From 5f286e113fa377e50bd18fc45e5a0d4d83f6950c Mon Sep 17 00:00:00 2001 From: Sergei Shtylyov Date: Sat, 28 Apr 2007 20:57:37 -0700 Subject: [NETPOLL]: Fix TX queue overflow in trapped mode. CONFIG_NETPOLL_TRAP causes the TX queue controls to be completely bypassed in the netpoll's "trapped" mode which easily causes overflows in the drivers with short TX queues (most notably, in 8139too with its 4-deep queue). So, make this option more sensible by making it only bypass the TX softirq wakeup. Signed-off-by: Sergei Shtylyov Acked-by: Jeff Garzik Acked-by: Tom Rini Acked-by: Matt Mackall Signed-off-by: David S. Miller --- include/linux/netdevice.h | 8 +++----- 1 file changed, 3 insertions(+), 5 deletions(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index e027a3750a7..24cef42f1e0 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -654,8 +654,10 @@ static inline void netif_start_queue(struct net_device *dev) static inline void netif_wake_queue(struct net_device *dev) { #ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) + if (netpoll_trap()) { + clear_bit(__LINK_STATE_XOFF, &dev->state); return; + } #endif if (test_and_clear_bit(__LINK_STATE_XOFF, &dev->state)) __netif_schedule(dev); @@ -663,10 +665,6 @@ static inline void netif_wake_queue(struct net_device *dev) static inline void netif_stop_queue(struct net_device *dev) { -#ifdef CONFIG_NETPOLL_TRAP - if (netpoll_trap()) - return; -#endif set_bit(__LINK_STATE_XOFF, &dev->state); } -- cgit v1.2.3 From 5a1b5898ee9e0bf68a86609ecb9775457b1857a5 Mon Sep 17 00:00:00 2001 From: Rusty Russell Date: Sat, 28 Apr 2007 21:04:03 -0700 Subject: [NET]: Remove NETIF_F_INTERNAL_STATS, default to internal stats. Herbert Xu conviced me that a new flag was overkill; every driver currently overrides get_stats, so we might as well make the internal one the default. If someone did fail to set get_stats, they would now get all 0 stats instead of "No statistics available". Signed-off-by: Rusty Russell Acked-by: Herbert Xu Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - 1 file changed, 1 deletion(-) (limited to 'include') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 24cef42f1e0..ac0c92b1e00 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -325,7 +325,6 @@ struct net_device #define NETIF_F_VLAN_CHALLENGED 1024 /* Device cannot handle VLAN packets */ #define NETIF_F_GSO 2048 /* Enable software GSO. */ #define NETIF_F_LLTX 4096 /* LockLess TX */ -#define NETIF_F_INTERNAL_STATS 8192 /* Use stats structure in net_device */ /* Segmentation offload features */ #define NETIF_F_GSO_SHIFT 16 -- cgit v1.2.3 From ecfd6b183780c6d9e85873693b3ce6c5f4d08b58 Mon Sep 17 00:00:00 2001 From: Jamal Hadi Salim Date: Sat, 28 Apr 2007 21:20:32 -0700 Subject: [XFRM]: Export SPD info With this patch you can use iproute2 in user space to efficiently see how many policies exist in different directions. Signed-off-by: Jamal Hadi Salim Signed-off-by: David S. Miller --- include/linux/xfrm.h | 35 +++++++++++++++++++++++++++++++++++ include/net/xfrm.h | 13 +++++++++++++ 2 files changed, 48 insertions(+) (limited to 'include') diff --git a/include/linux/xfrm.h b/include/linux/xfrm.h index 9c656a5cf84..a5d53e0fe15 100644 --- a/include/linux/xfrm.h +++ b/include/linux/xfrm.h @@ -185,6 +185,11 @@ enum { #define XFRM_MSG_NEWSADINFO XFRM_MSG_NEWSADINFO XFRM_MSG_GETSADINFO, #define XFRM_MSG_GETSADINFO XFRM_MSG_GETSADINFO + + XFRM_MSG_NEWSPDINFO, +#define XFRM_MSG_NEWSPDINFO XFRM_MSG_NEWSPDINFO + XFRM_MSG_GETSPDINFO, +#define XFRM_MSG_GETSPDINFO XFRM_MSG_GETSPDINFO __XFRM_MSG_MAX }; #define XFRM_MSG_MAX (__XFRM_MSG_MAX - 1) @@ -290,6 +295,36 @@ enum xfrm_sadattr_type_t { #define XFRMA_SAD_MAX (__XFRMA_SAD_MAX - 1) }; +/* SPD Table filter flags */ +enum xfrm_spd_ftype_t { + XFRM_SPD_UNSPEC, + XFRM_SPD_HMASK=1, + XFRM_SPD_HMAX=2, + XFRM_SPD_ICNT=4, + XFRM_SPD_OCNT=8, + XFRM_SPD_FCNT=16, + XFRM_SPD_ISCNT=32, + XFRM_SPD_OSCNT=64, + XFRM_SPD_FSCNT=128, + __XFRM_SPD_MAX + +#define XFRM_SPD_MAX (__XFRM_SPD_MAX - 1) +}; +enum xfrm_spdattr_type_t { + XFRMA_SPD_UNSPEC, + XFRMA_SPDHMASK, + XFRMA_SPDHMAX, + XFRMA_SPDICNT, + XFRMA_SPDOCNT, + XFRMA_SPDFCNT, + XFRMA_SPDISCNT, + XFRMA_SPDOSCNT, + XFRMA_SPDFSCNT, + __XFRMA_SPD_MAX + +#define XFRMA_SPD_MAX (__XFRMA_SPD_MAX - 1) +}; + struct xfrm_usersa_info { struct xfrm_selector sel; struct xfrm_id id; diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 8287081d77f..9561bf817b0 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -423,6 +423,18 @@ struct xfrm_sadinfo u32 sadhmcnt; /* max allowed hash bkts */ u32 sadcnt; /* current running count */ }; + +struct xfrm_spdinfo +{ + u32 incnt; + u32 outcnt; + u32 fwdcnt; + u32 inscnt; + u32 outscnt; + u32 fwdscnt; + u32 spdhcnt; + u32 spdhmcnt; +}; #ifdef CONFIG_AUDITSYSCALL extern void xfrm_audit_log(uid_t auid, u32 secid, int type, int result, struct xfrm_policy *xp, struct xfrm_state *x); @@ -946,6 +958,7 @@ extern struct xfrm_state *xfrm_find_acq_byseq(u32 seq); extern int xfrm_state_delete(struct xfrm_state *x); extern void xfrm_state_flush(u8 proto, struct xfrm_audit *audit_info); extern void xfrm_sad_getinfo(struct xfrm_sadinfo *si); +extern void xfrm_spd_getinfo(struct xfrm_spdinfo *si); extern int xfrm_replay_check(struct xfrm_state *x, __be32 seq); extern void xfrm_replay_advance(struct xfrm_state *x, __be32 seq); extern void xfrm_replay_notify(struct xfrm_state *x, int event); -- cgit v1.2.3 From 04b090d50c88ac8e5ec9c2e985bb65bd153893aa Mon Sep 17 00:00:00 2001 From: Martin Schwidefsky Date: Sat, 28 Apr 2007 23:03:59 -0700 Subject: [AF_IUCV/IUCV]: smp_call_function deadlock Calling smp_call_function can lead to a deadlock if it is called from tasklet context. Fixing this deadlock requires to move the smp_call_function from the tasklet context to a work queue. To do that queue the path pending interrupts to a separate list and move the path cleanup out of iucv_path_sever to iucv_path_connect and iucv_path_pending. This creates a new requirement for iucv_path_connect: it may not be called from tasklet context anymore. Also fixed compile problem for CONFIG_HOTPLUG_CPU=n and another one when walking the cpu_online mask. When doing this, we must disable cpu hotplug. Signed-off-by: Frank Pavlic Signed-off-by: Martin Schwidefsky Signed-off-by: David S. Miller --- include/net/iucv/iucv.h | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'include') diff --git a/include/net/iucv/iucv.h b/include/net/iucv/iucv.h index 746e7416261..fd70adbb356 100644 --- a/include/net/iucv/iucv.h +++ b/include/net/iucv/iucv.h @@ -16,7 +16,7 @@ * completed a register, it can exploit the other functions. * For furthur reference on all IUCV functionality, refer to the * CP Programming Services book, also available on the web thru - * www.ibm.com/s390/vm/pubs, manual # SC24-5760 + * www.vm.ibm.com/pubs, manual # SC24-6084 * * Definition of Return Codes * - All positive return codes including zero are reflected back -- cgit v1.2.3 From 46f8914e53c28d0716c586e08a7c819d8ebb9d54 Mon Sep 17 00:00:00 2001 From: James Chapman Date: Mon, 30 Apr 2007 00:07:31 -0700 Subject: [SKB]: Introduce skb_queue_walk_safe() This patch provides a method for walking skb lists while inserting or removing skbs from the list. Signed-off-by: James Chapman Signed-off-by: David S. Miller --- include/linux/skbuff.