From 75c0fd93c7d42362134e74fd381072a7642fcc3d Mon Sep 17 00:00:00 2001 From: "j223yang@asset.uwaterloo.ca" Date: Thu, 10 Mar 2011 12:36:37 +0000 Subject: [PATCH 01/20] ariadne: remove redundant NULL check Simply remove redundant 'dev' NULL check. Signed-off-by: Jinqiu Yang Signed-off-by: David S. Miller --- drivers/net/ariadne.c | 5 ----- 1 file changed, 5 deletions(-) diff --git a/drivers/net/ariadne.c b/drivers/net/ariadne.c index 39214e512452..7ca0eded2561 100644 --- a/drivers/net/ariadne.c +++ b/drivers/net/ariadne.c @@ -425,11 +425,6 @@ static irqreturn_t ariadne_interrupt(int irq, void *data) int csr0, boguscnt; int handled = 0; - if (dev == NULL) { - printk(KERN_WARNING "ariadne_interrupt(): irq for unknown device.\n"); - return IRQ_NONE; - } - lance->RAP = CSR0; /* PCnet-ISA Controller Status */ if (!(lance->RDP & INTR)) /* Check if any interrupt has been */ From 423cfa7e1fe68974b3b25fe8233ea57a5c2e5f02 Mon Sep 17 00:00:00 2001 From: Ariel Elior Date: Mon, 14 Mar 2011 13:43:22 -0700 Subject: [PATCH 02/20] bnx2x: fix swap of rx-ticks and tx-ticks parameters in interrupt coalescing flow Signed-off-by: Ariel Elior Signed-off-by: Eilon Greenstein Signed-off-by: David S. Miller --- drivers/net/bnx2x/bnx2x_main.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/bnx2x/bnx2x_main.c b/drivers/net/bnx2x/bnx2x_main.c index aa032339e321..10bc0a6a32d9 100644 --- a/drivers/net/bnx2x/bnx2x_main.c +++ b/drivers/net/bnx2x/bnx2x_main.c @@ -4208,7 +4208,7 @@ void bnx2x_update_coalesce(struct bnx2x *bp) for_each_eth_queue(bp, i) bnx2x_update_coalesce_sb(bp, bp->fp[i].fw_sb_id, - bp->rx_ticks, bp->tx_ticks); + bp->tx_ticks, bp->rx_ticks); } static void bnx2x_init_sp_ring(struct bnx2x *bp) From 0b32211164da2b100553cb45e4e862f09c5cab11 Mon Sep 17 00:00:00 2001 From: roel kluin Date: Tue, 8 Mar 2011 09:52:55 +0000 Subject: [PATCH 03/20] can: wrong index used in inner loop Index i was already used in the outer loop. Signed-off-by: Roel Kluin Signed-off-by: David S. Miller --- drivers/net/can/usb/esd_usb2.c | 6 +++--- 1 file changed, 3 insertions(+), 3 deletions(-) diff --git a/drivers/net/can/usb/esd_usb2.c b/drivers/net/can/usb/esd_usb2.c index 05a52754f486..dc53c831ea95 100644 --- a/drivers/net/can/usb/esd_usb2.c +++ b/drivers/net/can/usb/esd_usb2.c @@ -659,7 +659,7 @@ failed: static void unlink_all_urbs(struct esd_usb2 *dev) { struct esd_usb2_net_priv *priv; - int i; + int i, j; usb_kill_anchored_urbs(&dev->rx_submitted); for (i = 0; i < dev->net_count; i++) { @@ -668,8 +668,8 @@ static void unlink_all_urbs(struct esd_usb2 *dev) usb_kill_anchored_urbs(&priv->tx_submitted); atomic_set(&priv->active_tx_jobs, 0); - for (i = 0; i < MAX_TX_URBS; i++) - priv->tx_contexts[i].echo_index = MAX_TX_URBS; + for (j = 0; j < MAX_TX_URBS; j++) + priv->tx_contexts[j].echo_index = MAX_TX_URBS; } } } From 60aeba23101f34a690a0b0a048ffde3d023d4f3b Mon Sep 17 00:00:00 2001 From: Thomas Lange Date: Wed, 9 Mar 2011 04:41:16 +0000 Subject: [PATCH 04/20] Davinci: Do not reset EMAC TX overruns counter on read Don't reset tx_fifo_errors when reading out current EMAC stats. (tx_fifo_errors shows up as TX overruns in netdev stats.) Without this correction, the old counter value is lost every time stats are read out. Signed-off-by: Thomas Lange Signed-off-by: David S. Miller --- drivers/net/davinci_emac.