diff options
Diffstat (limited to 'Documentation')
| -rw-r--r-- | Documentation/DocBook/80211.tmpl | 1 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/broadcom-systemport.txt | 29 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt | 23 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/micrel-ksz9021.txt | 49 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/micrel-ksz90x1.txt | 83 | ||||
| -rw-r--r-- | Documentation/devicetree/bindings/net/via-rhine.txt | 17 | ||||
| -rw-r--r-- | Documentation/driver-model/devres.txt | 5 | ||||
| -rw-r--r-- | Documentation/networking/bonding.txt | 44 | ||||
| -rw-r--r-- | Documentation/networking/filter.txt | 171 |
9 files changed, 361 insertions, 61 deletions
diff --git a/Documentation/DocBook/80211.tmpl b/Documentation/DocBook/80211.tmpl index 044b76436e83..d9b9416c989f 100644 --- a/Documentation/DocBook/80211.tmpl +++ b/Documentation/DocBook/80211.tmpl @@ -100,6 +100,7 @@ !Finclude/net/cfg80211.h wdev_priv !Finclude/net/cfg80211.h ieee80211_iface_limit !Finclude/net/cfg80211.h ieee80211_iface_combination +!Finclude/net/cfg80211.h cfg80211_check_combinations </chapter> <chapter> <title>Actions and configuration</title> diff --git a/Documentation/devicetree/bindings/net/broadcom-systemport.txt b/Documentation/devicetree/bindings/net/broadcom-systemport.txt new file mode 100644 index 000000000000..1b7600e022dd --- /dev/null +++ b/Documentation/devicetree/bindings/net/broadcom-systemport.txt @@ -0,0 +1,29 @@ +* Broadcom BCM7xxx Ethernet Systemport Controller (SYSTEMPORT) + +Required properties: +- compatible: should be one of "brcm,systemport-v1.00" or "brcm,systemport" +- reg: address and length of the register set for the device. +- interrupts: interrupts for the device, first cell must be for the the rx + interrupts, and the second cell should be for the transmit queues +- local-mac-address: Ethernet MAC address (48 bits) of this adapter +- phy-mode: Should be a string describing the PHY interface to the + Ethernet switch/PHY, see Documentation/devicetree/bindings/net/ethernet.txt +- fixed-link: see Documentation/devicetree/bindings/net/fsl-tsec-phy.txt for + the property specific details + +Optional properties: +- systemport,num-tier2-arb: number of tier 2 arbiters, an integer +- systemport,num-tier1-arb: number of tier 1 arbiters, an integer +- systemport,num-txq: number of HW transmit queues, an integer +- systemport,num-rxq: number of HW receive queues, an integer + +Example: +ethernet@f04a0000 { + compatible = "brcm,systemport-v1.00"; + reg = <0xf04a0000 0x4650>; + local-mac-address = [ 00 11 22 33 44 55 ]; + fixed-link = <0 1 1000 0 0>; + phy-mode = "gmii"; + interrupts = <0x0 0x16 0x0>, + <0x0 0x17 0x0>; +}; diff --git a/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt b/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt new file mode 100644 index 000000000000..d3bbdded4cbe --- /dev/null +++ b/Documentation/devicetree/bindings/net/ieee802154/at86rf230.txt @@ -0,0 +1,23 @@ +* AT86RF230 IEEE 802.15.4 * + +Required properties: + - compatible: should be "atmel,at86rf230", "atmel,at86rf231", + "atmel,at86rf233" or "atmel,at86rf212" + - spi-max-frequency: maximal bus speed, should be set to 7500000 depends + sync or async operation mode + - reg: the chipselect index + - interrupts: the interrupt generated by the device + +Optional properties: + - reset-gpio: GPIO spec for the rstn pin + - sleep-gpio: GPIO spec for the slp_tr pin + +Example: + + at86rf231@0 { + compatible = "atmel,at86rf231"; + spi-max-frequency = <7500000>; + reg = <0>; + interrupts = <19 1>; + interrupt-parent = <&gpio3>; + }; diff --git a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt