From 38a7ddffa4b79d7b1fbc9bf2fa82b21b72622858 Mon Sep 17 00:00:00 2001 From: Petr Tesarik Date: Thu, 13 Nov 2008 22:44:11 -0800 Subject: tcp: remove an unnecessary field in struct tcp_skb_cb The urg_ptr field is not used anywhere and is merely confusing. Signed-off-by: Petr Tesarik Signed-off-by: David S. Miller --- include/net/tcp.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 438014d5761..8f26b28fb40 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -590,7 +590,6 @@ struct tcp_skb_cb { #define TCPCB_EVER_RETRANS 0x80 /* Ever retransmitted frame */ #define TCPCB_RETRANS (TCPCB_SACKED_RETRANS|TCPCB_EVER_RETRANS) - __u16 urg_ptr; /* Valid w/URG flags is set. */ __u32 ack_seq; /* Sequence number ACK'd */ }; -- cgit v1.2.3-70-g09d2 From e1aa680fa40e7492260a09cb57d94002245cc8fe Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 24 Nov 2008 21:11:55 -0800 Subject: tcp: move tcp_simple_retransmit to tcp_input MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 2 -- net/ipv4/tcp_input.c | 53 ++++++++++++++++++++++++++++++++++++++++++++++++++- net/ipv4/tcp_output.c | 50 ------------------------------------------------ 3 files changed, 52 insertions(+), 53 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 8f26b28fb40..90b4c3b4c33 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -472,8 +472,6 @@ extern void tcp_send_delayed_ack(struct sock *sk); /* tcp_input.c */ extern void tcp_cwnd_application_limited(struct sock *sk); -extern void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, - struct sk_buff *skb); /* tcp_timer.c */ extern void tcp_init_xmit_timers(struct sock *); diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 097294b7da3..8085704863f 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1002,7 +1002,8 @@ static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) } } -void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) +static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, + struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); @@ -2559,6 +2560,56 @@ static void tcp_mtup_probe_success(struct sock *sk, struct sk_buff *skb) tcp_sync_mss(sk, icsk->icsk_pmtu_cookie); } +/* Do a simple retransmit without using the backoff mechanisms in + * tcp_timer. This is used for path mtu discovery. + * The socket is already locked here. + */ +void tcp_simple_retransmit(struct sock *sk) +{ + const struct inet_connection_sock *icsk = inet_csk(sk); + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + unsigned int mss = tcp_current_mss(sk, 0); + u32 prior_lost = tp->lost_out; + + tcp_for_write_queue(skb, sk) { + if (skb == tcp_send_head(sk)) + break; + if (skb->len > mss && + !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { + if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { + TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; + tp->retrans_out -= tcp_skb_pcount(skb); + } + tcp_skb_mark_lost_uncond_verify(tp, skb); + } + } + + tcp_clear_retrans_hints_partial(tp); + + if (prior_lost == tp->lost_out) + return; + + if (tcp_is_reno(tp)) + tcp_limit_reno_sacked(tp); + + tcp_verify_left_out(tp); + + /* Don't muck with the congestion window here. + * Reason is that we do not increase amount of _data_ + * in network, but units changed and effective + * cwnd/ssthresh really reduced now. + */ + if (icsk->icsk_ca_state != TCP_CA_Loss) { + tp->high_seq = tp->snd_nxt; + tp->snd_ssthresh = tcp_current_ssthresh(sk); + tp->prior_ssthresh = 0; + tp->undo_marker = 0; + tcp_set_ca_state(sk, TCP_CA_Loss); + } + tcp_xmit_retransmit_queue(sk); +} + /* Process an event, which can update packets-in-flight not trivially. * Main goal of this function is to calculate new estimate for left_out, * taking into account both packets sitting in receiver's buffer and diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 86ef98975e9..c069ecb81ea 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -1879,56 +1879,6 @@ static void tcp_retrans_try_collapse(struct sock *sk, struct sk_buff *to, } } -/* Do a simple retransmit without using the backoff mechanisms in - * tcp_timer. This is used for path mtu discovery. - * The socket is already locked here. - */ -void tcp_simple_retransmit(struct sock *sk) -{ - const struct inet_connection_sock *icsk = inet_csk(sk); - struct tcp_sock *tp = tcp_sk(sk); - struct sk_buff *skb; - unsigned int mss = tcp_current_mss(sk, 0); - u32 prior_lost = tp->lost_out; - - tcp_for_write_queue(skb, sk) { - if (skb == tcp_send_head(sk)) - break; - if (skb->len > mss && - !(TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_ACKED)) { - if (TCP_SKB_CB(skb)->sacked & TCPCB_SACKED_RETRANS) { - TCP_SKB_CB(skb)->sacked &= ~TCPCB_SACKED_RETRANS; - tp->retrans_out -= tcp_skb_pcount(skb); - } - tcp_skb_mark_lost_uncond_verify(tp, skb); - } - } - - tcp_clear_retrans_hints_partial(tp); - - if (prior_lost == tp->lost_out) - return; - - if (tcp_is_reno(tp)) - tcp_limit_reno_sacked(tp); - - tcp_verify_left_out(tp); - - /* Don't muck with the congestion window here. - * Reason is that we do not increase amount of _data_ - * in network, but units changed and effective - * cwnd/ssthresh really reduced now. - */ - if (icsk->icsk_ca_state != TCP_CA_Loss) { - tp->high_seq = tp->snd_nxt; - tp->snd_ssthresh = tcp_current_ssthresh(sk); - tp->prior_ssthresh = 0; - tp->undo_marker = 0; - tcp_set_ca_state(sk, TCP_CA_Loss); - } - tcp_xmit_retransmit_queue(sk); -} - /* This retransmits one SKB. Policy decisions and retransmit queue * state updates are done by the caller. Returns non-zero if an * error occurred which prevented the send. -- cgit v1.2.3-70-g09d2 From 832d11c5cd076abc0aa1eaf7be96c81d1a59ce41 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Mon, 