diff options
897 files changed, 48382 insertions, 19672 deletions
diff --git a/Documentation/devicetree/bindings/net/dsa/dsa.txt b/Documentation/devicetree/bindings/net/dsa/dsa.txt index cfe8f64eca4f..3ceeb8de1196 100644 --- a/Documentation/devicetree/bindings/net/dsa/dsa.txt +++ b/Documentation/devicetree/bindings/net/dsa/dsa.txt @@ -82,8 +82,6 @@ linked into one DSA cluster. switch0: switch0@0 { compatible = "marvell,mv88e6085"; - #address-cells = <1>; - #size-cells = <0>; reg = <0>; dsa,member = <0 0>; @@ -135,8 +133,6 @@ linked into one DSA cluster. switch1: switch1@0 { compatible = "marvell,mv88e6085"; - #address-cells = <1>; - #size-cells = <0>; reg = <0>; dsa,member = <0 1>; @@ -204,8 +200,6 @@ linked into one DSA cluster. switch2: switch2@0 { compatible = "marvell,mv88e6085"; - #address-cells = <1>; - #size-cells = <0>; reg = <0>; dsa,member = <0 2>; diff --git a/Documentation/devicetree/bindings/net/meson-dwmac.txt b/Documentation/devicetree/bindings/net/meson-dwmac.txt index 61cada22ae6c..1321bb194ed9 100644 --- a/Documentation/devicetree/bindings/net/meson-dwmac.txt +++ b/Documentation/devicetree/bindings/net/meson-dwmac.txt @@ -11,6 +11,7 @@ Required properties on all platforms: - "amlogic,meson8b-dwmac" - "amlogic,meson8m2-dwmac" - "amlogic,meson-gxbb-dwmac" + - "amlogic,meson-axg-dwmac" Additionally "snps,dwmac" and any applicable more detailed version number described in net/stmmac.txt should be used. diff --git a/Documentation/devicetree/bindings/net/microchip,lan78xx.txt b/Documentation/devicetree/bindings/net/microchip,lan78xx.txt new file mode 100644 index 000000000000..76786a0f6d3d --- /dev/null +++ b/Documentation/devicetree/bindings/net/microchip,lan78xx.txt @@ -0,0 +1,54 @@ +Microchip LAN78xx Gigabit Ethernet controller + +The LAN78XX devices are usually configured by programming their OTP or with +an external EEPROM, but some platforms (e.g. Raspberry Pi 3 B+) have neither. +The Device Tree properties, if present, override the OTP and EEPROM. + +Required properties: +- compatible: Should be one of "usb424,7800", "usb424,7801" or "usb424,7850". + +Optional properties: +- local-mac-address: see ethernet.txt +- mac-address: see ethernet.txt + +Optional properties of the embedded PHY: +- microchip,led-modes: a 0..4 element vector, with each element configuring + the operating mode of an LED. Omitted LEDs are turned off. Allowed values + are defined in "include/dt-bindings/net/microchip-lan78xx.h". + +Example: + +/* Based on the configuration for a Raspberry Pi 3 B+ */ +&usb { + usb-port@1 { + compatible = "usb424,2514"; + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + usb-port@1 { + compatible = "usb424,2514"; + reg = <1>; + #address-cells = <1>; + #size-cells = <0>; + + ethernet: ethernet@1 { + compatible = "usb424,7800"; + reg = <1>; + local-mac-address = [ 00 11 22 33 44 55 ]; + + mdio { + #address-cells = <0x1>; + #size-cells = <0x0>; + eth_phy: ethernet-phy@1 { + reg = <1>; + microchip,led-modes = < + LAN78XX_LINK_1000_ACTIVITY + LAN78XX_LINK_10_100_ACTIVITY + >; + }; + }; + }; + }; + }; +}; diff --git a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt index 96398cc2982f..fc8f01718690 100644 --- a/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt +++ b/Documentation/devicetree/bindings/net/socionext,uniphier-ave4.txt @@ -13,13 +13,25 @@ Required properties: - reg: Address where registers are mapped and size of region. - interrupts: Should contain the MAC interrupt. - phy-mode: See ethernet.txt in the same directory. Allow to choose - "rgmii", "rmii", or "mii" according to the PHY. + "rgmii", "rmii", "mii", or "internal" according to the PHY. + The acceptable mode is SoC-dependent. - phy-handle: Should point to the external phy device. See ethernet.txt file in the same directory. - clocks: A phandle to the clock for the MAC. + For Pro4 SoC, that is "socionext,uniphier-pro4-ave4", + another MAC clock, GIO bus clock and PHY clock are also required. + - clock-names: Should contain + - "ether", "ether-gb", "gio", "ether-phy" for Pro4 SoC + - "ether" for others + - resets: A phandle to the reset control for the MAC. For Pro4 SoC, + GIO bus reset is also required. + - reset-names: Should contain + - "ether", "gio" for Pro4 SoC + - "ether" for others + - socionext,syscon-phy-mode: A phandle to syscon with one argument + that configures phy mode. The argument is the ID of MAC instance. Optional properties: - - resets: A phandle to the reset control for the MAC. - local-mac-address: See ethernet.txt in the same directory. Required subnode: @@ -34,8 +46,11 @@ Example: interrupts = <0 66 4>; phy-mode = "rgmii"; phy-handle = <ðphy>; + clock-names = "ether"; clocks = <&sys_clk 6>; + reset-names = "ether"; resets = <&sys_rst 6>; + socionext,syscon-phy-mode = <&soc_glue 0>; local-mac-address = [00 00 00 00 00 00]; mdio { diff --git a/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt b/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt index 77cd42cc5f54..b025770eeb92 100644 --- a/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt +++ b/Documentation/devicetree/bindings/soc/ti/keystone-navigator-qmss.txt @@ -17,7 +17,8 @@ pool management. Required properties: -- compatible : Must be "ti,keystone-navigator-qmss"; +- compatible : Must be "ti,keystone-navigator-qmss". + : Must be "ti,66ak2g-navss-qm" for QMSS on K2G SoC. - clocks : phandle to the reference clock for this device. - queue-range : <start number> total range of queue numbers for the device. - linkram0 : <address size> for internal link ram, where size is the total @@ -39,6 +40,12 @@ Required properties: - Descriptor memory setup region. - Queue Management/Queue Proxy region for queue Push. - Queue Management/Queue Proxy region for queue Pop. + +For QMSS on K2G SoC, following QM reg indexes are used in that order + - Queue Peek region. + - Queue configuration region. + - Queue Management/Queue Proxy region for queue Push/Pop. + - queue-pools : child node classifying the queue ranges into pools. Queue ranges are grouped into 3 type of pools: - qpend : pool of qpend(interruptible) queues diff --git a/Documentation/filesystems/nfs/nfsroot.txt b/Documentation/filesystems/nfs/nfsroot.txt index 5efae00f6c7f..d2963123eb1c 100644 --- a/Documentation/filesystems/nfs/nfsroot.txt +++ b/Documentation/filesystems/nfs/nfsroot.txt @@ -5,6 +5,7 @@ Written 1996 by Gero Kuhlmann <gero@gkminix.han.de> Updated 1997 by Martin Mares <mj@atrey.karlin.mff.cuni.cz> Updated 2006 by Nico Schottelius <nico-kernel-nfsroot@schottelius.org> Updated 2006 by Horms <horms@verge.net.au> +Updated 2018 by Chris Novakovic <chris@chrisn.me.uk> @@ -79,7 +80,7 @@ nfsroot=[<server-ip>:]<root-dir>[,<nfs-options>] ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>: - <dns0-ip>:<dns1-ip> + <dns0-ip>:<dns1-ip>:<ntp0-ip> This parameter tells the kernel how to configure IP addresses of devices and also how to set up the IP routing table. It was originally called @@ -110,6 +111,9 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>: will not be triggered if it is missing and NFS root is not in operation. + Value is exported to /proc/net/pnp with the prefix "bootserver " + (see below). + Default: Determined using autoconfiguration. The address of the autoconfiguration server is used. @@ -123,10 +127,13 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>: Default: Determined using autoconfiguration. - <hostname> Name of the client. May be supplied by autoconfiguration, - but its absence will not trigger autoconfiguration. - If specified and DHCP is used, the user provided hostname will - be carried in the DHCP request to hopefully update DNS record. + <hostname> Name of the client. If a '.' character is present, anything + before the first '.' is used as the client's hostname, and anything + after it is used as its NIS domain name. May be supplied by + autoconfiguration, but its absence will not trigger autoconfiguration. + If specified and DHCP is used, the user-provided hostname (and NIS + domain name, if present) will be carried in the DHCP request; this + may cause a DNS record to be created or updated for the client. Default: Client IP address is used in ASCII notation. @@ -162,12 +169,55 @@ ip=<client-ip>:<server-ip>:<gw-ip>:<netmask>:<hostname>:<device>:<autoconf>: Default: any - <dns0-ip> IP address of first nameserver. - Value gets exported by /proc/net/pnp which is often linked - on embedded systems by /etc/resolv.conf. + <dns0-ip> IP address of primary nameserver. + Value is exported to /proc/net/pnp with the prefix "nameserver " + (see below). + + Default: None if not using autoconfiguration; determined + automatically if using autoconfiguration. + + <dns1-ip> IP address of secondary nameserver. + See <dns0-ip>. + + <ntp0-ip> IP address of a Network Time Protocol (NTP) server. + Value is exported to /proc/net/ipconfig/ntp_servers, but is + otherwise unused (see below). + + Default: None if not using autoconfiguration; determined + automatically if using autoconfiguration. + + After configuration (whether manual or automatic) is complete, two files + are created in the following format; lines are omitted if their respective + value is empty following configuration: + + - /proc/net/pnp: + + #PROTO: <DHCP|BOOTP|RARP|MANUAL> (depending on configuration method) + domain <dns-domain> (if autoconfigured, the DNS domain) + nameserver <dns0-ip> (primary name server IP) + nameserver <dns1-ip> (secondary name server IP) + nameserver <dns2-ip> (tertiary name server IP) + bootserver <server-ip> (NFS server IP) + + - /proc/net/ipconfig/ntp_servers: + + <ntp0-ip> (NTP server IP) + <ntp1-ip> (NTP server IP) + <ntp2-ip> (NTP server IP) + + <dns-domain> and <dns2-ip> (in /proc/net/pnp) and <ntp1-ip> and <ntp2-ip> + (in /proc/net/ipconfig/ntp_servers) are requested during autoconfiguration; + they cannot be specified as part of the "ip=" kernel command line parameter. + + Because the "domain" and "nameserver" options are recognised by DNS + resolvers, /etc/resolv.conf is often linked to /proc/net/pnp on systems + that use an NFS root filesystem. - <dns1-ip> IP address of second nameserver. - Same as above. + Note that the kernel will not synchronise the system time with any NTP + servers it discovers; this is the responsibility of a user space process + (e.g. an initrd/initramfs script that passes the IP addresses listed in + /proc/net/ipconfig/ntp_servers to an NTP client before mounting the real + root filesystem if it is on NFS). nfsrootdebug diff --git a/Documentation/networking/af_xdp.rst b/Documentation/networking/af_xdp.rst new file mode 100644 index 000000000000..91928d9ee4bf --- /dev/null +++ b/Documentation/networking/af_xdp.rst @@ -0,0 +1,297 @@ +.. SPDX-License-Identifier: GPL-2.0 + +====== +AF_XDP +====== + +Overview +======== + +AF_XDP is an address family that is optimized for high performance +packet processing. + +This document assumes that the reader is familiar with BPF and XDP. If +not, the Cilium project has an excellent reference guide at +http://cilium.readthedocs.io/en/doc-1.0/bpf/. + +Using the XDP_REDIRECT action from an XDP program, the program can +redirect ingress frames to other XDP enabled netdevs, using the +bpf_redirect_map() function. AF_XDP sockets enable the possibility for +XDP programs to redirect frames to a memory buffer in a user-space +application. + +An AF_XDP socket (XSK) is created with the normal socket() +syscall. Associated with each XSK are two rings: the RX ring and the +TX ring. A socket can receive packets on the RX ring and it can send +packets on the TX ring. These rings are registered and sized with the +setsockopts XDP_RX_RING and XDP_TX_RING, respectively. It is mandatory +to have at least one of these rings for each socket. An RX or TX +descriptor ring points to a data buffer in a memory area called a +UMEM. RX and TX can share the same UMEM so that a packet does not have +to be copied between RX and TX. Moreover, if a packet needs to be kept +for a while due to a possible retransmit, the descriptor that points +to that packet can be changed to point to another and reused right +away. This again avoids copying data. + +The UMEM consists of a number of equally size frames and each frame +has a unique frame id. A descriptor in one of the rings references a +frame by referencing its frame id. The user space allocates memory for +this UMEM using whatever means it feels is most appropriate (malloc, +mmap, huge pages, etc). This memory area is then registered with the +kernel using the new setsockopt XDP_UMEM_REG. The UMEM also has two +rings: the FILL ring and the COMPLETION ring. The fill ring is used by +the application to send down frame ids for the kernel to fill in with +RX packet data. References to these frames will then appear in the RX +ring once each packet has been received. The completion ring, on the +other hand, contains frame ids that the kernel has transmitted +completely and can now be used again by user space, for either TX or +RX. Thus, the frame ids appearing in the completion ring are ids that +were previously transmitted using the TX ring. In summary, the RX and +FILL rings are used for the RX path and the TX and COMPLETION rings +are used for the TX path. + +The socket is then finally bound with a bind() call to a device and a +specific queue id on that device, and it is not until bind is +completed that traffic starts to flow. + +The UMEM can be shared between processes, if desired. If a process +wants to do this, it simply skips the registration of the UMEM and its +corresponding two rings, sets the XDP_SHARED_UMEM flag in the bind +call and submits the XSK of the process it would like to share UMEM +with as well as its own newly created XSK socket. The new process will +then receive frame id references in its own RX ring that point to this +shared UMEM. Note that since the ring structures are single-consumer / +single-producer (for performance reasons), the new process has to +create its own socket with associated RX and TX rings, since it cannot +share this with the other process. This is also the reason that there +is only one set of FILL and COMPLETION rings per UMEM. It is the +responsibility of a single process to handle the UMEM. + +How is then packets distributed from an XDP program to the XSKs? There +is a BPF map called XSKMAP (or BPF_MAP_TYPE_XSKMAP in full). The +user-space application can place an XSK at an arbitrary place in this +map. The XDP program can then redirect a packet to a specific index in +this map and at this point XDP validates that the XSK in that map was +indeed bound to that device and ring number. If not, the packet is +dropped. If the map is empty at that index, the packet is also +dropped. This also means that it is currently mandatory to have an XDP +program loaded (and one XSK in the XSKMAP) to be able to get any +traffic to user space through the XSK. + +AF_XDP can operate in two different modes: XDP_SKB and XDP_DRV. If the +driver does not have support for XDP, or XDP_SKB is explicitly chosen +when loading the XDP program, XDP_SKB mode is employed that uses SKBs +together with the generic XDP support and copies out the data to user +space. A fallback mode that works for any network device. On the other +hand, if the driver has support for XDP, it will be used by the AF_XDP +code to provide better performance, but there is still a copy of the +data into user space. + +Concepts +======== + +In order to use an AF_XDP socket, a number of associated objects need +to be setup. + +Jonathan Corbet has also written an excellent article on LWN, +"Accelerating networking with AF_XDP". It can be found at +https://lwn.net/Articles/750845/. + +UMEM +---- + +UMEM is a region of virtual contiguous memory, divided into +equal-sized frames. An UMEM is associated to a netdev and a specific +queue id of that netdev. It is created and configured (frame size, +frame headroom, start address and size) by using the XDP_UMEM_REG +setsockopt system call. A UMEM is bound to a netdev and queue id, via +the bind() system call. + +An AF_XDP is socket linked to a single UMEM, but one UMEM can have +multiple AF_XDP sockets. To share an UMEM created via one socket A, +the next socket B can do this by setting the XDP_SHARED_UMEM flag in +struct sockaddr_xdp member sxdp_flags, and passing the file descriptor +of A to struct sockaddr_xdp member sxdp_shared_umem_fd. + +The UMEM has two single-producer/single-consumer rings, that are used +to transfer ownership of UMEM frames between the kernel and the +user-space application. + +Rings +----- + +There are a four different kind of rings: Fill, Completion, RX and +TX. All rings are single-producer/single-consumer, so the user-space +application need explicit synchronization of multiple +processes/threads are reading/writing to them. + +The UMEM uses two rings: Fill and Completion. Each socket associated +with the UMEM must have an RX queue, TX queue or both. Say, that there +is a setup with four sockets (all doing TX and RX). Then there will be +one Fill ring, one Completion ring, four TX rings and four RX rings. + +The rings are head(producer)/tail(consumer) based rings. A producer +writes the data ring at the index pointed out by struct xdp_ring +producer member, and increasing the producer index. A consumer reads +the data ring at the index pointed out by struct xdp_ring consumer +member, and increasing the consumer index. + +The rings are configured and created via the _RING setsockopt system +calls and mmapped to user-space using the appropriate offset to mmap() +(XDP_PGOFF_RX_RING, XDP_PGOFF_TX_RING, XDP_UMEM_PGOFF_FILL_RING and +XDP_UMEM_PGOFF_COMPLETION_RING). + +The size of the rings need to be of size power of two. + +UMEM Fill Ring +~~~~~~~~~~~~~~ + +The Fill ring is used to transfer ownership of UMEM frames from +user-space to kernel-space. The UMEM indicies are passed in the +ring. As an example, if the UMEM is 64k and each frame is 4k, then the +UMEM has 16 frames and can pass indicies between 0 and 15. + +Frames passed to the kernel are used for the ingress path (RX rings). + +The user application produces UMEM indicies to this ring. + +UMEM Completetion Ring +~~~~~~~~~~~~~~~~~~~~~~ + +The Completion Ring is used transfer ownership of UMEM frames from +kernel-space to user-space. Just like the Fill ring, UMEM indicies are +used. + +Frames passed from the kernel to user-space are frames that has been +sent (TX ring) and can be used by user-space again. + +The user application consumes UMEM indicies from this ring. + + +RX Ring +~~~~~~~ + +The RX ring is the receiving side of a socket. Each entry in the ring +is a struct xdp_desc descriptor. The descriptor contains UMEM index +(idx), the length of the data (len), the offset into the frame +(offset). + +If no frames have been passed to kernel via the Fill ring, no +descriptors will (or can) appear on the RX ring. + +The user application consumes struct xdp_desc descriptors from this +ring. + +TX Ring +~~~~~~~ + +The TX ring is used to send frames. The struct xdp_desc descriptor is +filled (index, length and offset) and passed into the ring. + +To start the transfer a sendmsg() system call is required. This might +be relaxed in the future. + +The user application produces struct xdp_desc descriptors to this +ring. + +XSKMAP / BPF_MAP_TYPE_XSKMAP +---------------------------- + +On XDP side there is a BPF map type BPF_MAP_TYPE_XSKMAP (XSKMAP) that +is used in conjunction with bpf_redirect_map() to pass the ingress +frame to a socket. + +The user application inserts the socket into the map, via the bpf() +system call. + +Note that if an XDP program tries to redirect to a socket that does +not match the queue configuration and netdev, the frame will be +dropped. E.g. an AF_XDP socket is bound to netdev eth0 and +queue 17. Only the XDP program executing for eth0 and queue 17 will +successfully pass data to the socket. Please refer to the sample +application (samples/bpf/) in for an example. + +Usage +===== + +In order to use AF_XDP sockets there are two parts needed. The +user-space application and the XDP program. For a complete setup and +usage example, please refer to the sample application. The user-space +side is xdpsock_user.c and the XDP side xdpsock_kern.c. + +Naive ring dequeue and enqueue could look like this:: + + // typedef struct xdp_rxtx_ring RING; + // typedef struct xdp_umem_ring RING; + + // typedef struct xdp_desc RING_TYPE; + // typedef __u32 RING_TYPE; + + int dequeue_one(RING *ring, RING_TYPE *item) + { + __u32 entries = ring->ptrs.producer - ring->ptrs.consumer; + + if (entries == 0) + return -1; + + // read-barrier! + + *item = ring->desc[ring->ptrs.consumer & (RING_SIZE - 1)]; + ring->ptrs.consumer++; + return 0; + } + + int enqueue_one(RING *ring, const RING_TYPE *item) + { + u32 free_entries = RING_SIZE - (ring->ptrs.producer - ring->ptrs.consumer); + + if (free_entries == 0) + return -1; + + ring->desc[ring->ptrs.producer & (RING_SIZE - 1)] = *item; + + // write-barrier! + + ring->ptrs.producer++; + return 0; + } + + +For a more optimized version, please refer to the sample application. + +Sample application +================== + +There is a xdpsock benchmarking/test application included that +demonstrates how to use AF_XDP sockets with both private and shared +UMEMs. Say that you would like your UDP traffic from port 4242 to end +up in queue 16, that we will enable AF_XDP on. Here, we use ethtool +for this:: + + ethtool -N p3p2 rx-flow-hash udp4 fn + ethtool -N p3p2 flow-type udp4 src-port 4242 dst-port 4242 \ + action 16 + +Running the rxdrop benchmark in XDP_DRV mode can then be done +using:: + + samples/bpf/xdpsock -i p3p2 -q 16 -r -N + +For XDP_SKB mode, use the switch "-S" instead of "-N" and all options +can be displayed with "-h", as usual. + +Credits +======= + +- Björn Töpel (AF_XDP core) +- Magnus Karlsson (AF_XDP core) +- Alexander Duyck +- Alexei Starovoitov +- Daniel Borkmann +- Jesper Dangaard Brouer +- John Fastabend +- Jonathan Corbet (LWN coverage) +- Michael S. Tsirkin +- Qi Z Zhang +- Willem de Bruijn + diff --git a/Documentation/networking/bonding.txt b/Documentation/networking/bonding.txt index 9ba04c0bab8d..c13214d073a4 100644 --- a/Documentation/networking/bonding.txt +++ b/Documentation/networking/bonding.txt @@ -140,7 +140,7 @@ bonding module at load time, or are specified via sysfs. Module options may be given as command line arguments to the insmod or modprobe command, but are usually specified in either the -/etc/modrobe.d/*.conf configuration files, or in a distro-specific +/etc/modprobe.d/*.conf configuration files, or in a distro-specific configuration file (some of which are detailed in the next section). Details on bonding support for sysfs is provided in the diff --git a/Documentation/networking/filter.txt b/Documentation/networking/filter.txt index fd55c7de9991..5032e1263bc9 100644 --- a/Documentation/networking/filter.txt +++ b/Documentation/networking/filter.txt @@ -483,6 +483,12 @@ Example output from dmesg: [ 3389.935851] JIT code: 00000030: 00 e8 28 94 ff e0 83 f8 01 75 07 b8 ff ff 00 00 [ 3389.935852] JIT code: 00000040: eb 02 31 c0 c9 c3 +When CONFIG_BPF_JIT_ALWAYS_ON is enabled, bpf_jit_enable is permanently set to 1 and +setting any other value than that will return in failure. This is even the case for +setting bpf_jit_enable to 2, since dumping the final JIT image into the kernel log +is discouraged and introspection through bpftool (under tools/bpf/bpftool/) is the +generally recommended approach instead. + In the kernel source tree under tools/bpf/, there's bpf_jit_disasm for generating disassembly out of the kernel log's hexdump: diff --git a/Documentation/networking/index.rst b/Documentation/networking/index.rst index f204eaff657d..cbd9bdd4a79e 100644 --- a/Documentation/networking/index.rst +++ b/Documentation/networking/index.rst @@ -6,6 +6,7 @@ Contents: .. toctree:: :maxdepth: 2 + af_xdp batman-adv can dpaa2/index diff --git a/Documentation/networking/ip-sysctl.txt b/Documentation/networking/ip-sysctl.txt index 35ffaa281b26..59afc9a10b4f 100644 --- a/Documentation/networking/ip-sysctl.txt +++ b/Documentation/networking/ip-sysctl.txt @@ -1428,6 +1428,19 @@ ip6frag_low_thresh - INTEGER ip6frag_time - INTEGER Time in seconds to keep an IPv6 fragment in memory. +IPv6 Segment Routing: + +seg6_flowlabel - INTEGER + Controls the behaviour of computing the flowlabel of outer + IPv6 header in case of SR T.encaps + + -1 set flowlabel to zero. + 0 copy flowlabel from Inner packet in case of Inner IPv6 + (Set flowlabel to 0 in case IPv4/L2) + 1 Compute the flowlabel using seg6_make_flowlabel() + + Default is 0. + conf/default/*: Change the interface-specific default settings. diff --git a/Documentation/networking/netdev-features.txt b/Documentation/networking/netdev-features.txt index c77f9d57eb91..c4a54c162547 100644 --- a/Documentation/networking/netdev-features.txt +++ b/Documentation/networking/netdev-features.txt @@ -113,6 +113,13 @@ whatever headers there might be. NETIF_F_TSO_ECN means that hardware can properly split packets with CWR bit set, be it TCPv4 (when NETIF_F_TSO is enabled) or TCPv6 (NETIF_F_TSO6). + * Transmit UDP segmentation offload + +NETIF_F_GSO_UDP_GSO_L4 accepts a single UDP header with a payload that exceeds +gso_size. On segmentation, it segments the payload on gso_size boundaries and +replicates the network and UDP headers (fixing up the last one if less than +gso_size). + * Transmit DMA from high memory On platforms where this is relevant, NETIF_F_HIGHDMA signals that diff --git a/Documentation/sysctl/net.txt b/Documentation/sysctl/net.txt index 5992602469d8..9ecde517728c 100644 --- a/Documentation/sysctl/net.txt +++ b/Documentation/sysctl/net.txt @@ -45,6 +45,7 @@ through bpf(2) and passing a verifier in the kernel, a JIT will then translate these BPF proglets into native CPU instructions. There are two flavors of JITs, the newer eBPF JIT currently supported on: - x86_64 + - x86_32 - arm64 - arm32 - ppc64 diff --git a/MAINTAINERS b/MAINTAINERS index f913c80c8c38..cecf461678b5 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -2728,7 +2728,6 @@ F: Documentation/networking/filter.txt F: Documentation/bpf/ F: include/linux/bpf* F: include/linux/filter.h -F: include/trace/events/bpf.h F: include/trace/events/xdp.h F: include/uapi/linux/bpf* F: include/uapi/linux/filter.h @@ -5318,7 +5317,6 @@ F: include/linux/*mdio*.h F: include/linux/of_net.h F: include/linux/phy.h F: include/linux/phy_fixed.h -F: include/linux/platform_data/mdio-gpio.h F: include/linux/platform_data/mdio-bcm-unimac.h F: include/trace/events/mdio.h F: include/uapi/linux/mdio.h @@ -9021,26 +9019,17 @@ W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ F: drivers/net/ethernet/mellanox/mlx5/core/en_* -MELLANOX ETHERNET INNOVA DRIVER -M: Ilan Tayari <ilant@mellanox.com> -R: Boris Pismenny <borisp@mellanox.com> +MELLANOX ETHERNET INNOVA DRIVERS +M: Boris Pismenny <borisp@mellanox.com> L: netdev@vger.kernel.org S: Supported W: http://www.mellanox.com Q: http://patchwork.ozlabs.org/project/netdev/list/ +F: drivers/net/ethernet/mellanox/mlx5/core/en_accel/* +F: drivers/net/ethernet/mellanox/mlx5/core/accel/* F: drivers/net/ethernet/mellanox/mlx5/core/fpga/* F: include/linux/mlx5/mlx5_ifc_fpga.h -MELLANOX ETHERNET INNOVA IPSEC DRIVER -M: Ilan Tayari <ilant@mellanox.com> -R: Boris Pismenny <borisp@mellanox.com> -L: netdev@vger.kernel.org -S: Supported -W: http://www.mellanox.com -Q: http://patchwork.ozlabs.org/project/netdev/list/ -F: drivers/net/ethernet/mellanox/mlx5/core/en_ipsec/* -F: drivers/net/ethernet/mellanox/mlx5/core/ipsec* - MELLANOX ETHERNET SWITCH DRIVERS M: Jiri Pirko <jiri@mellanox.com> M: Ido Schimmel <idosch@mellanox.com> @@ -9833,7 +9822,7 @@ F: net/netfilter/xt_CONNSECMARK.c F: net/netfilter/xt_SECMARK.c NETWORKING [TLS] -M: Ilya Lesokhin <ilyal@mellanox.com> +M: Boris Pismenny <borisp@mellanox.com> M: Aviad Yehezkel <aviadye@mellanox.com> M: Dave Watson <davejwatson@fb.com> L: netdev@vger.kernel.org @@ -14612,7 +14601,9 @@ M: Woojung Huh <woojung.huh@microchip.com> M: Microchip Linux Driver Support <UNGLinuxDriver@microchip.com> L: netdev@vger.kernel.org S: Maintained +F: Documentation/devicetree/bindings/net/microchip,lan78xx.txt F: drivers/net/usb/lan78xx.* +F: include/dt-bindings/net/microchip-lan78xx.h USB MASS STORAGE DRIVER M: Alan Stern <stern@rowland.harvard.edu> @@ -15401,6 +15392,14 @@ T: git git://linuxtv.org/media_tree.git S: Maintained F: drivers/media/tuners/tuner-xc2028.* +XDP SOCKETS (AF_XDP) +M: Björn Töpel <bjorn.topel@intel.com> +M: Magnus Karlsson <magnus.karlsson@intel.com> +L: netdev@vger.kernel.org +S: Maintained +F: kernel/bpf/xskmap.c +F: net/xdp/ + XEN BLOCK SUBSYSTEM M: Konrad Rzeszutek Wilk <konrad.wilk@oracle.com> M: Roger Pau Monné <roger.pau@citrix.com> diff --git a/arch/arm/net/bpf_jit_32.c b/arch/arm/net/bpf_jit_32.c index b5030e1a41d8..82689b999257 100644 --- a/arch/arm/net/bpf_jit_32.c +++ b/arch/arm/net/bpf_jit_32.c @@ -1452,83 +1452,6 @@ exit: emit(ARM_LDR_I(rn, ARM_SP, STACK_VAR(src_lo)), ctx); emit_ldx_r(dst, rn, dstk, off, ctx, BPF_SIZE(code)); break; - /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ - case BPF_LD | BPF_ABS | BPF_W: - case BPF_LD | BPF_ABS | BPF_H: - case BPF_LD | BPF_ABS | BPF_B: - /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */ - case BPF_LD | BPF_IND | BPF_W: - case BPF_LD | BPF_IND | BPF_H: - case BPF_LD | BPF_IND | BPF_B: - { - const u8 r4 = bpf2a32[BPF_REG_6][1]; /* r4 = ptr to sk_buff */ - const u8 r0 = bpf2a32[BPF_REG_0][1]; /*r0: struct sk_buff *skb*/ - /* rtn value */ - const u8 r1 = bpf2a32[BPF_REG_0][0]; /* r1: int k */ - const u8 r2 = bpf2a32[BPF_REG_1][1]; /* r2: unsigned int size */ - const u8 r3 = bpf2a32[BPF_REG_1][0]; /* r3: void *buffer */ - const u8 r6 = bpf2a32[TMP_REG_1][1]; /* r6: void *(*func)(..) */ - int size; - - /* Setting up first argument */ - emit(ARM_MOV_R(r0, r4), ctx); - - /* Setting up second argument */ - emit_a32_mov_i(r1, imm, false, ctx); - if (BPF_MODE(code) == BPF_IND) - emit_a32_alu_r(r1, src_lo, false, sstk, ctx, - false, false, BPF_ADD); - - /* Setting up third argument */ - switch (BPF_SIZE(code)) { - case BPF_W: - size = 4; - break; - case BPF_H: - size = 2; - break; - case BPF_B: - size = 1; - break; - default: - return -EINVAL; - } - emit_a32_mov_i(r2, size, false, ctx); - - /* Setting up fourth argument */ - emit(ARM_ADD_I(r3, ARM_SP, imm8m(SKB_BUFFER)), ctx); - - /* Setting up function pointer to call */ - emit_a32_mov_i(r6, (unsigned int)bpf_load_pointer, false, ctx); - emit_blx_r(r6, ctx); - - emit(ARM_EOR_R(r1, r1, r1), ctx); - /* Check if return address is NULL or not. - * if NULL then jump to epilogue - * else continue to load the value from retn address - */ - emit(ARM_CMP_I(r0, 0), ctx); - jmp_offset = epilogue_offset(ctx); - check_imm24(jmp_offset); - _emit(ARM_COND_EQ, ARM_B(jmp_offset), ctx); - - /* Load value from the address */ - switch (BPF_SIZE(code)) { - case BPF_W: - emit(ARM_LDR_I(r0, r0, 0), ctx); - emit_rev32(r0, r0, ctx); - break; - case BPF_H: - emit(ARM_LDRH_I(r0, r0, 0), ctx); - emit_rev16(r0, r0, ctx); - break; - case BPF_B: - emit(ARM_LDRB_I(r0, r0, 0), ctx); - /* No need to reverse */ - break; - } - break; - } /* ST: *(size *)(dst + off) = imm */ case BPF_ST | BPF_MEM | BPF_W: case BPF_ST | BPF_MEM | BPF_H: diff --git a/arch/arm64/net/bpf_jit_comp.c b/arch/arm64/net/bpf_jit_comp.c index a93350451e8e..0b40c8fb0706 100644 --- a/arch/arm64/net/bpf_jit_comp.c +++ b/arch/arm64/net/bpf_jit_comp.c @@ -723,71 +723,6 @@ emit_cond_jmp: emit(A64_CBNZ(0, tmp3, jmp_offset), ctx); break; - /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ - case BPF_LD | BPF_ABS | BPF_W: - case BPF_LD | BPF_ABS | BPF_H: - case BPF_LD | BPF_ABS | BPF_B: - /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */ - case BPF_LD | BPF_IND | BPF_W: - case BPF_LD | BPF_IND | BPF_H: - case BPF_LD | BPF_IND | BPF_B: - { - const u8 r0 = bpf2a64[BPF_REG_0]; /* r0 = return value */ - const u8 r6 = bpf2a64[BPF_REG_6]; /* r6 = pointer to sk_buff */ - const u8 fp = bpf2a64[BPF_REG_FP]; - const u8 r1 = bpf2a64[BPF_REG_1]; /* r1: struct sk_buff *skb */ - const u8 r2 = bpf2a64[BPF_REG_2]; /* r2: int k */ - const u8 r3 = bpf2a64[BPF_REG_3]; /* r3: unsigned int size */ - const u8 r4 = bpf2a64[BPF_REG_4]; /* r4: void *buffer */ - const u8 r5 = bpf2a64[BPF_REG_5]; /* r5: void *(*func)(...) */ - int size; - - emit(A64_MOV(1, r1, r6), ctx); - emit_a64_mov_i(0, r2, imm, ctx); - if (BPF_MODE(code) == BPF_IND) - emit(A64_ADD(0, r2, r2, src), ctx); - switch (BPF_SIZE(code)) { - case BPF_W: - size = 4; - break; - case BPF_H: - size = 2; - break; - case BPF_B: - size = 1; - break; - default: - return -EINVAL; - } - emit_a64_mov_i64(r3, size, ctx); - emit(A64_SUB_I(1, r4, fp, ctx->stack_size), ctx); - emit_a64_mov_i64(r5, (unsigned long)bpf_load_pointer, ctx); - emit(A64_BLR(r5), ctx); - emit(A64_MOV(1, r0, A64_R(0)), ctx); - - jmp_offset = epilogue_offset(ctx); - check_imm19(jmp_offset); - emit(A64_CBZ(1, r0, jmp_offset), ctx); - emit(A64_MOV(1, r5, r0), ctx); - switch (BPF_SIZE(code)) { - case BPF_W: - emit(A64_LDR32(r0, r5, A64_ZR), ctx); -#ifndef CONFIG_CPU_BIG_ENDIAN - emit(A64_REV32(0, r0, r0), ctx); -#endif - break; - case BPF_H: - emit(A64_LDRH(r0, r5, A64_ZR), ctx); -#ifndef CONFIG_CPU_BIG_ENDIAN - emit(A64_REV16(0, r0, r0), ctx); -#endif - break; - case BPF_B: - emit(A64_LDRB(r0, r5, A64_ZR), ctx); - break; - } - break; - } default: pr_err_once("unknown opcode %02x\n", code); return -EINVAL; diff --git a/arch/mips/net/ebpf_jit.c b/arch/mips/net/ebpf_jit.c index 3e2798bfea4f..7ba7df9c28fc 100644 --- a/arch/mips/net/ebpf_jit.c +++ b/arch/mips/net/ebpf_jit.c @@ -1267,110 +1267,6 @@ jeq_common: return -EINVAL; break; - case BPF_LD | BPF_B | BPF_ABS: - case BPF_LD | BPF_H | BPF_ABS: - case BPF_LD | BPF_W | BPF_ABS: - case BPF_LD | BPF_DW | BPF_ABS: - ctx->flags |= EBPF_SAVE_RA; - - gen_imm_to_reg(insn, MIPS_R_A1, ctx); - emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn)); - - if (insn->imm < 0) { - emit_const_to_reg(ctx, MIPS_R_T9, (u64)bpf_internal_load_pointer_neg_helper); - } else { - emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer); - emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset); - } - goto ld_skb_common; - - case BPF_LD | BPF_B | BPF_IND: - case BPF_LD | BPF_H | BPF_IND: - case BPF_LD | BPF_W | BPF_IND: - case BPF_LD | BPF_DW | BPF_IND: - ctx->flags |= EBPF_SAVE_RA; - src = ebpf_to_mips_reg(ctx, insn, src_reg_no_fp); - if (src < 0) - return src; - ts = get_reg_val_type(ctx, this_idx, insn->src_reg); - if (ts == REG_32BIT_ZERO_EX) { - /* sign extend */ - emit_instr(ctx, sll, MIPS_R_A1, src, 0); - src = MIPS_R_A1; - } - if (insn->imm >= S16_MIN && insn->imm <= S16_MAX) { - emit_instr(ctx, daddiu, MIPS_R_A1, src, insn->imm); - } else { - gen_imm_to_reg(insn, MIPS_R_AT, ctx); - emit_instr(ctx, daddu, MIPS_R_A1, MIPS_R_AT, src); - } - /* truncate to 32-bit int */ - emit_instr(ctx, sll, MIPS_R_A1, MIPS_R_A1, 0); - emit_instr(ctx, daddiu, MIPS_R_A3, MIPS_R_SP, ctx->tmp_offset); - emit_instr(ctx, slt, MIPS_R_AT, MIPS_R_A1, MIPS_R_ZERO); - - emit_const_to_reg(ctx, MIPS_R_T8, (u64)bpf_internal_load_pointer_neg_helper); - emit_const_to_reg(ctx, MIPS_R_T9, (u64)ool_skb_header_pointer); - emit_instr(ctx, addiu, MIPS_R_A2, MIPS_R_ZERO, size_to_len(insn)); - emit_instr(ctx, movn, MIPS_R_T9, MIPS_R_T8, MIPS_R_AT); - -ld_skb_common: - emit_instr(ctx, jalr, MIPS_R_RA, MIPS_R_T9); - /* delay slot move */ - emit_instr(ctx, daddu, MIPS_R_A0, MIPS_R_S0, MIPS_R_ZERO); - - /* Check the error value */ - b_off = b_imm(exit_idx, ctx); - if (is_bad_offset(b_off)) { - target = j_target(ctx, exit_idx); - if (target == (unsigned int)-1) - return -E2BIG; - - if (!(ctx->offsets[this_idx] & OFFSETS_B_CONV)) { - ctx->offsets[this_idx] |= OFFSETS_B_CONV; - ctx->long_b_conversion = 1; - } - emit_instr(ctx, bne, MIPS_R_V0, MIPS_R_ZERO, 4 * 3); - emit_instr(ctx, nop); - emit_instr(ctx, j, target); - emit_instr(ctx, nop); - } else { - emit_instr(ctx, beq, MIPS_R_V0, MIPS_R_ZERO, b_off); - emit_instr(ctx, nop); - } - -#ifdef __BIG_ENDIAN - need_swap = false; -#else - need_swap = true; -#endif - dst = MIPS_R_V0; - switch (BPF_SIZE(insn->code)) { - case BPF_B: - emit_instr(ctx, lbu, dst, 0, MIPS_R_V0); - break; - case BPF_H: - emit_instr(ctx, lhu, dst, 0, MIPS_R_V0); - if (need_swap) - emit_instr(ctx, wsbh, dst, dst); - break; - case BPF_W: - emit_instr(ctx, lw, dst, 0, MIPS_R_V0); - if (need_swap) { - emit_instr(ctx, wsbh, dst, dst); - emit_instr(ctx, rotr, dst, dst, 16); - } - break; - case BPF_DW: - emit_instr(ctx, ld, dst, 0, MIPS_R_V0); - if (need_swap) { - emit_instr(ctx, dsbh, dst, dst); - emit_instr(ctx, dshd, dst, dst); - } - break; - } - - break; case BPF_ALU | BPF_END | BPF_FROM_BE: case BPF_ALU | BPF_END | BPF_FROM_LE: dst = ebpf_to_mips_reg(ctx, insn, dst_reg); diff --git a/arch/powerpc/net/Makefile b/arch/powerpc/net/Makefile index 02d369ca6a53..809f019d3cba 100644 --- a/arch/powerpc/net/Makefile +++ b/arch/powerpc/net/Makefile @@ -3,7 +3,7 @@ # Arch-specific network modules # ifeq ($(CONFIG_PPC64),y) -obj-$(CONFIG_BPF_JIT) += bpf_jit_asm64.o bpf_jit_comp64.o +obj-$(CONFIG_BPF_JIT) += bpf_jit_comp64.o else obj-$(CONFIG_BPF_JIT) += bpf_jit_asm.o bpf_jit_comp.o endif diff --git a/arch/powerpc/net/bpf_jit64.h b/arch/powerpc/net/bpf_jit64.h index 8bdef7ed28a8..3609be4692b3 100644 --- a/arch/powerpc/net/bpf_jit64.h +++ b/arch/powerpc/net/bpf_jit64.h @@ -20,7 +20,7 @@ * with our redzone usage. * * [ prev sp ] <------------- - * [ nv gpr save area ] 8*8 | + * [ nv gpr save area ] 6*8 | * [ tail_call_cnt ] 8 | * [ local_tmp_var ] 8 | * fp (r31) --> [ ebpf stack space ] upto 512 | @@ -28,8 +28,8 @@ * sp (r1) ---> [ stack pointer ] -------------- */ -/* for gpr non volatile registers BPG_REG_6 to 10, plus skb cache registers */ -#define BPF_PPC_STACK_SAVE (8*8) +/* for gpr non volatile registers BPG_REG_6 to 10 */ +#define BPF_PPC_STACK_SAVE (6*8) /* for bpf JIT code internal usage */ #define BPF_PPC_STACK_LOCALS 16 /* stack frame excluding BPF stack, ensure this is quadword aligned */ @@ -39,10 +39,8 @@ #ifndef __ASSEMBLY__ /* BPF register usage */ -#define SKB_HLEN_REG (MAX_BPF_JIT_REG + 0) -#define SKB_DATA_REG (MAX_BPF_JIT_REG + 1) -#define TMP_REG_1 (MAX_BPF_JIT_REG + 2) -#define TMP_REG_2 (MAX_BPF_JIT_REG + 3) +#define TMP_REG_1 (MAX_BPF_JIT_REG + 0) +#define TMP_REG_2 (MAX_BPF_JIT_REG + 1) /* BPF to ppc register mappings */ static const int b2p[] = { @@ -63,40 +61,23 @@ static const int b2p[] = { [BPF_REG_FP] = 31, /* eBPF jit internal registers */ [BPF_REG_AX] = 2, - [SKB_HLEN_REG] = 25, - [SKB_DATA_REG] = 26, [TMP_REG_1] = 9, [TMP_REG_2] = 10 }; -/* PPC NVR range -- update this if we ever use NVRs below r24 */ -#define BPF_PPC_NVR_MIN 24 - -/* Assembly helpers */ -#define DECLARE_LOAD_FUNC(func) u64 func(u64 r3, u64 r4); \ - u64 func##_negative_offset(u64 r3, u64 r4); \ - u64 func##_positive_offset(u64 r3, u64 r4); - -DECLARE_LOAD_FUNC(sk_load_word); -DECLARE_LOAD_FUNC(sk_load_half); -DECLARE_LOAD_FUNC(sk_load_byte); - -#define CHOOSE_LOAD_FUNC(imm, func) \ - (imm < 0 ? \ - (imm >= SKF_LL_OFF ? func##_negative_offset : func) : \ - func##_positive_offset) +/* PPC NVR range -- update this if we ever use NVRs below r27 */ +#define BPF_PPC_NVR_MIN 27 #define SEEN_FUNC 0x1000 /* might call external helpers */ #define SEEN_STACK 0x2000 /* uses BPF stack */ -#define SEEN_SKB 0x4000 /* uses sk_buff */ -#define SEEN_TAILCALL 0x8000 /* uses tail calls */ +#define SEEN_TAILCALL 0x4000 /* uses tail calls */ struct codegen_context { /* * This is used to track register usage as well * as calls to external helpers. * - register usage is tracked with corresponding - * bits (r3-r10 and r25-r31) + * bits (r3-r10 and r27-r31) * - rest of the bits can be used to track other * things -- for now, we use bits 16 to 23 * encoded in SEEN_* macros above diff --git a/arch/powerpc/net/bpf_jit_asm64.S b/arch/powerpc/net/bpf_jit_asm64.S deleted file mode 100644 index 7e4c51430b84..000000000000 --- a/arch/powerpc/net/bpf_jit_asm64.S +++ /dev/null @@ -1,180 +0,0 @@ -/* - * bpf_jit_asm64.S: Packet/header access helper functions - * for PPC64 BPF compiler. - * - * Copyright 2016, Naveen N. Rao <naveen.n.rao@linux.vnet.ibm.com> - * IBM Corporation - * - * Based on bpf_jit_asm.S by Matt Evans - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ - -#include <asm/ppc_asm.h> -#include <asm/ptrace.h> -#include "bpf_jit64.h" - -/* - * All of these routines are called directly from generated code, - * with the below register usage: - * r27 skb pointer (ctx) - * r25 skb header length - * r26 skb->data pointer - * r4 offset - * - * Result is passed back in: - * r8 data read in host endian format (accumulator) - * - * r9 is used as a temporary register - */ - -#define r_skb r27 -#define r_hlen r25 -#define r_data r26 -#define r_off r4 -#define r_val r8 -#define r_tmp r9 - -_GLOBAL_TOC(sk_load_word) - cmpdi r_off, 0 - blt bpf_slow_path_word_neg - b sk_load_word_positive_offset - -_GLOBAL_TOC(sk_load_word_positive_offset) - /* Are we accessing past headlen? */ - subi r_tmp, r_hlen, 4 - cmpd r_tmp, r_off - blt bpf_slow_path_word - /* Nope, just hitting the header. cr0 here is eq or gt! */ - LWZX_BE r_val, r_data, r_off - blr /* Return success, cr0 != LT */ - -_GLOBAL_TOC(sk_load_half) - cmpdi r_off, 0 - blt bpf_slow_path_half_neg - b sk_load_half_positive_offset - -_GLOBAL_TOC(sk_load_half_positive_offset) - subi r_tmp, r_hlen, 2 - cmpd r_tmp, r_off - blt bpf_slow_path_half - LHZX_BE r_val, r_data, r_off - blr - -_GLOBAL_TOC(sk_load_byte) - cmpdi r_off, 0 - blt bpf_slow_path_byte_neg - b sk_load_byte_positive_offset - -_GLOBAL_TOC(sk_load_byte_positive_offset) - cmpd r_hlen, r_off - ble bpf_slow_path_byte - lbzx r_val, r_data, r_off - blr - -/* - * Call out to skb_copy_bits: - * Allocate a new stack frame here to remain ABI-compliant in - * stashing LR. - */ -#define bpf_slow_path_common(SIZE) \ - mflr r0; \ - std r0, PPC_LR_STKOFF(r1); \ - stdu r1, -(STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS)(r1); \ - mr r3, r_skb; \ - /* r4 = r_off as passed */ \ - addi r5, r1, STACK_FRAME_MIN_SIZE; \ - li r6, SIZE; \ - bl skb_copy_bits; \ - nop; \ - /* save r5 */ \ - addi r5, r1, STACK_FRAME_MIN_SIZE; \ - /* r3 = 0 on success */ \ - addi r1, r1, STACK_FRAME_MIN_SIZE + BPF_PPC_STACK_LOCALS; \ - ld r0, PPC_LR_STKOFF(r1); \ - mtlr r0; \ - cmpdi r3, 0; \ - blt bpf_error; /* cr0 = LT */ - -bpf_slow_path_word: - bpf_slow_path_common(4) - /* Data value is on stack, and cr0 != LT */ - LWZX_BE r_val, 0, r5 - blr - -bpf_slow_path_half: - bpf_slow_path_common(2) - LHZX_BE r_val, 0, r5 - blr - -bpf_slow_path_byte: - bpf_slow_path_common(1) - lbzx r_val, 0, r5 - blr - -/* - * Call out to bpf_internal_load_pointer_neg_helper - */ -#define sk_negative_common(SIZE) \ - mflr r0; \ - std r0, PPC_LR_STKOFF(r1); \ - stdu r1, -STACK_FRAME_MIN_SIZE(r1); \ - mr r3, r_skb; \ - /* r4 = r_off, as passed */ \ - li r5, SIZE; \ - bl bpf_internal_load_pointer_neg_helper; \ - nop; \ - addi r1, r1, STACK_FRAME_MIN_SIZE; \ - ld r0, PPC_LR_STKOFF(r1); \ - mtlr r0; \ - /* R3 != 0 on success */ \ - cmpldi r3, 0; \ - beq bpf_error_slow; /* cr0 = EQ */ - -bpf_slow_path_word_neg: - lis r_tmp, -32 /* SKF_LL_OFF */ - cmpd r_off, r_tmp /* addr < SKF_* */ - blt bpf_error /* cr0 = LT */ - b sk_load_word_negative_offset - -_GLOBAL_TOC(sk_load_word_negative_offset) - sk_negative_common(4) - LWZX_BE r_val, 0, r3 - blr - -bpf_slow_path_half_neg: - lis r_tmp, -32 /* SKF_LL_OFF */ - cmpd r_off, r_tmp /* addr < SKF_* */ - blt bpf_error /* cr0 = LT */ - b sk_load_half_negative_offset - -_GLOBAL_TOC(sk_load_half_negative_offset) - sk_negative_common(2) - LHZX_BE r_val, 0, r3 - blr - -bpf_slow_path_byte_neg: - lis r_tmp, -32 /* SKF_LL_OFF */ - cmpd r_off, r_tmp /* addr < SKF_* */ - blt bpf_error /* cr0 = LT */ - b sk_load_byte_negative_offset - -_GLOBAL_TOC(sk_load_byte_negative_offset) - sk_negative_common(1) - lbzx r_val, 0, r3 - blr - -bpf_error_slow: - /* fabricate a cr0 = lt */ - li r_tmp, -1 - cmpdi r_tmp, 0 -bpf_error: - /* - * Entered with cr0 = lt - * Generated code will 'blt epilogue', returning 0. - */ - li r_val, 0 - blr diff --git a/arch/powerpc/net/bpf_jit_comp64.c b/arch/powerpc/net/bpf_jit_comp64.c index 0ef3d9580e98..1bdb1aff0619 100644 --- a/arch/powerpc/net/bpf_jit_comp64.c +++ b/arch/powerpc/net/bpf_jit_comp64.c @@ -59,7 +59,7 @@ static inline bool bpf_has_stack_frame(struct codegen_context *ctx) * [ prev sp ] <------------- * [ ... ] | * sp (r1) ---> [ stack pointer ] -------------- - * [ nv gpr save area ] 8*8 + * [ nv gpr save area ] 6*8 * [ tail_call_cnt ] 8 * [ local_tmp_var ] 8 * [ unused red zone ] 208 bytes protected @@ -88,21 +88,6 @@ static int bpf_jit_stack_offsetof(struct codegen_context *ctx, int reg) BUG(); } -static void bpf_jit_emit_skb_loads(u32 *image, struct codegen_context *ctx) -{ - /* - * Load skb->len and skb->data_len - * r3 points to skb - */ - PPC_LWZ(b2p[SKB_HLEN_REG], 3, offsetof(struct sk_buff, len)); - PPC_LWZ(b2p[TMP_REG_1], 3, offsetof(struct sk_buff, data_len)); - /* header_len = len - data_len */ - PPC_SUB(b2p[SKB_HLEN_REG], b2p[SKB_HLEN_REG], b2p[TMP_REG_1]); - - /* skb->data pointer */ - PPC_BPF_LL(b2p[SKB_DATA_REG], 3, offsetof(struct sk_buff, data)); -} - static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) { int i; @@ -145,18 +130,6 @@ static void bpf_jit_build_prologue(u32 *image, struct codegen_context *ctx) if (bpf_is_seen_register(ctx, i)) PPC_BPF_STL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i])); - /* - * Save additional non-volatile regs if we cache skb - * Also, setup skb data - */ - if (ctx->seen & SEEN_SKB) { - PPC_BPF_STL(b2p[SKB_HLEN_REG], 1, - bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG])); - PPC_BPF_STL(b2p[SKB_DATA_REG], 1, - bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG])); - bpf_jit_emit_skb_loads(image, ctx); - } - /* Setup frame pointer to point to the bpf stack area */ if (bpf_is_seen_register(ctx, BPF_REG_FP)) PPC_ADDI(b2p[BPF_REG_FP], 1, @@ -172,14 +145,6 @@ static void bpf_jit_emit_common_epilogue(u32 *image, struct codegen_context *ctx if (bpf_is_seen_register(ctx, i)) PPC_BPF_LL(b2p[i], 1, bpf_jit_stack_offsetof(ctx, b2p[i])); - /* Restore non-volatile registers used for skb cache */ - if (ctx->seen & SEEN_SKB) { - PPC_BPF_LL(b2p[SKB_HLEN_REG], 1, - bpf_jit_stack_offsetof(ctx, b2p[SKB_HLEN_REG])); - PPC_BPF_LL(b2p[SKB_DATA_REG], 1, - bpf_jit_stack_offsetof(ctx, b2p[SKB_DATA_REG])); - } - /* Tear down our stack frame */ if (bpf_has_stack_frame(ctx)) { PPC_ADDI(1, 1, BPF_PPC_STACKFRAME + ctx->stack_size); @@ -753,23 +718,10 @@ emit_clear: ctx->seen |= SEEN_FUNC; func = (u8 *) __bpf_call_base + imm; - /* Save skb pointer if we need to re-cache skb data */ - if ((ctx->seen & SEEN_SKB) && - bpf_helper_changes_pkt_data(func)) - PPC_BPF_STL(3, 1, bpf_jit_stack_local(ctx)); - bpf_jit_emit_func_call(image, ctx, (u64)func); /* move return value from r3 to BPF_REG_0 */ PPC_MR(b2p[BPF_REG_0], 3); - - /* refresh skb cache */ - if ((ctx->seen & SEEN_SKB) && - bpf_helper_changes_pkt_data(func)) { - /* reload skb pointer to r3 */ - PPC_BPF_LL(3, 1, bpf_jit_stack_local(ctx)); - bpf_jit_emit_skb_loads(image, ctx); - } break; /* @@ -887,65 +839,6 @@ cond_branch: break; /* - * Loads from packet header/data - * Assume 32-bit input value in imm and X (src_reg) - */ - - /* Absolute loads */ - case BPF_LD | BPF_W | BPF_ABS: - func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_word); - goto common_load_abs; - case BPF_LD | BPF_H | BPF_ABS: - func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_half); - goto common_load_abs; - case BPF_LD | BPF_B | BPF_ABS: - func = (u8 *)CHOOSE_LOAD_FUNC(imm, sk_load_byte); -common_load_abs: - /* - * Load from [imm] - * Load into r4, which can just be passed onto - * skb load helpers as the second parameter - */ - PPC_LI32(4, imm); - goto common_load; - - /* Indirect loads */ - case BPF_LD | BPF_W | BPF_IND: - func = (u8 *)sk_load_word; - goto common_load_ind; - case BPF_LD | BPF_H | BPF_IND: - func = (u8 *)sk_load_half; - goto common_load_ind; - case BPF_LD | BPF_B | BPF_IND: - func = (u8 *)sk_load_byte; -common_load_ind: - /* - * Load from [src_reg + imm] - * Treat src_reg as a 32-bit value - */ - PPC_EXTSW(4, src_reg); - if (imm) { - if (imm >= -32768 && imm < 32768) - PPC_ADDI(4, 4, IMM_L(imm)); - else { - PPC_LI32(b2p[TMP_REG_1], imm); - PPC_ADD(4, 4, b2p[TMP_REG_1]); - } - } - -common_load: - ctx->seen |= SEEN_SKB; - ctx->seen |= SEEN_FUNC; - bpf_jit_emit_func_call(image, ctx, (u64)func); - - /* - * Helper returns 'lt' condition on error, and an - * appropriate return value in BPF_REG_0 - */ - PPC_BCC(COND_LT, exit_addr); - break; - - /* * Tail call */ case BPF_JMP | BPF_TAIL_CALL: diff --git a/arch/s390/net/Makefile b/arch/s390/net/Makefile index e0d5f245e42b..d4663b4bf509 100644 --- a/arch/s390/net/Makefile +++ b/arch/s390/net/Makefile @@ -2,4 +2,4 @@ # # Arch-specific network modules # -obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o +obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o diff --git a/arch/s390/net/bpf_jit.S b/arch/s390/net/bpf_jit.S deleted file mode 100644 index 25bb4643c4f4..000000000000 --- a/arch/s390/net/bpf_jit.S +++ /dev/null @@ -1,116 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -/* - * BPF Jit compiler for s390, help functions. - * - * Copyright IBM Corp. 2012,2015 - * - * Author(s): Martin Schwidefsky <schwidefsky@de.ibm.com> - * Michael Holzheu <holzheu@linux.vnet.ibm.com> - */ - -#include <linux/linkage.h> -#include "bpf_jit.h" - -/* - * Calling convention: - * registers %r7-%r10, %r11,%r13, and %r15 are call saved - * - * Input (64 bit): - * %r3 (%b2) = offset into skb data - * %r6 (%b5) = return address - * %r7 (%b6) = skb pointer - * %r12 = skb data pointer - * - * Output: - * %r14= %b0 = return value (read skb value) - * - * Work registers: %r2,%r4,%r5,%r14 - * - * skb_copy_bits takes 4 parameters: - * %r2 = skb pointer - * %r3 = offset into skb data - * %r4 = pointer to temp buffer - * %r5 = length to copy - * Return value in %r2: 0 = ok - * - * bpf_internal_load_pointer_neg_helper takes 3 parameters: - * %r2 = skb pointer - * %r3 = offset into data - * %r4 = length to copy - * Return value in %r2: Pointer to data - */ - -#define SKF_MAX_NEG_OFF -0x200000 /* SKF_LL_OFF from filter.h */ - -/* - * Load SIZE bytes from SKB - */ -#define sk_load_common(NAME, SIZE, LOAD) \ -ENTRY(sk_load_##NAME); \ - ltgr %r3,%r3; /* Is offset negative? */ \ - jl sk_load_##NAME##_slow_neg; \ -ENTRY(sk_load_##NAME##_pos); \ - aghi %r3,SIZE; /* Offset + SIZE */ \ - clg %r3,STK_OFF_HLEN(%r15); /* Offset + SIZE > hlen? */ \ - jh sk_load_##NAME##_slow; \ - LOAD %r14,-SIZE(%r3,%r12); /* Get data from skb */ \ - b OFF_OK(%r6); /* Return */ \ - \ -sk_load_##NAME##_slow:; \ - lgr %r2,%r7; /* Arg1 = skb pointer */ \ - aghi %r3,-SIZE; /* Arg2 = offset */ \ - la %r4,STK_OFF_TMP(%r15); /* Arg3 = temp bufffer */ \ - lghi %r5,SIZE; /* Arg4 = size */ \ - brasl %r14,skb_copy_bits; /* Get data from skb */ \ - LOAD %r14,STK_OFF_TMP(%r15); /* Load from temp bufffer */ \ - ltgr %r2,%r2; /* Set cc to (%r2 != 0) */ \ - br %r6; /* Return */ - -sk_load_common(word, 4, llgf) /* r14 = *(u32 *) (skb->data+offset) */ -sk_load_common(half, 2, llgh) /* r14 = *(u16 *) (skb->data+offset) */ - -/* - * Load 1 byte from SKB (optimized version) - */ - /* r14 = *(u8 *) (skb->data+offset) */ -ENTRY(sk_load_byte) - ltgr %r3,%r3 # Is offset negative? - jl sk_load_byte_slow_neg -ENTRY(sk_load_byte_pos) - clg %r3,STK_OFF_HLEN(%r15) # Offset >= hlen? - jnl sk_load_byte_slow - llgc %r14,0(%r3,%r12) # Get byte from skb - b OFF_OK(%r6) # Return OK - -sk_load_byte_slow: - lgr %r2,%r7 # Arg1 = skb pointer - # Arg2 = offset - la %r4,STK_OFF_TMP(%r15) # Arg3 = pointer to temp buffer - lghi %r5,1 # Arg4 = size (1 byte) - brasl %r14,skb_copy_bits # Get data from skb - llgc %r14,STK_OFF_TMP(%r15) # Load result from temp buffer - ltgr %r2,%r2 # Set cc to (%r2 != 0) - br %r6 # Return cc - -#define sk_negative_common(NAME, SIZE, LOAD) \ -sk_load_##NAME##_slow_neg:; \ - cgfi %r3,SKF_MAX_NEG_OFF; \ - jl bpf_error; \ - lgr %r2,%r7; /* Arg1 = skb pointer */ \ - /* Arg2 = offset */ \ - lghi %r4,SIZE; /* Arg3 = size */ \ - brasl %r14,bpf_internal_load_pointer_neg_helper; \ - ltgr %r2,%r2; \ - jz bpf_error; \ - LOAD %r14,0(%r2); /* Get data from pointer */ \ - xr %r3,%r3; /* Set cc to zero */ \ - br %r6; /* Return cc */ - -sk_negative_common(word, 4, llgf) -sk_negative_common(half, 2, llgh) -sk_negative_common(byte, 1, llgc) - -bpf_error: -# force a return 0 from jit handler - ltgr %r15,%r15 # Set condition code - br %r6 diff --git a/arch/s390/net/bpf_jit.h b/arch/s390/net/bpf_jit.h index 5e1e5133132d..7822ea92e54a 100644 --- a/arch/s390/net/bpf_jit.h +++ b/arch/s390/net/bpf_jit.h @@ -16,9 +16,6 @@ #include <linux/filter.h> #include <linux/types.h> -extern u8 sk_load_word_pos[], sk_load_half_pos[], sk_load_byte_pos[]; -extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; - #endif /* __ASSEMBLY__ */ /* @@ -36,15 +33,6 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; * | | | * | BPF stack | | * | | | - * +---------------+ | - * | 8 byte skbp | | - * R15+176 -> +---------------+ | - * | 8 byte hlen | | - * R15+168 -> +---------------+ | - * | 4 byte align | | - * +---------------+ | - * | 4 byte temp | | - * | for bpf_jit.S | | * R15+160 -> +---------------+ | * | new backchain | | * R15+152 -> +---------------+ | @@ -57,17 +45,11 @@ extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; * The stack size used by the BPF program ("BPF stack" above) is passed * via "aux->stack_depth". */ -#define STK_SPACE_ADD (8 + 8 + 4 + 4 + 160) +#define STK_SPACE_ADD (160) #define STK_160_UNUSED (160 - 12 * 8) #define STK_OFF (STK_SPACE_ADD - STK_160_UNUSED) -#define STK_OFF_TMP 160 /* Offset of tmp buffer on stack */ -#define STK_OFF_HLEN 168 /* Offset of SKB header length on stack */ -#define STK_OFF_SKBP 176 /* Offset of SKB pointer on stack */ #define STK_OFF_R6 (160 - 11 * 8) /* Offset of r6 on stack */ #define STK_OFF_TCCNT (160 - 12 * 8) /* Offset of tail_call_cnt on stack */ -/* Offset to skip condition code check */ -#define OFF_OK 4 - #endif /* __ARCH_S390_NET_BPF_JIT_H */ diff --git a/arch/s390/net/bpf_jit_comp.c b/arch/s390/net/bpf_jit_comp.c index 78a19c93b380..b020bea040b7 100644 --- a/arch/s390/net/bpf_jit_comp.c +++ b/arch/s390/net/bpf_jit_comp.c @@ -47,23 +47,21 @@ struct bpf_jit { #define BPF_SIZE_MAX 0xffff /* Max size for program (16 bit branches) */ -#define SEEN_SKB 1 /* skb access */ -#define SEEN_MEM 2 /* use mem[] for temporary storage */ -#define SEEN_RET0 4 /* ret0_ip points to a valid return 0 */ -#define SEEN_LITERAL 8 /* code uses literals */ -#define SEEN_FUNC 16 /* calls C functions */ -#define SEEN_TAIL_CALL 32 /* code uses tail calls */ -#define SEEN_REG_AX 64 /* code uses constant blinding */ -#define SEEN_STACK (SEEN_FUNC | SEEN_MEM | SEEN_SKB) +#define SEEN_MEM (1 << 0) /* use mem[] for temporary storage */ +#define SEEN_RET0 (1 << 1) /* ret0_ip points to a valid return 0 */ +#define SEEN_LITERAL (1 << 2) /* code uses literals */ +#define SEEN_FUNC (1 << 3) /* calls C functions */ +#define SEEN_TAIL_CALL (1 << 4) /* code uses tail calls */ +#define SEEN_REG_AX (1 << 5) /* code uses constant blinding */ +#define SEEN_STACK (SEEN_FUNC | SEEN_MEM) /* * s390 registers */ #define REG_W0 (MAX_BPF_JIT_REG + 0) /* Work register 1 (even) */ #define REG_W1 (MAX_BPF_JIT_REG + 1) /* Work register 2 (odd) */ -#define REG_SKB_DATA (MAX_BPF_JIT_REG + 2) /* SKB data register */ -#define REG_L (MAX_BPF_JIT_REG + 3) /* Literal pool register */ -#define REG_15 (MAX_BPF_JIT_REG + 4) /* Register 15 */ +#define REG_L (MAX_BPF_JIT_REG + 2) /* Literal pool register */ +#define REG_15 (MAX_BPF_JIT_REG + 3) /* Register 15 */ #define REG_0 REG_W0 /* Register 0 */ #define REG_1 REG_W1 /* Register 1 */ #define REG_2 BPF_REG_1 /* Register 2 */ @@ -88,10 +86,8 @@ static const int reg2hex[] = { [BPF_REG_9] = 10, /* BPF stack pointer */ [BPF_REG_FP] = 13, - /* Register for blinding (shared with REG_SKB_DATA) */ + /* Register for blinding */ [BPF_REG_AX] = 12, - /* SKB data pointer */ - [REG_SKB_DATA] = 12, /* Work registers for s390x backend */ [REG_W0] = 0, [REG_W1] = 1, @@ -385,27 +381,6 @@ static void save_restore_regs(struct bpf_jit *jit, int op, u32 stack_depth) } /* - * For SKB access %b1 contains the SKB pointer. For "bpf_jit.S" - * we store the SKB header length on the stack and the SKB data - * pointer in REG_SKB_DATA if BPF_REG_AX is not used. - */ -static void emit_load_skb_data_hlen(struct bpf_jit *jit) -{ - /* Header length: llgf %w1,<len>(%b1) */ - EMIT6_DISP_LH(0xe3000000, 0x0016, REG_W1, REG_0, BPF_REG_1, - offsetof(struct sk_buff, len)); - /* s %w1,<data_len>(%b1) */ - EMIT4_DISP(0x5b000000, REG_W1, BPF_REG_1, - offsetof(struct sk_buff, data_len)); - /* stg %w1,ST_OFF_HLEN(%r0,%r15) */ - EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, STK_OFF_HLEN); - if (!(jit->seen & SEEN_REG_AX)) - /* lg %skb_data,data_off(%b1) */ - EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0, - BPF_REG_1, offsetof(struct sk_buff, data)); -} - -/* * Emit function prologue * * Save registers and create stack frame if necessary. @@ -445,12 +420,6 @@ static void bpf_jit_prologue(struct bpf_jit *jit, u32 stack_depth) EMIT6_DISP_LH(0xe3000000, 0x0024, REG_W1, REG_0, REG_15, 152); } - if (jit->seen & SEEN_SKB) { - emit_load_skb_data_hlen(jit); - /* stg %b1,ST_OFF_SKBP(%r0,%r15) */ - EMIT6_DISP_LH(0xe3000000, 0x0024, BPF_REG_1, REG_0, REG_15, - STK_OFF_SKBP); - } } /* @@ -483,12 +452,12 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i { struct bpf_insn *insn = &fp->insnsi[i]; int jmp_off, last, insn_count = 1; - unsigned int func_addr, mask; u32 dst_reg = insn->dst_reg; u32 src_reg = insn->src_reg; u32 *addrs = jit->addrs; s32 imm = insn->imm; s16 off = insn->off; + unsigned int mask; if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX) jit->seen |= SEEN_REG_AX; @@ -970,13 +939,6 @@ static noinline int bpf_jit_insn(struct bpf_jit *jit, struct bpf_prog *fp, int i EMIT2(0x0d00, REG_14, REG_W1); /* lgr %b0,%r2: load return value into %b0 */ EMIT4(0xb9040000, BPF_REG_0, REG_2); - if ((jit->seen & SEEN_SKB) && - bpf_helper_changes_pkt_data((void *)func)) { - /* lg %b1,ST_OFF_SKBP(%r15) */ - EMIT6_DISP_LH(0xe3000000, 0x0004, BPF_REG_1, REG_0, - REG_15, STK_OFF_SKBP); - emit_load_skb_data_hlen(jit); - } break; } case BPF_JMP | BPF_TAIL_CALL: @@ -1176,73 +1138,6 @@ branch_oc: jmp_off = addrs[i + off + 1] - (addrs[i + 1] - 4); EMIT4_PCREL(0xa7040000 | mask << 8, jmp_off); break; - /* - * BPF_LD - */ - case BPF_LD | BPF_ABS | BPF_B: /* b0 = *(u8 *) (skb->data+imm) */ - case BPF_LD | BPF_IND | BPF_B: /* b0 = *(u8 *) (skb->data+imm+src) */ - if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0)) - func_addr = __pa(sk_load_byte_pos); - else - func_addr = __pa(sk_load_byte); - goto call_fn; - case BPF_LD | BPF_ABS | BPF_H: /* b0 = *(u16 *) (skb->data+imm) */ - case BPF_LD | BPF_IND | BPF_H: /* b0 = *(u16 *) (skb->data+imm+src) */ - if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0)) - func_addr = __pa(sk_load_half_pos); - else - func_addr = __pa(sk_load_half); - goto call_fn; - case BPF_LD | BPF_ABS | BPF_W: /* b0 = *(u32 *) (skb->data+imm) */ - case BPF_LD | BPF_IND | BPF_W: /* b0 = *(u32 *) (skb->data+imm+src) */ - if ((BPF_MODE(insn->code) == BPF_ABS) && (imm >= 0)) - func_addr = __pa(sk_load_word_pos); - else - func_addr = __pa(sk_load_word); - goto call_fn; -call_fn: - jit->seen |= SEEN_SKB | SEEN_RET0 | SEEN_FUNC; - REG_SET_SEEN(REG_14); /* Return address of possible func call */ - - /* - * Implicit input: - * BPF_REG_6 (R7) : skb pointer - * REG_SKB_DATA (R12): skb data pointer (if no BPF_REG_AX) - * - * Calculated input: - * BPF_REG_2 (R3) : offset of byte(s) to fetch in skb - * BPF_REG_5 (R6) : return address - * - * Output: - * BPF_REG_0 (R14): data read from skb - * - * Scratch registers (BPF_REG_1-5) - */ - - /* Call function: llilf %w1,func_addr */ - EMIT6_IMM(0xc00f0000, REG_W1, func_addr); - - /* Offset: lgfi %b2,imm */ - EMIT6_IMM(0xc0010000, BPF_REG_2, imm); - if (BPF_MODE(insn->code) == BPF_IND) - /* agfr %b2,%src (%src is s32 here) */ - EMIT4(0xb9180000, BPF_REG_2, src_reg); - - /* Reload REG_SKB_DATA if BPF_REG_AX is used */ - if (jit->seen & SEEN_REG_AX) - /* lg %skb_data,data_off(%b6) */ - EMIT6_DISP_LH(0xe3000000, 0x0004, REG_SKB_DATA, REG_0, - BPF_REG_6, offsetof(struct sk_buff, data)); - /* basr %b5,%w1 (%b5 is call saved) */ - EMIT2(0x0d00, BPF_REG_5, REG_W1); - - /* - * Note: For fast access we jump directly after the - * jnz instruction from bpf_jit.S - */ - /* jnz <ret0> */ - EMIT4_PCREL(0xa7740000, jit->ret0_ip - jit->prg); - break; default: /* too complex, give up */ pr_err("Unknown opcode %02x\n", insn->code); return -1; diff --git a/arch/sparc/net/Makefile b/arch/sparc/net/Makefile index 76fa8e95b721..d32aac3a25b8 100644 --- a/arch/sparc/net/Makefile +++ b/arch/sparc/net/Makefile @@ -1,4 +1,7 @@ # # Arch-specific network modules # -obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_$(BITS).o bpf_jit_comp_$(BITS).o +obj-$(CONFIG_BPF_JIT) += bpf_jit_comp_$(BITS).o +ifeq ($(BITS),32) +obj-$(CONFIG_BPF_JIT) += bpf_jit_asm_32.o +endif diff --git a/arch/sparc/net/bpf_jit_64.h b/arch/sparc/net/bpf_jit_64.h index 428f7fd19175..fbc836f1c51c 100644 --- a/arch/sparc/net/bpf_jit_64.h +++ b/arch/sparc/net/bpf_jit_64.h @@ -33,35 +33,6 @@ #define I5 0x1d #define FP 0x1e #define I7 0x1f - -#define r_SKB L0 -#define r_HEADLEN L4 -#define r_SKB_DATA L5 -#define r_TMP G1 -#define r_TMP2 G3 - -/* assembly code in arch/sparc/net/bpf_jit_asm_64.S */ -extern u32 bpf_jit_load_word[]; -extern u32 bpf_jit_load_half[]; -extern u32 bpf_jit_load_byte[]; -extern u32 bpf_jit_load_byte_msh[]; -extern u32 bpf_jit_load_word_positive_offset[]; -extern u32 bpf_jit_load_half_positive_offset[]; -extern u32 bpf_jit_load_byte_positive_offset[]; -extern u32 bpf_jit_load_byte_msh_positive_offset[]; -extern u32 bpf_jit_load_word_negative_offset[]; -extern u32 bpf_jit_load_half_negative_offset[]; -extern u32 bpf_jit_load_byte_negative_offset[]; -extern u32 bpf_jit_load_byte_msh_negative_offset[]; - -#else -#define r_RESULT %o0 -#define r_SKB %o0 -#define r_OFF %o1 -#define r_HEADLEN %l4 -#define r_SKB_DATA %l5 -#define r_TMP %g1 -#define r_TMP2 %g3 #endif #endif /* _BPF_JIT_H */ diff --git a/arch/sparc/net/bpf_jit_asm_64.S b/arch/sparc/net/bpf_jit_asm_64.S deleted file mode 100644 index 7177867052a1..000000000000 --- a/arch/sparc/net/bpf_jit_asm_64.S +++ /dev/null @@ -1,162 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#include <asm/ptrace.h> - -#include "bpf_jit_64.h" - -#define SAVE_SZ 176 -#define SCRATCH_OFF STACK_BIAS + 128 -#define BE_PTR(label) be,pn %xcc, label -#define SIGN_EXTEND(reg) sra reg, 0, reg - -#define SKF_MAX_NEG_OFF (-0x200000) /* SKF_LL_OFF from filter.h */ - - .text - .globl bpf_jit_load_word -bpf_jit_load_word: - cmp r_OFF, 0 - bl bpf_slow_path_word_neg - nop - .globl bpf_jit_load_word_positive_offset -bpf_jit_load_word_positive_offset: - sub r_HEADLEN, r_OFF, r_TMP - cmp r_TMP, 3 - ble bpf_slow_path_word - add r_SKB_DATA, r_OFF, r_TMP - andcc r_TMP, 3, %g0 - bne load_word_unaligned - nop - retl - ld [r_TMP], r_RESULT -load_word_unaligned: - ldub [r_TMP + 0x0], r_OFF - ldub [r_TMP + 0x1], r_TMP2 - sll r_OFF, 8, r_OFF - or r_OFF, r_TMP2, r_OFF - ldub [r_TMP + 0x2], r_TMP2 - sll r_OFF, 8, r_OFF - or r_OFF, r_TMP2, r_OFF - ldub [r_TMP + 0x3], r_TMP2 - sll r_OFF, 8, r_OFF - retl - or r_OFF, r_TMP2, r_RESULT - - .globl bpf_jit_load_half -bpf_jit_load_half: - cmp r_OFF, 0 - bl bpf_slow_path_half_neg - nop - .globl bpf_jit_load_half_positive_offset -bpf_jit_load_half_positive_offset: - sub r_HEADLEN, r_OFF, r_TMP - cmp r_TMP, 1 - ble bpf_slow_path_half - add r_SKB_DATA, r_OFF, r_TMP - andcc r_TMP, 1, %g0 - bne load_half_unaligned - nop - retl - lduh [r_TMP], r_RESULT -load_half_unaligned: - ldub [r_TMP + 0x0], r_OFF - ldub [r_TMP + 0x1], r_TMP2 - sll r_OFF, 8, r_OFF - retl - or r_OFF, r_TMP2, r_RESULT - - .globl bpf_jit_load_byte -bpf_jit_load_byte: - cmp r_OFF, 0 - bl bpf_slow_path_byte_neg - nop - .globl bpf_jit_load_byte_positive_offset -bpf_jit_load_byte_positive_offset: - cmp r_OFF, r_HEADLEN - bge bpf_slow_path_byte - nop - retl - ldub [r_SKB_DATA + r_OFF], r_RESULT - -#define bpf_slow_path_common(LEN) \ - save %sp, -SAVE_SZ, %sp; \ - mov %i0, %o0; \ - mov %i1, %o1; \ - add %fp, SCRATCH_OFF, %o2; \ - call skb_copy_bits; \ - mov (LEN), %o3; \ - cmp %o0, 0; \ - restore; - -bpf_slow_path_word: - bpf_slow_path_common(4) - bl bpf_error - ld [%sp + SCRATCH_OFF], r_RESULT - retl - nop -bpf_slow_path_half: - bpf_slow_path_common(2) - bl bpf_error - lduh [%sp + SCRATCH_OFF], r_RESULT - retl - nop -bpf_slow_path_byte: - bpf_slow_path_common(1) - bl bpf_error - ldub [%sp + SCRATCH_OFF], r_RESULT - retl - nop - -#define bpf_negative_common(LEN) \ - save %sp, -SAVE_SZ, %sp; \ - mov %i0, %o0; \ - mov %i1, %o1; \ - SIGN_EXTEND(%o1); \ - call bpf_internal_load_pointer_neg_helper; \ - mov (LEN), %o2; \ - mov %o0, r_TMP; \ - cmp %o0, 0; \ - BE_PTR(bpf_error); \ - restore; - -bpf_slow_path_word_neg: - sethi %hi(SKF_MAX_NEG_OFF), r_TMP - cmp r_OFF, r_TMP - bl bpf_error - nop - .globl bpf_jit_load_word_negative_offset -bpf_jit_load_word_negative_offset: - bpf_negative_common(4) - andcc r_TMP, 3, %g0 - bne load_word_unaligned - nop - retl - ld [r_TMP], r_RESULT - -bpf_slow_path_half_neg: - sethi %hi(SKF_MAX_NEG_OFF), r_TMP - cmp r_OFF, r_TMP - bl bpf_error - nop - .globl bpf_jit_load_half_negative_offset -bpf_jit_load_half_negative_offset: - bpf_negative_common(2) - andcc r_TMP, 1, %g0 - bne load_half_unaligned - nop - retl - lduh [r_TMP], r_RESULT - -bpf_slow_path_byte_neg: - sethi %hi(SKF_MAX_NEG_OFF), r_TMP - cmp r_OFF, r_TMP - bl bpf_error - nop - .globl bpf_jit_load_byte_negative_offset -bpf_jit_load_byte_negative_offset: - bpf_negative_common(1) - retl - ldub [r_TMP], r_RESULT - -bpf_error: - /* Make the JIT program itself return zero. */ - ret - restore %g0, %g0, %o0 diff --git a/arch/sparc/net/bpf_jit_comp_64.c b/arch/sparc/net/bpf_jit_comp_64.c index 48a25869349b..9f5918e0693a 100644 --- a/arch/sparc/net/bpf_jit_comp_64.c +++ b/arch/sparc/net/bpf_jit_comp_64.c @@ -48,10 +48,6 @@ static void bpf_flush_icache(void *start_, void *end_) } } -#define SEEN_DATAREF 1 /* might call external helpers */ -#define SEEN_XREG 2 /* ebx is used */ -#define SEEN_MEM 4 /* use mem[] for temporary storage */ - #define S13(X) ((X) & 0x1fff) #define S5(X) ((X) & 0x1f) #define IMMED 0x00002000 @@ -198,7 +194,6 @@ struct jit_ctx { bool tmp_1_used; bool tmp_2_used; bool tmp_3_used; - bool saw_ld_abs_ind; bool saw_frame_pointer; bool saw_call; bool saw_tail_call; @@ -207,9 +202,7 @@ struct jit_ctx { #define TMP_REG_1 (MAX_BPF_JIT_REG + 0) #define TMP_REG_2 (MAX_BPF_JIT_REG + 1) -#define SKB_HLEN_REG (MAX_BPF_JIT_REG + 2) -#define SKB_DATA_REG (MAX_BPF_JIT_REG + 3) -#define TMP_REG_3 (MAX_BPF_JIT_REG + 4) +#define TMP_REG_3 (MAX_BPF_JIT_REG + 2) /* Map BPF registers to SPARC registers */ static const int bpf2sparc[] = { @@ -238,9 +231,6 @@ static const int bpf2sparc[] = { [TMP_REG_1] = G1, [TMP_REG_2] = G2, [TMP_REG_3] = G3, - - [SKB_HLEN_REG] = L4, - [SKB_DATA_REG] = L5, }; static void emit(const u32 insn, struct jit_ctx *ctx) @@ -800,25 +790,6 @@ static int emit_compare_and_branch(const u8 code, const u8 dst, u8 src, return 0; } -static void load_skb_regs(struct jit_ctx *ctx, u8 r_skb) -{ - const u8 r_headlen = bpf2sparc[SKB_HLEN_REG]; - const u8 r_data = bpf2sparc[SKB_DATA_REG]; - const u8 r_tmp = bpf2sparc[TMP_REG_1]; - unsigned int off; - - off = offsetof(struct sk_buff, len); - emit(LD32I | RS1(r_skb) | S13(off) | RD(r_headlen), ctx); - - off = offsetof(struct sk_buff, data_len); - emit(LD32I | RS1(r_skb) | S13(off) | RD(r_tmp), ctx); - - emit(SUB | RS1(r_headlen) | RS2(r_tmp) | RD(r_headlen), ctx); - - off = offsetof(struct sk_buff, data); - emit(LDPTRI | RS1(r_skb) | S13(off) | RD(r_data), ctx); -} - /* Just skip the save instruction and the ctx register move. */ #define BPF_TAILCALL_PROLOGUE_SKIP 16 #define BPF_TAILCALL_CNT_SP_OFF (STACK_BIAS + 128) @@ -857,9 +828,6 @@ static void build_prologue(struct jit_ctx *ctx) emit_reg_move(I0, O0, ctx); /* If you add anything here, adjust BPF_TAILCALL_PROLOGUE_SKIP above. */ - - if (ctx->saw_ld_abs_ind) - load_skb_regs(ctx, bpf2sparc[BPF_REG_1]); } static void build_epilogue(struct jit_ctx *ctx) @@ -1225,16 +1193,11 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) u8 *func = ((u8 *)__bpf_call_base) + imm; ctx->saw_call = true; - if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func)) - emit_reg_move(bpf2sparc[BPF_REG_1], L7, ctx); emit_call((u32 *)func, ctx); emit_nop(ctx); emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx); - - if (ctx->saw_ld_abs_ind && bpf_helper_changes_pkt_data(func)) - load_skb_regs(ctx, L7); break; } @@ -1412,43 +1375,6 @@ static int build_insn(const struct bpf_insn *insn, struct jit_ctx *ctx) emit_nop(ctx); break; } -#define CHOOSE_LOAD_FUNC(K, func) \ - ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) - - /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + imm)) */ - case BPF_LD | BPF_ABS | BPF_W: - func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_word); - goto common_load; - case BPF_LD | BPF_ABS | BPF_H: - func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_half); - goto common_load; - case BPF_LD | BPF_ABS | BPF_B: - func = CHOOSE_LOAD_FUNC(imm, bpf_jit_load_byte); - goto common_load; - /* R0 = ntohx(*(size *)(((struct sk_buff *)R6)->data + src + imm)) */ - case BPF_LD | BPF_IND | BPF_W: - func = bpf_jit_load_word; - goto common_load; - case BPF_LD | BPF_IND | BPF_H: - func = bpf_jit_load_half; - goto common_load; - - case BPF_LD | BPF_IND | BPF_B: - func = bpf_jit_load_byte; - common_load: - ctx->saw_ld_abs_ind = true; - - emit_reg_move(bpf2sparc[BPF_REG_6], O0, ctx); - emit_loadimm(imm, O1, ctx); - - if (BPF_MODE(code) == BPF_IND) - emit_alu(ADD, src, O1, ctx); - - emit_call(func, ctx); - emit_alu_K(SRA, O1, 0, ctx); - - emit_reg_move(O0, bpf2sparc[BPF_REG_0], ctx); - break; default: pr_err_once("unknown opcode %02x\n", code); @@ -1583,12 +1509,11 @@ skip_init_ctx: build_epilogue(&ctx); if (bpf_jit_enable > 1) - pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c%c]\n", pass, + pr_info("Pass %d: shrink = %d, seen = [%c%c%c%c%c%c]\n", pass, image_size - (ctx.idx * 4), ctx.tmp_1_used ? '1' : ' ', ctx.tmp_2_used ? '2' : ' ', ctx.tmp_3_used ? '3' : ' ', - ctx.saw_ld_abs_ind ? 'L' : ' ', ctx.saw_frame_pointer ? 'F' : ' ', ctx.saw_call ? 'C' : ' ', ctx.saw_tail_call ? 'T' : ' '); diff --git a/arch/x86/Kconfig b/arch/x86/Kconfig index c07f492b871a..d51a71dcbac2 100644 --- a/arch/x86/Kconfig +++ b/arch/x86/Kconfig @@ -138,7 +138,7 @@ config X86 select HAVE_DMA_CONTIGUOUS select HAVE_DYNAMIC_FTRACE select HAVE_DYNAMIC_FTRACE_WITH_REGS - select HAVE_EBPF_JIT if X86_64 + select HAVE_EBPF_JIT select HAVE_EFFICIENT_UNALIGNED_ACCESS select HAVE_EXIT_THREAD select HAVE_FENTRY if X86_64 || DYNAMIC_FTRACE diff --git a/arch/x86/include/asm/nospec-branch.h b/arch/x86/include/asm/nospec-branch.h index f928ad9b143f..2cd344d1a6e5 100644 --- a/arch/x86/include/asm/nospec-branch.h +++ b/arch/x86/include/asm/nospec-branch.h @@ -291,16 +291,20 @@ do { \ * lfence * jmp spec_trap * do_rop: - * mov %rax,(%rsp) + * mov %rax,(%rsp) for x86_64 + * mov %edx,(%esp) for x86_32 * retq * * Without retpolines configured: * - * jmp *%rax + * jmp *%rax for x86_64 + * jmp *%edx for x86_32 */ #ifdef CONFIG_RETPOLINE +#ifdef CONFIG_X86_64 # define RETPOLINE_RAX_BPF_JIT_SIZE 17 # define RETPOLINE_RAX_BPF_JIT() \ +do { \ EMIT1_off32(0xE8, 7); /* callq do_rop */ \ /* spec_trap: */ \ EMIT2(0xF3, 0x90); /* pause */ \ @@ -308,11 +312,31 @@ do { \ EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ /* do_rop: */ \ EMIT4(0x48, 0x89, 0x04, 0x24); /* mov %rax,(%rsp) */ \ - EMIT1(0xC3); /* retq */ + EMIT1(0xC3); /* retq */ \ +} while (0) #else +# define RETPOLINE_EDX_BPF_JIT() \ +do { \ + EMIT1_off32(0xE8, 7); /* call do_rop */ \ + /* spec_trap: */ \ + EMIT2(0xF3, 0x90); /* pause */ \ + EMIT3(0x0F, 0xAE, 0xE8); /* lfence */ \ + EMIT2(0xEB, 0xF9); /* jmp spec_trap */ \ + /* do_rop: */ \ + EMIT3(0x89, 0x14, 0x24); /* mov %edx,(%esp) */ \ + EMIT1(0xC3); /* ret */ \ +} while (0) +#endif +#else /* !CONFIG_RETPOLINE */ + +#ifdef CONFIG_X86_64 # define RETPOLINE_RAX_BPF_JIT_SIZE 2 # define RETPOLINE_RAX_BPF_JIT() \ EMIT2(0xFF, 0xE0); /* jmp *%rax */ +#else +# define RETPOLINE_EDX_BPF_JIT() \ + EMIT2(0xFF, 0xE2) /* jmp *%edx */ +#endif #endif #endif /* _ASM_X86_NOSPEC_BRANCH_H_ */ diff --git a/arch/x86/net/Makefile b/arch/x86/net/Makefile index fefb4b619598..59e123da580c 100644 --- a/arch/x86/net/Makefile +++ b/arch/x86/net/Makefile @@ -1,6 +1,9 @@ # # Arch-specific network modules # -OBJECT_FILES_NON_STANDARD_bpf_jit.o += y -obj-$(CONFIG_BPF_JIT) += bpf_jit.o bpf_jit_comp.o +ifeq ($(CONFIG_X86_32),y) + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp32.o +else + obj-$(CONFIG_BPF_JIT) += bpf_jit_comp.o +endif diff --git a/arch/x86/net/bpf_jit.S b/arch/x86/net/bpf_jit.S deleted file mode 100644 index b33093f84528..000000000000 --- a/arch/x86/net/bpf_jit.S +++ /dev/null @@ -1,154 +0,0 @@ -/* bpf_jit.S : BPF JIT helper functions - * - * Copyright (C) 2011 Eric Dumazet (eric.dumazet@gmail.com) - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of the GNU General Public License - * as published by the Free Software Foundation; version 2 - * of the License. - */ -#include <linux/linkage.h> -#include <asm/frame.h> - -/* - * Calling convention : - * rbx : skb pointer (callee saved) - * esi : offset of byte(s) to fetch in skb (can be scratched) - * r10 : copy of skb->data - * r9d : hlen = skb->len - skb->data_len - */ -#define SKBDATA %r10 -#define SKF_MAX_NEG_OFF $(-0x200000) /* SKF_LL_OFF from filter.h */ - -#define FUNC(name) \ - .globl name; \ - .type name, @function; \ - name: - -FUNC(sk_load_word) - test %esi,%esi - js bpf_slow_path_word_neg - -FUNC(sk_load_word_positive_offset) - mov %r9d,%eax # hlen - sub %esi,%eax # hlen - offset - cmp $3,%eax - jle bpf_slow_path_word - mov (SKBDATA,%rsi),%eax - bswap %eax /* ntohl() */ - ret - -FUNC(sk_load_half) - test %esi,%esi - js bpf_slow_path_half_neg - -FUNC(sk_load_half_positive_offset) - mov %r9d,%eax - sub %esi,%eax # hlen - offset - cmp $1,%eax - jle bpf_slow_path_half - movzwl (SKBDATA,%rsi),%eax - rol $8,%ax # ntohs() - ret - -FUNC(sk_load_byte) - test %esi,%esi - js bpf_slow_path_byte_neg - -FUNC(sk_load_byte_positive_offset) - cmp %esi,%r9d /* if (offset >= hlen) goto bpf_slow_path_byte */ - jle bpf_slow_path_byte - movzbl (SKBDATA,%rsi),%eax - ret - -/* rsi contains offset and can be scratched */ -#define bpf_slow_path_common(LEN) \ - lea 32(%rbp), %rdx;\ - FRAME_BEGIN; \ - mov %rbx, %rdi; /* arg1 == skb */ \ - push %r9; \ - push SKBDATA; \ -/* rsi already has offset */ \ - mov $LEN,%ecx; /* len */ \ - call skb_copy_bits; \ - test %eax,%eax; \ - pop SKBDATA; \ - pop %r9; \ - FRAME_END - - -bpf_slow_path_word: - bpf_slow_path_common(4) - js bpf_error - mov 32(%rbp),%eax - bswap %eax - ret - -bpf_slow_path_half: - bpf_slow_path_common(2) - js bpf_error - mov 32(%rbp),%ax - rol $8,%ax - movzwl %ax,%eax - ret - -bpf_slow_path_byte: - bpf_slow_path_common(1) - js bpf_error - movzbl 32(%rbp),%eax - ret - -#define sk_negative_common(SIZE) \ - FRAME_BEGIN; \ - mov %rbx, %rdi; /* arg1 == skb */ \ - push %r9; \ - push SKBDATA; \ -/* rsi already has offset */ \ - mov $SIZE,%edx; /* size */ \ - call bpf_internal_load_pointer_neg_helper; \ - test %rax,%rax; \ - pop SKBDATA; \ - pop %r9; \ - FRAME_END; \ - jz bpf_error - -bpf_slow_path_word_neg: - cmp SKF_MAX_NEG_OFF, %esi /* test range */ - jl bpf_error /* offset lower -> error */ - -FUNC(sk_load_word_negative_offset) - sk_negative_common(4) - mov (%rax), %eax - bswap %eax - ret - -bpf_slow_path_half_neg: - cmp SKF_MAX_NEG_OFF, %esi - jl bpf_error - -FUNC(sk_load_half_negative_offset) - sk_negative_common(2) - mov (%rax),%ax - rol $8,%ax - movzwl %ax,%eax - ret - -bpf_slow_path_byte_neg: - cmp SKF_MAX_NEG_OFF, %esi - jl bpf_error - -FUNC(sk_load_byte_negative_offset) - sk_negative_common(1) - movzbl (%rax), %eax - ret - -bpf_error: -# force a return 0 from jit handler - xor %eax,%eax - mov (%rbp),%rbx - mov 8(%rbp),%r13 - mov 16(%rbp),%r14 - mov 24(%rbp),%r15 - add $40, %rbp - leaveq - ret diff --git a/arch/x86/net/bpf_jit_comp.c b/arch/x86/net/bpf_jit_comp.c index 263c8453815e..8fca446aaef6 100644 --- a/arch/x86/net/bpf_jit_comp.c +++ b/arch/x86/net/bpf_jit_comp.c @@ -1,4 +1,5 @@ -/* bpf_jit_comp.c : BPF JIT compiler +/* + * bpf_jit_comp.c: BPF JIT compiler * * Copyright (C) 2011-2013 Eric Dumazet (eric.dumazet@gmail.com) * Internal BPF Copyright (c) 2011-2014 PLUMgrid, http://plumgrid.com @@ -16,15 +17,6 @@ #include <asm/set_memory.h> #include <asm/nospec-branch.h> -/* - * assembly code in arch/x86/net/bpf_jit.S - */ -extern u8 sk_load_word[], sk_load_half[], sk_load_byte[]; -extern u8 sk_load_word_positive_offset[], sk_load_half_positive_offset[]; -extern u8 sk_load_byte_positive_offset[]; -extern u8 sk_load_word_negative_offset[], sk_load_half_negative_offset[]; -extern u8 sk_load_byte_negative_offset[]; - static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) { if (len == 1) @@ -45,14 +37,15 @@ static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) #define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) #define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) #define EMIT4(b1, b2, b3, b4) EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) + #define EMIT1_off32(b1, off) \ - do {EMIT1(b1); EMIT(off, 4); } while (0) + do { EMIT1(b1); EMIT(off, 4); } while (0) #define EMIT2_off32(b1, b2, off) \ - do {EMIT2(b1, b2); EMIT(off, 4); } while (0) + do { EMIT2(b1, b2); EMIT(off, 4); } while (0) #define EMIT3_off32(b1, b2, b3, off) \ - do {EMIT3(b1, b2, b3); EMIT(off, 4); } while (0) + do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0) #define EMIT4_off32(b1, b2, b3, b4, off) \ - do {EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) + do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) static bool is_imm8(int value) { @@ -70,9 +63,10 @@ static bool is_uimm32(u64 value) } /* mov dst, src */ -#define EMIT_mov(DST, SRC) \ - do {if (DST != SRC) \ - EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \ +#define EMIT_mov(DST, SRC) \ + do { \ + if (DST != SRC) \ + EMIT3(add_2mod(0x48, DST, SRC), 0x89, add_2reg(0xC0, DST, SRC)); \ } while (0) static int bpf_size_to_x86_bytes(int bpf_size) @@ -89,7 +83,8 @@ static int bpf_size_to_x86_bytes(int bpf_size) return 0; } -/* list of x86 cond jumps opcodes (. + s8) +/* + * List of x86 cond jumps opcodes (. + s8) * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32) */ #define X86_JB 0x72 @@ -103,38 +98,37 @@ static int bpf_size_to_x86_bytes(int bpf_size) #define X86_JLE 0x7E #define X86_JG 0x7F -#define CHOOSE_LOAD_FUNC(K, func) \ - ((int)K < 0 ? ((int)K >= SKF_LL_OFF ? func##_negative_offset : func) : func##_positive_offset) - -/* pick a register outside of BPF range for JIT internal work */ +/* Pick a register outside of BPF range for JIT internal work */ #define AUX_REG (MAX_BPF_JIT_REG + 1) -/* The following table maps BPF registers to x64 registers. +/* + * The following table maps BPF registers to x86-64 registers. * - * x64 register r12 is unused, since if used as base address + * x86-64 register R12 is unused, since if used as base address * register in load/store instructions, it always needs an * extra byte of encoding and is callee saved. * - * r9 caches skb->len - skb->data_len - * r10 caches skb->data, and used for blinding (if enabled) + * Also x86-64 register R9 is unused. x86-64 register R10 is + * used for blinding (if enabled). */ static const int reg2hex[] = { - [BPF_REG_0] = 0, /* rax */ - [BPF_REG_1] = 7, /* rdi */ - [BPF_REG_2] = 6, /* rsi */ - [BPF_REG_3] = 2, /* rdx */ - [BPF_REG_4] = 1, /* rcx */ - [BPF_REG_5] = 0, /* r8 */ - [BPF_REG_6] = 3, /* rbx callee saved */ - [BPF_REG_7] = 5, /* r13 callee saved */ - [BPF_REG_8] = 6, /* r14 callee saved */ - [BPF_REG_9] = 7, /* r15 callee saved */ - [BPF_REG_FP] = 5, /* rbp readonly */ - [BPF_REG_AX] = 2, /* r10 temp register */ - [AUX_REG] = 3, /* r11 temp register */ + [BPF_REG_0] = 0, /* RAX */ + [BPF_REG_1] = 7, /* RDI */ + [BPF_REG_2] = 6, /* RSI */ + [BPF_REG_3] = 2, /* RDX */ + [BPF_REG_4] = 1, /* RCX */ + [BPF_REG_5] = 0, /* R8 */ + [BPF_REG_6] = 3, /* RBX callee saved */ + [BPF_REG_7] = 5, /* R13 callee saved */ + [BPF_REG_8] = 6, /* R14 callee saved */ + [BPF_REG_9] = 7, /* R15 callee saved */ + [BPF_REG_FP] = 5, /* RBP readonly */ + [BPF_REG_AX] = 2, /* R10 temp register */ + [AUX_REG] = 3, /* R11 temp register */ }; -/* is_ereg() == true if BPF register 'reg' maps to x64 r8..r15 +/* + * is_ereg() == true if BPF register 'reg' maps to x86-64 r8..r15 * which need extra byte of encoding. * rax,rcx,...,rbp have simpler encoding */ @@ -153,7 +147,7 @@ static bool is_axreg(u32 reg) return reg == BPF_REG_0; } -/* add modifiers if 'reg' maps to x64 registers r8..r15 */ +/* Add modifiers if 'reg' maps to x86-64 registers R8..R15 */ static u8 add_1mod(u8 byte, u32 reg) { if (is_ereg(reg)) @@ -170,13 +164,13 @@ static u8 add_2mod(u8 byte, u32 r1, u32 r2) return byte; } -/* encode 'dst_reg' register into x64 opcode 'byte' */ +/* Encode 'dst_reg' register into x86-64 opcode 'byte' */ static u8 add_1reg(u8 byte, u32 dst_reg) { return byte + reg2hex[dst_reg]; } -/* encode 'dst_reg' and 'src_reg' registers into x64 opcode 'byte' */ +/* Encode 'dst_reg' and 'src_reg' registers into x86-64 opcode 'byte' */ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) { return byte + reg2hex[dst_reg] + (reg2hex[src_reg] << 3); @@ -184,27 +178,24 @@ static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) static void jit_fill_hole(void *area, unsigned int size) { - /* fill whole space with int3 instructions */ + /* Fill whole space with INT3 instructions */ memset(area, 0xcc, size); } struct jit_context { - int cleanup_addr; /* epilogue code offset */ - bool seen_ld_abs; - bool seen_ax_reg; + int cleanup_addr; /* Epilogue code offset */ }; -/* maximum number of bytes emitted while JITing one eBPF insn */ +/* Maximum number of bytes emitted while JITing one eBPF insn */ #define BPF_MAX_INSN_SIZE 128 #define BPF_INSN_SAFETY 64 -#define AUX_STACK_SPACE \ - (32 /* space for rbx, r13, r14, r15 */ + \ - 8 /* space for skb_copy_bits() buffer */) +#define AUX_STACK_SPACE 40 /* Space for RBX, R13, R14, R15, tailcnt */ -#define PROLOGUE_SIZE 37 +#define PROLOGUE_SIZE 37 -/* emit x64 prologue code for BPF program and check it's size. +/* + * Emit x86-64 prologue code for BPF program and check its size. * bpf_tail_call helper will skip it while jumping into another program */ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) @@ -212,8 +203,11 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) u8 *prog = *pprog; int cnt = 0; - EMIT1(0x55); /* push rbp */ - EMIT3(0x48, 0x89, 0xE5); /* mov rbp,rsp */ + /* push rbp */ + EMIT1(0x55); + + /* mov rbp,rsp */ + EMIT3(0x48, 0x89, 0xE5); /* sub rsp, rounded_stack_depth + AUX_STACK_SPACE */ EMIT3_off32(0x48, 0x81, 0xEC, @@ -222,19 +216,8 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) /* sub rbp, AUX_STACK_SPACE */ EMIT4(0x48, 0x83, 0xED, AUX_STACK_SPACE); - /* all classic BPF filters use R6(rbx) save it */ - /* mov qword ptr [rbp+0],rbx */ EMIT4(0x48, 0x89, 0x5D, 0); - - /* bpf_convert_filter() maps classic BPF register X to R7 and uses R8 - * as temporary, so all tcpdump filters need to spill/fill R7(r13) and - * R8(r14). R9(r15) spill could be made conditional, but there is only - * one 'bpf_error' return path out of helper functions inside bpf_jit.S - * The overhead of extra spill is negligible for any filter other - * than synthetic ones. Therefore not worth adding complexity. - */ - /* mov qword ptr [rbp+8],r13 */ EMIT4(0x4C, 0x89, 0x6D, 8); /* mov qword ptr [rbp+16],r14 */ @@ -243,9 +226,10 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) EMIT4(0x4C, 0x89, 0x7D, 24); if (!ebpf_from_cbpf) { - /* Clear the tail call counter (tail_call_cnt): for eBPF tail + /* + * Clear the tail call counter (tail_call_cnt): for eBPF tail * calls we need to reset the counter to 0. It's done in two - * instructions, resetting rax register to 0, and moving it + * instructions, resetting RAX register to 0, and moving it * to the counter location. */ @@ -260,7 +244,9 @@ static void emit_prologue(u8 **pprog, u32 stack_depth, bool ebpf_from_cbpf) *pprog = prog; } -/* generate the following code: +/* + * Generate the following code: + * * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... * if (index >= array->map.max_entries) * goto out; @@ -278,23 +264,26 @@ static void emit_bpf_tail_call(u8 **pprog) int label1, label2, label3; int cnt = 0; - /* rdi - pointer to ctx + /* + * rdi - pointer to ctx * rsi - pointer to bpf_array * rdx - index in bpf_array */ - /* if (index >= array->map.max_entries) - * goto out; + /* + * if (index >= array->map.max_entries) + * goto out; */ EMIT2(0x89, 0xD2); /* mov edx, edx */ EMIT3(0x39, 0x56, /* cmp dword ptr [rsi + 16], edx */ offsetof(struct bpf_array, map.max_entries)); -#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* number of bytes to jump */ +#define OFFSET1 (41 + RETPOLINE_RAX_BPF_JIT_SIZE) /* Number of bytes to jump */ EMIT2(X86_JBE, OFFSET1); /* jbe out */ label1 = cnt; - /* if (tail_call_cnt > MAX_TAIL_CALL_CNT) - * goto out; + /* + * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; */ EMIT2_off32(0x8B, 0x85, 36); /* mov eax, dword ptr [rbp + 36] */ EMIT3(0x83, 0xF8, MAX_TAIL_CALL_CNT); /* cmp eax, MAX_TAIL_CALL_CNT */ @@ -308,8 +297,9 @@ static void emit_bpf_tail_call(u8 **pprog) EMIT4_off32(0x48, 0x8B, 0x84, 0xD6, /* mov rax, [rsi + rdx * 8 + offsetof(...)] */ offsetof(struct bpf_array, ptrs)); - /* if (prog == NULL) - * goto out; + /* + * if (prog == NULL) + * goto out; */ EMIT3(0x48, 0x85, 0xC0); /* test rax,rax */ #define OFFSET3 (8 + RETPOLINE_RAX_BPF_JIT_SIZE) @@ -321,7 +311,8 @@ static void emit_bpf_tail_call(u8 **pprog) offsetof(struct bpf_prog, bpf_func)); EMIT4(0x48, 0x83, 0xC0, PROLOGUE_SIZE); /* add rax, prologue_size */ - /* now we're ready to jump into next BPF program + /* + * Wow we're ready to jump into next BPF program * rdi == ctx (1st arg) * rax == prog->bpf_func + prologue_size */ @@ -334,26 +325,6 @@ static void emit_bpf_tail_call(u8 **pprog) *pprog = prog; } - -static void emit_load_skb_data_hlen(u8 **pprog) -{ - u8 *prog = *pprog; - int cnt = 0; - - /* r9d = skb->len - skb->data_len (headlen) - * r10 = skb->data - */ - /* mov %r9d, off32(%rdi) */ - EMIT3_off32(0x44, 0x8b, 0x8f, offsetof(struct sk_buff, len)); - - /* sub %r9d, off32(%rdi) */ - EMIT3_off32(0x44, 0x2b, 0x8f, offsetof(struct sk_buff, data_len)); - - /* mov %r10, off32(%rdi) */ - EMIT3_off32(0x4c, 0x8b, 0x97, offsetof(struct sk_buff, data)); - *pprog = prog; -} - static void emit_mov_imm32(u8 **pprog, bool sign_propagate, u32 dst_reg, const u32 imm32) { @@ -361,7 +332,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate, u8 b1, b2, b3; int cnt = 0; - /* optimization: if imm32 is positive, use 'mov %eax, imm32' + /* + * Optimization: if imm32 is positive, use 'mov %eax, imm32' * (which zero-extends imm32) to save 2 bytes. */ if (sign_propagate && (s32)imm32 < 0) { @@ -373,7 +345,8 @@ static void emit_mov_imm32(u8 **pprog, bool sign_propagate, goto done; } - /* optimization: if imm32 is zero, use 'xor %eax, %eax' + /* + * Optimization: if imm32 is zero, use 'xor %eax, %eax' * to save 3 bytes. */ if (imm32 == 0) { @@ -400,7 +373,8 @@ static void emit_mov_imm64(u8 **pprog, u32 dst_reg, int cnt = 0; if (is_uimm32(((u64)imm32_hi << 32) | (u32)imm32_lo)) { - /* For emitting plain u32, where sign bit must not be + /* + * For emitting plain u32, where sign bit must not be * propagated LLVM tends to load imm64 over mov32 * directly, so save couple of bytes by just doing * 'mov %eax, imm32' instead. @@ -439,8 +413,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, { struct bpf_insn *insn = bpf_prog->insnsi; int insn_cnt = bpf_prog->len; - bool seen_ld_abs = ctx->seen_ld_abs | (oldproglen == 0); - bool seen_ax_reg = ctx->seen_ax_reg | (oldproglen == 0); bool seen_exit = false; u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; int i, cnt = 0; @@ -450,9 +422,6 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, emit_prologue(&prog, bpf_prog->aux->stack_depth, bpf_prog_was_classic(bpf_prog)); - if (seen_ld_abs) - emit_load_skb_data_hlen(&prog); - for (i = 0; i < insn_cnt; i++, insn++) { const s32 imm32 = insn->imm; u32 dst_reg = insn->dst_reg; @@ -460,13 +429,9 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, u8 b2 = 0, b3 = 0; s64 jmp_offset; u8 jmp_cond; - bool reload_skb_data; int ilen; u8 *func; - if (dst_reg == BPF_REG_AX || src_reg == BPF_REG_AX) - ctx->seen_ax_reg = seen_ax_reg = true; - switch (insn->code) { /* ALU */ case BPF_ALU | BPF_ADD | BPF_X: @@ -525,7 +490,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, else if (is_ereg(dst_reg)) EMIT1(add_1mod(0x40, dst_reg)); - /* b3 holds 'normal' opcode, b2 short form only valid + /* + * b3 holds 'normal' opcode, b2 short form only valid * in case dst is eax/rax. */ switch (BPF_OP(insn->code)) { @@ -593,7 +559,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, /* mov rax, dst_reg */ EMIT_mov(BPF_REG_0, dst_reg); - /* xor edx, edx + /* + * xor edx, edx * equivalent to 'xor rdx, rdx', but one byte less */ EMIT2(0x31, 0xd2); @@ -655,7 +622,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, } break; } - /* shifts */ + /* Shifts */ case BPF_ALU | BPF_LSH | BPF_K: case BPF_ALU | BPF_RSH | BPF_K: case BPF_ALU | BPF_ARSH | BPF_K: @@ -686,7 +653,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU64 | BPF_RSH | BPF_X: case BPF_ALU64 | BPF_ARSH | BPF_X: - /* check for bad case when dst_reg == rcx */ + /* Check for bad case when dst_reg == rcx */ if (dst_reg == BPF_REG_4) { /* mov r11, dst_reg */ EMIT_mov(AUX_REG, dst_reg); @@ -724,13 +691,13 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU | BPF_END | BPF_FROM_BE: switch (imm32) { case 16: - /* emit 'ror %ax, 8' to swap lower 2 bytes */ + /* Emit 'ror %ax, 8' to swap lower 2 bytes */ EMIT1(0x66); if (is_ereg(dst_reg)) EMIT1(0x41); EMIT3(0xC1, add_1reg(0xC8, dst_reg), 8); - /* emit 'movzwl eax, ax' */ + /* Emit 'movzwl eax, ax' */ if (is_ereg(dst_reg)) EMIT3(0x45, 0x0F, 0xB7); else @@ -738,7 +705,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); break; case 32: - /* emit 'bswap eax' to swap lower 4 bytes */ + /* Emit 'bswap eax' to swap lower 4 bytes */ if (is_ereg(dst_reg)) EMIT2(0x41, 0x0F); else @@ -746,7 +713,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, EMIT1(add_1reg(0xC8, dst_reg)); break; case 64: - /* emit 'bswap rax' to swap 8 bytes */ + /* Emit 'bswap rax' to swap 8 bytes */ EMIT3(add_1mod(0x48, dst_reg), 0x0F, add_1reg(0xC8, dst_reg)); break; @@ -756,7 +723,8 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, case BPF_ALU | BPF_END | BPF_FROM_LE: switch (imm32) { case 16: - /* emit 'movzwl eax, ax' to zero extend 16-bit + /* + * Emit 'movzwl eax, ax' to zero extend 16-bit * into 64 bit */ if (is_ereg(dst_reg)) @@ -766,7 +734,7 @@ static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, EMIT1(add_2reg(0xC0, dst_reg, dst_reg)); break; case 32: - /* emit 'mov eax, eax' to clear upper 32-bits */ + /* Emit 'mov eax, eax' to clear upper 32-bits */ if (is_ereg(dst_reg)) EMIT1(0x45); EMIT2(0x89, add_2reg(0xC0, dst_reg, dst_reg)); @@ -809,9 +777,9 @@ st: if (is_imm8(insn->off)) /* STX: *(u8*)(dst_reg + off) = src_reg */ case BPF_STX | BPF_MEM | BPF_B: - /* emit 'mov byte ptr [rax + off], al' */ + /* Emit 'mov byte ptr [rax + off], al' */ if (is_ereg(dst_reg) || is_ereg(src_reg) || - /* have to add extra byte for x86 SIL, DIL regs */ + /* We have to add extra byte for x86 SIL, DIL regs */ src_reg == BPF_REG_1 || src_reg == BPF_REG_2) EMIT2(add_2mod(0x40, dst_reg, src_reg), 0x88); else @@ -840,25 +808,26 @@ stx: if (is_imm8(insn->off)) /* LDX: dst_reg = *(u8*)(src_reg + off) */ case BPF_LDX | BPF_MEM | BPF_B: - /* emit 'movzx rax, byte ptr [rax + off]' */ + /* Emit 'movzx rax, byte ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB6); goto ldx; case BPF_LDX | BPF_MEM | BPF_H: - /* emit 'movzx rax, word ptr [rax + off]' */ + /* Emit 'movzx rax, word ptr [rax + off]' */ EMIT3(add_2mod(0x48, src_reg, dst_reg), 0x0F, 0xB7); goto ldx; case BPF_LDX | BPF_MEM | BPF_W: - /* emit 'mov eax, dword ptr [rax+0x14]' */ + /* Emit 'mov eax, dword ptr [rax+0x14]' */ if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT2(add_2mod(0x40, src_reg, dst_reg), 0x8B); else EMIT1(0x8B); goto ldx; case BPF_LDX | BPF_MEM | BPF_DW: - /* emit 'mov rax, qword ptr [rax+0x14]' */ + /* Emit 'mov rax, qword ptr [rax+0x14]' */ EMIT2(add_2mod(0x48, src_reg, dst_reg), 0x8B); -ldx: /* if insn->off == 0 we can save one extra byte, but - * special case of x86 r13 which always needs an offset +ldx: /* + * If insn->off == 0 we can save one extra byte, but + * special case of x86 R13 which always needs an offset * is not worth the hassle */ if (is_imm8(insn->off)) @@ -870,7 +839,7 @@ ldx: /* if insn->off == 0 we can save one extra byte, but /* STX XADD: lock *(u32*)(dst_reg + off) += src_reg */ case BPF_STX | BPF_XADD | BPF_W: - /* emit 'lock add dword ptr [rax + off], eax' */ + /* Emit 'lock add dword ptr [rax + off], eax' */ if (is_ereg(dst_reg) || is_ereg(src_reg)) EMIT3(0xF0, add_2mod(0x40, dst_reg, src_reg), 0x01); else @@ -889,35 +858,12 @@ xadd: if (is_imm8(insn->off)) case BPF_JMP | BPF_CALL: func = (u8 *) __bpf_call_base + imm32; jmp_offset = func - (image + addrs[i]); - if (seen_ld_abs) { - reload_skb_data = bpf_helper_changes_pkt_data(func); - if (reload_skb_data) { - EMIT1(0x57); /* push %rdi */ - jmp_offset += 22; /* pop, mov, sub, mov */ - } else { - EMIT2(0x41, 0x52); /* push %r10 */ - EMIT2(0x41, 0x51); /* push %r9 */ - /* need to adjust jmp offset, since - * pop %r9, pop %r10 take 4 bytes after call insn - */ - jmp_offset += 4; - } - } if (!imm32 || !is_simm32(jmp_offset)) { - pr_err("unsupported bpf func %d addr %p image %p\n", + pr_err("unsupported BPF func %d addr %p image %p\n", imm32, func, image); return -EINVAL; } EMIT1_off32(0xE8, jmp_offset); - if (seen_ld_abs) { - if (reload_skb_data) { - EMIT1(0x5F); /* pop %rdi */ - emit_load_skb_data_hlen(&prog); - } else { - EMIT2(0x41, 0x59); /* pop %r9 */ - EMIT2(0x41, 0x5A); /* pop %r10 */ - } - } break; case BPF_JMP | BPF_TAIL_CALL: @@ -970,7 +916,7 @@ xadd: if (is_imm8(insn->off)) else EMIT2_off32(0x81, add_1reg(0xF8, dst_reg), imm32); -emit_cond_jmp: /* convert BPF opcode to x86 */ +emit_cond_jmp: /* Convert BPF opcode to x86 */ switch (BPF_OP(insn->code)) { case BPF_JEQ: jmp_cond = X86_JE; @@ -996,22 +942,22 @@ emit_cond_jmp: /* convert BPF opcode to x86 */ jmp_cond = X86_JBE; break; case BPF_JSGT: - /* signed '>', GT in x86 */ + /* Signed '>', GT in x86 */ jmp_cond = X86_JG; break; case BPF_JSLT: - /* signed '<', LT in x86 */ + /* Signed '<', LT in x86 */ jmp_cond = X86_JL; break; case BPF_JSGE: - /* signed '>=', GE in x86 */ + /* Signed '>=', GE in x86 */ jmp_cond = X86_JGE; break; case BPF_JSLE: - /* signed '<=', LE in x86 */ + /* Signed '<=', LE in x86 */ jmp_cond = X86_JLE; break; - default: /* to silence gcc warning */ + default: /* to silence GCC warning */ return -EFAULT; } jmp_offset = addrs[i + insn->off] - addrs[i]; @@ -1039,7 +985,7 @@ emit_cond_jmp: /* convert BPF opcode to x86 */ jmp_offset = addrs[i + insn->off] - addrs[i]; if (!jmp_offset) - /* optimize out nop jumps */ + /* Optimize out nop jumps */ break; emit_jmp: if (is_imm8(jmp_offset)) { @@ -1052,66 +998,13 @@ emit_jmp: } break; - case BPF_LD | BPF_IND | BPF_W: - func = sk_load_word; - goto common_load; - case BPF_LD | BPF_ABS | BPF_W: - func = CHOOSE_LOAD_FUNC(imm32, sk_load_word); -common_load: - ctx->seen_ld_abs = seen_ld_abs = true; - jmp_offset = func - (image + addrs[i]); - if (!func || !is_simm32(jmp_offset)) { - pr_err("unsupported bpf func %d addr %p image %p\n", - imm32, func, image); - return -EINVAL; - } - if (BPF_MODE(insn->code) == BPF_ABS) { - /* mov %esi, imm32 */ - EMIT1_off32(0xBE, imm32); - } else { - /* mov %rsi, src_reg */ - EMIT_mov(BPF_REG_2, src_reg); - if (imm32) { - if (is_imm8(imm32)) - /* add %esi, imm8 */ - EMIT3(0x83, 0xC6, imm32); - else - /* add %esi, imm32 */ - EMIT2_off32(0x81, 0xC6, imm32); - } - } - /* skb pointer is in R6 (%rbx), it will be copied into - * %rdi if skb_copy_bits() call is necessary. - * sk_load_* helpers also use %r10 and %r9d. - * See bpf_jit.S - */ - if (seen_ax_reg) - /* r10 = skb->data, mov %r10, off32(%rbx) */ - EMIT3_off32(0x4c, 0x8b, 0x93, - offsetof(struct sk_buff, data)); - EMIT1_off32(0xE8, jmp_offset); /* call */ - break; - - case BPF_LD | BPF_IND | BPF_H: - func = sk_load_half; - goto common_load; - case BPF_LD | BPF_ABS | BPF_H: - func = CHOOSE_LOAD_FUNC(imm32, sk_load_half); - goto common_load; - case BPF_LD | BPF_IND | BPF_B: - func = sk_load_byte; - goto common_load; - case BPF_LD | BPF_ABS | BPF_B: - func = CHOOSE_LOAD_FUNC(imm32, sk_load_byte); - goto common_load; - case BPF_JMP | BPF_EXIT: if (seen_exit) { jmp_offset = ctx->cleanup_addr - addrs[i]; goto emit_jmp; } seen_exit = true; - /* update cleanup_addr */ + /* Update cleanup_addr */ ctx->cleanup_addr = proglen; /* mov rbx, qword ptr [rbp+0] */ EMIT4(0x48, 0x8B, 0x5D, 0); @@ -1129,10 +1022,11 @@ common_load: break; default: - /* By design x64 JIT should support all BPF instructions + /* + * By design x86-64 JIT should support all BPF instructions. * This error will be seen if new instruction was added - * to interpreter, but not to JIT - * or if there is junk in bpf_prog + * to the interpreter, but not to the JIT, or if there is + * junk in bpf_prog. */ pr_err("bpf_jit: unknown opcode %02x\n", insn->code); return -EINVAL; @@ -1184,7 +1078,8 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) return orig_prog; tmp = bpf_jit_blind_constants(prog); - /* If blinding was requested and we failed during blinding, + /* + * If blinding was requested and we failed during blinding, * we must fall back to the interpreter. */ if (IS_ERR(tmp)) @@ -1218,8 +1113,9 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) goto out_addrs; } - /* Before first pass, make a rough estimation of addrs[] - * each bpf instruction is translated to less than 64 bytes + /* + * Before first pass, make a rough estimation of addrs[] + * each BPF instruction is translated to less than 64 bytes */ for (proglen = 0, i = 0; i < prog->len; i++) { proglen += 64; @@ -1228,10 +1124,11 @@ struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) ctx.cleanup_addr = proglen; skip_init_addrs: - /* JITed image shrinks with every pass and the loop iterates - * until the image stops shrinking. Very large bpf programs + /* + * JITed image shrinks with every pass and the loop iterates + * until the image stops shrinking. Very large BPF programs * may converge on the last pass. In such case do one more - * pass to emit the final image + * pass to emit the final image. */ for (pass = 0; pass < 20 || image; pass++) { proglen = do_jit(prog, addrs, image, oldproglen, &ctx); diff --git a/arch/x86/net/bpf_jit_comp32.c b/arch/x86/net/bpf_jit_comp32.c new file mode 100644 index 000000000000..0cc04e30adc1 --- /dev/null +++ b/arch/x86/net/bpf_jit_comp32.c @@ -0,0 +1,2419 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Just-In-Time compiler for eBPF filters on IA32 (32bit x86) + * + * Author: Wang YanQing (udknight@gmail.com) + * The code based on code and ideas from: + * Eric Dumazet (eric.dumazet@gmail.com) + * and from: + * Shubham Bansal <illusionist.neo@gmail.com> + */ + +#include <linux/netdevice.h> +#include <linux/filter.h> +#include <linux/if_vlan.h> +#include <asm/cacheflush.h> +#include <asm/set_memory.h> +#include <asm/nospec-branch.h> +#include <linux/bpf.h> + +/* + * eBPF prog stack layout: + * + * high + * original ESP => +-----+ + * | | callee saved registers + * +-----+ + * | ... | eBPF JIT scratch space + * BPF_FP,IA32_EBP => +-----+ + * | ... | eBPF prog stack + * +-----+ + * |RSVD | JIT scratchpad + * current ESP => +-----+ + * | | + * | ... | Function call stack + * | | + * +-----+ + * low + * + * The callee saved registers: + * + * high + * original ESP => +------------------+ \ + * | ebp | | + * current EBP => +------------------+ } callee saved registers + * | ebx,esi,edi | | + * +------------------+ / + * low + */ + +static u8 *emit_code(u8 *ptr, u32 bytes, unsigned int len) +{ + if (len == 1) + *ptr = bytes; + else if (len == 2) + *(u16 *)ptr = bytes; + else { + *(u32 *)ptr = bytes; + barrier(); + } + return ptr + len; +} + +#define EMIT(bytes, len) \ + do { prog = emit_code(prog, bytes, len); cnt += len; } while (0) + +#define EMIT1(b1) EMIT(b1, 1) +#define EMIT2(b1, b2) EMIT((b1) + ((b2) << 8), 2) +#define EMIT3(b1, b2, b3) EMIT((b1) + ((b2) << 8) + ((b3) << 16), 3) +#define EMIT4(b1, b2, b3, b4) \ + EMIT((b1) + ((b2) << 8) + ((b3) << 16) + ((b4) << 24), 4) + +#define EMIT1_off32(b1, off) \ + do { EMIT1(b1); EMIT(off, 4); } while (0) +#define EMIT2_off32(b1, b2, off) \ + do { EMIT2(b1, b2); EMIT(off, 4); } while (0) +#define EMIT3_off32(b1, b2, b3, off) \ + do { EMIT3(b1, b2, b3); EMIT(off, 4); } while (0) +#define EMIT4_off32(b1, b2, b3, b4, off) \ + do { EMIT4(b1, b2, b3, b4); EMIT(off, 4); } while (0) + +#define jmp_label(label, jmp_insn_len) (label - cnt - jmp_insn_len) + +static bool is_imm8(int value) +{ + return value <= 127 && value >= -128; +} + +static bool is_simm32(s64 value) +{ + return value == (s64) (s32) value; +} + +#define STACK_OFFSET(k) (k) +#define TCALL_CNT (MAX_BPF_JIT_REG + 0) /* Tail Call Count */ + +#define IA32_EAX (0x0) +#define IA32_EBX (0x3) +#define IA32_ECX (0x1) +#define IA32_EDX (0x2) +#define IA32_ESI (0x6) +#define IA32_EDI (0x7) +#define IA32_EBP (0x5) +#define IA32_ESP (0x4) + +/* + * List of x86 cond jumps opcodes (. + s8) + * Add 0x10 (and an extra 0x0f) to generate far jumps (. + s32) + */ +#define IA32_JB 0x72 +#define IA32_JAE 0x73 +#define IA32_JE 0x74 +#define IA32_JNE 0x75 +#define IA32_JBE 0x76 +#define IA32_JA 0x77 +#define IA32_JL 0x7C +#define IA32_JGE 0x7D +#define IA32_JLE 0x7E +#define IA32_JG 0x7F + +/* + * Map eBPF registers to IA32 32bit registers or stack scratch space. + * + * 1. All the registers, R0-R10, are mapped to scratch space on stack. + * 2. We need two 64 bit temp registers to do complex operations on eBPF + * registers. + * 3. For performance reason, the BPF_REG_AX for blinding constant, is + * mapped to real hardware register pair, IA32_ESI and IA32_EDI. + * + * As the eBPF registers are all 64 bit registers and IA32 has only 32 bit + * registers, we have to map each eBPF registers with two IA32 32 bit regs + * or scratch memory space and we have to build eBPF 64 bit register from those. + * + * We use IA32_EAX, IA32_EDX, IA32_ECX, IA32_EBX as temporary registers. + */ +static const u8 bpf2ia32[][2] = { + /* Return value from in-kernel function, and exit value from eBPF */ + [BPF_REG_0] = {STACK_OFFSET(0), STACK_OFFSET(4)}, + + /* The arguments from eBPF program to in-kernel function */ + /* Stored on stack scratch space */ + [BPF_REG_1] = {STACK_OFFSET(8), STACK_OFFSET(12)}, + [BPF_REG_2] = {STACK_OFFSET(16), STACK_OFFSET(20)}, + [BPF_REG_3] = {STACK_OFFSET(24), STACK_OFFSET(28)}, + [BPF_REG_4] = {STACK_OFFSET(32), STACK_OFFSET(36)}, + [BPF_REG_5] = {STACK_OFFSET(40), STACK_OFFSET(44)}, + + /* Callee saved registers that in-kernel function will preserve */ + /* Stored on stack scratch space */ + [BPF_REG_6] = {STACK_OFFSET(48), STACK_OFFSET(52)}, + [BPF_REG_7] = {STACK_OFFSET(56), STACK_OFFSET(60)}, + [BPF_REG_8] = {STACK_OFFSET(64), STACK_OFFSET(68)}, + [BPF_REG_9] = {STACK_OFFSET(72), STACK_OFFSET(76)}, + + /* Read only Frame Pointer to access Stack */ + [BPF_REG_FP] = {STACK_OFFSET(80), STACK_OFFSET(84)}, + + /* Temporary register for blinding constants. */ + [BPF_REG_AX] = {IA32_ESI, IA32_EDI}, + + /* Tail call count. Stored on stack scratch space. */ + [TCALL_CNT] = {STACK_OFFSET(88), STACK_OFFSET(92)}, +}; + +#define dst_lo dst[0] +#define dst_hi dst[1] +#define src_lo src[0] +#define src_hi src[1] + +#define STACK_ALIGNMENT 8 +/* + * Stack space for BPF_REG_1, BPF_REG_2, BPF_REG_3, BPF_REG_4, + * BPF_REG_5, BPF_REG_6, BPF_REG_7, BPF_REG_8, BPF_REG_9, + * BPF_REG_FP, BPF_REG_AX and Tail call counts. + */ +#define SCRATCH_SIZE 96 + +/* Total stack size used in JITed code */ +#define _STACK_SIZE (stack_depth + SCRATCH_SIZE) + +#define STACK_SIZE ALIGN(_STACK_SIZE, STACK_ALIGNMENT) + +/* Get the offset of eBPF REGISTERs stored on scratch space. */ +#define STACK_VAR(off) (off) + +/* Encode 'dst_reg' register into IA32 opcode 'byte' */ +static u8 add_1reg(u8 byte, u32 dst_reg) +{ + return byte + dst_reg; +} + +/* Encode 'dst_reg' and 'src_reg' registers into IA32 opcode 'byte' */ +static u8 add_2reg(u8 byte, u32 dst_reg, u32 src_reg) +{ + return byte + dst_reg + (src_reg << 3); +} + +static void jit_fill_hole(void *area, unsigned int size) +{ + /* Fill whole space with int3 instructions */ + memset(area, 0xcc, size); +} + +static inline void emit_ia32_mov_i(const u8 dst, const u32 val, bool dstk, + u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (dstk) { + if (val == 0) { + /* xor eax,eax */ + EMIT2(0x33, add_2reg(0xC0, IA32_EAX, IA32_EAX)); + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst)); + } else { + EMIT3_off32(0xC7, add_1reg(0x40, IA32_EBP), + STACK_VAR(dst), val); + } + } else { + if (val == 0) + EMIT2(0x33, add_2reg(0xC0, dst, dst)); + else + EMIT2_off32(0xC7, add_1reg(0xC0, dst), + val); + } + *pprog = prog; +} + +/* dst = imm (4 bytes)*/ +static inline void emit_ia32_mov_r(const u8 dst, const u8 src, bool dstk, + bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 sreg = sstk ? IA32_EAX : src; + + if (sstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(src)); + if (dstk) + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, sreg), STACK_VAR(dst)); + else + /* mov dst,sreg */ + EMIT2(0x89, add_2reg(0xC0, dst, sreg)); + + *pprog = prog; +} + +/* dst = src */ +static inline void emit_ia32_mov_r64(const bool is64, const u8 dst[], + const u8 src[], bool dstk, + bool sstk, u8 **pprog) +{ + emit_ia32_mov_r(dst_lo, src_lo, dstk, sstk, pprog); + if (is64) + /* complete 8 byte move */ + emit_ia32_mov_r(dst_hi, src_hi, dstk, sstk, pprog); + else + /* zero out high 4 bytes */ + emit_ia32_mov_i(dst_hi, 0, dstk, pprog); +} + +/* Sign extended move */ +static inline void emit_ia32_mov_i64(const bool is64, const u8 dst[], + const u32 val, bool dstk, u8 **pprog) +{ + u32 hi = 0; + + if (is64 && (val & (1<<31))) + hi = (u32)~0; + emit_ia32_mov_i(dst_lo, val, dstk, pprog); + emit_ia32_mov_i(dst_hi, hi, dstk, pprog); +} + +/* + * ALU operation (32 bit) + * dst = dst * src + */ +static inline void emit_ia32_mul_r(const u8 dst, const u8 src, bool dstk, + bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 sreg = sstk ? IA32_ECX : src; + + if (sstk) + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src)); + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst)); + else + /* mov eax,dst */ + EMIT2(0x8B, add_2reg(0xC0, dst, IA32_EAX)); + + + EMIT2(0xF7, add_1reg(0xE0, sreg)); + + if (dstk) + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst)); + else + /* mov dst,eax */ + EMIT2(0x89, add_2reg(0xC0, dst, IA32_EAX)); + + *pprog = prog; +} + +static inline void emit_ia32_to_le_r64(const u8 dst[], s32 val, + bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk && val != 64) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + switch (val) { + case 16: + /* + * Emit 'movzwl eax,ax' to zero extend 16-bit + * into 64 bit + */ + EMIT2(0x0F, 0xB7); + EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo)); + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + break; + case 32: + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + break; + case 64: + /* nop */ + break; + } + + if (dstk && val != 64) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + *pprog = prog; +} + +static inline void emit_ia32_to_be_r64(const u8 dst[], s32 val, + bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + switch (val) { + case 16: + /* Emit 'ror %ax, 8' to swap lower 2 bytes */ + EMIT1(0x66); + EMIT3(0xC1, add_1reg(0xC8, dreg_lo), 8); + + EMIT2(0x0F, 0xB7); + EMIT1(add_2reg(0xC0, dreg_lo, dreg_lo)); + + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + break; + case 32: + /* Emit 'bswap eax' to swap lower 4 bytes */ + EMIT1(0x0F); + EMIT1(add_1reg(0xC8, dreg_lo)); + + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + break; + case 64: + /* Emit 'bswap eax' to swap lower 4 bytes */ + EMIT1(0x0F); + EMIT1(add_1reg(0xC8, dreg_lo)); + + /* Emit 'bswap edx' to swap lower 4 bytes */ + EMIT1(0x0F); + EMIT1(add_1reg(0xC8, dreg_hi)); + + /* mov ecx,dreg_hi */ + EMIT2(0x89, add_2reg(0xC0, IA32_ECX, dreg_hi)); + /* mov dreg_hi,dreg_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo)); + /* mov dreg_lo,ecx */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX)); + + break; + } + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + *pprog = prog; +} + +/* + * ALU operation (32 bit) + * dst = dst (div|mod) src + */ +static inline void emit_ia32_div_mod_r(const u8 op, const u8 dst, const u8 src, + bool dstk, bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (sstk) + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(src)); + else if (src != IA32_ECX) + /* mov ecx,src */ + EMIT2(0x8B, add_2reg(0xC0, src, IA32_ECX)); + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst)); + else + /* mov eax,dst */ + EMIT2(0x8B, add_2reg(0xC0, dst, IA32_EAX)); + + /* xor edx,edx */ + EMIT2(0x31, add_2reg(0xC0, IA32_EDX, IA32_EDX)); + /* div ecx */ + EMIT2(0xF7, add_1reg(0xF0, IA32_ECX)); + + if (op == BPF_MOD) { + if (dstk) + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst)); + else + EMIT2(0x89, add_2reg(0xC0, dst, IA32_EDX)); + } else { + if (dstk) + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst)); + else + EMIT2(0x89, add_2reg(0xC0, dst, IA32_EAX)); + } + *pprog = prog; +} + +/* + * ALU operation (32 bit) + * dst = dst (shift) src + */ +static inline void emit_ia32_shift_r(const u8 op, const u8 dst, const u8 src, + bool dstk, bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg = dstk ? IA32_EAX : dst; + u8 b2; + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst)); + + if (sstk) + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src)); + else if (src != IA32_ECX) + /* mov ecx,src */ + EMIT2(0x8B, add_2reg(0xC0, src, IA32_ECX)); + + switch (op) { + case BPF_LSH: + b2 = 0xE0; break; + case BPF_RSH: + b2 = 0xE8; break; + case BPF_ARSH: + b2 = 0xF8; break; + default: + return; + } + EMIT2(0xD3, add_1reg(b2, dreg)); + + if (dstk) + /* mov dword ptr [ebp+off],dreg */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg), STACK_VAR(dst)); + *pprog = prog; +} + +/* + * ALU operation (32 bit) + * dst = dst (op) src + */ +static inline void emit_ia32_alu_r(const bool is64, const bool hi, const u8 op, + const u8 dst, const u8 src, bool dstk, + bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 sreg = sstk ? IA32_EAX : src; + u8 dreg = dstk ? IA32_EDX : dst; + + if (sstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(src)); + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(dst)); + + switch (BPF_OP(op)) { + /* dst = dst + src */ + case BPF_ADD: + if (hi && is64) + EMIT2(0x11, add_2reg(0xC0, dreg, sreg)); + else + EMIT2(0x01, add_2reg(0xC0, dreg, sreg)); + break; + /* dst = dst - src */ + case BPF_SUB: + if (hi && is64) + EMIT2(0x19, add_2reg(0xC0, dreg, sreg)); + else + EMIT2(0x29, add_2reg(0xC0, dreg, sreg)); + break; + /* dst = dst | src */ + case BPF_OR: + EMIT2(0x09, add_2reg(0xC0, dreg, sreg)); + break; + /* dst = dst & src */ + case BPF_AND: + EMIT2(0x21, add_2reg(0xC0, dreg, sreg)); + break; + /* dst = dst ^ src */ + case BPF_XOR: + EMIT2(0x31, add_2reg(0xC0, dreg, sreg)); + break; + } + + if (dstk) + /* mov dword ptr [ebp+off],dreg */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg), + STACK_VAR(dst)); + *pprog = prog; +} + +/* ALU operation (64 bit) */ +static inline void emit_ia32_alu_r64(const bool is64, const u8 op, + const u8 dst[], const u8 src[], + bool dstk, bool sstk, + u8 **pprog) +{ + u8 *prog = *pprog; + + emit_ia32_alu_r(is64, false, op, dst_lo, src_lo, dstk, sstk, &prog); + if (is64) + emit_ia32_alu_r(is64, true, op, dst_hi, src_hi, dstk, sstk, + &prog); + else + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + *pprog = prog; +} + +/* + * ALU operation (32 bit) + * dst = dst (op) val + */ +static inline void emit_ia32_alu_i(const bool is64, const bool hi, const u8 op, + const u8 dst, const s32 val, bool dstk, + u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg = dstk ? IA32_EAX : dst; + u8 sreg = IA32_EDX; + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(dst)); + + if (!is_imm8(val)) + /* mov edx,imm32*/ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EDX), val); + + switch (op) { + /* dst = dst + val */ + case BPF_ADD: + if (hi && is64) { + if (is_imm8(val)) + EMIT3(0x83, add_1reg(0xD0, dreg), val); + else + EMIT2(0x11, add_2reg(0xC0, dreg, sreg)); + } else { + if (is_imm8(val)) + EMIT3(0x83, add_1reg(0xC0, dreg), val); + else + EMIT2(0x01, add_2reg(0xC0, dreg, sreg)); + } + break; + /* dst = dst - val */ + case BPF_SUB: + if (hi && is64) { + if (is_imm8(val)) + EMIT3(0x83, add_1reg(0xD8, dreg), val); + else + EMIT2(0x19, add_2reg(0xC0, dreg, sreg)); + } else { + if (is_imm8(val)) + EMIT3(0x83, add_1reg(0xE8, dreg), val); + else + EMIT2(0x29, add_2reg(0xC0, dreg, sreg)); + } + break; + /* dst = dst | val */ + case BPF_OR: + if (is_imm8(val)) + EMIT3(0x83, add_1reg(0xC8, dreg), val); + else + EMIT2(0x09, add_2reg(0xC0, dreg, sreg)); + break; + /* dst = dst & val */ + case BPF_AND: + if (is_imm8(val)) + EMIT3(0x83, add_1reg(0xE0, dreg), val); + else + EMIT2(0x21, add_2reg(0xC0, dreg, sreg)); + break; + /* dst = dst ^ val */ + case BPF_XOR: + if (is_imm8(val)) + EMIT3(0x83, add_1reg(0xF0, dreg), val); + else + EMIT2(0x31, add_2reg(0xC0, dreg, sreg)); + break; + case BPF_NEG: + EMIT2(0xF7, add_1reg(0xD8, dreg)); + break; + } + + if (dstk) + /* mov dword ptr [ebp+off],dreg */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg), + STACK_VAR(dst)); + *pprog = prog; +} + +/* ALU operation (64 bit) */ +static inline void emit_ia32_alu_i64(const bool is64, const u8 op, + const u8 dst[], const u32 val, + bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + u32 hi = 0; + + if (is64 && (val & (1<<31))) + hi = (u32)~0; + + emit_ia32_alu_i(is64, false, op, dst_lo, val, dstk, &prog); + if (is64) + emit_ia32_alu_i(is64, true, op, dst_hi, hi, dstk, &prog); + else + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + + *pprog = prog; +} + +/* dst = ~dst (64 bit) */ +static inline void emit_ia32_neg64(const u8 dst[], bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + /* xor ecx,ecx */ + EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX)); + /* sub dreg_lo,ecx */ + EMIT2(0x2B, add_2reg(0xC0, dreg_lo, IA32_ECX)); + /* mov dreg_lo,ecx */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, IA32_ECX)); + + /* xor ecx,ecx */ + EMIT2(0x31, add_2reg(0xC0, IA32_ECX, IA32_ECX)); + /* sbb dreg_hi,ecx */ + EMIT2(0x19, add_2reg(0xC0, dreg_hi, IA32_ECX)); + /* mov dreg_hi,ecx */ + EMIT2(0x89, add_2reg(0xC0, dreg_hi, IA32_ECX)); + + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + *pprog = prog; +} + +/* dst = dst << src */ +static inline void emit_ia32_lsh_r64(const u8 dst[], const u8 src[], + bool dstk, bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + static int jmp_label1 = -1; + static int jmp_label2 = -1; + static int jmp_label3 = -1; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + if (sstk) + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(src_lo)); + else + /* mov ecx,src_lo */ + EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX)); + + /* cmp ecx,32 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); + /* Jumps when >= 32 */ + if (is_imm8(jmp_label(jmp_label1, 2))) + EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); + else + EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6)); + + /* < 32 */ + /* shl dreg_hi,cl */ + EMIT2(0xD3, add_1reg(0xE0, dreg_hi)); + /* mov ebx,dreg_lo */ + EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX)); + /* shl dreg_lo,cl */ + EMIT2(0xD3, add_1reg(0xE0, dreg_lo)); + + /* IA32_ECX = -IA32_ECX + 32 */ + /* neg ecx */ + EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); + /* add ecx,32 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); + + /* shr ebx,cl */ + EMIT2(0xD3, add_1reg(0xE8, IA32_EBX)); + /* or dreg_hi,ebx */ + EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX)); + + /* goto out; */ + if (is_imm8(jmp_label(jmp_label3, 2))) + EMIT2(0xEB, jmp_label(jmp_label3, 2)); + else + EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); + + /* >= 32 */ + if (jmp_label1 == -1) + jmp_label1 = cnt; + + /* cmp ecx,64 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64); + /* Jumps when >= 64 */ + if (is_imm8(jmp_label(jmp_label2, 2))) + EMIT2(IA32_JAE, jmp_label(jmp_label2, 2)); + else + EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6)); + + /* >= 32 && < 64 */ + /* sub ecx,32 */ + EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32); + /* shl dreg_lo,cl */ + EMIT2(0xD3, add_1reg(0xE0, dreg_lo)); + /* mov dreg_hi,dreg_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo)); + + /* xor dreg_lo,dreg_lo */ + EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); + + /* goto out; */ + if (is_imm8(jmp_label(jmp_label3, 2))) + EMIT2(0xEB, jmp_label(jmp_label3, 2)); + else + EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); + + /* >= 64 */ + if (jmp_label2 == -1) + jmp_label2 = cnt; + /* xor dreg_lo,dreg_lo */ + EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + + if (jmp_label3 == -1) + jmp_label3 = cnt; + + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + /* out: */ + *pprog = prog; +} + +/* dst = dst >> src (signed)*/ +static inline void emit_ia32_arsh_r64(const u8 dst[], const u8 src[], + bool dstk, bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + static int jmp_label1 = -1; + static int jmp_label2 = -1; + static int jmp_label3 = -1; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + if (sstk) + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(src_lo)); + else + /* mov ecx,src_lo */ + EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX)); + + /* cmp ecx,32 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); + /* Jumps when >= 32 */ + if (is_imm8(jmp_label(jmp_label1, 2))) + EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); + else + EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6)); + + /* < 32 */ + /* lshr dreg_lo,cl */ + EMIT2(0xD3, add_1reg(0xE8, dreg_lo)); + /* mov ebx,dreg_hi */ + EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); + /* ashr dreg_hi,cl */ + EMIT2(0xD3, add_1reg(0xF8, dreg_hi)); + + /* IA32_ECX = -IA32_ECX + 32 */ + /* neg ecx */ + EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); + /* add ecx,32 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); + + /* shl ebx,cl */ + EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); + /* or dreg_lo,ebx */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); + + /* goto out; */ + if (is_imm8(jmp_label(jmp_label3, 2))) + EMIT2(0xEB, jmp_label(jmp_label3, 2)); + else + EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); + + /* >= 32 */ + if (jmp_label1 == -1) + jmp_label1 = cnt; + + /* cmp ecx,64 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64); + /* Jumps when >= 64 */ + if (is_imm8(jmp_label(jmp_label2, 2))) + EMIT2(IA32_JAE, jmp_label(jmp_label2, 2)); + else + EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6)); + + /* >= 32 && < 64 */ + /* sub ecx,32 */ + EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32); + /* ashr dreg_hi,cl */ + EMIT2(0xD3, add_1reg(0xF8, dreg_hi)); + /* mov dreg_lo,dreg_hi */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); + + /* ashr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31); + + /* goto out; */ + if (is_imm8(jmp_label(jmp_label3, 2))) + EMIT2(0xEB, jmp_label(jmp_label3, 2)); + else + EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); + + /* >= 64 */ + if (jmp_label2 == -1) + jmp_label2 = cnt; + /* ashr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31); + /* mov dreg_lo,dreg_hi */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); + + if (jmp_label3 == -1) + jmp_label3 = cnt; + + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + /* out: */ + *pprog = prog; +} + +/* dst = dst >> src */ +static inline void emit_ia32_rsh_r64(const u8 dst[], const u8 src[], bool dstk, + bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + static int jmp_label1 = -1; + static int jmp_label2 = -1; + static int jmp_label3 = -1; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + if (sstk) + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(src_lo)); + else + /* mov ecx,src_lo */ + EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_ECX)); + + /* cmp ecx,32 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 32); + /* Jumps when >= 32 */ + if (is_imm8(jmp_label(jmp_label1, 2))) + EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); + else + EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label1, 6)); + + /* < 32 */ + /* lshr dreg_lo,cl */ + EMIT2(0xD3, add_1reg(0xE8, dreg_lo)); + /* mov ebx,dreg_hi */ + EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); + /* shr dreg_hi,cl */ + EMIT2(0xD3, add_1reg(0xE8, dreg_hi)); + + /* IA32_ECX = -IA32_ECX + 32 */ + /* neg ecx */ + EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); + /* add ecx,32 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); + + /* shl ebx,cl */ + EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); + /* or dreg_lo,ebx */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); + + /* goto out; */ + if (is_imm8(jmp_label(jmp_label3, 2))) + EMIT2(0xEB, jmp_label(jmp_label3, 2)); + else + EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); + + /* >= 32 */ + if (jmp_label1 == -1) + jmp_label1 = cnt; + /* cmp ecx,64 */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), 64); + /* Jumps when >= 64 */ + if (is_imm8(jmp_label(jmp_label2, 2))) + EMIT2(IA32_JAE, jmp_label(jmp_label2, 2)); + else + EMIT2_off32(0x0F, IA32_JAE + 0x10, jmp_label(jmp_label2, 6)); + + /* >= 32 && < 64 */ + /* sub ecx,32 */ + EMIT3(0x83, add_1reg(0xE8, IA32_ECX), 32); + /* shr dreg_hi,cl */ + EMIT2(0xD3, add_1reg(0xE8, dreg_hi)); + /* mov dreg_lo,dreg_hi */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + + /* goto out; */ + if (is_imm8(jmp_label(jmp_label3, 2))) + EMIT2(0xEB, jmp_label(jmp_label3, 2)); + else + EMIT1_off32(0xE9, jmp_label(jmp_label3, 5)); + + /* >= 64 */ + if (jmp_label2 == -1) + jmp_label2 = cnt; + /* xor dreg_lo,dreg_lo */ + EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + + if (jmp_label3 == -1) + jmp_label3 = cnt; + + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + /* out: */ + *pprog = prog; +} + +/* dst = dst << val */ +static inline void emit_ia32_lsh_i64(const u8 dst[], const u32 val, + bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + /* Do LSH operation */ + if (val < 32) { + /* shl dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xE0, dreg_hi), val); + /* mov ebx,dreg_lo */ + EMIT2(0x8B, add_2reg(0xC0, dreg_lo, IA32_EBX)); + /* shl dreg_lo,imm8 */ + EMIT3(0xC1, add_1reg(0xE0, dreg_lo), val); + + /* IA32_ECX = 32 - val */ + /* mov ecx,val */ + EMIT2(0xB1, val); + /* movzx ecx,ecx */ + EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX)); + /* neg ecx */ + EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); + /* add ecx,32 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); + + /* shr ebx,cl */ + EMIT2(0xD3, add_1reg(0xE8, IA32_EBX)); + /* or dreg_hi,ebx */ + EMIT2(0x09, add_2reg(0xC0, dreg_hi, IA32_EBX)); + } else if (val >= 32 && val < 64) { + u32 value = val - 32; + + /* shl dreg_lo,imm8 */ + EMIT3(0xC1, add_1reg(0xE0, dreg_lo), value); + /* mov dreg_hi,dreg_lo */ + EMIT2(0x89, add_2reg(0xC0, dreg_hi, dreg_lo)); + /* xor dreg_lo,dreg_lo */ + EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); + } else { + /* xor dreg_lo,dreg_lo */ + EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + } + + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + *pprog = prog; +} + +/* dst = dst >> val */ +static inline void emit_ia32_rsh_i64(const u8 dst[], const u32 val, + bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + /* Do RSH operation */ + if (val < 32) { + /* shr dreg_lo,imm8 */ + EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val); + /* mov ebx,dreg_hi */ + EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); + /* shr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xE8, dreg_hi), val); + + /* IA32_ECX = 32 - val */ + /* mov ecx,val */ + EMIT2(0xB1, val); + /* movzx ecx,ecx */ + EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX)); + /* neg ecx */ + EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); + /* add ecx,32 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); + + /* shl ebx,cl */ + EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); + /* or dreg_lo,ebx */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); + } else if (val >= 32 && val < 64) { + u32 value = val - 32; + + /* shr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xE8, dreg_hi), value); + /* mov dreg_lo,dreg_hi */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + } else { + /* xor dreg_lo,dreg_lo */ + EMIT2(0x33, add_2reg(0xC0, dreg_lo, dreg_lo)); + /* xor dreg_hi,dreg_hi */ + EMIT2(0x33, add_2reg(0xC0, dreg_hi, dreg_hi)); + } + + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + *pprog = prog; +} + +/* dst = dst >> val (signed) */ +static inline void emit_ia32_arsh_i64(const u8 dst[], const u32 val, + bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + /* Do RSH operation */ + if (val < 32) { + /* shr dreg_lo,imm8 */ + EMIT3(0xC1, add_1reg(0xE8, dreg_lo), val); + /* mov ebx,dreg_hi */ + EMIT2(0x8B, add_2reg(0xC0, dreg_hi, IA32_EBX)); + /* ashr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xF8, dreg_hi), val); + + /* IA32_ECX = 32 - val */ + /* mov ecx,val */ + EMIT2(0xB1, val); + /* movzx ecx,ecx */ + EMIT3(0x0F, 0xB6, add_2reg(0xC0, IA32_ECX, IA32_ECX)); + /* neg ecx */ + EMIT2(0xF7, add_1reg(0xD8, IA32_ECX)); + /* add ecx,32 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 32); + + /* shl ebx,cl */ + EMIT2(0xD3, add_1reg(0xE0, IA32_EBX)); + /* or dreg_lo,ebx */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, IA32_EBX)); + } else if (val >= 32 && val < 64) { + u32 value = val - 32; + + /* ashr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xF8, dreg_hi), value); + /* mov dreg_lo,dreg_hi */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); + + /* ashr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31); + } else { + /* ashr dreg_hi,imm8 */ + EMIT3(0xC1, add_1reg(0xF8, dreg_hi), 31); + /* mov dreg_lo,dreg_hi */ + EMIT2(0x89, add_2reg(0xC0, dreg_lo, dreg_hi)); + } + + if (dstk) { + /* mov dword ptr [ebp+off],dreg_lo */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_lo), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],dreg_hi */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, dreg_hi), + STACK_VAR(dst_hi)); + } + *pprog = prog; +} + +static inline void emit_ia32_mul_r64(const u8 dst[], const u8 src[], bool dstk, + bool sstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_hi)); + else + /* mov eax,dst_hi */ + EMIT2(0x8B, add_2reg(0xC0, dst_hi, IA32_EAX)); + + if (sstk) + /* mul dword ptr [ebp+off] */ + EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_lo)); + else + /* mul src_lo */ + EMIT2(0xF7, add_1reg(0xE0, src_lo)); + + /* mov ecx,eax */ + EMIT2(0x89, add_2reg(0xC0, IA32_ECX, IA32_EAX)); + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + else + /* mov eax,dst_lo */ + EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX)); + + if (sstk) + /* mul dword ptr [ebp+off] */ + EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_hi)); + else + /* mul src_hi */ + EMIT2(0xF7, add_1reg(0xE0, src_hi)); + + /* add eax,eax */ + EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EAX)); + + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + else + /* mov eax,dst_lo */ + EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX)); + + if (sstk) + /* mul dword ptr [ebp+off] */ + EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(src_lo)); + else + /* mul src_lo */ + EMIT2(0xF7, add_1reg(0xE0, src_lo)); + + /* add ecx,edx */ + EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EDX)); + + if (dstk) { + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],ecx */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(dst_hi)); + } else { + /* mov dst_lo,eax */ + EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EAX)); + /* mov dst_hi,ecx */ + EMIT2(0x89, add_2reg(0xC0, dst_hi, IA32_ECX)); + } + + *pprog = prog; +} + +static inline void emit_ia32_mul_i64(const u8 dst[], const u32 val, + bool dstk, u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + u32 hi; + + hi = val & (1<<31) ? (u32)~0 : 0; + /* movl eax,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), val); + if (dstk) + /* mul dword ptr [ebp+off] */ + EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_hi)); + else + /* mul dst_hi */ + EMIT2(0xF7, add_1reg(0xE0, dst_hi)); + + /* mov ecx,eax */ + EMIT2(0x89, add_2reg(0xC0, IA32_ECX, IA32_EAX)); + + /* movl eax,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), hi); + if (dstk) + /* mul dword ptr [ebp+off] */ + EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_lo)); + else + /* mul dst_lo */ + EMIT2(0xF7, add_1reg(0xE0, dst_lo)); + /* add ecx,eax */ + EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EAX)); + + /* movl eax,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EAX), val); + if (dstk) + /* mul dword ptr [ebp+off] */ + EMIT3(0xF7, add_1reg(0x60, IA32_EBP), STACK_VAR(dst_lo)); + else + /* mul dst_lo */ + EMIT2(0xF7, add_1reg(0xE0, dst_lo)); + + /* add ecx,edx */ + EMIT2(0x01, add_2reg(0xC0, IA32_ECX, IA32_EDX)); + + if (dstk) { + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + /* mov dword ptr [ebp+off],ecx */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(dst_hi)); + } else { + /* mov dword ptr [ebp+off],eax */ + EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EAX)); + /* mov dword ptr [ebp+off],ecx */ + EMIT2(0x89, add_2reg(0xC0, dst_hi, IA32_ECX)); + } + + *pprog = prog; +} + +static int bpf_size_to_x86_bytes(int bpf_size) +{ + if (bpf_size == BPF_W) + return 4; + else if (bpf_size == BPF_H) + return 2; + else if (bpf_size == BPF_B) + return 1; + else if (bpf_size == BPF_DW) + return 4; /* imm32 */ + else + return 0; +} + +struct jit_context { + int cleanup_addr; /* Epilogue code offset */ +}; + +/* Maximum number of bytes emitted while JITing one eBPF insn */ +#define BPF_MAX_INSN_SIZE 128 +#define BPF_INSN_SAFETY 64 + +#define PROLOGUE_SIZE 35 + +/* + * Emit prologue code for BPF program and check it's size. + * bpf_tail_call helper will skip it while jumping into another program. + */ +static void emit_prologue(u8 **pprog, u32 stack_depth) +{ + u8 *prog = *pprog; + int cnt = 0; + const u8 *r1 = bpf2ia32[BPF_REG_1]; + const u8 fplo = bpf2ia32[BPF_REG_FP][0]; + const u8 fphi = bpf2ia32[BPF_REG_FP][1]; + const u8 *tcc = bpf2ia32[TCALL_CNT]; + + /* push ebp */ + EMIT1(0x55); + /* mov ebp,esp */ + EMIT2(0x89, 0xE5); + /* push edi */ + EMIT1(0x57); + /* push esi */ + EMIT1(0x56); + /* push ebx */ + EMIT1(0x53); + + /* sub esp,STACK_SIZE */ + EMIT2_off32(0x81, 0xEC, STACK_SIZE); + /* sub ebp,SCRATCH_SIZE+4+12*/ + EMIT3(0x83, add_1reg(0xE8, IA32_EBP), SCRATCH_SIZE + 16); + /* xor ebx,ebx */ + EMIT2(0x31, add_2reg(0xC0, IA32_EBX, IA32_EBX)); + + /* Set up BPF prog stack base register */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBP), STACK_VAR(fplo)); + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(fphi)); + + /* Move BPF_CTX (EAX) to BPF_REG_R1 */ + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r1[0])); + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(r1[1])); + + /* Initialize Tail Count */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[0])); + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1])); + + BUILD_BUG_ON(cnt != PROLOGUE_SIZE); + *pprog = prog; +} + +/* Emit epilogue code for BPF program */ +static void emit_epilogue(u8 **pprog, u32 stack_depth) +{ + u8 *prog = *pprog; + const u8 *r0 = bpf2ia32[BPF_REG_0]; + int cnt = 0; + + /* mov eax,dword ptr [ebp+off]*/ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r0[0])); + /* mov edx,dword ptr [ebp+off]*/ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r0[1])); + + /* add ebp,SCRATCH_SIZE+4+12*/ + EMIT3(0x83, add_1reg(0xC0, IA32_EBP), SCRATCH_SIZE + 16); + + /* mov ebx,dword ptr [ebp-12]*/ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), -12); + /* mov esi,dword ptr [ebp-8]*/ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ESI), -8); + /* mov edi,dword ptr [ebp-4]*/ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDI), -4); + + EMIT1(0xC9); /* leave */ + EMIT1(0xC3); /* ret */ + *pprog = prog; +} + +/* + * Generate the following code: + * ... bpf_tail_call(void *ctx, struct bpf_array *array, u64 index) ... + * if (index >= array->map.max_entries) + * goto out; + * if (++tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + * prog = array->ptrs[index]; + * if (prog == NULL) + * goto out; + * goto *(prog->bpf_func + prologue_size); + * out: + */ +static void emit_bpf_tail_call(u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + const u8 *r1 = bpf2ia32[BPF_REG_1]; + const u8 *r2 = bpf2ia32[BPF_REG_2]; + const u8 *r3 = bpf2ia32[BPF_REG_3]; + const u8 *tcc = bpf2ia32[TCALL_CNT]; + u32 lo, hi; + static int jmp_label1 = -1; + + /* + * if (index >= array->map.max_entries) + * goto out; + */ + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r2[0])); + /* mov edx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), STACK_VAR(r3[0])); + + /* cmp dword ptr [eax+off],edx */ + EMIT3(0x39, add_2reg(0x40, IA32_EAX, IA32_EDX), + offsetof(struct bpf_array, map.max_entries)); + /* jbe out */ + EMIT2(IA32_JBE, jmp_label(jmp_label1, 2)); + + /* + * if (tail_call_cnt > MAX_TAIL_CALL_CNT) + * goto out; + */ + lo = (u32)MAX_TAIL_CALL_CNT; + hi = (u32)((u64)MAX_TAIL_CALL_CNT >> 32); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(tcc[0])); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1])); + + /* cmp edx,hi */ + EMIT3(0x83, add_1reg(0xF8, IA32_EBX), hi); + EMIT2(IA32_JNE, 3); + /* cmp ecx,lo */ + EMIT3(0x83, add_1reg(0xF8, IA32_ECX), lo); + + /* ja out */ + EMIT2(IA32_JAE, jmp_label(jmp_label1, 2)); + + /* add eax,0x1 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ECX), 0x01); + /* adc ebx,0x0 */ + EMIT3(0x83, add_1reg(0xD0, IA32_EBX), 0x00); + + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(tcc[0])); + /* mov dword ptr [ebp+off],edx */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EBX), STACK_VAR(tcc[1])); + + /* prog = array->ptrs[index]; */ + /* mov edx, [eax + edx * 4 + offsetof(...)] */ + EMIT3_off32(0x8B, 0x94, 0x90, offsetof(struct bpf_array, ptrs)); + + /* + * if (prog == NULL) + * goto out; + */ + /* test edx,edx */ + EMIT2(0x85, add_2reg(0xC0, IA32_EDX, IA32_EDX)); + /* je out */ + EMIT2(IA32_JE, jmp_label(jmp_label1, 2)); + + /* goto *(prog->bpf_func + prologue_size); */ + /* mov edx, dword ptr [edx + 32] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EDX, IA32_EDX), + offsetof(struct bpf_prog, bpf_func)); + /* add edx,prologue_size */ + EMIT3(0x83, add_1reg(0xC0, IA32_EDX), PROLOGUE_SIZE); + + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), STACK_VAR(r1[0])); + + /* + * Now we're ready to jump into next BPF program: + * eax == ctx (1st arg) + * edx == prog->bpf_func + prologue_size + */ + RETPOLINE_EDX_BPF_JIT(); + + if (jmp_label1 == -1) + jmp_label1 = cnt; + + /* out: */ + *pprog = prog; +} + +/* Push the scratch stack register on top of the stack. */ +static inline void emit_push_r64(const u8 src[], u8 **pprog) +{ + u8 *prog = *pprog; + int cnt = 0; + + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src_hi)); + /* push ecx */ + EMIT1(0x51); + + /* mov ecx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), STACK_VAR(src_lo)); + /* push ecx */ + EMIT1(0x51); + + *pprog = prog; +} + +static int do_jit(struct bpf_prog *bpf_prog, int *addrs, u8 *image, + int oldproglen, struct jit_context *ctx) +{ + struct bpf_insn *insn = bpf_prog->insnsi; + int insn_cnt = bpf_prog->len; + bool seen_exit = false; + u8 temp[BPF_MAX_INSN_SIZE + BPF_INSN_SAFETY]; + int i, cnt = 0; + int proglen = 0; + u8 *prog = temp; + + emit_prologue(&prog, bpf_prog->aux->stack_depth); + + for (i = 0; i < insn_cnt; i++, insn++) { + const s32 imm32 = insn->imm; + const bool is64 = BPF_CLASS(insn->code) == BPF_ALU64; + const bool dstk = insn->dst_reg == BPF_REG_AX ? false : true; + const bool sstk = insn->src_reg == BPF_REG_AX ? false : true; + const u8 code = insn->code; + const u8 *dst = bpf2ia32[insn->dst_reg]; + const u8 *src = bpf2ia32[insn->src_reg]; + const u8 *r0 = bpf2ia32[BPF_REG_0]; + s64 jmp_offset; + u8 jmp_cond; + int ilen; + u8 *func; + + switch (code) { + /* ALU operations */ + /* dst = src */ + case BPF_ALU | BPF_MOV | BPF_K: + case BPF_ALU | BPF_MOV | BPF_X: + case BPF_ALU64 | BPF_MOV | BPF_K: + case BPF_ALU64 | BPF_MOV | BPF_X: + switch (BPF_SRC(code)) { + case BPF_X: + emit_ia32_mov_r64(is64, dst, src, dstk, + sstk, &prog); + break; + case BPF_K: + /* Sign-extend immediate value to dst reg */ + emit_ia32_mov_i64(is64, dst, imm32, + dstk, &prog); + break; + } + break; + /* dst = dst + src/imm */ + /* dst = dst - src/imm */ + /* dst = dst | src/imm */ + /* dst = dst & src/imm */ + /* dst = dst ^ src/imm */ + /* dst = dst * src/imm */ + /* dst = dst << src */ + /* dst = dst >> src */ + case BPF_ALU | BPF_ADD | BPF_K: + case BPF_ALU | BPF_ADD | BPF_X: + case BPF_ALU | BPF_SUB | BPF_K: + case BPF_ALU | BPF_SUB | BPF_X: + case BPF_ALU | BPF_OR | BPF_K: + case BPF_ALU | BPF_OR | BPF_X: + case BPF_ALU | BPF_AND | BPF_K: + case BPF_ALU | BPF_AND | BPF_X: + case BPF_ALU | BPF_XOR | BPF_K: + case BPF_ALU | BPF_XOR | BPF_X: + case BPF_ALU64 | BPF_ADD | BPF_K: + case BPF_ALU64 | BPF_ADD | BPF_X: + case BPF_ALU64 | BPF_SUB | BPF_K: + case BPF_ALU64 | BPF_SUB | BPF_X: + case BPF_ALU64 | BPF_OR | BPF_K: + case BPF_ALU64 | BPF_OR | BPF_X: + case BPF_ALU64 | BPF_AND | BPF_K: + case BPF_ALU64 | BPF_AND | BPF_X: + case BPF_ALU64 | BPF_XOR | BPF_K: + case BPF_ALU64 | BPF_XOR | BPF_X: + switch (BPF_SRC(code)) { + case BPF_X: + emit_ia32_alu_r64(is64, BPF_OP(code), dst, + src, dstk, sstk, &prog); + break; + case BPF_K: + emit_ia32_alu_i64(is64, BPF_OP(code), dst, + imm32, dstk, &prog); + break; + } + break; + case BPF_ALU | BPF_MUL | BPF_K: + case BPF_ALU | BPF_MUL | BPF_X: + switch (BPF_SRC(code)) { + case BPF_X: + emit_ia32_mul_r(dst_lo, src_lo, dstk, + sstk, &prog); + break; + case BPF_K: + /* mov ecx,imm32*/ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), + imm32); + emit_ia32_mul_r(dst_lo, IA32_ECX, dstk, + false, &prog); + break; + } + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + break; + case BPF_ALU | BPF_LSH | BPF_X: + case BPF_ALU | BPF_RSH | BPF_X: + case BPF_ALU | BPF_ARSH | BPF_K: + case BPF_ALU | BPF_ARSH | BPF_X: + switch (BPF_SRC(code)) { + case BPF_X: + emit_ia32_shift_r(BPF_OP(code), dst_lo, src_lo, + dstk, sstk, &prog); + break; + case BPF_K: + /* mov ecx,imm32*/ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), + imm32); + emit_ia32_shift_r(BPF_OP(code), dst_lo, + IA32_ECX, dstk, false, + &prog); + break; + } + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + break; + /* dst = dst / src(imm) */ + /* dst = dst % src(imm) */ + case BPF_ALU | BPF_DIV | BPF_K: + case BPF_ALU | BPF_DIV | BPF_X: + case BPF_ALU | BPF_MOD | BPF_K: + case BPF_ALU | BPF_MOD | BPF_X: + switch (BPF_SRC(code)) { + case BPF_X: + emit_ia32_div_mod_r(BPF_OP(code), dst_lo, + src_lo, dstk, sstk, &prog); + break; + case BPF_K: + /* mov ecx,imm32*/ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), + imm32); + emit_ia32_div_mod_r(BPF_OP(code), dst_lo, + IA32_ECX, dstk, false, + &prog); + break; + } + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + break; + case BPF_ALU64 | BPF_DIV | BPF_K: + case BPF_ALU64 | BPF_DIV | BPF_X: + case BPF_ALU64 | BPF_MOD | BPF_K: + case BPF_ALU64 | BPF_MOD | BPF_X: + goto notyet; + /* dst = dst >> imm */ + /* dst = dst << imm */ + case BPF_ALU | BPF_RSH | BPF_K: + case BPF_ALU | BPF_LSH | BPF_K: + if (unlikely(imm32 > 31)) + return -EINVAL; + /* mov ecx,imm32*/ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32); + emit_ia32_shift_r(BPF_OP(code), dst_lo, IA32_ECX, dstk, + false, &prog); + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + break; + /* dst = dst << imm */ + case BPF_ALU64 | BPF_LSH | BPF_K: + if (unlikely(imm32 > 63)) + return -EINVAL; + emit_ia32_lsh_i64(dst, imm32, dstk, &prog); + break; + /* dst = dst >> imm */ + case BPF_ALU64 | BPF_RSH | BPF_K: + if (unlikely(imm32 > 63)) + return -EINVAL; + emit_ia32_rsh_i64(dst, imm32, dstk, &prog); + break; + /* dst = dst << src */ + case BPF_ALU64 | BPF_LSH | BPF_X: + emit_ia32_lsh_r64(dst, src, dstk, sstk, &prog); + break; + /* dst = dst >> src */ + case BPF_ALU64 | BPF_RSH | BPF_X: + emit_ia32_rsh_r64(dst, src, dstk, sstk, &prog); + break; + /* dst = dst >> src (signed) */ + case BPF_ALU64 | BPF_ARSH | BPF_X: + emit_ia32_arsh_r64(dst, src, dstk, sstk, &prog); + break; + /* dst = dst >> imm (signed) */ + case BPF_ALU64 | BPF_ARSH | BPF_K: + if (unlikely(imm32 > 63)) + return -EINVAL; + emit_ia32_arsh_i64(dst, imm32, dstk, &prog); + break; + /* dst = ~dst */ + case BPF_ALU | BPF_NEG: + emit_ia32_alu_i(is64, false, BPF_OP(code), + dst_lo, 0, dstk, &prog); + emit_ia32_mov_i(dst_hi, 0, dstk, &prog); + break; + /* dst = ~dst (64 bit) */ + case BPF_ALU64 | BPF_NEG: + emit_ia32_neg64(dst, dstk, &prog); + break; + /* dst = dst * src/imm */ + case BPF_ALU64 | BPF_MUL | BPF_X: + case BPF_ALU64 | BPF_MUL | BPF_K: + switch (BPF_SRC(code)) { + case BPF_X: + emit_ia32_mul_r64(dst, src, dstk, sstk, &prog); + break; + case BPF_K: + emit_ia32_mul_i64(dst, imm32, dstk, &prog); + break; + } + break; + /* dst = htole(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_LE: + emit_ia32_to_le_r64(dst, imm32, dstk, &prog); + break; + /* dst = htobe(dst) */ + case BPF_ALU | BPF_END | BPF_FROM_BE: + emit_ia32_to_be_r64(dst, imm32, dstk, &prog); + break; + /* dst = imm64 */ + case BPF_LD | BPF_IMM | BPF_DW: { + s32 hi, lo = imm32; + + hi = insn[1].imm; + emit_ia32_mov_i(dst_lo, lo, dstk, &prog); + emit_ia32_mov_i(dst_hi, hi, dstk, &prog); + insn++; + i++; + break; + } + /* ST: *(u8*)(dst_reg + off) = imm */ + case BPF_ST | BPF_MEM | BPF_H: + case BPF_ST | BPF_MEM | BPF_B: + case BPF_ST | BPF_MEM | BPF_W: + case BPF_ST | BPF_MEM | BPF_DW: + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + else + /* mov eax,dst_lo */ + EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX)); + + switch (BPF_SIZE(code)) { + case BPF_B: + EMIT(0xC6, 1); break; + case BPF_H: + EMIT2(0x66, 0xC7); break; + case BPF_W: + case BPF_DW: + EMIT(0xC7, 1); break; + } + + if (is_imm8(insn->off)) + EMIT2(add_1reg(0x40, IA32_EAX), insn->off); + else + EMIT1_off32(add_1reg(0x80, IA32_EAX), + insn->off); + EMIT(imm32, bpf_size_to_x86_bytes(BPF_SIZE(code))); + + if (BPF_SIZE(code) == BPF_DW) { + u32 hi; + + hi = imm32 & (1<<31) ? (u32)~0 : 0; + EMIT2_off32(0xC7, add_1reg(0x80, IA32_EAX), + insn->off + 4); + EMIT(hi, 4); + } + break; + + /* STX: *(u8*)(dst_reg + off) = src_reg */ + case BPF_STX | BPF_MEM | BPF_B: + case BPF_STX | BPF_MEM | BPF_H: + case BPF_STX | BPF_MEM | BPF_W: + case BPF_STX | BPF_MEM | BPF_DW: + if (dstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + else + /* mov eax,dst_lo */ + EMIT2(0x8B, add_2reg(0xC0, dst_lo, IA32_EAX)); + + if (sstk) + /* mov edx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(src_lo)); + else + /* mov edx,src_lo */ + EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_EDX)); + + switch (BPF_SIZE(code)) { + case BPF_B: + EMIT(0x88, 1); break; + case BPF_H: + EMIT2(0x66, 0x89); break; + case BPF_W: + case BPF_DW: + EMIT(0x89, 1); break; + } + + if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, IA32_EAX, IA32_EDX), + insn->off); + else + EMIT1_off32(add_2reg(0x80, IA32_EAX, IA32_EDX), + insn->off); + + if (BPF_SIZE(code) == BPF_DW) { + if (sstk) + /* mov edi,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, + IA32_EDX), + STACK_VAR(src_hi)); + else + /* mov edi,src_hi */ + EMIT2(0x8B, add_2reg(0xC0, src_hi, + IA32_EDX)); + EMIT1(0x89); + if (is_imm8(insn->off + 4)) { + EMIT2(add_2reg(0x40, IA32_EAX, + IA32_EDX), + insn->off + 4); + } else { + EMIT1(add_2reg(0x80, IA32_EAX, + IA32_EDX)); + EMIT(insn->off + 4, 4); + } + } + break; + + /* LDX: dst_reg = *(u8*)(src_reg + off) */ + case BPF_LDX | BPF_MEM | BPF_B: + case BPF_LDX | BPF_MEM | BPF_H: + case BPF_LDX | BPF_MEM | BPF_W: + case BPF_LDX | BPF_MEM | BPF_DW: + if (sstk) + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(src_lo)); + else + /* mov eax,dword ptr [ebp+off] */ + EMIT2(0x8B, add_2reg(0xC0, src_lo, IA32_EAX)); + + switch (BPF_SIZE(code)) { + case BPF_B: + EMIT2(0x0F, 0xB6); break; + case BPF_H: + EMIT2(0x0F, 0xB7); break; + case BPF_W: + case BPF_DW: + EMIT(0x8B, 1); break; + } + + if (is_imm8(insn->off)) + EMIT2(add_2reg(0x40, IA32_EAX, IA32_EDX), + insn->off); + else + EMIT1_off32(add_2reg(0x80, IA32_EAX, IA32_EDX), + insn->off); + + if (dstk) + /* mov dword ptr [ebp+off],edx */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_lo)); + else + /* mov dst_lo,edx */ + EMIT2(0x89, add_2reg(0xC0, dst_lo, IA32_EDX)); + switch (BPF_SIZE(code)) { + case BPF_B: + case BPF_H: + case BPF_W: + if (dstk) { + EMIT3(0xC7, add_1reg(0x40, IA32_EBP), + STACK_VAR(dst_hi)); + EMIT(0x0, 4); + } else { + EMIT3(0xC7, add_1reg(0xC0, dst_hi), 0); + } + break; + case BPF_DW: + EMIT2_off32(0x8B, + add_2reg(0x80, IA32_EAX, IA32_EDX), + insn->off + 4); + if (dstk) + EMIT3(0x89, + add_2reg(0x40, IA32_EBP, + IA32_EDX), + STACK_VAR(dst_hi)); + else + EMIT2(0x89, + add_2reg(0xC0, dst_hi, IA32_EDX)); + break; + default: + break; + } + break; + /* call */ + case BPF_JMP | BPF_CALL: + { + const u8 *r1 = bpf2ia32[BPF_REG_1]; + const u8 *r2 = bpf2ia32[BPF_REG_2]; + const u8 *r3 = bpf2ia32[BPF_REG_3]; + const u8 *r4 = bpf2ia32[BPF_REG_4]; + const u8 *r5 = bpf2ia32[BPF_REG_5]; + + if (insn->src_reg == BPF_PSEUDO_CALL) + goto notyet; + + func = (u8 *) __bpf_call_base + imm32; + jmp_offset = func - (image + addrs[i]); + + if (!imm32 || !is_simm32(jmp_offset)) { + pr_err("unsupported BPF func %d addr %p image %p\n", + imm32, func, image); + return -EINVAL; + } + + /* mov eax,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(r1[0])); + /* mov edx,dword ptr [ebp+off] */ + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(r1[1])); + + emit_push_r64(r5, &prog); + emit_push_r64(r4, &prog); + emit_push_r64(r3, &prog); + emit_push_r64(r2, &prog); + + EMIT1_off32(0xE8, jmp_offset + 9); + + /* mov dword ptr [ebp+off],eax */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(r0[0])); + /* mov dword ptr [ebp+off],edx */ + EMIT3(0x89, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(r0[1])); + + /* add esp,32 */ + EMIT3(0x83, add_1reg(0xC0, IA32_ESP), 32); + break; + } + case BPF_JMP | BPF_TAIL_CALL: + emit_bpf_tail_call(&prog); + break; + + /* cond jump */ + case BPF_JMP | BPF_JEQ | BPF_X: + case BPF_JMP | BPF_JNE | BPF_X: + case BPF_JMP | BPF_JGT | BPF_X: + case BPF_JMP | BPF_JLT | BPF_X: + case BPF_JMP | BPF_JGE | BPF_X: + case BPF_JMP | BPF_JLE | BPF_X: + case BPF_JMP | BPF_JSGT | BPF_X: + case BPF_JMP | BPF_JSLE | BPF_X: + case BPF_JMP | BPF_JSLT | BPF_X: + case BPF_JMP | BPF_JSGE | BPF_X: { + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 sreg_lo = sstk ? IA32_ECX : src_lo; + u8 sreg_hi = sstk ? IA32_EBX : src_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + if (sstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(src_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), + STACK_VAR(src_hi)); + } + + /* cmp dreg_hi,sreg_hi */ + EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi)); + EMIT2(IA32_JNE, 2); + /* cmp dreg_lo,sreg_lo */ + EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo)); + goto emit_cond_jmp; + } + case BPF_JMP | BPF_JSET | BPF_X: { + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 sreg_lo = sstk ? IA32_ECX : src_lo; + u8 sreg_hi = sstk ? IA32_EBX : src_hi; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + if (sstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_ECX), + STACK_VAR(src_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EBX), + STACK_VAR(src_hi)); + } + /* and dreg_lo,sreg_lo */ + EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo)); + /* and dreg_hi,sreg_hi */ + EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); + /* or dreg_lo,dreg_hi */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + goto emit_cond_jmp; + } + case BPF_JMP | BPF_JSET | BPF_K: { + u32 hi; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 sreg_lo = IA32_ECX; + u8 sreg_hi = IA32_EBX; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + hi = imm32 & (1<<31) ? (u32)~0 : 0; + + /* mov ecx,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32); + /* mov ebx,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi); + + /* and dreg_lo,sreg_lo */ + EMIT2(0x23, add_2reg(0xC0, sreg_lo, dreg_lo)); + /* and dreg_hi,sreg_hi */ + EMIT2(0x23, add_2reg(0xC0, sreg_hi, dreg_hi)); + /* or dreg_lo,dreg_hi */ + EMIT2(0x09, add_2reg(0xC0, dreg_lo, dreg_hi)); + goto emit_cond_jmp; + } + case BPF_JMP | BPF_JEQ | BPF_K: + case BPF_JMP | BPF_JNE | BPF_K: + case BPF_JMP | BPF_JGT | BPF_K: + case BPF_JMP | BPF_JLT | BPF_K: + case BPF_JMP | BPF_JGE | BPF_K: + case BPF_JMP | BPF_JLE | BPF_K: + case BPF_JMP | BPF_JSGT | BPF_K: + case BPF_JMP | BPF_JSLE | BPF_K: + case BPF_JMP | BPF_JSLT | BPF_K: + case BPF_JMP | BPF_JSGE | BPF_K: { + u32 hi; + u8 dreg_lo = dstk ? IA32_EAX : dst_lo; + u8 dreg_hi = dstk ? IA32_EDX : dst_hi; + u8 sreg_lo = IA32_ECX; + u8 sreg_hi = IA32_EBX; + + if (dstk) { + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EAX), + STACK_VAR(dst_lo)); + EMIT3(0x8B, add_2reg(0x40, IA32_EBP, IA32_EDX), + STACK_VAR(dst_hi)); + } + + hi = imm32 & (1<<31) ? (u32)~0 : 0; + /* mov ecx,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_ECX), imm32); + /* mov ebx,imm32 */ + EMIT2_off32(0xC7, add_1reg(0xC0, IA32_EBX), hi); + + /* cmp dreg_hi,sreg_hi */ + EMIT2(0x39, add_2reg(0xC0, dreg_hi, sreg_hi)); + EMIT2(IA32_JNE, 2); + /* cmp dreg_lo,sreg_lo */ + EMIT2(0x39, add_2reg(0xC0, dreg_lo, sreg_lo)); + +emit_cond_jmp: /* Convert BPF opcode to x86 */ + switch (BPF_OP(code)) { + case BPF_JEQ: + jmp_cond = IA32_JE; + break; + case BPF_JSET: + case BPF_JNE: + jmp_cond = IA32_JNE; + break; + case BPF_JGT: + /* GT is unsigned '>', JA in x86 */ + jmp_cond = IA32_JA; + break; + case BPF_JLT: + /* LT is unsigned '<', JB in x86 */ + jmp_cond = IA32_JB; + break; + case BPF_JGE: + /* GE is unsigned '>=', JAE in x86 */ + jmp_cond = IA32_JAE; + break; + case BPF_JLE: + /* LE is unsigned '<=', JBE in x86 */ + jmp_cond = IA32_JBE; + break; + case BPF_JSGT: + /* Signed '>', GT in x86 */ + jmp_cond = IA32_JG; + break; + case BPF_JSLT: + /* Signed '<', LT in x86 */ + jmp_cond = IA32_JL; + break; + case BPF_JSGE: + /* Signed '>=', GE in x86 */ + jmp_cond = IA32_JGE; + break; + case BPF_JSLE: + /* Signed '<=', LE in x86 */ + jmp_cond = IA32_JLE; + break; + default: /* to silence GCC warning */ + return -EFAULT; + } + jmp_offset = addrs[i + insn->off] - addrs[i]; + if (is_imm8(jmp_offset)) { + EMIT2(jmp_cond, jmp_offset); + } else if (is_simm32(jmp_offset)) { + EMIT2_off32(0x0F, jmp_cond + 0x10, jmp_offset); + } else { + pr_err("cond_jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } + + break; + } + case BPF_JMP | BPF_JA: + if (insn->off == -1) + /* -1 jmp instructions will always jump + * backwards two bytes. Explicitly handling + * this case avoids wasting too many passes + * when there are long sequences of replaced + * dead code. + */ + jmp_offset = -2; + else + jmp_offset = addrs[i + insn->off] - addrs[i]; + + if (!jmp_offset) + /* Optimize out nop jumps */ + break; +emit_jmp: + if (is_imm8(jmp_offset)) { + EMIT2(0xEB, jmp_offset); + } else if (is_simm32(jmp_offset)) { + EMIT1_off32(0xE9, jmp_offset); + } else { + pr_err("jmp gen bug %llx\n", jmp_offset); + return -EFAULT; + } + break; + /* STX XADD: lock *(u32 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_W: + /* STX XADD: lock *(u64 *)(dst + off) += src */ + case BPF_STX | BPF_XADD | BPF_DW: + goto notyet; + case BPF_JMP | BPF_EXIT: + if (seen_exit) { + jmp_offset = ctx->cleanup_addr - addrs[i]; + goto emit_jmp; + } + seen_exit = true; + /* Update cleanup_addr */ + ctx->cleanup_addr = proglen; + emit_epilogue(&prog, bpf_prog->aux->stack_depth); + break; +notyet: + pr_info_once("*** NOT YET: opcode %02x ***\n", code); + return -EFAULT; + default: + /* + * This error will be seen if new instruction was added + * to interpreter, but not to JIT or if there is junk in + * bpf_prog + */ + pr_err("bpf_jit: unknown opcode %02x\n", code); + return -EINVAL; + } + + ilen = prog - temp; + if (ilen > BPF_MAX_INSN_SIZE) { + pr_err("bpf_jit: fatal insn size error\n"); + return -EFAULT; + } + + if (image) { + if (unlikely(proglen + ilen > oldproglen)) { + pr_err("bpf_jit: fatal error\n"); + return -EFAULT; + } + memcpy(image + proglen, temp, ilen); + } + proglen += ilen; + addrs[i] = proglen; + prog = temp; + } + return proglen; +} + +struct bpf_prog *bpf_int_jit_compile(struct bpf_prog *prog) +{ + struct bpf_binary_header *header = NULL; + struct bpf_prog *tmp, *orig_prog = prog; + int proglen, oldproglen = 0; + struct jit_context ctx = {}; + bool tmp_blinded = false; + u8 *image = NULL; + int *addrs; + int pass; + int i; + + if (!prog->jit_requested) + return orig_prog; + + tmp = bpf_jit_blind_constants(prog); + /* + * If blinding was requested and we failed during blinding, + * we must fall back to the interpreter. + */ + if (IS_ERR(tmp)) + return orig_prog; + if (tmp != prog) { + tmp_blinded = true; + prog = tmp; + } + + addrs = kmalloc(prog->len * sizeof(*addrs), GFP_KERNEL); + if (!addrs) { + prog = orig_prog; + goto out; + } + + /* + * Before first pass, make a rough estimation of addrs[] + * each BPF instruction is translated to less than 64 bytes + */ + for (proglen = 0, i = 0; i < prog->len; i++) { + proglen += 64; + addrs[i] = proglen; + } + ctx.cleanup_addr = proglen; + + /* + * JITed image shrinks with every pass and the loop iterates + * until the image stops shrinking. Very large BPF programs + * may converge on the last pass. In such case do one more + * pass to emit the final image. + */ + for (pass = 0; pass < 20 || image; pass++) { + proglen = do_jit(prog, addrs, image, oldproglen, &ctx); + if (proglen <= 0) { +out_image: + image = NULL; + if (header) + bpf_jit_binary_free(header); + prog = orig_prog; + goto out_addrs; + } + if (image) { + if (proglen != oldproglen) { + pr_err("bpf_jit: proglen=%d != oldproglen=%d\n", + proglen, oldproglen); + goto out_image; + } + break; + } + if (proglen == oldproglen) { + header = bpf_jit_binary_alloc(proglen, &image, + 1, jit_fill_hole); + if (!header) { + prog = orig_prog; + goto out_addrs; + } + } + oldproglen = proglen; + cond_resched(); + } + + if (bpf_jit_enable > 1) + bpf_jit_dump(prog->len, proglen, pass + 1, image); + + if (image) { + bpf_jit_binary_lock_ro(header); + prog->bpf_func = (void *)image; + prog->jited = 1; + prog->jited_len = proglen; + } else { + prog = orig_prog; + } + +out_addrs: + kfree(addrs); +out: + if (tmp_blinded) + bpf_jit_prog_release_other(prog, prog == orig_prog ? + tmp : orig_prog); + return prog; +} diff --git a/drivers/connector/cn_proc.c b/drivers/connector/cn_proc.c index a782ce87715c..ed5e42461094 100644 --- a/drivers/connector/cn_proc.c +++ b/drivers/connector/cn_proc.c @@ -262,6 +262,8 @@ void proc_coredump_connector(struct task_struct *task) ev->what = PROC_EVENT_COREDUMP; ev->event_data.coredump.process_pid = task->pid; ev->event_data.coredump.process_tgid = task->tgid; + ev->event_data.coredump.parent_pid = task->real_parent->pid; + ev->event_data.coredump.parent_tgid = task->real_parent->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ @@ -288,6 +290,8 @@ void proc_exit_connector(struct task_struct *task) ev->event_data.exit.process_tgid = task->tgid; ev->event_data.exit.exit_code = task->exit_code; ev->event_data.exit.exit_signal = task->exit_signal; + ev->event_data.exit.parent_pid = task->real_parent->pid; + ev->event_data.exit.parent_tgid = task->real_parent->tgid; memcpy(&msg->id, &cn_proc_event_id, sizeof(msg->id)); msg->ack = 0; /* not used */ diff --git a/drivers/dca/dca-core.c b/drivers/dca/dca-core.c index 7afbb28d6a0f..1bc5ffb338c8 100644 --- a/drivers/dca/dca-core.c +++ b/drivers/dca/dca-core.c @@ -270,7 +270,7 @@ EXPORT_SYMBOL_GPL(dca_remove_requester); * @dev - the device that wants dca service * @cpu - the cpuid as returned by get_cpu() */ -u8 dca_common_get_tag(struct device *dev, int cpu) +static u8 dca_common_get_tag(struct device *dev, int cpu) { struct dca_provider *dca; u8 tag; diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c index 4be3aef40bd2..267da8215e08 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_encap.c @@ -443,17 +443,16 @@ static u8 opa_vnic_get_rc(struct __opa_veswport_info *info, } /* opa_vnic_calc_entropy - calculate the packet entropy */ -u8 opa_vnic_calc_entropy(struct opa_vnic_adapter *adapter, struct sk_buff *skb) +u8 opa_vnic_calc_entropy(struct sk_buff *skb) { - u16 hash16; - - /* - * Get flow based 16-bit hash and then XOR the upper and lower bytes - * to get the entropy. - * __skb_tx_hash limits qcount to 16 bits. Hence, get 15-bit hash. - */ - hash16 = __skb_tx_hash(adapter->netdev, skb, BIT(15)); - return (u8)((hash16 >> 8) ^ (hash16 & 0xff)); + u32 hash = skb_get_hash(skb); + + /* store XOR of all bytes in lower 8 bits */ + hash ^= hash >> 8; + hash ^= hash >> 16; + + /* return lower 8 bits as entropy */ + return (u8)(hash & 0xFF); } /* opa_vnic_get_def_port - get default port based on entropy */ @@ -490,7 +489,7 @@ void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb) hdr = skb_push(skb, OPA_VNIC_HDR_LEN); - entropy = opa_vnic_calc_entropy(adapter, skb); + entropy = opa_vnic_calc_entropy(skb); def_port = opa_vnic_get_def_port(adapter, entropy); len = opa_vnic_wire_length(skb); dlid = opa_vnic_get_dlid(adapter, skb, def_port); diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h b/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h index afd95f432262..43ac61ffef4a 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_internal.h @@ -299,7 +299,7 @@ struct opa_vnic_adapter *opa_vnic_add_netdev(struct ib_device *ibdev, void opa_vnic_rem_netdev(struct opa_vnic_adapter *adapter); void opa_vnic_encap_skb(struct opa_vnic_adapter *adapter, struct sk_buff *skb); u8 opa_vnic_get_vl(struct opa_vnic_adapter *adapter, struct sk_buff *skb); -u8 opa_vnic_calc_entropy(struct opa_vnic_adapter *adapter, struct sk_buff *skb); +u8 opa_vnic_calc_entropy(struct sk_buff *skb); void opa_vnic_process_vema_config(struct opa_vnic_adapter *adapter); void opa_vnic_release_mac_tbl(struct opa_vnic_adapter *adapter); void opa_vnic_query_mac_tbl(struct opa_vnic_adapter *adapter, diff --git a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c index ce57e0f10289..0c8aec62a425 100644 --- a/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c +++ b/drivers/infiniband/ulp/opa_vnic/opa_vnic_netdev.c @@ -104,7 +104,7 @@ static u16 opa_vnic_select_queue(struct net_device *netdev, struct sk_buff *skb, /* pass entropy and vl as metadata in skb */ mdata = skb_push(skb, sizeof(*mdata)); - mdata->entropy = opa_vnic_calc_entropy(adapter, skb); + mdata->entropy = opa_vnic_calc_entropy(skb); mdata->vl = opa_vnic_get_vl(adapter, skb); rc = adapter->rn_ops->ndo_select_queue(netdev, skb, accel_priv, fallback); diff --git a/drivers/net/Kconfig b/drivers/net/Kconfig index 891846655000..a029b27fd002 100644 --- a/drivers/net/Kconfig +++ b/drivers/net/Kconfig @@ -198,6 +198,7 @@ config VXLAN config GENEVE tristate "Generic Network Virtualization Encapsulation" depends on INET && NET_UDP_TUNNEL + depends on IPV6 || !IPV6 select NET_IP_TUNNEL select GRO_CELLS ---help--- diff --git a/drivers/net/bonding/bond_alb.c b/drivers/net/bonding/bond_alb.c index 5eb0df2e5464..a8f60982d483 100644 --- a/drivers/net/bonding/bond_alb.c +++ b/drivers/net/bonding/bond_alb.c @@ -1319,8 +1319,8 @@ void bond_alb_deinitialize(struct bonding *bond) rlb_deinitialize(bond); } -static int bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, - struct slave *tx_slave) +static netdev_tx_t bond_do_alb_xmit(struct sk_buff *skb, struct bonding *bond, + struct slave *tx_slave) { struct alb_bond_info *bond_info = &(BOND_ALB_INFO(bond)); struct ethhdr *eth_data = eth_hdr(skb); @@ -1354,7 +1354,7 @@ out: return NETDEV_TX_OK; } -int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) +netdev_tx_t bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct ethhdr *eth_data; @@ -1392,7 +1392,7 @@ int bond_tlb_xmit(struct sk_buff *skb, struct net_device *bond_dev) return bond_do_alb_xmit(skb, bond, tx_slave); } -int bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) +netdev_tx_t bond_alb_xmit(struct sk_buff *skb, struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct ethhdr *eth_data; diff --git a/drivers/net/bonding/bond_main.c b/drivers/net/bonding/bond_main.c index 1f1e97b26f95..4176e1d95f47 100644 --- a/drivers/net/bonding/bond_main.c +++ b/drivers/net/bonding/bond_main.c @@ -247,7 +247,7 @@ void bond_dev_queue_xmit(struct bonding *bond, struct sk_buff *skb, BUILD_BUG_ON(sizeof(skb->queue_mapping) != sizeof(qdisc_skb_cb(skb)->slave_dev_queue_mapping)); - skb->queue_mapping = qdisc_skb_cb(skb)->slave_dev_queue_mapping; + skb_set_queue_mapping(skb, qdisc_skb_cb(skb)->slave_dev_queue_mapping); if (unlikely(netpoll_tx_running(bond->dev))) bond_netpoll_send_skb(bond_get_slave_by_dev(bond, slave_dev), skb); @@ -3807,7 +3807,8 @@ static u32 bond_rr_gen_slave_id(struct bonding *bond) return slave_id; } -static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev) +static netdev_tx_t bond_xmit_roundrobin(struct sk_buff *skb, + struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct iphdr *iph = ip_hdr(skb); @@ -3843,7 +3844,8 @@ static int bond_xmit_roundrobin(struct sk_buff *skb, struct net_device *bond_dev /* In active-backup mode, we know that bond->curr_active_slave is always valid if * the bond has a usable interface. */ -static int bond_xmit_activebackup(struct sk_buff *skb, struct net_device *bond_dev) +static netdev_tx_t bond_xmit_activebackup(struct sk_buff *skb, + struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave; @@ -3981,7 +3983,8 @@ out: * usable slave array is formed in the control path. The xmit function * just calculates hash and sends the packet out. */ -static int bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) +static netdev_tx_t bond_3ad_xor_xmit(struct sk_buff *skb, + struct net_device *dev) { struct bonding *bond = netdev_priv(dev); struct slave *slave; @@ -4001,7 +4004,8 @@ static int bond_3ad_xor_xmit(struct sk_buff *skb, struct net_device *dev) } /* in broadcast mode, we send everything to all usable interfaces. */ -static int bond_xmit_broadcast(struct sk_buff *skb, struct net_device *bond_dev) +static netdev_tx_t bond_xmit_broadcast(struct sk_buff *skb, + struct net_device *bond_dev) { struct bonding *bond = netdev_priv(bond_dev); struct slave *slave = NULL; @@ -4038,12 +4042,12 @@ static inline int bond_slave_override(struct bonding *bond, struct slave *slave = NULL; struct list_head *iter; - if (!skb->queue_mapping) + if (!skb_rx_queue_recorded(skb)) return 1; /* Find out if any slaves have the same mapping as this skb. */ bond_for_each_slave_rcu(bond, slave, iter) { - if (slave->queue_id == skb->queue_mapping) { + if (slave->queue_id == skb_get_queue_mapping(skb)) { if (bond_slave_is_up(slave) && slave->link == BOND_LINK_UP) { bond_dev_queue_xmit(bond, skb, slave->dev); @@ -4069,7 +4073,7 @@ static u16 bond_select_queue(struct net_device *dev, struct sk_buff *skb, u16 txq = skb_rx_queue_recorded(skb) ? skb_get_rx_queue(skb) : 0; /* Save the original txq to restore before passing to the driver */ - qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb->queue_mapping; + qdisc_skb_cb(skb)->slave_dev_queue_mapping = skb_get_queue_mapping(skb); if (unlikely(txq >= dev->real_num_tx_queues)) { do { diff --git a/drivers/net/dsa/b53/b53_common.c b/drivers/net/dsa/b53/b53_common.c index 78616787f2a3..9f561fe505cb 100644 --- a/drivers/net/dsa/b53/b53_common.c +++ b/drivers/net/dsa/b53/b53_common.c @@ -806,16 +806,39 @@ static unsigned int b53_get_mib_size(struct b53_device *dev) return B53_MIBS_SIZE; } -void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data) +static struct phy_device *b53_get_phy_device(struct dsa_switch *ds, int port) +{ + /* These ports typically do not have built-in PHYs */ + switch (port) { + case B53_CPU_PORT_25: + case 7: + case B53_CPU_PORT: + return NULL; + } + + return mdiobus_get_phy(ds->slave_mii_bus, port); +} + +void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t *data) { struct b53_device *dev = ds->priv; const struct b53_mib_desc *mibs = b53_get_mib(dev); unsigned int mib_size = b53_get_mib_size(dev); + struct phy_device *phydev; unsigned int i; - for (i = 0; i < mib_size; i++) - strlcpy(data + i * ETH_GSTRING_LEN, - mibs[i].name, ETH_GSTRING_LEN); + if (stringset == ETH_SS_STATS) { + for (i = 0; i < mib_size; i++) + strlcpy(data + i * ETH_GSTRING_LEN, + mibs[i].name, ETH_GSTRING_LEN); + } else if (stringset == ETH_SS_PHY_STATS) { + phydev = b53_get_phy_device(ds, port); + if (!phydev) + return; + + phy_ethtool_get_strings(phydev, data); + } } EXPORT_SYMBOL(b53_get_strings); @@ -852,11 +875,34 @@ void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data) } EXPORT_SYMBOL(b53_get_ethtool_stats); -int b53_get_sset_count(struct dsa_switch *ds, int port) +void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data) +{ + struct phy_device *phydev; + + phydev = b53_get_phy_device(ds, port); + if (!phydev) + return; + + phy_ethtool_get_stats(phydev, NULL, data); +} +EXPORT_SYMBOL(b53_get_ethtool_phy_stats); + +int b53_get_sset_count(struct dsa_switch *ds, int port, int sset) { struct b53_device *dev = ds->priv; + struct phy_device *phydev; + + if (sset == ETH_SS_STATS) { + return b53_get_mib_size(dev); + } else if (sset == ETH_SS_PHY_STATS) { + phydev = b53_get_phy_device(ds, port); + if (!phydev) + return 0; + + return phy_ethtool_get_sset_count(phydev); + } - return b53_get_mib_size(dev); + return 0; } EXPORT_SYMBOL(b53_get_sset_count); @@ -1477,7 +1523,7 @@ void b53_br_fast_age(struct dsa_switch *ds, int port) } EXPORT_SYMBOL(b53_br_fast_age); -static bool b53_can_enable_brcm_tags(struct dsa_switch *ds, int port) +static bool b53_possible_cpu_port(struct dsa_switch *ds, int port) { /* Broadcom switches will accept enabling Broadcom tags on the * following ports: 5, 7 and 8, any other port is not supported @@ -1489,10 +1535,19 @@ static bool b53_can_enable_brcm_tags(struct dsa_switch *ds, int port) return true; } - dev_warn(ds->dev, "Port %d is not Broadcom tag capable\n", port); return false; } +static bool b53_can_enable_brcm_tags(struct dsa_switch *ds, int port) +{ + bool ret = b53_possible_cpu_port(ds, port); + + if (!ret) + dev_warn(ds->dev, "Port %d is not Broadcom tag capable\n", + port); + return ret; +} + enum dsa_tag_protocol b53_get_tag_protocol(struct dsa_switch *ds, int port) { struct b53_device *dev = ds->priv; @@ -1650,6 +1705,7 @@ static const struct dsa_switch_ops b53_switch_ops = { .get_strings = b53_get_strings, .get_ethtool_stats = b53_get_ethtool_stats, .get_sset_count = b53_get_sset_count, + .get_ethtool_phy_stats = b53_get_ethtool_phy_stats, .phy_read = b53_phy_read16, .phy_write = b53_phy_write16, .adjust_link = b53_adjust_link, @@ -1954,6 +2010,15 @@ static int b53_switch_init(struct b53_device *dev) dev->num_ports = dev->cpu_port + 1; dev->enabled_ports |= BIT(dev->cpu_port); + /* Include non standard CPU port built-in PHYs to be probed */ + if (is539x(dev) || is531x5(dev)) { + for (i = 0; i < dev->num_ports; i++) { + if (!(dev->ds->phys_mii_mask & BIT(i)) && + !b53_possible_cpu_port(dev->ds, i)) + dev->ds->phys_mii_mask |= BIT(i); + } + } + dev->ports = devm_kzalloc(dev->dev, sizeof(struct b53_port) * dev->num_ports, GFP_KERNEL); diff --git a/drivers/net/dsa/b53/b53_priv.h b/drivers/net/dsa/b53/b53_priv.h index 1187ebd79287..cc284a514de9 100644 --- a/drivers/net/dsa/b53/b53_priv.h +++ b/drivers/net/dsa/b53/b53_priv.h @@ -286,9 +286,11 @@ static inline int b53_switch_get_reset_gpio(struct b53_device *dev) /* Exported functions towards other drivers */ void b53_imp_vlan_setup(struct dsa_switch *ds, int cpu_port); int b53_configure_vlan(struct dsa_switch *ds); -void b53_get_strings(struct dsa_switch *ds, int port, uint8_t *data); +void b53_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t *data); void b53_get_ethtool_stats(struct dsa_switch *ds, int port, uint64_t *data); -int b53_get_sset_count(struct dsa_switch *ds, int port); +int b53_get_sset_count(struct dsa_switch *ds, int port, int sset); +void b53_get_ethtool_phy_stats(struct dsa_switch *ds, int port, uint64_t *data); int b53_br_join(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_leave(struct dsa_switch *ds, int port, struct net_device *bridge); void b53_br_set_stp_state(struct dsa_switch *ds, int port, u8 state); diff --git a/drivers/net/dsa/bcm_sf2.c b/drivers/net/dsa/bcm_sf2.c index 0378eded31f2..ac621f44237a 100644 --- a/drivers/net/dsa/bcm_sf2.c +++ b/drivers/net/dsa/bcm_sf2.c @@ -16,6 +16,7 @@ #include <linux/platform_device.h> #include <linux/phy.h> #include <linux/phy_fixed.h> +#include <linux/phylink.h> #include <linux/mii.h> #include <linux/of.h> #include <linux/of_irq.h> @@ -306,7 +307,8 @@ static int bcm_sf2_sw_mdio_write(struct mii_bus *bus, int addr, int regnum, static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id) { - struct bcm_sf2_priv *priv = dev_id; + struct dsa_switch *ds = dev_id; + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); priv->irq0_stat = intrl2_0_readl(priv, INTRL2_CPU_STATUS) & ~priv->irq0_mask; @@ -317,16 +319,21 @@ static irqreturn_t bcm_sf2_switch_0_isr(int irq, void *dev_id) static irqreturn_t bcm_sf2_switch_1_isr(int irq, void *dev_id) { - struct bcm_sf2_priv *priv = dev_id; + struct dsa_switch *ds = dev_id; + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); priv->irq1_stat = intrl2_1_readl(priv, INTRL2_CPU_STATUS) & ~priv->irq1_mask; intrl2_1_writel(priv, priv->irq1_stat, INTRL2_CPU_CLEAR); - if (priv->irq1_stat & P_LINK_UP_IRQ(P7_IRQ_OFF)) - priv->port_sts[7].link = 1; - if (priv->irq1_stat & P_LINK_DOWN_IRQ(P7_IRQ_OFF)) - priv->port_sts[7].link = 0; + if (priv->irq1_stat & P_LINK_UP_IRQ(P7_IRQ_OFF)) { + priv->port_sts[7].link = true; + dsa_port_phylink_mac_change(ds, 7, true); + } + if (priv->irq1_stat & P_LINK_DOWN_IRQ(P7_IRQ_OFF)) { + priv->port_sts[7].link = false; + dsa_port_phylink_mac_change(ds, 7, false); + } return IRQ_HANDLED; } @@ -473,13 +480,56 @@ static u32 bcm_sf2_sw_get_phy_flags(struct dsa_switch *ds, int port) return priv->hw_params.gphy_rev; } -static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port, - struct phy_device *phydev) +static void bcm_sf2_sw_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ + __ETHTOOL_DECLARE_LINK_MODE_MASK(mask) = { 0, }; + + if (!phy_interface_mode_is_rgmii(state->interface) && + state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII && + state->interface != PHY_INTERFACE_MODE_GMII && + state->interface != PHY_INTERFACE_MODE_INTERNAL && + state->interface != PHY_INTERFACE_MODE_MOCA) { + bitmap_zero(supported, __ETHTOOL_LINK_MODE_MASK_NBITS); + dev_err(ds->dev, + "Unsupported interface: %d\n", state->interface); + return; + } + + /* Allow all the expected bits */ + phylink_set(mask, Autoneg); + phylink_set_port_modes(mask); + phylink_set(mask, Pause); + phylink_set(mask, Asym_Pause); + + /* With the exclusion of MII and Reverse MII, we support Gigabit, + * including Half duplex + */ + if (state->interface != PHY_INTERFACE_MODE_MII && + state->interface != PHY_INTERFACE_MODE_REVMII) { + phylink_set(mask, 1000baseT_Full); + phylink_set(mask, 1000baseT_Half); + } + + phylink_set(mask, 10baseT_Half); + phylink_set(mask, 10baseT_Full); + phylink_set(mask, 100baseT_Half); + phylink_set(mask, 100baseT_Full); + + bitmap_and(supported, supported, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); + bitmap_and(state->advertising, state->advertising, mask, + __ETHTOOL_LINK_MODE_MASK_NBITS); +} + +static void bcm_sf2_sw_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - struct ethtool_eee *p = &priv->dev->ports[port].eee; u32 id_mode_dis = 0, port_mode; - const char *str = NULL; u32 reg, offset; if (priv->type == BCM7445_DEVICE_ID) @@ -487,62 +537,48 @@ static void bcm_sf2_sw_adjust_link(struct dsa_switch *ds, int port, else offset = CORE_STS_OVERRIDE_GMIIP2_PORT(port); - switch (phydev->interface) { + switch (state->interface) { case PHY_INTERFACE_MODE_RGMII: - str = "RGMII (no delay)"; id_mode_dis = 1; + /* fallthrough */ case PHY_INTERFACE_MODE_RGMII_TXID: - if (!str) - str = "RGMII (TX delay)"; port_mode = EXT_GPHY; break; case PHY_INTERFACE_MODE_MII: - str = "MII"; port_mode = EXT_EPHY; break; case PHY_INTERFACE_MODE_REVMII: - str = "Reverse MII"; port_mode = EXT_REVMII; break; default: - /* All other PHYs: internal and MoCA */ - goto force_link; - } - - /* If the link is down, just disable the interface to conserve power */ - if (!phydev->link) { - reg = reg_readl(priv, REG_RGMII_CNTRL_P(port)); - reg &= ~RGMII_MODE_EN; - reg_writel(priv, reg, REG_RGMII_CNTRL_P(port)); + /* all other PHYs: internal and MoCA */ goto force_link; } - /* Clear id_mode_dis bit, and the existing port mode, but - * make sure we enable the RGMII block for data to pass + /* Clear id_mode_dis bit, and the existing port mode, let + * RGMII_MODE_EN bet set by mac_link_{up,down} */ reg = reg_readl(priv, REG_RGMII_CNTRL_P(port)); reg &= ~ID_MODE_DIS; reg &= ~(PORT_MODE_MASK << PORT_MODE_SHIFT); reg &= ~(RX_PAUSE_EN | TX_PAUSE_EN); - reg |= port_mode | RGMII_MODE_EN; + reg |= port_mode; if (id_mode_dis) reg |= ID_MODE_DIS; - if (phydev->pause) { - if (phydev->asym_pause) + if (state->pause & MLO_PAUSE_TXRX_MASK) { + if (state->pause & MLO_PAUSE_TX) reg |= TX_PAUSE_EN; reg |= RX_PAUSE_EN; } reg_writel(priv, reg, REG_RGMII_CNTRL_P(port)); - pr_info("Port %d configured for %s\n", port, str); - force_link: /* Force link settings detected from the PHY */ reg = SW_OVERRIDE; - switch (phydev->speed) { + switch (state->speed) { case SPEED_1000: reg |= SPDSTS_1000 << SPEED_SHIFT; break; @@ -551,33 +587,61 @@ force_link: break; } - if (phydev->link) + if (state->link) reg |= LINK_STS; - if (phydev->duplex == DUPLEX_FULL) + if (state->duplex == DUPLEX_FULL) reg |= DUPLX_MODE; core_writel(priv, reg, offset); - - if (!phydev->is_pseudo_fixed_link) - p->eee_enabled = b53_eee_init(ds, port, phydev); } -static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, - struct fixed_phy_status *status) +static void bcm_sf2_sw_mac_link_set(struct dsa_switch *ds, int port, + phy_interface_t interface, bool link) { struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); - u32 duplex, pause, offset; u32 reg; - if (priv->type == BCM7445_DEVICE_ID) - offset = CORE_STS_OVERRIDE_GMIIP_PORT(port); + if (!phy_interface_mode_is_rgmii(interface) && + interface != PHY_INTERFACE_MODE_MII && + interface != PHY_INTERFACE_MODE_REVMII) + return; + + /* If the link is down, just disable the interface to conserve power */ + reg = reg_readl(priv, REG_RGMII_CNTRL_P(port)); + if (link) + reg |= RGMII_MODE_EN; else - offset = CORE_STS_OVERRIDE_GMIIP2_PORT(port); + reg &= ~RGMII_MODE_EN; + reg_writel(priv, reg, REG_RGMII_CNTRL_P(port)); +} + +static void bcm_sf2_sw_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + bcm_sf2_sw_mac_link_set(ds, port, interface, false); +} + +static void bcm_sf2_sw_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + struct ethtool_eee *p = &priv->dev->ports[port].eee; - duplex = core_readl(priv, CORE_DUPSTS); - pause = core_readl(priv, CORE_PAUSESTS); + bcm_sf2_sw_mac_link_set(ds, port, interface, true); - status->link = 0; + if (mode == MLO_AN_PHY && phydev) + p->eee_enabled = b53_eee_init(ds, port, phydev); +} + +static void bcm_sf2_sw_fixed_state(struct dsa_switch *ds, int port, + struct phylink_link_state *status) +{ + struct bcm_sf2_priv *priv = bcm_sf2_to_priv(ds); + + status->link = false; /* MoCA port is special as we do not get link status from CORE_LNKSTS, * which means that we need to force the link at the port override @@ -596,28 +660,10 @@ static void bcm_sf2_sw_fixed_link_update(struct dsa_switch *ds, int port, */ if (!status->link) netif_carrier_off(ds->ports[port].slave); - status->duplex = 1; + status->duplex = DUPLEX_FULL; } else { - status->link = 1; - status->duplex = !!(duplex & (1 << port)); - } - - reg = core_readl(priv, offset); - reg |= SW_OVERRIDE; - if (status->link) - reg |= LINK_STS; - else - reg &= ~LINK_STS; - core_writel(priv, reg, offset); - - if ((pause & (1 << port)) && - (pause & (1 << (port + PAUSESTS_TX_PAUSE_SHIFT)))) { - status->asym_pause = 1; - status->pause = 1; + status->link = true; } - - if (pause & (1 << port)) - status->pause = 1; } static void bcm_sf2_enable_acb(struct dsa_switch *ds) @@ -859,9 +905,13 @@ static const struct dsa_switch_ops bcm_sf2_ops = { .get_strings = b53_get_strings, .get_ethtool_stats = b53_get_ethtool_stats, .get_sset_count = b53_get_sset_count, + .get_ethtool_phy_stats = b53_get_ethtool_phy_stats, .get_phy_flags = bcm_sf2_sw_get_phy_flags, - .adjust_link = bcm_sf2_sw_adjust_link, - .fixed_link_update = bcm_sf2_sw_fixed_link_update, + .phylink_validate = bcm_sf2_sw_validate, + .phylink_mac_config = bcm_sf2_sw_mac_config, + .phylink_mac_link_down = bcm_sf2_sw_mac_link_down, + .phylink_mac_link_up = bcm_sf2_sw_mac_link_up, + .phylink_fixed_state = bcm_sf2_sw_fixed_state, .suspend = bcm_sf2_sw_suspend, .resume = bcm_sf2_sw_resume, .get_wol = bcm_sf2_sw_get_wol, @@ -1064,14 +1114,14 @@ static int bcm_sf2_sw_probe(struct platform_device *pdev) bcm_sf2_intr_disable(priv); ret = devm_request_irq(&pdev->dev, priv->irq0, bcm_sf2_switch_0_isr, 0, - "switch_0", priv); + "switch_0", ds); if (ret < 0) { pr_err("failed to request switch_0 IRQ\n"); goto out_mdio; } ret = devm_request_irq(&pdev->dev, priv->irq1, bcm_sf2_switch_1_isr, 0, - "switch_1", priv); + "switch_1", ds); if (ret < 0) { pr_err("failed to request switch_1 IRQ\n"); goto out_mdio; diff --git a/drivers/net/dsa/dsa_loop.c b/drivers/net/dsa/dsa_loop.c index f77be9f85cb3..58f14af04639 100644 --- a/drivers/net/dsa/dsa_loop.c +++ b/drivers/net/dsa/dsa_loop.c @@ -86,16 +86,23 @@ static int dsa_loop_setup(struct dsa_switch *ds) return 0; } -static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port) +static int dsa_loop_get_sset_count(struct dsa_switch *ds, int port, int sset) { + if (sset != ETH_SS_STATS && sset != ETH_SS_PHY_STATS) + return 0; + return __DSA_LOOP_CNT_MAX; } -static void dsa_loop_get_strings(struct dsa_switch *ds, int port, uint8_t *data) +static void dsa_loop_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data) { struct dsa_loop_priv *ps = ds->priv; unsigned int i; + if (stringset != ETH_SS_STATS && stringset != ETH_SS_PHY_STATS) + return; + for (i = 0; i < __DSA_LOOP_CNT_MAX; i++) memcpy(data + i * ETH_GSTRING_LEN, ps->ports[port].mib[i].name, ETH_GSTRING_LEN); @@ -256,6 +263,7 @@ static const struct dsa_switch_ops dsa_loop_driver = { .get_strings = dsa_loop_get_strings, .get_ethtool_stats = dsa_loop_get_ethtool_stats, .get_sset_count = dsa_loop_get_sset_count, + .get_ethtool_phy_stats = dsa_loop_get_ethtool_stats, .phy_read = dsa_loop_phy_read, .phy_write = dsa_loop_phy_write, .port_bridge_join = dsa_loop_port_bridge_join, diff --git a/drivers/net/dsa/lan9303-core.c b/drivers/net/dsa/lan9303-core.c index fefa454f3e56..b4f6e1a67dd9 100644 --- a/drivers/net/dsa/lan9303-core.c +++ b/drivers/net/dsa/lan9303-core.c @@ -977,10 +977,14 @@ static const struct lan9303_mib_desc lan9303_mib[] = { { .offset = LAN9303_MAC_TX_LATECOL_0, .name = "TxLateCol", }, }; -static void lan9303_get_strings(struct dsa_switch *ds, int port, uint8_t *data) +static void lan9303_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data) { unsigned int u; + if (stringset != ETH_SS_STATS) + return; + for (u = 0; u < ARRAY_SIZE(lan9303_mib); u++) { strncpy(data + u * ETH_GSTRING_LEN, lan9303_mib[u].name, ETH_GSTRING_LEN); @@ -1007,8 +1011,11 @@ static void lan9303_get_ethtool_stats(struct dsa_switch *ds, int port, } } -static int lan9303_get_sset_count(struct dsa_switch *ds, int port) +static int lan9303_get_sset_count(struct dsa_switch *ds, int port, int sset) { + if (sset != ETH_SS_STATS) + return 0; + return ARRAY_SIZE(lan9303_mib); } diff --git a/drivers/net/dsa/microchip/ksz_common.c b/drivers/net/dsa/microchip/ksz_common.c index bcb3e6c734f2..7210c49b7922 100644 --- a/drivers/net/dsa/microchip/ksz_common.c +++ b/drivers/net/dsa/microchip/ksz_common.c @@ -439,15 +439,22 @@ static void ksz_disable_port(struct dsa_switch *ds, int port, ksz_port_cfg(dev, port, REG_PORT_CTRL_0, PORT_MAC_LOOPBACK, true); } -static int ksz_sset_count(struct dsa_switch *ds, int port) +static int ksz_sset_count(struct dsa_switch *ds, int port, int sset) { + if (sset != ETH_SS_STATS) + return 0; + return TOTAL_SWITCH_COUNTER_NUM; } -static void ksz_get_strings(struct dsa_switch *ds, int port, uint8_t *buf) +static void ksz_get_strings(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *buf) { int i; + if (stringset != ETH_SS_STATS) + return; + for (i = 0; i < TOTAL_SWITCH_COUNTER_NUM; i++) { memcpy(buf + i * ETH_GSTRING_LEN, mib_names[i].string, ETH_GSTRING_LEN); diff --git a/drivers/net/dsa/mt7530.c b/drivers/net/dsa/mt7530.c index 80a4dbc3a499..62e486652e62 100644 --- a/drivers/net/dsa/mt7530.c +++ b/drivers/net/dsa/mt7530.c @@ -573,10 +573,14 @@ static int mt7530_phy_write(struct dsa_switch *ds, int port, int regnum, } static void -mt7530_get_strings(struct dsa_switch *ds, int port, uint8_t *data) +mt7530_get_strings(struct dsa_switch *ds, int port, u32 stringset, + uint8_t *data) { int i; + if (stringset != ETH_SS_STATS) + return; + for (i = 0; i < ARRAY_SIZE(mt7530_mib); i++) strncpy(data + i * ETH_GSTRING_LEN, mt7530_mib[i].name, ETH_GSTRING_LEN); @@ -604,8 +608,11 @@ mt7530_get_ethtool_stats(struct dsa_switch *ds, int port, } static int -mt7530_get_sset_count(struct dsa_switch *ds, int port) +mt7530_get_sset_count(struct dsa_switch *ds, int port, int sset) { + if (sset != ETH_SS_STATS) + return 0; + return ARRAY_SIZE(mt7530_mib); } diff --git a/drivers/net/dsa/mv88e6xxx/chip.c b/drivers/net/dsa/mv88e6xxx/chip.c index 5b4374f21d76..2910f68c0e5c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.c +++ b/drivers/net/dsa/mv88e6xxx/chip.c @@ -31,6 +31,7 @@ #include <linux/netdevice.h> #include <linux/gpio/consumer.h> #include <linux/phy.h> +#include <linux/phylink.h> #include <net/dsa.h> #include "chip.h" @@ -580,6 +581,83 @@ static void mv88e6xxx_adjust_link(struct dsa_switch *ds, int port, dev_err(ds->dev, "p%d: failed to configure MAC\n", port); } +static void mv88e6xxx_validate(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state) +{ +} + +static int mv88e6xxx_link_state(struct dsa_switch *ds, int port, + struct phylink_link_state *state) +{ + struct mv88e6xxx_chip *chip = ds->priv; + int err; + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_link_state(chip, port, state); + mutex_unlock(&chip->reg_lock); + + return err; +} + +static void mv88e6xxx_mac_config(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct mv88e6xxx_chip *chip = ds->priv; + int speed, duplex, link, err; + + if (mode == MLO_AN_PHY) + return; + + if (mode == MLO_AN_FIXED) { + link = LINK_FORCED_UP; + speed = state->speed; + duplex = state->duplex; + } else { + speed = SPEED_UNFORCED; + duplex = DUPLEX_UNFORCED; + link = LINK_UNFORCED; + } + + mutex_lock(&chip->reg_lock); + err = mv88e6xxx_port_setup_mac(chip, port, link, speed, duplex, + state->interface); + mutex_unlock(&chip->reg_lock); + + if (err && err != -EOPNOTSUPP) + dev_err(ds->dev, "p%d: failed to configure MAC\n", port); +} + +static void mv88e6xxx_mac_link_force(struct dsa_switch *ds, int port, int link) +{ + struct mv88e6xxx_chip *chip = ds->priv; + int err; + + mutex_lock(&chip->reg_lock); + err = chip->info->ops->port_set_link(chip, port, link); + mutex_unlock(&chip->reg_lock); + + if (err) + dev_err(chip->dev, "p%d: failed to force MAC link\n", port); +} + +static void mv88e6xxx_mac_link_down(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface) +{ + if (mode == MLO_AN_FIXED) + mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_DOWN); +} + +static void mv88e6xxx_mac_link_up(struct dsa_switch *ds, int port, + unsigned int mode, phy_interface_t interface, + struct phy_device *phydev) +{ + if (mode == MLO_AN_FIXED) + mv88e6xxx_mac_link_force(ds, port, LINK_FORCED_UP); +} + static int mv88e6xxx_stats_snapshot(struct mv88e6xxx_chip *chip, int port) { if (!chip->info->ops->stats_snapshot) @@ -665,13 +743,13 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, case STATS_TYPE_PORT: err = mv88e6xxx_port_read(chip, port, s->reg, ®); if (err) - return UINT64_MAX; + return U64_MAX; low = reg; if (s->size == 4) { err = mv88e6xxx_port_read(chip, port, s->reg + 1, ®); if (err) - return UINT64_MAX; + return U64_MAX; high = reg; } break; @@ -685,7 +763,7 @@ static uint64_t _mv88e6xxx_get_ethtool_stat(struct mv88e6xxx_chip *chip, mv88e6xxx_g1_stats_read(chip, reg + 1, &high); break; default: - return UINT64_MAX; + return U64_MAX; } value = (((u64)high) << 16) | low; return value; @@ -742,11 +820,14 @@ static void mv88e6xxx_atu_vtu_get_strings(uint8_t *data) } static void mv88e6xxx_get_strings(struct dsa_switch *ds, int port, - uint8_t *data) + u32 stringset, uint8_t *data) { struct mv88e6xxx_chip *chip = ds->priv; int count = 0; + if (stringset != ETH_SS_STATS) + return; + mutex_lock(&chip->reg_lock); if (chip->info->ops->stats_get_strings) @@ -789,12 +870,15 @@ static int mv88e6320_stats_get_sset_count(struct mv88e6xxx_chip *chip) STATS_TYPE_BANK1); } -static int mv88e6xxx_get_sset_count(struct dsa_switch *ds, int port) +static int mv88e6xxx_get_sset_count(struct dsa_switch *ds, int port, int sset) { struct mv88e6xxx_chip *chip = ds->priv; int serdes_count = 0; int count = 0; + if (sset != ETH_SS_STATS) + return 0; + mutex_lock(&chip->reg_lock); if (chip->info->ops->stats_get_sset_count) count = chip->info->ops->stats_get_sset_count(chip); @@ -1020,6 +1104,57 @@ static void mv88e6xxx_port_stp_state_set(struct dsa_switch *ds, int port, dev_err(ds->dev, "p%d: failed to update state\n", port); } +static int mv88e6xxx_devmap_setup(struct mv88e6xxx_chip *chip) +{ + int target, port; + int err; + + if (!chip->info->global2_addr) + return 0; + + /* Initialize the routing port to the 32 possible target devices */ + for (target = 0; target < 32; target++) { + port = 0x1f; + if (target < DSA_MAX_SWITCHES) + if (chip->ds->rtable[target] != DSA_RTABLE_NONE) + port = chip->ds->rtable[target]; + + err = mv88e6xxx_g2_device_mapping_write(chip, target, port); + if (err) + return err; + } + + if (chip->info->ops->set_cascade_port) { + port = MV88E6XXX_CASCADE_PORT_MULTIPLE; + err = chip->info->ops->set_cascade_port(chip, port); + if (err) + return err; + } + + err = mv88e6xxx_g1_set_device_number(chip, chip->ds->index); + if (err) + return err; + + return 0; +} + +static int mv88e6xxx_trunk_setup(struct mv88e6xxx_chip *chip) +{ + /* Clear all trunk masks and mapping */ + if (chip->info->global2_addr) + return mv88e6xxx_g2_trunk_clear(chip); + + return 0; +} + +static int mv88e6xxx_rmu_setup(struct mv88e6xxx_chip *chip) +{ + if (chip->info->ops->rmu_disable) + return chip->info->ops->rmu_disable(chip); + + return 0; +} + static int mv88e6xxx_pot_setup(struct mv88e6xxx_chip *chip) { if (chip->info->ops->pot_clear) @@ -2115,16 +2250,8 @@ static int mv88e6xxx_set_ageing_time(struct dsa_switch *ds, static int mv88e6xxx_g1_setup(struct mv88e6xxx_chip *chip) { - struct dsa_switch *ds = chip->ds; int err; - /* Disable remote management, and set the switch's DSA device number. */ - err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL2, - MV88E6XXX_G1_CTL2_MULTIPLE_CASCADE | - (ds->index & 0x1f)); - if (err) - return err; - /* Configure the IP ToS mapping registers. */ err = mv88e6xxx_g1_write(chip, MV88E6XXX_G1_IP_PRI_0, 0x0000); if (err) @@ -2190,13 +2317,6 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) if (err) goto unlock; - /* Setup Switch Global 2 Registers */ - if (chip->info->global2_addr) { - err = mv88e6xxx_g2_setup(chip); - if (err) - goto unlock; - } - err = mv88e6xxx_irl_setup(chip); if (err) goto unlock; @@ -2229,10 +2349,22 @@ static int mv88e6xxx_setup(struct dsa_switch *ds) if (err) goto unlock; + err = mv88e6xxx_rmu_setup(chip); + if (err) + goto unlock; + err = mv88e6xxx_rsvd2cpu_setup(chip); if (err) goto unlock; + err = mv88e6xxx_trunk_setup(chip); + if (err) + goto unlock; + + err = mv88e6xxx_devmap_setup(chip); + if (err) + goto unlock; + /* Setup PTP Hardware Clock and timestamping */ if (chip->info->ptp_support) { err = mv88e6xxx_ptp_setup(chip); @@ -2488,8 +2620,10 @@ static const struct mv88e6xxx_ops mv88e6085_ops = { .ppu_enable = mv88e6185_g1_ppu_enable, .ppu_disable = mv88e6185_g1_ppu_disable, .reset = mv88e6185_g1_reset, + .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6095_ops = { @@ -2545,6 +2679,7 @@ static const struct mv88e6xxx_ops mv88e6097_ops = { .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6085_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, }; @@ -2603,6 +2738,7 @@ static const struct mv88e6xxx_ops mv88e6131_ops = { .watchdog_ops = &mv88e6097_watchdog_ops, .mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu, .ppu_enable = mv88e6185_g1_ppu_enable, + .set_cascade_port = mv88e6185_g1_set_cascade_port, .ppu_disable = mv88e6185_g1_ppu_disable, .reset = mv88e6185_g1_reset, .vtu_getnext = mv88e6185_g1_vtu_getnext, @@ -2771,6 +2907,7 @@ static const struct mv88e6xxx_ops mv88e6172_ops = { .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6352_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, @@ -2809,6 +2946,7 @@ static const struct mv88e6xxx_ops mv88e6175_ops = { .reset = mv88e6352_g1_reset, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, + .serdes_power = mv88e6341_serdes_power, }; static const struct mv88e6xxx_ops mv88e6176_ops = { @@ -2843,6 +2981,7 @@ static const struct mv88e6xxx_ops mv88e6176_ops = { .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6352_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, @@ -2870,6 +3009,7 @@ static const struct mv88e6xxx_ops mv88e6185_ops = { .set_egress_port = mv88e6095_g1_set_egress_port, .watchdog_ops = &mv88e6097_watchdog_ops, .mgmt_rsvd2cpu = mv88e6185_g2_mgmt_rsvd2cpu, + .set_cascade_port = mv88e6185_g1_set_cascade_port, .ppu_enable = mv88e6185_g1_ppu_enable, .ppu_disable = mv88e6185_g1_ppu_disable, .reset = mv88e6185_g1_reset, @@ -2907,6 +3047,7 @@ static const struct mv88e6xxx_ops mv88e6190_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -2943,6 +3084,7 @@ static const struct mv88e6xxx_ops mv88e6190x_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -2979,6 +3121,7 @@ static const struct mv88e6xxx_ops mv88e6191_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -3016,6 +3159,7 @@ static const struct mv88e6xxx_ops mv88e6240_ops = { .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6352_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, @@ -3054,6 +3198,7 @@ static const struct mv88e6xxx_ops mv88e6290_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -3270,6 +3415,7 @@ static const struct mv88e6xxx_ops mv88e6352_ops = { .mgmt_rsvd2cpu = mv88e6352_g2_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6352_g1_rmu_disable, .vtu_getnext = mv88e6352_g1_vtu_getnext, .vtu_loadpurge = mv88e6352_g1_vtu_loadpurge, .serdes_power = mv88e6352_serdes_power, @@ -3313,6 +3459,7 @@ static const struct mv88e6xxx_ops mv88e6390_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -3353,6 +3500,7 @@ static const struct mv88e6xxx_ops mv88e6390x_ops = { .mgmt_rsvd2cpu = mv88e6390_g1_mgmt_rsvd2cpu, .pot_clear = mv88e6xxx_g2_pot_clear, .reset = mv88e6352_g1_reset, + .rmu_disable = mv88e6390_g1_rmu_disable, .vtu_getnext = mv88e6390_g1_vtu_getnext, .vtu_loadpurge = mv88e6390_g1_vtu_loadpurge, .serdes_power = mv88e6390_serdes_power, @@ -4125,6 +4273,11 @@ static const struct dsa_switch_ops mv88e6xxx_switch_ops = { .get_tag_protocol = mv88e6xxx_get_tag_protocol, .setup = mv88e6xxx_setup, .adjust_link = mv88e6xxx_adjust_link, + .phylink_validate = mv88e6xxx_validate, + .phylink_mac_link_state = mv88e6xxx_link_state, + .phylink_mac_config = mv88e6xxx_mac_config, + .phylink_mac_link_down = mv88e6xxx_mac_link_down, + .phylink_mac_link_up = mv88e6xxx_mac_link_up, .get_strings = mv88e6xxx_get_strings, .get_ethtool_stats = mv88e6xxx_get_ethtool_stats, .get_sset_count = mv88e6xxx_get_sset_count, diff --git a/drivers/net/dsa/mv88e6xxx/chip.h b/drivers/net/dsa/mv88e6xxx/chip.h index 12b7f4649b25..8eb5dfe17f5c 100644 --- a/drivers/net/dsa/mv88e6xxx/chip.h +++ b/drivers/net/dsa/mv88e6xxx/chip.h @@ -21,10 +21,6 @@ #include <linux/timecounter.h> #include <net/dsa.h> -#ifndef UINT64_MAX -#define UINT64_MAX (u64)(~((u64)0)) -#endif - #define SMI_CMD 0x00 #define SMI_CMD_BUSY BIT(15) #define SMI_CMD_CLAUSE_22 BIT(12) @@ -406,6 +402,12 @@ struct mv88e6xxx_ops { uint64_t *data); int (*set_cpu_port)(struct mv88e6xxx_chip *chip, int port); int (*set_egress_port)(struct mv88e6xxx_chip *chip, int port); + +#define MV88E6XXX_CASCADE_PORT_NONE 0xe +#define MV88E6XXX_CASCADE_PORT_MULTIPLE 0xf + + int (*set_cascade_port)(struct mv88e6xxx_chip *chip, int port); + const struct mv88e6xxx_irq_ops *watchdog_ops; int (*mgmt_rsvd2cpu)(struct mv88e6xxx_chip *chip); @@ -431,6 +433,9 @@ struct mv88e6xxx_ops { /* Interface to the AVB/PTP registers */ const struct mv88e6xxx_avb_ops *avb_ops; + + /* Remote Management Unit operations */ + int (*rmu_disable)(struct mv88e6xxx_chip *chip); }; struct mv88e6xxx_irq_ops { diff --git a/drivers/net/dsa/mv88e6xxx/global1.c b/drivers/net/dsa/mv88e6xxx/global1.c index b43bd6476632..244ee1ff9edc 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.c +++ b/drivers/net/dsa/mv88e6xxx/global1.c @@ -350,6 +350,47 @@ int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip) /* Offset 0x1c: Global Control 2 */ +static int mv88e6xxx_g1_ctl2_mask(struct mv88e6xxx_chip *chip, u16 mask, + u16 val) +{ + u16 reg; + int err; + + err = mv88e6xxx_g1_read(chip, MV88E6XXX_G1_CTL2, ®); + if (err) + return err; + + reg &= ~mask; + reg |= val & mask; + + return mv88e6xxx_g1_write(chip, MV88E6XXX_G1_CTL2, reg); +} + +int mv88e6185_g1_set_cascade_port(struct mv88e6xxx_chip *chip, int port) +{ + const u16 mask = MV88E6185_G1_CTL2_CASCADE_PORT_MASK; + + return mv88e6xxx_g1_ctl2_mask(chip, mask, port << __bf_shf(mask)); +} + +int mv88e6085_g1_rmu_disable(struct mv88e6xxx_chip *chip) +{ + return mv88e6xxx_g1_ctl2_mask(chip, MV88E6085_G1_CTL2_P10RM | + MV88E6085_G1_CTL2_RM_ENABLE, 0); +} + +int mv88e6352_g1_rmu_disable(struct mv88e6xxx_chip *chip) +{ + return mv88e6xxx_g1_ctl2_mask(chip, MV88E6352_G1_CTL2_RMU_MODE_MASK, + MV88E6352_G1_CTL2_RMU_MODE_DISABLED); +} + +int mv88e6390_g1_rmu_disable(struct mv88e6xxx_chip *chip) +{ + return mv88e6xxx_g1_ctl2_mask(chip, MV88E6390_G1_CTL2_RMU_MODE_MASK, + MV88E6390_G1_CTL2_RMU_MODE_DISABLED); +} + int mv88e6390_g1_stats_set_histogram(struct mv88e6xxx_chip *chip) { u16 val; @@ -366,6 +407,13 @@ int mv88e6390_g1_stats_set_histogram(struct mv88e6xxx_chip *chip) return err; } +int mv88e6xxx_g1_set_device_number(struct mv88e6xxx_chip *chip, int index) +{ + return mv88e6xxx_g1_ctl2_mask(chip, + MV88E6XXX_G1_CTL2_DEVICE_NUMBER_MASK, + index); +} + /* Offset 0x1d: Statistics Operation 2 */ int mv88e6xxx_g1_stats_wait(struct mv88e6xxx_chip *chip) diff --git a/drivers/net/dsa/mv88e6xxx/global1.h b/drivers/net/dsa/mv88e6xxx/global1.h index 6aee7316fea6..e186a026e1b1 100644 --- a/drivers/net/dsa/mv88e6xxx/global1.h +++ b/drivers/net/dsa/mv88e6xxx/global1.h @@ -201,11 +201,29 @@ /* Offset 0x1C: Global Control 2 */ #define MV88E6XXX_G1_CTL2 0x1c -#define MV88E6XXX_G1_CTL2_NO_CASCADE 0xe000 -#define MV88E6XXX_G1_CTL2_MULTIPLE_CASCADE 0xf000 #define MV88E6XXX_G1_CTL2_HIST_RX 0x0040 #define MV88E6XXX_G1_CTL2_HIST_TX 0x0080 #define MV88E6XXX_G1_CTL2_HIST_RX_TX 0x00c0 +#define MV88E6185_G1_CTL2_CASCADE_PORT_MASK 0xf000 +#define MV88E6185_G1_CTL2_CASCADE_PORT_NONE 0xe000 +#define MV88E6185_G1_CTL2_CASCADE_PORT_MULTI 0xf000 +#define MV88E6352_G1_CTL2_RMU_MODE_MASK 0x3000 +#define MV88E6352_G1_CTL2_RMU_MODE_DISABLED 0x0000 +#define MV88E6352_G1_CTL2_RMU_MODE_PORT_4 0x1000 +#define MV88E6352_G1_CTL2_RMU_MODE_PORT_5 0x2000 +#define MV88E6352_G1_CTL2_RMU_MODE_PORT_6 0x3000 +#define MV88E6085_G1_CTL2_DA_CHECK 0x4000 +#define MV88E6085_G1_CTL2_P10RM 0x2000 +#define MV88E6085_G1_CTL2_RM_ENABLE 0x1000 +#define MV88E6352_G1_CTL2_DA_CHECK 0x0800 +#define MV88E6390_G1_CTL2_RMU_MODE_MASK 0x0700 +#define MV88E6390_G1_CTL2_RMU_MODE_PORT_0 0x0000 +#define MV88E6390_G1_CTL2_RMU_MODE_PORT_1 0x0100 +#define MV88E6390_G1_CTL2_RMU_MODE_PORT_9 0x0200 +#define MV88E6390_G1_CTL2_RMU_MODE_PORT_10 0x0300 +#define MV88E6390_G1_CTL2_RMU_MODE_ALL_DSA 0x0600 +#define MV88E6390_G1_CTL2_RMU_MODE_DISABLED 0x0700 +#define MV88E6XXX_G1_CTL2_DEVICE_NUMBER_MASK 0x001f /* Offset 0x1D: Stats Operation Register */ #define MV88E6XXX_G1_STATS_OP 0x1d @@ -253,6 +271,14 @@ int mv88e6095_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_set_cpu_port(struct mv88e6xxx_chip *chip, int port); int mv88e6390_g1_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); +int mv88e6185_g1_set_cascade_port(struct mv88e6xxx_chip *chip, int port); + +int mv88e6085_g1_rmu_disable(struct mv88e6xxx_chip *chip); +int mv88e6352_g1_rmu_disable(struct mv88e6xxx_chip *chip); +int mv88e6390_g1_rmu_disable(struct mv88e6xxx_chip *chip); + +int mv88e6xxx_g1_set_device_number(struct mv88e6xxx_chip *chip, int index); + int mv88e6xxx_g1_atu_set_learn2all(struct mv88e6xxx_chip *chip, bool learn2all); int mv88e6xxx_g1_atu_set_age_time(struct mv88e6xxx_chip *chip, unsigned int msecs); diff --git a/drivers/net/dsa/mv88e6xxx/global2.c b/drivers/net/dsa/mv88e6xxx/global2.c index 8d22d66d84b7..f9bde011a3e6 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.c +++ b/drivers/net/dsa/mv88e6xxx/global2.c @@ -119,37 +119,17 @@ int mv88e6352_g2_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip) /* Offset 0x06: Device Mapping Table register */ -static int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, - int target, int port) +int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target, + int port) { - u16 val = (target << 8) | (port & 0xf); + u16 val = (target << 8) | (port & 0x1f); + /* Modern chips use 5 bits to define a device mapping port, + * but bit 4 is reserved on older chips, so it is safe to use. + */ return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_DEVICE_MAPPING, val); } -static int mv88e6xxx_g2_set_device_mapping(struct mv88e6xxx_chip *chip) -{ - int target, port; - int err; - - /* Initialize the routing port to the 32 possible target devices */ - for (target = 0; target < 32; ++target) { - port = 0xf; - - if (target < DSA_MAX_SWITCHES) { - port = chip->ds->rtable[target]; - if (port == DSA_RTABLE_NONE) - port = 0xf; - } - - err = mv88e6xxx_g2_device_mapping_write(chip, target, port); - if (err) - break; - } - - return err; -} - /* Offset 0x07: Trunk Mask Table register */ static int mv88e6xxx_g2_trunk_mask_write(struct mv88e6xxx_chip *chip, int num, @@ -174,7 +154,7 @@ static int mv88e6xxx_g2_trunk_mapping_write(struct mv88e6xxx_chip *chip, int id, return mv88e6xxx_g2_update(chip, MV88E6XXX_G2_TRUNK_MAPPING, val); } -static int mv88e6xxx_g2_clear_trunk(struct mv88e6xxx_chip *chip) +int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip) { const u16 port_mask = BIT(mv88e6xxx_num_ports(chip)) - 1; int i, err; @@ -1138,31 +1118,3 @@ void mv88e6xxx_g2_irq_mdio_free(struct mv88e6xxx_chip *chip, for (phy = 0; phy < chip->info->num_internal_phys; phy++) irq_dispose_mapping(bus->irq[phy]); } - -int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip) -{ - u16 reg; - int err; - - /* Ignore removed tag data on doubly tagged packets, disable - * flow control messages, force flow control priority to the - * highest, and send all special multicast frames to the CPU - * port at the highest priority. - */ - reg = MV88E6XXX_G2_SWITCH_MGMT_FORCE_FLOW_CTL_PRI | (0x7 << 4); - err = mv88e6xxx_g2_write(chip, MV88E6XXX_G2_SWITCH_MGMT, reg); - if (err) - return err; - - /* Program the DSA routing table. */ - err = mv88e6xxx_g2_set_device_mapping(chip); - if (err) - return err; - - /* Clear all trunk masks and mapping. */ - err = mv88e6xxx_g2_clear_trunk(chip); - if (err) - return err; - - return 0; -} diff --git a/drivers/net/dsa/mv88e6xxx/global2.h b/drivers/net/dsa/mv88e6xxx/global2.h index 520ec70d32e8..37e8ce2c72a0 100644 --- a/drivers/net/dsa/mv88e6xxx/global2.h +++ b/drivers/net/dsa/mv88e6xxx/global2.h @@ -60,7 +60,8 @@ #define MV88E6XXX_G2_DEVICE_MAPPING 0x06 #define MV88E6XXX_G2_DEVICE_MAPPING_UPDATE 0x8000 #define MV88E6XXX_G2_DEVICE_MAPPING_DEV_MASK 0x1f00 -#define MV88E6XXX_G2_DEVICE_MAPPING_PORT_MASK 0x000f +#define MV88E6352_G2_DEVICE_MAPPING_PORT_MASK 0x000f +#define MV88E6390_G2_DEVICE_MAPPING_PORT_MASK 0x001f /* Offset 0x07: Trunk Mask Table Register */ #define MV88E6XXX_G2_TRUNK_MASK 0x07 @@ -313,7 +314,6 @@ int mv88e6xxx_g2_pvt_write(struct mv88e6xxx_chip *chip, int src_dev, int src_port, u16 data); int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip); -int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip); int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip); void mv88e6xxx_g2_irq_free(struct mv88e6xxx_chip *chip); @@ -327,6 +327,11 @@ int mv88e6352_g2_mgmt_rsvd2cpu(struct mv88e6xxx_chip *chip); int mv88e6xxx_g2_pot_clear(struct mv88e6xxx_chip *chip); +int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip); + +int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, int target, + int port); + extern const struct mv88e6xxx_irq_ops mv88e6097_watchdog_ops; extern const struct mv88e6xxx_irq_ops mv88e6390_watchdog_ops; @@ -441,11 +446,6 @@ static inline int mv88e6xxx_g2_misc_4_bit_port(struct mv88e6xxx_chip *chip) return -EOPNOTSUPP; } -static inline int mv88e6xxx_g2_setup(struct mv88e6xxx_chip *chip) -{ - return -EOPNOTSUPP; -} - static inline int mv88e6xxx_g2_irq_setup(struct mv88e6xxx_chip *chip) { return -EOPNOTSUPP; @@ -495,6 +495,17 @@ static inline int mv88e6xxx_g2_scratch_gpio_set_smi(struct mv88e6xxx_chip *chip, return -EOPNOTSUPP; } +static inline int mv88e6xxx_g2_trunk_clear(struct mv88e6xxx_chip *chip) +{ + return -EOPNOTSUPP; +} + +static inline int mv88e6xxx_g2_device_mapping_write(struct mv88e6xxx_chip *chip, + int target, int port) +{ + return -EOPNOTSUPP; +} + #endif /* CONFIG_NET_DSA_MV88E6XXX_GLOBAL2 */ #endif /* _MV88E6XXX_GLOBAL2_H */ diff --git a/drivers/net/dsa/mv88e6xxx/port.c b/drivers/net/dsa/mv88e6xxx/port.c index 6315774d72b3..429d0ebcd5b1 100644 --- a/drivers/net/dsa/mv88e6xxx/port.c +++ b/drivers/net/dsa/mv88e6xxx/port.c @@ -15,6 +15,7 @@ #include <linux/bitfield.h> #include <linux/if_bridge.h> #include <linux/phy.h> +#include <linux/phylink.h> #include "chip.h" #include "port.h" @@ -378,6 +379,44 @@ int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode) return 0; } +int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port, + struct phylink_link_state *state) +{ + int err; + u16 reg; + + err = mv88e6xxx_port_read(chip, port, MV88E6XXX_PORT_STS, ®); + if (err) + return err; + + switch (reg & MV88E6XXX_PORT_STS_SPEED_MASK) { + case MV88E6XXX_PORT_STS_SPEED_10: + state->speed = SPEED_10; + break; + case MV88E6XXX_PORT_STS_SPEED_100: + state->speed = SPEED_100; + break; + case MV88E6XXX_PORT_STS_SPEED_1000: + state->speed = SPEED_1000; + break; + case MV88E6XXX_PORT_STS_SPEED_10000: + if ((reg &MV88E6XXX_PORT_STS_CMODE_MASK) == + MV88E6XXX_PORT_STS_CMODE_2500BASEX) + state->speed = SPEED_2500; + else + state->speed = SPEED_10000; + break; + } + + state->duplex = reg & MV88E6XXX_PORT_STS_DUPLEX ? + DUPLEX_FULL : DUPLEX_HALF; + state->link = !!(reg & MV88E6XXX_PORT_STS_LINK); + state->an_enabled = 1; + state->an_complete = state->link; + + return 0; +} + /* Offset 0x02: Jamming Control * * Do not limit the period of time that this port can be paused for by diff --git a/drivers/net/dsa/mv88e6xxx/port.h b/drivers/net/dsa/mv88e6xxx/port.h index b16d5f0e6e9c..5e1db1b221ca 100644 --- a/drivers/net/dsa/mv88e6xxx/port.h +++ b/drivers/net/dsa/mv88e6xxx/port.h @@ -29,6 +29,7 @@ #define MV88E6XXX_PORT_STS_SPEED_10 0x0000 #define MV88E6XXX_PORT_STS_SPEED_100 0x0100 #define MV88E6XXX_PORT_STS_SPEED_1000 0x0200 +#define MV88E6XXX_PORT_STS_SPEED_10000 0x0300 #define MV88E6352_PORT_STS_EEE 0x0040 #define MV88E6165_PORT_STS_AM_DIS 0x0040 #define MV88E6185_PORT_STS_MGMII 0x0040 @@ -295,6 +296,8 @@ int mv88e6390_port_pause_limit(struct mv88e6xxx_chip *chip, int port, u8 in, int mv88e6390x_port_set_cmode(struct mv88e6xxx_chip *chip, int port, phy_interface_t mode); int mv88e6xxx_port_get_cmode(struct mv88e6xxx_chip *chip, int port, u8 *cmode); +int mv88e6xxx_port_link_state(struct mv88e6xxx_chip *chip, int port, + struct phylink_link_state *state); int mv88e6xxx_port_set_map_da(struct mv88e6xxx_chip *chip, int port); int mv88e6095_port_set_upstream_port(struct mv88e6xxx_chip *chip, int port, int upstream_port); diff --git a/drivers/net/dsa/mv88e6xxx/serdes.c b/drivers/net/dsa/mv88e6xxx/serdes.c index fb058fd35c0d..880b2cf0a530 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.c +++ b/drivers/net/dsa/mv88e6xxx/serdes.c @@ -326,3 +326,23 @@ int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on) return 0; } + +int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on) +{ + int err; + u8 cmode; + + if (port != 5) + return 0; + + err = mv88e6xxx_port_get_cmode(chip, port, &cmode); + if (err) + return err; + + if (cmode == MV88E6XXX_PORT_STS_CMODE_1000BASE_X || + cmode == MV88E6XXX_PORT_STS_CMODE_SGMII || + cmode == MV88E6XXX_PORT_STS_CMODE_2500BASEX) + return mv88e6390_serdes_sgmii(chip, MV88E6341_ADDR_SERDES, on); + + return 0; +} diff --git a/drivers/net/dsa/mv88e6xxx/serdes.h b/drivers/net/dsa/mv88e6xxx/serdes.h index 1897c01c6e19..b6e5fbd46b5e 100644 --- a/drivers/net/dsa/mv88e6xxx/serdes.h +++ b/drivers/net/dsa/mv88e6xxx/serdes.h @@ -19,6 +19,8 @@ #define MV88E6352_ADDR_SERDES 0x0f #define MV88E6352_SERDES_PAGE_FIBER 0x01 +#define MV88E6341_ADDR_SERDES 0x15 + #define MV88E6390_PORT9_LANE0 0x09 #define MV88E6390_PORT9_LANE1 0x12 #define MV88E6390_PORT9_LANE2 0x13 @@ -42,6 +44,7 @@ #define MV88E6390_SGMII_CONTROL_LOOPBACK BIT(14) #define MV88E6390_SGMII_CONTROL_PDOWN BIT(11) +int mv88e6341_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on); int mv88e6352_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on); int mv88e6390_serdes_power(struct mv88e6xxx_chip *chip, int port, bool on); int mv88e6352_serdes_get_sset_count(struct mv88e6xxx_chip *chip, int port); diff --git a/drivers/net/dsa/qca8k.c b/drivers/net/dsa/qca8k.c index 600d5ad1fbde..757b6d90ea36 100644 --- a/drivers/net/dsa/qca8k.c +++ b/drivers/net/dsa/qca8k.c @@ -600,10 +600,13 @@ qca8k_phy_write(struct dsa_switch *ds, int phy, int regnum, u16 val) } static void -qca8k_get_strings(struct dsa_switch *ds, int port, uint8_t *data) +qca8k_get_strings(struct dsa_switch *ds, int port, u32 stringset, uint8_t *data) { int i; + if (stringset != ETH_SS_STATS) + return; + for (i = 0; i < ARRAY_SIZE(ar8327_mib); i++) strncpy(data + i * ETH_GSTRING_LEN, ar8327_mib[i].name, ETH_GSTRING_LEN); @@ -631,8 +634,11 @@ qca8k_get_ethtool_stats(struct dsa_switch *ds, int port, } static int -qca8k_get_sset_count(struct dsa_switch *ds, int port) +qca8k_get_sset_count(struct dsa_switch *ds, int port, int sset) { + if (sset != ETH_SS_STATS) + return 0; + return ARRAY_SIZE(ar8327_mib); } diff --git a/drivers/net/ethernet/3com/3c59x.c b/drivers/net/ethernet/3com/3c59x.c index 36c8950dbd2d..cabbe227bb98 100644 --- a/drivers/net/ethernet/3com/3c59x.c +++ b/drivers/net/ethernet/3com/3c59x.c @@ -765,8 +765,9 @@ static netdev_tx_t boomerang_start_xmit(struct sk_buff *skb, struct net_device *dev); static int vortex_rx(struct net_device *dev); static int boomerang_rx(struct net_device *dev); -static irqreturn_t vortex_interrupt(int irq, void *dev_id); -static irqreturn_t boomerang_interrupt(int irq, void *dev_id); +static irqreturn_t vortex_boomerang_interrupt(int irq, void *dev_id); +static irqreturn_t _vortex_interrupt(int irq, struct net_device *dev); +static irqreturn_t _boomerang_interrupt(int irq, struct net_device *dev); static int vortex_close(struct net_device *dev); static void dump_tx_ring(struct net_device *dev); static void update_stats(void __iomem *ioaddr, struct net_device *dev); @@ -838,11 +839,7 @@ MODULE_PARM_DESC(use_mmio, "3c59x: use memory-mapped PCI I/O resource (0-1)"); #ifdef CONFIG_NET_POLL_CONTROLLER static void poll_vortex(struct net_device *dev) { - struct vortex_private *vp = netdev_priv(dev); - unsigned long flags; - local_irq_save(flags); - (vp->full_bus_master_rx ? boomerang_interrupt:vortex_interrupt)(dev->irq,dev); - local_irq_restore(flags); + vortex_boomerang_interrupt(dev->irq, dev); } #endif @@ -1729,8 +1726,7 @@ vortex_open(struct net_device *dev) dma_addr_t dma; /* Use the now-standard shared IRQ implementation. */ - if ((retval = request_irq(dev->irq, vp->full_bus_master_rx ? - boomerang_interrupt : vortex_interrupt, IRQF_SHARED, dev->name, dev))) { + if ((retval = request_irq(dev->irq, vortex_boomerang_interrupt, IRQF_SHARED, dev->name, dev))) { pr_err("%s: Could not reserve IRQ %d\n", dev->name, dev->irq); goto err; } @@ -1905,18 +1901,7 @@ static void vortex_tx_timeout(struct net_device *dev) pr_err("%s: Interrupt posted but not delivered --" " IRQ blocked by another device?\n", dev->name); /* Bad idea here.. but we might as well handle a few events. */ - { - /* - * Block interrupts because vortex_interrupt does a bare spin_lock() - */ - unsigned long flags; - local_irq_save(flags); - if (vp->full_bus_master_tx) - boomerang_interrupt(dev->irq, dev); - else - vortex_interrupt(dev->irq, dev); - local_irq_restore(flags); - } + vortex_boomerang_interrupt(dev->irq, dev); } if (vortex_debug > 0) @@ -2267,9 +2252,8 @@ out_dma_err: */ static irqreturn_t -vortex_interrupt(int irq, void *dev_id) +_vortex_interrupt(int irq, struct net_device *dev) { - struct net_device *dev = dev_id; struct vortex_private *vp = netdev_priv(dev); void __iomem *ioaddr; int status; @@ -2278,7 +2262,6 @@ vortex_interrupt(int irq, void *dev_id) unsigned int bytes_compl = 0, pkts_compl = 0; ioaddr = vp->ioaddr; - spin_lock(&vp->lock); status = ioread16(ioaddr + EL3_STATUS); @@ -2376,7 +2359,6 @@ vortex_interrupt(int irq, void *dev_id) pr_debug("%s: exiting interrupt, status %4.4x.\n", dev->name, status); handler_exit: - spin_unlock(&vp->lock); return IRQ_RETVAL(handled); } @@ -2386,9 +2368,8 @@ handler_exit: */ static irqreturn_t -boomerang_interrupt(int irq, void *dev_id) +_boomerang_interrupt(int irq, struct net_device *dev) { - struct net_device *dev = dev_id; struct vortex_private *vp = netdev_priv(dev); void __iomem *ioaddr; int status; @@ -2398,12 +2379,6 @@ boomerang_interrupt(int irq, void *dev_id) ioaddr = vp->ioaddr; - - /* - * It seems dopey to put the spinlock this early, but we could race against vortex_tx_timeout - * and boomerang_start_xmit - */ - spin_lock(&vp->lock); vp->handling_irq = 1; status = ioread16(ioaddr + EL3_STATUS); @@ -2522,10 +2497,29 @@ boomerang_interrupt(int irq, void *dev_id) dev->name, status); handler_exit: vp->handling_irq = 0; - spin_unlock(&vp->lock); return IRQ_RETVAL(handled); } +static irqreturn_t +vortex_boomerang_interrupt(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + struct vortex_private *vp = netdev_priv(dev); + unsigned long flags; + irqreturn_t ret; + + spin_lock_irqsave(&vp->lock, flags); + + if (vp->full_bus_master_rx) + ret = _boomerang_interrupt(dev->irq, dev); + else + ret = _vortex_interrupt(dev->irq, dev); + + spin_unlock_irqrestore(&vp->lock, flags); + + return ret; +} + static int vortex_rx(struct net_device *dev) { struct vortex_private *vp = netdev_priv(dev); diff --git a/drivers/net/ethernet/8390/Kconfig b/drivers/net/ethernet/8390/Kconfig index 9fee7c83ef9f..f2f0264c58ba 100644 --- a/drivers/net/ethernet/8390/Kconfig +++ b/drivers/net/ethernet/8390/Kconfig @@ -29,8 +29,8 @@ config PCMCIA_AXNET called axnet_cs. If unsure, say N. config AX88796 - tristate "ASIX AX88796 NE2000 clone support" - depends on (ARM || MIPS || SUPERH) + tristate "ASIX AX88796 NE2000 clone support" if !ZORRO + depends on (ARM || MIPS || SUPERH || ZORRO || COMPILE_TEST) select CRC32 select PHYLIB select MDIO_BITBANG @@ -45,6 +45,19 @@ config AX88796_93CX6 ---help--- Select this if your platform comes with an external 93CX6 eeprom. +config XSURF100 + tristate "Amiga XSurf 100 AX88796/NE2000 clone support" + depends on ZORRO + select AX88796 + select ASIX_PHY + help + This driver is for the Individual Computers X-Surf 100 Ethernet + card (based on the Asix AX88796 chip). If you have such a card, + say Y. Otherwise, say N. + + To compile this driver as a module, choose M here: the module + will be called xsurf100. + config HYDRA tristate "Hydra support" depends on ZORRO diff --git a/drivers/net/ethernet/8390/Makefile b/drivers/net/ethernet/8390/Makefile index 1d650e66cc6e..85c83c566ec6 100644 --- a/drivers/net/ethernet/8390/Makefile +++ b/drivers/net/ethernet/8390/Makefile @@ -16,4 +16,5 @@ obj-$(CONFIG_PCMCIA_PCNET) += pcnet_cs.o 8390.o obj-$(CONFIG_STNIC) += stnic.o 8390.o obj-$(CONFIG_ULTRA) += smc-ultra.o 8390.o obj-$(CONFIG_WD80x3) += wd.o 8390.o +obj-$(CONFIG_XSURF100) += xsurf100.o obj-$(CONFIG_ZORRO8390) += zorro8390.o diff --git a/drivers/net/ethernet/8390/ax88796.c b/drivers/net/ethernet/8390/ax88796.c index da61cf3cb3a9..2a0ddec1dd56 100644 --- a/drivers/net/ethernet/8390/ax88796.c +++ b/drivers/net/ethernet/8390/ax88796.c @@ -163,6 +163,21 @@ static void ax_reset_8390(struct net_device *dev) ei_outb(ENISR_RESET, addr + EN0_ISR); /* Ack intr. */ } +/* Wrapper for __ei_interrupt for platforms that have a platform-specific + * way to find out whether the interrupt request might be caused by + * the ax88796 chip. + */ +static irqreturn_t ax_ei_interrupt_filtered(int irq, void *dev_id) +{ + struct net_device *dev = dev_id; + struct ax_device *ax = to_ax_dev(dev); + struct platform_device *pdev = to_platform_device(dev->dev.parent); + + if (!ax->plat->check_irq(pdev)) + return IRQ_NONE; + + return ax_ei_interrupt(irq, dev_id); +} static void ax_get_8390_hdr(struct net_device *dev, struct e8390_pkt_hdr *hdr, int ring_page) @@ -387,6 +402,90 @@ static void ax_phy_switch(struct net_device *dev, int on) ei_outb(reg_gpoc, ei_local->mem + EI_SHIFT(0x17)); } +static void ax_bb_mdc(struct mdiobb_ctrl *ctrl, int level) +{ + struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); + + if (level) + ax->reg_memr |= AX_MEMR_MDC; + else + ax->reg_memr &= ~AX_MEMR_MDC; + + ei_outb(ax->reg_memr, ax->addr_memr); +} + +static void ax_bb_dir(struct mdiobb_ctrl *ctrl, int output) +{ + struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); + + if (output) + ax->reg_memr &= ~AX_MEMR_MDIR; + else + ax->reg_memr |= AX_MEMR_MDIR; + + ei_outb(ax->reg_memr, ax->addr_memr); +} + +static void ax_bb_set_data(struct mdiobb_ctrl *ctrl, int value) +{ + struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); + + if (value) + ax->reg_memr |= AX_MEMR_MDO; + else + ax->reg_memr &= ~AX_MEMR_MDO; + + ei_outb(ax->reg_memr, ax->addr_memr); +} + +static int ax_bb_get_data(struct mdiobb_ctrl *ctrl) +{ + struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); + int reg_memr = ei_inb(ax->addr_memr); + + return reg_memr & AX_MEMR_MDI ? 1 : 0; +} + +static const struct mdiobb_ops bb_ops = { + .owner = THIS_MODULE, + .set_mdc = ax_bb_mdc, + .set_mdio_dir = ax_bb_dir, + .set_mdio_data = ax_bb_set_data, + .get_mdio_data = ax_bb_get_data, +}; + +static int ax_mii_init(struct net_device *dev) +{ + struct platform_device *pdev = to_platform_device(dev->dev.parent); + struct ei_device *ei_local = netdev_priv(dev); + struct ax_device *ax = to_ax_dev(dev); + int err; + + ax->bb_ctrl.ops = &bb_ops; + ax->addr_memr = ei_local->mem + AX_MEMR; + ax->mii_bus = alloc_mdio_bitbang(&ax->bb_ctrl); + if (!ax->mii_bus) { + err = -ENOMEM; + goto out; + } + + ax->mii_bus->name = "ax88796_mii_bus"; + ax->mii_bus->parent = dev->dev.parent; + snprintf(ax->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", + pdev->name, pdev->id); + + err = mdiobus_register(ax->mii_bus); + if (err) + goto out_free_mdio_bitbang; + + return 0; + + out_free_mdio_bitbang: + free_mdio_bitbang(ax->mii_bus); + out: + return err; +} + static int ax_open(struct net_device *dev) { struct ax_device *ax = to_ax_dev(dev); @@ -394,8 +493,16 @@ static int ax_open(struct net_device *dev) netdev_dbg(dev, "open\n"); - ret = request_irq(dev->irq, ax_ei_interrupt, ax->irqflags, - dev->name, dev); + ret = ax_mii_init(dev); + if (ret) + goto failed_mii; + + if (ax->plat->check_irq) + ret = request_irq(dev->irq, ax_ei_interrupt_filtered, + ax->irqflags, dev->name, dev); + else + ret = request_irq(dev->irq, ax_ei_interrupt, ax->irqflags, + dev->name, dev); if (ret) goto failed_request_irq; @@ -421,6 +528,10 @@ static int ax_open(struct net_device *dev) ax_phy_switch(dev, 0); free_irq(dev->irq, dev); failed_request_irq: + /* unregister mdiobus */ + mdiobus_unregister(ax->mii_bus); + free_mdio_bitbang(ax->mii_bus); + failed_mii: return ret; } @@ -440,6 +551,9 @@ static int ax_close(struct net_device *dev) phy_disconnect(dev->phydev); free_irq(dev->irq, dev); + + mdiobus_unregister(ax->mii_bus); + free_mdio_bitbang(ax->mii_bus); return 0; } @@ -539,92 +653,8 @@ static const struct net_device_ops ax_netdev_ops = { #endif }; -static void ax_bb_mdc(struct mdiobb_ctrl *ctrl, int level) -{ - struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); - - if (level) - ax->reg_memr |= AX_MEMR_MDC; - else - ax->reg_memr &= ~AX_MEMR_MDC; - - ei_outb(ax->reg_memr, ax->addr_memr); -} - -static void ax_bb_dir(struct mdiobb_ctrl *ctrl, int output) -{ - struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); - - if (output) - ax->reg_memr &= ~AX_MEMR_MDIR; - else - ax->reg_memr |= AX_MEMR_MDIR; - - ei_outb(ax->reg_memr, ax->addr_memr); -} - -static void ax_bb_set_data(struct mdiobb_ctrl *ctrl, int value) -{ - struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); - - if (value) - ax->reg_memr |= AX_MEMR_MDO; - else - ax->reg_memr &= ~AX_MEMR_MDO; - - ei_outb(ax->reg_memr, ax->addr_memr); -} - -static int ax_bb_get_data(struct mdiobb_ctrl *ctrl) -{ - struct ax_device *ax = container_of(ctrl, struct ax_device, bb_ctrl); - int reg_memr = ei_inb(ax->addr_memr); - - return reg_memr & AX_MEMR_MDI ? 1 : 0; -} - -static const struct mdiobb_ops bb_ops = { - .owner = THIS_MODULE, - .set_mdc = ax_bb_mdc, - .set_mdio_dir = ax_bb_dir, - .set_mdio_data = ax_bb_set_data, - .get_mdio_data = ax_bb_get_data, -}; - /* setup code */ -static int ax_mii_init(struct net_device *dev) -{ - struct platform_device *pdev = to_platform_device(dev->dev.parent); - struct ei_device *ei_local = netdev_priv(dev); - struct ax_device *ax = to_ax_dev(dev); - int err; - - ax->bb_ctrl.ops = &bb_ops; - ax->addr_memr = ei_local->mem + AX_MEMR; - ax->mii_bus = alloc_mdio_bitbang(&ax->bb_ctrl); - if (!ax->mii_bus) { - err = -ENOMEM; - goto out; - } - - ax->mii_bus->name = "ax88796_mii_bus"; - ax->mii_bus->parent = dev->dev.parent; - snprintf(ax->mii_bus->id, MII_BUS_ID_SIZE, "%s-%x", - pdev->name, pdev->id); - - err = mdiobus_register(ax->mii_bus); - if (err) - goto out_free_mdio_bitbang; - - return 0; - - out_free_mdio_bitbang: - free_mdio_bitbang(ax->mii_bus); - out: - return err; -} - static void ax_initial_setup(struct net_device *dev, struct ei_device *ei_local) { void __iomem *ioaddr = ei_local->mem; @@ -669,10 +699,16 @@ static int ax_init_dev(struct net_device *dev) if (ax->plat->flags & AXFLG_HAS_EEPROM) { unsigned char SA_prom[32]; + ei_outb(6, ioaddr + EN0_RCNTLO); + ei_outb(0, ioaddr + EN0_RCNTHI); + ei_outb(0, ioaddr + EN0_RSARLO); + ei_outb(0, ioaddr + EN0_RSARHI); + ei_outb(E8390_RREAD + E8390_START, ioaddr + NE_CMD); for (i = 0; i < sizeof(SA_prom); i += 2) { SA_prom[i] = ei_inb(ioaddr + NE_DATAPORT); SA_prom[i + 1] = ei_inb(ioaddr + NE_DATAPORT); } + ei_outb(ENISR_RDC, ioaddr + EN0_ISR); /* Ack intr. */ if (ax->plat->wordlength == 2) for (i = 0; i < 16; i++) @@ -741,18 +777,20 @@ static int ax_init_dev(struct net_device *dev) #endif ei_local->reset_8390 = &ax_reset_8390; - ei_local->block_input = &ax_block_input; - ei_local->block_output = &ax_block_output; + if (ax->plat->block_input) + ei_local->block_input = ax->plat->block_input; + else + ei_local->block_input = &ax_block_input; + if (ax->plat->block_output) + ei_local->block_output = ax->plat->block_output; + else + ei_local->block_output = &ax_block_output; ei_local->get_8390_hdr = &ax_get_8390_hdr; ei_local->priv = 0; dev->netdev_ops = &ax_netdev_ops; dev->ethtool_ops = &ax_ethtool_ops; - ret = ax_mii_init(dev); - if (ret) - goto err_out; - ax_NS8390_init(dev, 0); ret = register_netdev(dev); @@ -777,7 +815,6 @@ static int ax_remove(struct platform_device *pdev) struct resource *mem; unregister_netdev(dev); - free_irq(dev->irq, dev); iounmap(ei_local->mem); mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); @@ -789,6 +826,7 @@ static int ax_remove(struct platform_device *pdev) release_mem_region(mem->start, resource_size(mem)); } + platform_set_drvdata(pdev, NULL); free_netdev(dev); return 0; @@ -835,6 +873,9 @@ static int ax_probe(struct platform_device *pdev) dev->irq = irq->start; ax->irqflags = irq->flags & IRQF_TRIGGER_MASK; + if (irq->flags & IORESOURCE_IRQ_SHAREABLE) + ax->irqflags |= IRQF_SHARED; + mem = platform_get_resource(pdev, IORESOURCE_MEM, 0); if (!mem) { dev_err(&pdev->dev, "no MEM specified\n"); @@ -919,6 +960,7 @@ static int ax_probe(struct platform_device *pdev) release_mem_region(mem->start, mem_size); exit_mem: + platform_set_drvdata(pdev, NULL); free_netdev(dev); return ret; diff --git a/drivers/net/ethernet/8390/xsurf100.c b/drivers/net/ethernet/8390/xsurf100.c new file mode 100644 index 000000000000..e2c963821ffe --- /dev/null +++ b/drivers/net/ethernet/8390/xsurf100.c @@ -0,0 +1,382 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <linux/module.h> +#include <linux/netdevice.h> +#include <linux/platform_device.h> +#include <linux/zorro.h> +#include <net/ax88796.h> +#include <asm/amigaints.h> + +#define ZORRO_PROD_INDIVIDUAL_COMPUTERS_X_SURF100 \ + ZORRO_ID(INDIVIDUAL_COMPUTERS, 0x64, 0) + +#define XS100_IRQSTATUS_BASE 0x40 +#define XS100_8390_BASE 0x800 + +/* Longword-access area. Translated to 2 16-bit access cycles by the + * X-Surf 100 FPGA + */ +#define XS100_8390_DATA32_BASE 0x8000 +#define XS100_8390_DATA32_SIZE 0x2000 +/* Sub-Areas for fast data register access; addresses relative to area begin */ +#define XS100_8390_DATA_READ32_BASE 0x0880 +#define XS100_8390_DATA_WRITE32_BASE 0x0C80 +#define XS100_8390_DATA_AREA_SIZE 0x80 + +#define __NS8390_init ax_NS8390_init + +/* force unsigned long back to 'void __iomem *' */ +#define ax_convert_addr(_a) ((void __force __iomem *)(_a)) + +#define ei_inb(_a) z_readb(ax_convert_addr(_a)) +#define ei_outb(_v, _a) z_writeb(_v, ax_convert_addr(_a)) + +#define ei_inw(_a) z_readw(ax_convert_addr(_a)) +#define ei_outw(_v, _a) z_writew(_v, ax_convert_addr(_a)) + +#define ei_inb_p(_a) ei_inb(_a) +#define ei_outb_p(_v, _a) ei_outb(_v, _a) + +/* define EI_SHIFT() to take into account our register offsets */ +#define EI_SHIFT(x) (ei_local->reg_offset[(x)]) + +/* Ensure we have our RCR base value */ +#define AX88796_PLATFORM + +static unsigned char version[] = + "ax88796.c: Copyright 2005,2007 Simtec Electronics\n"; + +#include "lib8390.c" + +/* from ne.c */ +#define NE_CMD EI_SHIFT(0x00) +#define NE_RESET EI_SHIFT(0x1f) +#define NE_DATAPORT EI_SHIFT(0x10) + +struct xsurf100_ax_plat_data { + struct ax_plat_data ax; + void __iomem *base_regs; + void __iomem *data_area; +}; + +static int is_xsurf100_network_irq(struct platform_device *pdev) +{ + struct xsurf100_ax_plat_data *xs100 = dev_get_platdata(&pdev->dev); + + return (readw(xs100->base_regs + XS100_IRQSTATUS_BASE) & 0xaaaa) != 0; +} + +/* These functions guarantee that the iomem is accessed with 32 bit + * cycles only. z_memcpy_fromio / z_memcpy_toio don't + */ +static void z_memcpy_fromio32(void *dst, const void __iomem *src, size_t bytes) +{ + while (bytes > 32) { + asm __volatile__ + ("movem.l (%0)+,%%d0-%%d7\n" + "movem.l %%d0-%%d7,(%1)\n" + "adda.l #32,%1" : "=a"(src), "=a"(dst) + : "0"(src), "1"(dst) : "d0", "d1", "d2", "d3", "d4", + "d5", "d6", "d7", "memory"); + bytes -= 32; + } + while (bytes) { + *(uint32_t *)dst = z_readl(src); + src += 4; + dst += 4; + bytes -= 4; + } +} + +static void z_memcpy_toio32(void __iomem *dst, const void *src, size_t bytes) +{ + while (bytes) { + z_writel(*(const uint32_t *)src, dst); + src += 4; + dst += 4; + bytes -= 4; + } +} + +static void xs100_write(struct net_device *dev, const void *src, + unsigned int count) +{ + struct ei_device *ei_local = netdev_priv(dev); + struct platform_device *pdev = to_platform_device(dev->dev.parent); + struct xsurf100_ax_plat_data *xs100 = dev_get_platdata(&pdev->dev); + + /* copy whole blocks */ + while (count > XS100_8390_DATA_AREA_SIZE) { + z_memcpy_toio32(xs100->data_area + + XS100_8390_DATA_WRITE32_BASE, src, + XS100_8390_DATA_AREA_SIZE); + src += XS100_8390_DATA_AREA_SIZE; + count -= XS100_8390_DATA_AREA_SIZE; + } + /* copy whole dwords */ + z_memcpy_toio32(xs100->data_area + XS100_8390_DATA_WRITE32_BASE, + src, count & ~3); + src += count & ~3; + if (count & 2) { + ei_outw(*(uint16_t *)src, ei_local->mem + NE_DATAPORT); + src += 2; + } + if (count & 1) + ei_outb(*(uint8_t *)src, ei_local->mem + NE_DATAPORT); +} + +static void xs100_read(struct net_device *dev, void *dst, unsigned int count) +{ + struct ei_device *ei_local = netdev_priv(dev); + struct platform_device *pdev = to_platform_device(dev->dev.parent); + struct xsurf100_ax_plat_data *xs100 = dev_get_platdata(&pdev->dev); + + /* copy whole blocks */ + while (count > XS100_8390_DATA_AREA_SIZE) { + z_memcpy_fromio32(dst, xs100->data_area + + XS100_8390_DATA_READ32_BASE, + XS100_8390_DATA_AREA_SIZE); + dst += XS100_8390_DATA_AREA_SIZE; + count -= XS100_8390_DATA_AREA_SIZE; + } + /* copy whole dwords */ + z_memcpy_fromio32(dst, xs100->data_area + XS100_8390_DATA_READ32_BASE, + count & ~3); + dst += count & ~3; + if (count & 2) { + *(uint16_t *)dst = ei_inw(ei_local->mem + NE_DATAPORT); + dst += 2; + } + if (count & 1) + *(uint8_t *)dst = ei_inb(ei_local->mem + NE_DATAPORT); +} + +/* Block input and output, similar to the Crynwr packet driver. If + * you are porting to a new ethercard, look at the packet driver + * source for hints. The NEx000 doesn't share the on-board packet + * memory -- you have to put the packet out through the "remote DMA" + * dataport using ei_outb. + */ +static void xs100_block_input(struct net_device *dev, int count, + struct sk_buff *skb, int ring_offset) +{ + struct ei_device *ei_local = netdev_priv(dev); + void __iomem *nic_base = ei_local->mem; + char *buf = skb->data; + + if (ei_local->dmaing) { + netdev_err(dev, + "DMAing conflict in %s [DMAstat:%d][irqlock:%d]\n", + __func__, + ei_local->dmaing, ei_local->irqlock); + return; + } + + ei_local->dmaing |= 0x01; + + ei_outb(E8390_NODMA + E8390_PAGE0 + E8390_START, nic_base + NE_CMD); + ei_outb(count & 0xff, nic_base + EN0_RCNTLO); + ei_outb(count >> 8, nic_base + EN0_RCNTHI); + ei_outb(ring_offset & 0xff, nic_base + EN0_RSARLO); + ei_outb(ring_offset >> 8, nic_base + EN0_RSARHI); + ei_outb(E8390_RREAD + E8390_START, nic_base + NE_CMD); + + xs100_read(dev, buf, count); + + ei_local->dmaing &= ~1; +} + +static void xs100_block_output(struct net_device *dev, int count, + const unsigned char *buf, const int start_page) +{ + struct ei_device *ei_local = netdev_priv(dev); + void __iomem *nic_base = ei_local->mem; + unsigned long dma_start; + + /* Round the count up for word writes. Do we need to do this? + * What effect will an odd byte count have on the 8390? I + * should check someday. + */ + if (ei_local->word16 && (count & 0x01)) + count++; + + /* This *shouldn't* happen. If it does, it's the last thing + * you'll see + */ + if (ei_local->dmaing) { + netdev_err(dev, + "DMAing conflict in %s [DMAstat:%d][irqlock:%d]\n", + __func__, + ei_local->dmaing, ei_local->irqlock); + return; + } + + ei_local->dmaing |= 0x01; + /* We should already be in page 0, but to be safe... */ + ei_outb(E8390_PAGE0 + E8390_START + E8390_NODMA, nic_base + NE_CMD); + + ei_outb(ENISR_RDC, nic_base + EN0_ISR); + + /* Now the normal output. */ + ei_outb(count & 0xff, nic_base + EN0_RCNTLO); + ei_outb(count >> 8, nic_base + EN0_RCNTHI); + ei_outb(0x00, nic_base + EN0_RSARLO); + ei_outb(start_page, nic_base + EN0_RSARHI); + + ei_outb(E8390_RWRITE + E8390_START, nic_base + NE_CMD); + + xs100_write(dev, buf, count); + + dma_start = jiffies; + + while ((ei_inb(nic_base + EN0_ISR) & ENISR_RDC) == 0) { + if (jiffies - dma_start > 2 * HZ / 100) { /* 20ms */ + netdev_warn(dev, "timeout waiting for Tx RDC.\n"); + ei_local->reset_8390(dev); + ax_NS8390_init(dev, 1); + break; + } + } + + ei_outb(ENISR_RDC, nic_base + EN0_ISR); /* Ack intr. */ + ei_local->dmaing &= ~0x01; +} + +static int xsurf100_probe(struct zorro_dev *zdev, + const struct zorro_device_id *ent) +{ + struct platform_device *pdev; + struct xsurf100_ax_plat_data ax88796_data; + struct resource res[2] = { + DEFINE_RES_NAMED(IRQ_AMIGA_PORTS, 1, NULL, + IORESOURCE_IRQ | IORESOURCE_IRQ_SHAREABLE), + DEFINE_RES_MEM(zdev->resource.start + XS100_8390_BASE, + 4 * 0x20) + }; + int reg; + /* This table is referenced in the device structure, so it must + * outlive the scope of xsurf100_probe. + */ + static u32 reg_offsets[32]; + int ret = 0; + + /* X-Surf 100 control and 32 bit ring buffer data access areas. + * These resources are not used by the ax88796 driver, so must + * be requested here and passed via platform data. + */ + + if (!request_mem_region(zdev->resource.start, 0x100, zdev->name)) { + dev_err(&zdev->dev, "cannot reserve X-Surf 100 control registers\n"); + return -ENXIO; + } + + if (!request_mem_region(zdev->resource.start + + XS100_8390_DATA32_BASE, + XS100_8390_DATA32_SIZE, + "X-Surf 100 32-bit data access")) { + dev_err(&zdev->dev, "cannot reserve 32-bit area\n"); + ret = -ENXIO; + goto exit_req; + } + + for (reg = 0; reg < 0x20; reg++) + reg_offsets[reg] = 4 * reg; + + memset(&ax88796_data, 0, sizeof(ax88796_data)); + ax88796_data.ax.flags = AXFLG_HAS_EEPROM; + ax88796_data.ax.wordlength = 2; + ax88796_data.ax.dcr_val = 0x48; + ax88796_data.ax.rcr_val = 0x40; + ax88796_data.ax.reg_offsets = reg_offsets; + ax88796_data.ax.check_irq = is_xsurf100_network_irq; + ax88796_data.base_regs = ioremap(zdev->resource.start, 0x100); + + /* error handling for ioremap regs */ + if (!ax88796_data.base_regs) { + dev_err(&zdev->dev, "Cannot ioremap area %pR (registers)\n", + &zdev->resource); + + ret = -ENXIO; + goto exit_req2; + } + + ax88796_data.data_area = ioremap(zdev->resource.start + + XS100_8390_DATA32_BASE, XS100_8390_DATA32_SIZE); + + /* error handling for ioremap data */ + if (!ax88796_data.data_area) { + dev_err(&zdev->dev, + "Cannot ioremap area %pR offset %x (32-bit access)\n", + &zdev->resource, XS100_8390_DATA32_BASE); + + ret = -ENXIO; + goto exit_mem; + } + + ax88796_data.ax.block_output = xs100_block_output; + ax88796_data.ax.block_input = xs100_block_input; + + pdev = platform_device_register_resndata(&zdev->dev, "ax88796", + zdev->slotaddr, res, 2, + &ax88796_data, + sizeof(ax88796_data)); + + if (IS_ERR(pdev)) { + dev_err(&zdev->dev, "cannot register platform device\n"); + ret = -ENXIO; + goto exit_mem2; + } + + zorro_set_drvdata(zdev, pdev); + + if (!ret) + return 0; + + exit_mem2: + iounmap(ax88796_data.data_area); + + exit_mem: + iounmap(ax88796_data.base_regs); + + exit_req2: + release_mem_region(zdev->resource.start + XS100_8390_DATA32_BASE, + XS100_8390_DATA32_SIZE); + + exit_req: + release_mem_region(zdev->resource.start, 0x100); + + return ret; +} + +static void xsurf100_remove(struct zorro_dev *zdev) +{ + struct platform_device *pdev = zorro_get_drvdata(zdev); + struct xsurf100_ax_plat_data *xs100 = dev_get_platdata(&pdev->dev); + + platform_device_unregister(pdev); + + iounmap(xs100->base_regs); + release_mem_region(zdev->resource.start, 0x100); + iounmap(xs100->data_area); + release_mem_region(zdev->resource.start + XS100_8390_DATA32_BASE, + XS100_8390_DATA32_SIZE); +} + +static const struct zorro_device_id xsurf100_zorro_tbl[] = { + { ZORRO_PROD_INDIVIDUAL_COMPUTERS_X_SURF100, }, + { 0 } +}; + +MODULE_DEVICE_TABLE(zorro, xsurf100_zorro_tbl); + +static struct zorro_driver xsurf100_driver = { + .name = "xsurf100", + .id_table = xsurf100_zorro_tbl, + .probe = xsurf100_probe, + .remove = xsurf100_remove, +}; + +module_driver(xsurf100_driver, zorro_register_driver, zorro_unregister_driver); + +MODULE_DESCRIPTION("X-Surf 100 driver"); +MODULE_AUTHOR("Michael Karcher <kernel@mkarcher.dialup.fu-berlin.de>"); +MODULE_LICENSE("GPL v2"); diff --git a/drivers/net/ethernet/amd/amd8111e.c b/drivers/net/ethernet/amd/amd8111e.c index c99e3e845ac0..a90080f12e67 100644 --- a/drivers/net/ethernet/amd/amd8111e.c +++ b/drivers/net/ethernet/amd/amd8111e.c @@ -1074,16 +1074,12 @@ static int amd8111e_calc_coalesce(struct net_device *dev) amd8111e_set_coalesce(dev,TX_INTR_COAL); coal_conf->tx_coal_type = MEDIUM_COALESCE; } - - } - else if(tx_pkt_size >= 1024){ - if (tx_pkt_size >= 1024){ - if(coal_conf->tx_coal_type != HIGH_COALESCE){ - coal_conf->tx_timeout = 4; - coal_conf->tx_event_count = 8; - amd8111e_set_coalesce(dev,TX_INTR_COAL); - coal_conf->tx_coal_type = HIGH_COALESCE; - } + } else if (tx_pkt_size >= 1024) { + if (coal_conf->tx_coal_type != HIGH_COALESCE) { + coal_conf->tx_timeout = 4; + coal_conf->tx_event_count = 8; + amd8111e_set_coalesce(dev, TX_INTR_COAL); + coal_conf->tx_coal_type = HIGH_COALESCE; } } } diff --git a/drivers/net/ethernet/broadcom/bcmsysport.c b/drivers/net/ethernet/broadcom/bcmsysport.c index f33b25fbca63..d5fca2e5a9bc 100644 --- a/drivers/net/ethernet/broadcom/bcmsysport.c +++ b/drivers/net/ethernet/broadcom/bcmsysport.c @@ -654,7 +654,7 @@ static int bcm_sysport_set_coalesce(struct net_device *dev, pkts = priv->rx_max_coalesced_frames; if (ec->use_adaptive_rx_coalesce && !priv->dim.use_dim) { - moder = net_dim_get_def_profile(priv->dim.dim.mode); + moder = net_dim_get_def_rx_moderation(priv->dim.dim.mode); usecs = moder.usec; pkts = moder.pkts; } @@ -1064,7 +1064,7 @@ static void bcm_sysport_dim_work(struct work_struct *work) struct bcm_sysport_priv *priv = container_of(ndim, struct bcm_sysport_priv, dim); struct net_dim_cq_moder cur_profile = - net_dim_get_profile(dim->mode, dim->profile_ix); + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); bcm_sysport_set_rx_coalesce(priv, cur_profile.usec, cur_profile.pkts); dim->state = NET_DIM_START_MEASURE; @@ -1437,7 +1437,7 @@ static void bcm_sysport_init_rx_coalesce(struct bcm_sysport_priv *priv) /* If DIM was enabled, re-apply default parameters */ if (dim->use_dim) { - moder = net_dim_get_def_profile(dim->dim.mode); + moder = net_dim_get_def_rx_moderation(dim->dim.mode); usecs = moder.usec; pkts = moder.pkts; } diff --git a/drivers/net/ethernet/broadcom/bnxt/Makefile b/drivers/net/ethernet/broadcom/bnxt/Makefile index 7c560d545c03..5a779b19d149 100644 --- a/drivers/net/ethernet/broadcom/bnxt/Makefile +++ b/drivers/net/ethernet/broadcom/bnxt/Makefile @@ -2,3 +2,4 @@ obj-$(CONFIG_BNXT) += bnxt_en.o bnxt_en-y := bnxt.o bnxt_sriov.o bnxt_ethtool.o bnxt_dcb.o bnxt_ulp.o bnxt_xdp.o bnxt_vfr.o bnxt_devlink.o bnxt_dim.o bnxt_en-$(CONFIG_BNXT_FLOWER_OFFLOAD) += bnxt_tc.o +bnxt_en-$(CONFIG_DEBUG_FS) += bnxt_debugfs.o diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.c b/drivers/net/ethernet/broadcom/bnxt/bnxt.c index f83769d8047b..dfa0839f6656 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.c @@ -62,6 +62,7 @@ #include "bnxt_vfr.h" #include "bnxt_tc.h" #include "bnxt_devlink.h" +#include "bnxt_debugfs.h" #define BNXT_TX_TIMEOUT (5 * HZ) @@ -2383,6 +2384,7 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) for (i = 0, j = 0; i < bp->tx_nr_rings; i++) { struct bnxt_tx_ring_info *txr = &bp->tx_ring[i]; struct bnxt_ring_struct *ring; + u8 qidx; ring = &txr->tx_ring_struct; @@ -2411,7 +2413,8 @@ static int bnxt_alloc_tx_rings(struct bnxt *bp) memset(txr->tx_push, 0, sizeof(struct tx_push_bd)); } - ring->queue_id = bp->q_info[j].queue_id; + qidx = bp->tc_to_qidx[j]; + ring->queue_id = bp->q_info[qidx].queue_id; if (i < bp->tx_nr_rings_xdp) continue; if (i % bp->tx_nr_rings_per_tc == (bp->tx_nr_rings_per_tc - 1)) @@ -3493,15 +3496,29 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, if (!timeout) timeout = DFLT_HWRM_CMD_TIMEOUT; + /* convert timeout to usec */ + timeout *= 1000; i = 0; - tmo_count = timeout * 40; + /* Short timeout for the first few iterations: + * number of loops = number of loops for short timeout + + * number of loops for standard timeout. + */ + tmo_count = HWRM_SHORT_TIMEOUT_COUNTER; + timeout = timeout - HWRM_SHORT_MIN_TIMEOUT * HWRM_SHORT_TIMEOUT_COUNTER; + tmo_count += DIV_ROUND_UP(timeout, HWRM_MIN_TIMEOUT); resp_len = bp->hwrm_cmd_resp_addr + HWRM_RESP_LEN_OFFSET; if (intr_process) { /* Wait until hwrm response cmpl interrupt is processed */ while (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID && i++ < tmo_count) { - usleep_range(25, 40); + /* on first few passes, just barely sleep */ + if (i < HWRM_SHORT_TIMEOUT_COUNTER) + usleep_range(HWRM_SHORT_MIN_TIMEOUT, + HWRM_SHORT_MAX_TIMEOUT); + else + usleep_range(HWRM_MIN_TIMEOUT, + HWRM_MAX_TIMEOUT); } if (bp->hwrm_intr_seq_id != HWRM_SEQ_ID_INVALID) { @@ -3513,25 +3530,34 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, HWRM_RESP_LEN_SFT; valid = bp->hwrm_cmd_resp_addr + len - 1; } else { + int j; + /* Check if response len is updated */ for (i = 0; i < tmo_count; i++) { len = (le32_to_cpu(*resp_len) & HWRM_RESP_LEN_MASK) >> HWRM_RESP_LEN_SFT; if (len) break; - usleep_range(25, 40); + /* on first few passes, just barely sleep */ + if (i < DFLT_HWRM_CMD_TIMEOUT) + usleep_range(HWRM_SHORT_MIN_TIMEOUT, + HWRM_SHORT_MAX_TIMEOUT); + else + usleep_range(HWRM_MIN_TIMEOUT, + HWRM_MAX_TIMEOUT); } if (i >= tmo_count) { netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d\n", - timeout, le16_to_cpu(req->req_type), + HWRM_TOTAL_TIMEOUT(i), + le16_to_cpu(req->req_type), le16_to_cpu(req->seq_id), len); return -1; } /* Last byte of resp contains valid bit */ valid = bp->hwrm_cmd_resp_addr + len - 1; - for (i = 0; i < 5; i++) { + for (j = 0; j < HWRM_VALID_BIT_DELAY_USEC; j++) { /* make sure we read from updated DMA memory */ dma_rmb(); if (*valid) @@ -3539,9 +3565,10 @@ static int bnxt_hwrm_do_send_msg(struct bnxt *bp, void *msg, u32 msg_len, udelay(1); } - if (i >= 5) { + if (j >= HWRM_VALID_BIT_DELAY_USEC) { netdev_err(bp->dev, "Error (timeout: %d) msg {0x%x 0x%x} len:%d v:%d\n", - timeout, le16_to_cpu(req->req_type), + HWRM_TOTAL_TIMEOUT(i), + le16_to_cpu(req->req_type), le16_to_cpu(req->seq_id), len, *valid); return -1; } @@ -4334,26 +4361,9 @@ static int hwrm_ring_alloc_send_msg(struct bnxt *bp, mutex_unlock(&bp->hwrm_cmd_lock); if (rc || err) { - switch (ring_type) { - case RING_FREE_REQ_RING_TYPE_L2_CMPL: - netdev_err(bp->dev, "hwrm_ring_alloc cp failed. rc:%x err:%x\n", - rc, err); - return -1; - - case RING_FREE_REQ_RING_TYPE_RX: - netdev_err(bp->dev, "hwrm_ring_alloc rx failed. rc:%x err:%x\n", - rc, err); - return -1; - - case RING_FREE_REQ_RING_TYPE_TX: - netdev_err(bp->dev, "hwrm_ring_alloc tx failed. rc:%x err:%x\n", - rc, err); - return -1; - - default: - netdev_err(bp->dev, "Invalid ring\n"); - return -1; - } + netdev_err(bp->dev, "hwrm_ring_alloc type %d failed. rc:%x err:%x\n", + ring_type, rc, err); + return -EIO; } ring->fw_ring_id = ring_id; return rc; @@ -4477,23 +4487,9 @@ static int hwrm_ring_free_send_msg(struct bnxt *bp, mutex_unlock(&bp->hwrm_cmd_lock); if (rc || error_code) { - switch (ring_type) { - case RING_FREE_REQ_RING_TYPE_L2_CMPL: - netdev_err(bp->dev, "hwrm_ring_free cp failed. rc:%d\n", - rc); - return rc; - case RING_FREE_REQ_RING_TYPE_RX: - netdev_err(bp->dev, "hwrm_ring_free rx failed. rc:%d\n", - rc); - return rc; - case RING_FREE_REQ_RING_TYPE_TX: - netdev_err(bp->dev, "hwrm_ring_free tx failed. rc:%d\n", - rc); - return rc; - default: - netdev_err(bp->dev, "Invalid ring\n"); - return -1; - } + netdev_err(bp->dev, "hwrm_ring_free type %d failed. rc:%x err:%x\n", + ring_type, rc, error_code); + return -EIO; } return 0; } @@ -4721,6 +4717,10 @@ bnxt_hwrm_reserve_vf_rings(struct bnxt *bp, int tx_rings, int rx_rings, __bnxt_hwrm_reserve_vf_rings(bp, &req, tx_rings, rx_rings, ring_grps, cp_rings, vnics); + req.enables |= cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_NUM_RSSCOS_CTXS | + FUNC_VF_CFG_REQ_ENABLES_NUM_L2_CTXS); + req.num_rsscos_ctxs = cpu_to_le16(BNXT_VF_MAX_RSS_CTX); + req.num_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX); rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (rc) return -ENOMEM; @@ -5309,6 +5309,7 @@ static int bnxt_hwrm_queue_qportcfg(struct bnxt *bp) for (i = 0; i < bp->max_tc; i++) { bp->q_info[i].queue_id = *qptr++; bp->q_info[i].queue_profile = *qptr++; + bp->tc_to_qidx[i] = i; } qportcfg_exit: @@ -5376,7 +5377,8 @@ int bnxt_hwrm_fw_set_time(struct bnxt *bp) struct tm tm; time64_t now = ktime_get_real_seconds(); - if (bp->hwrm_spec_code < 0x10400) + if ((BNXT_VF(bp) && bp->hwrm_spec_code < 0x10901) || + bp->hwrm_spec_code < 0x10400) return -EOPNOTSUPP; time64_to_tm(now, 0, &tm); @@ -5958,6 +5960,9 @@ static int bnxt_init_msix(struct bnxt *bp) if (total_vecs > max) total_vecs = max; + if (!total_vecs) + return 0; + msix_ent = kcalloc(total_vecs, sizeof(struct msix_entry), GFP_KERNEL); if (!msix_ent) return -ENOMEM; @@ -6457,6 +6462,9 @@ static int bnxt_update_link(struct bnxt *bp, bool chng_link_state) } mutex_unlock(&bp->hwrm_cmd_lock); + if (!BNXT_SINGLE_PF(bp)) + return 0; + diff = link_info->support_auto_speeds ^ link_info->advertising; if ((link_info->support_auto_speeds | diff) != link_info->support_auto_speeds) { @@ -6843,6 +6851,8 @@ static void bnxt_preset_reg_win(struct bnxt *bp) } } +static int bnxt_init_dflt_ring_mode(struct bnxt *bp); + static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) { int rc = 0; @@ -6850,6 +6860,12 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) bnxt_preset_reg_win(bp); netif_carrier_off(bp->dev); if (irq_re_init) { + /* Reserve rings now if none were reserved at driver probe. */ + rc = bnxt_init_dflt_ring_mode(bp); + if (rc) { + netdev_err(bp->dev, "Failed to reserve default rings at open\n"); + return rc; + } rc = bnxt_reserve_rings(bp); if (rc) return rc; @@ -6877,6 +6893,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) } bnxt_enable_napi(bp); + bnxt_debug_dev_init(bp); rc = bnxt_init_nic(bp, irq_re_init); if (rc) { @@ -6909,6 +6926,7 @@ static int __bnxt_open_nic(struct bnxt *bp, bool irq_re_init, bool link_re_init) return 0; open_err: + bnxt_debug_dev_exit(bp); bnxt_disable_napi(bp); bnxt_del_napi(bp); @@ -7002,6 +7020,7 @@ static void __bnxt_close_nic(struct bnxt *bp, bool irq_re_init, /* TODO CHIMP_FW: Link/PHY related cleanup if (link_re_init) */ + bnxt_debug_dev_exit(bp); bnxt_disable_napi(bp); del_timer_sync(&bp->timer); bnxt_free_skbs(bp); @@ -7279,6 +7298,25 @@ skip_uc: return rc; } +static bool bnxt_can_reserve_rings(struct bnxt *bp) +{ +#ifdef CONFIG_BNXT_SRIOV + if ((bp->flags & BNXT_FLAG_NEW_RM) && BNXT_VF(bp)) { + struct bnxt_hw_resc *hw_resc = &bp->hw_resc; + + /* No minimum rings were provisioned by the PF. Don't + * reserve rings by default when device is down. + */ + if (hw_resc->min_tx_rings || hw_resc->resv_tx_rings) + return true; + + if (!netif_running(bp->dev)) + return false; + } +#endif + return true; +} + /* If the chip and firmware supports RFS */ static bool bnxt_rfs_supported(struct bnxt *bp) { @@ -7295,7 +7333,7 @@ static bool bnxt_rfs_capable(struct bnxt *bp) #ifdef CONFIG_RFS_ACCEL int vnics, max_vnics, max_rss_ctxs; - if (!(bp->flags & BNXT_FLAG_MSIX_CAP)) + if (!(bp->flags & BNXT_FLAG_MSIX_CAP) || !bnxt_can_reserve_rings(bp)) return false; vnics = 1 + bp->rx_nr_rings; @@ -7729,7 +7767,7 @@ static void bnxt_init_dflt_coal(struct bnxt *bp) coal->coal_bufs = 30; coal->coal_ticks_irq = 1; coal->coal_bufs_irq = 2; - coal->idle_thresh = 25; + coal->idle_thresh = 50; coal->bufs_per_record = 2; coal->budget = 64; /* NAPI budget */ @@ -8529,6 +8567,9 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh) { int dflt_rings, max_rx_rings, max_tx_rings, rc; + if (!bnxt_can_reserve_rings(bp)) + return 0; + if (sh) bp->flags |= BNXT_FLAG_SHARED_RINGS; dflt_rings = netif_get_num_default_rss_queues(); @@ -8574,6 +8615,29 @@ static int bnxt_set_dflt_rings(struct bnxt *bp, bool sh) return rc; } +static int bnxt_init_dflt_ring_mode(struct bnxt *bp) +{ + int rc; + + if (bp->tx_nr_rings) + return 0; + + rc = bnxt_set_dflt_rings(bp, true); + if (rc) { + netdev_err(bp->dev, "Not enough rings available.