diff --git a/go.mod b/go.mod index 80015949c..af7633af2 100644 --- a/go.mod +++ b/go.mod @@ -8,6 +8,9 @@ replace ( k8s.io/kube-openapi => k8s.io/kube-openapi v0.0.0-20200121204235-bf4fb3bd569c ) +// TODO: Remove this when https://github.com/vishvananda/netlink/pull/554 is merged +replace github.com/vishvananda/netlink => github.com/twelho/netlink v1.1.1-ageing + require ( github.com/alessio/shellescape v1.2.2 github.com/c2h5oh/datasize v0.0.0-20200112174442-28bbd4740fee @@ -50,7 +53,9 @@ require ( github.com/syndtr/gocapability v0.0.0-20180916011248-d98352740cb2 // indirect github.com/vishvananda/netlink v1.1.0 github.com/weaveworks/libgitops v0.0.0-20200611103311-2c871bbbbf0c - golang.org/x/crypto v0.0.0-20200406173513-056763e48d71 + golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9 + golang.org/x/net v0.0.0-20200625001655-4c5254603344 // indirect + golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208 // indirect golang.org/x/sys v0.0.0-20200610111108-226ff32320da gotest.tools v2.2.0+incompatible k8s.io/apimachinery v0.18.3 diff --git a/go.sum b/go.sum index 7ba485003..7b4d87b51 100644 --- a/go.sum +++ b/go.sum @@ -713,6 +713,8 @@ github.com/tidwall/pretty v1.0.0/go.mod h1:XNkn88O1ChpSDQmQeStsy+sBenx6DDtFZJxhV github.com/timakin/bodyclose v0.0.0-20190930140734-f7f2e9bca95e/go.mod h1:Qimiffbc6q9tBWlVV6x0P9sat/ao1xEkREYPPj9hphk= github.com/tmc/grpc-websocket-proxy v0.0.0-20170815181823-89b8d40f7ca8/go.mod h1:ncp9v5uamzpCO7NfCPTXjqaC+bZgJeR0sMTm6dMHP7U= github.com/tmc/grpc-websocket-proxy v0.0.0-20190109142713-0ad062ec5ee5/go.mod h1:ncp9v5uamzpCO7NfCPTXjqaC+bZgJeR0sMTm6dMHP7U= +github.com/twelho/netlink v1.1.1-ageing h1:A5/0WIegqA+Br6hXHqma4MN+bmnWWrZG91LRuveV+Xk= +github.com/twelho/netlink v1.1.1-ageing/go.mod h1:FSQhuTO7eHT34mPzX+B04SUAjiqLxtXs1et0S6l9k4k= github.com/ugorji/go v1.1.4/go.mod h1:uQMGLiO92mf5W77hV/PUCpI3pbzQx3CRekS0kk+RGrc= github.com/ugorji/go/codec v0.0.0-20181204163529-d75b2dcb6bc8/go.mod h1:VFNgLljTbGfSG7qAOspJ7OScBnGdDN/yBr0sguwnwf0= github.com/ulikunitz/xz v0.5.5/go.mod h1:2bypXElzHzzJZwzH67Y6wb67pO62Rzfn7BSiF4ABRW8= @@ -728,9 +730,6 @@ github.com/valyala/fasttemplate v1.0.1/go.mod h1:UQGH1tvbgY+Nz5t2n7tXsz52dQxojPU github.com/valyala/quicktemplate v1.2.0/go.mod h1:EH+4AkTd43SvgIbQHYu59/cJyxDoOVRUAfrukLPuGJ4= github.com/valyala/tcplisten v0.0.0-20161114210144-ceec8f93295a/go.mod h1:v3UYOV9WzVtRmSR+PDvWpU/qWl4Wa5LApYYX4ZtKbio= github.com/vektah/gqlparser v1.1.2/go.mod h1:1ycwN7Ij5njmMkPPAOaRFY4rET2Enx7IkVv3vaXspKw= -github.com/vishvananda/netlink v0.0.0-20181108222139-023a6dafdcdf/go.mod h1:+SR5DhBJrl6ZM7CoCKvpw5BKroDKQ+PJqOg65H/2ktk= -github.com/vishvananda/netlink v1.1.0 h1:1iyaYNBLmP6L0220aDnYQpo1QEV4t4hJ+xEEhhJH8j0= -github.com/vishvananda/netlink v1.1.0/go.mod h1:cTgwzPIzzgDAYoQrMm0EdrjRUBkTqKYppBueQtXaqoE= github.com/vishvananda/netns v0.0.0-20180720170159-13995c7128cc/go.mod h1:ZjcWmFBXmLKZu9Nxj3WKYEafiSqer2rnvPr0en9UNpI= github.com/vishvananda/netns v0.0.0-20191106174202-0a2b9b5464df h1:OviZH7qLw/7ZovXvuNyL3XQl8UFofeikI1NW1Gypu7k= github.com/vishvananda/netns v0.0.0-20191106174202-0a2b9b5464df/go.mod h1:JP3t17pCcGlemwknint6hfoeCVQrEMVwxRLRjXpq+BU= @@ -787,8 +786,8 @@ golang.org/x/crypto v0.0.0-20191011191535-87dc89f01550/go.mod h1:yigFU9vqHzYiE8U golang.org/x/crypto v0.0.0-20200128174031-69ecbb4d6d5d/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= golang.org/x/crypto v0.0.0-20200220183623-bac4c82f6975/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= golang.org/x/crypto v0.0.0-20200302210943-78000ba7a073/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= -golang.org/x/crypto v0.0.0-20200406173513-056763e48d71 h1:DOmugCavvUtnUD114C1Wh+UgTgQZ4pMLzXxi1pSt+/Y= -golang.org/x/crypto v0.0.0-20200406173513-056763e48d71/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= +golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9 h1:psW17arqaxU48Z5kZ0CQnkZWQJsqcURM6tKiBApRjXI= +golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9/go.mod h1:LzIPMQfyMNhhGPhUkYOs5KpL4U8rLKemX1yGLhDgUto= golang.org/x/exp v0.0.0-20190121172915-509febef88a4/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA= golang.org/x/exp v0.0.0-20190125153040-c74c464bbbf2/go.mod h1:CJ0aWSM057203Lf6IL+f9T1iT9GByDxfZKAQTCR3kQA= golang.org/x/exp v0.0.0-20190312203227-4b39c73a6495/go.mod h1:ZjyILWgesfNpC6sMxTJOJm9Kp84zZh5NQWvqDGG3Qr8= @@ -828,6 +827,8 @@ golang.org/x/net v0.0.0-20191004110552-13f9640d40b9/go.mod h1:z5CRVTTTmAJ677TzLL golang.org/x/net v0.0.0-20200226121028-0de0cce0169b/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= golang.org/x/net v0.0.0-20200301022130-244492dfa37a h1:GuSPYbZzB5/dcLNCwLQLsg3obCJtX9IJhpXkvY7kzk0= golang.org/x/net v0.0.0-20200301022130-244492dfa37a/go.mod h1:z5CRVTTTmAJ677TzLLGU+0bjPO0LkuOLi4/5GtJWs/s= +golang.org/x/net v0.0.0-20200625001655-4c5254603344 h1:vGXIOMxbNfDTk/aXCmfdLgkrSV+Z2tcbze+pEc3v5W4= +golang.org/x/net v0.0.0-20200625001655-4c5254603344/go.mod h1:/O7V0waA8r7cgGh81Ro3o1hOxt32SMVPicZroKQ2sZA= golang.org/x/oauth2 v0.0.0-20180821212333-d2e6202438be/go.mod h1:N/0e6XlmueqKjAGxoOufVs8QHGRruUQn6yWY3a++T0U= golang.org/x/oauth2 v0.0.0-20190226205417-e64efc72b421/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw= golang.org/x/oauth2 v0.0.0-20190604053449-0f29369cfe45/go.mod h1:gOpvHmFTYa4IltrdGE7lF6nIHvwfUNPOp7c8zoXwtLw= @@ -838,6 +839,8 @@ golang.org/x/sync v0.0.0-20190227155943-e225da77a7e6/go.mod h1:RxMgew5VJxzue5/jJ golang.org/x/sync v0.0.0-20190423024810-112230192c58/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e h1:vcxGaoTs7kV8m5Np9uUNQin4BrLOthgV7252N8V+FwY= golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= +golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208 h1:qwRHBd0NqMbJxfbotnDhm2ByMI1Shq4Y6oRJo21SGJA= +golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208/go.mod h1:RxMgew5VJxzue5/jJTE5uejpjVlOe/izrB70Jof72aM= golang.org/x/sys v0.0.0-20170830134202-bb24a47a89ea/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= golang.org/x/sys v0.0.0-20180830151530-49385e6e1522/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= golang.org/x/sys v0.0.0-20180905080454-ebe1bf3edb33/go.mod h1:STP8DvDyc/dI5b8T5hshtkjS+E42TnysNCUPdjciGhY= @@ -859,7 +862,6 @@ golang.org/x/sys v0.0.0-20190422165155-953cdadca894/go.mod h1:h1NjWce9XRLGQEsW7w golang.org/x/sys v0.0.0-20190502145724-3ef323f4f1fd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190514135907-3a4b5fb9f71f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190602015325-4c4f7f33c9ed/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= -golang.org/x/sys v0.0.0-20190606203320-7fc4e5ec1444/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190616124812-15dcb6c0061f/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190813064441-fde4db37ae7a/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20190826190057-c7b8b68b1456/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= @@ -871,8 +873,10 @@ golang.org/x/sys v0.0.0-20191022100944-742c48ecaeb7/go.mod h1:h1NjWce9XRLGQEsW7w golang.org/x/sys v0.0.0-20191120155948-bd437916bb0e/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20191210023423-ac6580df4449/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20200120151820-655fe14d7479/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20200121082415-34d275377bf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20200122134326-e047566fdf82/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20200302150141-5c8b2ff67527/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20200323222414-85ca7c5b95cd/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/sys v0.0.0-20200610111108-226ff32320da h1:bGb80FudwxpeucJUjPYJXuJ8Hk91vNtfvrymzwiei38= golang.org/x/sys v0.0.0-20200610111108-226ff32320da/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= golang.org/x/text v0.0.0-20160726164857-2910a502d2bf/go.mod h1:NqM8EUOU14njkJ3fqMW+pc6Ldnwhi/IjpwHt7yyuwOQ= diff --git a/pkg/container/network.go b/pkg/container/network.go index be809f626..3746d2bf5 100644 --- a/pkg/container/network.go +++ b/pkg/container/network.go @@ -112,44 +112,33 @@ func networkSetup(dhcpIfaces *[]DHCPInterface) (bool, error) { } // bridge creates the TAP device and performs the bridging, returning the base configuration for a DHCP server -func bridge(iface *net.Interface) (d *DHCPInterface, err error) { +func bridge(iface *net.Interface) (*DHCPInterface, error) { tapName := constants.TAP_PREFIX + iface.Name bridgeName := constants.BRIDGE_PREFIX + iface.Name - var handle *netlink.Handle - var bridge *netlink.Bridge - var tuntap, link netlink.Link - - if handle, err = netlink.NewHandle(); err != nil { - return - } - - if tuntap, err = createTAPAdapter(tapName); err != nil { - return - } - - if bridge, err = createBridge(bridgeName); err != nil { - return + eth, err := netlink.LinkByIndex(iface.Index) + if err != nil { + return nil, err } - if err = handle.LinkSetMaster(tuntap, bridge); err != nil { - return + tuntap, err := createTAPAdapter(tapName) + if err != nil { + return nil, err } - if link, err = netlink.LinkByName(iface.Name); err != nil { - return + bridge, err := createBridge(bridgeName) + if err != nil { + return nil, err } - if err = handle.LinkSetMaster(link, bridge); err != nil { - return + if err := setMaster(bridge, tuntap, eth); err != nil { + return nil, err } - d = &DHCPInterface{ + return &DHCPInterface{ VMTAP: tapName, Bridge: bridgeName, - } - - return + }, nil } // takeAddress removes the first address of an interface and returns it @@ -160,11 +149,6 @@ func takeAddress(iface *net.Interface) (*net.IPNet, bool, error) { return nil, true, fmt.Errorf("interface %q has no address", iface.Name) } - handle, err := netlink.NewHandle() - if err != nil { - return nil, false, fmt.Errorf("failed to acquire handle on network namespace: %v", err) - } - for _, addr := range addrs { var ip net.IP var mask net.IPMask @@ -197,7 +181,7 @@ func takeAddress(iface *net.Interface) (*net.IPNet, bool, error) { return nil, false, fmt.Errorf("failed to parse address from stringified IP %q: %v", addr.String(), err) } - if err = handle.AddrDel(link, delAddr); err != nil { + if err = netlink.AddrDel(link, delAddr); err != nil { return nil, false, fmt.Errorf("failed to remove address from interface %q: %v", iface.Name, err) } @@ -212,6 +196,7 @@ func takeAddress(iface *net.Interface) (*net.IPNet, bool, error) { return nil, false, fmt.Errorf("interface %s has no valid addresses", iface.Name) } +// createTAPAdapter creates a new TAP device with the given name func createTAPAdapter(tapName string) (*netlink.Tuntap, error) { la := netlink.NewLinkAttrs() la.Name = tapName @@ -222,13 +207,22 @@ func createTAPAdapter(tapName string) (*netlink.Tuntap, error) { return tuntap, addLink(tuntap) } +// createBridge creates a new bridge device with the given name func createBridge(bridgeName string) (*netlink.Bridge, error) { la := netlink.NewLinkAttrs() la.Name = bridgeName - bridge := &netlink.Bridge{LinkAttrs: la} + + // Disable MAC address age tracking. This causes issues in the container, + // the bridge is unable to resolve MACs from outside resulting in it never + // establishing the internal routes. This "optimization" is only really useful + // with more than two interfaces attached to the bridge anyways, so we're not + // taking any performance hit by disabling it here. + ageingTime := uint32(0) + bridge := &netlink.Bridge{LinkAttrs: la, AgeingTime: &ageingTime} return bridge, addLink(bridge) } +// addLink creates the given link and brings it up func addLink(link netlink.Link) (err error) { if err = netlink.LinkAdd(link); err == nil { err = netlink.LinkSetUp(link) @@ -237,6 +231,47 @@ func addLink(link netlink.Link) (err error) { return } +// This is a MAC address persistence workaround, netlink.LinkSetMaster{,ByIndex}() +// has a bug that arbitrarily changes the MAC addresses of the bridge and virtual +// device to be bound to it. TODO: Remove when fixed upstream +func setMaster(master netlink.Link, links ...netlink.Link) error { + masterIndex := master.Attrs().Index + masterMAC, err := getMAC(master) + if err != nil { + return err + } + + for _, link := range links { + mac, err := getMAC(link) + if err != nil { + return err + } + + if err = netlink.LinkSetMasterByIndex(link, masterIndex); err != nil { + return err + } + + if err = netlink.LinkSetHardwareAddr(link, mac); err != nil { + return err + } + } + + return netlink.LinkSetHardwareAddr(master, masterMAC) +} + +// getMAC fetches the generated MAC address for the given link +func getMAC(link netlink.Link) (addr net.HardwareAddr, err error) { + // The attributes of the netlink.Link passed to this function do not contain HardwareAddr + // as it is expected to be generated by the networking subsystem. Thus, "reload" the Link + // by querying it to retrieve the generated attributes after the link has been created. + if link, err = netlink.LinkByIndex(link.Attrs().Index); err != nil { + return + } + + addr = link.Attrs().HardwareAddr + return +} + func maskString(mask net.IPMask) string { if len(mask) < 4 { return "" diff --git a/vendor/github.com/vishvananda/netlink/addr.go b/vendor/github.com/vishvananda/netlink/addr.go index f08c95696..653f540db 100644 --- a/vendor/github.com/vishvananda/netlink/addr.go +++ b/vendor/github.com/vishvananda/netlink/addr.go @@ -17,6 +17,7 @@ type Addr struct { Broadcast net.IP PreferedLft int ValidLft int + LinkIndex int } // String returns $ip/$netmask $label diff --git a/vendor/github.com/vishvananda/netlink/addr_linux.go b/vendor/github.com/vishvananda/netlink/addr_linux.go index 28746d5af..71da251ca 100644 --- a/vendor/github.com/vishvananda/netlink/addr_linux.go +++ b/vendor/github.com/vishvananda/netlink/addr_linux.go @@ -11,9 +11,6 @@ import ( "golang.org/x/sys/unix" ) -// IFA_FLAGS is a u32 attribute. -const IFA_FLAGS = 0x8 - // AddrAdd will add an IP address to a link device. // // Equivalent to: `ip addr add $addr dev $link` @@ -125,7 +122,7 @@ func (h *Handle) addrHandle(link Link, addr *Addr, req *nl.NetlinkRequest) error } else { b := make([]byte, 4) native.PutUint32(b, uint32(addr.Flags)) - flagsData := nl.NewRtAttr(IFA_FLAGS, b) + flagsData := nl.NewRtAttr(unix.IFA_FLAGS, b) req.AddData(flagsData) } } @@ -156,10 +153,10 @@ func (h *Handle) addrHandle(link Link, addr *Addr, req *nl.NetlinkRequest) error // value should be "forever". To compensate for that, only add the attributes if at least one of the values is // non-zero, which means the caller has explicitly set them if addr.ValidLft > 0 || addr.PreferedLft > 0 { - cachedata := nl.IfaCacheInfo{ - IfaValid: uint32(addr.ValidLft), - IfaPrefered: uint32(addr.PreferedLft), - } + cachedata := nl.IfaCacheInfo{unix.IfaCacheinfo{ + Valid: uint32(addr.ValidLft), + Prefered: uint32(addr.PreferedLft), + }} req.AddData(nl.NewRtAttr(unix.IFA_CACHEINFO, cachedata.Serialize())) } @@ -196,12 +193,12 @@ func (h *Handle) AddrList(link Link, family int) ([]Addr, error) { var res []Addr for _, m := range msgs { - addr, msgFamily, ifindex, err := parseAddr(m) + addr, msgFamily, err := parseAddr(m) if err != nil { return res, err } - if link != nil && ifindex != indexFilter { + if link != nil && addr.LinkIndex != indexFilter { // Ignore messages from other interfaces continue } @@ -216,11 +213,11 @@ func (h *Handle) AddrList(link Link, family int) ([]Addr, error) { return res, nil } -func parseAddr(m []byte) (addr Addr, family, index int, err error) { +func parseAddr(m []byte) (addr Addr, family int, err error) { msg := nl.DeserializeIfAddrmsg(m) family = -1 - index = -1 + addr.LinkIndex = -1 attrs, err1 := nl.ParseRouteAttr(m[msg.Len():]) if err1 != nil { @@ -229,7 +226,7 @@ func parseAddr(m []byte) (addr Addr, family, index int, err error) { } family = int(msg.Family) - index = int(msg.Index) + addr.LinkIndex = int(msg.Index) var local, dst *net.IPNet for _, attr := range attrs { @@ -254,12 +251,12 @@ func parseAddr(m []byte) (addr Addr, family, index int, err error) { addr.Broadcast = attr.Value case unix.IFA_LABEL: addr.Label = string(attr.Value[:len(attr.Value)-1]) - case IFA_FLAGS: + case unix.IFA_FLAGS: addr.Flags = int(native.Uint32(attr.Value[0:4])) - case nl.IFA_CACHEINFO: + case unix.IFA_CACHEINFO: ci := nl.DeserializeIfaCacheInfo(attr.Value) - addr.PreferedLft = int(ci.IfaPrefered) - addr.ValidLft = int(ci.IfaValid) + addr.PreferedLft = int(ci.Prefered) + addr.ValidLft = int(ci.Valid) } } @@ -394,7 +391,7 @@ func addrSubscribeAt(newNs, curNs netns.NsHandle, ch chan<- AddrUpdate, done <-c continue } - addr, _, ifindex, err := parseAddr(m.Data) + addr, _, err := parseAddr(m.Data) if err != nil { if cberr != nil { cberr(fmt.Errorf("could not parse address: %v", err)) @@ -403,7 +400,7 @@ func addrSubscribeAt(newNs, curNs netns.NsHandle, ch chan<- AddrUpdate, done <-c } ch <- AddrUpdate{LinkAddress: *addr.IPNet, - LinkIndex: ifindex, + LinkIndex: addr.LinkIndex, NewAddr: msgType == unix.RTM_NEWADDR, Flags: addr.Flags, Scope: addr.Scope, diff --git a/vendor/github.com/vishvananda/netlink/class.go