aboutsummaryrefslogtreecommitdiff
AgeCommit message (Collapse)Author
2008-12-17dccp_diag: LISTEN sockets don't have CCIDsArnaldo Carvalho de Melo
And thus when we try to use 'ss -danemi' on these sockets that have no ccid blocks (data collected using systemtap after I fixed the problem): dccp_diag_get_info sk=0xffff8801220a3100, dp->dccps_hc_rx_ccid=0x0000000000000000, dp->dccps_hc_tx_ccid=0x0000000000000000 We get an OOPS: mica.ghostprotocols.net login: BUG: unable to handle kernel NULL pointer dereferenc0 IP: [<ffffffffa0136082>] dccp_diag_get_info+0x82/0xc0 [dccp_diag] PGD 12106f067 PUD 122488067 PMD 0 Oops: 0000 [#1] PREEMPT Fix is trivial, and 'ss -d' is working again: [root@mica ~]# ss -danemi State Recv-Q Send-Q Local Address:Port Peer Address:Port LISTEN 0 0 *:5001 *:* ino:7288 sk:220a3100ffff8801 mem:(r0,w0,f0,t0) cwnd:0 ssthresh:0 [root@mica ~]# Signed-off-by: Arnaldo Carvalho de Melo <acme@redhat.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-17Phonet: USB CDC Phonet function for gadget frameworkRémi Denis-Courmont
This implements the Nokia vendor-specific communication device class function to exchange Phonet messages over USB. This function is already found in the "PC suite" USB profile of (non-Linux) Nokia handsets. Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-17Phonet: get rid of deferred work on the transmission pathRémi Denis-Courmont
Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-17Phonet: use atomic for packet TX windowRémi Denis-Courmont
GPRS TX flow control won't need to lock the underlying socket anymore. Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-17Phonet: allocate separate ARP type for GPRS over a Phonet pipeRémi Denis-Courmont
A separate xmit lock class supports GPRS over a Phonet pipe over a TUN device (type ARPHRD_NONE). Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-17Phonet: allocate a non-Ethernet ARP typeRémi Denis-Courmont
Also leave some room for more 802.11 types. Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-17vcan: whitespace fixesOliver Hartkopp
Signed-off-by: Oliver Hartkopp <oliver@hartkopp.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-17net: ppp_generic - use idr technique instead of cardmapsCyrill Gorcunov
Use idr technique instead of own implemented cardmaps. It saves us a number of lines and gives an ability to use library functions. Signed-off-by: Cyrill Gorcunov <gorcunov@openvz.org> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16bnx2x: Fix namespace collision with FLOW_CTRL_{TX,RX}David S. Miller
These are now defined in linux/mii.h and the bnx2x driver defines different values which are shared with hardware data structures. So add a "BNX2X_" prefix to these macro names. Based upon a report from Stephen Rothwell. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16bnx2: Don't redefine FLOW_CTRL_{RX,TX}.David S. Miller
They are provided generically by linux/mii.h now. Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16bnx2: Update version to 1.9.0.Michael Chan
And fix the 5716S pci_device_id entry to point to the proper string. Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16bnx2: Rename MSI-X vectors.Michael Chan
Change MSI-X vector names to "ethx-%d". Signed-off-by: Michael Chan <mchan@broadcom.com> Signed-off-by: Benjamin Li <benli@broadcom.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16drivers/net/hamradio: Move a dereference below a NULL testJulia Lawall
In each case, if the NULL test is necessary, then the dereference should be moved below the NULL test. The semantic patch that makes this change is as follows: (http://www.emn.fr/x-info/coccinelle/) // <smpl> @@ type T; expression E; identifier i,fld; statement S; @@ - T i = E->fld; + T i; ... when != E when != i if (E == NULL) S + i = E->fld; // </smpl> Signed-off-by: Julia Lawall <julia@diku.dk> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16phylib: Remove unnecessary "reset" fixups in genphy_setup_forcedAndy Fleming
genphy_setup_forced hasn't actually reset the PHY for a long time, but a comment to that effect remained in the code, so code continued to act as if it *had* reset the PHY, and called the necessary fixup functions to respond to a PHY reset. With no reset, those functions are no longer needed, so we remove them. Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Make all BD status writes 32-bitDai Haruki