\n"); + return rc; + } + rc = bnxt_init_int_mode(bp); + if (rc) + return rc; + bp->tx_nr_rings_per_tc = bp->tx_nr_rings; + if (bnxt_rfs_supported(bp) && bnxt_rfs_capable(bp)) { + bp->flags |= BNXT_FLAG_RFS; + bp->dev->features |= NETIF_F_NTUPLE; + } + return 0; +} + int bnxt_restore_pf_fw_resources(struct bnxt *bp) { int rc; @@ -8614,8 +8678,8 @@ static int bnxt_init_mac_addr(struct bnxt *bp) memcpy(bp->dev->dev_addr, vf->mac_addr, ETH_ALEN); } else { eth_hw_addr_random(bp->dev); - rc = bnxt_approve_mac(bp, bp->dev->dev_addr); } + rc = bnxt_approve_mac(bp, bp->dev->dev_addr); #endif } return rc; @@ -9078,6 +9142,7 @@ static struct pci_driver bnxt_pci_driver = { static int __init bnxt_init(void) { + bnxt_debug_init(); return pci_register_driver(&bnxt_pci_driver); } @@ -9086,6 +9151,7 @@ static void __exit bnxt_exit(void) pci_unregister_driver(&bnxt_pci_driver); if (bnxt_pf_wq) destroy_workqueue(bnxt_pf_wq); + bnxt_debug_exit(); } module_init(bnxt_init); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt.h b/drivers/net/ethernet/broadcom/bnxt/bnxt.h index 3d55d3b56865..9b14eb610b9f 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt.h @@ -532,6 +532,19 @@ struct rx_tpa_end_cmp_ext { #define BNXT_HWRM_REQ_MAX_SIZE 128 #define BNXT_HWRM_REQS_PER_PAGE (BNXT_PAGE_SIZE / \ BNXT_HWRM_REQ_MAX_SIZE) +#define HWRM_SHORT_MIN_TIMEOUT 3 +#define HWRM_SHORT_MAX_TIMEOUT 10 +#define HWRM_SHORT_TIMEOUT_COUNTER 5 + +#define HWRM_MIN_TIMEOUT 25 +#define HWRM_MAX_TIMEOUT 40 + +#define HWRM_TOTAL_TIMEOUT(n) (((n) <= HWRM_SHORT_TIMEOUT_COUNTER) ? \ + ((n) * HWRM_SHORT_MIN_TIMEOUT) : \ + (HWRM_SHORT_TIMEOUT_COUNTER * HWRM_SHORT_MIN_TIMEOUT + \ + ((n) - HWRM_SHORT_TIMEOUT_COUNTER) * HWRM_MIN_TIMEOUT)) + +#define HWRM_VALID_BIT_DELAY_USEC 20 #define BNXT_RX_EVENT 1 #define BNXT_AGG_EVENT 2 @@ -1242,6 +1255,7 @@ struct bnxt { u8 max_tc; u8 max_lltc; /* lossless TCs */ struct bnxt_queue_info q_info[BNXT_MAX_QUEUE]; + u8 tc_to_qidx[BNXT_MAX_QUEUE]; unsigned int current_interval; #define BNXT_TIMER_INTERVAL HZ @@ -1384,6 +1398,8 @@ struct bnxt { u16 *cfa_code_map; /* cfa_code -> vf_idx map */ u8 switch_id[8]; struct bnxt_tc_info *tc_info; + struct dentry *debugfs_pdev; + struct dentry *debugfs_dim; }; #define BNXT_RX_STATS_OFFSET(counter) \ @@ -1398,8 +1414,7 @@ struct bnxt { #define I2C_DEV_ADDR_A0 0xa0 #define I2C_DEV_ADDR_A2 0xa2 -#define SFP_EEPROM_SFF_8472_COMP_ADDR 0x5e -#define SFP_EEPROM_SFF_8472_COMP_SIZE 1 +#define SFF_DIAG_SUPPORT_OFFSET 0x5c #define SFF_MODULE_ID_SFP 0x3 #define SFF_MODULE_ID_QSFP 0xc #define SFF_MODULE_ID_QSFP_PLUS 0xd diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c index 3c746f2d9ed8..d5bc72cecde3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dcb.c @@ -21,6 +21,21 @@ #include "bnxt_dcb.h" #ifdef CONFIG_BNXT_DCB +static int bnxt_queue_to_tc(struct bnxt *bp, u8 queue_id) +{ + int i, j; + + for (i = 0; i < bp->max_tc; i++) { + if (bp->q_info[i].queue_id == queue_id) { + for (j = 0; j < bp->max_tc; j++) { + if (bp->tc_to_qidx[j] == i) + return j; + } + } + } + return -EINVAL; +} + static int bnxt_hwrm_queue_pri2cos_cfg(struct bnxt *bp, struct ieee_ets *ets) { struct hwrm_queue_pri2cos_cfg_input req = {0}; @@ -33,10 +48,13 @@ static int bnxt_hwrm_queue_pri2cos_cfg(struct bnxt *bp, struct ieee_ets *ets) pri2cos = &req.pri0_cos_queue_id; for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { + u8 qidx; + req.enables |= cpu_to_le32( QUEUE_PRI2COS_CFG_REQ_ENABLES_PRI0_COS_QUEUE_ID << i); - pri2cos[i] = bp->q_info[ets->prio_tc[i]].queue_id; + qidx = bp->tc_to_qidx[ets->prio_tc[i]]; + pri2cos[i] = bp->q_info[qidx].queue_id; } rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); return rc; @@ -55,17 +73,15 @@ static int bnxt_hwrm_queue_pri2cos_qcfg(struct bnxt *bp, struct ieee_ets *ets) rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); if (!rc) { u8 *pri2cos = &resp->pri0_cos_queue_id; - int i, j; + int i; for (i = 0; i < IEEE_8021QAZ_MAX_TCS; i++) { u8 queue_id = pri2cos[i]; + int tc; - for (j = 0; j < bp->max_tc; j++) { - if (bp->q_info[j].queue_id == queue_id) { - ets->prio_tc[i] = j; - break; - } - } + tc = bnxt_queue_to_tc(bp, queue_id); + if (tc >= 0) + ets->prio_tc[i] = tc; } } mutex_unlock(&bp->hwrm_cmd_lock); @@ -81,13 +97,15 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets, void *data; bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_COS2BW_CFG, -1, -1); - data = &req.unused_0; - for (i = 0; i < max_tc; i++, data += sizeof(cos2bw) - 4) { + for (i = 0; i < max_tc; i++) { + u8 qidx; + req.enables |= cpu_to_le32( QUEUE_COS2BW_CFG_REQ_ENABLES_COS_QUEUE_ID0_VALID << i); memset(&cos2bw, 0, sizeof(cos2bw)); - cos2bw.queue_id = bp->q_info[i].queue_id; + qidx = bp->tc_to_qidx[i]; + cos2bw.queue_id = bp->q_info[qidx].queue_id; if (ets->tc_tsa[i] == IEEE_8021QAZ_TSA_STRICT) { cos2bw.tsa = QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP; @@ -103,8 +121,9 @@ static int bnxt_hwrm_queue_cos2bw_cfg(struct bnxt *bp, struct ieee_ets *ets, cpu_to_le32((ets->tc_tx_bw[i] * 100) | BW_VALUE_UNIT_PERCENT1_100); } + data = &req.unused_0 + qidx * (sizeof(cos2bw) - 4); memcpy(data, &cos2bw.queue_id, sizeof(cos2bw) - 4); - if (i == 0) { + if (qidx == 0) { req.queue_id0 = cos2bw.queue_id; req.unused_0 = 0; } @@ -132,66 +151,81 @@ static int bnxt_hwrm_queue_cos2bw_qcfg(struct bnxt *bp, struct ieee_ets *ets) data = &resp->queue_id0 + offsetof(struct bnxt_cos2bw_cfg, queue_id); for (i = 0; i < bp->max_tc; i++, data += sizeof(cos2bw) - 4) { - int j; + int tc; memcpy(&cos2bw.queue_id, data, sizeof(cos2bw) - 4); if (i == 0) cos2bw.queue_id = resp->queue_id0; - for (j = 0; j < bp->max_tc; j++) { - if (bp->q_info[j].queue_id != cos2bw.queue_id) - continue; - if (cos2bw.tsa == - QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP) { - ets->tc_tsa[j] = IEEE_8021QAZ_TSA_STRICT; - } else { - ets->tc_tsa[j] = IEEE_8021QAZ_TSA_ETS; - ets->tc_tx_bw[j] = cos2bw.bw_weight; - } + tc = bnxt_queue_to_tc(bp, cos2bw.queue_id); + if (tc < 0) + continue; + + if (cos2bw.tsa == + QUEUE_COS2BW_QCFG_RESP_QUEUE_ID0_TSA_ASSIGN_SP) { + ets->tc_tsa[tc] = IEEE_8021QAZ_TSA_STRICT; + } else { + ets->tc_tsa[tc] = IEEE_8021QAZ_TSA_ETS; + ets->tc_tx_bw[tc] = cos2bw.bw_weight; } } mutex_unlock(&bp->hwrm_cmd_lock); return 0; } -static int bnxt_hwrm_queue_cfg(struct bnxt *bp, unsigned int lltc_mask) +static int bnxt_queue_remap(struct bnxt *bp, unsigned int lltc_mask) { - struct hwrm_queue_cfg_input req = {0}; - int i; + unsigned long qmap = 0; + int max = bp->max_tc; + int i, j, rc; - if (netif_running(bp->dev)) - bnxt_tx_disable(bp); + /* Assign lossless TCs first */ + for (i = 0, j = 0; i < max; ) { + if (lltc_mask & (1 << i)) { + if (BNXT_LLQ(bp->q_info[j].queue_profile)) { + bp->tc_to_qidx[i] = j; + __set_bit(j, &qmap); + i++; + } + j++; + continue; + } + i++; + } - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_CFG, -1, -1); - req.flags = cpu_to_le32(QUEUE_CFG_REQ_FLAGS_PATH_BIDIR); - req.enables = cpu_to_le32(QUEUE_CFG_REQ_ENABLES_SERVICE_PROFILE); + for (i = 0, j = 0; i < max; i++) { + if (lltc_mask & (1 << i)) + continue; + j = find_next_zero_bit(&qmap, max, j); + bp->tc_to_qidx[i] = j; + __set_bit(j, &qmap); + j++; + } - /* Configure lossless queues to lossy first */ - req.service_profile = QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY; - for (i = 0; i < bp->max_tc; i++) { - if (BNXT_LLQ(bp->q_info[i].queue_profile)) { - req.queue_id = cpu_to_le32(bp->q_info[i].queue_id); - hwrm_send_message(bp, &req, sizeof(req), - HWRM_CMD_TIMEOUT); - bp->q_info[i].queue_profile = - QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSY; + if (netif_running(bp->dev)) { + bnxt_close_nic(bp, false, false); + rc = bnxt_open_nic(bp, false, false); + if (rc) { + netdev_warn(bp->dev, "failed to open NIC, rc = %d\n", rc); + return rc; } } - - /* Now configure desired queues to lossless */ - req.service_profile = QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS; - for (i = 0; i < bp->max_tc; i++) { - if (lltc_mask & (1 << i)) { - req.queue_id = cpu_to_le32(bp->q_info[i].queue_id); - hwrm_send_message(bp, &req, sizeof(req), - HWRM_CMD_TIMEOUT); - bp->q_info[i].queue_profile = - QUEUE_CFG_REQ_SERVICE_PROFILE_LOSSLESS; + if (bp->ieee_ets) { + int tc = netdev_get_num_tc(bp->dev); + + if (!tc) + tc = 1; + rc = bnxt_hwrm_queue_cos2bw_cfg(bp, bp->ieee_ets, tc); + if (rc) { + netdev_warn(bp->dev, "failed to config BW, rc = %d\n", rc); + return rc; + } + rc = bnxt_hwrm_queue_pri2cos_cfg(bp, bp->ieee_ets); + if (rc) { + netdev_warn(bp->dev, "failed to config prio, rc = %d\n", rc); + return rc; } } - if (netif_running(bp->dev)) - bnxt_tx_enable(bp); - return 0; } @@ -201,7 +235,7 @@ static int bnxt_hwrm_queue_pfc_cfg(struct bnxt *bp, struct ieee_pfc *pfc) struct ieee_ets *my_ets = bp->ieee_ets; unsigned int tc_mask = 0, pri_mask = 0; u8 i, pri, lltc_count = 0; - bool need_q_recfg = false; + bool need_q_remap = false; int rc; if (!my_ets) @@ -221,21 +255,25 @@ static int bnxt_hwrm_queue_pfc_cfg(struct bnxt *bp, struct ieee_pfc *pfc) if (lltc_count > bp->max_lltc) return -EINVAL; - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_CFG, -1, -1); - req.flags = cpu_to_le32(pri_mask); - rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); - if (rc) - return rc; - for (i = 0; i < bp->max_tc; i++) { if (tc_mask & (1 << i)) { - if (!BNXT_LLQ(bp->q_info[i].queue_profile)) - need_q_recfg = true; + u8 qidx = bp->tc_to_qidx[i]; + + if (!BNXT_LLQ(bp->q_info[qidx].queue_profile)) { + need_q_remap = true; + break; + } } } - if (need_q_recfg) - rc = bnxt_hwrm_queue_cfg(bp, tc_mask); + if (need_q_remap) + rc = bnxt_queue_remap(bp, tc_mask); + + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_QUEUE_PFCENABLE_CFG, -1, -1); + req.flags = cpu_to_le32(pri_mask); + rc = hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + if (rc) + return rc; return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c new file mode 100644 index 000000000000..94e208e9789f --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.c @@ -0,0 +1,124 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2017-2018 Broadcom Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#include <linux/debugfs.h> +#include <linux/module.h> +#include <linux/pci.h> +#include "bnxt_hsi.h" +#include <linux/net_dim.h> +#include "bnxt.h" +#include "bnxt_debugfs.h" + +static struct dentry *bnxt_debug_mnt; + +static ssize_t debugfs_dim_read(struct file *filep, + char __user *buffer, + size_t count, loff_t *ppos) +{ + struct net_dim *dim = filep->private_data; + int len; + char *buf; + + if (*ppos) + return 0; + if (!dim) + return -ENODEV; + buf = kasprintf(GFP_KERNEL, + "state = %d\n" \ + "profile_ix = %d\n" \ + "mode = %d\n" \ + "tune_state = %d\n" \ + "steps_right = %d\n" \ + "steps_left = %d\n" \ + "tired = %d\n", + dim->state, + dim->profile_ix, + dim->mode, + dim->tune_state, + dim->steps_right, + dim->steps_left, + dim->tired); + if (!buf) + return -ENOMEM; + if (count < strlen(buf)) { + kfree(buf); + return -ENOSPC; + } + len = simple_read_from_buffer(buffer, count, ppos, buf, strlen(buf)); + kfree(buf); + return len; +} + +static const struct file_operations debugfs_dim_fops = { + .owner = THIS_MODULE, + .open = simple_open, + .read = debugfs_dim_read, +}; + +static struct dentry *debugfs_dim_ring_init(struct net_dim *dim, int ring_idx, + struct dentry *dd) +{ + static char qname[16]; + + snprintf(qname, 10, "%d", ring_idx); + return debugfs_create_file(qname, 0600, dd, + dim, &debugfs_dim_fops); +} + +void bnxt_debug_dev_init(struct bnxt *bp) +{ + const char *pname = pci_name(bp->pdev); + struct dentry *pdevf; + int i; + + bp->debugfs_pdev = debugfs_create_dir(pname, bnxt_debug_mnt); + if (bp->debugfs_pdev) { + pdevf = debugfs_create_dir("dim", bp->debugfs_pdev); + if (!pdevf) { + pr_err("failed to create debugfs entry %s/dim\n", + pname); + return; + } + bp->debugfs_dim = pdevf; + /* create files for each rx ring */ + for (i = 0; i < bp->cp_nr_rings; i++) { + struct bnxt_cp_ring_info *cpr = &bp->bnapi[i]->cp_ring; + + if (cpr && bp->bnapi[i]->rx_ring) { + pdevf = debugfs_dim_ring_init(&cpr->dim, i, + bp->debugfs_dim); + if (!pdevf) + pr_err("failed to create debugfs entry %s/dim/%d\n", + pname, i); + } + } + } else { + pr_err("failed to create debugfs entry %s\n", pname); + } +} + +void bnxt_debug_dev_exit(struct bnxt *bp) +{ + if (bp) { + debugfs_remove_recursive(bp->debugfs_pdev); + bp->debugfs_pdev = NULL; + } +} + +void bnxt_debug_init(void) +{ + bnxt_debug_mnt = debugfs_create_dir("bnxt_en", NULL); + if (!bnxt_debug_mnt) + pr_err("failed to init bnxt_en debugfs\n"); +} + +void bnxt_debug_exit(void) +{ + debugfs_remove_recursive(bnxt_debug_mnt); +} diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h new file mode 100644 index 000000000000..d0bb4887acd0 --- /dev/null +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_debugfs.h @@ -0,0 +1,23 @@ +/* Broadcom NetXtreme-C/E network driver. + * + * Copyright (c) 2017-2018 Broadcom Limited + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License as published by + * the Free Software Foundation. + */ + +#include "bnxt_hsi.h" +#include "bnxt.h" + +#ifdef CONFIG_DEBUG_FS +void bnxt_debug_init(void); +void bnxt_debug_exit(void); +void bnxt_debug_dev_init(struct bnxt *bp); +void bnxt_debug_dev_exit(struct bnxt *bp); +#else +static inline void bnxt_debug_init(void) {} +static inline void bnxt_debug_exit(void) {} +static inline void bnxt_debug_dev_init(struct bnxt *bp) {} +static inline void bnxt_debug_dev_exit(struct bnxt *bp) {} +#endif diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c index 408dd190331e..afa97c8bb081 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_dim.c @@ -21,11 +21,11 @@ void bnxt_dim_work(struct work_struct *work) struct bnxt_napi *bnapi = container_of(cpr, struct bnxt_napi, cp_ring); - struct net_dim_cq_moder cur_profile = net_dim_get_profile(dim->mode, - dim->profile_ix); + struct net_dim_cq_moder cur_moder = + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); - cpr->rx_ring_coal.coal_ticks = cur_profile.usec; - cpr->rx_ring_coal.coal_bufs = cur_profile.pkts; + cpr->rx_ring_coal.coal_ticks = cur_moder.usec; + cpr->rx_ring_coal.coal_bufs = cur_moder.pkts; bnxt_hwrm_set_ring_coal(bnapi->bp, bnapi); dim->state = NET_DIM_START_MEASURE; diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c index 8ba14ae00e8f..7270c8b0cef3 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_ethtool.c @@ -140,6 +140,19 @@ reset_coalesce: #define BNXT_RX_STATS_EXT_ENTRY(counter) \ { BNXT_RX_STATS_EXT_OFFSET(counter), __stringify(counter) } +enum { + RX_TOTAL_DISCARDS, + TX_TOTAL_DISCARDS, +}; + +static struct { + u64 counter; + char string[ETH_GSTRING_LEN]; +} bnxt_sw_func_stats[] = { + {0, "rx_total_discard_pkts"}, + {0, "tx_total_discard_pkts"}, +}; + static const struct { long offset; char string[ETH_GSTRING_LEN]; @@ -237,6 +250,7 @@ static const struct { BNXT_RX_STATS_EXT_ENTRY(resume_roce_pause_events), }; +#define BNXT_NUM_SW_FUNC_STATS ARRAY_SIZE(bnxt_sw_func_stats) #define BNXT_NUM_PORT_STATS ARRAY_SIZE(bnxt_port_stats_arr) #define BNXT_NUM_PORT_STATS_EXT ARRAY_SIZE(bnxt_port_stats_ext_arr) @@ -244,6 +258,8 @@ static int bnxt_get_num_stats(struct bnxt *bp) { int num_stats = BNXT_NUM_STATS * bp->cp_nr_rings; + num_stats += BNXT_NUM_SW_FUNC_STATS; + if (bp->flags & BNXT_FLAG_PORT_STATS) num_stats += BNXT_NUM_PORT_STATS; @@ -279,6 +295,9 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, if (!bp->bnapi) return; + for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++) + bnxt_sw_func_stats[i].counter = 0; + for (i = 0; i < bp->cp_nr_rings; i++) { struct bnxt_napi *bnapi = bp->bnapi[i]; struct bnxt_cp_ring_info *cpr = &bnapi->cp_ring; @@ -288,7 +307,16 @@ static void bnxt_get_ethtool_stats(struct net_device *dev, for (k = 0; k < stat_fields; j++, k++) buf[j] = le64_to_cpu(hw_stats[k]); buf[j++] = cpr->rx_l4_csum_errors; + + bnxt_sw_func_stats[RX_TOTAL_DISCARDS].counter += + le64_to_cpu(cpr->hw_stats->rx_discard_pkts); + bnxt_sw_func_stats[TX_TOTAL_DISCARDS].counter += + le64_to_cpu(cpr->hw_stats->tx_discard_pkts); } + + for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++, j++) + buf[j] = bnxt_sw_func_stats[i].counter; + if (bp->flags & BNXT_FLAG_PORT_STATS) { __le64 *port_stats = (__le64 *)bp->hw_rx_port_stats; @@ -359,6 +387,11 @@ static void bnxt_get_strings(struct net_device *dev, u32 stringset, u8 *buf) sprintf(buf, "[%d]: rx_l4_csum_errors", i); buf += ETH_GSTRING_LEN; } + for (i = 0; i < BNXT_NUM_SW_FUNC_STATS; i++) { + strcpy(buf, bnxt_sw_func_stats[i].string); + buf += ETH_GSTRING_LEN; + } + if (bp->flags & BNXT_FLAG_PORT_STATS) { for (i = 0; i < BNXT_NUM_PORT_STATS; i++) { strcpy(buf, bnxt_port_stats_arr[i].string); @@ -551,6 +584,8 @@ static int bnxt_set_channels(struct net_device *dev, * to renable */ } + } else { + rc = bnxt_reserve_rings(bp); } return rc; @@ -1785,6 +1820,11 @@ static int nvm_get_dir_info(struct net_device *dev, u32 *entries, u32 *length) static int bnxt_get_eeprom_len(struct net_device *dev) { + struct bnxt *bp = netdev_priv(dev); + + if (BNXT_VF(bp)) + return 0; + /* The -1 return value allows the entire 32-bit range of offsets to be * passed via the ethtool command-line utility. */ @@ -2144,9 +2184,8 @@ static int bnxt_read_sfp_module_eeprom_info(struct bnxt *bp, u16 i2c_addr, static int bnxt_get_module_info(struct net_device *dev, struct ethtool_modinfo *modinfo) { + u8 data[SFF_DIAG_SUPPORT_OFFSET + 1]; struct bnxt *bp = netdev_priv(dev); - struct hwrm_port_phy_i2c_read_input req = {0}; - struct hwrm_port_phy_i2c_read_output *output = bp->hwrm_cmd_resp_addr; int rc; /* No point in going further if phy status indicates @@ -2161,21 +2200,19 @@ static int bnxt_get_module_info(struct net_device *dev, if (bp->hwrm_spec_code < 0x10202) return -EOPNOTSUPP; - bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_PORT_PHY_I2C_READ, -1, -1); - req.i2c_slave_addr = I2C_DEV_ADDR_A0; - req.page_number = 0; - req.page_offset = cpu_to_le16(SFP_EEPROM_SFF_8472_COMP_ADDR); - req.data_length = SFP_EEPROM_SFF_8472_COMP_SIZE; - req.port_id = cpu_to_le16(bp->pf.port_id); - mutex_lock(&bp->hwrm_cmd_lock); - rc = _hwrm_send_message(bp, &req, sizeof(req), HWRM_CMD_TIMEOUT); + rc = bnxt_read_sfp_module_eeprom_info(bp, I2C_DEV_ADDR_A0, 0, 0, + SFF_DIAG_SUPPORT_OFFSET + 1, + data); if (!rc) { - u32 module_id = le32_to_cpu(output->data[0]); + u8 module_id = data[0]; + u8 diag_supported = data[SFF_DIAG_SUPPORT_OFFSET]; switch (module_id) { case SFF_MODULE_ID_SFP: modinfo->type = ETH_MODULE_SFF_8472; modinfo->eeprom_len = ETH_MODULE_SFF_8472_LEN; + if (!diag_supported) + modinfo->eeprom_len = ETH_MODULE_SFF_8436_LEN; break; case SFF_MODULE_ID_QSFP: case SFF_MODULE_ID_QSFP_PLUS: @@ -2191,7 +2228,6 @@ static int bnxt_get_module_info(struct net_device *dev, break; } } - mutex_unlock(&bp->hwrm_cmd_lock); return rc; } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c index f952963d594e..a64910892c25 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.c @@ -462,13 +462,13 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) vf_vnics = hw_resc->max_vnics - bp->nr_vnics; vf_vnics = min_t(u16, vf_vnics, vf_rx_rings); - req.min_rsscos_ctx = cpu_to_le16(1); - req.max_rsscos_ctx = cpu_to_le16(1); + req.min_rsscos_ctx = cpu_to_le16(BNXT_VF_MIN_RSS_CTX); + req.max_rsscos_ctx = cpu_to_le16(BNXT_VF_MAX_RSS_CTX); if (pf->vf_resv_strategy == BNXT_VF_RESV_STRATEGY_MINIMAL) { req.min_cmpl_rings = cpu_to_le16(1); req.min_tx_rings = cpu_to_le16(1); req.min_rx_rings = cpu_to_le16(1); - req.min_l2_ctxs = cpu_to_le16(1); + req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MIN_L2_CTX); req.min_vnics = cpu_to_le16(1); req.min_stat_ctx = cpu_to_le16(1); req.min_hw_ring_grps = cpu_to_le16(1); @@ -483,7 +483,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) req.min_cmpl_rings = cpu_to_le16(vf_cp_rings); req.min_tx_rings = cpu_to_le16(vf_tx_rings); req.min_rx_rings = cpu_to_le16(vf_rx_rings); - req.min_l2_ctxs = cpu_to_le16(4); + req.min_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX); req.min_vnics = cpu_to_le16(vf_vnics); req.min_stat_ctx = cpu_to_le16(vf_stat_ctx); req.min_hw_ring_grps = cpu_to_le16(vf_ring_grps); @@ -491,7 +491,7 @@ static int bnxt_hwrm_func_vf_resc_cfg(struct bnxt *bp, int num_vfs) req.max_cmpl_rings = cpu_to_le16(vf_cp_rings); req.max_tx_rings = cpu_to_le16(vf_tx_rings); req.max_rx_rings = cpu_to_le16(vf_rx_rings); - req.max_l2_ctxs = cpu_to_le16(4); + req.max_l2_ctxs = cpu_to_le16(BNXT_VF_MAX_L2_CTX); req.max_vnics = cpu_to_le16(vf_vnics); req.max_stat_ctx = cpu_to_le16(vf_stat_ctx); req.max_hw_ring_grps = cpu_to_le16(vf_ring_grps); @@ -809,6 +809,9 @@ static int bnxt_hwrm_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, struct hwrm_fwd_resp_input req = {0}; struct hwrm_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr; + if (BNXT_FWD_RESP_SIZE_ERR(msg_size)) + return -EINVAL; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_FWD_RESP, -1, -1); /* Set the new target id */ @@ -845,6 +848,9 @@ static int bnxt_hwrm_fwd_err_resp(struct bnxt *bp, struct bnxt_vf_info *vf, struct hwrm_reject_fwd_resp_input req = {0}; struct hwrm_reject_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr; + if (BNXT_REJ_FWD_RESP_SIZE_ERR(msg_size)) + return -EINVAL; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_REJECT_FWD_RESP, -1, -1); /* Set the new target id */ req.target_id = cpu_to_le16(vf->fw_fid); @@ -877,6 +883,9 @@ static int bnxt_hwrm_exec_fwd_resp(struct bnxt *bp, struct bnxt_vf_info *vf, struct hwrm_exec_fwd_resp_input req = {0}; struct hwrm_exec_fwd_resp_output *resp = bp->hwrm_cmd_resp_addr; + if (BNXT_EXEC_FWD_RESP_SIZE_ERR(msg_size)) + return -EINVAL; + bnxt_hwrm_cmd_hdr_init(bp, &req, HWRM_EXEC_FWD_RESP, -1, -1); /* Set the new target id */ req.target_id = cpu_to_le16(vf->fw_fid); @@ -914,7 +923,8 @@ static int bnxt_vf_configure_mac(struct bnxt *bp, struct bnxt_vf_info *vf) if (req->enables & cpu_to_le32(FUNC_VF_CFG_REQ_ENABLES_DFLT_MAC_ADDR)) { if (is_valid_ether_addr(req->dflt_mac_addr) && ((vf->flags & BNXT_VF_TRUST) || - (!is_valid_ether_addr(vf->mac_addr)))) { + !is_valid_ether_addr(vf->mac_addr) || + ether_addr_equal(req->dflt_mac_addr, vf->mac_addr))) { ether_addr_copy(vf->vf_mac_addr, req->dflt_mac_addr); return bnxt_hwrm_exec_fwd_resp(bp, vf, msg_size); } diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h index d10f6f6c7860..e9b20cd19881 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_sriov.h @@ -11,6 +11,23 @@ #ifndef BNXT_SRIOV_H #define BNXT_SRIOV_H +#define BNXT_FWD_RESP_SIZE_ERR(n) \ + ((offsetof(struct hwrm_fwd_resp_input, encap_resp) + n) > \ + sizeof(struct hwrm_fwd_resp_input)) + +#define BNXT_EXEC_FWD_RESP_SIZE_ERR(n) \ + ((offsetof(struct hwrm_exec_fwd_resp_input, encap_request) + n) >\ + offsetof(struct hwrm_exec_fwd_resp_input, encap_resp_target_id)) + +#define BNXT_REJ_FWD_RESP_SIZE_ERR(n) \ + ((offsetof(struct hwrm_reject_fwd_resp_input, encap_request) + n) >\ + offsetof(struct hwrm_reject_fwd_resp_input, encap_resp_target_id)) + +#define BNXT_VF_MIN_RSS_CTX 1 +#define BNXT_VF_MAX_RSS_CTX 1 +#define BNXT_VF_MIN_L2_CTX 1 +#define BNXT_VF_MAX_L2_CTX 4 + int bnxt_get_vf_config(struct net_device *, int, struct ifla_vf_info *); int bnxt_set_vf_mac(struct net_device *, int, u8 *); int bnxt_set_vf_vlan(struct net_device *, int, u16, u8, __be16); diff --git a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c index 1389ab5e05df..1f0e872d0667 100644 --- a/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c +++ b/drivers/net/ethernet/broadcom/bnxt/bnxt_xdp.c @@ -113,10 +113,10 @@ bool bnxt_rx_xdp(struct bnxt *bp, struct bnxt_rx_ring_info *rxr, u16 cons, if (tx_avail != bp->tx_ring_size) *event &= ~BNXT_RX_EVENT; + *len = xdp.data_end - xdp.data; if (orig_data != xdp.data) { offset = xdp.data - xdp.data_hard_start; *data_ptr = xdp.data_hard_start + offset; - *len = xdp.data_end - xdp.data; } switch (act) { case XDP_PASS: diff --git a/drivers/net/ethernet/broadcom/genet/bcmgenet.c b/drivers/net/ethernet/broadcom/genet/bcmgenet.c index 0445f2c0c629..20c1681bb1af 100644 --- a/drivers/net/ethernet/broadcom/genet/bcmgenet.c +++ b/drivers/net/ethernet/broadcom/genet/bcmgenet.c @@ -652,7 +652,7 @@ static void bcmgenet_set_ring_rx_coalesce(struct bcmgenet_rx_ring *ring, pkts = ring->rx_max_coalesced_frames; if (ec->use_adaptive_rx_coalesce && !ring->dim.use_dim) { - moder = net_dim_get_def_profile(ring->dim.dim.mode); + moder = net_dim_get_def_rx_moderation(ring->dim.dim.mode); usecs = moder.usec; pkts = moder.pkts; } @@ -1925,7 +1925,7 @@ static void bcmgenet_dim_work(struct work_struct *work) struct bcmgenet_rx_ring *ring = container_of(ndim, struct bcmgenet_rx_ring, dim); struct net_dim_cq_moder cur_profile = - net_dim_get_profile(dim->mode, dim->profile_ix); + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); bcmgenet_set_rx_coalesce(ring, cur_profile.usec, cur_profile.pkts); dim->state = NET_DIM_START_MEASURE; @@ -2102,7 +2102,7 @@ static void bcmgenet_init_rx_coalesce(struct bcmgenet_rx_ring *ring) /* If DIM was enabled, re-apply default parameters */ if (dim->use_dim) { - moder = net_dim_get_def_profile(dim->dim.mode); + moder = net_dim_get_def_rx_moderation(dim->dim.mode); usecs = moder.usec; pkts = moder.pkts; } diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c index e8b290473ee2..929d485a3a2f 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.c @@ -1245,7 +1245,7 @@ static void cn23xx_setup_reg_address(struct octeon_device *oct) CN23XX_SLI_MAC_PF_INT_ENB64(oct->pcie_port, oct->pf_num); } -static int cn23xx_sriov_config(struct octeon_device *oct) +int cn23xx_sriov_config(struct octeon_device *oct) { struct octeon_cn23xx_pf *cn23xx = (struct octeon_cn23xx_pf *)oct->chip; u32 max_rings, total_rings, max_vfs, rings_per_vf; @@ -1269,8 +1269,8 @@ static int cn23xx_sriov_config(struct octeon_device *oct) break; } - if (max_rings <= num_present_cpus()) - num_pf_rings = 1; + if (oct->sriov_info.num_pf_rings) + num_pf_rings = oct->sriov_info.num_pf_rings; else num_pf_rings = num_present_cpus(); @@ -1497,3 +1497,57 @@ void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx, octeon_mbox_write(oct, &mbox_cmd); } } + +static void +cn23xx_get_vf_stats_callback(struct octeon_device *oct, + struct octeon_mbox_cmd *cmd, void *arg) +{ + struct oct_vf_stats_ctx *ctx = arg; + + memcpy(ctx->stats, cmd->data, sizeof(struct oct_vf_stats)); + atomic_set(&ctx->status, 1); +} + +int cn23xx_get_vf_stats(struct octeon_device *oct, int vfidx, + struct oct_vf_stats *stats) +{ + u32 timeout = HZ; // 1sec + struct octeon_mbox_cmd mbox_cmd; + struct oct_vf_stats_ctx ctx; + u32 count = 0, ret; + + if (!(oct->sriov_info.vf_drv_loaded_mask & (1ULL << vfidx))) + return -1; + + if (sizeof(struct oct_vf_stats) > sizeof(mbox_cmd.data)) + return -1; + + mbox_cmd.msg.u64 = 0; + mbox_cmd.msg.s.type = OCTEON_MBOX_REQUEST; + mbox_cmd.msg.s.resp_needed = 1; + mbox_cmd.msg.s.cmd = OCTEON_GET_VF_STATS; + mbox_cmd.msg.s.len = 1; + mbox_cmd.q_no = vfidx * oct->sriov_info.rings_per_vf; + mbox_cmd.recv_len = 0; + mbox_cmd.recv_status = 0; + mbox_cmd.fn = (octeon_mbox_callback_t)cn23xx_get_vf_stats_callback; + ctx.stats = stats; + atomic_set(&ctx.status, 0); + mbox_cmd.fn_arg = (void *)&ctx; + memset(mbox_cmd.data, 0, sizeof(mbox_cmd.data)); + octeon_mbox_write(oct, &mbox_cmd); + + do { + schedule_timeout_uninterruptible(1); + } while ((atomic_read(&ctx.status) == 0) && (count++ < timeout)); + + ret = atomic_read(&ctx.status); + if (ret == 0) { + octeon_mbox_cancel(oct, 0); + dev_err(&oct->pci_dev->dev, "Unable to get stats from VF-%d, timedout\n", + vfidx); + return -1; + } + + return 0; +} diff --git a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h index 2aba5247b6d8..e6f31d0d5c0b 100644 --- a/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h +++ b/drivers/net/ethernet/cavium/liquidio/cn23xx_pf_device.h @@ -43,6 +43,15 @@ struct octeon_cn23xx_pf { #define CN23XX_SLI_DEF_BP 0x40 +struct oct_vf_stats { + u64 rx_packets; + u64 tx_packets; + u64 rx_bytes; + u64 tx_bytes; + u64 broadcast; + u64 multicast; +}; + int setup_cn23xx_octeon_pf_device(struct octeon_device *oct); int validate_cn23xx_pf_config_info(struct octeon_device *oct, @@ -52,8 +61,13 @@ u32 cn23xx_pf_get_oq_ticks(struct octeon_device *oct, u32 time_intr_in_us); void cn23xx_dump_pf_initialized_regs(struct octeon_device *oct); +int cn23xx_sriov_config(struct octeon_device *oct); + int cn23xx_fw_loaded(struct octeon_device *oct); void cn23xx_tell_vf_its_macaddr_changed(struct octeon_device *oct, int vfidx, u8 *mac); + +int cn23xx_get_vf_stats(struct octeon_device *oct, int ifidx, + struct oct_vf_stats *stats); #endif diff --git a/drivers/net/ethernet/cavium/liquidio/lio_core.c b/drivers/net/ethernet/cavium/liquidio/lio_core.c index 2a94eee943b2..8093c5eafea2 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_core.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_core.c @@ -29,6 +29,162 @@ /* OOM task polling interval */ #define LIO_OOM_POLL_INTERVAL_MS 250 +#define OCTNIC_MAX_SG MAX_SKB_FRAGS + +/** + * \brief Callback for getting interface configuration + * @param status status of request + * @param buf pointer to resp structure + */ +void lio_if_cfg_callback(struct octeon_device *oct, + u32 status __attribute__((unused)), void *buf) +{ + struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; + struct liquidio_if_cfg_context *ctx; + struct liquidio_if_cfg_resp *resp; + + resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; + ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; + + oct = lio_get_device(ctx->octeon_id); + if (resp->status) + dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n", + CVM_CAST64(resp->status)); + WRITE_ONCE(ctx->cond, 1); + + snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s", + resp->cfg_info.liquidio_firmware_version); + + /* This barrier is required to be sure that the response has been + * written fully before waking up the handler + */ + wmb(); + + wake_up_interruptible(&ctx->wc); +} + +/** + * \brief Delete gather lists + * @param lio per-network private data + */ +void lio_delete_glists(struct lio *lio) +{ + struct octnic_gather *g; + int i; + + kfree(lio->glist_lock); + lio->glist_lock = NULL; + + if (!lio->glist) + return; + + for (i = 0; i < lio->oct_dev->num_iqs; i++) { + do { + g = (struct octnic_gather *) + lio_list_delete_head(&lio->glist[i]); + kfree(g); + } while (g); + + if (lio->glists_virt_base && lio->glists_virt_base[i] && + lio->glists_dma_base && lio->glists_dma_base[i]) { + lio_dma_free(lio->oct_dev, + lio->glist_entry_size * lio->tx_qsize, + lio->glists_virt_base[i], + lio->glists_dma_base[i]); + } + } + + kfree(lio->glists_virt_base); + lio->glists_virt_base = NULL; + + kfree(lio->glists_dma_base); + lio->glists_dma_base = NULL; + + kfree(lio->glist); + lio->glist = NULL; +} + +/** + * \brief Setup gather lists + * @param lio per-network private data + */ +int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs) +{ + struct octnic_gather *g; + int i, j; + + lio->glist_lock = + kcalloc(num_iqs, sizeof(*lio->glist_lock), GFP_KERNEL); + if (!lio->glist_lock) + return -ENOMEM; + + lio->glist = + kcalloc(num_iqs, sizeof(*lio->glist), GFP_KERNEL); + if (!lio->glist) { + kfree(lio->glist_lock); + lio->glist_lock = NULL; + return -ENOMEM; + } + + lio->glist_entry_size = + ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE); + + /* allocate memory to store virtual and dma base address of + * per glist consistent memory + */ + lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base), + GFP_KERNEL); + lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base), + GFP_KERNEL); + + if (!lio->glists_virt_base || !lio->glists_dma_base) { + lio_delete_glists(lio); + return -ENOMEM; + } + + for (i = 0; i < num_iqs; i++) { + int numa_node = dev_to_node(&oct->pci_dev->dev); + + spin_lock_init(&lio->glist_lock[i]); + + INIT_LIST_HEAD(&lio->glist[i]); + + lio->glists_virt_base[i] = + lio_dma_alloc(oct, + lio->glist_entry_size * lio->tx_qsize, + &lio->glists_dma_base[i]); + + if (!lio->glists_virt_base[i]) { + lio_delete_glists(lio); + return -ENOMEM; + } + + for (j = 0; j < lio->tx_qsize; j++) { + g = kzalloc_node(sizeof(*g), GFP_KERNEL, + numa_node); + if (!g) + g = kzalloc(sizeof(*g), GFP_KERNEL); + if (!g) + break; + + g->sg = lio->glists_virt_base[i] + + (j * lio->glist_entry_size); + + g->sg_dma_ptr = lio->glists_dma_base[i] + + (j * lio->glist_entry_size); + + list_add_tail(&g->list, &lio->glist[i]); + } + + if (j != lio->tx_qsize) { + lio_delete_glists(lio); + return -ENOMEM; + } + } + + return 0; +} + int liquidio_set_feature(struct net_device *netdev, int cmd, u16 param1) { struct lio *lio = GET_LIO(netdev); @@ -880,8 +1036,8 @@ int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs) int num_ioq_vectors; int irqret, err; - oct->num_msix_irqs = num_ioqs; if (oct->msix_on) { + oct->num_msix_irqs = num_ioqs; if (OCTEON_CN23XX_PF(oct)) { num_interrupts = MAX_IOQ_INTERRUPTS_PER_PF + 1; @@ -1169,3 +1325,355 @@ int lio_wait_for_clean_oq(struct octeon_device *oct) return pending_pkts; } + +static void +octnet_nic_stats_callback(struct octeon_device *oct_dev, + u32 status, void *ptr) +{ + struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr; + struct oct_nic_stats_resp *resp = + (struct oct_nic_stats_resp *)sc->virtrptr; + struct oct_nic_stats_ctrl *ctrl = + (struct oct_nic_stats_ctrl *)sc->ctxptr; + struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire; + struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost; + struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire; + struct nic_tx_stats *tstats = &oct_dev->link_stats.fromhost; + + if (status != OCTEON_REQUEST_TIMEOUT && !resp->status) { + octeon_swap_8B_data((u64 *)&resp->stats, + (sizeof(struct oct_link_stats)) >> 3); + + /* RX link-level stats */ + rstats->total_rcvd = rsp_rstats->total_rcvd; + rstats->bytes_rcvd = rsp_rstats->bytes_rcvd; + rstats->total_bcst = rsp_rstats->total_bcst; + rstats->total_mcst = rsp_rstats->total_mcst; + rstats->runts = rsp_rstats->runts; + rstats->ctl_rcvd = rsp_rstats->ctl_rcvd; + /* Accounts for over/under-run of buffers */ + rstats->fifo_err = rsp_rstats->fifo_err; + rstats->dmac_drop = rsp_rstats->dmac_drop; + rstats->fcs_err = rsp_rstats->fcs_err; + rstats->jabber_err = rsp_rstats->jabber_err; + rstats->l2_err = rsp_rstats->l2_err; + rstats->frame_err = rsp_rstats->frame_err; + rstats->red_drops = rsp_rstats->red_drops; + + /* RX firmware stats */ + rstats->fw_total_rcvd = rsp_rstats->fw_total_rcvd; + rstats->fw_total_fwd = rsp_rstats->fw_total_fwd; + rstats->fw_total_mcast = rsp_rstats->fw_total_mcast; + rstats->fw_total_bcast = rsp_rstats->fw_total_bcast; + rstats->fw_err_pko = rsp_rstats->fw_err_pko; + rstats->fw_err_link = rsp_rstats->fw_err_link; + rstats->fw_err_drop = rsp_rstats->fw_err_drop; + rstats->fw_rx_vxlan = rsp_rstats->fw_rx_vxlan; + rstats->fw_rx_vxlan_err = rsp_rstats->fw_rx_vxlan_err; + + /* Number of packets that are LROed */ + rstats->fw_lro_pkts = rsp_rstats->fw_lro_pkts; + /* Number of octets that are LROed */ + rstats->fw_lro_octs = rsp_rstats->fw_lro_octs; + /* Number of LRO packets formed */ + rstats->fw_total_lro = rsp_rstats->fw_total_lro; + /* Number of times lRO of packet aborted */ + rstats->fw_lro_aborts = rsp_rstats->fw_lro_aborts; + rstats->fw_lro_aborts_port = rsp_rstats->fw_lro_aborts_port; + rstats->fw_lro_aborts_seq = rsp_rstats->fw_lro_aborts_seq; + rstats->fw_lro_aborts_tsval = rsp_rstats->fw_lro_aborts_tsval; + rstats->fw_lro_aborts_timer = rsp_rstats->fw_lro_aborts_timer; + /* intrmod: packet forward rate */ + rstats->fwd_rate = rsp_rstats->fwd_rate; + + /* TX link-level stats */ + tstats->total_pkts_sent = rsp_tstats->total_pkts_sent; + tstats->total_bytes_sent = rsp_tstats->total_bytes_sent; + tstats->mcast_pkts_sent = rsp_tstats->mcast_pkts_sent; + tstats->bcast_pkts_sent = rsp_tstats->bcast_pkts_sent; + tstats->ctl_sent = rsp_tstats->ctl_sent; + /* Packets sent after one collision*/ + tstats->one_collision_sent = rsp_tstats->one_collision_sent; + /* Packets sent after multiple collision*/ + tstats->multi_collision_sent = rsp_tstats->multi_collision_sent; + /* Packets not sent due to max collisions */ + tstats->max_collision_fail = rsp_tstats->max_collision_fail; + /* Packets not sent due to max deferrals */ + tstats->max_deferral_fail = rsp_tstats->max_deferral_fail; + /* Accounts for over/under-run of buffers */ + tstats->fifo_err = rsp_tstats->fifo_err; + tstats->runts = rsp_tstats->runts; + /* Total number of collisions detected */ + tstats->total_collisions = rsp_tstats->total_collisions; + + /* firmware stats */ + tstats->fw_total_sent = rsp_tstats->fw_total_sent; + tstats->fw_total_fwd = rsp_tstats->fw_total_fwd; + tstats->fw_total_mcast_sent = rsp_tstats->fw_total_mcast_sent; + tstats->fw_total_bcast_sent = rsp_tstats->fw_total_bcast_sent; + tstats->fw_err_pko = rsp_tstats->fw_err_pko; + tstats->fw_err_pki = rsp_tstats->fw_err_pki; + tstats->fw_err_link = rsp_tstats->fw_err_link; + tstats->fw_err_drop = rsp_tstats->fw_err_drop; + tstats->fw_tso = rsp_tstats->fw_tso; + tstats->fw_tso_fwd = rsp_tstats->fw_tso_fwd; + tstats->fw_err_tso = rsp_tstats->fw_err_tso; + tstats->fw_tx_vxlan = rsp_tstats->fw_tx_vxlan; + + resp->status = 1; + } else { + resp->status = -1; + } + complete(&ctrl->complete); +} + +int octnet_get_link_stats(struct net_device *netdev) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct_dev = lio->oct_dev; + struct octeon_soft_command *sc; + struct oct_nic_stats_ctrl *ctrl; + struct oct_nic_stats_resp *resp; + int retval; + + /* Alloc soft command */ + sc = (struct octeon_soft_command *) + octeon_alloc_soft_command(oct_dev, + 0, + sizeof(struct oct_nic_stats_resp), + sizeof(struct octnic_ctrl_pkt)); + + if (!sc) + return -ENOMEM; + + resp = (struct oct_nic_stats_resp *)sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_stats_resp)); + + ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr; + memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl)); + ctrl->netdev = netdev; + init_completion(&ctrl->complete); + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, + OPCODE_NIC_PORT_STATS, 0, 0, 0); + + sc->callback = octnet_nic_stats_callback; + sc->callback_arg = sc; + sc->wait_time = 500; /*in milli seconds*/ + + retval = octeon_send_soft_command(oct_dev, sc); + if (retval == IQ_SEND_FAILED) { + octeon_free_soft_command(oct_dev, sc); + return -EINVAL; + } + + wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000)); + + if (resp->status != 1) { + octeon_free_soft_command(oct_dev, sc); + + return -EINVAL; + } + + octeon_free_soft_command(oct_dev, sc); + + return 0; +} + +static void liquidio_nic_seapi_ctl_callback(struct octeon_device *oct, + u32 status, + void *buf) +{ + struct liquidio_nic_seapi_ctl_context *ctx; + struct octeon_soft_command *sc = buf; + + ctx = sc->ctxptr; + + oct = lio_get_device(ctx->octeon_id); + if (status) { + dev_err(&oct->pci_dev->dev, "%s: instruction failed. Status: %llx\n", + __func__, + CVM_CAST64(status)); + } + ctx->status = status; + complete(&ctx->complete); +} + +int liquidio_set_speed(struct lio *lio, int speed) +{ + struct liquidio_nic_seapi_ctl_context *ctx; + struct octeon_device *oct = lio->oct_dev; + struct oct_nic_seapi_resp *resp; + struct octeon_soft_command *sc; + union octnet_cmd *ncmd; + u32 ctx_size; + int retval; + u32 var; + + if (oct->speed_setting == speed) + return 0; + + if (!OCTEON_CN23XX_PF(oct)) { + dev_err(&oct->pci_dev->dev, "%s: SET SPEED only for PF\n", + __func__); + return -EOPNOTSUPP; + } + + ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context); + sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, + sizeof(struct oct_nic_seapi_resp), + ctx_size); + if (!sc) + return -ENOMEM; + + ncmd = sc->virtdptr; + ctx = sc->ctxptr; + resp = sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); + + ctx->octeon_id = lio_get_device_id(oct); + ctx->status = 0; + init_completion(&ctx->complete); + + ncmd->u64 = 0; + ncmd->s.cmd = SEAPI_CMD_SPEED_SET; + ncmd->s.param1 = speed; + + octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3)); + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct, sc, OPCODE_NIC, + OPCODE_NIC_UBOOT_CTL, 0, 0, 0); + + sc->callback = liquidio_nic_seapi_ctl_callback; + sc->callback_arg = sc; + sc->wait_time = 5000; + + retval = octeon_send_soft_command(oct, sc); + if (retval == IQ_SEND_FAILED) { + dev_info(&oct->pci_dev->dev, "Failed to send soft command\n"); + retval = -EBUSY; + } else { + /* Wait for response or timeout */ + if (wait_for_completion_timeout(&ctx->complete, + msecs_to_jiffies(10000)) == 0) { + dev_err(&oct->pci_dev->dev, "%s: sc timeout\n", + __func__); + octeon_free_soft_command(oct, sc); + return -EINTR; + } + + retval = resp->status; + + if (retval) { + dev_err(&oct->pci_dev->dev, "%s failed, retval=%d\n", + __func__, retval); + octeon_free_soft_command(oct, sc); + return -EIO; + } + + var = be32_to_cpu((__force __be32)resp->speed); + if (var != speed) { + dev_err(&oct->pci_dev->dev, + "%s: setting failed speed= %x, expect %x\n", + __func__, var, speed); + } + + oct->speed_setting = var; + } + + octeon_free_soft_command(oct, sc); + + return retval; +} + +int liquidio_get_speed(struct lio *lio) +{ + struct liquidio_nic_seapi_ctl_context *ctx; + struct octeon_device *oct = lio->oct_dev; + struct oct_nic_seapi_resp *resp; + struct octeon_soft_command *sc; + union octnet_cmd *ncmd; + u32 ctx_size; + int retval; + + ctx_size = sizeof(struct liquidio_nic_seapi_ctl_context); + sc = octeon_alloc_soft_command(oct, OCTNET_CMD_SIZE, + sizeof(struct oct_nic_seapi_resp), + ctx_size); + if (!sc) + return -ENOMEM; + + ncmd = sc->virtdptr; + ctx = sc->ctxptr; + resp = sc->virtrptr; + memset(resp, 0, sizeof(struct oct_nic_seapi_resp)); + + ctx->octeon_id = lio_get_device_id(oct); + ctx->status = 0; + init_completion(&ctx->complete); + + ncmd->u64 = 0; + ncmd->s.cmd = SEAPI_CMD_SPEED_GET; + + octeon_swap_8B_data((u64 *)ncmd, (OCTNET_CMD_SIZE >> 3)); + + sc->iq_no = lio->linfo.txpciq[0].s.q_no; + + octeon_prepare_soft_command(oct, sc, OPCODE_NIC, + OPCODE_NIC_UBOOT_CTL, 0, 0, 0); + + sc->callback = liquidio_nic_seapi_ctl_callback; + sc->callback_arg = sc; + sc->wait_time = 5000; + + retval = octeon_send_soft_command(oct, sc); + if (retval == IQ_SEND_FAILED) { + dev_info(&oct->pci_dev->dev, "Failed to send soft command\n"); + oct->no_speed_setting = 1; + oct->speed_setting = 25; + + retval = -EBUSY; + } else { + if (wait_for_completion_timeout(&ctx->complete, + msecs_to_jiffies(10000)) == 0) { + dev_err(&oct->pci_dev->dev, "%s: sc timeout\n", + __func__); + + oct->speed_setting = 25; + oct->no_speed_setting = 1; + + octeon_free_soft_command(oct, sc); + + return -EINTR; + } + retval = resp->status; + if (retval) { + dev_err(&oct->pci_dev->dev, + "%s failed retval=%d\n", __func__, retval); + oct->no_speed_setting = 1; + oct->speed_setting = 25; + octeon_free_soft_command(oct, sc); + retval = -EIO; + } else { + u32 var; + + var = be32_to_cpu((__force __be32)resp->speed); + oct->speed_setting = var; + if (var == 0xffff) { + oct->no_speed_setting = 1; + /* unable to access boot variables + * get the default value based on the NIC type + */ + oct->speed_setting = 25; + } + } + } + + octeon_free_soft_command(oct, sc); + + return retval; +} diff --git a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c index 550ac29682a5..06f7449c569d 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_ethtool.c @@ -32,7 +32,6 @@ #include "cn23xx_vf_device.h" static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs); -static int octnet_get_link_stats(struct net_device *netdev); struct oct_intrmod_context { int octeon_id; @@ -96,11 +95,9 @@ static const char oct_stats_strings[][ETH_GSTRING_LEN] = { "tx_packets", "rx_bytes", "tx_bytes", - "rx_errors", /*jabber_err+l2_err+frame_err */ - "tx_errors", /*fw_err_pko+fw_err_link+fw_err_drop */ - "rx_dropped", /*st->fromwire.total_rcvd - st->fromwire.fw_total_rcvd + - *st->fromwire.dmac_drop + st->fromwire.fw_err_drop - */ + "rx_errors", + "tx_errors", + "rx_dropped", "tx_dropped", "tx_total_sent", @@ -115,14 +112,17 @@ static const char oct_stats_strings[][ETH_GSTRING_LEN] = { "tx_tso_err", "tx_vxlan", + "tx_mcast", + "tx_bcast", + "mac_tx_total_pkts", "mac_tx_total_bytes", "mac_tx_mcast_pkts", "mac_tx_bcast_pkts", - "mac_tx_ctl_packets", /*oct->link_stats.fromhost.ctl_sent */ + "mac_tx_ctl_packets", "mac_tx_total_collisions", "mac_tx_one_collision", - "mac_tx_multi_collison", + "mac_tx_multi_collision", "mac_tx_max_collision_fail", "mac_tx_max_deferal_fail", "mac_tx_fifo_err", @@ -130,6 +130,8 @@ static const char oct_stats_strings[][ETH_GSTRING_LEN] = { "rx_total_rcvd", "rx_total_fwd", + "rx_mcast", + "rx_bcast", "rx_jabber_err", "rx_l2_err", "rx_frame_err", @@ -170,17 +172,21 @@ static const char oct_vf_stats_strings[][ETH_GSTRING_LEN] = { "tx_packets", "rx_bytes", "tx_bytes", - "rx_errors", /* jabber_err + l2_err+frame_err */ - "tx_errors", /* fw_err_pko + fw_err_link+fw_err_drop */ - "rx_dropped", /* total_rcvd - fw_total_rcvd + dmac_drop + fw_err_drop */ + "rx_errors", + "tx_errors", + "rx_dropped", "tx_dropped", + "rx_mcast", + "tx_mcast", + "rx_bcast", + "tx_bcast", "link_state_changes", }; /* statistics of host tx queue */ static const char oct_iq_stats_strings[][ETH_GSTRING_LEN] = { - "packets", /*oct->instr_queue[iq_no]->stats.tx_done*/ - "bytes", /*oct->instr_queue[iq_no]->stats.tx_tot_bytes*/ + "packets", + "bytes", "dropped", "iq_busy", "sgentry_sent", @@ -197,13 +203,9 @@ static const char oct_iq_stats_strings[][ETH_GSTRING_LEN] = { /* statistics of host rx queue */ static const char oct_droq_stats_strings[][ETH_GSTRING_LEN] = { - "packets", /*oct->droq[oq_no]->stats.rx_pkts_received */ - "bytes", /*oct->droq[oq_no]->stats.rx_bytes_received */ - "dropped", /*oct->droq[oq_no]->stats.rx_dropped+ - *oct->droq[oq_no]->stats.dropped_nodispatch+ - *oct->droq[oq_no]->stats.dropped_toomany+ - *oct->droq[oq_no]->stats.dropped_nomem - */ + "packets", + "bytes", + "dropped", "dropped_nomem", "dropped_toomany", "fw_dropped", @@ -228,46 +230,147 @@ static int lio_get_link_ksettings(struct net_device *netdev, struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; struct oct_link_info *linfo; - u32 supported = 0, advertising = 0; linfo = &lio->linfo; + ethtool_link_ksettings_zero_link_mode(ecmd, supported); + ethtool_link_ksettings_zero_link_mode(ecmd, advertising); + switch (linfo->link.s.phy_type) { case LIO_PHY_PORT_TP: ecmd->base.port = PORT_TP; - supported = (SUPPORTED_10000baseT_Full | - SUPPORTED_TP | SUPPORTED_Pause); - advertising = (ADVERTISED_10000baseT_Full | ADVERTISED_Pause); ecmd->base.autoneg = AUTONEG_DISABLE; + ethtool_link_ksettings_add_link_mode(ecmd, supported, TP); + ethtool_link_ksettings_add_link_mode(ecmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(ecmd, supported, + 10000baseT_Full); + + ethtool_link_ksettings_add_link_mode(ecmd, advertising, Pause); + ethtool_link_ksettings_add_link_mode(ecmd, advertising, + 10000baseT_Full); + break; case LIO_PHY_PORT_FIBRE: - ecmd->base.port = PORT_FIBRE; - - if (linfo->link.s.speed == SPEED_10000) { - supported = SUPPORTED_10000baseT_Full; - advertising = ADVERTISED_10000baseT_Full; + if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI || + linfo->link.s.if_mode == INTERFACE_MODE_RXAUI || + linfo->link.s.if_mode == INTERFACE_MODE_XLAUI || + linfo->link.s.if_mode == INTERFACE_MODE_XFI) { + dev_dbg(&oct->pci_dev->dev, "ecmd->base.transceiver is XCVR_EXTERNAL\n"); + } else { + dev_err(&oct->pci_dev->dev, "Unknown link interface mode: %d\n", + linfo->link.s.if_mode); } - supported |= SUPPORTED_FIBRE | SUPPORTED_Pause; - advertising |= ADVERTISED_Pause; + ecmd->base.port = PORT_FIBRE; ecmd->base.autoneg = AUTONEG_DISABLE; + ethtool_link_ksettings_add_link_mode(ecmd, supported, FIBRE); + + ethtool_link_ksettings_add_link_mode(ecmd, supported, Pause); + ethtool_link_ksettings_add_link_mode(ecmd, advertising, Pause); + if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID || + oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) { + if (OCTEON_CN23XX_PF(oct)) { + ethtool_link_ksettings_add_link_mode + (ecmd, supported, 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, 25000baseCR_Full); + + if (oct->no_speed_setting == 0) { + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 10000baseCR_Full); + } + + if (oct->no_speed_setting == 0) + liquidio_get_speed(lio); + else + oct->speed_setting = 25; + + if (oct->speed_setting == 10) { + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 10000baseCR_Full); + } + if (oct->speed_setting == 25) { + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 25000baseCR_Full); + } + } else { /* VF */ + if (linfo->link.s.speed == 10000) { + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 10000baseCR_Full); + + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 10000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 10000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 10000baseCR_Full); + } + + if (linfo->link.s.speed == 25000) { + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, supported, + 25000baseCR_Full); + + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 25000baseSR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 25000baseKR_Full); + ethtool_link_ksettings_add_link_mode + (ecmd, advertising, + 25000baseCR_Full); + } + } + } else { + ethtool_link_ksettings_add_link_mode(ecmd, supported, + 10000baseT_Full); + ethtool_link_ksettings_add_link_mode(ecmd, advertising, + 10000baseT_Full); + } break; } - if (linfo->link.s.if_mode == INTERFACE_MODE_XAUI || - linfo->link.s.if_mode == INTERFACE_MODE_RXAUI || - linfo->link.s.if_mode == INTERFACE_MODE_XLAUI || - linfo->link.s.if_mode == INTERFACE_MODE_XFI) { - ethtool_convert_legacy_u32_to_link_mode( - ecmd->link_modes.supported, supported); - ethtool_convert_legacy_u32_to_link_mode( - ecmd->link_modes.advertising, advertising); - } else { - dev_err(&oct->pci_dev->dev, "Unknown link interface reported %d\n", - linfo->link.s.if_mode); - } - if (linfo->link.s.link_up) { ecmd->base.speed = linfo->link.s.speed; ecmd->base.duplex = linfo->link.s.duplex; @@ -279,6 +382,51 @@ static int lio_get_link_ksettings(struct net_device *netdev, return 0; } +static int lio_set_link_ksettings(struct net_device *netdev, + const struct ethtool_link_ksettings *ecmd) +{ + const int speed = ecmd->base.speed; + struct lio *lio = GET_LIO(netdev); + struct oct_link_info *linfo; + struct octeon_device *oct; + u32 is25G = 0; + + oct = lio->oct_dev; + + linfo = &lio->linfo; + + if (oct->subsystem_id == OCTEON_CN2350_25GB_SUBSYS_ID || + oct->subsystem_id == OCTEON_CN2360_25GB_SUBSYS_ID) { + is25G = 1; + } else { + return -EOPNOTSUPP; + } + + if (oct->no_speed_setting) { + dev_err(&oct->pci_dev->dev, "%s: Changing speed is not supported\n", + __func__); + return -EOPNOTSUPP; + } + + if ((ecmd->base.duplex != DUPLEX_UNKNOWN && + ecmd->base.duplex != linfo->link.s.duplex) || + ecmd->base.autoneg != AUTONEG_DISABLE || + (ecmd->base.speed != 10000 && ecmd->base.speed != 25000 && + ecmd->base.speed != SPEED_UNKNOWN)) + return -EOPNOTSUPP; + + if ((oct->speed_boot == speed / 1000) && + oct->speed_boot == oct->speed_setting) + return 0; + + liquidio_set_speed(lio, speed / 1000); + + dev_dbg(&oct->pci_dev->dev, "Port speed is set to %dG\n", + oct->speed_setting); + + return 0; +} + static void lio_get_drvinfo(struct net_device *netdev, struct ethtool_drvinfo *drvinfo) { @@ -359,7 +507,14 @@ lio_ethtool_get_channels(struct net_device *dev, rx_count = CFG_GET_NUM_RXQS_NIC_IF(conf6x, lio->ifidx); tx_count = CFG_GET_NUM_TXQS_NIC_IF(conf6x, lio->ifidx); } else if (OCTEON_CN23XX_PF(oct)) { - max_combined = lio->linfo.num_txpciq; + if (oct->sriov_info.sriov_enabled) { + max_combined = lio->linfo.num_txpciq; + } else { + struct octeon_config *conf23_pf = + CHIP_CONF(oct, cn23xx_pf); + + max_combined = CFG_GET_IQ_MAX_Q(conf23_pf); + } combined_count = oct->num_iqs; } else if (OCTEON_CN23XX_VF(oct)) { u64 reg_val = 0ULL; @@ -423,9 +578,15 @@ lio_irq_reallocate_irqs(struct octeon_device *oct, uint32_t num_ioqs) kfree(oct->irq_name_storage); oct->irq_name_storage = NULL; + + if (octeon_allocate_ioq_vector(oct, num_ioqs)) { + dev_err(&oct->pci_dev->dev, "OCTEON: ioq vector allocation failed\n"); + return -1; + } + if (octeon_setup_interrupt(oct, num_ioqs)) { dev_info(&oct->pci_dev->dev, "Setup interrupt failed\n"); - return 1; + return -1; } /* Enable Octeon device interrupts */ @@ -455,7 +616,16 @@ lio_ethtool_set_channels(struct net_device *dev, combined_count = channel->combined_count; if (OCTEON_CN23XX_PF(oct)) { - max_combined = channel->max_combined; + if (oct->sriov_info.sriov_enabled) { + max_combined = lio->linfo.num_txpciq; + } else { + struct octeon_config *conf23_pf = + CHIP_CONF(oct, + cn23xx_pf); + + max_combined = + CFG_GET_IQ_MAX_Q(conf23_pf); + } } else if (OCTEON_CN23XX_VF(oct)) { u64 reg_val = 0ULL; u64 ctrl = CN23XX_VF_SLI_IQ_PKT_CONTROL64(0); @@ -483,7 +653,6 @@ lio_ethtool_set_channels(struct net_device *dev, if (lio_reset_queues(dev, combined_count)) return -EINVAL; - lio_irq_reallocate_irqs(oct, combined_count); if (stopped) dev->netdev_ops->ndo_open(dev); @@ -822,12 +991,120 @@ lio_ethtool_get_ringparam(struct net_device *netdev, ering->rx_jumbo_max_pending = 0; } +static int lio_23xx_reconfigure_queue_count(struct lio *lio) +{ + struct octeon_device *oct = lio->oct_dev; + struct liquidio_if_cfg_context *ctx; + u32 resp_size, ctx_size, data_size; + struct liquidio_if_cfg_resp *resp; + struct octeon_soft_command *sc; + union oct_nic_if_cfg if_cfg; + struct lio_version *vdata; + u32 ifidx_or_pfnum; + int retval; + int j; + + resp_size = sizeof(struct liquidio_if_cfg_resp); + ctx_size = sizeof(struct liquidio_if_cfg_context); + data_size = sizeof(struct lio_version); + sc = (struct octeon_soft_command *) + octeon_alloc_soft_command(oct, data_size, + resp_size, ctx_size); + if (!sc) { + dev_err(&oct->pci_dev->dev, "%s: Failed to allocate soft command\n", + __func__); + return -1; + } + + resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; + ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; + vdata = (struct lio_version *)sc->virtdptr; + + vdata->major = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MAJOR_VERSION); + vdata->minor = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MINOR_VERSION); + vdata->micro = (__force u16)cpu_to_be16(LIQUIDIO_BASE_MICRO_VERSION); + + ifidx_or_pfnum = oct->pf_num; + WRITE_ONCE(ctx->cond, 0); + ctx->octeon_id = lio_get_device_id(oct); + init_waitqueue_head(&ctx->wc); + + if_cfg.u64 = 0; + if_cfg.s.num_iqueues = oct->sriov_info.num_pf_rings; + if_cfg.s.num_oqueues = oct->sriov_info.num_pf_rings; + if_cfg.s.base_queue = oct->sriov_info.pf_srn; + if_cfg.s.gmx_port_id = oct->pf_num; + + sc->iq_no = 0; + octeon_prepare_soft_command(oct, sc, OPCODE_NIC, + OPCODE_NIC_QCOUNT_UPDATE, 0, + if_cfg.u64, 0); + sc->callback = lio_if_cfg_callback; + sc->callback_arg = sc; + sc->wait_time = LIO_IFCFG_WAIT_TIME; + + retval = octeon_send_soft_command(oct, sc); + if (retval == IQ_SEND_FAILED) { + dev_err(&oct->pci_dev->dev, + "iq/oq config failed status: %x\n", + retval); + goto qcount_update_fail; + } + + if (sleep_cond(&ctx->wc, &ctx->cond) == -EINTR) { + dev_err(&oct->pci_dev->dev, "Wait interrupted\n"); + return -1; + } + + retval = resp->status; + if (retval) { + dev_err(&oct->pci_dev->dev, "iq/oq config failed\n"); + goto qcount_update_fail; + } + + octeon_swap_8B_data((u64 *)(&resp->cfg_info), + (sizeof(struct liquidio_if_cfg_info)) >> 3); + + lio->ifidx = ifidx_or_pfnum; + lio->linfo.num_rxpciq = hweight64(resp->cfg_info.iqmask); + lio->linfo.num_txpciq = hweight64(resp->cfg_info.iqmask); + for (j = 0; j < lio->linfo.num_rxpciq; j++) { + lio->linfo.rxpciq[j].u64 = + resp->cfg_info.linfo.rxpciq[j].u64; + } + + for (j = 0; j < lio->linfo.num_txpciq; j++) { + lio->linfo.txpciq[j].u64 = + resp->cfg_info.linfo.txpciq[j].u64; + } + + lio->linfo.hw_addr = resp->cfg_info.linfo.hw_addr; + lio->linfo.gmxport = resp->cfg_info.linfo.gmxport; + lio->linfo.link.u64 = resp->cfg_info.linfo.link.u64; + lio->txq = lio->linfo.txpciq[0].s.q_no; + lio->rxq = lio->linfo.rxpciq[0].s.q_no; + + octeon_free_soft_command(oct, sc); + dev_info(&oct->pci_dev->dev, "Queue count updated to %d\n", + lio->linfo.num_rxpciq); + + return 0; + +qcount_update_fail: + octeon_free_soft_command(oct, sc); + + return -1; +} + static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct = lio->oct_dev; + int i, queue_count_update = 0; struct napi_struct *napi, *n; - int i, update = 0; + int ret; + + schedule_timeout_uninterruptible(msecs_to_jiffies(100)); if (wait_for_pending_requests(oct)) dev_err(&oct->pci_dev->dev, "There were pending requests\n"); @@ -836,7 +1113,7 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) dev_err(&oct->pci_dev->dev, "IQ had pending instructions\n"); if (octeon_set_io_queues_off(oct)) { - dev_err(&oct->pci_dev->dev, "setting io queues off failed\n"); + dev_err(&oct->pci_dev->dev, "Setting io queues off failed\n"); return -1; } @@ -849,9 +1126,40 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) netif_napi_del(napi); if (num_qs != oct->num_iqs) { - netif_set_real_num_rx_queues(netdev, num_qs); - netif_set_real_num_tx_queues(netdev, num_qs); - update = 1; + ret = netif_set_real_num_rx_queues(netdev, num_qs); + if (ret) { + dev_err(&oct->pci_dev->dev, + "Setting real number rx failed\n"); + return ret; + } + + ret = netif_set_real_num_tx_queues(netdev, num_qs); + if (ret) { + dev_err(&oct->pci_dev->dev, + "Setting real number tx failed\n"); + return ret; + } + + /* The value of queue_count_update decides whether it is the + * queue count or the descriptor count that is being + * re-configured. + */ + queue_count_update = 1; + } + + /* Re-configuration of queues can happen in two scenarios, SRIOV enabled + * and SRIOV disabled. Few things like recreating queue zero, resetting + * glists and IRQs are required for both. For the latter, some more + * steps like updating sriov_info for the octeon device need to be done. + */ + if (queue_count_update) { + lio_delete_glists(lio); + + /* Delete mbox for PF which is SRIOV disabled because sriov_info + * will be now changed. + */ + if ((OCTEON_CN23XX_PF(oct)) && !oct->sriov_info.sriov_enabled) + oct->fn_list.free_mbox(oct); } for (i = 0; i < MAX_OCTEON_OUTPUT_QUEUES(oct); i++) { @@ -866,24 +1174,91 @@ static int lio_reset_queues(struct net_device *netdev, uint32_t num_qs) octeon_delete_instr_queue(oct, i); } + if (queue_count_update) { + /* For PF re-configure sriov related information */ + if ((OCTEON_CN23XX_PF(oct)) && + !oct->sriov_info.sriov_enabled) { + oct->sriov_info.num_pf_rings = num_qs; + if (cn23xx_sriov_config(oct)) { + dev_err(&oct->pci_dev->dev, + "Queue reset aborted: SRIOV config failed\n"); + return -1; + } + + num_qs = oct->sriov_info.num_pf_rings; + } + } + if (oct->fn_list.setup_device_regs(oct)) { dev_err(&oct->pci_dev->dev, "Failed to configure device registers\n"); return -1; } - if (liquidio_setup_io_queues(oct, 0, num_qs, num_qs)) { - dev_err(&oct->pci_dev->dev, "IO queues initialization failed\n"); - return -1; + /* The following are needed in case of queue count re-configuration and + * not for descriptor count re-configuration. + */ + if (queue_count_update) { + if (octeon_setup_instr_queues(oct)) + return -1; + + if (octeon_setup_output_queues(oct)) + return -1; + + /* Recreating mbox for PF that is SRIOV disabled */ + if (OCTEON_CN23XX_PF(oct) && !oct->sriov_info.sriov_enabled) { + if (oct->fn_list.setup_mbox(oct)) { + dev_err(&oct->pci_dev->dev, "Mailbox setup failed\n"); + return -1; + } + } + + /* Deleting and recreating IRQs whether the interface is SRIOV + * enabled or disabled. + */ + if (lio_irq_reallocate_irqs(oct, num_qs)) { + dev_err(&oct->pci_dev->dev, "IRQs could not be allocated\n"); + return -1; + } + + /* Enable the input and output queues for this Octeon device */ + if (oct->fn_list.enable_io_queues(oct)) { + dev_err(&oct->pci_dev->dev, "Failed to enable input/output queues\n"); + return -1; + } + + for (i = 0; i < oct->num_oqs; i++) + writel(oct->droq[i]->max_count, + oct->droq[i]->pkts_credit_reg); + + /* Informing firmware about the new queue count. It is required + * for firmware to allocate more number of queues than those at + * load time. + */ + if (OCTEON_CN23XX_PF(oct) && !oct->sriov_info.sriov_enabled) { + if (lio_23xx_reconfigure_queue_count(lio)) + return -1; + } } - /* Enable the input and output queues for this Octeon device */ - if (oct->fn_list.enable_io_queues(oct)) { - dev_err(&oct->pci_dev->dev, "Failed to enable input/output queues"); + /* Once firmware is aware of the new value, queues can be recreated */ + if (liquidio_setup_io_queues(oct, 0, num_qs, num_qs)) { + dev_err(&oct->pci_dev->dev, "I/O queues creation failed\n"); return -1; } - if (update && lio_send_queue_count_update(netdev, num_qs)) - return -1; + if (queue_count_update) { + if (lio_setup_glists(oct, lio, num_qs)) { + dev_err(&oct->pci_dev->dev, "Gather list allocation failed\n"); + return -1; + } + + /* Send firmware the information about new number of queues + * if the interface is a VF or a PF that is SRIOV enabled. + */ + if (oct->sriov_info.sriov_enabled || OCTEON_CN23XX_VF(oct)) + if (lio_send_queue_count_update(netdev, num_qs)) + return -1; + } return 0; } @@ -928,7 +1303,7 @@ static int lio_ethtool_set_ringparam(struct net_device *netdev, CFG_SET_NUM_RX_DESCS_NIC_IF(octeon_get_conf(oct), lio->ifidx, rx_count); - if (lio_reset_queues(netdev, lio->linfo.num_txpciq)) + if (lio_reset_queues(netdev, oct->num_iqs)) goto err_lio_reset_queues; if (stopped) @@ -1063,33 +1438,48 @@ lio_get_ethtool_stats(struct net_device *netdev, { struct lio *lio = GET_LIO(netdev); struct octeon_device *oct_dev = lio->oct_dev; - struct net_device_stats *netstats = &netdev->stats; + struct rtnl_link_stats64 lstats; int i = 0, j; if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) return; - netdev->netdev_ops->ndo_get_stats(netdev); - octnet_get_link_stats(netdev); - + netdev->netdev_ops->ndo_get_stats64(netdev, &lstats); /*sum of oct->droq[oq_no]->stats->rx_pkts_received */ - data[i++] = CVM_CAST64(netstats->rx_packets); + data[i++] = lstats.rx_packets; /*sum of oct->instr_queue[iq_no]->stats.tx_done */ - data[i++] = CVM_CAST64(netstats->tx_packets); + data[i++] = lstats.tx_packets; /*sum of oct->droq[oq_no]->stats->rx_bytes_received */ - data[i++] = CVM_CAST64(netstats->rx_bytes); + data[i++] = lstats.rx_bytes; /*sum of oct->instr_queue[iq_no]->stats.tx_tot_bytes */ - data[i++] = CVM_CAST64(netstats->tx_bytes); - data[i++] = CVM_CAST64(netstats->rx_errors); - data[i++] = CVM_CAST64(netstats->tx_errors); + data[i++] = lstats.tx_bytes; + data[i++] = lstats.rx_errors + + oct_dev->link_stats.fromwire.fcs_err + + oct_dev->link_stats.fromwire.jabber_err + + oct_dev->link_stats.fromwire.l2_err + + oct_dev->link_stats.fromwire.frame_err; + data[i++] = lstats.tx_errors; /*sum of oct->droq[oq_no]->stats->rx_dropped + *oct->droq[oq_no]->stats->dropped_nodispatch + *oct->droq[oq_no]->stats->dropped_toomany + *oct->droq[oq_no]->stats->dropped_nomem */ - data[i++] = CVM_CAST64(netstats->rx_dropped); + data[i++] = lstats.rx_dropped + + oct_dev->link_stats.fromwire.fifo_err + + oct_dev->link_stats.fromwire.dmac_drop + + oct_dev->link_stats.fromwire.red_drops + + oct_dev->link_stats.fromwire.fw_err_pko + + oct_dev->link_stats.fromwire.fw_err_link + + oct_dev->link_stats.fromwire.fw_err_drop; /*sum of oct->instr_queue[iq_no]->stats.tx_dropped */ - data[i++] = CVM_CAST64(netstats->tx_dropped); + data[i++] = lstats.tx_dropped + + oct_dev->link_stats.fromhost.max_collision_fail + + oct_dev->link_stats.fromhost.max_deferral_fail + + oct_dev->link_stats.fromhost.total_collisions + + oct_dev->link_stats.fromhost.fw_err_pko + + oct_dev->link_stats.fromhost.fw_err_link + + oct_dev->link_stats.fromhost.fw_err_drop + + oct_dev->link_stats.fromhost.fw_err_pki; /* firmware tx stats */ /*per_core_stats[cvmx_get_core_num()].link_stats[mdata->from_ifidx]. @@ -1124,6 +1514,10 @@ lio_get_ethtool_stats(struct net_device *netdev, */ data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.fw_tx_vxlan); + /* Multicast packets sent by this port */ + data[i++] = oct_dev->link_stats.fromhost.fw_total_mcast_sent; + data[i++] = oct_dev->link_stats.fromhost.fw_total_bcast_sent; + /* mac tx statistics */ /*CVMX_BGXX_CMRX_TX_STAT5 */ data[i++] = CVM_CAST64(oct_dev->link_stats.fromhost.total_pkts_sent); @@ -1160,6 +1554,9 @@ lio_get_ethtool_stats(struct net_device *netdev, *fw_total_fwd */ data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.fw_total_fwd); + /* Multicast packets received on this port */ + data[i++] = oct_dev->link_stats.fromwire.fw_total_mcast; + data[i++] = oct_dev->link_stats.fromwire.fw_total_bcast; /*per_core_stats[core_id].link_stats[ifidx].fromwire.jabber_err */ data[i++] = CVM_CAST64(oct_dev->link_stats.fromwire.jabber_err); /*per_core_stats[core_id].link_stats[ifidx].fromwire.l2_err */ @@ -1328,7 +1725,7 @@ static void lio_vf_get_ethtool_stats(struct net_device *netdev, __attribute__((unused)), u64 *data) { - struct net_device_stats *netstats = &netdev->stats; + struct rtnl_link_stats64 lstats; struct lio *lio = GET_LIO(netdev); struct octeon_device *oct_dev = lio->oct_dev; int i = 0, j, vj; @@ -1336,25 +1733,31 @@ static void lio_vf_get_ethtool_stats(struct net_device *netdev, if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) return; - netdev->netdev_ops->ndo_get_stats(netdev); + netdev->netdev_ops->ndo_get_stats64(netdev, &lstats); /* sum of oct->droq[oq_no]->stats->rx_pkts_received */ - data[i++] = CVM_CAST64(netstats->rx_packets); + data[i++] = lstats.rx_packets; /* sum of oct->instr_queue[iq_no]->stats.tx_done */ - data[i++] = CVM_CAST64(netstats->tx_packets); + data[i++] = lstats.tx_packets; /* sum of oct->droq[oq_no]->stats->rx_bytes_received */ - data[i++] = CVM_CAST64(netstats->rx_bytes); + data[i++] = lstats.rx_bytes; /* sum of oct->instr_queue[iq_no]->stats.tx_tot_bytes */ - data[i++] = CVM_CAST64(netstats->tx_bytes); - data[i++] = CVM_CAST64(netstats->rx_errors); - data[i++] = CVM_CAST64(netstats->tx_errors); + data[i++] = lstats.tx_bytes; + data[i++] = lstats.rx_errors; + data[i++] = lstats.tx_errors; /* sum of oct->droq[oq_no]->stats->rx_dropped + * oct->droq[oq_no]->stats->dropped_nodispatch + * oct->droq[oq_no]->stats->dropped_toomany + * oct->droq[oq_no]->stats->dropped_nomem */ - data[i++] = CVM_CAST64(netstats->rx_dropped); + data[i++] = lstats.rx_dropped; /* sum of oct->instr_queue[iq_no]->stats.tx_dropped */ - data[i++] = CVM_CAST64(netstats->tx_dropped); + data[i++] = lstats.tx_dropped; + + data[i++] = oct_dev->link_stats.fromwire.fw_total_mcast; + data[i++] = oct_dev->link_stats.fromhost.fw_total_mcast_sent; + data[i++] = oct_dev->link_stats.fromwire.fw_total_bcast; + data[i++] = oct_dev->link_stats.fromhost.fw_total_bcast_sent; + /* lio->link_changes */ data[i++] = CVM_CAST64(lio->link_changes); @@ -1765,161 +2168,6 @@ static int octnet_set_intrmod_cfg(struct lio *lio, return -EINTR; } -static void -octnet_nic_stats_callback(struct octeon_device *oct_dev, - u32 status, void *ptr) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)ptr; - struct oct_nic_stats_resp *resp = - (struct oct_nic_stats_resp *)sc->virtrptr; - struct oct_nic_stats_ctrl *ctrl = - (struct oct_nic_stats_ctrl *)sc->ctxptr; - struct nic_rx_stats *rsp_rstats = &resp->stats.fromwire; - struct nic_tx_stats *rsp_tstats = &resp->stats.fromhost; - - struct nic_rx_stats *rstats = &oct_dev->link_stats.fromwire; - struct nic_tx_stats *tstats = &oct_dev->link_stats.fromhost; - - if ((status != OCTEON_REQUEST_TIMEOUT) && !resp->status) { - octeon_swap_8B_data((u64 *)&resp->stats, - (sizeof(struct oct_link_stats)) >> 3); - - /* RX link-level stats */ - rstats->total_rcvd = rsp_rstats->total_rcvd; - rstats->bytes_rcvd = rsp_rstats->bytes_rcvd; - rstats->total_bcst = rsp_rstats->total_bcst; - rstats->total_mcst = rsp_rstats->total_mcst; - rstats->runts = rsp_rstats->runts; - rstats->ctl_rcvd = rsp_rstats->ctl_rcvd; - /* Accounts for over/under-run of buffers */ - rstats->fifo_err = rsp_rstats->fifo_err; - rstats->dmac_drop = rsp_rstats->dmac_drop; - rstats->fcs_err = rsp_rstats->fcs_err; - rstats->jabber_err = rsp_rstats->jabber_err; - rstats->l2_err = rsp_rstats->l2_err; - rstats->frame_err = rsp_rstats->frame_err; - - /* RX firmware stats */ - rstats->fw_total_rcvd = rsp_rstats->fw_total_rcvd; - rstats->fw_total_fwd = rsp_rstats->fw_total_fwd; - rstats->fw_err_pko = rsp_rstats->fw_err_pko; - rstats->fw_err_link = rsp_rstats->fw_err_link; - rstats->fw_err_drop = rsp_rstats->fw_err_drop; - rstats->fw_rx_vxlan = rsp_rstats->fw_rx_vxlan; - rstats->fw_rx_vxlan_err = rsp_rstats->fw_rx_vxlan_err; - - /* Number of packets that are LROed */ - rstats->fw_lro_pkts = rsp_rstats->fw_lro_pkts; - /* Number of octets that are LROed */ - rstats->fw_lro_octs = rsp_rstats->fw_lro_octs; - /* Number of LRO packets formed */ - rstats->fw_total_lro = rsp_rstats->fw_total_lro; - /* Number of times lRO of packet aborted */ - rstats->fw_lro_aborts = rsp_rstats->fw_lro_aborts; - rstats->fw_lro_aborts_port = rsp_rstats->fw_lro_aborts_port; - rstats->fw_lro_aborts_seq = rsp_rstats->fw_lro_aborts_seq; - rstats->fw_lro_aborts_tsval = rsp_rstats->fw_lro_aborts_tsval; - rstats->fw_lro_aborts_timer = rsp_rstats->fw_lro_aborts_timer; - /* intrmod: packet forward rate */ - rstats->fwd_rate = rsp_rstats->fwd_rate; - - /* TX link-level stats */ - tstats->total_pkts_sent = rsp_tstats->total_pkts_sent; - tstats->total_bytes_sent = rsp_tstats->total_bytes_sent; - tstats->mcast_pkts_sent = rsp_tstats->mcast_pkts_sent; - tstats->bcast_pkts_sent = rsp_tstats->bcast_pkts_sent; - tstats->ctl_sent = rsp_tstats->ctl_sent; - /* Packets sent after one collision*/ - tstats->one_collision_sent = rsp_tstats->one_collision_sent; - /* Packets sent after multiple collision*/ - tstats->multi_collision_sent = rsp_tstats->multi_collision_sent; - /* Packets not sent due to max collisions */ - tstats->max_collision_fail = rsp_tstats->max_collision_fail; - /* Packets not sent due to max deferrals */ - tstats->max_deferral_fail = rsp_tstats->max_deferral_fail; - /* Accounts for over/under-run of buffers */ - tstats->fifo_err = rsp_tstats->fifo_err; - tstats->runts = rsp_tstats->runts; - /* Total number of collisions detected */ - tstats->total_collisions = rsp_tstats->total_collisions; - - /* firmware stats */ - tstats->fw_total_sent = rsp_tstats->fw_total_sent; - tstats->fw_total_fwd = rsp_tstats->fw_total_fwd; - tstats->fw_err_pko = rsp_tstats->fw_err_pko; - tstats->fw_err_pki = rsp_tstats->fw_err_pki; - tstats->fw_err_link = rsp_tstats->fw_err_link; - tstats->fw_err_drop = rsp_tstats->fw_err_drop; - tstats->fw_tso = rsp_tstats->fw_tso; - tstats->fw_tso_fwd = rsp_tstats->fw_tso_fwd; - tstats->fw_err_tso = rsp_tstats->fw_err_tso; - tstats->fw_tx_vxlan = rsp_tstats->fw_tx_vxlan; - - resp->status = 1; - } else { - resp->status = -1; - } - complete(&ctrl->complete); -} - -/* Configure interrupt moderation parameters */ -static int octnet_get_link_stats(struct net_device *netdev) -{ - struct lio *lio = GET_LIO(netdev); - struct octeon_device *oct_dev = lio->oct_dev; - - struct octeon_soft_command *sc; - struct oct_nic_stats_ctrl *ctrl; - struct oct_nic_stats_resp *resp; - - int retval; - - /* Alloc soft command */ - sc = (struct octeon_soft_command *) - octeon_alloc_soft_command(oct_dev, - 0, - sizeof(struct oct_nic_stats_resp), - sizeof(struct octnic_ctrl_pkt)); - - if (!sc) - return -ENOMEM; - - resp = (struct oct_nic_stats_resp *)sc->virtrptr; - memset(resp, 0, sizeof(struct oct_nic_stats_resp)); - - ctrl = (struct oct_nic_stats_ctrl *)sc->ctxptr; - memset(ctrl, 0, sizeof(struct oct_nic_stats_ctrl)); - ctrl->netdev = netdev; - init_completion(&ctrl->complete); - - sc->iq_no = lio->linfo.txpciq[0].s.q_no; - - octeon_prepare_soft_command(oct_dev, sc, OPCODE_NIC, - OPCODE_NIC_PORT_STATS, 0, 0, 0); - - sc->callback = octnet_nic_stats_callback; - sc->callback_arg = sc; - sc->wait_time = 500; /*in milli seconds*/ - - retval = octeon_send_soft_command(oct_dev, sc); - if (retval == IQ_SEND_FAILED) { - octeon_free_soft_command(oct_dev, sc); - return -EINVAL; - } - - wait_for_completion_timeout(&ctrl->complete, msecs_to_jiffies(1000)); - - if (resp->status != 1) { - octeon_free_soft_command(oct_dev, sc); - - return -EINVAL; - } - - octeon_free_soft_command(oct_dev, sc); - - return 0; -} - static int lio_get_intr_coalesce(struct net_device *netdev, struct ethtool_coalesce *intr_coal) { @@ -2864,6 +3112,7 @@ static int lio_set_priv_flags(struct net_device *netdev, u32 flags) static const struct ethtool_ops lio_ethtool_ops = { .get_link_ksettings = lio_get_link_ksettings, + .set_link_ksettings = lio_set_link_ksettings, .get_link = ethtool_op_get_link, .get_drvinfo = lio_get_drvinfo, .get_ringparam = lio_ethtool_get_ringparam, diff --git a/drivers/net/ethernet/cavium/liquidio/lio_main.c b/drivers/net/ethernet/cavium/liquidio/lio_main.c index 603a144d3d9c..e500528ad751 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_main.c @@ -138,33 +138,10 @@ union tx_info { * by this structure in the NIC module. */ -#define OCTNIC_MAX_SG (MAX_SKB_FRAGS) - #define OCTNIC_GSO_MAX_HEADER_SIZE 128 #define OCTNIC_GSO_MAX_SIZE \ (CN23XX_DEFAULT_INPUT_JABBER - OCTNIC_GSO_MAX_HEADER_SIZE) -/** Structure of a node in list of gather components maintained by - * NIC driver for each network device. - */ -struct octnic_gather { - /** List manipulation. Next and prev pointers. */ - struct list_head list; - - /** Size of the gather component at sg in bytes. */ - int sg_size; - - /** Number of bytes that sg was adjusted to make it 8B-aligned. */ - int adjust; - - /** Gather component that can accommodate max sized fragment list - * received from the IP layer. - */ - struct octeon_sg_entry *sg; - - dma_addr_t sg_dma_ptr; -}; - struct handshake { struct completion init; struct completion started; @@ -520,7 +497,7 @@ static void liquidio_deinit_pci(void) */ static inline int check_txq_status(struct lio *lio) { - int numqs = lio->netdev->num_tx_queues; + int numqs = lio->netdev->real_num_tx_queues; int ret_val = 0; int q, iq; @@ -542,148 +519,6 @@ static inline int check_txq_status(struct lio *lio) } /** - * Remove the node at the head of the list. The list would be empty at - * the end of this call if there are no more nodes in the list. - */ -static inline struct list_head *list_delete_head(struct list_head *root) -{ - struct list_head *node; - - if ((root->prev == root) && (root->next == root)) - node = NULL; - else - node = root->next; - - if (node) - list_del(node); - - return node; -} - -/** - * \brief Delete gather lists - * @param lio per-network private data - */ -static void delete_glists(struct lio *lio) -{ - struct octnic_gather *g; - int i; - - kfree(lio->glist_lock); - lio->glist_lock = NULL; - - if (!lio->glist) - return; - - for (i = 0; i < lio->linfo.num_txpciq; i++) { - do { - g = (struct octnic_gather *) - list_delete_head(&lio->glist[i]); - if (g) - kfree(g); - } while (g); - - if (lio->glists_virt_base && lio->glists_virt_base[i] && - lio->glists_dma_base && lio->glists_dma_base[i]) { - lio_dma_free(lio->oct_dev, - lio->glist_entry_size * lio->tx_qsize, - lio->glists_virt_base[i], - lio->glists_dma_base[i]); - } - } - - kfree(lio->glists_virt_base); - lio->glists_virt_base = NULL; - - kfree(lio->glists_dma_base); - lio->glists_dma_base = NULL; - - kfree(lio->glist); - lio->glist = NULL; -} - -/** - * \brief Setup gather lists - * @param lio per-network private data - */ -static int setup_glists(struct octeon_device *oct, struct lio *lio, int num_iqs) -{ - int i, j; - struct octnic_gather *g; - - lio->glist_lock = kcalloc(num_iqs, sizeof(*lio->glist_lock), - GFP_KERNEL); - if (!lio->glist_lock) - return -ENOMEM; - - lio->glist = kcalloc(num_iqs, sizeof(*lio->glist), - GFP_KERNEL); - if (!lio->glist) { - kfree(lio->glist_lock); - lio->glist_lock = NULL; - return -ENOMEM; - } - - lio->glist_entry_size = - ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE); - - /* allocate memory to store virtual and dma base address of - * per glist consistent memory - */ - lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base), - GFP_KERNEL); - lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base), - GFP_KERNEL); - - if (!lio->glists_virt_base || !lio->glists_dma_base) { - delete_glists(lio); - return -ENOMEM; - } - - for (i = 0; i < num_iqs; i++) { - int numa_node = dev_to_node(&oct->pci_dev->dev); - - spin_lock_init(&lio->glist_lock[i]); - - INIT_LIST_HEAD(&lio->glist[i]); - - lio->glists_virt_base[i] = - lio_dma_alloc(oct, - lio->glist_entry_size * lio->tx_qsize, - &lio->glists_dma_base[i]); - - if (!lio->glists_virt_base[i]) { - delete_glists(lio); - return -ENOMEM; - } - - for (j = 0; j < lio->tx_qsize; j++) { - g = kzalloc_node(sizeof(*g), GFP_KERNEL, - numa_node); - if (!g) - g = kzalloc(sizeof(*g), GFP_KERNEL); - if (!g) - break; - - g->sg = lio->glists_virt_base[i] + - (j * lio->glist_entry_size); - - g->sg_dma_ptr = lio->glists_dma_base[i] + - (j * lio->glist_entry_size); - - list_add_tail(&g->list, &lio->glist[i]); - } - - if (j != lio->tx_qsize) { - delete_glists(lio); - return -ENOMEM; - } - } - - return 0; -} - -/** * \brief Print link information * @param netdev network device */ @@ -1077,6 +912,9 @@ liquidio_probe(struct pci_dev *pdev, /* set linux specific device pointer */ oct_dev->pci_dev = (void *)pdev; + oct_dev->subsystem_id = pdev->subsystem_vendor | + (pdev->subsystem_device << 16); + hs = &handshake[oct_dev->octeon_id]; init_completion(&hs->init); init_completion(&hs->started); @@ -1471,7 +1309,7 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) cleanup_rx_oom_poll_fn(netdev); - delete_glists(lio); + lio_delete_glists(lio); free_netdev(netdev); @@ -1686,7 +1524,7 @@ static void free_netsgbuf(void *buf) i++; } - iq = skb_iq(lio, skb); + iq = skb_iq(lio->oct_dev, skb); spin_lock(&lio->glist_lock[iq]); list_add_tail(&g->list, &lio->glist[iq]); spin_unlock(&lio->glist_lock[iq]); @@ -1729,7 +1567,7 @@ static void free_netsgbuf_with_resp(void *buf) i++; } - iq = skb_iq(lio, skb); + iq = skb_iq(lio->oct_dev, skb); spin_lock(&lio->glist_lock[iq]); list_add_tail(&g->list, &lio->glist[iq]); @@ -1942,39 +1780,6 @@ static int load_firmware(struct octeon_device *oct) } /** - * \brief Callback for getting interface configuration - * @param status status of request - * @param buf pointer to resp structure - */ -static void if_cfg_callback(struct octeon_device *oct, - u32 status __attribute__((unused)), - void *buf) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - struct liquidio_if_cfg_resp *resp; - struct liquidio_if_cfg_context *ctx; - - resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; - - oct = lio_get_device(ctx->octeon_id); - if (resp->status) - dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: 0x%llx (0x%08x)\n", - CVM_CAST64(resp->status), status); - WRITE_ONCE(ctx->cond, 1); - - snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s", - resp->cfg_info.liquidio_firmware_version); - - /* This barrier is required to be sure that the response has been - * written fully before waking up the handler - */ - wmb(); - - wake_up_interruptible(&ctx->wc); -} - -/** * \brief Poll routine for checking transmit queue status * @param work work_struct data structure */ @@ -2049,11 +1854,6 @@ static int liquidio_open(struct net_device *netdev) ifstate_set(lio, LIO_IFSTATE_RUNNING); - /* Ready for link status updates */ - lio->intf_open = 1; - - netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n"); - if (OCTEON_CN23XX_PF(oct)) { if (!oct->msix_on) if (setup_tx_poll_fn(netdev)) @@ -2063,7 +1863,12 @@ static int liquidio_open(struct net_device *netdev) return -1; } - start_txqs(netdev); + netif_tx_start_all_queues(netdev); + + /* Ready for link status updates */ + lio->intf_open = 1; + + netif_info(lio, ifup, lio->netdev, "Interface Open, ready for traffic\n"); /* tell Octeon to start forwarding packets to host */ send_rx_ctrl_cmd(lio, 1); @@ -2086,11 +1891,15 @@ static int liquidio_stop(struct net_device *netdev) ifstate_reset(lio, LIO_IFSTATE_RUNNING); - netif_tx_disable(netdev); + /* Stop any link updates */ + lio->intf_open = 0; + + stop_txqs(netdev); /* Inform that netif carrier is down */ netif_carrier_off(netdev); - lio->intf_open = 0; + netif_tx_disable(netdev); + lio->linfo.link.s.link_up = 0; lio->link_changes++; @@ -2252,14 +2061,11 @@ static int liquidio_set_mac(struct net_device *netdev, void *p) return 0; } -/** - * \brief Net device get_stats - * @param netdev network device - */ -static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) +static void +liquidio_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *lstats) { struct lio *lio = GET_LIO(netdev); - struct net_device_stats *stats = &netdev->stats; struct octeon_device *oct; u64 pkts = 0, drop = 0, bytes = 0; struct oct_droq_stats *oq_stats; @@ -2269,7 +2075,7 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) oct = lio->oct_dev; if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) - return stats; + return; for (i = 0; i < oct->num_iqs; i++) { iq_no = lio->linfo.txpciq[i].s.q_no; @@ -2279,9 +2085,9 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) bytes += iq_stats->tx_tot_bytes; } - stats->tx_packets = pkts; - stats->tx_bytes = bytes; - stats->tx_dropped = drop; + lstats->tx_packets = pkts; + lstats->tx_bytes = bytes; + lstats->tx_dropped = drop; pkts = 0; drop = 0; @@ -2298,11 +2104,34 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) bytes += oq_stats->rx_bytes_received; } - stats->rx_bytes = bytes; - stats->rx_packets = pkts; - stats->rx_dropped = drop; - - return stats; + lstats->rx_bytes = bytes; + lstats->rx_packets = pkts; + lstats->rx_dropped = drop; + + octnet_get_link_stats(netdev); + lstats->multicast = oct->link_stats.fromwire.fw_total_mcast; + lstats->collisions = oct->link_stats.fromhost.total_collisions; + + /* detailed rx_errors: */ + lstats->rx_length_errors = oct->link_stats.fromwire.l2_err; + /* recved pkt with crc error */ + lstats->rx_crc_errors = oct->link_stats.fromwire.fcs_err; + /* recv'd frame alignment error */ + lstats->rx_frame_errors = oct->link_stats.fromwire.frame_err; + /* recv'r fifo overrun */ + lstats->rx_fifo_errors = oct->link_stats.fromwire.fifo_err; + + lstats->rx_errors = lstats->rx_length_errors + lstats->rx_crc_errors + + lstats->rx_frame_errors + lstats->rx_fifo_errors; + + /* detailed tx_errors */ + lstats->tx_aborted_errors = oct->link_stats.fromhost.fw_err_pko; + lstats->tx_carrier_errors = oct->link_stats.fromhost.fw_err_link; + lstats->tx_fifo_errors = oct->link_stats.fromhost.fifo_err; + + lstats->tx_errors = lstats->tx_aborted_errors + + lstats->tx_carrier_errors + + lstats->tx_fifo_errors; } /** @@ -2510,7 +2339,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) lio = GET_LIO(netdev); oct = lio->oct_dev; - q_idx = skb_iq(lio, skb); + q_idx = skb_iq(oct, skb); tag = q_idx; iq_no = lio->linfo.txpciq[q_idx].s.q_no; @@ -2585,6 +2414,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) if (dma_mapping_error(&oct->pci_dev->dev, dptr)) { dev_err(&oct->pci_dev->dev, "%s DMA mapping error 1\n", __func__); + stats->tx_dmamap_fail++; return NETDEV_TX_BUSY; } @@ -2602,7 +2432,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) spin_lock(&lio->glist_lock[q_idx]); g = (struct octnic_gather *) - list_delete_head(&lio->glist[q_idx]); + lio_list_delete_head(&lio->glist[q_idx]); spin_unlock(&lio->glist_lock[q_idx]); if (!g) { @@ -2624,6 +2454,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) if (dma_mapping_error(&oct->pci_dev->dev, g->sg[0].ptr[0])) { dev_err(&oct->pci_dev->dev, "%s DMA mapping error 2\n", __func__); + stats->tx_dmamap_fail++; return NETDEV_TX_BUSY; } add_sg_size(&g->sg[0], (skb->len - skb->data_len), 0); @@ -3324,11 +3155,36 @@ static const struct switchdev_ops lio_pf_switchdev_ops = { .switchdev_port_attr_get = lio_pf_switchdev_attr_get, }; +static int liquidio_get_vf_stats(struct net_device *netdev, int vfidx, + struct ifla_vf_stats *vf_stats) +{ + struct lio *lio = GET_LIO(netdev); + struct octeon_device *oct = lio->oct_dev; + struct oct_vf_stats stats; + int ret; + + if (vfidx < 0 || vfidx >= oct->sriov_info.num_vfs_alloced) + return -EINVAL; + + memset(&stats, 0, sizeof(struct oct_vf_stats)); + ret = cn23xx_get_vf_stats(oct, vfidx, &stats); + if (!ret) { + vf_stats->rx_packets = stats.rx_packets; + vf_stats->tx_packets = stats.tx_packets; + vf_stats->rx_bytes = stats.rx_bytes; + vf_stats->tx_bytes = stats.tx_bytes; + vf_stats->broadcast = stats.broadcast; + vf_stats->multicast = stats.multicast; + } + + return ret; +} + static const struct net_device_ops lionetdevops = { .ndo_open = liquidio_open, .ndo_stop = liquidio_stop, .ndo_start_xmit = liquidio_xmit, - .ndo_get_stats = liquidio_get_stats, + .ndo_get_stats64 = liquidio_get_stats64, .ndo_set_mac_address = liquidio_set_mac, .ndo_set_rx_mode = liquidio_set_mcast_list, .ndo_tx_timeout = liquidio_tx_timeout, @@ -3346,6 +3202,7 @@ static const struct net_device_ops lionetdevops = { .ndo_get_vf_config = liquidio_get_vf_config, .ndo_set_vf_trust = liquidio_set_vf_trust, .ndo_set_vf_link_state = liquidio_set_vf_link_state, + .ndo_get_vf_stats = liquidio_get_vf_stats, }; /** \brief Entry point for the liquidio module @@ -3448,6 +3305,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) struct liquidio_if_cfg_resp *resp; struct octdev_props *props; int retval, num_iqueues, num_oqueues; + int max_num_queues = 0; union oct_nic_if_cfg if_cfg; unsigned int base_queue; unsigned int gmx_port_id; @@ -3528,9 +3386,9 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) OPCODE_NIC_IF_CFG, 0, if_cfg.u64, 0); - sc->callback = if_cfg_callback; + sc->callback = lio_if_cfg_callback; sc->callback_arg = sc; - sc->wait_time = 3000; + sc->wait_time = LIO_IFCFG_WAIT_TIME; retval = octeon_send_soft_command(octeon_dev, sc); if (retval == IQ_SEND_FAILED) { @@ -3584,11 +3442,20 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) resp->cfg_info.oqmask); goto setup_nic_dev_fail; } + + if (OCTEON_CN6XXX(octeon_dev)) { + max_num_queues = CFG_GET_IQ_MAX_Q(CHIP_CONF(octeon_dev, + cn6xxx)); + } else if (OCTEON_CN23XX_PF(octeon_dev)) { + max_num_queues = CFG_GET_IQ_MAX_Q(CHIP_CONF(octeon_dev, + cn23xx_pf)); + } + dev_dbg(&octeon_dev->pci_dev->dev, - "interface %d, iqmask %016llx, oqmask %016llx, numiqueues %d, numoqueues %d\n", + "interface %d, iqmask %016llx, oqmask %016llx, numiqueues %d, numoqueues %d max_num_queues: %d\n", i, resp->cfg_info.iqmask, resp->cfg_info.oqmask, - num_iqueues, num_oqueues); - netdev = alloc_etherdev_mq(LIO_SIZE, num_iqueues); + num_iqueues, num_oqueues, max_num_queues); + netdev = alloc_etherdev_mq(LIO_SIZE, max_num_queues); if (!netdev) { dev_err(&octeon_dev->pci_dev->dev, "Device allocation failed\n"); @@ -3603,6 +3470,20 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) netdev->netdev_ops = &lionetdevops; SWITCHDEV_SET_OPS(netdev, &lio_pf_switchdev_ops); + retval = netif_set_real_num_rx_queues(netdev, num_oqueues); + if (retval) { + dev_err(&octeon_dev->pci_dev->dev, + "setting real number rx failed\n"); + goto setup_nic_dev_fail; + } + + retval = netif_set_real_num_tx_queues(netdev, num_iqueues); + if (retval) { + dev_err(&octeon_dev->pci_dev->dev, + "setting real number tx failed\n"); + goto setup_nic_dev_fail; + } + lio = GET_LIO(netdev); memset(lio, 0, sizeof(struct lio)); @@ -3724,7 +3605,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio->tx_qsize = octeon_get_tx_qsize(octeon_dev, lio->txq); lio->rx_qsize = octeon_get_rx_qsize(octeon_dev, lio->rxq); - if (setup_glists(octeon_dev, lio, num_iqueues)) { + if (lio_setup_glists(octeon_dev, lio, num_iqueues)) { dev_err(&octeon_dev->pci_dev->dev, "Gather list allocation failed\n"); goto setup_nic_dev_fail; @@ -3786,6 +3667,23 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) "NIC ifidx:%d Setup successful\n", i); octeon_free_soft_command(octeon_dev, sc); + + if (octeon_dev->subsystem_id == + OCTEON_CN2350_25GB_SUBSYS_ID || + octeon_dev->subsystem_id == + OCTEON_CN2360_25GB_SUBSYS_ID) { + liquidio_get_speed(lio); + + if (octeon_dev->speed_setting == 0) { + octeon_dev->speed_setting = 25; + octeon_dev->no_speed_setting = 1; + } + } else { + octeon_dev->no_speed_setting = 1; + octeon_dev->speed_setting = 10; + } + octeon_dev->speed_boot = octeon_dev->speed_setting; + } devlink = devlink_alloc(&liquidio_devlink_ops, @@ -4223,7 +4121,9 @@ static int octeon_device_init(struct octeon_device *octeon_dev) } atomic_set(&octeon_dev->status, OCT_DEV_MBOX_SETUP_DONE); - if (octeon_allocate_ioq_vector(octeon_dev)) { + if (octeon_allocate_ioq_vector + (octeon_dev, + octeon_dev->sriov_info.num_pf_rings)) { dev_err(&octeon_dev->pci_dev->dev, "OCTEON: ioq vector allocation failed\n"); return 1; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c index f92dfa411de6..7fa0212873ac 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_main.c @@ -69,30 +69,10 @@ union tx_info { } s; }; -#define OCTNIC_MAX_SG (MAX_SKB_FRAGS) - #define OCTNIC_GSO_MAX_HEADER_SIZE 128 #define OCTNIC_GSO_MAX_SIZE \ (CN23XX_DEFAULT_INPUT_JABBER - OCTNIC_GSO_MAX_HEADER_SIZE) -struct octnic_gather { - /* List manipulation. Next and prev pointers. */ - struct list_head list; - - /* Size of the gather component at sg in bytes. */ - int sg_size; - - /* Number of bytes that sg was adjusted to make it 8B-aligned. */ - int adjust; - - /* Gather component that can accommodate max sized fragment list - * received from the IP layer. - */ - struct octeon_sg_entry *sg; - - dma_addr_t sg_dma_ptr; -}; - static int liquidio_vf_probe(struct pci_dev *pdev, const struct pci_device_id *ent); static void liquidio_vf_remove(struct pci_dev *pdev); @@ -285,142 +265,6 @@ static struct pci_driver liquidio_vf_pci_driver = { }; /** - * Remove the node at the head of the list. The list would be empty at - * the end of this call if there are no more nodes in the list. - */ -static struct list_head *list_delete_head(struct list_head *root) -{ - struct list_head *node; - - if ((root->prev == root) && (root->next == root)) - node = NULL; - else - node = root->next; - - if (node) - list_del(node); - - return node; -} - -/** - * \brief Delete gather lists - * @param lio per-network private data - */ -static void delete_glists(struct lio *lio) -{ - struct octnic_gather *g; - int i; - - kfree(lio->glist_lock); - lio->glist_lock = NULL; - - if (!lio->glist) - return; - - for (i = 0; i < lio->linfo.num_txpciq; i++) { - do { - g = (struct octnic_gather *) - list_delete_head(&lio->glist[i]); - kfree(g); - } while (g); - - if (lio->glists_virt_base && lio->glists_virt_base[i] && - lio->glists_dma_base && lio->glists_dma_base[i]) { - lio_dma_free(lio->oct_dev, - lio->glist_entry_size * lio->tx_qsize, - lio->glists_virt_base[i], - lio->glists_dma_base[i]); - } - } - - kfree(lio->glists_virt_base); - lio->glists_virt_base = NULL; - - kfree(lio->glists_dma_base); - lio->glists_dma_base = NULL; - - kfree(lio->glist); - lio->glist = NULL; -} - -/** - * \brief Setup gather lists - * @param lio per-network private data - */ -static int setup_glists(struct lio *lio, int num_iqs) -{ - struct octnic_gather *g; - int i, j; - - lio->glist_lock = - kzalloc(sizeof(*lio->glist_lock) * num_iqs, GFP_KERNEL); - if (!lio->glist_lock) - return -ENOMEM; - - lio->glist = - kzalloc(sizeof(*lio->glist) * num_iqs, GFP_KERNEL); - if (!lio->glist) { - kfree(lio->glist_lock); - lio->glist_lock = NULL; - return -ENOMEM; - } - - lio->glist_entry_size = - ROUNDUP8((ROUNDUP4(OCTNIC_MAX_SG) >> 2) * OCT_SG_ENTRY_SIZE); - - /* allocate memory to store virtual and dma base address of - * per glist consistent memory - */ - lio->glists_virt_base = kcalloc(num_iqs, sizeof(*lio->glists_virt_base), - GFP_KERNEL); - lio->glists_dma_base = kcalloc(num_iqs, sizeof(*lio->glists_dma_base), - GFP_KERNEL); - - if (!lio->glists_virt_base || !lio->glists_dma_base) { - delete_glists(lio); - return -ENOMEM; - } - - for (i = 0; i < num_iqs; i++) { - spin_lock_init(&lio->glist_lock[i]); - - INIT_LIST_HEAD(&lio->glist[i]); - - lio->glists_virt_base[i] = - lio_dma_alloc(lio->oct_dev, - lio->glist_entry_size * lio->tx_qsize, - &lio->glists_dma_base[i]); - - if (!lio->glists_virt_base[i]) { - delete_glists(lio); - return -ENOMEM; - } - - for (j = 0; j < lio->tx_qsize; j++) { - g = kzalloc(sizeof(*g), GFP_KERNEL); - if (!g) - break; - - g->sg = lio->glists_virt_base[i] + - (j * lio->glist_entry_size); - - g->sg_dma_ptr = lio->glists_dma_base[i] + - (j * lio->glist_entry_size); - - list_add_tail(&g->list, &lio->glist[i]); - } - - if (j != lio->tx_qsize) { - delete_glists(lio); - return -ENOMEM; - } - } - - return 0; -} - -/** * \brief Print link information * @param netdev network device */ @@ -567,6 +411,9 @@ liquidio_vf_probe(struct pci_dev *pdev, /* set linux specific device pointer */ oct_dev->pci_dev = pdev; + oct_dev->subsystem_id = pdev->subsystem_vendor | + (pdev->subsystem_device << 16); + if (octeon_device_init(oct_dev)) { liquidio_vf_remove(pdev); return -ENOMEM; @@ -856,7 +703,7 @@ static void liquidio_destroy_nic_device(struct octeon_device *oct, int ifidx) cleanup_link_status_change_wq(netdev); - delete_glists(lio); + lio_delete_glists(lio); free_netdev(netdev); @@ -1005,7 +852,7 @@ static void free_netsgbuf(void *buf) i++; } - iq = skb_iq(lio, skb); + iq = skb_iq(lio->oct_dev, skb); spin_lock(&lio->glist_lock[iq]); list_add_tail(&g->list, &lio->glist[iq]); @@ -1049,7 +896,7 @@ static void free_netsgbuf_with_resp(void *buf) i++; } - iq = skb_iq(lio, skb); + iq = skb_iq(lio->oct_dev, skb); spin_lock(&lio->glist_lock[iq]); list_add_tail(&g->list, &lio->glist[iq]); @@ -1059,38 +906,6 @@ static void free_netsgbuf_with_resp(void *buf) } /** - * \brief Callback for getting interface configuration - * @param status status of request - * @param buf pointer to resp structure - */ -static void if_cfg_callback(struct octeon_device *oct, - u32 status __attribute__((unused)), void *buf) -{ - struct octeon_soft_command *sc = (struct octeon_soft_command *)buf; - struct liquidio_if_cfg_context *ctx; - struct liquidio_if_cfg_resp *resp; - - resp = (struct liquidio_if_cfg_resp *)sc->virtrptr; - ctx = (struct liquidio_if_cfg_context *)sc->ctxptr; - - oct = lio_get_device(ctx->octeon_id); - if (resp->status) - dev_err(&oct->pci_dev->dev, "nic if cfg instruction failed. Status: %llx\n", - CVM_CAST64(resp->status)); - WRITE_ONCE(ctx->cond, 1); - - snprintf(oct->fw_info.liquidio_firmware_version, 32, "%s", - resp->cfg_info.liquidio_firmware_version); - - /* This barrier is required to be sure that the response has been - * written fully before waking up the handler - */ - wmb(); - - wake_up_interruptible(&ctx->wc); -} - -/** * \brief Net device open for LiquidIO * @param netdev network device */ @@ -1336,24 +1151,21 @@ static int liquidio_set_mac(struct net_device *netdev, void *p) return 0; } -/** - * \brief Net device get_stats - * @param netdev network device - */ -static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) +static void +liquidio_get_stats64(struct net_device *netdev, + struct rtnl_link_stats64 *lstats) { struct lio *lio = GET_LIO(netdev); - struct net_device_stats *stats = &netdev->stats; + struct octeon_device *oct; u64 pkts = 0, drop = 0, bytes = 0; struct oct_droq_stats *oq_stats; struct oct_iq_stats *iq_stats; - struct octeon_device *oct; int i, iq_no, oq_no; oct = lio->oct_dev; if (ifstate_check(lio, LIO_IFSTATE_RESETTING)) - return stats; + return; for (i = 0; i < oct->num_iqs; i++) { iq_no = lio->linfo.txpciq[i].s.q_no; @@ -1363,9 +1175,9 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) bytes += iq_stats->tx_tot_bytes; } - stats->tx_packets = pkts; - stats->tx_bytes = bytes; - stats->tx_dropped = drop; + lstats->tx_packets = pkts; + lstats->tx_bytes = bytes; + lstats->tx_dropped = drop; pkts = 0; drop = 0; @@ -1382,11 +1194,29 @@ static struct net_device_stats *liquidio_get_stats(struct net_device *netdev) bytes += oq_stats->rx_bytes_received; } - stats->rx_bytes = bytes; - stats->rx_packets = pkts; - stats->rx_dropped = drop; + lstats->rx_bytes = bytes; + lstats->rx_packets = pkts; + lstats->rx_dropped = drop; + + octnet_get_link_stats(netdev); + lstats->multicast = oct->link_stats.fromwire.fw_total_mcast; + + /* detailed rx_errors: */ + lstats->rx_length_errors = oct->link_stats.fromwire.l2_err; + /* recved pkt with crc error */ + lstats->rx_crc_errors = oct->link_stats.fromwire.fcs_err; + /* recv'd frame alignment error */ + lstats->rx_frame_errors = oct->link_stats.fromwire.frame_err; - return stats; + lstats->rx_errors = lstats->rx_length_errors + lstats->rx_crc_errors + + lstats->rx_frame_errors; + + /* detailed tx_errors */ + lstats->tx_aborted_errors = oct->link_stats.fromhost.fw_err_pko; + lstats->tx_carrier_errors = oct->link_stats.fromhost.fw_err_link; + + lstats->tx_errors = lstats->tx_aborted_errors + + lstats->tx_carrier_errors; } /** @@ -1580,7 +1410,7 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) lio = GET_LIO(netdev); oct = lio->oct_dev; - q_idx = skb_iq(lio, skb); + q_idx = skb_iq(lio->oct_dev, skb); tag = q_idx; iq_no = lio->linfo.txpciq[q_idx].s.q_no; @@ -1661,8 +1491,8 @@ static int liquidio_xmit(struct sk_buff *skb, struct net_device *netdev) int i, frags; spin_lock(&lio->glist_lock[q_idx]); - g = (struct octnic_gather *)list_delete_head( - &lio->glist[q_idx]); + g = (struct octnic_gather *) + lio_list_delete_head(&lio->glist[q_idx]); spin_unlock(&lio->glist_lock[q_idx]); if (!g) { @@ -2034,7 +1864,7 @@ static const struct net_device_ops lionetdevops = { .ndo_open = liquidio_open, .ndo_stop = liquidio_stop, .ndo_start_xmit = liquidio_xmit, - .ndo_get_stats = liquidio_get_stats, + .ndo_get_stats64 = liquidio_get_stats64, .ndo_set_mac_address = liquidio_set_mac, .ndo_set_rx_mode = liquidio_set_mcast_list, .ndo_tx_timeout = liquidio_tx_timeout, @@ -2156,7 +1986,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) OPCODE_NIC_IF_CFG, 0, if_cfg.u64, 0); - sc->callback = if_cfg_callback; + sc->callback = lio_if_cfg_callback; sc->callback_arg = sc; sc->wait_time = 5000; @@ -2273,6 +2103,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) netdev->features = (lio->dev_capability & ~NETIF_F_LRO); netdev->hw_features = lio->dev_capability; + netdev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX; /* MTU range: 68 - 16000 */ netdev->min_mtu = LIO_MIN_MTU_SIZE; @@ -2321,7 +2152,7 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) lio->tx_qsize = octeon_get_tx_qsize(octeon_dev, lio->txq); lio->rx_qsize = octeon_get_rx_qsize(octeon_dev, lio->rxq); - if (setup_glists(lio, num_iqueues)) { + if (lio_setup_glists(octeon_dev, lio, num_iqueues)) { dev_err(&octeon_dev->pci_dev->dev, "Gather list allocation failed\n"); goto setup_nic_dev_fail; @@ -2371,6 +2202,8 @@ static int setup_nic_devices(struct octeon_device *octeon_dev) "NIC ifidx:%d Setup successful\n", i); octeon_free_soft_command(octeon_dev, sc); + + octeon_dev->no_speed_setting = 1; } return 0; @@ -2512,7 +2345,7 @@ static int octeon_device_init(struct octeon_device *oct) } atomic_set(&oct->status, OCT_DEV_MBOX_SETUP_DONE); - if (octeon_allocate_ioq_vector(oct)) { + if (octeon_allocate_ioq_vector(oct, oct->sriov_info.rings_per_vf)) { dev_err(&oct->pci_dev->dev, "ioq vector allocation failed\n"); return 1; } diff --git a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c index 2adafa366d3f..ddd7431579f4 100644 --- a/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c +++ b/drivers/net/ethernet/cavium/liquidio/lio_vf_rep.c @@ -201,13 +201,14 @@ lio_vf_rep_get_stats64(struct net_device *dev, { struct lio_vf_rep_desc *vf_rep = netdev_priv(dev); - stats64->tx_packets = vf_rep->stats.tx_packets; - stats64->tx_bytes = vf_rep->stats.tx_bytes; - stats64->tx_dropped = vf_rep->stats.tx_dropped; - - stats64->rx_packets = vf_rep->stats.rx_packets; - stats64->rx_bytes = vf_rep->stats.rx_bytes; - stats64->rx_dropped = vf_rep->stats.rx_dropped; + /* Swap tx and rx stats as VF rep is a switch port */ + stats64->tx_packets = vf_rep->stats.rx_packets; + stats64->tx_bytes = vf_rep->stats.rx_bytes; + stats64->tx_dropped = vf_rep->stats.rx_dropped; + + stats64->rx_packets = vf_rep->stats.tx_packets; + stats64->rx_bytes = vf_rep->stats.tx_bytes; + stats64->rx_dropped = vf_rep->stats.tx_dropped; } static int diff --git a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h index 75eea83c7cc6..690424b6781a 100644 --- a/drivers/net/ethernet/cavium/liquidio/liquidio_common.h +++ b/drivers/net/ethernet/cavium/liquidio/liquidio_common.h @@ -28,7 +28,7 @@ #define LIQUIDIO_PACKAGE "" #define LIQUIDIO_BASE_MAJOR_VERSION 1 #define LIQUIDIO_BASE_MINOR_VERSION 7 -#define LIQUIDIO_BASE_MICRO_VERSION 0 +#define LIQUIDIO_BASE_MICRO_VERSION 2 #define LIQUIDIO_BASE_VERSION __stringify(LIQUIDIO_BASE_MAJOR_VERSION) "." \ __stringify(LIQUIDIO_BASE_MINOR_VERSION) #define LIQUIDIO_MICRO_VERSION "." __stringify(LIQUIDIO_BASE_MICRO_VERSION) @@ -84,6 +84,7 @@ enum octeon_tag_type { #define OPCODE_NIC_IF_CFG 0x09 #define OPCODE_NIC_VF_DRV_NOTICE 0x0A #define OPCODE_NIC_INTRMOD_PARAMS 0x0B +#define OPCODE_NIC_QCOUNT_UPDATE 0x12 #define OPCODE_NIC_SET_TRUSTED_VF 0x13 #define OPCODE_NIC_SYNC_OCTEON_TIME 0x14 #define VF_DRV_LOADED 1 @@ -92,6 +93,7 @@ enum octeon_tag_type { #define OPCODE_NIC_VF_REP_PKT 0x15 #define OPCODE_NIC_VF_REP_CMD 0x16 +#define OPCODE_NIC_UBOOT_CTL 0x17 #define CORE_DRV_TEST_SCATTER_OP 0xFFF5 @@ -248,6 +250,9 @@ static inline void add_sg_size(struct octeon_sg_entry *sg_entry, #define OCTNET_CMD_VLAN_FILTER_ENABLE 0x1 #define OCTNET_CMD_VLAN_FILTER_DISABLE 0x0 +#define SEAPI_CMD_SPEED_SET 0x2 +#define SEAPI_CMD_SPEED_GET 0x3 + #define LIO_CMD_WAIT_TM 100 /* RX(packets coming from wire) Checksum verification flags */ @@ -779,23 +784,32 @@ struct liquidio_if_cfg_info { /** Stats for each NIC port in RX direction. */ struct nic_rx_stats { /* link-level stats */ - u64 total_rcvd; - u64 bytes_rcvd; - u64 total_bcst; - u64 total_mcst; - u64 runts; - u64 ctl_rcvd; - u64 fifo_err; /* Accounts for over/under-run of buffers */ - u64 dmac_drop; - u64 fcs_err; - u64 jabber_err; - u64 l2_err; - u64 frame_err; + u64 total_rcvd; /* Received packets */ + u64 bytes_rcvd; /* Octets of received packets */ + u64 total_bcst; /* Number of non-dropped L2 broadcast packets */ + u64 total_mcst; /* Number of non-dropped L2 multicast packets */ + u64 runts; /* Packets shorter than allowed */ + u64 ctl_rcvd; /* Received PAUSE packets */ + u64 fifo_err; /* Packets dropped due to RX FIFO full */ + u64 dmac_drop; /* Packets dropped by the DMAC filter */ + u64 fcs_err; /* Sum of fragment, overrun, and FCS errors */ + u64 jabber_err; /* Packets larger than allowed */ + u64 l2_err; /* Sum of DMA, parity, PCAM access, no memory, + * buffer overflow, malformed L2 header or + * length, oversize errors + **/ + u64 frame_err; /* Sum of IPv4 and L4 checksum errors */ + u64 red_drops; /* Packets dropped by RED due to buffer + * exhaustion + **/ /* firmware stats */ u64 fw_total_rcvd; u64 fw_total_fwd; u64 fw_total_fwd_bytes; + u64 fw_total_mcast; + u64 fw_total_bcast; + u64 fw_err_pko; u64 fw_err_link; u64 fw_err_drop; @@ -806,11 +820,11 @@ struct nic_rx_stats { u64 fw_lro_pkts; /* Number of packets that are LROed */ u64 fw_lro_octs; /* Number of octets that are LROed */ u64 fw_total_lro; /* Number of LRO packets formed */ - u64 fw_lro_aborts; /* Number of times lRO of packet aborted */ + u64 fw_lro_aborts; /* Number of times LRO of packet aborted */ u64 fw_lro_aborts_port; u64 fw_lro_aborts_seq; u64 fw_lro_aborts_tsval; - u64 fw_lro_aborts_timer; + u64 fw_lro_aborts_timer; /* Timer setting error */ /* intrmod: packet forward rate */ u64 fwd_rate; }; @@ -818,23 +832,42 @@ struct nic_rx_stats { /** Stats for each NIC port in RX direction. */ struct nic_tx_stats { /* link-level stats */ - u64 total_pkts_sent; - u64 total_bytes_sent; - u64 mcast_pkts_sent; - u64 bcast_pkts_sent; - u64 ctl_sent; - u64 one_collision_sent; /* Packets sent after one collision*/ - u64 multi_collision_sent; /* Packets sent after multiple collision*/ - u64 max_collision_fail; /* Packets not sent due to max collisions */ - u64 max_deferral_fail; /* Packets not sent due to max deferrals */ - u64 fifo_err; /* Accounts for over/under-run of buffers */ - u64 runts; - u64 total_collisions; /* Total number of collisions detected */ + u64 total_pkts_sent; /* Total frames sent on the interface */ + u64 total_bytes_sent; /* Total octets sent on the interface */ + u64 mcast_pkts_sent; /* Packets sent to the multicast DMAC */ + u64 bcast_pkts_sent; /* Packets sent to a broadcast DMAC */ + u64 ctl_sent; /* Control/PAUSE packets sent */ + u64 one_collision_sent; /* Packets sent that experienced a + * single collision before successful + * transmission + **/ + u64 multi_collision_sent; /* Packets sent that experienced + * multiple collisions before successful + * transmission + **/ + u64 max_collision_fail; /* Packets dropped due to excessive + * collisions + **/ + u64 max_deferral_fail; /* Packets not sent due to max + * deferrals + **/ + u64 fifo_err; /* Packets sent that experienced a + * transmit underflow and were + * truncated + **/ + u64 runts; /* Packets sent with an octet count + * lessthan 64 + **/ + u64 total_collisions; /* Packets dropped due to excessive + * collisions + **/ /* firmware stats */ u64 fw_total_sent; u64 fw_total_fwd; u64 fw_total_fwd_bytes; + u64 fw_total_mcast_sent; + u64 fw_total_bcast_sent; u64 fw_err_pko; u64 fw_err_link; u64 fw_err_drop; diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.c b/drivers/net/ethernet/cavium/liquidio/octeon_device.c index f38abf626412..f878a552fef3 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.c @@ -824,23 +824,18 @@ int octeon_deregister_device(struct octeon_device *oct) } int -octeon_allocate_ioq_vector(struct octeon_device *oct) +octeon_allocate_ioq_vector(struct octeon_device *oct, u32 num_ioqs) { - int i, num_ioqs = 0; struct octeon_ioq_vector *ioq_vector; int cpu_num; int size; - - if (OCTEON_CN23XX_PF(oct)) - num_ioqs = oct->sriov_info.num_pf_rings; - else if (OCTEON_CN23XX_VF(oct)) - num_ioqs = oct->sriov_info.rings_per_vf; + int i; size = sizeof(struct octeon_ioq_vector) * num_ioqs; oct->ioq_vector = vzalloc(size); if (!oct->ioq_vector) - return 1; + return -1; for (i = 0; i < num_ioqs; i++) { ioq_vector = &oct->ioq_vector[i]; ioq_vector->oct_dev = oct; @@ -856,6 +851,7 @@ octeon_allocate_ioq_vector(struct octeon_device *oct) else ioq_vector->ioq_num = i; } + return 0; } diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_device.h b/drivers/net/ethernet/cavium/liquidio/octeon_device.h index 91937cc5c1d7..94a4ed88d618 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_device.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_device.h @@ -43,6 +43,13 @@ #define OCTEON_CN23XX_REV_1_1 0x01 #define OCTEON_CN23XX_REV_2_0 0x80 +/**SubsystemId for the chips */ +#define OCTEON_CN2350_10GB_SUBSYS_ID_1 0X3177d +#define OCTEON_CN2350_10GB_SUBSYS_ID_2 0X4177d +#define OCTEON_CN2360_10GB_SUBSYS_ID 0X5177d +#define OCTEON_CN2350_25GB_SUBSYS_ID 0X7177d +#define OCTEON_CN2360_25GB_SUBSYS_ID 0X6177d + /** Endian-swap modes supported by Octeon. */ enum octeon_pci_swap_mode { OCTEON_PCI_PASSTHROUGH = 0, @@ -430,6 +437,8 @@ struct octeon_device { u16 rev_id; + u32 subsystem_id; + u16 pf_num; u16 vf_num; @@ -584,6 +593,11 @@ struct octeon_device { struct lio_vf_rep_list vf_rep_list; struct devlink *devlink; enum devlink_eswitch_mode eswitch_mode; + + /* for 25G NIC speed change */ + u8 speed_boot; + u8 speed_setting; + u8 no_speed_setting; }; #define OCT_DRV_ONLINE 1 @@ -867,7 +881,7 @@ void *oct_get_config_info(struct octeon_device *oct, u16 card_type); struct octeon_config *octeon_get_conf(struct octeon_device *oct); void octeon_free_ioq_vector(struct octeon_device *oct); -int octeon_allocate_ioq_vector(struct octeon_device *oct); +int octeon_allocate_ioq_vector(struct octeon_device *oct, u32 num_ioqs); void lio_enable_irq(struct octeon_droq *droq, struct octeon_instr_queue *iq); /* LiquidIO driver pivate flags */ diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h index 81c987682941..5fed7b63223e 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_iq.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_iq.h @@ -62,8 +62,8 @@ struct oct_iq_stats { u64 tx_tot_bytes;/**< Total count of bytes sento to network. */ u64 tx_gso; /* count of tso */ u64 tx_vxlan; /* tunnel */ - u64 tx_dmamap_fail; - u64 tx_restart; + u64 tx_dmamap_fail; /* Number of times dma mapping failed */ + u64 tx_restart; /* Number of times this queue restarted */ }; #define OCT_IQ_STATS_SIZE (sizeof(struct oct_iq_stats)) diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c index 28e74ee23ff8..021d99cd1665 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.c @@ -24,6 +24,7 @@ #include "octeon_device.h" #include "octeon_main.h" #include "octeon_mailbox.h" +#include "cn23xx_pf_device.h" /** * octeon_mbox_read: @@ -205,6 +206,26 @@ int octeon_mbox_write(struct octeon_device *oct, return ret; } +static void get_vf_stats(struct octeon_device *oct, + struct oct_vf_stats *stats) +{ + int i; + + for (i = 0; i < oct->num_iqs; i++) { + if (!oct->instr_queue[i]) + continue; + stats->tx_packets += oct->instr_queue[i]->stats.tx_done; + stats->tx_bytes += oct->instr_queue[i]->stats.tx_tot_bytes; + } + + for (i = 0; i < oct->num_oqs; i++) { + if (!oct->droq[i]) + continue; + stats->rx_packets += oct->droq[i]->stats.rx_pkts_received; + stats->rx_bytes += oct->droq[i]->stats.rx_bytes_received; + } +} + /** * octeon_mbox_process_cmd: * @mbox: Pointer mailbox @@ -250,6 +271,15 @@ static int octeon_mbox_process_cmd(struct octeon_mbox *mbox, mbox_cmd->msg.s.params); break; + case OCTEON_GET_VF_STATS: + dev_dbg(&oct->pci_dev->dev, "Got VF stats request. Sending data back\n"); + mbox_cmd->msg.s.type = OCTEON_MBOX_RESPONSE; + mbox_cmd->msg.s.resp_needed = 1; + mbox_cmd->msg.s.len = 1 + + sizeof(struct oct_vf_stats) / sizeof(u64); + get_vf_stats(oct, (struct oct_vf_stats *)mbox_cmd->data); + octeon_mbox_write(oct, mbox_cmd); + break; default: break; } @@ -322,3 +352,25 @@ int octeon_mbox_process_message(struct octeon_mbox *mbox) return 0; } + +int octeon_mbox_cancel(struct octeon_device *oct, int q_no) +{ + struct octeon_mbox *mbox = oct->mbox[q_no]; + struct octeon_mbox_cmd *mbox_cmd; + unsigned long flags = 0; + + spin_lock_irqsave(&mbox->lock, flags); + mbox_cmd = &mbox->mbox_resp; + + if (!(mbox->state & OCTEON_MBOX_STATE_RESPONSE_PENDING)) { + spin_unlock_irqrestore(&mbox->lock, flags); + return 1; + } + + mbox->state = OCTEON_MBOX_STATE_IDLE; + memset(mbox_cmd, 0, sizeof(*mbox_cmd)); + writeq(OCTEON_PFVFSIG, mbox->mbox_read_reg); + spin_unlock_irqrestore(&mbox->lock, flags); + + return 0; +} diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h index 1def22afeff1..d92bd7e16477 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_mailbox.h @@ -25,6 +25,7 @@ #define OCTEON_VF_ACTIVE 0x1 #define OCTEON_VF_FLR_REQUEST 0x2 #define OCTEON_PF_CHANGED_VF_MACADDR 0x4 +#define OCTEON_GET_VF_STATS 0x8 /*Macro for Read acknowldgement*/ #define OCTEON_PFVFACK 0xffffffffffffffffULL @@ -107,9 +108,15 @@ struct octeon_mbox { }; +struct oct_vf_stats_ctx { + atomic_t status; + struct oct_vf_stats *stats; +}; + int octeon_mbox_read(struct octeon_mbox *mbox); int octeon_mbox_write(struct octeon_device *oct, struct octeon_mbox_cmd *mbox_cmd); int octeon_mbox_process_message(struct octeon_mbox *mbox); +int octeon_mbox_cancel(struct octeon_device *oct, int q_no); #endif diff --git a/drivers/net/ethernet/cavium/liquidio/octeon_network.h b/drivers/net/ethernet/cavium/liquidio/octeon_network.h index 4069710796a8..d7a3916fe877 100644 --- a/drivers/net/ethernet/cavium/liquidio/octeon_network.h +++ b/drivers/net/ethernet/cavium/liquidio/octeon_network.h @@ -47,6 +47,29 @@ struct liquidio_if_cfg_resp { u64 status; }; +#define LIO_IFCFG_WAIT_TIME 3000 /* In milli seconds */ + +/* Structure of a node in list of gather components maintained by + * NIC driver for each network device. + */ +struct octnic_gather { + /* List manipulation. Next and prev pointers. */ + struct list_head list; + + /* Size of the gather component at sg in bytes. */ + int sg_size; + + /* Number of bytes that sg was adjusted to make it 8B-aligned. */ + int adjust; + + /* Gather component that can accommodate max sized fragment list + * received from the IP layer. + */ + struct octeon_sg_entry *sg; + + dma_addr_t sg_dma_ptr; +}; + struct oct_nic_stats_resp { u64 rh; struct oct_link_stats stats; @@ -58,6 +81,18 @@ struct oct_nic_stats_ctrl { struct net_device *netdev; }; +struct oct_nic_seapi_resp { + u64 rh; + u32 speed; + u64 status; +}; + +struct liquidio_nic_seapi_ctl_context { + int octeon_id; + u32 status; + struct completion complete; +}; + /** LiquidIO per-interface network private data */ struct lio { /** State of the interface. Rx/Tx happens only in the RUNNING state. */ @@ -157,7 +192,7 @@ struct lio { #define LIO_SIZE (sizeof(struct lio)) #define GET_LIO(netdev) ((struct lio *)netdev_priv(netdev)) -#define LIO_MAX_CORES 12 +#define LIO_MAX_CORES 16 /** * \brief Enable or disable feature @@ -190,6 +225,8 @@ irqreturn_t liquidio_msix_intr_handler(int irq __attribute__((unused)), int octeon_setup_interrupt(struct octeon_device *oct, u32 num_ioqs); +int octnet_get_link_stats(struct net_device *netdev); + int lio_wait_for_clean_oq(struct octeon_device *oct); /** * \brief Register ethtool operations @@ -197,6 +234,17 @@ int lio_wait_for_clean_oq(struct octeon_device *oct); */ void liquidio_set_ethtool_ops(struct net_device *netdev); +void lio_if_cfg_callback(struct octeon_device *oct, + u32 status __attribute__((unused)), + void *buf); + +void lio_delete_glists(struct lio *lio); + +int lio_setup_glists(struct octeon_device *oct, struct lio *lio, int num_qs); + +int liquidio_get_speed(struct lio *lio); +int liquidio_set_speed(struct lio *lio, int speed); + /** * \brief Net device change_mtu * @param netdev network device @@ -515,7 +563,7 @@ static inline void stop_txqs(struct net_device *netdev) { int i; - for (i = 0; i < netdev->num_tx_queues; i++) + for (i = 0; i < netdev->real_num_tx_queues; i++) netif_stop_subqueue(netdev, i); } @@ -528,7 +576,7 @@ static inline void wake_txqs(struct net_device *netdev) struct lio *lio = GET_LIO(netdev); int i, qno; - for (i = 0; i < netdev->num_tx_queues; i++) { + for (i = 0; i < netdev->real_num_tx_queues; i++) { qno = lio->linfo.txpciq[i % lio->oct_dev->num_iqs].s.q_no; if (__netif_subqueue_stopped(netdev, i)) { @@ -549,14 +597,33 @@ static inline void start_txqs(struct net_device *netdev) int i; if (lio->linfo.link.s.link_up) { - for (i = 0; i < netdev->num_tx_queues; i++) + for (i = 0; i < netdev->real_num_tx_queues; i++) netif_start_subqueue(netdev, i); } } -static inline int skb_iq(struct lio *lio, struct sk_buff *skb) +static inline int skb_iq(struct octeon_device *oct, struct sk_buff *skb) { - return skb->queue_mapping % lio->linfo.num_txpciq; + return skb->queue_mapping % oct->num_iqs; +} + +/** + * Remove the node at the head of the list. The list would be empty at + * the end of this call if there are no more nodes in the list. + */ +static inline struct list_head *lio_list_delete_head(struct list_head *root) +{ + struct list_head *node; + + if (root->prev == root && root->next == root) + node = NULL; + else + node = root->next; + + if (node) + list_del(node); + + return node; } #endif diff --git a/drivers/net/ethernet/cavium/thunder/nicvf_main.c b/drivers/net/ethernet/cavium/thunder/nicvf_main.c index 707db3304396..7135db45927e 100644 --- a/drivers/net/ethernet/cavium/thunder/nicvf_main.c +++ b/drivers/net/ethernet/cavium/thunder/nicvf_main.c @@ -538,9 +538,9 @@ static inline bool nicvf_xdp_rx(struct nicvf *nic, struct bpf_prog *prog, action = bpf_prog_run_xdp(prog, &xdp); rcu_read_unlock(); + len = xdp.data_end - xdp.data; /* Check if XDP program has changed headers */ if (orig_data != xdp.data) { - len = xdp.data_end - xdp.data; offset = orig_data - xdp.data; dma_addr -= offset; } diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c index db92f1858060..aae980205ece 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_filter.c @@ -64,8 +64,7 @@ static int set_tcb_field(struct adapter *adap, struct filter_entry *f, if (!skb) return -ENOMEM; - req = (struct cpl_set_tcb_field *)__skb_put(skb, sizeof(*req)); - memset(req, 0, sizeof(*req)); + req = (struct cpl_set_tcb_field *)__skb_put_zero(skb, sizeof(*req)); INIT_TP_WR_CPL(req, CPL_SET_TCB_FIELD, ftid); req->reply_ctrl = htons(REPLY_CHAN_V(0) | QUEUENO_V(adap->sge.fw_evtq.abs_id) | diff --git a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c index 005283c7cdfe..c54fd189d835 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4/cxgb4_main.c @@ -2886,13 +2886,13 @@ static int cxgb_set_tx_maxrate(struct net_device *dev, int index, u32 rate) } /* Convert from Mbps to Kbps */ - req_rate = rate << 10; + req_rate = rate * 1000; /* Max rate is 100 Gbps */ - if (req_rate >= SCHED_MAX_RATE_KBPS) { + if (req_rate > SCHED_MAX_RATE_KBPS) { dev_err(adap->pdev_dev, "Invalid rate %u Mbps, Max rate is %u Mbps\n", - rate, SCHED_MAX_RATE_KBPS >> 10); + rate, SCHED_MAX_RATE_KBPS / 1000); return -ERANGE; } @@ -3081,7 +3081,7 @@ static void cxgb_del_udp_tunnel(struct net_device *netdev, match_all_mac, match_all_mac, adapter->rawf_start + pi->port_id, - 1, pi->port_id, true); + 1, pi->port_id, false); if (ret < 0) { netdev_info(netdev, "Failed to free mac filter entry, for port %d\n", i); @@ -3169,7 +3169,7 @@ static void cxgb_add_udp_tunnel(struct net_device *netdev, match_all_mac, adapter->rawf_start + pi->port_id, - 1, pi->port_id, true); + 1, pi->port_id, false); if (ret < 0) { netdev_info(netdev, "Failed to allocate a mac filter entry, not adding port %d\n", be16_to_cpu(ti->port)); @@ -4276,6 +4276,20 @@ static int adap_init0(struct adapter *adap) adap->tids.nftids = val[4] - val[3] + 1; adap->sge.ingr_start = val[5]; + if (CHELSIO_CHIP_VERSION(adap->params.chip) > CHELSIO_T5) { + /* Read the raw mps entries. In T6, the last 2 tcam entries + * are reserved for raw mac addresses (rawf = 2, one per port). + */ + params[0] = FW_PARAM_PFVF(RAWF_START); + params[1] = FW_PARAM_PFVF(RAWF_END); + ret = t4_query_params(adap, adap->mbox, adap->pf, 0, 2, + params, val); + if (ret == 0) { + adap->rawf_start = val[0]; + adap->rawf_cnt = val[1] - val[0] + 1; + } + } + /* qids (ingress/egress) returned from firmware can be anywhere * in the range from EQ(IQFLINT)_START to EQ(IQFLINT)_END. * Hence driver needs to allocate memory for this range to @@ -5181,6 +5195,7 @@ static void free_some_resources(struct adapter *adapter) { unsigned int i; + kvfree(adapter->mps_encap); kvfree(adapter->smt); kvfree(adapter->l2t); kvfree(adapter->srq); @@ -5610,8 +5625,15 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_TC; - if (CHELSIO_CHIP_VERSION(chip) > CHELSIO_T5) + if (CHELSIO_CHIP_VERSION(chip) > CHELSIO_T5) { + netdev->hw_enc_features |= NETIF_F_IP_CSUM | + NETIF_F_IPV6_CSUM | + NETIF_F_RXCSUM | + NETIF_F_GSO_UDP_TUNNEL | + NETIF_F_TSO | NETIF_F_TSO6; + netdev->hw_features |= NETIF_F_GSO_UDP_TUNNEL; + } if (highdma) netdev->hw_features |= NETIF_F_HIGHDMA; @@ -5676,6 +5698,12 @@ static int init_one(struct pci_dev *pdev, const struct pci_device_id *ent) adapter->params.offload = 0; } + adapter->mps_encap = kvzalloc(sizeof(struct mps_encap_entry) * + adapter->params.arch.mps_tcam_size, + GFP_KERNEL); + if (!adapter->mps_encap) + dev_warn(&pdev->dev, "could not allocate MPS Encap entries, continuing\n"); + #if IS_ENABLED(CONFIG_IPV6) if ((CHELSIO_CHIP_VERSION(adapter->params.chip) <= CHELSIO_T5) && (!(t4_read_reg(adapter, LE_DB_CONFIG_A) & ASLIPCOMPEN_F))) { diff --git a/drivers/net/ethernet/chelsio/cxgb4/sge.c b/drivers/net/ethernet/chelsio/cxgb4/sge.c index 1a28df137e1f..0f87e973a158 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/sge.c +++ b/drivers/net/ethernet/chelsio/cxgb4/sge.c @@ -1072,12 +1072,27 @@ static void *inline_tx_skb_header(const struct sk_buff *skb, static u64 hwcsum(enum chip_type chip, const struct sk_buff *skb) { int csum_type; - const struct iphdr *iph = ip_hdr(skb); + bool inner_hdr_csum = false; + u16 proto, ver; - if (iph->version == 4) { - if (iph->protocol == IPPROTO_TCP) + if (skb->encapsulation && + (CHELSIO_CHIP_VERSION(chip) > CHELSIO_T5)) + inner_hdr_csum = true; + + if (inner_hdr_csum) { + ver = inner_ip_hdr(skb)->version; + proto = (ver == 4) ? inner_ip_hdr(skb)->protocol : + inner_ipv6_hdr(skb)->nexthdr; + } else { + ver = ip_hdr(skb)->version; + proto = (ver == 4) ? ip_hdr(skb)->protocol : + ipv6_hdr(skb)->nexthdr; + } + + if (ver == 4) { + if (proto == IPPROTO_TCP) csum_type = TX_CSUM_TCPIP; - else if (iph->protocol == IPPROTO_UDP) + else if (proto == IPPROTO_UDP) csum_type = TX_CSUM_UDPIP; else { nocsum: /* @@ -1090,19 +1105,29 @@ nocsum: /* /* * this doesn't work with extension headers */ - const struct ipv6hdr *ip6h = (const struct ipv6hdr *)iph; - - if (ip6h->nexthdr == IPPROTO_TCP) + if (proto == IPPROTO_TCP) csum_type = TX_CSUM_TCPIP6; - else if (ip6h->nexthdr == IPPROTO_UDP) + else if (proto == IPPROTO_UDP) csum_type = TX_CSUM_UDPIP6; else goto nocsum; } if (likely(csum_type >= TX_CSUM_TCPIP)) { - u64 hdr_len = TXPKT_IPHDR_LEN_V(skb_network_header_len(skb)); - int eth_hdr_len = skb_network_offset(skb) - ETH_HLEN; + int eth_hdr_len, l4_len; + u64 hdr_len; + + if (inner_hdr_csum) { + /* This allows checksum offload for all encapsulated + * packets like GRE etc.. + */ + l4_len = skb_inner_network_header_len(skb); + eth_hdr_len = skb_inner_network_offset(skb) - ETH_HLEN; + } else { + l4_len = skb_network_header_len(skb); + eth_hdr_len = skb_network_offset(skb) - ETH_HLEN; + } + hdr_len = TXPKT_IPHDR_LEN_V(l4_len); if (CHELSIO_CHIP_VERSION(chip) <= CHELSIO_T5) hdr_len |= TXPKT_ETHHDR_LEN_V(eth_hdr_len); @@ -1273,7 +1298,7 @@ static inline void t6_fill_tnl_lso(struct sk_buff *skb, netdev_tx_t t4_eth_xmit(struct sk_buff *skb, struct net_device *dev) { u32 wr_mid, ctrl0, op; - u64 cntrl, *end; + u64 cntrl, *end, *sgl; int qidx, credits; unsigned int flits, ndesc; struct adapter *adap; @@ -1443,6 +1468,19 @@ out_free: dev_kfree_skb_any(skb); TX_CSUM_TCPIP6 : TX_CSUM_TCPIP) | TXPKT_IPHDR_LEN_V(l3hdr_len); } + sgl = (u64 *)(cpl + 1); /* sgl start here */ + if (unlikely((u8 *)sgl >= (u8 *)q->q.stat)) { + /* If current position is already at the end of the + * txq, reset the current to point to start of the queue + * and update the end ptr as well. + */ + if (sgl == (u64 *)q->q.stat) { + int left = (u8 *)end - (u8 *)q->q.stat; + + end = (void *)q->q.desc + left; + sgl = (void *)q->q.desc; + } + } q->tso++; q->tx_cso += ssi->gso_segs; } else { @@ -1454,6 +1492,7 @@ out_free: dev_kfree_skb_any(skb); wr->op_immdlen = htonl(FW_WR_OP_V(op) | FW_WR_IMMDLEN_V(len)); cpl = (void *)(wr + 1); + sgl = (u64 *)(cpl + 1); if (skb->ip_summed == CHECKSUM_PARTIAL) { cntrl = hwcsum(adap->params.chip, skb) | TXPKT_IPCSUM_DIS_F; @@ -1487,13 +1526,12 @@ out_free: dev_kfree_skb_any(skb); cpl->ctrl1 = cpu_to_be64(cntrl); if (immediate) { - cxgb4_inline_tx_skb(skb, &q->q, cpl + 1); + cxgb4_inline_tx_skb(skb, &q->q, sgl); dev_consume_skb_any(skb); } else { int last_desc; - cxgb4_write_sgl(skb, &q->q, (struct ulptx_sgl *)(cpl + 1), - end, 0, addr); + cxgb4_write_sgl(skb, &q->q, (void *)sgl, end, 0, addr); skb_orphan(skb); last_desc = q->q.pidx + ndesc - 1; @@ -2259,7 +2297,7 @@ static void cxgb4_sgetim_to_hwtstamp(struct adapter *adap, } static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, - const struct cpl_rx_pkt *pkt) + const struct cpl_rx_pkt *pkt, unsigned long tnl_hdr_len) { struct adapter *adapter = rxq->rspq.adap; struct sge *s = &adapter->sge; @@ -2275,6 +2313,8 @@ static void do_gro(struct sge_eth_rxq *rxq, const struct pkt_gl *gl, } copy_frags(skb, gl, s->pktshift); + if (tnl_hdr_len) + skb->csum_level = 1; skb->len = gl->tot_len - s->pktshift; skb->data_len = skb->len; skb->truesize += skb->data_len; @@ -2406,7 +2446,7 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, struct sge *s = &q->adap->sge; int cpl_trace_pkt = is_t4(q->adap->params.chip) ? CPL_TRACE_PKT : CPL_TRACE_PKT_T5; - u16 err_vec; + u16 err_vec, tnl_hdr_len = 0; struct port_info *pi; int ret = 0; @@ -2415,16 +2455,19 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, pkt = (const struct cpl_rx_pkt *)rsp; /* Compressed error vector is enabled for T6 only */ - if (q->adap->params.tp.rx_pkt_encap) + if (q->adap->params.tp.rx_pkt_encap) { err_vec = T6_COMPR_RXERR_VEC_G(be16_to_cpu(pkt->err_vec)); - else + tnl_hdr_len = T6_RX_TNLHDR_LEN_G(ntohs(pkt->err_vec)); + } else { err_vec = be16_to_cpu(pkt->err_vec); + } csum_ok = pkt->csum_calc && !err_vec && (q->netdev->features & NETIF_F_RXCSUM); - if ((pkt->l2info & htonl(RXF_TCP_F)) && + if (((pkt->l2info & htonl(RXF_TCP_F)) || + tnl_hdr_len) && (q->netdev->features & NETIF_F_GRO) && csum_ok && !pkt->ip_frag) { - do_gro(rxq, si, pkt); + do_gro(rxq, si, pkt, tnl_hdr_len); return 0; } @@ -2471,7 +2514,13 @@ int t4_ethrx_handler(struct sge_rspq *q, const __be64 *rsp, } else if (pkt->l2info & htonl(RXF_IP_F)) { __sum16 c = (__force __sum16)pkt->csum; skb->csum = csum_unfold(c); - skb->ip_summed = CHECKSUM_COMPLETE; + + if (tnl_hdr_len) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + skb->csum_level = 1; + } else { + skb->ip_summed = CHECKSUM_COMPLETE; + } rxq->stats.rx_cso++; } } else { diff --git a/drivers/net/ethernet/chelsio/cxgb4/srq.c b/drivers/net/ethernet/chelsio/cxgb4/srq.c index 6228a5708307..82b70a565e24 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/srq.c +++ b/drivers/net/ethernet/chelsio/cxgb4/srq.c @@ -84,8 +84,7 @@ int cxgb4_get_srq_entry(struct net_device *dev, if (!skb) return -ENOMEM; req = (struct cpl_srq_table_req *) - __skb_put(skb, sizeof(*req)); - memset(req, 0, sizeof(*req)); + __skb_put_zero(skb, sizeof(*req)); INIT_TP_WR(req, 0); OPCODE_TID(req) = htonl(MK_OPCODE_TID(CPL_SRQ_TABLE_REQ, TID_TID_V(srq_idx) | diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h index fe2029e993a2..09e38f0733bd 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_msg.h @@ -1233,6 +1233,11 @@ struct cpl_rx_pkt { #define T6_COMPR_RXERR_SUM_V(x) ((x) << T6_COMPR_RXERR_SUM_S) #define T6_COMPR_RXERR_SUM_F T6_COMPR_RXERR_SUM_V(1U) +#define T6_RX_TNLHDR_LEN_S 8 +#define T6_RX_TNLHDR_LEN_M 0xFF +#define T6_RX_TNLHDR_LEN_V(x) ((x) << T6_RX_TNLHDR_LEN_S) +#define T6_RX_TNLHDR_LEN_G(x) (((x) >> T6_RX_TNLHDR_LEN_S) & T6_RX_TNLHDR_LEN_M) + struct cpl_trace_pkt { u8 opcode; u8 intf; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h index 51b18035d691..adacc6399131 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4_pci_id_tbl.h @@ -145,6 +145,9 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x5016), /* T580-OCP-SO */ CH_PCI_ID_TABLE_FENTRY(0x5017), /* T520-OCP-SO */ CH_PCI_ID_TABLE_FENTRY(0x5018), /* T540-BT */ + CH_PCI_ID_TABLE_FENTRY(0x5019), /* T540-LP-BT */ + CH_PCI_ID_TABLE_FENTRY(0x501a), /* T540-SO-BT */ + CH_PCI_ID_TABLE_FENTRY(0x501b), /* T540-SO-CR */ CH_PCI_ID_TABLE_FENTRY(0x5080), /* Custom T540-cr */ CH_PCI_ID_TABLE_FENTRY(0x5081), /* Custom T540-LL-cr */ CH_PCI_ID_TABLE_FENTRY(0x5082), /* Custom T504-cr */ @@ -184,6 +187,7 @@ CH_PCI_DEVICE_ID_TABLE_DEFINE_BEGIN CH_PCI_ID_TABLE_FENTRY(0x50aa), /* Custom T580-CR */ CH_PCI_ID_TABLE_FENTRY(0x50ab), /* Custom T520-CR */ CH_PCI_ID_TABLE_FENTRY(0x50ac), /* Custom T540-BT */ + CH_PCI_ID_TABLE_FENTRY(0x50ad), /* Custom T520-CR */ /* T6 adapters: */ diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h index e3d4751f21ac..0e007ee72318 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_api.h @@ -1305,6 +1305,8 @@ enum fw_params_param_pfvf { FW_PARAMS_PARAM_PFVF_HPFILTER_END = 0x33, FW_PARAMS_PARAM_PFVF_TLS_START = 0x34, FW_PARAMS_PARAM_PFVF_TLS_END = 0x35, + FW_PARAMS_PARAM_PFVF_RAWF_START = 0x36, + FW_PARAMS_PARAM_PFVF_RAWF_END = 0x37, FW_PARAMS_PARAM_PFVF_NCRYPTO_LOOKASIDE = 0x39, FW_PARAMS_PARAM_PFVF_PORT_CAPS32 = 0x3A, }; diff --git a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h index 123e2c1b65f5..4eb15ceddca3 100644 --- a/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h +++ b/drivers/net/ethernet/chelsio/cxgb4/t4fw_version.h @@ -36,8 +36,8 @@ #define __T4FW_VERSION_H__ #define T4FW_VERSION_MAJOR 0x01 -#define T4FW_VERSION_MINOR 0x10 -#define T4FW_VERSION_MICRO 0x3F +#define T4FW_VERSION_MINOR 0x13 +#define T4FW_VERSION_MICRO 0x01 #define T4FW_VERSION_BUILD 0x00 #define T4FW_MIN_VERSION_MAJOR 0x01 @@ -45,8 +45,8 @@ #define T4FW_MIN_VERSION_MICRO 0x00 #define T5FW_VERSION_MAJOR 0x01 -#define T5FW_VERSION_MINOR 0x10 -#define T5FW_VERSION_MICRO 0x3F +#define T5FW_VERSION_MINOR 0x13 +#define T5FW_VERSION_MICRO 0x01 #define T5FW_VERSION_BUILD 0x00 #define T5FW_MIN_VERSION_MAJOR 0x00 @@ -54,8 +54,8 @@ #define T5FW_MIN_VERSION_MICRO 0x00 #define T6FW_VERSION_MAJOR 0x01 -#define T6FW_VERSION_MINOR 0x10 -#define T6FW_VERSION_MICRO 0x3F +#define T6FW_VERSION_MINOR 0x13 +#define T6FW_VERSION_MICRO 0x01 #define T6FW_VERSION_BUILD 0x00 #define T6FW_MIN_VERSION_MAJOR 0x00 diff --git a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c index 9a81b52307a9..71f13bd2b5e4 100644 --- a/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c +++ b/drivers/net/ethernet/chelsio/cxgb4vf/cxgb4vf_main.c @@ -1419,6 +1419,22 @@ static int cxgb4vf_get_link_ksettings(struct net_device *dev, base->duplex = DUPLEX_UNKNOWN; } + if (pi->link_cfg.fc & PAUSE_RX) { + if (pi->link_cfg.fc & PAUSE_TX) { + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, + Pause); + } else { + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, + Asym_Pause); + } + } else if (pi->link_cfg.fc & PAUSE_TX) { + ethtool_link_ksettings_add_link_mode(link_ksettings, + advertising, + Asym_Pause); + } + base->autoneg = pi->link_cfg.autoneg; if (pi->link_cfg.pcaps & FW_PORT_CAP32_ANEG) ethtool_link_ksettings_add_link_mode(link_ksettings, diff --git a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.h b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.h index 4b5aacc09cab..240ba9d4c399 100644 --- a/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.h +++ b/drivers/net/ethernet/chelsio/libcxgb/libcxgb_cm.h @@ -90,8 +90,7 @@ cxgb_mk_tid_release(struct sk_buff *skb, u32 len, u32 tid, u16 chan) { struct cpl_tid_release *req; - req = __skb_put(skb, len); - memset(req, 0, len); + req = __skb_put_zero(skb, len); INIT_TP_WR(req, tid); OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_TID_RELEASE, tid)); @@ -104,8 +103,7 @@ cxgb_mk_close_con_req(struct sk_buff *skb, u32 len, u32 tid, u16 chan, { struct cpl_close_con_req *req; - req = __skb_put(skb, len); - memset(req, 0, len); + req = __skb_put_zero(skb, len); INIT_TP_WR(req, tid); OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_CLOSE_CON_REQ, tid)); @@ -119,8 +117,7 @@ cxgb_mk_abort_req(struct sk_buff *skb, u32 len, u32 tid, u16 chan, { struct cpl_abort_req *req; - req = __skb_put(skb, len); - memset(req, 0, len); + req = __skb_put_zero(skb, len); INIT_TP_WR(req, tid); OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_REQ, tid)); @@ -134,8 +131,7 @@ cxgb_mk_abort_rpl(struct sk_buff *skb, u32 len, u32 tid, u16 chan) { struct cpl_abort_rpl *rpl; - rpl = __skb_put(skb, len); - memset(rpl, 0, len); + rpl = __skb_put_zero(skb, len); INIT_TP_WR(rpl, tid); OPCODE_TID(rpl) = cpu_to_be32(MK_OPCODE_TID(CPL_ABORT_RPL, tid)); @@ -149,8 +145,7 @@ cxgb_mk_rx_data_ack(struct sk_buff *skb, u32 len, u32 tid, u16 chan, { struct cpl_rx_data_ack *req; - req = __skb_put(skb, len); - memset(req, 0, len); + req = __skb_put_zero(skb, len); INIT_TP_WR(req, tid); OPCODE_TID(req) = cpu_to_be32(MK_OPCODE_TID(CPL_RX_DATA_ACK, tid)); diff --git a/drivers/net/ethernet/freescale/fman/fman_port.c b/drivers/net/ethernet/freescale/fman/fman_port.c index 6552d68ea6e1..ce6e24c74978 100644 --- a/drivers/net/ethernet/freescale/fman/fman_port.c +++ b/drivers/net/ethernet/freescale/fman/fman_port.c @@ -1391,12 +1391,10 @@ int fman_port_config(struct fman_port *port, struct fman_port_params *params) /* FM_WRONG_RESET_VALUES_ERRATA_FMAN_A005127 Errata * workaround */ - if (port->rev_info.major >= 6) { - u32 reg; + u32 reg; - reg = 0x00001013; - iowrite32be(reg, &port->bmi_regs->tx.fmbm_tfp); - } + reg = 0x00001013; + iowrite32be(reg, &port->bmi_regs->tx.fmbm_tfp); } return 0; diff --git a/drivers/net/ethernet/hisilicon/hns3/hnae3.h b/drivers/net/ethernet/hisilicon/hns3/hnae3.h index 37ec1b3286c6..804ea83e1713 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hnae3.h +++ b/drivers/net/ethernet/hisilicon/hns3/hnae3.h @@ -273,10 +273,6 @@ struct hnae3_ae_dev { * Map rings to vector * unmap_ring_from_vector() * Unmap rings from vector - * add_tunnel_udp() - * Add tunnel information to hardware - * del_tunnel_udp() - * Delete tunnel information from hardware * reset_queue() * Reset queue * get_fw_version() @@ -388,9 +384,6 @@ struct hnae3_ae_ops { int vector_num, struct hnae3_ring_chain_node *vr_chain); - int (*add_tunnel_udp)(struct hnae3_handle *handle, u16 port_num); - int (*del_tunnel_udp)(struct hnae3_handle *handle, u16 port_num); - void (*reset_queue)(struct hnae3_handle *handle, u16 queue_id); u32 (*get_fw_version)(struct hnae3_handle *handle); void (*get_mdix_mode)(struct hnae3_handle *handle, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c index 8c55965a66ac..4031174181a0 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_enet.c @@ -502,7 +502,7 @@ static int hns3_get_l4_protocol(struct sk_buff *skb, u8 *ol4_proto, /* find outer header point */ l3.hdr = skb_network_header(skb); - l4_hdr = skb_inner_transport_header(skb); + l4_hdr = skb_transport_header(skb); if (skb->protocol == htons(ETH_P_IPV6)) { exthdr = l3.hdr + sizeof(*l3.v6); @@ -1244,93 +1244,6 @@ static void hns3_nic_get_stats64(struct net_device *netdev, stats->tx_compressed = netdev->stats.tx_compressed; } -static void hns3_add_tunnel_port(struct net_device *netdev, u16 port, - enum hns3_udp_tnl_type type) -{ - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type]; - struct hnae3_handle *h = priv->ae_handle; - - if (udp_tnl->used && udp_tnl->dst_port == port) { - udp_tnl->used++; - return; - } - - if (udp_tnl->used) { - netdev_warn(netdev, - "UDP tunnel [%d], port [%d] offload\n", type, port); - return; - } - - udp_tnl->dst_port = port; - udp_tnl->used = 1; - /* TBD send command to hardware to add port */ - if (h->ae_algo->ops->add_tunnel_udp) - h->ae_algo->ops->add_tunnel_udp(h, port); -} - -static void hns3_del_tunnel_port(struct net_device *netdev, u16 port, - enum hns3_udp_tnl_type type) -{ - struct hns3_nic_priv *priv = netdev_priv(netdev); - struct hns3_udp_tunnel *udp_tnl = &priv->udp_tnl[type]; - struct hnae3_handle *h = priv->ae_handle; - - if (!udp_tnl->used || udp_tnl->dst_port != port) { - netdev_warn(netdev, - "Invalid UDP tunnel port %d\n", port); - return; - } - - udp_tnl->used--; - if (udp_tnl->used) - return; - - udp_tnl->dst_port = 0; - /* TBD send command to hardware to del port */ - if (h->ae_algo->ops->del_tunnel_udp) - h->ae_algo->ops->del_tunnel_udp(h, port); -} - -/* hns3_nic_udp_tunnel_add - Get notifiacetion about UDP tunnel ports - * @netdev: This physical ports's netdev - * @ti: Tunnel information - */ -static void hns3_nic_udp_tunnel_add(struct net_device *netdev, - struct udp_tunnel_info *ti) -{ - u16 port_n = ntohs(ti->port); - - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN); - break; - case UDP_TUNNEL_TYPE_GENEVE: - hns3_add_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE); - break; - default: - netdev_err(netdev, "unsupported tunnel type %d\n", ti->type); - break; - } -} - -static void hns3_nic_udp_tunnel_del(struct net_device *netdev, - struct udp_tunnel_info *ti) -{ - u16 port_n = ntohs(ti->port); - - switch (ti->type) { - case UDP_TUNNEL_TYPE_VXLAN: - hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_VXLAN); - break; - case UDP_TUNNEL_TYPE_GENEVE: - hns3_del_tunnel_port(netdev, port_n, HNS3_UDP_TNL_GENEVE); - break; - default: - break; - } -} - static int hns3_setup_tc(struct net_device *netdev, void *type_data) { struct tc_mqprio_qopt_offload *mqprio_qopt = type_data; @@ -1569,8 +1482,6 @@ static const struct net_device_ops hns3_nic_netdev_ops = { .ndo_get_stats64 = hns3_nic_get_stats64, .ndo_setup_tc = hns3_nic_setup_tc, .ndo_set_rx_mode = hns3_nic_set_rx_mode, - .ndo_udp_tunnel_add = hns3_nic_udp_tunnel_add, - .ndo_udp_tunnel_del = hns3_nic_udp_tunnel_del, .ndo_vlan_rx_add_vid = hns3_vlan_rx_add_vid, .ndo_vlan_rx_kill_vid = hns3_vlan_rx_kill_vid, .ndo_set_vf_vlan = hns3_ndo_set_vf_vlan, @@ -1626,8 +1537,6 @@ static struct pci_driver hns3_driver = { /* set default feature to hns3 */ static void hns3_set_default_feature(struct net_device *netdev) { - struct hnae3_handle *h = hns3_get_handle(netdev); - netdev->priv_flags |= IFF_UNICAST_FLT; netdev->hw_enc_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | @@ -1656,15 +1565,11 @@ static void hns3_set_default_feature(struct net_device *netdev) NETIF_F_GSO_UDP_TUNNEL_CSUM; netdev->hw_features |= NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | - NETIF_F_HW_VLAN_CTAG_TX | + NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_RXCSUM | NETIF_F_SG | NETIF_F_GSO | NETIF_F_GRO | NETIF_F_TSO | NETIF_F_TSO6 | NETIF_F_GSO_GRE | NETIF_F_GSO_GRE_CSUM | NETIF_F_GSO_UDP_TUNNEL | NETIF_F_GSO_UDP_TUNNEL_CSUM; - - if (!(h->flags & HNAE3_SUPPORT_VF)) - netdev->hw_features |= - NETIF_F_HW_VLAN_CTAG_FILTER | NETIF_F_HW_VLAN_CTAG_RX; } static int hns3_alloc_buffer(struct hns3_enet_ring *ring, @@ -3052,13 +2957,13 @@ int hns3_uninit_all_ring(struct hns3_nic_priv *priv) } /* Set mac addr if it is configured. or leave it to the AE driver */ -static void hns3_init_mac_addr(struct net_device *netdev) +static void hns3_init_mac_addr(struct net_device *netdev, bool init) { struct hns3_nic_priv *priv = netdev_priv(netdev); struct hnae3_handle *h = priv->ae_handle; u8 mac_addr_temp[ETH_ALEN]; - if (h->ae_algo->ops->get_mac_addr) { + if (h->ae_algo->ops->get_mac_addr && init) { h->ae_algo->ops->get_mac_addr(h, mac_addr_temp); ether_addr_copy(netdev->dev_addr, mac_addr_temp); } @@ -3112,7 +3017,7 @@ static int hns3_client_init(struct hnae3_handle *handle) handle->kinfo.netdev = netdev; handle->priv = (void *)priv; - hns3_init_mac_addr(netdev); + hns3_init_mac_addr(netdev, true); hns3_set_default_feature(netdev); @@ -3298,9 +3203,35 @@ static void hns3_recover_hw_addr(struct net_device *ndev) hns3_nic_mc_sync(ndev, ha->addr); } -static void hns3_drop_skb_data(struct hns3_enet_ring *ring, struct sk_buff *skb) +static void hns3_clear_tx_ring(struct hns3_enet_ring *ring) { - dev_kfree_skb_any(skb); + if (!HNAE3_IS_TX_RING(ring)) + return; + + while (ring->next_to_clean != ring->next_to_use) { + hns3_free_buffer_detach(ring, ring->next_to_clean); + ring_ptr_move_fw(ring, next_to_clean); + } +} + +static void hns3_clear_rx_ring(struct hns3_enet_ring *ring) +{ + if (HNAE3_IS_TX_RING(ring)) + return; + + while (ring->next_to_use != ring->next_to_clean) { + /* When a buffer is not reused, it's memory has been + * freed in hns3_handle_rx_bd or will be freed by + * stack, so only need to unmap the buffer here. + */ + if (!ring->desc_cb[ring->next_to_use].reuse_flag) { + hns3_unmap_buffer(ring, + &ring->desc_cb[ring->next_to_use]); + ring->desc_cb[ring->next_to_use].dma = 0; + } + + ring_ptr_move_fw(ring, next_to_use); + } } static void hns3_clear_all_ring(struct hnae3_handle *h) @@ -3314,13 +3245,13 @@ static void hns3_clear_all_ring(struct hnae3_handle *h) struct hns3_enet_ring *ring; ring = priv->ring_data[i].ring; - hns3_clean_tx_ring(ring, ring->desc_num); + hns3_clear_tx_ring(ring); dev_queue = netdev_get_tx_queue(ndev, priv->ring_data[i].queue_index); netdev_tx_reset_queue(dev_queue); ring = priv->ring_data[i + h->kinfo.num_tqps].ring; - hns3_clean_rx_ring(ring, ring->desc_num, hns3_drop_skb_data); + hns3_clear_rx_ring(ring); } } @@ -3359,7 +3290,7 @@ static int hns3_reset_notify_init_enet(struct hnae3_handle *handle) struct hns3_nic_priv *priv = netdev_priv(netdev); int ret; - hns3_init_mac_addr(netdev); + hns3_init_mac_addr(netdev, false); hns3_nic_set_rx_mode(netdev); hns3_recover_hw_addr(netdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c index eb3c34f3cf87..c16bb6cb0564 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3_ethtool.c @@ -74,7 +74,7 @@ struct hns3_link_mode_mapping { u32 ethtool_link_mode; }; -static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop) +static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop, bool en) { struct hnae3_handle *h = hns3_get_handle(ndev); int ret; @@ -85,11 +85,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop) switch (loop) { case HNAE3_MAC_INTER_LOOP_MAC: - ret = h->ae_algo->ops->set_loopback(h, loop, true); - break; - case HNAE3_MAC_LOOP_NONE: - ret = h->ae_algo->ops->set_loopback(h, - HNAE3_MAC_INTER_LOOP_MAC, false); + ret = h->ae_algo->ops->set_loopback(h, loop, en); break; default: ret = -ENOTSUPP; @@ -99,10 +95,7 @@ static int hns3_lp_setup(struct net_device *ndev, enum hnae3_loop loop) if (ret) return ret; - if (loop == HNAE3_MAC_LOOP_NONE) - h->ae_algo->ops->set_promisc_mode(h, ndev->flags & IFF_PROMISC); - else - h->ae_algo->ops->set_promisc_mode(h, 1); + h->ae_algo->ops->set_promisc_mode(h, en); return ret; } @@ -122,13 +115,13 @@ static int hns3_lp_up(struct net_device *ndev, enum hnae3_loop loop_mode) return ret; } - ret = hns3_lp_setup(ndev, loop_mode); + ret = hns3_lp_setup(ndev, loop_mode, true); usleep_range(10000, 20000); return ret; } -static int hns3_lp_down(struct net_device *ndev) +static int hns3_lp_down(struct net_device *ndev, enum hnae3_loop loop_mode) { struct hnae3_handle *h = hns3_get_handle(ndev); int ret; @@ -136,7 +129,7 @@ static int hns3_lp_down(struct net_device *ndev) if (!h->ae_algo->ops->stop) return -EOPNOTSUPP; - ret = hns3_lp_setup(ndev, HNAE3_MAC_LOOP_NONE); + ret = hns3_lp_setup(ndev, loop_mode, false); if (ret) { netdev_err(ndev, "lb_setup return error: %d\n", ret); return ret; @@ -332,7 +325,7 @@ static void hns3_self_test(struct net_device *ndev, data[test_index] = hns3_lp_up(ndev, loop_type); if (!data[test_index]) { data[test_index] = hns3_lp_run_test(ndev, loop_type); - hns3_lp_down(ndev); + hns3_lp_down(ndev, loop_type); } if (data[test_index]) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c index ff13d1876d9e..fab70683bbf7 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_cmd.c @@ -31,6 +31,17 @@ static int hclge_ring_space(struct hclge_cmq_ring *ring) return ring->desc_num - used - 1; } +static int is_valid_csq_clean_head(struct hclge_cmq_ring *ring, int h) +{ + int u = ring->next_to_use; + int c = ring->next_to_clean; + + if (unlikely(h >= ring->desc_num)) + return 0; + + return u > c ? (h > c && h <= u) : (h > c || h <= u); +} + static int hclge_alloc_cmd_desc(struct hclge_cmq_ring *ring) { int size = ring->desc_num * sizeof(struct hclge_desc); @@ -141,6 +152,7 @@ static void hclge_cmd_init_regs(struct hclge_hw *hw) static int hclge_cmd_csq_clean(struct hclge_hw *hw) { + struct hclge_dev *hdev = (struct hclge_dev *)hw->back; struct hclge_cmq_ring *csq = &hw->cmq.csq; u16 ntc = csq->next_to_clean; struct hclge_desc *desc; @@ -149,6 +161,13 @@ static int hclge_cmd_csq_clean(struct hclge_hw *hw) desc = &csq->desc[ntc]; head = hclge_read_dev(hw, HCLGE_NIC_CSQ_HEAD_REG); + rmb(); /* Make sure head is ready before touch any data */ + + if (!is_valid_csq_clean_head(csq, head)) { + dev_warn(&hdev->pdev->dev, "wrong head (%d, %d-%d)\n", head, + csq->next_to_use, csq->next_to_clean); + return 0; + } while (head != ntc) { memset(desc, 0, sizeof(*desc)); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c index 2066dd734444..316ec8427891 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.c @@ -304,8 +304,6 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = { HCLGE_MAC_STATS_FIELD_OFF(mac_tx_2048_4095_oct_pkt_num)}, {"mac_tx_4096_8191_oct_pkt_num", HCLGE_MAC_STATS_FIELD_OFF(mac_tx_4096_8191_oct_pkt_num)}, - {"mac_tx_8192_12287_oct_pkt_num", - HCLGE_MAC_STATS_FIELD_OFF(mac_tx_8192_12287_oct_pkt_num)}, {"mac_tx_8192_9216_oct_pkt_num", HCLGE_MAC_STATS_FIELD_OFF(mac_tx_8192_9216_oct_pkt_num)}, {"mac_tx_9217_12287_oct_pkt_num", @@ -356,8 +354,6 @@ static const struct hclge_comm_stats_str g_mac_stats_string[] = { HCLGE_MAC_STATS_FIELD_OFF(mac_rx_2048_4095_oct_pkt_num)}, {"mac_rx_4096_8191_oct_pkt_num", HCLGE_MAC_STATS_FIELD_OFF(mac_rx_4096_8191_oct_pkt_num)}, - {"mac_rx_8192_12287_oct_pkt_num", - HCLGE_MAC_STATS_FIELD_OFF(mac_rx_8192_12287_oct_pkt_num)}, {"mac_rx_8192_9216_oct_pkt_num", HCLGE_MAC_STATS_FIELD_OFF(mac_rx_8192_9216_oct_pkt_num)}, {"mac_rx_9217_12287_oct_pkt_num", @@ -1459,8 +1455,11 @@ static int hclge_alloc_vport(struct hclge_dev *hdev) /* We need to alloc a vport for main NIC of PF */ num_vport = hdev->num_vmdq_vport + hdev->num_req_vfs + 1; - if (hdev->num_tqps < num_vport) - num_vport = hdev->num_tqps; + if (hdev->num_tqps < num_vport) { + dev_err(&hdev->pdev->dev, "tqps(%d) is less than vports(%d)", + hdev->num_tqps, num_vport); + return -EINVAL; + } /* Alloc the same number of TQPs for every vport */ tqp_per_vport = hdev->num_tqps / num_vport; @@ -3683,48 +3682,50 @@ static void hclge_cfg_mac_mode(struct hclge_dev *hdev, bool enable) "mac enable fail, ret =%d.\n", ret); } -static int hclge_set_loopback(struct hnae3_handle *handle, - enum hnae3_loop loop_mode, bool en) +static int hclge_set_mac_loopback(struct hclge_dev *hdev, bool en) { - struct hclge_vport *vport = hclge_get_vport(handle); struct hclge_config_mac_mode_cmd *req; - struct hclge_dev *hdev = vport->back; struct hclge_desc desc; u32 loop_en; int ret; - switch (loop_mode) { - case HNAE3_MAC_INTER_LOOP_MAC: - req = (struct hclge_config_mac_mode_cmd *)&desc.data[0]; - /* 1 Read out the MAC mode config at first */ - hclge_cmd_setup_basic_desc(&desc, - HCLGE_OPC_CONFIG_MAC_MODE, - true); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) { - dev_err(&hdev->pdev->dev, - "mac loopback get fail, ret =%d.\n", - ret); - return ret; - } + req = (struct hclge_config_mac_mode_cmd *)&desc.data[0]; + /* 1 Read out the MAC mode config at first */ + hclge_cmd_setup_basic_desc(&desc, HCLGE_OPC_CONFIG_MAC_MODE, true); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) { + dev_err(&hdev->pdev->dev, + "mac loopback get fail, ret =%d.\n", ret); + return ret; + } - /* 2 Then setup the loopback flag */ - loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en); - if (en) - hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 1); - else - hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, 0); + /* 2 Then setup the loopback flag */ + loop_en = le32_to_cpu(req->txrx_pad_fcs_loop_en); + hnae_set_bit(loop_en, HCLGE_MAC_APP_LP_B, en ? 1 : 0); - req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); + req->txrx_pad_fcs_loop_en = cpu_to_le32(loop_en); - /* 3 Config mac work mode with loopback flag - * and its original configure parameters - */ - hclge_cmd_reuse_desc(&desc, false); - ret = hclge_cmd_send(&hdev->hw, &desc, 1); - if (ret) - dev_err(&hdev->pdev->dev, - "mac loopback set fail, ret =%d.\n", ret); + /* 3 Config mac work mode with loopback flag + * and its original configure parameters + */ + hclge_cmd_reuse_desc(&desc, false); + ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "mac loopback set fail, ret =%d.\n", ret); + return ret; +} + +static int hclge_set_loopback(struct hnae3_handle *handle, + enum hnae3_loop loop_mode, bool en) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + int ret; + + switch (loop_mode) { + case HNAE3_MAC_INTER_LOOP_MAC: + ret = hclge_set_mac_loopback(hdev, en); break; default: ret = -ENOTSUPP; @@ -4540,8 +4541,9 @@ static void hclge_enable_vlan_filter(struct hnae3_handle *handle, bool enable) hclge_set_vlan_filter_ctrl(hdev, HCLGE_FILTER_TYPE_VF, enable); } -int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, - bool is_kill, u16 vlan, u8 qos, __be16 proto) +static int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, + bool is_kill, u16 vlan, u8 qos, + __be16 proto) { #define HCLGE_MAX_VF_BYTES 16 struct hclge_vlan_filter_vf_cfg_cmd *req0; @@ -4599,12 +4601,9 @@ int hclge_set_vf_vlan_common(struct hclge_dev *hdev, int vfid, return -EIO; } -static int hclge_set_port_vlan_filter(struct hnae3_handle *handle, - __be16 proto, u16 vlan_id, - bool is_kill) +static int hclge_set_port_vlan_filter(struct hclge_dev *hdev, __be16 proto, + u16 vlan_id, bool is_kill) { - struct hclge_vport *vport = hclge_get_vport(handle); - struct hclge_dev *hdev = vport->back; struct hclge_vlan_filter_pf_cfg_cmd *req; struct hclge_desc desc; u8 vlan_offset_byte_val; @@ -4624,22 +4623,66 @@ static int hclge_set_port_vlan_filter(struct hnae3_handle *handle, req->vlan_offset_bitmap[vlan_offset_byte] = vlan_offset_byte_val; ret = hclge_cmd_send(&hdev->hw, &desc, 1); + if (ret) + dev_err(&hdev->pdev->dev, + "port vlan command, send fail, ret =%d.\n", ret); + return ret; +} + +static int hclge_set_vlan_filter_hw(struct hclge_dev *hdev, __be16 proto, + u16 vport_id, u16 vlan_id, u8 qos, + bool is_kill) +{ + u16 vport_idx, vport_num = 0; + int ret; + + ret = hclge_set_vf_vlan_common(hdev, vport_id, is_kill, vlan_id, + 0, proto); if (ret) { dev_err(&hdev->pdev->dev, - "port vlan command, send fail, ret =%d.\n", - ret); + "Set %d vport vlan filter config fail, ret =%d.\n", + vport_id, ret); return ret; } - ret = hclge_set_vf_vlan_common(hdev, 0, is_kill, vlan_id, 0, proto); - if (ret) { + /* vlan 0 may be added twice when 8021q module is enabled */ + if (!is_kill && !vlan_id && + test_bit(vport_id, hdev->vlan_table[vlan_id])) + return 0; + + if (!is_kill && test_and_set_bit(vport_id, hdev->vlan_table[vlan_id])) { dev_err(&hdev->pdev->dev, - "Set pf vlan filter config fail, ret =%d.\n", - ret); - return -EIO; + "Add port vlan failed, vport %d is already in vlan %d\n", + vport_id, vlan_id); + return -EINVAL; } - return 0; + if (is_kill && + !test_and_clear_bit(vport_id, hdev->vlan_table[vlan_id])) { + dev_err(&hdev->pdev->dev, + "Delete port vlan failed, vport %d is not in vlan %d\n", + vport_id, vlan_id); + return -EINVAL; + } + + for_each_set_bit(vport_idx, hdev->vlan_table[vlan_id], VLAN_N_VID) + vport_num++; + + if ((is_kill && vport_num == 0) || (!is_kill && vport_num == 1)) + ret = hclge_set_port_vlan_filter(hdev, proto, vlan_id, + is_kill); + + return ret; +} + +int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, + u16 vlan_id, bool is_kill) +{ + struct hclge_vport *vport = hclge_get_vport(handle); + struct hclge_dev *hdev = vport->back; + + return hclge_set_vlan_filter_hw(hdev, proto, vport->vport_id, vlan_id, + 0, is_kill); } static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, @@ -4653,7 +4696,7 @@ static int hclge_set_vf_vlan_filter(struct hnae3_handle *handle, int vfid, if (proto != htons(ETH_P_8021Q)) return -EPROTONOSUPPORT; - return hclge_set_vf_vlan_common(hdev, vfid, false, vlan, qos, proto); + return hclge_set_vlan_filter_hw(hdev, proto, vfid, vlan, qos, false); } static int hclge_set_vlan_tx_offload_cfg(struct hclge_vport *vport) @@ -4818,10 +4861,10 @@ static int hclge_init_vlan_config(struct hclge_dev *hdev) } handle = &hdev->vport[0].nic; - return hclge_set_port_vlan_filter(handle, htons(ETH_P_8021Q), 0, false); + return hclge_set_vlan_filter(handle, htons(ETH_P_8021Q), 0, false); } -static int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) +int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) { struct hclge_vport *vport = hclge_get_vport(handle); @@ -5166,12 +5209,6 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, struct phy_device *phydev = hdev->hw.mac.phydev; u32 fc_autoneg; - /* Only support flow control negotiation for netdev with - * phy attached for now. - */ - if (!phydev) - return -EOPNOTSUPP; - fc_autoneg = hclge_get_autoneg(handle); if (auto_neg != fc_autoneg) { dev_info(&hdev->pdev->dev, @@ -5190,6 +5227,12 @@ static int hclge_set_pauseparam(struct hnae3_handle *handle, u32 auto_neg, if (!fc_autoneg) return hclge_cfg_pauseparam(hdev, rx_en, tx_en); + /* Only support flow control negotiation for netdev with + * phy attached for now. + */ + if (!phydev) + return -EOPNOTSUPP; + return phy_start_aneg(phydev); } @@ -5427,7 +5470,7 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) hdev = devm_kzalloc(&pdev->dev, sizeof(*hdev), GFP_KERNEL); if (!hdev) { ret = -ENOMEM; - goto err_hclge_dev; + goto out; } hdev->pdev = pdev; @@ -5440,38 +5483,38 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) ret = hclge_pci_init(hdev); if (ret) { dev_err(&pdev->dev, "PCI init failed\n"); - goto err_pci_init; + goto out; } /* Firmware command queue initialize */ ret = hclge_cmd_queue_init(hdev); if (ret) { dev_err(&pdev->dev, "Cmd queue init failed, ret = %d.\n", ret); - return ret; + goto err_pci_uninit; } /* Firmware command initialize */ ret = hclge_cmd_init(hdev); if (ret) - goto err_cmd_init; + goto err_cmd_uninit; ret = hclge_get_cap(hdev); if (ret) { dev_err(&pdev->dev, "get hw capability error, ret = %d.\n", ret); - return ret; + goto err_cmd_uninit; } ret = hclge_configure(hdev); if (ret) { dev_err(&pdev->dev, "Configure dev error, ret = %d.\n", ret); - return ret; + goto err_cmd_uninit; } ret = hclge_init_msi(hdev); if (ret) { dev_err(&pdev->dev, "Init MSI/MSI-X error, ret = %d.\n", ret); - return ret; + goto err_cmd_uninit; } ret = hclge_misc_irq_init(hdev); @@ -5479,69 +5522,71 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) dev_err(&pdev->dev, "Misc IRQ(vector0) init error, ret = %d.\n", ret); - return ret; + goto err_msi_uninit; } ret = hclge_alloc_tqps(hdev); if (ret) { dev_err(&pdev->dev, "Allocate TQPs error, ret = %d.\n", ret); - return ret; + goto err_msi_irq_uninit; } ret = hclge_alloc_vport(hdev); if (ret) { dev_err(&pdev->dev, "Allocate vport error, ret = %d.\n", ret); - return ret; + goto err_msi_irq_uninit; } ret = hclge_map_tqp(hdev); if (ret) { dev_err(&pdev->dev, "Map tqp error, ret = %d.\n", ret); - return ret; + goto err_sriov_disable; } - ret = hclge_mac_mdio_config(hdev); - if (ret) { - dev_warn(&hdev->pdev->dev, - "mdio config fail ret=%d\n", ret); - return ret; + if (hdev->hw.mac.media_type == HNAE3_MEDIA_TYPE_COPPER) { + ret = hclge_mac_mdio_config(hdev); + if (ret) { + dev_err(&hdev->pdev->dev, + "mdio config fail ret=%d\n", ret); + goto err_sriov_disable; + } } ret = hclge_mac_init(hdev); if (ret) { dev_err(&pdev->dev, "Mac init error, ret = %d\n", ret); - return ret; + goto err_mdiobus_unreg; } ret = hclge_config_tso(hdev, HCLGE_TSO_MSS_MIN, HCLGE_TSO_MSS_MAX); if (ret) { dev_err(&pdev->dev, "Enable tso fail, ret =%d\n", ret); - return ret; + goto err_mdiobus_unreg; } ret = hclge_init_vlan_config(hdev); if (ret) { dev_err(&pdev->dev, "VLAN init fail, ret =%d\n", ret); - return ret; + goto err_mdiobus_unreg; } ret = hclge_tm_schd_init(hdev); if (ret) { dev_err(&pdev->dev, "tm schd init fail, ret =%d\n", ret); - return ret; + goto err_mdiobus_unreg; } hclge_rss_init_cfg(hdev); ret = hclge_rss_init_hw(hdev); if (ret) { dev_err(&pdev->dev, "Rss init fail, ret =%d\n", ret); - return ret; + goto err_mdiobus_unreg; } ret = init_mgr_tbl(hdev); if (ret) { dev_err(&pdev->dev, "manager table init fail, ret =%d\n", ret); - return ret; + goto err_mdiobus_unreg; } hclge_dcb_ops_set(hdev); @@ -5564,11 +5609,24 @@ static int hclge_init_ae_dev(struct hnae3_ae_dev *ae_dev) pr_info("%s driver initialization finished.\n", HCLGE_DRIVER_NAME); return 0; -err_cmd_init: +err_mdiobus_unreg: + if (hdev->hw.mac.phydev) + mdiobus_unregister(hdev->hw.mac.mdio_bus); +err_sriov_disable: + if (IS_ENABLED(CONFIG_PCI_IOV)) + hclge_disable_sriov(hdev); +err_msi_irq_uninit: + hclge_misc_irq_uninit(hdev); +err_msi_uninit: + pci_free_irq_vectors(pdev); +err_cmd_uninit: + hclge_destroy_cmd_queue(&hdev->hw); +err_pci_uninit: + pci_clear_master(pdev); pci_release_regions(pdev); -err_pci_init: + pci_disable_device(pdev); pci_set_drvdata(pdev, NULL); -err_hclge_dev: +out: return ret; } @@ -5586,6 +5644,7 @@ static int hclge_reset_ae_dev(struct hnae3_ae_dev *ae_dev) set_bit(HCLGE_STATE_DOWN, &hdev->state); hclge_stats_clear(hdev); + memset(hdev->vlan_table, 0, sizeof(hdev->vlan_table)); ret = hclge_cmd_init(hdev); if (ret) { @@ -6203,7 +6262,7 @@ static const struct hnae3_ae_ops hclge_ops = { .get_fw_version = hclge_get_fw_version, .get_mdix_mode = hclge_get_mdix_mode, .enable_vlan_filter = hclge_enable_vlan_filter, - .set_vlan_filter = hclge_set_port_vlan_filter, + .set_vlan_filter = hclge_set_vlan_filter, .set_vf_vlan_filter = hclge_set_vf_vlan_filter, .enable_hw_strip_rxvtag = hclge_en_hw_strip_rxvtag, .reset_event = hclge_reset_event, diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h index 0f4157e71282..af736a44607c 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_main.h @@ -12,6 +12,8 @@ #include <linux/fs.h> #include <linux/types.h> #include <linux/phy.h> +#include <linux/if_vlan.h> + #include "hclge_cmd.h" #include "hnae3.h" @@ -406,9 +408,9 @@ struct hclge_mac_stats { u64 mac_tx_1519_2047_oct_pkt_num; u64 mac_tx_2048_4095_oct_pkt_num; u64 mac_tx_4096_8191_oct_pkt_num; - u64 mac_tx_8192_12287_oct_pkt_num; /* valid for GE MAC only */ - u64 mac_tx_8192_9216_oct_pkt_num; /* valid for LGE & CGE MAC only */ - u64 mac_tx_9217_12287_oct_pkt_num; /* valid for LGE & CGE MAC */ + u64 rsv0; + u64 mac_tx_8192_9216_oct_pkt_num; + u64 mac_tx_9217_12287_oct_pkt_num; u64 mac_tx_12288_16383_oct_pkt_num; u64 mac_tx_1519_max_good_oct_pkt_num; u64 mac_tx_1519_max_bad_oct_pkt_num; @@ -433,9 +435,9 @@ struct hclge_mac_stats { u64 mac_rx_1519_2047_oct_pkt_num; u64 mac_rx_2048_4095_oct_pkt_num; u64 mac_rx_4096_8191_oct_pkt_num; - u64 mac_rx_8192_12287_oct_pkt_num;/* valid for GE MAC only */ - u64 mac_rx_8192_9216_oct_pkt_num; /* valid for LGE & CGE MAC only */ - u64 mac_rx_9217_12287_oct_pkt_num; /* valid for LGE & CGE MAC only */ + u64 rsv1; + u64 mac_rx_8192_9216_oct_pkt_num; + u64 mac_rx_9217_12287_oct_pkt_num; u64 mac_rx_12288_16383_oct_pkt_num; u64 mac_rx_1519_max_good_oct_pkt_num; u64 mac_rx_1519_max_bad_oct_pkt_num; @@ -471,6 +473,7 @@ struct hclge_vlan_type_cfg { u16 tx_in_vlan_type; }; +#define HCLGE_VPORT_NUM 256 struct hclge_dev { struct pci_dev *pdev; struct hnae3_ae_dev *ae_dev; @@ -562,6 +565,7 @@ struct hclge_dev { u64 rx_pkts_for_led; u64 tx_pkts_for_led; + unsigned long vlan_table[VLAN_N_VID][BITS_TO_LONGS(HCLGE_VPORT_NUM)]; }; /* VPort level vlan tag configuration for TX direction */ @@ -646,8 +650,9 @@ static inline int hclge_get_queue_id(struct hnae3_queue *queue) } int hclge_cfg_mac_speed_dup(struct hclge_dev *hdev, int speed, u8 duplex); -int hclge_set_vf_vlan_common(struct hclge_dev *vport, int vfid, - bool is_kill, u16 vlan, u8 qos, __be16 proto); +int hclge_set_vlan_filter(struct hnae3_handle *handle, __be16 proto, + u16 vlan_id, bool is_kill); +int hclge_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable); int hclge_buffer_alloc(struct hclge_dev *hdev); int hclge_rss_init_hw(struct hclge_dev *hdev); diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c index a6f7ffa9c259..b6ae26ba0a46 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mbx.c @@ -264,19 +264,23 @@ static int hclge_set_vf_vlan_cfg(struct hclge_vport *vport, struct hclge_mbx_vf_to_pf_cmd *mbx_req, bool gen_resp) { - struct hclge_dev *hdev = vport->back; int status = 0; if (mbx_req->msg[1] == HCLGE_MBX_VLAN_FILTER) { + struct hnae3_handle *handle = &vport->nic; u16 vlan, proto; bool is_kill; is_kill = !!mbx_req->msg[2]; memcpy(&vlan, &mbx_req->msg[3], sizeof(vlan)); memcpy(&proto, &mbx_req->msg[5], sizeof(proto)); - status = hclge_set_vf_vlan_common(hdev, vport->vport_id, - is_kill, vlan, 0, - cpu_to_be16(proto)); + status = hclge_set_vlan_filter(handle, cpu_to_be16(proto), + vlan, is_kill); + } else if (mbx_req->msg[1] == HCLGE_MBX_VLAN_RX_OFF_CFG) { + struct hnae3_handle *handle = &vport->nic; + bool en = mbx_req->msg[2] ? true : false; + + status = hclge_en_hw_strip_rxvtag(handle, en); } if (gen_resp) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c index 682c2d6618e7..9f7932e423b5 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_mdio.c @@ -140,8 +140,11 @@ int hclge_mac_mdio_config(struct hclge_dev *hdev) struct mii_bus *mdio_bus; int ret; - if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) - return 0; + if (hdev->hw.mac.phy_addr >= PHY_MAX_ADDR) { + dev_err(&hdev->pdev->dev, "phy_addr(%d) is too large.\n", + hdev->hw.mac.phy_addr); + return -EINVAL; + } mdio_bus = devm_mdiobus_alloc(&hdev->pdev->dev); if (!mdio_bus) diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c index 885f25cd7be4..c69ecab460f9 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3pf/hclge_tm.c @@ -134,11 +134,8 @@ static int hclge_pfc_stats_get(struct hclge_dev *hdev, } ret = hclge_cmd_send(&hdev->hw, desc, HCLGE_TM_PFC_PKT_GET_CMD_NUM); - if (ret) { - dev_err(&hdev->pdev->dev, - "Get pfc pause stats fail, ret = %d.\n", ret); + if (ret) return ret; - } for (i = 0; i < HCLGE_TM_PFC_PKT_GET_CMD_NUM; i++) { struct hclge_pfc_stats_cmd *pfc_stats = diff --git a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c index 2b8426412cc9..2dbffcef7109 100644 --- a/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c +++ b/drivers/net/ethernet/hisilicon/hns3/hns3vf/hclgevf_main.c @@ -830,6 +830,17 @@ static int hclgevf_set_vlan_filter(struct hnae3_handle *handle, HCLGEVF_VLAN_MBX_MSG_LEN, false, NULL, 0); } +static int hclgevf_en_hw_strip_rxvtag(struct hnae3_handle *handle, bool enable) +{ + struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); + u8 msg_data; + + msg_data = enable ? 1 : 0; + return hclgevf_send_mbx_msg(hdev, HCLGE_MBX_SET_VLAN, + HCLGE_MBX_VLAN_RX_OFF_CFG, &msg_data, + 1, false, NULL, 0); +} + static void hclgevf_reset_tqp(struct hnae3_handle *handle, u16 queue_id) { struct hclgevf_dev *hdev = hclgevf_ae_get_hdev(handle); @@ -1825,6 +1836,7 @@ static const struct hnae3_ae_ops hclgevf_ops = { .get_tc_size = hclgevf_get_tc_size, .get_fw_version = hclgevf_get_fw_version, .set_vlan_filter = hclgevf_set_vlan_filter, + .enable_hw_strip_rxvtag = hclgevf_en_hw_strip_rxvtag, .reset_event = hclgevf_reset_event, .get_channels = hclgevf_get_channels, .get_tqps_and_rss_info = hclgevf_get_tqps_and_rss_info, diff --git a/drivers/net/ethernet/huawei/hinic/Kconfig b/drivers/net/ethernet/huawei/hinic/Kconfig index 08db24954f7e..e4e8b24c1a5d 100644 --- a/drivers/net/ethernet/huawei/hinic/Kconfig +++ b/drivers/net/ethernet/huawei/hinic/Kconfig @@ -4,7 +4,7 @@ config HINIC tristate "Huawei Intelligent PCIE Network Interface Card" - depends on (PCI_MSI && X86) + depends on (PCI_MSI && (X86 || ARM64)) ---help--- This driver supports HiNIC PCIE Ethernet cards. To compile this driver as part of the kernel, choose Y here. diff --git a/drivers/net/ethernet/huawei/hinic/hinic_main.c b/drivers/net/ethernet/huawei/hinic/hinic_main.c index eb53bd93065e..5b122728dcb4 100644 --- a/drivers/net/ethernet/huawei/hinic/hinic_main.c +++ b/drivers/net/ethernet/huawei/hinic/hinic_main.c @@ -51,7 +51,9 @@ static unsigned int rx_weight = 64; module_param(rx_weight, uint, 0644); MODULE_PARM_DESC(rx_weight, "Number Rx packets for NAPI budget (default=64)"); -#define PCI_DEVICE_ID_HI1822_PF 0x1822 +#define HINIC_DEV_ID_QUAD_PORT_25GE 0x1822 +#define HINIC_DEV_ID_DUAL_PORT_25GE 0x0200 +#define HINIC_DEV_ID_DUAL_PORT_100GE 0x0201 #define HINIC_WQ_NAME "hinic_dev" @@ -1097,7 +1099,9 @@ static void hinic_remove(struct pci_dev *pdev) } static const struct pci_device_id hinic_pci_table[] = { - { PCI_VDEVICE(HUAWEI, PCI_DEVICE_ID_HI1822_PF), 0}, + { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_QUAD_PORT_25GE), 0}, + { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_25GE), 0}, + { PCI_VDEVICE(HUAWEI, HINIC_DEV_ID_DUAL_PORT_100GE), 0}, { 0, 0} }; MODULE_DEVICE_TABLE(pci, hinic_pci_table); diff --git a/drivers/net/ethernet/intel/e100.c b/drivers/net/ethernet/intel/e100.c index 41ad56edfb96..27d5f27163d2 100644 --- a/drivers/net/ethernet/intel/e100.c +++ b/drivers/net/ethernet/intel/e100.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel PRO/100 Linux driver - Copyright(c) 1999 - 2006 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2006 Intel Corporation. */ /* * e100.c: Intel(R) PRO/100 ethernet driver diff --git a/drivers/net/ethernet/intel/e1000/Makefile b/drivers/net/ethernet/intel/e1000/Makefile index c7caadd3c8af..314c52d44b7c 100644 --- a/drivers/net/ethernet/intel/e1000/Makefile +++ b/drivers/net/ethernet/intel/e1000/Makefile @@ -1,31 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel PRO/1000 Linux driver # Copyright(c) 1999 - 2006 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along with -# this program; if not, write to the Free Software Foundation, Inc., -# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# Linux NICS <linux.nics@intel.com> -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ # # Makefile for the Intel(R) PRO/1000 ethernet driver diff --git a/drivers/net/ethernet/intel/e1000/e1000.h b/drivers/net/ethernet/intel/e1000/e1000.h index 3a0feea2df54..c40729b2c184 100644 --- a/drivers/net/ethernet/intel/e1000/e1000.h +++ b/drivers/net/ethernet/intel/e1000/e1000.h @@ -1,32 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2006 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ - +/* Copyright(c) 1999 - 2006 Intel Corporation. */ /* Linux PRO/1000 Ethernet Driver main header file */ diff --git a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c index 3e80ca170dd7..5d365a986bb0 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_ethtool.c +++ b/drivers/net/ethernet/intel/e1000/e1000_ethtool.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2006 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 1999 - 2006 Intel Corporation. */ /* ethtool support for e1000 */ diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.c b/drivers/net/ethernet/intel/e1000/e1000_hw.c index 6e7e923d57bf..48428d6a00be 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.c +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* -* - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2006 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - - */ +/* Copyright(c) 1999 - 2006 Intel Corporation. */ /* e1000_hw.c * Shared functions for accessing and configuring the MAC diff --git a/drivers/net/ethernet/intel/e1000/e1000_hw.h b/drivers/net/ethernet/intel/e1000/e1000_hw.h index f09c569ec19b..b57a04954ccf 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_hw.h +++ b/drivers/net/ethernet/intel/e1000/e1000_hw.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2006 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2006 Intel Corporation. */ /* e1000_hw.h * Structures, enums, and macros for the MAC diff --git a/drivers/net/ethernet/intel/e1000/e1000_main.c b/drivers/net/ethernet/intel/e1000/e1000_main.c index d5eb19b86a0a..2110d5f2da19 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_main.c +++ b/drivers/net/ethernet/intel/e1000/e1000_main.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2006 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2006 Intel Corporation. */ #include "e1000.h" #include <net/ip6_checksum.h> diff --git a/drivers/net/ethernet/intel/e1000/e1000_osdep.h b/drivers/net/ethernet/intel/e1000/e1000_osdep.h index ae0559b8b011..e966bb290797 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_osdep.h +++ b/drivers/net/ethernet/intel/e1000/e1000_osdep.h @@ -1,32 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2006 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ - +/* Copyright(c) 1999 - 2006 Intel Corporation. */ /* glue for the OS independent part of e1000 * includes register access macros diff --git a/drivers/net/ethernet/intel/e1000/e1000_param.c b/drivers/net/ethernet/intel/e1000/e1000_param.c index 345f23927bcc..d3f29ffe1e47 100644 --- a/drivers/net/ethernet/intel/e1000/e1000_param.c +++ b/drivers/net/ethernet/intel/e1000/e1000_param.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel PRO/1000 Linux driver - Copyright(c) 1999 - 2006 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2006 Intel Corporation. */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.c b/drivers/net/ethernet/intel/e1000e/80003es2lan.c index 953e99df420c..257bd59bc9c6 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.c +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* 80003ES2LAN Gigabit Ethernet Controller (Copper) * 80003ES2LAN Gigabit Ethernet Controller (Serdes) diff --git a/drivers/net/ethernet/intel/e1000e/80003es2lan.h b/drivers/net/ethernet/intel/e1000e/80003es2lan.h index ee6d1256fda4..aa9d639c6cbb 100644 --- a/drivers/net/ethernet/intel/e1000e/80003es2lan.h +++ b/drivers/net/ethernet/intel/e1000e/80003es2lan.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_80003ES2LAN_H_ #define _E1000E_80003ES2LAN_H_ diff --git a/drivers/net/ethernet/intel/e1000e/82571.c b/drivers/net/ethernet/intel/e1000e/82571.c index 924f2c8dfa6c..b9309302c29e 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.c +++ b/drivers/net/ethernet/intel/e1000e/82571.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* 82571EB Gigabit Ethernet Controller * 82571EB Gigabit Ethernet Controller (Copper) diff --git a/drivers/net/ethernet/intel/e1000e/82571.h b/drivers/net/ethernet/intel/e1000e/82571.h index 9a24c645f726..834c238d02db 100644 --- a/drivers/net/ethernet/intel/e1000e/82571.h +++ b/drivers/net/ethernet/intel/e1000e/82571.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_82571_H_ #define _E1000E_82571_H_ diff --git a/drivers/net/ethernet/intel/e1000e/Makefile b/drivers/net/ethernet/intel/e1000e/Makefile index 24e391a4ac68..44e58b6e7660 100644 --- a/drivers/net/ethernet/intel/e1000e/Makefile +++ b/drivers/net/ethernet/intel/e1000e/Makefile @@ -1,30 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel PRO/1000 Linux driver -# Copyright(c) 1999 - 2014 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License -# along with this program; if not, see <http://www.gnu.org/licenses/>. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# Linux NICS <linux.nics@intel.com> -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ +# Copyright(c) 1999 - 2018 Intel Corporation. # # Makefile for the Intel(R) PRO/1000 ethernet driver diff --git a/drivers/net/ethernet/intel/e1000e/defines.h b/drivers/net/ethernet/intel/e1000e/defines.h index 22883015a695..fd550dee4982 100644 --- a/drivers/net/ethernet/intel/e1000e/defines.h +++ b/drivers/net/ethernet/intel/e1000e/defines.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000_DEFINES_H_ #define _E1000_DEFINES_H_ diff --git a/drivers/net/ethernet/intel/e1000e/e1000.h b/drivers/net/ethernet/intel/e1000e/e1000.h index da88555ba1fd..c760dc72c520 100644 --- a/drivers/net/ethernet/intel/e1000e/e1000.h +++ b/drivers/net/ethernet/intel/e1000e/e1000.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* Linux PRO/1000 Ethernet Driver main header file */ diff --git a/drivers/net/ethernet/intel/e1000e/ethtool.c b/drivers/net/ethernet/intel/e1000e/ethtool.c index 64dc0c11147f..e084cb734eb1 100644 --- a/drivers/net/ethernet/intel/e1000e/ethtool.c +++ b/drivers/net/ethernet/intel/e1000e/ethtool.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* ethtool support for e1000 */ diff --git a/drivers/net/ethernet/intel/e1000e/hw.h b/drivers/net/ethernet/intel/e1000e/hw.h index 21802396bed6..eff75bd8a8f0 100644 --- a/drivers/net/ethernet/intel/e1000e/hw.h +++ b/drivers/net/ethernet/intel/e1000e/hw.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000_HW_H_ #define _E1000_HW_H_ diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.c b/drivers/net/ethernet/intel/e1000e/ich8lan.c index 1551d6ce5341..cdae0efde8e6 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.c +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* 82562G 10/100 Network Connection * 82562G-2 10/100 Network Connection diff --git a/drivers/net/ethernet/intel/e1000e/ich8lan.h b/drivers/net/ethernet/intel/e1000e/ich8lan.h index 3c4f82c21084..eb09c755fa17 100644 --- a/drivers/net/ethernet/intel/e1000e/ich8lan.h +++ b/drivers/net/ethernet/intel/e1000e/ich8lan.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_ICH8LAN_H_ #define _E1000E_ICH8LAN_H_ diff --git a/drivers/net/ethernet/intel/e1000e/mac.c b/drivers/net/ethernet/intel/e1000e/mac.c index b293464a9f27..4abd55d646c5 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.c +++ b/drivers/net/ethernet/intel/e1000e/mac.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/mac.h b/drivers/net/ethernet/intel/e1000e/mac.h index cb0abf6c76a5..6ab261119801 100644 --- a/drivers/net/ethernet/intel/e1000e/mac.h +++ b/drivers/net/ethernet/intel/e1000e/mac.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_MAC_H_ #define _E1000E_MAC_H_ diff --git a/drivers/net/ethernet/intel/e1000e/manage.c b/drivers/net/ethernet/intel/e1000e/manage.c index e027660aeb92..c4c9b20bc51f 100644 --- a/drivers/net/ethernet/intel/e1000e/manage.c +++ b/drivers/net/ethernet/intel/e1000e/manage.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/manage.h b/drivers/net/ethernet/intel/e1000e/manage.h index 3268f2e58593..d868aad806d4 100644 --- a/drivers/net/ethernet/intel/e1000e/manage.h +++ b/drivers/net/ethernet/intel/e1000e/manage.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_MANAGE_H_ #define _E1000E_MANAGE_H_ diff --git a/drivers/net/ethernet/intel/e1000e/netdev.c b/drivers/net/ethernet/intel/e1000e/netdev.c index ec4a9759a6f2..d3fef7fefea8 100644 --- a/drivers/net/ethernet/intel/e1000e/netdev.c +++ b/drivers/net/ethernet/intel/e1000e/netdev.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/net/ethernet/intel/e1000e/nvm.c b/drivers/net/ethernet/intel/e1000e/nvm.c index 68949bb41b7b..937f9af22d26 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.c +++ b/drivers/net/ethernet/intel/e1000e/nvm.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/nvm.h b/drivers/net/ethernet/intel/e1000e/nvm.h index 8e082028be7d..6a30dfea4117 100644 --- a/drivers/net/ethernet/intel/e1000e/nvm.h +++ b/drivers/net/ethernet/intel/e1000e/nvm.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_NVM_H_ #define _E1000E_NVM_H_ diff --git a/drivers/net/ethernet/intel/e1000e/param.c b/drivers/net/ethernet/intel/e1000e/param.c index 2def33eba9e6..098369fd3e65 100644 --- a/drivers/net/ethernet/intel/e1000e/param.c +++ b/drivers/net/ethernet/intel/e1000e/param.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/netdevice.h> #include <linux/module.h> diff --git a/drivers/net/ethernet/intel/e1000e/phy.c b/drivers/net/ethernet/intel/e1000e/phy.c index b8226ed0e338..42233019255a 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.c +++ b/drivers/net/ethernet/intel/e1000e/phy.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "e1000.h" diff --git a/drivers/net/ethernet/intel/e1000e/phy.h b/drivers/net/ethernet/intel/e1000e/phy.h index d4180b5e9196..c48777d09523 100644 --- a/drivers/net/ethernet/intel/e1000e/phy.h +++ b/drivers/net/ethernet/intel/e1000e/phy.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_PHY_H_ #define _E1000E_PHY_H_ diff --git a/drivers/net/ethernet/intel/e1000e/ptp.c b/drivers/net/ethernet/intel/e1000e/ptp.c index f941e5085f44..37c76945ad9b 100644 --- a/drivers/net/ethernet/intel/e1000e/ptp.c +++ b/drivers/net/ethernet/intel/e1000e/ptp.c @@ -1,24 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* PTP 1588 Hardware Clock (PHC) * Derived from PTP Hardware Clock driver for Intel 82576 and 82580 (igb) diff --git a/drivers/net/ethernet/intel/e1000e/regs.h b/drivers/net/ethernet/intel/e1000e/regs.h index 16afc3c2a986..47f5ca793970 100644 --- a/drivers/net/ethernet/intel/e1000e/regs.h +++ b/drivers/net/ethernet/intel/e1000e/regs.h @@ -1,24 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel PRO/1000 Linux driver - * Copyright(c) 1999 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000E_REGS_H_ #define _E1000E_REGS_H_ diff --git a/drivers/net/ethernet/intel/fm10k/Makefile b/drivers/net/ethernet/intel/fm10k/Makefile index 93277cb99cb7..26a9746ccb14 100644 --- a/drivers/net/ethernet/intel/fm10k/Makefile +++ b/drivers/net/ethernet/intel/fm10k/Makefile @@ -1,26 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel(R) Ethernet Switch Host Interface Driver -# Copyright(c) 2013 - 2016 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ +# Copyright(c) 2013 - 2018 Intel Corporation. # # Makefile for the Intel(R) Ethernet Switch Host Interface Driver diff --git a/drivers/net/ethernet/intel/fm10k/fm10k.h b/drivers/net/ethernet/intel/fm10k/fm10k.h index a9cdf763c59d..a903a0ba45e1 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k.h @@ -1,23 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _FM10K_H_ #define _FM10K_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.c b/drivers/net/ethernet/intel/fm10k/fm10k_common.c index e303d88720ef..f51a63fca513 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_common.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2018 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k_common.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_common.h b/drivers/net/ethernet/intel/fm10k/fm10k_common.h index 2bdb24d2ca9d..4c48fb73b3e7 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_common.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_common.h @@ -1,23 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _FM10K_COMMON_H_ #define _FM10K_COMMON_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c index c4f733452ef2..20768ac7f17e 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_dcbnl.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c index 43e8d839831f..dca104121c05 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_debugfs.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c index 28b6b4e56487..7657daa27298 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_ethtool.c @@ -1,40 +1,32 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/vmalloc.h> #include "fm10k.h" struct fm10k_stats { + /* The stat_string is expected to be a format string formatted using + * vsnprintf by fm10k_add_stat_strings. Every member of a stats array + * should use the same format specifiers as they will be formatted + * using the same variadic arguments. + */ char stat_string[ETH_GSTRING_LEN]; int sizeof_stat; int stat_offset; }; -#define FM10K_NETDEV_STAT(_net_stat) { \ - .stat_string = #_net_stat, \ - .sizeof_stat = FIELD_SIZEOF(struct net_device_stats, _net_stat), \ - .stat_offset = offsetof(struct net_device_stats, _net_stat) \ +#define FM10K_STAT_FIELDS(_type, _name, _stat) { \ + .stat_string = _name, \ + .sizeof_stat = FIELD_SIZEOF(_type, _stat), \ + .stat_offset = offsetof(_type, _stat) \ } +/* netdevice statistics */ +#define FM10K_NETDEV_STAT(_net_stat) \ + FM10K_STAT_FIELDS(struct net_device_stats, __stringify(_net_stat), \ + _net_stat) + static const struct fm10k_stats fm10k_gstrings_net_stats[] = { FM10K_NETDEV_STAT(tx_packets), FM10K_NETDEV_STAT(tx_bytes), @@ -52,11 +44,9 @@ static const struct fm10k_stats fm10k_gstrings_net_stats[] = { #define FM10K_NETDEV_STATS_LEN ARRAY_SIZE(fm10k_gstrings_net_stats) -#define FM10K_STAT(_name, _stat) { \ - .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct fm10k_intfc, _stat), \ - .stat_offset = offsetof(struct fm10k_intfc, _stat) \ -} +/* General interface statistics */ +#define FM10K_STAT(_name, _stat) \ + FM10K_STAT_FIELDS(struct fm10k_intfc, _name, _stat) static const struct fm10k_stats fm10k_gstrings_global_stats[] = { FM10K_STAT("tx_restart_queue", restart_queue), @@ -93,11 +83,9 @@ static const struct fm10k_stats fm10k_gstrings_pf_stats[] = { FM10K_STAT("nodesc_drop", stats.nodesc_drop.count), }; -#define FM10K_MBX_STAT(_name, _stat) { \ - .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct fm10k_mbx_info, _stat), \ - .stat_offset = offsetof(struct fm10k_mbx_info, _stat) \ -} +/* mailbox statistics */ +#define FM10K_MBX_STAT(_name, _stat) \ + FM10K_STAT_FIELDS(struct fm10k_mbx_info, _name, _stat) static const struct fm10k_stats fm10k_gstrings_mbx_stats[] = { FM10K_MBX_STAT("mbx_tx_busy", tx_busy), @@ -111,15 +99,13 @@ static const struct fm10k_stats fm10k_gstrings_mbx_stats[] = { FM10K_MBX_STAT("mbx_rx_mbmem_pushed", rx_mbmem_pushed), }; -#define FM10K_QUEUE_STAT(_name, _stat) { \ - .stat_string = _name, \ - .sizeof_stat = FIELD_SIZEOF(struct fm10k_ring, _stat), \ - .stat_offset = offsetof(struct fm10k_ring, _stat) \ -} +/* per-queue ring statistics */ +#define FM10K_QUEUE_STAT(_name, _stat) \ + FM10K_STAT_FIELDS(struct fm10k_ring, _name, _stat) static const struct fm10k_stats fm10k_gstrings_queue_stats[] = { - FM10K_QUEUE_STAT("packets", stats.packets), - FM10K_QUEUE_STAT("bytes", stats.bytes), + FM10K_QUEUE_STAT("%s_queue_%u_packets", stats.packets), + FM10K_QUEUE_STAT("%s_queue_%u_bytes", stats.bytes), }; #define FM10K_GLOBAL_STATS_LEN ARRAY_SIZE(fm10k_gstrings_global_stats) @@ -149,49 +135,44 @@ enum { static const char fm10k_prv_flags[FM10K_PRV_FLAG_LEN][ETH_GSTRING_LEN] = { }; -static void fm10k_add_stat_strings(u8 **p, const char *prefix, - const struct fm10k_stats stats[], - const unsigned int size) +static void __fm10k_add_stat_strings(u8 **p, const struct fm10k_stats stats[], + const unsigned int size, ...) { unsigned int i; for (i = 0; i < size; i++) { - snprintf(*p, ETH_GSTRING_LEN, "%s%s", - prefix, stats[i].stat_string); + va_list args; + + va_start(args, size); + vsnprintf(*p, ETH_GSTRING_LEN, stats[i].stat_string, args); *p += ETH_GSTRING_LEN; + va_end(args); } } +#define fm10k_add_stat_strings(p, stats, ...) \ + __fm10k_add_stat_strings(p, stats, ARRAY_SIZE(stats), ## __VA_ARGS__) + static void fm10k_get_stat_strings(struct net_device *dev, u8 *data) { struct fm10k_intfc *interface = netdev_priv(dev); unsigned int i; - fm10k_add_stat_strings(&data, "", fm10k_gstrings_net_stats, - FM10K_NETDEV_STATS_LEN); + fm10k_add_stat_strings(&data, fm10k_gstrings_net_stats); - fm10k_add_stat_strings(&data, "", fm10k_gstrings_global_stats, - FM10K_GLOBAL_STATS_LEN); + fm10k_add_stat_strings(&data, fm10k_gstrings_global_stats); - fm10k_add_stat_strings(&data, "", fm10k_gstrings_mbx_stats, - FM10K_MBX_STATS_LEN); + fm10k_add_stat_strings(&data, fm10k_gstrings_mbx_stats); if (interface->hw.mac.type != fm10k_mac_vf) - fm10k_add_stat_strings(&data, "", fm10k_gstrings_pf_stats, - FM10K_PF_STATS_LEN); + fm10k_add_stat_strings(&data, fm10k_gstrings_pf_stats); for (i = 0; i < interface->hw.mac.max_queues; i++) { - char prefix[ETH_GSTRING_LEN]; - - snprintf(prefix, ETH_GSTRING_LEN, "tx_queue_%u_", i); - fm10k_add_stat_strings(&data, prefix, - fm10k_gstrings_queue_stats, - FM10K_QUEUE_STATS_LEN); + fm10k_add_stat_strings(&data, fm10k_gstrings_queue_stats, + "tx", i); - snprintf(prefix, ETH_GSTRING_LEN, "rx_queue_%u_", i); - fm10k_add_stat_strings(&data, prefix, - fm10k_gstrings_queue_stats, - FM10K_QUEUE_STATS_LEN); + fm10k_add_stat_strings(&data, fm10k_gstrings_queue_stats, + "rx", i); } } @@ -236,9 +217,9 @@ static int fm10k_get_sset_count(struct net_device *dev, int sset) } } -static void fm10k_add_ethtool_stats(u64 **data, void *pointer, - const struct fm10k_stats stats[], - const unsigned int size) +static void __fm10k_add_ethtool_stats(u64 **data, void *pointer, + const struct fm10k_stats stats[], + const unsigned int size) { unsigned int i; char *p; @@ -267,11 +248,16 @@ static void fm10k_add_ethtool_stats(u64 **data, void *pointer, *((*data)++) = *(u8 *)p; break; default: + WARN_ONCE(1, "unexpected stat size for %s", + stats[i].stat_string); *((*data)++) = 0; } } } +#define fm10k_add_ethtool_stats(data, pointer, stats) \ + __fm10k_add_ethtool_stats(data, pointer, stats, ARRAY_SIZE(stats)) + static void fm10k_get_ethtool_stats(struct net_device *netdev, struct ethtool_stats __always_unused *stats, u64 *data) @@ -282,20 +268,16 @@ static void fm10k_get_ethtool_stats(struct net_device *netdev, fm10k_update_stats(interface); - fm10k_add_ethtool_stats(&data, net_stats, fm10k_gstrings_net_stats, - FM10K_NETDEV_STATS_LEN); + fm10k_add_ethtool_stats(&data, net_stats, fm10k_gstrings_net_stats); - fm10k_add_ethtool_stats(&data, interface, fm10k_gstrings_global_stats, - FM10K_GLOBAL_STATS_LEN); + fm10k_add_ethtool_stats(&data, interface, fm10k_gstrings_global_stats); fm10k_add_ethtool_stats(&data, &interface->hw.mbx, - fm10k_gstrings_mbx_stats, - FM10K_MBX_STATS_LEN); + fm10k_gstrings_mbx_stats); if (interface->hw.mac.type != fm10k_mac_vf) { fm10k_add_ethtool_stats(&data, interface, - fm10k_gstrings_pf_stats, - FM10K_PF_STATS_LEN); + fm10k_gstrings_pf_stats); } for (i = 0; i < interface->hw.mac.max_queues; i++) { @@ -303,13 +285,11 @@ static void fm10k_get_ethtool_stats(struct net_device *netdev, ring = interface->tx_ring[i]; fm10k_add_ethtool_stats(&data, ring, - fm10k_gstrings_queue_stats, - FM10K_QUEUE_STATS_LEN); + fm10k_gstrings_queue_stats); ring = interface->rx_ring[i]; fm10k_add_ethtool_stats(&data, ring, - fm10k_gstrings_queue_stats, - FM10K_QUEUE_STATS_LEN); + fm10k_gstrings_queue_stats); } } diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c index 30395f5e5e87..e707d717012f 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_iov.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_iov.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k.h" #include "fm10k_vf.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_main.c b/drivers/net/ethernet/intel/fm10k/fm10k_main.c index df8607097e4a..3f536541f45f 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_main.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_main.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -445,15 +427,14 @@ static void fm10k_type_trans(struct fm10k_ring *rx_ring, l2_accel = NULL; } - skb->protocol = eth_type_trans(skb, dev); - /* Record Rx queue, or update macvlan statistics */ if (!l2_accel) skb_record_rx_queue(skb, rx_ring->queue_index); else macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true, - (skb->pkt_type == PACKET_BROADCAST) || - (skb->pkt_type == PACKET_MULTICAST)); + false); + + skb->protocol = eth_type_trans(skb, dev); } /** diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c index c01bf30a0c9e..21021fe4f1c3 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k_common.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h index 007e1dfa9b7a..56d1abff04e2 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_mbx.h @@ -1,23 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _FM10K_MBX_H_ #define _FM10K_MBX_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c index 45793491d4ba..929f538d28bc 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_netdev.c @@ -1,27 +1,10 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2018 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k.h" #include <linux/vmalloc.h> #include <net/udp_tunnel.h> +#include <linux/if_macvlan.h> /** * fm10k_setup_tx_resources - allocate Tx resources (Descriptors) @@ -924,7 +907,9 @@ static int fm10k_mc_vlan_unsync(struct net_device *netdev, static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) { struct fm10k_intfc *interface = netdev_priv(netdev); + struct fm10k_l2_accel *l2_accel = interface->l2_accel; struct fm10k_hw *hw = &interface->hw; + u16 glort; s32 err; int i; @@ -992,6 +977,22 @@ static int fm10k_update_vid(struct net_device *netdev, u16 vid, bool set) if (err) goto err_out; + /* Update L2 accelerated macvlan addresses */ + if (l2_accel) { + for (i = 0; i < l2_accel->size; i++) { + struct net_device *sdev = l2_accel->macvlan[i]; + + if (!sdev) + continue; + + glort = l2_accel->dglort + 1 + i; + + fm10k_queue_mac_request(interface, glort, + sdev->dev_addr, + vid, set); + } + } + /* set VLAN ID prior to syncing/unsyncing the VLAN */ interface->vid = vid + (set ? VLAN_N_VID : 0); @@ -1231,6 +1232,22 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) fm10k_queue_mac_request(interface, glort, hw->mac.addr, vid, true); + + /* synchronize macvlan addresses */ + if (l2_accel) { + for (i = 0; i < l2_accel->size; i++) { + struct net_device *sdev = l2_accel->macvlan[i]; + + if (!sdev) + continue; + + glort = l2_accel->dglort + 1 + i; + + fm10k_queue_mac_request(interface, glort, + sdev->dev_addr, + vid, true); + } + } } /* update xcast mode before synchronizing addresses if host's mailbox @@ -1254,7 +1271,7 @@ void fm10k_restore_rx_state(struct fm10k_intfc *interface) glort = l2_accel->dglort + 1 + i; hw->mac.ops.update_xcast_mode(hw, glort, - FM10K_XCAST_MODE_MULTI); + FM10K_XCAST_MODE_NONE); fm10k_queue_mac_request(interface, glort, sdev->dev_addr, hw->mac.default_vid, true); @@ -1447,7 +1464,14 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, struct fm10k_dglort_cfg dglort = { 0 }; struct fm10k_hw *hw = &interface->hw; int size = 0, i; - u16 glort; + u16 vid, glort; + + /* The hardware supported by fm10k only filters on the destination MAC + * address. In order to avoid issues we only support offloading modes + * where the hardware can actually provide the functionality. + */ + if (!macvlan_supports_dest_filter(sdev)) + return ERR_PTR(-EMEDIUMTYPE); /* allocate l2 accel structure if it is not available */ if (!l2_accel) { @@ -1513,12 +1537,18 @@ static void *fm10k_dfwd_add_station(struct net_device *dev, glort = l2_accel->dglort + 1 + i; - if (fm10k_host_mbx_ready(interface)) { + if (fm10k_host_mbx_ready(interface)) hw->mac.ops.update_xcast_mode(hw, glort, - FM10K_XCAST_MODE_MULTI); + FM10K_XCAST_MODE_NONE); + + fm10k_queue_mac_request(interface, glort, sdev->dev_addr, + hw->mac.default_vid, true); + + for (vid = fm10k_find_next_vlan(interface, 0); + vid < VLAN_N_VID; + vid = fm10k_find_next_vlan(interface, vid)) fm10k_queue_mac_request(interface, glort, sdev->dev_addr, - hw->mac.default_vid, true); - } + vid, true); fm10k_mbx_unlock(interface); @@ -1532,8 +1562,8 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv) struct fm10k_dglort_cfg dglort = { 0 }; struct fm10k_hw *hw = &interface->hw; struct net_device *sdev = priv; + u16 vid, glort; int i; - u16 glort; if (!l2_accel) return; @@ -1553,12 +1583,18 @@ static void fm10k_dfwd_del_station(struct net_device *dev, void *priv) glort = l2_accel->dglort + 1 + i; - if (fm10k_host_mbx_ready(interface)) { + if (fm10k_host_mbx_ready(interface)) hw->mac.ops.update_xcast_mode(hw, glort, FM10K_XCAST_MODE_NONE); + + fm10k_queue_mac_request(interface, glort, sdev->dev_addr, + hw->mac.default_vid, false); + + for (vid = fm10k_find_next_vlan(interface, 0); + vid < VLAN_N_VID; + vid = fm10k_find_next_vlan(interface, vid)) fm10k_queue_mac_request(interface, glort, sdev->dev_addr, - hw->mac.default_vid, false); - } + vid, false); fm10k_mbx_unlock(interface); diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c index c4a2b688b38b..15071e4adb98 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pci.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pci.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2018 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/module.h> #include <linux/interrupt.h> diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c index 7ba54c534f8c..8f0a99b6a537 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2018 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k_pf.h" #include "fm10k_vf.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h index ae81f9a16602..8e814df709d2 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_pf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_pf.h @@ -1,23 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _FM10K_PF_H_ #define _FM10K_PF_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c index 725ecb7abccd..2a7a40bf2b1c 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2018 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k_tlv.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h index 5d2ee759507e..160bc5b78f99 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_tlv.h @@ -1,23 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _FM10K_TLV_H_ #define _FM10K_TLV_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_type.h b/drivers/net/ethernet/intel/fm10k/fm10k_type.h index dd23af11e2c1..3e608e493f9d 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_type.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_type.h @@ -1,23 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _FM10K_TYPE_H_ #define _FM10K_TYPE_H_ diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c index f06913630b39..a8519c1f0406 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.c +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.c @@ -1,23 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "fm10k_vf.h" diff --git a/drivers/net/ethernet/intel/fm10k/fm10k_vf.h b/drivers/net/ethernet/intel/fm10k/fm10k_vf.h index 66a66b73a2f1..787d0d570a28 100644 --- a/drivers/net/ethernet/intel/fm10k/fm10k_vf.h +++ b/drivers/net/ethernet/intel/fm10k/fm10k_vf.h @@ -1,23 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Ethernet Switch Host Interface Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _FM10K_VF_H_ #define _FM10K_VF_H_ diff --git a/drivers/net/ethernet/intel/i40e/Makefile b/drivers/net/ethernet/intel/i40e/Makefile index 75437768a07c..14397e7e9925 100644 --- a/drivers/net/ethernet/intel/i40e/Makefile +++ b/drivers/net/ethernet/intel/i40e/Makefile @@ -1,29 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel Ethernet Controller XL710 Family Linux Driver -# Copyright(c) 2013 - 2015 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along -# with this program. If not, see <http://www.gnu.org/licenses/>. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ +# Copyright(c) 2013 - 2018 Intel Corporation. # # Makefile for the Intel(R) Ethernet Connection XL710 (i40e.ko) driver diff --git a/drivers/net/ethernet/intel/i40e/i40e.h b/drivers/net/ethernet/intel/i40e/i40e.h index a44139c1de80..7a80652e2500 100644 --- a/drivers/net/ethernet/intel/i40e/i40e.h +++ b/drivers/net/ethernet/intel/i40e/i40e.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_H_ #define _I40E_H_ @@ -334,10 +310,12 @@ struct i40e_tc_configuration { struct i40e_tc_info tc_info[I40E_MAX_TRAFFIC_CLASS]; }; +#define I40E_UDP_PORT_INDEX_UNUSED 255 struct i40e_udp_port_config { /* AdminQ command interface expects port number in Host byte order */ u16 port; u8 type; + u8 filter_index; }; /* macros related to FLX_PIT */ @@ -608,7 +586,7 @@ struct i40e_pf { unsigned long ptp_tx_start; struct hwtstamp_config tstamp_config; struct mutex tmreg_lock; /* Used to protect the SYSTIME registers. */ - u64 ptp_base_adj; + u32 ptp_adj_mult; u32 tx_hwtstamp_timeouts; u32 tx_hwtstamp_skipped; u32 rx_hwtstamp_cleared; @@ -1009,6 +987,9 @@ void i40e_service_event_schedule(struct i40e_pf *pf); void i40e_notify_client_of_vf_msg(struct i40e_vsi *vsi, u32 vf_id, u8 *msg, u16 len); +int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q, bool is_xdp, + bool enable); +int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable); int i40e_vsi_start_rings(struct i40e_vsi *vsi); void i40e_vsi_stop_rings(struct i40e_vsi *vsi); void i40e_vsi_stop_rings_no_wait(struct i40e_vsi *vsi); diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.c b/drivers/net/ethernet/intel/i40e/i40e_adminq.c index 843fc7781ef8..ddbea79d18e5 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_status.h" #include "i40e_type.h" diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq.h b/drivers/net/ethernet/intel/i40e/i40e_adminq.h index 0a8749ee9fd3..edec3df78971 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_ADMINQ_H_ #define _I40E_ADMINQ_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h index 0244923edeb8..7d888e05f96f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40e/i40e_adminq_cmd.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_ADMINQ_CMD_H_ #define _I40E_ADMINQ_CMD_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_alloc.h b/drivers/net/ethernet/intel/i40e/i40e_alloc.h index abed0c52e782..cb8689222c8b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_alloc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_alloc.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_ALLOC_H_ #define _I40E_ALLOC_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.c b/drivers/net/ethernet/intel/i40e/i40e_client.c index d8ce4999864f..5f3b8b9ff511 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.c +++ b/drivers/net/ethernet/intel/i40e/i40e_client.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/list.h> #include <linux/errno.h> @@ -64,7 +40,7 @@ static struct i40e_ops i40e_lan_ops = { /** * i40e_client_get_params - Get the params that can change at runtime * @vsi: the VSI with the message - * @param: clinet param struct + * @params: client param struct * **/ static @@ -590,7 +566,7 @@ static int i40e_client_virtchnl_send(struct i40e_info *ldev, * i40e_client_setup_qvlist * @ldev: pointer to L2 context. * @client: Client pointer. - * @qv_info: queue and vector list + * @qvlist_info: queue and vector list * * Return 0 on success or < 0 on error **/ @@ -665,7 +641,7 @@ err: * i40e_client_request_reset * @ldev: pointer to L2 context. * @client: Client pointer. - * @level: reset level + * @reset_level: reset level **/ static void i40e_client_request_reset(struct i40e_info *ldev, struct i40e_client *client, diff --git a/drivers/net/ethernet/intel/i40e/i40e_client.h b/drivers/net/ethernet/intel/i40e/i40e_client.h index 9d464d40bc17..72994baf4941 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_client.h +++ b/drivers/net/ethernet/intel/i40e/i40e_client.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_CLIENT_H_ #define _I40E_CLIENT_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_common.c b/drivers/net/ethernet/intel/i40e/i40e_common.c index c0a3dae8a2db..eb2d1530d331 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_common.c +++ b/drivers/net/ethernet/intel/i40e/i40e_common.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_type.h" #include "i40e_adminq.h" @@ -1695,6 +1671,8 @@ enum i40e_status_code i40e_aq_set_phy_config(struct i40e_hw *hw, /** * i40e_set_fc * @hw: pointer to the hw struct + * @aq_failures: buffer to return AdminQ failure information + * @atomic_restart: whether to enable atomic link restart * * Set the requested flow control mode using set_phy_config. **/ @@ -2831,8 +2809,8 @@ i40e_status i40e_aq_remove_macvlan(struct i40e_hw *hw, u16 seid, * @mr_list: list of mirrored VSI SEIDs or VLAN IDs * @cmd_details: pointer to command details structure or NULL * @rule_id: Rule ID returned from FW - * @rule_used: Number of rules used in internal switch - * @rule_free: Number of rules free in internal switch + * @rules_used: Number of rules used in internal switch + * @rules_free: Number of rules free in internal switch * * Add/Delete a mirror rule to a specific switch. Mirror rules are supported for * VEBs/VEPA elements only @@ -2892,8 +2870,8 @@ static i40e_status i40e_mirrorrule_op(struct i40e_hw *hw, * @mr_list: list of mirrored VSI SEIDs or VLAN IDs * @cmd_details: pointer to command details structure or NULL * @rule_id: Rule ID returned from FW - * @rule_used: Number of rules used in internal switch - * @rule_free: Number of rules free in internal switch + * @rules_used: Number of rules used in internal switch + * @rules_free: Number of rules free in internal switch * * Add mirror rule. Mirror rules are supported for VEBs or VEPA elements only **/ @@ -2923,8 +2901,8 @@ i40e_status i40e_aq_add_mirrorrule(struct i40e_hw *hw, u16 sw_seid, * add_mirrorrule. * @mr_list: list of mirrored VLAN IDs to be removed * @cmd_details: pointer to command details structure or NULL - * @rule_used: Number of rules used in internal switch - * @rule_free: Number of rules free in internal switch + * @rules_used: Number of rules used in internal switch + * @rules_free: Number of rules free in internal switch * * Delete a mirror rule. Mirror rules are supported for VEBs/VEPA elements only **/ @@ -3672,6 +3650,8 @@ i40e_status i40e_aq_stop_lldp(struct i40e_hw *hw, bool shutdown_agent, /** * i40e_aq_start_lldp * @hw: pointer to the hw struct + * @buff: buffer for result + * @buff_size: buffer size * @cmd_details: pointer to command details structure or NULL * * Start the embedded LLDP Agent on all ports. @@ -3752,7 +3732,6 @@ i40e_status i40e_aq_get_cee_dcb_config(struct i40e_hw *hw, * i40e_aq_add_udp_tunnel * @hw: pointer to the hw struct * @udp_port: the UDP port to add in Host byte order - * @header_len: length of the tunneling header length in DWords * @protocol_index: protocol index type * @filter_index: pointer to filter index * @cmd_details: pointer to command details structure or NULL @@ -3971,6 +3950,7 @@ i40e_status i40e_aq_config_vsi_tc_bw(struct i40e_hw *hw, * @hw: pointer to the hw struct * @seid: seid of the switching component connected to Physical Port * @ets_data: Buffer holding ETS parameters + * @opcode: Tx scheduler AQ command opcode * @cmd_details: pointer to command details structure or NULL **/ i40e_status i40e_aq_config_switch_comp_ets(struct i40e_hw *hw, @@ -4314,10 +4294,10 @@ i40e_status i40e_aq_add_rem_control_packet_filter(struct i40e_hw *hw, * @hw: pointer to the hw struct * @seid: VSI seid to add ethertype filter from **/ -#define I40E_FLOW_CONTROL_ETHTYPE 0x8808 void i40e_add_filter_to_drop_tx_flow_control_frames(struct i40e_hw *hw, u16 seid) { +#define I40E_FLOW_CONTROL_ETHTYPE 0x8808 u16 flag = I40E_AQC_ADD_CONTROL_PACKET_FLAGS_IGNORE_MAC | I40E_AQC_ADD_CONTROL_PACKET_FLAGS_DROP | I40E_AQC_ADD_CONTROL_PACKET_FLAGS_TX; @@ -4448,6 +4428,7 @@ void i40e_set_pci_config_data(struct i40e_hw *hw, u16 link_status) * @ret_buff_size: actual buffer size returned * @ret_next_table: next block to read * @ret_next_index: next index to read + * @cmd_details: pointer to command details structure or NULL * * Dump internal FW/HW data for debug purposes. * @@ -4574,7 +4555,7 @@ i40e_status i40e_aq_configure_partition_bw(struct i40e_hw *hw, * i40e_read_phy_register_clause22 * @hw: pointer to the HW structure * @reg: register address in the page - * @phy_adr: PHY address on MDIO interface + * @phy_addr: PHY address on MDIO interface * @value: PHY register value * * Reads specified PHY register value @@ -4619,7 +4600,7 @@ i40e_status i40e_read_phy_register_clause22(struct i40e_hw *hw, * i40e_write_phy_register_clause22 * @hw: pointer to the HW structure * @reg: register address in the page - * @phy_adr: PHY address on MDIO interface + * @phy_addr: PHY address on MDIO interface * @value: PHY register value * * Writes specified PHY register value @@ -4660,7 +4641,7 @@ i40e_status i40e_write_phy_register_clause22(struct i40e_hw *hw, * @hw: pointer to the HW structure * @page: registers page number * @reg: register address in the page - * @phy_adr: PHY address on MDIO interface + * @phy_addr: PHY address on MDIO interface * @value: PHY register value * * Reads specified PHY register value @@ -4734,7 +4715,7 @@ phy_read_end: * @hw: pointer to the HW structure * @page: registers page number * @reg: register address in the page - * @phy_adr: PHY address on MDIO interface + * @phy_addr: PHY address on MDIO interface * @value: PHY register value * * Writes value to specified PHY register @@ -4801,7 +4782,7 @@ phy_write_end: * @hw: pointer to the HW structure * @page: registers page number * @reg: register address in the page - * @phy_adr: PHY address on MDIO interface + * @phy_addr: PHY address on MDIO interface * @value: PHY register value * * Writes value to specified PHY register @@ -4837,7 +4818,7 @@ i40e_status i40e_write_phy_register(struct i40e_hw *hw, * @hw: pointer to the HW structure * @page: registers page number * @reg: register address in the page - * @phy_adr: PHY address on MDIO interface + * @phy_addr: PHY address on MDIO interface * @value: PHY register value * * Reads specified PHY register value @@ -4872,7 +4853,6 @@ i40e_status i40e_read_phy_register(struct i40e_hw *hw, * i40e_get_phy_address * @hw: pointer to the HW structure * @dev_num: PHY port num that address we want - * @phy_addr: Returned PHY address * * Gets PHY address for current port **/ @@ -5082,7 +5062,9 @@ i40e_status i40e_led_get_phy(struct i40e_hw *hw, u16 *led_addr, * i40e_led_set_phy * @hw: pointer to the HW structure * @on: true or false + * @led_addr: address of led register to use * @mode: original val plus bit for set or ignore + * * Set led's on or off when controlled by the PHY * **/ @@ -5371,6 +5353,7 @@ i40e_status_code i40e_aq_write_ddp(struct i40e_hw *hw, void *buff, * @hw: pointer to the hw struct * @buff: command buffer (size in bytes = buff_size) * @buff_size: buffer size in bytes + * @flags: AdminQ command flags * @cmd_details: pointer to command details structure or NULL **/ enum diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.c b/drivers/net/ethernet/intel/i40e/i40e_dcb.c index 9fec728dc4b9..56bff8faf371 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_adminq.h" #include "i40e_prototype.h" @@ -945,6 +921,70 @@ i40e_status i40e_init_dcb(struct i40e_hw *hw) } /** + * _i40e_read_lldp_cfg - generic read of LLDP Configuration data from NVM + * @hw: pointer to the HW structure + * @lldp_cfg: pointer to hold lldp configuration variables + * @module: address of the module pointer + * @word_offset: offset of LLDP configuration + * + * Reads the LLDP configuration data from NVM using passed addresses + **/ +static i40e_status _i40e_read_lldp_cfg(struct i40e_hw *hw, + struct i40e_lldp_variables *lldp_cfg, + u8 module, u32 word_offset) +{ + u32 address, offset = (2 * word_offset); + i40e_status ret; + __le16 raw_mem; + u16 mem; + + ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (ret) + return ret; + + ret = i40e_aq_read_nvm(hw, 0x0, module * 2, sizeof(raw_mem), &raw_mem, + true, NULL); + i40e_release_nvm(hw); + if (ret) + return ret; + + mem = le16_to_cpu(raw_mem); + /* Check if this pointer needs to be read in word size or 4K sector + * units. + */ + if (mem & I40E_PTR_TYPE) + address = (0x7FFF & mem) * 4096; + else + address = (0x7FFF & mem) * 2; + + ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (ret) + goto err_lldp_cfg; + + ret = i40e_aq_read_nvm(hw, module, offset, sizeof(raw_mem), &raw_mem, + true, NULL); + i40e_release_nvm(hw); + if (ret) + return ret; + + mem = le16_to_cpu(raw_mem); + offset = mem + word_offset; + offset *= 2; + + ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); + if (ret) + goto err_lldp_cfg; + + ret = i40e_aq_read_nvm(hw, 0, address + offset, + sizeof(struct i40e_lldp_variables), lldp_cfg, + true, NULL); + i40e_release_nvm(hw); + +err_lldp_cfg: + return ret; +} + +/** * i40e_read_lldp_cfg - read LLDP Configuration data from NVM * @hw: pointer to the HW structure * @lldp_cfg: pointer to hold lldp configuration variables @@ -955,21 +995,34 @@ i40e_status i40e_read_lldp_cfg(struct i40e_hw *hw, struct i40e_lldp_variables *lldp_cfg) { i40e_status ret = 0; - u32 offset = (2 * I40E_NVM_LLDP_CFG_PTR); + u32 mem; if (!lldp_cfg) return I40E_ERR_PARAM; ret = i40e_acquire_nvm(hw, I40E_RESOURCE_READ); if (ret) - goto err_lldp_cfg; + return ret; - ret = i40e_aq_read_nvm(hw, I40E_SR_EMP_MODULE_PTR, offset, - sizeof(struct i40e_lldp_variables), - (u8 *)lldp_cfg, - true, NULL); + ret = i40e_aq_read_nvm(hw, I40E_SR_NVM_CONTROL_WORD, 0, sizeof(mem), + &mem, true, NULL); i40e_release_nvm(hw); + if (ret) + return ret; + + /* Read a bit that holds information whether we are running flat or + * structured NVM image. Flat image has LLDP configuration in shadow + * ram, so there is a need to pass different addresses for both cases. + */ + if (mem & I40E_SR_NVM_MAP_STRUCTURE_TYPE) { + /* Flat NVM case */ + ret = _i40e_read_lldp_cfg(hw, lldp_cfg, I40E_SR_EMP_MODULE_PTR, + I40E_SR_LLDP_CFG_PTR); + } else { + /* Good old structured NVM image */ + ret = _i40e_read_lldp_cfg(hw, lldp_cfg, I40E_EMP_MODULE_PTR, + I40E_NVM_LLDP_CFG_PTR); + } -err_lldp_cfg: return ret; } diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb.h b/drivers/net/ethernet/intel/i40e/i40e_dcb.h index 4f806386cb22..2b748a60a843 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb.h +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_DCB_H_ #define _I40E_DCB_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c index 502818e3da78..9deae9a35423 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c +++ b/drivers/net/ethernet/intel/i40e/i40e_dcb_nl.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifdef CONFIG_I40E_DCB #include "i40e.h" @@ -47,7 +23,7 @@ static void i40e_get_pfc_delay(struct i40e_hw *hw, u16 *delay) /** * i40e_dcbnl_ieee_getets - retrieve local IEEE ETS configuration - * @netdev: the corresponding netdev + * @dev: the corresponding netdev * @ets: structure to hold the ETS information * * Returns local IEEE ETS configuration @@ -86,8 +62,8 @@ static int i40e_dcbnl_ieee_getets(struct net_device *dev, /** * i40e_dcbnl_ieee_getpfc - retrieve local IEEE PFC configuration - * @netdev: the corresponding netdev - * @ets: structure to hold the PFC information + * @dev: the corresponding netdev + * @pfc: structure to hold the PFC information * * Returns local IEEE PFC configuration **/ @@ -119,7 +95,7 @@ static int i40e_dcbnl_ieee_getpfc(struct net_device *dev, /** * i40e_dcbnl_getdcbx - retrieve current DCBx capability - * @netdev: the corresponding netdev + * @dev: the corresponding netdev * * Returns DCBx capability features **/ @@ -132,7 +108,8 @@ static u8 i40e_dcbnl_getdcbx(struct net_device *dev) /** * i40e_dcbnl_get_perm_hw_addr - MAC address used by DCBx - * @netdev: the corresponding netdev + * @dev: the corresponding netdev + * @perm_addr: buffer to store the MAC address * * Returns the SAN MAC address used for LLDP exchange **/ diff --git a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c index d494dcaf18d0..56b911a5dd8b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_debugfs.c +++ b/drivers/net/ethernet/intel/i40e/i40e_debugfs.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifdef CONFIG_DEBUG_FS @@ -36,8 +12,8 @@ static struct dentry *i40e_dbg_root; /** * i40e_dbg_find_vsi - searches for the vsi with the given seid - * @pf - the PF structure to search for the vsi - * @seid - seid of the vsi it is searching for + * @pf: the PF structure to search for the vsi + * @seid: seid of the vsi it is searching for **/ static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid) { @@ -55,8 +31,8 @@ static struct i40e_vsi *i40e_dbg_find_vsi(struct i40e_pf *pf, int seid) /** * i40e_dbg_find_veb - searches for the veb with the given seid - * @pf - the PF structure to search for the veb - * @seid - seid of the veb it is searching for + * @pf: the PF structure to search for the veb + * @seid: seid of the veb it is searching for **/ static struct i40e_veb *i40e_dbg_find_veb(struct i40e_pf *pf, int seid) { diff --git a/drivers/net/ethernet/intel/i40e/i40e_devids.h b/drivers/net/ethernet/intel/i40e/i40e_devids.h index ad6a66ccb576..334b05ff685a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_devids.h +++ b/drivers/net/ethernet/intel/i40e/i40e_devids.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_DEVIDS_H_ #define _I40E_DEVIDS_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.c b/drivers/net/ethernet/intel/i40e/i40e_diag.c index df3e60470f8b..ef4d3762bf37 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.c +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_diag.h" #include "i40e_prototype.h" diff --git a/drivers/net/ethernet/intel/i40e/i40e_diag.h b/drivers/net/ethernet/intel/i40e/i40e_diag.h index be8341763475..c3340f320a18 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_diag.h +++ b/drivers/net/ethernet/intel/i40e/i40e_diag.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_DIAG_H_ #define _I40E_DIAG_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c index b974482ff630..fc6a5eef141c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ethtool.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ethtool.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ /* ethtool support for i40e */ @@ -977,7 +953,9 @@ static int i40e_set_link_ksettings(struct net_device *netdev, ethtool_link_ksettings_test_link_mode(ks, advertising, 10000baseCR_Full) || ethtool_link_ksettings_test_link_mode(ks, advertising, - 10000baseSR_Full)) + 10000baseSR_Full) || + ethtool_link_ksettings_test_link_mode(ks, advertising, + 10000baseLR_Full)) config.link_speed |= I40E_LINK_SPEED_10GB; if (ethtool_link_ksettings_test_link_mode(ks, advertising, 20000baseKR2_Full)) @@ -1079,6 +1057,9 @@ static int i40e_nway_reset(struct net_device *netdev) /** * i40e_get_pauseparam - Get Flow Control status + * @netdev: netdevice structure + * @pause: buffer to return pause parameters + * * Return tx/rx-pause status **/ static void i40e_get_pauseparam(struct net_device *netdev, @@ -2550,7 +2531,7 @@ static int i40e_get_rss_hash_opts(struct i40e_pf *pf, struct ethtool_rxnfc *cmd) /** * i40e_check_mask - Check whether a mask field is set * @mask: the full mask value - * @field; mask of the field to check + * @field: mask of the field to check * * If the given mask is fully set, return positive value. If the mask for the * field is fully unset, return zero. Otherwise return a negative error code. @@ -2621,6 +2602,7 @@ static int i40e_parse_rx_flow_user_data(struct ethtool_rx_flow_spec *fsp, /** * i40e_fill_rx_flow_user_data - Fill in user-defined data field * @fsp: pointer to rx_flow specification + * @data: pointer to return userdef data * * Reads the userdef data structure and properly fills in the user defined * fields of the rx_flow_spec. @@ -2799,6 +2781,7 @@ no_input_set: * i40e_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command + * @rule_locs: pointer to store rule data * * Returns Success if the command is supported. **/ @@ -2840,7 +2823,7 @@ static int i40e_get_rxnfc(struct net_device *netdev, struct ethtool_rxnfc *cmd, /** * i40e_get_rss_hash_bits - Read RSS Hash bits from register * @nfc: pointer to user request - * @i_setc bits currently set + * @i_setc: bits currently set * * Returns value of bits to be set per user request **/ @@ -2885,7 +2868,7 @@ static u64 i40e_get_rss_hash_bits(struct ethtool_rxnfc *nfc, u64 i_setc) /** * i40e_set_rss_hash_opt - Enable/Disable flow types for RSS hash * @pf: pointer to the physical function struct - * @cmd: ethtool rxnfc command + * @nfc: ethtool rxnfc command * * Returns Success if the flow input set is supported. **/ @@ -3284,7 +3267,7 @@ static int i40e_add_flex_offset(struct list_head *flex_pit_list, * __i40e_reprogram_flex_pit - Re-program specific FLX_PIT table * @pf: Pointer to the PF structure * @flex_pit_list: list of flexible src offsets in use - * #flex_pit_start: index to first entry for this section of the table + * @flex_pit_start: index to first entry for this section of the table * * In order to handle flexible data, the hardware uses a table of values * called the FLX_PIT table. This table is used to indicate which sections of @@ -3398,7 +3381,7 @@ static void i40e_reprogram_flex_pit(struct i40e_pf *pf) /** * i40e_flow_str - Converts a flow_type into a human readable string - * @flow_type: the flow type from a flow specification + * @fsp: the flow specification * * Currently only flow types we support are included here, and the string * value attempts to match what ethtool would use to configure this flow type. @@ -4103,7 +4086,7 @@ static unsigned int i40e_max_channels(struct i40e_vsi *vsi) /** * i40e_get_channels - Get the current channels enabled and max supported etc. - * @netdev: network interface device structure + * @dev: network interface device structure * @ch: ethtool channels structure * * We don't support separate tx and rx queues as channels. The other count @@ -4112,7 +4095,7 @@ static unsigned int i40e_max_channels(struct i40e_vsi *vsi) * q_vectors since we support a lot more queue pairs than q_vectors. **/ static void i40e_get_channels(struct net_device *dev, - struct ethtool_channels *ch) + struct ethtool_channels *ch) { struct i40e_netdev_priv *np = netdev_priv(dev); struct i40e_vsi *vsi = np->vsi; @@ -4131,14 +4114,14 @@ static void i40e_get_channels(struct net_device *dev, /** * i40e_set_channels - Set the new channels count. - * @netdev: network interface device structure + * @dev: network interface device structure * @ch: ethtool channels structure * * The new channels count may not be the same as requested by the user * since it gets rounded down to a power of 2 value. **/ static int i40e_set_channels(struct net_device *dev, - struct ethtool_channels *ch) + struct ethtool_channels *ch) { const u8 drop = I40E_FILTER_PROGRAM_DESC_DEST_DROP_PACKET; struct i40e_netdev_priv *np = netdev_priv(dev); @@ -4273,6 +4256,7 @@ out: * @netdev: network interface device structure * @indir: indirection table * @key: hash key + * @hfunc: hash function to use * * Returns -EINVAL if the table specifies an invalid queue id, otherwise * returns 0 after programming the table. diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_hmc.c index 6d4b590f851b..19ce93d7fd0a 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_osdep.h" #include "i40e_register.h" @@ -198,7 +174,6 @@ exit: * @hw: pointer to our HW structure * @hmc_info: pointer to the HMC configuration information structure * @idx: the page index - * @is_pf: distinguishes a VF from a PF * * This function: * 1. Marks the entry in pd tabe (for paged address mode) or in sd table diff --git a/drivers/net/ethernet/intel/i40e/i40e_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_hmc.h index 7b5fd33d70ae..1c78de838857 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_hmc.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_HMC_H_ #define _I40E_HMC_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c index cd40dc487b38..994011c38fb4 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_osdep.h" #include "i40e_register.h" diff --git a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h index 79e1396735d9..c46a2c449e60 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h +++ b/drivers/net/ethernet/intel/i40e/i40e_lan_hmc.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_LAN_HMC_H_ #define _I40E_LAN_HMC_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_main.c b/drivers/net/ethernet/intel/i40e/i40e_main.c index 16229998fb1e..c8659fbd7111 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_main.c +++ b/drivers/net/ethernet/intel/i40e/i40e_main.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/etherdevice.h> #include <linux/of_net.h> @@ -278,8 +254,8 @@ static int i40e_put_lump(struct i40e_lump_tracking *pile, u16 index, u16 id) /** * i40e_find_vsi_from_id - searches for the vsi with the given id - * @pf - the pf structure to search for the vsi - * @id - id of the vsi it is searching for + * @pf: the pf structure to search for the vsi + * @id: id of the vsi it is searching for **/ struct i40e_vsi *i40e_find_vsi_from_id(struct i40e_pf *pf, u16 id) { @@ -435,6 +411,7 @@ static void i40e_get_netdev_stats_struct_tx(struct i40e_ring *ring, /** * i40e_get_netdev_stats_struct - Get statistics for netdev interface * @netdev: network interface device structure + * @stats: data structure to store statistics * * Returns the address of the device statistics structure. * The statistics are actually updated from the service task. @@ -2027,7 +2004,7 @@ struct i40e_new_mac_filter *i40e_next_filter(struct i40e_new_mac_filter *next) * from firmware * @count: Number of filters added * @add_list: return data from fw - * @head: pointer to first filter in current batch + * @add_head: pointer to first filter in current batch * * MAC filter entries from list were slated to be added to device. Returns * number of successful filters. Note that 0 does NOT mean success! @@ -2134,6 +2111,7 @@ void i40e_aqc_add_filters(struct i40e_vsi *vsi, const char *vsi_name, /** * i40e_aqc_broadcast_filter - Set promiscuous broadcast flags * @vsi: pointer to the VSI + * @vsi_name: the VSI name * @f: filter data * * This function sets or clears the promiscuous broadcast flags for VLAN @@ -2840,6 +2818,7 @@ void i40e_vsi_kill_vlan(struct i40e_vsi *vsi, u16 vid) /** * i40e_vlan_rx_add_vid - Add a vlan id filter to HW offload * @netdev: network interface to be adjusted + * @proto: unused protocol value * @vid: vlan id to be added * * net_device_ops implementation for adding vlan ids @@ -2864,6 +2843,7 @@ static int i40e_vlan_rx_add_vid(struct net_device *netdev, /** * i40e_vlan_rx_kill_vid - Remove a vlan id filter from HW offload * @netdev: network interface to be adjusted + * @proto: unused protocol value * @vid: vlan id to be removed * * net_device_ops implementation for removing vlan ids @@ -3485,7 +3465,7 @@ static void i40e_vsi_configure_msix(struct i40e_vsi *vsi) /** * i40e_enable_misc_int_causes - enable the non-queue interrupts - * @hw: ptr to the hardware info + * @pf: pointer to private device data structure **/ static void i40e_enable_misc_int_causes(struct i40e_pf *pf) { @@ -4255,8 +4235,8 @@ static void i40e_control_tx_q(struct i40e_pf *pf, int pf_q, bool enable) * @is_xdp: true if the queue is used for XDP * @enable: start or stop the queue **/ -static int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q, - bool is_xdp, bool enable) +int i40e_control_wait_tx_q(int seid, struct i40e_pf *pf, int pf_q, + bool is_xdp, bool enable) { int ret; @@ -4301,7 +4281,6 @@ static int i40e_vsi_control_tx(struct i40e_vsi *vsi, bool enable) if (ret) break; } - return ret; } @@ -4340,9 +4319,9 @@ static int i40e_pf_rxq_wait(struct i40e_pf *pf, int pf_q, bool enable) * @pf_q: the PF queue to configure * @enable: start or stop the queue * - * This function enables or disables a single queue. Note that any delay - * required after the operation is expected to be handled by the caller of - * this function. + * This function enables or disables a single queue. Note that + * any delay required after the operation is expected to be + * handled by the caller of this function. **/ static void i40e_control_rx_q(struct i40e_pf *pf, int pf_q, bool enable) { @@ -4372,6 +4351,30 @@ static void i40e_control_rx_q(struct i40e_pf *pf, int pf_q, bool enable) } /** + * i40e_control_wait_rx_q + * @pf: the PF structure + * @pf_q: queue being configured + * @enable: start or stop the rings + * + * This function enables or disables a single queue along with waiting + * for the change to finish. The caller of this function should handle + * the delays needed in the case of disabling queues. + **/ +int i40e_control_wait_rx_q(struct i40e_pf *pf, int pf_q, bool enable) +{ + int ret = 0; + + i40e_control_rx_q(pf, pf_q, enable); + + /* wait for the change to finish */ + ret = i40e_pf_rxq_wait(pf, pf_q, enable); + if (ret) + return ret; + + return ret; +} + +/** * i40e_vsi_control_rx - Start or stop a VSI's rings * @vsi: the VSI being configured * @enable: start or stop the rings @@ -4383,10 +4386,7 @@ static int i40e_vsi_control_rx(struct i40e_vsi *vsi, bool enable) pf_q = vsi->base_queue; for (i = 0; i < vsi->num_queue_pairs; i++, pf_q++) { - i40e_control_rx_q(pf, pf_q, enable); - - /* wait for the change to finish */ - ret = i40e_pf_rxq_wait(pf, pf_q, enable); + ret = i40e_control_wait_rx_q(pf, pf_q, enable); if (ret) { dev_info(&pf->pdev->dev, "VSI seid %d Rx ring %d %sable timeout\n", @@ -5096,7 +5096,7 @@ static int i40e_vsi_get_bw_info(struct i40e_vsi *vsi) * i40e_vsi_configure_bw_alloc - Configure VSI BW allocation per TC * @vsi: the VSI being configured * @enabled_tc: TC bitmap - * @bw_credits: BW shared credits per TC + * @bw_share: BW shared credits per TC * * Returns 0 on success, negative value on failure **/ @@ -6353,6 +6353,7 @@ out: /** * i40e_print_link_message - print link up or down * @vsi: the VSI for which link needs a message + * @isup: true of link is up, false otherwise */ void i40e_print_link_message(struct i40e_vsi *vsi, bool isup) { @@ -7212,8 +7213,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, if (mask->dst == cpu_to_be32(0xffffffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { - mask->dst = be32_to_cpu(mask->dst); - dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4\n", + dev_err(&pf->pdev->dev, "Bad ip dst mask %pI4b\n", &mask->dst); return I40E_ERR_CONFIG; } @@ -7223,8 +7223,7 @@ static int i40e_parse_cls_flower(struct i40e_vsi *vsi, if (mask->src == cpu_to_be32(0xffffffff)) { field_flags |= I40E_CLOUD_FIELD_IIP; } else { - mask->src = be32_to_cpu(mask->src); - dev_err(&pf->pdev->dev, "Bad ip src mask %pI4\n", + dev_err(&pf->pdev->dev, "Bad ip src mask %pI4b\n", &mask->src); return I40E_ERR_CONFIG; } @@ -9691,9 +9690,9 @@ static void i40e_handle_mdd_event(struct i40e_pf *pf) i40e_flush(hw); } -static const char *i40e_tunnel_name(struct i40e_udp_port_config *port) +static const char *i40e_tunnel_name(u8 type) { - switch (port->type) { + switch (type) { case UDP_TUNNEL_TYPE_VXLAN: return "vxlan"; case UDP_TUNNEL_TYPE_GENEVE: @@ -9727,37 +9726,68 @@ static void i40e_sync_udp_filters(struct i40e_pf *pf) static void i40e_sync_udp_filters_subtask(struct i40e_pf *pf) { struct i40e_hw *hw = &pf->hw; - i40e_status ret; + u8 filter_index, type; u16 port; int i; if (!test_and_clear_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state)) return; + /* acquire RTNL to maintain state of flags and port requests */ + rtnl_lock(); + for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { if (pf->pending_udp_bitmap & BIT_ULL(i)) { + struct i40e_udp_port_config *udp_port; + i40e_status ret = 0; + + udp_port = &pf->udp_ports[i]; pf->pending_udp_bitmap &= ~BIT_ULL(i); - port = pf->udp_ports[i].port; + + port = READ_ONCE(udp_port->port); + type = READ_ONCE(udp_port->type); + filter_index = READ_ONCE(udp_port->filter_index); + + /* release RTNL while we wait on AQ command */ + rtnl_unlock(); + if (port) ret = i40e_aq_add_udp_tunnel(hw, port, - pf->udp_ports[i].type, - NULL, NULL); - else - ret = i40e_aq_del_udp_tunnel(hw, i, NULL); + type, + &filter_index, + NULL); + else if (filter_index != I40E_UDP_PORT_INDEX_UNUSED) + ret = i40e_aq_del_udp_tunnel(hw, filter_index, + NULL); + + /* reacquire RTNL so we can update filter_index */ + rtnl_lock(); if (ret) { dev_info(&pf->pdev->dev, "%s %s port %d, index %d failed, err %s aq_err %s\n", - i40e_tunnel_name(&pf->udp_ports[i]), + i40e_tunnel_name(type), port ? "add" : "delete", - port, i, + port, + filter_index, i40e_stat_str(&pf->hw, ret), i40e_aq_str(&pf->hw, pf->hw.aq.asq_last_status)); - pf->udp_ports[i].port = 0; + if (port) { + /* failed to add, just reset port, + * drop pending bit for any deletion + */ + udp_port->port = 0; + pf->pending_udp_bitmap &= ~BIT_ULL(i); + } + } else if (port) { + /* record filter index on success */ + udp_port->filter_index = filter_index; } } } + + rtnl_unlock(); } /** @@ -10004,7 +10034,7 @@ unlock_pf: /** * i40e_vsi_free_arrays - Free queue and vector pointer arrays for the VSI - * @type: VSI pointer + * @vsi: VSI pointer * @free_qvectors: a bool to specify if q_vectors need to be freed. * * On error: returns error code (negative) @@ -10800,7 +10830,7 @@ int i40e_config_rss(struct i40e_vsi *vsi, u8 *seed, u8 *lut, u16 lut_size) * @vsi: Pointer to VSI structure * @seed: Buffer to store the keys * @lut: Buffer to store the lookup table entries - * lut_size: Size of buffer to store the lookup table entries + * @lut_size: Size of buffer to store the lookup table entries * * Returns 0 on success, negative on failure */ @@ -11374,6 +11404,11 @@ static u8 i40e_get_udp_port_idx(struct i40e_pf *pf, u16 port) u8 i; for (i = 0; i < I40E_MAX_PF_UDP_OFFLOAD_PORTS; i++) { + /* Do not report ports with pending deletions as + * being available. + */ + if (!port && (pf->pending_udp_bitmap & BIT_ULL(i))) + continue; if (pf->udp_ports[i].port == port) return i; } @@ -11428,6 +11463,7 @@ static void i40e_udp_tunnel_add(struct net_device *netdev, /* New port: add it and mark its index in the bitmap */ pf->udp_ports[next_idx].port = port; + pf->udp_ports[next_idx].filter_index = I40E_UDP_PORT_INDEX_UNUSED; pf->pending_udp_bitmap |= BIT_ULL(next_idx); set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state); } @@ -11469,7 +11505,12 @@ static void i40e_udp_tunnel_del(struct net_device *netdev, * and make it pending */ pf->udp_ports[idx].port = 0; - pf->pending_udp_bitmap |= BIT_ULL(idx); + + /* Toggle pending bit instead of setting it. This way if we are + * deleting a port that has yet to be added we just clear the pending + * bit and don't have to worry about it. + */ + pf->pending_udp_bitmap ^= BIT_ULL(idx); set_bit(__I40E_UDP_FILTER_SYNC_PENDING, pf->state); return; @@ -11500,6 +11541,7 @@ static int i40e_get_phys_port_id(struct net_device *netdev, * @tb: pointer to array of nladdr (unused) * @dev: the net device pointer * @addr: the MAC address entry being added + * @vid: VLAN ID * @flags: instructions from stack about fdb operation */ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], @@ -11545,6 +11587,7 @@ static int i40e_ndo_fdb_add(struct ndmsg *ndm, struct nlattr *tb[], * i40e_ndo_bridge_setlink - Set the hardware bridge mode * @dev: the netdev being configured * @nlh: RTNL message + * @flags: bridge flags * * Inserts a new hardware bridge if not already created and * enables the bridging mode requested (VEB or VEPA). If the @@ -14118,6 +14161,7 @@ static void i40e_remove(struct pci_dev *pdev) /** * i40e_pci_error_detected - warning that something funky happened in PCI land * @pdev: PCI device information struct + * @error: the type of PCI error * * Called to warn that something happened and the error handling steps * are in progress. Allows the driver to quiesce things, be ready for diff --git a/drivers/net/ethernet/intel/i40e/i40e_nvm.c b/drivers/net/ethernet/intel/i40e/i40e_nvm.c index ba9687c03795..0299e5bbb902 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_nvm.c +++ b/drivers/net/ethernet/intel/i40e/i40e_nvm.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_prototype.h" @@ -1173,6 +1149,7 @@ void i40e_nvmupd_clear_wait_state(struct i40e_hw *hw) * i40e_nvmupd_check_wait_event - handle NVM update operation events * @hw: pointer to the hardware structure * @opcode: the event that just happened + * @desc: AdminQ descriptor **/ void i40e_nvmupd_check_wait_event(struct i40e_hw *hw, u16 opcode, struct i40e_aq_desc *desc) diff --git a/drivers/net/ethernet/intel/i40e/i40e_osdep.h b/drivers/net/ethernet/intel/i40e/i40e_osdep.h index 9c3c3b0d3ac4..a07574bff550 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40e/i40e_osdep.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_OSDEP_H_ #define _I40E_OSDEP_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_prototype.h b/drivers/net/ethernet/intel/i40e/i40e_prototype.h index 2ec24188d6e2..3170655cdeb9 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40e/i40e_prototype.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_PROTOTYPE_H_ #define _I40E_PROTOTYPE_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_ptp.c b/drivers/net/ethernet/intel/i40e/i40e_ptp.c index 5b47dd1f75a5..aa3daec2049d 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_ptp.c +++ b/drivers/net/ethernet/intel/i40e/i40e_ptp.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e.h" #include <linux/ptp_classify.h> @@ -40,9 +16,9 @@ * At 1Gb link, the period is multiplied by 20. (32ns) * 1588 functionality is not supported at 100Mbps. */ -#define I40E_PTP_40GB_INCVAL 0x0199999999ULL -#define I40E_PTP_10GB_INCVAL 0x0333333333ULL -#define I40E_PTP_1GB_INCVAL 0x2000000000ULL +#define I40E_PTP_40GB_INCVAL 0x0199999999ULL +#define I40E_PTP_10GB_INCVAL_MULT 2 +#define I40E_PTP_1GB_INCVAL_MULT 20 #define I40E_PRTTSYN_CTL1_TSYNTYPE_V1 BIT(I40E_PRTTSYN_CTL1_TSYNTYPE_SHIFT) #define I40E_PRTTSYN_CTL1_TSYNTYPE_V2 (2 << \ @@ -130,17 +106,24 @@ static int i40e_ptp_adjfreq(struct ptp_clock_info *ptp, s32 ppb) ppb = -ppb; } - smp_mb(); /* Force any pending update before accessing. */ - adj = READ_ONCE(pf->ptp_base_adj); - - freq = adj; + freq = I40E_PTP_40GB_INCVAL; freq *= ppb; diff = div_u64(freq, 1000000000ULL); if (neg_adj) - adj -= diff; + adj = I40E_PTP_40GB_INCVAL - diff; else - adj += diff; + adj = I40E_PTP_40GB_INCVAL + diff; + + /* At some link speeds, the base incval is so large that directly + * multiplying by ppb would result in arithmetic overflow even when + * using a u64. Avoid this by instead calculating the new incval + * always in terms of the 40GbE clock rate and then multiplying by the + * link speed factor afterwards. This does result in slightly lower + * precision at lower link speeds, but it is fairly minor. + */ + smp_mb(); /* Force any pending update before accessing. */ + adj *= READ_ONCE(pf->ptp_adj_mult); wr32(hw, I40E_PRTTSYN_INC_L, adj & 0xFFFFFFFF); wr32(hw, I40E_PRTTSYN_INC_H, adj >> 32); @@ -462,6 +445,7 @@ void i40e_ptp_set_increment(struct i40e_pf *pf) struct i40e_link_status *hw_link_info; struct i40e_hw *hw = &pf->hw; u64 incval; + u32 mult; hw_link_info = &hw->phy.link_info; @@ -469,10 +453,10 @@ void i40e_ptp_set_increment(struct i40e_pf *pf) switch (hw_link_info->link_speed) { case I40E_LINK_SPEED_10GB: - incval = I40E_PTP_10GB_INCVAL; + mult = I40E_PTP_10GB_INCVAL_MULT; break; case I40E_LINK_SPEED_1GB: - incval = I40E_PTP_1GB_INCVAL; + mult = I40E_PTP_1GB_INCVAL_MULT; break; case I40E_LINK_SPEED_100MB: { @@ -483,15 +467,20 @@ void i40e_ptp_set_increment(struct i40e_pf *pf) "1588 functionality is not supported at 100 Mbps. Stopping the PHC.\n"); warn_once++; } - incval = 0; + mult = 0; break; } case I40E_LINK_SPEED_40GB: default: - incval = I40E_PTP_40GB_INCVAL; + mult = 1; break; } + /* The increment value is calculated by taking the base 40GbE incvalue + * and multiplying it by a factor based on the link speed. + */ + incval = I40E_PTP_40GB_INCVAL * mult; + /* Write the new increment value into the increment register. The * hardware will not update the clock until both registers have been * written. @@ -500,14 +489,14 @@ void i40e_ptp_set_increment(struct i40e_pf *pf) wr32(hw, I40E_PRTTSYN_INC_H, incval >> 32); /* Update the base adjustement value. */ - WRITE_ONCE(pf->ptp_base_adj, incval); + WRITE_ONCE(pf->ptp_adj_mult, mult); smp_mb(); /* Force the above update. */ } /** * i40e_ptp_get_ts_config - ioctl interface to read the HW timestamping * @pf: Board private structure - * @ifreq: ioctl data + * @ifr: ioctl data * * Obtain the current hardware timestamping settigs as requested. To do this, * keep a shadow copy of the timestamp settings rather than attempting to @@ -651,7 +640,7 @@ static int i40e_ptp_set_timestamp_mode(struct i40e_pf *pf, /** * i40e_ptp_set_ts_config - ioctl interface to control the HW timestamping * @pf: Board private structure - * @ifreq: ioctl data + * @ifr: ioctl data * * Respond to the user filter requests and make the appropriate hardware * changes here. The XL710 cannot support splitting of the Tx/Rx timestamping diff --git a/drivers/net/ethernet/intel/i40e/i40e_register.h b/drivers/net/ethernet/intel/i40e/i40e_register.h index b3e206e49cc2..52e3680c57f8 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_register.h +++ b/drivers/net/ethernet/intel/i40e/i40e_register.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_REGISTER_H_ #define _I40E_REGISTER_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_status.h b/drivers/net/ethernet/intel/i40e/i40e_status.h index 10c86f63dc52..77be0702d07c 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_status.h +++ b/drivers/net/ethernet/intel/i40e/i40e_status.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_STATUS_H_ #define _I40E_STATUS_H_ diff --git a/drivers/net/ethernet/intel/i40e/i40e_trace.h b/drivers/net/ethernet/intel/i40e/i40e_trace.h index 410ba13bcf21..424f02077e2e 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40e/i40e_trace.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel(R) 40-10 Gigabit Ethernet Connection Network Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ /* Modeled on trace-events-sample.h */ diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.c b/drivers/net/ethernet/intel/i40e/i40e_txrx.c index f174c72480ab..5efa68de935b 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/prefetch.h> #include <net/busy_poll.h> @@ -495,7 +471,7 @@ static int i40e_add_del_fdir_ipv4(struct i40e_vsi *vsi, /** * i40e_add_del_fdir - Build raw packets to add/del fdir filter * @vsi: pointer to the targeted VSI - * @cmd: command to get or set RX flow classification rules + * @input: filter to add or delete * @add: true adds a filter, false removes it * **/ @@ -638,7 +614,7 @@ static void i40e_unmap_and_free_tx_resource(struct i40e_ring *ring, if (tx_buffer->tx_flags & I40E_TX_FLAGS_FD_SB) kfree(tx_buffer->raw_buf); else if (ring_is_xdp(ring)) - page_frag_free(tx_buffer->raw_buf); + xdp_return_frame(tx_buffer->xdpf); else dev_kfree_skb_any(tx_buffer->skb); if (dma_unmap_len(tx_buffer, len)) @@ -713,7 +689,7 @@ void i40e_free_tx_resources(struct i40e_ring *tx_ring) /** * i40e_get_tx_pending - how many tx descriptors not processed - * @tx_ring: the ring of descriptors + * @ring: the ring of descriptors * @in_sw: use SW variables * * Since there is no access to the ring head register @@ -841,7 +817,7 @@ static bool i40e_clean_tx_irq(struct i40e_vsi *vsi, /* free the skb/XDP data */ if (ring_is_xdp(tx_ring)) - page_frag_free(tx_buf->raw_buf); + xdp_return_frame(tx_buf->xdpf); else napi_consume_skb(tx_buf->skb, napi_budget); @@ -1795,6 +1771,8 @@ static inline int i40e_ptype_to_htype(u8 ptype) * i40e_rx_hash - set the hash value in the skb * @ring: descriptor ring * @rx_desc: specific descriptor + * @skb: skb currently being received and modified + * @rx_ptype: Rx packet type **/ static inline void i40e_rx_hash(struct i40e_ring *ring, union i40e_rx_desc *rx_desc, @@ -2203,9 +2181,20 @@ static bool i40e_is_non_eop(struct i40e_ring *rx_ring, #define I40E_XDP_CONSUMED 1 #define I40E_XDP_TX 2 -static int i40e_xmit_xdp_ring(struct xdp_buff *xdp, +static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, struct i40e_ring *xdp_ring); +static int i40e_xmit_xdp_tx_ring(struct xdp_buff *xdp, + struct i40e_ring *xdp_ring) +{ + struct xdp_frame *xdpf = convert_to_xdp_frame(xdp); + + if (unlikely(!xdpf)) + return I40E_XDP_CONSUMED; + + return i40e_xmit_xdp_ring(xdpf, xdp_ring); +} + /** * i40e_run_xdp - run an XDP program * @rx_ring: Rx ring being processed @@ -2225,13 +2214,15 @@ static struct sk_buff *i40e_run_xdp(struct i40e_ring *rx_ring, if (!xdp_prog) goto xdp_out; + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: break; case XDP_TX: xdp_ring = rx_ring->vsi->xdp_rings[rx_ring->queue_index]; - result = i40e_xmit_xdp_ring(xdp, xdp_ring); + result = i40e_xmit_xdp_tx_ring(xdp, xdp_ring); break; case XDP_REDIRECT: err = xdp_do_redirect(rx_ring->netdev, xdp, xdp_prog); @@ -3478,13 +3469,13 @@ dma_error: * @xdp: data to transmit * @xdp_ring: XDP Tx ring **/ -static int i40e_xmit_xdp_ring(struct xdp_buff *xdp, +static int i40e_xmit_xdp_ring(struct xdp_frame *xdpf, struct i40e_ring *xdp_ring) { - u32 size = xdp->data_end - xdp->data; u16 i = xdp_ring->next_to_use; struct i40e_tx_buffer *tx_bi; struct i40e_tx_desc *tx_desc; + u32 size = xdpf->len; dma_addr_t dma; if (!unlikely(I40E_DESC_UNUSED(xdp_ring))) { @@ -3492,14 +3483,14 @@ static int i40e_xmit_xdp_ring(struct xdp_buff *xdp, return I40E_XDP_CONSUMED; } - dma = dma_map_single(xdp_ring->dev, xdp->data, size, DMA_TO_DEVICE); + dma = dma_map_single(xdp_ring->dev, xdpf->data, size, DMA_TO_DEVICE); if (dma_mapping_error(xdp_ring->dev, dma)) return I40E_XDP_CONSUMED; tx_bi = &xdp_ring->tx_bi[i]; tx_bi->bytecount = size; tx_bi->gso_segs = 1; - tx_bi->raw_buf = xdp->data; + tx_bi->xdpf = xdpf; /* record length, and DMA address */ dma_unmap_len_set(tx_bi, len, size); @@ -3675,7 +3666,7 @@ netdev_tx_t i40e_lan_xmit_frame(struct sk_buff *skb, struct net_device *netdev) * * Returns Zero if sent, else an error code **/ -int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) +int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf) { struct i40e_netdev_priv *np = netdev_priv(dev); unsigned int queue_index = smp_processor_id(); @@ -3688,7 +3679,7 @@ int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) if (!i40e_enabled_xdp_vsi(vsi) || queue_index >= vsi->num_queue_pairs) return -ENXIO; - err = i40e_xmit_xdp_ring(xdp, vsi->xdp_rings[queue_index]); + err = i40e_xmit_xdp_ring(xdpf, vsi->xdp_rings[queue_index]); if (err != I40E_XDP_TX) return -ENOSPC; diff --git a/drivers/net/ethernet/intel/i40e/i40e_txrx.h b/drivers/net/ethernet/intel/i40e/i40e_txrx.h index 3043483ec426..fdd2c55f03a6 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40e/i40e_txrx.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_TXRX_H_ #define _I40E_TXRX_H_ @@ -306,6 +282,7 @@ static inline unsigned int i40e_txd_use_count(unsigned int size) struct i40e_tx_buffer { struct i40e_tx_desc *next_to_watch; union { + struct xdp_frame *xdpf; struct sk_buff *skb; void *raw_buf; }; @@ -510,7 +487,7 @@ u32 i40e_get_tx_pending(struct i40e_ring *ring, bool in_sw); void i40e_detect_recover_hung(struct i40e_vsi *vsi); int __i40e_maybe_stop_tx(struct i40e_ring *tx_ring, int size); bool __i40e_chk_linearize(struct sk_buff *skb); -int i40e_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp); +int i40e_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf); void i40e_xdp_flush(struct net_device *dev); /** diff --git a/drivers/net/ethernet/intel/i40e/i40e_type.h b/drivers/net/ethernet/intel/i40e/i40e_type.h index bfb80092b352..7df969c59855 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_type.h +++ b/drivers/net/ethernet/intel/i40e/i40e_type.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_TYPE_H_ #define _I40E_TYPE_H_ @@ -1318,7 +1294,8 @@ struct i40e_hw_port_stats { /* Checksum and Shadow RAM pointers */ #define I40E_SR_NVM_CONTROL_WORD 0x00 -#define I40E_SR_EMP_MODULE_PTR 0x0F +#define I40E_EMP_MODULE_PTR 0x0F +#define I40E_SR_EMP_MODULE_PTR 0x48 #define I40E_SR_PBA_FLAGS 0x15 #define I40E_SR_PBA_BLOCK_PTR 0x16 #define I40E_SR_BOOT_CONFIG_PTR 0x17 @@ -1337,6 +1314,8 @@ struct i40e_hw_port_stats { #define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024 #define I40E_SR_CONTROL_WORD_1_SHIFT 0x06 #define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT) +#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID BIT(5) +#define I40E_SR_NVM_MAP_STRUCTURE_TYPE BIT(12) #define I40E_PTR_TYPE BIT(15) #define I40E_SR_OCP_CFG_WORD0 0x2B #define I40E_SR_OCP_ENABLED BIT(15) @@ -1454,7 +1433,8 @@ enum i40e_reset_type { }; /* IEEE 802.1AB LLDP Agent Variables from NVM */ -#define I40E_NVM_LLDP_CFG_PTR 0xD +#define I40E_NVM_LLDP_CFG_PTR 0x06 +#define I40E_SR_LLDP_CFG_PTR 0x31 struct i40e_lldp_variables { u16 length; u16 adminstatus; diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c index 35173cbe80f7..c6d24eaede18 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e.h" @@ -32,8 +8,8 @@ /** * i40e_vc_vf_broadcast * @pf: pointer to the PF structure - * @opcode: operation code - * @retval: return value + * @v_opcode: operation code + * @v_retval: return value * @msg: pointer to the msg buffer * @msglen: msg length * @@ -1663,6 +1639,7 @@ static int i40e_vc_send_resp_to_vf(struct i40e_vf *vf, /** * i40e_vc_get_version_msg * @vf: pointer to the VF info + * @msg: pointer to the msg buffer * * called from the VF to request the API version used by the PF **/ @@ -1706,7 +1683,6 @@ static void i40e_del_qch(struct i40e_vf *vf) * i40e_vc_get_vf_resources_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to request its resources **/ @@ -1830,8 +1806,6 @@ err: /** * i40e_vc_reset_vf_msg * @vf: pointer to the VF info - * @msg: pointer to the msg buffer - * @msglen: msg length * * called from the VF to reset itself, * unlike other virtchnl messages, PF driver @@ -2180,6 +2154,51 @@ error_param: } /** + * i40e_ctrl_vf_tx_rings + * @vsi: the SRIOV VSI being configured + * @q_map: bit map of the queues to be enabled + * @enable: start or stop the queue + **/ +static int i40e_ctrl_vf_tx_rings(struct i40e_vsi *vsi, unsigned long q_map, + bool enable) +{ + struct i40e_pf *pf = vsi->back; + int ret = 0; + u16 q_id; + + for_each_set_bit(q_id, &q_map, I40E_MAX_VF_QUEUES) { + ret = i40e_control_wait_tx_q(vsi->seid, pf, + vsi->base_queue + q_id, + false /*is xdp*/, enable); + if (ret) + break; + } + return ret; +} + +/** + * i40e_ctrl_vf_rx_rings + * @vsi: the SRIOV VSI being configured + * @q_map: bit map of the queues to be enabled + * @enable: start or stop the queue + **/ +static int i40e_ctrl_vf_rx_rings(struct i40e_vsi *vsi, unsigned long q_map, + bool enable) +{ + struct i40e_pf *pf = vsi->back; + int ret = 0; + u16 q_id; + + for_each_set_bit(q_id, &q_map, I40E_MAX_VF_QUEUES) { + ret = i40e_control_wait_rx_q(pf, vsi->base_queue + q_id, + enable); + if (ret) + break; + } + return ret; +} + +/** * i40e_vc_enable_queues_msg * @vf: pointer to the VF info * @msg: pointer to the msg buffer @@ -2211,8 +2230,17 @@ static int i40e_vc_enable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - if (i40e_vsi_start_rings(pf->vsi[vf->lan_vsi_idx])) + /* Use the queue bit map sent by the VF */ + if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues, + true)) { aq_ret = I40E_ERR_TIMEOUT; + goto error_param; + } + if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues, + true)) { + aq_ret = I40E_ERR_TIMEOUT; + goto error_param; + } /* need to start the rings for additional ADq VSI's as well */ if (vf->adq_enabled) { @@ -2260,8 +2288,17 @@ static int i40e_vc_disable_queues_msg(struct i40e_vf *vf, u8 *msg, u16 msglen) goto error_param; } - i40e_vsi_stop_rings(pf->vsi[vf->lan_vsi_idx]); - + /* Use the queue bit map sent by the VF */ + if (i40e_ctrl_vf_tx_rings(pf->vsi[vf->lan_vsi_idx], vqs->tx_queues, + false)) { + aq_ret = I40E_ERR_TIMEOUT; + goto error_param; + } + if (i40e_ctrl_vf_rx_rings(pf->vsi[vf->lan_vsi_idx], vqs->rx_queues, + false)) { + aq_ret = I40E_ERR_TIMEOUT; + goto error_param; + } error_param: /* send the response to the VF */ return i40e_vc_send_resp_to_vf(vf, VIRTCHNL_OP_DISABLE_QUEUES, @@ -3556,15 +3593,16 @@ err: * i40e_vc_process_vf_msg * @pf: pointer to the PF structure * @vf_id: source VF id + * @v_opcode: operation code + * @v_retval: unused return value code * @msg: pointer to the msg buffer * @msglen: msg length - * @msghndl: msg handle * * called from the common aeq/arq handler to * process request from VF **/ int i40e_vc_process_vf_msg(struct i40e_pf *pf, s16 vf_id, u32 v_opcode, - u32 v_retval, u8 *msg, u16 msglen) + u32 __always_unused v_retval, u8 *msg, u16 msglen) { struct i40e_hw *hw = &pf->hw; int local_vf_id = vf_id - (s16)hw->func_caps.vf_base_id; @@ -4015,7 +4053,8 @@ error_pvid: * i40e_ndo_set_vf_bw * @netdev: network interface device structure * @vf_id: VF identifier - * @tx_rate: Tx rate + * @min_tx_rate: Minimum Tx rate + * @max_tx_rate: Maximum Tx rate * * configure VF Tx rate **/ diff --git a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h index 57f727bb9e36..bf67d62e2b5f 100644 --- a/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h +++ b/drivers/net/ethernet/intel/i40e/i40e_virtchnl_pf.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Driver - * Copyright(c) 2013 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_VIRTCHNL_PF_H_ #define _I40E_VIRTCHNL_PF_H_ diff --git a/drivers/net/ethernet/intel/i40evf/Makefile b/drivers/net/ethernet/intel/i40evf/Makefile index 1e89c5487676..3c5c6e962280 100644 --- a/drivers/net/ethernet/intel/i40evf/Makefile +++ b/drivers/net/ethernet/intel/i40evf/Makefile @@ -1,29 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel Ethernet Controller XL710 Family Linux Virtual Function Driver -# Copyright(c) 2013 - 2014 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along -# with this program. If not, see <http://www.gnu.org/licenses/>. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ +# Copyright(c) 2013 - 2018 Intel Corporation. # ## Makefile for the Intel(R) 40GbE VF driver diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c index 6fd677efa9da..c355120dfdfd 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_status.h" #include "i40e_type.h" diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h index a7137c165256..1f264b9b6805 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_ADMINQ_H_ #define _I40E_ADMINQ_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h index 439e71882049..aa81e87cd471 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_adminq_cmd.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_ADMINQ_CMD_H_ #define _I40E_ADMINQ_CMD_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h index 7e0fddd8af36..cb8689222c8b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_alloc.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_alloc.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_ALLOC_H_ #define _I40E_ALLOC_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_common.c b/drivers/net/ethernet/intel/i40evf/i40e_common.c index 67140cdbcd7a..9cef54971312 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_common.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_common.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40e_type.h" #include "i40e_adminq.h" @@ -1255,6 +1231,7 @@ i40e_status_code i40evf_aq_write_ddp(struct i40e_hw *hw, void *buff, * @hw: pointer to the hw struct * @buff: command buffer (size in bytes = buff_size) * @buff_size: buffer size in bytes + * @flags: AdminQ command flags * @cmd_details: pointer to command details structure or NULL **/ enum diff --git a/drivers/net/ethernet/intel/i40evf/i40e_devids.h b/drivers/net/ethernet/intel/i40evf/i40e_devids.h index 352dd3f3eb6a..f300bf271824 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_devids.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_devids.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_DEVIDS_H_ #define _I40E_DEVIDS_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h index 7432596164f4..1c78de838857 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_hmc.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_hmc.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_HMC_H_ #define _I40E_HMC_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h index ddac0e4908d3..82b00f70a632 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_lan_hmc.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_LAN_HMC_H_ #define _I40E_LAN_HMC_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h index 8668ad6c1a65..3ddddb46455b 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_osdep.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_osdep.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_OSDEP_H_ #define _I40E_OSDEP_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h index 72501bd0f1a9..a358f4b9d5aa 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_prototype.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_prototype.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_PROTOTYPE_H_ #define _I40E_PROTOTYPE_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_register.h b/drivers/net/ethernet/intel/i40evf/i40e_register.h index c9c935659758..49e1f57d99cc 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_register.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_register.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_REGISTER_H_ #define _I40E_REGISTER_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_status.h b/drivers/net/ethernet/intel/i40evf/i40e_status.h index 0d7993ecb99a..77be0702d07c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_status.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_status.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_STATUS_H_ #define _I40E_STATUS_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_trace.h b/drivers/net/ethernet/intel/i40evf/i40e_trace.h index ece01dd12a3c..d7a4e68820a8 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_trace.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_trace.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel(R) 40-10 Gigabit Ethernet Virtual Function Driver - * Copyright(c) 2013 - 2017 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ /* Modeled on trace-events-sample.h */ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c index 12bd937861e7..a9730711e257 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.c +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include <linux/prefetch.h> #include <net/busy_poll.h> @@ -129,7 +105,7 @@ void i40evf_free_tx_resources(struct i40e_ring *tx_ring) /** * i40evf_get_tx_pending - how many Tx descriptors not processed - * @tx_ring: the ring of descriptors + * @ring: the ring of descriptors * @in_sw: is tx_pending being checked in SW or HW * * Since there is no access to the ring head register @@ -1070,6 +1046,8 @@ static inline int i40e_ptype_to_htype(u8 ptype) * i40e_rx_hash - set the hash value in the skb * @ring: descriptor ring * @rx_desc: specific descriptor + * @skb: skb currently being received and modified + * @rx_ptype: Rx packet type **/ static inline void i40e_rx_hash(struct i40e_ring *ring, union i40e_rx_desc *rx_desc, diff --git a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h index 5790897eae2e..3b5a63b3236e 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_txrx.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_txrx.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_TXRX_H_ #define _I40E_TXRX_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40e_type.h b/drivers/net/ethernet/intel/i40evf/i40e_type.h index 449de4b0058e..094387db3c11 100644 --- a/drivers/net/ethernet/intel/i40evf/i40e_type.h +++ b/drivers/net/ethernet/intel/i40evf/i40e_type.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40E_TYPE_H_ #define _I40E_TYPE_H_ @@ -1257,7 +1233,8 @@ struct i40e_hw_port_stats { /* Checksum and Shadow RAM pointers */ #define I40E_SR_NVM_CONTROL_WORD 0x00 -#define I40E_SR_EMP_MODULE_PTR 0x0F +#define I40E_EMP_MODULE_PTR 0x0F +#define I40E_SR_EMP_MODULE_PTR 0x48 #define I40E_NVM_OEM_VER_OFF 0x83 #define I40E_SR_NVM_DEV_STARTER_VERSION 0x18 #define I40E_SR_NVM_WAKE_ON_LAN 0x19 @@ -1273,6 +1250,9 @@ struct i40e_hw_port_stats { #define I40E_SR_PCIE_ALT_MODULE_MAX_SIZE 1024 #define I40E_SR_CONTROL_WORD_1_SHIFT 0x06 #define I40E_SR_CONTROL_WORD_1_MASK (0x03 << I40E_SR_CONTROL_WORD_1_SHIFT) +#define I40E_SR_CONTROL_WORD_1_NVM_BANK_VALID BIT(5) +#define I40E_SR_NVM_MAP_STRUCTURE_TYPE BIT(12) +#define I40E_PTR_TYPE BIT(15) /* Shadow RAM related */ #define I40E_SR_SECTOR_SIZE_IN_WORDS 0x800 @@ -1386,6 +1366,10 @@ enum i40e_reset_type { I40E_RESET_EMPR = 3, }; +/* IEEE 802.1AB LLDP Agent Variables from NVM */ +#define I40E_NVM_LLDP_CFG_PTR 0x06 +#define I40E_SR_LLDP_CFG_PTR 0x31 + /* RSS Hash Table Size */ #define I40E_PFQF_CTL_0_HASHLUTSIZE_512 0x00010000 diff --git a/drivers/net/ethernet/intel/i40evf/i40evf.h b/drivers/net/ethernet/intel/i40evf/i40evf.h index 3a7a1e77bf39..98b834932dd3 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #ifndef _I40EVF_H_ #define _I40EVF_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.c b/drivers/net/ethernet/intel/i40evf/i40evf_client.c index da60ce12b33d..3cc9d60d0d72 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_client.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.c @@ -1,4 +1,6 @@ // SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + #include <linux/list.h> #include <linux/errno.h> @@ -176,7 +178,6 @@ void i40evf_notify_client_close(struct i40e_vsi *vsi, bool reset) /** * i40evf_client_add_instance - add a client instance to the instance list * @adapter: pointer to the board struct - * @client: pointer to a client struct in the client list. * * Returns cinst ptr on success, NULL on failure **/ @@ -234,7 +235,6 @@ out: /** * i40evf_client_del_instance - removes a client instance from the list * @adapter: pointer to the board struct - * @client: pointer to the client struct * **/ static @@ -438,7 +438,7 @@ static u32 i40evf_client_virtchnl_send(struct i40e_info *ldev, * i40evf_client_setup_qvlist - send a message to the PF to setup iwarp qv map * @ldev: pointer to L2 context. * @client: Client pointer. - * @qv_info: queue and vector list + * @qvlist_info: queue and vector list * * Return 0 on success or < 0 on error **/ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_client.h b/drivers/net/ethernet/intel/i40evf/i40evf_client.h index 15a10da5bd4a..fc6592c3de9c 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_client.h +++ b/drivers/net/ethernet/intel/i40evf/i40evf_client.h @@ -1,4 +1,6 @@ /* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ + #ifndef _I40E_CLIENT_H_ #define _I40E_CLIENT_H_ diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c index dc4cde274fb8..69efe0aec76a 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_ethtool.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ /* ethtool support for i40evf */ #include "i40evf.h" @@ -226,7 +202,7 @@ static void i40evf_get_strings(struct net_device *netdev, u32 sset, u8 *data) /** * i40evf_get_priv_flags - report device private flags - * @dev: network interface device structure + * @netdev: network interface device structure * * The get string set count and the string set should be matched for each * flag returned. Add new strings for each flag to the i40e_gstrings_priv_flags @@ -253,7 +229,7 @@ static u32 i40evf_get_priv_flags(struct net_device *netdev) /** * i40evf_set_priv_flags - set private flags - * @dev: network interface device structure + * @netdev: network interface device structure * @flags: bit flags to be set **/ static int i40evf_set_priv_flags(struct net_device *netdev, u32 flags) @@ -627,6 +603,7 @@ static int i40evf_set_per_queue_coalesce(struct net_device *netdev, * i40evf_get_rxnfc - command to get RX flow classification rules * @netdev: network interface device structure * @cmd: ethtool rxnfc command + * @rule_locs: pointer to store rule locations * * Returns Success if the command is supported. **/ @@ -746,6 +723,7 @@ static u32 i40evf_get_rxfh_indir_size(struct net_device *netdev) * @netdev: network interface device structure * @indir: indirection table * @key: hash key + * @hfunc: hash function in use * * Reads the indirection table directly from the hardware. Always returns 0. **/ @@ -774,6 +752,7 @@ static int i40evf_get_rxfh(struct net_device *netdev, u32 *indir, u8 *key, * @netdev: network interface device structure * @indir: indirection table * @key: hash key + * @hfunc: hash function to use * * Returns -EINVAL if the table specifies an inavlid queue id, otherwise * returns 0 after programming the table. diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_main.c b/drivers/net/ethernet/intel/i40evf/i40evf_main.c index 5f71532be7f1..3f04a182903d 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_main.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_main.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40evf.h" #include "i40e_prototype.h" @@ -473,6 +449,7 @@ static void i40evf_irq_affinity_release(struct kref *ref) {} /** * i40evf_request_traffic_irqs - Initialize MSI-X interrupts * @adapter: board private structure + * @basename: device basename * * Allocates MSI-X vectors for tx and rx handling, and requests * interrupts from the kernel. @@ -705,7 +682,7 @@ i40evf_vlan_filter *i40evf_add_vlan(struct i40evf_adapter *adapter, u16 vlan) f = i40evf_find_vlan(adapter, vlan); if (!f) { - f = kzalloc(sizeof(*f), GFP_ATOMIC); + f = kzalloc(sizeof(*f), GFP_KERNEL); if (!f) goto clearout; @@ -745,6 +722,7 @@ static void i40evf_del_vlan(struct i40evf_adapter *adapter, u16 vlan) /** * i40evf_vlan_rx_add_vid - Add a VLAN filter to a device * @netdev: network device struct + * @proto: unused protocol data * @vid: VLAN tag **/ static int i40evf_vlan_rx_add_vid(struct net_device *netdev, @@ -762,6 +740,7 @@ static int i40evf_vlan_rx_add_vid(struct net_device *netdev, /** * i40evf_vlan_rx_kill_vid - Remove a VLAN filter from a device * @netdev: network device struct + * @proto: unused protocol data * @vid: VLAN tag **/ static int i40evf_vlan_rx_kill_vid(struct net_device *netdev, @@ -3160,7 +3139,7 @@ static int i40evf_set_features(struct net_device *netdev, /** * i40evf_features_check - Validate encapsulated packet conforms to limits * @skb: skb buff - * @netdev: This physical port's netdev + * @dev: This physical port's netdev * @features: Offload features that the stack believes apply **/ static netdev_features_t i40evf_features_check(struct sk_buff *skb, @@ -3378,6 +3357,24 @@ int i40evf_process_config(struct i40evf_adapter *adapter) if (vfres->vf_cap_flags & VIRTCHNL_VF_OFFLOAD_VLAN) netdev->features |= NETIF_F_HW_VLAN_CTAG_FILTER; + /* Do not turn on offloads when they are requested to be turned off. + * TSO needs minimum 576 bytes to work correctly. + */ + if (netdev->wanted_features) { + if (!(netdev->wanted_features & NETIF_F_TSO) || + netdev->mtu < 576) + netdev->features &= ~NETIF_F_TSO; + if (!(netdev->wanted_features & NETIF_F_TSO6) || + netdev->mtu < 576) + netdev->features &= ~NETIF_F_TSO6; + if (!(netdev->wanted_features & NETIF_F_TSO_ECN)) + netdev->features &= ~NETIF_F_TSO_ECN; + if (!(netdev->wanted_features & NETIF_F_GRO)) + netdev->features &= ~NETIF_F_GRO; + if (!(netdev->wanted_features & NETIF_F_GSO)) + netdev->features &= ~NETIF_F_GSO; + } + adapter->vsi.id = adapter->vsi_res->vsi_id; adapter->vsi.back = adapter; diff --git a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c index 26a59890532f..565677de5ba3 100644 --- a/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c +++ b/drivers/net/ethernet/intel/i40evf/i40evf_virtchnl.