Message-Id: <22aa4952ddd20310b5518e383b4c8ccf36b86f00.1491838390.git.jslaby@suse.cz>
Date:   Mon, 10 Apr 2017 17:32:04 +0200
From:   Jiri Slaby <jslaby@...e.cz>
To:     stable@...r.kernel.org
Cc:     linux-kernel@...r.kernel.org, Florian Westphal <fw@...len.de>,
        Daniel Borkmann <daniel@...earbox.net>,
        Ken-ichirou MATSUZAWA <chamaken@...il.com>,
        Pablo Neira Ayuso <pablo@...filter.org>,
        Patrick McHardy <kaber@...sh.net>, Thomas Graf <tgraf@...g.ch>,
        "David S . Miller" <davem@...emloft.net>,
        Jiri Slaby <jslaby@...e.cz>
Subject: [PATCH 3.12 043/142] netlink: remove mmapped netlink support

From: Florian Westphal <fw@...len.de>

3.12-stable review patch.  If anyone has any objections, please let me know.

===============

commit d1b4c689d4130bcfd3532680b64db562300716b6 upstream.

mmapped netlink has a number of unresolved issues:

- TX zerocopy support had to be disabled more than a year ago via
  commit 4682a0358639b29cf ("netlink: Always copy on mmap TX.")
  because the content of the mmapped area can change after netlink
  attribute validation but before message processing.

- RX support was implemented mainly to speed up nfqueue dumping packet
  payload to userspace.  However, since commit ae08ce0021087a5d812d2
  ("netfilter: nfnetlink_queue: zero copy support") we avoid one copy
  with the socket-based interface too (via the skb_zerocopy helper).

The other problem is that skbs attached to mmaped netlink socket
behave different from normal skbs:

- they don't have a shinfo area, so all functions that use skb_shinfo()
(e.g. skb_clone) cannot be used.

- reserving headroom prevents userspace from seeing the content as
it expects message to start at skb->head.
See for instance
commit aa3a022094fa ("netlink: not trim skb for mmaped socket when dump").

- skbs handed e.g. to netlink_ack must have non-NULL skb->sk, else we
crash because it needs the sk to check if a tx ring is attached.

Also not obvious, leads to non-intuitive bug fixes such as 7c7bdf359
("netfilter: nfnetlink: use original skbuff when acking batches").

mmaped netlink also didn't play nicely with the skb_zerocopy helper
used by nfqueue and openvswitch.  Daniel Borkmann fixed this via
commit 6bb0fef489f6 ("netlink, mmap: fix edge-case leakages in nf queue
zero-copy")' but at the cost of also needing to provide remaining
length to the allocation function.

nfqueue also has problems when used with mmaped rx netlink:
- mmaped netlink doesn't allow use of nfqueue batch verdict messages.
  Problem is that in the mmap case, the allocation time also determines
  the ordering in which the frame will be seen by userspace (A
  allocating before B means that A is located in earlier ring slot,
  but this also means that B might get a lower sequence number then A
  since seqno is decided later.  To fix this we would need to extend the
  spinlocked region to also cover the allocation and message setup which
  isn't desirable.
- nfqueue can now be configured to queue large (GSO) skbs to userspace.
  Queing GSO packets is faster than having to force a software segmentation
  in the kernel, so this is a desirable option.  However, with a mmap based
  ring one has to use 64kb per ring slot element, else mmap has to fall back
  to the socket path (NL_MMAP_STATUS_COPY) for all large packets.

To use the mmap interface, userspace not only has to probe for mmap netlink
support, it also has to implement a recv/socket receive path in order to
handle messages that exceed the size of an rx ring element.

Cc: Daniel Borkmann <daniel@...earbox.net>
Cc: Ken-ichirou MATSUZAWA <chamaken@...il.com>
Cc: Pablo Neira Ayuso <pablo@...filter.org>
Cc: Patrick McHardy <kaber@...sh.net>
Cc: Thomas Graf <tgraf@...g.ch>
Signed-off-by: Florian Westphal <fw@...len.de>
Signed-off-by: David S. Miller <davem@...emloft.net>
Signed-off-by: Jiri Slaby <jslaby@...e.cz>
---
 include/uapi/linux/netlink.h      |   4 +
 include/uapi/linux/netlink_diag.h |   2 +
 net/netlink/Kconfig               |   9 -
 net/netlink/af_netlink.c          | 726 +-------------------------------------
 net/netlink/af_netlink.h          |  15 -
 net/netlink/diag.c                |  39 --
 6 files changed, 14 insertions(+), 781 deletions(-)

diff --git a/include/uapi/linux/netlink.h b/include/uapi/linux/netlink.h
index 1a85940f8ab7..8a8135c4e99a 100644
--- a/include/uapi/linux/netlink.h
+++ b/include/uapi/linux/netlink.h
@@ -106,8 +106,10 @@ struct nlmsgerr {
 #define NETLINK_PKTINFO		3
 #define NETLINK_BROADCAST_ERROR	4
 #define NETLINK_NO_ENOBUFS	5
+#ifndef __KERNEL__
 #define NETLINK_RX_RING		6
 #define NETLINK_TX_RING		7
+#endif
 
 struct nl_pktinfo {
 	__u32	group;
@@ -130,6 +132,7 @@ struct nl_mmap_hdr {
 	__u32		nm_gid;
 };
 