Whenever we want to update the status field in a BD, we usually want to update the length field, too. By combining them into one 32-bit field, we reduce the number of stores to memory shared with the controller, and we eliminate the need for order-enforcement, as the length and "READY" bit are now updated atomically at the same time. Signed-off-by: Dai Haruki <Dai.Haruki@freescale.com> Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Add macros for stepping through BDsAndy Fleming
This code is based strongly on code from Dai Haruki <Dai.Haruki@freescale.com>. The gianfar Buffer Descriptors are arranged in a circular array, the end of which is denoted by setting the "WRAP" bit in the descriptor. However, the software knows the end of the ring because it knows how many descriptors are there. Rather than check each descriptor for whether the WRAP bit is set, use pointer math to determine where the next BD is. This is also useful for when we want to look at BDs other than the very next one (for Scatter-Gather). Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Remove unused gfar_add_fcb() function parameterDai Haruki
- Also, use cacheable_memzero instead of memset for performance reasons. Signed-off-by: Dai Haruki <dai.haruki@freescale.com> Acked-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Enable padding and Optimize the frame prepended bytes handlingDai Haruki
The eTSEC can prepend up to 32 bytes to a received frame, usually for the purpose of aligning the IP address to a word boundary, so this turns it on. While we're in there, make the handling of the pre-frame bytes (padding and Frame Control Block) cleaner. Signed-off-by: Dai Haruki <dai.haruki@freescale.com> Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Fix VLAN HW feature related frame/buffer size calculation.Dai Haruki
Optimize the VLAN checking logic as well. Signed-off-by: Dai Haruki <dai.haruki@freescale.com> Acked-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Fix eTSEC configuration procedureDai Haruki
Fix some bugs in the ethtool configuration functions: * gfar_clean_rx_ring should not be called with interrupts disabled. * Update last transmission time to avoid tx timeout. * Delete redundant NETIF_F_IP_CSUM check in gfar_start_xmit * Use netif_tx_lock_bh when reconfiguring the tx csum Signed-off-by: Dai Haruki <dai.haruki@freescale.com> Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Optimize interrupt coalescing configurationDai Haruki
Store the interrupt coalescing values in the form in which they will be written to the interrupt coalescing registers. This puts a little overhead into the ethtool configuration, and takes it out of the interrupt handler Signed-off-by: Dai Haruki <dai.haruki@freescale.com> Acked-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Convert gianfar to an of_platform_driverAndy Fleming
Does the same for the accompanying MDIO driver, and then modifies the TBI configuration method. The old way used fields in einfo, which no longer exists. The new way is to create an MDIO device-tree node for each instance of gianfar, and create a tbi-handle property to associate ethernet controllers with the TBI PHYs they are connected to. Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16gianfar: Use gfar_halt to stop DMA in gfar_probeAndy Fleming
gfar_halt does everything we want to do there, including disabling TX/RX. It also doesn't unnecessarily enable DMA if it's already stopped. Signed-off-by: Andy Fleming <afleming@freescale.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16tlan: Remove broken support for big buffersSakari Ailus
The big rx/tx buffer support is broken and unlikely to be very useful as such. Remove it. Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16Merge branch 'master' of ↵David S. Miller
master.kernel.org:/pub/scm/linux/kernel/git/davem/net-2.6 Conflicts: drivers/net/enc28j60.c
2008-12-16tlan: Fix pci memory unmappingSakari Ailus
Fix pci unmapping problem introduced by commit id 8953f1282793882a5444924f7a273dc72a43d0a3 "tlan: Fix small (< 64 bytes) datagram transmissions". Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16ipv6: fix the outgoing interface selection order in udpv6_sendmsg()Yang Hongyang
