From: Hideo AOKI <haoki@redhat.com>
To: David Miller <davem@davemloft.net>,
Herbert Xu <herbert@gondor.apana.org.au>,
vladislav.yasevich@hp.com, netdev <netdev@vger.kernel.org>
Cc: lksctp-developers@lists.sourceforge.net,
Takahiro Yasui <tyasui@redhat.com>,
Masami Hiramatsu <mhiramat@redhat.com>,
Satoshi Oshima <satoshi.oshima.fk@hitachi.com>,
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>,
haoki@redhat.com
Subject: [PATCH 3/4] [TCP]: using new interface
Date: Sun, 30 Dec 2007 03:53:53 -0500 [thread overview]
Message-ID: <47775CA1.10307@redhat.com> (raw)
In-Reply-To: <47775B25.7020401@redhat.com>
This patch replaces present memory accounting calls with new interface
in TCP.
Cc: Satoshi Oshima <satoshi.oshima.fk@hitachi.com>
Cc: Masami Hiramatsu <mhiramat@redhat.com>
signed-off-by: Takahiro Yasui <tyasui@redhat.com>
signed-off-by: Hideo Aoki <haoki@redhat.com>
---
include/net/tcp.h | 4 ++--
net/ipv4/tcp.c | 23 ++++++++++++-----------
net/ipv4/tcp_input.c | 26 +++++++++++++-------------
net/ipv4/tcp_output.c | 26 ++++++++++++++++----------
net/ipv4/tcp_timer.c | 8 ++++----
5 files changed, 47 insertions(+), 40 deletions(-)
diff -pruN net-2.6.25-t12t19m-p2/include/net/tcp.h net-2.6.25-t12t19m-p3/include/net/tcp.h
--- net-2.6.25-t12t19m-p2/include/net/tcp.h 2007-12-27 10:18:58.000000000 -0500
+++ net-2.6.25-t12t19m-p3/include/net/tcp.h 2007-12-29 20:49:59.000000000 -0500
@@ -1196,8 +1196,8 @@ static inline void tcp_write_queue_purge
struct sk_buff *skb;
while ((skb = __skb_dequeue(&sk->sk_write_queue)) != NULL)
- sk_stream_free_skb(sk, skb);
- sk_stream_mem_reclaim(sk);
+ sk_wmem_free_skb(sk, skb);
+ sk_mem_reclaim(sk);
}
static inline struct sk_buff *tcp_write_queue_head(struct sock *sk)
diff -pruN net-2.6.25-t12t19m-p2/net/ipv4/tcp.c net-2.6.25-t12t19m-p3/net/ipv4/tcp.c
--- net-2.6.25-t12t19m-p2/net/ipv4/tcp.c 2007-12-27 10:19:02.000000000 -0500
+++ net-2.6.25-t12t19m-p3/net/ipv4/tcp.c 2007-12-29 20:49:59.000000000 -0500
@@ -308,7 +308,7 @@ struct tcp_splice_state {
/*
* Pressure flag: try to collapse.
* Technical note: it is used by multiple contexts non atomically.
- * All the sk_stream_mem_schedule() is of this nature: accounting
+ * All the __sk_mem_schedule() is of this nature: accounting
* is strict, actions are advisory and have some latency.
*/
int tcp_memory_pressure __read_mostly;
@@ -485,7 +485,8 @@ static inline void skb_entail(struct soc
tcb->sacked = 0;
skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
- sk_charge_skb(sk, skb);
+ sk->sk_wmem_queued += skb->truesize;
+ sk_mem_charge(sk, skb->truesize);
if (tp->nonagle & TCP_NAGLE_PUSH)
tp->nonagle &= ~TCP_NAGLE_PUSH;
}
@@ -638,7 +639,7 @@ struct sk_buff *sk_stream_alloc_skb(stru
skb = alloc_skb_fclone(size + sk->sk_prot->max_header, gfp);
if (skb) {
- if (sk_stream_wmem_schedule(sk, skb->truesize)) {
+ if (sk_wmem_schedule(sk, skb->truesize)) {
/*
* Make sure that we have exactly size bytes
* available to the caller, no more, no less.
@@ -707,7 +708,7 @@ new_segment:
tcp_mark_push(tp, skb);
goto new_segment;
}
- if (!sk_stream_wmem_schedule(sk, copy))
+ if (!sk_wmem_schedule(sk, copy))
goto wait_for_memory;
if (can_coalesce) {
@@ -721,7 +722,7 @@ new_segment:
skb->data_len += copy;
skb->truesize += copy;
sk->sk_wmem_queued += copy;
- sk->sk_forward_alloc -= copy;
+ sk_mem_charge(sk, copy);
skb->ip_summed = CHECKSUM_PARTIAL;
tp->write_seq += copy;
TCP_SKB_CB(skb)->end_seq += copy;
@@ -928,7 +929,7 @@ new_segment:
if (copy > PAGE_SIZE - off)
copy = PAGE_SIZE - off;
- if (!sk_stream_wmem_schedule(sk, copy))
+ if (!sk_wmem_schedule(sk, copy))
goto wait_for_memory;
if (!page) {
@@ -1019,7 +1020,7 @@ do_fault:
* reset, where we can be unlinking the send_head.