b/vendor/github.com/vishvananda/netlink/class.go index dcc22d9e9..10ceffed8 100644 --- a/vendor/github.com/vishvananda/netlink/class.go +++ b/vendor/github.com/vishvananda/netlink/class.go @@ -132,7 +132,10 @@ func (class *GenericClass) Type() string { return class.ClassType } -// ServiceCurve is the way the HFSC curve are represented +// ServiceCurve is a nondecreasing function of some time unit, returning the amount of service +// (an allowed or allocated amount of bandwidth) at some specific point in time. The purpose of it +// should be subconsciously obvious: if a class was allowed to transfer not less than the amount +// specified by its service curve, then the service curve is not violated. type ServiceCurve struct { m1 uint32 d uint32 @@ -144,6 +147,21 @@ func (c *ServiceCurve) Attrs() (uint32, uint32, uint32) { return c.m1, c.d, c.m2 } +// Burst returns the burst rate (m1) of the curve +func (c *ServiceCurve) Burst() uint32 { + return c.m1 +} + +// Delay return the delay (d) of the curve +func (c *ServiceCurve) Delay() uint32 { + return c.d +} + +// Rate returns the rate (m2) of the curve +func (c *ServiceCurve) Rate() uint32 { + return c.m2 +} + // HfscClass is a representation of the HFSC class type HfscClass struct { ClassAttrs @@ -152,35 +170,44 @@ type HfscClass struct { Usc ServiceCurve } -// SetUsc sets the Usc curve +// SetUsc sets the USC curve. The bandwidth (m1 and m2) is specified in bits and the delay in +// seconds. func (hfsc *HfscClass) SetUsc(m1 uint32, d uint32, m2 uint32) { - hfsc.Usc = ServiceCurve{m1: m1 / 8, d: d, m2: m2 / 8} + hfsc.Usc = ServiceCurve{m1: m1, d: d, m2: m2} } -// SetFsc sets the Fsc curve +// SetFsc sets the Fsc curve. The bandwidth (m1 and m2) is specified in bits and the delay in +// seconds. func (hfsc *HfscClass) SetFsc(m1 uint32, d uint32, m2 uint32) { - hfsc.Fsc = ServiceCurve{m1: m1 / 8, d: d, m2: m2 / 8} + hfsc.Fsc = ServiceCurve{m1: m1, d: d, m2: m2} } -// SetRsc sets the Rsc curve +// SetRsc sets the Rsc curve. The bandwidth (m1 and m2) is specified in bits and the delay in +// seconds. func (hfsc *HfscClass) SetRsc(m1 uint32, d uint32, m2 uint32) { - hfsc.Rsc = ServiceCurve{m1: m1 / 8, d: d, m2: m2 / 8} + hfsc.Rsc = ServiceCurve{m1: m1, d: d, m2: m2} } -// SetSC implements the SC from the tc CLI +// SetSC implements the SC from the `tc` CLI. This function behaves the same as if one would set the +// USC through the `tc` command-line tool. This means bandwidth (m1 and m2) is specified in bits and +// the delay in ms. func (hfsc *HfscClass) SetSC(m1 uint32, d uint32, m2 uint32) { - hfsc.Rsc = ServiceCurve{m1: m1 / 8, d: d, m2: m2 / 8} - hfsc.Fsc = ServiceCurve{m1: m1 / 8, d: d, m2: m2 / 8} + hfsc.SetRsc(m1, d, m2) + hfsc.SetFsc(m1, d, m2) } -// SetUL implements the UL from the tc CLI +// SetUL implements the UL from the `tc` CLI. This function behaves the same as if one would set the +// USC through the `tc` command-line tool. This means bandwidth (m1 and m2) is specified in bits and +// the delay in ms. func (hfsc *HfscClass) SetUL(m1 uint32, d uint32, m2 uint32) { - hfsc.Usc = ServiceCurve{m1: m1 / 8, d: d, m2: m2 / 8} + hfsc.SetUsc(m1, d, m2) } -// SetLS implements the LS from the tc CLI +// SetLS implements the LS from the `tc` CLI. This function behaves the same as if one would set the +// USC through the `tc` command-line tool. This means bandwidth (m1 and m2) is specified in bits and +// the delay in ms. func (hfsc *HfscClass) SetLS(m1 uint32, d uint32, m2 uint32) { - hfsc.Fsc = ServiceCurve{m1: m1 / 8, d: d, m2: m2 / 8} + hfsc.SetFsc(m1, d, m2) } // NewHfscClass returns a new HFSC struct with the set parameters @@ -193,6 +220,7 @@ func NewHfscClass(attrs ClassAttrs) *HfscClass { } } +// String() returns a string that contains the information and attributes of the HFSC class func (hfsc *HfscClass) String() string { return fmt.Sprintf( "{%s -- {RSC: {m1=%d d=%d m2=%d}} {FSC: {m1=%d d=%d m2=%d}} {USC: {m1=%d d=%d m2=%d}}}", diff --git a/vendor/github.com/vishvananda/netlink/class_linux.go b/vendor/github.com/vishvananda/netlink/class_linux.go index 31091e501..1545455e8 100644 --- a/vendor/github.com/vishvananda/netlink/class_linux.go +++ b/vendor/github.com/vishvananda/netlink/class_linux.go @@ -179,12 +179,15 @@ func classPayload(req *nl.NetlinkRequest, class Class) error { case "hfsc": hfsc := class.(*HfscClass) opt := nl.HfscCopt{} - opt.Rsc.Set(hfsc.Rsc.Attrs()) - opt.Fsc.Set(hfsc.Fsc.Attrs()) - opt.Usc.Set(hfsc.Usc.Attrs()) - options.AddRtAttr(nl.TCA_HFSC_RSC, nl.SerializeHfscCurve(&opt.Rsc)) - options.AddRtAttr(nl.TCA_HFSC_FSC, nl.SerializeHfscCurve(&opt.Fsc)) - options.AddRtAttr(nl.TCA_HFSC_USC, nl.SerializeHfscCurve(&opt.Usc)) + rm1, rd, rm2 := hfsc.Rsc.Attrs() + opt.Rsc.Set(rm1/8, rd, rm2/8) + fm1, fd, fm2 := hfsc.Fsc.Attrs() + opt.Fsc.Set(fm1/8, fd, fm2/8) + um1, ud, um2 := hfsc.Usc.Attrs() + opt.Usc.Set(um1/8, ud, um2/8) + nl.NewRtAttrChild(options, nl.TCA_HFSC_RSC, nl.SerializeHfscCurve(&opt.Rsc)) + nl.NewRtAttrChild(options, nl.TCA_HFSC_FSC, nl.SerializeHfscCurve(&opt.Fsc)) + nl.NewRtAttrChild(options, nl.TCA_HFSC_USC, nl.SerializeHfscCurve(&opt.Usc)) } req.AddData(options) return nil @@ -315,11 +318,11 @@ func parseHfscClassData(class Class, data []syscall.NetlinkRouteAttr) (bool, err m1, d, m2 := nl.DeserializeHfscCurve(datum.Value).Attrs() switch datum.Attr.Type { case nl.TCA_HFSC_RSC: - hfsc.Rsc = ServiceCurve{m1: m1, d: d, m2: m2} + hfsc.Rsc = ServiceCurve{m1: m1 * 8, d: d, m2: m2 * 8} case nl.TCA_HFSC_FSC: - hfsc.Fsc = ServiceCurve{m1: m1, d: d, m2: m2} + hfsc.Fsc = ServiceCurve{m1: m1 * 8, d: d, m2: m2 * 8} case nl.TCA_HFSC_USC: - hfsc.Usc = ServiceCurve{m1: m1, d: d, m2: m2} + hfsc.Usc = ServiceCurve{m1: m1 * 8, d: d, m2: m2 * 8} } } return detailed, nil diff --git a/vendor/github.com/vishvananda/netlink/conntrack_linux.go b/vendor/github.com/vishvananda/netlink/conntrack_linux.go index 4bff0dcba..ab91f4e55 100644 --- a/vendor/github.com/vishvananda/netlink/conntrack_linux.go +++ b/vendor/github.com/vishvananda/netlink/conntrack_linux.go @@ -318,18 +318,25 @@ func parseRawData(data []byte) *ConntrackFlow { // --mask-src ip Source mask address // --mask-dst ip Destination mask address +// Layer 4 Protocol common parameters and options: +// TCP, UDP, SCTP, UDPLite and DCCP +// --sport, --orig-port-src port Source port in original direction +// --dport, --orig-port-dst port Destination port in original direction + // Filter types type ConntrackFilterType uint8 const ( - ConntrackOrigSrcIP = iota // -orig-src ip Source address from original direction - ConntrackOrigDstIP // -orig-dst ip Destination address from original direction - ConntrackReplySrcIP // --reply-src ip Reply Source IP - ConntrackReplyDstIP // --reply-dst ip Reply Destination IP - ConntrackReplyAnyIP // Match source or destination reply IP - ConntrackNatSrcIP = ConntrackReplySrcIP // deprecated use instead ConntrackReplySrcIP - ConntrackNatDstIP = ConntrackReplyDstIP // deprecated use instead ConntrackReplyDstIP - ConntrackNatAnyIP = ConntrackReplyAnyIP // deprecated use instaed ConntrackReplyAnyIP + ConntrackOrigSrcIP = iota // -orig-src ip Source address from original direction + ConntrackOrigDstIP // -orig-dst ip Destination address from original direction + ConntrackReplySrcIP // --reply-src ip Reply Source IP + ConntrackReplyDstIP // --reply-dst ip Reply Destination IP + ConntrackReplyAnyIP // Match source or destination reply IP + ConntrackOrigSrcPort // --orig-port-src port Source port in original direction + ConntrackOrigDstPort // --orig-port-dst port Destination port in original direction + ConntrackNatSrcIP = ConntrackReplySrcIP // deprecated use instead ConntrackReplySrcIP + ConntrackNatDstIP = ConntrackReplyDstIP // deprecated use instead ConntrackReplyDstIP + ConntrackNatAnyIP = ConntrackReplyAnyIP // deprecated use instead ConntrackReplyAnyIP ) type CustomConntrackFilter interface { @@ -339,7 +346,9 @@ type CustomConntrackFilter interface { } type ConntrackFilter struct { - ipFilter map[ConntrackFilterType]net.IP + ipFilter map[ConntrackFilterType]net.IP + portFilter map[ConntrackFilterType]uint16 + protoFilter uint8 } // AddIP adds an IP to the conntrack filter @@ -354,38 +363,89 @@ func (f *ConntrackFilter) AddIP(tp ConntrackFilterType, ip net.IP) error { return nil } +// AddPort adds a Port to the conntrack filter if the Layer 4 protocol allows it +func (f *ConntrackFilter) AddPort(tp ConntrackFilterType, port uint16) error { + switch f.protoFilter { + // TCP, UDP, DCCP, SCTP, UDPLite + case 6, 17, 33, 132, 136: + default: + return fmt.Errorf("Filter attribute not available without a valid Layer 4 protocol: %d", f.protoFilter) + } + + if f.portFilter == nil { + f.portFilter = make(map[ConntrackFilterType]uint16) + } + if _, ok := f.portFilter[tp]; ok { + return errors.New("Filter attribute already present") + } + f.portFilter[tp] = port + return nil +} + +// AddProtocol adds the Layer 4 protocol to the conntrack filter +func (f *ConntrackFilter) AddProtocol(proto uint8) error { + if f.protoFilter != 0 { + return errors.New("Filter attribute already present") + } + f.protoFilter = proto + return nil +} + // MatchConntrackFlow applies the filter to the flow and returns true if the flow matches the filter // false otherwise func (f *ConntrackFilter) MatchConntrackFlow(flow *ConntrackFlow) bool { - if len(f.ipFilter) == 0 { + if len(f.ipFilter) == 0 && len(f.portFilter) == 0 && f.protoFilter == 0 { // empty filter always not match return false } - match := true - // -orig-src ip Source address from original direction - if elem, found := f.ipFilter[ConntrackOrigSrcIP]; found { - match = match && elem.Equal(flow.Forward.SrcIP) + // -p, --protonum proto Layer 4 Protocol, eg. 'tcp' + if f.protoFilter != 0 && flow.Forward.Protocol != f.protoFilter { + // different Layer 4 protocol always not match + return false } - // -orig-dst ip Destination address from original direction - if elem, found := f.ipFilter[ConntrackOrigDstIP]; match && found { - match = match && elem.Equal(flow.Forward.DstIP) - } + match := true - // -src-nat ip Source NAT ip - if elem, found := f.ipFilter[ConntrackReplySrcIP]; match && found { - match = match && elem.Equal(flow.Reverse.SrcIP) - } + // IP conntrack filter + if len(f.ipFilter) > 0 { + // -orig-src ip Source address from original direction + if elem, found := f.ipFilter[ConntrackOrigSrcIP]; found { + match = match && elem.Equal(flow.Forward.SrcIP) + } + + // -orig-dst ip Destination address from original direction + if elem, found := f.ipFilter[ConntrackOrigDstIP]; match && found { + match = match && elem.Equal(flow.Forward.DstIP) + } - // -dst-nat ip Destination NAT ip - if elem, found := f.ipFilter[ConntrackReplyDstIP]; match && found { - match = match && elem.Equal(flow.Reverse.DstIP) + // -src-nat ip Source NAT ip + if elem, found := f.ipFilter[ConntrackReplySrcIP]; match && found { + match = match && elem.Equal(flow.Reverse.SrcIP) + } + + // -dst-nat ip Destination NAT ip + if elem, found := f.ipFilter[ConntrackReplyDstIP]; match && found { + match = match && elem.Equal(flow.Reverse.DstIP) + } + + // Match source or destination reply IP + if elem, found := f.ipFilter[ConntrackReplyAnyIP]; match && found { + match = match && (elem.Equal(flow.Reverse.SrcIP) || elem.Equal(flow.Reverse.DstIP)) + } } - // Match source or destination reply IP - if elem, found := f.ipFilter[ConntrackReplyAnyIP]; match && found { - match = match && (elem.Equal(flow.Reverse.SrcIP) || elem.Equal(flow.Reverse.DstIP)) + // Layer 4 Port filter + if len(f.portFilter) > 0 { + // -orig-port-src port Source port from original direction + if elem, found := f.portFilter[ConntrackOrigSrcPort]; match && found { + match = match && elem == flow.Forward.SrcPort + } + + // -orig-port-dst port Destination port from original direction + if elem, found := f.portFilter[ConntrackOrigDstPort]; match && found { + match = match && elem == flow.Forward.DstPort + } } return match diff --git a/vendor/github.com/vishvananda/netlink/go.mod b/vendor/github.com/vishvananda/netlink/go.mod index 09ee60e77..703322719 100644 --- a/vendor/github.com/vishvananda/netlink/go.mod +++ b/vendor/github.com/vishvananda/netlink/go.mod @@ -4,5 +4,5 @@ go 1.12 require ( github.com/vishvananda/netns v0.0.0-20191106174202-0a2b9b5464df - golang.org/x/sys v0.0.0-20190606203320-7fc4e5ec1444 + golang.org/x/sys v0.0.0-20200121082415-34d275377bf9 ) diff --git a/vendor/github.com/vishvananda/netlink/go.sum b/vendor/github.com/vishvananda/netlink/go.sum index 402d14ec5..28cda557e 100644 --- a/vendor/github.com/vishvananda/netlink/go.sum +++ b/vendor/github.com/vishvananda/netlink/go.sum @@ -1,4 +1,4 @@ github.com/vishvananda/netns v0.0.0-20191106174202-0a2b9b5464df h1:OviZH7qLw/7ZovXvuNyL3XQl8UFofeikI1NW1Gypu7k= github.com/vishvananda/netns v0.0.0-20191106174202-0a2b9b5464df/go.mod h1:JP3t17pCcGlemwknint6hfoeCVQrEMVwxRLRjXpq+BU= -golang.org/x/sys v0.0.0-20190606203320-7fc4e5ec1444 h1:/d2cWp6PSamH4jDPFLyO150psQdqvtoNX8Zjg3AQ31g= -golang.org/x/sys v0.0.0-20190606203320-7fc4e5ec1444/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= +golang.org/x/sys v0.0.0-20200121082415-34d275377bf9 h1:N19i1HjUnR7TF7rMt8O4p3dLvqvmYyzB6ifMFmrbY50= +golang.org/x/sys v0.0.0-20200121082415-34d275377bf9/go.mod h1:h1NjWce9XRLGQEsW7wpKNCjG9DtNlClVuFLEZdDNbEs= diff --git a/vendor/github.com/vishvananda/netlink/link.go b/vendor/github.com/vishvananda/netlink/link.go index 886d88d1b..8fba403e2 100644 --- a/vendor/github.com/vishvananda/netlink/link.go +++ b/vendor/github.com/vishvananda/netlink/link.go @@ -196,10 +196,11 @@ type LinkStatistics64 struct { } type LinkXdp struct { - Fd int - Attached bool - Flags uint32 - ProgId uint32 + Fd int + Attached bool + AttachMode uint32 + Flags uint32 + ProgId uint32 } // Device links cannot be created via netlink. These links @@ -246,6 +247,7 @@ func (ifb *Ifb) Type() string { type Bridge struct { LinkAttrs MulticastSnooping *bool + AgeingTime *uint32 HelloTime *uint32 VlanFiltering *bool } @@ -348,6 +350,19 @@ func (veth *Veth) Type() string { return "veth" } +// Wireguard represent links of type "wireguard", see https://www.wireguard.com/ +type Wireguard struct { + LinkAttrs +} + +func (wg *Wireguard) Attrs() *LinkAttrs { + return &wg.LinkAttrs +} + +func (wg *Wireguard) Type() string { + return "wireguard" +} + // GenericLink links represent types that are not currently understood // by this netlink library. type GenericLink struct { diff --git a/vendor/github.com/vishvananda/netlink/link_linux.go b/vendor/github.com/vishvananda/netlink/link_linux.go index ec915a0b9..3733acce0 100644 --- a/vendor/github.com/vishvananda/netlink/link_linux.go +++ b/vendor/github.com/vishvananda/netlink/link_linux.go @@ -247,6 +247,16 @@ func (h *Handle) BridgeSetMcastSnoop(link Link, on bool) error { return h.linkModify(bridge, unix.NLM_F_ACK) } +func BridgeSetVlanFiltering(link Link, on bool) error { + return pkgHandle.BridgeSetVlanFiltering(link, on) +} + +func (h *Handle) BridgeSetVlanFiltering(link Link, on bool) error { + bridge := link.