+#ifndef __KERNEL__
 enum nl_mmap_status {
 	NL_MMAP_STATUS_UNUSED,
 	NL_MMAP_STATUS_RESERVED,
@@ -141,6 +144,7 @@ enum nl_mmap_status {
 #define NL_MMAP_MSG_ALIGNMENT		NLMSG_ALIGNTO
 #define NL_MMAP_MSG_ALIGN(sz)		__ALIGN_KERNEL(sz, NL_MMAP_MSG_ALIGNMENT)
 #define NL_MMAP_HDRLEN			NL_MMAP_MSG_ALIGN(sizeof(struct nl_mmap_hdr))
+#endif
 
 #define NET_MAJOR 36		/* Major 36 is reserved for networking 						*/
 
diff --git a/include/uapi/linux/netlink_diag.h b/include/uapi/linux/netlink_diag.h
index 4e31db4eea41..01d7ff3b92dc 100644
--- a/include/uapi/linux/netlink_diag.h
+++ b/include/uapi/linux/netlink_diag.h
@@ -47,6 +47,8 @@ enum {
 
 #define NDIAG_SHOW_MEMINFO	0x00000001 /* show memory info of a socket */
 #define NDIAG_SHOW_GROUPS	0x00000002 /* show groups of a netlink socket */
+#ifndef __KERNEL__
 #define NDIAG_SHOW_RING_CFG	0x00000004 /* show ring configuration */
+#endif
 
 #endif
diff --git a/net/netlink/Kconfig b/net/netlink/Kconfig
index 2c5e95e9bfbd..5d6e8c05b3d4 100644
--- a/net/netlink/Kconfig
+++ b/net/netlink/Kconfig
@@ -2,15 +2,6 @@
 # Netlink Sockets
 #
 
-config NETLINK_MMAP
-	bool "NETLINK: mmaped IO"
-	---help---
-	  This option enables support for memory mapped netlink IO. This
-	  reduces overhead by avoiding copying data between kernel- and
-	  userspace.
-
-	  If unsure, say N.
-
 config NETLINK_DIAG
 	tristate "NETLINK: socket monitoring interface"
 	default n
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index bb04abe72d76..e60743f93ca3 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -219,7 +219,7 @@ static int __netlink_deliver_tap_skb(struct sk_buff *skb,
 
 	dev_hold(dev);
 
-	if (netlink_skb_is_mmaped(skb) || is_vmalloc_addr(skb->head))
+	if (is_vmalloc_addr(skb->head))
 		nskb = netlink_to_full_skb(skb, GFP_ATOMIC);
 	else
 		nskb = skb_clone(skb, GFP_ATOMIC);
@@ -284,599 +284,8 @@ static void netlink_rcv_wake(struct sock *sk)
 		wake_up_interruptible(&nlk->wait);
 }
 
