From 3019de124b9f5b1526cb3668b74af14371e21795 Mon Sep 17 00:00:00 2001 From: "David S. Miller" Date: Mon, 6 Jun 2011 16:41:33 -0700 Subject: net: Rework netdev_drivername() to avoid warning. This interface uses a temporary buffer, but for no real reason. And now can generate warnings like: net/sched/sch_generic.c: In function dev_watchdog net/sched/sch_generic.c:254:10: warning: unused variable drivername Just return driver->name directly or "". Reported-by: Connor Hansen Signed-off-by: David S. Miller --- net/core/dev.c | 16 +++++----------- 1 file changed, 5 insertions(+), 11 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 939307891e7..1af6cb27f67 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6264,29 +6264,23 @@ err_name: /** * netdev_drivername - network driver for the device * @dev: network device - * @buffer: buffer for resulting name - * @len: size of buffer * * Determine network driver for device. */ -char *netdev_drivername(const struct net_device *dev, char *buffer, int len) +const char *netdev_drivername(const struct net_device *dev) { const struct device_driver *driver; const struct device *parent; - - if (len <= 0 || !buffer) - return buffer; - buffer[0] = 0; + const char *empty = ""; parent = dev->dev.parent; - if (!parent) - return buffer; + return empty; driver = parent->driver; if (driver && driver->name) - strlcpy(buffer, driver->name, len); - return buffer; + return driver->name; + return empty; } static int __netdev_printk(const char *level, const struct net_device *dev, -- cgit v1.2.3-70-g09d2 From 264524d5e5195f6e0f099bee20253a22b651e272 Mon Sep 17 00:00:00 2001 From: Heiko Carstens Date: Mon, 6 Jun 2011 20:50:03 +0000 Subject: net: cpu offline cause napi stall Frank Blaschka reported : During heavy network load we turn off/on cpus. Sometimes this causes a stall on the network device. Digging into the dump I found out following: napi is scheduled but does not run. From the I/O buffers and the napi state I see napi/rx_softirq processing has stopped because the budget was reached. napi stays in the softnet_data poll_list and the rx_softirq was raised again. I assume at this time the cpu offline comes in, the rx softirq is raised/moved to another cpu but napi stays in the poll_list of the softnet_data of the now offline cpu. Reviewing dev_cpu_callback (net/core/dev.c) I did not find the poll_list is transfered to the new cpu. This patch is a straightforward implementation of Frank suggestion : Transfert poll_list and trigger NET_RX_SOFTIRQ on new cpu. Reported-by: Frank Blaschka Signed-off-by: Heiko Carstens Signed-off-by: Eric Dumazet Tested-by: Eric Dumazet Signed-off-by: David S. Miller --- net/core/dev.c | 5 +++++ 1 file changed, 5 insertions(+) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 1af6cb27f67..a54c9f87ddb 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -6178,6 +6178,11 @@ static int dev_cpu_callback(struct notifier_block *nfb, oldsd->output_queue = NULL; oldsd->output_queue_tailp = &oldsd->output_queue; } + /* Append NAPI poll list from offline CPU. */ + if (!list_empty(&oldsd->poll_list)) { + list_splice_init(&oldsd->poll_list, &sd->poll_list); + raise_softirq_irqoff(NET_RX_SOFTIRQ); + } raise_softirq_irqoff(NET_TX_SOFTIRQ); local_irq_enable(); -- cgit v1.2.3-70-g09d2 From bff55273f98dea0ceb78e28eb69462fe5f72ef3d Mon Sep 17 00:00:00 2001 From: Alexander Duyck Date: Wed, 8 Jun 2011 12:35:08 +0000 Subject: v2 ethtool: remove support for ETHTOOL_GRXNTUPLE This change is meant to remove all support for displaying an ntuple as strings via ETHTOOL_GRXNTUPLE. The reason for this change is due to the fact that multiple issues have been found including: - Multiple buffer overruns for strings being displayed. - Incorrect filters displayed, cleared filters with ring of -2 are displayed - Setting get_rx_ntuple displays no rules if defined. - Endianess wrong on displayed values. - Hard limit of 1024 filters makes display functionality extremely limited The only driver that had supported this interface was ixgbe. Since it no longer uses the interface and due to the issues mentioned above I am submitting this patch to remove it. v2: Updated based on comments from Ben Hutchings - Left ETH_SS_NTUPLE_FILTERS in code but commented on it being deprecated - Removed ethtool_rx_ntuple_list and ethtool_rx_ntuple_flow_spec_container - Left ETHTOOL_GRXNTUPLE but commented it as deprecated Also cleaned up set_rx_ntuple since there is no flow spec container to maintain we can drop all the code for the alloc and free of it and just return ops->set_rx_ntuple(). Signed-off-by: Alexander Duyck Acked-by: Ben Hutchings Signed-off-by: David S. Miller --- include/linux/ethtool.h | 19 +-- include/linux/netdevice.h | 3 - net/core/dev.c | 5 - net/core/ethtool.c | 309 +--------------------------------------------- 4 files changed, 3 insertions(+), 333 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index c6a850ab2ec..dfd34934213 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -287,7 +287,7 @@ enum ethtool_stringset { ETH_SS_TEST = 0, ETH_SS_STATS, ETH_SS_PRIV_FLAGS, - ETH_SS_NTUPLE_FILTERS, + ETH_SS_NTUPLE_FILTERS, /* Do not use, GRXNTUPLE is now deprecated */ ETH_SS_FEATURES, }; @@ -714,18 +714,6 @@ enum ethtool_sfeatures_retval_bits { /* needed by dev_disable_lro() */ extern int __ethtool_set_flags(struct net_device *dev, u32 flags); -struct ethtool_rx_ntuple_flow_spec_container { - struct ethtool_rx_ntuple_flow_spec fs; - struct list_head list; -}; - -struct ethtool_rx_ntuple_list { -#define ETHTOOL_MAX_NTUPLE_LIST_ENTRY 1024 -#define ETHTOOL_MAX_NTUPLE_STRING_PER_ENTRY 14 - struct list_head list; - unsigned int count; -}; - /** * enum ethtool_phys_id_state - indicator state for physical identification * @ETHTOOL_ID_INACTIVE: Physical ID indicator should be deactivated @@ -758,7 +746,6 @@ u32 ethtool_op_get_ufo(struct net_device *dev); int ethtool_op_set_ufo(struct net_device *dev, u32 data); u32 ethtool_op_get_flags(struct net_device *dev); int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported); -void ethtool_ntuple_flush(struct net_device *dev); bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported); /** @@ -865,7 +852,6 @@ bool ethtool_invalid_flags(struct net_device *dev, u32 data, u32 supported); * error code or zero. * @set_rx_ntuple: Set an RX n-tuple rule. Returns a negative error code * or zero. - * @get_rx_ntuple: Deprecated. * @get_rxfh_indir: Get the contents of the RX flow hash indirection table. * Returns a negative error code or zero. * @set_rxfh_indir: Set the contents of the RX flow hash indirection table. @@ -944,7 +930,6 @@ struct ethtool_ops { int (*reset)(struct net_device *, u32 *); int (*set_rx_ntuple)(struct net_device *, struct ethtool_rx_ntuple *); - int (*get_rx_ntuple)(struct net_device *, u32 stringset, void *); int (*get_rxfh_indir)(struct net_device *, struct ethtool_rxfh_indir *); int (*set_rxfh_indir)(struct net_device *, @@ -1017,7 +1002,7 @@ struct ethtool_ops { #define ETHTOOL_FLASHDEV 0x00000033 /* Flash firmware to device */ #define ETHTOOL_RESET 0x00000034 /* Reset hardware */ #define ETHTOOL_SRXNTUPLE 0x00000035 /* Add an n-tuple filter to device */ -#define ETHTOOL_GRXNTUPLE 0x00000036 /* Get n-tuple filters from device */ +#define ETHTOOL_GRXNTUPLE 0x00000036 /* deprecated */ #define ETHTOOL_GSSET_INFO 0x00000037 /* Get string set info */ #define ETHTOOL_GRXFHINDIR 0x00000038 /* Get RX flow hash indir'n table */ #define ETHTOOL_SRXFHINDIR 0x00000039 /* Set RX flow hash indir'n table */ diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 336288567c7..6469fa942d1 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1348,9 +1348,6 @@ struct net_device { /* max exchange id for FCoE LRO by ddp */ unsigned int fcoe_ddp_xid; #endif - /* n-tuple filter list attached to this device */ - struct ethtool_rx_ntuple_list ethtool_ntuple_list; - /* phy device may attach itself for hardware timestamping */ struct phy_device *phydev; diff --git a/net/core/dev.c b/net/core/dev.c index 939307891e7..b3f52d2f56d 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5867,8 +5867,6 @@ struct net_device *alloc_netdev_mqs(int sizeof_priv, const char *name, dev->gso_max_size = GSO_MAX_SIZE; - INIT_LIST_HEAD(&dev->ethtool_ntuple_list.list); - dev->ethtool_ntuple_list.count = 0; INIT_LIST_HEAD(&dev->napi_list); INIT_LIST_HEAD(&dev->unreg_list); INIT_LIST_HEAD(&dev->link_watch_list); @@ -5932,9 +5930,6 @@ void free_netdev(struct net_device *dev) /* Flush device addresses */ dev_addr_flush(dev); - /* Clear ethtool n-tuple list */ - ethtool_ntuple_flush(dev); - list_for_each_entry_safe(p, n, &dev->napi_list, dev_list) netif_napi_del(p); diff --git a/net/core/ethtool.c b/net/core/ethtool.c index fd14116ad7f..b7c12a63d0c 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -169,18 +169,6 @@ int ethtool_op_set_flags(struct net_device *dev, u32 data, u32 supported) } EXPORT_SYMBOL(ethtool_op_set_flags); -void ethtool_ntuple_flush(struct net_device *dev) -{ - struct ethtool_rx_ntuple_flow_spec_container *fsc, *f; - - list_for_each_entry_safe(fsc, f, &dev->ethtool_ntuple_list.list, list) { - list_del(&fsc->list); - kfree(fsc); - } - dev->ethtool_ntuple_list.count = 0; -} -EXPORT_SYMBOL(ethtool_ntuple_flush); - /* Handlers for each ethtool command */ #define ETHTOOL_DEV_FEATURE_WORDS 1 @@ -865,34 +853,6 @@ out: return ret; } -static void __rx_ntuple_filter_add(struct ethtool_rx_ntuple_list *list, - struct ethtool_rx_ntuple_flow_spec *spec, - struct ethtool_rx_ntuple_flow_spec_container *fsc) -{ - - /* don't add filters forever */ - if (list->count >= ETHTOOL_MAX_NTUPLE_LIST_ENTRY) { - /* free the container */ - kfree(fsc); - return; - } - - /* Copy the whole filter over */ - fsc->fs.flow_type = spec->flow_type; - memcpy(&fsc->fs.h_u, &spec->h_u, sizeof(spec->h_u)); - memcpy(&fsc->fs.m_u, &spec->m_u, sizeof(spec->m_u)); - - fsc->fs.vlan_tag = spec->vlan_tag; - fsc->fs.vlan_tag_mask = spec->vlan_tag_mask; - fsc->fs.data = spec->data; - fsc->fs.data_mask = spec->data_mask; - fsc->fs.action = spec->action; - - /* add to the list */ - list_add_tail_rcu(&fsc->list, &list->list); - list->count++; -} - /* * ethtool does not (or did not) set masks for flow parameters that are * not specified, so if both value and mask are 0 then this must be @@ -930,8 +890,6 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, { struct ethtool_rx_ntuple cmd; const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_rx_ntuple_flow_spec_container *fsc = NULL; - int ret; if (!ops->set_rx_ntuple) return -EOPNOTSUPP; @@ -944,269 +902,7 @@ static noinline_for_stack int ethtool_set_rx_ntuple(struct net_device *dev, rx_ntuple_fix_masks(&cmd.fs); - /* - * Cache filter in dev struct for GET operation only if - * the underlying driver doesn't have its own GET