b/Documentation/devicetree/bindings/net/micrel-ksz9021.txt deleted file mode 100644 index 997a63f1aea1..000000000000 --- a/Documentation/devicetree/bindings/net/micrel-ksz9021.txt +++ /dev/null @@ -1,49 +0,0 @@ -Micrel KSZ9021 Gigabit Ethernet PHY - -Some boards require special tuning values, particularly when it comes to -clock delays. You can specify clock delay values by adding -micrel-specific properties to an Ethernet OF device node. - -All skew control options are specified in picoseconds. The minimum -value is 0, and the maximum value is 3000. - -Optional properties: - - rxc-skew-ps : Skew control of RXC pad - - rxdv-skew-ps : Skew control of RX CTL pad - - txc-skew-ps : Skew control of TXC pad - - txen-skew-ps : Skew control of TX_CTL pad - - rxd0-skew-ps : Skew control of RX data 0 pad - - rxd1-skew-ps : Skew control of RX data 1 pad - - rxd2-skew-ps : Skew control of RX data 2 pad - - rxd3-skew-ps : Skew control of RX data 3 pad - - txd0-skew-ps : Skew control of TX data 0 pad - - txd1-skew-ps : Skew control of TX data 1 pad - - txd2-skew-ps : Skew control of TX data 2 pad - - txd3-skew-ps : Skew control of TX data 3 pad - -Examples: - - /* Attach to an Ethernet device with autodetected PHY */ - &enet { - rxc-skew-ps = <3000>; - rxdv-skew-ps = <0>; - txc-skew-ps = <3000>; - txen-skew-ps = <0>; - status = "okay"; - }; - - /* Attach to an explicitly-specified PHY */ - mdio { - phy0: ethernet-phy@0 { - rxc-skew-ps = <3000>; - rxdv-skew-ps = <0>; - txc-skew-ps = <3000>; - txen-skew-ps = <0>; - reg = <0>; - }; - }; - ethernet@70000 { - status = "okay"; - phy = <&phy0>; - phy-mode = "rgmii-id"; - }; diff --git a/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt new file mode 100644 index 000000000000..692076fda0e5 --- /dev/null +++ b/Documentation/devicetree/bindings/net/micrel-ksz90x1.txt @@ -0,0 +1,83 @@ +Micrel KSZ9021/KSZ9031 Gigabit Ethernet PHY + +Some boards require special tuning values, particularly when it comes to +clock delays. You can specify clock delay values by adding +micrel-specific properties to an Ethernet OF device node. + +Note that these settings are applied after any phy-specific fixup from +phy_fixup_list (see phy_init_hw() from drivers/net/phy/phy_device.c), +and therefore may overwrite them. + +KSZ9021: + + All skew control options are specified in picoseconds. The minimum + value is 0, the maximum value is 3000, and it is incremented by 200ps + steps. + + Optional properties: + + - rxc-skew-ps : Skew control of RXC pad + - rxdv-skew-ps : Skew control of RX CTL pad + - txc-skew-ps : Skew control of TXC pad + - txen-skew-ps : Skew control of TX CTL pad + - rxd0-skew-ps : Skew control of RX data 0 pad + - rxd1-skew-ps : Skew control of RX data 1 pad + - rxd2-skew-ps : Skew control of RX data 2 pad + - rxd3-skew-ps : Skew control of RX data 3 pad + - txd0-skew-ps : Skew control of TX data 0 pad + - txd1-skew-ps : Skew control of TX data 1 pad + - txd2-skew-ps : Skew control of TX data 2 pad + - txd3-skew-ps : Skew control of TX data 3 pad + +KSZ9031: + + All skew control options are specified in picoseconds. The minimum + value is 0, and the maximum is property-dependent. The increment + step is 60ps. + + Optional properties: + + Maximum value of 1860: + + - rxc-skew-ps : Skew control of RX clock pad + - txc-skew-ps : Skew control of TX clock pad + + Maximum value of 900: + + - rxdv-skew-ps : Skew control of RX CTL pad + - txen-skew-ps : Skew control of TX CTL pad + - rxd0-skew-ps : Skew control of RX data 0 pad + - rxd1-skew-ps : Skew control of RX data 1 pad + - rxd2-skew-ps : Skew control of RX data 2 pad + - rxd3-skew-ps : Skew control of RX data 3 pad + - txd0-skew-ps : Skew control of TX data 0 pad + - txd1-skew-ps : Skew control of TX data 