netdev.vger.kernel.org archive mirror
 help / color / mirror / Atom feed
From: Hideo AOKI <haoki@redhat.com>
To: David Miller <davem@davemloft.net>, netdev <netdev@vger.kernel.org>
Cc: Hideo AOKI <haoki@redhat.com>,
	Satoshi Oshima <satoshi.oshima.fk@hitachi.com>,
	Herbert Xu <herbert@gondor.apana.org.au>,
	Bill Fink <billfink@mindspring.com>,
	Andi Kleen <andi@firstfloor.org>,
	Evgeniy Polyakov <johnpol@2ka.mipt.ru>,
	Stephen Hemminger <shemminger@linux-foundation.org>,
	yoshfuji@linux-ipv6.org,
	Yumiko Sugita <yumiko.sugita.yf@hitachi.com>
Subject: [PATCH 3/5] memory accounting
Date: Tue, 13 Nov 2007 21:48:24 -0500	[thread overview]
Message-ID: <473A61F8.5040601@redhat.com> (raw)
In-Reply-To: <473A5FD6.5010209@redhat.com>

This patch adds UDP memory usage accounting in IPv4.

signed-off-by: Satoshi Oshima <satoshi.oshima.fk@hitachi.com>
signed-off-by: Hideo Aoki <haoki@redhat.com>
---

  af_inet.c   |   30 +++++++++++++++++++++++++++++-
  ip_output.c |   25 ++++++++++++++++++++++---
  udp.c       |    9 +++++++++
  3 files changed, 60 insertions(+), 4 deletions(-)

diff -pruN net-2.6-udp-p2/net/ipv4/af_inet.c net-2.6-udp-p3/net/ipv4/af_inet.c
--- net-2.6-udp-p2/net/ipv4/af_inet.c	2007-11-13 08:19:57.000000000 -0500
+++ net-2.6-udp-p3/net/ipv4/af_inet.c	2007-11-13 16:12:24.000000000 -0500
@@ -126,13 +126,41 @@ extern void ip_mc_drop_socket(struct soc
  static struct list_head inetsw[SOCK_MAX];
  static DEFINE_SPINLOCK(inetsw_lock);

+/**
+ *	__skb_queue_purge_and_sub_memory_allocated
+ *		- empty a list and subtruct memory allocation counter
+ *	@sk:   sk
+ *	@list: list to empty
+ *	Delete all buffers on an &sk_buff list and subtruct the
+ *	truesize of the sk_buff for memory accounting. Each buffer
+ *	is removed from the list and one reference dropped. This
+ *	function does not take the list lock and the caller must
+ *	hold the relevant locks to use it.
+ */
+static inline void __skb_queue_purge_and_sub_memory_allocated(struct sock *sk,
+					struct sk_buff_head *list)
+{
+	struct sk_buff *skb;
+	int purged_skb_size = 0;
+	while ((skb = __skb_dequeue(list)) != NULL) {
+		purged_skb_size += sk_datagram_pages(skb->truesize);
+		kfree_skb(skb);
+	}
+	atomic_sub(purged_skb_size, sk->sk_prot->memory_allocated);
+}
+
  /* New destruction routine */

  void inet_sock_destruct(struct sock *sk)
  {
  	struct inet_sock *inet = inet_sk(sk);

-	__skb_queue_purge(&sk->sk_receive_queue);
+	if (sk->sk_prot->memory_allocated && sk->sk_type != SOCK_STREAM)
+		__skb_queue_purge_and_sub_memory_allocated(sk,
+				&sk->sk_receive_queue);
+	else
+		__skb_queue_purge(&sk->sk_receive_queue);
+
  	__skb_queue_purge(&sk->sk_error_queue);