-#ifdef CONFIG_NETLINK_MMAP
-static bool netlink_rx_is_mmaped(struct sock *sk)
-{
-	return nlk_sk(sk)->rx_ring.pg_vec != NULL;
-}
-
-static bool netlink_tx_is_mmaped(struct sock *sk)
-{
-	return nlk_sk(sk)->tx_ring.pg_vec != NULL;
-}
-
-static __pure struct page *pgvec_to_page(const void *addr)
-{
-	if (is_vmalloc_addr(addr))
-		return vmalloc_to_page(addr);
-	else
-		return virt_to_page(addr);
-}
-
-static void free_pg_vec(void **pg_vec, unsigned int order, unsigned int len)
-{
-	unsigned int i;
-
-	for (i = 0; i < len; i++) {
-		if (pg_vec[i] != NULL) {
-			if (is_vmalloc_addr(pg_vec[i]))
-				vfree(pg_vec[i]);
-			else
-				free_pages((unsigned long)pg_vec[i], order);
-		}
-	}
-	kfree(pg_vec);
-}
-
-static void *alloc_one_pg_vec_page(unsigned long order)
-{
-	void *buffer;
-	gfp_t gfp_flags = GFP_KERNEL | __GFP_COMP | __GFP_ZERO |
-			  __GFP_NOWARN | __GFP_NORETRY;
-
-	buffer = (void *)__get_free_pages(gfp_flags, order);
-	if (buffer != NULL)
-		return buffer;
-
-	buffer = vzalloc((1 << order) * PAGE_SIZE);
-	if (buffer != NULL)
-		return buffer;
-
-	gfp_flags &= ~__GFP_NORETRY;
-	return (void *)__get_free_pages(gfp_flags, order);
-}
-
-static void **alloc_pg_vec(struct netlink_sock *nlk,
-			   struct nl_mmap_req *req, unsigned int order)
-{
-	unsigned int block_nr = req->nm_block_nr;
-	unsigned int i;
-	void **pg_vec;
-
-	pg_vec = kcalloc(block_nr, sizeof(void *), GFP_KERNEL);
-	if (pg_vec == NULL)
-		return NULL;
-
-	for (i = 0; i < block_nr; i++) {
-		pg_vec[i] = alloc_one_pg_vec_page(order);
-		if (pg_vec[i] == NULL)
-			goto err1;
-	}
-
-	return pg_vec;
-err1:
-	free_pg_vec(pg_vec, order, block_nr);
-	return NULL;
-}
-
-
-static void
-__netlink_set_ring(struct sock *sk, struct nl_mmap_req *req, bool tx_ring, void **pg_vec,
-		   unsigned int order)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct sk_buff_head *queue;
-	struct netlink_ring *ring;
-
-	queue = tx_ring ? &sk->sk_write_queue : &sk->sk_receive_queue;
-	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-
-	spin_lock_bh(&queue->lock);
-
-	ring->frame_max		= req->nm_frame_nr - 1;
-	ring->head		= 0;
-	ring->frame_size	= req->nm_frame_size;
-	ring->pg_vec_pages	= req->nm_block_size / PAGE_SIZE;
-
-	swap(ring->pg_vec_len, req->nm_block_nr);
-	swap(ring->pg_vec_order, order);
-	swap(ring->pg_vec, pg_vec);
-
-	__skb_queue_purge(queue);
-	spin_unlock_bh(&queue->lock);
-
-	WARN_ON(atomic_read(&nlk->mapped));
-
-	if (pg_vec)
-		free_pg_vec(pg_vec, order, req->nm_block_nr);
-}
-
-static int netlink_set_ring(struct sock *sk, struct nl_mmap_req *req,
-			    bool tx_ring)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring;
-	void **pg_vec = NULL;
-	unsigned int order = 0;
-
-	ring  = tx_ring ? &nlk->tx_ring : &nlk->rx_ring;
-
-	if (atomic_read(&nlk->mapped))
-		return -EBUSY;
-	if (atomic_read(&ring->pending))
-		return -EBUSY;
-
-	if (req->nm_block_nr) {
-		if (ring->pg_vec != NULL)
-			return -EBUSY;
-
-		if ((int)req->nm_block_size <= 0)
-			return -EINVAL;
-		if (!IS_ALIGNED(req->nm_block_size, PAGE_SIZE))
-			return -EINVAL;
-		if (req->nm_frame_size < NL_MMAP_HDRLEN)
-			return -EINVAL;
-		if (!IS_ALIGNED(req->nm_frame_size, NL_MMAP_MSG_ALIGNMENT))
-			return -EINVAL;
-
-		ring->frames_per_block = req->nm_block_size /
-					 req->nm_frame_size;
-		if (ring->frames_per_block == 0)
-			return -EINVAL;
-		if (ring->frames_per_block * req->nm_block_nr !=
-		    req->nm_frame_nr)
-			return -EINVAL;
-
-		order = get_order(req->nm_block_size);
-		pg_vec = alloc_pg_vec(nlk, req, order);
-		if (pg_vec == NULL)
-			return -ENOMEM;
-	} else {
-		if (req->nm_frame_nr)
-			return -EINVAL;
-	}
-
-	mutex_lock(&nlk->pg_vec_lock);
-	if (atomic_read(&nlk->mapped) == 0) {
-		__netlink_set_ring(sk, req, tx_ring, pg_vec, order);
-		mutex_unlock(&nlk->pg_vec_lock);
-		return 0;
-	}
-
-	mutex_unlock(&nlk->pg_vec_lock);
-
-	if (pg_vec)
-		free_pg_vec(pg_vec, order, req->nm_block_nr);
-
-	return -EBUSY;
-}
-
-static void netlink_mm_open(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-	struct socket *sock = file->private_data;
-	struct sock *sk = sock->sk;
-
-	if (sk)
-		atomic_inc(&nlk_sk(sk)->mapped);
-}
-
-static void netlink_mm_close(struct vm_area_struct *vma)
-{
-	struct file *file = vma->vm_file;
-	struct socket *sock = file->private_data;
-	struct sock *sk = sock->sk;
-
-	if (sk)
-		atomic_dec(&nlk_sk(sk)->mapped);
-}
-
-static const struct vm_operations_struct netlink_mmap_ops = {
-	.open	= netlink_mm_open,
-	.close	= netlink_mm_close,
-};
-
-static int netlink_mmap(struct file *file, struct socket *sock,
-			struct vm_area_struct *vma)
-{
-	struct sock *sk = sock->sk;
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring;
-	unsigned long start, size, expected;
-	unsigned int i;
-	int err = -EINVAL;
-
-	if (vma->vm_pgoff)
-		return -EINVAL;
-
-	mutex_lock(&nlk->pg_vec_lock);
-
-	expected = 0;
-	for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) {
-		if (ring->pg_vec == NULL)
-			continue;
-		expected += ring->pg_vec_len * ring->pg_vec_pages * PAGE_SIZE;
-	}
-
-	if (expected == 0)