(*Bridge) + bridge.VlanFiltering = &on + return h.linkModify(bridge, unix.NLM_F_ACK) +} + func SetPromiscOn(link Link) error { return pkgHandle.SetPromiscOn(link) } @@ -1048,6 +1058,10 @@ func (h *Handle) LinkAdd(link Link) error { return h.linkModify(link, unix.NLM_F_CREATE|unix.NLM_F_EXCL|unix.NLM_F_ACK) } +func (h *Handle) LinkModify(link Link) error { + return h.linkModify(link, unix.NLM_F_REQUEST|unix.NLM_F_ACK) +} + func (h *Handle) linkModify(link Link, flags int) error { // TODO: support extra data for macvlan base := link.Attrs() @@ -1089,21 +1103,52 @@ func (h *Handle) linkModify(link Link, flags int) error { } req.Flags |= uint16(tuntap.Mode) - + const TUN = "/dev/net/tun" for i := 0; i < queues; i++ { localReq := req - file, err := os.OpenFile("/dev/net/tun", os.O_RDWR, 0) + fd, err := unix.Open(TUN, os.O_RDWR|syscall.O_CLOEXEC, 0) if err != nil { cleanupFds(fds) return err } - fds = append(fds, file) - _, _, errno := unix.Syscall(unix.SYS_IOCTL, file.Fd(), uintptr(unix.TUNSETIFF), uintptr(unsafe.Pointer(&localReq))) + _, _, errno := unix.Syscall(unix.SYS_IOCTL, uintptr(fd), uintptr(unix.TUNSETIFF), uintptr(unsafe.Pointer(&localReq))) if errno != 0 { + // close the new fd + unix.Close(fd) + // and the already opened ones cleanupFds(fds) return fmt.Errorf("Tuntap IOCTL TUNSETIFF failed [%d], errno %v", i, errno) } + + // Set the tun device to non-blocking before use. The below comment + // taken from: + // + // https://github.com/mistsys/tuntap/commit/161418c25003bbee77d085a34af64d189df62bea + // + // Note there is a complication because in go, if a device node is + // opened, go sets it to use nonblocking I/O. However a /dev/net/tun + // doesn't work with epoll until after the TUNSETIFF ioctl has been + // done. So we open the unix fd directly, do the ioctl, then put the + // fd in nonblocking mode, an then finally wrap it in a os.File, + // which will see the nonblocking mode and add the fd to the + // pollable set, so later on when we Read() from it blocked the + // calling thread in the kernel. + // + // See + // https://github.com/golang/go/issues/30426 + // which got exposed in go 1.13 by the fix to + // https://github.com/golang/go/issues/30624 + err = unix.SetNonblock(fd, true) + if err != nil { + cleanupFds(fds) + return fmt.Errorf("Tuntap set to non-blocking failed [%d], err %v", i, err) + } + + // create the file from the file descriptor and store it + file := os.NewFile(uintptr(fd), TUN) + fds = append(fds, file) + // 1) we only care for the name of the first tap in the multi queue set // 2) if the original name was empty, the localReq has now the actual name // @@ -1114,6 +1159,7 @@ func (h *Handle) linkModify(link Link, flags int) error { if i == 0 { link.Attrs().Name = strings.Trim(string(localReq.Name[:]), "\x00") } + } // only persist interface if NonPersist is NOT set @@ -1193,6 +1239,11 @@ func (h *Handle) linkModify(link Link, flags int) error { nameData := nl.NewRtAttr(unix.IFLA_IFNAME, nl.ZeroTerminated(base.Name)) req.AddData(nameData) + if base.Alias != "" { + alias := nl.NewRtAttr(unix.IFLA_IFALIAS, []byte(base.Alias)) + req.AddData(alias) + } + if base.MTU > 0 { mtu := nl.NewRtAttr(unix.IFLA_MTU, nl.Uint32Attr(uint32(base.MTU))) req.AddData(mtu) @@ -1272,6 +1323,12 @@ func (h *Handle) linkModify(link Link, flags int) error { if base.TxQLen >= 0 { peer.AddRtAttr(unix.IFLA_TXQLEN, nl.Uint32Attr(uint32(base.TxQLen))) } + if base.NumTxQueues > 0 { + peer.AddRtAttr(unix.IFLA_NUM_TX_QUEUES, nl.Uint32Attr(uint32(base.NumTxQueues))) + } + if base.NumRxQueues > 0 { + peer.AddRtAttr(unix.IFLA_NUM_RX_QUEUES, nl.Uint32Attr(uint32(base.NumRxQueues))) + } if base.MTU > 0 { peer.AddRtAttr(unix.IFLA_MTU, nl.Uint32Attr(uint32(base.MTU))) } @@ -1543,6 +1600,8 @@ func LinkDeserialize(hdr *unix.NlMsghdr, m []byte) (Link, error) { link = &Vlan{} case "veth": link = &Veth{} + case "wireguard": + link = &Wireguard{} case "vxlan": link = &Vxlan{} case "bond": @@ -2116,7 +2175,11 @@ func parseVxlanData(link Link, data []syscall.NetlinkRouteAttr) { case nl.IFLA_VXLAN_GBP: vxlan.GBP = true case nl.IFLA_VXLAN_FLOWBASED: - vxlan.FlowBased = int8(datum.Value[0]) != 0 + // NOTE(vish): Apparently this message can be sent with no value. + // Unclear if the others be sent that way as well. + if len(datum.Value) > 0 { + vxlan.FlowBased = int8(datum.Value[0]) != 0 + } case nl.IFLA_VXLAN_AGEING: vxlan.Age = int(native.Uint32(datum.Value[0:4])) vxlan.NoAge = vxlan.Age == 0 @@ -2513,7 +2576,8 @@ func parseLinkXdp(data []byte) (*LinkXdp, error) { case nl.IFLA_XDP_FD: xdp.Fd = int(native.Uint32(attr.Value[0:4])) case nl.IFLA_XDP_ATTACHED: - xdp.Attached = attr.Value[0] != 0 + xdp.AttachMode = uint32(attr.Value[0]) + xdp.Attached = xdp.AttachMode != 0 case nl.IFLA_XDP_FLAGS: xdp.Flags = native.Uint32(attr.Value[0:4]) case nl.IFLA_XDP_PROG_ID: @@ -2577,7 +2641,7 @@ func parseIptunData(link Link, data []syscall.NetlinkRouteAttr) { case nl.IFLA_IPTUN_ENCAP_FLAGS: iptun.EncapFlags = native.Uint16(datum.Value[0:2]) case nl.IFLA_IPTUN_COLLECT_METADATA: - iptun.FlowBased = int8(datum.Value[0]) != 0 + iptun.FlowBased = true } } } @@ -2761,6 +2825,9 @@ func addBridgeAttrs(bridge *Bridge, linkInfo *nl.RtAttr) { if bridge.MulticastSnooping != nil { data.AddRtAttr(nl.IFLA_BR_MCAST_SNOOPING, boolToByte(*bridge.MulticastSnooping)) } + if bridge.AgeingTime != nil { + data.AddRtAttr(nl.IFLA_BR_AGEING_TIME, nl.Uint32Attr(*bridge.AgeingTime)) + } if bridge.HelloTime != nil { data.AddRtAttr(nl.IFLA_BR_HELLO_TIME, nl.Uint32Attr(*bridge.HelloTime)) } @@ -2773,6 +2840,9 @@ func parseBridgeData(bridge Link, data []syscall.NetlinkRouteAttr) { br := bridge.(*Bridge) for _, datum := range data { switch datum.Attr.Type { + case nl.IFLA_BR_AGEING_TIME: + ageingTime := native.Uint32(datum.Value[0:4]) + br.AgeingTime = &ageingTime case nl.IFLA_BR_HELLO_TIME: helloTime := native.Uint32(datum.Value[0:4]) br.HelloTime = &helloTime diff --git a/vendor/github.com/vishvananda/netlink/neigh_linux.go b/vendor/github.com/vishvananda/netlink/neigh_linux.go index cb3b55d35..fb220d141 100644 --- a/vendor/github.com/vishvananda/netlink/neigh_linux.go +++ b/vendor/github.com/vishvananda/netlink/neigh_linux.go @@ -243,6 +243,18 @@ func (h *Handle) NeighListExecute(msg Ndmsg) ([]Neigh, error) { // Ignore messages from other interfaces continue } + if msg.Family != 0 && ndm.Family != msg.Family { + continue + } + if msg.State != 0 && ndm.State != msg.State { + continue + } + if msg.Type != 0 && ndm.Type != msg.Type { + continue + } + if msg.Flags != 0 && ndm.Flags != msg.Flags { + continue + } neigh, err := NeighDeserialize(m) if err != nil { diff --git a/vendor/github.com/vishvananda/netlink/netlink_unspecified.go b/vendor/github.com/vishvananda/netlink/netlink_unspecified.go index 42d3acf91..932e30b58 100644 --- a/vendor/github.com/vishvananda/netlink/netlink_unspecified.go +++ b/vendor/github.com/vishvananda/netlink/netlink_unspecified.go @@ -72,6 +72,10 @@ func LinkSetXdpFd(link Link, fd int) error { return ErrNotImplemented } +func LinkSetXdpFdWithFlags(link Link, fd, flags int) error { + return ErrNotImplemented +} + func LinkSetARPOff(link Link) error { return ErrNotImplemented } diff --git a/vendor/github.com/vishvananda/netlink/nl/addr_linux.go b/vendor/github.com/vishvananda/netlink/nl/addr_linux.go index 50db3b4cd..6bea4ed02 100644 --- a/vendor/github.com/vishvananda/netlink/nl/addr_linux.go +++ b/vendor/github.com/vishvananda/netlink/nl/addr_linux.go @@ -54,24 +54,18 @@ func (msg *IfAddrmsg) Len() int { // __u32 tstamp; /* updated timestamp, hundredths of seconds */ // }; -const IFA_CACHEINFO = 6 -const SizeofIfaCacheInfo = 0x10 - type IfaCacheInfo struct { - IfaPrefered uint32 - IfaValid uint32 - Cstamp uint32 - Tstamp uint32 + unix.IfaCacheinfo } func (msg *IfaCacheInfo) Len() int { - return SizeofIfaCacheInfo + return unix.SizeofIfaCacheinfo } func DeserializeIfaCacheInfo(b []byte) *IfaCacheInfo { - return (*IfaCacheInfo)(unsafe.Pointer(&b[0:SizeofIfaCacheInfo][0])) + return (*IfaCacheInfo)(unsafe.Pointer(&b[0:unix.SizeofIfaCacheinfo][0])) } func (msg *IfaCacheInfo) Serialize() []byte { - return (*(*[SizeofIfaCacheInfo]byte)(unsafe.Pointer(msg)))[:] + return (*(*[unix.SizeofIfaCacheinfo]byte)(unsafe.Pointer(msg)))[:] } diff --git a/vendor/github.com/vishvananda/netlink/nl/link_linux.go b/vendor/github.com/vishvananda/netlink/nl/link_linux.go index afb16a9c1..5cb166c13 100644 --- a/vendor/github.com/vishvananda/netlink/nl/link_linux.go +++ b/vendor/github.com/vishvananda/netlink/nl/link_linux.go @@ -478,6 +478,14 @@ const ( IFLA_XDP_MAX = IFLA_XDP_PROG_ID ) +// XDP program attach mode (used as dump value for IFLA_XDP_ATTACHED) +const ( + XDP_ATTACHED_NONE = iota + XDP_ATTACHED_DRV + XDP_ATTACHED_SKB + XDP_ATTACHED_HW +) + const ( IFLA_IPTUN_UNSPEC = iota IFLA_IPTUN_LINK diff --git a/vendor/github.com/vishvananda/netlink/nl/nl_linux.go b/vendor/github.com/vishvananda/netlink/nl/nl_linux.go index aaf56c671..25b4d01dd 100644 --- a/vendor/github.com/vishvananda/netlink/nl/nl_linux.go +++ b/vendor/github.com/vishvananda/netlink/nl/nl_linux.go @@ -439,10 +439,7 @@ done: if m.Header.Pid != pid { continue } - if m.Header.Type == unix.NLMSG_DONE { - break done - } - if m.Header.Type == unix.NLMSG_ERROR { + if m.Header.Type == unix.NLMSG_DONE || m.Header.Type == unix.NLMSG_ERROR { native := NativeEndian() error := int32(native.Uint32(m.Data[0:4])) if error == 0 { diff --git a/vendor/github.com/vishvananda/netlink/nl/syscall.go b/vendor/github.com/vishvananda/netlink/nl/syscall.go index f7f7f92e6..4a01e6e59 100644 --- a/vendor/github.com/vishvananda/netlink/nl/syscall.go +++ b/vendor/github.com/vishvananda/netlink/nl/syscall.go @@ -21,6 +21,13 @@ const ( FRA_TABLE /* Extended table id */ FRA_FWMASK /* mask for netfilter mark */ FRA_OIFNAME + FRA_PAD + FRA_L3MDEV /* iif or oif is l3mdev goto its table */ + FRA_UID_RANGE /* UID range */ + FRA_PROTOCOL /* Originator of the rule */ + FRA_IP_PROTO /* ip proto */ + FRA_SPORT_RANGE /* sport */ + FRA_DPORT_RANGE /* dport */ ) // ip rule netlink request types diff --git a/vendor/github.com/vishvananda/netlink/nl/xfrm_state_linux.go b/vendor/github.com/vishvananda/netlink/nl/xfrm_state_linux.go index b6290fd54..43a947f22 100644 --- a/vendor/github.com/vishvananda/netlink/nl/xfrm_state_linux.go +++ b/vendor/github.com/vishvananda/netlink/nl/xfrm_state_linux.go @@ -13,7 +13,7 @@ const ( SizeofXfrmAlgoAuth = 0x48 SizeofXfrmAlgoAEAD = 0x48 SizeofXfrmEncapTmpl = 0x18 - SizeofXfrmUsersaFlush = 0x8 + SizeofXfrmUsersaFlush = 0x1 SizeofXfrmReplayStateEsn = 0x18 ) diff --git a/vendor/github.com/vishvananda/netlink/rdma_link_linux.go b/vendor/github.com/vishvananda/netlink/rdma_link_linux.go index 2d0bdc8c3..ff014ca4c 100644 --- a/vendor/github.com/vishvananda/netlink/rdma_link_linux.go +++ b/vendor/github.com/vishvananda/netlink/rdma_link_linux.go @@ -77,28 +77,39 @@ func executeOneGetRdmaLink(data []byte) (*RdmaLink, error) { return &link, nil } -func execRdmaGetLink(req *nl.NetlinkRequest, name string) (*RdmaLink, error) { +func execRdmaSetLink(req *nl.NetlinkRequest) error { + + _, err := req.Execute(unix.NETLINK_RDMA, 0) + return err +} + +// RdmaLinkList gets a list of RDMA link devices. +// Equivalent to: `rdma dev show` +func RdmaLinkList() ([]*RdmaLink, error) { + return pkgHandle.RdmaLinkList() +} + +// RdmaLinkList gets a list of RDMA link devices. +// Equivalent to: `rdma dev show` +func (h *Handle) RdmaLinkList() ([]*RdmaLink, error) { + proto := getProtoField(nl.RDMA_NL_NLDEV, nl.RDMA_NLDEV_CMD_GET) + req := h.newNetlinkRequest(proto, unix.NLM_F_ACK|unix.NLM_F_DUMP) msgs, err := req.Execute(unix.NETLINK_RDMA, 0) if err != nil { return nil, err } + + var res []*RdmaLink for _, m := range msgs { link, err := executeOneGetRdmaLink(m) if err != nil { return nil, err } - if link.Attrs.Name == name { - return link, nil - } + res = append(res, link) } - return nil, fmt.Errorf("Rdma device %v not found", name) -} -func execRdmaSetLink(req *nl.NetlinkRequest) error { - - _, err := req.Execute(unix.NETLINK_RDMA, 0) - return err + return res, nil } // RdmaLinkByName finds a link by name and returns a pointer to the object if @@ -110,11 +121,16 @@ func RdmaLinkByName(name string) (*RdmaLink, error) { // RdmaLinkByName finds a link by name and returns a pointer to the object if // found and nil error, otherwise returns error code. func (h *Handle) RdmaLinkByName(name string) (*RdmaLink, error) { - - proto := getProtoField(nl.RDMA_NL_NLDEV, nl.RDMA_NLDEV_CMD_GET) - req := h.newNetlinkRequest(proto, unix.NLM_F_ACK|unix.NLM_F_DUMP) - - return execRdmaGetLink(req, name) + links, err := h.RdmaLinkList() + if err != nil { + return nil, err + } + for _, link := range links { + if link.Attrs.Name == name { + return link, nil + } + } + return nil, fmt.Errorf("Rdma device %v not found", name) } // RdmaLinkSetName sets the name of the rdma link device. Return nil on success diff --git a/vendor/github.com/vishvananda/netlink/route_linux.go b/vendor/github.com/vishvananda/netlink/route_linux.go index c69c595ed..8d4954c29 100644 --- a/vendor/github.com/vishvananda/netlink/route_linux.go +++ b/vendor/github.com/vishvananda/netlink/route_linux.go @@ -33,6 +33,9 @@ const ( RT_FILTER_GW RT_FILTER_TABLE RT_FILTER_HOPLIMIT + RT_FILTER_PRIORITY + RT_FILTER_MARK + RT_FILTER_MASK ) const ( @@ -938,15 +941,27 @@ func deserializeRoute(m []byte) (Route, error) { return route, nil } +// RouteGetOptions contains a set of options to use with +// RouteGetWithOptions +type RouteGetOptions struct { + VrfName string +} + +// RouteGetWithOptions gets a route to a specific destination from the host system. +// Equivalent to: 'ip route get <> vrf '. +func RouteGetWithOptions(destination net.IP, options *RouteGetOptions) ([]Route, error) { + return pkgHandle.RouteGetWithOptions(destination, options) +} + // RouteGet gets a route to a specific destination from the host system. // Equivalent to: 'ip route get'. func RouteGet(destination net.IP) ([]Route, error) { return pkgHandle.RouteGet(destination) } -// RouteGet gets a route to a specific destination from the host system. -// Equivalent to: 'ip route get'. -func (h *Handle) RouteGet(destination net.IP) ([]Route, error) { +// RouteGetWithOptions gets a route to a specific destination from the host system. +// Equivalent to: 'ip route get <> vrf '. +func (h *Handle) RouteGetWithOptions(destination net.IP, options *RouteGetOptions) ([]Route, error) { req := h.newNetlinkRequest(unix.RTM_GETROUTE, unix.NLM_F_REQUEST) family := nl.GetIPFamily(destination) var destinationData []byte @@ -966,6 +981,20 @@ func (h *Handle) RouteGet(destination net.IP) ([]Route, error) { rtaDst := nl.NewRtAttr(unix.RTA_DST, destinationData) req.AddData(rtaDst) + if options != nil { + link, err := LinkByName(options.VrfName) + if err != nil { + return nil, err + } + var ( + b = make([]byte, 4) + native = nl.NativeEndian() + ) + native.PutUint32(b, uint32(link.Attrs().Index)) + + req.AddData(nl.NewRtAttr(unix.RTA_OIF, b)) + } + msgs, err := req.Execute(unix.NETLINK_ROUTE, unix.RTM_NEWROUTE) if err != nil { return nil, err @@ -980,7 +1009,12 @@ func (h *Handle) RouteGet(destination net.IP) ([]Route, error) { res = append(res, route) } return res, nil +} +// RouteGet gets a route to a specific destination from the host system. +// Equivalent to: 'ip route get'. +func (h *Handle) RouteGet(destination net.IP) ([]Route, error) { + return h.RouteGetWithOptions(destination, nil) } // RouteSubscribe takes a chan down which notifications will be sent diff --git a/vendor/github.com/vishvananda/netlink/rule.go b/vendor/github.com/vishvananda/netlink/rule.go index 7fc8ae5df..95f2facfb 100644 --- a/vendor/github.com/vishvananda/netlink/rule.go +++ b/vendor/github.com/vishvananda/netlink/rule.go @@ -12,6 +12,7 @@ type Rule struct { Table int Mark int Mask int + Tos uint TunID uint Goto int Src *net.IPNet @@ -22,6 +23,8 @@ type Rule struct { SuppressIfgroup int SuppressPrefixlen int Invert bool + Dport *RulePortRange + Sport *RulePortRange } func (r Rule) String() string { @@ -40,3 +43,14 @@ func NewRule() *Rule { Flow: -1, } } + +// NewRulePortRange creates rule sport/dport range. +func NewRulePortRange(start, end uint16) *RulePortRange { + return &RulePortRange{Start: start, End: end} +} + +// RulePortRange represents rule sport/dport range. +type RulePortRange struct { + Start uint16 + End uint16 +} diff --git a/vendor/github.com/vishvananda/netlink/rule_linux.go b/vendor/github.com/vishvananda/netlink/rule_linux.go index e12569fe4..71d62c6ed 100644 --- a/vendor/github.com/vishvananda/netlink/rule_linux.go +++ b/vendor/github.com/vishvananda/netlink/rule_linux.go @@ -1,6 +1,7 @@ package netlink import ( + "bytes" "fmt" "net" @@ -55,6 +56,9 @@ func ruleHandle(rule *Rule, req *nl.NetlinkRequest) error { if rule.Table >= 0 && rule.Table < 256 { msg.Table = uint8(rule.Table) } + if rule.Tos != 0 { + msg.Tos = uint8(rule.Tos) + } var dstFamily uint8 var rtAttrs []*nl.RtAttr @@ -150,6 +154,16 @@ func ruleHandle(rule *Rule, req *nl.NetlinkRequest) error { req.AddData(nl.NewRtAttr(nl.FRA_GOTO, b)) } + if rule.Dport != nil { + b := rule.Dport.toRtAttrData() + req.AddData(nl.NewRtAttr(nl.FRA_DPORT_RANGE, b)) + } + + if rule.Sport != nil { + b := rule.Sport.toRtAttrData() + req.AddData(nl.NewRtAttr(nl.FRA_SPORT_RANGE, b)) + } + _, err := req.Execute(unix.NETLINK_ROUTE, 0) return err } @@ -163,6 +177,19 @@ func RuleList(family int) ([]Rule, error) { // RuleList lists rules in the system. // Equivalent to: ip rule list func (h *Handle) RuleList(family int) ([]Rule, error) { + return h.RuleListFiltered(family, nil, 0) +} + +// RuleListFiltered gets a list of rules in the system filtered by the +// specified rule template `filter`. +// Equivalent to: ip rule list +func RuleListFiltered(family int, filter *Rule, filterMask uint64) ([]Rule, error) { + return pkgHandle.RuleListFiltered(family, filter, filterMask) +} + +// RuleListFiltered lists rules in the system. +// Equivalent to: ip rule list +func (h *Handle) RuleListFiltered(family int, filter *Rule, filterMask uint64) ([]Rule, error) { req := h.newNetlinkRequest(unix.RTM_GETRULE, unix.NLM_F_DUMP|unix.NLM_F_REQUEST) msg := nl.NewIfInfomsg(family) req.AddData(msg) @@ -184,6 +211,7 @@ func (h *Handle) RuleList(family int) ([]Rule, error) { rule := NewRule() rule.Invert = msg.Flags&FibRuleInvert > 0 + rule.Tos = uint(msg.Tos) for j := range attrs { switch attrs[j].Attr.Type { @@ -225,10 +253,44 @@ func (h *Handle) RuleList(family int) ([]Rule, error) { rule.Goto = int(native.Uint32(attrs[j].Value[0:4])) case nl.FRA_PRIORITY: rule.Priority = int(native.Uint32(attrs[j].Value[0:4])) + case nl.FRA_DPORT_RANGE: + rule.Dport = NewRulePortRange(native.Uint16(attrs[j].Value[0:2]), native.Uint16(attrs[j].Value[2:4])) + case nl.FRA_SPORT_RANGE: + rule.Sport = NewRulePortRange(native.Uint16(attrs[j].Value[0:2]), native.Uint16(attrs[j].Value[2:4])) + } + } + + if