  	if (sk->sk_type == SOCK_STREAM && sk->sk_state != TCP_CLOSE) {
diff -pruN net-2.6-udp-p2/net/ipv4/ip_output.c net-2.6-udp-p3/net/ipv4/ip_output.c
--- net-2.6-udp-p2/net/ipv4/ip_output.c	2007-11-13 16:10:03.000000000 -0500
+++ net-2.6-udp-p3/net/ipv4/ip_output.c	2007-11-13 16:12:24.000000000 -0500
@@ -743,6 +743,8 @@ static inline int ip_ufo_append_data(str
  		/* specify the length of each IP datagram fragment*/
  		skb_shinfo(skb)->gso_size = mtu - fragheaderlen;
  		skb_shinfo(skb)->gso_type = SKB_GSO_UDP;
+		atomic_add(sk_datagram_pages(skb->truesize),
+			   sk->sk_prot->memory_allocated);
  		__skb_queue_tail(&sk->sk_write_queue, skb);

  		return 0;
@@ -924,6 +926,9 @@ alloc_new_skb:
  			}
  			if (skb == NULL)
  				goto error;
+			if (sk->sk_prot->memory_allocated)
+				atomic_add(sk_datagram_pages(skb->truesize),
+					   sk->sk_prot->memory_allocated);

  			/*
  			 *	Fill in the control structures
@@ -1023,6 +1028,8 @@ alloc_new_skb:
  				frag = &skb_shinfo(skb)->frags[i];
  				skb->truesize += PAGE_SIZE;
  				atomic_add(PAGE_SIZE, &sk->sk_wmem_alloc);
+				if (sk->sk_prot->memory_allocated)
+					atomic_inc(sk->sk_prot->memory_allocated);
  			} else {
  				err = -EMSGSIZE;
  				goto error;
@@ -1123,7 +1130,9 @@ ssize_t	ip_append_page(struct sock *sk,
  			if (unlikely(!skb)) {
  				err = -ENOBUFS;
  				goto error;
-			}
+			} else if (sk->sk_prot->memory_allocated)
+				atomic_add(sk_datagram_pages(skb->truesize),
+					   sk->sk_prot->memory_allocated);

  			/*
  			 *	Fill in the control structures
@@ -1213,13 +1222,14 @@ int ip_push_pending_frames(struct sock *
  	struct iphdr *iph;
  	__be16 df = 0;
  	__u8 ttl;
-	int err = 0;
+	int err = 0, send_page_size;

  	if ((skb = __skb_dequeue(&sk->sk_write_queue)) == NULL)
  		goto out;
  	tail_skb = &(skb_shinfo(skb)->frag_list);

  	/* move skb->data to ip header from ext header */
+	send_page_size = sk_datagram_pages(skb->truesize);
  	if (skb->data < skb_network_header(skb))
  		__skb_pull(skb, skb_network_offset(skb));
  	while ((tmp_skb = __skb_dequeue(&sk->sk_write_queue)) != NULL) {
@@ -1229,6 +1239,7 @@ int ip_push_pending_frames(struct sock *
  		skb->len += tmp_skb->len;
  		skb->data_len += tmp_skb->len;
  		skb->truesize += tmp_skb->truesize;
+		send_page_size += sk_datagram_pages(tmp_skb->truesize);
  		__sock_put(tmp_skb->sk);
  		tmp_skb->destructor = NULL;
  		tmp_skb->sk = NULL;
@@ -1284,6 +1295,8 @@ int ip_push_pending_frames(struct sock *
  	/* Netfilter gets whole the not fragmented skb. */
  	err = NF_HOOK(PF_INET, NF_IP_LOCAL_OUT, skb, NULL,
  		      skb->dst->dev, dst_output);
+	if (sk->sk_prot->memory_allocated)
+		atomic_sub(send_page_size, sk->sk_prot->memory_allocated);
  	if (err) {
  		if (err > 0)
  			err = inet->recverr ? net_xmit_errno(err) : 0;
@@ -1306,9 +1319,15 @@ error:
  void ip_flush_pending_frames(struct sock *sk)
  {
  	struct sk_buff *skb;
+	int num_flush_mem = 0;