*/
tcp_check_send_head(sk, skb);
- sk_stream_free_skb(sk, skb);
+ sk_wmem_free_skb(sk, skb);
}
do_error:
@@ -1738,7 +1739,7 @@ void tcp_close(struct sock *sk, long tim
__kfree_skb(skb);
}
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
/* As outlined in RFC 2525, section 2.17, we send a RST here because
* data was lost. To witness the awful effects of the old behavior of
@@ -1841,7 +1842,7 @@ adjudge_to_death:
}
}
if (sk->sk_state != TCP_CLOSE) {
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
if (tcp_too_many_orphans(sk,
atomic_read(sk->sk_prot->orphan_count))) {
if (net_ratelimit())
@@ -2658,11 +2659,11 @@ void __init tcp_init(void)
limit = ((unsigned long)sysctl_tcp_mem[1]) << (PAGE_SHIFT - 7);
max_share = min(4UL*1024*1024, limit);
- sysctl_tcp_wmem[0] = SK_STREAM_MEM_QUANTUM;
+ sysctl_tcp_wmem[0] = SK_MEM_QUANTUM;
sysctl_tcp_wmem[1] = 16*1024;
sysctl_tcp_wmem[2] = max(64*1024, max_share);
- sysctl_tcp_rmem[0] = SK_STREAM_MEM_QUANTUM;
+ sysctl_tcp_rmem[0] = SK_MEM_QUANTUM;
sysctl_tcp_rmem[1] = 87380;
sysctl_tcp_rmem[2] = max(87380, max_share);
diff -pruN net-2.6.25-t12t19m-p2/net/ipv4/tcp_input.c net-2.6.25-t12t19m-p3/net/ipv4/tcp_input.c
--- net-2.6.25-t12t19m-p2/net/ipv4/tcp_input.c 2007-12-27 10:19:02.000000000 -0500
+++ net-2.6.25-t12t19m-p3/net/ipv4/tcp_input.c 2007-12-29 20:49:59.000000000 -0500
@@ -591,7 +591,7 @@ static void tcp_event_data_recv(struct s
* restart window, so that we send ACKs quickly.
*/
tcp_incr_quickack(sk);
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
}
}
icsk->icsk_ack.lrcvtime = now;
@@ -2848,7 +2848,7 @@ static int tcp_clean_rtx_queue(struct so
break;
tcp_unlink_write_queue(skb, sk);
- sk_stream_free_skb(sk, skb);
+ sk_wmem_free_skb(sk, skb);
tcp_clear_all_retrans_hints(tp);
}
@@ -3564,7 +3564,7 @@ static void tcp_fin(struct sk_buff *skb,
__skb_queue_purge(&tp->out_of_order_queue);
if (tcp_is_sack(tp))
tcp_sack_reset(&tp->rx_opt);
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
if (!sock_flag(sk, SOCK_DEAD)) {
sk->sk_state_change(sk);
@@ -3847,12 +3847,12 @@ static void tcp_data_queue(struct sock *
queue_and_out:
if (eaten < 0 &&
(atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- !sk_stream_rmem_schedule(sk, skb))) {
+ !sk_rmem_schedule(sk, skb->truesize))) {
if (tcp_prune_queue(sk) < 0 ||
- !sk_stream_rmem_schedule(sk, skb))
+ !sk_rmem_schedule(sk, skb->truesize))
goto drop;
}
- sk_stream_set_owner_r(skb, sk);
+ skb_set_owner_r(skb, sk);
__skb_queue_tail(&sk->sk_receive_queue, skb);
}
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
@@ -3921,9 +3921,9 @@ drop:
TCP_ECN_check_ce(tp, skb);
if (atomic_read(&sk->sk_rmem_alloc) > sk->sk_rcvbuf ||
- !sk_stream_rmem_schedule(sk, skb)) {
+ !sk_rmem_schedule(sk, skb->truesize)) {
if (tcp_prune_queue(sk) < 0 ||
- !sk_stream_rmem_schedule(sk, skb))
+ !sk_rmem_schedule(sk, skb->truesize))
goto drop;
}
@@ -3934,7 +3934,7 @@ drop:
SOCK_DEBUG(sk, "out of order segment: rcv_next %X seq %X - %X\n",
tp->rcv_nxt, TCP_SKB_CB(skb)->seq, TCP_SKB_CB(skb)->end_seq);
- sk_stream_set_owner_r(skb, sk);
+ skb_set_owner_r(skb, sk);
if (!skb_peek(&tp->out_of_order_queue)) {
/* Initial out of order segment, build 1 SACK. */
@@ -4076,7 +4076,7 @@ tcp_collapse(struct sock *sk, struct sk_