filter != nil { + switch { + case filterMask&RT_FILTER_SRC != 0 && + (rule.Src == nil || rule.Src.String() != filter.Src.String()): + continue + case filterMask&RT_FILTER_DST != 0 && + (rule.Dst == nil || rule.Dst.String() != filter.Dst.String()): + continue + case filterMask&RT_FILTER_TABLE != 0 && + filter.Table != unix.RT_TABLE_UNSPEC && rule.Table != filter.Table: + continue + case filterMask&RT_FILTER_TOS != 0 && rule.Tos != filter.Tos: + continue + case filterMask&RT_FILTER_PRIORITY != 0 && rule.Priority != filter.Priority: + continue + case filterMask&RT_FILTER_MARK != 0 && rule.Mark != filter.Mark: + continue + case filterMask&RT_FILTER_MASK != 0 && rule.Mask != filter.Mask: + continue } } + res = append(res, *rule) } return res, nil } + +func (pr *RulePortRange) toRtAttrData() []byte { + b := [][]byte{make([]byte, 2), make([]byte, 2)} + native.PutUint16(b[0], pr.Start) + native.PutUint16(b[1], pr.End) + return bytes.Join(b, []byte{}) +} diff --git a/vendor/golang.org/x/crypto/chacha20/chacha_generic.go b/vendor/golang.org/x/crypto/chacha20/chacha_generic.go index 7c498e90d..a2ecf5c32 100644 --- a/vendor/golang.org/x/crypto/chacha20/chacha_generic.go +++ b/vendor/golang.org/x/crypto/chacha20/chacha_generic.go @@ -42,10 +42,14 @@ type Cipher struct { // The last len bytes of buf are leftover key stream bytes from the previous // XORKeyStream invocation. The size of buf depends on how many blocks are - // computed at a time. + // computed at a time by xorKeyStreamBlocks. buf [bufSize]byte len int + // overflow is set when the counter overflowed, no more blocks can be + // generated, and the next XORKeyStream call should panic. + overflow bool + // The counter-independent results of the first round are cached after they // are computed the first time. precompDone bool @@ -89,6 +93,7 @@ func newUnauthenticatedCipher(c *Cipher, key, nonce []byte) (*Cipher, error) { return nil, errors.New("chacha20: wrong nonce size") } + key, nonce = key[:KeySize], nonce[:NonceSize] // bounds check elimination hint c.key = [8]uint32{ binary.LittleEndian.Uint32(key[0:4]), binary.LittleEndian.Uint32(key[4:8]), @@ -139,15 +144,18 @@ func quarterRound(a, b, c, d uint32) (uint32, uint32, uint32, uint32) { // SetCounter sets the Cipher counter. The next invocation of XORKeyStream will // behave as if (64 * counter) bytes had been encrypted so far. // -// To prevent accidental counter reuse, SetCounter panics if counter is -// less than the current value. +// To prevent accidental counter reuse, SetCounter panics if counter is less +// than the current value. +// +// Note that the execution time of XORKeyStream is not independent of the +// counter value. func (s *Cipher) SetCounter(counter uint32) { // Internally, s may buffer multiple blocks, which complicates this // implementation slightly. When checking whether the counter has rolled // back, we must use both s.counter and s.len to determine how many blocks // we have already output. outputCounter := s.counter - uint32(s.len)/blockSize - if counter < outputCounter { + if s.overflow || counter < outputCounter { panic("chacha20: SetCounter attempted to rollback counter") } @@ -196,34 +204,52 @@ func (s *Cipher) XORKeyStream(dst, src []byte) { dst[i] = src[i] ^ b } s.len -= len(keyStream) - src = src[len(keyStream):] - dst = dst[len(keyStream):] + dst, src = dst[len(keyStream):], src[len(keyStream):] + } + if len(src) == 0 { + return } - const blocksPerBuf = bufSize / blockSize - numBufs := (uint64(len(src)) + bufSize - 1) / bufSize - if uint64(s.counter)+numBufs*blocksPerBuf >= 1<<32 { + // If we'd need to let the counter overflow and keep generating output, + // panic immediately. If instead we'd only reach the last block, remember + // not to generate any more output after the buffer is drained. + numBlocks := (uint64(len(src)) + blockSize - 1) / blockSize + if s.overflow || uint64(s.counter)+numBlocks > 1<<32 { panic("chacha20: counter overflow") + } else if uint64(s.counter)+numBlocks == 1<<32 { + s.overflow = true } // xorKeyStreamBlocks implementations expect input lengths that are a // multiple of bufSize. Platform-specific ones process multiple blocks at a // time, so have bufSizes that are a multiple of blockSize. - rem := len(src) % bufSize - full := len(src) - rem - + full := len(src) - len(src)%bufSize if full > 0 { s.xorKeyStreamBlocks(dst[:full], src[:full]) } + dst, src = dst[full:], src[full:] + + // If using a multi-block xorKeyStreamBlocks would overflow, use the generic + // one that does one block at a time. + const blocksPerBuf = bufSize / blockSize + if uint64(s.counter)+blocksPerBuf > 1<<32 { + s.buf = [bufSize]byte{} + numBlocks := (len(src) + blockSize - 1) / blockSize + buf := s.buf[bufSize-numBlocks*blockSize:] + copy(buf, src) + s.xorKeyStreamBlocksGeneric(buf, buf) + s.len = len(buf) - copy(dst, buf) + return + } // If we have a partial (multi-)block, pad it for xorKeyStreamBlocks, and // keep the leftover keystream for the next XORKeyStream invocation. - if rem > 0 { + if len(src) > 0 { s.buf = [bufSize]byte{} - copy(s.buf[:], src[full:]) + copy(s.buf[:], src) s.xorKeyStreamBlocks(s.buf[:], s.buf[:]) - s.len = bufSize - copy(dst[full:], s.buf[:]) + s.len = bufSize - copy(dst, s.buf[:]) } } @@ -260,7 +286,9 @@ func (s *Cipher) xorKeyStreamBlocksGeneric(dst, src []byte) { s.precompDone = true } - for i := 0; i < len(src); i += blockSize { + // A condition of len(src) > 0 would be sufficient, but this also + // acts as a bounds check elimination hint. + for len(src) >= 64 && len(dst) >= 64 { // The remainder of the first column round. fcr0, fcr4, fcr8, fcr12 := quarterRound(c0, c4, c8, s.counter) @@ -285,49 +313,28 @@ func (s *Cipher) xorKeyStreamBlocksGeneric(dst, src []byte) { x3, x4, x9, x14 = quarterRound(x3, x4, x9, x14) } - // Finally, add back the initial state to generate the key stream. - x0 += c0 - x1 += c1 - x2 += c2 - x3 += c3 - x4 += c4 - x5 += c5 - x6 += c6 - x7 += c7 - x8 += c8 - x9 += c9 - x10 += c10 - x11 += c11 - x12 += s.counter - x13 += c13 - x14 += c14 - x15 += c15 + // Add back the initial state to generate the key stream, then + // XOR the key stream with the source and write out the result. + addXor(dst[0:4], src[0:4], x0, c0) + addXor(dst[4:8], src[4:8], x1, c1) + addXor(dst[8:12], src[8:12], x2, c2) + addXor(dst[12:16], src[12:16], x3, c3) + addXor(dst[16:20], src[16:20], x4, c4) + addXor(dst[20:24], src[20:24], x5, c5) + addXor(dst[24:28], src[24:28], x6, c6) + addXor(dst[28:32], src[28:32], x7, c7) + addXor(dst[32:36], src[32:36], x8, c8) + addXor(dst[36:40], src[36:40], x9, c9) + addXor(dst[40:44], src[40:44], x10, c10) + addXor(dst[44:48], src[44:48], x11, c11) + addXor(dst[48:52], src[48:52], x12, s.counter) + addXor(dst[52:56], src[52:56], x13, c13) + addXor(dst[56:60], src[56:60], x14, c14) + addXor(dst[60:64], src[60:64], x15, c15) s.counter += 1 - if s.counter == 0 { - panic("chacha20: internal error: counter overflow") - } - in, out := src[i:], dst[i:] - in, out = in[:blockSize], out[:blockSize] // bounds check elimination hint - - // XOR the key stream with the source and write out the result. - xor(out[0:], in[0:], x0) - xor(out[4:], in[4:], x1) - xor(out[8:], in[8:], x2) - xor(out[12:], in[12:], x3) - xor(out[16:], in[16:], x4) - xor(out[20:], in[20:], x5) - xor(out[24:], in[24:], x6) - xor(out[28:], in[28:], x7) - xor(out[32:], in[32:], x8) - xor(out[36:], in[36:], x9) - xor(out[40:], in[40:], x10) - xor(out[44:], in[44:], x11) - xor(out[48:], in[48:], x12) - xor(out[52:], in[52:], x13) - xor(out[56:], in[56:], x14) - xor(out[60:], in[60:], x15) + src, dst = src[blockSize:], dst[blockSize:] } } diff --git a/vendor/golang.org/x/crypto/chacha20/xor.go b/vendor/golang.org/x/crypto/chacha20/xor.go index 0110c9865..c2d04851e 100644 --- a/vendor/golang.org/x/crypto/chacha20/xor.go +++ b/vendor/golang.org/x/crypto/chacha20/xor.go @@ -13,10 +13,10 @@ const unaligned = runtime.GOARCH == "386" || runtime.GOARCH == "ppc64le" || runtime.GOARCH == "s390x" -// xor reads a little endian uint32 from src, XORs it with u and +// addXor reads a little endian uint32 from src, XORs it with (a + b) and // places the result in little endian byte order in dst. -func xor(dst, src []byte, u uint32) { - _, _ = src[3], dst[3] // eliminate bounds checks +func addXor(dst, src []byte, a, b uint32) { + _, _ = src[3], dst[3] // bounds check elimination hint if unaligned { // The compiler should optimize this code into // 32-bit unaligned little endian loads and stores. @@ -27,15 +27,16 @@ func xor(dst, src []byte, u uint32) { v |= uint32(src[1]) << 8 v |= uint32(src[2]) << 16 v |= uint32(src[3]) << 24 - v ^= u + v ^= a + b dst[0] = byte(v) dst[1] = byte(v >> 8) dst[2] = byte(v >> 16) dst[3] = byte(v >> 24) } else { - dst[0] = src[0] ^ byte(u) - dst[1] = src[1] ^ byte(u>>8) - dst[2] = src[2] ^ byte(u>>16) - dst[3] = src[3] ^ byte(u>>24) + a += b + dst[0] = src[0] ^ byte(a) + dst[1] = src[1] ^ byte(a>>8) + dst[2] = src[2] ^ byte(a>>16) + dst[3] = src[3] ^ byte(a>>24) } } diff --git a/vendor/golang.org/x/crypto/poly1305/mac_noasm.go b/vendor/golang.org/x/crypto/poly1305/mac_noasm.go index b0c2cd056..d118f30ed 100644 --- a/vendor/golang.org/x/crypto/poly1305/mac_noasm.go +++ b/vendor/golang.org/x/crypto/poly1305/mac_noasm.go @@ -2,10 +2,8 @@ // Use of this source code is governed by a BSD-style // license that can be found in the LICENSE file. -// +build !amd64,!ppc64le gccgo purego +// +build !amd64,!ppc64le,!s390x gccgo purego package poly1305 type mac struct{ macGeneric } - -func newMAC(key *[32]byte) mac { return mac{newMACGeneric(key)} } diff --git a/vendor/golang.org/x/crypto/poly1305/poly1305.go b/vendor/golang.org/x/crypto/poly1305/poly1305.go index 066159b79..9d7a6af09 100644 --- a/vendor/golang.org/x/crypto/poly1305/poly1305.go +++ b/vendor/golang.org/x/crypto/poly1305/poly1305.go @@ -26,7 +26,9 @@ const TagSize = 16 // 16-byte result into out. Authenticating two different messages with the same // key allows an attacker to forge messages at will. func Sum(out *[16]byte, m []byte, key *[32]byte) { - sum(out, m, key) + h := New(key) + h.Write(m) + h.Sum(out[:0]) } // Verify returns true if mac is a valid authenticator for m with the given key. @@ -46,10 +48,9 @@ func Verify(mac *[16]byte, m []byte, key *[32]byte) bool { // two different messages with the same key allows an attacker // to forge messages at will. func New(key *[32]byte) *MAC { - return &MAC{ - mac: newMAC(key), - finalized: false, - } + m := &MAC{} + initialize(key, &m.macState) + return m } // MAC is an io.Writer computing an authentication tag @@ -58,7 +59,7 @@ func New(key *[32]byte) *MAC { // MAC cannot be used like common hash.Hash implementations, // because using a poly1305 key twice breaks its security. // Therefore writing data to a running MAC after calling -// Sum causes it to panic. +// Sum or Verify causes it to panic. type MAC struct { mac // platform-dependent implementation @@ -71,10 +72,10 @@ func (h *MAC) Size() int { return TagSize } // Write adds more data to the running message authentication code. // It never returns an error. // -// It must not be called after the first call of Sum. +// It must not be called after the first call of Sum or Verify. func (h *MAC) Write(p []byte) (n int, err error) { if h.finalized { - panic("poly1305: write to MAC after Sum") + panic("poly1305: write to MAC after Sum or Verify") } return h.mac.Write(p) } @@ -87,3 +88,12 @@ func (h *MAC) Sum(b []byte) []byte { h.finalized = true return append(b, mac[:]...) } + +// Verify returns whether the authenticator of all data written to +// the message authentication code matches the expected value. +func (h *MAC) Verify(expected []byte) bool { + var mac [TagSize]byte + h.mac.Sum(&mac) + h.finalized = true + return subtle.ConstantTimeCompare(expected, mac[:]) == 1 +} diff --git a/vendor/golang.org/x/crypto/poly1305/sum_amd64.go b/vendor/golang.org/x/crypto/poly1305/sum_amd64.go index 35b9e38c9..99e5a1d50 100644 --- a/vendor/golang.org/x/crypto/poly1305/sum_amd64.go +++ b/vendor/golang.org/x/crypto/poly1305/sum_amd64.go @@ -9,17 +9,6 @@ package poly1305 //go:noescape func update(state *macState, msg []byte) -func sum(out *[16]byte, m []byte, key *[32]byte) { - h := newMAC(key) - h.Write(m) - h.Sum(out) -} - -func newMAC(key *[32]byte) (h mac) { - initialize(key, &h.r, &h.s) - return -} - // mac is a wrapper for macGeneric that redirects calls that would have gone to // updateGeneric to update. // diff --git a/vendor/golang.org/x/crypto/poly1305/sum_generic.go b/vendor/golang.org/x/crypto/poly1305/sum_generic.go index 1187eab78..c942a6590 100644 --- a/vendor/golang.org/x/crypto/poly1305/sum_generic.go +++ b/vendor/golang.org/x/crypto/poly1305/sum_generic.go @@ -31,16 +31,18 @@ func sumGeneric(out *[TagSize]byte, msg []byte, key *[32]byte) { h.Sum(out) } -func newMACGeneric(key *[32]byte) (h macGeneric) { - initialize(key, &h.r, &h.s) - return +func newMACGeneric(key *[32]byte) macGeneric { + m := macGeneric{} + initialize(key, &m.macState) + return m } // macState holds numbers in saturated 64-bit little-endian limbs. That is, // the value of [x0, x1, x2] is x[0] + x[1] * 2⁶⁴ + x[2] * 2¹²⁸. type macState struct { // h is the main accumulator. It is to be interpreted modulo 2¹³⁰ - 5, but - // can grow larger during and after rounds. + // can grow larger during and after rounds. It must, however, remain below + // 2 * (2¹³⁰ - 5). h [3]uint64 // r and s are the private key components. r [2]uint64 @@ -97,11 +99,12 @@ const ( rMask1 = 0x0FFFFFFC0FFFFFFC ) -func initialize(key *[32]byte, r, s *[2]uint64) { - r[0] = binary.LittleEndian.Uint64(key[0:8]) & rMask0 - r[1] = binary.LittleEndian.Uint64(key[8:16]) & rMask1 - s[0] = binary.LittleEndian.Uint64(key[16:24]) - s[1] = binary.LittleEndian.Uint64(key[24:32]) +// initialize loads the 256-bit key into the two 128-bit secret values r and s. +func initialize(key *[32]byte, m *macState) { + m.r[0] = binary.LittleEndian.Uint64(key[0:8]) & rMask0 + m.r[1] = binary.LittleEndian.Uint64(key[8:16]) & rMask1 + m.s[0] = binary.LittleEndian.Uint64(key[16:24]) + m.s[1] = binary.LittleEndian.Uint64(key[24:32]) } // uint128 holds a 128-bit number as two 64-bit limbs, for use with the diff --git a/vendor/golang.org/x/crypto/poly1305/sum_noasm.go b/vendor/golang.org/x/crypto/poly1305/sum_noasm.go deleted file mode 100644 index 2e3ae34c7..000000000 --- a/vendor/golang.org/x/crypto/poly1305/sum_noasm.go +++ /dev/null @@ -1,13 +0,0 @@ -// Copyright 2018 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -// +build s390x,!go1.11 !amd64,!s390x,!ppc64le gccgo purego - -package poly1305 - -func sum(out *[TagSize]byte, msg []byte, key *[32]byte) { - h := newMAC(key) - h.Write(msg) - h.Sum(out) -} diff --git a/vendor/golang.org/x/crypto/poly1305/sum_ppc64le.go b/vendor/golang.org/x/crypto/poly1305/sum_ppc64le.go index 92597bb8c..2e7a120b1 100644 --- a/vendor/golang.org/x/crypto/poly1305/sum_ppc64le.go +++ b/vendor/golang.org/x/crypto/poly1305/sum_ppc64le.go @@ -9,17 +9,6 @@ package poly1305 //go:noescape func update(state *macState, msg []byte) -func sum(out *[16]byte, m []byte, key *[32]byte) { - h := newMAC(key) - h.Write(m) - h.Sum(out) -} - -func newMAC(key *[32]byte) (h mac) { - initialize(key, &h.r, &h.s) - return -} - // mac is a wrapper for macGeneric that redirects calls that would have gone to // updateGeneric to update. // diff --git a/vendor/golang.org/x/crypto/poly1305/sum_s390x.go b/vendor/golang.org/x/crypto/poly1305/sum_s390x.go index 5f91ff84a..958fedc07 100644 --- a/vendor/golang.org/x/crypto/poly1305/sum_s390x.go +++ b/vendor/golang.org/x/crypto/poly1305/sum_s390x.go @@ -2,7 +2,7 @@ // Use of this source code is governed by a BSD-style // license that can be found in the LICENSE file. -// +build go1.11,!gccgo,!purego +// +build !gccgo,!purego package poly1305 @@ -10,30 +10,66 @@ import ( "golang.org/x/sys/cpu" ) -// poly1305vx is an assembly implementation of Poly1305 that uses vector +// updateVX is an assembly implementation of Poly1305 that uses vector // instructions. It must only be called if the vector facility (vx) is // available. //go:noescape -func poly1305vx(out *[16]byte, m *byte, mlen uint64, key *[32]byte) +func updateVX(state *macState, msg []byte) -// poly1305vmsl is an assembly implementation of Poly1305 that uses vector -// instructions, including VMSL. It must only be called if the vector facility (vx) is -// available and if VMSL is supported. -//go:noescape -func poly1305vmsl(out *[16]byte, m *byte, mlen uint64, key *[32]byte) +// mac is a replacement for macGeneric that uses a larger buffer and redirects +// calls that would have gone to updateGeneric to updateVX if the vector +// facility is installed. +// +// A larger buffer is required for good performance because the vector +// implementation has a higher fixed cost per call than the generic +// implementation. +type mac struct { + macState + + buffer [16 * TagSize]byte // size must be a multiple of block size (16) + offset int +} -func sum(out *[16]byte, m []byte, key *[32]byte) { - if cpu.S390X.HasVX { - var mPtr *byte - if len(m) > 0 { - mPtr = &m[0] +func (h *mac) Write(p []byte) (int, error) { + nn := len(p) + if h.offset > 0 { + n := copy(h.buffer[h.offset:], p) + if h.offset+n < len(h.buffer) { + h.offset += n + return nn, nil } - if cpu.S390X.HasVXE && len(m) > 256 { - poly1305vmsl(out, mPtr, uint64(len(m)), key) + p = p[n:] + h.offset = 0 + if cpu.S390X.HasVX { + updateVX(&h.macState, h.buffer[:]) } else { - poly1305vx(out, mPtr, uint64(len(m)), key) + updateGeneric(&h.macState, h.buffer[:]) } - } else { - sumGeneric(out, m, key) } + + tail := len(p) % len(h.buffer) // number of bytes to copy into buffer + body := len(p) - tail // number of bytes to process now + if body > 0 { + if cpu.S390X.HasVX { + updateVX(&h.macState, p[:body]) + } else { + updateGeneric(&h.macState, p[:body]) + } + } + h.offset = copy(h.buffer[:], p[body:]) // copy tail bytes - can be 0 + return nn, nil +} + +func (h *mac) Sum(out *[TagSize]byte) { + state := h.macState + remainder := h.buffer[:h.offset] + + // Use the generic implementation if we have 2 or fewer blocks left + // to sum. The vector implementation has a higher startup time. + if cpu.S390X.HasVX && len(remainder) > 2*TagSize { + updateVX(&state, remainder) + } else if len(remainder) > 0 { + updateGeneric(&state, remainder) + } + finalize(out, &state.h, &state.s) } diff --git a/vendor/golang.org/x/crypto/poly1305/sum_s390x.s b/vendor/golang.org/x/crypto/poly1305/sum_s390x.s index 806d1694b..0fa9ee6e0 100644 --- a/vendor/golang.org/x/crypto/poly1305/sum_s390x.s +++ b/vendor/golang.org/x/crypto/poly1305/sum_s390x.s @@ -2,115 +2,187 @@ // Use of this source code is governed by a BSD-style // license that can be found in the LICENSE file. -// +build go1.11,!gccgo,!purego +// +build !gccgo,!purego #include "textflag.h" -// Implementation of Poly1305 using the vector facility (vx). - -// constants -#define MOD26 V0 -#define EX0 V1 -#define EX1 V2 -#define EX2 V3 - -// temporaries -#define T_0 V4 -#define T_1 V5 -#define T_2 V6 -#define T_3 V7 -#define T_4 V8 - -// key (r) -#define R_0 V9 -#define R_1 V10 -#define R_2 V11 -#define R_3 V12 -#define R_4 V13 -#define R5_1 V14 -#define R5_2 V15 -#define R5_3 V16 -#define R5_4 V17 -#define RSAVE_0 R5 -#define RSAVE_1 R6 -#define RSAVE_2 R7 -#define RSAVE_3 R8 -#define RSAVE_4 R9 -#define R5SAVE_1 V28 -#define R5SAVE_2 V29 -#define R5SAVE_3 V30 -#define R5SAVE_4 V31 - -// message block -#define F_0 V18 -#define F_1 V19 -#define F_2 V20 -#define F_3 V21 -#define F_4 V22 - -// accumulator -#define H_0 V23 -#define H_1 V24 -#define H_2 V25 -#define H_3 V26 -#define H_4 V27 - -GLOBL ·keyMask<>(SB), RODATA, $16 -DATA ·keyMask<>+0(SB)/8, $0xffffff0ffcffff0f -DATA ·keyMask<>+8(SB)/8, $0xfcffff0ffcffff0f - -GLOBL ·bswapMask<>(SB), RODATA, $16 -DATA ·bswapMask<>+0(SB)/8, $0x0f0e0d0c0b0a0908 -DATA ·bswapMask<>+8(SB)/8, $0x0706050403020100 - -GLOBL ·constants<>(SB), RODATA, $64 -// MOD26 -DATA ·constants<>+0(SB)/8, $0x3ffffff -DATA ·constants<>+8(SB)/8, $0x3ffffff +// This implementation of Poly1305 uses the vector facility (vx) +// to process up to 2 blocks (32 bytes) per iteration using an +// algorithm based on the one described in: +// +// NEON crypto, Daniel J. Bernstein & Peter Schwabe +// https://cryptojedi.org/papers/neoncrypto-20120320.pdf +// +// This algorithm uses 5 26-bit limbs to represent a 130-bit +// value. These limbs are, for the most part, zero extended and +// placed into 64-bit vector register elements. Each vector +// register is 128-bits wide and so holds 2 of these elements. +// Using 26-bit limbs allows us plenty of headroom to accomodate +// accumulations before and after multiplication without +// overflowing either 32-bits (before multiplication) or 64-bits +// (after multiplication). +// +// In order to parallelise the operations required to calculate +// the sum we use two separate accumulators and then sum those +// in an extra final step. For compatibility with the generic +// implementation we perform this summation at the end of every +// updateVX call. +// +// To use two accumulators we must multiply the message blocks +// by r² rather than r. Only the final message block should be +// multiplied by r. +// +// Example: +// +// We want to calculate the sum (h) for a 64 byte message (m): +// +// h = m[0:16]r⁴ + m[16:32]r³ + m[32:48]r² + m[48:64]r +// +// To do this we split the calculation into the even indices +// and odd indices of the message. These form our SIMD 'lanes': +// +// h = m[ 0:16]r⁴ + m[32:48]r² + <- lane 0 +// m[16:32]r³ + m[48:64]r <- lane 1 +// +// To calculate this iteratively we refactor so that both lanes +// are written in terms of r² and r: +// +// h = (m[ 0:16]r² + m[32:48])r² + <- lane 0 +// (m[16:32]r² + m[48:64])r <- lane 1 +// ^ ^ +// | coefficients for second iteration +// coefficients for first iteration +// +// So in this case we would have two iterations. In the first +// both lanes are multiplied by r². In the second only the +// first lane is multiplied by r² and the second lane is +// instead multiplied by r. This gives use the odd and even +// powers of r that we need from the original equation. +// +// Notation: +// +// h - accumulator +// r - key +// m - message +// +// [a, b] - SIMD register holding two 64-bit values +// [a, b, c, d] - SIMD register holding four 32-bit values +// xᵢ[n] - limb n of variable x with bit width i +// +// Limbs are expressed in little endian order, so for 26-bit +// limbs x₂₆[4] will be the most significant limb and x₂₆[0] +// will be the least significant limb. + +// masking constants +#define MOD24 V0 // [0x0000000000ffffff, 0x0000000000ffffff] - mask low 24-bits +#define MOD26 V1 // [0x0000000003ffffff, 0x0000000003ffffff] - mask low 26-bits + +// expansion constants (see EXPAND macro) +#define EX0 V2 +#define EX1 V3 +#define EX2 V4 + +// key (r², r or 1 depending on context) +#define R_0 V5 +#define R_1 V6 +#define R_2 V7 +#define R_3 V8 +#define R_4 V9 + +// precalculated coefficients (5r², 5r or 0 depending on context) +#define R5_1 V10 +#define R5_2 V11 +#define R5_3 V12 +#define R5_4 V13 + +// message block (m) +#define M_0 V14 +#define M_1 V15 +#define M_2 V16 +#define M_3 V17 +#define M_4 V18 + +// accumulator (h) +#define H_0 V19 +#define H_1 V20 +#define H_2 V21 +#define H_3 V22 +#define H_4 V23 + +// temporary registers (for short-lived values) +#define T_0 V24 +#define T_1 V25 +#define T_2 V26 +#define T_3 V27 +#define T_4 V28 + +GLOBL ·constants<>(SB), RODATA, $0x30 // EX0 -DATA ·constants<>+16(SB)/8, $0x0006050403020100 -DATA ·constants<>+24(SB)/8, $0x1016151413121110 +DATA ·constants<>+0x00(SB)/8, $0x0006050403020100 +DATA ·constants<>+0x08(SB)/8, $0x1016151413121110 // EX1 -DATA ·constants<>+32(SB)/8, $0x060c0b0a09080706 -DATA ·constants<>+40(SB)/8, $0x161c1b1a19181716 +DATA ·constants<>+0x10(SB)/8, $0x060c0b0a09080706 +DATA ·constants<>+0x18(SB)/8, $0x161c1b1a19181716 // EX2 -DATA ·constants<>+48(SB)/8, $0x0d0d0d0d0d0f0e0d -DATA ·constants<>+56(SB)/8, $0x1d1d1d1d1d1f1e1d - -// h = (f*g) % (2**130-5) [partial reduction] +DATA ·constants<>+0x20(SB)/8, $0x0d0d0d0d0d0f0e0d +DATA ·constants<>+0x28(SB)/8, $0x1d1d1d1d1d1f1e1d + +// MULTIPLY multiplies each lane of f and g, partially reduced +// modulo 2¹³⁰ - 5. The result, h, consists of partial products +// in each lane that need to be reduced further to produce the +// final result. +// +// h₁₃₀ = (f₁₃₀g₁₃₀) % 2¹³⁰ + (5f₁₃₀g₁₃₀) / 2¹³⁰ +// +// Note that the multiplication by 5 of the high bits is +// achieved by precalculating the multiplication of four of the +// g coefficients by 5. These are g51-g54. #define MULTIPLY(f0, f1, f2, f3, f4, g0, g1, g2, g3, g4, g51, g52, g53, g54, h0, h1, h2, h3, h4) \ VMLOF f0, g0, h0 \ - VMLOF f0, g1, h1 \ - VMLOF f0, g2, h2 \ VMLOF f0, g3, h3 \ + VMLOF f0, g1, h1 \ VMLOF f0, g4, h4 \ + VMLOF f0, g2, h2 \ VMLOF f1, g54, T_0 \ - VMLOF f1, g0, T_1 \ - VMLOF f1, g1, T_2 \ VMLOF f1, g2, T_3 \ + VMLOF f1, g0, T_1 \ VMLOF f1, g3, T_4 \ + VMLOF f1, g1, T_2 \ VMALOF f2, g53, h0, h0 \ - VMALOF f2, g54, h1, h1 \ - VMALOF f2, g0, h2, h2 \ VMALOF f2, g1, h3, h3 \ + VMALOF f2, g54, h1, h1 \ VMALOF f2, g2, h4, h4 \ + VMALOF f2, g0, h2, h2 \ VMALOF f3, g52, T_0, T_0 \ - VMALOF f3, g53, T_1, T_1 \ - VMALOF f3, g54, T_2, T_2 \ VMALOF f3, g0, T_3, T_3 \ + VMALOF f3, g53, T_1, T_1 \ VMALOF f3, g1, T_4, T_4 \ + VMALOF f3, g54, T_2, T_2 \ VMALOF f4, g51, h0, h0 \ - VMALOF f4, g52, h1, h1 \ - VMALOF f4, g53, h2, h2 \ VMALOF f4, g54, h3, h3 \ + VMALOF f4, g52, h1, h1 \ VMALOF f4, g0, h4, h4 \ + VMALOF f4, g53, h2, h2 \ VAG T_0, h0, h0 \ - VAG T_1, h1, h1 \ - VAG T_2, h2, h2 \ VAG T_3, h3, h3 \ - VAG T_4, h4, h4 - -// carry h0->h1 h3->h4, h1->h2 h4->h0, h0->h1 h2->h3, h3->h4 + VAG T_1, h1, h1 \ + VAG T_4, h4, h4 \ + VAG T_2, h2, h2 + +// REDUCE performs the following carry operations in four +// stages, as specified in Bernstein & Schwabe: +// +// 1: h₂₆[0]->h₂₆[1] h₂₆[3]->h₂₆[4] +// 2: h₂₆[1]->h₂₆[2] h₂₆[4]->h₂₆[0] +// 3: h₂₆[0]->h₂₆[1] h₂₆[2]->h₂₆[3] +// 4: h₂₆[3]->h₂₆[4] +// +// The result is that all of the limbs are limited to 26-bits +// except for h₂₆[1] and h₂₆[4] which are limited to 27-bits. +// +// Note that although each limb is aligned at 26-bit intervals +// they may contain values that exceed 2²⁶ - 1, hence the need +// to carry the excess bits in each limb. #define REDUCE(h0, h1, h2, h3, h4) \ VESRLG $26, h0, T_0 \ VESRLG $26, h3, T_1 \ @@ -136,144 +208,155 @@ DATA ·constants<>+56(SB)/8, $0x1d1d1d1d1d1f1e1d VN MOD26, h3, h3 \ VAG T_2, h4, h4 -// expand in0 into d[0] and in1 into d[1] +// EXPAND splits the 128-bit little-endian values in0 and in1 +// into 26-bit big-endian limbs and places the results into +// the first and second lane of d₂₆[0:4] respectively. +// +// The EX0, EX1 and EX2 constants are arrays of byte indices +// for permutation. The permutation both reverses the bytes +// in the input and ensures the bytes are copied into the +// destination limb ready to be shifted into their final +// position. #define EXPAND(in0, in1, d0, d1, d2, d3, d4) \ - VGBM $0x0707, d1 \ // d1=tmp - VPERM in0, in1, EX2, d4 \ VPERM in0, in1, EX0, d0 \ VPERM in0, in1, EX1, d2 \ - VN d1, d4, d4 \ + VPERM in0, in1, EX2, d4 \ VESRLG $26, d0, d1 \ VESRLG $30, d2, d3 \ VESRLG $4, d2, d2 \ - VN MOD26, d0, d0 \ - VN MOD26, d1, d1 \ - VN MOD26, d2, d2 \ - VN MOD26, d3, d3 - -// pack h4:h0 into h1:h0 (no carry) -#define PACK(h0, h1, h2, h3, h4) \ - VESLG $26, h1, h1 \ - VESLG $26, h3, h3 \ - VO h0, h1, h0 \ - VO h2, h3, h2 \ - VESLG $4, h2, h2 \ - VLEIB $7, $48, h1 \ - VSLB h1, h2, h2 \ - VO h0, h2, h0 \ - VLEIB $7, $104, h1 \ - VSLB h1, h4, h3 \ - VO h3, h0, h0 \ - VLEIB $7, $24, h1 \ - VSRLB h1, h4, h1 - -// if h > 2**130-5 then h -= 2**130-5 -#define MOD(h0, h1, t0, t1, t2) \ - VZERO t0 \ - VLEIG $1, $5, t0 \ - VACCQ h0, t0, t1 \ - VAQ h0, t0, t0 \ - VONE t2 \ - VLEIG $1, $-4, t2 \ - VAQ t2, t1, t1 \ - VACCQ h1, t1, t1 \ - VONE t2 \ - VAQ t2, t1, t1 \ - VN h0, t1, t2 \ - VNC t0, t1, t1 \ - VO t1, t2, h0 - -// func poly1305vx(out *[16]byte, m *byte, mlen uint64, key *[32]key) -TEXT ·poly1305vx(SB), $0-32 - // This code processes up to 2 blocks (32 bytes) per iteration - // using the algorithm described in: - // NEON crypto, Daniel J. Bernstein & Peter Schwabe - // https://cryptojedi.org/papers/neoncrypto-20120320.pdf - LMG out+0(FP), R1, R4 // R1=out, R2=m, R3=mlen, R4=key - - // load MOD26, EX0, EX1 and EX2 + VN MOD26, d0, d0 \ // [in0₂₆[0], in1₂₆[0]] + VN MOD26, d3, d3 \ // [in0₂₆[3], in1₂₆[3]] + VN MOD26, d1, d1 \ // [in0₂₆[1], in1₂₆[1]] + VN MOD24, d4, d4 \ // [in0₂₆[4], in1₂₆[4]] + VN MOD26, d2, d2 // [in0₂₆[2], in1₂₆[2]] + +// func updateVX(state *macState, msg []byte) +TEXT ·updateVX(SB), NOSPLIT, $0 + MOVD state+0(FP), R1 + LMG msg+8(FP), R2, R3 // R2=msg_base, R3=msg_len + + // load EX0, EX1 and EX2 MOVD $·constants<>(SB), R5 - VLM (R5), MOD26, EX2 - - // setup r - VL (R4), T_0 - MOVD $·keyMask<>(SB), R6 - VL (R6), T_1 - VN T_0, T_1, T_0 - EXPAND(T_0, T_0, R_0, R_1, R_2, R_3, R_4) - - // setup r*5 - VLEIG $0, $5, T_0 - VLEIG $1, $5, T_0 - - // store r (for final block) - VMLOF T_0, R_1, R5SAVE_1 - VMLOF T_0, R_2, R5SAVE_2 - VMLOF T_0, R_3, R5SAVE_3 - VMLOF T_0, R_4, R5SAVE_4 - VLGVG $0, R_0, RSAVE_0 - VLGVG $0, R_1, RSAVE_1 - VLGVG $0, R_2, RSAVE_2 - VLGVG $0, R_3, RSAVE_3 - VLGVG $0, R_4, RSAVE_4 - - // skip r**2 calculation + VLM (R5), EX0, EX2 + + // generate masks + VGMG $(64-24), $63, MOD24 // [0x00ffffff, 0x00ffffff] + VGMG $(64-26), $63, MOD26 // [0x03ffffff, 0x03ffffff] + + // load h (accumulator) and r (key) from state + VZERO T_1 // [0, 0] + VL 0(R1), T_0 // [h₆₄[0], h₆₄[1]] + VLEG $0, 16(R1), T_1 // [h₆₄[2], 0] + VL 24(R1), T_2 // [r₆₄[0], r₆₄[1]] + VPDI $0, T_0, T_2, T_3 // [h₆₄[0], r₆₄[0]] + VPDI $5, T_0, T_2, T_4 // [h₆₄[1], r₆₄[1]] + + // unpack h and r into 26-bit limbs + // note: h₆₄[2] may have the low 3 bits set, so h₂₆[4] is a 27-bit value + VN MOD26, T_3, H_0 // [h₂₆[0], r₂₆[0]] + VZERO H_1 // [0, 0] + VZERO H_3 // [0, 0] + VGMG $(64-12-14), $(63-12), T_0 // [0x03fff000, 0x03fff000] - 26-bit mask with low 12 bits masked out + VESLG $24, T_1, T_1 // [h₆₄[2]<<24, 0] + VERIMG $-26&63, T_3, MOD26, H_1 // [h₂₆[1], r₂₆[1]] + VESRLG $+52&63, T_3, H_2 // [h₂₆[2], r₂₆[2]] - low 12 bits only + VERIMG $-14&63, T_4, MOD26, H_3 // [h₂₆[1], r₂₆[1]] + VESRLG $40, T_4, H_4 // [h₂₆[4], r₂₆[4]] - low 24 bits only + VERIMG $+12&63, T_4, T_0, H_2 // [h₂₆[2], r₂₆[2]] - complete + VO T_1, H_4, H_4 // [h₂₆[4], r₂₆[4]] - complete + + // replicate r across all 4 vector elements + VREPF $3, H_0, R_0 // [r₂₆[0], r₂₆[0], r₂₆[0], r₂₆[0]] + VREPF $3, H_1, R_1 // [r₂₆[1], r₂₆[1], r₂₆[1], r₂₆[1]] + VREPF $3, H_2, R_2 // [r₂₆[2], r₂₆[2], r₂₆[2], r₂₆[2]] + VREPF $3, H_3, R_3 // [r₂₆[3], r₂₆[3], r₂₆[3], r₂₆[3]] + VREPF $3, H_4, R_4 // [r₂₆[4], r₂₆[4], r₂₆[4], r₂₆[4]] + + // zero out lane 1 of h + VLEIG $1, $0, H_0 // [h₂₆[0], 0] + VLEIG $1, $0, H_1 // [h₂₆[1], 0] + VLEIG $1, $0, H_2 // [h₂₆[2], 0] + VLEIG $1, $0, H_3 // [h₂₆[3], 0] + VLEIG $1, $0, H_4 // [h₂₆[4], 0] + + // calculate 5r (ignore least significant limb) + VREPIF $5, T_0 + VMLF T_0, R_1, R5_1 // [5r₂₆[1], 5r₂₆[1], 5r₂₆[1], 5r₂₆[1]] + VMLF T_0, R_2, R5_2 // [5r₂₆[2], 5r₂₆[2], 5r₂₆[2], 5r₂₆[2]] + VMLF T_0, R_3, R5_3 // [5r₂₆[3], 5r₂₆[3], 5r₂₆[3], 5r₂₆[3]] + VMLF T_0, R_4, R5_4 // [5r₂₆[4], 5r₂₆[4], 5r₂₆[4], 5r₂₆[4]] + + // skip r² calculation if we are only calculating one block CMPBLE R3, $16, skip - // calculate r**2 - MULTIPLY(R_0, R_1, R_2, R_3, R_4, R_0, R_1, R_2, R_3, R_4, R5SAVE_1, R5SAVE_2, R5SAVE_3, R5SAVE_4, H_0, H_1, H_2, H_3, H_4) - REDUCE(H_0, H_1, H_2, H_3, H_4) - VLEIG $0, $5, T_0 - VLEIG $1, $5, T_0 - VMLOF T_0, H_1, R5_1 - VMLOF T_0, H_2, R5_2 - VMLOF T_0, H_3, R5_3 - VMLOF T_0, H_4, R5_4 - VLR H_0, R_0 - VLR H_1, R_1 - VLR H_2, R_2 - VLR H_3, R_3 - VLR H_4, R_4 - - // initialize h - VZERO H_0 - VZERO H_1 - VZERO H_2 - VZERO H_3 - VZERO H_4 + // calculate r² + MULTIPLY(R_0, R_1, R_2, R_3, R_4, R_0, R_1, R_2, R_3, R_4, R5_1, R5_2, R5_3, R5_4, M_0, M_1, M_2, M_3, M_4) + REDUCE(M_0, M_1, M_2, M_3, M_4) + VGBM $0x0f0f, T_0 + VERIMG $0, M_0, T_0, R_0 // [r₂₆[0], r²₂₆[0], r₂₆[0], r²₂₆[0]] + VERIMG $0, M_1, T_0, R_1 // [r₂₆[1], r²₂₆[1], r₂₆[1], r²₂₆[1]] + VERIMG $0, M_2, T_0, R_2 // [r₂₆[2], r²₂₆[2], r₂₆[2], r²₂₆[2]] + VERIMG $0, M_3, T_0, R_3 // [r₂₆[3], r²₂₆[3], r₂₆[3], r²₂₆[3]] + VERIMG $0, M_4, T_0, R_4 // [r₂₆[4], r²₂₆[4], r₂₆[4], r²₂₆[4]] + + // calculate 5r² (ignore least significant limb) + VREPIF $5, T_0 + VMLF T_0, R_1, R5_1 // [5r₂₆[1], 5r²₂₆[1], 5r₂₆[1], 5r²₂₆[1]] + VMLF T_0, R_2, R5_2 // [5r₂₆[2], 5r²₂₆[2], 5r₂₆[2], 5r²₂₆[2]] + VMLF T_0, R_3, R5_3 // [5r₂₆[3], 5r²₂₆[3], 5r₂₆[3], 5r²₂₆[3]] + VMLF T_0, R_4, R5_4 // [5r₂₆[4], 5r²₂₆[4], 5r₂₆[4], 5r²₂₆[4]] loop: - CMPBLE R3, $32, b2 - VLM (R2), T_0, T_1 - SUB $32, R3 - MOVD $32(R2), R2 - EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4) - VLEIB $4, $1, F_4 - VLEIB $12, $1, F_4 + CMPBLE R3, $32, b2 // 2 or fewer blocks remaining, need to change key coefficients + + // load next 2 blocks from message + VLM (R2), T_0, T_1 + + // update message slice + SUB $32, R3 + MOVD $32(R2), R2 + + // unpack message blocks into 26-bit big-endian limbs + EXPAND(T_0, T_1, M_0, M_1, M_2, M_3, M_4) + + // add 2¹²⁸ to each message block value + VLEIB $4, $1, M_4 + VLEIB $12, $1, M_4 multiply: - VAG H_0, F_0, F_0 - VAG H_1, F_1, F_1 - VAG H_2, F_2, F_2 - VAG H_3, F_3, F_3 - VAG H_4, F_4, F_4 - MULTIPLY(F_0, F_1, F_2, F_3, F_4, R_0, R_1, R_2, R_3, R_4, R5_1, R5_2, R5_3, R5_4, H_0, H_1, H_2, H_3, H_4) + // accumulate the incoming message + VAG H_0, M_0, M_0 + VAG H_3, M_3, M_3 + VAG H_1, M_1, M_1 + VAG H_4, M_4, M_4 + VAG H_2, M_2, M_2 + + // multiply the accumulator by the key coefficient + MULTIPLY(M_0, M_1, M_2, M_3, M_4, R_0, R_1, R_2, R_3, R_4, R5_1, R5_2, R5_3, R5_4, H_0, H_1, H_2, H_3, H_4) + + // carry and partially reduce the