-		goto out;
-
-	size = vma->vm_end - vma->vm_start;
-	if (size != expected)
-		goto out;
-
-	start = vma->vm_start;
-	for (ring = &nlk->rx_ring; ring <= &nlk->tx_ring; ring++) {
-		if (ring->pg_vec == NULL)
-			continue;
-
-		for (i = 0; i < ring->pg_vec_len; i++) {
-			struct page *page;
-			void *kaddr = ring->pg_vec[i];
-			unsigned int pg_num;
-
-			for (pg_num = 0; pg_num < ring->pg_vec_pages; pg_num++) {
-				page = pgvec_to_page(kaddr);
-				err = vm_insert_page(vma, start, page);
-				if (err < 0)
-					goto out;
-				start += PAGE_SIZE;
-				kaddr += PAGE_SIZE;
-			}
-		}
-	}
-
-	atomic_inc(&nlk->mapped);
-	vma->vm_ops = &netlink_mmap_ops;
-	err = 0;
-out:
-	mutex_unlock(&nlk->pg_vec_lock);
-	return err;
-}
-
-static void netlink_frame_flush_dcache(const struct nl_mmap_hdr *hdr, unsigned int nm_len)
-{
-#if ARCH_IMPLEMENTS_FLUSH_DCACHE_PAGE == 1
-	struct page *p_start, *p_end;
-
-	/* First page is flushed through netlink_{get,set}_status */
-	p_start = pgvec_to_page(hdr + PAGE_SIZE);
-	p_end   = pgvec_to_page((void *)hdr + NL_MMAP_HDRLEN + nm_len - 1);
-	while (p_start <= p_end) {
-		flush_dcache_page(p_start);
-		p_start++;
-	}
-#endif
-}
-
-static enum nl_mmap_status netlink_get_status(const struct nl_mmap_hdr *hdr)
-{
-	smp_rmb();
-	flush_dcache_page(pgvec_to_page(hdr));
-	return hdr->nm_status;
-}
-
-static void netlink_set_status(struct nl_mmap_hdr *hdr,
-			       enum nl_mmap_status status)
-{
-	smp_mb();
-	hdr->nm_status = status;
-	flush_dcache_page(pgvec_to_page(hdr));
-}
-
-static struct nl_mmap_hdr *
-__netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos)
-{
-	unsigned int pg_vec_pos, frame_off;
-
-	pg_vec_pos = pos / ring->frames_per_block;
-	frame_off  = pos % ring->frames_per_block;
-
-	return ring->pg_vec[pg_vec_pos] + (frame_off * ring->frame_size);
-}
-
-static struct nl_mmap_hdr *
-netlink_lookup_frame(const struct netlink_ring *ring, unsigned int pos,
-		     enum nl_mmap_status status)
-{
-	struct nl_mmap_hdr *hdr;
-
-	hdr = __netlink_lookup_frame(ring, pos);
-	if (netlink_get_status(hdr) != status)
-		return NULL;
-
-	return hdr;
-}
-
-static struct nl_mmap_hdr *
-netlink_current_frame(const struct netlink_ring *ring,
-		      enum nl_mmap_status status)
-{
-	return netlink_lookup_frame(ring, ring->head, status);
-}
-
-static struct nl_mmap_hdr *
-netlink_previous_frame(const struct netlink_ring *ring,
-		       enum nl_mmap_status status)
-{
-	unsigned int prev;
-
-	prev = ring->head ? ring->head - 1 : ring->frame_max;
-	return netlink_lookup_frame(ring, prev, status);
-}
-
-static void netlink_increment_head(struct netlink_ring *ring)
-{
-	ring->head = ring->head != ring->frame_max ? ring->head + 1 : 0;
-}
-
-static void netlink_forward_ring(struct netlink_ring *ring)
-{
-	unsigned int head = ring->head, pos = head;
-	const struct nl_mmap_hdr *hdr;
-
-	do {
-		hdr = __netlink_lookup_frame(ring, pos);
-		if (hdr->nm_status == NL_MMAP_STATUS_UNUSED)
-			break;
-		if (hdr->nm_status != NL_MMAP_STATUS_SKIP)
-			break;
-		netlink_increment_head(ring);
-	} while (ring->head != head);
-}
-
-static bool netlink_dump_space(struct netlink_sock *nlk)
-{
-	struct netlink_ring *ring = &nlk->rx_ring;
-	struct nl_mmap_hdr *hdr;
-	unsigned int n;
-
-	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
-	if (hdr == NULL)
-		return false;
-
-	n = ring->head + ring->frame_max / 2;
-	if (n > ring->frame_max)
-		n -= ring->frame_max;
-
-	hdr = __netlink_lookup_frame(ring, n);
-
-	return hdr->nm_status == NL_MMAP_STATUS_UNUSED;
-}
-
-static unsigned int netlink_poll(struct file *file, struct socket *sock,
-				 poll_table *wait)
-{
-	struct sock *sk = sock->sk;
-	struct netlink_sock *nlk = nlk_sk(sk);
-	unsigned int mask;
-	int err;
-
-	if (nlk->rx_ring.pg_vec != NULL) {
-		/* Memory mapped sockets don't call recvmsg(), so flow control
-		 * for dumps is performed here. A dump is allowed to continue
-		 * if at least half the ring is unused.
-		 */
-		while (nlk->cb_running && netlink_dump_space(nlk)) {
-			err = netlink_dump(sk);
-			if (err < 0) {
-				sk->sk_err = -err;
-				sk->sk_error_report(sk);
-				break;
-			}
-		}
-		netlink_rcv_wake(sk);
-	}
-
-	mask = datagram_poll(file, sock, wait);
-
-	spin_lock_bh(&sk->sk_receive_queue.lock);
-	if (nlk->rx_ring.pg_vec) {
-		netlink_forward_ring(&nlk->rx_ring);
-		if (!netlink_previous_frame(&nlk->rx_ring, NL_MMAP_STATUS_UNUSED))
-			mask |= POLLIN | POLLRDNORM;
-	}
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-
-	spin_lock_bh(&sk->sk_write_queue.lock);
-	if (nlk->tx_ring.pg_vec) {
-		if (netlink_current_frame(&nlk->tx_ring, NL_MMAP_STATUS_UNUSED))
-			mask |= POLLOUT | POLLWRNORM;
-	}
-	spin_unlock_bh(&sk->sk_write_queue.lock);
-
-	return mask;
-}
-
-static struct nl_mmap_hdr *netlink_mmap_hdr(struct sk_buff *skb)
-{
-	return (struct nl_mmap_hdr *)(skb->head - NL_MMAP_HDRLEN);
-}
-
-static void netlink_ring_setup_skb(struct sk_buff *skb, struct sock *sk,
-				   struct netlink_ring *ring,
-				   struct nl_mmap_hdr *hdr)
-{
-	unsigned int size;
-	void *data;
-