operation, and - * only if the filter was added successfully. First make sure we - * can allocate the filter, then continue if successful. - */ - if (!ops->get_rx_ntuple) { - fsc = kmalloc(sizeof(*fsc), GFP_ATOMIC); - if (!fsc) - return -ENOMEM; - } - - ret = ops->set_rx_ntuple(dev, &cmd); - if (ret) { - kfree(fsc); - return ret; - } - - if (!ops->get_rx_ntuple) - __rx_ntuple_filter_add(&dev->ethtool_ntuple_list, &cmd.fs, fsc); - - return ret; -} - -static int ethtool_get_rx_ntuple(struct net_device *dev, void __user *useraddr) -{ - struct ethtool_gstrings gstrings; - const struct ethtool_ops *ops = dev->ethtool_ops; - struct ethtool_rx_ntuple_flow_spec_container *fsc; - u8 *data; - char *p; - int ret, i, num_strings = 0; - - if (!ops->get_sset_count) - return -EOPNOTSUPP; - - if (copy_from_user(&gstrings, useraddr, sizeof(gstrings))) - return -EFAULT; - - ret = ops->get_sset_count(dev, gstrings.string_set); - if (ret < 0) - return ret; - - gstrings.len = ret; - - data = kzalloc(gstrings.len * ETH_GSTRING_LEN, GFP_USER); - if (!data) - return -ENOMEM; - - if (ops->get_rx_ntuple) { - /* driver-specific filter grab */ - ret = ops->get_rx_ntuple(dev, gstrings.string_set, data); - goto copy; - } - - /* default ethtool filter grab */ - i = 0; - p = (char *)data; - list_for_each_entry(fsc, &dev->ethtool_ntuple_list.list, list) { - sprintf(p, "Filter %d:\n", i); - p += ETH_GSTRING_LEN; - num_strings++; - - switch (fsc->fs.flow_type) { - case TCP_V4_FLOW: - sprintf(p, "\tFlow Type: TCP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case UDP_V4_FLOW: - sprintf(p, "\tFlow Type: UDP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case SCTP_V4_FLOW: - sprintf(p, "\tFlow Type: SCTP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case AH_ESP_V4_FLOW: - sprintf(p, "\tFlow Type: AH ESP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case ESP_V4_FLOW: - sprintf(p, "\tFlow Type: ESP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IP_USER_FLOW: - sprintf(p, "\tFlow Type: Raw IP\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IPV4_FLOW: - sprintf(p, "\tFlow Type: IPv4\n"); - p += ETH_GSTRING_LEN; - num_strings++; - break; - default: - sprintf(p, "\tFlow Type: Unknown\n"); - p += ETH_GSTRING_LEN; - num_strings++; - goto unknown_filter; - } - - /* now the rest of the filters */ - switch (fsc->fs.flow_type) { - case TCP_V4_FLOW: - case UDP_V4_FLOW: - case SCTP_V4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.tcp_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.psrc, - fsc->fs.m_u.tcp_ip4_spec.psrc); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest Port: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.pdst, - fsc->fs.m_u.tcp_ip4_spec.pdst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.tcp_ip4_spec.tos, - fsc->fs.m_u.tcp_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case AH_ESP_V4_FLOW: - case ESP_V4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.ah_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSPI: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.spi, - fsc->fs.m_u.ah_ip4_spec.spi); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.ah_ip4_spec.tos, - fsc->fs.m_u.ah_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IP_USER_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - break; - case IPV4_FLOW: - sprintf(p, "\tSrc IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tSrc IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4src); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP addr: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tDest IP mask: 0x%x\n", - fsc->fs.m_u.usr_ip4_spec.ip4dst); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tL4 bytes: 0x%x, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.l4_4_bytes, - fsc->fs.m_u.usr_ip4_spec.l4_4_bytes); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tTOS: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.tos, - fsc->fs.m_u.usr_ip4_spec.tos); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tIP Version: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.ip_ver, - fsc->fs.m_u.usr_ip4_spec.ip_ver); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tProtocol: %d, mask: 0x%x\n", - fsc->fs.h_u.usr_ip4_spec.proto, - fsc->fs.m_u.usr_ip4_spec.proto); - p += ETH_GSTRING_LEN; - num_strings++; - break; - } - sprintf(p, "\tVLAN: %d, mask: 0x%x\n", - fsc->fs.vlan_tag, fsc->fs.vlan_tag_mask); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tUser-defined: 0x%Lx\n", fsc->fs.data); - p += ETH_GSTRING_LEN; - num_strings++; - sprintf(p, "\tUser-defined mask: 0x%Lx\n", fsc->fs.data_mask); - p += ETH_GSTRING_LEN; - num_strings++; - if (fsc->fs.action == ETHTOOL_RXNTUPLE_ACTION_DROP) - sprintf(p, "\tAction: Drop\n"); - else - sprintf(p, "\tAction: Direct to queue %d\n", - fsc->fs.action); - p += ETH_GSTRING_LEN; - num_strings++; -unknown_filter: - i++; - } -copy: - /* indicate to userspace how many strings we actually have */ - gstrings.len = num_strings; - ret = -EFAULT; - if (copy_to_user(useraddr, &gstrings, sizeof(gstrings))) - goto out; - useraddr += sizeof(gstrings); - if (copy_to_user(useraddr, data, gstrings.len * ETH_GSTRING_LEN)) - goto out; - ret = 0; - -out: - kfree(data); - return ret; + return ops->set_rx_ntuple(dev, &cmd); } static int ethtool_get_regs(struct net_device *dev, char __user *useraddr) @@ -2101,9 +1797,6 @@ int dev_ethtool(struct net *net, struct ifreq *ifr) case ETHTOOL_SRXNTUPLE: rc = ethtool_set_rx_ntuple(dev, useraddr); break; - case ETHTOOL_GRXNTUPLE: - rc = ethtool_get_rx_ntuple(dev, useraddr); - break; case ETHTOOL_GSSET_INFO: rc = ethtool_get_sset_info(dev, useraddr); break; -- cgit v1.2.3-70-g09d2 From 0b5c9db1b11d3175bb42b80663a9f072f801edf5 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Fri, 10 Jun 2011 06:56:58 +0000 Subject: vlan: Fix the ingress VLAN_FLAG_REORDER_HDR check Testing of VLAN_FLAG_REORDER_HDR does not belong in vlan_untag but rather in vlan_do_receive. Otherwise the vlan header will not be properly put on the packet in the case of vlan header accelleration. As we remove the check from vlan_check_reorder_header rename it vlan_reorder_header to keep the naming clean. Fix up the skb->pkt_type early so we don't look at the packet after adding the vlan tag, which guarantees we don't goof and look at the wrong field. Use a simple if statement instead of a complicated switch statement to decided that we need to increment rx_stats for a multicast packet. Hopefully at somepoint we will just declare the case where VLAN_FLAG_REORDER_HDR is cleared as unsupported and remove the code. Until then this keeps it working correctly. Signed-off-by: Eric W. Biederman Signed-off-by: Jiri Pirko Acked-by: Changli Gao Signed-off-by: David S. Miller --- include/linux/if_vlan.h | 25 ++++++++++++++++++--- include/linux/skbuff.h | 5 +++++ net/8021q/vlan_core.c | 60 +++++++++++++++++++++++++++---------------------- net/core/dev.c | 2 +- 4 files changed, 61 insertions(+), 31 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/if_vlan.h b/include/linux/if_vlan.h index dc01681fbb4..affa27380b7 100644 --- a/include/linux/if_vlan.h +++ b/include/linux/if_vlan.h @@ -225,7 +225,7 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb, } /** - * __vlan_put_tag - regular VLAN tag inserting + * vlan_insert_tag - regular VLAN tag inserting * @skb: skbuff to tag * @vlan_tci: VLAN TCI to insert * @@ -234,8 +234,10 @@ static inline int vlan_hwaccel_receive_skb(struct sk_buff *skb, * * Following the skb_unshare() example, in case of error, the calling function * doesn't have to worry about freeing the original skb. + * + * Does not change skb->protocol so this function can be used during receive. */ -static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +static inline struct sk_buff *vlan_insert_tag(struct sk_buff *skb, u16 vlan_tci) { struct vlan_ethhdr *veth; @@ -255,8 +257,25 @@ static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) /* now, the TCI */ veth->h_vlan_TCI = htons(vlan_tci); - skb->protocol = htons(ETH_P_8021Q); + return skb; +} +/** + * __vlan_put_tag - regular VLAN tag inserting + * @skb: skbuff to tag + * @vlan_tci: VLAN TCI to insert + * + * Inserts the VLAN tag into @skb as part of the payload + * Returns a VLAN tagged skb. If a new skb is created, @skb is freed. + * + * Following the skb_unshare() example, in case of error, the calling function + * doesn't have to worry about freeing the original skb. + */ +static inline struct sk_buff *__vlan_put_tag(struct sk_buff *skb, u16 vlan_tci) +{ + skb = vlan_insert_tag(skb, vlan_tci); + if (skb) + skb->protocol = htons(ETH_P_8021Q); return skb; } diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index e8b78ce1447..c0a4f3ab0cc 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -1256,6 +1256,11 @@ static inline void skb_reserve(struct sk_buff *skb, int len) skb->tail += len; } +static inline void skb_reset_mac_len(struct sk_buff *skb) +{ + skb->mac_len = skb->network_header - skb->mac_header; +} + #ifdef NET_SKBUFF_DATA_USES_OFFSET static inline unsigned char *skb_transport_header(const struct sk_buff *skb) { diff --git a/net/8021q/vlan_core.c b/net/8021q/vlan_core.c index 41495dc2a4c..fcc684678af 100644 --- a/net/8021q/vlan_core.c +++ b/net/8021q/vlan_core.c @@ -23,6 +23,31 @@ bool vlan_do_receive(struct sk_buff **skbp) return false; skb->dev = vlan_dev; + if (skb->pkt_type == PACKET_OTHERHOST) { + /* Our lower layer thinks this is not local, let's make sure. + * This allows the VLAN to have a different MAC than the + * underlying device, and still route correctly. */ + if (!compare_ether_addr(eth_hdr(skb)->h_dest, + vlan_dev->dev_addr)) + skb->pkt_type = PACKET_HOST; + } + + if (!(vlan_dev_info(vlan_dev)->flags & VLAN_FLAG_REORDER_HDR)) { + unsigned int offset = skb->data - skb_mac_header(skb); + + /* + * vlan_insert_tag expect skb->data pointing to mac header. + * So change skb->data before calling it and change back to + * original position later + */ + skb_push(skb, offset); + skb = *skbp = vlan_insert_tag(skb, skb->vlan_tci); + if (!skb) + return false; + skb_pull(skb, offset + VLAN_HLEN); + skb_reset_mac_len(skb); + } + skb->priority = vlan_get_ingress_priority(vlan_dev, skb->vlan_tci); skb->vlan_tci = 0; @@ -31,22 +56,8 @@ bool vlan_do_receive(struct sk_buff **skbp) u64_stats_update_begin(&rx_stats->syncp); rx_stats->rx_packets++; rx_stats->rx_bytes += skb->len; - - switch (skb->pkt_type) { - case PACKET_BROADCAST: - break; - case PACKET_MULTICAST: + if (skb->pkt_type == PACKET_MULTICAST) rx_stats->rx_multicast++; - break; - case PACKET_OTHERHOST: - /* Our lower layer thinks this is not local, let's make sure. - * This allows the VLAN to have a different MAC than the - * underlying device, and still route correctly. */ - if (!compare_ether_addr(eth_hdr(skb)->h_dest, - vlan_dev->dev_addr)) - skb->pkt_type = PACKET_HOST; - break; - } u64_stats_update_end(&rx_stats->syncp); return true; @@ -89,18 +100,13 @@ gro_result_t vlan_gro_frags(struct napi_struct *napi, struct vlan_group *grp, } EXPORT_SYMBOL(vlan_gro_frags); -static struct sk_buff *vlan_check_reorder_header(struct sk_buff *skb) +static struct sk_buff *vlan_reorder_header(struct sk_buff *skb) { - if (vlan_dev_info(skb->dev)->flags & VLAN_FLAG_REORDER_HDR) { - if (skb_cow(skb, skb_headroom(skb)) < 0) - skb = NULL; - if (skb) { - /* Lifted from Gleb's VLAN code... */ - memmove(skb->data - ETH_HLEN, - skb->data - VLAN_ETH_HLEN, 12); - skb->mac_header += VLAN_HLEN; - } - } + if (skb_cow(skb, skb_headroom(skb)) < 0) + return NULL; + memmove(skb->data - ETH_HLEN, skb->data - VLAN_ETH_HLEN, 2 * ETH_ALEN); + skb->mac_header += VLAN_HLEN; + skb_reset_mac_len(skb); return skb; } @@ -161,7 +167,7 @@ struct sk_buff *vlan_untag(struct sk_buff *skb) skb_pull_rcsum(skb, VLAN_HLEN); vlan_set_encap_proto(skb, vhdr); - skb = vlan_check_reorder_header(skb); + skb = vlan_reorder_header(skb); if (unlikely(!skb)) goto err_free; diff --git a/net/core/dev.c b/net/core/dev.c index a54c9f87ddb..9c58c1ec41a 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -3114,7 +3114,7 @@ static int __netif_receive_skb(struct sk_buff *skb) skb_reset_network_header(skb); skb_reset_transport_header(skb); - skb->mac_len = skb->network_header - skb->mac_header; + skb_reset_mac_len(skb); pt_prev = NULL; -- cgit v1.2.3-70-g09d2 From 56f8a75c17abb854b5907f4a815dc4c3f186ba11 Mon Sep 17 00:00:00 2001 From: Paul Gortmaker Date: Tue, 21 Jun 2011 20:33:34 -0700 Subject: ip: introduce ip_is_fragment helper inline function There are enough instances of this: iph->frag_off & htons(IP_MF | IP_OFFSET) that a helper function is probably warranted. Signed-off-by: Paul Gortmaker Signed-off-by: David S. Miller --- drivers/net/bonding/bond_main.c | 2 +- drivers/net/ioc3-eth.c | 2 +- drivers/net/myri10ge/myri10ge.c | 2 +- drivers/net/s2io.c | 2 +- drivers/net/sfc/filter.c | 2 +- drivers/net/vxge/vxge-main.c | 2 +- include/net/ip.h | 5 +++++ net/core/dev.c | 2 +- net/ipv4/ip_input.c | 4 ++-- net/ipv4/ip_output.c | 2 +- net/ipv4/ipconfig.c | 2 +- net/ipv4/netfilter/nf_defrag_ipv4.c | 2 +- net/ipv4/netfilter/nf_nat_standalone.c | 2 +- net/ipv4/xfrm4_policy.c | 2 +- net/netfilter/ipvs/ip_vs_core.c | 7 +++---- net/sched/cls_flow.c | 4 ++-- net/sched/cls_rsvp.h | 2 +- net/sched/sch_choke.c | 2 +- net/sched/sch_sfq.c | 2 +- 19 files changed, 27 insertions(+), 23 deletions(-) (limited to 'net/core/dev.c') diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index d117280b9cd..ebb1d219b45 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -3438,7 +3438,7 @@ static int bond_xmit_hash_policy_l34(struct sk_buff *skb, int count) int layer4_xor = 0; if (skb->protocol == htons(ETH_P_IP)) { - if (!(iph->frag_off & htons(IP_MF|IP_OFFSET)) && + if (!ip_is_fragment(iph) && (iph->protocol == IPPROTO_TCP || iph->protocol == IPPROTO_UDP)) { layer4_xor = ntohs((*layer4hdr ^ *(layer4hdr + 1))); diff --git a/drivers/net/ioc3-eth.c b/drivers/net/ioc3-eth.c index 32f07f868d8..318a25a9231 100644 --- a/drivers/net/ioc3-eth.c +++ b/drivers/net/ioc3-eth.c @@ -532,7 +532,7 @@ static void ioc3_tcpudp_checksum(struct sk_buff *skb, uint32_t hwsum, int len) return; ih = (struct iphdr *) ((char *)eh + ETH_HLEN); - if (ih->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ih)) return; proto = ih->protocol; diff --git a/drivers/net/myri10ge/myri10ge.c b/drivers/net/myri10ge/myri10ge.c index 3e89a842fc5..3ed5f3505ce 100644 --- a/drivers/net/myri10ge/myri10ge.c +++ b/drivers/net/myri10ge/myri10ge.c @@ -2257,7 +2257,7 @@ myri10ge_get_frag_header(struct skb_frag_struct *frag, void **mac_hdr, *ip_hdr = iph; if (iph->protocol != IPPROTO_TCP) return -1; - if (iph->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(iph)) return -1; *hdr_flags |= LRO_TCP; *tcpudp_hdr = (u8 *) (*ip_hdr) + (iph->ihl << 2); diff --git a/drivers/net/s2io.c b/drivers/net/s2io.c index f4d80f9050e..043850b8c30 100644 --- a/drivers/net/s2io.c +++ b/drivers/net/s2io.c @@ -4109,7 +4109,7 @@ static netdev_tx_t s2io_xmit(struct sk_buff *skb, struct net_device *dev) struct tcphdr *th; ip = ip_hdr(skb); - if ((ip->frag_off & htons(IP_OFFSET|IP_MF)) == 0) { + if (!ip_is_fragment(ip)) { th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4); diff --git a/drivers/net/sfc/filter.c b/drivers/net/sfc/filter.c index 95a980fd63d..f2fc2587c09 100644 --- a/drivers/net/sfc/filter.c +++ b/drivers/net/sfc/filter.c @@ -652,7 +652,7 @@ int efx_filter_rfs(struct net_device *net_dev, const struct sk_buff *skb, /* RFS must validate the IP header length before calling us */ EFX_BUG_ON_PARANOID(!pskb_may_pull(skb, nhoff + sizeof(*ip))); ip = (const struct iphdr *)(skb->data + nhoff); - if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ip)) return -EPROTONOSUPPORT; EFX_BUG_ON_PARANOID(!pskb_may_pull(skb, nhoff + 4 * ip->ihl + 4)); ports = (const __be16 *)(skb->data + nhoff + 4 * ip->ihl); diff --git a/drivers/net/vxge/vxge-main.c b/drivers/net/vxge/vxge-main.c index 54ca74806bb..1c92af39299 100644 --- a/drivers/net/vxge/vxge-main.c +++ b/drivers/net/vxge/vxge-main.c @@ -633,7 +633,7 @@ static u32 vxge_get_vpath_no(struct vxgedev *vdev, struct sk_buff *skb) ip = ip_hdr(skb); - if ((ip->frag_off & htons(IP_OFFSET|IP_MF)) == 