From 1d147ccbfc35d7d45c87fb0c767e6e40c316aa32 Mon Sep 17 00:00:00 2001 From: Mugunthan V N Date: Mon, 7 Sep 2015 15:16:44 +0530 Subject: drivers: net: cpsw: Add support to drive gpios for ethernet to be functional In DRA72x EVM, by default slave 1 is connected to the onboard phy, but slave 2 pins are also muxed with video input module which is controlled by pcf857x gpio and currently to select slave 0 to connect to phy gpio hogging is used, but with omap2plus_defconfig the pcf857x gpio is built as module. So when using NFS on DRA72x EVM, board doesn't boot as gpio hogging do not set proper gpio state to connect slave 0 to phy as it is built as module and you do not see any errors for not setting gpio and just mentions dhcp reply not got. To solve this issue, introducing "mode-gpios" in DT when gpio based muxing is required. This will throw a warning when gpio get fails and returns probe defer. When gpio-pcf857x module is installed, cpsw probes again and ethernet becomes functional. Verified this on DRA72x with pcf as module and ramdisk. Signed-off-by: Mugunthan V N Acked-by: Tony Lindgren Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/cpsw.txt | 7 +++++++ 1 file changed, 7 insertions(+) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/cpsw.txt b/Documentation/devicetree/bindings/net/cpsw.txt index a9df21aaa154..676ecf62491d 100644 --- a/Documentation/devicetree/bindings/net/cpsw.txt +++ b/Documentation/devicetree/bindings/net/cpsw.txt @@ -30,6 +30,13 @@ Optional properties: - dual_emac : Specifies Switch to act as Dual EMAC - syscon : Phandle to the system control device node, which is the control module device of the am33x +- mode-gpios : Should be added if one/multiple gpio lines are + required to be driven so that cpsw data lines + can be connected to the phy via selective mux. + For example in dra72x-evm, pcf gpio has to be + driven low so that cpsw slave 0 and phy data + lines are connected via mux. + Slave Properties: Required properties: -- cgit v1.2.3 From 4e478098ac0ac1b6ef9a70fcdc2ec8b93f1b59a1 Mon Sep 17 00:00:00 2001 From: Alex Gartrell Date: Mon, 14 Sep 2015 23:23:05 -0700 Subject: ipvs: add sysctl to ignore tunneled packets This is a way to avoid nasty routing loops when multiple ipvs instances can forward to eachother. Signed-off-by: Alex Gartrell Signed-off-by: Simon Horman --- Documentation/networking/ipvs-sysctl.txt | 10 ++++++++++ include/net/ip_vs.h | 11 +++++++++++ net/netfilter/ipvs/ip_vs_core.c | 10 +++++++++- net/netfilter/ipvs/ip_vs_ctl.c | 7 +++++++ 4 files changed, 37 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/networking/ipvs-sysctl.txt b/Documentation/networking/ipvs-sysctl.txt index 3ba709531adb..e6b1c025fdd8 100644 --- a/Documentation/networking/ipvs-sysctl.txt +++ b/Documentation/networking/ipvs-sysctl.txt @@ -157,6 +157,16 @@ expire_quiescent_template - BOOLEAN persistence template if it is to be used to schedule a new connection and the destination server is quiescent. +ignore_tunneled - BOOLEAN + 0 - disabled (default) + not 0 - enabled + + If set, ipvs will set the ipvs_property on all packets which are of + unrecognized protocols. This prevents us from routing tunneled + protocols like ipip, which is useful to prevent rescheduling + packets that have been tunneled to the ipvs host (i.e. to prevent + ipvs routing loops when ipvs is also acting as a real server). + nat_icmp_send - BOOLEAN 0 - disabled (default) not 0 - enabled diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index 47677f0493c7..1096a71ab6ed 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -998,6 +998,7 @@ struct netns_ipvs { int sysctl_backup_only; int sysctl_conn_reuse_mode; int sysctl_schedule_icmp; + int sysctl_ignore_tunneled; /* ip_vs_lblc */ int sysctl_lblc_expiration; @@ -1121,6 +1122,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) return ipvs->sysctl_schedule_icmp; } +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return ipvs->sysctl_ignore_tunneled; +} + #else static inline int sysctl_sync_threshold(struct netns_ipvs *ipvs) @@ -1198,6 +1204,11 @@ static inline int sysctl_schedule_icmp(struct netns_ipvs *ipvs) return 0; } +static inline int sysctl_ignore_tunneled(struct netns_ipvs *ipvs) +{ + return 0; +} + #endif /* IPVS core functions diff --git a/net/netfilter/ipvs/ip_vs_core.c b/net/netfilter/ipvs/ip_vs_core.c index 99be6801c795..453972c6909e 100644 --- a/net/netfilter/ipvs/ip_vs_core.c +++ b/net/netfilter/ipvs/ip_vs_core.c @@ -1760,8 +1760,16 @@ ip_vs_in(unsigned int hooknum, struct sk_buff *skb, int af) /* Protocol supported? */ pd = ip_vs_proto_data_get(net, iph.protocol); - if (unlikely(!pd)) + if (unlikely(!pd)) { + /* The only way we'll see this packet again is if it's + * encapsulated, so mark it with ipvs_property=1 so we + * skip it if we're ignoring tunneled packets + */ + if (sysctl_ignore_tunneled(ipvs)) + skb->ipvs_property = 1; + return NF_ACCEPT; + } pp = pd->pp; /* * Check if the packet belongs to an existing connection entry diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index 31d80e203863..7338827ee5e9 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -1850,6 +1850,12 @@ static struct ctl_table vs_vars[] = { .mode = 0644, .proc_handler = proc_dointvec, }, + { + .procname = "ignore_tunneled", + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, #ifdef CONFIG_IP_VS_DEBUG { .procname = "debug_level", @@ -3902,6 +3908,7 @@ static int __net_init ip_vs_control_net_init_sysctl(struct net *net) ipvs->sysctl_conn_reuse_mode = 1; tbl[idx++].data = &ipvs->sysctl_conn_reuse_mode; tbl[idx++].data = &ipvs->sysctl_schedule_icmp; + tbl[idx++].data = &ipvs->sysctl_ignore_tunneled; ipvs->sysctl_hdr = register_net_sysctl(net, "net/ipv4/vs", tbl); if (ipvs->sysctl_hdr == NULL) { -- cgit v1.2.3 From 29cd5ddc45d66ce41632a76bb4dc2ae37b88b9e6 Mon Sep 17 00:00:00 2001 From: Stefan Schmidt Date: Thu, 3 Sep 2015 16:31:34 +0200 Subject: ieee802154: docs: fix project name to linux-wpan as well as some typos Signed-off-by: Stefan Schmidt Acked-by: Alexander Aring Signed-off-by: Marcel Holtmann --- Documentation/networking/ieee802154.txt | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/ieee802154.txt b/Documentation/networking/ieee802154.txt index 1700756af057..aa69ccc481db 100644 --- a/Documentation/networking/ieee802154.txt +++ b/Documentation/networking/ieee802154.txt @@ -7,11 +7,11 @@ Introduction The IEEE 802.15.4 working group focuses on standardization of bottom two layers: Medium Access Control (MAC) and Physical (PHY). And there are mainly two options available for upper layers: - - ZigBee - proprietary protocol from ZigBee Alliance - - 6LowPAN - IPv6 networking over low rate personal area networks + - ZigBee - proprietary protocol from the ZigBee Alliance + - 6LoWPAN - IPv6 networking over low rate personal area networks -The Linux-ZigBee project goal is to provide complete implementation -of IEEE 802.15.4 and 6LoWPAN protocols. IEEE 802.15.4 is a stack +The linux-wpan project goal is to provide a complete implementation +of the IEEE 802.15.4 and 6LoWPAN protocols. IEEE 802.15.4 is a stack of protocols for organizing Low-Rate Wireless Personal Area Networks. The stack is composed of three main parts: -- cgit v1.2.3 From 4366bd4fa8c46b61ec0a7d564bd978cfa882692b Mon Sep 17 00:00:00 2001 From: Gerhard Bertelsmann Date: Wed, 16 Sep 2015 13:21:19 +0200 Subject: can: Allwinner A10/A20 CAN Controller support - Devicetree bindings Devicetree bindings for Allwinner A10/A20 CAN controller. Signed-off-by: Gerhard Bertelsmann Acked-by: Maxime Ripard Signed-off-by: Marc Kleine-Budde --- .../devicetree/bindings/net/can/sun4i_can.txt | 36 ++++++++++++++++++++++ 1 file changed, 36 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/can/sun4i_can.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/can/sun4i_can.txt b/Documentation/devicetree/bindings/net/can/sun4i_can.txt new file mode 100644 index 000000000000..84ed1909df76 --- /dev/null +++ b/Documentation/devicetree/bindings/net/can/sun4i_can.txt @@ -0,0 +1,36 @@ +Allwinner A10/A20 CAN controller Device Tree Bindings +----------------------------------------------------- + +Required properties: +- compatible: "allwinner,sun4i-a10-can" +- reg: physical base address and size of the Allwinner A10/A20 CAN register map. +- interrupts: interrupt specifier for the sole interrupt. +- clock: phandle and clock specifier. + +Example +------- + +SoC common .dtsi file: + + can0_pins_a: can0@0 { + allwinner,pins = "PH20","PH21"; + allwinner,function = "can"; + allwinner,drive = <0>; + allwinner,pull = <0>; + }; +... + can0: can@01c2bc00 { + compatible = "allwinner,sun4i-a10-can"; + reg = <0x01c2bc00 0x400>; + interrupts = <0 26 4>; + clocks = <&apb1_gates 4>; + status = "disabled"; + }; + +Board specific .dts file: + + can0: can@01c2bc00 { + pinctrl-names = "default"; + pinctrl-0 = <&can0_pins_a>; + status = "okay"; + }; -- cgit v1.2.3 From fc7e37c6b2704fb0360f7ecf747d5d3012ef9632 Mon Sep 17 00:00:00 2001 From: huangdaode Date: Thu, 17 Sep 2015 14:51:46 +0800 Subject: net: add Hisilicon Network Subsystem support (config and documents) The Hisilicon Network Subsystem is a long term evolution IP which is supposed to be used in Hisilicon ICT SoC. The IP, which is called hns for short, is a TCP/IP acceleration engine, which can directly decode TCP/IP stream and distribute them to different ring buffers. HNS can be configured to work on different mode for different scenario. This patch make use only some of the mode to make it as standard ethernet NIC. The other mode will be added soon. The whole function has 4 kernel sub-modules: hnae: the HNS acceleration engine framework. It provides a abstract interface between the engine and the upper layers which make use of the engine by ring buffer. hns_enet_drv: a standard ethernet driver that base on the ring buffer. hns_dsaf: one of the implementation of HNS acceleration engine, which is applied on Hililicon hip05, Hi1610 and other later-on SoCs hns_mdio: the mdio control to the PHY, used by acceleration engine This submit add basic config and documents Signed-off-by: huangdaode Signed-off-by: Kenneth Lee Signed-off-by: Yisen Zhuang Signed-off-by: David S. Miller --- .../bindings/net/hisilicon-hip04-net.txt | 4 +- .../devicetree/bindings/net/hisilicon-hns-dsaf.txt | 49 ++++++ .../devicetree/bindings/net/hisilicon-hns-mdio.txt | 22 +++ .../devicetree/bindings/net/hisilicon-hns-nic.txt | 47 +++++ arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi | 193 +++++++++++++++++++++ 5 files changed, 313 insertions(+), 2 deletions(-) create mode 100644 Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt create mode 100644 Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt create mode 100644 Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt create mode 100644 arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt b/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt index 988fc694b663..d1df8a00e1f3 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hip04-net.txt @@ -32,13 +32,13 @@ Required properties: Required properties: -- compatible: should be "hisilicon,hip04-mdio". +- compatible: should be "hisilicon,mdio". - Inherits from MDIO bus node binding [2] [2] Documentation/devicetree/bindings/net/phy.txt Example: mdio { - compatible = "hisilicon,hip04-mdio"; + compatible = "hisilicon,mdio"; reg = <0x28f1000 0x1000>; #address-cells = <1>; #size-cells = <0>; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt new file mode 100644 index 000000000000..80411b2f0490 --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-dsaf.txt @@ -0,0 +1,49 @@ +Hisilicon DSA Fabric device controller + +Required properties: +- compatible: should be "hisilicon,hns-dsaf-v1" or "hisilicon,hns-dsaf-v2". + "hisilicon,hns-dsaf-v1" is for hip05. + "hisilicon,hns-dsaf-v2" is for Hi1610 and Hi1612. +- dsa-name: dsa fabric name who provide this interface. + should be "dsafX", X is the dsaf id. +- mode: dsa fabric mode string. only support one of dsaf modes like these: + "2port-64vf", + "6port-16rss", + "6port-16vf". +- interrupt-parent: the interrupt parent of this device. +- interrupts: should contain the DSA Fabric and rcb interrupt. +- reg: specifies base physical address(es) and size of the device registers. + The first region is external interface control register base and size. + The second region is SerDes base register and size. + The third region is the PPE register base and size. + The fourth region is dsa fabric base register and size. + The fifth region is cpld base register and size, it is not required if do not use cpld. +- phy-handle: phy handle of physicl port, 0 if not any phy device. see ethernet.txt [1]. +- buf-size: rx buffer size, should be 16-1024. +- desc-num: number of description in TX and RX queue, should be 512, 1024, 2048 or 4096. + +[1] Documentation/devicetree/bindings/net/phy.txt + +Example: + +dsa: dsa@c7000000 { + compatible = "hisilicon,hns-dsaf-v1"; + dsa_name = "dsaf0"; + mode = "6port-16rss"; + interrupt-parent = <&mbigen_dsa>; + reg = <0x0 0xC0000000 0x0 0x420000 + 0x0 0xC2000000 0x0 0x300000 + 0x0 0xc5000000 0x0 0x890000 + 0x0 0xc7000000 0x0 0x60000>; + phy-handle = <0 0 0 0 &soc0_phy4 &soc0_phy5 0 0>; + interrupts = <131 4>,<132 4>, <133 4>,<134 4>, + <135 4>,<136 4>, <137 4>,<138 4>, + <139 4>,<140 4>, <141 4>,<142 4>, + <143 4>,<144 4>, <145 4>,<146 4>, + <147 4>,<148 4>, <384 1>,<385 1>, + <386 1>,<387 1>, <388 1>,<389 1>, + <390 1>,<391 1>, + buf-size = <4096>; + desc-num = <1024>; + dma-coherent; +}; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt new file mode 100644 index 000000000000..9940aa02b8bd --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt @@ -0,0 +1,22 @@ +Hisilicon MDIO bus controller + +Properties: +- compatible: "hisilicon,mdio","hisilicon,hns-mdio". +- reg: The base address of the MDIO bus controller register bank. +- #address-cells: Must be <1>. +- #size-cells: Must be <0>. MDIO addresses have no size component. + +Typically an MDIO bus might have several children. + +Example: + mdio@803c0000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "hisilicon,mdio","hisilicon,hns-mdio"; + reg = <0x0 0x803c0000 0x0 0x10000>; + + ethernet-phy@0 { + ... + reg = <0>; + }; + }; diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt new file mode 100644 index 000000000000..41d19be7011e --- /dev/null +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-nic.txt @@ -0,0 +1,47 @@ +Hisilicon Network Subsystem NIC controller + +Required properties: +- compatible: "hisilicon,hns-nic-v1" or "hisilicon,hns-nic-v2". + "hisilicon,hns-nic-v1" is for hip05. + "hisilicon,hns-nic-v2" is for Hi1610 and Hi1612. +- ae-name: accelerator name who provides this interface, + is simply a name referring to the name of name in the accelerator node. +- port-id: is the index of port provided by DSAF (the accelerator). DSAF can + connect to 8 PHYs. Port 0 to 1 are both used for adminstration purpose. They + are called debug ports. + + The remaining 6 PHYs are taken according to the mode of DSAF. + + In NIC mode of DSAF, all 6 PHYs are taken as ethernet ports to the CPU. The + port-id can be 2 to 7. Here is the diagram: + +-----+---------------+ + | CPU | + +-+-+-+---+-+-+-+-+-+-+ + | | | | | | | | + debug service + port port + (0,1) (2-7) + + In Switch mode of DSAF, all 6 PHYs are taken as physical ports connect to a + LAN Switch while the CPU side assume itself have one single NIC connect to + this switch. In this case, the port-id will be 2 only. + +-----+---------------+ + | CPU | + +-+-+-+---+-+-+-+-+-+-+ + | | service| port(2) + debug +------------+ + port | switch | + (0,1) +-+-+-+-+-+-++ + | | | | | | + external port + +- local-mac-address: mac addr of the ethernet interface + +Example: + + ethernet@0{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <0>; + local-mac-address = [a2 14 e4 4b 56 76]; + }; diff --git a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi new file mode 100644 index 000000000000..35005866a34e --- /dev/null +++ b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi @@ -0,0 +1,193 @@ +soc0: soc@000000000 { + #address-cells = <2>; + #size-cells = <2>; + device_type = "soc"; + compatible = "simple-bus"; + ranges = <0x0 0x0 0x0 0x0 0x1 0x0>; + chip-id = <0>; + + soc0_mdio0: mdio@803c0000 { + #address-cells = <1>; + #size-cells = <0>; + compatible = "hisilicon,hns-mdio"; + reg = <0x0 0x803c0000 0x0 0x10000 + 0x0 0x80000000 0x0 0x10000>; + + soc0_phy4: ethernet-phy@4 { + reg = <0x0>; + device_type = "ethernet-phy"; + compatible = "ethernet-phy-ieee802.3-c22"; + }; + soc0_phy5: ethernet-phy@5 { + reg = <0x1>; + device_type = "ethernet-phy"; + compatible = "ethernet-phy-ieee802.3-c22"; + }; + }; + + dsa: dsa@c7000000 { + compatible = "hisilicon,hns-dsaf-v1"; + dsa_name = "dsaf0"; + mode = "6port-16rss"; + interrupt-parent = <&mbigen_dsa>; + + reg = <0x0 0xC0000000 0x0 0x420000 + 0x0 0xC2000000 0x0 0x300000 + 0x0 0xc5000000 0x0 0x890000 + 0x0 0xc7000000 0x0 0x60000 + >; + + phy-handle = <0 0 0 0 &soc0_phy4 &soc0_phy5 0 0>; + interrupts = < + /* [14] ge fifo err 8 / xge 6**/ + 149 0x4 150 0x4 151 0x4 152 0x4 + 153 0x4 154 0x4 26 0x4 27 0x4 + 155 0x4 156 0x4 157 0x4 158 0x4 159 0x4 160 0x4 + /* [12] rcb com 4*3**/ + 0x6 0x4 0x7 0x4 0x8 0x4 0x9 0x4 + 16 0x4 17 0x4 18 0x4 19 0x4 + 22 0x4 23 0x4 24 0x4 25 0x4 + /* [8] ppe tnl 0-7***/ + 0x0 0x4 0x1 0x4 0x2 0x4 0x3 0x4 + 0x4 0x4 0x5 0x4 12 0x4 13 0x4 + /* [21] dsaf event int 3+18**/ + 128 0x4 129 0x4 130 0x4 + 0x83 0x4 0x84 0x4 0x85 0x4 0x86 0x4 0x87 0x4 0x88 0x4 + 0x89 0x4 0x8a 0x4 0x8b 0x4 0x8c 0x4 0x8d 0x4 0x8e 0x4 + 0x8f 0x4 0x90 0x4 0x91 0x4 0x92 0x4 0x93 0x4 0x94 0x4 + /* [4] debug rcb 2*2*/ + 0xe 0x1 0xf 0x1 0x14 0x1 0x15 0x1 + /* [256] sevice rcb 2*128*/ + 0x180 0x1 0x181 0x1 0x182 0x1 0x183 0x1 + 0x184 0x1 0x185 0x1 0x186 0x1 0x187 0x1 + 0x188 0x1 0x189 0x1 0x18a 0x1 0x18b 0x1 + 0x18c 0x1 0x18d 0x1 0x18e 0x1 0x18f 0x1 + 0x190 0x1 0x191 0x1 0x192 0x1 0x193 0x1 + 0x194 0x1 0x195 0x1 0x196 0x1 0x197 0x1 + 0x198 0x1 0x199 0x1 0x19a 0x1 0x19b 0x1 + 0x19c 0x1 0x19d 0x1 0x19e 0x1 0x19f 0x1 + 0x1a0 0x1 0x1a1 0x1 0x1a2 0x1 0x1a3 0x1 + 0x1a4 0x1 0x1a5 0x1 0x1a6 0x1 0x1a7 0x1 + 0x1a8 0x1 0x1a9 0x1 0x1aa 0x1 0x1ab 0x1 + 0x1ac 0x1 0x1ad 0x1 0x1ae 0x1 0x1af 0x1 + 0x1b0 0x1 0x1b1 0x1 0x1b2 0x1 0x1b3 0x1 + 0x1b4 0x1 0x1b5 0x1 0x1b6 0x1 0x1b7 0x1 + 0x1b8 0x1 0x1b9 0x1 0x1ba 0x1 0x1bb 0x1 + 0x1bc 0x1 0x1bd 0x1 0x1be 0x1 0x1bf 0x1 + 0x1c0 0x1 0x1c1 0x1 0x1c2 0x1 0x1c3 0x1 + 0x1c4 0x1 0x1c5 0x1 0x1c6 0x1 0x1c7 0x1 + 0x1c8 0x1 0x1c9 0x1 0x1ca 0x1 0x1cb 0x1 + 0x1cc 0x1 0x1cd 0x1 0x1ce 0x1 0x1cf 0x1 + 0x1d0 0x1 0x1d1 0x1 0x1d2 0x1 0x1d3 0x1 + 0x1d4 0x1 0x1d5 0x1 0x1d6 0x1 0x1d7 0x1 + 0x1d8 0x1 0x1d9 0x1 0x1da 0x1 0x1db 0x1 + 0x1dc 0x1 0x1dd 0x1 0x1de 0x1 0x1df 0x1 + 0x1e0 0x1 0x1e1 0x1 0x1e2 0x1 0x1e3 0x1 + 0x1e4 0x1 0x1e5 0x1 0x1e6 0x1 0x1e7 0x1 + 0x1e8 0x1 0x1e9 0x1 0x1ea 0x1 0x1eb 0x1 + 0x1ec 0x1 0x1ed 0x1 0x1ee 0x1 0x1ef 0x1 + 0x1f0 0x1 0x1f1 0x1 0x1f2 0x1 0x1f3 0x1 + 0x1f4 0x1 0x1f5 0x1 0x1f6 0x1 0x1f7 0x1 + 0x1f8 0x1 0x1f9 0x1 0x1fa 0x1 0x1fb 0x1 + 0x1fc 0x1 0x1fd 0x1 0x1fe 0x1 0x1ff 0x1 + 0x200 0x1 0x201 0x1 0x202 0x1 0x203 0x1 + 0x204 0x1 0x205 0x1 0x206 0x1 0x207 0x1 + 0x208 0x1 0x209 0x1 0x20a 0x1 0x20b 0x1 + 0x20c 0x1 0x20d 0x1 0x20e 0x1 0x20f 0x1 + 0x210 0x1 0x211 0x1 0x212 0x1 0x213 0x1 + 0x214 0x1 0x215 0x1 0x216 0x1 0x217 0x1 + 0x218 0x1 0x219 0x1 0x21a 0x1 0x21b 0x1 + 0x21c 0x1 0x21d 0x1 0x21e 0x1 0x21f 0x1 + 0x220 0x1 0x221 0x1 0x222 0x1 0x223 0x1 + 0x224 0x1 0x225 0x1 0x226 0x1 0x227 0x1 + 0x228 0x1 0x229 0x1 0x22a 0x1 0x22b 0x1 + 0x22c 0x1 0x22d 0x1 0x22e 0x1 0x22f 0x1 + 0x230 0x1 0x231 0x1 0x232 0x1 0x233 0x1 + 0x234 0x1 0x235 0x1 0x236 0x1 0x237 0x1 + 0x238 0x1 0x239 0x1 0x23a 0x1 0x23b 0x1 + 0x23c 0x1 0x23d 0x1 0x23e 0x1 0x23f 0x1 + 0x240 0x1 0x241 0x1 0x242 0x1 0x243 0x1 + 0x244 0x1 0x245 0x1 0x246 0x1 0x247 0x1 + 0x248 0x1 0x249 0x1 0x24a 0x1 0x24b 0x1 + 0x24c 0x1 0x24d 0x1 0x24e 0x1 0x24f 0x1 + 0x250 0x1 0x251 0x1 0x252 0x1 0x253 0x1 + 0x254 0x1 0x255 0x1 0x256 0x1 0x257 0x1 + 0x258 0x1 0x259 0x1 0x25a 0x1 0x25b 0x1 + 0x25c 0x1 0x25d 0x1 0x25e 0x1 0x25f 0x1 + 0x260 0x1 0x261 0x1 0x262 0x1 0x263 0x1 + 0x264 0x1 0x265 0x1 0x266 0x1 0x267 0x1 + 0x268 0x1 0x269 0x1 0x26a 0x1 0x26b 0x1 + 0x26c 0x1 0x26d 0x1 0x26e 0x1 0x26f 0x1 + 0x270 0x1 0x271 0x1 0x272 0x1 0x273 0x1 + 0x274 0x1 0x275 0x1 0x276 0x1 0x277 0x1 + 0x278 0x1 0x279 0x1 0x27a 0x1 0x27b 0x1 + 0x27c 0x1 0x27d 0x1 0x27e 0x1 0x27f 0x1>; + buf-size = <4096>; + desc-num = <1024>; + dma-coherent; + }; + + eth0: ethernet@0{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <0>; + local-mac-address = [00 00 00 01 00 58]; + status = "disabled"; + dma-coherent; + }; + eth1: ethernet@1{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <1>; + status = "disabled"; + dma-coherent; + }; + eth2: ethernet@2{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <2>; + local-mac-address = [00 00 00 01 00 5a]; + status = "disabled"; + dma-coherent; + }; + eth3: ethernet@3{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <3>; + local-mac-address = [00 00 00 01 00 5b]; + status = "disabled"; + dma-coherent; + }; + eth4: ethernet@4{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <4>; + local-mac-address = [00 00 00 01 00 5c]; + status = "disabled"; + dma-coherent; + }; + eth5: ethernet@5{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <5>; + local-mac-address = [00 00 00 01 00 5d]; + status = "disabled"; + dma-coherent; + }; + eth6: ethernet@6{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <6>; + local-mac-address = [00 00 00 01 00 5e]; + status = "disabled"; + dma-coherent; + }; + eth7: ethernet@7{ + compatible = "hisilicon,hns-nic-v1"; + ae-name = "dsaf0"; + port-id = <7>; + local-mac-address = [00 00 00 01 00 5f]; + status = "disabled"; + dma-coherent; + }; +}; -- cgit v1.2.3 From 2e6fd648b6b87e6a2289c875c6067acc3bd88b3e Mon Sep 17 00:00:00 2001 From: Alexander Aring Date: Mon, 21 Sep 2015 11:24:26 +0200 Subject: mrf24j40: add device-tree support This patch adds devicetree support to mrf24j40 with proper devicetree compatible strings. Reviewed-by: Stefan Schmidt Signed-off-by: Alexander Aring Signed-off-by: Marcel Holtmann --- .../devicetree/bindings/net/ieee802154/mrf24j40.txt | 20 ++++++++++++++++++++ MAINTAINERS | 1 + drivers/net/ieee802154/mrf24j40.c | 9 +++++++++ 3 files changed, 30 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt b/Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt new file mode 100644 index 000000000000..a4ed2efb5b73 --- /dev/null +++ b/Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt @@ -0,0 +1,20 @@ +* MRF24J40 IEEE 802.15.4 * + +Required properties: + - compatible: should be "microchip,mrf24j40", "microchip,mrf24j40ma", + or "microchip,mrf24j40mc" depends on your transceiver + board + - spi-max-frequency: maximal bus speed, should be set something under or equal + 10000000 + - reg: the chipselect index + - interrupts: the interrupt generated by the device. + +Example: + + mrf24j40ma@0 { + compatible = "microchip,mrf24j40ma"; + spi-max-frequency = <8500000>; + reg = <0>; + interrupts = <19 8>; + interrupt-parent = <&gpio3>; + }; diff --git a/MAINTAINERS b/MAINTAINERS index 310da4295c70..6790ecc65e6b 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -6958,6 +6958,7 @@ M: Alan Ott L: linux-wpan@vger.kernel.org S: Maintained F: drivers/net/ieee802154/mrf24j40.c +F: Documentation/devicetree/bindings/net/ieee802154/mrf24j40.txt MSI LAPTOP SUPPORT M: "Lee, Chun-Yi" diff --git a/drivers/net/ieee802154/mrf24j40.c b/drivers/net/ieee802154/mrf24j40.c index 41d9f5770148..89150bd43ab2 100644 --- a/drivers/net/ieee802154/mrf24j40.c +++ b/drivers/net/ieee802154/mrf24j40.c @@ -799,6 +799,14 @@ static int mrf24j40_remove(struct spi_device *spi) return 0; } +static const struct of_device_id mrf24j40_of_match[] = { + { .compatible = "microchip,mrf24j40", .data = (void *)MRF24J40 }, + { .compatible = "microchip,mrf24j40ma", .data = (void *)MRF24J40MA }, + { .compatible = "microchip,mrf24j40mc", .data = (void *)MRF24J40MC }, + { }, +}; +MODULE_DEVICE_TABLE(of, mrf24j40_of_match); + static const struct spi_device_id mrf24j40_ids[] = { { "mrf24j40", MRF24J40 }, { "mrf24j40ma", MRF24J40MA }, @@ -809,6 +817,7 @@ MODULE_DEVICE_TABLE(spi, mrf24j40_ids); static struct spi_driver mrf24j40_driver = { .driver = { + .of_match_table = of_match_ptr(mrf24j40_of_match), .name = "mrf24j40", .owner = THIS_MODULE, }, -- cgit v1.2.3 From 45ffda75e145ed7a2b40f6a5de35431d7e62d1f0 Mon Sep 17 00:00:00 2001 From: Scott Feldman Date: Wed, 23 Sep 2015 08:39:20 -0700 Subject: switchdev: update documentation on FDB ageing_time Signed-off-by: Scott Feldman Reviewed-by: Vivien Didelot Acked-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 24 ++++++++++++------------ 1 file changed, 12 insertions(+), 12 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 476df0496686..67e43ee7840a 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -239,20 +239,20 @@ The driver should initialize the attributes to the hardware defaults. FDB Ageing ^^^^^^^^^^ -There are two FDB ageing models supported: 1) ageing by the device, and 2) -ageing by the kernel. Ageing by the device is preferred if many FDB entries -are supported. The driver calls call_switchdev_notifiers(SWITCHDEV_FDB_DEL, -...) to age out the FDB entry. In this model, ageing by the kernel should be -turned off. XXX: how to turn off ageing in kernel on a per-port basis or -otherwise prevent the kernel from ageing out the FDB entry? - -In the kernel ageing model, the standard bridge ageing mechanism is used to age -out stale FDB entries. To keep an FDB entry "alive", the driver should refresh -the FDB entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...). The +The bridge will skip ageing FDB entries marked with NTF_EXT_LEARNED and it is +the responsibility of the port driver/device to age out these entries. If the +port device supports ageing, when the FDB entry expires, it will notify the +driver which in turn will notify the bridge with SWITCHDEV_FDB_DEL. If the +device does not support ageing, the driver can simulate ageing using a +garbage collection timer to monitor FBD entries. Expired entries will be +notified to the bridge using SWITCHDEV_FDB_DEL. See rocker driver for +example of driver running ageing timer. + +To keep an NTF_EXT_LEARNED entry "alive", the driver should refresh the FDB +entry by calling call_switchdev_notifiers(SWITCHDEV_FDB_ADD, ...). The notification will reset the FDB entry's last-used time to now. The driver should rate limit refresh notifications, for example, no more than once a -second. If the FDB entry expires, fdb_delete is called to remove entry from -the device. +second. (The last-used time is visible using the bridge -s fdb option). STP State Change on Port ^^^^^^^^^^^^^^^^^^^^^^^^ -- cgit v1.2.3 From 7ea6eb3f56f45cf4babae8b9a7421868e5005f17 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 24 Sep 2015 10:02:41 +0200 Subject: switchdev: introduce transaction item queue for attr_set and obj_add Now, the memory allocation in prepare/commit state is done separatelly in each driver (rocker). Introduce the similar mechanism in generic switchdev code, in form of queue. That can be used not only for memory allocations, but also for different items. Abort item destruction is handled as well. Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 19 ++++++ drivers/net/ethernet/rocker/rocker.c | 6 +- include/net/switchdev.h | 24 ++++++- net/dsa/slave.c | 6 +- net/switchdev/switchdev.c | 111 +++++++++++++++++++++++++++++---- 5 files changed, 146 insertions(+), 20 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 67e43ee7840a..9f9e2587b347 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -369,3 +369,22 @@ The driver can monitor for updates to arp_tbl using the netevent notifier NETEVENT_NEIGH_UPDATE. The device can be programmed with resolved nexthops for the routes as arp_tbl updates. The driver implements ndo_neigh_destroy to know when arp_tbl neighbor entries are purged from the port. + +Transaction item queue +^^^^^^^^^^^^^^^^^^^^^^ + +For switchdev ops attr_set and obj_add, there is a 2 phase transaction model +used. First phase is to "prepare" anything needed, including various checks, +memory allocation, etc. The goal is to handle the stuff that is not unlikely +to fail here. The second phase is to "commit" the actual changes. + +Switchdev provides an inftrastructure for sharing items (for example memory +allocations) between the two phases. + +The object created by a driver in "prepare" phase and it is queued up by: +switchdev_trans_item_enqueue() +During the "commit" phase, the driver gets the object by: +switchdev_trans_item_dequeue() + +If a transaction is aborted during "prepare" phase, switchdev code will handle +cleanup of the queued-up objects. diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index cf03b077311e..dcc6f3fd13c9 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4383,7 +4383,8 @@ static int rocker_port_brport_flags_set(struct rocker_port *rocker_port, } static int rocker_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); int err = 0; @@ -4467,7 +4468,8 @@ static int rocker_port_fdb_add(struct rocker_port *rocker_port, } static int rocker_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { struct rocker_port *rocker_port = netdev_priv(dev); const struct switchdev_obj_ipv4_fib *fib4; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 494f51097dc6..1e394f1176b6 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -1,6 +1,6 @@ /* * include/net/switchdev.h - Switch device API - * Copyright (c) 2014 Jiri Pirko + * Copyright (c) 2014-2015 Jiri Pirko * Copyright (c) 2014-2015 Scott Feldman * * This program is free software; you can redistribute it and/or modify @@ -13,6 +13,7 @@ #include #include +#include #define SWITCHDEV_F_NO_RECURSE BIT(0) @@ -23,6 +24,16 @@ enum switchdev_trans_ph { SWITCHDEV_TRANS_COMMIT, }; +struct switchdev_trans_item { + struct list_head list; + void *data; + void (*destructor)(const void *data); +}; + +struct switchdev_trans { + struct list_head item_list; +}; + enum switchdev_attr_id { SWITCHDEV_ATTR_UNDEFINED, SWITCHDEV_ATTR_PORT_PARENT_ID, @@ -77,6 +88,11 @@ struct switchdev_obj { } u; }; +void switchdev_trans_item_enqueue(struct switchdev_trans *trans, + void *data, void (*destructor)(void const *), + struct switchdev_trans_item *tritem); +void *switchdev_trans_item_dequeue(struct switchdev_trans *trans); + /** * struct switchdev_ops - switchdev operations * @@ -94,9 +110,11 @@ struct switchdev_ops { int (*switchdev_port_attr_get)(struct net_device *dev, struct switchdev_attr *attr); int (*switchdev_port_attr_set)(struct net_device *dev, - struct switchdev_attr *attr); + struct switchdev_attr *attr, + struct switchdev_trans *trans); int (*switchdev_port_obj_add)(struct net_device *dev, - struct switchdev_obj *obj); + struct switchdev_obj *obj, + struct switchdev_trans *trans); int (*switchdev_port_obj_del)(struct net_device *dev, struct switchdev_obj *obj); int (*switchdev_port_obj_dump)(struct net_device *dev, diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7f50b7443402..ac76fd15ad8b 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -456,7 +456,8 @@ static int dsa_slave_stp_update(struct net_device *dev, u8 state) } static int dsa_slave_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { int ret = 0; @@ -474,7 +475,8 @@ static int dsa_slave_port_attr_set(struct net_device *dev, } static int dsa_slave_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { int err; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index df5a5446ff4c..35e2967ffa18 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -1,6 +1,6 @@ /* * net/switchdev/switchdev.c - Switch device API - * Copyright (c) 2014 Jiri Pirko + * Copyright (c) 2014-2015 Jiri Pirko * Copyright (c) 2014-2015 Scott Feldman * * This program is free software; you can redistribute it and/or modify @@ -16,9 +16,82 @@ #include #include #include +#include #include #include +/** + * switchdev_trans_item_enqueue - Enqueue data item to transaction queue + * + * @trans: transaction + * @data: pointer to data being queued + * @destructor: data destructor + * @tritem: transaction item being queued + * + * Enqeueue data item to transaction queue. tritem is typically placed in + * cointainter pointed at by data pointer. Destructor is called on + * transaction abort and after successful commit phase in case + * the caller did not dequeue the item before. + */ +void switchdev_trans_item_enqueue(struct switchdev_trans *trans, + void *data, void (*destructor)(void const *), + struct switchdev_trans_item *tritem) +{ + tritem->data = data; + tritem->destructor = destructor; + list_add_tail(&tritem->list, &trans->item_list); +} +EXPORT_SYMBOL_GPL(switchdev_trans_item_enqueue); + +static struct switchdev_trans_item * +__switchdev_trans_item_dequeue(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + if (list_empty(&trans->item_list)) + return NULL; + tritem = list_first_entry(&trans->item_list, + struct switchdev_trans_item, list); + list_del(&tritem->list); + return tritem; +} + +/** + * switchdev_trans_item_dequeue - Dequeue data item from transaction queue + * + * @trans: transaction + */ +void *switchdev_trans_item_dequeue(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + tritem = __switchdev_trans_item_dequeue(trans); + BUG_ON(!tritem); + return tritem->data; +} +EXPORT_SYMBOL_GPL(switchdev_trans_item_dequeue); + +static void switchdev_trans_init(struct switchdev_trans *trans) +{ + INIT_LIST_HEAD(&trans->item_list); +} + +static void switchdev_trans_items_destroy(struct switchdev_trans *trans) +{ + struct switchdev_trans_item *tritem; + + while ((tritem = __switchdev_trans_item_dequeue(trans))) + tritem->destructor(tritem->data); +} + +static void switchdev_trans_items_warn_destroy(struct net_device *dev, + struct switchdev_trans *trans) +{ + WARN(!list_empty(&trans->item_list), "%s: transaction item queue is not empty.\n", + dev->name); + switchdev_trans_items_destroy(trans); +} + /** * switchdev_port_attr_get - Get port attribute * @@ -62,7 +135,8 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) EXPORT_SYMBOL_GPL(switchdev_port_attr_get); static int __switchdev_port_attr_set(struct net_device *dev, - struct switchdev_attr *attr) + struct switchdev_attr *attr, + struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -70,7 +144,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_attr_set) - return ops->switchdev_port_attr_set(dev, attr); + return ops->switchdev_port_attr_set(dev, attr, trans); if (attr->flags & SWITCHDEV_F_NO_RECURSE) return err; @@ -81,7 +155,7 @@ static int __switchdev_port_attr_set(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_attr_set(lower_dev, attr); + err = __switchdev_port_attr_set(lower_dev, attr, trans); if (err) break; } @@ -144,6 +218,7 @@ static int switchdev_port_attr_set_defer(struct net_device *dev, */ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) { + struct switchdev_trans trans; int err; if (!rtnl_is_locked()) { @@ -156,6 +231,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) return switchdev_port_attr_set_defer(dev, attr); } + switchdev_trans_init(&trans); + /* Phase I: prepare for attr set. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -164,7 +241,7 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) */ attr->trans_ph = SWITCHDEV_TRANS_PREPARE; - err = __switchdev_port_attr_set(dev, attr); + err = __switchdev_port_attr_set(dev, attr, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are @@ -173,7 +250,8 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) if (err != -EOPNOTSUPP) { attr->trans_ph = SWITCHDEV_TRANS_ABORT; - __switchdev_port_attr_set(dev, attr); + __switchdev_port_attr_set(dev, attr, &trans); + switchdev_trans_items_destroy(&trans); } return err; @@ -185,16 +263,18 @@ int switchdev_port_attr_set(struct net_device *dev, struct switchdev_attr *attr) */ attr->trans_ph = SWITCHDEV_TRANS_COMMIT; - err = __switchdev_port_attr_set(dev, attr); + err = __switchdev_port_attr_set(dev, attr, &trans); WARN(err, "%s: Commit of attribute (id=%d) failed.\n", dev->name, attr->id); + switchdev_trans_items_warn_destroy(dev, &trans); return err; } EXPORT_SYMBOL_GPL(switchdev_port_attr_set); static int __switchdev_port_obj_add(struct net_device *dev, - struct switchdev_obj *obj) + struct switchdev_obj *obj, + struct switchdev_trans *trans) { const struct switchdev_ops *ops = dev->switchdev_ops; struct net_device *lower_dev; @@ -202,7 +282,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, int err = -EOPNOTSUPP; if (ops && ops->switchdev_port_obj_add) - return ops->switchdev_port_obj_add(dev, obj); + return ops->switchdev_port_obj_add(dev, obj, trans); /* Switch device port(s) may be stacked under * bond/team/vlan dev, so recurse down to add object on @@ -210,7 +290,7 @@ static int __switchdev_port_obj_add(struct net_device *dev, */ netdev_for_each_lower_dev(dev, lower_dev, iter) { - err = __switchdev_port_obj_add(lower_dev, obj); + err = __switchdev_port_obj_add(lower_dev, obj, trans); if (err) break; } @@ -232,10 +312,13 @@ static int __switchdev_port_obj_add(struct net_device *dev, */ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) { + struct switchdev_trans trans; int err; ASSERT_RTNL(); + switchdev_trans_init(&trans); + /* Phase I: prepare for obj add. Driver/device should fail * here if there are going to be issues in the commit phase, * such as lack of resources or support. The driver/device @@ -244,7 +327,7 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ obj->trans_ph = SWITCHDEV_TRANS_PREPARE; - err = __switchdev_port_obj_add(dev, obj); + err = __switchdev_port_obj_add(dev, obj, &trans); if (err) { /* Prepare phase failed: abort the transaction. Any * resources reserved in the prepare phase are @@ -253,7 +336,8 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) if (err != -EOPNOTSUPP) { obj->trans_ph = SWITCHDEV_TRANS_ABORT; - __switchdev_port_obj_add(dev, obj); + __switchdev_port_obj_add(dev, obj, &trans); + switchdev_trans_items_destroy(&trans); } return err; @@ -265,8 +349,9 @@ int switchdev_port_obj_add(struct net_device *dev, struct switchdev_obj *obj) */ obj->trans_ph = SWITCHDEV_TRANS_COMMIT; - err = __switchdev_port_obj_add(dev, obj); + err = __switchdev_port_obj_add(dev, obj, &trans); WARN(err, "%s: Commit of object (id=%d) failed.