1.When no interface is specified in an IPV6_PKTINFO ancillary data item, the interface specified in an IPV6_PKTINFO sticky optionis is used. RFC3542: 6.7. Summary of Outgoing Interface Selection This document and [RFC-3493] specify various methods that affect the selection of the packet's outgoing interface. This subsection summarizes the ordering among those in order to ensure deterministic behavior. For a given outgoing packet on a given socket, the outgoing interface is determined in the following order: 1. if an interface is specified in an IPV6_PKTINFO ancillary data item, the interface is used. 2. otherwise, if an interface is specified in an IPV6_PKTINFO sticky option, the interface is used. Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16ipv6: fix the return interface index when get it while no message is receivedYang Hongyang
When get receiving interface index while no message is received, the the value seted with setsockopt() should be returned. RFC 3542: Issuing getsockopt() for the above options will return the sticky option value i.e., the value set with setsockopt(). If no sticky option value has been set getsockopt() will return the following values: - For the IPV6_PKTINFO option, it will return an in6_pktinfo structure with ipi6_addr being in6addr_any and ipi6_ifindex being zero. Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16ipv6: Add IPV6_PKTINFO sticky option support to setsockopt()Yang Hongyang
There are three reasons for me to add this support: 1.When no interface is specified in an IPV6_PKTINFO ancillary data item, the interface specified in an IPV6_PKTINFO sticky optionis is used. RFC3542: 6.7. Summary of Outgoing Interface Selection This document and [RFC-3493] specify various methods that affect the selection of the packet's outgoing interface. This subsection summarizes the ordering among those in order to ensure deterministic behavior. For a given outgoing packet on a given socket, the outgoing interface is determined in the following order: 1. if an interface is specified in an IPV6_PKTINFO ancillary data item, the interface is used. 2. otherwise, if an interface is specified in an IPV6_PKTINFO sticky option, the interface is used. 2.When no IPV6_PKTINFO ancillary data is received,getsockopt() should return the sticky option value which set with setsockopt(). RFC 3542: Issuing getsockopt() for the above options will return the sticky option value i.e., the value set with setsockopt(). If no sticky option value has been set getsockopt() will return the following values: 3.Make the setsockopt implementation POSIX compliant. Signed-off-by: Yang Hongyang <yanghy@cn.fujitsu.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16net: Refactor full duplex flow control resolutionSteve Glendinning
These 4 drivers have identical full duplex flow control resolution functions. This patch changes them all to use one common function. The function in question decides whether a device should enable TX and RX flow control in a standard way (IEEE 802.3-2005 table 28B-3), so this should also be useful for other drivers. Signed-off-by: Steve Glendinning <steve.glendinning@smsc.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16net: Move flow control definitions to mii.hSteve Glendinning
flags used within drivers for indicating tx and rx flow control are defined in 4 drivers (and probably more), move these constants to mii.h. The 3 SMSC drivers use the same constants (FLOW_CTRL_TX), but TG3 uses TG3_FLOW_CTRL_TX, so this patch also renames the constants within TG3. Signed-off-by: Steve Glendinning <steve.glendinning@smsc.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16simeth: convert to net_device_opsAlexey Dobriyan
Signed-off-by: Alexey Dobriyan <adobriyan@gmail.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16cxgb3: untie strict FW matchingDivy Le Ray
The NIC driver can work with mutliple versions of the FW. Let the driver load when the embedded FW does not match, and the FW update mechanism failed. The iWARP module will make its own loading decision. Signed-off-by: Divy Le Ray <divy@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16enc28j60: use netif_rx_ni() to deliver RX packetsBaruch Siach