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 2694cb3ca76..253a2b9be9d 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1471,6 +1471,11 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) prefetch(skb->next), (skb != (struct sk_buff *)(queue)); \ skb = skb->next) +#define skb_queue_walk_safe(queue, skb, tmp) \ + for (skb = (queue)->next, tmp = skb->next; \ + skb != (struct sk_buff *)(queue); \ + skb = tmp, tmp = skb->next) + #define skb_queue_reverse_walk(queue, skb) \ for (skb = (queue)->prev; \ prefetch(skb->prev), (skb != (struct sk_buff *)(queue)); \ -- cgit v1.2.3 From 34588b4c046c34773e5a1a962da7b78b05c4d1bd Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 30 Apr 2007 00:57:33 -0700 Subject: [TCP]: Catch skb with S+L bugs earlier MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit SACKED_ACKED and LOST are mutually exclusive with SACK, thus having their sum larger than packets_out is bug with SACK. Eventually these bugs trigger traps in the tcp_clean_rtx_queue with SACK but it's much more informative to do this here. Non-SACK TCP, however, could get more than packets_out duplicate ACKs which each increment sacked_out, so it makes sense to do this kind of limitting for non-SACK TCP but not for SACK enabled one. Perhaps the author had the opposite in mind but did the logic accidently wrong way around? Anyway, the sacked_out incrementer code for non-SACK already deals this issue before calling sync_left_out so this trapping can be done unconditionally. Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 4 +--- 1 file changed, 1 insertion(+), 3 deletions(-) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index a385797f160..c6ecd455eda 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -736,9 +736,7 @@ static inline __u32 tcp_current_ssthresh(const struct sock *sk) static inline void tcp_sync_left_out(struct tcp_sock *tp) { - if (tp->rx_opt.sack_ok && - (tp->sacked_out >= tp->packets_out - tp->lost_out)) - tp->sacked_out = tp->packets_out - tp->lost_out; + BUG_ON(tp->sacked_out + tp->lost_out > tp->packets_out); tp->left_out = tp->sacked_out + tp->lost_out; } -- cgit v1.2.3 From 157bfc25020f7eb731f94140e099307ade47299e Mon Sep 17 00:00:00 2001 From: Masahide NAKAMURA Date: Mon, 30 Apr 2007 00:33:35 -0700 Subject: [XFRM]: Restrict upper layer information by bundle. On MIPv6 usage, XFRM sub policy is enabled. When main (IPsec) and sub (MIPv6) policy selectors have the same address set but different upper layer information (i.e. protocol number and its ports or type/code), multiple bundle should be created. However, currently we have issue to use the same bundle created for the first time with all flows covered by the case. It is useful for the bundle to have the upper layer information to be restructured correctly if it does not match with the flow. 1. Bundle was created by two policies Selector from another policy is added to xfrm_dst. If the flow does not match the selector, it goes to slow path to restructure new bundle by single policy. 