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/davinci_emac.c b/drivers/net/davinci_emac.c index 7018bfe408a4..082d6ea69920 100644 --- a/drivers/net/davinci_emac.c +++ b/drivers/net/davinci_emac.c @@ -1730,7 +1730,7 @@ static struct net_device_stats *emac_dev_getnetstats(struct net_device *ndev) emac_read(EMAC_TXCARRIERSENSE); emac_write(EMAC_TXCARRIERSENSE, stats_clear_mask); - ndev->stats.tx_fifo_errors = emac_read(EMAC_TXUNDERRUN); + ndev->stats.tx_fifo_errors += emac_read(EMAC_TXUNDERRUN); emac_write(EMAC_TXUNDERRUN, stats_clear_mask); return &ndev->stats; From a461c0297f2e80c78eaa03fc5141bf57a814ff4f Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Thu, 10 Mar 2011 05:57:04 +0000 Subject: [PATCH 05/20] bridge: skip forwarding delay if not using STP If Spanning Tree Protocol is not enabled, there is no good reason for the bridge code to wait for the forwarding delay period before enabling the link. The purpose of the forwarding delay is to allow STP to learn about other bridges before nominating itself. The only possible impact is that when starting up a new port the bridge may flood a packet now, where previously it might have seen traffic from the other host and preseeded the forwarding table. Includes change for local variable br already available in that func. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/bridge/br_stp.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 57186d84d2bd..47582d301fbe 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -375,12 +375,12 @@ static void br_make_forwarding(struct net_bridge_port *p) if (p->state != BR_STATE_BLOCKING) return; - if (br->forward_delay == 0) { + if (br->stp_enabled == BR_NO_STP || br->forward_delay == 0) { p->state = BR_STATE_FORWARDING; br_topology_change_detection(br); del_timer(&p->forward_delay_timer); } - else if (p->br->stp_enabled == BR_KERNEL_STP) + else if (br->stp_enabled == BR_KERNEL_STP) p->state = BR_STATE_LISTENING; else p->state = BR_STATE_LEARNING; From e9a799ea4a5551d20e458a45b541df0bbf8f1804 Mon Sep 17 00:00:00 2001 From: Ian Campbell Date: Thu, 10 Mar 2011 07:04:18 +0000 Subject: [PATCH 06/20] xen: netfront: ethtool stats fields should be unsigned long Fixup the rx_gso_checksum_fixup field added in e0ce4af920eb to be unsigned long as suggested by Ben Hutchings in <1298919198.2569.14.camel@bwh-desktop> Signed-off-by: Ian Campbell Cc: Ben Hutchings Signed-off-by: David S. Miller --- drivers/net/xen-netfront.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index da1f12120346..27cf72f26cbb 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -122,7 +122,7 @@ struct netfront_info { struct mmu_update rx_mmu[NET_RX_RING_SIZE]; /* Statistics */ - int rx_gso_checksum_fixup; + unsigned long rx_gso_checksum_fixup; }; struct netfront_rx_info { From ac90fa63432b3c03c189c39e62211d3b80418c30 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Sun, 13 Mar 2011 06:54:30 +0000 Subject: [PATCH 07/20] NET: cdc-phonet, fix stop-queue handling MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently there is a warning emitted by the cdc-phonet driver: WARNING: at include/linux/netdevice.h:1557 usbpn_probe+0x3bb/0x3f0 [cdc_phonet]() Modules linked in: ... Pid: 5877, comm: insmod Not tainted 2.6.37.3-16-desktop #1 Call Trace: [] dump_trace+0x79/0x340 [] dump_stack+0x69/0x6f [] warn_slowpath_common+0x7b/0xc0 [] usbpn_probe+0x3bb/0x3f0 [cdc_phonet] ... ---[ end trace f5d3e02908603ab4 ]--- netif_stop_queue() cannot be called before register_netdev() So remove netif_stop_queue from the probe funtction to avoid that. Signed-off-by: Jiri Slaby Cc: Rémi Denis-Courmont Cc: David S. Miller Acked-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- drivers/net/usb/cdc-phonet.c | 1 - 1 file changed, 1 deletion(-) diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 109751bad3bb..4cf4e361c121 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -392,7 +392,6 @@ int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *id) pnd = netdev_priv(dev); SET_NETDEV_DEV(dev, &intf->dev); - netif_stop_queue(dev); pnd->dev = dev; pnd->usb = usb_get_dev(usbdev); From 468c3f924f043cad7a04f4f4d5224a2c9bc886c1 Mon Sep 17 00:00:00 2001 From: Jiri Slaby Date: Sun, 13 Mar 2011 06:54:31 +0000 Subject: [PATCH 08/20] NET: cdc-phonet, handle empty phonet header MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Currently, for N 5800 XM I get: cdc_phonet: probe of 1-6:1.10 failed with error -22 It's because phonet_header is empty. Extra altsetting looks like there: E 05 24 00 01 10 03 24 ab 05 24 06 0a 0b 04 24 fd .