From 013dbb325be702d777118d5e4ffefff3dad2b153 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Wed, 19 Jun 2013 14:32:33 -0400 Subject: net: delete __cpuinit usage from all net files The __cpuinit type of throwaway sections might have made sense some time ago when RAM was more constrained, but now the savings do not offset the cost and complications. For example, the fix in commit 5e427ec2d0 ("x86: Fix bit corruption at CPU resume time") is a good example of the nasty type of bugs that can be created with improper use of the various __init prefixes. After a discussion on LKML[1] it was decided that cpuinit should go the way of devinit and be phased out. Once all the users are gone, we can then finally remove the macros themselves from linux/init.h. This removes all the net/* uses of the __cpuinit macros from all C files. [1] https://lkml.org/lkml/2013/5/20/589 Cc: "David S. Miller" Cc: netdev@vger.kernel.org Signed-off-by: Paul Gortmaker --- net/core/flow.c | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'net/core') diff --git a/net/core/flow.c b/net/core/flow.c index 7102f166482d..dfa602ceb8cd 100644 --- a/net/core/flow.c +++ b/net/core/flow.c @@ -403,7 +403,7 @@ void flow_cache_flush_deferred(void) schedule_work(&flow_cache_flush_work); } -static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) +static int flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) { struct flow_cache_percpu *fcp = per_cpu_ptr(fc->percpu, cpu); size_t sz = sizeof(struct hlist_head) * flow_cache_hash_size(fc); @@ -421,7 +421,7 @@ static int __cpuinit flow_cache_cpu_prepare(struct flow_cache *fc, int cpu) return 0; } -static int __cpuinit flow_cache_cpu(struct notifier_block *nfb, +static int flow_cache_cpu(struct notifier_block *nfb, unsigned long action, void *hcpu) { -- cgit v1.2.3 From 8a73125c36809527236e1d8d367a09a3f0e9f9e1 Mon Sep 17 00:00:00 2001 From: Dragos Foianu Date: Sat, 13 Jul 2013 14:43:00 +0100 Subject: ethtool: fixed trailing statements in ethtool Applied fixes suggested by checkpatch.pl. Signed-off-by: Dragos Foianu Signed-off-by: David S. Miller --- net/core/ethtool.c | 30 ++++++++++++++++++++---------- 1 file changed, 20 insertions(+), 10 deletions(-) (limited to 'net/core') diff --git a/net/core/ethtool.c b/net/core/ethtool.c index ab5fa6336c84..78e9d9223e40 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -279,11 +279,16 @@ static u32 __ethtool_get_flags(struct net_device *dev) { u32 flags = 0; - if (dev->features & NETIF_F_LRO) flags |= ETH_FLAG_LRO; - if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) flags |= ETH_FLAG_RXVLAN; - if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) flags |= ETH_FLAG_TXVLAN; - if (dev->features & NETIF_F_NTUPLE) flags |= ETH_FLAG_NTUPLE; - if (dev->features & NETIF_F_RXHASH) flags |= ETH_FLAG_RXHASH; + if (dev->features & NETIF_F_LRO) + flags |= ETH_FLAG_LRO; + if (dev->features & NETIF_F_HW_VLAN_CTAG_RX) + flags |= ETH_FLAG_RXVLAN; + if (dev->features & NETIF_F_HW_VLAN_CTAG_TX) + flags |= ETH_FLAG_TXVLAN; + if (dev->features & NETIF_F_NTUPLE) + flags |= ETH_FLAG_NTUPLE; + if (dev->features & NETIF_F_RXHASH) + flags |= ETH_FLAG_RXHASH; return flags; } @@ -295,11 +300,16 @@ static int __ethtool_set_flags(struct net_device *dev, u32 data) if (data & ~ETH_ALL_FLAGS) return -EINVAL; - if (data & ETH_FLAG_LRO) features |= NETIF_F_LRO; - if (data & ETH_FLAG_RXVLAN) features |= NETIF_F_HW_VLAN_CTAG_RX; - if (data & ETH_FLAG_TXVLAN) features |= NETIF_F_HW_VLAN_CTAG_TX; - if (data & ETH_FLAG_NTUPLE) features |= NETIF_F_NTUPLE; - if (data & ETH_FLAG_RXHASH) features |= NETIF_F_RXHASH; + if (data & ETH_FLAG_LRO) + features |= NETIF_F_LRO; + if (data & ETH_FLAG_RXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_RX; + if (data & ETH_FLAG_TXVLAN) + features |= NETIF_F_HW_VLAN_CTAG_TX; + if (data & ETH_FLAG_NTUPLE) + features |= NETIF_F_NTUPLE; + if (data & ETH_FLAG_RXHASH) + features |= NETIF_F_RXHASH; /* allow changing only bits set in hw_features */ changed = (features ^ dev->features) & ETH_ALL_FEATURES; -- cgit v1.2.3 From d4b812dea4a236f729526facf97df1a9d18e191c Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Thu, 18 Jul 2013 07:19:26 -0700 Subject: vlan: mask vlan prio bits In commit 48cc32d38a52d0b68f91a171a8d00531edc6a46e ("vlan: don't deliver frames for unknown vlans to protocols") Florian made sure we set pkt_type to PACKET_OTHERHOST if the vlan id is set and we could find a vlan device for this particular id. But we also have a problem if prio bits are set. Steinar reported an issue on a router receiving IPv6 frames with a vlan tag of 4000 (id 0, prio 2), and tunneled into a sit device, because skb->vlan_tci is set. Forwarded frame is completely corrupted : We can see (8100:4000) being inserted in the middle of IPv6 source address : 16:48:00.780413 IP6 2001:16d8:8100:4000:ee1c:0:9d9:bc87 > 9f94:4d95:2001:67c:29f4::: ICMP6, unknown icmp6 type (0), length 64 0x0000: 0000 0029 8000 c7c3 7103 0001 a0ae e651 0x0010: 0000 0000 ccce 0b00 0000 0000 1011 1213 0x0020: 1415 1617 1819 1a1b 1c1d 1e1f 2021 2223 0x0030: 2425 2627 2829 2a2b 2c2d 2e2f 3031 3233 It seems we are not really ready to properly cope with this right now. We can probably do better in future kernels : vlan_get_ingress_priority() should be a netdev property instead of a per vlan_dev one. For stable kernels, lets clear vlan_tci to fix the bugs. Reported-by: Steinar H. Gunderson Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 3 +-- net/8021q/vlan_core.c | 2 +- net/core/dev.c | 11 +++++++++-- 3 files changed, 11 insertions(+), 5 deletions(-) (limited to 'net/core') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index cdcbafa9b39a..715c343f7c00 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -79,9 +79,8 @@ static inline int is_vlan_dev(struct net_device *dev) } #define vlan_tx_tag_present(__skb) ((__skb)->vlan_tci & VLAN_TAG_PRESENT) -#define vlan_tx_nonzero_tag_present(__skb) \ - (vlan_tx_tag_present(__skb) && ((__skb)->vlan_tci & VLAN_VID_MASK)) #define vlan_tx_tag_get(__skb) ((__skb)->vlan_tci & ~VLAN_TAG_PRESENT) +#define vlan_tx_tag_get_id(__skb) ((__skb)->vlan_tci & VLAN_VID_MASK) #if defined(CONFIG_VLAN_8021Q) || defined(CONFIG_VLAN_8021Q_MODULE) diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 8a15eaadc4bd..4a78c4de9f20 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -9,7 +9,7 @@ bool vlan_do_receive(struct sk_buff **skbp) { struct sk_buff *skb = *skbp; __be16 vlan_proto = skb->vlan_proto; - u16 vlan_id = skb->vlan_tci & VLAN_VID_MASK; + u16 vlan_id = vlan_tx_tag_get_id(skb); struct net_device *vlan_dev; struct vlan_pcpu_stats *rx_stats; diff --git a/net/core/dev.c b/net/core/dev.c index a3d8d44cb7f4..26755dd40daa 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3580,8 +3580,15 @@ ncls: } } - if (vlan_tx_nonzero_tag_present(skb)) - skb->pkt_type = PACKET_OTHERHOST; + if (unlikely(vlan_tx_tag_present(skb))) { + if (vlan_tx_tag_get_id(skb)) + skb->pkt_type = PACKET_OTHERHOST; + /* Note: we might in the future use prio bits + * and set skb->priority like in vlan_do_receive() + * For the time being, just ignore Priority Code Point + */ + skb->vlan_tci = 0; + } /* deliver only exact match when indicated */ null_or_dev = deliver_exact ? skb->dev : NULL; -- cgit v1.2.3 From deceb4c062a8dd63fe554c3be2b4bf9151a5cedf Mon Sep 17 00:00:00 2001 From: Florian Fainelli Date: Tue, 23 Jul 2013 20:22:39 +0100 Subject: net: fix comment above build_skb() build_skb() specifies that the data parameter must come from a kmalloc'd area, this is only true if frag_size equals 0, because then build_skb() will use kzsize(data) to figure out the actual data size. Update the comment to reflect that special condition. Signed-off-by: Florian Fainelli Signed-off-by: David S. Miller --- net/core/skbuff.c | 3 ++- 1 file changed, 2 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 20e02d2605ec..3df4d4ccf440 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -309,7 +309,8 @@ EXPORT_SYMBOL(__alloc_skb); * @frag_size: size of fragment, or 0 if head