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

Pull tracing fixes from Steven Rostedt:

 - Fix error output of boot instance creation failure

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

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

 - Fix use-after-free for same named historgrams

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

   Free the duplicate variables along with the duplicated histogram
   data.

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

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

 - Fix race between reading trace_pipe and updating subbuffer size

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

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

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

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

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

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

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

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

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

 - Fix retry exhaustion in simple ring buffer reader swap

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

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

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

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

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

1 files changed, 1300 insertions, 0 deletions

diff --git a/drivers/net/ppp/pppoe.c b/drivers/net/ppp/pppoe.c
new file mode 100644
index 000000000..bf7414b46
--- /dev/null
+++ b/drivers/net/ppp/pppoe.c
@@ -0,0 +1,1300 @@
+// SPDX-License-Identifier: GPL-2.0-or-later
+/** -*- linux-c -*- ***********************************************************
+ * Linux PPP over Ethernet (PPPoX/PPPoE) Sockets
+ *
+ * PPPoX --- Generic PPP encapsulation socket family
+ * PPPoE --- PPP over Ethernet (RFC 2516)
+ *
+ * Version:	0.7.0
+ *
+ * 070228 :	Fix to allow multiple sessions with same remote MAC and same
+ *		session id by including the local device ifindex in the
+ *		tuple identifying a session. This also ensures packets can't
+ *		be injected into a session from interfaces other than the one
+ *		specified by userspace. Florian Zumbiehl <florz@florz.de>
+ *		(Oh, BTW, this one is YYMMDD, in case you were wondering ...)
+ * 220102 :	Fix module use count on failure in pppoe_create, pppox_sk -acme
+ * 030700 :	Fixed connect logic to allow for disconnect.
+ * 270700 :	Fixed potential SMP problems; we must protect against
+ *		simultaneous invocation of ppp_input
+ *		and ppp_unregister_channel.
+ * 040800 :	Respect reference count mechanisms on net-devices.
+ * 200800 :	fix kfree(skb) in pppoe_rcv (acme)
+ *		Module reference count is decremented in the right spot now,
+ *		guards against sock_put not actually freeing the sk
+ *		in pppoe_release.
+ * 051000 :	Initialization cleanup.
+ * 111100 :	Fix recvmsg.
+ * 050101 :	Fix PADT processing.
+ * 140501 :	Use pppoe_rcv_core to handle all backlog. (Alexey)
+ * 170701 :	Do not lock_sock with rwlock held. (DaveM)
+ *		Ignore discovery frames if user has socket
+ *		locked. (DaveM)
+ *		Ignore return value of dev_queue_xmit in __pppoe_xmit
+ *		or else we may kfree an SKB twice. (DaveM)
+ * 190701 :	When doing copies of skb's in __pppoe_xmit, always delete
+ *		the original skb that was passed in on success, never on
+ *		failure.  Delete the copy of the skb on failure to avoid
+ *		a memory leak.
+ * 081001 :	Misc. cleanup (licence string, non-blocking, prevent
+ *		reference of device on close).
+ * 121301 :	New ppp channels interface; cannot unregister a channel
+ *		from interrupts.  Thus, we mark the socket as a ZOMBIE
+ *		and do the unregistration later.
+ * 081002 :	seq_file support for proc stuff -acme
+ * 111602 :	Merge all 2.4 fixes into 2.5/2.6 tree.  Label 2.5/2.6
+ *		as version 0.7.  Spacing cleanup.
+ * Author:	Michal Ostrowski <mostrows@speakeasy.net>
+ * Contributors:
+ * 		Arnaldo Carvalho de Melo <acme@conectiva.com.br>
+ *		David S. Miller (davem@redhat.com)
+ *
+ * License:
+ */
+
+#include <linux/string.h>
+#include <linux/module.h>
+#include <linux/kernel.h>
+#include <linux/slab.h>