\n", dev->name, obj->id); + switchdev_trans_items_warn_destroy(dev, &trans); return err; } -- cgit v1.2.3 From 008aa6a4faac36fe623ff5a1ba753dc9b0d8102e Mon Sep 17 00:00:00 2001 From: stephen hemminger Date: Wed, 23 Sep 2015 21:33:36 -0700 Subject: l2tp: remove references to modprobe in documentation No longer need explicit modprobe's and update to use ip instead of deprecated ifconfig command. Signed-off-by: Stephen Hemminger Signed-off-by: David S. Miller --- Documentation/networking/l2tp.txt | 7 ++----- 1 file changed, 2 insertions(+), 5 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/l2tp.txt b/Documentation/networking/l2tp.txt index c74434de2fa5..4650a00ed012 100644 --- a/Documentation/networking/l2tp.txt +++ b/Documentation/networking/l2tp.txt @@ -213,15 +213,12 @@ To create an L2TPv3 ethernet pseudowire between local host 192.168.1.1 and peer 192.168.1.2, using IP addresses 10.5.1.1 and 10.5.1.2 for the tunnel endpoints:- -# modprobe l2tp_eth -# modprobe l2tp_netlink - # ip l2tp add tunnel tunnel_id 1 peer_tunnel_id 1 udp_sport 5000 \ udp_dport 5000 encap udp local 192.168.1.1 remote 192.168.1.2 # ip l2tp add session tunnel_id 1 session_id 1 peer_session_id 1 -# ifconfig -a +# ip -s -d show dev l2tpeth0 # ip addr add 10.5.1.2/32 peer 10.5.1.1/32 dev l2tpeth0 -# ifconfig l2tpeth0 up +# ip li set dev l2tpeth0 up Choose IP addresses to be the address of a local IP interface and that of the remote system. The IP addresses of the l2tpeth0 interface can be -- cgit v1.2.3 From c386578f1cdb4dac230395a951f88027f64346e3 Mon Sep 17 00:00:00 2001 From: Steffen Klassert Date: Tue, 29 Sep 2015 11:40:49 +0200 Subject: xfrm: Let the flowcache handle its size by default. The xfrm flowcache size is limited by the flowcache limit (4096 * number of online cpus) and the xfrm garbage collector threshold (2 * 32768), whatever is reached first. This means that we can hit the garbage collector limit only on systems with more than 16 cpus. On such systems we simply refuse new allocations if we reach the limit, so new flows are dropped. On syslems with 16 or less cpus, we hit the flowcache limit. In this case, we shrink the flow cache instead of refusing new flows. We increase the xfrm garbage collector threshold to INT_MAX to get the same behaviour, independent of the number of cpus. The xfrm garbage collector threshold can still be set below the flowcache limit to reduce the memory usage of the flowcache. Tested-by: Dan Streetman Signed-off-by: Steffen Klassert --- Documentation/networking/ip-sysctl.txt | 6 ++++-- net/ipv4/xfrm4_policy.c | 2 +- net/ipv6/xfrm6_policy.c | 2 +- 3 files changed, 6 insertions(+), 4 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ebe94f2cab98..260f30b2def6 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1199,7 +1199,8 @@ tag - INTEGER xfrm4_gc_thresh - INTEGER The threshold at which we will start garbage collecting for IPv4 destination cache entries. At twice this value the system will - refuse new allocations. + refuse new allocations. The value must be set below the flowcache + limit (4096 * number of online cpus) to take effect. igmp_link_local_mcast_reports - BOOLEAN Enable IGMP reports for link local multicast groups in the @@ -1645,7 +1646,8 @@ ratelimit - INTEGER xfrm6_gc_thresh - INTEGER The threshold at which we will start garbage collecting for IPv6 destination cache entries. At twice this value the system will - refuse new allocations. + refuse new allocations. The value must be set below the flowcache + limit (4096 * number of online cpus) to take effect. IPv6 Update by: diff --git a/net/ipv4/xfrm4_policy.c b/net/ipv4/xfrm4_policy.c index 0304d1680ca2..75e8d48c03fb 100644 --- a/net/ipv4/xfrm4_policy.c +++ b/net/ipv4/xfrm4_policy.c @@ -246,7 +246,7 @@ static struct dst_ops xfrm4_dst_ops = { .destroy = xfrm4_dst_destroy, .ifdown = xfrm4_dst_ifdown, .local_out = __ip_local_out, - .gc_thresh = 32768, + .gc_thresh = INT_MAX, }; static struct xfrm_policy_afinfo xfrm4_policy_afinfo = { diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 30caa289c5db..2fad59320b6c 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -287,7 +287,7 @@ static struct dst_ops xfrm6_dst_ops = { .destroy = xfrm6_dst_destroy, .ifdown = xfrm6_dst_ifdown, .local_out = __ip6_local_out, - .gc_thresh = 32768, + .gc_thresh = INT_MAX, }; static struct xfrm_policy_afinfo xfrm6_policy_afinfo = { -- cgit v1.2.3 From 57d80838dae55c1bc6ca629e471c84100513079a Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:41 +0200 Subject: switchdev: rename SWITCHDEV_OBJ_* enum values to SWITCHDEV_OBJ_ID_* Suggested-by: Vivien Didelot Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 6 +++--- drivers/net/ethernet/rocker/rocker.c | 16 ++++++++-------- include/net/switchdev.h | 14 +++++++------- net/bridge/br_fdb.c | 2 +- net/bridge/br_vlan.c | 6 ++++-- net/dsa/slave.c | 12 ++++++------ net/switchdev/switchdev.c | 16 ++++++++-------- 7 files changed, 37 insertions(+), 35 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 9f9e2587b347..c150a87c774b 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -178,7 +178,7 @@ entries are installed, for example, using iproute2 bridge cmd: bridge fdb add ADDR dev DEV [vlan VID] [self] The driver should use the helper switchdev_port_fdb_xxx ops for ndo_fdb_xxx -ops, and handle add/delete/dump of SWITCHDEV_OBJ_PORT_FDB object using +ops, and handle add/delete/dump of SWITCHDEV_OBJ_ID_PORT_FDB object using switchdev_port_obj_xxx ops. XXX: what should be done if offloading this rule to hardware fails (for @@ -316,9 +316,9 @@ SWITCHDEV_OBJ_IPV[4|6]_FIB object using switchdev_port_obj_xxx ops. switchdev_port_obj_add is used for both adding a new FIB entry to the device, or modifying an existing entry on the device. -XXX: Currently, only SWITCHDEV_OBJ_IPV4_FIB objects are supported. +XXX: Currently, only SWITCHDEV_OBJ_ID_IPV4_FIB objects are supported. -SWITCHDEV_OBJ_IPV4_FIB object passes: +SWITCHDEV_OBJ_ID_IPV4_FIB object passes: struct switchdev_obj_ipv4_fib { /* IPV4_FIB */ u32 dst; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 9773f5b65296..9b2e8bed8f83 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4445,16 +4445,16 @@ static int rocker_port_obj_add(struct net_device *dev, int err = 0; switch (id) { - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlans_add(rocker_port, trans, obj); break; - case SWITCHDEV_OBJ_IPV4_FIB: + case SWITCHDEV_OBJ_ID_IPV4_FIB: fib4 = obj; err = rocker_port_fib_ipv4(rocker_port, trans, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, 0); break; - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_add(rocker_port, trans, obj); break; default: @@ -4515,17 +4515,17 @@ static int rocker_port_obj_del(struct net_device *dev, int err = 0; switch (id) { - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlans_del(rocker_port, obj); break; - case SWITCHDEV_OBJ_IPV4_FIB: + case SWITCHDEV_OBJ_ID_IPV4_FIB: fib4 = obj; err = rocker_port_fib_ipv4(rocker_port, NULL, htonl(fib4->dst), fib4->dst_len, fib4->fi, fib4->tb_id, ROCKER_OP_FLAG_REMOVE); break; - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_del(rocker_port, NULL, obj); break; default: @@ -4594,10 +4594,10 @@ static int rocker_port_obj_dump(struct net_device *dev, int err = 0; switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = rocker_port_fdb_dump(rocker_port, obj, cb); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = rocker_port_vlan_dump(rocker_port, obj, cb); break; default: diff --git a/include/net/switchdev.h b/include/net/switchdev.h index e11425eb0735..11f9c706cf5c 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -58,20 +58,20 @@ struct switchdev_attr { struct fib_info; enum switchdev_obj_id { - SWITCHDEV_OBJ_UNDEFINED, - SWITCHDEV_OBJ_PORT_VLAN, - SWITCHDEV_OBJ_IPV4_FIB, - SWITCHDEV_OBJ_PORT_FDB, + SWITCHDEV_OBJ_ID_UNDEFINED, + SWITCHDEV_OBJ_ID_PORT_VLAN, + SWITCHDEV_OBJ_ID_IPV4_FIB, + SWITCHDEV_OBJ_ID_PORT_FDB, }; -/* SWITCHDEV_OBJ_PORT_VLAN */ +/* SWITCHDEV_OBJ_ID_PORT_VLAN */ struct switchdev_obj_vlan { u16 flags; u16 vid_begin; u16 vid_end; }; -/* SWITCHDEV_OBJ_IPV4_FIB */ +/* SWITCHDEV_OBJ_ID_IPV4_FIB */ struct switchdev_obj_ipv4_fib { u32 dst; int dst_len; @@ -82,7 +82,7 @@ struct switchdev_obj_ipv4_fib { u32 tb_id; }; -/* SWITCHDEV_OBJ_PORT_FDB */ +/* SWITCHDEV_OBJ_ID_PORT_FDB */ struct switchdev_obj_fdb { const unsigned char *addr; u16 vid; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index 7826782d62ab..6fc8e71277d4 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -138,7 +138,7 @@ static void fdb_del_external_learn(struct net_bridge_fdb_entry *f) .vid = f->vlan_id, }; - switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); + switchdev_port_obj_del(f->dst->dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); } static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 75214a51cf0e..68b5a1125667 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -88,7 +88,8 @@ static int __vlan_vid_add(struct net_device *dev, struct net_bridge *br, .vid_end = vid, }; - err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, + &v); if (err == -EOPNOTSUPP) err = 0; } @@ -136,7 +137,8 @@ static int __vlan_vid_del(struct net_device *dev, struct net_bridge *br, .vid_end = vid, }; - err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_VLAN, &v); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, + &v); if (err == -EOPNOTSUPP) err = 0; } diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 7b1d9ec74e09..a7060298b856 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -485,10 +485,10 @@ static int dsa_slave_port_obj_add(struct net_device *dev, */ switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_add(dev, obj, trans); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_add(dev, obj, trans); break; default: @@ -505,10 +505,10 @@ static int dsa_slave_port_obj_del(struct net_device *dev, int err; switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_del(dev, obj); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_del(dev, obj); break; default: @@ -526,10 +526,10 @@ static int dsa_slave_port_obj_dump(struct net_device *dev, int err; switch (id) { - case SWITCHDEV_OBJ_PORT_FDB: + case SWITCHDEV_OBJ_ID_PORT_FDB: err = dsa_slave_port_fdb_dump(dev, obj, cb); break; - case SWITCHDEV_OBJ_PORT_VLAN: + case SWITCHDEV_OBJ_ID_PORT_VLAN: err = dsa_slave_port_vlan_dump(dev, obj, cb); break; default: diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index fe82fab1d55c..5b1aa9f6f261 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -584,7 +584,7 @@ static int switchdev_port_vlan_fill(struct sk_buff *skb, struct net_device *dev, if ((filter_mask & RTEXT_FILTER_BRVLAN) || (filter_mask & RTEXT_FILTER_BRVLAN_COMPRESSED)) { - err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_VLAN, + err = switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &dump.vlan, switchdev_port_vlan_dump_cb); if (err) @@ -725,7 +725,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, vlan.vid_end = vinfo->vid; if (vlan.vid_end <= vlan.vid_begin) return -EINVAL; - err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); + err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -734,7 +734,7 @@ static int switchdev_port_br_afspec(struct net_device *dev, return -EINVAL; vlan.vid_begin = vinfo->vid; vlan.vid_end = vinfo->vid; - err = f(dev, SWITCHDEV_OBJ_PORT_VLAN, &vlan); + err = f(dev, SWITCHDEV_OBJ_ID_PORT_VLAN, &vlan); if (err) return err; memset(&vlan, 0, sizeof(vlan)); @@ -824,7 +824,7 @@ int switchdev_port_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], .vid = vid, }; - return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); + return switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_add); @@ -848,7 +848,7 @@ int switchdev_port_fdb_del(struct ndmsg *ndm, struct nlattr *tb[], .vid = vid, }; - return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_PORT_FDB, &fdb); + return switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &fdb); } EXPORT_SYMBOL_GPL(switchdev_port_fdb_del); @@ -926,7 +926,7 @@ int switchdev_port_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, .idx = idx, }; - switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_PORT_FDB, &dump.fdb, + switchdev_port_obj_dump(dev, SWITCHDEV_OBJ_ID_PORT_FDB, &dump.fdb, switchdev_port_fdb_dump_cb); return dump.idx; } @@ -1033,7 +1033,7 @@ int switchdev_fib_ipv4_add(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); + err = switchdev_port_obj_add(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags |= RTNH_F_OFFLOAD; @@ -1075,7 +1075,7 @@ int switchdev_fib_ipv4_del(u32 dst, int dst_len, struct fib_info *fi, if (!dev) return 0; - err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_IPV4_FIB, &ipv4_fib); + err = switchdev_port_obj_del(dev, SWITCHDEV_OBJ_ID_IPV4_FIB, &ipv4_fib); if (!err) fi->fib_flags &= ~RTNH_F_OFFLOAD; -- cgit v1.2.3 From 1f86839874a50c9ee2009567d2f312b1e1949e24 Mon Sep 17 00:00:00 2001 From: Jiri Pirko Date: Thu, 1 Oct 2015 11:03:42 +0200 Subject: switchdev: rename SWITCHDEV_ATTR_* enum values to SWITCHDEV_ATTR_ID_* To be aligned with obj. Signed-off-by: Jiri Pirko Acked-by: Scott Feldman Reviewed-by: Vivien Didelot Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 9 +++++---- drivers/net/ethernet/mellanox/mlxsw/switchx2.c | 2 +- drivers/net/ethernet/rocker/rocker.c | 8 ++++---- include/net/switchdev.h | 8 ++++---- net/bridge/br_stp.c | 2 +- net/core/net-sysfs.c | 2 +- net/core/rtnetlink.c | 2 +- net/dsa/slave.c | 4 ++-- net/switchdev/switchdev.c | 14 +++++++------- 9 files changed, 26 insertions(+), 25 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index c150a87c774b..0714fe555016 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -115,7 +115,7 @@ Switch ID ^^^^^^^^^ The switchdev driver must implement the switchdev op switchdev_port_attr_get -for SWITCHDEV_ATTR_PORT_PARENT_ID for each port netdev, returning the same +for SWITCHDEV_ATTR_ID_PORT_PARENT_ID for each port netdev, returning the same physical ID for each port of a switch. The ID must be unique between switches on the same system. The ID does not need to be unique between switches on different systems. @@ -233,8 +233,9 @@ the bridge's FDB. It's possible, but not optimal, to enable learning on the device port and on the bridge port, and disable learning_sync. To support learning and learning_sync port attributes, the driver implements -switchdev op switchdev_port_attr_get/set for SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS. -The driver should initialize the attributes to the hardware defaults. +switchdev op switchdev_port_attr_get/set for +SWITCHDEV_ATTR_PORT_ID_BRIDGE_FLAGS. The driver should initialize the attributes +to the hardware defaults. FDB Ageing ^^^^^^^^^^ @@ -260,7 +261,7 @@ STP State Change on Port Internally or with a third-party STP protocol implementation (e.g. mstpd), the bridge driver maintains the STP state for ports, and will notify the switch driver of STP state change on a port using the switchdev op -switchdev_attr_port_set for SWITCHDEV_ATTR_PORT_STP_UPDATE. +switchdev_attr_port_set for SWITCHDEV_ATTR_PORT_ID_STP_UPDATE. State is one of BR_STATE_*. The switch driver can use STP state updates to update ingress packet filter list for the port. For example, if port is diff --git a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c index 3e52ee93438c..d448431bbc83 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/switchx2.c +++ b/drivers/net/ethernet/mellanox/mlxsw/switchx2.c @@ -868,7 +868,7 @@ static int mlxsw_sx_port_attr_get(struct net_device *dev, struct mlxsw_sx *mlxsw_sx = mlxsw_sx_port->mlxsw_sx; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_PARENT_ID: + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: attr->u.ppid.id_len = sizeof(mlxsw_sx->hw_id); memcpy(&attr->u.ppid.id, &mlxsw_sx->hw_id, attr->u.ppid.id_len); break; diff --git a/drivers/net/ethernet/rocker/rocker.c b/drivers/net/ethernet/rocker/rocker.c index 9b2e8bed8f83..4540ca63a434 100644 --- a/drivers/net/ethernet/rocker/rocker.c +++ b/drivers/net/ethernet/rocker/rocker.c @@ -4329,11 +4329,11 @@ static int rocker_port_attr_get(struct net_device *dev, const struct rocker *rocker = rocker_port->rocker; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_PARENT_ID: + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: attr->u.ppid.id_len = sizeof(rocker->hw.id); memcpy(&attr->u.ppid.id, &rocker->hw.id, attr->u.ppid.id_len); break; - case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: attr->u.brport_flags = rocker_port->brport_flags; break; default: @@ -4369,12 +4369,12 @@ static int rocker_port_attr_set(struct net_device *dev, int err = 0; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_STP_STATE: + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: err = rocker_port_stp_update(rocker_port, trans, ROCKER_OP_FLAG_NOWAIT, attr->u.stp_state); break; - case SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS: + case SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS: err = rocker_port_brport_flags_set(rocker_port, trans, attr->u.brport_flags); break; diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 11f9c706cf5c..612719b9618a 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -39,10 +39,10 @@ static inline bool switchdev_trans_ph_commit(struct switchdev_trans *trans) } enum switchdev_attr_id { - SWITCHDEV_ATTR_UNDEFINED, - SWITCHDEV_ATTR_PORT_PARENT_ID, - SWITCHDEV_ATTR_PORT_STP_STATE, - SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + SWITCHDEV_ATTR_ID_UNDEFINED, + SWITCHDEV_ATTR_ID_PORT_PARENT_ID, + SWITCHDEV_ATTR_ID_PORT_STP_STATE, + SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; struct switchdev_attr { diff --git a/net/bridge/br_stp.c b/net/bridge/br_stp.c index 3a7392e6010e..3a982c02599a 100644 --- a/net/bridge/br_stp.c +++ b/net/bridge/br_stp.c @@ -40,7 +40,7 @@ void br_log_state(const struct net_bridge_port *p) void br_set_state(struct net_bridge_port *p, unsigned int state) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_STP_STATE, + .id = SWITCHDEV_ATTR_ID_PORT_STP_STATE, .u.stp_state = state, }; int err; diff --git a/net/core/net-sysfs.c b/net/core/net-sysfs.c index 410c6e42bf1f..f88a62ab019d 100644 --- a/net/core/net-sysfs.c +++ b/net/core/net-sysfs.c @@ -471,7 +471,7 @@ static ssize_t phys_switch_id_show(struct device *dev, if (dev_isalive(netdev)) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 474a6da3b51a..b2258a36d894 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -1025,7 +1025,7 @@ static int rtnl_phys_switch_id_fill(struct sk_buff *skb, struct net_device *dev) { int err; struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; diff --git a/net/dsa/slave.c b/net/dsa/slave.c index a7060298b856..8992568f5c0e 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -458,7 +458,7 @@ static int dsa_slave_port_attr_set(struct net_device *dev, int ret; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_STP_STATE: + case SWITCHDEV_ATTR_ID_PORT_STP_STATE: if (switchdev_trans_ph_prepare(trans)) ret = ds->drv->port_stp_update ? 0 : -EOPNOTSUPP; else @@ -584,7 +584,7 @@ static int dsa_slave_port_attr_get(struct net_device *dev, struct dsa_switch *ds = p->parent; switch (attr->id) { - case SWITCHDEV_ATTR_PORT_PARENT_ID: + case SWITCHDEV_ATTR_ID_PORT_PARENT_ID: attr->u.ppid.id_len = sizeof(ds->index); memcpy(&attr->u.ppid.id, &ds->index, attr->u.ppid.id_len); break; diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 5b1aa9f6f261..c457c1f73d35 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -104,7 +104,7 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) struct net_device *lower_dev; struct list_head *iter; struct switchdev_attr first = { - .id = SWITCHDEV_ATTR_UNDEFINED + .id = SWITCHDEV_ATTR_ID_UNDEFINED }; int err = -EOPNOTSUPP; @@ -124,7 +124,7 @@ int switchdev_port_attr_get(struct net_device *dev, struct switchdev_attr *attr) err = switchdev_port_attr_get(lower_dev, attr); if (err) break; - if (first.id == SWITCHDEV_ATTR_UNDEFINED) + if (first.id == SWITCHDEV_ATTR_ID_UNDEFINED) first = *attr; else if (memcmp(&first, attr, sizeof(*attr))) return -ENODATA; @@ -611,7 +611,7 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, int nlflags) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; u16 mode = BRIDGE_MODE_UNDEF; u32 mask = BR_LEARNING | BR_LEARNING_SYNC; @@ -632,7 +632,7 @@ static int switchdev_port_br_setflag(struct net_device *dev, unsigned long brport_flag) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_BRIDGE_FLAGS, + .