0) { + if (!ip_is_fragment(ip)) { th = (struct tcphdr *)(((unsigned char *)ip) + ip->ihl*4); diff --git a/include/net/ip.h b/include/net/ip.h index e9ea7c73f8c..d603cd329c4 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -250,6 +250,11 @@ int ip_decrease_ttl(struct iphdr *iph) return --iph->ttl; } +static inline bool ip_is_fragment(const struct iphdr *iph) +{ + return (iph->frag_off & htons(IP_MF | IP_OFFSET)) != 0; +} + static inline int ip_dont_fragment(struct sock *sk, struct dst_entry *dst) { diff --git a/net/core/dev.c b/net/core/dev.c index 8efe8507013..6b6ef14b42f 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -2532,7 +2532,7 @@ __u32 __skb_get_rxhash(struct sk_buff *skb) goto done; ip = (const struct iphdr *) (skb->data + nhoff); - if (ip->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ip)) ip_proto = 0; else ip_proto = ip->protocol; diff --git a/net/ipv4/ip_input.c b/net/ipv4/ip_input.c index c8f48efc5fd..073a9b01c40 100644 --- a/net/ipv4/ip_input.c +++ b/net/ipv4/ip_input.c @@ -165,7 +165,7 @@ int ip_call_ra_chain(struct sk_buff *skb) (!sk->sk_bound_dev_if || sk->sk_bound_dev_if == dev->ifindex) && net_eq(sock_net(sk), dev_net(dev))) { - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(skb, IP_DEFRAG_CALL_RA_CHAIN)) return 1; } @@ -256,7 +256,7 @@ int ip_local_deliver(struct sk_buff *skb) * Reassemble IP fragments. */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_defrag(skb, IP_DEFRAG_LOCAL_DELIVER)) return 0; } diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index a8024eaa0e8..167da8ba416 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -489,7 +489,7 @@ int ip_fragment(struct sk_buff *skb, int (*output)(struct sk_buff *)) if (first_len - hlen > mtu || ((first_len - hlen) & 7) || - (iph->frag_off & htons(IP_MF|IP_OFFSET)) || + ip_is_fragment(iph) || skb_cloned(skb)) goto slow_path; diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index ab7e5542c1c..ae93dd5ef40 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -932,7 +932,7 @@ static int __init ic_bootp_recv(struct sk_buff *skb, struct net_device *dev, str goto drop; /* Fragments are not supported */ - if (h->frag_off & htons(IP_OFFSET | IP_MF)) { + if (ip_is_fragment(h)) { if (net_ratelimit()) printk(KERN_ERR "DHCP/BOOTP: Ignoring fragmented " "reply.\n"); diff --git a/net/ipv4/netfilter/nf_defrag_ipv4.c b/net/ipv4/netfilter/nf_defrag_ipv4.c index f3a9b42b16c..9bb1b8a37a2 100644 --- a/net/ipv4/netfilter/nf_defrag_ipv4.c +++ b/net/ipv4/netfilter/nf_defrag_ipv4.c @@ -82,7 +82,7 @@ static unsigned int ipv4_conntrack_defrag(unsigned int hooknum, #endif #endif /* Gather fragments. */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { enum ip_defrag_users user = nf_ct_defrag_user(hooknum, skb); if (nf_ct_ipv4_gather_frags(skb, user)) return NF_STOLEN; diff --git a/net/ipv4/netfilter/nf_nat_standalone.c b/net/ipv4/netfilter/nf_nat_standalone.c index 483b76d042d..a6e606e8482 100644 --- a/net/ipv4/netfilter/nf_nat_standalone.c +++ b/net/ipv4/netfilter/nf_nat_standalone.c @@ -88,7 +88,7 @@ nf_nat_fn(unsigned int hooknum, /* We never see fragments: conntrack defrags on pre-routing and local-out, and nf_nat_out protects post-routing. */ - NF_CT_ASSERT(!(ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET))); + NF_CT_ASSERT(!ip_is_fragment(ip_hdr(skb))); ct = nf_ct_get(skb, &ctinfo); /* Can't track? It's not due to stress, or conntrack would diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 981e43eaf70..fc5368ad2b0 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -117,7 +117,7 @@ _decode_session4(struct sk_buff *skb, struct flowi *fl, int reverse) memset(fl4, 0, sizeof(struct flowi4)); fl4->flowi4_mark = skb->mark; - if (!(iph->frag_off & htons(IP_MF | IP_OFFSET))) { + if (!ip_is_fragment(iph)) { switch (iph->protocol) { case IPPROTO_UDP: case IPPROTO_UDPLITE: diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index e33d48cae9f..4f77bb16d22 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -852,7 +852,7 @@ static int ip_vs_out_icmp(struct sk_buff *skb, int *related, *related = 1; /* reassemble IP fragments */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } @@ -1156,8 +1156,7 @@ ip_vs_out(unsigned int hooknum, struct sk_buff *skb, int af) ip_vs_fill_iphdr(af, skb_network_header(skb), &iph); } else #endif - if (unlikely(ip_hdr(skb)->frag_off & htons(IP_MF|IP_OFFSET) && - !pp->dont_defrag)) { + if (unlikely(ip_is_fragment(ip_hdr(skb)) && !pp->dont_defrag)) { if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; @@ -1310,7 +1309,7 @@ ip_vs_in_icmp(struct sk_buff *skb, int *related, unsigned int hooknum) *related = 1; /* reassemble IP fragments */ - if (ip_hdr(skb)->frag_off & htons(IP_MF | IP_OFFSET)) { + if (ip_is_fragment(ip_hdr(skb))) { if (ip_vs_gather_frags(skb, ip_vs_defrag_user(hooknum))) return NF_STOLEN; } diff --git a/net/sched/cls_flow.c b/net/sched/cls_flow.c index 8ec01391d98..34533a5d1b3 100644 --- a/net/sched/cls_flow.c +++ b/net/sched/cls_flow.c @@ -121,7 +121,7 @@ static u32 flow_get_proto_src(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(iph)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && @@ -163,7 +163,7 @@ static u32 flow_get_proto_dst(struct sk_buff *skb) if (!pskb_network_may_pull(skb, sizeof(*iph))) break; iph = ip_hdr(skb); - if (iph->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(iph)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && diff --git a/net/sched/cls_rsvp.h b/net/sched/cls_rsvp.h index 402c44b241a..ed691b14838 100644 --- a/net/sched/cls_rsvp.h +++ b/net/sched/cls_rsvp.h @@ -167,7 +167,7 @@ restart: dst = &nhptr->daddr; protocol = nhptr->protocol; xprt = ((u8 *)nhptr) + (nhptr->ihl<<2); - if (nhptr->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(nhptr)) return -1; #endif diff --git a/net/sched/sch_choke.c b/net/sched/sch_choke.c index 06afbaeb4c8..3422b25df9e 100644 --- a/net/sched/sch_choke.c +++ b/net/sched/sch_choke.c @@ -181,7 +181,7 @@ static bool choke_match_flow(struct sk_buff *skb1, ip1->saddr != ip2->saddr || ip1->daddr != ip2->daddr) return false; - if ((ip1->frag_off | ip2->frag_off) & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(ip1) | ip_is_fragment(ip2)) ip_proto = 0; off1 += ip1->ihl * 4; off2 += ip2->ihl * 4; diff --git a/net/sched/sch_sfq.c b/net/sched/sch_sfq.c index b6ea6afa55b..4536ee64383 100644 --- a/net/sched/sch_sfq.c +++ b/net/sched/sch_sfq.c @@ -157,7 +157,7 @@ static unsigned int sfq_hash(struct sfq_sched_data *q, struct sk_buff *skb) iph = ip_hdr(skb); h = (__force u32)iph->daddr; h2 = (__force u32)iph->saddr ^ iph->protocol; - if (iph->frag_off & htons(IP_MF | IP_OFFSET)) + if (ip_is_fragment(iph)) break; poff = proto_ports_offset(iph->protocol); if (poff >= 0 && -- cgit v1.2.3-70-g09d2 From 4e985adaa504c1c1a05c8e013777ea0791a17b4d Mon Sep 17 00:00:00 2001 From: Thomas Graf Date: Tue, 21 Jun 2011 03:11:20 +0000 Subject: rtnl: provide link dump consistency info This patch adds a change sequence counter to each net namespace which is bumped whenever a netdevice is added or removed from the list. If such a change occurred while a link dump took place, the dump will have the NLM_F_DUMP_INTR flag set in the first message which has been interrupted and in all subsequent messages of the same dump. Note that links may still be modified or renamed while a dump is taking place but we can guarantee for userspace to receive a complete list of links and not miss any. Testing: I have added 500 VLAN netdevices to make sure the dump is split over multiple messages. Then while continuously dumping links in one process I also continuously deleted and re-added a dummy netdevice in another process. Multiple dumps per seconds have had the NLM_F_DUMP_INTR flag set. I guess we can wait for Johannes patch to hit net-next via the wireless tree. I just wanted to give this some testing right away. Signed-off-by: Thomas Graf Signed-off-by: David S. Miller --- include/net/net_namespace.h | 1 + net/core/dev.c | 10 ++++++++++ net/core/net_namespace.c | 1 + net/core/rtnetlink.c | 4 ++++ 4 files changed, 16 insertions(+) (limited to 'net/core/dev.c') diff --git a/include/net/net_namespace.h b/include/net/net_namespace.h index aef430d779b..1ab1aec209a 100644 --- a/include/net/net_namespace.h +++ b/include/net/net_namespace.h @@ -65,6 +65,7 @@ struct net { struct list_head dev_base_head; struct hlist_head *dev_name_head; struct hlist_head *dev_index_head; + unsigned int dev_base_seq; /* protected by rtnl_mutex */ /* core fib_rules */ struct list_head rules_ops; diff --git a/net/core/dev.c b/net/core/dev.c index 6b6ef14b42f..4577e6711ec 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -199,6 +199,11 @@ static struct list_head ptype_all __read_mostly; /* Taps */ DEFINE_RWLOCK(dev_base_lock); EXPORT_SYMBOL(dev_base_lock); +static inline void dev_base_seq_inc(struct net *net) +{ + while (++net->dev_base_seq == 0); +} + static inline struct hlist_head *dev_name_hash(struct net *net, const char *name) { unsigned hash = full_name_hash(name, strnlen(name, IFNAMSIZ)); @@ -237,6 +242,9 @@ static int list_netdevice(struct net_device *dev) hlist_add_head_rcu(&dev->index_hlist, dev_index_hash(net, dev->ifindex)); write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(net); + return 0; } @@ -253,6 +261,8 @@ static void unlist_netdevice(struct net_device *dev) hlist_del_rcu(&dev->name_hlist); hlist_del_rcu(&dev->index_hlist); write_unlock_bh(&dev_base_lock); + + dev_base_seq_inc(dev_net(dev)); } /* diff --git a/net/core/net_namespace.c b/net/core/net_namespace.c index ea489db1bc2..5bbdbf0d366 100644 --- a/net/core/net_namespace.c +++ b/net/core/net_namespace.c @@ -129,6 +129,7 @@ static __net_init int setup_net(struct net *net) atomic_set(&net->count, 1); atomic_set(&net->passive, 1); + net->dev_base_seq = 1; #ifdef NETNS_REFCNT_DEBUG atomic_set(&net->use_count, 0); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index a798fc6f2aa..99d9e953fe3 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1032,6 +1032,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) s_idx = cb->args[1]; rcu_read_lock(); + cb->seq = net->dev_base_seq; + for (h = s_h; h < NETDEV_HASHENTRIES; h++, s_idx = 0) { idx = 0; head = &net->dev_index_head[h]; @@ -1043,6 +1045,8 @@ static int rtnl_dump_ifinfo(struct sk_buff *skb, struct netlink_callback *cb) cb->nlh->nlmsg_seq, 0, NLM_F_MULTI) <= 0) goto out; + + nl_dump_check_consistent(cb, nlmsg_hdr(skb)); cont: idx++; } -- cgit v1.2.3-70-g09d2 From f9d7a1187dfefc6b54b53e0ffff4d26c0eff2702 Mon Sep 17 00:00:00 2001 From: Shan Wei Date: Tue, 5 Jul 2011 20:44:17 -0700 Subject: net: Add GSO to vlan_features initialization Just add GSO to vlan_features initialization, and update comments. When we set offload features, vlan_dev_fix_features() will do more check. In