diff options
author | Patrick McHardy <kaber@trash.net> | 2009-06-11 16:00:49 +0200 |
---|---|---|
committer | Patrick McHardy <kaber@trash.net> | 2009-06-11 16:00:49 +0200 |
commit | 36432dae73cf2c90a59b39c8df9fd8219272b005 (patch) | |
tree | 660b9104305a809ec4fdeb295ca13d6e90790ecc /net/core | |
parent | 440f0d588555892601cfe511728a0fc0c8204063 (diff) | |
parent | bb400801c2f40bbd9a688818323ad09abfc4e581 (diff) | |
download | op-kernel-dev-36432dae73cf2c90a59b39c8df9fd8219272b005.zip op-kernel-dev-36432dae73cf2c90a59b39c8df9fd8219272b005.tar.gz |
Merge branch 'master' of git://git.kernel.org/pub/scm/linux/kernel/git/davem/net-next-2.6
Diffstat (limited to 'net/core')
-rw-r--r-- | net/core/datagram.c | 181 | ||||
-rw-r--r-- | net/core/dev.c | 230 | ||||
-rw-r--r-- | net/core/iovec.c | 4 | ||||
-rw-r--r-- | net/core/neighbour.c | 57 | ||||
-rw-r--r-- | net/core/pktgen.c | 6 | ||||
-rw-r--r-- | net/core/skb_dma_map.c | 13 | ||||
-rw-r--r-- | net/core/skbuff.c | 241 | ||||
-rw-r--r-- | net/core/sock.c | 135 | ||||
-rw-r--r-- | net/core/user_dma.c | 46 |
9 files changed, 491 insertions, 422 deletions
diff --git a/net/core/datagram.c b/net/core/datagram.c index e2a36f0..58abee1 100644 --- a/net/core/datagram.c +++ b/net/core/datagram.c @@ -282,6 +282,7 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; /* Copy header. */ if (copy > 0) { @@ -322,28 +323,24 @@ int skb_copy_datagram_iovec(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_datagram_iovec(list, - offset - start, - to, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_iovec(frag_iter, + offset - start, + to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; } + start = end; } if (!len) return 0; @@ -369,6 +366,7 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; /* Copy header. */ if (copy > 0) { @@ -411,30 +409,26 @@ int skb_copy_datagram_const_iovec(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_datagram_const_iovec(list, - offset - start, - to, to_offset, - copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - to_offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_const_iovec(frag_iter, + offset - start, + to, to_offset, + copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to_offset += copy; } + start = end; } if (!len) return 0; @@ -461,12 +455,14 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; /* Copy header. */ if (copy > 0) { if (copy > len) copy = len; - if (memcpy_fromiovecend(skb->data + offset, from, 0, copy)) + if (memcpy_fromiovecend(skb->data + offset, from, from_offset, + copy)) goto fault; if ((len -= copy) == 0) return 0; @@ -505,31 +501,27 @@ int skb_copy_datagram_from_iovec(struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_datagram_from_iovec(list, - offset - start, - from, - from_offset, - copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - from_offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_datagram_from_iovec(frag_iter, + offset - start, + from, + from_offset, + copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + from_offset += copy; } + start = end; } if (!len) return 0; @@ -544,8 +536,9 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, __wsum *csump) { int start = skb_headlen(skb); - int pos = 0; int i, copy = start - offset; + struct sk_buff *frag_iter; + int pos = 0; /* Copy header. */ if (copy > 0) { @@ -596,33 +589,29 @@ static int skb_copy_and_csum_datagram(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list=list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - __wsum csum2 = 0; - if (copy > len) - copy = len; - if (skb_copy_and_csum_datagram(list, - offset - start, - to, copy, - &csum2)) - goto fault; - *csump = csum_block_add(*csump, csum2, pos); - if ((len -= copy) == 0) - return 0; - offset += copy; - to += copy; - pos += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + __wsum csum2 = 0; + if (copy > len) + copy = len; + if (skb_copy_and_csum_datagram(frag_iter, + offset - start, + to, copy, + &csum2)) + goto fault; + *csump = csum_block_add(*csump, csum2, pos); + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; + pos += copy; } + start = end; } if (!len) return 0; diff --git a/net/core/dev.c b/net/core/dev.c index ed4550f..11560e3 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -269,7 +269,8 @@ static const unsigned short netdev_lock_type[] = ARPHRD_IRDA, ARPHRD_FCPP, ARPHRD_FCAL, ARPHRD_FCPL, ARPHRD_FCFABRIC, ARPHRD_IEEE802_TR, ARPHRD_IEEE80211, ARPHRD_IEEE80211_PRISM, ARPHRD_IEEE80211_RADIOTAP, ARPHRD_PHONET, - ARPHRD_PHONET_PIPE, ARPHRD_VOID, ARPHRD_NONE}; + ARPHRD_PHONET_PIPE, ARPHRD_IEEE802154, ARPHRD_IEEE802154_PHY, + ARPHRD_VOID, ARPHRD_NONE}; static const char *netdev_lock_name[] = {"_xmit_NETROM", "_xmit_ETHER", "_xmit_EETHER", "_xmit_AX25", @@ -286,7 +287,8 @@ static const char *netdev_lock_name[] = "_xmit_IRDA", "_xmit_FCPP", "_xmit_FCAL", "_xmit_FCPL", "_xmit_FCFABRIC", "_xmit_IEEE802_TR", "_xmit_IEEE80211", "_xmit_IEEE80211_PRISM", "_xmit_IEEE80211_RADIOTAP", "_xmit_PHONET", - "_xmit_PHONET_PIPE", "_xmit_VOID", "_xmit_NONE"}; + "_xmit_PHONET_PIPE", "_xmit_IEEE802154", "_xmit_IEEE802154_PHY", + "_xmit_VOID", "_xmit_NONE"}; static struct lock_class_key netdev_xmit_lock_key[ARRAY_SIZE(netdev_lock_type)]; static struct lock_class_key netdev_addr_lock_key[ARRAY_SIZE(netdev_lock_type)]; @@ -1048,7 +1050,7 @@ void dev_load(struct net *net, const char *name) int dev_open(struct net_device *dev) { const struct net_device_ops *ops = dev->netdev_ops; - int ret = 0; + int ret; ASSERT_RTNL(); @@ -1065,6 +1067,11 @@ int dev_open(struct net_device *dev) if (!netif_device_present(dev)) return -ENODEV; + ret = call_netdevice_notifiers(NETDEV_PRE_UP, dev); + ret = notifier_to_errno(ret); + if (ret) + return ret; + /* * Call device private open method */ @@ -1693,10 +1700,9 @@ int dev_hard_start_xmit(struct sk_buff *skb, struct net_device *dev, * If device doesnt need skb->dst, release it right now while * its hot in this cpu cache */ - if ((dev->priv_flags & IFF_XMIT_DST_RELEASE) && skb->dst) { - dst_release(skb->dst); - skb->dst = NULL; - } + if (dev->priv_flags & IFF_XMIT_DST_RELEASE) + skb_dst_drop(skb); + rc = ops->ndo_start_xmit(skb, dev); if (rc == 0) txq_trans_update(txq); @@ -1816,7 +1822,7 @@ int dev_queue_xmit(struct sk_buff *skb) if (netif_needs_gso(dev, skb)) goto gso; - if (skb_shinfo(skb)->frag_list && + if (skb_has_frags(skb) && !