-	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL)
+	while ((skb = __skb_dequeue_tail(&sk->sk_write_queue)) != NULL) {
+		num_flush_mem += sk_datagram_pages(skb->truesize);
  		kfree_skb(skb);
+	}
+
+	if (sk->sk_prot->memory_allocated)
+		atomic_sub(num_flush_mem, sk->sk_prot->memory_allocated);

  	ip_cork_release(inet_sk(sk));
  }
diff -pruN net-2.6-udp-p2/net/ipv4/udp.c net-2.6-udp-p3/net/ipv4/udp.c
--- net-2.6-udp-p2/net/ipv4/udp.c	2007-11-13 16:10:05.000000000 -0500
+++ net-2.6-udp-p3/net/ipv4/udp.c	2007-11-13 16:12:24.000000000 -0500
@@ -894,6 +894,9 @@ try_again:

  out_free:
  	skb_free_datagram(sk, skb);
+	atomic_sub(sk_datagram_pages(skb->truesize),
+		   sk->sk_prot->memory_allocated);
+
  out:
  	return err;

@@ -901,6 +904,8 @@ csum_copy_err:
  	UDP_INC_STATS_BH(UDP_MIB_INERRORS, is_udplite);

  	skb_kill_datagram(sk, skb, flags);
+	atomic_sub(sk_datagram_pages(skb->truesize),
+		   sk->sk_prot->memory_allocated);

  	if (noblock)
  		return -EAGAIN;
@@ -1025,6 +1030,9 @@ int udp_queue_rcv_skb(struct sock * sk,
  		goto drop;
  	}

+	atomic_add(sk_datagram_pages(skb->truesize),
+		   sk->sk_prot->memory_allocated);
+
  	UDP_INC_STATS_BH(UDP_MIB_INDATAGRAMS, up->pcflag);
  	return 0;

@@ -1451,6 +1459,7 @@ struct proto udp_prot = {
  	.hash		   = udp_lib_hash,
  	.unhash		   = udp_lib_unhash,
  	.get_port	   = udp_v4_get_port,
+	.memory_allocated  = &udp_memory_allocated,
  	.obj_size	   = sizeof(struct udp_sock),
  #ifdef CONFIG_COMPAT
  	.compat_setsockopt = compat_udp_setsockopt,
--
Hideo Aoki
Hitachi Computer Products (America) Inc.

  parent reply	other threads:[~2007-11-14  2:49 UTC|newest]

Thread overview: 9+ messages / expand[flat|nested]  mbox.gz  Atom feed  top
2007-11-14  2:39 [PATCH 0/5] UDP memory accounting and limitation (take 7) Hideo AOKI
2007-11-14  2:47 ` [PATCH 1/5] fix send buffer check Hideo AOKI
2007-11-14  2:48 ` [PATCH 2/5] accounting unit and variable Hideo AOKI
2007-11-14  2:48 ` Hideo AOKI [this message]
2007-11-14  2:48 ` [PATCH 4/5] memory limitation by using udp_mem Hideo AOKI
2007-11-14  2:49 ` [PATCH 5/5] add udp_rmem_min and udp_wmem_min Hideo AOKI
2007-11-14  4:32 ` [PATCH 0/5] UDP memory accounting and limitation (take 7) David Miller
  -- strict thread matches above, loose matches on Subject: below --
2007-10-29 21:18 [PATCH 0/5] UDP memory accounting and limitation (take 6) Hideo AOKI
2007-10-29 21:23 ` [PATCH 3/5] memory accounting Hideo AOKI
2007-11-09 13:07   ` Herbert Xu

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=473A61F8.5040601@redhat.com \
    --to=haoki@redhat.com \
    --cc=andi@firstfloor.org \
    --cc=billfink@mindspring.com \
    --cc=davem@davemloft.net \
    --cc=herbert@gondor.apana.org.au \
    --cc=johnpol@2ka.mipt.ru \
    --cc=netdev@vger.kernel.org \
    --cc=satoshi.oshima.fk@hitachi.com \
    --cc=shemminger@linux-foundation.org \
    --cc=yoshfuji@linux-ipv6.org \
    --cc=yumiko.sugita.yf@hitachi.com \
    /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).