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - * - * Intel Ethernet Controller XL710 Family Linux Virtual Function Driver - * Copyright(c) 2013 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 2013 - 2018 Intel Corporation. */ #include "i40evf.h" #include "i40e_prototype.h" @@ -179,8 +155,7 @@ int i40evf_send_vf_config_msg(struct i40evf_adapter *adapter) /** * i40evf_get_vf_config - * @hw: pointer to the hardware structure - * @len: length of buffer + * @adapter: private adapter structure * * Get VF configuration from PF and populate hw structure. Must be called after * admin queue is initialized. Busy waits until response is received from PF, @@ -423,8 +398,6 @@ int i40evf_request_queues(struct i40evf_adapter *adapter, int num) /** * i40evf_add_ether_addrs * @adapter: adapter structure - * @addrs: the MAC address filters to add (contiguous) - * @count: number of filters * * Request that the PF add one or more addresses to our filters. **/ @@ -497,8 +470,6 @@ void i40evf_add_ether_addrs(struct i40evf_adapter *adapter) /** * i40evf_del_ether_addrs * @adapter: adapter structure - * @addrs: the MAC address filters to remove (contiguous) - * @count: number of filtes * * Request that the PF remove one or more addresses from our filters. **/ @@ -571,8 +542,6 @@ void i40evf_del_ether_addrs(struct i40evf_adapter *adapter) /** * i40evf_add_vlans * @adapter: adapter structure - * @vlans: the VLANs to add - * @count: number of VLANs * * Request that the PF add one or more VLAN filters to our VSI. **/ @@ -643,8 +612,6 @@ void i40evf_add_vlans(struct i40evf_adapter *adapter) /** * i40evf_del_vlans * @adapter: adapter structure - * @vlans: the VLANs to remove - * @count: number of VLANs * * Request that the PF remove one or more VLAN filters from our VSI. **/ diff --git a/drivers/net/ethernet/intel/igb/Makefile b/drivers/net/ethernet/intel/igb/Makefile index c48583e98ac1..394c1e0656b9 100644 --- a/drivers/net/ethernet/intel/igb/Makefile +++ b/drivers/net/ethernet/intel/igb/Makefile @@ -1,31 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel 82575 PCI-Express Ethernet Linux driver -# Copyright(c) 1999 - 2014 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along with -# this program; if not, see <http://www.gnu.org/licenses/>. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# Linux NICS <linux.nics@intel.com> -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ - +# Copyright(c) 1999 - 2018 Intel Corporation. # # Makefile for the Intel(R) 82575 PCI-Express ethernet driver # diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.c b/drivers/net/ethernet/intel/igb/e1000_82575.c index dd9b6cac220d..b13b42e5a1d9 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.c +++ b/drivers/net/ethernet/intel/igb/e1000_82575.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ /* e1000_82575 * e1000_82576 diff --git a/drivers/net/ethernet/intel/igb/e1000_82575.h b/drivers/net/ethernet/intel/igb/e1000_82575.h index e53ebe97d709..6ad775b1a4c5 100644 --- a/drivers/net/ethernet/intel/igb/e1000_82575.h +++ b/drivers/net/ethernet/intel/igb/e1000_82575.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_82575_H_ #define _E1000_82575_H_ diff --git a/drivers/net/ethernet/intel/igb/e1000_defines.h b/drivers/net/ethernet/intel/igb/e1000_defines.h index 98534f765e0e..252440a418dc 100644 --- a/drivers/net/ethernet/intel/igb/e1000_defines.h +++ b/drivers/net/ethernet/intel/igb/e1000_defines.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_DEFINES_H_ #define _E1000_DEFINES_H_ @@ -491,6 +470,8 @@ * manageability enabled, allowing us room for 15 multicast addresses. */ #define E1000_RAH_AV 0x80000000 /* Receive descriptor valid */ +#define E1000_RAH_ASEL_SRC_ADDR 0x00010000 +#define E1000_RAH_QSEL_ENABLE 0x10000000 #define E1000_RAL_MAC_ADDR_LEN 4 #define E1000_RAH_MAC_ADDR_LEN 2 #define E1000_RAH_POOL_MASK 0x03FC0000 diff --git a/drivers/net/ethernet/intel/igb/e1000_hw.h b/drivers/net/ethernet/intel/igb/e1000_hw.h index ff835e1e853d..5d87957b2627 100644 --- a/drivers/net/ethernet/intel/igb/e1000_hw.h +++ b/drivers/net/ethernet/intel/igb/e1000_hw.h @@ -1,25 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_HW_H_ #define _E1000_HW_H_ diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.c b/drivers/net/ethernet/intel/igb/e1000_i210.c index 6f548247e6d8..c54ebedca6da 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.c +++ b/drivers/net/ethernet/intel/igb/e1000_i210.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ /* e1000_i210 * e1000_i211 diff --git a/drivers/net/ethernet/intel/igb/e1000_i210.h b/drivers/net/ethernet/intel/igb/e1000_i210.h index 56f015ccb206..5c437fdc49ee 100644 --- a/drivers/net/ethernet/intel/igb/e1000_i210.h +++ b/drivers/net/ethernet/intel/igb/e1000_i210.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_I210_H_ #define _E1000_I210_H_ diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.c b/drivers/net/ethernet/intel/igb/e1000_mac.c index 298afa0d9159..79ee0a747260 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.c +++ b/drivers/net/ethernet/intel/igb/e1000_mac.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #include <linux/if_ether.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/igb/e1000_mac.h b/drivers/net/ethernet/intel/igb/e1000_mac.h index 04d80c765aee..6e110f28f922 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mac.h +++ b/drivers/net/ethernet/intel/igb/e1000_mac.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_MAC_H_ #define _E1000_MAC_H_ diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.c b/drivers/net/ethernet/intel/igb/e1000_mbx.c index ef42f1689b3b..46debd991bfe 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.c +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #include "e1000_mbx.h" diff --git a/drivers/net/ethernet/intel/igb/e1000_mbx.h b/drivers/net/ethernet/intel/igb/e1000_mbx.h index 4f0ecd28354d..178e60ec71d4 100644 --- a/drivers/net/ethernet/intel/igb/e1000_mbx.h +++ b/drivers/net/ethernet/intel/igb/e1000_mbx.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_MBX_H_ #define _E1000_MBX_H_ diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.c b/drivers/net/ethernet/intel/igb/e1000_nvm.c index e4596f151cd4..09f4dcb09632 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.c +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.c @@ -1,25 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #include <linux/if_ether.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/igb/e1000_nvm.h b/drivers/net/ethernet/intel/igb/e1000_nvm.h index dde68cd54a53..091cddf4ada8 100644 --- a/drivers/net/ethernet/intel/igb/e1000_nvm.h +++ b/drivers/net/ethernet/intel/igb/e1000_nvm.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_NVM_H_ #define _E1000_NVM_H_ diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.c b/drivers/net/ethernet/intel/igb/e1000_phy.c index 4ec61243da82..2be0e762ec69 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.c +++ b/drivers/net/ethernet/intel/igb/e1000_phy.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2015 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #include <linux/if_ether.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/igb/e1000_phy.h b/drivers/net/ethernet/intel/igb/e1000_phy.h index 856d2cda0643..5894e4b1d0a8 100644 --- a/drivers/net/ethernet/intel/igb/e1000_phy.h +++ b/drivers/net/ethernet/intel/igb/e1000_phy.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_PHY_H_ #define _E1000_PHY_H_ diff --git a/drivers/net/ethernet/intel/igb/e1000_regs.h b/drivers/net/ethernet/intel/igb/e1000_regs.h index e8fa8c6530e0..0ad737d2f289 100644 --- a/drivers/net/ethernet/intel/igb/e1000_regs.h +++ b/drivers/net/ethernet/intel/igb/e1000_regs.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #ifndef _E1000_REGS_H_ #define _E1000_REGS_H_ diff --git a/drivers/net/ethernet/intel/igb/igb.h b/drivers/net/ethernet/intel/igb/igb.h index 8dbc399b345e..9643b5b3d444 100644 --- a/drivers/net/ethernet/intel/igb/igb.h +++ b/drivers/net/ethernet/intel/igb/igb.h @@ -1,26 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ /* Linux PRO/1000 Ethernet Driver main header file */ @@ -442,6 +421,8 @@ struct hwmon_buff { enum igb_filter_match_flags { IGB_FILTER_FLAG_ETHER_TYPE = 0x1, IGB_FILTER_FLAG_VLAN_TCI = 0x2, + IGB_FILTER_FLAG_SRC_MAC_ADDR = 0x4, + IGB_FILTER_FLAG_DST_MAC_ADDR = 0x8, }; #define IGB_MAX_RXNFC_FILTERS 16 @@ -456,11 +437,14 @@ struct igb_nfc_input { u8 match_flags; __be16 etype; __be16 vlan_tci; + u8 src_addr[ETH_ALEN]; + u8 dst_addr[ETH_ALEN]; }; struct igb_nfc_filter { struct hlist_node nfc_node; struct igb_nfc_input filter; + unsigned long cookie; u16 etype_reg_index; u16 sw_idx; u16 action; @@ -474,6 +458,8 @@ struct igb_mac_addr { #define IGB_MAC_STATE_DEFAULT 0x1 #define IGB_MAC_STATE_IN_USE 0x2 +#define IGB_MAC_STATE_SRC_ADDR 0x4 +#define IGB_MAC_STATE_QUEUE_STEERING 0x8 /* board specific private data structure */ struct igb_adapter { @@ -598,6 +584,7 @@ struct igb_adapter { /* RX network flow classification support */ struct hlist_head nfc_filter_list; + struct hlist_head cls_flower_list; unsigned int nfc_filter_count; /* lock for RX network flow classification filter */ spinlock_t nfc_lock; @@ -739,4 +726,9 @@ int igb_add_filter(struct igb_adapter *adapter, int igb_erase_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input); +int igb_add_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags); +int igb_del_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags); + #endif /* _IGB_H_ */ diff --git a/drivers/net/ethernet/intel/igb/igb_ethtool.c b/drivers/net/ethernet/intel/igb/igb_ethtool.c index e77ba0d5866d..2d798499d35e 100644 --- a/drivers/net/ethernet/intel/igb/igb_ethtool.c +++ b/drivers/net/ethernet/intel/igb/igb_ethtool.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ /* ethtool support for igb */ @@ -2495,6 +2474,23 @@ static int igb_get_ethtool_nfc_entry(struct igb_adapter *adapter, fsp->h_ext.vlan_tci = rule->filter.vlan_tci; fsp->m_ext.vlan_tci = htons(VLAN_PRIO_MASK); } + if (rule->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) { + ether_addr_copy(fsp->h_u.ether_spec.h_dest, + rule->filter.dst_addr); + /* As we only support matching by the full + * mask, return the mask to userspace + */ + eth_broadcast_addr(fsp->m_u.ether_spec.h_dest); + } + if (rule->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) { + ether_addr_copy(fsp->h_u.ether_spec.h_source, + rule->filter.src_addr); + /* As we only support matching by the full + * mask, return the mask to userspace + */ + eth_broadcast_addr(fsp->m_u.ether_spec.h_source); + } + return 0; } return -EINVAL; @@ -2768,14 +2764,41 @@ static int igb_rxnfc_write_vlan_prio_filter(struct igb_adapter *adapter, int igb_add_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input) { + struct e1000_hw *hw = &adapter->hw; int err = -EINVAL; + if (hw->mac.type == e1000_i210 && + !(input->filter.match_flags & ~IGB_FILTER_FLAG_SRC_MAC_ADDR)) { + dev_err(&adapter->pdev->dev, + "i210 doesn't support flow classification rules specifying only source addresses.\n"); + return -EOPNOTSUPP; + } + if (input->filter.match_flags & IGB_FILTER_FLAG_ETHER_TYPE) { err = igb_rxnfc_write_etype_filter(adapter, input); if (err) return err; } + if (input->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) { + err = igb_add_mac_steering_filter(adapter, + input->filter.dst_addr, + input->action, 0); + err = min_t(int, err, 0); + if (err) + return err; + } + + if (input->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) { + err = igb_add_mac_steering_filter(adapter, + input->filter.src_addr, + input->action, + IGB_MAC_STATE_SRC_ADDR); + err = min_t(int, err, 0); + if (err) + return err; + } + if (input->filter.match_flags & IGB_FILTER_FLAG_VLAN_TCI) err = igb_rxnfc_write_vlan_prio_filter(adapter, input); @@ -2824,6 +2847,15 @@ int igb_erase_filter(struct igb_adapter *adapter, struct igb_nfc_filter *input) igb_clear_vlan_prio_filter(adapter, ntohs(input->filter.vlan_tci)); + if (input->filter.match_flags & IGB_FILTER_FLAG_SRC_MAC_ADDR) + igb_del_mac_steering_filter(adapter, input->filter.src_addr, + input->action, + IGB_MAC_STATE_SRC_ADDR); + + if (input->filter.match_flags & IGB_FILTER_FLAG_DST_MAC_ADDR) + igb_del_mac_steering_filter(adapter, input->filter.dst_addr, + input->action, 0); + return 0; } @@ -2865,7 +2897,7 @@ static int igb_update_ethtool_nfc_entry(struct igb_adapter *adapter, /* add filter to the list */ if (parent) - hlist_add_behind(&parent->nfc_node, &input->nfc_node); + hlist_add_behind(&input->nfc_node, &parent->nfc_node); else hlist_add_head(&input->nfc_node, &adapter->nfc_filter_list); @@ -2905,10 +2937,6 @@ static int igb_add_ethtool_nfc_entry(struct igb_adapter *adapter, if ((fsp->flow_type & ~FLOW_EXT) != ETHER_FLOW) return -EINVAL; - if (fsp->m_u.ether_spec.h_proto != ETHER_TYPE_FULL_MASK && - fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) - return -EINVAL; - input = kzalloc(sizeof(*input), GFP_KERNEL); if (!input) return -ENOMEM; @@ -2918,6 +2946,20 @@ static int igb_add_ethtool_nfc_entry(struct igb_adapter *adapter, input->filter.match_flags = IGB_FILTER_FLAG_ETHER_TYPE; } + /* Only support matching addresses by the full mask */ + if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_source)) { + input->filter.match_flags |= IGB_FILTER_FLAG_SRC_MAC_ADDR; + ether_addr_copy(input->filter.src_addr, + fsp->h_u.ether_spec.h_source); + } + + /* Only support matching addresses by the full mask */ + if (is_broadcast_ether_addr(fsp->m_u.ether_spec.h_dest)) { + input->filter.match_flags |= IGB_FILTER_FLAG_DST_MAC_ADDR; + ether_addr_copy(input->filter.dst_addr, + fsp->h_u.ether_spec.h_dest); + } + if ((fsp->flow_type & FLOW_EXT) && fsp->m_ext.vlan_tci) { if (fsp->m_ext.vlan_tci != htons(VLAN_PRIO_MASK)) { err = -EINVAL; diff --git a/drivers/net/ethernet/intel/igb/igb_hwmon.c b/drivers/net/ethernet/intel/igb/igb_hwmon.c index bebe43b3a836..3b83747b2700 100644 --- a/drivers/net/ethernet/intel/igb/igb_hwmon.c +++ b/drivers/net/ethernet/intel/igb/igb_hwmon.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #include "igb.h" #include "e1000_82575.h" diff --git a/drivers/net/ethernet/intel/igb/igb_main.c b/drivers/net/ethernet/intel/igb/igb_main.c index cce7ada89255..78574c06635b 100644 --- a/drivers/net/ethernet/intel/igb/igb_main.c +++ b/drivers/net/ethernet/intel/igb/igb_main.c @@ -1,26 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/* Intel(R) Gigabit Ethernet Linux driver - * Copyright(c) 2007-2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - */ +/* Copyright(c) 2007 - 2018 Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt @@ -36,6 +15,7 @@ #include <net/checksum.h> #include <net/ip6_checksum.h> #include <net/pkt_sched.h> +#include <net/pkt_cls.h> #include <linux/net_tstamp.h> #include <linux/mii.h> #include <linux/ethtool.h> @@ -2513,6 +2493,250 @@ static int igb_offload_cbs(struct igb_adapter *adapter, return 0; } +#define ETHER_TYPE_FULL_MASK ((__force __be16)~0) +#define VLAN_PRIO_FULL_MASK (0x07) + +static int igb_parse_cls_flower(struct igb_adapter *adapter, + struct tc_cls_flower_offload *f, + int traffic_class, + struct igb_nfc_filter *input) +{ + struct netlink_ext_ack *extack = f->common.extack; + + if (f->dissector->used_keys & + ~(BIT(FLOW_DISSECTOR_KEY_BASIC) | + BIT(FLOW_DISSECTOR_KEY_CONTROL) | + BIT(FLOW_DISSECTOR_KEY_ETH_ADDRS) | + BIT(FLOW_DISSECTOR_KEY_VLAN))) { + NL_SET_ERR_MSG_MOD(extack, + "Unsupported key used, only BASIC, CONTROL, ETH_ADDRS and VLAN are supported"); + return -EOPNOTSUPP; + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_ETH_ADDRS)) { + struct flow_dissector_key_eth_addrs *key, *mask; + + key = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->key); + mask = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_ETH_ADDRS, + f->mask); + + if (!is_zero_ether_addr(mask->dst)) { + if (!is_broadcast_ether_addr(mask->dst)) { + NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for destination MAC address"); + return -EINVAL; + } + + input->filter.match_flags |= + IGB_FILTER_FLAG_DST_MAC_ADDR; + ether_addr_copy(input->filter.dst_addr, key->dst); + } + + if (!is_zero_ether_addr(mask->src)) { + if (!is_broadcast_ether_addr(mask->src)) { + NL_SET_ERR_MSG_MOD(extack, "Only full masks are supported for source MAC address"); + return -EINVAL; + } + + input->filter.match_flags |= + IGB_FILTER_FLAG_SRC_MAC_ADDR; + ether_addr_copy(input->filter.src_addr, key->src); + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_BASIC)) { + struct flow_dissector_key_basic *key, *mask; + + key = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->key); + mask = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_BASIC, + f->mask); + + if (mask->n_proto) { + if (mask->n_proto != ETHER_TYPE_FULL_MASK) { + NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for EtherType filter"); + return -EINVAL; + } + + input->filter.match_flags |= IGB_FILTER_FLAG_ETHER_TYPE; + input->filter.etype = key->n_proto; + } + } + + if (dissector_uses_key(f->dissector, FLOW_DISSECTOR_KEY_VLAN)) { + struct flow_dissector_key_vlan *key, *mask; + + key = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->key); + mask = skb_flow_dissector_target(f->dissector, + FLOW_DISSECTOR_KEY_VLAN, + f->mask); + + if (mask->vlan_priority) { + if (mask->vlan_priority != VLAN_PRIO_FULL_MASK) { + NL_SET_ERR_MSG_MOD(extack, "Only full mask is supported for VLAN priority"); + return -EINVAL; + } + + input->filter.match_flags |= IGB_FILTER_FLAG_VLAN_TCI; + input->filter.vlan_tci = key->vlan_priority; + } + } + + input->action = traffic_class; + input->cookie = f->cookie; + + return 0; +} + +static int igb_configure_clsflower(struct igb_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + struct netlink_ext_ack *extack = cls_flower->common.extack; + struct igb_nfc_filter *filter, *f; + int err, tc; + + tc = tc_classid_to_hwtc(adapter->netdev, cls_flower->classid); + if (tc < 0) { + NL_SET_ERR_MSG_MOD(extack, "Invalid traffic class"); + return -EINVAL; + } + + filter = kzalloc(sizeof(*filter), GFP_KERNEL); + if (!filter) + return -ENOMEM; + + err = igb_parse_cls_flower(adapter, cls_flower, tc, filter); + if (err < 0) + goto err_parse; + + spin_lock(&adapter->nfc_lock); + + hlist_for_each_entry(f, &adapter->nfc_filter_list, nfc_node) { + if (!memcmp(&f->filter, &filter->filter, sizeof(f->filter))) { + err = -EEXIST; + NL_SET_ERR_MSG_MOD(extack, + "This filter is already set in ethtool"); + goto err_locked; + } + } + + hlist_for_each_entry(f, &adapter->cls_flower_list, nfc_node) { + if (!memcmp(&f->filter, &filter->filter, sizeof(f->filter))) { + err = -EEXIST; + NL_SET_ERR_MSG_MOD(extack, + "This filter is already set in cls_flower"); + goto err_locked; + } + } + + err = igb_add_filter(adapter, filter); + if (err < 0) { + NL_SET_ERR_MSG_MOD(extack, "Could not add filter to the adapter"); + goto err_locked; + } + + hlist_add_head(&filter->nfc_node, &adapter->cls_flower_list); + + spin_unlock(&adapter->nfc_lock); + + return 0; + +err_locked: + spin_unlock(&adapter->nfc_lock); + +err_parse: + kfree(filter); + + return err; +} + +static int igb_delete_clsflower(struct igb_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + struct igb_nfc_filter *filter; + int err; + + spin_lock(&adapter->nfc_lock); + + hlist_for_each_entry(filter, &adapter->cls_flower_list, nfc_node) + if (filter->cookie == cls_flower->cookie) + break; + + if (!filter) { + err = -ENOENT; + goto out; + } + + err = igb_erase_filter(adapter, filter); + if (err < 0) + goto out; + + hlist_del(&filter->nfc_node); + kfree(filter); + +out: + spin_unlock(&adapter->nfc_lock); + + return err; +} + +static int igb_setup_tc_cls_flower(struct igb_adapter *adapter, + struct tc_cls_flower_offload *cls_flower) +{ + switch (cls_flower->command) { + case TC_CLSFLOWER_REPLACE: + return igb_configure_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_DESTROY: + return igb_delete_clsflower(adapter, cls_flower); + case TC_CLSFLOWER_STATS: + return -EOPNOTSUPP; + default: + return -EINVAL; + } +} + +static int igb_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct igb_adapter *adapter = cb_priv; + + if (!tc_cls_can_offload_and_chain0(adapter->netdev, type_data)) + return -EOPNOTSUPP; + + switch (type) { + case TC_SETUP_CLSFLOWER: + return igb_setup_tc_cls_flower(adapter, type_data); + + default: + return -EOPNOTSUPP; + } +} + +static int igb_setup_tc_block(struct igb_adapter *adapter, + struct tc_block_offload *f) +{ + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, igb_setup_tc_block_cb, + adapter, adapter); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, igb_setup_tc_block_cb, + adapter); + return 0; + default: + return -EOPNOTSUPP; + } +} + static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, void *type_data) { @@ -2521,6 +2745,8 @@ static int igb_setup_tc(struct net_device *dev, enum tc_setup_type type, switch (type) { case TC_SETUP_QDISC_CBS: return igb_offload_cbs(adapter, type_data); + case TC_SETUP_BLOCK: + return igb_setup_tc_block(adapter, type_data); default: return -EOPNOTSUPP; @@ -2822,6 +3048,9 @@ static int igb_probe(struct pci_dev *pdev, const struct pci_device_id *ent) if (hw->mac.type >= e1000_82576) netdev->features |= NETIF_F_SCTP_CRC; + if (hw->mac.type >= e1000_i350) + netdev->features |= NETIF_F_HW_TC; + #define IGB_GSO_PARTIAL_FEATURES (NETIF_F_GSO_GRE | \ NETIF_F_GSO_GRE_CSUM | \ NETIF_F_GSO_IPXIP4 | \ @@ -6856,8 +7085,35 @@ static void igb_set_default_mac_filter(struct igb_adapter *adapter) igb_rar_set_index(adapter, 0); } -static int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr, - const u8 queue) +/* If the filter to be added and an already existing filter express + * the same address and address type, it should be possible to only + * override the other configurations, for example the queue to steer + * traffic. + */ +static bool igb_mac_entry_can_be_used(const struct igb_mac_addr *entry, + const u8 *addr, const u8 flags) +{ + if (!(entry->state & IGB_MAC_STATE_IN_USE)) + return true; + + if ((entry->state & IGB_MAC_STATE_SRC_ADDR) != + (flags & IGB_MAC_STATE_SRC_ADDR)) + return false; + + if (!ether_addr_equal(addr, entry->addr)) + return false; + + return true; +} + +/* Add a MAC filter for 'addr' directing matching traffic to 'queue', + * 'flags' is used to indicate what kind of match is made, match is by + * default for the destination address, if matching by source address + * is desired the flag IGB_MAC_STATE_SRC_ADDR can be used. + */ +static int igb_add_mac_filter_flags(struct igb_adapter *adapter, + const u8 *addr, const u8 queue, + const u8 flags) { struct e1000_hw *hw = &adapter->hw; int rar_entries = hw->mac.rar_entry_count - @@ -6872,12 +7128,13 @@ static int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr, * addresses. */ for (i = 0; i < rar_entries; i++) { - if (adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE) + if (!igb_mac_entry_can_be_used(&adapter->mac_table[i], + addr, flags)) continue; ether_addr_copy(adapter->mac_table[i].addr, addr); adapter->mac_table[i].queue = queue; - adapter->mac_table[i].state |= IGB_MAC_STATE_IN_USE; + adapter->mac_table[i].state |= IGB_MAC_STATE_IN_USE | flags; igb_rar_set_index(adapter, i); return i; @@ -6886,9 +7143,22 @@ static int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr, return -ENOSPC; } -static int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr, +static int igb_add_mac_filter(struct igb_adapter *adapter, const u8 *addr, const u8 queue) { + return igb_add_mac_filter_flags(adapter, addr, queue, 0); +} + +/* Remove a MAC filter for 'addr' directing matching traffic to + * 'queue', 'flags' is used to indicate what kind of match need to be + * removed, match is by default for the destination address, if + * matching by source address is to be removed the flag + * IGB_MAC_STATE_SRC_ADDR can be used. + */ +static int igb_del_mac_filter_flags(struct igb_adapter *adapter, + const u8 *addr, const u8 queue, + const u8 flags) +{ struct e1000_hw *hw = &adapter->hw; int rar_entries = hw->mac.rar_entry_count - adapter->vfs_allocated_count; @@ -6904,14 +7174,26 @@ static int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr, for (i = 0; i < rar_entries; i++) { if (!(adapter->mac_table[i].state & IGB_MAC_STATE_IN_USE)) continue; + if ((adapter->mac_table[i].state & flags) != flags) + continue; if (adapter->mac_table[i].queue != queue) continue; if (!ether_addr_equal(adapter->mac_table[i].addr, addr)) continue; - adapter->mac_table[i].state &= ~IGB_MAC_STATE_IN_USE; - memset(adapter->mac_table[i].addr, 0, ETH_ALEN); - adapter->mac_table[i].queue = 0; + /* When a filter for the default address is "deleted", + * we return it to its initial configuration + */ + if (adapter->mac_table[i].state & IGB_MAC_STATE_DEFAULT) { + adapter->mac_table[i].state = + IGB_MAC_STATE_DEFAULT | IGB_MAC_STATE_IN_USE; + adapter->mac_table[i].queue = + adapter->vfs_allocated_count; + } else { + adapter->mac_table[i].state = 0; + adapter->mac_table[i].queue = 0; + memset(adapter->mac_table[i].addr, 0, ETH_ALEN); + } igb_rar_set_index(adapter, i); return 0; @@ -6920,6 +7202,34 @@ static int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr, return -ENOENT; } +static int igb_del_mac_filter(struct igb_adapter *adapter, const u8 *addr, + const u8 queue) +{ + return igb_del_mac_filter_flags(adapter, addr, queue, 0); +} + +int igb_add_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags) +{ + struct e1000_hw *hw = &adapter->hw; + + /* In theory, this should be supported on 82575 as well, but + * that part wasn't easily accessible during development. + */ + if (hw->mac.type != e1000_i210) + return -EOPNOTSUPP; + + return igb_add_mac_filter_flags(adapter, addr, queue, + IGB_MAC_STATE_QUEUE_STEERING | flags); +} + +int igb_del_mac_steering_filter(struct igb_adapter *adapter, + const u8 *addr, u8 queue, u8 flags) +{ + return igb_del_mac_filter_flags(adapter, addr, queue, + IGB_MAC_STATE_QUEUE_STEERING | flags); +} + static int igb_uc_sync(struct net_device *netdev, const unsigned char *addr) { struct igb_adapter *adapter = netdev_priv(netdev); @@ -8763,12 +9073,24 @@ static void igb_rar_set_index(struct igb_adapter *adapter, u32 index) if (is_valid_ether_addr(addr)) rar_high |= E1000_RAH_AV; - if (hw->mac.type == e1000_82575) + if (adapter->mac_table[index].state & IGB_MAC_STATE_SRC_ADDR) + rar_high |= E1000_RAH_ASEL_SRC_ADDR; + + switch (hw->mac.type) { + case e1000_82575: + case e1000_i210: + if (adapter->mac_table[index].state & + IGB_MAC_STATE_QUEUE_STEERING) + rar_high |= E1000_RAH_QSEL_ENABLE; + rar_high |= E1000_RAH_POOL_1 * adapter->mac_table[index].queue; - else + break; + default: rar_high |= E1000_RAH_POOL_1 << adapter->mac_table[index].queue; + break; + } } wr32(E1000_RAL(index), rar_low); @@ -9206,6 +9528,9 @@ static void igb_nfc_filter_exit(struct igb_adapter *adapter) hlist_for_each_entry(rule, &adapter->nfc_filter_list, nfc_node) igb_erase_filter(adapter, rule); + hlist_for_each_entry(rule, &adapter->cls_flower_list, nfc_node) + igb_erase_filter(adapter, rule); + spin_unlock(&adapter->nfc_lock); } diff --git a/drivers/net/ethernet/intel/igb/igb_ptp.c b/drivers/net/ethernet/intel/igb/igb_ptp.c index 7454b9895a65..9f4d700e09df 100644 --- a/drivers/net/ethernet/intel/igb/igb_ptp.c +++ b/drivers/net/ethernet/intel/igb/igb_ptp.c @@ -1,21 +1,6 @@ // SPDX-License-Identifier: GPL-2.0+ -/* PTP Hardware Clock (PHC) driver for the Intel 82576 and 82580 - * - * Copyright (C) 2011 Richard Cochran <richardcochran@gmail.com> - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License as published by - * the Free Software Foundation; either version 2 of the License, or - * (at your option) any later version. - * - * This program is distributed in the hope that it will be useful, - * but WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the - * GNU General Public License for more details. - * - * You should have received a copy of the GNU General Public License along with - * this program; if not, see <http://www.gnu.org/licenses/>. - */ +/* Copyright (C) 2011 Richard Cochran <richardcochran@gmail.com> */ + #include <linux/module.h> #include <linux/device.h> #include <linux/pci.h> diff --git a/drivers/net/ethernet/intel/igbvf/Makefile b/drivers/net/ethernet/intel/igbvf/Makefile index efe29dae384a..afd3e36eae75 100644 --- a/drivers/net/ethernet/intel/igbvf/Makefile +++ b/drivers/net/ethernet/intel/igbvf/Makefile @@ -1,31 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel(R) 82576 Virtual Function Linux driver -# Copyright(c) 2009 - 2012 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along with -# this program; if not, write to the Free Software Foundation, Inc., -# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ - +# Copyright(c) 2009 - 2018 Intel Corporation. # # Makefile for the Intel(R) 82576 VF ethernet driver # diff --git a/drivers/net/ethernet/intel/igbvf/defines.h b/drivers/net/ethernet/intel/igbvf/defines.h index 04bcfec0641b..4437f832412d 100644 --- a/drivers/net/ethernet/intel/igbvf/defines.h +++ b/drivers/net/ethernet/intel/igbvf/defines.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000_DEFINES_H_ #define _E1000_DEFINES_H_ diff --git a/drivers/net/ethernet/intel/igbvf/ethtool.c b/drivers/net/ethernet/intel/igbvf/ethtool.c index ca39e3cccaeb..3ae358b35227 100644 --- a/drivers/net/ethernet/intel/igbvf/ethtool.c +++ b/drivers/net/ethernet/intel/igbvf/ethtool.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 2009 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2009 - 2018 Intel Corporation. */ /* ethtool support for igbvf */ diff --git a/drivers/net/ethernet/intel/igbvf/igbvf.h b/drivers/net/ethernet/intel/igbvf/igbvf.h index f5bf248e22eb..eee26a3be90b 100644 --- a/drivers/net/ethernet/intel/igbvf/igbvf.h +++ b/drivers/net/ethernet/intel/igbvf/igbvf.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 2009 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2009 - 2018 Intel Corporation. */ /* Linux PRO/1000 Ethernet Driver main header file */ diff --git a/drivers/net/ethernet/intel/igbvf/mbx.c b/drivers/net/ethernet/intel/igbvf/mbx.c index 9195884096f8..163e5838f7c2 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.c +++ b/drivers/net/ethernet/intel/igbvf/mbx.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 2009 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2009 - 2018 Intel Corporation. */ #include "mbx.h" diff --git a/drivers/net/ethernet/intel/igbvf/mbx.h b/drivers/net/ethernet/intel/igbvf/mbx.h index 479b062fe9ee..e5b31818d565 100644 --- a/drivers/net/ethernet/intel/igbvf/mbx.h +++ b/drivers/net/ethernet/intel/igbvf/mbx.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 1999 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _E1000_MBX_H_ #define _E1000_MBX_H_ diff --git a/drivers/net/ethernet/intel/igbvf/netdev.c b/drivers/net/ethernet/intel/igbvf/netdev.c index e2b7502f1953..f818f060e5a7 100644 --- a/drivers/net/ethernet/intel/igbvf/netdev.c +++ b/drivers/net/ethernet/intel/igbvf/netdev.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 2009 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2009 - 2018 Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/net/ethernet/intel/igbvf/regs.h b/drivers/net/ethernet/intel/igbvf/regs.h index 614e52409f11..625a309a3355 100644 --- a/drivers/net/ethernet/intel/igbvf/regs.h +++ b/drivers/net/ethernet/intel/igbvf/regs.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 2009 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2009 - 2018 Intel Corporation. */ #ifndef _E1000_REGS_H_ #define _E1000_REGS_H_ diff --git a/drivers/net/ethernet/intel/igbvf/vf.c b/drivers/net/ethernet/intel/igbvf/vf.c index bfe8d8297b2e..b8ba3f94c363 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.c +++ b/drivers/net/ethernet/intel/igbvf/vf.c @@ -1,29 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 2009 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2009 - 2018 Intel Corporation. */ #include "vf.h" diff --git a/drivers/net/ethernet/intel/igbvf/vf.h b/drivers/net/ethernet/intel/igbvf/vf.h index 193b50026246..c71b0d7dbcee 100644 --- a/drivers/net/ethernet/intel/igbvf/vf.h +++ b/drivers/net/ethernet/intel/igbvf/vf.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel(R) 82576 Virtual Function Linux driver - Copyright(c) 2009 - 2012 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2009 - 2018 Intel Corporation. */ #ifndef _E1000_VF_H_ #define _E1000_VF_H_ diff --git a/drivers/net/ethernet/intel/ixgb/Makefile b/drivers/net/ethernet/intel/ixgb/Makefile index 1b42dd554dd2..2433e9300a33 100644 --- a/drivers/net/ethernet/intel/ixgb/Makefile +++ b/drivers/net/ethernet/intel/ixgb/Makefile @@ -1,33 +1,6 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel PRO/10GbE Linux driver # Copyright(c) 1999 - 2008 Intel Corporation. # -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along with -# this program; if not, write to the Free Software Foundation, Inc., -# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# Linux NICS <linux.nics@intel.com> -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ - -# # Makefile for the Intel(R) PRO/10GbE ethernet driver # diff --git a/drivers/net/ethernet/intel/ixgb/ixgb.h b/drivers/net/ethernet/intel/ixgb/ixgb.h index 92022841755f..e85271b68410 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2008 Intel Corporation. */ #ifndef _IXGB_H_ #define _IXGB_H_ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ee.c b/drivers/net/ethernet/intel/ixgb/ixgb_ee.c index eca216b9b859..129286fc1634 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ee.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ee.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2008 Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ee.h b/drivers/net/ethernet/intel/ixgb/ixgb_ee.h index 475297a810fe..3ee0a09e5d0a 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ee.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ee.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2008 Intel Corporation. */ #ifndef _IXGB_EE_H_ #define _IXGB_EE_H_ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c index d10a0d242dda..43744bf0fc1c 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ethtool.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2008 Intel Corporation. */ /* ethtool support for ixgb */ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c index bf9a220f71fb..cbaa933ef30d 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2008 Intel Corporation. */ /* ixgb_hw.c * Shared functions for accessing and configuring the adapter diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h index 19f36d87ef61..6064583095da 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_hw.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_hw.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2008 Intel Corporation. */ #ifndef _IXGB_HW_H_ #define _IXGB_HW_H_ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_ids.h b/drivers/net/ethernet/intel/ixgb/ixgb_ids.h index 24e849902d60..9695b8215f01 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_ids.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_ids.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2008 Intel Corporation. */ #ifndef _IXGB_IDS_H_ #define _IXGB_IDS_H_ diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_main.c b/drivers/net/ethernet/intel/ixgb/ixgb_main.c index 2353c383f0a7..62f2173bc20e 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_main.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_main.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2008 Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_osdep.h b/drivers/net/ethernet/intel/ixgb/ixgb_osdep.h index b1710379192e..7bd54efa698d 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_osdep.h +++ b/drivers/net/ethernet/intel/ixgb/ixgb_osdep.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2008 Intel Corporation. */ /* glue for the OS independent part of ixgb * includes register access macros diff --git a/drivers/net/ethernet/intel/ixgb/ixgb_param.c b/drivers/net/ethernet/intel/ixgb/ixgb_param.c index 04a60640ddda..f0cadd532c53 100644 --- a/drivers/net/ethernet/intel/ixgb/ixgb_param.c +++ b/drivers/net/ethernet/intel/ixgb/ixgb_param.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel PRO/10GbE Linux driver - Copyright(c) 1999 - 2008 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2008 Intel Corporation. */ #define pr_fmt(fmt) KBUILD_MODNAME ": " fmt diff --git a/drivers/net/ethernet/intel/ixgbe/Makefile b/drivers/net/ethernet/intel/ixgbe/Makefile index 4cd96c88cb5d..5414685189ce 100644 --- a/drivers/net/ethernet/intel/ixgbe/Makefile +++ b/drivers/net/ethernet/intel/ixgbe/Makefile @@ -1,32 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel 10 Gigabit PCI Express Linux driver -# Copyright(c) 1999 - 2013 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along with -# this program; if not, write to the Free Software Foundation, Inc., -# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# Linux NICS <linux.nics@intel.com> -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ - +# Copyright(c) 1999 - 2018 Intel Corporation. # # Makefile for the Intel(R) 10GbE PCI Express ethernet driver # diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe.h index 4f08c712e58e..fc534e91c6b2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_H_ #define _IXGBE_H_ @@ -241,8 +215,7 @@ struct ixgbe_tx_buffer { unsigned long time_stamp; union { struct sk_buff *skb; - /* XDP uses address ptr on irq_clean */ - void *data; + struct xdp_frame *xdpf; }; unsigned int bytecount; unsigned short gso_segs; @@ -306,7 +279,6 @@ enum ixgbe_ring_state_t { struct ixgbe_fwd_adapter { unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; struct net_device *netdev; - struct ixgbe_adapter *real_adapter; unsigned int tx_base_queue; unsigned int rx_base_queue; int pool; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c index cb0fe5fedb33..eee277c1bedf 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82598.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c index 66a74f4651e8..42f63b943ea0 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_82599.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c index 633be93f3dbb..8d038837f72b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h index 2b311382167a..4b531e8ae38a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_common.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_COMMON_H_ #define _IXGBE_COMMON_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c index aaea8282bfd2..d26cea5b43bd 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.c @@ -1,31 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ - +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe.h" #include "ixgbe_type.h" diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h index 73b6362d4327..60cd5863bf5e 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _DCB_CONFIG_H_ #define _DCB_CONFIG_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c index 085130626330..379ae747cdce 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.c @@ -1,31 +1,5 @@ // SPDX-License-Identifier: GPL-2.0 -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe.h" #include "ixgbe_type.h" diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h index 7edce607f901..fdca41abb44c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82598.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _DCB_82598_CONFIG_H_ #define _DCB_82598_CONFIG_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c index 1eed6811e914..7948849840a5 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe.h" #include "ixgbe_type.h" diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h index fa030f0abc18..c6f084883cab 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_82599.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _DCB_82599_CONFIG_H_ #define _DCB_82599_CONFIG_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c index b33f3f87e4b1..c00332d2e02a 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_dcb_nl.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2014 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe.h" #include <linux/dcbnl.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c index ad54080488ee..55fe8114fe99 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_debugfs.c @@ -1,30 +1,6 @@ -/******************************************************************************* +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ #include <linux/debugfs.h> #include <linux/module.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c index c0e6ab42e0e1..bdd179c29ea4 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ethtool.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* ethtool support for ixgbe */ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c index 7a09a40e4472..b5219e024f70 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2014 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe.h" #include <linux/if_ether.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h index cf1919901514..724f5382329f 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_fcoe.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_FCOE_H #define _IXGBE_FCOE_H diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c index cead23e3db0c..195c0b65eee2 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.c @@ -1,29 +1,5 @@ -/******************************************************************************* - * - * Intel 10 Gigabit PCI Express Linux driver - * Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along with - * this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. */ #include "ixgbe.h" #include <net/xfrm.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h index 4f099f516645..9ef7faadda69 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ipsec.h @@ -1,30 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program. If not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 2017 Oracle and/or its affiliates. All rights reserved. */ #ifndef _IXGBE_IPSEC_H_ #define _IXGBE_IPSEC_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c index ed4cbe94c355..893a9206e718 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_lib.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe.h" #include "ixgbe_sriov.h" diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c index afadba99f7b8..6652b201df5b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_main.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -1216,7 +1191,7 @@ static bool ixgbe_clean_tx_irq(struct ixgbe_q_vector *q_vector, /* free the skb */ if (ring_is_xdp(tx_ring)) - page_frag_free(tx_buffer->data); + xdp_return_frame(tx_buffer->xdpf); else napi_consume_skb(tx_buffer->skb, napi_budget); @@ -1768,15 +1743,14 @@ static void ixgbe_process_skb_fields(struct ixgbe_ring *rx_ring, if (ixgbe_test_staterr(rx_desc, IXGBE_RXDADV_STAT_SECP)) ixgbe_ipsec_rx(rx_ring, rx_desc, skb); - skb->protocol = eth_type_trans(skb, dev); - /* record Rx queue, or update MACVLAN statistics */ if (netif_is_ixgbe(dev)) skb_record_rx_queue(skb, rx_ring->queue_index); else macvlan_count_rx(netdev_priv(dev), skb->len + ETH_HLEN, true, - (skb->pkt_type == PACKET_BROADCAST) || - (skb->pkt_type == PACKET_MULTICAST)); + false); + + skb->protocol = eth_type_trans(skb, dev); } static void ixgbe_rx_skb(struct ixgbe_q_vector *q_vector, @@ -2262,7 +2236,7 @@ static struct sk_buff *ixgbe_build_skb(struct ixgbe_ring *rx_ring, #define IXGBE_XDP_TX 2 static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, - struct xdp_buff *xdp); + struct xdp_frame *xdpf); static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, struct ixgbe_ring *rx_ring, @@ -2270,6 +2244,7 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, { int err, result = IXGBE_XDP_PASS; struct bpf_prog *xdp_prog; + struct xdp_frame *xdpf; u32 act; rcu_read_lock(); @@ -2278,12 +2253,19 @@ static struct sk_buff *ixgbe_run_xdp(struct ixgbe_adapter *adapter, if (!xdp_prog) goto xdp_out; + prefetchw(xdp->data_hard_start); /* xdp_frame write */ + act = bpf_prog_run_xdp(xdp_prog, xdp); switch (act) { case XDP_PASS: break; case XDP_TX: - result = ixgbe_xmit_xdp_ring(adapter, xdp); + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) { + result = IXGBE_XDP_CONSUMED; + break; + } + result = ixgbe_xmit_xdp_ring(adapter, xdpf); break; case XDP_REDIRECT: err = xdp_do_redirect(adapter->netdev, xdp, xdp_prog); @@ -4211,7 +4193,8 @@ static void ixgbe_setup_psrtype(struct ixgbe_adapter *adapter) static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) { struct ixgbe_hw *hw = &adapter->hw; - u32 reg_offset, vf_shift; + u16 pool = adapter->num_rx_pools; + u32 reg_offset, vf_shift, vmolr; u32 gcr_ext, vmdctl; int i; @@ -4225,6 +4208,13 @@ static void ixgbe_configure_virtualization(struct ixgbe_adapter *adapter) vmdctl |= IXGBE_VT_CTL_REPLEN; IXGBE_WRITE_REG(hw, IXGBE_VT_CTL, vmdctl); + /* accept untagged packets until a vlan tag is + * specifically set for the VMDQ queue/pool + */ + vmolr = IXGBE_VMOLR_AUPE; + while (pool--) + IXGBE_WRITE_REG(hw, IXGBE_VMOLR(VMDQ_P(pool)), vmolr); + vf_shift = VMDQ_P(0) % 32; reg_offset = (VMDQ_P(0) >= 32) ? 1 : 0; @@ -4892,36 +4882,6 @@ int ixgbe_del_mac_filter(struct ixgbe_adapter *adapter, return -ENOMEM; } -/** - * ixgbe_write_uc_addr_list - write unicast addresses to RAR table - * @netdev: network interface device structure - * @vfn: pool to associate with unicast addresses - * - * Writes unicast address list to the RAR table. - * Returns: -ENOMEM on failure/insufficient address space - * 0 on no addresses written - * X on writing X addresses to the RAR table - **/ -static int ixgbe_write_uc_addr_list(struct net_device *netdev, int vfn) -{ - struct ixgbe_adapter *adapter = netdev_priv(netdev); - int count = 0; - - /* return ENOMEM indicating insufficient memory for addresses */ - if (netdev_uc_count(netdev) > ixgbe_available_rars(adapter, vfn)) - return -ENOMEM; - - if (!netdev_uc_empty(netdev)) { - struct netdev_hw_addr *ha; - netdev_for_each_uc_addr(ha, netdev) { - ixgbe_del_mac_filter(adapter, ha->addr, vfn); - ixgbe_add_mac_filter(adapter, ha->addr, vfn); - count++; - } - } - return count; -} - static int ixgbe_uc_sync(struct net_device *netdev, const unsigned char *addr) { struct ixgbe_adapter *adapter = netdev_priv(netdev); @@ -5301,29 +5261,6 @@ static void ixgbe_fdir_filter_restore(struct ixgbe_adapter *adapter) spin_unlock(&adapter->fdir_perfect_lock); } -static void ixgbe_macvlan_set_rx_mode(struct net_device *dev, unsigned int pool, - struct ixgbe_adapter *adapter) -{ - struct ixgbe_hw *hw = &adapter->hw; - u32 vmolr; - - /* No unicast promiscuous support for VMDQ devices. */ - vmolr = IXGBE_READ_REG(hw, IXGBE_VMOLR(pool)); - vmolr |= (IXGBE_VMOLR_ROMPE | IXGBE_VMOLR_BAM | IXGBE_VMOLR_AUPE); - - /* clear the affected bit */ - vmolr &= ~IXGBE_VMOLR_MPE; - - if (dev->flags & IFF_ALLMULTI) { - vmolr |= IXGBE_VMOLR_MPE; - } else { - vmolr |= IXGBE_VMOLR_ROMPE; - hw->mac.ops.update_mc_addr_list(hw, dev); - } - ixgbe_write_uc_addr_list(adapter->netdev, pool); - IXGBE_WRITE_REG(hw, IXGBE_VMOLR(pool), vmolr); -} - /** * ixgbe_clean_rx_ring - Free Rx Buffers per Queue * @rx_ring: ring to free buffers from @@ -5376,21 +5313,17 @@ static void ixgbe_clean_rx_ring(struct ixgbe_ring *rx_ring) rx_ring->next_to_use = 0; } -static int ixgbe_fwd_ring_up(struct net_device *vdev, +static int ixgbe_fwd_ring_up(struct ixgbe_adapter *adapter, struct ixgbe_fwd_adapter *accel) { - struct ixgbe_adapter *adapter = accel->real_adapter; + struct net_device *vdev = accel->netdev; int i, baseq, err; - if (!test_bit(accel->pool, adapter->fwd_bitmask)) - return 0; - baseq = accel->pool * adapter->num_rx_queues_per_pool; netdev_dbg(vdev, "pool %i:%i queues %i:%i\n", accel->pool, adapter->num_rx_pools, baseq, baseq + adapter->num_rx_queues_per_pool); - accel->netdev = vdev; accel->rx_base_queue = baseq; accel->tx_base_queue = baseq; @@ -5407,26 +5340,36 @@ static int ixgbe_fwd_ring_up(struct net_device *vdev, */ err = ixgbe_add_mac_filter(adapter, vdev->dev_addr, VMDQ_P(accel->pool)); - if (err >= 0) { - ixgbe_macvlan_set_rx_mode(vdev, accel->pool, adapter); + if (err >= 0) return 0; - } + + /* if we cannot add the MAC rule then disable the offload */ + macvlan_release_l2fw_offload(vdev); for (i = 0; i < adapter->num_rx_queues_per_pool; i++) adapter->rx_ring[baseq + i]->netdev = NULL; + netdev_err(vdev, "L2FW offload disabled due to L2 filter error\n"); + + clear_bit(accel->pool, adapter->fwd_bitmask); + kfree(accel); + return err; } -static int ixgbe_upper_dev_walk(struct net_device *upper, void *data) +static int ixgbe_macvlan_up(struct net_device *vdev, void *data) { - if (netif_is_macvlan(upper)) { - struct macvlan_dev *dfwd = netdev_priv(upper); - struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + struct ixgbe_adapter *adapter = data; + struct ixgbe_fwd_adapter *accel; - if (dfwd->fwd_priv) - ixgbe_fwd_ring_up(upper, vadapter); - } + if (!netif_is_macvlan(vdev)) + return 0; + + accel = macvlan_accel_priv(vdev); + if (!accel) + return 0; + + ixgbe_fwd_ring_up(adapter, accel); return 0; } @@ -5434,7 +5377,7 @@ static int ixgbe_upper_dev_walk(struct net_device *upper, void *data) static void ixgbe_configure_dfwd(struct ixgbe_adapter *adapter) { netdev_walk_all_upper_dev_rcu(adapter->netdev, - ixgbe_upper_dev_walk, NULL); + ixgbe_macvlan_up, adapter); } static void ixgbe_configure(struct ixgbe_adapter *adapter) @@ -5797,7 +5740,7 @@ static void ixgbe_clean_tx_ring(struct ixgbe_ring *tx_ring) /* Free all the Tx ring sk_buffs */ if (ring_is_xdp(tx_ring)) - page_frag_free(tx_buffer->data); + xdp_return_frame(tx_buffer->xdpf); else dev_kfree_skb_any(tx_buffer->skb); @@ -6370,7 +6313,7 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, struct device *dev = rx_ring->dev; int orig_node = dev_to_node(dev); int ring_node = -1; - int size; + int size, err; size = sizeof(struct ixgbe_rx_buffer) * rx_ring->count; @@ -6407,6 +6350,13 @@ int ixgbe_setup_rx_resources(struct ixgbe_adapter *adapter, rx_ring->queue_index) < 0) goto err; + err = xdp_rxq_info_reg_mem_model(&rx_ring->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err) { + xdp_rxq_info_unreg(&rx_ring->xdp_rxq); + goto err; + } + rx_ring->xdp_prog = adapter->xdp_prog; return 0; @@ -8336,7 +8286,7 @@ static u16 ixgbe_select_queue(struct net_device *dev, struct sk_buff *skb, } static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, - struct xdp_buff *xdp) + struct xdp_frame *xdpf) { struct ixgbe_ring *ring = adapter->xdp_ring[smp_processor_id()]; struct ixgbe_tx_buffer *tx_buffer; @@ -8345,12 +8295,12 @@ static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, dma_addr_t dma; u16 i; - len = xdp->data_end - xdp->data; + len = xdpf->len; if (unlikely(!ixgbe_desc_unused(ring))) return IXGBE_XDP_CONSUMED; - dma = dma_map_single(ring->dev, xdp->data, len, DMA_TO_DEVICE); + dma = dma_map_single(ring->dev, xdpf->data, len, DMA_TO_DEVICE); if (dma_mapping_error(ring->dev, dma)) return IXGBE_XDP_CONSUMED; @@ -8365,7 +8315,8 @@ static int ixgbe_xmit_xdp_ring(struct ixgbe_adapter *adapter, dma_unmap_len_set(tx_buffer, len, len); dma_unmap_addr_set(tx_buffer, dma, dma); - tx_buffer->data = xdp->data; + tx_buffer->xdpf = xdpf; + tx_desc->read.buffer_addr = cpu_to_le64(dma); /* put descriptor type bits */ @@ -8827,6 +8778,49 @@ static void ixgbe_set_prio_tc_map(struct ixgbe_adapter *adapter) } #endif /* CONFIG_IXGBE_DCB */ +static int ixgbe_reassign_macvlan_pool(struct net_device *vdev, void *data) +{ + struct ixgbe_adapter *adapter = data; + struct ixgbe_fwd_adapter *accel; + int pool; + + /* we only care about macvlans... */ + if (!netif_is_macvlan(vdev)) + return 0; + + /* that have hardware offload enabled... */ + accel = macvlan_accel_priv(vdev); + if (!accel) + return 0; + + /* If we can relocate to a different bit do so */ + pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); + if (pool < adapter->num_rx_pools) { + set_bit(pool, adapter->fwd_bitmask); + accel->pool = pool; + return 0; + } + + /* if we cannot find a free pool then disable the offload */ + netdev_err(vdev, "L2FW offload disabled due to lack of queue resources\n"); + macvlan_release_l2fw_offload(vdev); + kfree(accel); + + return 0; +} + +static void ixgbe_defrag_macvlan_pools(struct net_device *dev) +{ + struct ixgbe_adapter *adapter = netdev_priv(dev); + + /* flush any stale bits out of the fwd bitmask */ + bitmap_clear(adapter->fwd_bitmask, 1, 63); + + /* walk through upper devices reassigning pools */ + netdev_walk_all_upper_dev_rcu(dev, ixgbe_reassign_macvlan_pool, + adapter); +} + /** * ixgbe_setup_tc - configure net_device for multiple traffic classes * @@ -8894,6 +8888,8 @@ int ixgbe_setup_tc(struct net_device *dev, u8 tc) #endif /* CONFIG_IXGBE_DCB */ ixgbe_init_interrupt_scheme(adapter); + ixgbe_defrag_macvlan_pools(dev); + if (netif_running(dev)) return ixgbe_open(dev); @@ -8998,13 +8994,12 @@ struct upper_walk_data { static int get_macvlan_queue(struct net_device *upper, void *_data) { if (netif_is_macvlan(upper)) { - struct macvlan_dev *dfwd = netdev_priv(upper); - struct ixgbe_fwd_adapter *vadapter = dfwd->fwd_priv; + struct ixgbe_fwd_adapter *vadapter = macvlan_accel_priv(upper); struct upper_walk_data *data = _data; struct ixgbe_adapter *adapter = data->adapter; int ifindex = data->ifindex; - if (vadapter && vadapter->netdev->ifindex == ifindex) { + if (vadapter && upper->ifindex == ifindex) { data->queue = adapter->rx_ring[vadapter->rx_base_queue]->reg_idx; data->action = data->queue; return 1; @@ -9444,6 +9439,22 @@ static netdev_features_t ixgbe_fix_features(struct net_device *netdev, return features; } +static void ixgbe_reset_l2fw_offload(struct ixgbe_adapter *adapter) +{ + int rss = min_t(int, ixgbe_max_rss_indices(adapter), + num_online_cpus()); + + /* go back to full RSS if we're not running SR-IOV */ + if (!adapter->ring_feature[RING_F_VMDQ].offset) + adapter->flags &= ~(IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED); + + adapter->ring_feature[RING_F_RSS].limit = rss; + adapter->ring_feature[RING_F_VMDQ].limit = 1; + + ixgbe_setup_tc(adapter->netdev, adapter->hw_tcs); +} + static int ixgbe_set_features(struct net_device *netdev, netdev_features_t features) { @@ -9524,7 +9535,9 @@ static int ixgbe_set_features(struct net_device *netdev, } } - if (need_reset) + if ((changed & NETIF_F_HW_L2FW_DOFFLOAD) && adapter->num_rx_pools > 1) + ixgbe_reset_l2fw_offload(adapter); + else if (need_reset) ixgbe_do_reset(netdev); else if (changed & (NETIF_F_HW_VLAN_CTAG_RX | NETIF_F_HW_VLAN_CTAG_FILTER)) @@ -9787,71 +9800,98 @@ static int ixgbe_ndo_bridge_getlink(struct sk_buff *skb, u32 pid, u32 seq, static void *ixgbe_fwd_add(struct net_device *pdev, struct net_device *vdev) { - struct ixgbe_fwd_adapter *fwd_adapter = NULL; struct ixgbe_adapter *adapter = netdev_priv(pdev); - int used_pools = adapter->num_vfs + adapter->num_rx_pools; + struct ixgbe_fwd_adapter *accel; int tcs = adapter->hw_tcs ? : 1; - unsigned int limit; int pool, err; - /* Hardware has a limited number of available pools. Each VF, and the - * PF require a pool. Check to ensure we don't attempt to use more - * then the available number of pools. + /* The hardware supported by ixgbe only filters on the destination MAC + * address. In order to avoid issues we only support offloading modes + * where the hardware can actually provide the functionality. */ - if (used_pools >= IXGBE_MAX_VF_FUNCTIONS) - return ERR_PTR(-EINVAL); + if (!macvlan_supports_dest_filter(vdev)) + return ERR_PTR(-EMEDIUMTYPE); - if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && - adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) || - (adapter->num_rx_pools > IXGBE_MAX_MACVLANS)) - return ERR_PTR(-EBUSY); + pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); + if (pool == adapter->num_rx_pools) { + u16 used_pools = adapter->num_vfs + adapter->num_rx_pools; + u16 reserved_pools; + + if (((adapter->flags & IXGBE_FLAG_DCB_ENABLED) && + adapter->num_rx_pools >= (MAX_TX_QUEUES / tcs)) || + adapter->num_rx_pools > IXGBE_MAX_MACVLANS) + return ERR_PTR(-EBUSY); + + /* Hardware has a limited number of available pools. Each VF, + * and the PF require a pool. Check to ensure we don't + * attempt to use more then the available number of pools. + */ + if (used_pools >= IXGBE_MAX_VF_FUNCTIONS) + return ERR_PTR(-EBUSY); - fwd_adapter = kzalloc(sizeof(*fwd_adapter), GFP_KERNEL); - if (!fwd_adapter) - return ERR_PTR(-ENOMEM); + /* Enable VMDq flag so device will be set in VM mode */ + adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | + IXGBE_FLAG_SRIOV_ENABLED; - pool = find_first_zero_bit(adapter->fwd_bitmask, adapter->num_rx_pools); - set_bit(pool, adapter->fwd_bitmask); - limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools + 1); + /* Try to reserve as many queues per pool as possible, + * we start with the configurations that support 4 queues + * per pools, followed by 2, and then by just 1 per pool. + */ + if (used_pools < 32 && adapter->num_rx_pools < 16) + reserved_pools = min_t(u16, + 32 - used_pools, + 16 - adapter->num_rx_pools); + else if (adapter->num_rx_pools < 32) + reserved_pools = min_t(u16, + 64 - used_pools, + 32 - adapter->num_rx_pools); + else + reserved_pools = 64 - used_pools; - /* Enable VMDq flag so device will be set in VM mode */ - adapter->flags |= IXGBE_FLAG_VMDQ_ENABLED | IXGBE_FLAG_SRIOV_ENABLED; - adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; - fwd_adapter->pool = pool; - fwd_adapter->real_adapter = adapter; + if (!reserved_pools) + return ERR_PTR(-EBUSY); - /* Force reinit of ring allocation with VMDQ enabled */ - err = ixgbe_setup_tc(pdev, adapter->hw_tcs); + adapter->ring_feature[RING_F_VMDQ].limit += reserved_pools; - if (!err && netif_running(pdev)) - err = ixgbe_fwd_ring_up(vdev, fwd_adapter); + /* Force reinit of ring allocation with VMDQ enabled */ + err = ixgbe_setup_tc(pdev, adapter->hw_tcs); + if (err) + return ERR_PTR(err); - if (!err) - return fwd_adapter; + if (pool >= adapter->num_rx_pools) + return ERR_PTR(-ENOMEM); + } - /* unwind counter and free adapter struct */ - netdev_info(pdev, - "%s: dfwd hardware acceleration failed\n", vdev->name); - clear_bit(pool, adapter->fwd_bitmask); - kfree(fwd_adapter); - return ERR_PTR(err); + accel = kzalloc(sizeof(*accel), GFP_KERNEL); + if (!accel) + return ERR_PTR(-ENOMEM); + + set_bit(pool, adapter->fwd_bitmask); + accel->pool = pool; + accel->netdev = vdev; + + if (!netif_running(pdev)) + return accel; + + err = ixgbe_fwd_ring_up(adapter, accel); + if (err) + return ERR_PTR(err); + + return accel; } static void ixgbe_fwd_del(struct net_device *pdev, void *priv) { struct ixgbe_fwd_adapter *accel = priv; - struct ixgbe_adapter *adapter = accel->real_adapter; + struct ixgbe_adapter *adapter = netdev_priv(pdev); unsigned int rxbase = accel->rx_base_queue; - unsigned int limit, i; + unsigned int i; /* delete unicast filter associated with offloaded interface */ ixgbe_del_mac_filter(adapter, accel->netdev->dev_addr, VMDQ_P(accel->pool)); - /* disable ability to receive packets for this pool */ - IXGBE_WRITE_REG(&adapter->hw, IXGBE_VMOLR(accel->pool), 0); - /* Allow remaining Rx packets to get flushed out of the * Rx FIFO before we drop the netdev for the ring. */ @@ -9870,25 +9910,6 @@ static void ixgbe_fwd_del(struct net_device *pdev, void *priv) } clear_bit(accel->pool, adapter->fwd_bitmask); - limit = find_last_bit(adapter->fwd_bitmask, adapter->num_rx_pools); - adapter->ring_feature[RING_F_VMDQ].limit = limit + 1; - - /* go back to full RSS if we're done with our VMQs */ - if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { - int rss = min_t(int, ixgbe_max_rss_indices(adapter), - num_online_cpus()); - - adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; - adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; - adapter->ring_feature[RING_F_RSS].limit = rss; - } - - ixgbe_setup_tc(pdev, adapter->hw_tcs); - netdev_dbg(pdev, "pool %i:%i queues %i:%i\n", - accel->pool, adapter->num_rx_pools, - accel->rx_base_queue, - accel->rx_base_queue + - adapter->num_rx_queues_per_pool); kfree(accel); } @@ -9996,7 +10017,7 @@ static int ixgbe_xdp(struct net_device *dev, struct netdev_bpf *xdp) } } -static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) +static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf) { struct ixgbe_adapter *adapter = netdev_priv(dev); struct ixgbe_ring *ring; @@ -10012,7 +10033,7 @@ static int ixgbe_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) if (unlikely(!ring)) return -ENXIO; - err = ixgbe_xmit_xdp_ring(adapter, xdp); + err = ixgbe_xmit_xdp_ring(adapter, xdpf); if (err != IXGBE_XDP_TX) return -ENOSPC; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c index a0cb84381cd0..5679293e53f7 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h index c4628b663590..e085b6520dac 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_mbx.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_MBX_H_ #define _IXGBE_MBX_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h index 72446644f9fa..fcae520647ce 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_model.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel 10 Gigabit PCI Express Linux drive - * Copyright(c) 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * You should have received a copy of the GNU General Public License along - * with this program. If not, see <http://www.gnu.org/licenses/>. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_MODEL_H_ #define _IXGBE_MODEL_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c index 91bde90f9265..919a7af84b42 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2014 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h index d6a7e77348c5..64e44e01c973 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_phy.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_PHY_H_ #define _IXGBE_PHY_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c index f6cc9166082a..b3e0d8bb5cbd 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_ptp.c @@ -1,30 +1,6 @@ -/******************************************************************************* +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ #include "ixgbe.h" #include <linux/ptp_classify.h> #include <linux/clocksource.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c index 008aa073a679..2649c06d877b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2015 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/types.h> #include <linux/module.h> @@ -266,7 +241,7 @@ int ixgbe_disable_sriov(struct ixgbe_adapter *adapter) #endif /* Disable VMDq flag so device will be set in VM mode */ - if (adapter->ring_feature[RING_F_VMDQ].limit == 1) { + if (bitmap_weight(adapter->fwd_bitmask, adapter->num_rx_pools) == 1) { adapter->flags &= ~IXGBE_FLAG_VMDQ_ENABLED; adapter->flags &= ~IXGBE_FLAG_SRIOV_ENABLED; rss = min_t(int, ixgbe_max_rss_indices(adapter), @@ -312,7 +287,8 @@ static int ixgbe_pci_sriov_enable(struct pci_dev *dev, int num_vfs) * other values out of range. */ num_tc = adapter->hw_tcs; - num_rx_pools = adapter->num_rx_pools; + num_rx_pools = bitmap_weight(adapter->fwd_bitmask, + adapter->num_rx_pools); limit = (num_tc > 4) ? IXGBE_MAX_VFS_8TC : (num_tc > 1) ? IXGBE_MAX_VFS_4TC : IXGBE_MAX_VFS_1TC; diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h index e30d1f07e891..3ec21923c89c 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sriov.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_SRIOV_H_ #define _IXGBE_SRIOV_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c index 24766e125592..204844288c16 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_sysfs.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2013 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe.h" #include "ixgbe_common.h" diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h index 2daa81e6e9b2..e8ed37749ab1 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_type.h @@ -1,31 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_TYPE_H_ #define _IXGBE_TYPE_H_ diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c index b8c5fd2a2115..de563cfd294d 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.c @@ -1,30 +1,5 @@ -/******************************************************************************* - - Intel 10 Gigabit PCI Express Linux driver - Copyright(c) 1999 - 2016 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, write to the Free Software Foundation, Inc., - 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - Linux NICS <linux.nics@intel.com> - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include <linux/pci.h> #include <linux/delay.h> diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h index 182d640e9f7a..e246c0d2a427 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x540.h @@ -1,27 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - * - * Intel 10 Gigabit PCI Express Linux driver - * Copyright(c) 1999 - 2014 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - *****************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "ixgbe_type.h" diff --git a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c index 9592f3e3e42e..ac71ed76a54b 100644 --- a/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c +++ b/drivers/net/ethernet/intel/ixgbe/ixgbe_x550.c @@ -1,26 +1,6 @@ -/******************************************************************************* - * - * Intel 10 Gigabit PCI Express Linux driver - * Copyright(c) 1999 - 2016 Intel Corporation. - * - * This program is free software; you can redistribute it and/or modify it - * under the terms and conditions of the GNU General Public License, - * version 2, as published by the Free Software Foundation. - * - * This program is distributed in the hope it will be useful, but WITHOUT - * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - * more details. - * - * The full GNU General Public License is included in this distribution in - * the file called "COPYING". - * - * Contact Information: - * Linux NICS <linux.nics@intel.com> - * e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - * Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - * - ******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ + #include "ixgbe_x540.h" #include "ixgbe_type.h" #include "ixgbe_common.h" diff --git a/drivers/net/ethernet/intel/ixgbevf/Makefile b/drivers/net/ethernet/intel/ixgbevf/Makefile index bb47814cfa90..aba1e6a37a6a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/Makefile +++ b/drivers/net/ethernet/intel/ixgbevf/Makefile @@ -1,31 +1,5 @@ # SPDX-License-Identifier: GPL-2.0 -################################################################################ -# -# Intel 82599 Virtual Function driver -# Copyright(c) 1999 - 2012 Intel Corporation. -# -# This program is free software; you can redistribute it and/or modify it -# under the terms and conditions of the GNU General Public License, -# version 2, as published by the Free Software Foundation. -# -# This program is distributed in the hope it will be useful, but WITHOUT -# ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or -# FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for -# more details. -# -# You should have received a copy of the GNU General Public License along with -# this program; if not, write to the Free Software Foundation, Inc., -# 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. -# -# The full GNU General Public License is included in this distribution in -# the file called "COPYING". -# -# Contact Information: -# e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> -# Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 -# -################################################################################ - +# Copyright(c) 1999 - 2018 Intel Corporation. # # Makefile for the Intel(R) 82599 VF ethernet driver # diff --git a/drivers/net/ethernet/intel/ixgbevf/defines.h b/drivers/net/ethernet/intel/ixgbevf/defines.h index 71c828842b11..700d8eb2f6f8 100644 --- a/drivers/net/ethernet/intel/ixgbevf/defines.h +++ b/drivers/net/ethernet/intel/ixgbevf/defines.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2015 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBEVF_DEFINES_H_ #define _IXGBEVF_DEFINES_H_ diff --git a/drivers/net/ethernet/intel/ixgbevf/ethtool.c b/drivers/net/ethernet/intel/ixgbevf/ethtool.c index 8e7d6c6f5c92..e7813d76527c 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ethtool.c +++ b/drivers/net/ethernet/intel/ixgbevf/ethtool.c @@ -1,28 +1,5 @@ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2018 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /* ethtool support for ixgbevf */ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h index 447ce1d5e0e3..70c75681495f 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2018 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBEVF_H_ #define _IXGBEVF_H_ diff --git a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c index 850f8af95e49..1ccce6cd51fc 100644 --- a/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c +++ b/drivers/net/ethernet/intel/ixgbevf/ixgbevf_main.c @@ -1,28 +1,5 @@ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2018 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ /****************************************************************************** Copyright (c)2006 - 2007 Myricom, Inc. for some LRO specific code diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.c b/drivers/net/ethernet/intel/ixgbevf/mbx.c index 2819abc454c7..6bc1953263b9 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.c +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.c @@ -1,28 +1,5 @@ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2015 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "mbx.h" #include "ixgbevf.h" diff --git a/drivers/net/ethernet/intel/ixgbevf/mbx.h b/drivers/net/ethernet/intel/ixgbevf/mbx.h index 5ec947fe3d09..bfd9ae150808 100644 --- a/drivers/net/ethernet/intel/ixgbevf/mbx.h +++ b/drivers/net/ethernet/intel/ixgbevf/mbx.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2015 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBE_MBX_H_ #define _IXGBE_MBX_H_ diff --git a/drivers/net/ethernet/intel/ixgbevf/regs.h b/drivers/net/ethernet/intel/ixgbevf/regs.h index 278f73980501..68d16ae5b65a 100644 --- a/drivers/net/ethernet/intel/ixgbevf/regs.h +++ b/drivers/net/ethernet/intel/ixgbevf/regs.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2015 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef _IXGBEVF_REGS_H_ #define _IXGBEVF_REGS_H_ diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.c b/drivers/net/ethernet/intel/ixgbevf/vf.c index 38d3a327c1bc..bf0577e819e1 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.c +++ b/drivers/net/ethernet/intel/ixgbevf/vf.c @@ -1,28 +1,5 @@ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2015 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #include "vf.h" #include "ixgbevf.h" diff --git a/drivers/net/ethernet/intel/ixgbevf/vf.h b/drivers/net/ethernet/intel/ixgbevf/vf.h index 194fbdaa4519..d1e9e306653b 100644 --- a/drivers/net/ethernet/intel/ixgbevf/vf.h +++ b/drivers/net/ethernet/intel/ixgbevf/vf.h @@ -1,29 +1,5 @@ /* SPDX-License-Identifier: GPL-2.0 */ -/******************************************************************************* - - Intel 82599 Virtual Function driver - Copyright(c) 1999 - 2015 Intel Corporation. - - This program is free software; you can redistribute it and/or modify it - under the terms and conditions of the GNU General Public License, - version 2, as published by the Free Software Foundation. - - This program is distributed in the hope it will be useful, but WITHOUT - ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or - FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for - more details. - - You should have received a copy of the GNU General Public License along with - this program; if not, see <http://www.gnu.org/licenses/>. - - The full GNU General Public License is included in this distribution in - the file called "COPYING". - - Contact Information: - e1000-devel Mailing List <e1000-devel@lists.sourceforge.net> - Intel Corporation, 5200 N.E. Elam Young Parkway, Hillsboro, OR 97124-6497 - -*******************************************************************************/ +/* Copyright(c) 1999 - 2018 Intel Corporation. */ #ifndef __IXGBE_VF_H__ #define __IXGBE_VF_H__ diff --git a/drivers/net/ethernet/mediatek/mtk_eth_soc.c b/drivers/net/ethernet/mediatek/mtk_eth_soc.c index e0b72bf428f7..d8ebf0a05e0c 100644 --- a/drivers/net/ethernet/mediatek/mtk_eth_soc.c +++ b/drivers/net/ethernet/mediatek/mtk_eth_soc.c @@ -2503,7 +2503,6 @@ static int mtk_probe(struct platform_device *pdev) { struct resource *res = platform_get_resource(pdev, IORESOURCE_MEM, 0); struct device_node *mac_np; - const struct of_device_id *match; struct mtk_eth *eth; int err; int i; @@ -2512,8 +2511,7 @@ static int mtk_probe(struct platform_device *pdev) if (!eth) return -ENOMEM; - match = of_match_device(of_mtk_match, &pdev->dev); - eth->soc = (struct mtk_soc_data *)match->data; + eth->soc = of_device_get_match_data(&pdev->dev); eth->dev = &pdev->dev; eth->base = devm_ioremap_resource(&pdev->dev, res); diff --git a/drivers/net/ethernet/mellanox/mlx4/en_rx.c b/drivers/net/ethernet/mellanox/mlx4/en_rx.c index 5c613c6663da..9f54ccbddea7 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_rx.c @@ -593,30 +593,25 @@ static int get_fixed_ipv4_csum(__wsum hw_checksum, struct sk_buff *skb, } #if IS_ENABLED(CONFIG_IPV6) -/* In IPv6 packets, besides subtracting the pseudo header checksum, - * we also compute/add the IP header checksum which - * is not added by the HW. +/* In IPv6 packets, hw_checksum lacks 6 bytes from IPv6 header: + * 4 first bytes : priority, version, flow_lbl + * and 2 additional bytes : nexthdr, hop_limit. */ static int get_fixed_ipv6_csum(__wsum hw_checksum, struct sk_buff *skb, struct ipv6hdr *ipv6h) { __u8 nexthdr = ipv6h->nexthdr; - __wsum csum_pseudo_hdr = 0; + __wsum temp; if (unlikely(nexthdr == IPPROTO_FRAGMENT || nexthdr == IPPROTO_HOPOPTS || nexthdr == IPPROTO_SCTP)) return -1; - hw_checksum = csum_add(hw_checksum, (__force __wsum)htons(nexthdr)); - csum_pseudo_hdr = csum_partial(&ipv6h->saddr, - sizeof(ipv6h->saddr) + sizeof(ipv6h->daddr), 0); - csum_pseudo_hdr = csum_add(csum_pseudo_hdr, (__force __wsum)ipv6h->payload_len); - csum_pseudo_hdr = csum_add(csum_pseudo_hdr, - (__force __wsum)htons(nexthdr)); - - skb->csum = csum_sub(hw_checksum, csum_pseudo_hdr); - skb->csum = csum_add(skb->csum, csum_partial(ipv6h, sizeof(struct ipv6hdr), 0)); + /* priority, version, flow_lbl */ + temp = csum_add(hw_checksum, *(__wsum *)ipv6h); + /* nexthdr and hop_limit */ + skb->csum = csum_add(temp, (__force __wsum)*(__be16 *)&ipv6h->nexthdr); return 0; } #endif @@ -775,8 +770,8 @@ int mlx4_en_process_rx_cq(struct net_device *dev, struct mlx4_en_cq *cq, int bud act = bpf_prog_run_xdp(xdp_prog, &xdp); + length = xdp.data_end - xdp.data; if (xdp.data != orig_data) { - length = xdp.data_end - xdp.data; frags[0].page_offset = xdp.data - xdp.data_hard_start; va = xdp.data; diff --git a/drivers/net/ethernet/mellanox/mlx4/en_tx.c b/drivers/net/ethernet/mellanox/mlx4/en_tx.c index 6b6853773848..0227786308af 100644 --- a/drivers/net/ethernet/mellanox/mlx4/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx4/en_tx.c @@ -694,7 +694,7 @@ u16 mlx4_en_select_queue(struct net_device *dev, struct sk_buff *skb, u16 rings_p_up = priv->num_tx_rings_p_up; if (netdev_get_num_tc(dev)) - return skb_tx_hash(dev, skb); + return fallback(dev, skb); return fallback(dev, skb) % rings_p_up; } diff --git a/drivers/net/ethernet/mellanox/mlx4/fw.c b/drivers/net/ethernet/mellanox/mlx4/fw.c index de6b3d416148..46dcbfbe4c5e 100644 --- a/drivers/net/ethernet/mellanox/mlx4/fw.c +++ b/drivers/net/ethernet/mellanox/mlx4/fw.c @@ -165,6 +165,7 @@ static void dump_dev_cap_flags2(struct mlx4_dev *dev, u64 flags) [36] = "QinQ VST mode support", [37] = "sl to vl mapping table change event support", [38] = "user MAC support", + [39] = "Report driver version to FW support", }; int i; @@ -1038,6 +1039,8 @@ int mlx4_QUERY_DEV_CAP(struct mlx4_dev *dev, struct mlx4_dev_cap *dev_cap) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_ETH_BACKPL_AN_REP; if (field32 & (1 << 7)) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT; + if (field32 & (1 << 8)) + dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW; MLX4_GET(field32, outbox, QUERY_DEV_CAP_DIAG_RPRT_PER_PORT); if (field32 & (1 << 17)) dev_cap->flags2 |= MLX4_DEV_CAP_FLAG2_DIAG_PER_PORT; @@ -1860,6 +1863,8 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) #define INIT_HCA_UC_STEERING_OFFSET (INIT_HCA_MCAST_OFFSET + 0x18) #define INIT_HCA_LOG_MC_TABLE_SZ_OFFSET (INIT_HCA_MCAST_OFFSET + 0x1b) #define INIT_HCA_DEVICE_MANAGED_FLOW_STEERING_EN 0x6 +#define INIT_HCA_DRIVER_VERSION_OFFSET 0x140 +#define INIT_HCA_DRIVER_VERSION_SZ 0x40 #define INIT_HCA_FS_PARAM_OFFSET 0x1d0 #define INIT_HCA_FS_BASE_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x00) #define INIT_HCA_FS_LOG_ENTRY_SZ_OFFSET (INIT_HCA_FS_PARAM_OFFSET + 0x12) @@ -1950,6 +1955,13 @@ int mlx4_INIT_HCA(struct mlx4_dev *dev, struct mlx4_init_hca_param *param) if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_RECOVERABLE_ERROR_EVENT) *(inbox + INIT_HCA_RECOVERABLE_ERROR_EVENT_OFFSET / 4) |= cpu_to_be32(1 << 31); + if (dev->caps.flags2 & MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW) { + u8 *dst = (u8 *)(inbox + INIT_HCA_DRIVER_VERSION_OFFSET / 4); + + strncpy(dst, DRV_NAME_FOR_FW, INIT_HCA_DRIVER_VERSION_SZ - 1); + mlx4_dbg(dev, "Reporting Driver Version to FW: %s\n", dst); + } + /* QPC/EEC/CQC/EQC/RDMARC attributes */ MLX4_PUT(inbox, param->qpc_base, INIT_HCA_QPC_BASE_OFFSET); diff --git a/drivers/net/ethernet/mellanox/mlx4/main.c b/drivers/net/ethernet/mellanox/mlx4/main.c index 211578ffc70d..80a75c80a463 100644 --- a/drivers/net/ethernet/mellanox/mlx4/main.c +++ b/drivers/net/ethernet/mellanox/mlx4/main.c @@ -73,7 +73,7 @@ MODULE_PARM_DESC(debug_level, "Enable debug tracing if > 0"); static int msi_x = 1; module_param(msi_x, int, 0444); -MODULE_PARM_DESC(msi_x, "attempt to use MSI-X if nonzero"); +MODULE_PARM_DESC(msi_x, "0 - don't use MSI-X, 1 - use MSI-X, >1 - limit number of MSI-X irqs to msi_x"); #else /* CONFIG_PCI_MSI */ @@ -2815,6 +2815,9 @@ static void mlx4_enable_msi_x(struct mlx4_dev *dev) dev->caps.num_eqs - dev->caps.reserved_eqs, MAX_MSIX); + if (msi_x > 1) + nreq = min_t(int, nreq, msi_x); + entries = kcalloc(nreq, sizeof(*entries), GFP_KERNEL); if (!entries) goto no_msi; @@ -4125,17 +4128,68 @@ static const struct pci_error_handlers mlx4_err_handler = { .resume = mlx4_pci_resume, }; +static int mlx4_suspend(struct pci_dev *pdev, pm_message_t state) +{ + struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; + + mlx4_err(dev, "suspend was called\n"); + mutex_lock(&persist->interface_state_mutex); + if (persist->interface_state & MLX4_INTERFACE_STATE_UP) + mlx4_unload_one(pdev); + mutex_unlock(&persist->interface_state_mutex); + + return 0; +} + +static int mlx4_resume(struct pci_dev *pdev) +{ + struct mlx4_dev_persistent *persist = pci_get_drvdata(pdev); + struct mlx4_dev *dev = persist->dev; + struct mlx4_priv *priv = mlx4_priv(dev); + int nvfs[MLX4_MAX_PORTS + 1] = {0, 0, 0}; + int total_vfs; + int ret = 0; + + mlx4_err(dev, "resume was called\n"); + total_vfs = dev->persist->num_vfs; + memcpy(nvfs, dev->persist->nvfs, sizeof(dev->persist->nvfs)); + + mutex_lock(&persist->interface_state_mutex); + if (!(persist->interface_state & MLX4_INTERFACE_STATE_UP)) { + ret = mlx4_load_one(pdev, priv->pci_dev_data, total_vfs, + nvfs, priv, 1); + if (!ret) { + ret = restore_current_port_types(dev, + dev->persist->curr_port_type, + dev->persist->curr_port_poss_type); + if (ret) + mlx4_err(dev, "resume: could not restore original port types (%d)\n", ret); + } + } + mutex_unlock(&persist->interface_state_mutex); + + return ret; +} + static struct pci_driver mlx4_driver = { .name = DRV_NAME, .id_table = mlx4_pci_table, .probe = mlx4_init_one, .shutdown = mlx4_shutdown, .remove = mlx4_remove_one, + .suspend = mlx4_suspend, + .resume = mlx4_resume, .err_handler = &mlx4_err_handler, }; static int __init mlx4_verify_params(void) { + if (msi_x < 0) { + pr_warn("mlx4_core: bad msi_x: %d\n", msi_x); + return -1; + } + if ((log_num_mac < 0) || (log_num_mac > 7)) { pr_warn("mlx4_core: bad num_mac: %d\n", log_num_mac); return -1; diff --git a/drivers/net/ethernet/mellanox/mlx4/mlx4.h b/drivers/net/ethernet/mellanox/mlx4/mlx4.h index c68da1986e51..cb9e923e8399 100644 --- a/drivers/net/ethernet/mellanox/mlx4/mlx4.h +++ b/drivers/net/ethernet/mellanox/mlx4/mlx4.h @@ -55,8 +55,8 @@ #include "fw_qos.h" #define DRV_NAME "mlx4_core" -#define PFX DRV_NAME ": " #define DRV_VERSION "4.0-0" +#define DRV_NAME_FOR_FW "Linux," DRV_NAME "," DRV_VERSION #define MLX4_FS_UDP_UC_EN (1 << 1) #define MLX4_FS_TCP_UC_EN (1 << 2) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig index c032319f1cb9..ee6684779d11 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Kconfig +++ b/drivers/net/ethernet/mellanox/mlx5/core/Kconfig @@ -30,6 +30,7 @@ config MLX5_CORE_EN bool "Mellanox Technologies ConnectX-4 Ethernet support" depends on NETDEVICES && ETHERNET && INET && PCI && MLX5_CORE depends on IPV6=y || IPV6=n || MLX5_CORE=m + select PAGE_POOL default n ---help--- Ethernet support in Mellanox Technologies ConnectX-4 NIC. @@ -85,3 +86,14 @@ config MLX5_EN_IPSEC Build support for IPsec cryptography-offload accelaration in the NIC. Note: Support for hardware with this capability needs to be selected for this option to become available. + +config MLX5_EN_TLS + bool "TLS cryptography-offload accelaration" + depends on MLX5_CORE_EN + depends on TLS_DEVICE + depends on MLX5_ACCEL + default n + ---help--- + Build support for TLS cryptography-offload accelaration in the NIC. + Note: Support for hardware with this capability needs to be selected + for this option to become available. diff --git a/drivers/net/ethernet/mellanox/mlx5/core/Makefile b/drivers/net/ethernet/mellanox/mlx5/core/Makefile index c805769d92a9..a7135f5d5cf6 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/Makefile +++ b/drivers/net/ethernet/mellanox/mlx5/core/Makefile @@ -8,10 +8,10 @@ mlx5_core-y := main.o cmd.o debugfs.o fw.o eq.o uar.o pagealloc.o \ fs_counters.o rl.o lag.o dev.o wq.o lib/gid.o lib/clock.o \ diag/fs_tracepoint.o -mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o +mlx5_core-$(CONFIG_MLX5_ACCEL) += accel/ipsec.o accel/tls.o mlx5_core-$(CONFIG_MLX5_FPGA) += fpga/cmd.o fpga/core.o fpga/conn.o fpga/sdk.o \ - fpga/ipsec.o + fpga/ipsec.o fpga/tls.o mlx5_core-$(CONFIG_MLX5_CORE_EN) += en_main.o en_common.o en_fs.o en_ethtool.o \ en_tx.o en_rx.o en_dim.o en_txrx.o en_stats.o vxlan.o \ @@ -28,4 +28,6 @@ mlx5_core-$(CONFIG_MLX5_CORE_IPOIB) += ipoib/ipoib.o ipoib/ethtool.o ipoib/ipoib mlx5_core-$(CONFIG_MLX5_EN_IPSEC) += en_accel/ipsec.o en_accel/ipsec_rxtx.o \ en_accel/ipsec_stats.o +mlx5_core-$(CONFIG_MLX5_EN_TLS) += en_accel/tls.o en_accel/tls_rxtx.o en_accel/tls_stats.o + CFLAGS_tracepoint.o := -I$(src) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c new file mode 100644 index 000000000000..77ac19f38cbe --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.c @@ -0,0 +1,71 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/mlx5/device.h> + +#include "accel/tls.h" +#include "mlx5_core.h" +#include "fpga/tls.h" + +int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid) +{ + return mlx5_fpga_tls_add_tx_flow(mdev, flow, crypto_info, + start_offload_tcp_sn, p_swid); +} + +void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) +{ + mlx5_fpga_tls_del_tx_flow(mdev, swid, GFP_KERNEL); +} + +bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) +{ + return mlx5_fpga_is_tls_device(mdev); +} + +u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) +{ + return mlx5_fpga_tls_device_caps(mdev); +} + +int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) +{ + return mlx5_fpga_tls_init(mdev); +} + +void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev) +{ + mlx5_fpga_tls_cleanup(mdev); +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h new file mode 100644 index 000000000000..6f9c9f446ecc --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/accel/tls.h @@ -0,0 +1,86 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5_ACCEL_TLS_H__ +#define __MLX5_ACCEL_TLS_H__ + +#include <linux/mlx5/driver.h> +#include <linux/tls.h> + +#ifdef CONFIG_MLX5_ACCEL + +enum { + MLX5_ACCEL_TLS_TX = BIT(0), + MLX5_ACCEL_TLS_RX = BIT(1), + MLX5_ACCEL_TLS_V12 = BIT(2), + MLX5_ACCEL_TLS_V13 = BIT(3), + MLX5_ACCEL_TLS_LRO = BIT(4), + MLX5_ACCEL_TLS_IPV6 = BIT(5), + MLX5_ACCEL_TLS_AES_GCM128 = BIT(30), + MLX5_ACCEL_TLS_AES_GCM256 = BIT(31), +}; + +struct mlx5_ifc_tls_flow_bits { + u8 src_port[0x10]; + u8 dst_port[0x10]; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; + u8 ipv6[0x1]; + u8 direction_sx[0x1]; + u8 reserved_at_2[0x1e]; +}; + +int mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid); +void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid); +bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev); +u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev); +int mlx5_accel_tls_init(struct mlx5_core_dev *mdev); +void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev); + +#else + +static inline int +mlx5_accel_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid) { return 0; } +static inline void mlx5_accel_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid) { } +static inline bool mlx5_accel_is_tls_device(struct mlx5_core_dev *mdev) { return false; } +static inline u32 mlx5_accel_tls_device_caps(struct mlx5_core_dev *mdev) { return 0; } +static inline int mlx5_accel_tls_init(struct mlx5_core_dev *mdev) { return 0; } +static inline void mlx5_accel_tls_cleanup(struct mlx5_core_dev *mdev) { } + +#endif + +#endif /* __MLX5_ACCEL_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c index 21cd1703a862..487388aed98f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/cmd.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/cmd.c @@ -135,6 +135,14 @@ static struct mlx5_cmd_layout *get_inst(struct mlx5_cmd *cmd, int idx) return cmd->cmd_buf + (idx << cmd->log_stride); } +static int mlx5_calc_cmd_blocks(struct mlx5_cmd_msg *msg) +{ + int size = msg->len; + int blen = size - min_t(int, sizeof(msg->first.data), size); + + return DIV_ROUND_UP(blen, MLX5_CMD_DATA_BLOCK_SIZE); +} + static u8 xor8_buf(void *buf, size_t offset, int len) { u8 *ptr = buf; @@ -174,10 +182,7 @@ static void calc_block_sig(struct mlx5_cmd_prot_block *block) static void calc_chain_sig(struct mlx5_cmd_msg *msg) { struct mlx5_cmd_mailbox *next = msg->next; - int size = msg->len; - int blen = size - min_t(int, sizeof(msg->first.data), size); - int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) - / MLX5_CMD_DATA_BLOCK_SIZE; + int n = mlx5_calc_cmd_blocks(msg); int i = 0; for (i = 0; i < n && next; i++) { @@ -220,12 +225,9 @@ static void free_cmd(struct mlx5_cmd_work_ent *ent) static int verify_signature(struct mlx5_cmd_work_ent *ent) { struct mlx5_cmd_mailbox *next = ent->out->next; + int n = mlx5_calc_cmd_blocks(ent->out); int err; u8 sig; - int size = ent->out->len; - int blen = size - min_t(int, sizeof(ent->out->first.data), size); - int n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) - / MLX5_CMD_DATA_BLOCK_SIZE; int i = 0; sig = xor8_buf(ent->lay, 0, sizeof(*ent->lay)); @@ -720,9 +722,11 @@ static void dump_command(struct mlx5_core_dev *dev, struct mlx5_cmd_msg *msg = input ? ent->in : ent->out; u16 op = MLX5_GET(mbox_in, ent->lay->in, opcode); struct mlx5_cmd_mailbox *next = msg->next; + int n = mlx5_calc_cmd_blocks(msg); int data_only; u32 offset = 0; int dump_len; + int i; data_only = !!(mlx5_core_debug_mask & (1 << MLX5_CMD_DATA)); @@ -749,7 +753,7 @@ static void dump_command(struct mlx5_core_dev *dev, offset += sizeof(*ent->lay); } - while (next && offset < msg->len) { + for (i = 0; i < n && next; i++) { if (data_only) { dump_len = min_t(int, MLX5_CMD_DATA_BLOCK_SIZE, msg->len - offset); dump_buf(next->buf, dump_len, 1, offset); @@ -1137,7 +1141,6 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, struct mlx5_cmd_mailbox *tmp, *head = NULL; struct mlx5_cmd_prot_block *block; struct mlx5_cmd_msg *msg; - int blen; int err; int n; int i; @@ -1146,8 +1149,8 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, if (!msg) return ERR_PTR(-ENOMEM); - blen = size - min_t(int, sizeof(msg->first.data), size); - n = (blen + MLX5_CMD_DATA_BLOCK_SIZE - 1) / MLX5_CMD_DATA_BLOCK_SIZE; + msg->len = size; + n = mlx5_calc_cmd_blocks(msg); for (i = 0; i < n; i++) { tmp = alloc_cmd_box(dev, flags); @@ -1165,7 +1168,6 @@ static struct mlx5_cmd_msg *mlx5_alloc_cmd_msg(struct mlx5_core_dev *dev, head = tmp; } msg->next = head; - msg->len = size; return msg; err_alloc: diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en.h b/drivers/net/ethernet/mellanox/mlx5/core/en.h index 30cad07be2b5..9cc07da09b70 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en.h @@ -53,6 +53,11 @@ #include "mlx5_core.h" #include "en_stats.h" +struct page_pool; + +#define MLX5E_METADATA_ETHER_TYPE (0x8CE4) +#define MLX5E_METADATA_ETHER_LEN 8 + #define MLX5_SET_CFG(p, f, v) MLX5_SET(create_flow_group_in, p, f, v) #define MLX5E_ETH_HARD_MTU (ETH_HLEN + VLAN_HLEN + ETH_FCS_LEN) @@ -239,6 +244,7 @@ struct mlx5e_params { bool vlan_strip_disable; bool scatter_fcs_en; bool rx_dim_enabled; + bool tx_dim_enabled; u32 lro_timeout; u32 pflags; struct bpf_prog *xdp_prog; @@ -328,6 +334,8 @@ enum { MLX5E_SQ_STATE_ENABLED, MLX5E_SQ_STATE_RECOVERING, MLX5E_SQ_STATE_IPSEC, + MLX5E_SQ_STATE_AM, + MLX5E_SQ_STATE_TLS, }; struct mlx5e_sq_wqe_info { @@ -340,6 +348,7 @@ struct mlx5e_txqsq { /* dirtied @completion */ u16 cc; u32 dma_fifo_cc; + struct net_dim dim; /* Adaptive Moderation */ /* dirtied @xmit */ u16 pc ____cacheline_aligned_in_smp; @@ -392,6 +401,7 @@ struct mlx5e_xdpsq { struct { struct mlx5e_dma_info *di; bool doorbell; + bool redirect_flush; } db; /* read only */ @@ -533,6 +543,7 @@ struct mlx5e_rq { unsigned int hw_mtu; struct mlx5e_xdpsq xdpsq; DECLARE_BITMAP(flags, 8); + struct page_pool *page_pool; /* control */ struct mlx5_wq_ctrl wq_ctrl; @@ -790,6 +801,9 @@ struct mlx5e_priv { #ifdef CONFIG_MLX5_EN_IPSEC struct mlx5e_ipsec *ipsec; #endif +#ifdef CONFIG_MLX5_EN_TLS + struct mlx5e_tls *tls; +#endif }; struct mlx5e_profile { @@ -820,6 +834,8 @@ void mlx5e_build_ptys2ethtool_map(void); u16 mlx5e_select_queue(struct net_device *dev, struct sk_buff *skb, void *accel_priv, select_queue_fallback_t fallback); netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev); +netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_tx_wqe *wqe, u16 pi); void mlx5e_completion_event(struct mlx5_core_cq *mcq); void mlx5e_cq_error_event(struct mlx5_core_cq *mcq, enum mlx5_event event); @@ -935,6 +951,18 @@ static inline bool mlx5e_tunnel_inner_ft_supported(struct mlx5_core_dev *mdev) MLX5_CAP_FLOWTABLE_NIC_RX(mdev, ft_field_support.inner_ip_version)); } +static inline void mlx5e_sq_fetch_wqe(struct mlx5e_txqsq *sq, + struct mlx5e_tx_wqe **wqe, + u16 *pi) +{ + struct mlx5_wq_cyc *wq; + + wq = &sq->wq; + *pi = sq->pc & wq->sz_m1; + *wqe = mlx5_wq_cyc_get_wqe(wq, *pi); + memset(*wqe, 0, sizeof(**wqe)); +} + static inline struct mlx5e_tx_wqe *mlx5e_post_nop(struct mlx5_wq_cyc *wq, u32 sqn, u16 *pc) { @@ -1107,4 +1135,5 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, u16 max_channels, u16 mtu); u8 mlx5e_params_calculate_tx_min_inline(struct mlx5_core_dev *mdev); void mlx5e_rx_dim_work(struct work_struct *work); +void mlx5e_tx_dim_work(struct work_struct *work); #endif /* __MLX5_EN_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h new file mode 100644 index 000000000000..68fcb40a2847 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/en_accel.h @@ -0,0 +1,72 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5E_EN_ACCEL_H__ +#define __MLX5E_EN_ACCEL_H__ + +#ifdef CONFIG_MLX5_ACCEL + +#include <linux/skbuff.h> +#include <linux/netdevice.h> +#include "en_accel/ipsec_rxtx.h" +#include "en_accel/tls_rxtx.h" +#include "en.h" + +static inline struct sk_buff *mlx5e_accel_handle_tx(struct sk_buff *skb, + struct mlx5e_txqsq *sq, + struct net_device *dev, + struct mlx5e_tx_wqe **wqe, + u16 *pi) +{ +#ifdef CONFIG_MLX5_EN_TLS + if (sq->state & BIT(MLX5E_SQ_STATE_TLS)) { + skb = mlx5e_tls_handle_tx_skb(dev, sq, skb, wqe, pi); + if (unlikely(!skb)) + return NULL; + } +#endif + +#ifdef CONFIG_MLX5_EN_IPSEC + if (sq->state & BIT(MLX5E_SQ_STATE_IPSEC)) { + skb = mlx5e_ipsec_handle_tx_skb(dev, *wqe, skb); + if (unlikely(!skb)) + return NULL; + } +#endif + + return skb; +} + +#endif /* CONFIG_MLX5_ACCEL */ + +#endif /* __MLX5E_EN_ACCEL_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h index 1198fc1eba4c..93bf10e6508c 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/ipsec.h @@ -45,9 +45,6 @@ #define MLX5E_IPSEC_SADB_RX_BITS 10 #define MLX5E_IPSEC_ESN_SCOPE_MID 0x80000000L -#define MLX5E_METADATA_ETHER_TYPE (0x8CE4) -#define MLX5E_METADATA_ETHER_LEN 8 - struct mlx5e_priv; struct mlx5e_ipsec_sw_stats { diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c new file mode 100644 index 000000000000..d167845271c3 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.c @@ -0,0 +1,197 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/netdevice.h> +#include <net/ipv6.h> +#include "en_accel/tls.h" +#include "accel/tls.h" + +static void mlx5e_tls_set_ipv4_flow(void *flow, struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + + MLX5_SET(tls_flow, flow, ipv6, 0); + memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv4_layout.ipv4), + &inet->inet_daddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4)); + memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv4_layout.ipv4), + &inet->inet_rcv_saddr, MLX5_FLD_SZ_BYTES(ipv4_layout, ipv4)); +} + +#if IS_ENABLED(CONFIG_IPV6) +static void mlx5e_tls_set_ipv6_flow(void *flow, struct sock *sk) +{ + struct ipv6_pinfo *np = inet6_sk(sk); + + MLX5_SET(tls_flow, flow, ipv6, 1); + memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_ipv4_dst_ipv6.ipv6_layout.ipv6), + &sk->sk_v6_daddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); + memcpy(MLX5_ADDR_OF(tls_flow, flow, src_ipv4_src_ipv6.ipv6_layout.ipv6), + &np->saddr, MLX5_FLD_SZ_BYTES(ipv6_layout, ipv6)); +} +#endif + +static void mlx5e_tls_set_flow_tcp_ports(void *flow, struct sock *sk) +{ + struct inet_sock *inet = inet_sk(sk); + + memcpy(MLX5_ADDR_OF(tls_flow, flow, src_port), &inet->inet_sport, + MLX5_FLD_SZ_BYTES(tls_flow, src_port)); + memcpy(MLX5_ADDR_OF(tls_flow, flow, dst_port), &inet->inet_dport, + MLX5_FLD_SZ_BYTES(tls_flow, dst_port)); +} + +static int mlx5e_tls_set_flow(void *flow, struct sock *sk, u32 caps) +{ + switch (sk->sk_family) { + case AF_INET: + mlx5e_tls_set_ipv4_flow(flow, sk); + break; +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: + if (!sk->sk_ipv6only && + ipv6_addr_type(&sk->sk_v6_daddr) == IPV6_ADDR_MAPPED) { + mlx5e_tls_set_ipv4_flow(flow, sk); + break; + } + if (!(caps & MLX5_ACCEL_TLS_IPV6)) + goto error_out; + + mlx5e_tls_set_ipv6_flow(flow, sk); + break; +#endif + default: + goto error_out; + } + + mlx5e_tls_set_flow_tcp_ports(flow, sk); + return 0; +error_out: + return -EINVAL; +} + +static int mlx5e_tls_add(struct net_device *netdev, struct sock *sk, + enum tls_offload_ctx_dir direction, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct mlx5_core_dev *mdev = priv->mdev; + u32 caps = mlx5_accel_tls_device_caps(mdev); + int ret = -ENOMEM; + void *flow; + + if (direction != TLS_OFFLOAD_CTX_DIR_TX) + return -EINVAL; + + flow = kzalloc(MLX5_ST_SZ_BYTES(tls_flow), GFP_KERNEL); + if (!flow) + return ret; + + ret = mlx5e_tls_set_flow(flow, sk, caps); + if (ret) + goto free_flow; + + if (direction == TLS_OFFLOAD_CTX_DIR_TX) { + struct mlx5e_tls_offload_context *tx_ctx = + mlx5e_get_tls_tx_context(tls_ctx); + u32 swid; + + ret = mlx5_accel_tls_add_tx_flow(mdev, flow, crypto_info, + start_offload_tcp_sn, &swid); + if (ret < 0) + goto free_flow; + + tx_ctx->swid = htonl(swid); + tx_ctx->expected_seq = start_offload_tcp_sn; + } + + return 0; +free_flow: + kfree(flow); + return ret; +} + +static void mlx5e_tls_del(struct net_device *netdev, + struct tls_context *tls_ctx, + enum tls_offload_ctx_dir direction) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + + if (direction == TLS_OFFLOAD_CTX_DIR_TX) { + u32 swid = ntohl(mlx5e_get_tls_tx_context(tls_ctx)->swid); + + mlx5_accel_tls_del_tx_flow(priv->mdev, swid); + } else { + netdev_err(netdev, "unsupported direction %d\n", direction); + } +} + +static const struct tlsdev_ops mlx5e_tls_ops = { + .tls_dev_add = mlx5e_tls_add, + .tls_dev_del = mlx5e_tls_del, +}; + +void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) +{ + struct net_device *netdev = priv->netdev; + + if (!mlx5_accel_is_tls_device(priv->mdev)) + return; + + netdev->features |= NETIF_F_HW_TLS_TX; + netdev->hw_features |= NETIF_F_HW_TLS_TX; + netdev->tlsdev_ops = &mlx5e_tls_ops; +} + +int mlx5e_tls_init(struct mlx5e_priv *priv) +{ + struct mlx5e_tls *tls = kzalloc(sizeof(*tls), GFP_KERNEL); + + if (!tls) + return -ENOMEM; + + priv->tls = tls; + return 0; +} + +void mlx5e_tls_cleanup(struct mlx5e_priv *priv) +{ + struct mlx5e_tls *tls = priv->tls; + + if (!tls) + return; + + kfree(tls); + priv->tls = NULL; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h new file mode 100644 index 000000000000..b6162178f621 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls.h @@ -0,0 +1,87 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ +#ifndef __MLX5E_TLS_H__ +#define __MLX5E_TLS_H__ + +#ifdef CONFIG_MLX5_EN_TLS + +#include <net/tls.h> +#include "en.h" + +struct mlx5e_tls_sw_stats { + atomic64_t tx_tls_drop_metadata; + atomic64_t tx_tls_drop_resync_alloc; + atomic64_t tx_tls_drop_no_sync_data; + atomic64_t tx_tls_drop_bypass_required; +}; + +struct mlx5e_tls { + struct mlx5e_tls_sw_stats sw_stats; +}; + +struct mlx5e_tls_offload_context { + struct tls_offload_context base; + u32 expected_seq; + __be32 swid; +}; + +static inline struct mlx5e_tls_offload_context * +mlx5e_get_tls_tx_context(struct tls_context *tls_ctx) +{ + BUILD_BUG_ON(sizeof(struct mlx5e_tls_offload_context) > + TLS_OFFLOAD_CONTEXT_SIZE); + return container_of(tls_offload_ctx(tls_ctx), + struct mlx5e_tls_offload_context, + base); +} + +void mlx5e_tls_build_netdev(struct mlx5e_priv *priv); +int mlx5e_tls_init(struct mlx5e_priv *priv); +void mlx5e_tls_cleanup(struct mlx5e_priv *priv); + +int mlx5e_tls_get_count(struct mlx5e_priv *priv); +int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data); +int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data); + +#else + +static inline void mlx5e_tls_build_netdev(struct mlx5e_priv *priv) { } +static inline int mlx5e_tls_init(struct mlx5e_priv *priv) { return 0; } +static inline void mlx5e_tls_cleanup(struct mlx5e_priv *priv) { } +static inline int mlx5e_tls_get_count(struct mlx5e_priv *priv) { return 0; } +static inline int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) { return 0; } +static inline int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) { return 0; } + +#endif + +#endif /* __MLX5E_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c new file mode 100644 index 000000000000..ad2790fb5966 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.c @@ -0,0 +1,278 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include "en_accel/tls.h" +#include "en_accel/tls_rxtx.h" + +#define SYNDROME_OFFLOAD_REQUIRED 32 +#define SYNDROME_SYNC 33 + +struct sync_info { + u64 rcd_sn; + s32 sync_len; + int nr_frags; + skb_frag_t frags[MAX_SKB_FRAGS]; +}; + +struct mlx5e_tls_metadata { + /* One byte of syndrome followed by 3 bytes of swid */ + __be32 syndrome_swid; + __be16 first_seq; + /* packet type ID field */ + __be16 ethertype; +} __packed; + +static int mlx5e_tls_add_metadata(struct sk_buff *skb, __be32 swid) +{ + struct mlx5e_tls_metadata *pet; + struct ethhdr *eth; + + if (skb_cow_head(skb, sizeof(struct mlx5e_tls_metadata))) + return -ENOMEM; + + eth = (struct ethhdr *)skb_push(skb, sizeof(struct mlx5e_tls_metadata)); + skb->mac_header -= sizeof(struct mlx5e_tls_metadata); + pet = (struct mlx5e_tls_metadata *)(eth + 1); + + memmove(skb->data, skb->data + sizeof(struct mlx5e_tls_metadata), + 2 * ETH_ALEN); + + eth->h_proto = cpu_to_be16(MLX5E_METADATA_ETHER_TYPE); + pet->syndrome_swid = htonl(SYNDROME_OFFLOAD_REQUIRED << 24) | swid; + + return 0; +} + +static int mlx5e_tls_get_sync_data(struct mlx5e_tls_offload_context *context, + u32 tcp_seq, struct sync_info *info) +{ + int remaining, i = 0, ret = -EINVAL; + struct tls_record_info *record; + unsigned long flags; + s32 sync_size; + + spin_lock_irqsave(&context->base.lock, flags); + record = tls_get_record(&context->base, tcp_seq, &info->rcd_sn); + + if (unlikely(!record)) + goto out; + + sync_size = tcp_seq - tls_record_start_seq(record); + info->sync_len = sync_size; + if (unlikely(sync_size < 0)) { + if (tls_record_is_start_marker(record)) + goto done; + + goto out; + } + + remaining = sync_size; + while (remaining > 0) { + info->frags[i] = record->frags[i]; + __skb_frag_ref(&info->frags[i]); + remaining -= skb_frag_size(&info->frags[i]); + + if (remaining < 0) + skb_frag_size_add(&info->frags[i], remaining); + + i++; + } + info->nr_frags = i; +done: + ret = 0; +out: + spin_unlock_irqrestore(&context->base.lock, flags); + return ret; +} + +static void mlx5e_tls_complete_sync_skb(struct sk_buff *skb, + struct sk_buff *nskb, u32 tcp_seq, + int headln, __be64 rcd_sn) +{ + struct mlx5e_tls_metadata *pet; + u8 syndrome = SYNDROME_SYNC; + struct iphdr *iph; + struct tcphdr *th; + int data_len, mss; + + nskb->dev = skb->dev; + skb_reset_mac_header(nskb); + skb_set_network_header(nskb, skb_network_offset(skb)); + skb_set_transport_header(nskb, skb_transport_offset(skb)); + memcpy(nskb->data, skb->data, headln); + memcpy(nskb->data + headln, &rcd_sn, sizeof(rcd_sn)); + + iph = ip_hdr(nskb); + iph->tot_len = htons(nskb->len - skb_network_offset(nskb)); + th = tcp_hdr(nskb); + data_len = nskb->len - headln; + tcp_seq -= data_len; + th->seq = htonl(tcp_seq); + + mss = nskb->dev->mtu - (headln - skb_network_offset(nskb)); + skb_shinfo(nskb)->gso_size = 0; + if (data_len > mss) { + skb_shinfo(nskb)->gso_size = mss; + skb_shinfo(nskb)->gso_segs = DIV_ROUND_UP(data_len, mss); + } + skb_shinfo(nskb)->gso_type = skb_shinfo(skb)->gso_type; + + pet = (struct mlx5e_tls_metadata *)(nskb->data + sizeof(struct ethhdr)); + memcpy(pet, &syndrome, sizeof(syndrome)); + pet->first_seq = htons(tcp_seq); + + /* MLX5 devices don't care about the checksum partial start, offset + * and pseudo header + */ + nskb->ip_summed = CHECKSUM_PARTIAL; + + nskb->xmit_more = 1; + nskb->queue_mapping = skb->queue_mapping; +} + +static struct sk_buff * +mlx5e_tls_handle_ooo(struct mlx5e_tls_offload_context *context, + struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi, + struct mlx5e_tls *tls) +{ + u32 tcp_seq = ntohl(tcp_hdr(skb)->seq); + struct sync_info info; + struct sk_buff *nskb; + int linear_len = 0; + int headln; + int i; + + sq->stats.tls_ooo++; + + if (mlx5e_tls_get_sync_data(context, tcp_seq, &info)) { + /* We might get here if a retransmission reaches the driver + * after the relevant record is acked. + * It should be safe to drop the packet in this case + */ + atomic64_inc(&tls->sw_stats.tx_tls_drop_no_sync_data); + goto err_out; + } + + if (unlikely(info.sync_len < 0)) { + u32 payload; + + headln = skb_transport_offset(skb) + tcp_hdrlen(skb); + payload = skb->len - headln; + if (likely(payload <= -info.sync_len)) + /* SKB payload doesn't require offload + */ + return skb; + + atomic64_inc(&tls->sw_stats.tx_tls_drop_bypass_required); + goto err_out; + } + + if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) { + atomic64_inc(&tls->sw_stats.tx_tls_drop_metadata); + goto err_out; + } + + headln = skb_transport_offset(skb) + tcp_hdrlen(skb); + linear_len += headln + sizeof(info.rcd_sn); + nskb = alloc_skb(linear_len, GFP_ATOMIC); + if (unlikely(!nskb)) { + atomic64_inc(&tls->sw_stats.tx_tls_drop_resync_alloc); + goto err_out; + } + + context->expected_seq = tcp_seq + skb->len - headln; + skb_put(nskb, linear_len); + for (i = 0; i < info.nr_frags; i++) + skb_shinfo(nskb)->frags[i] = info.frags[i]; + + skb_shinfo(nskb)->nr_frags = info.nr_frags; + nskb->data_len = info.sync_len; + nskb->len += info.sync_len; + sq->stats.tls_resync_bytes += nskb->len; + mlx5e_tls_complete_sync_skb(skb, nskb, tcp_seq, headln, + cpu_to_be64(info.rcd_sn)); + mlx5e_sq_xmit(sq, nskb, *wqe, *pi); + mlx5e_sq_fetch_wqe(sq, wqe, pi); + return skb; + +err_out: + dev_kfree_skb_any(skb); + return NULL; +} + +struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev, + struct mlx5e_txqsq *sq, + struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi) +{ + struct mlx5e_priv *priv = netdev_priv(netdev); + struct mlx5e_tls_offload_context *context; + struct tls_context *tls_ctx; + u32 expected_seq; + int datalen; + u32 skb_seq; + + if (!skb->sk || !tls_is_sk_tx_device_offloaded(skb->sk)) + goto out; + + datalen = skb->len - (skb_transport_offset(skb) + tcp_hdrlen(skb)); + if (!datalen) + goto out; + + tls_ctx = tls_get_ctx(skb->sk); + if (unlikely(tls_ctx->netdev != netdev)) + goto out; + + skb_seq = ntohl(tcp_hdr(skb)->seq); + context = mlx5e_get_tls_tx_context(tls_ctx); + expected_seq = context->expected_seq; + + if (unlikely(expected_seq != skb_seq)) { + skb = mlx5e_tls_handle_ooo(context, sq, skb, wqe, pi, priv->tls); + goto out; + } + + if (unlikely(mlx5e_tls_add_metadata(skb, context->swid))) { + atomic64_inc(&priv->tls->sw_stats.tx_tls_drop_metadata); + dev_kfree_skb_any(skb); + skb = NULL; + goto out; + } + + context->expected_seq = skb_seq + datalen; +out: + return skb; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h new file mode 100644 index 000000000000..405dfd302225 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_rxtx.h @@ -0,0 +1,50 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5E_TLS_RXTX_H__ +#define __MLX5E_TLS_RXTX_H__ + +#ifdef CONFIG_MLX5_EN_TLS + +#include <linux/skbuff.h> +#include "en.h" + +struct sk_buff *mlx5e_tls_handle_tx_skb(struct net_device *netdev, + struct mlx5e_txqsq *sq, + struct sk_buff *skb, + struct mlx5e_tx_wqe **wqe, + u16 *pi); + +#endif /* CONFIG_MLX5_EN_TLS */ + +#endif /* __MLX5E_TLS_RXTX_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c new file mode 100644 index 000000000000..01468ec27446 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_accel/tls_stats.c @@ -0,0 +1,89 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/ethtool.h> +#include <net/sock.h> + +#include "en.h" +#include "accel/tls.h" +#include "fpga/sdk.h" +#include "en_accel/tls.h" + +static const struct counter_desc mlx5e_tls_sw_stats_desc[] = { + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_metadata) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_resync_alloc) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_no_sync_data) }, + { MLX5E_DECLARE_STAT(struct mlx5e_tls_sw_stats, tx_tls_drop_bypass_required) }, +}; + +#define MLX5E_READ_CTR_ATOMIC64(ptr, dsc, i) \ + atomic64_read((atomic64_t *)((char *)(ptr) + (dsc)[i].offset)) + +#define NUM_TLS_SW_COUNTERS ARRAY_SIZE(mlx5e_tls_sw_stats_desc) + +int mlx5e_tls_get_count(struct mlx5e_priv *priv) +{ + if (!priv->tls) + return 0; + + return NUM_TLS_SW_COUNTERS; +} + +int mlx5e_tls_get_strings(struct mlx5e_priv *priv, uint8_t *data) +{ + unsigned int i, idx = 0; + + if (!priv->tls) + return 0; + + for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + strcpy(data + (idx++) * ETH_GSTRING_LEN, + mlx5e_tls_sw_stats_desc[i].format); + + return NUM_TLS_SW_COUNTERS; +} + +int mlx5e_tls_get_stats(struct mlx5e_priv *priv, u64 *data) +{ + int i, idx = 0; + + if (!priv->tls) + return 0; + + for (i = 0; i < NUM_TLS_SW_COUNTERS; i++) + data[idx++] = + MLX5E_READ_CTR_ATOMIC64(&priv->tls->sw_stats, + mlx5e_tls_sw_stats_desc, i); + + return NUM_TLS_SW_COUNTERS; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c index 610d485c4b03..f64b5e78519b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_arfs.c @@ -565,7 +565,7 @@ static void arfs_modify_rule_rq(struct mlx5e_priv *priv, err = mlx5_modify_rule_destination(rule, &dst, NULL); if (err) netdev_warn(priv->netdev, - "Failed to modfiy aRFS rule destination to rq=%d\n", rxq); + "Failed to modify aRFS rule destination to rq=%d\n", rxq); } static void arfs_handle_work(struct work_struct *work) diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c index 602851ab5b14..d67adf70a97b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_dim.c @@ -33,16 +33,30 @@ #include <linux/net_dim.h> #include "en.h" +static void +mlx5e_complete_dim_work(struct net_dim *dim, struct net_dim_cq_moder moder, + struct mlx5_core_dev *mdev, struct mlx5_core_cq *mcq) +{ + mlx5_core_modify_cq_moderation(mdev, mcq, moder.usec, moder.pkts); + dim->state = NET_DIM_START_MEASURE; +} + void mlx5e_rx_dim_work(struct work_struct *work) { - struct net_dim *dim = container_of(work, struct net_dim, - work); + struct net_dim *dim = container_of(work, struct net_dim, work); struct mlx5e_rq *rq = container_of(dim, struct mlx5e_rq, dim); - struct net_dim_cq_moder cur_profile = net_dim_get_profile(dim->mode, - dim->profile_ix); + struct net_dim_cq_moder cur_moder = + net_dim_get_rx_moderation(dim->mode, dim->profile_ix); - mlx5_core_modify_cq_moderation(rq->mdev, &rq->cq.mcq, - cur_profile.usec, cur_profile.pkts); + mlx5e_complete_dim_work(dim, cur_moder, rq->mdev, &rq->cq.mcq); +} - dim->state = NET_DIM_START_MEASURE; +void mlx5e_tx_dim_work(struct work_struct *work) +{ + struct net_dim *dim = container_of(work, struct net_dim, work); + struct mlx5e_txqsq *sq = container_of(dim, struct mlx5e_txqsq, dim); + struct net_dim_cq_moder cur_moder = + net_dim_get_tx_moderation(dim->mode, dim->profile_ix); + + mlx5e_complete_dim_work(dim, cur_moder, sq->cq.mdev, &sq->cq.mcq); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c index 37fd0245b6c1..2b786c4d3dab 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_ethtool.c @@ -389,14 +389,20 @@ static int mlx5e_set_channels(struct net_device *dev, int mlx5e_ethtool_get_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { + struct net_dim_cq_moder *rx_moder, *tx_moder; + if (!MLX5_CAP_GEN(priv->mdev, cq_moderation)) return -EOPNOTSUPP; - coal->rx_coalesce_usecs = priv->channels.params.rx_cq_moderation.usec; - coal->rx_max_coalesced_frames = priv->channels.params.rx_cq_moderation.pkts; - coal->tx_coalesce_usecs = priv->channels.params.tx_cq_moderation.usec; - coal->tx_max_coalesced_frames = priv->channels.params.tx_cq_moderation.pkts; - coal->use_adaptive_rx_coalesce = priv->channels.params.rx_dim_enabled; + rx_moder = &priv->channels.params.rx_cq_moderation; + coal->rx_coalesce_usecs = rx_moder->usec; + coal->rx_max_coalesced_frames = rx_moder->pkts; + coal->use_adaptive_rx_coalesce = priv->channels.params.rx_dim_enabled; + + tx_moder = &priv->channels.params.tx_cq_moderation; + coal->tx_coalesce_usecs = tx_moder->usec; + coal->tx_max_coalesced_frames = tx_moder->pkts; + coal->use_adaptive_tx_coalesce = priv->channels.params.tx_dim_enabled; return 0; } @@ -438,6 +444,7 @@ mlx5e_set_priv_channels_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesc int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, struct ethtool_coalesce *coal) { + struct net_dim_cq_moder *rx_moder, *tx_moder; struct mlx5_core_dev *mdev = priv->mdev; struct mlx5e_channels new_channels = {}; int err = 0; @@ -463,11 +470,15 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, mutex_lock(&priv->state_lock); new_channels.params = priv->channels.params; - new_channels.params.tx_cq_moderation.usec = coal->tx_coalesce_usecs; - new_channels.params.tx_cq_moderation.pkts = coal->tx_max_coalesced_frames; - new_channels.params.rx_cq_moderation.usec = coal->rx_coalesce_usecs; - new_channels.params.rx_cq_moderation.pkts = coal->rx_max_coalesced_frames; - new_channels.params.rx_dim_enabled = !!coal->use_adaptive_rx_coalesce; + rx_moder = &new_channels.params.rx_cq_moderation; + rx_moder->usec = coal->rx_coalesce_usecs; + rx_moder->pkts = coal->rx_max_coalesced_frames; + new_channels.params.rx_dim_enabled = !!coal->use_adaptive_rx_coalesce; + + tx_moder = &new_channels.params.tx_cq_moderation; + tx_moder->usec = coal->tx_coalesce_usecs; + tx_moder->pkts = coal->tx_max_coalesced_frames; + new_channels.params.tx_dim_enabled = !!coal->use_adaptive_tx_coalesce; if (!test_bit(MLX5E_STATE_OPENED, &priv->state)) { priv->channels.params = new_channels.params; @@ -475,7 +486,9 @@ int mlx5e_ethtool_set_coalesce(struct mlx5e_priv *priv, } /* we are opened */ - reset = !!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled; + reset = (!!coal->use_adaptive_rx_coalesce != priv->channels.params.rx_dim_enabled) || + (!!coal->use_adaptive_tx_coalesce != priv->channels.params.tx_dim_enabled); + if (!reset) { mlx5e_set_priv_channels_coalesce(priv, coal); priv->channels.params = new_channels.params; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c index b29c1d93f058..0f2b66b41899 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_main.c @@ -35,13 +35,16 @@ #include <linux/mlx5/fs.h> #include <net/vxlan.h> #include <linux/bpf.h> +#include <net/page_pool.h> #include "eswitch.h" #include "en.h" #include "en_tc.h" #include "en_rep.h" #include "en_accel/ipsec.h" #include "en_accel/ipsec_rxtx.h" +#include "en_accel/tls.h" #include "accel/ipsec.h" +#include "accel/tls.h" #include "vxlan.h" struct mlx5e_rq_param { @@ -389,10 +392,11 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, struct mlx5e_rq_param *rqp, struct mlx5e_rq *rq) { + struct page_pool_params pp_params = { 0 }; struct mlx5_core_dev *mdev = c->mdev; void *rqc = rqp->rqc; void *rqc_wq = MLX5_ADDR_OF(rqc, rqc, wq); - u32 byte_count; + u32 byte_count, pool_size; int npages; int wq_sz; int err; @@ -432,9 +436,12 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->buff.map_dir = rq->xdp_prog ? DMA_BIDIRECTIONAL : DMA_FROM_DEVICE; rq->buff.headroom = mlx5e_get_rq_headroom(mdev, params); + pool_size = 1 << params->log_rq_mtu_frames; switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: + + pool_size = MLX5_MPWRQ_PAGES_PER_WQE << mlx5e_mpwqe_get_log_rq_size(params); rq->post_wqes = mlx5e_post_rx_mpwqes; rq->dealloc_wqe = mlx5e_dealloc_rx_mpwqe; @@ -512,6 +519,32 @@ static int mlx5e_alloc_rq(struct mlx5e_channel *c, rq->mkey_be = c->mkey_be; } + /* Create a page_pool and register it with rxq */ + pp_params.order = rq->buff.page_order; + pp_params.flags = 0; /* No-internal DMA mapping in page_pool */ + pp_params.pool_size = pool_size; + pp_params.nid = cpu_to_node(c->cpu); + pp_params.dev = c->pdev; + pp_params.dma_dir = rq->buff.map_dir; + + /* page_pool can be used even when there is no rq->xdp_prog, + * given page_pool does not handle DMA mapping there is no + * required state to clear. And page_pool gracefully handle + * elevated refcnt. + */ + rq->page_pool = page_pool_create(&pp_params); + if (IS_ERR(rq->page_pool)) { + if (rq->wq_type != MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ) + kfree(rq->wqe.frag_info); + err = PTR_ERR(rq->page_pool); + rq->page_pool = NULL; + goto err_rq_wq_destroy; + } + err = xdp_rxq_info_reg_mem_model(&rq->xdp_rxq, + MEM_TYPE_PAGE_POOL, rq->page_pool); + if (err) + goto err_rq_wq_destroy; + for (i = 0; i < wq_sz; i++) { struct mlx5e_rx_wqe *wqe = mlx5_wq_ll_get_wqe(&rq->wq, i); @@ -548,6 +581,8 @@ err_rq_wq_destroy: if (rq->xdp_prog) bpf_prog_put(rq->xdp_prog); xdp_rxq_info_unreg(&rq->xdp_rxq); + if (rq->page_pool) + page_pool_destroy(rq->page_pool); mlx5_wq_destroy(&rq->wq_ctrl); return err; @@ -561,6 +596,8 @@ static void mlx5e_free_rq(struct mlx5e_rq *rq) bpf_prog_put(rq->xdp_prog); xdp_rxq_info_unreg(&rq->xdp_rxq); + if (rq->page_pool) + page_pool_destroy(rq->page_pool); switch (rq->wq_type) { case MLX5_WQ_TYPE_LINKED_LIST_STRIDING_RQ: @@ -979,6 +1016,8 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, INIT_WORK(&sq->recover.recover_work, mlx5e_sq_recover); if (MLX5_IPSEC_DEV(c->priv->mdev)) set_bit(MLX5E_SQ_STATE_IPSEC, &sq->state); + if (mlx5_accel_is_tls_device(c->priv->mdev)) + set_bit(MLX5E_SQ_STATE_TLS, &sq->state); param->wq.db_numa_node = cpu_to_node(c->cpu); err = mlx5_wq_cyc_create(mdev, ¶m->wq, sqc_wq, &sq->wq, &sq->wq_ctrl); @@ -990,6 +1029,9 @@ static int mlx5e_alloc_txqsq(struct mlx5e_channel *c, if (err) goto err_sq_wq_destroy; + INIT_WORK(&sq->dim.work, mlx5e_tx_dim_work); + sq->dim.mode = params->tx_cq_moderation.cq_period_mode; + sq->edge = (sq->wq.sz_m1 + 1) - MLX5_SEND_WQE_MAX_WQEBBS; return 0; @@ -1153,6 +1195,9 @@ static int mlx5e_open_txqsq(struct mlx5e_channel *c, if (tx_rate) mlx5e_set_sq_maxrate(c->netdev, sq, tx_rate); + if (params->tx_dim_enabled) + sq->state |= BIT(MLX5E_SQ_STATE_AM); + return 0; err_free_txqsq: @@ -1896,7 +1941,6 @@ static void mlx5e_build_rq_param(struct mlx5e_priv *priv, MLX5_SET(rqc, rqc, scatter_fcs, params->scatter_fcs_en); param->wq.buf_numa_node = dev_to_node(&mdev->pdev->dev); - param->wq.linear = 1; } static void mlx5e_build_drop_rq_param(struct mlx5e_priv *priv, @@ -4049,18 +4093,48 @@ static bool slow_pci_heuristic(struct mlx5_core_dev *mdev) link_speed > MLX5E_SLOW_PCI_RATIO * pci_bw; } -void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +static struct net_dim_cq_moder mlx5e_get_def_tx_moderation(u8 cq_period_mode) { - params->tx_cq_moderation.cq_period_mode = cq_period_mode; + struct net_dim_cq_moder moder; - params->tx_cq_moderation.pkts = - MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS; - params->tx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC; + moder.cq_period_mode = cq_period_mode; + moder.pkts = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_PKTS; + moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC; + if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE) + moder.usec = MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE; + + return moder; +} +static struct net_dim_cq_moder mlx5e_get_def_rx_moderation(u8 cq_period_mode) +{ + struct net_dim_cq_moder moder; + + moder.cq_period_mode = cq_period_mode; + moder.pkts = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS; + moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC; if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE) - params->tx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_TX_CQ_MODERATION_USEC_FROM_CQE; + moder.usec = MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE; + + return moder; +} + +static u8 mlx5_to_net_dim_cq_period_mode(u8 cq_period_mode) +{ + return cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE ? + NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE : + NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE; +} + +void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) +{ + if (params->tx_dim_enabled) { + u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode); + + params->tx_cq_moderation = net_dim_get_def_tx_moderation(dim_period_mode); + } else { + params->tx_cq_moderation = mlx5e_get_def_tx_moderation(cq_period_mode); + } MLX5E_SET_PFLAG(params, MLX5E_PFLAG_TX_CQE_BASED_MODER, params->tx_cq_moderation.cq_period_mode == @@ -4069,28 +4143,12 @@ void mlx5e_set_tx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) void mlx5e_set_rx_cq_mode_params(struct mlx5e_params *params, u8 cq_period_mode) { - params->rx_cq_moderation.cq_period_mode = cq_period_mode; - - params->rx_cq_moderation.pkts = - MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_PKTS; - params->rx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC; - - if (cq_period_mode == MLX5_CQ_PERIOD_MODE_START_FROM_CQE) - params->rx_cq_moderation.usec = - MLX5E_PARAMS_DEFAULT_RX_CQ_MODERATION_USEC_FROM_CQE; - if (params->rx_dim_enabled) { - switch (cq_period_mode) { - case MLX5_CQ_PERIOD_MODE_START_FROM_CQE: - params->rx_cq_moderation = - net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE); - break; - case MLX5_CQ_PERIOD_MODE_START_FROM_EQE: - default: - params->rx_cq_moderation = - net_dim_get_def_profile(NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE); - } + u8 dim_period_mode = mlx5_to_net_dim_cq_period_mode(cq_period_mode); + + params->rx_cq_moderation = net_dim_get_def_rx_moderation(dim_period_mode); + } else { + params->rx_cq_moderation = mlx5e_get_def_rx_moderation(cq_period_mode); } MLX5E_SET_PFLAG(params, MLX5E_PFLAG_RX_CQE_BASED_MODER, @@ -4154,6 +4212,7 @@ void mlx5e_build_nic_params(struct mlx5_core_dev *mdev, MLX5_CQ_PERIOD_MODE_START_FROM_CQE : MLX5_CQ_PERIOD_MODE_START_FROM_EQE; params->rx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); + params->tx_dim_enabled = MLX5_CAP_GEN(mdev, cq_moderation); mlx5e_set_rx_cq_mode_params(params, rx_cq_period_mode); mlx5e_set_tx_cq_mode_params(params, MLX5_CQ_PERIOD_MODE_START_FROM_EQE); @@ -4320,6 +4379,7 @@ static void mlx5e_build_nic_netdev(struct net_device *netdev) #endif mlx5e_ipsec_build_netdev(priv); + mlx5e_tls_build_netdev(priv); } static void mlx5e_create_q_counters(struct mlx5e_priv *priv) @@ -4361,12 +4421,16 @@ static void mlx5e_nic_init(struct mlx5_core_dev *mdev, err = mlx5e_ipsec_init(priv); if (err) mlx5_core_err(mdev, "IPSec initialization failed, %d\n", err); + err = mlx5e_tls_init(priv); + if (err) + mlx5_core_err(mdev, "TLS initialization failed, %d\n", err); mlx5e_build_nic_netdev(netdev); mlx5e_vxlan_init(priv); } static void mlx5e_nic_cleanup(struct mlx5e_priv *priv) { + mlx5e_tls_cleanup(priv); mlx5e_ipsec_cleanup(priv); mlx5e_vxlan_cleanup(priv); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c index 176645762e49..7bbf0db27a01 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_rx.c @@ -37,6 +37,7 @@ #include <linux/bpf_trace.h> #include <net/busy_poll.h> #include <net/ip6_checksum.h> +#include <net/page_pool.h> #include "en.h" #include "en_tc.h" #include "eswitch.h" @@ -221,7 +222,7 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, if (mlx5e_rx_cache_get(rq, dma_info)) return 0; - dma_info->page = dev_alloc_pages(rq->buff.page_order); + dma_info->page = page_pool_dev_alloc_pages(rq->page_pool); if (unlikely(!dma_info->page)) return -ENOMEM; @@ -236,15 +237,26 @@ static inline int mlx5e_page_alloc_mapped(struct mlx5e_rq *rq, return 0; } +static void mlx5e_page_dma_unmap(struct mlx5e_rq *rq, + struct mlx5e_dma_info *dma_info) +{ + dma_unmap_page(rq->pdev, dma_info->addr, RQ_PAGE_SIZE(rq), + rq->buff.map_dir); +} + void mlx5e_page_release(struct mlx5e_rq *rq, struct mlx5e_dma_info *dma_info, bool recycle) { - if (likely(recycle) && mlx5e_rx_cache_put(rq, dma_info)) - return; + if (likely(recycle)) { + if (mlx5e_rx_cache_put(rq, dma_info)) + return; - dma_unmap_page(rq->pdev, dma_info->addr, RQ_PAGE_SIZE(rq), - rq->buff.map_dir); - put_page(dma_info->page); + mlx5e_page_dma_unmap(rq, dma_info); + page_pool_recycle_direct(rq->page_pool, dma_info->page); + } else { + mlx5e_page_dma_unmap(rq, dma_info); + put_page(dma_info->page); + } } static inline bool mlx5e_page_reuse(struct mlx5e_rq *rq, @@ -800,9 +812,10 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, struct mlx5e_dma_info *di, void *va, u16 *rx_headroom, u32 *len) { - const struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); + struct bpf_prog *prog = READ_ONCE(rq->xdp_prog); struct xdp_buff xdp; u32 act; + int err; if (!prog) return false; @@ -823,6 +836,15 @@ static inline int mlx5e_xdp_handle(struct mlx5e_rq *rq, if (unlikely(!mlx5e_xmit_xdp_frame(rq, di, &xdp))) trace_xdp_exception(rq->netdev, prog, act); return true; + case XDP_REDIRECT: + /* When XDP enabled then page-refcnt==1 here */ + err = xdp_do_redirect(rq->netdev, &xdp, prog); + if (!err) { + __set_bit(MLX5E_RQ_FLAG_XDP_XMIT, rq->flags); + rq->xdpsq.db.redirect_flush = true; + mlx5e_page_dma_unmap(rq, di); + } + return true; default: bpf_warn_invalid_xdp_action(act); case XDP_ABORTED: @@ -868,6 +890,7 @@ struct sk_buff *skb_from_cqe(struct mlx5e_rq *rq, struct mlx5_cqe64 *cqe, dma_sync_single_range_for_cpu(rq->pdev, di->addr, wi->offset, frag_size, DMA_FROM_DEVICE); + prefetchw(va); /* xdp_frame data area */ prefetch(data); wi->offset += frag_size; @@ -1140,6 +1163,11 @@ int mlx5e_poll_rx_cq(struct mlx5e_cq *cq, int budget) xdpsq->db.doorbell = false; } + if (xdpsq->db.redirect_flush) { + xdp_do_flush_map(); + xdpsq->db.redirect_flush = false; + } + mlx5_cqwq_update_db_record(&cq->wq); /* ensure cq space is freed before enabling more cqes */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c index b08c94422907..e17919c0af08 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.c @@ -32,6 +32,7 @@ #include "en.h" #include "en_accel/ipsec.h" +#include "en_accel/tls.h" static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_packets) }, @@ -43,6 +44,12 @@ static const struct counter_desc sw_stats_desc[] = { { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tso_inner_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_added_vlan_packets) }, + +#ifdef CONFIG_MLX5_EN_TLS + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_ooo) }, + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, tx_tls_resync_bytes) }, +#endif + { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_packets) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_lro_bytes) }, { MLX5E_DECLARE_STAT(struct mlx5e_sw_stats, rx_removed_vlan_packets) }, @@ -161,6 +168,10 @@ static void mlx5e_grp_sw_update_stats(struct mlx5e_priv *priv) s->tx_csum_partial_inner += sq_stats->csum_partial_inner; s->tx_csum_none += sq_stats->csum_none; s->tx_csum_partial += sq_stats->csum_partial; +#ifdef CONFIG_MLX5_EN_TLS + s->tx_tls_ooo += sq_stats->tls_ooo; + s->tx_tls_resync_bytes += sq_stats->tls_resync_bytes; +#endif } } @@ -1065,6 +1076,22 @@ static void mlx5e_grp_ipsec_update_stats(struct mlx5e_priv *priv) mlx5e_ipsec_update_stats(priv); } +static int mlx5e_grp_tls_get_num_stats(struct mlx5e_priv *priv) +{ + return mlx5e_tls_get_count(priv); +} + +static int mlx5e_grp_tls_fill_strings(struct mlx5e_priv *priv, u8 *data, + int idx) +{ + return idx + mlx5e_tls_get_strings(priv, data + idx * ETH_GSTRING_LEN); +} + +static int mlx5e_grp_tls_fill_stats(struct mlx5e_priv *priv, u64 *data, int idx) +{ + return idx + mlx5e_tls_get_stats(priv, data + idx); +} + static const struct counter_desc rq_stats_desc[] = { { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, packets) }, { MLX5E_DECLARE_RX_STAT(struct mlx5e_rq_stats, bytes) }, @@ -1268,6 +1295,11 @@ const struct mlx5e_stats_grp mlx5e_stats_grps[] = { .update_stats = mlx5e_grp_ipsec_update_stats, }, { + .get_num_stats = mlx5e_grp_tls_get_num_stats, + .fill_strings = mlx5e_grp_tls_fill_strings, + .fill_stats = mlx5e_grp_tls_fill_stats, + }, + { .get_num_stats = mlx5e_grp_channels_get_num_stats, .fill_strings = mlx5e_grp_channels_fill_strings, .fill_stats = mlx5e_grp_channels_fill_stats, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h index 53111a2df587..a36e6a87066b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_stats.h @@ -93,6 +93,11 @@ struct mlx5e_sw_stats { u64 rx_cache_waive; u64 ch_eq_rearm; +#ifdef CONFIG_MLX5_EN_TLS + u64 tx_tls_ooo; + u64 tx_tls_resync_bytes; +#endif + /* Special handling counters */ u64 link_down_events_phy; }; @@ -194,6 +199,10 @@ struct mlx5e_sq_stats { u64 csum_partial_inner; u64 added_vlan_packets; u64 nop; +#ifdef CONFIG_MLX5_EN_TLS + u64 tls_ooo; + u64 tls_resync_bytes; +#endif /* less likely accessed in data path */ u64 csum_none; u64 stopped; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c index 5532aa3675c7..047614d2eda2 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_tx.c @@ -35,12 +35,21 @@ #include <net/dsfield.h> #include "en.h" #include "ipoib/ipoib.h" -#include "en_accel/ipsec_rxtx.h" +#include "en_accel/en_accel.h" #include "lib/clock.h" #define MLX5E_SQ_NOPS_ROOM MLX5_SEND_WQE_MAX_WQEBBS + +#ifndef CONFIG_MLX5_EN_TLS #define MLX5E_SQ_STOP_ROOM (MLX5_SEND_WQE_MAX_WQEBBS +\ MLX5E_SQ_NOPS_ROOM) +#else +/* TLS offload requires MLX5E_SQ_STOP_ROOM to have + * enough room for a resync SKB, a normal SKB and a NOP + */ +#define MLX5E_SQ_STOP_ROOM (2 * MLX5_SEND_WQE_MAX_WQEBBS +\ + MLX5E_SQ_NOPS_ROOM) +#endif static inline void mlx5e_tx_dma_unmap(struct device *pdev, struct mlx5e_sq_dma *dma) @@ -329,8 +338,8 @@ mlx5e_txwqe_complete(struct mlx5e_txqsq *sq, struct sk_buff *skb, } } -static netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, - struct mlx5e_tx_wqe *wqe, u16 pi) +netdev_tx_t mlx5e_sq_xmit(struct mlx5e_txqsq *sq, struct sk_buff *skb, + struct mlx5e_tx_wqe *wqe, u16 pi) { struct mlx5e_tx_wqe_info *wi = &sq->db.wqe_info[pi]; @@ -401,21 +410,19 @@ err_drop: netdev_tx_t mlx5e_xmit(struct sk_buff *skb, struct net_device *dev) { struct mlx5e_priv *priv = netdev_priv(dev); - struct mlx5e_txqsq *sq = priv->txq2sq[skb_get_queue_mapping(skb)]; - struct mlx5_wq_cyc *wq = &sq->wq; - u16 pi = sq->pc & wq->sz_m1; - struct mlx5e_tx_wqe *wqe = mlx5_wq_cyc_get_wqe(wq, pi); + struct mlx5e_tx_wqe *wqe; + struct mlx5e_txqsq *sq; + u16 pi; - memset(wqe, 0, sizeof(*wqe)); + sq = priv->txq2sq[skb_get_queue_mapping(skb)]; + mlx5e_sq_fetch_wqe(sq, &wqe, &pi); -#ifdef CONFIG_MLX5_EN_IPSEC - if (sq->state & BIT(MLX5E_SQ_STATE_IPSEC)) { - skb = mlx5e_ipsec_handle_tx_skb(dev, wqe, skb); - if (unlikely(!skb)) - return NETDEV_TX_OK; - } +#ifdef CONFIG_MLX5_ACCEL + /* might send skbs and update wqe and pi */ + skb = mlx5e_accel_handle_tx(skb, sq, dev, &wqe, &pi); + if (unlikely(!skb)) + return NETDEV_TX_OK; #endif - return mlx5e_sq_xmit(sq, skb, wqe, pi); } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c index f292bb346985..900661d45c8a 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/en_txrx.c @@ -44,6 +44,30 @@ static inline bool mlx5e_channel_no_affinity_change(struct mlx5e_channel *c) return cpumask_test_cpu(current_cpu, aff); } +static void mlx5e_handle_tx_dim(struct mlx5e_txqsq *sq) +{ + struct net_dim_sample dim_sample; + + if (unlikely(!MLX5E_TEST_BIT(sq->state, MLX5E_SQ_STATE_AM))) + return; + + net_dim_sample(sq->cq.event_ctr, sq->stats.packets, sq->stats.bytes, + &dim_sample); + net_dim(&sq->dim, dim_sample); +} + +static void mlx5e_handle_rx_dim(struct mlx5e_rq *rq) +{ + struct net_dim_sample dim_sample; + + if (unlikely(!MLX5E_TEST_BIT(rq->state, MLX5E_RQ_STATE_AM))) + return; + + net_dim_sample(rq->cq.event_ctr, rq->stats.packets, rq->stats.bytes, + &dim_sample); + net_dim(&rq->dim, dim_sample); +} + int mlx5e_napi_poll(struct napi_struct *napi, int budget) { struct mlx5e_channel *c = container_of(napi, struct mlx5e_channel, @@ -75,18 +99,13 @@ int mlx5e_napi_poll(struct napi_struct *napi, int budget) if (unlikely(!napi_complete_done(napi, work_done))) return work_done; - for (i = 0; i < c->num_tc; i++) + for (i = 0; i < c->num_tc; i++) { + mlx5e_handle_tx_dim(&c->sq[i]); mlx5e_cq_arm(&c->sq[i].cq); - - if (MLX5E_TEST_BIT(c->rq.state, MLX5E_RQ_STATE_AM)) { - struct net_dim_sample dim_sample; - net_dim_sample(c->rq.cq.event_ctr, - c->rq.stats.packets, - c->rq.stats.bytes, - &dim_sample); - net_dim(&c->rq.dim, dim_sample); } + mlx5e_handle_rx_dim(&c->rq); + mlx5e_cq_arm(&c->rq.cq); mlx5e_cq_arm(&c->icosq.cq); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h index 82405ed84725..3e2355c8df3f 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/core.h @@ -53,6 +53,7 @@ struct mlx5_fpga_device { } conn_res; struct mlx5_fpga_ipsec *ipsec; + struct mlx5_fpga_tls *tls; }; #define mlx5_fpga_dbg(__adev, format, ...) \ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c index 0f5da499a223..3c4f1f326e13 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/ipsec.c @@ -43,9 +43,6 @@ #include "fpga/sdk.h" #include "fpga/core.h" -#define SBU_QP_QUEUE_SIZE 8 -#define MLX5_FPGA_IPSEC_CMD_TIMEOUT_MSEC (60 * 1000) - enum mlx5_fpga_ipsec_cmd_status { MLX5_FPGA_IPSEC_CMD_PENDING, MLX5_FPGA_IPSEC_CMD_SEND_FAIL, @@ -258,7 +255,7 @@ static int mlx5_fpga_ipsec_cmd_wait(void *ctx) { struct mlx5_fpga_ipsec_cmd_context *context = ctx; unsigned long timeout = - msecs_to_jiffies(MLX5_FPGA_IPSEC_CMD_TIMEOUT_MSEC); + msecs_to_jiffies(MLX5_FPGA_CMD_TIMEOUT_MSEC); int res; res = wait_for_completion_timeout(&context->complete, timeout); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h index baa537e54a49..a0573cc2fc9b 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/sdk.h @@ -41,6 +41,8 @@ * DOC: Innova SDK * This header defines the in-kernel API for Innova FPGA client drivers. */ +#define SBU_QP_QUEUE_SIZE 8 +#define MLX5_FPGA_CMD_TIMEOUT_MSEC (60 * 1000) enum mlx5_fpga_access_type { MLX5_FPGA_ACCESS_TYPE_I2C = 0x0, diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c new file mode 100644 index 000000000000..21048013826c --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.c @@ -0,0 +1,562 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#include <linux/mlx5/device.h> +#include "fpga/tls.h" +#include "fpga/cmd.h" +#include "fpga/sdk.h" +#include "fpga/core.h" +#include "accel/tls.h" + +struct mlx5_fpga_tls_command_context; + +typedef void (*mlx5_fpga_tls_command_complete) + (struct mlx5_fpga_conn *conn, struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *ctx, + struct mlx5_fpga_dma_buf *resp); + +struct mlx5_fpga_tls_command_context { + struct list_head list; + /* There is no guarantee on the order between the TX completion + * and the command response. + * The TX completion is going to touch cmd->buf even in + * the case of successful transmission. + * So instead of requiring separate allocations for cmd + * and cmd->buf we've decided to use a reference counter + */ + refcount_t ref; + struct mlx5_fpga_dma_buf buf; + mlx5_fpga_tls_command_complete complete; +}; + +static void +mlx5_fpga_tls_put_command_ctx(struct mlx5_fpga_tls_command_context *ctx) +{ + if (refcount_dec_and_test(&ctx->ref)) + kfree(ctx); +} + +static void mlx5_fpga_tls_cmd_complete(struct mlx5_fpga_device *fdev, + struct mlx5_fpga_dma_buf *resp) +{ + struct mlx5_fpga_conn *conn = fdev->tls->conn; + struct mlx5_fpga_tls_command_context *ctx; + struct mlx5_fpga_tls *tls = fdev->tls; + unsigned long flags; + + spin_lock_irqsave(&tls->pending_cmds_lock, flags); + ctx = list_first_entry(&tls->pending_cmds, + struct mlx5_fpga_tls_command_context, list); + list_del(&ctx->list); + spin_unlock_irqrestore(&tls->pending_cmds_lock, flags); + ctx->complete(conn, fdev, ctx, resp); +} + +static void mlx5_fpga_cmd_send_complete(struct mlx5_fpga_conn *conn, + struct mlx5_fpga_device *fdev, + struct mlx5_fpga_dma_buf *buf, + u8 status) +{ + struct mlx5_fpga_tls_command_context *ctx = + container_of(buf, struct mlx5_fpga_tls_command_context, buf); + + mlx5_fpga_tls_put_command_ctx(ctx); + + if (unlikely(status)) + mlx5_fpga_tls_cmd_complete(fdev, NULL); +} + +static void mlx5_fpga_tls_cmd_send(struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *cmd, + mlx5_fpga_tls_command_complete complete) +{ + struct mlx5_fpga_tls *tls = fdev->tls; + unsigned long flags; + int ret; + + refcount_set(&cmd->ref, 2); + cmd->complete = complete; + cmd->buf.complete = mlx5_fpga_cmd_send_complete; + + spin_lock_irqsave(&tls->pending_cmds_lock, flags); + /* mlx5_fpga_sbu_conn_sendmsg is called under pending_cmds_lock + * to make sure commands are inserted to the tls->pending_cmds list + * and the command QP in the same order. + */ + ret = mlx5_fpga_sbu_conn_sendmsg(tls->conn, &cmd->buf); + if (likely(!ret)) + list_add_tail(&cmd->list, &tls->pending_cmds); + else + complete(tls->conn, fdev, cmd, NULL); + spin_unlock_irqrestore(&tls->pending_cmds_lock, flags); +} + +/* Start of context identifiers range (inclusive) */ +#define SWID_START 0 +/* End of context identifiers range (exclusive) */ +#define SWID_END BIT(24) + +static int mlx5_fpga_tls_alloc_swid(struct idr *idr, spinlock_t *idr_spinlock, + void *ptr) +{ + int ret; + + /* TLS metadata format is 1 byte for syndrome followed + * by 3 bytes of swid (software ID) + * swid must not exceed 3 bytes. + * See tls_rxtx.c:insert_pet() for details + */ + BUILD_BUG_ON((SWID_END - 1) & 0xFF000000); + + idr_preload(GFP_KERNEL); + spin_lock_irq(idr_spinlock); + ret = idr_alloc(idr, ptr, SWID_START, SWID_END, GFP_ATOMIC); + spin_unlock_irq(idr_spinlock); + idr_preload_end(); + + return ret; +} + +static void mlx5_fpga_tls_release_swid(struct idr *idr, + spinlock_t *idr_spinlock, u32 swid) +{ + unsigned long flags; + + spin_lock_irqsave(idr_spinlock, flags); + idr_remove(idr, swid); + spin_unlock_irqrestore(idr_spinlock, flags); +} + +struct mlx5_teardown_stream_context { + struct mlx5_fpga_tls_command_context cmd; + u32 swid; +}; + +static void +mlx5_fpga_tls_teardown_completion(struct mlx5_fpga_conn *conn, + struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *cmd, + struct mlx5_fpga_dma_buf *resp) +{ + struct mlx5_teardown_stream_context *ctx = + container_of(cmd, struct mlx5_teardown_stream_context, cmd); + + if (resp) { + u32 syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome); + + if (syndrome) + mlx5_fpga_err(fdev, + "Teardown stream failed with syndrome = %d", + syndrome); + else + mlx5_fpga_tls_release_swid(&fdev->tls->tx_idr, + &fdev->tls->idr_spinlock, + ctx->swid); + } + mlx5_fpga_tls_put_command_ctx(cmd); +} + +static void mlx5_fpga_tls_flow_to_cmd(void *flow, void *cmd) +{ + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, src_port), flow, + MLX5_BYTE_OFF(tls_flow, ipv6)); + + MLX5_SET(tls_cmd, cmd, ipv6, MLX5_GET(tls_flow, flow, ipv6)); + MLX5_SET(tls_cmd, cmd, direction_sx, + MLX5_GET(tls_flow, flow, direction_sx)); +} + +void mlx5_fpga_tls_send_teardown_cmd(struct mlx5_core_dev *mdev, void *flow, + u32 swid, gfp_t flags) +{ + struct mlx5_teardown_stream_context *ctx; + struct mlx5_fpga_dma_buf *buf; + void *cmd; + + ctx = kzalloc(sizeof(*ctx) + MLX5_TLS_COMMAND_SIZE, flags); + if (!ctx) + return; + + buf = &ctx->cmd.buf; + cmd = (ctx + 1); + MLX5_SET(tls_cmd, cmd, command_type, CMD_TEARDOWN_STREAM); + MLX5_SET(tls_cmd, cmd, swid, swid); + + mlx5_fpga_tls_flow_to_cmd(flow, cmd); + kfree(flow); + + buf->sg[0].data = cmd; + buf->sg[0].size = MLX5_TLS_COMMAND_SIZE; + + ctx->swid = swid; + mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd, + mlx5_fpga_tls_teardown_completion); +} + +void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid, + gfp_t flags) +{ + struct mlx5_fpga_tls *tls = mdev->fpga->tls; + void *flow; + + rcu_read_lock(); + flow = idr_find(&tls->tx_idr, swid); + rcu_read_unlock(); + + if (!flow) { + mlx5_fpga_err(mdev->fpga, "No flow information for swid %u\n", + swid); + return; + } + + mlx5_fpga_tls_send_teardown_cmd(mdev, flow, swid, flags); +} + +enum mlx5_fpga_setup_stream_status { + MLX5_FPGA_CMD_PENDING, + MLX5_FPGA_CMD_SEND_FAILED, + MLX5_FPGA_CMD_RESPONSE_RECEIVED, + MLX5_FPGA_CMD_ABANDONED, +}; + +struct mlx5_setup_stream_context { + struct mlx5_fpga_tls_command_context cmd; + atomic_t status; + u32 syndrome; + struct completion comp; +}; + +static void +mlx5_fpga_tls_setup_completion(struct mlx5_fpga_conn *conn, + struct mlx5_fpga_device *fdev, + struct mlx5_fpga_tls_command_context *cmd, + struct mlx5_fpga_dma_buf *resp) +{ + struct mlx5_setup_stream_context *ctx = + container_of(cmd, struct mlx5_setup_stream_context, cmd); + int status = MLX5_FPGA_CMD_SEND_FAILED; + void *tls_cmd = ctx + 1; + + /* If we failed to send to command resp == NULL */ + if (resp) { + ctx->syndrome = MLX5_GET(tls_resp, resp->sg[0].data, syndrome); + status = MLX5_FPGA_CMD_RESPONSE_RECEIVED; + } + + status = atomic_xchg_release(&ctx->status, status); + if (likely(status != MLX5_FPGA_CMD_ABANDONED)) { + complete(&ctx->comp); + return; + } + + mlx5_fpga_err(fdev, "Command was abandoned, syndrome = %u\n", + ctx->syndrome); + + if (!ctx->syndrome) { + /* The process was killed while waiting for the context to be + * added, and the add completed successfully. + * We need to destroy the HW context, and we can't can't reuse + * the command context because we might not have received + * the tx completion yet. + */ + mlx5_fpga_tls_del_tx_flow(fdev->mdev, + MLX5_GET(tls_cmd, tls_cmd, swid), + GFP_ATOMIC); + } + + mlx5_fpga_tls_put_command_ctx(cmd); +} + +static int mlx5_fpga_tls_setup_stream_cmd(struct mlx5_core_dev *mdev, + struct mlx5_setup_stream_context *ctx) +{ + struct mlx5_fpga_dma_buf *buf; + void *cmd = ctx + 1; + int status, ret = 0; + + buf = &ctx->cmd.buf; + buf->sg[0].data = cmd; + buf->sg[0].size = MLX5_TLS_COMMAND_SIZE; + MLX5_SET(tls_cmd, cmd, command_type, CMD_SETUP_STREAM); + + init_completion(&ctx->comp); + atomic_set(&ctx->status, MLX5_FPGA_CMD_PENDING); + ctx->syndrome = -1; + + mlx5_fpga_tls_cmd_send(mdev->fpga, &ctx->cmd, + mlx5_fpga_tls_setup_completion); + wait_for_completion_killable(&ctx->comp); + + status = atomic_xchg_acquire(&ctx->status, MLX5_FPGA_CMD_ABANDONED); + if (unlikely(status == MLX5_FPGA_CMD_PENDING)) + /* ctx is going to be released in mlx5_fpga_tls_setup_completion */ + return -EINTR; + + if (unlikely(ctx->syndrome)) + ret = -ENOMEM; + + mlx5_fpga_tls_put_command_ctx(&ctx->cmd); + return ret; +} + +static void mlx5_fpga_tls_hw_qp_recv_cb(void *cb_arg, + struct mlx5_fpga_dma_buf *buf) +{ + struct mlx5_fpga_device *fdev = (struct mlx5_fpga_device *)cb_arg; + + mlx5_fpga_tls_cmd_complete(fdev, buf); +} + +bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev) +{ + if (!mdev->fpga || !MLX5_CAP_GEN(mdev, fpga)) + return false; + + if (MLX5_CAP_FPGA(mdev, ieee_vendor_id) != + MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX) + return false; + + if (MLX5_CAP_FPGA(mdev, sandbox_product_id) != + MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS) + return false; + + if (MLX5_CAP_FPGA(mdev, sandbox_product_version) != 0) + return false; + + return true; +} + +static int mlx5_fpga_tls_get_caps(struct mlx5_fpga_device *fdev, + u32 *p_caps) +{ + int err, cap_size = MLX5_ST_SZ_BYTES(tls_extended_cap); + u32 caps = 0; + void *buf; + + buf = kzalloc(cap_size, GFP_KERNEL); + if (!buf) + return -ENOMEM; + + err = mlx5_fpga_get_sbu_caps(fdev, cap_size, buf); + if (err) + goto out; + + if (MLX5_GET(tls_extended_cap, buf, tx)) + caps |= MLX5_ACCEL_TLS_TX; + if (MLX5_GET(tls_extended_cap, buf, rx)) + caps |= MLX5_ACCEL_TLS_RX; + if (MLX5_GET(tls_extended_cap, buf, tls_v12)) + caps |= MLX5_ACCEL_TLS_V12; + if (MLX5_GET(tls_extended_cap, buf, tls_v13)) + caps |= MLX5_ACCEL_TLS_V13; + if (MLX5_GET(tls_extended_cap, buf, lro)) + caps |= MLX5_ACCEL_TLS_LRO; + if (MLX5_GET(tls_extended_cap, buf, ipv6)) + caps |= MLX5_ACCEL_TLS_IPV6; + + if (MLX5_GET(tls_extended_cap, buf, aes_gcm_128)) + caps |= MLX5_ACCEL_TLS_AES_GCM128; + if (MLX5_GET(tls_extended_cap, buf, aes_gcm_256)) + caps |= MLX5_ACCEL_TLS_AES_GCM256; + + *p_caps = caps; + err = 0; +out: + kfree(buf); + return err; +} + +int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev) +{ + struct mlx5_fpga_device *fdev = mdev->fpga; + struct mlx5_fpga_conn_attr init_attr = {0}; + struct mlx5_fpga_conn *conn; + struct mlx5_fpga_tls *tls; + int err = 0; + + if (!mlx5_fpga_is_tls_device(mdev) || !fdev) + return 0; + + tls = kzalloc(sizeof(*tls), GFP_KERNEL); + if (!tls) + return -ENOMEM; + + err = mlx5_fpga_tls_get_caps(fdev, &tls->caps); + if (err) + goto error; + + if (!(tls->caps & (MLX5_ACCEL_TLS_TX | MLX5_ACCEL_TLS_V12 | + MLX5_ACCEL_TLS_AES_GCM128))) { + err = -ENOTSUPP; + goto error; + } + + init_attr.rx_size = SBU_QP_QUEUE_SIZE; + init_attr.tx_size = SBU_QP_QUEUE_SIZE; + init_attr.recv_cb = mlx5_fpga_tls_hw_qp_recv_cb; + init_attr.cb_arg = fdev; + conn = mlx5_fpga_sbu_conn_create(fdev, &init_attr); + if (IS_ERR(conn)) { + err = PTR_ERR(conn); + mlx5_fpga_err(fdev, "Error creating TLS command connection %d\n", + err); + goto error; + } + + tls->conn = conn; + spin_lock_init(&tls->pending_cmds_lock); + INIT_LIST_HEAD(&tls->pending_cmds); + + idr_init(&tls->tx_idr); + spin_lock_init(&tls->idr_spinlock); + fdev->tls = tls; + return 0; + +error: + kfree(tls); + return err; +} + +void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev) +{ + struct mlx5_fpga_device *fdev = mdev->fpga; + + if (!fdev || !fdev->tls) + return; + + mlx5_fpga_sbu_conn_destroy(fdev->tls->conn); + kfree(fdev->tls); + fdev->tls = NULL; +} + +static void mlx5_fpga_tls_set_aes_gcm128_ctx(void *cmd, + struct tls_crypto_info *info, + __be64 *rcd_sn) +{ + struct tls12_crypto_info_aes_gcm_128 *crypto_info = + (struct tls12_crypto_info_aes_gcm_128 *)info; + + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_rcd_sn), crypto_info->rec_seq, + TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE); + + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, tls_implicit_iv), + crypto_info->salt, TLS_CIPHER_AES_GCM_128_SALT_SIZE); + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key), + crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); + + /* in AES-GCM 128 we need to write the key twice */ + memcpy(MLX5_ADDR_OF(tls_cmd, cmd, encryption_key) + + TLS_CIPHER_AES_GCM_128_KEY_SIZE, + crypto_info->key, TLS_CIPHER_AES_GCM_128_KEY_SIZE); + + MLX5_SET(tls_cmd, cmd, alg, MLX5_TLS_ALG_AES_GCM_128); +} + +static int mlx5_fpga_tls_set_key_material(void *cmd, u32 caps, + struct tls_crypto_info *crypto_info) +{ + __be64 rcd_sn; + + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: + if (!(caps & MLX5_ACCEL_TLS_AES_GCM128)) + return -EINVAL; + mlx5_fpga_tls_set_aes_gcm128_ctx(cmd, crypto_info, &rcd_sn); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int mlx5_fpga_tls_add_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, u32 swid, + u32 tcp_sn) +{ + u32 caps = mlx5_fpga_tls_device_caps(mdev); + struct mlx5_setup_stream_context *ctx; + int ret = -ENOMEM; + size_t cmd_size; + void *cmd; + + cmd_size = MLX5_TLS_COMMAND_SIZE + sizeof(*ctx); + ctx = kzalloc(cmd_size, GFP_KERNEL); + if (!ctx) + goto out; + + cmd = ctx + 1; + ret = mlx5_fpga_tls_set_key_material(cmd, caps, crypto_info); + if (ret) + goto free_ctx; + + mlx5_fpga_tls_flow_to_cmd(flow, cmd); + + MLX5_SET(tls_cmd, cmd, swid, swid); + MLX5_SET(tls_cmd, cmd, tcp_sn, tcp_sn); + + return mlx5_fpga_tls_setup_stream_cmd(mdev, ctx); + +free_ctx: + kfree(ctx); +out: + return ret; +} + +int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid) +{ + struct mlx5_fpga_tls *tls = mdev->fpga->tls; + int ret = -ENOMEM; + u32 swid; + + ret = mlx5_fpga_tls_alloc_swid(&tls->tx_idr, &tls->idr_spinlock, flow); + if (ret < 0) + return ret; + + swid = ret; + MLX5_SET(tls_flow, flow, direction_sx, 1); + + ret = mlx5_fpga_tls_add_flow(mdev, flow, crypto_info, swid, + start_offload_tcp_sn); + if (ret && ret != -EINTR) + goto free_swid; + + *p_swid = swid; + return 0; +free_swid: + mlx5_fpga_tls_release_swid(&tls->tx_idr, &tls->idr_spinlock, swid); + + return ret; +} diff --git a/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h new file mode 100644 index 000000000000..800a214e4e49 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlx5/core/fpga/tls.h @@ -0,0 +1,68 @@ +/* + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + * + */ + +#ifndef __MLX5_FPGA_TLS_H__ +#define __MLX5_FPGA_TLS_H__ + +#include <linux/mlx5/driver.h> + +#include <net/tls.h> +#include "fpga/core.h" + +struct mlx5_fpga_tls { + struct list_head pending_cmds; + spinlock_t pending_cmds_lock; /* Protects pending_cmds */ + u32 caps; + struct mlx5_fpga_conn *conn; + + struct idr tx_idr; + spinlock_t idr_spinlock; /* protects the IDR */ +}; + +int mlx5_fpga_tls_add_tx_flow(struct mlx5_core_dev *mdev, void *flow, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn, u32 *p_swid); + +void mlx5_fpga_tls_del_tx_flow(struct mlx5_core_dev *mdev, u32 swid, + gfp_t flags); + +bool mlx5_fpga_is_tls_device(struct mlx5_core_dev *mdev); +int mlx5_fpga_tls_init(struct mlx5_core_dev *mdev); +void mlx5_fpga_tls_cleanup(struct mlx5_core_dev *mdev); + +static inline u32 mlx5_fpga_tls_device_caps(struct mlx5_core_dev *mdev) +{ + return mdev->fpga->tls->caps; +} + +#endif /* __MLX5_FPGA_TLS_H__ */ diff --git a/drivers/net/ethernet/mellanox/mlx5/core/main.c b/drivers/net/ethernet/mellanox/mlx5/core/main.c index e2c465b0b3f8..615005e63819 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/main.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/main.c @@ -60,6 +60,7 @@ #include "fpga/core.h" #include "fpga/ipsec.h" #include "accel/ipsec.h" +#include "accel/tls.h" #include "lib/clock.h" MODULE_AUTHOR("Eli Cohen <eli@mellanox.com>"); @@ -1190,6 +1191,12 @@ static int mlx5_load_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, goto err_ipsec_start; } + err = mlx5_accel_tls_init(dev); + if (err) { + dev_err(&pdev->dev, "TLS device start failed %d\n", err); + goto err_tls_start; + } + err = mlx5_init_fs(dev); if (err) { dev_err(&pdev->dev, "Failed to init flow steering\n"); @@ -1231,6 +1238,9 @@ err_sriov: mlx5_cleanup_fs(dev); err_fs: + mlx5_accel_tls_cleanup(dev); + +err_tls_start: mlx5_accel_ipsec_cleanup(dev); err_ipsec_start: @@ -1306,6 +1316,7 @@ static int mlx5_unload_one(struct mlx5_core_dev *dev, struct mlx5_priv *priv, mlx5_sriov_detach(dev); mlx5_cleanup_fs(dev); mlx5_accel_ipsec_cleanup(dev); + mlx5_accel_tls_cleanup(dev); mlx5_fpga_device_stop(dev); mlx5_irq_clear_affinity_hints(dev); free_comp_eqs(dev); diff --git a/drivers/net/ethernet/mellanox/mlx5/core/mr.c b/drivers/net/ethernet/mellanox/mlx5/core/mr.c index b9736f505bdf..f4f02f775c93 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/mr.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/mr.c @@ -123,8 +123,8 @@ int mlx5_core_destroy_mkey(struct mlx5_core_dev *dev, deleted_mkey = radix_tree_delete(&table->tree, mlx5_base_mkey(mkey->key)); write_unlock_irqrestore(&table->lock, flags); if (!deleted_mkey) { - mlx5_core_warn(dev, "failed radix tree delete of mkey 0x%x\n", - mlx5_base_mkey(mkey->key)); + mlx5_core_dbg(dev, "failed radix tree delete of mkey 0x%x\n", + mlx5_base_mkey(mkey->key)); return -ENOENT; } diff --git a/drivers/net/ethernet/mellanox/mlx5/core/qp.c b/drivers/net/ethernet/mellanox/mlx5/core/qp.c index 02d6c5b5d502..4ca07bfb6b14 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/qp.c +++ b/drivers/net/ethernet/mellanox/mlx5/core/qp.c @@ -407,21 +407,21 @@ static int modify_qp_mbox_alloc(struct mlx5_core_dev *dev, u16 opcode, int qpn, case MLX5_CMD_OP_RST2INIT_QP: if (MBOX_ALLOC(mbox, rst2init_qp)) return -ENOMEM; - MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); - break; + MOD_QP_IN_SET_QPC(rst2init_qp, mbox->in, opcode, qpn, + opt_param_mask, qpc); + break; case MLX5_CMD_OP_INIT2RTR_QP: if (MBOX_ALLOC(mbox, init2rtr_qp)) return -ENOMEM; - MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); - break; + MOD_QP_IN_SET_QPC(init2rtr_qp, mbox->in, opcode, qpn, + opt_param_mask, qpc); + break; case MLX5_CMD_OP_RTR2RTS_QP: if (MBOX_ALLOC(mbox, rtr2rts_qp)) return -ENOMEM; - MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn, - opt_param_mask, qpc); - break; + MOD_QP_IN_SET_QPC(rtr2rts_qp, mbox->in, opcode, qpn, + opt_param_mask, qpc); + break; case MLX5_CMD_OP_RTS2RTS_QP: if (MBOX_ALLOC(mbox, rts2rts_qp)) return -ENOMEM; diff --git a/drivers/net/ethernet/mellanox/mlx5/core/wq.h b/drivers/net/ethernet/mellanox/mlx5/core/wq.h index fca90b94596d..f3dfa0ca3c5d 100644 --- a/drivers/net/ethernet/mellanox/mlx5/core/wq.h +++ b/drivers/net/ethernet/mellanox/mlx5/core/wq.h @@ -38,7 +38,6 @@ #include <linux/mlx5/qp.h> struct mlx5_wq_param { - int linear; int buf_numa_node; int db_numa_node; }; diff --git a/drivers/net/ethernet/mellanox/mlxsw/cmd.h b/drivers/net/ethernet/mellanox/mlxsw/cmd.h index 479511cf79bc..8da91b023b13 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/cmd.h +++ b/drivers/net/ethernet/mellanox/mlxsw/cmd.h @@ -424,10 +424,15 @@ MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_rdq_sz, 0x04, 24, 8); MLXSW_ITEM32(cmd_mbox, query_aq_cap, max_num_rdqs, 0x04, 0, 8); /* cmd_mbox_query_aq_cap_log_max_cq_sz - * Log (base 2) of max CQEs allowed on CQ. + * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv0 and CQEv1. */ MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cq_sz, 0x08, 24, 8); +/* cmd_mbox_query_aq_cap_log_max_cqv2_sz + * Log (base 2) of the Maximum CQEs allowed in a CQ for CQEv2. + */ +MLXSW_ITEM32(cmd_mbox, query_aq_cap, log_max_cqv2_sz, 0x08, 16, 8); + /* cmd_mbox_query_aq_cap_max_num_cqs * Maximum number of CQs. */ @@ -662,6 +667,12 @@ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_single_size, 0x0C, 25, 1); */ MLXSW_ITEM32(cmd_mbox, config_profile, set_kvd_hash_double_size, 0x0C, 26, 1); +/* cmd_mbox_config_set_cqe_version + * Capability bit. Setting a bit to 1 configures the profile + * according to the mailbox contents. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, set_cqe_version, 0x08, 0, 1); + /* cmd_mbox_config_profile_max_vepa_channels * Maximum number of VEPA channels per port (0 through 16) * 0 - multi-channel VEPA is disabled @@ -841,6 +852,14 @@ MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_type, MLXSW_ITEM32_INDEXED(cmd_mbox, config_profile, swid_config_properties, 0x60, 0, 8, 0x08, 0x00, false); +/* cmd_mbox_config_profile_cqe_version + * CQE version: + * 0: CQE version is 0 + * 1: CQE version is either 1 or 2 + * CQE ver 1 or 2 is configured by Completion Queue Context field cqe_ver. + */ +MLXSW_ITEM32(cmd_mbox, config_profile, cqe_version, 0xB0, 0, 8); + /* ACCESS_REG - Access EMAD Supported Register * ---------------------------------- * OpMod == 0 (N/A), INMmod == 0 (N/A) @@ -1032,11 +1051,15 @@ static inline int mlxsw_cmd_sw2hw_cq(struct mlxsw_core *mlxsw_core, 0, cq_number, in_mbox, MLXSW_CMD_MBOX_SIZE); } -/* cmd_mbox_sw2hw_cq_cv +enum mlxsw_cmd_mbox_sw2hw_cq_cqe_ver { + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1, + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2, +}; + +/* cmd_mbox_sw2hw_cq_cqe_ver * CQE Version. - * 0 - CQE Version 0, 1 - CQE Version 1 */ -MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cv, 0x00, 28, 4); +MLXSW_ITEM32(cmd_mbox, sw2hw_cq, cqe_ver, 0x00, 28, 4); /* cmd_mbox_sw2hw_cq_c_eqn * Event Queue this CQ reports completion events to. diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci.c b/drivers/net/ethernet/mellanox/mlxsw/pci.c index 3a9381977d6d..db794a1a3a7e 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci.c +++ b/drivers/net/ethernet/mellanox/mlxsw/pci.c @@ -117,6 +117,7 @@ struct mlxsw_pci_queue { struct { u32 comp_sdq_count; u32 comp_rdq_count; + enum mlxsw_pci_cqe_v v; } cq; struct { u32 ev_cmd_count; @@ -155,6 +156,8 @@ struct mlxsw_pci { } cmd; struct mlxsw_bus_info bus_info; const struct pci_device_id *id; + enum mlxsw_pci_cqe_v max_cqe_ver; /* Maximal supported CQE version */ + u8 num_sdq_cqs; /* Number of CQs used for SDQs */ }; static void mlxsw_pci_queue_tasklet_schedule(struct mlxsw_pci_queue *q) @@ -202,24 +205,6 @@ static bool mlxsw_pci_elem_hw_owned(struct mlxsw_pci_queue *q, bool owner_bit) return owner_bit != !!(q->consumer_counter & q->count); } -static char * -mlxsw_pci_queue_sw_elem_get(struct mlxsw_pci_queue *q, - u32 (*get_elem_owner_func)(const char *)) -{ - struct mlxsw_pci_queue_elem_info *elem_info; - char *elem; - bool owner_bit; - - elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); - elem = elem_info->elem; - owner_bit = get_elem_owner_func(elem); - if (mlxsw_pci_elem_hw_owned(q, owner_bit)) - return NULL; - q->consumer_counter++; - rmb(); /* make sure we read owned bit before the rest of elem */ - return elem; -} - static struct mlxsw_pci_queue_type_group * mlxsw_pci_queue_type_group_get(struct mlxsw_pci *mlxsw_pci, enum mlxsw_pci_queue_type q_type) @@ -494,6 +479,17 @@ static void mlxsw_pci_rdq_fini(struct mlxsw_pci *mlxsw_pci, } } +static void mlxsw_pci_cq_pre_init(struct mlxsw_pci *mlxsw_pci, + struct mlxsw_pci_queue *q) +{ + q->u.cq.v = mlxsw_pci->max_cqe_ver; + + /* For SDQ it is pointless to use CQEv2, so use CQEv1 instead */ + if (q->u.cq.v == MLXSW_PCI_CQE_V2 && + q->num < mlxsw_pci->num_sdq_cqs) + q->u.cq.v = MLXSW_PCI_CQE_V1; +} + static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q) { @@ -505,10 +501,16 @@ static int mlxsw_pci_cq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, for (i = 0; i < q->count; i++) { char *elem = mlxsw_pci_queue_elem_get(q, i); - mlxsw_pci_cqe_owner_set(elem, 1); + mlxsw_pci_cqe_owner_set(q->u.cq.v, elem, 1); } - mlxsw_cmd_mbox_sw2hw_cq_cv_set(mbox, 0); /* CQE ver 0 */ + if (q->u.cq.v == MLXSW_PCI_CQE_V1) + mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox, + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_1); + else if (q->u.cq.v == MLXSW_PCI_CQE_V2) + mlxsw_cmd_mbox_sw2hw_cq_cqe_ver_set(mbox, + MLXSW_CMD_MBOX_SW2HW_CQ_CQE_VER_2); + mlxsw_cmd_mbox_sw2hw_cq_c_eqn_set(mbox, MLXSW_PCI_EQ_COMP_NUM); mlxsw_cmd_mbox_sw2hw_cq_st_set(mbox, 0); mlxsw_cmd_mbox_sw2hw_cq_log_cq_size_set(mbox, ilog2(q->count)); @@ -559,7 +561,7 @@ static void mlxsw_pci_cqe_sdq_handle(struct mlxsw_pci *mlxsw_pci, static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, struct mlxsw_pci_queue *q, u16 consumer_counter_limit, - char *cqe) + enum mlxsw_pci_cqe_v cqe_v, char *cqe) { struct pci_dev *pdev = mlxsw_pci->pdev; struct mlxsw_pci_queue_elem_info *elem_info; @@ -579,10 +581,11 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, if (q->consumer_counter++ != consumer_counter_limit) dev_dbg_ratelimited(&pdev->dev, "Consumer counter does not match limit in RDQ\n"); - if (mlxsw_pci_cqe_lag_get(cqe)) { + if (mlxsw_pci_cqe_lag_get(cqe_v, cqe)) { rx_info.is_lag = true; - rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe); - rx_info.lag_port_index = mlxsw_pci_cqe_lag_port_index_get(cqe); + rx_info.u.lag_id = mlxsw_pci_cqe_lag_id_get(cqe_v, cqe); + rx_info.lag_port_index = + mlxsw_pci_cqe_lag_subport_get(cqe_v, cqe); } else { rx_info.is_lag = false; rx_info.u.sys_port = mlxsw_pci_cqe_system_port_get(cqe); @@ -591,7 +594,7 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, rx_info.trap_id = mlxsw_pci_cqe_trap_id_get(cqe); byte_count = mlxsw_pci_cqe_byte_count_get(cqe); - if (mlxsw_pci_cqe_crc_get(cqe)) + if (mlxsw_pci_cqe_crc_get(cqe_v, cqe)) byte_count -= ETH_FCS_LEN; skb_put(skb, byte_count); mlxsw_core_skb_receive(mlxsw_pci->core, skb, &rx_info); @@ -608,7 +611,18 @@ static void mlxsw_pci_cqe_rdq_handle(struct mlxsw_pci *mlxsw_pci, static char *mlxsw_pci_cq_sw_cqe_get(struct mlxsw_pci_queue *q) { - return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_cqe_owner_get); + struct mlxsw_pci_queue_elem_info *elem_info; + char *elem; + bool owner_bit; + + elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); + elem = elem_info->elem; + owner_bit = mlxsw_pci_cqe_owner_get(q->u.cq.v, elem); + if (mlxsw_pci_elem_hw_owned(q, owner_bit)) + return NULL; + q->consumer_counter++; + rmb(); /* make sure we read owned bit before the rest of elem */ + return elem; } static void mlxsw_pci_cq_tasklet(unsigned long data) @@ -621,8 +635,8 @@ static void mlxsw_pci_cq_tasklet(unsigned long data) while ((cqe = mlxsw_pci_cq_sw_cqe_get(q))) { u16 wqe_counter = mlxsw_pci_cqe_wqe_counter_get(cqe); - u8 sendq = mlxsw_pci_cqe_sr_get(cqe); - u8 dqn = mlxsw_pci_cqe_dqn_get(cqe); + u8 sendq = mlxsw_pci_cqe_sr_get(q->u.cq.v, cqe); + u8 dqn = mlxsw_pci_cqe_dqn_get(q->u.cq.v, cqe); if (sendq) { struct mlxsw_pci_queue *sdq; @@ -636,7 +650,7 @@ static void mlxsw_pci_cq_tasklet(unsigned long data) rdq = mlxsw_pci_rdq_get(mlxsw_pci, dqn); mlxsw_pci_cqe_rdq_handle(mlxsw_pci, rdq, - wqe_counter, cqe); + wqe_counter, q->u.cq.v, cqe); q->u.cq.comp_rdq_count++; } if (++items == credits) @@ -648,6 +662,18 @@ static void mlxsw_pci_cq_tasklet(unsigned long data) } } +static u16 mlxsw_pci_cq_elem_count(const struct mlxsw_pci_queue *q) +{ + return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_COUNT : + MLXSW_PCI_CQE01_COUNT; +} + +static u8 mlxsw_pci_cq_elem_size(const struct mlxsw_pci_queue *q) +{ + return q->u.cq.v == MLXSW_PCI_CQE_V2 ? MLXSW_PCI_CQE2_SIZE : + MLXSW_PCI_CQE01_SIZE; +} + static int mlxsw_pci_eq_init(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q) { @@ -696,7 +722,18 @@ static void mlxsw_pci_eq_cmd_event(struct mlxsw_pci *mlxsw_pci, char *eqe) static char *mlxsw_pci_eq_sw_eqe_get(struct mlxsw_pci_queue *q) { - return mlxsw_pci_queue_sw_elem_get(q, mlxsw_pci_eqe_owner_get); + struct mlxsw_pci_queue_elem_info *elem_info; + char *elem; + bool owner_bit; + + elem_info = mlxsw_pci_queue_elem_info_consumer_get(q); + elem = elem_info->elem; + owner_bit = mlxsw_pci_eqe_owner_get(elem); + if (mlxsw_pci_elem_hw_owned(q, owner_bit)) + return NULL; + q->consumer_counter++; + rmb(); /* make sure we read owned bit before the rest of elem */ + return elem; } static void mlxsw_pci_eq_tasklet(unsigned long data) @@ -749,11 +786,15 @@ static void mlxsw_pci_eq_tasklet(unsigned long data) struct mlxsw_pci_queue_ops { const char *name; enum mlxsw_pci_queue_type type; + void (*pre_init)(struct mlxsw_pci *mlxsw_pci, + struct mlxsw_pci_queue *q); int (*init)(struct mlxsw_pci *mlxsw_pci, char *mbox, struct mlxsw_pci_queue *q); void (*fini)(struct mlxsw_pci *mlxsw_pci, struct mlxsw_pci_queue *q); void (*tasklet)(unsigned long data); + u16 (*elem_count_f)(const struct mlxsw_pci_queue *q); + u8 (*elem_size_f)(const struct mlxsw_pci_queue *q); u16 elem_count; u8 elem_size; }; @@ -776,11 +817,12 @@ static const struct mlxsw_pci_queue_ops mlxsw_pci_rdq_ops = { static const struct mlxsw_pci_queue_ops mlxsw_pci_cq_ops = { .type = MLXSW_PCI_QUEUE_TYPE_CQ, + .pre_init = mlxsw_pci_cq_pre_init, .init = mlxsw_pci_cq_init, .fini = mlxsw_pci_cq_fini, .tasklet = mlxsw_pci_cq_tasklet, - .elem_count = MLXSW_PCI_CQE_COUNT, - .elem_size = MLXSW_PCI_CQE_SIZE + .elem_count_f = mlxsw_pci_cq_elem_count, + .elem_size_f = mlxsw_pci_cq_elem_size }; static const struct mlxsw_pci_queue_ops mlxsw_pci_eq_ops = { @@ -800,10 +842,15 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox, int i; int err; - spin_lock_init(&q->lock); q->num = q_num; - q->count = q_ops->elem_count; - q->elem_size = q_ops->elem_size; + if (q_ops->pre_init) + q_ops->pre_init(mlxsw_pci, q); + + spin_lock_init(&q->lock); + q->count = q_ops->elem_count_f ? q_ops->elem_count_f(q) : + q_ops->elem_count; + q->elem_size = q_ops->elem_size_f ? q_ops->elem_size_f(q) : + q_ops->elem_size; q->type = q_ops->type; q->pci = mlxsw_pci; @@ -832,7 +879,7 @@ static int mlxsw_pci_queue_init(struct mlxsw_pci *mlxsw_pci, char *mbox, elem_info = mlxsw_pci_queue_elem_info_get(q, i); elem_info->elem = - __mlxsw_pci_queue_elem_get(q, q_ops->elem_size, i); + __mlxsw_pci_queue_elem_get(q, q->elem_size, i); } mlxsw_cmd_mbox_zero(mbox); @@ -912,6 +959,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) u8 rdq_log2sz; u8 num_cqs; u8 cq_log2sz; + u8 cqv2_log2sz; u8 num_eqs; u8 eq_log2sz; int err; @@ -927,6 +975,7 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) rdq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_rdq_sz_get(mbox); num_cqs = mlxsw_cmd_mbox_query_aq_cap_max_num_cqs_get(mbox); cq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cq_sz_get(mbox); + cqv2_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_cqv2_sz_get(mbox); num_eqs = mlxsw_cmd_mbox_query_aq_cap_max_num_eqs_get(mbox); eq_log2sz = mlxsw_cmd_mbox_query_aq_cap_log_max_eq_sz_get(mbox); @@ -938,12 +987,16 @@ static int mlxsw_pci_aqs_init(struct mlxsw_pci *mlxsw_pci, char *mbox) if ((1 << sdq_log2sz != MLXSW_PCI_WQE_COUNT) || (1 << rdq_log2sz != MLXSW_PCI_WQE_COUNT) || - (1 << cq_log2sz != MLXSW_PCI_CQE_COUNT) || + (1 << cq_log2sz != MLXSW_PCI_CQE01_COUNT) || + (mlxsw_pci->max_cqe_ver == MLXSW_PCI_CQE_V2 && + (1 << cqv2_log2sz != MLXSW_PCI_CQE2_COUNT)) || (1 << eq_log2sz != MLXSW_PCI_EQE_COUNT)) { dev_err(&pdev->dev, "Unsupported number of async queue descriptors\n"); return -EINVAL; } + mlxsw_pci->num_sdq_cqs = num_sdqs; + err = mlxsw_pci_queue_group_init(mlxsw_pci, mbox, &mlxsw_pci_eq_ops, num_eqs); if (err) { @@ -1184,6 +1237,11 @@ static int mlxsw_pci_config_profile(struct mlxsw_pci *mlxsw_pci, char *mbox, mlxsw_pci_config_profile_swid_config(mlxsw_pci, mbox, i, &profile->swid_config[i]); + if (mlxsw_pci->max_cqe_ver > MLXSW_PCI_CQE_V0) { + mlxsw_cmd_mbox_config_profile_set_cqe_version_set(mbox, 1); + mlxsw_cmd_mbox_config_profile_cqe_version_set(mbox, 1); + } + return mlxsw_cmd_config_profile_set(mlxsw_pci->core, mbox); } @@ -1378,6 +1436,21 @@ static int mlxsw_pci_init(void *bus_priv, struct mlxsw_core *mlxsw_core, if (err) goto err_query_resources; + if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V2) && + MLXSW_CORE_RES_GET(mlxsw_core, CQE_V2)) + mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V2; + else if (MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V1) && + MLXSW_CORE_RES_GET(mlxsw_core, CQE_V1)) + mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V1; + else if ((MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0) && + MLXSW_CORE_RES_GET(mlxsw_core, CQE_V0)) || + !MLXSW_CORE_RES_VALID(mlxsw_core, CQE_V0)) { + mlxsw_pci->max_cqe_ver = MLXSW_PCI_CQE_V0; + } else { + dev_err(&pdev->dev, "Invalid supported CQE version combination reported\n"); + goto err_cqe_v_check; + } + err = mlxsw_pci_config_profile(mlxsw_pci, mbox, profile, res); if (err) goto err_config_profile; @@ -1400,6 +1473,7 @@ err_request_eq_irq: mlxsw_pci_aqs_fini(mlxsw_pci); err_aqs_init: err_config_profile: +err_cqe_v_check: err_query_resources: err_boardinfo: mlxsw_pci_fw_area_fini(mlxsw_pci); diff --git a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h index fb082ad21b00..963155f6a17a 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h +++ b/drivers/net/ethernet/mellanox/mlxsw/pci_hw.h @@ -82,10 +82,12 @@ #define MLXSW_PCI_AQ_PAGES 8 #define MLXSW_PCI_AQ_SIZE (MLXSW_PCI_PAGE_SIZE * MLXSW_PCI_AQ_PAGES) #define MLXSW_PCI_WQE_SIZE 32 /* 32 bytes per element */ -#define MLXSW_PCI_CQE_SIZE 16 /* 16 bytes per element */ +#define MLXSW_PCI_CQE01_SIZE 16 /* 16 bytes per element */ +#define MLXSW_PCI_CQE2_SIZE 32 /* 32 bytes per element */ #define MLXSW_PCI_EQE_SIZE 16 /* 16 bytes per element */ #define MLXSW_PCI_WQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_WQE_SIZE) -#define MLXSW_PCI_CQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE_SIZE) +#define MLXSW_PCI_CQE01_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE01_SIZE) +#define MLXSW_PCI_CQE2_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_CQE2_SIZE) #define MLXSW_PCI_EQE_COUNT (MLXSW_PCI_AQ_SIZE / MLXSW_PCI_EQE_SIZE) #define MLXSW_PCI_EQE_UPDATE_COUNT 0x80 @@ -126,10 +128,48 @@ MLXSW_ITEM16_INDEXED(pci, wqe, byte_count, 0x02, 0, 14, 0x02, 0x00, false); */ MLXSW_ITEM64_INDEXED(pci, wqe, address, 0x08, 0, 64, 0x8, 0x0, false); +enum mlxsw_pci_cqe_v { + MLXSW_PCI_CQE_V0, + MLXSW_PCI_CQE_V1, + MLXSW_PCI_CQE_V2, +}; + +#define mlxsw_pci_cqe_item_helpers(name, v0, v1, v2) \ +static inline u32 mlxsw_pci_cqe_##name##_get(enum mlxsw_pci_cqe_v v, char *cqe) \ +{ \ + switch (v) { \ + default: \ + case MLXSW_PCI_CQE_V0: \ + return mlxsw_pci_cqe##v0##_##name##_get(cqe); \ + case MLXSW_PCI_CQE_V1: \ + return mlxsw_pci_cqe##v1##_##name##_get(cqe); \ + case MLXSW_PCI_CQE_V2: \ + return mlxsw_pci_cqe##v2##_##name##_get(cqe); \ + } \ +} \ +static inline void mlxsw_pci_cqe_##name##_set(enum mlxsw_pci_cqe_v v, \ + char *cqe, u32 val) \ +{ \ + switch (v) { \ + default: \ + case MLXSW_PCI_CQE_V0: \ + mlxsw_pci_cqe##v0##_##name##_set(cqe, val); \ + break; \ + case MLXSW_PCI_CQE_V1: \ + mlxsw_pci_cqe##v1##_##name##_set(cqe, val); \ + break; \ + case MLXSW_PCI_CQE_V2: \ + mlxsw_pci_cqe##v2##_##name##_set(cqe, val); \ + break; \ + } \ +} + /* pci_cqe_lag * Packet arrives from a port which is a LAG */ -MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1); +MLXSW_ITEM32(pci, cqe0, lag, 0x00, 23, 1); +MLXSW_ITEM32(pci, cqe12, lag, 0x00, 24, 1); +mlxsw_pci_cqe_item_helpers(lag, 0, 12, 12); /* pci_cqe_system_port/lag_id * When lag=0: System port on which the packet was received @@ -138,8 +178,12 @@ MLXSW_ITEM32(pci, cqe, lag, 0x00, 23, 1); * bits [3:0] sub_port on which the packet was received */ MLXSW_ITEM32(pci, cqe, system_port, 0x00, 0, 16); -MLXSW_ITEM32(pci, cqe, lag_id, 0x00, 4, 12); -MLXSW_ITEM32(pci, cqe, lag_port_index, 0x00, 0, 4); +MLXSW_ITEM32(pci, cqe0, lag_id, 0x00, 4, 12); +MLXSW_ITEM32(pci, cqe12, lag_id, 0x00, 0, 16); +mlxsw_pci_cqe_item_helpers(lag_id, 0, 12, 12); +MLXSW_ITEM32(pci, cqe0, lag_subport, 0x00, 0, 4); +MLXSW_ITEM32(pci, cqe12, lag_subport, 0x00, 16, 8); +mlxsw_pci_cqe_item_helpers(lag_subport, 0, 12, 12); /* pci_cqe_wqe_counter * WQE count of the WQEs completed on the associated dqn @@ -162,28 +206,38 @@ MLXSW_ITEM32(pci, cqe, trap_id, 0x08, 0, 9); * Length include CRC. Indicates the length field includes * the packet's CRC. */ -MLXSW_ITEM32(pci, cqe, crc, 0x0C, 8, 1); +MLXSW_ITEM32(pci, cqe0, crc, 0x0C, 8, 1); +MLXSW_ITEM32(pci, cqe12, crc, 0x0C, 9, 1); +mlxsw_pci_cqe_item_helpers(crc, 0, 12, 12); /* pci_cqe_e * CQE with Error. */ -MLXSW_ITEM32(pci, cqe, e, 0x0C, 7, 1); +MLXSW_ITEM32(pci, cqe0, e, 0x0C, 7, 1); +MLXSW_ITEM32(pci, cqe12, e, 0x00, 27, 1); +mlxsw_pci_cqe_item_helpers(e, 0, 12, 12); /* pci_cqe_sr * 1 - Send Queue * 0 - Receive Queue */ -MLXSW_ITEM32(pci, cqe, sr, 0x0C, 6, 1); +MLXSW_ITEM32(pci, cqe0, sr, 0x0C, 6, 1); +MLXSW_ITEM32(pci, cqe12, sr, 0x00, 26, 1); +mlxsw_pci_cqe_item_helpers(sr, 0, 12, 12); /* pci_cqe_dqn * Descriptor Queue (DQ) Number. */ -MLXSW_ITEM32(pci, cqe, dqn, 0x0C, 1, 5); +MLXSW_ITEM32(pci, cqe0, dqn, 0x0C, 1, 5); +MLXSW_ITEM32(pci, cqe12, dqn, 0x0C, 1, 6); +mlxsw_pci_cqe_item_helpers(dqn, 0, 12, 12); /* pci_cqe_owner * Ownership bit. */ -MLXSW_ITEM32(pci, cqe, owner, 0x0C, 0, 1); +MLXSW_ITEM32(pci, cqe01, owner, 0x0C, 0, 1); +MLXSW_ITEM32(pci, cqe2, owner, 0x1C, 0, 1); +mlxsw_pci_cqe_item_helpers(owner, 01, 01, 2); /* pci_eqe_event_type * Event type. diff --git a/drivers/net/ethernet/mellanox/mlxsw/reg.h b/drivers/net/ethernet/mellanox/mlxsw/reg.h index 6218231e379e..3f4d7e22cece 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/reg.h +++ b/drivers/net/ethernet/mellanox/mlxsw/reg.h @@ -6833,6 +6833,12 @@ enum mlxsw_reg_mpat_span_type { */ MLXSW_REG_MPAT_SPAN_TYPE_LOCAL_ETH = 0x0, + /* Remote SPAN Ethernet VLAN. + * The packet is forwarded to the monitoring port on the monitoring + * VLAN. + */ + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH = 0x1, + /* Encapsulated Remote SPAN Ethernet L3 GRE. * The packet is encapsulated with GRE header. */ diff --git a/drivers/net/ethernet/mellanox/mlxsw/resources.h b/drivers/net/ethernet/mellanox/mlxsw/resources.h index 087aad52c195..fd9299ccec72 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/resources.h +++ b/drivers/net/ethernet/mellanox/mlxsw/resources.h @@ -43,6 +43,9 @@ enum mlxsw_res_id { MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE, MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE, MLXSW_RES_ID_MAX_TRAP_GROUPS, + MLXSW_RES_ID_CQE_V0, + MLXSW_RES_ID_CQE_V1, + MLXSW_RES_ID_CQE_V2, MLXSW_RES_ID_COUNTER_POOL_SIZE, MLXSW_RES_ID_MAX_SPAN, MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES, @@ -81,6 +84,9 @@ static u16 mlxsw_res_ids[] = { [MLXSW_RES_ID_KVD_SINGLE_MIN_SIZE] = 0x1002, [MLXSW_RES_ID_KVD_DOUBLE_MIN_SIZE] = 0x1003, [MLXSW_RES_ID_MAX_TRAP_GROUPS] = 0x2201, + [MLXSW_RES_ID_CQE_V0] = 0x2210, + [MLXSW_RES_ID_CQE_V1] = 0x2211, + [MLXSW_RES_ID_CQE_V2] = 0x2212, [MLXSW_RES_ID_COUNTER_POOL_SIZE] = 0x2410, [MLXSW_RES_ID_MAX_SPAN] = 0x2420, [MLXSW_RES_ID_COUNTER_SIZE_PACKETS_BYTES] = 0x2443, diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c index ca38a30fbe91..94132f6cec61 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.c @@ -441,29 +441,29 @@ static void mlxsw_sp_txhdr_construct(struct sk_buff *skb, mlxsw_tx_hdr_type_set(txhdr, MLXSW_TXHDR_TYPE_CONTROL); } -int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, - u8 state) +enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 state) { - struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; - enum mlxsw_reg_spms_state spms_state; - char *spms_pl; - int err; - switch (state) { case BR_STATE_FORWARDING: - spms_state = MLXSW_REG_SPMS_STATE_FORWARDING; - break; + return MLXSW_REG_SPMS_STATE_FORWARDING; case BR_STATE_LEARNING: - spms_state = MLXSW_REG_SPMS_STATE_LEARNING; - break; + return MLXSW_REG_SPMS_STATE_LEARNING; case BR_STATE_LISTENING: /* fall-through */ case BR_STATE_DISABLED: /* fall-through */ case BR_STATE_BLOCKING: - spms_state = MLXSW_REG_SPMS_STATE_DISCARDING; - break; + return MLXSW_REG_SPMS_STATE_DISCARDING; default: BUG(); } +} + +int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, + u8 state) +{ + enum mlxsw_reg_spms_state spms_state = mlxsw_sp_stp_spms_state(state); + struct mlxsw_sp *mlxsw_sp = mlxsw_sp_port->mlxsw_sp; + char *spms_pl; + int err; spms_pl = kmalloc(MLXSW_REG_SPMS_LEN, GFP_KERNEL); if (!spms_pl) @@ -3666,6 +3666,15 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_lag_init; } + /* Initialize SPAN before router and switchdev, so that those components + * can call mlxsw_sp_span_respin(). + */ + err = mlxsw_sp_span_init(mlxsw_sp); + if (err) { + dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); + goto err_span_init; + } + err = mlxsw_sp_switchdev_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize switchdev\n"); @@ -3684,15 +3693,6 @@ static int mlxsw_sp_init(struct mlxsw_core *mlxsw_core, goto err_afa_init; } - err = mlxsw_sp_span_init(mlxsw_sp); - if (err) { - dev_err(mlxsw_sp->bus_info->dev, "Failed to init span system\n"); - goto err_span_init; - } - - /* Initialize router after SPAN is initialized, so that the FIB and - * neighbor event handlers can issue SPAN respin. - */ err = mlxsw_sp_router_init(mlxsw_sp); if (err) { dev_err(mlxsw_sp->bus_info->dev, "Failed to initialize router\n"); @@ -3739,14 +3739,14 @@ err_acl_init: err_netdev_notifier: mlxsw_sp_router_fini(mlxsw_sp); err_router_init: - mlxsw_sp_span_fini(mlxsw_sp); -err_span_init: mlxsw_sp_afa_fini(mlxsw_sp); err_afa_init: mlxsw_sp_counter_pool_fini(mlxsw_sp); err_counter_pool_init: mlxsw_sp_switchdev_fini(mlxsw_sp); err_switchdev_init: + mlxsw_sp_span_fini(mlxsw_sp); +err_span_init: mlxsw_sp_lag_fini(mlxsw_sp); err_lag_init: mlxsw_sp_buffers_fini(mlxsw_sp); @@ -3768,10 +3768,10 @@ static void mlxsw_sp_fini(struct mlxsw_core *mlxsw_core) mlxsw_sp_acl_fini(mlxsw_sp); unregister_netdevice_notifier(&mlxsw_sp->netdevice_nb); mlxsw_sp_router_fini(mlxsw_sp); - mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_afa_fini(mlxsw_sp); mlxsw_sp_counter_pool_fini(mlxsw_sp); mlxsw_sp_switchdev_fini(mlxsw_sp); + mlxsw_sp_span_fini(mlxsw_sp); mlxsw_sp_lag_fini(mlxsw_sp); mlxsw_sp_buffers_fini(mlxsw_sp); mlxsw_sp_traps_fini(mlxsw_sp); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h index 804d4d2c8031..4a519d8edec8 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum.h @@ -364,6 +364,7 @@ int __mlxsw_sp_port_headroom_set(struct mlxsw_sp_port *mlxsw_sp_port, int mtu, int mlxsw_sp_port_ets_maxrate_set(struct mlxsw_sp_port *mlxsw_sp_port, enum mlxsw_reg_qeec_hr hr, u8 index, u8 next_index, u32 maxrate); +enum mlxsw_reg_spms_state mlxsw_sp_stp_spms_state(u8 stp_state); int mlxsw_sp_port_vid_stp_set(struct mlxsw_sp_port *mlxsw_sp_port, u16 vid, u8 state); int mlxsw_sp_port_vp_mode_set(struct mlxsw_sp_port *mlxsw_sp_port, bool enable); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c index 1904c0323d39..8028d221aece 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_router.c @@ -442,7 +442,7 @@ struct mlxsw_sp_fib6_entry { struct mlxsw_sp_rt6 { struct list_head list; - struct rt6_info *rt; + struct fib6_info *rt; }; struct mlxsw_sp_lpm_tree { @@ -2770,9 +2770,9 @@ mlxsw_sp_nexthop6_group_cmp(const struct mlxsw_sp_nexthop_group *nh_grp, struct in6_addr *gw; int ifindex, weight; - ifindex = mlxsw_sp_rt6->rt->dst.dev->ifindex; - weight = mlxsw_sp_rt6->rt->rt6i_nh_weight; - gw = &mlxsw_sp_rt6->rt->rt6i_gateway; + ifindex = mlxsw_sp_rt6->rt->fib6_nh.nh_dev->ifindex; + weight = mlxsw_sp_rt6->rt->fib6_nh.nh_weight; + gw = &mlxsw_sp_rt6->rt->fib6_nh.nh_gw; if (!mlxsw_sp_nexthop6_group_has_nexthop(nh_grp, gw, ifindex, weight)) return false; @@ -2838,7 +2838,7 @@ mlxsw_sp_nexthop6_group_hash(struct mlxsw_sp_fib6_entry *fib6_entry, u32 seed) struct net_device *dev; list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { - dev = mlxsw_sp_rt6->rt->dst.dev; + dev = mlxsw_sp_rt6->rt->fib6_nh.nh_dev; val ^= dev->ifindex; } @@ -3834,11 +3834,11 @@ mlxsw_sp_rt6_nexthop(struct mlxsw_sp_nexthop_group *nh_grp, for (i = 0; i < nh_grp->count; i++) { struct mlxsw_sp_nexthop *nh = &nh_grp->nexthops[i]; - struct rt6_info *rt = mlxsw_sp_rt6->rt; + struct fib6_info *rt = mlxsw_sp_rt6->rt; - if (nh->rif && nh->rif->dev == rt->dst.dev && + if (nh->rif && nh->rif->dev == rt->fib6_nh.nh_dev && ipv6_addr_equal((const struct in6_addr *) &nh->gw_addr, - &rt->rt6i_gateway)) + &rt->fib6_nh.nh_gw)) return nh; continue; } @@ -3895,7 +3895,7 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) if (fib_entry->type == MLXSW_SP_FIB_ENTRY_TYPE_LOCAL) { list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, - list)->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; + list)->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD; return; } @@ -3905,9 +3905,9 @@ mlxsw_sp_fib6_entry_offload_set(struct mlxsw_sp_fib_entry *fib_entry) nh = mlxsw_sp_rt6_nexthop(nh_grp, mlxsw_sp_rt6); if (nh && nh->offloaded) - mlxsw_sp_rt6->rt->rt6i_nh_flags |= RTNH_F_OFFLOAD; + mlxsw_sp_rt6->rt->fib6_nh.nh_flags |= RTNH_F_OFFLOAD; else - mlxsw_sp_rt6->rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; + mlxsw_sp_rt6->rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -3920,9 +3920,9 @@ mlxsw_sp_fib6_entry_offload_unset(struct mlxsw_sp_fib_entry *fib_entry) fib6_entry = container_of(fib_entry, struct mlxsw_sp_fib6_entry, common); list_for_each_entry(mlxsw_sp_rt6, &fib6_entry->rt6_list, list) { - struct rt6_info *rt = mlxsw_sp_rt6->rt; + struct fib6_info *rt = mlxsw_sp_rt6->rt; - rt->rt6i_nh_flags &= ~RTNH_F_OFFLOAD; + rt->fib6_nh.nh_flags &= ~RTNH_F_OFFLOAD; } } @@ -4699,29 +4699,29 @@ static void mlxsw_sp_router_fib4_del(struct mlxsw_sp *mlxsw_sp, mlxsw_sp_fib_node_put(mlxsw_sp, fib_node); } -static bool mlxsw_sp_fib6_rt_should_ignore(const struct rt6_info *rt) +static bool mlxsw_sp_fib6_rt_should_ignore(const struct fib6_info *rt) { /* Packets with link-local destination IP arriving to the router * are trapped to the CPU, so no need to program specific routes * for them. */ - if (ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_LINKLOCAL) + if (ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_LINKLOCAL) return true; /* Multicast routes aren't supported, so ignore them. Neighbour * Discovery packets are specifically trapped. */ - if (ipv6_addr_type(&rt->rt6i_dst.addr) & IPV6_ADDR_MULTICAST) + if (ipv6_addr_type(&rt->fib6_dst.addr) & IPV6_ADDR_MULTICAST) return true; /* Cloned routes are irrelevant in the forwarding path. */ - if (rt->rt6i_flags & RTF_CACHE) + if (rt->fib6_flags & RTF_CACHE) return true; return false; } -static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt) +static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; @@ -4734,18 +4734,18 @@ static struct mlxsw_sp_rt6 *mlxsw_sp_rt6_create(struct rt6_info *rt) * memory. */ mlxsw_sp_rt6->rt = rt; - rt6_hold(rt); + fib6_info_hold(rt); return mlxsw_sp_rt6; } #if IS_ENABLED(CONFIG_IPV6) -static void mlxsw_sp_rt6_release(struct rt6_info *rt) +static void mlxsw_sp_rt6_release(struct fib6_info *rt) { - rt6_release(rt); + fib6_info_release(rt); } #else -static void mlxsw_sp_rt6_release(struct rt6_info *rt) +static void mlxsw_sp_rt6_release(struct fib6_info *rt) { } #endif @@ -4756,13 +4756,13 @@ static void mlxsw_sp_rt6_destroy(struct mlxsw_sp_rt6 *mlxsw_sp_rt6) kfree(mlxsw_sp_rt6); } -static bool mlxsw_sp_fib6_rt_can_mp(const struct rt6_info *rt) +static bool mlxsw_sp_fib6_rt_can_mp(const struct fib6_info *rt) { /* RTF_CACHE routes are ignored */ - return (rt->rt6i_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; + return (rt->fib6_flags & (RTF_GATEWAY | RTF_ADDRCONF)) == RTF_GATEWAY; } -static struct rt6_info * +static struct fib6_info * mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) { return list_first_entry(&fib6_entry->rt6_list, struct mlxsw_sp_rt6, @@ -4771,7 +4771,7 @@ mlxsw_sp_fib6_entry_rt(const struct mlxsw_sp_fib6_entry *fib6_entry) static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, - const struct rt6_info *nrt, bool replace) + const struct fib6_info *nrt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; @@ -4779,21 +4779,21 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, return NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { - struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); /* RT6_TABLE_LOCAL and RT6_TABLE_MAIN share the same * virtual router. */ - if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id > nrt->fib6_table->tb6_id) continue; - if (rt->rt6i_table->tb6_id != nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id) break; - if (rt->rt6i_metric < nrt->rt6i_metric) + if (rt->fib6_metric < nrt->fib6_metric) continue; - if (rt->rt6i_metric == nrt->rt6i_metric && + if (rt->fib6_metric == nrt->fib6_metric && mlxsw_sp_fib6_rt_can_mp(rt)) return fib6_entry; - if (rt->rt6i_metric > nrt->rt6i_metric) + if (rt->fib6_metric > nrt->fib6_metric) break; } @@ -4802,7 +4802,7 @@ mlxsw_sp_fib6_node_mp_entry_find(const struct mlxsw_sp_fib_node *fib_node, static struct mlxsw_sp_rt6 * mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry, - const struct rt6_info *rt) + const struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; @@ -4815,21 +4815,21 @@ mlxsw_sp_fib6_entry_rt_find(const struct mlxsw_sp_fib6_entry *fib6_entry, } static bool mlxsw_sp_nexthop6_ipip_type(const struct mlxsw_sp *mlxsw_sp, - const struct rt6_info *rt, + const struct fib6_info *rt, enum mlxsw_sp_ipip_type *ret) { - return rt->dst.dev && - mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->dst.dev, ret); + return rt->fib6_nh.nh_dev && + mlxsw_sp_netdev_ipip_type(mlxsw_sp, rt->fib6_nh.nh_dev, ret); } static int mlxsw_sp_nexthop6_type_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, struct mlxsw_sp_nexthop *nh, - const struct rt6_info *rt) + const struct fib6_info *rt) { const struct mlxsw_sp_ipip_ops *ipip_ops; struct mlxsw_sp_ipip_entry *ipip_entry; - struct net_device *dev = rt->dst.dev; + struct net_device *dev = rt->fib6_nh.nh_dev; struct mlxsw_sp_rif *rif; int err; @@ -4870,13 +4870,13 @@ static void mlxsw_sp_nexthop6_type_fini(struct mlxsw_sp *mlxsw_sp, static int mlxsw_sp_nexthop6_init(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_nexthop_group *nh_grp, struct mlxsw_sp_nexthop *nh, - const struct rt6_info *rt) + const struct fib6_info *rt) { - struct net_device *dev = rt->dst.dev; + struct net_device *dev = rt->fib6_nh.nh_dev; nh->nh_grp = nh_grp; - nh->nh_weight = rt->rt6i_nh_weight; - memcpy(&nh->gw_addr, &rt->rt6i_gateway, sizeof(nh->gw_addr)); + nh->nh_weight = rt->fib6_nh.nh_weight; + memcpy(&nh->gw_addr, &rt->fib6_nh.nh_gw, sizeof(nh->gw_addr)); mlxsw_sp_nexthop_counter_alloc(mlxsw_sp, nh); list_add_tail(&nh->router_list_node, &mlxsw_sp->router->nexthop_list); @@ -4897,9 +4897,9 @@ static void mlxsw_sp_nexthop6_fini(struct mlxsw_sp *mlxsw_sp, } static bool mlxsw_sp_rt6_is_gateway(const struct mlxsw_sp *mlxsw_sp, - const struct rt6_info *rt) + const struct fib6_info *rt) { - return rt->rt6i_flags & RTF_GATEWAY || + return rt->fib6_flags & RTF_GATEWAY || mlxsw_sp_nexthop6_ipip_type(mlxsw_sp, rt, NULL); } @@ -4928,7 +4928,7 @@ mlxsw_sp_nexthop6_group_create(struct mlxsw_sp *mlxsw_sp, nh_grp->gateway = mlxsw_sp_rt6_is_gateway(mlxsw_sp, mlxsw_sp_rt6->rt); nh_grp->count = fib6_entry->nrt6; for (i = 0; i < nh_grp->count; i++) { - struct rt6_info *rt = mlxsw_sp_rt6->rt; + struct fib6_info *rt = mlxsw_sp_rt6->rt; nh = &nh_grp->nexthops[i]; err = mlxsw_sp_nexthop6_init(mlxsw_sp, nh_grp, nh, rt); @@ -5040,7 +5040,7 @@ err_nexthop6_group_get: static int mlxsw_sp_fib6_entry_nexthop_add(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; int err; @@ -5068,7 +5068,7 @@ err_nexthop6_group_update: static void mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib6_entry *fib6_entry, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_rt6 *mlxsw_sp_rt6; @@ -5084,7 +5084,7 @@ mlxsw_sp_fib6_entry_nexthop_del(struct mlxsw_sp *mlxsw_sp, static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_entry *fib_entry, - const struct rt6_info *rt) + const struct fib6_info *rt) { /* Packets hitting RTF_REJECT routes need to be discarded by the * stack. We can rely on their destination device not having a @@ -5092,9 +5092,9 @@ static void mlxsw_sp_fib6_entry_type_set(struct mlxsw_sp *mlxsw_sp, * local, which will cause them to be trapped with a lower * priority than packets that need to be locally received. */ - if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) + if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_TRAP; - else if (rt->rt6i_flags & RTF_REJECT) + else if (rt->fib6_flags & RTF_REJECT) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_LOCAL; else if (mlxsw_sp_rt6_is_gateway(mlxsw_sp, rt)) fib_entry->type = MLXSW_SP_FIB_ENTRY_TYPE_REMOTE; @@ -5118,7 +5118,7 @@ mlxsw_sp_fib6_entry_rt_destroy_all(struct mlxsw_sp_fib6_entry *fib6_entry) static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_entry_create(struct mlxsw_sp *mlxsw_sp, struct mlxsw_sp_fib_node *fib_node, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_entry *fib_entry; @@ -5168,25 +5168,25 @@ static void mlxsw_sp_fib6_entry_destroy(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_node_entry_find(const struct mlxsw_sp_fib_node *fib_node, - const struct rt6_info *nrt, bool replace) + const struct fib6_info *nrt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry, *fallback = NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { - struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(fib6_entry); - if (rt->rt6i_table->tb6_id > nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id > nrt->fib6_table->tb6_id) continue; - if (rt->rt6i_table->tb6_id != nrt->rt6i_table->tb6_id) + if (rt->fib6_table->tb6_id != nrt->fib6_table->tb6_id) break; - if (replace && rt->rt6i_metric == nrt->rt6i_metric) { + if (replace && rt->fib6_metric == nrt->fib6_metric) { if (mlxsw_sp_fib6_rt_can_mp(rt) == mlxsw_sp_fib6_rt_can_mp(nrt)) return fib6_entry; if (mlxsw_sp_fib6_rt_can_mp(nrt)) fallback = fallback ?: fib6_entry; } - if (rt->rt6i_metric > nrt->rt6i_metric) + if (rt->fib6_metric > nrt->fib6_metric) return fallback ?: fib6_entry; } @@ -5198,7 +5198,7 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry, bool replace) { struct mlxsw_sp_fib_node *fib_node = new6_entry->common.fib_node; - struct rt6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry); + struct fib6_info *nrt = mlxsw_sp_fib6_entry_rt(new6_entry); struct mlxsw_sp_fib6_entry *fib6_entry; fib6_entry = mlxsw_sp_fib6_node_entry_find(fib_node, nrt, replace); @@ -5213,9 +5213,9 @@ mlxsw_sp_fib6_node_list_insert(struct mlxsw_sp_fib6_entry *new6_entry, struct mlxsw_sp_fib6_entry *last; list_for_each_entry(last, &fib_node->entry_list, common.list) { - struct rt6_info *rt = mlxsw_sp_fib6_entry_rt(last); + struct fib6_info *rt = mlxsw_sp_fib6_entry_rt(last); - if (nrt->rt6i_table->tb6_id > rt->rt6i_table->tb6_id) + if (nrt->fib6_table->tb6_id > rt->fib6_table->tb6_id) break; fib6_entry = last; } @@ -5268,29 +5268,29 @@ mlxsw_sp_fib6_node_entry_unlink(struct mlxsw_sp *mlxsw_sp, static struct mlxsw_sp_fib6_entry * mlxsw_sp_fib6_entry_lookup(struct mlxsw_sp *mlxsw_sp, - const struct rt6_info *rt) + const struct fib6_info *rt) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; struct mlxsw_sp_fib *fib; struct mlxsw_sp_vr *vr; - vr = mlxsw_sp_vr_find(mlxsw_sp, rt->rt6i_table->tb6_id); + vr = mlxsw_sp_vr_find(mlxsw_sp, rt->fib6_table->tb6_id); if (!vr) return NULL; fib = mlxsw_sp_vr_fib(vr, MLXSW_SP_L3_PROTO_IPV6); - fib_node = mlxsw_sp_fib_node_lookup(fib, &rt->rt6i_dst.addr, - sizeof(rt->rt6i_dst.addr), - rt->rt6i_dst.plen); + fib_node = mlxsw_sp_fib_node_lookup(fib, &rt->fib6_dst.addr, + sizeof(rt->fib6_dst.addr), + rt->fib6_dst.plen); if (!fib_node) return NULL; list_for_each_entry(fib6_entry, &fib_node->entry_list, common.list) { - struct rt6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry); + struct fib6_info *iter_rt = mlxsw_sp_fib6_entry_rt(fib6_entry); - if (rt->rt6i_table->tb6_id == iter_rt->rt6i_table->tb6_id && - rt->rt6i_metric == iter_rt->rt6i_metric && + if (rt->fib6_table->tb6_id == iter_rt->fib6_table->tb6_id && + rt->fib6_metric == iter_rt->fib6_metric && mlxsw_sp_fib6_entry_rt_find(fib6_entry, rt)) return fib6_entry; } @@ -5316,7 +5316,7 @@ static void mlxsw_sp_fib6_entry_replace(struct mlxsw_sp *mlxsw_sp, } static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, - struct rt6_info *rt, bool replace) + struct fib6_info *rt, bool replace) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -5325,16 +5325,16 @@ static int mlxsw_sp_router_fib6_add(struct mlxsw_sp *mlxsw_sp, if (mlxsw_sp->router->aborted) return 0; - if (rt->rt6i_src.plen) + if (rt->fib6_src.plen) return -EINVAL; if (mlxsw_sp_fib6_rt_should_ignore(rt)) return 0; - fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, rt->rt6i_table->tb6_id, - &rt->rt6i_dst.addr, - sizeof(rt->rt6i_dst.addr), - rt->rt6i_dst.plen, + fib_node = mlxsw_sp_fib_node_get(mlxsw_sp, rt->fib6_table->tb6_id, + &rt->fib6_dst.addr, + sizeof(rt->fib6_dst.addr), + rt->fib6_dst.plen, MLXSW_SP_L3_PROTO_IPV6); if (IS_ERR(fib_node)) return PTR_ERR(fib_node); @@ -5373,7 +5373,7 @@ err_fib6_entry_nexthop_add: } static void mlxsw_sp_router_fib6_del(struct mlxsw_sp *mlxsw_sp, - struct rt6_info *rt) + struct fib6_info *rt) { struct mlxsw_sp_fib6_entry *fib6_entry; struct mlxsw_sp_fib_node *fib_node; @@ -5836,7 +5836,7 @@ static void mlxsw_sp_router_fib6_event(struct mlxsw_sp_fib_event_work *fib_work, fen6_info = container_of(info, struct fib6_entry_notifier_info, info); fib_work->fen6_info = *fen6_info; - rt6_hold(fib_work->fen6_info.rt); + fib6_info_hold(fib_work->fen6_info.rt); break; } } @@ -5882,24 +5882,24 @@ static int mlxsw_sp_router_fib_rule_event(unsigned long event, switch (info->family) { case AF_INET: if (!fib4_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; case AF_INET6: if (!fib6_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; case RTNL_FAMILY_IPMR: if (!ipmr_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; case RTNL_FAMILY_IP6MR: if (!ip6mr_rule_default(rule) && !rule->l3mdev) - err = -1; + err = -EOPNOTSUPP; break; } if (err < 0) - NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported. Aborting offload"); + NL_SET_ERR_MSG_MOD(extack, "FIB rules not supported"); return err; } @@ -5926,8 +5926,15 @@ static int mlxsw_sp_router_fib_event(struct notifier_block *nb, case FIB_EVENT_RULE_DEL: err = mlxsw_sp_router_fib_rule_event(event, info, router->mlxsw_sp); - if (!err) - return NOTIFY_DONE; + if (!err || info->extack) + return notifier_from_errno(err); + break; + case FIB_EVENT_ENTRY_ADD: + if (router->aborted) { + NL_SET_ERR_MSG_MOD(info->extack, "FIB offload was aborted. Not configuring route"); + return notifier_from_errno(-EINVAL); + } + break; } fib_work = kzalloc(sizeof(*fib_work), GFP_ATOMIC); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c index 65a77708ff61..e5f4f7620ab7 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.c @@ -32,6 +32,7 @@ * POSSIBILITY OF SUCH DAMAGE. */ +#include <linux/if_bridge.h> #include <linux/list.h> #include <net/arp.h> #include <net/gre.h> @@ -39,8 +40,9 @@ #include <net/ip6_tunnel.h> #include "spectrum.h" -#include "spectrum_span.h" #include "spectrum_ipip.h" +#include "spectrum_span.h" +#include "spectrum_switchdev.h" int mlxsw_sp_span_init(struct mlxsw_sp *mlxsw_sp) { @@ -135,14 +137,14 @@ struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_phys = { static int mlxsw_sp_span_dmac(struct neigh_table *tbl, const void *pkey, - struct net_device *l3edev, + struct net_device *dev, unsigned char dmac[ETH_ALEN]) { - struct neighbour *neigh = neigh_lookup(tbl, pkey, l3edev); + struct neighbour *neigh = neigh_lookup(tbl, pkey, dev); int err = 0; if (!neigh) { - neigh = neigh_create(tbl, pkey, l3edev); + neigh = neigh_create(tbl, pkey, dev); if (IS_ERR(neigh)) return PTR_ERR(neigh); } @@ -167,8 +169,84 @@ mlxsw_sp_span_entry_unoffloadable(struct mlxsw_sp_span_parms *sparmsp) return 0; } +static struct net_device * +mlxsw_sp_span_entry_bridge_8021q(const struct net_device *br_dev, + unsigned char *dmac, + u16 *p_vid) +{ + struct bridge_vlan_info vinfo; + struct net_device *edev; + u16 vid = *p_vid; + + if (!vid && WARN_ON(br_vlan_get_pvid(br_dev, &vid))) + return NULL; + if (!vid || + br_vlan_get_info(br_dev, vid, &vinfo) || + !(vinfo.flags & BRIDGE_VLAN_INFO_BRENTRY)) + return NULL; + + edev = br_fdb_find_port(br_dev, dmac, vid); + if (!edev) + return NULL; + + if (br_vlan_get_info(edev, vid, &vinfo)) + return NULL; + if (!(vinfo.flags & BRIDGE_VLAN_INFO_UNTAGGED)) + *p_vid = vid; + return edev; +} + +static struct net_device * +mlxsw_sp_span_entry_bridge_8021d(const struct net_device *br_dev, + unsigned char *dmac) +{ + return br_fdb_find_port(br_dev, dmac, 0); +} + +static struct net_device * +mlxsw_sp_span_entry_bridge(const struct net_device *br_dev, + unsigned char dmac[ETH_ALEN], + u16 *p_vid) +{ + struct mlxsw_sp_bridge_port *bridge_port; + enum mlxsw_reg_spms_state spms_state; + struct net_device *dev = NULL; + struct mlxsw_sp_port *port; + u8 stp_state; + + if (br_vlan_enabled(br_dev)) + dev = mlxsw_sp_span_entry_bridge_8021q(br_dev, dmac, p_vid); + else if (!*p_vid) + dev = mlxsw_sp_span_entry_bridge_8021d(br_dev, dmac); + if (!dev) + return NULL; + + port = mlxsw_sp_port_dev_lower_find(dev); + if (!port) + return NULL; + + bridge_port = mlxsw_sp_bridge_port_find(port->mlxsw_sp->bridge, dev); + if (!bridge_port) + return NULL; + + stp_state = mlxsw_sp_bridge_port_stp_state(bridge_port); + spms_state = mlxsw_sp_stp_spms_state(stp_state); + if (spms_state != MLXSW_REG_SPMS_STATE_FORWARDING) + return NULL; + + return dev; +} + +static struct net_device * +mlxsw_sp_span_entry_vlan(const struct net_device *vlan_dev, + u16 *p_vid) +{ + *p_vid = vlan_dev_vlan_id(vlan_dev); + return vlan_dev_real_dev(vlan_dev); +} + static __maybe_unused int -mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *l3edev, +mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *edev, union mlxsw_sp_l3addr saddr, union mlxsw_sp_l3addr daddr, union mlxsw_sp_l3addr gw, @@ -177,21 +255,43 @@ mlxsw_sp_span_entry_tunnel_parms_common(struct net_device *l3edev, struct mlxsw_sp_span_parms *sparmsp) { unsigned char dmac[ETH_ALEN]; + u16 vid = 0; if (mlxsw_sp_l3addr_is_zero(gw)) gw = daddr; - if (!l3edev || !mlxsw_sp_port_dev_check(l3edev) || - mlxsw_sp_span_dmac(tbl, &gw, l3edev, dmac)) - return mlxsw_sp_span_entry_unoffloadable(sparmsp); + if (!edev || mlxsw_sp_span_dmac(tbl, &gw, edev, dmac)) + goto unoffloadable; + + if (is_vlan_dev(edev)) + edev = mlxsw_sp_span_entry_vlan(edev, &vid); + + if (netif_is_bridge_master(edev)) { + edev = mlxsw_sp_span_entry_bridge(edev, dmac, &vid); + if (!edev) + goto unoffloadable; + } - sparmsp->dest_port = netdev_priv(l3edev); + if (is_vlan_dev(edev)) { + if (vid || !(edev->flags & IFF_UP)) + goto unoffloadable; + edev = mlxsw_sp_span_entry_vlan(edev, &vid); + } + + if (!mlxsw_sp_port_dev_check(edev)) + goto unoffloadable; + + sparmsp->dest_port = netdev_priv(edev); sparmsp->ttl = ttl; memcpy(sparmsp->dmac, dmac, ETH_ALEN); - memcpy(sparmsp->smac, l3edev->dev_addr, ETH_ALEN); + memcpy(sparmsp->smac, edev->dev_addr, ETH_ALEN); sparmsp->saddr = saddr; sparmsp->daddr = daddr; + sparmsp->vid = vid; return 0; + +unoffloadable: + return mlxsw_sp_span_entry_unoffloadable(sparmsp); } #if IS_ENABLED(CONFIG_NET_IPGRE) @@ -268,9 +368,10 @@ mlxsw_sp_span_entry_gretap4_configure(struct mlxsw_sp_span_entry *span_entry, /* Create a new port analayzer entry for local_port. */ mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid); mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, - sparms.dmac, false); + sparms.dmac, !!sparms.vid); mlxsw_reg_mpat_eth_rspan_l3_ipv4_pack(mpat_pl, sparms.ttl, sparms.smac, be32_to_cpu(sparms.saddr.addr4), @@ -368,9 +469,10 @@ mlxsw_sp_span_entry_gretap6_configure(struct mlxsw_sp_span_entry *span_entry, /* Create a new port analayzer entry for local_port. */ mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH_L3); + mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid); mlxsw_reg_mpat_eth_rspan_l2_pack(mpat_pl, MLXSW_REG_MPAT_ETH_RSPAN_VERSION_NO_HEADER, - sparms.dmac, false); + sparms.dmac, !!sparms.vid); mlxsw_reg_mpat_eth_rspan_l3_ipv6_pack(mpat_pl, sparms.ttl, sparms.smac, sparms.saddr.addr6, sparms.daddr.addr6); @@ -394,6 +496,61 @@ struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_gretap6 = { }; #endif +static bool +mlxsw_sp_span_vlan_can_handle(const struct net_device *dev) +{ + return is_vlan_dev(dev) && + mlxsw_sp_port_dev_check(vlan_dev_real_dev(dev)); +} + +static int +mlxsw_sp_span_entry_vlan_parms(const struct net_device *to_dev, + struct mlxsw_sp_span_parms *sparmsp) +{ + struct net_device *real_dev; + u16 vid; + + if (!(to_dev->flags & IFF_UP)) + return mlxsw_sp_span_entry_unoffloadable(sparmsp); + + real_dev = mlxsw_sp_span_entry_vlan(to_dev, &vid); + sparmsp->dest_port = netdev_priv(real_dev); + sparmsp->vid = vid; + return 0; +} + +static int +mlxsw_sp_span_entry_vlan_configure(struct mlxsw_sp_span_entry *span_entry, + struct mlxsw_sp_span_parms sparms) +{ + struct mlxsw_sp_port *dest_port = sparms.dest_port; + struct mlxsw_sp *mlxsw_sp = dest_port->mlxsw_sp; + u8 local_port = dest_port->local_port; + char mpat_pl[MLXSW_REG_MPAT_LEN]; + int pa_id = span_entry->id; + + mlxsw_reg_mpat_pack(mpat_pl, pa_id, local_port, true, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH); + mlxsw_reg_mpat_eth_rspan_pack(mpat_pl, sparms.vid); + + return mlxsw_reg_write(mlxsw_sp->core, MLXSW_REG(mpat), mpat_pl); +} + +static void +mlxsw_sp_span_entry_vlan_deconfigure(struct mlxsw_sp_span_entry *span_entry) +{ + mlxsw_sp_span_entry_deconfigure_common(span_entry, + MLXSW_REG_MPAT_SPAN_TYPE_REMOTE_ETH); +} + +static const +struct mlxsw_sp_span_entry_ops mlxsw_sp_span_entry_ops_vlan = { + .can_handle = mlxsw_sp_span_vlan_can_handle, + .parms = mlxsw_sp_span_entry_vlan_parms, + .configure = mlxsw_sp_span_entry_vlan_configure, + .deconfigure = mlxsw_sp_span_entry_vlan_deconfigure, +}; + static const struct mlxsw_sp_span_entry_ops *const mlxsw_sp_span_entry_types[] = { &mlxsw_sp_span_entry_ops_phys, @@ -403,6 +560,7 @@ struct mlxsw_sp_span_entry_ops *const mlxsw_sp_span_entry_types[] = { #if IS_ENABLED(CONFIG_IPV6_GRE) &mlxsw_sp_span_entry_ops_gretap6, #endif + &mlxsw_sp_span_entry_ops_vlan, }; static int @@ -766,7 +924,7 @@ int mlxsw_sp_span_mirror_add(struct mlxsw_sp_port *from, span_entry = mlxsw_sp_span_entry_get(mlxsw_sp, to_dev, ops, sparms); if (!span_entry) - return -ENOENT; + return -ENOBUFS; netdev_dbg(from->dev, "Adding inspected port to SPAN entry %d\n", span_entry->id); diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h index 4b87ec20e658..14a6de904db1 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_span.h @@ -63,6 +63,7 @@ struct mlxsw_sp_span_parms { unsigned char smac[ETH_ALEN]; union mlxsw_sp_l3addr daddr; union mlxsw_sp_l3addr saddr; + u16 vid; }; struct mlxsw_sp_span_entry_ops; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c index 4ed01182a82c..8c9cf8ee9398 100644 --- a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.c @@ -49,7 +49,9 @@ #include <linux/netlink.h> #include <net/switchdev.h> +#include "spectrum_span.h" #include "spectrum_router.h" +#include "spectrum_switchdev.h" #include "spectrum.h" #include "core.h" #include "reg.h" @@ -239,7 +241,7 @@ __mlxsw_sp_bridge_port_find(const struct mlxsw_sp_bridge_device *bridge_device, return NULL; } -static struct mlxsw_sp_bridge_port * +struct mlxsw_sp_bridge_port * mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge, struct net_device *brport_dev) { @@ -922,6 +924,9 @@ static int mlxsw_sp_port_attr_set(struct net_device *dev, break; } + if (switchdev_trans_ph_commit(trans)) + mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp); + return err; } @@ -1646,18 +1651,57 @@ mlxsw_sp_port_mrouter_update_mdb(struct mlxsw_sp_port *mlxsw_sp_port, } } +struct mlxsw_sp_span_respin_work { + struct work_struct work; + struct mlxsw_sp *mlxsw_sp; +}; + +static void mlxsw_sp_span_respin_work(struct work_struct *work) +{ + struct mlxsw_sp_span_respin_work *respin_work = + container_of(work, struct mlxsw_sp_span_respin_work, work); + + rtnl_lock(); + mlxsw_sp_span_respin(respin_work->mlxsw_sp); + rtnl_unlock(); + kfree(respin_work); +} + +static void mlxsw_sp_span_respin_schedule(struct mlxsw_sp *mlxsw_sp) +{ + struct mlxsw_sp_span_respin_work *respin_work; + + respin_work = kzalloc(sizeof(*respin_work), GFP_ATOMIC); + if (!respin_work) + return; + + INIT_WORK(&respin_work->work, mlxsw_sp_span_respin_work); + respin_work->mlxsw_sp = mlxsw_sp; + + mlxsw_core_schedule_work(&respin_work->work); +} + static int mlxsw_sp_port_obj_add(struct net_device *dev, const struct switchdev_obj *obj, struct switchdev_trans *trans) { struct mlxsw_sp_port *mlxsw_sp_port = netdev_priv(dev); + const struct switchdev_obj_port_vlan *vlan; int err = 0; switch (obj->id) { case SWITCHDEV_OBJ_ID_PORT_VLAN: - err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, - SWITCHDEV_OBJ_PORT_VLAN(obj), - trans); + vlan = SWITCHDEV_OBJ_PORT_VLAN(obj); + err = mlxsw_sp_port_vlans_add(mlxsw_sp_port, vlan, trans); + + if (switchdev_trans_ph_commit(trans)) { + /* The event is emitted before the changes are actually + * applied to the bridge. Therefore schedule the respin + * call for later, so that the respin logic sees the + * updated bridge state. + */ + mlxsw_sp_span_respin_schedule(mlxsw_sp_port->mlxsw_sp); + } break; case SWITCHDEV_OBJ_ID_PORT_MDB: err = mlxsw_sp_port_mdb_add(mlxsw_sp_port, @@ -1806,6 +1850,8 @@ static int mlxsw_sp_port_obj_del(struct net_device *dev, break; } + mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp); + return err; } @@ -2222,6 +2268,8 @@ static void mlxsw_sp_switchdev_event_work(struct work_struct *work) switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; err = mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, true); if (err) break; @@ -2231,10 +2279,20 @@ static void mlxsw_sp_switchdev_event_work(struct work_struct *work) break; case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; mlxsw_sp_port_fdb_set(mlxsw_sp_port, fdb_info, false); break; + case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */ + case SWITCHDEV_FDB_DEL_TO_BRIDGE: + /* These events are only used to potentially update an existing + * SPAN mirror. + */ + break; } + mlxsw_sp_span_respin(mlxsw_sp_port->mlxsw_sp); + out: rtnl_unlock(); kfree(switchdev_work->fdb_info.addr); @@ -2263,7 +2321,9 @@ static int mlxsw_sp_switchdev_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ - case SWITCHDEV_FDB_DEL_TO_DEVICE: + case SWITCHDEV_FDB_DEL_TO_DEVICE: /* fall through */ + case SWITCHDEV_FDB_ADD_TO_BRIDGE: /* fall through */ + case SWITCHDEV_FDB_DEL_TO_BRIDGE: memcpy(&switchdev_work->fdb_info, ptr, sizeof(switchdev_work->fdb_info)); switchdev_work->fdb_info.addr = kzalloc(ETH_ALEN, GFP_ATOMIC); @@ -2295,6 +2355,12 @@ static struct notifier_block mlxsw_sp_switchdev_notifier = { .notifier_call = mlxsw_sp_switchdev_event, }; +u8 +mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port) +{ + return bridge_port->stp_state; +} + static int mlxsw_sp_fdb_init(struct mlxsw_sp *mlxsw_sp) { struct mlxsw_sp_bridge *bridge = mlxsw_sp->bridge; diff --git a/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h new file mode 100644 index 000000000000..bc44d5effc28 --- /dev/null +++ b/drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: BSD-3-Clause OR GPL-2.0 + * drivers/net/ethernet/mellanox/mlxsw/spectrum_switchdev.h + * Copyright (c) 2018 Mellanox Technologies. All rights reserved. + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions are met: + * + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the names of the copyright holders nor the names of its + * contributors may be used to endorse or promote products derived from + * this software without specific prior written permission. + * + * Alternatively, this software may be distributed under the terms of the + * GNU General Public License ("GPL") version 2 as published by the Free + * Software Foundation. + * + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS "AS IS" + * AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT LIMITED TO, THE + * IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS FOR A PARTICULAR PURPOSE + * ARE DISCLAIMED. IN NO EVENT SHALL THE COPYRIGHT OWNER OR CONTRIBUTORS BE + * LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, SPECIAL, EXEMPLARY, OR + * CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT LIMITED TO, PROCUREMENT OF + * SUBSTITUTE GOODS OR SERVICES; LOSS OF USE, DATA, OR PROFITS; OR BUSINESS + * INTERRUPTION) HOWEVER CAUSED AND ON ANY THEORY OF LIABILITY, WHETHER IN + * CONTRACT, STRICT LIABILITY, OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) + * ARISING IN ANY WAY OUT OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE + * POSSIBILITY OF SUCH DAMAGE. + */ + +#include <linux/netdevice.h> + +struct mlxsw_sp_bridge; +struct mlxsw_sp_bridge_port; + +struct mlxsw_sp_bridge_port * +mlxsw_sp_bridge_port_find(struct mlxsw_sp_bridge *bridge, + struct net_device *brport_dev); + +u8 mlxsw_sp_bridge_port_stp_state(struct mlxsw_sp_bridge_port *bridge_port); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c index 7e298148ca26..cb87fccb9f6a 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/cmsg.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -102,6 +102,15 @@ nfp_bpf_cmsg_map_req_alloc(struct nfp_app_bpf *bpf, unsigned int n) return nfp_bpf_cmsg_alloc(bpf, size); } +static u8 nfp_bpf_cmsg_get_type(struct sk_buff *skb) +{ + struct cmsg_hdr *hdr; + + hdr = (struct cmsg_hdr *)skb->data; + + return hdr->type; +} + static unsigned int nfp_bpf_cmsg_get_tag(struct sk_buff *skb) { struct cmsg_hdr *hdr; @@ -431,6 +440,11 @@ void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb) goto err_free; } + if (nfp_bpf_cmsg_get_type(skb) == CMSG_TYPE_BPF_EVENT) { + nfp_bpf_event_output(bpf, skb); + return; + } + nfp_ctrl_lock(bpf->app->ctrl); tag = nfp_bpf_cmsg_get_tag(skb); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/fw.h b/drivers/net/ethernet/netronome/nfp/bpf/fw.h index 39639ac28b01..3dbc21653ce5 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/fw.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/fw.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -37,6 +37,14 @@ #include <linux/bitops.h> #include <linux/types.h> +/* Kernel's enum bpf_reg_type is not uABI so people may change it breaking + * our FW ABI. In that case we will do translation in the driver. + */ +#define NFP_BPF_SCALAR_VALUE 1 +#define NFP_BPF_MAP_VALUE 4 +#define NFP_BPF_STACK 6 +#define NFP_BPF_PACKET_DATA 8 + enum bpf_cap_tlv_type { NFP_BPF_CAP_TYPE_FUNC = 1, NFP_BPF_CAP_TYPE_ADJUST_HEAD = 2, @@ -81,6 +89,7 @@ enum nfp_bpf_cmsg_type { CMSG_TYPE_MAP_DELETE = 5, CMSG_TYPE_MAP_GETNEXT = 6, CMSG_TYPE_MAP_GETFIRST = 7, + CMSG_TYPE_BPF_EVENT = 8, __CMSG_TYPE_MAP_MAX, }; @@ -155,4 +164,13 @@ struct cmsg_reply_map_op { __be32 resv; struct cmsg_key_value_pair elem[0]; }; + +struct cmsg_bpf_event { + struct cmsg_hdr hdr; + __be32 cpu_id; + __be64 map_ptr; + __be32 data_size; + __be32 pkt_size; + u8 data[0]; +}; #endif diff --git a/drivers/net/ethernet/netronome/nfp/bpf/jit.c b/drivers/net/ethernet/netronome/nfp/bpf/jit.c index 29b4e5f8c102..326a2085d650 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/jit.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/jit.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2016-2017 Netronome Systems, Inc. + * Copyright (C) 2016-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -1214,45 +1214,83 @@ wrp_test_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, return 0; } -static int -wrp_cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, - enum br_mask br_mask, bool swap) +static const struct jmp_code_map { + enum br_mask br_mask; + bool swap; +} jmp_code_map[] = { + [BPF_JGT >> 4] = { BR_BLO, true }, + [BPF_JGE >> 4] = { BR_BHS, false }, + [BPF_JLT >> 4] = { BR_BLO, false }, + [BPF_JLE >> 4] = { BR_BHS, true }, + [BPF_JSGT >> 4] = { BR_BLT, true }, + [BPF_JSGE >> 4] = { BR_BGE, false }, + [BPF_JSLT >> 4] = { BR_BLT, false }, + [BPF_JSLE >> 4] = { BR_BGE, true }, +}; + +static const struct jmp_code_map *nfp_jmp_code_get(struct nfp_insn_meta *meta) +{ + unsigned int op; + + op = BPF_OP(meta->insn.code) >> 4; + /* br_mask of 0 is BR_BEQ which we don't use in jump code table */ + if (WARN_ONCE(op >= ARRAY_SIZE(jmp_code_map) || + !jmp_code_map[op].br_mask, + "no code found for jump instruction")) + return NULL; + + return &jmp_code_map[op]; +} + +static int cmp_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; u64 imm = insn->imm; /* sign extend */ + const struct jmp_code_map *code; + enum alu_op alu_op, carry_op; u8 reg = insn->dst_reg * 2; swreg tmp_reg; + code = nfp_jmp_code_get(meta); + if (!code) + return -EINVAL; + + alu_op = meta->jump_neg_op ? ALU_OP_ADD : ALU_OP_SUB; + carry_op = meta->jump_neg_op ? ALU_OP_ADD_C : ALU_OP_SUB_C; + tmp_reg = ur_load_imm_any(nfp_prog, imm & ~0U, imm_b(nfp_prog)); - if (!swap) - emit_alu(nfp_prog, reg_none(), reg_a(reg), ALU_OP_SUB, tmp_reg); + if (!code->swap) + emit_alu(nfp_prog, reg_none(), reg_a(reg), alu_op, tmp_reg); else - emit_alu(nfp_prog, reg_none(), tmp_reg, ALU_OP_SUB, reg_a(reg)); + emit_alu(nfp_prog, reg_none(), tmp_reg, alu_op, reg_a(reg)); tmp_reg = ur_load_imm_any(nfp_prog, imm >> 32, imm_b(nfp_prog)); - if (!swap) + if (!code->swap) emit_alu(nfp_prog, reg_none(), - reg_a(reg + 1), ALU_OP_SUB_C, tmp_reg); + reg_a(reg + 1), carry_op, tmp_reg); else emit_alu(nfp_prog, reg_none(), - tmp_reg, ALU_OP_SUB_C, reg_a(reg + 1)); + tmp_reg, carry_op, reg_a(reg + 1)); - emit_br(nfp_prog, br_mask, insn->off, 0); + emit_br(nfp_prog, code->br_mask, insn->off, 0); return 0; } -static int -wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, - enum br_mask br_mask, bool swap) +static int cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; + const struct jmp_code_map *code; u8 areg, breg; + code = nfp_jmp_code_get(meta); + if (!code) + return -EINVAL; + areg = insn->dst_reg * 2; breg = insn->src_reg * 2; - if (swap) { + if (code->swap) { areg ^= breg; breg ^= areg; areg ^= breg; @@ -1261,7 +1299,7 @@ wrp_cmp_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta, emit_alu(nfp_prog, reg_none(), reg_a(areg), ALU_OP_SUB, reg_b(breg)); emit_alu(nfp_prog, reg_none(), reg_a(areg + 1), ALU_OP_SUB_C, reg_b(breg + 1)); - emit_br(nfp_prog, br_mask, insn->off, 0); + emit_br(nfp_prog, code->br_mask, insn->off, 0); return 0; } @@ -1357,15 +1395,9 @@ static int adjust_head(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) static int map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { - struct bpf_offloaded_map *offmap; - struct nfp_bpf_map *nfp_map; bool load_lm_ptr; u32 ret_tgt; s64 lm_off; - swreg tid; - - offmap = (struct bpf_offloaded_map *)meta->arg1.map_ptr; - nfp_map = offmap->dev_priv; /* We only have to reload LM0 if the key is not at start of stack */ lm_off = nfp_prog->stack_depth; @@ -1378,17 +1410,12 @@ map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) if (meta->func_id == BPF_FUNC_map_update_elem) emit_csr_wr(nfp_prog, reg_b(3 * 2), NFP_CSR_ACT_LM_ADDR2); - /* Load map ID into a register, it should actually fit as an immediate - * but in case it doesn't deal with it here, not in the delay slots. - */ - tid = ur_load_imm_any(nfp_prog, nfp_map->tid, imm_a(nfp_prog)); - emit_br_relo(nfp_prog, BR_UNC, BR_OFF_RELO + meta->func_id, 2, RELO_BR_HELPER); ret_tgt = nfp_prog_current_offset(nfp_prog) + 2; /* Load map ID into A0 */ - wrp_mov(nfp_prog, reg_a(0), tid); + wrp_mov(nfp_prog, reg_a(0), reg_a(2)); /* Load the return address into B0 */ wrp_immed_relo(nfp_prog, reg_b(0), ret_tgt, RELO_IMMED_REL); @@ -1400,7 +1427,7 @@ map_call_stack_common(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) if (!load_lm_ptr) return 0; - emit_csr_wr(nfp_prog, stack_reg(nfp_prog), NFP_CSR_ACT_LM_ADDR0); + emit_csr_wr(nfp_prog, stack_reg(nfp_prog), NFP_CSR_ACT_LM_ADDR0); wrp_nops(nfp_prog, 3); return 0; @@ -1418,6 +1445,31 @@ nfp_get_prandom_u32(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return 0; } +static int +nfp_perf_event_output(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) +{ + swreg ptr_type; + u32 ret_tgt; + + ptr_type = ur_load_imm_any(nfp_prog, meta->arg1.type, imm_a(nfp_prog)); + + ret_tgt = nfp_prog_current_offset(nfp_prog) + 3; + + emit_br_relo(nfp_prog, BR_UNC, BR_OFF_RELO + meta->func_id, + 2, RELO_BR_HELPER); + + /* Load ptr type into A1 */ + wrp_mov(nfp_prog, reg_a(1), ptr_type); + + /* Load the return address into B0 */ + wrp_immed_relo(nfp_prog, reg_b(0), ret_tgt, RELO_IMMED_REL); + + if (!nfp_prog_confirm_current_offset(nfp_prog, ret_tgt)) + return -EINVAL; + + return 0; +} + /* --- Callbacks --- */ static int mov_reg64(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { @@ -2283,46 +2335,6 @@ static int jeq_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return 0; } -static int jgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BLO, true); -} - -static int jge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BHS, false); -} - -static int jlt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BLO, false); -} - -static int jle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BHS, true); -} - -static int jsgt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BLT, true); -} - -static int jsge_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BGE, false); -} - -static int jslt_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BLT, false); -} - -static int jsle_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_imm(nfp_prog, meta, BR_BGE, true); -} - static int jset_imm(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { const struct bpf_insn *insn = &meta->insn; @@ -2392,46 +2404,6 @@ static int jeq_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return 0; } -static int jgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BLO, true); -} - -static int jge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BHS, false); -} - -static int jlt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BLO, false); -} - -static int jle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BHS, true); -} - -static int jsgt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BLT, true); -} - -static int jsge_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BGE, false); -} - -static int jslt_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BLT, false); -} - -static int jsle_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) -{ - return wrp_cmp_reg(nfp_prog, meta, BR_BGE, true); -} - static int jset_reg(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) { return wrp_test_reg(nfp_prog, meta, ALU_OP_AND, BR_BNE); @@ -2453,6 +2425,8 @@ static int call(struct nfp_prog *nfp_prog, struct nfp_insn_meta *meta) return map_call_stack_common(nfp_prog, meta); case BPF_FUNC_get_prandom_u32: return nfp_get_prandom_u32(nfp_prog, meta); + case BPF_FUNC_perf_event_output: + return nfp_perf_event_output(nfp_prog, meta); default: WARN_ONCE(1, "verifier allowed unsupported function\n"); return -EOPNOTSUPP; @@ -2520,25 +2494,25 @@ static const instr_cb_t instr_cb[256] = { [BPF_ST | BPF_MEM | BPF_DW] = mem_st8, [BPF_JMP | BPF_JA | BPF_K] = jump, [BPF_JMP | BPF_JEQ | BPF_K] = jeq_imm, - [BPF_JMP | BPF_JGT | BPF_K] = jgt_imm, - [BPF_JMP | BPF_JGE | BPF_K] = jge_imm, - [BPF_JMP | BPF_JLT | BPF_K] = jlt_imm, - [BPF_JMP | BPF_JLE | BPF_K] = jle_imm, - [BPF_JMP | BPF_JSGT | BPF_K] = jsgt_imm, - [BPF_JMP | BPF_JSGE | BPF_K] = jsge_imm, - [BPF_JMP | BPF_JSLT | BPF_K] = jslt_imm, - [BPF_JMP | BPF_JSLE | BPF_K] = jsle_imm, + [BPF_JMP | BPF_JGT | BPF_K] = cmp_imm, + [BPF_JMP | BPF_JGE | BPF_K] = cmp_imm, + [BPF_JMP | BPF_JLT | BPF_K] = cmp_imm, + [BPF_JMP | BPF_JLE | BPF_K] = cmp_imm, + [BPF_JMP | BPF_JSGT | BPF_K] = cmp_imm, + [BPF_JMP | BPF_JSGE | BPF_K] = cmp_imm, + [BPF_JMP | BPF_JSLT | BPF_K] = cmp_imm, + [BPF_JMP | BPF_JSLE | BPF_K] = cmp_imm, [BPF_JMP | BPF_JSET | BPF_K] = jset_imm, [BPF_JMP | BPF_JNE | BPF_K] = jne_imm, [BPF_JMP | BPF_JEQ | BPF_X] = jeq_reg, - [BPF_JMP | BPF_JGT | BPF_X] = jgt_reg, - [BPF_JMP | BPF_JGE | BPF_X] = jge_reg, - [BPF_JMP | BPF_JLT | BPF_X] = jlt_reg, - [BPF_JMP | BPF_JLE | BPF_X] = jle_reg, - [BPF_JMP | BPF_JSGT | BPF_X] = jsgt_reg, - [BPF_JMP | BPF_JSGE | BPF_X] = jsge_reg, - [BPF_JMP | BPF_JSLT | BPF_X] = jslt_reg, - [BPF_JMP | BPF_JSLE | BPF_X] = jsle_reg, + [BPF_JMP | BPF_JGT | BPF_X] = cmp_reg, + [BPF_JMP | BPF_JGE | BPF_X] = cmp_reg, + [BPF_JMP | BPF_JLT | BPF_X] = cmp_reg, + [BPF_JMP | BPF_JLE | BPF_X] = cmp_reg, + [BPF_JMP | BPF_JSGT | BPF_X] = cmp_reg, + [BPF_JMP | BPF_JSGE | BPF_X] = cmp_reg, + [BPF_JMP | BPF_JSLT | BPF_X] = cmp_reg, + [BPF_JMP | BPF_JSLE | BPF_X] = cmp_reg, [BPF_JMP | BPF_JSET | BPF_X] = jset_reg, [BPF_JMP | BPF_JNE | BPF_X] = jne_reg, [BPF_JMP | BPF_CALL] = call, @@ -2777,6 +2751,54 @@ static void nfp_bpf_opt_reg_init(struct nfp_prog *nfp_prog) } } +/* abs(insn.imm) will fit better into unrestricted reg immediate - + * convert add/sub of a negative number into a sub/add of a positive one. + */ +static void nfp_bpf_opt_neg_add_sub(struct nfp_prog *nfp_prog) +{ + struct nfp_insn_meta *meta; + + list_for_each_entry(meta, &nfp_prog->insns, l) { + struct bpf_insn insn = meta->insn; + + if (meta->skip) + continue; + + if (BPF_CLASS(insn.code) != BPF_ALU && + BPF_CLASS(insn.code) != BPF_ALU64 && + BPF_CLASS(insn.code) != BPF_JMP) + continue; + if (BPF_SRC(insn.code) != BPF_K) + continue; + if (insn.imm >= 0) + continue; + + if (BPF_CLASS(insn.code) == BPF_JMP) { + switch (BPF_OP(insn.code)) { + case BPF_JGE: + case BPF_JSGE: + case BPF_JLT: + case BPF_JSLT: + meta->jump_neg_op = true; + break; + default: + continue; + } + } else { + if (BPF_OP(insn.code) == BPF_ADD) + insn.code = BPF_CLASS(insn.code) | BPF_SUB; + else if (BPF_OP(insn.code) == BPF_SUB) + insn.code = BPF_CLASS(insn.code) | BPF_ADD; + else + continue; + + meta->insn.code = insn.code | BPF_K; + } + + meta->insn.imm = -insn.imm; + } +} + /* Remove masking after load since our load guarantees this is not needed */ static void nfp_bpf_opt_ld_mask(struct nfp_prog *nfp_prog) { @@ -3212,6 +3234,7 @@ static int nfp_bpf_optimize(struct nfp_prog *nfp_prog) { nfp_bpf_opt_reg_init(nfp_prog); + nfp_bpf_opt_neg_add_sub(nfp_prog); nfp_bpf_opt_ld_mask(nfp_prog); nfp_bpf_opt_ld_shift(nfp_prog); nfp_bpf_opt_ldst_gather(nfp_prog); @@ -3220,6 +3243,33 @@ static int nfp_bpf_optimize(struct nfp_prog *nfp_prog) return 0; } +static int nfp_bpf_replace_map_ptrs(struct nfp_prog *nfp_prog) +{ + struct nfp_insn_meta *meta1, *meta2; + struct nfp_bpf_map *nfp_map; + struct bpf_map *map; + + nfp_for_each_insn_walk2(nfp_prog, meta1, meta2) { + if (meta1->skip || meta2->skip) + continue; + + if (meta1->insn.code != (BPF_LD | BPF_IMM | BPF_DW) || + meta1->insn.src_reg != BPF_PSEUDO_MAP_FD) + continue; + + map = (void *)(unsigned long)((u32)meta1->insn.imm | + (u64)meta2->insn.imm << 32); + if (bpf_map_offload_neutral(map)) + continue; + nfp_map = map_to_offmap(map)->dev_priv; + + meta1->insn.imm = nfp_map->tid; + meta2->insn.imm = 0; + } + + return 0; +} + static int nfp_bpf_ustore_calc(u64 *prog, unsigned int len) { __le64 *ustore = (__force __le64 *)prog; @@ -3256,6 +3306,10 @@ int nfp_bpf_jit(struct nfp_prog *nfp_prog) { int ret; + ret = nfp_bpf_replace_map_ptrs(nfp_prog); + if (ret) + return ret; + ret = nfp_bpf_optimize(nfp_prog); if (ret) return ret; @@ -3346,6 +3400,9 @@ void *nfp_bpf_relo_for_vnic(struct nfp_prog *nfp_prog, struct nfp_bpf_vnic *bv) case BPF_FUNC_map_delete_elem: val = nfp_prog->bpf->helpers.map_delete; break; + case BPF_FUNC_perf_event_output: + val = nfp_prog->bpf->helpers.perf_event_output; + break; default: pr_err("relocation of unknown helper %d\n", val); diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.c b/drivers/net/ethernet/netronome/nfp/bpf/main.c index 1dc424685f4e..d72f9e7f42da 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -43,6 +43,14 @@ #include "fw.h" #include "main.h" +const struct rhashtable_params nfp_bpf_maps_neutral_params = { + .nelem_hint = 4, + .key_len = FIELD_SIZEOF(struct nfp_bpf_neutral_map, ptr), + .key_offset = offsetof(struct nfp_bpf_neutral_map, ptr), + .head_offset = offsetof(struct nfp_bpf_neutral_map, l), + .automatic_shrinking = true, +}; + static bool nfp_net_ebpf_capable(struct nfp_net *nn) { #ifdef __LITTLE_ENDIAN @@ -290,6 +298,9 @@ nfp_bpf_parse_cap_func(struct nfp_app_bpf *bpf, void __iomem *value, u32 length) case BPF_FUNC_map_delete_elem: bpf->helpers.map_delete = readl(&cap->func_addr); break; + case BPF_FUNC_perf_event_output: + bpf->helpers.perf_event_output = readl(&cap->func_addr); + break; } return 0; @@ -401,17 +412,28 @@ static int nfp_bpf_init(struct nfp_app *app) init_waitqueue_head(&bpf->cmsg_wq); INIT_LIST_HEAD(&bpf->map_list); - err = nfp_bpf_parse_capabilities(app); + err = rhashtable_init(&bpf->maps_neutral, &nfp_bpf_maps_neutral_params); if (err) goto err_free_bpf; + err = nfp_bpf_parse_capabilities(app); + if (err) + goto err_free_neutral_maps; + return 0; +err_free_neutral_maps: + rhashtable_destroy(&bpf->maps_neutral); err_free_bpf: kfree(bpf); return err; } +static void nfp_check_rhashtable_empty(void *ptr, void *arg) +{ + WARN_ON_ONCE(1); +} + static void nfp_bpf_clean(struct nfp_app *app) { struct nfp_app_bpf *bpf = app->priv; @@ -419,6 +441,8 @@ static void nfp_bpf_clean(struct nfp_app *app) WARN_ON(!skb_queue_empty(&bpf->cmsg_replies)); WARN_ON(!list_empty(&bpf->map_list)); WARN_ON(bpf->maps_in_use || bpf->map_elems_in_use); + rhashtable_free_and_destroy(&bpf->maps_neutral, + nfp_check_rhashtable_empty, NULL); kfree(bpf); } diff --git a/drivers/net/ethernet/netronome/nfp/bpf/main.h b/drivers/net/ethernet/netronome/nfp/bpf/main.h index 4981c8944ca3..82682378d57f 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/main.h +++ b/drivers/net/ethernet/netronome/nfp/bpf/main.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2016-2017 Netronome Systems, Inc. + * Copyright (C) 2016-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -39,6 +39,7 @@ #include <linux/bpf_verifier.h> #include <linux/kernel.h> #include <linux/list.h> +#include <linux/rhashtable.h> #include <linux/skbuff.h> #include <linux/types.h> #include <linux/wait.h> @@ -114,6 +115,8 @@ enum pkt_vec { * @maps_in_use: number of currently offloaded maps * @map_elems_in_use: number of elements allocated to offloaded maps * + * @maps_neutral: hash table of offload-neutral maps (on pointer) + * * @adjust_head: adjust head capability * @adjust_head.flags: extra flags for adjust head * @adjust_head.off_min: minimal packet offset within buffer required @@ -133,6 +136,7 @@ enum pkt_vec { * @helpers.map_lookup: map lookup helper address * @helpers.map_update: map update helper address * @helpers.map_delete: map delete helper address + * @helpers.perf_event_output: output perf event to a ring buffer * * @pseudo_random: FW initialized the pseudo-random machinery (CSRs) */ @@ -150,6 +154,8 @@ struct nfp_app_bpf { unsigned int maps_in_use; unsigned int map_elems_in_use; + struct rhashtable maps_neutral; + struct nfp_bpf_cap_adjust_head { u32 flags; int off_min; @@ -171,6 +177,7 @@ struct nfp_app_bpf { u32 map_lookup; u32 map_update; u32 map_delete; + u32 perf_event_output; } helpers; bool pseudo_random; @@ -199,6 +206,14 @@ struct nfp_bpf_map { enum nfp_bpf_map_use use_map[]; }; +struct nfp_bpf_neutral_map { + struct rhash_head l; + struct bpf_map *ptr; + u32 count; +}; + +extern const struct rhashtable_params nfp_bpf_maps_neutral_params; + struct nfp_prog; struct nfp_insn_meta; typedef int (*instr_cb_t)(struct nfp_prog *, struct nfp_insn_meta *); @@ -236,6 +251,7 @@ struct nfp_bpf_reg_state { * @xadd_over_16bit: 16bit immediate is not guaranteed * @xadd_maybe_16bit: 16bit immediate is possible * @jmp_dst: destination info for jump instructions + * @jump_neg_op: jump instruction has inverted immediate, use ADD instead of SUB * @func_id: function id for call instructions * @arg1: arg1 for call instructions * @arg2: arg2 for call instructions @@ -264,7 +280,10 @@ struct nfp_insn_meta { bool xadd_maybe_16bit; }; /* jump */ - struct nfp_insn_meta *jmp_dst; + struct { + struct nfp_insn_meta *jmp_dst; + bool jump_neg_op; + }; /* function calls */ struct { u32 func_id; @@ -363,6 +382,8 @@ static inline bool is_mbpf_xadd(const struct nfp_insn_meta *meta) * @error: error code if something went wrong * @stack_depth: max stack depth from the verifier * @adjust_head_location: if program has single adjust head call - the insn no. + * @map_records_cnt: the number of map pointers recorded for this prog + * @map_records: the map record pointers from bpf->maps_neutral * @insns: list of BPF instruction wrappers (struct nfp_insn_meta) */ struct nfp_prog { @@ -386,6 +407,9 @@ struct nfp_prog { unsigned int stack_depth; unsigned int adjust_head_location; + unsigned int map_records_cnt; + struct nfp_bpf_neutral_map **map_records; + struct list_head insns; }; @@ -436,5 +460,7 @@ int nfp_bpf_ctrl_lookup_entry(struct bpf_offloaded_map *offmap, int nfp_bpf_ctrl_getnext_entry(struct bpf_offloaded_map *offmap, void *key, void *next_key); +int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb); + void nfp_bpf_ctrl_msg_rx(struct nfp_app *app, struct sk_buff *skb); #endif diff --git a/drivers/net/ethernet/netronome/nfp/bpf/offload.c b/drivers/net/ethernet/netronome/nfp/bpf/offload.c index 42d98792bd25..4db0ac1e42a8 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/offload.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/offload.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2016-2017 Netronome Systems, Inc. + * Copyright (C) 2016-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -57,6 +57,126 @@ #include "../nfp_net.h" static int +nfp_map_ptr_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog, + struct bpf_map *map) +{ + struct nfp_bpf_neutral_map *record; + int err; + + /* Map record paths are entered via ndo, update side is protected. */ + ASSERT_RTNL(); + + /* Reuse path - other offloaded program is already tracking this map. */ + record = rhashtable_lookup_fast(&bpf->maps_neutral, &map, + nfp_bpf_maps_neutral_params); + if (record) { + nfp_prog->map_records[nfp_prog->map_records_cnt++] = record; + record->count++; + return 0; + } + + /* Grab a single ref to the map for our record. The prog destroy ndo + * happens after free_used_maps(). + */ + map = bpf_map_inc(map, false); + if (IS_ERR(map)) + return PTR_ERR(map); + + record = kmalloc(sizeof(*record), GFP_KERNEL); + if (!record) { + err = -ENOMEM; + goto err_map_put; + } + + record->ptr = map; + record->count = 1; + + err = rhashtable_insert_fast(&bpf->maps_neutral, &record->l, + nfp_bpf_maps_neutral_params); + if (err) + goto err_free_rec; + + nfp_prog->map_records[nfp_prog->map_records_cnt++] = record; + + return 0; + +err_free_rec: + kfree(record); +err_map_put: + bpf_map_put(map); + return err; +} + +static void +nfp_map_ptrs_forget(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog) +{ + bool freed = false; + int i; + + ASSERT_RTNL(); + + for (i = 0; i < nfp_prog->map_records_cnt; i++) { + if (--nfp_prog->map_records[i]->count) { + nfp_prog->map_records[i] = NULL; + continue; + } + + WARN_ON(rhashtable_remove_fast(&bpf->maps_neutral, + &nfp_prog->map_records[i]->l, + nfp_bpf_maps_neutral_params)); + freed = true; + } + + if (freed) { + synchronize_rcu(); + + for (i = 0; i < nfp_prog->map_records_cnt; i++) + if (nfp_prog->map_records[i]) { + bpf_map_put(nfp_prog->map_records[i]->ptr); + kfree(nfp_prog->map_records[i]); + } + } + + kfree(nfp_prog->map_records); + nfp_prog->map_records = NULL; + nfp_prog->map_records_cnt = 0; +} + +static int +nfp_map_ptrs_record(struct nfp_app_bpf *bpf, struct nfp_prog *nfp_prog, + struct bpf_prog *prog) +{ + int i, cnt, err; + + /* Quickly count the maps we will have to remember */ + cnt = 0; + for (i = 0; i < prog->aux->used_map_cnt; i++) + if (bpf_map_offload_neutral(prog->aux->used_maps[i])) + cnt++; + if (!cnt) + return 0; + + nfp_prog->map_records = kmalloc_array(cnt, + sizeof(nfp_prog->map_records[0]), + GFP_KERNEL); + if (!nfp_prog->map_records) + return -ENOMEM; + + for (i = 0; i < prog->aux->used_map_cnt; i++) + if (bpf_map_offload_neutral(prog->aux->used_maps[i])) { + err = nfp_map_ptr_record(bpf, nfp_prog, + prog->aux->used_maps[i]); + if (err) { + nfp_map_ptrs_forget(bpf, nfp_prog); + return err; + } + } + WARN_ON(cnt != nfp_prog->map_records_cnt); + + return 0; +} + +static int nfp_prog_prepare(struct nfp_prog *nfp_prog, const struct bpf_insn *prog, unsigned int cnt) { @@ -151,7 +271,7 @@ static int nfp_bpf_translate(struct nfp_net *nn, struct bpf_prog *prog) prog->aux->offload->jited_len = nfp_prog->prog_len * sizeof(u64); prog->aux->offload->jited_image = nfp_prog->prog; - return 0; + return nfp_map_ptrs_record(nfp_prog->bpf, nfp_prog, prog); } static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog) @@ -159,6 +279,7 @@ static int nfp_bpf_destroy(struct nfp_net *nn, struct bpf_prog *prog) struct nfp_prog *nfp_prog = prog->aux->offload->dev_priv; kvfree(nfp_prog->prog); + nfp_map_ptrs_forget(nfp_prog->bpf, nfp_prog); nfp_prog_free(nfp_prog); return 0; @@ -320,6 +441,53 @@ int nfp_ndo_bpf(struct nfp_app *app, struct nfp_net *nn, struct netdev_bpf *bpf) } } +static unsigned long +nfp_bpf_perf_event_copy(void *dst, const void *src, + unsigned long off, unsigned long len) +{ + memcpy(dst, src + off, len); + return 0; +} + +int nfp_bpf_event_output(struct nfp_app_bpf *bpf, struct sk_buff *skb) +{ + struct cmsg_bpf_event *cbe = (void *)skb->data; + u32 pkt_size, data_size; + struct bpf_map *map; + + if (skb->len < sizeof(struct cmsg_bpf_event)) + goto err_drop; + + pkt_size = be32_to_cpu(cbe->pkt_size); + data_size = be32_to_cpu(cbe->data_size); + map = (void *)(unsigned long)be64_to_cpu(cbe->map_ptr); + + if (skb->len < sizeof(struct cmsg_bpf_event) + pkt_size + data_size) + goto err_drop; + if (cbe->hdr.ver != CMSG_MAP_ABI_VERSION) + goto err_drop; + + rcu_read_lock(); + if (!rhashtable_lookup_fast(&bpf->maps_neutral, &map, + nfp_bpf_maps_neutral_params)) { + rcu_read_unlock(); + pr_warn("perf event: dest map pointer %px not recognized, dropping event\n", + map); + goto err_drop; + } + + bpf_event_output(map, be32_to_cpu(cbe->cpu_id), + &cbe->data[round_up(pkt_size, 4)], data_size, + cbe->data, pkt_size, nfp_bpf_perf_event_copy); + rcu_read_unlock(); + + dev_consume_skb_any(skb); + return 0; +err_drop: + dev_kfree_skb_any(skb); + return -EINVAL; +} + static int nfp_net_bpf_load(struct nfp_net *nn, struct bpf_prog *prog, struct netlink_ext_ack *extack) diff --git a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c index 06ad53ce4ad9..e163f3cfa47d 100644 --- a/drivers/net/ethernet/netronome/nfp/bpf/verifier.c +++ b/drivers/net/ethernet/netronome/nfp/bpf/verifier.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2016-2017 Netronome Systems, Inc. + * Copyright (C) 2016-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -36,6 +36,8 @@ #include <linux/kernel.h> #include <linux/pkt_cls.h> +#include "../nfp_app.h" +#include "../nfp_main.h" #include "fw.h" #include "main.h" @@ -149,15 +151,6 @@ nfp_bpf_map_call_ok(const char *fname, struct bpf_verifier_env *env, return false; } - /* Rest of the checks is only if we re-parse the same insn */ - if (!meta->func_id) - return true; - - if (meta->arg1.map_ptr != reg1->map_ptr) { - pr_vlog(env, "%s: called for different map\n", fname); - return false; - } - return true; } @@ -216,6 +209,71 @@ nfp_bpf_check_call(struct nfp_prog *nfp_prog, struct bpf_verifier_env *env, pr_vlog(env, "bpf_get_prandom_u32(): FW doesn't support random number generation\n"); return -EOPNOTSUPP; + case BPF_FUNC_perf_event_output: + BUILD_BUG_ON(NFP_BPF_SCALAR_VALUE != SCALAR_VALUE || + NFP_BPF_MAP_VALUE != PTR_TO_MAP_VALUE || + NFP_BPF_STACK != PTR_TO_STACK || + NFP_BPF_PACKET_DATA != PTR_TO_PACKET); + + if (!bpf->helpers.perf_event_output) { + pr_vlog(env, "event_output: not supported by FW\n"); + return -EOPNOTSUPP; + } + + /* Force current CPU to make sure we can report the event + * wherever we get the control message from FW. + */ + if (reg3->var_off.mask & BPF_F_INDEX_MASK || + (reg3->var_off.value & BPF_F_INDEX_MASK) != + BPF_F_CURRENT_CPU) { + char tn_buf[48]; + + tnum_strn(tn_buf, sizeof(tn_buf), reg3->var_off); + pr_vlog(env, "event_output: must use BPF_F_CURRENT_CPU, var_off: %s\n", + tn_buf); + return -EOPNOTSUPP; + } + + /* Save space in meta, we don't care about arguments other + * than 4th meta, shove it into arg1. + */ + reg1 = cur_regs(env) + BPF_REG_4; + + if (reg1->type != SCALAR_VALUE /* NULL ptr */ && + reg1->type != PTR_TO_STACK && + reg1->type != PTR_TO_MAP_VALUE && + reg1->type != PTR_TO_PACKET) { + pr_vlog(env, "event_output: unsupported ptr type: %d\n", + reg1->type); + return -EOPNOTSUPP; + } + + if (reg1->type == PTR_TO_STACK && + !nfp_bpf_stack_arg_ok("event_output", env, reg1, NULL)) + return -EOPNOTSUPP; + + /* Warn user that on offload NFP may return success even if map + * is not going to accept the event, since the event output is + * fully async and device won't know the state of the map. + * There is also FW limitation on the event length. + * + * Lost events will not show up on the perf ring, driver + * won't see them at all. Events may also get reordered. + */ + dev_warn_once(&nfp_prog->bpf->app->pf->pdev->dev, + "bpf: note: return codes and behavior of bpf_event_output() helper differs for offloaded programs!\n"); + pr_vlog(env, "warning: return codes and behavior of event_output helper differ for offload!\n"); + + if (!meta->func_id) + break; + + if (reg1->type != meta->arg1.type) { + pr_vlog(env, "event_output: ptr type changed: %d %d\n", + meta->arg1.type, reg1->type); + return -EINVAL; + } + break; + default: pr_vlog(env, "unsupported function id: %d\n", func_id); return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/flower/main.h b/drivers/net/ethernet/netronome/nfp/flower/main.h index c67e1b54c614..733ff53cc601 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/main.h +++ b/drivers/net/ethernet/netronome/nfp/flower/main.h @@ -47,6 +47,7 @@ struct net_device; struct nfp_app; +#define NFP_FL_STATS_CTX_DONT_CARE cpu_to_be32(0xffffffff) #define NFP_FL_STATS_ENTRY_RS BIT(20) #define NFP_FL_STATS_ELEM_RS 4 #define NFP_FL_REPEATED_HASH_MAX BIT(17) @@ -189,9 +190,11 @@ struct nfp_fl_payload { spinlock_t lock; /* lock stats */ struct nfp_fl_stats stats; __be32 nfp_tun_ipv4_addr; + struct net_device *ingress_dev; char *unmasked_data; char *mask_data; char *action_data; + bool ingress_offload; }; struct nfp_fl_stats_frame { @@ -216,12 +219,14 @@ int nfp_flower_compile_action(struct tc_cls_flower_offload *flow, struct nfp_fl_payload *nfp_flow); int nfp_compile_flow_metadata(struct nfp_app *app, struct tc_cls_flower_offload *flow, - struct nfp_fl_payload *nfp_flow); + struct nfp_fl_payload *nfp_flow, + struct net_device *netdev); int nfp_modify_flow_metadata(struct nfp_app *app, struct nfp_fl_payload *nfp_flow); struct nfp_fl_payload * -nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie); +nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie, + struct net_device *netdev, __be32 host_ctx); struct nfp_fl_payload * nfp_flower_remove_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie); diff --git a/drivers/net/ethernet/netronome/nfp/flower/metadata.c b/drivers/net/ethernet/netronome/nfp/flower/metadata.c index db977cf8e933..21668aa435e8 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/metadata.c +++ b/drivers/net/ethernet/netronome/nfp/flower/metadata.c @@ -99,14 +99,18 @@ static int nfp_get_stats_entry(struct nfp_app *app, u32 *stats_context_id) /* Must be called with either RTNL or rcu_read_lock */ struct nfp_fl_payload * -nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie) +nfp_flower_search_fl_table(struct nfp_app *app, unsigned long tc_flower_cookie, + struct net_device *netdev, __be32 host_ctx) { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload *flower_entry; hash_for_each_possible_rcu(priv->flow_table, flower_entry, link, tc_flower_cookie) - if (flower_entry->tc_flower_cookie == tc_flower_cookie) + if (flower_entry->tc_flower_cookie == tc_flower_cookie && + (!netdev || flower_entry->ingress_dev == netdev) && + (host_ctx == NFP_FL_STATS_CTX_DONT_CARE || + flower_entry->meta.host_ctx_id == host_ctx)) return flower_entry; return NULL; @@ -121,13 +125,11 @@ nfp_flower_update_stats(struct nfp_app *app, struct nfp_fl_stats_frame *stats) flower_cookie = be64_to_cpu(stats->stats_cookie); rcu_read_lock(); - nfp_flow = nfp_flower_search_fl_table(app, flower_cookie); + nfp_flow = nfp_flower_search_fl_table(app, flower_cookie, NULL, + stats->stats_con_id); if (!nfp_flow) goto exit_rcu_unlock; - if (nfp_flow->meta.host_ctx_id != stats->stats_con_id) - goto exit_rcu_unlock; - spin_lock(&nfp_flow->lock); nfp_flow->stats.pkts += be32_to_cpu(stats->pkt_count); nfp_flow->stats.bytes += be64_to_cpu(stats->byte_count); @@ -317,7 +319,8 @@ nfp_check_mask_remove(struct nfp_app *app, char *mask_data, u32 mask_len, int nfp_compile_flow_metadata(struct nfp_app *app, struct tc_cls_flower_offload *flow, - struct nfp_fl_payload *nfp_flow) + struct nfp_fl_payload *nfp_flow, + struct net_device *netdev) { struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload *check_entry; @@ -348,7 +351,8 @@ int nfp_compile_flow_metadata(struct nfp_app *app, nfp_flow->stats.bytes = 0; nfp_flow->stats.used = jiffies; - check_entry = nfp_flower_search_fl_table(app, flow->cookie); + check_entry = nfp_flower_search_fl_table(app, flow->cookie, netdev, + NFP_FL_STATS_CTX_DONT_CARE); if (check_entry) { if (nfp_release_stats_entry(app, stats_cxt)) return -EINVAL; diff --git a/drivers/net/ethernet/netronome/nfp/flower/offload.c b/drivers/net/ethernet/netronome/nfp/flower/offload.c index 114d2ab02a38..70ec9d821b91 100644 --- a/drivers/net/ethernet/netronome/nfp/flower/offload.c +++ b/drivers/net/ethernet/netronome/nfp/flower/offload.c @@ -345,7 +345,7 @@ nfp_flower_calculate_key_layers(struct nfp_app *app, } static struct nfp_fl_payload * -nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) +nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer, bool egress) { struct nfp_fl_payload *flow_pay; @@ -371,6 +371,8 @@ nfp_flower_allocate_new(struct nfp_fl_key_ls *key_layer) flow_pay->meta.flags = 0; spin_lock_init(&flow_pay->lock); + flow_pay->ingress_offload = !egress; + return flow_pay; err_free_mask: @@ -402,8 +404,20 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, struct nfp_flower_priv *priv = app->priv; struct nfp_fl_payload *flow_pay; struct nfp_fl_key_ls *key_layer; + struct net_device *ingr_dev; int err; + ingr_dev = egress ? NULL : netdev; + flow_pay = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev, + NFP_FL_STATS_CTX_DONT_CARE); + if (flow_pay) { + /* Ignore as duplicate if it has been added by different cb. */ + if (flow_pay->ingress_offload && egress) + return 0; + else + return -EOPNOTSUPP; + } + key_layer = kmalloc(sizeof(*key_layer), GFP_KERNEL); if (!key_layer) return -ENOMEM; @@ -413,12 +427,14 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_free_key_ls; - flow_pay = nfp_flower_allocate_new(key_layer); + flow_pay = nfp_flower_allocate_new(key_layer, egress); if (!flow_pay) { err = -ENOMEM; goto err_free_key_ls; } + flow_pay->ingress_dev = egress ? NULL : netdev; + err = nfp_flower_compile_flow_match(flow, key_layer, netdev, flow_pay, tun_type); if (err) @@ -428,7 +444,8 @@ nfp_flower_add_offload(struct nfp_app *app, struct net_device *netdev, if (err) goto err_destroy_flow; - err = nfp_compile_flow_metadata(app, flow, flow_pay); + err = nfp_compile_flow_metadata(app, flow, flow_pay, + flow_pay->ingress_dev); if (err) goto err_destroy_flow; @@ -462,6 +479,7 @@ err_free_key_ls: * @app: Pointer to the APP handle * @netdev: netdev structure. * @flow: TC flower classifier offload structure + * @egress: Netdev is the egress dev. * * Removes a flow from the repeated hash structure and clears the * action payload. @@ -470,15 +488,18 @@ err_free_key_ls: */ static int nfp_flower_del_offload(struct nfp_app *app, struct net_device *netdev, - struct tc_cls_flower_offload *flow) + struct tc_cls_flower_offload *flow, bool egress) { struct nfp_port *port = nfp_port_from_netdev(netdev); struct nfp_fl_payload *nfp_flow; + struct net_device *ingr_dev; int err; - nfp_flow = nfp_flower_search_fl_table(app, flow->cookie); + ingr_dev = egress ? NULL : netdev; + nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev, + NFP_FL_STATS_CTX_DONT_CARE); if (!nfp_flow) - return -ENOENT; + return egress ? 0 : -ENOENT; err = nfp_modify_flow_metadata(app, nfp_flow); if (err) @@ -505,7 +526,9 @@ err_free_flow: /** * nfp_flower_get_stats() - Populates flow stats obtained from hardware. * @app: Pointer to the APP handle + * @netdev: Netdev structure. * @flow: TC flower classifier offload structure + * @egress: Netdev is the egress dev. * * Populates a flow statistics structure which which corresponds to a * specific flow. @@ -513,14 +536,21 @@ err_free_flow: * Return: negative value on error, 0 if stats populated successfully. */ static int -nfp_flower_get_stats(struct nfp_app *app, struct tc_cls_flower_offload *flow) +nfp_flower_get_stats(struct nfp_app *app, struct net_device *netdev, + struct tc_cls_flower_offload *flow, bool egress) { struct nfp_fl_payload *nfp_flow; + struct net_device *ingr_dev; - nfp_flow = nfp_flower_search_fl_table(app, flow->cookie); + ingr_dev = egress ? NULL : netdev; + nfp_flow = nfp_flower_search_fl_table(app, flow->cookie, ingr_dev, + NFP_FL_STATS_CTX_DONT_CARE); if (!nfp_flow) return -EINVAL; + if (nfp_flow->ingress_offload && egress) + return 0; + spin_lock_bh(&nfp_flow->lock); tcf_exts_stats_update(flow->exts, nfp_flow->stats.bytes, nfp_flow->stats.pkts, nfp_flow->stats.used); @@ -543,9 +573,9 @@ nfp_flower_repr_offload(struct nfp_app *app, struct net_device *netdev, case TC_CLSFLOWER_REPLACE: return nfp_flower_add_offload(app, netdev, flower, egress); case TC_CLSFLOWER_DESTROY: - return nfp_flower_del_offload(app, netdev, flower); + return nfp_flower_del_offload(app, netdev, flower, egress); case TC_CLSFLOWER_STATS: - return nfp_flower_get_stats(app, flower); + return nfp_flower_get_stats(app, netdev, flower, egress); } return -EOPNOTSUPP; diff --git a/drivers/net/ethernet/netronome/nfp/nfp_app.c b/drivers/net/ethernet/netronome/nfp/nfp_app.c index 6aedef0ad433..0e0253c7e17b 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_app.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_app.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this diff --git a/drivers/net/ethernet/netronome/nfp/nfp_main.c b/drivers/net/ethernet/netronome/nfp/nfp_main.c index c4b1f344b4da..0ade122805ad 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_main.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_main.c @@ -486,6 +486,10 @@ static int nfp_pci_probe(struct pci_dev *pdev, goto err_disable_msix; } + err = nfp_resource_table_init(pf->cpp); + if (err) + goto err_cpp_free; + pf->hwinfo = nfp_hwinfo_read(pf->cpp); dev_info(&pdev->dev, "Assembly: %s%s%s-%s CPLD: %s\n", @@ -548,6 +552,7 @@ err_fw_unload: vfree(pf->dumpspec); err_hwinfo_free: kfree(pf->hwinfo); +err_cpp_free: nfp_cpp_free(pf->cpp); err_disable_msix: destroy_workqueue(pf->wq); diff --git a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c index 1eb6549f2a54..d9111c077699 100644 --- a/drivers/net/ethernet/netronome/nfp/nfp_net_common.c +++ b/drivers/net/ethernet/netronome/nfp/nfp_net_common.c @@ -1722,7 +1722,7 @@ static int nfp_net_rx(struct nfp_net_rx_ring *rx_ring, int budget) act = bpf_prog_run_xdp(xdp_prog, &xdp); - pkt_len -= xdp.data - orig_data; + pkt_len = xdp.data_end - xdp.data; pkt_off += xdp.data - orig_data; switch (act) { diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h index ced62d112aa2..f44d0a857314 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp.h @@ -94,6 +94,8 @@ int nfp_nsp_read_sensors(struct nfp_nsp *state, unsigned int sensor_mask, /* MAC Statistics Accumulator */ #define NFP_RESOURCE_MAC_STATISTICS "mac.stat" +int nfp_resource_table_init(struct nfp_cpp *cpp); + struct nfp_resource * nfp_resource_acquire(struct nfp_cpp *cpp, const char *name); diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c index cd678323bacb..a0e336bd1d85 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp6000_pcie.c @@ -1330,6 +1330,7 @@ struct nfp_cpp *nfp_cpp_from_nfp6000_pcie(struct pci_dev *pdev) /* Finished with card initialization. */ dev_info(&pdev->dev, "Netronome Flow Processor NFP4000/NFP6000 PCIe Card Probe\n"); + pcie_print_link_status(pdev); nfp = kzalloc(sizeof(*nfp), GFP_KERNEL); if (!nfp) { diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h index c8f2c064cce3..4e19add1c539 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_cpp.h @@ -295,6 +295,8 @@ void nfp_cpp_mutex_free(struct nfp_cpp_mutex *mutex); int nfp_cpp_mutex_lock(struct nfp_cpp_mutex *mutex); int nfp_cpp_mutex_unlock(struct nfp_cpp_mutex *mutex); int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex); +int nfp_cpp_mutex_reclaim(struct nfp_cpp *cpp, int target, + unsigned long long address); /** * nfp_cppcore_pcie_unit() - Get PCI Unit of a CPP handle diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c index cb28ac03e4ca..c88bf673cb76 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_mutex.c @@ -59,6 +59,11 @@ static u32 nfp_mutex_unlocked(u16 interface) return (u32)interface << 16 | 0x0000; } +static u32 nfp_mutex_owner(u32 val) +{ + return val >> 16; +} + static bool nfp_mutex_is_locked(u32 val) { return (val & 0xffff) == 0x000f; @@ -351,3 +356,43 @@ int nfp_cpp_mutex_trylock(struct nfp_cpp_mutex *mutex) return nfp_mutex_is_locked(tmp) ? -EBUSY : -EINVAL; } + +/** + * nfp_cpp_mutex_reclaim() - Unlock mutex if held by local endpoint + * @cpp: NFP CPP handle + * @target: NFP CPP target ID (ie NFP_CPP_TARGET_CLS or NFP_CPP_TARGET_MU) + * @address: Offset into the address space of the NFP CPP target ID + * + * Release lock if held by local system. Extreme care is advised, call only + * when no local lock users can exist. + * + * Return: 0 if the lock was OK, 1 if locked by us, -errno on invalid mutex + */ +int nfp_cpp_mutex_reclaim(struct nfp_cpp *cpp, int target, + unsigned long long address) +{ + const u32 mur = NFP_CPP_ID(target, 3, 0); /* atomic_read */ + const u32 muw = NFP_CPP_ID(target, 4, 0); /* atomic_write */ + u16 interface = nfp_cpp_interface(cpp); + int err; + u32 tmp; + + err = nfp_cpp_mutex_validate(interface, &target, address); + if (err) + return err; + + /* Check lock */ + err = nfp_cpp_readl(cpp, mur, address, &tmp); + if (err < 0) + return err; + + if (nfp_mutex_is_unlocked(tmp) || nfp_mutex_owner(tmp) != interface) + return 0; + + /* Bust the lock */ + err = nfp_cpp_writel(cpp, muw, address, nfp_mutex_unlocked(interface)); + if (err < 0) + return err; + + return 1; +} diff --git a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c index 7e14725055c7..2dd89dba9311 100644 --- a/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c +++ b/drivers/net/ethernet/netronome/nfp/nfpcore/nfp_resource.c @@ -338,3 +338,62 @@ u64 nfp_resource_size(struct nfp_resource *res) { return res->size; } + +/** + * nfp_resource_table_init() - Run initial checks on the resource table + * @cpp: NFP CPP handle + * + * Start-of-day init procedure for resource table. Must be called before + * any local resource table users may exist. + * + * Return: 0 on success, -errno on failure + */ +int nfp_resource_table_init(struct nfp_cpp *cpp) +{ + struct nfp_cpp_mutex *dev_mutex; + int i, err; + + err = nfp_cpp_mutex_reclaim(cpp, NFP_RESOURCE_TBL_TARGET, + NFP_RESOURCE_TBL_BASE); + if (err < 0) { + nfp_err(cpp, "Error: failed to reclaim resource table mutex\n"); + return err; + } + if (err) + nfp_warn(cpp, "Warning: busted main resource table mutex\n"); + + dev_mutex = nfp_cpp_mutex_alloc(cpp, NFP_RESOURCE_TBL_TARGET, + NFP_RESOURCE_TBL_BASE, + NFP_RESOURCE_TBL_KEY); + if (!dev_mutex) + return -ENOMEM; + + if (nfp_cpp_mutex_lock(dev_mutex)) { + nfp_err(cpp, "Error: failed to claim resource table mutex\n"); + nfp_cpp_mutex_free(dev_mutex); + return -EINVAL; + } + + /* Resource 0 is the dev_mutex, start from 1 */ + for (i = 1; i < NFP_RESOURCE_TBL_ENTRIES; i++) { + u64 addr = NFP_RESOURCE_TBL_BASE + + sizeof(struct nfp_resource_entry) * i; + + err = nfp_cpp_mutex_reclaim(cpp, NFP_RESOURCE_TBL_TARGET, addr); + if (err < 0) { + nfp_err(cpp, + "Error: failed to reclaim resource %d mutex\n", + i); + goto err_unlock; + } + if (err) + nfp_warn(cpp, "Warning: busted resource %d mutex\n", i); + } + + err = 0; +err_unlock: + nfp_cpp_mutex_unlock(dev_mutex); + nfp_cpp_mutex_free(dev_mutex); + + return err; +} diff --git a/drivers/net/ethernet/qlogic/qed/qed.h b/drivers/net/ethernet/qlogic/qed/qed.h index e07460a68d30..adcff495466e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed.h +++ b/drivers/net/ethernet/qlogic/qed/qed.h @@ -439,6 +439,59 @@ struct qed_fw_data { u32 init_ops_size; }; +enum qed_mf_mode_bit { + /* Supports PF-classification based on tag */ + QED_MF_OVLAN_CLSS, + + /* Supports PF-classification based on MAC */ + QED_MF_LLH_MAC_CLSS, + + /* Supports PF-classification based on protocol type */ + QED_MF_LLH_PROTO_CLSS, + + /* Requires a default PF to be set */ + QED_MF_NEED_DEF_PF, + + /* Allow LL2 to multicast/broadcast */ + QED_MF_LL2_NON_UNICAST, + + /* Allow Cross-PF [& child VFs] Tx-switching */ + QED_MF_INTER_PF_SWITCH, + + /* Unified Fabtic Port support enabled */ + QED_MF_UFP_SPECIFIC, + + /* Disable Accelerated Receive Flow Steering (aRFS) */ + QED_MF_DISABLE_ARFS, + + /* Use vlan for steering */ + QED_MF_8021Q_TAGGING, + + /* Use stag for steering */ + QED_MF_8021AD_TAGGING, + + /* Allow DSCP to TC mapping */ + QED_MF_DSCP_TO_TC_MAP, +}; + +enum qed_ufp_mode { + QED_UFP_MODE_ETS, + QED_UFP_MODE_VNIC_BW, + QED_UFP_MODE_UNKNOWN +}; + +enum qed_ufp_pri_type { + QED_UFP_PRI_OS, + QED_UFP_PRI_VNIC, + QED_UFP_PRI_UNKNOWN +}; + +struct qed_ufp_info { + enum qed_ufp_pri_type pri_type; + enum qed_ufp_mode mode; + u8 tc; +}; + enum BAR_ID { BAR_ID_0, /* used for GRC */ BAR_ID_1 /* Used for doorbells */ @@ -547,6 +600,8 @@ struct qed_hwfn { struct qed_dcbx_info *p_dcbx_info; + struct qed_ufp_info ufp_info; + struct qed_dmae_info dmae_info; /* QM init */ @@ -669,10 +724,8 @@ struct qed_dev { u8 num_funcs_in_port; u8 path_id; - enum qed_mf_mode mf_mode; -#define IS_MF_DEFAULT(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_DEFAULT) -#define IS_MF_SI(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_NPAR) -#define IS_MF_SD(_p_hwfn) (((_p_hwfn)->cdev)->mf_mode == QED_MF_OVLAN) + + unsigned long mf_bits; int pcie_width; int pcie_speed; diff --git a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c index 449777f21237..8f31406ec894 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dcbx.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dcbx.c @@ -274,8 +274,8 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, u32 pri_tc_tbl, int count, u8 dcbx_version) { enum dcbx_protocol_type type; + bool enable, ieee, eth_tlv; u8 tc, priority_map; - bool enable, ieee; u16 protocol_id; int priority; int i; @@ -283,6 +283,7 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, DP_VERBOSE(p_hwfn, QED_MSG_DCB, "Num APP entries = %d\n", count); ieee = (dcbx_version == DCBX_CONFIG_VERSION_IEEE); + eth_tlv = false; /* Parse APP TLV */ for (i = 0; i < count; i++) { protocol_id = QED_MFW_GET_FIELD(p_tbl[i].entry, @@ -304,13 +305,22 @@ qed_dcbx_process_tlv(struct qed_hwfn *p_hwfn, * indication, but we only got here if there was an * app tlv for the protocol, so dcbx must be enabled. */ - enable = !(type == DCBX_PROTOCOL_ETH); + if (type == DCBX_PROTOCOL_ETH) { + enable = false; + eth_tlv = true; + } else { + enable = true; + } qed_dcbx_update_app_info(p_data, p_hwfn, enable, priority, tc, type); } } + /* If Eth TLV is not detected, use UFP TC as default TC */ + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) && !eth_tlv) + p_data->arr[DCBX_PROTOCOL_ETH].tc = p_hwfn->ufp_info.tc; + /* Update ramrod protocol data and hw_info fields * with default info when corresponding APP TLV's are not detected. * The enabled field has a different logic for ethernet as only for diff --git a/drivers/net/ethernet/qlogic/qed/qed_debug.c b/drivers/net/ethernet/qlogic/qed/qed_debug.c index 4926c5532fba..39124b594a36 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_debug.c +++ b/drivers/net/ethernet/qlogic/qed/qed_debug.c @@ -419,6 +419,7 @@ struct phy_defs { #define NUM_RSS_MEM_TYPES 5 #define NUM_BIG_RAM_TYPES 3 +#define BIG_RAM_NAME_LEN 3 #define NUM_PHY_TBUS_ADDRESSES 2048 #define PHY_DUMP_SIZE_DWORDS (NUM_PHY_TBUS_ADDRESSES / 2) @@ -3650,8 +3651,8 @@ static u32 qed_grc_dump_big_ram(struct qed_hwfn *p_hwfn, BIT(big_ram->is_256b_bit_offset[dev_data->chip_id]) ? 