-	size = ring->frame_size - NL_MMAP_HDRLEN;
-	data = (void *)hdr + NL_MMAP_HDRLEN;
-
-	skb->head	= data;
-	skb->data	= data;
-	skb_reset_tail_pointer(skb);
-	skb->end	= skb->tail + size;
-	skb->len	= 0;
-
-	skb->destructor	= netlink_skb_destructor;
-	NETLINK_CB(skb).flags |= NETLINK_SKB_MMAPED;
-	NETLINK_CB(skb).sk = sk;
-}
-
-static int netlink_mmap_sendmsg(struct sock *sk, struct msghdr *msg,
-				u32 dst_portid, u32 dst_group,
-				struct sock_iocb *siocb)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring;
-	struct nl_mmap_hdr *hdr;
-	struct sk_buff *skb;
-	unsigned int maxlen;
-	int err = 0, len = 0;
-
-	mutex_lock(&nlk->pg_vec_lock);
-
-	ring   = &nlk->tx_ring;
-	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
-
-	do {
-		unsigned int nm_len;
-
-		hdr = netlink_current_frame(ring, NL_MMAP_STATUS_VALID);
-		if (hdr == NULL) {
-			if (!(msg->msg_flags & MSG_DONTWAIT) &&
-			    atomic_read(&nlk->tx_ring.pending))
-				schedule();
-			continue;
-		}
-
-		nm_len = ACCESS_ONCE(hdr->nm_len);
-		if (nm_len > maxlen) {
-			err = -EINVAL;
-			goto out;
-		}
-
-		netlink_frame_flush_dcache(hdr, nm_len);
-
-		skb = alloc_skb(nm_len, GFP_KERNEL);
-		if (skb == NULL) {
-			err = -ENOBUFS;
-			goto out;
-		}
-		__skb_put(skb, nm_len);
-		memcpy(skb->data, (void *)hdr + NL_MMAP_HDRLEN, nm_len);
-		netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
-
-		netlink_increment_head(ring);
-
-		NETLINK_CB(skb).portid	  = nlk->portid;
-		NETLINK_CB(skb).dst_group = dst_group;
-		NETLINK_CB(skb).creds	  = siocb->scm->creds;
-
-		err = security_netlink_send(sk, skb);
-		if (err) {
-			kfree_skb(skb);
-			goto out;
-		}
-
-		if (unlikely(dst_group)) {
-			atomic_inc(&skb->users);
-			netlink_broadcast(sk, skb, dst_portid, dst_group,
-					  GFP_KERNEL);
-		}
-		err = netlink_unicast(sk, skb, dst_portid,
-				      msg->msg_flags & MSG_DONTWAIT);
-		if (err < 0)
-			goto out;
-		len += err;
-
-	} while (hdr != NULL ||
-		 (!(msg->msg_flags & MSG_DONTWAIT) &&
-		  atomic_read(&nlk->tx_ring.pending)));
-
-	if (len > 0)
-		err = len;
-out:
-	mutex_unlock(&nlk->pg_vec_lock);
-	return err;
-}
-
-static void netlink_queue_mmaped_skb(struct sock *sk, struct sk_buff *skb)
-{
-	struct nl_mmap_hdr *hdr;
-
-	hdr = netlink_mmap_hdr(skb);
-	hdr->nm_len	= skb->len;
-	hdr->nm_group	= NETLINK_CB(skb).dst_group;
-	hdr->nm_pid	= NETLINK_CB(skb).creds.pid;
-	hdr->nm_uid	= from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
-	hdr->nm_gid	= from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
-	netlink_frame_flush_dcache(hdr, hdr->nm_len);
-	netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
-
-	NETLINK_CB(skb).flags |= NETLINK_SKB_DELIVERED;
-	kfree_skb(skb);
-}
-
-static void netlink_ring_set_copied(struct sock *sk, struct sk_buff *skb)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	struct netlink_ring *ring = &nlk->rx_ring;
-	struct nl_mmap_hdr *hdr;
-
-	spin_lock_bh(&sk->sk_receive_queue.lock);
-	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
-	if (hdr == NULL) {
-		spin_unlock_bh(&sk->sk_receive_queue.lock);
-		kfree_skb(skb);
-		netlink_overrun(sk);
-		return;
-	}
-	netlink_increment_head(ring);
-	__skb_queue_tail(&sk->sk_receive_queue, skb);
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-
-	hdr->nm_len	= skb->len;
-	hdr->nm_group	= NETLINK_CB(skb).dst_group;
-	hdr->nm_pid	= NETLINK_CB(skb).creds.pid;
-	hdr->nm_uid	= from_kuid(sk_user_ns(sk), NETLINK_CB(skb).creds.uid);
-	hdr->nm_gid	= from_kgid(sk_user_ns(sk), NETLINK_CB(skb).creds.gid);
-	netlink_set_status(hdr, NL_MMAP_STATUS_COPY);
-}
-
-#else /* CONFIG_NETLINK_MMAP */
-#define netlink_rx_is_mmaped(sk)	false
-#define netlink_tx_is_mmaped(sk)	false
-#define netlink_mmap			sock_no_mmap
-#define netlink_poll			datagram_poll
-#define netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group, siocb)	0
-#endif /* CONFIG_NETLINK_MMAP */
-
 static void netlink_skb_destructor(struct sk_buff *skb)
 {
-#ifdef CONFIG_NETLINK_MMAP
-	struct nl_mmap_hdr *hdr;
-	struct netlink_ring *ring;
-	struct sock *sk;
-
-	/* If a packet from the kernel to userspace was freed because of an
-	 * error without being delivered to userspace, the kernel must reset
-	 * the status. In the direction userspace to kernel, the status is
-	 * always reset here after the packet was processed and freed.
-	 */
-	if (netlink_skb_is_mmaped(skb)) {
-		hdr = netlink_mmap_hdr(skb);
-		sk = NETLINK_CB(skb).sk;
-
-		if (NETLINK_CB(skb).flags & NETLINK_SKB_TX) {
-			netlink_set_status(hdr, NL_MMAP_STATUS_UNUSED);
-			ring = &nlk_sk(sk)->tx_ring;
-		} else {
-			if (!(NETLINK_CB(skb).flags & NETLINK_SKB_DELIVERED)) {
-				hdr->nm_len = 0;
-				netlink_set_status(hdr, NL_MMAP_STATUS_VALID);
-			}
-			ring = &nlk_sk(sk)->rx_ring;
-		}
-
-		WARN_ON(atomic_read(&ring->pending) == 0);
-		atomic_dec(&ring->pending);
-		sock_put(sk);
-
-		skb->head = NULL;
-	}
-#endif
 	if (is_vmalloc_addr(skb->head)) {
 		if (!skb->cloned ||
 		    !atomic_dec_return(&(skb_shinfo(skb)->dataref)))
@@ -910,18 +319,6 @@ static void netlink_sock_destruct(struct sock *sk)
 	}
 