The enc28j60 driver reads incoming packets in the process (workqueue) context, not in a tasklet or the interrupt context. Thus, we should use netif_rx_ni() to deliver those packets to the networking layer, instead of netif_rx(). This way incoming packets don't wait in the incoming queue for the next IRQ to be serviced. Signed-off-by: Baruch Siach <baruch@tkos.co.il> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16tlan: Fix small (< 64 bytes) datagram transmissionsSakari Ailus
The TLAN chip does not support tranmissions smaller than 64 bytes. Smaller transfers need to be padded up to that size. This was broken by commit id 41873e9aff0632d80c74380d58a89e8d420151bd ("tlan: get rid of padding buffer"). <URL:http://bugzilla.kernel.org/show_bug.cgi?id=11754> Signed-off-by: Sakari Ailus <sakari.ailus@iki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16vcan: convert to net_device_opsOliver Hartkopp
Signed-off-by: Oliver Hartkopp <oliver@hartkopp.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16l2tp: fix UDP checksum supportJames Chapman
The pppol2tp driver has had broken UDP checksum code for a long time. This patch fixes it. If UDP checksums are enabled in the tunnel's UDP socket, the L2TP driver now properly validates the checksum on receive and fills in the checksum on transmit. If the network device has hardware checksum support and is enabled, it is used instead of generating/checking the checksum in software. Signed-off-by: James Chapman <jchapman@katalix.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16netfilter: ctnetlink: fix missing CTA_NAT_SEQ_UNSPECPablo Neira Ayuso
This patch fixes an inconsistency in nfnetlink_conntrack.h that I introduced myself. The problem is that CTA_NAT_SEQ_UNSPEC is missing from enum ctattr_natseq. This inconsistency may lead to problems in the message parsing in userspace (if the message contains the CTA_NAT_SEQ_* attributes, of course). This patch breaks backward compatibility, however, the only known client of this code is libnetfilter_conntrack which indeed crashes because it assumes the existence of CTA_NAT_SEQ_UNSPEC to do the parsing. The CTA_NAT_SEQ_* attributes were introduced in 2.6.25. Signed-off-by: Pablo Neira Ayuso <pablo@netfilter.org> Signed-off-by: Patrick McHardy <kaber@trash.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16Phonet: improve GPRS variable namesRémi Denis-Courmont
Signed-off-by: Rémi Denis-Courmont <remi.denis-courmont@nokia.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16isdn: eicon: fix sparse warning: make global functions staticHannes Eder
Fix this sparse warnings by making the functions static: drivers/isdn/hardware/eicon/di.c:356:6: warning: symbol 'isdn_rc' was not declared. Should it be static? drivers/isdn/hardware/eicon/di.c:558:6: warning: symbol 'isdn_ind' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:595:6: warning: symbol 'api_parse' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:634:6: warning: symbol 'api_save_msg' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:666:6: warning: symbol 'api_load_msg' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:3417:6: warning: symbol 'manufacturer_req' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:3745:6: warning: symbol 'manufacturer_res' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:4077:6: warning: symbol 'control_rc' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:4743:6: warning: symbol 'data_rc' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:4779:6: warning: symbol 'data_ack' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:4805:6: warning: symbol 'sig_ind' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:6173:6: warning: symbol 'SendInfo' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:6349:6: warning: symbol 'SendMultiIE' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:6468:6: warning: symbol 'nl_ind' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:7250:6: warning: symbol 'get_plci' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:7409:6: warning: symbol 'add_d' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:7427:6: warning: symbol 'add_ai' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:7448:6: warning: symbol 'add_b1' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:7912:6: warning: symbol 'add_b23' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:8709:6: warning: symbol 