returned, so the caller
+ *	needs to unlock the socket in that case (usually by calling
+ *	skb_free_datagram)
+ *
+ *	* It does not lock socket since today. This function is
+ *	* free of race conditions. This measure should/can improve
+ *	* significantly datagram socket latencies at high loads,
+ *	* when data copying to user space takes lots of time.
+ *	* (BTW I've just killed the last cli() in IP/IPv6/core/netlink/packet
+ *	*  8) Great win.)
+ *	*			                    --ANK (980729)
+ *
+ *	The order of the tests when we find no data waiting are specified
+ *	quite explicitly by POSIX 1003.1g, don't change them without having
+ *	the standard around please.
+ */
+struct sk_buff *__skb_recv_datagram(struct sock *sk, unsigned int flags,
+				    int *peeked, int *off, int *err)
+{
+	struct sk_buff *skb, *last;
+	long timeo;
+	/*
+	 * Caller is allowed not to check sk->sk_err before skb_recv_datagram()
+	 */
+	int error = sock_error(sk);
+
+	if (error)
+		goto no_packet;
+
+	timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT);
+
+	do {
+		/* Again only user level code calls this function, so nothing
+		 * interrupt level will suddenly eat the receive_queue.
+		 *
+		 * Look at current nfs client by the way...
+		 * However, this function was correct in any case. 8)
+		 */
+		unsigned long cpu_flags;
+		struct sk_buff_head *queue = &sk->sk_receive_queue;
+		int _off = *off;
+
+		last = (struct sk_buff *)queue;
+		spin_lock_irqsave(&queue->lock, cpu_flags);
+		skb_queue_walk(queue, skb) {
+			last = skb;
+			*peeked = skb->peeked;
+			if (flags & MSG_PEEK) {
+				if (_off >= skb->len && (skb->len || _off ||
+							 skb->peeked)) {
+					_off -= skb->len;
+					continue;
+				}
+				skb->peeked = 1;
+				atomic_inc(&skb->users);
+			} else
+				__skb_unlink(skb, queue);
+
+			spin_unlock_irqrestore(&queue->lock, cpu_flags);
+			*off = _off;
+			return skb;
+		}
+		spin_unlock_irqrestore(&queue->lock, cpu_flags);
+
+		if (sk_can_busy_loop(sk) &&
+		    sk_busy_loop(sk, flags & MSG_DONTWAIT))
+			continue;
+
+		/* User doesn't want to wait */
+		error = -EAGAIN;
+		if (!timeo)
+			goto no_packet;
+
+	} while (!wait_for_more_packets(sk, err, &timeo, last));
+
+	return NULL;
+
+no_packet:
+	*err = error;
+	return NULL;
+}
+EXPORT_SYMBOL(__skb_recv_datagram);
+
+struct sk_buff *skb_recv_datagram(struct sock *sk, unsigned int flags,
+				  int noblock, int *err)
+{
+	int peeked, off = 0;
+
+	return __skb_recv_datagram(sk, flags | (noblock ? MSG_DONTWAIT : 0),
+				   &peeked, &off, err);
+}
+EXPORT_SYMBOL(skb_recv_datagram);
+
+void skb_free_datagram(struct sock *sk, struct sk_buff *skb)
+{
+	consume_skb(skb);
+	sk_mem_reclaim_partial(sk);
+}
+EXPORT_SYMBOL(skb_free_datagram);
+
+void skb_free_datagram_locked(struct sock *sk, struct sk_buff *skb)
+{
+	bool slow;
+
+	if (likely(atomic_read(&skb->users) == 1))
+		smp_rmb();
+	else if (likely(!atomic_dec_and_test(&skb->users)))
+		return;
+
+	slow = lock_sock_fast(sk);
+	skb_orphan(skb);
+	sk_mem_reclaim_partial(sk);
+	unlock_sock_fast(sk, slow);
+
+	/* skb is now orphaned, can be freed outside of locked section */
+	__kfree_skb(skb);
+}
+EXPORT_SYMBOL(skb_free_datagram_locked);
+
+/**
+ *	skb_kill_datagram - Free a datagram skbuff forcibly
+ *	@sk: socket
+ *	@skb: datagram skbuff
+ *	@flags: MSG_ flags
+ *
+ *	This function frees a datagram skbuff that was received by
+ *	skb_recv_datagram.  The flags argument must match the one
+ *	used for skb_recv_datagram.
+ *
+ *	If the MSG_PEEK flag is set, and the packet is still on the
+ *	receive queue of the socket, it will be taken off the queue
+ *	before it is freed.
+ *
+ *	This function currently only disables BH when acquiring the
+ *	sk_receive_queue lock.  Therefore it must not be used in a
+ *	context where that lock is acquired in an IRQ context.
+ *
+ *	It returns 0 if the packet was removed by us.
+ */
+
+int skb_kill_datagram(struct sock *sk, struct sk_buff *skb, unsigned int flags)
+{
+	int err = 0;
+
+	if (flags & MSG_PEEK) {
+		err = -ENOENT;
+		spin_lock_bh(&sk->sk_receive_queue.lock);
+		if (skb == skb_peek(&sk->sk_receive_queue)) {
+			__skb_unlink(skb, &sk->sk_receive_queue);
+			atomic_dec(&skb->users);
+			err = 0;
+		}
+		spin_unlock_bh(&sk->sk_receive_queue.lock);
+	}
+
+	kfree_skb(skb);
+	atomic_inc(&sk->sk_drops);
+	sk_mem_reclaim_partial(sk);
+
+	return err;
+}
+EXPORT_SYMBOL(skb_kill_datagram);
+
+/**
+ *	skb_copy_datagram_iovec - Copy a datagram to an iovec.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: io vector to copy to
+ *	@len: amount of data to copy from buffer to iovec
+ *
+ *	Note: the iovec is modified during the copy.
+ */
+int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset,
+			    struct iovec *to, int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	trace_skb_copy_datagram_iovec(skb, len);
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_toiovec(to, skb->data + offset, copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			struct page *page = skb_frag_page(frag);
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			err = memcpy_toiovec(to, vaddr + frag->page_offset +
+					     offset - start, copy);
+			kunmap(page);
+			if (err)
+				goto fault;
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_iovec(frag_iter,
+						    offset - start,
+						    to, copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+		}
+		start = end;
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_datagram_iovec);
+
+/**
+ *	skb_copy_datagram_const_iovec - Copy a datagram to an iovec.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying from
+ *	@to: io vector to copy to
+ *	@to_offset: offset in the io vector to start copying to
+ *	@len: amount of data to copy from buffer to iovec
+ *
+ *	Returns 0 or -EFAULT.
+ *	Note: the iovec is not modified during the copy.
+ */
+int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset,
+				  const struct iovec *to, int to_offset,
+				  int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_toiovecend(to, skb->data + offset, to_offset, copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+		to_offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			struct page *page = skb_frag_page(frag);
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			err = memcpy_toiovecend(to, vaddr + frag->page_offset +
+						offset - start, to_offset, copy);
+			kunmap(page);
+			if (err)
+				goto fault;
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+			to_offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_const_iovec(frag_iter,
+							  offset - start,
+							  to, to_offset,
+							  copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+			to_offset += copy;
+		}
+		start = end;
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_datagram_const_iovec);
+
+/**
+ *	skb_copy_datagram_from_iovec - Copy a datagram from an iovec.
+ *	@skb: buffer to copy
+ *	@offset: offset in the buffer to start copying to
+ *	@from: io vector to copy to
+ *	@from_offset: offset in the io vector to start copying from
+ *	@len: amount of data to copy to buffer from iovec
+ *
+ *	Returns 0 or -EFAULT.
+ *	Note: the iovec is not modified during the copy.
+ */
+int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset,
+				 const struct iovec *from, int from_offset,
+				 int len)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+
+	/* Copy header. */
+	if (copy > 0) {
+		if (copy > len)
+			copy = len;
+		if (memcpy_fromiovecend(skb->data + offset, from, from_offset,
+					copy))
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+		from_offset += copy;
+	}
+
+	/* Copy paged appendix. Hmm... why does this look so complicated? */
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		if ((copy = end - offset) > 0) {
+			int err;
+			u8  *vaddr;
+			struct page *page = skb_frag_page(frag);
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			err = memcpy_fromiovecend(vaddr + frag->page_offset +
+						  offset - start,
+						  from, from_offset, copy);
+			kunmap(page);
+			if (err)
+				goto fault;
+
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+			from_offset += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			if (copy > len)
+				copy = len;
+			if (skb_copy_datagram_from_iovec(frag_iter,
+							 offset - start,
+							 from,
+							 from_offset,
+							 copy))
+				goto fault;
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+			from_offset += copy;
+		}
+		start = end;
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_datagram_from_iovec);
+
+/**
+ *	zerocopy_sg_from_iovec - Build a zerocopy datagram from an iovec
+ *	@skb: buffer to copy
+ *	@from: io vector to copy from
+ *	@offset: offset in the io vector to start copying from
+ *	@count: amount of vectors to copy to buffer from
+ *
+ *	The function will first copy up to headlen, and then pin the userspace
+ *	pages and build frags through them.
+ *
+ *	Returns 0, -EFAULT or -EMSGSIZE.
+ *	Note: the iovec is not modified during the copy
+ */
+int zerocopy_sg_from_iovec(struct sk_buff *skb, const struct iovec *from,
+				  int offset, size_t count)
+{
+	int len = iov_length(from, count) - offset;
+	int copy = min_t(int, skb_headlen(skb), len);
+	int size;
+	int i = 0;
+
+	/* copy up to skb headlen */
+	if (skb_copy_datagram_from_iovec(skb, 0, from, offset, copy))
+		return -EFAULT;
+
+	if (len == copy)
+		return 0;
+
+	offset += copy;
+	while (count--) {
+		struct page *page[MAX_SKB_FRAGS];
+		int num_pages;
+		unsigned long base;
+		unsigned long truesize;
+
+		/* Skip over from offset and copied */
+		if (offset >= from->iov_len) {
+			offset -= from->iov_len;
+			++from;
+			continue;
+		}
+		len = from->iov_len - offset;
+		base = (unsigned long)from->iov_base + offset;
+		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+		if (i + size > MAX_SKB_FRAGS)
+			return -EMSGSIZE;
+		num_pages = get_user_pages_fast(base, size, 0, &page[i]);
+		if (num_pages != size) {
+			release_pages(&page[i], num_pages, 0);
+			return -EFAULT;
+		}
+		truesize = size * PAGE_SIZE;
+		skb->data_len += len;
+		skb->len += len;
+		skb->truesize += truesize;
+		atomic_add(truesize, &skb->sk->sk_wmem_alloc);
+		while (len) {
+			int off = base & ~PAGE_MASK;
+			int size = min_t(int, len, PAGE_SIZE - off);
+			skb_fill_page_desc(skb, i, page[i], off, size);
+			base += size;
+			len -= size;
+			i++;
+		}
+		offset = 0;
+		++from;
+	}
+	return 0;
+}
+EXPORT_SYMBOL(zerocopy_sg_from_iovec);
+
+static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset,
+				      u8 __user *to, int len,
+				      __wsum *csump)
+{
+	int start = skb_headlen(skb);
+	int i, copy = start - offset;
+	struct sk_buff *frag_iter;
+	int pos = 0;
+
+	/* Copy header. */
+	if (copy > 0) {
+		int err = 0;
+		if (copy > len)
+			copy = len;
+		*csump = csum_and_copy_to_user(skb->data + offset, to, copy,
+					       *csump, &err);
+		if (err)
+			goto fault;
+		if ((len -= copy) == 0)
+			return 0;
+		offset += copy;
+		to += copy;
+		pos = copy;
+	}
+
+	for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) {
+		int end;
+		const skb_frag_t *frag = &skb_shinfo(skb)->frags[i];
+
+		WARN_ON(start > offset + len);
+
+		end = start + skb_frag_size(frag);
+		if ((copy = end - offset) > 0) {
+			__wsum csum2;
+			int err = 0;
+			u8  *vaddr;
+			struct page *page = skb_frag_page(frag);
+
+			if (copy > len)
+				copy = len;
+			vaddr = kmap(page);
+			csum2 = csum_and_copy_to_user(vaddr +
+							frag->page_offset +
+							offset - start,
+						      to, copy, 0, &err);
+			kunmap(page);
+			if (err)
+				goto fault;
+			*csump = csum_block_add(*csump, csum2, pos);
+			if (!(len -= copy))
+				return 0;
+			offset += copy;
+			to += copy;
+			pos += copy;
+		}
+		start = end;
+	}
+
+	skb_walk_frags(skb, frag_iter) {
+		int end;
+
+		WARN_ON(start > offset + len);
+
+		end = start + frag_iter->len;
+		if ((copy = end - offset) > 0) {
+			__wsum csum2 = 0;
+			if (copy > len)
+				copy = len;
+			if (skb_copy_and_csum_datagram(frag_iter,
+						       offset - start,
+						       to, copy,
+						       &csum2))
+				goto fault;
+			*csump = csum_block_add(*csump, csum2, pos);
+			if ((len -= copy) == 0)
+				return 0;
+			offset += copy;
+			to += copy;
+			pos += copy;
+		}
+		start = end;
+	}
+	if (!len)
+		return 0;
+
+fault:
+	return -EFAULT;
+}
+
+__sum16 __skb_checksum_complete_head(struct sk_buff *skb, int len)
+{
+	__sum16 sum;
+
+	sum = csum_fold(skb_checksum(skb, 0, len, skb->csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+	skb->csum_valid = !sum;
+	return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete_head);
+
+__sum16 __skb_checksum_complete(struct sk_buff *skb)
+{
+	__wsum csum;
+	__sum16 sum;
+
+	csum = skb_checksum(skb, 0, skb->len, 0);
+
+	/* skb->csum holds pseudo checksum */
+	sum = csum_fold(csum_add(skb->csum, csum));
+	if (likely(!sum)) {
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE) &&
+		    !skb->csum_complete_sw)
+			netdev_rx_csum_fault(skb->dev);
+	}
+
+	/* Save full packet checksum */
+	skb->csum = csum;
+	skb->ip_summed = CHECKSUM_COMPLETE;
+	skb->csum_complete_sw = 1;
+	skb->csum_valid = !sum;
+
+	return sum;
+}
+EXPORT_SYMBOL(__skb_checksum_complete);
+
+/**
+ *	skb_copy_and_csum_datagram_iovec - Copy and checksum skb to user iovec.
+ *	@skb: skbuff
+ *	@hlen: hardware length
+ *	@iov: io vector
+ *	@len: amount of data to copy from skb to iov
+ *
+ *	Caller _must_ check that skb will fit to this iovec.
+ *
+ *	Returns: 0       - success.
+ *		 -EINVAL - checksum failure.
+ *		 -EFAULT - fault during copy. Beware, in this case iovec
+ *			   can be modified!
+ */
+int skb_copy_and_csum_datagram_iovec(struct sk_buff *skb,
+				     int hlen, struct iovec *iov, int len)
+{
+	__wsum csum;
+	int chunk = skb->len - hlen;
+
+	if (chunk > len)
+		chunk = len;
+
+	if (!chunk)
+		return 0;
+
+	/* Skip filled elements.
+	 * Pretty silly, look at memcpy_toiovec, though 8)
+	 */
+	while (!iov->iov_len)
+		iov++;
+
+	if (iov->iov_len < chunk) {
+		if (__skb_checksum_complete(skb))
+			goto csum_error;
+		if (skb_copy_datagram_iovec(skb, hlen, iov, chunk))
+			goto fault;
+	} else {
+		csum = csum_partial(skb->data, hlen, skb->csum);
+		if (skb_copy_and_csum_datagram(skb, hlen, iov->iov_base,
+					       chunk, &csum))
+			goto fault;
+		if (csum_fold(csum))
+			goto csum_error;
+		if (unlikely(skb->ip_summed == CHECKSUM_COMPLETE))
+			netdev_rx_csum_fault(skb->dev);
+		iov->iov_len -= chunk;
+		iov->iov_base += chunk;
+	}
+	return 0;
+csum_error:
+	return -EINVAL;
+fault:
+	return -EFAULT;
+}
+EXPORT_SYMBOL(skb_copy_and_csum_datagram_iovec);
+
+/**
+ * 	datagram_poll - generic datagram poll
+ *	@file: file struct
+ *	@sock: socket
+ *	@wait: poll table
+ *
+ *	Datagram poll: Again totally generic. This also handles
+ *	sequenced packet sockets providing the socket receive queue
+ *	is only ever holding data ready to receive.
+ *
+ *	Note: when you _don't_ use this routine for this protocol,
+ *	and you use a different write policy from sock_writeable()
+ *	then please supply your own write_space callback.
+ */
+unsigned int datagram_poll(struct file *file, struct socket *sock,
+			   poll_table *wait)
+{
+	struct sock *sk = sock->sk;
+	unsigned int mask;
+
+	sock_poll_wait(file, sk_sleep(sk), wait);
+	mask = 0;
+
+	/* exceptional events? */
+	if (sk->sk_err || !skb_queue_empty(&sk->sk_error_queue))
+		mask |= POLLERR |
+			(sock_flag(sk, SOCK_SELECT_ERR_QUEUE) ? POLLPRI : 0);
+
+	if (sk->sk_shutdown & RCV_SHUTDOWN)
+		mask |= POLLRDHUP | POLLIN | POLLRDNORM;
+	if (sk->sk_shutdown == SHUTDOWN_MASK)
+		mask |= POLLHUP;
+
+	/* readable? */
+	if (!skb_queue_empty(&sk->sk_receive_queue))
+		mask |= POLLIN | POLLRDNORM;
+
+	/* Connection-based need to check for termination and startup */
+	if (connection_based(sk)) {
+		if (sk->sk_state == TCP_CLOSE)
+			mask |= POLLHUP;
+		/* connection hasn't started yet? */
+		if (sk->sk_state == TCP_SYN_SENT)
+			return mask;
+	}
+
+	/* writable? */
+	if (sock_writeable(sk))
+		mask |= POLLOUT | POLLWRNORM | POLLWRBAND;
+	else
+		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+
+	return mask;
+}
+EXPORT_SYMBOL(datagram_poll);

net/core/dev_addr_lists.c

@@ -0,0 +1,851 @@
+/*
+ * net/core/dev_addr_lists.c - Functions for handling net device lists
+ * Copyright (c) 2010 Jiri Pirko <jpirko@redhat.com>
+ *
+ * This file contains functions for working with unicast, multicast and device
+ * addresses lists.
+ *
+ * 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; either version 2 of the License, or
+ * (at your option) any later version.
+ */
+
+#include <linux/netdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/export.h>
+#include <linux/list.h>
+
+/*
+ * General list handling functions
+ */
+
+static int __hw_addr_create_ex(struct netdev_hw_addr_list *list,
+			       const unsigned char *addr, int addr_len,
+			       unsigned char addr_type, bool global,
+			       bool sync)
+{
+	struct netdev_hw_addr *ha;
+	int alloc_size;
+
+	alloc_size = sizeof(*ha);
+	if (alloc_size < L1_CACHE_BYTES)
+		alloc_size = L1_CACHE_BYTES;
+	ha = kmalloc(alloc_size, GFP_ATOMIC);
+	if (!ha)
+		return -ENOMEM;
+	memcpy(ha->addr, addr, addr_len);
+	ha->type = addr_type;
+	ha->refcount = 1;
+	ha->global_use = global;
+	ha->synced = sync ? 1 : 0;
+	ha->sync_cnt = 0;
+	list_add_tail_rcu(&ha->list, &list->list);
+	list->count++;
+
+	return 0;
+}
+
+static int __hw_addr_add_ex(struct netdev_hw_addr_list *list,
+			    const unsigned char *addr, int addr_len,
+			    unsigned char addr_type, bool global, bool sync,
+			    int sync_count)
+{
+	struct netdev_hw_addr *ha;
+
+	if (addr_len > MAX_ADDR_LEN)
+		return -EINVAL;
+
+	list_for_each_entry(ha, &list->list, list) {
+		if (!memcmp(ha->addr, addr, addr_len) &&
+		    ha->type == addr_type) {
+			if (global) {
+				/* check if addr is already used as global */
+				if (ha->global_use)
+					return 0;
+				else
+					ha->global_use = true;
+			}
+			if (sync) {
+				if (ha->synced && sync_count)
+					return -EEXIST;
+				else
+					ha->synced++;
+			}
+			ha->refcount++;
+			return 0;
+		}
+	}
+
+	return __hw_addr_create_ex(list, addr, addr_len, addr_type, global,
+				   sync);
+}
+
+static int __hw_addr_add(struct netdev_hw_addr_list *list,
+			 const unsigned char *addr, int addr_len,
+			 unsigned char addr_type)
+{
+	return __hw_addr_add_ex(list, addr, addr_len, addr_type, false, false,
+				0);
+}
+
+static int __hw_addr_del_entry(struct netdev_hw_addr_list *list,
+			       struct netdev_hw_addr *ha, bool global,
+			       bool sync)
+{
+	if (global && !ha->global_use)
+		return -ENOENT;
+
+	if (sync && !ha->synced)
+		return -ENOENT;
+
+	if (global)
+		ha->global_use = false;
+
+	if (sync)
+		ha->synced--;
+
+	if (--ha->refcount)
+		return 0;
+	list_del_rcu(&ha->list);
+	kfree_rcu(ha, rcu_head);
+	list->count--;
+	return 0;
+}
+
+static int __hw_addr_del_ex(struct netdev_hw_addr_list *list,
+			    const unsigned char *addr, int addr_len,
+			    unsigned char addr_type, bool global, bool sync)
+{
+	struct netdev_hw_addr *ha;
+
+	list_for_each_entry(ha, &list->list, list) {
+		if (!memcmp(ha->addr, addr, addr_len) &&
+		    (ha->type == addr_type || !addr_type))
+			return __hw_addr_del_entry(list, ha, global, sync);
+	}
+	return -ENOENT;
+}
+
+static int __hw_addr_del(struct netdev_hw_addr_list *list,
+			 const unsigned char *addr, int addr_len,
+			 unsigned char addr_type)
+{
+	return __hw_addr_del_ex(list, addr, addr_len, addr_type, false, false);
+}
+
+static int __hw_addr_sync_one(struct netdev_hw_addr_list *to_list,
+			       struct netdev_hw_addr *ha,
+			       int addr_len)
+{
+	int err;
+
+	err = __hw_addr_add_ex(to_list, ha->addr, addr_len, ha->type,
+			       false, true, ha->sync_cnt);
+	if (err && err != -EEXIST)
+		return err;
+
+	if (!err) {
+		ha->sync_cnt++;
+		ha->refcount++;
+	}
+
+	return 0;
+}
+
+static void __hw_addr_unsync_one(struct netdev_hw_addr_list *to_list,
+				 struct netdev_hw_addr_list *from_list,
+				 struct netdev_hw_addr *ha,
+				 int addr_len)
+{
+	int err;
+
+	err = __hw_addr_del_ex(to_list, ha->addr, addr_len, ha->type,
+			       false, true);
+	if (err)
+		return;
+	ha->sync_cnt--;
+	/* address on from list is not marked synced */
+	__hw_addr_del_entry(from_list, ha, false, false);
+}
+
+static int __hw_addr_sync_multiple(struct netdev_hw_addr_list *to_list,
+				   struct netdev_hw_addr_list *from_list,
+				   int addr_len)
+{
+	int err = 0;
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
+		if (ha->sync_cnt == ha->refcount) {
+			__hw_addr_unsync_one(to_list, from_list, ha, addr_len);
+		} else {
+			err = __hw_addr_sync_one(to_list, ha, addr_len);
+			if (err)
+				break;
+		}
+	}
+	return err;
+}
+
+/* This function only works where there is a strict 1-1 relationship
+ * between source and destionation of they synch. If you ever need to
+ * sync addresses to more then 1 destination, you need to use
+ * __hw_addr_sync_multiple().
+ */
+int __hw_addr_sync(struct netdev_hw_addr_list *to_list,
+		   struct netdev_hw_addr_list *from_list,
+		   int addr_len)
+{
+	int err = 0;
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
+		if (!ha->sync_cnt) {
+			err = __hw_addr_sync_one(to_list, ha, addr_len);
+			if (err)
+				break;
+		} else if (ha->refcount == 1)
+			__hw_addr_unsync_one(to_list, from_list, ha, addr_len);
+	}
+	return err;
+}
+EXPORT_SYMBOL(__hw_addr_sync);
+
+void __hw_addr_unsync(struct netdev_hw_addr_list *to_list,
+		      struct netdev_hw_addr_list *from_list,
+		      int addr_len)
+{
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &from_list->list, list) {
+		if (ha->sync_cnt)
+			__hw_addr_unsync_one(to_list, from_list, ha, addr_len);
+	}
+}
+EXPORT_SYMBOL(__hw_addr_unsync);
+
+/**
+ *  __hw_addr_sync_dev - Synchonize device's multicast list
+ *  @list: address list to syncronize
+ *  @dev:  device to sync
+ *  @sync: function to call if address should be added
+ *  @unsync: function to call if address should be removed
+ *
+ *  This funciton is intended to be called from the ndo_set_rx_mode
+ *  function of devices that require explicit address add/remove
+ *  notifications.  The unsync function may be NULL in which case
+ *  the addresses requiring removal will simply be removed without
+ *  any notification to the device.
+ **/
+int __hw_addr_sync_dev(struct netdev_hw_addr_list *list,
+		       struct net_device *dev,
+		       int (*sync)(struct net_device *, const unsigned char *),
+		       int (*unsync)(struct net_device *,
+				     const unsigned char *))
+{
+	struct netdev_hw_addr *ha, *tmp;
+	int err;
+
+	/* first go through and flush out any stale entries */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt || ha->refcount != 1)
+			continue;
+
+		/* if unsync is defined and fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr))
+			continue;
+
+		ha->sync_cnt--;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+
+	/* go through and sync new entries to the list */
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (ha->sync_cnt)
+			continue;
+
+		err = sync(dev, ha->addr);
+		if (err)
+			return err;
+
+		ha->sync_cnt++;
+		ha->refcount++;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__hw_addr_sync_dev);
+
+/**
+ *  __hw_addr_unsync_dev - Remove synchonized addresses from device
+ *  @list: address list to remove syncronized addresses from
+ *  @dev:  device to sync
+ *  @unsync: function to call if address should be removed
+ *
+ *  Remove all addresses that were added to the device by __hw_addr_sync_dev().
+ *  This function is intended to be called from the ndo_stop or ndo_open
+ *  functions on devices that require explicit address add/remove
+ *  notifications.  If the unsync function pointer is NULL then this function
+ *  can be used to just reset the sync_cnt for the addresses in the list.
+ **/
+void __hw_addr_unsync_dev(struct netdev_hw_addr_list *list,
+			  struct net_device *dev,
+			  int (*unsync)(struct net_device *,
+					const unsigned char *))
+{
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		if (!ha->sync_cnt)
+			continue;
+
+		/* if unsync is defined and fails defer unsyncing address */
+		if (unsync && unsync(dev, ha->addr))
+			continue;
+
+		ha->sync_cnt--;
+		__hw_addr_del_entry(list, ha, false, false);
+	}
+}
+EXPORT_SYMBOL(__hw_addr_unsync_dev);
+
+static void __hw_addr_flush(struct netdev_hw_addr_list *list)
+{
+	struct netdev_hw_addr *ha, *tmp;
+
+	list_for_each_entry_safe(ha, tmp, &list->list, list) {
+		list_del_rcu(&ha->list);
+		kfree_rcu(ha, rcu_head);
+	}
+	list->count = 0;
+}
+
+void __hw_addr_init(struct netdev_hw_addr_list *list)
+{
+	INIT_LIST_HEAD(&list->list);
+	list->count = 0;
+}
+EXPORT_SYMBOL(__hw_addr_init);
+
+/*
+ * Device addresses handling functions
+ */
+
+/**
+ *	dev_addr_flush - Flush device address list
+ *	@dev: device
+ *
+ *	Flush device address list and reset ->dev_addr.
+ *
+ *	The caller must hold the rtnl_mutex.
+ */
+void dev_addr_flush(struct net_device *dev)
+{
+	/* rtnl_mutex must be held here */
+
+	__hw_addr_flush(&dev->dev_addrs);
+	dev->dev_addr = NULL;
+}
+EXPORT_SYMBOL(dev_addr_flush);
+
+/**
+ *	dev_addr_init - Init device address list
+ *	@dev: device
+ *
+ *	Init device address list and create the first element,
+ *	used by ->dev_addr.
+ *
+ *	The caller must hold the rtnl_mutex.
+ */
+int dev_addr_init(struct net_device *dev)
+{
+	unsigned char addr[MAX_ADDR_LEN];
+	struct netdev_hw_addr *ha;
+	int err;
+
+	/* rtnl_mutex must be held here */
+
+	__hw_addr_init(&dev->dev_addrs);
+	memset(addr, 0, sizeof(addr));
+	err = __hw_addr_add(&dev->dev_addrs, addr, sizeof(addr),
+			    NETDEV_HW_ADDR_T_LAN);
+	if (!err) {
+		/*
+		 * Get the first (previously created) address from the list
+		 * and set dev_addr pointer to this location.
+		 */
+		ha = list_first_entry(&dev->dev_addrs.list,
+				      struct netdev_hw_addr, list);
+		dev->dev_addr = ha->addr;
+	}
+	return err;
+}
+EXPORT_SYMBOL(dev_addr_init);
+
+/**
+ *	dev_addr_add - Add a device address
+ *	@dev: device
+ *	@addr: address to add
+ *	@addr_type: address type
+ *
+ *	Add a device address to the device or increase the reference count if
+ *	it already exists.
+ *
+ *	The caller must hold the rtnl_mutex.
+ */
+int dev_addr_add(struct net_device *dev, const unsigned char *addr,
+		 unsigned char addr_type)
+{
+	int err;
+
+	ASSERT_RTNL();
+
+	err = __hw_addr_add(&dev->dev_addrs, addr, dev->addr_len, addr_type);
+	if (!err)
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	return err;
+}
+EXPORT_SYMBOL(dev_addr_add);
+
+/**
+ *	dev_addr_del - Release a device address.
+ *	@dev: device
+ *	@addr: address to delete
+ *	@addr_type: address type
+ *
+ *	Release reference to a device address and remove it from the device
+ *	if the reference count drops to zero.
+ *
+ *	The caller must hold the rtnl_mutex.
+ */
+int dev_addr_del(struct net_device *dev, const unsigned char *addr,
+		 unsigned char addr_type)
+{
+	int err;
+	struct netdev_hw_addr *ha;
+
+	ASSERT_RTNL();
+
+	/*
+	 * We can not remove the first address from the list because
+	 * dev->dev_addr points to that.
+	 */
+	ha = list_first_entry(&dev->dev_addrs.list,
+			      struct netdev_hw_addr, list);
+	if (!memcmp(ha->addr, addr, dev->addr_len) &&
+	    ha->type == addr_type && ha->refcount == 1)
+		return -ENOENT;
+
+	err = __hw_addr_del(&dev->dev_addrs, addr, dev->addr_len,
+			    addr_type);
+	if (!err)
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+	return err;
+}
+EXPORT_SYMBOL(dev_addr_del);
+
+/*
+ * Unicast list handling functions
+ */
+
+/**
+ *	dev_uc_add_excl - Add a global secondary unicast address
+ *	@dev: device
+ *	@addr: address to add
+ */
+int dev_uc_add_excl(struct net_device *dev, const unsigned char *addr)
+{
+	struct netdev_hw_addr *ha;
+	int err;
+
+	netif_addr_lock_bh(dev);
+	list_for_each_entry(ha, &dev->uc.list, list) {
+		if (!memcmp(ha->addr, addr, dev->addr_len) &&
+		    ha->type == NETDEV_HW_ADDR_T_UNICAST) {
+			err = -EEXIST;
+			goto out;
+		}
+	}
+	err = __hw_addr_create_ex(&dev->uc, addr, dev->addr_len,
+				  NETDEV_HW_ADDR_T_UNICAST, true, false);
+	if (!err)
+		__dev_set_rx_mode(dev);
+out:
+	netif_addr_unlock_bh(dev);
+	return err;
+}
+EXPORT_SYMBOL(dev_uc_add_excl);
+
+/**
+ *	dev_uc_add - Add a secondary unicast address
+ *	@dev: device
+ *	@addr: address to add
+ *
+ *	Add a secondary unicast address to the device or increase
+ *	the reference count if it already exists.
+ */
+int dev_uc_add(struct net_device *dev, const unsigned char *addr)
+{
+	int err;
+
+	netif_addr_lock_bh(dev);
+	err = __hw_addr_add(&dev->uc, addr, dev->addr_len,
+			    NETDEV_HW_ADDR_T_UNICAST);
+	if (!err)
+		__dev_set_rx_mode(dev);
+	netif_addr_unlock_bh(dev);
+	return err;
+}
+EXPORT_SYMBOL(dev_uc_add);
+
+/**
+ *	dev_uc_del - Release secondary unicast address.
+ *	@dev: device
+ *	@addr: address to delete
+ *
+ *	Release reference to a secondary unicast address and remove it
+ *	from the device if the reference count drops to zero.
+ */
+int dev_uc_del(struct net_device *dev, const unsigned char *addr)
+{
+	int err;
+
+	netif_addr_lock_bh(dev);
+	err = __hw_addr_del(&dev->uc, addr, dev->addr_len,
+			    NETDEV_HW_ADDR_T_UNICAST);
+	if (!err)
+		__dev_set_rx_mode(dev);
+	netif_addr_unlock_bh(dev);
+	return err;
+}
+EXPORT_SYMBOL(dev_uc_del);
+
+/**
+ *	dev_uc_sync - Synchronize device's unicast list to another device
+ *	@to: destination device
+ *	@from: source device
+ *
+ *	Add newly added addresses to the destination device and release
+ *	addresses that have no users left. The source device must be
+ *	locked by netif_addr_lock_bh.
+ *
+ *	This function is intended to be called from the dev->set_rx_mode
+ *	function of layered software devices.  This function assumes that
+ *	addresses will only ever be synced to the @to devices and no other.
+ */
+int dev_uc_sync(struct net_device *to, struct net_device *from)
+{
+	int err = 0;
+
+	if (to->addr_len != from->addr_len)
+		return -EINVAL;
+
+	netif_addr_lock_nested(to);
+	err = __hw_addr_sync(&to->uc, &from->uc, to->addr_len);
+	if (!err)
+		__dev_set_rx_mode(to);
+	netif_addr_unlock(to);
+	return err;
+}
+EXPORT_SYMBOL(dev_uc_sync);
+
+/**
+ *	dev_uc_sync_multiple - Synchronize device's unicast list to another
+ *	device, but allow for multiple calls to sync to multiple devices.
+ *	@to: destination device
+ *	@from: source device
+ *
+ *	Add newly added addresses to the destination device and release
+ *	addresses that have been deleted from the source. The source device
+ *	must be locked by netif_addr_lock_bh.
+ *
+ *	This function is intended to be called from the dev->set_rx_mode
+ *	function of layered software devices.  It allows for a single source
+ *	device to be synced to multiple destination devices.
+ */
+int dev_uc_sync_multiple(struct net_device *to, struct net_device *from)
+{
+	int err = 0;
+
+	if (to->addr_len != from->addr_len)
+		return -EINVAL;
+
+	netif_addr_lock_nested(to);
+	err = __hw_addr_sync_multiple(&to->uc, &from->uc, to->addr_len);
+	if (!err)
+		__dev_set_rx_mode(to);
+	netif_addr_unlock(to);
+	return err;
+}
+EXPORT_SYMBOL(dev_uc_sync_multiple);
+
+/**
+ *	dev_uc_unsync - Remove synchronized addresses from the destination device
+ *	@to: destination device
+ *	@from: source device
+ *
+ *	Remove all addresses that were added to the destination device by
+ *	dev_uc_sync(). This function is intended to be called from the
+ *	dev->stop function of layered software devices.
+ */
+void dev_uc_unsync(struct net_device *to, struct net_device *from)
+{
+	if (to->addr_len != from->addr_len)
+		return;
+
+	netif_addr_lock_bh(from);
+	netif_addr_lock_nested(to);
+	__hw_addr_unsync(&to->uc, &from->uc, to->addr_len);
+	__dev_set_rx_mode(to);
+	netif_addr_unlock(to);
+	netif_addr_unlock_bh(from);
+}
+EXPORT_SYMBOL(dev_uc_unsync);
+
+/**
+ *	dev_uc_flush - Flush unicast addresses
+ *	@dev: device
+ *
+ *	Flush unicast addresses.
+ */
+void dev_uc_flush(struct net_device *dev)
+{
+	netif_addr_lock_bh(dev);
+	__hw_addr_flush(&dev->uc);
+	netif_addr_unlock_bh(dev);
+}
+EXPORT_SYMBOL(dev_uc_flush);
+
+/**
+ *	dev_uc_flush - Init unicast address list
+ *	@dev: device
+ *
+ *	Init unicast address list.
+ */
+void dev_uc_init(struct net_device *dev)
+{
+	__hw_addr_init(&dev->uc);
+}
+EXPORT_SYMBOL(dev_uc_init);
+
+/*
+ * Multicast list handling functions
+ */
+
+/**
+ *	dev_mc_add_excl - Add a global secondary multicast address
+ *	@dev: device
+ *	@addr: address to add
+ */
+int dev_mc_add_excl(struct net_device *dev, const unsigned char *addr)
+{
+	struct netdev_hw_addr *ha;
+	int err;
+
+	netif_addr_lock_bh(dev);
+	list_for_each_entry(ha, &dev->mc.list, list) {
+		if (!memcmp(ha->addr, addr, dev->addr_len) &&
+		    ha->type == NETDEV_HW_ADDR_T_MULTICAST) {
+			err = -EEXIST;
+			goto out;
+		}
+	}
+	err = __hw_addr_create_ex(&dev->mc, addr, dev->addr_len,
+				  NETDEV_HW_ADDR_T_MULTICAST, true, false);
+	if (!err)
+		__dev_set_rx_mode(dev);
+out:
+	netif_addr_unlock_bh(dev);
+	return err;
+}
+EXPORT_SYMBOL(dev_mc_add_excl);
+
+static int __dev_mc_add(struct net_device *dev, const unsigned char *addr,
+			bool global)
+{
+	int err;
+
+	netif_addr_lock_bh(dev);
+	err = __hw_addr_add_ex(&dev->mc, addr, dev->addr_len,
+			       NETDEV_HW_ADDR_T_MULTICAST, global, false, 0);
+	if (!err)
+		__dev_set_rx_mode(dev);
+	netif_addr_unlock_bh(dev);
+	return err;
+}
+/**
+ *	dev_mc_add - Add a multicast address
+ *	@dev: device
+ *	@addr: address to add
+ *
+ *	Add a multicast address to the device or increase
+ *	the reference count if it already exists.
+ */
+int dev_mc_add(struct net_device *dev, const unsigned char *addr)
+{
+	return __dev_mc_add(dev, addr, false);
+}
+EXPORT_SYMBOL(dev_mc_add);
+
+/**
+ *	dev_mc_add_global - Add a global multicast address
+ *	@dev: device
+ *	@addr: address to add
+ *
+ *	Add a global multicast address to the device.
+ */
+int dev_mc_add_global(struct net_device *dev, const unsigned char *addr)
+{
+	return __dev_mc_add(dev, addr, true);
+}
+EXPORT_SYMBOL(dev_mc_add_global);
+
+static int __dev_mc_del(struct net_device *dev, const unsigned char *addr,
+			bool global)
+{
+	int err;
+
+	netif_addr_lock_bh(dev);
+	err = __hw_addr_del_ex(&dev->mc, addr, dev->addr_len,
+			       NETDEV_HW_ADDR_T_MULTICAST, global, false);
+	if (!err)
+		__dev_set_rx_mode(dev);
+	netif_addr_unlock_bh(dev);
+	return err;
+}
+
+/**
+ *	dev_mc_del - Delete a multicast address.
+ *	@dev: device
+ *	@addr: address to delete
+ *
+ *	Release reference to a multicast address and remove it
+ *	from the device if the reference count drops to zero.
+ */
+int dev_mc_del(struct net_device *dev, const unsigned char *addr)
+{
+	return __dev_mc_del(dev, addr, false);
+}
+EXPORT_SYMBOL(dev_mc_del);
+
+/**
+ *	dev_mc_del_global - Delete a global multicast address.
+ *	@dev: device
+ *	@addr: address to delete
+ *
+ *	Release reference to a multicast address and remove it
+ *	from the device if the reference count drops to zero.
+ */
+int dev_mc_del_global(struct net_device *dev, const unsigned char *addr)
+{
+	return __dev_mc_del(dev, addr, true);
+}
+EXPORT_SYMBOL(dev_mc_del_global);
+
+/**
+ *	dev_mc_sync - Synchronize device's multicast list to another device
+ *	@to: destination device
+ *	@from: source device
+ *
+ *	Add newly added addresses to the destination device and release
+ *	addresses that have no users left. The source device must be
+ *	locked by netif_addr_lock_bh.
+ *
+ *	This function is intended to be called from the ndo_set_rx_mode
+ *	function of layered software devices.
+ */
+int dev_mc_sync(struct net_device *to, struct net_device *from)
+{
+	int err = 0;
+
+	if (to->addr_len != from->addr_len)
+		return -EINVAL;
+
+	netif_addr_lock_nested(to);
+	err = __hw_addr_sync(&to->mc, &from->mc, to->addr_len);
+	if (!err)
+		__dev_set_rx_mode(to);
+	netif_addr_unlock(to);
+	return err;
+}
+EXPORT_SYMBOL(dev_mc_sync);
+
+/**
+ *	dev_mc_sync_multiple - Synchronize device's multicast list to another
+ *	device, but allow for multiple calls to sync to multiple devices.
+ *	@to: destination device
+ *	@from: source device
+ *
+ *	Add newly added addresses to the destination device and release
+ *	addresses that have no users left. The source device must be
+ *	locked by netif_addr_lock_bh.
+ *
+ *	This function is intended to be called from the ndo_set_rx_mode
+ *	function of layered software devices.  It allows for a single
+ *	source device to be synced to multiple destination devices.
+ */
+int dev_mc_sync_multiple(struct net_device *to, struct net_device *from)
+{
+	int err = 0;
+
+	if (to->addr_len != from->addr_len)
+		return -EINVAL;
+
+	netif_addr_lock_nested(to);
+	err = __hw_addr_sync_multiple(&to->mc, &from->mc, to->addr_len);
+	if (!err)
+		__dev_set_rx_mode(to);
+	netif_addr_unlock(to);
+	return err;
+}
+EXPORT_SYMBOL(dev_mc_sync_multiple);
+
+/**
+ *	dev_mc_unsync - Remove synchronized addresses from the destination device
+ *	@to: destination device
+ *	@from: source device
+ *
+ *	Remove all addresses that were added to the destination device by
+ *	dev_mc_sync(). This function is intended to be called from the
+ *	dev->stop function of layered software devices.
+ */
+void dev_mc_unsync(struct net_device *to, struct net_device *from)
+{
+	if (to->addr_len != from->addr_len)
+		return;
+
+	netif_addr_lock_bh(from);
+	netif_addr_lock_nested(to);
+	__hw_addr_unsync(&to->mc, &from->mc, to->addr_len);
+	__dev_set_rx_mode(to);
+	netif_addr_unlock(to);
+	netif_addr_unlock_bh(from);
+}
+EXPORT_SYMBOL(dev_mc_unsync);
+
+/**
+ *	dev_mc_flush - Flush multicast addresses
+ *	@dev: device
+ *
+ *	Flush multicast addresses.
+ */
+void dev_mc_flush(struct net_device *dev)
+{
+	netif_addr_lock_bh(dev);
+	__hw_addr_flush(&dev->mc);
+	netif_addr_unlock_bh(dev);
+}
+EXPORT_SYMBOL(dev_mc_flush);
+
+/**
+ *	dev_mc_flush - Init multicast address list
+ *	@dev: device
+ *
+ *	Init multicast address list.
+ */
+void dev_mc_init(struct net_device *dev)
+{
+	__hw_addr_init(&dev->mc);
+}
+EXPORT_SYMBOL(dev_mc_init);