2. Bundle was created by one policy Flow cache is added to xfrm_dst as originated one. If the flow does not match the cache, it goes to slow path to try searching another policy. Signed-off-by: Masahide NAKAMURA Signed-off-by: David S. Miller --- include/net/flow.h | 6 ++++++ include/net/xfrm.h | 10 ++++++++++ 2 files changed, 16 insertions(+) (limited to 'include') diff --git a/include/net/flow.h b/include/net/flow.h index ce4b10d8b41..f3cc1f81261 100644 --- a/include/net/flow.h +++ b/include/net/flow.h @@ -97,4 +97,10 @@ extern void *flow_cache_lookup(struct flowi *key, u16 family, u8 dir, extern void flow_cache_flush(void); extern atomic_t flow_cache_genid; +static inline int flow_cache_uli_match(struct flowi *fl1, struct flowi *fl2) +{ + return (fl1->proto == fl2->proto && + !memcmp(&fl1->uli_u, &fl2->uli_u, sizeof(fl1->uli_u))); +} + #endif diff --git a/include/net/xfrm.h b/include/net/xfrm.h index 9561bf817b0..66c2d3eec03 100644 --- a/include/net/xfrm.h +++ b/include/net/xfrm.h @@ -603,6 +603,10 @@ struct xfrm_dst struct rt6_info rt6; } u; struct dst_entry *route; +#ifdef CONFIG_XFRM_SUB_POLICY + struct flowi *origin; + struct xfrm_selector *partner; +#endif u32 genid; u32 route_mtu_cached; u32 child_mtu_cached; @@ -615,6 +619,12 @@ static inline void xfrm_dst_destroy(struct xfrm_dst *xdst) dst_release(xdst->route); if (likely(xdst->u.dst.xfrm)) xfrm_state_put(xdst->u.dst.xfrm); +#ifdef CONFIG_XFRM_SUB_POLICY + kfree(xdst->origin); + xdst->origin = NULL; + kfree(xdst->partner); + xdst->partner = NULL; +#endif } extern void xfrm_dst_ifdown(struct dst_entry *dst, struct net_device *dev); -- cgit v1.2.3 From d551e4541dd60ae53459f77a971f2d6043431f5f Mon Sep 17 00:00:00 2001 From: =?UTF-8?q?Ilpo=20J=C3=A4rvinen?= Date: Mon, 30 Apr 2007 00:42:20 -0700 Subject: [TCP] FRTO: RFC4138 allows Nagle override when new data must be sent MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit This is a corner case where less than MSS sized new data thingie is awaiting in the send queue. For F-RTO to work correctly, a new data segment must be sent at certain point or F-RTO cannot be used at all. RFC4138 allows overriding of Nagle at that point. Implementation uses frto_counter states 2 and 3 to distinguish when Nagle override is needed. Signed-off-by: Ilpo Järvinen Signed-off-by: David S. Miller --- include/net/tcp.h | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'include') diff --git a/include/net/tcp.h b/include/net/tcp.h index c6ecd455eda..ef8f9d4dae8 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -1199,9 +1199,14 @@ static inline struct sk_buff *tcp_send_head(struct sock *sk) static inline void tcp_advance_send_head(struct sock *sk, struct sk_buff *skb) { + struct tcp_sock *tp = tcp_sk(sk); + sk->sk_send_head = skb->next; if (sk->sk_send_head == (struct sk_buff *)&sk->sk_write_queue) sk->sk_send_head = NULL; + /* Don't override Nagle indefinately with F-RTO */ + if (tp->frto_counter == 2) + tp->frto_counter = 3; } static inline void tcp_check_send_head(struct sock *sk, struct sk_buff *skb_unlinked) -- cgit v1.2.3 From 71ff6c0a857d11e70aec0c8f1e0d4ae9a45dd468 Mon Sep 17 00:00:00 2001 From: Mitsuru Chinen Date: Mon, 30 Apr 2007 00:45:02 -0700 Subject: [SNMP]: Add definitions for {In,Out}BcastPkts The updated IP-MIB RFC (RFC4293) specifys new objects, InBcastPkts and OutBcastPkts. This adds definitions for them. Signed-off-by: Mitsuru Chinen Signed-off-by: David S. Miller --- include/linux/snmp.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/snmp.h b/include/linux/snmp.h index 854aa6b543f..802b3a38b04 100644 --- a/include/linux/snmp.h +++ b/include/linux/snmp.h @@ -40,6 +40,8 @@ enum IPSTATS_MIB_FRAGCREATES, /* FragCreates */ IPSTATS_MIB_INMCASTPKTS, /* InMcastPkts */ IPSTATS_MIB_OUTMCASTPKTS, /* OutMcastPkts */ + IPSTATS_MIB_INBCASTPKTS, /* InBcastPkts */ + IPSTATS_MIB_OUTBCASTPKTS, /* OutBcastPkts */ __IPSTATS_MIB_MAX }; -- cgit v1.2.3