- 09 Nov, 2018 40 commits
-
-
Florian Westphal authored
This adds inexact lists per destination network, stored in a search tree. Inexact lookups now return two 'candidate lists', the 'any' policies ('any' destionations), and a list of policies that share same daddr/prefix. Next patch will add a second search tree for 'saddr:any' policies so we can avoid placing those on the 'any:any' list too. Signed-off-by:Florian Westphal <fw@strlen.de> Acked-by:
David S. Miller <davem@davemloft.net> Signed-off-by:
Steffen Klassert <steffen.klassert@secunet.com>
-
Florian Westphal authored
At this time inexact policies are all searched in-order until the first match is found. After removal of the flow cache, this resolution has to be performed for every packetm resulting in major slowdown when number of inexact policies is high. This adds infrastructure to later sort inexact policies into a tree. This only introduces a single class: any:any. Next patch will add a search tree to pre-sort policies that have a fixed daddr/prefixlen, so in this patch the any:any class will still be used for all policies. Signed-off-by:
-
Florian Westphal authored
This avoids searches of polices that cannot match in the first place due to different interface id by placing them in different bins. Signed-off-by:
-
Florian Westphal authored
Switch packet-path lookups for inexact policies to rhashtable. In this initial version, we now no longer need to search policies with non-matching address family and type. Next patch will add the if_id as well so lookups from the xfrm interface driver only need to search inexact policies for that device. Future patches will augment the hlist in each rhash bucket with a tree and pre-sort policies according to daddr/prefix. A single rhashtable is used. In order to avoid a full rhashtable walk on netns exit, the bins get placed on a pernet list, i.e. we add almost no cost for network namespaces that had no xfrm policies. The inexact lists are kept in place, and policies are added to both the per-rhash-inexact list and a pernet one. The latter is needed for the control plane to handle migrate -- these requests do not consider the if_id, so if we'd remove the inexact_list now we would have to search all hash buckets and then figure out which matching policy candidate is the most recent one -- this appears a bit harder than just keeping the 'old' inexact list for this purpose. Signed-off-by:
-
Florian Westphal authored
currently policy_hash_bysel() returns the hash bucket list (for exact policies), or the inexact list (when policy uses a prefix). Searching this inexact list is slow, so it might be better to pre-sort inexact lists into a tree or another data structure for faster searching. However, due to 'any' policies, that need to be searched in any case, doing so will require that 'inexact' policies need to be handled specially to decide the best search strategy. So change hash_bysel() and return NULL if the policy can't be handled via the policy hash table. Right now, we simply use the inexact list when this happens, but future patch can then implement a different strategy. Signed-off-by:
-
Florian Westphal authored
... so we can reuse this later without code duplication when we add policy to a second inexact list. Signed-off-by:
-
Florian Westphal authored
currently all non-socket policies are either hashed in the dst table, or placed on the 'inexact list'. When flushing, we first walk the table, then the (per-direction) inexact lists. When we try and get rid of the inexact lists to having "n" inexact lists (e.g. per-af inexact lists, or sorted into a tree), this walk would become more complicated. Simplify this: walk the 'all' list and skip socket policies during traversal so we don't need to handle exact and inexact policies separately anymore. Signed-off-by:
-
Florian Westphal authored
add a script that adds a ipsec tunnel between two network namespaces plus following policies: .0/24 -> ipsec tunnel .240/28 -> bypass .253/32 -> ipsec tunnel Then check that .254 bypasses tunnel (match /28 exception), and .2 (match /24) and .253 (match direct policy) pass through the tunnel. Abuses iptables to check if ping did resolve an ipsec policy or not. Also adds a bunch of 'block' rules that are not supposed to match. Signed-off-by:
-
Edward Cree authored
As added in 3e59020a ("net: bql: add __netdev_tx_sent_queue()"), which see for performance rationale. Signed-off-by:
Edward Cree <ecree@solarflare.com> Reviewed-by:
Eric Dumazet <edumazet@google.com> Signed-off-by:
-
David S. Miller authored
Michał Mirosław says: ==================== net: Remove VLAN_TAG_PRESENT from drivers This series removes VLAN_TAG_PRESENT use from network drivers in preparation to removing its special meaning. ==================== Signed-off-by: -