net/core/dev_ioctl.c

@@ -0,0 +1,564 @@
+#include <linux/kmod.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/rtnetlink.h>
+#include <linux/net_tstamp.h>
+#include <linux/wireless.h>
+#include <net/wext.h>
+
+/*
+ *	Map an interface index to its name (SIOCGIFNAME)
+ */
+
+/*
+ *	We need this ioctl for efficient implementation of the
+ *	if_indextoname() function required by the IPv6 API.  Without
+ *	it, we would have to search all the interfaces to find a
+ *	match.  --pb
+ */
+
+static int dev_ifname(struct net *net, struct ifreq __user *arg)
+{
+	struct ifreq ifr;
+	int error;
+
+	/*
+	 *	Fetch the caller's info block.
+	 */
+
+	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+		return -EFAULT;
+
+	error = netdev_get_name(net, ifr.ifr_name, ifr.ifr_ifindex);
+	if (error)
+		return error;
+
+	if (copy_to_user(arg, &ifr, sizeof(struct ifreq)))
+		return -EFAULT;
+	return 0;
+}
+
+static gifconf_func_t *gifconf_list[NPROTO];
+
+/**
+ *	register_gifconf	-	register a SIOCGIF handler
+ *	@family: Address family
+ *	@gifconf: Function handler
+ *
+ *	Register protocol dependent address dumping routines. The handler
+ *	that is passed must not be freed or reused until it has been replaced
+ *	by another handler.
+ */
+int register_gifconf(unsigned int family, gifconf_func_t *gifconf)
+{
+	if (family >= NPROTO)
+		return -EINVAL;
+	gifconf_list[family] = gifconf;
+	return 0;
+}
+EXPORT_SYMBOL(register_gifconf);
+
+/*
+ *	Perform a SIOCGIFCONF call. This structure will change
+ *	size eventually, and there is nothing I can do about it.
+ *	Thus we will need a 'compatibility mode'.
+ */
+
+static int dev_ifconf(struct net *net, char __user *arg)
+{
+	struct ifconf ifc;
+	struct net_device *dev;
+	char __user *pos;
+	int len;
+	int total;
+	int i;
+
+	/*
+	 *	Fetch the caller's info block.
+	 */
+
+	if (copy_from_user(&ifc, arg, sizeof(struct ifconf)))
+		return -EFAULT;
+
+	pos = ifc.ifc_buf;
+	len = ifc.ifc_len;
+
+	/*
+	 *	Loop over the interfaces, and write an info block for each.
+	 */
+
+	total = 0;
+	for_each_netdev(net, dev) {
+		for (i = 0; i < NPROTO; i++) {
+			if (gifconf_list[i]) {
+				int done;
+				if (!pos)
+					done = gifconf_list[i](dev, NULL, 0);
+				else
+					done = gifconf_list[i](dev, pos + total,
+							       len - total);
+				if (done < 0)
+					return -EFAULT;
+				total += done;
+			}
+		}
+	}
+
+	/*
+	 *	All done.  Write the updated control block back to the caller.
+	 */
+	ifc.ifc_len = total;
+
+	/*
+	 * 	Both BSD and Solaris return 0 here, so we do too.
+	 */
+	return copy_to_user(arg, &ifc, sizeof(struct ifconf)) ? -EFAULT : 0;
+}
+
+/*
+ *	Perform the SIOCxIFxxx calls, inside rcu_read_lock()
+ */
+static int dev_ifsioc_locked(struct net *net, struct ifreq *ifr, unsigned int cmd)
+{
+	int err;
+	struct net_device *dev = dev_get_by_name_rcu(net, ifr->ifr_name);
+
+	if (!dev)
+		return -ENODEV;
+
+	switch (cmd) {
+	case SIOCGIFFLAGS:	/* Get interface flags */
+		ifr->ifr_flags = (short) dev_get_flags(dev);
+		return 0;
+
+	case SIOCGIFMETRIC:	/* Get the metric on the interface
+				   (currently unused) */
+		ifr->ifr_metric = 0;
+		return 0;
+
+	case SIOCGIFMTU:	/* Get the MTU of a device */
+		ifr->ifr_mtu = dev->mtu;
+		return 0;
+
+	case SIOCGIFHWADDR:
+		if (!dev->addr_len)
+			memset(ifr->ifr_hwaddr.sa_data, 0, sizeof ifr->ifr_hwaddr.sa_data);
+		else
+			memcpy(ifr->ifr_hwaddr.sa_data, dev->dev_addr,
+			       min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+		ifr->ifr_hwaddr.sa_family = dev->type;
+		return 0;
+
+	case SIOCGIFSLAVE:
+		err = -EINVAL;
+		break;
+
+	case SIOCGIFMAP:
+		ifr->ifr_map.mem_start = dev->mem_start;
+		ifr->ifr_map.mem_end   = dev->mem_end;
+		ifr->ifr_map.base_addr = dev->base_addr;
+		ifr->ifr_map.irq       = dev->irq;
+		ifr->ifr_map.dma       = dev->dma;
+		ifr->ifr_map.port      = dev->if_port;
+		return 0;
+
+	case SIOCGIFINDEX:
+		ifr->ifr_ifindex = dev->ifindex;
+		return 0;
+
+	case SIOCGIFTXQLEN:
+		ifr->ifr_qlen = dev->tx_queue_len;
+		return 0;
+
+	default:
+		/* dev_ioctl() should ensure this case
+		 * is never reached
+		 */
+		WARN_ON(1);
+		err = -ENOTTY;
+		break;
+
+	}
+	return err;
+}
+
+static int net_hwtstamp_validate(struct ifreq *ifr)
+{
+	struct hwtstamp_config cfg;
+	enum hwtstamp_tx_types tx_type;
+	enum hwtstamp_rx_filters rx_filter;
+	int tx_type_valid = 0;
+	int rx_filter_valid = 0;
+
+	if (copy_from_user(&cfg, ifr->ifr_data, sizeof(cfg)))
+		return -EFAULT;
+
+	if (cfg.flags) /* reserved for future extensions */
+		return -EINVAL;
+
+	tx_type = cfg.tx_type;
+	rx_filter = cfg.rx_filter;
+
+	switch (tx_type) {
+	case HWTSTAMP_TX_OFF:
+	case HWTSTAMP_TX_ON:
+	case HWTSTAMP_TX_ONESTEP_SYNC:
+		tx_type_valid = 1;
+		break;
+	}
+
+	switch (rx_filter) {
+	case HWTSTAMP_FILTER_NONE:
+	case HWTSTAMP_FILTER_ALL:
+	case HWTSTAMP_FILTER_SOME:
+	case HWTSTAMP_FILTER_PTP_V1_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V1_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V1_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L4_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L4_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L4_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_L2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_L2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_L2_DELAY_REQ:
+	case HWTSTAMP_FILTER_PTP_V2_EVENT:
+	case HWTSTAMP_FILTER_PTP_V2_SYNC:
+	case HWTSTAMP_FILTER_PTP_V2_DELAY_REQ:
+		rx_filter_valid = 1;
+		break;
+	}
+
+	if (!tx_type_valid || !rx_filter_valid)
+		return -ERANGE;
+
+	return 0;
+}
+
+/*
+ *	Perform the SIOCxIFxxx calls, inside rtnl_lock()
+ */
+static int dev_ifsioc(struct net *net, struct ifreq *ifr, unsigned int cmd)
+{
+	int err;
+	struct net_device *dev = __dev_get_by_name(net, ifr->ifr_name);
+	const struct net_device_ops *ops;
+
+	if (!dev)
+		return -ENODEV;
+
+	ops = dev->netdev_ops;
+
+	switch (cmd) {
+	case SIOCSIFFLAGS:	/* Set interface flags */
+		return dev_change_flags(dev, ifr->ifr_flags);
+
+	case SIOCSIFMETRIC:	/* Set the metric on the interface
+				   (currently unused) */
+		return -EOPNOTSUPP;
+
+	case SIOCSIFMTU:	/* Set the MTU of a device */
+		return dev_set_mtu(dev, ifr->ifr_mtu);
+
+	case SIOCSIFHWADDR:
+		return dev_set_mac_address(dev, &ifr->ifr_hwaddr);
+
+	case SIOCSIFHWBROADCAST:
+		if (ifr->ifr_hwaddr.sa_family != dev->type)
+			return -EINVAL;
+		memcpy(dev->broadcast, ifr->ifr_hwaddr.sa_data,
+		       min(sizeof ifr->ifr_hwaddr.sa_data, (size_t) dev->addr_len));
+		call_netdevice_notifiers(NETDEV_CHANGEADDR, dev);
+		return 0;
+
+	case SIOCSIFMAP:
+		if (ops->ndo_set_config) {
+			if (!netif_device_present(dev))
+				return -ENODEV;
+			return ops->ndo_set_config(dev, &ifr->ifr_map);
+		}
+		return -EOPNOTSUPP;
+
+	case SIOCADDMULTI:
+		if (!ops->ndo_set_rx_mode ||
+		    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+			return -EINVAL;
+		if (!netif_device_present(dev))
+			return -ENODEV;
+		return dev_mc_add_global(dev, ifr->ifr_hwaddr.sa_data);
+
+	case SIOCDELMULTI:
+		if (!ops->ndo_set_rx_mode ||
+		    ifr->ifr_hwaddr.sa_family != AF_UNSPEC)
+			return -EINVAL;
+		if (!netif_device_present(dev))
+			return -ENODEV;
+		return dev_mc_del_global(dev, ifr->ifr_hwaddr.sa_data);
+
+	case SIOCSIFTXQLEN:
+		if (ifr->ifr_qlen < 0)
+			return -EINVAL;
+		dev->tx_queue_len = ifr->ifr_qlen;
+		return 0;
+
+	case SIOCSIFNAME:
+		ifr->ifr_newname[IFNAMSIZ-1] = '\0';
+		return dev_change_name(dev, ifr->ifr_newname);
+
+	case SIOCSHWTSTAMP:
+		err = net_hwtstamp_validate(ifr);
+		if (err)
+			return err;
+		/* fall through */
+
+	/*
+	 *	Unknown or private ioctl
+	 */
+	default:
+		if ((cmd >= SIOCDEVPRIVATE &&
+		    cmd <= SIOCDEVPRIVATE + 15) ||
+		    cmd == SIOCBONDENSLAVE ||
+		    cmd == SIOCBONDRELEASE ||
+		    cmd == SIOCBONDSETHWADDR ||
+		    cmd == SIOCBONDSLAVEINFOQUERY ||
+		    cmd == SIOCBONDINFOQUERY ||
+		    cmd == SIOCBONDCHANGEACTIVE ||
+		    cmd == SIOCGMIIPHY ||
+		    cmd == SIOCGMIIREG ||
+		    cmd == SIOCSMIIREG ||
+		    cmd == SIOCBRADDIF ||
+		    cmd == SIOCBRDELIF ||
+		    cmd == SIOCSHWTSTAMP ||
+		    cmd == SIOCGHWTSTAMP ||
+		    cmd == SIOCWANDEV) {
+			err = -EOPNOTSUPP;
+			if (ops->ndo_do_ioctl) {
+				if (netif_device_present(dev))
+					err = ops->ndo_do_ioctl(dev, ifr, cmd);
+				else
+					err = -ENODEV;
+			}
+		} else
+			err = -EINVAL;
+
+	}
+	return err;
+}
+
+/**
+ *	dev_load 	- load a network module
+ *	@net: the applicable net namespace
+ *	@name: name of interface
+ *
+ *	If a network interface is not present and the process has suitable
+ *	privileges this function loads the module. If module loading is not
+ *	available in this kernel then it becomes a nop.
+ */
+
+void dev_load(struct net *net, const char *name)
+{
+	struct net_device *dev;
+	int no_module;
+
+	rcu_read_lock();
+	dev = dev_get_by_name_rcu(net, name);
+	rcu_read_unlock();
+
+	no_module = !dev;
+	if (no_module && capable(CAP_NET_ADMIN))
+		no_module = request_module("netdev-%s", name);
+	if (no_module && capable(CAP_SYS_MODULE))
+		request_module("%s", name);
+}
+EXPORT_SYMBOL(dev_load);
+
+/*
+ *	This function handles all "interface"-type I/O control requests. The actual
+ *	'doing' part of this is dev_ifsioc above.
+ */
+
+/**
+ *	dev_ioctl	-	network device ioctl
+ *	@net: the applicable net namespace
+ *	@cmd: command to issue
+ *	@arg: pointer to a struct ifreq in user space
+ *
+ *	Issue ioctl functions to devices. This is normally called by the
+ *	user space syscall interfaces but can sometimes be useful for
+ *	other purposes. The return value is the return from the syscall if
+ *	positive or a negative errno code on error.
+ */
+
+int dev_ioctl(struct net *net, unsigned int cmd, void __user *arg)
+{
+	struct ifreq ifr;
+	int ret;
+	char *colon;
+
+	/* One special case: SIOCGIFCONF takes ifconf argument
+	   and requires shared lock, because it sleeps writing
+	   to user space.
+	 */
+
+	if (cmd == SIOCGIFCONF) {
+		rtnl_lock();
+		ret = dev_ifconf(net, (char __user *) arg);
+		rtnl_unlock();
+		return ret;
+	}
+	if (cmd == SIOCGIFNAME)
+		return dev_ifname(net, (struct ifreq __user *)arg);
+
+	if (copy_from_user(&ifr, arg, sizeof(struct ifreq)))
+		return -EFAULT;
+
+	ifr.ifr_name[IFNAMSIZ-1] = 0;
+
+	colon = strchr(ifr.ifr_name, ':');
+	if (colon)
+		*colon = 0;
+
+	/*
+	 *	See which interface the caller is talking about.
+	 */
+
+	switch (cmd) {
+	/*
+	 *	These ioctl calls:
+	 *	- can be done by all.
+	 *	- atomic and do not require locking.
+	 *	- return a value
+	 */
+	case SIOCGIFFLAGS:
+	case SIOCGIFMETRIC:
+	case SIOCGIFMTU:
+	case SIOCGIFHWADDR:
+	case SIOCGIFSLAVE:
+	case SIOCGIFMAP:
+	case SIOCGIFINDEX:
+	case SIOCGIFTXQLEN:
+		dev_load(net, ifr.ifr_name);
+		rcu_read_lock();
+		ret = dev_ifsioc_locked(net, &ifr, cmd);
+		rcu_read_unlock();
+		if (!ret) {
+			if (colon)
+				*colon = ':';
+			if (copy_to_user(arg, &ifr,
+					 sizeof(struct ifreq)))
+				ret = -EFAULT;
+		}
+		return ret;
+
+	case SIOCETHTOOL:
+		dev_load(net, ifr.ifr_name);
+		rtnl_lock();
+		ret = dev_ethtool(net, &ifr);
+		rtnl_unlock();
+		if (!ret) {
+			if (colon)
+				*colon = ':';
+			if (copy_to_user(arg, &ifr,
+					 sizeof(struct ifreq)))
+				ret = -EFAULT;
+		}
+		return ret;
+
+	/*
+	 *	These ioctl calls:
+	 *	- require superuser power.
+	 *	- require strict serialization.
+	 *	- return a value
+	 */
+	case SIOCGMIIPHY:
+	case SIOCGMIIREG:
+	case SIOCSIFNAME:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+		dev_load(net, ifr.ifr_name);
+		rtnl_lock();
+		ret = dev_ifsioc(net, &ifr, cmd);
+		rtnl_unlock();
+		if (!ret) {
+			if (colon)
+				*colon = ':';
+			if (copy_to_user(arg, &ifr,
+					 sizeof(struct ifreq)))
+				ret = -EFAULT;
+		}
+		return ret;
+
+	/*
+	 *	These ioctl calls:
+	 *	- require superuser power.
+	 *	- require strict serialization.
+	 *	- do not return a value
+	 */
+	case SIOCSIFMAP:
+	case SIOCSIFTXQLEN:
+		if (!capable(CAP_NET_ADMIN))
+			return -EPERM;
+		/* fall through */
+	/*
+	 *	These ioctl calls:
+	 *	- require local superuser power.
+	 *	- require strict serialization.
+	 *	- do not return a value
+	 */
+	case SIOCSIFFLAGS:
+	case SIOCSIFMETRIC:
+	case SIOCSIFMTU:
+	case SIOCSIFHWADDR:
+	case SIOCSIFSLAVE:
+	case SIOCADDMULTI:
+	case SIOCDELMULTI:
+	case SIOCSIFHWBROADCAST:
+	case SIOCSMIIREG:
+	case SIOCBONDENSLAVE:
+	case SIOCBONDRELEASE:
+	case SIOCBONDSETHWADDR:
+	case SIOCBONDCHANGEACTIVE:
+	case SIOCBRADDIF:
+	case SIOCBRDELIF:
+	case SIOCSHWTSTAMP:
+		if (!ns_capable(net->user_ns, CAP_NET_ADMIN))
+			return -EPERM;
+		/* fall through */
+	case SIOCBONDSLAVEINFOQUERY:
+	case SIOCBONDINFOQUERY:
+		dev_load(net, ifr.ifr_name);
+		rtnl_lock();
+		ret = dev_ifsioc(net, &ifr, cmd);
+		rtnl_unlock();
+		return ret;
+
+	case SIOCGIFMEM:
+		/* Get the per device memory space. We can add this but
+		 * currently do not support it */
+	case SIOCSIFMEM:
+		/* Set the per device memory buffer space.
+		 * Not applicable in our case */
+	case SIOCSIFLINK:
+		return -ENOTTY;
+
+	/*
+	 *	Unknown or private ioctl.
+	 */
+	default:
+		if (cmd == SIOCWANDEV ||
+		    cmd == SIOCGHWTSTAMP ||
+		    (cmd >= SIOCDEVPRIVATE &&
+		     cmd <= SIOCDEVPRIVATE + 15)) {
+			dev_load(net, ifr.ifr_name);
+			rtnl_lock();
+			ret = dev_ifsioc(net, &ifr, cmd);
+			rtnl_unlock();
+			if (!ret && copy_to_user(arg, &ifr,
+						 sizeof(struct ifreq)))
+				ret = -EFAULT;
+			return ret;
+		}
+		/* Take care of Wireless Extensions */
+		if (cmd >= SIOCIWFIRST && cmd <= SIOCIWLAST)
+			return wext_handle_ioctl(net, &ifr, cmd, arg);
+		return -ENOTTY;
+	}
+}

net/core/drop_monitor.c

@@ -0,0 +1,437 @@
+/*
+ * Monitoring code for network dropped packet alerts
+ *
+ * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/string.h>
+#include <linux/if_arp.h>
+#include <linux/inetdevice.h>
+#include <linux/inet.h>
+#include <linux/interrupt.h>
+#include <linux/netpoll.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/netlink.h>
+#include <linux/net_dropmon.h>
+#include <linux/percpu.h>
+#include <linux/timer.h>
+#include <linux/bitops.h>
+#include <linux/slab.h>
+#include <linux/module.h>
+#include <net/genetlink.h>
+#include <net/netevent.h>
+
+#include <trace/events/skb.h>
+#include <trace/events/napi.h>
+
+#include <asm/unaligned.h>
+
+#define TRACE_ON 1
+#define TRACE_OFF 0
+
+/*
+ * Globals, our netlink socket pointer
+ * and the work handle that will send up
+ * netlink alerts
+ */
+static int trace_state = TRACE_OFF;
+static DEFINE_MUTEX(trace_state_mutex);
+
+struct per_cpu_dm_data {
+	spinlock_t		lock;
+	struct sk_buff		*skb;
+	struct work_struct	dm_alert_work;
+	struct timer_list	send_timer;
+};
+
+struct dm_hw_stat_delta {
+	struct net_device *dev;
+	unsigned long last_rx;
+	struct list_head list;
+	struct rcu_head rcu;
+	unsigned long last_drop_val;
+};
+
+static struct genl_family net_drop_monitor_family = {
+	.id             = GENL_ID_GENERATE,
+	.hdrsize        = 0,
+	.name           = "NET_DM",
+	.version        = 2,
+};
+
+static DEFINE_PER_CPU(struct per_cpu_dm_data, dm_cpu_data);
+
+static int dm_hit_limit = 64;
+static int dm_delay = 1;
+static unsigned long dm_hw_check_delta = 2*HZ;
+static LIST_HEAD(hw_stats_list);
+
+static struct sk_buff *reset_per_cpu_data(struct per_cpu_dm_data *data)
+{
+	size_t al;
+	struct net_dm_alert_msg *msg;
+	struct nlattr *nla;
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	al = sizeof(struct net_dm_alert_msg);
+	al += dm_hit_limit * sizeof(struct net_dm_drop_point);
+	al += sizeof(struct nlattr);
+
+	skb = genlmsg_new(al, GFP_KERNEL);
+
+	if (skb) {
+		genlmsg_put(skb, 0, 0, &net_drop_monitor_family,
+				0, NET_DM_CMD_ALERT);
+		nla = nla_reserve(skb, NLA_UNSPEC,
+				  sizeof(struct net_dm_alert_msg));
+		msg = nla_data(nla);
+		memset(msg, 0, al);
+	} else {
+		mod_timer(&data->send_timer, jiffies + HZ / 10);
+	}
+
+	spin_lock_irqsave(&data->lock, flags);
+	swap(data->skb, skb);
+	spin_unlock_irqrestore(&data->lock, flags);
+
+	return skb;
+}
+
+static struct genl_multicast_group dropmon_mcgrps[] = {
+	{ .name = "events", },
+};
+
+static void send_dm_alert(struct work_struct *work)
+{
+	struct sk_buff *skb;
+	struct per_cpu_dm_data *data;
+
+	data = container_of(work, struct per_cpu_dm_data, dm_alert_work);
+
+	skb = reset_per_cpu_data(data);
+
+	if (skb)
+		genlmsg_multicast(&net_drop_monitor_family, skb, 0,
+				  0, GFP_KERNEL);
+}
+
+/*
+ * This is the timer function to delay the sending of an alert
+ * in the event that more drops will arrive during the
+ * hysteresis period.
+ */
+static void sched_send_work(unsigned long _data)
+{
+	struct per_cpu_dm_data *data = (struct per_cpu_dm_data *)_data;
+
+	schedule_work(&data->dm_alert_work);
+}
+
+static void trace_drop_common(struct sk_buff *skb, void *location)
+{
+	struct net_dm_alert_msg *msg;
+	struct nlmsghdr *nlh;
+	struct nlattr *nla;
+	int i;
+	struct sk_buff *dskb;
+	struct per_cpu_dm_data *data;
+	unsigned long flags;
+
+	local_irq_save(flags);
+	data = this_cpu_ptr(&dm_cpu_data);
+	spin_lock(&data->lock);
+	dskb = data->skb;
+
+	if (!dskb)
+		goto out;
+
+	nlh = (struct nlmsghdr *)dskb->data;
+	nla = genlmsg_data(nlmsg_data(nlh));
+	msg = nla_data(nla);
+	for (i = 0; i < msg->entries; i++) {
+		if (!memcmp(&location, msg->points[i].pc, sizeof(void *))) {
+			msg->points[i].count++;
+			goto out;
+		}
+	}
+	if (msg->entries == dm_hit_limit)
+		goto out;
+	/*
+	 * We need to create a new entry
+	 */
+	__nla_reserve_nohdr(dskb, sizeof(struct net_dm_drop_point));
+	nla->nla_len += NLA_ALIGN(sizeof(struct net_dm_drop_point));
+	memcpy(msg->points[msg->entries].pc, &location, sizeof(void *));
+	msg->points[msg->entries].count = 1;
+	msg->entries++;
+
+	if (!timer_pending(&data->send_timer)) {
+		data->send_timer.expires = jiffies + dm_delay * HZ;
+		add_timer(&data->send_timer);
+	}
+
+out:
+	spin_unlock_irqrestore(&data->lock, flags);
+}
+
+static void trace_kfree_skb_hit(void *ignore, struct sk_buff *skb, void *location)
+{
+	trace_drop_common(skb, location);
+}
+
+static void trace_napi_poll_hit(void *ignore, struct napi_struct *napi)
+{
+	struct dm_hw_stat_delta *new_stat;
+
+	/*
+	 * Don't check napi structures with no associated device
+	 */
+	if (!napi->dev)
+		return;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(new_stat, &hw_stats_list, list) {
+		/*
+		 * only add a note to our monitor buffer if:
+		 * 1) this is the dev we received on
+		 * 2) its after the last_rx delta
+		 * 3) our rx_dropped count has gone up
+		 */
+		if ((new_stat->dev == napi->dev)  &&
+		    (time_after(jiffies, new_stat->last_rx + dm_hw_check_delta)) &&
+		    (napi->dev->stats.rx_dropped != new_stat->last_drop_val)) {
+			trace_drop_common(NULL, NULL);
+			new_stat->last_drop_val = napi->dev->stats.rx_dropped;
+			new_stat->last_rx = jiffies;
+			break;
+		}
+	}
+	rcu_read_unlock();
+}
+
+static int set_all_monitor_traces(int state)
+{
+	int rc = 0;
+	struct dm_hw_stat_delta *new_stat = NULL;
+	struct dm_hw_stat_delta *temp;
+
+	mutex_lock(&trace_state_mutex);
+
+	if (state == trace_state) {
+		rc = -EAGAIN;
+		goto out_unlock;
+	}
+
+	switch (state) {
+	case TRACE_ON:
+		if (!try_module_get(THIS_MODULE)) {
+			rc = -ENODEV;
+			break;
+		}
+
+		rc |= register_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+		rc |= register_trace_napi_poll(trace_napi_poll_hit, NULL);
+		break;
+
+	case TRACE_OFF:
+		rc |= unregister_trace_kfree_skb(trace_kfree_skb_hit, NULL);
+		rc |= unregister_trace_napi_poll(trace_napi_poll_hit, NULL);
+
+		tracepoint_synchronize_unregister();
+
+		/*
+		 * Clean the device list
+		 */
+		list_for_each_entry_safe(new_stat, temp, &hw_stats_list, list) {
+			if (new_stat->dev == NULL) {
+				list_del_rcu(&new_stat->list);
+				kfree_rcu(new_stat, rcu);
+			}
+		}
+
+		module_put(THIS_MODULE);
+
+		break;
+	default:
+		rc = 1;
+		break;
+	}
+
+	if (!rc)
+		trace_state = state;
+	else
+		rc = -EINPROGRESS;
+
+out_unlock:
+	mutex_unlock(&trace_state_mutex);
+
+	return rc;
+}
+
+
+static int net_dm_cmd_config(struct sk_buff *skb,
+			struct genl_info *info)
+{
+	return -ENOTSUPP;
+}
+
+static int net_dm_cmd_trace(struct sk_buff *skb,
+			struct genl_info *info)
+{
+	switch (info->genlhdr->cmd) {
+	case NET_DM_CMD_START:
+		return set_all_monitor_traces(TRACE_ON);
+	case NET_DM_CMD_STOP:
+		return set_all_monitor_traces(TRACE_OFF);
+	}
+
+	return -ENOTSUPP;
+}
+
+static int dropmon_net_event(struct notifier_block *ev_block,
+			     unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct dm_hw_stat_delta *new_stat = NULL;
+	struct dm_hw_stat_delta *tmp;
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		new_stat = kzalloc(sizeof(struct dm_hw_stat_delta), GFP_KERNEL);
+
+		if (!new_stat)
+			goto out;
+
+		new_stat->dev = dev;
+		new_stat->last_rx = jiffies;
+		mutex_lock(&trace_state_mutex);
+		list_add_rcu(&new_stat->list, &hw_stats_list);
+		mutex_unlock(&trace_state_mutex);
+		break;
+	case NETDEV_UNREGISTER:
+		mutex_lock(&trace_state_mutex);
+		list_for_each_entry_safe(new_stat, tmp, &hw_stats_list, list) {
+			if (new_stat->dev == dev) {
+				new_stat->dev = NULL;
+				if (trace_state == TRACE_OFF) {
+					list_del_rcu(&new_stat->list);
+					kfree_rcu(new_stat, rcu);
+					break;
+				}
+			}
+		}
+		mutex_unlock(&trace_state_mutex);
+		break;
+	}
+out:
+	return NOTIFY_DONE;
+}
+
+static const struct genl_ops dropmon_ops[] = {
+	{
+		.cmd = NET_DM_CMD_CONFIG,
+		.doit = net_dm_cmd_config,
+	},
+	{
+		.cmd = NET_DM_CMD_START,
+		.doit = net_dm_cmd_trace,
+	},
+	{
+		.cmd = NET_DM_CMD_STOP,
+		.doit = net_dm_cmd_trace,
+	},
+};
+
+static struct notifier_block dropmon_net_notifier = {
+	.notifier_call = dropmon_net_event
+};
+
+static int __init init_net_drop_monitor(void)
+{
+	struct per_cpu_dm_data *data;
+	int cpu, rc;
+
+	pr_info("Initializing network drop monitor service\n");
+
+	if (sizeof(void *) > 8) {
+		pr_err("Unable to store program counters on this arch, Drop monitor failed\n");
+		return -ENOSPC;
+	}
+
+	rc = genl_register_family_with_ops_groups(&net_drop_monitor_family,
+						  dropmon_ops, dropmon_mcgrps);
+	if (rc) {
+		pr_err("Could not create drop monitor netlink family\n");
+		return rc;
+	}
+	WARN_ON(net_drop_monitor_family.mcgrp_offset != NET_DM_GRP_ALERT);
+
+	rc = register_netdevice_notifier(&dropmon_net_notifier);
+	if (rc < 0) {
+		pr_crit("Failed to register netdevice notifier\n");
+		goto out_unreg;
+	}
+
+	rc = 0;
+
+	for_each_possible_cpu(cpu) {
+		data = &per_cpu(dm_cpu_data, cpu);
+		INIT_WORK(&data->dm_alert_work, send_dm_alert);
+		init_timer(&data->send_timer);
+		data->send_timer.data = (unsigned long)data;
+		data->send_timer.function = sched_send_work;
+		spin_lock_init(&data->lock);
+		reset_per_cpu_data(data);
+	}
+
+
+	goto out;
+
+out_unreg:
+	genl_unregister_family(&net_drop_monitor_family);
+out:
+	return rc;
+}
+
+static void exit_net_drop_monitor(void)
+{
+	struct per_cpu_dm_data *data;
+	int cpu;
+
+	BUG_ON(unregister_netdevice_notifier(&dropmon_net_notifier));
+
+	/*
+	 * Because of the module_get/put we do in the trace state change path
+	 * we are guarnateed not to have any current users when we get here
+	 * all we need to do is make sure that we don't have any running timers
+	 * or pending schedule calls
+	 */
+
+	for_each_possible_cpu(cpu) {
+		data = &per_cpu(dm_cpu_data, cpu);
+		del_timer_sync(&data->send_timer);
+		cancel_work_sync(&data->dm_alert_work);
+		/*
+		 * At this point, we should have exclusive access
+		 * to this struct and can free the skb inside it
+		 */
+		kfree_skb(data->skb);
+	}
+
+	BUG_ON(genl_unregister_family(&net_drop_monitor_family));
+}
+
+module_init(init_net_drop_monitor);
+module_exit(exit_net_drop_monitor);
+
+MODULE_LICENSE("GPL v2");
+MODULE_AUTHOR("Neil Horman <nhorman@tuxdriver.com>");
+MODULE_ALIAS_GENL_FAMILY("NET_DM");

net/core/dst.c

@@ -0,0 +1,421 @@
+/*
+ * net/core/dst.c	Protocol independent destination cache.
+ *
+ * Authors:		Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ */
+
+#include <linux/bitops.h>
+#include <linux/errno.h>
+#include <linux/init.h>
+#include <linux/kernel.h>
+#include <linux/workqueue.h>
+#include <linux/mm.h>
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <net/net_namespace.h>
+#include <linux/sched.h>
+#include <linux/prefetch.h>
+
+#include <net/dst.h>
+
+/*
+ * Theory of operations:
+ * 1) We use a list, protected by a spinlock, to add
+ *    new entries from both BH and non-BH context.
+ * 2) In order to keep spinlock held for a small delay,
+ *    we use a second list where are stored long lived
+ *    entries, that are handled by the garbage collect thread
+ *    fired by a workqueue.
+ * 3) This list is guarded by a mutex,
+ *    so that the gc_task and dst_dev_event() can be synchronized.
+ */
+
+/*
+ * We want to keep lock & list close together
+ * to dirty as few cache lines as possible in __dst_free().
+ * As this is not a very strong hint, we dont force an alignment on SMP.
+ */
+static struct {
+	spinlock_t		lock;
+	struct dst_entry	*list;
+	unsigned long		timer_inc;
+	unsigned long		timer_expires;
+} dst_garbage = {
+	.lock = __SPIN_LOCK_UNLOCKED(dst_garbage.lock),
+	.timer_inc = DST_GC_MAX,
+};
+static void dst_gc_task(struct work_struct *work);
+static void ___dst_free(struct dst_entry *dst);
+
+static DECLARE_DELAYED_WORK(dst_gc_work, dst_gc_task);
+
+static DEFINE_MUTEX(dst_gc_mutex);
+/*
+ * long lived entries are maintained in this list, guarded by dst_gc_mutex
+ */
+static struct dst_entry         *dst_busy_list;
+
+static void dst_gc_task(struct work_struct *work)
+{
+	int    delayed = 0;
+	int    work_performed = 0;
+	unsigned long expires = ~0L;
+	struct dst_entry *dst, *next, head;
+	struct dst_entry *last = &head;
+
+	mutex_lock(&dst_gc_mutex);
+	next = dst_busy_list;
+
+loop:
+	while ((dst = next) != NULL) {
+		next = dst->next;
+		prefetch(&next->next);
+		cond_resched();
+		if (likely(atomic_read(&dst->__refcnt))) {
+			last->next = dst;
+			last = dst;
+			delayed++;
+			continue;
+		}
+		work_performed++;
+
+		dst = dst_destroy(dst);
+		if (dst) {
+			/* NOHASH and still referenced. Unless it is already
+			 * on gc list, invalidate it and add to gc list.
+			 *
+			 * Note: this is temporary. Actually, NOHASH dst's
+			 * must be obsoleted when parent is obsoleted.
+			 * But we do not have state "obsoleted, but
+			 * referenced by parent", so it is right.
+			 */
+			if (dst->obsolete > 0)
+				continue;
+
+			___dst_free(dst);
+			dst->next = next;
+			next = dst;
+		}
+	}
+
+	spin_lock_bh(&dst_garbage.lock);
+	next = dst_garbage.list;
+	if (next) {
+		dst_garbage.list = NULL;
+		spin_unlock_bh(&dst_garbage.lock);
+		goto loop;
+	}
+	last->next = NULL;
+	dst_busy_list = head.next;
+	if (!dst_busy_list)
+		dst_garbage.timer_inc = DST_GC_MAX;
+	else {
+		/*
+		 * if we freed less than 1/10 of delayed entries,
+		 * we can sleep longer.
+		 */
+		if (work_performed <= delayed/10) {
+			dst_garbage.timer_expires += dst_garbage.timer_inc;
+			if (dst_garbage.timer_expires > DST_GC_MAX)
+				dst_garbage.timer_expires = DST_GC_MAX;
+			dst_garbage.timer_inc += DST_GC_INC;
+		} else {
+			dst_garbage.timer_inc = DST_GC_INC;
+			dst_garbage.timer_expires = DST_GC_MIN;
+		}
+		expires = dst_garbage.timer_expires;
+		/*
+		 * if the next desired timer is more than 4 seconds in the
+		 * future then round the timer to whole seconds
+		 */
+		if (expires > 4*HZ)
+			expires = round_jiffies_relative(expires);
+		schedule_delayed_work(&dst_gc_work, expires);
+	}
+
+	spin_unlock_bh(&dst_garbage.lock);
+	mutex_unlock(&dst_gc_mutex);
+}
+
+int dst_discard_sk(struct sock *sk, struct sk_buff *skb)
+{
+	kfree_skb(skb);
+	return 0;
+}
+EXPORT_SYMBOL(dst_discard_sk);
+
+const u32 dst_default_metrics[RTAX_MAX + 1] = {
+	/* This initializer is needed to force linker to place this variable
+	 * into const section. Otherwise it might end into bss section.
+	 * We really want to avoid false sharing on this variable, and catch
+	 * any writes on it.
+	 */
+	[RTAX_MAX] = 0xdeadbeef,
+};
+
+
+void *dst_alloc(struct dst_ops *ops, struct net_device *dev,
+		int initial_ref, int initial_obsolete, unsigned short flags)
+{
+	struct dst_entry *dst;
+
+	if (ops->gc && dst_entries_get_fast(ops) > ops->gc_thresh) {
+		if (ops->gc(ops))
+			return NULL;
+	}
+	dst = kmem_cache_alloc(ops->kmem_cachep, GFP_ATOMIC);
+	if (!dst)
+		return NULL;
+	dst->child = NULL;
+	dst->dev = dev;
+	if (dev)
+		dev_hold(dev);
+	dst->ops = ops;
+	dst_init_metrics(dst, dst_default_metrics, true);
+	dst->expires = 0UL;
+	dst->path = dst;
+	dst->from = NULL;
+#ifdef CONFIG_XFRM
+	dst->xfrm = NULL;
+#endif
+	dst->input = dst_discard;
+	dst->output = dst_discard_sk;
+	dst->error = 0;
+	dst->obsolete = initial_obsolete;
+	dst->header_len = 0;
+	dst->trailer_len = 0;
+#ifdef CONFIG_IP_ROUTE_CLASSID
+	dst->tclassid = 0;
+#endif
+	atomic_set(&dst->__refcnt, initial_ref);
+	dst->__use = 0;
+	dst->lastuse = jiffies;
+	dst->flags = flags;
+	dst->pending_confirm = 0;
+	dst->next = NULL;
+	if (!(flags & DST_NOCOUNT))
+		dst_entries_add(ops, 1);
+	return dst;
+}
+EXPORT_SYMBOL(dst_alloc);
+
+static void ___dst_free(struct dst_entry *dst)
+{
+	/* The first case (dev==NULL) is required, when
+	   protocol module is unloaded.
+	 */
+	if (dst->dev == NULL || !(dst->dev->flags&IFF_UP)) {
+		dst->input = dst_discard;
+		dst->output = dst_discard_sk;
+	}
+	dst->obsolete = DST_OBSOLETE_DEAD;
+}
+
+void __dst_free(struct dst_entry *dst)
+{
+	spin_lock_bh(&dst_garbage.lock);
+	___dst_free(dst);
+	dst->next = dst_garbage.list;
+	dst_garbage.list = dst;
+	if (dst_garbage.timer_inc > DST_GC_INC) {
+		dst_garbage.timer_inc = DST_GC_INC;
+		dst_garbage.timer_expires = DST_GC_MIN;
+		mod_delayed_work(system_wq, &dst_gc_work,
+				 dst_garbage.timer_expires);
+	}
+	spin_unlock_bh(&dst_garbage.lock);
+}
+EXPORT_SYMBOL(__dst_free);
+
+struct dst_entry *dst_destroy(struct dst_entry * dst)
+{
+	struct dst_entry *child;
+
+	smp_rmb();
+
+again:
+	child = dst->child;
+
+	if (!(dst->flags & DST_NOCOUNT))
+		dst_entries_add(dst->ops, -1);
+
+	if (dst->ops->destroy)
+		dst->ops->destroy(dst);
+	if (dst->dev)
+		dev_put(dst->dev);
+	kmem_cache_free(dst->ops->kmem_cachep, dst);
+
+	dst = child;
+	if (dst) {
+		int nohash = dst->flags & DST_NOHASH;
+
+		if (atomic_dec_and_test(&dst->__refcnt)) {
+			/* We were real parent of this dst, so kill child. */
+			if (nohash)
+				goto again;
+		} else {
+			/* Child is still referenced, return it for freeing. */
+			if (nohash)
+				return dst;
+			/* Child is still in his hash table */
+		}
+	}
+	return NULL;
+}
+EXPORT_SYMBOL(dst_destroy);
+
+static void dst_destroy_rcu(struct rcu_head *head)
+{
+	struct dst_entry *dst = container_of(head, struct dst_entry, rcu_head);
+
+	dst = dst_destroy(dst);
+	if (dst)
+		__dst_free(dst);
+}
+
+void dst_release(struct dst_entry *dst)
+{
+	if (dst) {
+		int newrefcnt;
+
+		newrefcnt = atomic_dec_return(&dst->__refcnt);
+		WARN_ON(newrefcnt < 0);
+		if (unlikely(dst->flags & DST_NOCACHE) && !newrefcnt)
+			call_rcu(&dst->rcu_head, dst_destroy_rcu);
+	}
+}
+EXPORT_SYMBOL(dst_release);
+
+u32 *dst_cow_metrics_generic(struct dst_entry *dst, unsigned long old)
+{
+	u32 *p = kmalloc(sizeof(u32) * RTAX_MAX, GFP_ATOMIC);
+
+	if (p) {
+		u32 *old_p = __DST_METRICS_PTR(old);
+		unsigned long prev, new;
+
+		memcpy(p, old_p, sizeof(u32) * RTAX_MAX);
+
+		new = (unsigned long) p;
+		prev = cmpxchg(&dst->_metrics, old, new);
+
+		if (prev != old) {
+			kfree(p);
+			p = __DST_METRICS_PTR(prev);
+			if (prev & DST_METRICS_READ_ONLY)
+				p = NULL;
+		}
+	}
+	return p;
+}
+EXPORT_SYMBOL(dst_cow_metrics_generic);
+
+/* Caller asserts that dst_metrics_read_only(dst) is false.  */
+void __dst_destroy_metrics_generic(struct dst_entry *dst, unsigned long old)
+{
+	unsigned long prev, new;
+
+	new = ((unsigned long) dst_default_metrics) | DST_METRICS_READ_ONLY;
+	prev = cmpxchg(&dst->_metrics, old, new);
+	if (prev == old)
+		kfree(__DST_METRICS_PTR(old));
+}
+EXPORT_SYMBOL(__dst_destroy_metrics_generic);
+
+/**
+ * __skb_dst_set_noref - sets skb dst, without a reference
+ * @skb: buffer
+ * @dst: dst entry
+ * @force: if force is set, use noref version even for DST_NOCACHE entries
+ *
+ * Sets skb dst, assuming a reference was not taken on dst
+ * skb_dst_drop() should not dst_release() this dst
+ */
+void __skb_dst_set_noref(struct sk_buff *skb, struct dst_entry *dst, bool force)
+{
+	WARN_ON(!rcu_read_lock_held() && !rcu_read_lock_bh_held());
+	/* If dst not in cache, we must take a reference, because
+	 * dst_release() will destroy dst as soon as its refcount becomes zero
+	 */
+	if (unlikely((dst->flags & DST_NOCACHE) && !force)) {
+		dst_hold(dst);
+		skb_dst_set(skb, dst);
+	} else {
+		skb->_skb_refdst = (unsigned long)dst | SKB_DST_NOREF;
+	}
+}
+EXPORT_SYMBOL(__skb_dst_set_noref);
+
+/* Dirty hack. We did it in 2.2 (in __dst_free),
+ * we have _very_ good reasons not to repeat
+ * this mistake in 2.3, but we have no choice
+ * now. _It_ _is_ _explicit_ _deliberate_
+ * _race_ _condition_.
+ *
+ * Commented and originally written by Alexey.
+ */
+static void dst_ifdown(struct dst_entry *dst, struct net_device *dev,
+		       int unregister)
+{
+	if (dst->ops->ifdown)
+		dst->ops->ifdown(dst, dev, unregister);
+
+	if (dev != dst->dev)
+		return;
+
+	if (!unregister) {
+		dst->input = dst_discard;
+		dst->output = dst_discard_sk;
+	} else {
+		dst->dev = dev_net(dst->dev)->loopback_dev;
+		dev_hold(dst->dev);
+		dev_put(dev);
+	}
+}
+
+static int dst_dev_event(struct notifier_block *this, unsigned long event,
+			 void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct dst_entry *dst, *last = NULL;
+
+	switch (event) {
+	case NETDEV_UNREGISTER_FINAL:
+	case NETDEV_DOWN:
+		mutex_lock(&dst_gc_mutex);
+		for (dst = dst_busy_list; dst; dst = dst->next) {
+			last = dst;
+			dst_ifdown(dst, dev, event != NETDEV_DOWN);
+		}
+
+		spin_lock_bh(&dst_garbage.lock);
+		dst = dst_garbage.list;
+		dst_garbage.list = NULL;
+		spin_unlock_bh(&dst_garbage.lock);
+
+		if (last)
+			last->next = dst;
+		else
+			dst_busy_list = dst;
+		for (; dst; dst = dst->next)
+			dst_ifdown(dst, dev, event != NETDEV_DOWN);
+		mutex_unlock(&dst_gc_mutex);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block dst_dev_notifier = {
+	.notifier_call	= dst_dev_event,
+	.priority = -10, /* must be called after other network notifiers */
+};
+
+void __init dst_init(void)
+{
+	register_netdevice_notifier(&dst_dev_notifier);
+}