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; u8 flag = nla_get_u8(nlattr); int err; @@ -958,7 +958,7 @@ static struct net_device *switchdev_get_lowest_dev(struct net_device *dev) static struct net_device *switchdev_get_dev_by_nhs(struct fib_info *fi) { struct switchdev_attr attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, }; struct switchdev_attr prev_attr; struct net_device *dev = NULL; @@ -1107,11 +1107,11 @@ static bool switchdev_port_same_parent_id(struct net_device *a, struct net_device *b) { struct switchdev_attr a_attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; struct switchdev_attr b_attr = { - .id = SWITCHDEV_ATTR_PORT_PARENT_ID, + .id = SWITCHDEV_ATTR_ID_PORT_PARENT_ID, .flags = SWITCHDEV_F_NO_RECURSE, }; -- cgit v1.2.3 From 619f3bd2e1f24dd6221e563e051c798844b83a93 Mon Sep 17 00:00:00 2001 From: Kazuya Mizuguchi Date: Wed, 30 Sep 2015 15:15:54 +0900 Subject: ravb: Document binding for r8a7795 SoC This patch updates the ravb binding to support the r8a7795 SoC by: - Adding a compat string for the new hardware - Adding 25 named interrupts to binding for the new SoC; older SoCs continue to use a single multiplexed interrupt The example is also updated to reflect the r8a7795 as this is the more complex case. Based on work by Kazuya Mizuguchi and others. Signed-off-by: Simon Horman Acked-by: Geert Uytterhoeven Signed-off-by: David S. Miller --- .../devicetree/bindings/net/renesas,ravb.txt | 69 +++++++++++++++++++--- 1 file changed, 62 insertions(+), 7 deletions(-) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/renesas,ravb.txt b/Documentation/devicetree/bindings/net/renesas,ravb.txt index 1fd8831437bf..b486f3f5f6a3 100644 --- a/Documentation/devicetree/bindings/net/renesas,ravb.txt +++ b/Documentation/devicetree/bindings/net/renesas,ravb.txt @@ -6,8 +6,12 @@ interface contains. Required properties: - compatible: "renesas,etheravb-r8a7790" if the device is a part of R8A7790 SoC. "renesas,etheravb-r8a7794" if the device is a part of R8A7794 SoC. + "renesas,etheravb-r8a7795" if the device is a part of R8A7795 SoC. - reg: offset and length of (1) the register block and (2) the stream buffer. -- interrupts: interrupt specifier for the sole interrupt. +- interrupts: A list of interrupt-specifiers, one for each entry in + interrupt-names. + If interrupt-names is not present, an interrupt specifier + for a single muxed interrupt. - phy-mode: see ethernet.txt file in the same directory. - phy-handle: see ethernet.txt file in the same directory. - #address-cells: number of address cells for the MDIO bus, must be equal to 1. @@ -18,6 +22,12 @@ Required properties: Optional properties: - interrupt-parent: the phandle for the interrupt controller that services interrupts for this device. +- interrupt-names: A list of interrupt names. + For the R8A7795 SoC this property is mandatory; + it should include one entry per channel, named "ch%u", + where %u is the channel number ranging from 0 to 24. + For other SoCs this property is optional; if present + it should contain "mux" for a single muxed interrupt. - pinctrl-names: pin configuration state name ("default"). - renesas,no-ether-link: boolean, specify when a board does not provide a proper AVB_LINK signal. @@ -27,13 +37,46 @@ Optional properties: Example: ethernet@e6800000 { - compatible = "renesas,etheravb-r8a7790"; - reg = <0 0xe6800000 0 0x800>, <0 0xee0e8000 0 0x4000>; + compatible = "renesas,etheravb-r8a7795"; + reg = <0 0xe6800000 0 0x800>, <0 0xe6a00000 0 0x10000>; interrupt-parent = <&gic>; - interrupts = <0 163 IRQ_TYPE_LEVEL_HIGH>; - clocks = <&mstp8_clks R8A7790_CLK_ETHERAVB>; - phy-mode = "rmii"; + interrupts = , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + , + ; + interrupt-names = "ch0", "ch1", "ch2", "ch3", + "ch4", "ch5", "ch6", "ch7", + "ch8", "ch9", "ch10", "ch11", + "ch12", "ch13", "ch14", "ch15", + "ch16", "ch17", "ch18", "ch19", + "ch20", "ch21", "ch22", "ch23", + "ch24"; + clocks = <&mstp8_clks R8A7795_CLK_ETHERAVB>; + power-domains = <&cpg_clocks>; + phy-mode = "rgmii-id"; phy-handle = <&phy0>; + pinctrl-0 = <ðer_pins>; pinctrl-names = "default"; renesas,no-ether-link; @@ -41,8 +84,20 @@ Example: #size-cells = <0>; phy0: ethernet-phy@0 { + rxc-skew-ps = <900>; + rxdv-skew-ps = <0>; + rxd0-skew-ps = <0>; + rxd1-skew-ps = <0>; + rxd2-skew-ps = <0>; + rxd3-skew-ps = <0>; + txc-skew-ps = <900>; + txen-skew-ps = <0>; + txd0-skew-ps = <0>; + txd1-skew-ps = <0>; + txd2-skew-ps = <0>; + txd3-skew-ps = <0>; reg = <0>; interrupt-parent = <&gpio2>; - interrupts = <15 IRQ_TYPE_LEVEL_LOW>; + interrupts = <11 IRQ_TYPE_LEVEL_LOW>; }; }; -- cgit v1.2.3 From 66cebb86ac77c6dff0751efa382551cab24075cd Mon Sep 17 00:00:00 2001 From: Claudiu Manoil Date: Mon, 5 Oct 2015 17:19:57 +0300 Subject: doc: dt: net: Add fsl,wake-on-filer for eTSEC Add the "fsl,wake-on-filer" property for eTSEC nodes to indicate that the system has the power management infrastructure needed to be able to wake up the system via FGPI (filer, aka. h/w rx parser) interrupt. Cc: Li Yang Cc: Zhao Chenhui Signed-off-by: Claudiu Manoil Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/fsl-tsec-phy.txt | 4 ++++ 1 file changed, 4 insertions(+) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt index 1e97532a0b79..db74f0dc290c 100644 --- a/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt +++ b/Documentation/devicetree/bindings/net/fsl-tsec-phy.txt @@ -57,6 +57,10 @@ Properties: "rgmii-id", as all other connection types are detected by hardware. - fsl,magic-packet : If present, indicates that the hardware supports waking up via magic packet. + - fsl,wake-on-filer : If present, indicates that the hardware supports + waking up by Filer General Purpose Interrupt (FGPI) asserted on the + Rx int line. This is an advanced power management capability allowing + certain packet types (user) defined by filer rules to wake up the system. - bd-stash : If present, indicates that the hardware supports stashing buffer descriptors in the L2. - rx-stash-len : Denotes the number of bytes of a received buffer to stash -- cgit v1.2.3 From bb257c3813613ce11329568c21c200e95afe6fc1 Mon Sep 17 00:00:00 2001 From: Arun Parameswaran Date: Tue, 6 Oct 2015 12:25:46 -0700 Subject: dt-bindings: net: Broadcom iProc MDIO bus driver device tree binding Add device tree binding documentation for the Broadcom iProc MDIO bus driver. Signed-off-by: Arun Parameswaran Signed-off-by: David S. Miller --- .../devicetree/bindings/net/brcm,iproc-mdio.txt | 23 ++++++++++++++++++++++ 1 file changed, 23 insertions(+) create mode 100644 Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt new file mode 100644 index 000000000000..8ba9ed11d716 --- /dev/null +++ b/Documentation/devicetree/bindings/net/brcm,iproc-mdio.txt @@ -0,0 +1,23 @@ +* Broadcom iProc MDIO bus controller + +Required properties: +- compatible: should be "brcm,iproc-mdio" +- reg: address and length of the register set for the MDIO interface +- #size-cells: must be 1 +- #address-cells: must be 0 + +Child nodes of this MDIO bus controller node are standard Ethernet PHY device +nodes as described in Documentation/devicetree/bindings/net/phy.txt + +Example: + +mdio@18002000 { + compatible = "brcm,iproc-mdio"; + reg = <0x18002000 0x8>; + #size-cells = <1>; + #address-cells = <0>; + + enet-gphy@0 { + reg = <0>; + }; +}; -- cgit v1.2.3 From e2ca690b657f4ca5c204fcc6470d462b776d73b3 Mon Sep 17 00:00:00 2001 From: Paolo Abeni Date: Fri, 9 Oct 2015 14:34:31 +0200 Subject: ipv4/icmp: redirect messages can use the ingress daddr as source This patch allows configuring how the source address of ICMP redirect messages is selected; by default the old behaviour is retained, while setting icmp_redirects_use_orig_daddr force the usage of the destination address of the packet that caused the redirect. The new behaviour fits closely the RFC 5798 section 8.1.1, and fix the following scenario: Two machines are set up with VRRP to act as routers out of a subnet, they have IPs x.x.x.1/24 and x.x.x.2/24, with VRRP holding on to x.x.x.254/24. If a host in said subnet needs to get an ICMP redirect from the VRRP router, i.e. to reach a destination behind a different gateway, the source IP in the ICMP redirect is chosen as the primary IP on the interface that the packet arrived at, i.e. x.x.x.1 or x.x.x.2. The host will then ignore said redirect, due to RFC 1122 section 3.2.2.2, and will continue to use the wrong next-op. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 19 +++++++++++++++++-- include/net/netns/ipv4.h | 1 + net/ipv4/icmp.c | 9 ++++++++- net/ipv4/sysctl_net_ipv4.c | 7 +++++++ 4 files changed, 33 insertions(+), 3 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ebe94f2cab98..99838259e2e6 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -884,8 +884,8 @@ icmp_ignore_bogus_error_responses - BOOLEAN icmp_errors_use_inbound_ifaddr - BOOLEAN - If zero, icmp error messages are sent with the primary address of - the exiting interface. + If zero, icmp error messages except redirects are sent with the primary + address of the exiting interface. If non-zero, the message will be sent with the primary address of the interface that received the packet that caused the icmp error. @@ -897,8 +897,23 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN then the primary address of the first non-loopback interface that has one will be used regardless of this setting. + The source address selection of icmp redirect messages is controlled by + icmp_errors_use_inbound_ifaddr. Default: 0 +icmp_redirects_use_orig_daddr - BOOLEAN + + If zero, icmp redirect messages are sent using the address specified for + other icmp errors by icmp_errors_use_inbound_ifaddr. + + If non-zero, the message will be sent with the destination address of + the packet that caused the icmp redirect. + This behaviour is the preferred one on VRRP routers (see RFC 5798 + section 8.1.1). + + Default: 0 + + igmp_max_memberships - INTEGER Change the maximum number of multicast groups we can subscribe to. Default: 20 diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index c68926b4899c..46d336abca92 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -74,6 +74,7 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; + int sysctl_icmp_redirects_use_orig_daddr; struct local_ports ip_local_ports; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index 36e26977c908..f3c356b7c1f0 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -659,7 +659,9 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) */ saddr = iph->daddr; - if (!(rt->rt_flags & RTCF_LOCAL)) { + if (!((type == ICMP_REDIRECT) && + net->ipv4.sysctl_icmp_redirects_use_orig_daddr) && + !(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; rcu_read_lock(); @@ -1222,6 +1224,11 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; + /* Control paramerer - use the daddr of originating packets as saddr + * in redirect messages? + */ + net->ipv4.sysctl_icmp_redirects_use_orig_daddr = 0; + return 0; fail: diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 894da3a70aff..30a531ccbf77 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -817,6 +817,13 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "icmp_redirects_use_orig_daddr", + .data = &init_net.ipv4.sysctl_icmp_redirects_use_orig_daddr, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, -- cgit v1.2.3 From 6e19bc4b7091ffd26586100eee78232b44427ec7 Mon Sep 17 00:00:00 2001 From: Dmitry Shmidt Date: Wed, 7 Oct 2015 11:32:53 +0200 Subject: nl80211: allow BSS data to include CLOCK_BOOTTIME timestamp For location and connectivity services, userspace would often like to know the time when the BSS was last seen. The current "last seen" value is calculated in a way that makes it less useful, especially if the system suspended in the meantime. Add the ability for the driver to report a real CLOCK_BOOTTIME stamp that can then be reported to userspace (if present). Drivers wishing to use this must be converted to the new API to call cfg80211_inform_bss_data() or cfg80211_inform_bss_frame_data(). They need to ensure the reported value is accurate enough even when the frame might have been buffered in the device (e.g. firmware.) Signed-off-by: Dmitry Shmidt [modified to use struct, inlines] Signed-off-by: Johannes Berg --- Documentation/DocBook/80211.tmpl | 5 ++- include/net/cfg80211.h | 95 ++++++++++++++++++++++++++++++++-------- include/uapi/linux/nl80211.h | 4 ++ net/wireless/core.h | 1 + net/wireless/nl80211.c | 5 +++ net/wireless/scan.c | 58 ++++++++++++------------ net/wireless/trace.h | 22 +++++----- 7 files changed, 130 insertions(+), 60 deletions(-) (limited to 'Documentation') diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index aac9357d4866..f9b9ad7894f5 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -154,8 +154,9 @@ !Finclude/net/cfg80211.h cfg80211_scan_request !Finclude/net/cfg80211.h cfg80211_scan_done !Finclude/net/cfg80211.h cfg80211_bss -!Finclude/net/cfg80211.h cfg80211_inform_bss_width_frame -!Finclude/net/cfg80211.h cfg80211_inform_bss_width +!Finclude/net/cfg80211.h cfg80211_inform_bss +!Finclude/net/cfg80211.h cfg80211_inform_bss_frame_data +!Finclude/net/cfg80211.h cfg80211_inform_bss_data !Finclude/net/cfg80211.h cfg80211_unlink_bss !Finclude/net/cfg80211.h cfg80211_find_ie !Finclude/net/cfg80211.h ieee80211_bss_get_ie diff --git a/include/net/cfg80211.h b/include/net/cfg80211.h index 90332a1838cc..7f1e9ee844e2 100644 --- a/include/net/cfg80211.h +++ b/include/net/cfg80211.h @@ -1575,6 +1575,26 @@ enum cfg80211_signal_type { CFG80211_SIGNAL_TYPE_UNSPEC, }; +/** + * struct cfg80211_inform_bss - BSS inform data + * @chan: channel the frame was received on + * @scan_width: scan width that was used + * @signal: signal strength value, according to the wiphy's + * signal type + * @boottime_ns: timestamp (CLOCK_BOOTTIME) when the information was + * received; should match the time when the frame was actually + * received by the device (not just by the host, in case it was + * buffered on the device) and be accurate to about 10ms. + * If the frame isn't buffered, just passing the return value of + * ktime_get_boot_ns() is likely appropriate. + */ +struct cfg80211_inform_bss { + struct ieee80211_channel *chan; + enum nl80211_bss_scan_width scan_width; + s32 signal; + u64 boottime_ns; +}; + /** * struct cfg80211_bss_ie_data - BSS entry IE data * @tsf: TSF contained in the frame that carried these IEs @@ -3958,14 +3978,11 @@ void cfg80211_sched_scan_stopped(struct wiphy *wiphy); void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); /** - * cfg80211_inform_bss_width_frame - inform cfg80211 of a received BSS frame - * + * cfg80211_inform_bss_frame_data - inform cfg80211 of a received BSS frame * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @mgmt: the management frame (probe response or beacon) * @len: length of the management frame - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -3975,11 +3992,26 @@ void cfg80211_sched_scan_stopped_rtnl(struct wiphy *wiphy); * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width_frame(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_frame(struct wiphy *wiphy, @@ -3987,9 +4019,13 @@ cfg80211_inform_bss_frame(struct wiphy *wiphy, struct ieee80211_mgmt *mgmt, size_t len, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width_frame(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, - mgmt, len, signal, gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_frame_data(wiphy, &data, mgmt, len, gfp); } /** @@ -4006,11 +4042,10 @@ enum cfg80211_bss_frame_type { }; /** - * cfg80211_inform_bss_width - inform cfg80211 of a new BSS + * cfg80211_inform_bss_data - inform cfg80211 of a new BSS * * @wiphy: the wiphy reporting the BSS - * @rx_channel: The channel the frame was received on - * @scan_width: width of the control channel + * @data: the BSS metadata * @ftype: frame type (if known) * @bssid: the BSSID of the BSS * @tsf: the TSF sent by the peer in the beacon/probe response (or 0) @@ -4018,7 +4053,6 @@ enum cfg80211_bss_frame_type { * @beacon_interval: the beacon interval announced by the peer * @ie: additional IEs sent by the peer * @ielen: length of the additional IEs - * @signal: the signal strength, type depends on the wiphy's signal_type * @gfp: context flags * * This informs cfg80211 that BSS information was found and @@ -4028,13 +4062,32 @@ enum cfg80211_bss_frame_type { * Or %NULL on error. */ struct cfg80211_bss * __must_check +cfg80211_inform_bss_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + enum cfg80211_bss_frame_type ftype, + const u8 *bssid, u64 tsf, u16 capability, + u16 beacon_interval, const u8 *ie, size_t ielen, + gfp_t gfp); + +static inline struct cfg80211_bss * __must_check cfg80211_inform_bss_width(struct wiphy *wiphy, struct ieee80211_channel *rx_channel, enum nl80211_bss_scan_width scan_width, enum cfg80211_bss_frame_type ftype, const u8 *bssid, u64 tsf, u16 capability, u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp); + s32 signal, gfp_t gfp) +{ + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = scan_width, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); +} static inline struct cfg80211_bss * __must_check cfg80211_inform_bss(struct wiphy *wiphy, @@ -4044,11 +4097,15 @@ cfg80211_inform_bss(struct wiphy *wiphy, u16 beacon_interval, const u8 *ie, size_t ielen, s32 signal, gfp_t gfp) { - return cfg80211_inform_bss_width(wiphy, rx_channel, - NL80211_BSS_CHAN_WIDTH_20, ftype, - bssid, tsf, capability, - beacon_interval, ie, ielen, signal, - gfp); + struct cfg80211_inform_bss data = { + .chan = rx_channel, + .scan_width = NL80211_BSS_CHAN_WIDTH_20, + .signal = signal, + }; + + return cfg80211_inform_bss_data(wiphy, &data, ftype, bssid, tsf, + capability, beacon_interval, ie, ielen, + gfp); } struct cfg80211_bss *cfg80211_get_bss(struct wiphy *wiphy, diff --git a/include/uapi/linux/nl80211.h b/include/uapi/linux/nl80211.h index c0ab6b0a3919..5dadb844fe18 100644 --- a/include/uapi/linux/nl80211.h +++ b/include/uapi/linux/nl80211.h @@ -3364,6 +3364,9 @@ enum nl80211_bss_scan_width { * (not present if no beacon frame has been received yet) * @NL80211_BSS_PRESP_DATA: the data in @NL80211_BSS_INFORMATION_ELEMENTS and * @NL80211_BSS_TSF is known to be from a probe response (flag attribute) + * @NL80211_BSS_LAST_SEEN_BOOTTIME: CLOCK_BOOTTIME timestamp when this entry + * was last updated by a received frame. The value is expected to be + * accurate to about 10ms. (u64, nanoseconds) * @__NL80211_BSS_AFTER_LAST: internal * @NL80211_BSS_MAX: highest BSS attribute */ @@ -3383,6 +3386,7 @@ enum nl80211_bss { NL80211_BSS_CHAN_WIDTH, NL80211_BSS_BEACON_TSF, NL80211_BSS_PRESP_DATA, + NL80211_BSS_LAST_SEEN_BOOTTIME, /* keep last */ __NL80211_BSS_AFTER_LAST, diff --git a/net/wireless/core.h b/net/wireless/core.h index b9d5bc8c148d..a618b4b86fa4 100644 --- a/net/wireless/core.h +++ b/net/wireless/core.h @@ -137,6 +137,7 @@ struct cfg80211_internal_bss { struct list_head list; struct list_head hidden_list; struct rb_node rbn; + u64 ts_boottime; unsigned long ts; unsigned long refcount; atomic_t hold; diff --git a/net/wireless/nl80211.c b/net/wireless/nl80211.c index f05ba8b7af61..fb0712b3d9cb 100644 --- a/net/wireless/nl80211.c +++ b/net/wireless/nl80211.c @@ -6605,6 +6605,11 @@ static int nl80211_send_bss(struct sk_buff *msg, struct netlink_callback *cb, jiffies_to_msecs(jiffies - intbss->ts))) goto nla_put_failure; + if (intbss->ts_boottime && + nla_put_u64(msg, NL80211_BSS_LAST_SEEN_BOOTTIME, + intbss->ts_boottime)) + goto nla_put_failure; + switch (rdev->wiphy.signal_type) { case CFG80211_SIGNAL_TYPE_MBM: if (nla_put_u32(msg, NL80211_BSS_SIGNAL_MBM, res->signal)) diff --git a/net/wireless/scan.c b/net/wireless/scan.c index 3a50aa2553bf..3feaa03aa046 100644 --- a/net/wireless/scan.c +++ b/net/wireless/scan.c @@ -839,6 +839,7 @@ cfg80211_bss_update(struct cfg80211_registered_device *rdev, found->pub.signal = tmp->pub.signal; found->pub.capability = tmp->pub.capability; found->ts = tmp->ts; + found->ts_boottime = tmp->ts_boottime; } else { struct cfg80211_internal_bss *new; struct cfg80211_internal_bss *hidden; @@ -938,14 +939,13 @@ cfg80211_get_bss_channel(struct wiphy *wiphy, const u8 *ie, size_t ielen, } /* Returned bss is reference counted and must be cleaned up appropriately. */ -struct cfg80211_bss* -cfg80211_inform_bss_width(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - enum cfg80211_bss_frame_type ftype, - const u8 *bssid, u64 tsf, u16 capability, - u16 beacon_interval, const u8 *ie, size_t ielen, - s32 signal, gfp_t gfp) +struct cfg80211_bss * +cfg80211_inform_bss_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + enum cfg80211_bss_frame_type ftype, + const u8 *bssid, u64 tsf, u16 capability, + u16 beacon_interval, const u8 *ie, size_t ielen, + gfp_t gfp) { struct cfg80211_bss_ies *ies; struct ieee80211_channel *channel; @@ -957,19 +957,21 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, return NULL; if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && - (signal < 0 || signal > 100))) + (data->signal < 0 || data->signal > 100))) return NULL; - channel = cfg80211_get_bss_channel(wiphy, ie, ielen, rx_channel); + channel = cfg80211_get_bss_channel(wiphy, ie, ielen, data->chan); if (!channel) return NULL; memcpy(tmp.pub.bssid, bssid, ETH_ALEN); tmp.pub.channel = channel; - tmp.pub.scan_width = scan_width; - tmp.pub.signal = signal; + tmp.pub.scan_width = data->scan_width; + tmp.pub.signal = data->signal; tmp.pub.beacon_interval = beacon_interval; tmp.pub.capability = capability; + tmp.ts_boottime = data->boottime_ns; + /* * If we do not know here whether the IEs are from a Beacon or Probe * Response frame, we need to pick one of the options and only use it @@ -999,7 +1001,7 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, } rcu_assign_pointer(tmp.pub.ies, ies); - signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) @@ -1019,15 +1021,15 @@ cfg80211_inform_bss_width(struct wiphy *wiphy, /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } -EXPORT_SYMBOL(cfg80211_inform_bss_width); +EXPORT_SYMBOL(cfg80211_inform_bss_data); -/* Returned bss is reference counted and must be cleaned up appropriately. */ +/* cfg80211_inform_bss_width_frame helper */ struct cfg80211_bss * -cfg80211_inform_bss_width_frame(struct wiphy *wiphy, - struct ieee80211_channel *rx_channel, - enum nl80211_bss_scan_width scan_width, - struct ieee80211_mgmt *mgmt, size_t len, - s32 signal, gfp_t gfp) +cfg80211_inform_bss_frame_data(struct wiphy *wiphy, + struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len, + gfp_t gfp) + { struct cfg80211_internal_bss tmp = {}, *res; struct cfg80211_bss_ies *ies; @@ -1040,8 +1042,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, BUILD_BUG_ON(offsetof(struct ieee80211_mgmt, u.probe_resp.variable) != offsetof(struct ieee80211_mgmt, u.beacon.variable)); - trace_cfg80211_inform_bss_width_frame(wiphy, rx_channel, scan_width, mgmt, - len, signal); + trace_cfg80211_inform_bss_frame(wiphy, data, mgmt, len); if (WARN_ON(!mgmt)) return NULL; @@ -1050,14 +1051,14 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, return NULL; if (WARN_ON(wiphy->signal_type == CFG80211_SIGNAL_TYPE_UNSPEC && - (signal < 0 || signal > 100))) + (data->signal < 0 || data->signal > 100))) return NULL; if (WARN_ON(len < offsetof(struct ieee80211_mgmt, u.probe_resp.variable))) return