256 : 128; - strscpy(type_name, big_ram->instance_name, sizeof(type_name)); - strscpy(mem_name, big_ram->instance_name, sizeof(mem_name)); + strncpy(type_name, big_ram->instance_name, BIG_RAM_NAME_LEN); + strncpy(mem_name, big_ram->instance_name, BIG_RAM_NAME_LEN); /* Dump memory header */ offset += qed_grc_dump_mem_hdr(p_hwfn, @@ -7778,6 +7779,57 @@ int qed_dbg_igu_fifo_size(struct qed_dev *cdev) return qed_dbg_feature_size(cdev, DBG_FEATURE_IGU_FIFO); } +int qed_dbg_nvm_image_length(struct qed_hwfn *p_hwfn, + enum qed_nvm_images image_id, u32 *length) +{ + struct qed_nvm_image_att image_att; + int rc; + + *length = 0; + rc = qed_mcp_get_nvm_image_att(p_hwfn, image_id, &image_att); + if (rc) + return rc; + + *length = image_att.length; + + return rc; +} + +int qed_dbg_nvm_image(struct qed_dev *cdev, void *buffer, + u32 *num_dumped_bytes, enum qed_nvm_images image_id) +{ + struct qed_hwfn *p_hwfn = + &cdev->hwfns[cdev->dbg_params.engine_for_debug]; + u32 len_rounded, i; + __be32 val; + int rc; + + *num_dumped_bytes = 0; + rc = qed_dbg_nvm_image_length(p_hwfn, image_id, &len_rounded); + if (rc) + return rc; + + DP_NOTICE(p_hwfn->cdev, + "Collecting a debug feature [\"nvram image %d\"]\n", + image_id); + + len_rounded = roundup(len_rounded, sizeof(u32)); + rc = qed_mcp_get_nvm_image(p_hwfn, image_id, buffer, len_rounded); + if (rc) + return rc; + + /* QED_NVM_IMAGE_NVM_META image is not swapped like other images */ + if (image_id != QED_NVM_IMAGE_NVM_META) + for (i = 0; i < len_rounded; i += 4) { + val = cpu_to_be32(*(u32 *)(buffer + i)); + *(u32 *)(buffer + i) = val; + } + + *num_dumped_bytes = len_rounded; + + return rc; +} + int qed_dbg_protection_override(struct qed_dev *cdev, void *buffer, u32 *num_dumped_bytes) { @@ -7831,6 +7883,9 @@ enum debug_print_features { IGU_FIFO = 6, PHY = 7, FW_ASSERTS = 8, + NVM_CFG1 = 9, + DEFAULT_CFG = 10, + NVM_META = 11, }; static u32 qed_calc_regdump_header(enum debug_print_features feature, @@ -7965,13 +8020,61 @@ int qed_dbg_all_data(struct qed_dev *cdev, void *buffer) DP_ERR(cdev, "qed_dbg_mcp_trace failed. rc = %d\n", rc); } + /* nvm cfg1 */ + rc = qed_dbg_nvm_image(cdev, + (u8 *)buffer + offset + REGDUMP_HEADER_SIZE, + &feature_size, QED_NVM_IMAGE_NVM_CFG1); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(NVM_CFG1, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else if (rc != -ENOENT) { + DP_ERR(cdev, + "qed_dbg_nvm_image failed for image %d (%s), rc = %d\n", + QED_NVM_IMAGE_NVM_CFG1, "QED_NVM_IMAGE_NVM_CFG1", rc); + } + + /* nvm default */ + rc = qed_dbg_nvm_image(cdev, + (u8 *)buffer + offset + REGDUMP_HEADER_SIZE, + &feature_size, QED_NVM_IMAGE_DEFAULT_CFG); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(DEFAULT_CFG, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else if (rc != -ENOENT) { + DP_ERR(cdev, + "qed_dbg_nvm_image failed for image %d (%s), rc = %d\n", + QED_NVM_IMAGE_DEFAULT_CFG, "QED_NVM_IMAGE_DEFAULT_CFG", + rc); + } + + /* nvm meta */ + rc = qed_dbg_nvm_image(cdev, + (u8 *)buffer + offset + REGDUMP_HEADER_SIZE, + &feature_size, QED_NVM_IMAGE_NVM_META); + if (!rc) { + *(u32 *)((u8 *)buffer + offset) = + qed_calc_regdump_header(NVM_META, cur_engine, + feature_size, omit_engine); + offset += (feature_size + REGDUMP_HEADER_SIZE); + } else if (rc != -ENOENT) { + DP_ERR(cdev, + "qed_dbg_nvm_image failed for image %d (%s), rc = %d\n", + QED_NVM_IMAGE_NVM_META, "QED_NVM_IMAGE_NVM_META", rc); + } + return 0; } int qed_dbg_all_data_size(struct qed_dev *cdev) { + struct qed_hwfn *p_hwfn = + &cdev->hwfns[cdev->dbg_params.engine_for_debug]; + u32 regs_len = 0, image_len = 0; u8 cur_engine, org_engine; - u32 regs_len = 0; org_engine = qed_get_debug_engine(cdev); for (cur_engine = 0; cur_engine < cdev->num_hwfns; cur_engine++) { @@ -7993,6 +8096,15 @@ int qed_dbg_all_data_size(struct qed_dev *cdev) /* Engine common */ regs_len += REGDUMP_HEADER_SIZE + qed_dbg_mcp_trace_size(cdev); + qed_dbg_nvm_image_length(p_hwfn, QED_NVM_IMAGE_NVM_CFG1, &image_len); + if (image_len) + regs_len += REGDUMP_HEADER_SIZE + image_len; + qed_dbg_nvm_image_length(p_hwfn, QED_NVM_IMAGE_DEFAULT_CFG, &image_len); + if (image_len) + regs_len += REGDUMP_HEADER_SIZE + image_len; + qed_dbg_nvm_image_length(p_hwfn, QED_NVM_IMAGE_NVM_META, &image_len); + if (image_len) + regs_len += REGDUMP_HEADER_SIZE + image_len; return regs_len; } diff --git a/drivers/net/ethernet/qlogic/qed/qed_dev.c b/drivers/net/ethernet/qlogic/qed/qed_dev.c index d2ad5e92c74f..560528962658 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_dev.c +++ b/drivers/net/ethernet/qlogic/qed/qed_dev.c @@ -1149,18 +1149,10 @@ static int qed_calc_hw_mode(struct qed_hwfn *p_hwfn) return -EINVAL; } - switch (p_hwfn->cdev->mf_mode) { - case QED_MF_DEFAULT: - case QED_MF_NPAR: - hw_mode |= 1 << MODE_MF_SI; - break; - case QED_MF_OVLAN: + if (test_bit(QED_MF_OVLAN_CLSS, &p_hwfn->cdev->mf_bits)) hw_mode |= 1 << MODE_MF_SD; - break; - default: - DP_NOTICE(p_hwfn, "Unsupported MF mode, init as DEFAULT\n"); + else hw_mode |= 1 << MODE_MF_SI; - } hw_mode |= 1 << MODE_ASIC; @@ -1507,6 +1499,11 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn, STORE_RT_REG(p_hwfn, NIG_REG_LLH_FUNC_TAG_EN_RT_OFFSET, 1); STORE_RT_REG(p_hwfn, NIG_REG_LLH_FUNC_TAG_VALUE_RT_OFFSET, p_hwfn->hw_info.ovlan); + + DP_VERBOSE(p_hwfn, NETIF_MSG_HW, + "Configuring LLH_FUNC_FILTER_HDR_SEL\n"); + STORE_RT_REG(p_hwfn, NIG_REG_LLH_FUNC_FILTER_HDR_SEL_RT_OFFSET, + 1); } /* Enable classification by MAC if needed */ @@ -1557,7 +1554,6 @@ static int qed_hw_init_pf(struct qed_hwfn *p_hwfn, /* send function start command */ rc = qed_sp_pf_start(p_hwfn, p_ptt, p_tunn, - p_hwfn->cdev->mf_mode, allow_npar_tx_switch); if (rc) { DP_NOTICE(p_hwfn, "Function start ramrod failed\n"); @@ -1644,6 +1640,7 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) bool b_default_mtu = true; struct qed_hwfn *p_hwfn; int rc = 0, mfw_rc, i; + u16 ether_type; if ((p_params->int_mode == QED_INT_MODE_MSI) && (cdev->num_hwfns > 1)) { DP_NOTICE(cdev, "MSI mode is not supported for CMT devices\n"); @@ -1677,6 +1674,24 @@ int qed_hw_init(struct qed_dev *cdev, struct qed_hw_init_params *p_params) if (rc) return rc; + if (IS_PF(cdev) && (test_bit(QED_MF_8021Q_TAGGING, + &cdev->mf_bits) || + test_bit(QED_MF_8021AD_TAGGING, + &cdev->mf_bits))) { + if (test_bit(QED_MF_8021Q_TAGGING, &cdev->mf_bits)) + ether_type = ETH_P_8021Q; + else + ether_type = ETH_P_8021AD; + STORE_RT_REG(p_hwfn, PRS_REG_TAG_ETHERTYPE_0_RT_OFFSET, + ether_type); + STORE_RT_REG(p_hwfn, NIG_REG_TAG_ETHERTYPE_0_RT_OFFSET, + ether_type); + STORE_RT_REG(p_hwfn, PBF_REG_TAG_ETHERTYPE_0_RT_OFFSET, + ether_type); + STORE_RT_REG(p_hwfn, DORQ_REG_TAG1_ETHERTYPE_RT_OFFSET, + ether_type); + } + qed_fill_load_req_params(&load_req_params, p_params->p_drv_load_params); rc = qed_mcp_load_req(p_hwfn, p_hwfn->p_main_ptt, @@ -2639,31 +2654,57 @@ static int qed_hw_get_nvm_info(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) link->pause.autoneg, p_caps->default_eee, p_caps->eee_lpi_timer); - /* Read Multi-function information from shmem */ - addr = MCP_REG_SCRATCH + nvm_cfg1_offset + - offsetof(struct nvm_cfg1, glob) + - offsetof(struct nvm_cfg1_glob, generic_cont0); + if (IS_LEAD_HWFN(p_hwfn)) { + struct qed_dev *cdev = p_hwfn->cdev; - generic_cont0 = qed_rd(p_hwfn, p_ptt, addr); + /* Read Multi-function information from shmem */ + addr = MCP_REG_SCRATCH + nvm_cfg1_offset + + offsetof(struct nvm_cfg1, glob) + + offsetof(struct nvm_cfg1_glob, generic_cont0); - mf_mode = (generic_cont0 & NVM_CFG1_GLOB_MF_MODE_MASK) >> - NVM_CFG1_GLOB_MF_MODE_OFFSET; + generic_cont0 = qed_rd(p_hwfn, p_ptt, addr); - switch (mf_mode) { - case NVM_CFG1_GLOB_MF_MODE_MF_ALLOWED: - p_hwfn->cdev->mf_mode = QED_MF_OVLAN; - break; - case NVM_CFG1_GLOB_MF_MODE_NPAR1_0: - p_hwfn->cdev->mf_mode = QED_MF_NPAR; - break; - case NVM_CFG1_GLOB_MF_MODE_DEFAULT: - p_hwfn->cdev->mf_mode = QED_MF_DEFAULT; - break; + mf_mode = (generic_cont0 & NVM_CFG1_GLOB_MF_MODE_MASK) >> + NVM_CFG1_GLOB_MF_MODE_OFFSET; + + switch (mf_mode) { + case NVM_CFG1_GLOB_MF_MODE_MF_ALLOWED: + cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS); + break; + case NVM_CFG1_GLOB_MF_MODE_UFP: + cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS) | + BIT(QED_MF_LLH_PROTO_CLSS) | + BIT(QED_MF_UFP_SPECIFIC) | + BIT(QED_MF_8021Q_TAGGING); + break; + case NVM_CFG1_GLOB_MF_MODE_BD: + cdev->mf_bits = BIT(QED_MF_OVLAN_CLSS) | + BIT(QED_MF_LLH_PROTO_CLSS) | + BIT(QED_MF_8021AD_TAGGING); + break; + case NVM_CFG1_GLOB_MF_MODE_NPAR1_0: + cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | + BIT(QED_MF_LLH_PROTO_CLSS) | + BIT(QED_MF_LL2_NON_UNICAST) | + BIT(QED_MF_INTER_PF_SWITCH); + break; + case NVM_CFG1_GLOB_MF_MODE_DEFAULT: + cdev->mf_bits = BIT(QED_MF_LLH_MAC_CLSS) | + BIT(QED_MF_LLH_PROTO_CLSS) | + BIT(QED_MF_LL2_NON_UNICAST); + if (QED_IS_BB(p_hwfn->cdev)) + cdev->mf_bits |= BIT(QED_MF_NEED_DEF_PF); + break; + } + + DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", + cdev->mf_bits); } - DP_INFO(p_hwfn, "Multi function mode is %08x\n", - p_hwfn->cdev->mf_mode); - /* Read Multi-function information from shmem */ + DP_INFO(p_hwfn, "Multi function mode is 0x%lx\n", + p_hwfn->cdev->mf_bits); + + /* Read device capabilities information from shmem */ addr = MCP_REG_SCRATCH + nvm_cfg1_offset + offsetof(struct nvm_cfg1, glob) + offsetof(struct nvm_cfg1_glob, device_capabilities); @@ -2856,6 +2897,8 @@ qed_get_hw_info(struct qed_hwfn *p_hwfn, qed_mcp_cmd_port_init(p_hwfn, p_ptt); qed_get_eee_caps(p_hwfn, p_ptt); + + qed_mcp_read_ufp_config(p_hwfn, p_ptt); } if (qed_mcp_is_init(p_hwfn)) { @@ -3462,7 +3505,7 @@ int qed_llh_add_mac_filter(struct qed_hwfn *p_hwfn, u32 high = 0, low = 0, en; int i; - if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn))) + if (!test_bit(QED_MF_LLH_MAC_CLSS, &p_hwfn->cdev->mf_bits)) return 0; qed_llh_mac_to_filter(&high, &low, p_filter); @@ -3507,7 +3550,7 @@ void qed_llh_remove_mac_filter(struct qed_hwfn *p_hwfn, u32 high = 0, low = 0; int i; - if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn))) + if (!test_bit(QED_MF_LLH_MAC_CLSS, &p_hwfn->cdev->mf_bits)) return; qed_llh_mac_to_filter(&high, &low, p_filter); @@ -3549,7 +3592,7 @@ qed_llh_add_protocol_filter(struct qed_hwfn *p_hwfn, u32 high = 0, low = 0, en; int i; - if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn))) + if (!test_bit(QED_MF_LLH_PROTO_CLSS, &p_hwfn->cdev->mf_bits)) return 0; switch (type) { @@ -3647,7 +3690,7 @@ qed_llh_remove_protocol_filter(struct qed_hwfn *p_hwfn, u32 high = 0, low = 0; int i; - if (!(IS_MF_SI(p_hwfn) || IS_MF_DEFAULT(p_hwfn))) + if (!test_bit(QED_MF_LLH_PROTO_CLSS, &p_hwfn->cdev->mf_bits)) return; switch (type) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c index 2dc9b312a795..cc1b373c0ace 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_fcoe.c +++ b/drivers/net/ethernet/qlogic/qed/qed_fcoe.c @@ -313,6 +313,9 @@ qed_sp_fcoe_conn_offload(struct qed_hwfn *p_hwfn, p_data->d_id.addr_mid = p_conn->d_id.addr_mid; p_data->d_id.addr_lo = p_conn->d_id.addr_lo; p_data->flags = p_conn->flags; + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + SET_FIELD(p_data->flags, + FCOE_CONN_OFFLOAD_RAMROD_DATA_B_SINGLE_VLAN, 1); p_data->def_q_idx = p_conn->def_q_idx; return qed_spq_post(p_hwfn, p_ent, NULL); diff --git a/drivers/net/ethernet/qlogic/qed/qed_hsi.h b/drivers/net/ethernet/qlogic/qed/qed_hsi.h index 7f5ec42dde48..b5f70eff0182 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_hsi.h +++ b/drivers/net/ethernet/qlogic/qed/qed_hsi.h @@ -11993,6 +11993,16 @@ struct public_port { #define EEE_REMOTE_TW_TX_OFFSET 0 #define EEE_REMOTE_TW_RX_MASK 0xffff0000 #define EEE_REMOTE_TW_RX_OFFSET 16 + + u32 oem_cfg_port; +#define OEM_CFG_CHANNEL_TYPE_MASK 0x00000003 +#define OEM_CFG_CHANNEL_TYPE_OFFSET 0 +#define OEM_CFG_CHANNEL_TYPE_VLAN_PARTITION 0x1 +#define OEM_CFG_CHANNEL_TYPE_STAGGED 0x2 +#define OEM_CFG_SCHED_TYPE_MASK 0x0000000C +#define OEM_CFG_SCHED_TYPE_OFFSET 2 +#define OEM_CFG_SCHED_TYPE_ETS 0x1 +#define OEM_CFG_SCHED_TYPE_VNIC_BW 0x2 }; struct public_func { @@ -12069,6 +12079,23 @@ struct public_func { #define DRV_ID_DRV_INIT_HW_MASK 0x80000000 #define DRV_ID_DRV_INIT_HW_SHIFT 31 #define DRV_ID_DRV_INIT_HW_FLAG (1 << DRV_ID_DRV_INIT_HW_SHIFT) + + u32 oem_cfg_func; +#define OEM_CFG_FUNC_TC_MASK 0x0000000F +#define OEM_CFG_FUNC_TC_OFFSET 0 +#define OEM_CFG_FUNC_TC_0 0x0 +#define OEM_CFG_FUNC_TC_1 0x1 +#define OEM_CFG_FUNC_TC_2 0x2 +#define OEM_CFG_FUNC_TC_3 0x3 +#define OEM_CFG_FUNC_TC_4 0x4 +#define OEM_CFG_FUNC_TC_5 0x5 +#define OEM_CFG_FUNC_TC_6 0x6 +#define OEM_CFG_FUNC_TC_7 0x7 + +#define OEM_CFG_FUNC_HOST_PRI_CTRL_MASK 0x00000030 +#define OEM_CFG_FUNC_HOST_PRI_CTRL_OFFSET 4 +#define OEM_CFG_FUNC_HOST_PRI_CTRL_VNIC 0x1 +#define OEM_CFG_FUNC_HOST_PRI_CTRL_OS 0x2 }; struct mcp_mac { @@ -12495,6 +12522,7 @@ enum MFW_DRV_MSG_TYPE { MFW_DRV_MSG_BW_UPDATE10, MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE, MFW_DRV_MSG_BW_UPDATE11, + MFW_DRV_MSG_OEM_CFG_UPDATE, MFW_DRV_MSG_MAX }; diff --git a/drivers/net/ethernet/qlogic/qed/qed_l2.c b/drivers/net/ethernet/qlogic/qed/qed_l2.c index 8667799d0069..5e655c3601cf 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_l2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_l2.c @@ -2848,6 +2848,24 @@ static int qed_fp_cqe_completion(struct qed_dev *dev, cqe); } +static int qed_req_bulletin_update_mac(struct qed_dev *cdev, u8 *mac) +{ + int i, ret; + + if (IS_PF(cdev)) + return 0; + + for_each_hwfn(cdev, i) { + struct qed_hwfn *p_hwfn = &cdev->hwfns[i]; + + ret = qed_vf_pf_bulletin_update_mac(p_hwfn, mac); + if (ret) + return ret; + } + + return 0; +} + #ifdef CONFIG_QED_SRIOV extern const struct qed_iov_hv_ops qed_iov_ops_pass; #endif @@ -2885,6 +2903,7 @@ static const struct qed_eth_ops qed_eth_ops_pass = { .ntuple_filter_config = &qed_ntuple_arfs_filter_config, .configure_arfs_searcher = &qed_configure_arfs_searcher, .get_coalesce = &qed_get_coalesce, + .req_bulletin_update_mac = &qed_req_bulletin_update_mac, }; const struct qed_eth_ops *qed_get_eth_ops(void) diff --git a/drivers/net/ethernet/qlogic/qed/qed_ll2.c b/drivers/net/ethernet/qlogic/qed/qed_ll2.c index 38502815d681..c3c1a99a0252 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_ll2.c +++ b/drivers/net/ethernet/qlogic/qed/qed_ll2.c @@ -919,12 +919,16 @@ static int qed_sp_ll2_rx_queue_start(struct qed_hwfn *p_hwfn, p_ramrod->drop_ttl0_flg = p_ll2_conn->input.rx_drop_ttl0_flg; p_ramrod->inner_vlan_stripping_en = p_ll2_conn->input.rx_vlan_removal_en; + + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) && + p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE) + p_ramrod->report_outer_vlan = 1; p_ramrod->queue_id = p_ll2_conn->queue_id; p_ramrod->main_func_queue = p_ll2_conn->main_func_queue ? 1 : 0; - if ((IS_MF_DEFAULT(p_hwfn) || IS_MF_SI(p_hwfn)) && - p_ramrod->main_func_queue && (conn_type != QED_LL2_TYPE_ROCE) && - (conn_type != QED_LL2_TYPE_IWARP)) { + if (test_bit(QED_MF_LL2_NON_UNICAST, &p_hwfn->cdev->mf_bits) && + p_ramrod->main_func_queue && conn_type != QED_LL2_TYPE_ROCE && + conn_type != QED_LL2_TYPE_IWARP) { p_ramrod->mf_si_bcast_accept_all = 1; p_ramrod->mf_si_mcast_accept_all = 1; } else { @@ -1493,11 +1497,12 @@ int qed_ll2_establish_connection(void *cxt, u8 connection_handle) qed_ll2_establish_connection_ooo(p_hwfn, p_ll2_conn); if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE) { + if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + qed_llh_add_protocol_filter(p_hwfn, p_ptt, + ETH_P_FCOE, 0, + QED_LLH_FILTER_ETHERTYPE); qed_llh_add_protocol_filter(p_hwfn, p_ptt, - 0x8906, 0, - QED_LLH_FILTER_ETHERTYPE); - qed_llh_add_protocol_filter(p_hwfn, p_ptt, - 0x8914, 0, + ETH_P_FIP, 0, QED_LLH_FILTER_ETHERTYPE); } @@ -1653,11 +1658,16 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, start_bd = (struct core_tx_bd *)qed_chain_produce(p_tx_chain); if (QED_IS_IWARP_PERSONALITY(p_hwfn) && - p_ll2->input.conn_type == QED_LL2_TYPE_OOO) + p_ll2->input.conn_type == QED_LL2_TYPE_OOO) { start_bd->nw_vlan_or_lb_echo = cpu_to_le16(IWARP_LL2_IN_ORDER_TX_QUEUE); - else + } else { start_bd->nw_vlan_or_lb_echo = cpu_to_le16(pkt->vlan); + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits) && + p_ll2->input.conn_type == QED_LL2_TYPE_FCOE) + pkt->remove_stag = true; + } + SET_FIELD(start_bd->bitfield1, CORE_TX_BD_L4_HDR_OFFSET_W, cpu_to_le16(pkt->l4_hdr_offset_w)); SET_FIELD(start_bd->bitfield1, CORE_TX_BD_TX_DST, tx_dest); @@ -1668,6 +1678,9 @@ qed_ll2_prepare_tx_packet_set_bd(struct qed_hwfn *p_hwfn, SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_CSUM, !!(pkt->enable_ip_cksum)); SET_FIELD(bd_data, CORE_TX_BD_DATA_L4_CSUM, !!(pkt->enable_l4_cksum)); SET_FIELD(bd_data, CORE_TX_BD_DATA_IP_LEN, !!(pkt->calc_ip_len)); + SET_FIELD(bd_data, CORE_TX_BD_DATA_DISABLE_STAG_INSERTION, + !!(pkt->remove_stag)); + start_bd->bd_data.as_bitfield = cpu_to_le16(bd_data); DMA_REGPAIR_LE(start_bd->addr, pkt->first_frag); start_bd->nbytes = cpu_to_le16(pkt->first_frag_len); @@ -1884,11 +1897,12 @@ int qed_ll2_terminate_connection(void *cxt, u8 connection_handle) qed_ooo_release_all_isles(p_hwfn, p_hwfn->p_ooo_info); if (p_ll2_conn->input.conn_type == QED_LL2_TYPE_FCOE) { + if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + qed_llh_remove_protocol_filter(p_hwfn, p_ptt, + ETH_P_FCOE, 0, + QED_LLH_FILTER_ETHERTYPE); qed_llh_remove_protocol_filter(p_hwfn, p_ptt, - 0x8906, 0, - QED_LLH_FILTER_ETHERTYPE); - qed_llh_remove_protocol_filter(p_hwfn, p_ptt, - 0x8914, 0, + ETH_P_FIP, 0, QED_LLH_FILTER_ETHERTYPE); } @@ -2360,7 +2374,8 @@ fail: return -EINVAL; } -static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) +static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb, + unsigned long xmit_flags) { struct qed_ll2_tx_pkt_info pkt; const skb_frag_t *frag; @@ -2405,6 +2420,9 @@ static int qed_ll2_start_xmit(struct qed_dev *cdev, struct sk_buff *skb) pkt.first_frag = mapping; pkt.first_frag_len = skb->len; pkt.cookie = skb; + if (test_bit(QED_MF_UFP_SPECIFIC, &cdev->mf_bits) && + test_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &xmit_flags)) + pkt.remove_stag = true; rc = qed_ll2_prepare_tx_packet(&cdev->hwfns[0], cdev->ll2->handle, &pkt, 1); diff --git a/drivers/net/ethernet/qlogic/qed/qed_main.c b/drivers/net/ethernet/qlogic/qed/qed_main.c index 7870ae2a6f7e..9feed3b79cd4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_main.c +++ b/drivers/net/ethernet/qlogic/qed/qed_main.c @@ -264,7 +264,6 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->pci_mem_end = cdev->pci_params.mem_end; dev_info->pci_irq = cdev->pci_params.irq; dev_info->rdma_supported = QED_IS_RDMA_PERSONALITY(p_hwfn); - dev_info->is_mf_default = IS_MF_DEFAULT(&cdev->hwfns[0]); dev_info->dev_type = cdev->type; ether_addr_copy(dev_info->hw_mac, hw_info->hw_mac_addr); @@ -273,7 +272,8 @@ int qed_fill_dev_info(struct qed_dev *cdev, dev_info->fw_minor = FW_MINOR_VERSION; dev_info->fw_rev = FW_REVISION_VERSION; dev_info->fw_eng = FW_ENGINEERING_VERSION; - dev_info->mf_mode = cdev->mf_mode; + dev_info->b_inter_pf_switch = test_bit(QED_MF_INTER_PF_SWITCH, + &cdev->mf_bits); dev_info->tx_switching = true; if (hw_info->b_wol_support == QED_WOL_SUPPORT_PME) @@ -1894,15 +1894,8 @@ static int qed_nvm_get_image(struct qed_dev *cdev, enum qed_nvm_images type, u8 *buf, u16 len) { struct qed_hwfn *hwfn = QED_LEADING_HWFN(cdev); - struct qed_ptt *ptt = qed_ptt_acquire(hwfn); - int rc; - - if (!ptt) - return -EAGAIN; - rc = qed_mcp_get_nvm_image(hwfn, ptt, type, buf, len); - qed_ptt_release(hwfn, ptt); - return rc; + return qed_mcp_get_nvm_image(hwfn, type, buf, len); } static int qed_set_coalesce(struct qed_dev *cdev, u16 rx_coal, u16 tx_coal, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.c b/drivers/net/ethernet/qlogic/qed/qed_mcp.c index ec0d425766a7..e80f5e7c7992 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.c +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.c @@ -40,6 +40,7 @@ #include <linux/string.h> #include <linux/etherdevice.h> #include "qed.h" +#include "qed_cxt.h" #include "qed_dcbx.h" #include "qed_hsi.h" #include "qed_hw.h" @@ -1486,6 +1487,80 @@ static void qed_mcp_update_stag(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) &resp, ¶m); } +void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + struct public_func shmem_info; + u32 port_cfg, val; + + if (!test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) + return; + + memset(&p_hwfn->ufp_info, 0, sizeof(p_hwfn->ufp_info)); + port_cfg = qed_rd(p_hwfn, p_ptt, p_hwfn->mcp_info->port_addr + + offsetof(struct public_port, oem_cfg_port)); + val = (port_cfg & OEM_CFG_CHANNEL_TYPE_MASK) >> + OEM_CFG_CHANNEL_TYPE_OFFSET; + if (val != OEM_CFG_CHANNEL_TYPE_STAGGED) + DP_NOTICE(p_hwfn, "Incorrect UFP Channel type %d\n", val); + + val = (port_cfg & OEM_CFG_SCHED_TYPE_MASK) >> OEM_CFG_SCHED_TYPE_OFFSET; + if (val == OEM_CFG_SCHED_TYPE_ETS) { + p_hwfn->ufp_info.mode = QED_UFP_MODE_ETS; + } else if (val == OEM_CFG_SCHED_TYPE_VNIC_BW) { + p_hwfn->ufp_info.mode = QED_UFP_MODE_VNIC_BW; + } else { + p_hwfn->ufp_info.mode = QED_UFP_MODE_UNKNOWN; + DP_NOTICE(p_hwfn, "Unknown UFP scheduling mode %d\n", val); + } + + qed_mcp_get_shmem_func(p_hwfn, p_ptt, &shmem_info, MCP_PF_ID(p_hwfn)); + val = (port_cfg & OEM_CFG_FUNC_TC_MASK) >> OEM_CFG_FUNC_TC_OFFSET; + p_hwfn->ufp_info.tc = (u8)val; + val = (port_cfg & OEM_CFG_FUNC_HOST_PRI_CTRL_MASK) >> + OEM_CFG_FUNC_HOST_PRI_CTRL_OFFSET; + if (val == OEM_CFG_FUNC_HOST_PRI_CTRL_VNIC) { + p_hwfn->ufp_info.pri_type = QED_UFP_PRI_VNIC; + } else if (val == OEM_CFG_FUNC_HOST_PRI_CTRL_OS) { + p_hwfn->ufp_info.pri_type = QED_UFP_PRI_OS; + } else { + p_hwfn->ufp_info.pri_type = QED_UFP_PRI_UNKNOWN; + DP_NOTICE(p_hwfn, "Unknown Host priority control %d\n", val); + } + + DP_NOTICE(p_hwfn, + "UFP shmem config: mode = %d tc = %d pri_type = %d\n", + p_hwfn->ufp_info.mode, + p_hwfn->ufp_info.tc, p_hwfn->ufp_info.pri_type); +} + +static int +qed_mcp_handle_ufp_event(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) +{ + qed_mcp_read_ufp_config(p_hwfn, p_ptt); + + if (p_hwfn->ufp_info.mode == QED_UFP_MODE_VNIC_BW) { + p_hwfn->qm_info.ooo_tc = p_hwfn->ufp_info.tc; + p_hwfn->hw_info.offload_tc = p_hwfn->ufp_info.tc; + + qed_qm_reconf(p_hwfn, p_ptt); + } else if (p_hwfn->ufp_info.mode == QED_UFP_MODE_ETS) { + /* Merge UFP TC with the dcbx TC data */ + qed_dcbx_mib_update_event(p_hwfn, p_ptt, + QED_DCBX_OPERATIONAL_MIB); + } else { + DP_ERR(p_hwfn, "Invalid sched type, discard the UFP config\n"); + return -EINVAL; + } + + /* update storm FW with negotiation results */ + qed_sp_pf_update_ufp(p_hwfn); + + /* update stag pcp value */ + qed_sp_pf_update_stag(p_hwfn); + + return 0; +} + int qed_mcp_handle_events(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt) { @@ -1529,6 +1604,9 @@ int qed_mcp_handle_events(struct qed_hwfn *p_hwfn, qed_dcbx_mib_update_event(p_hwfn, p_ptt, QED_DCBX_OPERATIONAL_MIB); break; + case MFW_DRV_MSG_OEM_CFG_UPDATE: + qed_mcp_handle_ufp_event(p_hwfn, p_ptt); + break; case MFW_DRV_MSG_TRANSCEIVER_STATE_CHANGE: qed_mcp_handle_transceiver_change(p_hwfn, p_ptt); break; @@ -2529,9 +2607,8 @@ err0: return rc; } -static int +int qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, enum qed_nvm_images image_id, struct qed_nvm_image_att *p_image_att) { @@ -2546,6 +2623,15 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, case QED_NVM_IMAGE_FCOE_CFG: type = NVM_TYPE_FCOE_CFG; break; + case QED_NVM_IMAGE_NVM_CFG1: + type = NVM_TYPE_NVM_CFG1; + break; + case QED_NVM_IMAGE_DEFAULT_CFG: + type = NVM_TYPE_DEFAULT_CFG; + break; + case QED_NVM_IMAGE_NVM_META: + type = NVM_TYPE_META; + break; default: DP_NOTICE(p_hwfn, "Unknown request of image_id %08x\n", image_id); @@ -2569,7 +2655,6 @@ qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, } int qed_mcp_get_nvm_image(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, enum qed_nvm_images image_id, u8 *p_buffer, u32 buffer_len) { @@ -2578,7 +2663,7 @@ int qed_mcp_get_nvm_image(struct qed_hwfn *p_hwfn, memset(p_buffer, 0, buffer_len); - rc = qed_mcp_get_nvm_image_att(p_hwfn, p_ptt, image_id, &image_att); + rc = qed_mcp_get_nvm_image_att(p_hwfn, image_id, &image_att); if (rc) return rc; @@ -2590,9 +2675,6 @@ int qed_mcp_get_nvm_image(struct qed_hwfn *p_hwfn, return -EINVAL; } - /* Each NVM image is suffixed by CRC; Upper-layer has no need for it */ - image_att.length -= 4; - if (image_att.length > buffer_len) { DP_VERBOSE(p_hwfn, QED_MSG_STORAGE, diff --git a/drivers/net/ethernet/qlogic/qed/qed_mcp.h b/drivers/net/ethernet/qlogic/qed/qed_mcp.h index 8a5c988d0c3c..250579ba632b 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_mcp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_mcp.h @@ -486,7 +486,20 @@ struct qed_nvm_image_att { * @brief Allows reading a whole nvram image * * @param p_hwfn - * @param p_ptt + * @param image_id - image to get attributes for + * @param p_image_att - image attributes structure into which to fill data + * + * @return int - 0 - operation was successful. + */ +int +qed_mcp_get_nvm_image_att(struct qed_hwfn *p_hwfn, + enum qed_nvm_images image_id, + struct qed_nvm_image_att *p_image_att); + +/** + * @brief Allows reading a whole nvram image + * + * @param p_hwfn * @param image_id - image requested for reading * @param p_buffer - allocated buffer into which to fill data * @param buffer_len - length of the allocated buffer. @@ -494,7 +507,6 @@ struct qed_nvm_image_att { * @return 0 iff p_buffer now contains the nvram image. */ int qed_mcp_get_nvm_image(struct qed_hwfn *p_hwfn, - struct qed_ptt *p_ptt, enum qed_nvm_images image_id, u8 *p_buffer, u32 buffer_len); @@ -993,6 +1005,14 @@ int qed_mcp_get_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); int qed_mcp_set_capabilities(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); /** + * @brief Read ufp config from the shared memory. + * + * @param p_hwfn + * @param p_ptt + */ +void qed_mcp_read_ufp_config(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt); + +/** * @brief Populate the nvm info shadow in the given hardware function * * @param p_hwfn diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp.h b/drivers/net/ethernet/qlogic/qed/qed_sp.h index ab4ad8a1e2a5..e95431f6acd4 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp.h +++ b/drivers/net/ethernet/qlogic/qed/qed_sp.h @@ -416,7 +416,6 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, * @param p_hwfn * @param p_ptt * @param p_tunn - * @param mode * @param allow_npar_tx_switch * * @return int @@ -425,7 +424,7 @@ int qed_sp_init_request(struct qed_hwfn *p_hwfn, int qed_sp_pf_start(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_tunnel_info *p_tunn, - enum qed_mf_mode mode, bool allow_npar_tx_switch); + bool allow_npar_tx_switch); /** * @brief qed_sp_pf_update - PF Function Update Ramrod @@ -463,6 +462,15 @@ int qed_sp_pf_update_stag(struct qed_hwfn *p_hwfn); * @return int */ +/** + * @brief qed_sp_pf_update_ufp - PF ufp update Ramrod + * + * @param p_hwfn + * + * @return int + */ +int qed_sp_pf_update_ufp(struct qed_hwfn *p_hwfn); + int qed_sp_pf_stop(struct qed_hwfn *p_hwfn); int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c index 5e927b6cac22..8de644b4721e 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sp_commands.c @@ -306,7 +306,7 @@ qed_tunn_set_pf_start_params(struct qed_hwfn *p_hwfn, int qed_sp_pf_start(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, struct qed_tunnel_info *p_tunn, - enum qed_mf_mode mode, bool allow_npar_tx_switch) + bool allow_npar_tx_switch) { struct pf_start_ramrod_data *p_ramrod = NULL; u16 sb = qed_int_get_sp_sb_id(p_hwfn); @@ -314,7 +314,7 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, struct qed_spq_entry *p_ent = NULL; struct qed_sp_init_data init_data; int rc = -EINVAL; - u8 page_cnt; + u8 page_cnt, i; /* update initial eq producer */ qed_eq_prod_update(p_hwfn, @@ -339,21 +339,36 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, p_ramrod->dont_log_ramrods = 0; p_ramrod->log_type_mask = cpu_to_le16(0xf); - switch (mode) { - case QED_MF_DEFAULT: - case QED_MF_NPAR: - p_ramrod->mf_mode = MF_NPAR; - break; - case QED_MF_OVLAN: + if (test_bit(QED_MF_OVLAN_CLSS, &p_hwfn->cdev->mf_bits)) p_ramrod->mf_mode = MF_OVLAN; - break; - default: - DP_NOTICE(p_hwfn, "Unsupported MF mode, init as DEFAULT\n"); + else p_ramrod->mf_mode = MF_NPAR; - } p_ramrod->outer_tag_config.outer_tag.tci = - cpu_to_le16(p_hwfn->hw_info.ovlan); + cpu_to_le16(p_hwfn->hw_info.ovlan); + if (test_bit(QED_MF_8021Q_TAGGING, &p_hwfn->cdev->mf_bits)) { + p_ramrod->outer_tag_config.outer_tag.tpid = ETH_P_8021Q; + } else if (test_bit(QED_MF_8021AD_TAGGING, &p_hwfn->cdev->mf_bits)) { + p_ramrod->outer_tag_config.outer_tag.tpid = ETH_P_8021AD; + p_ramrod->outer_tag_config.enable_stag_pri_change = 1; + } + + p_ramrod->outer_tag_config.pri_map_valid = 1; + for (i = 0; i < QED_MAX_PFC_PRIORITIES; i++) + p_ramrod->outer_tag_config.inner_to_outer_pri_map[i] = i; + + /* enable_stag_pri_change should be set if port is in BD mode or, + * UFP with Host Control mode. + */ + if (test_bit(QED_MF_UFP_SPECIFIC, &p_hwfn->cdev->mf_bits)) { + if (p_hwfn->ufp_info.pri_type == QED_UFP_PRI_OS) + p_ramrod->outer_tag_config.enable_stag_pri_change = 1; + else + p_ramrod->outer_tag_config.enable_stag_pri_change = 0; + + p_ramrod->outer_tag_config.outer_tag.tci |= + cpu_to_le16(((u16)p_hwfn->ufp_info.tc << 13)); + } /* Place EQ address in RAMROD */ DMA_REGPAIR_LE(p_ramrod->event_ring_pbl_addr, @@ -365,7 +380,7 @@ int qed_sp_pf_start(struct qed_hwfn *p_hwfn, qed_tunn_set_pf_start_params(p_hwfn, p_tunn, &p_ramrod->tunnel_config); - if (IS_MF_SI(p_hwfn)) + if (test_bit(QED_MF_INTER_PF_SWITCH, &p_hwfn->cdev->mf_bits)) p_ramrod->allow_npar_tx_switching = allow_npar_tx_switch; switch (p_hwfn->hw_info.personality) { @@ -434,6 +449,39 @@ int qed_sp_pf_update(struct qed_hwfn *p_hwfn) return qed_spq_post(p_hwfn, p_ent, NULL); } +int qed_sp_pf_update_ufp(struct qed_hwfn *p_hwfn) +{ + struct qed_spq_entry *p_ent = NULL; + struct qed_sp_init_data init_data; + int rc = -EOPNOTSUPP; + + if (p_hwfn->ufp_info.pri_type == QED_UFP_PRI_UNKNOWN) { + DP_INFO(p_hwfn, "Invalid priority type %d\n", + p_hwfn->ufp_info.pri_type); + return -EINVAL; + } + + /* Get SPQ entry */ + memset(&init_data, 0, sizeof(init_data)); + init_data.cid = qed_spq_get_cid(p_hwfn); + init_data.opaque_fid = p_hwfn->hw_info.opaque_fid; + init_data.comp_mode = QED_SPQ_MODE_CB; + + rc = qed_sp_init_request(p_hwfn, &p_ent, + COMMON_RAMROD_PF_UPDATE, PROTOCOLID_COMMON, + &init_data); + if (rc) + return rc; + + p_ent->ramrod.pf_update.update_enable_stag_pri_change = true; + if (p_hwfn->ufp_info.pri_type == QED_UFP_PRI_OS) + p_ent->ramrod.pf_update.enable_stag_pri_change = 1; + else + p_ent->ramrod.pf_update.enable_stag_pri_change = 0; + + return qed_spq_post(p_hwfn, p_ent, NULL); +} + /* Set pf update ramrod command params */ int qed_sp_pf_update_tunn_cfg(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, diff --git a/drivers/net/ethernet/qlogic/qed/qed_sriov.c b/drivers/net/ethernet/qlogic/qed/qed_sriov.c index 5acb91b3564c..f01bf52bc381 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_sriov.c +++ b/drivers/net/ethernet/qlogic/qed/qed_sriov.c @@ -48,7 +48,7 @@ static int qed_sriov_eqe_event(struct qed_hwfn *p_hwfn, u8 opcode, __le16 echo, union event_ring_data *data, u8 fw_return_code); - +static int qed_iov_bulletin_set_mac(struct qed_hwfn *p_hwfn, u8 *mac, int vfid); static u8 qed_vf_calculate_legacy(struct qed_vf_info *p_vf) { @@ -1790,7 +1790,8 @@ static int qed_iov_configure_vport_forced(struct qed_hwfn *p_hwfn, if (!p_vf->vport_instance) return -EINVAL; - if (events & BIT(MAC_ADDR_FORCED)) { + if ((events & BIT(MAC_ADDR_FORCED)) || + p_vf->p_vf_info.is_trusted_configured) { /* Since there's no way [currently] of removing the MAC, * we can always assume this means we need to force it. */ @@ -1809,8 +1810,12 @@ static int qed_iov_configure_vport_forced(struct qed_hwfn *p_hwfn, "PF failed to configure MAC for VF\n"); return rc; } - - p_vf->configured_features |= 1 << MAC_ADDR_FORCED; + if (p_vf->p_vf_info.is_trusted_configured) + p_vf->configured_features |= + BIT(VFPF_BULLETIN_MAC_ADDR); + else + p_vf->configured_features |= + BIT(MAC_ADDR_FORCED); } if (events & BIT(VLAN_ADDR_FORCED)) { @@ -3170,6 +3175,10 @@ static int qed_iov_vf_update_mac_shadow(struct qed_hwfn *p_hwfn, if (p_vf->bulletin.p_virt->valid_bitmap & BIT(MAC_ADDR_FORCED)) return 0; + /* Don't keep track of shadow copy since we don't intend to restore. */ + if (p_vf->p_vf_info.is_trusted_configured) + return 0; + /* First remove entries and then add new ones */ if (p_params->opcode == QED_FILTER_REMOVE) { for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) { @@ -3244,9 +3253,17 @@ static int qed_iov_chk_ucast(struct qed_hwfn *hwfn, /* No real decision to make; Store the configured MAC */ if (params->type == QED_FILTER_MAC || - params->type == QED_FILTER_MAC_VLAN) + params->type == QED_FILTER_MAC_VLAN) { ether_addr_copy(vf->mac, params->mac); + if (vf->is_trusted_configured) { + qed_iov_bulletin_set_mac(hwfn, vf->mac, vfid); + + /* Update and post bulleitin again */ + qed_schedule_iov(hwfn, QED_IOV_WQ_BULLETIN_UPDATE_FLAG); + } + } + return 0; } @@ -3803,6 +3820,40 @@ static void qed_iov_get_link(struct qed_hwfn *p_hwfn, __qed_vf_get_link_caps(p_hwfn, p_caps, p_bulletin); } +static int +qed_iov_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, + struct qed_ptt *p_ptt, + struct qed_vf_info *p_vf) +{ + struct qed_bulletin_content *p_bulletin = p_vf->bulletin.p_virt; + struct qed_iov_vf_mbx *mbx = &p_vf->vf_mbx; + struct vfpf_bulletin_update_mac_tlv *p_req; + u8 status = PFVF_STATUS_SUCCESS; + int rc = 0; + + if (!p_vf->p_vf_info.is_trusted_configured) { + DP_VERBOSE(p_hwfn, + QED_MSG_IOV, + "Blocking bulletin update request from untrusted VF[%d]\n", + p_vf->abs_vf_id); + status = PFVF_STATUS_NOT_SUPPORTED; + rc = -EINVAL; + goto send_status; + } + + p_req = &mbx->req_virt->bulletin_update_mac; + ether_addr_copy(p_bulletin->mac, p_req->mac); + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "Updated bulletin of VF[%d] with requested MAC[%pM]\n", + p_vf->abs_vf_id, p_req->mac); + +send_status: + qed_iov_prepare_resp(p_hwfn, p_ptt, p_vf, + CHANNEL_TLV_BULLETIN_UPDATE_MAC, + sizeof(struct pfvf_def_resp_tlv), status); + return rc; +} + static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn, struct qed_ptt *p_ptt, int vfid) { @@ -3882,6 +3933,9 @@ static void qed_iov_process_mbx_req(struct qed_hwfn *p_hwfn, case CHANNEL_TLV_COALESCE_READ: qed_iov_vf_pf_get_coalesce(p_hwfn, p_ptt, p_vf); break; + case CHANNEL_TLV_BULLETIN_UPDATE_MAC: + qed_iov_vf_pf_bulletin_update_mac(p_hwfn, p_ptt, p_vf); + break; } } else if (qed_iov_tlv_supported(mbx->first_tlv.tl.type)) { DP_VERBOSE(p_hwfn, QED_MSG_IOV, @@ -4081,16 +4135,60 @@ static void qed_iov_bulletin_set_forced_mac(struct qed_hwfn *p_hwfn, return; } - feature = 1 << MAC_ADDR_FORCED; + if (vf_info->p_vf_info.is_trusted_configured) { + feature = BIT(VFPF_BULLETIN_MAC_ADDR); + /* Trust mode will disable Forced MAC */ + vf_info->bulletin.p_virt->valid_bitmap &= + ~BIT(MAC_ADDR_FORCED); + } else { + feature = BIT(MAC_ADDR_FORCED); + /* Forced MAC will disable MAC_ADDR */ + vf_info->bulletin.p_virt->valid_bitmap &= + ~BIT(VFPF_BULLETIN_MAC_ADDR); + } + memcpy(vf_info->bulletin.p_virt->mac, mac, ETH_ALEN); vf_info->bulletin.p_virt->valid_bitmap |= feature; - /* Forced MAC will disable MAC_ADDR */ - vf_info->bulletin.p_virt->valid_bitmap &= ~BIT(VFPF_BULLETIN_MAC_ADDR); qed_iov_configure_vport_forced(p_hwfn, vf_info, feature); } +static int qed_iov_bulletin_set_mac(struct qed_hwfn *p_hwfn, u8 *mac, int vfid) +{ + struct qed_vf_info *vf_info; + u64 feature; + + vf_info = qed_iov_get_vf_info(p_hwfn, (u16)vfid, true); + if (!vf_info) { + DP_NOTICE(p_hwfn->cdev, "Can not set MAC, invalid vfid [%d]\n", + vfid); + return -EINVAL; + } + + if (vf_info->b_malicious) { + DP_NOTICE(p_hwfn->cdev, "Can't set MAC to malicious VF [%d]\n", + vfid); + return -EINVAL; + } + + if (vf_info->bulletin.p_virt->valid_bitmap & BIT(MAC_ADDR_FORCED)) { + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "Can not set MAC, Forced MAC is configured\n"); + return -EINVAL; + } + + feature = BIT(VFPF_BULLETIN_MAC_ADDR); + ether_addr_copy(vf_info->bulletin.p_virt->mac, mac); + + vf_info->bulletin.p_virt->valid_bitmap |= feature; + + if (vf_info->p_vf_info.is_trusted_configured) + qed_iov_configure_vport_forced(p_hwfn, vf_info, feature); + + return 0; +} + static void qed_iov_bulletin_set_forced_vlan(struct qed_hwfn *p_hwfn, u16 pvid, int vfid) { @@ -4204,6 +4302,21 @@ out: return rc; } +static u8 *qed_iov_bulletin_get_mac(struct qed_hwfn *p_hwfn, u16 rel_vf_id) +{ + struct qed_vf_info *p_vf; + + p_vf = qed_iov_get_vf_info(p_hwfn, rel_vf_id, true); + if (!p_vf || !p_vf->bulletin.p_virt) + return NULL; + + if (!(p_vf->bulletin.p_virt->valid_bitmap & + BIT(VFPF_BULLETIN_MAC_ADDR))) + return NULL; + + return p_vf->bulletin.p_virt->mac; +} + static u8 *qed_iov_bulletin_get_forced_mac(struct qed_hwfn *p_hwfn, u16 rel_vf_id) { @@ -4493,8 +4606,12 @@ static int qed_sriov_pf_set_mac(struct qed_dev *cdev, u8 *mac, int vfid) if (!vf_info) continue; - /* Set the forced MAC, and schedule the IOV task */ - ether_addr_copy(vf_info->forced_mac, mac); + /* Set the MAC, and schedule the IOV task */ + if (vf_info->is_trusted_configured) + ether_addr_copy(vf_info->mac, mac); + else + ether_addr_copy(vf_info->forced_mac, mac); + qed_schedule_iov(hwfn, QED_IOV_WQ_SET_UNICAST_FILTER_FLAG); } @@ -4802,6 +4919,33 @@ static void qed_handle_vf_msg(struct qed_hwfn *hwfn) qed_ptt_release(hwfn, ptt); } +static bool qed_pf_validate_req_vf_mac(struct qed_hwfn *hwfn, + u8 *mac, + struct qed_public_vf_info *info) +{ + if (info->is_trusted_configured) { + if (is_valid_ether_addr(info->mac) && + (!mac || !ether_addr_equal(mac, info->mac))) + return true; + } else { + if (is_valid_ether_addr(info->forced_mac) && + (!mac || !ether_addr_equal(mac, info->forced_mac))) + return true; + } + + return false; +} + +static void qed_set_bulletin_mac(struct qed_hwfn *hwfn, + struct qed_public_vf_info *info, + int vfid) +{ + if (info->is_trusted_configured) + qed_iov_bulletin_set_mac(hwfn, info->mac, vfid); + else + qed_iov_bulletin_set_forced_mac(hwfn, info->forced_mac, vfid); +} + static void qed_handle_pf_set_vf_unicast(struct qed_hwfn *hwfn) { int i; @@ -4816,18 +4960,20 @@ static void qed_handle_pf_set_vf_unicast(struct qed_hwfn *hwfn) continue; /* Update data on bulletin board */ - mac = qed_iov_bulletin_get_forced_mac(hwfn, i); - if (is_valid_ether_addr(info->forced_mac) && - (!mac || !ether_addr_equal(mac, info->forced_mac))) { + if (info->is_trusted_configured) + mac = qed_iov_bulletin_get_mac(hwfn, i); + else + mac = qed_iov_bulletin_get_forced_mac(hwfn, i); + + if (qed_pf_validate_req_vf_mac(hwfn, mac, info)) { DP_VERBOSE(hwfn, QED_MSG_IOV, "Handling PF setting of VF MAC to VF 0x%02x [Abs 0x%02x]\n", i, hwfn->cdev->p_iov_info->first_vf_in_pf + i); - /* Update bulletin board with forced MAC */ - qed_iov_bulletin_set_forced_mac(hwfn, - info->forced_mac, i); + /* Update bulletin board with MAC */ + qed_set_bulletin_mac(hwfn, info, i); update = true; } @@ -4867,6 +5013,72 @@ static void qed_handle_bulletin_post(struct qed_hwfn *hwfn) qed_ptt_release(hwfn, ptt); } +static void qed_update_mac_for_vf_trust_change(struct qed_hwfn *hwfn, int vf_id) +{ + struct qed_public_vf_info *vf_info; + struct qed_vf_info *vf; + u8 *force_mac; + int i; + + vf_info = qed_iov_get_public_vf_info(hwfn, vf_id, true); + vf = qed_iov_get_vf_info(hwfn, vf_id, true); + + if (!vf_info || !vf) + return; + + /* Force MAC converted to generic MAC in case of VF trust on */ + if (vf_info->is_trusted_configured && + (vf->bulletin.p_virt->valid_bitmap & BIT(MAC_ADDR_FORCED))) { + force_mac = qed_iov_bulletin_get_forced_mac(hwfn, vf_id); + + if (force_mac) { + /* Clear existing shadow copy of MAC to have a clean + * slate. + */ + for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) { + if (ether_addr_equal(vf->shadow_config.macs[i], + vf_info->mac)) { + memset(vf->shadow_config.macs[i], 0, + ETH_ALEN); + DP_VERBOSE(hwfn, QED_MSG_IOV, + "Shadow MAC %pM removed for VF 0x%02x, VF trust mode is ON\n", + vf_info->mac, vf_id); + break; + } + } + + ether_addr_copy(vf_info->mac, force_mac); + memset(vf_info->forced_mac, 0, ETH_ALEN); + vf->bulletin.p_virt->valid_bitmap &= + ~BIT(MAC_ADDR_FORCED); + qed_schedule_iov(hwfn, QED_IOV_WQ_BULLETIN_UPDATE_FLAG); + } + } + + /* Update shadow copy with VF MAC when trust mode is turned off */ + if (!vf_info->is_trusted_configured) { + u8 empty_mac[ETH_ALEN]; + + memset(empty_mac, 0, ETH_ALEN); + for (i = 0; i < QED_ETH_VF_NUM_MAC_FILTERS; i++) { + if (ether_addr_equal(vf->shadow_config.macs[i], + empty_mac)) { + ether_addr_copy(vf->shadow_config.macs[i], + vf_info->mac); + DP_VERBOSE(hwfn, QED_MSG_IOV, + "Shadow is updated with %pM for VF 0x%02x, VF trust mode is OFF\n", + vf_info->mac, vf_id); + break; + } + } + /* Clear bulletin when trust mode is turned off, + * to have a clean slate for next (normal) operations. + */ + qed_iov_bulletin_set_mac(hwfn, empty_mac, vf_id); + qed_schedule_iov(hwfn, QED_IOV_WQ_BULLETIN_UPDATE_FLAG); + } +} + static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) { struct qed_sp_vport_update_params params; @@ -4890,6 +5102,9 @@ static void qed_iov_handle_trust_change(struct qed_hwfn *hwfn) continue; vf_info->is_trusted_configured = vf_info->is_trusted_request; + /* Handle forced MAC mode */ + qed_update_mac_for_vf_trust_change(hwfn, i); + /* Validate that the VF has a configured vport */ vf = qed_iov_get_vf_info(hwfn, i, true); if (!vf->vport_instance) diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.c b/drivers/net/ethernet/qlogic/qed/qed_vf.c index 91b5e9f02a62..2d7fcd6a0777 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.c +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.c @@ -1375,6 +1375,35 @@ exit: } int +qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, + u8 *p_mac) +{ + struct qed_vf_iov *p_iov = p_hwfn->vf_iov_info; + struct vfpf_bulletin_update_mac_tlv *p_req; + struct pfvf_def_resp_tlv *p_resp; + int rc; + + if (!p_mac) + return -EINVAL; + + /* clear mailbox and prep header tlv */ + p_req = qed_vf_pf_prep(p_hwfn, CHANNEL_TLV_BULLETIN_UPDATE_MAC, + sizeof(*p_req)); + ether_addr_copy(p_req->mac, p_mac); + DP_VERBOSE(p_hwfn, QED_MSG_IOV, + "Requesting bulletin update for MAC[%pM]\n", p_mac); + + /* add list termination tlv */ + qed_add_tlv(p_hwfn, &p_iov->offset, CHANNEL_TLV_LIST_END, + sizeof(struct channel_list_end_tlv)); + + p_resp = &p_iov->pf2vf_reply->default_resp; + rc = qed_send_msg2pf(p_hwfn, &p_resp->hdr.status, sizeof(*p_resp)); + qed_vf_pf_req_end(p_hwfn, rc); + return rc; +} + +int qed_vf_pf_set_coalesce(struct qed_hwfn *p_hwfn, u16 rx_coal, u16 tx_coal, struct qed_queue_cid *p_cid) { diff --git a/drivers/net/ethernet/qlogic/qed/qed_vf.h b/drivers/net/ethernet/qlogic/qed/qed_vf.h index 97d44dfb38ca..4f05d5eb3cf5 100644 --- a/drivers/net/ethernet/qlogic/qed/qed_vf.h +++ b/drivers/net/ethernet/qlogic/qed/qed_vf.h @@ -518,6 +518,12 @@ struct pfvf_read_coal_resp_tlv { u8 padding[6]; }; +struct vfpf_bulletin_update_mac_tlv { + struct vfpf_first_tlv first_tlv; + u8 mac[ETH_ALEN]; + u8 padding[2]; +}; + union vfpf_tlvs { struct vfpf_first_tlv first_tlv; struct vfpf_acquire_tlv acquire; @@ -532,6 +538,7 @@ union vfpf_tlvs { struct vfpf_update_tunn_param_tlv tunn_param_update; struct vfpf_update_coalesce update_coalesce; struct vfpf_read_coal_req_tlv read_coal_req; + struct vfpf_bulletin_update_mac_tlv bulletin_update_mac; struct tlv_buffer_size tlv_buf_size; }; @@ -650,6 +657,7 @@ enum { CHANNEL_TLV_COALESCE_UPDATE, CHANNEL_TLV_QID, CHANNEL_TLV_COALESCE_READ, + CHANNEL_TLV_BULLETIN_UPDATE_MAC, CHANNEL_TLV_MAX, /* Required for iterating over vport-update tlvs. @@ -1042,6 +1050,13 @@ int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn, struct qed_tunnel_info *p_tunn); u32 qed_vf_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id); +/** + * @brief - Ask PF to update the MAC address in it's bulletin board + * + * @param p_mac - mac address to be updated in bulletin board + */ +int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, u8 *p_mac); + #else static inline void qed_vf_get_link_params(struct qed_hwfn *p_hwfn, struct qed_mcp_link_params *params) @@ -1228,6 +1243,12 @@ static inline int qed_vf_pf_tunnel_param_update(struct qed_hwfn *p_hwfn, return -EINVAL; } +static inline int qed_vf_pf_bulletin_update_mac(struct qed_hwfn *p_hwfn, + u8 *p_mac) +{ + return -EINVAL; +} + static inline u32 qed_vf_hw_bar_size(struct qed_hwfn *p_hwfn, enum BAR_ID bar_id) diff --git a/drivers/net/ethernet/qlogic/qede/qede_filter.c b/drivers/net/ethernet/qlogic/qede/qede_filter.c index 6687e04d1558..43569b1839be 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_filter.c +++ b/drivers/net/ethernet/qlogic/qede/qede_filter.c @@ -550,8 +550,7 @@ void qede_force_mac(void *dev, u8 *mac, bool forced) __qede_lock(edev); - /* MAC hints take effect only if we haven't set one already */ - if (is_valid_ether_addr(edev->ndev->dev_addr) && !forced) { + if (!is_valid_ether_addr(mac)) { __qede_unlock(edev); return; } @@ -1161,6 +1160,10 @@ int qede_set_mac_addr(struct net_device *ndev, void *p) if (edev->state != QEDE_STATE_OPEN) { DP_VERBOSE(edev, NETIF_MSG_IFDOWN, "The device is currently down\n"); + /* Ask PF to explicitly update a copy in bulletin board */ + if (IS_VF(edev) && edev->ops->req_bulletin_update_mac) + edev->ops->req_bulletin_update_mac(edev->cdev, + ndev->dev_addr); goto out; } diff --git a/drivers/net/ethernet/qlogic/qede/qede_main.c b/drivers/net/ethernet/qlogic/qede/qede_main.c index a01e7d6e5442..89c581c3c21a 100644 --- a/drivers/net/ethernet/qlogic/qede/qede_main.c +++ b/drivers/net/ethernet/qlogic/qede/qede_main.c @@ -199,7 +199,7 @@ static int qede_sriov_configure(struct pci_dev *pdev, int num_vfs_param) /* Enable/Disable Tx switching for PF */ if ((rc == num_vfs_param) && netif_running(edev->ndev) && - qed_info->mf_mode != QED_MF_NPAR && qed_info->tx_switching) { + !qed_info->b_inter_pf_switch && qed_info->tx_switching) { vport_params->vport_id = 0; vport_params->update_tx_switching_flg = 1; vport_params->tx_switching_flg = num_vfs_param ? 1 : 0; @@ -1928,7 +1928,7 @@ static int qede_start_queues(struct qede_dev *edev, bool clear_stats) vport_update_params->update_vport_active_flg = 1; vport_update_params->vport_active_flg = 1; - if ((qed_info->mf_mode == QED_MF_NPAR || pci_num_vf(edev->pdev)) && + if ((qed_info->b_inter_pf_switch || pci_num_vf(edev->pdev)) && qed_info->tx_switching) { vport_update_params->update_tx_switching_flg = 1; vport_update_params->tx_switching_flg = 1; diff --git a/drivers/net/ethernet/realtek/r8169.c b/drivers/net/ethernet/realtek/r8169.c index c7aac1fc99e8..2c2f0c5b3f94 100644 --- a/drivers/net/ethernet/realtek/r8169.c +++ b/drivers/net/ethernet/realtek/r8169.c @@ -84,12 +84,11 @@ The RTL chips use a 64 element hash table based on the Ethernet CRC. */ static const int multicast_filter_limit = 32; -#define MAX_READ_REQUEST_SHIFT 12 #define TX_DMA_BURST 7 /* Maximum PCI burst, '7' is unlimited */ #define InterFrameGap 0x03 /* 3 means InterFrameGap = the shortest one */ #define R8169_REGS_SIZE 256 -#define R8169_NAPI_WEIGHT 64 +#define R8169_RX_BUF_SIZE (SZ_16K - 1) #define NUM_TX_DESC 64 /* Number of Tx descriptor registers */ #define NUM_RX_DESC 256U /* Number of Rx descriptor registers */ #define R8169_TX_RING_BYTES (NUM_TX_DESC * sizeof(struct TxDesc)) @@ -172,12 +171,11 @@ enum rtl_tx_desc_version { #define JUMBO_7K (7*1024 - ETH_HLEN - 2) #define JUMBO_9K (9*1024 - ETH_HLEN - 2) -#define _R(NAME,TD,FW,SZ,B) { \ +#define _R(NAME,TD,FW,SZ) { \ .name = NAME, \ .txd_version = TD, \ .fw_name = FW, \ .jumbo_max = SZ, \ - .jumbo_tx_csum = B \ } static const struct { @@ -185,135 +183,111 @@ static const struct { enum rtl_tx_desc_version txd_version; const char *fw_name; u16 jumbo_max; - bool jumbo_tx_csum; } rtl_chip_infos[] = { /* PCI devices. */ [RTL_GIGA_MAC_VER_01] = - _R("RTL8169", RTL_TD_0, NULL, JUMBO_7K, true), + _R("RTL8169", RTL_TD_0, NULL, JUMBO_7K), [RTL_GIGA_MAC_VER_02] = - _R("RTL8169s", RTL_TD_0, NULL, JUMBO_7K, true), + _R("RTL8169s", RTL_TD_0, NULL, JUMBO_7K), [RTL_GIGA_MAC_VER_03] = - _R("RTL8110s", RTL_TD_0, NULL, JUMBO_7K, true), + _R("RTL8110s", RTL_TD_0, NULL, JUMBO_7K), [RTL_GIGA_MAC_VER_04] = - _R("RTL8169sb/8110sb", RTL_TD_0, NULL, JUMBO_7K, true), + _R("RTL8169sb/8110sb", RTL_TD_0, NULL, JUMBO_7K), [RTL_GIGA_MAC_VER_05] = - _R("RTL8169sc/8110sc", RTL_TD_0, NULL, JUMBO_7K, true), + _R("RTL8169sc/8110sc", RTL_TD_0, NULL, JUMBO_7K), [RTL_GIGA_MAC_VER_06] = - _R("RTL8169sc/8110sc", RTL_TD_0, NULL, JUMBO_7K, true), + _R("RTL8169sc/8110sc", RTL_TD_0, NULL, JUMBO_7K), /* PCI-E devices. */ [RTL_GIGA_MAC_VER_07] = - _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K, true), + _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_08] = - _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K, true), + _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_09] = - _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K, true), + _R("RTL8102e", RTL_TD_1, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_10] = - _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true), + _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_11] = - _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K, false), + _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K), [RTL_GIGA_MAC_VER_12] = - _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K, false), + _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K), [RTL_GIGA_MAC_VER_13] = - _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true), + _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_14] = - _R("RTL8100e", RTL_TD_0, NULL, JUMBO_1K, true), + _R("RTL8100e", RTL_TD_0, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_15] = - _R("RTL8100e", RTL_TD_0, NULL, JUMBO_1K, true), + _R("RTL8100e", RTL_TD_0, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_16] = - _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K, true), + _R("RTL8101e", RTL_TD_0, NULL, JUMBO_1K), [RTL_GIGA_MAC_VER_17] = - _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K, false), + _R("RTL8168b/8111b", RTL_TD_0, NULL, JUMBO_4K), [RTL_GIGA_MAC_VER_18] = - _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false), + _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K), [RTL_GIGA_MAC_VER_19] = - _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false), + _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K), [RTL_GIGA_MAC_VER_20] = - _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false), + _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K), [RTL_GIGA_MAC_VER_21] = - _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false), + _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K), [RTL_GIGA_MAC_VER_22] = - _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K, false), + _R("RTL8168c/8111c", RTL_TD_1, NULL, JUMBO_6K), [RTL_GIGA_MAC_VER_23] = - _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false), + _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K), [RTL_GIGA_MAC_VER_24] = - _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K, false), + _R("RTL8168cp/8111cp", RTL_TD_1, NULL, JUMBO_6K), [RTL_GIGA_MAC_VER_25] = - _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_1, - JUMBO_9K, false), + _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_1, JUMBO_9K), [RTL_GIGA_MAC_VER_26] = - _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_2, - JUMBO_9K, false), + _R("RTL8168d/8111d", RTL_TD_1, FIRMWARE_8168D_2, JUMBO_9K), [RTL_GIGA_MAC_VER_27] = - _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K, false), + _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K), [RTL_GIGA_MAC_VER_28] = - _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K, false), + _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K), [RTL_GIGA_MAC_VER_29] = - _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1, - JUMBO_1K, true), + _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1, JUMBO_1K), [RTL_GIGA_MAC_VER_30] = - _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1, - JUMBO_1K, true), + _R("RTL8105e", RTL_TD_1, FIRMWARE_8105E_1, JUMBO_1K), [RTL_GIGA_MAC_VER_31] = - _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K, false), + _R("RTL8168dp/8111dp", RTL_TD_1, NULL, JUMBO_9K), [RTL_GIGA_MAC_VER_32] = - _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_1, - JUMBO_9K, false), + _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_1, JUMBO_9K), [RTL_GIGA_MAC_VER_33] = - _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_2, - JUMBO_9K, false), + _R("RTL8168e/8111e", RTL_TD_1, FIRMWARE_8168E_2, JUMBO_9K), [RTL_GIGA_MAC_VER_34] = - _R("RTL8168evl/8111evl",RTL_TD_1, FIRMWARE_8168E_3, - JUMBO_9K, false), + _R("RTL8168evl/8111evl",RTL_TD_1, FIRMWARE_8168E_3, JUMBO_9K), [RTL_GIGA_MAC_VER_35] = - _R("RTL8168f/8111f", RTL_TD_1, FIRMWARE_8168F_1, - JUMBO_9K, false), + _R("RTL8168f/8111f", RTL_TD_1, FIRMWARE_8168F_1, JUMBO_9K), [RTL_GIGA_MAC_VER_36] = - _R("RTL8168f/8111f", RTL_TD_1, FIRMWARE_8168F_2, - JUMBO_9K, false), + _R("RTL8168f/8111f", RTL_TD_1, FIRMWARE_8168F_2, JUMBO_9K), [RTL_GIGA_MAC_VER_37] = - _R("RTL8402", RTL_TD_1, FIRMWARE_8402_1, - JUMBO_1K, true), + _R("RTL8402", RTL_TD_1, FIRMWARE_8402_1, JUMBO_1K), [RTL_GIGA_MAC_VER_38] = - _R("RTL8411", RTL_TD_1, FIRMWARE_8411_1, - JUMBO_9K, false), + _R("RTL8411", RTL_TD_1, FIRMWARE_8411_1, JUMBO_9K), [RTL_GIGA_MAC_VER_39] = - _R("RTL8106e", RTL_TD_1, FIRMWARE_8106E_1, - JUMBO_1K, true), + _R("RTL8106e", RTL_TD_1, FIRMWARE_8106E_1, JUMBO_1K), [RTL_GIGA_MAC_VER_40] = - _R("RTL8168g/8111g", RTL_TD_1, FIRMWARE_8168G_2, - JUMBO_9K, false), + _R("RTL8168g/8111g", RTL_TD_1, FIRMWARE_8168G_2, JUMBO_9K), [RTL_GIGA_MAC_VER_41] = - _R("RTL8168g/8111g", RTL_TD_1, NULL, JUMBO_9K, false), + _R("RTL8168g/8111g", RTL_TD_1, NULL, JUMBO_9K), [RTL_GIGA_MAC_VER_42] = - _R("RTL8168g/8111g", RTL_TD_1, FIRMWARE_8168G_3, - JUMBO_9K, false), + _R("RTL8168g/8111g", RTL_TD_1, FIRMWARE_8168G_3, JUMBO_9K), [RTL_GIGA_MAC_VER_43] = - _R("RTL8106e", RTL_TD_1, FIRMWARE_8106E_2, - JUMBO_1K, true), + _R("RTL8106e", RTL_TD_1, FIRMWARE_8106E_2, JUMBO_1K), [RTL_GIGA_MAC_VER_44] = - _R("RTL8411", RTL_TD_1, FIRMWARE_8411_2, - JUMBO_9K, false), + _R("RTL8411", RTL_TD_1, FIRMWARE_8411_2, JUMBO_9K), [RTL_GIGA_MAC_VER_45] = - _R("RTL8168h/8111h", RTL_TD_1, FIRMWARE_8168H_1, - JUMBO_9K, false), + _R("RTL8168h/8111h", RTL_TD_1, FIRMWARE_8168H_1, JUMBO_9K), [RTL_GIGA_MAC_VER_46] = - _R("RTL8168h/8111h", RTL_TD_1, FIRMWARE_8168H_2, - JUMBO_9K, false), + _R("RTL8168h/8111h", RTL_TD_1, FIRMWARE_8168H_2, JUMBO_9K), [RTL_GIGA_MAC_VER_47] = - _R("RTL8107e", RTL_TD_1, FIRMWARE_8107E_1, - JUMBO_1K, false), + _R("RTL8107e", RTL_TD_1, FIRMWARE_8107E_1, JUMBO_1K), [RTL_GIGA_MAC_VER_48] = - _R("RTL8107e", RTL_TD_1, FIRMWARE_8107E_2, - JUMBO_1K, false), + _R("RTL8107e", RTL_TD_1, FIRMWARE_8107E_2, JUMBO_1K), [RTL_GIGA_MAC_VER_49] = - _R("RTL8168ep/8111ep", RTL_TD_1, NULL, - JUMBO_9K, false), + _R("RTL8168ep/8111ep", RTL_TD_1, NULL, JUMBO_9K), [RTL_GIGA_MAC_VER_50] = - _R("RTL8168ep/8111ep", RTL_TD_1, NULL, - JUMBO_9K, false), + _R("RTL8168ep/8111ep", RTL_TD_1, NULL, JUMBO_9K), [RTL_GIGA_MAC_VER_51] = - _R("RTL8168ep/8111ep", RTL_TD_1, NULL, - JUMBO_9K, false), + _R("RTL8168ep/8111ep", RTL_TD_1, NULL, JUMBO_9K), }; #undef _R @@ -345,7 +319,6 @@ static const struct pci_device_id rtl8169_pci_tbl[] = { MODULE_DEVICE_TABLE(pci, rtl8169_pci_tbl); -static int rx_buf_sz = 16383; static int use_dac = -1; static struct { u32 msg_enable; @@ -437,13 +410,8 @@ enum rtl8168_8101_registers { CSIAR = 0x68, #define CSIAR_FLAG 0x80000000 #define CSIAR_WRITE_CMD 0x80000000 -#define CSIAR_BYTE_ENABLE 0x0f -#define CSIAR_BYTE_ENABLE_SHIFT 12 -#define CSIAR_ADDR_MASK 0x0fff -#define CSIAR_FUNC_CARD 0x00000000 -#define CSIAR_FUNC_SDIO 0x00010000 -#define CSIAR_FUNC_NIC 0x00020000 -#define CSIAR_FUNC_NIC2 0x00010000 +#define CSIAR_BYTE_ENABLE 0x0000f000 +#define CSIAR_ADDR_MASK 0x00000fff PMCH = 0x6f, EPHYAR = 0x80, #define EPHYAR_FLAG 0x80000000 @@ -626,6 +594,7 @@ enum rtl_register_content { RxChkSum = (1 << 5), PCIDAC = (1 << 4), PCIMulRW = (1 << 3), +#define INTT_MASK GENMASK(1, 0) INTT_0 = 0x0000, // 8168 INTT_1 = 0x0001, // 8168 INTT_2 = 0x0002, // 8168 @@ -716,6 +685,7 @@ enum rtl_rx_desc_bit { }; #define RsvdMask 0x3fffc000 +#define CPCMD_QUIRK_MASK (Normal_mode | RxVlan | RxChkSum | INTT_MASK) struct TxDesc { __le32 opts1; @@ -778,7 +748,6 @@ struct rtl8169_private { struct net_device *dev; struct napi_struct napi; u32 msg_enable; - u16 txd_version; u16 mac_version; u32 cur_rx; /* Index into the Rx descriptor buffer of next Rx pkt. */ u32 cur_tx; /* Index into the Tx descriptor buffer of next Rx pkt. */ @@ -802,26 +771,16 @@ struct rtl8169_private { int (*read)(struct rtl8169_private *, int); } mdio_ops; - struct pll_power_ops { - void (*down)(struct rtl8169_private *); - void (*up)(struct rtl8169_private *); - } pll_power_ops; - struct jumbo_ops { void (*enable)(struct rtl8169_private *); void (*disable)(struct rtl8169_private *); } jumbo_ops; - struct csi_ops { - void (*write)(struct rtl8169_private *, int, int); - u32 (*read)(struct rtl8169_private *, int); - } csi_ops; - int (*set_speed)(struct net_device *, u8 aneg, u16 sp, u8 dpx, u32 adv); int (*get_link_ksettings)(struct net_device *, struct ethtool_link_ksettings *); void (*phy_reset_enable)(struct rtl8169_private *tp); - void (*hw_start)(struct net_device *); + void (*hw_start)(struct rtl8169_private *tp); unsigned int (*phy_reset_pending)(struct rtl8169_private *tp); unsigned int (*link_ok)(struct rtl8169_private *tp); int (*do_ioctl)(struct rtl8169_private *tp, struct mii_ioctl_data *data, int cmd); @@ -833,14 +792,11 @@ struct rtl8169_private { struct work_struct work; } wk; - unsigned features; - struct mii_if_info mii; dma_addr_t counters_phys_addr; struct rtl8169_counters *counters; struct rtl8169_tc_offsets tc_offset; u32 saved_wolopts; - u32 opts1_mask; struct rtl_fw { const struct firmware *fw; @@ -1645,23 +1601,8 @@ static u32 __rtl8169_get_wol(struct rtl8169_private *tp) if (options & LinkUp) wolopts |= WAKE_PHY; switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: if (rtl_eri_read(tp, 0xdc, ERIAR_EXGMAC) & MagicPacket_v2) wolopts |= WAKE_MAGIC; break; @@ -1722,23 +1663,8 @@ static void __rtl8169_set_wol(struct rtl8169_private *tp, u32 wolopts) RTL_W8(tp, Cfg9346, Cfg9346_Unlock); switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: tmp = ARRAY_SIZE(cfg) - 1; if (wolopts & WAKE_MAGIC) rtl_w0w1_eri(tp, @@ -1960,18 +1886,20 @@ static netdev_features_t rtl8169_fix_features(struct net_device *dev, features &= ~NETIF_F_ALL_TSO; if (dev->mtu > JUMBO_1K && - !rtl_chip_infos[tp->mac_version].jumbo_tx_csum) + tp->mac_version > RTL_GIGA_MAC_VER_06) features &= ~NETIF_F_IP_CSUM; return features; } -static void __rtl8169_set_features(struct net_device *dev, - netdev_features_t features) +static int rtl8169_set_features(struct net_device *dev, + netdev_features_t features) { struct rtl8169_private *tp = netdev_priv(dev); u32 rx_config; + rtl_lock_work(tp); + rx_config = RTL_R32(tp, RxConfig); if (features & NETIF_F_RXALL) rx_config |= (AcceptErr | AcceptRunt); @@ -1990,28 +1918,14 @@ static void __rtl8169_set_features(struct net_device *dev, else tp->cp_cmd &= ~RxVlan; - tp->cp_cmd |= RTL_R16(tp, CPlusCmd) & ~(RxVlan | RxChkSum); - RTL_W16(tp, CPlusCmd, tp->cp_cmd); RTL_R16(tp, CPlusCmd); -} -static int rtl8169_set_features(struct net_device *dev, - netdev_features_t features) -{ - struct rtl8169_private *tp = netdev_priv(dev); - - features &= NETIF_F_RXALL | NETIF_F_RXCSUM | NETIF_F_HW_VLAN_CTAG_RX; - - rtl_lock_work(tp); - if (features ^ dev->features) - __rtl8169_set_features(dev, features); rtl_unlock_work(tp); return 0; } - static inline u32 rtl8169_tx_vlan_tag(struct sk_buff *skb) { return (skb_vlan_tag_present(skb)) ? @@ -2155,9 +2069,8 @@ DECLARE_RTL_COND(rtl_counters_cond) return RTL_R32(tp, CounterAddrLow) & (CounterReset | CounterDump); } -static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd) +static bool rtl8169_do_counters(struct rtl8169_private *tp, u32 counter_cmd) { - struct rtl8169_private *tp = netdev_priv(dev); dma_addr_t paddr = tp->counters_phys_addr; u32 cmd; @@ -2170,10 +2083,8 @@ static bool rtl8169_do_counters(struct net_device *dev, u32 counter_cmd) return rtl_udelay_loop_wait_low(tp, &rtl_counters_cond, 10, 1000); } -static bool rtl8169_reset_counters(struct net_device *dev) +static bool rtl8169_reset_counters(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); - /* * Versions prior to RTL_GIGA_MAC_VER_19 don't support resetting the * tally counters. @@ -2181,13 +2092,11 @@ static bool rtl8169_reset_counters(struct net_device *dev) if (tp->mac_version < RTL_GIGA_MAC_VER_19) return true; - return rtl8169_do_counters(dev, CounterReset); + return rtl8169_do_counters(tp, CounterReset); } -static bool rtl8169_update_counters(struct net_device *dev) +static bool rtl8169_update_counters(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); - /* * Some chips are unable to dump tally counters when the receiver * is disabled. @@ -2195,12 +2104,11 @@ static bool rtl8169_update_counters(struct net_device *dev) if ((RTL_R8(tp, ChipCmd) & CmdRxEnb) == 0) return true; - return rtl8169_do_counters(dev, CounterDump); + return rtl8169_do_counters(tp, CounterDump); } -static bool rtl8169_init_counter_offsets(struct net_device *dev) +static bool rtl8169_init_counter_offsets(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); struct rtl8169_counters *counters = tp->counters; bool ret = false; @@ -2223,10 +2131,10 @@ static bool rtl8169_init_counter_offsets(struct net_device *dev) return true; /* If both, reset and update fail, propagate to caller. */ - if (rtl8169_reset_counters(dev)) + if (rtl8169_reset_counters(tp)) ret = true; - if (rtl8169_update_counters(dev)) + if (rtl8169_update_counters(tp)) ret = true; tp->tc_offset.tx_errors = counters->tx_errors; @@ -2249,7 +2157,7 @@ static void rtl8169_get_ethtool_stats(struct net_device *dev, pm_runtime_get_noresume(d); if (pm_runtime_active(d)) - rtl8169_update_counters(dev); + rtl8169_update_counters(tp); pm_runtime_put_noidle(d); @@ -2391,7 +2299,7 @@ static int rtl_get_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) if (IS_ERR(ci)) return PTR_ERR(ci); - scale = &ci->scalev[RTL_R16(tp, CPlusCmd) & 3]; + scale = &ci->scalev[tp->cp_cmd & INTT_MASK]; /* read IntrMitigate and adjust according to scale */ for (w = RTL_R16(tp, IntrMitigate); w; w >>= RTL_COALESCE_SHIFT, p++) { @@ -2490,7 +2398,7 @@ static int rtl_set_coalesce(struct net_device *dev, struct ethtool_coalesce *ec) RTL_W16(tp, IntrMitigate, swab16(w)); - tp->cp_cmd = (tp->cp_cmd & ~3) | cp01; + tp->cp_cmd = (tp->cp_cmd & ~INTT_MASK) | cp01; RTL_W16(tp, CPlusCmd, tp->cp_cmd); RTL_R16(tp, CPlusCmd); @@ -2520,7 +2428,7 @@ static const struct ethtool_ops rtl8169_ethtool_ops = { }; static void rtl8169_get_mac_version(struct rtl8169_private *tp, - struct net_device *dev, u8 default_version) + u8 default_version) { /* * The driver currently handles the 8168Bf and the 8168Be identically @@ -2560,12 +2468,10 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, /* 8168E family. */ { 0x7c800000, 0x2c800000, RTL_GIGA_MAC_VER_34 }, - { 0x7cf00000, 0x2c200000, RTL_GIGA_MAC_VER_33 }, { 0x7cf00000, 0x2c100000, RTL_GIGA_MAC_VER_32 }, { 0x7c800000, 0x2c000000, RTL_GIGA_MAC_VER_33 }, /* 8168D family. */ - { 0x7cf00000, 0x28300000, RTL_GIGA_MAC_VER_26 }, { 0x7cf00000, 0x28100000, RTL_GIGA_MAC_VER_25 }, { 0x7c800000, 0x28000000, RTL_GIGA_MAC_VER_26 }, @@ -2575,32 +2481,24 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, { 0x7cf00000, 0x28b00000, RTL_GIGA_MAC_VER_31 }, /* 8168C family. */ - { 0x7cf00000, 0x3cb00000, RTL_GIGA_MAC_VER_24 }, { 0x7cf00000, 0x3c900000, RTL_GIGA_MAC_VER_23 }, { 0x7cf00000, 0x3c800000, RTL_GIGA_MAC_VER_18 }, { 0x7c800000, 0x3c800000, RTL_GIGA_MAC_VER_24 }, { 0x7cf00000, 0x3c000000, RTL_GIGA_MAC_VER_19 }, { 0x7cf00000, 0x3c200000, RTL_GIGA_MAC_VER_20 }, { 0x7cf00000, 0x3c300000, RTL_GIGA_MAC_VER_21 }, - { 0x7cf00000, 0x3c400000, RTL_GIGA_MAC_VER_22 }, { 0x7c800000, 0x3c000000, RTL_GIGA_MAC_VER_22 }, /* 8168B family. */ { 0x7cf00000, 0x38000000, RTL_GIGA_MAC_VER_12 }, - { 0x7cf00000, 0x38500000, RTL_GIGA_MAC_VER_17 }, { 0x7c800000, 0x38000000, RTL_GIGA_MAC_VER_17 }, { 0x7c800000, 0x30000000, RTL_GIGA_MAC_VER_11 }, /* 8101 family. */ - { 0x7cf00000, 0x44900000, RTL_GIGA_MAC_VER_39 }, { 0x7c800000, 0x44800000, RTL_GIGA_MAC_VER_39 }, { 0x7c800000, 0x44000000, RTL_GIGA_MAC_VER_37 }, - { 0x7cf00000, 0x40b00000, RTL_GIGA_MAC_VER_30 }, - { 0x7cf00000, 0x40a00000, RTL_GIGA_MAC_VER_30 }, { 0x7cf00000, 0x40900000, RTL_GIGA_MAC_VER_29 }, { 0x7c800000, 0x40800000, RTL_GIGA_MAC_VER_30 }, - { 0x7cf00000, 0x34a00000, RTL_GIGA_MAC_VER_09 }, - { 0x7cf00000, 0x24a00000, RTL_GIGA_MAC_VER_09 }, { 0x7cf00000, 0x34900000, RTL_GIGA_MAC_VER_08 }, { 0x7cf00000, 0x24900000, RTL_GIGA_MAC_VER_08 }, { 0x7cf00000, 0x34800000, RTL_GIGA_MAC_VER_07 }, @@ -2635,8 +2533,8 @@ static void rtl8169_get_mac_version(struct rtl8169_private *tp, tp->mac_version = p->mac_version; if (tp->mac_version == RTL_GIGA_MAC_NONE) { - netif_notice(tp, probe, dev, - "unknown MAC, using family default\n"); + dev_notice(tp_to_dev(tp), + "unknown MAC, using family default\n"); tp->mac_version = default_version; } else if (tp->mac_version == RTL_GIGA_MAC_VER_42) { tp->mac_version = tp->mii.supports_gmii ? @@ -4685,18 +4583,7 @@ static void rtl_init_mdio_ops(struct rtl8169_private *tp) ops->write = r8168dp_2_mdio_write; ops->read = r8168dp_2_mdio_read; break; - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: ops->write = r8168g_mdio_write; ops->read = r8168g_mdio_read; break; @@ -4741,21 +4628,7 @@ static void rtl_wol_suspend_quirk(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_32: case RTL_GIGA_MAC_VER_33: case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_39: - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_37 ... RTL_GIGA_MAC_VER_51: RTL_W32(tp, RxConfig, RTL_R32(tp, RxConfig) | AcceptBroadcast | AcceptMulticast | AcceptMyPhys); break; @@ -4775,79 +4648,13 @@ static bool rtl_wol_pll_power_down(struct rtl8169_private *tp) return true; } -static void r810x_phy_power_down(struct rtl8169_private *tp) -{ - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, MII_BMCR, BMCR_PDOWN); -} - -static void r810x_phy_power_up(struct rtl8169_private *tp) -{ - rtl_writephy(tp, 0x1f, 0x0000); - rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE); -} - -static void r810x_pll_power_down(struct rtl8169_private *tp) -{ - if (rtl_wol_pll_power_down(tp)) - return; - - r810x_phy_power_down(tp); - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_07: - case RTL_GIGA_MAC_VER_08: - case RTL_GIGA_MAC_VER_09: - case RTL_GIGA_MAC_VER_10: - case RTL_GIGA_MAC_VER_13: - case RTL_GIGA_MAC_VER_16: - break; - default: - RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80); - break; - } -} - -static void r810x_pll_power_up(struct rtl8169_private *tp) -{ - r810x_phy_power_up(tp); - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_07: - case RTL_GIGA_MAC_VER_08: - case RTL_GIGA_MAC_VER_09: - case RTL_GIGA_MAC_VER_10: - case RTL_GIGA_MAC_VER_13: - case RTL_GIGA_MAC_VER_16: - break; - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0); - break; - default: - RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0x80); - break; - } -} - static void r8168_phy_power_up(struct rtl8169_private *tp) { rtl_writephy(tp, 0x1f, 0x0000); switch (tp->mac_version) { case RTL_GIGA_MAC_VER_11: case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_17: - case RTL_GIGA_MAC_VER_18: - case RTL_GIGA_MAC_VER_19: - case RTL_GIGA_MAC_VER_20: - case RTL_GIGA_MAC_VER_21: - case RTL_GIGA_MAC_VER_22: - case RTL_GIGA_MAC_VER_23: - case RTL_GIGA_MAC_VER_24: - case RTL_GIGA_MAC_VER_25: - case RTL_GIGA_MAC_VER_26: - case RTL_GIGA_MAC_VER_27: - case RTL_GIGA_MAC_VER_28: + case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: rtl_writephy(tp, 0x0e, 0x0000); break; @@ -4855,6 +4662,9 @@ static void r8168_phy_power_up(struct rtl8169_private *tp) break; } rtl_writephy(tp, MII_BMCR, BMCR_ANENABLE); + + /* give MAC/PHY some time to resume */ + msleep(20); } static void r8168_phy_power_down(struct rtl8169_private *tp) @@ -4870,18 +4680,7 @@ static void r8168_phy_power_down(struct rtl8169_private *tp) case RTL_GIGA_MAC_VER_11: case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_17: - case RTL_GIGA_MAC_VER_18: - case RTL_GIGA_MAC_VER_19: - case RTL_GIGA_MAC_VER_20: - case RTL_GIGA_MAC_VER_21: - case RTL_GIGA_MAC_VER_22: - case RTL_GIGA_MAC_VER_23: - case RTL_GIGA_MAC_VER_24: - case RTL_GIGA_MAC_VER_25: - case RTL_GIGA_MAC_VER_26: - case RTL_GIGA_MAC_VER_27: - case RTL_GIGA_MAC_VER_28: + case RTL_GIGA_MAC_VER_17 ... RTL_GIGA_MAC_VER_28: case RTL_GIGA_MAC_VER_31: rtl_writephy(tp, 0x0e, 0x0200); default: @@ -4895,12 +4694,6 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) if (r8168_check_dash(tp)) return; - if ((tp->mac_version == RTL_GIGA_MAC_VER_23 || - tp->mac_version == RTL_GIGA_MAC_VER_24) && - (RTL_R16(tp, CPlusCmd) & ASF)) { - return; - } - if (tp->mac_version == RTL_GIGA_MAC_VER_32 || tp->mac_version == RTL_GIGA_MAC_VER_33) rtl_ephy_write(tp, 0x19, 0xff64); @@ -4911,16 +4704,15 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) r8168_phy_power_down(tp); switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_25: - case RTL_GIGA_MAC_VER_26: - case RTL_GIGA_MAC_VER_27: - case RTL_GIGA_MAC_VER_28: - case RTL_GIGA_MAC_VER_31: - case RTL_GIGA_MAC_VER_32: - case RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_37: + case RTL_GIGA_MAC_VER_39: + case RTL_GIGA_MAC_VER_43: case RTL_GIGA_MAC_VER_44: case RTL_GIGA_MAC_VER_45: case RTL_GIGA_MAC_VER_46: + case RTL_GIGA_MAC_VER_47: + case RTL_GIGA_MAC_VER_48: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) & ~0x80); @@ -4938,18 +4730,17 @@ static void r8168_pll_power_down(struct rtl8169_private *tp) static void r8168_pll_power_up(struct rtl8169_private *tp) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_25: - case RTL_GIGA_MAC_VER_26: - case RTL_GIGA_MAC_VER_27: - case RTL_GIGA_MAC_VER_28: - case RTL_GIGA_MAC_VER_31: - case RTL_GIGA_MAC_VER_32: - case RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_25 ... RTL_GIGA_MAC_VER_33: + case RTL_GIGA_MAC_VER_37: + case RTL_GIGA_MAC_VER_39: + case RTL_GIGA_MAC_VER_43: RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0x80); break; case RTL_GIGA_MAC_VER_44: case RTL_GIGA_MAC_VER_45: case RTL_GIGA_MAC_VER_46: + case RTL_GIGA_MAC_VER_47: + case RTL_GIGA_MAC_VER_48: case RTL_GIGA_MAC_VER_50: case RTL_GIGA_MAC_VER_51: RTL_W8(tp, PMCH, RTL_R8(tp, PMCH) | 0xc0); @@ -4966,130 +4757,41 @@ static void r8168_pll_power_up(struct rtl8169_private *tp) r8168_phy_power_up(tp); } -static void rtl_generic_op(struct rtl8169_private *tp, - void (*op)(struct rtl8169_private *)) -{ - if (op) - op(tp); -} - static void rtl_pll_power_down(struct rtl8169_private *tp) { - rtl_generic_op(tp, tp->pll_power_ops.down); + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06: + case RTL_GIGA_MAC_VER_13 ... RTL_GIGA_MAC_VER_15: + break; + default: + r8168_pll_power_down(tp); + } } static void rtl_pll_power_up(struct rtl8169_private *tp) { - rtl_generic_op(tp, tp->pll_power_ops.up); - - /* give MAC/PHY some time to resume */ - msleep(20); -} - -static void rtl_init_pll_power_ops(struct rtl8169_private *tp) -{ - struct pll_power_ops *ops = &tp->pll_power_ops; - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_07: - case RTL_GIGA_MAC_VER_08: - case RTL_GIGA_MAC_VER_09: - case RTL_GIGA_MAC_VER_10: - case RTL_GIGA_MAC_VER_16: - case RTL_GIGA_MAC_VER_29: - case RTL_GIGA_MAC_VER_30: - case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_39: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - ops->down = r810x_pll_power_down; - ops->up = r810x_pll_power_up; - break; - - case RTL_GIGA_MAC_VER_11: - case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_17: - case RTL_GIGA_MAC_VER_18: - case RTL_GIGA_MAC_VER_19: - case RTL_GIGA_MAC_VER_20: - case RTL_GIGA_MAC_VER_21: - case RTL_GIGA_MAC_VER_22: - case RTL_GIGA_MAC_VER_23: - case RTL_GIGA_MAC_VER_24: - case RTL_GIGA_MAC_VER_25: - case RTL_GIGA_MAC_VER_26: - case RTL_GIGA_MAC_VER_27: - case RTL_GIGA_MAC_VER_28: - case RTL_GIGA_MAC_VER_31: - case RTL_GIGA_MAC_VER_32: - case RTL_GIGA_MAC_VER_33: - case RTL_GIGA_MAC_VER_34: - case RTL_GIGA_MAC_VER_35: - case RTL_GIGA_MAC_VER_36: - case RTL_GIGA_MAC_VER_38: - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: - ops->down = r8168_pll_power_down; - ops->up = r8168_pll_power_up; + case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06: + case RTL_GIGA_MAC_VER_13 ... RTL_GIGA_MAC_VER_15: break; - default: - ops->down = NULL; - ops->up = NULL; - break; + r8168_pll_power_up(tp); } } static void rtl_init_rxcfg(struct rtl8169_private *tp) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_01: - case RTL_GIGA_MAC_VER_02: - case RTL_GIGA_MAC_VER_03: - case RTL_GIGA_MAC_VER_04: - case RTL_GIGA_MAC_VER_05: - case RTL_GIGA_MAC_VER_06: - case RTL_GIGA_MAC_VER_10: - case RTL_GIGA_MAC_VER_11: - case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_13: - case RTL_GIGA_MAC_VER_14: - case RTL_GIGA_MAC_VER_15: - case RTL_GIGA_MAC_VER_16: - case RTL_GIGA_MAC_VER_17: + case RTL_GIGA_MAC_VER_01 ... RTL_GIGA_MAC_VER_06: + case RTL_GIGA_MAC_VER_10 ... RTL_GIGA_MAC_VER_17: RTL_W32(tp, RxConfig, RX_FIFO_THRESH | RX_DMA_BURST); break; - case RTL_GIGA_MAC_VER_18: - case RTL_GIGA_MAC_VER_19: - case RTL_GIGA_MAC_VER_20: - case RTL_GIGA_MAC_VER_21: - case RTL_GIGA_MAC_VER_22: - case RTL_GIGA_MAC_VER_23: - case RTL_GIGA_MAC_VER_24: + case RTL_GIGA_MAC_VER_18 ... RTL_GIGA_MAC_VER_24: case RTL_GIGA_MAC_VER_34: case RTL_GIGA_MAC_VER_35: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST); break; - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: RTL_W32(tp, RxConfig, RX128_INT_EN | RX_MULTI_EN | RX_DMA_BURST | RX_EARLY_OFF); break; default: @@ -5105,16 +4807,20 @@ static void rtl8169_init_ring_indexes(struct rtl8169_private *tp) static void rtl_hw_jumbo_enable(struct rtl8169_private *tp) { - RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - rtl_generic_op(tp, tp->jumbo_ops.enable); - RTL_W8(tp, Cfg9346, Cfg9346_Lock); + if (tp->jumbo_ops.enable) { + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); + tp->jumbo_ops.enable(tp); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); + } } static void rtl_hw_jumbo_disable(struct rtl8169_private *tp) { - RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - rtl_generic_op(tp, tp->jumbo_ops.disable); - RTL_W8(tp, Cfg9346, Cfg9346_Lock); + if (tp->jumbo_ops.disable) { + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); + tp->jumbo_ops.disable(tp); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); + } } static void r8168c_hw_jumbo_enable(struct rtl8169_private *tp) @@ -5128,7 +4834,7 @@ static void r8168c_hw_jumbo_disable(struct rtl8169_private *tp) { RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~Jumbo_En1); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); } static void r8168dp_hw_jumbo_enable(struct rtl8169_private *tp) @@ -5154,7 +4860,7 @@ static void r8168e_hw_jumbo_disable(struct rtl8169_private *tp) RTL_W8(tp, MaxTxPacketSize, 0x0c); RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Jumbo_En0); RTL_W8(tp, Config4, RTL_R8(tp, Config4) & ~0x01); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); } static void r8168b_0_hw_jumbo_enable(struct rtl8169_private *tp) @@ -5166,7 +4872,7 @@ static void r8168b_0_hw_jumbo_enable(struct rtl8169_private *tp) static void r8168b_0_hw_jumbo_disable(struct rtl8169_private *tp) { rtl_tx_performance_tweak(tp, - (0x5 << MAX_READ_REQUEST_SHIFT) | PCI_EXP_DEVCTL_NOSNOOP_EN); + PCI_EXP_DEVCTL_READRQ_4096B | PCI_EXP_DEVCTL_NOSNOOP_EN); } static void r8168b_1_hw_jumbo_enable(struct rtl8169_private *tp) @@ -5226,18 +4932,7 @@ static void rtl_init_jumbo_ops(struct rtl8169_private *tp) * No action needed for jumbo frames with 8169. * No jumbo for 810x at all. */ - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: default: ops->disable = NULL; ops->enable = NULL; @@ -5323,32 +5018,21 @@ static void rtl8169_hw_reset(struct rtl8169_private *tp) rtl_rx_close(tp); - if (tp->mac_version == RTL_GIGA_MAC_VER_27 || - tp->mac_version == RTL_GIGA_MAC_VER_28 || - tp->mac_version == RTL_GIGA_MAC_VER_31) { + switch (tp->mac_version) { + case RTL_GIGA_MAC_VER_27: + case RTL_GIGA_MAC_VER_28: + case RTL_GIGA_MAC_VER_31: rtl_udelay_loop_wait_low(tp, &rtl_npq_cond, 20, 42*42); - } else if (tp->mac_version == RTL_GIGA_MAC_VER_34 || - tp->mac_version == RTL_GIGA_MAC_VER_35 || - tp->mac_version == RTL_GIGA_MAC_VER_36 || - tp->mac_version == RTL_GIGA_MAC_VER_37 || - tp->mac_version == RTL_GIGA_MAC_VER_38 || - tp->mac_version == RTL_GIGA_MAC_VER_40 || - tp->mac_version == RTL_GIGA_MAC_VER_41 || - tp->mac_version == RTL_GIGA_MAC_VER_42 || - tp->mac_version == RTL_GIGA_MAC_VER_43 || - tp->mac_version == RTL_GIGA_MAC_VER_44 || - tp->mac_version == RTL_GIGA_MAC_VER_45 || - tp->mac_version == RTL_GIGA_MAC_VER_46 || - tp->mac_version == RTL_GIGA_MAC_VER_47 || - tp->mac_version == RTL_GIGA_MAC_VER_48 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) { + break; + case RTL_GIGA_MAC_VER_34 ... RTL_GIGA_MAC_VER_38: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); rtl_udelay_loop_wait_high(tp, &rtl_txcfg_empty_cond, 100, 666); - } else { + break; + default: RTL_W8(tp, ChipCmd, RTL_R8(tp, ChipCmd) | StopReq); udelay(100); + break; } rtl_hw_reset(tp); @@ -5361,13 +5045,10 @@ static void rtl_set_rx_tx_config_registers(struct rtl8169_private *tp) (InterFrameGap << TxInterFrameGapShift)); } -static void rtl_hw_start(struct net_device *dev) +static void rtl_set_rx_max_size(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); - - tp->hw_start(dev); - - rtl_irq_enable_all(tp); + /* Low hurts. Let's disable the filtering. */ + RTL_W16(tp, RxMaxSize, R8169_RX_BUF_SIZE + 1); } static void rtl_set_rx_tx_desc_registers(struct rtl8169_private *tp) @@ -5383,19 +5064,23 @@ static void rtl_set_rx_tx_desc_registers(struct rtl8169_private *tp) RTL_W32(tp, RxDescAddrLow, ((u64) tp->RxPhyAddr) & DMA_BIT_MASK(32)); } -static u16 rtl_rw_cpluscmd(struct rtl8169_private *tp) +static void rtl_hw_start(struct rtl8169_private *tp) { - u16 cmd; + RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - cmd = RTL_R16(tp, CPlusCmd); - RTL_W16(tp, CPlusCmd, cmd); - return cmd; -} + tp->hw_start(tp); -static void rtl_set_rx_max_size(struct rtl8169_private *tp, unsigned int rx_buf_sz) -{ - /* Low hurts. Let's disable the filtering. */ - RTL_W16(tp, RxMaxSize, rx_buf_sz + 1); + rtl_set_rx_max_size(tp); + rtl_set_rx_tx_desc_registers(tp); + rtl_set_rx_tx_config_registers(tp); + RTL_W8(tp, Cfg9346, Cfg9346_Lock); + + /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ + RTL_R8(tp, IntrMask); + RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); + /* no early-rx interrupts */ + RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); + rtl_irq_enable_all(tp); } static void rtl8169_set_magic_reg(struct rtl8169_private *tp, unsigned mac_version) @@ -5475,36 +5160,14 @@ static void rtl_set_rx_mode(struct net_device *dev) RTL_W32(tp, RxConfig, tmp); } -static void rtl_hw_start_8169(struct net_device *dev) +static void rtl_hw_start_8169(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); - struct pci_dev *pdev = tp->pci_dev; - - if (tp->mac_version == RTL_GIGA_MAC_VER_05) { - RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) | PCIMulRW); - pci_write_config_byte(pdev, PCI_CACHE_LINE_SIZE, 0x08); - } - - RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - if (tp->mac_version == RTL_GIGA_MAC_VER_01 || - tp->mac_version == RTL_GIGA_MAC_VER_02 || - tp->mac_version == RTL_GIGA_MAC_VER_03 || - tp->mac_version == RTL_GIGA_MAC_VER_04) - RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); - - rtl_init_rxcfg(tp); + if (tp->mac_version == RTL_GIGA_MAC_VER_05) + pci_write_config_byte(tp->pci_dev, PCI_CACHE_LINE_SIZE, 0x08); RTL_W8(tp, EarlyTxThres, NoEarlyTx); - rtl_set_rx_max_size(tp, rx_buf_sz); - - if (tp->mac_version == RTL_GIGA_MAC_VER_01 || - tp->mac_version == RTL_GIGA_MAC_VER_02 || - tp->mac_version == RTL_GIGA_MAC_VER_03 || - tp->mac_version == RTL_GIGA_MAC_VER_04) - rtl_set_rx_tx_config_registers(tp); - - tp->cp_cmd |= rtl_rw_cpluscmd(tp) | PCIMulRW; + tp->cp_cmd |= PCIMulRW; if (tp->mac_version == RTL_GIGA_MAC_VER_02 || tp->mac_version == RTL_GIGA_MAC_VER_03) { @@ -5523,56 +5186,7 @@ static void rtl_hw_start_8169(struct net_device *dev) */ RTL_W16(tp, IntrMitigate, 0x0000); - rtl_set_rx_tx_desc_registers(tp); - - if (tp->mac_version != RTL_GIGA_MAC_VER_01 && - tp->mac_version != RTL_GIGA_MAC_VER_02 && - tp->mac_version != RTL_GIGA_MAC_VER_03 && - tp->mac_version != RTL_GIGA_MAC_VER_04) { - RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); - rtl_set_rx_tx_config_registers(tp); - } - - RTL_W8(tp, Cfg9346, Cfg9346_Lock); - - /* Initially a 10 us delay. Turned it into a PCI commit. - FR */ - RTL_R8(tp, IntrMask); - RTL_W32(tp, RxMissed, 0); - - rtl_set_rx_mode(dev); - - /* no early-rx interrupts */ - RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); -} - -static void rtl_csi_write(struct rtl8169_private *tp, int addr, int value) -{ - if (tp->csi_ops.write) - tp->csi_ops.write(tp, addr, value); -} - -static u32 rtl_csi_read(struct rtl8169_private *tp, int addr) -{ - return tp->csi_ops.read ? tp->csi_ops.read(tp, addr) : ~0; -} - -static void rtl_csi_access_enable(struct rtl8169_private *tp, u32 bits) -{ - u32 csi; - - csi = rtl_csi_read(tp, 0x070c) & 0x00ffffff; - rtl_csi_write(tp, 0x070c, csi | bits); -} - -static void rtl_csi_access_enable_1(struct rtl8169_private *tp) -{ - rtl_csi_access_enable(tp, 0x17000000); -} - -static void rtl_csi_access_enable_2(struct rtl8169_private *tp) -{ - rtl_csi_access_enable(tp, 0x27000000); } DECLARE_RTL_COND(rtl_csiar_cond) @@ -5580,101 +5194,55 @@ DECLARE_RTL_COND(rtl_csiar_cond) return RTL_R32(tp, CSIAR) & CSIAR_FLAG; } -static void r8169_csi_write(struct rtl8169_private *tp, int addr, int value) -{ - RTL_W32(tp, CSIDR, value); - RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | - CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); - - rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100); -} - -static u32 r8169_csi_read(struct rtl8169_private *tp, int addr) +static void rtl_csi_write(struct rtl8169_private *tp, int addr, int value) { - RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | - CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); + u32 func = PCI_FUNC(tp->pci_dev->devfn); - return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ? - RTL_R32(tp, CSIDR) : ~0; -} - -static void r8402_csi_write(struct rtl8169_private *tp, int addr, int value) -{ RTL_W32(tp, CSIDR, value); RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | - CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT | - CSIAR_FUNC_NIC); + CSIAR_BYTE_ENABLE | func << 16); rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100); } -static u32 r8402_csi_read(struct rtl8169_private *tp, int addr) +static u32 rtl_csi_read(struct rtl8169_private *tp, int addr) { - RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC | - CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); + u32 func = PCI_FUNC(tp->pci_dev->devfn); + + RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | func << 16 | + CSIAR_BYTE_ENABLE); return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ? RTL_R32(tp, CSIDR) : ~0; } -static void r8411_csi_write(struct rtl8169_private *tp, int addr, int value) +static void rtl_csi_access_enable(struct rtl8169_private *tp, u8 val) { - RTL_W32(tp, CSIDR, value); - RTL_W32(tp, CSIAR, CSIAR_WRITE_CMD | (addr & CSIAR_ADDR_MASK) | - CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT | - CSIAR_FUNC_NIC2); + struct pci_dev *pdev = tp->pci_dev; + u32 csi; - rtl_udelay_loop_wait_low(tp, &rtl_csiar_cond, 10, 100); + /* According to Realtek the value at config space address 0x070f + * controls the L0s/L1 entrance latency. We try standard ECAM access + * first and if it fails fall back to CSI. + */ + if (pdev->cfg_size > 0x070f && + pci_write_config_byte(pdev, 0x070f, val) == PCIBIOS_SUCCESSFUL) + return; + + netdev_notice_once(tp->dev, + "No native access to PCI extended config space, falling back to CSI\n"); + csi = rtl_csi_read(tp, 0x070c) & 0x00ffffff; + rtl_csi_write(tp, 0x070c, csi | val << 24); } -static u32 r8411_csi_read(struct rtl8169_private *tp, int addr) +static void rtl_csi_access_enable_1(struct rtl8169_private *tp) { - RTL_W32(tp, CSIAR, (addr & CSIAR_ADDR_MASK) | CSIAR_FUNC_NIC2 | - CSIAR_BYTE_ENABLE << CSIAR_BYTE_ENABLE_SHIFT); - - return rtl_udelay_loop_wait_high(tp, &rtl_csiar_cond, 10, 100) ? - RTL_R32(tp, CSIDR) : ~0; + rtl_csi_access_enable(tp, 0x17); } -static void rtl_init_csi_ops(struct rtl8169_private *tp) +static void rtl_csi_access_enable_2(struct rtl8169_private *tp) { - struct csi_ops *ops = &tp->csi_ops; - - switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_01: - case RTL_GIGA_MAC_VER_02: - case RTL_GIGA_MAC_VER_03: - case RTL_GIGA_MAC_VER_04: - case RTL_GIGA_MAC_VER_05: - case RTL_GIGA_MAC_VER_06: - case RTL_GIGA_MAC_VER_10: - case RTL_GIGA_MAC_VER_11: - case RTL_GIGA_MAC_VER_12: - case RTL_GIGA_MAC_VER_13: - case RTL_GIGA_MAC_VER_14: - case RTL_GIGA_MAC_VER_15: - case RTL_GIGA_MAC_VER_16: - case RTL_GIGA_MAC_VER_17: - ops->write = NULL; - ops->read = NULL; - break; - - case RTL_GIGA_MAC_VER_37: - case RTL_GIGA_MAC_VER_38: - ops->write = r8402_csi_write; - ops->read = r8402_csi_read; - break; - - case RTL_GIGA_MAC_VER_44: - ops->write = r8411_csi_write; - ops->read = r8411_csi_read; - break; - - default: - ops->write = r8169_csi_write; - ops->read = r8169_csi_read; - break; - } + rtl_csi_access_enable(tp, 0x27); } struct ephy_info { @@ -5721,25 +5289,15 @@ static void rtl_pcie_state_l2l3_enable(struct rtl8169_private *tp, bool enable) RTL_W8(tp, Config3, data); } -#define R8168_CPCMD_QUIRK_MASK (\ - EnableBist | \ - Mac_dbgo_oe | \ - Force_half_dup | \ - Force_rxflow_en | \ - Force_txflow_en | \ - Cxpl_dbg_sel | \ - ASF | \ - PktCntrDisable | \ - Mac_dbgo_sel) - static void rtl_hw_start_8168bb(struct rtl8169_private *tp) { RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); - RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + tp->cp_cmd &= CPCMD_QUIRK_MASK; + RTL_W16(tp, CPlusCmd, tp->cp_cmd); if (tp->dev->mtu <= ETH_DATA_LEN) { - rtl_tx_performance_tweak(tp, (0x5 << MAX_READ_REQUEST_SHIFT) | + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B | PCI_EXP_DEVCTL_NOSNOOP_EN); } } @@ -5760,11 +5318,12 @@ static void __rtl_hw_start_8168cp(struct rtl8169_private *tp) RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); rtl_disable_clock_request(tp); - RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + tp->cp_cmd &= CPCMD_QUIRK_MASK; + RTL_W16(tp, CPlusCmd, tp->cp_cmd); } static void rtl_hw_start_8168cp_1(struct rtl8169_private *tp) @@ -5791,9 +5350,10 @@ static void rtl_hw_start_8168cp_2(struct rtl8169_private *tp) RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + tp->cp_cmd &= CPCMD_QUIRK_MASK; + RTL_W16(tp, CPlusCmd, tp->cp_cmd); } static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) @@ -5808,9 +5368,10 @@ static void rtl_hw_start_8168cp_3(struct rtl8169_private *tp) RTL_W8(tp, MaxTxPacketSize, TxPacketMax); if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + tp->cp_cmd &= CPCMD_QUIRK_MASK; + RTL_W16(tp, CPlusCmd, tp->cp_cmd); } static void rtl_hw_start_8168c_1(struct rtl8169_private *tp) @@ -5865,9 +5426,10 @@ static void rtl_hw_start_8168d(struct rtl8169_private *tp) RTL_W8(tp, MaxTxPacketSize, TxPacketMax); if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); - RTL_W16(tp, CPlusCmd, RTL_R16(tp, CPlusCmd) & ~R8168_CPCMD_QUIRK_MASK); + tp->cp_cmd &= CPCMD_QUIRK_MASK; + RTL_W16(tp, CPlusCmd, tp->cp_cmd); } static void rtl_hw_start_8168dp(struct rtl8169_private *tp) @@ -5875,7 +5437,7 @@ static void rtl_hw_start_8168dp(struct rtl8169_private *tp) rtl_csi_access_enable_1(tp); if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); RTL_W8(tp, MaxTxPacketSize, TxPacketMax); @@ -5892,7 +5454,7 @@ static void rtl_hw_start_8168d_4(struct rtl8169_private *tp) rtl_csi_access_enable_1(tp); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); RTL_W8(tp, MaxTxPacketSize, TxPacketMax); @@ -5924,7 +5486,7 @@ static void rtl_hw_start_8168e_1(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8168e_1, ARRAY_SIZE(e_info_8168e_1)); if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); RTL_W8(tp, MaxTxPacketSize, TxPacketMax); @@ -5949,7 +5511,7 @@ static void rtl_hw_start_8168e_2(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8168e_2, ARRAY_SIZE(e_info_8168e_2)); if (tp->dev->mtu <= ETH_DATA_LEN) - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); @@ -5979,7 +5541,7 @@ static void rtl_hw_start_8168f(struct rtl8169_private *tp) { rtl_csi_access_enable_2(tp); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); rtl_eri_write(tp, 0xc0, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); rtl_eri_write(tp, 0xb8, ERIAR_MASK_0011, 0x0000, ERIAR_EXGMAC); @@ -6050,7 +5612,7 @@ static void rtl_hw_start_8168g(struct rtl8169_private *tp) rtl_csi_access_enable_1(tp); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC); rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC); @@ -6150,7 +5712,7 @@ static void rtl_hw_start_8168h_1(struct rtl8169_private *tp) rtl_csi_access_enable_1(tp); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC); rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC); @@ -6232,7 +5794,7 @@ static void rtl_hw_start_8168ep(struct rtl8169_private *tp) rtl_csi_access_enable_1(tp); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x00, 0x01, ERIAR_EXGMAC); rtl_w0w1_eri(tp, 0xdc, ERIAR_MASK_0001, 0x01, 0x00, ERIAR_EXGMAC); @@ -6328,18 +5890,12 @@ static void rtl_hw_start_8168ep_3(struct rtl8169_private *tp) r8168_mac_ocp_write(tp, 0xe860, data); } -static void rtl_hw_start_8168(struct net_device *dev) +static void rtl_hw_start_8168(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); - - RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - RTL_W8(tp, MaxTxPacketSize, TxPacketMax); - rtl_set_rx_max_size(tp, rx_buf_sz); - - tp->cp_cmd |= RTL_R16(tp, CPlusCmd) | PktCntrDisable | INTT_1; - + tp->cp_cmd &= ~INTT_MASK; + tp->cp_cmd |= PktCntrDisable | INTT_1; RTL_W16(tp, CPlusCmd, tp->cp_cmd); RTL_W16(tp, IntrMitigate, 0x5151); @@ -6350,12 +5906,6 @@ static void rtl_hw_start_8168(struct net_device *dev) tp->event_slow &= ~RxOverflow; } - rtl_set_rx_tx_desc_registers(tp); - - rtl_set_rx_tx_config_registers(tp); - - RTL_R8(tp, IntrMask); - switch (tp->mac_version) { case RTL_GIGA_MAC_VER_11: rtl_hw_start_8168bb(tp); @@ -6456,30 +6006,11 @@ static void rtl_hw_start_8168(struct net_device *dev) default: printk(KERN_ERR PFX "%s: unknown chipset (mac_version = %d).\n", - dev->name, tp->mac_version); + tp->dev->name, tp->mac_version); break; } - - RTL_W8(tp, Cfg9346, Cfg9346_Lock); - - RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); - - rtl_set_rx_mode(dev); - - RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); } -#define R810X_CPCMD_QUIRK_MASK (\ - EnableBist | \ - Mac_dbgo_oe | \ - Force_half_dup | \ - Force_rxflow_en | \ - Force_txflow_en | \ - Cxpl_dbg_sel | \ - ASF | \ - PktCntrDisable | \ - Mac_dbgo_sel) - static void rtl_hw_start_8102e_1(struct rtl8169_private *tp) { static const struct ephy_info e_info_8102e_1[] = { @@ -6498,7 +6029,7 @@ static void rtl_hw_start_8102e_1(struct rtl8169_private *tp) RTL_W8(tp, DBG_REG, FIX_NAK_1); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); RTL_W8(tp, Config1, LEDS1 | LEDS0 | Speed_down | MEMMAP | IOMAP | VPD | PMEnable); @@ -6515,7 +6046,7 @@ static void rtl_hw_start_8102e_2(struct rtl8169_private *tp) { rtl_csi_access_enable_2(tp); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); RTL_W8(tp, Config1, MEMMAP | IOMAP | VPD | PMEnable); RTL_W8(tp, Config3, RTL_R8(tp, Config3) & ~Beacon_en); @@ -6578,7 +6109,7 @@ static void rtl_hw_start_8402(struct rtl8169_private *tp) rtl_ephy_init(tp, e_info_8402, ARRAY_SIZE(e_info_8402)); - rtl_tx_performance_tweak(tp, 0x5 << MAX_READ_REQUEST_SHIFT); + rtl_tx_performance_tweak(tp, PCI_EXP_DEVCTL_READRQ_4096B); rtl_eri_write(tp, 0xc8, ERIAR_MASK_1111, 0x00000002, ERIAR_EXGMAC); rtl_eri_write(tp, 0xe8, ERIAR_MASK_1111, 0x00000006, ERIAR_EXGMAC); @@ -6603,32 +6134,21 @@ static void rtl_hw_start_8106(struct rtl8169_private *tp) rtl_pcie_state_l2l3_enable(tp, false); } -static void rtl_hw_start_8101(struct net_device *dev) +static void rtl_hw_start_8101(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); - struct pci_dev *pdev = tp->pci_dev; - if (tp->mac_version >= RTL_GIGA_MAC_VER_30) tp->event_slow &= ~RxFIFOOver; if (tp->mac_version == RTL_GIGA_MAC_VER_13 || tp->mac_version == RTL_GIGA_MAC_VER_16) - pcie_capability_set_word(pdev, PCI_EXP_DEVCTL, + pcie_capability_set_word(tp->pci_dev, PCI_EXP_DEVCTL, PCI_EXP_DEVCTL_NOSNOOP_EN); - RTL_W8(tp, Cfg9346, Cfg9346_Unlock); - RTL_W8(tp, MaxTxPacketSize, TxPacketMax); - rtl_set_rx_max_size(tp, rx_buf_sz); - - tp->cp_cmd &= ~R810X_CPCMD_QUIRK_MASK; + tp->cp_cmd &= CPCMD_QUIRK_MASK; RTL_W16(tp, CPlusCmd, tp->cp_cmd); - rtl_set_rx_tx_desc_registers(tp); - - rtl_set_rx_tx_config_registers(tp); - switch (tp->mac_version) { case RTL_GIGA_MAC_VER_07: rtl_hw_start_8102e_1(tp); @@ -6665,17 +6185,7 @@ static void rtl_hw_start_8101(struct net_device *dev) break; } - RTL_W8(tp, Cfg9346, Cfg9346_Lock); - RTL_W16(tp, IntrMitigate, 0x0000); - - RTL_W8(tp, ChipCmd, CmdTxEnb | CmdRxEnb); - - rtl_set_rx_mode(dev); - - RTL_R8(tp, IntrMask); - - RTL_W16(tp, MultiIntr, RTL_R16(tp, MultiIntr) & 0xf000); } static int rtl8169_change_mtu(struct net_device *dev, int new_mtu) @@ -6702,29 +6212,22 @@ static inline void rtl8169_make_unusable_by_asic(struct RxDesc *desc) static void rtl8169_free_rx_databuff(struct rtl8169_private *tp, void **data_buff, struct RxDesc *desc) { - dma_unmap_single(tp_to_dev(tp), le64_to_cpu(desc->addr), rx_buf_sz, - DMA_FROM_DEVICE); + dma_unmap_single(tp_to_dev(tp), le64_to_cpu(desc->addr), + R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); kfree(*data_buff); *data_buff = NULL; rtl8169_make_unusable_by_asic(desc); } -static inline void rtl8169_mark_to_asic(struct RxDesc *desc, u32 rx_buf_sz) +static inline void rtl8169_mark_to_asic(struct RxDesc *desc) { u32 eor = le32_to_cpu(desc->opts1) & RingEnd; /* Force memory writes to complete before releasing descriptor */ dma_wmb(); - desc->opts1 = cpu_to_le32(DescOwn | eor | rx_buf_sz); -} - -static inline void rtl8169_map_to_asic(struct RxDesc *desc, dma_addr_t mapping, - u32 rx_buf_sz) -{ - desc->addr = cpu_to_le64(mapping); - rtl8169_mark_to_asic(desc, rx_buf_sz); + desc->opts1 = cpu_to_le32(DescOwn | eor | R8169_RX_BUF_SIZE); } static inline void *rtl8169_align(void *data) @@ -6738,21 +6241,20 @@ static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp, void *data; dma_addr_t mapping; struct device *d = tp_to_dev(tp); - struct net_device *dev = tp->dev; - int node = dev->dev.parent ? dev_to_node(dev->dev.parent) : -1; + int node = dev_to_node(d); - data = kmalloc_node(rx_buf_sz, GFP_KERNEL, node); + data = kmalloc_node(R8169_RX_BUF_SIZE, GFP_KERNEL, node); if (!data) return NULL; if (rtl8169_align(data) != data) { kfree(data); - data = kmalloc_node(rx_buf_sz + 15, GFP_KERNEL, node); + data = kmalloc_node(R8169_RX_BUF_SIZE + 15, GFP_KERNEL, node); if (!data) return NULL; } - mapping = dma_map_single(d, rtl8169_align(data), rx_buf_sz, + mapping = dma_map_single(d, rtl8169_align(data), R8169_RX_BUF_SIZE, DMA_FROM_DEVICE); if (unlikely(dma_mapping_error(d, mapping))) { if (net_ratelimit()) @@ -6760,7 +6262,8 @@ static struct sk_buff *rtl8169_alloc_rx_data(struct rtl8169_private *tp, goto err_out; } - rtl8169_map_to_asic(desc, mapping, rx_buf_sz); + desc->addr = cpu_to_le64(mapping); + rtl8169_mark_to_asic(desc); return data; err_out: @@ -6792,9 +6295,6 @@ static int rtl8169_rx_fill(struct rtl8169_private *tp) for (i = 0; i < NUM_RX_DESC; i++) { void *data; - if (tp->Rx_databuff[i]) - continue; - data = rtl8169_alloc_rx_data(tp, tp->RxDescArray + i); if (!data) { rtl8169_make_unusable_by_asic(tp->RxDescArray + i); @@ -6811,14 +6311,12 @@ err_out: return -ENOMEM; } -static int rtl8169_init_ring(struct net_device *dev) +static int rtl8169_init_ring(struct rtl8169_private *tp) { - struct rtl8169_private *tp = netdev_priv(dev); - rtl8169_init_ring_indexes(tp); - memset(tp->tx_skb, 0x0, NUM_TX_DESC * sizeof(struct ring_info)); - memset(tp->Rx_databuff, 0x0, NUM_RX_DESC * sizeof(void *)); + memset(tp->tx_skb, 0, sizeof(tp->tx_skb)); + memset(tp->Rx_databuff, 0, sizeof(tp->Rx_databuff)); return rtl8169_rx_fill(tp); } @@ -6877,13 +6375,13 @@ static void rtl_reset_work(struct rtl8169_private *tp) rtl8169_hw_reset(tp); for (i = 0; i < NUM_RX_DESC; i++) - rtl8169_mark_to_asic(tp->RxDescArray + i, rx_buf_sz); + rtl8169_mark_to_asic(tp->RxDescArray + i); rtl8169_tx_clear(tp); rtl8169_init_ring_indexes(tp); napi_enable(&tp->napi); - rtl_hw_start(dev); + rtl_hw_start(tp); netif_wake_queue(dev); rtl8169_check_link_status(dev, tp); } @@ -7015,18 +6513,6 @@ static int msdn_giant_send_check(struct sk_buff *skb) return ret; } -static inline __be16 get_protocol(struct sk_buff *skb) -{ - __be16 protocol; - - if (skb->protocol == htons(ETH_P_8021Q)) - protocol = vlan_eth_hdr(skb)->h_vlan_encapsulated_proto; - else - protocol = skb->protocol; - - return protocol; -} - static bool rtl8169_tso_csum_v1(struct rtl8169_private *tp, struct sk_buff *skb, u32 *opts) { @@ -7063,7 +6549,7 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, return false; } - switch (get_protocol(skb)) { + switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): opts[0] |= TD1_GTSENV4; break; @@ -7095,7 +6581,7 @@ static bool rtl8169_tso_csum_v2(struct rtl8169_private *tp, return false; } - switch (get_protocol(skb)) { + switch (vlan_get_protocol(skb)) { case htons(ETH_P_IP): opts[1] |= TD1_IPv4_CS; ip_protocol = ip_hdr(skb)->protocol; @@ -7365,7 +6851,7 @@ static struct sk_buff *rtl8169_try_rx_copy(void *data, prefetch(data); skb = napi_alloc_skb(&tp->napi, pkt_size); if (skb) - memcpy(skb->data, data, pkt_size); + skb_copy_to_linear_data(skb, data, pkt_size); dma_sync_single_for_device(d, addr, pkt_size, DMA_FROM_DEVICE); return skb; @@ -7383,7 +6869,7 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget struct RxDesc *desc = tp->RxDescArray + entry; u32 status; - status = le32_to_cpu(desc->opts1) & tp->opts1_mask; + status = le32_to_cpu(desc->opts1); if (status & DescOwn) break; @@ -7401,14 +6887,16 @@ static int rtl_rx(struct net_device *dev, struct rtl8169_private *tp, u32 budget dev->stats.rx_length_errors++; if (status & RxCRC) dev->stats.rx_crc_errors++; - if (status & RxFOVF) { + /* RxFOVF is a reserved bit on later chip versions */ + if (tp->mac_version == RTL_GIGA_MAC_VER_01 && + status & RxFOVF) { rtl_schedule_task(tp, RTL_FLAG_TASK_RESET_PENDING); dev->stats.rx_fifo_errors++; - } - if ((status & (RxRUNT | RxCRC)) && - !(status & (RxRWT | RxFOVF)) && - (dev->features & NETIF_F_RXALL)) + } else if (status & (RxRUNT | RxCRC) && + !(status & RxRWT) && + dev->features & NETIF_F_RXALL) { goto process_pkt; + } } else { struct sk_buff *skb; dma_addr_t addr; @@ -7457,7 +6945,7 @@ process_pkt: } release_descriptor: desc->opts2 = 0; - rtl8169_mark_to_asic(desc, rx_buf_sz); + rtl8169_mark_to_asic(desc); } count = cur_rx - tp->cur_rx; @@ -7468,8 +6956,7 @@ release_descriptor: static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) { - struct net_device *dev = dev_instance; - struct rtl8169_private *tp = netdev_priv(dev); + struct rtl8169_private *tp = dev_instance; int handled = 0; u16 status; @@ -7480,7 +6967,7 @@ static irqreturn_t rtl8169_interrupt(int irq, void *dev_instance) handled = 1; rtl_irq_disable(tp); - napi_schedule(&tp->napi); + napi_schedule_irqoff(&tp->napi); } } return IRQ_RETVAL(handled); @@ -7631,7 +7118,7 @@ static int rtl8169_close(struct net_device *dev) pm_runtime_get_sync(&pdev->dev); /* Update counters before going down */ - rtl8169_update_counters(dev); + rtl8169_update_counters(tp); rtl_lock_work(tp); clear_bit(RTL_FLAG_TASK_ENABLED, tp->wk.flags); @@ -7641,7 +7128,7 @@ static int rtl8169_close(struct net_device *dev) cancel_work_sync(&tp->wk.work); - pci_free_irq(pdev, 0, dev); + pci_free_irq(pdev, 0, tp); dma_free_coherent(&pdev->dev, R8169_RX_RING_BYTES, tp->RxDescArray, tp->RxPhyAddr); @@ -7686,7 +7173,7 @@ static int rtl_open(struct net_device *dev) if (!tp->RxDescArray) goto err_free_tx_0; - retval = rtl8169_init_ring(dev); + retval = rtl8169_init_ring(tp); if (retval < 0) goto err_free_rx_1; @@ -7696,7 +7183,7 @@ static int rtl_open(struct net_device *dev) rtl_request_firmware(tp); - retval = pci_request_irq(pdev, 0, rtl8169_interrupt, NULL, dev, + retval = pci_request_irq(pdev, 0, rtl8169_interrupt, NULL, tp, dev->name); if (retval < 0) goto err_release_fw_2; @@ -7709,13 +7196,11 @@ static int rtl_open(struct net_device *dev) rtl8169_init_phy(dev, tp); - __rtl8169_set_features(dev, dev->features); - rtl_pll_power_up(tp); - rtl_hw_start(dev); + rtl_hw_start(tp); - if (!rtl8169_init_counter_offsets(dev)) + if (!rtl8169_init_counter_offsets(tp)) netif_warn(tp, hw, dev, "counter reset/update failed\n"); netif_start_queue(dev); @@ -7784,7 +7269,7 @@ rtl8169_get_stats64(struct net_device *dev, struct rtnl_link_stats64 *stats) * from tally counters. */ if (pm_runtime_active(&pdev->dev)) - rtl8169_update_counters(dev); + rtl8169_update_counters(tp); /* * Subtract values fetched during initalization. @@ -7880,7 +7365,7 @@ static int rtl8169_runtime_suspend(struct device *device) /* Update counters before going runtime suspend */ rtl8169_rx_missed(dev); - rtl8169_update_counters(dev); + rtl8169_update_counters(tp); return 0; } @@ -8020,9 +7505,7 @@ static const struct net_device_ops rtl_netdev_ops = { }; static const struct rtl_cfg_info { - void (*hw_start)(struct net_device *); - unsigned int region; - unsigned int align; + void (*hw_start)(struct rtl8169_private *tp); u16 event_slow; unsigned int has_gmii:1; const struct rtl_coalesce_info *coalesce_info; @@ -8030,8 +7513,6 @@ static const struct rtl_cfg_info { } rtl_cfg_infos [] = { [RTL_CFG_0] = { .hw_start = rtl_hw_start_8169, - .region = 1, - .align = 0, .event_slow = SYSErr | LinkChg | RxOverflow | RxFIFOOver, .has_gmii = 1, .coalesce_info = rtl_coalesce_info_8169, @@ -8039,8 +7520,6 @@ static const struct rtl_cfg_info { }, [RTL_CFG_1] = { .hw_start = rtl_hw_start_8168, - .region = 2, - .align = 8, .event_slow = SYSErr | LinkChg | RxOverflow, .has_gmii = 1, .coalesce_info = rtl_coalesce_info_8168_8136, @@ -8048,8 +7527,6 @@ static const struct rtl_cfg_info { }, [RTL_CFG_2] = { .hw_start = rtl_hw_start_8101, - .region = 2, - .align = 8, .event_slow = SYSErr | LinkChg | RxOverflow | RxFIFOOver | PCSTimeout, .coalesce_info = rtl_coalesce_info_8168_8136, @@ -8125,20 +7602,10 @@ static void rtl_hw_init_8168ep(struct rtl8169_private *tp) static void rtl_hw_initialize(struct rtl8169_private *tp) { switch (tp->mac_version) { - case RTL_GIGA_MAC_VER_40: - case RTL_GIGA_MAC_VER_41: - case RTL_GIGA_MAC_VER_42: - case RTL_GIGA_MAC_VER_43: - case RTL_GIGA_MAC_VER_44: - case RTL_GIGA_MAC_VER_45: - case RTL_GIGA_MAC_VER_46: - case RTL_GIGA_MAC_VER_47: - case RTL_GIGA_MAC_VER_48: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_48: rtl_hw_init_8168g(tp); break; - case RTL_GIGA_MAC_VER_49: - case RTL_GIGA_MAC_VER_50: - case RTL_GIGA_MAC_VER_51: + case RTL_GIGA_MAC_VER_49 ... RTL_GIGA_MAC_VER_51: rtl_hw_init_8168ep(tp); break; default: @@ -8149,11 +7616,10 @@ static void rtl_hw_initialize(struct rtl8169_private *tp) static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) { const struct rtl_cfg_info *cfg = rtl_cfg_infos + ent->driver_data; - const unsigned int region = cfg->region; struct rtl8169_private *tp; struct mii_if_info *mii; struct net_device *dev; - int chipset, i; + int chipset, region, i; int rc; if (netif_msg_drv(&debug)) { @@ -8188,43 +7654,41 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* enable device (incl. PCI PM wakeup and hotplug setup) */ rc = pcim_enable_device(pdev); if (rc < 0) { - netif_err(tp, probe, dev, "enable failure\n"); + dev_err(&pdev->dev, "enable failure\n"); return rc; } if (pcim_set_mwi(pdev) < 0) - netif_info(tp, probe, dev, "Mem-Wr-Inval unavailable\n"); + dev_info(&pdev->dev, "Mem-Wr-Inval unavailable\n"); - /* make sure PCI base addr 1 is MMIO */ - if (!(pci_resource_flags(pdev, region) & IORESOURCE_MEM)) { - netif_err(tp, probe, dev, - "region #%d not an MMIO resource, aborting\n", - region); + /* use first MMIO region */ + region = ffs(pci_select_bars(pdev, IORESOURCE_MEM)) - 1; + if (region < 0) { + dev_err(&pdev->dev, "no MMIO resource found\n"); return -ENODEV; } /* check for weird/broken PCI region reporting */ if (pci_resource_len(pdev, region) < R8169_REGS_SIZE) { - netif_err(tp, probe, dev, - "Invalid PCI region size(s), aborting\n"); + dev_err(&pdev->dev, "Invalid PCI region size(s), aborting\n"); return -ENODEV; } rc = pcim_iomap_regions(pdev, BIT(region), MODULENAME); if (rc < 0) { - netif_err(tp, probe, dev, "cannot remap MMIO, aborting\n"); + dev_err(&pdev->dev, "cannot remap MMIO, aborting\n"); return rc; } tp->mmio_addr = pcim_iomap_table(pdev)[region]; if (!pci_is_pcie(pdev)) - netif_info(tp, probe, dev, "not PCI Express\n"); + dev_info(&pdev->dev, "not PCI Express\n"); /* Identify chip attached to board */ - rtl8169_get_mac_version(tp, dev, cfg->default_ver); + rtl8169_get_mac_version(tp, cfg->default_ver); - tp->cp_cmd = 0; + tp->cp_cmd = RTL_R16(tp, CPlusCmd); if ((sizeof(dma_addr_t) > 4) && (use_dac == 1 || (use_dac == -1 && pci_is_pcie(pdev) && @@ -8239,7 +7703,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) } else { rc = pci_set_dma_mask(pdev, DMA_BIT_MASK(32)); if (rc < 0) { - netif_err(tp, probe, dev, "DMA configuration failed\n"); + dev_err(&pdev->dev, "DMA configuration failed\n"); return rc; } } @@ -8257,18 +7721,15 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) pci_set_master(pdev); rtl_init_mdio_ops(tp); - rtl_init_pll_power_ops(tp); rtl_init_jumbo_ops(tp); - rtl_init_csi_ops(tp); rtl8169_print_mac_version(tp); chipset = tp->mac_version; - tp->txd_version = rtl_chip_infos[chipset].txd_version; rc = rtl_alloc_irq(tp); if (rc < 0) { - netif_err(tp, probe, dev, "Can't allocate interrupt\n"); + dev_err(&pdev->dev, "Can't allocate interrupt\n"); return rc; } @@ -8296,29 +7757,18 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) u64_stats_init(&tp->tx_stats.syncp); /* Get MAC address */ - if (tp->mac_version == RTL_GIGA_MAC_VER_35 || - tp->mac_version == RTL_GIGA_MAC_VER_36 || - tp->mac_version == RTL_GIGA_MAC_VER_37 || - tp->mac_version == RTL_GIGA_MAC_VER_38 || - tp->mac_version == RTL_GIGA_MAC_VER_40 || - tp->mac_version == RTL_GIGA_MAC_VER_41 || - tp->mac_version == RTL_GIGA_MAC_VER_42 || - tp->mac_version == RTL_GIGA_MAC_VER_43 || - tp->mac_version == RTL_GIGA_MAC_VER_44 || - tp->mac_version == RTL_GIGA_MAC_VER_45 || - tp->mac_version == RTL_GIGA_MAC_VER_46 || - tp->mac_version == RTL_GIGA_MAC_VER_47 || - tp->mac_version == RTL_GIGA_MAC_VER_48 || - tp->mac_version == RTL_GIGA_MAC_VER_49 || - tp->mac_version == RTL_GIGA_MAC_VER_50 || - tp->mac_version == RTL_GIGA_MAC_VER_51) { - u16 mac_addr[3]; - + switch (tp->mac_version) { + u8 mac_addr[ETH_ALEN] __aligned(4); + case RTL_GIGA_MAC_VER_35 ... RTL_GIGA_MAC_VER_38: + case RTL_GIGA_MAC_VER_40 ... RTL_GIGA_MAC_VER_51: *(u32 *)&mac_addr[0] = rtl_eri_read(tp, 0xe0, ERIAR_EXGMAC); - *(u16 *)&mac_addr[2] = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC); + *(u16 *)&mac_addr[4] = rtl_eri_read(tp, 0xe4, ERIAR_EXGMAC); - if (is_valid_ether_addr((u8 *)mac_addr)) - rtl_rar_set(tp, (u8 *)mac_addr); + if (is_valid_ether_addr(mac_addr)) + rtl_rar_set(tp, mac_addr); + break; + default: + break; } for (i = 0; i < ETH_ALEN; i++) dev->dev_addr[i] = RTL_R8(tp, MAC0 + i); @@ -8326,7 +7776,7 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) dev->ethtool_ops = &rtl8169_ethtool_ops; dev->watchdog_timeo = RTL8169_TX_TIMEOUT; - netif_napi_add(dev, &tp->napi, rtl8169_poll, R8169_NAPI_WEIGHT); + netif_napi_add(dev, &tp->napi, rtl8169_poll, NAPI_POLL_WEIGHT); /* don't enable SG, IP_CSUM and TSO by default - it might not work * properly for all devices */ @@ -8349,13 +7799,17 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) /* Disallow toggling */ dev->hw_features &= ~NETIF_F_HW_VLAN_CTAG_RX; - if (tp->txd_version == RTL_TD_0) + switch (rtl_chip_infos[chipset].txd_version) { + case RTL_TD_0: tp->tso_csum = rtl8169_tso_csum_v1; - else if (tp->txd_version == RTL_TD_1) { + break; + case RTL_TD_1: tp->tso_csum = rtl8169_tso_csum_v2; dev->hw_features |= NETIF_F_IPV6_CSUM | NETIF_F_TSO6; - } else + break; + default: WARN_ON_ONCE(1); + } dev->hw_features |= NETIF_F_RXALL; dev->hw_features |= NETIF_F_RXFCS; @@ -8368,9 +7822,6 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) tp->event_slow = cfg->event_slow; tp->coalesce_info = cfg->coalesce_info; - tp->opts1_mask = (tp->mac_version != RTL_GIGA_MAC_VER_01) ? - ~(RxBOVF | RxFOVF) : ~0; - timer_setup(&tp->timer, rtl8169_phy_timer, 0); tp->rtl_fw = RTL_FIRMWARE_UNKNOWN; @@ -8387,15 +7838,15 @@ static int rtl_init_one(struct pci_dev *pdev, const struct pci_device_id *ent) if (rc < 0) return rc; - netif_info(tp, probe, dev, "%s at 0x%p, %pM, XID %08x IRQ %d\n", - rtl_chip_infos[chipset].name, tp->mmio_addr, dev->dev_addr, - (u32)(RTL_R32(tp, TxConfig) & 0x9cf0f8ff), + netif_info(tp, probe, dev, "%s, %pM, XID %08x, IRQ %d\n", + rtl_chip_infos[chipset].name, dev->dev_addr, + (u32)(RTL_R32(tp, TxConfig) & 0xfcf0f8ff), pci_irq_vector(pdev, 0)); if (rtl_chip_infos[chipset].jumbo_max != JUMBO_1K) { netif_info(tp, probe, dev, "jumbo features [frames: %d bytes, " "tx checksumming: %s]\n", rtl_chip_infos[chipset].jumbo_max, - rtl_chip_infos[chipset].jumbo_tx_csum ? "ok" : "ko"); + tp->mac_version <= RTL_GIGA_MAC_VER_06 ? "ok" : "ko"); } if (r8168_check_dash(tp)) diff --git a/drivers/net/ethernet/renesas/sh_eth.c b/drivers/net/ethernet/renesas/sh_eth.c index b6b90a6314e3..5970d9e5ddf1 100644 --- a/drivers/net/ethernet/renesas/sh_eth.c +++ b/drivers/net/ethernet/renesas/sh_eth.c @@ -442,12 +442,22 @@ static void sh_eth_modify(struct net_device *ndev, int enum_index, u32 clear, static void sh_eth_tsu_write(struct sh_eth_private *mdp, u32 data, int enum_index) { - iowrite32(data, mdp->tsu_addr + mdp->reg_offset[enum_index]); + u16 offset = mdp->reg_offset[enum_index]; + + if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) + return; + + iowrite32(data, mdp->tsu_addr + offset); } static u32 sh_eth_tsu_read(struct sh_eth_private *mdp, int enum_index) { - return ioread32(mdp->tsu_addr + mdp->reg_offset[enum_index]); + u16 offset = mdp->reg_offset[enum_index]; + + if (WARN_ON(offset == SH_ETH_OFFSET_INVALID)) + return ~0U; + + return ioread32(mdp->tsu_addr + offset); } static void sh_eth_select_mii(struct net_device *ndev) @@ -2610,12 +2620,6 @@ static int sh_eth_change_mtu(struct net_device *ndev, int new_mtu) } /* For TSU_POSTn. Please refer to the manual about this (strange) bitfields */ -static void *sh_eth_tsu_get_post_reg_offset(struct sh_eth_private *mdp, - int entry) -{ - return sh_eth_tsu_get_offset(mdp, TSU_POST1) + (entry / 8 * 4); -} - static u32 sh_eth_tsu_get_post_mask(int entry) { return 0x0f << (28 - ((entry % 8) * 4)); @@ -2630,27 +2634,25 @@ static void sh_eth_tsu_enable_cam_entry_post(struct net_device *ndev, int entry) { struct sh_eth_private *mdp = netdev_priv(ndev); + int reg = TSU_POST1 + entry / 8; u32 tmp; - void *reg_offset; - reg_offset = sh_eth_tsu_get_post_reg_offset(mdp, entry); - tmp = ioread32(reg_offset); - iowrite32(tmp | sh_eth_tsu_get_post_bit(mdp, entry), reg_offset); + tmp = sh_eth_tsu_read(mdp, reg); + sh_eth_tsu_write(mdp, tmp | sh_eth_tsu_get_post_bit(mdp, entry), reg); } static bool sh_eth_tsu_disable_cam_entry_post(struct net_device *ndev, int entry) { struct sh_eth_private *mdp = netdev_priv(ndev); + int reg = TSU_POST1 + entry / 8; u32 post_mask, ref_mask, tmp; - void *reg_offset; - reg_offset = sh_eth_tsu_get_post_reg_offset(mdp, entry); post_mask = sh_eth_tsu_get_post_mask(entry); ref_mask = sh_eth_tsu_get_post_bit(mdp, entry) & ~post_mask; - tmp = ioread32(reg_offset); - iowrite32(tmp & ~post_mask, reg_offset); + tmp = sh_eth_tsu_read(mdp, reg); + sh_eth_tsu_write(mdp, tmp & ~post_mask, reg); /* If other port enables, the function returns "true" */ return tmp & ref_mask; diff --git a/drivers/net/ethernet/rocker/rocker_main.c b/drivers/net/ethernet/rocker/rocker_main.c index 056cb6093630..e73e4febeedb 100644 --- a/drivers/net/ethernet/rocker/rocker_main.c +++ b/drivers/net/ethernet/rocker/rocker_main.c @@ -2738,6 +2738,8 @@ static void rocker_switchdev_event_work(struct work_struct *work) switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; err = rocker_world_port_fdb_add(rocker_port, fdb_info); if (err) { netdev_dbg(rocker_port->dev, "fdb add failed err=%d\n", err); @@ -2747,6 +2749,8 @@ static void rocker_switchdev_event_work(struct work_struct *work) break; case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; err = rocker_world_port_fdb_del(rocker_port, fdb_info); if (err) netdev_dbg(rocker_port->dev, "fdb add failed err=%d\n", err); diff --git a/drivers/net/ethernet/sfc/efx.c b/drivers/net/ethernet/sfc/efx.c index a4ebd8715494..88c1eee677c2 100644 --- a/drivers/net/ethernet/sfc/efx.c +++ b/drivers/net/ethernet/sfc/efx.c @@ -1551,6 +1551,38 @@ static int efx_probe_interrupts(struct efx_nic *efx) return 0; } +#if defined(CONFIG_SMP) +static void efx_set_interrupt_affinity(struct efx_nic *efx) +{ + struct efx_channel *channel; + unsigned int cpu; + + efx_for_each_channel(channel, efx) { + cpu = cpumask_local_spread(channel->channel, + pcibus_to_node(efx->pci_dev->bus)); + irq_set_affinity_hint(channel->irq, cpumask_of(cpu)); + } +} + +static void efx_clear_interrupt_affinity(struct efx_nic *efx) +{ + struct efx_channel *channel; + + efx_for_each_channel(channel, efx) + irq_set_affinity_hint(channel->irq, NULL); +} +#else +static void +efx_set_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused))) +{ +} + +static void +efx_clear_interrupt_affinity(struct efx_nic *efx __attribute__ ((unused))) +{ +} +#endif /* CONFIG_SMP */ + static int efx_soft_enable_interrupts(struct efx_nic *efx) { struct efx_channel *channel, *end_channel; @@ -3308,6 +3340,7 @@ static void efx_pci_remove_main(struct efx_nic *efx) cancel_work_sync(&efx->reset_work); efx_disable_interrupts(efx); + efx_clear_interrupt_affinity(efx); efx_nic_fini_interrupt(efx); efx_fini_port(efx); efx->type->fini(efx); @@ -3457,6 +3490,8 @@ static int efx_pci_probe_main(struct efx_nic *efx) rc = efx_nic_init_interrupt(efx); if (rc) goto fail5; + + efx_set_interrupt_affinity(efx); rc = efx_enable_interrupts(efx); if (rc) goto fail6; @@ -3464,6 +3499,7 @@ static int efx_pci_probe_main(struct efx_nic *efx) return 0; fail6: + efx_clear_interrupt_affinity(efx); efx_nic_fini_interrupt(efx); fail5: efx_fini_port(efx); diff --git a/drivers/net/ethernet/socionext/Kconfig b/drivers/net/ethernet/socionext/Kconfig index 6bcfe27fc560..b80048ca82a0 100644 --- a/drivers/net/ethernet/socionext/Kconfig +++ b/drivers/net/ethernet/socionext/Kconfig @@ -14,6 +14,8 @@ if NET_VENDOR_SOCIONEXT config SNI_AVE tristate "Socionext AVE ethernet support" depends on (ARCH_UNIPHIER || COMPILE_TEST) && OF + depends on HAS_IOMEM + select MFD_SYSCON select PHYLIB ---help--- Driver for gigabit ethernet MACs, called AVE, in the diff --git a/drivers/net/ethernet/socionext/netsec.c b/drivers/net/ethernet/socionext/netsec.c index f4c0b02ddad8..aa50331b7607 100644 --- a/drivers/net/ethernet/socionext/netsec.c +++ b/drivers/net/ethernet/socionext/netsec.c @@ -1057,7 +1057,8 @@ static int netsec_netdev_load_microcode(struct netsec_priv *priv) return 0; } -static int netsec_reset_hardware(struct netsec_priv *priv) +static int netsec_reset_hardware(struct netsec_priv *priv, + bool load_ucode) { u32 value; int err; @@ -1102,11 +1103,14 @@ static int netsec_reset_hardware(struct netsec_priv *priv) netsec_write(priv, NETSEC_REG_NRM_RX_CONFIG, 1 << NETSEC_REG_DESC_ENDIAN); - err = netsec_netdev_load_microcode(priv); - if (err) { - netif_err(priv, probe, priv->ndev, - "%s: failed to load microcode (%d)\n", __func__, err); - return err; + if (load_ucode) { + err = netsec_netdev_load_microcode(priv); + if (err) { + netif_err(priv, probe, priv->ndev, + "%s: failed to load microcode (%d)\n", + __func__, err); + return err; + } } /* start DMA engines */ @@ -1313,8 +1317,8 @@ static int netsec_netdev_open(struct net_device *ndev) napi_enable(&priv->napi); netif_start_queue(ndev); - /* Enable RX intr. */ - netsec_write(priv, NETSEC_REG_INTEN_SET, NETSEC_IRQ_RX); + /* Enable TX+RX intr. */ + netsec_write(priv, NETSEC_REG_INTEN_SET, NETSEC_IRQ_RX | NETSEC_IRQ_TX); return 0; err3: @@ -1328,6 +1332,7 @@ err1: static int netsec_netdev_stop(struct net_device *ndev) { + int ret; struct netsec_priv *priv = netdev_priv(ndev); netif_stop_queue(priv->ndev); @@ -1343,12 +1348,14 @@ static int netsec_netdev_stop(struct net_device *ndev) netsec_uninit_pkt_dring(priv, NETSEC_RING_TX); netsec_uninit_pkt_dring(priv, NETSEC_RING_RX); + ret = netsec_reset_hardware(priv, false); + phy_stop(ndev->phydev); phy_disconnect(ndev->phydev); pm_runtime_put_sync(priv->dev); - return 0; + return ret; } static int netsec_netdev_init(struct net_device *ndev) @@ -1364,7 +1371,7 @@ static int netsec_netdev_init(struct net_device *ndev) if (ret) goto err1; - ret = netsec_reset_hardware(priv); + ret = netsec_reset_hardware(priv, true); if (ret) goto err2; diff --git a/drivers/net/ethernet/socionext/sni_ave.c b/drivers/net/ethernet/socionext/sni_ave.c index 0b3b7a460641..f7ecceeb1e28 100644 --- a/drivers/net/ethernet/socionext/sni_ave.c +++ b/drivers/net/ethernet/socionext/sni_ave.c @@ -11,6 +11,7 @@ #include <linux/interrupt.h> #include <linux/io.h> #include <linux/iopoll.h> +#include <linux/mfd/syscon.h> #include <linux/mii.h> #include <linux/module.h> #include <linux/netdevice.h> @@ -18,6 +19,7 @@ #include <linux/of_mdio.h> #include <linux/of_platform.h> #include <linux/phy.h> +#include <linux/regmap.h> #include <linux/reset.h> #include <linux/types.h> #include <linux/u64_stats_sync.h> @@ -197,8 +199,16 @@ #define AVE_INTM_COUNT 20 #define AVE_FORCE_TXINTCNT 1 +/* SG */ +#define SG_ETPINMODE 0x540 +#define SG_ETPINMODE_EXTPHY BIT(1) /* for LD11 */ +#define SG_ETPINMODE_RMII(ins) BIT(ins) + #define IS_DESC_64BIT(p) ((p)->data->is_desc_64bit) +#define AVE_MAX_CLKS 4 +#define AVE_MAX_RSTS 2 + enum desc_id { AVE_DESCID_RX, AVE_DESCID_TX, @@ -225,10 +235,6 @@ struct ave_desc_info { struct ave_desc *desc; /* skb info related descriptor */ }; -struct ave_soc_data { - bool is_desc_64bit; -}; - struct ave_stats { struct u64_stats_sync syncp; u64 packets; @@ -245,11 +251,16 @@ struct ave_private { int phy_id; unsigned int desc_size; u32 msg_enable; - struct clk *clk; - struct reset_control *rst; + int nclks; + struct clk *clk[AVE_MAX_CLKS]; + int nrsts; + struct reset_control *rst[AVE_MAX_RSTS]; phy_interface_t phy_mode; struct phy_device *phydev; struct mii_bus *mdio; + struct regmap *regmap; + unsigned int pinmode_mask; + unsigned int pinmode_val; /* stats */ struct ave_stats stats_rx; @@ -272,6 +283,14 @@ struct ave_private { const struct ave_soc_data *data; }; +struct ave_soc_data { + bool is_desc_64bit; + const char *clock_names[AVE_MAX_CLKS]; + const char *reset_names[AVE_MAX_RSTS]; + int (*get_pinmode)(struct ave_private *priv, + phy_interface_t phy_mode, u32 arg); +}; + static u32 ave_desc_read(struct net_device *ndev, enum desc_id id, int entry, int offset) { @@ -1153,20 +1172,30 @@ static int ave_init(struct net_device *ndev) struct device_node *np = dev->of_node; struct device_node *mdio_np; struct phy_device *phydev; - int ret; + int nc, nr, ret; /* enable clk because of hw access until ndo_open */ - ret = clk_prepare_enable(priv->clk); - if (ret) { - dev_err(dev, "can't enable clock\n"); - return ret; + for (nc = 0; nc < priv->nclks; nc++) { + ret = clk_prepare_enable(priv->clk[nc]); + if (ret) { + dev_err(dev, "can't enable clock\n"); + goto out_clk_disable; + } } - ret = reset_control_deassert(priv->rst); - if (ret) { - dev_err(dev, "can't deassert reset\n"); - goto out_clk_disable; + + for (nr = 0; nr < priv->nrsts; nr++) { + ret = reset_control_deassert(priv->rst[nr]); + if (ret) { + dev_err(dev, "can't deassert reset\n"); + goto out_reset_assert; + } } + ret = regmap_update_bits(priv->regmap, SG_ETPINMODE, + priv->pinmode_mask, priv->pinmode_val); + if (ret) + return ret; + ave_global_reset(ndev); mdio_np = of_get_child_by_name(np, "mdio"); @@ -1207,9 +1236,11 @@ static int ave_init(struct net_device *ndev) out_mdio_unregister: mdiobus_unregister(priv->mdio); out_reset_assert: - reset_control_assert(priv->rst); + while (--nr >= 0) + reset_control_assert(priv->rst[nr]); out_clk_disable: - clk_disable_unprepare(priv->clk); + while (--nc >= 0) + clk_disable_unprepare(priv->clk[nc]); return ret; } @@ -1217,13 +1248,16 @@ out_clk_disable: static void ave_uninit(struct net_device *ndev) { struct ave_private *priv = netdev_priv(ndev); + int i; phy_disconnect(priv->phydev); mdiobus_unregister(priv->mdio); /* disable clk because of hw access after ndo_stop */ - reset_control_assert(priv->rst); - clk_disable_unprepare(priv->clk); + for (i = 0; i < priv->nrsts; i++) + reset_control_assert(priv->rst[i]); + for (i = 0; i < priv->nclks; i++) + clk_disable_unprepare(priv->clk[i]); } static int ave_open(struct net_device *ndev) @@ -1520,6 +1554,7 @@ static int ave_probe(struct platform_device *pdev) const struct ave_soc_data *data; struct device *dev = &pdev->dev; char buf[ETHTOOL_FWVERS_LEN]; + struct of_phandle_args args; phy_interface_t phy_mode; struct ave_private *priv; struct net_device *ndev; @@ -1527,8 +1562,9 @@ static int ave_probe(struct platform_device *pdev) struct resource *res; const void *mac_addr; void __iomem *base; + const char *name; + int i, irq, ret; u64 dma_mask; - int irq, ret; u32 ave_id; data = of_device_get_match_data(dev); @@ -1541,12 +1577,6 @@ static int ave_probe(struct platform_device *pdev) dev_err(dev, "phy-mode not found\n"); return -EINVAL; } - if ((!phy_interface_mode_is_rgmii(phy_mode)) && - phy_mode != PHY_INTERFACE_MODE_RMII && - phy_mode != PHY_INTERFACE_MODE_MII) { - dev_err(dev, "phy-mode is invalid\n"); - return -EINVAL; - } irq = platform_get_irq(pdev, 0); if (irq < 0) { @@ -1614,15 +1644,47 @@ static int ave_probe(struct platform_device *pdev) u64_stats_init(&priv->stats_tx.syncp); u64_stats_init(&priv->stats_rx.syncp); - priv->clk = devm_clk_get(dev, NULL); - if (IS_ERR(priv->clk)) { - ret = PTR_ERR(priv->clk); - goto out_free_netdev; + for (i = 0; i < AVE_MAX_CLKS; i++) { + name = priv->data->clock_names[i]; + if (!name) + break; + priv->clk[i] = devm_clk_get(dev, name); + if (IS_ERR(priv->clk[i])) { + ret = PTR_ERR(priv->clk[i]); + goto out_free_netdev; + } + priv->nclks++; + } + + for (i = 0; i < AVE_MAX_RSTS; i++) { + name = priv->data->reset_names[i]; + if (!name) + break; + priv->rst[i] = devm_reset_control_get_shared(dev, name); + if (IS_ERR(priv->rst[i])) { + ret = PTR_ERR(priv->rst[i]); + goto out_free_netdev; + } + priv->nrsts++; } - priv->rst = devm_reset_control_get_optional_shared(dev, NULL); - if (IS_ERR(priv->rst)) { - ret = PTR_ERR(priv->rst); + ret = of_parse_phandle_with_fixed_args(np, + "socionext,syscon-phy-mode", + 1, 0, &args); + if (ret) { + netdev_err(ndev, "can't get syscon-phy-mode property\n"); + goto out_free_netdev; + } + priv->regmap = syscon_node_to_regmap(args.np); + of_node_put(args.np); + if (IS_ERR(priv->regmap)) { + netdev_err(ndev, "can't map syscon-phy-mode\n"); + ret = PTR_ERR(priv->regmap); + goto out_free_netdev; + } + ret = priv->data->get_pinmode(priv, phy_mode, args.args[0]); + if (ret) { + netdev_err(ndev, "invalid phy-mode setting\n"); goto out_free_netdev; } @@ -1685,24 +1747,148 @@ static int ave_remove(struct platform_device *pdev) return 0; } +static int ave_pro4_get_pinmode(struct ave_private *priv, + phy_interface_t phy_mode, u32 arg) +{ + if (arg > 0) + return -EINVAL; + + priv->pinmode_mask = SG_ETPINMODE_RMII(0); + + switch (phy_mode) { + case PHY_INTERFACE_MODE_RMII: + priv->pinmode_val = SG_ETPINMODE_RMII(0); + break; + case PHY_INTERFACE_MODE_MII: + case PHY_INTERFACE_MODE_RGMII: + priv->pinmode_val = 0; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int ave_ld11_get_pinmode(struct ave_private *priv, + phy_interface_t phy_mode, u32 arg) +{ + if (arg > 0) + return -EINVAL; + + priv->pinmode_mask = SG_ETPINMODE_EXTPHY | SG_ETPINMODE_RMII(0); + + switch (phy_mode) { + case PHY_INTERFACE_MODE_INTERNAL: + priv->pinmode_val = 0; + break; + case PHY_INTERFACE_MODE_RMII: + priv->pinmode_val = SG_ETPINMODE_EXTPHY | SG_ETPINMODE_RMII(0); + break; + default: + return -EINVAL; + } + + return 0; +} + +static int ave_ld20_get_pinmode(struct ave_private *priv, + phy_interface_t phy_mode, u32 arg) +{ + if (arg > 0) + return -EINVAL; + + priv->pinmode_mask = SG_ETPINMODE_RMII(0); + + switch (phy_mode) { + case PHY_INTERFACE_MODE_RMII: + priv->pinmode_val = SG_ETPINMODE_RMII(0); + break; + case PHY_INTERFACE_MODE_RGMII: + priv->pinmode_val = 0; + break; + default: + return -EINVAL; + } + + return 0; +} + +static int ave_pxs3_get_pinmode(struct ave_private *priv, + phy_interface_t phy_mode, u32 arg) +{ + if (arg > 1) + return -EINVAL; + + priv->pinmode_mask = SG_ETPINMODE_RMII(arg); + + switch (phy_mode) { + case PHY_INTERFACE_MODE_RMII: + priv->pinmode_val = SG_ETPINMODE_RMII(arg); + break; + case PHY_INTERFACE_MODE_RGMII: + priv->pinmode_val = 0; + break; + default: + return -EINVAL; + } + + return 0; +} + static const struct ave_soc_data ave_pro4_data = { .is_desc_64bit = false, + .clock_names = { + "gio", "ether", "ether-gb", "ether-phy", + }, + .reset_names = { + "gio", "ether", + }, + .get_pinmode = ave_pro4_get_pinmode, }; static const struct ave_soc_data ave_pxs2_data = { .is_desc_64bit = false, + .clock_names = { + "ether", + }, + .reset_names = { + "ether", + }, + .get_pinmode = ave_pro4_get_pinmode, }; static const struct ave_soc_data ave_ld11_data = { .is_desc_64bit = false, + .clock_names = { + "ether", + }, + .reset_names = { + "ether", + }, + .get_pinmode = ave_ld11_get_pinmode, }; static const struct ave_soc_data ave_ld20_data = { .is_desc_64bit = true, + .clock_names = { + "ether", + }, + .reset_names = { + "ether", + }, + .get_pinmode = ave_ld20_get_pinmode, }; static const struct ave_soc_data ave_pxs3_data = { .is_desc_64bit = false, + .clock_names = { + "ether", + }, + .reset_names = { + "ether", + }, + .get_pinmode = ave_pxs3_get_pinmode, }; static const struct of_device_id of_ave_match[] = { diff --git a/drivers/net/ethernet/stmicro/stmmac/Makefile b/drivers/net/ethernet/stmicro/stmmac/Makefile index 972e4ef6d414..68e9e2640c62 100644 --- a/drivers/net/ethernet/stmicro/stmmac/Makefile +++ b/drivers/net/ethernet/stmicro/stmmac/Makefile @@ -4,7 +4,8 @@ stmmac-objs:= stmmac_main.o stmmac_ethtool.o stmmac_mdio.o ring_mode.o \ chain_mode.o dwmac_lib.o dwmac1000_core.o dwmac1000_dma.o \ dwmac100_core.o dwmac100_dma.o enh_desc.o norm_desc.o \ mmc_core.o stmmac_hwtstamp.o stmmac_ptp.o dwmac4_descs.o \ - dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o $(stmmac-y) + dwmac4_dma.o dwmac4_lib.o dwmac4_core.o dwmac5.o hwif.o \ + stmmac_tc.o $(stmmac-y) # Ordering matters. Generic driver must be last. obj-$(CONFIG_STMMAC_PLATFORM) += stmmac-platform.o diff --git a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c index e93c40b4631e..b9c9003060c5 100644 --- a/drivers/net/ethernet/stmicro/stmmac/chain_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/chain_mode.c @@ -24,7 +24,7 @@ #include "stmmac.h" -static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) +static int jumbo_frm(void *p, struct sk_buff *skb, int csum) { struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p; unsigned int nopaged_len = skb_headlen(skb); @@ -51,8 +51,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].buf = des2; tx_q->tx_skbuff_dma[entry].len = bmax; /* do not close the descriptor and do not set own bit */ - priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, STMMAC_CHAIN_MODE, - 0, false, skb->len); + stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum, STMMAC_CHAIN_MODE, + 0, false, skb->len); while (len != 0) { tx_q->tx_skbuff[entry] = NULL; @@ -68,9 +68,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) return -1; tx_q->tx_skbuff_dma[entry].buf = des2; tx_q->tx_skbuff_dma[entry].len = bmax; - priv->hw->desc->prepare_tx_desc(desc, 0, bmax, csum, - STMMAC_CHAIN_MODE, 1, - false, skb->len); + stmmac_prepare_tx_desc(priv, desc, 0, bmax, csum, + STMMAC_CHAIN_MODE, 1, false, skb->len); len -= bmax; i++; } else { @@ -83,9 +82,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].buf = des2; tx_q->tx_skbuff_dma[entry].len = len; /* last descriptor can be set now */ - priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, - STMMAC_CHAIN_MODE, 1, - true, skb->len); + stmmac_prepare_tx_desc(priv, desc, 0, len, csum, + STMMAC_CHAIN_MODE, 1, true, skb->len); len = 0; } } @@ -95,7 +93,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) return entry; } -static unsigned int stmmac_is_jumbo_frm(int len, int enh_desc) +static unsigned int is_jumbo_frm(int len, int enh_desc) { unsigned int ret = 0; @@ -107,7 +105,7 @@ static unsigned int stmmac_is_jumbo_frm(int len, int enh_desc) return ret; } -static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr, +static void init_dma_chain(void *des, dma_addr_t phy_addr, unsigned int size, unsigned int extend_desc) { /* @@ -137,7 +135,7 @@ static void stmmac_init_dma_chain(void *des, dma_addr_t phy_addr, } } -static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) +static void refill_desc3(void *priv_ptr, struct dma_desc *p) { struct stmmac_rx_queue *rx_q = (struct stmmac_rx_queue *)priv_ptr; struct stmmac_priv *priv = rx_q->priv_data; @@ -153,7 +151,7 @@ static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) sizeof(struct dma_desc))); } -static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) +static void clean_desc3(void *priv_ptr, struct dma_desc *p) { struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr; struct stmmac_priv *priv = tx_q->priv_data; @@ -171,9 +169,9 @@ static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) } const struct stmmac_mode_ops chain_mode_ops = { - .init = stmmac_init_dma_chain, - .is_jumbo_frm = stmmac_is_jumbo_frm, - .jumbo_frm = stmmac_jumbo_frm, - .refill_desc3 = stmmac_refill_desc3, - .clean_desc3 = stmmac_clean_desc3, + .init = init_dma_chain, + .is_jumbo_frm = is_jumbo_frm, + .jumbo_frm = jumbo_frm, + .refill_desc3 = refill_desc3, + .clean_desc3 = clean_desc3, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/common.h b/drivers/net/ethernet/stmicro/stmmac/common.h index ad2388aee463..a679cb729d1d 100644 --- a/drivers/net/ethernet/stmicro/stmmac/common.h +++ b/drivers/net/ethernet/stmicro/stmmac/common.h @@ -32,12 +32,14 @@ #endif #include "descs.h" +#include "hwif.h" #include "mmc.h" /* Synopsys Core versions */ #define DWMAC_CORE_3_40 0x34 #define DWMAC_CORE_3_50 0x35 #define DWMAC_CORE_4_00 0x40 +#define DWMAC_CORE_4_10 0x41 #define DWMAC_CORE_5_00 0x50 #define DWMAC_CORE_5_10 0x51 #define STMMAC_CHAN0 0 /* Always supported and default for all chips */ @@ -351,6 +353,10 @@ struct dma_features { unsigned int rx_fifo_size; /* Automotive Safety Package */ unsigned int asp; + /* RX Parser */ + unsigned int frpsel; + unsigned int frpbs; + unsigned int frpes; }; /* GMAC TX FIFO is 8K, Rx FIFO is 16K */ @@ -377,197 +383,11 @@ struct dma_features { #define JUMBO_LEN 9000 -/* Descriptors helpers */ -struct stmmac_desc_ops { - /* DMA RX descriptor ring initialization */ - void (*init_rx_desc) (struct dma_desc *p, int disable_rx_ic, int mode, - int end); - /* DMA TX descriptor ring initialization */ - void (*init_tx_desc) (struct dma_desc *p, int mode, int end); - - /* Invoked by the xmit function to prepare the tx descriptor */ - void (*prepare_tx_desc) (struct dma_desc *p, int is_fs, int len, - bool csum_flag, int mode, bool tx_own, - bool ls, unsigned int tot_pkt_len); - void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1, - int len2, bool tx_own, bool ls, - unsigned int tcphdrlen, - unsigned int tcppayloadlen); - /* Set/get the owner of the descriptor */ - void (*set_tx_owner) (struct dma_desc *p); - int (*get_tx_owner) (struct dma_desc *p); - /* Clean the tx descriptor as soon as the tx irq is received */ - void (*release_tx_desc) (struct dma_desc *p, int mode); - /* Clear interrupt on tx frame completion. When this bit is - * set an interrupt happens as soon as the frame is transmitted */ - void (*set_tx_ic)(struct dma_desc *p); - /* Last tx segment reports the transmit status */ - int (*get_tx_ls) (struct dma_desc *p); - /* Return the transmit status looking at the TDES1 */ - int (*tx_status) (void *data, struct stmmac_extra_stats *x, - struct dma_desc *p, void __iomem *ioaddr); - /* Get the buffer size from the descriptor */ - int (*get_tx_len) (struct dma_desc *p); - /* Handle extra events on specific interrupts hw dependent */ - void (*set_rx_owner) (struct dma_desc *p); - /* Get the receive frame size */ - int (*get_rx_frame_len) (struct dma_desc *p, int rx_coe_type); - /* Return the reception status looking at the RDES1 */ - int (*rx_status) (void *data, struct stmmac_extra_stats *x, - struct dma_desc *p); - void (*rx_extended_status) (void *data, struct stmmac_extra_stats *x, - struct dma_extended_desc *p); - /* Set tx timestamp enable bit */ - void (*enable_tx_timestamp) (struct dma_desc *p); - /* get tx timestamp status */ - int (*get_tx_timestamp_status) (struct dma_desc *p); - /* get timestamp value */ - u64(*get_timestamp) (void *desc, u32 ats); - /* get rx timestamp status */ - int (*get_rx_timestamp_status)(void *desc, void *next_desc, u32 ats); - /* Display ring */ - void (*display_ring)(void *head, unsigned int size, bool rx); - /* set MSS via context descriptor */ - void (*set_mss)(struct dma_desc *p, unsigned int mss); -}; - extern const struct stmmac_desc_ops enh_desc_ops; extern const struct stmmac_desc_ops ndesc_ops; -/* Specific DMA helpers */ -struct stmmac_dma_ops { - /* DMA core initialization */ - int (*reset)(void __iomem *ioaddr); - void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, - u32 dma_tx, u32 dma_rx, int atds); - void (*init_chan)(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, u32 chan); - void (*init_rx_chan)(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, - u32 dma_rx_phy, u32 chan); - void (*init_tx_chan)(void __iomem *ioaddr, - struct stmmac_dma_cfg *dma_cfg, - u32 dma_tx_phy, u32 chan); - /* Configure the AXI Bus Mode Register */ - void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi); - /* Dump DMA registers */ - void (*dump_regs)(void __iomem *ioaddr, u32 *reg_space); - /* Set tx/rx threshold in the csr6 register - * An invalid value enables the store-and-forward mode */ - void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode, - int rxfifosz); - void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel, - int fifosz, u8 qmode); - void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel, - int fifosz, u8 qmode); - /* To track extra statistic (if supported) */ - void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, - void __iomem *ioaddr); - void (*enable_dma_transmission) (void __iomem *ioaddr); - void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan); - void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan); - void (*start_tx)(void __iomem *ioaddr, u32 chan); - void (*stop_tx)(void __iomem *ioaddr, u32 chan); - void (*start_rx)(void __iomem *ioaddr, u32 chan); - void (*stop_rx)(void __iomem *ioaddr, u32 chan); - int (*dma_interrupt) (void __iomem *ioaddr, - struct stmmac_extra_stats *x, u32 chan); - /* If supported then get the optional core features */ - void (*get_hw_feature)(void __iomem *ioaddr, - struct dma_features *dma_cap); - /* Program the HW RX Watchdog */ - void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan); - void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); - void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); - void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); - void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); - void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); -}; - struct mac_device_info; -/* Helpers to program the MAC core */ -struct stmmac_ops { - /* MAC core initialization */ - void (*core_init)(struct mac_device_info *hw, struct net_device *dev); - /* Enable the MAC RX/TX */ - void (*set_mac)(void __iomem *ioaddr, bool enable); - /* Enable and verify that the IPC module is supported */ - int (*rx_ipc)(struct mac_device_info *hw); - /* Enable RX Queues */ - void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue); - /* RX Queues Priority */ - void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); - /* TX Queues Priority */ - void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); - /* RX Queues Routing */ - void (*rx_queue_routing)(struct mac_device_info *hw, u8 packet, - u32 queue); - /* Program RX Algorithms */ - void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); - /* Program TX Algorithms */ - void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg); - /* Set MTL TX queues weight */ - void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw, - u32 weight, u32 queue); - /* RX MTL queue to RX dma mapping */ - void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan); - /* Configure AV Algorithm */ - void (*config_cbs)(struct mac_device_info *hw, u32 send_slope, - u32 idle_slope, u32 high_credit, u32 low_credit, - u32 queue); - /* Dump MAC registers */ - void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space); - /* Handle extra events on specific interrupts hw dependent */ - int (*host_irq_status)(struct mac_device_info *hw, - struct stmmac_extra_stats *x); - /* Handle MTL interrupts */ - int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan); - /* Multicast filter setting */ - void (*set_filter)(struct mac_device_info *hw, struct net_device *dev); - /* Flow control setting */ - void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex, - unsigned int fc, unsigned int pause_time, u32 tx_cnt); - /* Set power management mode (e.g. magic frame) */ - void (*pmt)(struct mac_device_info *hw, unsigned long mode); - /* Set/Get Unicast MAC addresses */ - void (*set_umac_addr)(struct mac_device_info *hw, unsigned char *addr, - unsigned int reg_n); - void (*get_umac_addr)(struct mac_device_info *hw, unsigned char *addr, - unsigned int reg_n); - void (*set_eee_mode)(struct mac_device_info *hw, - bool en_tx_lpi_clockgating); - void (*reset_eee_mode)(struct mac_device_info *hw); - void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw); - void (*set_eee_pls)(struct mac_device_info *hw, int link); - void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x, - u32 rx_queues, u32 tx_queues); - /* PCS calls */ - void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral, - bool loopback); - void (*pcs_rane)(void __iomem *ioaddr, bool restart); - void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv); - /* Safety Features */ - int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp); - bool (*safety_feat_irq_status)(struct net_device *ndev, - void __iomem *ioaddr, unsigned int asp, - struct stmmac_safety_stats *stats); - const char *(*safety_feat_dump)(struct stmmac_safety_stats *stats, - int index, unsigned long *count); -}; - -/* PTP and HW Timer helpers */ -struct stmmac_hwtimestamp { - void (*config_hw_tstamping) (void __iomem *ioaddr, u32 data); - u32 (*config_sub_second_increment)(void __iomem *ioaddr, u32 ptp_clock, - int gmac4); - int (*init_systime) (void __iomem *ioaddr, u32 sec, u32 nsec); - int (*config_addend) (void __iomem *ioaddr, u32 addend); - int (*adjust_systime) (void __iomem *ioaddr, u32 sec, u32 nsec, - int add_sub, int gmac4); - u64(*get_systime) (void __iomem *ioaddr); -}; - extern const struct stmmac_hwtimestamp stmmac_ptp; extern const struct stmmac_mode_ops dwmac4_ring_mode_ops; @@ -590,24 +410,13 @@ struct mii_regs { unsigned int clk_csr_mask; }; -/* Helpers to manage the descriptors for chain and ring modes */ -struct stmmac_mode_ops { - void (*init) (void *des, dma_addr_t phy_addr, unsigned int size, - unsigned int extend_desc); - unsigned int (*is_jumbo_frm) (int len, int ehn_desc); - int (*jumbo_frm)(void *priv, struct sk_buff *skb, int csum); - int (*set_16kib_bfsize)(int mtu); - void (*init_desc3)(struct dma_desc *p); - void (*refill_desc3) (void *priv, struct dma_desc *p); - void (*clean_desc3) (void *priv, struct dma_desc *p); -}; - struct mac_device_info { const struct stmmac_ops *mac; const struct stmmac_desc_ops *desc; const struct stmmac_dma_ops *dma; const struct stmmac_mode_ops *mode; const struct stmmac_hwtimestamp *ptp; + const struct stmmac_tc_ops *tc; struct mii_regs mii; /* MII register Addresses */ struct mac_link link; void __iomem *pcsr; /* vpointer to device CSRs */ @@ -625,12 +434,9 @@ struct stmmac_rx_routing { u32 reg_shift; }; -struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins, - int perfect_uc_entries, - int *synopsys_id); -struct mac_device_info *dwmac100_setup(void __iomem *ioaddr, int *synopsys_id); -struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins, - int perfect_uc_entries, int *synopsys_id); +int dwmac100_setup(struct stmmac_priv *priv); +int dwmac1000_setup(struct stmmac_priv *priv); +int dwmac4_setup(struct stmmac_priv *priv); void stmmac_set_mac_addr(void __iomem *ioaddr, u8 addr[6], unsigned int high, unsigned int low); @@ -650,24 +456,4 @@ extern const struct stmmac_mode_ops ring_mode_ops; extern const struct stmmac_mode_ops chain_mode_ops; extern const struct stmmac_desc_ops dwmac4_desc_ops; -/** - * stmmac_get_synopsys_id - return the SYINID. - * @priv: driver private structure - * Description: this simple function is to decode and return the SYINID - * starting from the HW core register. - */ -static inline u32 stmmac_get_synopsys_id(u32 hwid) -{ - /* Check Synopsys Id (not available on old chips) */ - if (likely(hwid)) { - u32 uid = ((hwid & 0x0000ff00) >> 8); - u32 synid = (hwid & 0x000000ff); - - pr_info("stmmac - user ID: 0x%x, Synopsys ID: 0x%x\n", - uid, synid); - - return synid; - } - return 0; -} #endif /* __COMMON_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c index 7cb794094a70..4ff231df7322 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac-meson8b.c @@ -18,6 +18,7 @@ #include <linux/io.h> #include <linux/ioport.h> #include <linux/module.h> +#include <linux/of_device.h> #include <linux/of_net.h> #include <linux/mfd/syscon.h> #include <linux/platform_device.h> @@ -29,6 +30,10 @@ #define PRG_ETH0_RGMII_MODE BIT(0) +#define PRG_ETH0_EXT_PHY_MODE_MASK GENMASK(2, 0) +#define PRG_ETH0_EXT_RGMII_MODE 1 +#define PRG_ETH0_EXT_RMII_MODE 4 + /* mux to choose between fclk_div2 (bit unset) and mpll2 (bit set) */ #define PRG_ETH0_CLK_M250_SEL_SHIFT 4 #define PRG_ETH0_CLK_M250_SEL_MASK GENMASK(4, 4) @@ -47,12 +52,20 @@ #define MUX_CLK_NUM_PARENTS 2 +struct meson8b_dwmac; + +struct meson8b_dwmac_data { + int (*set_phy_mode)(struct meson8b_dwmac *dwmac); +}; + struct meson8b_dwmac { - struct device *dev; - void __iomem *regs; - phy_interface_t phy_mode; - struct clk *rgmii_tx_clk; - u32 tx_delay_ns; + struct device *dev; + void __iomem *regs; + + const struct meson8b_dwmac_data *data; + phy_interface_t phy_mode; + struct clk *rgmii_tx_clk; + u32 tx_delay_ns; }; struct meson8b_dwmac_clk_configs { @@ -171,6 +184,59 @@ static int meson8b_init_rgmii_tx_clk(struct meson8b_dwmac *dwmac) return 0; } +static int meson8b_set_phy_mode(struct meson8b_dwmac *dwmac) +{ + switch (dwmac->phy_mode) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + /* enable RGMII mode */ + meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, + PRG_ETH0_RGMII_MODE, + PRG_ETH0_RGMII_MODE); + break; + case PHY_INTERFACE_MODE_RMII: + /* disable RGMII mode -> enables RMII mode */ + meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, + PRG_ETH0_RGMII_MODE, 0); + break; + default: + dev_err(dwmac->dev, "fail to set phy-mode %s\n", + phy_modes(dwmac->phy_mode)); + return -EINVAL; + } + + return 0; +} + +static int meson_axg_set_phy_mode(struct meson8b_dwmac *dwmac) +{ + switch (dwmac->phy_mode) { + case PHY_INTERFACE_MODE_RGMII: + case PHY_INTERFACE_MODE_RGMII_RXID: + case PHY_INTERFACE_MODE_RGMII_ID: + case PHY_INTERFACE_MODE_RGMII_TXID: + /* enable RGMII mode */ + meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, + PRG_ETH0_EXT_PHY_MODE_MASK, + PRG_ETH0_EXT_RGMII_MODE); + break; + case PHY_INTERFACE_MODE_RMII: + /* disable RGMII mode -> enables RMII mode */ + meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, + PRG_ETH0_EXT_PHY_MODE_MASK, + PRG_ETH0_EXT_RMII_MODE); + break; + default: + dev_err(dwmac->dev, "fail to set phy-mode %s\n", + phy_modes(dwmac->phy_mode)); + return -EINVAL; + } + + return 0; +} + static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) { int ret; @@ -188,10 +254,6 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) case PHY_INTERFACE_MODE_RGMII_ID: case PHY_INTERFACE_MODE_RGMII_TXID: - /* enable RGMII mode */ - meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_RGMII_MODE, - PRG_ETH0_RGMII_MODE); - /* only relevant for RMII mode -> disable in RGMII mode */ meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_INVERTED_RMII_CLK, 0); @@ -224,10 +286,6 @@ static int meson8b_init_prg_eth(struct meson8b_dwmac *dwmac) break; case PHY_INTERFACE_MODE_RMII: - /* disable RGMII mode -> enables RMII mode */ - meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_RGMII_MODE, - 0); - /* invert internal clk_rmii_i to generate 25/2.5 tx_rx_clk */ meson8b_dwmac_mask_bits(dwmac, PRG_ETH0, PRG_ETH0_INVERTED_RMII_CLK, @@ -274,6 +332,11 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) goto err_remove_config_dt; } + dwmac->data = (const struct meson8b_dwmac_data *) + of_device_get_match_data(&pdev->dev); + if (!dwmac->data) + return -EINVAL; + res = platform_get_resource(pdev, IORESOURCE_MEM, 1); dwmac->regs = devm_ioremap_resource(&pdev->dev, res); if (IS_ERR(dwmac->regs)) { @@ -298,6 +361,10 @@ static int meson8b_dwmac_probe(struct platform_device *pdev) if (ret) goto err_remove_config_dt; + ret = dwmac->data->set_phy_mode(dwmac); + if (ret) + goto err_remove_config_dt; + ret = meson8b_init_prg_eth(dwmac); if (ret) goto err_remove_config_dt; @@ -316,10 +383,31 @@ err_remove_config_dt: return ret; } +static const struct meson8b_dwmac_data meson8b_dwmac_data = { + .set_phy_mode = meson8b_set_phy_mode, +}; + +static const struct meson8b_dwmac_data meson_axg_dwmac_data = { + .set_phy_mode = meson_axg_set_phy_mode, +}; + static const struct of_device_id meson8b_dwmac_match[] = { - { .compatible = "amlogic,meson8b-dwmac" }, - { .compatible = "amlogic,meson8m2-dwmac" }, - { .compatible = "amlogic,meson-gxbb-dwmac" }, + { + .compatible = "amlogic,meson8b-dwmac", + .data = &meson8b_dwmac_data, + }, + { + .compatible = "amlogic,meson8m2-dwmac", + .data = &meson8b_dwmac_data, + }, + { + .compatible = "amlogic,meson-gxbb-dwmac", + .data = &meson8b_dwmac_data, + }, + { + .compatible = "amlogic,meson-axg-dwmac", + .data = &meson_axg_dwmac_data, + }, { } }; MODULE_DEVICE_TABLE(of, meson8b_dwmac_match); diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h index c02d36629c52..184ca13c8f79 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000.h @@ -29,7 +29,6 @@ #define GMAC_MII_DATA 0x00000014 /* MII Data */ #define GMAC_FLOW_CTRL 0x00000018 /* Flow Control */ #define GMAC_VLAN_TAG 0x0000001c /* VLAN Tag */ -#define GMAC_VERSION 0x00000020 /* GMAC CORE Version */ #define GMAC_DEBUG 0x00000024 /* GMAC debug register */ #define GMAC_WAKEUP_FILTER 0x00000028 /* Wake-up Frame Filter */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c index ef10baf14186..0877bde6e860 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac1000_core.c @@ -27,6 +27,7 @@ #include <linux/ethtool.h> #include <net/dsa.h> #include <asm/io.h> +#include "stmmac.h" #include "stmmac_pcs.h" #include "dwmac1000.h" @@ -498,7 +499,7 @@ static void dwmac1000_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x, x->mac_gmii_rx_proto_engine++; } -static const struct stmmac_ops dwmac1000_ops = { +const struct stmmac_ops dwmac1000_ops = { .core_init = dwmac1000_core_init, .set_mac = stmmac_set_mac, .rx_ipc = dwmac1000_rx_ipc_enable, @@ -519,28 +520,21 @@ static const struct stmmac_ops dwmac1000_ops = { .pcs_get_adv_lp = dwmac1000_get_adv_lp, }; -struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins, - int perfect_uc_entries, - int *synopsys_id) +int dwmac1000_setup(struct stmmac_priv *priv) { - struct mac_device_info *mac; - u32 hwid = readl(ioaddr + GMAC_VERSION); + struct mac_device_info *mac = priv->hw; - mac = kzalloc(sizeof(const struct mac_device_info), GFP_KERNEL); - if (!mac) - return NULL; + dev_info(priv->device, "\tDWMAC1000\n"); - mac->pcsr = ioaddr; - mac->multicast_filter_bins = mcbins; - mac->unicast_filter_entries = perfect_uc_entries; + priv->dev->priv_flags |= IFF_UNICAST_FLT; + mac->pcsr = priv->ioaddr; + mac->multicast_filter_bins = priv->plat->multicast_filter_bins; + mac->unicast_filter_entries = priv->plat->unicast_filter_entries; mac->mcast_bits_log2 = 0; if (mac->multicast_filter_bins) mac->mcast_bits_log2 = ilog2(mac->multicast_filter_bins); - mac->mac = &dwmac1000_ops; - mac->dma = &dwmac1000_dma_ops; - mac->link.duplex = GMAC_CONTROL_DM; mac->link.speed10 = GMAC_CONTROL_PS; mac->link.speed100 = GMAC_CONTROL_PS | GMAC_CONTROL_FES; @@ -555,8 +549,5 @@ struct mac_device_info *dwmac1000_setup(void __iomem *ioaddr, int mcbins, mac->mii.clk_csr_shift = 2; mac->mii.clk_csr_mask = GENMASK(5, 2); - /* Get and dump the chip ID */ - *synopsys_id = stmmac_get_synopsys_id(hwid); - - return mac; + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c index 91b23f9db31a..b735143987e1 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac100_core.c @@ -27,6 +27,7 @@ #include <linux/crc32.h> #include <net/dsa.h> #include <asm/io.h> +#include "stmmac.h" #include "dwmac100.h" static void dwmac100_core_init(struct mac_device_info *hw, @@ -159,7 +160,7 @@ static void dwmac100_pmt(struct mac_device_info *hw, unsigned long mode) return; } -static const struct stmmac_ops dwmac100_ops = { +const struct stmmac_ops dwmac100_ops = { .core_init = dwmac100_core_init, .set_mac = stmmac_set_mac, .rx_ipc = dwmac100_rx_ipc_enable, @@ -172,20 +173,13 @@ static const struct stmmac_ops dwmac100_ops = { .get_umac_addr = dwmac100_get_umac_addr, }; -struct mac_device_info *dwmac100_setup(void __iomem *ioaddr, int *synopsys_id) +int dwmac100_setup(struct stmmac_priv *priv) { - struct mac_device_info *mac; + struct mac_device_info *mac = priv->hw; - mac = kzalloc(sizeof(const struct mac_device_info), GFP_KERNEL); - if (!mac) - return NULL; - - pr_info("\tDWMAC100\n"); - - mac->pcsr = ioaddr; - mac->mac = &dwmac100_ops; - mac->dma = &dwmac100_dma_ops; + dev_info(priv->device, "\tDWMAC100\n"); + mac->pcsr = priv->ioaddr; mac->link.duplex = MAC_CONTROL_F; mac->link.speed10 = 0; mac->link.speed100 = 0; @@ -200,8 +194,5 @@ struct mac_device_info *dwmac100_setup(void __iomem *ioaddr, int *synopsys_id) mac->mii.clk_csr_shift = 2; mac->mii.clk_csr_mask = GENMASK(5, 2); - /* Synopsys Id is not available on old chips */ - *synopsys_id = 0; - - return mac; + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h index dedd40613090..6330a55953df 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4.h @@ -34,7 +34,6 @@ #define GMAC_PCS_BASE 0x000000e0 #define GMAC_PHYIF_CONTROL_STATUS 0x000000f8 #define GMAC_PMT 0x000000c0 -#define GMAC_VERSION 0x00000110 #define GMAC_DEBUG 0x00000114 #define GMAC_HW_FEATURE0 0x0000011c #define GMAC_HW_FEATURE1 0x00000120 @@ -195,6 +194,9 @@ enum power_event { /* MAC HW features3 bitmap */ #define GMAC_HW_FEAT_ASP GENMASK(29, 28) +#define GMAC_HW_FEAT_FRPES GENMASK(14, 13) +#define GMAC_HW_FEAT_FRPBS GENMASK(12, 11) +#define GMAC_HW_FEAT_FRPSEL BIT(10) /* MAC HW ADDR regs */ #define GMAC_HI_DCS GENMASK(18, 16) @@ -203,6 +205,7 @@ enum power_event { /* MTL registers */ #define MTL_OPERATION_MODE 0x00000c00 +#define MTL_FRPE BIT(15) #define MTL_OPERATION_SCHALG_MASK GENMASK(6, 5) #define MTL_OPERATION_SCHALG_WRR (0x0 << 5) #define MTL_OPERATION_SCHALG_WFQ (0x1 << 5) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c index 517b1f6736a8..a7121a7d9391 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_core.c @@ -18,6 +18,7 @@ #include <linux/ethtool.h> #include <linux/io.h> #include <net/dsa.h> +#include "stmmac.h" #include "stmmac_pcs.h" #include "dwmac4.h" #include "dwmac5.h" @@ -700,7 +701,7 @@ static void dwmac4_debug(void __iomem *ioaddr, struct stmmac_extra_stats *x, x->mac_gmii_rx_proto_engine++; } -static const struct stmmac_ops dwmac4_ops = { +const struct stmmac_ops dwmac4_ops = { .core_init = dwmac4_core_init, .set_mac = stmmac_set_mac, .rx_ipc = dwmac4_rx_ipc_enable, @@ -731,7 +732,7 @@ static const struct stmmac_ops dwmac4_ops = { .set_filter = dwmac4_set_filter, }; -static const struct stmmac_ops dwmac410_ops = { +const struct stmmac_ops dwmac410_ops = { .core_init = dwmac4_core_init, .set_mac = stmmac_dwmac4_set_mac, .rx_ipc = dwmac4_rx_ipc_enable, @@ -762,7 +763,7 @@ static const struct stmmac_ops dwmac410_ops = { .set_filter = dwmac4_set_filter, }; -static const struct stmmac_ops dwmac510_ops = { +const struct stmmac_ops dwmac510_ops = { .core_init = dwmac4_core_init, .set_mac = stmmac_dwmac4_set_mac, .rx_ipc = dwmac4_rx_ipc_enable, @@ -794,21 +795,19 @@ static const struct stmmac_ops dwmac510_ops = { .safety_feat_config = dwmac5_safety_feat_config, .safety_feat_irq_status = dwmac5_safety_feat_irq_status, .safety_feat_dump = dwmac5_safety_feat_dump, + .rxp_config = dwmac5_rxp_config, }; -struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins, - int perfect_uc_entries, int *synopsys_id) +int dwmac4_setup(struct stmmac_priv *priv) { - struct mac_device_info *mac; - u32 hwid = readl(ioaddr + GMAC_VERSION); + struct mac_device_info *mac = priv->hw; - mac = kzalloc(sizeof(const struct mac_device_info), GFP_KERNEL); - if (!mac) - return NULL; + dev_info(priv->device, "\tDWMAC4/5\n"); - mac->pcsr = ioaddr; - mac->multicast_filter_bins = mcbins; - mac->unicast_filter_entries = perfect_uc_entries; + priv->dev->priv_flags |= IFF_UNICAST_FLT; + mac->pcsr = priv->ioaddr; + mac->multicast_filter_bins = priv->plat->multicast_filter_bins; + mac->unicast_filter_entries = priv->plat->unicast_filter_entries; mac->mcast_bits_log2 = 0; if (mac->multicast_filter_bins) @@ -828,20 +827,5 @@ struct mac_device_info *dwmac4_setup(void __iomem *ioaddr, int mcbins, mac->mii.clk_csr_shift = 8; mac->mii.clk_csr_mask = GENMASK(11, 8); - /* Get and dump the chip ID */ - *synopsys_id = stmmac_get_synopsys_id(hwid); - - if (*synopsys_id > DWMAC_CORE_4_00) - mac->dma = &dwmac410_dma_ops; - else - mac->dma = &dwmac4_dma_ops; - - if (*synopsys_id >= DWMAC_CORE_5_10) - mac->mac = &dwmac510_ops; - else if (*synopsys_id >= DWMAC_CORE_4_00) - mac->mac = &dwmac410_ops; - else - mac->mac = &dwmac4_ops; - - return mac; + return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c index 2a6521d33e43..65ed896c13cb 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_descs.c @@ -223,7 +223,7 @@ static int dwmac4_wrback_get_tx_timestamp_status(struct dma_desc *p) return 0; } -static inline u64 dwmac4_get_timestamp(void *desc, u32 ats) +static inline void dwmac4_get_timestamp(void *desc, u32 ats, u64 *ts) { struct dma_desc *p = (struct dma_desc *)desc; u64 ns; @@ -232,7 +232,7 @@ static inline u64 dwmac4_get_timestamp(void *desc, u32 ats) /* convert high/sec time stamp value to nanosecond */ ns += le32_to_cpu(p->des1) * 1000000000ULL; - return ns; + *ts = ns; } static int dwmac4_rx_check_timestamp(void *desc) diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c index d37d457306d1..117c3a5288f0 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac4_dma.c @@ -379,6 +379,9 @@ static void dwmac4_get_hw_feature(void __iomem *ioaddr, /* 5.10 Features */ dma_cap->asp = (hw_cap & GMAC_HW_FEAT_ASP) >> 28; + dma_cap->frpes = (hw_cap & GMAC_HW_FEAT_FRPES) >> 13; + dma_cap->frpbs = (hw_cap & GMAC_HW_FEAT_FRPBS) >> 11; + dma_cap->frpsel = (hw_cap & GMAC_HW_FEAT_FRPSEL) >> 10; } /* Enable/disable TSO feature and set MSS */ diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c index 860de39999c7..b2becb80a697 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.c +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.c @@ -7,6 +7,7 @@ #include "common.h" #include "dwmac4.h" #include "dwmac5.h" +#include "stmmac.h" struct dwmac5_error_desc { bool valid; @@ -237,15 +238,16 @@ int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp) return 0; } -bool dwmac5_safety_feat_irq_status(struct net_device *ndev, +int dwmac5_safety_feat_irq_status(struct net_device *ndev, void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_stats *stats) { - bool ret = false, err, corr; + bool err, corr; u32 mtl, dma; + int ret = 0; if (!asp) - return false; + return -EINVAL; mtl = readl(ioaddr + MTL_SAFETY_INT_STATUS); dma = readl(ioaddr + DMA_SAFETY_INT_STATUS); @@ -282,17 +284,213 @@ static const struct dwmac5_error { { dwmac5_dma_errors }, }; -const char *dwmac5_safety_feat_dump(struct stmmac_safety_stats *stats, - int index, unsigned long *count) +int dwmac5_safety_feat_dump(struct stmmac_safety_stats *stats, + int index, unsigned long *count, const char **desc) { int module = index / 32, offset = index % 32; unsigned long *ptr = (unsigned long *)stats; if (module >= ARRAY_SIZE(dwmac5_all_errors)) - return NULL; + return -EINVAL; if (!dwmac5_all_errors[module].desc[offset].valid) - return NULL; + return -EINVAL; if (count) *count = *(ptr + index); - return dwmac5_all_errors[module].desc[offset].desc; + if (desc) + *desc = dwmac5_all_errors[module].desc[offset].desc; + return 0; +} + +static int dwmac5_rxp_disable(void __iomem *ioaddr) +{ + u32 val; + int ret; + + val = readl(ioaddr + MTL_OPERATION_MODE); + val &= ~MTL_FRPE; + writel(val, ioaddr + MTL_OPERATION_MODE); + + ret = readl_poll_timeout(ioaddr + MTL_RXP_CONTROL_STATUS, val, + val & RXPI, 1, 10000); + if (ret) + return ret; + return 0; +} + +static void dwmac5_rxp_enable(void __iomem *ioaddr) +{ + u32 val; + + val = readl(ioaddr + MTL_OPERATION_MODE); + val |= MTL_FRPE; + writel(val, ioaddr + MTL_OPERATION_MODE); +} + +static int dwmac5_rxp_update_single_entry(void __iomem *ioaddr, + struct stmmac_tc_entry *entry, + int pos) +{ + int ret, i; + + for (i = 0; i < (sizeof(entry->val) / sizeof(u32)); i++) { + int real_pos = pos * (sizeof(entry->val) / sizeof(u32)) + i; + u32 val; + + /* Wait for ready */ + ret = readl_poll_timeout(ioaddr + MTL_RXP_IACC_CTRL_STATUS, + val, !(val & STARTBUSY), 1, 10000); + if (ret) + return ret; + + /* Write data */ + val = *((u32 *)&entry->val + i); + writel(val, ioaddr + MTL_RXP_IACC_DATA); + + /* Write pos */ + val = real_pos & ADDR; + writel(val, ioaddr + MTL_RXP_IACC_CTRL_STATUS); + + /* Write OP */ + val |= WRRDN; + writel(val, ioaddr + MTL_RXP_IACC_CTRL_STATUS); + + /* Start Write */ + val |= STARTBUSY; + writel(val, ioaddr + MTL_RXP_IACC_CTRL_STATUS); + + /* Wait for done */ + ret = readl_poll_timeout(ioaddr + MTL_RXP_IACC_CTRL_STATUS, + val, !(val & STARTBUSY), 1, 10000); + if (ret) + return ret; + } + + return 0; +} + +static struct stmmac_tc_entry * +dwmac5_rxp_get_next_entry(struct stmmac_tc_entry *entries, unsigned int count, + u32 curr_prio) +{ + struct stmmac_tc_entry *entry; + u32 min_prio = ~0x0; + int i, min_prio_idx; + bool found = false; + + for (i = count - 1; i >= 0; i--) { + entry = &entries[i]; + + /* Do not update unused entries */ + if (!entry->in_use) + continue; + /* Do not update already updated entries (i.e. fragments) */ + if (entry->in_hw) + continue; + /* Let last entry be updated last */ + if (entry->is_last) + continue; + /* Do not return fragments */ + if (entry->is_frag) + continue; + /* Check if we already checked this prio */ + if (entry->prio < curr_prio) + continue; + /* Check if this is the minimum prio */ + if (entry->prio < min_prio) { + min_prio = entry->prio; + min_prio_idx = i; + found = true; + } + } + + if (found) + return &entries[min_prio_idx]; + return NULL; +} + +int dwmac5_rxp_config(void __iomem *ioaddr, struct stmmac_tc_entry *entries, + unsigned int count) +{ + struct stmmac_tc_entry *entry, *frag; + int i, ret, nve = 0; + u32 curr_prio = 0; + u32 old_val, val; + + /* Force disable RX */ + old_val = readl(ioaddr + GMAC_CONFIG); + val = old_val & ~GMAC_CONFIG_RE; + writel(val, ioaddr + GMAC_CONFIG); + + /* Disable RX Parser */ + ret = dwmac5_rxp_disable(ioaddr); + if (ret) + goto re_enable; + + /* Set all entries as NOT in HW */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + entry->in_hw = false; + } + + /* Update entries by reverse order */ + while (1) { + entry = dwmac5_rxp_get_next_entry(entries, count, curr_prio); + if (!entry) + break; + + curr_prio = entry->prio; + frag = entry->frag_ptr; + + /* Set special fragment requirements */ + if (frag) { + entry->val.af = 0; + entry->val.rf = 0; + entry->val.nc = 1; + entry->val.ok_index = nve + 2; + } + + ret = dwmac5_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + entry->in_hw = true; + + if (frag && !frag->in_hw) { + ret = dwmac5_rxp_update_single_entry(ioaddr, frag, nve); + if (ret) + goto re_enable; + frag->table_pos = nve++; + frag->in_hw = true; + } + } + + if (!nve) + goto re_enable; + + /* Update all pass entry */ + for (i = 0; i < count; i++) { + entry = &entries[i]; + if (!entry->is_last) + continue; + + ret = dwmac5_rxp_update_single_entry(ioaddr, entry, nve); + if (ret) + goto re_enable; + + entry->table_pos = nve++; + } + + /* Assume n. of parsable entries == n. of valid entries */ + val = (nve << 16) & NPE; + val |= nve & NVE; + writel(val, ioaddr + MTL_RXP_CONTROL_STATUS); + + /* Enable RX Parser */ + dwmac5_rxp_enable(ioaddr); + +re_enable: + /* Re-enable RX */ + writel(old_val, ioaddr + GMAC_CONFIG); + return ret; } diff --git a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h index a0d2c44711b9..cc810aff7100 100644 --- a/drivers/net/ethernet/stmicro/stmmac/dwmac5.h +++ b/drivers/net/ethernet/stmicro/stmmac/dwmac5.h @@ -11,6 +11,17 @@ #define PRTYEN BIT(1) #define TMOUTEN BIT(0) +#define MTL_RXP_CONTROL_STATUS 0x00000ca0 +#define RXPI BIT(31) +#define NPE GENMASK(23, 16) +#define NVE GENMASK(7, 0) +#define MTL_RXP_IACC_CTRL_STATUS 0x00000cb0 +#define STARTBUSY BIT(31) +#define RXPEIEC GENMASK(22, 21) +#define RXPEIEE BIT(20) +#define WRRDN BIT(16) +#define ADDR GENMASK(15, 0) +#define MTL_RXP_IACC_DATA 0x00000cb4 #define MTL_ECC_CONTROL 0x00000cc0 #define TSOEE BIT(4) #define MRXPEE BIT(3) @@ -43,10 +54,12 @@ #define DMA_ECC_INT_STATUS 0x00001088 int dwmac5_safety_feat_config(void __iomem *ioaddr, unsigned int asp); -bool dwmac5_safety_feat_irq_status(struct net_device *ndev, +int dwmac5_safety_feat_irq_status(struct net_device *ndev, void __iomem *ioaddr, unsigned int asp, struct stmmac_safety_stats *stats); -const char *dwmac5_safety_feat_dump(struct stmmac_safety_stats *stats, - int index, unsigned long *count); +int dwmac5_safety_feat_dump(struct stmmac_safety_stats *stats, + int index, unsigned long *count, const char **desc); +int dwmac5_rxp_config(void __iomem *ioaddr, struct stmmac_tc_entry *entries, + unsigned int count); #endif /* __DWMAC5_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c index 6768a25b6aa0..3bfb3f584be2 100644 --- a/drivers/net/ethernet/stmicro/stmmac/enh_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/enh_desc.c @@ -382,7 +382,7 @@ static int enh_desc_get_tx_timestamp_status(struct dma_desc *p) return (le32_to_cpu(p->des0) & ETDES0_TIME_STAMP_STATUS) >> 17; } -static u64 enh_desc_get_timestamp(void *desc, u32 ats) +static void enh_desc_get_timestamp(void *desc, u32 ats, u64 *ts) { u64 ns; @@ -397,7 +397,7 @@ static u64 enh_desc_get_timestamp(void *desc, u32 ats) ns += le32_to_cpu(p->des3) * 1000000000ULL; } - return ns; + *ts = ns; } static int enh_desc_get_rx_timestamp_status(void *desc, void *next_desc, diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.c b/drivers/net/ethernet/stmicro/stmmac/hwif.c new file mode 100644 index 000000000000..9acc8d2f1039 --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.c @@ -0,0 +1,228 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates. + * stmmac HW Interface Handling + */ + +#include "common.h" +#include "stmmac.h" + +static u32 stmmac_get_id(struct stmmac_priv *priv, u32 id_reg) +{ + u32 reg = readl(priv->ioaddr + id_reg); + + if (!reg) { + dev_info(priv->device, "Version ID not available\n"); + return 0x0; + } + + dev_info(priv->device, "User ID: 0x%x, Synopsys ID: 0x%x\n", + (unsigned int)(reg & GENMASK(15, 8)) >> 8, + (unsigned int)(reg & GENMASK(7, 0))); + return reg & GENMASK(7, 0); +} + +static void stmmac_dwmac_mode_quirk(struct stmmac_priv *priv) +{ + struct mac_device_info *mac = priv->hw; + + if (priv->chain_mode) { + dev_info(priv->device, "Chain mode enabled\n"); + priv->mode = STMMAC_CHAIN_MODE; + mac->mode = &chain_mode_ops; + } else { + dev_info(priv->device, "Ring mode enabled\n"); + priv->mode = STMMAC_RING_MODE; + mac->mode = &ring_mode_ops; + } +} + +static int stmmac_dwmac1_quirks(struct stmmac_priv *priv) +{ + struct mac_device_info *mac = priv->hw; + + if (priv->plat->enh_desc) { + dev_info(priv->device, "Enhanced/Alternate descriptors\n"); + + /* GMAC older than 3.50 has no extended descriptors */ + if (priv->synopsys_id >= DWMAC_CORE_3_50) { + dev_info(priv->device, "Enabled extended descriptors\n"); + priv->extend_desc = 1; + } else { + dev_warn(priv->device, "Extended descriptors not supported\n"); + } + + mac->desc = &enh_desc_ops; + } else { + dev_info(priv->device, "Normal descriptors\n"); + mac->desc = &ndesc_ops; + } + + stmmac_dwmac_mode_quirk(priv); + return 0; +} + +static int stmmac_dwmac4_quirks(struct stmmac_priv *priv) +{ + stmmac_dwmac_mode_quirk(priv); + return 0; +} + +static const struct stmmac_hwif_entry { + bool gmac; + bool gmac4; + u32 min_id; + const void *desc; + const void *dma; + const void *mac; + const void *hwtimestamp; + const void *mode; + const void *tc; + int (*setup)(struct stmmac_priv *priv); + int (*quirks)(struct stmmac_priv *priv); +} stmmac_hw[] = { + /* NOTE: New HW versions shall go to the end of this table */ + { + .gmac = false, + .gmac4 = false, + .min_id = 0, + .desc = NULL, + .dma = &dwmac100_dma_ops, + .mac = &dwmac100_ops, + .hwtimestamp = &stmmac_ptp, + .mode = NULL, + .tc = NULL, + .setup = dwmac100_setup, + .quirks = stmmac_dwmac1_quirks, + }, { + .gmac = true, + .gmac4 = false, + .min_id = 0, + .desc = NULL, + .dma = &dwmac1000_dma_ops, + .mac = &dwmac1000_ops, + .hwtimestamp = &stmmac_ptp, + .mode = NULL, + .tc = NULL, + .setup = dwmac1000_setup, + .quirks = stmmac_dwmac1_quirks, + }, { + .gmac = false, + .gmac4 = true, + .min_id = 0, + .desc = &dwmac4_desc_ops, + .dma = &dwmac4_dma_ops, + .mac = &dwmac4_ops, + .hwtimestamp = &stmmac_ptp, + .mode = NULL, + .tc = NULL, + .setup = dwmac4_setup, + .quirks = stmmac_dwmac4_quirks, + }, { + .gmac = false, + .gmac4 = true, + .min_id = DWMAC_CORE_4_00, + .desc = &dwmac4_desc_ops, + .dma = &dwmac4_dma_ops, + .mac = &dwmac410_ops, + .hwtimestamp = &stmmac_ptp, + .mode = &dwmac4_ring_mode_ops, + .tc = NULL, + .setup = dwmac4_setup, + .quirks = NULL, + }, { + .gmac = false, + .gmac4 = true, + .min_id = DWMAC_CORE_4_10, + .desc = &dwmac4_desc_ops, + .dma = &dwmac410_dma_ops, + .mac = &dwmac410_ops, + .hwtimestamp = &stmmac_ptp, + .mode = &dwmac4_ring_mode_ops, + .tc = NULL, + .setup = dwmac4_setup, + .quirks = NULL, + }, { + .gmac = false, + .gmac4 = true, + .min_id = DWMAC_CORE_5_10, + .desc = &dwmac4_desc_ops, + .dma = &dwmac410_dma_ops, + .mac = &dwmac510_ops, + .hwtimestamp = &stmmac_ptp, + .mode = &dwmac4_ring_mode_ops, + .tc = &dwmac510_tc_ops, + .setup = dwmac4_setup, + .quirks = NULL, + } +}; + +int stmmac_hwif_init(struct stmmac_priv *priv) +{ + bool needs_gmac4 = priv->plat->has_gmac4; + bool needs_gmac = priv->plat->has_gmac; + const struct stmmac_hwif_entry *entry; + struct mac_device_info *mac; + int i, ret; + u32 id; + + if (needs_gmac) { + id = stmmac_get_id(priv, GMAC_VERSION); + } else { + id = stmmac_get_id(priv, GMAC4_VERSION); + } + + /* Save ID for later use */ + priv->synopsys_id = id; + + /* Check for HW specific setup first */ + if (priv->plat->setup) { + priv->hw = priv->plat->setup(priv); + if (!priv->hw) + return -ENOMEM; + return 0; + } + + mac = devm_kzalloc(priv->device, sizeof(*mac), GFP_KERNEL); + if (!mac) + return -ENOMEM; + + /* Fallback to generic HW */ + for (i = ARRAY_SIZE(stmmac_hw) - 1; i >= 0; i--) { + entry = &stmmac_hw[i]; + + if (needs_gmac ^ entry->gmac) + continue; + if (needs_gmac4 ^ entry->gmac4) + continue; + if (id < entry->min_id) + continue; + + mac->desc = entry->desc; + mac->dma = entry->dma; + mac->mac = entry->mac; + mac->ptp = entry->hwtimestamp; + mac->mode = entry->mode; + mac->tc = entry->tc; + + priv->hw = mac; + + /* Entry found */ + ret = entry->setup(priv); + if (ret) + return ret; + + /* Run quirks, if needed */ + if (entry->quirks) { + ret = entry->quirks(priv); + if (ret) + return ret; + } + + return 0; + } + + dev_err(priv->device, "Failed to find HW IF (id=0x%x, gmac=%d/%d)\n", + id, needs_gmac, needs_gmac4); + return -EINVAL; +} diff --git a/drivers/net/ethernet/stmicro/stmmac/hwif.h b/drivers/net/ethernet/stmicro/stmmac/hwif.h new file mode 100644 index 000000000000..b7539a14e6ad --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/hwif.h @@ -0,0 +1,459 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +// Copyright (c) 2018 Synopsys, Inc. and/or its affiliates. +// stmmac HW Interface Callbacks + +#ifndef __STMMAC_HWIF_H__ +#define __STMMAC_HWIF_H__ + +#include <linux/netdevice.h> + +#define stmmac_do_void_callback(__priv, __module, __cname, __arg0, __args...) \ +({ \ + int __result = -EINVAL; \ + if ((__priv)->hw->__module && (__priv)->hw->__module->__cname) { \ + (__priv)->hw->__module->__cname((__arg0), ##__args); \ + __result = 0; \ + } \ + __result; \ +}) +#define stmmac_do_callback(__priv, __module, __cname, __arg0, __args...) \ +({ \ + int __result = -EINVAL; \ + if ((__priv)->hw->__module && (__priv)->hw->__module->__cname) \ + __result = (__priv)->hw->__module->__cname((__arg0), ##__args); \ + __result; \ +}) + +struct stmmac_extra_stats; +struct stmmac_safety_stats; +struct dma_desc; +struct dma_extended_desc; + +/* Descriptors helpers */ +struct stmmac_desc_ops { + /* DMA RX descriptor ring initialization */ + void (*init_rx_desc)(struct dma_desc *p, int disable_rx_ic, int mode, + int end); + /* DMA TX descriptor ring initialization */ + void (*init_tx_desc)(struct dma_desc *p, int mode, int end); + /* Invoked by the xmit function to prepare the tx descriptor */ + void (*prepare_tx_desc)(struct dma_desc *p, int is_fs, int len, + bool csum_flag, int mode, bool tx_own, bool ls, + unsigned int tot_pkt_len); + void (*prepare_tso_tx_desc)(struct dma_desc *p, int is_fs, int len1, + int len2, bool tx_own, bool ls, unsigned int tcphdrlen, + unsigned int tcppayloadlen); + /* Set/get the owner of the descriptor */ + void (*set_tx_owner)(struct dma_desc *p); + int (*get_tx_owner)(struct dma_desc *p); + /* Clean the tx descriptor as soon as the tx irq is received */ + void (*release_tx_desc)(struct dma_desc *p, int mode); + /* Clear interrupt on tx frame completion. When this bit is + * set an interrupt happens as soon as the frame is transmitted */ + void (*set_tx_ic)(struct dma_desc *p); + /* Last tx segment reports the transmit status */ + int (*get_tx_ls)(struct dma_desc *p); + /* Return the transmit status looking at the TDES1 */ + int (*tx_status)(void *data, struct stmmac_extra_stats *x, + struct dma_desc *p, void __iomem *ioaddr); + /* Get the buffer size from the descriptor */ + int (*get_tx_len)(struct dma_desc *p); + /* Handle extra events on specific interrupts hw dependent */ + void (*set_rx_owner)(struct dma_desc *p); + /* Get the receive frame size */ + int (*get_rx_frame_len)(struct dma_desc *p, int rx_coe_type); + /* Return the reception status looking at the RDES1 */ + int (*rx_status)(void *data, struct stmmac_extra_stats *x, + struct dma_desc *p); + void (*rx_extended_status)(void *data, struct stmmac_extra_stats *x, + struct dma_extended_desc *p); + /* Set tx timestamp enable bit */ + void (*enable_tx_timestamp) (struct dma_desc *p); + /* get tx timestamp status */ + int (*get_tx_timestamp_status) (struct dma_desc *p); + /* get timestamp value */ + void (*get_timestamp)(void *desc, u32 ats, u64 *ts); + /* get rx timestamp status */ + int (*get_rx_timestamp_status)(void *desc, void *next_desc, u32 ats); + /* Display ring */ + void (*display_ring)(void *head, unsigned int size, bool rx); + /* set MSS via context descriptor */ + void (*set_mss)(struct dma_desc *p, unsigned int mss); +}; + +#define stmmac_init_rx_desc(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, init_rx_desc, __args) +#define stmmac_init_tx_desc(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, init_tx_desc, __args) +#define stmmac_prepare_tx_desc(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, prepare_tx_desc, __args) +#define stmmac_prepare_tso_tx_desc(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, prepare_tso_tx_desc, __args) +#define stmmac_set_tx_owner(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_tx_owner, __args) +#define stmmac_get_tx_owner(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_tx_owner, __args) +#define stmmac_release_tx_desc(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, release_tx_desc, __args) +#define stmmac_set_tx_ic(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_tx_ic, __args) +#define stmmac_get_tx_ls(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_tx_ls, __args) +#define stmmac_tx_status(__priv, __args...) \ + stmmac_do_callback(__priv, desc, tx_status, __args) +#define stmmac_get_tx_len(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_tx_len, __args) +#define stmmac_set_rx_owner(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_rx_owner, __args) +#define stmmac_get_rx_frame_len(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_frame_len, __args) +#define stmmac_rx_status(__priv, __args...) \ + stmmac_do_callback(__priv, desc, rx_status, __args) +#define stmmac_rx_extended_status(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, rx_extended_status, __args) +#define stmmac_enable_tx_timestamp(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, enable_tx_timestamp, __args) +#define stmmac_get_tx_timestamp_status(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_tx_timestamp_status, __args) +#define stmmac_get_timestamp(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, get_timestamp, __args) +#define stmmac_get_rx_timestamp_status(__priv, __args...) \ + stmmac_do_callback(__priv, desc, get_rx_timestamp_status, __args) +#define stmmac_display_ring(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, display_ring, __args) +#define stmmac_set_mss(__priv, __args...) \ + stmmac_do_void_callback(__priv, desc, set_mss, __args) + +struct stmmac_dma_cfg; +struct dma_features; + +/* Specific DMA helpers */ +struct stmmac_dma_ops { + /* DMA core initialization */ + int (*reset)(void __iomem *ioaddr); + void (*init)(void __iomem *ioaddr, struct stmmac_dma_cfg *dma_cfg, + u32 dma_tx, u32 dma_rx, int atds); + void (*init_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, u32 chan); + void (*init_rx_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_rx_phy, u32 chan); + void (*init_tx_chan)(void __iomem *ioaddr, + struct stmmac_dma_cfg *dma_cfg, + u32 dma_tx_phy, u32 chan); + /* Configure the AXI Bus Mode Register */ + void (*axi)(void __iomem *ioaddr, struct stmmac_axi *axi); + /* Dump DMA registers */ + void (*dump_regs)(void __iomem *ioaddr, u32 *reg_space); + /* Set tx/rx threshold in the csr6 register + * An invalid value enables the store-and-forward mode */ + void (*dma_mode)(void __iomem *ioaddr, int txmode, int rxmode, + int rxfifosz); + void (*dma_rx_mode)(void __iomem *ioaddr, int mode, u32 channel, + int fifosz, u8 qmode); + void (*dma_tx_mode)(void __iomem *ioaddr, int mode, u32 channel, + int fifosz, u8 qmode); + /* To track extra statistic (if supported) */ + void (*dma_diagnostic_fr) (void *data, struct stmmac_extra_stats *x, + void __iomem *ioaddr); + void (*enable_dma_transmission) (void __iomem *ioaddr); + void (*enable_dma_irq)(void __iomem *ioaddr, u32 chan); + void (*disable_dma_irq)(void __iomem *ioaddr, u32 chan); + void (*start_tx)(void __iomem *ioaddr, u32 chan); + void (*stop_tx)(void __iomem *ioaddr, u32 chan); + void (*start_rx)(void __iomem *ioaddr, u32 chan); + void (*stop_rx)(void __iomem *ioaddr, u32 chan); + int (*dma_interrupt) (void __iomem *ioaddr, + struct stmmac_extra_stats *x, u32 chan); + /* If supported then get the optional core features */ + void (*get_hw_feature)(void __iomem *ioaddr, + struct dma_features *dma_cap); + /* Program the HW RX Watchdog */ + void (*rx_watchdog)(void __iomem *ioaddr, u32 riwt, u32 number_chan); + void (*set_tx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); + void (*set_rx_ring_len)(void __iomem *ioaddr, u32 len, u32 chan); + void (*set_rx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); + void (*set_tx_tail_ptr)(void __iomem *ioaddr, u32 tail_ptr, u32 chan); + void (*enable_tso)(void __iomem *ioaddr, bool en, u32 chan); +}; + +#define stmmac_reset(__priv, __args...) \ + stmmac_do_callback(__priv, dma, reset, __args) +#define stmmac_dma_init(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, init, __args) +#define stmmac_init_chan(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, init_chan, __args) +#define stmmac_init_rx_chan(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, init_rx_chan, __args) +#define stmmac_init_tx_chan(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, init_tx_chan, __args) +#define stmmac_axi(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, axi, __args) +#define stmmac_dump_dma_regs(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, dump_regs, __args) +#define stmmac_dma_mode(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, dma_mode, __args) +#define stmmac_dma_rx_mode(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, dma_rx_mode, __args) +#define stmmac_dma_tx_mode(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, dma_tx_mode, __args) +#define stmmac_dma_diagnostic_fr(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, dma_diagnostic_fr, __args) +#define stmmac_enable_dma_transmission(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, enable_dma_transmission, __args) +#define stmmac_enable_dma_irq(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, enable_dma_irq, __args) +#define stmmac_disable_dma_irq(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, disable_dma_irq, __args) +#define stmmac_start_tx(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, start_tx, __args) +#define stmmac_stop_tx(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, stop_tx, __args) +#define stmmac_start_rx(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, start_rx, __args) +#define stmmac_stop_rx(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, stop_rx, __args) +#define stmmac_dma_interrupt_status(__priv, __args...) \ + stmmac_do_callback(__priv, dma, dma_interrupt, __args) +#define stmmac_get_hw_feature(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, get_hw_feature, __args) +#define stmmac_rx_watchdog(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, rx_watchdog, __args) +#define stmmac_set_tx_ring_len(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, set_tx_ring_len, __args) +#define stmmac_set_rx_ring_len(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, set_rx_ring_len, __args) +#define stmmac_set_rx_tail_ptr(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, set_rx_tail_ptr, __args) +#define stmmac_set_tx_tail_ptr(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, set_tx_tail_ptr, __args) +#define stmmac_enable_tso(__priv, __args...) \ + stmmac_do_void_callback(__priv, dma, enable_tso, __args) + +struct mac_device_info; +struct net_device; +struct rgmii_adv; +struct stmmac_safety_stats; +struct stmmac_tc_entry; + +/* Helpers to program the MAC core */ +struct stmmac_ops { + /* MAC core initialization */ + void (*core_init)(struct mac_device_info *hw, struct net_device *dev); + /* Enable the MAC RX/TX */ + void (*set_mac)(void __iomem *ioaddr, bool enable); + /* Enable and verify that the IPC module is supported */ + int (*rx_ipc)(struct mac_device_info *hw); + /* Enable RX Queues */ + void (*rx_queue_enable)(struct mac_device_info *hw, u8 mode, u32 queue); + /* RX Queues Priority */ + void (*rx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); + /* TX Queues Priority */ + void (*tx_queue_prio)(struct mac_device_info *hw, u32 prio, u32 queue); + /* RX Queues Routing */ + void (*rx_queue_routing)(struct mac_device_info *hw, u8 packet, + u32 queue); + /* Program RX Algorithms */ + void (*prog_mtl_rx_algorithms)(struct mac_device_info *hw, u32 rx_alg); + /* Program TX Algorithms */ + void (*prog_mtl_tx_algorithms)(struct mac_device_info *hw, u32 tx_alg); + /* Set MTL TX queues weight */ + void (*set_mtl_tx_queue_weight)(struct mac_device_info *hw, + u32 weight, u32 queue); + /* RX MTL queue to RX dma mapping */ + void (*map_mtl_to_dma)(struct mac_device_info *hw, u32 queue, u32 chan); + /* Configure AV Algorithm */ + void (*config_cbs)(struct mac_device_info *hw, u32 send_slope, + u32 idle_slope, u32 high_credit, u32 low_credit, + u32 queue); + /* Dump MAC registers */ + void (*dump_regs)(struct mac_device_info *hw, u32 *reg_space); + /* Handle extra events on specific interrupts hw dependent */ + int (*host_irq_status)(struct mac_device_info *hw, + struct stmmac_extra_stats *x); + /* Handle MTL interrupts */ + int (*host_mtl_irq_status)(struct mac_device_info *hw, u32 chan); + /* Multicast filter setting */ + void (*set_filter)(struct mac_device_info *hw, struct net_device *dev); + /* Flow control setting */ + void (*flow_ctrl)(struct mac_device_info *hw, unsigned int duplex, + unsigned int fc, unsigned int pause_time, u32 tx_cnt); + /* Set power management mode (e.g. magic frame) */ + void (*pmt)(struct mac_device_info *hw, unsigned long mode); + /* Set/Get Unicast MAC addresses */ + void (*set_umac_addr)(struct mac_device_info *hw, unsigned char *addr, + unsigned int reg_n); + void (*get_umac_addr)(struct mac_device_info *hw, unsigned char *addr, + unsigned int reg_n); + void (*set_eee_mode)(struct mac_device_info *hw, + bool en_tx_lpi_clockgating); + void (*reset_eee_mode)(struct mac_device_info *hw); + void (*set_eee_timer)(struct mac_device_info *hw, int ls, int tw); + void (*set_eee_pls)(struct mac_device_info *hw, int link); + void (*debug)(void __iomem *ioaddr, struct stmmac_extra_stats *x, + u32 rx_queues, u32 tx_queues); + /* PCS calls */ + void (*pcs_ctrl_ane)(void __iomem *ioaddr, bool ane, bool srgmi_ral, + bool loopback); + void (*pcs_rane)(void __iomem *ioaddr, bool restart); + void (*pcs_get_adv_lp)(void __iomem *ioaddr, struct rgmii_adv *adv); + /* Safety Features */ + int (*safety_feat_config)(void __iomem *ioaddr, unsigned int asp); + int (*safety_feat_irq_status)(struct net_device *ndev, + void __iomem *ioaddr, unsigned int asp, + struct stmmac_safety_stats *stats); + int (*safety_feat_dump)(struct stmmac_safety_stats *stats, + int index, unsigned long *count, const char **desc); + /* Flexible RX Parser */ + int (*rxp_config)(void __iomem *ioaddr, struct stmmac_tc_entry *entries, + unsigned int count); +}; + +#define stmmac_core_init(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, core_init, __args) +#define stmmac_mac_set(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_mac, __args) +#define stmmac_rx_ipc(__priv, __args...) \ + stmmac_do_callback(__priv, mac, rx_ipc, __args) +#define stmmac_rx_queue_enable(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, rx_queue_enable, __args) +#define stmmac_rx_queue_prio(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, rx_queue_prio, __args) +#define stmmac_tx_queue_prio(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, tx_queue_prio, __args) +#define stmmac_rx_queue_routing(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, rx_queue_routing, __args) +#define stmmac_prog_mtl_rx_algorithms(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, prog_mtl_rx_algorithms, __args) +#define stmmac_prog_mtl_tx_algorithms(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, prog_mtl_tx_algorithms, __args) +#define stmmac_set_mtl_tx_queue_weight(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_mtl_tx_queue_weight, __args) +#define stmmac_map_mtl_to_dma(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, map_mtl_to_dma, __args) +#define stmmac_config_cbs(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, config_cbs, __args) +#define stmmac_dump_mac_regs(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, dump_regs, __args) +#define stmmac_host_irq_status(__priv, __args...) \ + stmmac_do_callback(__priv, mac, host_irq_status, __args) +#define stmmac_host_mtl_irq_status(__priv, __args...) \ + stmmac_do_callback(__priv, mac, host_mtl_irq_status, __args) +#define stmmac_set_filter(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_filter, __args) +#define stmmac_flow_ctrl(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, flow_ctrl, __args) +#define stmmac_pmt(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, pmt, __args) +#define stmmac_set_umac_addr(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_umac_addr, __args) +#define stmmac_get_umac_addr(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, get_umac_addr, __args) +#define stmmac_set_eee_mode(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_eee_mode, __args) +#define stmmac_reset_eee_mode(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, reset_eee_mode, __args) +#define stmmac_set_eee_timer(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_eee_timer, __args) +#define stmmac_set_eee_pls(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, set_eee_pls, __args) +#define stmmac_mac_debug(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, debug, __args) +#define stmmac_pcs_ctrl_ane(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, pcs_ctrl_ane, __args) +#define stmmac_pcs_rane(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, pcs_rane, __args) +#define stmmac_pcs_get_adv_lp(__priv, __args...) \ + stmmac_do_void_callback(__priv, mac, pcs_get_adv_lp, __args) +#define stmmac_safety_feat_config(__priv, __args...) \ + stmmac_do_callback(__priv, mac, safety_feat_config, __args) +#define stmmac_safety_feat_irq_status(__priv, __args...) \ + stmmac_do_callback(__priv, mac, safety_feat_irq_status, __args) +#define stmmac_safety_feat_dump(__priv, __args...) \ + stmmac_do_callback(__priv, mac, safety_feat_dump, __args) +#define stmmac_rxp_config(__priv, __args...) \ + stmmac_do_callback(__priv, mac, rxp_config, __args) + +/* PTP and HW Timer helpers */ +struct stmmac_hwtimestamp { + void (*config_hw_tstamping) (void __iomem *ioaddr, u32 data); + void (*config_sub_second_increment)(void __iomem *ioaddr, u32 ptp_clock, + int gmac4, u32 *ssinc); + int (*init_systime) (void __iomem *ioaddr, u32 sec, u32 nsec); + int (*config_addend) (void __iomem *ioaddr, u32 addend); + int (*adjust_systime) (void __iomem *ioaddr, u32 sec, u32 nsec, + int add_sub, int gmac4); + void (*get_systime) (void __iomem *ioaddr, u64 *systime); +}; + +#define stmmac_config_hw_tstamping(__priv, __args...) \ + stmmac_do_void_callback(__priv, ptp, config_hw_tstamping, __args) +#define stmmac_config_sub_second_increment(__priv, __args...) \ + stmmac_do_void_callback(__priv, ptp, config_sub_second_increment, __args) +#define stmmac_init_systime(__priv, __args...) \ + stmmac_do_callback(__priv, ptp, init_systime, __args) +#define stmmac_config_addend(__priv, __args...) \ + stmmac_do_callback(__priv, ptp, config_addend, __args) +#define stmmac_adjust_systime(__priv, __args...) \ + stmmac_do_callback(__priv, ptp, adjust_systime, __args) +#define stmmac_get_systime(__priv, __args...) \ + stmmac_do_void_callback(__priv, ptp, get_systime, __args) + +/* Helpers to manage the descriptors for chain and ring modes */ +struct stmmac_mode_ops { + void (*init) (void *des, dma_addr_t phy_addr, unsigned int size, + unsigned int extend_desc); + unsigned int (*is_jumbo_frm) (int len, int ehn_desc); + int (*jumbo_frm)(void *priv, struct sk_buff *skb, int csum); + int (*set_16kib_bfsize)(int mtu); + void (*init_desc3)(struct dma_desc *p); + void (*refill_desc3) (void *priv, struct dma_desc *p); + void (*clean_desc3) (void *priv, struct dma_desc *p); +}; + +#define stmmac_mode_init(__priv, __args...) \ + stmmac_do_void_callback(__priv, mode, init, __args) +#define stmmac_is_jumbo_frm(__priv, __args...) \ + stmmac_do_callback(__priv, mode, is_jumbo_frm, __args) +#define stmmac_jumbo_frm(__priv, __args...) \ + stmmac_do_callback(__priv, mode, jumbo_frm, __args) +#define stmmac_set_16kib_bfsize(__priv, __args...) \ + stmmac_do_callback(__priv, mode, set_16kib_bfsize, __args) +#define stmmac_init_desc3(__priv, __args...) \ + stmmac_do_void_callback(__priv, mode, init_desc3, __args) +#define stmmac_refill_desc3(__priv, __args...) \ + stmmac_do_void_callback(__priv, mode, refill_desc3, __args) +#define stmmac_clean_desc3(__priv, __args...) \ + stmmac_do_void_callback(__priv, mode, clean_desc3, __args) + +struct stmmac_priv; +struct tc_cls_u32_offload; + +struct stmmac_tc_ops { + int (*init)(struct stmmac_priv *priv); + int (*setup_cls_u32)(struct stmmac_priv *priv, + struct tc_cls_u32_offload *cls); +}; + +#define stmmac_tc_init(__priv, __args...) \ + stmmac_do_callback(__priv, tc, init, __args) +#define stmmac_tc_setup_cls_u32(__priv, __args...) \ + stmmac_do_callback(__priv, tc, setup_cls_u32, __args) + +extern const struct stmmac_ops dwmac100_ops; +extern const struct stmmac_dma_ops dwmac100_dma_ops; +extern const struct stmmac_ops dwmac1000_ops; +extern const struct stmmac_dma_ops dwmac1000_dma_ops; +extern const struct stmmac_ops dwmac4_ops; +extern const struct stmmac_dma_ops dwmac4_dma_ops; +extern const struct stmmac_ops dwmac410_ops; +extern const struct stmmac_dma_ops dwmac410_dma_ops; +extern const struct stmmac_ops dwmac510_ops; +extern const struct stmmac_tc_ops dwmac510_tc_ops; + +#define GMAC_VERSION 0x00000020 /* GMAC CORE Version */ +#define GMAC4_VERSION 0x00000110 /* GMAC4+ CORE Version */ + +int stmmac_hwif_init(struct stmmac_priv *priv); + +#endif /* __STMMAC_HWIF_H__ */ diff --git a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c index ebd9e5e00f16..7b1d901bf5bc 100644 --- a/drivers/net/ethernet/stmicro/stmmac/norm_desc.c +++ b/drivers/net/ethernet/stmicro/stmmac/norm_desc.c @@ -253,7 +253,7 @@ static int ndesc_get_tx_timestamp_status(struct dma_desc *p) return (le32_to_cpu(p->des0) & TDES0_TIME_STAMP_STATUS) >> 17; } -static u64 ndesc_get_timestamp(void *desc, u32 ats) +static void ndesc_get_timestamp(void *desc, u32 ats, u64 *ts) { struct dma_desc *p = (struct dma_desc *)desc; u64 ns; @@ -262,7 +262,7 @@ static u64 ndesc_get_timestamp(void *desc, u32 ats) /* convert high/sec time stamp value to nanosecond */ ns += le32_to_cpu(p->des3) * 1000000000ULL; - return ns; + *ts = ns; } static int ndesc_get_rx_timestamp_status(void *desc, void *next_desc, u32 ats) diff --git a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c index 28e4b5d50ce6..a7ffc73fffe8 100644 --- a/drivers/net/ethernet/stmicro/stmmac/ring_mode.c +++ b/drivers/net/ethernet/stmicro/stmmac/ring_mode.c @@ -24,7 +24,7 @@ #include "stmmac.h" -static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) +static int jumbo_frm(void *p, struct sk_buff *skb, int csum) { struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)p; unsigned int nopaged_len = skb_headlen(skb); @@ -58,9 +58,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); - priv->hw->desc->prepare_tx_desc(desc, 1, bmax, csum, - STMMAC_RING_MODE, 0, - false, skb->len); + stmmac_prepare_tx_desc(priv, desc, 1, bmax, csum, + STMMAC_RING_MODE, 0, false, skb->len); tx_q->tx_skbuff[entry] = NULL; entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); @@ -79,9 +78,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); - priv->hw->desc->prepare_tx_desc(desc, 0, len, csum, - STMMAC_RING_MODE, 1, - true, skb->len); + stmmac_prepare_tx_desc(priv, desc, 0, len, csum, + STMMAC_RING_MODE, 1, true, skb->len); } else { des2 = dma_map_single(priv->device, skb->data, nopaged_len, DMA_TO_DEVICE); @@ -92,9 +90,8 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) tx_q->tx_skbuff_dma[entry].len = nopaged_len; tx_q->tx_skbuff_dma[entry].is_jumbo = true; desc->des3 = cpu_to_le32(des2 + BUF_SIZE_4KiB); - priv->hw->desc->prepare_tx_desc(desc, 1, nopaged_len, csum, - STMMAC_RING_MODE, 0, - true, skb->len); + stmmac_prepare_tx_desc(priv, desc, 1, nopaged_len, csum, + STMMAC_RING_MODE, 0, true, skb->len); } tx_q->cur_tx = entry; @@ -102,7 +99,7 @@ static int stmmac_jumbo_frm(void *p, struct sk_buff *skb, int csum) return entry; } -static unsigned int stmmac_is_jumbo_frm(int len, int enh_desc) +static unsigned int is_jumbo_frm(int len, int enh_desc) { unsigned int ret = 0; @@ -112,7 +109,7 @@ static unsigned int stmmac_is_jumbo_frm(int len, int enh_desc) return ret; } -static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) +static void refill_desc3(void *priv_ptr, struct dma_desc *p) { struct stmmac_priv *priv = (struct stmmac_priv *)priv_ptr; @@ -122,12 +119,12 @@ static void stmmac_refill_desc3(void *priv_ptr, struct dma_desc *p) } /* In ring mode we need to fill the desc3 because it is used as buffer */ -static void stmmac_init_desc3(struct dma_desc *p) +static void init_desc3(struct dma_desc *p) { p->des3 = cpu_to_le32(le32_to_cpu(p->des2) + BUF_SIZE_8KiB); } -static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) +static void clean_desc3(void *priv_ptr, struct dma_desc *p) { struct stmmac_tx_queue *tx_q = (struct stmmac_tx_queue *)priv_ptr; struct stmmac_priv *priv = tx_q->priv_data; @@ -140,7 +137,7 @@ static void stmmac_clean_desc3(void *priv_ptr, struct dma_desc *p) p->des3 = 0; } -static int stmmac_set_16kib_bfsize(int mtu) +static int set_16kib_bfsize(int mtu) { int ret = 0; if (unlikely(mtu >= BUF_SIZE_8KiB)) @@ -149,10 +146,10 @@ static int stmmac_set_16kib_bfsize(int mtu) } const struct stmmac_mode_ops ring_mode_ops = { - .is_jumbo_frm = stmmac_is_jumbo_frm, - .jumbo_frm = stmmac_jumbo_frm, - .refill_desc3 = stmmac_refill_desc3, - .init_desc3 = stmmac_init_desc3, - .clean_desc3 = stmmac_clean_desc3, - .set_16kib_bfsize = stmmac_set_16kib_bfsize, + .is_jumbo_frm = is_jumbo_frm, + .jumbo_frm = jumbo_frm, + .refill_desc3 = refill_desc3, + .init_desc3 = init_desc3, + .clean_desc3 = clean_desc3, + .set_16kib_bfsize = set_16kib_bfsize, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac.h b/drivers/net/ethernet/stmicro/stmmac/stmmac.h index da50451f8999..42fc76e76bf9 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac.h +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac.h @@ -76,6 +76,30 @@ struct stmmac_rx_queue { struct napi_struct napi ____cacheline_aligned_in_smp; }; +struct stmmac_tc_entry { + bool in_use; + bool in_hw; + bool is_last; + bool is_frag; + void *frag_ptr; + unsigned int table_pos; + u32 handle; + u32 prio; + struct { + u32 match_data; + u32 match_en; + u8 af:1; + u8 rf:1; + u8 im:1; + u8 nc:1; + u8 res1:4; + u8 frame_offset; + u8 ok_index; + u8 dma_ch_no; + u32 res2; + } __packed val; +}; + struct stmmac_priv { /* Frequently used values are kept adjacent for cache effect */ u32 tx_count_frames; @@ -130,6 +154,7 @@ struct stmmac_priv { int eee_active; int tx_lpi_timer; unsigned int mode; + unsigned int chain_mode; int extend_desc; struct ptp_clock *ptp_clock; struct ptp_clock_info ptp_clock_ops; @@ -150,6 +175,11 @@ struct stmmac_priv { unsigned long state; struct workqueue_struct *wq; struct work_struct service_task; + + /* TC Handling */ + unsigned int tc_entries_max; + unsigned int tc_off_max; + struct stmmac_tc_entry *tc_entries; }; enum stmmac_state { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c index 2c6ed47704fc..6d82b3ef5c3b 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ethtool.c @@ -291,11 +291,9 @@ static int stmmac_ethtool_get_link_ksettings(struct net_device *dev, cmd->base.speed = priv->xstats.pcs_speed; /* Get and convert ADV/LP_ADV from the HW AN registers */ - if (!priv->hw->mac->pcs_get_adv_lp) + if (stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv)) return -EOPNOTSUPP; /* should never happen indeed */ - priv->hw->mac->pcs_get_adv_lp(priv->ioaddr, &adv); - /* Encoding of PSE bits is defined in 802.3z, 37.2.1.4 */ ethtool_convert_link_mode_to_legacy_u32( @@ -393,11 +391,7 @@ stmmac_ethtool_set_link_ksettings(struct net_device *dev, ADVERTISED_10baseT_Full); spin_lock(&priv->lock); - - if (priv->hw->mac->pcs_ctrl_ane) - priv->hw->mac->pcs_ctrl_ane(priv->ioaddr, 1, - priv->hw->ps, 0); - + stmmac_pcs_ctrl_ane(priv, priv->ioaddr, 1, priv->hw->ps, 0); spin_unlock(&priv->lock); return 0; @@ -442,8 +436,8 @@ static void stmmac_ethtool_gregs(struct net_device *dev, memset(reg_space, 0x0, REG_SPACE_SIZE); - priv->hw->mac->dump_regs(priv->hw, reg_space); - priv->hw->dma->dump_regs(priv->ioaddr, reg_space); + stmmac_dump_mac_regs(priv, priv->hw, reg_space); + stmmac_dump_dma_regs(priv, priv->ioaddr, reg_space); /* Copy DMA registers to where ethtool expects them */ memcpy(®_space[ETHTOOL_DMA_OFFSET], ®_space[DMA_BUS_MODE / 4], NUM_DWMAC1000_DMA_REGS * 4); @@ -454,15 +448,13 @@ stmmac_get_pauseparam(struct net_device *netdev, struct ethtool_pauseparam *pause) { struct stmmac_priv *priv = netdev_priv(netdev); + struct rgmii_adv adv_lp; pause->rx_pause = 0; pause->tx_pause = 0; - if (priv->hw->pcs && priv->hw->mac->pcs_get_adv_lp) { - struct rgmii_adv adv_lp; - + if (priv->hw->pcs && !stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv_lp)) { pause->autoneg = 1; - priv->hw->mac->pcs_get_adv_lp(priv->ioaddr, &adv_lp); if (!adv_lp.pause) return; } else { @@ -488,12 +480,10 @@ stmmac_set_pauseparam(struct net_device *netdev, u32 tx_cnt = priv->plat->tx_queues_to_use; struct phy_device *phy = netdev->phydev; int new_pause = FLOW_OFF; + struct rgmii_adv adv_lp; - if (priv->hw->pcs && priv->hw->mac->pcs_get_adv_lp) { - struct rgmii_adv adv_lp; - + if (priv->hw->pcs && !stmmac_pcs_get_adv_lp(priv, priv->ioaddr, &adv_lp)) { pause->autoneg = 1; - priv->hw->mac->pcs_get_adv_lp(priv->ioaddr, &adv_lp); if (!adv_lp.pause) return -EOPNOTSUPP; } else { @@ -515,37 +505,32 @@ stmmac_set_pauseparam(struct net_device *netdev, return phy_start_aneg(phy); } - priv->hw->mac->flow_ctrl(priv->hw, phy->duplex, priv->flow_ctrl, - priv->pause, tx_cnt); + stmmac_flow_ctrl(priv, priv->hw, phy->duplex, priv->flow_ctrl, + priv->pause, tx_cnt); return 0; } static void stmmac_get_ethtool_stats(struct net_device *dev, struct ethtool_stats *dummy, u64 *data) { - const char *(*dump)(struct stmmac_safety_stats *stats, int index, - unsigned long *count); struct stmmac_priv *priv = netdev_priv(dev); u32 rx_queues_count = priv->plat->rx_queues_to_use; u32 tx_queues_count = priv->plat->tx_queues_to_use; unsigned long count; - int i, j = 0; - - if (priv->dma_cap.asp && priv->hw->mac->safety_feat_dump) { - dump = priv->hw->mac->safety_feat_dump; + int i, j = 0, ret; + if (priv->dma_cap.asp) { for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) { - if (dump(&priv->sstats, i, &count)) + if (!stmmac_safety_feat_dump(priv, &priv->sstats, i, + &count, NULL)) data[j++] = count; } } /* Update the DMA HW counters for dwmac10/100 */ - if (priv->hw->dma->dma_diagnostic_fr) - priv->hw->dma->dma_diagnostic_fr(&dev->stats, - (void *) &priv->xstats, - priv->ioaddr); - else { + ret = stmmac_dma_diagnostic_fr(priv, &dev->stats, (void *) &priv->xstats, + priv->ioaddr); + if (ret) { /* If supported, for new GMAC chips expose the MMC counters */ if (priv->dma_cap.rmon) { dwmac_mmc_read(priv->mmcaddr, &priv->mmc); @@ -565,11 +550,10 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, priv->xstats.phy_eee_wakeup_error_n = val; } - if ((priv->hw->mac->debug) && - (priv->synopsys_id >= DWMAC_CORE_3_50)) - priv->hw->mac->debug(priv->ioaddr, - (void *)&priv->xstats, - rx_queues_count, tx_queues_count); + if (priv->synopsys_id >= DWMAC_CORE_3_50) + stmmac_mac_debug(priv, priv->ioaddr, + (void *)&priv->xstats, + rx_queues_count, tx_queues_count); } for (i = 0; i < STMMAC_STATS_LEN; i++) { char *p = (char *)priv + stmmac_gstrings_stats[i].stat_offset; @@ -581,8 +565,6 @@ static void stmmac_get_ethtool_stats(struct net_device *dev, static int stmmac_get_sset_count(struct net_device *netdev, int sset) { struct stmmac_priv *priv = netdev_priv(netdev); - const char *(*dump)(struct stmmac_safety_stats *stats, int index, - unsigned long *count); int i, len, safety_len = 0; switch (sset) { @@ -591,11 +573,11 @@ static int stmmac_get_sset_count(struct net_device *netdev, int sset) if (priv->dma_cap.rmon) len += STMMAC_MMC_STATS_LEN; - if (priv->dma_cap.asp && priv->hw->mac->safety_feat_dump) { - dump = priv->hw->mac->safety_feat_dump; - + if (priv->dma_cap.asp) { for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) { - if (dump(&priv->sstats, i, NULL)) + if (!stmmac_safety_feat_dump(priv, + &priv->sstats, i, + NULL, NULL)) safety_len++; } @@ -613,17 +595,15 @@ static void stmmac_get_strings(struct net_device *dev, u32 stringset, u8 *data) int i; u8 *p = data; struct stmmac_priv *priv = netdev_priv(dev); - const char *(*dump)(struct stmmac_safety_stats *stats, int index, - unsigned long *count); switch (stringset) { case ETH_SS_STATS: - if (priv->dma_cap.asp && priv->hw->mac->safety_feat_dump) { - dump = priv->hw->mac->safety_feat_dump; + if (priv->dma_cap.asp) { for (i = 0; i < STMMAC_SAFETY_FEAT_SIZE; i++) { - const char *desc = dump(&priv->sstats, i, NULL); - - if (desc) { + const char *desc; + if (!stmmac_safety_feat_dump(priv, + &priv->sstats, i, + NULL, &desc)) { memcpy(p, desc, ETH_GSTRING_LEN); p += ETH_GSTRING_LEN; } @@ -810,7 +790,7 @@ static int stmmac_set_coalesce(struct net_device *dev, priv->tx_coal_frames = ec->tx_max_coalesced_frames; priv->tx_coal_timer = ec->tx_coalesce_usecs; priv->rx_riwt = rx_riwt; - priv->hw->dma->rx_watchdog(priv->ioaddr, priv->rx_riwt, rx_cnt); + stmmac_rx_watchdog(priv, priv->ioaddr, priv->rx_riwt, rx_cnt); return 0; } diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c index 08c19ebd5306..8d9cc2157afd 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_hwtstamp.c @@ -24,13 +24,13 @@ #include "common.h" #include "stmmac_ptp.h" -static void stmmac_config_hw_tstamping(void __iomem *ioaddr, u32 data) +static void config_hw_tstamping(void __iomem *ioaddr, u32 data) { writel(data, ioaddr + PTP_TCR); } -static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, - u32 ptp_clock, int gmac4) +static void config_sub_second_increment(void __iomem *ioaddr, + u32 ptp_clock, int gmac4, u32 *ssinc) { u32 value = readl(ioaddr + PTP_TCR); unsigned long data; @@ -57,10 +57,11 @@ static u32 stmmac_config_sub_second_increment(void __iomem *ioaddr, writel(reg_value, ioaddr + PTP_SSIR); - return data; + if (ssinc) + *ssinc = data; } -static int stmmac_init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) +static int init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) { int limit; u32 value; @@ -85,7 +86,7 @@ static int stmmac_init_systime(void __iomem *ioaddr, u32 sec, u32 nsec) return 0; } -static int stmmac_config_addend(void __iomem *ioaddr, u32 addend) +static int config_addend(void __iomem *ioaddr, u32 addend) { u32 value; int limit; @@ -109,8 +110,8 @@ static int stmmac_config_addend(void __iomem *ioaddr, u32 addend) return 0; } -static int stmmac_adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, - int add_sub, int gmac4) +static int adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, + int add_sub, int gmac4) { u32 value; int limit; @@ -152,7 +153,7 @@ static int stmmac_adjust_systime(void __iomem *ioaddr, u32 sec, u32 nsec, return 0; } -static u64 stmmac_get_systime(void __iomem *ioaddr) +static void get_systime(void __iomem *ioaddr, u64 *systime) { u64 ns; @@ -161,14 +162,15 @@ static u64 stmmac_get_systime(void __iomem *ioaddr) /* Get the TSS and convert sec time value to nanosecond */ ns += readl(ioaddr + PTP_STSR) * 1000000000ULL; - return ns; + if (systime) + *systime = ns; } const struct stmmac_hwtimestamp stmmac_ptp = { - .config_hw_tstamping = stmmac_config_hw_tstamping, - .init_systime = stmmac_init_systime, - .config_sub_second_increment = stmmac_config_sub_second_increment, - .config_addend = stmmac_config_addend, - .adjust_systime = stmmac_adjust_systime, - .get_systime = stmmac_get_systime, + .config_hw_tstamping = config_hw_tstamping, + .init_systime = init_systime, + .config_sub_second_increment = config_sub_second_increment, + .config_addend = config_addend, + .adjust_systime = adjust_systime, + .get_systime = get_systime, }; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c index b65e2d144698..d9dbe1355896 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_main.c @@ -45,11 +45,13 @@ #include <linux/seq_file.h> #endif /* CONFIG_DEBUG_FS */ #include <linux/net_tstamp.h> +#include <net/pkt_cls.h> #include "stmmac_ptp.h" #include "stmmac.h" #include <linux/reset.h> #include <linux/of_mdio.h> #include "dwmac1000.h" +#include "hwif.h" #define STMMAC_ALIGN(x) L1_CACHE_ALIGN(x) #define TSO_MAX_BUFF_SIZE (SZ_16K - 1) @@ -335,8 +337,8 @@ static void stmmac_enable_eee_mode(struct stmmac_priv *priv) /* Check and enter in LPI mode */ if (!priv->tx_path_in_lpi_mode) - priv->hw->mac->set_eee_mode(priv->hw, - priv->plat->en_tx_lpi_clockgating); + stmmac_set_eee_mode(priv, priv->hw, + priv->plat->en_tx_lpi_clockgating); } /** @@ -347,7 +349,7 @@ static void stmmac_enable_eee_mode(struct stmmac_priv *priv) */ void stmmac_disable_eee_mode(struct stmmac_priv *priv) { - priv->hw->mac->reset_eee_mode(priv->hw); + stmmac_reset_eee_mode(priv, priv->hw); del_timer_sync(&priv->eee_ctrl_timer); priv->tx_path_in_lpi_mode = false; } @@ -410,8 +412,8 @@ bool stmmac_eee_init(struct stmmac_priv *priv) if (priv->eee_active) { netdev_dbg(priv->dev, "disable EEE\n"); del_timer_sync(&priv->eee_ctrl_timer); - priv->hw->mac->set_eee_timer(priv->hw, 0, - tx_lpi_timer); + stmmac_set_eee_timer(priv, priv->hw, 0, + tx_lpi_timer); } priv->eee_active = 0; spin_unlock_irqrestore(&priv->lock, flags); @@ -426,12 +428,11 @@ bool stmmac_eee_init(struct stmmac_priv *priv) mod_timer(&priv->eee_ctrl_timer, STMMAC_LPI_T(eee_timer)); - priv->hw->mac->set_eee_timer(priv->hw, - STMMAC_DEFAULT_LIT_LS, - tx_lpi_timer); + stmmac_set_eee_timer(priv, priv->hw, + STMMAC_DEFAULT_LIT_LS, tx_lpi_timer); } /* Set HW EEE according to the speed */ - priv->hw->mac->set_eee_pls(priv->hw, ndev->phydev->link); + stmmac_set_eee_pls(priv, priv->hw, ndev->phydev->link); ret = true; spin_unlock_irqrestore(&priv->lock, flags); @@ -464,9 +465,9 @@ static void stmmac_get_tx_hwtstamp(struct stmmac_priv *priv, return; /* check tx tstamp status */ - if (priv->hw->desc->get_tx_timestamp_status(p)) { + if (stmmac_get_tx_timestamp_status(priv, p)) { /* get the valid tstamp */ - ns = priv->hw->desc->get_timestamp(p, priv->adv_ts); + stmmac_get_timestamp(priv, p, priv->adv_ts, &ns); memset(&shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); shhwtstamp.hwtstamp = ns_to_ktime(ns); @@ -502,8 +503,8 @@ static void stmmac_get_rx_hwtstamp(struct stmmac_priv *priv, struct dma_desc *p, desc = np; /* Check if timestamp is available */ - if (priv->hw->desc->get_rx_timestamp_status(p, np, priv->adv_ts)) { - ns = priv->hw->desc->get_timestamp(desc, priv->adv_ts); + if (stmmac_get_rx_timestamp_status(priv, p, np, priv->adv_ts)) { + stmmac_get_timestamp(priv, desc, priv->adv_ts, &ns); netdev_dbg(priv->dev, "get valid RX hw timestamp %llu\n", ns); shhwtstamp = skb_hwtstamps(skb); memset(shhwtstamp, 0, sizeof(struct skb_shared_hwtstamps)); @@ -707,18 +708,18 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) priv->hwts_tx_en = config.tx_type == HWTSTAMP_TX_ON; if (!priv->hwts_tx_en && !priv->hwts_rx_en) - priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, 0); + stmmac_config_hw_tstamping(priv, priv->ptpaddr, 0); else { value = (PTP_TCR_TSENA | PTP_TCR_TSCFUPDT | PTP_TCR_TSCTRLSSR | tstamp_all | ptp_v2 | ptp_over_ethernet | ptp_over_ipv6_udp | ptp_over_ipv4_udp | ts_event_en | ts_master_en | snap_type_sel); - priv->hw->ptp->config_hw_tstamping(priv->ptpaddr, value); + stmmac_config_hw_tstamping(priv, priv->ptpaddr, value); /* program Sub Second Increment reg */ - sec_inc = priv->hw->ptp->config_sub_second_increment( - priv->ptpaddr, priv->plat->clk_ptp_rate, - priv->plat->has_gmac4); + stmmac_config_sub_second_increment(priv, + priv->ptpaddr, priv->plat->clk_ptp_rate, + priv->plat->has_gmac4, &sec_inc); temp = div_u64(1000000000ULL, sec_inc); /* calculate default added value: @@ -728,15 +729,14 @@ static int stmmac_hwtstamp_ioctl(struct net_device *dev, struct ifreq *ifr) */ temp = (u64)(temp << 32); priv->default_addend = div_u64(temp, priv->plat->clk_ptp_rate); - priv->hw->ptp->config_addend(priv->ptpaddr, - priv->default_addend); + stmmac_config_addend(priv, priv->ptpaddr, priv->default_addend); /* initialize system time */ ktime_get_real_ts64(&now); /* lower 32 bits of tv_sec are safe until y2106 */ - priv->hw->ptp->init_systime(priv->ptpaddr, (u32)now.tv_sec, - now.tv_nsec); + stmmac_init_systime(priv, priv->ptpaddr, + (u32)now.tv_sec, now.tv_nsec); } return copy_to_user(ifr->ifr_data, &config, @@ -770,7 +770,6 @@ static int stmmac_init_ptp(struct stmmac_priv *priv) netdev_info(priv->dev, "IEEE 1588-2008 Advanced Timestamp supported\n"); - priv->hw->ptp = &stmmac_ptp; priv->hwts_tx_en = 0; priv->hwts_rx_en = 0; @@ -795,8 +794,8 @@ static void stmmac_mac_flow_ctrl(struct stmmac_priv *priv, u32 duplex) { u32 tx_cnt = priv->plat->tx_queues_to_use; - priv->hw->mac->flow_ctrl(priv->hw, duplex, priv->flow_ctrl, - priv->pause, tx_cnt); + stmmac_flow_ctrl(priv, priv->hw, duplex, priv->flow_ctrl, + priv->pause, tx_cnt); } /** @@ -1008,7 +1007,7 @@ static void stmmac_display_rx_rings(struct stmmac_priv *priv) head_rx = (void *)rx_q->dma_rx; /* Display RX ring */ - priv->hw->desc->display_ring(head_rx, DMA_RX_SIZE, true); + stmmac_display_ring(priv, head_rx, DMA_RX_SIZE, true); } } @@ -1029,7 +1028,7 @@ static void stmmac_display_tx_rings(struct stmmac_priv *priv) else head_tx = (void *)tx_q->dma_tx; - priv->hw->desc->display_ring(head_tx, DMA_TX_SIZE, false); + stmmac_display_ring(priv, head_tx, DMA_TX_SIZE, false); } } @@ -1073,13 +1072,13 @@ static void stmmac_clear_rx_descriptors(struct stmmac_priv *priv, u32 queue) /* Clear the RX descriptors */ for (i = 0; i < DMA_RX_SIZE; i++) if (priv->extend_desc) - priv->hw->desc->init_rx_desc(&rx_q->dma_erx[i].basic, - priv->use_riwt, priv->mode, - (i == DMA_RX_SIZE - 1)); + stmmac_init_rx_desc(priv, &rx_q->dma_erx[i].basic, + priv->use_riwt, priv->mode, + (i == DMA_RX_SIZE - 1)); else - priv->hw->desc->init_rx_desc(&rx_q->dma_rx[i], - priv->use_riwt, priv->mode, - (i == DMA_RX_SIZE - 1)); + stmmac_init_rx_desc(priv, &rx_q->dma_rx[i], + priv->use_riwt, priv->mode, + (i == DMA_RX_SIZE - 1)); } /** @@ -1097,13 +1096,11 @@ static void stmmac_clear_tx_descriptors(struct stmmac_priv *priv, u32 queue) /* Clear the TX descriptors */ for (i = 0; i < DMA_TX_SIZE; i++) if (priv->extend_desc) - priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic, - priv->mode, - (i == DMA_TX_SIZE - 1)); + stmmac_init_tx_desc(priv, &tx_q->dma_etx[i].basic, + priv->mode, (i == DMA_TX_SIZE - 1)); else - priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i], - priv->mode, - (i == DMA_TX_SIZE - 1)); + stmmac_init_tx_desc(priv, &tx_q->dma_tx[i], + priv->mode, (i == DMA_TX_SIZE - 1)); } /** @@ -1164,9 +1161,8 @@ static int stmmac_init_rx_buffers(struct stmmac_priv *priv, struct dma_desc *p, else p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[i]); - if ((priv->hw->mode->init_desc3) && - (priv->dma_buf_sz == BUF_SIZE_16KiB)) - priv->hw->mode->init_desc3(p); + if (priv->dma_buf_sz == BUF_SIZE_16KiB) + stmmac_init_desc3(priv, p); return 0; } @@ -1232,13 +1228,14 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) { struct stmmac_priv *priv = netdev_priv(dev); u32 rx_count = priv->plat->rx_queues_to_use; - unsigned int bfsize = 0; int ret = -ENOMEM; + int bfsize = 0; int queue; int i; - if (priv->hw->mode->set_16kib_bfsize) - bfsize = priv->hw->mode->set_16kib_bfsize(dev->mtu); + bfsize = stmmac_set_16kib_bfsize(priv, dev->mtu); + if (bfsize < 0) + bfsize = 0; if (bfsize < BUF_SIZE_16KiB) bfsize = stmmac_set_bfsize(dev->mtu, priv->dma_buf_sz); @@ -1282,13 +1279,11 @@ static int init_dma_rx_desc_rings(struct net_device *dev, gfp_t flags) /* Setup the chained descriptor addresses */ if (priv->mode == STMMAC_CHAIN_MODE) { if (priv->extend_desc) - priv->hw->mode->init(rx_q->dma_erx, - rx_q->dma_rx_phy, - DMA_RX_SIZE, 1); + stmmac_mode_init(priv, rx_q->dma_erx, + rx_q->dma_rx_phy, DMA_RX_SIZE, 1); else - priv->hw->mode->init(rx_q->dma_rx, - rx_q->dma_rx_phy, - DMA_RX_SIZE, 0); + stmmac_mode_init(priv, rx_q->dma_rx, + rx_q->dma_rx_phy, DMA_RX_SIZE, 0); } } @@ -1335,13 +1330,11 @@ static int init_dma_tx_desc_rings(struct net_device *dev) /* Setup the chained descriptor addresses */ if (priv->mode == STMMAC_CHAIN_MODE) { if (priv->extend_desc) - priv->hw->mode->init(tx_q->dma_etx, - tx_q->dma_tx_phy, - DMA_TX_SIZE, 1); + stmmac_mode_init(priv, tx_q->dma_etx, + tx_q->dma_tx_phy, DMA_TX_SIZE, 1); else - priv->hw->mode->init(tx_q->dma_tx, - tx_q->dma_tx_phy, - DMA_TX_SIZE, 0); + stmmac_mode_init(priv, tx_q->dma_tx, + tx_q->dma_tx_phy, DMA_TX_SIZE, 0); } for (i = 0; i < DMA_TX_SIZE; i++) { @@ -1664,7 +1657,7 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv) for (queue = 0; queue < rx_queues_count; queue++) { mode = priv->plat->rx_queues_cfg[queue].mode_to_use; - priv->hw->mac->rx_queue_enable(priv->hw, mode, queue); + stmmac_rx_queue_enable(priv, priv->hw, mode, queue); } } @@ -1678,7 +1671,7 @@ static void stmmac_mac_enable_rx_queues(struct stmmac_priv *priv) static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan) { netdev_dbg(priv->dev, "DMA RX processes started in channel %d\n", chan); - priv->hw->dma->start_rx(priv->ioaddr, chan); + stmmac_start_rx(priv, priv->ioaddr, chan); } /** @@ -1691,7 +1684,7 @@ static void stmmac_start_rx_dma(struct stmmac_priv *priv, u32 chan) static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan) { netdev_dbg(priv->dev, "DMA TX processes started in channel %d\n", chan); - priv->hw->dma->start_tx(priv->ioaddr, chan); + stmmac_start_tx(priv, priv->ioaddr, chan); } /** @@ -1704,7 +1697,7 @@ static void stmmac_start_tx_dma(struct stmmac_priv *priv, u32 chan) static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan) { netdev_dbg(priv->dev, "DMA RX processes stopped in channel %d\n", chan); - priv->hw->dma->stop_rx(priv->ioaddr, chan); + stmmac_stop_rx(priv, priv->ioaddr, chan); } /** @@ -1717,7 +1710,7 @@ static void stmmac_stop_rx_dma(struct stmmac_priv *priv, u32 chan) static void stmmac_stop_tx_dma(struct stmmac_priv *priv, u32 chan) { netdev_dbg(priv->dev, "DMA TX processes stopped in channel %d\n", chan); - priv->hw->dma->stop_tx(priv->ioaddr, chan); + stmmac_stop_tx(priv, priv->ioaddr, chan); } /** @@ -1808,19 +1801,18 @@ static void stmmac_dma_operation_mode(struct stmmac_priv *priv) for (chan = 0; chan < rx_channels_count; chan++) { qmode = priv->plat->rx_queues_cfg[chan].mode_to_use; - priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, - rxfifosz, qmode); + stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, + rxfifosz, qmode); } for (chan = 0; chan < tx_channels_count; chan++) { qmode = priv->plat->tx_queues_cfg[chan].mode_to_use; - priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, - txfifosz, qmode); + stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan, + txfifosz, qmode); } } else { - priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, - rxfifosz); + stmmac_dma_mode(priv, priv->ioaddr, txmode, rxmode, rxfifosz); } } @@ -1851,9 +1843,8 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) else p = tx_q->dma_tx + entry; - status = priv->hw->desc->tx_status(&priv->dev->stats, - &priv->xstats, p, - priv->ioaddr); + status = stmmac_tx_status(priv, &priv->dev->stats, + &priv->xstats, p, priv->ioaddr); /* Check if the descriptor is owned by the DMA */ if (unlikely(status & tx_dma_own)) break; @@ -1891,8 +1882,7 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) tx_q->tx_skbuff_dma[entry].map_as_page = false; } - if (priv->hw->mode->clean_desc3) - priv->hw->mode->clean_desc3(tx_q, p); + stmmac_clean_desc3(priv, tx_q, p); tx_q->tx_skbuff_dma[entry].last_segment = false; tx_q->tx_skbuff_dma[entry].is_jumbo = false; @@ -1904,7 +1894,7 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) tx_q->tx_skbuff[entry] = NULL; } - priv->hw->desc->release_tx_desc(p, priv->mode); + stmmac_release_tx_desc(priv, p, priv->mode); entry = STMMAC_GET_ENTRY(entry, DMA_TX_SIZE); } @@ -1929,16 +1919,6 @@ static void stmmac_tx_clean(struct stmmac_priv *priv, u32 queue) netif_tx_unlock(priv->dev); } -static inline void stmmac_enable_dma_irq(struct stmmac_priv *priv, u32 chan) -{ - priv->hw->dma->enable_dma_irq(priv->ioaddr, chan); -} - -static inline void stmmac_disable_dma_irq(struct stmmac_priv *priv, u32 chan) -{ - priv->hw->dma->disable_dma_irq(priv->ioaddr, chan); -} - /** * stmmac_tx_err - to manage the tx error * @priv: driver private structure @@ -1957,13 +1937,11 @@ static void stmmac_tx_err(struct stmmac_priv *priv, u32 chan) dma_free_tx_skbufs(priv, chan); for (i = 0; i < DMA_TX_SIZE; i++) if (priv->extend_desc) - priv->hw->desc->init_tx_desc(&tx_q->dma_etx[i].basic, - priv->mode, - (i == DMA_TX_SIZE - 1)); + stmmac_init_tx_desc(priv, &tx_q->dma_etx[i].basic, + priv->mode, (i == DMA_TX_SIZE - 1)); else - priv->hw->desc->init_tx_desc(&tx_q->dma_tx[i], - priv->mode, - (i == DMA_TX_SIZE - 1)); + stmmac_init_tx_desc(priv, &tx_q->dma_tx[i], + priv->mode, (i == DMA_TX_SIZE - 1)); tx_q->dirty_tx = 0; tx_q->cur_tx = 0; tx_q->mss = 0; @@ -2004,30 +1982,30 @@ static void stmmac_set_dma_operation_mode(struct stmmac_priv *priv, u32 txmode, txfifosz /= tx_channels_count; if (priv->synopsys_id >= DWMAC_CORE_4_00) { - priv->hw->dma->dma_rx_mode(priv->ioaddr, rxmode, chan, - rxfifosz, rxqmode); - priv->hw->dma->dma_tx_mode(priv->ioaddr, txmode, chan, - txfifosz, txqmode); + stmmac_dma_rx_mode(priv, priv->ioaddr, rxmode, chan, rxfifosz, + rxqmode); + stmmac_dma_tx_mode(priv, priv->ioaddr, txmode, chan, txfifosz, + txqmode); } else { - priv->hw->dma->dma_mode(priv->ioaddr, txmode, rxmode, - rxfifosz); + stmmac_dma_mode(priv, priv->ioaddr, txmode, rxmode, rxfifosz); } } static bool stmmac_safety_feat_interrupt(struct stmmac_priv *priv) { - bool ret = false; + int ret = false; /* Safety features are only available in cores >= 5.10 */ if (priv->synopsys_id < DWMAC_CORE_5_10) return ret; - if (priv->hw->mac->safety_feat_irq_status) - ret = priv->hw->mac->safety_feat_irq_status(priv->dev, - priv->ioaddr, priv->dma_cap.asp, &priv->sstats); - - if (ret) + ret = stmmac_safety_feat_irq_status(priv, priv->dev, + priv->ioaddr, priv->dma_cap.asp, &priv->sstats); + if (ret && (ret != -EINVAL)) { stmmac_global_err(priv); - return ret; + return true; + } + + return false; } /** @@ -2045,7 +2023,11 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) tx_channel_count : rx_channel_count; u32 chan; bool poll_scheduled = false; - int status[channels_to_check]; + int status[max_t(u32, MTL_MAX_TX_QUEUES, MTL_MAX_RX_QUEUES)]; + + /* Make sure we never check beyond our status buffer. */ + if (WARN_ON_ONCE(channels_to_check > ARRAY_SIZE(status))) + channels_to_check = ARRAY_SIZE(status); /* Each DMA channel can be used for rx and tx simultaneously, yet * napi_struct is embedded in struct stmmac_rx_queue rather than in a @@ -2054,16 +2036,15 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) * all tx queues rather than just a single tx queue. */ for (chan = 0; chan < channels_to_check; chan++) - status[chan] = priv->hw->dma->dma_interrupt(priv->ioaddr, - &priv->xstats, - chan); + status[chan] = stmmac_dma_interrupt_status(priv, priv->ioaddr, + &priv->xstats, chan); for (chan = 0; chan < rx_channel_count; chan++) { if (likely(status[chan] & handle_rx)) { struct stmmac_rx_queue *rx_q = &priv->rx_queue[chan]; if (likely(napi_schedule_prep(&rx_q->napi))) { - stmmac_disable_dma_irq(priv, chan); + stmmac_disable_dma_irq(priv, priv->ioaddr, chan); __napi_schedule(&rx_q->napi); poll_scheduled = true; } @@ -2084,7 +2065,8 @@ static void stmmac_dma_interrupt(struct stmmac_priv *priv) &priv->rx_queue[0]; if (likely(napi_schedule_prep(&rx_q->napi))) { - stmmac_disable_dma_irq(priv, chan); + stmmac_disable_dma_irq(priv, + priv->ioaddr, chan); __napi_schedule(&rx_q->napi); } break; @@ -2144,32 +2126,6 @@ static void stmmac_mmc_setup(struct stmmac_priv *priv) } /** - * stmmac_selec_desc_mode - to select among: normal/alternate/extend descriptors - * @priv: driver private structure - * Description: select the Enhanced/Alternate or Normal descriptors. - * In case of Enhanced/Alternate, it checks if the extended descriptors are - * supported by the HW capability register. - */ -static void stmmac_selec_desc_mode(struct stmmac_priv *priv) -{ - if (priv->plat->enh_desc) { - dev_info(priv->device, "Enhanced/Alternate descriptors\n"); - - /* GMAC older than 3.50 has no extended descriptors */ - if (priv->synopsys_id >= DWMAC_CORE_3_50) { - dev_info(priv->device, "Enabled extended descriptors\n"); - priv->extend_desc = 1; - } else - dev_warn(priv->device, "Extended descriptors not supported\n"); - - priv->hw->desc = &enh_desc_ops; - } else { - dev_info(priv->device, "Normal descriptors\n"); - priv->hw->desc = &ndesc_ops; - } -} - -/** * stmmac_get_hw_features - get MAC capabilities from the HW cap. register. * @priv: driver private structure * Description: @@ -2180,15 +2136,7 @@ static void stmmac_selec_desc_mode(struct stmmac_priv *priv) */ static int stmmac_get_hw_features(struct stmmac_priv *priv) { - u32 ret = 0; - - if (priv->hw->dma->get_hw_feature) { - priv->hw->dma->get_hw_feature(priv->ioaddr, - &priv->dma_cap); - ret = 1; - } - - return ret; + return stmmac_get_hw_feature(priv, priv->ioaddr, &priv->dma_cap) == 0; } /** @@ -2201,8 +2149,7 @@ static int stmmac_get_hw_features(struct stmmac_priv *priv) static void stmmac_check_ether_addr(struct stmmac_priv *priv) { if (!is_valid_ether_addr(priv->dev->dev_addr)) { - priv->hw->mac->get_umac_addr(priv->hw, - priv->dev->dev_addr, 0); + stmmac_get_umac_addr(priv, priv->hw, priv->dev->dev_addr, 0); if (!is_valid_ether_addr(priv->dev->dev_addr)) eth_hw_addr_random(priv->dev); netdev_info(priv->dev, "device MAC address %pM\n", @@ -2238,7 +2185,7 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) if (priv->extend_desc && (priv->mode == STMMAC_RING_MODE)) atds = 1; - ret = priv->hw->dma->reset(priv->ioaddr); + ret = stmmac_reset(priv, priv->ioaddr); if (ret) { dev_err(priv->device, "Failed to reset the dma\n"); return ret; @@ -2246,51 +2193,48 @@ static int stmmac_init_dma_engine(struct stmmac_priv *priv) if (priv->synopsys_id >= DWMAC_CORE_4_00) { /* DMA Configuration */ - priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, - dummy_dma_tx_phy, dummy_dma_rx_phy, atds); + stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, + dummy_dma_tx_phy, dummy_dma_rx_phy, atds); /* DMA RX Channel Configuration */ for (chan = 0; chan < rx_channels_count; chan++) { rx_q = &priv->rx_queue[chan]; - priv->hw->dma->init_rx_chan(priv->ioaddr, - priv->plat->dma_cfg, - rx_q->dma_rx_phy, chan); + stmmac_init_rx_chan(priv, priv->ioaddr, + priv->plat->dma_cfg, rx_q->dma_rx_phy, + chan); rx_q->rx_tail_addr = rx_q->dma_rx_phy + (DMA_RX_SIZE * sizeof(struct dma_desc)); - priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - rx_q->rx_tail_addr, - chan); + stmmac_set_rx_tail_ptr(priv, priv->ioaddr, + rx_q->rx_tail_addr, chan); } /* DMA TX Channel Configuration */ for (chan = 0; chan < tx_channels_count; chan++) { tx_q = &priv->tx_queue[chan]; - priv->hw->dma->init_chan(priv->ioaddr, - priv->plat->dma_cfg, - chan); + stmmac_init_chan(priv, priv->ioaddr, + priv->plat->dma_cfg, chan); - priv->hw->dma->init_tx_chan(priv->ioaddr, - priv->plat->dma_cfg, - tx_q->dma_tx_phy, chan); + stmmac_init_tx_chan(priv, priv->ioaddr, + priv->plat->dma_cfg, tx_q->dma_tx_phy, + chan); tx_q->tx_tail_addr = tx_q->dma_tx_phy + (DMA_TX_SIZE * sizeof(struct dma_desc)); - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, - tx_q->tx_tail_addr, - chan); + stmmac_set_tx_tail_ptr(priv, priv->ioaddr, + tx_q->tx_tail_addr, chan); } } else { rx_q = &priv->rx_queue[chan]; tx_q = &priv->tx_queue[chan]; - priv->hw->dma->init(priv->ioaddr, priv->plat->dma_cfg, - tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds); + stmmac_dma_init(priv, priv->ioaddr, priv->plat->dma_cfg, + tx_q->dma_tx_phy, rx_q->dma_rx_phy, atds); } - if (priv->plat->axi && priv->hw->dma->axi) - priv->hw->dma->axi(priv->ioaddr, priv->plat->axi); + if (priv->plat->axi) + stmmac_axi(priv, priv->ioaddr, priv->plat->axi); return ret; } @@ -2336,18 +2280,14 @@ static void stmmac_set_rings_length(struct stmmac_priv *priv) u32 chan; /* set TX ring length */ - if (priv->hw->dma->set_tx_ring_len) { - for (chan = 0; chan < tx_channels_count; chan++) - priv->hw->dma->set_tx_ring_len(priv->ioaddr, - (DMA_TX_SIZE - 1), chan); - } + for (chan = 0; chan < tx_channels_count; chan++) + stmmac_set_tx_ring_len(priv, priv->ioaddr, + (DMA_TX_SIZE - 1), chan); /* set RX ring length */ - if (priv->hw->dma->set_rx_ring_len) { - for (chan = 0; chan < rx_channels_count; chan++) - priv->hw->dma->set_rx_ring_len(priv->ioaddr, - (DMA_RX_SIZE - 1), chan); - } + for (chan = 0; chan < rx_channels_count; chan++) + stmmac_set_rx_ring_len(priv, priv->ioaddr, + (DMA_RX_SIZE - 1), chan); } /** @@ -2363,7 +2303,7 @@ static void stmmac_set_tx_queue_weight(struct stmmac_priv *priv) for (queue = 0; queue < tx_queues_count; queue++) { weight = priv->plat->tx_queues_cfg[queue].weight; - priv->hw->mac->set_mtl_tx_queue_weight(priv->hw, weight, queue); + stmmac_set_mtl_tx_queue_weight(priv, priv->hw, weight, queue); } } @@ -2384,7 +2324,7 @@ static void stmmac_configure_cbs(struct stmmac_priv *priv) if (mode_to_use == MTL_QUEUE_DCB) continue; - priv->hw->mac->config_cbs(priv->hw, + stmmac_config_cbs(priv, priv->hw, priv->plat->tx_queues_cfg[queue].send_slope, priv->plat->tx_queues_cfg[queue].idle_slope, priv->plat->tx_queues_cfg[queue].high_credit, @@ -2406,7 +2346,7 @@ static void stmmac_rx_queue_dma_chan_map(struct stmmac_priv *priv) for (queue = 0; queue < rx_queues_count; queue++) { chan = priv->plat->rx_queues_cfg[queue].chan; - priv->hw->mac->map_mtl_to_dma(priv->hw, queue, chan); + stmmac_map_mtl_to_dma(priv, priv->hw, queue, chan); } } @@ -2426,7 +2366,7 @@ static void stmmac_mac_config_rx_queues_prio(struct stmmac_priv *priv) continue; prio = priv->plat->rx_queues_cfg[queue].prio; - priv->hw->mac->rx_queue_prio(priv->hw, prio, queue); + stmmac_rx_queue_prio(priv, priv->hw, prio, queue); } } @@ -2446,7 +2386,7 @@ static void stmmac_mac_config_tx_queues_prio(struct stmmac_priv *priv) continue; prio = priv->plat->tx_queues_cfg[queue].prio; - priv->hw->mac->tx_queue_prio(priv->hw, prio, queue); + stmmac_tx_queue_prio(priv, priv->hw, prio, queue); } } @@ -2467,7 +2407,7 @@ static void stmmac_mac_config_rx_queues_routing(struct stmmac_priv *priv) continue; packet = priv->plat->rx_queues_cfg[queue].pkt_route; - priv->hw->mac->rx_queue_routing(priv->hw, packet, queue); + stmmac_rx_queue_routing(priv, priv->hw, packet, queue); } } @@ -2481,50 +2421,47 @@ static void stmmac_mtl_configuration(struct stmmac_priv *priv) u32 rx_queues_count = priv->plat->rx_queues_to_use; u32 tx_queues_count = priv->plat->tx_queues_to_use; - if (tx_queues_count > 1 && priv->hw->mac->set_mtl_tx_queue_weight) + if (tx_queues_count > 1) stmmac_set_tx_queue_weight(priv); /* Configure MTL RX algorithms */ - if (rx_queues_count > 1 && priv->hw->mac->prog_mtl_rx_algorithms) - priv->hw->mac->prog_mtl_rx_algorithms(priv->hw, - priv->plat->rx_sched_algorithm); + if (rx_queues_count > 1) + stmmac_prog_mtl_rx_algorithms(priv, priv->hw, + priv->plat->rx_sched_algorithm); /* Configure MTL TX algorithms */ - if (tx_queues_count > 1 && priv->hw->mac->prog_mtl_tx_algorithms) - priv->hw->mac->prog_mtl_tx_algorithms(priv->hw, - priv->plat->tx_sched_algorithm); + if (tx_queues_count > 1) + stmmac_prog_mtl_tx_algorithms(priv, priv->hw, + priv->plat->tx_sched_algorithm); /* Configure CBS in AVB TX queues */ - if (tx_queues_count > 1 && priv->hw->mac->config_cbs) + if (tx_queues_count > 1) stmmac_configure_cbs(priv); /* Map RX MTL to DMA channels */ - if (priv->hw->mac->map_mtl_to_dma) - stmmac_rx_queue_dma_chan_map(priv); + stmmac_rx_queue_dma_chan_map(priv); /* Enable MAC RX Queues */ - if (priv->hw->mac->rx_queue_enable) - stmmac_mac_enable_rx_queues(priv); + stmmac_mac_enable_rx_queues(priv); /* Set RX priorities */ - if (rx_queues_count > 1 && priv->hw->mac->rx_queue_prio) + if (rx_queues_count > 1) stmmac_mac_config_rx_queues_prio(priv); /* Set TX priorities */ - if (tx_queues_count > 1 && priv->hw->mac->tx_queue_prio) + if (tx_queues_count > 1) stmmac_mac_config_tx_queues_prio(priv); /* Set RX routing */ - if (rx_queues_count > 1 && priv->hw->mac->rx_queue_routing) + if (rx_queues_count > 1) stmmac_mac_config_rx_queues_routing(priv); } static void stmmac_safety_feat_configuration(struct stmmac_priv *priv) { - if (priv->hw->mac->safety_feat_config && priv->dma_cap.asp) { + if (priv->dma_cap.asp) { netdev_info(priv->dev, "Enabling Safety Features\n"); - priv->hw->mac->safety_feat_config(priv->ioaddr, - priv->dma_cap.asp); + stmmac_safety_feat_config(priv, priv->ioaddr, priv->dma_cap.asp); } else { netdev_info(priv->dev, "No Safety Features support found\n"); } @@ -2559,7 +2496,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) } /* Copy the MAC addr into the HW */ - priv->hw->mac->set_umac_addr(priv->hw, dev->dev_addr, 0); + stmmac_set_umac_addr(priv, priv->hw, dev->dev_addr, 0); /* PS and related bits will be programmed according to the speed */ if (priv->hw->pcs) { @@ -2575,7 +2512,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) } /* Initialize the MAC Core */ - priv->hw->mac->core_init(priv->hw, dev); + stmmac_core_init(priv, priv->hw, dev); /* Initialize MTL*/ if (priv->synopsys_id >= DWMAC_CORE_4_00) @@ -2585,7 +2522,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) if (priv->synopsys_id >= DWMAC_CORE_5_10) stmmac_safety_feat_configuration(priv); - ret = priv->hw->mac->rx_ipc(priv->hw); + ret = stmmac_rx_ipc(priv, priv->hw); if (!ret) { netdev_warn(priv->dev, "RX IPC Checksum Offload disabled\n"); priv->plat->rx_coe = STMMAC_RX_COE_NONE; @@ -2593,7 +2530,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) } /* Enable the MAC Rx/Tx */ - priv->hw->mac->set_mac(priv->ioaddr, true); + stmmac_mac_set(priv, priv->ioaddr, true); /* Set the HW DMA mode and the COE */ stmmac_dma_operation_mode(priv); @@ -2623,13 +2560,14 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) priv->tx_lpi_timer = STMMAC_DEFAULT_TWT_LS; - if ((priv->use_riwt) && (priv->hw->dma->rx_watchdog)) { - priv->rx_riwt = MAX_DMA_RIWT; - priv->hw->dma->rx_watchdog(priv->ioaddr, MAX_DMA_RIWT, rx_cnt); + if (priv->use_riwt) { + ret = stmmac_rx_watchdog(priv, priv->ioaddr, MAX_DMA_RIWT, rx_cnt); + if (!ret) + priv->rx_riwt = MAX_DMA_RIWT; } - if (priv->hw->pcs && priv->hw->mac->pcs_ctrl_ane) - priv->hw->mac->pcs_ctrl_ane(priv->hw, 1, priv->hw->ps, 0); + if (priv->hw->pcs) + stmmac_pcs_ctrl_ane(priv, priv->hw, 1, priv->hw->ps, 0); /* set TX and RX rings length */ stmmac_set_rings_length(priv); @@ -2637,7 +2575,7 @@ static int stmmac_hw_setup(struct net_device *dev, bool init_ptp) /* Enable TSO */ if (priv->tso) { for (chan = 0; chan < tx_cnt; chan++) - priv->hw->dma->enable_tso(priv->ioaddr, 1, chan); + stmmac_enable_tso(priv, priv->ioaddr, 1, chan); } return 0; @@ -2808,7 +2746,7 @@ static int stmmac_release(struct net_device *dev) free_dma_desc_resources(priv); /* Disable the MAC Rx/Tx */ - priv->hw->mac->set_mac(priv->ioaddr, false); + stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(dev); @@ -2851,10 +2789,10 @@ static void stmmac_tso_allocator(struct stmmac_priv *priv, unsigned int des, buff_size = tmp_len >= TSO_MAX_BUFF_SIZE ? TSO_MAX_BUFF_SIZE : tmp_len; - priv->hw->desc->prepare_tso_tx_desc(desc, 0, buff_size, - 0, 1, - (last_segment) && (tmp_len <= TSO_MAX_BUFF_SIZE), - 0, 0); + stmmac_prepare_tso_tx_desc(priv, desc, 0, buff_size, + 0, 1, + (last_segment) && (tmp_len <= TSO_MAX_BUFF_SIZE), + 0, 0); tmp_len -= TSO_MAX_BUFF_SIZE; } @@ -2926,7 +2864,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) /* set new MSS value if needed */ if (mss != tx_q->mss) { mss_desc = tx_q->dma_tx + tx_q->cur_tx; - priv->hw->desc->set_mss(mss_desc, mss); + stmmac_set_mss(priv, mss_desc, mss); tx_q->mss = mss; tx_q->cur_tx = STMMAC_GET_ENTRY(tx_q->cur_tx, DMA_TX_SIZE); WARN_ON(tx_q->tx_skbuff[tx_q->cur_tx]); @@ -3012,7 +2950,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) STMMAC_COAL_TIMER(priv->tx_coal_timer)); } else { priv->tx_count_frames = 0; - priv->hw->desc->set_tx_ic(desc); + stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; } @@ -3022,11 +2960,11 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) priv->hwts_tx_en)) { /* declare that device is doing timestamping */ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - priv->hw->desc->enable_tx_timestamp(first); + stmmac_enable_tx_timestamp(priv, first); } /* Complete the first descriptor before granting the DMA */ - priv->hw->desc->prepare_tso_tx_desc(first, 1, + stmmac_prepare_tso_tx_desc(priv, first, 1, proto_hdr_len, pay_len, 1, tx_q->tx_skbuff_dma[first_entry].last_segment, @@ -3040,7 +2978,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) * sure that MSS's own bit is the last thing written. */ dma_wmb(); - priv->hw->desc->set_tx_owner(mss_desc); + stmmac_set_tx_owner(priv, mss_desc); } /* The own bit must be the latest setting done when prepare the @@ -3054,8 +2992,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) __func__, tx_q->cur_tx, tx_q->dirty_tx, first_entry, tx_q->cur_tx, first, nfrags); - priv->hw->desc->display_ring((void *)tx_q->dma_tx, DMA_TX_SIZE, - 0); + stmmac_display_ring(priv, (void *)tx_q->dma_tx, DMA_TX_SIZE, 0); pr_info(">>> frame to be transmitted: "); print_pkt(skb->data, skb_headlen(skb)); @@ -3063,8 +3000,7 @@ static netdev_tx_t stmmac_tso_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr, - queue); + stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, queue); return NETDEV_TX_OK; @@ -3136,11 +3072,11 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) enh_desc = priv->plat->enh_desc; /* To program the descriptors according to the size of the frame */ if (enh_desc) - is_jumbo = priv->hw->mode->is_jumbo_frm(skb->len, enh_desc); + is_jumbo = stmmac_is_jumbo_frm(priv, skb->len, enh_desc); if (unlikely(is_jumbo) && likely(priv->synopsys_id < DWMAC_CORE_4_00)) { - entry = priv->hw->mode->jumbo_frm(tx_q, skb, csum_insertion); + entry = stmmac_jumbo_frm(priv, tx_q, skb, csum_insertion); if (unlikely(entry < 0)) goto dma_map_err; } @@ -3174,9 +3110,8 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) tx_q->tx_skbuff_dma[entry].last_segment = last_segment; /* Prepare the descriptor and set the own bit too */ - priv->hw->desc->prepare_tx_desc(desc, 0, len, csum_insertion, - priv->mode, 1, last_segment, - skb->len); + stmmac_prepare_tx_desc(priv, desc, 0, len, csum_insertion, + priv->mode, 1, last_segment, skb->len); } /* Only the last descriptor gets to point to the skb. */ @@ -3203,7 +3138,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) else tx_head = (void *)tx_q->dma_tx; - priv->hw->desc->display_ring(tx_head, DMA_TX_SIZE, false); + stmmac_display_ring(priv, tx_head, DMA_TX_SIZE, false); netdev_dbg(priv->dev, ">>> frame to be transmitted: "); print_pkt(skb->data, skb->len); @@ -3228,7 +3163,7 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) STMMAC_COAL_TIMER(priv->tx_coal_timer)); } else { priv->tx_count_frames = 0; - priv->hw->desc->set_tx_ic(desc); + stmmac_set_tx_ic(priv, desc); priv->xstats.tx_set_ic_bit++; } @@ -3259,13 +3194,13 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) priv->hwts_tx_en)) { /* declare that device is doing timestamping */ skb_shinfo(skb)->tx_flags |= SKBTX_IN_PROGRESS; - priv->hw->desc->enable_tx_timestamp(first); + stmmac_enable_tx_timestamp(priv, first); } /* Prepare the first descriptor setting the OWN bit too */ - priv->hw->desc->prepare_tx_desc(first, 1, nopaged_len, - csum_insertion, priv->mode, 1, - last_segment, skb->len); + stmmac_prepare_tx_desc(priv, first, 1, nopaged_len, + csum_insertion, priv->mode, 1, last_segment, + skb->len); /* The own bit must be the latest setting done when prepare the * descriptor and then barrier is needed to make sure that @@ -3277,10 +3212,10 @@ static netdev_tx_t stmmac_xmit(struct sk_buff *skb, struct net_device *dev) netdev_tx_sent_queue(netdev_get_tx_queue(dev, queue), skb->len); if (priv->synopsys_id < DWMAC_CORE_4_00) - priv->hw->dma->enable_dma_transmission(priv->ioaddr); + stmmac_enable_dma_transmission(priv, priv->ioaddr); else - priv->hw->dma->set_tx_tail_ptr(priv->ioaddr, tx_q->tx_tail_addr, - queue); + stmmac_set_tx_tail_ptr(priv, priv->ioaddr, tx_q->tx_tail_addr, + queue); return NETDEV_TX_OK; @@ -3370,8 +3305,8 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) } else { p->des2 = cpu_to_le32(rx_q->rx_skbuff_dma[entry]); } - if (priv->hw->mode->refill_desc3) - priv->hw->mode->refill_desc3(rx_q, p); + + stmmac_refill_desc3(priv, rx_q, p); if (rx_q->rx_zeroc_thresh > 0) rx_q->rx_zeroc_thresh--; @@ -3382,9 +3317,9 @@ static inline void stmmac_rx_refill(struct stmmac_priv *priv, u32 queue) dma_wmb(); if (unlikely(priv->synopsys_id >= DWMAC_CORE_4_00)) - priv->hw->desc->init_rx_desc(p, priv->use_riwt, 0, 0); + stmmac_init_rx_desc(priv, p, priv->use_riwt, 0, 0); else - priv->hw->desc->set_rx_owner(p); + stmmac_set_rx_owner(priv, p); dma_wmb(); @@ -3418,7 +3353,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) else rx_head = (void *)rx_q->dma_rx; - priv->hw->desc->display_ring(rx_head, DMA_RX_SIZE, true); + stmmac_display_ring(priv, rx_head, DMA_RX_SIZE, true); } while (count < limit) { int status; @@ -3431,8 +3366,8 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) p = rx_q->dma_rx + entry; /* read the status of the incoming frame */ - status = priv->hw->desc->rx_status(&priv->dev->stats, - &priv->xstats, p); + status = stmmac_rx_status(priv, &priv->dev->stats, + &priv->xstats, p); /* check if managed by the DMA otherwise go ahead */ if (unlikely(status & dma_own)) break; @@ -3449,11 +3384,9 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) prefetch(np); - if ((priv->extend_desc) && (priv->hw->desc->rx_extended_status)) - priv->hw->desc->rx_extended_status(&priv->dev->stats, - &priv->xstats, - rx_q->dma_erx + - entry); + if (priv->extend_desc) + stmmac_rx_extended_status(priv, &priv->dev->stats, + &priv->xstats, rx_q->dma_erx + entry); if (unlikely(status == discard_frame)) { priv->dev->stats.rx_errors++; if (priv->hwts_rx_en && !priv->extend_desc) { @@ -3479,7 +3412,7 @@ static int stmmac_rx(struct stmmac_priv *priv, int limit, u32 queue) else des = le32_to_cpu(p->des2); - frame_len = priv->hw->desc->get_rx_frame_len(p, coe); + frame_len = stmmac_get_rx_frame_len(priv, p, coe); /* If frame length is greater than skb buffer size * (preallocated during init) then the packet is @@ -3621,7 +3554,7 @@ static int stmmac_poll(struct napi_struct *napi, int budget) work_done = stmmac_rx(priv, budget, rx_q->queue_index); if (work_done < budget) { napi_complete_done(napi, work_done); - stmmac_enable_dma_irq(priv, chan); + stmmac_enable_dma_irq(priv, priv->ioaddr, chan); } return work_done; } @@ -3654,7 +3587,7 @@ static void stmmac_set_rx_mode(struct net_device *dev) { struct stmmac_priv *priv = netdev_priv(dev); - priv->hw->mac->set_filter(priv->hw, dev); + stmmac_set_filter(priv, priv->hw, dev); } /** @@ -3727,7 +3660,7 @@ static int stmmac_set_features(struct net_device *netdev, /* No check needed because rx_coe has been set before and it will be * fixed in case of issue. */ - priv->hw->mac->rx_ipc(priv->hw); + stmmac_rx_ipc(priv, priv->hw); return 0; } @@ -3771,8 +3704,7 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) /* To handle GMAC own interrupts */ if ((priv->plat->has_gmac) || (priv->plat->has_gmac4)) { - int status = priv->hw->mac->host_irq_status(priv->hw, - &priv->xstats); + int status = stmmac_host_irq_status(priv, priv->hw, &priv->xstats); if (unlikely(status)) { /* For LPI we need to save the tx status */ @@ -3787,15 +3719,14 @@ static irqreturn_t stmmac_interrupt(int irq, void *dev_id) struct stmmac_rx_queue *rx_q = &priv->rx_queue[queue]; - status |= - priv->hw->mac->host_mtl_irq_status(priv->hw, - queue); + status |= stmmac_host_mtl_irq_status(priv, + priv->hw, queue); - if (status & CORE_IRQ_MTL_RX_OVERFLOW && - priv->hw->dma->set_rx_tail_ptr) - priv->hw->dma->set_rx_tail_ptr(priv->ioaddr, - rx_q->rx_tail_addr, - queue); + if (status & CORE_IRQ_MTL_RX_OVERFLOW) + stmmac_set_rx_tail_ptr(priv, + priv->ioaddr, + rx_q->rx_tail_addr, + queue); } } @@ -3860,6 +3791,58 @@ static int stmmac_ioctl(struct net_device *dev, struct ifreq *rq, int cmd) return ret; } +static int stmmac_setup_tc_block_cb(enum tc_setup_type type, void *type_data, + void *cb_priv) +{ + struct stmmac_priv *priv = cb_priv; + int ret = -EOPNOTSUPP; + + stmmac_disable_all_queues(priv); + + switch (type) { + case TC_SETUP_CLSU32: + if (tc_cls_can_offload_and_chain0(priv->dev, type_data)) + ret = stmmac_tc_setup_cls_u32(priv, priv, type_data); + break; + default: + break; + } + + stmmac_enable_all_queues(priv); + return ret; +} + +static int stmmac_setup_tc_block(struct stmmac_priv *priv, + struct tc_block_offload *f) +{ + if (f->binder_type != TCF_BLOCK_BINDER_TYPE_CLSACT_INGRESS) + return -EOPNOTSUPP; + + switch (f->command) { + case TC_BLOCK_BIND: + return tcf_block_cb_register(f->block, stmmac_setup_tc_block_cb, + priv, priv); + case TC_BLOCK_UNBIND: + tcf_block_cb_unregister(f->block, stmmac_setup_tc_block_cb, priv); + return 0; + default: + return -EOPNOTSUPP; + } +} + +static int stmmac_setup_tc(struct net_device *ndev, enum tc_setup_type type, + void *type_data) +{ + struct stmmac_priv *priv = netdev_priv(ndev); + + switch (type) { + case TC_SETUP_BLOCK: + return stmmac_setup_tc_block(priv, type_data); + default: + return -EOPNOTSUPP; + } +} + static int stmmac_set_mac_address(struct net_device *ndev, void *addr) { struct stmmac_priv *priv = netdev_priv(ndev); @@ -3869,7 +3852,7 @@ static int stmmac_set_mac_address(struct net_device *ndev, void *addr) if (ret) return ret; - priv->hw->mac->set_umac_addr(priv->hw, ndev->dev_addr, 0); + stmmac_set_umac_addr(priv, priv->hw, ndev->dev_addr, 0); return ret; } @@ -4098,6 +4081,7 @@ static const struct net_device_ops stmmac_netdev_ops = { .ndo_set_rx_mode = stmmac_set_rx_mode, .ndo_tx_timeout = stmmac_tx_timeout, .ndo_do_ioctl = stmmac_ioctl, + .ndo_setup_tc = stmmac_setup_tc, #ifdef CONFIG_NET_POLL_CONTROLLER .ndo_poll_controller = stmmac_poll_controller, #endif @@ -4145,49 +4129,17 @@ static void stmmac_service_task(struct work_struct *work) */ static int stmmac_hw_init(struct stmmac_priv *priv) { - struct mac_device_info *mac; - - /* Identify the MAC HW device */ - if (priv->plat->setup) { - mac = priv->plat->setup(priv); - } else if (priv->plat->has_gmac) { - priv->dev->priv_flags |= IFF_UNICAST_FLT; - mac = dwmac1000_setup(priv->ioaddr, - priv->plat->multicast_filter_bins, - priv->plat->unicast_filter_entries, - &priv->synopsys_id); - } else if (priv->plat->has_gmac4) { - priv->dev->priv_flags |= IFF_UNICAST_FLT; - mac = dwmac4_setup(priv->ioaddr, - priv->plat->multicast_filter_bins, - priv->plat->unicast_filter_entries, - &priv->synopsys_id); - } else { - mac = dwmac100_setup(priv->ioaddr, &priv->synopsys_id); - } - if (!mac) - return -ENOMEM; - - priv->hw = mac; + int ret; /* dwmac-sun8i only work in chain mode */ if (priv->plat->has_sun8i) chain_mode = 1; + priv->chain_mode = chain_mode; - /* To use the chained or ring mode */ - if (priv->synopsys_id >= DWMAC_CORE_4_00) { - priv->hw->mode = &dwmac4_ring_mode_ops; - } else { - if (chain_mode) { - priv->hw->mode = &chain_mode_ops; - dev_info(priv->device, "Chain mode enabled\n"); - priv->mode = STMMAC_CHAIN_MODE; - } else { - priv->hw->mode = &ring_mode_ops; - dev_info(priv->device, "Ring mode enabled\n"); - priv->mode = STMMAC_RING_MODE; - } - } + /* Initialize HW Interface */ + ret = stmmac_hwif_init(priv); + if (ret) + return ret; /* Get the HW capability (new GMAC newer than 3.50a) */ priv->hw_cap_support = stmmac_get_hw_features(priv); @@ -4221,12 +4173,6 @@ static int stmmac_hw_init(struct stmmac_priv *priv) dev_info(priv->device, "No HW DMA feature register supported\n"); } - /* To use alternate (extended), normal or GMAC4 descriptor structures */ - if (priv->synopsys_id >= DWMAC_CORE_4_00) - priv->hw->desc = &dwmac4_desc_ops; - else - stmmac_selec_desc_mode(priv); - if (priv->plat->rx_coe) { priv->hw->rx_csum = priv->plat->rx_coe; dev_info(priv->device, "RX Checksum Offload Engine supported\n"); @@ -4335,6 +4281,11 @@ int stmmac_dvr_probe(struct device *device, ndev->hw_features = NETIF_F_SG | NETIF_F_IP_CSUM | NETIF_F_IPV6_CSUM | NETIF_F_RXCSUM; + ret = stmmac_tc_init(priv, priv); + if (!ret) { + ndev->hw_features |= NETIF_F_HW_TC; + } + if ((priv->plat->tso_en) && (priv->dma_cap.tsoen)) { ndev->hw_features |= NETIF_F_TSO | NETIF_F_TSO6; priv->tso = true; @@ -4458,7 +4409,7 @@ int stmmac_dvr_remove(struct device *dev) stmmac_stop_all_dma(priv); - priv->hw->mac->set_mac(priv->ioaddr, false); + stmmac_mac_set(priv, priv->ioaddr, false); netif_carrier_off(ndev); unregister_netdev(ndev); if (priv->plat->stmmac_rst) @@ -4507,10 +4458,10 @@ int stmmac_suspend(struct device *dev) /* Enable Power down mode by programming the PMT regs */ if (device_may_wakeup(priv->device)) { - priv->hw->mac->pmt(priv->hw, priv->wolopts); + stmmac_pmt(priv, priv->hw, priv->wolopts); priv->irq_wake = 1; } else { - priv->hw->mac->set_mac(priv->ioaddr, false); + stmmac_mac_set(priv, priv->ioaddr, false); pinctrl_pm_select_sleep_state(priv->device); /* Disable clock in case of PWM is off */ clk_disable(priv->plat->pclk); @@ -4574,7 +4525,7 @@ int stmmac_resume(struct device *dev) */ if (device_may_wakeup(priv->device)) { spin_lock_irqsave(&priv->lock, flags); - priv->hw->mac->pmt(priv->hw, 0); + stmmac_pmt(priv, priv->hw, 0); spin_unlock_irqrestore(&priv->lock, flags); priv->irq_wake = 0; } else { diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c index e471a903c654..7d3a5c7f5db6 100644 --- a/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_ptp.c @@ -49,9 +49,7 @@ static int stmmac_adjust_freq(struct ptp_clock_info *ptp, s32 ppb) addend = neg_adj ? (addend - diff) : (addend + diff); spin_lock_irqsave(&priv->ptp_lock, flags); - - priv->hw->ptp->config_addend(priv->ptpaddr, addend); - + stmmac_config_addend(priv, priv->ptpaddr, addend); spin_unlock_irqrestore(&priv->ptp_lock, flags); return 0; @@ -84,10 +82,8 @@ static int stmmac_adjust_time(struct ptp_clock_info *ptp, s64 delta) nsec = reminder; spin_lock_irqsave(&priv->ptp_lock, flags); - - priv->hw->ptp->adjust_systime(priv->ptpaddr, sec, nsec, neg_adj, - priv->plat->has_gmac4); - + stmmac_adjust_systime(priv, priv->ptpaddr, sec, nsec, neg_adj, + priv->plat->has_gmac4); spin_unlock_irqrestore(&priv->ptp_lock, flags); return 0; @@ -110,9 +106,7 @@ static int stmmac_get_time(struct ptp_clock_info *ptp, struct timespec64 *ts) u64 ns; spin_lock_irqsave(&priv->ptp_lock, flags); - - ns = priv->hw->ptp->get_systime(priv->ptpaddr); - + stmmac_get_systime(priv, priv->ptpaddr, &ns); spin_unlock_irqrestore(&priv->ptp_lock, flags); *ts = ns_to_timespec64(ns); @@ -137,9 +131,7 @@ static int stmmac_set_time(struct ptp_clock_info *ptp, unsigned long flags; spin_lock_irqsave(&priv->ptp_lock, flags); - - priv->hw->ptp->init_systime(priv->ptpaddr, ts->tv_sec, ts->tv_nsec); - + stmmac_init_systime(priv, priv->ptpaddr, ts->tv_sec, ts->tv_nsec); spin_unlock_irqrestore(&priv->ptp_lock, flags); return 0; diff --git a/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c new file mode 100644 index 000000000000..881c94b73e2f --- /dev/null +++ b/drivers/net/ethernet/stmicro/stmmac/stmmac_tc.c @@ -0,0 +1,295 @@ +// SPDX-License-Identifier: (GPL-2.0 OR MIT) +/* + * Copyright (c) 2018 Synopsys, Inc. and/or its affiliates. + * stmmac TC Handling (HW only) + */ + +#include <net/pkt_cls.h> +#include <net/tc_act/tc_gact.h> +#include "common.h" +#include "dwmac4.h" +#include "dwmac5.h" +#include "stmmac.h" + +static void tc_fill_all_pass_entry(struct stmmac_tc_entry *entry) +{ + memset(entry, 0, sizeof(*entry)); + entry->in_use = true; + entry->is_last = true; + entry->is_frag = false; + entry->prio = ~0x0; + entry->handle = 0; + entry->val.match_data = 0x0; + entry->val.match_en = 0x0; + entry->val.af = 1; + entry->val.dma_ch_no = 0x0; +} + +static struct stmmac_tc_entry *tc_find_entry(struct stmmac_priv *priv, + struct tc_cls_u32_offload *cls, + bool free) +{ + struct stmmac_tc_entry *entry, *first = NULL, *dup = NULL; + u32 loc = cls->knode.handle; + int i; + + for (i = 0; i < priv->tc_entries_max; i++) { + entry = &priv->tc_entries[i]; + if (!entry->in_use && !first && free) + first = entry; + if (entry->handle == loc && !free) + dup = entry; + } + + if (dup) + return dup; + if (first) { + first->handle = loc; + first->in_use = true; + + /* Reset HW values */ + memset(&first->val, 0, sizeof(first->val)); + } + + return first; +} + +static int tc_fill_actions(struct stmmac_tc_entry *entry, + struct stmmac_tc_entry *frag, + struct tc_cls_u32_offload *cls) +{ + struct stmmac_tc_entry *action_entry = entry; + const struct tc_action *act; + struct tcf_exts *exts; + LIST_HEAD(actions); + + exts = cls->knode.exts; + if (!tcf_exts_has_actions(exts)) + return -EINVAL; + if (frag) + action_entry = frag; + + tcf_exts_to_list(exts, &actions); + list_for_each_entry(act, &actions, list) { + /* Accept */ + if (is_tcf_gact_ok(act)) { + action_entry->val.af = 1; + break; + } + /* Drop */ + if (is_tcf_gact_shot(act)) { + action_entry->val.rf = 1; + break; + } + + /* Unsupported */ + return -EINVAL; + } + + return 0; +} + +static int tc_fill_entry(struct stmmac_priv *priv, + struct tc_cls_u32_offload *cls) +{ + struct stmmac_tc_entry *entry, *frag = NULL; + struct tc_u32_sel *sel = cls->knode.sel; + u32 off, data, mask, real_off, rem; + u32 prio = cls->common.prio; + int ret; + + /* Only 1 match per entry */ + if (sel->nkeys <= 0 || sel->nkeys > 1) + return -EINVAL; + + off = sel->keys[0].off << sel->offshift; + data = sel->keys[0].val; + mask = sel->keys[0].mask; + + switch (ntohs(cls->common.protocol)) { + case ETH_P_ALL: + break; + case ETH_P_IP: + off += ETH_HLEN; + break; + default: + return -EINVAL; + } + + if (off > priv->tc_off_max) + return -EINVAL; + + real_off = off / 4; + rem = off % 4; + + entry = tc_find_entry(priv, cls, true); + if (!entry) + return -EINVAL; + + if (rem) { + frag = tc_find_entry(priv, cls, true); + if (!frag) { + ret = -EINVAL; + goto err_unuse; + } + + entry->frag_ptr = frag; + entry->val.match_en = (mask << (rem * 8)) & + GENMASK(31, rem * 8); + entry->val.match_data = (data << (rem * 8)) & + GENMASK(31, rem * 8); + entry->val.frame_offset = real_off; + entry->prio = prio; + + frag->val.match_en = (mask >> (rem * 8)) & + GENMASK(rem * 8 - 1, 0); + frag->val.match_data = (data >> (rem * 8)) & + GENMASK(rem * 8 - 1, 0); + frag->val.frame_offset = real_off + 1; + frag->prio = prio; + frag->is_frag = true; + } else { + entry->frag_ptr = NULL; + entry->val.match_en = mask; + entry->val.match_data = data; + entry->val.frame_offset = real_off; + entry->prio = prio; + } + + ret = tc_fill_actions(entry, frag, cls); + if (ret) + goto err_unuse; + + return 0; + +err_unuse: + if (frag) + frag->in_use = false; + entry->in_use = false; + return ret; +} + +static void tc_unfill_entry(struct stmmac_priv *priv, + struct tc_cls_u32_offload *cls) +{ + struct stmmac_tc_entry *entry; + + entry = tc_find_entry(priv, cls, false); + if (!entry) + return; + + entry->in_use = false; + if (entry->frag_ptr) { + entry = entry->frag_ptr; + entry->is_frag = false; + entry->in_use = false; + } +} + +static int tc_config_knode(struct stmmac_priv *priv, + struct tc_cls_u32_offload *cls) +{ + int ret; + + ret = tc_fill_entry(priv, cls); + if (ret) + return ret; + + ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries, + priv->tc_entries_max); + if (ret) + goto err_unfill; + + return 0; + +err_unfill: + tc_unfill_entry(priv, cls); + return ret; +} + +static int tc_delete_knode(struct stmmac_priv *priv, + struct tc_cls_u32_offload *cls) +{ + int ret; + + /* Set entry and fragments as not used */ + tc_unfill_entry(priv, cls); + + ret = stmmac_rxp_config(priv, priv->hw->pcsr, priv->tc_entries, + priv->tc_entries_max); + if (ret) + return ret; + + return 0; +} + +static int tc_setup_cls_u32(struct stmmac_priv *priv, + struct tc_cls_u32_offload *cls) +{ + switch (cls->command) { + case TC_CLSU32_REPLACE_KNODE: + tc_unfill_entry(priv, cls); + /* Fall through */ + case TC_CLSU32_NEW_KNODE: + return tc_config_knode(priv, cls); + case TC_CLSU32_DELETE_KNODE: + return tc_delete_knode(priv, cls); + default: + return -EOPNOTSUPP; + } +} + +static int tc_init(struct stmmac_priv *priv) +{ + struct dma_features *dma_cap = &priv->dma_cap; + unsigned int count; + + if (!dma_cap->frpsel) + return -EINVAL; + + switch (dma_cap->frpbs) { + case 0x0: + priv->tc_off_max = 64; + break; + case 0x1: + priv->tc_off_max = 128; + break; + case 0x2: + priv->tc_off_max = 256; + break; + default: + return -EINVAL; + } + + switch (dma_cap->frpes) { + case 0x0: + count = 64; + break; + case 0x1: + count = 128; + break; + case 0x2: + count = 256; + break; + default: + return -EINVAL; + } + + /* Reserve one last filter which lets all pass */ + priv->tc_entries_max = count; + priv->tc_entries = devm_kzalloc(priv->device, + sizeof(*priv->tc_entries) * count, GFP_KERNEL); + if (!priv->tc_entries) + return -ENOMEM; + + tc_fill_all_pass_entry(&priv->tc_entries[count - 1]); + + dev_info(priv->device, "Enabling HW TC (entries=%d, max_off=%d)\n", + priv->tc_entries_max, priv->tc_off_max); + return 0; +} + +const struct stmmac_tc_ops dwmac510_tc_ops = { + .init = tc_init, + .setup_cls_u32 = tc_setup_cls_u32, +}; diff --git a/drivers/net/ethernet/ti/davinci_mdio.c b/drivers/net/ethernet/ti/davinci_mdio.c index 3c33f4504d8e..98a1c97fb95e 100644 --- a/drivers/net/ethernet/ti/davinci_mdio.c +++ b/drivers/net/ethernet/ti/davinci_mdio.c @@ -34,6 +34,7 @@ #include <linux/clk.h> #include <linux/err.h> #include <linux/io.h> +#include <linux/iopoll.h> #include <linux/pm_runtime.h> #include <linux/davinci_emac.h> #include <linux/of.h> @@ -227,14 +228,14 @@ static inline int wait_for_user_access(struct davinci_mdio_data *data) static inline int wait_for_idle(struct davinci_mdio_data *data) { struct davinci_mdio_regs __iomem *regs = data->regs; - unsigned long timeout = jiffies + msecs_to_jiffies(MDIO_TIMEOUT); + u32 val, ret; - while (time_after(timeout, jiffies)) { - if (__raw_readl(®s->control) & CONTROL_IDLE) - return 0; - } - dev_err(data->dev, "timed out waiting for idle\n"); - return -ETIMEDOUT; + ret = readl_poll_timeout(®s->control, val, val & CONTROL_IDLE, + 0, MDIO_TIMEOUT * 1000); + if (ret) + dev_err(data->dev, "timed out waiting for idle\n"); + + return ret; } static int davinci_mdio_read(struct mii_bus *bus, int phy_id, int phy_reg) diff --git a/drivers/net/ethernet/ti/netcp.h b/drivers/net/ethernet/ti/netcp.h index 8900a6fad318..c4ffdf47bad5 100644 --- a/drivers/net/ethernet/ti/netcp.h +++ b/drivers/net/ethernet/ti/netcp.h @@ -33,6 +33,8 @@ #define SGMII_LINK_MAC_MAC_FORCED 2 #define SGMII_LINK_MAC_FIBER 3 #define SGMII_LINK_MAC_PHY_NO_MDIO 4 +#define RGMII_LINK_MAC_PHY 5 +#define RGMII_LINK_MAC_PHY_NO_MDIO 7 #define XGMII_LINK_MAC_PHY 10 #define XGMII_LINK_MAC_MAC_FORCED 11 @@ -212,6 +214,7 @@ struct netcp_module { int (*add_vid)(void *intf_priv, int vid); int (*del_vid)(void *intf_priv, int vid); int (*ioctl)(void *intf_priv, struct ifreq *req, int cmd); + int (*set_rx_mode)(void *intf_priv, bool promisc); /* used internally */ struct list_head module_list; diff --git a/drivers/net/ethernet/ti/netcp_core.c b/drivers/net/ethernet/ti/netcp_core.c index f5a7eb22d0f5..e40aa3e31af2 100644 --- a/drivers/net/ethernet/ti/netcp_core.c +++ b/drivers/net/ethernet/ti/netcp_core.c @@ -1509,6 +1509,24 @@ static void netcp_addr_sweep_add(struct netcp_intf *netcp) } } +static int netcp_set_promiscuous(struct netcp_intf *netcp, bool promisc) +{ + struct netcp_intf_modpriv *priv; + struct netcp_module *module; + int error; + + for_each_module(netcp, priv) { + module = priv->netcp_module; + if (!module->set_rx_mode) + continue; + + error = module->set_rx_mode(priv->module_priv, promisc); + if (error) + return error; + } + return 0; +} + static void netcp_set_rx_mode(struct net_device *ndev) { struct netcp_intf *netcp = netdev_priv(ndev); @@ -1538,6 +1556,7 @@ static void netcp_set_rx_mode(struct net_device *ndev) /* finally sweep and callout into modules */ netcp_addr_sweep_del(netcp); netcp_addr_sweep_add(netcp); + netcp_set_promiscuous(netcp, promisc); spin_unlock(&netcp->lock); } @@ -2155,8 +2174,13 @@ static int netcp_probe(struct platform_device *pdev) struct device_node *child, *interfaces; struct netcp_device *netcp_device; struct device *dev = &pdev->dev; + struct netcp_module *module; int ret; + if (!knav_dma_device_ready() || + !knav_qmss_device_ready()) + return -EPROBE_DEFER; + if (!node) { dev_err(dev, "could not find device info\n"); return -ENODEV; @@ -2203,6 +2227,14 @@ static int netcp_probe(struct platform_device *pdev) /* Add the device instance to the list */ list_add_tail(&netcp_device->device_list, &netcp_devices); + /* Probe & attach any modules already registered */ + mutex_lock(&netcp_modules_lock); + for_each_netcp_module(module) { + ret = netcp_module_probe(netcp_device, module); + if (ret < 0) + dev_err(dev, "module(%s) probe failed\n", module->name); + } + mutex_unlock(&netcp_modules_lock); return 0; probe_quit_interface: diff --git a/drivers/net/ethernet/ti/netcp_ethss.c b/drivers/net/ethernet/ti/netcp_ethss.c index 56dbc0b9fedc..6a728d35e776 100644 --- a/drivers/net/ethernet/ti/netcp_ethss.c +++ b/drivers/net/ethernet/ti/netcp_ethss.c @@ -21,6 +21,7 @@ #include <linux/io.h> #include <linux/module.h> #include <linux/of_mdio.h> +#include <linux/of_net.h> #include <linux/of_address.h> #include <linux/if_vlan.h> #include <linux/ptp_classify.h> @@ -42,7 +43,7 @@ /* 1G Ethernet SS defines */ #define GBE_MODULE_NAME "netcp-gbe" -#define GBE_SS_VERSION_14 0x4ed21104 +#define GBE_SS_VERSION_14 0x4ed2 #define GBE_SS_REG_INDEX 0 #define GBE_SGMII34_REG_INDEX 1 @@ -72,6 +73,11 @@ #define IS_SS_ID_NU(d) \ (GBE_IDENT((d)->ss_version) == GBE_SS_ID_NU) +#define IS_SS_ID_VER_14(d) \ + (GBE_IDENT((d)->ss_version) == GBE_SS_VERSION_14) +#define IS_SS_ID_2U(d) \ + (GBE_IDENT((d)->ss_version) == GBE_SS_ID_2U) + #define GBENU_SS_REG_INDEX 0 #define GBENU_SM_REG_INDEX 1 #define GBENU_SGMII_MODULE_OFFSET 0x100 @@ -86,7 +92,7 @@ /* 10G Ethernet SS defines */ #define XGBE_MODULE_NAME "netcp-xgbe" -#define XGBE_SS_VERSION_10 0x4ee42100 +#define XGBE_SS_VERSION_10 0x4ee4 #define XGBE_SS_REG_INDEX 0 #define XGBE_SM_REG_INDEX 1 @@ -166,6 +172,11 @@ #define GBE_RXHOOK_ORDER 0 #define GBE_DEFAULT_ALE_AGEOUT 30 #define SLAVE_LINK_IS_XGMII(s) ((s)->link_interface >= XGMII_LINK_MAC_PHY) +#define SLAVE_LINK_IS_RGMII(s) \ + (((s)->link_interface >= RGMII_LINK_MAC_PHY) && \ + ((s)->link_interface <= RGMII_LINK_MAC_PHY_NO_MDIO)) +#define SLAVE_LINK_IS_SGMII(s) \ + ((s)->link_interface <= SGMII_LINK_MAC_PHY_NO_MDIO) #define NETCP_LINK_STATE_INVALID -1 #define GBE_SET_REG_OFS(p, rb, rn) p->rb##_ofs.rn = \ @@ -549,6 +560,7 @@ struct gbe_ss_regs { struct gbe_ss_regs_ofs { u16 id_ver; u16 control; + u16 rgmii_status; /* 2U */ }; struct gbe_switch_regs { @@ -591,6 +603,7 @@ struct gbe_port_regs { struct gbe_port_regs_ofs { u16 port_vlan; u16 tx_pri_map; + u16 rx_pri_map; u16 sa_lo; u16 sa_hi; u16 ts_ctl; @@ -695,6 +708,7 @@ struct gbe_slave { u32 link_interface; u32 mac_control; u8 phy_port_t; + struct device_node *node; struct device_node *phy_node; struct ts_ctl ts_ctl; struct list_head slave_list; @@ -1915,7 +1929,7 @@ static void keystone_get_ethtool_stats(struct net_device *ndev, gbe_dev = gbe_intf->gbe_dev; spin_lock_bh(&gbe_dev->hw_stats_lock); - if (gbe_dev->ss_version == GBE_SS_VERSION_14) + if (IS_SS_ID_VER_14(gbe_dev)) gbe_update_stats_ver14(gbe_dev, data); else gbe_update_stats(gbe_dev, data); @@ -2091,8 +2105,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev, ALE_PORT_STATE_FORWARD); if (ndev && slave->open && - slave->link_interface != SGMII_LINK_MAC_PHY && - slave->link_interface != XGMII_LINK_MAC_PHY) + ((slave->link_interface != SGMII_LINK_MAC_PHY) && + (slave->link_interface != RGMII_LINK_MAC_PHY) && + (slave->link_interface != XGMII_LINK_MAC_PHY))) netif_carrier_on(ndev); } else { writel(mac_control, GBE_REG_ADDR(slave, emac_regs, @@ -2101,8 +2116,9 @@ static void netcp_ethss_link_state_action(struct gbe_priv *gbe_dev, ALE_PORT_STATE, ALE_PORT_STATE_DISABLE); if (ndev && - slave->link_interface != SGMII_LINK_MAC_PHY && - slave->link_interface != XGMII_LINK_MAC_PHY) + ((slave->link_interface != SGMII_LINK_MAC_PHY) && + (slave->link_interface != RGMII_LINK_MAC_PHY) && + (slave->link_interface != XGMII_LINK_MAC_PHY))) netif_carrier_off(ndev); } @@ -2115,23 +2131,35 @@ static bool gbe_phy_link_status(struct gbe_slave *slave) return !slave->phy || slave->phy->link; } +#define RGMII_REG_STATUS_LINK BIT(0) + +static void netcp_2u_rgmii_get_port_link(struct gbe_priv *gbe_dev, bool *status) +{ + u32 val = 0; + + val = readl(GBE_REG_ADDR(gbe_dev, ss_regs, rgmii_status)); + *status = !!