From: Patrick McHardy <kaber@trash.net>
To: Florian.Westphal@Sophos.com
Cc: netdev@vger.kernel.org, netfilter-devel@vger.kernel.org
Subject: [PATCH 08/11] netlink: implement memory mapped recvmsg()
Date: Mon, 20 Aug 2012 08:18:49 +0200 [thread overview]
Message-ID: <1345443532-3707-9-git-send-email-kaber@trash.net> (raw)
In-Reply-To: <1345443532-3707-1-git-send-email-kaber@trash.net>
Signed-off-by: Patrick McHardy <kaber@trash.net>
---
include/linux/netlink.h | 2 +
net/netlink/af_netlink.c | 145 ++++++++++++++++++++++++++++++++++++++++++++-
2 files changed, 143 insertions(+), 4 deletions(-)
diff --git a/include/linux/netlink.h b/include/linux/netlink.h
index 98754e8..144ef3a 100644
--- a/include/linux/netlink.h
+++ b/include/linux/netlink.h
@@ -232,6 +232,8 @@ extern void __netlink_clear_multicast_users(struct sock *sk, unsigned int group)
extern void netlink_clear_multicast_users(struct sock *sk, unsigned int group);
extern void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err);
extern int netlink_has_listeners(struct sock *sk, unsigned int group);
+extern struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
+ u32 dst_pid, gfp_t gfp_mask);
extern int netlink_unicast(struct sock *ssk, struct sk_buff *skb, __u32 pid, int nonblock);
extern int netlink_broadcast(struct sock *ssk, struct sk_buff *skb, __u32 pid,
__u32 group, gfp_t allocation);
diff --git a/net/netlink/af_netlink.c b/net/netlink/af_netlink.c
index 65867fd..c42a601 100644
--- a/net/netlink/af_netlink.c
+++ b/net/netlink/af_netlink.c
@@ -183,6 +183,11 @@ static bool netlink_skb_is_mmaped(const struct sk_buff *skb)
return NETLINK_CB(skb).flags & NETLINK_SKB_MMAPED;
}
+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;
@@ -654,8 +659,54 @@ 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 = NETLINK_CB(skb).creds.uid;
+ hdr->nm_gid = NETLINK_CB(skb).creds.gid;
+ netlink_frame_flush_dcache(hdr);
+ 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);
+ sk->sk_err = ENOBUFS;
+ sk->sk_error_report(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 = NETLINK_CB(skb).creds.uid;
+ hdr->nm_gid = NETLINK_CB(skb).creds.gid;
+ netlink_set_status(hdr, NL_MMAP_STATUS_COPY);
+}
+
#else /* CONFIG_NETLINK_MMAP */
#define netlink_skb_is_mmaped(skb) false
+#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
@@ -1434,7 +1485,14 @@ static int __netlink_sendskb(struct sock *sk, struct sk_buff *skb)
{
int len = skb->len;
- skb_queue_tail(&sk->sk_receive_queue, 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);
sk->sk_data_ready(sk, len);
return len;
}
@@ -1543,6 +1601,68 @@ retry:
}
EXPORT_SYMBOL(netlink_unicast);
+struct sk_buff *netlink_alloc_skb(struct sock *ssk, unsigned int size,
+ u32 dst_pid, 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_getsockbypid(ssk, dst_pid);
+ 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);
+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);
+
int netlink_has_listeners(struct sock *sk, unsigned int group)
{
int res = 0;
@@ -2328,9 +2448,13 @@ static int netlink_dump(struct sock *sk)
alloc_size = max_t(int, cb->min_dump_alloc, NLMSG_GOODSIZE);
- skb = sock_rmalloc(sk, alloc_size, 0, GFP_KERNEL);
+ if (!netlink_rx_is_mmaped(sk) &&
+ atomic_read(&sk->sk_rmem_alloc) >= sk->sk_rcvbuf)
+ goto errout_skb;
+ skb = netlink_alloc_skb(sk, alloc_size, nlk->pid, GFP_KERNEL);
if (!skb)
goto errout_skb;
+ netlink_skb_set_owner_r(skb, sk);
len = cb->dump(skb, cb);
@@ -2384,12 +2508,24 @@ int netlink_dump_start(struct sock *ssk, struct sk_buff *skb,
if (cb == NULL)
return -ENOBUFS;
+ /* Memory mapped dump requests need to be copied to avoid looping
+ * on the pending state in netlink_mmap_sendmsg() while the cb holds
+ * a reference to the skb.