$....$..$....$. E 00 . I don't see the header used anywhere so just check if the phonet descriptor is there, not the structure itself. Signed-off-by: Jiri Slaby Cc: Rémi Denis-Courmont Cc: David S. Miller Acked-by: Rémi Denis-Courmont Signed-off-by: David S. Miller --- drivers/net/usb/cdc-phonet.c | 9 +++------ 1 file changed, 3 insertions(+), 6 deletions(-) diff --git a/drivers/net/usb/cdc-phonet.c b/drivers/net/usb/cdc-phonet.c index 4cf4e361c121..f967913e11bc 100644 --- a/drivers/net/usb/cdc-phonet.c +++ b/drivers/net/usb/cdc-phonet.c @@ -328,13 +328,13 @@ int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *id) { static const char ifname[] = "usbpn%d"; const struct usb_cdc_union_desc *union_header = NULL; - const struct usb_cdc_header_desc *phonet_header = NULL; const struct usb_host_interface *data_desc; struct usb_interface *data_intf; struct usb_device *usbdev = interface_to_usbdev(intf); struct net_device *dev; struct usbpn_dev *pnd; u8 *data; + int phonet = 0; int len, err; data = intf->altsetting->extra; @@ -355,10 +355,7 @@ int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *id) (struct usb_cdc_union_desc *)data; break; case 0xAB: - if (phonet_header || dlen < 5) - break; - phonet_header = - (struct usb_cdc_header_desc *)data; + phonet = 1; break; } } @@ -366,7 +363,7 @@ int usbpn_probe(struct usb_interface *intf, const struct usb_device_id *id) len -= dlen; } - if (!union_header || !phonet_header) + if (!union_header || !phonet) return -EINVAL; data_intf = usb_ifnum_to_if(usbdev, union_header->bSlaveInterface0); From e5537bfc98f01561fbdfbd8a78f0dc3e2360491d Mon Sep 17 00:00:00 2001 From: Daniel Baluta Date: Mon, 14 Mar 2011 15:25:33 -0700 Subject: [PATCH 09/20] af_unix: update locking comment We latch our state using a spinlock not a r/w kind of lock. Signed-off-by: Daniel Baluta Signed-off-by: David S. Miller --- net/unix/af_unix.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/unix/af_unix.c b/net/unix/af_unix.c index 437a99e560e1..b213ce668c98 100644 --- a/net/unix/af_unix.c +++ b/net/unix/af_unix.c @@ -1124,7 +1124,7 @@ restart: /* Latch our state. - It is tricky place. We need to grab write lock and cannot + It is tricky place. We need to grab our state lock and cannot drop lock on peer. It is dangerous because deadlock is possible. Connect to self case and simultaneous attempt to connect are eliminated by checking socket From a23c37f1110d8912d4d0a66e78197e9195bb36d4 Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Nicolas=20de=20Peslo=C3=BCan?= Date: Sun, 13 Mar 2011 10:34:22 +0000 Subject: [PATCH 10/20] bonding: documentation update: mailing lists. MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit In commit a6c36ee677607b02d8ecc88e8a12785418b88107 ("bonding: change list contact to netdev@vger.kernel.org"), the mailing list for bonding developpement was changed from bonding-devel to netdev. Update the bonding documentation to reflect this change: - bonding-devel is used for usage discussions (despite the name). - netdev is used for developpement discussions. Also remove the reference to the sourceforge bonding page, which is deprecated. Signed-off-by: Nicolas de Pesloüan Signed-off-by: David S. Miller --- Documentation/networking/bonding.txt | 26 +++++++++++++++++--------- 1 file changed, 17 insertions(+), 9 deletions(-) diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 25d2f4141d27..b36e741e94db 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -2558,18 +2558,15 @@ enslaved. 