1 pad + - txd2-skew-ps : Skew control of TX data 2 pad + - txd3-skew-ps : Skew control of TX data 3 pad + +Examples: + + /* Attach to an Ethernet device with autodetected PHY */ + &enet { + rxc-skew-ps = <3000>; + rxdv-skew-ps = <0>; + txc-skew-ps = <3000>; + txen-skew-ps = <0>; + status = "okay"; + }; + + /* Attach to an explicitly-specified PHY */ + mdio { + phy0: ethernet-phy@0 { + rxc-skew-ps = <3000>; + rxdv-skew-ps = <0>; + txc-skew-ps = <3000>; + txen-skew-ps = <0>; + reg = <0>; + }; + }; + ethernet@70000 { + status = "okay"; + phy = <&phy0>; + phy-mode = "rgmii-id"; + }; diff --git a/Documentation/devicetree/bindings/net/via-rhine.txt b/Documentation/devicetree/bindings/net/via-rhine.txt new file mode 100644 index 000000000000..334eca2bf937 --- /dev/null +++ b/Documentation/devicetree/bindings/net/via-rhine.txt @@ -0,0 +1,17 @@ +* VIA Rhine 10/100 Network Controller + +Required properties: +- compatible : Should be "via,vt8500-rhine" for integrated + Rhine controllers found in VIA VT8500, WonderMedia WM8950 + and similar. These are listed as 1106:3106 rev. 0x84 on the + virtual PCI bus under vendor-provided kernels +- reg : Address and length of the io space +- interrupts : Should contain the controller interrupt line + +Examples: + +ethernet@d8004000 { + compatible = "via,vt8500-rhine"; + reg = <0xd8004000 0x100>; + interrupts = <10>; +}; diff --git a/Documentation/driver-model/devres.txt b/Documentation/driver-model/devres.txt index 4f7897e99cba..c74e04494ade 100644 --- a/Documentation/driver-model/devres.txt +++ b/Documentation/driver-model/devres.txt @@ -308,3 +308,8 @@ SLAVE DMA ENGINE SPI devm_spi_register_master() + +MDIO + devm_mdiobus_alloc() + devm_mdiobus_alloc_size() + devm_mdiobus_free() diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index a383c00392d0..9c723ecd0025 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -585,13 +585,19 @@ mode balance-tlb or 5 Adaptive transmit load balancing: channel bonding that - does not require any special switch support. The - outgoing traffic is distributed according to the - current load (computed relative to the speed) on each - slave. Incoming traffic is received by the current - slave. If the receiving slave fails, another slave - takes over the MAC address of the failed receiving - slave. + does not require any special switch support. + + In tlb_dynamic_lb=1 mode; the outgoing traffic is + distributed according to the current load (computed + relative to the speed) on each slave. + + In tlb_dynamic_lb=0 mode; the load balancing based on + current load is disabled and the load is distributed + only using the hash distribution. + + Incoming traffic is received by the current slave. + If the receiving slave fails, another slave takes over + the MAC address of the failed receiving slave. Prerequisite: @@ -736,6 +742,28 @@ primary_reselect This option was added for bonding version 3.6.0. +tlb_dynamic_lb + + Specifies if dynamic shuffling of flows is enabled in tlb + mode. The value has no effect on any other modes. + + The default behavior of tlb mode is to shuffle active flows across + slaves based on the load in that interval. This gives nice lb + characteristics but can cause packet reordering. If re-ordering is + a concern use this variable to disable flow shuffling and rely on + load balancing provided solely by the hash distribution. + xmit-hash-policy can be used to select the appropriate hashing for + the setup. + + The sysfs entry can be used to change the setting per bond device + and the initial value is derived from the module parameter. The + sysfs entry is allowed to be changed only if the bond device is + down. + + The default value is "1" that enables flow shuffling