(dev->features & NETIF_F_FRAGLIST) && __skb_linearize(skb)) goto out_kfree_skb; @@ -2403,7 +2409,7 @@ int dev_gro_receive(struct napi_struct *napi, struct sk_buff *skb) if (!(skb->dev->features & NETIF_F_GRO)) goto normal; - if (skb_is_gso(skb) || skb_shinfo(skb)->frag_list) + if (skb_is_gso(skb) || skb_has_frags(skb)) goto normal; rcu_read_lock(); @@ -3473,8 +3479,9 @@ void dev_set_rx_mode(struct net_device *dev) /* hw addresses list handling functions */ -static int __hw_addr_add(struct list_head *list, unsigned char *addr, - int addr_len, unsigned char addr_type) +static int __hw_addr_add(struct list_head *list, int *delta, + unsigned char *addr, int addr_len, + unsigned char addr_type) { struct netdev_hw_addr *ha; int alloc_size; @@ -3482,6 +3489,15 @@ static int __hw_addr_add(struct list_head *list, unsigned char *addr, if (addr_len > MAX_ADDR_LEN) return -EINVAL; + list_for_each_entry(ha, list, list) { + if (!memcmp(ha->addr, addr, addr_len) && + ha->type == addr_type) { + ha->refcount++; + return 0; + } + } + + alloc_size = sizeof(*ha); if (alloc_size < L1_CACHE_BYTES) alloc_size = L1_CACHE_BYTES; @@ -3490,7 +3506,11 @@ static int __hw_addr_add(struct list_head *list, unsigned char *addr, return -ENOMEM; memcpy(ha->addr, addr, addr_len); ha->type = addr_type; + ha->refcount = 1; + ha->synced = false; list_add_tail_rcu(&ha->list, list); + if (delta) + (*delta)++; return 0; } @@ -3502,29 +3522,30 @@ static void ha_rcu_free(struct rcu_head *head) kfree(ha); } -static int __hw_addr_del_ii(struct list_head *list, unsigned char *addr, - int addr_len, unsigned char addr_type, - int ignore_index) +static int __hw_addr_del(struct list_head *list, int *delta, + unsigned char *addr, int addr_len, + unsigned char addr_type) { struct netdev_hw_addr *ha; - int i = 0; list_for_each_entry(ha, list, list) { - if (i++ != ignore_index && - !memcmp(ha->addr, addr, addr_len) && + if (!memcmp(ha->addr, addr, addr_len) && (ha->type == addr_type || !addr_type)) { + if (--ha->refcount) + return 0; list_del_rcu(&ha->list); call_rcu(&ha->rcu_head, ha_rcu_free); + if (delta) + (*delta)--; return 0; } } return -ENOENT; } -static int __hw_addr_add_multiple_ii(struct list_head *to_list, - struct list_head *from_list, - int addr_len, unsigned char addr_type, - int ignore_index) +static int __hw_addr_add_multiple(struct list_head *to_list, int *to_delta, + struct list_head *from_list, int addr_len, + unsigned char addr_type) { int err; struct netdev_hw_addr *ha, *ha2; @@ -3532,7 +3553,8 @@ static int __hw_addr_add_multiple_ii(struct list_head *to_list, list_for_each_entry(ha, from_list, list) { type = addr_type ? addr_type : ha->type; - err = __hw_addr_add(to_list, ha->addr, addr_len, type); + err = __hw_addr_add(to_list, to_delta, ha->addr, + addr_len, type); if (err) goto unroll; } @@ -3543,27 +3565,69 @@ unroll: if (ha2 == ha) break; type = addr_type ? addr_type : ha2->type; - __hw_addr_del_ii(to_list, ha2->addr, addr_len, type, - ignore_index); + __hw_addr_del(to_list, to_delta, ha2->addr, + addr_len, type); } return err; } -static void __hw_addr_del_multiple_ii(struct list_head *to_list, - struct list_head *from_list, - int addr_len, unsigned char addr_type, - int ignore_index) +static void __hw_addr_del_multiple(struct list_head *to_list, int *to_delta, + struct list_head *from_list, int addr_len, + unsigned char addr_type) { struct netdev_hw_addr *ha; unsigned char type; list_for_each_entry(ha, from_list, list) { type = addr_type ? addr_type : ha->type; - __hw_addr_del_ii(to_list, ha->addr, addr_len, addr_type, - ignore_index); + __hw_addr_del(to_list, to_delta, ha->addr, + addr_len, addr_type); + } +} + +static int __hw_addr_sync(struct list_head *to_list, int *to_delta, + struct list_head *from_list, int *from_delta, + int addr_len) +{ + int err = 0; + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, from_list, list) { + if (!ha->synced) { + err = __hw_addr_add(to_list, to_delta, ha->addr, + addr_len, ha->type); + if (err) + break; + ha->synced = true; + ha->refcount++; + } else if (ha->refcount == 1) { + __hw_addr_del(to_list, to_delta, ha->addr, + addr_len, ha->type); + __hw_addr_del(from_list, from_delta, ha->addr, + addr_len, ha->type); + } + } + return err; +} + +static void __hw_addr_unsync(struct list_head *to_list, int *to_delta, + struct list_head *from_list, int *from_delta, + int addr_len) +{ + struct netdev_hw_addr *ha, *tmp; + + list_for_each_entry_safe(ha, tmp, from_list, list) { + if (ha->synced) { + __hw_addr_del(to_list, to_delta, ha->addr, + addr_len, ha->type); + ha->synced = false; + __hw_addr_del(from_list, from_delta, ha->addr, + addr_len, ha->type); + } } } + static void __hw_addr_flush(struct list_head *list) { struct netdev_hw_addr *ha, *tmp; @@ -3593,8 +3657,8 @@ static int dev_addr_init(struct net_device *dev) /* rtnl_mutex must be held here */ INIT_LIST_HEAD(&dev->dev_addr_list); - memset(addr, 0, sizeof(*addr)); - err = __hw_addr_add(&dev->dev_addr_list, addr, sizeof(*addr), + memset(addr, 0, sizeof(addr)); + err = __hw_addr_add(&dev->dev_addr_list, NULL, addr, sizeof(addr), NETDEV_HW_ADDR_T_LAN); if (!err) { /* @@ -3626,7 +3690,7 @@ int dev_addr_add(struct net_device *dev, unsigned char *addr, ASSERT_RTNL(); - err = __hw_addr_add(&dev->dev_addr_list, addr, dev->addr_len, + err = __hw_addr_add(&dev->dev_addr_list, NULL, addr, dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); @@ -3649,11 +3713,20 @@ int dev_addr_del(struct net_device *dev, unsigned char *addr, unsigned char addr_type) { int err; + struct netdev_hw_addr *ha; ASSERT_RTNL(); - err = __hw_addr_del_ii(&dev->dev_addr_list, addr, dev->addr_len, - addr_type, 0); + /* + * We can not remove the first address from the list because + * dev->dev_addr points to that. + */ + ha = list_first_entry(&dev->dev_addr_list, struct netdev_hw_addr, list); + if (ha->addr == dev->dev_addr && ha->refcount == 1) + return -ENOENT; + + err = __hw_addr_del(&dev->dev_addr_list, NULL, addr, dev->addr_len, + addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, dev); return err; @@ -3680,9 +3753,9 @@ int dev_addr_add_multiple(struct net_device *to_dev, if (from_dev->addr_len != to_dev->addr_len) return -EINVAL; - err = __hw_addr_add_multiple_ii(&to_dev->dev_addr_list, - &from_dev->dev_addr_list, - to_dev->addr_len, addr_type, 0); + err = __hw_addr_add_multiple(&to_dev->dev_addr_list, NULL, + &from_dev->dev_addr_list, + to_dev->addr_len, addr_type); if (!err) call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); return err; @@ -3707,9 +3780,9 @@ int dev_addr_del_multiple(struct net_device *to_dev, if (from_dev->addr_len != to_dev->addr_len) return -EINVAL; - __hw_addr_del_multiple_ii(&to_dev->dev_addr_list, - &from_dev->dev_addr_list, - to_dev->addr_len, addr_type, 0); + __hw_addr_del_multiple(&to_dev->dev_addr_list, NULL, + &from_dev->dev_addr_list, + to_dev->addr_len, addr_type); call_netdevice_notifiers(NETDEV_CHANGEADDR, to_dev); return 0; } @@ -3779,24 +3852,22 @@ int __dev_addr_add(struct dev_addr_list **list, int *count, * dev_unicast_delete - Release secondary unicast address. * @dev: device * @addr: address to delete - * @alen: length of @addr * * Release reference to a secondary unicast address and remove it * from the device if the reference count drops to zero. * * The caller must hold the rtnl_mutex. */ -int dev_unicast_delete(struct net_device *dev, void *addr, int alen) +int dev_unicast_delete(struct net_device *dev, void *addr) { int err; ASSERT_RTNL(); - netif_addr_lock_bh(dev); - err = __dev_addr_delete(&dev->uc_list, &dev->uc_count, addr, alen, 0); + err = __hw_addr_del(&dev->uc_list, &dev->uc_count, addr, + dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); - netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_delete); @@ -3805,24 +3876,22 @@ EXPORT_SYMBOL(dev_unicast_delete); * dev_unicast_add - add a secondary unicast address * @dev: device * @addr: address to add - * @alen: length of @addr * * Add a secondary unicast address to the device or increase * the reference count if it already exists. * * The caller must hold the rtnl_mutex. */ -int dev_unicast_add(struct net_device *dev, void *addr, int alen) +int dev_unicast_add(struct net_device *dev, void *addr) { int err; ASSERT_RTNL(); - netif_addr_lock_bh(dev); - err = __dev_addr_add(&dev->uc_list, &dev->uc_count, addr, alen, 0); + err = __hw_addr_add(&dev->uc_list, &dev->uc_count, addr, + dev->addr_len, NETDEV_HW_ADDR_T_UNICAST); if (!err) __dev_set_rx_mode(dev); - netif_addr_unlock_bh(dev); return err; } EXPORT_SYMBOL(dev_unicast_add); @@ -3879,8 +3948,7 @@ void __dev_addr_unsync(struct dev_addr_list **to, int *to_count, * @from: source device * * Add newly added addresses to the destination device and release - * addresses that have no users left. The source device must be - * locked by netif_tx_lock_bh. + * addresses that have no users left. * * This function is intended to be called from the dev->set_rx_mode * function of layered software devices. @@ -3889,12 +3957,15 @@ int dev_unicast_sync(struct net_device *to, struct net_device *from) { int err = 0; - netif_addr_lock_bh(to); - err = __dev_addr_sync(&to->uc_list, &to->uc_count, - &from->uc_list, &from->uc_count); + ASSERT_RTNL(); + + if (to->addr_len != from->addr_len) + return -EINVAL; + + err = __hw_addr_sync(&to->uc_list, &to->uc_count, + &from->uc_list, &from->uc_count, to->addr_len); if (!err) __dev_set_rx_mode(to); - netif_addr_unlock_bh(to); return err; } EXPORT_SYMBOL(dev_unicast_sync); @@ -3910,18 +3981,33 @@ EXPORT_SYMBOL(dev_unicast_sync); */ void dev_unicast_unsync(struct net_device *to, struct net_device *from) { - netif_addr_lock_bh(from); - netif_addr_lock(to); + ASSERT_RTNL(); - __dev_addr_unsync(&to->uc_list, &to->uc_count, - &from->uc_list, &from->uc_count); - __dev_set_rx_mode(to); + if (to->addr_len != from->addr_len) + return; - netif_addr_unlock(to); - netif_addr_unlock_bh(from); + __hw_addr_unsync(&to->uc_list, &to->uc_count, + &from->uc_list, &from->uc_count, to->addr_len); + __dev_set_rx_mode(to); } EXPORT_SYMBOL(dev_unicast_unsync); +static void dev_unicast_flush(struct net_device *dev) +{ + /* rtnl_mutex must be held here */ + + __hw_addr_flush(&dev->uc_list); + dev->uc_count = 0; +} + +static void dev_unicast_init(struct net_device *dev) +{ + /* rtnl_mutex must be held here */ + + INIT_LIST_HEAD(&dev->uc_list); +} + + static void __dev_addr_discard(struct dev_addr_list **list) { struct dev_addr_list *tmp; @@ -3940,9 +4026,6 @@ static void dev_addr_discard(struct net_device *dev) { netif_addr_lock_bh(dev); - __dev_addr_discard(&dev->uc_list); - dev->uc_count = 0; - __dev_addr_discard(&dev->mc_list); dev->mc_count = 0; @@ -4535,6 +4618,7 @@ static void rollback_registered(struct net_device *dev) /* * Flush the unicast and multicast chains */ + dev_unicast_flush(dev); dev_addr_discard(dev); if (dev->netdev_ops->ndo_uninit) @@ -4988,18 +5072,18 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, struct netdev_queue *tx; struct net_device *dev; size_t alloc_size; - void *p; + struct net_device *p; BUG_ON(strlen(name) >= sizeof(dev->name)); alloc_size = sizeof(struct net_device); if (sizeof_priv) { /* ensure 32-byte alignment of private area */ - alloc_size = (alloc_size + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST; + alloc_size = ALIGN(alloc_size, NETDEV_ALIGN); alloc_size += sizeof_priv; } /* ensure 32-byte alignment of whole construct */ - alloc_size += NETDEV_ALIGN_CONST; + alloc_size += NETDEV_ALIGN - 1; p = kzalloc(alloc_size, GFP_KERNEL); if (!p) { @@ -5014,13 +5098,14 @@ struct net_device *alloc_netdev_mq(int sizeof_priv, const char *name, goto free_p; } - dev = (struct net_device *) - (((long)p + NETDEV_ALIGN_CONST) & ~NETDEV_ALIGN_CONST); + dev = PTR_ALIGN(p, NETDEV_ALIGN); dev->padded = (char *)dev - (char *)p; if (dev_addr_init(dev)) goto free_tx; + dev_unicast_init(dev); + dev_net_set(dev, &init_net); dev->_tx = tx; @@ -5224,6 +5309,7 @@ int dev_change_net_namespace(struct net_device *dev, struct net *net, const char /* * Flush the unicast and multicast chains */ + dev_unicast_flush(dev); dev_addr_discard(dev); netdev_unregister_kobject(dev); diff --git a/net/core/iovec.c b/net/core/iovec.c index 40a76ce..16ad45d 100644 --- a/net/core/iovec.c +++ b/net/core/iovec.c @@ -112,9 +112,9 @@ int memcpy_toiovecend(const struct iovec *iov, unsigned char *kdata, continue; } copy = min_t(unsigned int, iov->iov_len - offset, len); - offset = 0; - if (copy_to_user(iov->iov_base, kdata, copy)) + if (copy_to_user(iov->iov_base + offset, kdata, copy)) return -EFAULT; + offset = 0; kdata += copy; len -= copy; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index a1cbce7..163b4f5 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -771,6 +771,28 @@ static __inline__ int neigh_max_probes(struct neighbour *n) p->ucast_probes + p->app_probes + p->mcast_probes); } +static void neigh_invalidate(struct neighbour *neigh) +{ + struct sk_buff *skb; + + NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); + NEIGH_PRINTK2("neigh %p is failed.\n", neigh); + neigh->updated = jiffies; + + /* It is very thin place. report_unreachable is very complicated + routine. Particularly, it can hit the same neighbour entry! + + So that, we try to be accurate and avoid dead loop. --ANK + */ + while (neigh->nud_state == NUD_FAILED && + (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { + write_unlock(&neigh->lock); + neigh->ops->error_report(neigh, skb); + write_lock(&neigh->lock); + } + skb_queue_purge(&neigh->arp_queue); +} + /* Called when a timer expires for a neighbour entry. */ static void neigh_timer_handler(unsigned long arg) @@ -835,26 +857,9 @@ static void neigh_timer_handler(unsigned long arg) if ((neigh->nud_state & (NUD_INCOMPLETE | NUD_PROBE)) && atomic_read(&neigh->probes) >= neigh_max_probes(neigh)) { - struct sk_buff *skb; - neigh->nud_state = NUD_FAILED; - neigh->updated = jiffies; notify = 1; - NEIGH_CACHE_STAT_INC(neigh->tbl, res_failed); - NEIGH_PRINTK2("neigh %p is failed.\n", neigh); - - /* It is very thin place. report_unreachable is very complicated - routine. Particularly, it can hit the same neighbour entry! - - So that, we try to be accurate and avoid dead loop. --ANK - */ - while (neigh->nud_state == NUD_FAILED && - (skb = __skb_dequeue(&neigh->arp_queue)) != NULL) { - write_unlock(&neigh->lock); - neigh->ops->error_report(neigh, skb); - write_lock(&neigh->lock); - } - skb_queue_purge(&neigh->arp_queue); + neigh_invalidate(neigh); } if (neigh->nud_state & NUD_IN_TIMER) { @@ -1001,6 +1006,11 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, neigh->nud_state = new; err = 0; notify = old & NUD_VALID; + if ((old & (NUD_INCOMPLETE | NUD_PROBE)) && + (new & NUD_FAILED)) { + neigh_invalidate(neigh); + notify = 1; + } goto out; } @@ -1088,8 +1098,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, struct neighbour *n1 = neigh; write_unlock_bh(&neigh->lock); /* On shaper/eql skb->dst->neighbour != neigh :( */ - if (skb->dst && skb->dst->neighbour) - n1 = skb->dst->neighbour; + if (skb_dst(skb) && skb_dst(skb)->neighbour) + n1 = skb_dst(skb)->neighbour; n1->output(skb); write_lock_bh(&neigh->lock); } @@ -1182,7 +1192,7 @@ EXPORT_SYMBOL(neigh_compat_output); int neigh_resolve_output(struct sk_buff *skb) { - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh; int rc = 0; @@ -1229,7 +1239,7 @@ EXPORT_SYMBOL(neigh_resolve_output); int neigh_connected_output(struct sk_buff *skb) { int err; - struct dst_entry *dst = skb->dst; + struct dst_entry *dst = skb_dst(skb); struct neighbour *neigh = dst->neighbour; struct net_device *dev = neigh->dev; @@ -1298,8 +1308,7 @@ void pneigh_enqueue(struct neigh_table *tbl, struct neigh_parms *p, if (time_before(tbl->proxy_timer.expires, sched_next)) sched_next = tbl->proxy_timer.expires; } - dst_release(skb->dst); - skb->dst = NULL; + skb_dst_drop(skb); dev_hold(skb->dev); __skb_queue_tail(&tbl->proxy_queue, skb); mod_timer(&tbl->proxy_timer, sched_next); diff --git a/net/core/pktgen.c b/net/core/pktgen.c index b8ccd3c..19b8c20 100644 --- a/net/core/pktgen.c +++ b/net/core/pktgen.c @@ -3691,8 +3691,7 @@ out1: #ifdef CONFIG_XFRM free_SAs(pkt_dev); #endif - if (pkt_dev->flows) - vfree(pkt_dev->flows); + vfree(pkt_dev->flows); kfree(pkt_dev); return err; } @@ -3791,8 +3790,7 @@ static int pktgen_remove_device(struct pktgen_thread *t, #ifdef CONFIG_XFRM free_SAs(pkt_dev); #endif - if (pkt_dev->flows) - vfree(pkt_dev->flows); + vfree(pkt_dev->flows); kfree(pkt_dev); return 0; } diff --git a/net/core/skb_dma_map.c b/net/core/skb_dma_map.c index 8623492..79687df 100644 --- a/net/core/skb_dma_map.c +++ b/net/core/skb_dma_map.c @@ -20,7 +20,7 @@ int skb_dma_map(struct device *dev, struct sk_buff *skb, if (dma_mapping_error(dev, map)) goto out_err; - sp->dma_maps[0] = map; + sp->dma_head = map; for (i = 0; i < sp->nr_frags; i++) { skb_frag_t *fp = &sp->frags[i]; @@ -28,9 +28,8 @@ int skb_dma_map(struct device *dev, struct sk_buff *skb, fp->size, dir); if (dma_mapping_error(dev, map)) goto unwind; - sp->dma_maps[i + 1] = map; + sp->dma_maps[i] = map; } - sp->num_dma_maps = i + 1; return 0; @@ -38,10 +37,10 @@ unwind: while (--i >= 0) { skb_frag_t *fp = &sp->frags[i]; - dma_unmap_page(dev, sp->dma_maps[i + 1], + dma_unmap_page(dev, sp->dma_maps[i], fp->size, dir); } - dma_unmap_single(dev, sp->dma_maps[0], + dma_unmap_single(dev, sp->dma_head, skb_headlen(skb), dir); out_err: return -ENOMEM; @@ -54,12 +53,12 @@ void skb_dma_unmap(struct device *dev, struct sk_buff *skb, struct skb_shared_info *sp = skb_shinfo(skb); int i; - dma_unmap_single(dev, sp->dma_maps[0], + dma_unmap_single(dev, sp->dma_head, skb_headlen(skb), dir); for (i = 0; i < sp->nr_frags; i++) { skb_frag_t *fp = &sp->frags[i]; - dma_unmap_page(dev, sp->dma_maps[i + 1], + dma_unmap_page(dev, sp->dma_maps[i], fp->size, dir); } } diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 8e815e6..b94d777 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -210,7 +210,7 @@ struct sk_buff *__alloc_skb(unsigned int size, gfp_t gfp_mask, shinfo->gso_type = 0; shinfo->ip6_frag_id = 0; shinfo->tx_flags.flags = 0; - shinfo->frag_list = NULL; + skb_frag_list_init(skb); memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps)); if (fclone) { @@ -323,7 +323,7 @@ static void skb_clone_fraglist(struct sk_buff *skb) { struct sk_buff *list; - for (list = skb_shinfo(skb)->frag_list; list; list = list->next) + skb_walk_frags(skb, list) skb_get(list); } @@ -338,7 +338,7 @@ static void skb_release_data(struct sk_buff *skb) put_page(skb_shinfo(skb)->frags[i].page); } - if (skb_shinfo(skb)->frag_list) + if (skb_has_frags(skb)) skb_drop_fraglist(skb); kfree(skb->head); @@ -381,7 +381,7 @@ static void kfree_skbmem(struct sk_buff *skb) static void skb_release_head_state(struct sk_buff *skb) { - dst_release(skb->dst); + skb_dst_drop(skb); #ifdef CONFIG_XFRM secpath_put(skb->sp); #endif @@ -503,7 +503,7 @@ int skb_recycle_check(struct sk_buff *skb, int skb_size) shinfo->gso_type = 0; shinfo->ip6_frag_id = 0; shinfo->tx_flags.flags = 0; - shinfo->frag_list = NULL; + skb_frag_list_init(skb); memset(&shinfo->hwtstamps, 0, sizeof(shinfo->hwtstamps)); memset(skb, 0, offsetof(struct sk_buff, tail)); @@ -521,7 +521,7 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->transport_header = old->transport_header; new->network_header = old->network_header; new->mac_header = old->mac_header; - new->dst = dst_clone(old->dst); + skb_dst_set(new, dst_clone(skb_dst(old))); #ifdef CONFIG_XFRM new->sp = secpath_get(old->sp); #endif @@ -552,7 +552,6 @@ static void __copy_skb_header(struct sk_buff *new, const struct sk_buff *old) new->vlan_tci = old->vlan_tci; #if defined(CONFIG_MAC80211) || defined(CONFIG_MAC80211_MODULE) new->do_not_encrypt = old->do_not_encrypt; - new->requeue = old->requeue; #endif skb_copy_secmark(new, old); @@ -758,7 +757,7 @@ struct sk_buff *pskb_copy(struct sk_buff *skb, gfp_t gfp_mask) skb_shinfo(n)->nr_frags = i; } - if (skb_shinfo(skb)->frag_list) { + if (skb_has_frags(skb)) { skb_shinfo(n)->frag_list = skb_shinfo(skb)->frag_list; skb_clone_fraglist(n); } @@ -821,7 +820,7 @@ int pskb_expand_head(struct sk_buff *skb, int nhead, int ntail, for (i = 0; i < skb_shinfo(skb)->nr_frags; i++) get_page(skb_shinfo(skb)->frags[i].page); - if (skb_shinfo(skb)->frag_list) + if (skb_has_frags(skb)) skb_clone_fraglist(skb); skb_release_data(skb); @@ -1093,7 +1092,7 @@ drop_pages: for (; i < nfrags; i++) put_page(skb_shinfo(skb)->frags[i].page); - if (skb_shinfo(skb)->frag_list) + if (skb_has_frags(skb)) skb_drop_fraglist(skb); goto done; } @@ -1188,7 +1187,7 @@ unsigned char *__pskb_pull_tail(struct sk_buff *skb, int delta) /* Optimization: no fragments, no reasons to preestimate * size of pulled pages. Superb. */ - if (!skb_shinfo(skb)->frag_list) + if (!skb_has_frags(skb)) goto pull_pages; /* Estimate size of pulled pages. */ @@ -1285,8 +1284,9 @@ EXPORT_SYMBOL(__pskb_pull_tail); int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) { - int i, copy; int start = skb_headlen(skb); + struct sk_buff *frag_iter; + int i, copy; if (offset > (int)skb->len - len) goto fault; @@ -1328,28 +1328,23 @@ int skb_copy_bits(const struct sk_buff *skb, int offset, void *to, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_copy_bits(list, offset - start, - to, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - to += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_copy_bits(frag_iter, offset - start, to, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + to += copy; } + start = end; } if (!len) return 0; @@ -1534,6 +1529,7 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, .ops = &sock_pipe_buf_ops, .spd_release = sock_spd_release, }; + struct sk_buff *frag_iter; struct sock *sk = skb->sk; /* @@ -1548,13 +1544,11 @@ int skb_splice_bits(struct sk_buff *skb, unsigned int offset, /* * now see if we have a frag_list to map */ - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list && tlen; list = list->next) { - if (__skb_splice_bits(list, &offset, &tlen, &spd, sk)) - break; - } + skb_walk_frags(skb, frag_iter) { + if (!tlen) + break; + if (__skb_splice_bits(frag_iter, &offset, &tlen, &spd, sk)) + break; } done: @@ -1593,8 +1587,9 @@ done: int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) { - int i, copy; int start = skb_headlen(skb); + struct sk_buff *frag_iter; + int i, copy; if (offset > (int)skb->len - len) goto fault; @@ -1635,28 +1630,24 @@ int skb_store_bits(struct sk_buff *skb, int offset, const void *from, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - if (skb_store_bits(list, offset - start, - from, copy)) - goto fault; - if ((len -= copy) == 0) - return 0; - offset += copy; - from += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + if (skb_store_bits(frag_iter, offset - start, + from, copy)) + goto fault; + if ((len -= copy) == 0) + return 0; + offset += copy; + from += copy; } + start = end; } if (!len) return 0; @@ -1673,6 +1664,7 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int pos = 0; /* Checksum header. */ @@ -1712,29 +1704,25 @@ __wsum skb_checksum(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + int end; - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - __wsum csum2; - if (copy > len) - copy = len; - csum2 = skb_checksum(list, offset - start, - copy, 0); - csum = csum_block_add(csum, csum2, pos); - if ((len -= copy) == 0) - return csum; - offset += copy; - pos += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + __wsum csum2; + if (copy > len) + copy = len; + csum2 = skb_checksum(frag_iter, offset - start, + copy, 0); + csum = csum_block_add(csum, csum2, pos); + if ((len -= copy) == 0) + return csum; + offset += copy; + pos += copy; } + start = end; } BUG_ON(len); @@ -1749,6 +1737,7 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int pos = 0; /* Copy header. */ @@ -1793,31 +1782,27 @@ __wsum skb_copy_and_csum_bits(const struct sk_buff *skb, int offset, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; + skb_walk_frags(skb, frag_iter) { + __wsum csum2; + int end; - for (; list; list = list->next) { - __wsum csum2; - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - csum2 = skb_copy_and_csum_bits(list, - offset - start, - to, copy, 