24 Nov 2008 21:20:15 -0800 Subject: tcp: Try to restore large SKBs while SACK processing MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit During SACK processing, most of the benefits of TSO are eaten by the SACK blocks that one-by-one fragment SKBs to MSS sized chunks. Then we're in problems when cleanup work for them has to be done when a large cumulative ACK comes. Try to return back to pre-split state already while more and more SACK info gets discovered by combining newly discovered SACK areas with the previous skb if that's SACKed as well. This approach has a number of benefits: 1) The processing overhead is spread more equally over the RTT 2) Write queue has less skbs to process (affect everything which has to walk in the queue past the sacked areas) 3) Write queue is consistent whole the time, so no other parts of TCP has to be aware of this (this was not the case with some other approach that was, well, quite intrusive all around). 4) Clean_rtx_queue can release most of the pages using single put_page instead of previous PAGE_SIZE/mss+1 calls In case a hole is fully filled by the new SACK block, we attempt to combine the next skb too which allows construction of skbs that are even larger than what tso split them to and it handles hole per on every nth patterns that often occur during slow start overshoot pretty nicely. Though this to be really useful also a retransmission would have to get lost since cumulative ACKs advance one hole at a time in the most typical case. TODO: handle upwards only merging. That should be rather easy when segment is fully sacked but I'm leaving that as future work item (it won't make very large difference anyway since this current approach already covers quite a lot of normal cases). I was earlier thinking of some sophisticated way of tracking timestamps of the first and the last segment but later on realized that it won't be that necessary at all to store the timestamp of the last segment. The cases that can occur are basically either: 1) ambiguous => no sensible measurement can be taken anyway 2) non-ambiguous is due to reordering => having the timestamp of the last segment there is just skewing things more off than does some good since the ack got triggered by one of the holes (besides some substle issues that would make determining right hole/skb even harder problem). Anyway, it has nothing to do with this change then. I choose to route some abnormal looking cases with goto noop, some could be handled differently (eg., by stopping the walking at that skb but again). In general, they either shouldn't happen at all or are rare enough to make no difference in practice. In theory this change (as whole) could cause some macroscale regression (global) because of cache misses that are taken over the round-trip time but it gets very likely better because of much less (local) cache misses per other write queue walkers and the big recovery clearing cumulative ack. Worth to note that these benefits would be very easy to get also without TSO/GSO being on as long as the data is in pages so that we can merge them. Currently I won't let that happen because DSACK splitting at fragment that would mess up pcounts due to sk_can_gso in tcp_set_skb_tso_segs. Once DSACKs fragments gets avoided, we have some conditions that can be made less strict. TODO: I will probably have to convert the excessive pointer passing to struct sacktag_state... :-) My testing revealed that considerable amount of skbs couldn't be shifted because they were cloned (most likely still awaiting tx reclaim)... [The rest is considering future work instead since I got repeatably EFAULT to tcpdump's recvfrom when I added pskb_expand_head to deal with clones, so I separated that into another, later patch] ...To counter that, I gave up on the fifth advantage: 5) When growing previous SACK block, less allocs for new skbs are done, basically a new alloc is needed only when new hole is detected and when the previous skb runs out of frags space ...which now only happens of if reclaim is fast enough to dispose the clone before the SACK block comes in (the window is RTT long), otherwise we'll have to alloc some. With clones being handled I got these numbers (will be somewhat worse without that), taken with fine-grained mibs: TCPSackShifted 398 TCPSackMerged 877 TCPSackShiftFallback 320 TCPSACKCOLLAPSEFALLBACKGSO 0 TCPSACKCOLLAPSEFALLBACKSKBBITS 0 TCPSACKCOLLAPSEFALLBACKSKBDATA 0 TCPSACKCOLLAPSEFALLBACKBELOW 0 TCPSACKCOLLAPSEFALLBACKFIRST 1 TCPSACKCOLLAPSEFALLBACKPREVBITS 318 TCPSACKCOLLAPSEFALLBACKMSS 1 TCPSACKCOLLAPSEFALLBACKNOHEAD 0 TCPSACKCOLLAPSEFALLBACKSHIFT 0 TCPSACKCOLLAPSENOOPSEQ 0 TCPSACKCOLLAPSENOOPSMALLPCOUNT 0 TCPSACKCOLLAPSENOOPSMALLLEN 0 TCPSACKCOLLAPSEHOLE 12 Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/linux/skbuff.h | 33 +++++++ include/net/tcp.h | 5 + net/core/skbuff.c | 140 +++++++++++++++++++++++++++ net/ipv4/tcp_input.c | 256 +++++++++++++++++++++++++++++++++++++++++++++++-- 4 files changed, 427 insertions(+), 7 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index a01b6f84e3b..acf17af45af 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -492,6 +492,19 @@ static inline bool skb_queue_is_last(const struct sk_buff_head *list, return (skb->next == (struct sk_buff *) list); } +/** + * skb_queue_is_first - check if skb is the first entry in the queue + * @list: queue head + * @skb: buffer + * + * Returns true if @skb is the first buffer on the list. + */ +static inline bool skb_queue_is_first(const struct sk_buff_head *list, + const struct sk_buff *skb) +{ + return (skb->prev == (struct sk_buff *) list); +} + /** * skb_queue_next - return the next packet in the queue * @list: queue head @@ -510,6 +523,24 @@ static inline struct sk_buff *skb_queue_next(const struct sk_buff_head *list, return skb->next; } +/** + * skb_queue_prev - return the prev packet in the queue + * @list: queue head + * @skb: current buffer + * + * Return the prev packet in @list before @skb. It is only valid to + * call this if skb_queue_is_first() evaluates to false. + */ +static inline struct sk_buff *skb_queue_prev(const struct sk_buff_head *list, + const struct sk_buff *skb) +{ + /* This BUG_ON may seem severe, but if we just return then we + * are going to dereference garbage. + */ + BUG_ON(skb_queue_is_first(list, skb)); + return skb->prev; +} + /** * skb_get - reference buffer * @skb: buffer to reference @@ -1652,6 +1683,8 @@ extern int skb_splice_bits(struct sk_buff *skb, extern void skb_copy_and_csum_dev(const struct sk_buff *skb, u8 *to); extern void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len); +extern int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, + int shiftlen); extern struct sk_buff *skb_segment(struct sk_buff *skb, int features); diff --git a/include/net/tcp.h b/include/net/tcp.h index 90b4c3b4c33..265392470b2 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1192,6 +1192,11 @@ static inline struct sk_buff *tcp_write_queue_next(struct sock *sk, struct sk_bu return skb_queue_next(&sk->sk_write_queue, skb); } +static inline struct sk_buff *tcp_write_queue_prev(struct sock *sk, struct sk_buff *skb) +{ + return skb_queue_prev(&sk->sk_write_queue, skb); +} + #define tcp_for_write_queue(skb, sk) \ skb_queue_walk(&(sk)->sk_write_queue, skb) diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 267185a848f..844b8abeb18 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -2018,6 +2018,146 @@ void skb_split(struct sk_buff *skb, struct sk_buff *skb1, const u32 len) skb_split_no_header(skb, skb1, len, pos); } +/* Shifting from/to a cloned skb is a no-go. + * + * TODO: handle cloned skbs by using pskb_expand_head() + */ +static int skb_prepare_for_shift(struct sk_buff *skb) +{ + return skb_cloned(skb); +} + +/** + * skb_shift - Shifts paged data partially from skb to another + * @tgt: buffer into which tail data gets added + * @skb: buffer from which the paged data comes from + * @shiftlen: shift up to this many bytes + * + * Attempts to shift up to shiftlen worth of bytes, which may be less than + * the length of the skb, from tgt to skb. Returns number bytes shifted. + * It's up to caller to free skb if everything was shifted. + * + * If @tgt runs out of frags, the whole operation is aborted. + * + * Skb cannot include anything else but paged data while tgt is allowed + * to have non-paged data as well. + * + * TODO: full sized shift could be optimized but that would need + * specialized skb free'er to handle frags without up-to-date nr_frags. + */ +int skb_shift(struct sk_buff *tgt, struct sk_buff *skb, int shiftlen) +{ + int from, to, merge, todo; + struct skb_frag_struct *fragfrom, *fragto; + + BUG_ON(shiftlen > skb->len); + BUG_ON(skb_headlen(skb)); /* Would corrupt stream */ + + todo = shiftlen; + from = 0; + to = skb_shinfo(tgt)->nr_frags; + fragfrom = &skb_shinfo(skb)->frags[from]; + + /* Actual merge is delayed until the point when we know we can + * commit all, so that we don't have to undo partial changes + */ + if (!to || + !skb_can_coalesce(tgt, to, fragfrom->page, fragfrom->page_offset)) { + merge = -1; + } else { + merge = to - 1; + + todo -= fragfrom->size; + if (todo < 0) { + if (skb_prepare_for_shift(skb) || + skb_prepare_for_shift(tgt)) + return 0; + + fragto = &skb_shinfo(tgt)->frags[merge]; + + fragto->size += shiftlen; + fragfrom->size -= shiftlen; + fragfrom->page_offset += shiftlen; + + goto onlymerged; + } + + from++; + } + + /* Skip full, not-fitting skb to avoid expensive operations */ + if ((shiftlen == skb->len) && + (skb_shinfo(skb)->nr_frags - from) > (MAX_SKB_FRAGS - to)) + return 0; + + if (skb_prepare_for_shift(skb) || skb_prepare_for_shift(tgt)) + return 0; + + while ((todo > 0) && (from < skb_shinfo(skb)->nr_frags)) { + if (to == MAX_SKB_FRAGS) + return 0; + + fragfrom = &skb_shinfo(skb)->frags[from]; + fragto = &skb_shinfo(tgt)->frags[to]; + + if (todo >= fragfrom->size) { + *fragto = *fragfrom; + todo -= fragfrom->size; + from++; + to++; + + } else { + get_page(fragfrom->page); + fragto->page = fragfrom->page; + fragto->page_offset = fragfrom->page_offset; + fragto->size = todo; + + fragfrom->page_offset += todo; + fragfrom->size -= todo; + todo = 0; + + to++; + break; + } + } + + /* Ready to "commit" this state change to tgt */ + skb_shinfo(tgt)->nr_frags = to; + + if (merge >= 0) { + fragfrom = &skb_shinfo(skb)->frags[0]; + fragto = &skb_shinfo(tgt)->frags[merge]; + + fragto->size += fragfrom->size; + put_page(fragfrom->page); + } + + /* Reposition in the original skb */ + to = 0; + while (from < skb_shinfo(skb)->nr_frags) + skb_shinfo(skb)->frags[to++] = skb_shinfo(skb)->frags[from++]; + skb_shinfo(skb)->nr_frags = to; + + BUG_ON(todo > 0 && !skb_shinfo(skb)->nr_frags); + +onlymerged: + /* Most likely the tgt won't ever need its checksum anymore, skb on + * the other hand might need it if it needs to be resent + */ + tgt->ip_summed = CHECKSUM_PARTIAL; + skb->ip_summed = CHECKSUM_PARTIAL; + + /* Yak, is it really working this way? Some helper please? */ + skb->len -= shiftlen; + skb->data_len -= shiftlen; + skb->truesize -= shiftlen; + tgt->len += shiftlen; + tgt->data_len += shiftlen; + tgt->truesize += shiftlen; + + return shiftlen; +} + /** * skb_prepare_seq_read - Prepare a sequential read of skb data * @skb: the buffer to read diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 3c8e297e2c3..97d57676b8e 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1242,6 +1242,8 @@ static int tcp_check_dsack(struct sock *sk, struct sk_buff *ack_skb, * aligned portion of it that matches. Therefore we might need to fragment * which may fail and creates some hassle (caller must handle error case * returns). + * + * FIXME: this could be merged to shift decision code */ static int tcp_match_skb_to_sack(struct sock *sk, struct sk_buff *skb, u32 start_seq, u32 end_seq) @@ -1353,9 +1355,6 @@ static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, if (fack_count > tp->fackets_out) tp->fackets_out = fack_count; - - if (!before(TCP_SKB_CB(skb)->seq, tcp_highest_sack_seq(tp))) - tcp_advance_highest_sack(sk, skb); } /* D-SACK. We can detect redundant retransmission in S|R and plain R @@ -1370,12 +1369,231 @@ static int tcp_sacktag_one(struct sk_buff *skb, struct sock *sk, return flag; } +static int tcp_shifted_skb(struct sock *sk, struct sk_buff *prev, + struct sk_buff *skb, unsigned int pcount, + int shifted, int fack_count, int *reord, + int *flag, int mss) +{ + struct tcp_sock *tp = tcp_sk(sk); + u8 dummy_sacked = TCP_SKB_CB(skb)->sacked; /* We discard results */ + + BUG_ON(!pcount); + + TCP_SKB_CB(prev)->end_seq += shifted; + TCP_SKB_CB(skb)->seq += shifted; + + skb_shinfo(prev)->gso_segs += pcount; + BUG_ON(skb_shinfo(skb)->gso_segs < pcount); + skb_shinfo(skb)->gso_segs -= pcount; + + /* When we're adding to gso_segs == 1, gso_size will be zero, + * in theory this shouldn't be necessary but as long as DSACK + * code can come after this skb later on it's better to keep + * setting gso_size to something. + */ + if (!skb_shinfo(prev)->gso_size) { + skb_shinfo(prev)->gso_size = mss; + skb_shinfo(prev)->gso_type = sk->sk_gso_type; + } + + /* CHECKME: To clear or not to clear? Mimics normal skb currently */ + if (skb_shinfo(skb)->gso_segs <= 1) { + skb_shinfo(skb)->gso_size = 0; + skb_shinfo(skb)->gso_type = 0; + } + + *flag |= tcp_sacktag_one(skb, sk, reord, 0, fack_count, &dummy_sacked, + pcount); + + /* Difference in this won't matter, both ACKed by the same cumul. ACK */ + TCP_SKB_CB(prev)->sacked |= (TCP_SKB_CB(skb)->sacked & TCPCB_EVER_RETRANS); + + tcp_clear_all_retrans_hints(tp); + + if (skb->len > 0) { + BUG_ON(!tcp_skb_pcount(skb)); + return 0; + } + + /* Whole SKB was eaten :-) */ + + TCP_SKB_CB(skb)->flags |= TCP_SKB_CB(prev)->flags; + if (skb == tcp_highest_sack(sk)) + tcp_advance_highest_sack(sk, skb); + + tcp_unlink_write_queue(skb, sk); + sk_wmem_free_skb(sk, skb); + + return 1; +} + +/* I wish gso_size would have a bit more sane initialization than + * something-or-zero which complicates things + */ +static int tcp_shift_mss(struct sk_buff *skb) +{ + int mss = tcp_skb_mss(skb); + + if (!mss) + mss = skb->len; + + return mss; +} + +/* Shifting pages past head area doesn't work */ +static int skb_can_shift(struct sk_buff *skb) +{ + return !skb_headlen(skb) && skb_is_nonlinear(skb); +} + +/* Try collapsing SACK blocks spanning across multiple skbs to a single + * skb. + */ +static struct sk_buff *tcp_shift_skb_data(struct sock *sk, struct sk_buff *skb, + u32 start_seq, u32 end_seq, + int dup_sack, int *fack_count, + int *reord, int *flag) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *prev; + int mss; + int pcount = 0; + int len; + int in_sack; + + if (!sk_can_gso(sk)) + goto fallback; + + /* Normally R but no L won't result in plain S */ + if (!dup_sack && + (TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) == TCPCB_SACKED_RETRANS) + goto fallback; + if (!skb_can_shift(skb)) + goto fallback; + /* This frame is about to be dropped (was ACKed). */ + if (!after(TCP_SKB_CB(skb)->end_seq, tp->snd_una)) + goto fallback; + + /* Can only happen with delayed DSACK + discard craziness */ + if (unlikely(skb == tcp_write_queue_head(sk))) + goto fallback; + prev = tcp_write_queue_prev(sk, skb); + + if ((TCP_SKB_CB(prev)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) + goto fallback; + + in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq) && + !before(end_seq, TCP_SKB_CB(skb)->end_seq); + + if (in_sack) { + len = skb->len; + pcount = tcp_skb_pcount(skb); + mss = tcp_shift_mss(skb); + + /* TODO: Fix DSACKs to not fragment already SACKed and we can + * drop this restriction as unnecessary + */ + if (mss != tcp_shift_mss(prev)) + goto fallback; + } else { + if (!after(TCP_SKB_CB(skb)->end_seq, start_seq)) + goto noop; + /* CHECKME: This is non-MSS split case only?, this will + * cause skipped skbs due to advancing loop btw, original + * has that feature too + */ + if (tcp_skb_pcount(skb) <= 1) + goto noop; + + in_sack = !after(start_seq, TCP_SKB_CB(skb)->seq); + if (!in_sack) { + /* TODO: head merge to next could be attempted here + * if (!after(TCP_SKB_CB(skb)->end_seq, end_seq)), + * though it might not be worth of the additional hassle + * + * ...we can probably just fallback to what was done + * previously. We could try merging non-SACKed ones + * as well but it probably isn't going to buy off + * because later SACKs might again split them, and + * it would make skb timestamp tracking considerably + * harder problem. + */ + goto fallback; + } + + len = end_seq - TCP_SKB_CB(skb)->seq; + BUG_ON(len < 0); + BUG_ON(len > skb->len); + + /* MSS boundaries should be honoured or else pcount will + * severely break even though it makes things bit trickier. + * Optimize common case to avoid most of the divides + */ + mss = tcp_skb_mss(skb); + + /* TODO: Fix DSACKs to not fragment already SACKed and we can + * drop this restriction as unnecessary + */ + if (mss != tcp_shift_mss(prev)) + goto