net/core/fib_rules.c

@@ -0,0 +1,854 @@
+/*
+ * net/core/fib_rules.c		Generic Routing Rules
+ *
+ *	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, version 2.
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/module.h>
+#include <net/net_namespace.h>
+#include <net/sock.h>
+#include <net/fib_rules.h>
+
+int fib_default_rule_add(struct fib_rules_ops *ops,
+			 u32 pref, u32 table, u32 flags)
+{
+	struct fib_rule *r;
+
+	r = kzalloc(ops->rule_size, GFP_KERNEL);
+	if (r == NULL)
+		return -ENOMEM;
+
+	atomic_set(&r->refcnt, 1);
+	r->action = FR_ACT_TO_TBL;
+	r->pref = pref;
+	r->table = table;
+	r->flags = flags;
+	r->uid_start = INVALID_UID;
+	r->uid_end = INVALID_UID;
+	r->fr_net = hold_net(ops->fro_net);
+
+	r->suppress_prefixlen = -1;
+	r->suppress_ifgroup = -1;
+
+	/* The lock is not required here, the list in unreacheable
+	 * at the moment this function is called */
+	list_add_tail(&r->list, &ops->rules_list);
+	return 0;
+}
+EXPORT_SYMBOL(fib_default_rule_add);
+
+u32 fib_default_rule_pref(struct fib_rules_ops *ops)
+{
+	struct list_head *pos;
+	struct fib_rule *rule;
+
+	if (!list_empty(&ops->rules_list)) {
+		pos = ops->rules_list.next;
+		if (pos->next != &ops->rules_list) {
+			rule = list_entry(pos->next, struct fib_rule, list);
+			if (rule->pref)
+				return rule->pref - 1;
+		}
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(fib_default_rule_pref);
+
+static void notify_rule_change(int event, struct fib_rule *rule,
+			       struct fib_rules_ops *ops, struct nlmsghdr *nlh,
+			       u32 pid);
+
+static struct fib_rules_ops *lookup_rules_ops(struct net *net, int family)
+{
+	struct fib_rules_ops *ops;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ops, &net->rules_ops, list) {
+		if (ops->family == family) {
+			if (!try_module_get(ops->owner))
+				ops = NULL;
+			rcu_read_unlock();
+			return ops;
+		}
+	}
+	rcu_read_unlock();
+
+	return NULL;
+}
+
+static void rules_ops_put(struct fib_rules_ops *ops)
+{
+	if (ops)
+		module_put(ops->owner);
+}
+
+static void flush_route_cache(struct fib_rules_ops *ops)
+{
+	if (ops->flush_cache)
+		ops->flush_cache(ops);
+}
+
+static int __fib_rules_register(struct fib_rules_ops *ops)
+{
+	int err = -EEXIST;
+	struct fib_rules_ops *o;
+	struct net *net;
+
+	net = ops->fro_net;
+
+	if (ops->rule_size < sizeof(struct fib_rule))
+		return -EINVAL;
+
+	if (ops->match == NULL || ops->configure == NULL ||
+	    ops->compare == NULL || ops->fill == NULL ||
+	    ops->action == NULL)
+		return -EINVAL;
+
+	spin_lock(&net->rules_mod_lock);
+	list_for_each_entry(o, &net->rules_ops, list)
+		if (ops->family == o->family)
+			goto errout;
+
+	hold_net(net);
+	list_add_tail_rcu(&ops->list, &net->rules_ops);
+	err = 0;
+errout:
+	spin_unlock(&net->rules_mod_lock);
+
+	return err;
+}
+
+struct fib_rules_ops *
+fib_rules_register(const struct fib_rules_ops *tmpl, struct net *net)
+{
+	struct fib_rules_ops *ops;
+	int err;
+
+	ops = kmemdup(tmpl, sizeof(*ops), GFP_KERNEL);
+	if (ops == NULL)
+		return ERR_PTR(-ENOMEM);
+
+	INIT_LIST_HEAD(&ops->rules_list);
+	ops->fro_net = net;
+
+	err = __fib_rules_register(ops);
+	if (err) {
+		kfree(ops);
+		ops = ERR_PTR(err);
+	}
+
+	return ops;
+}
+EXPORT_SYMBOL_GPL(fib_rules_register);
+
+static void fib_rules_cleanup_ops(struct fib_rules_ops *ops)
+{
+	struct fib_rule *rule, *tmp;
+
+	list_for_each_entry_safe(rule, tmp, &ops->rules_list, list) {
+		list_del_rcu(&rule->list);
+		if (ops->delete)
+			ops->delete(rule);
+		fib_rule_put(rule);
+	}
+}
+
+static void fib_rules_put_rcu(struct rcu_head *head)
+{
+	struct fib_rules_ops *ops = container_of(head, struct fib_rules_ops, rcu);
+	struct net *net = ops->fro_net;
+
+	release_net(net);
+	kfree(ops);
+}
+
+void fib_rules_unregister(struct fib_rules_ops *ops)
+{
+	struct net *net = ops->fro_net;
+
+	spin_lock(&net->rules_mod_lock);
+	list_del_rcu(&ops->list);
+	fib_rules_cleanup_ops(ops);
+	spin_unlock(&net->rules_mod_lock);
+
+	call_rcu(&ops->rcu, fib_rules_put_rcu);
+}
+EXPORT_SYMBOL_GPL(fib_rules_unregister);
+
+static inline kuid_t fib_nl_uid(struct nlattr *nla)
+{
+	return make_kuid(current_user_ns(), nla_get_u32(nla));
+}
+
+static int nla_put_uid(struct sk_buff *skb, int idx, kuid_t uid)
+{
+	return nla_put_u32(skb, idx, from_kuid_munged(current_user_ns(), uid));
+}
+
+static int fib_uid_range_match(struct flowi *fl, struct fib_rule *rule)
+{
+	return (!uid_valid(rule->uid_start) && !uid_valid(rule->uid_end)) ||
+	       (uid_gte(fl->flowi_uid, rule->uid_start) &&
+		uid_lte(fl->flowi_uid, rule->uid_end));
+}
+
+static int fib_rule_match(struct fib_rule *rule, struct fib_rules_ops *ops,
+			  struct flowi *fl, int flags)
+{
+	int ret = 0;
+
+	if (rule->iifindex && (rule->iifindex != fl->flowi_iif))
+		goto out;
+
+	if (rule->oifindex && (rule->oifindex != fl->flowi_oif))
+		goto out;
+
+	if ((rule->mark ^ fl->flowi_mark) & rule->mark_mask)
+		goto out;
+
+	if (!fib_uid_range_match(fl, rule))
+		goto out;
+
+	ret = ops->match(rule, fl, flags);
+out:
+	return (rule->flags & FIB_RULE_INVERT) ? !ret : ret;
+}
+
+int fib_rules_lookup(struct fib_rules_ops *ops, struct flowi *fl,
+		     int flags, struct fib_lookup_arg *arg)
+{
+	struct fib_rule *rule;
+	int err;
+
+	rcu_read_lock();
+
+	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+jumped:
+		if (!fib_rule_match(rule, ops, fl, flags))
+			continue;
+
+		if (rule->action == FR_ACT_GOTO) {
+			struct fib_rule *target;
+
+			target = rcu_dereference(rule->ctarget);
+			if (target == NULL) {
+				continue;
+			} else {
+				rule = target;
+				goto jumped;
+			}
+		} else if (rule->action == FR_ACT_NOP)
+			continue;
+		else
+			err = ops->action(rule, fl, flags, arg);
+
+		if (!err && ops->suppress && ops->suppress(rule, arg))
+			continue;
+
+		if (err != -EAGAIN) {
+			if ((arg->flags & FIB_LOOKUP_NOREF) ||
+			    likely(atomic_inc_not_zero(&rule->refcnt))) {
+				arg->rule = rule;
+				goto out;
+			}
+			break;
+		}
+	}
+
+	err = -ESRCH;
+out:
+	rcu_read_unlock();
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(fib_rules_lookup);
+
+static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb,
+			    struct fib_rules_ops *ops)
+{
+	int err = -EINVAL;
+
+	if (frh->src_len)
+		if (tb[FRA_SRC] == NULL ||
+		    frh->src_len > (ops->addr_size * 8) ||
+		    nla_len(tb[FRA_SRC]) != ops->addr_size)
+			goto errout;
+
+	if (frh->dst_len)
+		if (tb[FRA_DST] == NULL ||
+		    frh->dst_len > (ops->addr_size * 8) ||
+		    nla_len(tb[FRA_DST]) != ops->addr_size)
+			goto errout;
+
+	err = 0;
+errout:
+	return err;
+}
+
+static int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct fib_rule_hdr *frh = nlmsg_data(nlh);
+	struct fib_rules_ops *ops = NULL;
+	struct fib_rule *rule, *r, *last = NULL;
+	struct nlattr *tb[FRA_MAX+1];
+	int err = -EINVAL, unresolved = 0;
+
+	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
+		goto errout;
+
+	ops = lookup_rules_ops(net, frh->family);
+	if (ops == NULL) {
+		err = -EAFNOSUPPORT;
+		goto errout;
+	}
+
+	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy);
+	if (err < 0)
+		goto errout;
+
+	err = validate_rulemsg(frh, tb, ops);
+	if (err < 0)
+		goto errout;
+
+	rule = kzalloc(ops->rule_size, GFP_KERNEL);
+	if (rule == NULL) {
+		err = -ENOMEM;
+		goto errout;
+	}
+	rule->fr_net = hold_net(net);
+
+	if (tb[FRA_PRIORITY])
+		rule->pref = nla_get_u32(tb[FRA_PRIORITY]);
+
+	if (tb[FRA_IIFNAME]) {
+		struct net_device *dev;
+
+		rule->iifindex = -1;
+		nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ);
+		dev = __dev_get_by_name(net, rule->iifname);
+		if (dev)
+			rule->iifindex = dev->ifindex;
+	}
+
+	if (tb[FRA_OIFNAME]) {
+		struct net_device *dev;
+
+		rule->oifindex = -1;
+		nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ);
+		dev = __dev_get_by_name(net, rule->oifname);
+		if (dev)
+			rule->oifindex = dev->ifindex;
+	}
+
+	if (tb[FRA_FWMARK]) {
+		rule->mark = nla_get_u32(tb[FRA_FWMARK]);
+		if (rule->mark)
+			/* compatibility: if the mark value is non-zero all bits
+			 * are compared unless a mask is explicitly specified.
+			 */
+			rule->mark_mask = 0xFFFFFFFF;
+	}
+
+	if (tb[FRA_FWMASK])
+		rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]);
+
+	rule->action = frh->action;
+	rule->flags = frh->flags;
+	rule->table = frh_get_table(frh, tb);
+	if (tb[FRA_SUPPRESS_PREFIXLEN])
+		rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]);
+	else
+		rule->suppress_prefixlen = -1;
+
+	if (tb[FRA_SUPPRESS_IFGROUP])
+		rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]);
+	else
+		rule->suppress_ifgroup = -1;
+
+	if (!tb[FRA_PRIORITY] && ops->default_pref)
+		rule->pref = ops->default_pref(ops);
+
+	err = -EINVAL;
+	if (tb[FRA_GOTO]) {
+		if (rule->action != FR_ACT_GOTO)
+			goto errout_free;
+
+		rule->target = nla_get_u32(tb[FRA_GOTO]);
+		/* Backward jumps are prohibited to avoid endless loops */
+		if (rule->target <= rule->pref)
+			goto errout_free;
+
+		list_for_each_entry(r, &ops->rules_list, list) {
+			if (r->pref == rule->target) {
+				RCU_INIT_POINTER(rule->ctarget, r);
+				break;
+			}
+		}
+
+		if (rcu_dereference_protected(rule->ctarget, 1) == NULL)
+			unresolved = 1;
+	} else if (rule->action == FR_ACT_GOTO)
+		goto errout_free;
+
+	/* UID start and end must either both be valid or both unspecified. */
+	rule->uid_start = rule->uid_end = INVALID_UID;
+	if (tb[FRA_UID_START] || tb[FRA_UID_END]) {
+		if (tb[FRA_UID_START] && tb[FRA_UID_END]) {
+			rule->uid_start = fib_nl_uid(tb[FRA_UID_START]);
+			rule->uid_end = fib_nl_uid(tb[FRA_UID_END]);
+		}
+		if (!uid_valid(rule->uid_start) ||
+		    !uid_valid(rule->uid_end) ||
+		    !uid_lte(rule->uid_start, rule->uid_end))
+		goto errout_free;
+	}
+
+	err = ops->configure(rule, skb, frh, tb);
+	if (err < 0)
+		goto errout_free;
+
+	list_for_each_entry(r, &ops->rules_list, list) {
+		if (r->pref > rule->pref)
+			break;
+		last = r;
+	}
+
+	fib_rule_get(rule);
+
+	if (last)
+		list_add_rcu(&rule->list, &last->list);
+	else
+		list_add_rcu(&rule->list, &ops->rules_list);
+
+	if (ops->unresolved_rules) {
+		/*
+		 * There are unresolved goto rules in the list, check if
+		 * any of them are pointing to this new rule.
+		 */
+		list_for_each_entry(r, &ops->rules_list, list) {
+			if (r->action == FR_ACT_GOTO &&
+			    r->target == rule->pref &&
+			    rtnl_dereference(r->ctarget) == NULL) {
+				rcu_assign_pointer(r->ctarget, rule);
+				if (--ops->unresolved_rules == 0)
+					break;
+			}
+		}
+	}
+
+	if (rule->action == FR_ACT_GOTO)
+		ops->nr_goto_rules++;
+
+	if (unresolved)
+		ops->unresolved_rules++;
+
+	notify_rule_change(RTM_NEWRULE, rule, ops, nlh, NETLINK_CB(skb).portid);
+	flush_route_cache(ops);
+	rules_ops_put(ops);
+	return 0;
+
+errout_free:
+	release_net(rule->fr_net);
+	kfree(rule);
+errout:
+	rules_ops_put(ops);
+	return err;
+}
+
+static int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr* nlh)
+{
+	struct net *net = sock_net(skb->sk);
+	struct fib_rule_hdr *frh = nlmsg_data(nlh);
+	struct fib_rules_ops *ops = NULL;
+	struct fib_rule *rule, *tmp;
+	struct nlattr *tb[FRA_MAX+1];
+	int err = -EINVAL;
+
+	if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh)))
+		goto errout;
+
+	ops = lookup_rules_ops(net, frh->family);
+	if (ops == NULL) {
+		err = -EAFNOSUPPORT;
+		goto errout;
+	}
+
+	err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy);
+	if (err < 0)
+		goto errout;
+
+	err = validate_rulemsg(frh, tb, ops);
+	if (err < 0)
+		goto errout;
+
+	list_for_each_entry(rule, &ops->rules_list, list) {
+		if (frh->action && (frh->action != rule->action))
+			continue;
+
+		if (frh_get_table(frh, tb) &&
+		    (frh_get_table(frh, tb) != rule->table))
+			continue;
+
+		if (tb[FRA_PRIORITY] &&
+		    (rule->pref != nla_get_u32(tb[FRA_PRIORITY])))
+			continue;
+
+		if (tb[FRA_IIFNAME] &&
+		    nla_strcmp(tb[FRA_IIFNAME], rule->iifname))
+			continue;
+
+		if (tb[FRA_OIFNAME] &&
+		    nla_strcmp(tb[FRA_OIFNAME], rule->oifname))
+			continue;
+
+		if (tb[FRA_FWMARK] &&
+		    (rule->mark != nla_get_u32(tb[FRA_FWMARK])))
+			continue;
+
+		if (tb[FRA_FWMASK] &&
+		    (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK])))
+			continue;
+
+		if (tb[FRA_UID_START] &&
+		    !uid_eq(rule->uid_start, fib_nl_uid(tb[FRA_UID_START])))
+			continue;
+
+		if (tb[FRA_UID_END] &&
+		    !uid_eq(rule->uid_end, fib_nl_uid(tb[FRA_UID_END])))
+			continue;
+
+		if (!ops->compare(rule, frh, tb))
+			continue;
+
+		if (rule->flags & FIB_RULE_PERMANENT) {
+			err = -EPERM;
+			goto errout;
+		}
+
+		list_del_rcu(&rule->list);
+
+		if (rule->action == FR_ACT_GOTO) {
+			ops->nr_goto_rules--;
+			if (rtnl_dereference(rule->ctarget) == NULL)
+				ops->unresolved_rules--;
+		}
+
+		/*
+		 * Check if this rule is a target to any of them. If so,
+		 * disable them. As this operation is eventually very
+		 * expensive, it is only performed if goto rules have
+		 * actually been added.
+		 */
+		if (ops->nr_goto_rules > 0) {
+			list_for_each_entry(tmp, &ops->rules_list, list) {
+				if (rtnl_dereference(tmp->ctarget) == rule) {
+					RCU_INIT_POINTER(tmp->ctarget, NULL);
+					ops->unresolved_rules++;
+				}
+			}
+		}
+
+		notify_rule_change(RTM_DELRULE, rule, ops, nlh,
+				   NETLINK_CB(skb).portid);
+		if (ops->delete)
+			ops->delete(rule);
+		fib_rule_put(rule);
+		flush_route_cache(ops);
+		rules_ops_put(ops);
+		return 0;
+	}
+
+	err = -ENOENT;
+errout:
+	rules_ops_put(ops);
+	return err;
+}
+
+static inline size_t fib_rule_nlmsg_size(struct fib_rules_ops *ops,
+					 struct fib_rule *rule)
+{
+	size_t payload = NLMSG_ALIGN(sizeof(struct fib_rule_hdr))
+			 + nla_total_size(IFNAMSIZ) /* FRA_IIFNAME */
+			 + nla_total_size(IFNAMSIZ) /* FRA_OIFNAME */
+			 + nla_total_size(4) /* FRA_PRIORITY */
+			 + nla_total_size(4) /* FRA_TABLE */
+			 + nla_total_size(4) /* FRA_SUPPRESS_PREFIXLEN */
+			 + nla_total_size(4) /* FRA_SUPPRESS_IFGROUP */
+			 + nla_total_size(4) /* FRA_FWMARK */
+			 + nla_total_size(4) /* FRA_FWMASK */
+			 + nla_total_size(4) /* FRA_UID_START */
+			 + nla_total_size(4); /* FRA_UID_END */
+
+	if (ops->nlmsg_payload)
+		payload += ops->nlmsg_payload(rule);
+
+	return payload;
+}
+
+static int fib_nl_fill_rule(struct sk_buff *skb, struct fib_rule *rule,
+			    u32 pid, u32 seq, int type, int flags,
+			    struct fib_rules_ops *ops)
+{
+	struct nlmsghdr *nlh;
+	struct fib_rule_hdr *frh;
+
+	nlh = nlmsg_put(skb, pid, seq, type, sizeof(*frh), flags);
+	if (nlh == NULL)
+		return -EMSGSIZE;
+
+	frh = nlmsg_data(nlh);
+	frh->family = ops->family;
+	frh->table = rule->table;
+	if (nla_put_u32(skb, FRA_TABLE, rule->table))
+		goto nla_put_failure;
+	if (nla_put_u32(skb, FRA_SUPPRESS_PREFIXLEN, rule->suppress_prefixlen))
+		goto nla_put_failure;
+	frh->res1 = 0;
+	frh->res2 = 0;
+	frh->action = rule->action;
+	frh->flags = rule->flags;
+
+	if (rule->action == FR_ACT_GOTO &&
+	    rcu_access_pointer(rule->ctarget) == NULL)
+		frh->flags |= FIB_RULE_UNRESOLVED;
+
+	if (rule->iifname[0]) {
+		if (nla_put_string(skb, FRA_IIFNAME, rule->iifname))
+			goto nla_put_failure;
+		if (rule->iifindex == -1)
+			frh->flags |= FIB_RULE_IIF_DETACHED;
+	}
+
+	if (rule->oifname[0]) {
+		if (nla_put_string(skb, FRA_OIFNAME, rule->oifname))
+			goto nla_put_failure;
+		if (rule->oifindex == -1)
+			frh->flags |= FIB_RULE_OIF_DETACHED;
+	}
+
+	if ((rule->pref &&
+	     nla_put_u32(skb, FRA_PRIORITY, rule->pref)) ||
+	    (rule->mark &&
+	     nla_put_u32(skb, FRA_FWMARK, rule->mark)) ||
+	    ((rule->mark_mask || rule->mark) &&
+	     nla_put_u32(skb, FRA_FWMASK, rule->mark_mask)) ||
+	    (rule->target &&
+	     nla_put_u32(skb, FRA_GOTO, rule->target)) ||
+	    (uid_valid(rule->uid_start) &&
+	     nla_put_uid(skb, FRA_UID_START, rule->uid_start)) ||
+	    (uid_valid(rule->uid_end) &&
+	     nla_put_uid(skb, FRA_UID_END, rule->uid_end)))
+		goto nla_put_failure;
+
+	if (rule->suppress_ifgroup != -1) {
+		if (nla_put_u32(skb, FRA_SUPPRESS_IFGROUP, rule->suppress_ifgroup))
+			goto nla_put_failure;
+	}
+
+	if (ops->fill(rule, skb, frh) < 0)
+		goto nla_put_failure;
+
+	return nlmsg_end(skb, nlh);
+
+nla_put_failure:
+	nlmsg_cancel(skb, nlh);
+	return -EMSGSIZE;
+}
+
+static int dump_rules(struct sk_buff *skb, struct netlink_callback *cb,
+		      struct fib_rules_ops *ops)
+{
+	int idx = 0;
+	struct fib_rule *rule;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(rule, &ops->rules_list, list) {
+		if (idx < cb->args[1])
+			goto skip;
+
+		if (fib_nl_fill_rule(skb, rule, NETLINK_CB(cb->skb).portid,
+				     cb->nlh->nlmsg_seq, RTM_NEWRULE,
+				     NLM_F_MULTI, ops) < 0)
+			break;
+skip:
+		idx++;
+	}
+	rcu_read_unlock();
+	cb->args[1] = idx;
+	rules_ops_put(ops);
+
+	return skb->len;
+}
+
+static int fib_nl_dumprule(struct sk_buff *skb, struct netlink_callback *cb)
+{
+	struct net *net = sock_net(skb->sk);
+	struct fib_rules_ops *ops;
+	int idx = 0, family;
+
+	family = rtnl_msg_family(cb->nlh);
+	if (family != AF_UNSPEC) {
+		/* Protocol specific dump request */
+		ops = lookup_rules_ops(net, family);
+		if (ops == NULL)
+			return -EAFNOSUPPORT;
+
+		return dump_rules(skb, cb, ops);
+	}
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(ops, &net->rules_ops, list) {
+		if (idx < cb->args[0] || !try_module_get(ops->owner))
+			goto skip;
+
+		if (dump_rules(skb, cb, ops) < 0)
+			break;
+
+		cb->args[1] = 0;
+skip:
+		idx++;
+	}
+	rcu_read_unlock();
+	cb->args[0] = idx;
+
+	return skb->len;
+}
+
+static void notify_rule_change(int event, struct fib_rule *rule,
+			       struct fib_rules_ops *ops, struct nlmsghdr *nlh,
+			       u32 pid)
+{
+	struct net *net;
+	struct sk_buff *skb;
+	int err = -ENOBUFS;
+
+	net = ops->fro_net;
+	skb = nlmsg_new(fib_rule_nlmsg_size(ops, rule), GFP_KERNEL);
+	if (skb == NULL)
+		goto errout;
+
+	err = fib_nl_fill_rule(skb, rule, pid, nlh->nlmsg_seq, event, 0, ops);
+	if (err < 0) {
+		/* -EMSGSIZE implies BUG in fib_rule_nlmsg_size() */
+		WARN_ON(err == -EMSGSIZE);
+		kfree_skb(skb);
+		goto errout;
+	}
+
+	rtnl_notify(skb, net, pid, ops->nlgroup, nlh, GFP_KERNEL);
+	return;
+errout:
+	if (err < 0)
+		rtnl_set_sk_err(net, ops->nlgroup, err);
+}
+
+static void attach_rules(struct list_head *rules, struct net_device *dev)
+{
+	struct fib_rule *rule;
+
+	list_for_each_entry(rule, rules, list) {
+		if (rule->iifindex == -1 &&
+		    strcmp(dev->name, rule->iifname) == 0)
+			rule->iifindex = dev->ifindex;
+		if (rule->oifindex == -1 &&
+		    strcmp(dev->name, rule->oifname) == 0)
+			rule->oifindex = dev->ifindex;
+	}
+}
+
+static void detach_rules(struct list_head *rules, struct net_device *dev)
+{
+	struct fib_rule *rule;
+
+	list_for_each_entry(rule, rules, list) {
+		if (rule->iifindex == dev->ifindex)
+			rule->iifindex = -1;
+		if (rule->oifindex == dev->ifindex)
+			rule->oifindex = -1;
+	}
+}
+
+
+static int fib_rules_event(struct notifier_block *this, unsigned long event,
+			   void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct net *net = dev_net(dev);
+	struct fib_rules_ops *ops;
+
+	ASSERT_RTNL();
+
+	switch (event) {
+	case NETDEV_REGISTER:
+		list_for_each_entry(ops, &net->rules_ops, list)
+			attach_rules(&ops->rules_list, dev);
+		break;
+
+	case NETDEV_CHANGENAME:
+		list_for_each_entry(ops, &net->rules_ops, list) {
+			detach_rules(&ops->rules_list, dev);
+			attach_rules(&ops->rules_list, dev);
+		}
+		break;
+
+	case NETDEV_UNREGISTER:
+		list_for_each_entry(ops, &net->rules_ops, list)
+			detach_rules(&ops->rules_list, dev);
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block fib_rules_notifier = {
+	.notifier_call = fib_rules_event,
+};
+
+static int __net_init fib_rules_net_init(struct net *net)
+{
+	INIT_LIST_HEAD(&net->rules_ops);
+	spin_lock_init(&net->rules_mod_lock);
+	return 0;
+}
+
+static struct pernet_operations fib_rules_net_ops = {
+	.init = fib_rules_net_init,
+};
+
+static int __init fib_rules_init(void)
+{
+	int err;
+	rtnl_register(PF_UNSPEC, RTM_NEWRULE, fib_nl_newrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_DELRULE, fib_nl_delrule, NULL, NULL);
+	rtnl_register(PF_UNSPEC, RTM_GETRULE, NULL, fib_nl_dumprule, NULL);
+
+	err = register_pernet_subsys(&fib_rules_net_ops);
+	if (err < 0)
+		goto fail;
+
+	err = register_netdevice_notifier(&fib_rules_notifier);
+	if (err < 0)
+		goto fail_unregister;
+
+	return 0;
+
+fail_unregister:
+	unregister_pernet_subsys(&fib_rules_net_ops);
+fail:
+	rtnl_unregister(PF_UNSPEC, RTM_NEWRULE);
+	rtnl_unregister(PF_UNSPEC, RTM_DELRULE);
+	rtnl_unregister(PF_UNSPEC, RTM_GETRULE);
+	return err;
+}
+
+subsys_initcall(fib_rules_init);

net/core/flow.c

@@ -0,0 +1,511 @@
+/* flow.c: Generic flow cache.
+ *
+ * Copyright (C) 2003 Alexey N. Kuznetsov (kuznet@ms2.inr.ac.ru)
+ * Copyright (C) 2003 David S. Miller (davem@redhat.com)
+ */
+
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/list.h>
+#include <linux/jhash.h>
+#include <linux/interrupt.h>
+#include <linux/mm.h>
+#include <linux/random.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/smp.h>
+#include <linux/completion.h>
+#include <linux/percpu.h>
+#include <linux/bitops.h>
+#include <linux/notifier.h>
+#include <linux/cpu.h>
+#include <linux/cpumask.h>
+#include <linux/mutex.h>
+#include <net/flow.h>
+#include <linux/atomic.h>
+#include <linux/security.h>
+#include <net/net_namespace.h>
+
+struct flow_cache_entry {
+	union {
+		struct hlist_node	hlist;
+		struct list_head	gc_list;
+	} u;
+	struct net			*net;
+	u16				family;
+	u8				dir;
+	u32				genid;
+	struct flowi			key;
+	struct flow_cache_object	*object;
+};
+
+struct flow_flush_info {
+	struct flow_cache		*cache;
+	atomic_t			cpuleft;
+	struct completion		completion;
+};
+
+static struct kmem_cache *flow_cachep __read_mostly;
+
+#define flow_cache_hash_size(cache)	(1 << (cache)->hash_shift)
+#define FLOW_HASH_RND_PERIOD		(10 * 60 * HZ)
+
+static void flow_cache_new_hashrnd(unsigned long arg)
+{
+	struct flow_cache *fc = (void *) arg;
+	int i;
+
+	for_each_possible_cpu(i)
+		per_cpu_ptr(fc->percpu, i)->hash_rnd_recalc = 1;
+
+	fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
+	add_timer(&fc->rnd_timer);
+}
+
+static int flow_entry_valid(struct flow_cache_entry *fle,
+				struct netns_xfrm *xfrm)
+{
+	if (atomic_read(&xfrm->flow_cache_genid) != fle->genid)
+		return 0;
+	if (fle->object && !fle->object->ops->check(fle->object))
+		return 0;
+	return 1;
+}
+
+static void flow_entry_kill(struct flow_cache_entry *fle,
+				struct netns_xfrm *xfrm)
+{
+	if (fle->object)
+		fle->object->ops->delete(fle->object);
+	kmem_cache_free(flow_cachep, fle);
+}
+
+static void flow_cache_gc_task(struct work_struct *work)
+{
+	struct list_head gc_list;
+	struct flow_cache_entry *fce, *n;
+	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+						flow_cache_gc_work);
+
+	INIT_LIST_HEAD(&gc_list);
+	spin_lock_bh(&xfrm->flow_cache_gc_lock);
+	list_splice_tail_init(&xfrm->flow_cache_gc_list, &gc_list);
+	spin_unlock_bh(&xfrm->flow_cache_gc_lock);
+
+	list_for_each_entry_safe(fce, n, &gc_list, u.gc_list)
+		flow_entry_kill(fce, xfrm);
+}
+
+static void flow_cache_queue_garbage(struct flow_cache_percpu *fcp,
+				     int deleted, struct list_head *gc_list,
+				     struct netns_xfrm *xfrm)
+{
+	if (deleted) {
+		fcp->hash_count -= deleted;
+		spin_lock_bh(&xfrm->flow_cache_gc_lock);
+		list_splice_tail(gc_list, &xfrm->flow_cache_gc_list);
+		spin_unlock_bh(&xfrm->flow_cache_gc_lock);
+		schedule_work(&xfrm->flow_cache_gc_work);
+	}
+}
+
+static void __flow_cache_shrink(struct flow_cache *fc,
+				struct flow_cache_percpu *fcp,
+				int shrink_to)
+{
+	struct flow_cache_entry *fle;
+	struct hlist_node *tmp;
+	LIST_HEAD(gc_list);
+	int i, deleted = 0;
+	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+						flow_cache_global);
+
+	for (i = 0; i < flow_cache_hash_size(fc); i++) {
+		int saved = 0;
+
+		hlist_for_each_entry_safe(fle, tmp,
+					  &fcp->hash_table[i], u.hlist) {
+			if (saved < shrink_to &&
+			    flow_entry_valid(fle, xfrm)) {
+				saved++;
+			} else {
+				deleted++;
+				hlist_del(&fle->u.hlist);
+				list_add_tail(&fle->u.gc_list, &gc_list);
+			}
+		}
+	}
+
+	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
+}
+
+static void flow_cache_shrink(struct flow_cache *fc,
+			      struct flow_cache_percpu *fcp)
+{
+	int shrink_to = fc->low_watermark / flow_cache_hash_size(fc);
+
+	__flow_cache_shrink(fc, fcp, shrink_to);
+}
+
+static void flow_new_hash_rnd(struct flow_cache *fc,
+			      struct flow_cache_percpu *fcp)
+{
+	get_random_bytes(&fcp->hash_rnd, sizeof(u32));
+	fcp->hash_rnd_recalc = 0;
+	__flow_cache_shrink(fc, fcp, 0);
+}
+
+static u32 flow_hash_code(struct flow_cache *fc,
+			  struct flow_cache_percpu *fcp,
+			  const struct flowi *key,
+			  size_t keysize)
+{
+	const u32 *k = (const u32 *) key;
+	const u32 length = keysize * sizeof(flow_compare_t) / sizeof(u32);
+
+	return jhash2(k, length, fcp->hash_rnd)
+		& (flow_cache_hash_size(fc) - 1);
+}
+
+/* I hear what you're saying, use memcmp.  But memcmp cannot make
+ * important assumptions that we can here, such as alignment.
+ */
+static int flow_key_compare(const struct flowi *key1, const struct flowi *key2,
+			    size_t keysize)
+{
+	const flow_compare_t *k1, *k1_lim, *k2;
+
+	k1 = (const flow_compare_t *) key1;
+	k1_lim = k1 + keysize;
+
+	k2 = (const flow_compare_t *) key2;
+
+	do {
+		if (*k1++ != *k2++)
+			return 1;
+	} while (k1 < k1_lim);
+
+	return 0;
+}
+
+struct flow_cache_object *
+flow_cache_lookup(struct net *net, const struct flowi *key, u16 family, u8 dir,
+		  flow_resolve_t resolver, void *ctx)
+{
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
+	struct flow_cache_percpu *fcp;
+	struct flow_cache_entry *fle, *tfle;
+	struct flow_cache_object *flo;
+	size_t keysize;
+	unsigned int hash;
+
+	local_bh_disable();
+	fcp = this_cpu_ptr(fc->percpu);
+
+	fle = NULL;
+	flo = NULL;
+
+	keysize = flow_key_size(family);
+	if (!keysize)
+		goto nocache;
+
+	/* Packet really early in init?  Making flow_cache_init a
+	 * pre-smp initcall would solve this.  --RR */
+	if (!fcp->hash_table)
+		goto nocache;
+
+	if (fcp->hash_rnd_recalc)
+		flow_new_hash_rnd(fc, fcp);
+
+	hash = flow_hash_code(fc, fcp, key, keysize);
+	hlist_for_each_entry(tfle, &fcp->hash_table[hash], u.hlist) {
+		if (tfle->net == net &&
+		    tfle->family == family &&
+		    tfle->dir == dir &&
+		    flow_key_compare(key, &tfle->key, keysize) == 0) {
+			fle = tfle;
+			break;
+		}
+	}
+
+	if (unlikely(!fle)) {
+		if (fcp->hash_count > fc->high_watermark)
+			flow_cache_shrink(fc, fcp);
+
+		fle = kmem_cache_alloc(flow_cachep, GFP_ATOMIC);
+		if (fle) {
+			fle->net = net;
+			fle->family = family;
+			fle->dir = dir;
+			memcpy(&fle->key, key, keysize * sizeof(flow_compare_t));
+			fle->object = NULL;
+			hlist_add_head(&fle->u.hlist, &fcp->hash_table[hash]);
+			fcp->hash_count++;
+		}
+	} else if (likely(fle->genid == atomic_read(&net->xfrm.flow_cache_genid))) {
+		flo = fle->object;
+		if (!flo)
+			goto ret_object;
+		flo = flo->ops->get(flo);
+		if (flo)
+			goto ret_object;
+	} else if (fle->object) {
+	        flo = fle->object;
+	        flo->ops->delete(flo);
+	        fle->object = NULL;
+	}
+
+nocache:
+	flo = NULL;
+	if (fle) {
+		flo = fle->object;
+		fle->object = NULL;
+	}
+	flo = resolver(net, key, family, dir, flo, ctx);
+	if (fle) {
+		fle->genid = atomic_read(&net->xfrm.flow_cache_genid);
+		if (!IS_ERR(flo))
+			fle->object = flo;
+		else
+			fle->genid--;
+	} else {
+		if (!IS_ERR_OR_NULL(flo))
+			flo->ops->delete(flo);
+	}
+ret_object:
+	local_bh_enable();
+	return flo;
+}
+EXPORT_SYMBOL(flow_cache_lookup);
+
+static void flow_cache_flush_tasklet(unsigned long data)
+{
+	struct flow_flush_info *info = (void *)data;
+	struct flow_cache *fc = info->cache;
+	struct flow_cache_percpu *fcp;
+	struct flow_cache_entry *fle;
+	struct hlist_node *tmp;
+	LIST_HEAD(gc_list);
+	int i, deleted = 0;
+	struct netns_xfrm *xfrm = container_of(fc, struct netns_xfrm,
+						flow_cache_global);
+
+	fcp = this_cpu_ptr(fc->percpu);
+	for (i = 0; i < flow_cache_hash_size(fc); i++) {
+		hlist_for_each_entry_safe(fle, tmp,
+					  &fcp->hash_table[i], u.hlist) {
+			if (flow_entry_valid(fle, xfrm))
+				continue;
+
+			deleted++;
+			hlist_del(&fle->u.hlist);
+			list_add_tail(&fle->u.gc_list, &gc_list);
+		}
+	}
+
+	flow_cache_queue_garbage(fcp, deleted, &gc_list, xfrm);
+
+	if (atomic_dec_and_test(&info->cpuleft))
+		complete(&info->completion);
+}
+
+/*
+ * Return whether a cpu needs flushing.  Conservatively, we assume
+ * the presence of any entries means the core may require flushing,
+ * since the flow_cache_ops.check() function may assume it's running
+ * on the same core as the per-cpu cache component.
+ */
+static int flow_cache_percpu_empty(struct flow_cache *fc, int cpu)
+{
+	struct flow_cache_percpu *fcp;
+	int i;
+
+	fcp = per_cpu_ptr(fc->percpu, cpu);
+	for (i = 0; i < flow_cache_hash_size(fc); i++)
+		if (!hlist_empty(&fcp->hash_table[i]))
+			return 0;
+	return 1;
+}
+
+static void flow_cache_flush_per_cpu(void *data)
+{
+	struct flow_flush_info *info = data;
+	struct tasklet_struct *tasklet;
+
+	tasklet = &this_cpu_ptr(info->cache->percpu)->flush_tasklet;
+	tasklet->data = (unsigned long)info;
+	tasklet_schedule(tasklet);
+}
+
+void flow_cache_flush(struct net *net)
+{
+	struct flow_flush_info info;
+	cpumask_var_t mask;
+	int i, self;
+
+	/* Track which cpus need flushing to avoid disturbing all cores. */
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return;
+	cpumask_clear(mask);
+
+	/* Don't want cpus going down or up during this. */
+	get_online_cpus();
+	mutex_lock(&net->xfrm.flow_flush_sem);
+	info.cache = &net->xfrm.flow_cache_global;
+	for_each_online_cpu(i)
+		if (!flow_cache_percpu_empty(info.cache, i))
+			cpumask_set_cpu(i, mask);
+	atomic_set(&info.cpuleft, cpumask_weight(mask));
+	if (atomic_read(&info.cpuleft) == 0)
+		goto done;
+
+	init_completion(&info.completion);
+
+	local_bh_disable();
+	self = cpumask_test_and_clear_cpu(smp_processor_id(), mask);
+	on_each_cpu_mask(mask, flow_cache_flush_per_cpu, &info, 0);
+	if (self)
+		flow_cache_flush_tasklet((unsigned long)&info);
+	local_bh_enable();
+
+	wait_for_completion(&info.completion);
+
+done:
+	mutex_unlock(&net->xfrm.flow_flush_sem);
+	put_online_cpus();
+	free_cpumask_var(mask);
+}
+
+static void flow_cache_flush_task(struct work_struct *work)
+{
+	struct netns_xfrm *xfrm = container_of(work, struct netns_xfrm,
+						flow_cache_flush_work);
+	struct net *net = container_of(xfrm, struct net, xfrm);
+
+	flow_cache_flush(net);
+}
+
+void flow_cache_flush_deferred(struct net *net)
+{
+	schedule_work(&net->xfrm.flow_cache_flush_work);
+}
+
+static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu)
+{
+	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
+	size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc);
+
+	if (!fcp->hash_table) {
+		fcp->hash_table = kzalloc_node(sz, GFP_KERNEL, cpu_to_node(cpu));
+		if (!fcp->hash_table) {
+			pr_err("NET: failed to allocate flow cache sz %zu\n", sz);
+			return -ENOMEM;
+		}
+		fcp->hash_rnd_recalc = 1;
+		fcp->hash_count = 0;
+		tasklet_init(&fcp->flush_tasklet, flow_cache_flush_tasklet, 0);
+	}
+	return 0;
+}
+
+static int flow_cache_cpu(struct notifier_block *nfb,
+			  unsigned long action,
+			  void *hcpu)
+{
+	struct flow_cache *fc = container_of(nfb, struct flow_cache,
+						hotcpu_notifier);
+	int res, cpu = (unsigned long) hcpu;
+	struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu);
+
+	switch (action) {
+	case CPU_UP_PREPARE:
+	case CPU_UP_PREPARE_FROZEN:
+		res = flow_cache_cpu_prepare(fc, cpu);
+		if (res)
+			return notifier_from_errno(res);
+		break;
+	case CPU_DEAD:
+	case CPU_DEAD_FROZEN:
+		__flow_cache_shrink(fc, fcp, 0);
+		break;
+	}
+	return NOTIFY_OK;
+}
+
+int flow_cache_init(struct net *net)
+{
+	int i;
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
+
+	if (!flow_cachep)
+		flow_cachep = kmem_cache_create("flow_cache",
+						sizeof(struct flow_cache_entry),
+						0, SLAB_PANIC, NULL);
+	spin_lock_init(&net->xfrm.flow_cache_gc_lock);
+	INIT_LIST_HEAD(&net->xfrm.flow_cache_gc_list);
+	INIT_WORK(&net->xfrm.flow_cache_gc_work, flow_cache_gc_task);
+	INIT_WORK(&net->xfrm.flow_cache_flush_work, flow_cache_flush_task);
+	mutex_init(&net->xfrm.flow_flush_sem);
+
+	fc->hash_shift = 10;
+	fc->low_watermark = 2 * flow_cache_hash_size(fc);
+	fc->high_watermark = 4 * flow_cache_hash_size(fc);
+
+	fc->percpu = alloc_percpu(struct flow_cache_percpu);
+	if (!fc->percpu)
+		return -ENOMEM;
+
+	cpu_notifier_register_begin();
+
+	for_each_online_cpu(i) {
+		if (flow_cache_cpu_prepare(fc, i))
+			goto err;
+	}
+	fc->hotcpu_notifier = (struct notifier_block){
+		.notifier_call = flow_cache_cpu,
+	};
+	__register_hotcpu_notifier(&fc->hotcpu_notifier);
+
+	cpu_notifier_register_done();
+
+	setup_timer(&fc->rnd_timer, flow_cache_new_hashrnd,
+		    (unsigned long) fc);
+	fc->rnd_timer.expires = jiffies + FLOW_HASH_RND_PERIOD;
+	add_timer(&fc->rnd_timer);
+
+	return 0;
+
+err:
+	for_each_possible_cpu(i) {
+		struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
+		kfree(fcp->hash_table);
+		fcp->hash_table = NULL;
+	}
+
+	cpu_notifier_register_done();
+
+	free_percpu(fc->percpu);
+	fc->percpu = NULL;
+
+	return -ENOMEM;
+}
+EXPORT_SYMBOL(flow_cache_init);
+
+void flow_cache_fini(struct net *net)
+{
+	int i;
+	struct flow_cache *fc = &net->xfrm.flow_cache_global;
+
+	del_timer_sync(&fc->rnd_timer);
+	unregister_hotcpu_notifier(&fc->hotcpu_notifier);
+
+	for_each_possible_cpu(i) {
+		struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, i);
+		kfree(fcp->hash_table);
+		fcp->hash_table = NULL;
+	}
+
+	free_percpu(fc->percpu);
+	fc->percpu = NULL;
+}
+EXPORT_SYMBOL(flow_cache_fini);