(val & RGMII_REG_STATUS_LINK); +} + static void netcp_ethss_update_link_state(struct gbe_priv *gbe_dev, struct gbe_slave *slave, struct net_device *ndev) { - int sp = slave->slave_num; - int phy_link_state, sgmii_link_state = 1, link_state; + bool sw_link_state = true, phy_link_state; + int sp = slave->slave_num, link_state; if (!slave->open) return; - if (!SLAVE_LINK_IS_XGMII(slave)) { - sgmii_link_state = - netcp_sgmii_get_port_link(SGMII_BASE(gbe_dev, sp), sp); - } + if (SLAVE_LINK_IS_RGMII(slave)) + netcp_2u_rgmii_get_port_link(gbe_dev, + &sw_link_state); + if (SLAVE_LINK_IS_SGMII(slave)) + sw_link_state = + netcp_sgmii_get_port_link(SGMII_BASE(gbe_dev, sp), sp); phy_link_state = gbe_phy_link_status(slave); - link_state = phy_link_state & sgmii_link_state; + link_state = phy_link_state & sw_link_state; if (atomic_xchg(&slave->link_state, link_state) != link_state) netcp_ethss_link_state_action(gbe_dev, ndev, slave, @@ -2205,7 +2233,7 @@ static void gbe_port_config(struct gbe_priv *gbe_dev, struct gbe_slave *slave, max_rx_len = NETCP_MAX_FRAME_SIZE; /* Enable correct MII mode at SS level */ - if ((gbe_dev->ss_version == XGBE_SS_VERSION_10) && + if (IS_SS_ID_XGBE(gbe_dev) && (slave->link_interface >= XGMII_LINK_MAC_PHY)) { xgmii_mode = readl(GBE_REG_ADDR(gbe_dev, ss_regs, control)); xgmii_mode |= (1 << slave->slave_num); @@ -2236,7 +2264,8 @@ static void gbe_slave_stop(struct gbe_intf *intf) struct gbe_priv *gbe_dev = intf->gbe_dev; struct gbe_slave *slave = intf->slave; - gbe_sgmii_rtreset(gbe_dev, slave, true); + if (!IS_SS_ID_2U(gbe_dev)) + gbe_sgmii_rtreset(gbe_dev, slave, true); gbe_port_reset(slave); /* Disable forwarding */ cpsw_ale_control_set(gbe_dev->ale, slave->port_num, @@ -2271,11 +2300,20 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) void (*hndlr)(struct net_device *) = gbe_adjust_link; - gbe_sgmii_config(priv, slave); + if (!IS_SS_ID_2U(priv)) + gbe_sgmii_config(priv, slave); gbe_port_reset(slave); - gbe_sgmii_rtreset(priv, slave, false); + if (!IS_SS_ID_2U(priv)) + gbe_sgmii_rtreset(priv, slave, false); gbe_port_config(priv, slave, priv->rx_packet_max); gbe_set_slave_mac(slave, gbe_intf); + /* For NU & 2U switch, map the vlan priorities to zero + * as we only configure to use priority 0 + */ + if (IS_SS_ID_MU(priv)) + writel(HOST_TX_PRI_MAP_DEFAULT, + GBE_REG_ADDR(slave, port_regs, rx_pri_map)); + /* enable forwarding */ cpsw_ale_control_set(priv->ale, slave->port_num, ALE_PORT_STATE, ALE_PORT_STATE_FORWARD); @@ -2286,6 +2324,21 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) has_phy = true; phy_mode = PHY_INTERFACE_MODE_SGMII; slave->phy_port_t = PORT_MII; + } else if (slave->link_interface == RGMII_LINK_MAC_PHY) { + has_phy = true; + phy_mode = of_get_phy_mode(slave->node); + /* if phy-mode is not present, default to + * PHY_INTERFACE_MODE_RGMII + */ + if (phy_mode < 0) + phy_mode = PHY_INTERFACE_MODE_RGMII; + + if (!phy_interface_mode_is_rgmii(phy_mode)) { + dev_err(priv->dev, + "Unsupported phy mode %d\n", phy_mode); + return -EINVAL; + } + slave->phy_port_t = PORT_MII; } else if (slave->link_interface == XGMII_LINK_MAC_PHY) { has_phy = true; phy_mode = PHY_INTERFACE_MODE_NA; @@ -2293,7 +2346,7 @@ static int gbe_slave_open(struct gbe_intf *gbe_intf) } if (has_phy) { - if (priv->ss_version == XGBE_SS_VERSION_10) + if (IS_SS_ID_XGBE(priv)) hndlr = xgbe_adjust_link; slave->phy = of_phy_connect(gbe_intf->ndev, @@ -2722,6 +2775,61 @@ static inline int gbe_hwtstamp_set(struct gbe_intf *gbe_intf, struct ifreq *req) } #endif /* CONFIG_TI_CPTS */ +static int gbe_set_rx_mode(void *intf_priv, bool promisc) +{ + struct gbe_intf *gbe_intf = intf_priv; + struct gbe_priv *gbe_dev = gbe_intf->gbe_dev; + struct cpsw_ale *ale = gbe_dev->ale; + unsigned long timeout; + int i, ret = -ETIMEDOUT; + + /* Disable(1)/Enable(0) Learn for all ports (host is port 0 and + * slaves are port 1 and up + */ + for (i = 0; i <= gbe_dev->num_slaves; i++) { + cpsw_ale_control_set(ale, i, + ALE_PORT_NOLEARN, !!promisc); + cpsw_ale_control_set(ale, i, + ALE_PORT_NO_SA_UPDATE, !!promisc); + } + + if (!promisc) { + /* Don't Flood All Unicast Packets to Host port */ + cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 0); + dev_vdbg(gbe_dev->dev, "promiscuous mode disabled\n"); + return 0; + } + + timeout = jiffies + HZ; + + /* Clear All Untouched entries */ + cpsw_ale_control_set(ale, 0, ALE_AGEOUT, 1); + do { + cpu_relax(); + if (cpsw_ale_control_get(ale, 0, ALE_AGEOUT)) { + ret = 0; + break; + } + + } while (time_after(timeout, jiffies)); + + /* Make sure it is not a false timeout */ + if (ret && !cpsw_ale_control_get(ale, 0, ALE_AGEOUT)) + return ret; + + cpsw_ale_control_set(ale, 0, ALE_AGEOUT, 1); + + /* Clear all mcast from ALE */ + cpsw_ale_flush_multicast(ale, + GBE_PORT_MASK(gbe_dev->ale_ports), + -1); + + /* Flood All Unicast Packets to Host port */ + cpsw_ale_control_set(ale, 0, ALE_P0_UNI_FLOOD, 1); + dev_vdbg(gbe_dev->dev, "promiscuous mode enabled\n"); + return ret; +} + static int gbe_ioctl(void *intf_priv, struct ifreq *req, int cmd) { struct gbe_intf *gbe_intf = intf_priv; @@ -2764,7 +2872,7 @@ static void netcp_ethss_timer(struct timer_list *t) /* A timer runs as a BH, no need to block them */ spin_lock(&gbe_dev->hw_stats_lock); - if (gbe_dev->ss_version == GBE_SS_VERSION_14) + if (IS_SS_ID_VER_14(gbe_dev)) gbe_update_stats_ver14(gbe_dev, NULL); else gbe_update_stats(gbe_dev, NULL); @@ -2807,7 +2915,7 @@ static int gbe_open(void *intf_priv, struct net_device *ndev) GBE_RTL_VERSION(reg), GBE_IDENT(reg)); /* For 10G and on NetCP 1.5, use directed to port */ - if ((gbe_dev->ss_version == XGBE_SS_VERSION_10) || IS_SS_ID_MU(gbe_dev)) + if (IS_SS_ID_XGBE(gbe_dev) || IS_SS_ID_MU(gbe_dev)) gbe_intf->tx_pipe.flags = SWITCH_TO_PORT_IN_TAGINFO; if (gbe_dev->enable_ale) @@ -2911,8 +3019,10 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, slave->link_interface = SGMII_LINK_MAC_PHY; } + slave->node = node; slave->open = false; if ((slave->link_interface == SGMII_LINK_MAC_PHY) || + (slave->link_interface == RGMII_LINK_MAC_PHY) || (slave->link_interface == XGMII_LINK_MAC_PHY)) slave->phy_node = of_parse_phandle(node, "phy-handle", 0); slave->port_num = gbe_get_slave_port(gbe_dev, slave->slave_num); @@ -2924,7 +3034,7 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, /* Emac regs memmap are contiguous but port regs are not */ port_reg_num = slave->slave_num; - if (gbe_dev->ss_version == GBE_SS_VERSION_14) { + if (IS_SS_ID_VER_14(gbe_dev)) { if (slave->slave_num > 1) { port_reg_ofs = GBE13_SLAVE_PORT2_OFFSET; port_reg_num -= 2; @@ -2939,7 +3049,7 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, emac_reg_ofs = GBENU_EMAC_OFFSET; port_reg_blk_sz = 0x1000; emac_reg_blk_sz = 0x1000; - } else if (gbe_dev->ss_version == XGBE_SS_VERSION_10) { + } else if (IS_SS_ID_XGBE(gbe_dev)) { port_reg_ofs = XGBE10_SLAVE_PORT_OFFSET; emac_reg_ofs = XGBE10_EMAC_OFFSET; port_reg_blk_sz = 0x30; @@ -2955,7 +3065,7 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, slave->emac_regs = gbe_dev->switch_regs + emac_reg_ofs + (emac_reg_blk_sz * slave->slave_num); - if (gbe_dev->ss_version == GBE_SS_VERSION_14) { + if (IS_SS_ID_VER_14(gbe_dev)) { /* Initialize slave port register offsets */ GBE_SET_REG_OFS(slave, port_regs, port_vlan); GBE_SET_REG_OFS(slave, port_regs, tx_pri_map); @@ -2976,6 +3086,7 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, /* Initialize slave port register offsets */ GBENU_SET_REG_OFS(slave, port_regs, port_vlan); GBENU_SET_REG_OFS(slave, port_regs, tx_pri_map); + GBENU_SET_REG_OFS(slave, port_regs, rx_pri_map); GBENU_SET_REG_OFS(slave, port_regs, sa_lo); GBENU_SET_REG_OFS(slave, port_regs, sa_hi); GBENU_SET_REG_OFS(slave, port_regs, ts_ctl); @@ -2989,7 +3100,7 @@ static int init_slave(struct gbe_priv *gbe_dev, struct gbe_slave *slave, GBENU_SET_REG_OFS(slave, emac_regs, mac_control); GBENU_SET_REG_OFS(slave, emac_regs, soft_reset); - } else if (gbe_dev->ss_version == XGBE_SS_VERSION_10) { + } else if (IS_SS_ID_XGBE(gbe_dev)) { /* Initialize slave port register offsets */ XGBE_SET_REG_OFS(slave, port_regs, port_vlan); XGBE_SET_REG_OFS(slave, port_regs, tx_pri_map); @@ -3039,7 +3150,8 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev, continue; } - gbe_sgmii_config(gbe_dev, slave); + if (!IS_SS_ID_2U(gbe_dev)) + gbe_sgmii_config(gbe_dev, slave); gbe_port_reset(slave); gbe_port_config(gbe_dev, slave, gbe_dev->rx_packet_max); list_add_tail(&slave->slave_list, &gbe_dev->secondary_slaves); @@ -3073,6 +3185,9 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev, if (slave->link_interface == SGMII_LINK_MAC_PHY) { phy_mode = PHY_INTERFACE_MODE_SGMII; slave->phy_port_t = PORT_MII; + } else if (slave->link_interface == RGMII_LINK_MAC_PHY) { + phy_mode = PHY_INTERFACE_MODE_RGMII; + slave->phy_port_t = PORT_MII; } else { phy_mode = PHY_INTERFACE_MODE_NA; slave->phy_port_t = PORT_FIBRE; @@ -3080,6 +3195,7 @@ static void init_secondary_ports(struct gbe_priv *gbe_dev, for_each_sec_slave(slave, gbe_dev) { if ((slave->link_interface != SGMII_LINK_MAC_PHY) && + (slave->link_interface != RGMII_LINK_MAC_PHY) && (slave->link_interface != XGMII_LINK_MAC_PHY)) continue; slave->phy = @@ -3355,7 +3471,7 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev, gbe_dev->num_stats_mods = gbe_dev->max_num_ports; gbe_dev->et_stats = gbenu_et_stats; - if (IS_SS_ID_NU(gbe_dev)) + if (IS_SS_ID_MU(gbe_dev)) gbe_dev->num_et_stats = GBENU_ET_STATS_HOST_SIZE + (gbe_dev->max_num_slaves * GBENU_ET_STATS_PORT_SIZE); else @@ -3396,7 +3512,9 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev, } gbe_dev->switch_regs = regs; - gbe_dev->sgmii_port_regs = gbe_dev->ss_regs + GBENU_SGMII_MODULE_OFFSET; + if (!IS_SS_ID_2U(gbe_dev)) + gbe_dev->sgmii_port_regs = + gbe_dev->ss_regs + GBENU_SGMII_MODULE_OFFSET; /* Although sgmii modules are mem mapped to one contiguous * region on GBENU devices, setting sgmii_port34_regs allows @@ -3419,6 +3537,8 @@ static int set_gbenu_ethss_priv(struct gbe_priv *gbe_dev, /* Subsystem registers */ GBENU_SET_REG_OFS(gbe_dev, ss_regs, id_ver); + /* ok to set for MU, but used by 2U only */ + GBENU_SET_REG_OFS(gbe_dev, ss_regs, rgmii_status); /* Switch module registers */ GBENU_SET_REG_OFS(gbe_dev, switch_regs, id_ver); @@ -3464,6 +3584,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, gbe_dev->max_num_slaves = 8; } else if (of_device_is_compatible(node, "ti,netcp-gbe-2")) { gbe_dev->max_num_slaves = 1; + gbe_module.set_rx_mode = gbe_set_rx_mode; } else if (of_device_is_compatible(node, "ti,netcp-xgbe")) { gbe_dev->max_num_slaves = 2; } else { @@ -3508,7 +3629,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, dev_dbg(dev, "ss_version: 0x%08x\n", gbe_dev->ss_version); - if (gbe_dev->ss_version == GBE_SS_VERSION_14) + if (IS_SS_ID_VER_14(gbe_dev)) ret = set_gbe_ethss14_priv(gbe_dev, node); else if (IS_SS_ID_MU(gbe_dev)) ret = set_gbenu_ethss_priv(gbe_dev, node); @@ -3606,7 +3727,7 @@ static int gbe_probe(struct netcp_device *netcp_device, struct device *dev, spin_lock_bh(&gbe_dev->hw_stats_lock); for (i = 0; i < gbe_dev->num_stats_mods; i++) { - if (gbe_dev->ss_version == GBE_SS_VERSION_14) + if (IS_SS_ID_VER_14(gbe_dev)) gbe_reset_mod_stats_ver14(gbe_dev, i); else gbe_reset_mod_stats(gbe_dev, i); diff --git a/drivers/net/geneve.c b/drivers/net/geneve.c index b919e89a9b93..750eaa53bf0c 100644 --- a/drivers/net/geneve.c +++ b/drivers/net/geneve.c @@ -36,6 +36,8 @@ MODULE_PARM_DESC(log_ecn_error, "Log packets received with corrupted ECN"); #define GENEVE_VER 0 #define GENEVE_BASE_HLEN (sizeof(struct udphdr) + sizeof(struct genevehdr)) +#define GENEVE_IPV4_HLEN (ETH_HLEN + sizeof(struct iphdr) + GENEVE_BASE_HLEN) +#define GENEVE_IPV6_HLEN (ETH_HLEN + sizeof(struct ipv6hdr) + GENEVE_BASE_HLEN) /* per-network namespace private data for this module */ struct geneve_net { @@ -826,8 +828,8 @@ static int geneve_xmit_skb(struct sk_buff *skb, struct net_device *dev, return PTR_ERR(rt); if (skb_dst(skb)) { - int mtu = dst_mtu(&rt->dst) - sizeof(struct iphdr) - - GENEVE_BASE_HLEN - info->options_len - 14; + int mtu = dst_mtu(&rt->dst) - GENEVE_IPV4_HLEN - + info->options_len; skb_dst_update_pmtu(skb, mtu); } @@ -872,8 +874,7 @@ static int geneve6_xmit_skb(struct sk_buff *skb, struct net_device *dev, return PTR_ERR(dst); if (skb_dst(skb)) { - int mtu = dst_mtu(dst) - sizeof(struct ipv6hdr) - - GENEVE_BASE_HLEN - info->options_len - 14; + int mtu = dst_mtu(dst) - GENEVE_IPV6_HLEN - info->options_len; skb_dst_update_pmtu(skb, mtu); } @@ -941,11 +942,10 @@ tx_error: static int geneve_change_mtu(struct net_device *dev, int new_mtu) { - /* Only possible if called internally, ndo_change_mtu path's new_mtu - * is guaranteed to be between dev->min_mtu and dev->max_mtu. - */ if (new_mtu > dev->max_mtu) new_mtu = dev->max_mtu; + else if (new_mtu < dev->min_mtu) + new_mtu = dev->min_mtu; dev->mtu = new_mtu; return 0; @@ -1261,7 +1261,7 @@ static int geneve_nl2info(struct nlattr *tb[], struct nlattr *data[], } if (data[IFLA_GENEVE_REMOTE6]) { - #if IS_ENABLED(CONFIG_IPV6) +#if IS_ENABLED(CONFIG_IPV6) if (changelink && (ip_tunnel_info_af(info) == AF_INET)) { attrtype = IFLA_GENEVE_REMOTE6; goto change_notsup; @@ -1387,6 +1387,48 @@ change_notsup: return -EOPNOTSUPP; } +static void geneve_link_config(struct net_device *dev, + struct ip_tunnel_info *info, struct nlattr *tb[]) +{ + struct geneve_dev *geneve = netdev_priv(dev); + int ldev_mtu = 0; + + if (tb[IFLA_MTU]) { + geneve_change_mtu(dev, nla_get_u32(tb[IFLA_MTU])); + return; + } + + switch (ip_tunnel_info_af(info)) { + case AF_INET: { + struct flowi4 fl4 = { .daddr = info->key.u.ipv4.dst }; + struct rtable *rt = ip_route_output_key(geneve->net, &fl4); + + if (!IS_ERR(rt) && rt->dst.dev) { + ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV4_HLEN; + ip_rt_put(rt); + } + break; + } +#if IS_ENABLED(CONFIG_IPV6) + case AF_INET6: { + struct rt6_info *rt = rt6_lookup(geneve->net, + &info->key.u.ipv6.dst, NULL, 0, + NULL, 0); + + if (rt && rt->dst.dev) + ldev_mtu = rt->dst.dev->mtu - GENEVE_IPV6_HLEN; + ip6_rt_put(rt); + break; + } +#endif + } + + if (ldev_mtu <= 0) + return; + + geneve_change_mtu(dev, ldev_mtu - info->options_len); +} + static int geneve_newlink(struct net *net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack) @@ -1402,8 +1444,14 @@ static int geneve_newlink(struct net *net, struct net_device *dev, if (err) return err; - return geneve_configure(net, dev, extack, &info, metadata, - use_udp6_rx_checksums); + err = geneve_configure(net, dev, extack, &info, metadata, + use_udp6_rx_checksums); + if (err) + return err; + + geneve_link_config(dev, &info, tb); + + return 0; } /* Quiesces the geneve device data path for both TX and RX. @@ -1477,8 +1525,10 @@ static int geneve_changelink(struct net_device *dev, struct nlattr *tb[], if (err) return err; - if (!geneve_dst_addr_equal(&geneve->info, &info)) + if (!geneve_dst_addr_equal(&geneve->info, &info)) { dst_cache_reset(&info.dst_cache); + geneve_link_config(dev, &info, tb); + } geneve_quiesce(geneve, &gs4, &gs6); geneve->info = info; diff --git a/drivers/net/hamradio/mkiss.c b/drivers/net/hamradio/mkiss.c index c180b480f8ef..13e4c1eff353 100644 --- a/drivers/net/hamradio/mkiss.c +++ b/drivers/net/hamradio/mkiss.c @@ -217,7 +217,7 @@ static int kiss_esc_crc(unsigned char *s, unsigned char *d, unsigned short crc, c = *s++; else if (len > 1) c = crc >> 8; - else if (len > 0) + else c = crc & 0xff; len--; diff --git a/drivers/net/hyperv/Kconfig b/drivers/net/hyperv/Kconfig index 936968d23559..0765d5f61714 100644 --- a/drivers/net/hyperv/Kconfig +++ b/drivers/net/hyperv/Kconfig @@ -1,5 +1,6 @@ config HYPERV_NET tristate "Microsoft Hyper-V virtual network driver" depends on HYPERV + select UCS2_STRING help Select this option to enable the Hyper-V virtual network driver. diff --git a/drivers/net/hyperv/hyperv_net.h b/drivers/net/hyperv/hyperv_net.h index 960f06141472..1be34d2e3563 100644 --- a/drivers/net/hyperv/hyperv_net.h +++ b/drivers/net/hyperv/hyperv_net.h @@ -110,7 +110,7 @@ struct ndis_recv_scale_param { /* NDIS_RECEIVE_SCALE_PARAMETERS */ u16 hashkey_size; /* The offset of the secret key from the beginning of this structure */ - u32 kashkey_offset; + u32 hashkey_offset; u32 processor_masks_offset; u32 num_processor_masks; @@ -237,6 +237,8 @@ void netvsc_switch_datapath(struct net_device *nv_dev, bool vf); #define NVSP_PROTOCOL_VERSION_2 0x30002 #define NVSP_PROTOCOL_VERSION_4 0x40000 #define NVSP_PROTOCOL_VERSION_5 0x50000 +#define NVSP_PROTOCOL_VERSION_6 0x60000 +#define NVSP_PROTOCOL_VERSION_61 0x60001 enum { NVSP_MSG_TYPE_NONE = 0, @@ -308,6 +310,12 @@ enum { NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE, NVSP_MSG5_MAX = NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE, + + /* Version 6 messages */ + NVSP_MSG6_TYPE_PD_API, + NVSP_MSG6_TYPE_PD_POST_BATCH, + + NVSP_MSG6_MAX = NVSP_MSG6_TYPE_PD_POST_BATCH }; enum { @@ -619,12 +627,168 @@ union nvsp_5_message_uber { struct nvsp_5_send_indirect_table send_table; } __packed; +enum nvsp_6_pd_api_op { + PD_API_OP_CONFIG = 1, + PD_API_OP_SW_DATAPATH, /* Switch Datapath */ + PD_API_OP_OPEN_PROVIDER, + PD_API_OP_CLOSE_PROVIDER, + PD_API_OP_CREATE_QUEUE, + PD_API_OP_FLUSH_QUEUE, + PD_API_OP_FREE_QUEUE, + PD_API_OP_ALLOC_COM_BUF, /* Allocate Common Buffer */ + PD_API_OP_FREE_COM_BUF, /* Free Common Buffer */ + PD_API_OP_MAX +}; + +struct grp_affinity { + u64 mask; + u16 grp; + u16 reserved[3]; +} __packed; + +struct nvsp_6_pd_api_req { + u32 op; + + union { + /* MMIO information is sent from the VM to VSP */ + struct __packed { + u64 mmio_pa; /* MMIO Physical Address */ + u32 mmio_len; + + /* Number of PD queues a VM can support */ + u16 num_subchn; + } config; + + /* Switch Datapath */ + struct __packed { + /* Host Datapath Is PacketDirect */ + u8 host_dpath_is_pd; + + /* Guest PacketDirect Is Enabled */ + u8 guest_pd_enabled; + } sw_dpath; + + /* Open Provider*/ + struct __packed { + u32 prov_id; /* Provider id */ + u32 flag; + } open_prov; + + /* Close Provider */ + struct __packed { + u32 prov_id; + } cls_prov; + + /* Create Queue*/ + struct __packed { + u32 prov_id; + u16 q_id; + u16 q_size; + u8 is_recv_q; + u8 is_rss_q; + u32 recv_data_len; + struct grp_affinity affy; + } cr_q; + + /* Delete Queue*/ + struct __packed { + u32 prov_id; + u16 q_id; + } del_q; + + /* Flush Queue */ + struct __packed { + u32 prov_id; + u16 q_id; + } flush_q; + + /* Allocate Common Buffer */ + struct __packed { + u32 len; + u32 pf_node; /* Preferred Node */ + u16 region_id; + } alloc_com_buf; + + /* Free Common Buffer */ + struct __packed { + u32 len; + u64 pa; /* Physical Address */ + u32 pf_node; /* Preferred Node */ + u16 region_id; + u8 cache_type; + } free_com_buf; + } __packed; +} __packed; + +struct nvsp_6_pd_api_comp { + u32 op; + u32 status; + + union { + struct __packed { + /* actual number of PD queues allocated to the VM */ + u16 num_pd_q; + + /* Num Receive Rss PD Queues */ + u8 num_rss_q; + + u8 is_supported; /* Is supported by VSP */ + u8 is_enabled; /* Is enabled by VSP */ + } config; + + /* Open Provider */ + struct __packed { + u32 prov_id; + } open_prov; + + /* Create Queue */ + struct __packed { + u32 prov_id; + u16 q_id; + u16 q_size; + u32 recv_data_len; + struct grp_affinity affy; + } cr_q; + + /* Allocate Common Buffer */ + struct __packed { + u64 pa; /* Physical Address */ + u32 len; + u32 pf_node; /* Preferred Node */ + u16 region_id; + u8 cache_type; + } alloc_com_buf; + } __packed; +} __packed; + +struct nvsp_6_pd_buf { + u32 region_offset; + u16 region_id; + u16 is_partial:1; + u16 reserved:15; +} __packed; + +struct nvsp_6_pd_batch_msg { + struct nvsp_message_header hdr; + u16 count; + u16 guest2host:1; + u16 is_recv:1; + u16 reserved:14; + struct nvsp_6_pd_buf pd_buf[0]; +} __packed; + +union nvsp_6_message_uber { + struct nvsp_6_pd_api_req pd_req; + struct nvsp_6_pd_api_comp pd_comp; +} __packed; + union nvsp_all_messages { union nvsp_message_init_uber init_msg; union nvsp_1_message_uber v1_msg; union nvsp_2_message_uber v2_msg; union nvsp_4_message_uber v4_msg; union nvsp_5_message_uber v5_msg; + union nvsp_6_message_uber v6_msg; } __packed; /* ALL Messages */ diff --git a/drivers/net/hyperv/netvsc.c b/drivers/net/hyperv/netvsc.c index 04f611e6f678..d2ee66c259a7 100644 --- a/drivers/net/hyperv/netvsc.c +++ b/drivers/net/hyperv/netvsc.c @@ -525,7 +525,8 @@ static int netvsc_connect_vsp(struct hv_device *device, struct net_device *ndev = hv_get_drvdata(device); static const u32 ver_list[] = { NVSP_PROTOCOL_VERSION_1, NVSP_PROTOCOL_VERSION_2, - NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5 + NVSP_PROTOCOL_VERSION_4, NVSP_PROTOCOL_VERSION_5, + NVSP_PROTOCOL_VERSION_6, NVSP_PROTOCOL_VERSION_61 }; struct nvsp_message *init_packet; int ndis_version, i, ret; @@ -651,16 +652,14 @@ static inline void netvsc_free_send_slot(struct netvsc_device *net_device, sync_change_bit(index, net_device->send_section_map); } -static void netvsc_send_tx_complete(struct netvsc_device *net_device, - struct vmbus_channel *incoming_channel, - struct hv_device *device, +static void netvsc_send_tx_complete(struct net_device *ndev, + struct netvsc_device *net_device, + struct vmbus_channel *channel, const struct vmpacket_descriptor *desc, int budget) { struct sk_buff *skb = (struct sk_buff *)(unsigned long)desc->trans_id; - struct net_device *ndev = hv_get_drvdata(device); struct net_device_context *ndev_ctx = netdev_priv(ndev); - struct vmbus_channel *channel = device->channel; u16 q_idx = 0; int queue_sends; @@ -674,7 +673,6 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device, if (send_index != NETVSC_INVALID_INDEX) netvsc_free_send_slot(net_device, send_index); q_idx = packet->q_idx; - channel = incoming_channel; tx_stats = &net_device->chan_table[q_idx].tx_stats; @@ -704,14 +702,13 @@ static void netvsc_send_tx_complete(struct netvsc_device *net_device, } } -static void netvsc_send_completion(struct netvsc_device *net_device, +static void netvsc_send_completion(struct net_device *ndev, + struct netvsc_device *net_device, struct vmbus_channel *incoming_channel, - struct hv_device *device, const struct vmpacket_descriptor *desc, int budget) { - struct nvsp_message *nvsp_packet = hv_pkt_data(desc); - struct net_device *ndev = hv_get_drvdata(device); + const struct nvsp_message *nvsp_packet = hv_pkt_data(desc); switch (nvsp_packet->hdr.msg_type) { case NVSP_MSG_TYPE_INIT_COMPLETE: @@ -725,8 +722,8 @@ static void netvsc_send_completion(struct netvsc_device *net_device, break; case NVSP_MSG1_TYPE_SEND_RNDIS_PKT_COMPLETE: - netvsc_send_tx_complete(net_device, incoming_channel, - device, desc, budget); + netvsc_send_tx_complete(ndev, net_device, incoming_channel, + desc, budget); break; default: @@ -1091,12 +1088,11 @@ static void enq_receive_complete(struct net_device *ndev, static int netvsc_receive(struct net_device *ndev, struct netvsc_device *net_device, - struct net_device_context *net_device_ctx, - struct hv_device *device, struct vmbus_channel *channel, const struct vmpacket_descriptor *desc, - struct nvsp_message *nvsp) + const struct nvsp_message *nvsp) { + struct net_device_context *net_device_ctx = netdev_priv(ndev); const struct vmtransfer_page_packet_header *vmxferpage_packet = container_of(desc, const struct vmtransfer_page_packet_header, d); u16 q_idx = channel->offermsg.offer.sub_channel_index; @@ -1157,13 +1153,12 @@ static int netvsc_receive(struct net_device *ndev, return count; } -static void netvsc_send_table(struct hv_device *hdev, - struct nvsp_message *nvmsg) +static void netvsc_send_table(struct net_device *ndev, + const struct nvsp_message *nvmsg) { - struct net_device *ndev = hv_get_drvdata(hdev); struct net_device_context *net_device_ctx = netdev_priv(ndev); - int i; u32 count, *tab; + int i; count = nvmsg->msg.v5_msg.send_table.count; if (count != VRSS_SEND_TAB_SIZE) { @@ -1178,24 +1173,25 @@ static void netvsc_send_table(struct hv_device *hdev, net_device_ctx->tx_table[i] = tab[i]; } -static void netvsc_send_vf(struct net_device_context *net_device_ctx, - struct nvsp_message *nvmsg) +static void netvsc_send_vf(struct net_device *ndev, + const struct nvsp_message *nvmsg) { + struct net_device_context *net_device_ctx = netdev_priv(ndev); + net_device_ctx->vf_alloc = nvmsg->msg.v4_msg.vf_assoc.allocated; net_device_ctx->vf_serial = nvmsg->msg.v4_msg.vf_assoc.serial; } -static inline void netvsc_receive_inband(struct hv_device *hdev, - struct net_device_context *net_device_ctx, - struct nvsp_message *nvmsg) +static void netvsc_receive_inband(struct net_device *ndev, + const struct nvsp_message *nvmsg) { switch (nvmsg->hdr.msg_type) { case NVSP_MSG5_TYPE_SEND_INDIRECTION_TABLE: - netvsc_send_table(hdev, nvmsg); + netvsc_send_table(ndev, nvmsg); break; case NVSP_MSG4_TYPE_SEND_VF_ASSOCIATION: - netvsc_send_vf(net_device_ctx, nvmsg); + netvsc_send_vf(ndev, nvmsg); break; } } @@ -1207,24 +1203,23 @@ static int netvsc_process_raw_pkt(struct hv_device *device, const struct vmpacket_descriptor *desc, int budget) { - struct net_device_context *net_device_ctx = netdev_priv(ndev); - struct nvsp_message *nvmsg = hv_pkt_data(desc); + const struct nvsp_message *nvmsg = hv_pkt_data(desc); trace_nvsp_recv(ndev, channel, nvmsg); switch (desc->type) { case VM_PKT_COMP: - netvsc_send_completion(net_device, channel, device, + netvsc_send_completion(ndev, net_device, channel, desc, budget); break; case VM_PKT_DATA_USING_XFER_PAGES: - return netvsc_receive(ndev, net_device, net_device_ctx, - device, channel, desc, nvmsg); + return netvsc_receive(ndev, net_device, channel, + desc, nvmsg); break; case VM_PKT_DATA_INBAND: - netvsc_receive_inband(device, net_device_ctx, nvmsg); + netvsc_receive_inband(ndev, nvmsg); break; default: diff --git a/drivers/net/hyperv/rndis_filter.c b/drivers/net/hyperv/rndis_filter.c index e7ca5b5f39ed..7f3dab4b4cbc 100644 --- a/drivers/net/hyperv/rndis_filter.c +++ b/drivers/net/hyperv/rndis_filter.c @@ -29,6 +29,7 @@ #include <linux/nls.h> #include <linux/vmalloc.h> #include <linux/rtnetlink.h> +#include <linux/ucs2_string.h> #include "hyperv_net.h" #include "netvsc_trace.h" @@ -751,7 +752,7 @@ int rndis_filter_set_rss_param(struct rndis_device *rdev, rssp->indirect_tabsize = 4*ITAB_NUM; rssp->indirect_taboffset = sizeof(struct ndis_recv_scale_param); rssp->hashkey_size = NETVSC_HASH_KEYLEN; - rssp->kashkey_offset = rssp->indirect_taboffset + + rssp->hashkey_offset = rssp->indirect_taboffset + rssp->indirect_tabsize; /* Set indirection table entries */ @@ -760,7 +761,7 @@ int rndis_filter_set_rss_param(struct rndis_device *rdev, itab[i] = rdev->rx_table[i]; /* Set hask key values */ - keyp = (u8 *)((unsigned long)rssp + rssp->kashkey_offset); + keyp = (u8 *)((unsigned long)rssp + rssp->hashkey_offset); memcpy(keyp, rss_key, NETVSC_HASH_KEYLEN); ret = rndis_filter_send_request(rdev, request); @@ -1223,6 +1224,29 @@ static int rndis_netdev_set_hwcaps(struct rndis_device *rndis_device, return ret; } +static void rndis_get_friendly_name(struct net_device *net, + struct rndis_device *rndis_device, + struct netvsc_device *net_device) +{ + ucs2_char_t wname[256]; + unsigned long len; + u8 ifalias[256]; + u32 size; + + size = sizeof(wname); + if (rndis_filter_query_device(rndis_device, net_device, + RNDIS_OID_GEN_FRIENDLY_NAME, + wname, &size) != 0) + return; + + /* Convert Windows Unicode string to UTF-8 */ + len = ucs2_as_utf8(ifalias, wname, sizeof(ifalias)); + + /* ignore the default value from host */ + if (strcmp(ifalias, "Network Adapter") != 0) + dev_set_alias(net, ifalias, len); +} + struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, struct netvsc_device_info *device_info) { @@ -1276,6 +1300,10 @@ struct netvsc_device *rndis_filter_device_add(struct hv_device *dev, memcpy(device_info->mac_adr, rndis_device->hw_mac_adr, ETH_ALEN); + /* Get friendly name as ifalias*/ + if (!net->ifalias) + rndis_get_friendly_name(net, rndis_device, net_device); + /* Query and set hardware capabilities */ ret = rndis_netdev_set_hwcaps(rndis_device, net_device); if (ret != 0) diff --git a/drivers/net/macvlan.c b/drivers/net/macvlan.c index 725f4b4afc6d..adde8fc45588 100644 --- a/drivers/net/macvlan.c +++ b/drivers/net/macvlan.c @@ -514,6 +514,7 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) const struct macvlan_dev *vlan = netdev_priv(dev); const struct macvlan_port *port = vlan->port; const struct macvlan_dev *dest; + void *accel_priv = NULL; if (vlan->mode == MACVLAN_MODE_BRIDGE) { const struct ethhdr *eth = (void *)skb->data; @@ -533,9 +534,14 @@ static int macvlan_queue_xmit(struct sk_buff *skb, struct net_device *dev) } } + /* For packets that are non-multicast and not bridged we will pass + * the necessary information so that the lowerdev can distinguish + * the source of the packets via the accel_priv value. + */ + accel_priv = vlan->accel_priv; xmit_world: skb->dev = vlan->lowerdev; - return dev_queue_xmit(skb); + return dev_queue_xmit_accel(skb, accel_priv); } static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, struct sk_buff *skb) @@ -552,19 +558,14 @@ static inline netdev_tx_t macvlan_netpoll_send_skb(struct macvlan_dev *vlan, str static netdev_tx_t macvlan_start_xmit(struct sk_buff *skb, struct net_device *dev) { + struct macvlan_dev *vlan = netdev_priv(dev); unsigned int len = skb->len; int ret; - struct macvlan_dev *vlan = netdev_priv(dev); if (unlikely(netpoll_tx_running(dev))) return macvlan_netpoll_send_skb(vlan, skb); - if (vlan->fwd_priv) { - skb->dev = vlan->lowerdev; - ret = dev_queue_xmit_accel(skb, vlan->fwd_priv); - } else { - ret = macvlan_queue_xmit(skb, dev); - } + ret = macvlan_queue_xmit(skb, dev); if (likely(ret == NET_XMIT_SUCCESS || ret == NET_XMIT_CN)) { struct vlan_pcpu_stats *pcpu_stats; @@ -613,26 +614,27 @@ static int macvlan_open(struct net_device *dev) goto hash_add; } - if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) { - vlan->fwd_priv = - lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); - - /* If we get a NULL pointer back, or if we get an error - * then we should just fall through to the non accelerated path - */ - if (IS_ERR_OR_NULL(vlan->fwd_priv)) { - vlan->fwd_priv = NULL; - } else - return 0; - } - err = -EBUSY; if (macvlan_addr_busy(vlan->port, dev->dev_addr)) goto out; - err = dev_uc_add(lowerdev, dev->dev_addr); - if (err < 0) - goto out; + /* Attempt to populate accel_priv which is used to offload the L2 + * forwarding requests for unicast packets. + */ + if (lowerdev->features & NETIF_F_HW_L2FW_DOFFLOAD) + vlan->accel_priv = + lowerdev->netdev_ops->ndo_dfwd_add_station(lowerdev, dev); + + /* If earlier attempt to offload failed, or accel_priv is not + * populated we must add the unicast address to the lower device. + */ + if (IS_ERR_OR_NULL(vlan->accel_priv)) { + vlan->accel_priv = NULL; + err = dev_uc_add(lowerdev, dev->dev_addr); + if (err < 0) + goto out; + } + if (dev->flags & IFF_ALLMULTI) { err = dev_set_allmulti(lowerdev, 1); if (err < 0) @@ -653,13 +655,14 @@ clear_multi: if (dev->flags & IFF_ALLMULTI) dev_set_allmulti(lowerdev, -1); del_unicast: - dev_uc_del(lowerdev, dev->dev_addr); -out: - if (vlan->fwd_priv) { + if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, - vlan->fwd_priv); - vlan->fwd_priv = NULL; + vlan->accel_priv); + vlan->accel_priv = NULL; + } else { + dev_uc_del(lowerdev, dev->dev_addr); } +out: return err; } @@ -668,11 +671,10 @@ static int macvlan_stop(struct net_device *dev) struct macvlan_dev *vlan = netdev_priv(dev); struct net_device *lowerdev = vlan->lowerdev; - if (vlan->fwd_priv) { + if (vlan->accel_priv) { lowerdev->netdev_ops->ndo_dfwd_del_station(lowerdev, - vlan->fwd_priv); - vlan->fwd_priv = NULL; - return 0; + vlan->accel_priv); + vlan->accel_priv = NULL; } dev_uc_unsync(lowerdev, dev); diff --git a/drivers/net/phy/Kconfig b/drivers/net/phy/Kconfig index bdfbabb86ee0..19a5778a7ec7 100644 --- a/drivers/net/phy/Kconfig +++ b/drivers/net/phy/Kconfig @@ -218,6 +218,12 @@ config AQUANTIA_PHY ---help--- Currently supports the Aquantia AQ1202, AQ2104, AQR105, AQR405 +config ASIX_PHY + tristate "Asix PHYs" + help + Currently supports the Asix Electronics PHY found in the X-Surf 100 + AX88796B package. + config AT803X_PHY tristate "AT803X PHYs" ---help--- @@ -285,6 +291,11 @@ config DP83822_PHY ---help--- Supports the DP83822 PHY. +config DP83TC811_PHY + tristate "Texas Instruments DP83TC822 PHY" + ---help--- + Supports the DP83TC822 PHY. + config DP83848_PHY tristate "Texas Instruments DP83848 PHY" ---help--- @@ -354,6 +365,11 @@ config MICROCHIP_PHY help Supports the LAN88XX PHYs. +config MICROCHIP_T1_PHY + tristate "Microchip T1 PHYs" + ---help--- + Supports the LAN87XX PHYs. + config MICROSEMI_PHY tristate "Microsemi PHYs" ---help--- diff --git a/drivers/net/phy/Makefile b/drivers/net/phy/Makefile index 01acbcb2c798..738246960e3b 100644 --- a/drivers/net/phy/Makefile +++ b/drivers/net/phy/Makefile @@ -45,6 +45,7 @@ obj-y += $(sfp-obj-y) $(sfp-obj-m) obj-$(CONFIG_AMD_PHY) += amd.o obj-$(CONFIG_AQUANTIA_PHY) += aquantia.o +obj-$(CONFIG_ASIX_PHY) += asix.o obj-$(CONFIG_AT803X_PHY) += at803x.o obj-$(CONFIG_BCM63XX_PHY) += bcm63xx.o obj-$(CONFIG_BCM7XXX_PHY) += bcm7xxx.o @@ -57,6 +58,7 @@ obj-$(CONFIG_CORTINA_PHY) += cortina.o obj-$(CONFIG_DAVICOM_PHY) += davicom.o obj-$(CONFIG_DP83640_PHY) += dp83640.o obj-$(CONFIG_DP83822_PHY) += dp83822.o +obj-$(CONFIG_DP83TC811_PHY) += dp83tc811.o obj-$(CONFIG_DP83848_PHY) += dp83848.o obj-$(CONFIG_DP83867_PHY) += dp83867.o obj-$(CONFIG_FIXED_PHY) += fixed_phy.o @@ -70,6 +72,7 @@ obj-$(CONFIG_MESON_GXL_PHY) += meson-gxl.o obj-$(CONFIG_MICREL_KS8995MA) += spi_ks8995.o obj-$(CONFIG_MICREL_PHY) += micrel.o obj-$(CONFIG_MICROCHIP_PHY) += microchip.o +obj-$(CONFIG_MICROCHIP_T1_PHY) += microchip_t1.o obj-$(CONFIG_MICROSEMI_PHY) += mscc.o obj-$(CONFIG_NATIONAL_PHY) += national.o obj-$(CONFIG_QSEMI_PHY) += qsemi.o diff --git a/drivers/net/phy/asix.c b/drivers/net/phy/asix.c new file mode 100644 index 000000000000..8ebe7f5484ae --- /dev/null +++ b/drivers/net/phy/asix.c @@ -0,0 +1,63 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Driver for Asix PHYs + * + * Author: Michael Schmitz <schmitzmic@gmail.com> + * + * This program is free software; you can redistribute it and/or modify it + * under the terms of the GNU General Public License as published by the + * Free Software Foundation; either version 2 of the License, or (at your + * option) any later version. + * + */ +#include <linux/kernel.h> +#include <linux/errno.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/mii.h> +#include <linux/phy.h> + +#define PHY_ID_ASIX_AX88796B 0x003b1841 + +MODULE_DESCRIPTION("Asix PHY driver"); +MODULE_AUTHOR("Michael Schmitz <schmitzmic@gmail.com>"); +MODULE_LICENSE("GPL"); + +/** + * asix_soft_reset - software reset the PHY via BMCR_RESET bit + * @phydev: target phy_device struct + * + * Description: Perform a software PHY reset using the standard + * BMCR_RESET bit and poll for the reset bit to be cleared. + * Toggle BMCR_RESET bit off to accommodate broken AX8796B PHY implementation + * such as used on the Individual Computers' X-Surf 100 Zorro card. + * + * Returns: 0 on success, < 0 on failure + */ +static int asix_soft_reset(struct phy_device *phydev) +{ + int ret; + + /* Asix PHY won't reset unless reset bit toggles */ + ret = phy_write(phydev, MII_BMCR, 0); + if (ret < 0) + return ret; + + return genphy_soft_reset(phydev); +} + +static struct phy_driver asix_driver[] = { { + .phy_id = PHY_ID_ASIX_AX88796B, + .name = "Asix Electronics AX88796B", + .phy_id_mask = 0xfffffff0, + .features = PHY_BASIC_FEATURES, + .soft_reset = asix_soft_reset, +} }; + +module_phy_driver(asix_driver); + +static struct mdio_device_id __maybe_unused asix_tbl[] = { + { PHY_ID_ASIX_AX88796B, 0xfffffff0 }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, asix_tbl); diff --git a/drivers/net/phy/bcm-phy-lib.c b/drivers/net/phy/bcm-phy-lib.c index 5ad130c3da43..0876aec7328c 100644 --- a/drivers/net/phy/bcm-phy-lib.c +++ b/drivers/net/phy/bcm-phy-lib.c @@ -346,10 +346,6 @@ void bcm_phy_get_strings(struct phy_device *phydev, u8 *data) } EXPORT_SYMBOL_GPL(bcm_phy_get_strings); -#ifndef UINT64_MAX -#define UINT64_MAX (u64)(~((u64)0)) -#endif - /* Caller is supposed to provide appropriate storage for the library code to * access the shadow copy */ @@ -362,7 +358,7 @@ static u64 bcm_phy_get_stat(struct phy_device *phydev, u64 *shadow, val = phy_read(phydev, stat.reg); if (val < 0) { - ret = UINT64_MAX; + ret = U64_MAX; } else { val >>= stat.shift; val = val & ((1 << stat.bits) - 1); diff --git a/drivers/net/phy/dp83tc811.c b/drivers/net/phy/dp83tc811.c new file mode 100644 index 000000000000..081d99aa3985 --- /dev/null +++ b/drivers/net/phy/dp83tc811.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Driver for the Texas Instruments DP83TC811 PHY + * + * Copyright (C) 2018 Texas Instruments Incorporated - http://www.ti.com/ + * + */ + +#include <linux/ethtool.h> +#include <linux/etherdevice.h> +#include <linux/kernel.h> +#include <linux/mii.h> +#include <linux/module.h> +#include <linux/of.h> +#include <linux/phy.h> +#include <linux/netdevice.h> + +#define DP83TC811_PHY_ID 0x2000a253 +#define DP83811_DEVADDR 0x1f + +#define MII_DP83811_SGMII_CTRL 0x09 +#define MII_DP83811_INT_STAT1 0x12 +#define MII_DP83811_INT_STAT2 0x13 +#define MII_DP83811_RESET_CTRL 0x1f + +#define DP83811_HW_RESET BIT(15) +#define DP83811_SW_RESET BIT(14) + +/* INT_STAT1 bits */ +#define DP83811_RX_ERR_HF_INT_EN BIT(0) +#define DP83811_MS_TRAINING_INT_EN BIT(1) +#define DP83811_ANEG_COMPLETE_INT_EN BIT(2) +#define DP83811_ESD_EVENT_INT_EN BIT(3) +#define DP83811_WOL_INT_EN BIT(4) +#define DP83811_LINK_STAT_INT_EN BIT(5) +#define DP83811_ENERGY_DET_INT_EN BIT(6) +#define DP83811_LINK_QUAL_INT_EN BIT(7) + +/* INT_STAT2 bits */ +#define DP83811_JABBER_DET_INT_EN BIT(0) +#define DP83811_POLARITY_INT_EN BIT(1) +#define DP83811_SLEEP_MODE_INT_EN BIT(2) +#define DP83811_OVERTEMP_INT_EN BIT(3) +#define DP83811_OVERVOLTAGE_INT_EN BIT(6) +#define DP83811_UNDERVOLTAGE_INT_EN BIT(7) + +#define MII_DP83811_RXSOP1 0x04a5 +#define MII_DP83811_RXSOP2 0x04a6 +#define MII_DP83811_RXSOP3 0x04a7 + +/* WoL Registers */ +#define MII_DP83811_WOL_CFG 0x04a0 +#define MII_DP83811_WOL_STAT 0x04a1 +#define MII_DP83811_WOL_DA1 0x04a2 +#define MII_DP83811_WOL_DA2 0x04a3 +#define MII_DP83811_WOL_DA3 0x04a4 + +/* WoL bits */ +#define DP83811_WOL_MAGIC_EN BIT(0) +#define DP83811_WOL_SECURE_ON BIT(5) +#define DP83811_WOL_EN BIT(7) +#define DP83811_WOL_INDICATION_SEL BIT(8) +#define DP83811_WOL_CLR_INDICATION BIT(11) + +/* SGMII CTRL bits */ +#define DP83811_TDR_AUTO BIT(8) +#define DP83811_SGMII_EN BIT(12) +#define DP83811_SGMII_AUTO_NEG_EN BIT(13) +#define DP83811_SGMII_TX_ERR_DIS BIT(14) +#define DP83811_SGMII_SOFT_RESET BIT(15) + +static int dp83811_ack_interrupt(struct phy_device *phydev) +{ + int err; + + err = phy_read(phydev, MII_DP83811_INT_STAT1); + if (err < 0) + return err; + + err = phy_read(phydev, MII_DP83811_INT_STAT2); + if (err < 0) + return err; + + return 0; +} + +static int dp83811_set_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + struct net_device *ndev = phydev->attached_dev; + const u8 *mac; + u16 value; + + if (wol->wolopts & (WAKE_MAGIC | WAKE_MAGICSECURE)) { + mac = (const u8 *)ndev->dev_addr; + + if (!is_valid_ether_addr(mac)) + return -EINVAL; + + /* MAC addresses start with byte 5, but stored in mac[0]. + * 811 PHYs store bytes 4|5, 2|3, 0|1 + */ + phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_DA1, + (mac[1] << 8) | mac[0]); + phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_DA2, + (mac[3] << 8) | mac[2]); + phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_DA3, + (mac[5] << 8) | mac[4]); + + value = phy_read_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG); + if (wol->wolopts & WAKE_MAGIC) + value |= DP83811_WOL_MAGIC_EN; + else + value &= ~DP83811_WOL_MAGIC_EN; + + if (wol->wolopts & WAKE_MAGICSECURE) { + phy_write_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_RXSOP1, + (wol->sopass[1] << 8) | wol->sopass[0]); + phy_write_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_RXSOP2, + (wol->sopass[3] << 8) | wol->sopass[2]); + phy_write_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_RXSOP3, + (wol->sopass[5] << 8) | wol->sopass[4]); + value |= DP83811_WOL_SECURE_ON; + } else { + value &= ~DP83811_WOL_SECURE_ON; + } + + value |= (DP83811_WOL_EN | DP83811_WOL_INDICATION_SEL | + DP83811_WOL_CLR_INDICATION); + phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + value); + } else { + value = phy_read_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_WOL_CFG); + value &= ~DP83811_WOL_EN; + phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + value); + } + + return 0; +} + +static void dp83811_get_wol(struct phy_device *phydev, + struct ethtool_wolinfo *wol) +{ + u16 sopass_val; + int value; + + wol->supported = (WAKE_MAGIC | WAKE_MAGICSECURE); + wol->wolopts = 0; + + value = phy_read_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG); + + if (value & DP83811_WOL_MAGIC_EN) + wol->wolopts |= WAKE_MAGIC; + + if (value & DP83811_WOL_SECURE_ON) { + sopass_val = phy_read_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_RXSOP1); + wol->sopass[0] = (sopass_val & 0xff); + wol->sopass[1] = (sopass_val >> 8); + + sopass_val = phy_read_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_RXSOP2); + wol->sopass[2] = (sopass_val & 0xff); + wol->sopass[3] = (sopass_val >> 8); + + sopass_val = phy_read_mmd(phydev, DP83811_DEVADDR, + MII_DP83811_RXSOP3); + wol->sopass[4] = (sopass_val & 0xff); + wol->sopass[5] = (sopass_val >> 8); + + wol->wolopts |= WAKE_MAGICSECURE; + } + + /* WoL is not enabled so set wolopts to 0 */ + if (!(value & DP83811_WOL_EN)) + wol->wolopts = 0; +} + +static int dp83811_config_intr(struct phy_device *phydev) +{ + int misr_status, err; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + misr_status = phy_read(phydev, MII_DP83811_INT_STAT1); + if (misr_status < 0) + return misr_status; + + misr_status |= (DP83811_RX_ERR_HF_INT_EN | + DP83811_MS_TRAINING_INT_EN | + DP83811_ANEG_COMPLETE_INT_EN | + DP83811_ESD_EVENT_INT_EN | + DP83811_WOL_INT_EN | + DP83811_LINK_STAT_INT_EN | + DP83811_ENERGY_DET_INT_EN | + DP83811_LINK_QUAL_INT_EN); + + err = phy_write(phydev, MII_DP83811_INT_STAT1, misr_status); + if (err < 0) + return err; + + misr_status = phy_read(phydev, MII_DP83811_INT_STAT2); + if (misr_status < 0) + return misr_status; + + misr_status |= (DP83811_JABBER_DET_INT_EN | + DP83811_POLARITY_INT_EN | + DP83811_SLEEP_MODE_INT_EN | + DP83811_OVERTEMP_INT_EN | + DP83811_OVERVOLTAGE_INT_EN | + DP83811_UNDERVOLTAGE_INT_EN); + + err = phy_write(phydev, MII_DP83811_INT_STAT2, misr_status); + + } else { + err = phy_write(phydev, MII_DP83811_INT_STAT1, 0); + if (err < 0) + return err; + + err = phy_write(phydev, MII_DP83811_INT_STAT1, 0); + } + + return err; +} + +static int dp83811_config_aneg(struct phy_device *phydev) +{ + int value, err; + + if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { + value = phy_read(phydev, MII_DP83811_SGMII_CTRL); + if (phydev->autoneg == AUTONEG_ENABLE) { + err = phy_write(phydev, MII_DP83811_SGMII_CTRL, + (DP83811_SGMII_AUTO_NEG_EN | value)); + if (err < 0) + return err; + } else { + err = phy_write(phydev, MII_DP83811_SGMII_CTRL, + (~DP83811_SGMII_AUTO_NEG_EN & value)); + if (err < 0) + return err; + } + } + + return genphy_config_aneg(phydev); +} + +static int dp83811_config_init(struct phy_device *phydev) +{ + int value, err; + + err = genphy_config_init(phydev); + if (err < 0) + return err; + + if (phydev->interface == PHY_INTERFACE_MODE_SGMII) { + value = phy_read(phydev, MII_DP83811_SGMII_CTRL); + if (!(value & DP83811_SGMII_EN)) { + err = phy_write(phydev, MII_DP83811_SGMII_CTRL, + (DP83811_SGMII_EN | value)); + if (err < 0) + return err; + } else { + err = phy_write(phydev, MII_DP83811_SGMII_CTRL, + (~DP83811_SGMII_EN & value)); + if (err < 0) + return err; + } + } + + value = DP83811_WOL_MAGIC_EN | DP83811_WOL_SECURE_ON | DP83811_WOL_EN; + + return phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, + value); +} + +static int dp83811_phy_reset(struct phy_device *phydev) +{ + int err; + + err = phy_write(phydev, MII_DP83811_RESET_CTRL, DP83811_HW_RESET); + if (err < 0) + return err; + + return 0; +} + +static int dp83811_suspend(struct phy_device *phydev) +{ + int value; + + value = phy_read_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG); + + if (!(value & DP83811_WOL_EN)) + genphy_suspend(phydev); + + return 0; +} + +static int dp83811_resume(struct phy_device *phydev) +{ + int value; + + genphy_resume(phydev); + + value = phy_read_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG); + + phy_write_mmd(phydev, DP83811_DEVADDR, MII_DP83811_WOL_CFG, value | + DP83811_WOL_CLR_INDICATION); + + return 0; +} + +static struct phy_driver dp83811_driver[] = { + { + .phy_id = DP83TC811_PHY_ID, + .phy_id_mask = 0xfffffff0, + .name = "TI DP83TC811", + .features = PHY_BASIC_FEATURES, + .flags = PHY_HAS_INTERRUPT, + .config_init = dp83811_config_init, + .config_aneg = dp83811_config_aneg, + .soft_reset = dp83811_phy_reset, + .get_wol = dp83811_get_wol, + .set_wol = dp83811_set_wol, + .ack_interrupt = dp83811_ack_interrupt, + .config_intr = dp83811_config_intr, + .suspend = dp83811_suspend, + .resume = dp83811_resume, + }, +}; +module_phy_driver(dp83811_driver); + +static struct mdio_device_id __maybe_unused dp83811_tbl[] = { + { DP83TC811_PHY_ID, 0xfffffff0 }, + { }, +}; +MODULE_DEVICE_TABLE(mdio, dp83811_tbl); + +MODULE_DESCRIPTION("Texas Instruments DP83TC811 PHY driver"); +MODULE_AUTHOR("Dan Murphy <dmurphy@ti.com"); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/marvell.c b/drivers/net/phy/marvell.c index 25e2a099b71c..b8f57e9b9379 100644 --- a/drivers/net/phy/marvell.c +++ b/drivers/net/phy/marvell.c @@ -1482,9 +1482,6 @@ static void marvell_get_strings(struct phy_device *phydev, u8 *data) } } -#ifndef UINT64_MAX -#define UINT64_MAX (u64)(~((u64)0)) -#endif static u64 marvell_get_stat(struct phy_device *phydev, int i) { struct marvell_hw_stat stat = marvell_hw_stats[i]; @@ -1494,7 +1491,7 @@ static u64 marvell_get_stat(struct phy_device *phydev, int i) val = phy_read_paged(phydev, stat.page, stat.reg); if (val < 0) { - ret = UINT64_MAX; + ret = U64_MAX; } else { val = val & ((1 << stat.bits) - 1); priv->stats[i] += val; diff --git a/drivers/net/phy/mdio-bitbang.c b/drivers/net/phy/mdio-bitbang.c index 403b085f0a89..15352f987bdf 100644 --- a/drivers/net/phy/mdio-bitbang.c +++ b/drivers/net/phy/mdio-bitbang.c @@ -205,14 +205,6 @@ static int mdiobb_write(struct mii_bus *bus, int phy, int reg, u16 val) return 0; } -static int mdiobb_reset(struct mii_bus *bus) -{ - struct mdiobb_ctrl *ctrl = bus->priv; - if (ctrl->reset) - ctrl->reset(bus); - return 0; -} - struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl) { struct mii_bus *bus; @@ -225,7 +217,6 @@ struct mii_bus *alloc_mdio_bitbang(struct mdiobb_ctrl *ctrl) bus->read = mdiobb_read; bus->write = mdiobb_write; - bus->reset = mdiobb_reset; bus->priv = ctrl; return bus; diff --git a/drivers/net/phy/mdio-boardinfo.c b/drivers/net/phy/mdio-boardinfo.c index 1861f387820d..863496fa5d13 100644 --- a/drivers/net/phy/mdio-boardinfo.c +++ b/drivers/net/phy/mdio-boardinfo.c @@ -30,17 +30,20 @@ void mdiobus_setup_mdiodev_from_board_info(struct mii_bus *bus, struct mdio_board_info *bi)) { struct mdio_board_entry *be; + struct mdio_board_entry *tmp; struct mdio_board_info *bi; int ret; mutex_lock(&mdio_board_lock); - list_for_each_entry(be, &mdio_board_list, list) { + list_for_each_entry_safe(be, tmp, &mdio_board_list, list) { bi = &be->board_info; if (strcmp(bus->id, bi->bus_id)) continue; + mutex_unlock(&mdio_board_lock); ret = cb(bus, bi); + mutex_lock(&mdio_board_lock); if (ret) continue; diff --git a/drivers/net/phy/mdio-gpio.c b/drivers/net/phy/mdio-gpio.c index 4333c6e14742..b501221819e1 100644 --- a/drivers/net/phy/mdio-gpio.c +++ b/drivers/net/phy/mdio-gpio.c @@ -24,8 +24,10 @@ #include <linux/slab.h> #include <linux/interrupt.h> #include <linux/platform_device.h> +#include <linux/mdio-bitbang.h> +#include <linux/mdio-gpio.h> #include <linux/gpio.h> -#include <linux/platform_data/mdio-gpio.h> +#include <linux/gpio/consumer.h> #include <linux/of_gpio.h> #include <linux/of_mdio.h> @@ -35,37 +37,22 @@ struct mdio_gpio_info { struct gpio_desc *mdc, *mdio, *mdo; }; -static void *mdio_gpio_of_get_data(struct platform_device *pdev) +static int mdio_gpio_get_data(struct device *dev, + struct mdio_gpio_info *bitbang) { - struct device_node *np = pdev->dev.of_node; - struct mdio_gpio_platform_data *pdata; - enum of_gpio_flags flags; - int ret; - - pdata = devm_kzalloc(&pdev->dev, sizeof(*pdata), GFP_KERNEL); - if (!pdata) - return NULL; - - ret = of_get_gpio_flags(np, 0, &flags); - if (ret < 0) - return NULL; - - pdata->mdc = ret; - pdata->mdc_active_low = flags & OF_GPIO_ACTIVE_LOW; - - ret = of_get_gpio_flags(np, 1, &flags); - if (ret < 0) - return NULL; - pdata->mdio = ret; - pdata->mdio_active_low = flags & OF_GPIO_ACTIVE_LOW; - - ret = of_get_gpio_flags(np, 2, &flags); - if (ret > 0) { - pdata->mdo = ret; - pdata->mdo_active_low = flags & OF_GPIO_ACTIVE_LOW; - } - - return pdata; + bitbang->mdc = devm_gpiod_get_index(dev, NULL, MDIO_GPIO_MDC, + GPIOD_OUT_LOW); + if (IS_ERR(bitbang->mdc)) + return PTR_ERR(bitbang->mdc); + + bitbang->mdio = devm_gpiod_get_index(dev, NULL, MDIO_GPIO_MDIO, + GPIOD_IN); + if (IS_ERR(bitbang->mdio)) + return PTR_ERR(bitbang->mdio); + + bitbang->mdo = devm_gpiod_get_index_optional(dev, NULL, MDIO_GPIO_MDO, + GPIOD_OUT_LOW); + return PTR_ERR_OR_ZERO(bitbang->mdo); } static void mdio_dir(struct mdiobb_ctrl *ctrl, int dir) @@ -125,78 +112,28 @@ static const struct mdiobb_ops mdio_gpio_ops = { }; static struct mii_bus *mdio_gpio_bus_init(struct device *dev, - struct mdio_gpio_platform_data *pdata, + struct mdio_gpio_info *bitbang, int bus_id) { struct mii_bus *new_bus; - struct mdio_gpio_info *bitbang; - int i; - int mdc, mdio, mdo; - unsigned long mdc_flags = GPIOF_OUT_INIT_LOW; - unsigned long mdio_flags = GPIOF_DIR_IN; - unsigned long mdo_flags = GPIOF_OUT_INIT_HIGH; - - bitbang = devm_kzalloc(dev, sizeof(*bitbang), GFP_KERNEL); - if (!bitbang) - goto out; bitbang->ctrl.ops = &mdio_gpio_ops; - bitbang->ctrl.reset = pdata->reset; - mdc = pdata->mdc; - bitbang->mdc = gpio_to_desc(mdc); - if (pdata->mdc_active_low) - mdc_flags = GPIOF_OUT_INIT_HIGH | GPIOF_ACTIVE_LOW; - mdio = pdata->mdio; - bitbang->mdio = gpio_to_desc(mdio); - if (pdata->mdio_active_low) - mdio_flags |= GPIOF_ACTIVE_LOW; - mdo = pdata->mdo; - if (mdo) { - bitbang->mdo = gpio_to_desc(mdo); - if (pdata->mdo_active_low) - mdo_flags = GPIOF_OUT_INIT_LOW | GPIOF_ACTIVE_LOW; - } new_bus = alloc_mdio_bitbang(&bitbang->ctrl); if (!new_bus) - goto out; - - new_bus->name = "GPIO Bitbanged MDIO", + return NULL; - new_bus->phy_mask = pdata->phy_mask; - new_bus->phy_ignore_ta_mask = pdata->phy_ignore_ta_mask; - memcpy(new_bus->irq, pdata->irqs, sizeof(new_bus->irq)); + new_bus->name = "GPIO Bitbanged MDIO"; new_bus->parent = dev; - if (new_bus->phy_mask == ~0) - goto out_free_bus; - - for (i = 0; i < PHY_MAX_ADDR; i++) - if (!new_bus->irq[i]) - new_bus->irq[i] = PHY_POLL; - if (bus_id != -1) snprintf(new_bus->id, MII_BUS_ID_SIZE, "gpio-%x", bus_id); else strncpy(new_bus->id, "gpio", MII_BUS_ID_SIZE); - if (devm_gpio_request_one(dev, mdc, mdc_flags, "mdc")) - goto out_free_bus; - - if (devm_gpio_request_one(dev, mdio, mdio_flags, "mdio")) - goto out_free_bus; - - if (mdo && devm_gpio_request_one(dev, mdo, mdo_flags, "mdo")) - goto out_free_bus; - dev_set_drvdata(dev, new_bus); return new_bus; - -out_free_bus: - free_mdio_bitbang(new_bus); -out: - return NULL; } static void mdio_gpio_bus_deinit(struct device *dev) @@ -216,26 +153,29 @@ static void mdio_gpio_bus_destroy(struct device *dev) static int mdio_gpio_probe(struct platform_device *pdev) { - struct mdio_gpio_platform_data *pdata; + struct mdio_gpio_info *bitbang; struct mii_bus *new_bus; int ret, bus_id; + bitbang = devm_kzalloc(&pdev->dev, sizeof(*bitbang), GFP_KERNEL); + if (!bitbang) + return -ENOMEM; + + ret = mdio_gpio_get_data(&pdev->dev, bitbang); + if (ret) + return ret; + if (pdev->dev.of_node) { - pdata = mdio_gpio_of_get_data(pdev); bus_id = of_alias_get_id(pdev->dev.of_node, "mdio-gpio"); if (bus_id < 0) { dev_warn(&pdev->dev, "failed to get alias id\n"); bus_id = 0; } } else { - pdata = dev_get_platdata(&pdev->dev); bus_id = pdev->id; } - if (!pdata) - return -ENODEV; - - new_bus = mdio_gpio_bus_init(&pdev->dev, pdata, bus_id); + new_bus = mdio_gpio_bus_init(&pdev->dev, bitbang, bus_id); if (!new_bus) return -ENODEV; diff --git a/drivers/net/phy/micrel.c b/drivers/net/phy/micrel.c index f41b224a9cdb..de31c5170a5b 100644 --- a/drivers/net/phy/micrel.c +++ b/drivers/net/phy/micrel.c @@ -650,9 +650,6 @@ static void kszphy_get_strings(struct phy_device *phydev, u8 *data) } } -#ifndef UINT64_MAX -#define UINT64_MAX (u64)(~((u64)0)) -#endif static u64 kszphy_get_stat(struct phy_device *phydev, int i) { struct kszphy_hw_stat stat = kszphy_hw_stats[i]; @@ -662,7 +659,7 @@ static u64 kszphy_get_stat(struct phy_device *phydev, int i) val = phy_read(phydev, stat.reg); if (val < 0) { - ret = UINT64_MAX; + ret = U64_MAX; } else { val = val & ((1 << stat.bits) - 1); priv->stats[i] += val; diff --git a/drivers/net/phy/microchip.c b/drivers/net/phy/microchip.c index a97ac8c12c4c..2d67937866a3 100644 --- a/drivers/net/phy/microchip.c +++ b/drivers/net/phy/microchip.c @@ -21,6 +21,8 @@ #include <linux/phy.h> #include <linux/microchipphy.h> #include <linux/delay.h> +#include <linux/of.h> +#include <dt-bindings/net/microchip-lan78xx.h> #define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>" #define DRIVER_DESC "Microchip LAN88XX PHY driver" @@ -225,6 +227,8 @@ static int lan88xx_probe(struct phy_device *phydev) { struct device *dev = &phydev->mdio.dev; struct lan88xx_priv *priv; + u32 led_modes[4]; + int len; priv = devm_kzalloc(dev, sizeof(*priv), GFP_KERNEL); if (!priv) @@ -232,6 +236,27 @@ static int lan88xx_probe(struct phy_device *phydev) priv->wolopts = 0; + len = of_property_read_variable_u32_array(dev->of_node, + "microchip,led-modes", + led_modes, + 0, + ARRAY_SIZE(led_modes)); + if (len >= 0) { + u32 reg = 0; + int i; + + for (i = 0; i < len; i++) { + if (led_modes[i] > 15) + return -EINVAL; + reg |= led_modes[i] << (i * 4); + } + for (; i < ARRAY_SIZE(led_modes); i++) + reg |= LAN78XX_FORCE_LED_OFF << (i * 4); + (void)phy_write(phydev, LAN78XX_PHY_LED_MODE_SELECT, reg); + } else if (len == -EOVERFLOW) { + return -EINVAL; + } + /* these values can be used to identify internal PHY */ priv->chip_id = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_ID); priv->chip_rev = phy_read_mmd(phydev, 3, LAN88XX_MMD3_CHIP_REV); diff --git a/drivers/net/phy/microchip_t1.c b/drivers/net/phy/microchip_t1.c new file mode 100644 index 000000000000..b1917dd1978a --- /dev/null +++ b/drivers/net/phy/microchip_t1.c @@ -0,0 +1,74 @@ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (C) 2018 Microchip Technology + +#include <linux/kernel.h> +#include <linux/module.h> +#include <linux/mii.h> +#include <linux/phy.h> + +/* Interrupt Source Register */ +#define LAN87XX_INTERRUPT_SOURCE (0x18) + +/* Interrupt Mask Register */ +#define LAN87XX_INTERRUPT_MASK (0x19) +#define LAN87XX_MASK_LINK_UP (0x0004) +#define LAN87XX_MASK_LINK_DOWN (0x0002) + +#define DRIVER_AUTHOR "Nisar Sayed <nisar.sayed@microchip.com>" +#define DRIVER_DESC "Microchip LAN87XX T1 PHY driver" + +static int lan87xx_phy_config_intr(struct phy_device *phydev) +{ + int rc, val = 0; + + if (phydev->interrupts == PHY_INTERRUPT_ENABLED) { + /* unmask all source and clear them before enable */ + rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, 0x7FFF); + rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE); + val = LAN87XX_MASK_LINK_UP | LAN87XX_MASK_LINK_DOWN; + } + + rc = phy_write(phydev, LAN87XX_INTERRUPT_MASK, val); + + return rc < 0 ? rc : 0; +} + +static int lan87xx_phy_ack_interrupt(struct phy_device *phydev) +{ + int rc = phy_read(phydev, LAN87XX_INTERRUPT_SOURCE); + + return rc < 0 ? rc : 0; +} + +static struct phy_driver microchip_t1_phy_driver[] = { + { + .phy_id = 0x0007c150, + .phy_id_mask = 0xfffffff0, + .name = "Microchip LAN87xx T1", + + .features = SUPPORTED_100baseT_Full, + .flags = PHY_HAS_INTERRUPT, + + .config_init = genphy_config_init, + .config_aneg = genphy_config_aneg, + + .ack_interrupt = lan87xx_phy_ack_interrupt, + .config_intr = lan87xx_phy_config_intr, + + .suspend = genphy_suspend, + .resume = genphy_resume, + } +}; + +module_phy_driver(microchip_t1_phy_driver); + +static struct mdio_device_id __maybe_unused microchip_t1_tbl[] = { + { 0x0007c150, 0xfffffff0 }, + { } +}; + +MODULE_DEVICE_TABLE(mdio, microchip_t1_tbl); + +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); +MODULE_LICENSE("GPL"); diff --git a/drivers/net/phy/phylink.c b/drivers/net/phy/phylink.c index c582b2d7546c..581ce93ecaf9 100644 --- a/drivers/net/phy/phylink.c +++ b/drivers/net/phy/phylink.c @@ -19,6 +19,7 @@ #include <linux/phylink.h> #include <linux/rtnetlink.h> #include <linux/spinlock.h> +#include <linux/timer.h> #include <linux/workqueue.h> #include "sfp.h" @@ -54,6 +55,7 @@ struct phylink { /* The link configuration settings */ struct phylink_link_state link_config; struct gpio_desc *link_gpio; + struct timer_list link_poll; void (*get_fixed_state)(struct net_device *dev, struct phylink_link_state *s); @@ -360,7 +362,7 @@ static void phylink_get_fixed_state(struct phylink *pl, struct phylink_link_stat if (pl->get_fixed_state) pl->get_fixed_state(pl->netdev, state); else if (pl->link_gpio) - state->link = !!gpiod_get_value(pl->link_gpio); + state->link = !!gpiod_get_value_cansleep(pl->link_gpio); } /* Flow control is resolved according to our and the link partners @@ -500,6 +502,15 @@ static void phylink_run_resolve(struct phylink *pl) queue_work(system_power_efficient_wq, &pl->resolve); } +static void phylink_fixed_poll(struct timer_list *t) +{ + struct phylink *pl = container_of(t, struct phylink, link_poll); + + mod_timer(t, jiffies + HZ); + + phylink_run_resolve(pl); +} + static const struct sfp_upstream_ops sfp_phylink_ops; static int phylink_register_sfp(struct phylink *pl, @@ -572,6 +583,7 @@ struct phylink *phylink_create(struct net_device *ndev, pl->link_config.an_enabled = true; pl->ops = ops; __set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); + timer_setup(&pl->link_poll, phylink_fixed_poll, 0); bitmap_fill(pl->supported, __ETHTOOL_LINK_MODE_MASK_NBITS); linkmode_copy(pl->link_config.advertising, pl->supported); @@ -612,6 +624,8 @@ void phylink_destroy(struct phylink *pl) { if (pl->sfp_bus) sfp_unregister_upstream(pl->sfp_bus); + if (!IS_ERR(pl->link_gpio)) + gpiod_put(pl->link_gpio); cancel_work_sync(&pl->resolve); kfree(pl); @@ -903,6 +917,8 @@ void phylink_start(struct phylink *pl) clear_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); phylink_run_resolve(pl); + if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio)) + mod_timer(&pl->link_poll, jiffies + HZ); if (pl->sfp_bus) sfp_upstream_start(pl->sfp_bus); if (pl->phydev) @@ -927,6 +943,8 @@ void phylink_stop(struct phylink *pl) phy_stop(pl->phydev); if (pl->sfp_bus) sfp_upstream_stop(pl->sfp_bus); + if (pl->link_an_mode == MLO_AN_FIXED && !IS_ERR(pl->link_gpio)) + del_timer_sync(&pl->link_poll); set_bit(PHYLINK_DISABLE_STOPPED, &pl->phylink_disable_state); queue_work(system_power_efficient_wq, &pl->resolve); diff --git a/drivers/net/phy/sfp-bus.c b/drivers/net/phy/sfp-bus.c index fd6c23f69c2f..d437f4f5ed52 100644 --- a/drivers/net/phy/sfp-bus.c +++ b/drivers/net/phy/sfp-bus.c @@ -132,6 +132,13 @@ void sfp_parse_support(struct sfp_bus *bus, const struct sfp_eeprom_id *id, br_max = br_nom + br_nom * id->ext.br_min / 100; br_min = br_nom - br_nom * id->ext.br_min / 100; } + + /* When using passive cables, in case neither BR,min nor BR,max + * are specified, set br_min to 0 as the nominal value is then + * used as the maximum. + */ + if (br_min == br_max && id->base.sfp_ct_passive) + br_min = 0; } /* Set ethtool support from the compliance fields. */ diff --git a/drivers/net/phy/smsc.c b/drivers/net/phy/smsc.c index be399d645224..c328208388da 100644 --- a/drivers/net/phy/smsc.c +++ b/drivers/net/phy/smsc.c @@ -168,9 +168,6 @@ static void smsc_get_strings(struct phy_device *phydev, u8 *data) } } -#ifndef UINT64_MAX -#define UINT64_MAX (u64)(~((u64)0)) -#endif static u64 smsc_get_stat(struct phy_device *phydev, int i) { struct smsc_hw_stat stat = smsc_hw_stats[i]; @@ -179,7 +176,7 @@ static u64 smsc_get_stat(struct phy_device *phydev, int i) val = phy_read(phydev, stat.reg); if (val < 0) - ret = UINT64_MAX; + ret = U64_MAX; else ret = val; diff --git a/drivers/net/team/team.c b/drivers/net/team/team.c index ddb6bf85a59c..9dbd390ace34 100644 --- a/drivers/net/team/team.c +++ b/drivers/net/team/team.c @@ -2942,7 +2942,7 @@ static int team_device_event(struct notifier_block *unused, case NETDEV_CHANGE: if (netif_running(port->dev)) team_port_change_check(port, - !!netif_carrier_ok(port->dev)); + !!netif_oper_up(port->dev)); break; case NETDEV_UNREGISTER: team_del_slave(port->team->dev, dev); diff --git a/drivers/net/tun.c b/drivers/net/tun.c index ef33950a45d9..44d4f3d25350 100644 --- a/drivers/net/tun.c +++ b/drivers/net/tun.c @@ -248,11 +248,11 @@ struct veth { __be16 h_vlan_TCI; }; -bool tun_is_xdp_buff(void *ptr) +bool tun_is_xdp_frame(void *ptr) { return (unsigned long)ptr & TUN_XDP_FLAG; } -EXPORT_SYMBOL(tun_is_xdp_buff); +EXPORT_SYMBOL(tun_is_xdp_frame); void *tun_xdp_to_ptr(void *ptr) { @@ -525,11 +525,6 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, rcu_read_lock(); - /* We may get a very small possibility of OOO during switching, not - * worth to optimize.*/ - if (tun->numqueues == 1 || tfile->detached) - goto unlock; - e = tun_flow_find(head, rxhash); if (likely(e)) { /* TODO: keep queueing to old queue until it's empty? */ @@ -548,7 +543,6 @@ static void tun_flow_update(struct tun_struct *tun, u32 rxhash, spin_unlock_bh(&tun->lock); } -unlock: rcu_read_unlock(); } @@ -660,10 +654,10 @@ void tun_ptr_free(void *ptr) { if (!ptr) return; - if (tun_is_xdp_buff(ptr)) { - struct xdp_buff *xdp = tun_ptr_to_xdp(ptr); + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); - put_page(virt_to_head_page(xdp->data)); + xdp_return_frame(xdpf); } else { __skb_array_destroy_skb(ptr); } @@ -854,6 +848,12 @@ static int tun_attach(struct tun_struct *tun, struct file *file, tun->dev, tfile->queue_index); if (err < 0) goto out; + err = xdp_rxq_info_reg_mem_model(&tfile->xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) { + xdp_rxq_info_unreg(&tfile->xdp_rxq); + goto out; + } err = 0; } @@ -1290,21 +1290,13 @@ static const struct net_device_ops tun_netdev_ops = { .ndo_get_stats64 = tun_net_get_stats64, }; -static int tun_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) +static int tun_xdp_xmit(struct net_device *dev, struct xdp_frame *frame) { struct tun_struct *tun = netdev_priv(dev); - struct xdp_buff *buff = xdp->data_hard_start; - int headroom = xdp->data - xdp->data_hard_start; struct tun_file *tfile; u32 numqueues; int ret = 0; - /* Assure headroom is available and buff is properly aligned */ - if (unlikely(headroom < sizeof(*xdp) || tun_is_xdp_buff(xdp))) - return -ENOSPC; - - *buff = *xdp; - rcu_read_lock(); numqueues = READ_ONCE(tun->numqueues); @@ -1318,7 +1310,7 @@ static int tun_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) /* Encode the XDP flag into lowest bit for consumer to differ * XDP buffer from sk_buff. */ - if (ptr_ring_produce(&tfile->tx_ring, tun_xdp_to_ptr(buff))) { + if (ptr_ring_produce(&tfile->tx_ring, tun_xdp_to_ptr(frame))) { this_cpu_inc(tun->pcpu_stats->tx_dropped); ret = -ENOSPC; } @@ -1328,6 +1320,16 @@ out: return ret; } +static int tun_xdp_tx(struct net_device *dev, struct xdp_buff *xdp) +{ + struct xdp_frame *frame = convert_to_xdp_frame(xdp); + + if (unlikely(!frame)) + return -EOVERFLOW; + + return tun_xdp_xmit(dev, frame); +} + static void tun_xdp_flush(struct net_device *dev) { struct tun_struct *tun = netdev_priv(dev); @@ -1675,7 +1677,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, case XDP_TX: get_page(alloc_frag->page); alloc_frag->offset += buflen; - if (tun_xdp_xmit(tun->dev, &xdp)) + if (tun_xdp_tx(tun->dev, &xdp)) goto err_redirect; tun_xdp_flush(tun->dev); rcu_read_unlock(); @@ -1683,6 +1685,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, return NULL; case XDP_PASS: delta = orig_data - xdp.data; + len = xdp.data_end - xdp.data; break; default: bpf_warn_invalid_xdp_action(act); @@ -1703,7 +1706,7 @@ static struct sk_buff *tun_build_skb(struct tun_struct *tun, } skb_reserve(skb, pad - delta); - skb_put(skb, len + delta); + skb_put(skb, len); get_page(alloc_frag->page); alloc_frag->offset += buflen; @@ -1924,10 +1927,13 @@ static ssize_t tun_get_user(struct tun_struct *tun, struct tun_file *tfile, rcu_read_unlock(); } - rcu_read_lock(); - if (!rcu_dereference(tun->steering_prog)) + /* Compute the costly rx hash only if needed for flow updates. + * We may get a very small possibility of OOO during switching, not + * worth to optimize. + */ + if (!rcu_access_pointer(tun->steering_prog) && tun->numqueues > 1 && + !tfile->detached) rxhash = __skb_get_hash_symmetric(skb); - rcu_read_unlock(); if (frags) { /* Exercise flow dissector code path. */ @@ -1996,11 +2002,11 @@ static ssize_t tun_chr_write_iter(struct kiocb *iocb, struct iov_iter *from) static ssize_t tun_put_user_xdp(struct tun_struct *tun, struct tun_file *tfile, - struct xdp_buff *xdp, + struct xdp_frame *xdp_frame, struct iov_iter *iter) { int vnet_hdr_sz = 0; - size_t size = xdp->data_end - xdp->data; + size_t size = xdp_frame->len; struct tun_pcpu_stats *stats; size_t ret; @@ -2016,7 +2022,7 @@ static ssize_t tun_put_user_xdp(struct tun_struct *tun, iov_iter_advance(iter, vnet_hdr_sz - sizeof(gso)); } - ret = copy_to_iter(xdp->data, size, iter) + vnet_hdr_sz; + ret = copy_to_iter(xdp_frame->data, size, iter) + vnet_hdr_sz; stats = get_cpu_ptr(tun->pcpu_stats); u64_stats_update_begin(&stats->syncp); @@ -2184,11 +2190,11 @@ static ssize_t tun_do_read(struct tun_struct *tun, struct tun_file *tfile, return err; } - if (tun_is_xdp_buff(ptr)) { - struct xdp_buff *xdp = tun_ptr_to_xdp(ptr); + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); - ret = tun_put_user_xdp(tun, tfile, xdp, to); - put_page(virt_to_head_page(xdp->data)); + ret = tun_put_user_xdp(tun, tfile, xdpf, to); + xdp_return_frame(xdpf); } else { struct sk_buff *skb = ptr; @@ -2427,10 +2433,10 @@ out_free: static int tun_ptr_peek_len(void *ptr) { if (likely(ptr)) { - if (tun_is_xdp_buff(ptr)) { - struct xdp_buff *xdp = tun_ptr_to_xdp(ptr); + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); - return xdp->data_end - xdp->data; + return xdpf->len; } return __skb_array_len_with_tag(ptr); } else { @@ -2844,10 +2850,10 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, unsigned long arg, int ifreq_len) { struct tun_file *tfile = file->private_data; + struct net *net = sock_net(&tfile->sk); struct tun_struct *tun; void __user* argp = (void __user*)arg; struct ifreq ifr; - struct net *net; kuid_t owner; kgid_t group; int sndbuf; @@ -2871,14 +2877,18 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, */ return put_user(IFF_TUN | IFF_TAP | TUN_FEATURES, (unsigned int __user*)argp); - } else if (cmd == TUNSETQUEUE) + } else if (cmd == TUNSETQUEUE) { return tun_set_queue(file, &ifr); + } else if (cmd == SIOCGSKNS) { + if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) + return -EPERM; + return open_related_ns(&net->ns, get_net_ns); + } ret = 0; rtnl_lock(); tun = tun_get(tfile); - net = sock_net(&tfile->sk); if (cmd == TUNSETIFF) { ret = -EEXIST; if (tun) @@ -2908,14 +2918,6 @@ static long __tun_chr_ioctl(struct file *file, unsigned int cmd, tfile->ifindex = ifindex; goto unlock; } - if (cmd == SIOCGSKNS) { - ret = -EPERM; - if (!ns_capable(net->user_ns, CAP_NET_ADMIN)) - goto unlock; - - ret = open_related_ns(&net->ns, get_net_ns); - goto unlock; - } ret = -EBADFD; if (!tun) diff --git a/drivers/net/usb/Kconfig b/drivers/net/usb/Kconfig index f28bd74ac275..418b0904cecb 100644 --- a/drivers/net/usb/Kconfig +++ b/drivers/net/usb/Kconfig @@ -111,6 +111,7 @@ config USB_LAN78XX select MII select PHYLIB select MICROCHIP_PHY + select FIXED_PHY help This option adds support for Microchip LAN78XX based USB 2 & USB 3 10/100/1000 Ethernet adapters. diff --git a/drivers/net/usb/lan78xx.c b/drivers/net/usb/lan78xx.c index 0867f7275852..91761436709a 100644 --- a/drivers/net/usb/lan78xx.c +++ b/drivers/net/usb/lan78xx.c @@ -36,13 +36,14 @@ #include <linux/irq.h> #include <linux/irqchip/chained_irq.h> #include <linux/microchipphy.h> -#include <linux/phy.h> +#include <linux/phy_fixed.h> +#include <linux/of_mdio.h> +#include <linux/of_net.h> #include "lan78xx.h" #define DRIVER_AUTHOR "WOOJUNG HUH <woojung.huh@microchip.com>" #define DRIVER_DESC "LAN78XX USB 3.0 Gigabit Ethernet Devices" #define DRIVER_NAME "lan78xx" -#define DRIVER_VERSION "1.0.6" #define TX_TIMEOUT_JIFFIES (5 * HZ) #define THROTTLE_JIFFIES (HZ / 8) @@ -278,6 +279,30 @@ struct lan78xx_statstage64 { u64 eee_tx_lpi_time; }; +static u32 lan78xx_regs[] = { + ID_REV, + INT_STS, + HW_CFG, + PMT_CTL, + E2P_CMD, + E2P_DATA, + USB_STATUS, + VLAN_TYPE, + MAC_CR, + MAC_RX, + MAC_TX, + FLOW, + ERR_STS, + MII_ACC, + MII_DATA, + EEE_TX_LPI_REQ_DLY, + EEE_TW_TX_SYS, + EEE_TX_LPI_REM_DLY, + WUCSR +}; + +#define PHY_REG_SIZE (32 * sizeof(u32)) + struct lan78xx_net; struct lan78xx_priv { @@ -1477,7 +1502,6 @@ static void lan78xx_get_drvinfo(struct net_device *net, struct lan78xx_net *dev = netdev_priv(net); strncpy(info->driver, DRIVER_NAME, sizeof(info->driver)); - strncpy(info->version, DRIVER_VERSION, sizeof(info->version)); usb_make_path(dev->udev, info->bus_info, sizeof(info->bus_info)); } @@ -1605,6 +1629,34 @@ exit: return ret; } +static int lan78xx_get_regs_len(struct net_device *netdev) +{ + if (!netdev->phydev) + return (sizeof(lan78xx_regs)); + else + return (sizeof(lan78xx_regs) + PHY_REG_SIZE); +} + +static void +lan78xx_get_regs(struct net_device *netdev, struct ethtool_regs *regs, + void *buf) +{ + u32 *data = buf; + int i, j; + struct lan78xx_net *dev = netdev_priv(netdev); + + /* Read Device/MAC registers */ + for (i = 0; i < (sizeof(lan78xx_regs) / sizeof(u32)); i++) + lan78xx_read_reg(dev, lan78xx_regs[i], &data[i]); + + if (!netdev->phydev) + return; + + /* Read PHY registers */ + for (j = 0; j < 32; i++, j++) + data[i] = phy_read(netdev->phydev, j); +} + static const struct ethtool_ops lan78xx_ethtool_ops = { .get_link = lan78xx_get_link, .nway_reset = phy_ethtool_nway_reset, @@ -1625,6 +1677,8 @@ static const struct ethtool_ops lan78xx_ethtool_ops = { .set_pauseparam = lan78xx_set_pause, .get_link_ksettings = lan78xx_get_link_ksettings, .set_link_ksettings = lan78xx_set_link_ksettings, + .get_regs_len = lan78xx_get_regs_len, + .get_regs = lan78xx_get_regs, }; static int lan78xx_ioctl(struct net_device *netdev, struct ifreq *rq, int cmd) @@ -1652,34 +1706,31 @@ static void lan78xx_init_mac_address(struct lan78xx_net *dev) addr[5] = (addr_hi >> 8) & 0xFF; if (!is_valid_ether_addr(addr)) { - /* reading mac address from EEPROM or OTP */ - if ((lan78xx_read_eeprom(dev, EEPROM_MAC_OFFSET, ETH_ALEN, - addr) == 0) || - (lan78xx_read_otp(dev, EEPROM_MAC_OFFSET, ETH_ALEN, - addr) == 0)) { - if (is_valid_ether_addr(addr)) { - /* eeprom values are valid so use them */ - netif_dbg(dev, ifup, dev->net, - "MAC address read from EEPROM"); - } else { - /* generate random MAC */ - random_ether_addr(addr); - netif_dbg(dev, ifup, dev->net, - "MAC address set to random addr"); - } - - addr_lo = addr[0] | (addr[1] << 8) | - (addr[2] << 16) | (addr[3] << 24); - addr_hi = addr[4] | (addr[5] << 8); - - ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); - ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); + if (!eth_platform_get_mac_address(&dev->udev->dev, addr)) { + /* valid address present in Device Tree */ + netif_dbg(dev, ifup, dev->net, + "MAC address read from Device Tree"); + } else if (((lan78xx_read_eeprom(dev, EEPROM_MAC_OFFSET, + ETH_ALEN, addr) == 0) || + (lan78xx_read_otp(dev, EEPROM_MAC_OFFSET, + ETH_ALEN, addr) == 0)) && + is_valid_ether_addr(addr)) { + /* eeprom values are valid so use them */ + netif_dbg(dev, ifup, dev->net, + "MAC address read from EEPROM"); } else { /* generate random MAC */ random_ether_addr(addr); netif_dbg(dev, ifup, dev->net, "MAC address set to random addr"); } + + addr_lo = addr[0] | (addr[1] << 8) | + (addr[2] << 16) | (addr[3] << 24); + addr_hi = addr[4] | (addr[5] << 8); + + ret = lan78xx_write_reg(dev, RX_ADDRL, addr_lo); + ret = lan78xx_write_reg(dev, RX_ADDRH, addr_hi); } ret = lan78xx_write_reg(dev, MAF_LO(0), addr_lo); @@ -1762,6 +1813,7 @@ done: static int lan78xx_mdio_init(struct lan78xx_net *dev) { + struct device_node *node; int ret; dev->mdiobus = mdiobus_alloc(); @@ -1790,7 +1842,13 @@ static int lan78xx_mdio_init(struct lan78xx_net *dev) break; } - ret = mdiobus_register(dev->mdiobus); + node = of_get_child_by_name(dev->udev->dev.of_node, "mdio"); + if (node) { + ret = of_mdiobus_register(dev->mdiobus, node); + of_node_put(node); + } else { + ret = mdiobus_register(dev->mdiobus); + } if (ret) { netdev_err(dev->net, "can't register MDIO bus\n"); goto exit1; @@ -2003,52 +2061,91 @@ static int ksz9031rnx_fixup(struct phy_device *phydev) return 1; } -static int lan78xx_phy_init(struct lan78xx_net *dev) +static struct phy_device *lan7801_phy_init(struct lan78xx_net *dev) { + u32 buf; int ret; - u32 mii_adv; + struct fixed_phy_status fphy_status = { + .link = 1, + .speed = SPEED_1000, + .duplex = DUPLEX_FULL, + }; struct phy_device *phydev; phydev = phy_find_first(dev->mdiobus); if (!phydev) { - netdev_err(dev->net, "no PHY found\n"); - return -EIO; - } - - if ((dev->chipid == ID_REV_CHIP_ID_7800_) || - (dev->chipid == ID_REV_CHIP_ID_7850_)) { - phydev->is_internal = true; - dev->interface = PHY_INTERFACE_MODE_GMII; - - } else if (dev->chipid == ID_REV_CHIP_ID_7801_) { + netdev_dbg(dev->net, "PHY Not Found!! Registering Fixed PHY\n"); + phydev = fixed_phy_register(PHY_POLL, &fphy_status, -1, + NULL); + if (IS_ERR(phydev)) { + netdev_err(dev->net, "No PHY/fixed_PHY found\n"); + return NULL; + } + netdev_dbg(dev->net, "Registered FIXED PHY\n"); + dev->interface = PHY_INTERFACE_MODE_RGMII; + ret = lan78xx_write_reg(dev, MAC_RGMII_ID, + MAC_RGMII_ID_TXC_DELAY_EN_); + ret = lan78xx_write_reg(dev, RGMII_TX_BYP_DLL, 0x3D00); + ret = lan78xx_read_reg(dev, HW_CFG, &buf); + buf |= HW_CFG_CLK125_EN_; + buf |= HW_CFG_REFCLK25_EN_; + ret = lan78xx_write_reg(dev, HW_CFG, buf); + } else { if (!phydev->drv) { netdev_err(dev->net, "no PHY driver found\n"); - return -EIO; + return NULL; } - dev->interface = PHY_INTERFACE_MODE_RGMII; - /* external PHY fixup for KSZ9031RNX */ ret = phy_register_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0, ksz9031rnx_fixup); if (ret < 0) { - netdev_err(dev->net, "fail to register fixup\n"); - return ret; + netdev_err(dev->net, "Failed to register fixup for PHY_KSZ9031RNX\n"); + return NULL; } /* external PHY fixup for LAN8835 */ ret = phy_register_fixup_for_uid(PHY_LAN8835, 0xfffffff0, lan8835_fixup); if (ret < 0) { - netdev_err(dev->net, "fail to register fixup\n"); - return ret; + netdev_err(dev->net, "Failed to register fixup for PHY_LAN8835\n"); + return NULL; } /* add more external PHY fixup here if needed */ phydev->is_internal = false; - } else { - netdev_err(dev->net, "unknown ID found\n"); - ret = -EIO; - goto error; + } + return phydev; +} + +static int lan78xx_phy_init(struct lan78xx_net *dev) +{ + int ret; + u32 mii_adv; + struct phy_device *phydev; + + switch (dev->chipid) { + case ID_REV_CHIP_ID_7801_: + phydev = lan7801_phy_init(dev); + if (!phydev) { + netdev_err(dev->net, "lan7801: PHY Init Failed"); + return -EIO; + } + break; + + case ID_REV_CHIP_ID_7800_: + case ID_REV_CHIP_ID_7850_: + phydev = phy_find_first(dev->mdiobus); + if (!phydev) { + netdev_err(dev->net, "no PHY found\n"); + return -EIO; + } + phydev->is_internal = true; + dev->interface = PHY_INTERFACE_MODE_GMII; + break; + + default: + netdev_err(dev->net, "Unknown CHIP ID found\n"); + return -EIO; } /* if phyirq is not set, use polling mode in phylib */ @@ -2067,6 +2164,16 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) if (ret) { netdev_err(dev->net, "can't attach PHY to %s\n", dev->mdiobus->id); + if (dev->chipid == ID_REV_CHIP_ID_7801_) { + if (phy_is_pseudo_fixed_link(phydev)) { + fixed_phy_unregister(phydev); + } else { + phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, + 0xfffffff0); + phy_unregister_fixup_for_uid(PHY_LAN8835, + 0xfffffff0); + } + } return -EIO; } @@ -2079,17 +2186,33 @@ static int lan78xx_phy_init(struct lan78xx_net *dev) mii_adv = (u32)mii_advertise_flowctrl(dev->fc_request_control); phydev->advertising |= mii_adv_to_ethtool_adv_t(mii_adv); + if (phydev->mdio.dev.of_node) { + u32 reg; + int len; + + len = of_property_count_elems_of_size(phydev->mdio.dev.of_node, + "microchip,led-modes", + sizeof(u32)); + if (len >= 0) { + /* Ensure the appropriate LEDs are enabled */ + lan78xx_read_reg(dev, HW_CFG, ®); + reg &= ~(HW_CFG_LED0_EN_ | + HW_CFG_LED1_EN_ | + HW_CFG_LED2_EN_ | + HW_CFG_LED3_EN_); + reg |= (len > 0) * HW_CFG_LED0_EN_ | + (len > 1) * HW_CFG_LED1_EN_ | + (len > 2) * HW_CFG_LED2_EN_ | + (len > 3) * HW_CFG_LED3_EN_; + lan78xx_write_reg(dev, HW_CFG, reg); + } + } + genphy_config_aneg(phydev); dev->fc_autoneg = phydev->autoneg; return 0; - -error: - phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0); - phy_unregister_fixup_for_uid(PHY_LAN8835, 0xfffffff0); - - return ret; } static int lan78xx_set_rx_max_frame_length(struct lan78xx_net *dev, int size) @@ -3487,6 +3610,7 @@ static void lan78xx_disconnect(struct usb_interface *intf) struct lan78xx_net *dev; struct usb_device *udev; struct net_device *net; + struct phy_device *phydev; dev = usb_get_intfdata(intf); usb_set_intfdata(intf, NULL); @@ -3495,12 +3619,16 @@ static void lan78xx_disconnect(struct usb_interface *intf) udev = interface_to_usbdev(intf); net = dev->net; + phydev = net->phydev; phy_unregister_fixup_for_uid(PHY_KSZ9031RNX, 0xfffffff0); phy_unregister_fixup_for_uid(PHY_LAN8835, 0xfffffff0); phy_disconnect(net->phydev); + if (phy_is_pseudo_fixed_link(phydev)) + fixed_phy_unregister(phydev); + unregister_netdev(net); cancel_delayed_work_sync(&dev->wq); diff --git a/drivers/net/virtio_net.c b/drivers/net/virtio_net.c index 770422e953f7..f34794a76c4d 100644 --- a/drivers/net/virtio_net.c +++ b/drivers/net/virtio_net.c @@ -419,46 +419,51 @@ static void virtnet_xdp_flush(struct net_device *dev) virtqueue_kick(sq->vq); } -static bool __virtnet_xdp_xmit(struct virtnet_info *vi, - struct xdp_buff *xdp) +static int __virtnet_xdp_xmit(struct virtnet_info *vi, + struct xdp_frame *xdpf) { struct virtio_net_hdr_mrg_rxbuf *hdr; - unsigned int len; + struct xdp_frame *xdpf_sent; struct send_queue *sq; + unsigned int len; unsigned int qp; - void *xdp_sent; int err; qp = vi->curr_queue_pairs - vi->xdp_queue_pairs + smp_processor_id(); sq = &vi->sq[qp]; /* Free up any pending old buffers before queueing new ones. */ - while ((xdp_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) { - struct page *sent_page = virt_to_head_page(xdp_sent); + while ((xdpf_sent = virtqueue_get_buf(sq->vq, &len)) != NULL) + xdp_return_frame(xdpf_sent); - put_page(sent_page); - } + /* virtqueue want to use data area in-front of packet */ + if (unlikely(xdpf->metasize > 0)) + return -EOPNOTSUPP; - xdp->data -= vi->hdr_len; + if (unlikely(xdpf->headroom < vi->hdr_len)) + return -EOVERFLOW; + + /* Make room for virtqueue hdr (also change xdpf->headroom?) */ + xdpf->data -= vi->hdr_len; /* Zero header and leave csum up to XDP layers */ - hdr = xdp->data; + hdr = xdpf->data; memset(hdr, 0, vi->hdr_len); + xdpf->len += vi->hdr_len; - sg_init_one(sq->sg, xdp->data, xdp->data_end - xdp->data); + sg_init_one(sq->sg, xdpf->data, xdpf->len); - err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdp->data, GFP_ATOMIC); + err = virtqueue_add_outbuf(sq->vq, sq->sg, 1, xdpf, GFP_ATOMIC); if (unlikely(err)) - return false; /* Caller handle free/refcnt */ + return -ENOSPC; /* Caller handle free/refcnt */ - return true; + return 0; } -static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) +static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_frame *xdpf) { struct virtnet_info *vi = netdev_priv(dev); struct receive_queue *rq = vi->rq; struct bpf_prog *xdp_prog; - bool sent; /* Only allow ndo_xdp_xmit if XDP is loaded on dev, as this * indicate XDP resources have been successfully allocated. @@ -467,10 +472,7 @@ static int virtnet_xdp_xmit(struct net_device *dev, struct xdp_buff *xdp) if (!xdp_prog) return -ENXIO; - sent = __virtnet_xdp_xmit(vi, xdp); - if (!sent) - return -ENOSPC; - return 0; + return __virtnet_xdp_xmit(vi, xdpf); } static unsigned int virtnet_get_headroom(struct virtnet_info *vi) @@ -559,7 +561,6 @@ static struct sk_buff *receive_small(struct net_device *dev, struct page *page = virt_to_head_page(buf); unsigned int delta = 0; struct page *xdp_page; - bool sent; int err; len -= vi->hdr_len; @@ -568,6 +569,7 @@ static struct sk_buff *receive_small(struct net_device *dev, xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { struct virtio_net_hdr_mrg_rxbuf *hdr = buf + header_offset; + struct xdp_frame *xdpf; struct xdp_buff xdp; void *orig_data; u32 act; @@ -608,10 +610,14 @@ static struct sk_buff *receive_small(struct net_device *dev, case XDP_PASS: /* Recalculate length in case bpf program changed it */ delta = orig_data - xdp.data; + len = xdp.data_end - xdp.data; break; case XDP_TX: - sent = __virtnet_xdp_xmit(vi, &xdp); - if (unlikely(!sent)) { + xdpf = convert_to_xdp_frame(&xdp); + if (unlikely(!xdpf)) + goto err_xdp; + err = __virtnet_xdp_xmit(vi, xdpf); + if (unlikely(err)) { trace_xdp_exception(vi->dev, xdp_prog, act); goto err_xdp; } @@ -641,7 +647,7 @@ static struct sk_buff *receive_small(struct net_device *dev, goto err; } skb_reserve(skb, headroom - delta); - skb_put(skb, len + delta); + skb_put(skb, len); if (!delta) { buf += header_offset; memcpy(skb_vnet_hdr(skb), buf, vi->hdr_len); @@ -694,7 +700,6 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, struct bpf_prog *xdp_prog; unsigned int truesize; unsigned int headroom = mergeable_ctx_to_headroom(ctx); - bool sent; int err; head_skb = NULL; @@ -702,6 +707,7 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, rcu_read_lock(); xdp_prog = rcu_dereference(rq->xdp_prog); if (xdp_prog) { + struct xdp_frame *xdpf; struct page *xdp_page; struct xdp_buff xdp; void *data; @@ -756,6 +762,10 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, offset = xdp.data - page_address(xdp_page) - vi->hdr_len; + /* recalculate len if xdp.data or xdp.data_end were + * adjusted + */ + len = xdp.data_end - xdp.data + vi->hdr_len; /* We can only create skb based on xdp_page. */ if (unlikely(xdp_page != page)) { rcu_read_unlock(); @@ -766,8 +776,11 @@ static struct sk_buff *receive_mergeable(struct net_device *dev, } break; case XDP_TX: - sent = __virtnet_xdp_xmit(vi, &xdp); - if (unlikely(!sent)) { + xdpf = convert_to_xdp_frame(&xdp); + if (unlikely(!xdpf)) + goto err_xdp; + err = __virtnet_xdp_xmit(vi, xdpf); + if (unlikely(err)) { trace_xdp_exception(vi->dev, xdp_prog, act); if (unlikely(xdp_page != page)) put_page(xdp_page); @@ -1312,6 +1325,13 @@ static int virtnet_open(struct net_device *dev) if (err < 0) return err; + err = xdp_rxq_info_reg_mem_model(&vi->rq[i].xdp_rxq, + MEM_TYPE_PAGE_SHARED, NULL); + if (err < 0) { + xdp_rxq_info_unreg(&vi->rq[i].xdp_rxq); + return err; + } + virtnet_napi_enable(vi->rq[i].vq, &vi->rq[i].napi); virtnet_napi_tx_enable(vi, vi->sq[i].vq, &vi->sq[i].napi); } diff --git a/drivers/net/vrf.c b/drivers/net/vrf.c index 0a2b180d138a..90b5f3900c22 100644 --- a/drivers/net/vrf.c +++ b/drivers/net/vrf.c @@ -48,6 +48,9 @@ static unsigned int vrf_net_id; struct net_vrf { struct rtable __rcu *rth; struct rt6_info __rcu *rt6; +#if IS_ENABLED(CONFIG_IPV6) + struct fib6_table *fib6_table; +#endif u32 tb_id; }; @@ -496,7 +499,6 @@ static int vrf_rt6_create(struct net_device *dev) int flags = DST_HOST | DST_NOPOLICY | DST_NOXFRM; struct net_vrf *vrf = netdev_priv(dev); struct net *net = dev_net(dev); - struct fib6_table *rt6i_table; struct rt6_info *rt6; int rc = -ENOMEM; @@ -504,8 +506,8 @@ static int vrf_rt6_create(struct net_device *dev) if (!ipv6_mod_enabled()) return 0; - rt6i_table = fib6_new_table(net, vrf->tb_id); - if (!rt6i_table) + vrf->fib6_table = fib6_new_table(net, vrf->tb_id); + if (!vrf->fib6_table) goto out; /* create a dst for routing packets out a VRF device */ @@ -513,7 +515,6 @@ static int vrf_rt6_create(struct net_device *dev) if (!rt6) goto out; - rt6->rt6i_table = rt6i_table; rt6->dst.output = vrf_output6; rcu_assign_pointer(vrf->rt6, rt6); @@ -946,22 +947,8 @@ static struct rt6_info *vrf_ip6_route_lookup(struct net *net, int flags) { struct net_vrf *vrf = netdev_priv(dev); - struct fib6_table *table = NULL; - struct rt6_info *rt6; - - rcu_read_lock(); - - /* fib6_table does not have a refcnt and can not be freed */ - rt6 = rcu_dereference(vrf->rt6); - if (likely(rt6)) - table = rt6->rt6i_table; - - rcu_read_unlock(); - - if (!table) - return NULL; - return ip6_pol_route(net, table, ifindex, fl6, skb, flags); + return ip6_pol_route(net, vrf->fib6_table, ifindex, fl6, skb, flags); } static void vrf_ip6_input_dst(struct sk_buff *skb, struct net_device *vrf_dev, diff --git a/drivers/net/vxlan.c b/drivers/net/vxlan.c index fab7a4db249e..aee0e60471f1 100644 --- a/drivers/net/vxlan.c +++ b/drivers/net/vxlan.c @@ -2085,9 +2085,13 @@ static void vxlan_xmit_one(struct sk_buff *skb, struct net_device *dev, local_ip = vxlan->cfg.saddr; dst_cache = &rdst->dst_cache; md->gbp = skb->mark; - ttl = vxlan->cfg.ttl; - if (!ttl && vxlan_addr_multicast(dst)) - ttl = 1; + if (flags & VXLAN_F_TTL_INHERIT) { + ttl = ip_tunnel_get_ttl(old_iph, skb); + } else { + ttl = vxlan->cfg.ttl; + if (!ttl && vxlan_addr_multicast(dst)) + ttl = 1; + } tos = vxlan->cfg.tos; if (tos == 1) @@ -2709,6 +2713,7 @@ static const struct nla_policy vxlan_policy[IFLA_VXLAN_MAX + 1] = { [IFLA_VXLAN_GBP] = { .type = NLA_FLAG, }, [IFLA_VXLAN_GPE] = { .type = NLA_FLAG, }, [IFLA_VXLAN_REMCSUM_NOPARTIAL] = { .type = NLA_FLAG }, + [IFLA_VXLAN_TTL_INHERIT] = { .type = NLA_FLAG }, }; static int vxlan_validate(struct nlattr *tb[], struct nlattr *data[], @@ -3254,6 +3259,12 @@ static int vxlan_nl2conf(struct nlattr *tb[], struct nlattr *data[], if (data[IFLA_VXLAN_TTL]) conf->ttl = nla_get_u8(data[IFLA_VXLAN_TTL]); + if (data[IFLA_VXLAN_TTL_INHERIT]) { + if (changelink) + return -EOPNOTSUPP; + conf->flags |= VXLAN_F_TTL_INHERIT; + } + if (data[IFLA_VXLAN_LABEL]) conf->label = nla_get_be32(data[IFLA_VXLAN_LABEL]) & IPV6_FLOWLABEL_MASK; diff --git a/drivers/ptp/ptp_pch.c b/drivers/ptp/ptp_pch.c index b3285175f20f..78ccf936d356 100644 --- a/drivers/ptp/ptp_pch.c +++ b/drivers/ptp/ptp_pch.c @@ -452,7 +452,6 @@ static int ptp_pch_adjtime(struct ptp_clock_info *ptp, s64 delta) static int ptp_pch_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) { u64 ns; - u32 remainder; unsigned long flags; struct pch_dev *pch_dev = container_of(ptp, struct pch_dev, caps); struct pch_ts_regs __iomem *regs = pch_dev->regs; @@ -461,8 +460,7 @@ static int ptp_pch_gettime(struct ptp_clock_info *ptp, struct timespec64 *ts) ns = pch_systime_read(regs); spin_unlock_irqrestore(&pch_dev->register_lock, flags); - ts->tv_sec = div_u64_rem(ns, 1000000000, &remainder); - ts->tv_nsec = remainder; + *ts = ns_to_timespec64(ns); return 0; } @@ -474,8 +472,7 @@ static int ptp_pch_settime(struct ptp_clock_info *ptp, struct pch_dev *pch_dev = container_of(ptp, struct pch_dev, caps); struct pch_ts_regs __iomem *regs = pch_dev->regs; - ns = ts->tv_sec * 1000000000ULL; - ns += ts->tv_nsec; + ns = timespec64_to_ns(ts); spin_lock_irqsave(&pch_dev->register_lock, flags); pch_systime_write(regs, ns); diff --git a/drivers/s390/net/lcs.c b/drivers/s390/net/lcs.c index 0ee8f33efb54..2d9fe7e4ee40 100644 --- a/drivers/s390/net/lcs.c +++ b/drivers/s390/net/lcs.c @@ -1928,6 +1928,8 @@ lcs_portno_store (struct device *dev, struct device_attribute *attr, const char return -EINVAL; /* TODO: sanity checks */ card->portno = value; + if (card->dev) + card->dev->dev_port = card->portno; return count; @@ -2158,6 +2160,7 @@ lcs_new_device(struct ccwgroup_device *ccwgdev) card->dev = dev; card->dev->ml_priv = card; card->dev->netdev_ops = &lcs_netdev_ops; + card->dev->dev_port = card->portno; memcpy(card->dev->dev_addr, card->mac, LCS_MAC_LENGTH); #ifdef CONFIG_IP_MULTICAST if (!lcs_check_multicast_support(card)) diff --git a/drivers/s390/net/qeth_core.h b/drivers/s390/net/qeth_core.h index 78b98b3e7efa..2a5fec55bf60 100644 --- a/drivers/s390/net/qeth_core.h +++ b/drivers/s390/net/qeth_core.h @@ -148,6 +148,7 @@ struct qeth_perf_stats { unsigned int tx_csum; unsigned int tx_lin; unsigned int tx_linfail; + unsigned int rx_csum; }; /* Routing stuff */ @@ -712,9 +713,6 @@ enum qeth_discipline_id { struct qeth_discipline { const struct device_type *devtype; - void (*start_poll)(struct ccw_device *, int, unsigned long); - qdio_handler_t *input_handler; - qdio_handler_t *output_handler; int (*process_rx_buffer)(struct qeth_card *card, int budget, int *done); int (*recover)(void *ptr); int (*setup) (struct ccwgroup_device *); @@ -780,9 +778,9 @@ struct qeth_card { struct qeth_card_options options; wait_queue_head_t wait_q; - spinlock_t vlanlock; spinlock_t mclock; unsigned long active_vlans[BITS_TO_LONGS(VLAN_N_VID)]; + struct mutex vid_list_mutex; /* vid_list */ struct list_head vid_list; DECLARE_HASHTABLE(mac_htable, 4); DECLARE_HASHTABLE(ip_htable, 4); @@ -867,6 +865,32 @@ static inline int qeth_get_ip_version(struct sk_buff *skb) } } +static inline void qeth_rx_csum(struct qeth_card *card, struct sk_buff *skb, + u8 flags) +{ + if ((card->dev->features & NETIF_F_RXCSUM) && + (flags & QETH_HDR_EXT_CSUM_TRANSP_REQ)) { + skb->ip_summed = CHECKSUM_UNNECESSARY; + if (card->options.performance_stats) + card->perf_stats.rx_csum++; + } else { + skb->ip_summed = CHECKSUM_NONE; + } +} + +static inline void qeth_tx_csum(struct sk_buff *skb, u8 *flags, int ipv) +{ + *flags |= QETH_HDR_EXT_CSUM_TRANSP_REQ; + if ((ipv == 4 && ip_hdr(skb)->protocol == IPPROTO_UDP) || + (ipv == 6 && ipv6_hdr(skb)->nexthdr == IPPROTO_UDP)) + *flags |= QETH_HDR_EXT_UDP; + if (ipv == 4) { + /* some HW requires combined L3+L4 csum offload: */ + *flags |= QETH_HDR_EXT_CSUM_HDR_REQ; + ip_hdr(skb)->check = 0; + } +} + static inline void qeth_put_buffer_pool_entry(struct qeth_card *card, struct qeth_buffer_pool_entry *entry) { @@ -879,6 +903,27 @@ static inline int qeth_is_diagass_supported(struct qeth_card *card, return card->info.diagass_support & (__u32)cmd; } +int qeth_send_simple_setassparms_prot(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + u16 cmd_code, long data, + enum qeth_prot_versions prot); +/* IPv4 variant */ +static inline int qeth_send_simple_setassparms(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + u16 cmd_code, long data) +{ + return qeth_send_simple_setassparms_prot(card, ipa_func, cmd_code, + data, QETH_PROT_IPV4); +} + +static inline int qeth_send_simple_setassparms_v6(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + u16 cmd_code, long data) +{ + return qeth_send_simple_setassparms_prot(card, ipa_func, cmd_code, + data, QETH_PROT_IPV6); +} + extern struct qeth_discipline qeth_l2_discipline; extern struct qeth_discipline qeth_l3_discipline; extern const struct attribute_group *qeth_generic_attr_groups[]; @@ -921,13 +966,7 @@ struct sk_buff *qeth_core_get_next_skb(struct qeth_card *, struct qeth_qdio_buffer *, struct qdio_buffer_element **, int *, struct qeth_hdr **); void qeth_schedule_recovery(struct qeth_card *); -void qeth_qdio_start_poll(struct ccw_device *, int, unsigned long); int qeth_poll(struct napi_struct *napi, int budget); -void qeth_qdio_input_handler(struct ccw_device *, - unsigned int, unsigned int, int, - int, unsigned long); -void qeth_qdio_output_handler(struct ccw_device *, unsigned int, - int, int, int, unsigned long); void qeth_clear_ipacmd_list(struct qeth_card *); int qeth_qdio_clear_card(struct qeth_card *, int); void qeth_clear_working_pool_list(struct qeth_card *); @@ -979,8 +1018,6 @@ int qeth_hw_trap(struct qeth_card *, enum qeth_diags_trap_action); int qeth_query_ipassists(struct qeth_card *, enum qeth_prot_versions prot); void qeth_trace_features(struct qeth_card *); void qeth_close_dev(struct qeth_card *); -int qeth_send_simple_setassparms(struct qeth_card *, enum qeth_ipa_funcs, - __u16, long); int qeth_send_setassparms(struct qeth_card *, struct qeth_cmd_buffer *, __u16, long, int (*reply_cb)(struct qeth_card *, diff --git a/drivers/s390/net/qeth_core_main.c b/drivers/s390/net/qeth_core_main.c index dffd820731f2..06415b6a8f68 100644 --- a/drivers/s390/net/qeth_core_main.c +++ b/drivers/s390/net/qeth_core_main.c @@ -1467,13 +1467,13 @@ static int qeth_setup_card(struct qeth_card *card) card->lan_online = 0; card->read_or_write_problem = 0; card->dev = NULL; - spin_lock_init(&card->vlanlock); spin_lock_init(&card->mclock); spin_lock_init(&card->lock); spin_lock_init(&card->ip_lock); spin_lock_init(&card->thread_mask_lock); mutex_init(&card->conf_mutex); mutex_init(&card->discipline_mutex); + mutex_init(&card->vid_list_mutex); card->thread_start_mask = 0; card->thread_allowed_mask = 0; card->thread_running_mask = 0; @@ -3588,15 +3588,14 @@ static void qeth_check_outbound_queue(struct qeth_qdio_out_q *queue) } } -void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue, - unsigned long card_ptr) +static void qeth_qdio_start_poll(struct ccw_device *ccwdev, int queue, + unsigned long card_ptr) { struct qeth_card *card = (struct qeth_card *)card_ptr; if (card->dev && (card->dev->flags & IFF_UP)) napi_schedule(&card->napi); } -EXPORT_SYMBOL_GPL(qeth_qdio_start_poll); int qeth_configure_cq(struct qeth_card *card, enum qeth_cq cq) { @@ -3698,9 +3697,10 @@ out: return; } -void qeth_qdio_input_handler(struct ccw_device *ccwdev, unsigned int qdio_err, - unsigned int queue, int first_elem, int count, - unsigned long card_ptr) +static void qeth_qdio_input_handler(struct ccw_device *ccwdev, + unsigned int qdio_err, int queue, + int first_elem, int count, + unsigned long card_ptr) { struct qeth_card *card = (struct qeth_card *)card_ptr; @@ -3711,14 +3711,12 @@ void qeth_qdio_input_handler(struct ccw_device *ccwdev, unsigned int qdio_err, qeth_qdio_cq_handler(card, qdio_err, queue, first_elem, count); else if (qdio_err) qeth_schedule_recovery(card); - - } -EXPORT_SYMBOL_GPL(qeth_qdio_input_handler); -void qeth_qdio_output_handler(struct ccw_device *ccwdev, - unsigned int qdio_error, int __queue, int first_element, - int count, unsigned long card_ptr) +static void qeth_qdio_output_handler(struct ccw_device *ccwdev, + unsigned int qdio_error, int __queue, + int first_element, int count, + unsigned long card_ptr) { struct qeth_card *card = (struct qeth_card *) card_ptr; struct qeth_qdio_out_q *queue = card->qdio.out_qs[__queue]; @@ -3787,7 +3785,6 @@ void qeth_qdio_output_handler(struct ccw_device *ccwdev, card->perf_stats.outbound_handler_time += qeth_get_micros() - card->perf_stats.outbound_handler_start_time; } -EXPORT_SYMBOL_GPL(qeth_qdio_output_handler); /* We cannot use outbound queue 3 for unicast packets on HiperSockets */ static inline int qeth_cut_iqd_prio(struct qeth_card *card, int queue_num) @@ -4995,7 +4992,7 @@ static int qeth_qdio_establish(struct qeth_card *card) goto out_free_in_sbals; } for (i = 0; i < card->qdio.no_in_queues; ++i) - queue_start_poll[i] = card->discipline->start_poll; + queue_start_poll[i] = qeth_qdio_start_poll; qeth_qdio_establish_cq(card, in_sbal_ptrs, queue_start_poll); @@ -5019,8 +5016,8 @@ static int qeth_qdio_establish(struct qeth_card *card) init_data.qib_param_field = qib_param_field; init_data.no_input_qs = card->qdio.no_in_queues; init_data.no_output_qs = card->qdio.no_out_queues; - init_data.input_handler = card->discipline->input_handler; - init_data.output_handler = card->discipline->output_handler; + init_data.input_handler = qeth_qdio_input_handler; + init_data.output_handler = qeth_qdio_output_handler; init_data.queue_start_poll_array = queue_start_poll; init_data.int_parm = (unsigned long) card; init_data.input_sbal_addr_array = (void **) in_sbal_ptrs; @@ -5204,6 +5201,11 @@ retriable: rc = qeth_query_ipassists(card, QETH_PROT_IPV4); if (rc == -ENOMEM) goto out; + if (qeth_is_supported(card, IPA_IPV6)) { + rc = qeth_query_ipassists(card, QETH_PROT_IPV6); + if (rc == -ENOMEM) + goto out; + } if (qeth_is_supported(card, IPA_SETADAPTERPARMS)) { rc = qeth_query_setadapterparms(card); if (rc < 0) { @@ -5511,26 +5513,26 @@ int qeth_send_setassparms(struct qeth_card *card, } EXPORT_SYMBOL_GPL(qeth_send_setassparms); -int qeth_send_simple_setassparms(struct qeth_card *card, - enum qeth_ipa_funcs ipa_func, - __u16 cmd_code, long data) +int qeth_send_simple_setassparms_prot(struct qeth_card *card, + enum qeth_ipa_funcs ipa_func, + u16 cmd_code, long data, + enum qeth_prot_versions prot) { int rc; int length = 0; struct qeth_cmd_buffer *iob; - QETH_CARD_TEXT(card, 4, "simassp4"); + QETH_CARD_TEXT_(card, 4, "simassp%i", prot); if (data) length = sizeof(__u32); - iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, - length, QETH_PROT_IPV4); + iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, length, prot); if (!iob) return -ENOMEM; rc = qeth_send_setassparms(card, iob, length, data, qeth_setassparms_cb, NULL); return rc; } -EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms); +EXPORT_SYMBOL_GPL(qeth_send_simple_setassparms_prot); static void qeth_unregister_dbf_views(void) { @@ -6008,7 +6010,8 @@ static struct { {"tx lin"}, {"tx linfail"}, {"cq handler count"}, - {"cq handler time"} + {"cq handler time"}, + {"rx csum"} }; int qeth_core_get_sset_count(struct net_device *dev, int stringset) @@ -6070,6 +6073,7 @@ void qeth_core_get_ethtool_stats(struct net_device *dev, data[35] = card->perf_stats.tx_linfail; data[36] = card->perf_stats.cq_cnt; data[37] = card->perf_stats.cq_time; + data[38] = card->perf_stats.rx_csum; } EXPORT_SYMBOL_GPL(qeth_core_get_ethtool_stats); @@ -6326,14 +6330,15 @@ static int qeth_ipa_checksum_run_cmd_cb(struct qeth_card *card, static int qeth_ipa_checksum_run_cmd(struct qeth_card *card, enum qeth_ipa_funcs ipa_func, __u16 cmd_code, long data, - struct qeth_checksum_cmd *chksum_cb) + struct qeth_checksum_cmd *chksum_cb, + enum qeth_prot_versions prot) { struct qeth_cmd_buffer *iob; int rc = -ENOMEM; QETH_CARD_TEXT(card, 4, "chkdocmd"); iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, - sizeof(__u32), QETH_PROT_IPV4); + sizeof(__u32), prot); if (iob) rc = qeth_send_setassparms(card, iob, sizeof(__u32), data, qeth_ipa_checksum_run_cmd_cb, @@ -6341,16 +6346,17 @@ static int qeth_ipa_checksum_run_cmd(struct qeth_card *card, return rc; } -static int qeth_send_checksum_on(struct qeth_card *card, int cstype) +static int qeth_send_checksum_on(struct qeth_card *card, int cstype, + enum qeth_prot_versions prot) { - const __u32 required_features = QETH_IPA_CHECKSUM_IP_HDR | - QETH_IPA_CHECKSUM_UDP | - QETH_IPA_CHECKSUM_TCP; + u32 required_features = QETH_IPA_CHECKSUM_UDP | QETH_IPA_CHECKSUM_TCP; struct qeth_checksum_cmd chksum_cb; int rc; + if (prot == QETH_PROT_IPV4) + required_features |= QETH_IPA_CHECKSUM_IP_HDR; rc = qeth_ipa_checksum_run_cmd(card, cstype, IPA_CMD_ASS_START, 0, - &chksum_cb); + &chksum_cb, prot); if (!rc) { if ((required_features & chksum_cb.supported) != required_features) @@ -6362,37 +6368,42 @@ static int qeth_send_checksum_on(struct qeth_card *card, int cstype) QETH_CARD_IFNAME(card)); } if (rc) { - qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_STOP, 0); + qeth_send_simple_setassparms_prot(card, cstype, + IPA_CMD_ASS_STOP, 0, prot); dev_warn(&card->gdev->dev, - "Starting HW checksumming for %s failed, using SW checksumming\n", - QETH_CARD_IFNAME(card)); + "Starting HW IPv%d checksumming for %s failed, using SW checksumming\n", + prot, QETH_CARD_IFNAME(card)); return rc; } rc = qeth_ipa_checksum_run_cmd(card, cstype, IPA_CMD_ASS_ENABLE, - chksum_cb.supported, &chksum_cb); + chksum_cb.supported, &chksum_cb, + prot); if (!rc) { if ((required_features & chksum_cb.enabled) != required_features) rc = -EIO; } if (rc) { - qeth_send_simple_setassparms(card, cstype, IPA_CMD_ASS_STOP, 0); + qeth_send_simple_setassparms_prot(card, cstype, + IPA_CMD_ASS_STOP, 0, prot); dev_warn(&card->gdev->dev, - "Enabling HW checksumming for %s failed, using SW checksumming\n", - QETH_CARD_IFNAME(card)); + "Enabling HW IPv%d checksumming for %s failed, using SW checksumming\n", + prot, QETH_CARD_IFNAME(card)); return rc; } - dev_info(&card->gdev->dev, "HW Checksumming (%sbound) enabled\n", - cstype == IPA_INBOUND_CHECKSUM ? "in" : "out"); + dev_info(&card->gdev->dev, "HW Checksumming (%sbound IPv%d) enabled\n", + cstype == IPA_INBOUND_CHECKSUM ? "in" : "out", prot); return 0; } -static int qeth_set_ipa_csum(struct qeth_card *card, int on, int cstype) +static int qeth_set_ipa_csum(struct qeth_card *card, bool on, int cstype, + enum qeth_prot_versions prot) { - int rc = (on) ? qeth_send_checksum_on(card, cstype) - : qeth_send_simple_setassparms(card, cstype, - IPA_CMD_ASS_STOP, 0); + int rc = (on) ? qeth_send_checksum_on(card, cstype, prot) + : qeth_send_simple_setassparms_prot(card, cstype, + IPA_CMD_ASS_STOP, 0, + prot); return rc ? -EIO : 0; } @@ -6419,8 +6430,31 @@ static int qeth_set_ipa_tso(struct qeth_card *card, int on) return rc; } -#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO) +static int qeth_set_ipa_rx_csum(struct qeth_card *card, bool on) +{ + int rc_ipv4 = (on) ? -EOPNOTSUPP : 0; + int rc_ipv6; + + if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) + rc_ipv4 = qeth_set_ipa_csum(card, on, IPA_INBOUND_CHECKSUM, + QETH_PROT_IPV4); + if (!qeth_is_supported6(card, IPA_INBOUND_CHECKSUM_V6)) + /* no/one Offload Assist available, so the rc is trivial */ + return rc_ipv4; + rc_ipv6 = qeth_set_ipa_csum(card, on, IPA_INBOUND_CHECKSUM, + QETH_PROT_IPV6); + + if (on) + /* enable: success if any Assist is active */ + return (rc_ipv6) ? rc_ipv4 : 0; + + /* disable: failure if any Assist is still active */ + return (rc_ipv6) ? rc_ipv6 : rc_ipv4; +} + +#define QETH_HW_FEATURES (NETIF_F_RXCSUM | NETIF_F_IP_CSUM | NETIF_F_TSO | \ + NETIF_F_IPV6_CSUM) /** * qeth_recover_features() - Restore device features after recovery * @dev: the recovering net_device @@ -6455,16 +6489,19 @@ int qeth_set_features(struct net_device *dev, netdev_features_t features) QETH_DBF_HEX(SETUP, 2, &features, sizeof(features)); if ((changed & NETIF_F_IP_CSUM)) { - rc = qeth_set_ipa_csum(card, - features & NETIF_F_IP_CSUM ? 1 : 0, - IPA_OUTBOUND_CHECKSUM); + rc = qeth_set_ipa_csum(card, features & NETIF_F_IP_CSUM, + IPA_OUTBOUND_CHECKSUM, QETH_PROT_IPV4); if (rc) changed ^= NETIF_F_IP_CSUM; } - if ((changed & NETIF_F_RXCSUM)) { - rc = qeth_set_ipa_csum(card, - features & NETIF_F_RXCSUM ? 1 : 0, - IPA_INBOUND_CHECKSUM); + if (changed & NETIF_F_IPV6_CSUM) { + rc = qeth_set_ipa_csum(card, features & NETIF_F_IPV6_CSUM, + IPA_OUTBOUND_CHECKSUM, QETH_PROT_IPV6); + if (rc) + changed ^= NETIF_F_IPV6_CSUM; + } + if (changed & NETIF_F_RXCSUM) { + rc = qeth_set_ipa_rx_csum(card, features & NETIF_F_RXCSUM); if (rc) changed ^= NETIF_F_RXCSUM; } @@ -6491,7 +6528,10 @@ netdev_features_t qeth_fix_features(struct net_device *dev, QETH_DBF_TEXT(SETUP, 2, "fixfeat"); if (!qeth_is_supported(card, IPA_OUTBOUND_CHECKSUM)) features &= ~NETIF_F_IP_CSUM; - if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) + if (!qeth_is_supported6(card, IPA_OUTBOUND_CHECKSUM_V6)) + features &= ~NETIF_F_IPV6_CSUM; + if (!qeth_is_supported(card, IPA_INBOUND_CHECKSUM) && + !qeth_is_supported6(card, IPA_INBOUND_CHECKSUM_V6)) features &= ~NETIF_F_RXCSUM; if (!qeth_is_supported(card, IPA_OUTBOUND_TSO)) features &= ~NETIF_F_TSO; diff --git a/drivers/s390/net/qeth_core_mpc.h b/drivers/s390/net/qeth_core_mpc.h index f4d1ec0b8f5a..878e62f35169 100644 --- a/drivers/s390/net/qeth_core_mpc.h +++ b/drivers/s390/net/qeth_core_mpc.h @@ -246,6 +246,8 @@ enum qeth_ipa_funcs { IPA_QUERY_ARP_ASSIST = 0x00040000L, IPA_INBOUND_TSO = 0x00080000L, IPA_OUTBOUND_TSO = 0x00100000L, + IPA_INBOUND_CHECKSUM_V6 = 0x00400000L, + IPA_OUTBOUND_CHECKSUM_V6 = 0x00800000L, }; /* SETIP/DELIP IPA Command: ***************************************************/ diff --git a/drivers/s390/net/qeth_core_sys.c b/drivers/s390/net/qeth_core_sys.c index ae81534de912..c3f18afb368b 100644 --- a/drivers/s390/net/qeth_core_sys.c +++ b/drivers/s390/net/qeth_core_sys.c @@ -144,6 +144,8 @@ static ssize_t qeth_dev_portno_store(struct device *dev, goto out; } card->info.portno = portno; + if (card->dev) + card->dev->dev_port = portno; out: mutex_unlock(&card->conf_mutex); return rc ? rc : count; diff --git a/drivers/s390/net/qeth_l2_main.c b/drivers/s390/net/qeth_l2_main.c index b8079f2a65b3..a7cb37da6a21 100644 --- a/drivers/s390/net/qeth_l2_main.c +++ b/drivers/s390/net/qeth_l2_main.c @@ -17,7 +17,6 @@ #include <linux/kernel.h> #include <linux/slab.h> #include <linux/etherdevice.h> -#include <linux/ip.h> #include <linux/list.h> #include <linux/hash.h> #include <linux/hashtable.h> @@ -195,23 +194,6 @@ static int qeth_l2_get_cast_type(struct qeth_card *card, struct sk_buff *skb) return RTN_UNSPEC; } -static void qeth_l2_hdr_csum(struct qeth_card *card, struct qeth_hdr *hdr, - struct sk_buff *skb) -{ - struct iphdr *iph = ip_hdr(skb); - - /* tcph->check contains already the pseudo hdr checksum - * so just set the header flags - */ - if (iph->protocol == IPPROTO_UDP) - hdr->hdr.l2.flags[1] |= QETH_HDR_EXT_UDP; - hdr->hdr.l2.flags[1] |= QETH_HDR_EXT_CSUM_TRANSP_REQ | - QETH_HDR_EXT_CSUM_HDR_REQ; - iph->check = 0; - if (card->options.performance_stats) - card->perf_stats.tx_csum++; -} - static void qeth_l2_fill_header(struct qeth_hdr *hdr, struct sk_buff *skb, int cast_type, unsigned int data_len) { @@ -297,12 +279,13 @@ static int qeth_l2_send_setdelvlan(struct qeth_card *card, __u16 i, static void qeth_l2_process_vlans(struct qeth_card *card) { struct qeth_vlan_vid *id; + QETH_CARD_TEXT(card, 3, "L2prcvln"); - spin_lock_bh(&card->vlanlock); + mutex_lock(&card->vid_list_mutex); list_for_each_entry(id, &card->vid_list, list) { qeth_l2_send_setdelvlan(card, id->vid, IPA_CMD_SETVLAN); } - spin_unlock_bh(&card->vlanlock); + mutex_unlock(&card->vid_list_mutex); } static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, @@ -319,7 +302,7 @@ static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, QETH_CARD_TEXT(card, 3, "aidREC"); return 0; } - id = kmalloc(sizeof(struct qeth_vlan_vid), GFP_ATOMIC); + id = kmalloc(sizeof(*id), GFP_KERNEL); if (id) { id->vid = vid; rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_SETVLAN); @@ -327,9 +310,9 @@ static int qeth_l2_vlan_rx_add_vid(struct net_device *dev, kfree(id); return rc; } - spin_lock_bh(&card->vlanlock); + mutex_lock(&card->vid_list_mutex); list_add_tail(&id->list, &card->vid_list); - spin_unlock_bh(&card->vlanlock); + mutex_unlock(&card->vid_list_mutex); } else { return -ENOMEM; } @@ -348,7 +331,7 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, QETH_CARD_TEXT(card, 3, "kidREC"); return 0; } - spin_lock_bh(&card->vlanlock); + mutex_lock(&card->vid_list_mutex); list_for_each_entry(id, &card->vid_list, list) { if (id->vid == vid) { list_del(&id->list); @@ -356,7 +339,7 @@ static int qeth_l2_vlan_rx_kill_vid(struct net_device *dev, break; } } - spin_unlock_bh(&card->vlanlock); + mutex_unlock(&card->vid_list_mutex); if (tmpid) { rc = qeth_l2_send_setdelvlan(card, vid, IPA_CMD_DELVLAN); kfree(tmpid); @@ -423,15 +406,7 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, switch (hdr->hdr.l2.id) { case QETH_HEADER_TYPE_LAYER2: skb->protocol = eth_type_trans(skb, skb->dev); - if ((card->dev->features & NETIF_F_RXCSUM) - && ((hdr->hdr.l2.flags[1] & - (QETH_HDR_EXT_CSUM_HDR_REQ | - QETH_HDR_EXT_CSUM_TRANSP_REQ)) == - (QETH_HDR_EXT_CSUM_HDR_REQ | - QETH_HDR_EXT_CSUM_TRANSP_REQ))) - skb->ip_summed = CHECKSUM_UNNECESSARY; - else - skb->ip_summed = CHECKSUM_NONE; + qeth_rx_csum(card, skb, hdr->hdr.l2.flags[1]); if (skb->protocol == htons(ETH_P_802_2)) *((__u32 *)skb->cb) = ++card->seqno.pkt_seqno; len = skb->len; @@ -464,7 +439,6 @@ static int qeth_l2_process_inbound_buffer(struct qeth_card *card, static int qeth_l2_request_initial_mac(struct qeth_card *card) { int rc = 0; - char vendor_pre[] = {0x02, 0x00, 0x00}; QETH_DBF_TEXT(SETUP, 2, "l2reqmac"); QETH_DBF_TEXT_(SETUP, 2, "doL2%s", CARD_BUS_ID(card)); @@ -484,16 +458,20 @@ static int qeth_l2_request_initial_mac(struct qeth_card *card) card->info.type == QETH_CARD_TYPE_OSX || card->info.guestlan) { rc = qeth_setadpparms_change_macaddr(card); - if (rc) { - QETH_DBF_MESSAGE(2, "couldn't get MAC address on " - "device %s: x%x\n", CARD_BUS_ID(card), rc); - QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc); - return rc; - } - } else { - eth_random_addr(card->dev->dev_addr); - memcpy(card->dev->dev_addr, vendor_pre, 3); + if (!rc) + goto out; + QETH_DBF_MESSAGE(2, "READ_MAC Assist failed on device %s: x%x\n", + CARD_BUS_ID(card), rc); + QETH_DBF_TEXT_(SETUP, 2, "1err%04x", rc); + /* fall back once more: */ } + + /* some devices don't support a custom MAC address: */ + if (card->info.type == QETH_CARD_TYPE_OSM || + card->info.type == QETH_CARD_TYPE_OSX) + return (rc) ? rc : -EADDRNOTAVAIL; + eth_hw_addr_random(card->dev); + out: QETH_DBF_HEX(SETUP, 2, card->dev->dev_addr, card->dev->addr_len); return 0; @@ -685,7 +663,8 @@ out: } static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb, - struct qeth_qdio_out_q *queue, int cast_type) + struct qeth_qdio_out_q *queue, int cast_type, + int ipv) { int push_len = sizeof(struct qeth_hdr); unsigned int elements, nr_frags; @@ -723,8 +702,11 @@ static int qeth_l2_xmit_osa(struct qeth_card *card, struct sk_buff *skb, hdr_elements = 1; } qeth_l2_fill_header(hdr, skb, cast_type, skb->len - push_len); - if (skb->ip_summed == CHECKSUM_PARTIAL) - qeth_l2_hdr_csum(card, hdr, skb); + if (skb->ip_summed == CHECKSUM_PARTIAL) { + qeth_tx_csum(skb, &hdr->hdr.l2.flags[1], ipv); + if (card->options.performance_stats) + card->perf_stats.tx_csum++; + } elements = qeth_get_elements_no(card, skb, hdr_elements, 0); if (!elements) { @@ -776,6 +758,7 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, { struct qeth_card *card = dev->ml_priv; int cast_type = qeth_l2_get_cast_type(card, skb); + int ipv = qeth_get_ip_version(skb); struct qeth_qdio_out_q *queue; int tx_bytes = skb->len; int rc; @@ -783,7 +766,7 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, if (card->qdio.do_prio_queueing || (cast_type && card->info.is_multicast_different)) queue = card->qdio.out_qs[qeth_get_priority_queue(card, skb, - qeth_get_ip_version(skb), cast_type)]; + ipv, cast_type)]; else queue = card->qdio.out_qs[card->qdio.default_out_queue]; @@ -806,7 +789,7 @@ static netdev_tx_t qeth_l2_hard_start_xmit(struct sk_buff *skb, rc = qeth_l2_xmit_iqd(card, skb, queue, cast_type); break; default: - rc = qeth_l2_xmit_osa(card, skb, queue, cast_type); + rc = qeth_l2_xmit_osa(card, skb, queue, cast_type, ipv); } if (!rc) { @@ -983,6 +966,7 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) card->dev->mtu = card->info.initial_mtu; card->dev->min_mtu = 64; card->dev->max_mtu = ETH_MAX_MTU; + card->dev->dev_port = card->info.portno; card->dev->netdev_ops = &qeth_l2_netdev_ops; if (card->info.type == QETH_CARD_TYPE_OSN) { card->dev->ethtool_ops = &qeth_l2_osn_ops; @@ -1011,10 +995,15 @@ static int qeth_l2_setup_netdev(struct qeth_card *card) card->dev->hw_features |= NETIF_F_IP_CSUM; card->dev->vlan_features |= NETIF_F_IP_CSUM; } - if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM)) { - card->dev->hw_features |= NETIF_F_RXCSUM; - card->dev->vlan_features |= NETIF_F_RXCSUM; - } + } + if (qeth_is_supported6(card, IPA_OUTBOUND_CHECKSUM_V6)) { + card->dev->hw_features |= NETIF_F_IPV6_CSUM; + card->dev->vlan_features |= NETIF_F_IPV6_CSUM; + } + if (qeth_is_supported(card, IPA_INBOUND_CHECKSUM) || + qeth_is_supported6(card, IPA_INBOUND_CHECKSUM_V6)) { + card->dev->hw_features |= NETIF_F_RXCSUM; + card->dev->vlan_features |= NETIF_F_RXCSUM; } card->info.broadcast_capable = 1; @@ -1315,9 +1304,6 @@ static int qeth_l2_control_event(struct qeth_card *card, struct qeth_discipline qeth_l2_discipline = { .devtype = &qeth_l2_devtype, - .start_poll = qeth_qdio_start_poll, - .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, - .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, .process_rx_buffer = qeth_l2_process_inbound_buffer, .recover = qeth_l2_recover, .setup = qeth_l2_probe_device, diff --git a/drivers/s390/net/qeth_l3_main.c b/drivers/s390/net/qeth_l3_main.c index c1a16a74aa83..e7fa479adf47 100644 --- a/drivers/s390/net/qeth_l3_main.c +++ b/drivers/s390/net/qeth_l3_main.c @@ -735,22 +735,6 @@ static int qeth_l3_setadapter_parms(struct qeth_card *card) return rc; } -static int qeth_l3_send_simple_setassparms_ipv6(struct qeth_card *card, - enum qeth_ipa_funcs ipa_func, __u16 cmd_code) -{ - int rc; - struct qeth_cmd_buffer *iob; - - QETH_CARD_TEXT(card, 4, "simassp6"); - iob = qeth_get_setassparms_cmd(card, ipa_func, cmd_code, - 0, QETH_PROT_IPV6); - if (!iob) - return -ENOMEM; - rc = qeth_send_setassparms(card, iob, 0, 0, - qeth_setassparms_cb, NULL); - return rc; -} - static int qeth_l3_start_ipa_arp_processing(struct qeth_card *card) { int rc; @@ -851,14 +835,6 @@ static int qeth_l3_softsetup_ipv6(struct qeth_card *card) QETH_CARD_TEXT(card, 3, "softipv6"); - rc = qeth_query_ipassists(card, QETH_PROT_IPV6); - if (rc) { - dev_err(&card->gdev->dev, - "Activating IPv6 support for %s failed\n", - QETH_CARD_IFNAME(card)); - return rc; - } - if (card->info.type == QETH_CARD_TYPE_IQD) goto out; @@ -870,16 +846,16 @@ static int qeth_l3_softsetup_ipv6(struct qeth_card *card) QETH_CARD_IFNAME(card)); return rc; } - rc = qeth_l3_send_simple_setassparms_ipv6(card, IPA_IPV6, - IPA_CMD_ASS_START); + rc = qeth_send_simple_setassparms_v6(card, IPA_IPV6, + IPA_CMD_ASS_START, 0); if (rc) { dev_err(&card->gdev->dev, "Activating IPv6 support for %s failed\n", QETH_CARD_IFNAME(card)); return rc; } - rc = qeth_l3_send_simple_setassparms_ipv6(card, IPA_PASSTHRU, - IPA_CMD_ASS_START); + rc = qeth_send_simple_setassparms_v6(card, IPA_PASSTHRU, + IPA_CMD_ASS_START, 0); if (rc) { dev_warn(&card->gdev->dev, "Enabling the passthrough mode for %s failed\n", @@ -1293,91 +1269,6 @@ static void qeth_l3_add_multicast_ipv6(struct qeth_card *card) in6_dev_put(in6_dev); } -static void qeth_l3_free_vlan_addresses4(struct qeth_card *card, - unsigned short vid) -{ - struct in_device *in_dev; - struct in_ifaddr *ifa; - struct qeth_ipaddr *addr; - struct net_device *netdev; - - QETH_CARD_TEXT(card, 4, "frvaddr4"); - - netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid); - if (!netdev) - return; - in_dev = in_dev_get(netdev); - if (!in_dev) - return; - - addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV4); - if (!addr) - goto out; - - spin_lock_bh(&card->ip_lock); - - for (ifa = in_dev->ifa_list; ifa; ifa = ifa->ifa_next) { - addr->u.a4.addr = be32_to_cpu(ifa->ifa_address); - addr->u.a4.mask = be32_to_cpu(ifa->ifa_mask); - addr->type = QETH_IP_TYPE_NORMAL; - qeth_l3_delete_ip(card, addr); - } - - spin_unlock_bh(&card->ip_lock); - - kfree(addr); -out: - in_dev_put(in_dev); -} - -static void qeth_l3_free_vlan_addresses6(struct qeth_card *card, - unsigned short vid) -{ - struct inet6_dev *in6_dev; - struct inet6_ifaddr *ifa; - struct qeth_ipaddr *addr; - struct net_device *netdev; - - QETH_CARD_TEXT(card, 4, "frvaddr6"); - - netdev = __vlan_find_dev_deep_rcu(card->dev, htons(ETH_P_8021Q), vid); - if (!netdev) - return; - - in6_dev = in6_dev_get(netdev); - if (!in6_dev) - return; - - addr = qeth_l3_get_addr_buffer(QETH_PROT_IPV6); - if (!addr) - goto out; - - spin_lock_bh(&card->ip_lock); - - list_for_each_entry(ifa, &in6_dev->addr_list, if_list) { - memcpy(&addr->u.a6.addr, &ifa->addr, - sizeof(struct in6_addr)); - addr->u.a6.pfxlen = ifa->prefix_len; - addr->type = QETH_IP_TYPE_NORMAL; - qeth_l3_delete_ip(card, addr); - } - - spin_unlock_bh(&card->ip_lock); - - kfree(addr); -out: - in6_dev_put(in6_dev); -} - -static void qeth_l3_free_vlan_addresses(struct qeth_card *card, - unsigned short vid) -{ - rcu_read_lock(); - qeth_l3_free_vlan_addresses4(card, vid); - qeth_l3_free_vlan_addresses6(card, vid); - rcu_read_unlock(); -} - static int qeth_l3_vlan_rx_add_vid(struct net_device *dev, __be16 proto, u16 vid) { @@ -1398,8 +1289,6 @@ static int qeth_l3_vlan_rx_kill_vid(struct net_device *dev, QETH_CARD_TEXT(card, 3, "kidREC"); return 0; } - /* unregister IP addresses of vlan device */ - qeth_l3_free_vlan_addresses(card, vid); clear_bit(vid, card->active_vlans); qeth_l3_set_rx_mode(dev); return 0; @@ -1454,17 +1343,7 @@ static void qeth_l3_rebuild_skb(struct qeth_card *card, struct sk_buff *skb, __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), tag); } - if (card->dev->features & NETIF_F_RXCSUM) { - if ((hdr->hdr.l3.ext_flags & - (QETH_HDR_EXT_CSUM_HDR_REQ | - QETH_HDR_EXT_CSUM_TRANSP_REQ)) == - (QETH_HDR_EXT_CSUM_HDR_REQ | - QETH_HDR_EXT_CSUM_TRANSP_REQ)) - skb->ip_summed = CHECKSUM_UNNECESSARY; - else - skb->ip_summed = CHECKSUM_NONE; - } else - skb->ip_summed = CHECKSUM_NONE; + qeth_rx_csum(card, skb, hdr->hdr.l3.ext_flags); } static int qeth_l3_process_inbound_buffer(struct qeth_card *card, @@ -2210,23 +2089,6 @@ static void qeth_l3_fill_header(struct qeth_card *card, struct qeth_hdr *hdr, rcu_read_unlock(); } -static void qeth_l3_hdr_csum(struct qeth_card *card, struct qeth_hdr *hdr, - struct sk_buff *skb) -{ - struct iphdr *iph = ip_hdr(skb); - - /* tcph->check contains already the pseudo hdr checksum - * so just set the header flags - */ - if (iph->protocol == IPPROTO_UDP) - hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_UDP; - hdr->hdr.l3.ext_flags |= QETH_HDR_EXT_CSUM_TRANSP_REQ | - QETH_HDR_EXT_CSUM_HDR_REQ; - iph->check = 0; - if (card->options.performance_stats) - card->perf_stats.tx_csum++; -} - static void qeth_tso_fill_header(struct qeth_card *card, struct qeth_hdr *qhdr, struct sk_buff *skb) { @@ -2418,8 +2280,11 @@ static netdev_tx_t qeth_l3_hard_start_xmit(struct sk_buff *skb, } } - if (skb->ip_summed == CHECKSUM_PARTIAL) - qeth_l3_hdr_csum(card, hdr, new_skb); + if (new_skb->ip_summed == CHECKSUM_PARTIAL) { + qeth_tx_csum(new_skb, &hdr->hdr.l3.ext_flags, ipv); + if (card->options.performance_stats) + card->perf_stats.tx_csum++; + } } elements = use_tso ? @@ -2620,28 +2485,32 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) (card->info.link_type == QETH_LINK_TYPE_HSTR)) { pr_info("qeth_l3: ignoring TR device\n"); return -ENODEV; - } else { - card->dev = alloc_etherdev(0); - if (!card->dev) - return -ENODEV; - card->dev->netdev_ops = &qeth_l3_osa_netdev_ops; - - /*IPv6 address autoconfiguration stuff*/ - qeth_l3_get_unique_id(card); - if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD)) - card->dev->dev_id = card->info.unique_id & - 0xffff; - - card->dev->hw_features |= NETIF_F_SG; - card->dev->vlan_features |= NETIF_F_SG; - - if (!card->info.guestlan) { - card->dev->features |= NETIF_F_SG; - card->dev->hw_features |= NETIF_F_TSO | - NETIF_F_RXCSUM | NETIF_F_IP_CSUM; - card->dev->vlan_features |= NETIF_F_TSO | - NETIF_F_RXCSUM | NETIF_F_IP_CSUM; - } + } + + card->dev = alloc_etherdev(0); + if (!card->dev) + return -ENODEV; + card->dev->netdev_ops = &qeth_l3_osa_netdev_ops; + + /*IPv6 address autoconfiguration stuff*/ + qeth_l3_get_unique_id(card); + if (!(card->info.unique_id & UNIQUE_ID_NOT_BY_CARD)) + card->dev->dev_id = card->info.unique_id & 0xffff; + + card->dev->hw_features |= NETIF_F_SG; + card->dev->vlan_features |= NETIF_F_SG; + + if (!card->info.guestlan) { + card->dev->features |= NETIF_F_SG; + card->dev->hw_features |= NETIF_F_TSO | + NETIF_F_RXCSUM | NETIF_F_IP_CSUM; + card->dev->vlan_features |= NETIF_F_TSO | + NETIF_F_RXCSUM | NETIF_F_IP_CSUM; + } + + if (qeth_is_supported6(card, IPA_OUTBOUND_CHECKSUM_V6)) { + card->dev->hw_features |= NETIF_F_IPV6_CSUM; + card->dev->vlan_features |= NETIF_F_IPV6_CSUM; } } else if (card->info.type == QETH_CARD_TYPE_IQD) { card->dev = alloc_netdev(0, "hsi%d", NET_NAME_UNKNOWN, @@ -2663,6 +2532,7 @@ static int qeth_l3_setup_netdev(struct qeth_card *card) card->dev->mtu = card->info.initial_mtu; card->dev->min_mtu = 64; card->dev->max_mtu = ETH_MAX_MTU; + card->dev->dev_port = card->info.portno; card->dev->ethtool_ops = &qeth_l3_ethtool_ops; card->dev->features |= NETIF_F_HW_VLAN_CTAG_TX | NETIF_F_HW_VLAN_CTAG_RX | @@ -2960,9 +2830,6 @@ static int qeth_l3_control_event(struct qeth_card *card, struct qeth_discipline qeth_l3_discipline = { .devtype = &qeth_l3_devtype, - .start_poll = qeth_qdio_start_poll, - .input_handler = (qdio_handler_t *) qeth_qdio_input_handler, - .output_handler = (qdio_handler_t *) qeth_qdio_output_handler, .process_rx_buffer = qeth_l3_process_inbound_buffer, .recover = qeth_l3_recover, .setup = qeth_l3_probe_device, diff --git a/drivers/scsi/qedf/qedf_fip.c b/drivers/scsi/qedf/qedf_fip.c index 773558fc0697..16d1a21cdff9 100644 --- a/drivers/scsi/qedf/qedf_fip.c +++ b/drivers/scsi/qedf/qedf_fip.c @@ -23,6 +23,7 @@ void qedf_fcoe_send_vlan_req(struct qedf_ctx *qedf) struct fip_vlan *vlan; #define MY_FIP_ALL_FCF_MACS ((__u8[6]) { 1, 0x10, 0x18, 1, 0, 2 }) static u8 my_fcoe_all_fcfs[ETH_ALEN] = MY_FIP_ALL_FCF_MACS; + unsigned long flags = 0; skb = dev_alloc_skb(sizeof(struct fip_vlan)); if (!skb) @@ -65,7 +66,9 @@ void qedf_fcoe_send_vlan_req(struct qedf_ctx *qedf) kfree_skb(skb); return; } - qed_ops->ll2->start_xmit(qedf->cdev, skb); + + set_bit(QED_LL2_XMIT_FLAGS_FIP_DISCOVERY, &flags); + qed_ops->ll2->start_xmit(qedf->cdev, skb, flags); } static void qedf_fcoe_process_vlan_resp(struct qedf_ctx *qedf, @@ -139,7 +142,7 @@ void qedf_fip_send(struct fcoe_ctlr *fip, struct sk_buff *skb) print_hex_dump(KERN_WARNING, "fip ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, skb->len, false); - qed_ops->ll2->start_xmit(qedf->cdev, skb); + qed_ops->ll2->start_xmit(qedf->cdev, skb, 0); } /* Process incoming FIP frames. */ diff --git a/drivers/scsi/qedf/qedf_main.c b/drivers/scsi/qedf/qedf_main.c index 284ccb566b19..6c19015975a8 100644 --- a/drivers/scsi/qedf/qedf_main.c +++ b/drivers/scsi/qedf/qedf_main.c @@ -994,7 +994,7 @@ static int qedf_xmit(struct fc_lport *lport, struct fc_frame *fp) if (qedf_dump_frames) print_hex_dump(KERN_WARNING, "fcoe: ", DUMP_PREFIX_OFFSET, 16, 1, skb->data, skb->len, false); - qed_ops->ll2->start_xmit(qedf->cdev, skb); + qed_ops->ll2->start_xmit(qedf->cdev, skb, 0); return 0; } diff --git a/drivers/scsi/qedi/qedi_iscsi.c b/drivers/scsi/qedi/qedi_iscsi.c index 7ec7f6e00fb8..ff21aa1fd939 100644 --- a/drivers/scsi/qedi/qedi_iscsi.c +++ b/drivers/scsi/qedi/qedi_iscsi.c @@ -1150,7 +1150,7 @@ static int qedi_data_avail(struct qedi_ctx *qedi, u16 vlanid) if (vlanid) __vlan_hwaccel_put_tag(skb, htons(ETH_P_8021Q), vlanid); - rc = qedi_ops->ll2->start_xmit(cdev, skb); + rc = qedi_ops->ll2->start_xmit(cdev, skb, 0); if (rc) { QEDI_ERR(&qedi->dbg_ctx, "ll2 start_xmit returned %d\n", rc); diff --git a/drivers/soc/ti/knav_dma.c b/drivers/soc/ti/knav_dma.c index 026182d3b27c..224d7ddeeb76 100644 --- a/drivers/soc/ti/knav_dma.c +++ b/drivers/soc/ti/knav_dma.c @@ -134,6 +134,13 @@ struct knav_dma_chan { static struct knav_dma_pool_device *kdev; +static bool device_ready; +bool knav_dma_device_ready(void) +{ + return device_ready; +} +EXPORT_SYMBOL_GPL(knav_dma_device_ready); + static bool check_config(struct knav_dma_chan *chan, struct knav_dma_cfg *cfg) { if (!memcmp(&chan->cfg, cfg, sizeof(*cfg))) @@ -773,6 +780,7 @@ static int knav_dma_probe(struct platform_device *pdev) debugfs_create_file("knav_dma", S_IFREG | S_IRUGO, NULL, NULL, &knav_dma_debug_ops); + device_ready = true; return ret; } diff --git a/drivers/soc/ti/knav_qmss.h b/drivers/soc/ti/knav_qmss.h index 905b974d1bdc..56866ba4cfc4 100644 --- a/drivers/soc/ti/knav_qmss.h +++ b/drivers/soc/ti/knav_qmss.h @@ -292,6 +292,11 @@ struct knav_queue { struct list_head list; }; +enum qmss_version { + QMSS, + QMSS_66AK2G, +}; + struct knav_device { struct device *dev; unsigned base_id; @@ -305,6 +310,7 @@ struct knav_device { struct list_head pools; struct list_head pdsps; struct list_head qmgrs; + enum qmss_version version; }; struct knav_range_ops { diff --git a/drivers/soc/ti/knav_qmss_queue.c b/drivers/soc/ti/knav_qmss_queue.c index 77d6b5c03aae..419365a8d1c2 100644 --- a/drivers/soc/ti/knav_qmss_queue.c +++ b/drivers/soc/ti/knav_qmss_queue.c @@ -42,6 +42,15 @@ static DEFINE_MUTEX(knav_dev_lock); #define KNAV_QUEUE_PUSH_REG_INDEX 4 #define KNAV_QUEUE_POP_REG_INDEX 5 +/* Queue manager register indices in DTS for QMSS in K2G NAVSS. + * There are no status and vbusm push registers on this version + * of QMSS. Push registers are same as pop, So all indices above 1 + * are to be re-defined + */ +#define KNAV_L_QUEUE_CONFIG_REG_INDEX 1 +#define KNAV_L_QUEUE_REGION_REG_INDEX 2 +#define KNAV_L_QUEUE_PUSH_REG_INDEX 3 + /* PDSP register indices in DTS */ #define KNAV_QUEUE_PDSP_IRAM_REG_INDEX 0 #define KNAV_QUEUE_PDSP_REGS_REG_INDEX 1 @@ -65,6 +74,13 @@ static DEFINE_MUTEX(knav_dev_lock); */ const char *knav_acc_firmwares[] = {"ks2_qmss_pdsp_acc48.bin"}; +static bool device_ready; +bool knav_qmss_device_ready(void) +{ + return device_ready; +} +EXPORT_SYMBOL_GPL(knav_qmss_device_ready); + /** * knav_queue_notify: qmss queue notfier call * @@ -1169,8 +1185,12 @@ static int knav_queue_setup_link_ram(struct knav_device *kdev) dev_dbg(kdev->dev, "linkram0: dma:%pad, virt:%p, size:%x\n", &block->dma, block->virt, block->size); writel_relaxed((u32)block->dma, &qmgr->reg_config->link_ram_base0); - writel_relaxed(block->size, &qmgr->reg_config->link_ram_size0); - + if (kdev->version == QMSS_66AK2G) + writel_relaxed(block->size, + &qmgr->reg_config->link_ram_size0); + else + writel_relaxed(block->size - 1, + &qmgr->reg_config->link_ram_size0); block++; if (!block->size) continue; @@ -1387,42 +1407,64 @@ static int knav_queue_init_qmgrs(struct knav_device *kdev, qmgr->reg_peek = knav_queue_map_reg(kdev, child, KNAV_QUEUE_PEEK_REG_INDEX); - qmgr->reg_status = - knav_queue_map_reg(kdev, child, - KNAV_QUEUE_STATUS_REG_INDEX); + + if (kdev->version == QMSS) { + qmgr->reg_status = + knav_queue_map_reg(kdev, child, + KNAV_QUEUE_STATUS_REG_INDEX); + } + qmgr->reg_config = knav_queue_map_reg(kdev, child, + (kdev->version == QMSS_66AK2G) ? + KNAV_L_QUEUE_CONFIG_REG_INDEX : KNAV_QUEUE_CONFIG_REG_INDEX); qmgr->reg_region = knav_queue_map_reg(kdev, child, + (kdev->version == QMSS_66AK2G) ? + KNAV_L_QUEUE_REGION_REG_INDEX : KNAV_QUEUE_REGION_REG_INDEX); + qmgr->reg_push = knav_queue_map_reg(kdev, child, - KNAV_QUEUE_PUSH_REG_INDEX); - qmgr->reg_pop = - knav_queue_map_reg(kdev, child, - KNAV_QUEUE_POP_REG_INDEX); + (kdev->version == QMSS_66AK2G) ? + KNAV_L_QUEUE_PUSH_REG_INDEX : + KNAV_QUEUE_PUSH_REG_INDEX); + + if (kdev->version == QMSS) { + qmgr->reg_pop = + knav_queue_map_reg(kdev, child, + KNAV_QUEUE_POP_REG_INDEX); + } - if (IS_ERR(qmgr->reg_peek) || IS_ERR(qmgr->reg_status) || + if (IS_ERR(qmgr->reg_peek) || + ((kdev->version == QMSS) && + (IS_ERR(qmgr->reg_status) || IS_ERR(qmgr->reg_pop))) || IS_ERR(qmgr->reg_config) || IS_ERR(qmgr->reg_region) || - IS_ERR(qmgr->reg_push) || IS_ERR(qmgr->reg_pop)) { + IS_ERR(qmgr->reg_push)) { dev_err(dev, "failed to map qmgr regs\n"); + if (kdev->version == QMSS) { + if (!IS_ERR(qmgr->reg_status)) + devm_iounmap(dev, qmgr->reg_status); + if (!IS_ERR(qmgr->reg_pop)) + devm_iounmap(dev, qmgr->reg_pop); + } if (!IS_ERR(qmgr->reg_peek)) devm_iounmap(dev, qmgr->reg_peek); - if (!IS_ERR(qmgr->reg_status)) - devm_iounmap(dev, qmgr->reg_status); if (!IS_ERR(qmgr->reg_config)) devm_iounmap(dev, qmgr->reg_config); if (!IS_ERR(qmgr->reg_region)) devm_iounmap(dev, qmgr->reg_region); if (!IS_ERR(qmgr->reg_push)) devm_iounmap(dev, qmgr->reg_push); - if (!IS_ERR(qmgr->reg_pop)) - devm_iounmap(dev, qmgr->reg_pop); devm_kfree(dev, qmgr); continue; } + /* Use same push register for pop as well */ + if (kdev->version == QMSS_66AK2G) + qmgr->reg_pop = qmgr->reg_push; + list_add_tail(&qmgr->list, &kdev->qmgrs); dev_info(dev, "added qmgr start queue %d, num of queues %d, reg_peek %p, reg_status %p, reg_config %p, reg_region %p, reg_push %p, reg_pop %p\n", qmgr->start_queue, qmgr->num_queues, @@ -1681,10 +1723,24 @@ static int knav_queue_init_queues(struct knav_device *kdev) return 0; } +/* Match table for of_platform binding */ +static const struct of_device_id keystone_qmss_of_match[] = { + { + .compatible = "ti,keystone-navigator-qmss", + }, + { + .compatible = "ti,66ak2g-navss-qm", + .data = (void *)QMSS_66AK2G, + }, + {}, +}; +MODULE_DEVICE_TABLE(of, keystone_qmss_of_match); + static int knav_queue_probe(struct platform_device *pdev) { struct device_node *node = pdev->dev.of_node; struct device_node *qmgrs, *queue_pools, *regions, *pdsps; + const struct of_device_id *match; struct device *dev = &pdev->dev; u32 temp[2]; int ret; @@ -1700,6 +1756,10 @@ static int knav_queue_probe(struct platform_device *pdev) return -ENOMEM; } + match = of_match_device(of_match_ptr(keystone_qmss_of_match), dev); + if (match && match->data) + kdev->version = QMSS_66AK2G; + platform_set_drvdata(pdev, kdev); kdev->dev = dev; INIT_LIST_HEAD(&kdev->queue_ranges); @@ -1796,6 +1856,7 @@ static int knav_queue_probe(struct platform_device *pdev) debugfs_create_file("qmss", S_IFREG | S_IRUGO, NULL, NULL, &knav_queue_debug_ops); + device_ready = true; return 0; err: @@ -1815,13 +1876,6 @@ static int knav_queue_remove(struct platform_device *pdev) return 0; } -/* Match table for of_platform binding */ -static struct of_device_id keystone_qmss_of_match[] = { - { .compatible = "ti,keystone-navigator-qmss", }, - {}, -}; -MODULE_DEVICE_TABLE(of, keystone_qmss_of_match); - static struct platform_driver keystone_qmss_driver = { .probe = knav_queue_probe, .remove = knav_queue_remove, diff --git a/drivers/vhost/net.c b/drivers/vhost/net.c index 986058a57917..c4b49fca4871 100644 --- a/drivers/vhost/net.c +++ b/drivers/vhost/net.c @@ -32,6 +32,7 @@ #include <linux/skbuff.h> #include <net/sock.h> +#include <net/xdp.h> #include "vhost.h" @@ -45,8 +46,10 @@ MODULE_PARM_DESC(experimental_zcopytx, "Enable Zero Copy TX;" #define VHOST_NET_WEIGHT 0x80000 /* Max number of packets transferred before requeueing the job. - * Using this limit prevents one virtqueue from starving rx. */ -#define VHOST_NET_PKT_WEIGHT(vq) ((vq)->num * 2) + * Using this limit prevents one virtqueue from starving others with small + * pkts. + */ +#define VHOST_NET_PKT_WEIGHT 256 /* MAX number of TX used buffers for outstanding zerocopy */ #define VHOST_MAX_PEND 128 @@ -181,10 +184,10 @@ static void vhost_net_buf_unproduce(struct vhost_net_virtqueue *nvq) static int vhost_net_buf_peek_len(void *ptr) { - if (tun_is_xdp_buff(ptr)) { - struct xdp_buff *xdp = tun_ptr_to_xdp(ptr); + if (tun_is_xdp_frame(ptr)) { + struct xdp_frame *xdpf = tun_ptr_to_xdp(ptr); - return xdp->data_end - xdp->data; + return xdpf->len; } return __skb_array_len_with_tag(ptr); @@ -586,7 +589,7 @@ static void handle_tx(struct vhost_net *net) vhost_zerocopy_signal_used(net, vq); vhost_net_tx_packet(net); if (unlikely(total_len >= VHOST_NET_WEIGHT) || - unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT(vq))) { + unlikely(++sent_pkts >= VHOST_NET_PKT_WEIGHT)) { vhost_poll_queue(&vq->poll); break; } @@ -768,6 +771,7 @@ static void handle_rx(struct vhost_net *net) struct socket *sock; struct iov_iter fixup; __virtio16 num_buffers; + int recv_pkts = 0; mutex_lock_nested(&vq->mutex, 0); sock = vq->private_data; @@ -871,7 +875,8 @@ static void handle_rx(struct vhost_net *net) if (unlikely(vq_log)) vhost_log_write(vq, vq_log, log, vhost_len); total_len += vhost_len; - if (unlikely(total_len >= VHOST_NET_WEIGHT)) { + if (unlikely(total_len >= VHOST_NET_WEIGHT) || + unlikely(++recv_pkts >= VHOST_NET_PKT_WEIGHT)) { vhost_poll_queue(&vq->poll); goto out; } diff --git a/include/dt-bindings/net/microchip-lan78xx.h b/include/dt-bindings/net/microchip-lan78xx.h new file mode 100644 index 000000000000..0742ff075307 --- /dev/null +++ b/include/dt-bindings/net/microchip-lan78xx.h @@ -0,0 +1,21 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef _DT_BINDINGS_MICROCHIP_LAN78XX_H +#define _DT_BINDINGS_MICROCHIP_LAN78XX_H + +/* LED modes for LAN7800/LAN7850 embedded PHY */ + +#define LAN78XX_LINK_ACTIVITY 0 +#define LAN78XX_LINK_1000_ACTIVITY 1 +#define LAN78XX_LINK_100_ACTIVITY 2 +#define LAN78XX_LINK_10_ACTIVITY 3 +#define LAN78XX_LINK_100_1000_ACTIVITY 4 +#define LAN78XX_LINK_10_1000_ACTIVITY 5 +#define LAN78XX_LINK_10_100_ACTIVITY 6 +#define LAN78XX_DUPLEX_COLLISION 8 +#define LAN78XX_COLLISION 9 +#define LAN78XX_ACTIVITY 10 +#define LAN78XX_AUTONEG_FAULT 12 +#define LAN78XX_FORCE_LED_OFF 14 +#define LAN78XX_FORCE_LED_ON 15 + +#endif diff --git a/include/linux/bpf.h b/include/linux/bpf.h index 469b20e1dd7e..321969da67b7 100644 --- a/include/linux/bpf.h +++ b/include/linux/bpf.h @@ -22,6 +22,8 @@ struct perf_event; struct bpf_prog; struct bpf_map; struct sock; +struct seq_file; +struct btf; /* map is generic key/value storage optionally accesible by eBPF programs */ struct bpf_map_ops { @@ -44,10 +46,14 @@ struct bpf_map_ops { void (*map_fd_put_ptr)(void *ptr); u32 (*map_gen_lookup)(struct bpf_map *map, struct bpf_insn *insn_buf); u32 (*map_fd_sys_lookup_elem)(void *ptr); + void (*map_seq_show_elem)(struct bpf_map *map, void *key, + struct seq_file *m); + int (*map_check_btf)(const struct bpf_map *map, const struct btf *btf, + u32 key_type_id, u32 value_type_id); }; struct bpf_map { - /* 1st cacheline with read-mostly members of which some + /* The first two cachelines with read-mostly members of which some * are also accessed in fast-path (e.g. ops, max_entries). */ const struct bpf_map_ops *ops ____cacheline_aligned; @@ -63,10 +69,13 @@ struct bpf_map { u32 pages; u32 id; int numa_node; + u32 btf_key_id; + u32 btf_value_id; + struct btf *btf; bool unpriv_array; - /* 7 bytes hole */ + /* 55 bytes hole */ - /* 2nd cacheline with misc members to avoid false sharing + /* The 3rd and 4th cacheline with misc members to avoid false sharing * particularly with refcounting. */ struct user_struct *user ____cacheline_aligned; @@ -101,6 +110,16 @@ static inline struct bpf_offloaded_map *map_to_offmap(struct bpf_map *map) return container_of(map, struct bpf_offloaded_map, map); } +static inline bool bpf_map_offload_neutral(const struct bpf_map *map) +{ + return map->map_type == BPF_MAP_TYPE_PERF_EVENT_ARRAY; +} + +static inline bool bpf_map_support_seq_show(const struct bpf_map *map) +{ + return map->ops->map_seq_show_elem && map->ops->map_check_btf; +} + extern const struct bpf_map_ops bpf_map_offload_ops; /* function argument constraints */ @@ -221,6 +240,8 @@ struct bpf_verifier_ops { struct bpf_insn_access_aux *info); int (*gen_prologue)(struct bpf_insn *insn, bool direct_write, const struct bpf_prog *prog); + int (*gen_ld_abs)(const struct bpf_insn *orig, + struct bpf_insn *insn_buf); u32 (*convert_ctx_access)(enum bpf_access_type type, const struct bpf_insn *src, struct bpf_insn *dst, @@ -662,6 +683,31 @@ static inline int sock_map_prog(struct bpf_map *map, } #endif +#if defined(CONFIG_XDP_SOCKETS) +struct xdp_sock; +struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key); +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs); +void __xsk_map_flush(struct bpf_map *map); +#else +struct xdp_sock; +static inline struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, + u32 key) +{ + return NULL; +} + +static inline int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + return -EOPNOTSUPP; +} + +static inline void __xsk_map_flush(struct bpf_map *map) +{ +} +#endif + /* verifier prototypes for helper functions called from eBPF programs */ extern const struct bpf_func_proto bpf_map_lookup_elem_proto; extern const struct bpf_func_proto bpf_map_update_elem_proto; @@ -675,9 +721,8 @@ extern const struct bpf_func_proto bpf_ktime_get_ns_proto; extern const struct bpf_func_proto bpf_get_current_pid_tgid_proto; extern const struct bpf_func_proto bpf_get_current_uid_gid_proto; extern const struct bpf_func_proto bpf_get_current_comm_proto; -extern const struct bpf_func_proto bpf_skb_vlan_push_proto; -extern const struct bpf_func_proto bpf_skb_vlan_pop_proto; extern const struct bpf_func_proto bpf_get_stackid_proto; +extern const struct bpf_func_proto bpf_get_stack_proto; extern const struct bpf_func_proto bpf_sock_map_update_proto; /* Shared helpers among cBPF and eBPF. */ diff --git a/include/linux/bpf_trace.h b/include/linux/bpf_trace.h index e6fe98ae3794..ddf896abcfb6 100644 --- a/include/linux/bpf_trace.h +++ b/include/linux/bpf_trace.h @@ -2,7 +2,6 @@ #ifndef __LINUX_BPF_TRACE_H__ #define __LINUX_BPF_TRACE_H__ -#include <trace/events/bpf.h> #include <trace/events/xdp.h> #endif /* __LINUX_BPF_TRACE_H__ */ diff --git a/include/linux/bpf_types.h b/include/linux/bpf_types.h index 2b28fcf6f6ae..d7df1b323082 100644 --- a/include/linux/bpf_types.h +++ b/include/linux/bpf_types.h @@ -49,4 +49,7 @@ BPF_MAP_TYPE(BPF_MAP_TYPE_DEVMAP, dev_map_ops) BPF_MAP_TYPE(BPF_MAP_TYPE_SOCKMAP, sock_map_ops) #endif BPF_MAP_TYPE(BPF_MAP_TYPE_CPUMAP, cpu_map_ops) +#if defined(CONFIG_XDP_SOCKETS) +BPF_MAP_TYPE(BPF_MAP_TYPE_XSKMAP, xsk_map_ops) +#endif #endif diff --git a/include/linux/bpf_verifier.h b/include/linux/bpf_verifier.h index 7e61c395fddf..8f70dc181e23 100644 --- a/include/linux/bpf_verifier.h +++ b/include/linux/bpf_verifier.h @@ -173,6 +173,11 @@ static inline bool bpf_verifier_log_needed(const struct bpf_verifier_log *log) #define BPF_MAX_SUBPROGS 256 +struct bpf_subprog_info { + u32 start; /* insn idx of function entry point */ + u16 stack_depth; /* max. stack depth used by this function */ +}; + /* single container for all structs * one verifier_env per bpf_check() call */ @@ -191,9 +196,7 @@ struct bpf_verifier_env { bool seen_direct_write; struct bpf_insn_aux_data *insn_aux_data; /* array of per-insn state */ struct bpf_verifier_log log; - u32 subprog_starts[BPF_MAX_SUBPROGS]; - /* computes the stack depth of each bpf function */ - u16 subprog_stack_depth[BPF_MAX_SUBPROGS + 1]; + struct bpf_subprog_info subprog_info[BPF_MAX_SUBPROGS + 1]; u32 subprog_cnt; }; diff --git a/include/linux/btf.h b/include/linux/btf.h new file mode 100644 index 000000000000..a966dc6d61ee --- /dev/null +++ b/include/linux/btf.h @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#ifndef _LINUX_BTF_H +#define _LINUX_BTF_H 1 + +#include <linux/types.h> + +struct btf; +struct btf_type; +union bpf_attr; + +extern const struct file_operations btf_fops; + +void btf_put(struct btf *btf); +int btf_new_fd(const union bpf_attr *attr); +struct btf *btf_get_by_fd(int fd); +int btf_get_info_by_fd(const struct btf *btf, + const union bpf_attr *attr, + union bpf_attr __user *uattr); +/* Figure out the size of a type_id. If type_id is a modifier + * (e.g. const), it will be resolved to find out the type with size. + * + * For example: + * In describing "const void *", type_id is "const" and "const" + * refers to "void *". The return type will be "void *". + * + * If type_id is a simple "int", then return type will be "int". + * + * @btf: struct btf object + * @type_id: Find out the size of type_id. The type_id of the return + * type is set to *type_id. + * @ret_size: It can be NULL. If not NULL, the size of the return + * type is set to *ret_size. + * Return: The btf_type (resolved to another type with size info if needed). + * NULL is returned if type_id itself does not have size info + * (e.g. void) or it cannot be resolved to another type that + * has size info. + * *type_id and *ret_size will not be changed in the + * NULL return case. + */ +const struct btf_type *btf_type_id_size(const struct btf *btf, + u32 *type_id, + u32 *ret_size); +void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, + struct seq_file *m); + +#endif diff --git a/include/linux/ethtool.h b/include/linux/ethtool.h index b32cd2062f18..f8a2245b70ac 100644 --- a/include/linux/ethtool.h +++ b/include/linux/ethtool.h @@ -312,6 +312,9 @@ bool ethtool_convert_link_mode_to_legacy_u32(u32 *legacy_u32, * by kernel. Returns a negative error code or zero. * @get_fecparam: Get the network device Forward Error Correction parameters. * @set_fecparam: Set the network device Forward Error Correction parameters. + * @get_ethtool_phy_stats: Return extended statistics about the PHY device. + * This is only useful if the device maintains PHY statistics and + * cannot use the standard PHY library helpers. * * All operations are optional (i.e. the function pointer may be set * to %NULL) and callers must take this into account. Callers must @@ -407,5 +410,7 @@ struct ethtool_ops { struct ethtool_fecparam *); int (*set_fecparam)(struct net_device *, struct ethtool_fecparam *); + void (*get_ethtool_phy_stats)(struct net_device *, + struct ethtool_stats *, u64 *); }; #endif /* _LINUX_ETHTOOL_H */ diff --git a/include/linux/filter.h b/include/linux/filter.h index fc4e8f91b03d..da7e16523128 100644 --- a/include/linux/filter.h +++ b/include/linux/filter.h @@ -30,6 +30,7 @@ struct sock; struct seccomp_data; struct bpf_prog_aux; struct xdp_rxq_info; +struct xdp_buff; /* ArgX, context and stack frame pointer register positions. Note, * Arg1, Arg2, Arg3, etc are used as argument mappings of function @@ -46,7 +47,9 @@ struct xdp_rxq_info; /* Additional register mappings for converted user programs. */ #define BPF_REG_A BPF_REG_0 #define BPF_REG_X BPF_REG_7 -#define BPF_REG_TMP BPF_REG_8 +#define BPF_REG_TMP BPF_REG_2 /* scratch reg */ +#define BPF_REG_D BPF_REG_8 /* data, callee-saved */ +#define BPF_REG_H BPF_REG_9 /* hlen, callee-saved */ /* Kernel hidden auxiliary/helper register for hardening step. * Only used by eBPF JITs. It's nothing more than a temporary @@ -467,7 +470,8 @@ struct bpf_prog { dst_needed:1, /* Do we need dst entry? */ blinded:1, /* Was blinded */ is_func:1, /* program is a bpf function */ - kprobe_override:1; /* Do we override a kprobe? */ + kprobe_override:1, /* Do we override a kprobe? */ + has_callchain_buf:1; /* callchain buffer allocated? */ enum bpf_prog_type type; /* Type of BPF program */ enum bpf_attach_type expected_attach_type; /* For some prog types */ u32 len; /* Number of filter blocks */ @@ -500,14 +504,6 @@ struct bpf_skb_data_end { void *data_end; }; -struct xdp_buff { - void *data; - void *data_end; - void *data_meta; - void *data_hard_start; - struct xdp_rxq_info *rxq; -}; - struct sk_msg_buff { void *data; void *data_end; @@ -766,27 +762,12 @@ struct bpf_prog *bpf_patch_insn_single(struct bpf_prog *prog, u32 off, * This does not appear to be a real limitation for existing software. */ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *prog); + struct xdp_buff *xdp, struct bpf_prog *prog); int xdp_do_redirect(struct net_device *dev, struct xdp_buff *xdp, struct bpf_prog *prog); void xdp_do_flush_map(void); -/* Drivers not supporting XDP metadata can use this helper, which - * rejects any room expansion for metadata as a result. - */ -static __always_inline void -xdp_set_data_meta_invalid(struct xdp_buff *xdp) -{ - xdp->data_meta = xdp->data + 1; -} - -static __always_inline bool -xdp_data_meta_unsupported(const struct xdp_buff *xdp) -{ - return unlikely(xdp->data_meta > xdp->data); -} - void bpf_warn_invalid_xdp_action(u32 act); struct sock *do_sk_redirect_map(struct sk_buff *skb); diff --git a/include/linux/if_bridge.h b/include/linux/if_bridge.h index 02639ebea2f0..585d27182425 100644 --- a/include/linux/if_bridge.h +++ b/include/linux/if_bridge.h @@ -93,11 +93,39 @@ static inline bool br_multicast_router(const struct net_device *dev) #if IS_ENABLED(CONFIG_BRIDGE) && IS_ENABLED(CONFIG_BRIDGE_VLAN_FILTERING) bool br_vlan_enabled(const struct net_device *dev); +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid); +int br_vlan_get_info(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo); #else static inline bool br_vlan_enabled(const struct net_device *dev) { return false; } + +static inline int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) +{ + return -1; +} + +static inline int br_vlan_get_info(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) +{ + return -1; +} +#endif + +#if IS_ENABLED(CONFIG_BRIDGE) +struct net_device *br_fdb_find_port(const struct net_device *br_dev, + const unsigned char *addr, + __u16 vid); +#else +static inline struct net_device * +br_fdb_find_port(const struct net_device *br_dev, + const unsigned char *addr, + __u16 vid) +{ + return NULL; +} #endif #endif diff --git a/include/linux/if_macvlan.h b/include/linux/if_macvlan.h index 4cb7aeeafce0..2e55e4cdbd8a 100644 --- a/include/linux/if_macvlan.h +++ b/include/linux/if_macvlan.h @@ -21,7 +21,7 @@ struct macvlan_dev { struct hlist_node hlist; struct macvlan_port *port; struct net_device *lowerdev; - void *fwd_priv; + void *accel_priv; struct vlan_pcpu_stats __percpu *pcpu_stats; DECLARE_BITMAP(mc_filter, MACVLAN_MC_FILTER_SZ); @@ -61,10 +61,6 @@ extern int macvlan_common_newlink(struct net *src_net, struct net_device *dev, struct nlattr *tb[], struct nlattr *data[], struct netlink_ext_ack *extack); -extern void macvlan_count_rx(const struct macvlan_dev *vlan, - unsigned int len, bool success, - bool multicast); - extern void macvlan_dellink(struct net_device *dev, struct list_head *head); extern int macvlan_link_register(struct rtnl_link_ops *ops); @@ -86,4 +82,27 @@ macvlan_dev_real_dev(const struct net_device *dev) } #endif +static inline void *macvlan_accel_priv(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->accel_priv; +} + +static inline bool macvlan_supports_dest_filter(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + return macvlan->mode == MACVLAN_MODE_PRIVATE || + macvlan->mode == MACVLAN_MODE_VEPA || + macvlan->mode == MACVLAN_MODE_BRIDGE; +} + +static inline int macvlan_release_l2fw_offload(struct net_device *dev) +{ + struct macvlan_dev *macvlan = netdev_priv(dev); + + macvlan->accel_priv = NULL; + return dev_uc_add(macvlan->lowerdev, dev->dev_addr); +} #endif /* _LINUX_IF_MACVLAN_H */ diff --git a/include/linux/if_tun.h b/include/linux/if_tun.h index fd00170b494f..3d2996dc7d85 100644 --- a/include/linux/if_tun.h +++ b/include/linux/if_tun.h @@ -22,7 +22,7 @@ #if defined(CONFIG_TUN) || defined(CONFIG_TUN_MODULE) struct socket *tun_get_socket(struct file *); struct ptr_ring *tun_get_tx_ring(struct file *file); -bool tun_is_xdp_buff(void *ptr); +bool tun_is_xdp_frame(void *ptr); void *tun_xdp_to_ptr(void *ptr); void *tun_ptr_to_xdp(void *ptr); void tun_ptr_free(void *ptr); @@ -39,7 +39,7 @@ static inline struct ptr_ring *tun_get_tx_ring(struct file *f) { return ERR_PTR(-EINVAL); } -static inline bool tun_is_xdp_buff(void *ptr) +static inline bool tun_is_xdp_frame(void *ptr) { return false; } diff --git a/include/linux/mdio-bitbang.h b/include/linux/mdio-bitbang.h index a8ac9cfa014c..5d71e8a8500f 100644 --- a/include/linux/mdio-bitbang.h +++ b/include/linux/mdio-bitbang.h @@ -33,8 +33,6 @@ struct mdiobb_ops { struct mdiobb_ctrl { const struct mdiobb_ops *ops; - /* reset callback */ - int (*reset)(struct mii_bus *bus); }; /* The returned bus is not yet registered with the phy layer. */ diff --git a/include/linux/mdio-gpio.h b/include/linux/mdio-gpio.h new file mode 100644 index 000000000000..cea443a672cb --- /dev/null +++ b/include/linux/mdio-gpio.h @@ -0,0 +1,9 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __LINUX_MDIO_GPIO_H +#define __LINUX_MDIO_GPIO_H + +#define MDIO_GPIO_MDC 0 +#define MDIO_GPIO_MDIO 1 +#define MDIO_GPIO_MDO 2 + +#endif diff --git a/include/linux/microchipphy.h b/include/linux/microchipphy.h index 8f9c90379732..8c40128af240 100644 --- a/include/linux/microchipphy.h +++ b/include/linux/microchipphy.h @@ -70,6 +70,9 @@ #define LAN88XX_MMD3_CHIP_ID (32877) #define LAN88XX_MMD3_CHIP_REV (32878) +/* Registers specific to the LAN7800/LAN7850 embedded phy */ +#define LAN78XX_PHY_LED_MODE_SELECT (0x1D) + /* DSP registers */ #define PHY_ARDENNES_MMD_DEV_3_PHY_CFG (0x806A) #define PHY_ARDENNES_MMD_DEV_3_PHY_CFG_ZD_DLY_EN_ (0x2000) diff --git a/include/linux/mlx4/device.h b/include/linux/mlx4/device.h index 81d0799b6091..122e7e9d3091 100644 --- a/include/linux/mlx4/device.h +++ b/include/linux/mlx4/device.h @@ -225,6 +225,7 @@ enum { MLX4_DEV_CAP_FLAG2_SVLAN_BY_QP = 1ULL << 36, MLX4_DEV_CAP_FLAG2_SL_TO_VL_CHANGE_EVENT = 1ULL << 37, MLX4_DEV_CAP_FLAG2_USER_MAC_EN = 1ULL << 38, + MLX4_DEV_CAP_FLAG2_DRIVER_VERSION_TO_FW = 1ULL << 39, }; enum { diff --git a/include/linux/mlx5/mlx5_ifc.h b/include/linux/mlx5/mlx5_ifc.h index 1aad455538f4..b8918a1da11f 100644 --- a/include/linux/mlx5/mlx5_ifc.h +++ b/include/linux/mlx5/mlx5_ifc.h @@ -356,22 +356,6 @@ struct mlx5_ifc_odp_per_transport_service_cap_bits { u8 reserved_at_6[0x1a]; }; -struct mlx5_ifc_ipv4_layout_bits { - u8 reserved_at_0[0x60]; - - u8 ipv4[0x20]; -}; - -struct mlx5_ifc_ipv6_layout_bits { - u8 ipv6[16][0x8]; -}; - -union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { - struct mlx5_ifc_ipv6_layout_bits ipv6_layout; - struct mlx5_ifc_ipv4_layout_bits ipv4_layout; - u8 reserved_at_0[0x80]; -}; - struct mlx5_ifc_fte_match_set_lyr_2_4_bits { u8 smac_47_16[0x20]; diff --git a/include/linux/mlx5/mlx5_ifc_fpga.h b/include/linux/mlx5/mlx5_ifc_fpga.h index ec052491ba3d..193091537cb6 100644 --- a/include/linux/mlx5/mlx5_ifc_fpga.h +++ b/include/linux/mlx5/mlx5_ifc_fpga.h @@ -32,12 +32,29 @@ #ifndef MLX5_IFC_FPGA_H #define MLX5_IFC_FPGA_H +struct mlx5_ifc_ipv4_layout_bits { + u8 reserved_at_0[0x60]; + + u8 ipv4[0x20]; +}; + +struct mlx5_ifc_ipv6_layout_bits { + u8 ipv6[16][0x8]; +}; + +union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits { + struct mlx5_ifc_ipv6_layout_bits ipv6_layout; + struct mlx5_ifc_ipv4_layout_bits ipv4_layout; + u8 reserved_at_0[0x80]; +}; + enum { MLX5_FPGA_CAP_SANDBOX_VENDOR_ID_MLNX = 0x2c9, }; enum { MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_IPSEC = 0x2, + MLX5_FPGA_CAP_SANDBOX_PRODUCT_ID_TLS = 0x3, }; struct mlx5_ifc_fpga_shell_caps_bits { @@ -370,6 +387,27 @@ struct mlx5_ifc_fpga_destroy_qp_out_bits { u8 reserved_at_40[0x40]; }; +struct mlx5_ifc_tls_extended_cap_bits { + u8 aes_gcm_128[0x1]; + u8 aes_gcm_256[0x1]; + u8 reserved_at_2[0x1e]; + u8 reserved_at_20[0x20]; + u8 context_capacity_total[0x20]; + u8 context_capacity_rx[0x20]; + u8 context_capacity_tx[0x20]; + u8 reserved_at_a0[0x10]; + u8 tls_counter_size[0x10]; + u8 tls_counters_addr_low[0x20]; + u8 tls_counters_addr_high[0x20]; + u8 rx[0x1]; + u8 tx[0x1]; + u8 tls_v12[0x1]; + u8 tls_v13[0x1]; + u8 lro[0x1]; + u8 ipv6[0x1]; + u8 reserved_at_106[0x1a]; +}; + struct mlx5_ifc_ipsec_extended_cap_bits { u8 encapsulation[0x20]; @@ -519,4 +557,43 @@ struct mlx5_ifc_fpga_ipsec_sa { __be16 reserved2; } __packed; +enum fpga_tls_cmds { + CMD_SETUP_STREAM = 0x1001, + CMD_TEARDOWN_STREAM = 0x1002, +}; + +#define MLX5_TLS_1_2 (0) + +#define MLX5_TLS_ALG_AES_GCM_128 (0) +#define MLX5_TLS_ALG_AES_GCM_256 (1) + +struct mlx5_ifc_tls_cmd_bits { + u8 command_type[0x20]; + u8 ipv6[0x1]; + u8 direction_sx[0x1]; + u8 tls_version[0x2]; + u8 reserved[0x1c]; + u8 swid[0x20]; + u8 src_port[0x10]; + u8 dst_port[0x10]; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits src_ipv4_src_ipv6; + union mlx5_ifc_ipv6_layout_ipv4_layout_auto_bits dst_ipv4_dst_ipv6; + u8 tls_rcd_sn[0x40]; + u8 tcp_sn[0x20]; + u8 tls_implicit_iv[0x20]; + u8 tls_xor_iv[0x40]; + u8 encryption_key[0x100]; + u8 alg[4]; + u8 reserved2[0x1c]; + u8 reserved3[0x4a0]; +}; + +struct mlx5_ifc_tls_resp_bits { + u8 syndrome[0x20]; + u8 stream_id[0x20]; + u8 reserverd[0x40]; +}; + +#define MLX5_TLS_COMMAND_SIZE (0x100) + #endif /* MLX5_IFC_FPGA_H */ diff --git a/include/linux/net.h b/include/linux/net.h index 2248a052061d..6554d3ba4396 100644 --- a/include/linux/net.h +++ b/include/linux/net.h @@ -197,6 +197,7 @@ struct proto_ops { int offset, size_t size, int flags); int (*sendmsg_locked)(struct sock *sk, struct msghdr *msg, size_t size); + int (*set_rcvlowat)(struct sock *sk, int val); }; #define DECLARE_SOCKADDR(type, dst, src) \ diff --git a/include/linux/net_dim.h b/include/linux/net_dim.h index 29ed8fd6379a..db99240d00bd 100644 --- a/include/linux/net_dim.h +++ b/include/linux/net_dim.h @@ -103,11 +103,12 @@ enum { #define NET_DIM_PARAMS_NUM_PROFILES 5 /* Adaptive moderation profiles */ #define NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE 256 +#define NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE 128 #define NET_DIM_DEF_PROFILE_CQE 1 #define NET_DIM_DEF_PROFILE_EQE 1 /* All profiles sizes must be NET_PARAMS_DIM_NUM_PROFILES */ -#define NET_DIM_EQE_PROFILES { \ +#define NET_DIM_RX_EQE_PROFILES { \ {1, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ {8, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ {64, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ @@ -115,7 +116,7 @@ enum { {256, NET_DIM_DEFAULT_RX_CQ_MODERATION_PKTS_FROM_EQE}, \ } -#define NET_DIM_CQE_PROFILES { \ +#define NET_DIM_RX_CQE_PROFILES { \ {2, 256}, \ {8, 128}, \ {16, 64}, \ @@ -123,32 +124,68 @@ enum { {64, 64} \ } +#define NET_DIM_TX_EQE_PROFILES { \ + {1, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {8, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {32, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {64, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE}, \ + {128, NET_DIM_DEFAULT_TX_CQ_MODERATION_PKTS_FROM_EQE} \ +} + +#define NET_DIM_TX_CQE_PROFILES { \ + {5, 128}, \ + {8, 64}, \ + {16, 32}, \ + {32, 32}, \ + {64, 32} \ +} + static const struct net_dim_cq_moder -profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { - NET_DIM_EQE_PROFILES, - NET_DIM_CQE_PROFILES, +rx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_RX_EQE_PROFILES, + NET_DIM_RX_CQE_PROFILES, }; -static inline struct net_dim_cq_moder net_dim_get_profile(u8 cq_period_mode, - int ix) +static const struct net_dim_cq_moder +tx_profile[NET_DIM_CQ_PERIOD_NUM_MODES][NET_DIM_PARAMS_NUM_PROFILES] = { + NET_DIM_TX_EQE_PROFILES, + NET_DIM_TX_CQE_PROFILES, +}; + +static inline struct net_dim_cq_moder +net_dim_get_rx_moderation(u8 cq_period_mode, int ix) { - struct net_dim_cq_moder cq_moder; + struct net_dim_cq_moder cq_moder = rx_profile[cq_period_mode][ix]; - cq_moder = profile[cq_period_mode][ix]; cq_moder.cq_period_mode = cq_period_mode; return cq_moder; } -static inline struct net_dim_cq_moder net_dim_get_def_profile(u8 rx_cq_period_mode) +static inline struct net_dim_cq_moder +net_dim_get_def_rx_moderation(u8 cq_period_mode) +{ + u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? + NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; + + return net_dim_get_rx_moderation(cq_period_mode, profile_ix); +} + +static inline struct net_dim_cq_moder +net_dim_get_tx_moderation(u8 cq_period_mode, int ix) { - int default_profile_ix; + struct net_dim_cq_moder cq_moder = tx_profile[cq_period_mode][ix]; + + cq_moder.cq_period_mode = cq_period_mode; + return cq_moder; +} - if (rx_cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE) - default_profile_ix = NET_DIM_DEF_PROFILE_CQE; - else /* NET_DIM_CQ_PERIOD_MODE_START_FROM_EQE */ - default_profile_ix = NET_DIM_DEF_PROFILE_EQE; +static inline struct net_dim_cq_moder +net_dim_get_def_tx_moderation(u8 cq_period_mode) +{ + u8 profile_ix = cq_period_mode == NET_DIM_CQ_PERIOD_MODE_START_FROM_CQE ? + NET_DIM_DEF_PROFILE_CQE : NET_DIM_DEF_PROFILE_EQE; - return net_dim_get_profile(rx_cq_period_mode, default_profile_ix); + return net_dim_get_tx_moderation(cq_period_mode, profile_ix); } static inline bool net_dim_on_top(struct net_dim *dim) diff --git a/include/linux/netdev_features.h b/include/linux/netdev_features.h index 35b79f47a13d..c87c3a3453c1 100644 --- a/include/linux/netdev_features.h +++ b/include/linux/netdev_features.h @@ -55,8 +55,9 @@ enum { NETIF_F_GSO_SCTP_BIT, /* ... SCTP fragmentation */ NETIF_F_GSO_ESP_BIT, /* ... ESP with TSO */ NETIF_F_GSO_UDP_BIT, /* ... UFO, deprecated except tuntap */ + NETIF_F_GSO_UDP_L4_BIT, /* ... UDP payload GSO (not UFO) */ /**/NETIF_F_GSO_LAST = /* last bit, see GSO_MASK */ - NETIF_F_GSO_UDP_BIT, + NETIF_F_GSO_UDP_L4_BIT, NETIF_F_FCOE_CRC_BIT, /* FCoE CRC32 */ NETIF_F_SCTP_CRC_BIT, /* SCTP checksum offload */ @@ -77,6 +78,7 @@ enum { NETIF_F_HW_ESP_BIT, /* Hardware ESP transformation offload */ NETIF_F_HW_ESP_TX_CSUM_BIT, /* ESP with TX checksum offload */ NETIF_F_RX_UDP_TUNNEL_PORT_BIT, /* Offload of RX port for UDP tunnels */ + NETIF_F_HW_TLS_TX_BIT, /* Hardware TLS TX offload */ NETIF_F_GRO_HW_BIT, /* Hardware Generic receive offload */ NETIF_F_HW_TLS_RECORD_BIT, /* Offload TLS record */ @@ -147,6 +149,8 @@ enum { #define NETIF_F_HW_ESP_TX_CSUM __NETIF_F(HW_ESP_TX_CSUM) #define NETIF_F_RX_UDP_TUNNEL_PORT __NETIF_F(RX_UDP_TUNNEL_PORT) #define NETIF_F_HW_TLS_RECORD __NETIF_F(HW_TLS_RECORD) +#define NETIF_F_GSO_UDP_L4 __NETIF_F(GSO_UDP_L4) +#define NETIF_F_HW_TLS_TX __NETIF_F(HW_TLS_TX) #define for_each_netdev_feature(mask_addr, bit) \ for_each_set_bit(bit, (unsigned long *)mask_addr, NETDEV_FEATURE_COUNT) @@ -216,6 +220,7 @@ enum { NETIF_F_GSO_GRE_CSUM | \ NETIF_F_GSO_IPXIP4 | \ NETIF_F_GSO_IPXIP6 | \ + NETIF_F_GSO_UDP_L4 | \ NETIF_F_GSO_UDP_TUNNEL | \ NETIF_F_GSO_UDP_TUNNEL_CSUM) diff --git a/include/linux/netdevice.h b/include/linux/netdevice.h index cf44503ea81a..03ed492c4e14 100644 --- a/include/linux/netdevice.h +++ b/include/linux/netdevice.h @@ -865,6 +865,26 @@ struct xfrmdev_ops { }; #endif +#if IS_ENABLED(CONFIG_TLS_DEVICE) +enum tls_offload_ctx_dir { + TLS_OFFLOAD_CTX_DIR_RX, + TLS_OFFLOAD_CTX_DIR_TX, +}; + +struct tls_crypto_info; +struct tls_context; + +struct tlsdev_ops { + int (*tls_dev_add)(struct net_device *netdev, struct sock *sk, + enum tls_offload_ctx_dir direction, + struct tls_crypto_info *crypto_info, + u32 start_offload_tcp_sn); + void (*tls_dev_del)(struct net_device *netdev, + struct tls_context *ctx, + enum tls_offload_ctx_dir direction); +}; +#endif + struct dev_ifalias { struct rcu_head rcuhead; char ifalias[]; @@ -1165,7 +1185,7 @@ struct dev_ifalias { * This function is used to set or query state related to XDP on the * netdevice and manage BPF offload. See definition of * enum bpf_netdev_command for details. - * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_buff *xdp); + * int (*ndo_xdp_xmit)(struct net_device *dev, struct xdp_frame *xdp); * This function is used to submit a XDP packet for transmit on a * netdevice. * void (*ndo_xdp_flush)(struct net_device *dev); @@ -1356,7 +1376,7 @@ struct net_device_ops { int (*ndo_bpf)(struct net_device *dev, struct netdev_bpf *bpf); int (*ndo_xdp_xmit)(struct net_device *dev, - struct xdp_buff *xdp); + struct xdp_frame *xdp); void (*ndo_xdp_flush)(struct net_device *dev); }; @@ -1750,6 +1770,10 @@ struct net_device { const struct xfrmdev_ops *xfrmdev_ops; #endif +#if IS_ENABLED(CONFIG_TLS_DEVICE) + const struct tlsdev_ops *tlsdev_ops; +#endif + const struct header_ops *header_ops; unsigned int flags; @@ -2486,6 +2510,7 @@ void dev_disable_lro(struct net_device *dev); int dev_loopback_xmit(struct net *net, struct sock *sk, struct sk_buff *newskb); int dev_queue_xmit(struct sk_buff *skb); int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv); +int dev_direct_xmit(struct sk_buff *skb, u16 queue_id); int register_netdevice(struct net_device *dev); void unregister_netdevice_queue(struct net_device *dev, struct list_head *head); void unregister_netdevice_many(struct list_head *head); @@ -3213,19 +3238,6 @@ static inline int netif_set_xps_queue(struct net_device *dev, } #endif -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues); - -/* - * Returns a Tx hash for the given packet when dev->real_num_tx_queues is used - * as a distribution range limit for the returned value. - */ -static inline u16 skb_tx_hash(const struct net_device *dev, - struct sk_buff *skb) -{ - return __skb_tx_hash(dev, skb, dev->real_num_tx_queues); -} - /** * netif_is_multiqueue - test if device has multiple transmit queues * @dev: network device @@ -4186,6 +4198,7 @@ static inline bool net_gso_ok(netdev_features_t features, int gso_type) BUILD_BUG_ON(SKB_GSO_SCTP != (NETIF_F_GSO_SCTP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_ESP != (NETIF_F_GSO_ESP >> NETIF_F_GSO_SHIFT)); BUILD_BUG_ON(SKB_GSO_UDP != (NETIF_F_GSO_UDP >> NETIF_F_GSO_SHIFT)); + BUILD_BUG_ON(SKB_GSO_UDP_L4 != (NETIF_F_GSO_UDP_L4 >> NETIF_F_GSO_SHIFT)); return (features & feature) == feature; } diff --git a/include/linux/netfilter/nf_osf.h b/include/linux/netfilter/nf_osf.h new file mode 100644 index 000000000000..a2b39602e87d --- /dev/null +++ b/include/linux/netfilter/nf_osf.h @@ -0,0 +1,27 @@ +#include <uapi/linux/netfilter/nf_osf.h> + +/* Initial window size option state machine: multiple of mss, mtu or + * plain numeric value. Can also be made as plain numeric value which + * is not a multiple of specified value. + */ +enum nf_osf_window_size_options { + OSF_WSS_PLAIN = 0, + OSF_WSS_MSS, + OSF_WSS_MTU, + OSF_WSS_MODULO, + OSF_WSS_MAX, +}; + +enum osf_fmatch_states { + /* Packet does not match the fingerprint */ + FMATCH_WRONG = 0, + /* Packet matches the fingerprint */ + FMATCH_OK, + /* Options do not match the fingerprint, but header does */ + FMATCH_OPT_WRONG, +}; + +bool nf_osf_match(const struct sk_buff *skb, u_int8_t family, + int hooknum, struct net_device *in, struct net_device *out, + const struct nf_osf_info *info, struct net *net, + const struct list_head *nf_osf_fingers); diff --git a/include/linux/netfilter_bridge/ebtables.h b/include/linux/netfilter_bridge/ebtables.h index 0773b5a032f1..c6935be7c6ca 100644 --- a/include/linux/netfilter_bridge/ebtables.h +++ b/include/linux/netfilter_bridge/ebtables.h @@ -17,10 +17,6 @@ #include <linux/if_ether.h> #include <uapi/linux/netfilter_bridge/ebtables.h> -/* return values for match() functions */ -#define EBT_MATCH 0 -#define EBT_NOMATCH 1 - struct ebt_match { struct list_head list; const char name[EBT_FUNCTION_MAXNAMELEN]; diff --git a/include/linux/phy.h b/include/linux/phy.h index f0b5870a6d40..073235e70442 100644 --- a/include/linux/phy.h +++ b/include/linux/phy.h @@ -1068,6 +1068,52 @@ int __init mdio_bus_init(void); void mdio_bus_exit(void); #endif +/* Inline function for use within net/core/ethtool.c (built-in) */ +static inline int phy_ethtool_get_strings(struct phy_device *phydev, u8 *data) +{ + if (!phydev->drv) + return -EIO; + + mutex_lock(&phydev->lock); + phydev->drv->get_strings(phydev, data); + mutex_unlock(&phydev->lock); + + return 0; +} + +static inline int phy_ethtool_get_sset_count(struct phy_device *phydev) +{ + int ret; + + if (!phydev->drv) + return -EIO; + + if (phydev->drv->get_sset_count && + phydev->drv->get_strings && + phydev->drv->get_stats) { + mutex_lock(&phydev->lock); + ret = phydev->drv->get_sset_count(phydev); + mutex_unlock(&phydev->lock); + + return ret; + } + + return -EOPNOTSUPP; +} + +static inline int phy_ethtool_get_stats(struct phy_device *phydev, + struct ethtool_stats *stats, u64 *data) +{ + if (!phydev->drv) + return -EIO; + + mutex_lock(&phydev->lock); + phydev->drv->get_stats(phydev, stats, data); + mutex_unlock(&phydev->lock); + + return 0; +} + extern struct bus_type mdio_bus_type; struct mdio_board_info { diff --git a/include/linux/platform_data/mdio-gpio.h b/include/linux/platform_data/mdio-gpio.h deleted file mode 100644 index 11f00cdabe3d..000000000000 --- a/include/linux/platform_data/mdio-gpio.h +++ /dev/null @@ -1,33 +0,0 @@ -/* - * MDIO-GPIO bus platform data structures - * - * Copyright (C) 2008, Paulius Zaleckas <paulius.zaleckas@teltonika.lt> - * - * This file is licensed under the terms of the GNU General Public License - * version 2. This program is licensed "as is" without any warranty of any - * kind, whether express or implied. - */ - -#ifndef __LINUX_MDIO_GPIO_H -#define __LINUX_MDIO_GPIO_H - -#include <linux/mdio-bitbang.h> - -struct mdio_gpio_platform_data { - /* GPIO numbers for bus pins */ - unsigned int mdc; - unsigned int mdio; - unsigned int mdo; - - bool mdc_active_low; - bool mdio_active_low; - bool mdo_active_low; - - u32 phy_mask; - u32 phy_ignore_ta_mask; - int irqs[PHY_MAX_ADDR]; - /* reset callback */ - int (*reset)(struct mii_bus *bus); -}; - -#endif /* __LINUX_MDIO_GPIO_H */ diff --git a/include/linux/qed/qed_eth_if.h b/include/linux/qed/qed_eth_if.h index 147d08ccf813..7f9756fe9180 100644 --- a/include/linux/qed/qed_eth_if.h +++ b/include/linux/qed/qed_eth_if.h @@ -352,6 +352,7 @@ struct qed_eth_ops { int (*configure_arfs_searcher)(struct qed_dev *cdev, enum qed_filter_config_mode mode); int (*get_coalesce)(struct qed_dev *cdev, u16 *coal, void *handle); + int (*req_bulletin_update_mac)(struct qed_dev *cdev, u8 *mac); }; const struct qed_eth_ops *qed_get_eth_ops(void); diff --git a/include/linux/qed/qed_if.h b/include/linux/qed/qed_if.h index b5b2bc9eacca..907976fd56f7 100644 --- a/include/linux/qed/qed_if.h +++ b/include/linux/qed/qed_if.h @@ -159,6 +159,9 @@ struct qed_dcbx_get { enum qed_nvm_images { QED_NVM_IMAGE_ISCSI_CFG, QED_NVM_IMAGE_FCOE_CFG, + QED_NVM_IMAGE_NVM_CFG1, + QED_NVM_IMAGE_DEFAULT_CFG, + QED_NVM_IMAGE_NVM_META, }; struct qed_link_eee_params { @@ -336,7 +339,6 @@ struct qed_dev_info { u8 num_hwfns; u8 hw_mac[ETH_ALEN]; - bool is_mf_default; /* FW version */ u16 fw_major; @@ -356,7 +358,7 @@ struct qed_dev_info { #define QED_MFW_VERSION_3_OFFSET 24 u32 flash_size; - u8 mf_mode; + bool b_inter_pf_switch; bool tx_switching; bool rdma_supported; u16 mtu; diff --git a/include/linux/qed/qed_ll2_if.h b/include/linux/qed/qed_ll2_if.h index 266c1fb45387..5eb022953aca 100644 --- a/include/linux/qed/qed_ll2_if.h +++ b/include/linux/qed/qed_ll2_if.h @@ -202,6 +202,7 @@ struct qed_ll2_tx_pkt_info { bool enable_ip_cksum; bool enable_l4_cksum; bool calc_ip_len; + bool remove_stag; }; #define QED_LL2_UNUSED_HANDLE (0xff) @@ -220,6 +221,11 @@ struct qed_ll2_params { u8 ll2_mac_address[ETH_ALEN]; }; +enum qed_ll2_xmit_flags { + /* FIP discovery packet */ + QED_LL2_XMIT_FLAGS_FIP_DISCOVERY +}; + struct qed_ll2_ops { /** * @brief start - initializes ll2 @@ -245,10 +251,12 @@ struct qed_ll2_ops { * * @param cdev * @param skb + * @param xmit_flags - Transmit options defined by the enum qed_ll2_xmit_flags. * * @return 0 on success, otherwise error value. */ - int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb); + int (*start_xmit)(struct qed_dev *cdev, struct sk_buff *skb, + unsigned long xmit_flags); /** * @brief register_cb_ops - protocol driver register the callback for Rx/Tx diff --git a/include/linux/rhashtable.h b/include/linux/rhashtable.h index 1f8ad121eb43..4e1f535c2034 100644 --- a/include/linux/rhashtable.h +++ b/include/linux/rhashtable.h @@ -836,9 +836,8 @@ out: * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhashtable_insert_fast( struct rhashtable *ht, struct rhash_head *obj, @@ -866,9 +865,8 @@ static inline int rhashtable_insert_fast( * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhltable_insert_key( struct rhltable *hlt, const void *key, struct rhlist_head *list, @@ -890,9 +888,8 @@ static inline int rhltable_insert_key( * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhltable_insert( struct rhltable *hlt, struct rhlist_head *list, @@ -922,9 +919,8 @@ static inline int rhltable_insert( * * It is safe to call this function from atomic context. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. */ static inline int rhashtable_lookup_insert_fast( struct rhashtable *ht, struct rhash_head *obj, @@ -981,9 +977,8 @@ static inline void *rhashtable_lookup_get_insert_fast( * * Lookups may occur in parallel with hashtable mutations and resizing. * - * Will trigger an automatic deferred table resizing if the size grows - * beyond the watermark indicated by grow_decision() which can be passed - * to rhashtable_init(). + * Will trigger an automatic deferred table resizing if residency in the + * table grows beyond 70%. * * Returns zero on success. */ @@ -1134,8 +1129,8 @@ static inline int __rhashtable_remove_fast( * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * - * Will automatically shrink the table via rhashtable_expand() if the - * shrink_decision function specified at rhashtable_init() returns true. + * Will automatically shrink the table if permitted when residency drops + * below 30%. * * Returns zero on success, -ENOENT if the entry could not be found. */ @@ -1156,8 +1151,8 @@ static inline int rhashtable_remove_fast( * walk the bucket chain upon removal. The removal operation is thus * considerable slow if the hash table is not correctly sized. * - * Will automatically shrink the table via rhashtable_expand() if the - * shrink_decision function specified at rhashtable_init() returns true. + * Will automatically shrink the table if permitted when residency drops + * below 30% * * Returns zero on success, -ENOENT if the entry could not be found. */ @@ -1273,8 +1268,9 @@ static inline int rhashtable_walk_init(struct rhashtable *ht, * For a completely stable walk you should construct your own data * structure outside the hash table. * - * This function may sleep so you must not call it from interrupt - * context or with spin locks held. + * This function may be called from any process context, including + * non-preemptable context, but cannot be called from softirq or + * hardirq context. * * You must call rhashtable_walk_exit after this function returns. */ diff --git a/include/linux/skbuff.h b/include/linux/skbuff.h index 9065477ed255..693564a9a979 100644 --- a/include/linux/skbuff.h +++ b/include/linux/skbuff.h @@ -573,6 +573,8 @@ enum { SKB_GSO_ESP = 1 << 15, SKB_GSO_UDP = 1 << 16, + + SKB_GSO_UDP_L4 = 1 << 17, }; #if BITS_PER_LONG > 32 @@ -1032,6 +1034,7 @@ static inline struct sk_buff *alloc_skb_fclone(unsigned int size, struct sk_buff *skb_morph(struct sk_buff *dst, struct sk_buff *src); int skb_copy_ubufs(struct sk_buff *skb, gfp_t gfp_mask); struct sk_buff *skb_clone(struct sk_buff *skb, gfp_t priority); +void skb_copy_header(struct sk_buff *new, const struct sk_buff *old); struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t priority); struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, gfp_t gfp_mask, bool fclone); @@ -1168,7 +1171,7 @@ void __skb_get_hash(struct sk_buff *skb); u32 __skb_get_hash_symmetric(const struct sk_buff *skb); u32 skb_get_poff(const struct sk_buff *skb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, - const struct flow_keys *keys, int hlen); + const struct flow_keys_basic *keys, int hlen); __be32 __skb_flow_get_ports(const struct sk_buff *skb, int thoff, u8 ip_proto, void *data, int hlen_proto); @@ -1205,13 +1208,14 @@ static inline bool skb_flow_dissect_flow_keys(const struct sk_buff *skb, NULL, 0, 0, 0, flags); } -static inline bool skb_flow_dissect_flow_keys_buf(struct flow_keys *flow, - void *data, __be16 proto, - int nhoff, int hlen, - unsigned int flags) +static inline bool +skb_flow_dissect_flow_keys_basic(const struct sk_buff *skb, + struct flow_keys_basic *flow, void *data, + __be16 proto, int nhoff, int hlen, + unsigned int flags) { memset(flow, 0, sizeof(*flow)); - return __skb_flow_dissect(NULL, &flow_keys_buf_dissector, flow, + return __skb_flow_dissect(skb, &flow_keys_basic_dissector, flow, data, proto, nhoff, hlen, flags); } @@ -2347,11 +2351,12 @@ static inline void skb_pop_mac_header(struct sk_buff *skb) static inline void skb_probe_transport_header(struct sk_buff *skb, const int offset_hint) { - struct flow_keys keys; + struct flow_keys_basic keys; if (skb_transport_header_was_set(skb)) return; - else if (skb_flow_dissect_flow_keys(skb, &keys, 0)) + + if (skb_flow_dissect_flow_keys_basic(skb, &keys, 0, 0, 0, 0, 0)) skb_set_transport_header(skb, keys.control.thoff); else skb_set_transport_header(skb, offset_hint); @@ -3131,6 +3136,7 @@ static inline void *skb_push_rcsum(struct sk_buff *skb, unsigned int len) return skb->data; } +int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len); /** * pskb_trim_rcsum - trim received skb and update checksum * @skb: buffer to trim @@ -3144,9 +3150,7 @@ static inline int pskb_trim_rcsum(struct sk_buff *skb, unsigned int len) { if (likely(len >= skb->len)) return 0; - if (skb->ip_summed == CHECKSUM_COMPLETE) - skb->ip_summed = CHECKSUM_NONE; - return __pskb_trim(skb, len); + return pskb_trim_rcsum_slow(skb, len); } static inline int __skb_trim_rcsum(struct sk_buff *skb, unsigned int len) diff --git a/include/linux/soc/ti/knav_dma.h b/include/linux/soc/ti/knav_dma.h index 66693bc4c6ad..7127ec301537 100644 --- a/include/linux/soc/ti/knav_dma.h +++ b/include/linux/soc/ti/knav_dma.h @@ -167,6 +167,8 @@ struct knav_dma_desc { void *knav_dma_open_channel(struct device *dev, const char *name, struct knav_dma_cfg *config); void knav_dma_close_channel(void *channel); +int knav_dma_get_flow(void *channel); +bool knav_dma_device_ready(void); #else static inline void *knav_dma_open_channel(struct device *dev, const char *name, struct knav_dma_cfg *config) @@ -176,6 +178,16 @@ static inline void *knav_dma_open_channel(struct device *dev, const char *name, static inline void knav_dma_close_channel(void *channel) {} +static inline int knav_dma_get_flow(void *channel) +{ + return -EINVAL; +} + +static inline bool knav_dma_device_ready(void) +{ + return false; +} + #endif #endif /* __SOC_TI_KEYSTONE_NAVIGATOR_DMA_H__ */ diff --git a/include/linux/soc/ti/knav_qmss.h b/include/linux/soc/ti/knav_qmss.h index 9f0ebb3bad27..9745df6ed9d3 100644 --- a/include/linux/soc/ti/knav_qmss.h +++ b/include/linux/soc/ti/knav_qmss.h @@ -86,5 +86,6 @@ int knav_pool_desc_map(void *ph, void *desc, unsigned size, void *knav_pool_desc_unmap(void *ph, dma_addr_t dma, unsigned dma_sz); dma_addr_t knav_pool_desc_virt_to_dma(void *ph, void *virt); void *knav_pool_desc_dma_to_virt(void *ph, dma_addr_t dma); +bool knav_qmss_device_ready(void); #endif /* __SOC_TI_KNAV_QMSS_H__ */ diff --git a/include/linux/socket.h b/include/linux/socket.h index ea50f4a65816..7ed4713d5337 100644 --- a/include/linux/socket.h +++ b/include/linux/socket.h @@ -207,8 +207,9 @@ struct ucred { * PF_SMC protocol family that * reuses AF_INET address family */ +#define AF_XDP 44 /* XDP sockets */ -#define AF_MAX 44 /* For now.. */ +#define AF_MAX 45 /* For now.. */ /* Protocol families, same as address families. */ #define PF_UNSPEC AF_UNSPEC @@ -257,6 +258,7 @@ struct ucred { #define PF_KCM AF_KCM #define PF_QIPCRTR AF_QIPCRTR #define PF_SMC AF_SMC +#define PF_XDP AF_XDP #define PF_MAX AF_MAX /* Maximum queue length specifiable by listen. */ @@ -338,6 +340,7 @@ struct ucred { #define SOL_NFC 280 #define SOL_KCM 281 #define SOL_TLS 282 +#define SOL_XDP 283 /* IPX options */ #define IPX_TYPE 1 diff --git a/include/linux/tcp.h b/include/linux/tcp.h index 8f4c54986f97..807776928cb8 100644 --- a/include/linux/tcp.h +++ b/include/linux/tcp.h @@ -228,7 +228,7 @@ struct tcp_sock { unused:2; u8 nonagle : 4,/* Disable Nagle algorithm? */ thin_lto : 1,/* Use linear timeouts for thin streams */ - unused1 : 1, + recvmsg_inq : 1,/* Indicate # of bytes in queue upon recvmsg */ repair : 1, frto : 1;/* F-RTO (RFC5682) activated in CA_Loss */ u8 repair_queue; @@ -281,6 +281,7 @@ struct tcp_sock { * receiver in Recovery. */ u32 prr_out; /* Total number of pkts sent during Recovery. */ u32 delivered; /* Total data packets delivered incl. rexmits */ + u32 delivered_ce; /* Like the above but only ECE marked packets */ u32 lost; /* Total data packets lost incl. rexmits */ u32 app_limited; /* limited until "delivered" reaches this val */ u64 first_tx_mstamp; /* start of window send phase */ diff --git a/include/linux/tnum.h b/include/linux/tnum.h index 0d2d3da46139..c7dc2b5902c0 100644 --- a/include/linux/tnum.h +++ b/include/linux/tnum.h @@ -23,8 +23,10 @@ struct tnum tnum_range(u64 min, u64 max); /* Arithmetic and logical ops */ /* Shift a tnum left (by a fixed shift) */ struct tnum tnum_lshift(struct tnum a, u8 shift); -/* Shift a tnum right (by a fixed shift) */ +/* Shift (rsh) a tnum right (by a fixed shift) */ struct tnum tnum_rshift(struct tnum a, u8 shift); +/* Shift (arsh) a tnum right (by a fixed min_shift) */ +struct tnum tnum_arshift(struct tnum a, u8 min_shift); /* Add two tnums, return @a + @b */ struct tnum tnum_add(struct tnum a, struct tnum b); /* Subtract two tnums, return @a - @b */ diff --git a/include/linux/u64_stats_sync.h b/include/linux/u64_stats_sync.h index 07ee0f84a46c..a27604f99ed0 100644 --- a/include/linux/u64_stats_sync.h +++ b/include/linux/u64_stats_sync.h @@ -112,20 +112,6 @@ u64_stats_update_end_irqrestore(struct u64_stats_sync *syncp, #endif } -static inline void u64_stats_update_begin_raw(struct u64_stats_sync *syncp) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - raw_write_seqcount_begin(&syncp->seq); -#endif -} - -static inline void u64_stats_update_end_raw(struct u64_stats_sync *syncp) -{ -#if BITS_PER_LONG==32 && defined(CONFIG_SMP) - raw_write_seqcount_end(&syncp->seq); -#endif -} - static inline unsigned int __u64_stats_fetch_begin(const struct u64_stats_sync *syncp) { #if BITS_PER_LONG==32 && defined(CONFIG_SMP) diff --git a/include/linux/udp.h b/include/linux/udp.h index eaea63bc79bb..ca840345571b 100644 --- a/include/linux/udp.h +++ b/include/linux/udp.h @@ -55,6 +55,7 @@ struct udp_sock { * when the socket is uncorked. */ __u16 len; /* total length of pending frames */ + __u16 gso_size; /* * Fields specific to UDP-Lite. */ @@ -87,6 +88,8 @@ struct udp_sock { int forward_deficit; }; +#define UDP_MAX_SEGMENTS (1 << 6UL) + static inline struct udp_sock *udp_sk(const struct sock *sk) { return (struct udp_sock *)sk; diff --git a/include/net/addrconf.h b/include/net/addrconf.h index 378d601258be..8312cc25a3af 100644 --- a/include/net/addrconf.h +++ b/include/net/addrconf.h @@ -308,6 +308,20 @@ static inline struct inet6_dev *__in6_dev_get(const struct net_device *dev) } /** + * __in6_dev_get_safely - get inet6_dev pointer from netdevice + * @dev: network device + * + * This is a safer version of __in6_dev_get + */ +static inline struct inet6_dev *__in6_dev_get_safely(const struct net_device *dev) +{ + if (likely(dev)) + return rcu_dereference_rtnl(dev->ip6_ptr); + else + return NULL; +} + +/** * in6_dev_get - get inet6_dev pointer from netdevice * @dev: network device * diff --git a/include/net/ax88796.h b/include/net/ax88796.h index b9a3beca0ce4..84b3785d0e66 100644 --- a/include/net/ax88796.h +++ b/include/net/ax88796.h @@ -12,6 +12,10 @@ #ifndef __NET_AX88796_PLAT_H #define __NET_AX88796_PLAT_H +struct sk_buff; +struct net_device; +struct platform_device; + #define AXFLG_HAS_EEPROM (1<<0) #define AXFLG_MAC_FROMDEV (1<<1) /* device already has MAC */ #define AXFLG_HAS_93CX6 (1<<2) /* use eeprom_93cx6 driver */ @@ -26,6 +30,16 @@ struct ax_plat_data { u32 *reg_offsets; /* register offsets */ u8 *mac_addr; /* MAC addr (only used when AXFLG_MAC_FROMPLATFORM is used */ + + /* uses default ax88796 buffer if set to NULL */ + void (*block_output)(struct net_device *dev, int count, + const unsigned char *buf, int star_page); + void (*block_input)(struct net_device *dev, int count, + struct sk_buff *skb, int ring_offset); + /* returns nonzero if a pending interrupt request might by caused by + * the ax88786. Handles all interrupts if set to NULL + */ + int (*check_irq)(struct platform_device *pdev); }; #endif /* __NET_AX88796_PLAT_H */ diff --git a/include/net/dsa.h b/include/net/dsa.h index 60fb4ec8ba61..fdbd6082945d 100644 --- a/include/net/dsa.h +++ b/include/net/dsa.h @@ -20,12 +20,14 @@ #include <linux/of.h> #include <linux/ethtool.h> #include <linux/net_tstamp.h> +#include <linux/phy.h> #include <net/devlink.h> #include <net/switchdev.h> struct tc_action; struct phy_device; struct fixed_phy_status; +struct phylink_link_state; enum dsa_tag_protocol { DSA_TAG_PROTO_NONE = 0, @@ -199,6 +201,7 @@ struct dsa_port { u8 stp_state; struct net_device *bridge_dev; struct devlink_port devlink_port; + struct phylink *pl; /* * Original copy of the master netdev ethtool_ops */ @@ -354,12 +357,36 @@ struct dsa_switch_ops { struct fixed_phy_status *st); /* + * PHYLINK integration + */ + void (*phylink_validate)(struct dsa_switch *ds, int port, + unsigned long *supported, + struct phylink_link_state *state); + int (*phylink_mac_link_state)(struct dsa_switch *ds, int port, + struct phylink_link_state *state); + void (*phylink_mac_config)(struct dsa_switch *ds, int port, + unsigned int mode, + const struct phylink_link_state *state); + void (*phylink_mac_an_restart)(struct dsa_switch *ds, int port); + void (*phylink_mac_link_down)(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface); + void (*phylink_mac_link_up)(struct dsa_switch *ds, int port, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev); + void (*phylink_fixed_state)(struct dsa_switch *ds, int port, + struct phylink_link_state *state); + /* * ethtool hardware statistics. */ - void (*get_strings)(struct dsa_switch *ds, int port, uint8_t *data); + void (*get_strings)(struct dsa_switch *ds, int port, + u32 stringset, uint8_t *data); void (*get_ethtool_stats)(struct dsa_switch *ds, int port, uint64_t *data); - int (*get_sset_count)(struct dsa_switch *ds, int port); + int (*get_sset_count)(struct dsa_switch *ds, int port, int sset); + void (*get_ethtool_phy_stats)(struct dsa_switch *ds, + int port, uint64_t *data); /* * ethtool Wake-on-LAN @@ -588,4 +615,10 @@ static inline int call_dsa_notifiers(unsigned long val, struct net_device *dev, #define BRCM_TAG_GET_PORT(v) ((v) >> 8) #define BRCM_TAG_GET_QUEUE(v) ((v) & 0xff) + +int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data); +int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data); +int dsa_port_get_phy_sset_count(struct dsa_port *dp); +void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up); + #endif diff --git a/include/net/fib_rules.h b/include/net/fib_rules.h index e5cfcfc7dd93..b473df5b9512 100644 --- a/include/net/fib_rules.h +++ b/include/net/fib_rules.h @@ -75,7 +75,8 @@ struct fib_rules_ops { int (*configure)(struct fib_rule *, struct sk_buff *, struct fib_rule_hdr *, - struct nlattr **); + struct nlattr **, + struct netlink_ext_ack *); int (*delete)(struct fib_rule *); int (*compare)(struct fib_rule *, struct fib_rule_hdr *, diff --git a/include/net/flow_dissector.h b/include/net/flow_dissector.h index d1fcf2442a42..adc24df56b90 100644 --- a/include/net/flow_dissector.h +++ b/include/net/flow_dissector.h @@ -226,6 +226,11 @@ struct flow_dissector { unsigned short int offset[FLOW_DISSECTOR_KEY_MAX]; }; +struct flow_keys_basic { + struct flow_dissector_key_control control; + struct flow_dissector_key_basic basic; +}; + struct flow_keys { struct flow_dissector_key_control control; #define FLOW_KEYS_HASH_START_FIELD basic @@ -244,7 +249,7 @@ __be32 flow_get_u32_src(const struct flow_keys *flow); __be32 flow_get_u32_dst(const struct flow_keys *flow); extern struct flow_dissector flow_keys_dissector; -extern struct flow_dissector flow_keys_buf_dissector; +extern struct flow_dissector flow_keys_basic_dissector; /* struct flow_keys_digest: * diff --git a/include/net/if_inet6.h b/include/net/if_inet6.h index d4088d1a688d..db389253dc2a 100644 --- a/include/net/if_inet6.h +++ b/include/net/if_inet6.h @@ -64,7 +64,7 @@ struct inet6_ifaddr { struct delayed_work dad_work; struct inet6_dev *idev; - struct rt6_info *rt; + struct fib6_info *rt; struct hlist_node addr_lst; struct list_head if_list; @@ -143,8 +143,7 @@ struct ipv6_ac_socklist { struct ifacaddr6 { struct in6_addr aca_addr; - struct inet6_dev *aca_idev; - struct rt6_info *aca_rt; + struct fib6_info *aca_rt; struct ifacaddr6 *aca_next; int aca_users; refcount_t aca_refcnt; diff --git a/include/net/inet_connection_sock.h b/include/net/inet_connection_sock.h index b68fea022a82..0a6c9e0f2b5a 100644 --- a/include/net/inet_connection_sock.h +++ b/include/net/inet_connection_sock.h @@ -23,8 +23,6 @@ #include <net/inet_sock.h> #include <net/request_sock.h> -#define INET_CSK_DEBUG 1 - /* Cancel timers, when they are not required. */ #undef INET_CSK_CLEAR_TIMERS @@ -77,6 +75,7 @@ struct inet_connection_sock_af_ops { * @icsk_af_ops Operations which are AF_INET{4,6} specific * @icsk_ulp_ops Pluggable ULP control hook * @icsk_ulp_data ULP private data + * @icsk_clean_acked Clean acked data hook * @icsk_listen_portaddr_node hash to the portaddr listener hashtable * @icsk_ca_state: Congestion control state * @icsk_retransmits: Number of unrecovered [RTO] timeouts @@ -102,6 +101,7 @@ struct inet_connection_sock { const struct inet_connection_sock_af_ops *icsk_af_ops; const struct tcp_ulp_ops *icsk_ulp_ops; void *icsk_ulp_data; + void (*icsk_clean_acked)(struct sock *sk, u32 acked_seq); struct hlist_node icsk_listen_portaddr_node; unsigned int (*icsk_sync_mss)(struct sock *sk, u32 pmtu); __u8 icsk_ca_state:6, @@ -194,10 +194,6 @@ static inline void inet_csk_delack_init(struct sock *sk) void inet_csk_delete_keepalive_timer(struct sock *sk); void inet_csk_reset_keepalive_timer(struct sock *sk, unsigned long timeout); -#ifdef INET_CSK_DEBUG -extern const char inet_csk_timer_bug_msg[]; -#endif - static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) { struct inet_connection_sock *icsk = inet_csk(sk); @@ -212,12 +208,9 @@ static inline void inet_csk_clear_xmit_timer(struct sock *sk, const int what) #ifdef INET_CSK_CLEAR_TIMERS sk_stop_timer(sk, &icsk->icsk_delack_timer); #endif + } else { + pr_debug("inet_csk BUG: unknown timer value\n"); } -#ifdef INET_CSK_DEBUG - else { - pr_debug("%s", inet_csk_timer_bug_msg); - } -#endif } /* @@ -230,10 +223,8 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, struct inet_connection_sock *icsk = inet_csk(sk); if (when > max_when) { -#ifdef INET_CSK_DEBUG pr_debug("reset_xmit_timer: sk=%p %d when=0x%lx, caller=%p\n", sk, what, when, current_text_addr()); -#endif when = max_when; } @@ -247,12 +238,9 @@ static inline void inet_csk_reset_xmit_timer(struct sock *sk, const int what, icsk->icsk_ack.pending |= ICSK_ACK_TIMER; icsk->icsk_ack.timeout = jiffies + when; sk_reset_timer(sk, &icsk->icsk_delack_timer, icsk->icsk_ack.timeout); + } else { + pr_debug("inet_csk BUG: unknown timer value\n"); } -#ifdef INET_CSK_DEBUG - else { - pr_debug("%s", inet_csk_timer_bug_msg); - } -#endif } static inline unsigned long diff --git a/include/net/inet_sock.h b/include/net/inet_sock.h index 0a671c32d6b9..83d5b3c2ac42 100644 --- a/include/net/inet_sock.h +++ b/include/net/inet_sock.h @@ -147,6 +147,7 @@ struct inet_cork { __u8 ttl; __s16 tos; char priority; + __u16 gso_size; }; struct inet_cork_full { diff --git a/include/net/inet_timewait_sock.h b/include/net/inet_timewait_sock.h index c7be1ca8e562..659d8ed5a3bc 100644 --- a/include/net/inet_timewait_sock.h +++ b/include/net/inet_timewait_sock.h @@ -62,6 +62,7 @@ struct inet_timewait_sock { #define tw_dr __tw_common.skc_tw_dr int tw_timeout; + __u32 tw_mark; volatile unsigned char tw_substate; unsigned char tw_rcv_wscale; diff --git a/include/net/ip.h b/include/net/ip.h index ecffd843e7b8..bada1f1f871e 100644 --- a/include/net/ip.h +++ b/include/net/ip.h @@ -76,6 +76,7 @@ struct ipcm_cookie { __u8 ttl; __s16 tos; char priority; + __u16 gso_size; }; #define IPCB(skb) ((struct inet_skb_parm*)((skb)->cb)) @@ -171,7 +172,7 @@ struct sk_buff *ip_make_skb(struct sock *sk, struct flowi4 *fl4, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, - unsigned int flags); + struct inet_cork *cork, unsigned int flags); static inline struct sk_buff *ip_finish_skb(struct sock *sk, struct flowi4 *fl4) { @@ -396,6 +397,9 @@ static inline unsigned int ip_skb_dst_mtu(struct sock *sk, return min(READ_ONCE(skb_dst(skb)->dev->mtu), IP_MAX_MTU); } +int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, + u32 *metrics); + u32 ip_idents_reserve(u32 hash, int segs); void __ip_select_ident(struct net *net, struct iphdr *iph, int segs); diff --git a/include/net/ip6_fib.h b/include/net/ip6_fib.h index 5e86fd9dc857..a3ec08d05756 100644 --- a/include/net/ip6_fib.h +++ b/include/net/ip6_fib.h @@ -38,6 +38,7 @@ #endif struct rt6_info; +struct fib6_info; struct fib6_config { u32 fc_table; @@ -74,12 +75,12 @@ struct fib6_node { #ifdef CONFIG_IPV6_SUBTREES struct fib6_node __rcu *subtree; #endif - struct rt6_info __rcu *leaf; + struct fib6_info __rcu *leaf; __u16 fn_bit; /* bit key */ __u16 fn_flags; int fn_sernum; - struct rt6_info __rcu *rr_ptr; + struct fib6_info __rcu *rr_ptr; struct rcu_head rcu; }; @@ -94,11 +95,6 @@ struct fib6_gc_args { #define FIB6_SUBTREE(fn) (rcu_dereference_protected((fn)->subtree, 1)) #endif -struct mx6_config { - const u32 *mx; - DECLARE_BITMAP(mx_valid, RTAX_MAX); -}; - /* * routing information * @@ -127,92 +123,104 @@ struct rt6_exception { #define FIB6_EXCEPTION_BUCKET_SIZE (1 << FIB6_EXCEPTION_BUCKET_SIZE_SHIFT) #define FIB6_MAX_DEPTH 5 -struct rt6_info { - struct dst_entry dst; - struct rt6_info __rcu *rt6_next; - struct rt6_info *from; +struct fib6_nh { + struct in6_addr nh_gw; + struct net_device *nh_dev; + struct lwtunnel_state *nh_lwtstate; - /* - * Tail elements of dst_entry (__refcnt etc.) - * and these elements (rarely used in hot path) are in - * the same cache line. - */ - struct fib6_table *rt6i_table; - struct fib6_node __rcu *rt6i_node; + unsigned int nh_flags; + atomic_t nh_upper_bound; + int nh_weight; +}; - struct in6_addr rt6i_gateway; +struct fib6_info { + struct fib6_table *fib6_table; + struct fib6_info __rcu *fib6_next; + struct fib6_node __rcu *fib6_node; /* Multipath routes: - * siblings is a list of rt6_info that have the the same metric/weight, + * siblings is a list of fib6_info that have the the same metric/weight, * destination, but not the same gateway. nsiblings is just a cache * to speed up lookup. */ - struct list_head rt6i_siblings; - unsigned int rt6i_nsiblings; - atomic_t rt6i_nh_upper_bound; + struct list_head fib6_siblings; + unsigned int fib6_nsiblings; - atomic_t rt6i_ref; + atomic_t fib6_ref; + unsigned long expires; + struct dst_metrics *fib6_metrics; +#define fib6_pmtu fib6_metrics->metrics[RTAX_MTU-1] - unsigned int rt6i_nh_flags; + struct rt6key fib6_dst; + u32 fib6_flags; + struct rt6key fib6_src; + struct rt6key fib6_prefsrc; - /* These are in a separate cache line. */ - struct rt6key rt6i_dst ____cacheline_aligned_in_smp; - u32 rt6i_flags; + struct rt6_info * __percpu *rt6i_pcpu; + struct rt6_exception_bucket __rcu *rt6i_exception_bucket; + + u32 fib6_metric; + u8 fib6_protocol; + u8 fib6_type; + u8 exception_bucket_flushed:1, + should_flush:1, + dst_nocount:1, + dst_nopolicy:1, + dst_host:1, + unused:3; + + struct fib6_nh fib6_nh; +}; + +struct rt6_info { + struct dst_entry dst; + struct fib6_info __rcu *from; + + struct rt6key rt6i_dst; struct rt6key rt6i_src; + struct in6_addr rt6i_gateway; + struct inet6_dev *rt6i_idev; + u32 rt6i_flags; struct rt6key rt6i_prefsrc; struct list_head rt6i_uncached; struct uncached_list *rt6i_uncached_list; - struct inet6_dev *rt6i_idev; - struct rt6_info * __percpu *rt6i_pcpu; - struct rt6_exception_bucket __rcu *rt6i_exception_bucket; - - u32 rt6i_metric; - u32 rt6i_pmtu; /* more non-fragment space at head required */ - int rt6i_nh_weight; unsigned short rt6i_nfheader_len; - u8 rt6i_protocol; - u8 exception_bucket_flushed:1, - should_flush:1, - unused:6; }; #define for_each_fib6_node_rt_rcu(fn) \ for (rt = rcu_dereference((fn)->leaf); rt; \ - rt = rcu_dereference(rt->rt6_next)) + rt = rcu_dereference(rt->fib6_next)) #define for_each_fib6_walker_rt(w) \ for (rt = (w)->leaf; rt; \ - rt = rcu_dereference_protected(rt->rt6_next, 1)) + rt = rcu_dereference_protected(rt->fib6_next, 1)) static inline struct inet6_dev *ip6_dst_idev(struct dst_entry *dst) { return ((struct rt6_info *)dst)->rt6i_idev; } -static inline void rt6_clean_expires(struct rt6_info *rt) +static inline void fib6_clean_expires(struct fib6_info *f6i) { - rt->rt6i_flags &= ~RTF_EXPIRES; - rt->dst.expires = 0; + f6i->fib6_flags &= ~RTF_EXPIRES; + f6i->expires = 0; } -static inline void rt6_set_expires(struct rt6_info *rt, unsigned long expires) +static inline void fib6_set_expires(struct fib6_info *f6i, + unsigned long expires) { - rt->dst.expires = expires; - rt->rt6i_flags |= RTF_EXPIRES; + f6i->expires = expires; + f6i->fib6_flags |= RTF_EXPIRES; } -static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) +static inline bool fib6_check_expired(const struct fib6_info *f6i) { - struct rt6_info *rt; - - for (rt = rt0; rt && !(rt->rt6i_flags & RTF_EXPIRES); rt = rt->from); - if (rt && rt != rt0) - rt0->dst.expires = rt->dst.expires; - dst_set_expires(&rt0->dst, timeout); - rt0->rt6i_flags |= RTF_EXPIRES; + if (f6i->fib6_flags & RTF_EXPIRES) + return time_after(jiffies, f6i->expires); + return false; } /* Function to safely get fn->sernum for passed in rt @@ -220,14 +228,13 @@ static inline void rt6_update_expires(struct rt6_info *rt0, int timeout) * Return true if we can get cookie safely * Return false if not */ -static inline bool rt6_get_cookie_safe(const struct rt6_info *rt, - u32 *cookie) +static inline bool fib6_get_cookie_safe(const struct fib6_info *f6i, + u32 *cookie) { struct fib6_node *fn; bool status = false; - rcu_read_lock(); - fn = rcu_dereference(rt->rt6i_node); + fn = rcu_dereference(f6i->fib6_node); if (fn) { *cookie = fn->fn_sernum; @@ -236,19 +243,22 @@ static inline bool rt6_get_cookie_safe(const struct rt6_info *rt, status = true; } - rcu_read_unlock(); return status; } static inline u32 rt6_get_cookie(const struct rt6_info *rt) { + struct fib6_info *from; u32 cookie = 0; - if (rt->rt6i_flags & RTF_PCPU || - (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from)) - rt = rt->from; + rcu_read_lock(); + + from = rcu_dereference(rt->from); + if (from && (rt->rt6i_flags & RTF_PCPU || + unlikely(!list_empty(&rt->rt6i_uncached)))) + fib6_get_cookie_safe(from, &cookie); - rt6_get_cookie_safe(rt, &cookie); + rcu_read_unlock(); return cookie; } @@ -262,20 +272,18 @@ static inline void ip6_rt_put(struct rt6_info *rt) dst_release(&rt->dst); } -void rt6_free_pcpu(struct rt6_info *non_pcpu_rt); +struct fib6_info *fib6_info_alloc(gfp_t gfp_flags); +void fib6_info_destroy(struct fib6_info *f6i); -static inline void rt6_hold(struct rt6_info *rt) +static inline void fib6_info_hold(struct fib6_info *f6i) { - atomic_inc(&rt->rt6i_ref); + atomic_inc(&f6i->fib6_ref); } -static inline void rt6_release(struct rt6_info *rt) +static inline void fib6_info_release(struct fib6_info *f6i) { - if (atomic_dec_and_test(&rt->rt6i_ref)) { - rt6_free_pcpu(rt); - dst_dev_put(&rt->dst); - dst_release(&rt->dst); - } + if (f6i && atomic_dec_and_test(&f6i->fib6_ref)) + fib6_info_destroy(f6i); } enum fib6_walk_state { @@ -291,7 +299,7 @@ enum fib6_walk_state { struct fib6_walker { struct list_head lh; struct fib6_node *root, *node; - struct rt6_info *leaf; + struct fib6_info *leaf; enum fib6_walk_state state; unsigned int skip; unsigned int count; @@ -355,7 +363,7 @@ typedef struct rt6_info *(*pol_lookup_t)(struct net *, struct fib6_entry_notifier_info { struct fib_notifier_info info; /* must be first */ - struct rt6_info *rt; + struct fib6_info *rt; }; /* @@ -377,15 +385,19 @@ struct fib6_node *fib6_locate(struct fib6_node *root, const struct in6_addr *saddr, int src_len, bool exact_match); -void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *arg), +void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *arg), void *arg); -int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc, - struct netlink_ext_ack *extack); -int fib6_del(struct rt6_info *rt, struct nl_info *info); +int fib6_add(struct fib6_node *root, struct fib6_info *rt, + struct nl_info *info, struct netlink_ext_ack *extack); +int fib6_del(struct fib6_info *rt, struct nl_info *info); + +static inline struct net_device *fib6_info_nh_dev(const struct fib6_info *f6i) +{ + return f6i->fib6_nh.nh_dev; +} -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, +void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int flags); void fib6_run_gc(unsigned long expires, struct net *net, bool force); @@ -408,8 +420,14 @@ void __net_exit fib6_notifier_exit(struct net *net); unsigned int fib6_tables_seq_read(struct net *net); int fib6_tables_dump(struct net *net, struct notifier_block *nb); -void fib6_update_sernum(struct rt6_info *rt); -void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt); +void fib6_update_sernum(struct net *net, struct fib6_info *rt); +void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt); + +void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val); +static inline bool fib6_metric_locked(struct fib6_info *f6i, int metric) +{ + return !!(f6i->fib6_metrics->metrics[RTAX_LOCK - 1] & (1 << metric)); +} #ifdef CONFIG_IPV6_MULTIPLE_TABLES int fib6_rules_init(void); diff --git a/include/net/ip6_route.h b/include/net/ip6_route.h index 08b132381984..4cf1ef935ed9 100644 --- a/include/net/ip6_route.h +++ b/include/net/ip6_route.h @@ -66,9 +66,9 @@ static inline bool rt6_need_strict(const struct in6_addr *daddr) (IPV6_ADDR_MULTICAST | IPV6_ADDR_LINKLOCAL | IPV6_ADDR_LOOPBACK); } -static inline bool rt6_qualify_for_ecmp(const struct rt6_info *rt) +static inline bool rt6_qualify_for_ecmp(const struct fib6_info *f6i) { - return (rt->rt6i_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == + return (f6i->fib6_flags & (RTF_GATEWAY|RTF_ADDRCONF|RTF_DYNAMIC)) == RTF_GATEWAY; } @@ -100,29 +100,29 @@ void ip6_route_cleanup(void); int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg); -int ip6_route_add(struct fib6_config *cfg, struct netlink_ext_ack *extack); -int ip6_ins_rt(struct rt6_info *); -int ip6_del_rt(struct rt6_info *); +int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, + struct netlink_ext_ack *extack); +int ip6_ins_rt(struct net *net, struct fib6_info *f6i); +int ip6_del_rt(struct net *net, struct fib6_info *f6i); -void rt6_flush_exceptions(struct rt6_info *rt); -int rt6_remove_exception_rt(struct rt6_info *rt); -void rt6_age_exceptions(struct rt6_info *rt, struct fib6_gc_args *gc_args, +void rt6_flush_exceptions(struct fib6_info *f6i); +void rt6_age_exceptions(struct fib6_info *f6i, struct fib6_gc_args *gc_args, unsigned long now); -static inline int ip6_route_get_saddr(struct net *net, struct rt6_info *rt, +static inline int ip6_route_get_saddr(struct net *net, struct fib6_info *f6i, const struct in6_addr *daddr, unsigned int prefs, struct in6_addr *saddr) { - struct inet6_dev *idev = - rt ? ip6_dst_idev((struct dst_entry *)rt) : NULL; int err = 0; - if (rt && rt->rt6i_prefsrc.plen) - *saddr = rt->rt6i_prefsrc.addr; - else - err = ipv6_dev_get_saddr(net, idev ? idev->dev : NULL, - daddr, prefs, saddr); + if (f6i && f6i->fib6_prefsrc.plen) { + *saddr = f6i->fib6_prefsrc.addr; + } else { + struct net_device *dev = f6i ? fib6_info_nh_dev(f6i) : NULL; + + err = ipv6_dev_get_saddr(net, dev, daddr, prefs, saddr); + } return err; } @@ -137,8 +137,9 @@ struct dst_entry *icmp6_dst_alloc(struct net_device *dev, struct flowi6 *fl6); void fib6_force_start_gc(struct net *net); -struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, - const struct in6_addr *addr, bool anycast); +struct fib6_info *addrconf_f6i_alloc(struct net *net, struct inet6_dev *idev, + const struct in6_addr *addr, bool anycast, + gfp_t gfp_flags); struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, int flags); @@ -147,9 +148,11 @@ struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, * support functions for ND * */ -struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, +struct fib6_info *rt6_get_dflt_router(struct net *net, + const struct in6_addr *addr, struct net_device *dev); -struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, +struct fib6_info *rt6_add_dflt_router(struct net *net, + const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); void rt6_purge_dflt_routers(struct net *net); @@ -174,14 +177,14 @@ struct rt6_rtnl_dump_arg { struct net *net; }; -int rt6_dump_route(struct rt6_info *rt, void *p_arg); +int rt6_dump_route(struct fib6_info *f6i, void *p_arg); void rt6_mtu_change(struct net_device *dev, unsigned int mtu); void rt6_remove_prefsrc(struct inet6_ifaddr *ifp); void rt6_clean_tohost(struct net *net, struct in6_addr *gateway); void rt6_sync_up(struct net_device *dev, unsigned int nh_flags); void rt6_disable_ip(struct net_device *dev, unsigned long event); void rt6_sync_down_dev(struct net_device *dev, unsigned long event); -void rt6_multipath_rebalance(struct rt6_info *rt); +void rt6_multipath_rebalance(struct fib6_info *f6i); void rt6_uncached_list_add(struct rt6_info *rt); void rt6_uncached_list_del(struct rt6_info *rt); @@ -269,12 +272,35 @@ static inline struct in6_addr *rt6_nexthop(struct rt6_info *rt, return daddr; } -static inline bool rt6_duplicate_nexthop(struct rt6_info *a, struct rt6_info *b) +static inline bool rt6_duplicate_nexthop(struct fib6_info *a, struct fib6_info *b) +{ + return a->fib6_nh.nh_dev == b->fib6_nh.nh_dev && + ipv6_addr_equal(&a->fib6_nh.nh_gw, &b->fib6_nh.nh_gw) && + !lwtunnel_cmp_encap(a->fib6_nh.nh_lwtstate, b->fib6_nh.nh_lwtstate); +} + +static inline unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) { - return a->dst.dev == b->dst.dev && - a->rt6i_idev == b->rt6i_idev && - ipv6_addr_equal(&a->rt6i_gateway, &b->rt6i_gateway) && - !lwtunnel_cmp_encap(a->dst.lwtstate, b->dst.lwtstate); + struct inet6_dev *idev; + unsigned int mtu; + + if (dst_metric_locked(dst, RTAX_MTU)) { + mtu = dst_metric_raw(dst, RTAX_MTU); + if (mtu) + return mtu; + } + + mtu = IPV6_MIN_MTU; + rcu_read_lock(); + idev = __in6_dev_get(dst->dev); + if (idev) + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + + return mtu; } +struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, + struct net_device *dev, struct sk_buff *skb, + const void *daddr); #endif diff --git a/include/net/ip_tunnels.h b/include/net/ip_tunnels.h index 540a4b4417bf..90ff430f5e9d 100644 --- a/include/net/ip_tunnels.h +++ b/include/net/ip_tunnels.h @@ -379,6 +379,17 @@ static inline u8 ip_tunnel_get_dsfield(const struct iphdr *iph, return 0; } +static inline u8 ip_tunnel_get_ttl(const struct iphdr *iph, + const struct sk_buff *skb) +{ + if (skb->protocol == htons(ETH_P_IP)) + return iph->ttl; + else if (skb->protocol == htons(ETH_P_IPV6)) + return ((const struct ipv6hdr *)iph)->hop_limit; + else + return 0; +} + /* Propogate ECN bits out */ static inline u8 ip_tunnel_ecn_encap(u8 tos, const struct iphdr *iph, const struct sk_buff *skb) @@ -466,12 +477,12 @@ static inline struct ip_tunnel_info *lwt_tun_info(struct lwtunnel_state *lwtstat return (struct ip_tunnel_info *)lwtstate->data; } -extern struct static_key ip_tunnel_metadata_cnt; +DECLARE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); /* Returns > 0 if metadata should be collected */ static inline int ip_tunnel_collect_metadata(void) { - return static_key_false(&ip_tunnel_metadata_cnt); + return static_branch_unlikely(&ip_tunnel_metadata_cnt); } void __init ip_tunnel_core_init(void); diff --git a/include/net/ip_vs.h b/include/net/ip_vs.h index eb0bec043c96..0ac795b41ab8 100644 --- a/include/net/ip_vs.h +++ b/include/net/ip_vs.h @@ -668,6 +668,7 @@ struct ip_vs_dest { volatile unsigned int flags; /* dest status flags */ atomic_t conn_flags; /* flags to copy to conn */ atomic_t weight; /* server weight */ + atomic_t last_weight; /* server latest weight */ refcount_t refcnt; /* reference counter */ struct ip_vs_stats stats; /* statistics */ diff --git a/include/net/ipv6.h b/include/net/ipv6.h index 836f31af1369..798558fd1681 100644 --- a/include/net/ipv6.h +++ b/include/net/ipv6.h @@ -298,6 +298,7 @@ struct ipcm6_cookie { __s16 tclass; __s8 dontfrag; struct ipv6_txoptions *opt; + __u16 gso_size; }; static inline struct ipv6_txoptions *txopt_get(const struct ipv6_pinfo *np) @@ -950,6 +951,7 @@ struct sk_buff *ip6_make_skb(struct sock *sk, void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, + struct inet_cork_full *cork, const struct sockcm_cookie *sockc); static inline struct sk_buff *ip6_finish_skb(struct sock *sk) @@ -958,8 +960,6 @@ static inline struct sk_buff *ip6_finish_skb(struct sock *sk) &inet6_sk(sk)->cork); } -unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst); - int ip6_dst_lookup(struct net *net, struct sock *sk, struct dst_entry **dst, struct flowi6 *fl6); struct dst_entry *ip6_dst_lookup_flow(const struct sock *sk, struct flowi6 *fl6, @@ -1044,8 +1044,6 @@ void ipv6_local_error(struct sock *sk, int err, struct flowi6 *fl6, u32 info); void ipv6_local_rxpmtu(struct sock *sk, struct flowi6 *fl6, u32 mtu); int inet6_release(struct socket *sock); -int __inet6_bind(struct sock *sock, struct sockaddr *uaddr, int addr_len, - bool force_bind_address_no_port, bool with_lock); int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len); int inet6_getname(struct socket *sock, struct sockaddr *uaddr, int peer); diff --git a/include/net/neighbour.h b/include/net/neighbour.h index e421f86af043..6c1eecd56a4d 100644 --- a/include/net/neighbour.h +++ b/include/net/neighbour.h @@ -246,6 +246,7 @@ static inline void *neighbour_priv(const struct neighbour *n) #define NEIGH_UPDATE_F_OVERRIDE 0x00000001 #define NEIGH_UPDATE_F_WEAK_OVERRIDE 0x00000002 #define NEIGH_UPDATE_F_OVERRIDE_ISROUTER 0x00000004 +#define NEIGH_UPDATE_F_EXT_LEARNED 0x20000000 #define NEIGH_UPDATE_F_ISROUTER 0x40000000 #define NEIGH_UPDATE_F_ADMIN 0x80000000 @@ -526,5 +527,21 @@ static inline void neigh_ha_snapshot(char *dst, const struct neighbour *n, } while (read_seqretry(&n->ha_lock, seq)); } - +static inline void neigh_update_ext_learned(struct neighbour *neigh, u32 flags, + int *notify) +{ + u8 ndm_flags = 0; + + if (!(flags & NEIGH_UPDATE_F_ADMIN)) + return; + + ndm_flags |= (flags & NEIGH_UPDATE_F_EXT_LEARNED) ? NTF_EXT_LEARNED : 0; + if ((neigh->flags ^ ndm_flags) & NTF_EXT_LEARNED) { + if (ndm_flags & NTF_EXT_LEARNED) + neigh->flags |= NTF_EXT_LEARNED; + else + neigh->flags &= ~NTF_EXT_LEARNED; + *notify = 1; + } +} #endif diff --git a/include/net/netfilter/ipv4/nf_nat_masquerade.h b/include/net/netfilter/ipv4/nf_nat_masquerade.h index ebd869473603..cd24be4c4a99 100644 --- a/include/net/netfilter/ipv4/nf_nat_masquerade.h +++ b/include/net/netfilter/ipv4/nf_nat_masquerade.h @@ -6,7 +6,7 @@ unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, const struct net_device *out); void nf_nat_masquerade_ipv4_register_notifier(void); diff --git a/include/net/netfilter/ipv6/nf_nat_masquerade.h b/include/net/netfilter/ipv6/nf_nat_masquerade.h index 1ed4f2631ed6..0c3b5ebf0bb8 100644 --- a/include/net/netfilter/ipv6/nf_nat_masquerade.h +++ b/include/net/netfilter/ipv6/nf_nat_masquerade.h @@ -3,7 +3,7 @@ #define _NF_NAT_MASQUERADE_IPV6_H_ unsigned int -nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, +nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out); void nf_nat_masquerade_ipv6_register_notifier(void); void nf_nat_masquerade_ipv6_unregister_notifier(void); diff --git a/include/net/netfilter/nf_flow_table.h b/include/net/netfilter/nf_flow_table.h index 833752dd0c58..ba9fa4592f2b 100644 --- a/include/net/netfilter/nf_flow_table.h +++ b/include/net/netfilter/nf_flow_table.h @@ -6,6 +6,7 @@ #include <linux/netdevice.h> #include <linux/rhashtable.h> #include <linux/rcupdate.h> +#include <linux/netfilter/nf_conntrack_tuple_common.h> #include <net/dst.h> struct nf_flowtable; @@ -13,25 +14,24 @@ struct nf_flowtable; struct nf_flowtable_type { struct list_head list; int family; - void (*gc)(struct work_struct *work); + int (*init)(struct nf_flowtable *ft); void (*free)(struct nf_flowtable *ft); - const struct rhashtable_params *params; nf_hookfn *hook; struct module *owner; }; struct nf_flowtable { + struct list_head list; struct rhashtable rhashtable; const struct nf_flowtable_type *type; struct delayed_work gc_work; }; enum flow_offload_tuple_dir { - FLOW_OFFLOAD_DIR_ORIGINAL, - FLOW_OFFLOAD_DIR_REPLY, - __FLOW_OFFLOAD_DIR_MAX = FLOW_OFFLOAD_DIR_REPLY, + FLOW_OFFLOAD_DIR_ORIGINAL = IP_CT_DIR_ORIGINAL, + FLOW_OFFLOAD_DIR_REPLY = IP_CT_DIR_REPLY, + FLOW_OFFLOAD_DIR_MAX = IP_CT_DIR_MAX }; -#define FLOW_OFFLOAD_DIR_MAX (__FLOW_OFFLOAD_DIR_MAX + 1) struct flow_offload_tuple { union { @@ -55,6 +55,8 @@ struct flow_offload_tuple { int oifidx; + u16 mtu; + struct dst_entry *dst_cache; }; @@ -66,6 +68,7 @@ struct flow_offload_tuple_rhash { #define FLOW_OFFLOAD_SNAT 0x1 #define FLOW_OFFLOAD_DNAT 0x2 #define FLOW_OFFLOAD_DYING 0x4 +#define FLOW_OFFLOAD_TEARDOWN 0x8 struct flow_offload { struct flow_offload_tuple_rhash tuplehash[FLOW_OFFLOAD_DIR_MAX]; @@ -98,11 +101,14 @@ int nf_flow_table_iterate(struct nf_flowtable *flow_table, void nf_flow_table_cleanup(struct net *net, struct net_device *dev); +int nf_flow_table_init(struct nf_flowtable *flow_table); void nf_flow_table_free(struct nf_flowtable *flow_table); -void nf_flow_offload_work_gc(struct work_struct *work); -extern const struct rhashtable_params nf_flow_offload_rhash_params; -void flow_offload_dead(struct flow_offload *flow); +void flow_offload_teardown(struct flow_offload *flow); +static inline void flow_offload_dead(struct flow_offload *flow) +{ + flow->flags |= FLOW_OFFLOAD_DYING; +} int nf_flow_snat_port(const struct flow_offload *flow, struct sk_buff *skb, unsigned int thoff, diff --git a/include/net/netfilter/nf_nat.h b/include/net/netfilter/nf_nat.h index 207a467e7ca6..da3d601cadee 100644 --- a/include/net/netfilter/nf_nat.h +++ b/include/net/netfilter/nf_nat.h @@ -39,7 +39,7 @@ struct nf_conn_nat { /* Set up the info structure to map into this range. */ unsigned int nf_nat_setup_info(struct nf_conn *ct, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype); extern unsigned int nf_nat_alloc_null_binding(struct nf_conn *ct, diff --git a/include/net/netfilter/nf_nat_l3proto.h b/include/net/netfilter/nf_nat_l3proto.h index ce7c2b4e64bb..8bad2560576f 100644 --- a/include/net/netfilter/nf_nat_l3proto.h +++ b/include/net/netfilter/nf_nat_l3proto.h @@ -7,7 +7,7 @@ struct nf_nat_l3proto { u8 l3proto; bool (*in_range)(const struct nf_conntrack_tuple *t, - const struct nf_nat_range *range); + const struct nf_nat_range2 *range); u32 (*secure_port)(const struct nf_conntrack_tuple *t, __be16); @@ -33,7 +33,7 @@ struct nf_nat_l3proto { struct flowi *fl); int (*nlattr_to_range)(struct nlattr *tb[], - struct nf_nat_range *range); + struct nf_nat_range2 *range); }; int nf_nat_l3proto_register(const struct nf_nat_l3proto *); @@ -48,30 +48,26 @@ unsigned int nf_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); unsigned int nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); unsigned int nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); unsigned int nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); int nf_nat_icmpv6_reply_translation(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, @@ -81,29 +77,25 @@ unsigned int nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); unsigned int nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); unsigned int nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); unsigned int nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)); + const struct nf_hook_state *state)); #endif /* _NF_NAT_L3PROTO_H */ diff --git a/include/net/netfilter/nf_nat_l4proto.h b/include/net/netfilter/nf_nat_l4proto.h index 67835ff8a2d9..b4d6b29bca62 100644 --- a/include/net/netfilter/nf_nat_l4proto.h +++ b/include/net/netfilter/nf_nat_l4proto.h @@ -34,12 +34,12 @@ struct nf_nat_l4proto { */ void (*unique_tuple)(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct); int (*nlattr_to_range)(struct nlattr *tb[], - struct nf_nat_range *range); + struct nf_nat_range2 *range); }; /* Protocol registration. */ @@ -72,11 +72,11 @@ bool nf_nat_l4proto_in_range(const struct nf_conntrack_tuple *tuple, void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct, u16 *rover); int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range); + struct nf_nat_range2 *range); #endif /*_NF_NAT_L4PROTO_H*/ diff --git a/include/net/netfilter/nf_nat_redirect.h b/include/net/netfilter/nf_nat_redirect.h index 5ddabb08c472..c129aacc8ae8 100644 --- a/include/net/netfilter/nf_nat_redirect.h +++ b/include/net/netfilter/nf_nat_redirect.h @@ -7,7 +7,7 @@ nf_nat_redirect_ipv4(struct sk_buff *skb, const struct nf_nat_ipv4_multi_range_compat *mr, unsigned int hooknum); unsigned int -nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, +nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, unsigned int hooknum); #endif /* _NF_NAT_REDIRECT_H_ */ diff --git a/include/net/netfilter/nf_tables.h b/include/net/netfilter/nf_tables.h index cd368d1b8cb8..435c9e3b9181 100644 --- a/include/net/netfilter/nf_tables.h +++ b/include/net/netfilter/nf_tables.h @@ -275,23 +275,6 @@ struct nft_set_estimate { enum nft_set_class space; }; -/** - * struct nft_set_type - nf_tables set type - * - * @select_ops: function to select nft_set_ops - * @ops: default ops, used when no select_ops functions is present - * @list: used internally - * @owner: module reference - */ -struct nft_set_type { - const struct nft_set_ops *(*select_ops)(const struct nft_ctx *, - const struct nft_set_desc *desc, - u32 flags); - const struct nft_set_ops *ops; - struct list_head list; - struct module *owner; -}; - struct nft_set_ext; struct nft_expr; @@ -310,7 +293,6 @@ struct nft_expr; * @init: initialize private data of new set instance * @destroy: destroy private data of set instance * @elemsize: element private size - * @features: features supported by the implementation */ struct nft_set_ops { bool (*lookup)(const struct net *net, @@ -361,9 +343,23 @@ struct nft_set_ops { void (*destroy)(const struct nft_set *set); unsigned int elemsize; +}; + +/** + * struct nft_set_type - nf_tables set type + * + * @ops: set ops for this type + * @list: used internally + * @owner: module reference + * @features: features supported by the implementation + */ +struct nft_set_type { + const struct nft_set_ops ops; + struct list_head list; + struct module *owner; u32 features; - const struct nft_set_type *type; }; +#define to_set_type(o) container_of(o, struct nft_set_type, ops) int nft_register_set(struct nft_set_type *type); void nft_unregister_set(struct nft_set_type *type); @@ -589,7 +585,7 @@ static inline u64 *nft_set_ext_timeout(const struct nft_set_ext *ext) return nft_set_ext(ext, NFT_SET_EXT_TIMEOUT); } -static inline unsigned long *nft_set_ext_expiration(const struct nft_set_ext *ext) +static inline u64 *nft_set_ext_expiration(const struct nft_set_ext *ext) { return nft_set_ext(ext, NFT_SET_EXT_EXPIRATION); } @@ -607,7 +603,7 @@ static inline struct nft_expr *nft_set_ext_expr(const struct nft_set_ext *ext) static inline bool nft_set_elem_expired(const struct nft_set_ext *ext) { return nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION) && - time_is_before_eq_jiffies(*nft_set_ext_expiration(ext)); + time_is_before_eq_jiffies64(*nft_set_ext_expiration(ext)); } static inline struct nft_set_ext *nft_set_elem_ext(const struct nft_set *set, @@ -1015,9 +1011,9 @@ static inline void *nft_obj_data(const struct nft_object *obj) #define nft_expr_obj(expr) *((struct nft_object **)nft_expr_priv(expr)) -struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, - const struct nlattr *nla, u32 objtype, - u8 genmask); +struct nft_object *nft_obj_lookup(const struct nft_table *table, + const struct nlattr *nla, u32 objtype, + u8 genmask); void nft_obj_notify(struct net *net, struct nft_table *table, struct nft_object *obj, u32 portid, u32 seq, @@ -1106,12 +1102,9 @@ struct nft_flowtable { struct nf_flowtable data; }; -struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table, - const struct nlattr *nla, - u8 genmask); -void nft_flow_table_iterate(struct net *net, - void (*iter)(struct nf_flowtable *flowtable, void *data), - void *data); +struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, + const struct nlattr *nla, + u8 genmask); void nft_register_flowtable_type(struct nf_flowtable_type *type); void nft_unregister_flowtable_type(struct nf_flowtable_type *type); diff --git a/include/net/netfilter/nf_tables_core.h b/include/net/netfilter/nf_tables_core.h index ea5aab568be8..cd6915b6c054 100644 --- a/include/net/netfilter/nf_tables_core.h +++ b/include/net/netfilter/nf_tables_core.h @@ -10,6 +10,9 @@ extern struct nft_expr_type nft_byteorder_type; extern struct nft_expr_type nft_payload_type; extern struct nft_expr_type nft_dynset_type; extern struct nft_expr_type nft_range_type; +extern struct nft_expr_type nft_meta_type; +extern struct nft_expr_type nft_rt_type; +extern struct nft_expr_type nft_exthdr_type; int nf_tables_core_module_init(void); void nf_tables_core_module_exit(void); diff --git a/include/net/netfilter/nfnetlink_log.h b/include/net/netfilter/nfnetlink_log.h index 612cfb63ac68..ea32a7d3cf1b 100644 --- a/include/net/netfilter/nfnetlink_log.h +++ b/include/net/netfilter/nfnetlink_log.h @@ -1,18 +1 @@ /* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _KER_NFNETLINK_LOG_H -#define _KER_NFNETLINK_LOG_H - -void -nfulnl_log_packet(struct net *net, - u_int8_t pf, - unsigned int hooknum, - const struct sk_buff *skb, - const struct net_device *in, - const struct net_device *out, - const struct nf_loginfo *li_user, - const char *prefix); - -#define NFULNL_COPY_DISABLED 0xff - -#endif /* _KER_NFNETLINK_LOG_H */ - diff --git a/include/net/netfilter/nft_meta.h b/include/net/netfilter/nft_meta.h deleted file mode 100644 index 5c69e9b09388..000000000000 --- a/include/net/netfilter/nft_meta.h +++ /dev/null @@ -1,44 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#ifndef _NFT_META_H_ -#define _NFT_META_H_ - -struct nft_meta { - enum nft_meta_keys key:8; - union { - enum nft_registers dreg:8; - enum nft_registers sreg:8; - }; -}; - -extern const struct nla_policy nft_meta_policy[]; - -int nft_meta_get_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]); - -int nft_meta_set_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]); - -int nft_meta_get_dump(struct sk_buff *skb, - const struct nft_expr *expr); - -int nft_meta_set_dump(struct sk_buff *skb, - const struct nft_expr *expr); - -void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt); - -void nft_meta_set_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt); - -void nft_meta_set_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr); - -int nft_meta_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data); - -#endif diff --git a/include/net/netns/ipv6.h b/include/net/netns/ipv6.h index c29f09cfc9d7..c978a31b0f84 100644 --- a/include/net/netns/ipv6.h +++ b/include/net/netns/ipv6.h @@ -43,6 +43,7 @@ struct netns_sysctl_ipv6 { int max_hbh_opts_cnt; int max_dst_opts_len; int max_hbh_opts_len; + int seg6_flowlabel; }; struct netns_ipv6 { @@ -60,7 +61,8 @@ struct netns_ipv6 { #endif struct xt_table *ip6table_nat; #endif - struct rt6_info *ip6_null_entry; + struct fib6_info *fib6_null_entry; + struct rt6_info *ip6_null_entry; struct rt6_statistics *rt6_stats; struct timer_list ip6_fib_timer; struct hlist_head *fib_table_hash; diff --git a/include/net/page_pool.h b/include/net/page_pool.h new file mode 100644 index 000000000000..c79087153148 --- /dev/null +++ b/include/net/page_pool.h @@ -0,0 +1,143 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * page_pool.h + * Author: Jesper Dangaard Brouer <netoptimizer@brouer.com> + * Copyright (C) 2016 Red Hat, Inc. + */ + +/** + * DOC: page_pool allocator + * + * This page_pool allocator is optimized for the XDP mode that + * uses one-frame-per-page, but have fallbacks that act like the + * regular page allocator APIs. + * + * Basic use involve replacing alloc_pages() calls with the + * page_pool_alloc_pages() call. Drivers should likely use + * page_pool_dev_alloc_pages() replacing dev_alloc_pages(). + * + * If page_pool handles DMA mapping (use page->private), then API user + * is responsible for invoking page_pool_put_page() once. In-case of + * elevated refcnt, the DMA state is released, assuming other users of + * the page will eventually call put_page(). + * + * If no DMA mapping is done, then it can act as shim-layer that + * fall-through to alloc_page. As no state is kept on the page, the + * regular put_page() call is sufficient. + */ +#ifndef _NET_PAGE_POOL_H +#define _NET_PAGE_POOL_H + +#include <linux/mm.h> /* Needed by ptr_ring */ +#include <linux/ptr_ring.h> +#include <linux/dma-direction.h> + +#define PP_FLAG_DMA_MAP 1 /* Should page_pool do the DMA map/unmap */ +#define PP_FLAG_ALL PP_FLAG_DMA_MAP + +/* + * Fast allocation side cache array/stack + * + * The cache size and refill watermark is related to the network + * use-case. The NAPI budget is 64 packets. After a NAPI poll the RX + * ring is usually refilled and the max consumed elements will be 64, + * thus a natural max size of objects needed in the cache. + * + * Keeping room for more objects, is due to XDP_DROP use-case. As + * XDP_DROP allows the opportunity to recycle objects directly into + * this array, as it shares the same softirq/NAPI protection. If + * cache is already full (or partly full) then the XDP_DROP recycles + * would have to take a slower code path. + */ +#define PP_ALLOC_CACHE_SIZE 128 +#define PP_ALLOC_CACHE_REFILL 64 +struct pp_alloc_cache { + u32 count; + void *cache[PP_ALLOC_CACHE_SIZE]; +}; + +struct page_pool_params { + unsigned int flags; + unsigned int order; + unsigned int pool_size; + int nid; /* Numa node id to allocate from pages from */ + struct device *dev; /* device, for DMA pre-mapping purposes */ + enum dma_data_direction dma_dir; /* DMA mapping direction */ +}; + +struct page_pool { + struct rcu_head rcu; + struct page_pool_params p; + + /* + * Data structure for allocation side + * + * Drivers allocation side usually already perform some kind + * of resource protection. Piggyback on this protection, and + * require driver to protect allocation side. + * + * For NIC drivers this means, allocate a page_pool per + * RX-queue. As the RX-queue is already protected by + * Softirq/BH scheduling and napi_schedule. NAPI schedule + * guarantee that a single napi_struct will only be scheduled + * on a single CPU (see napi_schedule). + */ + struct pp_alloc_cache alloc ____cacheline_aligned_in_smp; + + /* Data structure for storing recycled pages. + * + * Returning/freeing pages is more complicated synchronization + * wise, because free's can happen on remote CPUs, with no + * association with allocation resource. + * + * Use ptr_ring, as it separates consumer and producer + * effeciently, it a way that doesn't bounce cache-lines. + * + * TODO: Implement bulk return pages into this structure. + */ + struct ptr_ring ring; +}; + +struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp); + +static inline struct page *page_pool_dev_alloc_pages(struct page_pool *pool) +{ + gfp_t gfp = (GFP_ATOMIC | __GFP_NOWARN); + + return page_pool_alloc_pages(pool, gfp); +} + +struct page_pool *page_pool_create(const struct page_pool_params *params); + +void page_pool_destroy(struct page_pool *pool); + +/* Never call this directly, use helpers below */ +void __page_pool_put_page(struct page_pool *pool, + struct page *page, bool allow_direct); + +static inline void page_pool_put_page(struct page_pool *pool, struct page *page) +{ + /* When page_pool isn't compiled-in, net/core/xdp.c doesn't + * allow registering MEM_TYPE_PAGE_POOL, but shield linker. + */ +#ifdef CONFIG_PAGE_POOL + __page_pool_put_page(pool, page, false); +#endif +} +/* Very limited use-cases allow recycle direct */ +static inline void page_pool_recycle_direct(struct page_pool *pool, + struct page *page) +{ + __page_pool_put_page(pool, page, true); +} + +static inline bool is_page_pool_compiled_in(void) +{ +#ifdef CONFIG_PAGE_POOL + return true; +#else + return false; +#endif +} + +#endif /* _NET_PAGE_POOL_H */ diff --git a/include/net/sctp/constants.h b/include/net/sctp/constants.h index 20ff237c5eb2..86f034b524d4 100644 --- a/include/net/sctp/constants.h +++ b/include/net/sctp/constants.h @@ -254,11 +254,10 @@ enum { SCTP_ARBITRARY_COOKIE_ECHO_LEN = 200 }; #define SCTP_TSN_MAP_SIZE 4096 /* We will not record more than this many duplicate TSNs between two - * SACKs. The minimum PMTU is 576. Remove all the headers and there - * is enough room for 131 duplicate reports. Round down to the + * SACKs. The minimum PMTU is 512. Remove all the headers and there + * is enough room for 117 duplicate reports. Round down to the * nearest power of 2. */ -enum { SCTP_MIN_PMTU = 576 }; enum { SCTP_MAX_DUP_TSNS = 16 }; enum { SCTP_MAX_GABS = 16 }; diff --git a/include/net/sctp/sctp.h b/include/net/sctp/sctp.h index 28b996d63490..f66d44350007 100644 --- a/include/net/sctp/sctp.h +++ b/include/net/sctp/sctp.h @@ -428,32 +428,6 @@ static inline int sctp_list_single_entry(struct list_head *head) return (head->next != head) && (head->next == head->prev); } -/* Break down data chunks at this point. */ -static inline int sctp_frag_point(const struct sctp_association *asoc, int pmtu) -{ - struct sctp_sock *sp = sctp_sk(asoc->base.sk); - struct sctp_af *af = sp->pf->af; - int frag = pmtu; - - frag -= af->ip_options_len(asoc->base.sk); - frag -= af->net_header_len; - frag -= sizeof(struct sctphdr) + sctp_datachk_len(&asoc->stream); - - if (asoc->user_frag) - frag = min_t(int, frag, asoc->user_frag); - - frag = SCTP_TRUNC4(min_t(int, frag, SCTP_MAX_CHUNK_LEN - - sctp_datachk_len(&asoc->stream))); - - return frag; -} - -static inline void sctp_assoc_pending_pmtu(struct sctp_association *asoc) -{ - sctp_assoc_sync_pmtu(asoc); - asoc->pmtu_pending = 0; -} - static inline bool sctp_chunk_pending(const struct sctp_chunk *chunk) { return !list_empty(&chunk->list); @@ -607,17 +581,29 @@ static inline struct dst_entry *sctp_transport_dst_check(struct sctp_transport * return t->dst; } -static inline bool sctp_transport_pmtu_check(struct sctp_transport *t) +/* Calculate max payload size given a MTU, or the total overhead if + * given MTU is zero + */ +static inline __u32 sctp_mtu_payload(const struct sctp_sock *sp, + __u32 mtu, __u32 extra) { - __u32 pmtu = max_t(size_t, SCTP_TRUNC4(dst_mtu(t->dst)), - SCTP_DEFAULT_MINSEGMENT); + __u32 overhead = sizeof(struct sctphdr) + extra; - if (t->pathmtu == pmtu) - return true; + if (sp) + overhead += sp->pf->af->net_header_len; + else + overhead += sizeof(struct ipv6hdr); - t->pathmtu = pmtu; + if (WARN_ON_ONCE(mtu && mtu <= overhead)) + mtu = overhead; - return false; + return mtu ? mtu - overhead : overhead; +} + +static inline __u32 sctp_dst_mtu(const struct dst_entry *dst) +{ + return SCTP_TRUNC4(max_t(__u32, dst_mtu(dst), + SCTP_DEFAULT_MINSEGMENT)); } #endif /* __net_sctp_h__ */ diff --git a/include/net/sctp/sm.h b/include/net/sctp/sm.h index 2d0e782c9055..5ef1bad81ef5 100644 --- a/include/net/sctp/sm.h +++ b/include/net/sctp/sm.h @@ -207,7 +207,7 @@ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, int len, __u8 flags, gfp_t gfp); struct sctp_chunk *sctp_make_ecne(const struct sctp_association *asoc, const __u32 lowest_tsn); -struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc); +struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc); struct sctp_chunk *sctp_make_shutdown(const struct sctp_association *asoc, const struct sctp_chunk *chunk); struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, @@ -215,7 +215,7 @@ struct sctp_chunk *sctp_make_shutdown_ack(const struct sctp_association *asoc, struct sctp_chunk *sctp_make_shutdown_complete( const struct sctp_association *asoc, const struct sctp_chunk *chunk); -void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause, size_t paylen); +int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause, size_t paylen); struct sctp_chunk *sctp_make_abort(const struct sctp_association *asoc, const struct sctp_chunk *chunk, const size_t hint); diff --git a/include/net/sctp/structs.h b/include/net/sctp/structs.h index a0ec462bc1a9..ebf809eed33a 100644 --- a/include/net/sctp/structs.h +++ b/include/net/sctp/structs.h @@ -2091,16 +2091,14 @@ void sctp_assoc_control_transport(struct sctp_association *asoc, enum sctp_transport_cmd command, sctp_sn_error_t error); struct sctp_transport *sctp_assoc_lookup_tsn(struct sctp_association *, __u32); -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *, - struct net *, - const union sctp_addr *, - const union sctp_addr *); void sctp_assoc_migrate(struct sctp_association *, struct sock *); int sctp_assoc_update(struct sctp_association *old, struct sctp_association *new); __u32 sctp_association_get_next_tsn(struct sctp_association *); +void sctp_assoc_update_frag_point(struct sctp_association *asoc); +void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu); void sctp_assoc_sync_pmtu(struct sctp_association *asoc); void sctp_assoc_rwnd_increase(struct sctp_association *, unsigned int); void sctp_assoc_rwnd_decrease(struct sctp_association *, unsigned int); diff --git a/include/net/sock.h b/include/net/sock.h index 74d725fdbe0f..4f7c584e9765 100644 --- a/include/net/sock.h +++ b/include/net/sock.h @@ -481,6 +481,11 @@ struct sock { void (*sk_error_report)(struct sock *sk); int (*sk_backlog_rcv)(struct sock *sk, struct sk_buff *skb); +#ifdef CONFIG_SOCK_VALIDATE_XMIT + struct sk_buff* (*sk_validate_xmit_skb)(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb); +#endif void (*sk_destruct)(struct sock *sk); struct sock_reuseport __rcu *sk_reuseport_cb; struct rcu_head sk_rcu; @@ -803,10 +808,10 @@ static inline bool sock_flag(const struct sock *sk, enum sock_flags flag) } #ifdef CONFIG_NET -extern struct static_key memalloc_socks; +DECLARE_STATIC_KEY_FALSE(memalloc_socks_key); static inline int sk_memalloc_socks(void) { - return static_key_false(&memalloc_socks); + return static_branch_unlikely(&memalloc_socks_key); } #else @@ -2332,6 +2337,22 @@ static inline bool sk_fullsock(const struct sock *sk) return (1 << sk->sk_state) & ~(TCPF_TIME_WAIT | TCPF_NEW_SYN_RECV); } +/* Checks if this SKB belongs to an HW offloaded socket + * and whether any SW fallbacks are required based on dev. + */ +static inline struct sk_buff *sk_validate_xmit_skb(struct sk_buff *skb, + struct net_device *dev) +{ +#ifdef CONFIG_SOCK_VALIDATE_XMIT + struct sock *sk = skb->sk; + + if (sk && sk_fullsock(sk) && sk->sk_validate_xmit_skb) + skb = sk->sk_validate_xmit_skb(sk, dev, skb); +#endif + + return skb; +} + /* This helper checks if a socket is a LISTEN or NEW_SYN_RECV * SYNACK messages can be attached to either ones (depending on SYNCOOKIE) */ diff --git a/include/net/switchdev.h b/include/net/switchdev.h index 39bc855d7fee..d574ce63bf22 100644 --- a/include/net/switchdev.h +++ b/include/net/switchdev.h @@ -155,6 +155,7 @@ struct switchdev_notifier_fdb_info { struct switchdev_notifier_info info; /* must be first */ const unsigned char *addr; u16 vid; + bool added_by_user; }; static inline struct net_device * diff --git a/include/net/tcp.h b/include/net/tcp.h index 9c9b3768b350..3b1d617b0110 100644 --- a/include/net/tcp.h +++ b/include/net/tcp.h @@ -402,6 +402,10 @@ void tcp_set_keepalive(struct sock *sk, int val); void tcp_syn_ack_timeout(const struct request_sock *req); int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); +int tcp_set_rcvlowat(struct sock *sk, int val); +void tcp_data_ready(struct sock *sk); +int tcp_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma); void tcp_parse_options(const struct net *net, const struct sk_buff *skb, struct tcp_options_received *opt_rx, int estab, struct tcp_fastopen_cookie *foc); @@ -553,7 +557,9 @@ void tcp_fin(struct sock *sk); void tcp_init_xmit_timers(struct sock *); static inline void tcp_clear_xmit_timers(struct sock *sk) { - hrtimer_cancel(&tcp_sk(sk)->pacing_timer); + if (hrtimer_try_to_cancel(&tcp_sk(sk)->pacing_timer) == 1) + sock_put(sk); + inet_csk_clear_xmit_timers(sk); } @@ -2101,4 +2107,12 @@ static inline bool tcp_bpf_ca_needs_ecn(struct sock *sk) #if IS_ENABLED(CONFIG_SMC) extern struct static_key_false tcp_have_smc; #endif + +#if IS_ENABLED(CONFIG_TLS_DEVICE) +void clean_acked_data_enable(struct inet_connection_sock *icsk, + void (*cad)(struct sock *sk, u32 ack_seq)); +void clean_acked_data_disable(struct inet_connection_sock *icsk); + +#endif + #endif /* _TCP_H */ diff --git a/include/net/tipc.h b/include/net/tipc.h index 07670ec022a7..f0e7e6bc1bef 100644 --- a/include/net/tipc.h +++ b/include/net/tipc.h @@ -44,11 +44,11 @@ struct tipc_basic_hdr { __be32 w[4]; }; -static inline u32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr) +static inline __be32 tipc_hdr_rps_key(struct tipc_basic_hdr *hdr) { u32 w0 = ntohl(hdr->w[0]); bool keepalive_msg = (w0 & KEEPALIVE_MSG_MASK) == KEEPALIVE_MSG_MASK; - int key; + __be32 key; /* Return source node identity as key */ if (likely(!keepalive_msg)) diff --git a/include/net/tls.h b/include/net/tls.h index b400d0bb7448..ee78f339b4b3 100644 --- a/include/net/tls.h +++ b/include/net/tls.h @@ -83,21 +83,10 @@ struct tls_device { void (*unhash)(struct tls_device *device, struct sock *sk); }; -struct tls_sw_context { +struct tls_sw_context_tx { struct crypto_aead *aead_send; - struct crypto_aead *aead_recv; struct crypto_wait async_wait; - /* Receive context */ - struct strparser strp; - void (*saved_data_ready)(struct sock *sk); - unsigned int (*sk_poll)(struct file *file, struct socket *sock, - struct poll_table_struct *wait); - struct sk_buff *recv_pkt; - u8 control; - bool decrypted; - - /* Sending context */ char aad_space[TLS_AAD_SPACE_SIZE]; unsigned int sg_plaintext_size; @@ -114,6 +103,50 @@ struct tls_sw_context { struct scatterlist sg_aead_out[2]; }; +struct tls_sw_context_rx { + struct crypto_aead *aead_recv; + struct crypto_wait async_wait; + + struct strparser strp; + void (*saved_data_ready)(struct sock *sk); + unsigned int (*sk_poll)(struct file *file, struct socket *sock, + struct poll_table_struct *wait); + struct sk_buff *recv_pkt; + u8 control; + bool decrypted; +}; + +struct tls_record_info { + struct list_head list; + u32 end_seq; + int len; + int num_frags; + skb_frag_t frags[MAX_SKB_FRAGS]; +}; + +struct tls_offload_context { + struct crypto_aead *aead_send; + spinlock_t lock; /* protects records list */ + struct list_head records_list; + struct tls_record_info *open_record; + struct tls_record_info *retransmit_hint; + u64 hint_record_sn; + u64 unacked_record_sn; + + struct scatterlist sg_tx_data[MAX_SKB_FRAGS]; + void (*sk_destruct)(struct sock *sk); + u8 driver_state[]; + /* The TLS layer reserves room for driver specific state + * Currently the belief is that there is not enough + * driver specific state to justify another layer of indirection + */ +#define TLS_DRIVER_STATE_SIZE (max_t(size_t, 8, sizeof(void *))) +}; + +#define TLS_OFFLOAD_CONTEXT_SIZE \ + (ALIGN(sizeof(struct tls_offload_context), sizeof(void *)) + \ + TLS_DRIVER_STATE_SIZE) + enum { TLS_PENDING_CLOSED_RECORD }; @@ -138,9 +171,15 @@ struct tls_context { struct tls12_crypto_info_aes_gcm_128 crypto_recv_aes_gcm_128; }; - void *priv_ctx; + struct list_head list; + struct net_device *netdev; + refcount_t refcount; + + void *priv_ctx_tx; + void *priv_ctx_rx; - u8 conf:3; + u8 tx_conf:3; + u8 rx_conf:3; struct cipher_context tx; struct cipher_context rx; @@ -178,7 +217,8 @@ int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags); void tls_sw_close(struct sock *sk, long timeout); -void tls_sw_free_resources(struct sock *sk); +void tls_sw_free_resources_tx(struct sock *sk); +void tls_sw_free_resources_rx(struct sock *sk); int tls_sw_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, int flags, int *addr_len); unsigned int tls_sw_poll(struct file *file, struct socket *sock, @@ -187,9 +227,28 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, unsigned int flags); -void tls_sk_destruct(struct sock *sk, struct tls_context *ctx); -void tls_icsk_clean_acked(struct sock *sk); +int tls_set_device_offload(struct sock *sk, struct tls_context *ctx); +int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size); +int tls_device_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags); +void tls_device_sk_destruct(struct sock *sk); +void tls_device_init(void); +void tls_device_cleanup(void); +struct tls_record_info *tls_get_record(struct tls_offload_context *context, + u32 seq, u64 *p_record_sn); + +static inline bool tls_record_is_start_marker(struct tls_record_info *rec) +{ + return rec->len == 0; +} + +static inline u32 tls_record_start_seq(struct tls_record_info *rec) +{ + return rec->end_seq - rec->len; +} + +void tls_sk_destruct(struct sock *sk, struct tls_context *ctx); int tls_push_sg(struct sock *sk, struct tls_context *ctx, struct scatterlist *sg, u16 first_offset, int flags); @@ -226,6 +285,13 @@ static inline bool tls_is_pending_open_record(struct tls_context *tls_ctx) return tls_ctx->pending_open_record_frags; } +static inline bool tls_is_sk_tx_device_offloaded(struct sock *sk) +{ + return sk_fullsock(sk) && + /* matches smp_store_release in tls_set_device_offload */ + smp_load_acquire(&sk->sk_destruct) == &tls_device_sk_destruct; +} + static inline void tls_err_abort(struct sock *sk, int err) { sk->sk_err = err; @@ -298,16 +364,22 @@ static inline struct tls_context *tls_get_ctx(const struct sock *sk) return icsk->icsk_ulp_data; } -static inline struct tls_sw_context *tls_sw_ctx( +static inline struct tls_sw_context_rx *tls_sw_ctx_rx( const struct tls_context *tls_ctx) { - return (struct tls_sw_context *)tls_ctx->priv_ctx; + return (struct tls_sw_context_rx *)tls_ctx->priv_ctx_rx; +} + +static inline struct tls_sw_context_tx *tls_sw_ctx_tx( + const struct tls_context *tls_ctx) +{ + return (struct tls_sw_context_tx *)tls_ctx->priv_ctx_tx; } static inline struct tls_offload_context *tls_offload_ctx( const struct tls_context *tls_ctx) { - return (struct tls_offload_context *)tls_ctx->priv_ctx; + return (struct tls_offload_context *)tls_ctx->priv_ctx_tx; } int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, @@ -315,4 +387,12 @@ int tls_proccess_cmsg(struct sock *sk, struct msghdr *msg, void tls_register_device(struct tls_device *device); void tls_unregister_device(struct tls_device *device); +struct sk_buff *tls_validate_xmit_skb(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb); + +int tls_sw_fallback_init(struct sock *sk, + struct tls_offload_context *offload_ctx, + struct tls_crypto_info *crypto_info); + #endif /* _TLS_OFFLOAD_H */ diff --git a/include/net/udp.h b/include/net/udp.h index 0676b272f6ac..9289b6425032 100644 --- a/include/net/udp.h +++ b/include/net/udp.h @@ -174,6 +174,9 @@ struct sk_buff **udp_gro_receive(struct sk_buff **head, struct sk_buff *skb, struct udphdr *uh, udp_lookup_t lookup); int udp_gro_complete(struct sk_buff *skb, int nhoff, udp_lookup_t lookup); +struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, + netdev_features_t features); + static inline struct udphdr *udp_gro_udphdr(struct sk_buff *skb) { struct udphdr *uh; @@ -269,6 +272,7 @@ int udp_abort(struct sock *sk, int err); int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len); int udp_push_pending_frames(struct sock *sk); void udp_flush_pending_frames(struct sock *sk); +int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size); void udp4_hwcsum(struct sk_buff *skb, __be32 src, __be32 dst); int udp_rcv(struct sk_buff *skb); int udp_ioctl(struct sock *sk, int cmd, unsigned long arg); diff --git a/include/net/vxlan.h b/include/net/vxlan.h index ad73d8b3fcc2..b99a02ae3934 100644 --- a/include/net/vxlan.h +++ b/include/net/vxlan.h @@ -262,6 +262,7 @@ struct vxlan_dev { #define VXLAN_F_COLLECT_METADATA 0x2000 #define VXLAN_F_GPE 0x4000 #define VXLAN_F_IPV6_LINKLOCAL 0x8000 +#define VXLAN_F_TTL_INHERIT 0x10000 /* Flags that are used in the receive path. These flags must match in * order for a socket to be shareable diff --git a/include/net/xdp.h b/include/net/xdp.h index b2362ddfa694..0b689cf561c7 100644 --- a/include/net/xdp.h +++ b/include/net/xdp.h @@ -33,16 +33,100 @@ * also mandatory during RX-ring setup. */ +enum xdp_mem_type { + MEM_TYPE_PAGE_SHARED = 0, /* Split-page refcnt based model */ + MEM_TYPE_PAGE_ORDER0, /* Orig XDP full page model */ + MEM_TYPE_PAGE_POOL, + MEM_TYPE_MAX, +}; + +struct xdp_mem_info { + u32 type; /* enum xdp_mem_type, but known size type */ + u32 id; +}; + +struct page_pool; + struct xdp_rxq_info { struct net_device *dev; u32 queue_index; u32 reg_state; + struct xdp_mem_info mem; } ____cacheline_aligned; /* perf critical, avoid false-sharing */ +struct xdp_buff { + void *data; + void *data_end; + void *data_meta; + void *data_hard_start; + struct xdp_rxq_info *rxq; +}; + +struct xdp_frame { + void *data; + u16 len; + u16 headroom; + u16 metasize; + /* Lifetime of xdp_rxq_info is limited to NAPI/enqueue time, + * while mem info is valid on remote CPU. + */ + struct xdp_mem_info mem; + struct net_device *dev_rx; /* used by cpumap */ +}; + +/* Convert xdp_buff to xdp_frame */ +static inline +struct xdp_frame *convert_to_xdp_frame(struct xdp_buff *xdp) +{ + struct xdp_frame *xdp_frame; + int metasize; + int headroom; + + /* Assure headroom is available for storing info */ + headroom = xdp->data - xdp->data_hard_start; + metasize = xdp->data - xdp->data_meta; + metasize = metasize > 0 ? metasize : 0; + if (unlikely((headroom - metasize) < sizeof(*xdp_frame))) + return NULL; + + /* Store info in top of packet */ + xdp_frame = xdp->data_hard_start; + + xdp_frame->data = xdp->data; + xdp_frame->len = xdp->data_end - xdp->data; + xdp_frame->headroom = headroom - sizeof(*xdp_frame); + xdp_frame->metasize = metasize; + + /* rxq only valid until napi_schedule ends, convert to xdp_mem_info */ + xdp_frame->mem = xdp->rxq->mem; + + return xdp_frame; +} + +void xdp_return_frame(struct xdp_frame *xdpf); +void xdp_return_buff(struct xdp_buff *xdp); + int xdp_rxq_info_reg(struct xdp_rxq_info *xdp_rxq, struct net_device *dev, u32 queue_index); void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq); void xdp_rxq_info_unused(struct xdp_rxq_info *xdp_rxq); bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq); +int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, + enum xdp_mem_type type, void *allocator); + +/* Drivers not supporting XDP metadata can use this helper, which + * rejects any room expansion for metadata as a result. + */ +static __always_inline void +xdp_set_data_meta_invalid(struct xdp_buff *xdp) +{ + xdp->data_meta = xdp->data + 1; +} + +static __always_inline bool +xdp_data_meta_unsupported(const struct xdp_buff *xdp) +{ + return unlikely(xdp->data_meta > xdp->data); +} #endif /* __LINUX_NET_XDP_H__ */ diff --git a/include/net/xdp_sock.h b/include/net/xdp_sock.h new file mode 100644 index 000000000000..185f4928fbda --- /dev/null +++ b/include/net/xdp_sock.h @@ -0,0 +1,66 @@ +/* SPDX-License-Identifier: GPL-2.0 + * AF_XDP internal functions + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _LINUX_XDP_SOCK_H +#define _LINUX_XDP_SOCK_H + +#include <linux/mutex.h> +#include <net/sock.h> + +struct net_device; +struct xsk_queue; +struct xdp_umem; + +struct xdp_sock { + /* struct sock must be the first member of struct xdp_sock */ + struct sock sk; + struct xsk_queue *rx; + struct net_device *dev; + struct xdp_umem *umem; + struct list_head flush_node; + u16 queue_id; + struct xsk_queue *tx ____cacheline_aligned_in_smp; + /* Protects multiple processes in the control path */ + struct mutex mutex; + u64 rx_dropped; +}; + +struct xdp_buff; +#ifdef CONFIG_XDP_SOCKETS +int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); +int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp); +void xsk_flush(struct xdp_sock *xs); +bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs); +#else +static inline int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + return -ENOTSUPP; +} + +static inline int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + return -ENOTSUPP; +} + +static inline void xsk_flush(struct xdp_sock *xs) +{ +} + +static inline bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) +{ + return false; +} +#endif /* CONFIG_XDP_SOCKETS */ + +#endif /* _LINUX_XDP_SOCK_H */ diff --git a/include/trace/events/bpf.h b/include/trace/events/bpf.h deleted file mode 100644 index 150185647e6b..000000000000 --- a/include/trace/events/bpf.h +++ /dev/null @@ -1,355 +0,0 @@ -/* SPDX-License-Identifier: GPL-2.0 */ -#undef TRACE_SYSTEM -#define TRACE_SYSTEM bpf - -#if !defined(_TRACE_BPF_H) || defined(TRACE_HEADER_MULTI_READ) -#define _TRACE_BPF_H - -/* These are only used within the BPF_SYSCALL code */ -#ifdef CONFIG_BPF_SYSCALL - -#include <linux/filter.h> -#include <linux/bpf.h> -#include <linux/fs.h> -#include <linux/tracepoint.h> - -#define __PROG_TYPE_MAP(FN) \ - FN(SOCKET_FILTER) \ - FN(KPROBE) \ - FN(SCHED_CLS) \ - FN(SCHED_ACT) \ - FN(TRACEPOINT) \ - FN(XDP) \ - FN(PERF_EVENT) \ - FN(CGROUP_SKB) \ - FN(CGROUP_SOCK) \ - FN(LWT_IN) \ - FN(LWT_OUT) \ - FN(LWT_XMIT) - -#define __MAP_TYPE_MAP(FN) \ - FN(HASH) \ - FN(ARRAY) \ - FN(PROG_ARRAY) \ - FN(PERF_EVENT_ARRAY) \ - FN(PERCPU_HASH) \ - FN(PERCPU_ARRAY) \ - FN(STACK_TRACE) \ - FN(CGROUP_ARRAY) \ - FN(LRU_HASH) \ - FN(LRU_PERCPU_HASH) \ - FN(LPM_TRIE) - -#define __PROG_TYPE_TP_FN(x) \ - TRACE_DEFINE_ENUM(BPF_PROG_TYPE_##x); -#define __PROG_TYPE_SYM_FN(x) \ - { BPF_PROG_TYPE_##x, #x }, -#define __PROG_TYPE_SYM_TAB \ - __PROG_TYPE_MAP(__PROG_TYPE_SYM_FN) { -1, 0 } -__PROG_TYPE_MAP(__PROG_TYPE_TP_FN) - -#define __MAP_TYPE_TP_FN(x) \ - TRACE_DEFINE_ENUM(BPF_MAP_TYPE_##x); -#define __MAP_TYPE_SYM_FN(x) \ - { BPF_MAP_TYPE_##x, #x }, -#define __MAP_TYPE_SYM_TAB \ - __MAP_TYPE_MAP(__MAP_TYPE_SYM_FN) { -1, 0 } -__MAP_TYPE_MAP(__MAP_TYPE_TP_FN) - -DECLARE_EVENT_CLASS(bpf_prog_event, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(u32, type) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __entry->type = prg->type; - ), - - TP_printk("prog=%s type=%s", - __print_hex_str(__entry->prog_tag, 8), - __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB)) -); - -DEFINE_EVENT(bpf_prog_event, bpf_prog_get_type, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg) -); - -DEFINE_EVENT(bpf_prog_event, bpf_prog_put_rcu, - - TP_PROTO(const struct bpf_prog *prg), - - TP_ARGS(prg) -); - -TRACE_EVENT(bpf_prog_load, - - TP_PROTO(const struct bpf_prog *prg, int ufd), - - TP_ARGS(prg, ufd), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(u32, type) - __field(int, ufd) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __entry->type = prg->type; - __entry->ufd = ufd; - ), - - TP_printk("prog=%s type=%s ufd=%d", - __print_hex_str(__entry->prog_tag, 8), - __print_symbolic(__entry->type, __PROG_TYPE_SYM_TAB), - __entry->ufd) -); - -TRACE_EVENT(bpf_map_create, - - TP_PROTO(const struct bpf_map *map, int ufd), - - TP_ARGS(map, ufd), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, size_key) - __field(u32, size_value) - __field(u32, max_entries) - __field(u32, flags) - __field(int, ufd) - ), - - TP_fast_assign( - __entry->type = map->map_type; - __entry->size_key = map->key_size; - __entry->size_value = map->value_size; - __entry->max_entries = map->max_entries; - __entry->flags = map->map_flags; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=%u val=%u max=%u flags=%x", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, __entry->size_key, __entry->size_value, - __entry->max_entries, __entry->flags) -); - -DECLARE_EVENT_CLASS(bpf_obj_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname), - - TP_STRUCT__entry( - __array(u8, prog_tag, 8) - __field(int, ufd) - __string(path, pname->name) - ), - - TP_fast_assign( - BUILD_BUG_ON(sizeof(__entry->prog_tag) != sizeof(prg->tag)); - memcpy(__entry->prog_tag, prg->tag, sizeof(prg->tag)); - __assign_str(path, pname->name); - __entry->ufd = ufd; - ), - - TP_printk("prog=%s path=%s ufd=%d", - __print_hex_str(__entry->prog_tag, 8), - __get_str(path), __entry->ufd) -); - -DEFINE_EVENT(bpf_obj_prog, bpf_obj_pin_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname) -); - -DEFINE_EVENT(bpf_obj_prog, bpf_obj_get_prog, - - TP_PROTO(const struct bpf_prog *prg, int ufd, - const struct filename *pname), - - TP_ARGS(prg, ufd, pname) -); - -DECLARE_EVENT_CLASS(bpf_obj_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname), - - TP_STRUCT__entry( - __field(u32, type) - __field(int, ufd) - __string(path, pname->name) - ), - - TP_fast_assign( - __assign_str(path, pname->name); - __entry->type = map->map_type; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d path=%s", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, __get_str(path)) -); - -DEFINE_EVENT(bpf_obj_map, bpf_obj_pin_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname) -); - -DEFINE_EVENT(bpf_obj_map, bpf_obj_get_map, - - TP_PROTO(const struct bpf_map *map, int ufd, - const struct filename *pname), - - TP_ARGS(map, ufd, pname) -); - -DECLARE_EVENT_CLASS(bpf_map_keyval, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __field(bool, key_trunc) - __field(u32, val_len) - __dynamic_array(u8, val, map->value_size) - __field(bool, val_trunc) - __field(int, ufd) - ), - - TP_fast_assign( - memcpy(__get_dynamic_array(key), key, map->key_size); - memcpy(__get_dynamic_array(val), val, map->value_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->val_len = min(map->value_size, 16U); - __entry->val_trunc = map->value_size != __entry->val_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s] val=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __print_hex(__get_dynamic_array(key), __entry->key_len), - __entry->key_trunc ? " ..." : "", - __print_hex(__get_dynamic_array(val), __entry->val_len), - __entry->val_trunc ? " ..." : "") -); - -DEFINE_EVENT(bpf_map_keyval, bpf_map_lookup_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val) -); - -DEFINE_EVENT(bpf_map_keyval, bpf_map_update_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *val), - - TP_ARGS(map, ufd, key, val) -); - -TRACE_EVENT(bpf_map_delete_elem, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key), - - TP_ARGS(map, ufd, key), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __field(bool, key_trunc) - __field(int, ufd) - ), - - TP_fast_assign( - memcpy(__get_dynamic_array(key), key, map->key_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __print_hex(__get_dynamic_array(key), __entry->key_len), - __entry->key_trunc ? " ..." : "") -); - -TRACE_EVENT(bpf_map_next_key, - - TP_PROTO(const struct bpf_map *map, int ufd, - const void *key, const void *key_next), - - TP_ARGS(map, ufd, key, key_next), - - TP_STRUCT__entry( - __field(u32, type) - __field(u32, key_len) - __dynamic_array(u8, key, map->key_size) - __dynamic_array(u8, nxt, map->key_size) - __field(bool, key_trunc) - __field(bool, key_null) - __field(int, ufd) - ), - - TP_fast_assign( - if (key) - memcpy(__get_dynamic_array(key), key, map->key_size); - __entry->key_null = !key; - memcpy(__get_dynamic_array(nxt), key_next, map->key_size); - __entry->type = map->map_type; - __entry->key_len = min(map->key_size, 16U); - __entry->key_trunc = map->key_size != __entry->key_len; - __entry->ufd = ufd; - ), - - TP_printk("map type=%s ufd=%d key=[%s%s] next=[%s%s]", - __print_symbolic(__entry->type, __MAP_TYPE_SYM_TAB), - __entry->ufd, - __entry->key_null ? "NULL" : __print_hex(__get_dynamic_array(key), - __entry->key_len), - __entry->key_trunc && !