 	skb_queue_purge(&sk->sk_receive_queue);
-#ifdef CONFIG_NETLINK_MMAP
-	if (1) {
-		struct nl_mmap_req req;
-
-		memset(&req, 0, sizeof(req));
-		if (nlk->rx_ring.pg_vec)
-			__netlink_set_ring(sk, &req, false, NULL, 0);
-		memset(&req, 0, sizeof(req));
-		if (nlk->tx_ring.pg_vec)
-			__netlink_set_ring(sk, &req, true, NULL, 0);
-	}
-#endif /* CONFIG_NETLINK_MMAP */
 
 	if (!sock_flag(sk, SOCK_DEAD)) {
 		printk(KERN_ERR "Freeing alive netlink socket %p\n", sk);
@@ -1194,9 +591,6 @@ static int __netlink_create(struct net *net, struct socket *sock,
 		mutex_init(nlk->cb_mutex);
 	}
 	init_waitqueue_head(&nlk->wait);
-#ifdef CONFIG_NETLINK_MMAP
-	mutex_init(&nlk->pg_vec_lock);
-#endif
 
 	sk->sk_destruct = netlink_sock_destruct;
 	sk->sk_protocol = protocol;
@@ -1674,8 +1068,7 @@ int netlink_attachskb(struct sock *sk, struct sk_buff *skb,
 	nlk = nlk_sk(sk);
 
 	if ((atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
-	     test_bit(NETLINK_CONGESTED, &nlk->state)) &&
-	    !netlink_skb_is_mmaped(skb)) {
+	     test_bit(NETLINK_CONGESTED, &nlk->state))) {
 		DECLARE_WAITQUEUE(wait, current);
 		if (!*timeo) {
 			if (!ssk || netlink_is_kernel(ssk))
@@ -1713,14 +1106,7 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
 
 	netlink_deliver_tap(skb);
 