+#include <linux/errno.h>
+#include <linux/netdevice.h>
+#include <linux/net.h>
+#include <linux/inetdevice.h>
+#include <linux/etherdevice.h>
+#include <linux/skbuff.h>
+#include <linux/init.h>
+#include <linux/if_ether.h>
+#include <linux/if_pppox.h>
+#include <linux/ppp_channel.h>
+#include <linux/ppp_defs.h>
+#include <linux/ppp-ioctl.h>
+#include <linux/notifier.h>
+#include <linux/file.h>
+#include <linux/proc_fs.h>
+#include <linux/seq_file.h>
+
+#include <linux/nsproxy.h>
+#include <net/net_namespace.h>
+#include <net/netns/generic.h>
+#include <net/sock.h>
+#include <net/gro.h>
+
+#include <linux/uaccess.h>
+
+#define PPPOE_HASH_BITS CONFIG_PPPOE_HASH_BITS
+#define PPPOE_HASH_SIZE (1 << PPPOE_HASH_BITS)
+#define PPPOE_HASH_MASK	(PPPOE_HASH_SIZE - 1)
+
+static const struct proto_ops pppoe_ops;
+static const struct ppp_channel_ops pppoe_chan_ops;
+
+/* per-net private data for this module */
+static unsigned int pppoe_net_id __read_mostly;
+struct pppoe_net {
+	/*
+	 * we could use _single_ hash table for all
+	 * nets by injecting net id into the hash but
+	 * it would increase hash chains and add
+	 * a few additional math comparisons messy
+	 * as well, moreover in case of SMP less locking
+	 * controversy here
+	 */
+	struct pppox_sock __rcu *hash_table[PPPOE_HASH_SIZE];
+	spinlock_t hash_lock;
+};
+
+/*
+ * PPPoE could be in the following stages:
+ * 1) Discovery stage (to obtain remote MAC and Session ID)
+ * 2) Session stage (MAC and SID are known)
+ *
+ * Ethernet frames have a special tag for this but
+ * we use simpler approach based on session id
+ */
+static inline bool stage_session(__be16 sid)
+{
+	return sid != 0;
+}
+
+static inline struct pppoe_net *pppoe_pernet(struct net *net)
+{
+	return net_generic(net, pppoe_net_id);
+}
+
+static inline int cmp_2_addr(struct pppoe_addr *a, struct pppoe_addr *b)
+{
+	return a->sid == b->sid && ether_addr_equal(a->remote, b->remote);
+}
+
+static inline int cmp_addr(struct pppoe_addr *a, __be16 sid, char *addr)
+{
+	return a->sid == sid && ether_addr_equal(a->remote, addr);
+}
+
+#if 8 % PPPOE_HASH_BITS
+#error 8 must be a multiple of PPPOE_HASH_BITS
+#endif
+
+static u8 hash_item(__be16 sid, const u8 addr[ETH_ALEN])
+{
+	const u16 *addr16 = (const u16 *)addr;
+	unsigned int i;
+	u16 hash16;
+	u8 hash;
+
+	hash16 = addr16[0] ^ addr16[1] ^ addr16[2] ^ (__force u16)sid;
+	hash = (hash16 >> 8) ^ hash16;
+	for (i = 8; (i >>= 1) >= PPPOE_HASH_BITS;)
+		hash ^= hash >> i;
+
+	return hash & PPPOE_HASH_MASK;
+}
+
+/**********************************************************************
+ *
+ *  Set/get/delete/rehash items  (internal versions)
+ *
+ **********************************************************************/
+static struct pppox_sock *__get_item(struct pppoe_net *pn, __be16 sid,
+				unsigned char *addr, int ifindex)
+{
+	int hash = hash_item(sid, addr);
+	struct pppox_sock *ret;
+
+	ret = rcu_dereference(pn->hash_table[hash]);
+	while (ret) {
+		if (cmp_addr(&ret->pppoe_pa, sid, addr) &&
+		    ret->pppoe_ifindex == ifindex)
+			return ret;
+
+		ret = rcu_dereference(ret->next);
+	}
+
+	return NULL;
+}
+
+static int __set_item(struct pppoe_net *pn, struct pppox_sock *po)
+{
+	int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);
+	struct pppox_sock *ret, *first;
+
+	first = rcu_dereference_protected(pn->hash_table[hash], lockdep_is_held(&pn->hash_lock));
+	ret = first;
+	while (ret) {
+		if (cmp_2_addr(&ret->pppoe_pa, &po->pppoe_pa) &&
+		    ret->pppoe_ifindex == po->pppoe_ifindex)
+			return -EALREADY;
+
+		ret = rcu_dereference_protected(ret->next, lockdep_is_held(&pn->hash_lock));
+	}
+
+	RCU_INIT_POINTER(po->next, first);
+	rcu_assign_pointer(pn->hash_table[hash], po);
+
+	return 0;
+}
+
+static void __delete_item(struct pppoe_net *pn, __be16 sid,
+					char *addr, int ifindex)
+{
+	int hash = hash_item(sid, addr);
+	struct pppox_sock *ret, __rcu **src;
+
+	ret = rcu_dereference_protected(pn->hash_table[hash], lockdep_is_held(&pn->hash_lock));
+	src = &pn->hash_table[hash];
+
+	while (ret) {
+		if (cmp_addr(&ret->pppoe_pa, sid, addr) &&
+		    ret->pppoe_ifindex == ifindex) {
+			struct pppox_sock *next;
+
+			next = rcu_dereference_protected(ret->next,
+							 lockdep_is_held(&pn->hash_lock));