Michał Mirosław authored
Reviewed-by:
Claudiu Manoil <claudiu.manoil@nxp.com> Signed-off-by:
Michał Mirosław <mirq-linux@rere.qmqm.pl> Signed-off-by:
-
Michał Mirosław authored
This is a minimal change to allow removing of VLAN_TAG_PRESENT. It leaves OVS unable to use CFI bit, as fixing this would need a deeper surgery involving userspace interface. Signed-off-by:
-
Michał Mirosław authored
This just removes VLAN_TAG_PRESENT use. VLAN TCI=0 special meaning is deeply embedded in the driver code and so is left as is. Signed-off-by:
-
Michał Mirosław authored
Signed-off-by:
-
Ilias Apalodimas authored
return -ENOMEM directly instead of assigning it in a variable Signed-off-by:
Ilias Apalodimas <ilias.apalodimas@linaro.org> Signed-off-by:
-
Ilias Apalodimas authored
Current driver dynamically allocates an skb and maps it as DMA Rx buffer. In order to prepare for upcoming XDP changes, let's introduce a different allocation scheme. Buffers are allocated dynamically and mapped into hardware. During the Rx operation the driver uses build_skb() to produce the necessary buffers for the network stack. This change increases performance ~15% on 64b packets with smmu disabled and ~5% with smmu enabled Signed-off-by:
-
Stefan Wahren authored
Interferences on the SPI line could distort the response of available buffer space. So at least we should check that the response doesn't exceed the maximum available buffer space. In error case increase a new error counter and retry it later. This behavior avoids buffer errors in the QCA7000, which results in an unnecessary chip reset including packet loss. Signed-off-by:
Stefan Wahren <stefan.wahren@i2se.com> Signed-off-by:
-
David Barmann authored
When setting the SO_MARK socket option, if the mark changes, the dst needs to be reset so that a new route lookup is performed. This fixes the case where an application wants to change routing by setting a new sk_mark. If this is done after some packets have already been sent, the dst is cached and has no effect. Signed-off-by:
David Barmann <david.barmann@stackpath.com> Reviewed-by:
-
David S. Miller authored
Julian Wiedmann says: ==================== s390/qeth: updates 2018-11-08 please apply the following qeth patches to net-next. The first patch allows one more device type to query the FW for a MAC address, the others are all basically just removal of duplicated or unused code. ==================== Signed-off-by: -
Julian Wiedmann authored
qeth_l3_setup_netdev() checks if the hsuid attribute is set on the qeth device, and propagates it to the net_device. In the past this was needed to pick up any hsuid that was set before allocation of the net_device. With commit d3d1b205 ("s390/qeth: allocate netdevice early") this is no longer necessary, qeth_l3_dev_hsuid_store() always stores the hsuid straight into dev->perm_addr. Signed-off-by:
Julian Wiedmann <jwi@linux.ibm.com> Signed-off-by:
-
Julian Wiedmann authored
If the CREATE ADDR sent by qeth_l3_iqd_read_initial_mac() fails, its callback sets a random MAC address on the net_device. The error then propagates back, and qeth_l3_setup_netdev() bails out without registering the net_device. Any subsequent call to qeth_l3_setup_netdev() will then attempt a fresh CREATE ADDR which either 1) also fails, or 2) sets a proper MAC address on the net_device. Consequently, the net_device will never be registered with a random MAC and we can drop the fallback code. Signed-off-by:
-
Julian Wiedmann authored
qeth_l3_send_ipa_arp_cmd() is merely a wrapper around qeth_send_control_data() now. So push the length adjustment into QETH_SETASS_BASE_LEN, and remove the wrapper. While at it, also remove some redundant 0-initializations. qeth_send_setassparms() requires that callers prepare their command parameters, so that they can be copied into the parameter area in one go. Skip the indirection, and just let callers set up the command themselves. Signed-off-by:
-
Julian Wiedmann authored
Call qeth_prepare_ipa_cmd() during setup of a new IPA cmd buffer, so that it is used for all commands. Thus ARP and SNMP requests don't have to do their own initialization. This will now also set the proper MPC protocol version for SNMP requests on L2 devices. Signed-off-by:
-
Julian Wiedmann authored
Re-implement the card-by-RDEV lookup by using device model concepts, and remove the now redundant list of all qeth card instances in the system. Signed-off-by:
-
Julian Wiedmann authored
Since commit 82bf5c08 ("s390/qeth: add support for IPv6 TSO"), qeth_xmit() also knows how to build TSO packets and is practically identical to qeth_l3_xmit(). Convert qeth_l3_xmit() into a thin wrapper that merely strips the L2 header off a packet, and calls qeth_xmit() for the actual TX processing. Signed-off-by:
-
Julian Wiedmann authored
Filling the HW header from one single function will make it easier to rip out all the duplicated transmit code in qeth_l3_xmit(). On top, this saves one conditional branch in the TSO path. Signed-off-by:
-
Julian Wiedmann authored
By default, READ MAC on a Layer2 OSD device returns the adapter's burnt-in MAC address. Given the default scenario of many virtual devices on the same adapter, qeth can't make any use of this address and therefore skips the READ MAC call for this device type. But in some configurations, the READ MAC command for a Layer2 OSD device actually returns a pre-provisioned, virtual MAC address. So enable the READ MAC code to detect this situation, and let the L2 subdriver call READ MAC for OSD devices. This also removes the QETH_LAYER2_MAC_READ flag, which protects L2 devices against calling READ MAC multiple times. Instead protect the whole call to qeth_l2_request_initial_mac(). Signed-off-by:
-
Li RongQing authored
if local is NULL pointer, and the following access of local's dev will trigger panic, which is same as BUG_ON Signed-off-by:
Li RongQing <lirongqing@baidu.com> Signed-off-by:
-
David S. Miller authored
Stefano Brivio says: ==================== ICMP error handling for UDP tunnels This series introduces ICMP error handling for UDP tunnels and encapsulations and related selftests. We need to handle ICMP errors to support PMTU discovery and route redirection -- this support is entirely missing right now: - patch 1/11 adds a socket lookup for UDP tunnels that use, by design, the same destination port on both endpoints -- i.e. VXLAN and GENEVE - patches 2/11 to 7/11 are specific to VxLAN and GENEVE - patches 8/11 and 9/11 add infrastructure for lookup of encapsulations where sent packets cannot be matched via receiving socket lookup, i.e. FoU and GUE - patches 10/11 and 11/11 are specific to FoU and GUE v2: changes are listed in the single patches ==================== Signed-off-by: -
Stefano Brivio authored
Introduce eight tests, for FoU and GUE, with IPv4 and IPv6 payload, on IPv4 and IPv6 transport, that check that PMTU exceptions are created with the right value when exceeding the MTU on a link of the path. Signed-off-by:
Stefano Brivio <sbrivio@redhat.com> Reviewed-by:
Sabrina Dubroca <sd@queasysnail.net> Signed-off-by:
-
Stefano Brivio authored
As the destination port in FoU and GUE receiving sockets doesn't necessarily match the remote destination port, we can't associate errors to the encapsulating tunnels with a socket lookup -- we need to blindly try them instead. This means we don't even know if we are handling errors for FoU or GUE without digging into the packets. Hence, implement a single handler for both, one for IPv4 and one for IPv6, that will check whether the packet that generated the ICMP error used a direct IP encapsulation or if it had a GUE header, and send the error to the matching protocol handler, if any. Signed-off-by:
-
Stefano Brivio authored
ICMP error handling is currently not possible for UDP tunnels not employing a receiving socket with local destination port matching the remote one, because we have no way to look them up. Add an err_handler tunnel encapsulation operation that can be exported by tunnels in order to pass the error to the protocol implementing the encapsulation. We can't easily use a lookup function as we did for VXLAN and GENEVE, as protocol error handlers, which would be in turn called by implementations of this new operation, handle the errors themselves, together with the tunnel lookup. Without a socket, we can't be sure which encapsulation error handler is the appropriate one: encapsulation handlers (the ones for FoU and GUE introduced in the next patch, e.g.) will need to check the new error codes returned by protocol handlers to figure out if errors match the given encapsulation, and, in turn, report this error back, so that we can try all of them in __udp{4,6}_lib_err_encap_no_sk() until we have a match. v2: - Name all arguments in err_handler prototypes (David Miller) Signed-off-by: -
Stefano Brivio authored
We'll need this to handle ICMP errors for tunnels without a sending socket (i.e. FoU and GUE). There, we might have to look up different types of IP tunnels, registered as network protocols, before we get a match, so we want this for the error handlers of IPPROTO_IPIP and IPPROTO_IPV6 in both inet_protos and inet6_protos. These error codes will be used in the next patch. For consistency, return sensible error codes in protocol error handlers whenever handlers can't handle errors because, even if valid, they don't match a protocol or any of its states. This has no effect on existing error handling paths. Signed-off-by:
-
Stefano Brivio authored
Use a router between endpoints, implemented via namespaces, set a low MTU between router and destination endpoint, exceed it and check PMTU value in route exceptions. v2: - Introduce IPv4 tests right away, if iproute2 doesn't support the 'df' link option they will be skipped (David Ahern) Signed-off-by:
-
Stefano Brivio authored
draft-ietf-nvo3-geneve-08 says: It is strongly RECOMMENDED that Path MTU Discovery ([RFC1191], [RFC1981]) be used by setting the DF bit in the IP header when Geneve packets are transmitted over IPv4 (this is the default with IPv6). Now that ICMP error handling is working for GENEVE, we can comply with this recommendation. Make this configurable, though, to avoid breaking existing setups. By default, DF won't be set. It can be set or inherited from inner IPv4 packets. If it's configured to be inherited and we are encapsulating IPv6, it will be set. This only applies to non-lwt tunnels: if an external control plane is used, tunnel key will still control the DF flag. v2: - DF behaviour configuration only applies for non-lwt tunnels, apply DF setting only if (!geneve->collect_md) in geneve_xmit_skb() (Stephen Hemminger) Signed-off-by:
-
Stefano Brivio authored
Export an encap_err_lookup() operation to match an ICMP error against a valid VNI. Signed-off-by:
-
Stefano Brivio authored
Use a router between endpoints, implemented via namespaces, set a low MTU between router and destination endpoint, exceed it and check PMTU value in route exceptions. v2: - Change all occurrences of VxLAN to VXLAN (Jiri Benc) - Introduce IPv4 tests right away, if iproute2 doesn't support the 'df' link option they will be skipped (David Ahern) Signed-off-by:
-
Stefano Brivio authored
Allow users to set the IPv4 DF bit in outgoing packets, or to inherit its value from the IPv4 inner header. If the encapsulated protocol is IPv6 and DF is configured to be inherited, always set it. For IPv4, inheriting DF from the inner header was probably intended from the very beginning judging by the comment to vxlan_xmit(), but it wasn't actually implemented -- also because it would have done more harm than good, without handling for ICMP Fragmentation Needed messages. According to RFC 7348, "Path MTU discovery MAY be used". An expired RFC draft, draft-saum-nvo3-pmtud-over-vxlan-05, whose purpose was to describe PMTUD implementation, says that "is a MUST that Vxlan gateways [...] SHOULD set the DF-bit [...]", whatever that means. Given this background, the only sane option is probably to let the user decide, and keep the current behaviour as default. This only applies to non-lwt tunnels: if an external control plane is used, tunnel key will still control the DF flag. v2: - DF behaviour configuration only applies for non-lwt tunnels, move DF setting to if (!info) block in vxlan_xmit_one() (Stephen Hemminger) Signed-off-by:
-
Stefano Brivio authored
Export an encap_err_lookup() operation to match an ICMP error against a valid VNI. Signed-off-by:
-
Stefano Brivio authored
For both IPv4 and IPv6, if we can't match errors to a socket, try tunnels before ignoring them. Look up a socket with the original source and destination ports as found in the UDP packet inside the ICMP payload, this will work for tunnels that force the same destination port for both endpoints, i.e. VXLAN and GENEVE. Actually, lwtunnels could break this assumption if they are configured by an external control plane to have different destination ports on the endpoints: in this case, we won't be able to trace ICMP messages back to them. For IPv6 redirect messages, call ip6_redirect() directly with the output interface argument set to the interface we received the packet from (as it's the very interface we should build the exception on), otherwise the new nexthop will be rejected. There's no such need for IPv4. Tunnels can now export an encap_err_lookup() operation that indicates a match. Pass the packet to the lookup function, and if the tunnel driver reports a matching association, continue with regular ICMP error handling. v2: - Added newline between network and transport header sets in __udp{4,6}_lib_err_encap() (David Miller) - Removed redundant skb_reset_network_header(skb); in __udp4_lib_err_encap() - Removed redundant reassignment of iph in __udp4_lib_err_encap() (Sabrina Dubroca) - Edited comment to __udp{4,6}_lib_err_encap() to reflect the fact this won't work with lwtunnels configured to use asymmetric ports. By the way, it's VXLAN, not VxLAN (Jiri Benc) Signed-off-by:
-