was kmalloced * * Allocate a new &sk_buff. Caller provides space holding head and - * skb_shared_info. @data must have been allocated by kmalloc() + * skb_shared_info. @data must have been allocated by kmalloc() only if + * @frag_size is 0, otherwise data should come from the page allocator. * The return is the new skb buffer. * On a failure the return is %NULL, and @data is not freed. * Notes : -- cgit v1.2.3 From 555445cd11803c6bc93b2be31968f3949ef7708b Mon Sep 17 00:00:00 2001 From: Francesco Fusco Date: Wed, 24 Jul 2013 10:39:06 +0200 Subject: neigh: prevent overflowing params in /proc/sys/net/ipv4/neigh/ Without this patch, the fields app_solicit, gc_thresh1, gc_thresh2, gc_thresh3, proxy_qlen, ucast_solicit, mcast_solicit could have assumed negative values when setting large numbers. Signed-off-by: Francesco Fusco Signed-off-by: David S. Miller --- net/core/neighbour.c | 29 ++++++++++++++++++++++------- 1 file changed, 22 insertions(+), 7 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index b7de821f98df..9232c68941ab 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -2767,6 +2767,7 @@ EXPORT_SYMBOL(neigh_app_ns); #ifdef CONFIG_SYSCTL static int zero; +static int int_max = INT_MAX; static int unres_qlen_max = INT_MAX / SKB_TRUESIZE(ETH_FRAME_LEN); static int proc_unres_qlen(struct ctl_table *ctl, int write, @@ -2819,19 +2820,25 @@ static struct neigh_sysctl_table { .procname = "mcast_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_UCAST_PROBE] = { .procname = "ucast_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_APP_PROBE] = { .procname = "app_solicit", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_RETRANS_TIME] = { .procname = "retrans_time", @@ -2874,7 +2881,9 @@ static struct neigh_sysctl_table { .procname = "proxy_qlen", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_ANYCAST_DELAY] = { .procname = "anycast_delay", @@ -2916,19 +2925,25 @@ static struct neigh_sysctl_table { .procname = "gc_thresh1", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH2] = { .procname = "gc_thresh2", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, [NEIGH_VAR_GC_THRESH3] = { .procname = "gc_thresh3", .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec, + .extra1 = &zero, + .extra2 = &int_max, + .proc_handler = proc_dointvec_minmax, }, {}, }, -- cgit v1.2.3 From e0d1095ae3405404d247afb00233ef837d58da83 Mon Sep 17 00:00:00 2001 From: Cong Wang Date: Thu, 1 Aug 2013 11:10:25 +0800 Subject: net: rename CONFIG_NET_LL_RX_POLL to CONFIG_NET_RX_BUSY_POLL Eliezer renames several *ll_poll to *busy_poll, but forgets CONFIG_NET_LL_RX_POLL, so in case of confusion, rename it too. Cc: Eliezer Tamir Cc: David S. Miller Signed-off-by: Cong Wang Signed-off-by: David S. Miller --- Documentation/sysctl/net.txt | 4 ++-- drivers/net/ethernet/broadcom/bnx2x/bnx2x.h | 8 ++++---- drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c | 2 +- drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c | 2 +- drivers/net/ethernet/intel/ixgbe/ixgbe.h | 12 ++++++------ drivers/net/ethernet/intel/ixgbe/ixgbe_main.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/en_ethtool.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/en_netdev.c | 6 +++--- drivers/net/ethernet/mellanox/mlx4/mlx4_en.h | 10 +++++----- include/linux/netdevice.h | 2 +- include/linux/skbuff.h | 2 +- include/net/busy_poll.h | 6 +++--- include/net/sock.h | 2 +- net/Kconfig | 2 +- net/core/skbuff.c | 2 +- net/core/sock.c | 6 +++--- net/core/sysctl_net_core.c | 2 +- net/socket.c | 2 +- 18 files changed, 41 insertions(+), 41 deletions(-) (limited to 'net/core') diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 1c15043aaee4..d569f2a424d5 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -52,7 +52,7 @@ Default: 64 busy_read ---------------- -Low latency busy poll timeout for socket reads. (needs CONFIG_NET_LL_RX_POLL) +Low latency busy poll timeout for socket reads. (needs CONFIG_NET_RX_BUSY_POLL) Approximate time in us to busy loop waiting for packets on the