+			rcu_assign_pointer(*src, next);
+			break;
+		}
+
+		src = &ret->next;
+		ret = rcu_dereference_protected(ret->next, lockdep_is_held(&pn->hash_lock));
+	}
+}
+
+/**********************************************************************
+ *
+ *  Set/get/delete/rehash items
+ *
+ **********************************************************************/
+static inline struct pppox_sock *get_item(struct pppoe_net *pn, __be16 sid,
+					unsigned char *addr, int ifindex)
+{
+	struct pppox_sock *po;
+
+	po = __get_item(pn, sid, addr, ifindex);
+	if (po && !refcount_inc_not_zero(&po->sk.sk_refcnt))
+		po = NULL;
+
+	return po;
+}
+
+static inline void delete_item(struct pppoe_net *pn, __be16 sid,
+					char *addr, int ifindex)
+{
+	spin_lock(&pn->hash_lock);
+	__delete_item(pn, sid, addr, ifindex);
+	spin_unlock(&pn->hash_lock);
+}
+
+/***************************************************************************
+ *
+ *  Handler for device events.
+ *  Certain device events require that sockets be unconnected.
+ *
+ **************************************************************************/
+
+static void pppoe_flush_dev(struct net_device *dev)
+{
+	struct pppoe_net *pn;
+	int i;
+
+	pn = pppoe_pernet(dev_net(dev));
+	spin_lock(&pn->hash_lock);
+	for (i = 0; i < PPPOE_HASH_SIZE; i++) {
+		struct pppox_sock *po = rcu_dereference_protected(pn->hash_table[i],
+								  lockdep_is_held(&pn->hash_lock));
+		struct sock *sk;
+
+		while (po) {
+			while (po && po->pppoe_dev != dev) {
+				po = rcu_dereference_protected(po->next,
+							       lockdep_is_held(&pn->hash_lock));
+			}
+
+			if (!po)
+				break;
+
+			sk = &po->sk;
+
+			/* We always grab the socket lock, followed by the
+			 * hash_lock, in that order.  Since we should hold the
+			 * sock lock while doing any unbinding, we need to
+			 * release the lock we're holding.  Hold a reference to
+			 * the sock so it doesn't disappear as we're jumping
+			 * between locks.
+			 */
+
+			sock_hold(sk);
+			spin_unlock(&pn->hash_lock);
+			lock_sock(sk);
+
+			if (po->pppoe_dev == dev &&
+			    sk->sk_state & (PPPOX_CONNECTED | PPPOX_BOUND)) {
+				pppox_unbind_sock(sk);
+				sk->sk_state_change(sk);
+				po->pppoe_dev = NULL;
+				dev_put(dev);
+			}
+
+			release_sock(sk);
+			sock_put(sk);
+
+			/* Restart the process from the start of the current
+			 * hash chain. We dropped locks so the world may have
+			 * change from underneath us.
+			 */
+
+			BUG_ON(pppoe_pernet(dev_net(dev)) == NULL);
+			spin_lock(&pn->hash_lock);
+			po = rcu_dereference_protected(pn->hash_table[i],
+						       lockdep_is_held(&pn->hash_lock));
+		}
+	}
+	spin_unlock(&pn->hash_lock);
+}
+
+static int pppoe_device_event(struct notifier_block *this,
+			      unsigned long event, void *ptr)
+{
+	struct net_device *dev = netdev_notifier_info_to_dev(ptr);
+
+	/* Only look at sockets that are using this specific device. */
+	switch (event) {
+	case NETDEV_CHANGEADDR:
+	case NETDEV_CHANGEMTU:
+		/* A change in mtu or address is a bad thing, requiring
+		 * LCP re-negotiation.
+		 */
+
+	case NETDEV_GOING_DOWN:
+	case NETDEV_DOWN:
+		/* Find every socket on this device and kill it. */
+		pppoe_flush_dev(dev);
+		break;
+
+	default:
+		break;
+	}
+
+	return NOTIFY_DONE;
+}
+
+static struct notifier_block pppoe_notifier = {
+	.notifier_call = pppoe_device_event,
+};
+
+/************************************************************************
+ *
+ * Do the real work of receiving a PPPoE Session frame.
+ *
+ ***********************************************************************/
+static int pppoe_rcv_core(struct sock *sk, struct sk_buff *skb)
+{
+	struct pppox_sock *po = pppox_sk(sk);
+
+	/* Backlog receive. Semantics of backlog rcv preclude any code from
+	 * executing in lock_sock()/release_sock() bounds; meaning sk->sk_state
+	 * can't change.
+	 */
+
+	if (sk->sk_state & PPPOX_BOUND) {
+		ppp_input(&po->chan, skb);
+	} else {
+		if (sock_queue_rcv_skb(sk, skb))
+			goto abort_kfree;
+	}
+
+	return NET_RX_SUCCESS;
+
+abort_kfree:
+	kfree_skb(skb);
+	return NET_RX_DROP;
+}
+
+/************************************************************************
+ *
+ * Receive wrapper called in BH context.
+ *