fallback; + + if (len == mss) { + pcount = 1; + } else if (len < mss) { + goto noop; + } else { + pcount = len / mss; + len = pcount * mss; + } + } + + if (!skb_shift(prev, skb, len)) + goto fallback; + if (!tcp_shifted_skb(sk, prev, skb, pcount, len, *fack_count, reord, + flag, mss)) + goto out; + + /* Hole filled allows collapsing with the next as well, this is very + * useful when hole on every nth skb pattern happens + */ + if (prev == tcp_write_queue_tail(sk)) + goto out; + skb = tcp_write_queue_next(sk, prev); + + if (!skb_can_shift(skb)) + goto out; + if (skb == tcp_send_head(sk)) + goto out; + if ((TCP_SKB_CB(skb)->sacked & TCPCB_TAGBITS) != TCPCB_SACKED_ACKED) + goto out; + + len = skb->len; + if (skb_shift(prev, skb, len)) { + pcount += tcp_skb_pcount(skb); + tcp_shifted_skb(sk, prev, skb, tcp_skb_pcount(skb), len, + *fack_count, reord, flag, mss); + } + +out: + *fack_count += pcount; + return prev; + +noop: + return skb; + +fallback: + return NULL; +} + static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, struct tcp_sack_block *next_dup, u32 start_seq, u32 end_seq, int dup_sack_in, int *fack_count, int *reord, int *flag) { + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *tmp; + tcp_for_write_queue_from(skb, sk) { int in_sack = 0; int dup_sack = dup_sack_in; @@ -1396,18 +1614,42 @@ static struct sk_buff *tcp_sacktag_walk(struct sk_buff *skb, struct sock *sk, dup_sack = 1; } - if (in_sack <= 0) - in_sack = tcp_match_skb_to_sack(sk, skb, start_seq, - end_seq); + /* skb reference here is a bit tricky to get right, since + * shifting can eat and free both this skb and the next, + * so not even _safe variant of the loop is enough. + */ + if (in_sack <= 0) { + tmp = tcp_shift_skb_data(sk, skb, start_seq, + end_seq, dup_sack, + fack_count, reord, flag); + if (tmp != NULL) { + if (tmp != skb) { + skb = tmp; + continue; + } + + in_sack = 0; + } else { + in_sack = tcp_match_skb_to_sack(sk, skb, + start_seq, + end_seq); + } + } + if (unlikely(in_sack < 0)) break; - if (in_sack) + if (in_sack) { *flag |= tcp_sacktag_one(skb, sk, reord, dup_sack, *fack_count, &(TCP_SKB_CB(skb)->sacked), tcp_skb_pcount(skb)); + if (!before(TCP_SKB_CB(skb)->seq, + tcp_highest_sack_seq(tp))) + tcp_advance_highest_sack(sk, skb); + } + *fack_count += tcp_skb_pcount(skb); } return skb; -- cgit v1.2.3-70-g09d2 From 8eecaba900e89643029fd2c253ad8ebb60761165 Mon Sep 17 00:00:00 2001 From: Ilpo Järvinen Date: Tue, 25 Nov 2008 13:45:29 -0800 Subject: tcp: tcp_limit_reno_sacked can become static MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 2 -- net/ipv4/tcp_input.c | 2 +- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index 265392470b2..e8ae90a8c35 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -761,8 +761,6 @@ static inline unsigned int tcp_packets_in_flight(const struct tcp_sock *tp) return tp->packets_out - tcp_left_out(tp) + tp->retrans_out; } -extern int tcp_limit_reno_sacked(struct tcp_sock *tp); - /* If cwnd > ssthresh, we may raise ssthresh to be half-way to cwnd. * The exception is rate halving phase, when cwnd is decreasing towards * ssthresh. diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 9f8a80ba17b..d67b6e9cc54 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -1940,7 +1940,7 @@ out: /* Limits sacked_out so that sum with lost_out isn't ever larger than * packets_out. Returns zero if sacked_out adjustement wasn't necessary. */ -int tcp_limit_reno_sacked(struct tcp_sock *tp) +static int tcp_limit_reno_sacked(struct tcp_sock *tp) { u32 holes; -- cgit v1.2.3-70-g09d2 From 1748376b6626acf59c24e9592ac67b3fe2a0e026 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Nov 2008 21:16:35 -0800 Subject: net: Use a percpu_counter for sockets_allocated Instead of using one atomic_t per protocol, use a percpu_counter for "sockets_allocated", to reduce cache line contention on heavy duty network servers. Note : We revert commit (248969ae31e1b3276fc4399d67ce29a5d81e6fd9 net: af_unix can make unix_nr_socks visbile in /proc), since it is not anymore used after sock_prot_inuse_add() addition Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sctp/sctp.h | 1 + include/net/sock.h | 2 +- include/net/tcp.h | 2 +- net/core/sock.c | 10 +++++++--- net/ipv4/proc.c | 3 ++- net/ipv4/tcp.c | 8 ++++++-- net/ipv4/tcp_ipv4.c | 4 ++-- net/ipv6/tcp_ipv6.c | 2 +- net/sctp/protocol.c | 6 +++++- net/sctp/socket.c | 6 +++--- net/unix/af_unix.c | 1 - 11 files changed, 29 insertions(+), 16 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 23797506f59..bbb7742195b 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -138,6 +138,7 @@ void sctp_write_space(struct sock *sk); unsigned int sctp_poll(struct file *file, struct socket *sock, poll_table *wait); void sctp_sock_rfree(struct sk_buff *skb); +extern struct percpu_counter sctp_sockets_allocated; /* * sctp/primitive.c diff --git a/include/net/sock.h b/include/net/sock.h index 00cd486d362..a2a3890959c 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -649,7 +649,7 @@ struct proto { /* Memory pressure */ void (*enter_memory_pressure)(struct sock *sk); atomic_t *memory_allocated; /* Current allocated memory. */ - atomic_t *sockets_allocated; /* Current number of sockets. */ + struct percpu_counter *sockets_allocated; /* Current number of sockets. */ /* * Pressure flag: try to collapse. * Technical note: it is used by multiple contexts non atomically. diff --git a/include/net/tcp.h b/include/net/tcp.h index e8ae90a8c35..cbca3b8a133 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -238,7 +238,7 @@ extern int sysctl_tcp_slow_start_after_idle; extern int sysctl_tcp_max_ssthresh; extern atomic_t tcp_memory_allocated; -extern atomic_t tcp_sockets_allocated; +extern struct percpu_counter tcp_sockets_allocated; extern int tcp_memory_pressure; /* diff --git a/net/core/sock.c b/net/core/sock.c index a4e840e5a05..7a081b647bf 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -1071,7 +1071,7 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_sleep = NULL; if (newsk->sk_prot->sockets_allocated) - atomic_inc(newsk->sk_prot->sockets_allocated); + percpu_counter_inc(newsk->sk_prot->sockets_allocated); } out: return newsk; @@ -1463,8 +1463,12 @@ int __sk_mem_schedule(struct sock *sk, int size, int kind) } if (prot->memory_pressure) { - if (!