'nl_req_ncci' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:8731:6: warning: symbol 'send_req' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:8866:6: warning: symbol 'listen_check' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:8909:6: warning: symbol 'IndParse' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:8994:6: warning: symbol 'ie_compare' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:9003:6: warning: symbol 'find_cip' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:9071:6: warning: symbol 'SetVoiceChannel' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:9089:6: warning: symbol 'VoiceChannelOff' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:9102:6: warning: symbol 'AdvCodecSupport' was not declared. Should it be static? drivers/isdn/hardware/eicon/message.c:9198:6: warning: symbol 'CodecIdCheck' was not declared. Should it be static? Signed-off-by: Hannes Eder <hannes@hanneseder.net> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16ipmr: merge common codeIlpo Järvinen
Also removes redundant skb->len < x check which can't be true once pskb_may_pull(skb, x) succeeded. $ diff-funcs pim_rcv ipmr.c ipmr.c pim_rcv_v1 --- ipmr.c:pim_rcv() +++ ipmr.c:pim_rcv_v1() @@ -1,22 +1,27 @@ -static int pim_rcv(struct sk_buff * skb) +int pim_rcv_v1(struct sk_buff * skb) { - struct pimreghdr *pim; + struct igmphdr *pim; struct iphdr *encap; struct net_device *reg_dev = NULL; if (!pskb_may_pull(skb, sizeof(*pim) + sizeof(*encap))) goto drop; - pim = (struct pimreghdr *)skb_transport_header(skb); - if (pim->type != ((PIM_VERSION<<4)|(PIM_REGISTER)) || - (pim->flags&PIM_NULL_REGISTER) || - (ip_compute_csum((void *)pim, sizeof(*pim)) != 0 && - csum_fold(skb_checksum(skb, 0, skb->len, 0)))) + pim = igmp_hdr(skb); + + if (!mroute_do_pim || + skb->len < sizeof(*pim) + sizeof(*encap) || + pim->group != PIM_V1_VERSION || pim->code != PIM_V1_REGISTER) goto drop; - /* check if the inner packet is destined to mcast group */ encap = (struct iphdr *)(skb_transport_header(skb) + - sizeof(struct pimreghdr)); + sizeof(struct igmphdr)); + /* + Check that: + a. packet is really destinted to a multicast group + b. packet is not a NULL-REGISTER + c. packet is not truncated + */ if (!ipv4_is_multicast(encap->daddr) || encap->tot_len == 0 || ntohs(encap->tot_len) + sizeof(*pim) > skb->len) @@ -40,9 +45,9 @@ skb->ip_summed = 0; skb->pkt_type = PACKET_HOST; dst_release(skb->dst); + skb->dst = NULL; reg_dev->stats.rx_bytes += skb->len; reg_dev->stats.rx_packets++; - skb->dst = NULL; nf_reset(skb); netif_rx(skb); dev_put(reg_dev); $ codiff net/ipv4/ipmr.o.old net/ipv4/ipmr.o.new net/ipv4/ipmr.c: pim_rcv_v1 | -283 pim_rcv | -284 2 functions changed, 567 bytes removed net/ipv4/ipmr.c: __pim_rcv | +307 1 function changed, 307 bytes added net/ipv4/ipmr.o.new: 3 functions changed, 307 bytes added, 567 bytes removed, diff: -260 (Tested on x86_64). It seems that pimlen arg could be left out as well and eq-sizedness of structs trapped with BUILD_BUG_ON but I don't think that's more than a cosmetic flaw since there aren't that many args anyway. Compile tested. Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16hp100: use roundup instead of open codingIlpo Järvinen
Signed-off-by: Ilpo Järvinen <ilpo.jarvinen@helsinki.fi> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-16cxgb3: Add multiple Tx queue support.Divy Le Ray
Implement NIC Tx multiqueue. Bump up driver version. Signed-off-by: Divy Le Ray <divy@chelsio.com> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-15e1000e: Add GRO supportHerbert Xu
This patch adds GRO support to e1000e by making it invoke napi_gro_receive instead of netif_receive_skb. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-15ethtool: Add GGRO and SGRO opsHerbert Xu
This patch adds the ethtool ops to enable and disable GRO. It also makes GRO depend on RX checksum offload much the same as how TSO depends on SG support. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-15tcp: Add GRO supportHerbert Xu
This patch adds the TCP-specific portion of GRO. The criterion for merging is extremely strict (the TCP header must match exactly apart from the checksum) so as to allow refragmentation. Otherwise this is pretty much identical to LRO, except that we support the merging of ECN packets. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-15net: Add skb_gro_receiveHerbert Xu