__entry->key_null ? " ..." : "", - __print_hex(__get_dynamic_array(nxt), __entry->key_len), - __entry->key_trunc ? " ..." : "") -); -#endif /* CONFIG_BPF_SYSCALL */ -#endif /* _TRACE_BPF_H */ - -#include <trace/define_trace.h> diff --git a/include/trace/events/tcp.h b/include/trace/events/tcp.h index 878b2be7ce77..c1a5284713b8 100644 --- a/include/trace/events/tcp.h +++ b/include/trace/events/tcp.h @@ -10,6 +10,7 @@ #include <linux/tracepoint.h> #include <net/ipv6.h> #include <net/tcp.h> +#include <linux/sock_diag.h> #define TP_STORE_V4MAPPED(__entry, saddr, daddr) \ do { \ @@ -113,7 +114,7 @@ DEFINE_EVENT(tcp_event_sk_skb, tcp_send_reset, */ DECLARE_EVENT_CLASS(tcp_event_sk, - TP_PROTO(const struct sock *sk), + TP_PROTO(struct sock *sk), TP_ARGS(sk), @@ -125,6 +126,7 @@ DECLARE_EVENT_CLASS(tcp_event_sk, __array(__u8, daddr, 4) __array(__u8, saddr_v6, 16) __array(__u8, daddr_v6, 16) + __field(__u64, sock_cookie) ), TP_fast_assign( @@ -144,73 +146,36 @@ DECLARE_EVENT_CLASS(tcp_event_sk, TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); + + __entry->sock_cookie = sock_gen_cookie(sk); ), - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c", + TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c sock_cookie=%llx", __entry->sport, __entry->dport, __entry->saddr, __entry->daddr, - __entry->saddr_v6, __entry->daddr_v6) + __entry->saddr_v6, __entry->daddr_v6, + __entry->sock_cookie) ); DEFINE_EVENT(tcp_event_sk, tcp_receive_reset, - TP_PROTO(const struct sock *sk), + TP_PROTO(struct sock *sk), TP_ARGS(sk) ); DEFINE_EVENT(tcp_event_sk, tcp_destroy_sock, - TP_PROTO(const struct sock *sk), + TP_PROTO(struct sock *sk), TP_ARGS(sk) ); -TRACE_EVENT(tcp_set_state, - - TP_PROTO(const struct sock *sk, const int oldstate, const int newstate), - - TP_ARGS(sk, oldstate, newstate), - - TP_STRUCT__entry( - __field(const void *, skaddr) - __field(int, oldstate) - __field(int, newstate) - __field(__u16, sport) - __field(__u16, dport) - __array(__u8, saddr, 4) - __array(__u8, daddr, 4) - __array(__u8, saddr_v6, 16) - __array(__u8, daddr_v6, 16) - ), - - TP_fast_assign( - struct inet_sock *inet = inet_sk(sk); - __be32 *p32; - - __entry->skaddr = sk; - __entry->oldstate = oldstate; - __entry->newstate = newstate; - - __entry->sport = ntohs(inet->inet_sport); - __entry->dport = ntohs(inet->inet_dport); +DEFINE_EVENT(tcp_event_sk, tcp_rcv_space_adjust, - p32 = (__be32 *) __entry->saddr; - *p32 = inet->inet_saddr; + TP_PROTO(struct sock *sk), - p32 = (__be32 *) __entry->daddr; - *p32 = inet->inet_daddr; - - TP_STORE_ADDRS(__entry, inet->inet_saddr, inet->inet_daddr, - sk->sk_v6_rcv_saddr, sk->sk_v6_daddr); - ), - - TP_printk("sport=%hu dport=%hu saddr=%pI4 daddr=%pI4 saddrv6=%pI6c daddrv6=%pI6c oldstate=%s newstate=%s", - __entry->sport, __entry->dport, - __entry->saddr, __entry->daddr, - __entry->saddr_v6, __entry->daddr_v6, - show_tcp_state_name(__entry->oldstate), - show_tcp_state_name(__entry->newstate)) + TP_ARGS(sk) ); TRACE_EVENT(tcp_retransmit_synack, @@ -279,6 +244,7 @@ TRACE_EVENT(tcp_probe, __field(__u32, snd_wnd) __field(__u32, srtt) __field(__u32, rcv_wnd) + __field(__u64, sock_cookie) ), TP_fast_assign( @@ -303,15 +269,14 @@ TRACE_EVENT(tcp_probe, __entry->rcv_wnd = tp->rcv_wnd; __entry->ssthresh = tcp_current_ssthresh(sk); __entry->srtt = tp->srtt_us >> 3; + __entry->sock_cookie = sock_gen_cookie(sk); ), - TP_printk("src=%pISpc dest=%pISpc mark=%#x length=%d snd_nxt=%#x " - "snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u " - "rcv_wnd=%u", + TP_printk("src=%pISpc dest=%pISpc mark=%#x length=%d snd_nxt=%#x snd_una=%#x snd_cwnd=%u ssthresh=%u snd_wnd=%u srtt=%u rcv_wnd=%u sock_cookie=%llx", __entry->saddr, __entry->daddr, __entry->mark, __entry->length, __entry->snd_nxt, __entry->snd_una, __entry->snd_cwnd, __entry->ssthresh, __entry->snd_wnd, - __entry->srtt, __entry->rcv_wnd) + __entry->srtt, __entry->rcv_wnd, __entry->sock_cookie) ); #endif /* _TRACE_TCP_H */ diff --git a/include/uapi/linux/bpf.h b/include/uapi/linux/bpf.h index c5ec89732a8d..93d5a4eeec2a 100644 --- a/include/uapi/linux/bpf.h +++ b/include/uapi/linux/bpf.h @@ -95,6 +95,7 @@ enum bpf_cmd { BPF_OBJ_GET_INFO_BY_FD, BPF_PROG_QUERY, BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, }; enum bpf_map_type { @@ -115,6 +116,7 @@ enum bpf_map_type { BPF_MAP_TYPE_DEVMAP, BPF_MAP_TYPE_SOCKMAP, BPF_MAP_TYPE_CPUMAP, + BPF_MAP_TYPE_XSKMAP, }; enum bpf_prog_type { @@ -279,6 +281,9 @@ union bpf_attr { */ char map_name[BPF_OBJ_NAME_LEN]; __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_id; /* BTF type_id of the key */ + __u32 btf_value_id; /* BTF type_id of the value */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -363,398 +368,1464 @@ union bpf_attr { __u64 name; __u32 prog_fd; } raw_tracepoint; + + struct { /* anonymous struct for BPF_BTF_LOAD */ + __aligned_u64 btf; + __aligned_u64 btf_log_buf; + __u32 btf_size; + __u32 btf_log_size; + __u32 btf_log_level; + }; } __attribute__((aligned(8))); -/* BPF helper function descriptions: - * - * void *bpf_map_lookup_elem(&map, &key) - * Return: Map value or NULL - * - * int bpf_map_update_elem(&map, &key, &value, flags) - * Return: 0 on success or negative error - * - * int bpf_map_delete_elem(&map, &key) - * Return: 0 on success or negative error - * - * int bpf_probe_read(void *dst, int size, void *src) - * Return: 0 on success or negative error +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_helpers_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read(void *dst, u32 size, const void *src) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * address *src* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) - * Return: current ktime - * - * int bpf_trace_printk(const char *fmt, int fmt_size, ...) - * Return: length of buffer written or negative error - * - * u32 bpf_prandom_u32(void) - * Return: random value - * - * u32 bpf_raw_smp_processor_id(void) - * Return: SMP processor ID - * - * int bpf_skb_store_bytes(skb, offset, from, len, flags) - * store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l3_csum_replace(skb, offset, from, to, flags) - * recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l4_csum_replace(skb, offset, from, to, flags) - * recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_tail_call(ctx, prog_array_map, index) - * jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: 32-bit index inside array that selects specific program to run - * Return: 0 on success or negative error - * - * int bpf_clone_redirect(skb, ifindex, flags) - * redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success or negative error + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) - * Return: current_gid << 32 | current_uid - * - * int bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success or negative error - * - * u32 bpf_get_cgroup_classid(skb) - * retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - * - * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) - * Return: 0 on success or negative error - * - * int bpf_skb_vlan_pop(skb) - * Return: 0 on success or negative error - * - * int bpf_skb_get_tunnel_key(skb, key, size, flags) - * int bpf_skb_set_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Return: 0 on success or negative error - * - * u64 bpf_perf_event_read(map, flags) - * read perf event counter value - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * Return: value of perf event counter read or error code - * - * int bpf_redirect(ifindex, flags) - * redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: - * cls_bpf: - * bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * xdp_bpf: - * all bits - reserved - * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error - * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error - * int bpf_redirect_map(map, key, flags) - * redirect to endpoint in map - * @map: pointer to dev map - * @key: index in map to lookup - * @flags: -- - * Return: XDP_REDIRECT on success or XDP_ABORT on error - * - * u32 bpf_get_route_realm(skb) - * retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - * - * int bpf_perf_event_output(ctx, map, flags, data, size) - * output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success or negative error - * - * int bpf_get_stackid(ctx, map, flags) - * walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - * - * s64 bpf_csum_diff(from, from_size, to, to_size, seed) - * calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result or negative error code - * - * int bpf_skb_get_tunnel_opt(skb, opt, size) - * retrieve tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: option size - * - * int bpf_skb_set_tunnel_opt(skb, opt, size) - * populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success or negative error - * - * int bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is v4 -> v6, - * v6 -> v4 transitions. The helper will also resize the skb. eBPF - * program is expected to fill the new headers via skb_store_bytes - * and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - * - * int bpf_skb_under_cgroup(skb, map, index) - * Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - * - * u32 bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(char *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/cgroup-v1/net_cls.txt*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. * * u64 bpf_get_current_task(void) - * Returns current task_struct - * Return: current - * - * int bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - * - * int bpf_current_task_under_cgroup(map, index) - * Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - * - * int bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, to be used f.e. - * with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the skb is non-linear - * and not all of len are part of the linear section. Only needed for - * read/write with direct packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - * - * s64 bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - * - * void bpf_set_hash_invalid(skb) - * Invalidate current skb->hash. - * @skb: pointer to skb - * - * int bpf_get_numa_node_id() - * Return: Id of current NUMA node. - * - * int bpf_skb_change_head() - * Grows headroom of skb and adjusts MAC header offset accordingly. - * Will extends/reallocae as required automatically. - * May change skb data pointer and will thus invalidate any check - * performed for direct packet access. - * @skb: pointer to skb - * @len: length of header to be pushed in front - * @flags: Flags (unused for now) - * Return: 0 on success or negative error - * - * int bpf_xdp_adjust_head(xdp_md, delta) - * Adjust the xdp_md.data by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data - * Return: 0 on success or negative on error + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) - * Copy a NUL terminated string from unsafe address. In case the string - * length is smaller than size, the target is not padded with further NUL - * bytes. In case the string length is larger than size, just count-1 - * bytes are copied and the last byte is set to NUL. - * @dst: destination address - * @size: maximum number of bytes to copy, including the trailing NUL - * @unsafe_ptr: unsafe address - * Return: - * > 0 length of the string including the trailing NUL on success - * < 0 error - * - * u64 bpf_get_socket_cookie(skb) - * Get the cookie for the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: 8 Bytes non-decreasing number on success or 0 if the socket - * field is missing inside sk_buff - * - * u32 bpf_get_socket_uid(skb) - * Get the owner uid of the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: uid of the socket owner on success or overflowuid if failed. - * - * u32 bpf_set_hash(skb, hash) - * Set full skb->hash. - * @skb: pointer to skb - * @hash: hash to set - * - * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) - * Calls setsockopt. Not all opts are available, only those with - * integer optvals plus TCP_CONGESTION. - * Supported levels: SOL_SOCKET and IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) - * Calls getsockopt. Not all opts are available. - * Supported levels: IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) - * Set callback flags for sock_ops - * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct - * @flags: flags value - * Return: 0 for no error - * -EINVAL if there is no full tcp socket - * bits in flags that are not supported by current kernel - * - * int bpf_skb_adjust_room(skb, len_diff, mode, flags) - * Grow or shrink room in sk_buff. - * @skb: pointer to skb - * @len_diff: (signed) amount of room to grow/shrink - * @mode: operation mode (enum bpf_adj_room_mode) - * @flags: reserved for future use - * Return: 0 on success or negative error code - * - * int bpf_sk_redirect_map(map, key, flags) - * Redirect skb to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_sock_map_update(skops, map, key, flags) - * @skops: pointer to bpf_sock_ops - * @map: pointer to sockmap to update - * @key: key to insert/update sock in map - * @flags: same flags as map update elem - * - * int bpf_xdp_adjust_meta(xdp_md, delta) - * Adjust the xdp_md.data_meta by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data_meta - * Return: 0 on success or negative on error - * - * int bpf_perf_event_read_value(map, flags, buf, buf_size) - * read perf event counter value and perf event enabled/running time - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @buf: buf to fill - * @buf_size: size of the buf - * Return: 0 on success or negative error code - * - * int bpf_perf_prog_read_value(ctx, buf, buf_size) - * read perf prog attached perf event counter and enabled/running time - * @ctx: pointer to ctx - * @buf: buf to fill - * @buf_size: size of the buf - * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set - * - * int bpf_msg_redirect_map(map, key, flags) - * Redirect msg to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_bind(ctx, addr, addr_len) - * Bind socket to address. Only binding to IP is supported, no port can be - * set in addr. - * @ctx: pointer to context of type bpf_sock_addr - * @addr: pointer to struct sockaddr to bind socket to - * @addr_len: length of sockaddr structure - * Return: 0 on success or negative error code + * Description + * Copy a NUL terminated string from an unsafe address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read()** helper here instead + * to read the string would require to estimate the length at + * compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There is a single supported mode at this time: + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * The supported callback values that *argval* can combine are: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * + * Return + * a non-negative value equal to or less than size on success, or + * a negative error in case of failure. + * + * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * + * Return + * 0 on success, or a negative error in case of failure. + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -821,7 +1892,11 @@ union bpf_attr { FN(msg_apply_bytes), \ FN(msg_cork_bytes), \ FN(msg_pull_data), \ - FN(bind), + FN(bind), \ + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -855,11 +1930,14 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) -/* BPF_FUNC_get_stackid flags. */ +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ #define BPF_F_SKIP_FIELD_MASK 0xffULL #define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ #define BPF_F_FAST_STACK_CMP (1ULL << 9) #define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) /* BPF_FUNC_skb_set_tunnel_key flags. */ #define BPF_F_ZERO_CSUM_TX (1ULL << 1) @@ -879,6 +1957,12 @@ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, }; +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -927,6 +2011,19 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + /* Generic BPF return codes which all BPF program types may support. * The values are binary compatible with their TC_ACT_* counter-part to * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT @@ -1017,6 +2114,7 @@ struct bpf_prog_info { __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; + __u32 gpl_compatible:1; __u64 netns_dev; __u64 netns_ino; } __attribute__((aligned(8))); diff --git a/include/uapi/linux/btf.h b/include/uapi/linux/btf.h new file mode 100644 index 000000000000..bcb56ee47014 --- /dev/null +++ b/include/uapi/linux/btf.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef _UAPI__LINUX_BTF_H__ +#define _UAPI__LINUX_BTF_H__ + +#include <linux/types.h> + +#define BTF_MAGIC 0xeB9F +#define BTF_VERSION 1 + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + + __u32 parent_label; + __u32 parent_name; + + /* All offsets are in bytes relative to the end of this header */ + __u32 label_off; /* offset of label section */ + __u32 object_off; /* offset of data object section*/ + __u32 func_off; /* offset of function section */ + __u32 type_off; /* offset of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ +}; + +/* Max # of type identifier */ +#define BTF_MAX_TYPE 0x7fffffff +/* Max offset into the string section */ +#define BTF_MAX_NAME_OFFSET 0x7fffffff +/* Max # of struct/union/enum members or func args */ +#define BTF_MAX_VLEN 0xffff + +/* The type id is referring to a parent BTF */ +#define BTF_TYPE_PARENT(id) (((id) >> 31) & 0x1) +#define BTF_TYPE_ID(id) ((id) & BTF_MAX_TYPE) + +/* String is in the ELF string section */ +#define BTF_STR_TBL_ELF_ID(ref) (((ref) >> 31) & 0x1) +#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET) + +struct btf_type { + __u32 name_off; + /* "info" bits arrangement + * bits 0-15: vlen (e.g. # of struct's members) + * bits 16-23: unused + * bits 24-28: kind (e.g. int, ptr, array...etc) + * bits 29-30: unused + * bits 31: root + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT and UNION. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f) +#define BTF_INFO_ISROOT(info) (!!(((info) >> 24) & 0x80)) +#define BTF_INFO_VLEN(info) ((info) & 0xffff) + +#define BTF_KIND_UNKN 0 /* Unknown */ +#define BTF_KIND_INT 1 /* Integer */ +#define BTF_KIND_PTR 2 /* Pointer */ +#define BTF_KIND_ARRAY 3 /* Array */ +#define BTF_KIND_STRUCT 4 /* Struct */ +#define BTF_KIND_UNION 5 /* Union */ +#define BTF_KIND_ENUM 6 /* Enumeration */ +#define BTF_KIND_FWD 7 /* Forward */ +#define BTF_KIND_TYPEDEF 8 /* Typedef */ +#define BTF_KIND_VOLATILE 9 /* Volatile */ +#define BTF_KIND_CONST 10 /* Const */ +#define BTF_KIND_RESTRICT 11 /* Restrict */ +#define BTF_KIND_MAX 11 +#define NR_BTF_KINDS 12 + +/* For some specific BTF_KIND, "struct btf_type" is immediately + * followed by extra data. + */ + +/* BTF_KIND_INT is followed by a u32 and the following + * is the 32 bits arrangement: + */ +#define BTF_INT_ENCODING(VAL) (((VAL) & 0xff000000) >> 24) +#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) +#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) + +/* Attributes stored in the BTF_INT_ENCODING */ +#define BTF_INT_SIGNED 0x1 +#define BTF_INT_CHAR 0x2 +#define BTF_INT_BOOL 0x4 +#define BTF_INT_VARARGS 0x8 + +/* BTF_KIND_ENUM is followed by multiple "struct btf_enum". + * The exact number of btf_enum is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +/* BTF_KIND_ARRAY is followed by one "struct btf_array" */ +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed + * by multiple "struct btf_member". The exact number + * of btf_member is stored in the vlen (of the info in + * "struct btf_type"). + */ +struct btf_member { + __u32 name_off; + __u32 type; + __u32 offset; /* offset in bits */ +}; + +#endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/include/uapi/linux/cn_proc.h b/include/uapi/linux/cn_proc.h index 68ff25414700..db210625cee8 100644 --- a/include/uapi/linux/cn_proc.h +++ b/include/uapi/linux/cn_proc.h @@ -116,12 +116,16 @@ struct proc_event { struct coredump_proc_event { __kernel_pid_t process_pid; __kernel_pid_t process_tgid; + __kernel_pid_t parent_pid; + __kernel_pid_t parent_tgid; } coredump; struct exit_proc_event { __kernel_pid_t process_pid; __kernel_pid_t process_tgid; __u32 exit_code, exit_signal; + __kernel_pid_t parent_pid; + __kernel_pid_t parent_tgid; } exit; } event_data; diff --git a/include/uapi/linux/if_link.h b/include/uapi/linux/if_link.h index 68699f654118..b85266420bfb 100644 --- a/include/uapi/linux/if_link.h +++ b/include/uapi/linux/if_link.h @@ -516,6 +516,7 @@ enum { IFLA_VXLAN_COLLECT_METADATA, IFLA_VXLAN_LABEL, IFLA_VXLAN_GPE, + IFLA_VXLAN_TTL_INHERIT, __IFLA_VXLAN_MAX }; #define IFLA_VXLAN_MAX (__IFLA_VXLAN_MAX - 1) diff --git a/include/uapi/linux/if_xdp.h b/include/uapi/linux/if_xdp.h new file mode 100644 index 000000000000..77b88c4efe98 --- /dev/null +++ b/include/uapi/linux/if_xdp.h @@ -0,0 +1,87 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note + * + * if_xdp: XDP socket user-space interface + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * Author(s): Björn Töpel <bjorn.topel@intel.com> + * Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#ifndef _LINUX_IF_XDP_H +#define _LINUX_IF_XDP_H + +#include <linux/types.h> + +/* Options for the sxdp_flags field */ +#define XDP_SHARED_UMEM 1 + +struct sockaddr_xdp { + __u16 sxdp_family; + __u32 sxdp_ifindex; + __u32 sxdp_queue_id; + __u32 sxdp_shared_umem_fd; + __u16 sxdp_flags; +}; + +/* XDP socket options */ +#define XDP_RX_RING 1 +#define XDP_TX_RING 2 +#define XDP_UMEM_REG 3 +#define XDP_UMEM_FILL_RING 4 +#define XDP_UMEM_COMPLETION_RING 5 +#define XDP_STATISTICS 6 + +struct xdp_umem_reg { + __u64 addr; /* Start of packet data area */ + __u64 len; /* Length of packet data area */ + __u32 frame_size; /* Frame size */ + __u32 frame_headroom; /* Frame head room */ +}; + +struct xdp_statistics { + __u64 rx_dropped; /* Dropped for reasons other than invalid desc */ + __u64 rx_invalid_descs; /* Dropped due to invalid descriptor */ + __u64 tx_invalid_descs; /* Dropped due to invalid descriptor */ +}; + +/* Pgoff for mmaping the rings */ +#define XDP_PGOFF_RX_RING 0 +#define XDP_PGOFF_TX_RING 0x80000000 +#define XDP_UMEM_PGOFF_FILL_RING 0x100000000 +#define XDP_UMEM_PGOFF_COMPLETION_RING 0x180000000 + +struct xdp_desc { + __u32 idx; + __u32 len; + __u16 offset; + __u8 flags; + __u8 padding[5]; +}; + +struct xdp_ring { + __u32 producer __attribute__((aligned(64))); + __u32 consumer __attribute__((aligned(64))); +}; + +/* Used for the RX and TX queues for packets */ +struct xdp_rxtx_ring { + struct xdp_ring ptrs; + struct xdp_desc desc[0] __attribute__((aligned(64))); +}; + +/* Used for the fill and completion queues for buffers */ +struct xdp_umem_ring { + struct xdp_ring ptrs; + __u32 desc[0] __attribute__((aligned(64))); +}; + +#endif /* _LINUX_IF_XDP_H */ diff --git a/include/uapi/linux/netfilter/nf_nat.h b/include/uapi/linux/netfilter/nf_nat.h index a33000da7229..4a95c0db14d4 100644 --- a/include/uapi/linux/netfilter/nf_nat.h +++ b/include/uapi/linux/netfilter/nf_nat.h @@ -10,6 +10,7 @@ #define NF_NAT_RANGE_PROTO_RANDOM (1 << 2) #define NF_NAT_RANGE_PERSISTENT (1 << 3) #define NF_NAT_RANGE_PROTO_RANDOM_FULLY (1 << 4) +#define NF_NAT_RANGE_PROTO_OFFSET (1 << 5) #define NF_NAT_RANGE_PROTO_RANDOM_ALL \ (NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PROTO_RANDOM_FULLY) @@ -17,7 +18,7 @@ #define NF_NAT_RANGE_MASK \ (NF_NAT_RANGE_MAP_IPS | NF_NAT_RANGE_PROTO_SPECIFIED | \ NF_NAT_RANGE_PROTO_RANDOM | NF_NAT_RANGE_PERSISTENT | \ - NF_NAT_RANGE_PROTO_RANDOM_FULLY) + NF_NAT_RANGE_PROTO_RANDOM_FULLY | NF_NAT_RANGE_PROTO_OFFSET) struct nf_nat_ipv4_range { unsigned int flags; @@ -40,4 +41,13 @@ struct nf_nat_range { union nf_conntrack_man_proto max_proto; }; +struct nf_nat_range2 { + unsigned int flags; + union nf_inet_addr min_addr; + union nf_inet_addr max_addr; + union nf_conntrack_man_proto min_proto; + union nf_conntrack_man_proto max_proto; + union nf_conntrack_man_proto base_proto; +}; + #endif /* _NETFILTER_NF_NAT_H */ diff --git a/include/uapi/linux/netfilter/nf_osf.h b/include/uapi/linux/netfilter/nf_osf.h new file mode 100644 index 000000000000..45376eae31ef --- /dev/null +++ b/include/uapi/linux/netfilter/nf_osf.h @@ -0,0 +1,90 @@ +#ifndef _NF_OSF_H +#define _NF_OSF_H + +#define MAXGENRELEN 32 + +#define NF_OSF_GENRE (1 << 0) +#define NF_OSF_TTL (1 << 1) +#define NF_OSF_LOG (1 << 2) +#define NF_OSF_INVERT (1 << 3) + +#define NF_OSF_LOGLEVEL_ALL 0 /* log all matched fingerprints */ +#define NF_OSF_LOGLEVEL_FIRST 1 /* log only the first matced fingerprint */ +#define NF_OSF_LOGLEVEL_ALL_KNOWN 2 /* do not log unknown packets */ + +#define NF_OSF_TTL_TRUE 0 /* True ip and fingerprint TTL comparison */ + +/* Do not compare ip and fingerprint TTL at all */ +#define NF_OSF_TTL_NOCHECK 2 + +/* Wildcard MSS (kind of). + * It is used to implement a state machine for the different wildcard values + * of the MSS and window sizes. + */ +struct nf_osf_wc { + __u32 wc; + __u32 val; +}; + +/* This struct represents IANA options + * http://www.iana.org/assignments/tcp-parameters + */ +struct nf_osf_opt { + __u16 kind, length; + struct nf_osf_wc wc; +}; + +struct nf_osf_info { + char genre[MAXGENRELEN]; + __u32 len; + __u32 flags; + __u32 loglevel; + __u32 ttl; +}; + +struct nf_osf_user_finger { + struct nf_osf_wc wss; + + __u8 ttl, df; + __u16 ss, mss; + __u16 opt_num; + + char genre[MAXGENRELEN]; + char version[MAXGENRELEN]; + char subtype[MAXGENRELEN]; + + /* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */ + struct nf_osf_opt opt[MAX_IPOPTLEN]; +}; + +struct nf_osf_finger { + struct rcu_head rcu_head; + struct list_head finger_entry; + struct nf_osf_user_finger finger; +}; + +struct nf_osf_nlmsg { + struct nf_osf_user_finger f; + struct iphdr ip; + struct tcphdr tcp; +}; + +/* Defines for IANA option kinds */ +enum iana_options { + OSFOPT_EOL = 0, /* End of options */ + OSFOPT_NOP, /* NOP */ + OSFOPT_MSS, /* Maximum segment size */ + OSFOPT_WSO, /* Window scale option */ + OSFOPT_SACKP, /* SACK permitted */ + OSFOPT_SACK, /* SACK */ + OSFOPT_ECHO, + OSFOPT_ECHOREPLY, + OSFOPT_TS, /* Timestamp option */ + OSFOPT_POCP, /* Partial Order Connection Permitted */ + OSFOPT_POSP, /* Partial Order Service Profile */ + + /* Others are not used in the current OSF */ + OSFOPT_EMPTY = 255, +}; + +#endif /* _NF_OSF_H */ diff --git a/include/uapi/linux/netfilter/nf_tables.h b/include/uapi/linux/netfilter/nf_tables.h index 6a3d653d5b27..ce031cf72288 100644 --- a/include/uapi/linux/netfilter/nf_tables.h +++ b/include/uapi/linux/netfilter/nf_tables.h @@ -831,7 +831,9 @@ enum nft_rt_keys { NFT_RT_NEXTHOP4, NFT_RT_NEXTHOP6, NFT_RT_TCPMSS, + __NFT_RT_MAX }; +#define NFT_RT_MAX (__NFT_RT_MAX - 1) /** * enum nft_hash_types - nf_tables hash expression types @@ -949,7 +951,9 @@ enum nft_ct_keys { NFT_CT_DST_IP, NFT_CT_SRC_IP6, NFT_CT_DST_IP6, + __NFT_CT_MAX }; +#define NFT_CT_MAX (__NFT_CT_MAX - 1) /** * enum nft_ct_attributes - nf_tables ct expression netlink attributes @@ -1450,6 +1454,8 @@ enum nft_trace_types { * @NFTA_NG_MODULUS: maximum counter value (NLA_U32) * @NFTA_NG_TYPE: operation type (NLA_U32) * @NFTA_NG_OFFSET: offset to be added to the counter (NLA_U32) + * @NFTA_NG_SET_NAME: name of the map to lookup (NLA_STRING) + * @NFTA_NG_SET_ID: id of the map (NLA_U32) */ enum nft_ng_attributes { NFTA_NG_UNSPEC, @@ -1457,6 +1463,8 @@ enum nft_ng_attributes { NFTA_NG_MODULUS, NFTA_NG_TYPE, NFTA_NG_OFFSET, + NFTA_NG_SET_NAME, + NFTA_NG_SET_ID, __NFTA_NG_MAX }; #define NFTA_NG_MAX (__NFTA_NG_MAX - 1) diff --git a/include/uapi/linux/netfilter/nfnetlink_conntrack.h b/include/uapi/linux/netfilter/nfnetlink_conntrack.h index 77987111cab0..1d41810d17e2 100644 --- a/include/uapi/linux/netfilter/nfnetlink_conntrack.h +++ b/include/uapi/linux/netfilter/nfnetlink_conntrack.h @@ -262,6 +262,7 @@ enum ctattr_stats_cpu { enum ctattr_stats_global { CTA_STATS_GLOBAL_UNSPEC, CTA_STATS_GLOBAL_ENTRIES, + CTA_STATS_GLOBAL_MAX_ENTRIES, __CTA_STATS_GLOBAL_MAX, }; #define CTA_STATS_GLOBAL_MAX (__CTA_STATS_GLOBAL_MAX - 1) diff --git a/include/uapi/linux/netfilter/xt_osf.h b/include/uapi/linux/netfilter/xt_osf.h index dad197e2ab99..72956eceeb09 100644 --- a/include/uapi/linux/netfilter/xt_osf.h +++ b/include/uapi/linux/netfilter/xt_osf.h @@ -23,101 +23,29 @@ #include <linux/types.h> #include <linux/ip.h> #include <linux/tcp.h> +#include <linux/netfilter/nf_osf.h> -#define MAXGENRELEN 32 +#define XT_OSF_GENRE NF_OSF_GENRE +#define XT_OSF_INVERT NF_OSF_INVERT -#define XT_OSF_GENRE (1<<0) -#define XT_OSF_TTL (1<<1) -#define XT_OSF_LOG (1<<2) -#define XT_OSF_INVERT (1<<3) +#define XT_OSF_TTL NF_OSF_TTL +#define XT_OSF_LOG NF_OSF_LOG -#define XT_OSF_LOGLEVEL_ALL 0 /* log all matched fingerprints */ -#define XT_OSF_LOGLEVEL_FIRST 1 /* log only the first matced fingerprint */ -#define XT_OSF_LOGLEVEL_ALL_KNOWN 2 /* do not log unknown packets */ +#define XT_OSF_LOGLEVEL_ALL NF_OSF_LOGLEVEL_ALL +#define XT_OSF_LOGLEVEL_FIRST NF_OSF_LOGLEVEL_FIRST +#define XT_OSF_LOGLEVEL_ALL_KNOWN NF_OSF_LOGLEVEL_ALL_KNOWN -#define XT_OSF_TTL_TRUE 0 /* True ip and fingerprint TTL comparison */ -#define XT_OSF_TTL_LESS 1 /* Check if ip TTL is less than fingerprint one */ -#define XT_OSF_TTL_NOCHECK 2 /* Do not compare ip and fingerprint TTL at all */ +#define XT_OSF_TTL_TRUE NF_OSF_TTL_TRUE +#define XT_OSF_TTL_NOCHECK NF_OSF_TTL_NOCHECK -struct xt_osf_info { - char genre[MAXGENRELEN]; - __u32 len; - __u32 flags; - __u32 loglevel; - __u32 ttl; -}; - -/* - * Wildcard MSS (kind of). - * It is used to implement a state machine for the different wildcard values - * of the MSS and window sizes. - */ -struct xt_osf_wc { - __u32 wc; - __u32 val; -}; - -/* - * This struct represents IANA options - * http://www.iana.org/assignments/tcp-parameters - */ -struct xt_osf_opt { - __u16 kind, length; - struct xt_osf_wc wc; -}; - -struct xt_osf_user_finger { - struct xt_osf_wc wss; - - __u8 ttl, df; - __u16 ss, mss; - __u16 opt_num; - - char genre[MAXGENRELEN]; - char version[MAXGENRELEN]; - char subtype[MAXGENRELEN]; +#define XT_OSF_TTL_LESS 1 /* Check if ip TTL is less than fingerprint one */ - /* MAX_IPOPTLEN is maximum if all options are NOPs or EOLs */ - struct xt_osf_opt opt[MAX_IPOPTLEN]; -}; - -struct xt_osf_nlmsg { - struct xt_osf_user_finger f; - struct iphdr ip; - struct tcphdr tcp; -}; - -/* Defines for IANA option kinds */ - -enum iana_options { - OSFOPT_EOL = 0, /* End of options */ - OSFOPT_NOP, /* NOP */ - OSFOPT_MSS, /* Maximum segment size */ - OSFOPT_WSO, /* Window scale option */ - OSFOPT_SACKP, /* SACK permitted */ - OSFOPT_SACK, /* SACK */ - OSFOPT_ECHO, - OSFOPT_ECHOREPLY, - OSFOPT_TS, /* Timestamp option */ - OSFOPT_POCP, /* Partial Order Connection Permitted */ - OSFOPT_POSP, /* Partial Order Service Profile */ - - /* Others are not used in the current OSF */ - OSFOPT_EMPTY = 255, -}; - -/* - * Initial window size option state machine: multiple of mss, mtu or - * plain numeric value. Can also be made as plain numeric value which - * is not a multiple of specified value. - */ -enum xt_osf_window_size_options { - OSF_WSS_PLAIN = 0, - OSF_WSS_MSS, - OSF_WSS_MTU, - OSF_WSS_MODULO, - OSF_WSS_MAX, -}; +#define xt_osf_wc nf_osf_wc +#define xt_osf_opt nf_osf_opt +#define xt_osf_info nf_osf_info +#define xt_osf_user_finger nf_osf_user_finger +#define xt_osf_finger nf_osf_finger +#define xt_osf_nlmsg nf_osf_nlmsg /* * Add/remove fingerprint from the kernel. diff --git a/include/uapi/linux/netfilter_bridge/ebtables.h b/include/uapi/linux/netfilter_bridge/ebtables.h index 0c7dc8315013..3b86c14ea49d 100644 --- a/include/uapi/linux/netfilter_bridge/ebtables.h +++ b/include/uapi/linux/netfilter_bridge/ebtables.h @@ -191,6 +191,12 @@ struct ebt_entry { unsigned char elems[0] __attribute__ ((aligned (__alignof__(struct ebt_replace)))); }; +static __inline__ struct ebt_entry_target * +ebt_get_target(struct ebt_entry *e) +{ + return (void *)e + e->target_offset; +} + /* {g,s}etsockopt numbers */ #define EBT_BASE_CTL 128 diff --git a/include/uapi/linux/netfilter_ipv6/ip6t_srh.h b/include/uapi/linux/netfilter_ipv6/ip6t_srh.h index f3cc0ef514a7..54ed83360dac 100644 --- a/include/uapi/linux/netfilter_ipv6/ip6t_srh.h +++ b/include/uapi/linux/netfilter_ipv6/ip6t_srh.h @@ -17,7 +17,10 @@ #define IP6T_SRH_LAST_GT 0x0100 #define IP6T_SRH_LAST_LT 0x0200 #define IP6T_SRH_TAG 0x0400 -#define IP6T_SRH_MASK 0x07FF +#define IP6T_SRH_PSID 0x0800 +#define IP6T_SRH_NSID 0x1000 +#define IP6T_SRH_LSID 0x2000 +#define IP6T_SRH_MASK 0x3FFF /* Values for "mt_invflags" field in struct ip6t_srh */ #define IP6T_SRH_INV_NEXTHDR 0x0001 @@ -31,7 +34,10 @@ #define IP6T_SRH_INV_LAST_GT 0x0100 #define IP6T_SRH_INV_LAST_LT 0x0200 #define IP6T_SRH_INV_TAG 0x0400 -#define IP6T_SRH_INV_MASK 0x07FF +#define IP6T_SRH_INV_PSID 0x0800 +#define IP6T_SRH_INV_NSID 0x1000 +#define IP6T_SRH_INV_LSID 0x2000 +#define IP6T_SRH_INV_MASK 0x3FFF /** * struct ip6t_srh - SRH match options @@ -54,4 +60,37 @@ struct ip6t_srh { __u16 mt_invflags; }; +/** + * struct ip6t_srh1 - SRH match options (revision 1) + * @ next_hdr: Next header field of SRH + * @ hdr_len: Extension header length field of SRH + * @ segs_left: Segments left field of SRH + * @ last_entry: Last entry field of SRH + * @ tag: Tag field of SRH + * @ psid_addr: Address of previous SID in SRH SID list + * @ nsid_addr: Address of NEXT SID in SRH SID list + * @ lsid_addr: Address of LAST SID in SRH SID list + * @ psid_msk: Mask of previous SID in SRH SID list + * @ nsid_msk: Mask of next SID in SRH SID list + * @ lsid_msk: MAsk of last SID in SRH SID list + * @ mt_flags: match options + * @ mt_invflags: Invert the sense of match options + */ + +struct ip6t_srh1 { + __u8 next_hdr; + __u8 hdr_len; + __u8 segs_left; + __u8 last_entry; + __u16 tag; + struct in6_addr psid_addr; + struct in6_addr nsid_addr; + struct in6_addr lsid_addr; + struct in6_addr psid_msk; + struct in6_addr nsid_msk; + struct in6_addr lsid_msk; + __u16 mt_flags; + __u16 mt_invflags; +}; + #endif /*_IP6T_SRH_H*/ diff --git a/include/uapi/linux/pci_regs.h b/include/uapi/linux/pci_regs.h index 103ba797a8f3..83ade9b5cf95 100644 --- a/include/uapi/linux/pci_regs.h +++ b/include/uapi/linux/pci_regs.h @@ -506,6 +506,8 @@ #define PCI_EXP_DEVCTL_READRQ_256B 0x1000 /* 256 Bytes */ #define PCI_EXP_DEVCTL_READRQ_512B 0x2000 /* 512 Bytes */ #define PCI_EXP_DEVCTL_READRQ_1024B 0x3000 /* 1024 Bytes */ +#define PCI_EXP_DEVCTL_READRQ_2048B 0x4000 /* 2048 Bytes */ +#define PCI_EXP_DEVCTL_READRQ_4096B 0x5000 /* 4096 Bytes */ #define PCI_EXP_DEVCTL_BCR_FLR 0x8000 /* Bridge Configuration Retry / FLR */ #define PCI_EXP_DEVSTA 10 /* Device Status */ #define PCI_EXP_DEVSTA_CED 0x0001 /* Correctable Error Detected */ diff --git a/include/uapi/linux/snmp.h b/include/uapi/linux/snmp.h index 33a70ece462f..d02e859301ff 100644 --- a/include/uapi/linux/snmp.h +++ b/include/uapi/linux/snmp.h @@ -276,6 +276,8 @@ enum LINUX_MIB_TCPKEEPALIVE, /* TCPKeepAlive */ LINUX_MIB_TCPMTUPFAIL, /* TCPMTUPFail */ LINUX_MIB_TCPMTUPSUCCESS, /* TCPMTUPSuccess */ + LINUX_MIB_TCPDELIVERED, /* TCPDelivered */ + LINUX_MIB_TCPDELIVEREDCE, /* TCPDeliveredCE */ __LINUX_MIB_MAX }; diff --git a/include/uapi/linux/tcp.h b/include/uapi/linux/tcp.h index 560374c978f9..29eb659aa77a 100644 --- a/include/uapi/linux/tcp.h +++ b/include/uapi/linux/tcp.h @@ -122,6 +122,10 @@ enum { #define TCP_MD5SIG_EXT 32 /* TCP MD5 Signature with extensions */ #define TCP_FASTOPEN_KEY 33 /* Set the key for Fast Open (cookie) */ #define TCP_FASTOPEN_NO_COOKIE 34 /* Enable TFO without a TFO cookie */ +#define TCP_ZEROCOPY_RECEIVE 35 +#define TCP_INQ 36 /* Notify bytes available to read as a cmsg on read */ + +#define TCP_CM_INQ TCP_INQ struct tcp_repair_opt { __u32 opt_code; @@ -224,6 +228,9 @@ struct tcp_info { __u64 tcpi_busy_time; /* Time (usec) busy sending data */ __u64 tcpi_rwnd_limited; /* Time (usec) limited by receive window */ __u64 tcpi_sndbuf_limited; /* Time (usec) limited by send buffer */ + + __u32 tcpi_delivered; + __u32 tcpi_delivered_ce; }; /* netlink attributes types for SCM_TIMESTAMPING_OPT_STATS */ @@ -244,6 +251,8 @@ enum { TCP_NLA_SNDQ_SIZE, /* Data (bytes) pending in send queue */ TCP_NLA_CA_STATE, /* ca_state of socket */ TCP_NLA_SND_SSTHRESH, /* Slow start size threshold */ + TCP_NLA_DELIVERED, /* Data pkts delivered incl. out-of-order */ + TCP_NLA_DELIVERED_CE, /* Like above but only ones w/ CE marks */ }; @@ -271,4 +280,11 @@ struct tcp_diag_md5sig { __u8 tcpm_key[TCP_MD5SIG_MAXKEYLEN]; }; +/* setsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, ...) */ + +struct tcp_zerocopy_receive { + __u64 address; /* in: address of mapping */ + __u32 length; /* in/out: number of bytes to map/mapped */ + __u32 recv_skip_hint; /* out: amount of bytes to skip */ +}; #endif /* _UAPI_LINUX_TCP_H */ diff --git a/include/uapi/linux/tipc.h b/include/uapi/linux/tipc.h index bf6d28677cfe..6b2fd4d9655f 100644 --- a/include/uapi/linux/tipc.h +++ b/include/uapi/linux/tipc.h @@ -209,16 +209,16 @@ struct tipc_group_req { * The string formatting for each name element is: * media: media * interface: media:interface name - * link: Z.C.N:interface-Z.C.N:interface - * + * link: node:interface-node:interface */ - +#define TIPC_NODEID_LEN 16 #define TIPC_MAX_MEDIA_NAME 16 #define TIPC_MAX_IF_NAME 16 #define TIPC_MAX_BEARER_NAME 32 #define TIPC_MAX_LINK_NAME 68 -#define SIOCGETLINKNAME SIOCPROTOPRIVATE +#define SIOCGETLINKNAME SIOCPROTOPRIVATE +#define SIOCGETNODEID (SIOCPROTOPRIVATE + 1) struct tipc_sioc_ln_req { __u32 peer; @@ -226,6 +226,10 @@ struct tipc_sioc_ln_req { char linkname[TIPC_MAX_LINK_NAME]; }; +struct tipc_sioc_nodeid_req { + __u32 peer; + char node_id[TIPC_NODEID_LEN]; +}; /* The macros and functions below are deprecated: */ diff --git a/include/uapi/linux/tipc_config.h b/include/uapi/linux/tipc_config.h index 3f29e3c8ed06..4b2c93b1934c 100644 --- a/include/uapi/linux/tipc_config.h +++ b/include/uapi/linux/tipc_config.h @@ -185,6 +185,11 @@ #define TIPC_DEF_LINK_WIN 50 #define TIPC_MAX_LINK_WIN 8191 +/* + * Default MTU for UDP media + */ + +#define TIPC_DEF_LINK_UDP_MTU 14000 struct tipc_node_info { __be32 addr; /* network address of node */ diff --git a/include/uapi/linux/tipc_netlink.h b/include/uapi/linux/tipc_netlink.h index 0affb682e5e3..85c11982c89b 100644 --- a/include/uapi/linux/tipc_netlink.h +++ b/include/uapi/linux/tipc_netlink.h @@ -266,6 +266,7 @@ enum { TIPC_NLA_PROP_PRIO, /* u32 */ TIPC_NLA_PROP_TOL, /* u32 */ TIPC_NLA_PROP_WIN, /* u32 */ + TIPC_NLA_PROP_MTU, /* u32 */ __TIPC_NLA_PROP_MAX, TIPC_NLA_PROP_MAX = __TIPC_NLA_PROP_MAX - 1 diff --git a/include/uapi/linux/udp.h b/include/uapi/linux/udp.h index efb7b5991c2f..09d00f8c442b 100644 --- a/include/uapi/linux/udp.h +++ b/include/uapi/linux/udp.h @@ -32,6 +32,7 @@ struct udphdr { #define UDP_ENCAP 100 /* Set the socket to accept encapsulated packets */ #define UDP_NO_CHECK6_TX 101 /* Disable sending checksum for UDP6X */ #define UDP_NO_CHECK6_RX 102 /* Disable accpeting checksum for UDP6 */ +#define UDP_SEGMENT 103 /* Set GSO segmentation size */ /* UDP encapsulation types */ #define UDP_ENCAP_ESPINUDP_NON_IKE 1 /* draft-ietf-ipsec-nat-t-ike-00/01 */ diff --git a/kernel/bpf/Makefile b/kernel/bpf/Makefile index a713fd23ec88..f27f5496d6fe 100644 --- a/kernel/bpf/Makefile +++ b/kernel/bpf/Makefile @@ -4,9 +4,13 @@ obj-y := core.o obj-$(CONFIG_BPF_SYSCALL) += syscall.o verifier.o inode.o helpers.o tnum.o obj-$(CONFIG_BPF_SYSCALL) += hashtab.o arraymap.o percpu_freelist.o bpf_lru_list.o lpm_trie.o map_in_map.o obj-$(CONFIG_BPF_SYSCALL) += disasm.o +obj-$(CONFIG_BPF_SYSCALL) += btf.o ifeq ($(CONFIG_NET),y) obj-$(CONFIG_BPF_SYSCALL) += devmap.o obj-$(CONFIG_BPF_SYSCALL) += cpumap.o +ifeq ($(CONFIG_XDP_SOCKETS),y) +obj-$(CONFIG_BPF_SYSCALL) += xskmap.o +endif obj-$(CONFIG_BPF_SYSCALL) += offload.o ifeq ($(CONFIG_STREAM_PARSER),y) ifeq ($(CONFIG_INET),y) diff --git a/kernel/bpf/arraymap.c b/kernel/bpf/arraymap.c index 027107f4be53..0fd8d8f1a398 100644 --- a/kernel/bpf/arraymap.c +++ b/kernel/bpf/arraymap.c @@ -11,11 +11,13 @@ * General Public License for more details. */ #include <linux/bpf.h> +#include <linux/btf.h> #include <linux/err.h> #include <linux/slab.h> #include <linux/mm.h> #include <linux/filter.h> #include <linux/perf_event.h> +#include <uapi/linux/btf.h> #include "map_in_map.h" @@ -336,6 +338,52 @@ static void array_map_free(struct bpf_map *map) bpf_map_area_free(array); } +static void array_map_seq_show_elem(struct bpf_map *map, void *key, + struct seq_file *m) +{ + void *value; + + rcu_read_lock(); + + value = array_map_lookup_elem(map, key); + if (!value) { + rcu_read_unlock(); + return; + } + + seq_printf(m, "%u: ", *(u32 *)key); + btf_type_seq_show(map->btf, map->btf_value_id, value, m); + seq_puts(m, "\n"); + + rcu_read_unlock(); +} + +static int array_map_check_btf(const struct bpf_map *map, const struct btf *btf, + u32 btf_key_id, u32 btf_value_id) +{ + const struct btf_type *key_type, *value_type; + u32 key_size, value_size; + u32 int_data; + + key_type = btf_type_id_size(btf, &btf_key_id, &key_size); + if (!key_type || BTF_INFO_KIND(key_type->info) != BTF_KIND_INT) + return -EINVAL; + + int_data = *(u32 *)(key_type + 1); + /* bpf array can only take a u32 key. This check makes + * sure that the btf matches the attr used during map_create. + */ + if (BTF_INT_BITS(int_data) != 32 || key_size != 4 || + BTF_INT_OFFSET(int_data)) + return -EINVAL; + + value_type = btf_type_id_size(btf, &btf_value_id, &value_size); + if (!value_type || value_size > map->value_size) + return -EINVAL; + + return 0; +} + const struct bpf_map_ops array_map_ops = { .map_alloc_check = array_map_alloc_check, .map_alloc = array_map_alloc, @@ -345,6 +393,8 @@ const struct bpf_map_ops array_map_ops = { .map_update_elem = array_map_update_elem, .map_delete_elem = array_map_delete_elem, .map_gen_lookup = array_map_gen_lookup, + .map_seq_show_elem = array_map_seq_show_elem, + .map_check_btf = array_map_check_btf, }; const struct bpf_map_ops percpu_array_map_ops = { diff --git a/kernel/bpf/btf.c b/kernel/bpf/btf.c new file mode 100644 index 000000000000..22e1046a1a86 --- /dev/null +++ b/kernel/bpf/btf.c @@ -0,0 +1,2064 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <uapi/linux/btf.h> +#include <uapi/linux/types.h> +#include <linux/seq_file.h> +#include <linux/compiler.h> +#include <linux/errno.h> +#include <linux/slab.h> +#include <linux/anon_inodes.h> +#include <linux/file.h> +#include <linux/uaccess.h> +#include <linux/kernel.h> +#include <linux/bpf_verifier.h> +#include <linux/btf.h> + +/* BTF (BPF Type Format) is the meta data format which describes + * the data types of BPF program/map. Hence, it basically focus + * on the C programming language which the modern BPF is primary + * using. + * + * ELF Section: + * ~~~~~~~~~~~ + * The BTF data is stored under the ".BTF" ELF section + * + * struct btf_type: + * ~~~~~~~~~~~~~~~ + * Each 'struct btf_type' object describes a C data type. + * Depending on the type it is describing, a 'struct btf_type' + * object may be followed by more data. F.e. + * To describe an array, 'struct btf_type' is followed by + * 'struct btf_array'. + * + * 'struct btf_type' and any extra data following it are + * 4 bytes aligned. + * + * Type section: + * ~~~~~~~~~~~~~ + * The BTF type section contains a list of 'struct btf_type' objects. + * Each one describes a C type. Recall from the above section + * that a 'struct btf_type' object could be immediately followed by extra + * data in order to desribe some particular C types. + * + * type_id: + * ~~~~~~~ + * Each btf_type object is identified by a type_id. The type_id + * is implicitly implied by the location of the btf_type object in + * the BTF type section. The first one has type_id 1. The second + * one has type_id 2...etc. Hence, an earlier btf_type has + * a smaller type_id. + * + * A btf_type object may refer to another btf_type object by using + * type_id (i.e. the "type" in the "struct btf_type"). + * + * NOTE that we cannot assume any reference-order. + * A btf_type object can refer to an earlier btf_type object + * but it can also refer to a later btf_type object. + * + * For example, to describe "const void *". A btf_type + * object describing "const" may refer to another btf_type + * object describing "void *". This type-reference is done + * by specifying type_id: + * + * [1] CONST (anon) type_id=2 + * [2] PTR (anon) type_id=0 + * + * The above is the btf_verifier debug log: + * - Each line started with "[?]" is a btf_type object + * - [?] is the type_id of the btf_type object. + * - CONST/PTR is the BTF_KIND_XXX + * - "(anon)" is the name of the type. It just + * happens that CONST and PTR has no name. + * - type_id=XXX is the 'u32 type' in btf_type + * + * NOTE: "void" has type_id 0 + * + * String section: + * ~~~~~~~~~~~~~~ + * The BTF string section contains the names used by the type section. + * Each string is referred by an "offset" from the beginning of the + * string section. + * + * Each string is '\0' terminated. + * + * The first character in the string section must be '\0' + * which is used to mean 'anonymous'. Some btf_type may not + * have a name. + */ + +/* BTF verification: + * + * To verify BTF data, two passes are needed. + * + * Pass #1 + * ~~~~~~~ + * The first pass is to collect all btf_type objects to + * an array: "btf->types". + * + * Depending on the C type that a btf_type is describing, + * a btf_type may be followed by extra data. We don't know + * how many btf_type is there, and more importantly we don't + * know where each btf_type is located in the type section. + * + * Without knowing the location of each type_id, most verifications + * cannot be done. e.g. an earlier btf_type may refer to a later + * btf_type (recall the "const void *" above), so we cannot + * check this type-reference in the first pass. + * + * In the first pass, it still does some verifications (e.g. + * checking the name is a valid offset to the string section). + * + * Pass #2 + * ~~~~~~~ + * The main focus is to resolve a btf_type that is referring + * to another type. + * + * We have to ensure the referring type: + * 1) does exist in the BTF (i.e. in btf->types[]) + * 2) does not cause a loop: + * struct A { + * struct B b; + * }; + * + * struct B { + * struct A a; + * }; + * + * btf_type_needs_resolve() decides if a btf_type needs + * to be resolved. + * + * The needs_resolve type implements the "resolve()" ops which + * essentially does a DFS and detects backedge. + * + * During resolve (or DFS), different C types have different + * "RESOLVED" conditions. + * + * When resolving a BTF_KIND_STRUCT, we need to resolve all its + * members because a member is always referring to another + * type. A struct's member can be treated as "RESOLVED" if + * it is referring to a BTF_KIND_PTR. Otherwise, the + * following valid C struct would be rejected: + * + * struct A { + * int m; + * struct A *a; + * }; + * + * When resolving a BTF_KIND_PTR, it needs to keep resolving if + * it is referring to another BTF_KIND_PTR. Otherwise, we cannot + * detect a pointer loop, e.g.: + * BTF_KIND_CONST -> BTF_KIND_PTR -> BTF_KIND_CONST -> BTF_KIND_PTR + + * ^ | + * +-----------------------------------------+ + * + */ + +#define BITS_PER_U64 (sizeof(u64) * BITS_PER_BYTE) +#define BITS_PER_BYTE_MASK (BITS_PER_BYTE - 1) +#define BITS_PER_BYTE_MASKED(bits) ((bits) & BITS_PER_BYTE_MASK) +#define BITS_ROUNDDOWN_BYTES(bits) ((bits) >> 3) +#define BITS_ROUNDUP_BYTES(bits) \ + (BITS_ROUNDDOWN_BYTES(bits) + !!BITS_PER_BYTE_MASKED(bits)) + +/* 16MB for 64k structs and each has 16 members and + * a few MB spaces for the string section. + * The hard limit is S32_MAX. + */ +#define BTF_MAX_SIZE (16 * 1024 * 1024) +/* 64k. We can raise it later. The hard limit is S32_MAX. */ +#define BTF_MAX_NR_TYPES 65535 + +#define for_each_member(i, struct_type, member) \ + for (i = 0, member = btf_type_member(struct_type); \ + i < btf_type_vlen(struct_type); \ + i++, member++) + +#define for_each_member_from(i, from, struct_type, member) \ + for (i = from, member = btf_type_member(struct_type) + from; \ + i < btf_type_vlen(struct_type); \ + i++, member++) + +struct btf { + union { + struct btf_header *hdr; + void *data; + }; + struct btf_type **types; + u32 *resolved_ids; + u32 *resolved_sizes; + const char *strings; + void *nohdr_data; + u32 nr_types; + u32 types_size; + u32 data_size; + refcount_t refcnt; +}; + +enum verifier_phase { + CHECK_META, + CHECK_TYPE, +}; + +struct resolve_vertex { + const struct btf_type *t; + u32 type_id; + u16 next_member; +}; + +enum visit_state { + NOT_VISITED, + VISITED, + RESOLVED, +}; + +enum resolve_mode { + RESOLVE_TBD, /* To Be Determined */ + RESOLVE_PTR, /* Resolving for Pointer */ + RESOLVE_STRUCT_OR_ARRAY, /* Resolving for struct/union + * or array + */ +}; + +#define MAX_RESOLVE_DEPTH 32 + +struct btf_verifier_env { + struct btf *btf; + u8 *visit_states; + struct resolve_vertex stack[MAX_RESOLVE_DEPTH]; + struct bpf_verifier_log log; + u32 log_type_id; + u32 top_stack; + enum verifier_phase phase; + enum resolve_mode resolve_mode; +}; + +static const char * const btf_kind_str[NR_BTF_KINDS] = { + [BTF_KIND_UNKN] = "UNKNOWN", + [BTF_KIND_INT] = "INT", + [BTF_KIND_PTR] = "PTR", + [BTF_KIND_ARRAY] = "ARRAY", + [BTF_KIND_STRUCT] = "STRUCT", + [BTF_KIND_UNION] = "UNION", + [BTF_KIND_ENUM] = "ENUM", + [BTF_KIND_FWD] = "FWD", + [BTF_KIND_TYPEDEF] = "TYPEDEF", + [BTF_KIND_VOLATILE] = "VOLATILE", + [BTF_KIND_CONST] = "CONST", + [BTF_KIND_RESTRICT] = "RESTRICT", +}; + +struct btf_kind_operations { + s32 (*check_meta)(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left); + int (*resolve)(struct btf_verifier_env *env, + const struct resolve_vertex *v); + int (*check_member)(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type); + void (*log_details)(struct btf_verifier_env *env, + const struct btf_type *t); + void (*seq_show)(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offsets, + struct seq_file *m); +}; + +static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS]; +static struct btf_type btf_void; + +static bool btf_type_is_modifier(const struct btf_type *t) +{ + /* Some of them is not strictly a C modifier + * but they are grouped into the same bucket + * for BTF concern: + * A type (t) that refers to another + * type through t->type AND its size cannot + * be determined without following the t->type. + * + * ptr does not fall into this bucket + * because its size is always sizeof(void *). + */ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + return true; + } + + return false; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + /* void => no type and size info. + * Hence, FWD is also treated as void. + */ + return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +/* union is only a special case of struct: + * all its offsetof(member) == 0 + */ +static bool btf_type_is_struct(const struct btf_type *t) +{ + u8 kind = BTF_INFO_KIND(t->info); + + return kind == BTF_KIND_STRUCT || kind == BTF_KIND_UNION; +} + +static bool btf_type_is_array(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_ARRAY; +} + +static bool btf_type_is_ptr(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_PTR; +} + +static bool btf_type_is_int(const struct btf_type *t) +{ + return BTF_INFO_KIND(t->info) == BTF_KIND_INT; +} + +/* What types need to be resolved? + * + * btf_type_is_modifier() is an obvious one. + * + * btf_type_is_struct() because its member refers to + * another type (through member->type). + + * btf_type_is_array() because its element (array->type) + * refers to another type. Array can be thought of a + * special case of struct while array just has the same + * member-type repeated by array->nelems of times. + */ +static bool btf_type_needs_resolve(const struct btf_type *t) +{ + return btf_type_is_modifier(t) || + btf_type_is_ptr(t) || + btf_type_is_struct(t) || + btf_type_is_array(t); +} + +/* t->size can be used */ +static bool btf_type_has_size(const struct btf_type *t) +{ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + return true; + } + + return false; +} + +static const char *btf_int_encoding_str(u8 encoding) +{ + if (encoding == 0) + return "(none)"; + else if (encoding == BTF_INT_SIGNED) + return "SIGNED"; + else if (encoding == BTF_INT_CHAR) + return "CHAR"; + else if (encoding == BTF_INT_BOOL) + return "BOOL"; + else if (encoding == BTF_INT_VARARGS) + return "VARARGS"; + else + return "UNKN"; +} + +static u16 btf_type_vlen(const struct btf_type *t) +{ + return BTF_INFO_VLEN(t->info); +} + +static u32 btf_type_int(const struct btf_type *t) +{ + return *(u32 *)(t + 1); +} + +static const struct btf_array *btf_type_array(const struct btf_type *t) +{ + return (const struct btf_array *)(t + 1); +} + +static const struct btf_member *btf_type_member(const struct btf_type *t) +{ + return (const struct btf_member *)(t + 1); +} + +static const struct btf_enum *btf_type_enum(const struct btf_type *t) +{ + return (const struct btf_enum *)(t + 1); +} + +static const struct btf_kind_operations *btf_type_ops(const struct btf_type *t) +{ + return kind_ops[BTF_INFO_KIND(t->info)]; +} + +static bool btf_name_offset_valid(const struct btf *btf, u32 offset) +{ + return !BTF_STR_TBL_ELF_ID(offset) && + BTF_STR_OFFSET(offset) < btf->hdr->str_len; +} + +static const char *btf_name_by_offset(const struct btf *btf, u32 offset) +{ + if (!BTF_STR_OFFSET(offset)) + return "(anon)"; + else if (BTF_STR_OFFSET(offset) < btf->hdr->str_len) + return &btf->strings[BTF_STR_OFFSET(offset)]; + else + return "(invalid-name-offset)"; +} + +static const struct btf_type *btf_type_by_id(const struct btf *btf, u32 type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +__printf(2, 3) static void __btf_verifier_log(struct bpf_verifier_log *log, + const char *fmt, ...) +{ + va_list args; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + +__printf(2, 3) static void btf_verifier_log(struct btf_verifier_env *env, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); +} + +__printf(4, 5) static void __btf_verifier_log_type(struct btf_verifier_env *env, + const struct btf_type *t, + bool log_details, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + u8 kind = BTF_INFO_KIND(t->info); + struct btf *btf = env->btf; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + __btf_verifier_log(log, "[%u] %s %s%s", + env->log_type_id, + btf_kind_str[kind], + btf_name_by_offset(btf, t->name_off), + log_details ? " " : ""); + + if (log_details) + btf_type_ops(t)->log_details(env, t); + + if (fmt && *fmt) { + __btf_verifier_log(log, " "); + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); + } + + __btf_verifier_log(log, "\n"); +} + +#define btf_verifier_log_type(env, t, ...) \ + __btf_verifier_log_type((env), (t), true, __VA_ARGS__) +#define btf_verifier_log_basic(env, t, ...) \ + __btf_verifier_log_type((env), (t), false, __VA_ARGS__) + +__printf(4, 5) +static void btf_verifier_log_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const char *fmt, ...) +{ + struct bpf_verifier_log *log = &env->log; + struct btf *btf = env->btf; + va_list args; + + if (!bpf_verifier_log_needed(log)) + return; + + /* The CHECK_META phase already did a btf dump. + * + * If member is logged again, it must hit an error in + * parsing this member. It is useful to print out which + * struct this member belongs to. + */ + if (env->phase != CHECK_META) + btf_verifier_log_type(env, struct_type, NULL); + + __btf_verifier_log(log, "\t%s type_id=%u bits_offset=%u", + btf_name_by_offset(btf, member->name_off), + member->type, member->offset); + + if (fmt && *fmt) { + __btf_verifier_log(log, " "); + va_start(args, fmt); + bpf_verifier_vlog(log, fmt, args); + va_end(args); + } + + __btf_verifier_log(log, "\n"); +} + +static void btf_verifier_log_hdr(struct btf_verifier_env *env) +{ + struct bpf_verifier_log *log = &env->log; + const struct btf *btf = env->btf; + const struct btf_header *hdr; + + if (!bpf_verifier_log_needed(log)) + return; + + hdr = btf->hdr; + __btf_verifier_log(log, "magic: 0x%x\n", hdr->magic); + __btf_verifier_log(log, "version: %u\n", hdr->version); + __btf_verifier_log(log, "flags: 0x%x\n", hdr->flags); + __btf_verifier_log(log, "parent_label: %u\n", hdr->parent_label); + __btf_verifier_log(log, "parent_name: %u\n", hdr->parent_name); + __btf_verifier_log(log, "label_off: %u\n", hdr->label_off); + __btf_verifier_log(log, "object_off: %u\n", hdr->object_off); + __btf_verifier_log(log, "func_off: %u\n", hdr->func_off); + __btf_verifier_log(log, "type_off: %u\n", hdr->type_off); + __btf_verifier_log(log, "str_off: %u\n", hdr->str_off); + __btf_verifier_log(log, "str_len: %u\n", hdr->str_len); + __btf_verifier_log(log, "btf_total_size: %u\n", btf->data_size); +} + +static int btf_add_type(struct btf_verifier_env *env, struct btf_type *t) +{ + struct btf *btf = env->btf; + + /* < 2 because +1 for btf_void which is always in btf->types[0]. + * btf_void is not accounted in btf->nr_types because btf_void + * does not come from the BTF file. + */ + if (btf->types_size - btf->nr_types < 2) { + /* Expand 'types' array */ + + struct btf_type **new_types; + u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_NR_TYPES) { + btf_verifier_log(env, "Exceeded max num of types"); + return -E2BIG; + } + + expand_by = max_t(u32, btf->types_size >> 2, 16); + new_size = min_t(u32, BTF_MAX_NR_TYPES, + btf->types_size + expand_by); + + new_types = kvzalloc(new_size * sizeof(*new_types), + GFP_KERNEL | __GFP_NOWARN); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + else + memcpy(new_types, btf->types, + sizeof(*btf->types) * (btf->nr_types + 1)); + + kvfree(btf->types); + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static void btf_free(struct btf *btf) +{ + kvfree(btf->types); + kvfree(btf->resolved_sizes); + kvfree(btf->resolved_ids); + kvfree(btf->data); + kfree(btf); +} + +static void btf_get(struct btf *btf) +{ + refcount_inc(&btf->refcnt); +} + +void btf_put(struct btf *btf) +{ + if (btf && refcount_dec_and_test(&btf->refcnt)) + btf_free(btf); +} + +static int env_resolve_init(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + u32 nr_types = btf->nr_types; + u32 *resolved_sizes = NULL; + u32 *resolved_ids = NULL; + u8 *visit_states = NULL; + + /* +1 for btf_void */ + resolved_sizes = kvzalloc((nr_types + 1) * sizeof(*resolved_sizes), + GFP_KERNEL | __GFP_NOWARN); + if (!resolved_sizes) + goto nomem; + + resolved_ids = kvzalloc((nr_types + 1) * sizeof(*resolved_ids), + GFP_KERNEL | __GFP_NOWARN); + if (!resolved_ids) + goto nomem; + + visit_states = kvzalloc((nr_types + 1) * sizeof(*visit_states), + GFP_KERNEL | __GFP_NOWARN); + if (!visit_states) + goto nomem; + + btf->resolved_sizes = resolved_sizes; + btf->resolved_ids = resolved_ids; + env->visit_states = visit_states; + + return 0; + +nomem: + kvfree(resolved_sizes); + kvfree(resolved_ids); + kvfree(visit_states); + return -ENOMEM; +} + +static void btf_verifier_env_free(struct btf_verifier_env *env) +{ + kvfree(env->visit_states); + kfree(env); +} + +static bool env_type_is_resolve_sink(const struct btf_verifier_env *env, + const struct btf_type *next_type) +{ + switch (env->resolve_mode) { + case RESOLVE_TBD: + /* int, enum or void is a sink */ + return !btf_type_needs_resolve(next_type); + case RESOLVE_PTR: + /* int, enum, void, struct or array is a sink for ptr */ + return !btf_type_is_modifier(next_type) && + !btf_type_is_ptr(next_type); + case RESOLVE_STRUCT_OR_ARRAY: + /* int, enum, void or ptr is a sink for struct and array */ + return !btf_type_is_modifier(next_type) && + !btf_type_is_array(next_type) && + !btf_type_is_struct(next_type); + default: + BUG_ON(1); + } +} + +static bool env_type_is_resolved(const struct btf_verifier_env *env, + u32 type_id) +{ + return env->visit_states[type_id] == RESOLVED; +} + +static int env_stack_push(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + struct resolve_vertex *v; + + if (env->top_stack == MAX_RESOLVE_DEPTH) + return -E2BIG; + + if (env->visit_states[type_id] != NOT_VISITED) + return -EEXIST; + + env->visit_states[type_id] = VISITED; + + v = &env->stack[env->top_stack++]; + v->t = t; + v->type_id = type_id; + v->next_member = 0; + + if (env->resolve_mode == RESOLVE_TBD) { + if (btf_type_is_ptr(t)) + env->resolve_mode = RESOLVE_PTR; + else if (btf_type_is_struct(t) || btf_type_is_array(t)) + env->resolve_mode = RESOLVE_STRUCT_OR_ARRAY; + } + + return 0; +} + +static void env_stack_set_next_member(struct btf_verifier_env *env, + u16 next_member) +{ + env->stack[env->top_stack - 1].next_member = next_member; +} + +static void env_stack_pop_resolved(struct btf_verifier_env *env, + u32 resolved_type_id, + u32 resolved_size) +{ + u32 type_id = env->stack[--(env->top_stack)].type_id; + struct btf *btf = env->btf; + + btf->resolved_sizes[type_id] = resolved_size; + btf->resolved_ids[type_id] = resolved_type_id; + env->visit_states[type_id] = RESOLVED; +} + +static const struct resolve_vertex *env_stack_peak(struct btf_verifier_env *env) +{ + return env->top_stack ? &env->stack[env->top_stack - 1] : NULL; +} + +/* The input param "type_id" must point to a needs_resolve type */ +static const struct btf_type *btf_type_id_resolve(const struct btf *btf, + u32 *type_id) +{ + *type_id = btf->resolved_ids[*type_id]; + return btf_type_by_id(btf, *type_id); +} + +const struct btf_type *btf_type_id_size(const struct btf *btf, + u32 *type_id, u32 *ret_size) +{ + const struct btf_type *size_type; + u32 size_type_id = *type_id; + u32 size = 0; + + size_type = btf_type_by_id(btf, size_type_id); + if (btf_type_is_void_or_null(size_type)) + return NULL; + + if (btf_type_has_size(size_type)) { + size = size_type->size; + } else if (btf_type_is_array(size_type)) { + size = btf->resolved_sizes[size_type_id]; + } else if (btf_type_is_ptr(size_type)) { + size = sizeof(void *); + } else { + if (WARN_ON_ONCE(!btf_type_is_modifier(size_type))) + return NULL; + + size = btf->resolved_sizes[size_type_id]; + size_type_id = btf->resolved_ids[size_type_id]; + size_type = btf_type_by_id(btf, size_type_id); + if (btf_type_is_void(size_type)) + return NULL; + } + + *type_id = size_type_id; + if (ret_size) + *ret_size = size; + + return size_type; +} + +static int btf_df_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + btf_verifier_log_basic(env, struct_type, + "Unsupported check_member"); + return -EINVAL; +} + +static int btf_df_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + btf_verifier_log_basic(env, v->t, "Unsupported resolve"); + return -EINVAL; +} + +static void btf_df_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offsets, + struct seq_file *m) +{ + seq_printf(m, "<unsupported kind:%u>", BTF_INFO_KIND(t->info)); +} + +static int btf_int_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 int_data = btf_type_int(member_type); + u32 struct_bits_off = member->offset; + u32 struct_size = struct_type->size; + u32 nr_copy_bits; + u32 bytes_offset; + + if (U32_MAX - struct_bits_off < BTF_INT_OFFSET(int_data)) { + btf_verifier_log_member(env, struct_type, member, + "bits_offset exceeds U32_MAX"); + return -EINVAL; + } + + struct_bits_off += BTF_INT_OFFSET(int_data); + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + nr_copy_bits = BTF_INT_BITS(int_data) + + BITS_PER_BYTE_MASKED(struct_bits_off); + + if (nr_copy_bits > BITS_PER_U64) { + btf_verifier_log_member(env, struct_type, member, + "nr_copy_bits exceeds 64"); + return -EINVAL; + } + + if (struct_size < bytes_offset || + struct_size - bytes_offset < BITS_ROUNDUP_BYTES(nr_copy_bits)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_int_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 int_data, nr_bits, meta_needed = sizeof(int_data); + u16 encoding; + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + int_data = btf_type_int(t); + nr_bits = BTF_INT_BITS(int_data) + BTF_INT_OFFSET(int_data); + + if (nr_bits > BITS_PER_U64) { + btf_verifier_log_type(env, t, "nr_bits exceeds %zu", + BITS_PER_U64); + return -EINVAL; + } + + if (BITS_ROUNDUP_BYTES(nr_bits) > t->size) { + btf_verifier_log_type(env, t, "nr_bits exceeds type_size"); + return -EINVAL; + } + + encoding = BTF_INT_ENCODING(int_data); + if (encoding && + encoding != BTF_INT_SIGNED && + encoding != BTF_INT_CHAR && + encoding != BTF_INT_BOOL && + encoding != BTF_INT_VARARGS) { + btf_verifier_log_type(env, t, "Unsupported encoding"); + return -ENOTSUPP; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static void btf_int_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + int int_data = btf_type_int(t); + + btf_verifier_log(env, + "size=%u bits_offset=%u nr_bits=%u encoding=%s", + t->size, BTF_INT_OFFSET(int_data), + BTF_INT_BITS(int_data), + btf_int_encoding_str(BTF_INT_ENCODING(int_data))); +} + +static void btf_int_bits_seq_show(const struct btf *btf, + const struct btf_type *t, + void *data, u8 bits_offset, + struct seq_file *m) +{ + u32 int_data = btf_type_int(t); + u16 nr_bits = BTF_INT_BITS(int_data); + u16 total_bits_offset; + u16 nr_copy_bytes; + u16 nr_copy_bits; + u8 nr_upper_bits; + union { + u64 u64_num; + u8 u8_nums[8]; + } print_num; + + total_bits_offset = bits_offset + BTF_INT_OFFSET(int_data); + data += BITS_ROUNDDOWN_BYTES(total_bits_offset); + bits_offset = BITS_PER_BYTE_MASKED(total_bits_offset); + nr_copy_bits = nr_bits + bits_offset; + nr_copy_bytes = BITS_ROUNDUP_BYTES(nr_copy_bits); + + print_num.u64_num = 0; + memcpy(&print_num.u64_num, data, nr_copy_bytes); + + /* Ditch the higher order bits */ + nr_upper_bits = BITS_PER_BYTE_MASKED(nr_copy_bits); + if (nr_upper_bits) { + /* We need to mask out some bits of the upper byte. */ + u8 mask = (1 << nr_upper_bits) - 1; + + print_num.u8_nums[nr_copy_bytes - 1] &= mask; + } + + print_num.u64_num >>= bits_offset; + + seq_printf(m, "0x%llx", print_num.u64_num); +} + +static void btf_int_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + u32 int_data = btf_type_int(t); + u8 encoding = BTF_INT_ENCODING(int_data); + bool sign = encoding & BTF_INT_SIGNED; + u32 nr_bits = BTF_INT_BITS(int_data); + + if (bits_offset || BTF_INT_OFFSET(int_data) || + BITS_PER_BYTE_MASKED(nr_bits)) { + btf_int_bits_seq_show(btf, t, data, bits_offset, m); + return; + } + + switch (nr_bits) { + case 64: + if (sign) + seq_printf(m, "%lld", *(s64 *)data); + else + seq_printf(m, "%llu", *(u64 *)data); + break; + case 32: + if (sign) + seq_printf(m, "%d", *(s32 *)data); + else + seq_printf(m, "%u", *(u32 *)data); + break; + case 16: + if (sign) + seq_printf(m, "%d", *(s16 *)data); + else + seq_printf(m, "%u", *(u16 *)data); + break; + case 8: + if (sign) + seq_printf(m, "%d", *(s8 *)data); + else + seq_printf(m, "%u", *(u8 *)data); + break; + default: + btf_int_bits_seq_show(btf, t, data, bits_offset, m); + } +} + +static const struct btf_kind_operations int_ops = { + .check_meta = btf_int_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_int_check_member, + .log_details = btf_int_log, + .seq_show = btf_int_seq_show, +}; + +static int btf_modifier_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + const struct btf_type *resolved_type; + u32 resolved_type_id = member->type; + struct btf_member resolved_member; + struct btf *btf = env->btf; + + resolved_type = btf_type_id_size(btf, &resolved_type_id, NULL); + if (!resolved_type) { + btf_verifier_log_member(env, struct_type, member, + "Invalid member"); + return -EINVAL; + } + + resolved_member = *member; + resolved_member.type = resolved_type_id; + + return btf_type_ops(resolved_type)->check_member(env, struct_type, + &resolved_member, + resolved_type); +} + +static int btf_ptr_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_size, struct_bits_off, bytes_offset; + + struct_size = struct_type->size; + struct_bits_off = member->offset; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + if (struct_size - bytes_offset < sizeof(void *)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static int btf_ref_type_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + if (BTF_TYPE_PARENT(t->type)) { + btf_verifier_log_type(env, t, "Invalid type_id"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return 0; +} + +static int btf_modifier_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *t = v->t; + const struct btf_type *next_type; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + u32 next_type_size = 0; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + /* "typedef void new_void", "const void"...etc */ + if (btf_type_is_void(next_type)) + goto resolved; + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + /* Figure out the resolved next_type_id with size. + * They will be stored in the current modifier's + * resolved_ids and resolved_sizes such that it can + * save us a few type-following when we use it later (e.g. in + * pretty print). + */ + if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && + !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + +resolved: + env_stack_pop_resolved(env, next_type_id, next_type_size); + + return 0; +} + +static int btf_ptr_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_type *next_type; + const struct btf_type *t = v->t; + u32 next_type_id = t->type; + struct btf *btf = env->btf; + u32 next_type_size = 0; + + next_type = btf_type_by_id(btf, next_type_id); + if (!next_type) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + + /* "void *" */ + if (btf_type_is_void(next_type)) + goto resolved; + + if (!env_type_is_resolve_sink(env, next_type) && + !env_type_is_resolved(env, next_type_id)) + return env_stack_push(env, next_type, next_type_id); + + /* If the modifier was RESOLVED during RESOLVE_STRUCT_OR_ARRAY, + * the modifier may have stopped resolving when it was resolved + * to a ptr (last-resolved-ptr). + * + * We now need to continue from the last-resolved-ptr to + * ensure the last-resolved-ptr will not referring back to + * the currenct ptr (t). + */ + if (btf_type_is_modifier(next_type)) { + const struct btf_type *resolved_type; + u32 resolved_type_id; + + resolved_type_id = next_type_id; + resolved_type = btf_type_id_resolve(btf, &resolved_type_id); + + if (btf_type_is_ptr(resolved_type) && + !env_type_is_resolve_sink(env, resolved_type) && + !env_type_is_resolved(env, resolved_type_id)) + return env_stack_push(env, resolved_type, + resolved_type_id); + } + + if (!btf_type_id_size(btf, &next_type_id, &next_type_size) && + !btf_type_is_void(btf_type_id_resolve(btf, &next_type_id))) { + btf_verifier_log_type(env, v->t, "Invalid type_id"); + return -EINVAL; + } + +resolved: + env_stack_pop_resolved(env, next_type_id, 0); + + return 0; +} + +static void btf_modifier_seq_show(const struct btf *btf, + const struct btf_type *t, + u32 type_id, void *data, + u8 bits_offset, struct seq_file *m) +{ + t = btf_type_id_resolve(btf, &type_id); + + btf_type_ops(t)->seq_show(btf, t, type_id, data, bits_offset, m); +} + +static void btf_ptr_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + /* It is a hashed value */ + seq_printf(m, "%p", *(void **)data); +} + +static void btf_ref_type_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "type_id=%u", t->type); +} + +static struct btf_kind_operations modifier_ops = { + .check_meta = btf_ref_type_check_meta, + .resolve = btf_modifier_resolve, + .check_member = btf_modifier_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_modifier_seq_show, +}; + +static struct btf_kind_operations ptr_ops = { + .check_meta = btf_ref_type_check_meta, + .resolve = btf_ptr_resolve, + .check_member = btf_ptr_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_ptr_seq_show, +}; + +static struct btf_kind_operations fwd_ops = { + .check_meta = btf_ref_type_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_df_check_member, + .log_details = btf_ref_type_log, + .seq_show = btf_df_seq_show, +}; + +static int btf_array_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + u32 array_type_id, array_size; + struct btf *btf = env->btf; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + array_type_id = member->type; + btf_type_id_size(btf, &array_type_id, &array_size); + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < array_size) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_array_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_array *array = btf_type_array(t); + u32 meta_needed = sizeof(*array); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (btf_type_vlen(t)) { + btf_verifier_log_type(env, t, "vlen != 0"); + return -EINVAL; + } + + /* We are a little forgiving on array->index_type since + * the kernel is not using it. + */ + /* Array elem cannot be in type void, + * so !array->type is not allowed. + */ + if (!array->type || BTF_TYPE_PARENT(array->type)) { + btf_verifier_log_type(env, t, "Invalid type_id"); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + return meta_needed; +} + +static int btf_array_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_array *array = btf_type_array(v->t); + const struct btf_type *elem_type; + u32 elem_type_id = array->type; + struct btf *btf = env->btf; + u32 elem_size; + + elem_type = btf_type_by_id(btf, elem_type_id); + if (btf_type_is_void_or_null(elem_type)) { + btf_verifier_log_type(env, v->t, + "Invalid elem"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, elem_type) && + !env_type_is_resolved(env, elem_type_id)) + return env_stack_push(env, elem_type, elem_type_id); + + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + if (!elem_type) { + btf_verifier_log_type(env, v->t, "Invalid elem"); + return -EINVAL; + } + + if (btf_type_is_int(elem_type)) { + int int_type_data = btf_type_int(elem_type); + u16 nr_bits = BTF_INT_BITS(int_type_data); + u16 nr_bytes = BITS_ROUNDUP_BYTES(nr_bits); + + /* Put more restriction on array of int. The int cannot + * be a bit field and it must be either u8/u16/u32/u64. + */ + if (BITS_PER_BYTE_MASKED(nr_bits) || + BTF_INT_OFFSET(int_type_data) || + (nr_bytes != sizeof(u8) && nr_bytes != sizeof(u16) && + nr_bytes != sizeof(u32) && nr_bytes != sizeof(u64))) { + btf_verifier_log_type(env, v->t, + "Invalid array of int"); + return -EINVAL; + } + } + + if (array->nelems && elem_size > U32_MAX / array->nelems) { + btf_verifier_log_type(env, v->t, + "Array size overflows U32_MAX"); + return -EINVAL; + } + + env_stack_pop_resolved(env, elem_type_id, elem_size * array->nelems); + + return 0; +} + +static void btf_array_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + const struct btf_array *array = btf_type_array(t); + + btf_verifier_log(env, "type_id=%u index_type_id=%u nr_elems=%u", + array->type, array->index_type, array->nelems); +} + +static void btf_array_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const struct btf_array *array = btf_type_array(t); + const struct btf_kind_operations *elem_ops; + const struct btf_type *elem_type; + u32 i, elem_size, elem_type_id; + + elem_type_id = array->type; + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + elem_ops = btf_type_ops(elem_type); + seq_puts(m, "["); + for (i = 0; i < array->nelems; i++) { + if (i) + seq_puts(m, ","); + + elem_ops->seq_show(btf, elem_type, elem_type_id, data, + bits_offset, m); + data += elem_size; + } + seq_puts(m, "]"); +} + +static struct btf_kind_operations array_ops = { + .check_meta = btf_array_check_meta, + .resolve = btf_array_resolve, + .check_member = btf_array_check_member, + .log_details = btf_array_log, + .seq_show = btf_array_seq_show, +}; + +static int btf_struct_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < member_type->size) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_struct_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + bool is_union = BTF_INFO_KIND(t->info) == BTF_KIND_UNION; + const struct btf_member *member; + struct btf *btf = env->btf; + u32 struct_size = t->size; + u32 meta_needed; + u16 i; + + meta_needed = btf_type_vlen(t) * sizeof(*member); + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for_each_member(i, t, member) { + if (!btf_name_offset_valid(btf, member->name_off)) { + btf_verifier_log_member(env, t, member, + "Invalid member name_offset:%u", + member->name_off); + return -EINVAL; + } + + /* A member cannot be in type void */ + if (!member->type || BTF_TYPE_PARENT(member->type)) { + btf_verifier_log_member(env, t, member, + "Invalid type_id"); + return -EINVAL; + } + + if (is_union && member->offset) { + btf_verifier_log_member(env, t, member, + "Invalid member bits_offset"); + return -EINVAL; + } + + if (BITS_ROUNDUP_BYTES(member->offset) > struct_size) { + btf_verifier_log_member(env, t, member, + "Memmber bits_offset exceeds its struct size"); + return -EINVAL; + } + + btf_verifier_log_member(env, t, member, NULL); + } + + return meta_needed; +} + +static int btf_struct_resolve(struct btf_verifier_env *env, + const struct resolve_vertex *v) +{ + const struct btf_member *member; + int err; + u16 i; + + /* Before continue resolving the next_member, + * ensure the last member is indeed resolved to a + * type with size info. + */ + if (v->next_member) { + const struct btf_type *last_member_type; + const struct btf_member *last_member; + u16 last_member_type_id; + + last_member = btf_type_member(v->t) + v->next_member - 1; + last_member_type_id = last_member->type; + if (WARN_ON_ONCE(!env_type_is_resolved(env, + last_member_type_id))) + return -EINVAL; + + last_member_type = btf_type_by_id(env->btf, + last_member_type_id); + err = btf_type_ops(last_member_type)->check_member(env, v->t, + last_member, + last_member_type); + if (err) + return err; + } + + for_each_member_from(i, v->next_member, v->t, member) { + u32 member_type_id = member->type; + const struct btf_type *member_type = btf_type_by_id(env->btf, + member_type_id); + + if (btf_type_is_void_or_null(member_type)) { + btf_verifier_log_member(env, v->t, member, + "Invalid member"); + return -EINVAL; + } + + if (!env_type_is_resolve_sink(env, member_type) && + !env_type_is_resolved(env, member_type_id)) { + env_stack_set_next_member(env, i + 1); + return env_stack_push(env, member_type, member_type_id); + } + + err = btf_type_ops(member_type)->check_member(env, v->t, + member, + member_type); + if (err) + return err; + } + + env_stack_pop_resolved(env, 0, 0); + + return 0; +} + +static void btf_struct_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); +} + +static void btf_struct_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const char *seq = BTF_INFO_KIND(t->info) == BTF_KIND_UNION ? "|" : ","; + const struct btf_member *member; + u32 i; + + seq_puts(m, "{"); + for_each_member(i, t, member) { + const struct btf_type *member_type = btf_type_by_id(btf, + member->type); + u32 member_offset = member->offset; + u32 bytes_offset = BITS_ROUNDDOWN_BYTES(member_offset); + u8 bits8_offset = BITS_PER_BYTE_MASKED(member_offset); + const struct btf_kind_operations *ops; + + if (i) + seq_puts(m, seq); + + ops = btf_type_ops(member_type); + ops->seq_show(btf, member_type, member->type, + data + bytes_offset, bits8_offset, m); + } + seq_puts(m, "}"); +} + +static struct btf_kind_operations struct_ops = { + .check_meta = btf_struct_check_meta, + .resolve = btf_struct_resolve, + .check_member = btf_struct_check_member, + .log_details = btf_struct_log, + .seq_show = btf_struct_seq_show, +}; + +static int btf_enum_check_member(struct btf_verifier_env *env, + const struct btf_type *struct_type, + const struct btf_member *member, + const struct btf_type *member_type) +{ + u32 struct_bits_off = member->offset; + u32 struct_size, bytes_offset; + + if (BITS_PER_BYTE_MASKED(struct_bits_off)) { + btf_verifier_log_member(env, struct_type, member, + "Member is not byte aligned"); + return -EINVAL; + } + + struct_size = struct_type->size; + bytes_offset = BITS_ROUNDDOWN_BYTES(struct_bits_off); + if (struct_size - bytes_offset < sizeof(int)) { + btf_verifier_log_member(env, struct_type, member, + "Member exceeds struct_size"); + return -EINVAL; + } + + return 0; +} + +static s32 btf_enum_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + const struct btf_enum *enums = btf_type_enum(t); + struct btf *btf = env->btf; + u16 i, nr_enums; + u32 meta_needed; + + nr_enums = btf_type_vlen(t); + meta_needed = nr_enums * sizeof(*enums); + + if (meta_left < meta_needed) { + btf_verifier_log_basic(env, t, + "meta_left:%u meta_needed:%u", + meta_left, meta_needed); + return -EINVAL; + } + + if (t->size != sizeof(int)) { + btf_verifier_log_type(env, t, "Expected size:%zu", + sizeof(int)); + return -EINVAL; + } + + btf_verifier_log_type(env, t, NULL); + + for (i = 0; i < nr_enums; i++) { + if (!btf_name_offset_valid(btf, enums[i].name_off)) { + btf_verifier_log(env, "\tInvalid name_offset:%u", + enums[i].name_off); + return -EINVAL; + } + + btf_verifier_log(env, "\t%s val=%d\n", + btf_name_by_offset(btf, enums[i].name_off), + enums[i].val); + } + + return meta_needed; +} + +static void btf_enum_log(struct btf_verifier_env *env, + const struct btf_type *t) +{ + btf_verifier_log(env, "size=%u vlen=%u", t->size, btf_type_vlen(t)); +} + +static void btf_enum_seq_show(const struct btf *btf, const struct btf_type *t, + u32 type_id, void *data, u8 bits_offset, + struct seq_file *m) +{ + const struct btf_enum *enums = btf_type_enum(t); + u32 i, nr_enums = btf_type_vlen(t); + int v = *(int *)data; + + for (i = 0; i < nr_enums; i++) { + if (v == enums[i].val) { + seq_printf(m, "%s", + btf_name_by_offset(btf, enums[i].name_off)); + return; + } + } + + seq_printf(m, "%d", v); +} + +static struct btf_kind_operations enum_ops = { + .check_meta = btf_enum_check_meta, + .resolve = btf_df_resolve, + .check_member = btf_enum_check_member, + .log_details = btf_enum_log, + .seq_show = btf_enum_seq_show, +}; + +static const struct btf_kind_operations * const kind_ops[NR_BTF_KINDS] = { + [BTF_KIND_INT] = &int_ops, + [BTF_KIND_PTR] = &ptr_ops, + [BTF_KIND_ARRAY] = &array_ops, + [BTF_KIND_STRUCT] = &struct_ops, + [BTF_KIND_UNION] = &struct_ops, + [BTF_KIND_ENUM] = &enum_ops, + [BTF_KIND_FWD] = &fwd_ops, + [BTF_KIND_TYPEDEF] = &modifier_ops, + [BTF_KIND_VOLATILE] = &modifier_ops, + [BTF_KIND_CONST] = &modifier_ops, + [BTF_KIND_RESTRICT] = &modifier_ops, +}; + +static s32 btf_check_meta(struct btf_verifier_env *env, + const struct btf_type *t, + u32 meta_left) +{ + u32 saved_meta_left = meta_left; + s32 var_meta_size; + + if (meta_left < sizeof(*t)) { + btf_verifier_log(env, "[%u] meta_left:%u meta_needed:%zu", + env->log_type_id, meta_left, sizeof(*t)); + return -EINVAL; + } + meta_left -= sizeof(*t); + + if (BTF_INFO_KIND(t->info) > BTF_KIND_MAX || + BTF_INFO_KIND(t->info) == BTF_KIND_UNKN) { + btf_verifier_log(env, "[%u] Invalid kind:%u", + env->log_type_id, BTF_INFO_KIND(t->info)); + return -EINVAL; + } + + if (!btf_name_offset_valid(env->btf, t->name_off)) { + btf_verifier_log(env, "[%u] Invalid name_offset:%u", + env->log_type_id, t->name_off); + return -EINVAL; + } + + var_meta_size = btf_type_ops(t)->check_meta(env, t, meta_left); + if (var_meta_size < 0) + return var_meta_size; + + meta_left -= var_meta_size; + + return saved_meta_left - meta_left; +} + +static int btf_check_all_metas(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + struct btf_header *hdr; + void *cur, *end; + + hdr = btf->hdr; + cur = btf->nohdr_data + hdr->type_off; + end = btf->nohdr_data + hdr->str_off; + + env->log_type_id = 1; + while (cur < end) { + struct btf_type *t = cur; + s32 meta_size; + + meta_size = btf_check_meta(env, t, end - cur); + if (meta_size < 0) + return meta_size; + + btf_add_type(env, t); + cur += meta_size; + env->log_type_id++; + } + + return 0; +} + +static int btf_resolve(struct btf_verifier_env *env, + const struct btf_type *t, u32 type_id) +{ + const struct resolve_vertex *v; + int err = 0; + + env->resolve_mode = RESOLVE_TBD; + env_stack_push(env, t, type_id); + while (!err && (v = env_stack_peak(env))) { + env->log_type_id = v->type_id; + err = btf_type_ops(v->t)->resolve(env, v); + } + + env->log_type_id = type_id; + if (err == -E2BIG) + btf_verifier_log_type(env, t, + "Exceeded max resolving depth:%u", + MAX_RESOLVE_DEPTH); + else if (err == -EEXIST) + btf_verifier_log_type(env, t, "Loop detected"); + + return err; +} + +static bool btf_resolve_valid(struct btf_verifier_env *env, + const struct btf_type *t, + u32 type_id) +{ + struct btf *btf = env->btf; + + if (!env_type_is_resolved(env, type_id)) + return false; + + if (btf_type_is_struct(t)) + return !btf->resolved_ids[type_id] && + !btf->resolved_sizes[type_id]; + + if (btf_type_is_modifier(t) || btf_type_is_ptr(t)) { + t = btf_type_id_resolve(btf, &type_id); + return t && !btf_type_is_modifier(t); + } + + if (btf_type_is_array(t)) { + const struct btf_array *array = btf_type_array(t); + const struct btf_type *elem_type; + u32 elem_type_id = array->type; + u32 elem_size; + + elem_type = btf_type_id_size(btf, &elem_type_id, &elem_size); + return elem_type && !btf_type_is_modifier(elem_type) && + (array->nelems * elem_size == + btf->resolved_sizes[type_id]); + } + + return false; +} + +static int btf_check_all_types(struct btf_verifier_env *env) +{ + struct btf *btf = env->btf; + u32 type_id; + int err; + + err = env_resolve_init(env); + if (err) + return err; + + env->phase++; + for (type_id = 1; type_id <= btf->nr_types; type_id++) { + const struct btf_type *t = btf_type_by_id(btf, type_id); + + env->log_type_id = type_id; + if (btf_type_needs_resolve(t) && + !env_type_is_resolved(env, type_id)) { + err = btf_resolve(env, t, type_id); + if (err) + return err; + } + + if (btf_type_needs_resolve(t) && + !btf_resolve_valid(env, t, type_id)) { + btf_verifier_log_type(env, t, "Invalid resolve state"); + return -EINVAL; + } + } + + return 0; +} + +static int btf_parse_type_sec(struct btf_verifier_env *env) +{ + int err; + + err = btf_check_all_metas(env); + if (err) + return err; + + return btf_check_all_types(env); +} + +static int btf_parse_str_sec(struct btf_verifier_env *env) +{ + const struct btf_header *hdr; + struct btf *btf = env->btf; + const char *start, *end; + + hdr = btf->hdr; + start = btf->nohdr_data + hdr->str_off; + end = start + hdr->str_len; + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + start[0] || end[-1]) { + btf_verifier_log(env, "Invalid string section"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static int btf_parse_hdr(struct btf_verifier_env *env) +{ + const struct btf_header *hdr; + struct btf *btf = env->btf; + u32 meta_left; + + if (btf->data_size < sizeof(*hdr)) { + btf_verifier_log(env, "btf_header not found"); + return -EINVAL; + } + + btf_verifier_log_hdr(env); + + hdr = btf->hdr; + if (hdr->magic != BTF_MAGIC) { + btf_verifier_log(env, "Invalid magic"); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + btf_verifier_log(env, "Unsupported version"); + return -ENOTSUPP; + } + + if (hdr->flags) { + btf_verifier_log(env, "Unsupported flags"); + return -ENOTSUPP; + } + + meta_left = btf->data_size - sizeof(*hdr); + if (!meta_left) { + btf_verifier_log(env, "No data"); + return -EINVAL; + } + + if (meta_left < hdr->type_off || hdr->str_off <= hdr->type_off || + /* Type section must align to 4 bytes */ + hdr->type_off & (sizeof(u32) - 1)) { + btf_verifier_log(env, "Invalid type_off"); + return -EINVAL; + } + + if (meta_left < hdr->str_off || + meta_left - hdr->str_off < hdr->str_len) { + btf_verifier_log(env, "Invalid str_off or str_len"); + return -EINVAL; + } + + btf->nohdr_data = btf->hdr + 1; + + return 0; +} + +static struct btf *btf_parse(void __user *btf_data, u32 btf_data_size, + u32 log_level, char __user *log_ubuf, u32 log_size) +{ + struct btf_verifier_env *env = NULL; + struct bpf_verifier_log *log; + struct btf *btf = NULL; + u8 *data; + int err; + + if (btf_data_size > BTF_MAX_SIZE) + return ERR_PTR(-E2BIG); + + env = kzalloc(sizeof(*env), GFP_KERNEL | __GFP_NOWARN); + if (!env) + return ERR_PTR(-ENOMEM); + + log = &env->log; + if (log_level || log_ubuf || log_size) { + /* user requested verbose verifier output + * and supplied buffer to store the verification trace + */ + log->level = log_level; + log->ubuf = log_ubuf; + log->len_total = log_size; + + /* log attributes have to be sane */ + if (log->len_total < 128 || log->len_total > UINT_MAX >> 8 || + !log->level || !log->ubuf) { + err = -EINVAL; + goto errout; + } + } + + btf = kzalloc(sizeof(*btf), GFP_KERNEL | __GFP_NOWARN); + if (!btf) { + err = -ENOMEM; + goto errout; + } + + data = kvmalloc(btf_data_size, GFP_KERNEL | __GFP_NOWARN); + if (!data) { + err = -ENOMEM; + goto errout; + } + + btf->data = data; + btf->data_size = btf_data_size; + + if (copy_from_user(data, btf_data, btf_data_size)) { + err = -EFAULT; + goto errout; + } + + env->btf = btf; + + err = btf_parse_hdr(env); + if (err) + goto errout; + + err = btf_parse_str_sec(env); + if (err) + goto errout; + + err = btf_parse_type_sec(env); + if (err) + goto errout; + + if (!err && log->level && bpf_verifier_log_full(log)) { + err = -ENOSPC; + goto errout; + } + + if (!err) { + btf_verifier_env_free(env); + btf_get(btf); + return btf; + } + +errout: + btf_verifier_env_free(env); + if (btf) + btf_free(btf); + return ERR_PTR(err); +} + +void btf_type_seq_show(const struct btf *btf, u32 type_id, void *obj, + struct seq_file *m) +{ + const struct btf_type *t = btf_type_by_id(btf, type_id); + + btf_type_ops(t)->seq_show(btf, t, type_id, obj, 0, m); +} + +static int btf_release(struct inode *inode, struct file *filp) +{ + btf_put(filp->private_data); + return 0; +} + +const struct file_operations btf_fops = { + .release = btf_release, +}; + +int btf_new_fd(const union bpf_attr *attr) +{ + struct btf *btf; + int fd; + + btf = btf_parse(u64_to_user_ptr(attr->btf), + attr->btf_size, attr->btf_log_level, + u64_to_user_ptr(attr->btf_log_buf), + attr->btf_log_size); + if (IS_ERR(btf)) + return PTR_ERR(btf); + + fd = anon_inode_getfd("btf", &btf_fops, btf, + O_RDONLY | O_CLOEXEC); + if (fd < 0) + btf_put(btf); + + return fd; +} + +struct btf *btf_get_by_fd(int fd) +{ + struct btf *btf; + struct fd f; + + f = fdget(fd); + + if (!f.file) + return ERR_PTR(-EBADF); + + if (f.file->f_op != &btf_fops) { + fdput(f); + return ERR_PTR(-EINVAL); + } + + btf = f.file->private_data; + btf_get(btf); + fdput(f); + + return btf; +} + +int btf_get_info_by_fd(const struct btf *btf, + const union bpf_attr *attr, + union bpf_attr __user *uattr) +{ + void __user *udata = u64_to_user_ptr(attr->info.info); + u32 copy_len = min_t(u32, btf->data_size, + attr->info.info_len); + + if (copy_to_user(udata, btf->data, copy_len) || + put_user(btf->data_size, &uattr->info.info_len)) + return -EFAULT; + + return 0; +} diff --git a/kernel/bpf/core.c b/kernel/bpf/core.c index ba03ec39efb3..d0d7d9462368 100644 --- a/kernel/bpf/core.c +++ b/kernel/bpf/core.c @@ -31,6 +31,7 @@ #include <linux/rbtree_latch.h> #include <linux/kallsyms.h> #include <linux/rcupdate.h> +#include <linux/perf_event.h> #include <asm/unaligned.h> @@ -633,23 +634,6 @@ static int bpf_jit_blind_insn(const struct bpf_insn *from, *to++ = BPF_JMP_REG(from->code, from->dst_reg, BPF_REG_AX, off); break; - case BPF_LD | BPF_ABS | BPF_W: - case BPF_LD | BPF_ABS | BPF_H: - case BPF_LD | BPF_ABS | BPF_B: - *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); - *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); - break; - - case BPF_LD | BPF_IND | BPF_W: - case BPF_LD | BPF_IND | BPF_H: - case BPF_LD | BPF_IND | BPF_B: - *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ from->imm); - *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); - *to++ = BPF_ALU32_REG(BPF_ADD, BPF_REG_AX, from->src_reg); - *to++ = BPF_LD_IND(from->code, BPF_REG_AX, 0); - break; - case BPF_LD | BPF_IMM | BPF_DW: *to++ = BPF_ALU64_IMM(BPF_MOV, BPF_REG_AX, imm_rnd ^ aux[1].imm); *to++ = BPF_ALU64_IMM(BPF_XOR, BPF_REG_AX, imm_rnd); @@ -890,14 +874,7 @@ EXPORT_SYMBOL_GPL(__bpf_call_base); INSN_3(LDX, MEM, W), \ INSN_3(LDX, MEM, DW), \ /* Immediate based. */ \ - INSN_3(LD, IMM, DW), \ - /* Misc (old cBPF carry-over). */ \ - INSN_3(LD, ABS, B), \ - INSN_3(LD, ABS, H), \ - INSN_3(LD, ABS, W), \ - INSN_3(LD, IND, B), \ - INSN_3(LD, IND, H), \ - INSN_3(LD, IND, W) + INSN_3(LD, IMM, DW) bool bpf_opcode_in_insntable(u8 code) { @@ -907,6 +884,13 @@ bool bpf_opcode_in_insntable(u8 code) [0 ... 255] = false, /* Now overwrite non-defaults ... */ BPF_INSN_MAP(BPF_INSN_2_TBL, BPF_INSN_3_TBL), + /* UAPI exposed, but rewritten opcodes. cBPF carry-over. */ + [BPF_LD | BPF_ABS | BPF_B] = true, + [BPF_LD | BPF_ABS | BPF_H] = true, + [BPF_LD | BPF_ABS | BPF_W] = true, + [BPF_LD | BPF_IND | BPF_B] = true, + [BPF_LD | BPF_IND | BPF_H] = true, + [BPF_LD | BPF_IND | BPF_W] = true, }; #undef BPF_INSN_3_TBL #undef BPF_INSN_2_TBL @@ -937,8 +921,6 @@ static u64 ___bpf_prog_run(u64 *regs, const struct bpf_insn *insn, u64 *stack) #undef BPF_INSN_3_LBL #undef BPF_INSN_2_LBL u32 tail_call_cnt = 0; - void *ptr; - int off; #define CONT ({ insn++; goto select_insn; }) #define CONT_JMP ({ insn++; goto select_insn; }) @@ -1265,67 +1247,6 @@ out: atomic64_add((u64) SRC, (atomic64_t *)(unsigned long) (DST + insn->off)); CONT; - LD_ABS_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + imm32)) */ - off = IMM; -load_word: - /* BPF_LD + BPD_ABS and BPF_LD + BPF_IND insns are only - * appearing in the programs where ctx == skb - * (see may_access_skb() in the verifier). All programs - * keep 'ctx' in regs[BPF_REG_CTX] == BPF_R6, - * bpf_convert_filter() saves it in BPF_R6, internal BPF - * verifier will check that BPF_R6 == ctx. - * - * BPF_ABS and BPF_IND are wrappers of function calls, - * so they scratch BPF_R1-BPF_R5 registers, preserve - * BPF_R6-BPF_R9, and store return value into BPF_R0. - * - * Implicit input: - * ctx == skb == BPF_R6 == CTX - * - * Explicit input: - * SRC == any register - * IMM == 32-bit immediate - * - * Output: - * BPF_R0 - 8/16/32-bit skb data converted to cpu endianness - */ - - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 4, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be32(ptr); - CONT; - } - - return 0; - LD_ABS_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + imm32)) */ - off = IMM; -load_half: - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 2, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = get_unaligned_be16(ptr); - CONT; - } - - return 0; - LD_ABS_B: /* BPF_R0 = *(u8 *) (skb->data + imm32) */ - off = IMM; -load_byte: - ptr = bpf_load_pointer((struct sk_buff *) (unsigned long) CTX, off, 1, &tmp); - if (likely(ptr != NULL)) { - BPF_R0 = *(u8 *)ptr; - CONT; - } - - return 0; - LD_IND_W: /* BPF_R0 = ntohl(*(u32 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_word; - LD_IND_H: /* BPF_R0 = ntohs(*(u16 *) (skb->data + src_reg + imm32)) */ - off = IMM + SRC; - goto load_half; - LD_IND_B: /* BPF_R0 = *(u8 *) (skb->data + src_reg + imm32) */ - off = IMM + SRC; - goto load_byte; default_label: /* If we ever reach this, we have a bug somewhere. Die hard here @@ -1722,6 +1643,10 @@ static void bpf_prog_free_deferred(struct work_struct *work) aux = container_of(work, struct bpf_prog_aux, work); if (bpf_prog_is_dev_bound(aux)) bpf_prog_offload_destroy(aux->prog); +#ifdef CONFIG_PERF_EVENTS + if (aux->prog->has_callchain_buf) + put_callchain_buffers(); +#endif for (i = 0; i < aux->func_cnt; i++) bpf_jit_free(aux->func[i]); if (aux->func_cnt) { @@ -1794,6 +1719,7 @@ bpf_event_output(struct bpf_map *map, u64 flags, void *meta, u64 meta_size, { return -ENOTSUPP; } +EXPORT_SYMBOL_GPL(bpf_event_output); /* Always built-in helper functions. */ const struct bpf_func_proto bpf_tail_call_proto = { @@ -1840,9 +1766,3 @@ int __weak skb_copy_bits(const struct sk_buff *skb, int offset, void *to, #include <linux/bpf_trace.h> EXPORT_TRACEPOINT_SYMBOL_GPL(xdp_exception); - -/* These are only used within the BPF_SYSCALL code */ -#ifdef CONFIG_BPF_SYSCALL -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_get_type); -EXPORT_TRACEPOINT_SYMBOL_GPL(bpf_prog_put_rcu); -#endif diff --git a/kernel/bpf/cpumap.c b/kernel/bpf/cpumap.c index a4bb0b34375a..c95b04ec103e 100644 --- a/kernel/bpf/cpumap.c +++ b/kernel/bpf/cpumap.c @@ -19,6 +19,7 @@ #include <linux/bpf.h> #include <linux/filter.h> #include <linux/ptr_ring.h> +#include <net/xdp.h> #include <linux/sched.h> #include <linux/workqueue.h> @@ -137,27 +138,6 @@ free_cmap: return ERR_PTR(err); } -static void __cpu_map_queue_destructor(void *ptr) -{ - /* The tear-down procedure should have made sure that queue is - * empty. See __cpu_map_entry_replace() and work-queue - * invoked cpu_map_kthread_stop(). Catch any broken behaviour - * gracefully and warn once. - */ - if (WARN_ON_ONCE(ptr)) - page_frag_free(ptr); -} - -static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) -{ - if (atomic_dec_and_test(&rcpu->refcnt)) { - /* The queue should be empty at this point */ - ptr_ring_cleanup(rcpu->queue, __cpu_map_queue_destructor); - kfree(rcpu->queue); - kfree(rcpu); - } -} - static void get_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) { atomic_inc(&rcpu->refcnt); @@ -179,45 +159,8 @@ static void cpu_map_kthread_stop(struct work_struct *work) kthread_stop(rcpu->kthread); } -/* For now, xdp_pkt is a cpumap internal data structure, with info - * carried between enqueue to dequeue. It is mapped into the top - * headroom of the packet, to avoid allocating separate mem. - */ -struct xdp_pkt { - void *data; - u16 len; - u16 headroom; - u16 metasize; - struct net_device *dev_rx; -}; - -/* Convert xdp_buff to xdp_pkt */ -static struct xdp_pkt *convert_to_xdp_pkt(struct xdp_buff *xdp) -{ - struct xdp_pkt *xdp_pkt; - int metasize; - int headroom; - - /* Assure headroom is available for storing info */ - headroom = xdp->data - xdp->data_hard_start; - metasize = xdp->data - xdp->data_meta; - metasize = metasize > 0 ? metasize : 0; - if (unlikely((headroom - metasize) < sizeof(*xdp_pkt))) - return NULL; - - /* Store info in top of packet */ - xdp_pkt = xdp->data_hard_start; - - xdp_pkt->data = xdp->data; - xdp_pkt->len = xdp->data_end - xdp->data; - xdp_pkt->headroom = headroom - sizeof(*xdp_pkt); - xdp_pkt->metasize = metasize; - - return xdp_pkt; -} - static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, - struct xdp_pkt *xdp_pkt) + struct xdp_frame *xdpf) { unsigned int frame_size; void *pkt_data_start; @@ -232,7 +175,7 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * would be preferred to set frame_size to 2048 or 4096 * depending on the driver. * frame_size = 2048; - * frame_len = frame_size - sizeof(*xdp_pkt); + * frame_len = frame_size - sizeof(*xdp_frame); * * Instead, with info avail, skb_shared_info in placed after * packet len. This, unfortunately fakes the truesize. @@ -240,21 +183,21 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, * is not at a fixed memory location, with mixed length * packets, which is bad for cache-line hotness. */ - frame_size = SKB_DATA_ALIGN(xdp_pkt->len) + xdp_pkt->headroom + + frame_size = SKB_DATA_ALIGN(xdpf->len) + xdpf->headroom + SKB_DATA_ALIGN(sizeof(struct skb_shared_info)); - pkt_data_start = xdp_pkt->data - xdp_pkt->headroom; + pkt_data_start = xdpf->data - xdpf->headroom; skb = build_skb(pkt_data_start, frame_size); if (!skb) return NULL; - skb_reserve(skb, xdp_pkt->headroom); - __skb_put(skb, xdp_pkt->len); - if (xdp_pkt->metasize) - skb_metadata_set(skb, xdp_pkt->metasize); + skb_reserve(skb, xdpf->headroom); + __skb_put(skb, xdpf->len); + if (xdpf->metasize) + skb_metadata_set(skb, xdpf->metasize); /* Essential SKB info: protocol and skb->dev */ - skb->protocol = eth_type_trans(skb, xdp_pkt->dev_rx); + skb->protocol = eth_type_trans(skb, xdpf->dev_rx); /* Optional SKB info, currently missing: * - HW checksum info (skb->ip_summed) @@ -265,6 +208,31 @@ static struct sk_buff *cpu_map_build_skb(struct bpf_cpu_map_entry *rcpu, return skb; } +static void __cpu_map_ring_cleanup(struct ptr_ring *ring) +{ + /* The tear-down procedure should have made sure that queue is + * empty. See __cpu_map_entry_replace() and work-queue + * invoked cpu_map_kthread_stop(). Catch any broken behaviour + * gracefully and warn once. + */ + struct xdp_frame *xdpf; + + while ((xdpf = ptr_ring_consume(ring))) + if (WARN_ON_ONCE(xdpf)) + xdp_return_frame(xdpf); +} + +static void put_cpu_map_entry(struct bpf_cpu_map_entry *rcpu) +{ + if (atomic_dec_and_test(&rcpu->refcnt)) { + /* The queue should be empty at this point */ + __cpu_map_ring_cleanup(rcpu->queue); + ptr_ring_cleanup(rcpu->queue, NULL); + kfree(rcpu->queue); + kfree(rcpu); + } +} + static int cpu_map_kthread_run(void *data) { struct bpf_cpu_map_entry *rcpu = data; @@ -278,7 +246,7 @@ static int cpu_map_kthread_run(void *data) */ while (!kthread_should_stop() || !__ptr_ring_empty(rcpu->queue)) { unsigned int processed = 0, drops = 0, sched = 0; - struct xdp_pkt *xdp_pkt; + struct xdp_frame *xdpf; /* Release CPU reschedule checks */ if (__ptr_ring_empty(rcpu->queue)) { @@ -301,13 +269,13 @@ static int cpu_map_kthread_run(void *data) * kthread CPU pinned. Lockless access to ptr_ring * consume side valid as no-resize allowed of queue. */ - while ((xdp_pkt = __ptr_ring_consume(rcpu->queue))) { + while ((xdpf = __ptr_ring_consume(rcpu->queue))) { struct sk_buff *skb; int ret; - skb = cpu_map_build_skb(rcpu, xdp_pkt); + skb = cpu_map_build_skb(rcpu, xdpf); if (!skb) { - page_frag_free(xdp_pkt); + xdp_return_frame(xdpf); continue; } @@ -604,13 +572,13 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, spin_lock(&q->producer_lock); for (i = 0; i < bq->count; i++) { - void *xdp_pkt = bq->q[i]; + struct xdp_frame *xdpf = bq->q[i]; int err; - err = __ptr_ring_produce(q, xdp_pkt); + err = __ptr_ring_produce(q, xdpf); if (err) { drops++; - page_frag_free(xdp_pkt); /* Free xdp_pkt */ + xdp_return_frame(xdpf); } processed++; } @@ -625,7 +593,7 @@ static int bq_flush_to_queue(struct bpf_cpu_map_entry *rcpu, /* Runs under RCU-read-side, plus in softirq under NAPI protection. * Thus, safe percpu variable access. */ -static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) +static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_frame *xdpf) { struct xdp_bulk_queue *bq = this_cpu_ptr(rcpu->bulkq); @@ -636,28 +604,28 @@ static int bq_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_pkt *xdp_pkt) * driver to code invoking us to finished, due to driver * (e.g. ixgbe) recycle tricks based on page-refcnt. * - * Thus, incoming xdp_pkt is always queued here (else we race + * Thus, incoming xdp_frame is always queued here (else we race * with another CPU on page-refcnt and remaining driver code). * Queue time is very short, as driver will invoke flush * operation, when completing napi->poll call. */ - bq->q[bq->count++] = xdp_pkt; + bq->q[bq->count++] = xdpf; return 0; } int cpu_map_enqueue(struct bpf_cpu_map_entry *rcpu, struct xdp_buff *xdp, struct net_device *dev_rx) { - struct xdp_pkt *xdp_pkt; + struct xdp_frame *xdpf; - xdp_pkt = convert_to_xdp_pkt(xdp); - if (unlikely(!xdp_pkt)) + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) return -EOVERFLOW; /* Info needed when constructing SKB on remote CPU */ - xdp_pkt->dev_rx = dev_rx; + xdpf->dev_rx = dev_rx; - bq_enqueue(rcpu, xdp_pkt); + bq_enqueue(rcpu, xdpf); return 0; } diff --git a/kernel/bpf/inode.c b/kernel/bpf/inode.c index bf6da59ae0d0..ed13645bd80c 100644 --- a/kernel/bpf/inode.c +++ b/kernel/bpf/inode.c @@ -150,8 +150,154 @@ static int bpf_mkdir(struct inode *dir, struct dentry *dentry, umode_t mode) return 0; } +struct map_iter { + void *key; + bool done; +}; + +static struct map_iter *map_iter(struct seq_file *m) +{ + return m->private; +} + +static struct bpf_map *seq_file_to_map(struct seq_file *m) +{ + return file_inode(m->file)->i_private; +} + +static void map_iter_free(struct map_iter *iter) +{ + if (iter) { + kfree(iter->key); + kfree(iter); + } +} + +static struct map_iter *map_iter_alloc(struct bpf_map *map) +{ + struct map_iter *iter; + + iter = kzalloc(sizeof(*iter), GFP_KERNEL | __GFP_NOWARN); + if (!iter) + goto error; + + iter->key = kzalloc(map->key_size, GFP_KERNEL | __GFP_NOWARN); + if (!iter->key) + goto error; + + return iter; + +error: + map_iter_free(iter); + return NULL; +} + +static void *map_seq_next(struct seq_file *m, void *v, loff_t *pos) +{ + struct bpf_map *map = seq_file_to_map(m); + void *key = map_iter(m)->key; + + if (map_iter(m)->done) + return NULL; + + if (unlikely(v == SEQ_START_TOKEN)) + goto done; + + if (map->ops->map_get_next_key(map, key, key)) { + map_iter(m)->done = true; + return NULL; + } + +done: + ++(*pos); + return key; +} + +static void *map_seq_start(struct seq_file *m, loff_t *pos) +{ + if (map_iter(m)->done) + return NULL; + + return *pos ? map_iter(m)->key : SEQ_START_TOKEN; +} + +static void map_seq_stop(struct seq_file *m, void *v) +{ +} + +static int map_seq_show(struct seq_file *m, void *v) +{ + struct bpf_map *map = seq_file_to_map(m); + void *key = map_iter(m)->key; + + if (unlikely(v == SEQ_START_TOKEN)) { + seq_puts(m, "# WARNING!! The output is for debug purpose only\n"); + seq_puts(m, "# WARNING!! The output format will change\n"); + } else { + map->ops->map_seq_show_elem(map, key, m); + } + + return 0; +} + +static const struct seq_operations bpffs_map_seq_ops = { + .start = map_seq_start, + .next = map_seq_next, + .show = map_seq_show, + .stop = map_seq_stop, +}; + +static int bpffs_map_open(struct inode *inode, struct file *file) +{ + struct bpf_map *map = inode->i_private; + struct map_iter *iter; + struct seq_file *m; + int err; + + iter = map_iter_alloc(map); + if (!iter) + return -ENOMEM; + + err = seq_open(file, &bpffs_map_seq_ops); + if (err) { + map_iter_free(iter); + return err; + } + + m = file->private_data; + m->private = iter; + + return 0; +} + +static int bpffs_map_release(struct inode *inode, struct file *file) +{ + struct seq_file *m = file->private_data; + + map_iter_free(map_iter(m)); + + return seq_release(inode, file); +} + +/* bpffs_map_fops should only implement the basic + * read operation for a BPF map. The purpose is to + * provide a simple user intuitive way to do + * "cat bpffs/pathto/a-pinned-map". + * + * Other operations (e.g. write, lookup...) should be realized by + * the userspace tools (e.g. bpftool) through the + * BPF_OBJ_GET_INFO_BY_FD and the map's lookup/update + * interface. + */ +static const struct file_operations bpffs_map_fops = { + .open = bpffs_map_open, + .read = seq_read, + .release = bpffs_map_release, +}; + static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, - const struct inode_operations *iops) + const struct inode_operations *iops, + const struct file_operations *fops) { struct inode *dir = dentry->d_parent->d_inode; struct inode *inode = bpf_get_inode(dir->i_sb, dir, mode); @@ -159,6 +305,7 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, return PTR_ERR(inode); inode->i_op = iops; + inode->i_fop = fops; inode->i_private = raw; bpf_dentry_finalize(dentry, inode, dir); @@ -167,12 +314,15 @@ static int bpf_mkobj_ops(struct dentry *dentry, umode_t mode, void *raw, static int bpf_mkprog(struct dentry *dentry, umode_t mode, void *arg) { - return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops); + return bpf_mkobj_ops(dentry, mode, arg, &bpf_prog_iops, NULL); } static int bpf_mkmap(struct dentry *dentry, umode_t mode, void *arg) { - return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops); + struct bpf_map *map = arg; + + return bpf_mkobj_ops(dentry, mode, arg, &bpf_map_iops, + map->btf ? &bpffs_map_fops : NULL); } static struct dentry * @@ -279,13 +429,6 @@ int bpf_obj_pin_user(u32 ufd, const char __user *pathname) ret = bpf_obj_do_pin(pname, raw, type); if (ret != 0) bpf_any_put(raw, type); - if ((trace_bpf_obj_pin_prog_enabled() || - trace_bpf_obj_pin_map_enabled()) && !ret) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_pin_prog(raw, ufd, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_pin_map(raw, ufd, pname); - } out: putname(pname); return ret; @@ -352,15 +495,8 @@ int bpf_obj_get_user(const char __user *pathname, int flags) else goto out; - if (ret < 0) { + if (ret < 0) bpf_any_put(raw, type); - } else if (trace_bpf_obj_get_prog_enabled() || - trace_bpf_obj_get_map_enabled()) { - if (type == BPF_TYPE_PROG) - trace_bpf_obj_get_prog(raw, ret, pname); - if (type == BPF_TYPE_MAP) - trace_bpf_obj_get_map(raw, ret, pname); - } out: putname(pname); return ret; diff --git a/kernel/bpf/offload.c b/kernel/bpf/offload.c index c9401075b58c..ac747d5cf7c6 100644 --- a/kernel/bpf/offload.c +++ b/kernel/bpf/offload.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -474,8 +474,10 @@ bool bpf_offload_dev_match(struct bpf_prog *prog, struct bpf_map *map) struct bpf_prog_offload *offload; bool ret; - if (!bpf_prog_is_dev_bound(prog->aux) || !bpf_map_is_dev_bound(map)) + if (!bpf_prog_is_dev_bound(prog->aux)) return false; + if (!bpf_map_is_dev_bound(map)) + return bpf_map_offload_neutral(map); down_read(&bpf_devs_lock); offload = prog->aux->offload; diff --git a/kernel/bpf/stackmap.c b/kernel/bpf/stackmap.c index 57eeb1234b67..3ba102b41512 100644 --- a/kernel/bpf/stackmap.c +++ b/kernel/bpf/stackmap.c @@ -262,16 +262,11 @@ out: return ret; } -static void stack_map_get_build_id_offset(struct bpf_map *map, - struct stack_map_bucket *bucket, +static void stack_map_get_build_id_offset(struct bpf_stack_build_id *id_offs, u64 *ips, u32 trace_nr, bool user) { int i; struct vm_area_struct *vma; - struct bpf_stack_build_id *id_offs; - - bucket->nr = trace_nr; - id_offs = (struct bpf_stack_build_id *)bucket->data; /* * We cannot do up_read() in nmi context, so build_id lookup is @@ -361,8 +356,10 @@ BPF_CALL_3(bpf_get_stackid, struct pt_regs *, regs, struct bpf_map *, map, pcpu_freelist_pop(&smap->freelist); if (unlikely(!new_bucket)) return -ENOMEM; - stack_map_get_build_id_offset(map, new_bucket, ips, - trace_nr, user); + new_bucket->nr = trace_nr; + stack_map_get_build_id_offset( + (struct bpf_stack_build_id *)new_bucket->data, + ips, trace_nr, user); trace_len = trace_nr * sizeof(struct bpf_stack_build_id); if (hash_matches && bucket->nr == trace_nr && memcmp(bucket->data, new_bucket->data, trace_len) == 0) { @@ -405,6 +402,73 @@ const struct bpf_func_proto bpf_get_stackid_proto = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack, struct pt_regs *, regs, void *, buf, u32, size, + u64, flags) +{ + u32 init_nr, trace_nr, copy_len, elem_size, num_elem; + bool user_build_id = flags & BPF_F_USER_BUILD_ID; + u32 skip = flags & BPF_F_SKIP_FIELD_MASK; + bool user = flags & BPF_F_USER_STACK; + struct perf_callchain_entry *trace; + bool kernel = !user; + int err = -EINVAL; + u64 *ips; + + if (unlikely(flags & ~(BPF_F_SKIP_FIELD_MASK | BPF_F_USER_STACK | + BPF_F_USER_BUILD_ID))) + goto clear; + if (kernel && user_build_id) + goto clear; + + elem_size = (user && user_build_id) ? sizeof(struct bpf_stack_build_id) + : sizeof(u64); + if (unlikely(size % elem_size)) + goto clear; + + num_elem = size / elem_size; + if (sysctl_perf_event_max_stack < num_elem) + init_nr = 0; + else + init_nr = sysctl_perf_event_max_stack - num_elem; + trace = get_perf_callchain(regs, init_nr, kernel, user, + sysctl_perf_event_max_stack, false, false); + if (unlikely(!trace)) + goto err_fault; + + trace_nr = trace->nr - init_nr; + if (trace_nr < skip) + goto err_fault; + + trace_nr -= skip; + trace_nr = (trace_nr <= num_elem) ? trace_nr : num_elem; + copy_len = trace_nr * elem_size; + ips = trace->ip + skip + init_nr; + if (user && user_build_id) + stack_map_get_build_id_offset(buf, ips, trace_nr, user); + else + memcpy(buf, ips, copy_len); + + if (size > copy_len) + memset(buf + copy_len, 0, size - copy_len); + return copy_len; + +err_fault: + err = -EFAULT; +clear: + memset(buf, 0, size); + return err; +} + +const struct bpf_func_proto bpf_get_stack_proto = { + .func = bpf_get_stack, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + /* Called from eBPF program */ static void *stack_map_lookup_elem(struct bpf_map *map, void *key) { diff --git a/kernel/bpf/syscall.c b/kernel/bpf/syscall.c index 016ef9025827..c286e75ec087 100644 --- a/kernel/bpf/syscall.c +++ b/kernel/bpf/syscall.c @@ -11,6 +11,7 @@ */ #include <linux/bpf.h> #include <linux/bpf_trace.h> +#include <linux/btf.h> #include <linux/syscalls.h> #include <linux/slab.h> #include <linux/sched/signal.h> @@ -26,6 +27,7 @@ #include <linux/cred.h> #include <linux/timekeeping.h> #include <linux/ctype.h> +#include <linux/btf.h> #include <linux/nospec.h> #define IS_FD_ARRAY(map) ((map)->map_type == BPF_MAP_TYPE_PROG_ARRAY || \ @@ -253,6 +255,7 @@ static void bpf_map_free_deferred(struct work_struct *work) bpf_map_uncharge_memlock(map); security_bpf_map_free(map); + btf_put(map->btf); /* implementation dependent freeing */ map->ops->map_free(map); } @@ -282,6 +285,7 @@ void bpf_map_put(struct bpf_map *map) { __bpf_map_put(map, true); } +EXPORT_SYMBOL_GPL(bpf_map_put); void bpf_map_put_with_uref(struct bpf_map *map) { @@ -418,7 +422,7 @@ static int bpf_obj_name_cpy(char *dst, const char *src) return 0; } -#define BPF_MAP_CREATE_LAST_FIELD map_ifindex +#define BPF_MAP_CREATE_LAST_FIELD btf_value_id /* called via syscall */ static int map_create(union bpf_attr *attr) { @@ -452,6 +456,33 @@ static int map_create(union bpf_attr *attr) atomic_set(&map->refcnt, 1); atomic_set(&map->usercnt, 1); + if (bpf_map_support_seq_show(map) && + (attr->btf_key_id || attr->btf_value_id)) { + struct btf *btf; + + if (!attr->btf_key_id || !attr->btf_value_id) { + err = -EINVAL; + goto free_map_nouncharge; + } + + btf = btf_get_by_fd(attr->btf_fd); + if (IS_ERR(btf)) { + err = PTR_ERR(btf); + goto free_map_nouncharge; + } + + err = map->ops->map_check_btf(map, btf, attr->btf_key_id, + attr->btf_value_id); + if (err) { + btf_put(btf); + goto free_map_nouncharge; + } + + map->btf = btf; + map->btf_key_id = attr->btf_key_id; + map->btf_value_id = attr->btf_value_id; + } + err = security_bpf_map_alloc(map); if (err) goto free_map_nouncharge; @@ -476,7 +507,6 @@ static int map_create(union bpf_attr *attr) return err; } - trace_bpf_map_create(map, err); return err; free_map: @@ -484,6 +514,7 @@ free_map: free_map_sec: security_bpf_map_free(map); free_map_nouncharge: + btf_put(map->btf); map->ops->map_free(map); return err; } @@ -516,6 +547,7 @@ struct bpf_map *bpf_map_inc(struct bpf_map *map, bool uref) atomic_inc(&map->usercnt); return map; } +EXPORT_SYMBOL_GPL(bpf_map_inc); struct bpf_map *bpf_map_get_with_uref(u32 ufd) { @@ -635,7 +667,6 @@ static int map_lookup_elem(union bpf_attr *attr) if (copy_to_user(uvalue, value, value_size) != 0) goto free_value; - trace_bpf_map_lookup_elem(map, ufd, key, value); err = 0; free_value: @@ -732,8 +763,6 @@ static int map_update_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_update_elem(map, ufd, key, value); free_value: kfree(value); free_key: @@ -786,8 +815,6 @@ static int map_delete_elem(union bpf_attr *attr) __this_cpu_dec(bpf_prog_active); preempt_enable(); out: - if (!err) - trace_bpf_map_delete_elem(map, ufd, key); kfree(key); err_put: fdput(f); @@ -851,7 +878,6 @@ out: if (copy_to_user(unext_key, next_key, map->key_size) != 0) goto free_next_key; - trace_bpf_map_next_key(map, ufd, key, next_key); err = 0; free_next_key: @@ -1005,7 +1031,6 @@ static void __bpf_prog_put(struct bpf_prog *prog, bool do_idr_lock) if (atomic_dec_and_test(&prog->aux->refcnt)) { int i; - trace_bpf_prog_put_rcu(prog); /* bpf_prog_free_id() must be called first */ bpf_prog_free_id(prog, do_idr_lock); @@ -1172,11 +1197,7 @@ struct bpf_prog *bpf_prog_get(u32 ufd) struct bpf_prog *bpf_prog_get_type_dev(u32 ufd, enum bpf_prog_type type, bool attach_drv) { - struct bpf_prog *prog = __bpf_prog_get(ufd, &type, attach_drv); - - if (!IS_ERR(prog)) - trace_bpf_prog_get_type(prog); - return prog; + return __bpf_prog_get(ufd, &type, attach_drv); } EXPORT_SYMBOL_GPL(bpf_prog_get_type_dev); @@ -1351,7 +1372,6 @@ static int bpf_prog_load(union bpf_attr *attr) } bpf_prog_kallsyms_add(prog); - trace_bpf_prog_load(prog, err); return err; free_used_maps: @@ -1892,6 +1912,7 @@ static int bpf_prog_get_info_by_fd(struct bpf_prog *prog, info.load_time = prog->aux->load_time; info.created_by_uid = from_kuid_munged(current_user_ns(), prog->aux->user->uid); + info.gpl_compatible = prog->gpl_compatible; memcpy(info.tag, prog->tag, sizeof(prog->tag)); memcpy(info.name, prog->aux->name, sizeof(prog->aux->name)); @@ -2025,6 +2046,8 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, else if (f.file->f_op == &bpf_map_fops) err = bpf_map_get_info_by_fd(f.file->private_data, attr, uattr); + else if (f.file->f_op == &btf_fops) + err = btf_get_info_by_fd(f.file->private_data, attr, uattr); else err = -EINVAL; @@ -2032,6 +2055,19 @@ static int bpf_obj_get_info_by_fd(const union bpf_attr *attr, return err; } +#define BPF_BTF_LOAD_LAST_FIELD btf_log_level + +static int bpf_btf_load(const union bpf_attr *attr) +{ + if (CHECK_ATTR(BPF_BTF_LOAD)) + return -EINVAL; + + if (!capable(CAP_SYS_ADMIN)) + return -EPERM; + + return btf_new_fd(attr); +} + SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, size) { union bpf_attr attr = {}; @@ -2112,6 +2148,9 @@ SYSCALL_DEFINE3(bpf, int, cmd, union bpf_attr __user *, uattr, unsigned int, siz case BPF_RAW_TRACEPOINT_OPEN: err = bpf_raw_tracepoint_open(&attr); break; + case BPF_BTF_LOAD: + err = bpf_btf_load(&attr); + break; default: err = -EINVAL; break; diff --git a/kernel/bpf/tnum.c b/kernel/bpf/tnum.c index 1f4bf68c12db..938d41211be7 100644 --- a/kernel/bpf/tnum.c +++ b/kernel/bpf/tnum.c @@ -43,6 +43,16 @@ struct tnum tnum_rshift(struct tnum a, u8 shift) return TNUM(a.value >> shift, a.mask >> shift); } +struct tnum tnum_arshift(struct tnum a, u8 min_shift) +{ + /* if a.value is negative, arithmetic shifting by minimum shift + * will have larger negative offset compared to more shifting. + * If a.value is nonnegative, arithmetic shifting by minimum shift + * will have larger positive offset compare to more shifting. + */ + return TNUM((s64)a.value >> min_shift, (s64)a.mask >> min_shift); +} + struct tnum tnum_add(struct tnum a, struct tnum b) { u64 sm, sv, sigma, chi, mu; diff --git a/kernel/bpf/verifier.c b/kernel/bpf/verifier.c index 5dd1dcb902bf..d5e1a6c4165d 100644 --- a/kernel/bpf/verifier.c +++ b/kernel/bpf/verifier.c @@ -22,6 +22,7 @@ #include <linux/stringify.h> #include <linux/bsearch.h> #include <linux/sort.h> +#include <linux/perf_event.h> #include "disasm.h" @@ -164,6 +165,8 @@ struct bpf_call_arg_meta { bool pkt_access; int regno; int access_size; + s64 msize_smax_value; + u64 msize_umax_value; }; static DEFINE_MUTEX(bpf_verifier_lock); @@ -738,18 +741,19 @@ enum reg_arg_type { static int cmp_subprogs(const void *a, const void *b) { - return *(int *)a - *(int *)b; + return ((struct bpf_subprog_info *)a)->start - + ((struct bpf_subprog_info *)b)->start; } static int find_subprog(struct bpf_verifier_env *env, int off) { - u32 *p; + struct bpf_subprog_info *p; - p = bsearch(&off, env->subprog_starts, env->subprog_cnt, - sizeof(env->subprog_starts[0]), cmp_subprogs); + p = bsearch(&off, env->subprog_info, env->subprog_cnt, + sizeof(env->subprog_info[0]), cmp_subprogs); if (!p) return -ENOENT; - return p - env->subprog_starts; + return p - env->subprog_info; } @@ -769,18 +773,24 @@ static int add_subprog(struct bpf_verifier_env *env, int off) verbose(env, "too many subprograms\n"); return -E2BIG; } - env->subprog_starts[env->subprog_cnt++] = off; - sort(env->subprog_starts, env->subprog_cnt, - sizeof(env->subprog_starts[0]), cmp_subprogs, NULL); + env->subprog_info[env->subprog_cnt++].start = off; + sort(env->subprog_info, env->subprog_cnt, + sizeof(env->subprog_info[0]), cmp_subprogs, NULL); return 0; } static int check_subprogs(struct bpf_verifier_env *env) { int i, ret, subprog_start, subprog_end, off, cur_subprog = 0; + struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; int insn_cnt = env->prog->len; + /* Add entry function. */ + ret = add_subprog(env, 0); + if (ret < 0) + return ret; + /* determine subprog starts. The end is one before the next starts */ for (i = 0; i < insn_cnt; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) @@ -800,16 +810,18 @@ static int check_subprogs(struct bpf_verifier_env *env) return ret; } + /* Add a fake 'exit' subprog which could simplify subprog iteration + * logic. 'subprog_cnt' should not be increased. + */ + subprog[env->subprog_cnt].start = insn_cnt; + if (env->log.level > 1) for (i = 0; i < env->subprog_cnt; i++) - verbose(env, "func#%d @%d\n", i, env->subprog_starts[i]); + verbose(env, "func#%d @%d\n", i, subprog[i].start); /* now check that all jumps are within the same subprog */ - subprog_start = 0; - if (env->subprog_cnt == cur_subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[cur_subprog++]; + subprog_start = subprog[cur_subprog].start; + subprog_end = subprog[cur_subprog + 1].start; for (i = 0; i < insn_cnt; i++) { u8 code = insn[i].code; @@ -834,10 +846,9 @@ next: return -EINVAL; } subprog_start = subprog_end; - if (env->subprog_cnt == cur_subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[cur_subprog++]; + cur_subprog++; + if (cur_subprog < env->subprog_cnt) + subprog_end = subprog[cur_subprog + 1].start; } } return 0; @@ -1470,13 +1481,13 @@ static int update_stack_depth(struct bpf_verifier_env *env, const struct bpf_func_state *func, int off) { - u16 stack = env->subprog_stack_depth[func->subprogno]; + u16 stack = env->subprog_info[func->subprogno].stack_depth; if (stack >= -off) return 0; /* update known max for given subprogram */ - env->subprog_stack_depth[func->subprogno] = -off; + env->subprog_info[func->subprogno].stack_depth = -off; return 0; } @@ -1488,9 +1499,9 @@ static int update_stack_depth(struct bpf_verifier_env *env, */ static int check_max_stack_depth(struct bpf_verifier_env *env) { - int depth = 0, frame = 0, subprog = 0, i = 0, subprog_end; + int depth = 0, frame = 0, idx = 0, i = 0, subprog_end; + struct bpf_subprog_info *subprog = env->subprog_info; struct bpf_insn *insn = env->prog->insnsi; - int insn_cnt = env->prog->len; int ret_insn[MAX_CALL_FRAMES]; int ret_prog[MAX_CALL_FRAMES]; @@ -1498,17 +1509,14 @@ process_func: /* round up to 32-bytes, since this is granularity * of interpreter stack size */ - depth += round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32); + depth += round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); if (depth > MAX_BPF_STACK) { verbose(env, "combined stack size of %d calls is %d. Too large\n", frame + 1, depth); return -EACCES; } continue_func: - if (env->subprog_cnt == subprog) - subprog_end = insn_cnt; - else - subprog_end = env->subprog_starts[subprog]; + subprog_end = subprog[idx + 1].start; for (; i < subprog_end; i++) { if (insn[i].code != (BPF_JMP | BPF_CALL)) continue; @@ -1516,17 +1524,16 @@ continue_func: continue; /* remember insn and function to return to */ ret_insn[frame] = i + 1; - ret_prog[frame] = subprog; + ret_prog[frame] = idx; /* find the callee */ i = i + insn[i].imm + 1; - subprog = find_subprog(env, i); - if (subprog < 0) { + idx = find_subprog(env, i); + if (idx < 0) { WARN_ONCE(1, "verifier bug. No program starts at insn %d\n", i); return -EFAULT; } - subprog++; frame++; if (frame >= MAX_CALL_FRAMES) { WARN_ONCE(1, "verifier bug. Call stack is too deep\n"); @@ -1539,10 +1546,10 @@ continue_func: */ if (frame == 0) return 0; - depth -= round_up(max_t(u32, env->subprog_stack_depth[subprog], 1), 32); + depth -= round_up(max_t(u32, subprog[idx].stack_depth, 1), 32); frame--; i = ret_insn[frame]; - subprog = ret_prog[frame]; + idx = ret_prog[frame]; goto continue_func; } @@ -1558,8 +1565,7 @@ static int get_callee_stack_depth(struct bpf_verifier_env *env, start); return -EFAULT; } - subprog++; - return env->subprog_stack_depth[subprog]; + return env->subprog_info[subprog].stack_depth; } #endif @@ -1914,7 +1920,7 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, if (arg_type == ARG_PTR_TO_MAP_KEY || arg_type == ARG_PTR_TO_MAP_VALUE) { expected_type = PTR_TO_STACK; - if (!type_is_pkt_pointer(type) && + if (!type_is_pkt_pointer(type) && type != PTR_TO_MAP_VALUE && type != expected_type) goto err_type; } else if (arg_type == ARG_CONST_SIZE || @@ -1966,14 +1972,9 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->key\n"); return -EACCES; } - if (type_is_pkt_pointer(type)) - err = check_packet_access(env, regno, reg->off, - meta->map_ptr->key_size, - false); - else - err = check_stack_boundary(env, regno, - meta->map_ptr->key_size, - false, NULL); + err = check_helper_mem_access(env, regno, + meta->map_ptr->key_size, false, + NULL); } else if (arg_type == ARG_PTR_TO_MAP_VALUE) { /* bpf_map_xxx(..., map_ptr, ..., value) call: * check [value, value + map->value_size) validity @@ -1983,17 +1984,18 @@ static int check_func_arg(struct bpf_verifier_env *env, u32 regno, verbose(env, "invalid map_ptr to access map->value\n"); return -EACCES; } - if (type_is_pkt_pointer(type)) - err = check_packet_access(env, regno, reg->off, - meta->map_ptr->value_size, - false); - else - err = check_stack_boundary(env, regno, - meta->map_ptr->value_size, - false, NULL); + err = check_helper_mem_access(env, regno, + meta->map_ptr->value_size, false, + NULL); } else if (arg_type_is_mem_size(arg_type)) { bool zero_size_allowed = (arg_type == ARG_CONST_SIZE_OR_ZERO); + /* remember the mem_size which may be used later + * to refine return values. + */ + meta->msize_smax_value = reg->smax_value; + meta->msize_umax_value = reg->umax_value; + /* The register is SCALAR_VALUE; the access check * happens using its boundaries. */ @@ -2071,8 +2073,11 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, if (func_id != BPF_FUNC_redirect_map) goto error; break; - /* Restrict bpf side of cpumap, open when use-cases appear */ + /* Restrict bpf side of cpumap and xskmap, open when use-cases + * appear. + */ case BPF_MAP_TYPE_CPUMAP: + case BPF_MAP_TYPE_XSKMAP: if (func_id != BPF_FUNC_redirect_map) goto error; break; @@ -2097,7 +2102,7 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, case BPF_FUNC_tail_call: if (map->map_type != BPF_MAP_TYPE_PROG_ARRAY) goto error; - if (env->subprog_cnt) { + if (env->subprog_cnt > 1) { verbose(env, "tail_calls are not allowed in programs with bpf-to-bpf calls\n"); return -EINVAL; } @@ -2119,7 +2124,8 @@ static int check_map_func_compatibility(struct bpf_verifier_env *env, break; case BPF_FUNC_redirect_map: if (map->map_type != BPF_MAP_TYPE_DEVMAP && - map->map_type != BPF_MAP_TYPE_CPUMAP) + map->map_type != BPF_MAP_TYPE_CPUMAP && + map->map_type != BPF_MAP_TYPE_XSKMAP) goto error; break; case BPF_FUNC_sk_redirect_map: @@ -2269,7 +2275,7 @@ static int check_func_call(struct bpf_verifier_env *env, struct bpf_insn *insn, /* remember the callsite, it will be used by bpf_exit */ *insn_idx /* callsite */, state->curframe + 1 /* frameno within this callchain */, - subprog + 1 /* subprog number within this prog */); + subprog /* subprog number within this prog */); /* copy r1 - r5 args that callee can access */ for (i = BPF_REG_1; i <= BPF_REG_5; i++) @@ -2333,6 +2339,23 @@ static int prepare_func_exit(struct bpf_verifier_env *env, int *insn_idx) return 0; } +static void do_refine_retval_range(struct bpf_reg_state *regs, int ret_type, + int func_id, + struct bpf_call_arg_meta *meta) +{ + struct bpf_reg_state *ret_reg = ®s[BPF_REG_0]; + + if (ret_type != RET_INTEGER || + (func_id != BPF_FUNC_get_stack && + func_id != BPF_FUNC_probe_read_str)) + return; + + ret_reg->smax_value = meta->msize_smax_value; + ret_reg->umax_value = meta->msize_umax_value; + __reg_deduce_bounds(ret_reg); + __reg_bound_offset(ret_reg); +} + static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn_idx) { const struct bpf_func_proto *fn = NULL; @@ -2456,10 +2479,30 @@ static int check_helper_call(struct bpf_verifier_env *env, int func_id, int insn return -EINVAL; } + do_refine_retval_range(regs, fn->ret_type, func_id, &meta); + err = check_map_func_compatibility(env, meta.map_ptr, func_id); if (err) return err; + if (func_id == BPF_FUNC_get_stack && !env->prog->has_callchain_buf) { + const char *err_str; + +#ifdef CONFIG_PERF_EVENTS + err = get_callchain_buffers(sysctl_perf_event_max_stack); + err_str = "cannot get callchain buffer for func %s#%d\n"; +#else + err = -ENOTSUPP; + err_str = "func %s#%d not supported without CONFIG_PERF_EVENTS\n"; +#endif + if (err) { + verbose(env, err_str, func_id_name(func_id), func_id); + return err; + } + + env->prog->has_callchain_buf = true; + } + if (changes_data) clear_all_pkt_pointers(env); return 0; @@ -2904,10 +2947,7 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, dst_reg->umin_value <<= umin_val; dst_reg->umax_value <<= umax_val; } - if (src_known) - dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); - else - dst_reg->var_off = tnum_lshift(tnum_unknown, umin_val); + dst_reg->var_off = tnum_lshift(dst_reg->var_off, umin_val); /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); break; @@ -2935,16 +2975,35 @@ static int adjust_scalar_min_max_vals(struct bpf_verifier_env *env, */ dst_reg->smin_value = S64_MIN; dst_reg->smax_value = S64_MAX; - if (src_known) - dst_reg->var_off = tnum_rshift(dst_reg->var_off, - umin_val); - else - dst_reg->var_off = tnum_rshift(tnum_unknown, umin_val); + dst_reg->var_off = tnum_rshift(dst_reg->var_off, umin_val); dst_reg->umin_value >>= umax_val; dst_reg->umax_value >>= umin_val; /* We may learn something more from the var_off */ __update_reg_bounds(dst_reg); break; + case BPF_ARSH: + if (umax_val >= insn_bitness) { + /* Shifts greater than 31 or 63 are undefined. + * This includes shifts by a negative number. + */ + mark_reg_unknown(env, regs, insn->dst_reg); + break; + } + + /* Upon reaching here, src_known is true and + * umax_val is equal to umin_val. + */ + dst_reg->smin_value >>= umin_val; + dst_reg->smax_value >>= umin_val; + dst_reg->var_off = tnum_arshift(dst_reg->var_off, umin_val); + + /* blow away the dst_reg umin_value/umax_value and rely on + * dst_reg var_off to refine the result. + */ + dst_reg->umin_value = 0; + dst_reg->umax_value = U64_MAX; + __update_reg_bounds(dst_reg); + break; default: mark_reg_unknown(env, regs, insn->dst_reg); break; @@ -3828,7 +3887,12 @@ static int check_ld_abs(struct bpf_verifier_env *env, struct bpf_insn *insn) return -EINVAL; } - if (env->subprog_cnt) { + if (!env->ops->gen_ld_abs) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + if (env->subprog_cnt > 1) { /* when program has LD_ABS insn JITs and interpreter assume * that r1 == ctx == skb which is not the case for callees * that can have arbitrary arguments. It's problematic @@ -4859,15 +4923,15 @@ process_bpf_exit: verbose(env, "processed %d insns (limit %d), stack depth ", insn_processed, BPF_COMPLEXITY_LIMIT_INSNS); - for (i = 0; i < env->subprog_cnt + 1; i++) { - u32 depth = env->subprog_stack_depth[i]; + for (i = 0; i < env->subprog_cnt; i++) { + u32 depth = env->subprog_info[i].stack_depth; verbose(env, "%d", depth); - if (i + 1 < env->subprog_cnt + 1) + if (i + 1 < env->subprog_cnt) verbose(env, "+"); } verbose(env, "\n"); - env->prog->aux->stack_depth = env->subprog_stack_depth[0]; + env->prog->aux->stack_depth = env->subprog_info[0].stack_depth; return 0; } @@ -4991,7 +5055,7 @@ static int replace_map_fd_with_map_ptr(struct bpf_verifier_env *env) /* hold the map. If the program is rejected by verifier, * the map will be released by release_maps() or it * will be used by the valid program until it's unloaded - * and all maps are released in free_bpf_prog_info() + * and all maps are released in free_used_maps() */ map = bpf_map_inc(map, false); if (IS_ERR(map)) { @@ -5073,10 +5137,11 @@ static void adjust_subprog_starts(struct bpf_verifier_env *env, u32 off, u32 len if (len == 1) return; - for (i = 0; i < env->subprog_cnt; i++) { - if (env->subprog_starts[i] < off) + /* NOTE: fake 'exit' subprog should be updated as well. */ + for (i = 0; i <= env->subprog_cnt; i++) { + if (env->subprog_info[i].start < off) continue; - env->subprog_starts[i] += len - 1; + env->subprog_info[i].start += len - 1; } } @@ -5240,7 +5305,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) void *old_bpf_func; int err = -ENOMEM; - if (env->subprog_cnt == 0) + if (env->subprog_cnt <= 1) return 0; for (i = 0, insn = prog->insnsi; i < prog->len; i++, insn++) { @@ -5256,7 +5321,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) /* temporarily remember subprog id inside insn instead of * aux_data, since next loop will split up all insns into funcs */ - insn->off = subprog + 1; + insn->off = subprog; /* remember original imm in case JIT fails and fallback * to interpreter will be needed */ @@ -5265,16 +5330,13 @@ static int jit_subprogs(struct bpf_verifier_env *env) insn->imm = 1; } - func = kzalloc(sizeof(prog) * (env->subprog_cnt + 1), GFP_KERNEL); + func = kzalloc(sizeof(prog) * env->subprog_cnt, GFP_KERNEL); if (!func) return -ENOMEM; - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { subprog_start = subprog_end; - if (env->subprog_cnt == i) - subprog_end = prog->len; - else - subprog_end = env->subprog_starts[i]; + subprog_end = env->subprog_info[i + 1].start; len = subprog_end - subprog_start; func[i] = bpf_prog_alloc(bpf_prog_size(len), GFP_USER); @@ -5291,7 +5353,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) * Long term would need debug info to populate names */ func[i]->aux->name[0] = 'F'; - func[i]->aux->stack_depth = env->subprog_stack_depth[i]; + func[i]->aux->stack_depth = env->subprog_info[i].stack_depth; func[i]->jit_requested = 1; func[i] = bpf_int_jit_compile(func[i]); if (!func[i]->jited) { @@ -5304,7 +5366,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) * now populate all bpf_calls with correct addresses and * run last pass of JIT */ - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { insn = func[i]->insnsi; for (j = 0; j < func[i]->len; j++, insn++) { if (insn->code != (BPF_JMP | BPF_CALL) || @@ -5317,7 +5379,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) __bpf_call_base; } } - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { old_bpf_func = func[i]->bpf_func; tmp = bpf_int_jit_compile(func[i]); if (tmp != func[i] || func[i]->bpf_func != old_bpf_func) { @@ -5331,7 +5393,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) /* finally lock prog and jit images for all functions and * populate kallsysm */ - for (i = 0; i <= env->subprog_cnt; i++) { + for (i = 0; i < env->subprog_cnt; i++) { bpf_prog_lock_ro(func[i]); bpf_prog_kallsyms_add(func[i]); } @@ -5348,7 +5410,7 @@ static int jit_subprogs(struct bpf_verifier_env *env) continue; insn->off = env->insn_aux_data[i].call_imm; subprog = find_subprog(env, i + insn->off + 1); - addr = (unsigned long)func[subprog + 1]->bpf_func; + addr = (unsigned long)func[subprog]->bpf_func; addr &= PAGE_MASK; insn->imm = (u64 (*)(u64, u64, u64, u64, u64)) addr - __bpf_call_base; @@ -5357,10 +5419,10 @@ static int jit_subprogs(struct bpf_verifier_env *env) prog->jited = 1; prog->bpf_func = func[0]->bpf_func; prog->aux->func = func; - prog->aux->func_cnt = env->subprog_cnt + 1; + prog->aux->func_cnt = env->subprog_cnt; return 0; out_free: - for (i = 0; i <= env->subprog_cnt; i++) + for (i = 0; i < env->subprog_cnt; i++) if (func[i]) bpf_jit_free(func[i]); kfree(func); @@ -5463,6 +5525,25 @@ static int fixup_bpf_calls(struct bpf_verifier_env *env) continue; } + if (BPF_CLASS(insn->code) == BPF_LD && + (BPF_MODE(insn->code) == BPF_ABS || + BPF_MODE(insn->code) == BPF_IND)) { + cnt = env->ops->gen_ld_abs(insn, insn_buf); + if (cnt == 0 || cnt >= ARRAY_SIZE(insn_buf)) { + verbose(env, "bpf verifier is misconfigured\n"); + return -EINVAL; + } + + new_prog = bpf_patch_insn_data(env, i + delta, insn_buf, cnt); + if (!new_prog) + return -ENOMEM; + + delta += cnt - 1; + env->prog = prog = new_prog; + insn = new_prog->insnsi + i + delta; + continue; + } + if (insn->code != (BPF_JMP | BPF_CALL)) continue; if (insn->src_reg == BPF_PSEUDO_CALL) @@ -5660,16 +5741,16 @@ int bpf_check(struct bpf_prog **prog, union bpf_attr *attr) if (!IS_ENABLED(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS)) env->strict_alignment = true; + ret = replace_map_fd_with_map_ptr(env); + if (ret < 0) + goto skip_full_check; + if (bpf_prog_is_dev_bound(env->prog->aux)) { ret = bpf_prog_offload_verifier_prep(env); if (ret) - goto err_unlock; + goto skip_full_check; } - ret = replace_map_fd_with_map_ptr(env); - if (ret < 0) - goto skip_full_check; - env->explored_states = kcalloc(env->prog->len, sizeof(struct bpf_verifier_state_list *), GFP_USER); @@ -5740,7 +5821,7 @@ skip_full_check: err_release_maps: if (!env->prog->aux->used_maps) /* if we didn't copy map pointers into bpf_prog_info, release - * them now. Otherwise free_bpf_prog_info() will release them. + * them now. Otherwise free_used_maps() will release them. */ release_maps(env); *prog = env->prog; diff --git a/kernel/bpf/xskmap.c b/kernel/bpf/xskmap.c new file mode 100644 index 000000000000..cb3a12137404 --- /dev/null +++ b/kernel/bpf/xskmap.c @@ -0,0 +1,241 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XSKMAP used for AF_XDP sockets + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/bpf.h> +#include <linux/capability.h> +#include <net/xdp_sock.h> +#include <linux/slab.h> +#include <linux/sched.h> + +struct xsk_map { + struct bpf_map map; + struct xdp_sock **xsk_map; + struct list_head __percpu *flush_list; +}; + +static struct bpf_map *xsk_map_alloc(union bpf_attr *attr) +{ + int cpu, err = -EINVAL; + struct xsk_map *m; + u64 cost; + + if (!capable(CAP_NET_ADMIN)) + return ERR_PTR(-EPERM); + + if (attr->max_entries == 0 || attr->key_size != 4 || + attr->value_size != 4 || + attr->map_flags & ~(BPF_F_NUMA_NODE | BPF_F_RDONLY | BPF_F_WRONLY)) + return ERR_PTR(-EINVAL); + + m = kzalloc(sizeof(*m), GFP_USER); + if (!m) + return ERR_PTR(-ENOMEM); + + bpf_map_init_from_attr(&m->map, attr); + + cost = (u64)m->map.max_entries * sizeof(struct xdp_sock *); + cost += sizeof(struct list_head) * num_possible_cpus(); + if (cost >= U32_MAX - PAGE_SIZE) + goto free_m; + + m->map.pages = round_up(cost, PAGE_SIZE) >> PAGE_SHIFT; + + /* Notice returns -EPERM on if map size is larger than memlock limit */ + err = bpf_map_precharge_memlock(m->map.pages); + if (err) + goto free_m; + + err = -ENOMEM; + + m->flush_list = alloc_percpu(struct list_head); + if (!m->flush_list) + goto free_m; + + for_each_possible_cpu(cpu) + INIT_LIST_HEAD(per_cpu_ptr(m->flush_list, cpu)); + + m->xsk_map = bpf_map_area_alloc(m->map.max_entries * + sizeof(struct xdp_sock *), + m->map.numa_node); + if (!m->xsk_map) + goto free_percpu; + return &m->map; + +free_percpu: + free_percpu(m->flush_list); +free_m: + kfree(m); + return ERR_PTR(err); +} + +static void xsk_map_free(struct bpf_map *map) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + int i; + + synchronize_net(); + + for (i = 0; i < map->max_entries; i++) { + struct xdp_sock *xs; + + xs = m->xsk_map[i]; + if (!xs) + continue; + + sock_put((struct sock *)xs); + } + + free_percpu(m->flush_list); + bpf_map_area_free(m->xsk_map); + kfree(m); +} + +static int xsk_map_get_next_key(struct bpf_map *map, void *key, void *next_key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + u32 index = key ? *(u32 *)key : U32_MAX; + u32 *next = next_key; + + if (index >= m->map.max_entries) { + *next = 0; + return 0; + } + + if (index == m->map.max_entries - 1) + return -ENOENT; + *next = index + 1; + return 0; +} + +struct xdp_sock *__xsk_map_lookup_elem(struct bpf_map *map, u32 key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *xs; + + if (key >= map->max_entries) + return NULL; + + xs = READ_ONCE(m->xsk_map[key]); + return xs; +} + +int __xsk_map_redirect(struct bpf_map *map, struct xdp_buff *xdp, + struct xdp_sock *xs) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + int err; + + err = xsk_rcv(xs, xdp); + if (err) + return err; + + if (!xs->flush_node.prev) + list_add(&xs->flush_node, flush_list); + + return 0; +} + +void __xsk_map_flush(struct bpf_map *map) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct list_head *flush_list = this_cpu_ptr(m->flush_list); + struct xdp_sock *xs, *tmp; + + list_for_each_entry_safe(xs, tmp, flush_list, flush_node) { + xsk_flush(xs); + __list_del(xs->flush_node.prev, xs->flush_node.next); + xs->flush_node.prev = NULL; + } +} + +static void *xsk_map_lookup_elem(struct bpf_map *map, void *key) +{ + return NULL; +} + +static int xsk_map_update_elem(struct bpf_map *map, void *key, void *value, + u64 map_flags) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + u32 i = *(u32 *)key, fd = *(u32 *)value; + struct xdp_sock *xs, *old_xs; + struct socket *sock; + int err; + + if (unlikely(map_flags > BPF_EXIST)) + return -EINVAL; + if (unlikely(i >= m->map.max_entries)) + return -E2BIG; + if (unlikely(map_flags == BPF_NOEXIST)) + return -EEXIST; + + sock = sockfd_lookup(fd, &err); + if (!sock) + return err; + + if (sock->sk->sk_family != PF_XDP) { + sockfd_put(sock); + return -EOPNOTSUPP; + } + + xs = (struct xdp_sock *)sock->sk; + + if (!xsk_is_setup_for_bpf_map(xs)) { + sockfd_put(sock); + return -EOPNOTSUPP; + } + + sock_hold(sock->sk); + + old_xs = xchg(&m->xsk_map[i], xs); + if (old_xs) { + /* Make sure we've flushed everything. */ + synchronize_net(); + sock_put((struct sock *)old_xs); + } + + sockfd_put(sock); + return 0; +} + +static int xsk_map_delete_elem(struct bpf_map *map, void *key) +{ + struct xsk_map *m = container_of(map, struct xsk_map, map); + struct xdp_sock *old_xs; + int k = *(u32 *)key; + + if (k >= map->max_entries) + return -EINVAL; + + old_xs = xchg(&m->xsk_map[k], NULL); + if (old_xs) { + /* Make sure we've flushed everything. */ + synchronize_net(); + sock_put((struct sock *)old_xs); + } + + return 0; +} + +const struct bpf_map_ops xsk_map_ops = { + .map_alloc = xsk_map_alloc, + .map_free = xsk_map_free, + .map_get_next_key = xsk_map_get_next_key, + .map_lookup_elem = xsk_map_lookup_elem, + .map_update_elem = xsk_map_update_elem, + .map_delete_elem = xsk_map_delete_elem, +}; + + diff --git a/kernel/trace/bpf_trace.c b/kernel/trace/bpf_trace.c index 56ba0f2a01db..ce2cbbff27e4 100644 --- a/kernel/trace/bpf_trace.c +++ b/kernel/trace/bpf_trace.c @@ -20,6 +20,7 @@ #include "trace.h" u64 bpf_get_stackid(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); +u64 bpf_get_stack(u64 r1, u64 r2, u64 r3, u64 r4, u64 r5); /** * trace_call_bpf - invoke BPF program @@ -474,8 +475,6 @@ BPF_CALL_2(bpf_current_task_under_cgroup, struct bpf_map *, map, u32, idx) struct bpf_array *array = container_of(map, struct bpf_array, map); struct cgroup *cgrp; - if (unlikely(in_interrupt())) - return -EINVAL; if (unlikely(idx >= array->map.max_entries)) return -E2BIG; @@ -577,6 +576,8 @@ kprobe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto; case BPF_FUNC_perf_event_read_value: return &bpf_perf_event_read_value_proto; #ifdef CONFIG_BPF_KPROBE_OVERRIDE @@ -664,6 +665,25 @@ static const struct bpf_func_proto bpf_get_stackid_proto_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_tp, void *, tp_buff, void *, buf, u32, size, + u64, flags) +{ + struct pt_regs *regs = *(struct pt_regs **)tp_buff; + + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_tp = { + .func = bpf_get_stack_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_UNINIT_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -672,6 +692,8 @@ tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; default: return tracing_func_proto(func_id, prog); } @@ -734,6 +756,8 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_tp; case BPF_FUNC_perf_prog_read_value: return &bpf_perf_prog_read_value_proto; default: @@ -744,7 +768,7 @@ pe_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) /* * bpf_raw_tp_regs are separate from bpf_pt_regs used from skb/xdp * to avoid potential recursive reuse issue when/if tracepoints are added - * inside bpf_*_event_output and/or bpf_get_stack_id + * inside bpf_*_event_output, bpf_get_stackid and/or bpf_get_stack */ static DEFINE_PER_CPU(struct pt_regs, bpf_raw_tp_regs); BPF_CALL_5(bpf_perf_event_output_raw_tp, struct bpf_raw_tracepoint_args *, args, @@ -787,6 +811,26 @@ static const struct bpf_func_proto bpf_get_stackid_proto_raw_tp = { .arg3_type = ARG_ANYTHING, }; +BPF_CALL_4(bpf_get_stack_raw_tp, struct bpf_raw_tracepoint_args *, args, + void *, buf, u32, size, u64, flags) +{ + struct pt_regs *regs = this_cpu_ptr(&bpf_raw_tp_regs); + + perf_fetch_caller_regs(regs); + return bpf_get_stack((unsigned long) regs, (unsigned long) buf, + (unsigned long) size, flags, 0); +} + +static const struct bpf_func_proto bpf_get_stack_proto_raw_tp = { + .func = bpf_get_stack_raw_tp, + .gpl_only = true, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_PTR_TO_MEM, + .arg3_type = ARG_CONST_SIZE_OR_ZERO, + .arg4_type = ARG_ANYTHING, +}; + static const struct bpf_func_proto * raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) { @@ -795,6 +839,8 @@ raw_tp_prog_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_perf_event_output_proto_raw_tp; case BPF_FUNC_get_stackid: return &bpf_get_stackid_proto_raw_tp; + case BPF_FUNC_get_stack: + return &bpf_get_stack_proto_raw_tp; default: return tracing_func_proto(func_id, prog); } diff --git a/lib/kobject_uevent.c b/lib/kobject_uevent.c index 15ea216a67ce..63d0816ab23b 100644 --- a/lib/kobject_uevent.c +++ b/lib/kobject_uevent.c @@ -22,6 +22,7 @@ #include <linux/socket.h> #include <linux/skbuff.h> #include <linux/netlink.h> +#include <linux/uidgid.h> #include <linux/uuid.h> #include <linux/ctype.h> #include <net/sock.h> @@ -231,30 +232,6 @@ out: return r; } -#ifdef CONFIG_NET -static int kobj_bcast_filter(struct sock *dsk, struct sk_buff *skb, void *data) -{ - struct kobject *kobj = data, *ksobj; - const struct kobj_ns_type_operations *ops; - - ops = kobj_ns_ops(kobj); - if (!ops && kobj->kset) { - ksobj = &kobj->kset->kobj; - if (ksobj->parent != NULL) - ops = kobj_ns_ops(ksobj->parent); - } - - if (ops && ops->netlink_ns && kobj->ktype->namespace) { - const void *sock_ns, *ns; - ns = kobj->ktype->namespace(kobj); - sock_ns = ops->netlink_ns(dsk); - return sock_ns != ns; - } - - return 0; -} -#endif - #ifdef CONFIG_UEVENT_HELPER static int kobj_usermode_filter(struct kobject *kobj) { @@ -296,15 +273,44 @@ static void cleanup_uevent_env(struct subprocess_info *info) } #endif -static int kobject_uevent_net_broadcast(struct kobject *kobj, - struct kobj_uevent_env *env, +#ifdef CONFIG_NET +static struct sk_buff *alloc_uevent_skb(struct kobj_uevent_env *env, const char *action_string, const char *devpath) { - int retval = 0; -#if defined(CONFIG_NET) + struct netlink_skb_parms *parms; + struct sk_buff *skb = NULL; + char *scratch; + size_t len; + + /* allocate message with maximum possible size */ + len = strlen(action_string) + strlen(devpath) + 2; + skb = alloc_skb(len + env->buflen, GFP_KERNEL); + if (!skb) + return NULL; + + /* add header */ + scratch = skb_put(skb, len); + sprintf(scratch, "%s@%s", action_string, devpath); + + skb_put_data(skb, env->buf, env->buflen); + + parms = &NETLINK_CB(skb); + parms->creds.uid = GLOBAL_ROOT_UID; + parms->creds.gid = GLOBAL_ROOT_GID; + parms->dst_group = 1; + parms->portid = 0; + + return skb; +} + +static int uevent_net_broadcast_untagged(struct kobj_uevent_env *env, + const char *action_string, + const char *devpath) +{ struct sk_buff *skb = NULL; struct uevent_sock *ue_sk; + int retval = 0; /* send netlink message */ list_for_each_entry(ue_sk, &uevent_sock_list, list) { @@ -314,37 +320,99 @@ static int kobject_uevent_net_broadcast(struct kobject *kobj, continue; if (!skb) { - /* allocate message with the maximum possible size */ - size_t len = strlen(action_string) + strlen(devpath) + 2; - char *scratch; - retval = -ENOMEM; - skb = alloc_skb(len + env->buflen, GFP_KERNEL); + skb = alloc_uevent_skb(env, action_string, devpath); if (!skb) continue; - - /* add header */ - scratch = skb_put(skb, len); - sprintf(scratch, "%s@%s", action_string, devpath); - - skb_put_data(skb, env->buf, env->buflen); - - NETLINK_CB(skb).dst_group = 1; } - retval = netlink_broadcast_filtered(uevent_sock, skb_get(skb), - 0, 1, GFP_KERNEL, - kobj_bcast_filter, - kobj); + retval = netlink_broadcast(uevent_sock, skb_get(skb), 0, 1, + GFP_KERNEL); /* ENOBUFS should be handled in userspace */ if (retval == -ENOBUFS || retval == -ESRCH) retval = 0; } consume_skb(skb); -#endif + return retval; } +static int uevent_net_broadcast_tagged(struct sock *usk, + struct kobj_uevent_env *env, + const char *action_string, + const char *devpath) +{ + struct user_namespace *owning_user_ns = sock_net(usk)->user_ns; + struct sk_buff *skb = NULL; + int ret = 0; + + skb = alloc_uevent_skb(env, action_string, devpath); + if (!skb) + return -ENOMEM; + + /* fix credentials */ + if (owning_user_ns != &init_user_ns) { + struct netlink_skb_parms *parms = &NETLINK_CB(skb); + kuid_t root_uid; + kgid_t root_gid; + + /* fix uid */ + root_uid = make_kuid(owning_user_ns, 0); + if (uid_valid(root_uid)) + parms->creds.uid = root_uid; + + /* fix gid */ + root_gid = make_kgid(owning_user_ns, 0); + if (gid_valid(root_gid)) + parms->creds.gid = root_gid; + } + + ret = netlink_broadcast(usk, skb, 0, 1, GFP_KERNEL); + /* ENOBUFS should be handled in userspace */ + if (ret == -ENOBUFS || ret == -ESRCH) + ret = 0; + + return ret; +} +#endif + +static int kobject_uevent_net_broadcast(struct kobject *kobj, + struct kobj_uevent_env *env, + const char *action_string, + const char *devpath) +{ + int ret = 0; + +#ifdef CONFIG_NET + const struct kobj_ns_type_operations *ops; + const struct net *net = NULL; + + ops = kobj_ns_ops(kobj); + if (!ops && kobj->kset) { + struct kobject *ksobj = &kobj->kset->kobj; + if (ksobj->parent != NULL) + ops = kobj_ns_ops(ksobj->parent); + } + + /* kobjects currently only carry network namespace tags and they + * are the only tag relevant here since we want to decide which + * network namespaces to broadcast the uevent into. + */ + if (ops && ops->netlink_ns && kobj->ktype->namespace) + if (ops->type == KOBJ_NS_TYPE_NET) + net = kobj->ktype->namespace(kobj); + + if (!net) + ret = uevent_net_broadcast_untagged(env, action_string, + devpath); + else + ret = uevent_net_broadcast_tagged(net->uevent_sock->sk, env, + action_string, devpath); +#endif + + return ret; +} + static void zap_modalias_env(struct kobj_uevent_env *env) { static const char modalias_prefix[] = "MODALIAS="; @@ -703,9 +771,13 @@ static int uevent_net_init(struct net *net) net->uevent_sock = ue_sk; - mutex_lock(&uevent_sock_mutex); - list_add_tail(&ue_sk->list, &uevent_sock_list); - mutex_unlock(&uevent_sock_mutex); + /* Restrict uevents to initial user namespace. */ + if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { + mutex_lock(&uevent_sock_mutex); + list_add_tail(&ue_sk->list, &uevent_sock_list); + mutex_unlock(&uevent_sock_mutex); + } + return 0; } @@ -713,9 +785,11 @@ static void uevent_net_exit(struct net *net) { struct uevent_sock *ue_sk = net->uevent_sock; - mutex_lock(&uevent_sock_mutex); - list_del(&ue_sk->list); - mutex_unlock(&uevent_sock_mutex); + if (sock_net(ue_sk->sk)->user_ns == &init_user_ns) { + mutex_lock(&uevent_sock_mutex); + list_del(&ue_sk->list); + mutex_unlock(&uevent_sock_mutex); + } netlink_kernel_release(ue_sk->sk); kfree(ue_sk); diff --git a/lib/rhashtable.c b/lib/rhashtable.c index 2b2b79974b61..9427b5766134 100644 --- a/lib/rhashtable.c +++ b/lib/rhashtable.c @@ -668,8 +668,9 @@ EXPORT_SYMBOL_GPL(rhashtable_insert_slow); * For a completely stable walk you should construct your own data * structure outside the hash table. * - * This function may sleep so you must not call it from interrupt - * context or with spin locks held. + * This function may be called from any process context, including + * non-preemptable context, but cannot be called from softirq or + * hardirq context. * * You must call rhashtable_walk_exit after this function returns. */ @@ -726,6 +727,7 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter) __acquires(RCU) { struct rhashtable *ht = iter->ht; + bool rhlist = ht->rhlist; rcu_read_lock(); @@ -734,11 +736,52 @@ int rhashtable_walk_start_check(struct rhashtable_iter *iter) list_del(&iter->walker.list); spin_unlock(&ht->lock); - if (!iter->walker.tbl && !iter->end_of_table) { + if (iter->end_of_table) + return 0; + if (!iter->walker.tbl) { iter->walker.tbl = rht_dereference_rcu(ht->tbl, ht); + iter->slot = 0; + iter->skip = 0; return -EAGAIN; } + if (iter->p && !rhlist) { + /* + * We need to validate that 'p' is still in the table, and + * if so, update 'skip' + */ + struct rhash_head *p; + int skip = 0; + rht_for_each_rcu(p, iter->walker.tbl, iter->slot) { + skip++; + if (p == iter->p) { + iter->skip = skip; + goto found; + } + } + iter->p = NULL; + } else if (iter->p && rhlist) { + /* Need to validate that 'list' is still in the table, and + * if so, update 'skip' and 'p'. + */ + struct rhash_head *p; + struct rhlist_head *list; + int skip = 0; + rht_for_each_rcu(p, iter->walker.tbl, iter->slot) { + for (list = container_of(p, struct rhlist_head, rhead); + list; + list = rcu_dereference(list->next)) { + skip++; + if (list == iter->list) { + iter->p = p; + skip = skip; + goto found; + } + } + } + iter->p = NULL; + } +found: return 0; } EXPORT_SYMBOL_GPL(rhashtable_walk_start_check); @@ -914,8 +957,6 @@ void rhashtable_walk_stop(struct rhashtable_iter *iter) iter->walker.tbl = NULL; spin_unlock(&ht->lock); - iter->p = NULL; - out: rcu_read_unlock(); } diff --git a/lib/test_bpf.c b/lib/test_bpf.c index 8e157806df7a..317f231462d4 100644 --- a/lib/test_bpf.c +++ b/lib/test_bpf.c @@ -386,116 +386,6 @@ static int bpf_fill_ld_abs_get_processor_id(struct bpf_test *self) return 0; } -#define PUSH_CNT 68 -/* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */ -static int bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self) -{ - unsigned int len = BPF_MAXINSNS; - struct bpf_insn *insn; - int i = 0, j, k = 0; - - insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); - if (!insn) - return -ENOMEM; - - insn[i++] = BPF_MOV64_REG(R6, R1); -loop: - for (j = 0; j < PUSH_CNT; j++) { - insn[i++] = BPF_LD_ABS(BPF_B, 0); - insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2); - i++; - insn[i++] = BPF_MOV64_REG(R1, R6); - insn[i++] = BPF_MOV64_IMM(R2, 1); - insn[i++] = BPF_MOV64_IMM(R3, 2); - insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - bpf_skb_vlan_push_proto.func - __bpf_call_base); - insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2); - i++; - } - - for (j = 0; j < PUSH_CNT; j++) { - insn[i++] = BPF_LD_ABS(BPF_B, 0); - insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0x34, len - i - 2); - i++; - insn[i++] = BPF_MOV64_REG(R1, R6); - insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - bpf_skb_vlan_pop_proto.func - __bpf_call_base); - insn[i] = BPF_JMP_IMM(BPF_JNE, R0, 0, len - i - 2); - i++; - } - if (++k < 5) - goto loop; - - for (; i < len - 1; i++) - insn[i] = BPF_ALU32_IMM(BPF_MOV, R0, 0xbef); - - insn[len - 1] = BPF_EXIT_INSN(); - - self->u.ptr.insns = insn; - self->u.ptr.len = len; - - return 0; -} - -static int bpf_fill_ld_abs_vlan_push_pop2(struct bpf_test *self) -{ - struct bpf_insn *insn; - - insn = kmalloc_array(16, sizeof(*insn), GFP_KERNEL); - if (!insn) - return -ENOMEM; - - /* Due to func address being non-const, we need to - * assemble this here. - */ - insn[0] = BPF_MOV64_REG(R6, R1); - insn[1] = BPF_LD_ABS(BPF_B, 0); - insn[2] = BPF_LD_ABS(BPF_H, 0); - insn[3] = BPF_LD_ABS(BPF_W, 0); - insn[4] = BPF_MOV64_REG(R7, R6); - insn[5] = BPF_MOV64_IMM(R6, 0); - insn[6] = BPF_MOV64_REG(R1, R7); - insn[7] = BPF_MOV64_IMM(R2, 1); - insn[8] = BPF_MOV64_IMM(R3, 2); - insn[9] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, - bpf_skb_vlan_push_proto.func - __bpf_call_base); - insn[10] = BPF_MOV64_REG(R6, R7); - insn[11] = BPF_LD_ABS(BPF_B, 0); - insn[12] = BPF_LD_ABS(BPF_H, 0); - insn[13] = BPF_LD_ABS(BPF_W, 0); - insn[14] = BPF_MOV64_IMM(R0, 42); - insn[15] = BPF_EXIT_INSN(); - - self->u.ptr.insns = insn; - self->u.ptr.len = 16; - - return 0; -} - -static int bpf_fill_jump_around_ld_abs(struct bpf_test *self) -{ - unsigned int len = BPF_MAXINSNS; - struct bpf_insn *insn; - int i = 0; - - insn = kmalloc_array(len, sizeof(*insn), GFP_KERNEL); - if (!insn) - return -ENOMEM; - - insn[i++] = BPF_MOV64_REG(R6, R1); - insn[i++] = BPF_LD_ABS(BPF_B, 0); - insn[i] = BPF_JMP_IMM(BPF_JEQ, R0, 10, len - i - 2); - i++; - while (i < len - 1) - insn[i++] = BPF_LD_ABS(BPF_B, 1); - insn[i] = BPF_EXIT_INSN(); - - self->u.ptr.insns = insn; - self->u.ptr.len = len; - - return 0; -} - static int __bpf_fill_stxdw(struct bpf_test *self, int size) { unsigned int len = BPF_MAXINSNS; @@ -1988,40 +1878,6 @@ static struct bpf_test tests[] = { { { 0, -1 } } }, { - "INT: DIV + ABS", - .u.insns_int = { - BPF_ALU64_REG(BPF_MOV, R6, R1), - BPF_LD_ABS(BPF_B, 3), - BPF_ALU64_IMM(BPF_MOV, R2, 2), - BPF_ALU32_REG(BPF_DIV, R0, R2), - BPF_ALU64_REG(BPF_MOV, R8, R0), - BPF_LD_ABS(BPF_B, 4), - BPF_ALU64_REG(BPF_ADD, R8, R0), - BPF_LD_IND(BPF_B, R8, -70), - BPF_EXIT_INSN(), - }, - INTERNAL, - { 10, 20, 30, 40, 50 }, - { { 4, 0 }, { 5, 10 } } - }, - { - /* This one doesn't go through verifier, but is just raw insn - * as opposed to cBPF tests from here. Thus div by 0 tests are - * done in test_verifier in BPF kselftests. - */ - "INT: DIV by -1", - .u.insns_int = { - BPF_ALU64_REG(BPF_MOV, R6, R1), - BPF_ALU64_IMM(BPF_MOV, R7, -1), - BPF_LD_ABS(BPF_B, 3), - BPF_ALU32_REG(BPF_DIV, R0, R7), - BPF_EXIT_INSN(), - }, - INTERNAL, - { 10, 20, 30, 40, 50 }, - { { 3, 0 }, { 4, 0 } } - }, - { "check: missing ret", .u.insns = { BPF_STMT(BPF_LD | BPF_IMM, 1), @@ -2383,50 +2239,6 @@ static struct bpf_test tests[] = { { }, { { 0, 1 } } }, - { - "nmap reduced", - .u.insns_int = { - BPF_MOV64_REG(R6, R1), - BPF_LD_ABS(BPF_H, 12), - BPF_JMP_IMM(BPF_JNE, R0, 0x806, 28), - BPF_LD_ABS(BPF_H, 12), - BPF_JMP_IMM(BPF_JNE, R0, 0x806, 26), - BPF_MOV32_IMM(R0, 18), - BPF_STX_MEM(BPF_W, R10, R0, -64), - BPF_LDX_MEM(BPF_W, R7, R10, -64), - BPF_LD_IND(BPF_W, R7, 14), - BPF_STX_MEM(BPF_W, R10, R0, -60), - BPF_MOV32_IMM(R0, 280971478), - BPF_STX_MEM(BPF_W, R10, R0, -56), - BPF_LDX_MEM(BPF_W, R7, R10, -56), - BPF_LDX_MEM(BPF_W, R0, R10, -60), - BPF_ALU32_REG(BPF_SUB, R0, R7), - BPF_JMP_IMM(BPF_JNE, R0, 0, 15), - BPF_LD_ABS(BPF_H, 12), - BPF_JMP_IMM(BPF_JNE, R0, 0x806, 13), - BPF_MOV32_IMM(R0, 22), - BPF_STX_MEM(BPF_W, R10, R0, -56), - BPF_LDX_MEM(BPF_W, R7, R10, -56), - BPF_LD_IND(BPF_H, R7, 14), - BPF_STX_MEM(BPF_W, R10, R0, -52), - BPF_MOV32_IMM(R0, 17366), - BPF_STX_MEM(BPF_W, R10, R0, -48), - BPF_LDX_MEM(BPF_W, R7, R10, -48), - BPF_LDX_MEM(BPF_W, R0, R10, -52), - BPF_ALU32_REG(BPF_SUB, R0, R7), - BPF_JMP_IMM(BPF_JNE, R0, 0, 2), - BPF_MOV32_IMM(R0, 256), - BPF_EXIT_INSN(), - BPF_MOV32_IMM(R0, 0), - BPF_EXIT_INSN(), - }, - INTERNAL, - { 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, 0, - 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, - 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6}, - { { 38, 256 } }, - .stack_depth = 64, - }, /* BPF_ALU | BPF_MOV | BPF_X */ { "ALU_MOV_X: dst = 2", @@ -5485,22 +5297,6 @@ static struct bpf_test tests[] = { { { 1, 0xbee } }, .fill_helper = bpf_fill_ld_abs_get_processor_id, }, - { - "BPF_MAXINSNS: ld_abs+vlan_push/pop", - { }, - INTERNAL, - { 0x34 }, - { { ETH_HLEN, 0xbef } }, - .fill_helper = bpf_fill_ld_abs_vlan_push_pop, - }, - { - "BPF_MAXINSNS: jump around ld_abs", - { }, - INTERNAL, - { 10, 11 }, - { { 2, 10 } }, - .fill_helper = bpf_fill_jump_around_ld_abs, - }, /* * LD_IND / LD_ABS on fragmented SKBs */ @@ -5683,6 +5479,53 @@ static struct bpf_test tests[] = { { {0x40, 0x05 } }, }, { + "LD_IND byte positive offset, all ff", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3e), + BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff }, + { {0x40, 0xff } }, + }, + { + "LD_IND byte positive offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3e), + BPF_STMT(BPF_LD | BPF_IND | BPF_B, 0x1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LD_IND byte negative offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3e), + BPF_STMT(BPF_LD | BPF_IND | BPF_B, -0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 } }, + }, + { + "LD_IND byte negative offset, multiple calls", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3b), + BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 1), + BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 2), + BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 3), + BPF_STMT(BPF_LD | BPF_IND | BPF_B, SKF_LL_OFF + 4), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x82 }, }, + }, + { "LD_IND halfword positive offset", .u.insns = { BPF_STMT(BPF_LDX | BPF_IMM, 0x20), @@ -5731,6 +5574,39 @@ static struct bpf_test tests[] = { { {0x40, 0x66cc } }, }, { + "LD_IND halfword positive offset, all ff", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3d), + BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff }, + { {0x40, 0xffff } }, + }, + { + "LD_IND halfword positive offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3e), + BPF_STMT(BPF_LD | BPF_IND | BPF_H, 0x1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LD_IND halfword negative offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3e), + BPF_STMT(BPF_LD | BPF_IND | BPF_H, -0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 } }, + }, + { "LD_IND word positive offset", .u.insns = { BPF_STMT(BPF_LDX | BPF_IMM, 0x20), @@ -5821,6 +5697,39 @@ static struct bpf_test tests[] = { { {0x40, 0x66cc77dd } }, }, { + "LD_IND word positive offset, all ff", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3b), + BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff }, + { {0x40, 0xffffffff } }, + }, + { + "LD_IND word positive offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3e), + BPF_STMT(BPF_LD | BPF_IND | BPF_W, 0x1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LD_IND word negative offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LDX | BPF_IMM, 0x3e), + BPF_STMT(BPF_LD | BPF_IND | BPF_W, -0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 } }, + }, + { "LD_ABS byte", .u.insns = { BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x20), @@ -5838,6 +5747,68 @@ static struct bpf_test tests[] = { { {0x40, 0xcc } }, }, { + "LD_ABS byte positive offset, all ff", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff }, + { {0x40, 0xff } }, + }, + { + "LD_ABS byte positive offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LD_ABS byte negative offset, out of bounds load", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, -1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC | FLAG_EXPECTED_FAIL, + .expected_errcode = -EINVAL, + }, + { + "LD_ABS byte negative offset, in bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x82 }, }, + }, + { + "LD_ABS byte negative offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LD_ABS byte negative offset, multiple calls", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3c), + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3d), + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3e), + BPF_STMT(BPF_LD | BPF_ABS | BPF_B, SKF_LL_OFF + 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x82 }, }, + }, + { "LD_ABS halfword", .u.insns = { BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x22), @@ -5872,6 +5843,55 @@ static struct bpf_test tests[] = { { {0x40, 0x99ff } }, }, { + "LD_ABS halfword positive offset, all ff", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3e), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff }, + { {0x40, 0xffff } }, + }, + { + "LD_ABS halfword positive offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_H, 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LD_ABS halfword negative offset, out of bounds load", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_H, -1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC | FLAG_EXPECTED_FAIL, + .expected_errcode = -EINVAL, + }, + { + "LD_ABS halfword negative offset, in bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x1982 }, }, + }, + { + "LD_ABS halfword negative offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_H, SKF_LL_OFF + 0x3e), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { "LD_ABS word", .u.insns = { BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x1c), @@ -5939,6 +5959,140 @@ static struct bpf_test tests[] = { }, { {0x40, 0x88ee99ff } }, }, + { + "LD_ABS word positive offset, all ff", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3c), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0xff, [0x3d] = 0xff, [0x3e] = 0xff, [0x3f] = 0xff }, + { {0x40, 0xffffffff } }, + }, + { + "LD_ABS word positive offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_W, 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LD_ABS word negative offset, out of bounds load", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_W, -1), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC | FLAG_EXPECTED_FAIL, + .expected_errcode = -EINVAL, + }, + { + "LD_ABS word negative offset, in bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x25051982 }, }, + }, + { + "LD_ABS word negative offset, out of bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_ABS | BPF_W, SKF_LL_OFF + 0x3c), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x3f, 0 }, }, + }, + { + "LDX_MSH standalone, preserved A", + .u.insns = { + BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0xffeebbaa }, }, + }, + { + "LDX_MSH standalone, preserved A 2", + .u.insns = { + BPF_STMT(BPF_LD | BPF_IMM, 0x175e9d63), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3d), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3f), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x175e9d63 }, }, + }, + { + "LDX_MSH standalone, test result 1", + .u.insns = { + BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3c), + BPF_STMT(BPF_MISC | BPF_TXA, 0), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x14 }, }, + }, + { + "LDX_MSH standalone, test result 2", + .u.insns = { + BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x3e), + BPF_STMT(BPF_MISC | BPF_TXA, 0), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x24 }, }, + }, + { + "LDX_MSH standalone, negative offset", + .u.insns = { + BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, -1), + BPF_STMT(BPF_MISC | BPF_TXA, 0), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0 }, }, + }, + { + "LDX_MSH standalone, negative offset 2", + .u.insns = { + BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, SKF_LL_OFF + 0x3e), + BPF_STMT(BPF_MISC | BPF_TXA, 0), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0x24 }, }, + }, + { + "LDX_MSH standalone, out of bounds", + .u.insns = { + BPF_STMT(BPF_LD | BPF_IMM, 0xffeebbaa), + BPF_STMT(BPF_LDX | BPF_B | BPF_MSH, 0x40), + BPF_STMT(BPF_MISC | BPF_TXA, 0), + BPF_STMT(BPF_RET | BPF_A, 0x0), + }, + CLASSIC, + { [0x3c] = 0x25, [0x3d] = 0x05, [0x3e] = 0x19, [0x3f] = 0x82 }, + { {0x40, 0 }, }, + }, /* * verify that the interpreter or JIT correctly sets A and X * to 0. @@ -6127,14 +6281,6 @@ static struct bpf_test tests[] = { {}, { {0x1, 0x42 } }, }, - { - "LD_ABS with helper changing skb data", - { }, - INTERNAL, - { 0x34 }, - { { ETH_HLEN, 42 } }, - .fill_helper = bpf_fill_ld_abs_vlan_push_pop2, - }, /* Checking interpreter vs JIT wrt signed extended imms. */ { "JNE signed compare, test 1", diff --git a/net/8021q/vlan_dev.c b/net/8021q/vlan_dev.c index 236452ebbd9e..546af0e73ac3 100644 --- a/net/8021q/vlan_dev.c +++ b/net/8021q/vlan_dev.c @@ -215,7 +215,9 @@ int vlan_dev_set_egress_priority(const struct net_device *dev, return 0; } -/* Flags are defined in the vlan_flags enum in include/linux/if_vlan.h file. */ +/* Flags are defined in the vlan_flags enum in + * include/uapi/linux/if_vlan.h file. + */ int vlan_dev_change_flags(const struct net_device *dev, u32 flags, u32 mask) { struct vlan_dev_priv *vlan = vlan_dev_priv(dev); diff --git a/net/9p/mod.c b/net/9p/mod.c index 6ab36aea7727..eb9777f05755 100644 --- a/net/9p/mod.c +++ b/net/9p/mod.c @@ -104,7 +104,7 @@ EXPORT_SYMBOL(v9fs_unregister_trans); /** * v9fs_get_trans_by_name - get transport with the matching name - * @name: string identifying transport + * @s: string identifying transport * */ struct p9_trans_module *v9fs_get_trans_by_name(char *s) diff --git a/net/Kconfig b/net/Kconfig index 0428f12c25c2..df8d45ef47d8 100644 --- a/net/Kconfig +++ b/net/Kconfig @@ -59,6 +59,7 @@ source "net/tls/Kconfig" source "net/xfrm/Kconfig" source "net/iucv/Kconfig" source "net/smc/Kconfig" +source "net/xdp/Kconfig" config INET bool "TCP/IP networking" @@ -407,6 +408,9 @@ config GRO_CELLS bool default n +config SOCK_VALIDATE_XMIT + bool + config NET_DEVLINK tristate "Network physical/parent device Netlink interface" help @@ -423,6 +427,9 @@ config MAY_USE_DEVLINK on MAY_USE_DEVLINK to ensure they do not cause link errors when devlink is a loadable module and the driver using it is built-in. +config PAGE_POOL + bool + endif # if NET # Used by archs to tell that they support BPF JIT compiler plus which flavour. diff --git a/net/Makefile b/net/Makefile index a6147c61b174..77aaddedbd29 100644 --- a/net/Makefile +++ b/net/Makefile @@ -85,3 +85,4 @@ obj-y += l3mdev/ endif obj-$(CONFIG_QRTR) += qrtr/ obj-$(CONFIG_NET_NCSI) += ncsi/ +obj-$(CONFIG_XDP_SOCKETS) += xdp/ diff --git a/net/bpf/test_run.c b/net/bpf/test_run.c index 2ced48662c1f..68c3578343b4 100644 --- a/net/bpf/test_run.c +++ b/net/bpf/test_run.c @@ -170,7 +170,8 @@ int bpf_prog_test_run_xdp(struct bpf_prog *prog, const union bpf_attr *kattr, xdp.rxq = &rxqueue->xdp_rxq; retval = bpf_test_run(prog, &xdp, repeat, &duration); - if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN) + if (xdp.data != data + XDP_PACKET_HEADROOM + NET_IP_ALIGN || + xdp.data_end != xdp.data + size) size = xdp.data_end - xdp.data; ret = bpf_test_finish(kattr, uattr, xdp.data, size, retval, duration); kfree(data); diff --git a/net/bridge/br.c b/net/bridge/br.c index 671d13c10f6f..b0a0b82e2d91 100644 --- a/net/bridge/br.c +++ b/net/bridge/br.c @@ -34,6 +34,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v struct net_device *dev = netdev_notifier_info_to_dev(ptr); struct net_bridge_port *p; struct net_bridge *br; + bool notified = false; bool changed_addr; int err; @@ -67,7 +68,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v break; case NETDEV_CHANGE: - br_port_carrier_check(p); + br_port_carrier_check(p, ¬ified); break; case NETDEV_FEAT_CHANGE: @@ -76,8 +77,10 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v case NETDEV_DOWN: spin_lock_bh(&br->lock); - if (br->dev->flags & IFF_UP) + if (br->dev->flags & IFF_UP) { br_stp_disable_port(p); + notified = true; + } spin_unlock_bh(&br->lock); break; @@ -85,6 +88,7 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v if (netif_running(br->dev) && netif_oper_up(dev)) { spin_lock_bh(&br->lock); br_stp_enable_port(p); + notified = true; spin_unlock_bh(&br->lock); } break; @@ -110,8 +114,8 @@ static int br_device_event(struct notifier_block *unused, unsigned long event, v } /* Events that may cause spanning tree to refresh */ - if (event == NETDEV_CHANGEADDR || event == NETDEV_UP || - event == NETDEV_CHANGE || event == NETDEV_DOWN) + if (!notified && (event == NETDEV_CHANGEADDR || event == NETDEV_UP || + event == NETDEV_CHANGE || event == NETDEV_DOWN)) br_ifinfo_notify(RTM_NEWLINK, NULL, p); return NOTIFY_DONE; @@ -141,7 +145,7 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_ADD_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_add(br, p, fdb_info->addr, - fdb_info->vid); + fdb_info->vid, false); if (err) { err = notifier_from_errno(err); break; @@ -152,7 +156,7 @@ static int br_switchdev_event(struct notifier_block *unused, case SWITCHDEV_FDB_DEL_TO_BRIDGE: fdb_info = ptr; err = br_fdb_external_learn_del(br, p, fdb_info->addr, - fdb_info->vid); + fdb_info->vid, false); if (err) err = notifier_from_errno(err); break; diff --git a/net/bridge/br_fdb.c b/net/bridge/br_fdb.c index d9e69e4514be..b19e3104afd6 100644 --- a/net/bridge/br_fdb.c +++ b/net/bridge/br_fdb.c @@ -40,7 +40,7 @@ static struct kmem_cache *br_fdb_cache __read_mostly; static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, const unsigned char *addr, u16 vid); static void fdb_notify(struct net_bridge *br, - const struct net_bridge_fdb_entry *, int); + const struct net_bridge_fdb_entry *, int, bool); int __init br_fdb_init(void) { @@ -121,6 +121,28 @@ static struct net_bridge_fdb_entry *br_fdb_find(struct net_bridge *br, return fdb; } +struct net_device *br_fdb_find_port(const struct net_device *br_dev, + const unsigned char *addr, + __u16 vid) +{ + struct net_bridge_fdb_entry *f; + struct net_device *dev = NULL; + struct net_bridge *br; + + ASSERT_RTNL(); + + if (!netif_is_bridge_master(br_dev)) + return NULL; + + br = netdev_priv(br_dev); + f = br_fdb_find(br, addr, vid); + if (f && f->dst) + dev = f->dst->dev; + + return dev; +} +EXPORT_SYMBOL_GPL(br_fdb_find_port); + struct net_bridge_fdb_entry *br_fdb_find_rcu(struct net_bridge *br, const unsigned char *addr, __u16 vid) @@ -173,7 +195,8 @@ static void fdb_del_hw_addr(struct net_bridge *br, const unsigned char *addr) } } -static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) +static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f, + bool swdev_notify) { trace_fdb_delete(br, f); @@ -183,7 +206,7 @@ static void fdb_delete(struct net_bridge *br, struct net_bridge_fdb_entry *f) hlist_del_init_rcu(&f->fdb_node); rhashtable_remove_fast(&br->fdb_hash_tbl, &f->rhnode, br_fdb_rht_params); - fdb_notify(br, f, RTM_DELNEIGH); + fdb_notify(br, f, RTM_DELNEIGH, swdev_notify); call_rcu(&f->rcu, fdb_rcu_free); } @@ -219,7 +242,7 @@ static void fdb_delete_local(struct net_bridge *br, return; } - fdb_delete(br, f); + fdb_delete(br, f, true); } void br_fdb_find_delete_local(struct net_bridge *br, @@ -334,7 +357,7 @@ void br_fdb_cleanup(struct work_struct *work) } else { spin_lock_bh(&br->hash_lock); if (!hlist_unhashed(&f->fdb_node)) - fdb_delete(br, f); + fdb_delete(br, f, true); spin_unlock_bh(&br->hash_lock); } } @@ -354,7 +377,7 @@ void br_fdb_flush(struct net_bridge *br) spin_lock_bh(&br->hash_lock); hlist_for_each_entry_safe(f, tmp, &br->fdb_list, fdb_node) { if (!f->is_static) - fdb_delete(br, f); + fdb_delete(br, f, true); } spin_unlock_bh(&br->hash_lock); } @@ -383,7 +406,7 @@ void br_fdb_delete_by_port(struct net_bridge *br, if (f->is_local) fdb_delete_local(br, p, f); else - fdb_delete(br, f); + fdb_delete(br, f, true); } spin_unlock_bh(&br->hash_lock); } @@ -509,7 +532,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, return 0; br_warn(br, "adding interface %s with same address as a received packet (addr:%pM, vlan:%u)\n", source ? source->dev->name : br->dev->name, addr, vid); - fdb_delete(br, fdb); + fdb_delete(br, fdb, true); } fdb = fdb_create(br, source, addr, vid, 1, 1); @@ -517,7 +540,7 @@ static int fdb_insert(struct net_bridge *br, struct net_bridge_port *source, return -ENOMEM; fdb_add_hw_addr(br, addr); - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); return 0; } @@ -572,7 +595,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, fdb->added_by_user = 1; if (unlikely(fdb_modified)) { trace_br_fdb_update(br, source, addr, vid, added_by_user); - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); } } } else { @@ -583,7 +606,7 @@ void br_fdb_update(struct net_bridge *br, struct net_bridge_port *source, fdb->added_by_user = 1; trace_br_fdb_update(br, source, addr, vid, added_by_user); - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); } /* else we lose race and someone else inserts * it first, don't bother updating @@ -665,13 +688,15 @@ static inline size_t fdb_nlmsg_size(void) } static void fdb_notify(struct net_bridge *br, - const struct net_bridge_fdb_entry *fdb, int type) + const struct net_bridge_fdb_entry *fdb, int type, + bool swdev_notify) { struct net *net = dev_net(br->dev); struct sk_buff *skb; int err = -ENOBUFS; - br_switchdev_fdb_notify(fdb, type); + if (swdev_notify) + br_switchdev_fdb_notify(fdb, type); skb = nlmsg_new(fdb_nlmsg_size(), GFP_ATOMIC); if (skb == NULL) @@ -810,7 +835,7 @@ static int fdb_add_entry(struct net_bridge *br, struct net_bridge_port *source, fdb->used = jiffies; if (modified) { fdb->updated = jiffies; - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, true); } return 0; @@ -834,7 +859,7 @@ static int __br_fdb_add(struct ndmsg *ndm, struct net_bridge *br, rcu_read_unlock(); local_bh_enable(); } else if (ndm->ndm_flags & NTF_EXT_LEARNED) { - err = br_fdb_external_learn_add(br, p, addr, vid); + err = br_fdb_external_learn_add(br, p, addr, vid, true); } else { spin_lock_bh(&br->hash_lock); err = fdb_add_entry(br, p, addr, ndm->ndm_state, @@ -923,7 +948,7 @@ static int fdb_delete_by_addr_and_port(struct net_bridge *br, if (!fdb || fdb->dst != p) return -ENOENT; - fdb_delete(br, fdb); + fdb_delete(br, fdb, true); return 0; } @@ -1043,7 +1068,8 @@ void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p) } int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid) + const unsigned char *addr, u16 vid, + bool swdev_notify) { struct net_bridge_fdb_entry *fdb; bool modified = false; @@ -1061,7 +1087,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, goto err_unlock; } fdb->added_by_external_learn = 1; - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } else { fdb->updated = jiffies; @@ -1080,7 +1106,7 @@ int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, } if (modified) - fdb_notify(br, fdb, RTM_NEWNEIGH); + fdb_notify(br, fdb, RTM_NEWNEIGH, swdev_notify); } err_unlock: @@ -1090,7 +1116,8 @@ err_unlock: } int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid) + const unsigned char *addr, u16 vid, + bool swdev_notify) { struct net_bridge_fdb_entry *fdb; int err = 0; @@ -1099,7 +1126,7 @@ int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, fdb = br_fdb_find(br, addr, vid); if (fdb && fdb->added_by_external_learn) - fdb_delete(br, fdb); + fdb_delete(br, fdb, swdev_notify); else err = -ENOENT; diff --git a/net/bridge/br_forward.c b/net/bridge/br_forward.c index b4eed113d2ec..7a7fd672ccf2 100644 --- a/net/bridge/br_forward.c +++ b/net/bridge/br_forward.c @@ -274,8 +274,7 @@ void br_multicast_flood(struct net_bridge_mdb_entry *mdst, struct net_bridge_port *port, *lport, *rport; lport = p ? p->port : NULL; - rport = rp ? hlist_entry(rp, struct net_bridge_port, rlist) : - NULL; + rport = hlist_entry_safe(rp, struct net_bridge_port, rlist); if ((unsigned long)lport > (unsigned long)rport) { port = lport; diff --git a/net/bridge/br_if.c b/net/bridge/br_if.c index 5bb6681fa91e..05e42d86882d 100644 --- a/net/bridge/br_if.c +++ b/net/bridge/br_if.c @@ -64,7 +64,7 @@ static int port_cost(struct net_device *dev) /* Check for port carrier transitions. */ -void br_port_carrier_check(struct net_bridge_port *p) +void br_port_carrier_check(struct net_bridge_port *p, bool *notified) { struct net_device *dev = p->dev; struct net_bridge *br = p->br; @@ -73,16 +73,21 @@ void br_port_carrier_check(struct net_bridge_port *p) netif_running(dev) && netif_oper_up(dev)) p->path_cost = port_cost(dev); + *notified = false; if (!netif_running(br->dev)) return; spin_lock_bh(&br->lock); if (netif_running(dev) && netif_oper_up(dev)) { - if (p->state == BR_STATE_DISABLED) + if (p->state == BR_STATE_DISABLED) { br_stp_enable_port(p); + *notified = true; + } } else { - if (p->state != BR_STATE_DISABLED) + if (p->state != BR_STATE_DISABLED) { br_stp_disable_port(p); + *notified = true; + } } spin_unlock_bh(&br->lock); } diff --git a/net/bridge/br_private.h b/net/bridge/br_private.h index a7cb3ece5031..742f40aefdaf 100644 --- a/net/bridge/br_private.h +++ b/net/bridge/br_private.h @@ -553,9 +553,11 @@ int br_fdb_dump(struct sk_buff *skb, struct netlink_callback *cb, int br_fdb_sync_static(struct net_bridge *br, struct net_bridge_port *p); void br_fdb_unsync_static(struct net_bridge *br, struct net_bridge_port *p); int br_fdb_external_learn_add(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + bool swdev_notify); int br_fdb_external_learn_del(struct net_bridge *br, struct net_bridge_port *p, - const unsigned char *addr, u16 vid); + const unsigned char *addr, u16 vid, + bool swdev_notify); void br_fdb_offloaded_set(struct net_bridge *br, struct net_bridge_port *p, const unsigned char *addr, u16 vid); @@ -573,7 +575,7 @@ void br_flood(struct net_bridge *br, struct sk_buff *skb, enum br_pkt_type pkt_type, bool local_rcv, bool local_orig); /* br_if.c */ -void br_port_carrier_check(struct net_bridge_port *p); +void br_port_carrier_check(struct net_bridge_port *p, bool *notified); int br_add_bridge(struct net *net, const char *name); int br_del_bridge(struct net *net, const char *name); int br_add_if(struct net_bridge *br, struct net_device *dev, @@ -594,11 +596,22 @@ static inline bool br_rx_handler_check_rcu(const struct net_device *dev) return rcu_dereference(dev->rx_handler) == br_handle_frame; } +static inline bool br_rx_handler_check_rtnl(const struct net_device *dev) +{ + return rcu_dereference_rtnl(dev->rx_handler) == br_handle_frame; +} + static inline struct net_bridge_port *br_port_get_check_rcu(const struct net_device *dev) { return br_rx_handler_check_rcu(dev) ? br_port_get_rcu(dev) : NULL; } +static inline struct net_bridge_port * +br_port_get_check_rtnl(const struct net_device *dev) +{ + return br_rx_handler_check_rtnl(dev) ? br_port_get_rtnl_rcu(dev) : NULL; +} + /* br_ioctl.c */ int br_dev_ioctl(struct net_device *dev, struct ifreq *rq, int cmd); int br_ioctl_deviceless_stub(struct net *net, unsigned int cmd, diff --git a/net/bridge/br_switchdev.c b/net/bridge/br_switchdev.c index ee775f4ff76c..35474d49555d 100644 --- a/net/bridge/br_switchdev.c +++ b/net/bridge/br_switchdev.c @@ -102,13 +102,15 @@ int br_switchdev_set_port_flag(struct net_bridge_port *p, static void br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, - u16 vid, struct net_device *dev) + u16 vid, struct net_device *dev, + bool added_by_user) { struct switchdev_notifier_fdb_info info; unsigned long notifier_type; info.addr = mac; info.vid = vid; + info.added_by_user = added_by_user; notifier_type = adding ? SWITCHDEV_FDB_ADD_TO_DEVICE : SWITCHDEV_FDB_DEL_TO_DEVICE; call_switchdev_notifiers(notifier_type, dev, &info.info); } @@ -116,19 +118,21 @@ br_switchdev_fdb_call_notifiers(bool adding, const unsigned char *mac, void br_switchdev_fdb_notify(const struct net_bridge_fdb_entry *fdb, int type) { - if (!fdb->added_by_user || !fdb->dst) + if (!fdb->dst) return; switch (type) { case RTM_DELNEIGH: br_switchdev_fdb_call_notifiers(false, fdb->key.addr.addr, fdb->key.vlan_id, - fdb->dst->dev); + fdb->dst->dev, + fdb->added_by_user); break; case RTM_NEWNEIGH: br_switchdev_fdb_call_notifiers(true, fdb->key.addr.addr, fdb->key.vlan_id, - fdb->dst->dev); + fdb->dst->dev, + fdb->added_by_user); break; } } diff --git a/net/bridge/br_vlan.c b/net/bridge/br_vlan.c index 9896f4975353..dc832c0934c6 100644 --- a/net/bridge/br_vlan.c +++ b/net/bridge/br_vlan.c @@ -1149,3 +1149,44 @@ void br_vlan_get_stats(const struct net_bridge_vlan *v, stats->tx_packets += txpackets; } } + +int br_vlan_get_pvid(const struct net_device *dev, u16 *p_pvid) +{ + struct net_bridge_vlan_group *vg; + + ASSERT_RTNL(); + if (netif_is_bridge_master(dev)) + vg = br_vlan_group(netdev_priv(dev)); + else + return -EINVAL; + + *p_pvid = br_get_pvid(vg); + return 0; +} +EXPORT_SYMBOL_GPL(br_vlan_get_pvid); + +int br_vlan_get_info(const struct net_device *dev, u16 vid, + struct bridge_vlan_info *p_vinfo) +{ + struct net_bridge_vlan_group *vg; + struct net_bridge_vlan *v; + struct net_bridge_port *p; + + ASSERT_RTNL(); + p = br_port_get_check_rtnl(dev); + if (p) + vg = nbp_vlan_group(p); + else if (netif_is_bridge_master(dev)) + vg = br_vlan_group(netdev_priv(dev)); + else + return -EINVAL; + + v = br_vlan_find(vg, vid); + if (!v) + return -ENOENT; + + p_vinfo->vid = vid; + p_vinfo->flags = v->flags; + return 0; +} +EXPORT_SYMBOL_GPL(br_vlan_get_info); diff --git a/net/bridge/netfilter/Kconfig b/net/bridge/netfilter/Kconfig index f212447794bd..9a0159aebe1a 100644 --- a/net/bridge/netfilter/Kconfig +++ b/net/bridge/netfilter/Kconfig @@ -8,13 +8,6 @@ menuconfig NF_TABLES_BRIDGE bool "Ethernet Bridge nf_tables support" if NF_TABLES_BRIDGE - -config NFT_BRIDGE_META - tristate "Netfilter nf_table bridge meta support" - depends on NFT_META - help - Add support for bridge dedicated meta key. - config NFT_BRIDGE_REJECT tristate "Netfilter nf_tables bridge reject support" depends on NFT_REJECT && NFT_REJECT_IPV4 && NFT_REJECT_IPV6 diff --git a/net/bridge/netfilter/Makefile b/net/bridge/netfilter/Makefile index 4bc758dd4a8c..9b868861f21a 100644 --- a/net/bridge/netfilter/Makefile +++ b/net/bridge/netfilter/Makefile @@ -3,7 +3,6 @@ # Makefile for the netfilter modules for Link Layer filtering on a bridge. # -obj-$(CONFIG_NFT_BRIDGE_META) += nft_meta_bridge.o obj-$(CONFIG_NFT_BRIDGE_REJECT) += nft_reject_bridge.o # packet logging diff --git a/net/bridge/netfilter/ebtables.c b/net/bridge/netfilter/ebtables.c index 28a4c3490359..b286ed5596c3 100644 --- a/net/bridge/netfilter/ebtables.c +++ b/net/bridge/netfilter/ebtables.c @@ -101,7 +101,7 @@ ebt_do_match(struct ebt_entry_match *m, const struct sk_buff *skb, { par->match = m->u.match; par->matchinfo = m->data; - return m->u.match->match(skb, par) ? EBT_MATCH : EBT_NOMATCH; + return !m->u.match->match(skb, par); } static inline int @@ -177,6 +177,12 @@ struct ebt_entry *ebt_next_entry(const struct ebt_entry *entry) return (void *)entry + entry->next_offset; } +static inline const struct ebt_entry_target * +ebt_get_target_c(const struct ebt_entry *e) +{ + return ebt_get_target((struct ebt_entry *)e); +} + /* Do some firewalling */ unsigned int ebt_do_table(struct sk_buff *skb, const struct nf_hook_state *state, @@ -230,8 +236,7 @@ unsigned int ebt_do_table(struct sk_buff *skb, */ EBT_WATCHER_ITERATE(point, ebt_do_watcher, skb, &acpar); - t = (struct ebt_entry_target *) - (((char *)point) + point->target_offset); + t = ebt_get_target_c(point); /* standard target */ if (!t->u.target->target) verdict = ((struct ebt_standard_target *)t)->verdict; @@ -343,6 +348,16 @@ find_table_lock(struct net *net, const char *name, int *error, "ebtable_", error, mutex); } +static inline void ebt_free_table_info(struct ebt_table_info *info) +{ + int i; + + if (info->chainstack) { + for_each_possible_cpu(i) + vfree(info->chainstack[i]); + vfree(info->chainstack); + } +} static inline int ebt_check_match(struct ebt_entry_match *m, struct xt_mtchk_param *par, unsigned int *cnt) @@ -627,7 +642,7 @@ ebt_cleanup_entry(struct ebt_entry *e, struct net *net, unsigned int *cnt) return 1; EBT_WATCHER_ITERATE(e, ebt_cleanup_watcher, net, NULL); EBT_MATCH_ITERATE(e, ebt_cleanup_match, net, NULL); - t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + t = ebt_get_target(e); par.net = net; par.target = t->u.target; @@ -706,7 +721,7 @@ ebt_check_entry(struct ebt_entry *e, struct net *net, ret = EBT_WATCHER_ITERATE(e, ebt_check_watcher, &tgpar, &j); if (ret != 0) goto cleanup_watchers; - t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + t = ebt_get_target(e); gap = e->next_offset - e->target_offset; target = xt_request_find_target(NFPROTO_BRIDGE, t->u.name, 0); @@ -779,8 +794,7 @@ static int check_chainloops(const struct ebt_entries *chain, struct ebt_cl_stack if (pos == nentries) continue; } - t = (struct ebt_entry_target *) - (((char *)e) + e->target_offset); + t = ebt_get_target_c(e); if (strcmp(t->u.name, EBT_STANDARD_TARGET)) goto letscontinue; if (e->target_offset + sizeof(struct ebt_standard_target) > @@ -975,7 +989,7 @@ static void get_counters(const struct ebt_counter *oldcounters, static int do_replace_finish(struct net *net, struct ebt_replace *repl, struct ebt_table_info *newinfo) { - int ret, i; + int ret; struct ebt_counter *counterstmp = NULL; /* used to be able to unlock earlier */ struct ebt_table_info *table; @@ -1051,13 +1065,8 @@ static int do_replace_finish(struct net *net, struct ebt_replace *repl, ebt_cleanup_entry, net, NULL); vfree(table->entries); - if (table->chainstack) { - for_each_possible_cpu(i) - vfree(table->chainstack[i]); - vfree(table->chainstack); - } + ebt_free_table_info(table); vfree(table); - vfree(counterstmp); #ifdef CONFIG_AUDIT @@ -1078,11 +1087,7 @@ free_iterate: free_counterstmp: vfree(counterstmp); /* can be initialized in translate_table() */ - if (newinfo->chainstack) { - for_each_possible_cpu(i) - vfree(newinfo->chainstack[i]); - vfree(newinfo->chainstack); - } + ebt_free_table_info(newinfo); return ret; } @@ -1147,8 +1152,6 @@ free_newinfo: static void __ebt_unregister_table(struct net *net, struct ebt_table *table) { - int i; - mutex_lock(&ebt_mutex); list_del(&table->list); mutex_unlock(&ebt_mutex); @@ -1157,11 +1160,7 @@ static void __ebt_unregister_table(struct net *net, struct ebt_table *table) if (table->private->nentries) module_put(table->me); vfree(table->private->entries); - if (table->private->chainstack) { - for_each_possible_cpu(i) - vfree(table->private->chainstack[i]); - vfree(table->private->chainstack); - } + ebt_free_table_info(table->private); vfree(table->private); kfree(table); } @@ -1263,11 +1262,7 @@ int ebt_register_table(struct net *net, const struct ebt_table *input_table, free_unlock: mutex_unlock(&ebt_mutex); free_chainstack: - if (newinfo->chainstack) { - for_each_possible_cpu(i) - vfree(newinfo->chainstack[i]); - vfree(newinfo->chainstack); - } + ebt_free_table_info(newinfo); vfree(newinfo->entries); free_newinfo: vfree(newinfo); @@ -1405,7 +1400,7 @@ static inline int ebt_entry_to_user(struct ebt_entry *e, const char *base, return -EFAULT; hlp = ubase + (((char *)e + e->target_offset) - base); - t = (struct ebt_entry_target *)(((char *)e) + e->target_offset); + t = ebt_get_target_c(e); ret = EBT_MATCH_ITERATE(e, ebt_match_to_user, base, ubase); if (ret != 0) @@ -1746,7 +1741,7 @@ static int compat_copy_entry_to_user(struct ebt_entry *e, void __user **dstptr, return ret; target_offset = e->target_offset - (origsize - *size); - t = (struct ebt_entry_target *) ((char *) e + e->target_offset); + t = ebt_get_target(e); ret = compat_target_to_user(t, dstptr, size); if (ret) @@ -1794,7 +1789,7 @@ static int compat_calc_entry(const struct ebt_entry *e, EBT_MATCH_ITERATE(e, compat_calc_match, &off); EBT_WATCHER_ITERATE(e, compat_calc_watcher, &off); - t = (const struct ebt_entry_target *) ((char *) e + e->target_offset); + t = ebt_get_target_c(e); off += xt_compat_target_offset(t->u.target); off += ebt_compat_entry_padsize(); diff --git a/net/bridge/netfilter/nft_meta_bridge.c b/net/bridge/netfilter/nft_meta_bridge.c deleted file mode 100644 index bb63c9aed55d..000000000000 --- a/net/bridge/netfilter/nft_meta_bridge.c +++ /dev/null @@ -1,135 +0,0 @@ -/* - * Copyright (c) 2014 Intel Corporation - * - * This program is free software; you can redistribute it and/or modify - * it under the terms of the GNU General Public License version 2 as - * published by the Free Software Foundation. - * - */ - -#include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> -#include <linux/netlink.h> -#include <linux/netfilter.h> -#include <linux/netfilter/nf_tables.h> -#include <net/netfilter/nf_tables.h> -#include <net/netfilter/nft_meta.h> - -#include "../br_private.h" - -static void nft_meta_bridge_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) -{ - const struct nft_meta *priv = nft_expr_priv(expr); - const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); - u32 *dest = ®s->data[priv->dreg]; - const struct net_bridge_port *p; - - switch (priv->key) { - case NFT_META_BRI_IIFNAME: - if (in == NULL || (p = br_port_get_rcu(in)) == NULL) - goto err; - break; - case NFT_META_BRI_OIFNAME: - if (out == NULL || (p = br_port_get_rcu(out)) == NULL) - goto err; - break; - default: - goto out; - } - - strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); - return; -out: - return nft_meta_get_eval(expr, regs, pkt); -err: - regs->verdict.code = NFT_BREAK; -} - -static int nft_meta_bridge_get_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) -{ - struct nft_meta *priv = nft_expr_priv(expr); - unsigned int len; - - priv->key = ntohl(nla_get_be32(tb[NFTA_META_KEY])); - switch (priv->key) { - case NFT_META_BRI_IIFNAME: - case NFT_META_BRI_OIFNAME: - len = IFNAMSIZ; - break; - default: - return nft_meta_get_init(ctx, expr, tb); - } - - priv->dreg = nft_parse_register(tb[NFTA_META_DREG]); - return nft_validate_register_store(ctx, priv->dreg, NULL, - NFT_DATA_VALUE, len); -} - -static struct nft_expr_type nft_meta_bridge_type; -static const struct nft_expr_ops nft_meta_bridge_get_ops = { - .type = &nft_meta_bridge_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), - .eval = nft_meta_bridge_get_eval, - .init = nft_meta_bridge_get_init, - .dump = nft_meta_get_dump, -}; - -static const struct nft_expr_ops nft_meta_bridge_set_ops = { - .type = &nft_meta_bridge_type, - .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), - .eval = nft_meta_set_eval, - .init = nft_meta_set_init, - .destroy = nft_meta_set_destroy, - .dump = nft_meta_set_dump, - .validate = nft_meta_set_validate, -}; - -static const struct nft_expr_ops * -nft_meta_bridge_select_ops(const struct nft_ctx *ctx, - const struct nlattr * const tb[]) -{ - if (tb[NFTA_META_KEY] == NULL) - return ERR_PTR(-EINVAL); - - if (tb[NFTA_META_DREG] && tb[NFTA_META_SREG]) - return ERR_PTR(-EINVAL); - - if (tb[NFTA_META_DREG]) - return &nft_meta_bridge_get_ops; - - if (tb[NFTA_META_SREG]) - return &nft_meta_bridge_set_ops; - - return ERR_PTR(-EINVAL); -} - -static struct nft_expr_type nft_meta_bridge_type __read_mostly = { - .family = NFPROTO_BRIDGE, - .name = "meta", - .select_ops = nft_meta_bridge_select_ops, - .policy = nft_meta_policy, - .maxattr = NFTA_META_MAX, - .owner = THIS_MODULE, -}; - -static int __init nft_meta_bridge_module_init(void) -{ - return nft_register_expr(&nft_meta_bridge_type); -} - -static void __exit nft_meta_bridge_module_exit(void) -{ - nft_unregister_expr(&nft_meta_bridge_type); -} - -module_init(nft_meta_bridge_module_init); -module_exit(nft_meta_bridge_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com>"); -MODULE_ALIAS_NFT_AF_EXPR(AF_BRIDGE, "meta"); diff --git a/net/core/Makefile b/net/core/Makefile index 6dbbba8c57ae..7080417f8bc8 100644 --- a/net/core/Makefile +++ b/net/core/Makefile @@ -14,6 +14,7 @@ obj-y += dev.o ethtool.o dev_addr_lists.o dst.o netevent.o \ fib_notifier.o xdp.o obj-y += net-sysfs.o +obj-$(CONFIG_PAGE_POOL) += page_pool.o obj-$(CONFIG_PROC_FS) += net-procfs.o obj-$(CONFIG_NET_PKTGEN) += pktgen.o obj-$(CONFIG_NETPOLL) += netpoll.o diff --git a/net/core/dev.c b/net/core/dev.c index af0558b00c6c..9f4390182384 100644 --- a/net/core/dev.c +++ b/net/core/dev.c @@ -1285,6 +1285,7 @@ int dev_set_alias(struct net_device *dev, const char *alias, size_t len) return len; } +EXPORT_SYMBOL(dev_set_alias); /** * dev_get_alias - get ifalias of a device @@ -1586,7 +1587,7 @@ const char *netdev_cmd_to_name(enum netdev_cmd cmd) N(UDP_TUNNEL_DROP_INFO) N(CHANGE_TX_QUEUE_LEN) N(CVLAN_FILTER_PUSH_INFO) N(CVLAN_FILTER_DROP_INFO) N(SVLAN_FILTER_PUSH_INFO) N(SVLAN_FILTER_DROP_INFO) - }; + } #undef N return "UNKNOWN_NETDEV_EVENT"; } @@ -1754,38 +1755,38 @@ int call_netdevice_notifiers(unsigned long val, struct net_device *dev) EXPORT_SYMBOL(call_netdevice_notifiers); #ifdef CONFIG_NET_INGRESS -static struct static_key ingress_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(ingress_needed_key); void net_inc_ingress_queue(void) { - static_key_slow_inc(&ingress_needed); + static_branch_inc(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_ingress_queue); void net_dec_ingress_queue(void) { - static_key_slow_dec(&ingress_needed); + static_branch_dec(&ingress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_ingress_queue); #endif #ifdef CONFIG_NET_EGRESS -static struct static_key egress_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(egress_needed_key); void net_inc_egress_queue(void) { - static_key_slow_inc(&egress_needed); + static_branch_inc(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_inc_egress_queue); void net_dec_egress_queue(void) { - static_key_slow_dec(&egress_needed); + static_branch_dec(&egress_needed_key); } EXPORT_SYMBOL_GPL(net_dec_egress_queue); #endif -static struct static_key netstamp_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(netstamp_needed_key); #ifdef HAVE_JUMP_LABEL static atomic_t netstamp_needed_deferred; static atomic_t netstamp_wanted; @@ -1796,9 +1797,9 @@ static void netstamp_clear(struct work_struct *work) wanted = atomic_add_return(deferred, &netstamp_wanted); if (wanted > 0) - static_key_enable(&netstamp_needed); + static_branch_enable(&netstamp_needed_key); else - static_key_disable(&netstamp_needed); + static_branch_disable(&netstamp_needed_key); } static DECLARE_WORK(netstamp_work, netstamp_clear); #endif @@ -1818,7 +1819,7 @@ void net_enable_timestamp(void) atomic_inc(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else - static_key_slow_inc(&netstamp_needed); + static_branch_inc(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_enable_timestamp); @@ -1838,7 +1839,7 @@ void net_disable_timestamp(void) atomic_dec(&netstamp_needed_deferred); schedule_work(&netstamp_work); #else - static_key_slow_dec(&netstamp_needed); + static_branch_dec(&netstamp_needed_key); #endif } EXPORT_SYMBOL(net_disable_timestamp); @@ -1846,15 +1847,15 @@ EXPORT_SYMBOL(net_disable_timestamp); static inline void net_timestamp_set(struct sk_buff *skb) { skb->tstamp = 0; - if (static_key_false(&netstamp_needed)) + if (static_branch_unlikely(&netstamp_needed_key)) __net_timestamp(skb); } -#define net_timestamp_check(COND, SKB) \ - if (static_key_false(&netstamp_needed)) { \ - if ((COND) && !(SKB)->tstamp) \ - __net_timestamp(SKB); \ - } \ +#define net_timestamp_check(COND, SKB) \ + if (static_branch_unlikely(&netstamp_needed_key)) { \ + if ((COND) && !(SKB)->tstamp) \ + __net_timestamp(SKB); \ + } \ bool is_skb_forwardable(const struct net_device *dev, const struct sk_buff *skb) { @@ -2614,17 +2615,16 @@ EXPORT_SYMBOL(netif_device_attach); * Returns a Tx hash based on the given packet descriptor a Tx queues' number * to be used as a distribution range. */ -u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, - unsigned int num_tx_queues) +static u16 skb_tx_hash(const struct net_device *dev, struct sk_buff *skb) { u32 hash; u16 qoffset = 0; - u16 qcount = num_tx_queues; + u16 qcount = dev->real_num_tx_queues; if (skb_rx_queue_recorded(skb)) { hash = skb_get_rx_queue(skb); - while (unlikely(hash >= num_tx_queues)) - hash -= num_tx_queues; + while (unlikely(hash >= qcount)) + hash -= qcount; return hash; } @@ -2637,7 +2637,6 @@ u16 __skb_tx_hash(const struct net_device *dev, struct sk_buff *skb, return (u16) reciprocal_scale(skb_get_hash(skb), qcount) + qoffset; } -EXPORT_SYMBOL(__skb_tx_hash); static void skb_warn_bad_offload(const struct sk_buff *skb) { @@ -3113,6 +3112,10 @@ static struct sk_buff *validate_xmit_skb(struct sk_buff *skb, struct net_device if (unlikely(!skb)) goto out_null; + skb = sk_validate_xmit_skb(skb, dev); + if (unlikely(!skb)) + goto out_null; + if (netif_needs_gso(skb, features)) { struct sk_buff *segs; @@ -3529,7 +3532,7 @@ static int __dev_queue_xmit(struct sk_buff *skb, void *accel_priv) #ifdef CONFIG_NET_CLS_ACT skb->tc_at_ingress = 0; # ifdef CONFIG_NET_EGRESS - if (static_key_false(&egress_needed)) { + if (static_branch_unlikely(&egress_needed_key)) { skb = sch_handle_egress(skb, &rc, dev); if (!skb) goto out; @@ -3624,6 +3627,44 @@ int dev_queue_xmit_accel(struct sk_buff *skb, void *accel_priv) } EXPORT_SYMBOL(dev_queue_xmit_accel); +int dev_direct_xmit(struct sk_buff *skb, u16 queue_id) +{ + struct net_device *dev = skb->dev; + struct sk_buff *orig_skb = skb; + struct netdev_queue *txq; + int ret = NETDEV_TX_BUSY; + bool again = false; + + if (unlikely(!netif_running(dev) || + !netif_carrier_ok(dev))) + goto drop; + + skb = validate_xmit_skb_list(skb, dev, &again); + if (skb != orig_skb) + goto drop; + + skb_set_queue_mapping(skb, queue_id); + txq = skb_get_tx_queue(dev, skb); + + local_bh_disable(); + + HARD_TX_LOCK(dev, txq, smp_processor_id()); + if (!netif_xmit_frozen_or_drv_stopped(txq)) + ret = netdev_start_xmit(skb, dev, txq, false); + HARD_TX_UNLOCK(dev, txq); + + local_bh_enable(); + + if (!dev_xmit_complete(ret)) + kfree_skb(skb); + + return ret; +drop: + atomic_long_inc(&dev->tx_dropped); + kfree_skb_list(skb); + return NET_XMIT_DROP; +} +EXPORT_SYMBOL(dev_direct_xmit); /************************************************************************* * Receiver routines @@ -3993,12 +4034,12 @@ static struct netdev_rx_queue *netif_get_rxqueue(struct sk_buff *skb) } static u32 netif_receive_generic_xdp(struct sk_buff *skb, + struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct netdev_rx_queue *rxqueue; + void *orig_data, *orig_data_end; u32 metalen, act = XDP_DROP; - struct xdp_buff xdp; - void *orig_data; int hlen, off; u32 mac_len; @@ -4033,31 +4074,42 @@ static u32 netif_receive_generic_xdp(struct sk_buff *skb, */ mac_len = skb->data - skb_mac_header(skb); hlen = skb_headlen(skb) + mac_len; - xdp.data = skb->data - mac_len; - xdp.data_meta = xdp.data; - xdp.data_end = xdp.data + hlen; - xdp.data_hard_start = skb->data - skb_headroom(skb); - orig_data = xdp.data; + xdp->data = skb->data - mac_len; + xdp->data_meta = xdp->data; + xdp->data_end = xdp->data + hlen; + xdp->data_hard_start = skb->data - skb_headroom(skb); + orig_data_end = xdp->data_end; + orig_data = xdp->data; rxqueue = netif_get_rxqueue(skb); - xdp.rxq = &rxqueue->xdp_rxq; + xdp->rxq = &rxqueue->xdp_rxq; - act = bpf_prog_run_xdp(xdp_prog, &xdp); + act = bpf_prog_run_xdp(xdp_prog, xdp); - off = xdp.data - orig_data; + off = xdp->data - orig_data; if (off > 0) __skb_pull(skb, off); else if (off < 0) __skb_push(skb, -off); skb->mac_header += off; + /* check if bpf_xdp_adjust_tail was used. it can only "shrink" + * pckt. + */ + off = orig_data_end - xdp->data_end; + if (off != 0) { + skb_set_tail_pointer(skb, xdp->data_end - xdp->data); + skb->len -= off; + + } + switch (act) { case XDP_REDIRECT: case XDP_TX: __skb_push(skb, mac_len); break; case XDP_PASS: - metalen = xdp.data - xdp.data_meta; + metalen = xdp->data - xdp->data_meta; if (metalen) skb_metadata_set(skb, metalen); break; @@ -4102,22 +4154,24 @@ void generic_xdp_tx(struct sk_buff *skb, struct bpf_prog *xdp_prog) } EXPORT_SYMBOL_GPL(generic_xdp_tx); -static struct static_key generic_xdp_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(generic_xdp_needed_key); int do_xdp_generic(struct bpf_prog *xdp_prog, struct sk_buff *skb) { if (xdp_prog) { - u32 act = netif_receive_generic_xdp(skb, xdp_prog); + struct xdp_buff xdp; + u32 act; int err; + act = netif_receive_generic_xdp(skb, &xdp, xdp_prog); if (act != XDP_PASS) { switch (act) { case XDP_REDIRECT: err = xdp_do_generic_redirect(skb->dev, skb, - xdp_prog); + &xdp, xdp_prog); if (err) goto out_redir; - /* fallthru to submit skb */ + break; case XDP_TX: generic_xdp_tx(skb, xdp_prog); break; @@ -4140,7 +4194,7 @@ static int netif_rx_internal(struct sk_buff *skb) trace_netif_rx(skb); - if (static_key_false(&generic_xdp_needed)) { + if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret; preempt_disable(); @@ -4512,7 +4566,7 @@ another_round: skip_taps: #ifdef CONFIG_NET_INGRESS - if (static_key_false(&ingress_needed)) { + if (static_branch_unlikely(&ingress_needed_key)) { skb = sch_handle_ingress(skb, &pt_prev, &ret, orig_dev); if (!skb) goto out; @@ -4672,9 +4726,9 @@ static int generic_xdp_install(struct net_device *dev, struct netdev_bpf *xdp) bpf_prog_put(old); if (old && !new) { - static_key_slow_dec(&generic_xdp_needed); + static_branch_dec(&generic_xdp_needed_key); } else if (new && !old) { - static_key_slow_inc(&generic_xdp_needed); + static_branch_inc(&generic_xdp_needed_key); dev_disable_lro(dev); dev_disable_gro_hw(dev); } @@ -4702,7 +4756,7 @@ static int netif_receive_skb_internal(struct sk_buff *skb) if (skb_defer_rx_timestamp(skb)) return NET_RX_SUCCESS; - if (static_key_false(&generic_xdp_needed)) { + if (static_branch_unlikely(&generic_xdp_needed_key)) { int ret; preempt_disable(); @@ -7870,6 +7924,8 @@ int register_netdevice(struct net_device *dev) int ret; struct net *net = dev_net(dev); + BUILD_BUG_ON(sizeof(netdev_features_t) * BITS_PER_BYTE < + NETDEV_FEATURE_COUNT); BUG_ON(dev_boot_phase); ASSERT_RTNL(); diff --git a/net/core/dst.c b/net/core/dst.c index 007aa0b08291..2d9b37f8944a 100644 --- a/net/core/dst.c +++ b/net/core/dst.c @@ -58,6 +58,7 @@ const struct dst_metrics dst_default_metrics = { */ .refcnt = REFCOUNT_INIT(1), }; +EXPORT_SYMBOL(dst_default_metrics); void dst_init(struct dst_entry *dst, struct dst_ops *ops, struct net_device *dev, int initial_ref, int initial_obsolete, diff --git a/net/core/ethtool.c b/net/core/ethtool.c index ba02f0dfe85c..c15075dc7572 100644 --- a/net/core/ethtool.c +++ b/net/core/ethtool.c @@ -92,6 +92,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_GSO_PARTIAL_BIT] = "tx-gso-partial", [NETIF_F_GSO_SCTP_BIT] = "tx-sctp-segmentation", [NETIF_F_GSO_ESP_BIT] = "tx-esp-segmentation", + [NETIF_F_GSO_UDP_L4_BIT] = "tx-udp-segmentation", [NETIF_F_FCOE_CRC_BIT] = "tx-checksum-fcoe-crc", [NETIF_F_SCTP_CRC_BIT] = "tx-checksum-sctp", @@ -109,6 +110,7 @@ static const char netdev_features_strings[NETDEV_FEATURE_COUNT][ETH_GSTRING_LEN] [NETIF_F_HW_ESP_TX_CSUM_BIT] = "esp-tx-csum-hw-offload", [NETIF_F_RX_UDP_TUNNEL_PORT_BIT] = "rx-udp_tunnel-port-offload", [NETIF_F_HW_TLS_RECORD_BIT] = "tls-hw-record", + [NETIF_F_HW_TLS_TX_BIT] = "tls-hw-tx-offload", }; static const char @@ -210,23 +212,6 @@ static int ethtool_set_features(struct net_device *dev, void __user *useraddr) return ret; } -static int phy_get_sset_count(struct phy_device *phydev) -{ - int ret; - - if (phydev->drv->get_sset_count && - phydev->drv->get_strings && - phydev->drv->get_stats) { - mutex_lock(&phydev->lock); - ret = phydev->drv->get_sset_count(phydev); - mutex_unlock(&phydev->lock); - - return ret; - } - - return -EOPNOTSUPP; -} - static int __ethtool_get_sset_count(struct net_device *dev, int sset) { const struct ethtool_ops *ops = dev->ethtool_ops; @@ -243,12 +228,9 @@ static int __ethtool_get_sset_count(struct net_device *dev, int sset) if (sset == ETH_SS_PHY_TUNABLES) return ARRAY_SIZE(phy_tunable_strings); - if (sset == ETH_SS_PHY_STATS) { - if (dev->phydev) - return phy_get_sset_count(dev->phydev); - else - return -EOPNOTSUPP; - } + if (sset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + return phy_ethtool_get_sset_count(dev->phydev); if (ops->get_sset_count && ops->get_strings) return ops->get_sset_count(dev, sset); @@ -271,17 +253,10 @@ static void __ethtool_get_strings(struct net_device *dev, memcpy(data, tunable_strings, sizeof(tunable_strings)); else if (stringset == ETH_SS_PHY_TUNABLES) memcpy(data, phy_tunable_strings, sizeof(phy_tunable_strings)); - else if (stringset == ETH_SS_PHY_STATS) { - struct phy_device *phydev = dev->phydev; - - if (phydev) { - mutex_lock(&phydev->lock); - phydev->drv->get_strings(phydev, data); - mutex_unlock(&phydev->lock); - } else { - return; - } - } else + else if (stringset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + phy_ethtool_get_strings(dev->phydev, data); + else /* ops->get_strings is valid because checked earlier */ ops->get_strings(dev, stringset, data); } @@ -1998,15 +1973,19 @@ static int ethtool_get_stats(struct net_device *dev, void __user *useraddr) static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) { - struct ethtool_stats stats; + const struct ethtool_ops *ops = dev->ethtool_ops; struct phy_device *phydev = dev->phydev; + struct ethtool_stats stats; u64 *data; int ret, n_stats; - if (!phydev) + if (!phydev && (!ops->get_ethtool_phy_stats || !ops->get_sset_count)) return -EOPNOTSUPP; - n_stats = phy_get_sset_count(phydev); + if (dev->phydev && !ops->get_ethtool_phy_stats) + n_stats = phy_ethtool_get_sset_count(dev->phydev); + else + n_stats = ops->get_sset_count(dev, ETH_SS_PHY_STATS); if (n_stats < 0) return n_stats; if (n_stats > S32_MAX / sizeof(u64)) @@ -2021,9 +2000,13 @@ static int ethtool_get_phy_stats(struct net_device *dev, void __user *useraddr) if (n_stats && !data) return -ENOMEM; - mutex_lock(&phydev->lock); - phydev->drv->get_stats(phydev, &stats, data); - mutex_unlock(&phydev->lock); + if (dev->phydev && !ops->get_ethtool_phy_stats) { + ret = phy_ethtool_get_stats(dev->phydev, &stats, data); + if (ret < 0) + return ret; + } else { + ops->get_ethtool_phy_stats(dev, &stats, data); + } ret = -EFAULT; if (copy_to_user(useraddr, &stats, sizeof(stats))) diff --git a/net/core/fib_rules.c b/net/core/fib_rules.c index 33958f84c173..126ffc5bc630 100644 --- a/net/core/fib_rules.c +++ b/net/core/fib_rules.c @@ -387,247 +387,304 @@ unsigned int fib_rules_seq_read(struct net *net, int family) } EXPORT_SYMBOL_GPL(fib_rules_seq_read); -static int validate_rulemsg(struct fib_rule_hdr *frh, struct nlattr **tb, - struct fib_rules_ops *ops) -{ - int err = -EINVAL; - - if (frh->src_len) - if (tb[FRA_SRC] == NULL || - frh->src_len > (ops->addr_size * 8) || - nla_len(tb[FRA_SRC]) != ops->addr_size) - goto errout; - - if (frh->dst_len) - if (tb[FRA_DST] == NULL || - frh->dst_len > (ops->addr_size * 8) || - nla_len(tb[FRA_DST]) != ops->addr_size) - goto errout; - - err = 0; -errout: - return err; -} - -static int rule_exists(struct fib_rules_ops *ops, struct fib_rule_hdr *frh, - struct nlattr **tb, struct fib_rule *rule) +static struct fib_rule *rule_find(struct fib_rules_ops *ops, + struct fib_rule_hdr *frh, + struct nlattr **tb, + struct fib_rule *rule, + bool user_priority) { struct fib_rule *r; list_for_each_entry(r, &ops->rules_list, list) { - if (r->action != rule->action) + if (rule->action && r->action != rule->action) continue; - if (r->table != rule->table) + if (rule->table && r->table != rule->table) continue; - if (r->pref != rule->pref) + if (user_priority && r->pref != rule->pref) continue; - if (memcmp(r->iifname, rule->iifname, IFNAMSIZ)) + if (rule->iifname[0] && + memcmp(r->iifname, rule->iifname, IFNAMSIZ)) continue; - if (memcmp(r->oifname, rule->oifname, IFNAMSIZ)) + if (rule->oifname[0] && + memcmp(r->oifname, rule->oifname, IFNAMSIZ)) continue; - if (r->mark != rule->mark) + if (rule->mark && r->mark != rule->mark) continue; - if (r->mark_mask != rule->mark_mask) + if (rule->mark_mask && r->mark_mask != rule->mark_mask) continue; - if (r->tun_id != rule->tun_id) + if (rule->tun_id && r->tun_id != rule->tun_id) continue; if (r->fr_net != rule->fr_net) continue; - if (r->l3mdev != rule->l3mdev) + if (rule->l3mdev && r->l3mdev != rule->l3mdev) continue; - if (!uid_eq(r->uid_range.start, rule->uid_range.start) || - !uid_eq(r->uid_range.end, rule->uid_range.end)) + if (uid_range_set(&rule->uid_range) && + (!uid_eq(r->uid_range.start, rule->uid_range.start) || + !uid_eq(r->uid_range.end, rule->uid_range.end))) continue; - if (r->ip_proto != rule->ip_proto) + if (rule->ip_proto && r->ip_proto != rule->ip_proto) continue; - if (!fib_rule_port_range_compare(&r->sport_range, + if (fib_rule_port_range_set(&rule->sport_range) && + !fib_rule_port_range_compare(&r->sport_range, &rule->sport_range)) continue; - if (!fib_rule_port_range_compare(&r->dport_range, + if (fib_rule_port_range_set(&rule->dport_range) && + !fib_rule_port_range_compare(&r->dport_range, &rule->dport_range)) continue; if (!ops->compare(r, frh, tb)) continue; - return 1; + return r; + } + + return NULL; +} + +#ifdef CONFIG_NET_L3_MASTER_DEV +static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, + struct netlink_ext_ack *extack) +{ + nlrule->l3mdev = nla_get_u8(nla); + if (nlrule->l3mdev != 1) { + NL_SET_ERR_MSG(extack, "Invalid l3mdev attribute"); + return -1; } + return 0; } +#else +static int fib_nl2rule_l3mdev(struct nlattr *nla, struct fib_rule *nlrule, + struct netlink_ext_ack *extack) +{ + NL_SET_ERR_MSG(extack, "l3mdev support is not enabled in kernel"); + return -1; +} +#endif -int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, - struct netlink_ext_ack *extack) +static int fib_nl2rule(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack, + struct fib_rules_ops *ops, + struct nlattr *tb[], + struct fib_rule **rule, + bool *user_priority) { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); - struct fib_rules_ops *ops = NULL; - struct fib_rule *rule, *r, *last = NULL; - struct nlattr *tb[FRA_MAX+1]; - int err = -EINVAL, unresolved = 0; - - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) - goto errout; + struct fib_rule *nlrule = NULL; + int err = -EINVAL; - ops = lookup_rules_ops(net, frh->family); - if (ops == NULL) { - err = -EAFNOSUPPORT; - goto errout; + if (frh->src_len) + if (!tb[FRA_SRC] || + frh->src_len > (ops->addr_size * 8) || + nla_len(tb[FRA_SRC]) != ops->addr_size) { + NL_SET_ERR_MSG(extack, "Invalid source address"); + goto errout; } - err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); - if (err < 0) - goto errout; - - err = validate_rulemsg(frh, tb, ops); - if (err < 0) - goto errout; + if (frh->dst_len) + if (!tb[FRA_DST] || + frh->dst_len > (ops->addr_size * 8) || + nla_len(tb[FRA_DST]) != ops->addr_size) { + NL_SET_ERR_MSG(extack, "Invalid dst address"); + goto errout; + } - rule = kzalloc(ops->rule_size, GFP_KERNEL); - if (rule == NULL) { + nlrule = kzalloc(ops->rule_size, GFP_KERNEL); + if (!nlrule) { err = -ENOMEM; goto errout; } - refcount_set(&rule->refcnt, 1); - rule->fr_net = net; + refcount_set(&nlrule->refcnt, 1); + nlrule->fr_net = net; - rule->pref = tb[FRA_PRIORITY] ? nla_get_u32(tb[FRA_PRIORITY]) - : fib_default_rule_pref(ops); + if (tb[FRA_PRIORITY]) { + nlrule->pref = nla_get_u32(tb[FRA_PRIORITY]); + *user_priority = true; + } else { + nlrule->pref = fib_default_rule_pref(ops); + } - rule->proto = tb[FRA_PROTOCOL] ? + nlrule->proto = tb[FRA_PROTOCOL] ? nla_get_u8(tb[FRA_PROTOCOL]) : RTPROT_UNSPEC; if (tb[FRA_IIFNAME]) { struct net_device *dev; - rule->iifindex = -1; - nla_strlcpy(rule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->iifname); + nlrule->iifindex = -1; + nla_strlcpy(nlrule->iifname, tb[FRA_IIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, nlrule->iifname); if (dev) - rule->iifindex = dev->ifindex; + nlrule->iifindex = dev->ifindex; } if (tb[FRA_OIFNAME]) { struct net_device *dev; - rule->oifindex = -1; - nla_strlcpy(rule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); - dev = __dev_get_by_name(net, rule->oifname); + nlrule->oifindex = -1; + nla_strlcpy(nlrule->oifname, tb[FRA_OIFNAME], IFNAMSIZ); + dev = __dev_get_by_name(net, nlrule->oifname); if (dev) - rule->oifindex = dev->ifindex; + nlrule->oifindex = dev->ifindex; } if (tb[FRA_FWMARK]) { - rule->mark = nla_get_u32(tb[FRA_FWMARK]); - if (rule->mark) + nlrule->mark = nla_get_u32(tb[FRA_FWMARK]); + if (nlrule->mark) /* compatibility: if the mark value is non-zero all bits * are compared unless a mask is explicitly specified. */ - rule->mark_mask = 0xFFFFFFFF; + nlrule->mark_mask = 0xFFFFFFFF; } if (tb[FRA_FWMASK]) - rule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); + nlrule->mark_mask = nla_get_u32(tb[FRA_FWMASK]); if (tb[FRA_TUN_ID]) - rule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); + nlrule->tun_id = nla_get_be64(tb[FRA_TUN_ID]); err = -EINVAL; - if (tb[FRA_L3MDEV]) { -#ifdef CONFIG_NET_L3_MASTER_DEV - rule->l3mdev = nla_get_u8(tb[FRA_L3MDEV]); - if (rule->l3mdev != 1) -#endif - goto errout_free; - } + if (tb[FRA_L3MDEV] && + fib_nl2rule_l3mdev(tb[FRA_L3MDEV], nlrule, extack) < 0) + goto errout_free; - rule->action = frh->action; - rule->flags = frh->flags; - rule->table = frh_get_table(frh, tb); + nlrule->action = frh->action; + nlrule->flags = frh->flags; + nlrule->table = frh_get_table(frh, tb); if (tb[FRA_SUPPRESS_PREFIXLEN]) - rule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); + nlrule->suppress_prefixlen = nla_get_u32(tb[FRA_SUPPRESS_PREFIXLEN]); else - rule->suppress_prefixlen = -1; + nlrule->suppress_prefixlen = -1; if (tb[FRA_SUPPRESS_IFGROUP]) - rule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); + nlrule->suppress_ifgroup = nla_get_u32(tb[FRA_SUPPRESS_IFGROUP]); else - rule->suppress_ifgroup = -1; + nlrule->suppress_ifgroup = -1; if (tb[FRA_GOTO]) { - if (rule->action != FR_ACT_GOTO) + if (nlrule->action != FR_ACT_GOTO) { + NL_SET_ERR_MSG(extack, "Unexpected goto"); goto errout_free; + } - rule->target = nla_get_u32(tb[FRA_GOTO]); + nlrule->target = nla_get_u32(tb[FRA_GOTO]); /* Backward jumps are prohibited to avoid endless loops */ - if (rule->target <= rule->pref) + if (nlrule->target <= nlrule->pref) { + NL_SET_ERR_MSG(extack, "Backward goto not supported"); goto errout_free; - - list_for_each_entry(r, &ops->rules_list, list) { - if (r->pref == rule->target) { - RCU_INIT_POINTER(rule->ctarget, r); - break; - } } - - if (rcu_dereference_protected(rule->ctarget, 1) == NULL) - unresolved = 1; - } else if (rule->action == FR_ACT_GOTO) + } else if (nlrule->action == FR_ACT_GOTO) { + NL_SET_ERR_MSG(extack, "Missing goto target for action goto"); goto errout_free; + } - if (rule->l3mdev && rule->table) + if (nlrule->l3mdev && nlrule->table) { + NL_SET_ERR_MSG(extack, "l3mdev and table are mutually exclusive"); goto errout_free; + } if (tb[FRA_UID_RANGE]) { if (current_user_ns() != net->user_ns) { err = -EPERM; + NL_SET_ERR_MSG(extack, "No permission to set uid"); goto errout_free; } - rule->uid_range = nla_get_kuid_range(tb); + nlrule->uid_range = nla_get_kuid_range(tb); - if (!uid_range_set(&rule->uid_range) || - !uid_lte(rule->uid_range.start, rule->uid_range.end)) + if (!uid_range_set(&nlrule->uid_range) || + !uid_lte(nlrule->uid_range.start, nlrule->uid_range.end)) { + NL_SET_ERR_MSG(extack, "Invalid uid range"); goto errout_free; + } } else { - rule->uid_range = fib_kuid_range_unset; + nlrule->uid_range = fib_kuid_range_unset; } if (tb[FRA_IP_PROTO]) - rule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); + nlrule->ip_proto = nla_get_u8(tb[FRA_IP_PROTO]); if (tb[FRA_SPORT_RANGE]) { err = nla_get_port_range(tb[FRA_SPORT_RANGE], - &rule->sport_range); - if (err) + &nlrule->sport_range); + if (err) { + NL_SET_ERR_MSG(extack, "Invalid sport range"); goto errout_free; + } } if (tb[FRA_DPORT_RANGE]) { err = nla_get_port_range(tb[FRA_DPORT_RANGE], - &rule->dport_range); - if (err) + &nlrule->dport_range); + if (err) { + NL_SET_ERR_MSG(extack, "Invalid dport range"); goto errout_free; + } } + *rule = nlrule; + + return 0; + +errout_free: + kfree(nlrule); +errout: + return err; +} + +int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, + struct netlink_ext_ack *extack) +{ + struct net *net = sock_net(skb->sk); + struct fib_rule_hdr *frh = nlmsg_data(nlh); + struct fib_rules_ops *ops = NULL; + struct fib_rule *rule = NULL, *r, *last = NULL; + struct nlattr *tb[FRA_MAX + 1]; + int err = -EINVAL, unresolved = 0; + bool user_priority = false; + + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { + NL_SET_ERR_MSG(extack, "Invalid msg length"); + goto errout; + } + + ops = lookup_rules_ops(net, frh->family); + if (!ops) { + err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Rule family not supported"); + goto errout; + } + + err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); + if (err < 0) { + NL_SET_ERR_MSG(extack, "Error parsing msg"); + goto errout; + } + + err = fib_nl2rule(skb, nlh, extack, ops, tb, &rule, &user_priority); + if (err) + goto errout; + if ((nlh->nlmsg_flags & NLM_F_EXCL) && - rule_exists(ops, frh, tb, rule)) { + rule_find(ops, frh, tb, rule, user_priority)) { err = -EEXIST; goto errout_free; } - err = ops->configure(rule, skb, frh, tb); + err = ops->configure(rule, skb, frh, tb, extack); if (err < 0) goto errout_free; @@ -637,6 +694,16 @@ int fib_nl_newrule(struct sk_buff *skb, struct nlmsghdr *nlh, goto errout_free; list_for_each_entry(r, &ops->rules_list, list) { + if (r->pref == rule->target) { + RCU_INIT_POINTER(rule->ctarget, r); + break; + } + } + + if (rcu_dereference_protected(rule->ctarget, 1) == NULL) + unresolved = 1; + + list_for_each_entry(r, &ops->rules_list, list) { if (r->pref > rule->pref) break; last = r; @@ -690,171 +757,97 @@ int fib_nl_delrule(struct sk_buff *skb, struct nlmsghdr *nlh, { struct net *net = sock_net(skb->sk); struct fib_rule_hdr *frh = nlmsg_data(nlh); - struct fib_rule_port_range sprange = {0, 0}; - struct fib_rule_port_range dprange = {0, 0}; struct fib_rules_ops *ops = NULL; - struct fib_rule *rule, *r; + struct fib_rule *rule = NULL, *r, *nlrule = NULL; struct nlattr *tb[FRA_MAX+1]; - struct fib_kuid_range range; int err = -EINVAL; + bool user_priority = false; - if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) + if (nlh->nlmsg_len < nlmsg_msg_size(sizeof(*frh))) { + NL_SET_ERR_MSG(extack, "Invalid msg length"); goto errout; + } ops = lookup_rules_ops(net, frh->family); if (ops == NULL) { err = -EAFNOSUPPORT; + NL_SET_ERR_MSG(extack, "Rule family not supported"); goto errout; } err = nlmsg_parse(nlh, sizeof(*frh), tb, FRA_MAX, ops->policy, extack); - if (err < 0) + if (err < 0) { + NL_SET_ERR_MSG(extack, "Error parsing msg"); goto errout; + } - err = validate_rulemsg(frh, tb, ops); - if (err < 0) + err = fib_nl2rule(skb, nlh, extack, ops, tb, &nlrule, &user_priority); + if (err) goto errout; - if (tb[FRA_UID_RANGE]) { - range = nla_get_kuid_range(tb); - if (!uid_range_set(&range)) { - err = -EINVAL; - goto errout; - } - } else { - range = fib_kuid_range_unset; + rule = rule_find(ops, frh, tb, nlrule, user_priority); + if (!rule) { + err = -ENOENT; + goto errout; } - if (tb[FRA_SPORT_RANGE]) { - err = nla_get_port_range(tb[FRA_SPORT_RANGE], - &sprange); - if (err) - goto errout; + if (rule->flags & FIB_RULE_PERMANENT) { + err = -EPERM; + goto errout; } - if (tb[FRA_DPORT_RANGE]) { - err = nla_get_port_range(tb[FRA_DPORT_RANGE], - &dprange); + if (ops->delete) { + err = ops->delete(rule); if (err) goto errout; } - list_for_each_entry(rule, &ops->rules_list, list) { - if (tb[FRA_PROTOCOL] && - (rule->proto != nla_get_u8(tb[FRA_PROTOCOL]))) - continue; - - if (frh->action && (frh->action != rule->action)) - continue; - - if (frh_get_table(frh, tb) && - (frh_get_table(frh, tb) != rule->table)) - continue; - - if (tb[FRA_PRIORITY] && - (rule->pref != nla_get_u32(tb[FRA_PRIORITY]))) - continue; - - if (tb[FRA_IIFNAME] && - nla_strcmp(tb[FRA_IIFNAME], rule->iifname)) - continue; - - if (tb[FRA_OIFNAME] && - nla_strcmp(tb[FRA_OIFNAME], rule->oifname)) - continue; - - if (tb[FRA_FWMARK] && - (rule->mark != nla_get_u32(tb[FRA_FWMARK]))) - continue; - - if (tb[FRA_FWMASK] && - (rule->mark_mask != nla_get_u32(tb[FRA_FWMASK]))) - continue; - - if (tb[FRA_TUN_ID] && - (rule->tun_id != nla_get_be64(tb[FRA_TUN_ID]))) - continue; - - if (tb[FRA_L3MDEV] && - (rule->l3mdev != nla_get_u8(tb[FRA_L3MDEV]))) - continue; - - if (uid_range_set(&range) && - (!uid_eq(rule->uid_range.start, range.start) || - !uid_eq(rule->uid_range.end, range.end))) - continue; - - if (tb[FRA_IP_PROTO] && - (rule->ip_proto != nla_get_u8(tb[FRA_IP_PROTO]))) - continue; - - if (fib_rule_port_range_set(&sprange) && - !fib_rule_port_range_compare(&rule->sport_range, &sprange)) - continue; - - if (fib_rule_port_range_set(&dprange) && - !fib_rule_port_range_compare(&rule->dport_range, &dprange)) - continue; - - if (!ops->compare(rule, frh, tb)) - continue; - - if (rule->flags & FIB_RULE_PERMANENT) { - err = -EPERM; - goto errout; - } - - if (ops->delete) { - err = ops->delete(rule); - if (err) - goto errout; - } + if (rule->tun_id) + ip_tunnel_unneed_metadata(); - if (rule->tun_id) - ip_tunnel_unneed_metadata(); + list_del_rcu(&rule->list); - list_del_rcu(&rule->list); - - if (rule->action == FR_ACT_GOTO) { - ops->nr_goto_rules--; - if (rtnl_dereference(rule->ctarget) == NULL) - ops->unresolved_rules--; - } + if (rule->action == FR_ACT_GOTO) { + ops->nr_goto_rules--; + if (rtnl_dereference(rule->ctarget) == NULL) + ops->unresolved_rules--; + } - /* - * Check if this rule is a target to any of them. If so, - * adjust to the next one with the same preference or - * disable them. As this operation is eventually very - * expensive, it is only performed if goto rules, except - * current if it is goto rule, have actually been added. - */ - if (ops->nr_goto_rules > 0) { - struct fib_rule *n; - - n = list_next_entry(rule, list); - if (&n->list == &ops->rules_list || n->pref != rule->pref) - n = NULL; - list_for_each_entry(r, &ops->rules_list, list) { - if (rtnl_dereference(r->ctarget) != rule) - continue; - rcu_assign_pointer(r->ctarget, n); - if (!n) - ops->unresolved_rules++; - } + /* + * Check if this rule is a target to any of them. If so, + * adjust to the next one with the same preference or + * disable them. As this operation is eventually very + * expensive, it is only performed if goto rules, except + * current if it is goto rule, have actually been added. + */ + if (ops->nr_goto_rules > 0) { + struct fib_rule *n; + + n = list_next_entry(rule, list); + if (&n->list == &ops->rules_list || n->pref != rule->pref) + n = NULL; + list_for_each_entry(r, &ops->rules_list, list) { + if (rtnl_dereference(r->ctarget) != rule) + continue; + rcu_assign_pointer(r->ctarget, n); + if (!n) + ops->unresolved_rules++; } - - call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, - NULL); - notify_rule_change(RTM_DELRULE, rule, ops, nlh, - NETLINK_CB(skb).portid); - fib_rule_put(rule); - flush_route_cache(ops); - rules_ops_put(ops); - return 0; } - err = -ENOENT; + call_fib_rule_notifiers(net, FIB_EVENT_RULE_DEL, rule, ops, + NULL); + notify_rule_change(RTM_DELRULE, rule, ops, nlh, + NETLINK_CB(skb).portid); + fib_rule_put(rule); + flush_route_cache(ops); + rules_ops_put(ops); + kfree(nlrule); + return 0; + errout: + if (nlrule) + kfree(nlrule); rules_ops_put(ops); return err; } diff --git a/net/core/filter.c b/net/core/filter.c index e77c30ca491d..6877426c23a6 100644 --- a/net/core/filter.c +++ b/net/core/filter.c @@ -57,7 +57,9 @@ #include <net/sock_reuseport.h> #include <net/busy_poll.h> #include <net/tcp.h> +#include <net/xfrm.h> #include <linux/bpf_trace.h> +#include <net/xdp_sock.h> /** * sk_filter_trim_cap - run a packet through a socket filter @@ -111,12 +113,12 @@ int sk_filter_trim_cap(struct sock *sk, struct sk_buff *skb, unsigned int cap) } EXPORT_SYMBOL(sk_filter_trim_cap); -BPF_CALL_1(__skb_get_pay_offset, struct sk_buff *, skb) +BPF_CALL_1(bpf_skb_get_pay_offset, struct sk_buff *, skb) { return skb_get_poff(skb); } -BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) +BPF_CALL_3(bpf_skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; @@ -136,7 +138,7 @@ BPF_CALL_3(__skb_get_nlattr, struct sk_buff *, skb, u32, a, u32, x) return 0; } -BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) +BPF_CALL_3(bpf_skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) { struct nlattr *nla; @@ -160,13 +162,94 @@ BPF_CALL_3(__skb_get_nlattr_nest, struct sk_buff *, skb, u32, a, u32, x) return 0; } -BPF_CALL_0(__get_raw_cpu_id) +BPF_CALL_4(bpf_skb_load_helper_8, const struct sk_buff *, skb, const void *, + data, int, headlen, int, offset) +{ + u8 tmp, *ptr; + const int len = sizeof(tmp); + + if (offset >= 0) { + if (headlen - offset >= len) + return *(u8 *)(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return tmp; + } else { + ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); + if (likely(ptr)) + return *(u8 *)ptr; + } + + return -EFAULT; +} + +BPF_CALL_2(bpf_skb_load_helper_8_no_cache, const struct sk_buff *, skb, + int, offset) +{ + return ____bpf_skb_load_helper_8(skb, skb->data, skb->len - skb->data_len, + offset); +} + +BPF_CALL_4(bpf_skb_load_helper_16, const struct sk_buff *, skb, const void *, + data, int, headlen, int, offset) +{ + u16 tmp, *ptr; + const int len = sizeof(tmp); + + if (offset >= 0) { + if (headlen - offset >= len) + return get_unaligned_be16(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return be16_to_cpu(tmp); + } else { + ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); + if (likely(ptr)) + return get_unaligned_be16(ptr); + } + + return -EFAULT; +} + +BPF_CALL_2(bpf_skb_load_helper_16_no_cache, const struct sk_buff *, skb, + int, offset) +{ + return ____bpf_skb_load_helper_16(skb, skb->data, skb->len - skb->data_len, + offset); +} + +BPF_CALL_4(bpf_skb_load_helper_32, const struct sk_buff *, skb, const void *, + data, int, headlen, int, offset) +{ + u32 tmp, *ptr; + const int len = sizeof(tmp); + + if (likely(offset >= 0)) { + if (headlen - offset >= len) + return get_unaligned_be32(data + offset); + if (!skb_copy_bits(skb, offset, &tmp, sizeof(tmp))) + return be32_to_cpu(tmp); + } else { + ptr = bpf_internal_load_pointer_neg_helper(skb, offset, len); + if (likely(ptr)) + return get_unaligned_be32(ptr); + } + + return -EFAULT; +} + +BPF_CALL_2(bpf_skb_load_helper_32_no_cache, const struct sk_buff *, skb, + int, offset) +{ + return ____bpf_skb_load_helper_32(skb, skb->data, skb->len - skb->data_len, + offset); +} + +BPF_CALL_0(bpf_get_raw_cpu_id) { return raw_smp_processor_id(); } static const struct bpf_func_proto bpf_get_raw_smp_processor_id_proto = { - .func = __get_raw_cpu_id, + .func = bpf_get_raw_cpu_id, .gpl_only = false, .ret_type = RET_INTEGER, }; @@ -316,16 +399,16 @@ static bool convert_bpf_extensions(struct sock_filter *fp, /* Emit call(arg1=CTX, arg2=A, arg3=X) */ switch (fp->k) { case SKF_AD_OFF + SKF_AD_PAY_OFFSET: - *insn = BPF_EMIT_CALL(__skb_get_pay_offset); + *insn = BPF_EMIT_CALL(bpf_skb_get_pay_offset); break; case SKF_AD_OFF + SKF_AD_NLATTR: - *insn = BPF_EMIT_CALL(__skb_get_nlattr); + *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr); break; case SKF_AD_OFF + SKF_AD_NLATTR_NEST: - *insn = BPF_EMIT_CALL(__skb_get_nlattr_nest); + *insn = BPF_EMIT_CALL(bpf_skb_get_nlattr_nest); break; case SKF_AD_OFF + SKF_AD_CPU: - *insn = BPF_EMIT_CALL(__get_raw_cpu_id); + *insn = BPF_EMIT_CALL(bpf_get_raw_cpu_id); break; case SKF_AD_OFF + SKF_AD_RANDOM: *insn = BPF_EMIT_CALL(bpf_user_rnd_u32); @@ -352,26 +435,87 @@ static bool convert_bpf_extensions(struct sock_filter *fp, return true; } +static bool convert_bpf_ld_abs(struct sock_filter *fp, struct bpf_insn **insnp) +{ + const bool unaligned_ok = IS_BUILTIN(CONFIG_HAVE_EFFICIENT_UNALIGNED_ACCESS); + int size = bpf_size_to_bytes(BPF_SIZE(fp->code)); + bool endian = BPF_SIZE(fp->code) == BPF_H || + BPF_SIZE(fp->code) == BPF_W; + bool indirect = BPF_MODE(fp->code) == BPF_IND; + const int ip_align = NET_IP_ALIGN; + struct bpf_insn *insn = *insnp; + int offset = fp->k; + + if (!indirect && + ((unaligned_ok && offset >= 0) || + (!unaligned_ok && offset >= 0 && + offset + ip_align >= 0 && + offset + ip_align % size == 0))) { + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_H); + *insn++ = BPF_ALU64_IMM(BPF_SUB, BPF_REG_TMP, offset); + *insn++ = BPF_JMP_IMM(BPF_JSLT, BPF_REG_TMP, size, 2 + endian); + *insn++ = BPF_LDX_MEM(BPF_SIZE(fp->code), BPF_REG_A, BPF_REG_D, + offset); + if (endian) + *insn++ = BPF_ENDIAN(BPF_FROM_BE, BPF_REG_A, size * 8); + *insn++ = BPF_JMP_A(8); + } + + *insn++ = BPF_MOV64_REG(BPF_REG_ARG1, BPF_REG_CTX); + *insn++ = BPF_MOV64_REG(BPF_REG_ARG2, BPF_REG_D); + *insn++ = BPF_MOV64_REG(BPF_REG_ARG3, BPF_REG_H); + if (!indirect) { + *insn++ = BPF_MOV64_IMM(BPF_REG_ARG4, offset); + } else { + *insn++ = BPF_MOV64_REG(BPF_REG_ARG4, BPF_REG_X); + if (fp->k) + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_ARG4, offset); + } + + switch (BPF_SIZE(fp->code)) { + case BPF_B: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8); + break; + case BPF_H: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16); + break; + case BPF_W: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32); + break; + default: + return false; + } + + *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_A, 0, 2); + *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_A, BPF_REG_A); + *insn = BPF_EXIT_INSN(); + + *insnp = insn; + return true; +} + /** * bpf_convert_filter - convert filter program * @prog: the user passed filter program * @len: the length of the user passed filter program * @new_prog: allocated 'struct bpf_prog' or NULL * @new_len: pointer to store length of converted program + * @seen_ld_abs: bool whether we've seen ld_abs/ind * * Remap 'sock_filter' style classic BPF (cBPF) instruction set to 'bpf_insn' * style extended BPF (eBPF). * Conversion workflow: * * 1) First pass for calculating the new program length: - * bpf_convert_filter(old_prog, old_len, NULL, &new_len) + * bpf_convert_filter(old_prog, old_len, NULL, &new_len, &seen_ld_abs) * * 2) 2nd pass to remap in two passes: 1st pass finds new * jump offsets, 2nd pass remapping: - * bpf_convert_filter(old_prog, old_len, new_prog, &new_len); + * bpf_convert_filter(old_prog, old_len, new_prog, &new_len, &seen_ld_abs) */ static int bpf_convert_filter(struct sock_filter *prog, int len, - struct bpf_prog *new_prog, int *new_len) + struct bpf_prog *new_prog, int *new_len, + bool *seen_ld_abs) { int new_flen = 0, pass = 0, target, i, stack_off; struct bpf_insn *new_insn, *first_insn = NULL; @@ -410,12 +554,27 @@ do_pass: * do this ourself. Initial CTX is present in BPF_REG_ARG1. */ *new_insn++ = BPF_MOV64_REG(BPF_REG_CTX, BPF_REG_ARG1); + if (*seen_ld_abs) { + /* For packet access in classic BPF, cache skb->data + * in callee-saved BPF R8 and skb->len - skb->data_len + * (headlen) in BPF R9. Since classic BPF is read-only + * on CTX, we only need to cache it once. + */ + *new_insn++ = BPF_LDX_MEM(BPF_FIELD_SIZEOF(struct sk_buff, data), + BPF_REG_D, BPF_REG_CTX, + offsetof(struct sk_buff, data)); + *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_H, BPF_REG_CTX, + offsetof(struct sk_buff, len)); + *new_insn++ = BPF_LDX_MEM(BPF_W, BPF_REG_TMP, BPF_REG_CTX, + offsetof(struct sk_buff, data_len)); + *new_insn++ = BPF_ALU32_REG(BPF_SUB, BPF_REG_H, BPF_REG_TMP); + } } else { new_insn += 3; } for (i = 0; i < len; fp++, i++) { - struct bpf_insn tmp_insns[6] = { }; + struct bpf_insn tmp_insns[32] = { }; struct bpf_insn *insn = tmp_insns; if (addrs) @@ -458,6 +617,11 @@ do_pass: BPF_MODE(fp->code) == BPF_ABS && convert_bpf_extensions(fp, &insn)) break; + if (BPF_CLASS(fp->code) == BPF_LD && + convert_bpf_ld_abs(fp, &insn)) { + *seen_ld_abs = true; + break; + } if (fp->code == (BPF_ALU | BPF_DIV | BPF_X) || fp->code == (BPF_ALU | BPF_MOD | BPF_X)) { @@ -560,21 +724,31 @@ jmp_rest: break; /* ldxb 4 * ([14] & 0xf) is remaped into 6 insns. */ - case BPF_LDX | BPF_MSH | BPF_B: - /* tmp = A */ - *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_A); + case BPF_LDX | BPF_MSH | BPF_B: { + struct sock_filter tmp = { + .code = BPF_LD | BPF_ABS | BPF_B, + .k = fp->k, + }; + + *seen_ld_abs = true; + + /* X = A */ + *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = BPF_R0 = *(u8 *) (skb->data + K) */ - *insn++ = BPF_LD_ABS(BPF_B, fp->k); + convert_bpf_ld_abs(&tmp, &insn); + insn++; /* A &= 0xf */ *insn++ = BPF_ALU32_IMM(BPF_AND, BPF_REG_A, 0xf); /* A <<= 2 */ *insn++ = BPF_ALU32_IMM(BPF_LSH, BPF_REG_A, 2); + /* tmp = X */ + *insn++ = BPF_MOV64_REG(BPF_REG_TMP, BPF_REG_X); /* X = A */ *insn++ = BPF_MOV64_REG(BPF_REG_X, BPF_REG_A); /* A = tmp */ *insn = BPF_MOV64_REG(BPF_REG_A, BPF_REG_TMP); break; - + } /* RET_K is remaped into 2 insns. RET_A case doesn't need an * extra mov as BPF_REG_0 is already mapped into BPF_REG_A. */ @@ -656,6 +830,8 @@ jmp_rest: if (!new_prog) { /* Only calculating new length. */ *new_len = new_insn - first_insn; + if (*seen_ld_abs) + *new_len += 4; /* Prologue bits. */ return 0; } @@ -1017,6 +1193,7 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) struct sock_filter *old_prog; struct bpf_prog *old_fp; int err, new_len, old_len = fp->len; + bool seen_ld_abs = false; /* We are free to overwrite insns et al right here as it * won't be used at this point in time anymore internally @@ -1038,7 +1215,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) } /* 1st pass: calculate the new program length. */ - err = bpf_convert_filter(old_prog, old_len, NULL, &new_len); + err = bpf_convert_filter(old_prog, old_len, NULL, &new_len, + &seen_ld_abs); if (err) goto out_err_free; @@ -1057,7 +1235,8 @@ static struct bpf_prog *bpf_migrate_filter(struct bpf_prog *fp) fp->len = new_len; /* 2nd pass: remap sock_filter insns into bpf_insn insns. */ - err = bpf_convert_filter(old_prog, old_len, fp, &new_len); + err = bpf_convert_filter(old_prog, old_len, fp, &new_len, + &seen_ld_abs); if (err) /* 2nd bpf_convert_filter() can fail only if it fails * to allocate memory, remapping must succeed. Note, @@ -1505,6 +1684,47 @@ static const struct bpf_func_proto bpf_skb_load_bytes_proto = { .arg4_type = ARG_CONST_SIZE, }; +BPF_CALL_5(bpf_skb_load_bytes_relative, const struct sk_buff *, skb, + u32, offset, void *, to, u32, len, u32, start_header) +{ + u8 *ptr; + + if (unlikely(offset > 0xffff || len > skb_headlen(skb))) + goto err_clear; + + switch (start_header) { + case BPF_HDR_START_MAC: + ptr = skb_mac_header(skb) + offset; + break; + case BPF_HDR_START_NET: + ptr = skb_network_header(skb) + offset; + break; + default: + goto err_clear; + } + + if (likely(ptr >= skb_mac_header(skb) && + ptr + len <= skb_tail_pointer(skb))) { + memcpy(to, ptr, len); + return 0; + } + +err_clear: + memset(to, 0, len); + return -EFAULT; +} + +static const struct bpf_func_proto bpf_skb_load_bytes_relative_proto = { + .func = bpf_skb_load_bytes_relative, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, + .arg5_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_skb_pull_data, struct sk_buff *, skb, u32, len) { /* Idea is the following: should the needed direct read/write @@ -2179,7 +2399,7 @@ BPF_CALL_3(bpf_skb_vlan_push, struct sk_buff *, skb, __be16, vlan_proto, return ret; } -const struct bpf_func_proto bpf_skb_vlan_push_proto = { +static const struct bpf_func_proto bpf_skb_vlan_push_proto = { .func = bpf_skb_vlan_push, .gpl_only = false, .ret_type = RET_INTEGER, @@ -2187,7 +2407,6 @@ const struct bpf_func_proto bpf_skb_vlan_push_proto = { .arg2_type = ARG_ANYTHING, .arg3_type = ARG_ANYTHING, }; -EXPORT_SYMBOL_GPL(bpf_skb_vlan_push_proto); BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) { @@ -2201,13 +2420,12 @@ BPF_CALL_1(bpf_skb_vlan_pop, struct sk_buff *, skb) return ret; } -const struct bpf_func_proto bpf_skb_vlan_pop_proto = { +static const struct bpf_func_proto bpf_skb_vlan_pop_proto = { .func = bpf_skb_vlan_pop, .gpl_only = false, .ret_type = RET_INTEGER, .arg1_type = ARG_PTR_TO_CTX, }; -EXPORT_SYMBOL_GPL(bpf_skb_vlan_pop_proto); static int bpf_skb_generic_push(struct sk_buff *skb, u32 off, u32 len) { @@ -2692,8 +2910,9 @@ static unsigned long xdp_get_metalen(const struct xdp_buff *xdp) BPF_CALL_2(bpf_xdp_adjust_head, struct xdp_buff *, xdp, int, offset) { + void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); unsigned long metalen = xdp_get_metalen(xdp); - void *data_start = xdp->data_hard_start + metalen; + void *data_start = xdp_frame_end + metalen; void *data = xdp->data + offset; if (unlikely(data < data_start || @@ -2717,14 +2936,39 @@ static const struct bpf_func_proto bpf_xdp_adjust_head_proto = { .arg2_type = ARG_ANYTHING, }; +BPF_CALL_2(bpf_xdp_adjust_tail, struct xdp_buff *, xdp, int, offset) +{ + void *data_end = xdp->data_end + offset; + + /* only shrinking is allowed for now. */ + if (unlikely(offset >= 0)) + return -EINVAL; + + if (unlikely(data_end < xdp->data + ETH_HLEN)) + return -EINVAL; + + xdp->data_end = data_end; + + return 0; +} + +static const struct bpf_func_proto bpf_xdp_adjust_tail_proto = { + .func = bpf_xdp_adjust_tail, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, +}; + BPF_CALL_2(bpf_xdp_adjust_meta, struct xdp_buff *, xdp, int, offset) { + void *xdp_frame_end = xdp->data_hard_start + sizeof(struct xdp_frame); void *meta = xdp->data_meta + offset; unsigned long metalen = xdp->data - meta; if (xdp_data_meta_unsupported(xdp)) return -ENOTSUPP; - if (unlikely(meta < xdp->data_hard_start || + if (unlikely(meta < xdp_frame_end || meta > xdp->data)) return -EINVAL; if (unlikely((metalen & (sizeof(__u32) - 1)) || @@ -2749,13 +2993,18 @@ static int __bpf_tx_xdp(struct net_device *dev, struct xdp_buff *xdp, u32 index) { + struct xdp_frame *xdpf; int err; if (!dev->netdev_ops->ndo_xdp_xmit) { return -EOPNOTSUPP; } - err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf); if (err) return err; dev->netdev_ops->ndo_xdp_flush(dev); @@ -2769,24 +3018,44 @@ static int __bpf_tx_xdp_map(struct net_device *dev_rx, void *fwd, { int err; - if (map->map_type == BPF_MAP_TYPE_DEVMAP) { + switch (map->map_type) { + case BPF_MAP_TYPE_DEVMAP: { struct net_device *dev = fwd; + struct xdp_frame *xdpf; if (!dev->netdev_ops->ndo_xdp_xmit) return -EOPNOTSUPP; - err = dev->netdev_ops->ndo_xdp_xmit(dev, xdp); + xdpf = convert_to_xdp_frame(xdp); + if (unlikely(!xdpf)) + return -EOVERFLOW; + + /* TODO: move to inside map code instead, for bulk support + * err = dev_map_enqueue(dev, xdp); + */ + err = dev->netdev_ops->ndo_xdp_xmit(dev, xdpf); if (err) return err; __dev_map_insert_ctx(map, index); - - } else if (map->map_type == BPF_MAP_TYPE_CPUMAP) { + break; + } + case BPF_MAP_TYPE_CPUMAP: { struct bpf_cpu_map_entry *rcpu = fwd; err = cpu_map_enqueue(rcpu, xdp, dev_rx); if (err) return err; __cpu_map_insert_ctx(map, index); + break; + } + case BPF_MAP_TYPE_XSKMAP: { + struct xdp_sock *xs = fwd; + + err = __xsk_map_redirect(map, xdp, xs); + return err; + } + default: + break; } return 0; } @@ -2805,6 +3074,9 @@ void xdp_do_flush_map(void) case BPF_MAP_TYPE_CPUMAP: __cpu_map_flush(map); break; + case BPF_MAP_TYPE_XSKMAP: + __xsk_map_flush(map); + break; default: break; } @@ -2819,6 +3091,8 @@ static void *__xdp_map_lookup_elem(struct bpf_map *map, u32 index) return __dev_map_lookup_elem(map, index); case BPF_MAP_TYPE_CPUMAP: return __cpu_map_lookup_elem(map, index); + case BPF_MAP_TYPE_XSKMAP: + return __xsk_map_lookup_elem(map, index); default: return NULL; } @@ -2916,13 +3190,14 @@ static int __xdp_generic_ok_fwd_dev(struct sk_buff *skb, struct net_device *fwd) static int xdp_do_generic_redirect_map(struct net_device *dev, struct sk_buff *skb, + struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); unsigned long map_owner = ri->map_owner; struct bpf_map *map = ri->map; - struct net_device *fwd = NULL; u32 index = ri->ifindex; + void *fwd = NULL; int err = 0; ri->ifindex = 0; @@ -2944,6 +3219,14 @@ static int xdp_do_generic_redirect_map(struct net_device *dev, if (unlikely((err = __xdp_generic_ok_fwd_dev(skb, fwd)))) goto err; skb->dev = fwd; + generic_xdp_tx(skb, xdp_prog); + } else if (map->map_type == BPF_MAP_TYPE_XSKMAP) { + struct xdp_sock *xs = fwd; + + err = xsk_generic_rcv(xs, xdp); + if (err) + goto err; + consume_skb(skb); } else { /* TODO: Handle BPF_MAP_TYPE_CPUMAP */ err = -EBADRQC; @@ -2958,7 +3241,7 @@ err: } int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, - struct bpf_prog *xdp_prog) + struct xdp_buff *xdp, struct bpf_prog *xdp_prog) { struct redirect_info *ri = this_cpu_ptr(&redirect_info); u32 index = ri->ifindex; @@ -2966,7 +3249,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, int err = 0; if (ri->map) - return xdp_do_generic_redirect_map(dev, skb, xdp_prog); + return xdp_do_generic_redirect_map(dev, skb, xdp, xdp_prog); ri->ifindex = 0; fwd = dev_get_by_index_rcu(dev_net(dev), index); @@ -2980,6 +3263,7 @@ int xdp_do_generic_redirect(struct net_device *dev, struct sk_buff *skb, skb->dev = fwd; _trace_xdp_redirect(dev, xdp_prog, index); + generic_xdp_tx(skb, xdp_prog); return 0; err: _trace_xdp_redirect_err(dev, xdp_prog, index, err); @@ -3053,7 +3337,8 @@ bool bpf_helper_changes_pkt_data(void *func) func == bpf_l4_csum_replace || func == bpf_xdp_adjust_head || func == bpf_xdp_adjust_meta || - func == bpf_msg_pull_data) + func == bpf_msg_pull_data || + func == bpf_xdp_adjust_tail) return true; return false; @@ -3704,6 +3989,49 @@ static const struct bpf_func_proto bpf_bind_proto = { .arg3_type = ARG_CONST_SIZE, }; +#ifdef CONFIG_XFRM +BPF_CALL_5(bpf_skb_get_xfrm_state, struct sk_buff *, skb, u32, index, + struct bpf_xfrm_state *, to, u32, size, u64, flags) +{ + const struct sec_path *sp = skb_sec_path(skb); + const struct xfrm_state *x; + + if (!sp || unlikely(index >= sp->len || flags)) + goto err_clear; + + x = sp->xvec[index]; + + if (unlikely(size != sizeof(struct bpf_xfrm_state))) + goto err_clear; + + to->reqid = x->props.reqid; + to->spi = x->id.spi; + to->family = x->props.family; + if (to->family == AF_INET6) { + memcpy(to->remote_ipv6, x->props.saddr.a6, + sizeof(to->remote_ipv6)); + } else { + to->remote_ipv4 = x->props.saddr.a4; + } + + return 0; +err_clear: + memset(to, 0, size); + return -EINVAL; +} + +static const struct bpf_func_proto bpf_skb_get_xfrm_state_proto = { + .func = bpf_skb_get_xfrm_state, + .gpl_only = false, + .ret_type = RET_INTEGER, + .arg1_type = ARG_PTR_TO_CTX, + .arg2_type = ARG_ANYTHING, + .arg3_type = ARG_PTR_TO_UNINIT_MEM, + .arg4_type = ARG_CONST_SIZE, + .arg5_type = ARG_ANYTHING, +}; +#endif + static const struct bpf_func_proto * bpf_base_func_proto(enum bpf_func_id func_id) { @@ -3774,6 +4102,8 @@ sk_filter_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) switch (func_id) { case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_load_bytes_relative: + return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_get_socket_cookie: return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: @@ -3791,6 +4121,8 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_skb_store_bytes_proto; case BPF_FUNC_skb_load_bytes: return &bpf_skb_load_bytes_proto; + case BPF_FUNC_skb_load_bytes_relative: + return &bpf_skb_load_bytes_relative_proto; case BPF_FUNC_skb_pull_data: return &bpf_skb_pull_data_proto; case BPF_FUNC_csum_diff: @@ -3845,6 +4177,10 @@ tc_cls_act_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_get_socket_cookie_proto; case BPF_FUNC_get_socket_uid: return &bpf_get_socket_uid_proto; +#ifdef CONFIG_XFRM + case BPF_FUNC_skb_get_xfrm_state: + return &bpf_skb_get_xfrm_state_proto; +#endif default: return bpf_base_func_proto(func_id); } @@ -3868,6 +4204,8 @@ xdp_func_proto(enum bpf_func_id func_id, const struct bpf_prog *prog) return &bpf_xdp_redirect_proto; case BPF_FUNC_redirect_map: return &bpf_xdp_redirect_map_proto; + case BPF_FUNC_xdp_adjust_tail: + return &bpf_xdp_adjust_tail_proto; default: return bpf_base_func_proto(func_id); } @@ -4214,6 +4552,41 @@ static int bpf_unclone_prologue(struct bpf_insn *insn_buf, bool direct_write, return insn - insn_buf; } +static int bpf_gen_ld_abs(const struct bpf_insn *orig, + struct bpf_insn *insn_buf) +{ + bool indirect = BPF_MODE(orig->code) == BPF_IND; + struct bpf_insn *insn = insn_buf; + + /* We're guaranteed here that CTX is in R6. */ + *insn++ = BPF_MOV64_REG(BPF_REG_1, BPF_REG_CTX); + if (!indirect) { + *insn++ = BPF_MOV64_IMM(BPF_REG_2, orig->imm); + } else { + *insn++ = BPF_MOV64_REG(BPF_REG_2, orig->src_reg); + if (orig->imm) + *insn++ = BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, orig->imm); + } + + switch (BPF_SIZE(orig->code)) { + case BPF_B: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_8_no_cache); + break; + case BPF_H: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_16_no_cache); + break; + case BPF_W: + *insn++ = BPF_EMIT_CALL(bpf_skb_load_helper_32_no_cache); + break; + } + + *insn++ = BPF_JMP_IMM(BPF_JSGE, BPF_REG_0, 0, 2); + *insn++ = BPF_ALU32_REG(BPF_XOR, BPF_REG_0, BPF_REG_0); + *insn++ = BPF_EXIT_INSN(); + + return insn - insn_buf; +} + static int tc_cls_act_prologue(struct bpf_insn *insn_buf, bool direct_write, const struct bpf_prog *prog) { @@ -5483,6 +5856,7 @@ const struct bpf_verifier_ops sk_filter_verifier_ops = { .get_func_proto = sk_filter_func_proto, .is_valid_access = sk_filter_is_valid_access, .convert_ctx_access = bpf_convert_ctx_access, + .