16. Resources and Links ======================= -The latest version of the bonding driver can be found in the latest + The latest version of the bonding driver can be found in the latest version of the linux kernel, found on http://kernel.org -The latest version of this document can be found in either the latest -kernel source (named Documentation/networking/bonding.txt), or on the -bonding sourceforge site: + The latest version of this document can be found in the latest kernel +source (named Documentation/networking/bonding.txt). -http://www.sourceforge.net/projects/bonding - -Discussions regarding the bonding driver take place primarily on the -bonding-devel mailing list, hosted at sourceforge.net. If you have -questions or problems, post them to the list. The list address is: + Discussions regarding the usage of the bonding driver take place on the +bonding-devel mailing list, hosted at sourceforge.net. If you have questions or +problems, post them to the list. The list address is: bonding-devel@lists.sourceforge.net @@ -2578,6 +2575,17 @@ be found at: https://lists.sourceforge.net/lists/listinfo/bonding-devel + Discussions regarding the developpement of the bonding driver take place +on the main Linux network mailing list, hosted at vger.kernel.org. The list +address is: + +netdev@vger.kernel.org + + The administrative interface (to subscribe or unsubscribe) can +be found at: + +http://vger.kernel.org/vger-lists.html#netdev + Donald Becker's Ethernet Drivers and diag programs may be found at : - http://web.archive.org/web/*/http://www.scyld.com/network/ From febf081987ec445f071ed10b73e9707a88cc5cc4 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 14 Mar 2011 07:52:12 +0000 Subject: [PATCH 11/20] tcp: fix RTT for quick packets in congestion control In the congestion control interface, the callback for each ACK includes an estimated round trip time in microseconds. Some algorithms need high resolution (Vegas style) but most only need jiffie resolution. If RTT is not accurate (like a retransmission) -1 is used as a flag value. When doing coarse resolution if RTT is less than a a jiffie then 0 should be returned rather than no estimate. Otherwise algorithms that expect good ack's to trigger slow start (like CUBIC Hystart) will be confused. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/tcp_input.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 65f6c0406245..e16b17efcf57 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -3350,7 +3350,7 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, net_invalid_timestamp())) rtt_us = ktime_us_delta(ktime_get_real(), last_ackt); - else if (ca_seq_rtt > 0) + else if (ca_seq_rtt >= 0) rtt_us = jiffies_to_usecs(ca_seq_rtt); } From c54b4b7655447c1f24f6d50779c22eba9ee0fd24 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 14 Mar 2011 07:52:13 +0000 Subject: [PATCH 12/20] tcp_cubic: fix comparison of jiffies Jiffies wraps around therefore the correct way to compare is to use cast to signed value. Note: cubic is not using full jiffies value on 64 bit arch because using full unsigned long makes struct bictcp grow too large for the available ca_priv area. Includes correction from Sangtae Ha to improve ack train detection. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/tcp_cubic.c | 6 ++++-- 1 file changed, 4 insertions(+), 2 deletions(-) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 71d5f2f29fa6..43bb34c9b8bf 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -342,9 +342,11 @@ static void hystart_update(struct sock *sk, u32 delay) u32 curr_jiffies = jiffies; /* first detection parameter - ack-train detection */ - if (curr_jiffies - ca->last_jiffies <= msecs_to_jiffies(2)) { + if ((s32)(curr_jiffies - ca->last_jiffies) <= + msecs_to_jiffies(2)) { ca->last_jiffies = curr_jiffies; - if (curr_jiffies - ca->round_start >= ca->delay_min>>4) + if ((s32) (curr_jiffies - ca->round_start) > + ca->delay_min >> 4) ca->found |= HYSTART_ACK_TRAIN; } From aac46324e12a2bf2e9e0855ad6a287945e34ad39 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 14 Mar 2011 07:52:14 +0000 Subject: [PATCH 13/20] tcp_cubic: make ack train delta value a parameter Make the spacing between ACK's that indicates a train a tuneable value like other hystart values. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/tcp_cubic.c | 5 ++++- 1 file changed, 4 insertions(+), 1 deletion(-) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 43bb34c9b8bf..66d3b00233ec 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -52,6 +52,7 @@ static int tcp_friendliness __read_mostly = 1; static int hystart __read_mostly = 1; static int hystart_detect __read_mostly = HYSTART_ACK_TRAIN | HYSTART_DELAY; static int hystart_low_window __read_mostly = 16; +static int hystart_ack_delta __read_mostly = 2; static u32 cube_rtt_scale __read_mostly; static u32 beta_scale __read_mostly; @@ -75,6 +76,8 @@ MODULE_PARM_DESC(hystart_detect, "hyrbrid slow start detection mechanisms" " 1: packet-train 2: delay 3: both packet-train and delay"); module_param(hystart_low_window, int, 0644); MODULE_PARM_DESC(hystart_low_window, "lower bound cwnd for hybrid slow start"); +module_param(hystart_ack_delta, int, 0644); +MODULE_PARM_DESC(hystart_ack_delta, "spacing between ack's indicating train (msecs)"); /* BIC TCP Parameters */ struct bictcp { @@ -343,7 +346,7 @@ static void hystart_update(struct sock *sk, u32 delay) /* first detection parameter - ack-train detection */ if ((s32)(curr_jiffies - ca->last_jiffies) <= - msecs_to_jiffies(2)) { + msecs_to_jiffies(hystart_ack_delta)) { ca->last_jiffies = curr_jiffies; if ((s32) (curr_jiffies - ca->round_start) > ca->delay_min >> 4) From 17a6e9f1aa9ba07ca13a1eaf1e631e743af50cca Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 14 Mar 2011 07:52:15 +0000 Subject: [PATCH 14/20] tcp_cubic: fix clock dependency The hystart code was written with assumption that HZ=1000. Replace the use of jiffies with bictcp_clock as a millisecond real time clock. Signed-off-by: Stephen Hemminger Reported-by: Lucas Nussbaum Signed-off-by: David S. Miller --- net/ipv4/tcp_cubic.c | 31 +++++++++++++++++++------------ 1 file changed, 19 insertions(+), 12 deletions(-) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 66d3b00233ec..f4fb2d4b90ad 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -88,7 +88,7 @@ struct bictcp { u32 last_time; /* time when updated last_cwnd */ u32 bic_origin_point;/* origin point of bic function */ u32 bic_K; /* time to origin point from the beginning of the current epoch */ - u32 delay_min; /* min delay */ + u32 delay_min; /* min delay (msec << 3) */ u32 epoch_start; /* beginning of an epoch */ u32 ack_cnt; /* number of acks */ u32 tcp_cwnd; /* estimated tcp cwnd */ @@ -98,7 +98,7 @@ struct bictcp { u8 found; /* the exit point is found? */ u32 round_start; /* beginning of each round */ u32 end_seq; /* end_seq of the round */ - u32 last_jiffies; /* last time when the ACK spacing is close */ + u32 last_ack; /* last time when the ACK spacing is close */ u32 curr_rtt; /* the minimum rtt of current round */ }; @@ -119,12 +119,21 @@ static inline void bictcp_reset(struct bictcp *ca) ca->found = 0; } +static inline u32 bictcp_clock(void) +{ +#if HZ < 1000 + return ktime_to_ms(ktime_get_real()); +#else + return jiffies_to_msecs(jiffies); +#endif +} + static inline void bictcp_hystart_reset(struct sock *sk) { struct tcp_sock *tp = tcp_sk(sk); struct bictcp *ca = inet_csk_ca(sk); - ca->round_start = ca->last_jiffies = jiffies; + ca->round_start = ca->last_ack = bictcp_clock(); ca->end_seq = tp->snd_nxt; ca->curr_rtt = 0; ca->sample_cnt = 0; @@ -239,8 +248,8 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) */ /* change the unit from HZ to bictcp_HZ */ - t = ((tcp_time_stamp + (ca->delay_min>>3) - ca->epoch_start) - << BICTCP_HZ) / HZ; + t = ((tcp_time_stamp + msecs_to_jiffies(ca->delay_min>>3) + - ca->epoch_start) << BICTCP_HZ) / HZ; if (t < ca->bic_K) /* t - K */ offs = ca->bic_K - t; @@ -342,14 +351,12 @@ static void hystart_update(struct sock *sk, u32 delay) struct bictcp *ca = inet_csk_ca(sk); if (!