net/core/flow_dissector.c

@@ -0,0 +1,471 @@
+#include <linux/skbuff.h>
+#include <linux/export.h>
+#include <linux/ip.h>
+#include <linux/ipv6.h>
+#include <linux/if_vlan.h>
+#include <net/ip.h>
+#include <net/ipv6.h>
+#include <linux/igmp.h>
+#include <linux/icmp.h>
+#include <linux/sctp.h>
+#include <linux/dccp.h>
+#include <linux/if_tunnel.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_defs.h>
+#include <net/flow_keys.h>
+#include <scsi/fc/fc_fcoe.h>
+
+/* copy saddr & daddr, possibly using 64bit load/store
+ * Equivalent to :	flow->src = iph->saddr;
+ *			flow->dst = iph->daddr;
+ */
+static void iph_to_flow_copy_addrs(struct flow_keys *flow, const struct iphdr *iph)
+{
+	BUILD_BUG_ON(offsetof(typeof(*flow), dst) !=
+		     offsetof(typeof(*flow), src) + sizeof(flow->src));
+	memcpy(&flow->src, &iph->saddr, sizeof(flow->src) + sizeof(flow->dst));
+}
+
+/**
+ * __skb_flow_get_ports - extract the upper layer ports and return them
+ * @skb: sk_buff to extract the ports from
+ * @thoff: transport header offset
+ * @ip_proto: protocol for which to get port offset
+ * @data: raw buffer pointer to the packet, if NULL use skb->data
+ * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
+ *
+ * The function will try to retrieve the ports at offset thoff + poff where poff
+ * is the protocol port offset returned from proto_ports_offset
+ */
+__be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto,
+			    void *data, int hlen)
+{
+	int poff = proto_ports_offset(ip_proto);
+
+	if (!data) {
+		data = skb->data;
+		hlen = skb_headlen(skb);
+	}
+
+	if (poff >= 0) {
+		__be32 *ports, _ports;
+
+		ports = __skb_header_pointer(skb, thoff + poff,
+					     sizeof(_ports), data, hlen, &_ports);
+		if (ports)
+			return *ports;
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(__skb_flow_get_ports);
+
+/**
+ * __skb_flow_dissect - extract the flow_keys struct and return it
+ * @skb: sk_buff to extract the flow from, can be NULL if the rest are specified
+ * @data: raw buffer pointer to the packet, if NULL use skb->data
+ * @proto: protocol for which to get the flow, if @data is NULL use skb->protocol
+ * @nhoff: network header offset, if @data is NULL use skb_network_offset(skb)
+ * @hlen: packet header length, if @data is NULL use skb_headlen(skb)
+ *
+ * The function will try to retrieve the struct flow_keys from either the skbuff
+ * or a raw buffer specified by the rest parameters
+ */
+bool __skb_flow_dissect(const struct sk_buff *skb, struct flow_keys *flow,
+			void *data, __be16 proto, int nhoff, int hlen)
+{
+	u8 ip_proto;
+
+	if (!data) {
+		data = skb->data;
+		proto = skb->protocol;
+		nhoff = skb_network_offset(skb);
+		hlen = skb_headlen(skb);
+	}
+
+	memset(flow, 0, sizeof(*flow));
+
+again:
+	switch (proto) {
+	case htons(ETH_P_IP): {
+		const struct iphdr *iph;
+		struct iphdr _iph;
+ip:
+		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
+		if (!iph || iph->ihl < 5)
+			return false;
+		nhoff += iph->ihl * 4;
+
+		ip_proto = iph->protocol;
+		if (ip_is_fragment(iph))
+			ip_proto = 0;
+
+		/* skip the address processing if skb is NULL.  The assumption
+		 * here is that if there is no skb we are not looking for flow
+		 * info but lengths and protocols.
+		 */
+		if (!skb)
+			break;
+
+		iph_to_flow_copy_addrs(flow, iph);
+		break;
+	}
+	case htons(ETH_P_IPV6): {
+		const struct ipv6hdr *iph;
+		struct ipv6hdr _iph;
+		__be32 flow_label;
+
+ipv6:
+		iph = __skb_header_pointer(skb, nhoff, sizeof(_iph), data, hlen, &_iph);
+		if (!iph)
+			return false;
+
+		ip_proto = iph->nexthdr;
+		nhoff += sizeof(struct ipv6hdr);
+
+		/* see comment above in IPv4 section */
+		if (!skb)
+			break;
+
+		flow->src = (__force __be32)ipv6_addr_hash(&iph->saddr);
+		flow->dst = (__force __be32)ipv6_addr_hash(&iph->daddr);
+
+		flow_label = ip6_flowlabel(iph);
+		if (flow_label) {
+			/* Awesome, IPv6 packet has a flow label so we can
+			 * use that to represent the ports without any
+			 * further dissection.
+			 */
+			flow->n_proto = proto;
+			flow->ip_proto = ip_proto;
+			flow->ports = flow_label;
+			flow->thoff = (u16)nhoff;
+
+			return true;
+		}
+
+		break;
+	}
+	case htons(ETH_P_8021AD):
+	case htons(ETH_P_8021Q): {
+		const struct vlan_hdr *vlan;
+		struct vlan_hdr _vlan;
+
+		vlan = __skb_header_pointer(skb, nhoff, sizeof(_vlan), data, hlen, &_vlan);
+		if (!vlan)
+			return false;
+
+		proto = vlan->h_vlan_encapsulated_proto;
+		nhoff += sizeof(*vlan);
+		goto again;
+	}
+	case htons(ETH_P_PPP_SES): {
+		struct {
+			struct pppoe_hdr hdr;
+			__be16 proto;
+		} *hdr, _hdr;
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
+		if (!hdr)
+			return false;
+		proto = hdr->proto;
+		nhoff += PPPOE_SES_HLEN;
+		switch (proto) {
+		case htons(PPP_IP):
+			goto ip;
+		case htons(PPP_IPV6):
+			goto ipv6;
+		default:
+			return false;
+		}
+	}
+	case htons(ETH_P_FCOE):
+		flow->thoff = (u16)(nhoff + FCOE_HEADER_LEN);
+		/* fall through */
+	default:
+		return false;
+	}
+
+	switch (ip_proto) {
+	case IPPROTO_GRE: {
+		struct gre_hdr {
+			__be16 flags;
+			__be16 proto;
+		} *hdr, _hdr;
+
+		hdr = __skb_header_pointer(skb, nhoff, sizeof(_hdr), data, hlen, &_hdr);
+		if (!hdr)
+			return false;
+		/*
+		 * Only look inside GRE if version zero and no
+		 * routing
+		 */
+		if (!(hdr->flags & (GRE_VERSION|GRE_ROUTING))) {
+			proto = hdr->proto;
+			nhoff += 4;
+			if (hdr->flags & GRE_CSUM)
+				nhoff += 4;
+			if (hdr->flags & GRE_KEY)
+				nhoff += 4;
+			if (hdr->flags & GRE_SEQ)
+				nhoff += 4;
+			if (proto == htons(ETH_P_TEB)) {
+				const struct ethhdr *eth;
+				struct ethhdr _eth;
+
+				eth = __skb_header_pointer(skb, nhoff,
+							   sizeof(_eth),
+							   data, hlen, &_eth);
+				if (!eth)
+					return false;
+				proto = eth->h_proto;
+				nhoff += sizeof(*eth);
+			}
+			goto again;
+		}
+		break;
+	}
+	case IPPROTO_IPIP:
+		proto = htons(ETH_P_IP);
+		goto ip;
+	case IPPROTO_IPV6:
+		proto = htons(ETH_P_IPV6);
+		goto ipv6;
+	default:
+		break;
+	}
+
+	flow->n_proto = proto;
+	flow->ip_proto = ip_proto;
+	flow->thoff = (u16) nhoff;
+
+	/* unless skb is set we don't need to record port info */
+	if (skb)
+		flow->ports = __skb_flow_get_ports(skb, nhoff, ip_proto,
+						   data, hlen);
+
+	return true;
+}
+EXPORT_SYMBOL(__skb_flow_dissect);
+
+static u32 hashrnd __read_mostly;
+static __always_inline void __flow_hash_secret_init(void)
+{
+	net_get_random_once(&hashrnd, sizeof(hashrnd));
+}
+
+static __always_inline u32 __flow_hash_3words(u32 a, u32 b, u32 c)
+{
+	__flow_hash_secret_init();
+	return jhash_3words(a, b, c, hashrnd);
+}
+
+static inline u32 __flow_hash_from_keys(struct flow_keys *keys)
+{
+	u32 hash;
+
+	/* get a consistent hash (same value on both flow directions) */
+	if (((__force u32)keys->dst < (__force u32)keys->src) ||
+	    (((__force u32)keys->dst == (__force u32)keys->src) &&
+	     ((__force u16)keys->port16[1] < (__force u16)keys->port16[0]))) {
+		swap(keys->dst, keys->src);
+		swap(keys->port16[0], keys->port16[1]);
+	}
+
+	hash = __flow_hash_3words((__force u32)keys->dst,
+				  (__force u32)keys->src,
+				  (__force u32)keys->ports);
+	if (!hash)
+		hash = 1;
+
+	return hash;
+}
+
+u32 flow_hash_from_keys(struct flow_keys *keys)
+{
+	return __flow_hash_from_keys(keys);
+}
+EXPORT_SYMBOL(flow_hash_from_keys);
+
+/*
+ * __skb_get_hash: calculate a flow hash based on src/dst addresses
+ * and src/dst port numbers.  Sets hash in skb to non-zero hash value
+ * on success, zero indicates no valid hash.  Also, sets l4_hash in skb
+ * if hash is a canonical 4-tuple hash over transport ports.
+ */
+void __skb_get_hash(struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	if (!skb_flow_dissect(skb, &keys))
+		return;
+
+	if (keys.ports)
+		skb->l4_hash = 1;
+
+	skb->sw_hash = 1;
+
+	skb->hash = __flow_hash_from_keys(&keys);
+}
+EXPORT_SYMBOL(__skb_get_hash);
+
+/*
+ * Returns a Tx hash based on the given packet descriptor a Tx queues' number
+ * to be used as a distribution range.
+ */
+u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb,
+		  unsigned int num_tx_queues)
+{
+	u32 hash;
+	u16 qoffset = 0;
+	u16 qcount = num_tx_queues;
+
+	if (skb_rx_queue_recorded(skb)) {
+		hash = skb_get_rx_queue(skb);
+		while (unlikely(hash >= num_tx_queues))
+			hash -= num_tx_queues;
+		return hash;
+	}
+
+	if (dev->num_tc) {
+		u8 tc = netdev_get_prio_tc_map(dev, skb->priority);
+		qoffset = dev->tc_to_txq[tc].offset;
+		qcount = dev->tc_to_txq[tc].count;
+	}
+
+	return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset;
+}
+EXPORT_SYMBOL(__skb_tx_hash);
+
+u32 __skb_get_poff(const struct sk_buff *skb, void *data,
+		   const struct flow_keys *keys, int hlen)
+{
+	u32 poff = keys->thoff;
+
+	switch (keys->ip_proto) {
+	case IPPROTO_TCP: {
+		/* access doff as u8 to avoid unaligned access */
+		const u8 *doff;
+		u8 _doff;
+
+		doff = __skb_header_pointer(skb, poff + 12, sizeof(_doff),
+					    data, hlen, &_doff);
+		if (!doff)
+			return poff;
+
+		poff += max_t(u32, sizeof(struct tcphdr), (*doff & 0xF0) >> 2);
+		break;
+	}
+	case IPPROTO_UDP:
+	case IPPROTO_UDPLITE:
+		poff += sizeof(struct udphdr);
+		break;
+	/* For the rest, we do not really care about header
+	 * extensions at this point for now.
+	 */
+	case IPPROTO_ICMP:
+		poff += sizeof(struct icmphdr);
+		break;
+	case IPPROTO_ICMPV6:
+		poff += sizeof(struct icmp6hdr);
+		break;
+	case IPPROTO_IGMP:
+		poff += sizeof(struct igmphdr);
+		break;
+	case IPPROTO_DCCP:
+		poff += sizeof(struct dccp_hdr);
+		break;
+	case IPPROTO_SCTP:
+		poff += sizeof(struct sctphdr);
+		break;
+	}
+
+	return poff;
+}
+
+/* skb_get_poff() returns the offset to the payload as far as it could
+ * be dissected. The main user is currently BPF, so that we can dynamically
+ * truncate packets without needing to push actual payload to the user
+ * space and can analyze headers only, instead.
+ */
+u32 skb_get_poff(const struct sk_buff *skb)
+{
+	struct flow_keys keys;
+
+	if (!skb_flow_dissect(skb, &keys))
+		return 0;
+
+	return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb));
+}
+
+static inline int get_xps_queue(struct net_device *dev, struct sk_buff *skb)
+{
+#ifdef CONFIG_XPS
+	struct xps_dev_maps *dev_maps;
+	struct xps_map *map;
+	int queue_index = -1;
+
+	rcu_read_lock();
+	dev_maps = rcu_dereference(dev->xps_maps);
+	if (dev_maps) {
+		map = rcu_dereference(
+		    dev_maps->cpu_map[raw_smp_processor_id()]);
+		if (map) {
+			if (map->len == 1)
+				queue_index = map->queues[0];
+			else
+				queue_index = map->queues[reciprocal_scale(skb_get_hash(skb),
+									   map->len)];
+			if (unlikely(queue_index >= dev->real_num_tx_queues))
+				queue_index = -1;
+		}
+	}
+	rcu_read_unlock();
+
+	return queue_index;
+#else
+	return -1;
+#endif
+}
+
+static u16 __netdev_pick_tx(struct net_device *dev, struct sk_buff *skb)
+{
+	struct sock *sk = skb->sk;
+	int queue_index = sk_tx_queue_get(sk);
+
+	if (queue_index < 0 || skb->ooo_okay ||
+	    queue_index >= dev->real_num_tx_queues) {
+		int new_index = get_xps_queue(dev, skb);
+		if (new_index < 0)
+			new_index = skb_tx_hash(dev, skb);
+
+		if (queue_index != new_index && sk &&
+		    rcu_access_pointer(sk->sk_dst_cache))
+			sk_tx_queue_set(sk, new_index);
+
+		queue_index = new_index;
+	}
+
+	return queue_index;
+}
+
+struct netdev_queue *netdev_pick_tx(struct net_device *dev,
+				    struct sk_buff *skb,
+				    void *accel_priv)
+{
+	int queue_index = 0;
+
+	if (dev->real_num_tx_queues != 1) {
+		const struct net_device_ops *ops = dev->netdev_ops;
+		if (ops->ndo_select_queue)
+			queue_index = ops->ndo_select_queue(dev, skb, accel_priv,
+							    __netdev_pick_tx);
+		else
+			queue_index = __netdev_pick_tx(dev, skb);
+
+		if (!accel_priv)
+			queue_index = netdev_cap_txqueue(dev, queue_index);
+	}
+
+	skb_set_queue_mapping(skb, queue_index);
+	return netdev_get_tx_queue(dev, queue_index);
+}

net/core/gen_estimator.c

@@ -0,0 +1,328 @@
+/*
+ * net/sched/gen_estimator.c	Simple rate estimator.
+ *
+ *		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; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ * Changes:
+ *              Jamal Hadi Salim - moved it to net/core and reshulfed
+ *              names to make it usable in general net subsystem.
+ */
+
+#include <asm/uaccess.h>
+#include <linux/bitops.h>
+#include <linux/module.h>
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/jiffies.h>
+#include <linux/string.h>
+#include <linux/mm.h>
+#include <linux/socket.h>
+#include <linux/sockios.h>
+#include <linux/in.h>
+#include <linux/errno.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/skbuff.h>
+#include <linux/rtnetlink.h>
+#include <linux/init.h>
+#include <linux/rbtree.h>
+#include <linux/slab.h>
+#include <net/sock.h>
+#include <net/gen_stats.h>
+
+/*
+   This code is NOT intended to be used for statistics collection,
+   its purpose is to provide a base for statistical multiplexing
+   for controlled load service.
+   If you need only statistics, run a user level daemon which
+   periodically reads byte counters.
+
+   Unfortunately, rate estimation is not a very easy task.
+   F.e. I did not find a simple way to estimate the current peak rate
+   and even failed to formulate the problem 8)8)
+
+   So I preferred not to built an estimator into the scheduler,
+   but run this task separately.
+   Ideally, it should be kernel thread(s), but for now it runs
+   from timers, which puts apparent top bounds on the number of rated
+   flows, has minimal overhead on small, but is enough
+   to handle controlled load service, sets of aggregates.
+
+   We measure rate over A=(1<<interval) seconds and evaluate EWMA:
+
+   avrate = avrate*(1-W) + rate*W
+
+   where W is chosen as negative power of 2: W = 2^(-ewma_log)
+
+   The resulting time constant is:
+
+   T = A/(-ln(1-W))
+
+
+   NOTES.
+
+   * avbps is scaled by 2^5, avpps is scaled by 2^10.
+   * both values are reported as 32 bit unsigned values. bps can
+     overflow for fast links : max speed being 34360Mbit/sec
+   * Minimal interval is HZ/4=250msec (it is the greatest common divisor
+     for HZ=100 and HZ=1024 8)), maximal interval
+     is (HZ*2^EST_MAX_INTERVAL)/4 = 8sec. Shorter intervals
+     are too expensive, longer ones can be implemented
+     at user level painlessly.
+ */
+
+#define EST_MAX_INTERVAL	5
+
+struct gen_estimator
+{
+	struct list_head	list;
+	struct gnet_stats_basic_packed	*bstats;
+	struct gnet_stats_rate_est64	*rate_est;
+	spinlock_t		*stats_lock;
+	int			ewma_log;
+	u64			last_bytes;
+	u64			avbps;
+	u32			last_packets;
+	u32			avpps;
+	struct rcu_head		e_rcu;
+	struct rb_node		node;
+	struct gnet_stats_basic_cpu __percpu *cpu_bstats;
+	struct rcu_head		head;
+};
+
+struct gen_estimator_head
+{
+	struct timer_list	timer;
+	struct list_head	list;
+};
+
+static struct gen_estimator_head elist[EST_MAX_INTERVAL+1];
+
+/* Protects against NULL dereference */
+static DEFINE_RWLOCK(est_lock);
+
+/* Protects against soft lockup during large deletion */
+static struct rb_root est_root = RB_ROOT;
+static DEFINE_SPINLOCK(est_tree_lock);
+
+static void est_timer(unsigned long arg)
+{
+	int idx = (int)arg;
+	struct gen_estimator *e;
+
+	rcu_read_lock();
+	list_for_each_entry_rcu(e, &elist[idx].list, list) {
+		struct gnet_stats_basic_packed b = {0};
+		u64 brate;
+		u32 rate;
+
+		spin_lock(e->stats_lock);
+		read_lock(&est_lock);
+		if (e->bstats == NULL)
+			goto skip;
+
+		__gnet_stats_copy_basic(&b, e->cpu_bstats, e->bstats);
+
+		brate = (b.bytes - e->last_bytes)<<(7 - idx);
+		e->last_bytes = b.bytes;
+		e->avbps += (brate >> e->ewma_log) - (e->avbps >> e->ewma_log);
+		e->rate_est->bps = (e->avbps+0xF)>>5;
+
+		rate = (b.packets - e->last_packets)<<(12 - idx);
+		e->last_packets = b.packets;
+		e->avpps += (rate >> e->ewma_log) - (e->avpps >> e->ewma_log);
+		e->rate_est->pps = (e->avpps+0x1FF)>>10;
+skip:
+		read_unlock(&est_lock);
+		spin_unlock(e->stats_lock);
+	}
+
+	if (!list_empty(&elist[idx].list))
+		mod_timer(&elist[idx].timer, jiffies + ((HZ/4) << idx));
+	rcu_read_unlock();
+}
+
+static void gen_add_node(struct gen_estimator *est)
+{
+	struct rb_node **p = &est_root.rb_node, *parent = NULL;
+
+	while (*p) {
+		struct gen_estimator *e;
+
+		parent = *p;
+		e = rb_entry(parent, struct gen_estimator, node);
+
+		if (est->bstats > e->bstats)
+			p = &parent->rb_right;
+		else
+			p = &parent->rb_left;
+	}
+	rb_link_node(&est->node, parent, p);
+	rb_insert_color(&est->node, &est_root);
+}
+
+static
+struct gen_estimator *gen_find_node(const struct gnet_stats_basic_packed *bstats,
+				    const struct gnet_stats_rate_est64 *rate_est)
+{
+	struct rb_node *p = est_root.rb_node;
+
+	while (p) {
+		struct gen_estimator *e;
+
+		e = rb_entry(p, struct gen_estimator, node);
+
+		if (bstats > e->bstats)
+			p = p->rb_right;
+		else if (bstats < e->bstats || rate_est != e->rate_est)
+			p = p->rb_left;
+		else
+			return e;
+	}
+	return NULL;
+}
+
+/**
+ * gen_new_estimator - create a new rate estimator
+ * @bstats: basic statistics
+ * @rate_est: rate estimator statistics
+ * @stats_lock: statistics lock
+ * @opt: rate estimator configuration TLV
+ *
+ * Creates a new rate estimator with &bstats as source and &rate_est
+ * as destination. A new timer with the interval specified in the
+ * configuration TLV is created. Upon each interval, the latest statistics
+ * will be read from &bstats and the estimated rate will be stored in
+ * &rate_est with the statistics lock grabbed during this period.
+ *
+ * Returns 0 on success or a negative error code.
+ *
+ */
+int gen_new_estimator(struct gnet_stats_basic_packed *bstats,
+		      struct gnet_stats_basic_cpu __percpu *cpu_bstats,
+		      struct gnet_stats_rate_est64 *rate_est,
+		      spinlock_t *stats_lock,
+		      struct nlattr *opt)
+{
+	struct gen_estimator *est;
+	struct gnet_estimator *parm = nla_data(opt);
+	struct gnet_stats_basic_packed b = {0};
+	int idx;
+
+	if (nla_len(opt) < sizeof(*parm))
+		return -EINVAL;
+
+	if (parm->interval < -2 || parm->interval > 3)
+		return -EINVAL;
+
+	est = kzalloc(sizeof(*est), GFP_KERNEL);
+	if (est == NULL)
+		return -ENOBUFS;
+
+	__gnet_stats_copy_basic(&b, cpu_bstats, bstats);
+
+	idx = parm->interval + 2;
+	est->bstats = bstats;
+	est->rate_est = rate_est;
+	est->stats_lock = stats_lock;
+	est->ewma_log = parm->ewma_log;
+	est->last_bytes = b.bytes;
+	est->avbps = rate_est->bps<<5;
+	est->last_packets = b.packets;
+	est->avpps = rate_est->pps<<10;
+	est->cpu_bstats = cpu_bstats;
+
+	spin_lock_bh(&est_tree_lock);
+	if (!elist[idx].timer.function) {
+		INIT_LIST_HEAD(&elist[idx].list);
+		setup_timer(&elist[idx].timer, est_timer, idx);
+	}
+
+	if (list_empty(&elist[idx].list))
+		mod_timer(&elist[idx].timer, jiffies + ((HZ/4) << idx));
+
+	list_add_rcu(&est->list, &elist[idx].list);
+	gen_add_node(est);
+	spin_unlock_bh(&est_tree_lock);
+
+	return 0;
+}
+EXPORT_SYMBOL(gen_new_estimator);
+
+/**
+ * gen_kill_estimator - remove a rate estimator
+ * @bstats: basic statistics
+ * @rate_est: rate estimator statistics
+ *
+ * Removes the rate estimator specified by &bstats and &rate_est.
+ *
+ * Note : Caller should respect an RCU grace period before freeing stats_lock
+ */
+void gen_kill_estimator(struct gnet_stats_basic_packed *bstats,
+			struct gnet_stats_rate_est64 *rate_est)
+{
+	struct gen_estimator *e;
+
+	spin_lock_bh(&est_tree_lock);
+	while ((e = gen_find_node(bstats, rate_est))) {
+		rb_erase(&e->node, &est_root);
+
+		write_lock(&est_lock);
+		e->bstats = NULL;
+		write_unlock(&est_lock);
+
+		list_del_rcu(&e->list);
+		kfree_rcu(e, e_rcu);
+	}
+	spin_unlock_bh(&est_tree_lock);
+}
+EXPORT_SYMBOL(gen_kill_estimator);
+
+/**
+ * gen_replace_estimator - replace rate estimator configuration
+ * @bstats: basic statistics
+ * @rate_est: rate estimator statistics
+ * @stats_lock: statistics lock
+ * @opt: rate estimator configuration TLV
+ *
+ * Replaces the configuration of a rate estimator by calling
+ * gen_kill_estimator() and gen_new_estimator().
+ *
+ * Returns 0 on success or a negative error code.
+ */
+int gen_replace_estimator(struct gnet_stats_basic_packed *bstats,
+			  struct gnet_stats_basic_cpu __percpu *cpu_bstats,
+			  struct gnet_stats_rate_est64 *rate_est,
+			  spinlock_t *stats_lock, struct nlattr *opt)
+{
+	gen_kill_estimator(bstats, rate_est);
+	return gen_new_estimator(bstats, cpu_bstats, rate_est, stats_lock, opt);
+}
+EXPORT_SYMBOL(gen_replace_estimator);
+
+/**
+ * gen_estimator_active - test if estimator is currently in use
+ * @bstats: basic statistics
+ * @rate_est: rate estimator statistics
+ *
+ * Returns true if estimator is active, and false if not.
+ */
+bool gen_estimator_active(const struct gnet_stats_basic_packed *bstats,
+			  const struct gnet_stats_rate_est64 *rate_est)
+{
+	bool res;
+
+	ASSERT_RTNL();
+
+	spin_lock_bh(&est_tree_lock);
+	res = gen_find_node(bstats, rate_est) != NULL;
+	spin_unlock_bh(&est_tree_lock);
+
+	return res;
+}
+EXPORT_SYMBOL(gen_estimator_active);

net/core/gen_stats.c

@@ -0,0 +1,364 @@
+/*
+ * net/core/gen_stats.c
+ *
+ *             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; either version
+ *             2 of the License, or (at your option) any later version.
+ *
+ * Authors:  Thomas Graf <tgraf@suug.ch>
+ *           Jamal Hadi Salim
+ *           Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *
+ * See Documentation/networking/gen_stats.txt
+ */
+
+#include <linux/types.h>
+#include <linux/kernel.h>
+#include <linux/module.h>
+#include <linux/interrupt.h>
+#include <linux/socket.h>
+#include <linux/rtnetlink.h>
+#include <linux/gen_stats.h>
+#include <net/netlink.h>
+#include <net/gen_stats.h>
+
+
+static inline int
+gnet_stats_copy(struct gnet_dump *d, int type, void *buf, int size)
+{
+	if (nla_put(d->skb, type, size, buf))
+		goto nla_put_failure;
+	return 0;
+
+nla_put_failure:
+	kfree(d->xstats);
+	d->xstats = NULL;
+	d->xstats_len = 0;
+	spin_unlock_bh(d->lock);
+	return -1;
+}
+
+/**
+ * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode
+ * @skb: socket buffer to put statistics TLVs into
+ * @type: TLV type for top level statistic TLV
+ * @tc_stats_type: TLV type for backward compatibility struct tc_stats TLV
+ * @xstats_type: TLV type for backward compatibility xstats TLV
+ * @lock: statistics lock
+ * @d: dumping handle
+ *
+ * Initializes the dumping handle, grabs the statistic lock and appends
+ * an empty TLV header to the socket buffer for use a container for all
+ * other statistic TLVS.
+ *
+ * The dumping handle is marked to be in backward compatibility mode telling
+ * all gnet_stats_copy_XXX() functions to fill a local copy of struct tc_stats.
+ *
+ * Returns 0 on success or -1 if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_start_copy_compat(struct sk_buff *skb, int type, int tc_stats_type,
+	int xstats_type, spinlock_t *lock, struct gnet_dump *d)
+	__acquires(lock)
+{
+	memset(d, 0, sizeof(*d));
+
+	spin_lock_bh(lock);
+	d->lock = lock;
+	if (type)
+		d->tail = (struct nlattr *)skb_tail_pointer(skb);
+	d->skb = skb;
+	d->compat_tc_stats = tc_stats_type;
+	d->compat_xstats = xstats_type;
+
+	if (d->tail)
+		return gnet_stats_copy(d, type, NULL, 0);
+
+	return 0;
+}
+EXPORT_SYMBOL(gnet_stats_start_copy_compat);
+
+/**
+ * gnet_stats_start_copy_compat - start dumping procedure in compatibility mode
+ * @skb: socket buffer to put statistics TLVs into
+ * @type: TLV type for top level statistic TLV
+ * @lock: statistics lock
+ * @d: dumping handle
+ *
+ * Initializes the dumping handle, grabs the statistic lock and appends
+ * an empty TLV header to the socket buffer for use a container for all
+ * other statistic TLVS.
+ *
+ * Returns 0 on success or -1 if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_start_copy(struct sk_buff *skb, int type, spinlock_t *lock,
+	struct gnet_dump *d)
+{
+	return gnet_stats_start_copy_compat(skb, type, 0, 0, lock, d);
+}
+EXPORT_SYMBOL(gnet_stats_start_copy);
+
+static void
+__gnet_stats_copy_basic_cpu(struct gnet_stats_basic_packed *bstats,
+			    struct gnet_stats_basic_cpu __percpu *cpu)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		struct gnet_stats_basic_cpu *bcpu = per_cpu_ptr(cpu, i);
+		unsigned int start;
+		u64 bytes;
+		u32 packets;
+
+		do {
+			start = u64_stats_fetch_begin_irq(&bcpu->syncp);
+			bytes = bcpu->bstats.bytes;
+			packets = bcpu->bstats.packets;
+		} while (u64_stats_fetch_retry_irq(&bcpu->syncp, start));
+
+		bstats->bytes += bytes;
+		bstats->packets += packets;
+	}
+}
+
+void
+__gnet_stats_copy_basic(struct gnet_stats_basic_packed *bstats,
+			struct gnet_stats_basic_cpu __percpu *cpu,
+			struct gnet_stats_basic_packed *b)
+{
+	if (cpu) {
+		__gnet_stats_copy_basic_cpu(bstats, cpu);
+	} else {
+		bstats->bytes = b->bytes;
+		bstats->packets = b->packets;
+	}
+}
+EXPORT_SYMBOL(__gnet_stats_copy_basic);
+
+/**
+ * gnet_stats_copy_basic - copy basic statistics into statistic TLV
+ * @d: dumping handle
+ * @b: basic statistics
+ *
+ * Appends the basic statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_basic(struct gnet_dump *d,
+		      struct gnet_stats_basic_cpu __percpu *cpu,
+		      struct gnet_stats_basic_packed *b)
+{
+	struct gnet_stats_basic_packed bstats = {0};
+
+	__gnet_stats_copy_basic(&bstats, cpu, b);
+
+	if (d->compat_tc_stats) {
+		d->tc_stats.bytes = bstats.bytes;
+		d->tc_stats.packets = bstats.packets;
+	}
+
+	if (d->tail) {
+		struct gnet_stats_basic sb;
+
+		memset(&sb, 0, sizeof(sb));
+		sb.bytes = bstats.bytes;
+		sb.packets = bstats.packets;
+		return gnet_stats_copy(d, TCA_STATS_BASIC, &sb, sizeof(sb));
+	}
+	return 0;
+}
+EXPORT_SYMBOL(gnet_stats_copy_basic);
+
+/**
+ * gnet_stats_copy_rate_est - copy rate estimator statistics into statistics TLV
+ * @d: dumping handle
+ * @b: basic statistics
+ * @r: rate estimator statistics
+ *
+ * Appends the rate estimator statistics to the top level TLV created by
+ * gnet_stats_start_copy().
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_rate_est(struct gnet_dump *d,
+			 const struct gnet_stats_basic_packed *b,
+			 struct gnet_stats_rate_est64 *r)
+{
+	struct gnet_stats_rate_est est;
+	int res;
+
+	if (b && !gen_estimator_active(b, r))
+		return 0;
+
+	est.bps = min_t(u64, UINT_MAX, r->bps);
+	/* we have some time before reaching 2^32 packets per second */
+	est.pps = r->pps;
+
+	if (d->compat_tc_stats) {
+		d->tc_stats.bps = est.bps;
+		d->tc_stats.pps = est.pps;
+	}
+
+	if (d->tail) {
+		res = gnet_stats_copy(d, TCA_STATS_RATE_EST, &est, sizeof(est));
+		if (res < 0 || est.bps == r->bps)
+			return res;
+		/* emit 64bit stats only if needed */
+		return gnet_stats_copy(d, TCA_STATS_RATE_EST64, r, sizeof(*r));
+	}
+
+	return 0;
+}
+EXPORT_SYMBOL(gnet_stats_copy_rate_est);
+
+static void
+__gnet_stats_copy_queue_cpu(struct gnet_stats_queue *qstats,
+			    const struct gnet_stats_queue __percpu *q)
+{
+	int i;
+
+	for_each_possible_cpu(i) {
+		const struct gnet_stats_queue *qcpu = per_cpu_ptr(q, i);
+
+		qstats->qlen = 0;
+		qstats->backlog += qcpu->backlog;
+		qstats->drops += qcpu->drops;
+		qstats->requeues += qcpu->requeues;
+		qstats->overlimits += qcpu->overlimits;
+	}
+}
+
+static void __gnet_stats_copy_queue(struct gnet_stats_queue *qstats,
+				    const struct gnet_stats_queue __percpu *cpu,
+				    const struct gnet_stats_queue *q,
+				    __u32 qlen)
+{
+	if (cpu) {
+		__gnet_stats_copy_queue_cpu(qstats, cpu);
+	} else {
+		qstats->qlen = q->qlen;
+		qstats->backlog = q->backlog;
+		qstats->drops = q->drops;
+		qstats->requeues = q->requeues;
+		qstats->overlimits = q->overlimits;
+	}
+
+	qstats->qlen = qlen;
+}
+
+/**
+ * gnet_stats_copy_queue - copy queue statistics into statistics TLV
+ * @d: dumping handle
+ * @cpu_q: per cpu queue statistics
+ * @q: queue statistics
+ * @qlen: queue length statistics
+ *
+ * Appends the queue statistics to the top level TLV created by
+ * gnet_stats_start_copy(). Using per cpu queue statistics if
+ * they are available.
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_queue(struct gnet_dump *d,
+		      struct gnet_stats_queue __percpu *cpu_q,
+		      struct gnet_stats_queue *q, __u32 qlen)
+{
+	struct gnet_stats_queue qstats = {0};
+
+	__gnet_stats_copy_queue(&qstats, cpu_q, q, qlen);
+
+	if (d->compat_tc_stats) {
+		d->tc_stats.drops = qstats.drops;
+		d->tc_stats.qlen = qstats.qlen;
+		d->tc_stats.backlog = qstats.backlog;
+		d->tc_stats.overlimits = qstats.overlimits;
+	}
+
+	if (d->tail)
+		return gnet_stats_copy(d, TCA_STATS_QUEUE,
+				       &qstats, sizeof(qstats));
+
+	return 0;
+}
+EXPORT_SYMBOL(gnet_stats_copy_queue);
+
+/**
+ * gnet_stats_copy_app - copy application specific statistics into statistics TLV
+ * @d: dumping handle
+ * @st: application specific statistics data
+ * @len: length of data
+ *
+ * Appends the application specific statistics to the top level TLV created by
+ * gnet_stats_start_copy() and remembers the data for XSTATS if the dumping
+ * handle is in backward compatibility mode.
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_copy_app(struct gnet_dump *d, void *st, int len)
+{
+	if (d->compat_xstats) {
+		d->xstats = kmemdup(st, len, GFP_ATOMIC);
+		if (!d->xstats)
+			goto err_out;
+		d->xstats_len = len;
+	}
+
+	if (d->tail)
+		return gnet_stats_copy(d, TCA_STATS_APP, st, len);
+
+	return 0;
+
+err_out:
+	d->xstats_len = 0;
+	spin_unlock_bh(d->lock);
+	return -1;
+}
+EXPORT_SYMBOL(gnet_stats_copy_app);
+
+/**
+ * gnet_stats_finish_copy - finish dumping procedure
+ * @d: dumping handle
+ *
+ * Corrects the length of the top level TLV to include all TLVs added
+ * by gnet_stats_copy_XXX() calls. Adds the backward compatibility TLVs
+ * if gnet_stats_start_copy_compat() was used and releases the statistics
+ * lock.
+ *
+ * Returns 0 on success or -1 with the statistic lock released
+ * if the room in the socket buffer was not sufficient.
+ */
+int
+gnet_stats_finish_copy(struct gnet_dump *d)
+{
+	if (d->tail)
+		d->tail->nla_len = skb_tail_pointer(d->skb) - (u8 *)d->tail;
+
+	if (d->compat_tc_stats)
+		if (gnet_stats_copy(d, d->compat_tc_stats, &d->tc_stats,
+			sizeof(d->tc_stats)) < 0)
+			return -1;
+
+	if (d->compat_xstats && d->xstats) {
+		if (gnet_stats_copy(d, d->compat_xstats, d->xstats,
+			d->xstats_len) < 0)
+			return -1;
+	}
+
+	kfree(d->xstats);
+	d->xstats = NULL;
+	d->xstats_len = 0;
+	spin_unlock_bh(d->lock);
+	return 0;
+}
+EXPORT_SYMBOL(gnet_stats_finish_copy);