partial products REDUCE(H_0, H_1, H_2, H_3, H_4) + CMPBNE R3, $0, loop finish: - // sum vectors + // sum lane 0 and lane 1 and put the result in lane 1 VZERO T_0 VSUMQG H_0, T_0, H_0 - VSUMQG H_1, T_0, H_1 - VSUMQG H_2, T_0, H_2 VSUMQG H_3, T_0, H_3 + VSUMQG H_1, T_0, H_1 VSUMQG H_4, T_0, H_4 + VSUMQG H_2, T_0, H_2 - // h may be >= 2*(2**130-5) so we need to reduce it again + // reduce again after summation + // TODO(mundaym): there might be a more efficient way to do this + // now that we only have 1 active lane. For example, we could + // simultaneously pack the values as we reduce them. REDUCE(H_0, H_1, H_2, H_3, H_4) - // carry h1->h4 + // carry h[1] through to h[4] so that only h[4] can exceed 2²⁶ - 1 + // TODO(mundaym): in testing this final carry was unnecessary. + // Needs a proof before it can be removed though. VESRLG $26, H_1, T_1 VN MOD26, H_1, H_1 VAQ T_1, H_2, H_2 @@ -284,95 +367,137 @@ finish: VN MOD26, H_3, H_3 VAQ T_3, H_4, H_4 - // h is now < 2*(2**130-5) - // pack h into h1 (hi) and h0 (lo) - PACK(H_0, H_1, H_2, H_3, H_4) - - // if h > 2**130-5 then h -= 2**130-5 - MOD(H_0, H_1, T_0, T_1, T_2) - - // h += s - MOVD $·bswapMask<>(SB), R5 - VL (R5), T_1 - VL 16(R4), T_0 - VPERM T_0, T_0, T_1, T_0 // reverse bytes (to big) - VAQ T_0, H_0, H_0 - VPERM H_0, H_0, T_1, H_0 // reverse bytes (to little) - VST H_0, (R1) - + // h is now < 2(2¹³⁰ - 5) + // Pack each lane in h₂₆[0:4] into h₁₂₈[0:1]. + VESLG $26, H_1, H_1 + VESLG $26, H_3, H_3 + VO H_0, H_1, H_0 + VO H_2, H_3, H_2 + VESLG $4, H_2, H_2 + VLEIB $7, $48, H_1 + VSLB H_1, H_2, H_2 + VO H_0, H_2, H_0 + VLEIB $7, $104, H_1 + VSLB H_1, H_4, H_3 + VO H_3, H_0, H_0 + VLEIB $7, $24, H_1 + VSRLB H_1, H_4, H_1 + + // update state + VSTEG $1, H_0, 0(R1) + VSTEG $0, H_0, 8(R1) + VSTEG $1, H_1, 16(R1) RET -b2: +b2: // 2 or fewer blocks remaining CMPBLE R3, $16, b1 - // 2 blocks remaining - SUB $17, R3 - VL (R2), T_0 - VLL R3, 16(R2), T_1 - ADD $1, R3 + // Load the 2 remaining blocks (17-32 bytes remaining). + MOVD $-17(R3), R0 // index of final byte to load modulo 16 + VL (R2), T_0 // load full 16 byte block + VLL R0, 16(R2), T_1 // load final (possibly partial) block and pad with zeros to 16 bytes + + // The Poly1305 algorithm requires that a 1 bit be appended to + // each message block. If the final block is less than 16 bytes + // long then it is easiest to insert the 1 before the message + // block is split into 26-bit limbs. If, on the other hand, the + // final message block is 16 bytes long then we append the 1 bit + // after expansion as normal. MOVBZ $1, R0 - CMPBEQ R3, $16, 2(PC) - VLVGB R3, R0, T_1 - EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4) + MOVD $-16(R3), R3 // index of byte in last block to insert 1 at (could be 16) + CMPBEQ R3, $16, 2(PC) // skip the insertion if the final block is 16 bytes long + VLVGB R3, R0, T_1 // insert 1 into the byte at index R3 + + // Split both blocks into 26-bit limbs in the appropriate lanes. + EXPAND(T_0, T_1, M_0, M_1, M_2, M_3, M_4) + + // Append a 1 byte to the end of the second to last block. + VLEIB $4, $1, M_4 + + // Append a 1 byte to the end of the last block only if it is a + // full 16 byte block. CMPBNE R3, $16, 2(PC) - VLEIB $12, $1, F_4 - VLEIB $4, $1, F_4 - - // setup [r²,r] - VLVGG $1, RSAVE_0, R_0 - VLVGG $1, RSAVE_1, R_1 - VLVGG $1, RSAVE_2, R_2 - VLVGG $1, RSAVE_3, R_3 - VLVGG $1, RSAVE_4, R_4 - VPDI $0, R5_1, R5SAVE_1, R5_1 - VPDI $0, R5_2, R5SAVE_2, R5_2 - VPDI $0, R5_3, R5SAVE_3, R5_3 - VPDI $0, R5_4, R5SAVE_4, R5_4 + VLEIB $12, $1, M_4 + + // Finally, set up the coefficients for the final multiplication. + // We have previously saved r and 5r in the 32-bit even indexes + // of the R_[0-4] and R5_[1-4] coefficient registers. + // + // We want lane 0 to be multiplied by r² so that can be kept the + // same. We want lane 1 to be multiplied by r so we need to move + // the saved r value into the 32-bit odd index in lane 1 by + // rotating the 64-bit lane by 32. + VGBM $0x00ff, T_0 // [0, 0xffffffffffffffff] - mask lane 1 only + VERIMG $32, R_0, T_0, R_0 // [_, r²₂₆[0], _, r₂₆[0]] + VERIMG $32, R_1, T_0, R_1 // [_, r²₂₆[1], _, r₂₆[1]] + VERIMG $32, R_2, T_0, R_2 // [_, r²₂₆[2], _, r₂₆[2]] + VERIMG $32, R_3, T_0, R_3 // [_, r²₂₆[3], _, r₂₆[3]] + VERIMG $32, R_4, T_0, R_4 // [_, r²₂₆[4], _, r₂₆[4]] + VERIMG $32, R5_1, T_0, R5_1 // [_, 5r²₂₆[1], _, 5r₂₆[1]] + VERIMG $32, R5_2, T_0, R5_2 // [_, 5r²₂₆[2], _, 5r₂₆[2]] + VERIMG $32, R5_3, T_0, R5_3 // [_, 5r²₂₆[3], _, 5r₂₆[3]] + VERIMG $32, R5_4, T_0, R5_4 // [_, 5r²₂₆[4], _, 5r₂₆[4]] MOVD $0, R3 BR multiply skip: - VZERO H_0 - VZERO H_1 - VZERO H_2 - VZERO H_3 - VZERO H_4 - CMPBEQ R3, $0, finish -b1: - // 1 block remaining - SUB $1, R3 - VLL R3, (R2), T_0 - ADD $1, R3 +b1: // 1 block remaining + + // Load the final block (1-16 bytes). This will be placed into + // lane 0. + MOVD $-1(R3), R0 + VLL R0, (R2), T_0 // pad to 16 bytes with zeros + + // The Poly1305 algorithm requires that a 1 bit be appended to + // each message block. If the final block is less than 16 bytes + // long then it is easiest to insert the 1 before the message + // block is split into 26-bit limbs. If, on the other hand, the + // final message block is 16 bytes long then we append the 1 bit + // after expansion as normal. MOVBZ $1, R0 CMPBEQ R3, $16, 2(PC) VLVGB R3, R0, T_0 - VZERO T_1 - EXPAND(T_0, T_1, F_0, F_1, F_2, F_3, F_4) + + // Set the message block in lane 1 to the value 0 so that it + // can be accumulated without affecting the final result. + VZERO T_1 + + // Split the final message block into 26-bit limbs in lane 0. + // Lane 1 will be contain 0. + EXPAND(T_0, T_1, M_0, M_1, M_2, M_3, M_4) + + // Append a 1 byte to the end of the last block only if it is a + // full 16 byte block. CMPBNE R3, $16, 2(PC) - VLEIB $4, $1, F_4 - VLEIG $1, $1, R_0 - VZERO R_1 - VZERO R_2 - VZERO R_3 - VZERO R_4 - VZERO R5_1 - VZERO R5_2 - VZERO R5_3 - VZERO R5_4 - - // setup [r, 1] - VLVGG $0, RSAVE_0, R_0 - VLVGG $0, RSAVE_1, R_1 - VLVGG $0, RSAVE_2, R_2 - VLVGG $0, RSAVE_3, R_3 - VLVGG $0, RSAVE_4, R_4 - VPDI $0, R5SAVE_1, R5_1, R5_1 - VPDI $0, R5SAVE_2, R5_2, R5_2 - VPDI $0, R5SAVE_3, R5_3, R5_3 - VPDI $0, R5SAVE_4, R5_4, R5_4 + VLEIB $4, $1, M_4 + + // We have previously saved r and 5r in the 32-bit even indexes + // of the R_[0-4] and R5_[1-4] coefficient registers. + // + // We want lane 0 to be multiplied by r so we need to move the + // saved r value into the 32-bit odd index in lane 0. We want + // lane 1 to be set to the value 1. This makes multiplication + // a no-op. We do this by setting lane 1 in every register to 0 + // and then just setting the 32-bit index 3 in R_0 to 1. + VZERO T_0 + MOVD $0, R0 + MOVD $0x10111213, R12 + VLVGP R12, R0, T_1 // [_, 0x10111213, _, 0x00000000] + VPERM T_0, R_0, T_1, R_0 // [_, r₂₆[0], _, 0] + VPERM T_0, R_1, T_1, R_1 // [_, r₂₆[1], _, 0] + VPERM T_0, R_2, T_1, R_2 // [_, r₂₆[2], _, 0] + VPERM T_0, R_3, T_1, R_3 // [_, r₂₆[3], _, 0] + VPERM T_0, R_4, T_1, R_4 // [_, r₂₆[4], _, 0] + VPERM T_0, R5_1, T_1, R5_1 // [_, 5r₂₆[1], _, 0] + VPERM T_0, R5_2, T_1, R5_2 // [_, 5r₂₆[2], _, 0] + VPERM T_0, R5_3, T_1, R5_3 // [_, 5r₂₆[3], _, 0] + VPERM T_0, R5_4, T_1, R5_4 // [_, 5r₂₆[4], _, 0] + + // Set the value of lane 1 to be 1. + VLEIF $3, $1, R_0 // [_, r₂₆[0], _, 1] MOVD $0, R3 BR multiply diff --git a/vendor/golang.org/x/crypto/poly1305/sum_vmsl_s390x.s b/vendor/golang.org/x/crypto/poly1305/sum_vmsl_s390x.s deleted file mode 100644 index b439af936..000000000 --- a/vendor/golang.org/x/crypto/poly1305/sum_vmsl_s390x.s +++ /dev/null @@ -1,909 +0,0 @@ -// Copyright 2018 The Go Authors. All rights reserved. -// Use of this source code is governed by a BSD-style -// license that can be found in the LICENSE file. - -// +build go1.11,!gccgo,!purego - -#include "textflag.h" - -// Implementation of Poly1305 using the vector facility (vx) and the VMSL instruction. - -// constants -#define EX0 V1 -#define EX1 V2 -#define EX2 V3 - -// temporaries -#define T_0 V4 -#define T_1 V5 -#define T_2 V6 -#define T_3 V7 -#define T_4 V8 -#define T_5 V9 -#define T_6 V10 -#define T_7 V11 -#define T_8 V12 -#define T_9 V13 -#define T_10 V14 - -// r**2 & r**4 -#define R_0 V15 -#define R_1 V16 -#define R_2 V17 -#define R5_1 V18 -#define R5_2 V19 -// key (r) -#define RSAVE_0 R7 -#define RSAVE_1 R8 -#define RSAVE_2 R9 -#define R5SAVE_1 R10 -#define R5SAVE_2 R11 - -// message block -#define M0 V20 -#define M1 V21 -#define M2 V22 -#define M3 V23 -#define M4 V24 -#define M5 V25 - -// accumulator -#define H0_0 V26 -#define H1_0 V27 -#define H2_0 V28 -#define H0_1 V29 -#define H1_1 V30 -#define H2_1 V31 - -GLOBL ·keyMask<>(SB), RODATA, $16 -DATA ·keyMask<>+0(SB)/8, $0xffffff0ffcffff0f -DATA ·keyMask<>+8(SB)/8, $0xfcffff0ffcffff0f - -GLOBL ·bswapMask<>(SB), RODATA, $16 -DATA ·bswapMask<>+0(SB)/8, $0x0f0e0d0c0b0a0908 -DATA ·bswapMask<>+8(SB)/8, $0x0706050403020100 - -GLOBL ·constants<>(SB), RODATA, $48 -// EX0 -DATA ·constants<>+0(SB)/8, $0x18191a1b1c1d1e1f -DATA ·constants<>+8(SB)/8, $0x0000050403020100 -// EX1 -DATA ·constants<>+16(SB)/8, $0x18191a1b1c1d1e1f -DATA ·constants<>+24(SB)/8, $0x00000a0908070605 -// EX2 -DATA ·constants<>+32(SB)/8, $0x18191a1b1c1d1e1f -DATA ·constants<>+40(SB)/8, $0x0000000f0e0d0c0b - -GLOBL ·c<>(SB), RODATA, $48 -// EX0 -DATA ·c<>+0(SB)/8, $0x0000050403020100 -DATA ·c<>+8(SB)/8, $0x0000151413121110 -// EX1 -DATA ·c<>+16(SB)/8, $0x00000a0908070605 -DATA ·c<>+24(SB)/8, $0x00001a1918171615 -// EX2 -DATA ·c<>+32(SB)/8, $0x0000000f0e0d0c0b -DATA ·c<>+40(SB)/8, $0x0000001f1e1d1c1b - -GLOBL ·reduce<>(SB), RODATA, $32 -// 44 bit -DATA ·reduce<>+0(SB)/8, $0x0 -DATA ·reduce<>+8(SB)/8, $0xfffffffffff -// 42 bit -DATA ·reduce<>+16(SB)/8, $0x0 -DATA ·reduce<>+24(SB)/8, $0x3ffffffffff - -// h = (f*g) % (2**130-5) [partial reduction] -// uses T_0...T_9 temporary registers -// input: m02_0, m02_1, m02_2, m13_0, m13_1, m13_2, r_0, r_1, r_2, r5_1, r5_2, m4_0, m4_1, m4_2, m5_0, m5_1, m5_2 -// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8, t9 -// output: m02_0, m02_1, m02_2, m13_0, m13_1, m13_2 -#define MULTIPLY(m02_0, m02_1, m02_2, m13_0, m13_1, m13_2, r_0, r_1, r_2, r5_1, r5_2, m4_0, m4_1, m4_2, m5_0, m5_1, m5_2, t0, t1, t2, t3, t4, t5, t6, t7, t8, t9) \ - \ // Eliminate the dependency for the last 2 VMSLs - VMSLG m02_0, r_2, m4_2, m4_2 \ - VMSLG m13_0, r_2, m5_2, m5_2 \ // 8 VMSLs pipelined - VMSLG m02_0, r_0, m4_0, m4_0 \ - VMSLG m02_1, r5_2, V0, T_0 \ - VMSLG m02_0, r_1, m4_1, m4_1 \ - VMSLG m02_1, r_0, V0, T_1 \ - VMSLG m02_1, r_1, V0, T_2 \ - VMSLG m02_2, r5_1, V0, T_3 \ - VMSLG m02_2, r5_2, V0, T_4 \ - VMSLG m13_0, r_0, m5_0, m5_0 \ - VMSLG m13_1, r5_2, V0, T_5 \ - VMSLG m13_0, r_1, m5_1, m5_1 \ - VMSLG m13_1, r_0, V0, T_6 \ - VMSLG m13_1, r_1, V0, T_7 \ - VMSLG m13_2, r5_1, V0, T_8 \ - VMSLG m13_2, r5_2, V0, T_9 \ - VMSLG m02_2, r_0, m4_2, m4_2 \ - VMSLG m13_2, r_0, m5_2, m5_2 \ - VAQ m4_0, T_0, m02_0 \ - VAQ m4_1, T_1, m02_1 \ - VAQ m5_0, T_5, m13_0 \ - VAQ m5_1, T_6, m13_1 \ - VAQ m02_0, T_3, m02_0 \ - VAQ m02_1, T_4, m02_1 \ - VAQ m13_0, T_8, m13_0 \ - VAQ m13_1, T_9, m13_1 \ - VAQ m4_2, T_2, m02_2 \ - VAQ m5_2, T_7, m13_2 \ - -// SQUARE uses three limbs of r and r_2*5 to output square of r -// uses T_1, T_5 and T_7 temporary registers -// input: r_0, r_1, r_2, r5_2 -// temp: TEMP0, TEMP1, TEMP2 -// output: p0, p1, p2 -#define SQUARE(r_0, r_1, r_2, r5_2, p0, p1, p2, TEMP0, TEMP1, TEMP2) \ - VMSLG r_0, r_0, p0, p0 \ - VMSLG r_1, r5_2, V0, TEMP0 \ - VMSLG r_2, r5_2, p1, p1 \ - VMSLG r_0, r_1, V0, TEMP1 \ - VMSLG r_1, r_1, p2, p2 \ - VMSLG r_0, r_2, V0, TEMP2 \ - VAQ TEMP0, p0, p0 \ - VAQ TEMP1, p1, p1 \ - VAQ TEMP2, p2, p2 \ - VAQ TEMP0, p0, p0 \ - VAQ TEMP1, p1, p1 \ - VAQ TEMP2, p2, p2 \ - -// carry h0->h1->h2->h0 || h3->h4->h5->h3 -// uses T_2, T_4, T_5, T_7, T_8, T_9 -// t6, t7, t8, t9, t10, t11 -// input: h0, h1, h2, h3, h4, h5 -// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11 -// output: h0, h1, h2, h3, h4, h5 -#define REDUCE(h0, h1, h2, h3, h4, h5, t0, t1, t2, t3, t4, t5, t6, t7, t8, t9, t10, t11) \ - VLM (R12), t6, t7 \ // 44 and 42 bit clear mask - VLEIB $7, $0x28, t10 \ // 5 byte shift mask - VREPIB $4, t8 \ // 4 bit shift mask - VREPIB $2, t11 \ // 2 bit shift mask - VSRLB t10, h0, t0 \ // h0 byte shift - VSRLB t10, h1, t1 \ // h1 byte shift - VSRLB t10, h2, t2 \ // h2 byte shift - VSRLB t10, h3, t3 \ // h3 byte shift - VSRLB t10, h4, t4 \ // h4 byte shift - VSRLB t10, h5, t5 \ // h5 byte shift - VSRL t8, t0, t0 \ // h0 bit shift - VSRL t8, t1, t1 \ // h2 bit shift - VSRL t11, t2, t2 \ // h2 bit shift - VSRL t8, t3, t3 \ // h3 bit shift - VSRL t8, t4, t4 \ // h4 bit shift - VESLG $2, t2, t9 \ // h2 carry x5 - VSRL t11, t5, t5 \ // h5 bit shift - VN t6, h0, h0 \ // h0 clear carry - VAQ t2, t9, t2 \ // h2 carry x5 - VESLG $2, t5, t9 \ // h5 carry x5 - VN t6, h1, h1 \ // h1 clear carry - VN t7, h2, h2 \ // h2 clear carry - VAQ t5, t9, t5 \ // h5 carry x5 - VN t6, h3, h3 \ // h3 clear carry - VN t6, h4, h4 \ // h4 clear carry - VN t7, h5, h5 \ // h5 clear carry - VAQ t0, h1, h1 \ // h0->h1 - VAQ t3, h4, h4 \ // h3->h4 - VAQ t1, h2, h2 \ // h1->h2 - VAQ t4, h5, h5 \ // h4->h5 - VAQ t2, h0, h0 \ // h2->h0 - VAQ t5, h3, h3 \ // h5->h3 - VREPG $1, t6, t6 \ // 44 and 42 bit masks across both halves - VREPG $1, t7, t7 \ - VSLDB $8, h0, h0, h0 \ // set up [h0/1/2, h3/4/5] - VSLDB $8, h1, h1, h1 \ - VSLDB $8, h2, h2, h2 \ - VO h0, h3, h3 \ - VO h1, h4, h4 \ - VO h2, h5, h5 \ - VESRLG $44, h3, t0 \ // 44 bit shift right - VESRLG $44, h4, t1 \ - VESRLG $42, h5, t2 \ - VN t6, h3, h3 \ // clear carry bits - VN t6, h4, h4 \ - VN t7, h5, h5 \ - VESLG $2, t2, t9 \ // multiply carry by 5 - VAQ t9, t2, t2 \ - VAQ t0, h4, h4 \ - VAQ t1, h5, h5 \ - VAQ t2, h3, h3 \ - -// carry h0->h1->h2->h0 -// input: h0, h1, h2 -// temp: t0, t1, t2, t3, t4, t5, t6, t7, t8 -// output: h0, h1, h2 -#define REDUCE2(h0, h1, h2, t0, t1, t2, t3, t4, t5, t6, t7, t8) \ - VLEIB $7, $0x28, t3 \ // 5 byte shift mask - VREPIB $4, t4 \ // 4 bit shift mask - VREPIB $2, t7 \ // 2 bit shift mask - VGBM $0x003F, t5 \ // mask to clear carry bits - VSRLB t3, h0, t0 \ - VSRLB t3, h1, t1 \ - VSRLB t3, h2, t2 \ - VESRLG $4, t5, t5 \ // 44 bit clear mask - VSRL t4, t0, t0 \ - VSRL t4, t1, t1 \ - VSRL t7, t2, t2 \ - VESRLG $2, t5, t6 \ // 42 bit clear mask - VESLG $2, t2, t8 \ - VAQ t8, t2, t2 \ - VN t5, h0, h0 \ - VN t5, h1, h1 \ - VN t6, h2, h2 \ - VAQ t0, h1, h1 \ - VAQ t1, h2, h2 \ - VAQ t2, h0, h0 \ - VSRLB t3, h0, t0 \ - VSRLB t3, h1, t1 \ - VSRLB t3, h2, t2 \ - VSRL t4, t0, t0 \ - VSRL t4, t1, t1 \ - VSRL t7, t2, t2 \ - VN t5, h0, h0 \ - VN t5, h1, h1 \ - VESLG $2, t2, t8 \ - VN t6, h2, h2 \ - VAQ t0, h1, h1 \ - VAQ t8, t2, t2 \ - VAQ t1, h2, h2 \ - VAQ t2, h0, h0 \ - -// expands two message blocks into the lower halfs of the d registers -// moves the contents of the d registers into upper halfs -// input: in1, in2, d0, d1, d2, d3, d4, d5 -// temp: TEMP0, TEMP1, TEMP2, TEMP3 -// output: d0, d1, d2, d3, d4, d5 -#define EXPACC(in1, in2, d0, d1, d2, d3, d4, d5, TEMP0, TEMP1, TEMP2, TEMP3) \ - VGBM $0xff3f, TEMP0 \ - VGBM $0xff1f, TEMP1 \ - VESLG $4, d1, TEMP2 \ - VESLG $4, d4, TEMP3 \ - VESRLG $4, TEMP0, TEMP0 \ - VPERM in1, d0, EX0, d0 \ - VPERM in2, d3, EX0, d3 \ - VPERM in1, d2, EX2, d2 \ - VPERM in2, d5, EX2, d5 \ - VPERM in1, TEMP2, EX1, d1 \ - VPERM in2, TEMP3, EX1, d4 \ - VN TEMP0, d0, d0 \ - VN TEMP0, d3, d3 \ - VESRLG $4, d1, d1 \ - VESRLG $4, d4, d4 \ - VN TEMP1, d2, d2 \ - VN TEMP1, d5, d5 \ - VN TEMP0, d1, d1 \ - VN TEMP0, d4, d4 \ - -// expands one message block into the lower halfs of the d registers -// moves the contents of the d registers into upper halfs -// input: in, d0, d1, d2 -// temp: TEMP0, TEMP1, TEMP2 -// output: d0, d1, d2 -#define EXPACC2(in, d0, d1, d2, TEMP0, TEMP1, TEMP2) \ - VGBM $0xff3f, TEMP0 \ - VESLG $4, d1, TEMP2 \ - VGBM $0xff1f, TEMP1 \ - VPERM in, d0, EX0, d0 \ - VESRLG $4, TEMP0, TEMP0 \ - VPERM in, d2, EX2, d2 \ - VPERM in, TEMP2, EX1, d1 \ - VN TEMP0, d0, d0 \ - VN TEMP1, d2, d2 \ - VESRLG $4, d1, d1 \ - VN TEMP0, d1, d1 \ - -// pack h2:h0 into h1:h0 (no carry) -// input: h0, h1, h2 -// output: h0, h1, h2 -#define PACK(h0, h1, h2) \ - VMRLG h1, h2, h2 \ // copy h1 to upper half h2 - VESLG $44, h1, h1 \ // shift limb 1 44 bits, leaving 20 - VO h0, h1, h0 \ // combine h0 with 20 bits from limb 1 - VESRLG $20, h2, h1 \ // put top 24 bits of limb 1 into h1 - VLEIG $1, $0, h1 \ // clear h2 stuff from lower half of h1 - VO h0, h1, h0 \ // h0 now has 88 bits (limb 0 and 1) - VLEIG $0, $0, h2 \ // clear upper half of h2 - VESRLG $40, h2, h1 \ // h1 now has upper two bits of result - VLEIB $7, $88, h1 \ // for byte shift (11 bytes) - VSLB h1, h2, h2 \ // shift h2 11 bytes to the left - VO h0, h2, h0 \ // combine h0 with 20 bits from limb 1 - VLEIG $0, $0, h1 \ // clear upper half of h1 - -// if h > 2**130-5 then h -= 2**130-5 -// input: h0, h1 -// temp: t0, t1, t2 -// output: h0 -#define MOD(h0, h1, t0, t1, t2) \ - VZERO t0 \ - VLEIG $1, $5, t0 \ - VACCQ h0, t0, t1 \ - VAQ h0, t0, t0 \ - VONE t2 \ - VLEIG $1, $-4, t2 \ - VAQ t2, t1, t1 \ - VACCQ h1, t1, t1 \ - VONE t2 \ - VAQ t2, t1, t1 \ - VN h0, t1, t2 \ - VNC t0, t1, t1 \ - VO t1, t2, h0 \ - -// func poly1305vmsl(out *[16]byte, m *byte, mlen uint64, key *[32]key) -TEXT ·poly1305vmsl(SB), $0-32 - // This code processes 6 + up to 4 blocks (32 bytes) per iteration - // using the algorithm described in: - // NEON crypto, Daniel J. Bernstein & Peter Schwabe - // https://cryptojedi.org/papers/neoncrypto-20120320.pdf - // And as moddified for VMSL as described in - // Accelerating Poly1305 Cryptographic Message Authentication on the z14 - // O'Farrell et al, CASCON 2017, p48-55 - // https://ibm.ent.box.com/s/jf9gedj0e9d2vjctfyh186shaztavnht - - LMG out+0(FP), R1, R4 // R1=out, R2=m, R3=mlen, R4=key - VZERO V0 // c - - // load EX0, EX1 and EX2 - MOVD $·constants<>(SB), R5 - VLM (R5), EX0, EX2 // c - - // setup r - VL (R4), T_0 - MOVD $·keyMask<>(SB), R6 - VL (R6), T_1 - VN T_0, T_1, T_0 - VZERO T_2 // limbs for r - VZERO T_3 - VZERO T_4 - EXPACC2(T_0, T_2, T_3, T_4, T_1, T_5, T_7) - - // T_2, T_3, T_4: [0, r] - - // setup r*20 - VLEIG $0, $0, T_0 - VLEIG $1, $20, T_0 // T_0: [0, 20] - VZERO T_5 - VZERO T_6 - VMSLG T_0, T_3, T_5, T_5 - VMSLG T_0, T_4, T_6, T_6 - - // store r for final block in GR - VLGVG $1, T_2, RSAVE_0 // c - VLGVG $1, T_3, RSAVE_1 // c - VLGVG $1, T_4, RSAVE_2 // c - VLGVG $1, T_5, R5SAVE_1 // c - VLGVG $1, T_6, R5SAVE_2 // c - - // initialize h - VZERO H0_0 - VZERO H1_0 - VZERO H2_0 - VZERO H0_1 - VZERO H1_1 - VZERO H2_1 - - // initialize pointer for reduce constants - MOVD $·reduce<>(SB), R12 - - // calculate r**2 and 20*(r**2) - VZERO R_0 - VZERO R_1 - VZERO R_2 - SQUARE(T_2, T_3, T_4, T_6, R_0, R_1, R_2, T_1, T_5, T_7) - REDUCE2(R_0, R_1, R_2, M0, M1, M2, M3, M4, R5_1, R5_2, M5, T_1) - VZERO R5_1 - VZERO R5_2 - VMSLG T_0, R_1, R5_1, R5_1 - VMSLG T_0, R_2, R5_2, R5_2 - - // skip r**4 calculation if 3 blocks or less - CMPBLE R3, $48, b4 - - // calculate r**4 and 20*(r**4) - VZERO T_8 - VZERO T_9 - VZERO T_10 - SQUARE(R_0, R_1, R_2, R5_2, T_8, T_9, T_10, T_1, T_5, T_7) - REDUCE2(T_8, T_9, T_10, M0, M1, M2, M3, M4, T_2, T_3, M5, T_1) - VZERO T_2 - VZERO T_3 - VMSLG T_0, T_9, T_2, T_2 - VMSLG T_0, T_10, T_3, T_3 - - // put r**2 to the right and r**4 to the left of R_0, R_1, R_2 - VSLDB $8, T_8, T_8, T_8 - VSLDB $8, T_9, T_9, T_9 - VSLDB $8, T_10, T_10, T_10 - VSLDB $8, T_2, T_2, T_2 - VSLDB $8, T_3, T_3, T_3 - - VO T_8, R_0, R_0 - VO T_9, R_1, R_1 - VO T_10, R_2, R_2 - VO T_2, R5_1, R5_1 - VO T_3, R5_2, R5_2 - - CMPBLE R3, $80, load // less than or equal to 5 blocks in message - - // 6(or 5+1) blocks - SUB $81, R3 - VLM (R2), M0, M4 - VLL R3, 80(R2), M5 - ADD $1, R3 - MOVBZ $1, R0 - CMPBGE R3, $16, 2(PC) - VLVGB R3, R0, M5 - MOVD $96(R2), R2 - EXPACC(M0, M1, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3) - EXPACC(M2, M3, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3) - VLEIB $2, $1, H2_0 - VLEIB $2, $1, H2_1 - VLEIB $10, $1, H2_0 - VLEIB $10, $1, H2_1 - - VZERO M0 - VZERO M1 - VZERO M2 - VZERO M3 - VZERO T_4 - VZERO T_10 - EXPACC(M4, M5, M0, M1, M2, M3, T_4, T_10, T_0, T_1, T_2, T_3) - VLR T_4, M4 - VLEIB $10, $1, M2 - CMPBLT R3, $16, 2(PC) - VLEIB $10, $1, T_10 - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M2, M3, M4, T_4, T_5, T_2, T_7, T_8, T_9) - VMRHG V0, H0_1, H0_0 - VMRHG V0, H1_1, H1_0 - VMRHG V0, H2_1, H2_0 - VMRLG V0, H0_1, H0_1 - VMRLG V0, H1_1, H1_1 - VMRLG V0, H2_1, H2_1 - - SUB $16, R3 - CMPBLE R3, $0, square - -load: - // load EX0, EX1 and EX2 - MOVD $·c<>(SB), R5 - VLM (R5), EX0, EX2 - -loop: - CMPBLE R3, $64, add // b4 // last 4 or less blocks left - - // next 4 full blocks - VLM (R2), M2, M5 - SUB $64, R3 - MOVD $64(R2), R2 - REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, T_0, T_1, T_3, T_4, T_5, T_2, T_7, T_8, T_9) - - // expacc in-lined to create [m2, m3] limbs - VGBM $0x3f3f, T_0 // 44 bit clear mask - VGBM $0x1f1f, T_1 // 40 bit clear mask - VPERM M2, M3, EX0, T_3 - VESRLG $4, T_0, T_0 // 44 bit clear mask ready - VPERM M2, M3, EX1, T_4 - VPERM M2, M3, EX2, T_5 - VN T_0, T_3, T_3 - VESRLG $4, T_4, T_4 - VN T_1, T_5, T_5 - VN T_0, T_4, T_4 - VMRHG H0_1, T_3, H0_0 - VMRHG H1_1, T_4, H1_0 - VMRHG H2_1, T_5, H2_0 - VMRLG H0_1, T_3, H0_1 - VMRLG H1_1, T_4, H1_1 - VMRLG H2_1, T_5, H2_1 - VLEIB $10, $1, H2_0 - VLEIB $10, $1, H2_1 - VPERM M4, M5, EX0, T_3 - VPERM M4, M5, EX1, T_4 - VPERM M4, M5, EX2, T_5 - VN T_0, T_3, T_3 - VESRLG $4, T_4, T_4 - VN T_1, T_5, T_5 - VN T_0, T_4, T_4 - VMRHG V0, T_3, M0 - VMRHG V0, T_4, M1 - VMRHG V0, T_5, M2 - VMRLG V0, T_3, M3 - VMRLG V0, T_4, M4 - VMRLG V0, T_5, M5 - VLEIB $10, $1, M2 - VLEIB $10, $1, M5 - - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - CMPBNE R3, $0, loop - REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9) - VMRHG V0, H0_1, H0_0 - VMRHG V0, H1_1, H1_0 - VMRHG V0, H2_1, H2_0 - VMRLG V0, H0_1, H0_1 - VMRLG V0, H1_1, H1_1 - VMRLG V0, H2_1, H2_1 - - // load EX0, EX1, EX2 - MOVD $·constants<>(SB), R5 - VLM (R5), EX0, EX2 - - // sum vectors - VAQ H0_0, H0_1, H0_0 - VAQ H1_0, H1_1, H1_0 - VAQ H2_0, H2_1, H2_0 - - // h may be >= 2*(2**130-5) so we need to reduce it again - // M0...M4 are used as temps here - REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5) - -next: // carry h1->h2 - VLEIB $7, $0x28, T_1 - VREPIB $4, T_2 - VGBM $0x003F, T_3 - VESRLG $4, T_3 - - // byte shift - VSRLB T_1, H1_0, T_4 - - // bit shift - VSRL T_2, T_4, T_4 - - // clear h1 carry bits - VN T_3, H1_0, H1_0 - - // add carry - VAQ T_4, H2_0, H2_0 - - // h is now < 2*(2**130-5) - // pack h into h1 (hi) and h0 (lo) - PACK(H0_0, H1_0, H2_0) - - // if h > 2**130-5 then h -= 2**130-5 - MOD(H0_0, H1_0, T_0, T_1, T_2) - - // h += s - MOVD $·bswapMask<>(SB), R5 - VL (R5), T_1 - VL 16(R4), T_0 - VPERM T_0, T_0, T_1, T_0 // reverse bytes (to big) - VAQ T_0, H0_0, H0_0 - VPERM H0_0, H0_0, T_1, H0_0 // reverse bytes (to little) - VST H0_0, (R1) - RET - -add: - // load EX0, EX1, EX2 - MOVD $·constants<>(SB), R5 - VLM (R5), EX0, EX2 - - REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9) - VMRHG V0, H0_1, H0_0 - VMRHG V0, H1_1, H1_0 - VMRHG V0, H2_1, H2_0 - VMRLG V0, H0_1, H0_1 - VMRLG V0, H1_1, H1_1 - VMRLG V0, H2_1, H2_1 - CMPBLE R3, $64, b4 - -b4: - CMPBLE R3, $48, b3 // 3 blocks or less - - // 4(3+1) blocks remaining - SUB $49, R3 - VLM (R2), M0, M2 - VLL R3, 48(R2), M3 - ADD $1, R3 - MOVBZ $1, R0 - CMPBEQ R3, $16, 2(PC) - VLVGB R3, R0, M3 - MOVD $64(R2), R2 - EXPACC(M0, M1, H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_0, T_1, T_2, T_3) - VLEIB $10, $1, H2_0 - VLEIB $10, $1, H2_1 - VZERO M0 - VZERO M1 - VZERO M4 - VZERO M5 - VZERO T_4 - VZERO T_10 - EXPACC(M2, M3, M0, M1, M4, M5, T_4, T_10, T_0, T_1, T_2, T_3) - VLR T_4, M2 - VLEIB $10, $1, M4 - CMPBNE R3, $16, 2(PC) - VLEIB $10, $1, T_10 - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M4, M5, M2, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M3, M4, M5, T_4, T_5, T_2, T_7, T_8, T_9) - VMRHG V0, H0_1, H0_0 - VMRHG V0, H1_1, H1_0 - VMRHG V0, H2_1, H2_0 - VMRLG V0, H0_1, H0_1 - VMRLG V0, H1_1, H1_1 - VMRLG V0, H2_1, H2_1 - SUB $16, R3 - CMPBLE R3, $0, square // this condition must always hold true! - -b3: - CMPBLE R3, $32, b2 - - // 3 blocks remaining - - // setup [r²,r] - VSLDB $8, R_0, R_0, R_0 - VSLDB $8, R_1, R_1, R_1 - VSLDB $8, R_2, R_2, R_2 - VSLDB $8, R5_1, R5_1, R5_1 - VSLDB $8, R5_2, R5_2, R5_2 - - VLVGG $1, RSAVE_0, R_0 - VLVGG $1, RSAVE_1, R_1 - VLVGG $1, RSAVE_2, R_2 - VLVGG $1, R5SAVE_1, R5_1 - VLVGG $1, R5SAVE_2, R5_2 - - // setup [h0, h1] - VSLDB $8, H0_0, H0_0, H0_0 - VSLDB $8, H1_0, H1_0, H1_0 - VSLDB $8, H2_0, H2_0, H2_0 - VO H0_1, H0_0, H0_0 - VO H1_1, H1_0, H1_0 - VO H2_1, H2_0, H2_0 - VZERO H0_1 - VZERO H1_1 - VZERO H2_1 - - VZERO M0 - VZERO M1 - VZERO M2 - VZERO M3 - VZERO M4 - VZERO M5 - - // H*[r**2, r] - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, H0_1, H1_1, T_10, M5) - - SUB $33, R3 - VLM (R2), M0, M1 - VLL R3, 32(R2), M2 - ADD $1, R3 - MOVBZ $1, R0 - CMPBEQ R3, $16, 2(PC) - VLVGB R3, R0, M2 - - // H += m0 - VZERO T_1 - VZERO T_2 - VZERO T_3 - EXPACC2(M0, T_1, T_2, T_3, T_4, T_5, T_6) - VLEIB $10, $1, T_3 - VAG H0_0, T_1, H0_0 - VAG H1_0, T_2, H1_0 - VAG H2_0, T_3, H2_0 - - VZERO M0 - VZERO M3 - VZERO M4 - VZERO M5 - VZERO T_10 - - // (H+m0)*r - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M3, M4, M5, V0, T_10, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE2(H0_0, H1_0, H2_0, M0, M3, M4, M5, T_10, H0_1, H1_1, H2_1, T_9) - - // H += m1 - VZERO V0 - VZERO T_1 - VZERO T_2 - VZERO T_3 - EXPACC2(M1, T_1, T_2, T_3, T_4, T_5, T_6) - VLEIB $10, $1, T_3 - VAQ H0_0, T_1, H0_0 - VAQ H1_0, T_2, H1_0 - VAQ H2_0, T_3, H2_0 - REDUCE2(H0_0, H1_0, H2_0, M0, M3, M4, M5, T_9, H0_1, H1_1, H2_1, T_10) - - // [H, m2] * [r**2, r] - EXPACC2(M2, H0_0, H1_0, H2_0, T_1, T_2, T_3) - CMPBNE R3, $16, 2(PC) - VLEIB $10, $1, H2_0 - VZERO M0 - VZERO M1 - VZERO M2 - VZERO M3 - VZERO M4 - VZERO M5 - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, H0_1, H1_1, M5, T_10) - SUB $16, R3 - CMPBLE R3, $0, next // this condition must always hold true! - -b2: - CMPBLE R3, $16, b1 - - // 2 blocks remaining - - // setup [r²,r] - VSLDB $8, R_0, R_0, R_0 - VSLDB $8, R_1, R_1, R_1 - VSLDB $8, R_2, R_2, R_2 - VSLDB $8, R5_1, R5_1, R5_1 - VSLDB $8, R5_2, R5_2, R5_2 - - VLVGG $1, RSAVE_0, R_0 - VLVGG $1, RSAVE_1, R_1 - VLVGG $1, RSAVE_2, R_2 - VLVGG $1, R5SAVE_1, R5_1 - VLVGG $1, R5SAVE_2, R5_2 - - // setup [h0, h1] - VSLDB $8, H0_0, H0_0, H0_0 - VSLDB $8, H1_0, H1_0, H1_0 - VSLDB $8, H2_0, H2_0, H2_0 - VO H0_1, H0_0, H0_0 - VO H1_1, H1_0, H1_0 - VO H2_1, H2_0, H2_0 - VZERO H0_1 - VZERO H1_1 - VZERO H2_1 - - VZERO M0 - VZERO M1 - VZERO M2 - VZERO M3 - VZERO M4 - VZERO M5 - - // H*[r**2, r] - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, T_10, M0, M1, M2, M3, M4, T_4, T_5, T_2, T_7, T_8, T_9) - VMRHG V0, H0_1, H0_0 - VMRHG V0, H1_1, H1_0 - VMRHG V0, H2_1, H2_0 - VMRLG V0, H0_1, H0_1 - VMRLG V0, H1_1, H1_1 - VMRLG V0, H2_1, H2_1 - - // move h to the left and 0s at the right - VSLDB $8, H0_0, H0_0, H0_0 - VSLDB $8, H1_0, H1_0, H1_0 - VSLDB $8, H2_0, H2_0, H2_0 - - // get message blocks and append 1 to start - SUB $17, R3 - VL (R2), M0 - VLL R3, 16(R2), M1 - ADD $1, R3 - MOVBZ $1, R0 - CMPBEQ R3, $16, 2(PC) - VLVGB R3, R0, M1 - VZERO T_6 - VZERO T_7 - VZERO T_8 - EXPACC2(M0, T_6, T_7, T_8, T_1, T_2, T_3) - EXPACC2(M1, T_6, T_7, T_8, T_1, T_2, T_3) - VLEIB $2, $1, T_8 - CMPBNE R3, $16, 2(PC) - VLEIB $10, $1, T_8 - - // add [m0, m1] to h - VAG H0_0, T_6, H0_0 - VAG H1_0, T_7, H1_0 - VAG H2_0, T_8, H2_0 - - VZERO M2 - VZERO M3 - VZERO M4 - VZERO M5 - VZERO T_10 - VZERO M0 - - // at this point R_0 .. R5_2 look like [r**2, r] - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M2, M3, M4, M5, T_10, M0, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE2(H0_0, H1_0, H2_0, M2, M3, M4, M5, T_9, H0_1, H1_1, H2_1, T_10) - SUB $16, R3, R3 - CMPBLE R3, $0, next - -b1: - CMPBLE R3, $0, next - - // 1 block remaining - - // setup [r²,r] - VSLDB $8, R_0, R_0, R_0 - VSLDB $8, R_1, R_1, R_1 - VSLDB $8, R_2, R_2, R_2 - VSLDB $8, R5_1, R5_1, R5_1 - VSLDB $8, R5_2, R5_2, R5_2 - - VLVGG $1, RSAVE_0, R_0 - VLVGG $1, RSAVE_1, R_1 - VLVGG $1, RSAVE_2, R_2 - VLVGG $1, R5SAVE_1, R5_1 - VLVGG $1, R5SAVE_2, R5_2 - - // setup [h0, h1] - VSLDB $8, H0_0, H0_0, H0_0 - VSLDB $8, H1_0, H1_0, H1_0 - VSLDB $8, H2_0, H2_0, H2_0 - VO H0_1, H0_0, H0_0 - VO H1_1, H1_0, H1_0 - VO H2_1, H2_0, H2_0 - VZERO H0_1 - VZERO H1_1 - VZERO H2_1 - - VZERO M0 - VZERO M1 - VZERO M2 - VZERO M3 - VZERO M4 - VZERO M5 - - // H*[r**2, r] - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5) - - // set up [0, m0] limbs - SUB $1, R3 - VLL R3, (R2), M0 - ADD $1, R3 - MOVBZ $1, R0 - CMPBEQ R3, $16, 2(PC) - VLVGB R3, R0, M0 - VZERO T_1 - VZERO T_2 - VZERO T_3 - EXPACC2(M0, T_1, T_2, T_3, T_4, T_5, T_6)// limbs: [0, m] - CMPBNE R3, $16, 2(PC) - VLEIB $10, $1, T_3 - - // h+m0 - VAQ H0_0, T_1, H0_0 - VAQ H1_0, T_2, H1_0 - VAQ H2_0, T_3, H2_0 - - VZERO M0 - VZERO M1 - VZERO M2 - VZERO M3 - VZERO M4 - VZERO M5 - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5) - - BR next - -square: - // setup [r²,r] - VSLDB $8, R_0, R_0, R_0 - VSLDB $8, R_1, R_1, R_1 - VSLDB $8, R_2, R_2, R_2 - VSLDB $8, R5_1, R5_1, R5_1 - VSLDB $8, R5_2, R5_2, R5_2 - - VLVGG $1, RSAVE_0, R_0 - VLVGG $1, RSAVE_1, R_1 - VLVGG $1, RSAVE_2, R_2 - VLVGG $1, R5SAVE_1, R5_1 - VLVGG $1, R5SAVE_2, R5_2 - - // setup [h0, h1] - VSLDB $8, H0_0, H0_0, H0_0 - VSLDB $8, H1_0, H1_0, H1_0 - VSLDB $8, H2_0, H2_0, H2_0 - VO H0_1, H0_0, H0_0 - VO H1_1, H1_0, H1_0 - VO H2_1, H2_0, H2_0 - VZERO H0_1 - VZERO H1_1 - VZERO H2_1 - - VZERO M0 - VZERO M1 - VZERO M2 - VZERO M3 - VZERO M4 - VZERO M5 - - // (h0*r**2) + (h1*r) - MULTIPLY(H0_0, H1_0, H2_0, H0_1, H1_1, H2_1, R_0, R_1, R_2, R5_1, R5_2, M0, M1, M2, M3, M4, M5, T_0, T_1, T_2, T_3, T_4, T_5, T_6, T_7, T_8, T_9) - REDUCE2(H0_0, H1_0, H2_0, M0, M1, M2, M3, M4, T_9, T_10, H0_1, M5) - BR next diff --git a/vendor/golang.org/x/crypto/ssh/certs.go b/vendor/golang.org/x/crypto/ssh/certs.go index 0f89aec1c..916c840b6 100644 --- a/vendor/golang.org/x/crypto/ssh/certs.go +++ b/vendor/golang.org/x/crypto/ssh/certs.go @@ -414,8 +414,8 @@ func (c *CertChecker) CheckCert(principal string, cert *Certificate) error { return nil } -// SignCert sets c.SignatureKey to the authority's public key and stores a -// Signature, by authority, in the certificate. +// SignCert signs the certificate with an authority, setting the Nonce, +// SignatureKey, and Signature fields. func (c *Certificate) SignCert(rand io.Reader, authority Signer) error { c.Nonce = make([]byte, 32) if _, err := io.ReadFull(rand, c.Nonce); err != nil { diff --git a/vendor/golang.org/x/crypto/ssh/cipher.go b/vendor/golang.org/x/crypto/ssh/cipher.go index b0204ee59..8bd6b3daf 100644 --- a/vendor/golang.org/x/crypto/ssh/cipher.go +++ b/vendor/golang.org/x/crypto/ssh/cipher.go @@ -119,7 +119,7 @@ var cipherModes = map[string]*cipherMode{ chacha20Poly1305ID: {64, 0, newChaCha20Cipher}, // CBC mode is insecure and so is not included in the default config. - // (See http://www.isg.rhul.ac.uk/~kp/SandPfinal.pdf). If absolutely + // (See https://www.ieee-security.org/TC/SP2013/papers/4977a526.pdf). If absolutely // needed, it's possible to specify a custom Config to enable it. // You should expect that an active attacker can recover plaintext if // you do. diff --git a/vendor/golang.org/x/crypto/ssh/client_auth.go b/vendor/golang.org/x/crypto/ssh/client_auth.go index 0590070e2..f3265655e 100644 --- a/vendor/golang.org/x/crypto/ssh/client_auth.go +++ b/vendor/golang.org/x/crypto/ssh/client_auth.go @@ -36,7 +36,7 @@ func (c *connection) clientAuthenticate(config *ClientConfig) error { // during the authentication phase the client first attempts the "none" method // then any untried methods suggested by the server. - tried := make(map[string]bool) + var tried []string var lastMethods []string sessionID := c.transport.getSessionID() @@ -49,7 +49,9 @@ func (c *connection) clientAuthenticate(config *ClientConfig) error { // success return nil } else if ok == authFailure { - tried[auth.method()] = true + if m := auth.method(); !contains(tried, m) { + tried = append(tried, m) + } } if methods == nil { methods = lastMethods @@ -61,7 +63,7 @@ func (c *connection) clientAuthenticate(config *ClientConfig) error { findNext: for _, a := range config.Auth { candidateMethod := a.method() - if tried[candidateMethod] { + if contains(tried, candidateMethod) { continue } for _, meth := range methods { @@ -72,16 +74,16 @@ func (c *connection) clientAuthenticate(config *ClientConfig) error { } } } - return fmt.Errorf("ssh: unable to authenticate, attempted methods %v, no supported methods remain", keys(tried)) + return fmt.Errorf("ssh: unable to authenticate, attempted methods %v, no supported methods remain", tried) } -func keys(m map[string]bool) []string { - s := make([]string, 0, len(m)) - - for key := range m { - s = append(s, key) +func contains(list []string, e string) bool { + for _, s := range list { + if s == e { + return true + } } - return s + return false } // An AuthMethod represents an instance of an RFC 4252 authentication method. diff --git a/vendor/golang.org/x/crypto/ssh/mux.go b/vendor/golang.org/x/crypto/ssh/mux.go index f19016270..9654c0186 100644 --- a/vendor/golang.org/x/crypto/ssh/mux.go +++ b/vendor/golang.org/x/crypto/ssh/mux.go @@ -240,7 +240,7 @@ func (m *mux) onePacket() error { id := binary.BigEndian.Uint32(packet[1:]) ch := m.chanList.getChan(id) if ch == nil { - return fmt.Errorf("ssh: invalid channel %d", id) + return m.handleUnknownChannelPacket(id, packet) } return ch.handlePacket(packet) @@ -328,3 +328,24 @@ func (m *mux) openChannel(chanType string, extra []byte) (*channel, error) { return nil, fmt.Errorf("ssh: unexpected packet in response to channel open: %T", msg) } } + +func (m *mux) handleUnknownChannelPacket(id uint32, packet []byte) error { + msg, err := decode(packet) + if err != nil { + return err + } + + switch msg := msg.