(ca->found & hystart_detect)) { - u32 curr_jiffies = jiffies; + u32 now = bictcp_clock(); /* first detection parameter - ack-train detection */ - if ((s32)(curr_jiffies - ca->last_jiffies) <= - msecs_to_jiffies(hystart_ack_delta)) { - ca->last_jiffies = curr_jiffies; - if ((s32) (curr_jiffies - ca->round_start) > - ca->delay_min >> 4) + if ((s32)(now - ca->last_ack) <= hystart_ack_delta) { + ca->last_ack = now; + if ((s32)(now - ca->round_start) > ca->delay_min >> 4) ca->found |= HYSTART_ACK_TRAIN; } @@ -396,7 +403,7 @@ static void bictcp_acked(struct sock *sk, u32 cnt, s32 rtt_us) if ((s32)(tcp_time_stamp - ca->epoch_start) < HZ) return; - delay = usecs_to_jiffies(rtt_us) << 3; + delay = (rtt_us << 3) / USEC_PER_MSEC; if (delay == 0) delay = 1; From 3b585b34493ec9db382d6c325d4ed77b9eb2d2a5 Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Mon, 14 Mar 2011 07:52:16 +0000 Subject: [PATCH 15/20] tcp_cubic: enable high resolution ack time if needed This is a refined version of an earlier patch by Lucas Nussbaum. Cubic needs RTT values in milliseconds. If HZ < 1000 then the values will be too coarse. Signed-off-by: Stephen Hemminger Reported-by: Lucas Nussbaum Signed-off-by: David S. Miller --- net/ipv4/tcp_cubic.c | 4 ++++ 1 file changed, 4 insertions(+) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index f4fb2d4b90ad..5e0491d742ca 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -459,6 +459,10 @@ static int __init cubictcp_register(void) /* divide by bic_scale and by constant Srtt (100ms) */ do_div(cube_factor, bic_scale * 10); + /* hystart needs ms clock resolution */ + if (hystart && HZ < 1000) + cubictcp.flags |= TCP_CONG_RTT_STAMP; + return tcp_register_congestion_control(&cubictcp); } From 2b4636a5f8ca547000f6aba24ec1c58f31f4a91d Mon Sep 17 00:00:00 2001 From: Sangtae Ha Date: Mon, 14 Mar 2011 07:52:17 +0000 Subject: [PATCH 16/20] tcp_cubic: make the delay threshold of HyStart less sensitive Make HyStart less sensitive to abrupt delay variations due to buffer bloat. Signed-off-by: Sangtae Ha Acked-by: Stephen Hemminger Reported-by: Lucas Nussbaum Signed-off-by: David S. Miller --- net/ipv4/tcp_cubic.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 5e0491d742ca..7172c129ff19 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -39,7 +39,7 @@ /* Number of delay samples for detecting the increase of delay */ #define HYSTART_MIN_SAMPLES 8 -#define HYSTART_DELAY_MIN (2U<<3) +#define HYSTART_DELAY_MIN (4U<<3) #define HYSTART_DELAY_MAX (16U<<3) #define HYSTART_DELAY_THRESH(x) clamp(x, HYSTART_DELAY_MIN, HYSTART_DELAY_MAX) From b5ccd07337489fa9c9d32e0b628a2168b7953adf Mon Sep 17 00:00:00 2001 From: Sangtae Ha Date: Mon, 14 Mar 2011 07:52:18 +0000 Subject: [PATCH 17/20] tcp_cubic: fix low utilization of CUBIC with HyStart HyStart sets the initial exit point of slow start. Suppose that HyStart exits at 0.5BDP in a BDP network and no history exists. If the BDP of a network is large, CUBIC's initial cwnd growth may be too conservative to utilize the link. CUBIC increases the cwnd 20% per RTT in this case. Signed-off-by: Sangtae Ha Acked-by: Stephen Hemminger Signed-off-by: David S. Miller --- net/ipv4/tcp_cubic.c | 7 +++++++ 1 file changed, 7 insertions(+) diff --git a/net/ipv4/tcp_cubic.c b/net/ipv4/tcp_cubic.c index 7172c129ff19..90d92dd4cf13 100644 --- a/net/ipv4/tcp_cubic.c +++ b/net/ipv4/tcp_cubic.c @@ -270,6 +270,13 @@ static inline void bictcp_update(struct