net/core/iovec.c

@@ -0,0 +1,184 @@
+/*
+ *	iovec manipulation routines.
+ *
+ *
+ *		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; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ *	Fixes:
+ *		Andrew Lunn	:	Errors in iovec copying.
+ *		Pedro Roque	:	Added memcpy_fromiovecend and
+ *					csum_..._fromiovecend.
+ *		Andi Kleen	:	fixed error handling for 2.1
+ *		Alexey Kuznetsov:	2.1 optimisations
+ *		Andi Kleen	:	Fix csum*fromiovecend for IPv6.
+ */
+
+#include <linux/errno.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/mm.h>
+#include <linux/net.h>
+#include <linux/in6.h>
+#include <asm/uaccess.h>
+#include <asm/byteorder.h>
+#include <net/checksum.h>
+#include <net/sock.h>
+
+/*
+ *	Verify iovec. The caller must ensure that the iovec is big enough
+ *	to hold the message iovec.
+ *
+ *	Save time not doing access_ok. copy_*_user will make this work
+ *	in any case.
+ */
+
+int verify_iovec(struct msghdr *m, struct iovec *iov, struct sockaddr_storage *address, int mode)
+{
+	int size, ct, err;
+
+	if (m->msg_name && m->msg_namelen) {
+		if (mode == VERIFY_READ) {
+			void __user *namep;
+			namep = (void __user __force *) m->msg_name;
+			err = move_addr_to_kernel(namep, m->msg_namelen,
+						  address);
+			if (err < 0)
+				return err;
+		}
+		m->msg_name = address;
+	} else {
+		m->msg_name = NULL;
+		m->msg_namelen = 0;
+	}
+
+	size = m->msg_iovlen * sizeof(struct iovec);
+	if (copy_from_user(iov, (void __user __force *) m->msg_iov, size))
+		return -EFAULT;
+
+	m->msg_iov = iov;
+	err = 0;
+
+	for (ct = 0; ct < m->msg_iovlen; ct++) {
+		size_t len = iov[ct].iov_len;
+
+		if (len > INT_MAX - err) {
+			len = INT_MAX - err;
+			iov[ct].iov_len = len;
+		}
+		err += len;
+	}
+
+	return err;
+}
+
+/*
+ *	And now for the all-in-one: copy and checksum from a user iovec
+ *	directly to a datagram
+ *	Calls to csum_partial but the last must be in 32 bit chunks
+ *
+ *	ip_build_xmit must ensure that when fragmenting only the last
+ *	call to this function will be unaligned also.
+ */
+int csum_partial_copy_fromiovecend(unsigned char *kdata, struct iovec *iov,
+				 int offset, unsigned int len, __wsum *csump)
+{
+	__wsum csum = *csump;
+	int partial_cnt = 0, err = 0;
+
+	/* Skip over the finished iovecs */
+	while (offset >= iov->iov_len) {
+		offset -= iov->iov_len;
+		iov++;
+	}
+
+	while (len > 0) {
+		u8 __user *base = iov->iov_base + offset;
+		int copy = min_t(unsigned int, len, iov->iov_len - offset);
+
+		offset = 0;
+
+		/* There is a remnant from previous iov. */
+		if (partial_cnt) {
+			int par_len = 4 - partial_cnt;
+
+			/* iov component is too short ... */
+			if (par_len > copy) {
+				if (copy_from_user(kdata, base, copy))
+					goto out_fault;
+				kdata += copy;
+				base += copy;
+				partial_cnt += copy;
+				len -= copy;
+				iov++;
+				if (len)
+					continue;
+				*csump = csum_partial(kdata - partial_cnt,
+							 partial_cnt, csum);
+				goto out;
+			}
+			if (copy_from_user(kdata, base, par_len))
+				goto out_fault;
+			csum = csum_partial(kdata - partial_cnt, 4, csum);
+			kdata += par_len;
+			base  += par_len;
+			copy  -= par_len;
+			len   -= par_len;
+			partial_cnt = 0;
+		}
+
+		if (len > copy) {
+			partial_cnt = copy % 4;
+			if (partial_cnt) {
+				copy -= partial_cnt;
+				if (copy_from_user(kdata + copy, base + copy,
+						partial_cnt))
+					goto out_fault;
+			}
+		}
+
+		if (copy) {
+			csum = csum_and_copy_from_user(base, kdata, copy,
+							csum, &err);
+			if (err)
+				goto out;
+		}
+		len   -= copy + partial_cnt;
+		kdata += copy + partial_cnt;
+		iov++;
+	}
+	*csump = csum;
+out:
+	return err;
+
+out_fault:
+	err = -EFAULT;
+	goto out;
+}
+EXPORT_SYMBOL(csum_partial_copy_fromiovecend);
+
+unsigned long iov_pages(const struct iovec *iov, int offset,
+			unsigned long nr_segs)
+{
+	unsigned long seg, base;
+	int pages = 0, len, size;
+
+	while (nr_segs && (offset >= iov->iov_len)) {
+		offset -= iov->iov_len;
+		++iov;
+		--nr_segs;
+	}
+
+	for (seg = 0; seg < nr_segs; seg++) {
+		base = (unsigned long)iov[seg].iov_base + offset;
+		len = iov[seg].iov_len - offset;
+		size = ((base & ~PAGE_MASK) + len + ~PAGE_MASK) >> PAGE_SHIFT;
+		pages += size;
+		offset = 0;
+	}
+
+	return pages;
+}
+EXPORT_SYMBOL(iov_pages);

net/core/link_watch.c

@@ -0,0 +1,253 @@
+/*
+ * Linux network device link state notification
+ *
+ * Author:
+ *     Stefan Rompf <sux@loplof.de>
+ *
+ * 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; either version
+ * 2 of the License, or (at your option) any later version.
+ *
+ */
+
+#include <linux/module.h>
+#include <linux/netdevice.h>
+#include <linux/if.h>
+#include <net/sock.h>
+#include <net/pkt_sched.h>
+#include <linux/rtnetlink.h>
+#include <linux/jiffies.h>
+#include <linux/spinlock.h>
+#include <linux/workqueue.h>
+#include <linux/bitops.h>
+#include <asm/types.h>
+
+
+enum lw_bits {
+	LW_URGENT = 0,
+};
+
+static unsigned long linkwatch_flags;
+static unsigned long linkwatch_nextevent;
+
+static void linkwatch_event(struct work_struct *dummy);
+static DECLARE_DELAYED_WORK(linkwatch_work, linkwatch_event);
+
+static LIST_HEAD(lweventlist);
+static DEFINE_SPINLOCK(lweventlist_lock);
+
+static unsigned char default_operstate(const struct net_device *dev)
+{
+	if (!netif_carrier_ok(dev))
+		return (dev->ifindex != dev->iflink ?
+			IF_OPER_LOWERLAYERDOWN : IF_OPER_DOWN);
+
+	if (netif_dormant(dev))
+		return IF_OPER_DORMANT;
+
+	return IF_OPER_UP;
+}
+
+
+static void rfc2863_policy(struct net_device *dev)
+{
+	unsigned char operstate = default_operstate(dev);
+
+	if (operstate == dev->operstate)
+		return;
+
+	write_lock_bh(&dev_base_lock);
+
+	switch(dev->link_mode) {
+	case IF_LINK_MODE_DORMANT:
+		if (operstate == IF_OPER_UP)
+			operstate = IF_OPER_DORMANT;
+		break;
+
+	case IF_LINK_MODE_DEFAULT:
+	default:
+		break;
+	}
+
+	dev->operstate = operstate;
+
+	write_unlock_bh(&dev_base_lock);
+}
+
+
+void linkwatch_init_dev(struct net_device *dev)
+{
+	/* Handle pre-registration link state changes */
+	if (!netif_carrier_ok(dev) || netif_dormant(dev))
+		rfc2863_policy(dev);
+}
+
+
+static bool linkwatch_urgent_event(struct net_device *dev)
+{
+	if (!netif_running(dev))
+		return false;
+
+	if (dev->ifindex != dev->iflink)
+		return true;
+
+	if (dev->priv_flags & IFF_TEAM_PORT)
+		return true;
+
+	return netif_carrier_ok(dev) &&	qdisc_tx_changing(dev);
+}
+
+
+static void linkwatch_add_event(struct net_device *dev)
+{
+	unsigned long flags;
+
+	spin_lock_irqsave(&lweventlist_lock, flags);
+	if (list_empty(&dev->link_watch_list)) {
+		list_add_tail(&dev->link_watch_list, &lweventlist);
+		dev_hold(dev);
+	}
+	spin_unlock_irqrestore(&lweventlist_lock, flags);
+}
+
+
+static void linkwatch_schedule_work(int urgent)
+{
+	unsigned long delay = linkwatch_nextevent - jiffies;
+
+	if (test_bit(LW_URGENT, &linkwatch_flags))
+		return;
+
+	/* Minimise down-time: drop delay for up event. */
+	if (urgent) {
+		if (test_and_set_bit(LW_URGENT, &linkwatch_flags))
+			return;
+		delay = 0;
+	}
+
+	/* If we wrap around we'll delay it by at most HZ. */
+	if (delay > HZ)
+		delay = 0;
+
+	/*
+	 * If urgent, schedule immediate execution; otherwise, don't
+	 * override the existing timer.
+	 */
+	if (test_bit(LW_URGENT, &linkwatch_flags))
+		mod_delayed_work(system_wq, &linkwatch_work, 0);
+	else
+		schedule_delayed_work(&linkwatch_work, delay);
+}
+
+
+static void linkwatch_do_dev(struct net_device *dev)
+{
+	/*
+	 * Make sure the above read is complete since it can be
+	 * rewritten as soon as we clear the bit below.
+	 */
+	smp_mb__before_atomic();
+
+	/* We are about to handle this device,
+	 * so new events can be accepted
+	 */
+	clear_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state);
+
+	rfc2863_policy(dev);
+	if (dev->flags & IFF_UP) {
+		if (netif_carrier_ok(dev))
+			dev_activate(dev);
+		else
+			dev_deactivate(dev);
+
+		netdev_state_change(dev);
+	}
+	dev_put(dev);
+}
+
+static void __linkwatch_run_queue(int urgent_only)
+{
+	struct net_device *dev;
+	LIST_HEAD(wrk);
+
+	/*
+	 * Limit the number of linkwatch events to one
+	 * per second so that a runaway driver does not
+	 * cause a storm of messages on the netlink
+	 * socket.  This limit does not apply to up events
+	 * while the device qdisc is down.
+	 */
+	if (!urgent_only)
+		linkwatch_nextevent = jiffies + HZ;
+	/* Limit wrap-around effect on delay. */
+	else if (time_after(linkwatch_nextevent, jiffies + HZ))
+		linkwatch_nextevent = jiffies;
+
+	clear_bit(LW_URGENT, &linkwatch_flags);
+
+	spin_lock_irq(&lweventlist_lock);
+	list_splice_init(&lweventlist, &wrk);
+
+	while (!list_empty(&wrk)) {
+
+		dev = list_first_entry(&wrk, struct net_device, link_watch_list);
+		list_del_init(&dev->link_watch_list);
+
+		if (urgent_only && !linkwatch_urgent_event(dev)) {
+			list_add_tail(&dev->link_watch_list, &lweventlist);
+			continue;
+		}
+		spin_unlock_irq(&lweventlist_lock);
+		linkwatch_do_dev(dev);
+		spin_lock_irq(&lweventlist_lock);
+	}
+
+	if (!list_empty(&lweventlist))
+		linkwatch_schedule_work(0);
+	spin_unlock_irq(&lweventlist_lock);
+}
+
+void linkwatch_forget_dev(struct net_device *dev)
+{
+	unsigned long flags;
+	int clean = 0;
+
+	spin_lock_irqsave(&lweventlist_lock, flags);
+	if (!list_empty(&dev->link_watch_list)) {
+		list_del_init(&dev->link_watch_list);
+		clean = 1;
+	}
+	spin_unlock_irqrestore(&lweventlist_lock, flags);
+	if (clean)
+		linkwatch_do_dev(dev);
+}
+
+
+/* Must be called with the rtnl semaphore held */
+void linkwatch_run_queue(void)
+{
+	__linkwatch_run_queue(0);
+}
+
+
+static void linkwatch_event(struct work_struct *dummy)
+{
+	rtnl_lock();
+	__linkwatch_run_queue(time_after(linkwatch_nextevent, jiffies));
+	rtnl_unlock();
+}
+
+
+void linkwatch_fire_event(struct net_device *dev)
+{
+	bool urgent = linkwatch_urgent_event(dev);
+
+	if (!test_and_set_bit(__LINK_STATE_LINKWATCH_PENDING, &dev->state)) {
+		linkwatch_add_event(dev);
+	} else if (!urgent)
+		return;
+
+	linkwatch_schedule_work(urgent);
+}
+EXPORT_SYMBOL(linkwatch_fire_event);

net/core/net-procfs.c

@@ -0,0 +1,423 @@
+#include <linux/netdevice.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+#include <net/wext.h>
+
+#define BUCKET_SPACE (32 - NETDEV_HASHBITS - 1)
+
+#define get_bucket(x) ((x) >> BUCKET_SPACE)
+#define get_offset(x) ((x) & ((1 << BUCKET_SPACE) - 1))
+#define set_bucket_offset(b, o) ((b) << BUCKET_SPACE | (o))
+
+extern struct list_head ptype_all __read_mostly;
+extern struct list_head ptype_base[PTYPE_HASH_SIZE] __read_mostly;
+
+static inline struct net_device *dev_from_same_bucket(struct seq_file *seq, loff_t *pos)
+{
+	struct net *net = seq_file_net(seq);
+	struct net_device *dev;
+	struct hlist_head *h;
+	unsigned int count = 0, offset = get_offset(*pos);
+
+	h = &net->dev_name_head[get_bucket(*pos)];
+	hlist_for_each_entry_rcu(dev, h, name_hlist) {
+		if (++count == offset)
+			return dev;
+	}
+
+	return NULL;
+}
+
+static inline struct net_device *dev_from_bucket(struct seq_file *seq, loff_t *pos)
+{
+	struct net_device *dev;
+	unsigned int bucket;
+
+	do {
+		dev = dev_from_same_bucket(seq, pos);
+		if (dev)
+			return dev;
+
+		bucket = get_bucket(*pos) + 1;
+		*pos = set_bucket_offset(bucket, 1);
+	} while (bucket < NETDEV_HASHENTRIES);
+
+	return NULL;
+}
+
+/*
+ *	This is invoked by the /proc filesystem handler to display a device
+ *	in detail.
+ */
+static void *dev_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(RCU)
+{
+	rcu_read_lock();
+	if (!*pos)
+		return SEQ_START_TOKEN;
+
+	if (get_bucket(*pos) >= NETDEV_HASHENTRIES)
+		return NULL;
+
+	return dev_from_bucket(seq, pos);
+}
+
+static void *dev_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return dev_from_bucket(seq, pos);
+}
+
+static void dev_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
+{
+	rcu_read_unlock();
+}
+
+static void dev_seq_printf_stats(struct seq_file *seq, struct net_device *dev)
+{
+	struct rtnl_link_stats64 temp;
+	const struct rtnl_link_stats64 *stats = dev_get_stats(dev, &temp);
+
+	seq_printf(seq, "%6s: %7llu %7llu %4llu %4llu %4llu %5llu %10llu %9llu "
+		   "%8llu %7llu %4llu %4llu %4llu %5llu %7llu %10llu\n",
+		   dev->name, stats->rx_bytes, stats->rx_packets,
+		   stats->rx_errors,
+		   stats->rx_dropped + stats->rx_missed_errors,
+		   stats->rx_fifo_errors,
+		   stats->rx_length_errors + stats->rx_over_errors +
+		    stats->rx_crc_errors + stats->rx_frame_errors,
+		   stats->rx_compressed, stats->multicast,
+		   stats->tx_bytes, stats->tx_packets,
+		   stats->tx_errors, stats->tx_dropped,
+		   stats->tx_fifo_errors, stats->collisions,
+		   stats->tx_carrier_errors +
+		    stats->tx_aborted_errors +
+		    stats->tx_window_errors +
+		    stats->tx_heartbeat_errors,
+		   stats->tx_compressed);
+}
+
+/*
+ *	Called from the PROCfs module. This now uses the new arbitrary sized
+ *	/proc/net interface to create /proc/net/dev
+ */
+static int dev_seq_show(struct seq_file *seq, void *v)
+{
+	if (v == SEQ_START_TOKEN)
+		seq_puts(seq, "Inter-|   Receive                            "
+			      "                    |  Transmit\n"
+			      " face |bytes    packets errs drop fifo frame "
+			      "compressed multicast|bytes    packets errs "
+			      "drop fifo colls carrier compressed\n");
+	else
+		dev_seq_printf_stats(seq, v);
+	return 0;
+}
+
+static struct softnet_data *softnet_get_online(loff_t *pos)
+{
+	struct softnet_data *sd = NULL;
+
+	while (*pos < nr_cpu_ids)
+		if (cpu_online(*pos)) {
+			sd = &per_cpu(softnet_data, *pos);
+			break;
+		} else
+			++*pos;
+	return sd;
+}
+
+static void *softnet_seq_start(struct seq_file *seq, loff_t *pos)
+{
+	return softnet_get_online(pos);
+}
+
+static void *softnet_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	++*pos;
+	return softnet_get_online(pos);
+}
+
+static void softnet_seq_stop(struct seq_file *seq, void *v)
+{
+}
+
+static int softnet_seq_show(struct seq_file *seq, void *v)
+{
+	struct softnet_data *sd = v;
+	unsigned int flow_limit_count = 0;
+
+#ifdef CONFIG_NET_FLOW_LIMIT
+	struct sd_flow_limit *fl;
+
+	rcu_read_lock();
+	fl = rcu_dereference(sd->flow_limit);
+	if (fl)
+		flow_limit_count = fl->count;
+	rcu_read_unlock();
+#endif
+
+	seq_printf(seq,
+		   "%08x %08x %08x %08x %08x %08x %08x %08x %08x %08x %08x\n",
+		   sd->processed, sd->dropped, sd->time_squeeze, 0,
+		   0, 0, 0, 0, /* was fastroute */
+		   sd->cpu_collision, sd->received_rps, flow_limit_count);
+	return 0;
+}
+
+static const struct seq_operations dev_seq_ops = {
+	.start = dev_seq_start,
+	.next  = dev_seq_next,
+	.stop  = dev_seq_stop,
+	.show  = dev_seq_show,
+};
+
+static int dev_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open_net(inode, file, &dev_seq_ops,
+			    sizeof(struct seq_net_private));
+}
+
+static const struct file_operations dev_seq_fops = {
+	.owner	 = THIS_MODULE,
+	.open    = dev_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_net,
+};
+
+static const struct seq_operations softnet_seq_ops = {
+	.start = softnet_seq_start,
+	.next  = softnet_seq_next,
+	.stop  = softnet_seq_stop,
+	.show  = softnet_seq_show,
+};
+
+static int softnet_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open(file, &softnet_seq_ops);
+}
+
+static const struct file_operations softnet_seq_fops = {
+	.owner	 = THIS_MODULE,
+	.open    = softnet_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release,
+};
+
+static void *ptype_get_idx(loff_t pos)
+{
+	struct packet_type *pt = NULL;
+	loff_t i = 0;
+	int t;
+
+	list_for_each_entry_rcu(pt, &ptype_all, list) {
+		if (i == pos)
+			return pt;
+		++i;
+	}
+
+	for (t = 0; t < PTYPE_HASH_SIZE; t++) {
+		list_for_each_entry_rcu(pt, &ptype_base[t], list) {
+			if (i == pos)
+				return pt;
+			++i;
+		}
+	}
+	return NULL;
+}
+
+static void *ptype_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(RCU)
+{
+	rcu_read_lock();
+	return *pos ? ptype_get_idx(*pos - 1) : SEQ_START_TOKEN;
+}
+
+static void *ptype_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct packet_type *pt;
+	struct list_head *nxt;
+	int hash;
+
+	++*pos;
+	if (v == SEQ_START_TOKEN)
+		return ptype_get_idx(0);
+
+	pt = v;
+	nxt = pt->list.next;
+	if (pt->type == htons(ETH_P_ALL)) {
+		if (nxt != &ptype_all)
+			goto found;
+		hash = 0;
+		nxt = ptype_base[0].next;
+	} else
+		hash = ntohs(pt->type) & PTYPE_HASH_MASK;
+
+	while (nxt == &ptype_base[hash]) {
+		if (++hash >= PTYPE_HASH_SIZE)
+			return NULL;
+		nxt = ptype_base[hash].next;
+	}
+found:
+	return list_entry(nxt, struct packet_type, list);
+}
+
+static void ptype_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
+{
+	rcu_read_unlock();
+}
+
+static int ptype_seq_show(struct seq_file *seq, void *v)
+{
+	struct packet_type *pt = v;
+
+	if (v == SEQ_START_TOKEN)
+		seq_puts(seq, "Type Device      Function\n");
+	else if (pt->dev == NULL || dev_net(pt->dev) == seq_file_net(seq)) {
+		if (pt->type == htons(ETH_P_ALL))
+			seq_puts(seq, "ALL ");
+		else
+			seq_printf(seq, "%04x", ntohs(pt->type));
+
+		seq_printf(seq, " %-8s %pf\n",
+			   pt->dev ? pt->dev->name : "", pt->func);
+	}
+
+	return 0;
+}
+
+static const struct seq_operations ptype_seq_ops = {
+	.start = ptype_seq_start,
+	.next  = ptype_seq_next,
+	.stop  = ptype_seq_stop,
+	.show  = ptype_seq_show,
+};
+
+static int ptype_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open_net(inode, file, &ptype_seq_ops,
+			sizeof(struct seq_net_private));
+}
+
+static const struct file_operations ptype_seq_fops = {
+	.owner	 = THIS_MODULE,
+	.open    = ptype_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_net,
+};
+
+
+static int __net_init dev_proc_net_init(struct net *net)
+{
+	int rc = -ENOMEM;
+
+	if (!proc_create("dev", S_IRUGO, net->proc_net, &dev_seq_fops))
+		goto out;
+	if (!proc_create("softnet_stat", S_IRUGO, net->proc_net,
+			 &softnet_seq_fops))
+		goto out_dev;
+	if (!proc_create("ptype", S_IRUGO, net->proc_net, &ptype_seq_fops))
+		goto out_softnet;
+
+	if (wext_proc_init(net))
+		goto out_ptype;
+	rc = 0;
+out:
+	return rc;
+out_ptype:
+	remove_proc_entry("ptype", net->proc_net);
+out_softnet:
+	remove_proc_entry("softnet_stat", net->proc_net);
+out_dev:
+	remove_proc_entry("dev", net->proc_net);
+	goto out;
+}
+
+static void __net_exit dev_proc_net_exit(struct net *net)
+{
+	wext_proc_exit(net);
+
+	remove_proc_entry("ptype", net->proc_net);
+	remove_proc_entry("softnet_stat", net->proc_net);
+	remove_proc_entry("dev", net->proc_net);
+}
+
+static struct pernet_operations __net_initdata dev_proc_ops = {
+	.init = dev_proc_net_init,
+	.exit = dev_proc_net_exit,
+};
+
+static int dev_mc_seq_show(struct seq_file *seq, void *v)
+{
+	struct netdev_hw_addr *ha;
+	struct net_device *dev = v;
+
+	if (v == SEQ_START_TOKEN)
+		return 0;
+
+	netif_addr_lock_bh(dev);
+	netdev_for_each_mc_addr(ha, dev) {
+		int i;
+
+		seq_printf(seq, "%-4d %-15s %-5d %-5d ", dev->ifindex,
+			   dev->name, ha->refcount, ha->global_use);
+
+		for (i = 0; i < dev->addr_len; i++)
+			seq_printf(seq, "%02x", ha->addr[i]);
+
+		seq_putc(seq, '\n');
+	}
+	netif_addr_unlock_bh(dev);
+	return 0;
+}
+
+static const struct seq_operations dev_mc_seq_ops = {
+	.start = dev_seq_start,
+	.next  = dev_seq_next,
+	.stop  = dev_seq_stop,
+	.show  = dev_mc_seq_show,
+};
+
+static int dev_mc_seq_open(struct inode *inode, struct file *file)
+{
+	return seq_open_net(inode, file, &dev_mc_seq_ops,
+			    sizeof(struct seq_net_private));
+}
+
+static const struct file_operations dev_mc_seq_fops = {
+	.owner	 = THIS_MODULE,
+	.open    = dev_mc_seq_open,
+	.read    = seq_read,
+	.llseek  = seq_lseek,
+	.release = seq_release_net,
+};
+
+static int __net_init dev_mc_net_init(struct net *net)
+{
+	if (!proc_create("dev_mcast", 0, net->proc_net, &dev_mc_seq_fops))
+		return -ENOMEM;
+	return 0;
+}
+
+static void __net_exit dev_mc_net_exit(struct net *net)
+{
+	remove_proc_entry("dev_mcast", net->proc_net);
+}
+
+static struct pernet_operations __net_initdata dev_mc_net_ops = {
+	.init = dev_mc_net_init,
+	.exit = dev_mc_net_exit,
+};
+
+int __init dev_proc_init(void)
+{
+	int ret = register_pernet_subsys(&dev_proc_ops);
+	if (!ret)
+		return register_pernet_subsys(&dev_mc_net_ops);
+	return ret;
+}

net/core/net-sysfs.h

@@ -0,0 +1,11 @@
+#ifndef __NET_SYSFS_H__
+#define __NET_SYSFS_H__
+
+int __init netdev_kobject_init(void);
+int netdev_register_kobject(struct net_device *);
+void netdev_unregister_kobject(struct net_device *);
+int net_rx_queue_update_kobjects(struct net_device *, int old_num, int new_num);
+int netdev_queue_update_kobjects(struct net_device *net,
+				 int old_num, int new_num);
+
+#endif

net/core/net-traces.c

@@ -0,0 +1,37 @@
+/*
+ * consolidates trace point definitions
+ *
+ * Copyright (C) 2009 Neil Horman <nhorman@tuxdriver.com>
+ */
+
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/string.h>
+#include <linux/if_arp.h>
+#include <linux/inetdevice.h>
+#include <linux/inet.h>
+#include <linux/interrupt.h>
+#include <linux/export.h>
+#include <linux/netpoll.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/rcupdate.h>
+#include <linux/types.h>
+#include <linux/workqueue.h>
+#include <linux/netlink.h>
+#include <linux/net_dropmon.h>
+#include <linux/slab.h>
+
+#include <asm/unaligned.h>
+#include <asm/bitops.h>
+
+#define CREATE_TRACE_POINTS
+#include <trace/events/skb.h>
+#include <trace/events/net.h>
+#include <trace/events/napi.h>
+#include <trace/events/sock.h>
+#include <trace/events/udp.h>
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(kfree_skb);
+
+EXPORT_TRACEPOINT_SYMBOL_GPL(napi_poll);

net/core/net_namespace.c

@@ -0,0 +1,678 @@
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/workqueue.h>
+#include <linux/rtnetlink.h>
+#include <linux/cache.h>
+#include <linux/slab.h>
+#include <linux/list.h>
+#include <linux/delay.h>
+#include <linux/sched.h>
+#include <linux/idr.h>
+#include <linux/rculist.h>
+#include <linux/nsproxy.h>
+#include <linux/fs.h>
+#include <linux/proc_ns.h>
+#include <linux/file.h>
+#include <linux/export.h>
+#include <linux/user_namespace.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+
+/*
+ *	Our network namespace constructor/destructor lists
+ */
+
+static LIST_HEAD(pernet_list);
+static struct list_head *first_device = &pernet_list;
+DEFINE_MUTEX(net_mutex);
+
+LIST_HEAD(net_namespace_list);
+EXPORT_SYMBOL_GPL(net_namespace_list);
+
+struct net init_net = {
+	.dev_base_head = LIST_HEAD_INIT(init_net.dev_base_head),
+};
+EXPORT_SYMBOL(init_net);
+
+#define INITIAL_NET_GEN_PTRS	13 /* +1 for len +2 for rcu_head */
+
+static unsigned int max_gen_ptrs = INITIAL_NET_GEN_PTRS;
+
+static struct net_generic *net_alloc_generic(void)
+{
+	struct net_generic *ng;
+	size_t generic_size = offsetof(struct net_generic, ptr[max_gen_ptrs]);
+
+	ng = kzalloc(generic_size, GFP_KERNEL);
+	if (ng)
+		ng->len = max_gen_ptrs;
+
+	return ng;
+}
+
+static int net_assign_generic(struct net *net, int id, void *data)
+{
+	struct net_generic *ng, *old_ng;
+
+	BUG_ON(!mutex_is_locked(&net_mutex));
+	BUG_ON(id == 0);
+
+	old_ng = rcu_dereference_protected(net->gen,
+					   lockdep_is_held(&net_mutex));
+	ng = old_ng;
+	if (old_ng->len >= id)
+		goto assign;
+
+	ng = net_alloc_generic();
+	if (ng == NULL)
+		return -ENOMEM;
+
+	/*
+	 * Some synchronisation notes:
+	 *
+	 * The net_generic explores the net->gen array inside rcu
+	 * read section. Besides once set the net->gen->ptr[x]
+	 * pointer never changes (see rules in netns/generic.h).
+	 *
+	 * That said, we simply duplicate this array and schedule
+	 * the old copy for kfree after a grace period.
+	 */
+
+	memcpy(&ng->ptr, &old_ng->ptr, old_ng->len * sizeof(void*));
+
+	rcu_assign_pointer(net->gen, ng);
+	kfree_rcu(old_ng, rcu);
+assign:
+	ng->ptr[id - 1] = data;
+	return 0;
+}
+
+static int ops_init(const struct pernet_operations *ops, struct net *net)
+{
+	int err = -ENOMEM;
+	void *data = NULL;
+
+	if (ops->id && ops->size) {
+		data = kzalloc(ops->size, GFP_KERNEL);
+		if (!data)
+			goto out;
+
+		err = net_assign_generic(net, *ops->id, data);
+		if (err)
+			goto cleanup;
+	}
+	err = 0;
+	if (ops->init)
+		err = ops->init(net);
+	if (!err)
+		return 0;
+
+cleanup:
+	kfree(data);
+
+out:
+	return err;
+}
+
+static void ops_free(const struct pernet_operations *ops, struct net *net)
+{
+	if (ops->id && ops->size) {
+		int id = *ops->id;
+		kfree(net_generic(net, id));
+	}
+}
+
+static void ops_exit_list(const struct pernet_operations *ops,
+			  struct list_head *net_exit_list)
+{
+	struct net *net;
+	if (ops->exit) {
+		list_for_each_entry(net, net_exit_list, exit_list)
+			ops->exit(net);
+	}
+	if (ops->exit_batch)
+		ops->exit_batch(net_exit_list);
+}
+
+static void ops_free_list(const struct pernet_operations *ops,
+			  struct list_head *net_exit_list)
+{
+	struct net *net;
+	if (ops->size && ops->id) {
+		list_for_each_entry(net, net_exit_list, exit_list)
+			ops_free(ops, net);
+	}
+}
+
+/*
+ * setup_net runs the initializers for the network namespace object.
+ */
+static __net_init int setup_net(struct net *net, struct user_namespace *user_ns)
+{
+	/* Must be called with net_mutex held */
+	const struct pernet_operations *ops, *saved_ops;
+	int error = 0;
+	LIST_HEAD(net_exit_list);
+
+	atomic_set(&net->count, 1);
+	atomic_set(&net->passive, 1);
+	net->dev_base_seq = 1;
+	net->user_ns = user_ns;
+
+#ifdef NETNS_REFCNT_DEBUG
+	atomic_set(&net->use_count, 0);
+#endif
+
+	list_for_each_entry(ops, &pernet_list, list) {
+		error = ops_init(ops, net);
+		if (error < 0)
+			goto out_undo;
+	}
+out:
+	return error;
+
+out_undo:
+	/* Walk through the list backwards calling the exit functions
+	 * for the pernet modules whose init functions did not fail.
+	 */
+	list_add(&net->exit_list, &net_exit_list);
+	saved_ops = ops;
+	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
+		ops_exit_list(ops, &net_exit_list);
+
+	ops = saved_ops;
+	list_for_each_entry_continue_reverse(ops, &pernet_list, list)
+		ops_free_list(ops, &net_exit_list);
+
+	rcu_barrier();
+	goto out;
+}
+
+
+#ifdef CONFIG_NET_NS
+static struct kmem_cache *net_cachep;
+static struct workqueue_struct *netns_wq;
+
+static struct net *net_alloc(void)
+{
+	struct net *net = NULL;
+	struct net_generic *ng;
+
+	ng = net_alloc_generic();
+	if (!ng)
+		goto out;
+
+	net = kmem_cache_zalloc(net_cachep, GFP_KERNEL);
+	if (!net)
+		goto out_free;
+
+	rcu_assign_pointer(net->gen, ng);
+out:
+	return net;
+
+out_free:
+	kfree(ng);
+	goto out;
+}
+
+static void net_free(struct net *net)
+{
+#ifdef NETNS_REFCNT_DEBUG
+	if (unlikely(atomic_read(&net->use_count) != 0)) {
+		pr_emerg("network namespace not free! Usage: %d\n",
+			 atomic_read(&net->use_count));
+		return;
+	}
+#endif
+	kfree(rcu_access_pointer(net->gen));
+	kmem_cache_free(net_cachep, net);
+}
+
+void net_drop_ns(void *p)
+{
+	struct net *ns = p;
+	if (ns && atomic_dec_and_test(&ns->passive))
+		net_free(ns);
+}
+
+struct net *copy_net_ns(unsigned long flags,
+			struct user_namespace *user_ns, struct net *old_net)
+{
+	struct net *net;
+	int rv;
+
+	if (!(flags & CLONE_NEWNET))
+		return get_net(old_net);
+
+	net = net_alloc();
+	if (!net)
+		return ERR_PTR(-ENOMEM);
+
+	get_user_ns(user_ns);
+
+	mutex_lock(&net_mutex);
+	rv = setup_net(net, user_ns);
+	if (rv == 0) {
+		rtnl_lock();
+		list_add_tail_rcu(&net->list, &net_namespace_list);
+		rtnl_unlock();
+	}
+	mutex_unlock(&net_mutex);
+	if (rv < 0) {
+		put_user_ns(user_ns);
+		net_drop_ns(net);
+		return ERR_PTR(rv);
+	}
+	return net;
+}
+
+static DEFINE_SPINLOCK(cleanup_list_lock);
+static LIST_HEAD(cleanup_list);  /* Must hold cleanup_list_lock to touch */
+
+static void cleanup_net(struct work_struct *work)
+{
+	const struct pernet_operations *ops;
+	struct net *net, *tmp;
+	struct list_head net_kill_list;
+	LIST_HEAD(net_exit_list);
+
+	/* Atomically snapshot the list of namespaces to cleanup */
+	spin_lock_irq(&cleanup_list_lock);
+	list_replace_init(&cleanup_list, &net_kill_list);
+	spin_unlock_irq(&cleanup_list_lock);
+
+	mutex_lock(&net_mutex);
+
+	/* Don't let anyone else find us. */
+	rtnl_lock();
+	list_for_each_entry(net, &net_kill_list, cleanup_list) {
+		list_del_rcu(&net->list);
+		list_add_tail(&net->exit_list, &net_exit_list);
+	}
+	rtnl_unlock();
+
+	/*
+	 * Another CPU might be rcu-iterating the list, wait for it.
+	 * This needs to be before calling the exit() notifiers, so
+	 * the rcu_barrier() below isn't sufficient alone.
+	 */
+	synchronize_rcu();
+
+	/* Run all of the network namespace exit methods */
+	list_for_each_entry_reverse(ops, &pernet_list, list)
+		ops_exit_list(ops, &net_exit_list);
+
+	/* Free the net generic variables */
+	list_for_each_entry_reverse(ops, &pernet_list, list)
+		ops_free_list(ops, &net_exit_list);
+
+	mutex_unlock(&net_mutex);
+
+	/* Ensure there are no outstanding rcu callbacks using this
+	 * network namespace.
+	 */
+	rcu_barrier();
+
+	/* Finally it is safe to free my network namespace structure */
+	list_for_each_entry_safe(net, tmp, &net_exit_list, exit_list) {
+		list_del_init(&net->exit_list);
+		put_user_ns(net->user_ns);
+		net_drop_ns(net);
+	}
+}
+static DECLARE_WORK(net_cleanup_work, cleanup_net);
+
+void __put_net(struct net *net)
+{
+	/* Cleanup the network namespace in process context */
+	unsigned long flags;
+
+	spin_lock_irqsave(&cleanup_list_lock, flags);
+	list_add(&net->cleanup_list, &cleanup_list);
+	spin_unlock_irqrestore(&cleanup_list_lock, flags);
+
+	queue_work(netns_wq, &net_cleanup_work);
+}
+EXPORT_SYMBOL_GPL(__put_net);
+
+struct net *get_net_ns_by_fd(int fd)
+{
+	struct proc_ns *ei;
+	struct file *file;
+	struct net *net;
+
+	file = proc_ns_fget(fd);
+	if (IS_ERR(file))
+		return ERR_CAST(file);
+
+	ei = get_proc_ns(file_inode(file));
+	if (ei->ns_ops == &netns_operations)
+		net = get_net(ei->ns);
+	else
+		net = ERR_PTR(-EINVAL);
+
+	fput(file);
+	return net;
+}
+
+#else
+struct net *get_net_ns_by_fd(int fd)
+{
+	return ERR_PTR(-EINVAL);
+}
+#endif
+
+struct net *get_net_ns_by_pid(pid_t pid)
+{
+	struct task_struct *tsk;
+	struct net *net;
+
+	/* Lookup the network namespace */
+	net = ERR_PTR(-ESRCH);
+	rcu_read_lock();
+	tsk = find_task_by_vpid(pid);
+	if (tsk) {
+		struct nsproxy *nsproxy;
+		task_lock(tsk);
+		nsproxy = tsk->nsproxy;
+		if (nsproxy)
+			net = get_net(nsproxy->net_ns);
+		task_unlock(tsk);
+	}
+	rcu_read_unlock();
+	return net;
+}
+EXPORT_SYMBOL_GPL(get_net_ns_by_pid);
+
+static __net_init int net_ns_net_init(struct net *net)
+{
+	return proc_alloc_inum(&net->proc_inum);
+}
+
+static __net_exit void net_ns_net_exit(struct net *net)
+{
+	proc_free_inum(net->proc_inum);
+}
+
+static struct pernet_operations __net_initdata net_ns_ops = {
+	.init = net_ns_net_init,
+	.exit = net_ns_net_exit,
+};
+
+static int __init net_ns_init(void)
+{
+	struct net_generic *ng;
+
+#ifdef CONFIG_NET_NS
+	net_cachep = kmem_cache_create("net_namespace", sizeof(struct net),
+					SMP_CACHE_BYTES,
+					SLAB_PANIC, NULL);
+
+	/* Create workqueue for cleanup */
+	netns_wq = create_singlethread_workqueue("netns");
+	if (!netns_wq)
+		panic("Could not create netns workq");
+#endif
+
+	ng = net_alloc_generic();
+	if (!ng)
+		panic("Could not allocate generic netns");
+
+	rcu_assign_pointer(init_net.gen, ng);
+
+	mutex_lock(&net_mutex);
+	if (setup_net(&init_net, &init_user_ns))
+		panic("Could not setup the initial network namespace");
+
+	rtnl_lock();
+	list_add_tail_rcu(&init_net.list, &net_namespace_list);
+	rtnl_unlock();
+
+	mutex_unlock(&net_mutex);
+
+	register_pernet_subsys(&net_ns_ops);
+
+	return 0;
+}
+
+pure_initcall(net_ns_init);
+
+#ifdef CONFIG_NET_NS
+static int __register_pernet_operations(struct list_head *list,
+					struct pernet_operations *ops)
+{
+	struct net *net;
+	int error;
+	LIST_HEAD(net_exit_list);
+
+	list_add_tail(&ops->list, list);
+	if (ops->init || (ops->id && ops->size)) {
+		for_each_net(net) {
+			error = ops_init(ops, net);
+			if (error)
+				goto out_undo;
+			list_add_tail(&net->exit_list, &net_exit_list);
+		}
+	}
+	return 0;
+
+out_undo:
+	/* If I have an error cleanup all namespaces I initialized */
+	list_del(&ops->list);
+	ops_exit_list(ops, &net_exit_list);
+	ops_free_list(ops, &net_exit_list);
+	return error;
+}
+
+static void __unregister_pernet_operations(struct pernet_operations *ops)
+{
+	struct net *net;
+	LIST_HEAD(net_exit_list);
+
+	list_del(&ops->list);
+	for_each_net(net)
+		list_add_tail(&net->exit_list, &net_exit_list);
+	ops_exit_list(ops, &net_exit_list);
+	ops_free_list(ops, &net_exit_list);
+}
+
+#else
+
+static int __register_pernet_operations(struct list_head *list,
+					struct pernet_operations *ops)
+{
+	return ops_init(ops, &init_net);
+}
+
+static void __unregister_pernet_operations(struct pernet_operations *ops)
+{
+	LIST_HEAD(net_exit_list);
+	list_add(&init_net.exit_list, &net_exit_list);
+	ops_exit_list(ops, &net_exit_list);
+	ops_free_list(ops, &net_exit_list);
+}
+
+#endif /* CONFIG_NET_NS */
+
+static DEFINE_IDA(net_generic_ids);
+
+static int register_pernet_operations(struct list_head *list,
+				      struct pernet_operations *ops)
+{
+	int error;
+
+	if (ops->id) {
+again:
+		error = ida_get_new_above(&net_generic_ids, 1, ops->id);
+		if (error < 0) {
+			if (error == -EAGAIN) {
+				ida_pre_get(&net_generic_ids, GFP_KERNEL);
+				goto again;
+			}
+			return error;
+		}
+		max_gen_ptrs = max_t(unsigned int, max_gen_ptrs, *ops->id);
+	}
+	error = __register_pernet_operations(list, ops);
+	if (error) {
+		rcu_barrier();
+		if (ops->id)
+			ida_remove(&net_generic_ids, *ops->id);
+	}
+
+	return error;
+}
+
+static void unregister_pernet_operations(struct pernet_operations *ops)
+{
+	
+	__unregister_pernet_operations(ops);
+	rcu_barrier();
+	if (ops->id)
+		ida_remove(&net_generic_ids, *ops->id);
+}
+
+/**
+ *      register_pernet_subsys - register a network namespace subsystem
+ *	@ops:  pernet operations structure for the subsystem
+ *
+ *	Register a subsystem which has init and exit functions
+ *	that are called when network namespaces are created and
+ *	destroyed respectively.
+ *
+ *	When registered all network namespace init functions are
+ *	called for every existing network namespace.  Allowing kernel
+ *	modules to have a race free view of the set of network namespaces.
+ *
+ *	When a new network namespace is created all of the init
+ *	methods are called in the order in which they were registered.
+ *
+ *	When a network namespace is destroyed all of the exit methods
+ *	are called in the reverse of the order with which they were
+ *	registered.
+ */
+int register_pernet_subsys(struct pernet_operations *ops)
+{
+	int error;
+	mutex_lock(&net_mutex);
+	error =  register_pernet_operations(first_device, ops);
+	mutex_unlock(&net_mutex);
+	return error;
+}
+EXPORT_SYMBOL_GPL(register_pernet_subsys);
+
+/**
+ *      unregister_pernet_subsys - unregister a network namespace subsystem
+ *	@ops: pernet operations structure to manipulate
+ *
+ *	Remove the pernet operations structure from the list to be
+ *	used when network namespaces are created or destroyed.  In
+ *	addition run the exit method for all existing network
+ *	namespaces.
+ */
+void unregister_pernet_subsys(struct pernet_operations *ops)
+{
+	mutex_lock(&net_mutex);
+	unregister_pernet_operations(ops);
+	mutex_unlock(&net_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_pernet_subsys);
+
+/**
+ *      register_pernet_device - register a network namespace device
+ *	@ops:  pernet operations structure for the subsystem
+ *
+ *	Register a device which has init and exit functions
+ *	that are called when network namespaces are created and
+ *	destroyed respectively.
+ *
+ *	When registered all network namespace init functions are
+ *	called for every existing network namespace.  Allowing kernel
+ *	modules to have a race free view of the set of network namespaces.
+ *
+ *	When a new network namespace is created all of the init
+ *	methods are called in the order in which they were registered.
+ *
+ *	When a network namespace is destroyed all of the exit methods
+ *	are called in the reverse of the order with which they were
+ *	registered.
+ */
+int register_pernet_device(struct pernet_operations *ops)
+{
+	int error;
+	mutex_lock(&net_mutex);
+	error = register_pernet_operations(&pernet_list, ops);
+	if (!error && (first_device == &pernet_list))
+		first_device = &ops->list;
+	mutex_unlock(&net_mutex);
+	return error;
+}
+EXPORT_SYMBOL_GPL(register_pernet_device);
+
+/**
+ *      unregister_pernet_device - unregister a network namespace netdevice
+ *	@ops: pernet operations structure to manipulate
+ *
+ *	Remove the pernet operations structure from the list to be
+ *	used when network namespaces are created or destroyed.  In
+ *	addition run the exit method for all existing network
+ *	namespaces.
+ */
+void unregister_pernet_device(struct pernet_operations *ops)
+{
+	mutex_lock(&net_mutex);
+	if (&ops->list == first_device)
+		first_device = first_device->next;
+	unregister_pernet_operations(ops);
+	mutex_unlock(&net_mutex);
+}
+EXPORT_SYMBOL_GPL(unregister_pernet_device);
+
+#ifdef CONFIG_NET_NS
+static void *netns_get(struct task_struct *task)
+{
+	struct net *net = NULL;
+	struct nsproxy *nsproxy;
+
+	task_lock(task);
+	nsproxy = task->nsproxy;
+	if (nsproxy)
+		net = get_net(nsproxy->net_ns);
+	task_unlock(task);
+
+	return net;
+}
+
+static void netns_put(void *ns)
+{
+	put_net(ns);
+}
+
+static int netns_install(struct nsproxy *nsproxy, void *ns)
+{
+	struct net *net = ns;
+
+	if (!ns_capable(net->user_ns, CAP_SYS_ADMIN) ||
+	    !ns_capable(current_user_ns(), CAP_SYS_ADMIN))
+		return -EPERM;
+
+	put_net(nsproxy->net_ns);
+	nsproxy->net_ns = get_net(net);
+	return 0;
+}
+
+static unsigned int netns_inum(void *ns)
+{
+	struct net *net = ns;
+	return net->proc_inum;
+}
+
+const struct proc_ns_operations netns_operations = {
+	.name		= "net",
+	.type		= CLONE_NEWNET,
+	.get		= netns_get,
+	.put		= netns_put,
+	.install	= netns_install,
+	.inum		= netns_inum,
+};
+#endif