+ ***********************************************************************/
+static int pppoe_rcv(struct sk_buff *skb, struct net_device *dev,
+		     struct packet_type *pt, struct net_device *orig_dev)
+{
+	struct pppoe_hdr *ph;
+	struct pppox_sock *po;
+	struct pppoe_net *pn;
+	int len;
+
+	if (skb->pkt_type == PACKET_OTHERHOST)
+		goto drop;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		goto out;
+
+	if (skb_mac_header_len(skb) < ETH_HLEN)
+		goto drop;
+
+	if (!pskb_may_pull(skb, PPPOE_SES_HLEN))
+		goto drop;
+
+	ph = pppoe_hdr(skb);
+	len = ntohs(ph->length);
+
+	skb_pull_rcsum(skb, sizeof(*ph));
+	if (skb->len < len)
+		goto drop;
+
+	/* skb->data points to the PPP protocol header after skb_pull_rcsum.
+	 * Drop PFC frames.
+	 */
+	if (ppp_skb_is_compressed_proto(skb))
+		goto drop;
+
+	if (!skb_is_gso(skb) && pskb_trim_rcsum(skb, len))
+		goto drop;
+
+	ph = pppoe_hdr(skb);
+	pn = pppoe_pernet(dev_net(dev));
+
+	po = __get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
+	if (!po)
+		goto drop;
+
+	return __sk_receive_skb(&po->sk, skb, 0, 1, false);
+
+drop:
+	kfree_skb(skb);
+out:
+	return NET_RX_DROP;
+}
+
+static void pppoe_unbind_sock_work(struct work_struct *work)
+{
+	struct pppox_sock *po = container_of(work, struct pppox_sock,
+					     proto.pppoe.padt_work);
+	struct sock *sk = &po->sk;
+
+	lock_sock(sk);
+	if (po->pppoe_dev) {
+		dev_put(po->pppoe_dev);
+		po->pppoe_dev = NULL;
+	}
+	pppox_unbind_sock(sk);
+	release_sock(sk);
+	sock_put(sk);
+}
+
+/************************************************************************
+ *
+ * Receive a PPPoE Discovery frame.
+ * This is solely for detection of PADT frames
+ *
+ ***********************************************************************/
+static int pppoe_disc_rcv(struct sk_buff *skb, struct net_device *dev,
+			  struct packet_type *pt, struct net_device *orig_dev)
+
+{
+	struct pppoe_hdr *ph;
+	struct pppox_sock *po;
+	struct pppoe_net *pn;
+
+	skb = skb_share_check(skb, GFP_ATOMIC);
+	if (!skb)
+		goto out;
+
+	if (skb->pkt_type != PACKET_HOST)
+		goto abort;
+
+	if (!pskb_may_pull(skb, sizeof(struct pppoe_hdr)))
+		goto abort;
+
+	ph = pppoe_hdr(skb);
+	if (ph->code != PADT_CODE)
+		goto abort;
+
+	pn = pppoe_pernet(dev_net(dev));
+	po = get_item(pn, ph->sid, eth_hdr(skb)->h_source, dev->ifindex);
+	if (po)
+		if (!schedule_work(&po->proto.pppoe.padt_work))
+			sock_put(&po->sk);
+
+abort:
+	kfree_skb(skb);
+out:
+	return NET_RX_SUCCESS; /* Lies... :-) */
+}
+
+static struct packet_type pppoes_ptype __read_mostly = {
+	.type	= cpu_to_be16(ETH_P_PPP_SES),
+	.func	= pppoe_rcv,
+};
+
+static struct packet_type pppoed_ptype __read_mostly = {
+	.type	= cpu_to_be16(ETH_P_PPP_DISC),
+	.func	= pppoe_disc_rcv,
+};
+
+static struct proto pppoe_sk_proto __read_mostly = {
+	.name	  = "PPPOE",
+	.owner	  = THIS_MODULE,
+	.obj_size = sizeof(struct pppox_sock),
+};
+
+static void pppoe_destruct(struct sock *sk)
+{
+	skb_queue_purge(&sk->sk_receive_queue);
+}
+
+/***********************************************************************
+ *
+ * Initialize a new struct sock.
+ *
+ **********************************************************************/
+static int pppoe_create(struct net *net, struct socket *sock, int kern)
+{
+	struct sock *sk;
+
+	sk = sk_alloc(net, PF_PPPOX, GFP_KERNEL, &pppoe_sk_proto, kern);
+	if (!sk)
+		return -ENOMEM;
+
+	sock_init_data(sock, sk);
+	sock_set_flag(sk, SOCK_RCU_FREE);
+
+	sock->state	= SS_UNCONNECTED;
+	sock->ops	= &pppoe_ops;
+
+	sk->sk_backlog_rcv	= pppoe_rcv_core;
+	sk->sk_destruct		= pppoe_destruct;
+	sk->sk_state		= PPPOX_NONE;
+	sk->sk_type		= SOCK_STREAM;
+	sk->sk_family		= PF_PPPOX;
+	sk->sk_protocol		= PX_PROTO_OE;
+
+	INIT_WORK(&pppox_sk(sk)->proto.pppoe.padt_work,
+		  pppoe_unbind_sock_work);
+
+	return 0;
+}
+
+static int pppoe_release(struct socket *sock)
+{
+	struct sock *sk = sock->sk;
+	struct pppox_sock *po;
+	struct pppoe_net *pn;
+	struct net *net = NULL;
+
+	if (!sk)
+		return 0;
+
+	lock_sock(sk);
+	if (sock_flag(sk, SOCK_DEAD)) {
+		release_sock(sk);
+		return -EBADF;
+	}
+
+	po = pppox_sk(sk);
+
+	if (po->pppoe_dev) {
+		dev_put(po->pppoe_dev);
+		po->pppoe_dev = NULL;
+	}
+
+	pppox_unbind_sock(sk);
+
+	/* Signal the death of the socket. */
+	sk->sk_state = PPPOX_DEAD;