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops sk_filter_prog_ops = { @@ -5494,6 +5868,7 @@ const struct bpf_verifier_ops tc_cls_act_verifier_ops = { .is_valid_access = tc_cls_act_is_valid_access, .convert_ctx_access = tc_cls_act_convert_ctx_access, .gen_prologue = tc_cls_act_prologue, + .gen_ld_abs = bpf_gen_ld_abs, }; const struct bpf_prog_ops tc_cls_act_prog_ops = { diff --git a/net/core/flow_dissector.c b/net/core/flow_dissector.c index d29f09bc5ff9..4fc1e84d77ec 100644 --- a/net/core/flow_dissector.c +++ b/net/core/flow_dissector.c @@ -1253,7 +1253,7 @@ __u32 skb_get_hash_perturb(const struct sk_buff *skb, u32 perturb) EXPORT_SYMBOL(skb_get_hash_perturb); u32 __skb_get_poff(const struct sk_buff *skb, void *data, - const struct flow_keys *keys, int hlen) + const struct flow_keys_basic *keys, int hlen) { u32 poff = keys->control.thoff; @@ -1314,9 +1314,9 @@ u32 __skb_get_poff(const struct sk_buff *skb, void *data, */ u32 skb_get_poff(const struct sk_buff *skb) { - struct flow_keys keys; + struct flow_keys_basic keys; - if (!skb_flow_dissect_flow_keys(skb, &keys, 0)) + if (!skb_flow_dissect_flow_keys_basic(skb, &keys, NULL, 0, 0, 0, 0)) return 0; return __skb_get_poff(skb, skb->data, &keys, skb_headlen(skb)); @@ -1403,7 +1403,7 @@ static const struct flow_dissector_key flow_keys_dissector_symmetric_keys[] = { }, }; -static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { +static const struct flow_dissector_key flow_keys_basic_dissector_keys[] = { { .key_id = FLOW_DISSECTOR_KEY_CONTROL, .offset = offsetof(struct flow_keys, control), @@ -1417,7 +1417,8 @@ static const struct flow_dissector_key flow_keys_buf_dissector_keys[] = { struct flow_dissector flow_keys_dissector __read_mostly; EXPORT_SYMBOL(flow_keys_dissector); -struct flow_dissector flow_keys_buf_dissector __read_mostly; +struct flow_dissector flow_keys_basic_dissector __read_mostly; +EXPORT_SYMBOL(flow_keys_basic_dissector); static int __init init_default_flow_dissectors(void) { @@ -1427,9 +1428,9 @@ static int __init init_default_flow_dissectors(void) skb_flow_dissector_init(&flow_keys_dissector_symmetric, flow_keys_dissector_symmetric_keys, ARRAY_SIZE(flow_keys_dissector_symmetric_keys)); - skb_flow_dissector_init(&flow_keys_buf_dissector, - flow_keys_buf_dissector_keys, - ARRAY_SIZE(flow_keys_buf_dissector_keys)); + skb_flow_dissector_init(&flow_keys_basic_dissector, + flow_keys_basic_dissector_keys, + ARRAY_SIZE(flow_keys_basic_dissector_keys)); return 0; } diff --git a/net/core/neighbour.c b/net/core/neighbour.c index ce519861be59..5afae29367c1 100644 --- a/net/core/neighbour.c +++ b/net/core/neighbour.c @@ -820,7 +820,8 @@ static void neigh_periodic_work(struct work_struct *work) write_lock(&n->lock); state = n->nud_state; - if (state & (NUD_PERMANENT | NUD_IN_TIMER)) { + if ((state & (NUD_PERMANENT | NUD_IN_TIMER)) || + (n->flags & NTF_EXT_LEARNED)) { write_unlock(&n->lock); goto next_elt; } @@ -1136,6 +1137,8 @@ int neigh_update(struct neighbour *neigh, const u8 *lladdr, u8 new, if (neigh->dead) goto out; + neigh_update_ext_learned(neigh, flags, ¬ify); + if (!(new & NUD_VALID)) { neigh_del_timer(neigh); if (old & NUD_CONNECTED) @@ -1781,6 +1784,9 @@ static int neigh_add(struct sk_buff *skb, struct nlmsghdr *nlh, flags &= ~NEIGH_UPDATE_F_OVERRIDE; } + if (ndm->ndm_flags & NTF_EXT_LEARNED) + flags |= NEIGH_UPDATE_F_EXT_LEARNED; + if (ndm->ndm_flags & NTF_USE) { neigh_event_send(neigh, NULL); err = 0; diff --git a/net/core/page_pool.c b/net/core/page_pool.c new file mode 100644 index 000000000000..68bf07206744 --- /dev/null +++ b/net/core/page_pool.c @@ -0,0 +1,317 @@ +/* SPDX-License-Identifier: GPL-2.0 + * + * page_pool.c + * Author: Jesper Dangaard Brouer <netoptimizer@brouer.com> + * Copyright (C) 2016 Red Hat, Inc. + */ +#include <linux/types.h> +#include <linux/kernel.h> +#include <linux/slab.h> + +#include <net/page_pool.h> +#include <linux/dma-direction.h> +#include <linux/dma-mapping.h> +#include <linux/page-flags.h> +#include <linux/mm.h> /* for __put_page() */ + +static int page_pool_init(struct page_pool *pool, + const struct page_pool_params *params) +{ + unsigned int ring_qsize = 1024; /* Default */ + + memcpy(&pool->p, params, sizeof(pool->p)); + + /* Validate only known flags were used */ + if (pool->p.flags & ~(PP_FLAG_ALL)) + return -EINVAL; + + if (pool->p.pool_size) + ring_qsize = pool->p.pool_size; + + /* Sanity limit mem that can be pinned down */ + if (ring_qsize > 32768) + return -E2BIG; + + /* DMA direction is either DMA_FROM_DEVICE or DMA_BIDIRECTIONAL. + * DMA_BIDIRECTIONAL is for allowing page used for DMA sending, + * which is the XDP_TX use-case. + */ + if ((pool->p.dma_dir != DMA_FROM_DEVICE) && + (pool->p.dma_dir != DMA_BIDIRECTIONAL)) + return -EINVAL; + + if (ptr_ring_init(&pool->ring, ring_qsize, GFP_KERNEL) < 0) + return -ENOMEM; + + return 0; +} + +struct page_pool *page_pool_create(const struct page_pool_params *params) +{ + struct page_pool *pool; + int err = 0; + + pool = kzalloc_node(sizeof(*pool), GFP_KERNEL, params->nid); + if (!pool) + return ERR_PTR(-ENOMEM); + + err = page_pool_init(pool, params); + if (err < 0) { + pr_warn("%s() gave up with errno %d\n", __func__, err); + kfree(pool); + return ERR_PTR(err); + } + return pool; +} +EXPORT_SYMBOL(page_pool_create); + +/* fast path */ +static struct page *__page_pool_get_cached(struct page_pool *pool) +{ + struct ptr_ring *r = &pool->ring; + struct page *page; + + /* Quicker fallback, avoid locks when ring is empty */ + if (__ptr_ring_empty(r)) + return NULL; + + /* Test for safe-context, caller should provide this guarantee */ + if (likely(in_serving_softirq())) { + if (likely(pool->alloc.count)) { + /* Fast-path */ + page = pool->alloc.cache[--pool->alloc.count]; + return page; + } + /* Slower-path: Alloc array empty, time to refill + * + * Open-coded bulk ptr_ring consumer. + * + * Discussion: the ring consumer lock is not really + * needed due to the softirq/NAPI protection, but + * later need the ability to reclaim pages on the + * ring. Thus, keeping the locks. + */ + spin_lock(&r->consumer_lock); + while ((page = __ptr_ring_consume(r))) { + if (pool->alloc.count == PP_ALLOC_CACHE_REFILL) + break; + pool->alloc.cache[pool->alloc.count++] = page; + } + spin_unlock(&r->consumer_lock); + return page; + } + + /* Slow-path: Get page from locked ring queue */ + page = ptr_ring_consume(&pool->ring); + return page; +} + +/* slow path */ +noinline +static struct page *__page_pool_alloc_pages_slow(struct page_pool *pool, + gfp_t _gfp) +{ + struct page *page; + gfp_t gfp = _gfp; + dma_addr_t dma; + + /* We could always set __GFP_COMP, and avoid this branch, as + * prep_new_page() can handle order-0 with __GFP_COMP. + */ + if (pool->p.order) + gfp |= __GFP_COMP; + + /* FUTURE development: + * + * Current slow-path essentially falls back to single page + * allocations, which doesn't improve performance. This code + * need bulk allocation support from the page allocator code. + */ + + /* Cache was empty, do real allocation */ + page = alloc_pages_node(pool->p.nid, gfp, pool->p.order); + if (!page) + return NULL; + + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + goto skip_dma_map; + + /* Setup DMA mapping: use page->private for DMA-addr + * This mapping is kept for lifetime of page, until leaving pool. + */ + dma = dma_map_page(pool->p.dev, page, 0, + (PAGE_SIZE << pool->p.order), + pool->p.dma_dir); + if (dma_mapping_error(pool->p.dev, dma)) { + put_page(page); + return NULL; + } + set_page_private(page, dma); /* page->private = dma; */ + +skip_dma_map: + /* When page just alloc'ed is should/must have refcnt 1. */ + return page; +} + +/* For using page_pool replace: alloc_pages() API calls, but provide + * synchronization guarantee for allocation side. + */ +struct page *page_pool_alloc_pages(struct page_pool *pool, gfp_t gfp) +{ + struct page *page; + + /* Fast-path: Get a page from cache */ + page = __page_pool_get_cached(pool); + if (page) + return page; + + /* Slow-path: cache empty, do real allocation */ + page = __page_pool_alloc_pages_slow(pool, gfp); + return page; +} +EXPORT_SYMBOL(page_pool_alloc_pages); + +/* Cleanup page_pool state from page */ +static void __page_pool_clean_page(struct page_pool *pool, + struct page *page) +{ + if (!(pool->p.flags & PP_FLAG_DMA_MAP)) + return; + + /* DMA unmap */ + dma_unmap_page(pool->p.dev, page_private(page), + PAGE_SIZE << pool->p.order, pool->p.dma_dir); + set_page_private(page, 0); +} + +/* Return a page to the page allocator, cleaning up our state */ +static void __page_pool_return_page(struct page_pool *pool, struct page *page) +{ + __page_pool_clean_page(pool, page); + put_page(page); + /* An optimization would be to call __free_pages(page, pool->p.order) + * knowing page is not part of page-cache (thus avoiding a + * __page_cache_release() call). + */ +} + +static bool __page_pool_recycle_into_ring(struct page_pool *pool, + struct page *page) +{ + int ret; + /* BH protection not needed if current is serving softirq */ + if (in_serving_softirq()) + ret = ptr_ring_produce(&pool->ring, page); + else + ret = ptr_ring_produce_bh(&pool->ring, page); + + return (ret == 0) ? true : false; +} + +/* Only allow direct recycling in special circumstances, into the + * alloc side cache. E.g. during RX-NAPI processing for XDP_DROP use-case. + * + * Caller must provide appropriate safe context. + */ +static bool __page_pool_recycle_direct(struct page *page, + struct page_pool *pool) +{ + if (unlikely(pool->alloc.count == PP_ALLOC_CACHE_SIZE)) + return false; + + /* Caller MUST have verified/know (page_ref_count(page) == 1) */ + pool->alloc.cache[pool->alloc.count++] = page; + return true; +} + +void __page_pool_put_page(struct page_pool *pool, + struct page *page, bool allow_direct) +{ + /* This allocator is optimized for the XDP mode that uses + * one-frame-per-page, but have fallbacks that act like the + * regular page allocator APIs. + * + * refcnt == 1 means page_pool owns page, and can recycle it. + */ + if (likely(page_ref_count(page) == 1)) { + /* Read barrier done in page_ref_count / READ_ONCE */ + + if (allow_direct && in_serving_softirq()) + if (__page_pool_recycle_direct(page, pool)) + return; + + if (!__page_pool_recycle_into_ring(pool, page)) { + /* Cache full, fallback to free pages */ + __page_pool_return_page(pool, page); + } + return; + } + /* Fallback/non-XDP mode: API user have elevated refcnt. + * + * Many drivers split up the page into fragments, and some + * want to keep doing this to save memory and do refcnt based + * recycling. Support this use case too, to ease drivers + * switching between XDP/non-XDP. + * + * In-case page_pool maintains the DMA mapping, API user must + * call page_pool_put_page once. In this elevated refcnt + * case, the DMA is unmapped/released, as driver is likely + * doing refcnt based recycle tricks, meaning another process + * will be invoking put_page. + */ + __page_pool_clean_page(pool, page); + put_page(page); +} +EXPORT_SYMBOL(__page_pool_put_page); + +static void __page_pool_empty_ring(struct page_pool *pool) +{ + struct page *page; + + /* Empty recycle ring */ + while ((page = ptr_ring_consume(&pool->ring))) { + /* Verify the refcnt invariant of cached pages */ + if (!(page_ref_count(page) == 1)) + pr_crit("%s() page_pool refcnt %d violation\n", + __func__, page_ref_count(page)); + + __page_pool_return_page(pool, page); + } +} + +static void __page_pool_destroy_rcu(struct rcu_head *rcu) +{ + struct page_pool *pool; + + pool = container_of(rcu, struct page_pool, rcu); + + WARN(pool->alloc.count, "API usage violation"); + + __page_pool_empty_ring(pool); + ptr_ring_cleanup(&pool->ring, NULL); + kfree(pool); +} + +/* Cleanup and release resources */ +void page_pool_destroy(struct page_pool *pool) +{ + struct page *page; + + /* Empty alloc cache, assume caller made sure this is + * no-longer in use, and page_pool_alloc_pages() cannot be + * call concurrently. + */ + while (pool->alloc.count) { + page = pool->alloc.cache[--pool->alloc.count]; + __page_pool_return_page(pool, page); + } + + /* No more consumers should exist, but producers could still + * be in-flight. + */ + __page_pool_empty_ring(pool); + + /* An xdp_mem_allocator can still ref page_pool pointer */ + call_rcu(&pool->rcu, __page_pool_destroy_rcu); +} +EXPORT_SYMBOL(page_pool_destroy); diff --git a/net/core/rtnetlink.c b/net/core/rtnetlink.c index 45936922d7e2..80802546c279 100644 --- a/net/core/rtnetlink.c +++ b/net/core/rtnetlink.c @@ -785,13 +785,15 @@ int rtnl_put_cacheinfo(struct sk_buff *skb, struct dst_entry *dst, u32 id, long expires, u32 error) { struct rta_cacheinfo ci = { - .rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse), - .rta_used = dst->__use, - .rta_clntref = atomic_read(&(dst->__refcnt)), .rta_error = error, .rta_id = id, }; + if (dst) { + ci.rta_lastuse = jiffies_delta_to_clock_t(jiffies - dst->lastuse); + ci.rta_used = dst->__use; + ci.rta_clntref = atomic_read(&dst->__refcnt); + } if (expires) { unsigned long clock; diff --git a/net/core/skbuff.c b/net/core/skbuff.c index 345b51837ca8..c642304f178c 100644 --- a/net/core/skbuff.c +++ b/net/core/skbuff.c @@ -1305,7 +1305,7 @@ static void skb_headers_offset_update(struct sk_buff *skb, int off) skb->inner_mac_header += off; } -static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) +void skb_copy_header(struct sk_buff *new, const struct sk_buff *old) { __copy_skb_header(new, old); @@ -1313,6 +1313,7 @@ static void copy_skb_header(struct sk_buff *new, const struct sk_buff *old) skb_shinfo(new)->gso_segs = skb_shinfo(old)->gso_segs; skb_shinfo(new)->gso_type = skb_shinfo(old)->gso_type; } +EXPORT_SYMBOL(skb_copy_header); static inline int skb_alloc_rx_flag(const struct sk_buff *skb) { @@ -1355,7 +1356,7 @@ struct sk_buff *skb_copy(const struct sk_buff *skb, gfp_t gfp_mask) BUG_ON(skb_copy_bits(skb, -headerlen, n->head, headerlen + skb->len)); - copy_skb_header(n, skb); + skb_copy_header(n, skb); return n; } EXPORT_SYMBOL(skb_copy); @@ -1419,7 +1420,7 @@ struct sk_buff *__pskb_copy_fclone(struct sk_buff *skb, int headroom, skb_clone_fraglist(n); } - copy_skb_header(n, skb); + skb_copy_header(n, skb); out: return n; } @@ -1599,7 +1600,7 @@ struct sk_buff *skb_copy_expand(const struct sk_buff *skb, BUG_ON(skb_copy_bits(skb, -head_copy_len, n->head + head_copy_off, skb->len + head_copy_len)); - copy_skb_header(n, skb); + skb_copy_header(n, skb); skb_headers_offset_update(n, newheadroom - oldheadroom); @@ -1839,6 +1840,20 @@ done: } EXPORT_SYMBOL(___pskb_trim); +/* Note : use pskb_trim_rcsum() instead of calling this directly + */ +int pskb_trim_rcsum_slow(struct sk_buff *skb, unsigned int len) +{ + if (skb->ip_summed == CHECKSUM_COMPLETE) { + int delta = skb->len - len; + + skb->csum = csum_sub(skb->csum, + skb_checksum(skb, len, delta, 0)); + } + return __pskb_trim(skb, len); +} +EXPORT_SYMBOL(pskb_trim_rcsum_slow); + /** * __pskb_pull_tail - advance tail of skb header * @skb: buffer to reallocate @@ -4926,6 +4941,8 @@ static unsigned int skb_gso_transport_seglen(const struct sk_buff *skb) thlen = tcp_hdrlen(skb); } else if (unlikely(skb_is_gso_sctp(skb))) { thlen = sizeof(struct sctphdr); + } else if (shinfo->gso_type & SKB_GSO_UDP_L4) { + thlen = sizeof(struct udphdr); } /* UFO sets gso_size to the size of the fragmentation * payload, i.e. the size of the L4 (UDP) header is already diff --git a/net/core/sock.c b/net/core/sock.c index 6444525f610c..042cfc612660 100644 --- a/net/core/sock.c +++ b/net/core/sock.c @@ -226,7 +226,8 @@ static struct lock_class_key af_family_kern_slock_keys[AF_MAX]; x "AF_RXRPC" , x "AF_ISDN" , x "AF_PHONET" , \ x "AF_IEEE802154", x "AF_CAIF" , x "AF_ALG" , \ x "AF_NFC" , x "AF_VSOCK" , x "AF_KCM" , \ - x "AF_QIPCRTR", x "AF_SMC" , x "AF_MAX" + x "AF_QIPCRTR", x "AF_SMC" , x "AF_XDP" , \ + x "AF_MAX" static const char *const af_family_key_strings[AF_MAX+1] = { _sock_locks("sk_lock-") @@ -262,7 +263,8 @@ static const char *const af_family_rlock_key_strings[AF_MAX+1] = { "rlock-AF_RXRPC" , "rlock-AF_ISDN" , "rlock-AF_PHONET" , "rlock-AF_IEEE802154", "rlock-AF_CAIF" , "rlock-AF_ALG" , "rlock-AF_NFC" , "rlock-AF_VSOCK" , "rlock-AF_KCM" , - "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_MAX" + "rlock-AF_QIPCRTR", "rlock-AF_SMC" , "rlock-AF_XDP" , + "rlock-AF_MAX" }; static const char *const af_family_wlock_key_strings[AF_MAX+1] = { "wlock-AF_UNSPEC", "wlock-AF_UNIX" , "wlock-AF_INET" , @@ -279,7 +281,8 @@ static const char *const af_family_wlock_key_strings[AF_MAX+1] = { "wlock-AF_RXRPC" , "wlock-AF_ISDN" , "wlock-AF_PHONET" , "wlock-AF_IEEE802154", "wlock-AF_CAIF" , "wlock-AF_ALG" , "wlock-AF_NFC" , "wlock-AF_VSOCK" , "wlock-AF_KCM" , - "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_MAX" + "wlock-AF_QIPCRTR", "wlock-AF_SMC" , "wlock-AF_XDP" , + "wlock-AF_MAX" }; static const char *const af_family_elock_key_strings[AF_MAX+1] = { "elock-AF_UNSPEC", "elock-AF_UNIX" , "elock-AF_INET" , @@ -296,7 +299,8 @@ static const char *const af_family_elock_key_strings[AF_MAX+1] = { "elock-AF_RXRPC" , "elock-AF_ISDN" , "elock-AF_PHONET" , "elock-AF_IEEE802154", "elock-AF_CAIF" , "elock-AF_ALG" , "elock-AF_NFC" , "elock-AF_VSOCK" , "elock-AF_KCM" , - "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_MAX" + "elock-AF_QIPCRTR", "elock-AF_SMC" , "elock-AF_XDP" , + "elock-AF_MAX" }; /* @@ -323,8 +327,8 @@ EXPORT_SYMBOL(sysctl_optmem_max); int sysctl_tstamp_allow_data __read_mostly = 1; -struct static_key memalloc_socks = STATIC_KEY_INIT_FALSE; -EXPORT_SYMBOL_GPL(memalloc_socks); +DEFINE_STATIC_KEY_FALSE(memalloc_socks_key); +EXPORT_SYMBOL_GPL(memalloc_socks_key); /** * sk_set_memalloc - sets %SOCK_MEMALLOC @@ -338,7 +342,7 @@ void sk_set_memalloc(struct sock *sk) { sock_set_flag(sk, SOCK_MEMALLOC); sk->sk_allocation |= __GFP_MEMALLOC; - static_key_slow_inc(&memalloc_socks); + static_branch_inc(&memalloc_socks_key); } EXPORT_SYMBOL_GPL(sk_set_memalloc); @@ -346,7 +350,7 @@ void sk_clear_memalloc(struct sock *sk) { sock_reset_flag(sk, SOCK_MEMALLOC); sk->sk_allocation &= ~__GFP_MEMALLOC; - static_key_slow_dec(&memalloc_socks); + static_branch_dec(&memalloc_socks_key); /* * SOCK_MEMALLOC is allowed to ignore rmem limits to ensure forward @@ -905,7 +909,10 @@ set_rcvbuf: case SO_RCVLOWAT: if (val < 0) val = INT_MAX; - sk->sk_rcvlowat = val ? : 1; + if (sock->ops->set_rcvlowat) + ret = sock->ops->set_rcvlowat(sk, val); + else + sk->sk_rcvlowat = val ? : 1; break; case SO_RCVTIMEO: diff --git a/net/core/xdp.c b/net/core/xdp.c index 097a0f74e004..bf6758f74339 100644 --- a/net/core/xdp.c +++ b/net/core/xdp.c @@ -5,6 +5,10 @@ */ #include <linux/types.h> #include <linux/mm.h> +#include <linux/slab.h> +#include <linux/idr.h> +#include <linux/rhashtable.h> +#include <net/page_pool.h> #include <net/xdp.h> @@ -13,6 +17,104 @@ #define REG_STATE_UNREGISTERED 0x2 #define REG_STATE_UNUSED 0x3 +static DEFINE_IDA(mem_id_pool); +static DEFINE_MUTEX(mem_id_lock); +#define MEM_ID_MAX 0xFFFE +#define MEM_ID_MIN 1 +static int mem_id_next = MEM_ID_MIN; + +static bool mem_id_init; /* false */ +static struct rhashtable *mem_id_ht; + +struct xdp_mem_allocator { + struct xdp_mem_info mem; + union { + void *allocator; + struct page_pool *page_pool; + }; + struct rhash_head node; + struct rcu_head rcu; +}; + +static u32 xdp_mem_id_hashfn(const void *data, u32 len, u32 seed) +{ + const u32 *k = data; + const u32 key = *k; + + BUILD_BUG_ON(FIELD_SIZEOF(struct xdp_mem_allocator, mem.id) + != sizeof(u32)); + + /* Use cyclic increasing ID as direct hash key, see rht_bucket_index */ + return key << RHT_HASH_RESERVED_SPACE; +} + +static int xdp_mem_id_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) +{ + const struct xdp_mem_allocator *xa = ptr; + u32 mem_id = *(u32 *)arg->key; + + return xa->mem.id != mem_id; +} + +static const struct rhashtable_params mem_id_rht_params = { + .nelem_hint = 64, + .head_offset = offsetof(struct xdp_mem_allocator, node), + .key_offset = offsetof(struct xdp_mem_allocator, mem.id), + .key_len = FIELD_SIZEOF(struct xdp_mem_allocator, mem.id), + .max_size = MEM_ID_MAX, + .min_size = 8, + .automatic_shrinking = true, + .hashfn = xdp_mem_id_hashfn, + .obj_cmpfn = xdp_mem_id_cmp, +}; + +static void __xdp_mem_allocator_rcu_free(struct rcu_head *rcu) +{ + struct xdp_mem_allocator *xa; + + xa = container_of(rcu, struct xdp_mem_allocator, rcu); + + /* Allow this ID to be reused */ + ida_simple_remove(&mem_id_pool, xa->mem.id); + + /* Notice, driver is expected to free the *allocator, + * e.g. page_pool, and MUST also use RCU free. + */ + + /* Poison memory */ + xa->mem.id = 0xFFFF; + xa->mem.type = 0xF0F0; + xa->allocator = (void *)0xDEAD9001; + + kfree(xa); +} + +static void __xdp_rxq_info_unreg_mem_model(struct xdp_rxq_info *xdp_rxq) +{ + struct xdp_mem_allocator *xa; + int id = xdp_rxq->mem.id; + int err; + + if (id == 0) + return; + + mutex_lock(&mem_id_lock); + + xa = rhashtable_lookup(mem_id_ht, &id, mem_id_rht_params); + if (!xa) { + mutex_unlock(&mem_id_lock); + return; + } + + err = rhashtable_remove_fast(mem_id_ht, &xa->node, mem_id_rht_params); + WARN_ON(err); + + call_rcu(&xa->rcu, __xdp_mem_allocator_rcu_free); + + mutex_unlock(&mem_id_lock); +} + void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) { /* Simplify driver cleanup code paths, allow unreg "unused" */ @@ -21,8 +123,14 @@ void xdp_rxq_info_unreg(struct xdp_rxq_info *xdp_rxq) WARN(!(xdp_rxq->reg_state == REG_STATE_REGISTERED), "Driver BUG"); + __xdp_rxq_info_unreg_mem_model(xdp_rxq); + xdp_rxq->reg_state = REG_STATE_UNREGISTERED; xdp_rxq->dev = NULL; + + /* Reset mem info to defaults */ + xdp_rxq->mem.id = 0; + xdp_rxq->mem.type = 0; } EXPORT_SYMBOL_GPL(xdp_rxq_info_unreg); @@ -71,3 +179,173 @@ bool xdp_rxq_info_is_reg(struct xdp_rxq_info *xdp_rxq) return (xdp_rxq->reg_state == REG_STATE_REGISTERED); } EXPORT_SYMBOL_GPL(xdp_rxq_info_is_reg); + +static int __mem_id_init_hash_table(void) +{ + struct rhashtable *rht; + int ret; + + if (unlikely(mem_id_init)) + return 0; + + rht = kzalloc(sizeof(*rht), GFP_KERNEL); + if (!rht) + return -ENOMEM; + + ret = rhashtable_init(rht, &mem_id_rht_params); + if (ret < 0) { + kfree(rht); + return ret; + } + mem_id_ht = rht; + smp_mb(); /* mutex lock should provide enough pairing */ + mem_id_init = true; + + return 0; +} + +/* Allocate a cyclic ID that maps to allocator pointer. + * See: https://www.kernel.org/doc/html/latest/core-api/idr.html + * + * Caller must lock mem_id_lock. + */ +static int __mem_id_cyclic_get(gfp_t gfp) +{ + int retries = 1; + int id; + +again: + id = ida_simple_get(&mem_id_pool, mem_id_next, MEM_ID_MAX, gfp); + if (id < 0) { + if (id == -ENOSPC) { + /* Cyclic allocator, reset next id */ + if (retries--) { + mem_id_next = MEM_ID_MIN; + goto again; + } + } + return id; /* errno */ + } + mem_id_next = id + 1; + + return id; +} + +static bool __is_supported_mem_type(enum xdp_mem_type type) +{ + if (type == MEM_TYPE_PAGE_POOL) + return is_page_pool_compiled_in(); + + if (type >= MEM_TYPE_MAX) + return false; + + return true; +} + +int xdp_rxq_info_reg_mem_model(struct xdp_rxq_info *xdp_rxq, + enum xdp_mem_type type, void *allocator) +{ + struct xdp_mem_allocator *xdp_alloc; + gfp_t gfp = GFP_KERNEL; + int id, errno, ret; + void *ptr; + + if (xdp_rxq->reg_state != REG_STATE_REGISTERED) { + WARN(1, "Missing register, driver bug"); + return -EFAULT; + } + + if (!__is_supported_mem_type(type)) + return -EOPNOTSUPP; + + xdp_rxq->mem.type = type; + + if (!allocator) { + if (type == MEM_TYPE_PAGE_POOL) + return -EINVAL; /* Setup time check page_pool req */ + return 0; + } + + /* Delay init of rhashtable to save memory if feature isn't used */ + if (!mem_id_init) { + mutex_lock(&mem_id_lock); + ret = __mem_id_init_hash_table(); + mutex_unlock(&mem_id_lock); + if (ret < 0) { + WARN_ON(1); + return ret; + } + } + + xdp_alloc = kzalloc(sizeof(*xdp_alloc), gfp); + if (!xdp_alloc) + return -ENOMEM; + + mutex_lock(&mem_id_lock); + id = __mem_id_cyclic_get(gfp); + if (id < 0) { + errno = id; + goto err; + } + xdp_rxq->mem.id = id; + xdp_alloc->mem = xdp_rxq->mem; + xdp_alloc->allocator = allocator; + + /* Insert allocator into ID lookup table */ + ptr = rhashtable_insert_slow(mem_id_ht, &id, &xdp_alloc->node); + if (IS_ERR(ptr)) { + errno = PTR_ERR(ptr); + goto err; + } + + mutex_unlock(&mem_id_lock); + + return 0; +err: + mutex_unlock(&mem_id_lock); + kfree(xdp_alloc); + return errno; +} +EXPORT_SYMBOL_GPL(xdp_rxq_info_reg_mem_model); + +static void xdp_return(void *data, struct xdp_mem_info *mem) +{ + struct xdp_mem_allocator *xa; + struct page *page; + + switch (mem->type) { + case MEM_TYPE_PAGE_POOL: + rcu_read_lock(); + /* mem->id is valid, checked in xdp_rxq_info_reg_mem_model() */ + xa = rhashtable_lookup(mem_id_ht, &mem->id, mem_id_rht_params); + page = virt_to_head_page(data); + if (xa) + page_pool_put_page(xa->page_pool, page); + else + put_page(page); + rcu_read_unlock(); + break; + case MEM_TYPE_PAGE_SHARED: + page_frag_free(data); + break; + case MEM_TYPE_PAGE_ORDER0: + page = virt_to_page(data); /* Assumes order0 page*/ + put_page(page); + break; + default: + /* Not possible, checked in xdp_rxq_info_reg_mem_model() */ + break; + } +} + +void xdp_return_frame(struct xdp_frame *xdpf) +{ + xdp_return(xdpf->data, &xdpf->mem); +} +EXPORT_SYMBOL_GPL(xdp_return_frame); + +void xdp_return_buff(struct xdp_buff *xdp) +{ + xdp_return(xdp->data, &xdp->rxq->mem); +} +EXPORT_SYMBOL_GPL(xdp_return_buff); diff --git a/net/decnet/dn_rules.c b/net/decnet/dn_rules.c index c795c3f509c9..72236695db3d 100644 --- a/net/decnet/dn_rules.c +++ b/net/decnet/dn_rules.c @@ -121,13 +121,16 @@ static int dn_fib_rule_match(struct fib_rule *rule, struct flowi *fl, int flags) static int dn_fib_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, - struct nlattr **tb) + struct nlattr **tb, + struct netlink_ext_ack *extack) { int err = -EINVAL; struct dn_fib_rule *r = (struct dn_fib_rule *)rule; - if (frh->tos) + if (frh->tos) { + NL_SET_ERR_MSG(extack, "Invalid tos value"); goto errout; + } if (rule->table == RT_TABLE_UNSPEC) { if (rule->action == FR_ACT_TO_TBL) { diff --git a/net/dsa/Kconfig b/net/dsa/Kconfig index bbf2c82cf7b2..4183e4ba27a5 100644 --- a/net/dsa/Kconfig +++ b/net/dsa/Kconfig @@ -9,7 +9,7 @@ config NET_DSA depends on HAVE_NET_DSA && MAY_USE_DEVLINK depends on BRIDGE || BRIDGE=n select NET_SWITCHDEV - select PHYLIB + select PHYLINK ---help--- Say Y if you want to enable support for the hardware switches supported by the Distributed Switch Architecture. diff --git a/net/dsa/dsa_priv.h b/net/dsa/dsa_priv.h index 053731473c99..3964c6f7a7c0 100644 --- a/net/dsa/dsa_priv.h +++ b/net/dsa/dsa_priv.h @@ -75,15 +75,6 @@ struct dsa_slave_priv { /* DSA port data, such as switch, port index, etc. */ struct dsa_port *dp; - /* - * The phylib phy_device pointer for the PHY connected - * to this port. - */ - phy_interface_t phy_interface; - int old_link; - int old_pause; - int old_duplex; - #ifdef CONFIG_NET_POLL_CONTROLLER struct netpoll *netpoll; #endif diff --git a/net/dsa/master.c b/net/dsa/master.c index 90e6df0351eb..c90ee3227dea 100644 --- a/net/dsa/master.c +++ b/net/dsa/master.c @@ -22,7 +22,7 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, int port = cpu_dp->index; int count = 0; - if (ops && ops->get_sset_count && ops->get_ethtool_stats) { + if (ops->get_sset_count && ops->get_ethtool_stats) { count = ops->get_sset_count(dev, ETH_SS_STATS); ops->get_ethtool_stats(dev, stats, data); } @@ -31,6 +31,32 @@ static void dsa_master_get_ethtool_stats(struct net_device *dev, ds->ops->get_ethtool_stats(ds, port, data + count); } +static void dsa_master_get_ethtool_phy_stats(struct net_device *dev, + struct ethtool_stats *stats, + uint64_t *data) +{ + struct dsa_port *cpu_dp = dev->dsa_ptr; + const struct ethtool_ops *ops = cpu_dp->orig_ethtool_ops; + struct dsa_switch *ds = cpu_dp->ds; + int port = cpu_dp->index; + int count = 0; + + if (dev->phydev && !ops->get_ethtool_phy_stats) { + count = phy_ethtool_get_sset_count(dev->phydev); + if (count >= 0) + phy_ethtool_get_stats(dev->phydev, stats, data); + } else if (ops->get_sset_count && ops->get_ethtool_phy_stats) { + count = ops->get_sset_count(dev, ETH_SS_PHY_STATS); + ops->get_ethtool_phy_stats(dev, stats, data); + } + + if (count < 0) + count = 0; + + if (ds->ops->get_ethtool_phy_stats) + ds->ops->get_ethtool_phy_stats(ds, port, data + count); +} + static int dsa_master_get_sset_count(struct net_device *dev, int sset) { struct dsa_port *cpu_dp = dev->dsa_ptr; @@ -38,11 +64,17 @@ static int dsa_master_get_sset_count(struct net_device *dev, int sset) struct dsa_switch *ds = cpu_dp->ds; int count = 0; - if (ops && ops->get_sset_count) - count += ops->get_sset_count(dev, sset); + if (sset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) + count = phy_ethtool_get_sset_count(dev->phydev); + else if (ops->get_sset_count) + count = ops->get_sset_count(dev, sset); + + if (count < 0) + count = 0; - if (sset == ETH_SS_STATS && ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, cpu_dp->index); + if (ds->ops->get_sset_count) + count += ds->ops->get_sset_count(ds, cpu_dp->index, sset); return count; } @@ -64,19 +96,28 @@ static void dsa_master_get_strings(struct net_device *dev, uint32_t stringset, /* We do not want to be NULL-terminated, since this is a prefix */ pfx[sizeof(pfx) - 1] = '_'; - if (ops && ops->get_sset_count && ops->get_strings) { - mcount = ops->get_sset_count(dev, ETH_SS_STATS); + if (stringset == ETH_SS_PHY_STATS && dev->phydev && + !ops->get_ethtool_phy_stats) { + mcount = phy_ethtool_get_sset_count(dev->phydev); + if (mcount < 0) + mcount = 0; + else + phy_ethtool_get_strings(dev->phydev, data); + } else if (ops->get_sset_count && ops->get_strings) { + mcount = ops->get_sset_count(dev, stringset); + if (mcount < 0) + mcount = 0; ops->get_strings(dev, stringset, data); } - if (stringset == ETH_SS_STATS && ds->ops->get_strings) { + if (ds->ops->get_strings) { ndata = data + mcount * len; /* This function copies ETH_GSTRINGS_LEN bytes, we will mangle * the output after to prepend our CPU port prefix we * constructed earlier */ - ds->ops->get_strings(ds, port, ndata); - count = ds->ops->get_sset_count(ds, port); + ds->ops->get_strings(ds, port, stringset, ndata); + count = ds->ops->get_sset_count(ds, port, stringset); for (i = 0; i < count; i++) { memmove(ndata + (i * len + sizeof(pfx)), ndata + i * len, len - sizeof(pfx)); @@ -102,6 +143,7 @@ static int dsa_master_ethtool_setup(struct net_device *dev) ops->get_sset_count = dsa_master_get_sset_count; ops->get_ethtool_stats = dsa_master_get_ethtool_stats; ops->get_strings = dsa_master_get_strings; + ops->get_ethtool_phy_stats = dsa_master_get_ethtool_phy_stats; dev->ethtool_ops = ops; diff --git a/net/dsa/port.c b/net/dsa/port.c index 7acc1169d75e..2413beb995be 100644 --- a/net/dsa/port.c +++ b/net/dsa/port.c @@ -273,25 +273,38 @@ int dsa_port_vlan_del(struct dsa_port *dp, return 0; } -static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) +static struct phy_device *dsa_port_get_phy_device(struct dsa_port *dp) { - struct device_node *port_dn = dp->dn; struct device_node *phy_dn; - struct dsa_switch *ds = dp->ds; struct phy_device *phydev; - int port = dp->index; - int err = 0; - phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); + phy_dn = of_parse_phandle(dp->dn, "phy-handle", 0); if (!phy_dn) - return 0; + return NULL; phydev = of_phy_find_device(phy_dn); if (!phydev) { - err = -EPROBE_DEFER; - goto err_put_of; + of_node_put(phy_dn); + return ERR_PTR(-EPROBE_DEFER); } + return phydev; +} + +static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) +{ + struct dsa_switch *ds = dp->ds; + struct phy_device *phydev; + int port = dp->index; + int err = 0; + + phydev = dsa_port_get_phy_device(dp); + if (!phydev) + return 0; + + if (IS_ERR(phydev)) + return PTR_ERR(phydev); + if (enable) { err = genphy_config_init(phydev); if (err < 0) @@ -317,8 +330,6 @@ static int dsa_port_setup_phy_of(struct dsa_port *dp, bool enable) err_put_dev: put_device(&phydev->mdio.dev); -err_put_of: - of_node_put(phy_dn); return err; } @@ -372,3 +383,60 @@ void dsa_port_link_unregister_of(struct dsa_port *dp) else dsa_port_setup_phy_of(dp, false); } + +int dsa_port_get_phy_strings(struct dsa_port *dp, uint8_t *data) +{ + struct phy_device *phydev; + int ret = -EOPNOTSUPP; + + if (of_phy_is_fixed_link(dp->dn)) + return ret; + + phydev = dsa_port_get_phy_device(dp); + if (IS_ERR_OR_NULL(phydev)) + return ret; + + ret = phy_ethtool_get_strings(phydev, data); + put_device(&phydev->mdio.dev); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_port_get_phy_strings); + +int dsa_port_get_ethtool_phy_stats(struct dsa_port *dp, uint64_t *data) +{ + struct phy_device *phydev; + int ret = -EOPNOTSUPP; + + if (of_phy_is_fixed_link(dp->dn)) + return ret; + + phydev = dsa_port_get_phy_device(dp); + if (IS_ERR_OR_NULL(phydev)) + return ret; + + ret = phy_ethtool_get_stats(phydev, NULL, data); + put_device(&phydev->mdio.dev); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_port_get_ethtool_phy_stats); + +int dsa_port_get_phy_sset_count(struct dsa_port *dp) +{ + struct phy_device *phydev; + int ret = -EOPNOTSUPP; + + if (of_phy_is_fixed_link(dp->dn)) + return ret; + + phydev = dsa_port_get_phy_device(dp); + if (IS_ERR_OR_NULL(phydev)) + return ret; + + ret = phy_ethtool_get_sset_count(phydev); + put_device(&phydev->mdio.dev); + + return ret; +} +EXPORT_SYMBOL_GPL(dsa_port_get_phy_sset_count); diff --git a/net/dsa/slave.c b/net/dsa/slave.c index 18561af7a8f1..1e3b6a6d8a40 100644 --- a/net/dsa/slave.c +++ b/net/dsa/slave.c @@ -13,6 +13,7 @@ #include <linux/netdevice.h> #include <linux/phy.h> #include <linux/phy_fixed.h> +#include <linux/phylink.h> #include <linux/of_net.h> #include <linux/of_mdio.h> #include <linux/mdio.h> @@ -97,8 +98,7 @@ static int dsa_slave_open(struct net_device *dev) if (err) goto clear_promisc; - if (dev->phydev) - phy_start(dev->phydev); + phylink_start(dp->pl); return 0; @@ -120,8 +120,7 @@ static int dsa_slave_close(struct net_device *dev) struct net_device *master = dsa_slave_to_master(dev); struct dsa_port *dp = dsa_slave_to_port(dev); - if (dev->phydev) - phy_stop(dev->phydev); + phylink_stop(dp->pl); dsa_port_disable(dp, dev->phydev); @@ -272,10 +271,7 @@ static int dsa_slave_ioctl(struct net_device *dev, struct ifreq *ifr, int cmd) break; } - if (!dev->phydev) - return -ENODEV; - - return phy_mii_ioctl(dev->phydev, ifr, cmd); + return phylink_mii_ioctl(p->dp->pl, ifr, cmd); } static int dsa_slave_port_attr_set(struct net_device *dev, @@ -498,14 +494,11 @@ dsa_slave_get_regs(struct net_device *dev, struct ethtool_regs *regs, void *_p) ds->ops->get_regs(ds, dp->index, regs, _p); } -static u32 dsa_slave_get_link(struct net_device *dev) +static int dsa_slave_nway_reset(struct net_device *dev) { - if (!dev->phydev) - return -ENODEV; - - genphy_update_link(dev->phydev); + struct dsa_port *dp = dsa_slave_to_port(dev); - return dev->phydev->link; + return phylink_ethtool_nway_reset(dp->pl); } static int dsa_slave_get_eeprom_len(struct net_device *dev) @@ -560,7 +553,8 @@ static void dsa_slave_get_strings(struct net_device *dev, strncpy(data + 2 * len, "rx_packets", len); strncpy(data + 3 * len, "rx_bytes", len); if (ds->ops->get_strings) - ds->ops->get_strings(ds, dp->index, data + 4 * len); + ds->ops->get_strings(ds, dp->index, stringset, + data + 4 * len); } } @@ -605,7 +599,7 @@ static int dsa_slave_get_sset_count(struct net_device *dev, int sset) count = 4; if (ds->ops->get_sset_count) - count += ds->ops->get_sset_count(ds, dp->index); + count += ds->ops->get_sset_count(ds, dp->index, sset); return count; } @@ -618,6 +612,8 @@ static void dsa_slave_get_wol(struct net_device *dev, struct ethtool_wolinfo *w) struct dsa_port *dp = dsa_slave_to_port(dev); struct dsa_switch *ds = dp->ds; + phylink_ethtool_get_wol(dp->pl, w); + if (ds->ops->get_wol) ds->ops->get_wol(ds, dp->index, w); } @@ -628,6 +624,8 @@ static int dsa_slave_set_wol(struct net_device *dev, struct ethtool_wolinfo *w) struct dsa_switch *ds = dp->ds; int ret = -EOPNOTSUPP; + phylink_ethtool_set_wol(dp->pl, w); + if (ds->ops->set_wol) ret = ds->ops->set_wol(ds, dp->index, w); @@ -651,13 +649,7 @@ static int dsa_slave_set_eee(struct net_device *dev, struct ethtool_eee *e) if (ret) return ret; - if (e->eee_enabled) { - ret = phy_init_eee(dev->phydev, 0); - if (ret) - return ret; - } - - return phy_ethtool_set_eee(dev->phydev, e); + return phylink_ethtool_set_eee(dp->pl, e); } static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) @@ -677,7 +669,23 @@ static int dsa_slave_get_eee(struct net_device *dev, struct ethtool_eee *e) if (ret) return ret; - return phy_ethtool_get_eee(dev->phydev, e); + return phylink_ethtool_get_eee(dp->pl, e); +} + +static int dsa_slave_get_link_ksettings(struct net_device *dev, + struct ethtool_link_ksettings *cmd) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return phylink_ethtool_ksettings_get(dp->pl, cmd); +} + +static int dsa_slave_set_link_ksettings(struct net_device *dev, + const struct ethtool_link_ksettings *cmd) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + + return phylink_ethtool_ksettings_set(dp->pl, cmd); } #ifdef CONFIG_NET_POLL_CONTROLLER @@ -980,8 +988,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_drvinfo = dsa_slave_get_drvinfo, .get_regs_len = dsa_slave_get_regs_len, .get_regs = dsa_slave_get_regs, - .nway_reset = phy_ethtool_nway_reset, - .get_link = dsa_slave_get_link, + .nway_reset = dsa_slave_nway_reset, + .get_link = ethtool_op_get_link, .get_eeprom_len = dsa_slave_get_eeprom_len, .get_eeprom = dsa_slave_get_eeprom, .set_eeprom = dsa_slave_set_eeprom, @@ -992,8 +1000,8 @@ static const struct ethtool_ops dsa_slave_ethtool_ops = { .get_wol = dsa_slave_get_wol, .set_eee = dsa_slave_set_eee, .get_eee = dsa_slave_get_eee, - .get_link_ksettings = phy_ethtool_get_link_ksettings, - .set_link_ksettings = phy_ethtool_set_link_ksettings, + .get_link_ksettings = dsa_slave_get_link_ksettings, + .set_link_ksettings = dsa_slave_set_link_ksettings, .get_rxnfc = dsa_slave_get_rxnfc, .set_rxnfc = dsa_slave_set_rxnfc, .get_ts_info = dsa_slave_get_ts_info, @@ -1052,56 +1060,122 @@ static struct device_type dsa_type = { .name = "dsa", }; -static void dsa_slave_adjust_link(struct net_device *dev) +static void dsa_slave_phylink_validate(struct net_device *dev, + unsigned long *supported, + struct phylink_link_state *state) { struct dsa_port *dp = dsa_slave_to_port(dev); - struct dsa_slave_priv *p = netdev_priv(dev); struct dsa_switch *ds = dp->ds; - unsigned int status_changed = 0; - if (p->old_link != dev->phydev->link) { - status_changed = 1; - p->old_link = dev->phydev->link; - } + if (!ds->ops->phylink_validate) + return; - if (p->old_duplex != dev->phydev->duplex) { - status_changed = 1; - p->old_duplex = dev->phydev->duplex; - } + ds->ops->phylink_validate(ds, dp->index, supported, state); +} - if (p->old_pause != dev->phydev->pause) { - status_changed = 1; - p->old_pause = dev->phydev->pause; - } +static int dsa_slave_phylink_mac_link_state(struct net_device *dev, + struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + /* Only called for SGMII and 802.3z */ + if (!ds->ops->phylink_mac_link_state) + return -EOPNOTSUPP; + + return ds->ops->phylink_mac_link_state(ds, dp->index, state); +} + +static void dsa_slave_phylink_mac_config(struct net_device *dev, + unsigned int mode, + const struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_mac_config) + return; + + ds->ops->phylink_mac_config(ds, dp->index, mode, state); +} - if (ds->ops->adjust_link && status_changed) - ds->ops->adjust_link(ds, dp->index, dev->phydev); +static void dsa_slave_phylink_mac_an_restart(struct net_device *dev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; - if (status_changed) - phy_print_status(dev->phydev); + if (!ds->ops->phylink_mac_an_restart) + return; + + ds->ops->phylink_mac_an_restart(ds, dp->index); } -static int dsa_slave_fixed_link_update(struct net_device *dev, - struct fixed_phy_status *status) +static void dsa_slave_phylink_mac_link_down(struct net_device *dev, + unsigned int mode, + phy_interface_t interface) { - struct dsa_switch *ds; - struct dsa_port *dp; + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; - if (dev) { - dp = dsa_slave_to_port(dev); - ds = dp->ds; - if (ds->ops->fixed_link_update) - ds->ops->fixed_link_update(ds, dp->index, status); + if (!ds->ops->phylink_mac_link_down) { + if (ds->ops->adjust_link && dev->phydev) + ds->ops->adjust_link(ds, dp->index, dev->phydev); + return; } - return 0; + ds->ops->phylink_mac_link_down(ds, dp->index, mode, interface); +} + +static void dsa_slave_phylink_mac_link_up(struct net_device *dev, + unsigned int mode, + phy_interface_t interface, + struct phy_device *phydev) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + if (!ds->ops->phylink_mac_link_up) { + if (ds->ops->adjust_link && dev->phydev) + ds->ops->adjust_link(ds, dp->index, dev->phydev); + return; + } + + ds->ops->phylink_mac_link_up(ds, dp->index, mode, interface, phydev); +} + +static const struct phylink_mac_ops dsa_slave_phylink_mac_ops = { + .validate = dsa_slave_phylink_validate, + .mac_link_state = dsa_slave_phylink_mac_link_state, + .mac_config = dsa_slave_phylink_mac_config, + .mac_an_restart = dsa_slave_phylink_mac_an_restart, + .mac_link_down = dsa_slave_phylink_mac_link_down, + .mac_link_up = dsa_slave_phylink_mac_link_up, +}; + +void dsa_port_phylink_mac_change(struct dsa_switch *ds, int port, bool up) +{ + const struct dsa_port *dp = dsa_to_port(ds, port); + + phylink_mac_change(dp->pl, up); +} +EXPORT_SYMBOL_GPL(dsa_port_phylink_mac_change); + +static void dsa_slave_phylink_fixed_state(struct net_device *dev, + struct phylink_link_state *state) +{ + struct dsa_port *dp = dsa_slave_to_port(dev); + struct dsa_switch *ds = dp->ds; + + /* No need to check that this operation is valid, the callback would + * not be called if it was not. + */ + ds->ops->phylink_fixed_state(ds, dp->index, state); } /* slave device setup *******************************************************/ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_slave_priv *p = netdev_priv(slave_dev); struct dsa_switch *ds = dp->ds; slave_dev->phydev = mdiobus_get_phy(ds->slave_mii_bus, addr); @@ -1110,75 +1184,54 @@ static int dsa_slave_phy_connect(struct net_device *slave_dev, int addr) return -ENODEV; } - /* Use already configured phy mode */ - if (p->phy_interface == PHY_INTERFACE_MODE_NA) - p->phy_interface = slave_dev->phydev->interface; - - return phy_connect_direct(slave_dev, slave_dev->phydev, - dsa_slave_adjust_link, p->phy_interface); + return phylink_connect_phy(dp->pl, slave_dev->phydev); } static int dsa_slave_phy_setup(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); - struct dsa_slave_priv *p = netdev_priv(slave_dev); struct device_node *port_dn = dp->dn; struct dsa_switch *ds = dp->ds; - struct device_node *phy_dn; - bool phy_is_fixed = false; u32 phy_flags = 0; int mode, ret; mode = of_get_phy_mode(port_dn); if (mode < 0) mode = PHY_INTERFACE_MODE_NA; - p->phy_interface = mode; - phy_dn = of_parse_phandle(port_dn, "phy-handle", 0); - if (!phy_dn && of_phy_is_fixed_link(port_dn)) { - /* In the case of a fixed PHY, the DT node associated - * to the fixed PHY is the Port DT node - */ - ret = of_phy_register_fixed_link(port_dn); - if (ret) { - netdev_err(slave_dev, "failed to register fixed PHY: %d\n", ret); - return ret; - } - phy_is_fixed = true; - phy_dn = of_node_get(port_dn); + dp->pl = phylink_create(slave_dev, of_fwnode_handle(port_dn), mode, + &dsa_slave_phylink_mac_ops); + if (IS_ERR(dp->pl)) { + netdev_err(slave_dev, + "error creating PHYLINK: %ld\n", PTR_ERR(dp->pl)); + return PTR_ERR(dp->pl); } + /* Register only if the switch provides such a callback, since this + * callback takes precedence over polling the link GPIO in PHYLINK + * (see phylink_get_fixed_state). + */ + if (ds->ops->phylink_fixed_state) + phylink_fixed_state_cb(dp->pl, dsa_slave_phylink_fixed_state); + if (ds->ops->get_phy_flags) phy_flags = ds->ops->get_phy_flags(ds, dp->index); - if (phy_dn) { - slave_dev->phydev = of_phy_connect(slave_dev, phy_dn, - dsa_slave_adjust_link, - phy_flags, - p->phy_interface); - of_node_put(phy_dn); - } - - if (slave_dev->phydev && phy_is_fixed) - fixed_phy_set_link_update(slave_dev->phydev, - dsa_slave_fixed_link_update); - - /* We could not connect to a designated PHY, so use the switch internal - * MDIO bus instead - */ - if (!slave_dev->phydev) { + ret = phylink_of_phy_connect(dp->pl, port_dn, phy_flags); + if (ret == -ENODEV) { + /* We could not connect to a designated PHY or SFP, so use the + * switch internal MDIO bus instead + */ ret = dsa_slave_phy_connect(slave_dev, dp->index); if (ret) { - netdev_err(slave_dev, "failed to connect to port %d: %d\n", + netdev_err(slave_dev, + "failed to connect to port %d: %d\n", dp->index, ret); - if (phy_is_fixed) - of_phy_deregister_fixed_link(port_dn); + phylink_destroy(dp->pl); return ret; } } - phy_attached_info(slave_dev->phydev); - return 0; } @@ -1193,29 +1246,26 @@ static void dsa_slave_set_lockdep_class_one(struct net_device *dev, int dsa_slave_suspend(struct net_device *slave_dev) { - struct dsa_slave_priv *p = netdev_priv(slave_dev); + struct dsa_port *dp = dsa_slave_to_port(slave_dev); netif_device_detach(slave_dev); - if (slave_dev->phydev) { - phy_stop(slave_dev->phydev); - p->old_pause = -1; - p->old_link = -1; - p->old_duplex = -1; - phy_suspend(slave_dev->phydev); - } + rtnl_lock(); + phylink_stop(dp->pl); + rtnl_unlock(); return 0; } int dsa_slave_resume(struct net_device *slave_dev) { + struct dsa_port *dp = dsa_slave_to_port(slave_dev); + netif_device_attach(slave_dev); - if (slave_dev->phydev) { - phy_resume(slave_dev->phydev); - phy_start(slave_dev->phydev); - } + rtnl_lock(); + phylink_start(dp->pl); + rtnl_unlock(); return 0; } @@ -1280,11 +1330,6 @@ int dsa_slave_create(struct dsa_port *port) p->dp = port; INIT_LIST_HEAD(&p->mall_tc_list); p->xmit = cpu_dp->tag_ops->xmit; - - p->old_pause = -1; - p->old_link = -1; - p->old_duplex = -1; - port->slave = slave_dev; netif_carrier_off(slave_dev); @@ -1307,9 +1352,10 @@ int dsa_slave_create(struct dsa_port *port) return 0; out_phy: - phy_disconnect(slave_dev->phydev); - if (of_phy_is_fixed_link(port->dn)) - of_phy_deregister_fixed_link(port->dn); + rtnl_lock(); + phylink_disconnect_phy(p->dp->pl); + rtnl_unlock(); + phylink_destroy(p->dp->pl); out_free: free_percpu(p->stats64); free_netdev(slave_dev); @@ -1321,17 +1367,15 @@ void dsa_slave_destroy(struct net_device *slave_dev) { struct dsa_port *dp = dsa_slave_to_port(slave_dev); struct dsa_slave_priv *p = netdev_priv(slave_dev); - struct device_node *port_dn = dp->dn; netif_carrier_off(slave_dev); - if (slave_dev->phydev) { - phy_disconnect(slave_dev->phydev); + rtnl_lock(); + phylink_disconnect_phy(dp->pl); + rtnl_unlock(); - if (of_phy_is_fixed_link(port_dn)) - of_phy_deregister_fixed_link(port_dn); - } dsa_slave_notify(slave_dev, DSA_PORT_UNREGISTER); unregister_netdev(slave_dev); + phylink_destroy(dp->pl); free_percpu(p->stats64); free_netdev(slave_dev); } @@ -1394,6 +1438,9 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) switch (switchdev_work->event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; + err = dsa_port_fdb_add(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb add failed err=%d\n", err); @@ -1405,6 +1452,9 @@ static void dsa_slave_switchdev_event_work(struct work_struct *work) case SWITCHDEV_FDB_DEL_TO_DEVICE: fdb_info = &switchdev_work->fdb_info; + if (!fdb_info->added_by_user) + break; + err = dsa_port_fdb_del(dp, fdb_info->addr, fdb_info->vid); if (err) { netdev_dbg(dev, "fdb del failed err=%d\n", err); @@ -1457,8 +1507,7 @@ static int dsa_slave_switchdev_event(struct notifier_block *unused, switch (event) { case SWITCHDEV_FDB_ADD_TO_DEVICE: /* fall through */ case SWITCHDEV_FDB_DEL_TO_DEVICE: - if (dsa_slave_switchdev_fdb_work_init(switchdev_work, - ptr)) + if (dsa_slave_switchdev_fdb_work_init(switchdev_work, ptr)) goto err_fdb_work_init; dev_hold(dev); break; diff --git a/net/ethernet/eth.c b/net/ethernet/eth.c index eaeba9b99a73..ee28440f57c5 100644 --- a/net/ethernet/eth.c +++ b/net/ethernet/eth.c @@ -128,15 +128,15 @@ u32 eth_get_headlen(void *data, unsigned int len) { const unsigned int flags = FLOW_DISSECTOR_F_PARSE_1ST_FRAG; const struct ethhdr *eth = (const struct ethhdr *)data; - struct flow_keys keys; + struct flow_keys_basic keys; /* this should never happen, but better safe than sorry */ if (unlikely(len < sizeof(*eth))) return len; /* parse any remaining L2/L3 headers, check for L4 */ - if (!skb_flow_dissect_flow_keys_buf(&keys, data, eth->h_proto, - sizeof(*eth), len, flags)) + if (!skb_flow_dissect_flow_keys_basic(NULL, &keys, data, eth->h_proto, + sizeof(*eth), len, flags)) return max_t(u32, keys.control.thoff, sizeof(*eth)); /* parse for any L4 headers */ diff --git a/net/ipv4/Makefile b/net/ipv4/Makefile index a07b7dd06def..b379520f9133 100644 --- a/net/ipv4/Makefile +++ b/net/ipv4/Makefile @@ -13,7 +13,8 @@ obj-y := route.o inetpeer.o protocol.o \ tcp_offload.o datagram.o raw.o udp.o udplite.o \ udp_offload.o arp.o icmp.o devinet.o af_inet.o igmp.o \ fib_frontend.o fib_semantics.o fib_trie.o fib_notifier.o \ - inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o + inet_fragment.o ping.o ip_tunnel_core.o gre_offload.o \ + metrics.o obj-$(CONFIG_NET_IP_TUNNEL) += ip_tunnel.o obj-$(CONFIG_SYSCTL) += sysctl_net_ipv4.o diff --git a/net/ipv4/af_inet.c b/net/ipv4/af_inet.c index eaed0367e669..b403499fdabe 100644 --- a/net/ipv4/af_inet.c +++ b/net/ipv4/af_inet.c @@ -994,7 +994,9 @@ const struct proto_ops inet_stream_ops = { .getsockopt = sock_common_getsockopt, .sendmsg = inet_sendmsg, .recvmsg = inet_recvmsg, - .mmap = sock_no_mmap, +#ifdef CONFIG_MMU + .mmap = tcp_mmap, +#endif .sendpage = inet_sendpage, .splice_read = tcp_splice_read, .read_sock = tcp_read_sock, @@ -1006,6 +1008,7 @@ const struct proto_ops inet_stream_ops = { .compat_getsockopt = compat_sock_common_getsockopt, .compat_ioctl = inet_compat_ioctl, #endif + .set_rcvlowat = tcp_set_rcvlowat, }; EXPORT_SYMBOL(inet_stream_ops); diff --git a/net/ipv4/fib_rules.c b/net/ipv4/fib_rules.c index 737d11bc8838..f8eb78d042a4 100644 --- a/net/ipv4/fib_rules.c +++ b/net/ipv4/fib_rules.c @@ -213,14 +213,17 @@ static const struct nla_policy fib4_rule_policy[FRA_MAX+1] = { static int fib4_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, - struct nlattr **tb) + struct nlattr **tb, + struct netlink_ext_ack *extack) { struct net *net = sock_net(skb->sk); int err = -EINVAL; struct fib4_rule *rule4 = (struct fib4_rule *) rule; - if (frh->tos & ~IPTOS_TOS_MASK) + if (frh->tos & ~IPTOS_TOS_MASK) { + NL_SET_ERR_MSG(extack, "Invalid tos"); goto errout; + } /* split local/main if they are not already split */ err = fib_unmerge(net); diff --git a/net/ipv4/fib_semantics.c b/net/ipv4/fib_semantics.c index c27122f01b87..6608db23f54b 100644 --- a/net/ipv4/fib_semantics.c +++ b/net/ipv4/fib_semantics.c @@ -1019,47 +1019,8 @@ static bool fib_valid_prefsrc(struct fib_config *cfg, __be32 fib_prefsrc) static int fib_convert_metrics(struct fib_info *fi, const struct fib_config *cfg) { - bool ecn_ca = false; - struct nlattr *nla; - int remaining; - - if (!cfg->fc_mx) - return 0; - - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - u32 val; - - if (!type) - continue; - if (type > RTAX_MAX) - return -EINVAL; - - if (type == RTAX_CC_ALGO) { - char tmp[TCP_CA_NAME_MAX]; - - nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(fi->fib_net, tmp, &ecn_ca); - if (val == TCP_CA_UNSPEC) - return -EINVAL; - } else { - val = nla_get_u32(nla); - } - if (type == RTAX_ADVMSS && val > 65535 - 40) - val = 65535 - 40; - if (type == RTAX_MTU && val > 65535 - 15) - val = 65535 - 15; - if (type == RTAX_HOPLIMIT && val > 255) - val = 255; - if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) - return -EINVAL; - fi->fib_metrics->metrics[type - 1] = val; - } - - if (ecn_ca) - fi->fib_metrics->metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; - - return 0; + return ip_metrics_convert(fi->fib_net, cfg->fc_mx, cfg->fc_mx_len, + fi->fib_metrics->metrics); } struct fib_info *fib_create_info(struct fib_config *cfg, diff --git a/net/ipv4/inet_connection_sock.c b/net/ipv4/inet_connection_sock.c index 881ac6d046f2..33a88e045efd 100644 --- a/net/ipv4/inet_connection_sock.c +++ b/net/ipv4/inet_connection_sock.c @@ -27,11 +27,6 @@ #include <net/sock_reuseport.h> #include <net/addrconf.h> -#ifdef INET_CSK_DEBUG -const char inet_csk_timer_bug_msg[] = "inet_csk BUG: unknown timer value\n"; -EXPORT_SYMBOL(inet_csk_timer_bug_msg); -#endif - #if IS_ENABLED(CONFIG_IPV6) /* match_wildcard == true: IPV6_ADDR_ANY equals to any IPv6 addresses if IPv6 * only, and any IPv4 addresses if not IPv6 only diff --git a/net/ipv4/ip_gre.c b/net/ipv4/ip_gre.c index 9c169bb2444d..2409e648454d 100644 --- a/net/ipv4/ip_gre.c +++ b/net/ipv4/ip_gre.c @@ -578,6 +578,8 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, int tunnel_hlen; int version; __be16 df; + int nhoff; + int thoff; tun_info = skb_tunnel_info(skb); if (unlikely(!tun_info || !(tun_info->mode & IP_TUNNEL_INFO_TX) || @@ -605,6 +607,16 @@ static void erspan_fb_xmit(struct sk_buff *skb, struct net_device *dev, truncate = true; } + nhoff = skb_network_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IP) && + (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) + truncate = true; + + thoff = skb_transport_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IPV6) && + (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) + truncate = true; + if (version == 1) { erspan_build_header(skb, ntohl(tunnel_id_to_key32(key->tun_id)), ntohl(md->u.index), truncate, true); diff --git a/net/ipv4/ip_output.c b/net/ipv4/ip_output.c index 83c73bab2c3d..b5e21eb198d8 100644 --- a/net/ipv4/ip_output.c +++ b/net/ipv4/ip_output.c @@ -878,11 +878,14 @@ static int __ip_append_data(struct sock *sk, struct rtable *rt = (struct rtable *)cork->dst; unsigned int wmem_alloc_delta = 0; u32 tskey = 0; + bool paged; skb = skb_peek_tail(queue); exthdrlen = !skb ? rt->dst.header_len : 0; - mtu = cork->fragsize; + mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; + paged = !!cork->gso_size; + if (cork->tx_flags & SKBTX_ANY_SW_TSTAMP && sk->sk_tsflags & SOF_TIMESTAMPING_OPT_ID) tskey = sk->sk_tskey++; @@ -906,8 +909,8 @@ static int __ip_append_data(struct sock *sk, if (transhdrlen && length + fragheaderlen <= mtu && rt->dst.dev->features & (NETIF_F_HW_CSUM | NETIF_F_IP_CSUM) && - !(flags & MSG_MORE) && - !exthdrlen) + (!(flags & MSG_MORE) || cork->gso_size) && + (!exthdrlen || (rt->dst.dev->features & NETIF_F_HW_ESP_TX_CSUM))) csummode = CHECKSUM_PARTIAL; cork->length += length; @@ -933,6 +936,7 @@ static int __ip_append_data(struct sock *sk, unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; + unsigned int pagedlen = 0; struct sk_buff *skb_prev; alloc_new_skb: skb_prev = skb; @@ -953,8 +957,12 @@ alloc_new_skb: if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else + else if (!paged) alloclen = fraglen; + else { + alloclen = min_t(int, fraglen, MAX_HEADER); + pagedlen = fraglen - alloclen; + } alloclen += exthdrlen; @@ -998,7 +1006,7 @@ alloc_new_skb: /* * Find where to start putting bytes. */ - data = skb_put(skb, fraglen + exthdrlen); + data = skb_put(skb, fraglen + exthdrlen - pagedlen); skb_set_network_header(skb, exthdrlen); skb->transport_header = (skb->network_header + fragheaderlen); @@ -1014,7 +1022,7 @@ alloc_new_skb: pskb_trim_unique(skb_prev, maxfraglen); } - copy = datalen - transhdrlen - fraggap; + copy = datalen - transhdrlen - fraggap - pagedlen; if (copy > 0 && getfrag(from, data + transhdrlen, offset, copy, fraggap, skb) < 0) { err = -EFAULT; kfree_skb(skb); @@ -1022,7 +1030,7 @@ alloc_new_skb: } offset += copy; - length -= datalen - fraggap; + length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; csummode = CHECKSUM_NONE; @@ -1135,6 +1143,8 @@ static int ip_setup_cork(struct sock *sk, struct inet_cork *cork, *rtp = NULL; cork->fragsize = ip_sk_use_pmtu(sk) ? dst_mtu(&rt->dst) : rt->dst.dev->mtu; + + cork->gso_size = sk->sk_type == SOCK_DGRAM ? ipc->gso_size : 0; cork->dst = &rt->dst; cork->length = 0; cork->ttl = ipc->ttl; @@ -1214,7 +1224,7 @@ ssize_t ip_append_page(struct sock *sk, struct flowi4 *fl4, struct page *page, return -EOPNOTSUPP; hh_len = LL_RESERVED_SPACE(rt->dst.dev); - mtu = cork->fragsize; + mtu = cork->gso_size ? IP_MAX_MTU : cork->fragsize; fragheaderlen = sizeof(struct iphdr) + (opt ? opt->optlen : 0); maxfraglen = ((mtu - fragheaderlen) & ~7) + fragheaderlen; @@ -1470,9 +1480,8 @@ struct sk_buff *ip_make_skb(struct sock *sk, int len, int odd, struct sk_buff *skb), void *from, int length, int transhdrlen, struct ipcm_cookie *ipc, struct rtable **rtp, - unsigned int flags) + struct inet_cork *cork, unsigned int flags) { - struct inet_cork cork; struct sk_buff_head queue; int err; @@ -1481,22 +1490,22 @@ struct sk_buff *ip_make_skb(struct sock *sk, __skb_queue_head_init(&queue); - cork.flags = 0; - cork.addr = 0; - cork.opt = NULL; - err = ip_setup_cork(sk, &cork, ipc, rtp); + cork->flags = 0; + cork->addr = 0; + cork->opt = NULL; + err = ip_setup_cork(sk, cork, ipc, rtp); if (err) return ERR_PTR(err); - err = __ip_append_data(sk, fl4, &queue, &cork, + err = __ip_append_data(sk, fl4, &queue, cork, ¤t->task_frag, getfrag, from, length, transhdrlen, flags); if (err) { - __ip_flush_pending_frames(sk, &queue, &cork); + __ip_flush_pending_frames(sk, &queue, cork); return ERR_PTR(err); } - return __ip_make_skb(sk, fl4, &queue, &cork); + return __ip_make_skb(sk, fl4, &queue, cork); } /* @@ -1552,7 +1561,7 @@ void ip_send_unicast_reply(struct sock *sk, struct sk_buff *skb, oif = skb->skb_iif; flowi4_init_output(&fl4, oif, - IP4_REPLY_MARK(net, skb->mark), + IP4_REPLY_MARK(net, skb->mark) ?: sk->sk_mark, RT_TOS(arg->tos), RT_SCOPE_UNIVERSE, ip_hdr(skb)->protocol, ip_reply_arg_flowi_flags(arg), diff --git a/net/ipv4/ip_tunnel_core.c b/net/ipv4/ip_tunnel_core.c index 2f39479be92f..dde671e97829 100644 --- a/net/ipv4/ip_tunnel_core.c +++ b/net/ipv4/ip_tunnel_core.c @@ -423,17 +423,17 @@ void __init ip_tunnel_core_init(void) lwtunnel_encap_add_ops(&ip6_tun_lwt_ops, LWTUNNEL_ENCAP_IP6); } -struct static_key ip_tunnel_metadata_cnt = STATIC_KEY_INIT_FALSE; +DEFINE_STATIC_KEY_FALSE(ip_tunnel_metadata_cnt); EXPORT_SYMBOL(ip_tunnel_metadata_cnt); void ip_tunnel_need_metadata(void) { - static_key_slow_inc(&ip_tunnel_metadata_cnt); + static_branch_inc(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_need_metadata); void ip_tunnel_unneed_metadata(void) { - static_key_slow_dec(&ip_tunnel_metadata_cnt); + static_branch_dec(&ip_tunnel_metadata_cnt); } EXPORT_SYMBOL_GPL(ip_tunnel_unneed_metadata); diff --git a/net/ipv4/ipconfig.c b/net/ipv4/ipconfig.c index 43f620feb1c4..d839d74853fc 100644 --- a/net/ipv4/ipconfig.c +++ b/net/ipv4/ipconfig.c @@ -28,6 +28,9 @@ * * Multiple Nameservers in /proc/net/pnp * -- Josef Siemes <jsiemes@web.de>, Aug 2002 + * + * NTP servers in /proc/net/ipconfig/ntp_servers + * -- Chris Novakovic <chris@chrisn.me.uk>, April 2018 */ #include <linux/types.h> @@ -93,6 +96,7 @@ #define CONF_TIMEOUT_MAX (HZ*30) /* Maximum allowed timeout */ #define CONF_NAMESERVERS_MAX 3 /* Maximum number of nameservers - '3' from resolv.h */ +#define CONF_NTP_SERVERS_MAX 3 /* Maximum number of NTP servers */ #define NONE cpu_to_be32(INADDR_NONE) #define ANY cpu_to_be32(INADDR_ANY) @@ -152,12 +156,16 @@ static int ic_proto_used; /* Protocol used, if any */ #define ic_proto_used 0 #endif static __be32 ic_nameservers[CONF_NAMESERVERS_MAX]; /* DNS Server IP addresses */ +static __be32 ic_ntp_servers[CONF_NTP_SERVERS_MAX]; /* NTP server IP addresses */ static u8 ic_domain[64]; /* DNS (not NIS) domain name */ /* * Private state. */ +/* proc_dir_entry for /proc/net/ipconfig */ +static struct proc_dir_entry *ipconfig_dir; + /* Name of user-selected boot device */ static char user_dev_name[IFNAMSIZ] __initdata = { 0, }; @@ -576,6 +584,15 @@ static inline void __init ic_nameservers_predef(void) ic_nameservers[i] = NONE; } +/* Predefine NTP servers */ +static inline void __init ic_ntp_servers_predef(void) +{ + int i; + + for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) + ic_ntp_servers[i] = NONE; +} + /* * DHCP/BOOTP support. */ @@ -671,6 +688,7 @@ ic_dhcp_init_options(u8 *options, struct ic_device *d) 17, /* Boot path */ 26, /* MTU */ 40, /* NIS domain name */ + 42, /* NTP servers */ }; *e++ = 55; /* Parameter request list */ @@ -721,9 +739,11 @@ static void __init ic_bootp_init_ext(u8 *e) *e++ = 3; /* Default gateway request */ *e++ = 4; e += 4; - *e++ = 5; /* Name server request */ - *e++ = 8; - e += 8; +#if CONF_NAMESERVERS_MAX > 0 + *e++ = 6; /* (DNS) name server request */ + *e++ = 4 * CONF_NAMESERVERS_MAX; + e += 4 * CONF_NAMESERVERS_MAX; +#endif *e++ = 12; /* Host name request */ *e++ = 32; e += 32; @@ -748,7 +768,13 @@ static void __init ic_bootp_init_ext(u8 *e) */ static inline void __init ic_bootp_init(void) { + /* Re-initialise all name servers and NTP servers to NONE, in case any + * were set via the "ip=" or "nfsaddrs=" kernel command line parameters: + * any IP addresses specified there will already have been decoded but + * are no longer needed + */ ic_nameservers_predef(); + ic_ntp_servers_predef(); dev_add_pack(&bootp_packet_type); } @@ -912,6 +938,15 @@ static void __init ic_do_bootp_ext(u8 *ext) ic_bootp_string(utsname()->domainname, ext+1, *ext, __NEW_UTS_LEN); break; + case 42: /* NTP servers */ + servers = *ext / 4; + if (servers > CONF_NTP_SERVERS_MAX) + servers = CONF_NTP_SERVERS_MAX; + for (i = 0; i < servers; i++) { + if (ic_ntp_servers[i] == NONE) + memcpy(&ic_ntp_servers[i], ext+1+4*i, 4); + } + break; } } @@ -1258,6 +1293,7 @@ static int __init ic_dynamic(void) #ifdef CONFIG_PROC_FS +/* Name servers: */ static int pnp_seq_show(struct seq_file *seq, void *v) { int i; @@ -1294,6 +1330,62 @@ static const struct file_operations pnp_seq_fops = { .llseek = seq_lseek, .release = single_release, }; + +/* Create the /proc/net/ipconfig directory */ +static int __init ipconfig_proc_net_init(void) +{ + ipconfig_dir = proc_net_mkdir(&init_net, "ipconfig", init_net.proc_net); + if (!ipconfig_dir) + return -ENOMEM; + + return 0; +} + +/* Create a new file under /proc/net/ipconfig */ +static int ipconfig_proc_net_create(const char *name, + const struct file_operations *fops) +{ + char *pname; + struct proc_dir_entry *p; + + if (!ipconfig_dir) + return -ENOMEM; + + pname = kasprintf(GFP_KERNEL, "%s%s", "ipconfig/", name); + if (!pname) + return -ENOMEM; + + p = proc_create(pname, 0444, init_net.proc_net, fops); + kfree(pname); + if (!p) + return -ENOMEM; + + return 0; +} + +/* Write NTP server IP addresses to /proc/net/ipconfig/ntp_servers */ +static int ntp_servers_seq_show(struct seq_file *seq, void *v) +{ + int i; + + for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) { + if (ic_ntp_servers[i] != NONE) + seq_printf(seq, "%pI4\n", &ic_ntp_servers[i]); + } + return 0; +} + +static int ntp_servers_seq_open(struct inode *inode, struct file *file) +{ + return single_open(file, ntp_servers_seq_show, NULL); +} + +static const struct file_operations ntp_servers_seq_fops = { + .open = ntp_servers_seq_open, + .read = seq_read, + .llseek = seq_lseek, + .release = single_release, +}; #endif /* CONFIG_PROC_FS */ /* @@ -1368,8 +1460,20 @@ static int __init ip_auto_config(void) int err; unsigned int i; + /* Initialise all name servers and NTP servers to NONE (but only if the + * "ip=" or "nfsaddrs=" kernel command line parameters weren't decoded, + * otherwise we'll overwrite the IP addresses specified there) + */ + if (ic_set_manually == 0) { + ic_nameservers_predef(); + ic_ntp_servers_predef(); + } + #ifdef CONFIG_PROC_FS proc_create("pnp", 0444, init_net.proc_net, &pnp_seq_fops); + + if (ipconfig_proc_net_init() == 0) + ipconfig_proc_net_create("ntp_servers", &ntp_servers_seq_fops); #endif /* CONFIG_PROC_FS */ if (!ic_enable) @@ -1481,16 +1585,32 @@ static int __init ip_auto_config(void) &ic_servaddr, &root_server_addr, root_server_path); if (ic_dev_mtu) pr_cont(", mtu=%d", ic_dev_mtu); - for (i = 0; i < CONF_NAMESERVERS_MAX; i++) + /* Name servers (if any): */ + for (i = 0; i < CONF_NAMESERVERS_MAX; i++) { if (ic_nameservers[i] != NONE) { - pr_cont(" nameserver%u=%pI4", - i, &ic_nameservers[i]); - break; + if (i == 0) + pr_info(" nameserver%u=%pI4", + i, &ic_nameservers[i]); + else + pr_cont(", nameserver%u=%pI4", + i, &ic_nameservers[i]); } - for (i++; i < CONF_NAMESERVERS_MAX; i++) - if (ic_nameservers[i] != NONE) - pr_cont(", nameserver%u=%pI4", i, &ic_nameservers[i]); - pr_cont("\n"); + if (i + 1 == CONF_NAMESERVERS_MAX) + pr_cont("\n"); + } + /* NTP servers (if any): */ + for (i = 0; i < CONF_NTP_SERVERS_MAX; i++) { + if (ic_ntp_servers[i] != NONE) { + if (i == 0) + pr_info(" ntpserver%u=%pI4", + i, &ic_ntp_servers[i]); + else + pr_cont(", ntpserver%u=%pI4", + i, &ic_ntp_servers[i]); + } + if (i + 1 == CONF_NTP_SERVERS_MAX) + pr_cont("\n"); + } #endif /* !SILENT */ /* @@ -1588,7 +1708,9 @@ static int __init ip_auto_config_setup(char *addrs) return 1; } + /* Initialise all name servers and NTP servers to NONE */ ic_nameservers_predef(); + ic_ntp_servers_predef(); /* Parse string for static IP assignment. */ ip = addrs; @@ -1647,6 +1769,13 @@ static int __init ip_auto_config_setup(char *addrs) ic_nameservers[1] = NONE; } break; + case 9: + if (CONF_NTP_SERVERS_MAX >= 1) { + ic_ntp_servers[0] = in_aton(ip); + if (ic_ntp_servers[0] == ANY) + ic_ntp_servers[0] = NONE; + } + break; } } ip = cp; diff --git a/net/ipv4/ipmr.c b/net/ipv4/ipmr.c index 2fb4de3f7f66..38e092eafc97 100644 --- a/net/ipv4/ipmr.c +++ b/net/ipv4/ipmr.c @@ -201,7 +201,8 @@ static const struct nla_policy ipmr_rule_policy[FRA_MAX + 1] = { }; static int ipmr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh, struct nlattr **tb) + struct fib_rule_hdr *frh, struct nlattr **tb, + struct netlink_ext_ack *extack) { return 0; } diff --git a/net/ipv4/metrics.c b/net/ipv4/metrics.c new file mode 100644 index 000000000000..5121c6475e6b --- /dev/null +++ b/net/ipv4/metrics.c @@ -0,0 +1,53 @@ +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <linux/types.h> +#include <net/ip.h> +#include <net/net_namespace.h> +#include <net/tcp.h> + +int ip_metrics_convert(struct net *net, struct nlattr *fc_mx, int fc_mx_len, + u32 *metrics) +{ + bool ecn_ca = false; + struct nlattr *nla; + int remaining; + + if (!fc_mx) + return 0; + + nla_for_each_attr(nla, fc_mx, fc_mx_len, remaining) { + int type = nla_type(nla); + u32 val; + + if (!type) + continue; + if (type > RTAX_MAX) + return -EINVAL; + + if (type == RTAX_CC_ALGO) { + char tmp[TCP_CA_NAME_MAX]; + + nla_strlcpy(tmp, nla, sizeof(tmp)); + val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); + if (val == TCP_CA_UNSPEC) + return -EINVAL; + } else { + val = nla_get_u32(nla); + } + if (type == RTAX_ADVMSS && val > 65535 - 40) + val = 65535 - 40; + if (type == RTAX_MTU && val > 65535 - 15) + val = 65535 - 15; + if (type == RTAX_HOPLIMIT && val > 255) + val = 255; + if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) + return -EINVAL; + metrics[type - 1] = val; + } + + if (ecn_ca) + metrics[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; + + return 0; +} +EXPORT_SYMBOL_GPL(ip_metrics_convert); diff --git a/net/ipv4/netfilter/ip_tables.c b/net/ipv4/netfilter/ip_tables.c index 44b308d93ec2..444f125f3974 100644 --- a/net/ipv4/netfilter/ip_tables.c +++ b/net/ipv4/netfilter/ip_tables.c @@ -300,7 +300,7 @@ ipt_do_table(struct sk_buff *skb, counter = xt_get_this_cpu_counter(&e->counters); ADD_COUNTER(*counter, skb->len, 1); - t = ipt_get_target(e); + t = ipt_get_target_c(e); WARN_ON(!t->u.kernel.target); #if IS_ENABLED(CONFIG_NETFILTER_XT_TARGET_TRACE) diff --git a/net/ipv4/netfilter/ipt_MASQUERADE.c b/net/ipv4/netfilter/ipt_MASQUERADE.c index a03e4e7ef5f9..ce1512b02cb2 100644 --- a/net/ipv4/netfilter/ipt_MASQUERADE.c +++ b/net/ipv4/netfilter/ipt_MASQUERADE.c @@ -47,7 +47,7 @@ static int masquerade_tg_check(const struct xt_tgchk_param *par) static unsigned int masquerade_tg(struct sk_buff *skb, const struct xt_action_param *par) { - struct nf_nat_range range; + struct nf_nat_range2 range; const struct nf_nat_ipv4_multi_range_compat *mr; mr = par->targinfo; diff --git a/net/ipv4/netfilter/iptable_nat.c b/net/ipv4/netfilter/iptable_nat.c index 0f7255cc65ee..529d89ec31e8 100644 --- a/net/ipv4/netfilter/iptable_nat.c +++ b/net/ipv4/netfilter/iptable_nat.c @@ -33,8 +33,7 @@ static const struct xt_table nf_nat_ipv4_table = { static unsigned int iptable_nat_do_chain(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) + const struct nf_hook_state *state) { return ipt_do_table(skb, state, state->net->ipv4.nat_table); } diff --git a/net/ipv4/netfilter/nf_flow_table_ipv4.c b/net/ipv4/netfilter/nf_flow_table_ipv4.c index 0cd46bffa469..e1e56d7123d2 100644 --- a/net/ipv4/netfilter/nf_flow_table_ipv4.c +++ b/net/ipv4/netfilter/nf_flow_table_ipv4.c @@ -2,265 +2,12 @@ #include <linux/init.h> #include <linux/module.h> #include <linux/netfilter.h> -#include <linux/rhashtable.h> -#include <linux/ip.h> -#include <linux/netdevice.h> -#include <net/ip.h> -#include <net/neighbour.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_tables.h> -/* For layer 4 checksum field offset. */ -#include <linux/tcp.h> -#include <linux/udp.h> - -static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) -{ - struct tcphdr *tcph; - - if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || - skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - - tcph = (void *)(skb_network_header(skb) + thoff); - inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true); - - return 0; -} - -static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, - __be32 addr, __be32 new_addr) -{ - struct udphdr *udph; - - if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || - skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - - udph = (void *)(skb_network_header(skb) + thoff); - if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { - inet_proto_csum_replace4(&udph->check, skb, addr, - new_addr, true); - if (!udph->check) - udph->check = CSUM_MANGLED_0; - } - - return 0; -} - -static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, - unsigned int thoff, __be32 addr, - __be32 new_addr) -{ - switch (iph->protocol) { - case IPPROTO_TCP: - if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - case IPPROTO_UDP: - if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - } - - return 0; -} - -static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - __be32 addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = iph->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr; - iph->saddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = iph->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; - iph->daddr = new_addr; - break; - default: - return -1; - } - csum_replace4(&iph->check, addr, new_addr); - - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); -} - -static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, - struct iphdr *iph, unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - __be32 addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = iph->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr; - iph->daddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = iph->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; - iph->saddr = new_addr; - break; - default: - return -1; - } - csum_replace4(&iph->check, addr, new_addr); - - return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); -} - -static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, - enum flow_offload_tuple_dir dir) -{ - struct iphdr *iph = ip_hdr(skb); - unsigned int thoff = iph->ihl * 4; - - if (flow->flags & FLOW_OFFLOAD_SNAT && - (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0)) - return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && - (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || - nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0)) - return -1; - - return 0; -} - -static bool ip_has_options(unsigned int thoff) -{ - return thoff != sizeof(struct iphdr); -} - -static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) -{ - struct flow_ports *ports; - unsigned int thoff; - struct iphdr *iph; - - if (!pskb_may_pull(skb, sizeof(*iph))) - return -1; - - iph = ip_hdr(skb); - thoff = iph->ihl * 4; - - if (ip_is_fragment(iph) || - unlikely(ip_has_options(thoff))) - return -1; - - if (iph->protocol != IPPROTO_TCP && - iph->protocol != IPPROTO_UDP) - return -1; - - thoff = iph->ihl * 4; - if (!pskb_may_pull(skb, thoff + sizeof(*ports))) - return -1; - - ports = (struct flow_ports *)(skb_network_header(skb) + thoff); - - tuple->src_v4.s_addr = iph->saddr; - tuple->dst_v4.s_addr = iph->daddr; - tuple->src_port = ports->source; - tuple->dst_port = ports->dest; - tuple->l3proto = AF_INET; - tuple->l4proto = iph->protocol; - tuple->iifidx = dev->ifindex; - - return 0; -} - -/* Based on ip_exceeds_mtu(). */ -static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) -{ - if (skb->len <= mtu) - return false; - - if ((ip_hdr(skb)->frag_off & htons(IP_DF)) == 0) - return false; - - if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) - return false; - - return true; -} - -static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rtable *rt) -{ - u32 mtu; - - mtu = ip_dst_mtu_maybe_forward(&rt->dst, true); - if (__nf_flow_exceeds_mtu(skb, mtu)) - return true; - - return false; -} - -unsigned int -nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct flow_offload_tuple_rhash *tuplehash; - struct nf_flowtable *flow_table = priv; - struct flow_offload_tuple tuple = {}; - enum flow_offload_tuple_dir dir; - struct flow_offload *flow; - struct net_device *outdev; - const struct rtable *rt; - struct iphdr *iph; - __be32 nexthop; - - if (skb->protocol != htons(ETH_P_IP)) - return NF_ACCEPT; - - if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0) - return NF_ACCEPT; - - tuplehash = flow_offload_lookup(flow_table, &tuple); - if (tuplehash == NULL) - return NF_ACCEPT; - - outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); - if (!outdev) - return NF_ACCEPT; - - dir = tuplehash->tuple.dir; - flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - - rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache; - if (unlikely(nf_flow_exceeds_mtu(skb, rt))) - return NF_ACCEPT; - - if (skb_try_make_writable(skb, sizeof(*iph))) - return NF_DROP; - - if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && - nf_flow_nat_ip(flow, skb, dir) < 0) - return NF_DROP; - - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; - iph = ip_hdr(skb); - ip_decrease_ttl(iph); - - skb->dev = outdev; - nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); - neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); - - return NF_STOLEN; -} -EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook); static struct nf_flowtable_type flowtable_ipv4 = { .family = NFPROTO_IPV4, - .params = &nf_flow_offload_rhash_params, - .gc = nf_flow_offload_work_gc, + .init = nf_flow_table_init, .free = nf_flow_table_free, .hook = nf_flow_offload_ip_hook, .owner = THIS_MODULE, diff --git a/net/ipv4/netfilter/nf_nat_h323.c b/net/ipv4/netfilter/nf_nat_h323.c index ac8342dcb55e..4e6b53ab6c33 100644 --- a/net/ipv4/netfilter/nf_nat_h323.c +++ b/net/ipv4/netfilter/nf_nat_h323.c @@ -395,7 +395,7 @@ static int nat_h245(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_q931_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_range range; + struct nf_nat_range2 range; if (this->tuple.src.u3.ip != 0) { /* Only accept calls from GK */ nf_nat_follow_master(new, this); @@ -497,7 +497,7 @@ static int nat_q931(struct sk_buff *skb, struct nf_conn *ct, static void ip_nat_callforwarding_expect(struct nf_conn *new, struct nf_conntrack_expect *this) { - struct nf_nat_range range; + struct nf_nat_range2 range; /* This must be a fresh one. */ BUG_ON(new->status & IPS_NAT_DONE_MASK); diff --git a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c index f7ff6a364d7b..325e02956bf5 100644 --- a/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_l3proto_ipv4.c @@ -63,7 +63,7 @@ static void nf_nat_ipv4_decode_session(struct sk_buff *skb, #endif /* CONFIG_XFRM */ static bool nf_nat_ipv4_in_range(const struct nf_conntrack_tuple *t, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { return ntohl(t->src.u3.ip) >= ntohl(range->min_addr.ip) && ntohl(t->src.u3.ip) <= ntohl(range->max_addr.ip); @@ -143,7 +143,7 @@ static void nf_nat_ipv4_csum_recalc(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int nf_nat_ipv4_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range) + struct nf_nat_range2 *range) { if (tb[CTA_NAT_V4_MINIP]) { range->min_addr.ip = nla_get_be32(tb[CTA_NAT_V4_MINIP]); @@ -246,8 +246,7 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -285,7 +284,7 @@ nf_nat_ipv4_fn(void *priv, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(priv, skb, state, ct); + ret = do_chain(priv, skb, state); if (ret != NF_ACCEPT) return ret; @@ -326,8 +325,7 @@ nf_nat_ipv4_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { unsigned int ret; __be32 daddr = ip_hdr(skb)->daddr; @@ -346,8 +344,7 @@ nf_nat_ipv4_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { #ifdef CONFIG_XFRM const struct nf_conn *ct; @@ -383,8 +380,7 @@ nf_nat_ipv4_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c index 0c366aad89cb..f538c5001547 100644 --- a/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c +++ b/net/ipv4/netfilter/nf_nat_masquerade_ipv4.c @@ -24,13 +24,13 @@ unsigned int nf_nat_masquerade_ipv4(struct sk_buff *skb, unsigned int hooknum, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, const struct net_device *out) { struct nf_conn *ct; struct nf_conn_nat *nat; enum ip_conntrack_info ctinfo; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; const struct rtable *rt; __be32 newsrc, nh; diff --git a/net/ipv4/netfilter/nf_nat_pptp.c b/net/ipv4/netfilter/nf_nat_pptp.c index 8a69363b4884..5d259a12e25f 100644 --- a/net/ipv4/netfilter/nf_nat_pptp.c +++ b/net/ipv4/netfilter/nf_nat_pptp.c @@ -48,7 +48,7 @@ static void pptp_nat_expected(struct nf_conn *ct, struct nf_conntrack_tuple t = {}; const struct nf_ct_pptp_master *ct_pptp_info; const struct nf_nat_pptp *nat_pptp_info; - struct nf_nat_range range; + struct nf_nat_range2 range; struct nf_conn_nat *nat; nat = nf_ct_nat_ext_add(ct); diff --git a/net/ipv4/netfilter/nf_nat_proto_gre.c b/net/ipv4/netfilter/nf_nat_proto_gre.c index edf05002d674..00fda6331ce5 100644 --- a/net/ipv4/netfilter/nf_nat_proto_gre.c +++ b/net/ipv4/netfilter/nf_nat_proto_gre.c @@ -41,7 +41,7 @@ MODULE_DESCRIPTION("Netfilter NAT protocol helper module for GRE"); static void gre_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/ipv4/netfilter/nf_nat_proto_icmp.c b/net/ipv4/netfilter/nf_nat_proto_icmp.c index 7b98baa13ede..6d7cf1d79baf 100644 --- a/net/ipv4/netfilter/nf_nat_proto_icmp.c +++ b/net/ipv4/netfilter/nf_nat_proto_icmp.c @@ -30,7 +30,7 @@ icmp_in_range(const struct nf_conntrack_tuple *tuple, static void icmp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/ipv4/netfilter/nft_chain_nat_ipv4.c b/net/ipv4/netfilter/nft_chain_nat_ipv4.c index b5464a3f253b..285baccfbdea 100644 --- a/net/ipv4/netfilter/nft_chain_nat_ipv4.c +++ b/net/ipv4/netfilter/nft_chain_nat_ipv4.c @@ -28,8 +28,7 @@ static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; diff --git a/net/ipv4/netfilter/nft_masq_ipv4.c b/net/ipv4/netfilter/nft_masq_ipv4.c index f18677277119..f1193e1e928a 100644 --- a/net/ipv4/netfilter/nft_masq_ipv4.c +++ b/net/ipv4/netfilter/nft_masq_ipv4.c @@ -21,7 +21,7 @@ static void nft_masq_ipv4_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_masq *priv = nft_expr_priv(expr); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); range.flags = priv->flags; diff --git a/net/ipv4/proc.c b/net/ipv4/proc.c index a058de677e94..261b71d0ccc5 100644 --- a/net/ipv4/proc.c +++ b/net/ipv4/proc.c @@ -296,6 +296,8 @@ static const struct snmp_mib snmp4_net_list[] = { SNMP_MIB_ITEM("TCPKeepAlive", LINUX_MIB_TCPKEEPALIVE), SNMP_MIB_ITEM("TCPMTUPFail", LINUX_MIB_TCPMTUPFAIL), SNMP_MIB_ITEM("TCPMTUPSuccess", LINUX_MIB_TCPMTUPSUCCESS), + SNMP_MIB_ITEM("TCPDelivered", LINUX_MIB_TCPDELIVERED), + SNMP_MIB_ITEM("TCPDeliveredCE", LINUX_MIB_TCPDELIVEREDCE), SNMP_MIB_SENTINEL }; diff --git a/net/ipv4/tcp.c b/net/ipv4/tcp.c index c9d00ef54dec..62b776f90037 100644 --- a/net/ipv4/tcp.c +++ b/net/ipv4/tcp.c @@ -1702,6 +1702,139 @@ int tcp_peek_len(struct socket *sock) } EXPORT_SYMBOL(tcp_peek_len); +/* Make sure sk_rcvbuf is big enough to satisfy SO_RCVLOWAT hint */ +int tcp_set_rcvlowat(struct sock *sk, int val) +{ + sk->sk_rcvlowat = val ? : 1; + + /* Check if we need to signal EPOLLIN right now */ + tcp_data_ready(sk); + + if (sk->sk_userlocks & SOCK_RCVBUF_LOCK) + return 0; + + /* val comes from user space and might be close to INT_MAX */ + val <<= 1; + if (val < 0) + val = INT_MAX; + + val = min(val, sock_net(sk)->ipv4.sysctl_tcp_rmem[2]); + if (val > sk->sk_rcvbuf) { + sk->sk_rcvbuf = val; + tcp_sk(sk)->window_clamp = tcp_win_from_space(sk, val); + } + return 0; +} +EXPORT_SYMBOL(tcp_set_rcvlowat); + +#ifdef CONFIG_MMU +static const struct vm_operations_struct tcp_vm_ops = { +}; + +int tcp_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) +{ + if (vma->vm_flags & (VM_WRITE | VM_EXEC)) + return -EPERM; + vma->vm_flags &= ~(VM_MAYWRITE | VM_MAYEXEC); + + /* Instruct vm_insert_page() to not down_read(mmap_sem) */ + vma->vm_flags |= VM_MIXEDMAP; + + vma->vm_ops = &tcp_vm_ops; + return 0; +} +EXPORT_SYMBOL(tcp_mmap); + +static int tcp_zerocopy_receive(struct sock *sk, + struct tcp_zerocopy_receive *zc) +{ + unsigned long address = (unsigned long)zc->address; + const skb_frag_t *frags = NULL; + u32 length = 0, seq, offset; + struct vm_area_struct *vma; + struct sk_buff *skb = NULL; + struct tcp_sock *tp; + int ret; + + if (address & (PAGE_SIZE - 1) || address != zc->address) + return -EINVAL; + + if (sk->sk_state == TCP_LISTEN) + return -ENOTCONN; + + sock_rps_record_flow(sk); + + down_read(¤t->mm->mmap_sem); + + ret = -EINVAL; + vma = find_vma(current->mm, address); + if (!vma || vma->vm_start > address || vma->vm_ops != &tcp_vm_ops) + goto out; + zc->length = min_t(unsigned long, zc->length, vma->vm_end - address); + + tp = tcp_sk(sk); + seq = tp->copied_seq; + zc->length = min_t(u32, zc->length, tcp_inq(sk)); + zc->length &= ~(PAGE_SIZE - 1); + + zap_page_range(vma, address, zc->length); + + zc->recv_skip_hint = 0; + ret = 0; + while (length + PAGE_SIZE <= zc->length) { + if (zc->recv_skip_hint < PAGE_SIZE) { + if (skb) { + skb = skb->next; + offset = seq - TCP_SKB_CB(skb)->seq; + } else { + skb = tcp_recv_skb(sk, seq, &offset); + } + + zc->recv_skip_hint = skb->len - offset; + offset -= skb_headlen(skb); + if ((int)offset < 0 || skb_has_frag_list(skb)) + break; + frags = skb_shinfo(skb)->frags; + while (offset) { + if (frags->size > offset) + goto out; + offset -= frags->size; + frags++; + } + } + if (frags->size != PAGE_SIZE || frags->page_offset) + break; + ret = vm_insert_page(vma, address + length, + skb_frag_page(frags)); + if (ret) + break; + length += PAGE_SIZE; + seq += PAGE_SIZE; + zc->recv_skip_hint -= PAGE_SIZE; + frags++; + } +out: + up_read(¤t->mm->mmap_sem); + if (length) { + tp->copied_seq = seq; + tcp_rcv_space_adjust(sk); + + /* Clean up data we have read: This will do ACK frames. */ + tcp_recv_skb(sk, seq, &offset); + tcp_cleanup_rbuf(sk, length); + ret = 0; + if (length == zc->length) + zc->recv_skip_hint = 0; + } else { + if (!zc->recv_skip_hint && sock_flag(sk, SOCK_DONE)) + ret = -EIO; + } + zc->length = length; + return ret; +} +#endif + static void tcp_update_recv_tstamps(struct sk_buff *skb, struct scm_timestamping *tss) { @@ -1757,6 +1890,22 @@ static void tcp_recv_timestamp(struct msghdr *msg, const struct sock *sk, } } +static int tcp_inq_hint(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + u32 copied_seq = READ_ONCE(tp->copied_seq); + u32 rcv_nxt = READ_ONCE(tp->rcv_nxt); + int inq; + + inq = rcv_nxt - copied_seq; + if (unlikely(inq < 0 || copied_seq != READ_ONCE(tp->copied_seq))) { + lock_sock(sk); + inq = tp->rcv_nxt - tp->copied_seq; + release_sock(sk); + } + return inq; +} + /* * This routine copies from a sock struct into the user buffer. * @@ -1773,13 +1922,14 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, u32 peek_seq; u32 *seq; unsigned long used; - int err; + int err, inq; int target; /* Read at least this many bytes */ long timeo; struct sk_buff *skb, *last; u32 urg_hole = 0; struct scm_timestamping tss; bool has_tss = false; + bool has_cmsg; if (unlikely(flags & MSG_ERRQUEUE)) return inet_recv_error(sk, msg, len, addr_len); @@ -1794,6 +1944,7 @@ int tcp_recvmsg(struct sock *sk, struct msghdr *msg, size_t len, int nonblock, if (sk->sk_state == TCP_LISTEN) goto out; + has_cmsg = tp->recvmsg_inq; timeo = sock_rcvtimeo(sk, nonblock); /* Urgent data needs to be handled specially. */ @@ -1980,6 +2131,7 @@ skip_copy: if (TCP_SKB_CB(skb)->has_rxtstamp) { tcp_update_recv_tstamps(skb, &tss); has_tss = true; + has_cmsg = true; } if (TCP_SKB_CB(skb)->tcp_flags & TCPHDR_FIN) goto found_fin_ok; @@ -1999,13 +2151,20 @@ skip_copy: * on connected socket. I was just happy when found this 8) --ANK */ - if (has_tss) - tcp_recv_timestamp(msg, sk, &tss); - /* Clean up data we have read: This will do ACK frames. */ tcp_cleanup_rbuf(sk, copied); release_sock(sk); + + if (has_cmsg) { + if (has_tss) + tcp_recv_timestamp(msg, sk, &tss); + if (tp->recvmsg_inq) { + inq = tcp_inq_hint(sk); + put_cmsg(msg, SOL_TCP, TCP_CM_INQ, sizeof(inq), &inq); + } + } + return copied; out: @@ -2422,6 +2581,7 @@ int tcp_disconnect(struct sock *sk, int flags) tp->snd_ssthresh = TCP_INFINITE_SSTHRESH; tp->snd_cwnd_cnt = 0; tp->window_clamp = 0; + tp->delivered_ce = 0; tcp_set_ca_state(sk, TCP_CA_Open); tp->is_sack_reneg = 0; tcp_clear_retrans(tp); @@ -2873,6 +3033,12 @@ static int do_tcp_setsockopt(struct sock *sk, int level, tp->notsent_lowat = val; sk->sk_write_space(sk); break; + case TCP_INQ: + if (val > 1 || val < 0) + err = -EINVAL; + else + tp->recvmsg_inq = val; + break; default: err = -ENOPROTOOPT; break; @@ -3031,6 +3197,8 @@ void tcp_get_info(struct sock *sk, struct tcp_info *info) rate64 = tcp_compute_delivery_rate(tp); if (rate64) info->tcpi_delivery_rate = rate64; + info->tcpi_delivered = tp->delivered; + info->tcpi_delivered_ce = tp->delivered_ce; unlock_sock_fast(sk, slow); } EXPORT_SYMBOL_GPL(tcp_get_info); @@ -3044,7 +3212,7 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) u32 rate; stats = alloc_skb(7 * nla_total_size_64bit(sizeof(u64)) + - 5 * nla_total_size(sizeof(u32)) + + 7 * nla_total_size(sizeof(u32)) + 3 * nla_total_size(sizeof(u8)), GFP_ATOMIC); if (!stats) return NULL; @@ -3075,9 +3243,12 @@ struct sk_buff *tcp_get_timestamping_opt_stats(const struct sock *sk) nla_put_u8(stats, TCP_NLA_RECUR_RETRANS, inet_csk(sk)->icsk_retransmits); nla_put_u8(stats, TCP_NLA_DELIVERY_RATE_APP_LMT, !!tp->rate_app_limited); nla_put_u32(stats, TCP_NLA_SND_SSTHRESH, tp->snd_ssthresh); + nla_put_u32(stats, TCP_NLA_DELIVERED, tp->delivered); + nla_put_u32(stats, TCP_NLA_DELIVERED_CE, tp->delivered_ce); nla_put_u32(stats, TCP_NLA_SNDQ_SIZE, tp->write_seq - tp->snd_una); nla_put_u8(stats, TCP_NLA_CA_STATE, inet_csk(sk)->icsk_ca_state); + return stats; } @@ -3293,6 +3464,9 @@ static int do_tcp_getsockopt(struct sock *sk, int level, case TCP_NOTSENT_LOWAT: val = tp->notsent_lowat; break; + case TCP_INQ: + val = tp->recvmsg_inq; + break; case TCP_SAVE_SYN: val = tp->save_syn; break; @@ -3329,6 +3503,25 @@ static int do_tcp_getsockopt(struct sock *sk, int level, } return 0; } +#ifdef CONFIG_MMU + case TCP_ZEROCOPY_RECEIVE: { + struct tcp_zerocopy_receive zc; + int err; + + if (get_user(len, optlen)) + return -EFAULT; + if (len != sizeof(zc)) + return -EINVAL; + if (copy_from_user(&zc, optval, len)) + return -EFAULT; + lock_sock(sk); + err = tcp_zerocopy_receive(sk, &zc); + release_sock(sk); + if (!err && copy_to_user(optval, &zc, len)) + err = -EFAULT; + return err; + } +#endif default: return -ENOPROTOOPT; } diff --git a/net/ipv4/tcp_input.c b/net/ipv4/tcp_input.c index e51c644484dc..b188e0d75edd 100644 --- a/net/ipv4/tcp_input.c +++ b/net/ipv4/tcp_input.c @@ -111,6 +111,25 @@ int sysctl_tcp_max_orphans __read_mostly = NR_FILE; #define REXMIT_LOST 1 /* retransmit packets marked lost */ #define REXMIT_NEW 2 /* FRTO-style transmit of unsent/new packets */ +#if IS_ENABLED(CONFIG_TLS_DEVICE) +static DEFINE_STATIC_KEY_FALSE(clean_acked_data_enabled); + +void clean_acked_data_enable(struct inet_connection_sock *icsk, + void (*cad)(struct sock *sk, u32 ack_seq)) +{ + icsk->icsk_clean_acked = cad; + static_branch_inc(&clean_acked_data_enabled); +} +EXPORT_SYMBOL_GPL(clean_acked_data_enable); + +void clean_acked_data_disable(struct inet_connection_sock *icsk) +{ + static_branch_dec(&clean_acked_data_enabled); + icsk->icsk_clean_acked = NULL; +} +EXPORT_SYMBOL_GPL(clean_acked_data_disable); +#endif + static void tcp_gro_dev_warn(struct sock *sk, const struct sk_buff *skb, unsigned int len) { @@ -582,6 +601,8 @@ void tcp_rcv_space_adjust(struct sock *sk) u32 copied; int time; + trace_tcp_rcv_space_adjust(sk); + tcp_mstamp_refresh(tp); time = tcp_stamp_us_delta(tp->tcp_mstamp, tp->rcvq_space.time); if (time < (tp->rcv_rtt_est.rtt_us >> 3) || tp->rcv_rtt_est.rtt_us == 0) @@ -3496,6 +3517,22 @@ static void tcp_xmit_recovery(struct sock *sk, int rexmit) tcp_xmit_retransmit_queue(sk); } +/* Returns the number of packets newly acked or sacked by the current ACK */ +static u32 tcp_newly_delivered(struct sock *sk, u32 prior_delivered, int flag) +{ + const struct net *net = sock_net(sk); + struct tcp_sock *tp = tcp_sk(sk); + u32 delivered; + + delivered = tp->delivered - prior_delivered; + NET_ADD_STATS(net, LINUX_MIB_TCPDELIVERED, delivered); + if (flag & FLAG_ECE) { + tp->delivered_ce += delivered; + NET_ADD_STATS(net, LINUX_MIB_TCPDELIVEREDCE, delivered); + } + return delivered; +} + /* This routine deals with incoming acks, but not outgoing ones. */ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) { @@ -3542,6 +3579,12 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if (after(ack, prior_snd_una)) { flag |= FLAG_SND_UNA_ADVANCED; icsk->icsk_retransmits = 0; + +#if IS_ENABLED(CONFIG_TLS_DEVICE) + if (static_branch_unlikely(&clean_acked_data_enabled)) + if (icsk->icsk_clean_acked) + icsk->icsk_clean_acked(sk, ack); +#endif } prior_fack = tcp_is_sack(tp) ? tcp_highest_sack_seq(tp) : tp->snd_una; @@ -3619,7 +3662,7 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) if ((flag & FLAG_FORWARD_PROGRESS) || !(flag & FLAG_NOT_DUP)) sk_dst_confirm(sk); - delivered = tp->delivered - delivered; /* freshly ACKed or SACKed */ + delivered = tcp_newly_delivered(sk, delivered, flag); lost = tp->lost - lost; /* freshly marked lost */ rs.is_ack_delayed = !!(flag & FLAG_ACK_MAYBE_DELAYED); tcp_rate_gen(sk, delivered, lost, is_sack_reneg, sack_state.rate); @@ -3629,9 +3672,11 @@ static int tcp_ack(struct sock *sk, const struct sk_buff *skb, int flag) no_queue: /* If data was DSACKed, see if we can undo a cwnd reduction. */ - if (flag & FLAG_DSACKING_ACK) + if (flag & FLAG_DSACKING_ACK) { tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag, &rexmit); + tcp_newly_delivered(sk, delivered, flag); + } /* If this ack opens up a zero window, clear backoff. It was * being used to time the probes, and is probably far higher than * it needs to be for normal retransmission. @@ -3655,6 +3700,7 @@ old_ack: &sack_state); tcp_fastretrans_alert(sk, prior_snd_una, is_dupack, &flag, &rexmit); + tcp_newly_delivered(sk, delivered, flag); tcp_xmit_recovery(sk, rexmit); } @@ -4573,6 +4619,17 @@ err: } +void tcp_data_ready(struct sock *sk) +{ + const struct tcp_sock *tp = tcp_sk(sk); + int avail = tp->rcv_nxt - tp->copied_seq; + + if (avail < sk->sk_rcvlowat && !sock_flag(sk, SOCK_DONE)) + return; + + sk->sk_data_ready(sk); +} + static void tcp_data_queue(struct sock *sk, struct sk_buff *skb) { struct tcp_sock *tp = tcp_sk(sk); @@ -4630,7 +4687,7 @@ queue_and_out: if (eaten > 0) kfree_skb_partial(skb, fragstolen); if (!sock_flag(sk, SOCK_DEAD)) - sk->sk_data_ready(sk); + tcp_data_ready(sk); return; } @@ -5023,9 +5080,12 @@ static void __tcp_ack_snd_check(struct sock *sk, int ofo_possible) /* More than one full frame received... */ if (((tp->rcv_nxt - tp->rcv_wup) > inet_csk(sk)->icsk_ack.rcv_mss && /* ... and right edge of window advances far enough. - * (tcp_recvmsg() will send ACK otherwise). Or... + * (tcp_recvmsg() will send ACK otherwise). + * If application uses SO_RCVLOWAT, we want send ack now if + * we have not received enough bytes to satisfy the condition. */ - __tcp_select_window(sk) >= tp->rcv_wnd) || + (tp->rcv_nxt - tp->copied_seq < sk->sk_rcvlowat || + __tcp_select_window(sk) >= tp->rcv_wnd)) || /* We ACK each frame or... */ tcp_in_quickack_mode(sk) || /* We have out of order data. */ @@ -5428,7 +5488,7 @@ void tcp_rcv_established(struct sock *sk, struct sk_buff *skb, no_ack: if (eaten) kfree_skb_partial(skb, fragstolen); - sk->sk_data_ready(sk); + tcp_data_ready(sk); return; } } @@ -5550,9 +5610,12 @@ static bool tcp_rcv_fastopen_synack(struct sock *sk, struct sk_buff *synack, return true; } tp->syn_data_acked = tp->syn_data; - if (tp->syn_data_acked) - NET_INC_STATS(sock_net(sk), - LINUX_MIB_TCPFASTOPENACTIVE); + if (tp->syn_data_acked) { + NET_INC_STATS(sock_net(sk), LINUX_MIB_TCPFASTOPENACTIVE); + /* SYN-data is counted as two separate packets in tcp_ack() */ + if (tp->delivered > 1) + --tp->delivered; + } tcp_fastopen_add_skb(sk, synack); @@ -5884,6 +5947,7 @@ int tcp_rcv_state_process(struct sock *sk, struct sk_buff *skb) } switch (sk->sk_state) { case TCP_SYN_RECV: + tp->delivered++; /* SYN-ACK delivery isn't tracked in tcp_ack */ if (!tp->srtt_us) tcp_synack_rtt_meas(sk, req); diff --git a/net/ipv4/tcp_ipv4.c b/net/ipv4/tcp_ipv4.c index f70586b50838..caf23de88f8a 100644 --- a/net/ipv4/tcp_ipv4.c +++ b/net/ipv4/tcp_ipv4.c @@ -621,6 +621,7 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) struct sock *sk1 = NULL; #endif struct net *net; + struct sock *ctl_sk; /* Never send a reset in response to a reset. */ if (th->rst) @@ -723,11 +724,16 @@ static void tcp_v4_send_reset(const struct sock *sk, struct sk_buff *skb) arg.tos = ip_hdr(skb)->tos; arg.uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); + ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); __TCP_INC_STATS(net, TCP_MIB_OUTRSTS); local_bh_enable(); @@ -759,6 +765,7 @@ static void tcp_v4_send_ack(const struct sock *sk, } rep; struct net *net = sock_net(sk); struct ip_reply_arg arg; + struct sock *ctl_sk; memset(&rep.th, 0, sizeof(struct tcphdr)); memset(&arg, 0, sizeof(arg)); @@ -809,11 +816,16 @@ static void tcp_v4_send_ack(const struct sock *sk, arg.tos = tos; arg.uid = sock_net_uid(net, sk_fullsock(sk) ? sk : NULL); local_bh_disable(); - ip_send_unicast_reply(*this_cpu_ptr(net->ipv4.tcp_sk), + ctl_sk = *this_cpu_ptr(net->ipv4.tcp_sk); + if (sk) + ctl_sk->sk_mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + ip_send_unicast_reply(ctl_sk, skb, &TCP_SKB_CB(skb)->header.h4.opt, ip_hdr(skb)->saddr, ip_hdr(skb)->daddr, &arg, arg.iov[0].iov_len); + ctl_sk->sk_mark = 0; __TCP_INC_STATS(net, TCP_MIB_OUTSEGS); local_bh_enable(); } diff --git a/net/ipv4/tcp_minisocks.c b/net/ipv4/tcp_minisocks.c index 57b5468b5139..f867658b4b30 100644 --- a/net/ipv4/tcp_minisocks.c +++ b/net/ipv4/tcp_minisocks.c @@ -263,6 +263,7 @@ void tcp_time_wait(struct sock *sk, int state, int timeo) struct inet_sock *inet = inet_sk(sk); tw->tw_transparent = inet->transparent; + tw->tw_mark = sk->sk_mark; tw->tw_rcv_wscale = tp->rx_opt.rcv_wscale; tcptw->tw_rcv_nxt = tp->rcv_nxt; tcptw->tw_snd_nxt = tp->snd_nxt; diff --git a/net/ipv4/tcp_output.c b/net/ipv4/tcp_output.c index 383cac0ff0ec..0d8f950a9006 100644 --- a/net/ipv4/tcp_output.c +++ b/net/ipv4/tcp_output.c @@ -229,11 +229,9 @@ void tcp_select_initial_window(const struct sock *sk, int __space, __u32 mss, } } - if (mss > (1 << *rcv_wscale)) { - if (!init_rcv_wnd) /* Use default unless specified otherwise */ - init_rcv_wnd = tcp_default_init_rwnd(mss); - *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); - } + if (!init_rcv_wnd) /* Use default unless specified otherwise */ + init_rcv_wnd = tcp_default_init_rwnd(mss); + *rcv_wnd = min(*rcv_wnd, init_rcv_wnd * mss); /* Set the clamp no higher than max representable value */ (*window_clamp) = min_t(__u32, U16_MAX << (*rcv_wscale), *window_clamp); @@ -585,14 +583,15 @@ static unsigned int tcp_syn_options(struct sock *sk, struct sk_buff *skb, unsigned int remaining = MAX_TCP_OPTION_SPACE; struct tcp_fastopen_request *fastopen = tp->fastopen_req; + *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (*md5) { - opts->options |= OPTION_MD5; - remaining -= TCPOLEN_MD5SIG_ALIGNED; + if (unlikely(rcu_access_pointer(tp->md5sig_info))) { + *md5 = tp->af_specific->md5_lookup(sk, sk); + if (*md5) { + opts->options |= OPTION_MD5; + remaining -= TCPOLEN_MD5SIG_ALIGNED; + } } -#else - *md5 = NULL; #endif /* We always get an MSS option. The option bytes which will be seen in @@ -720,14 +719,15 @@ static unsigned int tcp_established_options(struct sock *sk, struct sk_buff *skb opts->options = 0; + *md5 = NULL; #ifdef CONFIG_TCP_MD5SIG - *md5 = tp->af_specific->md5_lookup(sk, sk); - if (unlikely(*md5)) { - opts->options |= OPTION_MD5; - size += TCPOLEN_MD5SIG_ALIGNED; + if (unlikely(rcu_access_pointer(tp->md5sig_info))) { + *md5 = tp->af_specific->md5_lookup(sk, sk); + if (*md5) { + opts->options |= OPTION_MD5; + size += TCPOLEN_MD5SIG_ALIGNED; + } } -#else - *md5 = NULL; #endif if (likely(tp->rx_opt.tstamp_ok)) { @@ -772,7 +772,7 @@ struct tsq_tasklet { }; static DEFINE_PER_CPU(struct tsq_tasklet, tsq_tasklet); -static void tcp_tsq_handler(struct sock *sk) +static void tcp_tsq_write(struct sock *sk) { if ((1 << sk->sk_state) & (TCPF_ESTABLISHED | TCPF_FIN_WAIT1 | TCPF_CLOSING | @@ -789,6 +789,16 @@ static void tcp_tsq_handler(struct sock *sk) 0, GFP_ATOMIC); } } + +static void tcp_tsq_handler(struct sock *sk) +{ + bh_lock_sock(sk); + if (!sock_owned_by_user(sk)) + tcp_tsq_write(sk); + else if (!test_and_set_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) + sock_hold(sk); + bh_unlock_sock(sk); +} /* * One tasklet per cpu tries to send more skbs. * We run in tasklet context but need to disable irqs when @@ -816,16 +826,7 @@ static void tcp_tasklet_func(unsigned long data) smp_mb__before_atomic(); clear_bit(TSQ_QUEUED, &sk->sk_tsq_flags); - if (!sk->sk_lock.owned && - test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) { - bh_lock_sock(sk); - if (!sock_owned_by_user(sk)) { - clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags); - tcp_tsq_handler(sk); - } - bh_unlock_sock(sk); - } - + tcp_tsq_handler(sk); sk_free(sk); } } @@ -853,9 +854,10 @@ void tcp_release_cb(struct sock *sk) nflags = flags & ~TCP_DEFERRED_ALL; } while (cmpxchg(&sk->sk_tsq_flags, flags, nflags) != flags); - if (flags & TCPF_TSQ_DEFERRED) - tcp_tsq_handler(sk); - + if (flags & TCPF_TSQ_DEFERRED) { + tcp_tsq_write(sk); + __sock_put(sk); + } /* Here begins the tricky part : * We are called from release_sock() with : * 1) BH disabled @@ -929,7 +931,7 @@ void tcp_wfree(struct sk_buff *skb) if (!(oval & TSQF_THROTTLED) || (oval & TSQF_QUEUED)) goto out; - nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; + nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED; nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); if (nval != oval) continue; @@ -948,37 +950,17 @@ out: sk_free(sk); } -/* Note: Called under hard irq. - * We can not call TCP stack right away. +/* Note: Called under soft irq. + * We can call TCP stack right away, unless socket is owned by user. */ enum hrtimer_restart tcp_pace_kick(struct hrtimer *timer) { struct tcp_sock *tp = container_of(timer, struct tcp_sock, pacing_timer); struct sock *sk = (struct sock *)tp; - unsigned long nval, oval; - - for (oval = READ_ONCE(sk->sk_tsq_flags);; oval = nval) { - struct tsq_tasklet *tsq; - bool empty; - - if (oval & TSQF_QUEUED) - break; - nval = (oval & ~TSQF_THROTTLED) | TSQF_QUEUED | TCPF_TSQ_DEFERRED; - nval = cmpxchg(&sk->sk_tsq_flags, oval, nval); - if (nval != oval) - continue; + tcp_tsq_handler(sk); + sock_put(sk); - if (!refcount_inc_not_zero(&sk->sk_wmem_alloc)) - break; - /* queue this socket to tasklet queue */ - tsq = this_cpu_ptr(&tsq_tasklet); - empty = list_empty(&tsq->head); - list_add(&tp->tsq_node, &tsq->head); - if (empty) - tasklet_schedule(&tsq->tasklet); - break; - } return HRTIMER_NORESTART; } @@ -1011,7 +993,8 @@ static void tcp_internal_pacing(struct sock *sk, const struct sk_buff *skb) do_div(len_ns, rate); hrtimer_start(&tcp_sk(sk)->pacing_timer, ktime_add_ns(ktime_get(), len_ns), - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_SOFT); + sock_hold(sk); } static void tcp_update_skb_after_send(struct tcp_sock *tp, struct sk_buff *skb) @@ -1078,7 +1061,7 @@ static int tcp_transmit_skb(struct sock *sk, struct sk_buff *skb, int clone_it, /* if no packet is in qdisc/device queue, then allow XPS to select * another queue. We can be called from tcp_tsq_handler() - * which holds one reference to sk_wmem_alloc. + * which holds one reference to sk. * * TODO: Ideally, in-flight pure ACK packets should not matter here. * One way to get this would be to set skb->truesize = 2 on them. @@ -2185,7 +2168,7 @@ static int tcp_mtu_probe(struct sock *sk) static bool tcp_pacing_check(const struct sock *sk) { return tcp_needs_internal_pacing(sk) && - hrtimer_active(&tcp_sk(sk)->pacing_timer); + hrtimer_is_queued(&tcp_sk(sk)->pacing_timer); } /* TCP Small Queues : @@ -2365,8 +2348,6 @@ static bool tcp_write_xmit(struct sock *sk, unsigned int mss_now, int nonagle, skb, limit, mss_now, gfp))) break; - if (test_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags)) - clear_bit(TCP_TSQ_DEFERRED, &sk->sk_tsq_flags); if (tcp_small_queue_check(sk, skb, 0)) break; diff --git a/net/ipv4/tcp_timer.c b/net/ipv4/tcp_timer.c index f7d944855f8e..92bdf64fffae 100644 --- a/net/ipv4/tcp_timer.c +++ b/net/ipv4/tcp_timer.c @@ -713,6 +713,6 @@ void tcp_init_xmit_timers(struct sock *sk) inet_csk_init_xmit_timers(sk, &tcp_write_timer, &tcp_delack_timer, &tcp_keepalive_timer); hrtimer_init(&tcp_sk(sk)->pacing_timer, CLOCK_MONOTONIC, - HRTIMER_MODE_ABS_PINNED); + HRTIMER_MODE_ABS_PINNED_SOFT); tcp_sk(sk)->pacing_timer.function = tcp_pace_kick; } diff --git a/net/ipv4/udp.c b/net/ipv4/udp.c index b61a770884fa..ff4d4ba67735 100644 --- a/net/ipv4/udp.c +++ b/net/ipv4/udp.c @@ -757,7 +757,8 @@ void udp_set_csum(bool nocheck, struct sk_buff *skb, } EXPORT_SYMBOL(udp_set_csum); -static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) +static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4, + struct inet_cork *cork) { struct sock *sk = skb->sk; struct inet_sock *inet = inet_sk(sk); @@ -777,6 +778,26 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) uh->len = htons(len); uh->check = 0; + if (cork->gso_size) { + const int hlen = skb_network_header_len(skb) + + sizeof(struct udphdr); + + if (hlen + cork->gso_size > cork->fragsize) + return -EINVAL; + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + return -EINVAL; + if (sk->sk_no_check_tx) + return -EINVAL; + if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite) + return -EIO; + + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + skb_shinfo(skb)->gso_segs = DIV_ROUND_UP(len - sizeof(uh), + cork->gso_size); + goto csum_partial; + } + if (is_udplite) /* UDP-Lite */ csum = udplite_csum(skb); @@ -786,6 +807,7 @@ static int udp_send_skb(struct sk_buff *skb, struct flowi4 *fl4) goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ +csum_partial: udp4_hwcsum(skb, fl4->saddr, fl4->daddr); goto send; @@ -828,7 +850,7 @@ int udp_push_pending_frames(struct sock *sk) if (!skb) goto out; - err = udp_send_skb(skb, fl4); + err = udp_send_skb(skb, fl4, &inet->cork.base); out: up->len = 0; @@ -837,6 +859,43 @@ out: } EXPORT_SYMBOL(udp_push_pending_frames); +static int __udp_cmsg_send(struct cmsghdr *cmsg, u16 *gso_size) +{ + switch (cmsg->cmsg_type) { + case UDP_SEGMENT: + if (cmsg->cmsg_len != CMSG_LEN(sizeof(__u16))) + return -EINVAL; + *gso_size = *(__u16 *)CMSG_DATA(cmsg); + return 0; + default: + return -EINVAL; + } +} + +int udp_cmsg_send(struct sock *sk, struct msghdr *msg, u16 *gso_size) +{ + struct cmsghdr *cmsg; + bool need_ip = false; + int err; + + for_each_cmsghdr(cmsg, msg) { + if (!CMSG_OK(msg, cmsg)) + return -EINVAL; + + if (cmsg->cmsg_level != SOL_UDP) { + need_ip = true; + continue; + } + + err = __udp_cmsg_send(cmsg, gso_size); + if (err) + return err; + } + + return need_ip; +} +EXPORT_SYMBOL_GPL(udp_cmsg_send); + int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) { struct inet_sock *inet = inet_sk(sk); @@ -922,10 +981,14 @@ int udp_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc.sockc.tsflags = sk->sk_tsflags; ipc.addr = inet->inet_saddr; ipc.oif = sk->sk_bound_dev_if; + ipc.gso_size = up->gso_size; if (msg->msg_controllen) { - err = ip_cmsg_send(sk, msg, &ipc, sk->sk_family == AF_INET6); - if (unlikely(err)) { + err = udp_cmsg_send(sk, msg, &ipc.gso_size); + if (err > 0) + err = ip_cmsg_send(sk, msg, &ipc, + sk->sk_family == AF_INET6); + if (unlikely(err < 0)) { kfree(ipc.opt); return err; } @@ -1032,12 +1095,14 @@ back_from_confirm: /* Lockless fast path for the non-corking case. */ if (!corkreq) { + struct inet_cork cork; + skb = ip_make_skb(sk, fl4, getfrag, msg, ulen, sizeof(struct udphdr), &ipc, &rt, - msg->msg_flags); + &cork, msg->msg_flags); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) - err = udp_send_skb(skb, fl4); + err = udp_send_skb(skb, fl4, &cork); goto out; } @@ -1813,10 +1878,10 @@ static int __udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) return 0; } -static struct static_key udp_encap_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(udp_encap_needed_key); void udp_encap_enable(void) { - static_key_enable(&udp_encap_needed); + static_branch_enable(&udp_encap_needed_key); } EXPORT_SYMBOL(udp_encap_enable); @@ -1840,7 +1905,7 @@ static int udp_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) goto drop; nf_reset(skb); - if (static_key_false(&udp_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -2303,7 +2368,7 @@ void udp_destroy_sock(struct sock *sk) bool slow = lock_sock_fast(sk); udp_flush_pending_frames(sk); unlock_sock_fast(sk, slow); - if (static_key_false(&udp_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udp_encap_needed_key) && up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) @@ -2368,6 +2433,12 @@ int udp_lib_setsockopt(struct sock *sk, int level, int optname, up->no_check6_rx = valbool; break; + case UDP_SEGMENT: + if (val < 0 || val > USHRT_MAX) + return -EINVAL; + up->gso_size = val; + break; + /* * UDP-Lite's partial checksum coverage (RFC 3828). */ @@ -2458,6 +2529,10 @@ int udp_lib_getsockopt(struct sock *sk, int level, int optname, val = up->no_check6_rx; break; + case UDP_SEGMENT: + val = up->gso_size; + break; + /* The following two cannot be changed on UDP sockets, the return is * always 0 (which corresponds to the full checksum coverage of UDP). */ case UDPLITE_SEND_CSCOV: diff --git a/net/ipv4/udp_offload.c b/net/ipv4/udp_offload.c index ea6e6e7df0ee..92dc9e5a7ff3 100644 --- a/net/ipv4/udp_offload.c +++ b/net/ipv4/udp_offload.c @@ -187,6 +187,102 @@ out_unlock: } EXPORT_SYMBOL(skb_udp_tunnel_segment); +struct sk_buff *__udp_gso_segment(struct sk_buff *gso_skb, + netdev_features_t features) +{ + struct sock *sk = gso_skb->sk; + unsigned int sum_truesize = 0; + struct sk_buff *segs, *seg; + struct udphdr *uh; + unsigned int mss; + bool copy_dtor; + __sum16 check; + __be16 newlen; + + mss = skb_shinfo(gso_skb)->gso_size; + if (gso_skb->len <= sizeof(*uh) + mss) + return ERR_PTR(-EINVAL); + + skb_pull(gso_skb, sizeof(*uh)); + + /* clear destructor to avoid skb_segment assigning it to tail */ + copy_dtor = gso_skb->destructor == sock_wfree; + if (copy_dtor) + gso_skb->destructor = NULL; + + segs = skb_segment(gso_skb, features); + if (unlikely(IS_ERR_OR_NULL(segs))) { + if (copy_dtor) + gso_skb->destructor = sock_wfree; + return segs; + } + + /* GSO partial and frag_list segmentation only requires splitting + * the frame into an MSS multiple and possibly a remainder, both + * cases return a GSO skb. So update the mss now. + */ + if (skb_is_gso(segs)) + mss *= skb_shinfo(segs)->gso_segs; + + seg = segs; + uh = udp_hdr(seg); + + /* compute checksum adjustment based on old length versus new */ + newlen = htons(sizeof(*uh) + mss); + check = csum16_add(csum16_sub(uh->check, uh->len), newlen); + + for (;;) { + if (copy_dtor) { + seg->destructor = sock_wfree; + seg->sk = sk; + sum_truesize += seg->truesize; + } + + if (!seg->next) + break; + + uh->len = newlen; + uh->check = check; + + if (seg->ip_summed == CHECKSUM_PARTIAL) + gso_reset_checksum(seg, ~check); + else + uh->check = gso_make_checksum(seg, ~check) ? : + CSUM_MANGLED_0; + + seg = seg->next; + uh = udp_hdr(seg); + } + + /* last packet can be partial gso_size, account for that in checksum */ + newlen = htons(skb_tail_pointer(seg) - skb_transport_header(seg) + + seg->data_len); + check = csum16_add(csum16_sub(uh->check, uh->len), newlen); + + uh->len = newlen; + uh->check = check; + + if (seg->ip_summed == CHECKSUM_PARTIAL) + gso_reset_checksum(seg, ~check); + else + uh->check = gso_make_checksum(seg, ~check) ? : CSUM_MANGLED_0; + + /* update refcount for the packet */ + if (copy_dtor) { + int delta = sum_truesize - gso_skb->truesize; + + /* In some pathological cases, delta can be negative. + * We need to either use refcount_add() or refcount_sub_and_test() + */ + if (likely(delta >= 0)) + refcount_add(delta, &sk->sk_wmem_alloc); + else + WARN_ON_ONCE(refcount_sub_and_test(-delta, &sk->sk_wmem_alloc)); + } + return segs; +} +EXPORT_SYMBOL_GPL(__udp_gso_segment); + static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, netdev_features_t features) { @@ -203,12 +299,15 @@ static struct sk_buff *udp4_ufo_fragment(struct sk_buff *skb, goto out; } - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + return __udp_gso_segment(skb, features); + mss = skb_shinfo(skb)->gso_size; if (unlikely(skb->len <= mss)) goto out; diff --git a/net/ipv6/addrconf.c b/net/ipv6/addrconf.c index 78cef00c9596..fbfd71a2d9c8 100644 --- a/net/ipv6/addrconf.c +++ b/net/ipv6/addrconf.c @@ -170,7 +170,7 @@ static void addrconf_type_change(struct net_device *dev, unsigned long event); static int addrconf_ifdown(struct net_device *dev, int how); -static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, +static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags); @@ -916,7 +916,6 @@ void inet6_ifa_finish_destroy(struct inet6_ifaddr *ifp) pr_warn("Freeing alive inet6 address %p\n", ifp); return; } - ip6_rt_put(ifp->rt); kfree_rcu(ifp, rcu); } @@ -995,7 +994,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, gfp_t gfp_flags = can_block ? GFP_KERNEL : GFP_ATOMIC; struct net *net = dev_net(idev->dev); struct inet6_ifaddr *ifa = NULL; - struct rt6_info *rt = NULL; + struct fib6_info *f6i = NULL; int err = 0; int addr_type = ipv6_addr_type(addr); @@ -1037,16 +1036,16 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, goto out; } - rt = addrconf_dst_alloc(idev, addr, false); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - rt = NULL; + f6i = addrconf_f6i_alloc(net, idev, addr, false, gfp_flags); + if (IS_ERR(f6i)) { + err = PTR_ERR(f6i); + f6i = NULL; goto out; } if (net->ipv6.devconf_all->disable_policy || idev->cnf.disable_policy) - rt->dst.flags |= DST_NOPOLICY; + f6i->dst_nopolicy = true; neigh_parms_data_state_setall(idev->nd_parms); @@ -1068,7 +1067,7 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, ifa->cstamp = ifa->tstamp = jiffies; ifa->tokenized = false; - ifa->rt = rt; + ifa->rt = f6i; ifa->idev = idev; in6_dev_hold(idev); @@ -1102,8 +1101,8 @@ ipv6_add_addr(struct inet6_dev *idev, const struct in6_addr *addr, inet6addr_notifier_call_chain(NETDEV_UP, ifa); out: if (unlikely(err < 0)) { - if (rt) - ip6_rt_put(rt); + fib6_info_release(f6i); + if (ifa) { if (ifa->idev) in6_dev_put(ifa->idev); @@ -1179,19 +1178,19 @@ check_cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long *expires) static void cleanup_prefix_route(struct inet6_ifaddr *ifp, unsigned long expires, bool del_rt) { - struct rt6_info *rt; + struct fib6_info *f6i; - rt = addrconf_get_prefix_route(&ifp->addr, + f6i = addrconf_get_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, 0, RTF_GATEWAY | RTF_DEFAULT); - if (rt) { + if (f6i) { if (del_rt) - ip6_del_rt(rt); + ip6_del_rt(dev_net(ifp->idev->dev), f6i); else { - if (!(rt->rt6i_flags & RTF_EXPIRES)) - rt6_set_expires(rt, expires); - ip6_rt_put(rt); + if (!(f6i->fib6_flags & RTF_EXPIRES)) + fib6_set_expires(f6i, expires); + fib6_info_release(f6i); } } } @@ -2320,7 +2319,7 @@ static void ipv6_try_regen_rndid(struct inet6_dev *idev, struct in6_addr *tmpad static void addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, - unsigned long expires, u32 flags) + unsigned long expires, u32 flags, gfp_t gfp_flags) { struct fib6_config cfg = { .fc_table = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX, @@ -2331,6 +2330,7 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, .fc_flags = RTF_UP | flags, .fc_nlinfo.nl_net = dev_net(dev), .fc_protocol = RTPROT_KERNEL, + .fc_type = RTN_UNICAST, }; cfg.fc_dst = *pfx; @@ -2344,17 +2344,17 @@ addrconf_prefix_route(struct in6_addr *pfx, int plen, struct net_device *dev, cfg.fc_flags |= RTF_NONEXTHOP; #endif - ip6_route_add(&cfg, NULL); + ip6_route_add(&cfg, gfp_flags, NULL); } -static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, +static struct fib6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, int plen, const struct net_device *dev, u32 flags, u32 noflags) { struct fib6_node *fn; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; struct fib6_table *table; u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_PREFIX; @@ -2368,14 +2368,13 @@ static struct rt6_info *addrconf_get_prefix_route(const struct in6_addr *pfx, goto out; for_each_fib6_node_rt_rcu(fn) { - if (rt->dst.dev->ifindex != dev->ifindex) + if (rt->fib6_nh.nh_dev->ifindex != dev->ifindex) continue; - if ((rt->rt6i_flags & flags) != flags) + if ((rt->fib6_flags & flags) != flags) continue; - if ((rt->rt6i_flags & noflags) != 0) + if ((rt->fib6_flags & noflags) != 0) continue; - if (!dst_hold_safe(&rt->dst)) - rt = NULL; + fib6_info_hold(rt); break; } out: @@ -2394,12 +2393,13 @@ static void addrconf_add_mroute(struct net_device *dev) .fc_ifindex = dev->ifindex, .fc_dst_len = 8, .fc_flags = RTF_UP, + .fc_type = RTN_UNICAST, .fc_nlinfo.nl_net = dev_net(dev), }; ipv6_addr_set(&cfg.fc_dst, htonl(0xFF000000), 0, 0, 0); - ip6_route_add(&cfg, NULL); + ip6_route_add(&cfg, GFP_ATOMIC, NULL); } static struct inet6_dev *addrconf_add_dev(struct net_device *dev) @@ -2529,7 +2529,6 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, if (IS_ERR_OR_NULL(ifp)) return -1; - update_lft = 0; create = 1; spin_lock_bh(&ifp->lock); ifp->flags |= IFA_F_MANAGETEMPADDR; @@ -2551,7 +2550,7 @@ int addrconf_prefix_rcv_add_addr(struct net *net, struct net_device *dev, stored_lft = ifp->valid_lft - (now - ifp->tstamp) / HZ; else stored_lft = 0; - if (!update_lft && !create && stored_lft) { + if (!create && stored_lft) { const u32 minimum_lft = min_t(u32, stored_lft, MIN_VALID_LIFETIME); valid_lft = max(valid_lft, minimum_lft); @@ -2642,7 +2641,7 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) */ if (pinfo->onlink) { - struct rt6_info *rt; + struct fib6_info *rt; unsigned long rt_expires; /* Avoid arithmetic overflow. Really, we could @@ -2667,13 +2666,13 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) if (rt) { /* Autoconf prefix route */ if (valid_lft == 0) { - ip6_del_rt(rt); + ip6_del_rt(net, rt); rt = NULL; } else if (addrconf_finite_timeout(rt_expires)) { /* not infinity */ - rt6_set_expires(rt, jiffies + rt_expires); + fib6_set_expires(rt, jiffies + rt_expires); } else { - rt6_clean_expires(rt); + fib6_clean_expires(rt); } } else if (valid_lft) { clock_t expires = 0; @@ -2684,9 +2683,9 @@ void addrconf_prefix_rcv(struct net_device *dev, u8 *opt, int len, bool sllao) expires = jiffies_to_clock_t(rt_expires); } addrconf_prefix_route(&pinfo->prefix, pinfo->prefix_len, - dev, expires, flags); + dev, expires, flags, GFP_ATOMIC); } - ip6_rt_put(rt); + fib6_info_release(rt); } /* Try to figure out our local address for this prefix */ @@ -2899,9 +2898,14 @@ static int inet6_addr_add(struct net *net, int ifindex, if (!IS_ERR(ifp)) { if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, dev, - expires, flags); + expires, flags, GFP_KERNEL); } + /* Send a netlink notification if DAD is enabled and + * optimistic flag is not set + */ + if (!(ifp->flags & (IFA_F_OPTIMISTIC | IFA_F_NODAD))) + ipv6_ifa_notify(0, ifp); /* * Note that section 3.1 of RFC 4429 indicates * that the Optimistic flag should not be set for @@ -3047,7 +3051,8 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) if (addr.s6_addr32[3]) { add_addr(idev, &addr, plen, scope); - addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags); + addrconf_prefix_route(&addr, plen, idev->dev, 0, pflags, + GFP_ATOMIC); return; } @@ -3072,7 +3077,7 @@ static void sit_add_v4_addrs(struct inet6_dev *idev) add_addr(idev, &addr, plen, flag); addrconf_prefix_route(&addr, plen, idev->dev, 0, - pflags); + pflags, GFP_ATOMIC); } } } @@ -3112,7 +3117,8 @@ void addrconf_add_linklocal(struct inet6_dev *idev, ifp = ipv6_add_addr(idev, addr, NULL, 64, IFA_LINK, addr_flags, INFINITY_LIFE_TIME, INFINITY_LIFE_TIME, true, NULL); if (!IS_ERR(ifp)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, 0, 0); + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, idev->dev, + 0, 0, GFP_ATOMIC); addrconf_dad_start(ifp); in6_ifa_put(ifp); } @@ -3227,7 +3233,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) addrconf_add_linklocal(idev, &addr, IFA_F_STABLE_PRIVACY); else if (prefix_route) - addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + addrconf_prefix_route(&addr, 64, idev->dev, + 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_EUI64: /* addrconf_add_linklocal also adds a prefix_route and we @@ -3237,7 +3244,8 @@ static void addrconf_addr_gen(struct inet6_dev *idev, bool prefix_route) if (ipv6_generate_eui64(addr.s6_addr + 8, idev->dev) == 0) addrconf_add_linklocal(idev, &addr, 0); else if (prefix_route) - addrconf_prefix_route(&addr, 64, idev->dev, 0, 0); + addrconf_prefix_route(&addr, 64, idev->dev, + 0, 0, GFP_KERNEL); break; case IN6_ADDR_GEN_MODE_NONE: default: @@ -3329,32 +3337,34 @@ static void addrconf_gre_config(struct net_device *dev) } #endif -static int fixup_permanent_addr(struct inet6_dev *idev, +static int fixup_permanent_addr(struct net *net, + struct inet6_dev *idev, struct inet6_ifaddr *ifp) { - /* !rt6i_node means the host route was removed from the + /* !fib6_node means the host route was removed from the * FIB, for example, if 'lo' device is taken down. In that * case regenerate the host route. */ - if (!ifp->rt || !ifp->rt->rt6i_node) { - struct rt6_info *rt, *prev; + if (!ifp->rt || !ifp->rt->fib6_node) { + struct fib6_info *f6i, *prev; - rt = addrconf_dst_alloc(idev, &ifp->addr, false); - if (IS_ERR(rt)) - return PTR_ERR(rt); + f6i = addrconf_f6i_alloc(net, idev, &ifp->addr, false, + GFP_ATOMIC); + if (IS_ERR(f6i)) + return PTR_ERR(f6i); /* ifp->rt can be accessed outside of rtnl */ spin_lock(&ifp->lock); prev = ifp->rt; - ifp->rt = rt; + ifp->rt = f6i; spin_unlock(&ifp->lock); - ip6_rt_put(prev); + fib6_info_release(prev); } if (!(ifp->flags & IFA_F_NOPREFIXROUTE)) { addrconf_prefix_route(&ifp->addr, ifp->prefix_len, - idev->dev, 0, 0); + idev->dev, 0, 0, GFP_ATOMIC); } if (ifp->state == INET6_IFADDR_STATE_PREDAD) @@ -3363,7 +3373,7 @@ static int fixup_permanent_addr(struct inet6_dev *idev, return 0; } -static void addrconf_permanent_addr(struct net_device *dev) +static void addrconf_permanent_addr(struct net *net, struct net_device *dev) { struct inet6_ifaddr *ifp, *tmp; struct inet6_dev *idev; @@ -3376,7 +3386,7 @@ static void addrconf_permanent_addr(struct net_device *dev) list_for_each_entry_safe(ifp, tmp, &idev->addr_list, if_list) { if ((ifp->flags & IFA_F_PERMANENT) && - fixup_permanent_addr(idev, ifp) < 0) { + fixup_permanent_addr(net, idev, ifp) < 0) { write_unlock_bh(&idev->lock); in6_ifa_hold(ifp); ipv6_del_addr(ifp); @@ -3445,7 +3455,7 @@ static int addrconf_notify(struct notifier_block *this, unsigned long event, if (event == NETDEV_UP) { /* restore routes for permanent addresses */ - addrconf_permanent_addr(dev); + addrconf_permanent_addr(net, dev); if (!addrconf_link_ready(dev)) { /* device is not ready yet. */ @@ -3612,8 +3622,7 @@ static int addrconf_ifdown(struct net_device *dev, int how) struct net *net = dev_net(dev); struct inet6_dev *idev; struct inet6_ifaddr *ifa, *tmp; - int _keep_addr; - bool keep_addr; + bool keep_addr = false; int state, i; ASSERT_RTNL(); @@ -3639,15 +3648,18 @@ static int addrconf_ifdown(struct net_device *dev, int how) } - /* aggregate the system setting and interface setting */ - _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; - if (!_keep_addr) - _keep_addr = idev->cnf.keep_addr_on_down; - /* combine the user config with event to determine if permanent * addresses are to be removed from address hash table */ - keep_addr = !(how || _keep_addr <= 0 || idev->cnf.disable_ipv6); + if (!how && !idev->cnf.disable_ipv6) { + /* aggregate the system setting and interface setting */ + int _keep_addr = net->ipv6.devconf_all->keep_addr_on_down; + + if (!_keep_addr) + _keep_addr = idev->cnf.keep_addr_on_down; + + keep_addr = (_keep_addr > 0); + } /* Step 2: clear hash table */ for (i = 0; i < IN6_ADDR_HSIZE; i++) { @@ -3697,13 +3709,8 @@ restart: write_lock_bh(&idev->lock); } - /* re-combine the user config with event to determine if permanent - * addresses are to be removed from the interface list - */ - keep_addr = (!how && _keep_addr > 0 && !idev->cnf.disable_ipv6); - list_for_each_entry_safe(ifa, tmp, &idev->addr_list, if_list) { - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; bool keep; addrconf_del_dad_work(ifa); @@ -3731,7 +3738,7 @@ restart: spin_unlock_bh(&ifa->lock); if (rt) - ip6_del_rt(rt); + ip6_del_rt(net, rt); if (state != INET6_IFADDR_STATE_DEAD) { __ipv6_ifa_notify(RTM_DELADDR, ifa); @@ -3849,6 +3856,7 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) struct inet6_dev *idev = ifp->idev; struct net_device *dev = idev->dev; bool bump_id, notify = false; + struct net *net; addrconf_join_solict(dev, &ifp->addr); @@ -3859,8 +3867,9 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) if (ifp->state == INET6_IFADDR_STATE_DEAD) goto out; + net = dev_net(dev); if (dev->flags&(IFF_NOARP|IFF_LOOPBACK) || - (dev_net(dev)->ipv6.devconf_all->accept_dad < 1 && + (net->ipv6.devconf_all->accept_dad < 1 && idev->cnf.accept_dad < 1) || !(ifp->flags&IFA_F_TENTATIVE) || ifp->flags & IFA_F_NODAD) { @@ -3896,8 +3905,8 @@ static void addrconf_dad_begin(struct inet6_ifaddr *ifp) * Frames right away */ if (ifp->flags & IFA_F_OPTIMISTIC) { - ip6_ins_rt(ifp->rt); - if (ipv6_use_optimistic_addr(dev_net(dev), idev)) { + ip6_ins_rt(net, ifp->rt); + if (ipv6_use_optimistic_addr(net, idev)) { /* Because optimistic nodes can use this address, * notify listeners. If DAD fails, RTM_DELADDR is sent. */ @@ -4563,8 +4572,9 @@ static int inet6_addr_modify(struct inet6_ifaddr *ifp, u32 ifa_flags, ipv6_ifa_notify(0, ifp); if (!(ifa_flags & IFA_F_NOPREFIXROUTE)) { - addrconf_prefix_route(&ifp->addr, ifp->prefix_len, ifp->idev->dev, - expires, flags); + addrconf_prefix_route(&ifp->addr, ifp->prefix_len, + ifp->idev->dev, expires, flags, + GFP_KERNEL); } else if (had_prefixroute) { enum cleanup_prefix_rt_t action; unsigned long rt_expires; @@ -4804,9 +4814,10 @@ static int inet6_fill_ifmcaddr(struct sk_buff *skb, struct ifmcaddr6 *ifmca, static int inet6_fill_ifacaddr(struct sk_buff *skb, struct ifacaddr6 *ifaca, u32 portid, u32 seq, int event, unsigned int flags) { + struct net_device *dev = fib6_info_nh_dev(ifaca->aca_rt); + int ifindex = dev ? dev->ifindex : 1; struct nlmsghdr *nlh; u8 scope = RT_SCOPE_UNIVERSE; - int ifindex = ifaca->aca_idev->dev->ifindex; if (ipv6_addr_scope(&ifaca->aca_addr) & IFA_SITE) scope = RT_SCOPE_SITE; @@ -5029,14 +5040,6 @@ static void inet6_ifa_notify(int event, struct inet6_ifaddr *ifa) struct net *net = dev_net(ifa->idev->dev); int err = -ENOBUFS; - /* Don't send DELADDR notification for TENTATIVE address, - * since NEWADDR notification is sent only after removing - * TENTATIVE flag, if DAD has not failed. - */ - if (ifa->flags & IFA_F_TENTATIVE && !(ifa->flags & IFA_F_DADFAILED) && - event == RTM_DELADDR) - return; - skb = nlmsg_new(inet6_ifaddr_msgsize(), GFP_ATOMIC); if (!skb) goto errout; @@ -5607,29 +5610,30 @@ static void __ipv6_ifa_notify(int event, struct inet6_ifaddr *ifp) * our DAD process, so we don't need * to do it again */ - if (!rcu_access_pointer(ifp->rt->rt6i_node)) - ip6_ins_rt(ifp->rt); + if (!rcu_access_pointer(ifp->rt->fib6_node)) + ip6_ins_rt(net, ifp->rt); if (ifp->idev->cnf.forwarding) addrconf_join_anycast(ifp); if (!ipv6_addr_any(&ifp->peer_addr)) addrconf_prefix_route(&ifp->peer_addr, 128, - ifp->idev->dev, 0, 0); + ifp->idev->dev, 0, 0, + GFP_ATOMIC); break; case RTM_DELADDR: if (ifp->idev->cnf.forwarding) addrconf_leave_anycast(ifp); addrconf_leave_solict(ifp->idev, &ifp->addr); if (!ipv6_addr_any(&ifp->peer_addr)) { - struct rt6_info *rt; + struct fib6_info *rt; rt = addrconf_get_prefix_route(&ifp->peer_addr, 128, ifp->idev->dev, 0, 0); if (rt) - ip6_del_rt(rt); + ip6_del_rt(net, rt); } if (ifp->rt) { - if (dst_hold_safe(&ifp->rt->dst)) - ip6_del_rt(ifp->rt); + ip6_del_rt(net, ifp->rt); + ifp->rt = NULL; } rt_genid_bump_ipv6(net); break; @@ -5976,11 +5980,11 @@ void addrconf_disable_policy_idev(struct inet6_dev *idev, int val) list_for_each_entry(ifa, &idev->addr_list, if_list) { spin_lock(&ifa->lock); if (ifa->rt) { - struct rt6_info *rt = ifa->rt; + struct fib6_info *rt = ifa->rt; int cpu; rcu_read_lock(); - addrconf_set_nopolicy(ifa->rt, val); + ifa->rt->dst_nopolicy = val ? true : false; if (rt->rt6i_pcpu) { for_each_possible_cpu(cpu) { struct rt6_info **rtp; diff --git a/net/ipv6/af_inet6.c b/net/ipv6/af_inet6.c index 8da0b513f188..d0af96e0d109 100644 --- a/net/ipv6/af_inet6.c +++ b/net/ipv6/af_inet6.c @@ -273,33 +273,8 @@ out_rcu_unlock: goto out; } - -/* bind for INET6 API */ -int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) -{ - struct sock *sk = sock->sk; - int err = 0; - - /* If the socket has its own bind function then use it. */ - if (sk->sk_prot->bind) - return sk->sk_prot->bind(sk, uaddr, addr_len); - - if (addr_len < SIN6_LEN_RFC2133) - return -EINVAL; - - /* BPF prog is run before any checks are done so that if the prog - * changes context in a wrong way it will be caught. - */ - err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr); - if (err) - return err; - - return __inet6_bind(sk, uaddr, addr_len, false, true); -} -EXPORT_SYMBOL(inet6_bind); - -int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, - bool force_bind_address_no_port, bool with_lock) +static int __inet6_bind(struct sock *sk, struct sockaddr *uaddr, int addr_len, + bool force_bind_address_no_port, bool with_lock) { struct sockaddr_in6 *addr = (struct sockaddr_in6 *)uaddr; struct inet_sock *inet = inet_sk(sk); @@ -444,6 +419,30 @@ out_unlock: goto out; } +/* bind for INET6 API */ +int inet6_bind(struct socket *sock, struct sockaddr *uaddr, int addr_len) +{ + struct sock *sk = sock->sk; + int err = 0; + + /* If the socket has its own bind function then use it. */ + if (sk->sk_prot->bind) + return sk->sk_prot->bind(sk, uaddr, addr_len); + + if (addr_len < SIN6_LEN_RFC2133) + return -EINVAL; + + /* BPF prog is run before any checks are done so that if the prog + * changes context in a wrong way it will be caught. + */ + err = BPF_CGROUP_RUN_PROG_INET6_BIND(sk, uaddr); + if (err) + return err; + + return __inet6_bind(sk, uaddr, addr_len, false, true); +} +EXPORT_SYMBOL(inet6_bind); + int inet6_release(struct socket *sock) { struct sock *sk = sock->sk; @@ -579,7 +578,9 @@ const struct proto_ops inet6_stream_ops = { .getsockopt = sock_common_getsockopt, /* ok */ .sendmsg = inet_sendmsg, /* ok */ .recvmsg = inet_recvmsg, /* ok */ - .mmap = sock_no_mmap, +#ifdef CONFIG_MMU + .mmap = tcp_mmap, +#endif .sendpage = inet_sendpage, .sendmsg_locked = tcp_sendmsg_locked, .sendpage_locked = tcp_sendpage_locked, @@ -590,6 +591,7 @@ const struct proto_ops inet6_stream_ops = { .compat_setsockopt = compat_sock_common_setsockopt, .compat_getsockopt = compat_sock_common_getsockopt, #endif + .set_rcvlowat = tcp_set_rcvlowat, }; const struct proto_ops inet6_dgram_ops = { diff --git a/net/ipv6/anycast.c b/net/ipv6/anycast.c index bbcabbba9bd8..0250d199e527 100644 --- a/net/ipv6/anycast.c +++ b/net/ipv6/anycast.c @@ -212,16 +212,14 @@ static void aca_get(struct ifacaddr6 *aca) static void aca_put(struct ifacaddr6 *ac) { if (refcount_dec_and_test(&ac->aca_refcnt)) { - in6_dev_put(ac->aca_idev); - dst_release(&ac->aca_rt->dst); + fib6_info_release(ac->aca_rt); kfree(ac); } } -static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, +static struct ifacaddr6 *aca_alloc(struct fib6_info *f6i, const struct in6_addr *addr) { - struct inet6_dev *idev = rt->rt6i_idev; struct ifacaddr6 *aca; aca = kzalloc(sizeof(*aca), GFP_ATOMIC); @@ -229,9 +227,8 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, return NULL; aca->aca_addr = *addr; - in6_dev_hold(idev); - aca->aca_idev = idev; - aca->aca_rt = rt; + fib6_info_hold(f6i); + aca->aca_rt = f6i; aca->aca_users = 1; /* aca_tstamp should be updated upon changes */ aca->aca_cstamp = aca->aca_tstamp = jiffies; @@ -246,7 +243,8 @@ static struct ifacaddr6 *aca_alloc(struct rt6_info *rt, int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) { struct ifacaddr6 *aca; - struct rt6_info *rt; + struct fib6_info *f6i; + struct net *net; int err; ASSERT_RTNL(); @@ -265,14 +263,15 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) } } - rt = addrconf_dst_alloc(idev, addr, true); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); + net = dev_net(idev->dev); + f6i = addrconf_f6i_alloc(net, idev, addr, true, GFP_ATOMIC); + if (IS_ERR(f6i)) { + err = PTR_ERR(f6i); goto out; } - aca = aca_alloc(rt, addr); + aca = aca_alloc(f6i, addr); if (!aca) { - ip6_rt_put(rt); + fib6_info_release(f6i); err = -ENOMEM; goto out; } @@ -286,7 +285,7 @@ int __ipv6_dev_ac_inc(struct inet6_dev *idev, const struct in6_addr *addr) aca_get(aca); write_unlock_bh(&idev->lock); - ip6_ins_rt(rt); + ip6_ins_rt(net, f6i); addrconf_join_solict(idev->dev, &aca->aca_addr); @@ -328,8 +327,7 @@ int __ipv6_dev_ac_dec(struct inet6_dev *idev, const struct in6_addr *addr) write_unlock_bh(&idev->lock); addrconf_leave_solict(idev, &aca->aca_addr); - dst_hold(&aca->aca_rt->dst); - ip6_del_rt(aca->aca_rt); + ip6_del_rt(dev_net(idev->dev), aca->aca_rt); aca_put(aca); return 0; @@ -356,8 +354,7 @@ void ipv6_ac_destroy_dev(struct inet6_dev *idev) addrconf_leave_solict(idev, &aca->aca_addr); - dst_hold(&aca->aca_rt->dst); - ip6_del_rt(aca->aca_rt); + ip6_del_rt(dev_net(idev->dev), aca->aca_rt); aca_put(aca); diff --git a/net/ipv6/exthdrs.c b/net/ipv6/exthdrs.c index bc68eb661970..5bc2bf3733ab 100644 --- a/net/ipv6/exthdrs.c +++ b/net/ipv6/exthdrs.c @@ -280,6 +280,7 @@ static const struct tlvtype_proc tlvprocdestopt_lst[] = { static int ipv6_destopt_rcv(struct sk_buff *skb) { + struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); #if IS_ENABLED(CONFIG_IPV6_MIP6) __u16 dstbuf; @@ -291,7 +292,7 @@ static int ipv6_destopt_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - __IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + __IP6_INC_STATS(dev_net(dst->dev), idev, IPSTATS_MIB_INHDRERRORS); fail_and_free: kfree_skb(skb); @@ -319,8 +320,7 @@ fail_and_free: return 1; } - __IP6_INC_STATS(dev_net(dst->dev), - ip6_dst_idev(dst), IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return -1; } @@ -416,8 +416,7 @@ looped_back: } if (hdr->segments_left >= (hdr->hdrlen >> 1)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); @@ -456,8 +455,7 @@ looped_back: if (skb_dst(skb)->dev->flags & IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); @@ -481,10 +479,10 @@ looped_back: /* called with rcu_read_lock() */ static int ipv6_rthdr_rcv(struct sk_buff *skb) { + struct inet6_dev *idev = __in6_dev_get(skb->dev); struct inet6_skb_parm *opt = IP6CB(skb); struct in6_addr *addr = NULL; struct in6_addr daddr; - struct inet6_dev *idev; int n, i; struct ipv6_rt_hdr *hdr; struct rt0_hdr *rthdr; @@ -498,8 +496,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (!pskb_may_pull(skb, skb_transport_offset(skb) + 8) || !pskb_may_pull(skb, (skb_transport_offset(skb) + ((skb_transport_header(skb)[1] + 1) << 3)))) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } @@ -508,8 +505,7 @@ static int ipv6_rthdr_rcv(struct sk_buff *skb) if (ipv6_addr_is_multicast(&ipv6_hdr(skb)->daddr) || skb->pkt_type != PACKET_HOST) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -527,7 +523,7 @@ looped_back: * processed by own */ if (!addr) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; @@ -553,8 +549,7 @@ looped_back: goto unknown_rh; /* Silently discard invalid RTH type 2 */ if (hdr->hdrlen != 2 || hdr->segments_left != 1) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -1; } @@ -572,8 +567,7 @@ looped_back: n = hdr->hdrlen >> 1; if (hdr->segments_left > n) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, ((&hdr->segments_left) - skb_network_header(skb))); @@ -609,14 +603,12 @@ looped_back: if (xfrm6_input_addr(skb, (xfrm_address_t *)addr, (xfrm_address_t *)&ipv6_hdr(skb)->saddr, IPPROTO_ROUTING) < 0) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } if (!ipv6_chk_home_addr(dev_net(skb_dst(skb)->dev), addr)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -627,8 +619,7 @@ looped_back: } if (ipv6_addr_is_multicast(addr)) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); kfree_skb(skb); return -1; } @@ -647,8 +638,7 @@ looped_back: if (skb_dst(skb)->dev->flags&IFF_LOOPBACK) { if (ipv6_hdr(skb)->hop_limit <= 1) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); kfree_skb(skb); @@ -663,7 +653,7 @@ looped_back: return -1; unknown_rh: - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, (&hdr->type) - skb_network_header(skb)); return -1; @@ -755,34 +745,31 @@ static bool ipv6_hop_ra(struct sk_buff *skb, int optoff) static bool ipv6_hop_jumbo(struct sk_buff *skb, int optoff) { const unsigned char *nh = skb_network_header(skb); + struct inet6_dev *idev = __in6_dev_get_safely(skb->dev); struct net *net = ipv6_skb_net(skb); u32 pkt_len; if (nh[optoff + 1] != 4 || (optoff & 3) != 2) { net_dbg_ratelimited("ipv6_hop_jumbo: wrong jumbo opt length/alignment %d\n", nh[optoff+1]); - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); goto drop; } pkt_len = ntohl(*(__be32 *)(nh + optoff + 2)); if (pkt_len <= IPV6_MAXPLEN) { - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff+2); return false; } if (ipv6_hdr(skb)->payload_len) { - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, optoff); return false; } if (pkt_len > skb->len - sizeof(struct ipv6hdr)) { - __IP6_INC_STATS(net, ipv6_skb_idev(skb), - IPSTATS_MIB_INTRUNCATEDPKTS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTRUNCATEDPKTS); goto drop; } diff --git a/net/ipv6/exthdrs_core.c b/net/ipv6/exthdrs_core.c index b643f5ce6c80..ae365df8abf7 100644 --- a/net/ipv6/exthdrs_core.c +++ b/net/ipv6/exthdrs_core.c @@ -161,7 +161,7 @@ EXPORT_SYMBOL_GPL(ipv6_find_tlv); * if target < 0. "last header" is transport protocol header, ESP, or * "No next header". * - * Note that *offset is used as input/output parameter. an if it is not zero, + * Note that *offset is used as input/output parameter, and if it is not zero, * then it must be a valid offset to an inner IPv6 header. This can be used * to explore inner IPv6 header, eg. ICMPv6 error messages. * diff --git a/net/ipv6/fib6_rules.c b/net/ipv6/fib6_rules.c index df113c7b5fc8..6547fc6491a6 100644 --- a/net/ipv6/fib6_rules.c +++ b/net/ipv6/fib6_rules.c @@ -245,15 +245,18 @@ static const struct nla_policy fib6_rule_policy[FRA_MAX+1] = { static int fib6_rule_configure(struct fib_rule *rule, struct sk_buff *skb, struct fib_rule_hdr *frh, - struct nlattr **tb) + struct nlattr **tb, + struct netlink_ext_ack *extack) { int err = -EINVAL; struct net *net = sock_net(skb->sk); struct fib6_rule *rule6 = (struct fib6_rule *) rule; if (rule->action == FR_ACT_TO_TBL && !rule->l3mdev) { - if (rule->table == RT6_TABLE_UNSPEC) + if (rule->table == RT6_TABLE_UNSPEC) { + NL_SET_ERR_MSG(extack, "Invalid table"); goto errout; + } if (fib6_new_table(net, rule->table) == NULL) { err = -ENOBUFS; diff --git a/net/ipv6/ip6_fib.c b/net/ipv6/ip6_fib.c index deab2db6692e..f0a4262a4789 100644 --- a/net/ipv6/ip6_fib.c +++ b/net/ipv6/ip6_fib.c @@ -43,7 +43,7 @@ static struct kmem_cache *fib6_node_kmem __read_mostly; struct fib6_cleaner { struct fib6_walker w; struct net *net; - int (*func)(struct rt6_info *, void *arg); + int (*func)(struct fib6_info *, void *arg); int sernum; void *arg; }; @@ -54,7 +54,7 @@ struct fib6_cleaner { #define FWS_INIT FWS_L #endif -static struct rt6_info *fib6_find_prefix(struct net *net, +static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn); static struct fib6_node *fib6_repair_tree(struct net *net, @@ -105,13 +105,12 @@ enum { FIB6_NO_SERNUM_CHANGE = 0, }; -void fib6_update_sernum(struct rt6_info *rt) +void fib6_update_sernum(struct net *net, struct fib6_info *f6i) { - struct net *net = dev_net(rt->dst.dev); struct fib6_node *fn; - fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + fn = rcu_dereference_protected(f6i->fib6_node, + lockdep_is_held(&f6i->fib6_table->tb6_lock)); if (fn) fn->fn_sernum = fib6_new_sernum(net); } @@ -146,6 +145,69 @@ static __be32 addr_bit_set(const void *token, int fn_bit) addr[fn_bit >> 5]; } +struct fib6_info *fib6_info_alloc(gfp_t gfp_flags) +{ + struct fib6_info *f6i; + + f6i = kzalloc(sizeof(*f6i), gfp_flags); + if (!f6i) + return NULL; + + f6i->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, gfp_flags); + if (!f6i->rt6i_pcpu) { + kfree(f6i); + return NULL; + } + + INIT_LIST_HEAD(&f6i->fib6_siblings); + f6i->fib6_metrics = (struct dst_metrics *)&dst_default_metrics; + + atomic_inc(&f6i->fib6_ref); + + return f6i; +} + +void fib6_info_destroy(struct fib6_info *f6i) +{ + struct rt6_exception_bucket *bucket; + struct dst_metrics *m; + + WARN_ON(f6i->fib6_node); + + bucket = rcu_dereference_protected(f6i->rt6i_exception_bucket, 1); + if (bucket) { + f6i->rt6i_exception_bucket = NULL; + kfree(bucket); + } + + if (f6i->rt6i_pcpu) { + int cpu; + + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; + + ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + dst_dev_put(&pcpu_rt->dst); + dst_release(&pcpu_rt->dst); + *ppcpu_rt = NULL; + } + } + } + + if (f6i->fib6_nh.nh_dev) + dev_put(f6i->fib6_nh.nh_dev); + + m = f6i->fib6_metrics; + if (m != &dst_default_metrics && refcount_dec_and_test(&m->refcnt)) + kfree(m); + + kfree(f6i); +} +EXPORT_SYMBOL_GPL(fib6_info_destroy); + static struct fib6_node *node_alloc(struct net *net) { struct fib6_node *fn; @@ -176,28 +238,6 @@ static void node_free(struct net *net, struct fib6_node *fn) net->ipv6.rt6_stats->fib_nodes--; } -void rt6_free_pcpu(struct rt6_info *non_pcpu_rt) -{ - int cpu; - - if (!non_pcpu_rt->rt6i_pcpu) - return; - - for_each_possible_cpu(cpu) { - struct rt6_info **ppcpu_rt; - struct rt6_info *pcpu_rt; - - ppcpu_rt = per_cpu_ptr(non_pcpu_rt->rt6i_pcpu, cpu); - pcpu_rt = *ppcpu_rt; - if (pcpu_rt) { - dst_dev_put(&pcpu_rt->dst); - dst_release(&pcpu_rt->dst); - *ppcpu_rt = NULL; - } - } -} -EXPORT_SYMBOL_GPL(rt6_free_pcpu); - static void fib6_free_table(struct fib6_table *table) { inetpeer_invalidate_tree(&table->tb6_peers); @@ -232,7 +272,7 @@ static struct fib6_table *fib6_alloc_table(struct net *net, u32 id) if (table) { table->tb6_id = id; rcu_assign_pointer(table->tb6_root.leaf, - net->ipv6.ip6_null_entry); + net->ipv6.fib6_null_entry); table->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&table->tb6_peers); } @@ -340,7 +380,7 @@ unsigned int fib6_tables_seq_read(struct net *net) static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, enum fib_event_type event_type, - struct rt6_info *rt) + struct fib6_info *rt) { struct fib6_entry_notifier_info info = { .rt = rt, @@ -351,7 +391,7 @@ static int call_fib6_entry_notifier(struct notifier_block *nb, struct net *net, static int call_fib6_entry_notifiers(struct net *net, enum fib_event_type event_type, - struct rt6_info *rt, + struct fib6_info *rt, struct netlink_ext_ack *extack) { struct fib6_entry_notifier_info info = { @@ -359,7 +399,7 @@ static int call_fib6_entry_notifiers(struct net *net, .rt = rt, }; - rt->rt6i_table->fib_seq++; + rt->fib6_table->fib_seq++; return call_fib6_notifiers(net, event_type, &info.info); } @@ -368,16 +408,16 @@ struct fib6_dump_arg { struct notifier_block *nb; }; -static void fib6_rt_dump(struct rt6_info *rt, struct fib6_dump_arg *arg) +static void fib6_rt_dump(struct fib6_info *rt, struct fib6_dump_arg *arg) { - if (rt == arg->net->ipv6.ip6_null_entry) + if (rt == arg->net->ipv6.fib6_null_entry) return; call_fib6_entry_notifier(arg->nb, arg->net, FIB_EVENT_ENTRY_ADD, rt); } static int fib6_node_dump(struct fib6_walker *w) { - struct rt6_info *rt; + struct fib6_info *rt; for_each_fib6_walker_rt(w) fib6_rt_dump(rt, w->args); @@ -426,7 +466,7 @@ int fib6_tables_dump(struct net *net, struct notifier_block *nb) static int fib6_dump_node(struct fib6_walker *w) { int res; - struct rt6_info *rt; + struct fib6_info *rt; for_each_fib6_walker_rt(w) { res = rt6_dump_route(rt, w->args); @@ -441,10 +481,10 @@ static int fib6_dump_node(struct fib6_walker *w) * last sibling of this route (no need to dump the * sibling routes again) */ - if (rt->rt6i_nsiblings) - rt = list_last_entry(&rt->rt6i_siblings, - struct rt6_info, - rt6i_siblings); + if (rt->fib6_nsiblings) + rt = list_last_entry(&rt->fib6_siblings, + struct fib6_info, + fib6_siblings); } w->leaf = NULL; return 0; @@ -579,6 +619,24 @@ out: return res; } +void fib6_metric_set(struct fib6_info *f6i, int metric, u32 val) +{ + if (!f6i) + return; + + if (f6i->fib6_metrics == &dst_default_metrics) { + struct dst_metrics *p = kzalloc(sizeof(*p), GFP_ATOMIC); + + if (!p) + return; + + refcount_set(&p->refcnt, 1); + f6i->fib6_metrics = p; + } + + f6i->fib6_metrics->metrics[metric - 1] = val; +} + /* * Routing Table * @@ -608,7 +666,7 @@ static struct fib6_node *fib6_add_1(struct net *net, fn = root; do { - struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); key = (struct rt6key *)((u8 *)leaf + offset); @@ -637,11 +695,11 @@ static struct fib6_node *fib6_add_1(struct net *net, /* clean up an intermediate node */ if (!(fn->fn_flags & RTN_RTINFO)) { RCU_INIT_POINTER(fn->leaf, NULL); - rt6_release(leaf); + fib6_info_release(leaf); /* remove null_entry in the root node */ } else if (fn->fn_flags & RTN_TL_ROOT && rcu_access_pointer(fn->leaf) == - net->ipv6.ip6_null_entry) { + net->ipv6.fib6_null_entry) { RCU_INIT_POINTER(fn->leaf, NULL); } @@ -750,7 +808,7 @@ insert_above: RCU_INIT_POINTER(in->parent, pn); in->leaf = fn->leaf; atomic_inc(&rcu_dereference_protected(in->leaf, - lockdep_is_held(&table->tb6_lock))->rt6i_ref); + lockdep_is_held(&table->tb6_lock))->fib6_ref); /* update parent pointer */ if (dir) @@ -802,44 +860,37 @@ insert_above: return ln; } -static void fib6_copy_metrics(u32 *mp, const struct mx6_config *mxc) -{ - int i; - - for (i = 0; i < RTAX_MAX; i++) { - if (test_bit(i, mxc->mx_valid)) - mp[i] = mxc->mx[i]; - } -} - -static int fib6_commit_metrics(struct dst_entry *dst, struct mx6_config *mxc) +static void fib6_drop_pcpu_from(struct fib6_info *f6i, + const struct fib6_table *table) { - if (!mxc->mx) - return 0; - - if (dst->flags & DST_HOST) { - u32 *mp = dst_metrics_write_ptr(dst); + int cpu; - if (unlikely(!mp)) - return -ENOMEM; + /* release the reference to this fib entry from + * all of its cached pcpu routes + */ + for_each_possible_cpu(cpu) { + struct rt6_info **ppcpu_rt; + struct rt6_info *pcpu_rt; - fib6_copy_metrics(mp, mxc); - } else { - dst_init_metrics(dst, mxc->mx, false); + ppcpu_rt = per_cpu_ptr(f6i->rt6i_pcpu, cpu); + pcpu_rt = *ppcpu_rt; + if (pcpu_rt) { + struct fib6_info *from; - /* We've stolen mx now. */ - mxc->mx = NULL; + from = rcu_dereference_protected(pcpu_rt->from, + lockdep_is_held(&table->tb6_lock)); + rcu_assign_pointer(pcpu_rt->from, NULL); + fib6_info_release(from); + } } - - return 0; } -static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, +static void fib6_purge_rt(struct fib6_info *rt, struct fib6_node *fn, struct net *net) { - struct fib6_table *table = rt->rt6i_table; + struct fib6_table *table = rt->fib6_table; - if (atomic_read(&rt->rt6i_ref) != 1) { + if (atomic_read(&rt->fib6_ref) != 1) { /* This route is used as dummy address holder in some split * nodes. It is not leaked, but it still holds other resources, * which must be released in time. So, scan ascendant nodes @@ -847,18 +898,22 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * to still alive ones. */ while (fn) { - struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, + struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *new_leaf; + struct fib6_info *new_leaf; if (!(fn->fn_flags & RTN_RTINFO) && leaf == rt) { new_leaf = fib6_find_prefix(net, table, fn); - atomic_inc(&new_leaf->rt6i_ref); + atomic_inc(&new_leaf->fib6_ref); + rcu_assign_pointer(fn->leaf, new_leaf); - rt6_release(rt); + fib6_info_release(rt); } fn = rcu_dereference_protected(fn->parent, lockdep_is_held(&table->tb6_lock)); } + + if (rt->rt6i_pcpu) + fib6_drop_pcpu_from(rt, table); } } @@ -866,15 +921,15 @@ static void fib6_purge_rt(struct rt6_info *rt, struct fib6_node *fn, * Insert routing information in a node. */ -static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc, +static int fib6_add_rt2node(struct fib6_node *fn, struct fib6_info *rt, + struct nl_info *info, struct netlink_ext_ack *extack) { - struct rt6_info *leaf = rcu_dereference_protected(fn->leaf, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); - struct rt6_info *iter = NULL; - struct rt6_info __rcu **ins; - struct rt6_info __rcu **fallback_ins = NULL; + struct fib6_info *leaf = rcu_dereference_protected(fn->leaf, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + struct fib6_info *iter = NULL; + struct fib6_info __rcu **ins; + struct fib6_info __rcu **fallback_ins = NULL; int replace = (info->nlh && (info->nlh->nlmsg_flags & NLM_F_REPLACE)); int add = (!info->nlh || @@ -890,13 +945,13 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, ins = &fn->leaf; for (iter = leaf; iter; - iter = rcu_dereference_protected(iter->rt6_next, - lockdep_is_held(&rt->rt6i_table->tb6_lock))) { + iter = rcu_dereference_protected(iter->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock))) { /* * Search for duplicates */ - if (iter->rt6i_metric == rt->rt6i_metric) { + if (iter->fib6_metric == rt->fib6_metric) { /* * Same priority level */ @@ -916,15 +971,15 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, } if (rt6_duplicate_nexthop(iter, rt)) { - if (rt->rt6i_nsiblings) - rt->rt6i_nsiblings = 0; - if (!(iter->rt6i_flags & RTF_EXPIRES)) + if (rt->fib6_nsiblings) + rt->fib6_nsiblings = 0; + if (!(iter->fib6_flags & RTF_EXPIRES)) return -EEXIST; - if (!(rt->rt6i_flags & RTF_EXPIRES)) - rt6_clean_expires(iter); + if (!(rt->fib6_flags & RTF_EXPIRES)) + fib6_clean_expires(iter); else - rt6_set_expires(iter, rt->dst.expires); - iter->rt6i_pmtu = rt->rt6i_pmtu; + fib6_set_expires(iter, rt->expires); + fib6_metric_set(iter, RTAX_MTU, rt->fib6_pmtu); return -EEXIST; } /* If we have the same destination and the same metric, @@ -940,21 +995,21 @@ static int fib6_add_rt2node(struct fib6_node *fn, struct rt6_info *rt, */ if (rt_can_ecmp && rt6_qualify_for_ecmp(iter)) - rt->rt6i_nsiblings++; + rt->fib6_nsiblings++; } - if (iter->rt6i_metric > rt->rt6i_metric) + if (iter->fib6_metric > rt->fib6_metric) break; next_iter: - ins = &iter->rt6_next; + ins = &iter->fib6_next; } if (fallback_ins && !found) { /* No ECMP-able route found, replace first non-ECMP one */ ins = fallback_ins; iter = rcu_dereference_protected(*ins, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + lockdep_is_held(&rt->fib6_table->tb6_lock)); found++; } @@ -963,34 +1018,34 @@ next_iter: fn->rr_ptr = NULL; /* Link this route to others same route. */ - if (rt->rt6i_nsiblings) { - unsigned int rt6i_nsiblings; - struct rt6_info *sibling, *temp_sibling; + if (rt->fib6_nsiblings) { + unsigned int fib6_nsiblings; + struct fib6_info *sibling, *temp_sibling; /* Find the first route that have the same metric */ sibling = leaf; while (sibling) { - if (sibling->rt6i_metric == rt->rt6i_metric && + if (sibling->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(sibling)) { - list_add_tail(&rt->rt6i_siblings, - &sibling->rt6i_siblings); + list_add_tail(&rt->fib6_siblings, + &sibling->fib6_siblings); break; } - sibling = rcu_dereference_protected(sibling->rt6_next, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + sibling = rcu_dereference_protected(sibling->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } /* For each sibling in the list, increment the counter of * siblings. BUG() if counters does not match, list of siblings * is broken! */ - rt6i_nsiblings = 0; + fib6_nsiblings = 0; list_for_each_entry_safe(sibling, temp_sibling, - &rt->rt6i_siblings, rt6i_siblings) { - sibling->rt6i_nsiblings++; - BUG_ON(sibling->rt6i_nsiblings != rt->rt6i_nsiblings); - rt6i_nsiblings++; + &rt->fib6_siblings, fib6_siblings) { + sibling->fib6_nsiblings++; + BUG_ON(sibling->fib6_nsiblings != rt->fib6_nsiblings); + fib6_nsiblings++; } - BUG_ON(rt6i_nsiblings != rt->rt6i_nsiblings); + BUG_ON(fib6_nsiblings != rt->fib6_nsiblings); rt6_multipath_rebalance(temp_sibling); } @@ -1003,9 +1058,6 @@ next_iter: add: nlflags |= NLM_F_CREATE; - err = fib6_commit_metrics(&rt->dst, mxc); - if (err) - return err; err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_ADD, @@ -1013,9 +1065,9 @@ add: if (err) return err; - rcu_assign_pointer(rt->rt6_next, iter); - atomic_inc(&rt->rt6i_ref); - rcu_assign_pointer(rt->rt6i_node, fn); + rcu_assign_pointer(rt->fib6_next, iter); + atomic_inc(&rt->fib6_ref); + rcu_assign_pointer(rt->fib6_node, fn); rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, nlflags); @@ -1036,19 +1088,15 @@ add: return -ENOENT; } - err = fib6_commit_metrics(&rt->dst, mxc); - if (err) - return err; - err = call_fib6_entry_notifiers(info->nl_net, FIB_EVENT_ENTRY_REPLACE, rt, extack); if (err) return err; - atomic_inc(&rt->rt6i_ref); - rcu_assign_pointer(rt->rt6i_node, fn); - rt->rt6_next = iter->rt6_next; + atomic_inc(&rt->fib6_ref); + rcu_assign_pointer(rt->fib6_node, fn); + rt->fib6_next = iter->fib6_next; rcu_assign_pointer(*ins, rt); if (!info->skip_notify) inet6_rt_notify(RTM_NEWROUTE, rt, info, NLM_F_REPLACE); @@ -1056,35 +1104,35 @@ add: info->nl_net->ipv6.rt6_stats->fib_route_nodes++; fn->fn_flags |= RTN_RTINFO; } - nsiblings = iter->rt6i_nsiblings; - iter->rt6i_node = NULL; + nsiblings = iter->fib6_nsiblings; + iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; - rt6_release(iter); + fib6_info_release(iter); if (nsiblings) { /* Replacing an ECMP route, remove all siblings */ - ins = &rt->rt6_next; + ins = &rt->fib6_next; iter = rcu_dereference_protected(*ins, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { - if (iter->rt6i_metric > rt->rt6i_metric) + if (iter->fib6_metric > rt->fib6_metric) break; if (rt6_qualify_for_ecmp(iter)) { - *ins = iter->rt6_next; - iter->rt6i_node = NULL; + *ins = iter->fib6_next; + iter->fib6_node = NULL; fib6_purge_rt(iter, fn, info->nl_net); if (rcu_access_pointer(fn->rr_ptr) == iter) fn->rr_ptr = NULL; - rt6_release(iter); + fib6_info_release(iter); nsiblings--; info->nl_net->ipv6.rt6_stats->fib_rt_entries--; } else { - ins = &iter->rt6_next; + ins = &iter->fib6_next; } iter = rcu_dereference_protected(*ins, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + lockdep_is_held(&rt->fib6_table->tb6_lock)); } WARN_ON(nsiblings != 0); } @@ -1093,10 +1141,10 @@ add: return 0; } -static void fib6_start_gc(struct net *net, struct rt6_info *rt) +static void fib6_start_gc(struct net *net, struct fib6_info *rt) { if (!timer_pending(&net->ipv6.ip6_fib_timer) && - (rt->rt6i_flags & (RTF_EXPIRES | RTF_CACHE))) + (rt->fib6_flags & RTF_EXPIRES)) mod_timer(&net->ipv6.ip6_fib_timer, jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } @@ -1108,22 +1156,22 @@ void fib6_force_start_gc(struct net *net) jiffies + net->ipv6.sysctl.ip6_rt_gc_interval); } -static void __fib6_update_sernum_upto_root(struct rt6_info *rt, +static void __fib6_update_sernum_upto_root(struct fib6_info *rt, int sernum) { - struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&rt->fib6_table->tb6_lock)); /* paired with smp_rmb() in rt6_get_cookie_safe() */ smp_wmb(); while (fn) { fn->fn_sernum = sernum; fn = rcu_dereference_protected(fn->parent, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + lockdep_is_held(&rt->fib6_table->tb6_lock)); } } -void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt) +void fib6_update_sernum_upto_root(struct net *net, struct fib6_info *rt) { __fib6_update_sernum_upto_root(rt, fib6_new_sernum(net)); } @@ -1135,22 +1183,16 @@ void fib6_update_sernum_upto_root(struct net *net, struct rt6_info *rt) * Need to own table->tb6_lock */ -int fib6_add(struct fib6_node *root, struct rt6_info *rt, - struct nl_info *info, struct mx6_config *mxc, - struct netlink_ext_ack *extack) +int fib6_add(struct fib6_node *root, struct fib6_info *rt, + struct nl_info *info, struct netlink_ext_ack *extack) { - struct fib6_table *table = rt->rt6i_table; + struct fib6_table *table = rt->fib6_table; struct fib6_node *fn, *pn = NULL; int err = -ENOMEM; int allow_create = 1; int replace_required = 0; int sernum = fib6_new_sernum(info->nl_net); - if (WARN_ON_ONCE(!atomic_read(&rt->dst.__refcnt))) - return -EINVAL; - if (WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE)) - return -EINVAL; - if (info->nlh) { if (!(info->nlh->nlmsg_flags & NLM_F_CREATE)) allow_create = 0; @@ -1161,8 +1203,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, pr_warn("RTM_NEWROUTE with no NLM_F_CREATE or NLM_F_REPLACE\n"); fn = fib6_add_1(info->nl_net, table, root, - &rt->rt6i_dst.addr, rt->rt6i_dst.plen, - offsetof(struct rt6_info, rt6i_dst), allow_create, + &rt->fib6_dst.addr, rt->fib6_dst.plen, + offsetof(struct fib6_info, fib6_dst), allow_create, replace_required, extack); if (IS_ERR(fn)) { err = PTR_ERR(fn); @@ -1173,7 +1215,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, pn = fn; #ifdef CONFIG_IPV6_SUBTREES - if (rt->rt6i_src.plen) { + if (rt->fib6_src.plen) { struct fib6_node *sn; if (!rcu_access_pointer(fn->subtree)) { @@ -1194,16 +1236,16 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (!sfn) goto failure; - atomic_inc(&info->nl_net->ipv6.ip6_null_entry->rt6i_ref); + atomic_inc(&info->nl_net->ipv6.fib6_null_entry->fib6_ref); rcu_assign_pointer(sfn->leaf, - info->nl_net->ipv6.ip6_null_entry); + info->nl_net->ipv6.fib6_null_entry); sfn->fn_flags = RTN_ROOT; /* Now add the first leaf node to new subtree */ sn = fib6_add_1(info->nl_net, table, sfn, - &rt->rt6i_src.addr, rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src), + &rt->fib6_src.addr, rt->fib6_src.plen, + offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { @@ -1221,8 +1263,8 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, rcu_assign_pointer(fn->subtree, sfn); } else { sn = fib6_add_1(info->nl_net, table, FIB6_SUBTREE(fn), - &rt->rt6i_src.addr, rt->rt6i_src.plen, - offsetof(struct rt6_info, rt6i_src), + &rt->fib6_src.addr, rt->fib6_src.plen, + offsetof(struct fib6_info, fib6_src), allow_create, replace_required, extack); if (IS_ERR(sn)) { @@ -1235,9 +1277,9 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, if (fn->fn_flags & RTN_TL_ROOT) { /* put back null_entry for root node */ rcu_assign_pointer(fn->leaf, - info->nl_net->ipv6.ip6_null_entry); + info->nl_net->ipv6.fib6_null_entry); } else { - atomic_inc(&rt->rt6i_ref); + atomic_inc(&rt->fib6_ref); rcu_assign_pointer(fn->leaf, rt); } } @@ -1245,7 +1287,7 @@ int fib6_add(struct fib6_node *root, struct rt6_info *rt, } #endif - err = fib6_add_rt2node(fn, rt, info, mxc, extack); + err = fib6_add_rt2node(fn, rt, info, extack); if (!err) { __fib6_update_sernum_upto_root(rt, sernum); fib6_start_gc(info->nl_net, rt); @@ -1259,13 +1301,13 @@ out: * super-tree leaf node we have to find a new one for it. */ if (pn != fn) { - struct rt6_info *pn_leaf = + struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); if (pn_leaf == rt) { pn_leaf = NULL; RCU_INIT_POINTER(pn->leaf, NULL); - atomic_dec(&rt->rt6i_ref); + fib6_info_release(rt); } if (!pn_leaf && !(pn->fn_flags & RTN_RTINFO)) { pn_leaf = fib6_find_prefix(info->nl_net, table, @@ -1274,10 +1316,10 @@ out: if (!pn_leaf) { WARN_ON(!pn_leaf); pn_leaf = - info->nl_net->ipv6.ip6_null_entry; + info->nl_net->ipv6.fib6_null_entry; } #endif - atomic_inc(&pn_leaf->rt6i_ref); + fib6_info_hold(pn_leaf); rcu_assign_pointer(pn->leaf, pn_leaf); } } @@ -1299,10 +1341,6 @@ failure: (fn->fn_flags & RTN_TL_ROOT && !rcu_access_pointer(fn->leaf)))) fib6_repair_tree(info->nl_net, table, fn); - /* Always release dst as dst->__refcnt is guaranteed - * to be taken before entering this function - */ - dst_release_immediate(&rt->dst); return err; } @@ -1312,7 +1350,7 @@ failure: */ struct lookup_args { - int offset; /* key offset on rt6_info */ + int offset; /* key offset on fib6_info */ const struct in6_addr *addr; /* search key */ }; @@ -1350,7 +1388,7 @@ static struct fib6_node *fib6_lookup_1(struct fib6_node *root, struct fib6_node *subtree = FIB6_SUBTREE(fn); if (subtree || fn->fn_flags & RTN_RTINFO) { - struct rt6_info *leaf = rcu_dereference(fn->leaf); + struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; if (!leaf) @@ -1390,12 +1428,12 @@ struct fib6_node *fib6_lookup(struct fib6_node *root, const struct in6_addr *dad struct fib6_node *fn; struct lookup_args args[] = { { - .offset = offsetof(struct rt6_info, rt6i_dst), + .offset = offsetof(struct fib6_info, fib6_dst), .addr = daddr, }, #ifdef CONFIG_IPV6_SUBTREES { - .offset = offsetof(struct rt6_info, rt6i_src), + .offset = offsetof(struct fib6_info, fib6_src), .addr = saddr, }, #endif @@ -1431,7 +1469,7 @@ static struct fib6_node *fib6_locate_1(struct fib6_node *root, struct fib6_node *fn, *prev = NULL; for (fn = root; fn ; ) { - struct rt6_info *leaf = rcu_dereference(fn->leaf); + struct fib6_info *leaf = rcu_dereference(fn->leaf); struct rt6key *key; /* This node is being deleted */ @@ -1480,7 +1518,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root, struct fib6_node *fn; fn = fib6_locate_1(root, daddr, dst_len, - offsetof(struct rt6_info, rt6i_dst), + offsetof(struct fib6_info, fib6_dst), exact_match); #ifdef CONFIG_IPV6_SUBTREES @@ -1491,7 +1529,7 @@ struct fib6_node *fib6_locate(struct fib6_node *root, if (subtree) { fn = fib6_locate_1(subtree, saddr, src_len, - offsetof(struct rt6_info, rt6i_src), + offsetof(struct fib6_info, fib6_src), exact_match); } } @@ -1510,14 +1548,14 @@ struct fib6_node *fib6_locate(struct fib6_node *root, * */ -static struct rt6_info *fib6_find_prefix(struct net *net, +static struct fib6_info *fib6_find_prefix(struct net *net, struct fib6_table *table, struct fib6_node *fn) { struct fib6_node *child_left, *child_right; if (fn->fn_flags & RTN_ROOT) - return net->ipv6.ip6_null_entry; + return net->ipv6.fib6_null_entry; while (fn) { child_left = rcu_dereference_protected(fn->left, @@ -1554,7 +1592,7 @@ static struct fib6_node *fib6_repair_tree(struct net *net, /* Set fn->leaf to null_entry for root node. */ if (fn->fn_flags & RTN_TL_ROOT) { - rcu_assign_pointer(fn->leaf, net->ipv6.ip6_null_entry); + rcu_assign_pointer(fn->leaf, net->ipv6.fib6_null_entry); return fn; } @@ -1569,11 +1607,11 @@ static struct fib6_node *fib6_repair_tree(struct net *net, lockdep_is_held(&table->tb6_lock)); struct fib6_node *pn_l = rcu_dereference_protected(pn->left, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *fn_leaf = rcu_dereference_protected(fn->leaf, + struct fib6_info *fn_leaf = rcu_dereference_protected(fn->leaf, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *pn_leaf = rcu_dereference_protected(pn->leaf, + struct fib6_info *pn_leaf = rcu_dereference_protected(pn->leaf, lockdep_is_held(&table->tb6_lock)); - struct rt6_info *new_fn_leaf; + struct fib6_info *new_fn_leaf; RT6_TRACE("fixing tree: plen=%d iter=%d\n", fn->fn_bit, iter); iter++; @@ -1599,10 +1637,10 @@ static struct fib6_node *fib6_repair_tree(struct net *net, #if RT6_DEBUG >= 2 if (!new_fn_leaf) { WARN_ON(!new_fn_leaf); - new_fn_leaf = net->ipv6.ip6_null_entry; + new_fn_leaf = net->ipv6.fib6_null_entry; } #endif - atomic_inc(&new_fn_leaf->rt6i_ref); + fib6_info_hold(new_fn_leaf); rcu_assign_pointer(fn->leaf, new_fn_leaf); return pn; } @@ -1658,26 +1696,24 @@ static struct fib6_node *fib6_repair_tree(struct net *net, return pn; RCU_INIT_POINTER(pn->leaf, NULL); - rt6_release(pn_leaf); + fib6_info_release(pn_leaf); fn = pn; } } static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, - struct rt6_info __rcu **rtp, struct nl_info *info) + struct fib6_info __rcu **rtp, struct nl_info *info) { struct fib6_walker *w; - struct rt6_info *rt = rcu_dereference_protected(*rtp, + struct fib6_info *rt = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); struct net *net = info->nl_net; RT6_TRACE("fib6_del_route\n"); - WARN_ON_ONCE(rt->rt6i_flags & RTF_CACHE); - /* Unlink it */ - *rtp = rt->rt6_next; - rt->rt6i_node = NULL; + *rtp = rt->fib6_next; + rt->fib6_node = NULL; net->ipv6.rt6_stats->fib_rt_entries--; net->ipv6.rt6_stats->fib_discarded_routes++; @@ -1689,14 +1725,14 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, fn->rr_ptr = NULL; /* Remove this entry from other siblings */ - if (rt->rt6i_nsiblings) { - struct rt6_info *sibling, *next_sibling; + if (rt->fib6_nsiblings) { + struct fib6_info *sibling, *next_sibling; list_for_each_entry_safe(sibling, next_sibling, - &rt->rt6i_siblings, rt6i_siblings) - sibling->rt6i_nsiblings--; - rt->rt6i_nsiblings = 0; - list_del_init(&rt->rt6i_siblings); + &rt->fib6_siblings, fib6_siblings) + sibling->fib6_nsiblings--; + rt->fib6_nsiblings = 0; + list_del_init(&rt->fib6_siblings); rt6_multipath_rebalance(next_sibling); } @@ -1705,7 +1741,7 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, FOR_WALKERS(net, w) { if (w->state == FWS_C && w->leaf == rt) { RT6_TRACE("walker %p adjusted by delroute\n", w); - w->leaf = rcu_dereference_protected(rt->rt6_next, + w->leaf = rcu_dereference_protected(rt->fib6_next, lockdep_is_held(&table->tb6_lock)); if (!w->leaf) w->state = FWS_U; @@ -1730,46 +1766,36 @@ static void fib6_del_route(struct fib6_table *table, struct fib6_node *fn, call_fib6_entry_notifiers(net, FIB_EVENT_ENTRY_DEL, rt, NULL); if (!info->skip_notify) inet6_rt_notify(RTM_DELROUTE, rt, info, 0); - rt6_release(rt); + fib6_info_release(rt); } /* Need to own table->tb6_lock */ -int fib6_del(struct rt6_info *rt, struct nl_info *info) +int fib6_del(struct fib6_info *rt, struct nl_info *info) { - struct fib6_node *fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); - struct fib6_table *table = rt->rt6i_table; + struct fib6_node *fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&rt->fib6_table->tb6_lock)); + struct fib6_table *table = rt->fib6_table; struct net *net = info->nl_net; - struct rt6_info __rcu **rtp; - struct rt6_info __rcu **rtp_next; + struct fib6_info __rcu **rtp; + struct fib6_info __rcu **rtp_next; -#if RT6_DEBUG >= 2 - if (rt->dst.obsolete > 0) { - WARN_ON(fn); - return -ENOENT; - } -#endif - if (!fn || rt == net->ipv6.ip6_null_entry) + if (!fn || rt == net->ipv6.fib6_null_entry) return -ENOENT; WARN_ON(!(fn->fn_flags & RTN_RTINFO)); - /* remove cached dst from exception table */ - if (rt->rt6i_flags & RTF_CACHE) - return rt6_remove_exception_rt(rt); - /* * Walk the leaf entries looking for ourself */ for (rtp = &fn->leaf; *rtp; rtp = rtp_next) { - struct rt6_info *cur = rcu_dereference_protected(*rtp, + struct fib6_info *cur = rcu_dereference_protected(*rtp, lockdep_is_held(&table->tb6_lock)); if (rt == cur) { fib6_del_route(table, fn, rtp, info); return 0; } - rtp_next = &cur->rt6_next; + rtp_next = &cur->fib6_next; } return -ENOENT; } @@ -1907,7 +1933,7 @@ static int fib6_walk(struct net *net, struct fib6_walker *w) static int fib6_clean_node(struct fib6_walker *w) { int res; - struct rt6_info *rt; + struct fib6_info *rt; struct fib6_cleaner *c = container_of(w, struct fib6_cleaner, w); struct nl_info info = { .nl_net = c->net, @@ -1932,17 +1958,17 @@ static int fib6_clean_node(struct fib6_walker *w) #if RT6_DEBUG >= 2 pr_debug("%s: del failed: rt=%p@%p err=%d\n", __func__, rt, - rcu_access_pointer(rt->rt6i_node), + rcu_access_pointer(rt->fib6_node), res); #endif continue; } return 0; } else if (res == -2) { - if (WARN_ON(!rt->rt6i_nsiblings)) + if (WARN_ON(!rt->fib6_nsiblings)) continue; - rt = list_last_entry(&rt->rt6i_siblings, - struct rt6_info, rt6i_siblings); + rt = list_last_entry(&rt->fib6_siblings, + struct fib6_info, fib6_siblings); continue; } WARN_ON(res != 0); @@ -1961,7 +1987,7 @@ static int fib6_clean_node(struct fib6_walker *w) */ static void fib6_clean_tree(struct net *net, struct fib6_node *root, - int (*func)(struct rt6_info *, void *arg), + int (*func)(struct fib6_info *, void *arg), int sernum, void *arg) { struct fib6_cleaner c; @@ -1979,7 +2005,7 @@ static void fib6_clean_tree(struct net *net, struct fib6_node *root, } static void __fib6_clean_all(struct net *net, - int (*func)(struct rt6_info *, void *), + int (*func)(struct fib6_info *, void *), int sernum, void *arg) { struct fib6_table *table; @@ -1999,7 +2025,7 @@ static void __fib6_clean_all(struct net *net, rcu_read_unlock(); } -void fib6_clean_all(struct net *net, int (*func)(struct rt6_info *, void *), +void fib6_clean_all(struct net *net, int (*func)(struct fib6_info *, void *), void *arg) { __fib6_clean_all(net, func, FIB6_NO_SERNUM_CHANGE, arg); @@ -2016,7 +2042,7 @@ static void fib6_flush_trees(struct net *net) * Garbage collection */ -static int fib6_age(struct rt6_info *rt, void *arg) +static int fib6_age(struct fib6_info *rt, void *arg) { struct fib6_gc_args *gc_args = arg; unsigned long now = jiffies; @@ -2026,8 +2052,8 @@ static int fib6_age(struct rt6_info *rt, void *arg) * Routes are expired even if they are in use. */ - if (rt->rt6i_flags & RTF_EXPIRES && rt->dst.expires) { - if (time_after(now, rt->dst.expires)) { + if (rt->fib6_flags & RTF_EXPIRES && rt->expires) { + if (time_after(now, rt->expires)) { RT6_TRACE("expiring %p\n", rt); return -1; } @@ -2110,7 +2136,7 @@ static int __net_init fib6_net_init(struct net *net) net->ipv6.fib6_main_tbl->tb6_id = RT6_TABLE_MAIN; rcu_assign_pointer(net->ipv6.fib6_main_tbl->tb6_root.leaf, - net->ipv6.ip6_null_entry); + net->ipv6.fib6_null_entry); net->ipv6.fib6_main_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_main_tbl->tb6_peers); @@ -2122,7 +2148,7 @@ static int __net_init fib6_net_init(struct net *net) goto out_fib6_main_tbl; net->ipv6.fib6_local_tbl->tb6_id = RT6_TABLE_LOCAL; rcu_assign_pointer(net->ipv6.fib6_local_tbl->tb6_root.leaf, - net->ipv6.ip6_null_entry); + net->ipv6.fib6_null_entry); net->ipv6.fib6_local_tbl->tb6_root.fn_flags = RTN_ROOT | RTN_TL_ROOT | RTN_RTINFO; inet_peer_base_init(&net->ipv6.fib6_local_tbl->tb6_peers); @@ -2220,25 +2246,26 @@ struct ipv6_route_iter { static int ipv6_route_seq_show(struct seq_file *seq, void *v) { - struct rt6_info *rt = v; + struct fib6_info *rt = v; struct ipv6_route_iter *iter = seq->private; + const struct net_device *dev; - seq_printf(seq, "%pi6 %02x ", &rt->rt6i_dst.addr, rt->rt6i_dst.plen); + seq_printf(seq, "%pi6 %02x ", &rt->fib6_dst.addr, rt->fib6_dst.plen); #ifdef CONFIG_IPV6_SUBTREES - seq_printf(seq, "%pi6 %02x ", &rt->rt6i_src.addr, rt->rt6i_src.plen); + seq_printf(seq, "%pi6 %02x ", &rt->fib6_src.addr, rt->fib6_src.plen); #else seq_puts(seq, "00000000000000000000000000000000 00 "); #endif - if (rt->rt6i_flags & RTF_GATEWAY) - seq_printf(seq, "%pi6", &rt->rt6i_gateway); + if (rt->fib6_flags & RTF_GATEWAY) + seq_printf(seq, "%pi6", &rt->fib6_nh.nh_gw); else seq_puts(seq, "00000000000000000000000000000000"); + dev = rt->fib6_nh.nh_dev; seq_printf(seq, " %08x %08x %08x %08x %8s\n", - rt->rt6i_metric, atomic_read(&rt->dst.__refcnt), - rt->dst.__use, rt->rt6i_flags, - rt->dst.dev ? rt->dst.dev->name : ""); + rt->fib6_metric, atomic_read(&rt->fib6_ref), 0, + rt->fib6_flags, dev ? dev->name : ""); iter->w.leaf = NULL; return 0; } @@ -2252,7 +2279,7 @@ static int ipv6_route_yield(struct fib6_walker *w) do { iter->w.leaf = rcu_dereference_protected( - iter->w.leaf->rt6_next, + iter->w.leaf->fib6_next, lockdep_is_held(&iter->tbl->tb6_lock)); iter->skip--; if (!iter->skip && iter->w.leaf) @@ -2311,14 +2338,14 @@ static void ipv6_route_check_sernum(struct ipv6_route_iter *iter) static void *ipv6_route_seq_next(struct seq_file *seq, void *v, loff_t *pos) { int r; - struct rt6_info *n; + struct fib6_info *n; struct net *net = seq_file_net(seq); struct ipv6_route_iter *iter = seq->private; if (!v) goto iter_table; - n = rcu_dereference_bh(((struct rt6_info *)v)->rt6_next); + n = rcu_dereference_bh(((struct fib6_info *)v)->fib6_next); if (n) { ++*pos; return n; diff --git a/net/ipv6/ip6_gre.c b/net/ipv6/ip6_gre.c index 69727bc168cb..bede77f24784 100644 --- a/net/ipv6/ip6_gre.c +++ b/net/ipv6/ip6_gre.c @@ -807,7 +807,7 @@ static inline int ip6gre_xmit_ipv6(struct sk_buff *skb, struct net_device *dev) } /** - * ip6_tnl_addr_conflict - compare packet addresses to tunnel's own + * ip6gre_tnl_addr_conflict - compare packet addresses to tunnel's own * @t: the outgoing tunnel device * @hdr: IPv6 header from the incoming packet * @@ -896,6 +896,8 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, struct flowi6 fl6; int err = -EINVAL; __u32 mtu; + int nhoff; + int thoff; if (!ip6_tnl_xmit_ctl(t, &t->parms.laddr, &t->parms.raddr)) goto tx_err; @@ -908,6 +910,16 @@ static netdev_tx_t ip6erspan_tunnel_xmit(struct sk_buff *skb, truncate = true; } + nhoff = skb_network_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IP) && + (ntohs(ip_hdr(skb)->tot_len) > skb->len - nhoff)) + truncate = true; + + thoff = skb_transport_header(skb) - skb_mac_header(skb); + if (skb->protocol == htons(ETH_P_IPV6) && + (ntohs(ipv6_hdr(skb)->payload_len) > skb->len - thoff)) + truncate = true; + if (skb_cow_head(skb, dev->needed_headroom)) goto tx_err; @@ -1308,6 +1320,7 @@ static void ip6gre_dev_free(struct net_device *dev) { struct ip6_tnl *t = netdev_priv(dev); + gro_cells_destroy(&t->gro_cells); dst_cache_destroy(&t->dst_cache); free_percpu(dev->tstats); } @@ -1375,11 +1388,12 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) return -ENOMEM; ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (ret) { - free_percpu(dev->tstats); - dev->tstats = NULL; - return ret; - } + if (ret) + goto cleanup_alloc_pcpu_stats; + + ret = gro_cells_init(&tunnel->gro_cells, dev); + if (ret) + goto cleanup_dst_cache_init; tunnel->tun_hlen = gre_calc_hlen(tunnel->parms.o_flags); tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen; @@ -1399,6 +1413,13 @@ static int ip6gre_tunnel_init_common(struct net_device *dev) ip6gre_tnl_init_features(dev); return 0; + +cleanup_dst_cache_init: + dst_cache_destroy(&tunnel->dst_cache); +cleanup_alloc_pcpu_stats: + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; } static int ip6gre_tunnel_init(struct net_device *dev) @@ -1745,11 +1766,12 @@ static int ip6erspan_tap_init(struct net_device *dev) return -ENOMEM; ret = dst_cache_init(&tunnel->dst_cache, GFP_KERNEL); - if (ret) { - free_percpu(dev->tstats); - dev->tstats = NULL; - return ret; - } + if (ret) + goto cleanup_alloc_pcpu_stats; + + ret = gro_cells_init(&tunnel->gro_cells, dev); + if (ret) + goto cleanup_dst_cache_init; tunnel->tun_hlen = 8; tunnel->hlen = tunnel->tun_hlen + tunnel->encap_hlen + @@ -1767,6 +1789,13 @@ static int ip6erspan_tap_init(struct net_device *dev) ip6gre_tnl_link_config(tunnel, 1); return 0; + +cleanup_dst_cache_init: + dst_cache_destroy(&tunnel->dst_cache); +cleanup_alloc_pcpu_stats: + free_percpu(dev->tstats); + dev->tstats = NULL; + return ret; } static const struct net_device_ops ip6erspan_netdev_ops = { diff --git a/net/ipv6/ip6_input.c b/net/ipv6/ip6_input.c index 9ee208a348f5..f08d34491ece 100644 --- a/net/ipv6/ip6_input.c +++ b/net/ipv6/ip6_input.c @@ -336,7 +336,7 @@ int ip6_mc_input(struct sk_buff *skb) bool deliver; __IP6_UPD_PO_STATS(dev_net(skb_dst(skb)->dev), - ip6_dst_idev(skb_dst(skb)), IPSTATS_MIB_INMCAST, + __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INMCAST, skb->len); hdr = ipv6_hdr(skb); diff --git a/net/ipv6/ip6_offload.c b/net/ipv6/ip6_offload.c index 4a87f9428ca5..5b3f2f89ef41 100644 --- a/net/ipv6/ip6_offload.c +++ b/net/ipv6/ip6_offload.c @@ -88,9 +88,11 @@ static struct sk_buff *ipv6_gso_segment(struct sk_buff *skb, if (skb->encapsulation && skb_shinfo(skb)->gso_type & (SKB_GSO_IPXIP4 | SKB_GSO_IPXIP6)) - udpfrag = proto == IPPROTO_UDP && encap; + udpfrag = proto == IPPROTO_UDP && encap && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); else - udpfrag = proto == IPPROTO_UDP && !skb->encapsulation; + udpfrag = proto == IPPROTO_UDP && !skb->encapsulation && + (skb_shinfo(skb)->gso_type & SKB_GSO_UDP); ops = rcu_dereference(inet6_offloads[proto]); if (likely(ops && ops->callbacks.gso_segment)) { diff --git a/net/ipv6/ip6_output.c b/net/ipv6/ip6_output.c index 2e891d2c30ef..7f4493080df6 100644 --- a/net/ipv6/ip6_output.c +++ b/net/ipv6/ip6_output.c @@ -383,28 +383,6 @@ static inline int ip6_forward_finish(struct net *net, struct sock *sk, return dst_output(net, sk, skb); } -unsigned int ip6_dst_mtu_forward(const struct dst_entry *dst) -{ - unsigned int mtu; - struct inet6_dev *idev; - - if (dst_metric_locked(dst, RTAX_MTU)) { - mtu = dst_metric_raw(dst, RTAX_MTU); - if (mtu) - return mtu; - } - - mtu = IPV6_MIN_MTU; - rcu_read_lock(); - idev = __in6_dev_get(dst->dev); - if (idev) - mtu = idev->cnf.mtu6; - rcu_read_unlock(); - - return mtu; -} -EXPORT_SYMBOL_GPL(ip6_dst_mtu_forward); - static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) { if (skb->len <= mtu) @@ -425,6 +403,7 @@ static bool ip6_pkt_too_big(const struct sk_buff *skb, unsigned int mtu) int ip6_forward(struct sk_buff *skb) { + struct inet6_dev *idev = __in6_dev_get_safely(skb->dev); struct dst_entry *dst = skb_dst(skb); struct ipv6hdr *hdr = ipv6_hdr(skb); struct inet6_skb_parm *opt = IP6CB(skb); @@ -444,8 +423,7 @@ int ip6_forward(struct sk_buff *skb) goto drop; if (!xfrm6_policy_check(NULL, XFRM_POLICY_FWD, skb)) { - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INDISCARDS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } @@ -476,8 +454,7 @@ int ip6_forward(struct sk_buff *skb) /* Force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); kfree_skb(skb); return -ETIMEDOUT; @@ -490,15 +467,13 @@ int ip6_forward(struct sk_buff *skb) if (proxied > 0) return ip6_input(skb); else if (proxied < 0) { - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INDISCARDS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } } if (!xfrm6_route_forward(skb)) { - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INDISCARDS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INDISCARDS); goto drop; } dst = skb_dst(skb); @@ -554,8 +529,7 @@ int ip6_forward(struct sk_buff *skb) /* Again, force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_PKT_TOOBIG, 0, mtu); - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INTOOBIGERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INTOOBIGERRORS); __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_FRAGFAILS); kfree_skb(skb); @@ -579,7 +553,7 @@ int ip6_forward(struct sk_buff *skb) ip6_forward_finish); error: - __IP6_INC_STATS(net, ip6_dst_idev(dst), IPSTATS_MIB_INADDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INADDRERRORS); drop: kfree_skb(skb); return -EINVAL; @@ -966,15 +940,21 @@ static int ip6_dst_lookup_tail(struct net *net, const struct sock *sk, * that's why we try it again later. */ if (ipv6_addr_any(&fl6->saddr) && (!*dst || !(*dst)->error)) { + struct fib6_info *from; struct rt6_info *rt; bool had_dst = *dst != NULL; if (!had_dst) *dst = ip6_route_output(net, sk, fl6); rt = (*dst)->error ? NULL : (struct rt6_info *)*dst; - err = ip6_route_get_saddr(net, rt, &fl6->daddr, + + rcu_read_lock(); + from = rt ? rcu_dereference(rt->from) : NULL; + err = ip6_route_get_saddr(net, from, &fl6->daddr, sk ? inet6_sk(sk)->srcprefs : 0, &fl6->saddr); + rcu_read_unlock(); + if (err) goto out_err_release; @@ -1238,6 +1218,8 @@ static int ip6_setup_cork(struct sock *sk, struct inet_cork_full *cork, if (mtu < IPV6_MIN_MTU) return -EINVAL; cork->base.fragsize = mtu; + cork->base.gso_size = sk->sk_type == SOCK_DGRAM ? ipc6->gso_size : 0; + if (dst_allfrag(xfrm_dst_path(&rt->dst))) cork->base.flags |= IPCORK_ALLFRAG; cork->base.length = 0; @@ -1272,6 +1254,7 @@ static int __ip6_append_data(struct sock *sk, int csummode = CHECKSUM_NONE; unsigned int maxnonfragsize, headersize; unsigned int wmem_alloc_delta = 0; + bool paged; skb = skb_peek_tail(queue); if (!skb) { @@ -1279,7 +1262,8 @@ static int __ip6_append_data(struct sock *sk, dst_exthdrlen = rt->dst.header_len - rt->rt6i_nfheader_len; } - mtu = cork->fragsize; + paged = !!cork->gso_size; + mtu = cork->gso_size ? IP6_MAX_MTU : cork->fragsize; orig_mtu = mtu; hh_len = LL_RESERVED_SPACE(rt->dst.dev); @@ -1327,7 +1311,7 @@ emsgsize: if (transhdrlen && sk->sk_protocol == IPPROTO_UDP && headersize == sizeof(struct ipv6hdr) && length <= mtu - headersize && - !(flags & MSG_MORE) && + (!(flags & MSG_MORE) || cork->gso_size) && rt->dst.dev->features & (NETIF_F_IPV6_CSUM | NETIF_F_HW_CSUM)) csummode = CHECKSUM_PARTIAL; @@ -1370,6 +1354,7 @@ emsgsize: unsigned int fraglen; unsigned int fraggap; unsigned int alloclen; + unsigned int pagedlen = 0; alloc_new_skb: /* There's no room in the current skb */ if (skb) @@ -1392,11 +1377,17 @@ alloc_new_skb: if (datalen > (cork->length <= mtu && !(cork->flags & IPCORK_ALLFRAG) ? mtu : maxfraglen) - fragheaderlen) datalen = maxfraglen - fragheaderlen - rt->dst.trailer_len; + fraglen = datalen + fragheaderlen; + if ((flags & MSG_MORE) && !(rt->dst.dev->features&NETIF_F_SG)) alloclen = mtu; - else - alloclen = datalen + fragheaderlen; + else if (!paged) + alloclen = fraglen; + else { + alloclen = min_t(int, fraglen, MAX_HEADER); + pagedlen = fraglen - alloclen; + } alloclen += dst_exthdrlen; @@ -1418,7 +1409,7 @@ alloc_new_skb: */ alloclen += sizeof(struct frag_hdr); - copy = datalen - transhdrlen - fraggap; + copy = datalen - transhdrlen - fraggap - pagedlen; if (copy < 0) { err = -EINVAL; goto error; @@ -1457,7 +1448,7 @@ alloc_new_skb: /* * Find where to start putting bytes */ - data = skb_put(skb, fraglen); + data = skb_put(skb, fraglen - pagedlen); skb_set_network_header(skb, exthdrlen); data += fragheaderlen; skb->transport_header = (skb->network_header + @@ -1480,7 +1471,7 @@ alloc_new_skb: } offset += copy; - length -= datalen - fraggap; + length -= copy + transhdrlen; transhdrlen = 0; exthdrlen = 0; dst_exthdrlen = 0; @@ -1753,9 +1744,9 @@ struct sk_buff *ip6_make_skb(struct sock *sk, void *from, int length, int transhdrlen, struct ipcm6_cookie *ipc6, struct flowi6 *fl6, struct rt6_info *rt, unsigned int flags, + struct inet_cork_full *cork, const struct sockcm_cookie *sockc) { - struct inet_cork_full cork; struct inet6_cork v6_cork; struct sk_buff_head queue; int exthdrlen = (ipc6->opt ? ipc6->opt->opt_flen : 0); @@ -1766,27 +1757,27 @@ struct sk_buff *ip6_make_skb(struct sock *sk, __skb_queue_head_init(&queue); - cork.base.flags = 0; - cork.base.addr = 0; - cork.base.opt = NULL; - cork.base.dst = NULL; + cork->base.flags = 0; + cork->base.addr = 0; + cork->base.opt = NULL; + cork->base.dst = NULL; v6_cork.opt = NULL; - err = ip6_setup_cork(sk, &cork, &v6_cork, ipc6, rt, fl6); + err = ip6_setup_cork(sk, cork, &v6_cork, ipc6, rt, fl6); if (err) { - ip6_cork_release(&cork, &v6_cork); + ip6_cork_release(cork, &v6_cork); return ERR_PTR(err); } if (ipc6->dontfrag < 0) ipc6->dontfrag = inet6_sk(sk)->dontfrag; - err = __ip6_append_data(sk, fl6, &queue, &cork.base, &v6_cork, + err = __ip6_append_data(sk, fl6, &queue, &cork->base, &v6_cork, ¤t->task_frag, getfrag, from, length + exthdrlen, transhdrlen + exthdrlen, flags, ipc6, sockc); if (err) { - __ip6_flush_pending_frames(sk, &queue, &cork, &v6_cork); + __ip6_flush_pending_frames(sk, &queue, cork, &v6_cork); return ERR_PTR(err); } - return __ip6_make_skb(sk, &queue, &cork, &v6_cork); + return __ip6_make_skb(sk, &queue, cork, &v6_cork); } diff --git a/net/ipv6/ip6_vti.c b/net/ipv6/ip6_vti.c index ca957dd93a29..b7f28deddaea 100644 --- a/net/ipv6/ip6_vti.c +++ b/net/ipv6/ip6_vti.c @@ -743,7 +743,7 @@ vti6_parm_to_user(struct ip6_tnl_parm2 *u, const struct __ip6_tnl_parm *p) } /** - * vti6_tnl_ioctl - configure vti6 tunnels from userspace + * vti6_ioctl - configure vti6 tunnels from userspace * @dev: virtual device associated with tunnel * @ifr: parameters passed from userspace * @cmd: command to be performed diff --git a/net/ipv6/ip6mr.c b/net/ipv6/ip6mr.c index 298fd8b6ed17..20a419ee8000 100644 --- a/net/ipv6/ip6mr.c +++ b/net/ipv6/ip6mr.c @@ -180,7 +180,8 @@ static const struct nla_policy ip6mr_rule_policy[FRA_MAX + 1] = { }; static int ip6mr_rule_configure(struct fib_rule *rule, struct sk_buff *skb, - struct fib_rule_hdr *frh, struct nlattr **tb) + struct fib_rule_hdr *frh, struct nlattr **tb, + struct netlink_ext_ack *extack) { return 0; } diff --git a/net/ipv6/ndisc.c b/net/ipv6/ndisc.c index 9de4dfb126ba..9ac5366064e3 100644 --- a/net/ipv6/ndisc.c +++ b/net/ipv6/ndisc.c @@ -1155,7 +1155,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) struct ra_msg *ra_msg = (struct ra_msg *)skb_transport_header(skb); struct neighbour *neigh = NULL; struct inet6_dev *in6_dev; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; + struct net *net; int lifetime; struct ndisc_options ndopts; int optlen; @@ -1253,9 +1254,9 @@ static void ndisc_router_discovery(struct sk_buff *skb) /* Do not accept RA with source-addr found on local machine unless * accept_ra_from_local is set to true. */ + net = dev_net(in6_dev->dev); if (!in6_dev->cnf.accept_ra_from_local && - ipv6_chk_addr(dev_net(in6_dev->dev), &ipv6_hdr(skb)->saddr, - in6_dev->dev, 0)) { + ipv6_chk_addr(net, &ipv6_hdr(skb)->saddr, in6_dev->dev, 0)) { ND_PRINTK(2, info, "RA from local address detected on dev: %s: default router ignored\n", skb->dev->name); @@ -1272,20 +1273,22 @@ static void ndisc_router_discovery(struct sk_buff *skb) pref = ICMPV6_ROUTER_PREF_MEDIUM; #endif - rt = rt6_get_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev); + rt = rt6_get_dflt_router(net, &ipv6_hdr(skb)->saddr, skb->dev); if (rt) { - neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); + neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw, + rt->fib6_nh.nh_dev, NULL, + &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - ip6_rt_put(rt); + fib6_info_release(rt); return; } } if (rt && lifetime == 0) { - ip6_del_rt(rt); + ip6_del_rt(net, rt); rt = NULL; } @@ -1294,7 +1297,8 @@ static void ndisc_router_discovery(struct sk_buff *skb) if (!rt && lifetime) { ND_PRINTK(3, info, "RA: adding default router\n"); - rt = rt6_add_dflt_router(&ipv6_hdr(skb)->saddr, skb->dev, pref); + rt = rt6_add_dflt_router(net, &ipv6_hdr(skb)->saddr, + skb->dev, pref); if (!rt) { ND_PRINTK(0, err, "RA: %s failed to add default route\n", @@ -1302,28 +1306,29 @@ static void ndisc_router_discovery(struct sk_buff *skb) return; } - neigh = dst_neigh_lookup(&rt->dst, &ipv6_hdr(skb)->saddr); + neigh = ip6_neigh_lookup(&rt->fib6_nh.nh_gw, + rt->fib6_nh.nh_dev, NULL, + &ipv6_hdr(skb)->saddr); if (!neigh) { ND_PRINTK(0, err, "RA: %s got default router without neighbour\n", __func__); - ip6_rt_put(rt); + fib6_info_release(rt); return; } neigh->flags |= NTF_ROUTER; } else if (rt) { - rt->rt6i_flags = (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + rt->fib6_flags = (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); } if (rt) - rt6_set_expires(rt, jiffies + (HZ * lifetime)); + fib6_set_expires(rt, jiffies + (HZ * lifetime)); if (in6_dev->cnf.accept_ra_min_hop_limit < 256 && ra_msg->icmph.icmp6_hop_limit) { if (in6_dev->cnf.accept_ra_min_hop_limit <= ra_msg->icmph.icmp6_hop_limit) { in6_dev->cnf.hop_limit = ra_msg->icmph.icmp6_hop_limit; - if (rt) - dst_metric_set(&rt->dst, RTAX_HOPLIMIT, - ra_msg->icmph.icmp6_hop_limit); + fib6_metric_set(rt, RTAX_HOPLIMIT, + ra_msg->icmph.icmp6_hop_limit); } else { ND_PRINTK(2, warn, "RA: Got route advertisement with lower hop_limit than minimum\n"); } @@ -1475,10 +1480,7 @@ skip_routeinfo: ND_PRINTK(2, warn, "RA: invalid mtu: %d\n", mtu); } else if (in6_dev->cnf.mtu6 != mtu) { in6_dev->cnf.mtu6 = mtu; - - if (rt) - dst_metric_set(&rt->dst, RTAX_MTU, mtu); - + fib6_metric_set(rt, RTAX_MTU, mtu); rt6_mtu_change(skb->dev, mtu); } } @@ -1497,7 +1499,7 @@ skip_routeinfo: ND_PRINTK(2, warn, "RA: invalid RA options\n"); } out: - ip6_rt_put(rt); + fib6_info_release(rt); if (neigh) neigh_release(neigh); } diff --git a/net/ipv6/netfilter/ip6_tables.c b/net/ipv6/netfilter/ip6_tables.c index 65c9e1a58305..7097bbf95843 100644 --- a/net/ipv6/netfilter/ip6_tables.c +++ b/net/ipv6/netfilter/ip6_tables.c @@ -528,7 +528,6 @@ static int check_target(struct ip6t_entry *e, struct net *net, const char *name) .family = NFPROTO_IPV6, }; - t = ip6t_get_target(e); return xt_check_target(&par, t->u.target_size - sizeof(*t), e->ipv6.proto, e->ipv6.invflags & IP6T_INV_PROTO); diff --git a/net/ipv6/netfilter/ip6t_MASQUERADE.c b/net/ipv6/netfilter/ip6t_MASQUERADE.c index 92c0047e7e33..491f808e356a 100644 --- a/net/ipv6/netfilter/ip6t_MASQUERADE.c +++ b/net/ipv6/netfilter/ip6t_MASQUERADE.c @@ -29,7 +29,7 @@ masquerade_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int masquerade_tg6_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range2 *range = par->targinfo; if (range->flags & NF_NAT_RANGE_MAP_IPS) return -EINVAL; diff --git a/net/ipv6/netfilter/ip6t_srh.c b/net/ipv6/netfilter/ip6t_srh.c index 33719d5560c8..1059894a6f4c 100644 --- a/net/ipv6/netfilter/ip6t_srh.c +++ b/net/ipv6/netfilter/ip6t_srh.c @@ -117,6 +117,130 @@ static bool srh_mt6(const struct sk_buff *skb, struct xt_action_param *par) return true; } +static bool srh1_mt6(const struct sk_buff *skb, struct xt_action_param *par) +{ + int hdrlen, psidoff, nsidoff, lsidoff, srhoff = 0; + const struct ip6t_srh1 *srhinfo = par->matchinfo; + struct in6_addr *psid, *nsid, *lsid; + struct in6_addr _psid, _nsid, _lsid; + struct ipv6_sr_hdr *srh; + struct ipv6_sr_hdr _srh; + + if (ipv6_find_hdr(skb, &srhoff, IPPROTO_ROUTING, NULL, NULL) < 0) + return false; + srh = skb_header_pointer(skb, srhoff, sizeof(_srh), &_srh); + if (!srh) + return false; + + hdrlen = ipv6_optlen(srh); + if (skb->len - srhoff < hdrlen) + return false; + + if (srh->type != IPV6_SRCRT_TYPE_4) + return false; + + if (srh->segments_left > srh->first_segment) + return false; + + /* Next Header matching */ + if (srhinfo->mt_flags & IP6T_SRH_NEXTHDR) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NEXTHDR, + !(srh->nexthdr == srhinfo->next_hdr))) + return false; + + /* Header Extension Length matching */ + if (srhinfo->mt_flags & IP6T_SRH_LEN_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_EQ, + !(srh->hdrlen == srhinfo->hdr_len))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LEN_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_GT, + !(srh->hdrlen > srhinfo->hdr_len))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LEN_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LEN_LT, + !(srh->hdrlen < srhinfo->hdr_len))) + return false; + + /* Segments Left matching */ + if (srhinfo->mt_flags & IP6T_SRH_SEGS_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_EQ, + !(srh->segments_left == srhinfo->segs_left))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_SEGS_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_GT, + !(srh->segments_left > srhinfo->segs_left))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_SEGS_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_SEGS_LT, + !(srh->segments_left < srhinfo->segs_left))) + return false; + + /** + * Last Entry matching + * Last_Entry field was introduced in revision 6 of the SRH draft. + * It was called First_Segment in the previous revision + */ + if (srhinfo->mt_flags & IP6T_SRH_LAST_EQ) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_EQ, + !(srh->first_segment == srhinfo->last_entry))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LAST_GT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_GT, + !(srh->first_segment > srhinfo->last_entry))) + return false; + if (srhinfo->mt_flags & IP6T_SRH_LAST_LT) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LAST_LT, + !(srh->first_segment < srhinfo->last_entry))) + return false; + + /** + * Tag matchig + * Tag field was introduced in revision 6 of the SRH draft + */ + if (srhinfo->mt_flags & IP6T_SRH_TAG) + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_TAG, + !(srh->tag == srhinfo->tag))) + return false; + + /* Previous SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_PSID) { + if (srh->segments_left == srh->first_segment) + return false; + psidoff = srhoff + sizeof(struct ipv6_sr_hdr) + + ((srh->segments_left + 1) * sizeof(struct in6_addr)); + psid = skb_header_pointer(skb, psidoff, sizeof(_psid), &_psid); + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_PSID, + ipv6_masked_addr_cmp(psid, &srhinfo->psid_msk, + &srhinfo->psid_addr))) + return false; + } + + /* Next SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_NSID) { + if (srh->segments_left == 0) + return false; + nsidoff = srhoff + sizeof(struct ipv6_sr_hdr) + + ((srh->segments_left - 1) * sizeof(struct in6_addr)); + nsid = skb_header_pointer(skb, nsidoff, sizeof(_nsid), &_nsid); + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_NSID, + ipv6_masked_addr_cmp(nsid, &srhinfo->nsid_msk, + &srhinfo->nsid_addr))) + return false; + } + + /* Last SID matching */ + if (srhinfo->mt_flags & IP6T_SRH_LSID) { + lsidoff = srhoff + sizeof(struct ipv6_sr_hdr); + lsid = skb_header_pointer(skb, lsidoff, sizeof(_lsid), &_lsid); + if (NF_SRH_INVF(srhinfo, IP6T_SRH_INV_LSID, + ipv6_masked_addr_cmp(lsid, &srhinfo->lsid_msk, + &srhinfo->lsid_addr))) + return false; + } + return true; +} + static int srh_mt6_check(const struct xt_mtchk_param *par) { const struct ip6t_srh *srhinfo = par->matchinfo; @@ -136,23 +260,54 @@ static int srh_mt6_check(const struct xt_mtchk_param *par) return 0; } -static struct xt_match srh_mt6_reg __read_mostly = { - .name = "srh", - .family = NFPROTO_IPV6, - .match = srh_mt6, - .matchsize = sizeof(struct ip6t_srh), - .checkentry = srh_mt6_check, - .me = THIS_MODULE, +static int srh1_mt6_check(const struct xt_mtchk_param *par) +{ + const struct ip6t_srh1 *srhinfo = par->matchinfo; + + if (srhinfo->mt_flags & ~IP6T_SRH_MASK) { + pr_info_ratelimited("unknown srh match flags %X\n", + srhinfo->mt_flags); + return -EINVAL; + } + + if (srhinfo->mt_invflags & ~IP6T_SRH_INV_MASK) { + pr_info_ratelimited("unknown srh invflags %X\n", + srhinfo->mt_invflags); + return -EINVAL; + } + + return 0; +} + +static struct xt_match srh_mt6_reg[] __read_mostly = { + { + .name = "srh", + .revision = 0, + .family = NFPROTO_IPV6, + .match = srh_mt6, + .matchsize = sizeof(struct ip6t_srh), + .checkentry = srh_mt6_check, + .me = THIS_MODULE, + }, + { + .name = "srh", + .revision = 1, + .family = NFPROTO_IPV6, + .match = srh1_mt6, + .matchsize = sizeof(struct ip6t_srh1), + .checkentry = srh1_mt6_check, + .me = THIS_MODULE, + } }; static int __init srh_mt6_init(void) { - return xt_register_match(&srh_mt6_reg); + return xt_register_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg)); } static void __exit srh_mt6_exit(void) { - xt_unregister_match(&srh_mt6_reg); + xt_unregister_matches(srh_mt6_reg, ARRAY_SIZE(srh_mt6_reg)); } module_init(srh_mt6_init); diff --git a/net/ipv6/netfilter/ip6table_nat.c b/net/ipv6/netfilter/ip6table_nat.c index 47306e45a80a..2bf554e18af8 100644 --- a/net/ipv6/netfilter/ip6table_nat.c +++ b/net/ipv6/netfilter/ip6table_nat.c @@ -35,8 +35,7 @@ static const struct xt_table nf_nat_ipv6_table = { static unsigned int ip6table_nat_do_chain(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) + const struct nf_hook_state *state) { return ip6t_do_table(skb, state, state->net->ipv6.ip6table_nat); } diff --git a/net/ipv6/netfilter/nf_flow_table_ipv6.c b/net/ipv6/netfilter/nf_flow_table_ipv6.c index 207cb35569b1..c511d206bf9b 100644 --- a/net/ipv6/netfilter/nf_flow_table_ipv6.c +++ b/net/ipv6/netfilter/nf_flow_table_ipv6.c @@ -3,256 +3,12 @@ #include <linux/module.h> #include <linux/netfilter.h> #include <linux/rhashtable.h> -#include <linux/ipv6.h> -#include <linux/netdevice.h> -#include <net/ipv6.h> -#include <net/ip6_route.h> -#include <net/neighbour.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_tables.h> -/* For layer 4 checksum field offset. */ -#include <linux/tcp.h> -#include <linux/udp.h> - -static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) -{ - struct tcphdr *tcph; - - if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || - skb_try_make_writable(skb, thoff + sizeof(*tcph))) - return -1; - - tcph = (void *)(skb_network_header(skb) + thoff); - inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32, - new_addr->s6_addr32, true); - - return 0; -} - -static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, - struct in6_addr *addr, - struct in6_addr *new_addr) -{ - struct udphdr *udph; - - if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || - skb_try_make_writable(skb, thoff + sizeof(*udph))) - return -1; - - udph = (void *)(skb_network_header(skb) + thoff); - if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { - inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32, - new_addr->s6_addr32, true); - if (!udph->check) - udph->check = CSUM_MANGLED_0; - } - - return 0; -} - -static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, struct in6_addr *addr, - struct in6_addr *new_addr) -{ - switch (ip6h->nexthdr) { - case IPPROTO_TCP: - if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - case IPPROTO_UDP: - if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0) - return NF_DROP; - break; - } - - return 0; -} - -static int nf_flow_snat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - struct in6_addr addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = ip6h->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6; - ip6h->saddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = ip6h->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6; - ip6h->daddr = new_addr; - break; - default: - return -1; - } - - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); -} - -static int nf_flow_dnat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, struct ipv6hdr *ip6h, - unsigned int thoff, - enum flow_offload_tuple_dir dir) -{ - struct in6_addr addr, new_addr; - - switch (dir) { - case FLOW_OFFLOAD_DIR_ORIGINAL: - addr = ip6h->daddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6; - ip6h->daddr = new_addr; - break; - case FLOW_OFFLOAD_DIR_REPLY: - addr = ip6h->saddr; - new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6; - ip6h->saddr = new_addr; - break; - default: - return -1; - } - - return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); -} - -static int nf_flow_nat_ipv6(const struct flow_offload *flow, - struct sk_buff *skb, - enum flow_offload_tuple_dir dir) -{ - struct ipv6hdr *ip6h = ipv6_hdr(skb); - unsigned int thoff = sizeof(*ip6h); - - if (flow->flags & FLOW_OFFLOAD_SNAT && - (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) - return -1; - if (flow->flags & FLOW_OFFLOAD_DNAT && - (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || - nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) - return -1; - - return 0; -} - -static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, - struct flow_offload_tuple *tuple) -{ - struct flow_ports *ports; - struct ipv6hdr *ip6h; - unsigned int thoff; - - if (!pskb_may_pull(skb, sizeof(*ip6h))) - return -1; - - ip6h = ipv6_hdr(skb); - - if (ip6h->nexthdr != IPPROTO_TCP && - ip6h->nexthdr != IPPROTO_UDP) - return -1; - - thoff = sizeof(*ip6h); - if (!pskb_may_pull(skb, thoff + sizeof(*ports))) - return -1; - - ports = (struct flow_ports *)(skb_network_header(skb) + thoff); - - tuple->src_v6 = ip6h->saddr; - tuple->dst_v6 = ip6h->daddr; - tuple->src_port = ports->source; - tuple->dst_port = ports->dest; - tuple->l3proto = AF_INET6; - tuple->l4proto = ip6h->nexthdr; - tuple->iifidx = dev->ifindex; - - return 0; -} - -/* Based on ip_exceeds_mtu(). */ -static bool __nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) -{ - if (skb->len <= mtu) - return false; - - if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) - return false; - - return true; -} - -static bool nf_flow_exceeds_mtu(struct sk_buff *skb, const struct rt6_info *rt) -{ - u32 mtu; - - mtu = ip6_dst_mtu_forward(&rt->dst); - if (__nf_flow_exceeds_mtu(skb, mtu)) - return true; - - return false; -} - -unsigned int -nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state) -{ - struct flow_offload_tuple_rhash *tuplehash; - struct nf_flowtable *flow_table = priv; - struct flow_offload_tuple tuple = {}; - enum flow_offload_tuple_dir dir; - struct flow_offload *flow; - struct net_device *outdev; - struct in6_addr *nexthop; - struct ipv6hdr *ip6h; - struct rt6_info *rt; - - if (skb->protocol != htons(ETH_P_IPV6)) - return NF_ACCEPT; - - if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0) - return NF_ACCEPT; - - tuplehash = flow_offload_lookup(flow_table, &tuple); - if (tuplehash == NULL) - return NF_ACCEPT; - - outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); - if (!outdev) - return NF_ACCEPT; - - dir = tuplehash->tuple.dir; - flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); - - rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache; - if (unlikely(nf_flow_exceeds_mtu(skb, rt))) - return NF_ACCEPT; - - if (skb_try_make_writable(skb, sizeof(*ip6h))) - return NF_DROP; - - if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && - nf_flow_nat_ipv6(flow, skb, dir) < 0) - return NF_DROP; - - flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; - ip6h = ipv6_hdr(skb); - ip6h->hop_limit--; - - skb->dev = outdev; - nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); - neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); - - return NF_STOLEN; -} -EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook); static struct nf_flowtable_type flowtable_ipv6 = { .family = NFPROTO_IPV6, - .params = &nf_flow_offload_rhash_params, - .gc = nf_flow_offload_work_gc, + .init = nf_flow_table_init, .free = nf_flow_table_free, .hook = nf_flow_offload_ipv6_hook, .owner = THIS_MODULE, diff --git a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c index 6b7f075f811f..f1582b6f9588 100644 --- a/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_l3proto_ipv6.c @@ -62,7 +62,7 @@ static void nf_nat_ipv6_decode_session(struct sk_buff *skb, #endif static bool nf_nat_ipv6_in_range(const struct nf_conntrack_tuple *t, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { return ipv6_addr_cmp(&t->src.u3.in6, &range->min_addr.in6) >= 0 && ipv6_addr_cmp(&t->src.u3.in6, &range->max_addr.in6) <= 0; @@ -151,7 +151,7 @@ static void nf_nat_ipv6_csum_recalc(struct sk_buff *skb, #if IS_ENABLED(CONFIG_NF_CT_NETLINK) static int nf_nat_ipv6_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range) + struct nf_nat_range2 *range) { if (tb[CTA_NAT_V6_MINIP]) { nla_memcpy(&range->min_addr.ip6, tb[CTA_NAT_V6_MINIP], @@ -257,8 +257,7 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { struct nf_conn *ct; enum ip_conntrack_info ctinfo; @@ -303,7 +302,7 @@ nf_nat_ipv6_fn(void *priv, struct sk_buff *skb, if (!nf_nat_initialized(ct, maniptype)) { unsigned int ret; - ret = do_chain(priv, skb, state, ct); + ret = do_chain(priv, skb, state); if (ret != NF_ACCEPT) return ret; @@ -343,8 +342,7 @@ nf_nat_ipv6_in(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { unsigned int ret; struct in6_addr daddr = ipv6_hdr(skb)->daddr; @@ -363,8 +361,7 @@ nf_nat_ipv6_out(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { #ifdef CONFIG_XFRM const struct nf_conn *ct; @@ -400,8 +397,7 @@ nf_nat_ipv6_local_fn(void *priv, struct sk_buff *skb, const struct nf_hook_state *state, unsigned int (*do_chain)(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct)) + const struct nf_hook_state *state)) { const struct nf_conn *ct; enum ip_conntrack_info ctinfo; diff --git a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c index 98f61fcb9108..9dfc2b90c362 100644 --- a/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c +++ b/net/ipv6/netfilter/nf_nat_masquerade_ipv6.c @@ -26,14 +26,14 @@ static atomic_t v6_worker_count; unsigned int -nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, +nf_nat_masquerade_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, const struct net_device *out) { enum ip_conntrack_info ctinfo; struct nf_conn_nat *nat; struct in6_addr src; struct nf_conn *ct; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; ct = nf_ct_get(skb, &ctinfo); WARN_ON(!(ct && (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || diff --git a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c index 57593b00c5b4..d9bf42ba44fa 100644 --- a/net/ipv6/netfilter/nf_nat_proto_icmpv6.c +++ b/net/ipv6/netfilter/nf_nat_proto_icmpv6.c @@ -32,7 +32,7 @@ icmpv6_in_range(const struct nf_conntrack_tuple *tuple, static void icmpv6_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/ipv6/netfilter/nft_chain_nat_ipv6.c b/net/ipv6/netfilter/nft_chain_nat_ipv6.c index 3557b114446c..100a6bd1046a 100644 --- a/net/ipv6/netfilter/nft_chain_nat_ipv6.c +++ b/net/ipv6/netfilter/nft_chain_nat_ipv6.c @@ -26,8 +26,7 @@ static unsigned int nft_nat_do_chain(void *priv, struct sk_buff *skb, - const struct nf_hook_state *state, - struct nf_conn *ct) + const struct nf_hook_state *state) { struct nft_pktinfo pkt; diff --git a/net/ipv6/netfilter/nft_masq_ipv6.c b/net/ipv6/netfilter/nft_masq_ipv6.c index 4146536e9c15..dd0122f3cffe 100644 --- a/net/ipv6/netfilter/nft_masq_ipv6.c +++ b/net/ipv6/netfilter/nft_masq_ipv6.c @@ -22,7 +22,7 @@ static void nft_masq_ipv6_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_masq *priv = nft_expr_priv(expr); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); range.flags = priv->flags; diff --git a/net/ipv6/netfilter/nft_redir_ipv6.c b/net/ipv6/netfilter/nft_redir_ipv6.c index a27e424f690d..74269865acc8 100644 --- a/net/ipv6/netfilter/nft_redir_ipv6.c +++ b/net/ipv6/netfilter/nft_redir_ipv6.c @@ -22,7 +22,7 @@ static void nft_redir_ipv6_eval(const struct nft_expr *expr, const struct nft_pktinfo *pkt) { struct nft_redir *priv = nft_expr_priv(expr); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); if (priv->sreg_proto_min) { diff --git a/net/ipv6/reassembly.c b/net/ipv6/reassembly.c index 4979610287e2..b939b94e7e91 100644 --- a/net/ipv6/reassembly.c +++ b/net/ipv6/reassembly.c @@ -163,7 +163,8 @@ fq_find(struct net *net, __be32 id, const struct ipv6hdr *hdr, int iif) } static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, - struct frag_hdr *fhdr, int nhoff) + struct frag_hdr *fhdr, int nhoff, + u32 *prob_offset) { struct sk_buff *prev, *next; struct net_device *dev; @@ -179,11 +180,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, ((u8 *)(fhdr + 1) - (u8 *)(ipv6_hdr(skb) + 1))); if ((unsigned int)end > IPV6_MAXPLEN) { - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, - ((u8 *)&fhdr->frag_off - - skb_network_header(skb))); + *prob_offset = (u8 *)&fhdr->frag_off - skb_network_header(skb); return -1; } @@ -214,10 +211,7 @@ static int ip6_frag_queue(struct frag_queue *fq, struct sk_buff *skb, /* RFC2460 says always send parameter problem in * this case. -DaveM */ - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), - IPSTATS_MIB_INHDRERRORS); - icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, - offsetof(struct ipv6hdr, payload_len)); + *prob_offset = offsetof(struct ipv6hdr, payload_len); return -1; } if (end > fq->q.len) { @@ -519,15 +513,22 @@ static int ipv6_frag_rcv(struct sk_buff *skb) iif = skb->dev ? skb->dev->ifindex : 0; fq = fq_find(net, fhdr->identification, hdr, iif); if (fq) { + u32 prob_offset = 0; int ret; spin_lock(&fq->q.lock); fq->iif = iif; - ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff); + ret = ip6_frag_queue(fq, skb, fhdr, IP6CB(skb)->nhoff, + &prob_offset); spin_unlock(&fq->q.lock); inet_frag_put(&fq->q); + if (prob_offset) { + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), + IPSTATS_MIB_INHDRERRORS); + icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, prob_offset); + } return ret; } @@ -536,7 +537,7 @@ static int ipv6_frag_rcv(struct sk_buff *skb) return -1; fail_hdr: - __IP6_INC_STATS(net, ip6_dst_idev(skb_dst(skb)), + __IP6_INC_STATS(net, __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INHDRERRORS); icmpv6_param_prob(skb, ICMPV6_HDR_FIELD, skb_network_header_len(skb)); return -1; diff --git a/net/ipv6/route.c b/net/ipv6/route.c index f4d61736c41a..af0416701fb2 100644 --- a/net/ipv6/route.c +++ b/net/ipv6/route.c @@ -78,7 +78,6 @@ enum rt6_nud_state { RT6_NUD_SUCCEED = 1 }; -static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort); static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie); static unsigned int ip6_default_advmss(const struct dst_entry *dst); static unsigned int ip6_mtu(const struct dst_entry *dst); @@ -97,25 +96,24 @@ static void ip6_rt_update_pmtu(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb, u32 mtu); static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_buff *skb); -static void rt6_dst_from_metrics_check(struct rt6_info *rt); -static int rt6_score_route(struct rt6_info *rt, int oif, int strict); -static size_t rt6_nlmsg_size(struct rt6_info *rt); -static int rt6_fill_node(struct net *net, - struct sk_buff *skb, struct rt6_info *rt, - struct in6_addr *dst, struct in6_addr *src, +static int rt6_score_route(struct fib6_info *rt, int oif, int strict); +static size_t rt6_nlmsg_size(struct fib6_info *rt); +static int rt6_fill_node(struct net *net, struct sk_buff *skb, + struct fib6_info *rt, struct dst_entry *dst, + struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags); -static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, +static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt, struct in6_addr *daddr, struct in6_addr *saddr); #ifdef CONFIG_IPV6_ROUTE_INFO -static struct rt6_info *rt6_add_route_info(struct net *net, +static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref); -static struct rt6_info *rt6_get_route_info(struct net *net, +static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev); @@ -184,29 +182,10 @@ static void rt6_uncached_list_flush_dev(struct net *net, struct net_device *dev) } } -static u32 *rt6_pcpu_cow_metrics(struct rt6_info *rt) -{ - return dst_metrics_write_ptr(&rt->from->dst); -} - -static u32 *ipv6_cow_metrics(struct dst_entry *dst, unsigned long old) -{ - struct rt6_info *rt = (struct rt6_info *)dst; - - if (rt->rt6i_flags & RTF_PCPU) - return rt6_pcpu_cow_metrics(rt); - else if (rt->rt6i_flags & RTF_CACHE) - return NULL; - else - return dst_cow_metrics_generic(dst, old); -} - -static inline const void *choose_neigh_daddr(struct rt6_info *rt, +static inline const void *choose_neigh_daddr(const struct in6_addr *p, struct sk_buff *skb, const void *daddr) { - struct in6_addr *p = &rt->rt6i_gateway; - if (!ipv6_addr_any(p)) return (const void *) p; else if (skb) @@ -214,18 +193,27 @@ static inline const void *choose_neigh_daddr(struct rt6_info *rt, return daddr; } -static struct neighbour *ip6_neigh_lookup(const struct dst_entry *dst, - struct sk_buff *skb, - const void *daddr) +struct neighbour *ip6_neigh_lookup(const struct in6_addr *gw, + struct net_device *dev, + struct sk_buff *skb, + const void *daddr) { - struct rt6_info *rt = (struct rt6_info *) dst; struct neighbour *n; - daddr = choose_neigh_daddr(rt, skb, daddr); - n = __ipv6_neigh_lookup(dst->dev, daddr); + daddr = choose_neigh_daddr(gw, skb, daddr); + n = __ipv6_neigh_lookup(dev, daddr); if (n) return n; - return neigh_create(&nd_tbl, daddr, dst->dev); + return neigh_create(&nd_tbl, daddr, dev); +} + +static struct neighbour *ip6_dst_neigh_lookup(const struct dst_entry *dst, + struct sk_buff *skb, + const void *daddr) +{ + const struct rt6_info *rt = container_of(dst, struct rt6_info, dst); + + return ip6_neigh_lookup(&rt->rt6i_gateway, dst->dev, skb, daddr); } static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) @@ -233,7 +221,7 @@ static void ip6_confirm_neigh(const struct dst_entry *dst, const void *daddr) struct net_device *dev = dst->dev; struct rt6_info *rt = (struct rt6_info *)dst; - daddr = choose_neigh_daddr(rt, NULL, daddr); + daddr = choose_neigh_daddr(&rt->rt6i_gateway, NULL, daddr); if (!daddr) return; if (dev->flags & (IFF_NOARP | IFF_LOOPBACK)) @@ -250,7 +238,7 @@ static struct dst_ops ip6_dst_ops_template = { .check = ip6_dst_check, .default_advmss = ip6_default_advmss, .mtu = ip6_mtu, - .cow_metrics = ipv6_cow_metrics, + .cow_metrics = dst_cow_metrics_generic, .destroy = ip6_dst_destroy, .ifdown = ip6_dst_ifdown, .negative_advice = ip6_negative_advice, @@ -258,7 +246,7 @@ static struct dst_ops ip6_dst_ops_template = { .update_pmtu = ip6_rt_update_pmtu, .redirect = rt6_do_redirect, .local_out = __ip6_local_out, - .neigh_lookup = ip6_neigh_lookup, + .neigh_lookup = ip6_dst_neigh_lookup, .confirm_neigh = ip6_confirm_neigh, }; @@ -288,13 +276,22 @@ static struct dst_ops ip6_dst_blackhole_ops = { .update_pmtu = ip6_rt_blackhole_update_pmtu, .redirect = ip6_rt_blackhole_redirect, .cow_metrics = dst_cow_metrics_generic, - .neigh_lookup = ip6_neigh_lookup, + .neigh_lookup = ip6_dst_neigh_lookup, }; static const u32 ip6_template_metrics[RTAX_MAX] = { [RTAX_HOPLIMIT - 1] = 0, }; +static const struct fib6_info fib6_null_entry_template = { + .fib6_flags = (RTF_REJECT | RTF_NONEXTHOP), + .fib6_protocol = RTPROT_KERNEL, + .fib6_metric = ~(u32)0, + .fib6_ref = ATOMIC_INIT(1), + .fib6_type = RTN_UNREACHABLE, + .fib6_metrics = (struct dst_metrics *)&dst_default_metrics, +}; + static const struct rt6_info ip6_null_entry_template = { .dst = { .__refcnt = ATOMIC_INIT(1), @@ -305,9 +302,6 @@ static const struct rt6_info ip6_null_entry_template = { .output = ip6_pkt_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), - .rt6i_protocol = RTPROT_KERNEL, - .rt6i_metric = ~(u32) 0, - .rt6i_ref = ATOMIC_INIT(1), }; #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -322,9 +316,6 @@ static const struct rt6_info ip6_prohibit_entry_template = { .output = ip6_pkt_prohibit_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), - .rt6i_protocol = RTPROT_KERNEL, - .rt6i_metric = ~(u32) 0, - .rt6i_ref = ATOMIC_INIT(1), }; static const struct rt6_info ip6_blk_hole_entry_template = { @@ -337,9 +328,6 @@ static const struct rt6_info ip6_blk_hole_entry_template = { .output = dst_discard_out, }, .rt6i_flags = (RTF_REJECT | RTF_NONEXTHOP), - .rt6i_protocol = RTPROT_KERNEL, - .rt6i_metric = ~(u32) 0, - .rt6i_ref = ATOMIC_INIT(1), }; #endif @@ -349,14 +337,12 @@ static void rt6_info_init(struct rt6_info *rt) struct dst_entry *dst = &rt->dst; memset(dst + 1, 0, sizeof(*rt) - sizeof(*dst)); - INIT_LIST_HEAD(&rt->rt6i_siblings); INIT_LIST_HEAD(&rt->rt6i_uncached); } /* allocate dst with ip6_dst_ops */ -static struct rt6_info *__ip6_dst_alloc(struct net *net, - struct net_device *dev, - int flags) +struct rt6_info *ip6_dst_alloc(struct net *net, struct net_device *dev, + int flags) { struct rt6_info *rt = dst_alloc(&net->ipv6.ip6_dst_ops, dev, 1, DST_OBSOLETE_FORCE_CHK, flags); @@ -368,34 +354,15 @@ static struct rt6_info *__ip6_dst_alloc(struct net *net, return rt; } - -struct rt6_info *ip6_dst_alloc(struct net *net, - struct net_device *dev, - int flags) -{ - struct rt6_info *rt = __ip6_dst_alloc(net, dev, flags); - - if (rt) { - rt->rt6i_pcpu = alloc_percpu_gfp(struct rt6_info *, GFP_ATOMIC); - if (!rt->rt6i_pcpu) { - dst_release_immediate(&rt->dst); - return NULL; - } - } - - return rt; -} EXPORT_SYMBOL(ip6_dst_alloc); static void ip6_dst_destroy(struct dst_entry *dst) { struct rt6_info *rt = (struct rt6_info *)dst; - struct rt6_exception_bucket *bucket; - struct rt6_info *from = rt->from; + struct fib6_info *from; struct inet6_dev *idev; dst_destroy_metrics_generic(dst); - free_percpu(rt->rt6i_pcpu); rt6_uncached_list_del(rt); idev = rt->rt6i_idev; @@ -403,14 +370,12 @@ static void ip6_dst_destroy(struct dst_entry *dst) rt->rt6i_idev = NULL; in6_dev_put(idev); } - bucket = rcu_dereference_protected(rt->rt6i_exception_bucket, 1); - if (bucket) { - rt->rt6i_exception_bucket = NULL; - kfree(bucket); - } - rt->from = NULL; - dst_release(&from->dst); + rcu_read_lock(); + from = rcu_dereference(rt->from); + rcu_assign_pointer(rt->from, NULL); + fib6_info_release(from); + rcu_read_unlock(); } static void ip6_dst_ifdown(struct dst_entry *dst, struct net_device *dev, @@ -440,23 +405,27 @@ static bool __rt6_check_expired(const struct rt6_info *rt) static bool rt6_check_expired(const struct rt6_info *rt) { + struct fib6_info *from; + + from = rcu_dereference(rt->from); + if (rt->rt6i_flags & RTF_EXPIRES) { if (time_after(jiffies, rt->dst.expires)) return true; - } else if (rt->from) { + } else if (from) { return rt->dst.obsolete != DST_OBSOLETE_FORCE_CHK || - rt6_check_expired(rt->from); + fib6_check_expired(from); } return false; } -static struct rt6_info *rt6_multipath_select(const struct net *net, - struct rt6_info *match, +static struct fib6_info *rt6_multipath_select(const struct net *net, + struct fib6_info *match, struct flowi6 *fl6, int oif, const struct sk_buff *skb, int strict) { - struct rt6_info *sibling, *next_sibling; + struct fib6_info *sibling, *next_sibling; /* We might have already computed the hash for ICMPv6 errors. In such * case it will always be non-zero. Otherwise now is the time to do it. @@ -464,12 +433,15 @@ static struct rt6_info *rt6_multipath_select(const struct net *net, if (!fl6->mp_hash) fl6->mp_hash = rt6_multipath_hash(net, fl6, skb, NULL); - if (fl6->mp_hash <= atomic_read(&match->rt6i_nh_upper_bound)) + if (fl6->mp_hash <= atomic_read(&match->fib6_nh.nh_upper_bound)) return match; - list_for_each_entry_safe(sibling, next_sibling, &match->rt6i_siblings, - rt6i_siblings) { - if (fl6->mp_hash > atomic_read(&sibling->rt6i_nh_upper_bound)) + list_for_each_entry_safe(sibling, next_sibling, &match->fib6_siblings, + fib6_siblings) { + int nh_upper_bound; + + nh_upper_bound = atomic_read(&sibling->fib6_nh.nh_upper_bound); + if (fl6->mp_hash > nh_upper_bound) continue; if (rt6_score_route(sibling, oif, strict) < 0) break; @@ -484,38 +456,27 @@ static struct rt6_info *rt6_multipath_select(const struct net *net, * Route lookup. rcu_read_lock() should be held. */ -static inline struct rt6_info *rt6_device_match(struct net *net, - struct rt6_info *rt, +static inline struct fib6_info *rt6_device_match(struct net *net, + struct fib6_info *rt, const struct in6_addr *saddr, int oif, int flags) { - struct rt6_info *local = NULL; - struct rt6_info *sprt; + struct fib6_info *sprt; - if (!oif && ipv6_addr_any(saddr) && !(rt->rt6i_nh_flags & RTNH_F_DEAD)) + if (!oif && ipv6_addr_any(saddr) && + !(rt->fib6_nh.nh_flags & RTNH_F_DEAD)) return rt; - for (sprt = rt; sprt; sprt = rcu_dereference(sprt->rt6_next)) { - struct net_device *dev = sprt->dst.dev; + for (sprt = rt; sprt; sprt = rcu_dereference(sprt->fib6_next)) { + const struct net_device *dev = sprt->fib6_nh.nh_dev; - if (sprt->rt6i_nh_flags & RTNH_F_DEAD) + if (sprt->fib6_nh.nh_flags & RTNH_F_DEAD) continue; if (oif) { if (dev->ifindex == oif) return sprt; - if (dev->flags & IFF_LOOPBACK) { - if (!sprt->rt6i_idev || - sprt->rt6i_idev->dev->ifindex != oif) { - if (flags & RT6_LOOKUP_F_IFACE) - continue; - if (local && - local->rt6i_idev->dev->ifindex == oif) - continue; - } - local = sprt; - } } else { if (ipv6_chk_addr(net, saddr, dev, flags & RT6_LOOKUP_F_IFACE)) @@ -523,15 +484,10 @@ static inline struct rt6_info *rt6_device_match(struct net *net, } } - if (oif) { - if (local) - return local; - - if (flags & RT6_LOOKUP_F_IFACE) - return net->ipv6.ip6_null_entry; - } + if (oif && flags & RT6_LOOKUP_F_IFACE) + return net->ipv6.fib6_null_entry; - return rt->rt6i_nh_flags & RTNH_F_DEAD ? net->ipv6.ip6_null_entry : rt; + return rt->fib6_nh.nh_flags & RTNH_F_DEAD ? net->ipv6.fib6_null_entry : rt; } #ifdef CONFIG_IPV6_ROUTER_PREF @@ -553,10 +509,13 @@ static void rt6_probe_deferred(struct work_struct *w) kfree(work); } -static void rt6_probe(struct rt6_info *rt) +static void rt6_probe(struct fib6_info *rt) { struct __rt6_probe_work *work; + const struct in6_addr *nh_gw; struct neighbour *neigh; + struct net_device *dev; + /* * Okay, this does not seem to be appropriate * for now, however, we need to check if it @@ -565,20 +524,25 @@ static void rt6_probe(struct rt6_info *rt) * Router Reachability Probe MUST be rate-limited * to no more than one per minute. */ - if (!rt || !(rt->rt6i_flags & RTF_GATEWAY)) + if (!rt || !(rt->fib6_flags & RTF_GATEWAY)) return; + + nh_gw = &rt->fib6_nh.nh_gw; + dev = rt->fib6_nh.nh_dev; rcu_read_lock_bh(); - neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + neigh = __ipv6_neigh_lookup_noref(dev, nh_gw); if (neigh) { + struct inet6_dev *idev; + if (neigh->nud_state & NUD_VALID) goto out; + idev = __in6_dev_get(dev); work = NULL; write_lock(&neigh->lock); if (!(neigh->nud_state & NUD_VALID) && time_after(jiffies, - neigh->updated + - rt->rt6i_idev->cnf.rtr_probe_interval)) { + neigh->updated + idev->cnf.rtr_probe_interval)) { work = kmalloc(sizeof(*work), GFP_ATOMIC); if (work) __neigh_set_probe_once(neigh); @@ -590,9 +554,9 @@ static void rt6_probe(struct rt6_info *rt) if (work) { INIT_WORK(&work->work, rt6_probe_deferred); - work->target = rt->rt6i_gateway; - dev_hold(rt->dst.dev); - work->dev = rt->dst.dev; + work->target = *nh_gw; + dev_hold(dev); + work->dev = dev; schedule_work(&work->work); } @@ -600,7 +564,7 @@ out: rcu_read_unlock_bh(); } #else -static inline void rt6_probe(struct rt6_info *rt) +static inline void rt6_probe(struct fib6_info *rt) { } #endif @@ -608,28 +572,27 @@ static inline void rt6_probe(struct rt6_info *rt) /* * Default Router Selection (RFC 2461 6.3.6) */ -static inline int rt6_check_dev(struct rt6_info *rt, int oif) +static inline int rt6_check_dev(struct fib6_info *rt, int oif) { - struct net_device *dev = rt->dst.dev; + const struct net_device *dev = rt->fib6_nh.nh_dev; + if (!oif || dev->ifindex == oif) return 2; - if ((dev->flags & IFF_LOOPBACK) && - rt->rt6i_idev && rt->rt6i_idev->dev->ifindex == oif) - return 1; return 0; } -static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) +static inline enum rt6_nud_state rt6_check_neigh(struct fib6_info *rt) { - struct neighbour *neigh; enum rt6_nud_state ret = RT6_NUD_FAIL_HARD; + struct neighbour *neigh; - if (rt->rt6i_flags & RTF_NONEXTHOP || - !(rt->rt6i_flags & RTF_GATEWAY)) + if (rt->fib6_flags & RTF_NONEXTHOP || + !(rt->fib6_flags & RTF_GATEWAY)) return RT6_NUD_SUCCEED; rcu_read_lock_bh(); - neigh = __ipv6_neigh_lookup_noref(rt->dst.dev, &rt->rt6i_gateway); + neigh = __ipv6_neigh_lookup_noref(rt->fib6_nh.nh_dev, + &rt->fib6_nh.nh_gw); if (neigh) { read_lock(&neigh->lock); if (neigh->nud_state & NUD_VALID) @@ -650,8 +613,7 @@ static inline enum rt6_nud_state rt6_check_neigh(struct rt6_info *rt) return ret; } -static int rt6_score_route(struct rt6_info *rt, int oif, - int strict) +static int rt6_score_route(struct fib6_info *rt, int oif, int strict) { int m; @@ -659,7 +621,7 @@ static int rt6_score_route(struct rt6_info *rt, int oif, if (!m && (strict & RT6_LOOKUP_F_IFACE)) return RT6_NUD_FAIL_HARD; #ifdef CONFIG_IPV6_ROUTER_PREF - m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->rt6i_flags)) << 2; + m |= IPV6_DECODE_PREF(IPV6_EXTRACT_PREF(rt->fib6_flags)) << 2; #endif if (strict & RT6_LOOKUP_F_REACHABLE) { int n = rt6_check_neigh(rt); @@ -669,23 +631,37 @@ static int rt6_score_route(struct rt6_info *rt, int oif, return m; } -static struct rt6_info *find_match(struct rt6_info *rt, int oif, int strict, - int *mpri, struct rt6_info *match, +/* called with rc_read_lock held */ +static inline bool fib6_ignore_linkdown(const struct fib6_info *f6i) +{ + const struct net_device *dev = fib6_info_nh_dev(f6i); + bool rc = false; + + if (dev) { + const struct inet6_dev *idev = __in6_dev_get(dev); + + rc = !!idev->cnf.ignore_routes_with_linkdown; + } + + return rc; +} + +static struct fib6_info *find_match(struct fib6_info *rt, int oif, int strict, + int *mpri, struct fib6_info *match, bool *do_rr) { int m; bool match_do_rr = false; - struct inet6_dev *idev = rt->rt6i_idev; - if (rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD) goto out; - if (idev->cnf.ignore_routes_with_linkdown && - rt->rt6i_nh_flags & RTNH_F_LINKDOWN && + if (fib6_ignore_linkdown(rt) && + rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN && !(strict & RT6_LOOKUP_F_IGNORE_LINKSTATE)) goto out; - if (rt6_check_expired(rt)) + if (fib6_check_expired(rt)) goto out; m = rt6_score_route(rt, oif, strict); @@ -709,19 +685,19 @@ out: return match; } -static struct rt6_info *find_rr_leaf(struct fib6_node *fn, - struct rt6_info *leaf, - struct rt6_info *rr_head, +static struct fib6_info *find_rr_leaf(struct fib6_node *fn, + struct fib6_info *leaf, + struct fib6_info *rr_head, u32 metric, int oif, int strict, bool *do_rr) { - struct rt6_info *rt, *match, *cont; + struct fib6_info *rt, *match, *cont; int mpri = -1; match = NULL; cont = NULL; - for (rt = rr_head; rt; rt = rcu_dereference(rt->rt6_next)) { - if (rt->rt6i_metric != metric) { + for (rt = rr_head; rt; rt = rcu_dereference(rt->fib6_next)) { + if (rt->fib6_metric != metric) { cont = rt; break; } @@ -730,8 +706,8 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, } for (rt = leaf; rt && rt != rr_head; - rt = rcu_dereference(rt->rt6_next)) { - if (rt->rt6i_metric != metric) { + rt = rcu_dereference(rt->fib6_next)) { + if (rt->fib6_metric != metric) { cont = rt; break; } @@ -742,22 +718,22 @@ static struct rt6_info *find_rr_leaf(struct fib6_node *fn, if (match || !cont) return match; - for (rt = cont; rt; rt = rcu_dereference(rt->rt6_next)) + for (rt = cont; rt; rt = rcu_dereference(rt->fib6_next)) match = find_match(rt, oif, strict, &mpri, match, do_rr); return match; } -static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, +static struct fib6_info *rt6_select(struct net *net, struct fib6_node *fn, int oif, int strict) { - struct rt6_info *leaf = rcu_dereference(fn->leaf); - struct rt6_info *match, *rt0; + struct fib6_info *leaf = rcu_dereference(fn->leaf); + struct fib6_info *match, *rt0; bool do_rr = false; int key_plen; - if (!leaf || leaf == net->ipv6.ip6_null_entry) - return net->ipv6.ip6_null_entry; + if (!leaf || leaf == net->ipv6.fib6_null_entry) + return net->ipv6.fib6_null_entry; rt0 = rcu_dereference(fn->rr_ptr); if (!rt0) @@ -768,39 +744,39 @@ static struct rt6_info *rt6_select(struct net *net, struct fib6_node *fn, * (This might happen if all routes under fn are deleted from * the tree and fib6_repair_tree() is called on the node.) */ - key_plen = rt0->rt6i_dst.plen; + key_plen = rt0->fib6_dst.plen; #ifdef CONFIG_IPV6_SUBTREES - if (rt0->rt6i_src.plen) - key_plen = rt0->rt6i_src.plen; + if (rt0->fib6_src.plen) + key_plen = rt0->fib6_src.plen; #endif if (fn->fn_bit != key_plen) - return net->ipv6.ip6_null_entry; + return net->ipv6.fib6_null_entry; - match = find_rr_leaf(fn, leaf, rt0, rt0->rt6i_metric, oif, strict, + match = find_rr_leaf(fn, leaf, rt0, rt0->fib6_metric, oif, strict, &do_rr); if (do_rr) { - struct rt6_info *next = rcu_dereference(rt0->rt6_next); + struct fib6_info *next = rcu_dereference(rt0->fib6_next); /* no entries matched; do round-robin */ - if (!next || next->rt6i_metric != rt0->rt6i_metric) + if (!next || next->fib6_metric != rt0->fib6_metric) next = leaf; if (next != rt0) { - spin_lock_bh(&leaf->rt6i_table->tb6_lock); + spin_lock_bh(&leaf->fib6_table->tb6_lock); /* make sure next is not being deleted from the tree */ - if (next->rt6i_node) + if (next->fib6_node) rcu_assign_pointer(fn->rr_ptr, next); - spin_unlock_bh(&leaf->rt6i_table->tb6_lock); + spin_unlock_bh(&leaf->fib6_table->tb6_lock); } } - return match ? match : net->ipv6.ip6_null_entry; + return match ? match : net->ipv6.fib6_null_entry; } -static bool rt6_is_gw_or_nonexthop(const struct rt6_info *rt) +static bool rt6_is_gw_or_nonexthop(const struct fib6_info *rt) { - return (rt->rt6i_flags & (RTF_NONEXTHOP | RTF_GATEWAY)); + return (rt->fib6_flags & (RTF_NONEXTHOP | RTF_GATEWAY)); } #ifdef CONFIG_IPV6_ROUTE_INFO @@ -812,7 +788,7 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, struct in6_addr prefix_buf, *prefix; unsigned int pref; unsigned long lifetime; - struct rt6_info *rt; + struct fib6_info *rt; if (len < sizeof(struct route_info)) { return -EINVAL; @@ -850,13 +826,13 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, } if (rinfo->prefix_len == 0) - rt = rt6_get_dflt_router(gwaddr, dev); + rt = rt6_get_dflt_router(net, gwaddr, dev); else rt = rt6_get_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev); if (rt && !lifetime) { - ip6_del_rt(rt); + ip6_del_rt(net, rt); rt = NULL; } @@ -864,21 +840,162 @@ int rt6_route_rcv(struct net_device *dev, u8 *opt, int len, rt = rt6_add_route_info(net, prefix, rinfo->prefix_len, gwaddr, dev, pref); else if (rt) - rt->rt6i_flags = RTF_ROUTEINFO | - (rt->rt6i_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); + rt->fib6_flags = RTF_ROUTEINFO | + (rt->fib6_flags & ~RTF_PREF_MASK) | RTF_PREF(pref); if (rt) { if (!addrconf_finite_timeout(lifetime)) - rt6_clean_expires(rt); + fib6_clean_expires(rt); else - rt6_set_expires(rt, jiffies + HZ * lifetime); + fib6_set_expires(rt, jiffies + HZ * lifetime); - ip6_rt_put(rt); + fib6_info_release(rt); } return 0; } #endif +/* + * Misc support functions + */ + +/* called with rcu_lock held */ +static struct net_device *ip6_rt_get_dev_rcu(struct fib6_info *rt) +{ + struct net_device *dev = rt->fib6_nh.nh_dev; + + if (rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) { + /* for copies of local routes, dst->dev needs to be the + * device if it is a master device, the master device if + * device is enslaved, and the loopback as the default + */ + if (netif_is_l3_slave(dev) && + !rt6_need_strict(&rt->fib6_dst.addr)) + dev = l3mdev_master_dev_rcu(dev); + else if (!netif_is_l3_master(dev)) + dev = dev_net(dev)->loopback_dev; + /* last case is netif_is_l3_master(dev) is true in which + * case we want dev returned to be dev + */ + } + + return dev; +} + +static const int fib6_prop[RTN_MAX + 1] = { + [RTN_UNSPEC] = 0, + [RTN_UNICAST] = 0, + [RTN_LOCAL] = 0, + [RTN_BROADCAST] = 0, + [RTN_ANYCAST] = 0, + [RTN_MULTICAST] = 0, + [RTN_BLACKHOLE] = -EINVAL, + [RTN_UNREACHABLE] = -EHOSTUNREACH, + [RTN_PROHIBIT] = -EACCES, + [RTN_THROW] = -EAGAIN, + [RTN_NAT] = -EINVAL, + [RTN_XRESOLVE] = -EINVAL, +}; + +static int ip6_rt_type_to_error(u8 fib6_type) +{ + return fib6_prop[fib6_type]; +} + +static unsigned short fib6_info_dst_flags(struct fib6_info *rt) +{ + unsigned short flags = 0; + + if (rt->dst_nocount) + flags |= DST_NOCOUNT; + if (rt->dst_nopolicy) + flags |= DST_NOPOLICY; + if (rt->dst_host) + flags |= DST_HOST; + + return flags; +} + +static void ip6_rt_init_dst_reject(struct rt6_info *rt, struct fib6_info *ort) +{ + rt->dst.error = ip6_rt_type_to_error(ort->fib6_type); + + switch (ort->fib6_type) { + case RTN_BLACKHOLE: + rt->dst.output = dst_discard_out; + rt->dst.input = dst_discard; + break; + case RTN_PROHIBIT: + rt->dst.output = ip6_pkt_prohibit_out; + rt->dst.input = ip6_pkt_prohibit; + break; + case RTN_THROW: + case RTN_UNREACHABLE: + default: + rt->dst.output = ip6_pkt_discard_out; + rt->dst.input = ip6_pkt_discard; + break; + } +} + +static void ip6_rt_init_dst(struct rt6_info *rt, struct fib6_info *ort) +{ + rt->dst.flags |= fib6_info_dst_flags(ort); + + if (ort->fib6_flags & RTF_REJECT) { + ip6_rt_init_dst_reject(rt, ort); + return; + } + + rt->dst.error = 0; + rt->dst.output = ip6_output; + + if (ort->fib6_type == RTN_LOCAL) { + rt->dst.input = ip6_input; + } else if (ipv6_addr_type(&ort->fib6_dst.addr) & IPV6_ADDR_MULTICAST) { + rt->dst.input = ip6_mc_input; + } else { + rt->dst.input = ip6_forward; + } + + if (ort->fib6_nh.nh_lwtstate) { + rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); + lwtunnel_set_redirect(&rt->dst); + } + + rt->dst.lastuse = jiffies; +} + +static void rt6_set_from(struct rt6_info *rt, struct fib6_info *from) +{ + rt->rt6i_flags &= ~RTF_EXPIRES; + fib6_info_hold(from); + rcu_assign_pointer(rt->from, from); + dst_init_metrics(&rt->dst, from->fib6_metrics->metrics, true); + if (from->fib6_metrics != &dst_default_metrics) { + rt->dst._metrics |= DST_METRICS_REFCOUNTED; + refcount_inc(&from->fib6_metrics->refcnt); + } +} + +static void ip6_rt_copy_init(struct rt6_info *rt, struct fib6_info *ort) +{ + struct net_device *dev = fib6_info_nh_dev(ort); + + ip6_rt_init_dst(rt, ort); + + rt->rt6i_dst = ort->fib6_dst; + rt->rt6i_idev = dev ? in6_dev_get(dev) : NULL; + rt->rt6i_gateway = ort->fib6_nh.nh_gw; + rt->rt6i_flags = ort->fib6_flags; + rt6_set_from(rt, ort); +#ifdef CONFIG_IPV6_SUBTREES + rt->rt6i_src = ort->fib6_src; +#endif + rt->rt6i_prefsrc = ort->fib6_prefsrc; + rt->dst.lwtstate = lwtstate_get(ort->fib6_nh.nh_lwtstate); +} + static struct fib6_node* fib6_backtrack(struct fib6_node *fn, struct in6_addr *saddr) { @@ -914,14 +1031,29 @@ static bool ip6_hold_safe(struct net *net, struct rt6_info **prt, return false; } +/* called with rcu_lock held */ +static struct rt6_info *ip6_create_rt_rcu(struct fib6_info *rt) +{ + unsigned short flags = fib6_info_dst_flags(rt); + struct net_device *dev = rt->fib6_nh.nh_dev; + struct rt6_info *nrt; + + nrt = ip6_dst_alloc(dev_net(dev), dev, flags); + if (nrt) + ip6_rt_copy_init(nrt, rt); + + return nrt; +} + static struct rt6_info *ip6_pol_route_lookup(struct net *net, struct fib6_table *table, struct flowi6 *fl6, const struct sk_buff *skb, int flags) { - struct rt6_info *rt, *rt_cache; + struct fib6_info *f6i; struct fib6_node *fn; + struct rt6_info *rt; if (fl6->flowi6_flags & FLOWI_FLAG_SKIP_NH_OIF) flags &= ~RT6_LOOKUP_F_IFACE; @@ -929,35 +1061,43 @@ static struct rt6_info *ip6_pol_route_lookup(struct net *net, rcu_read_lock(); fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: - rt = rcu_dereference(fn->leaf); - if (!rt) { - rt = net->ipv6.ip6_null_entry; + f6i = rcu_dereference(fn->leaf); + if (!f6i) { + f6i = net->ipv6.fib6_null_entry; } else { - rt = rt6_device_match(net, rt, &fl6->saddr, + f6i = rt6_device_match(net, f6i, &fl6->saddr, fl6->flowi6_oif, flags); - if (rt->rt6i_nsiblings && fl6->flowi6_oif == 0) - rt = rt6_multipath_select(net, rt, fl6, fl6->flowi6_oif, - skb, flags); + if (f6i->fib6_nsiblings && fl6->flowi6_oif == 0) + f6i = rt6_multipath_select(net, f6i, fl6, + fl6->flowi6_oif, skb, flags); } - if (rt == net->ipv6.ip6_null_entry) { + if (f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } - /* Search through exception table */ - rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); - if (rt_cache) - rt = rt_cache; - if (ip6_hold_safe(net, &rt, true)) - dst_use_noref(&rt->dst, jiffies); + /* Search through exception table */ + rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr); + if (rt) { + if (ip6_hold_safe(net, &rt, true)) + dst_use_noref(&rt->dst, jiffies); + } else if (f6i == net->ipv6.fib6_null_entry) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } else { + rt = ip6_create_rt_rcu(f6i); + if (!rt) { + rt = net->ipv6.ip6_null_entry; + dst_hold(&rt->dst); + } + } rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table, fl6); return rt; - } struct dst_entry *ip6_route_lookup(struct net *net, struct flowi6 *fl6, @@ -999,55 +1139,28 @@ EXPORT_SYMBOL(rt6_lookup); * Caller must hold dst before calling it. */ -static int __ip6_ins_rt(struct rt6_info *rt, struct nl_info *info, - struct mx6_config *mxc, +static int __ip6_ins_rt(struct fib6_info *rt, struct nl_info *info, struct netlink_ext_ack *extack) { int err; struct fib6_table *table; - table = rt->rt6i_table; + table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); - err = fib6_add(&table->tb6_root, rt, info, mxc, extack); + err = fib6_add(&table->tb6_root, rt, info, extack); spin_unlock_bh(&table->tb6_lock); return err; } -int ip6_ins_rt(struct rt6_info *rt) +int ip6_ins_rt(struct net *net, struct fib6_info *rt) { - struct nl_info info = { .nl_net = dev_net(rt->dst.dev), }; - struct mx6_config mxc = { .mx = NULL, }; - - /* Hold dst to account for the reference from the fib6 tree */ - dst_hold(&rt->dst); - return __ip6_ins_rt(rt, &info, &mxc, NULL); -} - -/* called with rcu_lock held */ -static struct net_device *ip6_rt_get_dev_rcu(struct rt6_info *rt) -{ - struct net_device *dev = rt->dst.dev; - - if (rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) { - /* for copies of local routes, dst->dev needs to be the - * device if it is a master device, the master device if - * device is enslaved, and the loopback as the default - */ - if (netif_is_l3_slave(dev) && - !rt6_need_strict(&rt->rt6i_dst.addr)) - dev = l3mdev_master_dev_rcu(dev); - else if (!netif_is_l3_master(dev)) - dev = dev_net(dev)->loopback_dev; - /* last case is netif_is_l3_master(dev) is true in which - * case we want dev returned to be dev - */ - } + struct nl_info info = { .nl_net = net, }; - return dev; + return __ip6_ins_rt(rt, &info, NULL); } -static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, +static struct rt6_info *ip6_rt_cache_alloc(struct fib6_info *ort, const struct in6_addr *daddr, const struct in6_addr *saddr) { @@ -1058,26 +1171,20 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, * Clone the route. */ - if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) - ort = ort->from; - - rcu_read_lock(); dev = ip6_rt_get_dev_rcu(ort); - rt = __ip6_dst_alloc(dev_net(dev), dev, 0); - rcu_read_unlock(); + rt = ip6_dst_alloc(dev_net(dev), dev, 0); if (!rt) return NULL; ip6_rt_copy_init(rt, ort); rt->rt6i_flags |= RTF_CACHE; - rt->rt6i_metric = 0; rt->dst.flags |= DST_HOST; rt->rt6i_dst.addr = *daddr; rt->rt6i_dst.plen = 128; if (!rt6_is_gw_or_nonexthop(ort)) { - if (ort->rt6i_dst.plen != 128 && - ipv6_addr_equal(&ort->rt6i_dst.addr, daddr)) + if (ort->fib6_dst.plen != 128 && + ipv6_addr_equal(&ort->fib6_dst.addr, daddr)) rt->rt6i_flags |= RTF_ANYCAST; #ifdef CONFIG_IPV6_SUBTREES if (rt->rt6i_src.plen && saddr) { @@ -1090,45 +1197,44 @@ static struct rt6_info *ip6_rt_cache_alloc(struct rt6_info *ort, return rt; } -static struct rt6_info *ip6_rt_pcpu_alloc(struct rt6_info *rt) +static struct rt6_info *ip6_rt_pcpu_alloc(struct fib6_info *rt) { + unsigned short flags = fib6_info_dst_flags(rt); struct net_device *dev; struct rt6_info *pcpu_rt; rcu_read_lock(); dev = ip6_rt_get_dev_rcu(rt); - pcpu_rt = __ip6_dst_alloc(dev_net(dev), dev, rt->dst.flags); + pcpu_rt = ip6_dst_alloc(dev_net(dev), dev, flags); rcu_read_unlock(); if (!pcpu_rt) return NULL; ip6_rt_copy_init(pcpu_rt, rt); - pcpu_rt->rt6i_protocol = rt->rt6i_protocol; pcpu_rt->rt6i_flags |= RTF_PCPU; return pcpu_rt; } /* It should be called with rcu_read_lock() acquired */ -static struct rt6_info *rt6_get_pcpu_route(struct rt6_info *rt) +static struct rt6_info *rt6_get_pcpu_route(struct fib6_info *rt) { struct rt6_info *pcpu_rt, **p; p = this_cpu_ptr(rt->rt6i_pcpu); pcpu_rt = *p; - if (pcpu_rt && ip6_hold_safe(NULL, &pcpu_rt, false)) - rt6_dst_from_metrics_check(pcpu_rt); + if (pcpu_rt) + ip6_hold_safe(NULL, &pcpu_rt, false); return pcpu_rt; } -static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) +static struct rt6_info *rt6_make_pcpu_route(struct net *net, + struct fib6_info *rt) { struct rt6_info *pcpu_rt, *prev, **p; pcpu_rt = ip6_rt_pcpu_alloc(rt); if (!pcpu_rt) { - struct net *net = dev_net(rt->dst.dev); - dst_hold(&net->ipv6.ip6_null_entry->dst); return net->ipv6.ip6_null_entry; } @@ -1138,7 +1244,6 @@ static struct rt6_info *rt6_make_pcpu_route(struct rt6_info *rt) prev = cmpxchg(p, NULL, pcpu_rt); BUG_ON(prev); - rt6_dst_from_metrics_check(pcpu_rt); return pcpu_rt; } @@ -1158,9 +1263,8 @@ static void rt6_remove_exception(struct rt6_exception_bucket *bucket, return; net = dev_net(rt6_ex->rt6i->dst.dev); - rt6_ex->rt6i->rt6i_node = NULL; hlist_del_rcu(&rt6_ex->hlist); - rt6_release(rt6_ex->rt6i); + dst_release(&rt6_ex->rt6i->dst); kfree_rcu(rt6_ex, rcu); WARN_ON_ONCE(!bucket->depth); bucket->depth--; @@ -1268,20 +1372,36 @@ __rt6_find_exception_rcu(struct rt6_exception_bucket **bucket, return NULL; } +static unsigned int fib6_mtu(const struct fib6_info *rt) +{ + unsigned int mtu; + + if (rt->fib6_pmtu) { + mtu = rt->fib6_pmtu; + } else { + struct net_device *dev = fib6_info_nh_dev(rt); + struct inet6_dev *idev; + + rcu_read_lock(); + idev = __in6_dev_get(dev); + mtu = idev->cnf.mtu6; + rcu_read_unlock(); + } + + mtu = min_t(unsigned int, mtu, IP6_MAX_MTU); + + return mtu - lwtunnel_headroom(rt->fib6_nh.nh_lwtstate, mtu); +} + static int rt6_insert_exception(struct rt6_info *nrt, - struct rt6_info *ort) + struct fib6_info *ort) { - struct net *net = dev_net(ort->dst.dev); + struct net *net = dev_net(nrt->dst.dev); struct rt6_exception_bucket *bucket; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; int err = 0; - /* ort can't be a cache or pcpu route */ - if (ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)) - ort = ort->from; - WARN_ON_ONCE(ort->rt6i_flags & (RTF_CACHE | RTF_PCPU)); - spin_lock_bh(&rt6_exception_lock); if (ort->exception_bucket_flushed) { @@ -1308,19 +1428,19 @@ static int rt6_insert_exception(struct rt6_info *nrt, * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (ort->rt6i_src.plen) + if (ort->fib6_src.plen) src_key = &nrt->rt6i_src.addr; #endif /* Update rt6i_prefsrc as it could be changed * in rt6_remove_prefsrc() */ - nrt->rt6i_prefsrc = ort->rt6i_prefsrc; + nrt->rt6i_prefsrc = ort->fib6_prefsrc; /* rt6_mtu_change() might lower mtu on ort. * Only insert this exception route if its mtu * is less than ort's mtu value. */ - if (nrt->rt6i_pmtu >= dst_mtu(&ort->dst)) { + if (dst_metric_raw(&nrt->dst, RTAX_MTU) >= fib6_mtu(ort)) { err = -EINVAL; goto out; } @@ -1337,8 +1457,6 @@ static int rt6_insert_exception(struct rt6_info *nrt, } rt6_ex->rt6i = nrt; rt6_ex->stamp = jiffies; - atomic_inc(&nrt->rt6i_ref); - nrt->rt6i_node = ort->rt6i_node; hlist_add_head_rcu(&rt6_ex->hlist, &bucket->chain); bucket->depth++; net->ipv6.rt6_stats->fib_rt_cache++; @@ -1351,16 +1469,16 @@ out: /* Update fn->fn_sernum to invalidate all cached dst */ if (!err) { - spin_lock_bh(&ort->rt6i_table->tb6_lock); - fib6_update_sernum(ort); - spin_unlock_bh(&ort->rt6i_table->tb6_lock); + spin_lock_bh(&ort->fib6_table->tb6_lock); + fib6_update_sernum(net, ort); + spin_unlock_bh(&ort->fib6_table->tb6_lock); fib6_force_start_gc(net); } return err; } -void rt6_flush_exceptions(struct rt6_info *rt) +void rt6_flush_exceptions(struct fib6_info *rt) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1390,7 +1508,7 @@ out: /* Find cached rt in the hash table inside passed in rt * Caller has to hold rcu_read_lock() */ -static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, +static struct rt6_info *rt6_find_cached_rt(struct fib6_info *rt, struct in6_addr *daddr, struct in6_addr *saddr) { @@ -1408,7 +1526,7 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (rt->rt6i_src.plen) + if (rt->fib6_src.plen) src_key = saddr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, daddr, src_key); @@ -1420,14 +1538,15 @@ static struct rt6_info *rt6_find_cached_rt(struct rt6_info *rt, } /* Remove the passed in cached rt from the hash table that contains it */ -int rt6_remove_exception_rt(struct rt6_info *rt) +static int rt6_remove_exception_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct rt6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; + struct fib6_info *from; int err; + from = rcu_dereference(rt->from); if (!from || !(rt->rt6i_flags & RTF_CACHE)) return -EINVAL; @@ -1445,7 +1564,7 @@ int rt6_remove_exception_rt(struct rt6_info *rt) * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (from->rt6i_src.plen) + if (from->fib6_src.plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_spinlock(&bucket, @@ -1468,7 +1587,7 @@ int rt6_remove_exception_rt(struct rt6_info *rt) static void rt6_update_exception_stamp_rt(struct rt6_info *rt) { struct rt6_exception_bucket *bucket; - struct rt6_info *from = rt->from; + struct fib6_info *from = rt->from; struct in6_addr *src_key = NULL; struct rt6_exception *rt6_ex; @@ -1486,7 +1605,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) * Otherwise, the exception table is indexed by * a hash of only rt6i_dst. */ - if (from->rt6i_src.plen) + if (from->fib6_src.plen) src_key = &rt->rt6i_src.addr; #endif rt6_ex = __rt6_find_exception_rcu(&bucket, @@ -1498,7 +1617,7 @@ static void rt6_update_exception_stamp_rt(struct rt6_info *rt) rcu_read_unlock(); } -static void rt6_exceptions_remove_prefsrc(struct rt6_info *rt) +static void rt6_exceptions_remove_prefsrc(struct fib6_info *rt) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1540,7 +1659,7 @@ static bool rt6_mtu_change_route_allowed(struct inet6_dev *idev, } static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, - struct rt6_info *rt, int mtu) + struct fib6_info *rt, int mtu) { struct rt6_exception_bucket *bucket; struct rt6_exception *rt6_ex; @@ -1557,12 +1676,12 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, struct rt6_info *entry = rt6_ex->rt6i; /* For RTF_CACHE with rt6i_pmtu == 0 (i.e. a redirected - * route), the metrics of its rt->dst.from have already + * route), the metrics of its rt->from have already * been updated. */ - if (entry->rt6i_pmtu && + if (dst_metric_raw(&entry->dst, RTAX_MTU) && rt6_mtu_change_route_allowed(idev, entry, mtu)) - entry->rt6i_pmtu = mtu; + dst_metric_set(&entry->dst, RTAX_MTU, mtu); } bucket++; } @@ -1570,7 +1689,7 @@ static void rt6_exceptions_update_pmtu(struct inet6_dev *idev, #define RTF_CACHE_GATEWAY (RTF_GATEWAY | RTF_CACHE) -static void rt6_exceptions_clean_tohost(struct rt6_info *rt, +static void rt6_exceptions_clean_tohost(struct fib6_info *rt, struct in6_addr *gateway) { struct rt6_exception_bucket *bucket; @@ -1649,7 +1768,7 @@ static void rt6_age_examine_exception(struct rt6_exception_bucket *bucket, gc_args->more++; } -void rt6_age_exceptions(struct rt6_info *rt, +void rt6_age_exceptions(struct fib6_info *rt, struct fib6_gc_args *gc_args, unsigned long now) { @@ -1685,7 +1804,8 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, const struct sk_buff *skb, int flags) { struct fib6_node *fn, *saved_fn; - struct rt6_info *rt, *rt_cache; + struct fib6_info *f6i; + struct rt6_info *rt; int strict = 0; strict |= flags & RT6_LOOKUP_F_IFACE; @@ -1702,10 +1822,10 @@ struct rt6_info *ip6_pol_route(struct net *net, struct fib6_table *table, oif = 0; redo_rt6_select: - rt = rt6_select(net, fn, oif, strict); - if (rt->rt6i_nsiblings) - rt = rt6_multipath_select(net, rt, fl6, oif, skb, strict); - if (rt == net->ipv6.ip6_null_entry) { + f6i = rt6_select(net, fn, oif, strict); + if (f6i->fib6_nsiblings) + f6i = rt6_multipath_select(net, f6i, fl6, oif, skb, strict); + if (f6i == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto redo_rt6_select; @@ -1717,45 +1837,35 @@ redo_rt6_select: } } - /*Search through exception table */ - rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); - if (rt_cache) - rt = rt_cache; - - if (rt == net->ipv6.ip6_null_entry) { + if (f6i == net->ipv6.fib6_null_entry) { + rt = net->ipv6.ip6_null_entry; rcu_read_unlock(); dst_hold(&rt->dst); trace_fib6_table_lookup(net, rt, table, fl6); return rt; - } else if (rt->rt6i_flags & RTF_CACHE) { - if (ip6_hold_safe(net, &rt, true)) { + } + + /*Search through exception table */ + rt = rt6_find_cached_rt(f6i, &fl6->daddr, &fl6->saddr); + if (rt) { + if (ip6_hold_safe(net, &rt, true)) dst_use_noref(&rt->dst, jiffies); - rt6_dst_from_metrics_check(rt); - } + rcu_read_unlock(); trace_fib6_table_lookup(net, rt, table, fl6); return rt; } else if (unlikely((fl6->flowi6_flags & FLOWI_FLAG_KNOWN_NH) && - !(rt->rt6i_flags & RTF_GATEWAY))) { + !(f6i->fib6_flags & RTF_GATEWAY))) { /* Create a RTF_CACHE clone which will not be * owned by the fib6 tree. It is for the special case where * the daddr in the skb during the neighbor look-up is different * from the fl6->daddr used to look-up route here. */ - struct rt6_info *uncached_rt; - if (ip6_hold_safe(net, &rt, true)) { - dst_use_noref(&rt->dst, jiffies); - } else { - rcu_read_unlock(); - uncached_rt = rt; - goto uncached_rt_out; - } - rcu_read_unlock(); + uncached_rt = ip6_rt_cache_alloc(f6i, &fl6->daddr, NULL); - uncached_rt = ip6_rt_cache_alloc(rt, &fl6->daddr, NULL); - dst_release(&rt->dst); + rcu_read_unlock(); if (uncached_rt) { /* Uncached_rt's refcnt is taken during ip6_rt_cache_alloc() @@ -1768,7 +1878,6 @@ redo_rt6_select: dst_hold(&uncached_rt->dst); } -uncached_rt_out: trace_fib6_table_lookup(net, uncached_rt, table, fl6); return uncached_rt; @@ -1777,24 +1886,12 @@ uncached_rt_out: struct rt6_info *pcpu_rt; - dst_use_noref(&rt->dst, jiffies); local_bh_disable(); - pcpu_rt = rt6_get_pcpu_route(rt); - - if (!pcpu_rt) { - /* atomic_inc_not_zero() is needed when using rcu */ - if (atomic_inc_not_zero(&rt->rt6i_ref)) { - /* No dst_hold() on rt is needed because grabbing - * rt->rt6i_ref makes sure rt can't be released. - */ - pcpu_rt = rt6_make_pcpu_route(rt); - rt6_release(rt); - } else { - /* rt is already removed from tree */ - pcpu_rt = net->ipv6.ip6_null_entry; - dst_hold(&pcpu_rt->dst); - } - } + pcpu_rt = rt6_get_pcpu_route(f6i); + + if (!pcpu_rt) + pcpu_rt = rt6_make_pcpu_route(net, f6i); + local_bh_enable(); rcu_read_unlock(); trace_fib6_table_lookup(net, pcpu_rt, table, fl6); @@ -2020,7 +2117,6 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori rt->rt6i_idev = in6_dev_get(loopback_dev); rt->rt6i_gateway = ort->rt6i_gateway; rt->rt6i_flags = ort->rt6i_flags & ~RTF_PCPU; - rt->rt6i_metric = 0; memcpy(&rt->rt6i_dst, &ort->rt6i_dst, sizeof(struct rt6key)); #ifdef CONFIG_IPV6_SUBTREES @@ -2036,18 +2132,27 @@ struct dst_entry *ip6_blackhole_route(struct net *net, struct dst_entry *dst_ori * Destination cache support functions */ -static void rt6_dst_from_metrics_check(struct rt6_info *rt) +static bool fib6_check(struct fib6_info *f6i, u32 cookie) { - if (rt->from && - dst_metrics_ptr(&rt->dst) != dst_metrics_ptr(&rt->from->dst)) - dst_init_metrics(&rt->dst, dst_metrics_ptr(&rt->from->dst), true); + u32 rt_cookie = 0; + + if (!fib6_get_cookie_safe(f6i, &rt_cookie) || rt_cookie != cookie) + return false; + + if (fib6_check_expired(f6i)) + return false; + + return true; } -static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) +static struct dst_entry *rt6_check(struct rt6_info *rt, + struct fib6_info *from, + u32 cookie) { u32 rt_cookie = 0; - if (!rt6_get_cookie_safe(rt, &rt_cookie) || rt_cookie != cookie) + if ((from && !fib6_get_cookie_safe(from, &rt_cookie)) || + rt_cookie != cookie) return NULL; if (rt6_check_expired(rt)) @@ -2056,11 +2161,13 @@ static struct dst_entry *rt6_check(struct rt6_info *rt, u32 cookie) return &rt->dst; } -static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) +static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, + struct fib6_info *from, + u32 cookie) { if (!__rt6_check_expired(rt) && rt->dst.obsolete == DST_OBSOLETE_FORCE_CHK && - rt6_check(rt->from, cookie)) + fib6_check(from, cookie)) return &rt->dst; else return NULL; @@ -2068,22 +2175,30 @@ static struct dst_entry *rt6_dst_from_check(struct rt6_info *rt, u32 cookie) static struct dst_entry *ip6_dst_check(struct dst_entry *dst, u32 cookie) { + struct dst_entry *dst_ret; + struct fib6_info *from; struct rt6_info *rt; - rt = (struct rt6_info *) dst; + rt = container_of(dst, struct rt6_info, dst); + + rcu_read_lock(); /* All IPV6 dsts are created with ->obsolete set to the value * DST_OBSOLETE_FORCE_CHK which forces validation calls down * into this function always. */ - rt6_dst_from_metrics_check(rt); + from = rcu_dereference(rt->from); - if (rt->rt6i_flags & RTF_PCPU || - (unlikely(!list_empty(&rt->rt6i_uncached)) && rt->from)) - return rt6_dst_from_check(rt, cookie); + if (from && (rt->rt6i_flags & RTF_PCPU || + unlikely(!list_empty(&rt->rt6i_uncached)))) + dst_ret = rt6_dst_from_check(rt, from, cookie); else - return rt6_check(rt, cookie); + dst_ret = rt6_check(rt, from, cookie); + + rcu_read_unlock(); + + return dst_ret; } static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) @@ -2092,10 +2207,12 @@ static struct dst_entry *ip6_negative_advice(struct dst_entry *dst) if (rt) { if (rt->rt6i_flags & RTF_CACHE) { + rcu_read_lock(); if (rt6_check_expired(rt)) { - ip6_del_rt(rt); + rt6_remove_exception_rt(rt); dst = NULL; } + rcu_read_unlock(); } else { dst_release(dst); dst = NULL; @@ -2112,35 +2229,60 @@ static void ip6_link_failure(struct sk_buff *skb) rt = (struct rt6_info *) skb_dst(skb); if (rt) { + rcu_read_lock(); if (rt->rt6i_flags & RTF_CACHE) { if (dst_hold_safe(&rt->dst)) - ip6_del_rt(rt); + rt6_remove_exception_rt(rt); } else { + struct fib6_info *from; struct fib6_node *fn; - rcu_read_lock(); - fn = rcu_dereference(rt->rt6i_node); - if (fn && (rt->rt6i_flags & RTF_DEFAULT)) - fn->fn_sernum = -1; - rcu_read_unlock(); + from = rcu_dereference(rt->from); + if (from) { + fn = rcu_dereference(from->fib6_node); + if (fn && (rt->rt6i_flags & RTF_DEFAULT)) + fn->fn_sernum = -1; + } } + rcu_read_unlock(); } } +static void rt6_update_expires(struct rt6_info *rt0, int timeout) +{ + if (!(rt0->rt6i_flags & RTF_EXPIRES)) { + struct fib6_info *from; + + rcu_read_lock(); + from = rcu_dereference(rt0->from); + if (from) + rt0->dst.expires = from->expires; + rcu_read_unlock(); + } + + dst_set_expires(&rt0->dst, timeout); + rt0->rt6i_flags |= RTF_EXPIRES; +} + static void rt6_do_update_pmtu(struct rt6_info *rt, u32 mtu) { struct net *net = dev_net(rt->dst.dev); + dst_metric_set(&rt->dst, RTAX_MTU, mtu); rt->rt6i_flags |= RTF_MODIFIED; - rt->rt6i_pmtu = mtu; rt6_update_expires(rt, net->ipv6.sysctl.ip6_rt_mtu_expires); } static bool rt6_cache_allowed_for_pmtu(const struct rt6_info *rt) { + bool from_set; + + rcu_read_lock(); + from_set = !!rcu_dereference(rt->from); + rcu_read_unlock(); + return !(rt->rt6i_flags & RTF_CACHE) && - (rt->rt6i_flags & RTF_PCPU || - rcu_access_pointer(rt->rt6i_node)); + (rt->rt6i_flags & RTF_PCPU || from_set); } static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, @@ -2176,14 +2318,18 @@ static void __ip6_rt_update_pmtu(struct dst_entry *dst, const struct sock *sk, if (rt6->rt6i_flags & RTF_CACHE) rt6_update_exception_stamp_rt(rt6); } else if (daddr) { + struct fib6_info *from; struct rt6_info *nrt6; - nrt6 = ip6_rt_cache_alloc(rt6, daddr, saddr); + rcu_read_lock(); + from = rcu_dereference(rt6->from); + nrt6 = ip6_rt_cache_alloc(from, daddr, saddr); if (nrt6) { rt6_do_update_pmtu(nrt6, mtu); - if (rt6_insert_exception(nrt6, rt6)) + if (rt6_insert_exception(nrt6, from)) dst_release_immediate(&nrt6->dst); } + rcu_read_unlock(); } } @@ -2264,7 +2410,8 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, int flags) { struct ip6rd_flowi *rdfl = (struct ip6rd_flowi *)fl6; - struct rt6_info *rt, *rt_cache; + struct rt6_info *ret = NULL, *rt_cache; + struct fib6_info *rt; struct fib6_node *fn; /* Get the "current" route for this destination and @@ -2281,29 +2428,29 @@ static struct rt6_info *__ip6_route_redirect(struct net *net, fn = fib6_lookup(&table->tb6_root, &fl6->daddr, &fl6->saddr); restart: for_each_fib6_node_rt_rcu(fn) { - if (rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD) continue; - if (rt6_check_expired(rt)) + if (fib6_check_expired(rt)) continue; - if (rt->dst.error) + if (rt->fib6_flags & RTF_REJECT) break; - if (!(rt->rt6i_flags & RTF_GATEWAY)) + if (!(rt->fib6_flags & RTF_GATEWAY)) continue; - if (fl6->flowi6_oif != rt->dst.dev->ifindex) + if (fl6->flowi6_oif != rt->fib6_nh.nh_dev->ifindex) continue; /* rt_cache's gateway might be different from its 'parent' * in the case of an ip redirect. * So we keep searching in the exception table if the gateway * is different. */ - if (!ipv6_addr_equal(&rdfl->gateway, &rt->rt6i_gateway)) { + if (!ipv6_addr_equal(&rdfl->gateway, &rt->fib6_nh.nh_gw)) { rt_cache = rt6_find_cached_rt(rt, &fl6->daddr, &fl6->saddr); if (rt_cache && ipv6_addr_equal(&rdfl->gateway, &rt_cache->rt6i_gateway)) { - rt = rt_cache; + ret = rt_cache; break; } continue; @@ -2312,25 +2459,28 @@ restart: } if (!rt) - rt = net->ipv6.ip6_null_entry; - else if (rt->dst.error) { - rt = net->ipv6.ip6_null_entry; + rt = net->ipv6.fib6_null_entry; + else if (rt->fib6_flags & RTF_REJECT) { + ret = net->ipv6.ip6_null_entry; goto out; } - if (rt == net->ipv6.ip6_null_entry) { + if (rt == net->ipv6.fib6_null_entry) { fn = fib6_backtrack(fn, &fl6->saddr); if (fn) goto restart; } out: - ip6_hold_safe(net, &rt, true); + if (ret) + dst_hold(&ret->dst); + else + ret = ip6_create_rt_rcu(rt); rcu_read_unlock(); - trace_fib6_table_lookup(net, rt, table, fl6); - return rt; + trace_fib6_table_lookup(net, ret, table, fl6); + return ret; }; static struct dst_entry *ip6_route_redirect(struct net *net, @@ -2422,12 +2572,8 @@ static unsigned int ip6_default_advmss(const struct dst_entry *dst) static unsigned int ip6_mtu(const struct dst_entry *dst) { - const struct rt6_info *rt = (const struct rt6_info *)dst; - unsigned int mtu = rt->rt6i_pmtu; struct inet6_dev *idev; - - if (mtu) - goto out; + unsigned int mtu; mtu = dst_metric_raw(dst, RTAX_MTU); if (mtu) @@ -2511,60 +2657,22 @@ out: return entries > rt_max_size; } -static int ip6_convert_metrics(struct mx6_config *mxc, - const struct fib6_config *cfg) +static int ip6_convert_metrics(struct net *net, struct fib6_info *rt, + struct fib6_config *cfg) { - struct net *net = cfg->fc_nlinfo.nl_net; - bool ecn_ca = false; - struct nlattr *nla; - int remaining; - u32 *mp; + struct dst_metrics *p; if (!cfg->fc_mx) return 0; - mp = kzalloc(sizeof(u32) * RTAX_MAX, GFP_KERNEL); - if (unlikely(!mp)) + p = kzalloc(sizeof(*rt->fib6_metrics), GFP_KERNEL); + if (unlikely(!p)) return -ENOMEM; - nla_for_each_attr(nla, cfg->fc_mx, cfg->fc_mx_len, remaining) { - int type = nla_type(nla); - u32 val; - - if (!type) - continue; - if (unlikely(type > RTAX_MAX)) - goto err; - - if (type == RTAX_CC_ALGO) { - char tmp[TCP_CA_NAME_MAX]; - - nla_strlcpy(tmp, nla, sizeof(tmp)); - val = tcp_ca_get_key_by_name(net, tmp, &ecn_ca); - if (val == TCP_CA_UNSPEC) - goto err; - } else { - val = nla_get_u32(nla); - } - if (type == RTAX_HOPLIMIT && val > 255) - val = 255; - if (type == RTAX_FEATURES && (val & ~RTAX_FEATURE_MASK)) - goto err; + refcount_set(&p->refcnt, 1); + rt->fib6_metrics = p; - mp[type - 1] = val; - __set_bit(type - 1, mxc->mx_valid); - } - - if (ecn_ca) { - __set_bit(RTAX_FEATURES - 1, mxc->mx_valid); - mp[RTAX_FEATURES - 1] |= DST_FEATURE_ECN_CA; - } - - mxc->mx = mp; - return 0; - err: - kfree(mp); - return -EINVAL; + return ip_metrics_convert(net, cfg->fc_mx, cfg->fc_mx_len, p->metrics); } static struct rt6_info *ip6_nh_lookup_table(struct net *net, @@ -2750,11 +2858,12 @@ out: return err; } -static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, +static struct fib6_info *ip6_route_info_create(struct fib6_config *cfg, + gfp_t gfp_flags, struct netlink_ext_ack *extack) { struct net *net = cfg->fc_nlinfo.nl_net; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; struct net_device *dev = NULL; struct inet6_dev *idev = NULL; struct fib6_table *table; @@ -2773,6 +2882,11 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } + if (cfg->fc_type > RTN_MAX) { + NL_SET_ERR_MSG(extack, "Invalid route type"); + goto out; + } + if (cfg->fc_dst_len > 128) { NL_SET_ERR_MSG(extack, "Invalid prefix length"); goto out; @@ -2831,35 +2945,30 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, if (!table) goto out; - rt = ip6_dst_alloc(net, NULL, - (cfg->fc_flags & RTF_ADDRCONF) ? 