memcpy(nskb->cb, skb->cb, sizeof(skb->cb));
TCP_SKB_CB(nskb)->seq = TCP_SKB_CB(nskb)->end_seq = start;
__skb_insert(nskb, skb->prev, skb, list);
- sk_stream_set_owner_r(nskb, sk);
+ skb_set_owner_r(nskb, sk);
/* Copy data, releasing collapsed skbs. */
while (copy > 0) {
@@ -4174,7 +4174,7 @@ static int tcp_prune_queue(struct sock *
sk->sk_receive_queue.next,
(struct sk_buff*)&sk->sk_receive_queue,
tp->copied_seq, tp->rcv_nxt);
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
return 0;
@@ -4194,7 +4194,7 @@ static int tcp_prune_queue(struct sock *
*/
if (tcp_is_sack(tp))
tcp_sack_reset(&tp->rx_opt);
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
}
if (atomic_read(&sk->sk_rmem_alloc) <= sk->sk_rcvbuf)
@@ -4696,7 +4696,7 @@ int tcp_rcv_established(struct sock *sk,
/* Bulk data transfer: receiver */
__skb_pull(skb,tcp_header_len);
__skb_queue_tail(&sk->sk_receive_queue, skb);
- sk_stream_set_owner_r(skb, sk);
+ skb_set_owner_r(skb, sk);
tp->rcv_nxt = TCP_SKB_CB(skb)->end_seq;
}
diff -pruN net-2.6.25-t12t19m-p2/net/ipv4/tcp_output.c net-2.6.25-t12t19m-p3/net/ipv4/tcp_output.c
--- net-2.6.25-t12t19m-p2/net/ipv4/tcp_output.c 2007-12-27 10:19:02.000000000 -0500
+++ net-2.6.25-t12t19m-p3/net/ipv4/tcp_output.c 2007-12-29 20:49:59.000000000 -0500
@@ -637,7 +637,8 @@ static void tcp_queue_skb(struct sock *s
tp->write_seq = TCP_SKB_CB(skb)->end_seq;
skb_header_release(skb);
tcp_add_write_queue_tail(sk, skb);
- sk_charge_skb(sk, skb);
+ sk->sk_wmem_queued += skb->truesize;
+ sk_mem_charge(sk, skb->truesize);
}
static void tcp_set_skb_tso_segs(struct sock *sk, struct sk_buff *skb, unsigned int mss_now)
@@ -701,7 +702,8 @@ int tcp_fragment(struct sock *sk, struct
if (buff == NULL)
return -ENOMEM; /* We'll just try again later. */
- sk_charge_skb(sk, buff);
+ sk->sk_wmem_queued += buff->truesize;
+ sk_mem_charge(sk, buff->truesize);
nlen = skb->len - len - nsize;
buff->truesize += nlen;
skb->truesize -= nlen;
@@ -825,7 +827,7 @@ int tcp_trim_head(struct sock *sk, struc
skb->truesize -= len;
sk->sk_wmem_queued -= len;
- sk->sk_forward_alloc += len;
+ sk_mem_uncharge(sk, len);
sock_set_flag(sk, SOCK_QUEUE_SHRUNK);
/* Any change of skb->len requires recalculation of tso
@@ -1197,7 +1199,8 @@ static int tso_fragment(struct sock *sk,
if (unlikely(buff == NULL))
return -ENOMEM;
- sk_charge_skb(sk, buff);
+ sk->sk_wmem_queued += buff->truesize;
+ sk_mem_charge(sk, buff->truesize);
buff->truesize += nlen;
skb->truesize -= nlen;
@@ -1350,7 +1353,8 @@ static int tcp_mtu_probe(struct sock *sk
/* We're allowed to probe. Build it now. */
if ((nskb = sk_stream_alloc_skb(sk, probe_size, GFP_ATOMIC)) == NULL)
return -1;
- sk_charge_skb(sk, nskb);
+ sk->sk_wmem_queued += nskb->truesize;
+ sk_mem_charge(sk, nskb->truesize);
skb = tcp_send_head(sk);
@@ -1377,7 +1381,7 @@ static int tcp_mtu_probe(struct sock *sk
* Throw it away. */
TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags;
tcp_unlink_write_queue(skb, sk);
- sk_stream_free_skb(sk, skb);
+ sk_wmem_free_skb(sk, skb);
} else {
TCP_SKB_CB(nskb)->flags |= TCP_SKB_CB(skb)->flags &
~(TCPCB_FLAG_FIN|TCPCB_FLAG_PSH);
@@ -1744,7 +1748,7 @@ static void tcp_retrans_try_collapse(str
/* changed transmit queue under us so clear hints */