while value "0" + disables it. This option was added in bonding driver 3.7.1 + + updelay Specifies the time, in milliseconds, to wait before enabling a @@ -769,7 +797,7 @@ use_carrier xmit_hash_policy Selects the transmit hash policy to use for slave selection in - balance-xor and 802.3ad modes. Possible values are: + balance-xor, 802.3ad, and tlb modes. Possible values are: layer2 diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index 81f940f4e884..748fd385535d 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -281,6 +281,7 @@ Possible BPF extensions are shown in the following table: cpu raw_smp_processor_id() vlan_tci vlan_tx_tag_get(skb) vlan_pr vlan_tx_tag_present(skb) + rand prandom_u32() These extensions can also be prefixed with '#'. Examples for low-level BPF: @@ -308,6 +309,18 @@ Examples for low-level BPF: ret #-1 drop: ret #0 +** icmp random packet sampling, 1 in 4 + ldh [12] + jne #0x800, drop + ldb [23] + jneq #1, drop + # get a random uint32 number + ld rand + mod #4 + jneq #1, drop + ret #-1 + drop: ret #0 + ** SECCOMP filter example: ld [4] /* offsetof(struct seccomp_data, arch) */ @@ -600,7 +613,7 @@ Some core changes of the new internal format: Therefore, BPF calling convention is defined as: - * R0 - return value from in-kernel function + * R0 - return value from in-kernel function, and exit value for BPF program * R1 - R5 - arguments from BPF program to in-kernel function * R6 - R9 - callee saved registers that in-kernel function will preserve * R10 - read-only frame pointer to access stack @@ -646,9 +659,140 @@ Some core changes of the new internal format: - Introduces bpf_call insn and register passing convention for zero overhead calls from/to other kernel functions: - After a kernel function call, R1 - R5 are reset to unreadable and R0 has a - return type of the function. Since R6 - R9 are callee saved, their state is - preserved across the call. + Before an in-kernel function call, the internal BPF program needs to + place function arguments into R1 to R5 registers to satisfy calling + convention, then the interpreter will take them from registers and pass + to in-kernel function. If R1 - R5 registers are mapped to CPU registers + that are used for argument passing on given architecture, the JIT compiler + doesn't need to emit extra moves. Function arguments will be in the correct + registers and BPF_CALL instruction will be JITed as single 'call' HW + instruction. This calling convention was picked to cover common call + situations without performance penalty. + + After an in-kernel function call, R1 - R5 are reset to unreadable and R0 has + a return value of the function. Since R6 - R9 are callee saved, their state + is preserved across the call. + + For example, consider three C functions: + + u64 f1() { return (*_f2)(1); } + u64 f2(u64 a) { return f3(a + 1, a); } + u64 f3(u64 a, u64 b) { return a - b; } + + GCC can compile f1, f3 into x86_64: + + f1: + movl $1, %edi + movq _f2(%rip), %rax + jmp *%rax + f3: + movq %rdi, %rax + subq %rsi, %rax + ret + + Function f2 in BPF may look like: + + f2: + bpf_mov R2, R1 + bpf_add R1, 1 + bpf_call f3 + bpf_exit + + If f2 is JITed and the pointer stored to '_f2'. The calls f1 -> f2 -> f3 and + returns will be seamless. Without JIT, __sk_run_filter() interpreter needs to + be used to call into f2. + + For practical reasons all BPF programs have only one argument 'ctx' which is + already placed into R1 (e.g. on __sk_run_filter() startup) and the programs + can call kernel functions with up to 5 arguments. Calls with 6 or more arguments + are currently not supported, but these restrictions can be lifted if necessary + in the future. + + On 64-bit architectures all register map to