device queue. This sets the default value of the SO_BUSY_POLL socket option. Can be set or overridden per socket by setting socket option SO_BUSY_POLL, @@ -63,7 +63,7 @@ Default: 0 (off) busy_poll ---------------- -Low latency busy poll timeout for poll and select. (needs CONFIG_NET_LL_RX_POLL) +Low latency busy poll timeout for poll and select. (needs CONFIG_NET_RX_BUSY_POLL) Approximate time in us to busy loop waiting for events. Recommended value depends on the number of sockets you poll on. For several sockets 50, for several hundreds 100. diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h index dedbd76c033e..d80e34b8285f 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x.h @@ -486,7 +486,7 @@ struct bnx2x_fastpath { struct napi_struct napi; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL unsigned int state; #define BNX2X_FP_STATE_IDLE 0 #define BNX2X_FP_STATE_NAPI (1 << 0) /* NAPI owns this FP */ @@ -498,7 +498,7 @@ struct bnx2x_fastpath { #define BNX2X_FP_USER_PEND (BNX2X_FP_STATE_POLL | BNX2X_FP_STATE_POLL_YIELD) /* protect state */ spinlock_t lock; -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ union host_hc_status_block status_blk; /* chip independent shortcuts into sb structure */ @@ -572,7 +572,7 @@ struct bnx2x_fastpath { #define bnx2x_fp_stats(bp, fp) (&((bp)->fp_stats[(fp)->index])) #define bnx2x_fp_qstats(bp, fp) (&((bp)->fp_stats[(fp)->index].eth_q_stats)) -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL static inline void bnx2x_fp_init_lock(struct bnx2x_fastpath *fp) { spin_lock_init(&fp->lock); @@ -680,7 +680,7 @@ static inline bool bnx2x_fp_ll_polling(struct bnx2x_fastpath *fp) { return false; } -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ /* Use 2500 as a mini-jumbo MTU for FCoE */ #define BNX2X_FCOE_MINI_JUMBO_MTU 2500 diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c index ee350bde1818..f2d1ff10054b 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_cmn.c @@ -3117,7 +3117,7 @@ int bnx2x_poll(struct napi_struct *napi, int budget) return work_done; } -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL /* must be called with local_bh_disable()d */ int bnx2x_low_latency_recv(struct napi_struct *napi) { diff --git a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c index e5da07858a2f..e06186c305d8 100644 --- a/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c +++ b/drivers/net/ethernet/broadcom/bnx2x/bnx2x_main.c @@ -12026,7 +12026,7 @@ static const struct net_device_ops bnx2x_netdev_ops = { .ndo_fcoe_get_wwn = bnx2x_fcoe_get_wwn, #endif -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL .ndo_busy_poll = bnx2x_low_latency_recv, #endif }; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 7be725cdfea8..a6494e5daffe 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -54,7 +54,7 @@ #include -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL #define LL_EXTENDED_STATS #endif /* common prefix used by pr_<> macros */ @@ -366,7 +366,7 @@ struct ixgbe_q_vector { struct rcu_head rcu; /* to avoid race with update stats on free */ char name[IFNAMSIZ + 9]; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL unsigned int state; #define IXGBE_QV_STATE_IDLE 0 #define IXGBE_QV_STATE_NAPI 1 /* NAPI owns this QV */ @@ -377,12 +377,12 @@ struct ixgbe_q_vector { #define IXGBE_QV_YIELD (IXGBE_QV_STATE_NAPI_YIELD | IXGBE_QV_STATE_POLL_YIELD) #define IXGBE_QV_USER_PEND (IXGBE_QV_STATE_POLL | IXGBE_QV_STATE_POLL_YIELD) spinlock_t lock; -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ /* for dynamic allocation of rings associated with this q_vector */ struct ixgbe_ring ring[0] ____cacheline_internodealigned_in_smp; }; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector) { @@ -462,7 +462,7 @@ static inline bool ixgbe_qv_ll_polling(struct ixgbe_q_vector *q_vector) WARN_ON(!