net/core/netclassid_cgroup.c

@@ -0,0 +1,111 @@
+/*
+ * net/core/netclassid_cgroup.c	Classid Cgroupfs Handling
+ *
+ *		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; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Thomas Graf <tgraf@suug.ch>
+ */
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/cgroup.h>
+#include <linux/fdtable.h>
+#include <net/cls_cgroup.h>
+#include <net/sock.h>
+
+static inline struct cgroup_cls_state *css_cls_state(struct cgroup_subsys_state *css)
+{
+	return css ? container_of(css, struct cgroup_cls_state, css) : NULL;
+}
+
+struct cgroup_cls_state *task_cls_state(struct task_struct *p)
+{
+	return css_cls_state(task_css(p, net_cls_cgrp_id));
+}
+EXPORT_SYMBOL_GPL(task_cls_state);
+
+static struct cgroup_subsys_state *
+cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct cgroup_cls_state *cs;
+
+	cs = kzalloc(sizeof(*cs), GFP_KERNEL);
+	if (!cs)
+		return ERR_PTR(-ENOMEM);
+
+	return &cs->css;
+}
+
+static int cgrp_css_online(struct cgroup_subsys_state *css)
+{
+	struct cgroup_cls_state *cs = css_cls_state(css);
+	struct cgroup_cls_state *parent = css_cls_state(css->parent);
+
+	if (parent)
+		cs->classid = parent->classid;
+
+	return 0;
+}
+
+static void cgrp_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css_cls_state(css));
+}
+
+static int update_classid(const void *v, struct file *file, unsigned n)
+{
+	int err;
+	struct socket *sock = sock_from_file(file, &err);
+
+	if (sock)
+		sock->sk->sk_classid = (u32)(unsigned long)v;
+
+	return 0;
+}
+
+static void cgrp_attach(struct cgroup_subsys_state *css,
+			struct cgroup_taskset *tset)
+{
+	struct cgroup_cls_state *cs = css_cls_state(css);
+	void *v = (void *)(unsigned long)cs->classid;
+	struct task_struct *p;
+
+	cgroup_taskset_for_each(p, tset) {
+		task_lock(p);
+		iterate_fd(p->files, 0, update_classid, v);
+		task_unlock(p);
+	}
+}
+
+static u64 read_classid(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	return css_cls_state(css)->classid;
+}
+
+static int write_classid(struct cgroup_subsys_state *css, struct cftype *cft,
+			 u64 value)
+{
+	css_cls_state(css)->classid = (u32) value;
+
+	return 0;
+}
+
+static struct cftype ss_files[] = {
+	{
+		.name		= "classid",
+		.read_u64	= read_classid,
+		.write_u64	= write_classid,
+	},
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys net_cls_cgrp_subsys = {
+	.css_alloc		= cgrp_css_alloc,
+	.css_online		= cgrp_css_online,
+	.css_free		= cgrp_css_free,
+	.attach			= cgrp_attach,
+	.legacy_cftypes		= ss_files,
+};

net/core/netevent.c

@@ -0,0 +1,70 @@
+/*
+ *	Network event notifiers
+ *
+ *	Authors:
+ *      Tom Tucker             <tom@opengridcomputing.com>
+ *      Steve Wise             <swise@opengridcomputing.com>
+ *
+ *	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; either version
+ *      2 of the License, or (at your option) any later version.
+ *
+ *	Fixes:
+ */
+
+#include <linux/rtnetlink.h>
+#include <linux/notifier.h>
+#include <linux/export.h>
+#include <net/netevent.h>
+
+static ATOMIC_NOTIFIER_HEAD(netevent_notif_chain);
+
+/**
+ *	register_netevent_notifier - register a netevent notifier block
+ *	@nb: notifier
+ *
+ *	Register a notifier to be called when a netevent occurs.
+ *	The notifier passed is linked into the kernel structures and must
+ *	not be reused until it has been unregistered. A negative errno code
+ *	is returned on a failure.
+ */
+int register_netevent_notifier(struct notifier_block *nb)
+{
+	int err;
+
+	err = atomic_notifier_chain_register(&netevent_notif_chain, nb);
+	return err;
+}
+EXPORT_SYMBOL_GPL(register_netevent_notifier);
+
+/**
+ *	netevent_unregister_notifier - unregister a netevent notifier block
+ *	@nb: notifier
+ *
+ *	Unregister a notifier previously registered by
+ *	register_neigh_notifier(). The notifier is unlinked into the
+ *	kernel structures and may then be reused. A negative errno code
+ *	is returned on a failure.
+ */
+
+int unregister_netevent_notifier(struct notifier_block *nb)
+{
+	return atomic_notifier_chain_unregister(&netevent_notif_chain, nb);
+}
+EXPORT_SYMBOL_GPL(unregister_netevent_notifier);
+
+/**
+ *	call_netevent_notifiers - call all netevent notifier blocks
+ *      @val: value passed unmodified to notifier function
+ *      @v:   pointer passed unmodified to notifier function
+ *
+ *	Call all neighbour notifier blocks.  Parameters and return value
+ *	are as for notifier_call_chain().
+ */
+
+int call_netevent_notifiers(unsigned long val, void *v)
+{
+	return atomic_notifier_call_chain(&netevent_notif_chain, val, v);
+}
+EXPORT_SYMBOL_GPL(call_netevent_notifiers);

net/core/netpoll.c

@@ -0,0 +1,852 @@
+/*
+ * Common framework for low-level network console, dump, and debugger code
+ *
+ * Sep 8 2003  Matt Mackall <mpm@selenic.com>
+ *
+ * based on the netconsole code from:
+ *
+ * Copyright (C) 2001  Ingo Molnar <mingo@redhat.com>
+ * Copyright (C) 2002  Red Hat, Inc.
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/moduleparam.h>
+#include <linux/kernel.h>
+#include <linux/netdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/string.h>
+#include <linux/if_arp.h>
+#include <linux/inetdevice.h>
+#include <linux/inet.h>
+#include <linux/interrupt.h>
+#include <linux/netpoll.h>
+#include <linux/sched.h>
+#include <linux/delay.h>
+#include <linux/rcupdate.h>
+#include <linux/workqueue.h>
+#include <linux/slab.h>
+#include <linux/export.h>
+#include <linux/if_vlan.h>
+#include <net/tcp.h>
+#include <net/udp.h>
+#include <net/addrconf.h>
+#include <net/ndisc.h>
+#include <net/ip6_checksum.h>
+#include <asm/unaligned.h>
+#include <trace/events/napi.h>
+
+/*
+ * We maintain a small pool of fully-sized skbs, to make sure the
+ * message gets out even in extreme OOM situations.
+ */
+
+#define MAX_UDP_CHUNK 1460
+#define MAX_SKBS 32
+
+static struct sk_buff_head skb_pool;
+
+DEFINE_STATIC_SRCU(netpoll_srcu);
+
+#define USEC_PER_POLL	50
+
+#define MAX_SKB_SIZE							\
+	(sizeof(struct ethhdr) +					\
+	 sizeof(struct iphdr) +						\
+	 sizeof(struct udphdr) +					\
+	 MAX_UDP_CHUNK)
+
+static void zap_completion_queue(void);
+static void netpoll_async_cleanup(struct work_struct *work);
+
+static unsigned int carrier_timeout = 4;
+module_param(carrier_timeout, uint, 0644);
+
+#define np_info(np, fmt, ...)				\
+	pr_info("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_err(np, fmt, ...)				\
+	pr_err("%s: " fmt, np->name, ##__VA_ARGS__)
+#define np_notice(np, fmt, ...)				\
+	pr_notice("%s: " fmt, np->name, ##__VA_ARGS__)
+
+static int netpoll_start_xmit(struct sk_buff *skb, struct net_device *dev,
+			      struct netdev_queue *txq)
+{
+	int status = NETDEV_TX_OK;
+	netdev_features_t features;
+
+	features = netif_skb_features(skb);
+
+	if (vlan_tx_tag_present(skb) &&
+	    !vlan_hw_offload_capable(features, skb->vlan_proto)) {
+		skb = __vlan_hwaccel_push_inside(skb);
+		if (unlikely(!skb)) {
+			/* This is actually a packet drop, but we
+			 * don't want the code that calls this
+			 * function to try and operate on a NULL skb.
+			 */
+			goto out;
+		}
+	}
+
+	status = netdev_start_xmit(skb, dev, txq, false);
+
+out:
+	return status;
+}
+
+static void queue_process(struct work_struct *work)
+{
+	struct netpoll_info *npinfo =
+		container_of(work, struct netpoll_info, tx_work.work);
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	while ((skb = skb_dequeue(&npinfo->txq))) {
+		struct net_device *dev = skb->dev;
+		struct netdev_queue *txq;
+
+		if (!netif_device_present(dev) || !netif_running(dev)) {
+			kfree_skb(skb);
+			continue;
+		}
+
+		txq = skb_get_tx_queue(dev, skb);
+
+		local_irq_save(flags);
+		HARD_TX_LOCK(dev, txq, smp_processor_id());
+		if (netif_xmit_frozen_or_stopped(txq) ||
+		    netpoll_start_xmit(skb, dev, txq) != NETDEV_TX_OK) {
+			skb_queue_head(&npinfo->txq, skb);
+			HARD_TX_UNLOCK(dev, txq);
+			local_irq_restore(flags);
+
+			schedule_delayed_work(&npinfo->tx_work, HZ/10);
+			return;
+		}
+		HARD_TX_UNLOCK(dev, txq);
+		local_irq_restore(flags);
+	}
+}
+
+/*
+ * Check whether delayed processing was scheduled for our NIC. If so,
+ * we attempt to grab the poll lock and use ->poll() to pump the card.
+ * If this fails, either we've recursed in ->poll() or it's already
+ * running on another CPU.
+ *
+ * Note: we don't mask interrupts with this lock because we're using
+ * trylock here and interrupts are already disabled in the softirq
+ * case. Further, we test the poll_owner to avoid recursion on UP
+ * systems where the lock doesn't exist.
+ */
+static int poll_one_napi(struct napi_struct *napi, int budget)
+{
+	int work;
+
+	/* net_rx_action's ->poll() invocations and our's are
+	 * synchronized by this test which is only made while
+	 * holding the napi->poll_lock.
+	 */
+	if (!test_bit(NAPI_STATE_SCHED, &napi->state))
+		return budget;
+
+	set_bit(NAPI_STATE_NPSVC, &napi->state);
+
+	work = napi->poll(napi, budget);
+	WARN_ONCE(work > budget, "%pF exceeded budget in poll\n", napi->poll);
+	trace_napi_poll(napi);
+
+	clear_bit(NAPI_STATE_NPSVC, &napi->state);
+
+	return budget - work;
+}
+
+static void poll_napi(struct net_device *dev, int budget)
+{
+	struct napi_struct *napi;
+
+	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		if (napi->poll_owner != smp_processor_id() &&
+		    spin_trylock(&napi->poll_lock)) {
+			budget = poll_one_napi(napi, budget);
+			spin_unlock(&napi->poll_lock);
+		}
+	}
+}
+
+static void netpoll_poll_dev(struct net_device *dev)
+{
+	const struct net_device_ops *ops;
+	struct netpoll_info *ni = rcu_dereference_bh(dev->npinfo);
+	int budget = 0;
+
+	/* Don't do any rx activity if the dev_lock mutex is held
+	 * the dev_open/close paths use this to block netpoll activity
+	 * while changing device state
+	 */
+	if (down_trylock(&ni->dev_lock))
+		return;
+
+	if (!netif_running(dev)) {
+		up(&ni->dev_lock);
+		return;
+	}
+
+	ops = dev->netdev_ops;
+	if (!ops->ndo_poll_controller) {
+		up(&ni->dev_lock);
+		return;
+	}
+
+	/* Process pending work on NIC */
+	ops->ndo_poll_controller(dev);
+
+	poll_napi(dev, budget);
+
+	up(&ni->dev_lock);
+
+	zap_completion_queue();
+}
+
+void netpoll_poll_disable(struct net_device *dev)
+{
+	struct netpoll_info *ni;
+	int idx;
+	might_sleep();
+	idx = srcu_read_lock(&netpoll_srcu);
+	ni = srcu_dereference(dev->npinfo, &netpoll_srcu);
+	if (ni)
+		down(&ni->dev_lock);
+	srcu_read_unlock(&netpoll_srcu, idx);
+}
+EXPORT_SYMBOL(netpoll_poll_disable);
+
+void netpoll_poll_enable(struct net_device *dev)
+{
+	struct netpoll_info *ni;
+	rcu_read_lock();
+	ni = rcu_dereference(dev->npinfo);
+	if (ni)
+		up(&ni->dev_lock);
+	rcu_read_unlock();
+}
+EXPORT_SYMBOL(netpoll_poll_enable);
+
+static void refill_skbs(void)
+{
+	struct sk_buff *skb;
+	unsigned long flags;
+
+	spin_lock_irqsave(&skb_pool.lock, flags);
+	while (skb_pool.qlen < MAX_SKBS) {
+		skb = alloc_skb(MAX_SKB_SIZE, GFP_ATOMIC);
+		if (!skb)
+			break;
+
+		__skb_queue_tail(&skb_pool, skb);
+	}
+	spin_unlock_irqrestore(&skb_pool.lock, flags);
+}
+
+static void zap_completion_queue(void)
+{
+	unsigned long flags;
+	struct softnet_data *sd = &get_cpu_var(softnet_data);
+
+	if (sd->completion_queue) {
+		struct sk_buff *clist;
+
+		local_irq_save(flags);
+		clist = sd->completion_queue;
+		sd->completion_queue = NULL;
+		local_irq_restore(flags);
+
+		while (clist != NULL) {
+			struct sk_buff *skb = clist;
+			clist = clist->next;
+			if (!skb_irq_freeable(skb)) {
+				atomic_inc(&skb->users);
+				dev_kfree_skb_any(skb); /* put this one back */
+			} else {
+				__kfree_skb(skb);
+			}
+		}
+	}
+
+	put_cpu_var(softnet_data);
+}
+
+static struct sk_buff *find_skb(struct netpoll *np, int len, int reserve)
+{
+	int count = 0;
+	struct sk_buff *skb;
+
+	zap_completion_queue();
+	refill_skbs();
+repeat:
+
+	skb = alloc_skb(len, GFP_ATOMIC);
+	if (!skb)
+		skb = skb_dequeue(&skb_pool);
+
+	if (!skb) {
+		if (++count < 10) {
+			netpoll_poll_dev(np->dev);
+			goto repeat;
+		}
+		return NULL;
+	}
+
+	atomic_set(&skb->users, 1);
+	skb_reserve(skb, reserve);
+	return skb;
+}
+
+static int netpoll_owner_active(struct net_device *dev)
+{
+	struct napi_struct *napi;
+
+	list_for_each_entry(napi, &dev->napi_list, dev_list) {
+		if (napi->poll_owner == smp_processor_id())
+			return 1;
+	}
+	return 0;
+}
+
+/* call with IRQ disabled */
+void netpoll_send_skb_on_dev(struct netpoll *np, struct sk_buff *skb,
+			     struct net_device *dev)
+{
+	int status = NETDEV_TX_BUSY;
+	unsigned long tries;
+	/* It is up to the caller to keep npinfo alive. */
+	struct netpoll_info *npinfo;
+
+	WARN_ON_ONCE(!irqs_disabled());
+
+	npinfo = rcu_dereference_bh(np->dev->npinfo);
+	if (!npinfo || !netif_running(dev) || !netif_device_present(dev)) {
+		dev_kfree_skb_irq(skb);
+		return;
+	}
+
+	/* don't get messages out of order, and no recursion */
+	if (skb_queue_len(&npinfo->txq) == 0 && !netpoll_owner_active(dev)) {
+		struct netdev_queue *txq;
+
+		txq = netdev_pick_tx(dev, skb, NULL);
+
+		/* try until next clock tick */
+		for (tries = jiffies_to_usecs(1)/USEC_PER_POLL;
+		     tries > 0; --tries) {
+			if (HARD_TX_TRYLOCK(dev, txq)) {
+				if (!netif_xmit_stopped(txq))
+					status = netpoll_start_xmit(skb, dev, txq);
+
+				HARD_TX_UNLOCK(dev, txq);
+
+				if (status == NETDEV_TX_OK)
+					break;
+
+			}
+
+			/* tickle device maybe there is some cleanup */
+			netpoll_poll_dev(np->dev);
+
+			udelay(USEC_PER_POLL);
+		}
+
+		WARN_ONCE(!irqs_disabled(),
+			"netpoll_send_skb_on_dev(): %s enabled interrupts in poll (%pF)\n",
+			dev->name, dev->netdev_ops->ndo_start_xmit);
+
+	}
+
+	if (status != NETDEV_TX_OK) {
+		skb_queue_tail(&npinfo->txq, skb);
+		schedule_delayed_work(&npinfo->tx_work,0);
+	}
+}
+EXPORT_SYMBOL(netpoll_send_skb_on_dev);
+
+void netpoll_send_udp(struct netpoll *np, const char *msg, int len)
+{
+	int total_len, ip_len, udp_len;
+	struct sk_buff *skb;
+	struct udphdr *udph;
+	struct iphdr *iph;
+	struct ethhdr *eth;
+	static atomic_t ip_ident;
+	struct ipv6hdr *ip6h;
+
+	udp_len = len + sizeof(*udph);
+	if (np->ipv6)
+		ip_len = udp_len + sizeof(*ip6h);
+	else
+		ip_len = udp_len + sizeof(*iph);
+
+	total_len = ip_len + LL_RESERVED_SPACE(np->dev);
+
+	skb = find_skb(np, total_len + np->dev->needed_tailroom,
+		       total_len - len);
+	if (!skb)
+		return;
+
+	skb_copy_to_linear_data(skb, msg, len);
+	skb_put(skb, len);
+
+	skb_push(skb, sizeof(*udph));
+	skb_reset_transport_header(skb);
+	udph = udp_hdr(skb);
+	udph->source = htons(np->local_port);
+	udph->dest = htons(np->remote_port);
+	udph->len = htons(udp_len);
+
+	if (np->ipv6) {
+		udph->check = 0;
+		udph->check = csum_ipv6_magic(&np->local_ip.in6,
+					      &np->remote_ip.in6,
+					      udp_len, IPPROTO_UDP,
+					      csum_partial(udph, udp_len, 0));
+		if (udph->check == 0)
+			udph->check = CSUM_MANGLED_0;
+
+		skb_push(skb, sizeof(*ip6h));
+		skb_reset_network_header(skb);
+		ip6h = ipv6_hdr(skb);
+
+		/* ip6h->version = 6; ip6h->priority = 0; */
+		put_unaligned(0x60, (unsigned char *)ip6h);
+		ip6h->flow_lbl[0] = 0;
+		ip6h->flow_lbl[1] = 0;
+		ip6h->flow_lbl[2] = 0;
+
+		ip6h->payload_len = htons(sizeof(struct udphdr) + len);
+		ip6h->nexthdr = IPPROTO_UDP;
+		ip6h->hop_limit = 32;
+		ip6h->saddr = np->local_ip.in6;
+		ip6h->daddr = np->remote_ip.in6;
+
+		eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
+		skb_reset_mac_header(skb);
+		skb->protocol = eth->h_proto = htons(ETH_P_IPV6);
+	} else {
+		udph->check = 0;
+		udph->check = csum_tcpudp_magic(np->local_ip.ip,
+						np->remote_ip.ip,
+						udp_len, IPPROTO_UDP,
+						csum_partial(udph, udp_len, 0));
+		if (udph->check == 0)
+			udph->check = CSUM_MANGLED_0;
+
+		skb_push(skb, sizeof(*iph));
+		skb_reset_network_header(skb);
+		iph = ip_hdr(skb);
+
+		/* iph->version = 4; iph->ihl = 5; */
+		put_unaligned(0x45, (unsigned char *)iph);
+		iph->tos      = 0;
+		put_unaligned(htons(ip_len), &(iph->tot_len));
+		iph->id       = htons(atomic_inc_return(&ip_ident));
+		iph->frag_off = 0;
+		iph->ttl      = 64;
+		iph->protocol = IPPROTO_UDP;
+		iph->check    = 0;
+		put_unaligned(np->local_ip.ip, &(iph->saddr));
+		put_unaligned(np->remote_ip.ip, &(iph->daddr));
+		iph->check    = ip_fast_csum((unsigned char *)iph, iph->ihl);
+
+		eth = (struct ethhdr *) skb_push(skb, ETH_HLEN);
+		skb_reset_mac_header(skb);
+		skb->protocol = eth->h_proto = htons(ETH_P_IP);
+	}
+
+	ether_addr_copy(eth->h_source, np->dev->dev_addr);
+	ether_addr_copy(eth->h_dest, np->remote_mac);
+
+	skb->dev = np->dev;
+
+	netpoll_send_skb(np, skb);
+}
+EXPORT_SYMBOL(netpoll_send_udp);
+
+void netpoll_print_options(struct netpoll *np)
+{
+	np_info(np, "local port %d\n", np->local_port);
+	if (np->ipv6)
+		np_info(np, "local IPv6 address %pI6c\n", &np->local_ip.in6);
+	else
+		np_info(np, "local IPv4 address %pI4\n", &np->local_ip.ip);
+	np_info(np, "interface '%s'\n", np->dev_name);
+	np_info(np, "remote port %d\n", np->remote_port);
+	if (np->ipv6)
+		np_info(np, "remote IPv6 address %pI6c\n", &np->remote_ip.in6);
+	else
+		np_info(np, "remote IPv4 address %pI4\n", &np->remote_ip.ip);
+	np_info(np, "remote ethernet address %pM\n", np->remote_mac);
+}
+EXPORT_SYMBOL(netpoll_print_options);
+
+static int netpoll_parse_ip_addr(const char *str, union inet_addr *addr)
+{
+	const char *end;
+
+	if (!strchr(str, ':') &&
+	    in4_pton(str, -1, (void *)addr, -1, &end) > 0) {
+		if (!*end)
+			return 0;
+	}
+	if (in6_pton(str, -1, addr->in6.s6_addr, -1, &end) > 0) {
+#if IS_ENABLED(CONFIG_IPV6)
+		if (!*end)
+			return 1;
+#else
+		return -1;
+#endif
+	}
+	return -1;
+}
+
+int netpoll_parse_options(struct netpoll *np, char *opt)
+{
+	char *cur=opt, *delim;
+	int ipv6;
+	bool ipversion_set = false;
+
+	if (*cur != '@') {
+		if ((delim = strchr(cur, '@')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+		if (kstrtou16(cur, 10, &np->local_port))
+			goto parse_failed;
+		cur = delim;
+	}
+	cur++;
+
+	if (*cur != '/') {
+		ipversion_set = true;
+		if ((delim = strchr(cur, '/')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+		ipv6 = netpoll_parse_ip_addr(cur, &np->local_ip);
+		if (ipv6 < 0)
+			goto parse_failed;
+		else
+			np->ipv6 = (bool)ipv6;
+		cur = delim;
+	}
+	cur++;
+
+	if (*cur != ',') {
+		/* parse out dev name */
+		if ((delim = strchr(cur, ',')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+		strlcpy(np->dev_name, cur, sizeof(np->dev_name));
+		cur = delim;
+	}
+	cur++;
+
+	if (*cur != '@') {
+		/* dst port */
+		if ((delim = strchr(cur, '@')) == NULL)
+			goto parse_failed;
+		*delim = 0;
+		if (*cur == ' ' || *cur == '\t')
+			np_info(np, "warning: whitespace is not allowed\n");
+		if (kstrtou16(cur, 10, &np->remote_port))
+			goto parse_failed;
+		cur = delim;
+	}
+	cur++;
+
+	/* dst ip */
+	if ((delim = strchr(cur, '/')) == NULL)
+		goto parse_failed;
+	*delim = 0;
+	ipv6 = netpoll_parse_ip_addr(cur, &np->remote_ip);
+	if (ipv6 < 0)
+		goto parse_failed;
+	else if (ipversion_set && np->ipv6 != (bool)ipv6)
+		goto parse_failed;
+	else
+		np->ipv6 = (bool)ipv6;
+	cur = delim + 1;
+
+	if (*cur != 0) {
+		/* MAC address */
+		if (!mac_pton(cur, np->remote_mac))
+			goto parse_failed;
+	}
+
+	netpoll_print_options(np);
+
+	return 0;
+
+ parse_failed:
+	np_info(np, "couldn't parse config at '%s'!\n", cur);
+	return -1;
+}
+EXPORT_SYMBOL(netpoll_parse_options);
+
+int __netpoll_setup(struct netpoll *np, struct net_device *ndev)
+{
+	struct netpoll_info *npinfo;
+	const struct net_device_ops *ops;
+	int err;
+
+	np->dev = ndev;
+	strlcpy(np->dev_name, ndev->name, IFNAMSIZ);
+	INIT_WORK(&np->cleanup_work, netpoll_async_cleanup);
+
+	if ((ndev->priv_flags & IFF_DISABLE_NETPOLL) ||
+	    !ndev->netdev_ops->ndo_poll_controller) {
+		np_err(np, "%s doesn't support polling, aborting\n",
+		       np->dev_name);
+		err = -ENOTSUPP;
+		goto out;
+	}
+
+	if (!ndev->npinfo) {
+		npinfo = kmalloc(sizeof(*npinfo), GFP_KERNEL);
+		if (!npinfo) {
+			err = -ENOMEM;
+			goto out;
+		}
+
+		sema_init(&npinfo->dev_lock, 1);
+		skb_queue_head_init(&npinfo->txq);
+		INIT_DELAYED_WORK(&npinfo->tx_work, queue_process);
+
+		atomic_set(&npinfo->refcnt, 1);
+
+		ops = np->dev->netdev_ops;
+		if (ops->ndo_netpoll_setup) {
+			err = ops->ndo_netpoll_setup(ndev, npinfo);
+			if (err)
+				goto free_npinfo;
+		}
+	} else {
+		npinfo = rtnl_dereference(ndev->npinfo);
+		atomic_inc(&npinfo->refcnt);
+	}
+
+	npinfo->netpoll = np;
+
+	/* last thing to do is link it to the net device structure */
+	rcu_assign_pointer(ndev->npinfo, npinfo);
+
+	return 0;
+
+free_npinfo:
+	kfree(npinfo);
+out:
+	return err;
+}
+EXPORT_SYMBOL_GPL(__netpoll_setup);
+
+int netpoll_setup(struct netpoll *np)
+{
+	struct net_device *ndev = NULL;
+	struct in_device *in_dev;
+	int err;
+
+	rtnl_lock();
+	if (np->dev_name) {
+		struct net *net = current->nsproxy->net_ns;
+		ndev = __dev_get_by_name(net, np->dev_name);
+	}
+	if (!ndev) {
+		np_err(np, "%s doesn't exist, aborting\n", np->dev_name);
+		err = -ENODEV;
+		goto unlock;
+	}
+	dev_hold(ndev);
+
+	if (netdev_master_upper_dev_get(ndev)) {
+		np_err(np, "%s is a slave device, aborting\n", np->dev_name);
+		err = -EBUSY;
+		goto put;
+	}
+
+	if (!netif_running(ndev)) {
+		unsigned long atmost, atleast;
+
+		np_info(np, "device %s not up yet, forcing it\n", np->dev_name);
+
+		err = dev_open(ndev);
+
+		if (err) {
+			np_err(np, "failed to open %s\n", ndev->name);
+			goto put;
+		}
+
+		rtnl_unlock();
+		atleast = jiffies + HZ/10;
+		atmost = jiffies + carrier_timeout * HZ;
+		while (!netif_carrier_ok(ndev)) {
+			if (time_after(jiffies, atmost)) {
+				np_notice(np, "timeout waiting for carrier\n");
+				break;
+			}
+			msleep(1);
+		}
+
+		/* If carrier appears to come up instantly, we don't
+		 * trust it and pause so that we don't pump all our
+		 * queued console messages into the bitbucket.
+		 */
+
+		if (time_before(jiffies, atleast)) {
+			np_notice(np, "carrier detect appears untrustworthy, waiting 4 seconds\n");
+			msleep(4000);
+		}
+		rtnl_lock();
+	}
+
+	if (!np->local_ip.ip) {
+		if (!np->ipv6) {
+			in_dev = __in_dev_get_rtnl(ndev);
+
+			if (!in_dev || !in_dev->ifa_list) {
+				np_err(np, "no IP address for %s, aborting\n",
+				       np->dev_name);
+				err = -EDESTADDRREQ;
+				goto put;
+			}
+
+			np->local_ip.ip = in_dev->ifa_list->ifa_local;
+			np_info(np, "local IP %pI4\n", &np->local_ip.ip);
+		} else {
+#if IS_ENABLED(CONFIG_IPV6)
+			struct inet6_dev *idev;
+
+			err = -EDESTADDRREQ;
+			idev = __in6_dev_get(ndev);
+			if (idev) {
+				struct inet6_ifaddr *ifp;
+
+				read_lock_bh(&idev->lock);
+				list_for_each_entry(ifp, &idev->addr_list, if_list) {
+					if (ipv6_addr_type(&ifp->addr) & IPV6_ADDR_LINKLOCAL)
+						continue;
+					np->local_ip.in6 = ifp->addr;
+					err = 0;
+					break;
+				}
+				read_unlock_bh(&idev->lock);
+			}
+			if (err) {
+				np_err(np, "no IPv6 address for %s, aborting\n",
+				       np->dev_name);
+				goto put;
+			} else
+				np_info(np, "local IPv6 %pI6c\n", &np->local_ip.in6);
+#else
+			np_err(np, "IPv6 is not supported %s, aborting\n",
+			       np->dev_name);
+			err = -EINVAL;
+			goto put;
+#endif
+		}
+	}
+
+	/* fill up the skb queue */
+	refill_skbs();
+
+	err = __netpoll_setup(np, ndev);
+	if (err)
+		goto put;
+
+	rtnl_unlock();
+	return 0;
+
+put:
+	dev_put(ndev);
+unlock:
+	rtnl_unlock();
+	return err;
+}
+EXPORT_SYMBOL(netpoll_setup);
+
+static int __init netpoll_init(void)
+{
+	skb_queue_head_init(&skb_pool);
+	return 0;
+}
+core_initcall(netpoll_init);
+
+static void rcu_cleanup_netpoll_info(struct rcu_head *rcu_head)
+{
+	struct netpoll_info *npinfo =
+			container_of(rcu_head, struct netpoll_info, rcu);
+
+	skb_queue_purge(&npinfo->txq);
+
+	/* we can't call cancel_delayed_work_sync here, as we are in softirq */
+	cancel_delayed_work(&npinfo->tx_work);
+
+	/* clean after last, unfinished work */
+	__skb_queue_purge(&npinfo->txq);
+	/* now cancel it again */
+	cancel_delayed_work(&npinfo->tx_work);
+	kfree(npinfo);
+}
+
+void __netpoll_cleanup(struct netpoll *np)
+{
+	struct netpoll_info *npinfo;
+
+	/* rtnl_dereference would be preferable here but
+	 * rcu_cleanup_netpoll path can put us in here safely without
+	 * holding the rtnl, so plain rcu_dereference it is
+	 */
+	npinfo = rtnl_dereference(np->dev->npinfo);
+	if (!npinfo)
+		return;
+
+	synchronize_srcu(&netpoll_srcu);
+
+	if (atomic_dec_and_test(&npinfo->refcnt)) {
+		const struct net_device_ops *ops;
+
+		ops = np->dev->netdev_ops;
+		if (ops->ndo_netpoll_cleanup)
+			ops->ndo_netpoll_cleanup(np->dev);
+
+		RCU_INIT_POINTER(np->dev->npinfo, NULL);
+		call_rcu_bh(&npinfo->rcu, rcu_cleanup_netpoll_info);
+	} else
+		RCU_INIT_POINTER(np->dev->npinfo, NULL);
+}
+EXPORT_SYMBOL_GPL(__netpoll_cleanup);
+
+static void netpoll_async_cleanup(struct work_struct *work)
+{
+	struct netpoll *np = container_of(work, struct netpoll, cleanup_work);
+
+	rtnl_lock();
+	__netpoll_cleanup(np);
+	rtnl_unlock();
+	kfree(np);
+}
+
+void __netpoll_free_async(struct netpoll *np)
+{
+	schedule_work(&np->cleanup_work);
+}
+EXPORT_SYMBOL_GPL(__netpoll_free_async);
+
+void netpoll_cleanup(struct netpoll *np)
+{
+	rtnl_lock();
+	if (!np->dev)
+		goto out;
+	__netpoll_cleanup(np);
+	dev_put(np->dev);
+	np->dev = NULL;
+out:
+	rtnl_unlock();
+}
+EXPORT_SYMBOL(netpoll_cleanup);