+
+	net = sock_net(sk);
+	pn = pppoe_pernet(net);
+
+	/*
+	 * protect "po" from concurrent updates
+	 * on pppoe_flush_dev
+	 */
+	delete_item(pn, po->pppoe_pa.sid, po->pppoe_pa.remote,
+		    po->pppoe_ifindex);
+
+	sock_orphan(sk);
+	sock->sk = NULL;
+
+	release_sock(sk);
+	sock_put(sk);
+
+	return 0;
+}
+
+static int pppoe_connect(struct socket *sock, struct sockaddr_unsized *uservaddr,
+			 int sockaddr_len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sockaddr_pppox *sp = (struct sockaddr_pppox *)uservaddr;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct net_device *dev = NULL;
+	struct pppoe_net *pn;
+	struct net *net = NULL;
+	int error;
+
+	lock_sock(sk);
+
+	error = -EINVAL;
+
+	if (sockaddr_len != sizeof(struct sockaddr_pppox))
+		goto end;
+
+	if (sp->sa_protocol != PX_PROTO_OE)
+		goto end;
+
+	/* Check for already bound sockets */
+	error = -EBUSY;
+	if ((sk->sk_state & PPPOX_CONNECTED) &&
+	     stage_session(sp->sa_addr.pppoe.sid))
+		goto end;
+
+	/* Check for already disconnected sockets, on attempts to disconnect */
+	error = -EALREADY;
+	if ((sk->sk_state & PPPOX_DEAD) &&
+	     !stage_session(sp->sa_addr.pppoe.sid))
+		goto end;
+
+	error = 0;
+
+	/* Delete the old binding */
+	if (stage_session(po->pppoe_pa.sid)) {
+		pppox_unbind_sock(sk);
+		pn = pppoe_pernet(sock_net(sk));
+		delete_item(pn, po->pppoe_pa.sid,
+			    po->pppoe_pa.remote, po->pppoe_ifindex);
+		if (po->pppoe_dev) {
+			dev_put(po->pppoe_dev);
+			po->pppoe_dev = NULL;
+		}
+
+		po->pppoe_ifindex = 0;
+		memset(&po->pppoe_pa, 0, sizeof(po->pppoe_pa));
+		memset(&po->chan, 0, sizeof(po->chan));
+		po->next = NULL;
+		po->num = 0;
+
+		sk->sk_state = PPPOX_NONE;
+	}
+
+	/* Re-bind in session stage only */
+	if (stage_session(sp->sa_addr.pppoe.sid)) {
+		error = -ENODEV;
+		net = sock_net(sk);
+		dev = dev_get_by_name(net, sp->sa_addr.pppoe.dev);
+		if (!dev)
+			goto err_put;
+
+		po->pppoe_dev = dev;
+		po->pppoe_ifindex = dev->ifindex;
+		pn = pppoe_pernet(net);
+		if (!(dev->flags & IFF_UP)) {
+			goto err_put;
+		}
+
+		memcpy(&po->pppoe_pa,
+		       &sp->sa_addr.pppoe,
+		       sizeof(struct pppoe_addr));
+
+		spin_lock(&pn->hash_lock);
+		error = __set_item(pn, po);
+		spin_unlock(&pn->hash_lock);
+		if (error < 0)
+			goto err_put;
+
+		po->chan.hdrlen = (sizeof(struct pppoe_hdr) +
+				   dev->hard_header_len);
+
+		po->chan.mtu = dev->mtu - sizeof(struct pppoe_hdr) - 2;
+		po->chan.private = sk;
+		po->chan.ops = &pppoe_chan_ops;
+		po->chan.direct_xmit = true;
+
+		error = ppp_register_net_channel(dev_net(dev), &po->chan);
+		if (error) {
+			delete_item(pn, po->pppoe_pa.sid,
+				    po->pppoe_pa.remote, po->pppoe_ifindex);
+			goto err_put;
+		}
+
+		sk->sk_state = PPPOX_CONNECTED;
+	}
+
+	po->num = sp->sa_addr.pppoe.sid;
+
+end:
+	release_sock(sk);
+	return error;
+err_put:
+	if (po->pppoe_dev) {
+		dev_put(po->pppoe_dev);
+		po->pppoe_dev = NULL;
+	}
+	goto end;
+}
+
+static int pppoe_getname(struct socket *sock, struct sockaddr *uaddr,
+		  int peer)
+{
+	int len = sizeof(struct sockaddr_pppox);
+	struct sockaddr_pppox sp;
+
+	sp.sa_family	= AF_PPPOX;
+	sp.sa_protocol	= PX_PROTO_OE;
+	memcpy(&sp.sa_addr.pppoe, &pppox_sk(sock->sk)->pppoe_pa,
+	       sizeof(struct pppoe_addr));
+
+	memcpy(uaddr, &sp, len);
+
+	return len;
+}
+
+static int pppoe_ioctl(struct socket *sock, unsigned int cmd,
+		unsigned long arg)
+{
+	struct sock *sk = sock->sk;
+	struct pppox_sock *po = pppox_sk(sk);
+	int val;
+	int err;
+
+	switch (cmd) {
+	case PPPIOCGMRU:
+		err = -ENXIO;
+		if (!(sk->sk_state & PPPOX_CONNECTED))
+			break;
+
+		err = -EFAULT;
+		if (put_user(po->pppoe_dev->mtu -
+			     sizeof(struct pppoe_hdr) -
+			     PPP_HDRLEN,
+			     (int __user *)arg))
+			break;
+		err = 0;
+		break;
+
+	case PPPIOCSMRU:
+		err = -ENXIO;
+		if (!(sk->sk_state & PPPOX_CONNECTED))
+			break;
+
+		err = -EFAULT;
+		if (get_user(val, (int __user *)arg))
+			break;
+
+		if (val < (po->pppoe_dev->mtu
+			   - sizeof(struct pppoe_hdr)
+			   - PPP_HDRLEN))
+			err = 0;
+		else
+			err = -EINVAL;
+		break;
+
+	case PPPIOCSFLAGS:
+		err = -EFAULT;
+		if (get_user(val, (int __user *)arg))
+			break;
+		err = 0;
+		break;
+
+	default:
+		err = -ENOTTY;
+	}
+
+	return err;