0); - csum = csum_block_add(csum, csum2, pos); - if ((len -= copy) == 0) - return csum; - offset += copy; - to += copy; - pos += copy; - } - start = end; + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + csum2 = skb_copy_and_csum_bits(frag_iter, + offset - start, + to, copy, 0); + csum = csum_block_add(csum, csum2, pos); + if ((len -= copy) == 0) + return csum; + offset += copy; + to += copy; + pos += copy; } + start = end; } BUG_ON(len); return csum; @@ -2327,8 +2312,7 @@ next_skb: st->frag_data = NULL; } - if (st->root_skb == st->cur_skb && - skb_shinfo(st->root_skb)->frag_list) { + if (st->root_skb == st->cur_skb && skb_has_frags(st->root_skb)) { st->cur_skb = skb_shinfo(st->root_skb)->frag_list; st->frag_idx = 0; goto next_skb; @@ -2639,7 +2623,7 @@ struct sk_buff *skb_segment(struct sk_buff *skb, int features) } else skb_get(fskb2); - BUG_ON(skb_shinfo(nskb)->frag_list); + SKB_FRAG_ASSERT(nskb); skb_shinfo(nskb)->frag_list = fskb2; } @@ -2796,6 +2780,7 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; int elt = 0; if (copy > 0) { @@ -2829,26 +2814,22 @@ __skb_to_sgvec(struct sk_buff *skb, struct scatterlist *sg, int offset, int len) start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; + skb_walk_frags(skb, frag_iter) { + int end; - WARN_ON(start > offset + len); + WARN_ON(start > offset + len); - end = start + list->len; - if ((copy = end - offset) > 0) { - if (copy > len) - copy = len; - elt += __skb_to_sgvec(list, sg+elt, offset - start, - copy); - if ((len -= copy) == 0) - return elt; - offset += copy; - } - start = end; + end = start + frag_iter->len; + if ((copy = end - offset) > 0) { + if (copy > len) + copy = len; + elt += __skb_to_sgvec(frag_iter, sg+elt, offset - start, + copy); + if ((len -= copy) == 0) + return elt; + offset += copy; } + start = end; } BUG_ON(len); return elt; @@ -2896,7 +2877,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) return -ENOMEM; /* Easy case. Most of packets will go this way. */ - if (!skb_shinfo(skb)->frag_list) { + if (!skb_has_frags(skb)) { /* A little of trouble, not enough of space for trailer. * This should not happen, when stack is tuned to generate * good frames. OK, on miss we reallocate and reserve even more @@ -2931,7 +2912,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) if (skb1->next == NULL && tailbits) { if (skb_shinfo(skb1)->nr_frags || - skb_shinfo(skb1)->frag_list || + skb_has_frags(skb1) || skb_tailroom(skb1) < tailbits) ntail = tailbits + 128; } @@ -2940,7 +2921,7 @@ int skb_cow_data(struct sk_buff *skb, int tailbits, struct sk_buff **trailer) skb_cloned(skb1) || ntail || skb_shinfo(skb1)->nr_frags || - skb_shinfo(skb1)->frag_list) { + skb_has_frags(skb1)) { struct sk_buff *skb2; /* Fuck, we are miserable poor guys... */ @@ -3026,12 +3007,12 @@ EXPORT_SYMBOL_GPL(skb_tstamp_tx); */ bool skb_partial_csum_set(struct sk_buff *skb, u16 start, u16 off) { - if (unlikely(start > skb->len - 2) || - unlikely((int)start + off > skb->len - 2)) { + if (unlikely(start > skb_headlen(skb)) || + unlikely((int)start + off > skb_headlen(skb) - 2)) { if (net_ratelimit()) printk(KERN_WARNING "bad partial csum: csum=%u/%u len=%u\n", - start, off, skb->len); + start, off, skb_headlen(skb)); return false; } skb->ip_summed = CHECKSUM_PARTIAL; diff --git a/net/core/sock.c b/net/core/sock.c index 7dbf3ff..06e26b7 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -155,6 +155,7 @@ static const char *af_family_key_strings[AF_MAX+1] = { "sk_lock-27" , "sk_lock-28" , "sk_lock-AF_CAN" , "sk_lock-AF_TIPC" , "sk_lock-AF_BLUETOOTH", "sk_lock-IUCV" , "sk_lock-AF_RXRPC" , "sk_lock-AF_ISDN" , "sk_lock-AF_PHONET" , + "sk_lock-AF_IEEE802154", "sk_lock-AF_MAX" }; static const char *af_family_slock_key_strings[AF_MAX+1] = { @@ -170,6 +171,7 @@ static const char *af_family_slock_key_strings[AF_MAX+1] = { "slock-27" , "slock-28" , "slock-AF_CAN" , "slock-AF_TIPC" , "slock-AF_BLUETOOTH", "slock-AF_IUCV" , "slock-AF_RXRPC" , "slock-AF_ISDN" , "slock-AF_PHONET" , + "slock-AF_IEEE802154", "slock-AF_MAX" }; static const char *af_family_clock_key_strings[AF_MAX+1] = { @@ -185,6 +187,7 @@ static const char *af_family_clock_key_strings[AF_MAX+1] = { "clock-27" , "clock-28" , "clock-AF_CAN" , "clock-AF_TIPC" , "clock-AF_BLUETOOTH", "clock-AF_IUCV" , "clock-AF_RXRPC" , "clock-AF_ISDN" , "clock-AF_PHONET" , + "clock-AF_IEEE802154", "clock-AF_MAX" }; @@ -212,6 +215,7 @@ __u32 sysctl_rmem_default __read_mostly = SK_RMEM_MAX; /* Maximal space eaten by iovec or ancilliary data plus some space */ int sysctl_optmem_max __read_mostly = sizeof(unsigned long)*(2*UIO_MAXIOV+512); +EXPORT_SYMBOL(sysctl_optmem_max); static int sock_set_timeout(long *timeo_p, char __user *optval, int optlen) { @@ -444,7 +448,7 @@ static inline void sock_valbool_flag(struct sock *sk, int bit, int valbool) int sock_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) { - struct sock *sk=sock->sk; + struct sock *sk = sock->sk; int val; int valbool; struct linger ling; @@ -463,15 +467,15 @@ int sock_setsockopt(struct socket *sock, int level, int optname, if (get_user(val, (int __user *)optval)) return -EFAULT; - valbool = val?1:0; + valbool = val ? 1 : 0; lock_sock(sk); - switch(optname) { + switch (optname) { case SO_DEBUG: - if (val && !capable(CAP_NET_ADMIN)) { + if (val && !capable(CAP_NET_ADMIN)) ret = -EACCES; - } else + else sock_valbool_flag(sk, SOCK_DBG, valbool); break; case SO_REUSEADDR: @@ -582,7 +586,7 @@ set_rcvbuf: ret = -EINVAL; /* 1003.1g */ break; } - if (copy_from_user(&ling,optval,sizeof(ling))) { + if (copy_from_user(&ling, optval, sizeof(ling))) { ret = -EFAULT; break; } @@ -690,9 +694,8 @@ set_rcvbuf: case SO_MARK: if (!capable(CAP_NET_ADMIN)) ret = -EPERM; - else { + else sk->sk_mark = val; - } break; /* We implement the SO_SNDLOWAT etc to @@ -704,6 +707,7 @@ set_rcvbuf: release_sock(sk); return ret; } +EXPORT_SYMBOL(sock_setsockopt); int sock_getsockopt(struct socket *sock, int level, int optname, @@ -727,7 +731,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, memset(&v, 0, sizeof(v)); - switch(optname) { + switch (optname) { case SO_DEBUG: v.val = sock_flag(sk, SOCK_DBG); break; @@ -762,7 +766,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, case SO_ERROR: v.val = -sock_error(sk); - if (v.val==0) + if (v.val == 0) v.val = xchg(&sk->sk_err_soft, 0); break; @@ -816,7 +820,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_RCVTIMEO: - lv=sizeof(struct timeval); + lv = sizeof(struct timeval); if (sk->sk_rcvtimeo == MAX_SCHEDULE_TIMEOUT) { v.tm.tv_sec = 0; v.tm.tv_usec = 0; @@ -827,7 +831,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_SNDTIMEO: - lv=sizeof(struct timeval); + lv = sizeof(struct timeval); if (sk->sk_sndtimeo == MAX_SCHEDULE_TIMEOUT) { v.tm.tv_sec = 0; v.tm.tv_usec = 0; @@ -842,7 +846,7 @@ int sock_getsockopt(struct socket *sock, int level, int optname, break; case SO_SNDLOWAT: - v.val=1; + v.val = 1; break; case SO_PASSCRED: @@ -1002,8 +1006,9 @@ struct sock *sk_alloc(struct net *net, int family, gfp_t priority, return sk; } +EXPORT_SYMBOL(sk_alloc); -void sk_free(struct sock *sk) +static void __sk_free(struct sock *sk) { struct sk_filter *filter; @@ -1027,6 +1032,18 @@ void sk_free(struct sock *sk) sk_prot_free(sk->sk_prot_creator, sk); } +void sk_free(struct sock *sk) +{ + /* + * We substract one from sk_wmem_alloc and can know if + * some packets are still in some tx queue. + * If not null, sock_wfree() will call __sk_free(sk) later + */ + if (atomic_dec_and_test(&sk->sk_wmem_alloc)) + __sk_free(sk); +} +EXPORT_SYMBOL(sk_free); + /* * Last sock_put should drop referrence to sk->sk_net. It has already * been dropped in sk_change_net. Taking referrence to stopping namespace @@ -1065,7 +1082,10 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) newsk->sk_backlog.head = newsk->sk_backlog.tail = NULL; atomic_set(&newsk->sk_rmem_alloc, 0); - atomic_set(&newsk->sk_wmem_alloc, 0); + /* + * sk_wmem_alloc set to one (see sk_free() and sock_wfree()) + */ + atomic_set(&newsk->sk_wmem_alloc, 1); atomic_set(&newsk->sk_omem_alloc, 0); skb_queue_head_init(&newsk->sk_receive_queue); skb_queue_head_init(&newsk->sk_write_queue); @@ -1126,7 +1146,6 @@ struct sock *sk_clone(const struct sock *sk, const gfp_t priority) out: return newsk; } - EXPORT_SYMBOL_GPL(sk_clone); void sk_setup_caps(struct sock *sk, struct dst_entry *dst) @@ -1170,13 +1189,20 @@ void __init sk_init(void) void sock_wfree(struct sk_buff *skb) { struct sock *sk = skb->sk; + int res; /* In case it might be waiting for more memory. */ - atomic_sub(skb->truesize, &sk->sk_wmem_alloc); + res = atomic_sub_return(skb->truesize, &sk->sk_wmem_alloc); if (!sock_flag(sk, SOCK_USE_WRITE_QUEUE)) sk->sk_write_space(sk); - sock_put(sk); + /* + * if sk_wmem_alloc reached 0, we are last user and should + * free this sock, as sk_free() call could not do it. + */ + if (res == 0) + __sk_free(sk); } +EXPORT_SYMBOL(sock_wfree); /* * Read buffer destructor automatically called from kfree_skb. @@ -1188,6 +1214,7 @@ void sock_rfree(struct sk_buff *skb) atomic_sub(skb->truesize, &sk->sk_rmem_alloc); sk_mem_uncharge(skb->sk, skb->truesize); } +EXPORT_SYMBOL(sock_rfree); int sock_i_uid(struct sock *sk) @@ -1199,6 +1226,7 @@ int sock_i_uid(struct sock *sk) read_unlock(&sk->sk_callback_lock); return uid; } +EXPORT_SYMBOL(sock_i_uid); unsigned long sock_i_ino(struct sock *sk) { @@ -1209,6 +1237,7 @@ unsigned long sock_i_ino(struct sock *sk) read_unlock(&sk->sk_callback_lock); return ino; } +EXPORT_SYMBOL(sock_i_ino); /* * Allocate a skb from the socket's send buffer. @@ -1217,7 +1246,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, gfp_t priority) { if (force || atomic_read(&sk->sk_wmem_alloc) < sk->sk_sndbuf) { - struct sk_buff * skb = alloc_skb(size, priority); + struct sk_buff *skb = alloc_skb(size, priority); if (skb) { skb_set_owner_w(skb, sk); return skb; @@ -1225,6 +1254,7 @@ struct sk_buff *sock_wmalloc(struct sock *sk, unsigned long size, int force, } return NULL; } +EXPORT_SYMBOL(sock_wmalloc); /* * Allocate a skb from the socket's receive buffer. @@ -1261,6 +1291,7 @@ void *sock_kmalloc(struct sock *sk, int size, gfp_t priority) } return NULL; } +EXPORT_SYMBOL(sock_kmalloc); /* * Free an option memory block. @@ -1270,11 +1301,12 @@ void sock_kfree_s(struct sock *sk, void *mem, int size) kfree(mem); atomic_sub(size, &sk->sk_omem_alloc); } +EXPORT_SYMBOL(sock_kfree_s); /* It is almost wait_for_tcp_memory minus release_sock/lock_sock. I think, these locks should be removed for datagram sockets. */ -static long sock_wait_for_wmem(struct sock * sk, long timeo) +static long sock_wait_for_wmem(struct sock *sk, long timeo) { DEFINE_WAIT(wait); @@ -1392,6 +1424,7 @@ struct sk_buff *sock_alloc_send_skb(struct sock *sk, unsigned long size, { return sock_alloc_send_pskb(sk, size, 0, noblock, errcode); } +EXPORT_SYMBOL(sock_alloc_send_skb); static void __lock_sock(struct sock *sk) { @@ -1460,7 +1493,6 @@ int sk_wait_data(struct sock *sk, long *timeo) finish_wait(sk->sk_sleep, &wait); return rc; } - EXPORT_SYMBOL(sk_wait_data); /** @@ -1541,7 +1573,6 @@ suppress_allocation: atomic_sub(amt, prot->memory_allocated); return 0; } - EXPORT_SYMBOL(__sk_mem_schedule); /** @@ -1560,7 +1591,6 @@ void __sk_mem_reclaim(struct sock *sk) (atomic_read(prot->memory_allocated) < prot->sysctl_mem[0])) *prot->memory_pressure = 0; } - EXPORT_SYMBOL(__sk_mem_reclaim); @@ -1575,78 +1605,92 @@ int sock_no_bind(struct socket *sock, struct sockaddr *saddr, int len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_bind); int sock_no_connect(struct socket *sock, struct sockaddr *saddr, int len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_connect); int sock_no_socketpair(struct socket *sock1, struct socket *sock2) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_socketpair); int sock_no_accept(struct socket *sock, struct socket *newsock, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_accept); int sock_no_getname(struct socket *sock, struct sockaddr *saddr, int *len, int peer) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getname); -unsigned int sock_no_poll(struct file * file, struct socket *sock, poll_table *pt) +unsigned int sock_no_poll(struct file *file, struct socket *sock, poll_table *pt) { return 0; } +EXPORT_SYMBOL(sock_no_poll); int sock_no_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_ioctl); int sock_no_listen(struct socket *sock, int backlog) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_listen); int sock_no_shutdown(struct socket *sock, int how) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_shutdown); int sock_no_setsockopt(struct socket *sock, int level, int optname, char __user *optval, int optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_setsockopt); int sock_no_getsockopt(struct socket *sock, int level, int optname, char __user *optval, int __user *optlen) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_getsockopt); int sock_no_sendmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_sendmsg); int sock_no_recvmsg(struct kiocb *iocb, struct socket *sock, struct msghdr *m, size_t len, int flags) { return -EOPNOTSUPP; } +EXPORT_SYMBOL(sock_no_recvmsg); int sock_no_mmap(struct file *file, struct socket *sock, struct vm_area_struct *vma) { /* Mirror missing mmap method error code */ return -ENODEV; } +EXPORT_SYMBOL(sock_no_mmap); ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, size_t size, int flags) { @@ -1660,6 +1704,7 @@ ssize_t sock_no_sendpage(struct socket *sock, struct page *page, int offset, siz kunmap(page); return res; } +EXPORT_SYMBOL(sock_no_sendpage); /* * Default Socket Callbacks @@ -1723,6 +1768,7 @@ void sk_send_sigurg(struct sock *sk) if (send_sigurg(&sk->sk_socket->file->f_owner)) sk_wake_async(sk, SOCK_WAKE_URG, POLL_PRI); } +EXPORT_SYMBOL(sk_send_sigurg); void sk_reset_timer(struct sock *sk, struct timer_list* timer, unsigned long expires) @@ -1730,7 +1776,6 @@ void sk_reset_timer(struct sock *sk, struct timer_list* timer, if (!mod_timer(timer, expires)) sock_hold(sk); } - EXPORT_SYMBOL(sk_reset_timer); void sk_stop_timer(struct sock *sk, struct timer_list* timer) @@ -1738,7 +1783,6 @@ void sk_stop_timer(struct sock *sk, struct timer_list* timer) if (timer_pending(timer) && del_timer(timer)) __sock_put(sk); } - EXPORT_SYMBOL(sk_stop_timer); void sock_init_data(struct socket *sock, struct sock *sk) @@ -1795,8 +1839,10 @@ void sock_init_data(struct socket *sock, struct sock *sk) sk->sk_stamp = ktime_set(-1L, 0); atomic_set(&sk->sk_refcnt, 1); + atomic_set(&sk->sk_wmem_alloc, 1); atomic_set(&sk->sk_drops, 0); } +EXPORT_SYMBOL(sock_init_data); void lock_sock_nested(struct sock *sk, int subclass) { @@ -1812,7 +1858,6 @@ void lock_sock_nested(struct sock *sk, int subclass) mutex_acquire(&sk->sk_lock.dep_map, subclass, 0, _RET_IP_); local_bh_enable(); } - EXPORT_SYMBOL(lock_sock_nested); void release_sock(struct sock *sk) @@ -1895,7 +1940,6 @@ int sock_common_getsockopt(struct socket *sock, int level, int optname, return sk->sk_prot->getsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(sock_common_getsockopt); #ifdef CONFIG_COMPAT @@ -1925,7 +1969,6 @@ int sock_common_recvmsg(struct kiocb *iocb, struct socket *sock, msg->msg_namelen = addr_len; return err; } - EXPORT_SYMBOL(sock_common_recvmsg); /* @@ -1938,7 +1981,6 @@ int sock_common_setsockopt(struct socket *sock, int level, int optname, return sk->sk_prot->setsockopt(sk, level, optname, optval, optlen); } - EXPORT_SYMBOL(sock_common_setsockopt); #ifdef CONFIG_COMPAT @@ -1989,7 +2031,6 @@ void sk_common_release(struct sock *sk) sk_refcnt_debug_release(sk); sock_put(sk); } - EXPORT_SYMBOL(sk_common_release); static DEFINE_RWLOCK(proto_list_lock); @@ -2171,7 +2212,6 @@ out_free_sock_slab: out: return -ENOBUFS; } - EXPORT_SYMBOL(proto_register); void proto_unregister(struct proto *prot) @@ -2198,7 +2238,6 @@ void proto_unregister(struct proto *prot) prot->twsk_prot->twsk_slab = NULL; } } - EXPORT_SYMBOL(proto_unregister); #ifdef CONFIG_PROC_FS @@ -2324,33 +2363,3 @@ static int __init proto_init(void) subsys_initcall(proto_init); #endif /* PROC_FS */ - -EXPORT_SYMBOL(sk_alloc); -EXPORT_SYMBOL(sk_free); -EXPORT_SYMBOL(sk_send_sigurg); -EXPORT_SYMBOL(sock_alloc_send_skb); -EXPORT_SYMBOL(sock_init_data); -EXPORT_SYMBOL(sock_kfree_s); -EXPORT_SYMBOL(sock_kmalloc); -EXPORT_SYMBOL(sock_no_accept); -EXPORT_SYMBOL(sock_no_bind); -EXPORT_SYMBOL(sock_no_connect); -EXPORT_SYMBOL(sock_no_getname); -EXPORT_SYMBOL(sock_no_getsockopt); -EXPORT_SYMBOL(sock_no_ioctl); -EXPORT_SYMBOL(sock_no_listen); -EXPORT_SYMBOL(sock_no_mmap); -EXPORT_SYMBOL(sock_no_poll); -EXPORT_SYMBOL(sock_no_recvmsg); -EXPORT_SYMBOL(sock_no_sendmsg); -EXPORT_SYMBOL(sock_no_sendpage); -EXPORT_SYMBOL(sock_no_setsockopt); -EXPORT_SYMBOL(sock_no_shutdown); -EXPORT_SYMBOL(sock_no_socketpair); -EXPORT_SYMBOL(sock_rfree); -EXPORT_SYMBOL(sock_setsockopt); -EXPORT_SYMBOL(sock_wfree); -EXPORT_SYMBOL(sock_wmalloc); -EXPORT_SYMBOL(sock_i_uid); -EXPORT_SYMBOL(sock_i_ino); -EXPORT_SYMBOL(sysctl_optmem_max); diff --git a/net/core/user_dma.c b/net/core/user_dma.c index 164b090..25d717e 100644 --- a/net/core/user_dma.c +++ b/net/core/user_dma.c @@ -51,6 +51,7 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, { int start = skb_headlen(skb); int i, copy = start - offset; + struct sk_buff *frag_iter; dma_cookie_t cookie = 0; /* Copy header. */ @@ -94,31 +95,28 @@ int dma_skb_copy_datagram_iovec(struct dma_chan *chan, start = end; } - if (skb_shinfo(skb)->frag_list) { - struct sk_buff *list = skb_shinfo(skb)->frag_list; - - for (; list; list = list->next) { - int end; - - WARN_ON(start > offset + len); - - end = start + list->len; - copy = end - offset; - if (copy > 0) { - if (copy > len) - copy = len; - cookie = dma_skb_copy_datagram_iovec(chan, list, - offset - start, to, copy, - pinned_list); - if (cookie < 0) - goto fault; - len -= copy; - if (len == 0) - goto end; - offset += copy; - } - start = end; + skb_walk_frags(skb, frag_iter) { + int end; + + WARN_ON(start > offset + len); + + end = start + frag_iter->len; + copy = end - offset; + if (copy > 0) { + if (copy > len) + copy = len; + cookie = dma_skb_copy_datagram_iovec(chan, frag_iter, + offset - start, + to, copy, + pinned_list); + if (cookie < 0) + goto fault; + len -= copy; + if (len == 0) + goto end; + offset += copy; } + start = end; } end: |