HW registers one to one. For + example, x86_64 JIT compiler can map them as ... + + R0 - rax + R1 - rdi + R2 - rsi + R3 - rdx + R4 - rcx + R5 - r8 + R6 - rbx + R7 - r13 + R8 - r14 + R9 - r15 + R10 - rbp + + ... since x86_64 ABI mandates rdi, rsi, rdx, rcx, r8, r9 for argument passing + and rbx, r12 - r15 are callee saved. + + Then the following internal BPF pseudo-program: + + bpf_mov R6, R1 /* save ctx */ + bpf_mov R2, 2 + bpf_mov R3, 3 + bpf_mov R4, 4 + bpf_mov R5, 5 + bpf_call foo + bpf_mov R7, R0 /* save foo() return value */ + bpf_mov R1, R6 /* restore ctx for next call */ + bpf_mov R2, 6 + bpf_mov R3, 7 + bpf_mov R4, 8 + bpf_mov R5, 9 + bpf_call bar + bpf_add R0, R7 + bpf_exit + + After JIT to x86_64 may look like: + + push %rbp + mov %rsp,%rbp + sub $0x228,%rsp + mov %rbx,-0x228(%rbp) + mov %r13,-0x220(%rbp) + mov %rdi,%rbx + mov $0x2,%esi + mov $0x3,%edx + mov $0x4,%ecx + mov $0x5,%r8d + callq foo + mov %rax,%r13 + mov %rbx,%rdi + mov $0x2,%esi + mov $0x3,%edx + mov $0x4,%ecx + mov $0x5,%r8d + callq bar + add %r13,%rax + mov -0x228(%rbp),%rbx + mov -0x220(%rbp),%r13 + leaveq + retq + + Which is in this example equivalent in C to: + + u64 bpf_filter(u64 ctx) + { + return foo(ctx, 2, 3, 4, 5) + bar(ctx, 6, 7, 8, 9); + } + + In-kernel functions foo() and bar() with prototype: u64 (*)(u64 arg1, u64 + arg2, u64 arg3, u64 arg4, u64 arg5); will receive arguments in proper + registers and place their return value into '%rax' which is R0 in BPF. + Prologue and epilogue are emitted by JIT and are implicit in the + interpreter. R0-R5 are scratch registers, so BPF program needs to preserve + them across the calls as defined by calling convention. + + For example the following program is invalid: + + bpf_mov R1, 1 + bpf_call foo + bpf_mov R0, R1 + bpf_exit + + After the call the registers R1-R5 contain junk values and cannot be read. + In the future a BPF verifier can be used to validate internal BPF programs. Also in the new design, BPF is limited to 4096 insns, which means that any program will terminate quickly and will only call a fixed number of kernel @@ -663,6 +807,25 @@ A program, that is translated internally consists of the following elements: op:16, jt:8, jf:8, k:32 ==> op:8, a_reg:4, x_reg:4, off:16, imm:32 +So far 87 internal BPF instructions were implemented. 8-bit 'op' opcode field +has room for new instructions. Some of them may use 16/24/32 byte encoding. New +instructions must be multiple of 8 bytes to preserve backward compatibility. + +Internal BPF is a general purpose RISC instruction set. Not every register and +every instruction are used during translation from original BPF to new format. +For example, socket filters are not using 'exclusive add' instruction, but +tracing filters may do to maintain counters of events, for example. Register R9 +is not used by socket filters either, but more complex filters may be running +out of registers and would have to resort to spill/fill to stack. + +Internal BPF can used as generic assembler for last step performance +optimizations, socket filters and seccomp are using it as assembler. Tracing +filters may use it as assembler to generate code from kernel. In kernel usage +may not be bounded by security considerations, since generated internal BPF code +may be optimizing internal code path and not being exposed to the user space. +Safety of internal BPF can come from a verifier (TBD). In such use cases as +described, it may be used as safe instruction set. + Just like the original BPF, the new format runs within a controlled environment, is deterministic and the kernel can easily prove that. The safety of the program can be determined in two steps: first step does depth-first-search to disallow |