bictcp *ca, u32 cwnd) ca->cnt = 100 * cwnd; /* very small increment*/ } + /* + * The initial growth of cubic function may be too conservative + * when the available bandwidth is still unknown. + */ + if (ca->loss_cwnd == 0 && ca->cnt > 20) + ca->cnt = 20; /* increase cwnd 5% per RTT */ + /* TCP Friendly */ if (tcp_friendliness) { u32 scale = beta_scale; From 12a2856b604476c27d85a5f9a57ae1661fc46019 Mon Sep 17 00:00:00 2001 From: Daniel Lezcano Date: Mon, 14 Mar 2011 06:08:07 +0000 Subject: [PATCH 18/20] macvlan : fix checksums error when we are in bridge mode When the lower device has offloading capabilities, the packets checksums are not computed. That leads to have any macvlan port in bridge mode to not work because the packets are dropped due to a bad checksum. If the macvlan is in bridge mode, the packet is forwarded to another macvlan port and reach the network stack where it looks for a checksum but this one was not computed due to the offloading of the lower device. In this case, we have to set the packet with CHECKSUM_UNNECESSARY when it is forwarded to a bridged port and restore the previous value of ip_summed when the packet goes to the lowerdev. Signed-off-by: Daniel Lezcano Cc: Patrick McHardy Cc: Andrian Nord Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/macvlan.c | 3 +++ 1 file changed, 3 insertions(+) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 6ed577b065df..497991bd3b64 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -219,9 +219,11 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; + __u8 ip_summed = skb->ip_summed; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = (void *)skb->data; + skb->ip_summed = CHECKSUM_UNNECESSARY; /* send to other bridge ports directly */ if (is_multicast_ether_addr(eth->h_dest)) { @@ -241,6 +243,7 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) } xmit_world: + skb->ip_summed = ip_summed; skb_set_dev(skb, vlan->lowerdev); return dev_queue_xmit(skb); } From 48f26d514ed14f717ebd49439894a9637e0353a9 Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Mon, 14 Mar 2011 21:05:40 -0700 Subject: [PATCH 19/20] xen: netfront: fix xennet_get_ethtool_stats() commit e9a799ea4a5551d2 (xen: netfront: ethtool stats fields should be unsigned long) made rx_gso_checksum_fixup an unsigned long. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- drivers/net/xen-netfront.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/drivers/net/xen-netfront.c b/drivers/net/xen-netfront.c index 27cf72f26cbb..5b399b54fef7 100644 --- a/drivers/net/xen-netfront.c +++ b/drivers/net/xen-netfront.c @@ -1692,7 +1692,7 @@ static void xennet_get_ethtool_stats(struct net_device *dev, int i; for (i = 0; i < ARRAY_SIZE(xennet_stats); i++) - data[i] = *(int *)(np + xennet_stats[i].offset); + data[i] = *(unsigned long *)(np + xennet_stats[i].offset); } static void xennet_get_strings(struct net_device *dev, u32 stringset, u8 * data) From 84c0c6933cb0303fa006992a6659c2b46de4eb17 Mon Sep 17 00:00:00 2001 From: Jeongtae Park Date: Tue, 15 Mar 2011 14:52:48 -0700 Subject: [PATCH 20/20] smsc911x: Fix build error when SMSC_TRACE() used This patch fixes build error when SMSC_TRACE() used. Signed-off-by: Jeongtae Park Signed-off-by: David S. Miller --- drivers/net/smsc911x.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) diff --git a/drivers/net/smsc911x.c b/drivers/net/smsc911x.c index d70bde95460b..1566259c1f27 100644 --- a/drivers/net/smsc911x.c +++ b/drivers/net/smsc911x.c @@ -791,8 +791,8 @@ static int smsc911x_mii_probe(struct net_device *dev) return -ENODEV; } - SMSC_TRACE(PROBE, "PHY %d: addr %d, phy_id 0x%08X", - phy_addr, phydev->addr, phydev->phy_id); + SMSC_TRACE(PROBE, "PHY: addr %d, phy_id 0x%08X", + phydev->addr, phydev->phy_id); ret = phy_connect_direct(dev, phydev, &smsc911x_phy_adjust_link, 0,