(q_vector->state & IXGBE_QV_LOCKED)); return q_vector->state & IXGBE_QV_USER_PEND; } -#else /* CONFIG_NET_LL_RX_POLL */ +#else /* CONFIG_NET_RX_BUSY_POLL */ static inline void ixgbe_qv_init_lock(struct ixgbe_q_vector *q_vector) { } @@ -491,7 +491,7 @@ static inline bool ixgbe_qv_ll_polling(struct ixgbe_q_vector *q_vector) { return false; } -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ #ifdef CONFIG_IXGBE_HWMON diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index bad8f14b1941..be4b1fb3d0d2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1998,7 +1998,7 @@ static int ixgbe_clean_rx_irq(struct ixgbe_q_vector *q_vector, return total_rx_packets; } -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL /* must be called with local_bh_disable()d */ static int ixgbe_low_latency_recv(struct napi_struct *napi) { @@ -2030,7 +2030,7 @@ static int ixgbe_low_latency_recv(struct napi_struct *napi) return found; } -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ /** * ixgbe_configure_msix - Configure MSI-X hardware @@ -7227,7 +7227,7 @@ static const struct net_device_ops ixgbe_netdev_ops = { #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = ixgbe_netpoll, #endif -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL .ndo_busy_poll = ixgbe_low_latency_recv, #endif #ifdef IXGBE_FCOE diff --git a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c index 727874f575ce..a28cd801a236 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_ethtool.c @@ -223,7 +223,7 @@ static int mlx4_en_get_sset_count(struct net_device *dev, int sset) case ETH_SS_STATS: return (priv->stats_bitmap ? bit_count : NUM_ALL_STATS) + (priv->tx_ring_num * 2) + -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL (priv->rx_ring_num * 5); #else (priv->rx_ring_num * 2); @@ -276,7 +276,7 @@ static void mlx4_en_get_ethtool_stats(struct net_device *dev, for (i = 0; i < priv->rx_ring_num; i++) { data[index++] = priv->rx_ring[i].packets; data[index++] = priv->rx_ring[i].bytes; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL data[index++] = priv->rx_ring[i].yields; data[index++] = priv->rx_ring[i].misses; data[index++] = priv->rx_ring[i].cleaned; @@ -344,7 +344,7 @@ static void mlx4_en_get_strings(struct net_device *dev, "rx%d_packets", i); sprintf(data + (index++) * ETH_GSTRING_LEN, "rx%d_bytes", i); -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL sprintf(data + (index++) * ETH_GSTRING_LEN, "rx%d_napi_yield", i); sprintf(data + (index++) * ETH_GSTRING_LEN, diff --git a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c index 5eac871399d8..fa37b7a61213 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_netdev.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_netdev.c @@ -68,7 +68,7 @@ int mlx4_en_setup_tc(struct net_device *dev, u8 up) return 0; } -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL /* must be called with local_bh_disable()d */ static int mlx4_en_low_latency_recv(struct napi_struct *napi) { @@ -94,7 +94,7 @@ static int mlx4_en_low_latency_recv(struct napi_struct *napi) return done; } -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ #ifdef CONFIG_RFS_ACCEL @@ -2140,7 +2140,7 @@ static const struct net_device_ops mlx4_netdev_ops = { #ifdef CONFIG_RFS_ACCEL .ndo_rx_flow_steer = mlx4_en_filter_rfs, #endif -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL .ndo_busy_poll = mlx4_en_low_latency_recv, #endif }; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h index 35fb60e2320c..5e0aa569306a 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4_en.h @@ -292,7 +292,7 @@ struct mlx4_en_rx_ring { void *rx_info; unsigned long bytes; unsigned long packets; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL unsigned long yields; unsigned long misses; unsigned long cleaned; @@ -318,7 +318,7 @@ struct mlx4_en_cq { struct mlx4_cqe *buf; #define MLX4_EN_OPCODE_ERROR 0x1e -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL unsigned int state; #define MLX4_EN_CQ_STATE_IDLE 0 #define MLX4_EN_CQ_STATE_NAPI 1 /* NAPI owns this CQ */ @@ -329,7 +329,7 @@ struct mlx4_en_cq { #define CQ_YIELD (MLX4_EN_CQ_STATE_NAPI_YIELD | MLX4_EN_CQ_STATE_POLL_YIELD) #define CQ_USER_PEND (MLX4_EN_CQ_STATE_POLL | MLX4_EN_CQ_STATE_POLL_YIELD) spinlock_t poll_lock; /* protects from LLS/napi conflicts */ -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ }; struct mlx4_en_port_profile { @@ -580,7 +580,7 @@ struct mlx4_mac_entry { struct rcu_head rcu; }; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL static inline void mlx4_en_cq_init_lock(struct mlx4_en_cq *cq) { spin_lock_init(&cq->poll_lock); @@ -687,7 +687,7 @@ static inline bool mlx4_en_cq_ll_polling(struct mlx4_en_cq *cq) { return false; } -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ #define MLX4_EN_WOL_DO_MODIFY (1ULL << 63) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 0741a1e919a5..9a4156845e93 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -973,7 +973,7 @@ struct net_device_ops { gfp_t gfp); void (*ndo_netpoll_cleanup)(struct net_device *dev); #endif -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL int (*ndo_busy_poll)(struct napi_struct *dev); #endif int (*ndo_set_vf_mac)(struct net_device *dev, diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 5afefa01a13c..3b71a4e83642 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -501,7 +501,7 @@ struct sk_buff { /* 7/9 bit hole (depending on ndisc_nodetype presence) */ kmemcheck_bitfield_end(flags2); -#if defined CONFIG_NET_DMA || defined CONFIG_NET_LL_RX_POLL +#if defined CONFIG_NET_DMA || defined CONFIG_NET_RX_BUSY_POLL union { unsigned int napi_id; dma_cookie_t dma_cookie; diff --git a/include/net/busy_poll.h b/include/net/busy_poll.h index 6cd8848fec68..f18b91966d3d 100644 --- a/include/net/busy_poll.h +++ b/include/net/busy_poll.h @@ -27,7 +27,7 @@ #include #include -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL struct napi_struct; extern unsigned int sysctl_net_busy_read __read_mostly; @@ -146,7 +146,7 @@ static inline void sk_mark_napi_id(struct sock *sk, struct sk_buff *skb) sk->sk_napi_id = skb->napi_id; } -#else /* CONFIG_NET_LL_RX_POLL */ +#else /* CONFIG_NET_RX_BUSY_POLL */ static inline unsigned long net_busy_loop_on(void) { return 0; @@ -186,5 +186,5 @@ static inline bool sk_busy_loop(struct sock *sk, int nonblock) return false; } -#endif /* CONFIG_NET_LL_RX_POLL */ +#endif /* CONFIG_NET_RX_BUSY_POLL */ #endif /* _LINUX_NET_BUSY_POLL_H */ diff --git a/include/net/sock.h b/include/net/sock.h index 95a5a2c6925a..31d5cfbb51ec 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -327,7 +327,7 @@ struct sock { #ifdef CONFIG_RPS __u32 sk_rxhash; #endif -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sk_napi_id; unsigned int sk_ll_usec; #endif diff --git a/net/Kconfig b/net/Kconfig index 37702491abe9..2b406608a1a4 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -244,7 +244,7 @@ config NETPRIO_CGROUP Cgroup subsystem for use in assigning processes to network priorities on a per-interface basis -config NET_LL_RX_POLL +config NET_RX_BUSY_POLL boolean default y diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 3df4d4ccf440..2c3d0f53d198 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -740,7 +740,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_copy_secmark(new, old); -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL new->napi_id = old->napi_id; #endif } diff --git a/net/core/sock.c b/net/core/sock.c index 548d716c5f62..2c097c5a35dd 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -900,7 +900,7 @@ set_rcvbuf: sock_valbool_flag(sk, SOCK_SELECT_ERR_QUEUE, valbool); break; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: /* allow unprivileged users to decrease the value */ if ((val > sk->sk_ll_usec) && !capable(CAP_NET_ADMIN)) @@ -1170,7 +1170,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, v.val = sock_flag(sk, SOCK_SELECT_ERR_QUEUE); break; -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL case SO_BUSY_POLL: v.val = sk->sk_ll_usec; break; @@ -2292,7 +2292,7 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL sk->sk_napi_id = 0; sk->sk_ll_usec = sysctl_net_busy_read; #endif diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index 660968616637..b59b6804fd98 