+}
+
+static int pppoe_sendmsg(struct socket *sock, struct msghdr *m,
+			 size_t total_len)
+{
+	struct sk_buff *skb;
+	struct sock *sk = sock->sk;
+	struct pppox_sock *po = pppox_sk(sk);
+	int error;
+	struct pppoe_hdr hdr;
+	struct pppoe_hdr *ph;
+	struct net_device *dev;
+	char *start;
+	int hlen;
+
+	lock_sock(sk);
+	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED)) {
+		error = -ENOTCONN;
+		goto end;
+	}
+
+	hdr.ver = 1;
+	hdr.type = 1;
+	hdr.code = 0;
+	hdr.sid = po->num;
+
+	dev = po->pppoe_dev;
+
+	error = -EMSGSIZE;
+	if (total_len > (dev->mtu + dev->hard_header_len))
+		goto end;
+
+	hlen = LL_RESERVED_SPACE(dev);
+	skb = sock_wmalloc(sk, hlen + sizeof(*ph) + total_len +
+			   dev->needed_tailroom, 0, GFP_KERNEL);
+	if (!skb) {
+		error = -ENOMEM;
+		goto end;
+	}
+
+	/* Reserve space for headers. */
+	skb_reserve(skb, hlen);
+	skb_reset_network_header(skb);
+
+	skb->dev = dev;
+
+	skb->priority = READ_ONCE(sk->sk_priority);
+	skb->protocol = cpu_to_be16(ETH_P_PPP_SES);
+
+	ph = skb_put(skb, total_len + sizeof(struct pppoe_hdr));
+	start = (char *)ph + sizeof(*ph);
+
+	error = memcpy_from_msg(start, m, total_len);
+	if (error < 0) {
+		kfree_skb(skb);
+		goto end;
+	}
+
+	error = total_len;
+	dev_hard_header(skb, dev, ETH_P_PPP_SES,
+			po->pppoe_pa.remote, NULL, total_len);
+
+	ph = pppoe_hdr(skb);
+	memcpy(ph, &hdr, sizeof(struct pppoe_hdr));
+
+	ph->length = htons(total_len);
+
+	dev_queue_xmit(skb);
+
+end:
+	release_sock(sk);
+	return error;
+}
+
+/************************************************************************
+ *
+ * xmit function called by generic PPP driver
+ * sends PPP frame over PPPoE socket
+ *
+ ***********************************************************************/
+static int pppoe_xmit(struct ppp_channel *chan, struct sk_buff *skb)
+{
+	struct sock *sk = chan->private;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct net_device *dev = po->pppoe_dev;
+	struct pppoe_hdr *ph;
+	int data_len = skb->len;
+
+	/* The higher-level PPP code (ppp_unregister_channel()) ensures the PPP
+	 * xmit operations conclude prior to an unregistration call.  Thus
+	 * sk->sk_state cannot change, so we don't need to do lock_sock().
+	 * But, we also can't do a lock_sock since that introduces a potential
+	 * deadlock as we'd reverse the lock ordering used when calling
+	 * ppp_unregister_channel().
+	 */
+
+	if (sock_flag(sk, SOCK_DEAD) || !(sk->sk_state & PPPOX_CONNECTED))
+		goto abort;
+
+	if (!dev)
+		goto abort;
+
+	/* Copy the data if there is no space for the header or if it's
+	 * read-only.
+	 */
+	if (skb_cow_head(skb, LL_RESERVED_SPACE(dev) + sizeof(*ph)))
+		goto abort;
+
+	__skb_push(skb, sizeof(*ph));
+	skb_reset_network_header(skb);
+
+	ph = pppoe_hdr(skb);
+	ph->ver	= 1;
+	ph->type = 1;
+	ph->code = 0;
+	ph->sid	= po->num;
+	ph->length = htons(data_len);
+
+	skb->protocol = cpu_to_be16(ETH_P_PPP_SES);
+	skb->dev = dev;
+
+	dev_hard_header(skb, dev, ETH_P_PPP_SES,
+			po->pppoe_pa.remote, NULL, data_len);
+
+	dev_queue_xmit(skb);
+	return 1;
+
+abort:
+	kfree_skb(skb);
+	return 1;
+}
+
+static int pppoe_fill_forward_path(struct net_device_path_ctx *ctx,
+				   struct net_device_path *path,
+				   const struct ppp_channel *chan)
+{
+	struct sock *sk = chan->private;
+	struct pppox_sock *po = pppox_sk(sk);
+	struct net_device *dev = po->pppoe_dev;
+
+	if (sock_flag(sk, SOCK_DEAD) ||
+	    !(sk->sk_state & PPPOX_CONNECTED) || !dev)
+		return -1;
+
+	path->type = DEV_PATH_PPPOE;
+	path->encap.proto = htons(ETH_P_PPP_SES);
+	path->encap.id = be16_to_cpu(po->num);
+	memcpy(path->encap.h_dest, po->pppoe_pa.remote, ETH_ALEN);
+	memcpy(ctx->daddr, po->pppoe_pa.remote, ETH_ALEN);
+	path->dev = ctx->dev;
+	ctx->dev = dev;
+
+	return 0;
+}
+
+static const struct ppp_channel_ops pppoe_chan_ops = {
+	.start_xmit = pppoe_xmit,
+	.fill_forward_path = pppoe_fill_forward_path,
+};
+
+static int pppoe_recvmsg(struct socket *sock, struct msghdr *m,
+			 size_t total_len, int flags)
+{
+	struct sock *sk = sock->sk;
+	struct sk_buff *skb;
+	int error = 0;
+
+	if (sk->sk_state & PPPOX_BOUND)
+		return -EIO;
+
+	skb = skb_recv_datagram(sk, flags, &error);
+	if (!skb)
+		return error;
+
+	total_len = min_t(size_t, total_len, skb->len);