*prot->memory_pressure || - prot->sysctl_mem[2] > atomic_read(prot->sockets_allocated) * + int alloc; + + if (!*prot->memory_pressure) + return 1; + alloc = percpu_counter_read_positive(prot->sockets_allocated); + if (prot->sysctl_mem[2] > alloc * sk_mem_pages(sk->sk_wmem_queued + atomic_read(&sk->sk_rmem_alloc) + sk->sk_forward_alloc)) diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 731789bb499..4944b47ad62 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -55,7 +55,8 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", sock_prot_inuse_get(net, &tcp_prot), atomic_read(&tcp_orphan_count), - tcp_death_row.tw_count, atomic_read(&tcp_sockets_allocated), + tcp_death_row.tw_count, + (int)percpu_counter_sum_positive(&tcp_sockets_allocated), atomic_read(&tcp_memory_allocated)); seq_printf(seq, "UDP: inuse %d mem %d\n", sock_prot_inuse_get(net, &udp_prot), diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 044224a341e..e6fade9ebf6 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -290,9 +290,12 @@ EXPORT_SYMBOL(sysctl_tcp_rmem); EXPORT_SYMBOL(sysctl_tcp_wmem); atomic_t tcp_memory_allocated; /* Current allocated memory. */ -atomic_t tcp_sockets_allocated; /* Current number of TCP sockets. */ - EXPORT_SYMBOL(tcp_memory_allocated); + +/* + * Current number of TCP sockets. + */ +struct percpu_counter tcp_sockets_allocated; EXPORT_SYMBOL(tcp_sockets_allocated); /* @@ -2685,6 +2688,7 @@ void __init tcp_init(void) BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); + percpu_counter_init(&tcp_sockets_allocated, 0); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index cab2458f86f..26b9030747c 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -1797,7 +1797,7 @@ static int tcp_v4_init_sock(struct sock *sk) sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - atomic_inc(&tcp_sockets_allocated); + percpu_counter_inc(&tcp_sockets_allocated); return 0; } @@ -1845,7 +1845,7 @@ void tcp_v4_destroy_sock(struct sock *sk) sk->sk_sndmsg_page = NULL; } - atomic_dec(&tcp_sockets_allocated); + percpu_counter_dec(&tcp_sockets_allocated); } EXPORT_SYMBOL(tcp_v4_destroy_sock); diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index f259c9671f3..8702b06cb60 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -1830,7 +1830,7 @@ static int tcp_v6_init_sock(struct sock *sk) sk->sk_sndbuf = sysctl_tcp_wmem[1]; sk->sk_rcvbuf = sysctl_tcp_rmem[1]; - atomic_inc(&tcp_sockets_allocated); + percpu_counter_inc(&tcp_sockets_allocated); return 0; } diff --git a/net/sctp/protocol.c b/net/sctp/protocol.c index a8ca743241e..d5ea232c912 100644 --- a/net/sctp/protocol.c +++ b/net/sctp/protocol.c @@ -102,6 +102,8 @@ struct sock *sctp_get_ctl_sock(void) /* Set up the proc fs entry for the SCTP protocol. */ static __init int sctp_proc_init(void) { + if (percpu_counter_init(&sctp_sockets_allocated, 0)) + goto out_nomem; #ifdef CONFIG_PROC_FS if (!proc_net_sctp) { struct proc_dir_entry *ent; @@ -110,7 +112,7 @@ static __init int sctp_proc_init(void) ent->owner = THIS_MODULE; proc_net_sctp = ent; } else - goto out_nomem; + goto out_free_percpu; } if (sctp_snmp_proc_init()) @@ -135,6 +137,8 @@ out_snmp_proc_init: proc_net_sctp = NULL; remove_proc_entry("sctp", init_net.proc_net); } +out_free_percpu: + percpu_counter_destroy(&sctp_sockets_allocated); out_nomem: return -ENOMEM; #else diff --git a/net/sctp/socket.c b/net/sctp/socket.c index ba81fe3ccab..a2de585888d 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -114,7 +114,7 @@ extern int sysctl_sctp_wmem[3]; static int sctp_memory_pressure; static atomic_t sctp_memory_allocated; -static atomic_t sctp_sockets_allocated; +struct percpu_counter sctp_sockets_allocated; static void sctp_enter_memory_pressure(struct sock *sk) { @@ -3613,7 +3613,7 @@ SCTP_STATIC int sctp_init_sock(struct sock *sk) sp->hmac = NULL; SCTP_DBG_OBJCNT_INC(sock); - atomic_inc(&sctp_sockets_allocated); + percpu_counter_inc(&sctp_sockets_allocated); local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, 1); @@ -3632,7 +3632,7 @@ SCTP_STATIC void sctp_destroy_sock(struct sock *sk) /* Release our hold on the endpoint. */ ep = sctp_sk(sk)->ep; sctp_endpoint_free(ep); - atomic_dec(&sctp_sockets_allocated); + percpu_counter_dec(&sctp_sockets_allocated); local_bh_disable(); sock_prot_inuse_add(sock_net(sk), sk->sk_prot, -1); local_bh_enable(); diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 3a35a6e8bf9..5aaf23e43f1 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -571,7 +571,6 @@ static const struct proto_ops unix_seqpacket_ops = { static struct proto unix_proto = { .name = "UNIX", .owner = THIS_MODULE, - .sockets_allocated = &unix_nr_socks, .obj_size = sizeof(struct unix_sock), }; -- cgit v1.2.3-70-g09d2 From dd24c00191d5e4a1ae896aafe33c6b8095ab4bd1 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 25 Nov 2008 21:17:14 -0800 Subject: net: Use a percpu_counter for orphan_count Instead of using one atomic_t per protocol, use a percpu_counter for "orphan_count", to reduce cache line contention on heavy duty network servers. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/net/sock.h | 2 +- include/net/tcp.h | 2 +- net/dccp/dccp.h | 2 +- net/dccp/proto.c | 16 ++++++++++------ net/ipv4/inet_connection_sock.c | 4 ++-- net/ipv4/proc.c | 2 +- net/ipv4/tcp.c | 12 +++++++----- net/ipv4/tcp_timer.c | 2 +- 8 files changed, 24 insertions(+), 18 deletions(-) (limited to 'include/net/tcp.h') diff --git a/include/net/sock.h b/include/net/sock.h index a2a3890959c..5a3a151bd73 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -666,7 +666,7 @@ struct proto { unsigned int obj_size; int slab_flags; - atomic_t *orphan_count; + struct percpu_counter *orphan_count; struct request_sock_ops *rsk_prot; struct timewait_sock_ops *twsk_prot; diff --git a/include/net/tcp.h b/include/net/tcp.h index cbca3b8a133..de1e91d959b 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -46,7 +46,7 @@ extern struct inet_hashinfo tcp_hashinfo; -extern atomic_t tcp_orphan_count; +extern struct percpu_counter tcp_orphan_count; extern void tcp_time_wait(struct sock *sk, int state, int timeo); #define MAX_TCP_HEADER (128 + MAX_HEADER) diff --git a/net/dccp/dccp.h b/net/dccp/dccp.h index 031ce350d3c..33a1127270c 100644 --- a/net/dccp/dccp.h +++ b/net/dccp/dccp.h @@ -49,7 +49,7 @@ extern int dccp_debug; extern struct inet_hashinfo dccp_hashinfo; -extern atomic_t dccp_orphan_count; +extern struct percpu_counter dccp_orphan_count; extern void dccp_time_wait(struct sock *sk, int state, int timeo); diff --git a/net/dccp/proto.c b/net/dccp/proto.c index ea85c423cdb..db225f93cd5 100644 --- a/net/dccp/proto.c +++ b/net/dccp/proto.c @@ -40,8 +40,7 @@ DEFINE_SNMP_STAT(struct dccp_mib, dccp_statistics) __read_mostly; EXPORT_SYMBOL_GPL(dccp_statistics); -atomic_t dccp_orphan_count = ATOMIC_INIT(0); - +struct percpu_counter dccp_orphan_count; EXPORT_SYMBOL_GPL(dccp_orphan_count); struct inet_hashinfo dccp_hashinfo; @@ -1000,7 +999,7 @@ adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); - atomic_inc(sk->sk_prot->orphan_count); + percpu_counter_inc(sk->sk_prot->orphan_count); /* * It is the last release_sock in its life. It will remove backlog. @@ -1064,18 +1063,21 @@ static int __init dccp_init(void) { unsigned long goal; int ehash_order, bhash_order, i; - int rc = -ENOBUFS; + int rc; BUILD_BUG_ON(sizeof(struct dccp_skb_cb) > FIELD_SIZEOF(struct sk_buff, cb)); - + rc = percpu_counter_init(&dccp_orphan_count, 0); + if (rc) + goto out; + rc = -ENOBUFS; inet_hashinfo_init(&dccp_hashinfo); dccp_hashinfo.bind_bucket_cachep = kmem_cache_create("dccp_bind_bucket", sizeof(struct inet_bind_bucket), 0, SLAB_HWCACHE_ALIGN, NULL); if (!dccp_hashinfo.bind_bucket_cachep) - goto out; + goto out_free_percpu; /* * Size and allocate the main established and bind bucket @@ -1168,6 +1170,8 @@ out_free_dccp_ehash: out_free_bind_bucket_cachep: kmem_cache_destroy(dccp_hashinfo.bind_bucket_cachep); dccp_hashinfo.bind_bucket_cachep = NULL; +out_free_percpu: + percpu_counter_destroy(&dccp_orphan_count); goto out; } diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 05af807ca9b..1ccdbba528b 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -561,7 +561,7 @@ void inet_csk_destroy_sock(struct sock *sk) sk_refcnt_debug_release(sk); - atomic_dec(sk->sk_prot->orphan_count); + percpu_counter_dec(sk->sk_prot->orphan_count); sock_put(sk); } @@ -641,7 +641,7 @@ void inet_csk_listen_stop(struct sock *sk) sock_orphan(child); - atomic_inc(sk->sk_prot->orphan_count); + percpu_counter_inc(sk->sk_prot->orphan_count); inet_csk_destroy_sock(child); diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index 4944b47ad62..614958b7c27 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -54,7 +54,7 @@ static int sockstat_seq_show(struct seq_file *seq, void *v) socket_seq_show(seq); seq_printf(seq, "TCP: inuse %d orphan %d tw %d alloc %d mem %d\n", sock_prot_inuse_get(net, &tcp_prot), - atomic_read(&tcp_orphan_count), + (int)percpu_counter_sum_positive(&tcp_orphan_count), tcp_death_row.tw_count, (int)percpu_counter_sum_positive(&tcp_sockets_allocated), atomic_read(&tcp_memory_allocated)); diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index e6fade9ebf6..01924340862 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -277,8 +277,7 @@ int sysctl_tcp_fin_timeout __read_mostly = TCP_FIN_TIMEOUT; -atomic_t tcp_orphan_count = ATOMIC_INIT(0); - +struct percpu_counter tcp_orphan_count; EXPORT_SYMBOL_GPL(tcp_orphan_count); int sysctl_tcp_mem[3] __read_mostly; @@ -1837,7 +1836,7 @@ adjudge_to_death: state = sk->sk_state; sock_hold(sk); sock_orphan(sk); - atomic_inc(sk->sk_prot->orphan_count); + percpu_counter_inc(sk->sk_prot->orphan_count); /* It is the last release_sock in its life. It will remove backlog. */ release_sock(sk); @@ -1888,9 +1887,11 @@ adjudge_to_death: } } if (sk->sk_state != TCP_CLOSE) { + int orphan_count = percpu_counter_read_positive( + sk->sk_prot->orphan_count); + sk_mem_reclaim(sk); - if (tcp_too_many_orphans(sk, - atomic_read(sk->sk_prot->orphan_count))) { + if (tcp_too_many_orphans(sk, orphan_count)) { if (net_ratelimit()) printk(KERN_INFO "TCP: too many of orphaned " "sockets\n"); @@ -2689,6 +2690,7 @@ void __init tcp_init(void) BUILD_BUG_ON(sizeof(struct tcp_skb_cb) > sizeof(skb->cb)); percpu_counter_init(&tcp_sockets_allocated, 0); + percpu_counter_init(&tcp_orphan_count, 0); tcp_hashinfo.bind_bucket_cachep = kmem_cache_create("tcp_bind_bucket", sizeof(struct inet_bind_bucket), 0, diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index 3df339e3e36..cc4e6d27ded 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -65,7 +65,7 @@ static void tcp_write_err(struct sock *sk) static int tcp_out_of_resources(struct sock *sk, int do_reset) { struct