(type) { + // RFC 4254 section 5.4 says unrecognized channel requests should + // receive a failure response. + case *channelRequestMsg: + if msg.WantReply { + return m.sendMessage(channelRequestFailureMsg{ + PeersID: msg.PeersID, + }) + } + return nil + default: + return fmt.Errorf("ssh: invalid channel %d", id) + } +} diff --git a/vendor/golang.org/x/crypto/ssh/terminal/terminal.go b/vendor/golang.org/x/crypto/ssh/terminal/terminal.go index d1b4fca3a..2ffb97bfb 100644 --- a/vendor/golang.org/x/crypto/ssh/terminal/terminal.go +++ b/vendor/golang.org/x/crypto/ssh/terminal/terminal.go @@ -113,6 +113,7 @@ func NewTerminal(c io.ReadWriter, prompt string) *Terminal { } const ( + keyCtrlC = 3 keyCtrlD = 4 keyCtrlU = 21 keyEnter = '\r' @@ -151,8 +152,12 @@ func bytesToKey(b []byte, pasteActive bool) (rune, []byte) { switch b[0] { case 1: // ^A return keyHome, b[1:] + case 2: // ^B + return keyLeft, b[1:] case 5: // ^E return keyEnd, b[1:] + case 6: // ^F + return keyRight, b[1:] case 8: // ^H return keyBackspace, b[1:] case 11: // ^K @@ -738,6 +743,9 @@ func (t *Terminal) readLine() (line string, err error) { return "", io.EOF } } + if key == keyCtrlC { + return "", io.EOF + } if key == keyPasteStart { t.pasteActive = true if len(t.line) == 0 { diff --git a/vendor/golang.org/x/net/http2/client_conn_pool.go b/vendor/golang.org/x/net/http2/client_conn_pool.go index f4d9b5ece..3a67636fe 100644 --- a/vendor/golang.org/x/net/http2/client_conn_pool.go +++ b/vendor/golang.org/x/net/http2/client_conn_pool.go @@ -107,6 +107,7 @@ func (p *clientConnPool) getClientConn(req *http.Request, addr string, dialOnMis // dialCall is an in-flight Transport dial call to a host. type dialCall struct { + _ incomparable p *clientConnPool done chan struct{} // closed when done res *ClientConn // valid after done is closed @@ -180,6 +181,7 @@ func (p *clientConnPool) addConnIfNeeded(key string, t *Transport, c *tls.Conn) } type addConnCall struct { + _ incomparable p *clientConnPool done chan struct{} // closed when done err error @@ -200,12 +202,6 @@ func (c *addConnCall) run(t *Transport, key string, tc *tls.Conn) { close(c.done) } -func (p *clientConnPool) addConn(key string, cc *ClientConn) { - p.mu.Lock() - p.addConnLocked(key, cc) - p.mu.Unlock() -} - // p.mu must be held func (p *clientConnPool) addConnLocked(key string, cc *ClientConn) { for _, v := range p.conns[key] { diff --git a/vendor/golang.org/x/net/http2/flow.go b/vendor/golang.org/x/net/http2/flow.go index cea601fcd..b51f0e0cf 100644 --- a/vendor/golang.org/x/net/http2/flow.go +++ b/vendor/golang.org/x/net/http2/flow.go @@ -8,6 +8,8 @@ package http2 // flow is the flow control window's size. type flow struct { + _ incomparable + // n is the number of DATA bytes we're allowed to send. // A flow is kept both on a conn and a per-stream. n int32 diff --git a/vendor/golang.org/x/net/http2/hpack/huffman.go b/vendor/golang.org/x/net/http2/hpack/huffman.go index b412a96c5..a1ab2f056 100644 --- a/vendor/golang.org/x/net/http2/hpack/huffman.go +++ b/vendor/golang.org/x/net/http2/hpack/huffman.go @@ -105,7 +105,14 @@ func huffmanDecode(buf *bytes.Buffer, maxLen int, v []byte) error { return nil } +// incomparable is a zero-width, non-comparable type. Adding it to a struct +// makes that struct also non-comparable, and generally doesn't add +// any size (as long as it's first). +type incomparable [0]func() + type node struct { + _ incomparable + // children is non-nil for internal nodes children *[256]*node diff --git a/vendor/golang.org/x/net/http2/http2.go b/vendor/golang.org/x/net/http2/http2.go index 27cc893cc..5571ccfd2 100644 --- a/vendor/golang.org/x/net/http2/http2.go +++ b/vendor/golang.org/x/net/http2/http2.go @@ -241,6 +241,7 @@ func (cw closeWaiter) Wait() { // Its buffered writer is lazily allocated as needed, to minimize // idle memory usage with many connections. type bufferedWriter struct { + _ incomparable w io.Writer // immutable bw *bufio.Writer // non-nil when data is buffered } @@ -313,6 +314,7 @@ func bodyAllowedForStatus(status int) bool { } type httpError struct { + _ incomparable msg string timeout bool } @@ -376,3 +378,8 @@ func (s *sorter) SortStrings(ss []string) { func validPseudoPath(v string) bool { return (len(v) > 0 && v[0] == '/') || v == "*" } + +// incomparable is a zero-width, non-comparable type. Adding it to a struct +// makes that struct also non-comparable, and generally doesn't add +// any size (as long as it's first). +type incomparable [0]func() diff --git a/vendor/golang.org/x/net/http2/server.go b/vendor/golang.org/x/net/http2/server.go index bc9e41a1b..345b7cd85 100644 --- a/vendor/golang.org/x/net/http2/server.go +++ b/vendor/golang.org/x/net/http2/server.go @@ -761,6 +761,7 @@ func (sc *serverConn) readFrames() { // frameWriteResult is the message passed from writeFrameAsync to the serve goroutine. type frameWriteResult struct { + _ incomparable wr FrameWriteRequest // what was written (or attempted) err error // result of the writeFrame call } @@ -771,7 +772,7 @@ type frameWriteResult struct { // serverConn. func (sc *serverConn) writeFrameAsync(wr FrameWriteRequest) { err := wr.write.writeFrame(sc) - sc.wroteFrameCh <- frameWriteResult{wr, err} + sc.wroteFrameCh <- frameWriteResult{wr: wr, err: err} } func (sc *serverConn) closeAllStreamsOnConnClose() { @@ -1161,7 +1162,7 @@ func (sc *serverConn) startFrameWrite(wr FrameWriteRequest) { if wr.write.staysWithinBuffer(sc.bw.Available()) { sc.writingFrameAsync = false err := wr.write.writeFrame(sc) - sc.wroteFrame(frameWriteResult{wr, err}) + sc.wroteFrame(frameWriteResult{wr: wr, err: err}) } else { sc.writingFrameAsync = true go sc.writeFrameAsync(wr) @@ -2057,7 +2058,7 @@ func (sc *serverConn) newWriterAndRequestNoBody(st *stream, rp requestParam) (*r var trailer http.Header for _, v := range rp.header["Trailer"] { for _, key := range strings.Split(v, ",") { - key = http.CanonicalHeaderKey(strings.TrimSpace(key)) + key = http.CanonicalHeaderKey(textproto.TrimString(key)) switch key { case "Transfer-Encoding", "Trailer", "Content-Length": // Bogus. (copy of http1 rules) @@ -2275,6 +2276,7 @@ func (sc *serverConn) sendWindowUpdate32(st *stream, n int32) { // requestBody is the Handler's Request.Body type. // Read and Close may be called concurrently. type requestBody struct { + _ incomparable stream *stream conn *serverConn closed bool // for use by Close only diff --git a/vendor/golang.org/x/net/http2/transport.go b/vendor/golang.org/x/net/http2/transport.go index 81778bec6..76a92e0ca 100644 --- a/vendor/golang.org/x/net/http2/transport.go +++ b/vendor/golang.org/x/net/http2/transport.go @@ -108,6 +108,19 @@ type Transport struct { // waiting for their turn. StrictMaxConcurrentStreams bool + // ReadIdleTimeout is the timeout after which a health check using ping + // frame will be carried out if no frame is received on the connection. + // Note that a ping response will is considered a received frame, so if + // there is no other traffic on the connection, the health check will + // be performed every ReadIdleTimeout interval. + // If zero, no health check is performed. + ReadIdleTimeout time.Duration + + // PingTimeout is the timeout after which the connection will be closed + // if a response to Ping is not received. + // Defaults to 15s. + PingTimeout time.Duration + // t1, if non-nil, is the standard library Transport using // this transport. Its settings are used (but not its // RoundTrip method, etc). @@ -131,6 +144,14 @@ func (t *Transport) disableCompression() bool { return t.DisableCompression || (t.t1 != nil && t.t1.DisableCompression) } +func (t *Transport) pingTimeout() time.Duration { + if t.PingTimeout == 0 { + return 15 * time.Second + } + return t.PingTimeout + +} + // ConfigureTransport configures a net/http HTTP/1 Transport to use HTTP/2. // It returns an error if t1 has already been HTTP/2-enabled. func ConfigureTransport(t1 *http.Transport) error { @@ -675,6 +696,20 @@ func (t *Transport) newClientConn(c net.Conn, singleUse bool) (*ClientConn, erro return cc, nil } +func (cc *ClientConn) healthCheck() { + pingTimeout := cc.t.pingTimeout() + // We don't need to periodically ping in the health check, because the readLoop of ClientConn will + // trigger the healthCheck again if there is no frame received. + ctx, cancel := context.WithTimeout(context.Background(), pingTimeout) + defer cancel() + err := cc.Ping(ctx) + if err != nil { + cc.closeForLostPing() + cc.t.connPool().MarkDead(cc) + return + } +} + func (cc *ClientConn) setGoAway(f *GoAwayFrame) { cc.mu.Lock() defer cc.mu.Unlock() @@ -846,14 +881,12 @@ func (cc *ClientConn) sendGoAway() error { return nil } -// Close closes the client connection immediately. -// -// In-flight requests are interrupted. For a graceful shutdown, use Shutdown instead. -func (cc *ClientConn) Close() error { +// closes the client connection immediately. In-flight requests are interrupted. +// err is sent to streams. +func (cc *ClientConn) closeForError(err error) error { cc.mu.Lock() defer cc.cond.Broadcast() defer cc.mu.Unlock() - err := errors.New("http2: client connection force closed via ClientConn.Close") for id, cs := range cc.streams { select { case cs.resc <- resAndError{err: err}: @@ -866,6 +899,20 @@ func (cc *ClientConn) Close() error { return cc.tconn.Close() } +// Close closes the client connection immediately. +// +// In-flight requests are interrupted. For a graceful shutdown, use Shutdown instead. +func (cc *ClientConn) Close() error { + err := errors.New("http2: client connection force closed via ClientConn.Close") + return cc.closeForError(err) +} + +// closes the client connection immediately. In-flight requests are interrupted. +func (cc *ClientConn) closeForLostPing() error { + err := errors.New("http2: client connection lost") + return cc.closeForError(err) +} + const maxAllocFrameSize = 512 << 10 // frameBuffer returns a scratch buffer suitable for writing DATA frames. @@ -916,7 +963,7 @@ func commaSeparatedTrailers(req *http.Request) (string, error) { k = http.CanonicalHeaderKey(k) switch k { case "Transfer-Encoding", "Trailer", "Content-Length": - return "", &badStringError{"invalid Trailer key", k} + return "", fmt.Errorf("invalid Trailer key %q", k) } keys = append(keys, k) } @@ -1394,13 +1441,6 @@ func (cs *clientStream) awaitFlowControl(maxBytes int) (taken int32, err error) } } -type badStringError struct { - what string - str string -} - -func (e *badStringError) Error() string { return fmt.Sprintf("%s %q", e.what, e.str) } - // requires cc.mu be held. func (cc *ClientConn) encodeHeaders(req *http.Request, addGzipHeader bool, trailers string, contentLength int64) ([]byte, error) { cc.hbuf.Reset() @@ -1616,6 +1656,7 @@ func (cc *ClientConn) writeHeader(name, value string) { } type resAndError struct { + _ incomparable res *http.Response err error } @@ -1663,6 +1704,7 @@ func (cc *ClientConn) streamByID(id uint32, andRemove bool) *clientStream { // clientConnReadLoop is the state owned by the clientConn's frame-reading readLoop. type clientConnReadLoop struct { + _ incomparable cc *ClientConn closeWhenIdle bool } @@ -1742,8 +1784,17 @@ func (rl *clientConnReadLoop) run() error { rl.closeWhenIdle = cc.t.disableKeepAlives() || cc.singleUse gotReply := false // ever saw a HEADERS reply gotSettings := false + readIdleTimeout := cc.t.ReadIdleTimeout + var t *time.Timer + if readIdleTimeout != 0 { + t = time.AfterFunc(readIdleTimeout, cc.healthCheck) + defer t.Stop() + } for { f, err := cc.fr.ReadFrame() + if t != nil { + t.Reset(readIdleTimeout) + } if err != nil { cc.vlogf("http2: Transport readFrame error on conn %p: (%T) %v", cc, err, err) } @@ -1892,7 +1943,9 @@ func (rl *clientConnReadLoop) handleResponse(cs *clientStream, f *MetaHeadersFra return nil, errors.New("malformed response from server: malformed non-numeric status pseudo header") } - header := make(http.Header) + regularFields := f.RegularFields() + strs := make([]string, len(regularFields)) + header := make(http.Header, len(regularFields)) res := &http.Response{ Proto: "HTTP/2.0", ProtoMajor: 2, @@ -1900,7 +1953,7 @@ func (rl *clientConnReadLoop) handleResponse(cs *clientStream, f *MetaHeadersFra StatusCode: statusCode, Status: status + " " + http.StatusText(statusCode), } - for _, hf := range f.RegularFields() { + for _, hf := range regularFields { key := http.CanonicalHeaderKey(hf.Name) if key == "Trailer" { t := res.Trailer @@ -1912,7 +1965,18 @@ func (rl *clientConnReadLoop) handleResponse(cs *clientStream, f *MetaHeadersFra t[http.CanonicalHeaderKey(v)] = nil }) } else { - header[key] = append(header[key], hf.Value) + vv := header[key] + if vv == nil && len(strs) > 0 { + // More than likely this will be a single-element key. + // Most headers aren't multi-valued. + // Set the capacity on strs[0] to 1, so any future append + // won't extend the slice into the other strings. + vv, strs = strs[:1:1], strs[1:] + vv[0] = hf.Value + header[key] = vv + } else { + header[key] = append(vv, hf.Value) + } } } @@ -2466,6 +2530,7 @@ func (rt erringRoundTripper) RoundTrip(*http.Request) (*http.Response, error) { // gzipReader wraps a response body so it can lazily // call gzip.NewReader on the first call to Read type gzipReader struct { + _ incomparable body io.ReadCloser // underlying Response.Body zr *gzip.Reader // lazily-initialized gzip reader zerr error // sticky error diff --git a/vendor/golang.org/x/net/ipv4/header.go b/vendor/golang.org/x/net/ipv4/header.go index 701bd4b22..c271ca46c 100644 --- a/vendor/golang.org/x/net/ipv4/header.go +++ b/vendor/golang.org/x/net/ipv4/header.go @@ -14,9 +14,8 @@ import ( ) const ( - Version = 4 // protocol version - HeaderLen = 20 // header length without extension headers - maxHeaderLen = 60 // sensible default, revisit if later RFCs define new usage of version and header length fields + Version = 4 // protocol version + HeaderLen = 20 // header length without extension headers ) type HeaderFlags int diff --git a/vendor/golang.org/x/sync/semaphore/semaphore.go b/vendor/golang.org/x/sync/semaphore/semaphore.go index 7f096fef0..30f632c57 100644 --- a/vendor/golang.org/x/sync/semaphore/semaphore.go +++ b/vendor/golang.org/x/sync/semaphore/semaphore.go @@ -67,7 +67,12 @@ func (s *Weighted) Acquire(ctx context.Context, n int64) error { // fix up the queue, just pretend we didn't notice the cancelation. err = nil default: + isFront := s.waiters.Front() == elem s.waiters.Remove(elem) + // If we're at the front and there're extra tokens left, notify other waiters. + if isFront && s.size > s.cur { + s.notifyWaiters() + } } s.mu.Unlock() return err @@ -97,6 +102,11 @@ func (s *Weighted) Release(n int64) { s.mu.Unlock() panic("semaphore: released more than held") } + s.notifyWaiters() + s.mu.Unlock() +} + +func (s *Weighted) notifyWaiters() { for { next := s.waiters.Front() if next == nil { @@ -123,5 +133,4 @@ func (s *Weighted) Release(n int64) { s.waiters.Remove(next) close(w.ready) } - s.mu.Unlock() } diff --git a/vendor/modules.txt b/vendor/modules.txt index e44c53afa..4d9121b7f 100644 --- a/vendor/modules.txt +++ b/vendor/modules.txt @@ -431,7 +431,7 @@ github.com/stretchr/testify/assert # github.com/syndtr/gocapability v0.0.0-20180916011248-d98352740cb2 ## explicit github.com/syndtr/gocapability/capability -# github.com/vishvananda/netlink v1.1.0 +# github.com/vishvananda/netlink v1.1.0 => github.com/twelho/netlink v1.1.1-ageing ## explicit github.com/vishvananda/netlink github.com/vishvananda/netlink/nl @@ -469,7 +469,7 @@ go.opencensus.io/internal go.opencensus.io/trace go.opencensus.io/trace/internal go.opencensus.io/trace/tracestate -# golang.org/x/crypto v0.0.0-20200406173513-056763e48d71 +# golang.org/x/crypto v0.0.0-20200622213623-75b288015ac9 ## explicit golang.org/x/crypto/blowfish golang.org/x/crypto/cast5 @@ -490,7 +490,8 @@ golang.org/x/crypto/ssh/agent golang.org/x/crypto/ssh/internal/bcrypt_pbkdf golang.org/x/crypto/ssh/knownhosts golang.org/x/crypto/ssh/terminal -# golang.org/x/net v0.0.0-20200301022130-244492dfa37a +# golang.org/x/net v0.0.0-20200625001655-4c5254603344 +## explicit golang.org/x/net/bpf golang.org/x/net/context golang.org/x/net/context/ctxhttp @@ -506,7 +507,8 @@ golang.org/x/net/ipv4 golang.org/x/net/ipv6 golang.org/x/net/proxy golang.org/x/net/trace -# golang.org/x/sync v0.0.0-20190911185100-cd5d95a43a6e +# golang.org/x/sync v0.0.0-20200625203802-6e8e738ad208 +## explicit golang.org/x/sync/errgroup golang.org/x/sync/semaphore # golang.org/x/sys v0.0.0-20200610111108-226ff32320da @@ -625,3 +627,4 @@ sigs.k8s.io/yaml # github.com/docker/distribution => github.com/docker/distribution v0.0.0-20190711223531-1fb7fffdb266 # github.com/docker/docker => github.com/docker/docker v0.7.3-0.20190327010347-be7ac8be2ae0 # k8s.io/kube-openapi => k8s.io/kube-openapi v0.0.0-20200121204235-bf4fb3bd569c +# github.com/vishvananda/netlink => github.com/twelho/netlink v1.1.1-ageing