-#ifdef CONFIG_NETLINK_MMAP
-	if (netlink_skb_is_mmaped(skb))
-		netlink_queue_mmaped_skb(sk, skb);
-	else if (netlink_rx_is_mmaped(sk))
-		netlink_ring_set_copied(sk, skb);
-	else
-#endif /* CONFIG_NETLINK_MMAP */
-		skb_queue_tail(&sk->sk_receive_queue, skb);
+	skb_queue_tail(&sk->sk_receive_queue, skb);
 	sk->sk_data_ready(sk, len);
 	return len;
 }
@@ -1744,9 +1130,6 @@ static struct sk_buff *netlink_trim(struct sk_buff *skb, gfp_t allocation)
 	int delta;
 
 	WARN_ON(skb->sk != NULL);
-	if (netlink_skb_is_mmaped(skb))
-		return skb;
-
 	delta = skb->end - skb->tail;
 	if (is_vmalloc_addr(skb->head) || delta * 2 < skb->truesize)
 		return skb;
@@ -1829,62 +1212,6 @@ EXPORT_SYMBOL(netlink_unicast);
 struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
 				  u32 dst_portid, gfp_t gfp_mask)
 {
-#ifdef CONFIG_NETLINK_MMAP
-	struct sock *sk = NULL;
-	struct sk_buff *skb;
-	struct netlink_ring *ring;
-	struct nl_mmap_hdr *hdr;
-	unsigned int maxlen;
-
-	sk = netlink_getsockbyportid(ssk, dst_portid);
-	if (IS_ERR(sk))
-		goto out;
-
-	ring = &nlk_sk(sk)->rx_ring;
-	/* fast-path without atomic ops for common case: non-mmaped receiver */
-	if (ring->pg_vec == NULL)
-		goto out_put;
-
-	skb = alloc_skb_head(gfp_mask);
-	if (skb == NULL)
-		goto err1;
-
-	spin_lock_bh(&sk->sk_receive_queue.lock);
-	/* check again under lock */
-	if (ring->pg_vec == NULL)
-		goto out_free;
-
-	maxlen = ring->frame_size - NL_MMAP_HDRLEN;
-	if (maxlen < size)
-		goto out_free;
-
-	netlink_forward_ring(ring);
-	hdr = netlink_current_frame(ring, NL_MMAP_STATUS_UNUSED);
-	if (hdr == NULL)
-		goto err2;
-	netlink_ring_setup_skb(skb, sk, ring, hdr);
-	netlink_set_status(hdr, NL_MMAP_STATUS_RESERVED);
-	atomic_inc(&ring->pending);
-	netlink_increment_head(ring);
-
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-	return skb;
-
-err2:
-	kfree_skb(skb);
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-	netlink_overrun(sk);
-err1:
-	sock_put(sk);
-	return NULL;
-
-out_free:
-	kfree_skb(skb);
-	spin_unlock_bh(&sk->sk_receive_queue.lock);
-out_put:
-	sock_put(sk);
-out:
-#endif
 	return alloc_skb(size, gfp_mask);
 }
 EXPORT_SYMBOL_GPL(netlink_alloc_skb);
@@ -2149,8 +1476,7 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 	if (level != SOL_NETLINK)
 		return -ENOPROTOOPT;
 
-	if (optname != NETLINK_RX_RING && optname != NETLINK_TX_RING &&
-	    optlen >= sizeof(int) &&
+	if (optlen >= sizeof(int) &&
 	    get_user(val, (unsigned int __user *)optval))
 		return -EFAULT;
 
@@ -2199,25 +1525,6 @@ static int netlink_setsockopt(struct socket *sock, int level, int optname,
 		}
 		err = 0;
 		break;
-#ifdef CONFIG_NETLINK_MMAP
-	case NETLINK_RX_RING:
-	case NETLINK_TX_RING: {
-		struct nl_mmap_req req;
-
-		/* Rings might consume more memory than queue limits, require
-		 * CAP_NET_ADMIN.
-		 */
-		if (!capable(CAP_NET_ADMIN))
-			return -EPERM;
-		if (optlen < sizeof(req))
-			return -EINVAL;
-		if (copy_from_user(&req, optval, sizeof(req)))
-			return -EFAULT;
-		err = netlink_set_ring(sk, &req,
-				       optname == NETLINK_TX_RING);
-		break;
-	}
-#endif /* CONFIG_NETLINK_MMAP */
 	default:
 		err = -ENOPROTOOPT;
 	}
@@ -2330,13 +1637,6 @@ static int netlink_sendmsg(struct kiocb *kiocb, struct socket *sock,
 			goto out;
 	}
 
-	if (netlink_tx_is_mmaped(sk) &&
-	    msg->msg_iov->iov_base == NULL) {
-		err = netlink_mmap_sendmsg(sk, msg, dst_portid, dst_group,
-					   siocb);
-		goto out;
-	}
-
 	err = -EMSGSIZE;
 	if (len > sk->sk_sndbuf - 32)
 		goto out;
@@ -2671,8 +1971,7 @@ static int netlink_dump(struct sock *sk)
 	cb = &nlk->cb;
 	alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
 
-	if (!netlink_rx_is_mmaped(sk) &&
-	    atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+	if (atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
 		goto errout_skb;
 	skb = netlink_alloc_skb(sk, alloc_size, nlk->portid, GFP_KERNEL);
 	if (!skb)
@@ -2730,16 +2029,7 @@ int __netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
 	struct netlink_sock *nlk;
 	int ret;
 