tcp_sock *tp = tcp_sk(sk); - int orphans = atomic_read(&tcp_orphan_count); + int orphans = percpu_counter_read_positive(&tcp_orphan_count); /* If peer does not open window for long time, or did not transmit * anything for long time, penalize it. */ -- cgit v1.2.3-70-g09d2 From bf296b125b21b8d558ceb6ec30bb4eba2730cd6b Mon Sep 17 00:00:00 2001 From: Herbert Xu Date: Mon, 15 Dec 2008 23:43:36 -0800 Subject: tcp: Add GRO support This patch adds the TCP-specific portion of GRO. The criterion for merging is extremely strict (the TCP header must match exactly apart from the checksum) so as to allow refragmentation. Otherwise this is pretty much identical to LRO, except that we support the merging of ECN packets. Signed-off-by: Herbert Xu Signed-off-by: David S. Miller --- include/net/tcp.h | 6 ++++ net/ipv4/af_inet.c | 2 ++ net/ipv4/tcp.c | 100 ++++++++++++++++++++++++++++++++++++++++++++++++++++ net/ipv4/tcp_ipv4.c | 35 ++++++++++++++++++ 4 files changed, 143 insertions(+) (limited to 'include/net/tcp.h') diff --git a/include/net/tcp.h b/include/net/tcp.h index de1e91d959b..218235de896 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1358,6 +1358,12 @@ extern void tcp_v4_destroy_sock(struct sock *sk); extern int tcp_v4_gso_send_check(struct sk_buff *skb); extern struct sk_buff *tcp_tso_segment(struct sk_buff *skb, int features); +extern struct sk_buff **tcp_gro_receive(struct sk_buff **head, + struct sk_buff *skb); +extern struct sk_buff **tcp4_gro_receive(struct sk_buff **head, + struct sk_buff *skb); +extern int tcp_gro_complete(struct sk_buff *skb); +extern int tcp4_gro_complete(struct sk_buff *skb); #ifdef CONFIG_PROC_FS extern int tcp4_proc_init(void); diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index a85595307fa..664ff0ee1c8 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -1410,6 +1410,8 @@ static struct net_protocol tcp_protocol = { .err_handler = tcp_v4_err, .gso_send_check = tcp_v4_gso_send_check, .gso_segment = tcp_tso_segment, + .gro_receive = tcp4_gro_receive, + .gro_complete = tcp4_gro_complete, .no_policy = 1, .netns_ok = 1, }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index 01924340862..1f3d52946b3 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -2465,6 +2465,106 @@ out: } EXPORT_SYMBOL(tcp_tso_segment); +struct sk_buff **tcp_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct sk_buff **pp = NULL; + struct sk_buff *p; + struct tcphdr *th; + struct tcphdr *th2; + unsigned int thlen; + unsigned int flags; + unsigned int total; + unsigned int mss = 1; + int flush = 1; + + if (!pskb_may_pull(skb, sizeof(*th))) + goto out; + + th = tcp_hdr(skb); + thlen = th->doff * 4; + if (thlen < sizeof(*th)) + goto out; + + if (!pskb_may_pull(skb, thlen)) + goto out; + + th = tcp_hdr(skb); + __skb_pull(skb, thlen); + + flags = tcp_flag_word(th); + + for (; (p = *head); head = &p->next) { + if (!NAPI_GRO_CB(p)->same_flow) + continue; + + th2 = tcp_hdr(p); + + if (th->source != th2->source || th->dest != th2->dest) { + NAPI_GRO_CB(p)->same_flow = 0; + continue; + } + + goto found; + } + + goto out_check_final; + +found: + flush = NAPI_GRO_CB(p)->flush; + flush |= flags & TCP_FLAG_CWR; + flush |= (flags ^ tcp_flag_word(th2)) & + ~(TCP_FLAG_CWR | TCP_FLAG_FIN | TCP_FLAG_PSH); + flush |= th->ack_seq != th2->ack_seq || th->window != th2->window; + flush |= memcmp(th + 1, th2 + 1, thlen - sizeof(*th)); + + total = p->len; + mss = total; + if (skb_shinfo(p)->frag_list) + mss = skb_shinfo(p)->frag_list->len; + + flush |= skb->len > mss || skb->len <= 0; + flush |= ntohl(th2->seq) + total != ntohl(th->seq); + + if (flush || skb_gro_receive(head, skb)) { + mss = 1; + goto out_check_final; + } + + p = *head; + th2 = tcp_hdr(p); + tcp_flag_word(th2) |= flags & (TCP_FLAG_FIN | TCP_FLAG_PSH); + +out_check_final: + flush = skb->len < mss; + flush |= flags & (TCP_FLAG_URG | TCP_FLAG_PSH | TCP_FLAG_RST | + TCP_FLAG_SYN | TCP_FLAG_FIN); + + if (p && (!NAPI_GRO_CB(skb)->same_flow || flush)) + pp = head; + +out: + NAPI_GRO_CB(skb)->flush |= flush; + + return pp; +} + +int tcp_gro_complete(struct sk_buff *skb) +{ + struct tcphdr *th = tcp_hdr(skb); + + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); + skb->ip_summed = CHECKSUM_PARTIAL; + + skb_shinfo(skb)->gso_size = skb_shinfo(skb)->frag_list->len; + skb_shinfo(skb)->gso_segs = NAPI_GRO_CB(skb)->count; + + if (th->cwr) + skb_shinfo(skb)->gso_type |= SKB_GSO_TCP_ECN; + + return 0; +} + #ifdef CONFIG_TCP_MD5SIG static unsigned long tcp_md5sig_users; static struct tcp_md5sig_pool **tcp_md5sig_pool; diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index 26b9030747c..10172487921 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -2346,6 +2346,41 @@ void tcp4_proc_exit(void) } #endif /* CONFIG_PROC_FS */ +struct sk_buff **tcp4_gro_receive(struct sk_buff **head, struct sk_buff *skb) +{ + struct iphdr *iph = ip_hdr(skb); + + switch (skb->ip_summed) { + case CHECKSUM_COMPLETE: + if (!tcp_v4_check(skb->len, iph->saddr, iph->daddr, + skb->csum)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + break; + } + + /* fall through */ + case CHECKSUM_NONE: + NAPI_GRO_CB(skb)->flush = 1; + return NULL; + } + + return tcp_gro_receive(head, skb); +} +EXPORT_SYMBOL(tcp4_gro_receive); + +int tcp4_gro_complete(struct sk_buff *skb) +{ + struct iphdr *iph = ip_hdr(skb); + struct tcphdr *th = tcp_hdr(skb); + + th->check = ~tcp_v4_check(skb->len - skb_transport_offset(skb), + iph->saddr, iph->daddr, 0); + skb_shinfo(skb)->gso_type = SKB_GSO_TCPV4; + + return tcp_gro_complete(skb); +} +EXPORT_SYMBOL(tcp4_gro_complete); + struct proto tcp_prot = { .name = "TCP", .owner = THIS_MODULE, -- cgit v1.2.3-70-g09d2