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -298,7 +298,7 @@ static struct ctl_table net_core_table[] = { .proc_handler = flow_limit_table_len_sysctl }, #endif /* CONFIG_NET_FLOW_LIMIT */ -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL { .procname = "busy_poll", .data = &sysctl_net_busy_poll, diff --git a/net/socket.c b/net/socket.c index 829b460acb87..b2d7c629eeb9 100644 --- a/net/socket.c +++ b/net/socket.c @@ -106,7 +106,7 @@ #include #include -#ifdef CONFIG_NET_LL_RX_POLL +#ifdef CONFIG_NET_RX_BUSY_POLL unsigned int sysctl_net_busy_read __read_mostly; unsigned int sysctl_net_busy_poll __read_mostly; #endif -- cgit v1.2.3 From 5f671d6b4ec3e6d66c2a868738af2cdea09e7509 Mon Sep 17 00:00:00 2001 From: Roman Gushchin Date: Fri, 2 Aug 2013 18:36:40 +0400 Subject: net: check net.core.somaxconn sysctl values It's possible to assign an invalid value to the net.core.somaxconn sysctl variable, because there is no checks at all. The sk_max_ack_backlog field of the sock structure is defined as unsigned short. Therefore, the backlog argument in inet_listen() shouldn't exceed USHRT_MAX. The backlog argument in the listen() syscall is truncated to the somaxconn value. So, the somaxconn value shouldn't exceed 65535 (USHRT_MAX). Also, negative values of somaxconn are meaningless. before: $ sysctl -w net.core.somaxconn=256 net.core.somaxconn = 256 $ sysctl -w net.core.somaxconn=65536 net.core.somaxconn = 65536 $ sysctl -w net.core.somaxconn=-100 net.core.somaxconn = -100 after: $ sysctl -w net.core.somaxconn=256 net.core.somaxconn = 256 $ sysctl -w net.core.somaxconn=65536 error: "Invalid argument" setting key "net.core.somaxconn" $ sysctl -w net.core.somaxconn=-100 error: "Invalid argument" setting key "net.core.somaxconn" Based on a prior patch from Changli Gao. Signed-off-by: Roman Gushchin Reported-by: Changli Gao Suggested-by: Eric Dumazet Acked-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/sysctl_net_core.c | 6 +++++- 1 file changed, 5 insertions(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/sysctl_net_core.c b/net/core/sysctl_net_core.c index b59b6804fd98..31107abd2783 100644 --- a/net/core/sysctl_net_core.c +++ b/net/core/sysctl_net_core.c @@ -21,7 +21,9 @@ #include #include +static int zero = 0; static int one = 1; +static int ushort_max = USHRT_MAX; #ifdef CONFIG_RPS static int rps_sock_flow_sysctl(struct ctl_table *table, int write, @@ -339,7 +341,9 @@ static struct ctl_table netns_core_table[] = { .data = &init_net.core.sysctl_somaxconn, .maxlen = sizeof(int), .mode = 0644, - .proc_handler = proc_dointvec + .extra1 = &zero, + .extra2 = &ushort_max, + .proc_handler = proc_dointvec_minmax }, { } }; -- cgit v1.2.3 From fc7f8f5c53fdb82d4689e24df3da1a88bc3859f7 Mon Sep 17 00:00:00 2001 From: Veaceslav Falico Date: Fri, 2 Aug 2013 19:07:38 +0200 Subject: neighbour: populate neigh_parms on alloc before calling ndo_neigh_setup dev->ndo_neigh_setup() might need some of the values of neigh_parms, so populate them before calling it. Signed-off-by: Veaceslav Falico Signed-off-by: David S. Miller --- net/core/neighbour.c | 10 ++++++---- 1 file changed, 6 insertions(+), 4 deletions(-) (limited to 'net/core') diff --git a/net/core/neighbour.c b/net/core/neighbour.c index 9232c68941ab..60533db8b72d 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -1441,16 +1441,18 @@ struct neigh_parms *neigh_parms_alloc(struct net_device *dev, atomic_set(&p->refcnt, 1); p->reachable_time = neigh_rand_reach_time(p->base_reachable_time); + dev_hold(dev); + p->dev = dev; + write_pnet(&p->net, hold_net(net)); + p->sysctl_table = NULL; if (ops->ndo_neigh_setup && ops->ndo_neigh_setup(dev, p)) { + release_net(net); + dev_put(dev); kfree(p); return NULL; } - dev_hold(dev); - p->dev = dev; - write_pnet(&p->net, hold_net(net)); - p->sysctl_table = NULL; write_lock_bh(&tbl->lock); p->next = tbl->parms.next; tbl->parms.next = p; -- cgit v1.2.3 From e11aada32b39a060e26fa4091cb968bd42e3bcbf Mon Sep 17 00:00:00 2001 From: Eric Dumazet Date: Tue, 6 Aug 2013 04:35:06 -0700 Subject: net: flow_dissector: add 802.1ad support Same behavior than 802.1q : finds the encapsulated protocol and skip 32bit header. Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/flow_dissector.c | 1 + 1 file changed, 1 insertion(+) (limited to 'net/core') diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index 00ee068efc1c..b84a1b155bc1 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -65,6 +65,7 @@ ipv6: nhoff += sizeof(struct ipv6hdr); break; } + case __constant_htons(ETH_P_8021AD): case __constant_htons(ETH_P_8021Q): { const struct vlan_hdr *vlan; struct vlan_hdr _vlan; -- cgit v1.2.3 From 645359930231d5e78fd3296a38b98c1a658a7ade Mon Sep 17 00:00:00 2001 From: Sridhar Samudrala Date: Thu, 8 Aug 2013 15:19:48 -0700 Subject: rtnetlink: Fix inverted check in ndo_dflt_fdb_del() Fix inverted check when deleting an fdb entry. Signed-off-by: Sridhar Samudrala Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 3de740834d1f..82d968527121 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2156,7 +2156,7 @@ int ndo_dflt_fdb_del(struct ndmsg *ndm, /* If aging addresses are supported device will need to * implement its own handler for this. */ - if (ndm->ndm_state & NUD_PERMANENT) { + if (!(ndm->ndm_state & NUD_PERMANENT)) { pr_info("%s: FDB only supports static addresses\n", dev->name); return -EINVAL; } -- cgit v1.2.3 From 3e805ad288c524bb65aad3f1e004402223d3d504 Mon Sep 17 00:00:00 2001 From: Asbjoern Sloth Toennesen Date: Mon, 12 Aug 2013 16:30:09 +0000 Subject: rtnetlink: rtnl_bridge_getlink: Call nlmsg_find_attr() with ifinfomsg header Fix the iproute2 command `bridge vlan show`, after switching from rtgenmsg to ifinfomsg. Let's start with a little history: Feb 20: Vlad Yasevich got his VLAN-aware bridge patchset included in the 3.9 merge window. In the kernel commit 6cbdceeb, he added attribute support to bridge GETLINK requests sent with rtgenmsg. Mar 6th: Vlad got this iproute2 reference implementation of the bridge vlan netlink interface accepted (iproute2 9eff0e5c) Apr 25th: iproute2 switched from using rtgenmsg to ifinfomsg (63338dca) http://patchwork.ozlabs.org/patch/239602/ http://marc.info/?t=136680900700007 Apr 28th: Linus released 3.9 Apr 30th: Stephen released iproute2 3.9.0 The `bridge vlan show` command haven't been working since the switch to ifinfomsg, or in a released version of iproute2. Since the kernel side only supports rtgenmsg, which iproute2 switched away from just prior to the iproute2 3.9.0 release. I haven't been able to find any documentation, about neither rtgenmsg nor ifinfomsg, and in which situation to use which, but kernel commit 88c5b5ce seams to suggest that ifinfomsg should be used. Fixing this in kernel will break compatibility, but I doubt that anybody have been using it due to this bug in the user space reference implementation, at least not without noticing this bug. That said the functionality is still fully functional in 3.9, when reversing iproute2 commit 63338dca. This could also be fixed in iproute2, but thats an ugly patch that would reintroduce rtgenmsg in iproute2, and from searching in netdev it seams like rtgenmsg usage is discouraged. I'm assuming that the only reason that Vlad implemented the kernel side to use rtgenmsg, was because iproute2 was using it at the time. Signed-off-by: Asbjoern Sloth Toennesen Reviewed-by: Vlad Yasevich Signed-off-by: David S. Miller --- net/core/rtnetlink.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) (limited to 'net/core') diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 82d968527121..ca198c1d1d30 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -2384,7 +2384,7 @@ static int rtnl_bridge_getlink(struct sk_buff *skb, struct netlink_callback *cb) struct nlattr *extfilt; u32 filter_mask = 0; - extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct rtgenmsg), + extfilt = nlmsg_find_attr(cb->nlh, sizeof(struct ifinfomsg), IFLA_EXT_MASK); if (extfilt) filter_mask = nla_get_u32(extfilt); -- cgit v1.2.3