net/core/netprio_cgroup.c

@@ -0,0 +1,288 @@
+/*
+ * net/core/netprio_cgroup.c	Priority Control Group
+ *
+ *		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; either version
+ *		2 of the License, or (at your option) any later version.
+ *
+ * Authors:	Neil Horman <nhorman@tuxdriver.com>
+ */
+
+#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt
+
+#include <linux/module.h>
+#include <linux/slab.h>
+#include <linux/types.h>
+#include <linux/string.h>
+#include <linux/errno.h>
+#include <linux/skbuff.h>
+#include <linux/cgroup.h>
+#include <linux/rcupdate.h>
+#include <linux/atomic.h>
+#include <net/rtnetlink.h>
+#include <net/pkt_cls.h>
+#include <net/sock.h>
+#include <net/netprio_cgroup.h>
+
+#include <linux/fdtable.h>
+
+#define PRIOMAP_MIN_SZ		128
+
+/*
+ * Extend @dev->priomap so that it's large enough to accommodate
+ * @target_idx.  @dev->priomap.priomap_len > @target_idx after successful
+ * return.  Must be called under rtnl lock.
+ */
+static int extend_netdev_table(struct net_device *dev, u32 target_idx)
+{
+	struct netprio_map *old, *new;
+	size_t new_sz, new_len;
+
+	/* is the existing priomap large enough? */
+	old = rtnl_dereference(dev->priomap);
+	if (old && old->priomap_len > target_idx)
+		return 0;
+
+	/*
+	 * Determine the new size.  Let's keep it power-of-two.  We start
+	 * from PRIOMAP_MIN_SZ and double it until it's large enough to
+	 * accommodate @target_idx.
+	 */
+	new_sz = PRIOMAP_MIN_SZ;
+	while (true) {
+		new_len = (new_sz - offsetof(struct netprio_map, priomap)) /
+			sizeof(new->priomap[0]);
+		if (new_len > target_idx)
+			break;
+		new_sz *= 2;
+		/* overflowed? */
+		if (WARN_ON(new_sz < PRIOMAP_MIN_SZ))
+			return -ENOSPC;
+	}
+
+	/* allocate & copy */
+	new = kzalloc(new_sz, GFP_KERNEL);
+	if (!new)
+		return -ENOMEM;
+
+	if (old)
+		memcpy(new->priomap, old->priomap,
+		       old->priomap_len * sizeof(old->priomap[0]));
+
+	new->priomap_len = new_len;
+
+	/* install the new priomap */
+	rcu_assign_pointer(dev->priomap, new);
+	if (old)
+		kfree_rcu(old, rcu);
+	return 0;
+}
+
+/**
+ * netprio_prio - return the effective netprio of a cgroup-net_device pair
+ * @css: css part of the target pair
+ * @dev: net_device part of the target pair
+ *
+ * Should be called under RCU read or rtnl lock.
+ */
+static u32 netprio_prio(struct cgroup_subsys_state *css, struct net_device *dev)
+{
+	struct netprio_map *map = rcu_dereference_rtnl(dev->priomap);
+	int id = css->cgroup->id;
+
+	if (map && id < map->priomap_len)
+		return map->priomap[id];
+	return 0;
+}
+
+/**
+ * netprio_set_prio - set netprio on a cgroup-net_device pair
+ * @css: css part of the target pair
+ * @dev: net_device part of the target pair
+ * @prio: prio to set
+ *
+ * Set netprio to @prio on @css-@dev pair.  Should be called under rtnl
+ * lock and may fail under memory pressure for non-zero @prio.
+ */
+static int netprio_set_prio(struct cgroup_subsys_state *css,
+			    struct net_device *dev, u32 prio)
+{
+	struct netprio_map *map;
+	int id = css->cgroup->id;
+	int ret;
+
+	/* avoid extending priomap for zero writes */
+	map = rtnl_dereference(dev->priomap);
+	if (!prio && (!map || map->priomap_len <= id))
+		return 0;
+
+	ret = extend_netdev_table(dev, id);
+	if (ret)
+		return ret;
+
+	map = rtnl_dereference(dev->priomap);
+	map->priomap[id] = prio;
+	return 0;
+}
+
+static struct cgroup_subsys_state *
+cgrp_css_alloc(struct cgroup_subsys_state *parent_css)
+{
+	struct cgroup_subsys_state *css;
+
+	css = kzalloc(sizeof(*css), GFP_KERNEL);
+	if (!css)
+		return ERR_PTR(-ENOMEM);
+
+	return css;
+}
+
+static int cgrp_css_online(struct cgroup_subsys_state *css)
+{
+	struct cgroup_subsys_state *parent_css = css->parent;
+	struct net_device *dev;
+	int ret = 0;
+
+	if (!parent_css)
+		return 0;
+
+	rtnl_lock();
+	/*
+	 * Inherit prios from the parent.  As all prios are set during
+	 * onlining, there is no need to clear them on offline.
+	 */
+	for_each_netdev(&init_net, dev) {
+		u32 prio = netprio_prio(parent_css, dev);
+
+		ret = netprio_set_prio(css, dev, prio);
+		if (ret)
+			break;
+	}
+	rtnl_unlock();
+	return ret;
+}
+
+static void cgrp_css_free(struct cgroup_subsys_state *css)
+{
+	kfree(css);
+}
+
+static u64 read_prioidx(struct cgroup_subsys_state *css, struct cftype *cft)
+{
+	return css->cgroup->id;
+}
+
+static int read_priomap(struct seq_file *sf, void *v)
+{
+	struct net_device *dev;
+
+	rcu_read_lock();
+	for_each_netdev_rcu(&init_net, dev)
+		seq_printf(sf, "%s %u\n", dev->name,
+			   netprio_prio(seq_css(sf), dev));
+	rcu_read_unlock();
+	return 0;
+}
+
+static ssize_t write_priomap(struct kernfs_open_file *of,
+			     char *buf, size_t nbytes, loff_t off)
+{
+	char devname[IFNAMSIZ + 1];
+	struct net_device *dev;
+	u32 prio;
+	int ret;
+
+	if (sscanf(buf, "%"__stringify(IFNAMSIZ)"s %u", devname, &prio) != 2)
+		return -EINVAL;
+
+	dev = dev_get_by_name(&init_net, devname);
+	if (!dev)
+		return -ENODEV;
+
+	rtnl_lock();
+
+	ret = netprio_set_prio(of_css(of), dev, prio);
+
+	rtnl_unlock();
+	dev_put(dev);
+	return ret ?: nbytes;
+}
+
+static int update_netprio(const void *v, struct file *file, unsigned n)
+{
+	int err;
+	struct socket *sock = sock_from_file(file, &err);
+	if (sock)
+		sock->sk->sk_cgrp_prioidx = (u32)(unsigned long)v;
+	return 0;
+}
+
+static void net_prio_attach(struct cgroup_subsys_state *css,
+			    struct cgroup_taskset *tset)
+{
+	struct task_struct *p;
+	void *v = (void *)(unsigned long)css->cgroup->id;
+
+	cgroup_taskset_for_each(p, tset) {
+		task_lock(p);
+		iterate_fd(p->files, 0, update_netprio, v);
+		task_unlock(p);
+	}
+}
+
+static struct cftype ss_files[] = {
+	{
+		.name = "prioidx",
+		.read_u64 = read_prioidx,
+	},
+	{
+		.name = "ifpriomap",
+		.seq_show = read_priomap,
+		.write = write_priomap,
+	},
+	{ }	/* terminate */
+};
+
+struct cgroup_subsys net_prio_cgrp_subsys = {
+	.css_alloc	= cgrp_css_alloc,
+	.css_online	= cgrp_css_online,
+	.css_free	= cgrp_css_free,
+	.attach		= net_prio_attach,
+	.legacy_cftypes	= ss_files,
+};
+
+static int netprio_device_event(struct notifier_block *unused,
+				unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+	struct netprio_map *old;
+
+	/*
+	 * Note this is called with rtnl_lock held so we have update side
+	 * protection on our rcu assignments
+	 */
+
+	switch (event) {
+	case NETDEV_UNREGISTER:
+		old = rtnl_dereference(dev->priomap);
+		RCU_INIT_POINTER(dev->priomap, NULL);
+		if (old)
+			kfree_rcu(old, rcu);
+		break;
+	}
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block netprio_device_notifier = {
+	.notifier_call = netprio_device_event
+};
+
+static int __init init_cgroup_netprio(void)
+{
+	register_netdevice_notifier(&netprio_device_notifier);
+	return 0;
+}
+
+subsys_initcall(init_cgroup_netprio);
+MODULE_LICENSE("GPL v2");

net/core/ptp_classifier.c

@@ -0,0 +1,193 @@
+/* PTP classifier
+ *
+ * This program is free software; you can redistribute it and/or
+ * modify it under the terms of version 2 of the GNU General Public
+ * License as published by the Free Software Foundation.
+ *
+ * This program is distributed in the hope that it will be useful, but
+ * WITHOUT ANY WARRANTY; without even the implied warranty of
+ * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU
+ * General Public License for more details.
+ */
+
+/* The below program is the bpf_asm (tools/net/) representation of
+ * the opcode array in the ptp_filter structure.
+ *
+ * For convenience, this can easily be altered and reviewed with
+ * bpf_asm and bpf_dbg, e.g. `./bpf_asm -c prog` where prog is a
+ * simple file containing the below program:
+ *
+ * ldh [12]                        ; load ethertype
+ *
+ * ; PTP over UDP over IPv4 over Ethernet
+ * test_ipv4:
+ *   jneq #0x800, test_ipv6        ; ETH_P_IP ?
+ *   ldb [23]                      ; load proto
+ *   jneq #17, drop_ipv4           ; IPPROTO_UDP ?
+ *   ldh [20]                      ; load frag offset field
+ *   jset #0x1fff, drop_ipv4       ; don't allow fragments
+ *   ldxb 4*([14]&0xf)             ; load IP header len
+ *   ldh [x + 16]                  ; load UDP dst port
+ *   jneq #319, drop_ipv4          ; is port PTP_EV_PORT ?
+ *   ldh [x + 22]                  ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x10                      ; PTP_CLASS_IPV4
+ *   ret a                         ; return PTP class
+ *   drop_ipv4: ret #0x0           ; PTP_CLASS_NONE
+ *
+ * ; PTP over UDP over IPv6 over Ethernet
+ * test_ipv6:
+ *   jneq #0x86dd, test_8021q      ; ETH_P_IPV6 ?
+ *   ldb [20]                      ; load proto
+ *   jneq #17, drop_ipv6           ; IPPROTO_UDP ?
+ *   ldh [56]                      ; load UDP dst port
+ *   jneq #319, drop_ipv6          ; is port PTP_EV_PORT ?
+ *   ldh [62]                      ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x20                      ; PTP_CLASS_IPV6
+ *   ret a                         ; return PTP class
+ *   drop_ipv6: ret #0x0           ; PTP_CLASS_NONE
+ *
+ * ; PTP over 802.1Q over Ethernet
+ * test_8021q:
+ *   jneq #0x8100, test_ieee1588   ; ETH_P_8021Q ?
+ *   ldh [16]                      ; load inner type
+ *   jneq #0x88f7, test_8021q_ipv4 ; ETH_P_1588 ?
+ *   ldb [18]                      ; load payload
+ *   and #0x8                      ; as we don't have ports here, test
+ *   jneq #0x0, drop_ieee1588      ; for PTP_GEN_BIT and drop these
+ *   ldh [18]                      ; reload payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x70                      ; PTP_CLASS_VLAN|PTP_CLASS_L2
+ *   ret a                         ; return PTP class
+ *
+ * ; PTP over UDP over IPv4 over 802.1Q over Ethernet
+ * test_8021q_ipv4:
+ *   jneq #0x800, test_8021q_ipv6  ; ETH_P_IP ?
+ *   ldb [27]                      ; load proto
+ *   jneq #17, drop_8021q_ipv4     ; IPPROTO_UDP ?
+ *   ldh [24]                      ; load frag offset field
+ *   jset #0x1fff, drop_8021q_ipv4; don't allow fragments
+ *   ldxb 4*([18]&0xf)             ; load IP header len
+ *   ldh [x + 20]                  ; load UDP dst port
+ *   jneq #319, drop_8021q_ipv4    ; is port PTP_EV_PORT ?
+ *   ldh [x + 26]                  ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x50                      ; PTP_CLASS_VLAN|PTP_CLASS_IPV4
+ *   ret a                         ; return PTP class
+ *   drop_8021q_ipv4: ret #0x0     ; PTP_CLASS_NONE
+ *
+ * ; PTP over UDP over IPv6 over 802.1Q over Ethernet
+ * test_8021q_ipv6:
+ *   jneq #0x86dd, drop_8021q_ipv6 ; ETH_P_IPV6 ?
+ *   ldb [24]                      ; load proto
+ *   jneq #17, drop_8021q_ipv6           ; IPPROTO_UDP ?
+ *   ldh [60]                      ; load UDP dst port
+ *   jneq #319, drop_8021q_ipv6          ; is port PTP_EV_PORT ?
+ *   ldh [66]                      ; load payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x60                      ; PTP_CLASS_VLAN|PTP_CLASS_IPV6
+ *   ret a                         ; return PTP class
+ *   drop_8021q_ipv6: ret #0x0     ; PTP_CLASS_NONE
+ *
+ * ; PTP over Ethernet
+ * test_ieee1588:
+ *   jneq #0x88f7, drop_ieee1588   ; ETH_P_1588 ?
+ *   ldb [14]                      ; load payload
+ *   and #0x8                      ; as we don't have ports here, test
+ *   jneq #0x0, drop_ieee1588      ; for PTP_GEN_BIT and drop these
+ *   ldh [14]                      ; reload payload
+ *   and #0xf                      ; mask PTP_CLASS_VMASK
+ *   or #0x30                      ; PTP_CLASS_L2
+ *   ret a                         ; return PTP class
+ *   drop_ieee1588: ret #0x0       ; PTP_CLASS_NONE
+ */
+
+#include <linux/skbuff.h>
+#include <linux/filter.h>
+#include <linux/ptp_classify.h>
+
+static struct bpf_prog *ptp_insns __read_mostly;
+
+unsigned int ptp_classify_raw(const struct sk_buff *skb)
+{
+	return BPF_PROG_RUN(ptp_insns, skb);
+}
+EXPORT_SYMBOL_GPL(ptp_classify_raw);
+
+void __init ptp_classifier_init(void)
+{
+	static struct sock_filter ptp_filter[] __initdata = {
+		{ 0x28,  0,  0, 0x0000000c },
+		{ 0x15,  0, 12, 0x00000800 },
+		{ 0x30,  0,  0, 0x00000017 },
+		{ 0x15,  0,  9, 0x00000011 },
+		{ 0x28,  0,  0, 0x00000014 },
+		{ 0x45,  7,  0, 0x00001fff },
+		{ 0xb1,  0,  0, 0x0000000e },
+		{ 0x48,  0,  0, 0x00000010 },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x48,  0,  0, 0x00000016 },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000010 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0,  9, 0x000086dd },
+		{ 0x30,  0,  0, 0x00000014 },
+		{ 0x15,  0,  6, 0x00000011 },
+		{ 0x28,  0,  0, 0x00000038 },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x28,  0,  0, 0x0000003e },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000020 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0, 32, 0x00008100 },
+		{ 0x28,  0,  0, 0x00000010 },
+		{ 0x15,  0,  7, 0x000088f7 },
+		{ 0x30,  0,  0, 0x00000012 },
+		{ 0x54,  0,  0, 0x00000008 },
+		{ 0x15,  0, 35, 0x00000000 },
+		{ 0x28,  0,  0, 0x00000012 },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000070 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x15,  0, 12, 0x00000800 },
+		{ 0x30,  0,  0, 0x0000001b },
+		{ 0x15,  0,  9, 0x00000011 },
+		{ 0x28,  0,  0, 0x00000018 },
+		{ 0x45,  7,  0, 0x00001fff },
+		{ 0xb1,  0,  0, 0x00000012 },
+		{ 0x48,  0,  0, 0x00000014 },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x48,  0,  0, 0x0000001a },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000050 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0,  8, 0x000086dd },
+		{ 0x30,  0,  0, 0x00000018 },
+		{ 0x15,  0,  6, 0x00000011 },
+		{ 0x28,  0,  0, 0x0000003c },
+		{ 0x15,  0,  4, 0x0000013f },
+		{ 0x28,  0,  0, 0x00000042 },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000060 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+		{ 0x15,  0,  7, 0x000088f7 },
+		{ 0x30,  0,  0, 0x0000000e },
+		{ 0x54,  0,  0, 0x00000008 },
+		{ 0x15,  0,  4, 0x00000000 },
+		{ 0x28,  0,  0, 0x0000000e },
+		{ 0x54,  0,  0, 0x0000000f },
+		{ 0x44,  0,  0, 0x00000030 },
+		{ 0x16,  0,  0, 0x00000000 },
+		{ 0x06,  0,  0, 0x00000000 },
+	};
+	struct sock_fprog_kern ptp_prog = {
+		.len = ARRAY_SIZE(ptp_filter), .filter = ptp_filter,
+	};
+
+	BUG_ON(bpf_prog_create(&ptp_insns, &ptp_prog));
+}

net/core/request_sock.c

@@ -0,0 +1,205 @@
+/*
+ * NET		Generic infrastructure for Network protocols.
+ *
+ * Authors:	Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *
+ * 		From code originally in include/net/tcp.h
+ *
+ *		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; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/random.h>
+#include <linux/slab.h>
+#include <linux/string.h>
+#include <linux/tcp.h>
+#include <linux/vmalloc.h>
+
+#include <net/request_sock.h>
+
+/*
+ * Maximum number of SYN_RECV sockets in queue per LISTEN socket.
+ * One SYN_RECV socket costs about 80bytes on a 32bit machine.
+ * It would be better to replace it with a global counter for all sockets
+ * but then some measure against one socket starving all other sockets
+ * would be needed.
+ *
+ * The minimum value of it is 128. Experiments with real servers show that
+ * it is absolutely not enough even at 100conn/sec. 256 cures most
+ * of problems.
+ * This value is adjusted to 128 for low memory machines,
+ * and it will increase in proportion to the memory of machine.
+ * Note : Dont forget somaxconn that may limit backlog too.
+ */
+int sysctl_max_syn_backlog = 256;
+EXPORT_SYMBOL(sysctl_max_syn_backlog);
+
+int reqsk_queue_alloc(struct request_sock_queue *queue,
+		      unsigned int nr_table_entries)
+{
+	size_t lopt_size = sizeof(struct listen_sock);
+	struct listen_sock *lopt = NULL;
+
+	nr_table_entries = min_t(u32, nr_table_entries, sysctl_max_syn_backlog);
+	nr_table_entries = max_t(u32, nr_table_entries, 8);
+	nr_table_entries = roundup_pow_of_two(nr_table_entries + 1);
+	lopt_size += nr_table_entries * sizeof(struct request_sock *);
+
+	if (lopt_size <= (PAGE_SIZE << PAGE_ALLOC_COSTLY_ORDER))
+		lopt = kzalloc(lopt_size, GFP_KERNEL |
+					  __GFP_NOWARN |
+					  __GFP_NORETRY);
+	if (!lopt)
+		lopt = vzalloc(lopt_size);
+	if (!lopt)
+		return -ENOMEM;
+
+	get_random_bytes(&lopt->hash_rnd, sizeof(lopt->hash_rnd));
+	rwlock_init(&queue->syn_wait_lock);
+	queue->rskq_accept_head = NULL;
+	lopt->nr_table_entries = nr_table_entries;
+	lopt->max_qlen_log = ilog2(nr_table_entries);
+
+	write_lock_bh(&queue->syn_wait_lock);
+	queue->listen_opt = lopt;
+	write_unlock_bh(&queue->syn_wait_lock);
+
+	return 0;
+}
+
+void __reqsk_queue_destroy(struct request_sock_queue *queue)
+{
+	/* This is an error recovery path only, no locking needed */
+	kvfree(queue->listen_opt);
+}
+
+static inline struct listen_sock *reqsk_queue_yank_listen_sk(
+		struct request_sock_queue *queue)
+{
+	struct listen_sock *lopt;
+
+	write_lock_bh(&queue->syn_wait_lock);
+	lopt = queue->listen_opt;
+	queue->listen_opt = NULL;
+	write_unlock_bh(&queue->syn_wait_lock);
+
+	return lopt;
+}
+
+void reqsk_queue_destroy(struct request_sock_queue *queue)
+{
+	/* make all the listen_opt local to us */
+	struct listen_sock *lopt = reqsk_queue_yank_listen_sk(queue);
+
+	if (lopt->qlen != 0) {
+		unsigned int i;
+
+		for (i = 0; i < lopt->nr_table_entries; i++) {
+			struct request_sock *req;
+
+			while ((req = lopt->syn_table[i]) != NULL) {
+				lopt->syn_table[i] = req->dl_next;
+				lopt->qlen--;
+				reqsk_free(req);
+			}
+		}
+	}
+
+	WARN_ON(lopt->qlen != 0);
+	kvfree(lopt);
+}
+
+/*
+ * This function is called to set a Fast Open socket's "fastopen_rsk" field
+ * to NULL when a TFO socket no longer needs to access the request_sock.
+ * This happens only after 3WHS has been either completed or aborted (e.g.,
+ * RST is received).
+ *
+ * Before TFO, a child socket is created only after 3WHS is completed,
+ * hence it never needs to access the request_sock. things get a lot more
+ * complex with TFO. A child socket, accepted or not, has to access its
+ * request_sock for 3WHS processing, e.g., to retransmit SYN-ACK pkts,
+ * until 3WHS is either completed or aborted. Afterwards the req will stay
+ * until either the child socket is accepted, or in the rare case when the
+ * listener is closed before the child is accepted.
+ *
+ * In short, a request socket is only freed after BOTH 3WHS has completed
+ * (or aborted) and the child socket has been accepted (or listener closed).
+ * When a child socket is accepted, its corresponding req->sk is set to
+ * NULL since it's no longer needed. More importantly, "req->sk == NULL"
+ * will be used by the code below to determine if a child socket has been
+ * accepted or not, and the check is protected by the fastopenq->lock
+ * described below.
+ *
+ * Note that fastopen_rsk is only accessed from the child socket's context
+ * with its socket lock held. But a request_sock (req) can be accessed by
+ * both its child socket through fastopen_rsk, and a listener socket through
+ * icsk_accept_queue.rskq_accept_head. To protect the access a simple spin
+ * lock per listener "icsk->icsk_accept_queue.fastopenq->lock" is created.
+ * only in the rare case when both the listener and the child locks are held,
+ * e.g., in inet_csk_listen_stop() do we not need to acquire the lock.
+ * The lock also protects other fields such as fastopenq->qlen, which is
+ * decremented by this function when fastopen_rsk is no longer needed.
+ *
+ * Note that another solution was to simply use the existing socket lock
+ * from the listener. But first socket lock is difficult to use. It is not
+ * a simple spin lock - one must consider sock_owned_by_user() and arrange
+ * to use sk_add_backlog() stuff. But what really makes it infeasible is the
+ * locking hierarchy violation. E.g., inet_csk_listen_stop() may try to
+ * acquire a child's lock while holding listener's socket lock. A corner
+ * case might also exist in tcp_v4_hnd_req() that will trigger this locking
+ * order.
+ *
+ * When a TFO req is created, it needs to sock_hold its listener to prevent
+ * the latter data structure from going away.
+ *
+ * This function also sets "treq->listener" to NULL and unreference listener
+ * socket. treq->listener is used by the listener so it is protected by the
+ * fastopenq->lock in this function.
+ */
+void reqsk_fastopen_remove(struct sock *sk, struct request_sock *req,
+			   bool reset)
+{
+	struct sock *lsk = tcp_rsk(req)->listener;
+	struct fastopen_queue *fastopenq =
+	    inet_csk(lsk)->icsk_accept_queue.fastopenq;
+
+	tcp_sk(sk)->fastopen_rsk = NULL;
+	spin_lock_bh(&fastopenq->lock);
+	fastopenq->qlen--;
+	tcp_rsk(req)->listener = NULL;
+	if (req->sk)	/* the child socket hasn't been accepted yet */
+		goto out;
+
+	if (!reset || lsk->sk_state != TCP_LISTEN) {
+		/* If the listener has been closed don't bother with the
+		 * special RST handling below.
+		 */
+		spin_unlock_bh(&fastopenq->lock);
+		sock_put(lsk);
+		reqsk_free(req);
+		return;
+	}
+	/* Wait for 60secs before removing a req that has triggered RST.
+	 * This is a simple defense against TFO spoofing attack - by
+	 * counting the req against fastopen.max_qlen, and disabling
+	 * TFO when the qlen exceeds max_qlen.
+	 *
+	 * For more details see CoNext'11 "TCP Fast Open" paper.
+	 */
+	req->expires = jiffies + 60*HZ;
+	if (fastopenq->rskq_rst_head == NULL)
+		fastopenq->rskq_rst_head = req;
+	else
+		fastopenq->rskq_rst_tail->dl_next = req;
+
+	req->dl_next = NULL;
+	fastopenq->rskq_rst_tail = req;
+	fastopenq->qlen++;
+out:
+	spin_unlock_bh(&fastopenq->lock);
+	sock_put(lsk);
+}

net/core/scm.c

@@ -0,0 +1,341 @@
+/* scm.c - Socket level control messages processing.
+ *
+ * Author:	Alexey Kuznetsov, <kuznet@ms2.inr.ac.ru>
+ *              Alignment and value checking mods by Craig Metz
+ *
+ *		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; either version
+ *		2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/signal.h>
+#include <linux/capability.h>
+#include <linux/errno.h>
+#include <linux/sched.h>
+#include <linux/mm.h>
+#include <linux/kernel.h>
+#include <linux/stat.h>
+#include <linux/socket.h>
+#include <linux/file.h>
+#include <linux/fcntl.h>
+#include <linux/net.h>
+#include <linux/interrupt.h>
+#include <linux/netdevice.h>
+#include <linux/security.h>
+#include <linux/pid_namespace.h>
+#include <linux/pid.h>
+#include <linux/nsproxy.h>
+#include <linux/slab.h>
+
+#include <asm/uaccess.h>
+
+#include <net/protocol.h>
+#include <linux/skbuff.h>
+#include <net/sock.h>
+#include <net/compat.h>
+#include <net/scm.h>
+#include <net/cls_cgroup.h>
+
+
+/*
+ *	Only allow a user to send credentials, that they could set with
+ *	setu(g)id.
+ */
+
+static __inline__ int scm_check_creds(struct ucred *creds)
+{
+	const struct cred *cred = current_cred();
+	kuid_t uid = make_kuid(cred->user_ns, creds->uid);
+	kgid_t gid = make_kgid(cred->user_ns, creds->gid);
+
+	if (!uid_valid(uid) || !gid_valid(gid))
+		return -EINVAL;
+
+	if ((creds->pid == task_tgid_vnr(current) ||
+	     ns_capable(task_active_pid_ns(current)->user_ns, CAP_SYS_ADMIN)) &&
+	    ((uid_eq(uid, cred->uid)   || uid_eq(uid, cred->euid) ||
+	      uid_eq(uid, cred->suid)) || ns_capable(cred->user_ns, CAP_SETUID)) &&
+	    ((gid_eq(gid, cred->gid)   || gid_eq(gid, cred->egid) ||
+	      gid_eq(gid, cred->sgid)) || ns_capable(cred->user_ns, CAP_SETGID))) {
+	       return 0;
+	}
+	return -EPERM;
+}
+
+static int scm_fp_copy(struct cmsghdr *cmsg, struct scm_fp_list **fplp)
+{
+	int *fdp = (int*)CMSG_DATA(cmsg);
+	struct scm_fp_list *fpl = *fplp;
+	struct file **fpp;
+	int i, num;
+
+	num = (cmsg->cmsg_len - CMSG_ALIGN(sizeof(struct cmsghdr)))/sizeof(int);
+
+	if (num <= 0)
+		return 0;
+
+	if (num > SCM_MAX_FD)
+		return -EINVAL;
+
+	if (!fpl)
+	{
+		fpl = kmalloc(sizeof(struct scm_fp_list), GFP_KERNEL);
+		if (!fpl)
+			return -ENOMEM;
+		*fplp = fpl;
+		fpl->count = 0;
+		fpl->max = SCM_MAX_FD;
+	}
+	fpp = &fpl->fp[fpl->count];
+
+	if (fpl->count + num > fpl->max)
+		return -EINVAL;
+
+	/*
+	 *	Verify the descriptors and increment the usage count.
+	 */
+
+	for (i=0; i< num; i++)
+	{
+		int fd = fdp[i];
+		struct file *file;
+
+		if (fd < 0 || !(file = fget_raw(fd)))
+			return -EBADF;
+		*fpp++ = file;
+		fpl->count++;
+	}
+	return num;
+}
+
+void __scm_destroy(struct scm_cookie *scm)
+{
+	struct scm_fp_list *fpl = scm->fp;
+	int i;
+
+	if (fpl) {
+		scm->fp = NULL;
+		for (i=fpl->count-1; i>=0; i--)
+			fput(fpl->fp[i]);
+		kfree(fpl);
+	}
+}
+EXPORT_SYMBOL(__scm_destroy);
+
+int __scm_send(struct socket *sock, struct msghdr *msg, struct scm_cookie *p)
+{
+	struct cmsghdr *cmsg;
+	int err;
+
+	for (cmsg = CMSG_FIRSTHDR(msg); cmsg; cmsg = CMSG_NXTHDR(msg, cmsg))
+	{
+		err = -EINVAL;
+
+		/* Verify that cmsg_len is at least sizeof(struct cmsghdr) */
+		/* The first check was omitted in <= 2.2.5. The reasoning was
+		   that parser checks cmsg_len in any case, so that
+		   additional check would be work duplication.
+		   But if cmsg_level is not SOL_SOCKET, we do not check
+		   for too short ancillary data object at all! Oops.
+		   OK, let's add it...
+		 */
+		if (!CMSG_OK(msg, cmsg))
+			goto error;
+
+		if (cmsg->cmsg_level != SOL_SOCKET)
+			continue;
+
+		switch (cmsg->cmsg_type)
+		{
+		case SCM_RIGHTS:
+			if (!sock->ops || sock->ops->family != PF_UNIX)
+				goto error;
+			err=scm_fp_copy(cmsg, &p->fp);
+			if (err<0)
+				goto error;
+			break;
+		case SCM_CREDENTIALS:
+		{
+			struct ucred creds;
+			kuid_t uid;
+			kgid_t gid;
+			if (cmsg->cmsg_len != CMSG_LEN(sizeof(struct ucred)))
+				goto error;
+			memcpy(&creds, CMSG_DATA(cmsg), sizeof(struct ucred));
+			err = scm_check_creds(&creds);
+			if (err)
+				goto error;
+
+			p->creds.pid = creds.pid;
+			if (!p->pid || pid_vnr(p->pid) != creds.pid) {
+				struct pid *pid;
+				err = -ESRCH;
+				pid = find_get_pid(creds.pid);
+				if (!pid)
+					goto error;
+				put_pid(p->pid);
+				p->pid = pid;
+			}
+
+			err = -EINVAL;
+			uid = make_kuid(current_user_ns(), creds.uid);
+			gid = make_kgid(current_user_ns(), creds.gid);
+			if (!uid_valid(uid) || !gid_valid(gid))
+				goto error;
+
+			p->creds.uid = uid;
+			p->creds.gid = gid;
+			break;
+		}
+		default:
+			goto error;
+		}
+	}
+
+	if (p->fp && !p->fp->count)
+	{
+		kfree(p->fp);
+		p->fp = NULL;
+	}
+	return 0;
+
+error:
+	scm_destroy(p);
+	return err;
+}
+EXPORT_SYMBOL(__scm_send);
+
+int put_cmsg(struct msghdr * msg, int level, int type, int len, void *data)
+{
+	struct cmsghdr __user *cm
+		= (__force struct cmsghdr __user *)msg->msg_control;
+	struct cmsghdr cmhdr;
+	int cmlen = CMSG_LEN(len);
+	int err;
+
+	if (MSG_CMSG_COMPAT & msg->msg_flags)
+		return put_cmsg_compat(msg, level, type, len, data);
+
+	if (cm==NULL || msg->msg_controllen < sizeof(*cm)) {
+		msg->msg_flags |= MSG_CTRUNC;
+		return 0; /* XXX: return error? check spec. */
+	}
+	if (msg->msg_controllen < cmlen) {
+		msg->msg_flags |= MSG_CTRUNC;
+		cmlen = msg->msg_controllen;
+	}
+	cmhdr.cmsg_level = level;
+	cmhdr.cmsg_type = type;
+	cmhdr.cmsg_len = cmlen;
+
+	err = -EFAULT;
+	if (copy_to_user(cm, &cmhdr, sizeof cmhdr))
+		goto out;
+	if (copy_to_user(CMSG_DATA(cm), data, cmlen - sizeof(struct cmsghdr)))
+		goto out;
+	cmlen = CMSG_SPACE(len);
+	if (msg->msg_controllen < cmlen)
+		cmlen = msg->msg_controllen;
+	msg->msg_control += cmlen;
+	msg->msg_controllen -= cmlen;
+	err = 0;
+out:
+	return err;
+}
+EXPORT_SYMBOL(put_cmsg);
+
+void scm_detach_fds(struct msghdr *msg, struct scm_cookie *scm)
+{
+	struct cmsghdr __user *cm
+		= (__force struct cmsghdr __user*)msg->msg_control;
+
+	int fdmax = 0;
+	int fdnum = scm->fp->count;
+	struct file **fp = scm->fp->fp;
+	int __user *cmfptr;
+	int err = 0, i;
+
+	if (MSG_CMSG_COMPAT & msg->msg_flags) {
+		scm_detach_fds_compat(msg, scm);
+		return;
+	}
+
+	if (msg->msg_controllen > sizeof(struct cmsghdr))
+		fdmax = ((msg->msg_controllen - sizeof(struct cmsghdr))
+			 / sizeof(int));
+
+	if (fdnum < fdmax)
+		fdmax = fdnum;
+
+	for (i=0, cmfptr=(__force int __user *)CMSG_DATA(cm); i<fdmax;
+	     i++, cmfptr++)
+	{
+		struct socket *sock;
+		int new_fd;
+		err = security_file_receive(fp[i]);
+		if (err)
+			break;
+		err = get_unused_fd_flags(MSG_CMSG_CLOEXEC & msg->msg_flags
+					  ? O_CLOEXEC : 0);
+		if (err < 0)
+			break;
+		new_fd = err;
+		err = put_user(new_fd, cmfptr);
+		if (err) {
+			put_unused_fd(new_fd);
+			break;
+		}
+		/* Bump the usage count and install the file. */
+		sock = sock_from_file(fp[i], &err);
+		if (sock) {
+			sock_update_netprioidx(sock->sk);
+			sock_update_classid(sock->sk);
+		}
+		fd_install(new_fd, get_file(fp[i]));
+	}
+
+	if (i > 0)
+	{
+		int cmlen = CMSG_LEN(i*sizeof(int));
+		err = put_user(SOL_SOCKET, &cm->cmsg_level);
+		if (!err)
+			err = put_user(SCM_RIGHTS, &cm->cmsg_type);
+		if (!err)
+			err = put_user(cmlen, &cm->cmsg_len);
+		if (!err) {
+			cmlen = CMSG_SPACE(i*sizeof(int));
+			msg->msg_control += cmlen;
+			msg->msg_controllen -= cmlen;
+		}
+	}
+	if (i < fdnum || (fdnum && fdmax <= 0))
+		msg->msg_flags |= MSG_CTRUNC;
+
+	/*
+	 * All of the files that fit in the message have had their
+	 * usage counts incremented, so we just free the list.
+	 */
+	__scm_destroy(scm);
+}
+EXPORT_SYMBOL(scm_detach_fds);
+
+struct scm_fp_list *scm_fp_dup(struct scm_fp_list *fpl)
+{
+	struct scm_fp_list *new_fpl;
+	int i;
+
+	if (!fpl)
+		return NULL;
+
+	new_fpl = kmemdup(fpl, offsetof(struct scm_fp_list, fp[fpl->count]),
+			  GFP_KERNEL);
+	if (new_fpl) {
+		for (i = 0; i < fpl->count; i++)
+			get_file(fpl->fp[i]);
+		new_fpl->max = new_fpl->count;
+	}
+	return new_fpl;
+}
+EXPORT_SYMBOL(scm_fp_dup);

net/core/secure_seq.c

@@ -0,0 +1,173 @@
+#include <linux/kernel.h>
+#include <linux/init.h>
+#include <linux/cryptohash.h>
+#include <linux/module.h>
+#include <linux/cache.h>
+#include <linux/random.h>
+#include <linux/hrtimer.h>
+#include <linux/ktime.h>
+#include <linux/string.h>
+#include <linux/net.h>
+
+#include <net/secure_seq.h>
+
+#if IS_ENABLED(CONFIG_IPV6) || IS_ENABLED(CONFIG_INET)
+#define NET_SECRET_SIZE (MD5_MESSAGE_BYTES / 4)
+
+static u32 net_secret[NET_SECRET_SIZE] ____cacheline_aligned;
+
+static __always_inline void net_secret_init(void)
+{
+	net_get_random_once(net_secret, sizeof(net_secret));
+}
+#endif
+
+#ifdef CONFIG_INET
+static u32 seq_scale(u32 seq)
+{
+	/*
+	 *	As close as possible to RFC 793, which
+	 *	suggests using a 250 kHz clock.
+	 *	Further reading shows this assumes 2 Mb/s networks.
+	 *	For 10 Mb/s Ethernet, a 1 MHz clock is appropriate.
+	 *	For 10 Gb/s Ethernet, a 1 GHz clock should be ok, but
+	 *	we also need to limit the resolution so that the u32 seq
+	 *	overlaps less than one time per MSL (2 minutes).
+	 *	Choosing a clock of 64 ns period is OK. (period of 274 s)
+	 */
+	return seq + (ktime_get_real_ns() >> 6);
+}
+#endif
+
+#if IS_ENABLED(CONFIG_IPV6)
+__u32 secure_tcpv6_sequence_number(const __be32 *saddr, const __be32 *daddr,
+				   __be16 sport, __be16 dport)
+{
+	u32 secret[MD5_MESSAGE_BYTES / 4];
+	u32 hash[MD5_DIGEST_WORDS];
+	u32 i;
+
+	net_secret_init();
+	memcpy(hash, saddr, 16);
+	for (i = 0; i < 4; i++)
+		secret[i] = net_secret[i] + (__force u32)daddr[i];
+	secret[4] = net_secret[4] +
+		(((__force u16)sport << 16) + (__force u16)dport);
+	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+		secret[i] = net_secret[i];
+
+	md5_transform(hash, secret);
+
+	return seq_scale(hash[0]);
+}
+EXPORT_SYMBOL(secure_tcpv6_sequence_number);
+
+u32 secure_ipv6_port_ephemeral(const __be32 *saddr, const __be32 *daddr,
+			       __be16 dport)
+{
+	u32 secret[MD5_MESSAGE_BYTES / 4];
+	u32 hash[MD5_DIGEST_WORDS];
+	u32 i;
+
+	net_secret_init();
+	memcpy(hash, saddr, 16);
+	for (i = 0; i < 4; i++)
+		secret[i] = net_secret[i] + (__force u32) daddr[i];
+	secret[4] = net_secret[4] + (__force u32)dport;
+	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+		secret[i] = net_secret[i];
+
+	md5_transform(hash, secret);
+
+	return hash[0];
+}
+EXPORT_SYMBOL(secure_ipv6_port_ephemeral);
+#endif
+
+#ifdef CONFIG_INET
+
+__u32 secure_tcp_sequence_number(__be32 saddr, __be32 daddr,
+				 __be16 sport, __be16 dport)
+{
+	u32 hash[MD5_DIGEST_WORDS];
+
+	net_secret_init();
+	hash[0] = (__force u32)saddr;
+	hash[1] = (__force u32)daddr;
+	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
+	hash[3] = net_secret[15];
+
+	md5_transform(hash, net_secret);
+
+	return seq_scale(hash[0]);
+}
+
+u32 secure_ipv4_port_ephemeral(__be32 saddr, __be32 daddr, __be16 dport)
+{
+	u32 hash[MD5_DIGEST_WORDS];
+
+	net_secret_init();
+	hash[0] = (__force u32)saddr;
+	hash[1] = (__force u32)daddr;
+	hash[2] = (__force u32)dport ^ net_secret[14];
+	hash[3] = net_secret[15];
+
+	md5_transform(hash, net_secret);
+
+	return hash[0];
+}
+EXPORT_SYMBOL_GPL(secure_ipv4_port_ephemeral);
+#endif
+
+#if IS_ENABLED(CONFIG_IP_DCCP)
+u64 secure_dccp_sequence_number(__be32 saddr, __be32 daddr,
+				__be16 sport, __be16 dport)
+{
+	u32 hash[MD5_DIGEST_WORDS];
+	u64 seq;
+
+	net_secret_init();
+	hash[0] = (__force u32)saddr;
+	hash[1] = (__force u32)daddr;
+	hash[2] = ((__force u16)sport << 16) + (__force u16)dport;
+	hash[3] = net_secret[15];
+
+	md5_transform(hash, net_secret);
+
+	seq = hash[0] | (((u64)hash[1]) << 32);
+	seq += ktime_get_real_ns();
+	seq &= (1ull << 48) - 1;
+
+	return seq;
+}
+EXPORT_SYMBOL(secure_dccp_sequence_number);
+
+#if IS_ENABLED(CONFIG_IPV6)
+u64 secure_dccpv6_sequence_number(__be32 *saddr, __be32 *daddr,
+				  __be16 sport, __be16 dport)
+{
+	u32 secret[MD5_MESSAGE_BYTES / 4];
+	u32 hash[MD5_DIGEST_WORDS];
+	u64 seq;
+	u32 i;
+
+	net_secret_init();
+	memcpy(hash, saddr, 16);
+	for (i = 0; i < 4; i++)
+		secret[i] = net_secret[i] + daddr[i];
+	secret[4] = net_secret[4] +
+		(((__force u16)sport << 16) + (__force u16)dport);
+	for (i = 5; i < MD5_MESSAGE_BYTES / 4; i++)
+		secret[i] = net_secret[i];
+
+	md5_transform(hash, secret);
+
+	seq = hash[0] | (((u64)hash[1]) << 32);
+	seq += ktime_get_real_ns();
+	seq &= (1ull << 48) - 1;
+
+	return seq;
+}
+EXPORT_SYMBOL(secure_dccpv6_sequence_number);
+#endif
+#endif