tcp_clear_retrans_hints_partial(tp);
- sk_stream_free_skb(sk, next_skb);
+ sk_wmem_free_skb(sk, next_skb);
}
}
@@ -2139,8 +2143,9 @@ int tcp_send_synack(struct sock *sk)
tcp_unlink_write_queue(skb, sk);
skb_header_release(nskb);
__tcp_add_write_queue_head(sk, nskb);
- sk_stream_free_skb(sk, skb);
- sk_charge_skb(sk, nskb);
+ sk_wmem_free_skb(sk, skb);
+ sk->sk_wmem_queued += nskb->truesize;
+ sk_mem_charge(sk, nskb->truesize);
skb = nskb;
}
@@ -2343,7 +2348,8 @@ int tcp_connect(struct sock *sk)
tp->retrans_stamp = TCP_SKB_CB(buff)->when;
skb_header_release(buff);
__tcp_add_write_queue_tail(sk, buff);
- sk_charge_skb(sk, buff);
+ sk->sk_wmem_queued += buff->truesize;
+ sk_mem_charge(sk, buff->truesize);
tp->packets_out += tcp_skb_pcount(buff);
tcp_transmit_skb(sk, buff, 1, GFP_KERNEL);
diff -pruN net-2.6.25-t12t19m-p2/net/ipv4/tcp_timer.c net-2.6.25-t12t19m-p3/net/ipv4/tcp_timer.c
--- net-2.6.25-t12t19m-p2/net/ipv4/tcp_timer.c 2007-12-27 10:19:02.000000000 -0500
+++ net-2.6.25-t12t19m-p3/net/ipv4/tcp_timer.c 2007-12-29 20:49:59.000000000 -0500
@@ -186,7 +186,7 @@ static void tcp_delack_timer(unsigned lo
goto out_unlock;
}
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
if (sk->sk_state == TCP_CLOSE || !(icsk->icsk_ack.pending & ICSK_ACK_TIMER))
goto out;
@@ -226,7 +226,7 @@ static void tcp_delack_timer(unsigned lo
out:
if (tcp_memory_pressure)
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
out_unlock:
bh_unlock_sock(sk);
sock_put(sk);
@@ -420,7 +420,7 @@ static void tcp_write_timer(unsigned lon
TCP_CHECK_TIMER(sk);
out:
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
out_unlock:
bh_unlock_sock(sk);
sock_put(sk);
@@ -514,7 +514,7 @@ static void tcp_keepalive_timer (unsigne
}
TCP_CHECK_TIMER(sk);
- sk_stream_mem_reclaim(sk);
+ sk_mem_reclaim(sk);
resched:
inet_csk_reset_keepalive_timer (sk, elapsed);
--
Hitachi Computer Products (America) Inc.
next prev parent reply other threads:[~2007-12-30 8:59 UTC|newest]
Thread overview: 12+ messages / expand[flat|nested] mbox.gz Atom feed top
2007-12-30 8:47 [PATCH 0/4] New interface for memory accounting (take 1) Hideo AOKI
2007-12-30 8:51 ` [PATCH 1/4] [CORE]: introducing new memory accounting interface Hideo AOKI
2007-12-30 8:51 ` [PATCH 2/4] [CORE]: adding memory accounting points Hideo AOKI
2007-12-31 7:58 ` David Miller
2007-12-31 18:52 ` Hideo AOKI
2007-12-30 8:53 ` Hideo AOKI [this message]
2007-12-30 8:54 ` [PATCH 4/4] [SCTP]: using new interface Hideo AOKI
2007-12-31 7:34 ` [PATCH 0/4] New interface for memory accounting (take 1) David Miller
2007-12-31 15:17 ` Eric Dumazet
2007-12-31 19:03 ` Hideo AOKI
2007-12-31 23:01 ` David Miller
2007-12-31 18:46 ` Hideo AOKI
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=47775CA1.10307@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=lksctp-developers@lists.sourceforge.net \
--cc=mhiramat@redhat.com \
--cc=netdev@vger.kernel.org \
--cc=satoshi.oshima.fk@hitachi.com \
--cc=shemminger@linux-foundation.org \
--cc=tyasui@redhat.com \
--cc=vladislav.yasevich@hp.com \
--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 an external index of several public inboxes,
see mirroring instructions on how to clone and mirror
all data and code used by this external index.