NULL; channel = cfg80211_get_bss_channel(wiphy, mgmt->u.beacon.variable, - ielen, rx_channel); + ielen, data->chan); if (!channel) return NULL; @@ -1077,12 +1078,13 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, memcpy(tmp.pub.bssid, mgmt->bssid, ETH_ALEN); tmp.pub.channel = channel; - tmp.pub.scan_width = scan_width; - tmp.pub.signal = signal; + tmp.pub.scan_width = data->scan_width; + tmp.pub.signal = data->signal; tmp.pub.beacon_interval = le16_to_cpu(mgmt->u.probe_resp.beacon_int); tmp.pub.capability = le16_to_cpu(mgmt->u.probe_resp.capab_info); + tmp.ts_boottime = data->boottime_ns; - signal_valid = abs(rx_channel->center_freq - channel->center_freq) <= + signal_valid = abs(data->chan->center_freq - channel->center_freq) <= wiphy->max_adj_channel_rssi_comp; res = cfg80211_bss_update(wiphy_to_rdev(wiphy), &tmp, signal_valid); if (!res) @@ -1102,7 +1104,7 @@ cfg80211_inform_bss_width_frame(struct wiphy *wiphy, /* cfg80211_bss_update gives us a referenced result */ return &res->pub; } -EXPORT_SYMBOL(cfg80211_inform_bss_width_frame); +EXPORT_SYMBOL(cfg80211_inform_bss_frame_data); void cfg80211_ref_bss(struct wiphy *wiphy, struct cfg80211_bss *pub) { diff --git a/net/wireless/trace.h b/net/wireless/trace.h index a808279a432a..0c392d36781b 100644 --- a/net/wireless/trace.h +++ b/net/wireless/trace.h @@ -2670,30 +2670,30 @@ TRACE_EVENT(cfg80211_get_bss, __entry->privacy) ); -TRACE_EVENT(cfg80211_inform_bss_width_frame, - TP_PROTO(struct wiphy *wiphy, struct ieee80211_channel *channel, - enum nl80211_bss_scan_width scan_width, - struct ieee80211_mgmt *mgmt, size_t len, - s32 signal), - TP_ARGS(wiphy, channel, scan_width, mgmt, len, signal), +TRACE_EVENT(cfg80211_inform_bss_frame, + TP_PROTO(struct wiphy *wiphy, struct cfg80211_inform_bss *data, + struct ieee80211_mgmt *mgmt, size_t len), + TP_ARGS(wiphy, data, mgmt, len), TP_STRUCT__entry( WIPHY_ENTRY CHAN_ENTRY __field(enum nl80211_bss_scan_width, scan_width) __dynamic_array(u8, mgmt, len) __field(s32, signal) + __field(u64, ts_boottime) ), TP_fast_assign( WIPHY_ASSIGN; - CHAN_ASSIGN(channel); - __entry->scan_width = scan_width; + CHAN_ASSIGN(data->chan); + __entry->scan_width = data->scan_width; if (mgmt) memcpy(__get_dynamic_array(mgmt), mgmt, len); - __entry->signal = signal; + __entry->signal = data->signal; + __entry->ts_boottime = data->boottime_ns; ), - TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT "(scan_width: %d) signal: %d", + TP_printk(WIPHY_PR_FMT ", " CHAN_PR_FMT "(scan_width: %d) signal: %d, tsb:%llu", WIPHY_PR_ARG, CHAN_PR_ARG, __entry->scan_width, - __entry->signal) + __entry->signal, (unsigned long long)__entry->ts_boottime) ); DECLARE_EVENT_CLASS(cfg80211_bss_evt, -- cgit v1.2.3 From 4b418bff3dae0c017126220df3e148ba8127e99a Mon Sep 17 00:00:00 2001 From: David Ahern Date: Mon, 12 Oct 2015 13:54:38 -0700 Subject: net: vrf: Documentation update, ip commands Add ip commands with examples for creating VRF devics, enslaving interfaces and dumping VRF-focused data (address, neighbors, routes). Signed-off-by: David Ahern Signed-off-by: David S. Miller --- Documentation/networking/vrf.txt | 301 ++++++++++++++++++++++++++++++++++++++- 1 file changed, 299 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/vrf.txt b/Documentation/networking/vrf.txt index 031ef4a63485..d52aa10cfe91 100644 --- a/Documentation/networking/vrf.txt +++ b/Documentation/networking/vrf.txt @@ -90,7 +90,304 @@ or to specify the output device using cmsg and IP_PKTINFO. Limitations ----------- -VRF device currently only works for IPv4. Support for IPv6 is under development. - Index of original ingress interface is not available via cmsg. Will address soon. + +################################################################################ + +Using iproute2 for VRFs +======================= +VRF devices do *not* have to start with 'vrf-'. That is a convention used here +for emphasis of the device type, similar to use of 'br' in bridge names. + +1. Create a VRF + + To instantiate a VRF device and associate it with a table: + $ ip link add dev NAME type vrf table ID + + Remember to add the ip rules as well: + $ ip ru add oif NAME table 10 + $ ip ru add iif NAME table 10 + $ ip -6 ru add oif NAME table 10 + $ ip -6 ru add iif NAME table 10 + + Without the rules route lookups are not directed to the table. + + For example: + $ ip link add dev vrf-blue type vrf table 10 + $ ip ru add pref 200 oif vrf-blue table 10 + $ ip ru add pref 200 iif vrf-blue table 10 + $ ip -6 ru add pref 200 oif vrf-blue table 10 + $ ip -6 ru add pref 200 iif vrf-blue table 10 + + +2. List VRFs + + To list VRFs that have been created: + $ ip [-d] link show type vrf + NOTE: The -d option is needed to show the table id + + For example: + $ ip -d link show type vrf + 11: vrf-mgmt: mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether 72:b3:ba:91:e2:24 brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 1 addrgenmode eui64 + 12: vrf-red: mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether b6:6f:6e:f6:da:73 brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 10 addrgenmode eui64 + 13: vrf-blue: mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether 36:62:e8:7d:bb:8c brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 66 addrgenmode eui64 + 14: vrf-green: mtu 1500 qdisc pfifo_fast state UP mode DEFAULT group default qlen 1000 + link/ether e6:28:b8:63:70:bb brd ff:ff:ff:ff:ff:ff promiscuity 0 + vrf table 81 addrgenmode eui64 + + + Or in brief output: + + $ ip -br link show type vrf + vrf-mgmt UP 72:b3:ba:91:e2:24 + vrf-red UP b6:6f:6e:f6:da:73 + vrf-blue UP 36:62:e8:7d:bb:8c + vrf-green UP e6:28:b8:63:70:bb + + +3. Assign a Network Interface to a VRF + + Network interfaces are assigned to a VRF by enslaving the netdevice to a + VRF device: + $ ip link set dev NAME master VRF-NAME + + On enslavement connected and local routes are automatically moved to the + table associated with the VRF device. + + For example: + $ ip link set dev eth0 master vrf-mgmt + + +4. Show Devices Assigned to a VRF + + To show devices that have been assigned to a specific VRF add the master + option to the ip command: + $ ip link show master VRF-NAME + + For example: + $ ip link show master vrf-red + 3: eth1: mtu 1500 qdisc pfifo_fast master vrf-red state UP mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:02 brd ff:ff:ff:ff:ff:ff + 4: eth2: mtu 1500 qdisc pfifo_fast master vrf-red state UP mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:03 brd ff:ff:ff:ff:ff:ff + 7: eth5: mtu 1500 qdisc noop master vrf-red state DOWN mode DEFAULT group default qlen 1000 + link/ether 02:00:00:00:02:06 brd ff:ff:ff:ff:ff:ff + + + Or using the brief output: + $ ip -br link show master vrf-red + eth1 UP 02:00:00:00:02:02 + eth2 UP 02:00:00:00:02:03 + eth5 DOWN 02:00:00:00:02:06 + + +5. Show Neighbor Entries for a VRF + + To list neighbor entries associated with devices enslaved to a VRF device + add the master option to the ip command: + $ ip [-6] neigh show master VRF-NAME + + For example: + $ ip neigh show master vrf-red + 10.2.1.254 dev eth1 lladdr a6:d9:c7:4f:06:23 REACHABLE + 10.2.2.254 dev eth2 lladdr 5e:54:01:6a:ee:80 REACHABLE + + $ ip -6 neigh show master vrf-red + 2002:1::64 dev eth1 lladdr a6:d9:c7:4f:06:23 REACHABLE + + +6. Show Addresses for a VRF + + To show addresses for interfaces associated with a VRF add the master + option to the ip command: + $ ip addr show master VRF-NAME + + For example: + $ ip addr show master vrf-red + 3: eth1: mtu 1500 qdisc pfifo_fast master vrf-red state UP group default qlen 1000 + link/ether 02:00:00:00:02:02 brd ff:ff:ff:ff:ff:ff + inet 10.2.1.2/24 brd 10.2.1.255 scope global eth1 + valid_lft forever preferred_lft forever + inet6 2002:1::2/120 scope global + valid_lft forever preferred_lft forever + inet6 fe80::ff:fe00:202/64 scope link + valid_lft forever preferred_lft forever + 4: eth2: mtu 1500 qdisc pfifo_fast master vrf-red state UP group default qlen 1000 + link/ether 02:00:00:00:02:03 brd ff:ff:ff:ff:ff:ff + inet 10.2.2.2/24 brd 10.2.2.255 scope global eth2 + valid_lft forever preferred_lft forever + inet6 2002:2::2/120 scope global + valid_lft forever preferred_lft forever + inet6 fe80::ff:fe00:203/64 scope link + valid_lft forever preferred_lft forever + 7: eth5: mtu 1500 qdisc noop master vrf-red state DOWN group default qlen 1000 + link/ether 02:00:00:00:02:06 brd ff:ff:ff:ff:ff:ff + + Or in brief format: + $ ip -br addr show master vrf-red + eth1 UP 10.2.1.2/24 2002:1::2/120 fe80::ff:fe00:202/64 + eth2 UP 10.2.2.2/24 2002:2::2/120 fe80::ff:fe00:203/64 + eth5 DOWN + + +7. Show Routes for a VRF + + To show routes for a VRF use the ip command to display the table associated + with the VRF device: + $ ip [-6] route show table ID + + For example: + $ ip route show table vrf-red + prohibit default + broadcast 10.2.1.0 dev eth1 proto kernel scope link src 10.2.1.2 + 10.2.1.0/24 dev eth1 proto kernel scope link src 10.2.1.2 + local 10.2.1.2 dev eth1 proto kernel scope host src 10.2.1.2 + broadcast 10.2.1.255 dev eth1 proto kernel scope link src 10.2.1.2 + broadcast 10.2.2.0 dev eth2 proto kernel scope link src 10.2.2.2 + 10.2.2.0/24 dev eth2 proto kernel scope link src 10.2.2.2 + local 10.2.2.2 dev eth2 proto kernel scope host src 10.2.2.2 + broadcast 10.2.2.255 dev eth2 proto kernel scope link src 10.2.2.2 + + $ ip -6 route show table vrf-red + local 2002:1:: dev lo proto none metric 0 pref medium + local 2002:1::2 dev lo proto none metric 0 pref medium + 2002:1::/120 dev eth1 proto kernel metric 256 pref medium + local 2002:2:: dev lo proto none metric 0 pref medium + local 2002:2::2 dev lo proto none metric 0 pref medium + 2002:2::/120 dev eth2 proto kernel metric 256 pref medium + local fe80:: dev lo proto none metric 0 pref medium + local fe80:: dev lo proto none metric 0 pref medium + local fe80::ff:fe00:202 dev lo proto none metric 0 pref medium + local fe80::ff:fe00:203 dev lo proto none metric 0 pref medium + fe80::/64 dev eth1 proto kernel metric 256 pref medium + fe80::/64 dev eth2 proto kernel metric 256 pref medium + ff00::/8 dev vrf-red metric 256 pref medium + ff00::/8 dev eth1 metric 256 pref medium + ff00::/8 dev eth2 metric 256 pref medium + + +8. Route Lookup for a VRF + + A test route lookup can be done for a VRF by adding the oif option to ip: + $ ip [-6] route get oif VRF-NAME ADDRESS + + For example: + $ ip route get 10.2.1.40 oif vrf-red + 10.2.1.40 dev eth1 table vrf-red src 10.2.1.2 + cache + + $ ip -6 route get 2002:1::32 oif vrf-red + 2002:1::32 from :: dev eth1 table vrf-red proto kernel src 2002:1::2 metric 256 pref medium + + +9. Removing Network Interface from a VRF + + Network interfaces are removed from a VRF by breaking the enslavement to + the VRF device: + $ ip link set dev NAME nomaster + + Connected routes are moved back to the default table and local entries are + moved to the local table. + + For example: + $ ip link set dev eth0 nomaster + +-------------------------------------------------------------------------------- + +Commands used in this example: + +cat >> /etc/iproute2/rt_tables < Date: Wed, 14 Oct 2015 14:25:53 +0200 Subject: Revert "ipv4/icmp: redirect messages can use the ingress daddr as source" Revert the commit e2ca690b657f ("ipv4/icmp: redirect messages can use the ingress daddr as source"), which tried to introduce a more suitable behaviour for ICMP redirect messages generated by VRRP routers. However RFC 5798 section 8.1.1 states: The IPv4 source address of an ICMP redirect should be the address that the end-host used when making its next-hop routing decision. while said commit used the generating packet destination address, which do not match the above and in most cases leads to no redirect packets to be generated. Signed-off-by: Paolo Abeni Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 19 ++----------------- include/net/netns/ipv4.h | 1 - net/ipv4/icmp.c | 9 +-------- net/ipv4/sysctl_net_ipv4.c | 7 ------- 4 files changed, 3 insertions(+), 33 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 99838259e2e6..ebe94f2cab98 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -884,8 +884,8 @@ icmp_ignore_bogus_error_responses - BOOLEAN icmp_errors_use_inbound_ifaddr - BOOLEAN - If zero, icmp error messages except redirects are sent with the primary - address of the exiting interface. + If zero, icmp error messages are sent with the primary address of + the exiting interface. If non-zero, the message will be sent with the primary address of the interface that received the packet that caused the icmp error. @@ -897,23 +897,8 @@ icmp_errors_use_inbound_ifaddr - BOOLEAN then the primary address of the first non-loopback interface that has one will be used regardless of this setting. - The source address selection of icmp redirect messages is controlled by - icmp_errors_use_inbound_ifaddr. Default: 0 -icmp_redirects_use_orig_daddr - BOOLEAN - - If zero, icmp redirect messages are sent using the address specified for - other icmp errors by icmp_errors_use_inbound_ifaddr. - - If non-zero, the message will be sent with the destination address of - the packet that caused the icmp redirect. - This behaviour is the preferred one on VRRP routers (see RFC 5798 - section 8.1.1). - - Default: 0 - - igmp_max_memberships - INTEGER Change the maximum number of multicast groups we can subscribe to. Default: 20 diff --git a/include/net/netns/ipv4.h b/include/net/netns/ipv4.h index 46d336abca92..c68926b4899c 100644 --- a/include/net/netns/ipv4.h +++ b/include/net/netns/ipv4.h @@ -74,7 +74,6 @@ struct netns_ipv4 { int sysctl_icmp_ratelimit; int sysctl_icmp_ratemask; int sysctl_icmp_errors_use_inbound_ifaddr; - int sysctl_icmp_redirects_use_orig_daddr; struct local_ports ip_local_ports; diff --git a/net/ipv4/icmp.c b/net/ipv4/icmp.c index f3c356b7c1f0..36e26977c908 100644 --- a/net/ipv4/icmp.c +++ b/net/ipv4/icmp.c @@ -659,9 +659,7 @@ void icmp_send(struct sk_buff *skb_in, int type, int code, __be32 info) */ saddr = iph->daddr; - if (!((type == ICMP_REDIRECT) && - net->ipv4.sysctl_icmp_redirects_use_orig_daddr) && - !(rt->rt_flags & RTCF_LOCAL)) { + if (!(rt->rt_flags & RTCF_LOCAL)) { struct net_device *dev = NULL; rcu_read_lock(); @@ -1224,11 +1222,6 @@ static int __net_init icmp_sk_init(struct net *net) net->ipv4.sysctl_icmp_ratemask = 0x1818; net->ipv4.sysctl_icmp_errors_use_inbound_ifaddr = 0; - /* Control paramerer - use the daddr of originating packets as saddr - * in redirect messages? - */ - net->ipv4.sysctl_icmp_redirects_use_orig_daddr = 0; - return 0; fail: diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 30a531ccbf77..894da3a70aff 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -817,13 +817,6 @@ static struct ctl_table ipv4_net_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, - { - .procname = "icmp_redirects_use_orig_daddr", - .data = &init_net.ipv4.sysctl_icmp_redirects_use_orig_daddr, - .maxlen = sizeof(int), - .mode = 0644, - .proc_handler = proc_dointvec - }, { .procname = "icmp_ratelimit", .data = &init_net.ipv4.sysctl_icmp_ratelimit, -- cgit v1.2.3 From 26fb342c734061859fec1bd9e987bb6b78061ef0 Mon Sep 17 00:00:00 2001 From: Li RongQing Date: Thu, 15 Oct 2015 16:54:36 +0800 Subject: ipconfig: send Client-identifier in DHCP requests A dhcp server may provide parameters to a client from a pool of IP addresses and using a shared rootfs, or provide a specific set of parameters for a specific client, usually using the MAC address to identify each client individually. The dhcp protocol also specifies a client-id field which can be used to determine the correct parameters to supply when no MAC address is available. There is currently no way to tell the kernel to supply a specific client-id, only the userspace dhcp clients support this feature, but this can not be used when the network is needed before userspace is available such as when the root filesystem is on NFS. This patch is to be able to do something like "ip=dhcp,client_id_type, client_id_value", as a kernel parameter to enable the kernel to identify itself to the server. Signed-off-by: Li RongQing Signed-off-by: David S. Miller --- Documentation/filesystems/nfs/nfsroot.txt | 3 +++ net/ipv4/ipconfig.c | 32 ++++++++++++++++++++++++++++++- 2 files changed, 34 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt index 2d66ed688125..bb5ab6de5924 100644 --- a/Documentation/filesystems/nfs/nfsroot.txt +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -157,6 +157,9 @@ ip=::::::: both: use both BOOTP and RARP but not DHCP (old option kept for backwards compatibility) + if dhcp is used, the client identifier can be used by following + format "ip=dhcp,client-id-type,client-id-value" + Default: any IP address of first nameserver. diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index ed4ef09c2136..0bc7412d9e14 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -146,6 +146,10 @@ u8 root_server_path[256] = { 0, }; /* Path to mount as root */ /* vendor class identifier */ static char vendor_class_identifier[253] __initdata; +#if defined(CONFIG_IP_PNP_DHCP) +static char dhcp_client_identifier[253] __initdata; +#endif + /* Persistent data: */ static int ic_proto_used; /* Protocol used, if any */ @@ -728,6 +732,16 @@ ic_dhcp_init_options(u8 *options) memcpy(e, vendor_class_identifier, len); e += len; } + len = strlen(dhcp_client_identifier + 1); + /* the minimum length of identifier is 2, include 1 byte type, + * and can not be larger than the length of options + */ + if (len >= 1 && len < 312 - (e - options) - 1) { + *e++ = 61; + *e++ = len + 1; + memcpy(e, dhcp_client_identifier, len + 1); + e += len + 1; + } } *e++ = 255; /* End of the list */ @@ -1557,8 +1571,24 @@ static int __init ic_proto_name(char *name) return 0; } #ifdef CONFIG_IP_PNP_DHCP - else if (!strcmp(name, "dhcp")) { + else if (!strncmp(name, "dhcp", 4)) { + char *client_id; + ic_proto_enabled &= ~IC_RARP; + client_id = strstr(name, "dhcp,"); + if (client_id) { + char *v; + + client_id = client_id + 5; + v = strchr(client_id, ','); + if (!v) + return 1; + *v = 0; + if (kstrtou8(client_id, 0, dhcp_client_identifier)) + DBG("DHCP: Invalid client identifier type\n"); + strncpy(dhcp_client_identifier + 1, v + 1, 251); + *v = ','; + } return 1; } #endif -- cgit v1.2.3 From f672258391b42a5c7cc2732c9c063e56a85c8dbe Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:42 -0700 Subject: tcp: track min RTT using windowed min-filter Kathleen Nichols' algorithm for tracking the minimum RTT of a data stream over some measurement window. It uses constant space and constant time per update. Yet it almost always delivers the same minimum as an implementation that has to keep all the data in the window. The measurement window is tunable via sysctl.net.ipv4.tcp_min_rtt_wlen with a default value of 5 minutes. The algorithm keeps track of the best, 2nd best & 3rd best min values, maintaining an invariant that the measurement time of the n'th best >= n-1'th best. It also makes sure that the three values are widely separated in the time window since that bounds the worse case error when that data is monotonically increasing over the window. Upon getting a new min, we can forget everything earlier because it has no value - the new min is less than everything else in the window by definition and it's the most recent. So we restart fresh on every new min and overwrites the 2nd & 3rd choices. The same property holds for the 2nd & 3rd best. Therefore we have to maintain two invariants to maximize the information in the samples, one on values (1st.v <= 2nd.v <= 3rd.v) and the other on times (now-win <=1st.t <= 2nd.t <= 3rd.t <= now). These invariants determine the structure of the code The RTT input to the windowed filter is the minimum RTT measured from ACK or SACK, or as the last resort from TCP timestamps. The accessor tcp_min_rtt() returns the minimum RTT seen in the window. ~0U indicates it is not available. The minimum is 1usec even if the true RTT is below that. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 8 ++++ include/linux/tcp.h | 3 ++ include/net/tcp.h | 7 +++ net/ipv4/sysctl_net_ipv4.c | 7 +++ net/ipv4/tcp.c | 1 + net/ipv4/tcp_input.c | 78 +++++++++++++++++++++++++++++++--- net/ipv4/tcp_minisocks.c | 1 + 7 files changed, 100 insertions(+), 5 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index ebe94f2cab98..502d6a572b4f 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -384,6 +384,14 @@ tcp_mem - vector of 3 INTEGERs: min, pressure, max Defaults are calculated at boot time from amount of available memory. +tcp_min_rtt_wlen - INTEGER + The window length of the windowed min filter to track the minimum RTT. + A shorter window lets a flow more quickly pick up new (higher) + minimum RTT when it is moved to a longer path (e.g., due to traffic + engineering). A longer window makes the filter more resistant to RTT + inflations such as transient congestion. The unit is seconds. + Default: 300 + tcp_moderate_rcvbuf - BOOLEAN If set, TCP performs receive buffer auto-tuning, attempting to automatically size the buffer (no greater than tcp_rmem[2]) to diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 86a7edaa6797..90edef5508f9 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -217,6 +217,9 @@ struct tcp_sock { u32 mdev_max_us; /* maximal mdev for the last rtt period */ u32 rttvar_us; /* smoothed mdev_max */ u32 rtt_seq; /* sequence number to update rttvar */ + struct rtt_meas { + u32 rtt, ts; /* RTT in usec and sampling time in jiffies. */ + } rtt_min[3]; u32 packets_out; /* Packets which are "in flight" */ u32 retrans_out; /* Retransmitted packets out */ diff --git a/include/net/tcp.h b/include/net/tcp.h index eed94fc355c1..4a43152229ea 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -279,6 +279,7 @@ extern int sysctl_tcp_limit_output_bytes; extern int sysctl_tcp_challenge_ack_limit; extern unsigned int sysctl_tcp_notsent_lowat; extern int sysctl_tcp_min_tso_segs; +extern int sysctl_tcp_min_rtt_wlen; extern int sysctl_tcp_autocorking; extern int sysctl_tcp_invalid_ratelimit; extern int sysctl_tcp_pacing_ss_ratio; @@ -671,6 +672,12 @@ static inline bool tcp_ca_dst_locked(const struct dst_entry *dst) return dst_metric_locked(dst, RTAX_CC_ALGO); } +/* Minimum RTT in usec. ~0 means not available. */ +static inline u32 tcp_min_rtt(const struct tcp_sock *tp) +{ + return tp->rtt_min[0].rtt; +} + /* Compute the actual receive window we are currently advertising. * Rcv_nxt can be after the window if our peer push more data * than the offered window. diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 894da3a70aff..13ab434c2909 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -576,6 +576,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_min_rtt_wlen", + .data = &sysctl_tcp_min_rtt_wlen, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { .procname = "tcp_low_latency", .data = &sysctl_tcp_low_latency, diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index ac1bdbb50352..0cfa7c0c1e80 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -388,6 +388,7 @@ void tcp_init_sock(struct sock *sk) icsk->icsk_rto = TCP_TIMEOUT_INIT; tp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + tp->rtt_min[0].rtt = ~0U; /* So many TCP implementations out there (incorrectly) count the * initial SYN frame in their delayed-ACK and congestion control diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index 62ee71efd1ce..eedb25db3947 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -95,6 +95,7 @@ int sysctl_tcp_stdurg __read_mostly; int sysctl_tcp_rfc1337 __read_mostly; int sysctl_tcp_max_orphans __read_mostly = NR_FILE; int sysctl_tcp_frto __read_mostly = 2; +int sysctl_tcp_min_rtt_wlen __read_mostly = 300; int sysctl_tcp_thin_dupack __read_mostly; @@ -2915,8 +2916,69 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, tcp_xmit_retransmit_queue(sk); } +/* Kathleen Nichols' algorithm for tracking the minimum value of + * a data stream over some fixed time interval. (E.g., the minimum + * RTT over the past five minutes.) It uses constant space and constant + * time per update yet almost always delivers the same minimum as an + * implementation that has to keep all the data in the window. + * + * The algorithm keeps track of the best, 2nd best & 3rd best min + * values, maintaining an invariant that the measurement time of the + * n'th best >= n-1'th best. It also makes sure that the three values + * are widely separated in the time window since that bounds the worse + * case error when that data is monotonically increasing over the window. + * + * Upon getting a new min, we can forget everything earlier because it + * has no value - the new min is <= everything else in the window by + * definition and it's the most recent. So we restart fresh on every new min + * and overwrites 2nd & 3rd choices. The same property holds for 2nd & 3rd + * best. + */ +static void tcp_update_rtt_min(struct sock *sk, u32 rtt_us) +{ + const u32 now = tcp_time_stamp, wlen = sysctl_tcp_min_rtt_wlen * HZ; + struct rtt_meas *m = tcp_sk(sk)->rtt_min; + struct rtt_meas rttm = { .rtt = (rtt_us ? : 1), .ts = now }; + u32 elapsed; + + /* Check if the new measurement updates the 1st, 2nd, or 3rd choices */ + if (unlikely(rttm.rtt <= m[0].rtt)) + m[0] = m[1] = m[2] = rttm; + else if (rttm.rtt <= m[1].rtt) + m[1] = m[2] = rttm; + else if (rttm.rtt <= m[2].rtt) + m[2] = rttm; + + elapsed = now - m[0].ts; + if (unlikely(elapsed > wlen)) { + /* Passed entire window without a new min so make 2nd choice + * the new min & 3rd choice the new 2nd. So forth and so on. + */ + m[0] = m[1]; + m[1] = m[2]; + m[2] = rttm; + if (now - m[0].ts > wlen) { + m[0] = m[1]; + m[1] = rttm; + if (now - m[0].ts > wlen) + m[0] = rttm; + } + } else if (m[1].ts == m[0].ts && elapsed > wlen / 4) { + /* Passed a quarter of the window without a new min so + * take 2nd choice from the 2nd quarter of the window. + */ + m[2] = m[1] = rttm; + } else if (m[2].ts == m[1].ts && elapsed > wlen / 2) { + /* Passed half the window without a new min so take the 3rd + * choice from the last half of the window. + */ + m[2] = rttm; + } +} + static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, - long seq_rtt_us, long sack_rtt_us) + long seq_rtt_us, long sack_rtt_us, + long ca_rtt_us) { const struct tcp_sock *tp = tcp_sk(sk); @@ -2936,11 +2998,16 @@ static inline bool tcp_ack_update_rtt(struct sock *sk, const int flag, */ if (seq_rtt_us < 0 && tp->rx_opt.saw_tstamp && tp->rx_opt.rcv_tsecr && flag & FLAG_ACKED) - seq_rtt_us = jiffies_to_usecs(tcp_time_stamp - tp->rx_opt.rcv_tsecr); - + seq_rtt_us = ca_rtt_us = jiffies_to_usecs(tcp_time_stamp - + tp->rx_opt.rcv_tsecr); if (seq_rtt_us < 0) return false; + /* ca_rtt_us >= 0 is counting on the invariant that ca_rtt_us is + * always taken together with ACK, SACK, or TS-opts. Any negative + * values will be skipped with the seq_rtt_us < 0 check above. + */ + tcp_update_rtt_min(sk, ca_rtt_us); tcp_rtt_estimator(sk, seq_rtt_us); tcp_set_rto(sk); @@ -2961,7 +3028,7 @@ void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req) rtt_us = skb_mstamp_us_delta(&now, &tcp_rsk(req)->snt_synack); } - tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L); + tcp_ack_update_rtt(sk, FLAG_SYN_ACKED, rtt_us, -1L, rtt_us); } @@ -3175,7 +3242,8 @@ static int tcp_clean_rtx_queue(struct sock *sk, int prior_fackets, ca_rtt_us = skb_mstamp_us_delta(&now, &sack->last_sackt); } - rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us); + rtt_update = tcp_ack_update_rtt(sk, flag, seq_rtt_us, sack_rtt_us, + ca_rtt_us); if (flag & FLAG_ACKED) { tcp_rearm_rto(sk); diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 41828bdc5d32..b875c288daaa 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -470,6 +470,7 @@ struct sock *tcp_create_openreq_child(const struct sock *sk, newtp->srtt_us = 0; newtp->mdev_us = jiffies_to_usecs(TCP_TIMEOUT_INIT); + newtp->rtt_min[0].rtt = ~0U; newicsk->icsk_rto = TCP_TIMEOUT_INIT; newtp->packets_out = 0; -- cgit v1.2.3 From 4f41b1c58a32537542f14c1150099131613a5e8a Mon Sep 17 00:00:00 2001 From: Yuchung Cheng Date: Fri, 16 Oct 2015 21:57:47 -0700 Subject: tcp: use RACK to detect losses This patch implements the second half of RACK that uses the the most recent transmit time among all delivered packets to detect losses. tcp_rack_mark_lost() is called upon receiving a dubious ACK. It then checks if an not-yet-sacked packet was sent at least "reo_wnd" prior to the sent time of the most recently delivered. If so the packet is deemed lost. The "reo_wnd" reordering window starts with 1msec for fast loss detection and changes to min-RTT/4 when reordering is observed. We found 1msec accommodates well on tiny degree of reordering (<3 pkts) on faster links. We use min-RTT instead of SRTT because reordering is more of a path property but SRTT can be inflated by self-inflicated congestion. The factor of 4 is borrowed from the delayed early retransmit and seems to work reasonably well. Since RACK is still experimental, it is now used as a supplemental loss detection on top of existing algorithms. It is only effective after the fast recovery starts or after the timeout occurs. The fast recovery is still triggered by FACK and/or dupack threshold instead of RACK. We introduce a new sysctl net.ipv4.tcp_recovery for future experiments of loss recoveries. For now RACK can be disabled by setting it to 0. Signed-off-by: Yuchung Cheng Signed-off-by: Neal Cardwell Signed-off-by: Eric Dumazet Signed-off-by: David S. Miller --- Documentation/networking/ip-sysctl.txt | 9 ++++ include/net/tcp.h | 9 ++++ net/ipv4/sysctl_net_ipv4.c | 7 ++++ net/ipv4/tcp_input.c | 9 +++- net/ipv4/tcp_recovery.c | 77 ++++++++++++++++++++++++++++++++++ 5 files changed, 109 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 502d6a572b4f..85752c81c5ec 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -433,6 +433,15 @@ tcp_orphan_retries - INTEGER you should think about lowering this value, such sockets may consume significant resources. Cf. tcp_max_orphans. +tcp_recovery - INTEGER + This value is a bitmap to enable various experimental loss recovery + features. + + RACK: 0x1 enables the RACK loss detection for fast detection of lost + retransmissions and tail drops. + + Default: 0x1 + tcp_reordering - INTEGER Initial reordering level of packets in a TCP stream. TCP stack can then dynamically adjust flow reordering level diff --git a/include/net/tcp.h b/include/net/tcp.h index 3c3a9fe057d3..11e320412216 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -567,6 +567,7 @@ void tcp_resume_early_retransmit(struct sock *sk); void tcp_rearm_rto(struct sock *sk); void tcp_synack_rtt_meas(struct sock *sk, struct request_sock *req); void tcp_reset(struct sock *sk); +void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb); /* tcp_timer.c */ void tcp_init_xmit_timers(struct sock *); @@ -1752,6 +1753,14 @@ void tcp_init(void); /* tcp_recovery.c */ +/* Flags to enable various loss recovery features. See below */ +extern int sysctl_tcp_recovery; + +/* Use TCP RACK to detect (some) tail and retransmit losses */ +#define TCP_RACK_LOST_RETRANS 0x1 + +extern int tcp_rack_mark_lost(struct sock *sk); + extern void tcp_rack_advance(struct tcp_sock *tp, const struct skb_mstamp *xmit_time, u8 sacked); diff --git a/net/ipv4/sysctl_net_ipv4.c b/net/ipv4/sysctl_net_ipv4.c index 13ab434c2909..25300c5e283b 100644 --- a/net/ipv4/sysctl_net_ipv4.c +++ b/net/ipv4/sysctl_net_ipv4.c @@ -495,6 +495,13 @@ static struct ctl_table ipv4_table[] = { .mode = 0644, .proc_handler = proc_dointvec }, + { + .procname = "tcp_recovery", + .data = &sysctl_tcp_recovery, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec, + }, { .procname = "tcp_reordering", .data = &sysctl_tcp_reordering, diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index ce8370525832..fdd88c3803a6 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -881,6 +881,7 @@ static void tcp_update_reordering(struct sock *sk, const int metric, if (metric > 0) tcp_disable_early_retrans(tp); + tp->rack.reord = 1; } /* This must be called before lost_out is incremented */ @@ -906,8 +907,7 @@ static void tcp_skb_mark_lost(struct tcp_sock *tp, struct sk_buff *skb) } } -static void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, - struct sk_buff *skb) +void tcp_skb_mark_lost_uncond_verify(struct tcp_sock *tp, struct sk_buff *skb) { tcp_verify_retransmit_hint(tp, skb); @@ -2806,6 +2806,11 @@ static void tcp_fastretrans_alert(struct sock *sk, const int acked, } } + /* Use RACK to detect loss */ + if (sysctl_tcp_recovery & TCP_RACK_LOST_RETRANS && + tcp_rack_mark_lost(sk)) + flag |= FLAG_LOST_RETRANS; + /* E. Process state. */ switch (icsk->icsk_ca_state) { case TCP_CA_Recovery: diff --git a/net/ipv4/tcp_recovery.c b/net/ipv4/tcp_recovery.c index 8f66a6584845..5353085fd0b2 100644 --- a/net/ipv4/tcp_recovery.c +++ b/net/ipv4/tcp_recovery.c @@ -1,6 +1,83 @@ #include #include +int sysctl_tcp_recovery __read_mostly = TCP_RACK_LOST_RETRANS; + +/* Marks a packet lost, if some packet sent later has been (s)acked. + * The underlying idea is similar to the traditional dupthresh and FACK + * but they look at different metrics: + * + * dupthresh: 3 OOO packets delivered (packet count) + * FACK: sequence delta to highest sacked sequence (sequence space) + * RACK: sent time delta to the latest delivered packet (time domain) + * + * The advantage of RACK is it applies to both original and retransmitted + * packet and therefore is robust against tail losses. Another advantage + * is being more resilient to reordering by simply allowing some + * "settling delay", instead of tweaking the dupthresh. + * + * The current version is only used after recovery starts but can be + * easily extended to detect the first loss. + */ +int tcp_rack_mark_lost(struct sock *sk) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct sk_buff *skb; + u32 reo_wnd, prior_retrans = tp->retrans_out; + + if (inet_csk(sk)->icsk_ca_state < TCP_CA_Recovery || !tp->rack.advanced) + return 0; + + /* Reset the advanced flag to avoid unnecessary queue scanning */ + tp->rack.advanced = 0; + + /* To be more reordering resilient, allow min_rtt/4 settling delay + * (lower-bounded to 1000uS). We use min_rtt instead of the smoothed + * RTT because reordering is often a path property and less related + * to queuing or delayed ACKs. + * + * TODO: measure and adapt to the observed reordering delay, and + * use a timer to retransmit like the delayed early retransmit. + */ + reo_wnd = 1000; + if (tp->rack.reord && tcp_min_rtt(tp) != ~0U) + reo_wnd = max(tcp_min_rtt(tp) >> 2, reo_wnd); + + tcp_for_write_queue(skb, sk) { + struct tcp_skb_cb *scb = TCP_SKB_CB(skb); + + if (skb == tcp_send_head(sk)) + break; + + /* Skip ones already (s)acked */ + if (!after(scb->end_seq, tp->snd_una) || + scb->sacked & TCPCB_SACKED_ACKED) + continue; + + if (skb_mstamp_after(&tp->rack.mstamp, &skb->skb_mstamp)) { + + if (skb_mstamp_us_delta(&tp->rack.mstamp, + &skb->skb_mstamp) <= reo_wnd) + continue; + + /* skb is lost if packet sent later is sacked */ + tcp_skb_mark_lost_uncond_verify(tp, skb); + if (scb->sacked & TCPCB_SACKED_RETRANS) { + scb->sacked &= ~TCPCB_SACKED_RETRANS; + tp->retrans_out -= tcp_skb_pcount(skb); + NET_INC_STATS_BH(sock_net(sk), + LINUX_MIB_TCPLOSTRETRANSMIT); + } + } else if (!(scb->sacked & TCPCB_RETRANS)) { + /* Original data are sent sequentially so stop early + * b/c the rest are all sent after rack_sent + */ + break; + } + } + return prior_retrans - tp->retrans_out; +} + /* Record the most recently (re)sent time among the (s)acked packets */ void tcp_rack_advance(struct tcp_sock *tp, const struct skb_mstamp *xmit_time, u8 sacked) -- cgit v1.2.3 From 3648dc6d27f648b8e3ce9b48874627a833d53c3a Mon Sep 17 00:00:00 2001 From: Christophe Ricard Date: Sun, 25 Oct 2015 22:54:39 +0100 Subject: NFC: st-nci: Add ese-present/uicc-present dts properties In order to align with st21nfca, dts configuration properties ese_present and uicc_present are made available in st-nci driver. So far, in early development firmware, because nci_nfcee_mode_set(DISABLE) was not supported we had to try to enable it during the secure element discovery phase. After several trials on commercial and qualified firmware it appears that nci_nfcee_mode_set(ENABLE) and nci_nfcee_mode_set(DISABLE) are properly supported. Such feature also help us to eventually save some time (~5ms) when only one secure element is connected. Acked-by: Rob Herring Signed-off-by: Christophe Ricard Signed-off-by: Samuel Ortiz --- .../devicetree/bindings/net/nfc/st-nci-i2c.txt | 7 ++ .../devicetree/bindings/net/nfc/st-nci-spi.txt | 9 +- drivers/nfc/st-nci/core.c | 4 +- drivers/nfc/st-nci/i2c.c | 12 ++- drivers/nfc/st-nci/ndlc.c | 6 +- drivers/nfc/st-nci/ndlc.h | 5 +- drivers/nfc/st-nci/se.c | 98 ++++++++++++++-------- drivers/nfc/st-nci/spi.c | 12 ++- drivers/nfc/st-nci/st-nci.h | 13 ++- include/linux/platform_data/st-nci.h | 2 + 10 files changed, 122 insertions(+), 46 deletions(-) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt index d707588ed734..263732e8879f 100644 --- a/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt +++ b/Documentation/devicetree/bindings/net/nfc/st-nci-i2c.txt @@ -11,6 +11,10 @@ Required properties: Optional SoC Specific Properties: - pinctrl-names: Contains only one value - "default". - pintctrl-0: Specifies the pin control groups used for this controller. +- ese-present: Specifies that an ese is physically connected to the nfc +controller. +- uicc-present: Specifies that the uicc swp signal can be physically +connected to the nfc controller. Example (for ARM-based BeagleBoard xM with ST21NFCB on I2C2): @@ -29,5 +33,8 @@ Example (for ARM-based BeagleBoard xM with ST21NFCB on I2C2): interrupts = <2 IRQ_TYPE_LEVEL_HIGH>; reset-gpios = <&gpio5 29 GPIO_ACTIVE_HIGH>; + + ese-present; + uicc-present; }; }; diff --git a/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt index 525681b6dc39..711ca85a363d 100644 --- a/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt +++ b/Documentation/devicetree/bindings/net/nfc/st-nci-spi.txt @@ -2,7 +2,7 @@ Required properties: - compatible: Should be "st,st21nfcb-spi" -- spi-max-frequency: Maximum SPI frequency (<= 10000000). +- spi-max-frequency: Maximum SPI frequency (<= 4000000). - interrupt-parent: phandle for the interrupt gpio controller - interrupts: GPIO interrupt to which the chip is connected - reset-gpios: Output GPIO pin used to reset the ST21NFCB @@ -10,6 +10,10 @@ Required properties: Optional SoC Specific Properties: - pinctrl-names: Contains only one value - "default". - pintctrl-0: Specifies the pin control groups used for this controller. +- ese-present: Specifies that an ese is physically connected to the nfc +controller. +- uicc-present: Specifies that the uicc swp signal can be physically +connected to the nfc controller. Example (for ARM-based BeagleBoard xM with ST21NFCB on SPI4): @@ -27,5 +31,8 @@ Example (for ARM-based BeagleBoard xM with ST21NFCB on SPI4): interrupts = <2 IRQ_TYPE_EDGE_RISING>; reset-gpios = <&gpio5 29 GPIO_ACTIVE_HIGH>; + + ese-present; + uicc-present; }; }; diff --git a/drivers/nfc/st-nci/core.c b/drivers/nfc/st-nci/core.c index 73d36dd8345c..c693128ee6fb 100644 --- a/drivers/nfc/st-nci/core.c +++ b/drivers/nfc/st-nci/core.c @@ -123,7 +123,7 @@ static struct nci_ops st_nci_ops = { }; int st_nci_probe(struct llt_ndlc *ndlc, int phy_headroom, - int phy_tailroom) + int phy_tailroom, struct st_nci_se_status *se_status) { struct st_nci_info *info; int r; @@ -164,7 +164,7 @@ int st_nci_probe(struct llt_ndlc *ndlc, int phy_headroom, goto err_reg_dev; } - return st_nci_se_init(ndlc->ndev); + return st_nci_se_init(ndlc->ndev, se_status); err_reg_dev: nci_free_device(ndlc->ndev); diff --git a/drivers/nfc/st-nci/i2c.c b/drivers/nfc/st-nci/i2c.c index 02e585f2be74..172cbc34cc9f 100644 --- a/drivers/nfc/st-nci/i2c.c +++ b/drivers/nfc/st-nci/i2c.c @@ -52,6 +52,8 @@ struct st_nci_i2c_phy { unsigned int gpio_reset; unsigned int irq_polarity; + + struct st_nci_se_status se_status; }; #define I2C_DUMP_SKB(info, skb) \ @@ -245,6 +247,11 @@ static int st_nci_i2c_of_request_resources(struct i2c_client *client) phy->irq_polarity = irq_get_trigger_type(client->irq); + phy->se_status.is_ese_present = + of_property_read_bool(pp, "ese-present"); + phy->se_status.is_uicc_present = + of_property_read_bool(pp, "uicc-present"); + return 0; } #else @@ -277,6 +284,9 @@ static int st_nci_i2c_request_resources(struct i2c_client *client) return r; } + phy->se_status.is_ese_present = pdata->is_ese_present; + phy->se_status.is_uicc_present = pdata->is_uicc_present; + return 0; } @@ -326,7 +336,7 @@ static int st_nci_i2c_probe(struct i2c_client *client, r = ndlc_probe(phy, &i2c_phy_ops, &client->dev, ST_NCI_FRAME_HEADROOM, ST_NCI_FRAME_TAILROOM, - &phy->ndlc); + &phy->ndlc, &phy->se_status); if (r < 0) { nfc_err(&client->dev, "Unable to register ndlc layer\n"); return r; diff --git a/drivers/nfc/st-nci/ndlc.c b/drivers/nfc/st-nci/ndlc.c index fb50007ac32a..0884b11001ef 100644 --- a/drivers/nfc/st-nci/ndlc.c +++ b/drivers/nfc/st-nci/ndlc.c @@ -20,6 +20,7 @@ #include #include "st-nci.h" +#include "ndlc.h" #define NDLC_TIMER_T1 100 #define NDLC_TIMER_T1_WAIT 400 @@ -265,7 +266,8 @@ static void ndlc_t2_timeout(unsigned long data) } int ndlc_probe(void *phy_id, struct nfc_phy_ops *phy_ops, struct device *dev, - int phy_headroom, int phy_tailroom, struct llt_ndlc **ndlc_id) + int phy_headroom, int phy_tailroom, struct llt_ndlc **ndlc_id, + struct st_nci_se_status *se_status) { struct llt_ndlc *ndlc; @@ -295,7 +297,7 @@ int ndlc_probe(void *phy_id, struct nfc_phy_ops *phy_ops, struct device *dev, INIT_WORK(&ndlc->sm_work, llt_ndlc_sm_work); - return st_nci_probe(ndlc, phy_headroom, phy_tailroom); + return st_nci_probe(ndlc, phy_headroom, phy_tailroom, se_status); } EXPORT_SYMBOL(ndlc_probe); diff --git a/drivers/nfc/st-nci/ndlc.h b/drivers/nfc/st-nci/ndlc.h index 6361005ef003..bdf78ffd5bb7 100644 --- a/drivers/nfc/st-nci/ndlc.h +++ b/drivers/nfc/st-nci/ndlc.h @@ -22,6 +22,8 @@ #include #include +struct st_nci_se_status; + /* Low Level Transport description */ struct llt_ndlc { struct nci_dev *ndev; @@ -55,6 +57,7 @@ void ndlc_close(struct llt_ndlc *ndlc); int ndlc_send(struct llt_ndlc *ndlc, struct sk_buff *skb); void ndlc_recv(struct llt_ndlc *ndlc, struct sk_buff *skb); int ndlc_probe(void *phy_id, struct nfc_phy_ops *phy_ops, struct device *dev, - int phy_headroom, int phy_tailroom, struct llt_ndlc **ndlc_id); + int phy_headroom, int phy_tailroom, struct llt_ndlc **ndlc_id, + struct st_nci_se_status *se_status); void ndlc_remove(struct llt_ndlc *ndlc); #endif /* __LOCAL_NDLC_H__ */ diff --git a/drivers/nfc/st-nci/se.c b/drivers/nfc/st-nci/se.c index 281288484794..147e2d904c63 100644 --- a/drivers/nfc/st-nci/se.c +++ b/drivers/nfc/st-nci/se.c @@ -419,12 +419,8 @@ void st_nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, u8 cmd, } EXPORT_SYMBOL_GPL(st_nci_hci_cmd_received); -/* - * Remarks: On some early st_nci firmware, nci_nfcee_mode_set(0) - * is rejected - */ static int st_nci_control_se(struct nci_dev *ndev, u8 se_idx, - u8 state) + u8 state) { struct st_nci_info *info = nci_get_drvdata(ndev); int r; @@ -449,7 +445,7 @@ static int st_nci_control_se(struct nci_dev *ndev, u8 se_idx, * retrieve a relevant host list. */ reinit_completion(&info->se_info.req_completion); - r = nci_nfcee_mode_set(ndev, se_idx, NCI_NFCEE_ENABLE); + r = nci_nfcee_mode_set(ndev, se_idx, state); if (r != NCI_STATUS_OK) return r; @@ -465,7 +461,9 @@ static int st_nci_control_se(struct nci_dev *ndev, u8 se_idx, * There is no possible synchronization to prevent this. * Adding a small delay is the only way to solve the issue. */ - usleep_range(3000, 5000); + if (info->se_info.se_status->is_ese_present && + info->se_info.se_status->is_uicc_present) + usleep_range(3000, 5000); r = nci_hci_get_param(ndev, NCI_HCI_ADMIN_GATE, NCI_HCI_ADMIN_PARAM_HOST_LIST, &sk_host_list); @@ -488,11 +486,20 @@ int st_nci_disable_se(struct nci_dev *ndev, u32 se_idx) pr_debug("st_nci_disable_se\n"); - if (se_idx == NFC_SE_EMBEDDED) { - r = nci_hci_send_event(ndev, ST_NCI_APDU_READER_GATE, - ST_NCI_EVT_SE_END_OF_APDU_TRANSFER, NULL, 0); - if (r < 0) - return r; + /* + * According to upper layer, se_idx == NFC_SE_UICC when + * info->se_info.se_status->is_uicc_enable is true should never happen + * Same for eSE. + */ + r = st_nci_control_se(ndev, se_idx, ST_NCI_SE_MODE_OFF); + if (r < 0) { + /* Do best effort to release SWP */ + if (se_idx == NFC_SE_EMBEDDED) { + r = nci_hci_send_event(ndev, ST_NCI_APDU_READER_GATE, + ST_NCI_EVT_SE_END_OF_APDU_TRANSFER, + NULL, 0); + } + return r; } return 0; @@ -505,11 +512,25 @@ int st_nci_enable_se(struct nci_dev *ndev, u32 se_idx) pr_debug("st_nci_enable_se\n"); - if (se_idx == ST_NCI_HCI_HOST_ID_ESE) { + /* + * According to upper layer, se_idx == NFC_SE_UICC when + * info->se_info.se_status->is_uicc_enable is true should never happen. + * Same for eSE. + */ + r = st_nci_control_se(ndev, se_idx, ST_NCI_SE_MODE_ON); + if (r == ST_NCI_HCI_HOST_ID_ESE) { + st_nci_se_get_atr(ndev); r = nci_hci_send_event(ndev, ST_NCI_APDU_READER_GATE, ST_NCI_EVT_SE_SOFT_RESET, NULL, 0); - if (r < 0) - return r; + } + + if (r < 0) { + /* + * The activation procedure failed, the secure element + * is not connected. Remove from the list. + */ + nfc_remove_se(ndev->nfc_dev, se_idx); + return r; } return 0; @@ -592,8 +613,8 @@ exit: int st_nci_discover_se(struct nci_dev *ndev) { - u8 param[2]; - int r; + u8 white_list[2]; + int r, wl_size = 0; int se_count = 0; struct st_nci_info *info = nci_get_drvdata(ndev); @@ -606,29 +627,34 @@ int st_nci_discover_se(struct nci_dev *ndev) if (test_bit(ST_NCI_FACTORY_MODE, &info->flags)) return 0; - param[0] = ST_NCI_UICC_HOST_ID; - param[1] = ST_NCI_HCI_HOST_ID_ESE; - r = nci_hci_set_param(ndev, NCI_HCI_ADMIN_GATE, - NCI_HCI_ADMIN_PARAM_WHITELIST, - param, sizeof(param)); - if (r != NCI_HCI_ANY_OK) - return r; + if (info->se_info.se_status->is_ese_present && + info->se_info.se_status->is_uicc_present) { + white_list[wl_size++] = ST_NCI_UICC_HOST_ID; + white_list[wl_size++] = ST_NCI_ESE_HOST_ID; + } else if (!info->se_info.se_status->is_ese_present && + info->se_info.se_status->is_uicc_present) { + white_list[wl_size++] = ST_NCI_UICC_HOST_ID; + } else if (info->se_info.se_status->is_ese_present && + !info->se_info.se_status->is_uicc_present) { + white_list[wl_size++] = ST_NCI_ESE_HOST_ID; + } + + if (wl_size) { + r = nci_hci_set_param(ndev, NCI_HCI_ADMIN_GATE, + NCI_HCI_ADMIN_PARAM_WHITELIST, + white_list, wl_size); + if (r != NCI_HCI_ANY_OK) + return r; + } - r = st_nci_control_se(ndev, ST_NCI_UICC_HOST_ID, - ST_NCI_SE_MODE_ON); - if (r == ST_NCI_UICC_HOST_ID) { + if (info->se_info.se_status->is_uicc_present) { nfc_add_se(ndev->nfc_dev, ST_NCI_UICC_HOST_ID, NFC_SE_UICC); se_count++; } - /* Try to enable eSE in order to check availability */ - r = st_nci_control_se(ndev, ST_NCI_HCI_HOST_ID_ESE, - ST_NCI_SE_MODE_ON); - if (r == ST_NCI_HCI_HOST_ID_ESE) { - nfc_add_se(ndev->nfc_dev, ST_NCI_HCI_HOST_ID_ESE, - NFC_SE_EMBEDDED); + if (info->se_info.se_status->is_ese_present) { + nfc_add_se(ndev->nfc_dev, ST_NCI_ESE_HOST_ID, NFC_SE_EMBEDDED); se_count++; - st_nci_se_get_atr(ndev); } return !se_count; @@ -701,7 +727,7 @@ static void st_nci_se_activation_timeout(unsigned long data) complete(&info->se_info.req_completion); } -int st_nci_se_init(struct nci_dev *ndev) +int st_nci_se_init(struct nci_dev *ndev, struct st_nci_se_status *se_status) { struct st_nci_info *info = nci_get_drvdata(ndev); @@ -723,6 +749,8 @@ int st_nci_se_init(struct nci_dev *ndev) info->se_info.wt_timeout = ST_NCI_BWI_TO_TIMEOUT(ST_NCI_ATR_DEFAULT_BWI); + info->se_info.se_status = se_status; + return 0; } EXPORT_SYMBOL(st_nci_se_init); diff --git a/drivers/nfc/st-nci/spi.c b/drivers/nfc/st-nci/spi.c index b43f448b8d78..889720336474 100644 --- a/drivers/nfc/st-nci/spi.c +++ b/drivers/nfc/st-nci/spi.c @@ -53,6 +53,8 @@ struct st_nci_spi_phy { unsigned int gpio_reset; unsigned int irq_polarity; + + struct st_nci_se_status se_status; }; #define SPI_DUMP_SKB(info, skb) \ @@ -260,6 +262,11 @@ static int st_nci_spi_of_request_resources(struct spi_device *dev) phy->irq_polarity = irq_get_trigger_type(dev->irq); + phy->se_status.is_ese_present = + of_property_read_bool(pp, "ese-present"); + phy->se_status.is_uicc_present = + of_property_read_bool(pp, "uicc-present"); + return 0; } #else @@ -292,6 +299,9 @@ static int st_nci_spi_request_resources(struct spi_device *dev) return r; } + phy->se_status.is_ese_present = pdata->is_ese_present; + phy->se_status.is_uicc_present = pdata->is_uicc_present; + return 0; } @@ -342,7 +352,7 @@ static int st_nci_spi_probe(struct spi_device *dev) r = ndlc_probe(phy, &spi_phy_ops, &dev->dev, ST_NCI_FRAME_HEADROOM, ST_NCI_FRAME_TAILROOM, - &phy->ndlc); + &phy->ndlc, &phy->se_status); if (r < 0) { nfc_err(&dev->dev, "Unable to register ndlc layer\n"); return r; diff --git a/drivers/nfc/st-nci/st-nci.h b/drivers/nfc/st-nci/st-nci.h index 9c9bb19cc9ff..8b9f77b0249c 100644 --- a/drivers/nfc/st-nci/st-nci.h +++ b/drivers/nfc/st-nci/st-nci.h @@ -48,7 +48,13 @@ struct nci_mode_set_rsp { u8 status; } __packed; +struct st_nci_se_status { + bool is_ese_present; + bool is_uicc_present; +}; + struct st_nci_se_info { + struct st_nci_se_status *se_status; u8 atr[ST_NCI_ESE_MAX_LENGTH]; struct completion req_completion; @@ -126,15 +132,16 @@ struct st_nci_vendor_info { struct st_nci_info { struct llt_ndlc *ndlc; unsigned long flags; + struct st_nci_se_info se_info; struct st_nci_vendor_info vendor_info; }; void st_nci_remove(struct nci_dev *ndev); int st_nci_probe(struct llt_ndlc *ndlc, int phy_headroom, - int phy_tailroom); + int phy_tailroom, struct st_nci_se_status *se_status); -int st_nci_se_init(struct nci_dev *ndev); +int st_nci_se_init(struct nci_dev *ndev, struct st_nci_se_status *se_status); void st_nci_se_deinit(struct nci_dev *ndev); int st_nci_discover_se(struct nci_dev *ndev); @@ -150,7 +157,7 @@ void st_nci_hci_cmd_received(struct nci_dev *ndev, u8 pipe, u8 cmd, struct sk_buff *skb); void st_nci_hci_loopback_event_received(struct nci_dev *ndev, u8 event, - struct sk_buff *skb); + struct sk_buff *skb); int st_nci_vendor_cmds_init(struct nci_dev *ndev); #endif /* __LOCAL_ST_NCI_H_ */ diff --git a/include/linux/platform_data/st-nci.h b/include/linux/platform_data/st-nci.h index d9d400a297bd..f6494b347c06 100644 --- a/include/linux/platform_data/st-nci.h +++ b/include/linux/platform_data/st-nci.h @@ -24,6 +24,8 @@ struct st_nci_nfc_platform_data { unsigned int gpio_reset; unsigned int irq_polarity; + bool is_ese_present; + bool is_uicc_present; }; #endif /* _ST_NCI_H_ */ -- cgit v1.2.3 From b5b3e23e4cace008e1a30e8614a484d14dfd07a1 Mon Sep 17 00:00:00 2001 From: Vincent Cuissard Date: Mon, 26 Oct 2015 10:27:41 +0100 Subject: NFC: nfcmrvl: add i2c driver This driver adds the support of I2C-based Marvell NFC controller. Signed-off-by: Vincent Cuissard Signed-off-by: Samuel Ortiz --- .../devicetree/bindings/net/nfc/nfcmrvl.txt | 34 ++- drivers/nfc/nfcmrvl/Kconfig | 12 + drivers/nfc/nfcmrvl/Makefile | 3 + drivers/nfc/nfcmrvl/i2c.c | 290 +++++++++++++++++++++ drivers/nfc/nfcmrvl/main.c | 9 +- drivers/nfc/nfcmrvl/nfcmrvl.h | 1 + include/linux/platform_data/nfcmrvl.h | 8 + include/net/nfc/nci.h | 1 + 8 files changed, 353 insertions(+), 5 deletions(-) create mode 100644 drivers/nfc/nfcmrvl/i2c.c (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt index 7c4a0cc370cf..0fa20cc2c33c 100644 --- a/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt +++ b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt @@ -1,7 +1,9 @@ * Marvell International Ltd. NCI NFC Controller Required properties: -- compatible: Should be "mrvl,nfc-uart". +- compatible: Should be: + - "mrvl,nfc-uart" for UART devices + - "mrvl,nfc-i2c" for I2C devices Optional SoC specific properties: - pinctrl-names: Contains only one value - "default". @@ -13,6 +15,12 @@ Optional UART-based chip specific properties: - flow-control: Specifies that the chip is using RTS/CTS. - break-control: Specifies that the chip needs specific break management. +Optional I2C-based chip specific properties: +- i2c-int-falling: Specifies that the chip read event shall be trigged on + falling edge. +- i2c-int-rising: Specifies that the chip read event shall be trigged on + rising edge. + Example (for ARM-based BeagleBoard Black with 88W8887 on UART5): &uart5 { @@ -27,3 +35,27 @@ Example (for ARM-based BeagleBoard Black with 88W8887 on UART5): flow-control; } }; + + +Example (for ARM-based BeagleBoard Black with 88W8887 on I2C1): + +&i2c1 { + status = "okay"; + clock-frequency = <400000>; + + nfcmrvli2c0: i2c@1 { + compatible = "mrvl,nfc-i2c"; + + reg = <0x8>; + + /* I2C INT configuration */ + interrupt-parent = <&gpio3>; + interrupts = <21 0>; + + /* I2C INT trigger configuration */ + i2c-int-rising; + + /* Reset IO */ + reset-n-io = <&gpio3 19 0>; + }; +}; diff --git a/drivers/nfc/nfcmrvl/Kconfig b/drivers/nfc/nfcmrvl/Kconfig index 19ac492bc25f..e18a979bb6d3 100644 --- a/drivers/nfc/nfcmrvl/Kconfig +++ b/drivers/nfc/nfcmrvl/Kconfig @@ -30,3 +30,15 @@ config NFC_MRVL_UART Say Y here to compile support for Marvell NFC-over-UART driver into the kernel or say M to compile it as module. + +config NFC_MRVL_I2C + tristate "Marvell NFC-over-I2C driver" + depends on NFC_MRVL && I2C + help + Marvell NFC-over-I2C driver. + + This driver provides support for Marvell NFC-over-I2C devices. + + Say Y here to compile support for Marvell NFC-over-I2C driver + into the kernel or say M to compile it as module. + diff --git a/drivers/nfc/nfcmrvl/Makefile b/drivers/nfc/nfcmrvl/Makefile index 4554ee8e3680..895866a3ebc6 100644 --- a/drivers/nfc/nfcmrvl/Makefile +++ b/drivers/nfc/nfcmrvl/Makefile @@ -10,3 +10,6 @@ obj-$(CONFIG_NFC_MRVL_USB) += nfcmrvl_usb.o nfcmrvl_uart-y += uart.o obj-$(CONFIG_NFC_MRVL_UART) += nfcmrvl_uart.o + +nfcmrvl_i2c-y += i2c.o +obj-$(CONFIG_NFC_MRVL_I2C) += nfcmrvl_i2c.o diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c new file mode 100644 index 000000000000..7a44025bdaad --- /dev/null +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -0,0 +1,290 @@ +/** + * Marvell NFC-over-I2C driver: I2C interface related functions + * + * Copyright (C) 2015, Marvell International Ltd. + * + * This software file (the "File") is distributed by Marvell International + * Ltd. under the terms of the GNU General Public License Version 2, June 1991 + * (the "License"). You may use, redistribute and/or modify this File in + * accordance with the terms and conditions of the License, a copy of which + * is available on the worldwide web at + * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. + * + * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE + * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE + * ARE EXPRESSLY DISCLAIMED. The License provides additional details about + * this warranty disclaimer. + **/ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "nfcmrvl.h" + +struct nfcmrvl_i2c_drv_data { + unsigned long flags; + struct device *dev; + struct i2c_client *i2c; + struct nfcmrvl_private *priv; +}; + +static int nfcmrvl_i2c_read(struct nfcmrvl_i2c_drv_data *drv_data, + struct sk_buff **skb) +{ + int ret; + struct nci_ctrl_hdr nci_hdr; + + /* Read NCI header to know the payload size */ + ret = i2c_master_recv(drv_data->i2c, (u8 *)&nci_hdr, NCI_CTRL_HDR_SIZE); + if (ret != NCI_CTRL_HDR_SIZE) { + nfc_err(&drv_data->i2c->dev, "cannot read NCI header\n"); + return -EBADMSG; + } + + if (nci_hdr.plen > NCI_MAX_PAYLOAD_SIZE) { + nfc_err(&drv_data->i2c->dev, "invalid packet payload size\n"); + return -EBADMSG; + } + + *skb = nci_skb_alloc(drv_data->priv->ndev, + nci_hdr.plen + NCI_CTRL_HDR_SIZE, GFP_KERNEL); + if (!*skb) + return -ENOMEM; + + /* Copy NCI header into the SKB */ + memcpy(skb_put(*skb, NCI_CTRL_HDR_SIZE), &nci_hdr, NCI_CTRL_HDR_SIZE); + + if (nci_hdr.plen) { + /* Read the NCI payload */ + ret = i2c_master_recv(drv_data->i2c, + skb_put(*skb, nci_hdr.plen), + nci_hdr.plen); + + if (ret != nci_hdr.plen) { + nfc_err(&drv_data->i2c->dev, + "Invalid frame payload length: %u (expected %u)\n", + ret, nci_hdr.plen); + kfree_skb(*skb); + return -EBADMSG; + } + } + + return 0; +} + +static irqreturn_t nfcmrvl_i2c_int_irq_thread_fn(int irq, void *drv_data_ptr) +{ + struct nfcmrvl_i2c_drv_data *drv_data = drv_data_ptr; + struct sk_buff *skb = NULL; + int ret; + + if (!drv_data->priv) + return IRQ_HANDLED; + + if (test_bit(NFCMRVL_PHY_ERROR, &drv_data->priv->flags)) + return IRQ_HANDLED; + + ret = nfcmrvl_i2c_read(drv_data, &skb); + + switch (ret) { + case -EREMOTEIO: + set_bit(NFCMRVL_PHY_ERROR, &drv_data->priv->flags); + break; + case -ENOMEM: + case -EBADMSG: + nfc_err(&drv_data->i2c->dev, "read failed %d\n", ret); + break; + default: + if (nfcmrvl_nci_recv_frame(drv_data->priv, skb) < 0) + nfc_err(&drv_data->i2c->dev, "corrupted RX packet\n"); + break; + } + return IRQ_HANDLED; +} + +static int nfcmrvl_i2c_nci_open(struct nfcmrvl_private *priv) +{ + struct nfcmrvl_i2c_drv_data *drv_data = priv->drv_data; + + if (!drv_data) + return -ENODEV; + + return 0; +} + +static int nfcmrvl_i2c_nci_close(struct nfcmrvl_private *priv) +{ + return 0; +} + +static int nfcmrvl_i2c_nci_send(struct nfcmrvl_private *priv, + struct sk_buff *skb) +{ + struct nfcmrvl_i2c_drv_data *drv_data = priv->drv_data; + int ret; + + if (test_bit(NFCMRVL_PHY_ERROR, &priv->flags)) + return -EREMOTEIO; + + ret = i2c_master_send(drv_data->i2c, skb->data, skb->len); + + /* Retry if chip was in standby */ + if (ret == -EREMOTEIO) { + nfc_info(drv_data->dev, "chip may sleep, retry\n"); + usleep_range(6000, 10000); + ret = i2c_master_send(drv_data->i2c, skb->data, skb->len); + } + + if (ret >= 0) { + if (ret != skb->len) { + nfc_err(drv_data->dev, + "Invalid length sent: %u (expected %u)\n", + ret, skb->len); + ret = -EREMOTEIO; + } else + ret = 0; + kfree_skb(skb); + } + + return ret; +} + +static void nfcmrvl_i2c_nci_update_config(struct nfcmrvl_private *priv, + const void *param) +{ +} + +static struct nfcmrvl_if_ops i2c_ops = { + .nci_open = nfcmrvl_i2c_nci_open, + .nci_close = nfcmrvl_i2c_nci_close, + .nci_send = nfcmrvl_i2c_nci_send, + .nci_update_config = nfcmrvl_i2c_nci_update_config, +}; + +static int nfcmrvl_i2c_parse_dt(struct device_node *node, + struct nfcmrvl_platform_data *pdata) +{ + int ret; + + ret = nfcmrvl_parse_dt(node, pdata); + if (ret < 0) { + pr_err("Failed to get generic entries\n"); + return ret; + } + + if (of_find_property(node, "i2c-int-falling", NULL)) + pdata->irq_polarity = IRQF_TRIGGER_FALLING; + else + pdata->irq_polarity = IRQF_TRIGGER_RISING; + + ret = irq_of_parse_and_map(node, 0); + if (ret < 0) { + pr_err("Unable to get irq, error: %d\n", ret); + return ret; + } + pdata->irq = ret; + + return 0; +} + +static int nfcmrvl_i2c_probe(struct i2c_client *client, + const struct i2c_device_id *id) +{ + struct nfcmrvl_i2c_drv_data *drv_data; + struct nfcmrvl_platform_data *pdata; + struct nfcmrvl_platform_data config; + int ret; + + if (!i2c_check_functionality(client->adapter, I2C_FUNC_I2C)) { + nfc_err(&client->dev, "Need I2C_FUNC_I2C\n"); + return -ENODEV; + } + + drv_data = devm_kzalloc(&client->dev, sizeof(*drv_data), GFP_KERNEL); + if (!drv_data) + return -ENOMEM; + + drv_data->i2c = client; + drv_data->dev = &client->dev; + drv_data->priv = NULL; + + i2c_set_clientdata(client, drv_data); + + pdata = client->dev.platform_data; + + if (!pdata && client->dev.of_node) + if (nfcmrvl_i2c_parse_dt(client->dev.of_node, &config) == 0) + pdata = &config; + + if (!pdata) + return -EINVAL; + + /* Request the read IRQ */ + ret = devm_request_threaded_irq(&drv_data->i2c->dev, pdata->irq, + NULL, nfcmrvl_i2c_int_irq_thread_fn, + pdata->irq_polarity | IRQF_ONESHOT, + "nfcmrvl_i2c_int", drv_data); + if (ret < 0) { + nfc_err(&drv_data->i2c->dev, + "Unable to register IRQ handler\n"); + return ret; + } + + drv_data->priv = nfcmrvl_nci_register_dev(NFCMRVL_PHY_I2C, + drv_data, &i2c_ops, + &drv_data->i2c->dev, pdata); + + if (IS_ERR(drv_data->priv)) + return PTR_ERR(drv_data->priv); + + drv_data->priv->support_fw_dnld = true; + + return 0; +} + +static int nfcmrvl_i2c_remove(struct i2c_client *client) +{ + struct nfcmrvl_i2c_drv_data *drv_data = i2c_get_clientdata(client); + + nfcmrvl_nci_unregister_dev(drv_data->priv); + + return 0; +} + + +static const struct of_device_id of_nfcmrvl_i2c_match[] = { + { .compatible = "mrvl,nfc-i2c", }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_nfcmrvl_i2c_match); + +static struct i2c_device_id nfcmrvl_i2c_id_table[] = { + { "nfcmrvl_i2c", 0 }, + {} +}; +MODULE_DEVICE_TABLE(i2c, nfcmrvl_i2c_id_table); + +static struct i2c_driver nfcmrvl_i2c_driver = { + .probe = nfcmrvl_i2c_probe, + .id_table = nfcmrvl_i2c_id_table, + .remove = nfcmrvl_i2c_remove, + .driver = { + .name = "nfcmrvl_i2c", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(of_nfcmrvl_i2c_match), + }, +}; + +module_i2c_driver(nfcmrvl_i2c_driver); + +MODULE_AUTHOR("Marvell International Ltd."); +MODULE_DESCRIPTION("Marvell NFC-over-I2C driver"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index a24a7ca9f33d..0c27de60a6bd 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -33,6 +33,9 @@ static int nfcmrvl_nci_open(struct nci_dev *ndev) if (test_and_set_bit(NFCMRVL_NCI_RUNNING, &priv->flags)) return 0; + /* Reset possible fault of previous session */ + clear_bit(NFCMRVL_PHY_ERROR, &priv->flags); + err = priv->if_ops->nci_open(priv); if (err) @@ -226,10 +229,8 @@ EXPORT_SYMBOL_GPL(nfcmrvl_nci_recv_frame); void nfcmrvl_chip_reset(struct nfcmrvl_private *priv) { - /* - * This function does not take care if someone