net/core/sock_diag.c

@@ -0,0 +1,248 @@
+#include <linux/mutex.h>
+#include <linux/socket.h>
+#include <linux/skbuff.h>
+#include <net/netlink.h>
+#include <net/net_namespace.h>
+#include <linux/module.h>
+#include <net/sock.h>
+
+#include <linux/inet_diag.h>
+#include <linux/sock_diag.h>
+
+static const struct sock_diag_handler *sock_diag_handlers[AF_MAX];
+static int (*inet_rcv_compat)(struct sk_buff *skb, struct nlmsghdr *nlh);
+static DEFINE_MUTEX(sock_diag_table_mutex);
+
+int sock_diag_check_cookie(void *sk, __u32 *cookie)
+{
+	if ((cookie[0] != INET_DIAG_NOCOOKIE ||
+	     cookie[1] != INET_DIAG_NOCOOKIE) &&
+	    ((u32)(unsigned long)sk != cookie[0] ||
+	     (u32)((((unsigned long)sk) >> 31) >> 1) != cookie[1]))
+		return -ESTALE;
+	else
+		return 0;
+}
+EXPORT_SYMBOL_GPL(sock_diag_check_cookie);
+
+void sock_diag_save_cookie(void *sk, __u32 *cookie)
+{
+	cookie[0] = (u32)(unsigned long)sk;
+	cookie[1] = (u32)(((unsigned long)sk >> 31) >> 1);
+}
+EXPORT_SYMBOL_GPL(sock_diag_save_cookie);
+
+int sock_diag_put_meminfo(struct sock *sk, struct sk_buff *skb, int attrtype)
+{
+	u32 mem[SK_MEMINFO_VARS];
+
+	mem[SK_MEMINFO_RMEM_ALLOC] = sk_rmem_alloc_get(sk);
+	mem[SK_MEMINFO_RCVBUF] = sk->sk_rcvbuf;
+	mem[SK_MEMINFO_WMEM_ALLOC] = sk_wmem_alloc_get(sk);
+	mem[SK_MEMINFO_SNDBUF] = sk->sk_sndbuf;
+	mem[SK_MEMINFO_FWD_ALLOC] = sk->sk_forward_alloc;
+	mem[SK_MEMINFO_WMEM_QUEUED] = sk->sk_wmem_queued;
+	mem[SK_MEMINFO_OPTMEM] = atomic_read(&sk->sk_omem_alloc);
+	mem[SK_MEMINFO_BACKLOG] = sk->sk_backlog.len;
+
+	return nla_put(skb, attrtype, sizeof(mem), &mem);
+}
+EXPORT_SYMBOL_GPL(sock_diag_put_meminfo);
+
+int sock_diag_put_filterinfo(bool may_report_filterinfo, struct sock *sk,
+			     struct sk_buff *skb, int attrtype)
+{
+	struct sock_fprog_kern *fprog;
+	struct sk_filter *filter;
+	struct nlattr *attr;
+	unsigned int flen;
+	int err = 0;
+
+	if (!may_report_filterinfo) {
+		nla_reserve(skb, attrtype, 0);
+		return 0;
+	}
+
+	rcu_read_lock();
+	filter = rcu_dereference(sk->sk_filter);
+	if (!filter)
+		goto out;
+
+	fprog = filter->prog->orig_prog;
+	flen = bpf_classic_proglen(fprog);
+
+	attr = nla_reserve(skb, attrtype, flen);
+	if (attr == NULL) {
+		err = -EMSGSIZE;
+		goto out;
+	}
+
+	memcpy(nla_data(attr), fprog->filter, flen);
+out:
+	rcu_read_unlock();
+	return err;
+}
+EXPORT_SYMBOL(sock_diag_put_filterinfo);
+
+void sock_diag_register_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+{
+	mutex_lock(&sock_diag_table_mutex);
+	inet_rcv_compat = fn;
+	mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_register_inet_compat);
+
+void sock_diag_unregister_inet_compat(int (*fn)(struct sk_buff *skb, struct nlmsghdr *nlh))
+{
+	mutex_lock(&sock_diag_table_mutex);
+	inet_rcv_compat = NULL;
+	mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_unregister_inet_compat);
+
+int sock_diag_register(const struct sock_diag_handler *hndl)
+{
+	int err = 0;
+
+	if (hndl->family >= AF_MAX)
+		return -EINVAL;
+
+	mutex_lock(&sock_diag_table_mutex);
+	if (sock_diag_handlers[hndl->family])
+		err = -EBUSY;
+	else
+		sock_diag_handlers[hndl->family] = hndl;
+	mutex_unlock(&sock_diag_table_mutex);
+
+	return err;
+}
+EXPORT_SYMBOL_GPL(sock_diag_register);
+
+void sock_diag_unregister(const struct sock_diag_handler *hnld)
+{
+	int family = hnld->family;
+
+	if (family >= AF_MAX)
+		return;
+
+	mutex_lock(&sock_diag_table_mutex);
+	BUG_ON(sock_diag_handlers[family] != hnld);
+	sock_diag_handlers[family] = NULL;
+	mutex_unlock(&sock_diag_table_mutex);
+}
+EXPORT_SYMBOL_GPL(sock_diag_unregister);
+
+static int __sock_diag_cmd(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int err;
+	struct sock_diag_req *req = nlmsg_data(nlh);
+	const struct sock_diag_handler *hndl;
+
+	if (nlmsg_len(nlh) < sizeof(*req))
+		return -EINVAL;
+
+	if (req->sdiag_family >= AF_MAX)
+		return -EINVAL;
+
+	if (sock_diag_handlers[req->sdiag_family] == NULL)
+		request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+				NETLINK_SOCK_DIAG, req->sdiag_family);
+
+	mutex_lock(&sock_diag_table_mutex);
+	hndl = sock_diag_handlers[req->sdiag_family];
+	if (hndl == NULL)
+		err = -ENOENT;
+	else if (nlh->nlmsg_type == SOCK_DIAG_BY_FAMILY)
+		err = hndl->dump(skb, nlh);
+	else if (nlh->nlmsg_type == SOCK_DESTROY_BACKPORT && hndl->destroy)
+		err = hndl->destroy(skb, nlh);
+	else
+		err = -EOPNOTSUPP;
+	mutex_unlock(&sock_diag_table_mutex);
+
+	return err;
+}
+
+static int sock_diag_rcv_msg(struct sk_buff *skb, struct nlmsghdr *nlh)
+{
+	int ret;
+
+	switch (nlh->nlmsg_type) {
+	case TCPDIAG_GETSOCK:
+	case DCCPDIAG_GETSOCK:
+		if (inet_rcv_compat == NULL)
+			request_module("net-pf-%d-proto-%d-type-%d", PF_NETLINK,
+					NETLINK_SOCK_DIAG, AF_INET);
+
+		mutex_lock(&sock_diag_table_mutex);
+		if (inet_rcv_compat != NULL)
+			ret = inet_rcv_compat(skb, nlh);
+		else
+			ret = -EOPNOTSUPP;
+		mutex_unlock(&sock_diag_table_mutex);
+
+		return ret;
+	case SOCK_DIAG_BY_FAMILY:
+	case SOCK_DESTROY_BACKPORT:
+		return __sock_diag_cmd(skb, nlh);
+	default:
+		return -EINVAL;
+	}
+}
+
+static DEFINE_MUTEX(sock_diag_mutex);
+
+static void sock_diag_rcv(struct sk_buff *skb)
+{
+	mutex_lock(&sock_diag_mutex);
+	netlink_rcv_skb(skb, &sock_diag_rcv_msg);
+	mutex_unlock(&sock_diag_mutex);
+}
+
+int sock_diag_destroy(struct sock *sk, int err)
+{
+	if (!ns_capable(sock_net(sk)->user_ns, CAP_NET_ADMIN))
+		return -EPERM;
+
+	if (!sk->sk_prot->diag_destroy)
+		return -EOPNOTSUPP;
+
+	return sk->sk_prot->diag_destroy(sk, err);
+}
+EXPORT_SYMBOL_GPL(sock_diag_destroy);
+
+static int __net_init diag_net_init(struct net *net)
+{
+	struct netlink_kernel_cfg cfg = {
+		.input	= sock_diag_rcv,
+	};
+
+	net->diag_nlsk = netlink_kernel_create(net, NETLINK_SOCK_DIAG, &cfg);
+	return net->diag_nlsk == NULL ? -ENOMEM : 0;
+}
+
+static void __net_exit diag_net_exit(struct net *net)
+{
+	netlink_kernel_release(net->diag_nlsk);
+	net->diag_nlsk = NULL;
+}
+
+static struct pernet_operations diag_net_ops = {
+	.init = diag_net_init,
+	.exit = diag_net_exit,
+};
+
+static int __init sock_diag_init(void)
+{
+	return register_pernet_subsys(&diag_net_ops);
+}
+
+static void __exit sock_diag_exit(void)
+{
+	unregister_pernet_subsys(&diag_net_ops);
+}
+
+module_init(sock_diag_init);
+module_exit(sock_diag_exit);
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_NETLINK, NETLINK_SOCK_DIAG);

net/core/stream.c

@@ -0,0 +1,208 @@
+/*
+ *     SUCS NET3:
+ *
+ *     Generic stream handling routines. These are generic for most
+ *     protocols. Even IP. Tonight 8-).
+ *     This is used because TCP, LLC (others too) layer all have mostly
+ *     identical sendmsg() and recvmsg() code.
+ *     So we (will) share it here.
+ *
+ *     Authors:        Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *                     (from old tcp.c code)
+ *                     Alan Cox <alan@lxorguk.ukuu.org.uk> (Borrowed comments 8-))
+ */
+
+#include <linux/module.h>
+#include <linux/net.h>
+#include <linux/signal.h>
+#include <linux/tcp.h>
+#include <linux/wait.h>
+#include <net/sock.h>
+
+/**
+ * sk_stream_write_space - stream socket write_space callback.
+ * @sk: socket
+ *
+ * FIXME: write proper description
+ */
+void sk_stream_write_space(struct sock *sk)
+{
+	struct socket *sock = sk->sk_socket;
+	struct socket_wq *wq;
+
+	if (sk_stream_is_writeable(sk) && sock) {
+		clear_bit(SOCK_NOSPACE, &sock->flags);
+
+		rcu_read_lock();
+		wq = rcu_dereference(sk->sk_wq);
+		if (wq_has_sleeper(wq))
+			wake_up_interruptible_poll(&wq->wait, POLLOUT |
+						POLLWRNORM | POLLWRBAND);
+		if (wq && wq->fasync_list && !(sk->sk_shutdown & SEND_SHUTDOWN))
+			sock_wake_async(sock, SOCK_WAKE_SPACE, POLL_OUT);
+		rcu_read_unlock();
+	}
+}
+EXPORT_SYMBOL(sk_stream_write_space);
+
+/**
+ * sk_stream_wait_connect - Wait for a socket to get into the connected state
+ * @sk: sock to wait on
+ * @timeo_p: for how long to wait
+ *
+ * Must be called with the socket locked.
+ */
+int sk_stream_wait_connect(struct sock *sk, long *timeo_p)
+{
+	struct task_struct *tsk = current;
+	DEFINE_WAIT(wait);
+	int done;
+
+	do {
+		int err = sock_error(sk);
+		if (err)
+			return err;
+		if ((1 << sk->sk_state) & ~(TCPF_SYN_SENT | TCPF_SYN_RECV))
+			return -EPIPE;
+		if (!*timeo_p)
+			return -EAGAIN;
+		if (signal_pending(tsk))
+			return sock_intr_errno(*timeo_p);
+
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+		sk->sk_write_pending++;
+		done = sk_wait_event(sk, timeo_p,
+				     !sk->sk_err &&
+				     !((1 << sk->sk_state) &
+				       ~(TCPF_ESTABLISHED | TCPF_CLOSE_WAIT)));
+		finish_wait(sk_sleep(sk), &wait);
+		sk->sk_write_pending--;
+	} while (!done);
+	return 0;
+}
+EXPORT_SYMBOL(sk_stream_wait_connect);
+
+/**
+ * sk_stream_closing - Return 1 if we still have things to send in our buffers.
+ * @sk: socket to verify
+ */
+static inline int sk_stream_closing(struct sock *sk)
+{
+	return (1 << sk->sk_state) &
+	       (TCPF_FIN_WAIT1 | TCPF_CLOSING | TCPF_LAST_ACK);
+}
+
+void sk_stream_wait_close(struct sock *sk, long timeout)
+{
+	if (timeout) {
+		DEFINE_WAIT(wait);
+
+		do {
+			prepare_to_wait(sk_sleep(sk), &wait,
+					TASK_INTERRUPTIBLE);
+			if (sk_wait_event(sk, &timeout, !sk_stream_closing(sk)))
+				break;
+		} while (!signal_pending(current) && timeout);
+
+		finish_wait(sk_sleep(sk), &wait);
+	}
+}
+EXPORT_SYMBOL(sk_stream_wait_close);
+
+/**
+ * sk_stream_wait_memory - Wait for more memory for a socket
+ * @sk: socket to wait for memory
+ * @timeo_p: for how long
+ */
+int sk_stream_wait_memory(struct sock *sk, long *timeo_p)
+{
+	int err = 0;
+	long vm_wait = 0;
+	long current_timeo = *timeo_p;
+	DEFINE_WAIT(wait);
+
+	if (sk_stream_memory_free(sk))
+		current_timeo = vm_wait = (prandom_u32() % (HZ / 5)) + 2;
+
+	while (1) {
+		set_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+
+		prepare_to_wait(sk_sleep(sk), &wait, TASK_INTERRUPTIBLE);
+
+		if (sk->sk_err || (sk->sk_shutdown & SEND_SHUTDOWN))
+			goto do_error;
+		if (!*timeo_p)
+			goto do_nonblock;
+		if (signal_pending(current))
+			goto do_interrupted;
+		clear_bit(SOCK_ASYNC_NOSPACE, &sk->sk_socket->flags);
+		if (sk_stream_memory_free(sk) && !vm_wait)
+			break;
+
+		set_bit(SOCK_NOSPACE, &sk->sk_socket->flags);
+		sk->sk_write_pending++;
+		sk_wait_event(sk, &current_timeo, sk->sk_err ||
+						  (sk->sk_shutdown & SEND_SHUTDOWN) ||
+						  (sk_stream_memory_free(sk) &&
+						  !vm_wait));
+		sk->sk_write_pending--;
+
+		if (vm_wait) {
+			vm_wait -= current_timeo;
+			current_timeo = *timeo_p;
+			if (current_timeo != MAX_SCHEDULE_TIMEOUT &&
+			    (current_timeo -= vm_wait) < 0)
+				current_timeo = 0;
+			vm_wait = 0;
+		}
+		*timeo_p = current_timeo;
+	}
+out:
+	finish_wait(sk_sleep(sk), &wait);
+	return err;
+
+do_error:
+	err = -EPIPE;
+	goto out;
+do_nonblock:
+	err = -EAGAIN;
+	goto out;
+do_interrupted:
+	err = sock_intr_errno(*timeo_p);
+	goto out;
+}
+EXPORT_SYMBOL(sk_stream_wait_memory);
+
+int sk_stream_error(struct sock *sk, int flags, int err)
+{
+	if (err == -EPIPE)
+		err = sock_error(sk) ? : -EPIPE;
+	if (err == -EPIPE && !(flags & MSG_NOSIGNAL))
+		send_sig(SIGPIPE, current, 0);
+	return err;
+}
+EXPORT_SYMBOL(sk_stream_error);
+
+void sk_stream_kill_queues(struct sock *sk)
+{
+	/* First the read buffer. */
+	__skb_queue_purge(&sk->sk_receive_queue);
+
+	/* Next, the error queue. */
+	__skb_queue_purge(&sk->sk_error_queue);
+
+	/* Next, the write queue. */
+	WARN_ON(!skb_queue_empty(&sk->sk_write_queue));
+
+	/* Account for returned memory. */
+	sk_mem_reclaim(sk);
+
+	WARN_ON(sk->sk_wmem_queued);
+	WARN_ON(sk->sk_forward_alloc);
+
+	/* It is _impossible_ for the backlog to contain anything
+	 * when we get here.  All user references to this socket
+	 * have gone away, only the net layer knows can touch it.
+	 */
+}
+EXPORT_SYMBOL(sk_stream_kill_queues);

net/core/sysctl_net_core.c

@@ -0,0 +1,435 @@
+/* -*- linux-c -*-
+ * sysctl_net_core.c: sysctl interface to net core subsystem.
+ *
+ * Begun April 1, 1996, Mike Shaver.
+ * Added /proc/sys/net/core directory entry (empty =) ). [MS]
+ */
+
+#include <linux/mm.h>
+#include <linux/sysctl.h>
+#include <linux/module.h>
+#include <linux/socket.h>
+#include <linux/netdevice.h>
+#include <linux/ratelimit.h>
+#include <linux/vmalloc.h>
+#include <linux/init.h>
+#include <linux/slab.h>
+#include <linux/kmemleak.h>
+
+#include <net/ip.h>
+#include <net/sock.h>
+#include <net/net_ratelimit.h>
+#include <net/busy_poll.h>
+#include <net/pkt_sched.h>
+
+static int zero = 0;
+static int ushort_max = USHRT_MAX;
+static int min_sndbuf = SOCK_MIN_SNDBUF;
+static int min_rcvbuf = SOCK_MIN_RCVBUF;
+
+#ifdef CONFIG_RPS
+static int rps_sock_flow_sysctl(struct ctl_table *table, int write,
+				void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	unsigned int orig_size, size;
+	int ret, i;
+	struct ctl_table tmp = {
+		.data = &size,
+		.maxlen = sizeof(size),
+		.mode = table->mode
+	};
+	struct rps_sock_flow_table *orig_sock_table, *sock_table;
+	static DEFINE_MUTEX(sock_flow_mutex);
+
+	mutex_lock(&sock_flow_mutex);
+
+	orig_sock_table = rcu_dereference_protected(rps_sock_flow_table,
+					lockdep_is_held(&sock_flow_mutex));
+	size = orig_size = orig_sock_table ? orig_sock_table->mask + 1 : 0;
+
+	ret = proc_dointvec(&tmp, write, buffer, lenp, ppos);
+
+	if (write) {
+		if (size) {
+			if (size > 1<<30) {
+				/* Enforce limit to prevent overflow */
+				mutex_unlock(&sock_flow_mutex);
+				return -EINVAL;
+			}
+			size = roundup_pow_of_two(size);
+			if (size != orig_size) {
+				sock_table =
+				    vmalloc(RPS_SOCK_FLOW_TABLE_SIZE(size));
+				if (!sock_table) {
+					mutex_unlock(&sock_flow_mutex);
+					return -ENOMEM;
+				}
+
+				sock_table->mask = size - 1;
+			} else
+				sock_table = orig_sock_table;
+
+			for (i = 0; i < size; i++)
+				sock_table->ents[i] = RPS_NO_CPU;
+		} else
+			sock_table = NULL;
+
+		if (sock_table != orig_sock_table) {
+			rcu_assign_pointer(rps_sock_flow_table, sock_table);
+			if (sock_table)
+				static_key_slow_inc(&rps_needed);
+			if (orig_sock_table) {
+				static_key_slow_dec(&rps_needed);
+				synchronize_rcu();
+				vfree(orig_sock_table);
+			}
+		}
+	}
+
+	mutex_unlock(&sock_flow_mutex);
+
+	return ret;
+}
+#endif /* CONFIG_RPS */
+
+#ifdef CONFIG_NET_FLOW_LIMIT
+static DEFINE_MUTEX(flow_limit_update_mutex);
+
+static int flow_limit_cpu_sysctl(struct ctl_table *table, int write,
+				 void __user *buffer, size_t *lenp,
+				 loff_t *ppos)
+{
+	struct sd_flow_limit *cur;
+	struct softnet_data *sd;
+	cpumask_var_t mask;
+	int i, len, ret = 0;
+
+	if (!alloc_cpumask_var(&mask, GFP_KERNEL))
+		return -ENOMEM;
+
+	if (write) {
+		ret = cpumask_parse_user(buffer, *lenp, mask);
+		if (ret)
+			goto done;
+
+		mutex_lock(&flow_limit_update_mutex);
+		len = sizeof(*cur) + netdev_flow_limit_table_len;
+		for_each_possible_cpu(i) {
+			sd = &per_cpu(softnet_data, i);
+			cur = rcu_dereference_protected(sd->flow_limit,
+				     lockdep_is_held(&flow_limit_update_mutex));
+			if (cur && !cpumask_test_cpu(i, mask)) {
+				RCU_INIT_POINTER(sd->flow_limit, NULL);
+				synchronize_rcu();
+				kfree(cur);
+			} else if (!cur && cpumask_test_cpu(i, mask)) {
+				cur = kzalloc_node(len, GFP_KERNEL,
+						   cpu_to_node(i));
+				if (!cur) {
+					/* not unwinding previous changes */
+					ret = -ENOMEM;
+					goto write_unlock;
+				}
+				cur->num_buckets = netdev_flow_limit_table_len;
+				rcu_assign_pointer(sd->flow_limit, cur);
+			}
+		}
+write_unlock:
+		mutex_unlock(&flow_limit_update_mutex);
+	} else {
+		char kbuf[128];
+
+		if (*ppos || !*lenp) {
+			*lenp = 0;
+			goto done;
+		}
+
+		cpumask_clear(mask);
+		rcu_read_lock();
+		for_each_possible_cpu(i) {
+			sd = &per_cpu(softnet_data, i);
+			if (rcu_dereference(sd->flow_limit))
+				cpumask_set_cpu(i, mask);
+		}
+		rcu_read_unlock();
+
+		len = min(sizeof(kbuf) - 1, *lenp);
+		len = cpumask_scnprintf(kbuf, len, mask);
+		if (!len) {
+			*lenp = 0;
+			goto done;
+		}
+		if (len < *lenp)
+			kbuf[len++] = '\n';
+		if (copy_to_user(buffer, kbuf, len)) {
+			ret = -EFAULT;
+			goto done;
+		}
+		*lenp = len;
+		*ppos += len;
+	}
+
+done:
+	free_cpumask_var(mask);
+	return ret;
+}
+
+static int flow_limit_table_len_sysctl(struct ctl_table *table, int write,
+				       void __user *buffer, size_t *lenp,
+				       loff_t *ppos)
+{
+	unsigned int old, *ptr;
+	int ret;
+
+	mutex_lock(&flow_limit_update_mutex);
+
+	ptr = table->data;
+	old = *ptr;
+	ret = proc_dointvec(table, write, buffer, lenp, ppos);
+	if (!ret && write && !is_power_of_2(*ptr)) {
+		*ptr = old;
+		ret = -EINVAL;
+	}
+
+	mutex_unlock(&flow_limit_update_mutex);
+	return ret;
+}
+#endif /* CONFIG_NET_FLOW_LIMIT */
+
+#ifdef CONFIG_NET_SCHED
+static int set_default_qdisc(struct ctl_table *table, int write,
+			     void __user *buffer, size_t *lenp, loff_t *ppos)
+{
+	char id[IFNAMSIZ];
+	struct ctl_table tbl = {
+		.data = id,
+		.maxlen = IFNAMSIZ,
+	};
+	int ret;
+
+	qdisc_get_default(id, IFNAMSIZ);
+
+	ret = proc_dostring(&tbl, write, buffer, lenp, ppos);
+	if (write && ret == 0)
+		ret = qdisc_set_default(id);
+	return ret;
+}
+#endif
+
+static struct ctl_table net_core_table[] = {
+#ifdef CONFIG_NET
+	{
+		.procname	= "wmem_max",
+		.data		= &sysctl_wmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_sndbuf,
+	},
+	{
+		.procname	= "rmem_max",
+		.data		= &sysctl_rmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_rcvbuf,
+	},
+	{
+		.procname	= "wmem_default",
+		.data		= &sysctl_wmem_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_sndbuf,
+	},
+	{
+		.procname	= "rmem_default",
+		.data		= &sysctl_rmem_default,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_minmax,
+		.extra1		= &min_rcvbuf,
+	},
+	{
+		.procname	= "dev_weight",
+		.data		= &weight_p,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "netdev_max_backlog",
+		.data		= &netdev_max_backlog,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#ifdef CONFIG_BPF_JIT
+	{
+		.procname	= "bpf_jit_enable",
+		.data		= &bpf_jit_enable,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#endif
+	{
+		.procname	= "netdev_tstamp_prequeue",
+		.data		= &netdev_tstamp_prequeue,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "message_cost",
+		.data		= &net_ratelimit_state.interval,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec_jiffies,
+	},
+	{
+		.procname	= "message_burst",
+		.data		= &net_ratelimit_state.burst,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec,
+	},
+	{
+		.procname	= "optmem_max",
+		.data		= &sysctl_optmem_max,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#ifdef CONFIG_RPS
+	{
+		.procname	= "rps_sock_flow_entries",
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= rps_sock_flow_sysctl
+	},
+#endif
+#ifdef CONFIG_NET_FLOW_LIMIT
+	{
+		.procname	= "flow_limit_cpu_bitmap",
+		.mode		= 0644,
+		.proc_handler	= flow_limit_cpu_sysctl
+	},
+	{
+		.procname	= "flow_limit_table_len",
+		.data		= &netdev_flow_limit_table_len,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= flow_limit_table_len_sysctl
+	},
+#endif /* CONFIG_NET_FLOW_LIMIT */
+#ifdef CONFIG_NET_RX_BUSY_POLL
+	{
+		.procname	= "busy_poll",
+		.data		= &sysctl_net_busy_poll,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "busy_read",
+		.data		= &sysctl_net_busy_read,
+		.maxlen		= sizeof(unsigned int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+#endif
+#ifdef CONFIG_NET_SCHED
+	{
+		.procname	= "default_qdisc",
+		.mode		= 0644,
+		.maxlen		= IFNAMSIZ,
+		.proc_handler	= set_default_qdisc
+	},
+#endif
+#endif /* CONFIG_NET */
+	{
+		.procname	= "netdev_budget",
+		.data		= &netdev_budget,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{
+		.procname	= "warnings",
+		.data		= &net_msg_warn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.proc_handler	= proc_dointvec
+	},
+	{ }
+};
+
+static struct ctl_table netns_core_table[] = {
+	{
+		.procname	= "somaxconn",
+		.data		= &init_net.core.sysctl_somaxconn,
+		.maxlen		= sizeof(int),
+		.mode		= 0644,
+		.extra1		= &zero,
+		.extra2		= &ushort_max,
+		.proc_handler	= proc_dointvec_minmax
+	},
+	{ }
+};
+
+static __net_init int sysctl_core_net_init(struct net *net)
+{
+	struct ctl_table *tbl;
+
+	net->core.sysctl_somaxconn = SOMAXCONN;
+
+	tbl = netns_core_table;
+	if (!net_eq(net, &init_net)) {
+		tbl = kmemdup(tbl, sizeof(netns_core_table), GFP_KERNEL);
+		if (tbl == NULL)
+			goto err_dup;
+
+		tbl[0].data = &net->core.sysctl_somaxconn;
+
+		/* Don't export any sysctls to unprivileged users */
+		if (net->user_ns != &init_user_ns) {
+			tbl[0].procname = NULL;
+		}
+	}
+
+	net->core.sysctl_hdr = register_net_sysctl(net, "net/core", tbl);
+	if (net->core.sysctl_hdr == NULL)
+		goto err_reg;
+
+	return 0;
+
+err_reg:
+	if (tbl != netns_core_table)
+		kfree(tbl);
+err_dup:
+	return -ENOMEM;
+}
+
+static __net_exit void sysctl_core_net_exit(struct net *net)
+{
+	struct ctl_table *tbl;
+
+	tbl = net->core.sysctl_hdr->ctl_table_arg;
+	unregister_net_sysctl_table(net->core.sysctl_hdr);
+	BUG_ON(tbl == netns_core_table);
+	kfree(tbl);
+}
+
+static __net_initdata struct pernet_operations sysctl_core_ops = {
+	.init = sysctl_core_net_init,
+	.exit = sysctl_core_net_exit,
+};
+
+static __init int sysctl_core_init(void)
+{
+	register_net_sysctl(&init_net, "net/core", net_core_table);
+	return register_pernet_subsys(&sysctl_core_ops);
+}
+
+fs_initcall(sysctl_core_init);

net/core/timestamping.c

@@ -0,0 +1,80 @@
+/*
+ * PTP 1588 clock support - support for timestamping in PHY devices
+ *
+ * Copyright (C) 2010 OMICRON electronics GmbH
+ *
+ *  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; either version 2 of the License, or
+ *  (at your option) any later version.
+ *
+ *  This program is distributed in the hope that it will be useful,
+ *  but WITHOUT ANY WARRANTY; without even the implied warranty of
+ *  MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE.  See the
+ *  GNU General Public License for more details.
+ *
+ *  You should have received a copy of the GNU General Public License
+ *  along with this program; if not, write to the Free Software
+ *  Foundation, Inc., 675 Mass Ave, Cambridge, MA 02139, USA.
+ */
+#include <linux/errqueue.h>
+#include <linux/phy.h>
+#include <linux/ptp_classify.h>
+#include <linux/skbuff.h>
+#include <linux/export.h>
+
+static unsigned int classify(const struct sk_buff *skb)
+{
+	if (likely(skb->dev && skb->dev->phydev &&
+		   skb->dev->phydev->drv))
+		return ptp_classify_raw(skb);
+	else
+		return PTP_CLASS_NONE;
+}
+
+void skb_clone_tx_timestamp(struct sk_buff *skb)
+{
+	struct phy_device *phydev;
+	struct sk_buff *clone;
+	unsigned int type;
+
+	if (!skb->sk)
+		return;
+
+	type = classify(skb);
+	if (type == PTP_CLASS_NONE)
+		return;
+
+	phydev = skb->dev->phydev;
+	if (likely(phydev->drv->txtstamp)) {
+		clone = skb_clone_sk(skb);
+		if (!clone)
+			return;
+		phydev->drv->txtstamp(phydev, clone, type);
+	}
+}
+EXPORT_SYMBOL_GPL(skb_clone_tx_timestamp);
+
+bool skb_defer_rx_timestamp(struct sk_buff *skb)
+{
+	struct phy_device *phydev;
+	unsigned int type;
+
+	if (skb_headroom(skb) < ETH_HLEN)
+		return false;
+	__skb_push(skb, ETH_HLEN);
+
+	type = classify(skb);
+
+	__skb_pull(skb, ETH_HLEN);
+
+	if (type == PTP_CLASS_NONE)
+		return false;
+
+	phydev = skb->dev->phydev;
+	if (likely(phydev->drv->rxtstamp))
+		return phydev->drv->rxtstamp(phydev, skb, type);
+
+	return false;
+}
+EXPORT_SYMBOL_GPL(skb_defer_rx_timestamp);

net/core/tso.c

@@ -0,0 +1,78 @@
+#include <linux/export.h>
+#include <net/ip.h>
+#include <net/tso.h>
+#include <asm/unaligned.h>
+
+/* Calculate expected number of TX descriptors */
+int tso_count_descs(struct sk_buff *skb)
+{
+	/* The Marvell Way */
+	return skb_shinfo(skb)->gso_segs * 2 + skb_shinfo(skb)->nr_frags;
+}
+EXPORT_SYMBOL(tso_count_descs);
+
+void tso_build_hdr(struct sk_buff *skb, char *hdr, struct tso_t *tso,
+		   int size, bool is_last)
+{
+	struct iphdr *iph;
+	struct tcphdr *tcph;
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+	int mac_hdr_len = skb_network_offset(skb);
+
+	memcpy(hdr, skb->data, hdr_len);
+	iph = (struct iphdr *)(hdr + mac_hdr_len);
+	iph->id = htons(tso->ip_id);
+	iph->tot_len = htons(size + hdr_len - mac_hdr_len);
+	tcph = (struct tcphdr *)(hdr + skb_transport_offset(skb));
+	put_unaligned_be32(tso->tcp_seq, &tcph->seq);
+	tso->ip_id++;
+
+	if (!is_last) {
+		/* Clear all special flags for not last packet */
+		tcph->psh = 0;
+		tcph->fin = 0;
+		tcph->rst = 0;
+	}
+}
+EXPORT_SYMBOL(tso_build_hdr);
+
+void tso_build_data(struct sk_buff *skb, struct tso_t *tso, int size)
+{
+	tso->tcp_seq += size;
+	tso->size -= size;
+	tso->data += size;
+
+	if ((tso->size == 0) &&
+	    (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+		/* Move to next segment */
+		tso->size = frag->size;
+		tso->data = page_address(frag->page.p) + frag->page_offset;
+		tso->next_frag_idx++;
+	}
+}
+EXPORT_SYMBOL(tso_build_data);
+
+void tso_start(struct sk_buff *skb, struct tso_t *tso)
+{
+	int hdr_len = skb_transport_offset(skb) + tcp_hdrlen(skb);
+
+	tso->ip_id = ntohs(ip_hdr(skb)->id);
+	tso->tcp_seq = ntohl(tcp_hdr(skb)->seq);
+	tso->next_frag_idx = 0;
+
+	/* Build first data */
+	tso->size = skb_headlen(skb) - hdr_len;
+	tso->data = skb->data + hdr_len;
+	if ((tso->size == 0) &&
+	    (tso->next_frag_idx < skb_shinfo(skb)->nr_frags)) {
+		skb_frag_t *frag = &skb_shinfo(skb)->frags[tso->next_frag_idx];
+
+		/* Move to next segment */
+		tso->size = frag->size;
+		tso->data = page_address(frag->page.p) + frag->page_offset;
+		tso->next_frag_idx++;
+	}
+}
+EXPORT_SYMBOL(tso_start);

net/core/utils.c

@@ -0,0 +1,387 @@
+/*
+ *	Generic address resultion entity
+ *
+ *	Authors:
+ *	net_random Alan Cox
+ *	net_ratelimit Andi Kleen
+ *	in{4,6}_pton YOSHIFUJI Hideaki, Copyright (C)2006 USAGI/WIDE Project
+ *
+ *	Created by Alexey Kuznetsov <kuznet@ms2.inr.ac.ru>
+ *
+ *	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; either version
+ *      2 of the License, or (at your option) any later version.
+ */
+
+#include <linux/module.h>
+#include <linux/jiffies.h>
+#include <linux/kernel.h>
+#include <linux/ctype.h>
+#include <linux/inet.h>
+#include <linux/mm.h>
+#include <linux/net.h>
+#include <linux/string.h>
+#include <linux/types.h>
+#include <linux/percpu.h>
+#include <linux/init.h>
+#include <linux/ratelimit.h>
+
+#include <net/sock.h>
+#include <net/net_ratelimit.h>
+
+#include <asm/byteorder.h>
+#include <asm/uaccess.h>
+
+int net_msg_warn __read_mostly = 1;
+EXPORT_SYMBOL(net_msg_warn);
+
+DEFINE_RATELIMIT_STATE(net_ratelimit_state, 5 * HZ, 10);
+/*
+ * All net warning printk()s should be guarded by this function.
+ */
+int net_ratelimit(void)
+{
+	return __ratelimit(&net_ratelimit_state);
+}
+EXPORT_SYMBOL(net_ratelimit);
+
+/*
+ * Convert an ASCII string to binary IP.
+ * This is outside of net/ipv4/ because various code that uses IP addresses
+ * is otherwise not dependent on the TCP/IP stack.
+ */
+
+__be32 in_aton(const char *str)
+{
+	unsigned long l;
+	unsigned int val;
+	int i;
+
+	l = 0;
+	for (i = 0; i < 4; i++)	{
+		l <<= 8;
+		if (*str != '\0') {
+			val = 0;
+			while (*str != '\0' && *str != '.' && *str != '\n') {
+				val *= 10;
+				val += *str - '0';
+				str++;
+			}
+			l |= val;
+			if (*str != '\0')
+				str++;
+		}
+	}
+	return htonl(l);
+}
+EXPORT_SYMBOL(in_aton);
+
+#define IN6PTON_XDIGIT		0x00010000
+#define IN6PTON_DIGIT		0x00020000
+#define IN6PTON_COLON_MASK	0x00700000
+#define IN6PTON_COLON_1		0x00100000	/* single : requested */
+#define IN6PTON_COLON_2		0x00200000	/* second : requested */
+#define IN6PTON_COLON_1_2	0x00400000	/* :: requested */
+#define IN6PTON_DOT		0x00800000	/* . */
+#define IN6PTON_DELIM		0x10000000
+#define IN6PTON_NULL		0x20000000	/* first/tail */
+#define IN6PTON_UNKNOWN		0x40000000
+
+static inline int xdigit2bin(char c, int delim)
+{
+	int val;
+
+	if (c == delim || c == '\0')
+		return IN6PTON_DELIM;
+	if (c == ':')
+		return IN6PTON_COLON_MASK;
+	if (c == '.')
+		return IN6PTON_DOT;
+
+	val = hex_to_bin(c);
+	if (val >= 0)
+		return val | IN6PTON_XDIGIT | (val < 10 ? IN6PTON_DIGIT : 0);
+
+	if (delim == -1)
+		return IN6PTON_DELIM;
+	return IN6PTON_UNKNOWN;
+}
+
+/**
+ * in4_pton - convert an IPv4 address from literal to binary representation
+ * @src: the start of the IPv4 address string
+ * @srclen: the length of the string, -1 means strlen(src)
+ * @dst: the binary (u8[4] array) representation of the IPv4 address
+ * @delim: the delimiter of the IPv4 address in @src, -1 means no delimiter
+ * @end: A pointer to the end of the parsed string will be placed here
+ *
+ * Return one on success, return zero when any error occurs
+ * and @end will point to the end of the parsed string.
+ *
+ */
+int in4_pton(const char *src, int srclen,
+	     u8 *dst,
+	     int delim, const char **end)
+{
+	const char *s;
+	u8 *d;
+	u8 dbuf[4];
+	int ret = 0;
+	int i;
+	int w = 0;
+
+	if (srclen < 0)
+		srclen = strlen(src);
+	s = src;
+	d = dbuf;
+	i = 0;
+	while(1) {
+		int c;
+		c = xdigit2bin(srclen > 0 ? *s : '\0', delim);
+		if (!(c & (IN6PTON_DIGIT | IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK))) {
+			goto out;
+		}
+		if (c & (IN6PTON_DOT | IN6PTON_DELIM | IN6PTON_COLON_MASK)) {
+			if (w == 0)
+				goto out;
+			*d++ = w & 0xff;
+			w = 0;
+			i++;
+			if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) {
+				if (i != 4)
+					goto out;
+				break;
+			}
+			goto cont;
+		}
+		w = (w * 10) + c;
+		if ((w & 0xffff) > 255) {
+			goto out;
+		}
+cont:
+		if (i >= 4)
+			goto out;
+		s++;
+		srclen--;
+	}
+	ret = 1;
+	memcpy(dst, dbuf, sizeof(dbuf));
+out:
+	if (end)
+		*end = s;
+	return ret;
+}
+EXPORT_SYMBOL(in4_pton);
+
+/**
+ * in6_pton - convert an IPv6 address from literal to binary representation
+ * @src: the start of the IPv6 address string
+ * @srclen: the length of the string, -1 means strlen(src)
+ * @dst: the binary (u8[16] array) representation of the IPv6 address
+ * @delim: the delimiter of the IPv6 address in @src, -1 means no delimiter
+ * @end: A pointer to the end of the parsed string will be placed here
+ *
+ * Return one on success, return zero when any error occurs
+ * and @end will point to the end of the parsed string.
+ *
+ */
+int in6_pton(const char *src, int srclen,
+	     u8 *dst,
+	     int delim, const char **end)
+{
+	const char *s, *tok = NULL;
+	u8 *d, *dc = NULL;
+	u8 dbuf[16];
+	int ret = 0;
+	int i;
+	int state = IN6PTON_COLON_1_2 | IN6PTON_XDIGIT | IN6PTON_NULL;
+	int w = 0;
+
+	memset(dbuf, 0, sizeof(dbuf));
+
+	s = src;
+	d = dbuf;
+	if (srclen < 0)
+		srclen = strlen(src);
+
+	while (1) {
+		int c;
+
+		c = xdigit2bin(srclen > 0 ? *s : '\0', delim);
+		if (!(c & state))
+			goto out;
+		if (c & (IN6PTON_DELIM | IN6PTON_COLON_MASK)) {
+			/* process one 16-bit word */
+			if (!(state & IN6PTON_NULL)) {
+				*d++ = (w >> 8) & 0xff;
+				*d++ = w & 0xff;
+			}
+			w = 0;
+			if (c & IN6PTON_DELIM) {
+				/* We've processed last word */
+				break;
+			}
+			/*
+			 * COLON_1 => XDIGIT
+			 * COLON_2 => XDIGIT|DELIM
+			 * COLON_1_2 => COLON_2
+			 */
+			switch (state & IN6PTON_COLON_MASK) {
+			case IN6PTON_COLON_2:
+				dc = d;
+				state = IN6PTON_XDIGIT | IN6PTON_DELIM;
+				if (dc - dbuf >= sizeof(dbuf))
+					state |= IN6PTON_NULL;
+				break;
+			case IN6PTON_COLON_1|IN6PTON_COLON_1_2:
+				state = IN6PTON_XDIGIT | IN6PTON_COLON_2;
+				break;
+			case IN6PTON_COLON_1:
+				state = IN6PTON_XDIGIT;
+				break;
+			case IN6PTON_COLON_1_2:
+				state = IN6PTON_COLON_2;
+				break;
+			default:
+				state = 0;
+			}
+			tok = s + 1;
+			goto cont;
+		}
+
+		if (c & IN6PTON_DOT) {
+			ret = in4_pton(tok ? tok : s, srclen + (int)(s - tok), d, delim, &s);
+			if (ret > 0) {
+				d += 4;
+				break;
+			}
+			goto out;
+		}
+
+		w = (w << 4) | (0xff & c);
+		state = IN6PTON_COLON_1 | IN6PTON_DELIM;
+		if (!(w & 0xf000)) {
+			state |= IN6PTON_XDIGIT;
+		}
+		if (!dc && d + 2 < dbuf + sizeof(dbuf)) {
+			state |= IN6PTON_COLON_1_2;
+			state &= ~IN6PTON_DELIM;
+		}
+		if (d + 2 >= dbuf + sizeof(dbuf)) {
+			state &= ~(IN6PTON_COLON_1|IN6PTON_COLON_1_2);
+		}
+cont:
+		if ((dc && d + 4 < dbuf + sizeof(dbuf)) ||
+		    d + 4 == dbuf + sizeof(dbuf)) {
+			state |= IN6PTON_DOT;
+		}
+		if (d >= dbuf + sizeof(dbuf)) {
+			state &= ~(IN6PTON_XDIGIT|IN6PTON_COLON_MASK);
+		}
+		s++;
+		srclen--;
+	}
+
+	i = 15; d--;
+
+	if (dc) {
+		while(d >= dc)
+			dst[i--] = *d--;
+		while(i >= dc - dbuf)
+			dst[i--] = 0;
+		while(i >= 0)
+			dst[i--] = *d--;
+	} else
+		memcpy(dst, dbuf, sizeof(dbuf));
+
+	ret = 1;
+out:
+	if (end)
+		*end = s;
+	return ret;
+}
+EXPORT_SYMBOL(in6_pton);
+
+void inet_proto_csum_replace4(__sum16 *sum, struct sk_buff *skb,
+			      __be32 from, __be32 to, int pseudohdr)
+{
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		*sum = csum_fold(csum_add(csum_sub(~csum_unfold(*sum), from),
+				 to));
+		if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
+			skb->csum = ~csum_add(csum_sub(~(skb->csum), from), to);
+	} else if (pseudohdr)
+		*sum = ~csum_fold(csum_add(csum_sub(csum_unfold(*sum), from),
+				  to));
+}
+EXPORT_SYMBOL(inet_proto_csum_replace4);
+
+void inet_proto_csum_replace16(__sum16 *sum, struct sk_buff *skb,
+			       const __be32 *from, const __be32 *to,
+			       int pseudohdr)
+{
+	__be32 diff[] = {
+		~from[0], ~from[1], ~from[2], ~from[3],
+		to[0], to[1], to[2], to[3],
+	};
+	if (skb->ip_summed != CHECKSUM_PARTIAL) {
+		*sum = csum_fold(csum_partial(diff, sizeof(diff),
+				 ~csum_unfold(*sum)));
+		if (skb->ip_summed == CHECKSUM_COMPLETE && pseudohdr)
+			skb->csum = ~csum_partial(diff, sizeof(diff),
+						  ~skb->csum);
+	} else if (pseudohdr)
+		*sum = ~csum_fold(csum_partial(diff, sizeof(diff),
+				  csum_unfold(*sum)));
+}
+EXPORT_SYMBOL(inet_proto_csum_replace16);
+
+struct __net_random_once_work {
+	struct work_struct work;
+	struct static_key *key;
+};
+
+static void __net_random_once_deferred(struct work_struct *w)
+{
+	struct __net_random_once_work *work =
+		container_of(w, struct __net_random_once_work, work);
+	BUG_ON(!static_key_enabled(work->key));
+	static_key_slow_dec(work->key);
+	kfree(work);
+}
+
+static void __net_random_once_disable_jump(struct static_key *key)
+{
+	struct __net_random_once_work *w;
+
+	w = kmalloc(sizeof(*w), GFP_ATOMIC);
+	if (!w)
+		return;
+
+	INIT_WORK(&w->work, __net_random_once_deferred);
+	w->key = key;
+	schedule_work(&w->work);
+}
+
+bool __net_get_random_once(void *buf, int nbytes, bool *done,
+			   struct static_key *once_key)
+{
+	static DEFINE_SPINLOCK(lock);
+	unsigned long flags;
+
+	spin_lock_irqsave(&lock, flags);
+	if (*done) {
+		spin_unlock_irqrestore(&lock, flags);
+		return false;
+	}
+
+	get_random_bytes(buf, nbytes);
+	*done = true;
+	spin_unlock_irqrestore(&lock, flags);
+
+	__net_random_once_disable_jump(once_key);
+
+	return true;
+}
+EXPORT_SYMBOL(__net_get_random_once);