This patch adds the helper skb_gro_receive to merge packets for GRO. The current method is to allocate a new header skb and then chain the original packets to its frag_list. This is done to make it easier to integrate into the existing GSO framework. In future as GSO is moved into the drivers, we can undo this and simply chain the original packets together. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-15ipv4: Add GRO infrastructureHerbert Xu
This patch adds GRO support for IPv4. The criteria for merging is more stringent than LRO, in particular, we require all fields in the IP header to be identical except for the length, ID and checksum. In addition, the ID must form an arithmetic sequence with a difference of one. The ID requirement might seem overly strict, however, most hardware TSO solutions already obey this rule. Linux itself also obeys this whether GSO is in use or not. In future we could relax this rule by storing the IDs (or rather making sure that we don't drop them when pulling the aggregate skb's tail). Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-15net: Add Generic Receive Offload infrastructureHerbert Xu
This patch adds the top-level GRO (Generic Receive Offload) infrastructure. This is pretty similar to LRO except that this is protocol-independent. Instead of holding packets in an lro_mgr structure, they're now held in napi_struct. For drivers that intend to use this, they can set the NETIF_F_GRO bit and call napi_gro_receive instead of netif_receive_skb or just call netif_rx. The latter will call napi_receive_skb automatically. When napi_gro_receive is used, the driver must either call napi_complete/napi_rx_complete, or call napi_gro_flush in softirq context if the driver uses the primitives __napi_complete/__napi_rx_complete. Protocols will set the gro_receive and gro_complete function pointers in order to participate in this scheme. In addition to the packet, gro_receive will get a list of currently held packets. Each packet in the list has a same_flow field which is non-zero if it is a potential match for the new packet. For each packet that may match, they also have a flush field which is non-zero if the held packet must not be merged with the new packet. Once gro_receive has determined that the new skb matches a held packet, the held packet may be processed immediately if the new skb cannot be merged with it. In this case gro_receive should return the pointer to the existing skb in gro_list. Otherwise the new skb should be merged into the existing packet and NULL should be returned, unless the new skb makes it impossible for any further merges to be made (e.g., FIN packet) where the merged skb should be returned. Whenever the skb is merged into an existing entry, the gro_receive function should set NAPI_GRO_CB(skb)->same_flow. Note that if an skb merely matches an existing entry but can't be merged with it, then this shouldn't be set. If gro_receive finds it pointless to hold the new skb for future merging, it should set NAPI_GRO_CB(skb)->flush. Held packets will be flushed by napi_gro_flush which is called by napi_complete and napi_rx_complete. Currently held packets are stored in a singly liked list just like LRO. The list is limited to a maximum of 8 entries. In future, this may be expanded to use a hash table to allow more flows to be held for merging. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>
2008-12-15net: Add frag_list support to GSOHerbert Xu
This patch allows GSO to handle frag_list in a limited way for the purposes of allowing packets merged by GRO to be refragmented on output. Most hardware won't (and aren't expected to) support handling GRO frag_list packets directly. Therefore we will perform GSO in software for those cases. However, for drivers that can support it (such as virtual NICs) we may not have to segment the packets at all. Whether the added overhead of GRO/GSO is worthwhile for bridges and routers when weighed against the benefit of potentially increasing the MTU within the host is still an open question. However, for the case of host nodes this is undoubtedly a win. Signed-off-by: Herbert Xu <herbert@gondor.apana.org.au> Signed-off-by: David S. Miller <davem@davemloft.net>