is using the device. - * To be improved. - */ + /* Reset possible fault of previous session */ + clear_bit(NFCMRVL_PHY_ERROR, &priv->flags); if (priv->config.reset_n_io) { nfc_info(priv->dev, "reset the chip\n"); diff --git a/drivers/nfc/nfcmrvl/nfcmrvl.h b/drivers/nfc/nfcmrvl/nfcmrvl.h index f82678be5aa9..de68ff45e49a 100644 --- a/drivers/nfc/nfcmrvl/nfcmrvl.h +++ b/drivers/nfc/nfcmrvl/nfcmrvl.h @@ -25,6 +25,7 @@ /* Define private flags: */ #define NFCMRVL_NCI_RUNNING 1 +#define NFCMRVL_PHY_ERROR 2 #define NFCMRVL_EXT_COEX_ID 0xE0 #define NFCMRVL_NOT_ALLOWED_ID 0xE1 diff --git a/include/linux/platform_data/nfcmrvl.h b/include/linux/platform_data/nfcmrvl.h index ac91707dabcb..a6f9d633f5be 100644 --- a/include/linux/platform_data/nfcmrvl.h +++ b/include/linux/platform_data/nfcmrvl.h @@ -35,6 +35,14 @@ struct nfcmrvl_platform_data { unsigned int flow_control; /* Tell if firmware supports break control for power management */ unsigned int break_control; + + + /* + * I2C specific + */ + + unsigned int irq; + unsigned int irq_polarity; }; #endif /* _NFCMRVL_PTF_H_ */ diff --git a/include/net/nfc/nci.h b/include/net/nfc/nci.h index b495825f8f49..707e3ab816c2 100644 --- a/include/net/nfc/nci.h +++ b/include/net/nfc/nci.h @@ -35,6 +35,7 @@ #define NCI_MAX_NUM_RF_CONFIGS 10 #define NCI_MAX_NUM_CONN 10 #define NCI_MAX_PARAM_LEN 251 +#define NCI_MAX_PAYLOAD_SIZE 255 #define NCI_MAX_PACKET_SIZE 258 /* NCI Status Codes */ -- cgit v1.2.3 From caf6e49bf6d02e6bb94df680bbe3beaf680fdefa Mon Sep 17 00:00:00 2001 From: Vincent Cuissard Date: Mon, 26 Oct 2015 10:27:44 +0100 Subject: NFC: nfcmrvl: add spi driver This driver adds the support of SPI-based Marvell NFC controller. Signed-off-by: Vincent Cuissard Signed-off-by: Samuel Ortiz --- .../devicetree/bindings/net/nfc/nfcmrvl.txt | 25 +++ drivers/nfc/nfcmrvl/Kconfig | 10 + drivers/nfc/nfcmrvl/Makefile | 3 + drivers/nfc/nfcmrvl/main.c | 6 +- drivers/nfc/nfcmrvl/spi.c | 228 +++++++++++++++++++++ 5 files changed, 271 insertions(+), 1 deletion(-) create mode 100644 drivers/nfc/nfcmrvl/spi.c (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt index 0fa20cc2c33c..41058fcbd9ae 100644 --- a/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt +++ b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt @@ -4,6 +4,7 @@ Required properties: - compatible: Should be: - "mrvl,nfc-uart" for UART devices - "mrvl,nfc-i2c" for I2C devices + - "mrvl,nfc-spi" for SPI devices Optional SoC specific properties: - pinctrl-names: Contains only one value - "default". @@ -59,3 +60,27 @@ Example (for ARM-based BeagleBoard Black with 88W8887 on I2C1): reset-n-io = <&gpio3 19 0>; }; }; + + +Example (for ARM-based BeagleBoard Black on SPI0): + +&spi0 { + + mrvlnfcspi0: spi@0 { + compatible = "mrvl,nfc-spi"; + + reg = <0>; + + /* SPI Bus configuration */ + spi-max-frequency = <3000000>; + spi-cpha; + spi-cpol; + + /* SPI INT configuration */ + interrupt-parent = <&gpio1>; + interrupts = <17 0>; + + /* Reset IO */ + reset-n-io = <&gpio3 19 0>; + }; +}; diff --git a/drivers/nfc/nfcmrvl/Kconfig b/drivers/nfc/nfcmrvl/Kconfig index e18a979bb6d3..444ca94697d9 100644 --- a/drivers/nfc/nfcmrvl/Kconfig +++ b/drivers/nfc/nfcmrvl/Kconfig @@ -42,3 +42,13 @@ config NFC_MRVL_I2C Say Y here to compile support for Marvell NFC-over-I2C driver into the kernel or say M to compile it as module. +config NFC_MRVL_SPI + tristate "Marvell NFC-over-SPI driver" + depends on NFC_MRVL && SPI + help + Marvell NFC-over-SPI driver. + + This driver provides support for Marvell NFC-over-SPI devices. + + Say Y here to compile support for Marvell NFC-over-SPI driver + into the kernel or say M to compile it as module. diff --git a/drivers/nfc/nfcmrvl/Makefile b/drivers/nfc/nfcmrvl/Makefile index 895866a3ebc6..fa07c7806492 100644 --- a/drivers/nfc/nfcmrvl/Makefile +++ b/drivers/nfc/nfcmrvl/Makefile @@ -13,3 +13,6 @@ obj-$(CONFIG_NFC_MRVL_UART) += nfcmrvl_uart.o nfcmrvl_i2c-y += i2c.o obj-$(CONFIG_NFC_MRVL_I2C) += nfcmrvl_i2c.o + +nfcmrvl_spi-y += spi.o +obj-$(CONFIG_NFC_MRVL_SPI) += nfcmrvl_spi.o diff --git a/drivers/nfc/nfcmrvl/main.c b/drivers/nfc/nfcmrvl/main.c index 0c27de60a6bd..8079ae0de21e 100644 --- a/drivers/nfc/nfcmrvl/main.c +++ b/drivers/nfc/nfcmrvl/main.c @@ -132,7 +132,11 @@ struct nfcmrvl_private *nfcmrvl_nci_register_dev(enum nfcmrvl_phy phy, nfc_err(dev, "failed to request reset_n io\n"); } - headroom = tailroom = 0; + if (phy == NFCMRVL_PHY_SPI) { + headroom = NCI_SPI_HDR_LEN; + tailroom = 1; + } else + headroom = tailroom = 0; if (priv->config.hci_muxed) headroom += NFCMRVL_HCI_EVENT_HEADER_SIZE; diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c new file mode 100644 index 000000000000..358660acd54a --- /dev/null +++ b/drivers/nfc/nfcmrvl/spi.c @@ -0,0 +1,228 @@ +/** + * Marvell NFC-over-SPI driver: SPI interface related functions + * + * Copyright (C) 2015, Marvell International Ltd. + * + * This software file (the "File") is distributed by Marvell International + * Ltd. under the terms of the GNU General Public License Version 2, June 1991 + * (the "License"). You may use, redistribute and/or modify this File in + * accordance with the terms and conditions of the License, a copy of which + * is available on the worldwide web at + * http://www.gnu.org/licenses/old-licenses/gpl-2.0.txt. + * + * THE FILE IS DISTRIBUTED AS-IS, WITHOUT WARRANTY OF ANY KIND, AND THE + * IMPLIED WARRANTIES OF MERCHANTABILITY OR FITNESS FOR A PARTICULAR PURPOSE + * ARE EXPRESSLY DISCLAIMED. The License provides additional details about + * this warranty disclaimer. + **/ + +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include +#include "nfcmrvl.h" + +#define SPI_WAIT_HANDSHAKE 1 + +struct nfcmrvl_spi_drv_data { + unsigned long flags; + struct spi_device *spi; + struct nci_spi *nci_spi; + struct completion handshake_completion; + struct nfcmrvl_private *priv; +}; + +static irqreturn_t nfcmrvl_spi_int_irq_thread_fn(int irq, void *drv_data_ptr) +{ + struct nfcmrvl_spi_drv_data *drv_data = drv_data_ptr; + struct sk_buff *skb; + + /* + * Special case where we are waiting for SPI_INT deassertion to start a + * transfer. + */ + if (test_and_clear_bit(SPI_WAIT_HANDSHAKE, &drv_data->flags)) { + complete(&drv_data->handshake_completion); + return IRQ_HANDLED; + } + + /* Normal case, SPI_INT deasserted by slave to trigger a master read */ + + skb = nci_spi_read(drv_data->nci_spi); + if (!skb) { + nfc_err(&drv_data->spi->dev, "failed to read spi packet"); + return IRQ_HANDLED; + } + + if (nfcmrvl_nci_recv_frame(drv_data->priv, skb) < 0) + nfc_err(&drv_data->spi->dev, "corrupted RX packet"); + + return IRQ_HANDLED; +} + +static int nfcmrvl_spi_nci_open(struct nfcmrvl_private *priv) +{ + return 0; +} + +static int nfcmrvl_spi_nci_close(struct nfcmrvl_private *priv) +{ + return 0; +} + +static int nfcmrvl_spi_nci_send(struct nfcmrvl_private *priv, + struct sk_buff *skb) +{ + struct nfcmrvl_spi_drv_data *drv_data = priv->drv_data; + int err; + + /* Reinit completion for slave handshake */ + reinit_completion(&drv_data->handshake_completion); + set_bit(SPI_WAIT_HANDSHAKE, &drv_data->flags); + + /* + * Append a dummy byte at the end of SPI frame. This is due to a + * specific DMA implementation in the controller + */ + skb_put(skb, 1); + + /* Send the SPI packet */ + err = nci_spi_send(drv_data->nci_spi, &drv_data->handshake_completion, + skb); + if (err != 0) { + nfc_err(priv->dev, "spi_send failed %d", err); + kfree_skb(skb); + } + return err; +} + +static void nfcmrvl_spi_nci_update_config(struct nfcmrvl_private *priv, + const void *param) +{ + struct nfcmrvl_spi_drv_data *drv_data = priv->drv_data; + const struct nfcmrvl_fw_spi_config *config = param; + + drv_data->nci_spi->xfer_speed_hz = config->clk; +} + +static struct nfcmrvl_if_ops spi_ops = { + .nci_open = nfcmrvl_spi_nci_open, + .nci_close = nfcmrvl_spi_nci_close, + .nci_send = nfcmrvl_spi_nci_send, + .nci_update_config = nfcmrvl_spi_nci_update_config, +}; + +static int nfcmrvl_spi_parse_dt(struct device_node *node, + struct nfcmrvl_platform_data *pdata) +{ + int ret; + + ret = nfcmrvl_parse_dt(node, pdata); + if (ret < 0) { + pr_err("Failed to get generic entries\n"); + return ret; + } + + ret = irq_of_parse_and_map(node, 0); + if (ret < 0) { + pr_err("Unable to get irq, error: %d\n", ret); + return ret; + } + pdata->irq = ret; + + return 0; +} + +static int nfcmrvl_spi_probe(struct spi_device *spi) +{ + struct nfcmrvl_platform_data *pdata; + struct nfcmrvl_platform_data config; + struct nfcmrvl_spi_drv_data *drv_data; + int ret = 0; + + drv_data = devm_kzalloc(&spi->dev, sizeof(*drv_data), GFP_KERNEL); + if (!drv_data) + return -ENOMEM; + + drv_data->spi = spi; + drv_data->priv = NULL; + spi_set_drvdata(spi, drv_data); + + pdata = spi->dev.platform_data; + + if (!pdata && spi->dev.of_node) + if (nfcmrvl_spi_parse_dt(spi->dev.of_node, &config) == 0) + pdata = &config; + + if (!pdata) + return -EINVAL; + + ret = devm_request_threaded_irq(&drv_data->spi->dev, pdata->irq, + NULL, nfcmrvl_spi_int_irq_thread_fn, + IRQF_TRIGGER_FALLING | IRQF_ONESHOT, + "nfcmrvl_spi_int", drv_data); + if (ret < 0) { + nfc_err(&drv_data->spi->dev, "Unable to register IRQ handler"); + return -ENODEV; + } + + drv_data->priv = nfcmrvl_nci_register_dev(NFCMRVL_PHY_SPI, + drv_data, &spi_ops, + &drv_data->spi->dev, + pdata); + if (IS_ERR(drv_data->priv)) + return PTR_ERR(drv_data->priv); + + drv_data->priv->support_fw_dnld = true; + + drv_data->nci_spi = nci_spi_allocate_spi(drv_data->spi, 0, 10, + drv_data->priv->ndev); + + /* Init completion for slave handshake */ + init_completion(&drv_data->handshake_completion); + return 0; +} + +static int nfcmrvl_spi_remove(struct spi_device *spi) +{ + struct nfcmrvl_spi_drv_data *drv_data = spi_get_drvdata(spi); + + nfcmrvl_nci_unregister_dev(drv_data->priv); + return 0; +} + +static const struct of_device_id of_nfcmrvl_spi_match[] = { + { .compatible = "mrvl,nfc-spi", }, + {}, +}; +MODULE_DEVICE_TABLE(of, of_nfcmrvl_spi_match); + +static const struct spi_device_id nfcmrvl_spi_id_table[] = { + { "nfcmrvl_spi", 0 }, + { } +}; +MODULE_DEVICE_TABLE(spi, nfcmrvl_spi_id_table); + +static struct spi_driver nfcmrvl_spi_driver = { + .probe = nfcmrvl_spi_probe, + .remove = nfcmrvl_spi_remove, + .id_table = nfcmrvl_spi_id_table, + .driver = { + .name = "nfcmrvl_spi", + .owner = THIS_MODULE, + .of_match_table = of_match_ptr(of_nfcmrvl_spi_match), + }, +}; + +module_spi_driver(nfcmrvl_spi_driver); + +MODULE_AUTHOR("Marvell International Ltd."); +MODULE_DESCRIPTION("Marvell NFC-over-SPI driver"); +MODULE_LICENSE("GPL v2"); -- cgit v1.2.3 From d8e018c0b3211902af1bfb5d5b280f955a4633b7 Mon Sep 17 00:00:00 2001 From: Vincent Cuissard Date: Mon, 26 Oct 2015 10:27:45 +0100 Subject: NFC: nfcmrvl: update device tree bindings for Marvell NFC Align NFC bindgins to use marvell instead of mrvl. Signed-off-by: Vincent Cuissard Signed-off-by: Samuel Ortiz --- Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt | 12 ++++++------ drivers/nfc/nfcmrvl/i2c.c | 2 +- drivers/nfc/nfcmrvl/spi.c | 2 +- drivers/nfc/nfcmrvl/uart.c | 10 +++++++--- 4 files changed, 15 insertions(+), 11 deletions(-) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt index 41058fcbd9ae..76df9173825a 100644 --- a/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt +++ b/Documentation/devicetree/bindings/net/nfc/nfcmrvl.txt @@ -2,9 +2,9 @@ Required properties: - compatible: Should be: - - "mrvl,nfc-uart" for UART devices - - "mrvl,nfc-i2c" for I2C devices - - "mrvl,nfc-spi" for SPI devices + - "marvell,nfc-uart" or "mrvl,nfc-uart" for UART devices + - "marvell,nfc-i2c" for I2C devices + - "marvell,nfc-spi" for SPI devices Optional SoC specific properties: - pinctrl-names: Contains only one value - "default". @@ -28,7 +28,7 @@ Example (for ARM-based BeagleBoard Black with 88W8887 on UART5): status = "okay"; nfcmrvluart: nfcmrvluart@5 { - compatible = "mrvl,nfc-uart"; + compatible = "marvell,nfc-uart"; reset-n-io = <&gpio3 16 0>; @@ -45,7 +45,7 @@ Example (for ARM-based BeagleBoard Black with 88W8887 on I2C1): clock-frequency = <400000>; nfcmrvli2c0: i2c@1 { - compatible = "mrvl,nfc-i2c"; + compatible = "marvell,nfc-i2c"; reg = <0x8>; @@ -67,7 +67,7 @@ Example (for ARM-based BeagleBoard Black on SPI0): &spi0 { mrvlnfcspi0: spi@0 { - compatible = "mrvl,nfc-spi"; + compatible = "marvell,nfc-spi"; reg = <0>; diff --git a/drivers/nfc/nfcmrvl/i2c.c b/drivers/nfc/nfcmrvl/i2c.c index 7a44025bdaad..78b7aa835c81 100644 --- a/drivers/nfc/nfcmrvl/i2c.c +++ b/drivers/nfc/nfcmrvl/i2c.c @@ -261,7 +261,7 @@ static int nfcmrvl_i2c_remove(struct i2c_client *client) static const struct of_device_id of_nfcmrvl_i2c_match[] = { - { .compatible = "mrvl,nfc-i2c", }, + { .compatible = "marvell,nfc-i2c", }, {}, }; MODULE_DEVICE_TABLE(of, of_nfcmrvl_i2c_match); diff --git a/drivers/nfc/nfcmrvl/spi.c b/drivers/nfc/nfcmrvl/spi.c index 358660acd54a..a7faa0bcc01e 100644 --- a/drivers/nfc/nfcmrvl/spi.c +++ b/drivers/nfc/nfcmrvl/spi.c @@ -199,7 +199,7 @@ static int nfcmrvl_spi_remove(struct spi_device *spi) } static const struct of_device_id of_nfcmrvl_spi_match[] = { - { .compatible = "mrvl,nfc-spi", }, + { .compatible = "marvell,nfc-spi", }, {}, }; MODULE_DEVICE_TABLE(of, of_nfcmrvl_spi_match); diff --git a/drivers/nfc/nfcmrvl/uart.c b/drivers/nfc/nfcmrvl/uart.c index 4dccee2566cf..f3d041c4f249 100644 --- a/drivers/nfc/nfcmrvl/uart.c +++ b/drivers/nfc/nfcmrvl/uart.c @@ -75,9 +75,13 @@ static int nfcmrvl_uart_parse_dt(struct device_node *node, struct device_node *matched_node; int ret; - matched_node = of_find_compatible_node(node, NULL, "mrvl,nfc-uart"); - if (!matched_node) - return -ENODEV; + matched_node = of_find_compatible_node(node, NULL, "marvell,nfc-uart"); + if (!matched_node) { + matched_node = of_find_compatible_node(node, NULL, + "mrvl,nfc-uart"); + if (!matched_node) + return -ENODEV; + } ret = nfcmrvl_parse_dt(matched_node, pdata); if (ret < 0) { -- cgit v1.2.3 From 6d08f617872cc048173d59f1ce4660b030bab5a6 Mon Sep 17 00:00:00 2001 From: yankejian Date: Tue, 27 Oct 2015 19:16:34 +0800 Subject: net: hisilicon: updates HNS config and documents updates the bindings documents and dtsi file according to the review comments[https://lkml.org/lkml/2015/9/21/670] from Rob Herring Acked-by: Rob Herring Signed-off-by: yankejian Signed-off-by: huangdaode Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt | 2 +- arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi | 8 +++----- 2 files changed, 4 insertions(+), 6 deletions(-) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt index 9940aa02b8bd..9c23fdf25018 100644 --- a/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt +++ b/Documentation/devicetree/bindings/net/hisilicon-hns-mdio.txt @@ -12,7 +12,7 @@ Example: mdio@803c0000 { #address-cells = <1>; #size-cells = <0>; - compatible = "hisilicon,mdio","hisilicon,hns-mdio"; + compatible = "hisilicon,hns-mdio","hisilicon,mdio"; reg = <0x0 0x803c0000 0x0 0x10000>; ethernet-phy@0 { diff --git a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi index 35005866a34e..606dd5a05c2d 100644 --- a/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi +++ b/arch/arm64/boot/dts/hisilicon/hip05_hns.dtsi @@ -13,14 +13,12 @@ soc0: soc@000000000 { reg = <0x0 0x803c0000 0x0 0x10000 0x0 0x80000000 0x0 0x10000>; - soc0_phy4: ethernet-phy@4 { + soc0_phy0: ethernet-phy@0 { reg = <0x0>; - device_type = "ethernet-phy"; compatible = "ethernet-phy-ieee802.3-c22"; }; - soc0_phy5: ethernet-phy@5 { + soc0_phy1: ethernet-phy@1 { reg = <0x1>; - device_type = "ethernet-phy"; compatible = "ethernet-phy-ieee802.3-c22"; }; }; @@ -37,7 +35,7 @@ soc0: soc@000000000 { 0x0 0xc7000000 0x0 0x60000 >; - phy-handle = <0 0 0 0 &soc0_phy4 &soc0_phy5 0 0>; + phy-handle = <0 0 0 0 &soc0_phy0 &soc0_phy1 0 0>; interrupts = < /* [14] ge fifo err 8 / xge 6**/ 149 0x4 150 0x4 151 0x4 152 0x4 -- cgit v1.2.3 From 6ccbe6b248ef8cc31477a388ea9841b56030bea9 Mon Sep 17 00:00:00 2001 From: Iyappan Subramanian Date: Mon, 26 Oct 2015 15:25:16 -0700 Subject: Documentation: dts: xgene: Add TX/RX delay field Signed-off-by: Iyappan Subramanian Signed-off-by: David S. Miller --- Documentation/devicetree/bindings/net/apm-xgene-enet.txt | 10 ++++++++++ 1 file changed, 10 insertions(+) (limited to 'Documentation') diff --git a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt index f55aa280d34f..078060a97f95 100644 --- a/Documentation/devicetree/bindings/net/apm-xgene-enet.txt +++ b/Documentation/devicetree/bindings/net/apm-xgene-enet.txt @@ -37,6 +37,14 @@ Required properties for ethernet interfaces that have external PHY: Optional properties: - status: Should be "ok" or "disabled" for enabled/disabled. Default is "ok". +- tx-delay: Delay value for RGMII bridge TX clock. + Valid values are between 0 to 7, that maps to + 417, 717, 1020, 1321, 1611, 1913, 2215, 2514 ps + Default value is 4, which corresponds to 1611 ps +- rx-delay: Delay value for RGMII bridge RX clock. + Valid values are between 0 to 7, that maps to + 273, 589, 899, 1222, 1480, 1806, 2147, 2464 ps + Default value is 2, which corresponds to 899 ps Example: menetclk: menetclk { @@ -72,5 +80,7 @@ Example: /* Board-specific peripheral configurations */ &menet { + tx-delay = <4>; + rx-delay = <2>; status = "ok"; }; -- cgit v1.2.3 From 741af0053b43d8b9a688a12c57ece62338616ae8 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 28 Oct 2015 10:16:54 +0100 Subject: switchdev: Add support for flood control Allow devices supporting this feature to control the flooding of unknown unicast traffic, by making switchdev infrastructure propagate this setting to the switch driver. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 3 +++ net/switchdev/switchdev.c | 5 ++++- 2 files changed, 7 insertions(+), 1 deletion(-) (limited to 'Documentation') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index 0714fe555016..ce510e1a3e87 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -298,6 +298,9 @@ packets up to the bridge driver for flooding. This is not ideal as the number of ports scale in the L2 domain as the device is much more efficient at flooding packets that software. +If supported by the device, flood control can be offloaded to it, preventing +certain netdevs from flooding unicast traffic for which there is no FDB entry. + IGMP Snooping ^^^^^^^^^^^^^ diff --git a/net/switchdev/switchdev.c b/net/switchdev/switchdev.c index 1eb76956b439..8950d39af341 100644 --- a/net/switchdev/switchdev.c +++ b/net/switchdev/switchdev.c @@ -746,7 +746,7 @@ int switchdev_port_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, .id = SWITCHDEV_ATTR_ID_PORT_BRIDGE_FLAGS, }; u16 mode = BRIDGE_MODE_UNDEF; - u32 mask = BR_LEARNING | BR_LEARNING_SYNC; + u32 mask = BR_LEARNING | BR_LEARNING_SYNC | BR_FLOOD; int err; err = switchdev_port_attr_get(dev, &attr); @@ -817,6 +817,9 @@ static int switchdev_port_br_setlink_protinfo(struct net_device *dev, err = switchdev_port_br_setflag(dev, attr, BR_LEARNING_SYNC); break; + case IFLA_BRPORT_UNICAST_FLOOD: + err = switchdev_port_br_setflag(dev, attr, BR_FLOOD); + break; default: err = -EOPNOTSUPP; break; -- cgit v1.2.3 From 371e59adcebf9953385bf46d5325ac39a53c5520 Mon Sep 17 00:00:00 2001 From: Ido Schimmel Date: Wed, 28 Oct 2015 10:16:55 +0100 Subject: switchdev: Make flood to CPU optional In certain use cases it is not always desirable for the switch device to flood traffic to CPU port. Instead, only certain packet types (e.g. STP, LACP) should be trapped to it. Signed-off-by: Ido Schimmel Signed-off-by: Jiri Pirko Signed-off-by: David S. Miller --- Documentation/networking/switchdev.txt | 4 ++-- 1 file changed, 2 insertions(+), 2 deletions(-) (limited to 'Documentation') diff --git a/Documentation/networking/switchdev.txt b/Documentation/networking/switchdev.txt index ce510e1a3e87..91994134efca 100644 --- a/Documentation/networking/switchdev.txt +++ b/Documentation/networking/switchdev.txt @@ -278,8 +278,8 @@ Flooding L2 domain For a given L2 VLAN domain, the switch device should flood multicast/broadcast and unknown unicast packets to all ports in domain, if allowed by port's current STP state. The switch driver, knowing which ports are within which -vlan L2 domain, can program the switch device for flooding. The packet should -also be sent to the port netdev for processing by the bridge driver. The +vlan L2 domain, can program the switch device for flooding. The packet may +be sent to the port netdev for processing by the bridge driver. The bridge should not reflood the packet to the same ports the device flooded, otherwise there will be duplicate packets on the wire. -- cgit v1.2.3