-	/* Memory mapped dump requests need to be copied to avoid looping
-	 * on the pending state in netlink_mmap_sendmsg() while the CB hold
-	 * a reference to the skb.
-	 */
-	if (netlink_skb_is_mmaped(skb)) {
-		skb = skb_copy(skb, GFP_KERNEL);
-		if (skb == NULL)
-			return -ENOBUFS;
-	} else
-		atomic_inc(&skb->users);
+	atomic_inc(&skb->users);
 
 	sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).portid);
 	if (sk == NULL) {
@@ -3075,7 +2365,7 @@ static const struct proto_ops netlink_ops = {
 	.socketpair =	sock_no_socketpair,
 	.accept =	sock_no_accept,
 	.getname =	netlink_getname,
-	.poll =		netlink_poll,
+	.poll =		datagram_poll,
 	.ioctl =	sock_no_ioctl,
 	.listen =	sock_no_listen,
 	.shutdown =	sock_no_shutdown,
@@ -3083,7 +2373,7 @@ static const struct proto_ops netlink_ops = {
 	.getsockopt =	netlink_getsockopt,
 	.sendmsg =	netlink_sendmsg,
 	.recvmsg =	netlink_recvmsg,
-	.mmap =		netlink_mmap,
+	.mmap =		sock_no_mmap,
 	.sendpage =	sock_no_sendpage,
 };
 
diff --git a/net/netlink/af_netlink.h b/net/netlink/af_netlink.h
index dcc89c74b514..4a12e9ee6052 100644
--- a/net/netlink/af_netlink.h
+++ b/net/netlink/af_netlink.h
@@ -39,12 +39,6 @@ struct netlink_sock {
 	void			(*netlink_rcv)(struct sk_buff *skb);
 	void			(*netlink_bind)(int group);
 	struct module		*module;
-#ifdef CONFIG_NETLINK_MMAP
-	struct mutex		pg_vec_lock;
-	struct netlink_ring	rx_ring;
-	struct netlink_ring	tx_ring;
-	atomic_t		mapped;
-#endif /* CONFIG_NETLINK_MMAP */
 };
 
 static inline struct netlink_sock *nlk_sk(struct sock *sk)
@@ -65,15 +59,6 @@ struct nl_portid_hash {
 	u32			rnd;
 };
 
-static inline bool netlink_skb_is_mmaped(const struct sk_buff *skb)
-{
-#ifdef CONFIG_NETLINK_MMAP
-	return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
-#else
-	return false;
-#endif /* CONFIG_NETLINK_MMAP */
-}
-
 struct netlink_table {
 	struct nl_portid_hash	hash;
 	struct hlist_head	mc_list;
diff --git a/net/netlink/diag.c b/net/netlink/diag.c
index 1af29624b92f..5ffb1d1cf402 100644
--- a/net/netlink/diag.c
+++ b/net/netlink/diag.c
@@ -7,41 +7,6 @@
 
 #include "af_netlink.h"
 
-#ifdef CONFIG_NETLINK_MMAP
-static int sk_diag_put_ring(struct netlink_ring *ring, int nl_type,
-			    struct sk_buff *nlskb)
-{
-	struct netlink_diag_ring ndr;
-
-	ndr.ndr_block_size = ring->pg_vec_pages << PAGE_SHIFT;
-	ndr.ndr_block_nr   = ring->pg_vec_len;
-	ndr.ndr_frame_size = ring->frame_size;
-	ndr.ndr_frame_nr   = ring->frame_max + 1;
-
-	return nla_put(nlskb, nl_type, sizeof(ndr), &ndr);
-}
-
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
-	struct netlink_sock *nlk = nlk_sk(sk);
-	int ret;
-
-	mutex_lock(&nlk->pg_vec_lock);
-	ret = sk_diag_put_ring(&nlk->rx_ring, NETLINK_DIAG_RX_RING, nlskb);
-	if (!ret)
-		ret = sk_diag_put_ring(&nlk->tx_ring, NETLINK_DIAG_TX_RING,
-				       nlskb);
-	mutex_unlock(&nlk->pg_vec_lock);
-
-	return ret;
-}
-#else
-static int sk_diag_put_rings_cfg(struct sock *sk, struct sk_buff *nlskb)
-{
-	return 0;
-}
-#endif
-
 static int sk_diag_dump_groups(struct sock *sk, struct sk_buff *nlskb)
 {
 	struct netlink_sock *nlk = nlk_sk(sk);
@@ -86,10 +51,6 @@ static int sk_diag_fill(struct sock *sk, struct sk_buff *skb,
 	    sock_diag_put_meminfo(sk, skb, NETLINK_DIAG_MEMINFO))
 		goto out_nlmsg_trim;
 
-	if ((req->ndiag_show & NDIAG_SHOW_RING_CFG) &&
-	    sk_diag_put_rings_cfg(sk, skb))
-		goto out_nlmsg_trim;
-
 	return nlmsg_end(skb, nlh);
 
 out_nlmsg_trim:
-- 
2.12.2

Powered by blists - more mailing lists