+ */
+ if (netlink_skb_is_mmaped(skb)) {
+ skb = skb_copy(skb, GFP_KERNEL);
+ if (skb == NULL) {
+ kfree(cb);
+ return -ENOBUFS;
+ }
+ } else
+ atomic_inc(&skb->users);
+
cb->dump = control->dump;
cb->done = control->done;
cb->nlh = nlh;
cb->data = control->data;
cb->min_dump_alloc = control->min_dump_alloc;
- atomic_inc(&skb->users);
cb->skb = skb;
sk = netlink_lookup(sock_net(ssk), ssk->sk_protocol, NETLINK_CB(skb).pid);
@@ -2434,7 +2570,8 @@ void netlink_ack(struct sk_buff *in_skb, struct nlmsghdr *nlh, int err)
if (err)
payload += nlmsg_len(nlh);
- skb = nlmsg_new(payload, GFP_KERNEL);
+ skb = netlink_alloc_skb(in_skb->sk, nlmsg_total_size(payload),
+ NETLINK_CB(in_skb).pid, GFP_KERNEL);
if (!skb) {
struct sock *sk;
--
1.7.7.6
next prev parent reply other threads:[~2012-08-20 6:18 UTC|newest]
Thread overview: 17+ messages / expand[flat|nested] mbox.gz Atom feed top
2012-08-20 6:18 [PATCH 00/11] netlink: memory mapped I/O Patrick McHardy
2012-08-20 6:18 ` [PATCH 01/11] netlink: add symbolic value for congested state Patrick McHardy
2012-08-20 6:18 ` [PATCH 02/11] net: add function to allocate skbuff head without data area Patrick McHardy
2012-08-20 6:39 ` Eric Dumazet
2012-08-20 6:41 ` Patrick McHardy
2012-08-20 6:18 ` [PATCH 03/11] netlink: don't orphan skb in netlink_trim() Patrick McHardy
2012-08-20 6:18 ` [PATCH 04/11] netlink: add netlink_skb_set_owner_r() Patrick McHardy
2012-08-20 6:18 ` [PATCH 05/11] netlink: mmaped netlink: ring setup Patrick McHardy
2012-08-20 6:18 ` [PATCH 06/11] netlink: add mmap'ed netlink helper functions Patrick McHardy
2012-08-20 6:18 ` [PATCH 07/11] netlink: implement memory mapped sendmsg() Patrick McHardy
2012-08-20 6:18 ` Patrick McHardy [this message]
2012-08-20 6:18 ` [PATCH 09/11] nfnetlink: add support for memory mapped netlink Patrick McHardy
2012-08-20 6:18 ` [PATCH 10/11] netlink: add flow control for memory mapped I/O Patrick McHardy
2012-08-20 6:18 ` [PATCH 11/11] netlink: add documentation " Patrick McHardy
2012-08-20 10:32 ` Jan Engelhardt
2012-08-22 22:19 ` Patrick McHardy
2012-08-22 9:29 ` [PATCH 00/11] netlink: " David Miller
Reply instructions:
You may reply publicly to this message via plain-text email
using any one of the following methods:
* Save the following mbox file, import it into your mail client,
and reply-to-all from there: mbox
Avoid top-posting and favor interleaved quoting:
https://en.wikipedia.org/wiki/Posting_style#Interleaved_style
* Reply using the --to, --cc, and --in-reply-to
switches of git-send-email(1):
git send-email \
--in-reply-to=1345443532-3707-9-git-send-email-kaber@trash.net \
--to=kaber@trash.net \
--cc=Florian.Westphal@Sophos.com \
--cc=netdev@vger.kernel.org \
--cc=netfilter-devel@vger.kernel.org \
/path/to/YOUR_REPLY
https://kernel.org/pub/software/scm/git/docs/git-send-email.html
* If your mail client supports setting the In-Reply-To header
via mailto: links, try the mailto: link
Be sure your reply has a Subject: header at the top and a blank line
before the message body.
This is a public inbox, see mirroring instructions
for how to clone and mirror all data and code used for this inbox;
as well as URLs for NNTP newsgroup(s).