vlan_dev_fix_features(), final features is decided by features of real device and vlan_features of real device. Signed-off-by: Shan Wei Signed-off-by: David S. Miller --- net/core/dev.c | 9 +++++---- 1 file changed, 5 insertions(+), 4 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 4577e6711ec..9ca15142d82 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5488,11 +5488,12 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_NOCACHE_COPY; } - /* Enable GRO and NETIF_F_HIGHDMA for vlans by default, - * vlan_dev_init() will do the dev->features check, so these features - * are enabled only if supported by underlying device. + /* Enable GSO, GRO and NETIF_F_HIGHDMA for vlans by default, + * vlan_dev_fix_features() will do the features check, + * so NETIF_F_HIGHDMA feature is enabled only if supported + * by underlying device. */ - dev->vlan_features |= (NETIF_F_GRO | NETIF_F_HIGHDMA); + dev->vlan_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_HIGHDMA); ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); -- cgit v1.2.3-70-g09d2 From 1180e7d6599c1fb0c56a23a649a3eb37d877b9d0 Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Thu, 14 Jul 2011 14:41:11 -0700 Subject: net: cleanup vlan_features setting in register_netdev MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit vlan_features contains features inherited from underlying device. NETIF_SOFT_FEATURES are not inherited but belong to the vlan device itself (ensured in vlan_dev_fix_features()). Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- net/core/dev.c | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'net/core/dev.c') diff --git a/net/core/dev.c b/net/core/dev.c index 9ca15142d82..e57be026205 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5488,12 +5488,9 @@ int register_netdevice(struct net_device *dev) dev->features |= NETIF_F_NOCACHE_COPY; } - /* Enable GSO, GRO and NETIF_F_HIGHDMA for vlans by default, - * vlan_dev_fix_features() will do the features check, - * so NETIF_F_HIGHDMA feature is enabled only if supported - * by underlying device. + /* Make NETIF_F_HIGHDMA inheritable to VLAN devices. */ - dev->vlan_features |= (NETIF_F_SOFT_FEATURES | NETIF_F_HIGHDMA); + dev->vlan_features |= NETIF_F_HIGHDMA; ret = call_netdevice_notifiers(NETDEV_POST_INIT, dev); ret = notifier_to_errno(ret); -- cgit v1.2.3-70-g09d2 From fec30c33819b442fd618b10f405248ee7cbb51d8 Mon Sep 17 00:00:00 2001 From: Michał Mirosław Date: Wed, 13 Jul 2011 14:10:30 +0000 Subject: net: unexport netdev_fix_features() MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit It is not used anywhere except net/core/dev.c now. Signed-off-by: Michał Mirosław Signed-off-by: David S. Miller --- include/linux/netdevice.h | 1 - net/core/dev.c | 3 +-- 2 files changed, 1 insertion(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 5ccc0cb8352..f84dfd25c43 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -2529,7 +2529,6 @@ static inline u32 netdev_get_wanted_features(struct net_device *dev) return (dev->features & ~dev->hw_features) | dev->wanted_features; } u32 netdev_increment_features(u32 all, u32 one, u32 mask); -u32 netdev_fix_features(struct net_device *dev, u32 features); int __netdev_update_features(struct net_device *dev); void netdev_update_features(struct net_device *dev); void netdev_change_features(struct net_device *dev); diff --git a/net/core/dev.c b/net/core/dev.c index e57be026205..9444c5cb413 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -5209,7 +5209,7 @@ static void rollback_registered(struct net_device *dev) list_del(&single); } -u32 netdev_fix_features(struct net_device *dev, u32 features) +static u32 netdev_fix_features(struct net_device *dev, u32 features) { /* Fix illegal checksum combinations */ if ((features & NETIF_F_HW_CSUM) && @@ -5268,7 +5268,6 @@ u32 netdev_fix_features(struct net_device *dev, u32 features) return features; } -EXPORT_SYMBOL(netdev_fix_features); int __netdev_update_features(struct net_device *dev) { -- cgit v1.2.3-70-g09d2 From 2d348d1f569f051d2609b04d27bb55cd25eda8fe Mon Sep 17 00:00:00 2001 From: Joe Perches Date: Mon, 25 Jul 2011 16:17:35 -0700 Subject: net: Convert struct net_device uc_promisc to bool No need to use int, its uses are boolean. May save a few bytes one day. Signed-off-by: Joe Perches Signed-off-by: David S. Miller --- include/linux/netdevice.h | 2 +- net/core/dev.c | 4 ++-- 2 files changed, 3 insertions(+), 3 deletions(-) (limited to 'net/core/dev.c') diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index 34f3abc6457..1d92acc0777 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -1132,7 +1132,7 @@ struct net_device { spinlock_t addr_list_lock; struct netdev_hw_addr_list uc; /* Unicast mac addresses */ struct netdev_hw_addr_list mc; /* Multicast mac addresses */ - int uc_promisc; + bool uc_promisc; unsigned int promiscuity; unsigned int allmulti; diff --git a/net/core/dev.c b/net/core/dev.c index 9444c5cb413..17d67b579be 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -4497,10 +4497,10 @@ void __dev_set_rx_mode(struct net_device *dev) */ if (!netdev_uc_empty(dev) && !dev->uc_promisc) { __dev_set_promiscuity(dev, 1); - dev->uc_promisc = 1; + dev->uc_promisc = true; } else if (netdev_uc_empty(dev) && dev->uc_promisc) { __dev_set_promiscuity(dev, -1); - dev->uc_promisc = 0; + dev->uc_promisc = false; } if (ops->ndo_set_multicast_list) -- cgit v1.2.3-70-g09d2