+	error = skb_copy_datagram_msg(skb, 0, m, total_len);
+	if (error == 0) {
+		consume_skb(skb);
+		return total_len;
+	}
+
+	kfree_skb(skb);
+	return error;
+}
+
+#ifdef CONFIG_PROC_FS
+static int pppoe_seq_show(struct seq_file *seq, void *v)
+{
+	struct pppox_sock *po;
+	char *dev_name;
+
+	if (v == SEQ_START_TOKEN) {
+		seq_puts(seq, "Id       Address              Device\n");
+		goto out;
+	}
+
+	po = v;
+	dev_name = po->pppoe_pa.dev;
+
+	seq_printf(seq, "%08X %pM %8s\n",
+		po->pppoe_pa.sid, po->pppoe_pa.remote, dev_name);
+out:
+	return 0;
+}
+
+static inline struct pppox_sock *pppoe_get_idx(struct pppoe_net *pn, loff_t pos)
+{
+	struct pppox_sock *po;
+	int i;
+
+	for (i = 0; i < PPPOE_HASH_SIZE; i++) {
+		po = rcu_dereference(pn->hash_table[i]);
+		while (po) {
+			if (!pos--)
+				goto out;
+			po = rcu_dereference(po->next);
+		}
+	}
+
+out:
+	return po;
+}
+
+static void *pppoe_seq_start(struct seq_file *seq, loff_t *pos)
+	__acquires(RCU)
+{
+	struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
+	loff_t l = *pos;
+
+	rcu_read_lock();
+	return l ? pppoe_get_idx(pn, --l) : SEQ_START_TOKEN;
+}
+
+static void *pppoe_seq_next(struct seq_file *seq, void *v, loff_t *pos)
+{
+	struct pppoe_net *pn = pppoe_pernet(seq_file_net(seq));
+	struct pppox_sock *po, *next;
+
+	++*pos;
+	if (v == SEQ_START_TOKEN) {
+		po = pppoe_get_idx(pn, 0);
+		goto out;
+	}
+	po = v;
+	next = rcu_dereference(po->next);
+	if (next)
+		po = next;
+	else {
+		int hash = hash_item(po->pppoe_pa.sid, po->pppoe_pa.remote);
+
+		po = NULL;
+		while (++hash < PPPOE_HASH_SIZE) {
+			po = rcu_dereference(pn->hash_table[hash]);
+			if (po)
+				break;
+		}
+	}
+
+out:
+	return po;
+}
+
+static void pppoe_seq_stop(struct seq_file *seq, void *v)
+	__releases(RCU)
+{
+	rcu_read_unlock();
+}
+
+static const struct seq_operations pppoe_seq_ops = {
+	.start		= pppoe_seq_start,
+	.next		= pppoe_seq_next,
+	.stop		= pppoe_seq_stop,
+	.show		= pppoe_seq_show,
+};
+#endif /* CONFIG_PROC_FS */
+
+static const struct proto_ops pppoe_ops = {
+	.family		= AF_PPPOX,
+	.owner		= THIS_MODULE,
+	.release	= pppoe_release,
+	.bind		= sock_no_bind,
+	.connect	= pppoe_connect,
+	.socketpair	= sock_no_socketpair,
+	.accept		= sock_no_accept,
+	.getname	= pppoe_getname,
+	.poll		= datagram_poll,
+	.listen		= sock_no_listen,
+	.shutdown	= sock_no_shutdown,
+	.sendmsg	= pppoe_sendmsg,
+	.recvmsg	= pppoe_recvmsg,
+	.mmap		= sock_no_mmap,
+	.ioctl		= pppox_ioctl,
+#ifdef CONFIG_COMPAT
+	.compat_ioctl	= pppox_compat_ioctl,
+#endif
+};
+
+static const struct pppox_proto pppoe_proto = {
+	.create	= pppoe_create,
+	.ioctl	= pppoe_ioctl,
+	.owner	= THIS_MODULE,
+};
+
+static __net_init int pppoe_init_net(struct net *net)
+{
+	struct pppoe_net *pn = pppoe_pernet(net);
+	struct proc_dir_entry *pde;
+
+	spin_lock_init(&pn->hash_lock);
+
+	pde = proc_create_net("pppoe", 0444, net->proc_net,
+			&pppoe_seq_ops, sizeof(struct seq_net_private));
+#ifdef CONFIG_PROC_FS
+	if (!pde)
+		return -ENOMEM;
+#endif
+
+	return 0;
+}
+
+static __net_exit void pppoe_exit_net(struct net *net)
+{
+	remove_proc_entry("pppoe", net->proc_net);
+}
+
+static struct pernet_operations pppoe_net_ops = {
+	.init = pppoe_init_net,
+	.exit = pppoe_exit_net,
+	.id   = &pppoe_net_id,
+	.size = sizeof(struct pppoe_net),
+};
+
+static u16
+compare_pppoe_header(const struct pppoe_hdr *phdr,
+		     const struct pppoe_hdr *phdr2)
+{
+	__be16 proto = *(const __be16 *)(phdr + 1);
+	__be16 proto2 = *(const __be16 *)(phdr2 + 1);
+
+	return (__force u16)((phdr->sid ^ phdr2->sid) | (proto ^ proto2));
+}
+
+static __be16 pppoe_hdr_proto(const struct pppoe_hdr *phdr)
+{
+	__be16 proto = *(const __be16 *)(phdr + 1);
+
+	switch (proto) {
+	case cpu_to_be16(PPP_IP):
+		return cpu_to_be16(ETH_P_IP);
+#if IS_ENABLED(CONFIG_IPV6)
+	case cpu_to_be16(PPP_IPV6):
+		return cpu_to_be16(ETH_P_IPV6);
+#endif
+	default:
+		return 0;
+	}
+}
+
+static struct sk_buff *pppoe_gro_receive(struct list_head *head,
+					 struct sk_buff *skb)
+{
+	const struct packet_offload *ptype;
+	unsigned int hlen, off_pppoe;
+	const struct pppoe_hdr *phdr;
+	struct sk_buff *pp = NULL;
+	struct sk_buff *p;
+	int flush = 1;
+	__be16 type;
+
+	off_pppoe = skb_gro_offset(skb);
+	hlen = off_pppoe + PPPOE_SES_HLEN;
+	phdr = skb_gro_header(skb, hlen, off_pppoe);
+	if (unlikely(!phdr))
+		goto out;
+
+	/* filter for session packets (type:1, ver:1, code:0) */
+	if (*(const __be16 *)phdr != cpu_to_be16(0x1100))
+		goto out;
+
+	/* ignore packets with padding or invalid length */
+	if (skb_gro_len(skb) != be16_to_cpu(phdr->length) + sizeof(*phdr))
+		goto out;
+
+	type = pppoe_hdr_proto(phdr);
+	ptype = gro_find_receive_by_type(type);
+	if (!ptype)
+		goto out;
+
+	flush = 0;
+
+	list_for_each_entry(p, head, list) {
+		const struct pppoe_hdr *phdr2;
+
+		if (!NAPI_GRO_CB(p)->same_flow)
+			continue;
+
+		phdr2 = (const struct pppoe_hdr *)(p->data + off_pppoe);
+		if (compare_pppoe_header(phdr, phdr2))
+			NAPI_GRO_CB(p)->same_flow = 0;
+	}
+
+	skb_gro_pull(skb, PPPOE_SES_HLEN);
+	skb_gro_postpull_rcsum(skb, phdr, PPPOE_SES_HLEN);
+
+	pp = indirect_call_gro_receive_inet(ptype->callbacks.gro_receive,
+					    ipv6_gro_receive, inet_gro_receive,
+					    head, skb);
+
+out:
+	skb_gro_flush_final(skb, pp, flush);
+
+	return pp;
+}
+
+static int pppoe_gro_complete(struct sk_buff *skb, int nhoff)
+{
+	struct pppoe_hdr *phdr = (struct pppoe_hdr *)(skb->data + nhoff);
+	__be16 type = pppoe_hdr_proto(phdr);
+	struct packet_offload *ptype;
+	unsigned int len;
+
+	ptype = gro_find_complete_by_type(type);
+	if (!ptype)
+		return -ENOENT;
+
+	len = skb->len - (nhoff + sizeof(*phdr));
+	len = min(len, 0xFFFFU);
+	phdr->length = cpu_to_be16(len);
+
+	return INDIRECT_CALL_INET(ptype->callbacks.gro_complete,
+				  ipv6_gro_complete, inet_gro_complete,
+				  skb, nhoff + PPPOE_SES_HLEN);
+}
+
+static struct sk_buff *pppoe_gso_segment(struct sk_buff *skb,
+					 netdev_features_t features)
+{
+	struct sk_buff *segs = ERR_PTR(-EINVAL);
+	struct packet_offload *ptype;
+	struct pppoe_hdr *phdr;
+	__be16 orig_type, type;
+	int len, nhoff;
+
+	skb_reset_network_header(skb);
+	nhoff = skb_network_header(skb) - skb_mac_header(skb);
+
+	if (unlikely(!pskb_may_pull(skb, PPPOE_SES_HLEN)))
+		goto out;
+
+	phdr = (struct pppoe_hdr *)skb_network_header(skb);
+	type = pppoe_hdr_proto(phdr);
+	ptype = gro_find_complete_by_type(type);
+	if (!ptype)
+		goto out;
+
+	orig_type = skb->protocol;
+	__skb_pull(skb, PPPOE_SES_HLEN);
+	features &= ~NETIF_F_GSO_SOFTWARE;
+	segs = ptype->callbacks.gso_segment(skb, features);
+	if (IS_ERR_OR_NULL(segs))
+		goto out;
+
+	skb = segs;
+	do {
+		phdr = (struct pppoe_hdr *)(skb_mac_header(skb) + nhoff);
+		len = skb->len - (nhoff + sizeof(*phdr));
+		phdr->length = cpu_to_be16(len);
+		skb->network_header = (u8 *)phdr - skb->head;
+		skb->protocol = orig_type;
+		skb_reset_mac_len(skb);
+	} while ((skb = skb->next));
+
+out:
+	return segs;
+}
+
+static struct packet_offload pppoe_packet_offload __read_mostly = {
+	.type = cpu_to_be16(ETH_P_PPP_SES),
+	.priority = 20,
+	.callbacks = {
+		.gro_receive = pppoe_gro_receive,
+		.gro_complete = pppoe_gro_complete,
+		.gso_segment = pppoe_gso_segment,
+	},
+};
+
+static int __init pppoe_init(void)
+{
+	int err;
+
+	err = register_pernet_device(&pppoe_net_ops);
+	if (err)
+		goto out;
+
+	err = proto_register(&pppoe_sk_proto, 0);
+	if (err)
+		goto out_unregister_net_ops;
+
+	err = register_pppox_proto(PX_PROTO_OE, &pppoe_proto);
+	if (err)
+		goto out_unregister_pppoe_proto;
+
+	if (IS_ENABLED(CONFIG_INET))
+		dev_add_offload(&pppoe_packet_offload);
+	dev_add_pack(&pppoes_ptype);
+	dev_add_pack(&pppoed_ptype);
+	register_netdevice_notifier(&pppoe_notifier);
+
+	return 0;
+
+out_unregister_pppoe_proto:
+	proto_unregister(&pppoe_sk_proto);
+out_unregister_net_ops:
+	unregister_pernet_device(&pppoe_net_ops);
+out:
+	return err;
+}
+
+static void __exit pppoe_exit(void)
+{
+	unregister_netdevice_notifier(&pppoe_notifier);
+	dev_remove_pack(&pppoed_ptype);
+	dev_remove_pack(&pppoes_ptype);
+	if (IS_ENABLED(CONFIG_INET))
+		dev_remove_offload(&pppoe_packet_offload);
+	unregister_pppox_proto(PX_PROTO_OE);
+	proto_unregister(&pppoe_sk_proto);
+	unregister_pernet_device(&pppoe_net_ops);
+}
+
+module_init(pppoe_init);
+module_exit(pppoe_exit);
+
+MODULE_AUTHOR("Michal Ostrowski <mostrows@speakeasy.net>");
+MODULE_DESCRIPTION("PPP over Ethernet driver");
+MODULE_LICENSE("GPL");
+MODULE_ALIAS_NET_PF_PROTO(PF_PPPOX, PX_PROTO_OE);