0 : DST_NOCOUNT); + err = -ENOMEM; + rt = fib6_info_alloc(gfp_flags); + if (!rt) + goto out; - if (!rt) { - err = -ENOMEM; + if (cfg->fc_flags & RTF_ADDRCONF) + rt->dst_nocount = true; + + err = ip6_convert_metrics(net, rt, cfg); + if (err < 0) goto out; - } if (cfg->fc_flags & RTF_EXPIRES) - rt6_set_expires(rt, jiffies + + fib6_set_expires(rt, jiffies + clock_t_to_jiffies(cfg->fc_expires)); else - rt6_clean_expires(rt); + fib6_clean_expires(rt); if (cfg->fc_protocol == RTPROT_UNSPEC) cfg->fc_protocol = RTPROT_BOOT; - rt->rt6i_protocol = cfg->fc_protocol; + rt->fib6_protocol = cfg->fc_protocol; addr_type = ipv6_addr_type(&cfg->fc_dst); - if (addr_type & IPV6_ADDR_MULTICAST) - rt->dst.input = ip6_mc_input; - else if (cfg->fc_flags & RTF_LOCAL) - rt->dst.input = ip6_input; - else - rt->dst.input = ip6_forward; - - rt->dst.output = ip6_output; - if (cfg->fc_encap) { struct lwtunnel_state *lwtstate; @@ -2868,22 +2977,23 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, &lwtstate, extack); if (err) goto out; - rt->dst.lwtstate = lwtstate_get(lwtstate); - lwtunnel_set_redirect(&rt->dst); + rt->fib6_nh.nh_lwtstate = lwtstate_get(lwtstate); } - ipv6_addr_prefix(&rt->rt6i_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); - rt->rt6i_dst.plen = cfg->fc_dst_len; - if (rt->rt6i_dst.plen == 128) - rt->dst.flags |= DST_HOST; + ipv6_addr_prefix(&rt->fib6_dst.addr, &cfg->fc_dst, cfg->fc_dst_len); + rt->fib6_dst.plen = cfg->fc_dst_len; + if (rt->fib6_dst.plen == 128) + rt->dst_host = true; #ifdef CONFIG_IPV6_SUBTREES - ipv6_addr_prefix(&rt->rt6i_src.addr, &cfg->fc_src, cfg->fc_src_len); - rt->rt6i_src.plen = cfg->fc_src_len; + ipv6_addr_prefix(&rt->fib6_src.addr, &cfg->fc_src, cfg->fc_src_len); + rt->fib6_src.plen = cfg->fc_src_len; #endif - rt->rt6i_metric = cfg->fc_metric; - rt->rt6i_nh_weight = 1; + rt->fib6_metric = cfg->fc_metric; + rt->fib6_nh.nh_weight = 1; + + rt->fib6_type = cfg->fc_type; /* We cannot add true routes via loopback here, they would result in kernel looping; promote them to reject routes @@ -2906,28 +3016,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, goto out; } } - rt->rt6i_flags = RTF_REJECT|RTF_NONEXTHOP; - switch (cfg->fc_type) { - case RTN_BLACKHOLE: - rt->dst.error = -EINVAL; - rt->dst.output = dst_discard_out; - rt->dst.input = dst_discard; - break; - case RTN_PROHIBIT: - rt->dst.error = -EACCES; - rt->dst.output = ip6_pkt_prohibit_out; - rt->dst.input = ip6_pkt_prohibit; - break; - case RTN_THROW: - case RTN_UNREACHABLE: - default: - rt->dst.error = (cfg->fc_type == RTN_THROW) ? -EAGAIN - : (cfg->fc_type == RTN_UNREACHABLE) - ? -EHOSTUNREACH : -ENETUNREACH; - rt->dst.output = ip6_pkt_discard_out; - rt->dst.input = ip6_pkt_discard; - break; - } + rt->fib6_flags = RTF_REJECT|RTF_NONEXTHOP; goto install_route; } @@ -2936,7 +3025,7 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, if (err) goto out; - rt->rt6i_gateway = cfg->fc_gateway; + rt->fib6_nh.nh_gw = cfg->fc_gateway; } err = -ENODEV; @@ -2961,96 +3050,82 @@ static struct rt6_info *ip6_route_info_create(struct fib6_config *cfg, err = -EINVAL; goto out; } - rt->rt6i_prefsrc.addr = cfg->fc_prefsrc; - rt->rt6i_prefsrc.plen = 128; + rt->fib6_prefsrc.addr = cfg->fc_prefsrc; + rt->fib6_prefsrc.plen = 128; } else - rt->rt6i_prefsrc.plen = 0; + rt->fib6_prefsrc.plen = 0; - rt->rt6i_flags = cfg->fc_flags; + rt->fib6_flags = cfg->fc_flags; install_route: - if (!(rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) && + if (!(rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) && !netif_carrier_ok(dev)) - rt->rt6i_nh_flags |= RTNH_F_LINKDOWN; - rt->rt6i_nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK); - rt->dst.dev = dev; - rt->rt6i_idev = idev; - rt->rt6i_table = table; + rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN; + rt->fib6_nh.nh_flags |= (cfg->fc_flags & RTNH_F_ONLINK); + rt->fib6_nh.nh_dev = dev; + rt->fib6_table = table; cfg->fc_nlinfo.nl_net = dev_net(dev); + if (idev) + in6_dev_put(idev); + return rt; out: if (dev) dev_put(dev); if (idev) in6_dev_put(idev); - if (rt) - dst_release_immediate(&rt->dst); + fib6_info_release(rt); return ERR_PTR(err); } -int ip6_route_add(struct fib6_config *cfg, +int ip6_route_add(struct fib6_config *cfg, gfp_t gfp_flags, struct netlink_ext_ack *extack) { - struct mx6_config mxc = { .mx = NULL, }; - struct rt6_info *rt; + struct fib6_info *rt; int err; - rt = ip6_route_info_create(cfg, extack); - if (IS_ERR(rt)) { - err = PTR_ERR(rt); - rt = NULL; - goto out; - } + rt = ip6_route_info_create(cfg, gfp_flags, extack); + if (IS_ERR(rt)) + return PTR_ERR(rt); - err = ip6_convert_metrics(&mxc, cfg); - if (err) - goto out; - - err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, &mxc, extack); - - kfree(mxc.mx); - - return err; -out: - if (rt) - dst_release_immediate(&rt->dst); + err = __ip6_ins_rt(rt, &cfg->fc_nlinfo, extack); + fib6_info_release(rt); return err; } -static int __ip6_del_rt(struct rt6_info *rt, struct nl_info *info) +static int __ip6_del_rt(struct fib6_info *rt, struct nl_info *info) { - int err; + struct net *net = info->nl_net; struct fib6_table *table; - struct net *net = dev_net(rt->dst.dev); + int err; - if (rt == net->ipv6.ip6_null_entry) { + if (rt == net->ipv6.fib6_null_entry) { err = -ENOENT; goto out; } - table = rt->rt6i_table; + table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); err = fib6_del(rt, info); spin_unlock_bh(&table->tb6_lock); out: - ip6_rt_put(rt); + fib6_info_release(rt); return err; } -int ip6_del_rt(struct rt6_info *rt) +int ip6_del_rt(struct net *net, struct fib6_info *rt) { - struct nl_info info = { - .nl_net = dev_net(rt->dst.dev), - }; + struct nl_info info = { .nl_net = net }; + return __ip6_del_rt(rt, &info); } -static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) +static int __ip6_del_rt_siblings(struct fib6_info *rt, struct fib6_config *cfg) { struct nl_info *info = &cfg->fc_nlinfo; struct net *net = info->nl_net; @@ -3058,20 +3133,20 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) struct fib6_table *table; int err = -ENOENT; - if (rt == net->ipv6.ip6_null_entry) + if (rt == net->ipv6.fib6_null_entry) goto out_put; - table = rt->rt6i_table; + table = rt->fib6_table; spin_lock_bh(&table->tb6_lock); - if (rt->rt6i_nsiblings && cfg->fc_delete_all_nh) { - struct rt6_info *sibling, *next_sibling; + if (rt->fib6_nsiblings && cfg->fc_delete_all_nh) { + struct fib6_info *sibling, *next_sibling; /* prefer to send a single notification with all hops */ skb = nlmsg_new(rt6_nlmsg_size(rt), gfp_any()); if (skb) { u32 seq = info->nlh ? info->nlh->nlmsg_seq : 0; - if (rt6_fill_node(net, skb, rt, + if (rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, RTM_DELROUTE, info->portid, seq, 0) < 0) { kfree_skb(skb); @@ -3081,8 +3156,8 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) } list_for_each_entry_safe(sibling, next_sibling, - &rt->rt6i_siblings, - rt6i_siblings) { + &rt->fib6_siblings, + fib6_siblings) { err = fib6_del(sibling, info); if (err) goto out_unlock; @@ -3093,7 +3168,7 @@ static int __ip6_del_rt_siblings(struct rt6_info *rt, struct fib6_config *cfg) out_unlock: spin_unlock_bh(&table->tb6_lock); out_put: - ip6_rt_put(rt); + fib6_info_release(rt); if (skb) { rtnl_notify(skb, net, info->portid, RTNLGRP_IPV6_ROUTE, @@ -3102,11 +3177,28 @@ out_put: return err; } +static int ip6_del_cached_rt(struct rt6_info *rt, struct fib6_config *cfg) +{ + int rc = -ESRCH; + + if (cfg->fc_ifindex && rt->dst.dev->ifindex != cfg->fc_ifindex) + goto out; + + if (cfg->fc_flags & RTF_GATEWAY && + !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) + goto out; + if (dst_hold_safe(&rt->dst)) + rc = rt6_remove_exception_rt(rt); +out: + return rc; +} + static int ip6_route_del(struct fib6_config *cfg, struct netlink_ext_ack *extack) { - struct rt6_info *rt, *rt_cache; + struct rt6_info *rt_cache; struct fib6_table *table; + struct fib6_info *rt; struct fib6_node *fn; int err = -ESRCH; @@ -3126,25 +3218,31 @@ static int ip6_route_del(struct fib6_config *cfg, if (fn) { for_each_fib6_node_rt_rcu(fn) { if (cfg->fc_flags & RTF_CACHE) { + int rc; + rt_cache = rt6_find_cached_rt(rt, &cfg->fc_dst, &cfg->fc_src); - if (!rt_cache) - continue; - rt = rt_cache; + if (rt_cache) { + rc = ip6_del_cached_rt(rt_cache, cfg); + if (rc != -ESRCH) { + rcu_read_unlock(); + return rc; + } + } + continue; } if (cfg->fc_ifindex && - (!rt->dst.dev || - rt->dst.dev->ifindex != cfg->fc_ifindex)) + (!rt->fib6_nh.nh_dev || + rt->fib6_nh.nh_dev->ifindex != cfg->fc_ifindex)) continue; if (cfg->fc_flags & RTF_GATEWAY && - !ipv6_addr_equal(&cfg->fc_gateway, &rt->rt6i_gateway)) + !ipv6_addr_equal(&cfg->fc_gateway, &rt->fib6_nh.nh_gw)) continue; - if (cfg->fc_metric && cfg->fc_metric != rt->rt6i_metric) + if (cfg->fc_metric && cfg->fc_metric != rt->fib6_metric) continue; - if (cfg->fc_protocol && cfg->fc_protocol != rt->rt6i_protocol) + if (cfg->fc_protocol && cfg->fc_protocol != rt->fib6_protocol) continue; - if (!dst_hold_safe(&rt->dst)) - break; + fib6_info_hold(rt); rcu_read_unlock(); /* if gateway was specified only delete the one hop */ @@ -3166,6 +3264,7 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu struct ndisc_options ndopts; struct inet6_dev *in6_dev; struct neighbour *neigh; + struct fib6_info *from; struct rd_msg *msg; int optlen, on_link; u8 *lladdr; @@ -3247,7 +3346,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu NEIGH_UPDATE_F_ISROUTER)), NDISC_REDIRECT, &ndopts); - nrt = ip6_rt_cache_alloc(rt, &msg->dest, NULL); + rcu_read_lock(); + from = rcu_dereference(rt->from); + fib6_info_hold(from); + rcu_read_unlock(); + + nrt = ip6_rt_cache_alloc(from, &msg->dest, NULL); if (!nrt) goto out; @@ -3255,14 +3359,13 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu if (on_link) nrt->rt6i_flags &= ~RTF_GATEWAY; - nrt->rt6i_protocol = RTPROT_REDIRECT; nrt->rt6i_gateway = *(struct in6_addr *)neigh->primary_key; /* No need to remove rt from the exception table if rt is * a cached route because rt6_insert_exception() will * takes care of it */ - if (rt6_insert_exception(nrt, rt)) { + if (rt6_insert_exception(nrt, from)) { dst_release_immediate(&nrt->dst); goto out; } @@ -3274,47 +3377,12 @@ static void rt6_do_redirect(struct dst_entry *dst, struct sock *sk, struct sk_bu call_netevent_notifiers(NETEVENT_REDIRECT, &netevent); out: + fib6_info_release(from); neigh_release(neigh); } -/* - * Misc support functions - */ - -static void rt6_set_from(struct rt6_info *rt, struct rt6_info *from) -{ - BUG_ON(from->from); - - rt->rt6i_flags &= ~RTF_EXPIRES; - dst_hold(&from->dst); - rt->from = from; - dst_init_metrics(&rt->dst, dst_metrics_ptr(&from->dst), true); -} - -static void ip6_rt_copy_init(struct rt6_info *rt, struct rt6_info *ort) -{ - rt->dst.input = ort->dst.input; - rt->dst.output = ort->dst.output; - rt->rt6i_dst = ort->rt6i_dst; - rt->dst.error = ort->dst.error; - rt->rt6i_idev = ort->rt6i_idev; - if (rt->rt6i_idev) - in6_dev_hold(rt->rt6i_idev); - rt->dst.lastuse = jiffies; - rt->rt6i_gateway = ort->rt6i_gateway; - rt->rt6i_flags = ort->rt6i_flags; - rt6_set_from(rt, ort); - rt->rt6i_metric = ort->rt6i_metric; -#ifdef CONFIG_IPV6_SUBTREES - rt->rt6i_src = ort->rt6i_src; -#endif - rt->rt6i_prefsrc = ort->rt6i_prefsrc; - rt->rt6i_table = ort->rt6i_table; - rt->dst.lwtstate = lwtstate_get(ort->dst.lwtstate); -} - #ifdef CONFIG_IPV6_ROUTE_INFO -static struct rt6_info *rt6_get_route_info(struct net *net, +static struct fib6_info *rt6_get_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev) @@ -3322,7 +3390,7 @@ static struct rt6_info *rt6_get_route_info(struct net *net, u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_INFO; int ifindex = dev->ifindex; struct fib6_node *fn; - struct rt6_info *rt = NULL; + struct fib6_info *rt = NULL; struct fib6_table *table; table = fib6_get_table(net, tb_id); @@ -3335,13 +3403,13 @@ static struct rt6_info *rt6_get_route_info(struct net *net, goto out; for_each_fib6_node_rt_rcu(fn) { - if (rt->dst.dev->ifindex != ifindex) + if (rt->fib6_nh.nh_dev->ifindex != ifindex) continue; - if ((rt->rt6i_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) + if ((rt->fib6_flags & (RTF_ROUTEINFO|RTF_GATEWAY)) != (RTF_ROUTEINFO|RTF_GATEWAY)) continue; - if (!ipv6_addr_equal(&rt->rt6i_gateway, gwaddr)) + if (!ipv6_addr_equal(&rt->fib6_nh.nh_gw, gwaddr)) continue; - ip6_hold_safe(NULL, &rt, false); + fib6_info_hold(rt); break; } out: @@ -3349,7 +3417,7 @@ out: return rt; } -static struct rt6_info *rt6_add_route_info(struct net *net, +static struct fib6_info *rt6_add_route_info(struct net *net, const struct in6_addr *prefix, int prefixlen, const struct in6_addr *gwaddr, struct net_device *dev, @@ -3362,6 +3430,7 @@ static struct rt6_info *rt6_add_route_info(struct net *net, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_ROUTEINFO | RTF_UP | RTF_PREF(pref), .fc_protocol = RTPROT_RA, + .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, .fc_nlinfo.nl_net = net, @@ -3375,36 +3444,39 @@ static struct rt6_info *rt6_add_route_info(struct net *net, if (!prefixlen) cfg.fc_flags |= RTF_DEFAULT; - ip6_route_add(&cfg, NULL); + ip6_route_add(&cfg, GFP_ATOMIC, NULL); return rt6_get_route_info(net, prefix, prefixlen, gwaddr, dev); } #endif -struct rt6_info *rt6_get_dflt_router(const struct in6_addr *addr, struct net_device *dev) +struct fib6_info *rt6_get_dflt_router(struct net *net, + const struct in6_addr *addr, + struct net_device *dev) { u32 tb_id = l3mdev_fib_table(dev) ? : RT6_TABLE_DFLT; - struct rt6_info *rt; + struct fib6_info *rt; struct fib6_table *table; - table = fib6_get_table(dev_net(dev), tb_id); + table = fib6_get_table(net, tb_id); if (!table) return NULL; rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { - if (dev == rt->dst.dev && - ((rt->rt6i_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && - ipv6_addr_equal(&rt->rt6i_gateway, addr)) + if (dev == rt->fib6_nh.nh_dev && + ((rt->fib6_flags & (RTF_ADDRCONF | RTF_DEFAULT)) == (RTF_ADDRCONF | RTF_DEFAULT)) && + ipv6_addr_equal(&rt->fib6_nh.nh_gw, addr)) break; } if (rt) - ip6_hold_safe(NULL, &rt, false); + fib6_info_hold(rt); rcu_read_unlock(); return rt; } -struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, +struct fib6_info *rt6_add_dflt_router(struct net *net, + const struct in6_addr *gwaddr, struct net_device *dev, unsigned int pref) { @@ -3415,14 +3487,15 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, .fc_flags = RTF_GATEWAY | RTF_ADDRCONF | RTF_DEFAULT | RTF_UP | RTF_EXPIRES | RTF_PREF(pref), .fc_protocol = RTPROT_RA, + .fc_type = RTN_UNICAST, .fc_nlinfo.portid = 0, .fc_nlinfo.nlh = NULL, - .fc_nlinfo.nl_net = dev_net(dev), + .fc_nlinfo.nl_net = net, }; cfg.fc_gateway = *gwaddr; - if (!ip6_route_add(&cfg, NULL)) { + if (!ip6_route_add(&cfg, GFP_ATOMIC, NULL)) { struct fib6_table *table; table = fib6_get_table(dev_net(dev), cfg.fc_table); @@ -3430,24 +3503,25 @@ struct rt6_info *rt6_add_dflt_router(const struct in6_addr *gwaddr, table->flags |= RT6_TABLE_HAS_DFLT_ROUTER; } - return rt6_get_dflt_router(gwaddr, dev); + return rt6_get_dflt_router(net, gwaddr, dev); } -static void __rt6_purge_dflt_routers(struct fib6_table *table) +static void __rt6_purge_dflt_routers(struct net *net, + struct fib6_table *table) { - struct rt6_info *rt; + struct fib6_info *rt; restart: rcu_read_lock(); for_each_fib6_node_rt_rcu(&table->tb6_root) { - if (rt->rt6i_flags & (RTF_DEFAULT | RTF_ADDRCONF) && - (!rt->rt6i_idev || rt->rt6i_idev->cnf.accept_ra != 2)) { - if (dst_hold_safe(&rt->dst)) { - rcu_read_unlock(); - ip6_del_rt(rt); - } else { - rcu_read_unlock(); - } + struct net_device *dev = fib6_info_nh_dev(rt); + struct inet6_dev *idev = dev ? __in6_dev_get(dev) : NULL; + + if (rt->fib6_flags & (RTF_DEFAULT | RTF_ADDRCONF) && + (!idev || idev->cnf.accept_ra != 2)) { + fib6_info_hold(rt); + rcu_read_unlock(); + ip6_del_rt(net, rt); goto restart; } } @@ -3468,7 +3542,7 @@ void rt6_purge_dflt_routers(struct net *net) head = &net->ipv6.fib_table_hash[h]; hlist_for_each_entry_rcu(table, head, tb6_hlist) { if (table->flags & RT6_TABLE_HAS_DFLT_ROUTER) - __rt6_purge_dflt_routers(table); + __rt6_purge_dflt_routers(net, table); } } @@ -3489,6 +3563,7 @@ static void rtmsg_to_fib6_config(struct net *net, cfg->fc_dst_len = rtmsg->rtmsg_dst_len; cfg->fc_src_len = rtmsg->rtmsg_src_len; cfg->fc_flags = rtmsg->rtmsg_flags; + cfg->fc_type = rtmsg->rtmsg_type; cfg->fc_nlinfo.nl_net = net; @@ -3518,7 +3593,7 @@ int ipv6_route_ioctl(struct net *net, unsigned int cmd, void __user *arg) rtnl_lock(); switch (cmd) { case SIOCADDRT: - err = ip6_route_add(&cfg, NULL); + err = ip6_route_add(&cfg, GFP_KERNEL, NULL); break; case SIOCDELRT: err = ip6_route_del(&cfg, NULL); @@ -3546,7 +3621,8 @@ static int ip6_pkt_drop(struct sk_buff *skb, u8 code, int ipstats_mib_noroutes) case IPSTATS_MIB_INNOROUTES: type = ipv6_addr_type(&ipv6_hdr(skb)->daddr); if (type == IPV6_ADDR_ANY) { - IP6_INC_STATS(dev_net(dst->dev), ip6_dst_idev(dst), + IP6_INC_STATS(dev_net(dst->dev), + __in6_dev_get_safely(skb->dev), IPSTATS_MIB_INADDRERRORS); break; } @@ -3587,40 +3663,40 @@ static int ip6_pkt_prohibit_out(struct net *net, struct sock *sk, struct sk_buff * Allocate a dst for local (unicast / anycast) address. */ -struct rt6_info *addrconf_dst_alloc(struct inet6_dev *idev, - const struct in6_addr *addr, - bool anycast) +struct fib6_info *addrconf_f6i_alloc(struct net *net, + struct inet6_dev *idev, + const struct in6_addr *addr, + bool anycast, gfp_t gfp_flags) { u32 tb_id; - struct net *net = dev_net(idev->dev); struct net_device *dev = idev->dev; - struct rt6_info *rt; + struct fib6_info *f6i; - rt = ip6_dst_alloc(net, dev, DST_NOCOUNT); - if (!rt) + f6i = fib6_info_alloc(gfp_flags); + if (!f6i) return ERR_PTR(-ENOMEM); - in6_dev_hold(idev); - - rt->dst.flags |= DST_HOST; - rt->dst.input = ip6_input; - rt->dst.output = ip6_output; - rt->rt6i_idev = idev; - - rt->rt6i_protocol = RTPROT_KERNEL; - rt->rt6i_flags = RTF_UP | RTF_NONEXTHOP; - if (anycast) - rt->rt6i_flags |= RTF_ANYCAST; - else - rt->rt6i_flags |= RTF_LOCAL; + f6i->dst_nocount = true; + f6i->dst_host = true; + f6i->fib6_protocol = RTPROT_KERNEL; + f6i->fib6_flags = RTF_UP | RTF_NONEXTHOP; + if (anycast) { + f6i->fib6_type = RTN_ANYCAST; + f6i->fib6_flags |= RTF_ANYCAST; + } else { + f6i->fib6_type = RTN_LOCAL; + f6i->fib6_flags |= RTF_LOCAL; + } - rt->rt6i_gateway = *addr; - rt->rt6i_dst.addr = *addr; - rt->rt6i_dst.plen = 128; + f6i->fib6_nh.nh_gw = *addr; + dev_hold(dev); + f6i->fib6_nh.nh_dev = dev; + f6i->fib6_dst.addr = *addr; + f6i->fib6_dst.plen = 128; tb_id = l3mdev_fib_table(idev->dev) ? : RT6_TABLE_LOCAL; - rt->rt6i_table = fib6_get_table(net, tb_id); + f6i->fib6_table = fib6_get_table(net, tb_id); - return rt; + return f6i; } /* remove deleted ip from prefsrc entries */ @@ -3630,18 +3706,18 @@ struct arg_dev_net_ip { struct in6_addr *addr; }; -static int fib6_remove_prefsrc(struct rt6_info *rt, void *arg) +static int fib6_remove_prefsrc(struct fib6_info *rt, void *arg) { struct net_device *dev = ((struct arg_dev_net_ip *)arg)->dev; struct net *net = ((struct arg_dev_net_ip *)arg)->net; struct in6_addr *addr = ((struct arg_dev_net_ip *)arg)->addr; - if (((void *)rt->dst.dev == dev || !dev) && - rt != net->ipv6.ip6_null_entry && - ipv6_addr_equal(addr, &rt->rt6i_prefsrc.addr)) { + if (((void *)rt->fib6_nh.nh_dev == dev || !dev) && + rt != net->ipv6.fib6_null_entry && + ipv6_addr_equal(addr, &rt->fib6_prefsrc.addr)) { spin_lock_bh(&rt6_exception_lock); /* remove prefsrc entry */ - rt->rt6i_prefsrc.plen = 0; + rt->fib6_prefsrc.plen = 0; /* need to update cache as well */ rt6_exceptions_remove_prefsrc(rt); spin_unlock_bh(&rt6_exception_lock); @@ -3663,12 +3739,12 @@ void rt6_remove_prefsrc(struct inet6_ifaddr *ifp) #define RTF_RA_ROUTER (RTF_ADDRCONF | RTF_DEFAULT | RTF_GATEWAY) /* Remove routers and update dst entries when gateway turn into host. */ -static int fib6_clean_tohost(struct rt6_info *rt, void *arg) +static int fib6_clean_tohost(struct fib6_info *rt, void *arg) { struct in6_addr *gateway = (struct in6_addr *)arg; - if (((rt->rt6i_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && - ipv6_addr_equal(gateway, &rt->rt6i_gateway)) { + if (((rt->fib6_flags & RTF_RA_ROUTER) == RTF_RA_ROUTER) && + ipv6_addr_equal(gateway, &rt->fib6_nh.nh_gw)) { return -1; } @@ -3694,85 +3770,85 @@ struct arg_netdev_event { }; }; -static struct rt6_info *rt6_multipath_first_sibling(const struct rt6_info *rt) +static struct fib6_info *rt6_multipath_first_sibling(const struct fib6_info *rt) { - struct rt6_info *iter; + struct fib6_info *iter; struct fib6_node *fn; - fn = rcu_dereference_protected(rt->rt6i_node, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + fn = rcu_dereference_protected(rt->fib6_node, + lockdep_is_held(&rt->fib6_table->tb6_lock)); iter = rcu_dereference_protected(fn->leaf, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + lockdep_is_held(&rt->fib6_table->tb6_lock)); while (iter) { - if (iter->rt6i_metric == rt->rt6i_metric && + if (iter->fib6_metric == rt->fib6_metric && rt6_qualify_for_ecmp(iter)) return iter; - iter = rcu_dereference_protected(iter->rt6_next, - lockdep_is_held(&rt->rt6i_table->tb6_lock)); + iter = rcu_dereference_protected(iter->fib6_next, + lockdep_is_held(&rt->fib6_table->tb6_lock)); } return NULL; } -static bool rt6_is_dead(const struct rt6_info *rt) +static bool rt6_is_dead(const struct fib6_info *rt) { - if (rt->rt6i_nh_flags & RTNH_F_DEAD || - (rt->rt6i_nh_flags & RTNH_F_LINKDOWN && - rt->rt6i_idev->cnf.ignore_routes_with_linkdown)) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD || + (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN && + fib6_ignore_linkdown(rt))) return true; return false; } -static int rt6_multipath_total_weight(const struct rt6_info *rt) +static int rt6_multipath_total_weight(const struct fib6_info *rt) { - struct rt6_info *iter; + struct fib6_info *iter; int total = 0; if (!rt6_is_dead(rt)) - total += rt->rt6i_nh_weight; + total += rt->fib6_nh.nh_weight; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) { + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) { if (!rt6_is_dead(iter)) - total += iter->rt6i_nh_weight; + total += iter->fib6_nh.nh_weight; } return total; } -static void rt6_upper_bound_set(struct rt6_info *rt, int *weight, int total) +static void rt6_upper_bound_set(struct fib6_info *rt, int *weight, int total) { int upper_bound = -1; if (!rt6_is_dead(rt)) { - *weight += rt->rt6i_nh_weight; + *weight += rt->fib6_nh.nh_weight; upper_bound = DIV_ROUND_CLOSEST_ULL((u64) (*weight) << 31, total) - 1; } - atomic_set(&rt->rt6i_nh_upper_bound, upper_bound); + atomic_set(&rt->fib6_nh.nh_upper_bound, upper_bound); } -static void rt6_multipath_upper_bound_set(struct rt6_info *rt, int total) +static void rt6_multipath_upper_bound_set(struct fib6_info *rt, int total) { - struct rt6_info *iter; + struct fib6_info *iter; int weight = 0; rt6_upper_bound_set(rt, &weight, total); - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) rt6_upper_bound_set(iter, &weight, total); } -void rt6_multipath_rebalance(struct rt6_info *rt) +void rt6_multipath_rebalance(struct fib6_info *rt) { - struct rt6_info *first; + struct fib6_info *first; int total; /* In case the entire multipath route was marked for flushing, * then there is no need to rebalance upon the removal of every * sibling route. */ - if (!rt->rt6i_nsiblings || rt->should_flush) + if (!rt->fib6_nsiblings || rt->should_flush) return; /* During lookup routes are evaluated in order, so we need to @@ -3787,14 +3863,14 @@ void rt6_multipath_rebalance(struct rt6_info *rt) rt6_multipath_upper_bound_set(first, total); } -static int fib6_ifup(struct rt6_info *rt, void *p_arg) +static int fib6_ifup(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; - const struct net *net = dev_net(arg->dev); + struct net *net = dev_net(arg->dev); - if (rt != net->ipv6.ip6_null_entry && rt->dst.dev == arg->dev) { - rt->rt6i_nh_flags &= ~arg->nh_flags; - fib6_update_sernum_upto_root(dev_net(rt->dst.dev), rt); + if (rt != net->ipv6.fib6_null_entry && rt->fib6_nh.nh_dev == arg->dev) { + rt->fib6_nh.nh_flags &= ~arg->nh_flags; + fib6_update_sernum_upto_root(net, rt); rt6_multipath_rebalance(rt); } @@ -3816,95 +3892,96 @@ void rt6_sync_up(struct net_device *dev, unsigned int nh_flags) fib6_clean_all(dev_net(dev), fib6_ifup, &arg); } -static bool rt6_multipath_uses_dev(const struct rt6_info *rt, +static bool rt6_multipath_uses_dev(const struct fib6_info *rt, const struct net_device *dev) { - struct rt6_info *iter; + struct fib6_info *iter; - if (rt->dst.dev == dev) + if (rt->fib6_nh.nh_dev == dev) return true; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) - if (iter->dst.dev == dev) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) + if (iter->fib6_nh.nh_dev == dev) return true; return false; } -static void rt6_multipath_flush(struct rt6_info *rt) +static void rt6_multipath_flush(struct fib6_info *rt) { - struct rt6_info *iter; + struct fib6_info *iter; rt->should_flush = 1; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) iter->should_flush = 1; } -static unsigned int rt6_multipath_dead_count(const struct rt6_info *rt, +static unsigned int rt6_multipath_dead_count(const struct fib6_info *rt, const struct net_device *down_dev) { - struct rt6_info *iter; + struct fib6_info *iter; unsigned int dead = 0; - if (rt->dst.dev == down_dev || rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_dev == down_dev || + rt->fib6_nh.nh_flags & RTNH_F_DEAD) dead++; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) - if (iter->dst.dev == down_dev || - iter->rt6i_nh_flags & RTNH_F_DEAD) + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) + if (iter->fib6_nh.nh_dev == down_dev || + iter->fib6_nh.nh_flags & RTNH_F_DEAD) dead++; return dead; } -static void rt6_multipath_nh_flags_set(struct rt6_info *rt, +static void rt6_multipath_nh_flags_set(struct fib6_info *rt, const struct net_device *dev, unsigned int nh_flags) { - struct rt6_info *iter; + struct fib6_info *iter; - if (rt->dst.dev == dev) - rt->rt6i_nh_flags |= nh_flags; - list_for_each_entry(iter, &rt->rt6i_siblings, rt6i_siblings) - if (iter->dst.dev == dev) - iter->rt6i_nh_flags |= nh_flags; + if (rt->fib6_nh.nh_dev == dev) + rt->fib6_nh.nh_flags |= nh_flags; + list_for_each_entry(iter, &rt->fib6_siblings, fib6_siblings) + if (iter->fib6_nh.nh_dev == dev) + iter->fib6_nh.nh_flags |= nh_flags; } /* called with write lock held for table with rt */ -static int fib6_ifdown(struct rt6_info *rt, void *p_arg) +static int fib6_ifdown(struct fib6_info *rt, void *p_arg) { const struct arg_netdev_event *arg = p_arg; const struct net_device *dev = arg->dev; - const struct net *net = dev_net(dev); + struct net *net = dev_net(dev); - if (rt == net->ipv6.ip6_null_entry) + if (rt == net->ipv6.fib6_null_entry) return 0; switch (arg->event) { case NETDEV_UNREGISTER: - return rt->dst.dev == dev ? -1 : 0; + return rt->fib6_nh.nh_dev == dev ? -1 : 0; case NETDEV_DOWN: if (rt->should_flush) return -1; - if (!rt->rt6i_nsiblings) - return rt->dst.dev == dev ? -1 : 0; + if (!rt->fib6_nsiblings) + return rt->fib6_nh.nh_dev == dev ? -1 : 0; if (rt6_multipath_uses_dev(rt, dev)) { unsigned int count; count = rt6_multipath_dead_count(rt, dev); - if (rt->rt6i_nsiblings + 1 == count) { + if (rt->fib6_nsiblings + 1 == count) { rt6_multipath_flush(rt); return -1; } rt6_multipath_nh_flags_set(rt, dev, RTNH_F_DEAD | RTNH_F_LINKDOWN); - fib6_update_sernum(rt); + fib6_update_sernum(net, rt); rt6_multipath_rebalance(rt); } return -2; case NETDEV_CHANGE: - if (rt->dst.dev != dev || - rt->rt6i_flags & (RTF_LOCAL | RTF_ANYCAST)) + if (rt->fib6_nh.nh_dev != dev || + rt->fib6_flags & (RTF_LOCAL | RTF_ANYCAST)) break; - rt->rt6i_nh_flags |= RTNH_F_LINKDOWN; + rt->fib6_nh.nh_flags |= RTNH_F_LINKDOWN; rt6_multipath_rebalance(rt); break; } @@ -3936,7 +4013,7 @@ struct rt6_mtu_change_arg { unsigned int mtu; }; -static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) +static int rt6_mtu_change_route(struct fib6_info *rt, void *p_arg) { struct rt6_mtu_change_arg *arg = (struct rt6_mtu_change_arg *) p_arg; struct inet6_dev *idev; @@ -3956,12 +4033,15 @@ static int rt6_mtu_change_route(struct rt6_info *rt, void *p_arg) Since RFC 1981 doesn't include administrative MTU increase update PMTU increase is a MUST. (i.e. jumbo frame) */ - if (rt->dst.dev == arg->dev && - !dst_metric_locked(&rt->dst, RTAX_MTU)) { + if (rt->fib6_nh.nh_dev == arg->dev && + !fib6_metric_locked(rt, RTAX_MTU)) { + u32 mtu = rt->fib6_pmtu; + + if (mtu >= arg->mtu || + (mtu < arg->mtu && mtu == idev->cnf.mtu6)) + fib6_metric_set(rt, RTAX_MTU, arg->mtu); + spin_lock_bh(&rt6_exception_lock); - if (dst_metric_raw(&rt->dst, RTAX_MTU) && - rt6_mtu_change_route_allowed(idev, rt, arg->mtu)) - dst_metric_set(&rt->dst, RTAX_MTU, arg->mtu); rt6_exceptions_update_pmtu(idev, rt, arg->mtu); spin_unlock_bh(&rt6_exception_lock); } @@ -4122,9 +4202,8 @@ errout: } struct rt6_nh { - struct rt6_info *rt6_info; + struct fib6_info *fib6_info; struct fib6_config r_cfg; - struct mx6_config mxc; struct list_head next; }; @@ -4139,23 +4218,25 @@ static void ip6_print_replace_route_err(struct list_head *rt6_nh_list) } } -static int ip6_route_info_append(struct list_head *rt6_nh_list, - struct rt6_info *rt, struct fib6_config *r_cfg) +static int ip6_route_info_append(struct net *net, + struct list_head *rt6_nh_list, + struct fib6_info *rt, + struct fib6_config *r_cfg) { struct rt6_nh *nh; int err = -EEXIST; list_for_each_entry(nh, rt6_nh_list, next) { - /* check if rt6_info already exists */ - if (rt6_duplicate_nexthop(nh->rt6_info, rt)) + /* check if fib6_info already exists */ + if (rt6_duplicate_nexthop(nh->fib6_info, rt)) return err; } nh = kzalloc(sizeof(*nh), GFP_KERNEL); if (!nh) return -ENOMEM; - nh->rt6_info = rt; - err = ip6_convert_metrics(&nh->mxc, r_cfg); + nh->fib6_info = rt; + err = ip6_convert_metrics(net, rt, r_cfg); if (err) { kfree(nh); return err; @@ -4166,8 +4247,8 @@ static int ip6_route_info_append(struct list_head *rt6_nh_list, return 0; } -static void ip6_route_mpath_notify(struct rt6_info *rt, - struct rt6_info *rt_last, +static void ip6_route_mpath_notify(struct fib6_info *rt, + struct fib6_info *rt_last, struct nl_info *info, __u16 nlflags) { @@ -4177,10 +4258,10 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, * nexthop. Since sibling routes are always added at the end of * the list, find the first sibling of the last route appended */ - if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->rt6i_nsiblings) { - rt = list_first_entry(&rt_last->rt6i_siblings, - struct rt6_info, - rt6i_siblings); + if ((nlflags & NLM_F_APPEND) && rt_last && rt_last->fib6_nsiblings) { + rt = list_first_entry(&rt_last->fib6_siblings, + struct fib6_info, + fib6_siblings); } if (rt) @@ -4190,11 +4271,11 @@ static void ip6_route_mpath_notify(struct rt6_info *rt, static int ip6_route_multipath_add(struct fib6_config *cfg, struct netlink_ext_ack *extack) { - struct rt6_info *rt_notif = NULL, *rt_last = NULL; + struct fib6_info *rt_notif = NULL, *rt_last = NULL; struct nl_info *info = &cfg->fc_nlinfo; struct fib6_config r_cfg; struct rtnexthop *rtnh; - struct rt6_info *rt; + struct fib6_info *rt; struct rt6_nh *err_nh; struct rt6_nh *nh, *nh_safe; __u16 nlflags; @@ -4214,7 +4295,7 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, rtnh = (struct rtnexthop *)cfg->fc_mp; /* Parse a Multipath Entry and build a list (rt6_nh_list) of - * rt6_info structs per nexthop + * fib6_info structs per nexthop */ while (rtnh_ok(rtnh, remaining)) { memcpy(&r_cfg, cfg, sizeof(*cfg)); @@ -4237,18 +4318,19 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, } r_cfg.fc_flags |= (rtnh->rtnh_flags & RTNH_F_ONLINK); - rt = ip6_route_info_create(&r_cfg, extack); + rt = ip6_route_info_create(&r_cfg, GFP_KERNEL, extack); if (IS_ERR(rt)) { err = PTR_ERR(rt); rt = NULL; goto cleanup; } - rt->rt6i_nh_weight = rtnh->rtnh_hops + 1; + rt->fib6_nh.nh_weight = rtnh->rtnh_hops + 1; - err = ip6_route_info_append(&rt6_nh_list, rt, &r_cfg); + err = ip6_route_info_append(info->nl_net, &rt6_nh_list, + rt, &r_cfg); if (err) { - dst_release_immediate(&rt->dst); + fib6_info_release(rt); goto cleanup; } @@ -4263,14 +4345,16 @@ static int ip6_route_multipath_add(struct fib6_config *cfg, err_nh = NULL; list_for_each_entry(nh, &rt6_nh_list, next) { - rt_last = nh->rt6_info; - err = __ip6_ins_rt(nh->rt6_info, info, &nh->mxc, extack); + rt_last = nh->fib6_info; + err = __ip6_ins_rt(nh->fib6_info, info, extack); + fib6_info_release(nh->fib6_info); + /* save reference to first route for notification */ if (!rt_notif && !err) - rt_notif = nh->rt6_info; + rt_notif = nh->fib6_info; - /* nh->rt6_info is used or freed at this point, reset to NULL*/ - nh->rt6_info = NULL; + /* nh->fib6_info is used or freed at this point, reset to NULL*/ + nh->fib6_info = NULL; if (err) { if (replace && nhn) ip6_print_replace_route_err(&rt6_nh_list); @@ -4311,9 +4395,8 @@ add_errout: cleanup: list_for_each_entry_safe(nh, nh_safe, &rt6_nh_list, next) { - if (nh->rt6_info) - dst_release_immediate(&nh->rt6_info->dst); - kfree(nh->mxc.mx); + if (nh->fib6_info) + fib6_info_release(nh->fib6_info); list_del(&nh->next); kfree(nh); } @@ -4390,20 +4473,20 @@ static int inet6_rtm_newroute(struct sk_buff *skb, struct nlmsghdr *nlh, if (cfg.fc_mp) return ip6_route_multipath_add(&cfg, extack); else - return ip6_route_add(&cfg, extack); + return ip6_route_add(&cfg, GFP_KERNEL, extack); } -static size_t rt6_nlmsg_size(struct rt6_info *rt) +static size_t rt6_nlmsg_size(struct fib6_info *rt) { int nexthop_len = 0; - if (rt->rt6i_nsiblings) { + if (rt->fib6_nsiblings) { nexthop_len = nla_total_size(0) /* RTA_MULTIPATH */ + NLA_ALIGN(sizeof(struct rtnexthop)) + nla_total_size(16) /* RTA_GATEWAY */ - + lwtunnel_get_encap_size(rt->dst.lwtstate); + + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate); - nexthop_len *= rt->rt6i_nsiblings; + nexthop_len *= rt->fib6_nsiblings; } return NLMSG_ALIGN(sizeof(struct rtmsg)) @@ -4419,38 +4502,41 @@ static size_t rt6_nlmsg_size(struct rt6_info *rt) + nla_total_size(sizeof(struct rta_cacheinfo)) + nla_total_size(TCP_CA_NAME_MAX) /* RTAX_CC_ALGO */ + nla_total_size(1) /* RTA_PREF */ - + lwtunnel_get_encap_size(rt->dst.lwtstate) + + lwtunnel_get_encap_size(rt->fib6_nh.nh_lwtstate) + nexthop_len; } -static int rt6_nexthop_info(struct sk_buff *skb, struct rt6_info *rt, +static int rt6_nexthop_info(struct sk_buff *skb, struct fib6_info *rt, unsigned int *flags, bool skip_oif) { - if (rt->rt6i_nh_flags & RTNH_F_DEAD) + if (rt->fib6_nh.nh_flags & RTNH_F_DEAD) *flags |= RTNH_F_DEAD; - if (rt->rt6i_nh_flags & RTNH_F_LINKDOWN) { + if (rt->fib6_nh.nh_flags & RTNH_F_LINKDOWN) { *flags |= RTNH_F_LINKDOWN; - if (rt->rt6i_idev->cnf.ignore_routes_with_linkdown) + + rcu_read_lock(); + if (fib6_ignore_linkdown(rt)) *flags |= RTNH_F_DEAD; + rcu_read_unlock(); } - if (rt->rt6i_flags & RTF_GATEWAY) { - if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->rt6i_gateway) < 0) + if (rt->fib6_flags & RTF_GATEWAY) { + if (nla_put_in6_addr(skb, RTA_GATEWAY, &rt->fib6_nh.nh_gw) < 0) goto nla_put_failure; } - *flags |= (rt->rt6i_nh_flags & RTNH_F_ONLINK); - if (rt->rt6i_nh_flags & RTNH_F_OFFLOAD) + *flags |= (rt->fib6_nh.nh_flags & RTNH_F_ONLINK); + if (rt->fib6_nh.nh_flags & RTNH_F_OFFLOAD) *flags |= RTNH_F_OFFLOAD; /* not needed for multipath encoding b/c it has a rtnexthop struct */ - if (!skip_oif && rt->dst.dev && - nla_put_u32(skb, RTA_OIF, rt->dst.dev->ifindex)) + if (!skip_oif && rt->fib6_nh.nh_dev && + nla_put_u32(skb, RTA_OIF, rt->fib6_nh.nh_dev->ifindex)) goto nla_put_failure; - if (rt->dst.lwtstate && - lwtunnel_fill_encap(skb, rt->dst.lwtstate) < 0) + if (rt->fib6_nh.nh_lwtstate && + lwtunnel_fill_encap(skb, rt->fib6_nh.nh_lwtstate) < 0) goto nla_put_failure; return 0; @@ -4460,8 +4546,9 @@ nla_put_failure: } /* add multipath next hop */ -static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) +static int rt6_add_nexthop(struct sk_buff *skb, struct fib6_info *rt) { + const struct net_device *dev = rt->fib6_nh.nh_dev; struct rtnexthop *rtnh; unsigned int flags = 0; @@ -4469,8 +4556,8 @@ static int rt6_add_nexthop(struct sk_buff *skb, struct rt6_info *rt) if (!rtnh) goto nla_put_failure; - rtnh->rtnh_hops = rt->rt6i_nh_weight - 1; - rtnh->rtnh_ifindex = rt->dst.dev ? rt->dst.dev->ifindex : 0; + rtnh->rtnh_hops = rt->fib6_nh.nh_weight - 1; + rtnh->rtnh_ifindex = dev ? dev->ifindex : 0; if (rt6_nexthop_info(skb, rt, &flags, true) < 0) goto nla_put_failure; @@ -4486,16 +4573,16 @@ nla_put_failure: return -EMSGSIZE; } -static int rt6_fill_node(struct net *net, - struct sk_buff *skb, struct rt6_info *rt, - struct in6_addr *dst, struct in6_addr *src, +static int rt6_fill_node(struct net *net, struct sk_buff *skb, + struct fib6_info *rt, struct dst_entry *dst, + struct in6_addr *dest, struct in6_addr *src, int iif, int type, u32 portid, u32 seq, unsigned int flags) { - u32 metrics[RTAX_MAX]; struct rtmsg *rtm; struct nlmsghdr *nlh; - long expires; + long expires = 0; + u32 *pmetrics; u32 table; nlh = nlmsg_put(skb, portid, seq, type, sizeof(*rtm), flags); @@ -4504,53 +4591,31 @@ static int rt6_fill_node(struct net *net, rtm = nlmsg_data(nlh); rtm->rtm_family = AF_INET6; - rtm->rtm_dst_len = rt->rt6i_dst.plen; - rtm->rtm_src_len = rt->rt6i_src.plen; + rtm->rtm_dst_len = rt->fib6_dst.plen; + rtm->rtm_src_len = rt->fib6_src.plen; rtm->rtm_tos = 0; - if (rt->rt6i_table) - table = rt->rt6i_table->tb6_id; + if (rt->fib6_table) + table = rt->fib6_table->tb6_id; else table = RT6_TABLE_UNSPEC; rtm->rtm_table = table; if (nla_put_u32(skb, RTA_TABLE, table)) goto nla_put_failure; - if (rt->rt6i_flags & RTF_REJECT) { - switch (rt->dst.error) { - case -EINVAL: - rtm->rtm_type = RTN_BLACKHOLE; - break; - case -EACCES: - rtm->rtm_type = RTN_PROHIBIT; - break; - case -EAGAIN: - rtm->rtm_type = RTN_THROW; - break; - default: - rtm->rtm_type = RTN_UNREACHABLE; - break; - } - } - else if (rt->rt6i_flags & RTF_LOCAL) - rtm->rtm_type = RTN_LOCAL; - else if (rt->rt6i_flags & RTF_ANYCAST) - rtm->rtm_type = RTN_ANYCAST; - else if (rt->dst.dev && (rt->dst.dev->flags & IFF_LOOPBACK)) - rtm->rtm_type = RTN_LOCAL; - else - rtm->rtm_type = RTN_UNICAST; + + rtm->rtm_type = rt->fib6_type; rtm->rtm_flags = 0; rtm->rtm_scope = RT_SCOPE_UNIVERSE; - rtm->rtm_protocol = rt->rt6i_protocol; + rtm->rtm_protocol = rt->fib6_protocol; - if (rt->rt6i_flags & RTF_CACHE) + if (rt->fib6_flags & RTF_CACHE) rtm->rtm_flags |= RTM_F_CLONED; - if (dst) { - if (nla_put_in6_addr(skb, RTA_DST, dst)) + if (dest) { + if (nla_put_in6_addr(skb, RTA_DST, dest)) goto nla_put_failure; rtm->rtm_dst_len = 128; } else if (rtm->rtm_dst_len) - if (nla_put_in6_addr(skb, RTA_DST, &rt->rt6i_dst.addr)) + if (nla_put_in6_addr(skb, RTA_DST, &rt->fib6_dst.addr)) goto nla_put_failure; #ifdef CONFIG_IPV6_SUBTREES if (src) { @@ -4558,12 +4623,12 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; rtm->rtm_src_len = 128; } else if (rtm->rtm_src_len && - nla_put_in6_addr(skb, RTA_SRC, &rt->rt6i_src.addr)) + nla_put_in6_addr(skb, RTA_SRC, &rt->fib6_src.addr)) goto nla_put_failure; #endif if (iif) { #ifdef CONFIG_IPV6_MROUTE - if (ipv6_addr_is_multicast(&rt->rt6i_dst.addr)) { + if (ipv6_addr_is_multicast(&rt->fib6_dst.addr)) { int err = ip6mr_get_route(net, skb, rtm, portid); if (err == 0) @@ -4574,34 +4639,32 @@ static int rt6_fill_node(struct net *net, #endif if (nla_put_u32(skb, RTA_IIF, iif)) goto nla_put_failure; - } else if (dst) { + } else if (dest) { struct in6_addr saddr_buf; - if (ip6_route_get_saddr(net, rt, dst, 0, &saddr_buf) == 0 && + if (ip6_route_get_saddr(net, rt, dest, 0, &saddr_buf) == 0 && nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } - if (rt->rt6i_prefsrc.plen) { + if (rt->fib6_prefsrc.plen) { struct in6_addr saddr_buf; - saddr_buf = rt->rt6i_prefsrc.addr; + saddr_buf = rt->fib6_prefsrc.addr; if (nla_put_in6_addr(skb, RTA_PREFSRC, &saddr_buf)) goto nla_put_failure; } - memcpy(metrics, dst_metrics_ptr(&rt->dst), sizeof(metrics)); - if (rt->rt6i_pmtu) - metrics[RTAX_MTU - 1] = rt->rt6i_pmtu; - if (rtnetlink_put_metrics(skb, metrics) < 0) + pmetrics = dst ? dst_metrics_ptr(dst) : rt->fib6_metrics->metrics; + if (rtnetlink_put_metrics(skb, pmetrics) < 0) goto nla_put_failure; - if (nla_put_u32(skb, RTA_PRIORITY, rt->rt6i_metric)) + if (nla_put_u32(skb, RTA_PRIORITY, rt->fib6_metric)) goto nla_put_failure; /* For multipath routes, walk the siblings list and add * each as a nexthop within RTA_MULTIPATH. */ - if (rt->rt6i_nsiblings) { - struct rt6_info *sibling, *next_sibling; + if (rt->fib6_nsiblings) { + struct fib6_info *sibling, *next_sibling; struct nlattr *mp; mp = nla_nest_start(skb, RTA_MULTIPATH); @@ -4612,7 +4675,7 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; list_for_each_entry_safe(sibling, next_sibling, - &rt->rt6i_siblings, rt6i_siblings) { + &rt->fib6_siblings, fib6_siblings) { if (rt6_add_nexthop(skb, sibling) < 0) goto nla_put_failure; } @@ -4623,12 +4686,15 @@ static int rt6_fill_node(struct net *net, goto nla_put_failure; } - expires = (rt->rt6i_flags & RTF_EXPIRES) ? rt->dst.expires - jiffies : 0; + if (rt->fib6_flags & RTF_EXPIRES) { + expires = dst ? dst->expires : rt->expires; + expires -= jiffies; + } - if (rtnl_put_cacheinfo(skb, &rt->dst, 0, expires, rt->dst.error) < 0) + if (rtnl_put_cacheinfo(skb, dst, 0, expires, dst ? dst->error : 0) < 0) goto nla_put_failure; - if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->rt6i_flags))) + if (nla_put_u8(skb, RTA_PREF, IPV6_EXTRACT_PREF(rt->fib6_flags))) goto nla_put_failure; @@ -4640,12 +4706,12 @@ nla_put_failure: return -EMSGSIZE; } -int rt6_dump_route(struct rt6_info *rt, void *p_arg) +int rt6_dump_route(struct fib6_info *rt, void *p_arg) { struct rt6_rtnl_dump_arg *arg = (struct rt6_rtnl_dump_arg *) p_arg; struct net *net = arg->net; - if (rt == net->ipv6.ip6_null_entry) + if (rt == net->ipv6.fib6_null_entry) return 0; if (nlmsg_len(arg->cb->nlh) >= sizeof(struct rtmsg)) { @@ -4653,16 +4719,15 @@ int rt6_dump_route(struct rt6_info *rt, void *p_arg) /* user wants prefix routes only */ if (rtm->rtm_flags & RTM_F_PREFIX && - !(rt->rt6i_flags & RTF_PREFIX_RT)) { + !(rt->fib6_flags & RTF_PREFIX_RT)) { /* success since this is not a prefix route */ return 1; } } - return rt6_fill_node(net, - arg->skb, rt, NULL, NULL, 0, RTM_NEWROUTE, - NETLINK_CB(arg->cb->skb).portid, arg->cb->nlh->nlmsg_seq, - NLM_F_MULTI); + return rt6_fill_node(net, arg->skb, rt, NULL, NULL, NULL, 0, + RTM_NEWROUTE, NETLINK_CB(arg->cb->skb).portid, + arg->cb->nlh->nlmsg_seq, NLM_F_MULTI); } static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, @@ -4671,6 +4736,7 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, struct net *net = sock_net(in_skb->sk); struct nlattr *tb[RTA_MAX+1]; int err, iif = 0, oif = 0; + struct fib6_info *from; struct dst_entry *dst; struct rt6_info *rt; struct sk_buff *skb; @@ -4759,14 +4825,6 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, goto errout; } - if (fibmatch && rt->from) { - struct rt6_info *ort = rt->from; - - dst_hold(&ort->dst); - ip6_rt_put(rt); - rt = ort; - } - skb = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb) { ip6_rt_put(rt); @@ -4775,14 +4833,21 @@ static int inet6_rtm_getroute(struct sk_buff *in_skb, struct nlmsghdr *nlh, } skb_dst_set(skb, &rt->dst); + + rcu_read_lock(); + from = rcu_dereference(rt->from); + if (fibmatch) - err = rt6_fill_node(net, skb, rt, NULL, NULL, iif, + err = rt6_fill_node(net, skb, from, NULL, NULL, NULL, iif, RTM_NEWROUTE, NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, 0); else - err = rt6_fill_node(net, skb, rt, &fl6.daddr, &fl6.saddr, iif, - RTM_NEWROUTE, NETLINK_CB(in_skb).portid, - nlh->nlmsg_seq, 0); + err = rt6_fill_node(net, skb, from, dst, &fl6.daddr, + &fl6.saddr, iif, RTM_NEWROUTE, + NETLINK_CB(in_skb).portid, nlh->nlmsg_seq, + 0); + rcu_read_unlock(); + if (err < 0) { kfree_skb(skb); goto errout; @@ -4793,7 +4858,7 @@ errout: return err; } -void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, +void inet6_rt_notify(int event, struct fib6_info *rt, struct nl_info *info, unsigned int nlm_flags) { struct sk_buff *skb; @@ -4808,8 +4873,8 @@ void inet6_rt_notify(int event, struct rt6_info *rt, struct nl_info *info, if (!skb) goto errout; - err = rt6_fill_node(net, skb, rt, NULL, NULL, 0, - event, info->portid, seq, nlm_flags); + err = rt6_fill_node(net, skb, rt, NULL, NULL, NULL, 0, + event, info->portid, seq, nlm_flags); if (err < 0) { /* -EMSGSIZE implies BUG in rt6_nlmsg_size() */ WARN_ON(err == -EMSGSIZE); @@ -4834,6 +4899,7 @@ static int ip6_route_dev_notify(struct notifier_block *this, return NOTIFY_OK; if (event == NETDEV_REGISTER) { + net->ipv6.fib6_null_entry->fib6_nh.nh_dev = dev; net->ipv6.ip6_null_entry->dst.dev = dev; net->ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES @@ -5030,11 +5096,17 @@ static int __net_init ip6_route_net_init(struct net *net) if (dst_entries_init(&net->ipv6.ip6_dst_ops) < 0) goto out_ip6_dst_ops; + net->ipv6.fib6_null_entry = kmemdup(&fib6_null_entry_template, + sizeof(*net->ipv6.fib6_null_entry), + GFP_KERNEL); + if (!net->ipv6.fib6_null_entry) + goto out_ip6_dst_entries; + net->ipv6.ip6_null_entry = kmemdup(&ip6_null_entry_template, sizeof(*net->ipv6.ip6_null_entry), GFP_KERNEL); if (!net->ipv6.ip6_null_entry) - goto out_ip6_dst_entries; + goto out_fib6_null_entry; net->ipv6.ip6_null_entry->dst.ops = &net->ipv6.ip6_dst_ops; dst_init_metrics(&net->ipv6.ip6_null_entry->dst, ip6_template_metrics, true); @@ -5081,6 +5153,8 @@ out_ip6_prohibit_entry: out_ip6_null_entry: kfree(net->ipv6.ip6_null_entry); #endif +out_fib6_null_entry: + kfree(net->ipv6.fib6_null_entry); out_ip6_dst_entries: dst_entries_destroy(&net->ipv6.ip6_dst_ops); out_ip6_dst_ops: @@ -5089,6 +5163,7 @@ out_ip6_dst_ops: static void __net_exit ip6_route_net_exit(struct net *net) { + kfree(net->ipv6.fib6_null_entry); kfree(net->ipv6.ip6_null_entry); #ifdef CONFIG_IPV6_MULTIPLE_TABLES kfree(net->ipv6.ip6_prohibit_entry); @@ -5159,6 +5234,7 @@ void __init ip6_route_init_special_entries(void) /* Registering of the loopback is done before this portion of code, * the loopback reference in rt6_info will not be taken, do it * manually for init_net */ + init_net.ipv6.fib6_null_entry->fib6_nh.nh_dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->dst.dev = init_net.loopback_dev; init_net.ipv6.ip6_null_entry->rt6i_idev = in6_dev_get(init_net.loopback_dev); #ifdef CONFIG_IPV6_MULTIPLE_TABLES diff --git a/net/ipv6/seg6_iptunnel.c b/net/ipv6/seg6_iptunnel.c index 5fe139484919..eab39bd91548 100644 --- a/net/ipv6/seg6_iptunnel.c +++ b/net/ipv6/seg6_iptunnel.c @@ -91,6 +91,24 @@ static void set_tun_src(struct net *net, struct net_device *dev, rcu_read_unlock(); } +/* Compute flowlabel for outer IPv6 header */ +static __be32 seg6_make_flowlabel(struct net *net, struct sk_buff *skb, + struct ipv6hdr *inner_hdr) +{ + int do_flowlabel = net->ipv6.sysctl.seg6_flowlabel; + __be32 flowlabel = 0; + u32 hash; + + if (do_flowlabel > 0) { + hash = skb_get_hash(skb); + rol32(hash, 16); + flowlabel = (__force __be32)hash & IPV6_FLOWLABEL_MASK; + } else if (!do_flowlabel && skb->protocol == htons(ETH_P_IPV6)) { + flowlabel = ip6_flowlabel(inner_hdr); + } + return flowlabel; +} + /* encapsulate an IPv6 packet within an outer IPv6 header with a given SRH */ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) { @@ -99,6 +117,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) struct ipv6hdr *hdr, *inner_hdr; struct ipv6_sr_hdr *isrh; int hdrlen, tot_len, err; + __be32 flowlabel; hdrlen = (osrh->hdrlen + 1) << 3; tot_len = hdrlen + sizeof(*hdr); @@ -108,6 +127,7 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) return err; inner_hdr = ipv6_hdr(skb); + flowlabel = seg6_make_flowlabel(net, skb, inner_hdr); skb_push(skb, tot_len); skb_reset_network_header(skb); @@ -121,10 +141,10 @@ int seg6_do_srh_encap(struct sk_buff *skb, struct ipv6_sr_hdr *osrh, int proto) if (skb->protocol == htons(ETH_P_IPV6)) { ip6_flow_hdr(hdr, ip6_tclass(ip6_flowinfo(inner_hdr)), - ip6_flowlabel(inner_hdr)); + flowlabel); hdr->hop_limit = inner_hdr->hop_limit; } else { - ip6_flow_hdr(hdr, 0, 0); + ip6_flow_hdr(hdr, 0, flowlabel); hdr->hop_limit = ip6_dst_hoplimit(skb_dst(skb)); } diff --git a/net/ipv6/sysctl_net_ipv6.c b/net/ipv6/sysctl_net_ipv6.c index 6fbdef630152..e15cd37024fd 100644 --- a/net/ipv6/sysctl_net_ipv6.c +++ b/net/ipv6/sysctl_net_ipv6.c @@ -152,6 +152,13 @@ static struct ctl_table ipv6_table_template[] = { .extra1 = &zero, .extra2 = &one, }, + { + .procname = "seg6_flowlabel", + .data = &init_net.ipv6.sysctl.seg6_flowlabel, + .maxlen = sizeof(int), + .mode = 0644, + .proc_handler = proc_dointvec + }, { } }; @@ -217,6 +224,7 @@ static int __net_init ipv6_sysctl_net_init(struct net *net) ipv6_table[12].data = &net->ipv6.sysctl.max_dst_opts_len; ipv6_table[13].data = &net->ipv6.sysctl.max_hbh_opts_len; ipv6_table[14].data = &net->ipv6.sysctl.multipath_hash_policy, + ipv6_table[15].data = &net->ipv6.sysctl.seg6_flowlabel; ipv6_route_table = ipv6_route_sysctl_init(net); if (!ipv6_route_table) diff --git a/net/ipv6/tcp_ipv6.c b/net/ipv6/tcp_ipv6.c index 6d664d83cd16..7d47c2b550a9 100644 --- a/net/ipv6/tcp_ipv6.c +++ b/net/ipv6/tcp_ipv6.c @@ -803,6 +803,7 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 unsigned int tot_len = sizeof(struct tcphdr); struct dst_entry *dst; __be32 *topt; + __u32 mark = 0; if (tsecr) tot_len += TCPOLEN_TSTAMP_ALIGNED; @@ -871,7 +872,10 @@ static void tcp_v6_send_response(const struct sock *sk, struct sk_buff *skb, u32 fl6.flowi6_oif = oif; } - fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark); + if (sk) + mark = (sk->sk_state == TCP_TIME_WAIT) ? + inet_twsk(sk)->tw_mark : sk->sk_mark; + fl6.flowi6_mark = IP6_REPLY_MARK(net, skb->mark) ?: mark; fl6.fl6_dport = t1->dest; fl6.fl6_sport = t1->source; fl6.flowi6_uid = sock_net_uid(net, sk && sk_fullsock(sk) ? sk : NULL); diff --git a/net/ipv6/udp.c b/net/ipv6/udp.c index ea0730028e5d..2839c1bd1e58 100644 --- a/net/ipv6/udp.c +++ b/net/ipv6/udp.c @@ -546,10 +546,10 @@ static __inline__ void udpv6_err(struct sk_buff *skb, __udp6_lib_err(skb, opt, type, code, offset, info, &udp_table); } -static struct static_key udpv6_encap_needed __read_mostly; +static DEFINE_STATIC_KEY_FALSE(udpv6_encap_needed_key); void udpv6_encap_enable(void) { - static_key_enable(&udpv6_encap_needed); + static_branch_enable(&udpv6_encap_needed_key); } EXPORT_SYMBOL(udpv6_encap_enable); @@ -561,7 +561,7 @@ static int udpv6_queue_rcv_skb(struct sock *sk, struct sk_buff *skb) if (!xfrm6_policy_check(sk, XFRM_POLICY_IN, skb)) goto drop; - if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { int (*encap_rcv)(struct sock *sk, struct sk_buff *skb); /* @@ -1023,7 +1023,8 @@ static void udp6_hwcsum_outgoing(struct sock *sk, struct sk_buff *skb, * Sending */ -static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6) +static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6, + struct inet_cork *cork) { struct sock *sk = skb->sk; struct udphdr *uh; @@ -1042,12 +1043,31 @@ static int udp_v6_send_skb(struct sk_buff *skb, struct flowi6 *fl6) uh->len = htons(len); uh->check = 0; + if (cork->gso_size) { + const int hlen = skb_network_header_len(skb) + + sizeof(struct udphdr); + + if (hlen + cork->gso_size > cork->fragsize) + return -EINVAL; + if (skb->len > cork->gso_size * UDP_MAX_SEGMENTS) + return -EINVAL; + if (udp_sk(sk)->no_check6_tx) + return -EINVAL; + if (skb->ip_summed != CHECKSUM_PARTIAL || is_udplite) + return -EIO; + + skb_shinfo(skb)->gso_size = cork->gso_size; + skb_shinfo(skb)->gso_type = SKB_GSO_UDP_L4; + goto csum_partial; + } + if (is_udplite) csum = udplite_csum(skb); else if (udp_sk(sk)->no_check6_tx) { /* UDP csum disabled */ skb->ip_summed = CHECKSUM_NONE; goto send; } else if (skb->ip_summed == CHECKSUM_PARTIAL) { /* UDP hardware csum */ +csum_partial: udp6_hwcsum_outgoing(sk, skb, &fl6->saddr, &fl6->daddr, len); goto send; } else @@ -1093,7 +1113,7 @@ static int udp_v6_push_pending_frames(struct sock *sk) if (!skb) goto out; - err = udp_v6_send_skb(skb, &fl6); + err = udp_v6_send_skb(skb, &fl6, &inet_sk(sk)->cork.base); out: up->len = 0; @@ -1127,6 +1147,7 @@ int udpv6_sendmsg(struct sock *sk, struct msghdr *msg, size_t len) ipc6.hlimit = -1; ipc6.tclass = -1; ipc6.dontfrag = -1; + ipc6.gso_size = up->gso_size; sockc.tsflags = sk->sk_tsflags; /* destination address check */ @@ -1259,7 +1280,10 @@ do_udp_sendmsg: opt->tot_len = sizeof(*opt); ipc6.opt = opt; - err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, &ipc6, &sockc); + err = udp_cmsg_send(sk, msg, &ipc6.gso_size); + if (err > 0) + err = ip6_datagram_send_ctl(sock_net(sk), sk, msg, &fl6, + &ipc6, &sockc); if (err < 0) { fl6_sock_release(flowlabel); return err; @@ -1324,15 +1348,16 @@ back_from_confirm: /* Lockless fast path for the non-corking case */ if (!corkreq) { + struct inet_cork_full cork; struct sk_buff *skb; skb = ip6_make_skb(sk, getfrag, msg, ulen, sizeof(struct udphdr), &ipc6, &fl6, (struct rt6_info *)dst, - msg->msg_flags, &sockc); + msg->msg_flags, &cork, &sockc); err = PTR_ERR(skb); if (!IS_ERR_OR_NULL(skb)) - err = udp_v6_send_skb(skb, &fl6); + err = udp_v6_send_skb(skb, &fl6, &cork.base); goto out; } @@ -1402,7 +1427,7 @@ void udpv6_destroy_sock(struct sock *sk) udp_v6_flush_pending_frames(sk); release_sock(sk); - if (static_key_false(&udpv6_encap_needed) && up->encap_type) { + if (static_branch_unlikely(&udpv6_encap_needed_key) && up->encap_type) { void (*encap_destroy)(struct sock *sk); encap_destroy = READ_ONCE(up->encap_destroy); if (encap_destroy) diff --git a/net/ipv6/udp_offload.c b/net/ipv6/udp_offload.c index 2a04dc9c781b..03a2ff3fe1e6 100644 --- a/net/ipv6/udp_offload.c +++ b/net/ipv6/udp_offload.c @@ -42,12 +42,15 @@ static struct sk_buff *udp6_ufo_fragment(struct sk_buff *skb, const struct ipv6hdr *ipv6h; struct udphdr *uh; - if (!(skb_shinfo(skb)->gso_type & SKB_GSO_UDP)) + if (!(skb_shinfo(skb)->gso_type & (SKB_GSO_UDP | SKB_GSO_UDP_L4))) goto out; if (!pskb_may_pull(skb, sizeof(struct udphdr))) goto out; + if (skb_shinfo(skb)->gso_type & SKB_GSO_UDP_L4) + return __udp_gso_segment(skb, features); + /* Do software UFO. Complete and fill in the UDP checksum as HW cannot * do checksum of UDP packets sent as multiple IP fragments. */ diff --git a/net/ipv6/xfrm6_policy.c b/net/ipv6/xfrm6_policy.c index 416fe67271a9..2cff209d0fc1 100644 --- a/net/ipv6/xfrm6_policy.c +++ b/net/ipv6/xfrm6_policy.c @@ -107,8 +107,6 @@ static int xfrm6_fill_dst(struct xfrm_dst *xdst, struct net_device *dev, * it was magically lost, so this code needs audit */ xdst->u.rt6.rt6i_flags = rt->rt6i_flags & (RTF_ANYCAST | RTF_LOCAL); - xdst->u.rt6.rt6i_metric = rt->rt6i_metric; - xdst->u.rt6.rt6i_node = rt->rt6i_node; xdst->route_cookie = rt6_get_cookie(rt); xdst->u.rt6.rt6i_gateway = rt->rt6i_gateway; xdst->u.rt6.rt6i_dst = rt->rt6i_dst; diff --git a/net/ipv6/xfrm6_state.c b/net/ipv6/xfrm6_state.c index 16f434791763..5bdca3d5d6b7 100644 --- a/net/ipv6/xfrm6_state.c +++ b/net/ipv6/xfrm6_state.c @@ -60,11 +60,9 @@ xfrm6_init_temprop(struct xfrm_state *x, const struct xfrm_tmpl *tmpl, static int __xfrm6_sort(void **dst, void **src, int n, int (*cmp)(void *p), int maxclass) { - int i; + int count[XFRM_MAX_DEPTH] = { }; int class[XFRM_MAX_DEPTH]; - int count[maxclass]; - - memset(count, 0, sizeof(count)); + int i; for (i = 0; i < n; i++) { int c; diff --git a/net/l2tp/l2tp_debugfs.c b/net/l2tp/l2tp_debugfs.c index 7f1e842ef05a..e87686f7d63c 100644 --- a/net/l2tp/l2tp_debugfs.c +++ b/net/l2tp/l2tp_debugfs.c @@ -57,6 +57,10 @@ static void l2tp_dfs_next_tunnel(struct l2tp_dfs_seq_data *pd) static void l2tp_dfs_next_session(struct l2tp_dfs_seq_data *pd) { + /* Drop reference taken during previous invocation */ + if (pd->session) + l2tp_session_dec_refcount(pd->session); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); pd->session_idx++; @@ -105,11 +109,16 @@ static void l2tp_dfs_seq_stop(struct seq_file *p, void *v) if (!pd || pd == SEQ_START_TOKEN) return; - /* Drop reference taken by last invocation of l2tp_dfs_next_tunnel() */ + /* Drop reference taken by last invocation of l2tp_dfs_next_session() + * or l2tp_dfs_next_tunnel(). + */ + if (pd->session) { + l2tp_session_dec_refcount(pd->session); + pd->session = NULL; + } if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); pd->tunnel = NULL; - pd->session = NULL; } } @@ -250,13 +259,10 @@ static int l2tp_dfs_seq_show(struct seq_file *m, void *v) goto out; } - /* Show the tunnel or session context */ - if (!pd->session) { + if (!pd->session) l2tp_dfs_seq_tunnel_show(m, pd->tunnel); - } else { + else l2tp_dfs_seq_session_show(m, pd->session); - l2tp_session_dec_refcount(pd->session); - } out: return 0; diff --git a/net/l2tp/l2tp_ppp.c b/net/l2tp/l2tp_ppp.c index 1fd9e145076a..f951c768dcf2 100644 --- a/net/l2tp/l2tp_ppp.c +++ b/net/l2tp/l2tp_ppp.c @@ -1576,6 +1576,10 @@ static void pppol2tp_next_tunnel(struct net *net, struct pppol2tp_seq_data *pd) static void pppol2tp_next_session(struct net *net, struct pppol2tp_seq_data *pd) { + /* Drop reference taken during previous invocation */ + if (pd->session) + l2tp_session_dec_refcount(pd->session); + pd->session = l2tp_session_get_nth(pd->tunnel, pd->session_idx); pd->session_idx++; @@ -1624,11 +1628,16 @@ static void pppol2tp_seq_stop(struct seq_file *p, void *v) if (!pd || pd == SEQ_START_TOKEN) return; - /* Drop reference taken by last invocation of pppol2tp_next_tunnel() */ + /* Drop reference taken by last invocation of pppol2tp_next_session() + * or pppol2tp_next_tunnel(). + */ + if (pd->session) { + l2tp_session_dec_refcount(pd->session); + pd->session = NULL; + } if (pd->tunnel) { l2tp_tunnel_dec_refcount(pd->tunnel); pd->tunnel = NULL; - pd->session = NULL; } } @@ -1723,14 +1732,10 @@ static int pppol2tp_seq_show(struct seq_file *m, void *v) goto out; } - /* Show the tunnel or session context. - */ - if (!pd->session) { + if (!pd->session) pppol2tp_seq_tunnel_show(m, pd->tunnel); - } else { + else pppol2tp_seq_session_show(m, pd->session); - l2tp_session_dec_refcount(pd->session); - } out: return 0; diff --git a/net/ncsi/internal.h b/net/ncsi/internal.h index 8da84312cd3b..8055e3965cef 100644 --- a/net/ncsi/internal.h +++ b/net/ncsi/internal.h @@ -68,15 +68,6 @@ enum { NCSI_MODE_MAX }; -enum { - NCSI_FILTER_BASE = 0, - NCSI_FILTER_VLAN = 0, - NCSI_FILTER_UC, - NCSI_FILTER_MC, - NCSI_FILTER_MIXED, - NCSI_FILTER_MAX -}; - struct ncsi_channel_version { u32 version; /* Supported BCD encoded NCSI version */ u32 alpha2; /* Supported BCD encoded NCSI version */ @@ -98,11 +89,18 @@ struct ncsi_channel_mode { u32 data[8]; /* Data entries */ }; -struct ncsi_channel_filter { - u32 index; /* Index of channel filters */ - u32 total; /* Total entries in the filter table */ - u64 bitmap; /* Bitmap of valid entries */ - u32 data[]; /* Data for the valid entries */ +struct ncsi_channel_mac_filter { + u8 n_uc; + u8 n_mc; + u8 n_mixed; + u64 bitmap; + unsigned char *addrs; +}; + +struct ncsi_channel_vlan_filter { + u8 n_vids; + u64 bitmap; + u16 *vids; }; struct ncsi_channel_stats { @@ -186,7 +184,9 @@ struct ncsi_channel { struct ncsi_channel_version version; struct ncsi_channel_cap caps[NCSI_CAP_MAX]; struct ncsi_channel_mode modes[NCSI_MODE_MAX]; - struct ncsi_channel_filter *filters[NCSI_FILTER_MAX]; + /* Filtering Settings */ + struct ncsi_channel_mac_filter mac_filter; + struct ncsi_channel_vlan_filter vlan_filter; struct ncsi_channel_stats stats; struct { struct timer_list timer; @@ -320,10 +320,6 @@ extern spinlock_t ncsi_dev_lock; list_for_each_entry_rcu(nc, &np->channels, node) /* Resources */ -u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index); -int ncsi_find_filter(struct ncsi_channel *nc, int table, void *data); -int ncsi_add_filter(struct ncsi_channel *nc, int table, void *data); -int ncsi_remove_filter(struct ncsi_channel *nc, int table, int index); void ncsi_start_channel_monitor(struct ncsi_channel *nc); void ncsi_stop_channel_monitor(struct ncsi_channel *nc); struct ncsi_channel *ncsi_find_channel(struct ncsi_package *np, diff --git a/net/ncsi/ncsi-manage.c b/net/ncsi/ncsi-manage.c index c3695ba0cf94..5561e221b71f 100644 --- a/net/ncsi/ncsi-manage.c +++ b/net/ncsi/ncsi-manage.c @@ -27,125 +27,6 @@ LIST_HEAD(ncsi_dev_list); DEFINE_SPINLOCK(ncsi_dev_lock); -static inline int ncsi_filter_size(int table) -{ - int sizes[] = { 2, 6, 6, 6 }; - - BUILD_BUG_ON(ARRAY_SIZE(sizes) != NCSI_FILTER_MAX); - if (table < NCSI_FILTER_BASE || table >= NCSI_FILTER_MAX) - return -EINVAL; - - return sizes[table]; -} - -u32 *ncsi_get_filter(struct ncsi_channel *nc, int table, int index) -{ - struct ncsi_channel_filter *ncf; - int size; - - ncf = nc->filters[table]; - if (!ncf) - return NULL; - - size = ncsi_filter_size(table); - if (size < 0) - return NULL; - - return ncf->data + size * index; -} - -/* Find the first active filter in a filter table that matches the given - * data parameter. If data is NULL, this returns the first active filter. - */ -int ncsi_find_filter(struct ncsi_channel *nc, int table, void *data) -{ - struct ncsi_channel_filter *ncf; - void *bitmap; - int index, size; - unsigned long flags; - - ncf = nc->filters[table]; - if (!ncf) - return -ENXIO; - - size = ncsi_filter_size(table); - if (size < 0) - return size; - - spin_lock_irqsave(&nc->lock, flags); - bitmap = (void *)&ncf->bitmap; - index = -1; - while ((index = find_next_bit(bitmap, ncf->total, index + 1)) - < ncf->total) { - if (!data || !memcmp(ncf->data + size * index, data, size)) { - spin_unlock_irqrestore(&nc->lock, flags); - return index; - } - } - spin_unlock_irqrestore(&nc->lock, flags); - - return -ENOENT; -} - -int ncsi_add_filter(struct ncsi_channel *nc, int table, void *data) -{ - struct ncsi_channel_filter *ncf; - int index, size; - void *bitmap; - unsigned long flags; - - size = ncsi_filter_size(table); - if (size < 0) - return size; - - index = ncsi_find_filter(nc, table, data); - if (index >= 0) - return index; - - ncf = nc->filters[table]; - if (!ncf) - return -ENODEV; - - spin_lock_irqsave(&nc->lock, flags); - bitmap = (void *)&ncf->bitmap; - do { - index = find_next_zero_bit(bitmap, ncf->total, 0); - if (index >= ncf->total) { - spin_unlock_irqrestore(&nc->lock, flags); - return -ENOSPC; - } - } while (test_and_set_bit(index, bitmap)); - - memcpy(ncf->data + size * index, data, size); - spin_unlock_irqrestore(&nc->lock, flags); - - return index; -} - -int ncsi_remove_filter(struct ncsi_channel *nc, int table, int index) -{ - struct ncsi_channel_filter *ncf; - int size; - void *bitmap; - unsigned long flags; - - size = ncsi_filter_size(table); - if (size < 0) - return size; - - ncf = nc->filters[table]; - if (!ncf || index >= ncf->total) - return -ENODEV; - - spin_lock_irqsave(&nc->lock, flags); - bitmap = (void *)&ncf->bitmap; - if (test_and_clear_bit(index, bitmap)) - memset(ncf->data + size * index, 0, size); - spin_unlock_irqrestore(&nc->lock, flags); - - return 0; -} - static void ncsi_report_link(struct ncsi_dev_priv *ndp, bool force_down) { struct ncsi_dev *nd = &ndp->ndev; @@ -339,20 +220,13 @@ struct ncsi_channel *ncsi_add_channel(struct ncsi_package *np, unsigned char id) static void ncsi_remove_channel(struct ncsi_channel *nc) { struct ncsi_package *np = nc->package; - struct ncsi_channel_filter *ncf; unsigned long flags; - int i; - /* Release filters */ spin_lock_irqsave(&nc->lock, flags); - for (i = 0; i < NCSI_FILTER_MAX; i++) { - ncf = nc->filters[i]; - if (!ncf) - continue; - nc->filters[i] = NULL; - kfree(ncf); - } + /* Release filters */ + kfree(nc->mac_filter.addrs); + kfree(nc->vlan_filter.vids); nc->state = NCSI_CHANNEL_INACTIVE; spin_unlock_irqrestore(&nc->lock, flags); @@ -670,32 +544,26 @@ error: static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, struct ncsi_cmd_arg *nca) { + struct ncsi_channel_vlan_filter *ncf; + unsigned long flags; + void *bitmap; int index; - u32 *data; u16 vid; - index = ncsi_find_filter(nc, NCSI_FILTER_VLAN, NULL); - if (index < 0) { - /* Filter table empty */ - return -1; - } + ncf = &nc->vlan_filter; + bitmap = &ncf->bitmap; - data = ncsi_get_filter(nc, NCSI_FILTER_VLAN, index); - if (!data) { - netdev_err(ndp->ndev.dev, - "NCSI: failed to retrieve filter %d\n", index); - /* Set the VLAN id to 0 - this will still disable the entry in - * the filter table, but we won't know what it was. - */ - vid = 0; - } else { - vid = *(u16 *)data; + spin_lock_irqsave(&nc->lock, flags); + index = find_next_bit(bitmap, ncf->n_vids, 0); + if (index >= ncf->n_vids) { + spin_unlock_irqrestore(&nc->lock, flags); + return -1; } + vid = ncf->vids[index]; - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: removed vlan tag %u at index %d\n", - vid, index + 1); - ncsi_remove_filter(nc, NCSI_FILTER_VLAN, index); + clear_bit(index, bitmap); + ncf->vids[index] = 0; + spin_unlock_irqrestore(&nc->lock, flags); nca->type = NCSI_PKT_CMD_SVF; nca->words[1] = vid; @@ -711,45 +579,55 @@ static int clear_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, static int set_one_vid(struct ncsi_dev_priv *ndp, struct ncsi_channel *nc, struct ncsi_cmd_arg *nca) { + struct ncsi_channel_vlan_filter *ncf; struct vlan_vid *vlan = NULL; - int index = 0; + unsigned long flags; + int i, index; + void *bitmap; + u16 vid; + if (list_empty(&ndp->vlan_vids)) + return -1; + + ncf = &nc->vlan_filter; + bitmap = &ncf->bitmap; + + spin_lock_irqsave(&nc->lock, flags); + + rcu_read_lock(); list_for_each_entry_rcu(vlan, &ndp->vlan_vids, list) { - index = ncsi_find_filter(nc, NCSI_FILTER_VLAN, &vlan->vid); - if (index < 0) { - /* New tag to add */ - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: new vlan id to set: %u\n", - vlan->vid); + vid = vlan->vid; + for (i = 0; i < ncf->n_vids; i++) + if (ncf->vids[i] == vid) { + vid = 0; + break; + } + if (vid) break; - } - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "vid %u already at filter pos %d\n", - vlan->vid, index); } + rcu_read_unlock(); - if (!vlan || index >= 0) { - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "no vlan ids left to set\n"); + if (!vid) { + /* No VLAN ID is not set */ + spin_unlock_irqrestore(&nc->lock, flags); return -1; } - index = ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan->vid); - if (index < 0) { + index = find_next_zero_bit(bitmap, ncf->n_vids, 0); + if (index < 0 || index >= ncf->n_vids) { netdev_err(ndp->ndev.dev, - "Failed to add new VLAN tag, error %d\n", index); - if (index == -ENOSPC) - netdev_err(ndp->ndev.dev, - "Channel %u already has all VLAN filters set\n", - nc->id); + "Channel %u already has all VLAN filters set\n", + nc->id); + spin_unlock_irqrestore(&nc->lock, flags); return -1; } - netdev_printk(KERN_DEBUG, ndp->ndev.dev, - "NCSI: set vid %u in packet, index %u\n", - vlan->vid, index + 1); + ncf->vids[index] = vid; + set_bit(index, bitmap); + spin_unlock_irqrestore(&nc->lock, flags); + nca->type = NCSI_PKT_CMD_SVF; - nca->words[1] = vlan->vid; + nca->words[1] = vid; /* HW filter index starts at 1 */ nca->bytes[6] = index + 1; nca->bytes[7] = 0x01; diff --git a/net/ncsi/ncsi-netlink.c b/net/ncsi/ncsi-netlink.c index 8d7e849d4825..b09ef77bf4cd 100644 --- a/net/ncsi/ncsi-netlink.c +++ b/net/ncsi/ncsi-netlink.c @@ -58,10 +58,9 @@ static int ncsi_write_channel_info(struct sk_buff *skb, struct ncsi_dev_priv *ndp, struct ncsi_channel *nc) { - struct nlattr *vid_nest; - struct ncsi_channel_filter *ncf; + struct ncsi_channel_vlan_filter *ncf; struct ncsi_channel_mode *m; - u32 *data; + struct nlattr *vid_nest; int i; nla_put_u32(skb, NCSI_CHANNEL_ATTR_ID, nc->id); @@ -79,18 +78,13 @@ static int ncsi_write_channel_info(struct sk_buff *skb, vid_nest = nla_nest_start(skb, NCSI_CHANNEL_ATTR_VLAN_LIST); if (!vid_nest) return -ENOMEM; - ncf = nc->filters[NCSI_FILTER_VLAN]; + ncf = &nc->vlan_filter; i = -1; - if (ncf) { - while ((i = find_next_bit((void *)&ncf->bitmap, ncf->total, - i + 1)) < ncf->total) { - data = ncsi_get_filter(nc, NCSI_FILTER_VLAN, i); - /* Uninitialised channels will have 'zero' vlan ids */ - if (!data || !*data) - continue; + while ((i = find_next_bit((void *)&ncf->bitmap, ncf->n_vids, + i + 1)) < ncf->n_vids) { + if (ncf->vids[i]) nla_put_u16(skb, NCSI_CHANNEL_ATTR_VLAN_ID, - *(u16 *)data); - } + ncf->vids[i]); } nla_nest_end(skb, vid_nest); diff --git a/net/ncsi/ncsi-rsp.c b/net/ncsi/ncsi-rsp.c index efd933ff5570..ce9497966ebe 100644 --- a/net/ncsi/ncsi-rsp.c +++ b/net/ncsi/ncsi-rsp.c @@ -334,9 +334,9 @@ static int ncsi_rsp_handler_svf(struct ncsi_request *nr) struct ncsi_rsp_pkt *rsp; struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_channel *nc; - struct ncsi_channel_filter *ncf; - unsigned short vlan; - int ret; + struct ncsi_channel_vlan_filter *ncf; + unsigned long flags; + void *bitmap; /* Find the package and channel */ rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); @@ -346,22 +346,23 @@ static int ncsi_rsp_handler_svf(struct ncsi_request *nr) return -ENODEV; cmd = (struct ncsi_cmd_svf_pkt *)skb_network_header(nr->cmd); - ncf = nc->filters[NCSI_FILTER_VLAN]; - if (!ncf) - return -ENOENT; - if (cmd->index >= ncf->total) + ncf = &nc->vlan_filter; + if (cmd->index > ncf->n_vids) return -ERANGE; - /* Add or remove the VLAN filter */ + /* Add or remove the VLAN filter. Remember HW indexes from 1 */ + spin_lock_irqsave(&nc->lock, flags); + bitmap = &ncf->bitmap; if (!(cmd->enable & 0x1)) { - /* HW indexes from 1 */ - ret = ncsi_remove_filter(nc, NCSI_FILTER_VLAN, cmd->index - 1); + if (test_and_clear_bit(cmd->index - 1, bitmap)) + ncf->vids[cmd->index - 1] = 0; } else { - vlan = ntohs(cmd->vlan); - ret = ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan); + set_bit(cmd->index - 1, bitmap); + ncf->vids[cmd->index - 1] = ntohs(cmd->vlan); } + spin_unlock_irqrestore(&nc->lock, flags); - return ret; + return 0; } static int ncsi_rsp_handler_ev(struct ncsi_request *nr) @@ -422,8 +423,12 @@ static int ncsi_rsp_handler_sma(struct ncsi_request *nr) struct ncsi_rsp_pkt *rsp; struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_channel *nc; - struct ncsi_channel_filter *ncf; + struct ncsi_channel_mac_filter *ncf; + unsigned long flags; void *bitmap; + bool enabled; + int index; + /* Find the package and channel */ rsp = (struct ncsi_rsp_pkt *)skb_network_header(nr->rsp); @@ -436,31 +441,23 @@ static int ncsi_rsp_handler_sma(struct ncsi_request *nr) * isn't supported yet. */ cmd = (struct ncsi_cmd_sma_pkt *)skb_network_header(nr->cmd); - switch (cmd->at_e >> 5) { - case 0x0: /* UC address */ - ncf = nc->filters[NCSI_FILTER_UC]; - break; - case 0x1: /* MC address */ - ncf = nc->filters[NCSI_FILTER_MC]; - break; - default: - return -EINVAL; - } + enabled = cmd->at_e & 0x1; + ncf = &nc->mac_filter; + bitmap = &ncf->bitmap; - /* Sanity check on the filter */ - if (!ncf) - return -ENOENT; - else if (cmd->index >= ncf->total) + if (cmd->index > ncf->n_uc + ncf->n_mc + ncf->n_mixed) return -ERANGE; - bitmap = &ncf->bitmap; - if (cmd->at_e & 0x1) { - set_bit(cmd->index, bitmap); - memcpy(ncf->data + 6 * cmd->index, cmd->mac, 6); + index = (cmd->index - 1) * ETH_ALEN; + spin_lock_irqsave(&nc->lock, flags); + if (enabled) { + set_bit(cmd->index - 1, bitmap); + memcpy(&ncf->addrs[index], cmd->mac, ETH_ALEN); } else { - clear_bit(cmd->index, bitmap); - memset(ncf->data + 6 * cmd->index, 0, 6); + clear_bit(cmd->index - 1, bitmap); + memset(&ncf->addrs[index], 0, ETH_ALEN); } + spin_unlock_irqrestore(&nc->lock, flags); return 0; } @@ -631,9 +628,7 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) struct ncsi_rsp_gc_pkt *rsp; struct ncsi_dev_priv *ndp = nr->ndp; struct ncsi_channel *nc; - struct ncsi_channel_filter *ncf; - size_t size, entry_size; - int cnt, i; + size_t size; /* Find the channel */ rsp = (struct ncsi_rsp_gc_pkt *)skb_network_header(nr->rsp); @@ -655,64 +650,40 @@ static int ncsi_rsp_handler_gc(struct ncsi_request *nr) nc->caps[NCSI_CAP_VLAN].cap = rsp->vlan_mode & NCSI_CAP_VLAN_MASK; - /* Build filters */ - for (i = 0; i < NCSI_FILTER_MAX; i++) { - switch (i) { - case NCSI_FILTER_VLAN: - cnt = rsp->vlan_cnt; - entry_size = 2; - break; - case NCSI_FILTER_MIXED: - cnt = rsp->mixed_cnt; - entry_size = 6; - break; - case NCSI_FILTER_MC: - cnt = rsp->mc_cnt; - entry_size = 6; - break; - case NCSI_FILTER_UC: - cnt = rsp->uc_cnt; - entry_size = 6; - break; - default: - continue; - } - - if (!cnt || nc->filters[i]) - continue; - - size = sizeof(*ncf) + cnt * entry_size; - ncf = kzalloc(size, GFP_ATOMIC); - if (!ncf) { - pr_warn("%s: Cannot alloc filter table (%d)\n", - __func__, i); - return -ENOMEM; - } - - ncf->index = i; - ncf->total = cnt; - if (i == NCSI_FILTER_VLAN) { - /* Set VLAN filters active so they are cleared in - * first configuration state - */ - ncf->bitmap = U64_MAX; - } else { - ncf->bitmap = 0x0ul; - } - nc->filters[i] = ncf; - } + size = (rsp->uc_cnt + rsp->mc_cnt + rsp->mixed_cnt) * ETH_ALEN; + nc->mac_filter.addrs = kzalloc(size, GFP_KERNEL); + if (!nc->mac_filter.addrs) + return -ENOMEM; + nc->mac_filter.n_uc = rsp->uc_cnt; + nc->mac_filter.n_mc = rsp->mc_cnt; + nc->mac_filter.n_mixed = rsp->mixed_cnt; + + nc->vlan_filter.vids = kcalloc(rsp->vlan_cnt, + sizeof(*nc->vlan_filter.vids), + GFP_KERNEL); + if (!nc->vlan_filter.vids) + return -ENOMEM; + /* Set VLAN filters active so they are cleared in the first + * configuration state + */ + nc->vlan_filter.bitmap = U64_MAX; + nc->vlan_filter.n_vids = rsp->vlan_cnt; return 0; } static int ncsi_rsp_handler_gp(struct ncsi_request *nr) { - struct ncsi_rsp_gp_pkt *rsp; + struct ncsi_channel_vlan_filter *ncvf; + struct ncsi_channel_mac_filter *ncmf; struct ncsi_dev_priv *ndp = nr->ndp; + struct ncsi_rsp_gp_pkt *rsp; struct ncsi_channel *nc; - unsigned short enable, vlan; + unsigned short enable; unsigned char *pdata; - int table, i; + unsigned long flags; + void *bitmap; + int i; /* Find the channel */ rsp = (struct ncsi_rsp_gp_pkt *)skb_network_header(nr->rsp); @@ -746,36 +717,33 @@ static int ncsi_rsp_handler_gp(struct ncsi_request *nr) /* MAC addresses filter table */ pdata = (unsigned char *)rsp + 48; enable = rsp->mac_enable; + ncmf = &nc->mac_filter; + spin_lock_irqsave(&nc->lock, flags); + bitmap = &ncmf->bitmap; for (i = 0; i < rsp->mac_cnt; i++, pdata += 6) { - if (i >= (nc->filters[NCSI_FILTER_UC]->total + - nc->filters[NCSI_FILTER_MC]->total)) - table = NCSI_FILTER_MIXED; - else if (i >= nc->filters[NCSI_FILTER_UC]->total) - table = NCSI_FILTER_MC; - else - table = NCSI_FILTER_UC; - if (!(enable & (0x1 << i))) - continue; - - if (ncsi_find_filter(nc, table, pdata) >= 0) - continue; + clear_bit(i, bitmap); + else + set_bit(i, bitmap); - ncsi_add_filter(nc, table, pdata); + memcpy(&ncmf->addrs[i * ETH_ALEN], pdata, ETH_ALEN); } + spin_unlock_irqrestore(&nc->lock, flags); /* VLAN filter table */ enable = ntohs(rsp->vlan_enable); + ncvf = &nc->vlan_filter; + bitmap = &ncvf->bitmap; + spin_lock_irqsave(&nc->lock, flags); for (i = 0; i < rsp->vlan_cnt; i++, pdata += 2) { if (!(enable & (0x1 << i))) - continue; - - vlan = ntohs(*(__be16 *)pdata); - if (ncsi_find_filter(nc, NCSI_FILTER_VLAN, &vlan) >= 0) - continue; + clear_bit(i, bitmap); + else + set_bit(i, bitmap); - ncsi_add_filter(nc, NCSI_FILTER_VLAN, &vlan); + ncvf->vids[i] = ntohs(*(__be16 *)pdata); } + spin_unlock_irqrestore(&nc->lock, flags); return 0; } diff --git a/net/netfilter/Kconfig b/net/netfilter/Kconfig index 44d8a55e9721..e57c9d479503 100644 --- a/net/netfilter/Kconfig +++ b/net/netfilter/Kconfig @@ -444,6 +444,9 @@ config NETFILTER_SYNPROXY endif # NF_CONNTRACK +config NF_OSF + tristate 'Passive OS fingerprint infrastructure' + config NF_TABLES select NETFILTER_NETLINK tristate "Netfilter nf_tables support" @@ -474,24 +477,6 @@ config NF_TABLES_NETDEV help This option enables support for the "netdev" table. -config NFT_EXTHDR - tristate "Netfilter nf_tables exthdr module" - help - This option adds the "exthdr" expression that you can use to match - IPv6 extension headers and tcp options. - -config NFT_META - tristate "Netfilter nf_tables meta module" - help - This option adds the "meta" expression that you can use to match and - to set packet metainformation such as the packet mark. - -config NFT_RT - tristate "Netfilter nf_tables routing module" - help - This option adds the "rt" expression that you can use to match - packet routing information such as the packet nexthop. - config NFT_NUMGEN tristate "Netfilter nf_tables number generator module" help @@ -667,8 +652,7 @@ endif # NF_TABLES config NF_FLOW_TABLE_INET tristate "Netfilter flow table mixed IPv4/IPv6 module" - depends on NF_FLOW_TABLE_IPV4 - depends on NF_FLOW_TABLE_IPV6 + depends on NF_FLOW_TABLE help This option adds the flow table mixed IPv4/IPv6 support. @@ -1378,6 +1362,7 @@ config NETFILTER_XT_MATCH_NFACCT config NETFILTER_XT_MATCH_OSF tristate '"osf" Passive OS fingerprint match' depends on NETFILTER_ADVANCED && NETFILTER_NETLINK + select NF_OSF help This option selects the Passive OS Fingerprinting match module that allows to passively match the remote operating system by diff --git a/net/netfilter/Makefile b/net/netfilter/Makefile index fd32bd2c9521..1aa710b5d384 100644 --- a/net/netfilter/Makefile +++ b/net/netfilter/Makefile @@ -76,13 +76,10 @@ obj-$(CONFIG_NF_DUP_NETDEV) += nf_dup_netdev.o nf_tables-objs := nf_tables_core.o nf_tables_api.o nft_chain_filter.o \ nf_tables_trace.o nft_immediate.o nft_cmp.o nft_range.o \ nft_bitwise.o nft_byteorder.o nft_payload.o nft_lookup.o \ - nft_dynset.o + nft_dynset.o nft_meta.o nft_rt.o nft_exthdr.o obj-$(CONFIG_NF_TABLES) += nf_tables.o obj-$(CONFIG_NFT_COMPAT) += nft_compat.o -obj-$(CONFIG_NFT_EXTHDR) += nft_exthdr.o -obj-$(CONFIG_NFT_META) += nft_meta.o -obj-$(CONFIG_NFT_RT) += nft_rt.o obj-$(CONFIG_NFT_NUMGEN) += nft_numgen.o obj-$(CONFIG_NFT_CT) += nft_ct.o obj-$(CONFIG_NFT_FLOW_OFFLOAD) += nft_flow_offload.o @@ -104,6 +101,7 @@ obj-$(CONFIG_NFT_HASH) += nft_hash.o obj-$(CONFIG_NFT_FIB) += nft_fib.o obj-$(CONFIG_NFT_FIB_INET) += nft_fib_inet.o obj-$(CONFIG_NFT_FIB_NETDEV) += nft_fib_netdev.o +obj-$(CONFIG_NF_OSF) += nf_osf.o # nf_tables netdev obj-$(CONFIG_NFT_DUP_NETDEV) += nft_dup_netdev.o @@ -111,6 +109,8 @@ obj-$(CONFIG_NFT_FWD_NETDEV) += nft_fwd_netdev.o # flow table infrastructure obj-$(CONFIG_NF_FLOW_TABLE) += nf_flow_table.o +nf_flow_table-objs := nf_flow_table_core.o nf_flow_table_ip.o + obj-$(CONFIG_NF_FLOW_TABLE_INET) += nf_flow_table_inet.o # generic X tables diff --git a/net/netfilter/ipvs/Kconfig b/net/netfilter/ipvs/Kconfig index b32fb0dbe237..05dc1b77e466 100644 --- a/net/netfilter/ipvs/Kconfig +++ b/net/netfilter/ipvs/Kconfig @@ -225,6 +225,25 @@ config IP_VS_SH If you want to compile it in kernel, say Y. To compile it as a module, choose M here. If unsure, say N. +config IP_VS_MH + tristate "maglev hashing scheduling" + ---help--- + The maglev consistent hashing scheduling algorithm provides the + Google's Maglev hashing algorithm as a IPVS scheduler. It assigns + network connections to the servers through looking up a statically + assigned special hash table called the lookup table. Maglev hashing + is to assign a preference list of all the lookup table positions + to each destination. + + Through this operation, The maglev hashing gives an almost equal + share of the lookup table to each of the destinations and provides + minimal disruption by using the lookup table. When the set of + destinations changes, a connection will likely be sent to the same + destination as it was before. + + If you want to compile it in kernel, say Y. To compile it as a + module, choose M here. If unsure, say N. + config IP_VS_SED tristate "shortest expected delay scheduling" ---help--- @@ -266,6 +285,24 @@ config IP_VS_SH_TAB_BITS needs to be large enough to effectively fit all the destinations multiplied by their respective weights. +comment 'IPVS MH scheduler' + +config IP_VS_MH_TAB_INDEX + int "IPVS maglev hashing table index of size (the prime numbers)" + range 8 17 + default 12 + ---help--- + The maglev hashing scheduler maps source IPs to destinations + stored in a hash table. This table is assigned by a preference + list of the positions to each destination until all slots in + the table are filled. The index determines the prime for size of + the table as 251, 509, 1021, 2039, 4093, 8191, 16381, 32749, + 65521 or 131071. When using weights to allow destinations to + receive more connections, the table is assigned an amount + proportional to the weights specified. The table needs to be large + enough to effectively fit all the destinations multiplied by their + respective weights. + comment 'IPVS application helper' config IP_VS_FTP diff --git a/net/netfilter/ipvs/Makefile b/net/netfilter/ipvs/Makefile index c552993fa4b9..bfce2677fda2 100644 --- a/net/netfilter/ipvs/Makefile +++ b/net/netfilter/ipvs/Makefile @@ -33,6 +33,7 @@ obj-$(CONFIG_IP_VS_LBLC) += ip_vs_lblc.o obj-$(CONFIG_IP_VS_LBLCR) += ip_vs_lblcr.o obj-$(CONFIG_IP_VS_DH) += ip_vs_dh.o obj-$(CONFIG_IP_VS_SH) += ip_vs_sh.o +obj-$(CONFIG_IP_VS_MH) += ip_vs_mh.o obj-$(CONFIG_IP_VS_SED) += ip_vs_sed.o obj-$(CONFIG_IP_VS_NQ) += ip_vs_nq.o diff --git a/net/netfilter/ipvs/ip_vs_ctl.c b/net/netfilter/ipvs/ip_vs_ctl.c index f36098887ad0..d4f68d0f7df7 100644 --- a/net/netfilter/ipvs/ip_vs_ctl.c +++ b/net/netfilter/ipvs/ip_vs_ctl.c @@ -821,6 +821,10 @@ __ip_vs_update_dest(struct ip_vs_service *svc, struct ip_vs_dest *dest, if (add && udest->af != svc->af) ipvs->mixed_address_family_dests++; + /* keep the last_weight with latest non-0 weight */ + if (add || udest->weight != 0) + atomic_set(&dest->last_weight, udest->weight); + /* set the weight and the flags */ atomic_set(&dest->weight, udest->weight); conn_flags = udest->conn_flags & IP_VS_CONN_F_DEST_MASK; diff --git a/net/netfilter/ipvs/ip_vs_dh.c b/net/netfilter/ipvs/ip_vs_dh.c index 75f798f8e83b..07459e71d907 100644 --- a/net/netfilter/ipvs/ip_vs_dh.c +++ b/net/netfilter/ipvs/ip_vs_dh.c @@ -43,6 +43,7 @@ #include <linux/module.h> #include <linux/kernel.h> #include <linux/skbuff.h> +#include <linux/hash.h> #include <net/ip_vs.h> @@ -81,7 +82,7 @@ static inline unsigned int ip_vs_dh_hashkey(int af, const union nf_inet_addr *ad addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (ntohl(addr_fold)*2654435761UL) & IP_VS_DH_TAB_MASK; + return hash_32(ntohl(addr_fold), IP_VS_DH_TAB_BITS); } diff --git a/net/netfilter/ipvs/ip_vs_lblc.c b/net/netfilter/ipvs/ip_vs_lblc.c index 3057e453bf31..b9f375e6dc93 100644 --- a/net/netfilter/ipvs/ip_vs_lblc.c +++ b/net/netfilter/ipvs/ip_vs_lblc.c @@ -48,6 +48,7 @@ #include <linux/kernel.h> #include <linux/skbuff.h> #include <linux/jiffies.h> +#include <linux/hash.h> /* for sysctl */ #include <linux/fs.h> @@ -160,7 +161,7 @@ ip_vs_lblc_hashkey(int af, const union nf_inet_addr *addr) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLC_TAB_MASK; + return hash_32(ntohl(addr_fold), IP_VS_LBLC_TAB_BITS); } @@ -371,6 +372,7 @@ static int ip_vs_lblc_init_svc(struct ip_vs_service *svc) tbl->counter = 1; tbl->dead = false; tbl->svc = svc; + atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection diff --git a/net/netfilter/ipvs/ip_vs_lblcr.c b/net/netfilter/ipvs/ip_vs_lblcr.c index 92adc04557ed..542c4949937a 100644 --- a/net/netfilter/ipvs/ip_vs_lblcr.c +++ b/net/netfilter/ipvs/ip_vs_lblcr.c @@ -47,6 +47,7 @@ #include <linux/jiffies.h> #include <linux/list.h> #include <linux/slab.h> +#include <linux/hash.h> /* for sysctl */ #include <linux/fs.h> @@ -323,7 +324,7 @@ ip_vs_lblcr_hashkey(int af, const union nf_inet_addr *addr) addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (ntohl(addr_fold)*2654435761UL) & IP_VS_LBLCR_TAB_MASK; + return hash_32(ntohl(addr_fold), IP_VS_LBLCR_TAB_BITS); } @@ -534,6 +535,7 @@ static int ip_vs_lblcr_init_svc(struct ip_vs_service *svc) tbl->counter = 1; tbl->dead = false; tbl->svc = svc; + atomic_set(&tbl->entries, 0); /* * Hook periodic timer for garbage collection diff --git a/net/netfilter/ipvs/ip_vs_mh.c b/net/netfilter/ipvs/ip_vs_mh.c new file mode 100644 index 000000000000..0f795b186eb3 --- /dev/null +++ b/net/netfilter/ipvs/ip_vs_mh.c @@ -0,0 +1,540 @@ +// SPDX-License-Identifier: GPL-2.0 +/* IPVS: Maglev Hashing scheduling module + * + * Authors: Inju Song <inju.song@navercorp.com> + * + */ + +/* The mh algorithm is to assign a preference list of all the lookup + * table positions to each destination and populate the table with + * the most-preferred position of destinations. Then it is to select + * destination with the hash key of source IP address through looking + * up a the lookup table. + * + * The algorithm is detailed in: + * [3.4 Consistent Hasing] +https://www.usenix.org/system/files/conference/nsdi16/nsdi16-paper-eisenbud.pdf + * + */ + +#define KMSG_COMPONENT "IPVS" +#define pr_fmt(fmt) KMSG_COMPONENT ": " fmt + +#include <linux/ip.h> +#include <linux/slab.h> +#include <linux/module.h> +#include <linux/kernel.h> +#include <linux/skbuff.h> + +#include <net/ip_vs.h> + +#include <linux/siphash.h> +#include <linux/bitops.h> +#include <linux/gcd.h> + +#define IP_VS_SVC_F_SCHED_MH_FALLBACK IP_VS_SVC_F_SCHED1 /* MH fallback */ +#define IP_VS_SVC_F_SCHED_MH_PORT IP_VS_SVC_F_SCHED2 /* MH use port */ + +struct ip_vs_mh_lookup { + struct ip_vs_dest __rcu *dest; /* real server (cache) */ +}; + +struct ip_vs_mh_dest_setup { + unsigned int offset; /* starting offset */ + unsigned int skip; /* skip */ + unsigned int perm; /* next_offset */ + int turns; /* weight / gcd() and rshift */ +}; + +/* Available prime numbers for MH table */ +static int primes[] = {251, 509, 1021, 2039, 4093, + 8191, 16381, 32749, 65521, 131071}; + +/* For IPVS MH entry hash table */ +#ifndef CONFIG_IP_VS_MH_TAB_INDEX +#define CONFIG_IP_VS_MH_TAB_INDEX 12 +#endif +#define IP_VS_MH_TAB_BITS (CONFIG_IP_VS_MH_TAB_INDEX / 2) +#define IP_VS_MH_TAB_INDEX (CONFIG_IP_VS_MH_TAB_INDEX - 8) +#define IP_VS_MH_TAB_SIZE primes[IP_VS_MH_TAB_INDEX] + +struct ip_vs_mh_state { + struct rcu_head rcu_head; + struct ip_vs_mh_lookup *lookup; + struct ip_vs_mh_dest_setup *dest_setup; + hsiphash_key_t hash1, hash2; + int gcd; + int rshift; +}; + +static inline void generate_hash_secret(hsiphash_key_t *hash1, + hsiphash_key_t *hash2) +{ + hash1->key[0] = 2654435761UL; + hash1->key[1] = 2654435761UL; + + hash2->key[0] = 2654446892UL; + hash2->key[1] = 2654446892UL; +} + +/* Helper function to determine if server is unavailable */ +static inline bool is_unavailable(struct ip_vs_dest *dest) +{ + return atomic_read(&dest->weight) <= 0 || + dest->flags & IP_VS_DEST_F_OVERLOAD; +} + +/* Returns hash value for IPVS MH entry */ +static inline unsigned int +ip_vs_mh_hashkey(int af, const union nf_inet_addr *addr, + __be16 port, hsiphash_key_t *key, unsigned int offset) +{ + unsigned int v; + __be32 addr_fold = addr->ip; + +#ifdef CONFIG_IP_VS_IPV6 + if (af == AF_INET6) + addr_fold = addr->ip6[0] ^ addr->ip6[1] ^ + addr->ip6[2] ^ addr->ip6[3]; +#endif + v = (offset + ntohs(port) + ntohl(addr_fold)); + return hsiphash(&v, sizeof(v), key); +} + +/* Reset all the hash buckets of the specified table. */ +static void ip_vs_mh_reset(struct ip_vs_mh_state *s) +{ + int i; + struct ip_vs_mh_lookup *l; + struct ip_vs_dest *dest; + + l = &s->lookup[0]; + for (i = 0; i < IP_VS_MH_TAB_SIZE; i++) { + dest = rcu_dereference_protected(l->dest, 1); + if (dest) { + ip_vs_dest_put(dest); + RCU_INIT_POINTER(l->dest, NULL); + } + l++; + } +} + +static int ip_vs_mh_permutate(struct ip_vs_mh_state *s, + struct ip_vs_service *svc) +{ + struct list_head *p; + struct ip_vs_mh_dest_setup *ds; + struct ip_vs_dest *dest; + int lw; + + /* If gcd is smaller then 1, number of dests or + * all last_weight of dests are zero. So, skip + * permutation for the dests. + */ + if (s->gcd < 1) + return 0; + + /* Set dest_setup for the dests permutation */ + p = &svc->destinations; + ds = &s->dest_setup[0]; + while ((p = p->next) != &svc->destinations) { + dest = list_entry(p, struct ip_vs_dest, n_list); + + ds->offset = ip_vs_mh_hashkey(svc->af, &dest->addr, + dest->port, &s->hash1, 0) % + IP_VS_MH_TAB_SIZE; + ds->skip = ip_vs_mh_hashkey(svc->af, &dest->addr, + dest->port, &s->hash2, 0) % + (IP_VS_MH_TAB_SIZE - 1) + 1; + ds->perm = ds->offset; + + lw = atomic_read(&dest->last_weight); + ds->turns = ((lw / s->gcd) >> s->rshift) ? : (lw != 0); + ds++; + } + + return 0; +} + +static int ip_vs_mh_populate(struct ip_vs_mh_state *s, + struct ip_vs_service *svc) +{ + int n, c, dt_count; + unsigned long *table; + struct list_head *p; + struct ip_vs_mh_dest_setup *ds; + struct ip_vs_dest *dest, *new_dest; + + /* If gcd is smaller then 1, number of dests or + * all last_weight of dests are zero. So, skip + * the population for the dests and reset lookup table. + */ + if (s->gcd < 1) { + ip_vs_mh_reset(s); + return 0; + } + + table = kcalloc(BITS_TO_LONGS(IP_VS_MH_TAB_SIZE), + sizeof(unsigned long), GFP_KERNEL); + if (!table) + return -ENOMEM; + + p = &svc->destinations; + n = 0; + dt_count = 0; + while (n < IP_VS_MH_TAB_SIZE) { + if (p == &svc->destinations) + p = p->next; + + ds = &s->dest_setup[0]; + while (p != &svc->destinations) { + /* Ignore added server with zero weight */ + if (ds->turns < 1) { + p = p->next; + ds++; + continue; + } + + c = ds->perm; + while (test_bit(c, table)) { + /* Add skip, mod IP_VS_MH_TAB_SIZE */ + ds->perm += ds->skip; + if (ds->perm >= IP_VS_MH_TAB_SIZE) + ds->perm -= IP_VS_MH_TAB_SIZE; + c = ds->perm; + } + + __set_bit(c, table); + + dest = rcu_dereference_protected(s->lookup[c].dest, 1); + new_dest = list_entry(p, struct ip_vs_dest, n_list); + if (dest != new_dest) { + if (dest) + ip_vs_dest_put(dest); + ip_vs_dest_hold(new_dest); + RCU_INIT_POINTER(s->lookup[c].dest, new_dest); + } + + if (++n == IP_VS_MH_TAB_SIZE) + goto out; + + if (++dt_count >= ds->turns) { + dt_count = 0; + p = p->next; + ds++; + } + } + } + +out: + kfree(table); + return 0; +} + +/* Get ip_vs_dest associated with supplied parameters. */ +static inline struct ip_vs_dest * +ip_vs_mh_get(struct ip_vs_service *svc, struct ip_vs_mh_state *s, + const union nf_inet_addr *addr, __be16 port) +{ + unsigned int hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1, 0) + % IP_VS_MH_TAB_SIZE; + struct ip_vs_dest *dest = rcu_dereference(s->lookup[hash].dest); + + return (!dest || is_unavailable(dest)) ? NULL : dest; +} + +/* As ip_vs_mh_get, but with fallback if selected server is unavailable */ +static inline struct ip_vs_dest * +ip_vs_mh_get_fallback(struct ip_vs_service *svc, struct ip_vs_mh_state *s, + const union nf_inet_addr *addr, __be16 port) +{ + unsigned int offset, roffset; + unsigned int hash, ihash; + struct ip_vs_dest *dest; + + /* First try the dest it's supposed to go to */ + ihash = ip_vs_mh_hashkey(svc->af, addr, port, + &s->hash1, 0) % IP_VS_MH_TAB_SIZE; + dest = rcu_dereference(s->lookup[ihash].dest); + if (!dest) + return NULL; + if (!is_unavailable(dest)) + return dest; + + IP_VS_DBG_BUF(6, "MH: selected unavailable server %s:%u, reselecting", + IP_VS_DBG_ADDR(dest->af, &dest->addr), ntohs(dest->port)); + + /* If the original dest is unavailable, loop around the table + * starting from ihash to find a new dest + */ + for (offset = 0; offset < IP_VS_MH_TAB_SIZE; offset++) { + roffset = (offset + ihash) % IP_VS_MH_TAB_SIZE; + hash = ip_vs_mh_hashkey(svc->af, addr, port, &s->hash1, + roffset) % IP_VS_MH_TAB_SIZE; + dest = rcu_dereference(s->lookup[hash].dest); + if (!dest) + break; + if (!is_unavailable(dest)) + return dest; + IP_VS_DBG_BUF(6, + "MH: selected unavailable server %s:%u (offset %u), reselecting", + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port), roffset); + } + + return NULL; +} + +/* Assign all the hash buckets of the specified table with the service. */ +static int ip_vs_mh_reassign(struct ip_vs_mh_state *s, + struct ip_vs_service *svc) +{ + int ret; + + if (svc->num_dests > IP_VS_MH_TAB_SIZE) + return -EINVAL; + + if (svc->num_dests >= 1) { + s->dest_setup = kcalloc(svc->num_dests, + sizeof(struct ip_vs_mh_dest_setup), + GFP_KERNEL); + if (!s->dest_setup) + return -ENOMEM; + } + + ip_vs_mh_permutate(s, svc); + + ret = ip_vs_mh_populate(s, svc); + if (ret < 0) + goto out; + + IP_VS_DBG_BUF(6, "MH: reassign lookup table of %s:%u\n", + IP_VS_DBG_ADDR(svc->af, &svc->addr), + ntohs(svc->port)); + +out: + if (svc->num_dests >= 1) { + kfree(s->dest_setup); + s->dest_setup = NULL; + } + return ret; +} + +static int ip_vs_mh_gcd_weight(struct ip_vs_service *svc) +{ + struct ip_vs_dest *dest; + int weight; + int g = 0; + + list_for_each_entry(dest, &svc->destinations, n_list) { + weight = atomic_read(&dest->last_weight); + if (weight > 0) { + if (g > 0) + g = gcd(weight, g); + else + g = weight; + } + } + return g; +} + +/* To avoid assigning huge weight for the MH table, + * calculate shift value with gcd. + */ +static int ip_vs_mh_shift_weight(struct ip_vs_service *svc, int gcd) +{ + struct ip_vs_dest *dest; + int new_weight, weight = 0; + int mw, shift; + + /* If gcd is smaller then 1, number of dests or + * all last_weight of dests are zero. So, return + * shift value as zero. + */ + if (gcd < 1) + return 0; + + list_for_each_entry(dest, &svc->destinations, n_list) { + new_weight = atomic_read(&dest->last_weight); + if (new_weight > weight) + weight = new_weight; + } + + /* Because gcd is greater than zero, + * the maximum weight and gcd are always greater than zero + */ + mw = weight / gcd; + + /* shift = occupied bits of weight/gcd - MH highest bits */ + shift = fls(mw) - IP_VS_MH_TAB_BITS; + return (shift >= 0) ? shift : 0; +} + +static void ip_vs_mh_state_free(struct rcu_head *head) +{ + struct ip_vs_mh_state *s; + + s = container_of(head, struct ip_vs_mh_state, rcu_head); + kfree(s->lookup); + kfree(s); +} + +static int ip_vs_mh_init_svc(struct ip_vs_service *svc) +{ + int ret; + struct ip_vs_mh_state *s; + + /* Allocate the MH table for this service */ + s = kzalloc(sizeof(*s), GFP_KERNEL); + if (!s) + return -ENOMEM; + + s->lookup = kcalloc(IP_VS_MH_TAB_SIZE, sizeof(struct ip_vs_mh_lookup), + GFP_KERNEL); + if (!s->lookup) { + kfree(s); + return -ENOMEM; + } + + generate_hash_secret(&s->hash1, &s->hash2); + s->gcd = ip_vs_mh_gcd_weight(svc); + s->rshift = ip_vs_mh_shift_weight(svc, s->gcd); + + IP_VS_DBG(6, + "MH lookup table (memory=%zdbytes) allocated for current service\n", + sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE); + + /* Assign the lookup table with current dests */ + ret = ip_vs_mh_reassign(s, svc); + if (ret < 0) { + ip_vs_mh_reset(s); + ip_vs_mh_state_free(&s->rcu_head); + return ret; + } + + /* No more failures, attach state */ + svc->sched_data = s; + return 0; +} + +static void ip_vs_mh_done_svc(struct ip_vs_service *svc) +{ + struct ip_vs_mh_state *s = svc->sched_data; + + /* Got to clean up lookup entry here */ + ip_vs_mh_reset(s); + + call_rcu(&s->rcu_head, ip_vs_mh_state_free); + IP_VS_DBG(6, "MH lookup table (memory=%zdbytes) released\n", + sizeof(struct ip_vs_mh_lookup) * IP_VS_MH_TAB_SIZE); +} + +static int ip_vs_mh_dest_changed(struct ip_vs_service *svc, + struct ip_vs_dest *dest) +{ + struct ip_vs_mh_state *s = svc->sched_data; + + s->gcd = ip_vs_mh_gcd_weight(svc); + s->rshift = ip_vs_mh_shift_weight(svc, s->gcd); + + /* Assign the lookup table with the updated service */ + return ip_vs_mh_reassign(s, svc); +} + +/* Helper function to get port number */ +static inline __be16 +ip_vs_mh_get_port(const struct sk_buff *skb, struct ip_vs_iphdr *iph) +{ + __be16 _ports[2], *ports; + + /* At this point we know that we have a valid packet of some kind. + * Because ICMP packets are only guaranteed to have the first 8 + * bytes, let's just grab the ports. Fortunately they're in the + * same position for all three of the protocols we care about. + */ + switch (iph->protocol) { + case IPPROTO_TCP: + case IPPROTO_UDP: + case IPPROTO_SCTP: + ports = skb_header_pointer(skb, iph->len, sizeof(_ports), + &_ports); + if (unlikely(!ports)) + return 0; + + if (likely(!ip_vs_iph_inverse(iph))) + return ports[0]; + else + return ports[1]; + default: + return 0; + } +} + +/* Maglev Hashing scheduling */ +static struct ip_vs_dest * +ip_vs_mh_schedule(struct ip_vs_service *svc, const struct sk_buff *skb, + struct ip_vs_iphdr *iph) +{ + struct ip_vs_dest *dest; + struct ip_vs_mh_state *s; + __be16 port = 0; + const union nf_inet_addr *hash_addr; + + hash_addr = ip_vs_iph_inverse(iph) ? &iph->daddr : &iph->saddr; + + IP_VS_DBG(6, "%s : Scheduling...\n", __func__); + + if (svc->flags & IP_VS_SVC_F_SCHED_MH_PORT) + port = ip_vs_mh_get_port(skb, iph); + + s = (struct ip_vs_mh_state *)svc->sched_data; + + if (svc->flags & IP_VS_SVC_F_SCHED_MH_FALLBACK) + dest = ip_vs_mh_get_fallback(svc, s, hash_addr, port); + else + dest = ip_vs_mh_get(svc, s, hash_addr, port); + + if (!dest) { + ip_vs_scheduler_err(svc, "no destination available"); + return NULL; + } + + IP_VS_DBG_BUF(6, "MH: source IP address %s:%u --> server %s:%u\n", + IP_VS_DBG_ADDR(svc->af, hash_addr), + ntohs(port), + IP_VS_DBG_ADDR(dest->af, &dest->addr), + ntohs(dest->port)); + + return dest; +} + +/* IPVS MH Scheduler structure */ +static struct ip_vs_scheduler ip_vs_mh_scheduler = { + .name = "mh", + .refcnt = ATOMIC_INIT(0), + .module = THIS_MODULE, + .n_list = LIST_HEAD_INIT(ip_vs_mh_scheduler.n_list), + .init_service = ip_vs_mh_init_svc, + .done_service = ip_vs_mh_done_svc, + .add_dest = ip_vs_mh_dest_changed, + .del_dest = ip_vs_mh_dest_changed, + .upd_dest = ip_vs_mh_dest_changed, + .schedule = ip_vs_mh_schedule, +}; + +static int __init ip_vs_mh_init(void) +{ + return register_ip_vs_scheduler(&ip_vs_mh_scheduler); +} + +static void __exit ip_vs_mh_cleanup(void) +{ + unregister_ip_vs_scheduler(&ip_vs_mh_scheduler); + rcu_barrier(); +} + +module_init(ip_vs_mh_init); +module_exit(ip_vs_mh_cleanup); +MODULE_DESCRIPTION("Maglev hashing ipvs scheduler"); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR("Inju Song <inju.song@navercorp.com>"); diff --git a/net/netfilter/ipvs/ip_vs_proto_tcp.c b/net/netfilter/ipvs/ip_vs_proto_tcp.c index bcd9b7bde4ee..569631d2b2a1 100644 --- a/net/netfilter/ipvs/ip_vs_proto_tcp.c +++ b/net/netfilter/ipvs/ip_vs_proto_tcp.c @@ -436,7 +436,7 @@ static bool tcp_state_active(int state) return tcp_state_active_table[state]; } -static struct tcp_states_t tcp_states [] = { +static struct tcp_states_t tcp_states[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSR }}, @@ -459,7 +459,7 @@ static struct tcp_states_t tcp_states [] = { /*rst*/ {{sCL, sCL, sCL, sSR, sCL, sCL, sCL, sCL, sLA, sLI, sCL }}, }; -static struct tcp_states_t tcp_states_dos [] = { +static struct tcp_states_t tcp_states_dos[] = { /* INPUT */ /* sNO, sES, sSS, sSR, sFW, sTW, sCL, sCW, sLA, sLI, sSA */ /*syn*/ {{sSR, sES, sES, sSR, sSR, sSR, sSR, sSR, sSR, sSR, sSA }}, diff --git a/net/netfilter/ipvs/ip_vs_sh.c b/net/netfilter/ipvs/ip_vs_sh.c index 16aaac6eedc9..1e01c782583a 100644 --- a/net/netfilter/ipvs/ip_vs_sh.c +++ b/net/netfilter/ipvs/ip_vs_sh.c @@ -96,7 +96,8 @@ ip_vs_sh_hashkey(int af, const union nf_inet_addr *addr, addr_fold = addr->ip6[0]^addr->ip6[1]^ addr->ip6[2]^addr->ip6[3]; #endif - return (offset + (ntohs(port) + ntohl(addr_fold))*2654435761UL) & + return (offset + hash_32(ntohs(port) + ntohl(addr_fold), + IP_VS_SH_TAB_BITS)) & IP_VS_SH_TAB_MASK; } diff --git a/net/netfilter/ipvs/ip_vs_xmit.c b/net/netfilter/ipvs/ip_vs_xmit.c index 4527921b1c3a..ba0a0fd045c8 100644 --- a/net/netfilter/ipvs/ip_vs_xmit.c +++ b/net/netfilter/ipvs/ip_vs_xmit.c @@ -266,12 +266,13 @@ static inline bool decrement_ttl(struct netns_ipvs *ipvs, /* check and decrement ttl */ if (ipv6_hdr(skb)->hop_limit <= 1) { + struct inet6_dev *idev = __in6_dev_get_safely(skb->dev); + /* Force OUTPUT device used as source address */ skb->dev = dst->dev; icmpv6_send(skb, ICMPV6_TIME_EXCEED, ICMPV6_EXC_HOPLIMIT, 0); - __IP6_INC_STATS(net, ip6_dst_idev(dst), - IPSTATS_MIB_INHDRERRORS); + __IP6_INC_STATS(net, idev, IPSTATS_MIB_INHDRERRORS); return false; } diff --git a/net/netfilter/nf_conntrack_core.c b/net/netfilter/nf_conntrack_core.c index 41ff04ee2554..605441727008 100644 --- a/net/netfilter/nf_conntrack_core.c +++ b/net/netfilter/nf_conntrack_core.c @@ -186,6 +186,7 @@ unsigned int nf_conntrack_htable_size __read_mostly; EXPORT_SYMBOL_GPL(nf_conntrack_htable_size); unsigned int nf_conntrack_max __read_mostly; +EXPORT_SYMBOL_GPL(nf_conntrack_max); seqcount_t nf_conntrack_generation __read_mostly; static unsigned int nf_conntrack_hash_rnd __read_mostly; diff --git a/net/netfilter/nf_conntrack_ftp.c b/net/netfilter/nf_conntrack_ftp.c index f0e9a7511e1a..a11c304fb771 100644 --- a/net/netfilter/nf_conntrack_ftp.c +++ b/net/netfilter/nf_conntrack_ftp.c @@ -566,8 +566,7 @@ static const struct nf_conntrack_expect_policy ftp_exp_policy = { .timeout = 5 * 60, }; -/* don't make this __exit, since it's called from __init ! */ -static void nf_conntrack_ftp_fini(void) +static void __exit nf_conntrack_ftp_fini(void) { nf_conntrack_helpers_unregister(ftp, ports_c * 2); kfree(ftp_buffer); diff --git a/net/netfilter/nf_conntrack_irc.c b/net/netfilter/nf_conntrack_irc.c index 5523acce9d69..4099f4d79bae 100644 --- a/net/netfilter/nf_conntrack_irc.c +++ b/net/netfilter/nf_conntrack_irc.c @@ -232,8 +232,6 @@ static int help(struct sk_buff *skb, unsigned int protoff, static struct nf_conntrack_helper irc[MAX_PORTS] __read_mostly; static struct nf_conntrack_expect_policy irc_exp_policy; -static void nf_conntrack_irc_fini(void); - static int __init nf_conntrack_irc_init(void) { int i, ret; @@ -276,9 +274,7 @@ static int __init nf_conntrack_irc_init(void) return 0; } -/* This function is intentionally _NOT_ defined as __exit, because - * it is needed by the init function */ -static void nf_conntrack_irc_fini(void) +static void __exit nf_conntrack_irc_fini(void) { nf_conntrack_helpers_unregister(irc, ports_c); kfree(irc_buffer); diff --git a/net/netfilter/nf_conntrack_netlink.c b/net/netfilter/nf_conntrack_netlink.c index 4c1d0c5bc268..d807b8770be3 100644 --- a/net/netfilter/nf_conntrack_netlink.c +++ b/net/netfilter/nf_conntrack_netlink.c @@ -2205,6 +2205,9 @@ ctnetlink_stat_ct_fill_info(struct sk_buff *skb, u32 portid, u32 seq, u32 type, if (nla_put_be32(skb, CTA_STATS_GLOBAL_ENTRIES, htonl(nr_conntracks))) goto nla_put_failure; + if (nla_put_be32(skb, CTA_STATS_GLOBAL_MAX_ENTRIES, htonl(nf_conntrack_max))) + goto nla_put_failure; + nlmsg_end(skb, nlh); return skb->len; diff --git a/net/netfilter/nf_conntrack_sane.c b/net/netfilter/nf_conntrack_sane.c index ae457f39d5ce..5072ff96ab33 100644 --- a/net/netfilter/nf_conntrack_sane.c +++ b/net/netfilter/nf_conntrack_sane.c @@ -173,8 +173,7 @@ static const struct nf_conntrack_expect_policy sane_exp_policy = { .timeout = 5 * 60, }; -/* don't make this __exit, since it's called from __init ! */ -static void nf_conntrack_sane_fini(void) +static void __exit nf_conntrack_sane_fini(void) { nf_conntrack_helpers_unregister(sane, ports_c * 2); kfree(sane_buffer); diff --git a/net/netfilter/nf_conntrack_sip.c b/net/netfilter/nf_conntrack_sip.c index 908e51e2dc2b..c8d2b6688a2a 100644 --- a/net/netfilter/nf_conntrack_sip.c +++ b/net/netfilter/nf_conntrack_sip.c @@ -1617,7 +1617,7 @@ static const struct nf_conntrack_expect_policy sip_exp_policy[SIP_EXPECT_MAX + 1 }, }; -static void nf_conntrack_sip_fini(void) +static void __exit nf_conntrack_sip_fini(void) { nf_conntrack_helpers_unregister(sip, ports_c * 4); } diff --git a/net/netfilter/nf_conntrack_tftp.c b/net/netfilter/nf_conntrack_tftp.c index 0ec6779fd5d9..548b673b3625 100644 --- a/net/netfilter/nf_conntrack_tftp.c +++ b/net/netfilter/nf_conntrack_tftp.c @@ -104,7 +104,7 @@ static const struct nf_conntrack_expect_policy tftp_exp_policy = { .timeout = 5 * 60, }; -static void nf_conntrack_tftp_fini(void) +static void __exit nf_conntrack_tftp_fini(void) { nf_conntrack_helpers_unregister(tftp, ports_c * 2); } diff --git a/net/netfilter/nf_flow_table.c b/net/netfilter/nf_flow_table_core.c index ec410cae9307..eb0d1658ac05 100644 --- a/net/netfilter/nf_flow_table.c +++ b/net/netfilter/nf_flow_table_core.c @@ -4,6 +4,8 @@ #include <linux/netfilter.h> #include <linux/rhashtable.h> #include <linux/netdevice.h> +#include <net/ip.h> +#include <net/ip6_route.h> #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_flow_table.h> #include <net/netfilter/nf_conntrack.h> @@ -16,6 +18,43 @@ struct flow_offload_entry { struct rcu_head rcu_head; }; +static DEFINE_MUTEX(flowtable_lock); +static LIST_HEAD(flowtables); + +static void +flow_offload_fill_dir(struct flow_offload *flow, struct nf_conn *ct, + struct nf_flow_route *route, + enum flow_offload_tuple_dir dir) +{ + struct flow_offload_tuple *ft = &flow->tuplehash[dir].tuple; + struct nf_conntrack_tuple *ctt = &ct->tuplehash[dir].tuple; + struct dst_entry *dst = route->tuple[dir].dst; + + ft->dir = dir; + + switch (ctt->src.l3num) { + case NFPROTO_IPV4: + ft->src_v4 = ctt->src.u3.in; + ft->dst_v4 = ctt->dst.u3.in; + ft->mtu = ip_dst_mtu_maybe_forward(dst, true); + break; + case NFPROTO_IPV6: + ft->src_v6 = ctt->src.u3.in6; + ft->dst_v6 = ctt->dst.u3.in6; + ft->mtu = ip6_dst_mtu_forward(dst); + break; + } + + ft->l3proto = ctt->src.l3num; + ft->l4proto = ctt->dst.protonum; + ft->src_port = ctt->src.u.tcp.port; + ft->dst_port = ctt->dst.u.tcp.port; + + ft->iifidx = route->tuple[dir].ifindex; + ft->oifidx = route->tuple[!dir].ifindex; + ft->dst_cache = dst; +} + struct flow_offload * flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route) { @@ -40,69 +79,12 @@ flow_offload_alloc(struct nf_conn *ct, struct nf_flow_route *route) entry->ct = ct; - switch (ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num) { - case NFPROTO_IPV4: - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in; - break; - case NFPROTO_IPV6: - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u3.in6; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6 = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u3.in6; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3.in6; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6 = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3.in6; - break; - } - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l3proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.l4proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l3proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.l3num; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.l4proto = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.protonum; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache = - route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].dst; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache = - route->tuple[FLOW_OFFLOAD_DIR_REPLY].dst; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_port = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.src.u.tcp.port; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_port = - ct->tuplehash[IP_CT_DIR_ORIGINAL].tuple.dst.u.tcp.port; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_port = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u.tcp.port; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_port = - ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u.tcp.port; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dir = - FLOW_OFFLOAD_DIR_ORIGINAL; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dir = - FLOW_OFFLOAD_DIR_REPLY; - - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.iifidx = - route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex; - flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.oifidx = - route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.iifidx = - route->tuple[FLOW_OFFLOAD_DIR_REPLY].ifindex; - flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.oifidx = - route->tuple[FLOW_OFFLOAD_DIR_ORIGINAL].ifindex; + flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_ORIGINAL); + flow_offload_fill_dir(flow, ct, route, FLOW_OFFLOAD_DIR_REPLY); if (ct->status & IPS_SRC_NAT) flow->flags |= FLOW_OFFLOAD_SNAT; - else if (ct->status & IPS_DST_NAT) + if (ct->status & IPS_DST_NAT) flow->flags |= FLOW_OFFLOAD_DNAT; return flow; @@ -118,6 +100,43 @@ err_ct_refcnt: } EXPORT_SYMBOL_GPL(flow_offload_alloc); +static void flow_offload_fixup_tcp(struct ip_ct_tcp *tcp) +{ + tcp->state = TCP_CONNTRACK_ESTABLISHED; + tcp->seen[0].td_maxwin = 0; + tcp->seen[1].td_maxwin = 0; +} + +static void flow_offload_fixup_ct_state(struct nf_conn *ct) +{ + const struct nf_conntrack_l4proto *l4proto; + struct net *net = nf_ct_net(ct); + unsigned int *timeouts; + unsigned int timeout; + int l4num; + + l4num = nf_ct_protonum(ct); + if (l4num == IPPROTO_TCP) + flow_offload_fixup_tcp(&ct->proto.tcp); + + l4proto = __nf_ct_l4proto_find(nf_ct_l3num(ct), l4num); + if (!l4proto) + return; + + timeouts = l4proto->get_timeouts(net); + if (!timeouts) + return; + + if (l4num == IPPROTO_TCP) + timeout = timeouts[TCP_CONNTRACK_ESTABLISHED]; + else if (l4num == IPPROTO_UDP) + timeout = timeouts[UDP_CT_REPLIED]; + else + return; + + ct->timeout = nfct_time_stamp + timeout; +} + void flow_offload_free(struct flow_offload *flow) { struct flow_offload_entry *e; @@ -125,17 +144,46 @@ void flow_offload_free(struct flow_offload *flow) dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_cache); dst_release(flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_cache); e = container_of(flow, struct flow_offload_entry, flow); - nf_ct_delete(e->ct, 0, 0); + if (flow->flags & FLOW_OFFLOAD_DYING) + nf_ct_delete(e->ct, 0, 0); nf_ct_put(e->ct); kfree_rcu(e, rcu_head); } EXPORT_SYMBOL_GPL(flow_offload_free); -void flow_offload_dead(struct flow_offload *flow) +static u32 flow_offload_hash(const void *data, u32 len, u32 seed) +{ + const struct flow_offload_tuple *tuple = data; + + return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed); +} + +static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed) +{ + const struct flow_offload_tuple_rhash *tuplehash = data; + + return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed); +} + +static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg, + const void *ptr) { - flow->flags |= FLOW_OFFLOAD_DYING; + const struct flow_offload_tuple *tuple = arg->key; + const struct flow_offload_tuple_rhash *x = ptr; + + if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir))) + return 1; + + return 0; } -EXPORT_SYMBOL_GPL(flow_offload_dead); + +static const struct rhashtable_params nf_flow_offload_rhash_params = { + .head_offset = offsetof(struct flow_offload_tuple_rhash, node), + .hashfn = flow_offload_hash, + .obj_hashfn = flow_offload_hash_obj, + .obj_cmpfn = flow_offload_hash_cmp, + .automatic_shrinking = true, +}; int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) { @@ -143,10 +191,10 @@ int flow_offload_add(struct nf_flowtable *flow_table, struct flow_offload *flow) rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); rhashtable_insert_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); return 0; } EXPORT_SYMBOL_GPL(flow_offload_add); @@ -154,22 +202,51 @@ EXPORT_SYMBOL_GPL(flow_offload_add); static void flow_offload_del(struct nf_flowtable *flow_table, struct flow_offload *flow) { + struct flow_offload_entry *e; + rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); rhashtable_remove_fast(&flow_table->rhashtable, &flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].node, - *flow_table->type->params); + nf_flow_offload_rhash_params); + + e = container_of(flow, struct flow_offload_entry, flow); + clear_bit(IPS_OFFLOAD_BIT, &e->ct->status); flow_offload_free(flow); } +void flow_offload_teardown(struct flow_offload *flow) +{ + struct flow_offload_entry *e; + + flow->flags |= FLOW_OFFLOAD_TEARDOWN; + + e = container_of(flow, struct flow_offload_entry, flow); + flow_offload_fixup_ct_state(e->ct); +} +EXPORT_SYMBOL_GPL(flow_offload_teardown); + struct flow_offload_tuple_rhash * flow_offload_lookup(struct nf_flowtable *flow_table, struct flow_offload_tuple *tuple) { - return rhashtable_lookup_fast(&flow_table->rhashtable, tuple, - *flow_table->type->params); + struct flow_offload_tuple_rhash *tuplehash; + struct flow_offload *flow; + int dir; + + tuplehash = rhashtable_lookup_fast(&flow_table->rhashtable, tuple, + nf_flow_offload_rhash_params); + if (!tuplehash) + return NULL; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + if (flow->flags & (FLOW_OFFLOAD_DYING | FLOW_OFFLOAD_TEARDOWN)) + return NULL; + + return tuplehash; } EXPORT_SYMBOL_GPL(flow_offload_lookup); @@ -216,11 +293,6 @@ static inline bool nf_flow_has_expired(const struct flow_offload *flow) return (__s32)(flow->timeout - (u32)jiffies) <= 0; } -static inline bool nf_flow_is_dying(const struct flow_offload *flow) -{ - return flow->flags & FLOW_OFFLOAD_DYING; -} - static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table) { struct flow_offload_tuple_rhash *tuplehash; @@ -248,7 +320,8 @@ static int nf_flow_offload_gc_step(struct nf_flowtable *flow_table) flow = container_of(tuplehash, struct flow_offload, tuplehash[0]); if (nf_flow_has_expired(flow) || - nf_flow_is_dying(flow)) + (flow->flags & (FLOW_OFFLOAD_DYING | + FLOW_OFFLOAD_TEARDOWN))) flow_offload_del(flow_table, flow); } out: @@ -258,7 +331,7 @@ out: return 1; } -void nf_flow_offload_work_gc(struct work_struct *work) +static void nf_flow_offload_work_gc(struct work_struct *work) { struct nf_flowtable *flow_table; @@ -266,42 +339,6 @@ void nf_flow_offload_work_gc(struct work_struct *work) nf_flow_offload_gc_step(flow_table); queue_delayed_work(system_power_efficient_wq, &flow_table->gc_work, HZ); } -EXPORT_SYMBOL_GPL(nf_flow_offload_work_gc); - -static u32 flow_offload_hash(const void *data, u32 len, u32 seed) -{ - const struct flow_offload_tuple *tuple = data; - - return jhash(tuple, offsetof(struct flow_offload_tuple, dir), seed); -} - -static u32 flow_offload_hash_obj(const void *data, u32 len, u32 seed) -{ - const struct flow_offload_tuple_rhash *tuplehash = data; - - return jhash(&tuplehash->tuple, offsetof(struct flow_offload_tuple, dir), seed); -} - -static int flow_offload_hash_cmp(struct rhashtable_compare_arg *arg, - const void *ptr) -{ - const struct flow_offload_tuple *tuple = arg->key; - const struct flow_offload_tuple_rhash *x = ptr; - - if (memcmp(&x->tuple, tuple, offsetof(struct flow_offload_tuple, dir))) - return 1; - - return 0; -} - -const struct rhashtable_params nf_flow_offload_rhash_params = { - .head_offset = offsetof(struct flow_offload_tuple_rhash, node), - .hashfn = flow_offload_hash, - .obj_hashfn = flow_offload_hash_obj, - .obj_cmpfn = flow_offload_hash_cmp, - .automatic_shrinking = true, -}; -EXPORT_SYMBOL_GPL(nf_flow_offload_rhash_params); static int nf_flow_nat_port_tcp(struct sk_buff *skb, unsigned int thoff, __be16 port, __be16 new_port) @@ -419,33 +456,69 @@ int nf_flow_dnat_port(const struct flow_offload *flow, } EXPORT_SYMBOL_GPL(nf_flow_dnat_port); +int nf_flow_table_init(struct nf_flowtable *flowtable) +{ + int err; + + INIT_DEFERRABLE_WORK(&flowtable->gc_work, nf_flow_offload_work_gc); + + err = rhashtable_init(&flowtable->rhashtable, + &nf_flow_offload_rhash_params); + if (err < 0) + return err; + + queue_delayed_work(system_power_efficient_wq, + &flowtable->gc_work, HZ); + + mutex_lock(&flowtable_lock); + list_add(&flowtable->list, &flowtables); + mutex_unlock(&flowtable_lock); + + return 0; +} +EXPORT_SYMBOL_GPL(nf_flow_table_init); + static void nf_flow_table_do_cleanup(struct flow_offload *flow, void *data) { struct net_device *dev = data; - if (dev && flow->tuplehash[0].tuple.iifidx != dev->ifindex) + if (!dev) { + flow_offload_teardown(flow); return; + } - flow_offload_dead(flow); + if (flow->tuplehash[0].tuple.iifidx == dev->ifindex || + flow->tuplehash[1].tuple.iifidx == dev->ifindex) + flow_offload_dead(flow); } static void nf_flow_table_iterate_cleanup(struct nf_flowtable *flowtable, - void *data) + struct net_device *dev) { - nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, data); + nf_flow_table_iterate(flowtable, nf_flow_table_do_cleanup, dev); flush_delayed_work(&flowtable->gc_work); } void nf_flow_table_cleanup(struct net *net, struct net_device *dev) { - nft_flow_table_iterate(net, nf_flow_table_iterate_cleanup, dev); + struct nf_flowtable *flowtable; + + mutex_lock(&flowtable_lock); + list_for_each_entry(flowtable, &flowtables, list) + nf_flow_table_iterate_cleanup(flowtable, dev); + mutex_unlock(&flowtable_lock); } EXPORT_SYMBOL_GPL(nf_flow_table_cleanup); void nf_flow_table_free(struct nf_flowtable *flow_table) { + mutex_lock(&flowtable_lock); + list_del(&flow_table->list); + mutex_unlock(&flowtable_lock); + cancel_delayed_work_sync(&flow_table->gc_work); nf_flow_table_iterate(flow_table, nf_flow_table_do_cleanup, NULL); WARN_ON(!nf_flow_offload_gc_step(flow_table)); + rhashtable_destroy(&flow_table->rhashtable); } EXPORT_SYMBOL_GPL(nf_flow_table_free); diff --git a/net/netfilter/nf_flow_table_inet.c b/net/netfilter/nf_flow_table_inet.c index 375a1881d93d..99771aa7e7ea 100644 --- a/net/netfilter/nf_flow_table_inet.c +++ b/net/netfilter/nf_flow_table_inet.c @@ -22,8 +22,7 @@ nf_flow_offload_inet_hook(void *priv, struct sk_buff *skb, static struct nf_flowtable_type flowtable_inet = { .family = NFPROTO_INET, - .params = &nf_flow_offload_rhash_params, - .gc = nf_flow_offload_work_gc, + .init = nf_flow_table_init, .free = nf_flow_table_free, .hook = nf_flow_offload_inet_hook, .owner = THIS_MODULE, diff --git a/net/netfilter/nf_flow_table_ip.c b/net/netfilter/nf_flow_table_ip.c new file mode 100644 index 000000000000..82451b7e0acb --- /dev/null +++ b/net/netfilter/nf_flow_table_ip.c @@ -0,0 +1,487 @@ +#include <linux/kernel.h> +#include <linux/init.h> +#include <linux/module.h> +#include <linux/netfilter.h> +#include <linux/rhashtable.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/netdevice.h> +#include <net/ip.h> +#include <net/ipv6.h> +#include <net/ip6_route.h> +#include <net/neighbour.h> +#include <net/netfilter/nf_flow_table.h> +/* For layer 4 checksum field offset. */ +#include <linux/tcp.h> +#include <linux/udp.h> + +static int nf_flow_state_check(struct flow_offload *flow, int proto, + struct sk_buff *skb, unsigned int thoff) +{ + struct tcphdr *tcph; + + if (proto != IPPROTO_TCP) + return 0; + + if (!pskb_may_pull(skb, thoff + sizeof(*tcph))) + return -1; + + tcph = (void *)(skb_network_header(skb) + thoff); + if (unlikely(tcph->fin || tcph->rst)) { + flow_offload_teardown(flow); + return -1; + } + + return 0; +} + +static int nf_flow_nat_ip_tcp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) +{ + struct tcphdr *tcph; + + if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || + skb_try_make_writable(skb, thoff + sizeof(*tcph))) + return -1; + + tcph = (void *)(skb_network_header(skb) + thoff); + inet_proto_csum_replace4(&tcph->check, skb, addr, new_addr, true); + + return 0; +} + +static int nf_flow_nat_ip_udp(struct sk_buff *skb, unsigned int thoff, + __be32 addr, __be32 new_addr) +{ + struct udphdr *udph; + + if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || + skb_try_make_writable(skb, thoff + sizeof(*udph))) + return -1; + + udph = (void *)(skb_network_header(skb) + thoff); + if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { + inet_proto_csum_replace4(&udph->check, skb, addr, + new_addr, true); + if (!udph->check) + udph->check = CSUM_MANGLED_0; + } + + return 0; +} + +static int nf_flow_nat_ip_l4proto(struct sk_buff *skb, struct iphdr *iph, + unsigned int thoff, __be32 addr, + __be32 new_addr) +{ + switch (iph->protocol) { + case IPPROTO_TCP: + if (nf_flow_nat_ip_tcp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + case IPPROTO_UDP: + if (nf_flow_nat_ip_udp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + } + + return 0; +} + +static int nf_flow_snat_ip(const struct flow_offload *flow, struct sk_buff *skb, + struct iphdr *iph, unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + __be32 addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = iph->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v4.s_addr; + iph->saddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = iph->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v4.s_addr; + iph->daddr = new_addr; + break; + default: + return -1; + } + csum_replace4(&iph->check, addr, new_addr); + + return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); +} + +static int nf_flow_dnat_ip(const struct flow_offload *flow, struct sk_buff *skb, + struct iphdr *iph, unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + __be32 addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = iph->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v4.s_addr; + iph->daddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = iph->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v4.s_addr; + iph->saddr = new_addr; + break; + default: + return -1; + } + csum_replace4(&iph->check, addr, new_addr); + + return nf_flow_nat_ip_l4proto(skb, iph, thoff, addr, new_addr); +} + +static int nf_flow_nat_ip(const struct flow_offload *flow, struct sk_buff *skb, + unsigned int thoff, enum flow_offload_tuple_dir dir) +{ + struct iphdr *iph = ip_hdr(skb); + + if (flow->flags & FLOW_OFFLOAD_SNAT && + (nf_flow_snat_port(flow, skb, thoff, iph->protocol, dir) < 0 || + nf_flow_snat_ip(flow, skb, iph, thoff, dir) < 0)) + return -1; + if (flow->flags & FLOW_OFFLOAD_DNAT && + (nf_flow_dnat_port(flow, skb, thoff, iph->protocol, dir) < 0 || + nf_flow_dnat_ip(flow, skb, iph, thoff, dir) < 0)) + return -1; + + return 0; +} + +static bool ip_has_options(unsigned int thoff) +{ + return thoff != sizeof(struct iphdr); +} + +static int nf_flow_tuple_ip(struct sk_buff *skb, const struct net_device *dev, + struct flow_offload_tuple *tuple) +{ + struct flow_ports *ports; + unsigned int thoff; + struct iphdr *iph; + + if (!pskb_may_pull(skb, sizeof(*iph))) + return -1; + + iph = ip_hdr(skb); + thoff = iph->ihl * 4; + + if (ip_is_fragment(iph) || + unlikely(ip_has_options(thoff))) + return -1; + + if (iph->protocol != IPPROTO_TCP && + iph->protocol != IPPROTO_UDP) + return -1; + + thoff = iph->ihl * 4; + if (!pskb_may_pull(skb, thoff + sizeof(*ports))) + return -1; + + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + + tuple->src_v4.s_addr = iph->saddr; + tuple->dst_v4.s_addr = iph->daddr; + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + tuple->l3proto = AF_INET; + tuple->l4proto = iph->protocol; + tuple->iifidx = dev->ifindex; + + return 0; +} + +/* Based on ip_exceeds_mtu(). */ +static bool nf_flow_exceeds_mtu(const struct sk_buff *skb, unsigned int mtu) +{ + if (skb->len <= mtu) + return false; + + if (skb_is_gso(skb) && skb_gso_validate_network_len(skb, mtu)) + return false; + + return true; +} + +unsigned int +nf_flow_offload_ip_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct flow_offload_tuple_rhash *tuplehash; + struct nf_flowtable *flow_table = priv; + struct flow_offload_tuple tuple = {}; + enum flow_offload_tuple_dir dir; + struct flow_offload *flow; + struct net_device *outdev; + const struct rtable *rt; + unsigned int thoff; + struct iphdr *iph; + __be32 nexthop; + + if (skb->protocol != htons(ETH_P_IP)) + return NF_ACCEPT; + + if (nf_flow_tuple_ip(skb, state->in, &tuple) < 0) + return NF_ACCEPT; + + tuplehash = flow_offload_lookup(flow_table, &tuple); + if (tuplehash == NULL) + return NF_ACCEPT; + + outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); + if (!outdev) + return NF_ACCEPT; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + rt = (const struct rtable *)flow->tuplehash[dir].tuple.dst_cache; + + if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu)) && + (ip_hdr(skb)->frag_off & htons(IP_DF)) != 0) + return NF_ACCEPT; + + if (skb_try_make_writable(skb, sizeof(*iph))) + return NF_DROP; + + thoff = ip_hdr(skb)->ihl * 4; + if (nf_flow_state_check(flow, ip_hdr(skb)->protocol, skb, thoff)) + return NF_ACCEPT; + + if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && + nf_flow_nat_ip(flow, skb, thoff, dir) < 0) + return NF_DROP; + + flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + iph = ip_hdr(skb); + ip_decrease_ttl(iph); + + skb->dev = outdev; + nexthop = rt_nexthop(rt, flow->tuplehash[!dir].tuple.src_v4.s_addr); + neigh_xmit(NEIGH_ARP_TABLE, outdev, &nexthop, skb); + + return NF_STOLEN; +} +EXPORT_SYMBOL_GPL(nf_flow_offload_ip_hook); + +static int nf_flow_nat_ipv6_tcp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr) +{ + struct tcphdr *tcph; + + if (!pskb_may_pull(skb, thoff + sizeof(*tcph)) || + skb_try_make_writable(skb, thoff + sizeof(*tcph))) + return -1; + + tcph = (void *)(skb_network_header(skb) + thoff); + inet_proto_csum_replace16(&tcph->check, skb, addr->s6_addr32, + new_addr->s6_addr32, true); + + return 0; +} + +static int nf_flow_nat_ipv6_udp(struct sk_buff *skb, unsigned int thoff, + struct in6_addr *addr, + struct in6_addr *new_addr) +{ + struct udphdr *udph; + + if (!pskb_may_pull(skb, thoff + sizeof(*udph)) || + skb_try_make_writable(skb, thoff + sizeof(*udph))) + return -1; + + udph = (void *)(skb_network_header(skb) + thoff); + if (udph->check || skb->ip_summed == CHECKSUM_PARTIAL) { + inet_proto_csum_replace16(&udph->check, skb, addr->s6_addr32, + new_addr->s6_addr32, true); + if (!udph->check) + udph->check = CSUM_MANGLED_0; + } + + return 0; +} + +static int nf_flow_nat_ipv6_l4proto(struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, struct in6_addr *addr, + struct in6_addr *new_addr) +{ + switch (ip6h->nexthdr) { + case IPPROTO_TCP: + if (nf_flow_nat_ipv6_tcp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + case IPPROTO_UDP: + if (nf_flow_nat_ipv6_udp(skb, thoff, addr, new_addr) < 0) + return NF_DROP; + break; + } + + return 0; +} + +static int nf_flow_snat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + struct in6_addr addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = ip6h->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.dst_v6; + ip6h->saddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = ip6h->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.src_v6; + ip6h->daddr = new_addr; + break; + default: + return -1; + } + + return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); +} + +static int nf_flow_dnat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, struct ipv6hdr *ip6h, + unsigned int thoff, + enum flow_offload_tuple_dir dir) +{ + struct in6_addr addr, new_addr; + + switch (dir) { + case FLOW_OFFLOAD_DIR_ORIGINAL: + addr = ip6h->daddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_REPLY].tuple.src_v6; + ip6h->daddr = new_addr; + break; + case FLOW_OFFLOAD_DIR_REPLY: + addr = ip6h->saddr; + new_addr = flow->tuplehash[FLOW_OFFLOAD_DIR_ORIGINAL].tuple.dst_v6; + ip6h->saddr = new_addr; + break; + default: + return -1; + } + + return nf_flow_nat_ipv6_l4proto(skb, ip6h, thoff, &addr, &new_addr); +} + +static int nf_flow_nat_ipv6(const struct flow_offload *flow, + struct sk_buff *skb, + enum flow_offload_tuple_dir dir) +{ + struct ipv6hdr *ip6h = ipv6_hdr(skb); + unsigned int thoff = sizeof(*ip6h); + + if (flow->flags & FLOW_OFFLOAD_SNAT && + (nf_flow_snat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || + nf_flow_snat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) + return -1; + if (flow->flags & FLOW_OFFLOAD_DNAT && + (nf_flow_dnat_port(flow, skb, thoff, ip6h->nexthdr, dir) < 0 || + nf_flow_dnat_ipv6(flow, skb, ip6h, thoff, dir) < 0)) + return -1; + + return 0; +} + +static int nf_flow_tuple_ipv6(struct sk_buff *skb, const struct net_device *dev, + struct flow_offload_tuple *tuple) +{ + struct flow_ports *ports; + struct ipv6hdr *ip6h; + unsigned int thoff; + + if (!pskb_may_pull(skb, sizeof(*ip6h))) + return -1; + + ip6h = ipv6_hdr(skb); + + if (ip6h->nexthdr != IPPROTO_TCP && + ip6h->nexthdr != IPPROTO_UDP) + return -1; + + thoff = sizeof(*ip6h); + if (!pskb_may_pull(skb, thoff + sizeof(*ports))) + return -1; + + ports = (struct flow_ports *)(skb_network_header(skb) + thoff); + + tuple->src_v6 = ip6h->saddr; + tuple->dst_v6 = ip6h->daddr; + tuple->src_port = ports->source; + tuple->dst_port = ports->dest; + tuple->l3proto = AF_INET6; + tuple->l4proto = ip6h->nexthdr; + tuple->iifidx = dev->ifindex; + + return 0; +} + +unsigned int +nf_flow_offload_ipv6_hook(void *priv, struct sk_buff *skb, + const struct nf_hook_state *state) +{ + struct flow_offload_tuple_rhash *tuplehash; + struct nf_flowtable *flow_table = priv; + struct flow_offload_tuple tuple = {}; + enum flow_offload_tuple_dir dir; + struct flow_offload *flow; + struct net_device *outdev; + struct in6_addr *nexthop; + struct ipv6hdr *ip6h; + struct rt6_info *rt; + + if (skb->protocol != htons(ETH_P_IPV6)) + return NF_ACCEPT; + + if (nf_flow_tuple_ipv6(skb, state->in, &tuple) < 0) + return NF_ACCEPT; + + tuplehash = flow_offload_lookup(flow_table, &tuple); + if (tuplehash == NULL) + return NF_ACCEPT; + + outdev = dev_get_by_index_rcu(state->net, tuplehash->tuple.oifidx); + if (!outdev) + return NF_ACCEPT; + + dir = tuplehash->tuple.dir; + flow = container_of(tuplehash, struct flow_offload, tuplehash[dir]); + rt = (struct rt6_info *)flow->tuplehash[dir].tuple.dst_cache; + + if (unlikely(nf_flow_exceeds_mtu(skb, flow->tuplehash[dir].tuple.mtu))) + return NF_ACCEPT; + + if (nf_flow_state_check(flow, ipv6_hdr(skb)->nexthdr, skb, + sizeof(*ip6h))) + return NF_ACCEPT; + + if (skb_try_make_writable(skb, sizeof(*ip6h))) + return NF_DROP; + + if (flow->flags & (FLOW_OFFLOAD_SNAT | FLOW_OFFLOAD_DNAT) && + nf_flow_nat_ipv6(flow, skb, dir) < 0) + return NF_DROP; + + flow->timeout = (u32)jiffies + NF_FLOW_TIMEOUT; + ip6h = ipv6_hdr(skb); + ip6h->hop_limit--; + + skb->dev = outdev; + nexthop = rt6_nexthop(rt, &flow->tuplehash[!dir].tuple.src_v6); + neigh_xmit(NEIGH_ND_TABLE, outdev, nexthop, skb); + + return NF_STOLEN; +} +EXPORT_SYMBOL_GPL(nf_flow_offload_ipv6_hook); diff --git a/net/netfilter/nf_nat_core.c b/net/netfilter/nf_nat_core.c index 617693ff9f4c..37b3c9913b08 100644 --- a/net/netfilter/nf_nat_core.c +++ b/net/netfilter/nf_nat_core.c @@ -157,7 +157,7 @@ EXPORT_SYMBOL(nf_nat_used_tuple); static int in_range(const struct nf_nat_l3proto *l3proto, const struct nf_nat_l4proto *l4proto, const struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { /* If we are supposed to map IPs, then we must be in the * range specified, otherwise let this drag us onto a new src IP. @@ -194,7 +194,7 @@ find_appropriate_src(struct net *net, const struct nf_nat_l4proto *l4proto, const struct nf_conntrack_tuple *tuple, struct nf_conntrack_tuple *result, - const struct nf_nat_range *range) + const struct nf_nat_range2 *range) { unsigned int h = hash_by_src(net, tuple); const struct nf_conn *ct; @@ -224,7 +224,7 @@ find_appropriate_src(struct net *net, static void find_best_ips_proto(const struct nf_conntrack_zone *zone, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, const struct nf_conn *ct, enum nf_nat_manip_type maniptype) { @@ -298,7 +298,7 @@ find_best_ips_proto(const struct nf_conntrack_zone *zone, static void get_unique_tuple(struct nf_conntrack_tuple *tuple, const struct nf_conntrack_tuple *orig_tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, struct nf_conn *ct, enum nf_nat_manip_type maniptype) { @@ -349,9 +349,10 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, /* Only bother mapping if it's not already in range and unique */ if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) { if (range->flags & NF_NAT_RANGE_PROTO_SPECIFIED) { - if (l4proto->in_range(tuple, maniptype, - &range->min_proto, - &range->max_proto) && + if (!(range->flags & NF_NAT_RANGE_PROTO_OFFSET) && + l4proto->in_range(tuple, maniptype, + &range->min_proto, + &range->max_proto) && (range->min_proto.all == range->max_proto.all || !nf_nat_used_tuple(tuple, ct))) goto out; @@ -360,7 +361,7 @@ get_unique_tuple(struct nf_conntrack_tuple *tuple, } } - /* Last change: get protocol to try to obtain unique tuple. */ + /* Last chance: get protocol to try to obtain unique tuple. */ l4proto->unique_tuple(l3proto, tuple, range, maniptype, ct); out: rcu_read_unlock(); @@ -381,7 +382,7 @@ EXPORT_SYMBOL_GPL(nf_ct_nat_ext_add); unsigned int nf_nat_setup_info(struct nf_conn *ct, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { struct net *net = nf_ct_net(ct); @@ -459,7 +460,7 @@ __nf_nat_alloc_null_binding(struct nf_conn *ct, enum nf_nat_manip_type manip) (manip == NF_NAT_MANIP_SRC ? ct->tuplehash[IP_CT_DIR_REPLY].tuple.dst.u3 : ct->tuplehash[IP_CT_DIR_REPLY].tuple.src.u3); - struct nf_nat_range range = { + struct nf_nat_range2 range = { .flags = NF_NAT_RANGE_MAP_IPS, .min_addr = ip, .max_addr = ip, @@ -702,7 +703,7 @@ static const struct nla_policy protonat_nla_policy[CTA_PROTONAT_MAX+1] = { static int nfnetlink_parse_nat_proto(struct nlattr *attr, const struct nf_conn *ct, - struct nf_nat_range *range) + struct nf_nat_range2 *range) { struct nlattr *tb[CTA_PROTONAT_MAX+1]; const struct nf_nat_l4proto *l4proto; @@ -730,7 +731,7 @@ static const struct nla_policy nat_nla_policy[CTA_NAT_MAX+1] = { static int nfnetlink_parse_nat(const struct nlattr *nat, - const struct nf_conn *ct, struct nf_nat_range *range, + const struct nf_conn *ct, struct nf_nat_range2 *range, const struct nf_nat_l3proto *l3proto) { struct nlattr *tb[CTA_NAT_MAX+1]; @@ -758,7 +759,7 @@ nfnetlink_parse_nat_setup(struct nf_conn *ct, enum nf_nat_manip_type manip, const struct nlattr *attr) { - struct nf_nat_range range; + struct nf_nat_range2 range; const struct nf_nat_l3proto *l3proto; int err; diff --git a/net/netfilter/nf_nat_helper.c b/net/netfilter/nf_nat_helper.c index 607a373379b4..99606baedda4 100644 --- a/net/netfilter/nf_nat_helper.c +++ b/net/netfilter/nf_nat_helper.c @@ -191,7 +191,7 @@ EXPORT_SYMBOL(nf_nat_mangle_udp_packet); void nf_nat_follow_master(struct nf_conn *ct, struct nf_conntrack_expect *exp) { - struct nf_nat_range range; + struct nf_nat_range2 range; /* This must be a fresh one. */ BUG_ON(ct->status & IPS_NAT_DONE_MASK); diff --git a/net/netfilter/nf_nat_proto_common.c b/net/netfilter/nf_nat_proto_common.c index 7d7466dbf663..5d849d835561 100644 --- a/net/netfilter/nf_nat_proto_common.c +++ b/net/netfilter/nf_nat_proto_common.c @@ -36,7 +36,7 @@ EXPORT_SYMBOL_GPL(nf_nat_l4proto_in_range); void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct, u16 *rover) @@ -83,6 +83,8 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, : tuple->src.u.all); } else if (range->flags & NF_NAT_RANGE_PROTO_RANDOM_FULLY) { off = prandom_u32(); + } else if (range->flags & NF_NAT_RANGE_PROTO_OFFSET) { + off = (ntohs(*portptr) - ntohs(range->base_proto.all)); } else { off = *rover; } @@ -91,7 +93,8 @@ void nf_nat_l4proto_unique_tuple(const struct nf_nat_l3proto *l3proto, *portptr = htons(min + off % range_size); if (++i != range_size && nf_nat_used_tuple(tuple, ct)) continue; - if (!(range->flags & NF_NAT_RANGE_PROTO_RANDOM_ALL)) + if (!(range->flags & (NF_NAT_RANGE_PROTO_RANDOM_ALL| + NF_NAT_RANGE_PROTO_OFFSET))) *rover = off; return; } @@ -100,7 +103,7 @@ EXPORT_SYMBOL_GPL(nf_nat_l4proto_unique_tuple); #if IS_ENABLED(CONFIG_NF_CT_NETLINK) int nf_nat_l4proto_nlattr_to_range(struct nlattr *tb[], - struct nf_nat_range *range) + struct nf_nat_range2 *range) { if (tb[CTA_PROTONAT_PORT_MIN]) { range->min_proto.all = nla_get_be16(tb[CTA_PROTONAT_PORT_MIN]); diff --git a/net/netfilter/nf_nat_proto_dccp.c b/net/netfilter/nf_nat_proto_dccp.c index 269fcd5dc34c..67ea0d83aa5a 100644 --- a/net/netfilter/nf_nat_proto_dccp.c +++ b/net/netfilter/nf_nat_proto_dccp.c @@ -23,7 +23,7 @@ static u_int16_t dccp_port_rover; static void dccp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_sctp.c b/net/netfilter/nf_nat_proto_sctp.c index c57ee3240b1d..1c5d9b65fbba 100644 --- a/net/netfilter/nf_nat_proto_sctp.c +++ b/net/netfilter/nf_nat_proto_sctp.c @@ -17,7 +17,7 @@ static u_int16_t nf_sctp_port_rover; static void sctp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_tcp.c b/net/netfilter/nf_nat_proto_tcp.c index 4f8820fc5148..f15fcd475f98 100644 --- a/net/netfilter/nf_nat_proto_tcp.c +++ b/net/netfilter/nf_nat_proto_tcp.c @@ -23,7 +23,7 @@ static u16 tcp_port_rover; static void tcp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_udp.c b/net/netfilter/nf_nat_proto_udp.c index edd4a77dc09a..5790f70a83b2 100644 --- a/net/netfilter/nf_nat_proto_udp.c +++ b/net/netfilter/nf_nat_proto_udp.c @@ -22,7 +22,7 @@ static u16 udp_port_rover; static void udp_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { @@ -100,7 +100,7 @@ static bool udplite_manip_pkt(struct sk_buff *skb, static void udplite_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_proto_unknown.c b/net/netfilter/nf_nat_proto_unknown.c index 6e494d584412..c5db3e251232 100644 --- a/net/netfilter/nf_nat_proto_unknown.c +++ b/net/netfilter/nf_nat_proto_unknown.c @@ -27,7 +27,7 @@ static bool unknown_in_range(const struct nf_conntrack_tuple *tuple, static void unknown_unique_tuple(const struct nf_nat_l3proto *l3proto, struct nf_conntrack_tuple *tuple, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype, const struct nf_conn *ct) { diff --git a/net/netfilter/nf_nat_redirect.c b/net/netfilter/nf_nat_redirect.c index 25b06b959118..7c4bb0a773ca 100644 --- a/net/netfilter/nf_nat_redirect.c +++ b/net/netfilter/nf_nat_redirect.c @@ -36,7 +36,7 @@ nf_nat_redirect_ipv4(struct sk_buff *skb, struct nf_conn *ct; enum ip_conntrack_info ctinfo; __be32 newdst; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; WARN_ON(hooknum != NF_INET_PRE_ROUTING && hooknum != NF_INET_LOCAL_OUT); @@ -82,10 +82,10 @@ EXPORT_SYMBOL_GPL(nf_nat_redirect_ipv4); static const struct in6_addr loopback_addr = IN6ADDR_LOOPBACK_INIT; unsigned int -nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range *range, +nf_nat_redirect_ipv6(struct sk_buff *skb, const struct nf_nat_range2 *range, unsigned int hooknum) { - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; struct in6_addr newdst; enum ip_conntrack_info ctinfo; struct nf_conn *ct; diff --git a/net/netfilter/nf_nat_sip.c b/net/netfilter/nf_nat_sip.c index 791fac4fd745..1f3086074981 100644 --- a/net/netfilter/nf_nat_sip.c +++ b/net/netfilter/nf_nat_sip.c @@ -316,7 +316,7 @@ static void nf_nat_sip_seq_adjust(struct sk_buff *skb, unsigned int protoff, static void nf_nat_sip_expected(struct nf_conn *ct, struct nf_conntrack_expect *exp) { - struct nf_nat_range range; + struct nf_nat_range2 range; /* This must be a fresh one. */ BUG_ON(ct->status & IPS_NAT_DONE_MASK); diff --git a/net/netfilter/nf_osf.c b/net/netfilter/nf_osf.c new file mode 100644 index 000000000000..5ba5c7bef2f9 --- /dev/null +++ b/net/netfilter/nf_osf.c @@ -0,0 +1,218 @@ +#define pr_fmt(fmt) KBUILD_MODNAME ": " fmt +#include <linux/module.h> +#include <linux/kernel.h> + +#include <linux/capability.h> +#include <linux/if.h> +#include <linux/inetdevice.h> +#include <linux/ip.h> +#include <linux/list.h> +#include <linux/rculist.h> +#include <linux/skbuff.h> +#include <linux/slab.h> +#include <linux/tcp.h> + +#include <net/ip.h> +#include <net/tcp.h> + +#include <linux/netfilter/nfnetlink.h> +#include <linux/netfilter/x_tables.h> +#include <net/netfilter/nf_log.h> +#include <linux/netfilter/nf_osf.h> + +static inline int nf_osf_ttl(const struct sk_buff *skb, + const struct nf_osf_info *info, + unsigned char f_ttl) +{ + const struct iphdr *ip = ip_hdr(skb); + + if (info->flags & NF_OSF_TTL) { + if (info->ttl == NF_OSF_TTL_TRUE) + return ip->ttl == f_ttl; + if (info->ttl == NF_OSF_TTL_NOCHECK) + return 1; + else if (ip->ttl <= f_ttl) + return 1; + else { + struct in_device *in_dev = __in_dev_get_rcu(skb->dev); + int ret = 0; + + for_ifa(in_dev) { + if (inet_ifa_match(ip->saddr, ifa)) { + ret = (ip->ttl == f_ttl); + break; + } + } + endfor_ifa(in_dev); + + return ret; + } + } + + return ip->ttl == f_ttl; +} + +bool +nf_osf_match(const struct sk_buff *skb, u_int8_t family, + int hooknum, struct net_device *in, struct net_device *out, + const struct nf_osf_info *info, struct net *net, + const struct list_head *nf_osf_fingers) +{ + const unsigned char *optp = NULL, *_optp = NULL; + unsigned int optsize = 0, check_WSS = 0; + int fmatch = FMATCH_WRONG, fcount = 0; + const struct iphdr *ip = ip_hdr(skb); + const struct nf_osf_user_finger *f; + unsigned char opts[MAX_IPOPTLEN]; + const struct nf_osf_finger *kf; + u16 window, totlen, mss = 0; + const struct tcphdr *tcp; + struct tcphdr _tcph; + bool df; + + tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); + if (!tcp) + return false; + + if (!tcp->syn) + return false; + + totlen = ntohs(ip->tot_len); + df = ntohs(ip->frag_off) & IP_DF; + window = ntohs(tcp->window); + + if (tcp->doff * 4 > sizeof(struct tcphdr)) { + optsize = tcp->doff * 4 - sizeof(struct tcphdr); + + _optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) + + sizeof(struct tcphdr), optsize, opts); + } + + list_for_each_entry_rcu(kf, &nf_osf_fingers[df], finger_entry) { + int foptsize, optnum; + + f = &kf->finger; + + if (!(info->flags & NF_OSF_LOG) && strcmp(info->genre, f->genre)) + continue; + + optp = _optp; + fmatch = FMATCH_WRONG; + + if (totlen != f->ss || !nf_osf_ttl(skb, info, f->ttl)) + continue; + + /* + * Should not happen if userspace parser was written correctly. + */ + if (f->wss.wc >= OSF_WSS_MAX) + continue; + + /* Check options */ + + foptsize = 0; + for (optnum = 0; optnum < f->opt_num; ++optnum) + foptsize += f->opt[optnum].length; + + if (foptsize > MAX_IPOPTLEN || + optsize > MAX_IPOPTLEN || + optsize != foptsize) + continue; + + check_WSS = f->wss.wc; + + for (optnum = 0; optnum < f->opt_num; ++optnum) { + if (f->opt[optnum].kind == (*optp)) { + __u32 len = f->opt[optnum].length; + const __u8 *optend = optp + len; + + fmatch = FMATCH_OK; + + switch (*optp) { + case OSFOPT_MSS: + mss = optp[3]; + mss <<= 8; + mss |= optp[2]; + + mss = ntohs((__force __be16)mss); + break; + case OSFOPT_TS: + break; + } + + optp = optend; + } else + fmatch = FMATCH_OPT_WRONG; + + if (fmatch != FMATCH_OK) + break; + } + + if (fmatch != FMATCH_OPT_WRONG) { + fmatch = FMATCH_WRONG; + + switch (check_WSS) { + case OSF_WSS_PLAIN: + if (f->wss.val == 0 || window == f->wss.val) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MSS: + /* + * Some smart modems decrease mangle MSS to + * SMART_MSS_2, so we check standard, decreased + * and the one provided in the fingerprint MSS + * values. + */ +#define SMART_MSS_1 1460 +#define SMART_MSS_2 1448 + if (window == f->wss.val * mss || + window == f->wss.val * SMART_MSS_1 || + window == f->wss.val * SMART_MSS_2) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MTU: + if (window == f->wss.val * (mss + 40) || + window == f->wss.val * (SMART_MSS_1 + 40) || + window == f->wss.val * (SMART_MSS_2 + 40)) + fmatch = FMATCH_OK; + break; + case OSF_WSS_MODULO: + if ((window % f->wss.val) == 0) + fmatch = FMATCH_OK; + break; + } + } + + if (fmatch != FMATCH_OK) + continue; + + fcount++; + + if (info->flags & NF_OSF_LOG) + nf_log_packet(net, family, hooknum, skb, + in, out, NULL, + "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", + f->genre, f->version, f->subtype, + &ip->saddr, ntohs(tcp->source), + &ip->daddr, ntohs(tcp->dest), + f->ttl - ip->ttl); + + if ((info->flags & NF_OSF_LOG) && + info->loglevel == NF_OSF_LOGLEVEL_FIRST) + break; + } + + if (!fcount && (info->flags & NF_OSF_LOG)) + nf_log_packet(net, family, hooknum, skb, in, out, NULL, + "Remote OS is not known: %pI4:%u -> %pI4:%u\n", + &ip->saddr, ntohs(tcp->source), + &ip->daddr, ntohs(tcp->dest)); + + if (fcount) + fmatch = FMATCH_OK; + + return fmatch == FMATCH_OK; +} +EXPORT_SYMBOL_GPL(nf_osf_match); + +MODULE_LICENSE("GPL"); diff --git a/net/netfilter/nf_tables_api.c b/net/netfilter/nf_tables_api.c index 04d4e3772584..18bd584fadda 100644 --- a/net/netfilter/nf_tables_api.c +++ b/net/netfilter/nf_tables_api.c @@ -386,13 +386,17 @@ static struct nft_table *nft_table_lookup(const struct net *net, { struct nft_table *table; + if (nla == NULL) + return ERR_PTR(-EINVAL); + list_for_each_entry(table, &net->nft.tables, list) { if (!nla_strcmp(nla, table->name) && table->family == family && nft_active_genmask(table, genmask)) return table; } - return NULL; + + return ERR_PTR(-ENOENT); } static struct nft_table *nft_table_lookup_byhandle(const struct net *net, @@ -406,37 +410,6 @@ static struct nft_table *nft_table_lookup_byhandle(const struct net *net, nft_active_genmask(table, genmask)) return table; } - return NULL; -} - -static struct nft_table *nf_tables_table_lookup(const struct net *net, - const struct nlattr *nla, - u8 family, u8 genmask) -{ - struct nft_table *table; - - if (nla == NULL) - return ERR_PTR(-EINVAL); - - table = nft_table_lookup(net, nla, family, genmask); - if (table != NULL) - return table; - - return ERR_PTR(-ENOENT); -} - -static struct nft_table *nf_tables_table_lookup_byhandle(const struct net *net, - const struct nlattr *nla, - u8 genmask) -{ - struct nft_table *table; - - if (nla == NULL) - return ERR_PTR(-EINVAL); - - table = nft_table_lookup_byhandle(net, nla, genmask); - if (table != NULL) - return table; return ERR_PTR(-ENOENT); } @@ -608,10 +581,11 @@ static int nf_tables_gettable(struct net *net, struct sock *nlsk, return netlink_dump_start(nlsk, skb, nlh, &c); } - table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_TABLE_NAME], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_TABLE_NAME]); return PTR_ERR(table); + } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -727,21 +701,23 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); - const struct nlattr *name; - struct nft_table *table; int family = nfmsg->nfgen_family; + const struct nlattr *attr; + struct nft_table *table; u32 flags = 0; struct nft_ctx ctx; int err; - name = nla[NFTA_TABLE_NAME]; - table = nf_tables_table_lookup(net, name, family, genmask); + attr = nla[NFTA_TABLE_NAME]; + table = nft_table_lookup(net, attr, family, genmask); if (IS_ERR(table)) { if (PTR_ERR(table) != -ENOENT) return PTR_ERR(table); } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; @@ -760,7 +736,7 @@ static int nf_tables_newtable(struct net *net, struct sock *nlsk, if (table == NULL) goto err_kzalloc; - table->name = nla_strdup(name, GFP_KERNEL); + table->name = nla_strdup(attr, GFP_KERNEL); if (table->name == NULL) goto err_strdup; @@ -883,8 +859,9 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); - struct nft_table *table; int family = nfmsg->nfgen_family; + const struct nlattr *attr; + struct nft_table *table; struct nft_ctx ctx; nft_ctx_init(&ctx, net, skb, nlh, 0, NULL, NULL, nla); @@ -892,16 +869,18 @@ static int nf_tables_deltable(struct net *net, struct sock *nlsk, (!nla[NFTA_TABLE_NAME] && !nla[NFTA_TABLE_HANDLE])) return nft_flush(&ctx, family); - if (nla[NFTA_TABLE_HANDLE]) - table = nf_tables_table_lookup_byhandle(net, - nla[NFTA_TABLE_HANDLE], - genmask); - else - table = nf_tables_table_lookup(net, nla[NFTA_TABLE_NAME], - family, genmask); + if (nla[NFTA_TABLE_HANDLE]) { + attr = nla[NFTA_TABLE_HANDLE]; + table = nft_table_lookup_byhandle(net, attr, genmask); + } else { + attr = nla[NFTA_TABLE_NAME]; + table = nft_table_lookup(net, attr, family, genmask); + } - if (IS_ERR(table)) + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(table); + } if (nlh->nlmsg_flags & NLM_F_NONREC && table->use > 0) @@ -949,8 +928,7 @@ EXPORT_SYMBOL_GPL(nft_unregister_chain_type); */ static struct nft_chain * -nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle, - u8 genmask) +nft_chain_lookup_byhandle(const struct nft_table *table, u64 handle, u8 genmask) { struct nft_chain *chain; @@ -963,9 +941,8 @@ nf_tables_chain_lookup_byhandle(const struct nft_table *table, u64 handle, return ERR_PTR(-ENOENT); } -static struct nft_chain *nf_tables_chain_lookup(const struct nft_table *table, - const struct nlattr *nla, - u8 genmask) +static struct nft_chain *nft_chain_lookup(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_chain *chain; @@ -1194,14 +1171,17 @@ static int nf_tables_getchain(struct net *net, struct sock *nlsk, return netlink_dump_start(nlsk, skb, nlh, &c); } - table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); + } - chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_NAME]); return PTR_ERR(chain); + } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -1513,8 +1493,7 @@ static int nf_tables_updchain(struct nft_ctx *ctx, u8 genmask, u8 policy, nla[NFTA_CHAIN_NAME]) { struct nft_chain *chain2; - chain2 = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], - genmask); + chain2 = nft_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); if (!IS_ERR(chain2)) return -EEXIST; } @@ -1564,9 +1543,9 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, struct netlink_ext_ack *extack) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); - const struct nlattr * uninitialized_var(name); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; + const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; u8 policy = NF_ACCEPT; @@ -1576,36 +1555,46 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); + } chain = NULL; - name = nla[NFTA_CHAIN_NAME]; + attr = nla[NFTA_CHAIN_NAME]; if (nla[NFTA_CHAIN_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); - chain = nf_tables_chain_lookup_byhandle(table, handle, genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup_byhandle(table, handle, genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_HANDLE]); return PTR_ERR(chain); + } + attr = nla[NFTA_CHAIN_HANDLE]; } else { - chain = nf_tables_chain_lookup(table, name, genmask); + chain = nft_chain_lookup(table, attr, genmask); if (IS_ERR(chain)) { - if (PTR_ERR(chain) != -ENOENT) + if (PTR_ERR(chain) != -ENOENT) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); + } chain = NULL; } } if (nla[NFTA_CHAIN_POLICY]) { if (chain != NULL && - !nft_is_base_chain(chain)) + !nft_is_base_chain(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; + } if (chain == NULL && - nla[NFTA_CHAIN_HOOK] == NULL) + nla[NFTA_CHAIN_HOOK] == NULL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_POLICY]); return -EOPNOTSUPP; + } policy = ntohl(nla_get_be32(nla[NFTA_CHAIN_POLICY])); switch (policy) { @@ -1620,8 +1609,10 @@ static int nf_tables_newchain(struct net *net, struct sock *nlsk, nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); if (chain != NULL) { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, attr); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; @@ -1638,28 +1629,34 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); + int family = nfmsg->nfgen_family; + const struct nlattr *attr; struct nft_table *table; struct nft_chain *chain; struct nft_rule *rule; - int family = nfmsg->nfgen_family; struct nft_ctx ctx; u64 handle; u32 use; int err; - table = nf_tables_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_CHAIN_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_CHAIN_TABLE]); return PTR_ERR(table); + } if (nla[NFTA_CHAIN_HANDLE]) { - handle = be64_to_cpu(nla_get_be64(nla[NFTA_CHAIN_HANDLE])); - chain = nf_tables_chain_lookup_byhandle(table, handle, genmask); + attr = nla[NFTA_CHAIN_HANDLE]; + handle = be64_to_cpu(nla_get_be64(attr)); + chain = nft_chain_lookup_byhandle(table, handle, genmask); } else { - chain = nf_tables_chain_lookup(table, nla[NFTA_CHAIN_NAME], genmask); + attr = nla[NFTA_CHAIN_NAME]; + chain = nft_chain_lookup(table, attr, genmask); } - if (IS_ERR(chain)) + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(chain); + } if (nlh->nlmsg_flags & NLM_F_NONREC && chain->use > 0) @@ -1681,8 +1678,10 @@ static int nf_tables_delchain(struct net *net, struct sock *nlsk, /* There are rules and elements that are still holding references to us, * we cannot do a recursive removal in this case. */ - if (use > 0) + if (use > 0) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } return nft_delchain(&ctx); } @@ -1939,8 +1938,8 @@ void nft_expr_destroy(const struct nft_ctx *ctx, struct nft_expr *expr) * Rules */ -static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain, - u64 handle) +static struct nft_rule *__nft_rule_lookup(const struct nft_chain *chain, + u64 handle) { struct nft_rule *rule; @@ -1953,13 +1952,13 @@ static struct nft_rule *__nf_tables_rule_lookup(const struct nft_chain *chain, return ERR_PTR(-ENOENT); } -static struct nft_rule *nf_tables_rule_lookup(const struct nft_chain *chain, - const struct nlattr *nla) +static struct nft_rule *nft_rule_lookup(const struct nft_chain *chain, + const struct nlattr *nla) { if (nla == NULL) return ERR_PTR(-EINVAL); - return __nf_tables_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla))); + return __nft_rule_lookup(chain, be64_to_cpu(nla_get_be64(nla))); } static const struct nla_policy nft_rule_policy[NFTA_RULE_MAX + 1] = { @@ -2191,18 +2190,23 @@ static int nf_tables_getrule(struct net *net, struct sock *nlsk, return netlink_dump_start(nlsk, skb, nlh, &c); } - table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); + } - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); + } - rule = nf_tables_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); - if (IS_ERR(rule)) + rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); + } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -2265,23 +2269,30 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); + } - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); + } if (nla[NFTA_RULE_HANDLE]) { handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_HANDLE])); - rule = __nf_tables_rule_lookup(chain, handle); - if (IS_ERR(rule)) + rule = __nft_rule_lookup(chain, handle); + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); + } - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) old_rule = rule; else @@ -2300,9 +2311,11 @@ static int nf_tables_newrule(struct net *net, struct sock *nlsk, return -EOPNOTSUPP; pos_handle = be64_to_cpu(nla_get_be64(nla[NFTA_RULE_POSITION])); - old_rule = __nf_tables_rule_lookup(chain, pos_handle); - if (IS_ERR(old_rule)) + old_rule = __nft_rule_lookup(chain, pos_handle); + if (IS_ERR(old_rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_POSITION]); return PTR_ERR(old_rule); + } } nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); @@ -2440,32 +2453,37 @@ static int nf_tables_delrule(struct net *net, struct sock *nlsk, int family = nfmsg->nfgen_family, err = 0; struct nft_ctx ctx; - table = nf_tables_table_lookup(net, nla[NFTA_RULE_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_RULE_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_TABLE]); return PTR_ERR(table); + } if (nla[NFTA_RULE_CHAIN]) { - chain = nf_tables_chain_lookup(table, nla[NFTA_RULE_CHAIN], - genmask); - if (IS_ERR(chain)) + chain = nft_chain_lookup(table, nla[NFTA_RULE_CHAIN], genmask); + if (IS_ERR(chain)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_CHAIN]); return PTR_ERR(chain); + } } nft_ctx_init(&ctx, net, skb, nlh, family, table, chain, nla); if (chain) { if (nla[NFTA_RULE_HANDLE]) { - rule = nf_tables_rule_lookup(chain, - nla[NFTA_RULE_HANDLE]); - if (IS_ERR(rule)) + rule = nft_rule_lookup(chain, nla[NFTA_RULE_HANDLE]); + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_HANDLE]); return PTR_ERR(rule); + } err = nft_delrule(&ctx, rule); } else if (nla[NFTA_RULE_ID]) { rule = nft_rule_lookup_byid(net, nla[NFTA_RULE_ID]); - if (IS_ERR(rule)) + if (IS_ERR(rule)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_RULE_ID]); return PTR_ERR(rule); + } err = nft_delrule(&ctx, rule); } else { @@ -2510,14 +2528,12 @@ void nft_unregister_set(struct nft_set_type *type) EXPORT_SYMBOL_GPL(nft_unregister_set); #define NFT_SET_FEATURES (NFT_SET_INTERVAL | NFT_SET_MAP | \ - NFT_SET_TIMEOUT | NFT_SET_OBJECT) + NFT_SET_TIMEOUT | NFT_SET_OBJECT | \ + NFT_SET_EVAL) -static bool nft_set_ops_candidate(const struct nft_set_ops *ops, u32 flags) +static bool nft_set_ops_candidate(const struct nft_set_type *type, u32 flags) { - if ((flags & NFT_SET_EVAL) && !ops->update) - return false; - - return (flags & ops->features) == (flags & NFT_SET_FEATURES); + return (flags & type->features) == (flags & NFT_SET_FEATURES); } /* @@ -2554,14 +2570,9 @@ nft_select_set_ops(const struct nft_ctx *ctx, best.space = ~0; list_for_each_entry(type, &nf_tables_set_types, list) { - if (!type->select_ops) - ops = type->ops; - else - ops = type->select_ops(ctx, desc, flags); - if (!ops) - continue; + ops = &type->ops; - if (!nft_set_ops_candidate(ops, flags)) + if (!nft_set_ops_candidate(type, flags)) continue; if (!ops->estimate(desc, flags, &est)) continue; @@ -2592,7 +2603,7 @@ nft_select_set_ops(const struct nft_ctx *ctx, if (!try_module_get(type->owner)) continue; if (bops != NULL) - module_put(bops->type->owner); + module_put(to_set_type(bops)->owner); bops = ops; best = est; @@ -2633,6 +2644,7 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], + struct netlink_ext_ack *extack, u8 genmask) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); @@ -2640,18 +2652,20 @@ static int nft_ctx_init_from_setattr(struct nft_ctx *ctx, struct net *net, struct nft_table *table = NULL; if (nla[NFTA_SET_TABLE] != NULL) { - table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); + } } nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); return 0; } -static struct nft_set *nf_tables_set_lookup(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +static struct nft_set *nft_set_lookup(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_set *set; @@ -2666,14 +2680,12 @@ static struct nft_set *nf_tables_set_lookup(const struct nft_table *table, return ERR_PTR(-ENOENT); } -static struct nft_set *nf_tables_set_lookup_byhandle(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +static struct nft_set *nft_set_lookup_byhandle(const struct nft_table *table, + const struct nlattr *nla, + u8 genmask) { struct nft_set *set; - if (nla == NULL) - return ERR_PTR(-EINVAL); - list_for_each_entry(set, &table->sets, list) { if (be64_to_cpu(nla_get_be64(nla)) == set->handle && nft_active_genmask(set, genmask)) @@ -2682,9 +2694,8 @@ static struct nft_set *nf_tables_set_lookup_byhandle(const struct nft_table *tab return ERR_PTR(-ENOENT); } -static struct nft_set *nf_tables_set_lookup_byid(const struct net *net, - const struct nlattr *nla, - u8 genmask) +static struct nft_set *nft_set_lookup_byid(const struct net *net, + const struct nlattr *nla, u8 genmask) { struct nft_trans *trans; u32 id = ntohl(nla_get_be32(nla)); @@ -2708,12 +2719,12 @@ struct nft_set *nft_set_lookup_global(const struct net *net, { struct nft_set *set; - set = nf_tables_set_lookup(table, nla_set_name, genmask); + set = nft_set_lookup(table, nla_set_name, genmask); if (IS_ERR(set)) { if (!nla_set_id) return set; - set = nf_tables_set_lookup_byid(net, nla_set_id, genmask); + set = nft_set_lookup_byid(net, nla_set_id, genmask); } return set; } @@ -2773,6 +2784,27 @@ cont: return 0; } +static int nf_msecs_to_jiffies64(const struct nlattr *nla, u64 *result) +{ + u64 ms = be64_to_cpu(nla_get_be64(nla)); + u64 max = (u64)(~((u64)0)); + + max = div_u64(max, NSEC_PER_MSEC); + if (ms >= max) + return -ERANGE; + + ms *= NSEC_PER_MSEC; + *result = nsecs_to_jiffies64(ms); + return 0; +} + +static u64 nf_jiffies64_to_msecs(u64 input) +{ + u64 ms = jiffies64_to_nsecs(input); + + return cpu_to_be64(div_u64(ms, NSEC_PER_MSEC)); +} + static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, const struct nft_set *set, u16 event, u16 flags) { @@ -2820,7 +2852,7 @@ static int nf_tables_fill_set(struct sk_buff *skb, const struct nft_ctx *ctx, if (set->timeout && nla_put_be64(skb, NFTA_SET_TIMEOUT, - cpu_to_be64(jiffies_to_msecs(set->timeout)), + nf_jiffies64_to_msecs(set->timeout), NFTA_SET_PAD)) goto nla_put_failure; if (set->gc_int && @@ -2958,7 +2990,8 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, int err; /* Verify existence before starting dump */ - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; @@ -2985,7 +3018,7 @@ static int nf_tables_getset(struct net *net, struct sock *nlsk, if (!nla[NFTA_SET_TABLE]) return -EINVAL; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -3115,8 +3148,10 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TIMEOUT] != NULL) { if (!(flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( - nla[NFTA_SET_TIMEOUT]))); + + err = nf_msecs_to_jiffies64(nla[NFTA_SET_TIMEOUT], &timeout); + if (err) + return err; } gc_int = 0; if (nla[NFTA_SET_GC_INTERVAL] != NULL) { @@ -3137,22 +3172,28 @@ static int nf_tables_newset(struct net *net, struct sock *nlsk, create = nlh->nlmsg_flags & NLM_F_CREATE ? true : false; - table = nf_tables_table_lookup(net, nla[NFTA_SET_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_SET_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_TABLE]); return PTR_ERR(table); + } nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); - set = nf_tables_set_lookup(table, nla[NFTA_SET_NAME], genmask); + set = nft_set_lookup(table, nla[NFTA_SET_NAME], genmask); if (IS_ERR(set)) { - if (PTR_ERR(set) != -ENOENT) + if (PTR_ERR(set) != -ENOENT) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return PTR_ERR(set); + } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_NAME]); return -EEXIST; + } if (nlh->nlmsg_flags & NLM_F_REPLACE) return -EOPNOTSUPP; + return 0; } @@ -3229,14 +3270,14 @@ err3: err2: kvfree(set); err1: - module_put(ops->type->owner); + module_put(to_set_type(ops)->owner); return err; } static void nft_set_destroy(struct nft_set *set) { set->ops->destroy(set); - module_put(set->ops->type->owner); + module_put(to_set_type(set->ops)->owner); kfree(set->name); kvfree(set); } @@ -3255,6 +3296,7 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); + const struct nlattr *attr; struct nft_set *set; struct nft_ctx ctx; int err; @@ -3264,20 +3306,28 @@ static int nf_tables_delset(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_TABLE] == NULL) return -EINVAL; - err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_setattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; - if (nla[NFTA_SET_HANDLE]) - set = nf_tables_set_lookup_byhandle(ctx.table, nla[NFTA_SET_HANDLE], genmask); - else - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_NAME], genmask); - if (IS_ERR(set)) - return PTR_ERR(set); + if (nla[NFTA_SET_HANDLE]) { + attr = nla[NFTA_SET_HANDLE]; + set = nft_set_lookup_byhandle(ctx.table, attr, genmask); + } else { + attr = nla[NFTA_SET_NAME]; + set = nft_set_lookup(ctx.table, attr, genmask); + } + if (IS_ERR(set)) { + NL_SET_BAD_ATTR(extack, attr); + return PTR_ERR(set); + } if (!list_empty(&set->bindings) || - (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) + (nlh->nlmsg_flags & NLM_F_NONREC && atomic_read(&set->nelems) > 0)) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } return nft_delset(&ctx, set); } @@ -3367,8 +3417,8 @@ const struct nft_set_ext_type nft_set_ext_types[] = { .align = __alignof__(u64), }, [NFT_SET_EXT_EXPIRATION] = { - .len = sizeof(unsigned long), - .align = __alignof__(unsigned long), + .len = sizeof(u64), + .align = __alignof__(u64), }, [NFT_SET_EXT_USERDATA] = { .len = sizeof(struct nft_userdata), @@ -3405,16 +3455,19 @@ static int nft_ctx_init_from_elemattr(struct nft_ctx *ctx, struct net *net, const struct sk_buff *skb, const struct nlmsghdr *nlh, const struct nlattr * const nla[], + struct netlink_ext_ack *extack, u8 genmask) { const struct nfgenmsg *nfmsg = nlmsg_data(nlh); int family = nfmsg->nfgen_family; struct nft_table *table; - table = nf_tables_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_SET_ELEM_LIST_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_SET_ELEM_LIST_TABLE]); return PTR_ERR(table); + } nft_ctx_init(ctx, net, skb, nlh, family, table, NULL, nla); return 0; @@ -3458,22 +3511,21 @@ static int nf_tables_fill_setelem(struct sk_buff *skb, if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT) && nla_put_be64(skb, NFTA_SET_ELEM_TIMEOUT, - cpu_to_be64(jiffies_to_msecs( - *nft_set_ext_timeout(ext))), + nf_jiffies64_to_msecs(*nft_set_ext_timeout(ext)), NFTA_SET_ELEM_PAD)) goto nla_put_failure; if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { - unsigned long expires, now = jiffies; + u64 expires, now = get_jiffies_64(); expires = *nft_set_ext_expiration(ext); - if (time_before(now, expires)) + if (time_before64(now, expires)) expires -= now; else expires = 0; if (nla_put_be64(skb, NFTA_SET_ELEM_EXPIRATION, - cpu_to_be64(jiffies_to_msecs(expires)), + nf_jiffies64_to_msecs(expires), NFTA_SET_ELEM_PAD)) goto nla_put_failure; } @@ -3744,12 +3796,12 @@ static int nf_tables_getsetelem(struct net *net, struct sock *nlsk, struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], - genmask); + set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); @@ -3848,7 +3900,7 @@ void *nft_set_elem_init(const struct nft_set *set, memcpy(nft_set_ext_data(ext), data, set->dlen); if (nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) *nft_set_ext_expiration(ext) = - jiffies + timeout; + get_jiffies_64() + timeout; if (nft_set_ext_exists(ext, NFT_SET_EXT_TIMEOUT)) *nft_set_ext_timeout(ext) = timeout; @@ -3935,8 +3987,10 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, if (nla[NFTA_SET_ELEM_TIMEOUT] != NULL) { if (!(set->flags & NFT_SET_TIMEOUT)) return -EINVAL; - timeout = msecs_to_jiffies(be64_to_cpu(nla_get_be64( - nla[NFTA_SET_ELEM_TIMEOUT]))); + err = nf_msecs_to_jiffies64(nla[NFTA_SET_ELEM_TIMEOUT], + &timeout); + if (err) + return err; } else if (set->flags & NFT_SET_TIMEOUT) { timeout = set->timeout; } @@ -3961,8 +4015,8 @@ static int nft_add_set_elem(struct nft_ctx *ctx, struct nft_set *set, err = -EINVAL; goto err2; } - obj = nf_tables_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], - set->objtype, genmask); + obj = nft_obj_lookup(ctx->table, nla[NFTA_SET_ELEM_OBJREF], + set->objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); goto err2; @@ -4099,7 +4153,8 @@ static int nf_tables_newsetelem(struct net *net, struct sock *nlsk, if (nla[NFTA_SET_ELEM_LIST_ELEMENTS] == NULL) return -EINVAL; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; @@ -4287,12 +4342,12 @@ static int nf_tables_delsetelem(struct net *net, struct sock *nlsk, struct nft_ctx ctx; int rem, err = 0; - err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, genmask); + err = nft_ctx_init_from_elemattr(&ctx, net, skb, nlh, nla, extack, + genmask); if (err < 0) return err; - set = nf_tables_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], - genmask); + set = nft_set_lookup(ctx.table, nla[NFTA_SET_ELEM_LIST_SET], genmask); if (IS_ERR(set)) return PTR_ERR(set); if (!list_empty(&set->bindings) && set->flags & NFT_SET_CONSTANT) @@ -4380,9 +4435,9 @@ void nft_unregister_obj(struct nft_object_type *obj_type) } EXPORT_SYMBOL_GPL(nft_unregister_obj); -struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, - const struct nlattr *nla, - u32 objtype, u8 genmask) +struct nft_object *nft_obj_lookup(const struct nft_table *table, + const struct nlattr *nla, u32 objtype, + u8 genmask) { struct nft_object *obj; @@ -4394,11 +4449,11 @@ struct nft_object *nf_tables_obj_lookup(const struct nft_table *table, } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_obj_lookup); +EXPORT_SYMBOL_GPL(nft_obj_lookup); -static struct nft_object *nf_tables_obj_lookup_byhandle(const struct nft_table *table, - const struct nlattr *nla, - u32 objtype, u8 genmask) +static struct nft_object *nft_obj_lookup_byhandle(const struct nft_table *table, + const struct nlattr *nla, + u32 objtype, u8 genmask) { struct nft_object *obj; @@ -4542,22 +4597,25 @@ static int nf_tables_newobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_DATA]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); + } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); if (IS_ERR(obj)) { err = PTR_ERR(obj); - if (err != -ENOENT) + if (err != -ENOENT) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return err; - + } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return -EEXIST; - + } return 0; } @@ -4768,15 +4826,18 @@ static int nf_tables_getobj(struct net *net, struct sock *nlsk, !nla[NFTA_OBJ_TYPE]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); + } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); - if (IS_ERR(obj)) + obj = nft_obj_lookup(table, nla[NFTA_OBJ_NAME], objtype, genmask); + if (IS_ERR(obj)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_NAME]); return PTR_ERR(obj); + } skb2 = alloc_skb(NLMSG_GOODSIZE, GFP_KERNEL); if (!skb2) @@ -4815,6 +4876,7 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, const struct nfgenmsg *nfmsg = nlmsg_data(nlh); u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; + const struct nlattr *attr; struct nft_table *table; struct nft_object *obj; struct nft_ctx ctx; @@ -4824,22 +4886,29 @@ static int nf_tables_delobj(struct net *net, struct sock *nlsk, (!nla[NFTA_OBJ_NAME] && !nla[NFTA_OBJ_HANDLE])) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_OBJ_TABLE], family, - genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_OBJ_TABLE], family, genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_OBJ_TABLE]); return PTR_ERR(table); + } objtype = ntohl(nla_get_be32(nla[NFTA_OBJ_TYPE])); - if (nla[NFTA_OBJ_HANDLE]) - obj = nf_tables_obj_lookup_byhandle(table, nla[NFTA_OBJ_HANDLE], - objtype, genmask); - else - obj = nf_tables_obj_lookup(table, nla[NFTA_OBJ_NAME], - objtype, genmask); - if (IS_ERR(obj)) + if (nla[NFTA_OBJ_HANDLE]) { + attr = nla[NFTA_OBJ_HANDLE]; + obj = nft_obj_lookup_byhandle(table, attr, objtype, genmask); + } else { + attr = nla[NFTA_OBJ_NAME]; + obj = nft_obj_lookup(table, attr, objtype, genmask); + } + + if (IS_ERR(obj)) { + NL_SET_BAD_ATTR(extack, attr); return PTR_ERR(obj); - if (obj->use > 0) + } + if (obj->use > 0) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); @@ -4910,9 +4979,8 @@ static const struct nla_policy nft_flowtable_policy[NFTA_FLOWTABLE_MAX + 1] = { [NFTA_FLOWTABLE_HANDLE] = { .type = NLA_U64 }, }; -struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table, - const struct nlattr *nla, - u8 genmask) +struct nft_flowtable *nft_flowtable_lookup(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; @@ -4923,11 +4991,11 @@ struct nft_flowtable *nf_tables_flowtable_lookup(const struct nft_table *table, } return ERR_PTR(-ENOENT); } -EXPORT_SYMBOL_GPL(nf_tables_flowtable_lookup); +EXPORT_SYMBOL_GPL(nft_flowtable_lookup); static struct nft_flowtable * -nf_tables_flowtable_lookup_byhandle(const struct nft_table *table, - const struct nlattr *nla, u8 genmask) +nft_flowtable_lookup_byhandle(const struct nft_table *table, + const struct nlattr *nla, u8 genmask) { struct nft_flowtable *flowtable; @@ -5026,7 +5094,7 @@ static int nf_tables_flowtable_parse_hook(const struct nft_ctx *ctx, flowtable->ops[i].pf = NFPROTO_NETDEV; flowtable->ops[i].hooknum = hooknum; flowtable->ops[i].priority = priority; - flowtable->ops[i].priv = &flowtable->data.rhashtable; + flowtable->ops[i].priv = &flowtable->data; flowtable->ops[i].hook = flowtable->data.type->hook; flowtable->ops[i].dev = dev_array[i]; flowtable->dev_name[i] = kstrdup(dev_array[i]->name, @@ -5067,23 +5135,6 @@ static const struct nf_flowtable_type *nft_flowtable_type_get(u8 family) return ERR_PTR(-ENOENT); } -void nft_flow_table_iterate(struct net *net, - void (*iter)(struct nf_flowtable *flowtable, void *data), - void *data) -{ - struct nft_flowtable *flowtable; - const struct nft_table *table; - - nfnl_lock(NFNL_SUBSYS_NFTABLES); - list_for_each_entry(table, &net->nft.tables, list) { - list_for_each_entry(flowtable, &table->flowtables, list) { - iter(&flowtable->data, data); - } - } - nfnl_unlock(NFNL_SUBSYS_NFTABLES); -} -EXPORT_SYMBOL_GPL(nft_flow_table_iterate); - static void nft_unregister_flowtable_net_hooks(struct net *net, struct nft_flowtable *flowtable) { @@ -5117,20 +5168,26 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, !nla[NFTA_FLOWTABLE_HOOK]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); + } - flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], - genmask); + flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], + genmask); if (IS_ERR(flowtable)) { err = PTR_ERR(flowtable); - if (err != -ENOENT) + if (err != -ENOENT) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return err; + } } else { - if (nlh->nlmsg_flags & NLM_F_EXCL) + if (nlh->nlmsg_flags & NLM_F_EXCL) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_NAME]); return -EEXIST; + } return 0; } @@ -5157,14 +5214,14 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, } flowtable->data.type = type; - err = rhashtable_init(&flowtable->data.rhashtable, type->params); + err = type->init(&flowtable->data); if (err < 0) goto err3; err = nf_tables_flowtable_parse_hook(&ctx, nla[NFTA_FLOWTABLE_HOOK], flowtable); if (err < 0) - goto err3; + goto err4; for (i = 0; i < flowtable->ops_len; i++) { if (!flowtable->ops[i].dev) @@ -5178,37 +5235,35 @@ static int nf_tables_newflowtable(struct net *net, struct sock *nlsk, if (flowtable->ops[i].dev == ft->ops[k].dev && flowtable->ops[i].pf == ft->ops[k].pf) { err = -EBUSY; - goto err4; + goto err5; } } } err = nf_register_net_hook(net, &flowtable->ops[i]); if (err < 0) - goto err4; + goto err5; } err = nft_trans_flowtable_add(&ctx, NFT_MSG_NEWFLOWTABLE, flowtable); if (err < 0) - goto err5; - - INIT_DEFERRABLE_WORK(&flowtable->data.gc_work, type->gc); - queue_delayed_work(system_power_efficient_wq, - &flowtable->data.gc_work, HZ); + goto err6; list_add_tail_rcu(&flowtable->list, &table->flowtables); table->use++; return 0; -err5: +err6: i = flowtable->ops_len; -err4: +err5: for (k = i - 1; k >= 0; k--) { kfree(flowtable->dev_name[k]); nf_unregister_net_hook(net, &flowtable->ops[k]); } kfree(flowtable->ops); +err4: + flowtable->data.type->free(&flowtable->data); err3: module_put(type->owner); err2: @@ -5228,6 +5283,7 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, u8 genmask = nft_genmask_next(net); int family = nfmsg->nfgen_family; struct nft_flowtable *flowtable; + const struct nlattr *attr; struct nft_table *table; struct nft_ctx ctx; @@ -5236,23 +5292,29 @@ static int nf_tables_delflowtable(struct net *net, struct sock *nlsk, !nla[NFTA_FLOWTABLE_HANDLE])) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], - family, genmask); - if (IS_ERR(table)) + table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, + genmask); + if (IS_ERR(table)) { + NL_SET_BAD_ATTR(extack, nla[NFTA_FLOWTABLE_TABLE]); return PTR_ERR(table); + } - if (nla[NFTA_FLOWTABLE_HANDLE]) - flowtable = nf_tables_flowtable_lookup_byhandle(table, - nla[NFTA_FLOWTABLE_HANDLE], - genmask); - else - flowtable = nf_tables_flowtable_lookup(table, - nla[NFTA_FLOWTABLE_NAME], - genmask); - if (IS_ERR(flowtable)) - return PTR_ERR(flowtable); - if (flowtable->use > 0) + if (nla[NFTA_FLOWTABLE_HANDLE]) { + attr = nla[NFTA_FLOWTABLE_HANDLE]; + flowtable = nft_flowtable_lookup_byhandle(table, attr, genmask); + } else { + attr = nla[NFTA_FLOWTABLE_NAME]; + flowtable = nft_flowtable_lookup(table, attr, genmask); + } + + if (IS_ERR(flowtable)) { + NL_SET_BAD_ATTR(extack, attr); + return PTR_ERR(flowtable); + } + if (flowtable->use > 0) { + NL_SET_BAD_ATTR(extack, attr); return -EBUSY; + } nft_ctx_init(&ctx, net, skb, nlh, family, table, NULL, nla); @@ -5433,13 +5495,13 @@ static int nf_tables_getflowtable(struct net *net, struct sock *nlsk, if (!nla[NFTA_FLOWTABLE_NAME]) return -EINVAL; - table = nf_tables_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], - family, genmask); + table = nft_table_lookup(net, nla[NFTA_FLOWTABLE_TABLE], family, + genmask); if (IS_ERR(table)) return PTR_ERR(table); - flowtable = nf_tables_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], - genmask); + flowtable = nft_flowtable_lookup(table, nla[NFTA_FLOWTABLE_NAME], + genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); @@ -5492,11 +5554,9 @@ err: static void nf_tables_flowtable_destroy(struct nft_flowtable *flowtable) { - cancel_delayed_work_sync(&flowtable->data.gc_work); kfree(flowtable->ops); kfree(flowtable->name); flowtable->data.type->free(&flowtable->data); - rhashtable_destroy(&flowtable->data.rhashtable); module_put(flowtable->data.type->owner); } @@ -6410,8 +6470,8 @@ static int nft_verdict_init(const struct nft_ctx *ctx, struct nft_data *data, case NFT_GOTO: if (!tb[NFTA_VERDICT_CHAIN]) return -EINVAL; - chain = nf_tables_chain_lookup(ctx->table, - tb[NFTA_VERDICT_CHAIN], genmask); + chain = nft_chain_lookup(ctx->table, tb[NFTA_VERDICT_CHAIN], + genmask); if (IS_ERR(chain)) return PTR_ERR(chain); if (nft_is_base_chain(chain)) diff --git a/net/netfilter/nf_tables_core.c b/net/netfilter/nf_tables_core.c index dfd0bf3810d2..9cf47c4cb9d5 100644 --- a/net/netfilter/nf_tables_core.c +++ b/net/netfilter/nf_tables_core.c @@ -251,6 +251,9 @@ static struct nft_expr_type *nft_basic_types[] = { &nft_payload_type, &nft_dynset_type, &nft_range_type, + &nft_meta_type, + &nft_rt_type, + &nft_exthdr_type, }; int __init nf_tables_core_module_init(void) diff --git a/net/netfilter/nfnetlink_log.c b/net/netfilter/nfnetlink_log.c index 7b46aa4c478d..e5cc4d9b9ce7 100644 --- a/net/netfilter/nfnetlink_log.c +++ b/net/netfilter/nfnetlink_log.c @@ -37,7 +37,6 @@ #include <net/sock.h> #include <net/netfilter/nf_log.h> #include <net/netns/generic.h> -#include <net/netfilter/nfnetlink_log.h> #include <linux/atomic.h> #include <linux/refcount.h> @@ -47,6 +46,7 @@ #include "../bridge/br_private.h" #endif +#define NFULNL_COPY_DISABLED 0xff #define NFULNL_NLBUFSIZ_DEFAULT NLMSG_GOODSIZE #define NFULNL_TIMEOUT_DEFAULT 100 /* every second */ #define NFULNL_QTHRESH_DEFAULT 100 /* 100 packets */ @@ -618,7 +618,7 @@ static const struct nf_loginfo default_loginfo = { }; /* log handler for internal netfilter logging api */ -void +static void nfulnl_log_packet(struct net *net, u_int8_t pf, unsigned int hooknum, @@ -633,7 +633,7 @@ nfulnl_log_packet(struct net *net, struct nfulnl_instance *inst; const struct nf_loginfo *li; unsigned int qthreshold; - unsigned int plen; + unsigned int plen = 0; struct nfnl_log_net *log = nfnl_log_pernet(net); const struct nfnl_ct_hook *nfnl_ct = NULL; struct nf_conn *ct = NULL; @@ -648,7 +648,6 @@ nfulnl_log_packet(struct net *net, if (!inst) return; - plen = 0; if (prefix) plen = strlen(prefix) + 1; @@ -760,7 +759,6 @@ alloc_failure: /* FIXME: statistics */ goto unlock_and_release; } -EXPORT_SYMBOL_GPL(nfulnl_log_packet); static int nfulnl_rcv_nl_event(struct notifier_block *this, diff --git a/net/netfilter/nft_dynset.c b/net/netfilter/nft_dynset.c index 04863fad05dd..b07a3fd9eeea 100644 --- a/net/netfilter/nft_dynset.c +++ b/net/netfilter/nft_dynset.c @@ -36,7 +36,7 @@ static void *nft_dynset_new(struct nft_set *set, const struct nft_expr *expr, u64 timeout; void *elem; - if (set->size && !atomic_add_unless(&set->nelems, 1, set->size)) + if (!atomic_add_unless(&set->nelems, 1, set->size)) return NULL; timeout = priv->timeout ? : set->timeout; @@ -81,7 +81,7 @@ static void nft_dynset_eval(const struct nft_expr *expr, if (priv->op == NFT_DYNSET_OP_UPDATE && nft_set_ext_exists(ext, NFT_SET_EXT_EXPIRATION)) { timeout = priv->timeout ? : set->timeout; - *nft_set_ext_expiration(ext) = jiffies + timeout; + *nft_set_ext_expiration(ext) = get_jiffies_64() + timeout; } if (sexpr != NULL) @@ -216,6 +216,9 @@ static int nft_dynset_init(const struct nft_ctx *ctx, if (err < 0) goto err1; + if (set->size == 0) + set->size = 0xffff; + priv->set = set; return 0; diff --git a/net/netfilter/nft_exthdr.c b/net/netfilter/nft_exthdr.c index 47ec1046ad11..a940c9fd9045 100644 --- a/net/netfilter/nft_exthdr.c +++ b/net/netfilter/nft_exthdr.c @@ -10,11 +10,10 @@ #include <asm/unaligned.h> #include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> +#include <net/netfilter/nf_tables_core.h> #include <net/netfilter/nf_tables.h> #include <net/tcp.h> @@ -353,7 +352,6 @@ static int nft_exthdr_dump_set(struct sk_buff *skb, const struct nft_expr *expr) return nft_exthdr_dump_common(skb, priv); } -static struct nft_expr_type nft_exthdr_type; static const struct nft_expr_ops nft_exthdr_ipv6_ops = { .type = &nft_exthdr_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_exthdr)), @@ -407,27 +405,10 @@ nft_exthdr_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EOPNOTSUPP); } -static struct nft_expr_type nft_exthdr_type __read_mostly = { +struct nft_expr_type nft_exthdr_type __read_mostly = { .name = "exthdr", .select_ops = nft_exthdr_select_ops, .policy = nft_exthdr_policy, .maxattr = NFTA_EXTHDR_MAX, .owner = THIS_MODULE, }; - -static int __init nft_exthdr_module_init(void) -{ - return nft_register_expr(&nft_exthdr_type); -} - -static void __exit nft_exthdr_module_exit(void) -{ - nft_unregister_expr(&nft_exthdr_type); -} - -module_init(nft_exthdr_module_init); -module_exit(nft_exthdr_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("exthdr"); diff --git a/net/netfilter/nft_flow_offload.c b/net/netfilter/nft_flow_offload.c index b65829b2be22..d6bab8c3cbb0 100644 --- a/net/netfilter/nft_flow_offload.c +++ b/net/netfilter/nft_flow_offload.c @@ -142,9 +142,8 @@ static int nft_flow_offload_init(const struct nft_ctx *ctx, if (!tb[NFTA_FLOW_TABLE_NAME]) return -EINVAL; - flowtable = nf_tables_flowtable_lookup(ctx->table, - tb[NFTA_FLOW_TABLE_NAME], - genmask); + flowtable = nft_flowtable_lookup(ctx->table, tb[NFTA_FLOW_TABLE_NAME], + genmask); if (IS_ERR(flowtable)) return PTR_ERR(flowtable); diff --git a/net/netfilter/nft_hash.c b/net/netfilter/nft_hash.c index 24f2f7567ddb..e235c17f1b8b 100644 --- a/net/netfilter/nft_hash.c +++ b/net/netfilter/nft_hash.c @@ -97,7 +97,7 @@ static int nft_jhash_init(const struct nft_ctx *ctx, priv->len = len; priv->modulus = ntohl(nla_get_be32(tb[NFTA_HASH_MODULUS])); - if (priv->modulus <= 1) + if (priv->modulus < 1) return -ERANGE; if (priv->offset + priv->modulus - 1 < priv->offset) diff --git a/net/netfilter/nft_meta.c b/net/netfilter/nft_meta.c index 8fb91940e2e7..5348bd058c88 100644 --- a/net/netfilter/nft_meta.c +++ b/net/netfilter/nft_meta.c @@ -1,5 +1,7 @@ /* * Copyright (c) 2008-2009 Patrick McHardy <kaber@trash.net> + * Copyright (c) 2014 Intel Corporation + * Author: Tomasz Bursztyka <tomasz.bursztyka@linux.intel.com> * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as @@ -9,8 +11,6 @@ */ #include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -24,21 +24,35 @@ #include <net/tcp_states.h> /* for TCP_TIME_WAIT */ #include <net/netfilter/nf_tables.h> #include <net/netfilter/nf_tables_core.h> -#include <net/netfilter/nft_meta.h> #include <uapi/linux/netfilter_bridge.h> /* NF_BR_PRE_ROUTING */ +struct nft_meta { + enum nft_meta_keys key:8; + union { + enum nft_registers dreg:8; + enum nft_registers sreg:8; + }; +}; + static DEFINE_PER_CPU(struct rnd_state, nft_prandom_state); -void nft_meta_get_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +#ifdef CONFIG_NF_TABLES_BRIDGE +#include "../bridge/br_private.h" +#endif + +static void nft_meta_get_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_meta *priv = nft_expr_priv(expr); const struct sk_buff *skb = pkt->skb; const struct net_device *in = nft_in(pkt), *out = nft_out(pkt); struct sock *sk; u32 *dest = ®s->data[priv->dreg]; +#ifdef CONFIG_NF_TABLES_BRIDGE + const struct net_bridge_port *p; +#endif switch (priv->key) { case NFT_META_LEN: @@ -215,6 +229,18 @@ void nft_meta_get_eval(const struct nft_expr *expr, nft_reg_store8(dest, !!skb->sp); break; #endif +#ifdef CONFIG_NF_TABLES_BRIDGE + case NFT_META_BRI_IIFNAME: + if (in == NULL || (p = br_port_get_rcu(in)) == NULL) + goto err; + strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); + return; + case NFT_META_BRI_OIFNAME: + if (out == NULL || (p = br_port_get_rcu(out)) == NULL) + goto err; + strncpy((char *)dest, p->br->dev->name, IFNAMSIZ); + return; +#endif default: WARN_ON(1); goto err; @@ -224,11 +250,10 @@ void nft_meta_get_eval(const struct nft_expr *expr, err: regs->verdict.code = NFT_BREAK; } -EXPORT_SYMBOL_GPL(nft_meta_get_eval); -void nft_meta_set_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static void nft_meta_set_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) { const struct nft_meta *meta = nft_expr_priv(expr); struct sk_buff *skb = pkt->skb; @@ -258,18 +283,16 @@ void nft_meta_set_eval(const struct nft_expr *expr, WARN_ON(1); } } -EXPORT_SYMBOL_GPL(nft_meta_set_eval); -const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { +static const struct nla_policy nft_meta_policy[NFTA_META_MAX + 1] = { [NFTA_META_DREG] = { .type = NLA_U32 }, [NFTA_META_KEY] = { .type = NLA_U32 }, [NFTA_META_SREG] = { .type = NLA_U32 }, }; -EXPORT_SYMBOL_GPL(nft_meta_policy); -int nft_meta_get_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_meta_get_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; @@ -318,6 +341,14 @@ int nft_meta_get_init(const struct nft_ctx *ctx, len = sizeof(u8); break; #endif +#ifdef CONFIG_NF_TABLES_BRIDGE + case NFT_META_BRI_IIFNAME: + case NFT_META_BRI_OIFNAME: + if (ctx->family != NFPROTO_BRIDGE) + return -EOPNOTSUPP; + len = IFNAMSIZ; + break; +#endif default: return -EOPNOTSUPP; } @@ -326,7 +357,6 @@ int nft_meta_get_init(const struct nft_ctx *ctx, return nft_validate_register_store(ctx, priv->dreg, NULL, NFT_DATA_VALUE, len); } -EXPORT_SYMBOL_GPL(nft_meta_get_init); static int nft_meta_get_validate(const struct nft_ctx *ctx, const struct nft_expr *expr, @@ -360,9 +390,9 @@ static int nft_meta_get_validate(const struct nft_ctx *ctx, #endif } -int nft_meta_set_validate(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nft_data **data) +static int nft_meta_set_validate(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nft_data **data) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int hooks; @@ -388,11 +418,10 @@ int nft_meta_set_validate(const struct nft_ctx *ctx, return nft_chain_validate_hooks(ctx->chain, hooks); } -EXPORT_SYMBOL_GPL(nft_meta_set_validate); -int nft_meta_set_init(const struct nft_ctx *ctx, - const struct nft_expr *expr, - const struct nlattr * const tb[]) +static int nft_meta_set_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) { struct nft_meta *priv = nft_expr_priv(expr); unsigned int len; @@ -424,10 +453,9 @@ int nft_meta_set_init(const struct nft_ctx *ctx, return 0; } -EXPORT_SYMBOL_GPL(nft_meta_set_init); -int nft_meta_get_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_meta_get_dump(struct sk_buff *skb, + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -440,10 +468,8 @@ int nft_meta_get_dump(struct sk_buff *skb, nla_put_failure: return -1; } -EXPORT_SYMBOL_GPL(nft_meta_get_dump); -int nft_meta_set_dump(struct sk_buff *skb, - const struct nft_expr *expr) +static int nft_meta_set_dump(struct sk_buff *skb, const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); @@ -457,19 +483,16 @@ int nft_meta_set_dump(struct sk_buff *skb, nla_put_failure: return -1; } -EXPORT_SYMBOL_GPL(nft_meta_set_dump); -void nft_meta_set_destroy(const struct nft_ctx *ctx, - const struct nft_expr *expr) +static void nft_meta_set_destroy(const struct nft_ctx *ctx, + const struct nft_expr *expr) { const struct nft_meta *priv = nft_expr_priv(expr); if (priv->key == NFT_META_NFTRACE) static_branch_dec(&nft_trace_enabled); } -EXPORT_SYMBOL_GPL(nft_meta_set_destroy); -static struct nft_expr_type nft_meta_type; static const struct nft_expr_ops nft_meta_get_ops = { .type = &nft_meta_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_meta)), @@ -508,27 +531,10 @@ nft_meta_select_ops(const struct nft_ctx *ctx, return ERR_PTR(-EINVAL); } -static struct nft_expr_type nft_meta_type __read_mostly = { +struct nft_expr_type nft_meta_type __read_mostly = { .name = "meta", .select_ops = nft_meta_select_ops, .policy = nft_meta_policy, .maxattr = NFTA_META_MAX, .owner = THIS_MODULE, }; - -static int __init nft_meta_module_init(void) -{ - return nft_register_expr(&nft_meta_type); -} - -static void __exit nft_meta_module_exit(void) -{ - nft_unregister_expr(&nft_meta_type); -} - -module_init(nft_meta_module_init); -module_exit(nft_meta_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); -MODULE_ALIAS_NFT_EXPR("meta"); diff --git a/net/netfilter/nft_nat.c b/net/netfilter/nft_nat.c index 1f36954c2ba9..c15807d10b91 100644 --- a/net/netfilter/nft_nat.c +++ b/net/netfilter/nft_nat.c @@ -43,7 +43,7 @@ static void nft_nat_eval(const struct nft_expr *expr, const struct nft_nat *priv = nft_expr_priv(expr); enum ip_conntrack_info ctinfo; struct nf_conn *ct = nf_ct_get(pkt->skb, &ctinfo); - struct nf_nat_range range; + struct nf_nat_range2 range; memset(&range, 0, sizeof(range)); if (priv->sreg_addr_min) { diff --git a/net/netfilter/nft_numgen.c b/net/netfilter/nft_numgen.c index 5a3a52c71545..8a64db8f2e69 100644 --- a/net/netfilter/nft_numgen.c +++ b/net/netfilter/nft_numgen.c @@ -24,13 +24,11 @@ struct nft_ng_inc { u32 modulus; atomic_t counter; u32 offset; + struct nft_set *map; }; -static void nft_ng_inc_eval(const struct nft_expr *expr, - struct nft_regs *regs, - const struct nft_pktinfo *pkt) +static u32 nft_ng_inc_gen(struct nft_ng_inc *priv) { - struct nft_ng_inc *priv = nft_expr_priv(expr); u32 nval, oval; do { @@ -38,7 +36,36 @@ static void nft_ng_inc_eval(const struct nft_expr *expr, nval = (oval + 1 < priv->modulus) ? oval + 1 : 0; } while (atomic_cmpxchg(&priv->counter, oval, nval) != oval); - regs->data[priv->dreg] = nval + priv->offset; + return nval + priv->offset; +} + +static void nft_ng_inc_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + + regs->data[priv->dreg] = nft_ng_inc_gen(priv); +} + +static void nft_ng_inc_map_eval(const struct nft_expr *expr, + struct nft_regs *regs, + const struct nft_pktinfo *pkt) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + const struct nft_set *map = priv->map; + const struct nft_set_ext *ext; + u32 result; + bool found; + + result = nft_ng_inc_gen(priv); + found = map->ops->lookup(nft_net(pkt), map, &result, &ext); + + if (!found) + return; + + nft_data_copy(®s->data[priv->dreg], + nft_set_ext_data(ext), map->dlen); } static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { @@ -46,6 +73,9 @@ static const struct nla_policy nft_ng_policy[NFTA_NG_MAX + 1] = { [NFTA_NG_MODULUS] = { .type = NLA_U32 }, [NFTA_NG_TYPE] = { .type = NLA_U32 }, [NFTA_NG_OFFSET] = { .type = NLA_U32 }, + [NFTA_NG_SET_NAME] = { .type = NLA_STRING, + .len = NFT_SET_MAXNAMELEN - 1 }, + [NFTA_NG_SET_ID] = { .type = NLA_U32 }, }; static int nft_ng_inc_init(const struct nft_ctx *ctx, @@ -71,6 +101,25 @@ static int nft_ng_inc_init(const struct nft_ctx *ctx, NFT_DATA_VALUE, sizeof(u32)); } +static int nft_ng_inc_map_init(const struct nft_ctx *ctx, + const struct nft_expr *expr, + const struct nlattr * const tb[]) +{ + struct nft_ng_inc *priv = nft_expr_priv(expr); + u8 genmask = nft_genmask_next(ctx->net); + + nft_ng_inc_init(ctx, expr, tb); + + priv->map = nft_set_lookup_global(ctx->net, ctx->table, + tb[NFTA_NG_SET_NAME], + tb[NFTA_NG_SET_ID], genmask); + + if (IS_ERR(priv->map)) + return PTR_ERR(priv->map); + + return 0; +} + static int nft_ng_dump(struct sk_buff *skb, enum nft_registers dreg, u32 modulus, enum nft_ng_types type, u32 offset) { @@ -97,6 +146,22 @@ static int nft_ng_inc_dump(struct sk_buff *skb, const struct nft_expr *expr) priv->offset); } +static int nft_ng_inc_map_dump(struct sk_buff *skb, + const struct nft_expr *expr) +{ + const struct nft_ng_inc *priv = nft_expr_priv(expr); + + if (nft_ng_dump(skb, priv->dreg, priv->modulus, + NFT_NG_INCREMENTAL, priv->offset) || + nla_put_string(skb, NFTA_NG_SET_NAME, priv->map->name)) + goto nla_put_failure; + + return 0; + +nla_put_failure: + return -1; +} + struct nft_ng_random { enum nft_registers dreg:8; u32 modulus; @@ -156,6 +221,14 @@ static const struct nft_expr_ops nft_ng_inc_ops = { .dump = nft_ng_inc_dump, }; +static const struct nft_expr_ops nft_ng_inc_map_ops = { + .type = &nft_ng_type, + .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_inc)), + .eval = nft_ng_inc_map_eval, + .init = nft_ng_inc_map_init, + .dump = nft_ng_inc_map_dump, +}; + static const struct nft_expr_ops nft_ng_random_ops = { .type = &nft_ng_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_ng_random)), @@ -178,6 +251,8 @@ nft_ng_select_ops(const struct nft_ctx *ctx, const struct nlattr * const tb[]) switch (type) { case NFT_NG_INCREMENTAL: + if (tb[NFTA_NG_SET_NAME]) + return &nft_ng_inc_map_ops; return &nft_ng_inc_ops; case NFT_NG_RANDOM: return &nft_ng_random_ops; diff --git a/net/netfilter/nft_objref.c b/net/netfilter/nft_objref.c index 0b02407773ad..cdf348f751ec 100644 --- a/net/netfilter/nft_objref.c +++ b/net/netfilter/nft_objref.c @@ -38,8 +38,8 @@ static int nft_objref_init(const struct nft_ctx *ctx, return -EINVAL; objtype = ntohl(nla_get_be32(tb[NFTA_OBJREF_IMM_TYPE])); - obj = nf_tables_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, - genmask); + obj = nft_obj_lookup(ctx->table, tb[NFTA_OBJREF_IMM_NAME], objtype, + genmask); if (IS_ERR(obj)) return -ENOENT; diff --git a/net/netfilter/nft_rt.c b/net/netfilter/nft_rt.c index 11a2071b6dd4..76dba9f6b6f6 100644 --- a/net/netfilter/nft_rt.c +++ b/net/netfilter/nft_rt.c @@ -7,8 +7,6 @@ */ #include <linux/kernel.h> -#include <linux/init.h> -#include <linux/module.h> #include <linux/netlink.h> #include <linux/netfilter.h> #include <linux/netfilter/nf_tables.h> @@ -179,7 +177,6 @@ static int nft_rt_validate(const struct nft_ctx *ctx, const struct nft_expr *exp return nft_chain_validate_hooks(ctx->chain, hooks); } -static struct nft_expr_type nft_rt_type; static const struct nft_expr_ops nft_rt_get_ops = { .type = &nft_rt_type, .size = NFT_EXPR_SIZE(sizeof(struct nft_rt)), @@ -189,27 +186,10 @@ static const struct nft_expr_ops nft_rt_get_ops = { .validate = nft_rt_validate, }; -static struct nft_expr_type nft_rt_type __read_mostly = { +struct nft_expr_type nft_rt_type __read_mostly = { .name = "rt", .ops = &nft_rt_get_ops, .policy = nft_rt_policy, .maxattr = NFTA_RT_MAX, .owner = THIS_MODULE, }; - -static int __init nft_rt_module_init(void) -{ - return nft_register_expr(&nft_rt_type); -} - -static void __exit nft_rt_module_exit(void) -{ - nft_unregister_expr(&nft_rt_type); -} - -module_init(nft_rt_module_init); -module_exit(nft_rt_module_exit); - -MODULE_LICENSE("GPL"); -MODULE_AUTHOR("Anders K. Pedersen <akp@cohaesio.com>"); -MODULE_ALIAS_NFT_EXPR("rt"); diff --git a/net/netfilter/nft_set_bitmap.c b/net/netfilter/nft_set_bitmap.c index 45fb2752fb63..d6626e01c7ee 100644 --- a/net/netfilter/nft_set_bitmap.c +++ b/net/netfilter/nft_set_bitmap.c @@ -296,27 +296,23 @@ static bool nft_bitmap_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_bitmap_type; -static struct nft_set_ops nft_bitmap_ops __read_mostly = { - .type = &nft_bitmap_type, - .privsize = nft_bitmap_privsize, - .elemsize = offsetof(struct nft_bitmap_elem, ext), - .estimate = nft_bitmap_estimate, - .init = nft_bitmap_init, - .destroy = nft_bitmap_destroy, - .insert = nft_bitmap_insert, - .remove = nft_bitmap_remove, - .deactivate = nft_bitmap_deactivate, - .flush = nft_bitmap_flush, - .activate = nft_bitmap_activate, - .lookup = nft_bitmap_lookup, - .walk = nft_bitmap_walk, - .get = nft_bitmap_get, -}; - static struct nft_set_type nft_bitmap_type __read_mostly = { - .ops = &nft_bitmap_ops, .owner = THIS_MODULE, + .ops = { + .privsize = nft_bitmap_privsize, + .elemsize = offsetof(struct nft_bitmap_elem, ext), + .estimate = nft_bitmap_estimate, + .init = nft_bitmap_init, + .destroy = nft_bitmap_destroy, + .insert = nft_bitmap_insert, + .remove = nft_bitmap_remove, + .deactivate = nft_bitmap_deactivate, + .flush = nft_bitmap_flush, + .activate = nft_bitmap_activate, + .lookup = nft_bitmap_lookup, + .walk = nft_bitmap_walk, + .get = nft_bitmap_get, + }, }; static int __init nft_bitmap_module_init(void) diff --git a/net/netfilter/nft_set_hash.c b/net/netfilter/nft_set_hash.c index fc9c6d5d64cd..dbf1f4ad077c 100644 --- a/net/netfilter/nft_set_hash.c +++ b/net/netfilter/nft_set_hash.c @@ -605,6 +605,12 @@ static void nft_hash_destroy(const struct nft_set *set) static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, struct nft_set_estimate *est) { + if (!desc->size) + return false; + + if (desc->klen == 4) + return false; + est->size = sizeof(struct nft_hash) + nft_hash_buckets(desc->size) * sizeof(struct hlist_head) + desc->size * sizeof(struct nft_hash_elem); @@ -614,91 +620,100 @@ static bool nft_hash_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_hash_type; -static struct nft_set_ops nft_rhash_ops __read_mostly = { - .type = &nft_hash_type, - .privsize = nft_rhash_privsize, - .elemsize = offsetof(struct nft_rhash_elem, ext), - .estimate = nft_rhash_estimate, - .init = nft_rhash_init, - .destroy = nft_rhash_destroy, - .insert = nft_rhash_insert, - .activate = nft_rhash_activate, - .deactivate = nft_rhash_deactivate, - .flush = nft_rhash_flush, - .remove = nft_rhash_remove, - .lookup = nft_rhash_lookup, - .update = nft_rhash_update, - .walk = nft_rhash_walk, - .get = nft_rhash_get, - .features = NFT_SET_MAP | NFT_SET_OBJECT | NFT_SET_TIMEOUT, -}; +static bool nft_hash_fast_estimate(const struct nft_set_desc *desc, u32 features, + struct nft_set_estimate *est) +{ + if (!desc->size) + return false; -static struct nft_set_ops nft_hash_ops __read_mostly = { - .type = &nft_hash_type, - .privsize = nft_hash_privsize, - .elemsize = offsetof(struct nft_hash_elem, ext), - .estimate = nft_hash_estimate, - .init = nft_hash_init, - .destroy = nft_hash_destroy, - .insert = nft_hash_insert, - .activate = nft_hash_activate, - .deactivate = nft_hash_deactivate, - .flush = nft_hash_flush, - .remove = nft_hash_remove, - .lookup = nft_hash_lookup, - .walk = nft_hash_walk, - .get = nft_hash_get, - .features = NFT_SET_MAP | NFT_SET_OBJECT, -}; + if (desc->klen != 4) + return false; -static struct nft_set_ops nft_hash_fast_ops __read_mostly = { - .type = &nft_hash_type, - .privsize = nft_hash_privsize, - .elemsize = offsetof(struct nft_hash_elem, ext), - .estimate = nft_hash_estimate, - .init = nft_hash_init, - .destroy = nft_hash_destroy, - .insert = nft_hash_insert, - .activate = nft_hash_activate, - .deactivate = nft_hash_deactivate, - .flush = nft_hash_flush, - .remove = nft_hash_remove, - .lookup = nft_hash_lookup_fast, - .walk = nft_hash_walk, - .get = nft_hash_get, - .features = NFT_SET_MAP | NFT_SET_OBJECT, -}; - -static const struct nft_set_ops * -nft_hash_select_ops(const struct nft_ctx *ctx, const struct nft_set_desc *desc, - u32 flags) -{ - if (desc->size && !(flags & (NFT_SET_EVAL | NFT_SET_TIMEOUT))) { - switch (desc->klen) { - case 4: - return &nft_hash_fast_ops; - default: - return &nft_hash_ops; - } - } + est->size = sizeof(struct nft_hash) + + nft_hash_buckets(desc->size) * sizeof(struct hlist_head) + + desc->size * sizeof(struct nft_hash_elem); + est->lookup = NFT_SET_CLASS_O_1; + est->space = NFT_SET_CLASS_O_N; - return &nft_rhash_ops; + return true; } +static struct nft_set_type nft_rhash_type __read_mostly = { + .owner = THIS_MODULE, + .features = NFT_SET_MAP | NFT_SET_OBJECT | + NFT_SET_TIMEOUT | NFT_SET_EVAL, + .ops = { + .privsize = nft_rhash_privsize, + .elemsize = offsetof(struct nft_rhash_elem, ext), + .estimate = nft_rhash_estimate, + .init = nft_rhash_init, + .destroy = nft_rhash_destroy, + .insert = nft_rhash_insert, + .activate = nft_rhash_activate, + .deactivate = nft_rhash_deactivate, + .flush = nft_rhash_flush, + .remove = nft_rhash_remove, + .lookup = nft_rhash_lookup, + .update = nft_rhash_update, + .walk = nft_rhash_walk, + .get = nft_rhash_get, + }, +}; + static struct nft_set_type nft_hash_type __read_mostly = { - .select_ops = nft_hash_select_ops, .owner = THIS_MODULE, + .features = NFT_SET_MAP | NFT_SET_OBJECT, + .ops = { + .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), + .estimate = nft_hash_estimate, + .init = nft_hash_init, + .destroy = nft_hash_destroy, + .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, + .flush = nft_hash_flush, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup, + .walk = nft_hash_walk, + .get = nft_hash_get, + }, +}; + +static struct nft_set_type nft_hash_fast_type __read_mostly = { + .owner = THIS_MODULE, + .features = NFT_SET_MAP | NFT_SET_OBJECT, + .ops = { + .privsize = nft_hash_privsize, + .elemsize = offsetof(struct nft_hash_elem, ext), + .estimate = nft_hash_fast_estimate, + .init = nft_hash_init, + .destroy = nft_hash_destroy, + .insert = nft_hash_insert, + .activate = nft_hash_activate, + .deactivate = nft_hash_deactivate, + .flush = nft_hash_flush, + .remove = nft_hash_remove, + .lookup = nft_hash_lookup_fast, + .walk = nft_hash_walk, + .get = nft_hash_get, + }, }; static int __init nft_hash_module_init(void) { - return nft_register_set(&nft_hash_type); + if (nft_register_set(&nft_hash_fast_type) || + nft_register_set(&nft_hash_type) || + nft_register_set(&nft_rhash_type)) + return 1; + return 0; } static void __exit nft_hash_module_exit(void) { + nft_unregister_set(&nft_rhash_type); nft_unregister_set(&nft_hash_type); + nft_unregister_set(&nft_hash_fast_type); } module_init(nft_hash_module_init); diff --git a/net/netfilter/nft_set_rbtree.c b/net/netfilter/nft_set_rbtree.c index e6f08bc5f359..22c57d7612c4 100644 --- a/net/netfilter/nft_set_rbtree.c +++ b/net/netfilter/nft_set_rbtree.c @@ -393,28 +393,24 @@ static bool nft_rbtree_estimate(const struct nft_set_desc *desc, u32 features, return true; } -static struct nft_set_type nft_rbtree_type; -static struct nft_set_ops nft_rbtree_ops __read_mostly = { - .type = &nft_rbtree_type, - .privsize = nft_rbtree_privsize, - .elemsize = offsetof(struct nft_rbtree_elem, ext), - .estimate = nft_rbtree_estimate, - .init = nft_rbtree_init, - .destroy = nft_rbtree_destroy, - .insert = nft_rbtree_insert, - .remove = nft_rbtree_remove, - .deactivate = nft_rbtree_deactivate, - .flush = nft_rbtree_flush, - .activate = nft_rbtree_activate, - .lookup = nft_rbtree_lookup, - .walk = nft_rbtree_walk, - .get = nft_rbtree_get, - .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, -}; - static struct nft_set_type nft_rbtree_type __read_mostly = { - .ops = &nft_rbtree_ops, .owner = THIS_MODULE, + .features = NFT_SET_INTERVAL | NFT_SET_MAP | NFT_SET_OBJECT, + .ops = { + .privsize = nft_rbtree_privsize, + .elemsize = offsetof(struct nft_rbtree_elem, ext), + .estimate = nft_rbtree_estimate, + .init = nft_rbtree_init, + .destroy = nft_rbtree_destroy, + .insert = nft_rbtree_insert, + .remove = nft_rbtree_remove, + .deactivate = nft_rbtree_deactivate, + .flush = nft_rbtree_flush, + .activate = nft_rbtree_activate, + .lookup = nft_rbtree_lookup, + .walk = nft_rbtree_walk, + .get = nft_rbtree_get, + }, }; static int __init nft_rbtree_module_init(void) diff --git a/net/netfilter/xt_NETMAP.c b/net/netfilter/xt_NETMAP.c index 58aa9dd3c5b7..1d437875e15a 100644 --- a/net/netfilter/xt_NETMAP.c +++ b/net/netfilter/xt_NETMAP.c @@ -21,8 +21,8 @@ static unsigned int netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) { - const struct nf_nat_range *range = par->targinfo; - struct nf_nat_range newrange; + const struct nf_nat_range2 *range = par->targinfo; + struct nf_nat_range2 newrange; struct nf_conn *ct; enum ip_conntrack_info ctinfo; union nf_inet_addr new_addr, netmask; @@ -56,7 +56,7 @@ netmap_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int netmap_tg6_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range2 *range = par->targinfo; if (!(range->flags & NF_NAT_RANGE_MAP_IPS)) return -EINVAL; @@ -75,7 +75,7 @@ netmap_tg4(struct sk_buff *skb, const struct xt_action_param *par) enum ip_conntrack_info ctinfo; __be32 new_ip, netmask; const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range newrange; + struct nf_nat_range2 newrange; WARN_ON(xt_hooknum(par) != NF_INET_PRE_ROUTING && xt_hooknum(par) != NF_INET_POST_ROUTING && diff --git a/net/netfilter/xt_NFLOG.c b/net/netfilter/xt_NFLOG.c index c7f8958cea4a..1ed0cac585c4 100644 --- a/net/netfilter/xt_NFLOG.c +++ b/net/netfilter/xt_NFLOG.c @@ -13,7 +13,6 @@ #include <linux/netfilter/x_tables.h> #include <linux/netfilter/xt_NFLOG.h> #include <net/netfilter/nf_log.h> -#include <net/netfilter/nfnetlink_log.h> MODULE_AUTHOR("Patrick McHardy <kaber@trash.net>"); MODULE_DESCRIPTION("Xtables: packet logging to netlink using NFLOG"); @@ -37,8 +36,9 @@ nflog_tg(struct sk_buff *skb, const struct xt_action_param *par) if (info->flags & XT_NFLOG_F_COPY_LEN) li.u.ulog.flags |= NF_LOG_F_COPY_LEN; - nfulnl_log_packet(net, xt_family(par), xt_hooknum(par), skb, - xt_in(par), xt_out(par), &li, info->prefix); + nf_log_packet(net, xt_family(par), xt_hooknum(par), skb, xt_in(par), + xt_out(par), &li, "%s", info->prefix); + return XT_CONTINUE; } @@ -50,7 +50,13 @@ static int nflog_tg_check(const struct xt_tgchk_param *par) return -EINVAL; if (info->prefix[sizeof(info->prefix) - 1] != '\0') return -EINVAL; - return 0; + + return nf_logger_find_get(par->family, NF_LOG_TYPE_ULOG); +} + +static void nflog_tg_destroy(const struct xt_tgdtor_param *par) +{ + nf_logger_put(par->family, NF_LOG_TYPE_ULOG); } static struct xt_target nflog_tg_reg __read_mostly = { @@ -58,6 +64,7 @@ static struct xt_target nflog_tg_reg __read_mostly = { .revision = 0, .family = NFPROTO_UNSPEC, .checkentry = nflog_tg_check, + .destroy = nflog_tg_destroy, .target = nflog_tg, .targetsize = sizeof(struct xt_nflog_info), .me = THIS_MODULE, diff --git a/net/netfilter/xt_REDIRECT.c b/net/netfilter/xt_REDIRECT.c index 98a4c6d4f1cb..5ce9461e979c 100644 --- a/net/netfilter/xt_REDIRECT.c +++ b/net/netfilter/xt_REDIRECT.c @@ -36,7 +36,7 @@ redirect_tg6(struct sk_buff *skb, const struct xt_action_param *par) static int redirect_tg6_checkentry(const struct xt_tgchk_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range2 *range = par->targinfo; if (range->flags & NF_NAT_RANGE_MAP_IPS) return -EINVAL; diff --git a/net/netfilter/xt_nat.c b/net/netfilter/xt_nat.c index bdb689cdc829..8af9707f8789 100644 --- a/net/netfilter/xt_nat.c +++ b/net/netfilter/xt_nat.c @@ -37,11 +37,12 @@ static void xt_nat_destroy(const struct xt_tgdtor_param *par) nf_ct_netns_put(par->net, par->family); } -static void xt_nat_convert_range(struct nf_nat_range *dst, +static void xt_nat_convert_range(struct nf_nat_range2 *dst, const struct nf_nat_ipv4_range *src) { memset(&dst->min_addr, 0, sizeof(dst->min_addr)); memset(&dst->max_addr, 0, sizeof(dst->max_addr)); + memset(&dst->base_proto, 0, sizeof(dst->base_proto)); dst->flags = src->flags; dst->min_addr.ip = src->min_ip; @@ -54,7 +55,7 @@ static unsigned int xt_snat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range range; + struct nf_nat_range2 range; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -71,7 +72,7 @@ static unsigned int xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) { const struct nf_nat_ipv4_multi_range_compat *mr = par->targinfo; - struct nf_nat_range range; + struct nf_nat_range2 range; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -86,7 +87,8 @@ xt_dnat_target_v0(struct sk_buff *skb, const struct xt_action_param *par) static unsigned int xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range *range_v1 = par->targinfo; + struct nf_nat_range2 range; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -95,13 +97,49 @@ xt_snat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || ctinfo == IP_CT_RELATED_REPLY))); - return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); + memcpy(&range, range_v1, sizeof(*range_v1)); + memset(&range.base_proto, 0, sizeof(range.base_proto)); + + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_SRC); } static unsigned int xt_dnat_target_v1(struct sk_buff *skb, const struct xt_action_param *par) { - const struct nf_nat_range *range = par->targinfo; + const struct nf_nat_range *range_v1 = par->targinfo; + struct nf_nat_range2 range; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED))); + + memcpy(&range, range_v1, sizeof(*range_v1)); + memset(&range.base_proto, 0, sizeof(range.base_proto)); + + return nf_nat_setup_info(ct, &range, NF_NAT_MANIP_DST); +} + +static unsigned int +xt_snat_target_v2(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range2 *range = par->targinfo; + enum ip_conntrack_info ctinfo; + struct nf_conn *ct; + + ct = nf_ct_get(skb, &ctinfo); + WARN_ON(!(ct != NULL && + (ctinfo == IP_CT_NEW || ctinfo == IP_CT_RELATED || + ctinfo == IP_CT_RELATED_REPLY))); + + return nf_nat_setup_info(ct, range, NF_NAT_MANIP_SRC); +} + +static unsigned int +xt_dnat_target_v2(struct sk_buff *skb, const struct xt_action_param *par) +{ + const struct nf_nat_range2 *range = par->targinfo; enum ip_conntrack_info ctinfo; struct nf_conn *ct; @@ -163,6 +201,28 @@ static struct xt_target xt_nat_target_reg[] __read_mostly = { (1 << NF_INET_LOCAL_OUT), .me = THIS_MODULE, }, + { + .name = "SNAT", + .revision = 2, + .checkentry = xt_nat_checkentry, + .destroy = xt_nat_destroy, + .target = xt_snat_target_v2, + .targetsize = sizeof(struct nf_nat_range2), + .table = "nat", + .hooks = (1 << NF_INET_POST_ROUTING) | + (1 << NF_INET_LOCAL_IN), + .me = THIS_MODULE, + }, + { + .name = "DNAT", + .revision = 2, + .target = xt_dnat_target_v2, + .targetsize = sizeof(struct nf_nat_range2), + .table = "nat", + .hooks = (1 << NF_INET_PRE_ROUTING) | + (1 << NF_INET_LOCAL_OUT), + .me = THIS_MODULE, + }, }; static int __init xt_nat_init(void) diff --git a/net/netfilter/xt_osf.c b/net/netfilter/xt_osf.c index a34f314a8c23..9cfef73b4107 100644 --- a/net/netfilter/xt_osf.c +++ b/net/netfilter/xt_osf.c @@ -37,21 +37,6 @@ #include <net/netfilter/nf_log.h> #include <linux/netfilter/xt_osf.h> -struct xt_osf_finger { - struct rcu_head rcu_head; - struct list_head finger_entry; - struct xt_osf_user_finger finger; -}; - -enum osf_fmatch_states { - /* Packet does not match the fingerprint */ - FMATCH_WRONG = 0, - /* Packet matches the fingerprint */ - FMATCH_OK, - /* Options do not match the fingerprint, but header does */ - FMATCH_OPT_WRONG, -}; - /* * Indexed by dont-fragment bit. * It is the only constant value in the fingerprint. @@ -164,200 +149,17 @@ static const struct nfnetlink_subsystem xt_osf_nfnetlink = { .cb = xt_osf_nfnetlink_callbacks, }; -static inline int xt_osf_ttl(const struct sk_buff *skb, const struct xt_osf_info *info, - unsigned char f_ttl) -{ - const struct iphdr *ip = ip_hdr(skb); - - if (info->flags & XT_OSF_TTL) { - if (info->ttl == XT_OSF_TTL_TRUE) - return ip->ttl == f_ttl; - if (info->ttl == XT_OSF_TTL_NOCHECK) - return 1; - else if (ip->ttl <= f_ttl) - return 1; - else { - struct in_device *in_dev = __in_dev_get_rcu(skb->dev); - int ret = 0; - - for_ifa(in_dev) { - if (inet_ifa_match(ip->saddr, ifa)) { - ret = (ip->ttl == f_ttl); - break; - } - } - endfor_ifa(in_dev); - - return ret; - } - } - - return ip->ttl == f_ttl; -} - static bool xt_osf_match_packet(const struct sk_buff *skb, struct xt_action_param *p) { const struct xt_osf_info *info = p->matchinfo; - const struct iphdr *ip = ip_hdr(skb); - const struct tcphdr *tcp; - struct tcphdr _tcph; - int fmatch = FMATCH_WRONG, fcount = 0; - unsigned int optsize = 0, check_WSS = 0; - u16 window, totlen, mss = 0; - bool df; - const unsigned char *optp = NULL, *_optp = NULL; - unsigned char opts[MAX_IPOPTLEN]; - const struct xt_osf_finger *kf; - const struct xt_osf_user_finger *f; struct net *net = xt_net(p); if (!info) return false; - tcp = skb_header_pointer(skb, ip_hdrlen(skb), sizeof(struct tcphdr), &_tcph); - if (!tcp) - return false; - - if (!tcp->syn) - return false; - - totlen = ntohs(ip->tot_len); - df = ntohs(ip->frag_off) & IP_DF; - window = ntohs(tcp->window); - - if (tcp->doff * 4 > sizeof(struct tcphdr)) { - optsize = tcp->doff * 4 - sizeof(struct tcphdr); - - _optp = optp = skb_header_pointer(skb, ip_hdrlen(skb) + - sizeof(struct tcphdr), optsize, opts); - } - - list_for_each_entry_rcu(kf, &xt_osf_fingers[df], finger_entry) { - int foptsize, optnum; - - f = &kf->finger; - - if (!(info->flags & XT_OSF_LOG) && strcmp(info->genre, f->genre)) - continue; - - optp = _optp; - fmatch = FMATCH_WRONG; - - if (totlen != f->ss || !xt_osf_ttl(skb, info, f->ttl)) - continue; - - /* - * Should not happen if userspace parser was written correctly. - */ - if (f->wss.wc >= OSF_WSS_MAX) - continue; - - /* Check options */ - - foptsize = 0; - for (optnum = 0; optnum < f->opt_num; ++optnum) - foptsize += f->opt[optnum].length; - - if (foptsize > MAX_IPOPTLEN || - optsize > MAX_IPOPTLEN || - optsize != foptsize) - continue; - - check_WSS = f->wss.wc; - - for (optnum = 0; optnum < f->opt_num; ++optnum) { - if (f->opt[optnum].kind == (*optp)) { - __u32 len = f->opt[optnum].length; - const __u8 *optend = optp + len; - - fmatch = FMATCH_OK; - - switch (*optp) { - case OSFOPT_MSS: - mss = optp[3]; - mss <<= 8; - mss |= optp[2]; - - mss = ntohs((__force __be16)mss); - break; - case OSFOPT_TS: - break; - } - - optp = optend; - } else - fmatch = FMATCH_OPT_WRONG; - - if (fmatch != FMATCH_OK) - break; - } - - if (fmatch != FMATCH_OPT_WRONG) { - fmatch = FMATCH_WRONG; - - switch (check_WSS) { - case OSF_WSS_PLAIN: - if (f->wss.val == 0 || window == f->wss.val) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MSS: - /* - * Some smart modems decrease mangle MSS to - * SMART_MSS_2, so we check standard, decreased - * and the one provided in the fingerprint MSS - * values. - */ -#define SMART_MSS_1 1460 -#define SMART_MSS_2 1448 - if (window == f->wss.val * mss || - window == f->wss.val * SMART_MSS_1 || - window == f->wss.val * SMART_MSS_2) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MTU: - if (window == f->wss.val * (mss + 40) || - window == f->wss.val * (SMART_MSS_1 + 40) || - window == f->wss.val * (SMART_MSS_2 + 40)) - fmatch = FMATCH_OK; - break; - case OSF_WSS_MODULO: - if ((window % f->wss.val) == 0) - fmatch = FMATCH_OK; - break; - } - } - - if (fmatch != FMATCH_OK) - continue; - - fcount++; - - if (info->flags & XT_OSF_LOG) - nf_log_packet(net, xt_family(p), xt_hooknum(p), skb, - xt_in(p), xt_out(p), NULL, - "%s [%s:%s] : %pI4:%d -> %pI4:%d hops=%d\n", - f->genre, f->version, f->subtype, - &ip->saddr, ntohs(tcp->source), - &ip->daddr, ntohs(tcp->dest), - f->ttl - ip->ttl); - - if ((info->flags & XT_OSF_LOG) && - info->loglevel == XT_OSF_LOGLEVEL_FIRST) - break; - } - - if (!fcount && (info->flags & XT_OSF_LOG)) - nf_log_packet(net, xt_family(p), xt_hooknum(p), skb, xt_in(p), - xt_out(p), NULL, - "Remote OS is not known: %pI4:%u -> %pI4:%u\n", - &ip->saddr, ntohs(tcp->source), - &ip->daddr, ntohs(tcp->dest)); - - if (fcount) - fmatch = FMATCH_OK; - - return fmatch == FMATCH_OK; + return nf_osf_match(skb, xt_family(p), xt_hooknum(p), xt_in(p), + xt_out(p), info, net, xt_osf_fingers); } static struct xt_match xt_osf_match = { diff --git a/net/openvswitch/conntrack.c b/net/openvswitch/conntrack.c index c5904f629091..02fc343feb66 100644 --- a/net/openvswitch/conntrack.c +++ b/net/openvswitch/conntrack.c @@ -72,7 +72,7 @@ struct ovs_conntrack_info { struct md_mark mark; struct md_labels labels; #ifdef CONFIG_NF_NAT_NEEDED - struct nf_nat_range range; /* Only present for SRC NAT and DST NAT. */ + struct nf_nat_range2 range; /* Only present for SRC NAT and DST NAT. */ #endif }; @@ -710,7 +710,7 @@ static bool skb_nfct_cached(struct net *net, */ static int ovs_ct_nat_execute(struct sk_buff *skb, struct nf_conn *ct, enum ip_conntrack_info ctinfo, - const struct nf_nat_range *range, + const struct nf_nat_range2 *range, enum nf_nat_manip_type maniptype) { int hooknum, nh_off, err = NF_ACCEPT; diff --git a/net/packet/af_packet.c b/net/packet/af_packet.c index 01f3515cada0..611a26d5235c 100644 --- a/net/packet/af_packet.c +++ b/net/packet/af_packet.c @@ -209,7 +209,7 @@ static void prb_clear_rxhash(struct tpacket_kbdq_core *, static void prb_fill_vlan_info(struct tpacket_kbdq_core *, struct tpacket3_hdr *); static void packet_flush_mclist(struct sock *sk); -static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb); +static u16 packet_pick_tx_queue(struct sk_buff *skb); struct packet_skb_cb { union { @@ -243,40 +243,7 @@ static void __fanout_link(struct sock *sk, struct packet_sock *po); static int packet_direct_xmit(struct sk_buff *skb) { - struct net_device *dev = skb->dev; - struct sk_buff *orig_skb = skb; - struct netdev_queue *txq; - int ret = NETDEV_TX_BUSY; - bool again = false; - - if (unlikely(!netif_running(dev) || - !netif_carrier_ok(dev))) - goto drop; - - skb = validate_xmit_skb_list(skb, dev, &again); - if (skb != orig_skb) - goto drop; - - packet_pick_tx_queue(dev, skb); - txq = skb_get_tx_queue(dev, skb); - - local_bh_disable(); - - HARD_TX_LOCK(dev, txq, smp_processor_id()); - if (!netif_xmit_frozen_or_drv_stopped(txq)) - ret = netdev_start_xmit(skb, dev, txq, false); - HARD_TX_UNLOCK(dev, txq); - - local_bh_enable(); - - if (!dev_xmit_complete(ret)) - kfree_skb(skb); - - return ret; -drop: - atomic_long_inc(&dev->tx_dropped); - kfree_skb_list(skb); - return NET_XMIT_DROP; + return dev_direct_xmit(skb, packet_pick_tx_queue(skb)); } static struct net_device *packet_cached_dev_get(struct packet_sock *po) @@ -313,8 +280,9 @@ static u16 __packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) return (u16) raw_smp_processor_id() % dev->real_num_tx_queues; } -static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) +static u16 packet_pick_tx_queue(struct sk_buff *skb) { + struct net_device *dev = skb->dev; const struct net_device_ops *ops = dev->netdev_ops; u16 queue_index; @@ -326,7 +294,7 @@ static void packet_pick_tx_queue(struct net_device *dev, struct sk_buff *skb) queue_index = __packet_pick_tx_queue(dev, skb); } - skb_set_queue_mapping(skb, queue_index); + return queue_index; } /* __register_prot_hook must be invoked through register_prot_hook diff --git a/net/qrtr/Kconfig b/net/qrtr/Kconfig index 326fd97444f5..1944834d225c 100644 --- a/net/qrtr/Kconfig +++ b/net/qrtr/Kconfig @@ -21,4 +21,11 @@ config QRTR_SMD Say Y here to support SMD based ipcrouter channels. SMD is the most common transport for IPC Router. +config QRTR_TUN + tristate "TUN device for Qualcomm IPC Router" + ---help--- + Say Y here to expose a character device that allows user space to + implement endpoints of QRTR, for purpose of tunneling data to other + hosts or testing purposes. + endif # QRTR diff --git a/net/qrtr/Makefile b/net/qrtr/Makefile index ab09e40f7c74..be012bfd3e52 100644 --- a/net/qrtr/Makefile +++ b/net/qrtr/Makefile @@ -2,3 +2,5 @@ obj-$(CONFIG_QRTR) := qrtr.o obj-$(CONFIG_QRTR_SMD) += qrtr-smd.o qrtr-smd-y := smd.o +obj-$(CONFIG_QRTR_TUN) += qrtr-tun.o +qrtr-tun-y := tun.o diff --git a/net/qrtr/tun.c b/net/qrtr/tun.c new file mode 100644 index 000000000000..ccff1e544c21 --- /dev/null +++ b/net/qrtr/tun.c @@ -0,0 +1,161 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright (c) 2018, Linaro Ltd */ + +#include <linux/miscdevice.h> +#include <linux/module.h> +#include <linux/poll.h> +#include <linux/skbuff.h> +#include <linux/uaccess.h> + +#include "qrtr.h" + +struct qrtr_tun { + struct qrtr_endpoint ep; + + struct sk_buff_head queue; + wait_queue_head_t readq; +}; + +static int qrtr_tun_send(struct qrtr_endpoint *ep, struct sk_buff *skb) +{ + struct qrtr_tun *tun = container_of(ep, struct qrtr_tun, ep); + + skb_queue_tail(&tun->queue, skb); + + /* wake up any blocking processes, waiting for new data */ + wake_up_interruptible(&tun->readq); + + return 0; +} + +static int qrtr_tun_open(struct inode *inode, struct file *filp) +{ + struct qrtr_tun *tun; + + tun = kzalloc(sizeof(*tun), GFP_KERNEL); + if (!tun) + return -ENOMEM; + + skb_queue_head_init(&tun->queue); + init_waitqueue_head(&tun->readq); + + tun->ep.xmit = qrtr_tun_send; + + filp->private_data = tun; + + return qrtr_endpoint_register(&tun->ep, QRTR_EP_NID_AUTO); +} + +static ssize_t qrtr_tun_read_iter(struct kiocb *iocb, struct iov_iter *to) +{ + struct file *filp = iocb->ki_filp; + struct qrtr_tun *tun = filp->private_data; + struct sk_buff *skb; + int count; + + while (!(skb = skb_dequeue(&tun->queue))) { + if (filp->f_flags & O_NONBLOCK) + return -EAGAIN; + + /* Wait until we get data or the endpoint goes away */ + if (wait_event_interruptible(tun->readq, + !skb_queue_empty(&tun->queue))) + return -ERESTARTSYS; + } + + count = min_t(size_t, iov_iter_count(to), skb->len); + if (copy_to_iter(skb->data, count, to) != count) + count = -EFAULT; + + kfree_skb(skb); + + return count; +} + +static ssize_t qrtr_tun_write_iter(struct kiocb *iocb, struct iov_iter *from) +{ + struct file *filp = iocb->ki_filp; + struct qrtr_tun *tun = filp->private_data; + size_t len = iov_iter_count(from); + ssize_t ret; + void *kbuf; + + kbuf = kzalloc(len, GFP_KERNEL); + if (!kbuf) + return -ENOMEM; + + if (!copy_from_iter_full(kbuf, len, from)) + return -EFAULT; + + ret = qrtr_endpoint_post(&tun->ep, kbuf, len); + + return ret < 0 ? ret : len; +} + +static __poll_t qrtr_tun_poll(struct file *filp, poll_table *wait) +{ + struct qrtr_tun *tun = filp->private_data; + __poll_t mask = 0; + + poll_wait(filp, &tun->readq, wait); + + if (!skb_queue_empty(&tun->queue)) + mask |= EPOLLIN | EPOLLRDNORM; + + return mask; +} + +static int qrtr_tun_release(struct inode *inode, struct file *filp) +{ + struct qrtr_tun *tun = filp->private_data; + struct sk_buff *skb; + + qrtr_endpoint_unregister(&tun->ep); + + /* Discard all SKBs */ + while (!skb_queue_empty(&tun->queue)) { + skb = skb_dequeue(&tun->queue); + kfree_skb(skb); + } + + kfree(tun); + + return 0; +} + +static const struct file_operations qrtr_tun_ops = { + .owner = THIS_MODULE, + .open = qrtr_tun_open, + .poll = qrtr_tun_poll, + .read_iter = qrtr_tun_read_iter, + .write_iter = qrtr_tun_write_iter, + .release = qrtr_tun_release, +}; + +static struct miscdevice qrtr_tun_miscdev = { + MISC_DYNAMIC_MINOR, + "qrtr-tun", + &qrtr_tun_ops, +}; + +static int __init qrtr_tun_init(void) +{ + int ret; + + ret = misc_register(&qrtr_tun_miscdev); + if (ret) + pr_err("failed to register Qualcomm IPC Router tun device\n"); + + return ret; +} + +static void __exit qrtr_tun_exit(void) +{ + misc_deregister(&qrtr_tun_miscdev); +} + +module_init(qrtr_tun_init); +module_exit(qrtr_tun_exit); + +MODULE_DESCRIPTION("Qualcomm IPC Router TUN device"); +MODULE_LICENSE("GPL v2"); diff --git a/net/sched/act_csum.c b/net/sched/act_csum.c index 7e28b2ce1437..526a8e491626 100644 --- a/net/sched/act_csum.c +++ b/net/sched/act_csum.c @@ -648,6 +648,11 @@ static int tcf_csum_search(struct net *net, struct tc_action **a, u32 index, return tcf_idr_search(tn, a, index); } +static size_t tcf_csum_get_fill_size(const struct tc_action *act) +{ + return nla_total_size(sizeof(struct tc_csum)); +} + static struct tc_action_ops act_csum_ops = { .kind = "csum", .type = TCA_ACT_CSUM, @@ -658,6 +663,7 @@ static struct tc_action_ops act_csum_ops = { .cleanup = tcf_csum_cleanup, .walk = tcf_csum_walker, .lookup = tcf_csum_search, + .get_fill_size = tcf_csum_get_fill_size, .size = sizeof(struct tcf_csum), }; diff --git a/net/sched/cls_flower.c b/net/sched/cls_flower.c index d964e60c730e..eacaaf803914 100644 --- a/net/sched/cls_flower.c +++ b/net/sched/cls_flower.c @@ -61,16 +61,18 @@ struct fl_flow_mask_range { struct fl_flow_mask { struct fl_flow_key key; struct fl_flow_mask_range range; - struct rcu_head rcu; + struct rhash_head ht_node; + struct rhashtable ht; + struct rhashtable_params filter_ht_params; + struct flow_dissector dissector; + struct list_head filters; + struct rcu_head rcu; + struct list_head list; }; struct cls_fl_head { struct rhashtable ht; - struct fl_flow_mask mask; - struct flow_dissector dissector; - bool mask_assigned; - struct list_head filters; - struct rhashtable_params ht_params; + struct list_head masks; union { struct work_struct work; struct rcu_head rcu; @@ -79,6 +81,7 @@ struct cls_fl_head { }; struct cls_fl_filter { + struct fl_flow_mask *mask; struct rhash_head ht_node; struct fl_flow_key mkey; struct tcf_exts exts; @@ -94,6 +97,13 @@ struct cls_fl_filter { struct net_device *hw_dev; }; +static const struct rhashtable_params mask_ht_params = { + .key_offset = offsetof(struct fl_flow_mask, key), + .key_len = sizeof(struct fl_flow_key), + .head_offset = offsetof(struct fl_flow_mask, ht_node), + .automatic_shrinking = true, +}; + static unsigned short int fl_mask_range(const struct fl_flow_mask *mask) { return mask->range.end - mask->range.start; @@ -103,13 +113,19 @@ static void fl_mask_update_range(struct fl_flow_mask *mask) { const u8 *bytes = (const u8 *) &mask->key; size_t size = sizeof(mask->key); - size_t i, first = 0, last = size - 1; + size_t i, first = 0, last; - for (i = 0; i < sizeof(mask->key); i++) { + for (i = 0; i < size; i++) { + if (bytes[i]) { + first = i; + break; + } + } + last = first; + for (i = size - 1; i != first; i--) { if (bytes[i]) { - if (!first && i) - first = i; last = i; + break; } } mask->range.start = rounddown(first, sizeof(long)); @@ -140,12 +156,11 @@ static void fl_clear_masked_range(struct fl_flow_key *key, memset(fl_key_get_start(key, mask), 0, fl_mask_range(mask)); } -static struct cls_fl_filter *fl_lookup(struct cls_fl_head *head, +static struct cls_fl_filter *fl_lookup(struct fl_flow_mask *mask, struct fl_flow_key *mkey) { - return rhashtable_lookup_fast(&head->ht, - fl_key_get_start(mkey, &head->mask), - head->ht_params); + return rhashtable_lookup_fast(&mask->ht, fl_key_get_start(mkey, mask), + mask->filter_ht_params); } static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, @@ -153,28 +168,28 @@ static int fl_classify(struct sk_buff *skb, const struct tcf_proto *tp, { struct cls_fl_head *head = rcu_dereference_bh(tp->root); struct cls_fl_filter *f; + struct fl_flow_mask *mask; struct fl_flow_key skb_key; struct fl_flow_key skb_mkey; - if (!atomic_read(&head->ht.nelems)) - return -1; - - fl_clear_masked_range(&skb_key, &head->mask); + list_for_each_entry_rcu(mask, &head->masks, list) { + fl_clear_masked_range(&skb_key, mask); - skb_key.indev_ifindex = skb->skb_iif; - /* skb_flow_dissect() does not set n_proto in case an unknown protocol, - * so do it rather here. - */ - skb_key.basic.n_proto = skb->protocol; - skb_flow_dissect_tunnel_info(skb, &head->dissector, &skb_key); - skb_flow_dissect(skb, &head->dissector, &skb_key, 0); + skb_key.indev_ifindex = skb->skb_iif; + /* skb_flow_dissect() does not set n_proto in case an unknown + * protocol, so do it rather here. + */ + skb_key.basic.n_proto = skb->protocol; + skb_flow_dissect_tunnel_info(skb, &mask->dissector, &skb_key); + skb_flow_dissect(skb, &mask->dissector, &skb_key, 0); - fl_set_masked_key(&skb_mkey, &skb_key, &head->mask); + fl_set_masked_key(&skb_mkey, &skb_key, mask); - f = fl_lookup(head, &skb_mkey); - if (f && !tc_skip_sw(f->flags)) { - *res = f->res; - return tcf_exts_exec(skb, &f->exts, res); + f = fl_lookup(mask, &skb_mkey); + if (f && !tc_skip_sw(f->flags)) { + *res = f->res; + return tcf_exts_exec(skb, &f->exts, res); + } } return -1; } @@ -187,11 +202,28 @@ static int fl_init(struct tcf_proto *tp) if (!head) return -ENOBUFS; - INIT_LIST_HEAD_RCU(&head->filters); + INIT_LIST_HEAD_RCU(&head->masks); rcu_assign_pointer(tp->root, head); idr_init(&head->handle_idr); - return 0; + return rhashtable_init(&head->ht, &mask_ht_params); +} + +static bool fl_mask_put(struct cls_fl_head *head, struct fl_flow_mask *mask, + bool async) +{ + if (!list_empty(&mask->filters)) + return false; + + rhashtable_remove_fast(&head->ht, &mask->ht_node, mask_ht_params); + rhashtable_destroy(&mask->ht); + list_del_rcu(&mask->list); + if (async) + kfree_rcu(mask, rcu); + else + kfree(mask); + + return true; } static void __fl_destroy_filter(struct cls_fl_filter *f) @@ -234,8 +266,6 @@ static void fl_hw_destroy_filter(struct tcf_proto *tp, struct cls_fl_filter *f, } static int fl_hw_replace_filter(struct tcf_proto *tp, - struct flow_dissector *dissector, - struct fl_flow_key *mask, struct cls_fl_filter *f, struct netlink_ext_ack *extack) { @@ -247,8 +277,8 @@ static int fl_hw_replace_filter(struct tcf_proto *tp, tc_cls_common_offload_init(&cls_flower.common, tp, f->flags, extack); cls_flower.command = TC_CLSFLOWER_REPLACE; cls_flower.cookie = (unsigned long) f; - cls_flower.dissector = dissector; - cls_flower.mask = mask; + cls_flower.dissector = &f->mask->dissector; + cls_flower.mask = &f->mask->key; cls_flower.key = &f->mkey; cls_flower.exts = &f->exts; cls_flower.classid = f->res.classid; @@ -283,28 +313,31 @@ static void fl_hw_update_stats(struct tcf_proto *tp, struct cls_fl_filter *f) &cls_flower, false); } -static void __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, +static bool __fl_delete(struct tcf_proto *tp, struct cls_fl_filter *f, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); + bool async = tcf_exts_get_net(&f->exts); + bool last; idr_remove(&head->handle_idr, f->handle); list_del_rcu(&f->list); + last = fl_mask_put(head, f->mask, async); if (!tc_skip_hw(f->flags)) fl_hw_destroy_filter(tp, f, extack); tcf_unbind_filter(tp, &f->res); - if (tcf_exts_get_net(&f->exts)) + if (async) call_rcu(&f->rcu, fl_destroy_filter); else __fl_destroy_filter(f); + + return last; } static void fl_destroy_sleepable(struct work_struct *work) { struct cls_fl_head *head = container_of(work, struct cls_fl_head, work); - if (head->mask_assigned) - rhashtable_destroy(&head->ht); kfree(head); module_put(THIS_MODULE); } @@ -320,10 +353,15 @@ static void fl_destroy_rcu(struct rcu_head *rcu) static void fl_destroy(struct tcf_proto *tp, struct netlink_ext_ack *extack) { struct cls_fl_head *head = rtnl_dereference(tp->root); + struct fl_flow_mask *mask, *next_mask; struct cls_fl_filter *f, *next; - list_for_each_entry_safe(f, next, &head->filters, list) - __fl_delete(tp, f, extack); + list_for_each_entry_safe(mask, next_mask, &head->masks, list) { + list_for_each_entry_safe(f, next, &mask->filters, list) { + if (__fl_delete(tp, f, extack)) + break; + } + } idr_destroy(&head->handle_idr); __module_get(THIS_MODULE); @@ -715,14 +753,14 @@ static int fl_set_key(struct net *net, struct nlattr **tb, return ret; } -static bool fl_mask_eq(struct fl_flow_mask *mask1, - struct fl_flow_mask *mask2) +static void fl_mask_copy(struct fl_flow_mask *dst, + struct fl_flow_mask *src) { - const long *lmask1 = fl_key_get_start(&mask1->key, mask1); - const long *lmask2 = fl_key_get_start(&mask2->key, mask2); + const void *psrc = fl_key_get_start(&src->key, src); + void *pdst = fl_key_get_start(&dst->key, src); - return !memcmp(&mask1->range, &mask2->range, sizeof(mask1->range)) && - !memcmp(lmask1, lmask2, fl_mask_range(mask1)); + memcpy(pdst, psrc, fl_mask_range(src)); + dst->range = src->range; } static const struct rhashtable_params fl_ht_params = { @@ -731,14 +769,13 @@ static const struct rhashtable_params fl_ht_params = { .automatic_shrinking = true, }; -static int fl_init_hashtable(struct cls_fl_head *head, - struct fl_flow_mask *mask) +static int fl_init_mask_hashtable(struct fl_flow_mask *mask) { - head->ht_params = fl_ht_params; - head->ht_params.key_len = fl_mask_range(mask); - head->ht_params.key_offset += mask->range.start; + mask->filter_ht_params = fl_ht_params; + mask->filter_ht_params.key_len = fl_mask_range(mask); + mask->filter_ht_params.key_offset += mask->range.start; - return rhashtable_init(&head->ht, &head->ht_params); + return rhashtable_init(&mask->ht, &mask->filter_ht_params); } #define FL_KEY_MEMBER_OFFSET(member) offsetof(struct fl_flow_key, member) @@ -761,8 +798,7 @@ static int fl_init_hashtable(struct cls_fl_head *head, FL_KEY_SET(keys, cnt, id, member); \ } while(0); -static void fl_init_dissector(struct cls_fl_head *head, - struct fl_flow_mask *mask) +static void fl_init_dissector(struct fl_flow_mask *mask) { struct flow_dissector_key keys[FLOW_DISSECTOR_KEY_MAX]; size_t cnt = 0; @@ -802,31 +838,66 @@ static void fl_init_dissector(struct cls_fl_head *head, FL_KEY_SET_IF_MASKED(&mask->key, keys, cnt, FLOW_DISSECTOR_KEY_ENC_PORTS, enc_tp); - skb_flow_dissector_init(&head->dissector, keys, cnt); + skb_flow_dissector_init(&mask->dissector, keys, cnt); +} + +static struct fl_flow_mask *fl_create_new_mask(struct cls_fl_head *head, + struct fl_flow_mask *mask) +{ + struct fl_flow_mask *newmask; + int err; + + newmask = kzalloc(sizeof(*newmask), GFP_KERNEL); + if (!newmask) + return ERR_PTR(-ENOMEM); + + fl_mask_copy(newmask, mask); + + err = fl_init_mask_hashtable(newmask); + if (err) + goto errout_free; + + fl_init_dissector(newmask); + + INIT_LIST_HEAD_RCU(&newmask->filters); + + err = rhashtable_insert_fast(&head->ht, &newmask->ht_node, + mask_ht_params); + if (err) + goto errout_destroy; + + list_add_tail_rcu(&newmask->list, &head->masks); + + return newmask; + +errout_destroy: + rhashtable_destroy(&newmask->ht); +errout_free: + kfree(newmask); + + return ERR_PTR(err); } static int fl_check_assign_mask(struct cls_fl_head *head, + struct cls_fl_filter *fnew, + struct cls_fl_filter *fold, struct fl_flow_mask *mask) { - int err; + struct fl_flow_mask *newmask; - if (head->mask_assigned) { - if (!fl_mask_eq(&head->mask, mask)) + fnew->mask = rhashtable_lookup_fast(&head->ht, mask, mask_ht_params); + if (!fnew->mask) { + if (fold) return -EINVAL; - else - return 0; - } - /* Mask is not assigned yet. So assign it and init hashtable - * according to that. - */ - err = fl_init_hashtable(head, mask); - if (err) - return err; - memcpy(&head->mask, mask, sizeof(head->mask)); - head->mask_assigned = true; + newmask = fl_create_new_mask(head, mask); + if (IS_ERR(newmask)) + return PTR_ERR(newmask); - fl_init_dissector(head, mask); + fnew->mask = newmask; + } else if (fold && fold->mask == fnew->mask) { + return -EINVAL; + } return 0; } @@ -924,30 +995,26 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (err) goto errout_idr; - err = fl_check_assign_mask(head, &mask); + err = fl_check_assign_mask(head, fnew, fold, &mask); if (err) goto errout_idr; if (!tc_skip_sw(fnew->flags)) { - if (!fold && fl_lookup(head, &fnew->mkey)) { + if (!fold && fl_lookup(fnew->mask, &fnew->mkey)) { err = -EEXIST; - goto errout_idr; + goto errout_mask; } - err = rhashtable_insert_fast(&head->ht, &fnew->ht_node, - head->ht_params); + err = rhashtable_insert_fast(&fnew->mask->ht, &fnew->ht_node, + fnew->mask->filter_ht_params); if (err) - goto errout_idr; + goto errout_mask; } if (!tc_skip_hw(fnew->flags)) { - err = fl_hw_replace_filter(tp, - &head->dissector, - &mask.key, - fnew, - extack); + err = fl_hw_replace_filter(tp, fnew, extack); if (err) - goto errout_idr; + goto errout_mask; } if (!tc_in_hw(fnew->flags)) @@ -955,8 +1022,9 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, if (fold) { if (!tc_skip_sw(fold->flags)) - rhashtable_remove_fast(&head->ht, &fold->ht_node, - head->ht_params); + rhashtable_remove_fast(&fold->mask->ht, + &fold->ht_node, + fold->mask->filter_ht_params); if (!tc_skip_hw(fold->flags)) fl_hw_destroy_filter(tp, fold, NULL); } @@ -970,12 +1038,15 @@ static int fl_change(struct net *net, struct sk_buff *in_skb, tcf_exts_get_net(&fold->exts); call_rcu(&fold->rcu, fl_destroy_filter); } else { - list_add_tail_rcu(&fnew->list, &head->filters); + list_add_tail_rcu(&fnew->list, &fnew->mask->filters); } kfree(tb); return 0; +errout_mask: + fl_mask_put(head, fnew->mask, false); + errout_idr: if (fnew->handle) idr_remove(&head->handle_idr, fnew->handle); @@ -994,10 +1065,10 @@ static int fl_delete(struct tcf_proto *tp, void *arg, bool *last, struct cls_fl_filter *f = arg; if (!tc_skip_sw(f->flags)) - rhashtable_remove_fast(&head->ht, &f->ht_node, - head->ht_params); + rhashtable_remove_fast(&f->mask->ht, &f->ht_node, + f->mask->filter_ht_params); __fl_delete(tp, f, extack); - *last = list_empty(&head->filters); + *last = list_empty(&head->masks); return 0; } @@ -1005,16 +1076,19 @@ static void fl_walk(struct tcf_proto *tp, struct tcf_walker *arg) { struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f; - - list_for_each_entry_rcu(f, &head->filters, list) { - if (arg->count < arg->skip) - goto skip; - if (arg->fn(tp, f, arg) < 0) { - arg->stop = 1; - break; - } + struct fl_flow_mask *mask; + + list_for_each_entry_rcu(mask, &head->masks, list) { + list_for_each_entry_rcu(f, &mask->filters, list) { + if (arg->count < arg->skip) + goto skip; + if (arg->fn(tp, f, arg) < 0) { + arg->stop = 1; + break; + } skip: - arg->count++; + arg->count++; + } } } @@ -1150,7 +1224,6 @@ static int fl_dump_key_flags(struct sk_buff *skb, u32 flags_key, u32 flags_mask) static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, struct sk_buff *skb, struct tcmsg *t) { - struct cls_fl_head *head = rtnl_dereference(tp->root); struct cls_fl_filter *f = fh; struct nlattr *nest; struct fl_flow_key *key, *mask; @@ -1169,7 +1242,7 @@ static int fl_dump(struct net *net, struct tcf_proto *tp, void *fh, goto nla_put_failure; key = &f->key; - mask = &head->mask.key; + mask = &f->mask->key; if (mask->indev_ifindex) { struct net_device *dev; diff --git a/net/sctp/associola.c b/net/sctp/associola.c index a47179da24e6..5d5a16204d50 100644 --- a/net/sctp/associola.c +++ b/net/sctp/associola.c @@ -652,33 +652,20 @@ struct sctp_transport *sctp_assoc_add_peer(struct sctp_association *asoc, */ peer->param_flags = asoc->param_flags; - sctp_transport_route(peer, NULL, sp); - /* Initialize the pmtu of the transport. */ - if (peer->param_flags & SPP_PMTUD_DISABLE) { - if (asoc->pathmtu) - peer->pathmtu = asoc->pathmtu; - else - peer->pathmtu = SCTP_DEFAULT_MAXSEGMENT; - } + sctp_transport_route(peer, NULL, sp); /* If this is the first transport addr on this association, * initialize the association PMTU to the peer's PMTU. * If not and the current association PMTU is higher than the new * peer's PMTU, reset the association PMTU to the new peer's PMTU. */ - if (asoc->pathmtu) - asoc->pathmtu = min_t(int, peer->pathmtu, asoc->pathmtu); - else - asoc->pathmtu = peer->pathmtu; - - pr_debug("%s: association:%p PMTU set to %d\n", __func__, asoc, - asoc->pathmtu); + sctp_assoc_set_pmtu(asoc, asoc->pathmtu ? + min_t(int, peer->pathmtu, asoc->pathmtu) : + peer->pathmtu); peer->pmtu_pending = 0; - asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); - /* The asoc->peer.port might not be meaningful yet, but * initialize the packet structure anyway. */ @@ -988,31 +975,6 @@ out: return match; } -/* Is this the association we are looking for? */ -struct sctp_transport *sctp_assoc_is_match(struct sctp_association *asoc, - struct net *net, - const union sctp_addr *laddr, - const union sctp_addr *paddr) -{ - struct sctp_transport *transport; - - if ((htons(asoc->base.bind_addr.port) == laddr->v4.sin_port) && - (htons(asoc->peer.port) == paddr->v4.sin_port) && - net_eq(sock_net(asoc->base.sk), net)) { - transport = sctp_assoc_lookup_paddr(asoc, paddr); - if (!transport) - goto out; - - if (sctp_bind_addr_match(&asoc->base.bind_addr, laddr, - sctp_sk(asoc->base.sk))) - goto out; - } - transport = NULL; - -out: - return transport; -} - /* Do delayed input processing. This is scheduled by sctp_rcv(). */ static void sctp_assoc_bh_rcv(struct work_struct *work) { @@ -1434,6 +1396,31 @@ sctp_assoc_choose_alter_transport(struct sctp_association *asoc, } } +void sctp_assoc_update_frag_point(struct sctp_association *asoc) +{ + int frag = sctp_mtu_payload(sctp_sk(asoc->base.sk), asoc->pathmtu, + sctp_datachk_len(&asoc->stream)); + + if (asoc->user_frag) + frag = min_t(int, frag, asoc->user_frag); + + frag = min_t(int, frag, SCTP_MAX_CHUNK_LEN - + sctp_datachk_len(&asoc->stream)); + + asoc->frag_point = SCTP_TRUNC4(frag); +} + +void sctp_assoc_set_pmtu(struct sctp_association *asoc, __u32 pmtu) +{ + if (asoc->pathmtu != pmtu) { + asoc->pathmtu = pmtu; + sctp_assoc_update_frag_point(asoc); + } + + pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc, + asoc->pathmtu, asoc->frag_point); +} + /* Update the association's pmtu and frag_point by going through all the * transports. This routine is called when a transport's PMTU has changed. */ @@ -1446,24 +1433,16 @@ void sctp_assoc_sync_pmtu(struct sctp_association *asoc) return; /* Get the lowest pmtu of all the transports. */ - list_for_each_entry(t, &asoc->peer.transport_addr_list, - transports) { + list_for_each_entry(t, &asoc->peer.transport_addr_list, transports) { if (t->pmtu_pending && t->dst) { - sctp_transport_update_pmtu( - t, SCTP_TRUNC4(dst_mtu(t->dst))); + sctp_transport_update_pmtu(t, sctp_dst_mtu(t->dst)); t->pmtu_pending = 0; } if (!pmtu || (t->pathmtu < pmtu)) pmtu = t->pathmtu; } - if (pmtu) { - asoc->pathmtu = pmtu; - asoc->frag_point = sctp_frag_point(asoc, pmtu); - } - - pr_debug("%s: asoc:%p, pmtu:%d, frag_point:%d\n", __func__, asoc, - asoc->pathmtu, asoc->frag_point); + sctp_assoc_set_pmtu(asoc, pmtu); } /* Should we send a SACK to update our peer? */ diff --git a/net/sctp/chunk.c b/net/sctp/chunk.c index be296d633e95..79daa98208c3 100644 --- a/net/sctp/chunk.c +++ b/net/sctp/chunk.c @@ -172,8 +172,6 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, struct list_head *pos, *temp; struct sctp_chunk *chunk; struct sctp_datamsg *msg; - struct sctp_sock *sp; - struct sctp_af *af; int err; msg = sctp_datamsg_new(GFP_KERNEL); @@ -192,12 +190,7 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, /* This is the biggest possible DATA chunk that can fit into * the packet */ - sp = sctp_sk(asoc->base.sk); - af = sp->pf->af; - max_data = asoc->pathmtu - af->net_header_len - - sizeof(struct sctphdr) - sctp_datachk_len(&asoc->stream) - - af->ip_options_len(asoc->base.sk); - max_data = SCTP_TRUNC4(max_data); + max_data = asoc->frag_point; /* If the the peer requested that we authenticate DATA chunks * we need to account for bundling of the AUTH chunks along with @@ -222,9 +215,6 @@ struct sctp_datamsg *sctp_datamsg_from_user(struct sctp_association *asoc, } } - /* Check what's our max considering the above */ - max_data = min_t(size_t, max_data, asoc->frag_point); - /* Set first_len and then account for possible bundles on first frag */ first_len = max_data; diff --git a/net/sctp/output.c b/net/sctp/output.c index 690d8557bb7b..e672dee302c7 100644 --- a/net/sctp/output.c +++ b/net/sctp/output.c @@ -90,8 +90,8 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, { struct sctp_transport *tp = packet->transport; struct sctp_association *asoc = tp->asoc; + struct sctp_sock *sp = NULL; struct sock *sk; - size_t overhead = sizeof(struct ipv6hdr) + sizeof(struct sctphdr); pr_debug("%s: packet:%p vtag:0x%x\n", __func__, packet, vtag); packet->vtag = vtag; @@ -102,28 +102,20 @@ void sctp_packet_config(struct sctp_packet *packet, __u32 vtag, /* set packet max_size with pathmtu, then calculate overhead */ packet->max_size = tp->pathmtu; + if (asoc) { - struct sctp_sock *sp = sctp_sk(asoc->base.sk); - struct sctp_af *af = sp->pf->af; - - overhead = af->net_header_len + - af->ip_options_len(asoc->base.sk); - overhead += sizeof(struct sctphdr); - packet->overhead = overhead; - packet->size = overhead; - } else { - packet->overhead = overhead; - packet->size = overhead; - return; + sk = asoc->base.sk; + sp = sctp_sk(sk); } + packet->overhead = sctp_mtu_payload(sp, 0, 0); + packet->size = packet->overhead; + + if (!asoc) + return; /* update dst or transport pathmtu if in need */ - sk = asoc->base.sk; if (!sctp_transport_dst_check(tp)) { - sctp_transport_route(tp, NULL, sctp_sk(sk)); - if (asoc->param_flags & SPP_PMTUD_ENABLE) - sctp_assoc_sync_pmtu(asoc); - } else if (!sctp_transport_pmtu_check(tp)) { + sctp_transport_route(tp, NULL, sp); if (asoc->param_flags & SPP_PMTUD_ENABLE) sctp_assoc_sync_pmtu(asoc); } diff --git a/net/sctp/outqueue.c b/net/sctp/outqueue.c index f211b3db6a35..dee7cbd54831 100644 --- a/net/sctp/outqueue.c +++ b/net/sctp/outqueue.c @@ -1457,7 +1457,7 @@ static void sctp_check_transmitted(struct sctp_outq *q, * the outstanding bytes for this chunk, so only * count bytes associated with a transport. */ - if (transport) { + if (transport && !tchunk->tsn_gap_acked) { /* If this chunk is being used for RTT * measurement, calculate the RTT and update * the RTO using this value. @@ -1469,14 +1469,34 @@ static void sctp_check_transmitted(struct sctp_outq *q, * first instance of the packet or a later * instance). */ - if (!tchunk->tsn_gap_acked && - !sctp_chunk_retransmitted(tchunk) && + if (!sctp_chunk_retransmitted(tchunk) && tchunk->rtt_in_progress) { tchunk->rtt_in_progress = 0; rtt = jiffies - tchunk->sent_at; sctp_transport_update_rto(transport, rtt); } + + if (TSN_lte(tsn, sack_ctsn)) { + /* + * SFR-CACC algorithm: + * 2) If the SACK contains gap acks + * and the flag CHANGEOVER_ACTIVE is + * set the receiver of the SACK MUST + * take the following action: + * + * B) For each TSN t being acked that + * has not been acked in any SACK so + * far, set cacc_saw_newack to 1 for + * the destination that the TSN was + * sent to. + */ + if (sack->num_gap_ack_blocks && + q->asoc->peer.primary_path->cacc. + changeover_active) + transport->cacc.cacc_saw_newack + = 1; + } } /* If the chunk hasn't been marked as ACKED, @@ -1508,28 +1528,6 @@ static void sctp_check_transmitted(struct sctp_outq *q, restart_timer = 1; forward_progress = true; - if (!tchunk->tsn_gap_acked) { - /* - * SFR-CACC algorithm: - * 2) If the SACK contains gap acks - * and the flag CHANGEOVER_ACTIVE is - * set the receiver of the SACK MUST - * take the following action: - * - * B) For each TSN t being acked that - * has not been acked in any SACK so - * far, set cacc_saw_newack to 1 for - * the destination that the TSN was - * sent to. - */ - if (transport && - sack->num_gap_ack_blocks && - q->asoc->peer.primary_path->cacc. - changeover_active) - transport->cacc.cacc_saw_newack - = 1; - } - list_add_tail(&tchunk->transmitted_list, &q->sacked); } else { diff --git a/net/sctp/sm_make_chunk.c b/net/sctp/sm_make_chunk.c index e62addb60434..4a4fd1971255 100644 --- a/net/sctp/sm_make_chunk.c +++ b/net/sctp/sm_make_chunk.c @@ -81,8 +81,6 @@ static int sctp_process_param(struct sctp_association *asoc, gfp_t gfp); static void *sctp_addto_param(struct sctp_chunk *chunk, int len, const void *data); -static void *sctp_addto_chunk_fixed(struct sctp_chunk *, int len, - const void *data); /* Control chunk destructor */ static void sctp_control_release_owner(struct sk_buff *skb) @@ -154,12 +152,11 @@ static const struct sctp_paramhdr prsctp_param = { cpu_to_be16(sizeof(struct sctp_paramhdr)), }; -/* A helper to initialize an op error inside a - * provided chunk, as most cause codes will be embedded inside an - * abort chunk. +/* A helper to initialize an op error inside a provided chunk, as most + * cause codes will be embedded inside an abort chunk. */ -void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, - size_t paylen) +int sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, + size_t paylen) { struct sctp_errhdr err; __u16 len; @@ -167,33 +164,16 @@ void sctp_init_cause(struct sctp_chunk *chunk, __be16 cause_code, /* Cause code constants are now defined in network order. */ err.cause = cause_code; len = sizeof(err) + paylen; - err.length = htons(len); - chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err); -} - -/* A helper to initialize an op error inside a - * provided chunk, as most cause codes will be embedded inside an - * abort chunk. Differs from sctp_init_cause in that it won't oops - * if there isn't enough space in the op error chunk - */ -static int sctp_init_cause_fixed(struct sctp_chunk *chunk, __be16 cause_code, - size_t paylen) -{ - struct sctp_errhdr err; - __u16 len; - - /* Cause code constants are now defined in network order. */ - err.cause = cause_code; - len = sizeof(err) + paylen; - err.length = htons(len); + err.length = htons(len); if (skb_tailroom(chunk->skb) < len) return -ENOSPC; - chunk->subh.err_hdr = sctp_addto_chunk_fixed(chunk, sizeof(err), &err); + chunk->subh.err_hdr = sctp_addto_chunk(chunk, sizeof(err), &err); return 0; } + /* 3.3.2 Initiation (INIT) (1) * * This chunk is used to initiate a SCTP association between two @@ -779,10 +759,9 @@ struct sctp_chunk *sctp_make_datafrag_empty(const struct sctp_association *asoc, * association. This reports on which TSN's we've seen to date, * including duplicates and gaps. */ -struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) +struct sctp_chunk *sctp_make_sack(struct sctp_association *asoc) { struct sctp_tsnmap *map = (struct sctp_tsnmap *)&asoc->peer.tsn_map; - struct sctp_association *aptr = (struct sctp_association *)asoc; struct sctp_gap_ack_block gabs[SCTP_MAX_GABS]; __u16 num_gabs, num_dup_tsns; struct sctp_transport *trans; @@ -857,7 +836,7 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) /* Add the duplicate TSN information. */ if (num_dup_tsns) { - aptr->stats.idupchunks += num_dup_tsns; + asoc->stats.idupchunks += num_dup_tsns; sctp_addto_chunk(retval, sizeof(__u32) * num_dup_tsns, sctp_tsnmap_get_dups(map)); } @@ -869,11 +848,11 @@ struct sctp_chunk *sctp_make_sack(const struct sctp_association *asoc) * association so no transport will match after a wrap event like this, * Until the next sack */ - if (++aptr->peer.sack_generation == 0) { + if (++asoc->peer.sack_generation == 0) { list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) trans->sack_generation = 0; - aptr->peer.sack_generation = 1; + asoc->peer.sack_generation = 1; } nodata: return retval; @@ -1258,20 +1237,26 @@ nodata: return retval; } -/* Create an Operation Error chunk of a fixed size, - * specifically, max(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - * This is a helper function to allocate an error chunk for - * for those invalid parameter codes in which we may not want - * to report all the errors, if the incoming chunk is large +/* Create an Operation Error chunk of a fixed size, specifically, + * min(asoc->pathmtu, SCTP_DEFAULT_MAXSEGMENT) - overheads. + * This is a helper function to allocate an error chunk for for those + * invalid parameter codes in which we may not want to report all the + * errors, if the incoming chunk is large. If it can't fit in a single + * packet, we ignore it. */ -static inline struct sctp_chunk *sctp_make_op_error_fixed( +static inline struct sctp_chunk *sctp_make_op_error_limited( const struct sctp_association *asoc, const struct sctp_chunk *chunk) { - size_t size = asoc ? asoc->pathmtu : 0; + size_t size = SCTP_DEFAULT_MAXSEGMENT; + struct sctp_sock *sp = NULL; - if (!size) - size = SCTP_DEFAULT_MAXSEGMENT; + if (asoc) { + size = min_t(size_t, size, asoc->pathmtu); + sp = sctp_sk(asoc->base.sk); + } + + size = sctp_mtu_payload(sp, size, sizeof(struct sctp_errhdr)); return sctp_make_op_error_space(asoc, chunk, size); } @@ -1523,18 +1508,6 @@ void *sctp_addto_chunk(struct sctp_chunk *chunk, int len, const void *data) return target; } -/* Append bytes to the end of a chunk. Returns NULL if there isn't sufficient - * space in the chunk - */ -static void *sctp_addto_chunk_fixed(struct sctp_chunk *chunk, - int len, const void *data) -{ - if (skb_tailroom(chunk->skb) >= len) - return sctp_addto_chunk(chunk, len, data); - else - return NULL; -} - /* Append bytes from user space to the end of a chunk. Will panic if * chunk is not big enough. * Returns a kernel err value. @@ -1829,6 +1802,9 @@ no_hmac: kt = ktime_get_real(); if (!asoc && ktime_before(bear_cookie->expiration, kt)) { + suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration)); + __be32 n = htonl(usecs); + /* * Section 3.3.10.3 Stale Cookie Error (3) * @@ -1837,17 +1813,12 @@ no_hmac: * Stale Cookie Error: Indicates the receipt of a valid State * Cookie that has expired. */ - len = ntohs(chunk->chunk_hdr->length); - *errp = sctp_make_op_error_space(asoc, chunk, len); - if (*errp) { - suseconds_t usecs = ktime_to_us(ktime_sub(kt, bear_cookie->expiration)); - __be32 n = htonl(usecs); - - sctp_init_cause(*errp, SCTP_ERROR_STALE_COOKIE, - sizeof(n)); - sctp_addto_chunk(*errp, sizeof(n), &n); + *errp = sctp_make_op_error(asoc, chunk, + SCTP_ERROR_STALE_COOKIE, &n, + sizeof(n), 0); + if (*errp) *error = -SCTP_IERROR_STALE_COOKIE; - } else + else *error = -SCTP_IERROR_NOMEM; goto fail; @@ -1998,12 +1969,8 @@ static int sctp_process_hn_param(const struct sctp_association *asoc, if (*errp) sctp_chunk_free(*errp); - *errp = sctp_make_op_error_space(asoc, chunk, len); - - if (*errp) { - sctp_init_cause(*errp, SCTP_ERROR_DNS_FAILED, len); - sctp_addto_chunk(*errp, len, param.v); - } + *errp = sctp_make_op_error(asoc, chunk, SCTP_ERROR_DNS_FAILED, + param.v, len, 0); /* Stop processing this chunk. */ return 0; @@ -2128,23 +2095,23 @@ static enum sctp_ierror sctp_process_unk_param( /* Make an ERROR chunk, preparing enough room for * returning multiple unknown parameters. */ - if (NULL == *errp) - *errp = sctp_make_op_error_fixed(asoc, chunk); - - if (*errp) { - if (!sctp_init_cause_fixed(*errp, SCTP_ERROR_UNKNOWN_PARAM, - SCTP_PAD4(ntohs(param.p->length)))) - sctp_addto_chunk_fixed(*errp, - SCTP_PAD4(ntohs(param.p->length)), - param.v); - } else { - /* If there is no memory for generating the ERROR - * report as specified, an ABORT will be triggered - * to the peer and the association won't be - * established. - */ - retval = SCTP_IERROR_NOMEM; + if (!*errp) { + *errp = sctp_make_op_error_limited(asoc, chunk); + if (!*errp) { + /* If there is no memory for generating the + * ERROR report as specified, an ABORT will be + * triggered to the peer and the association + * won't be established. + */ + retval = SCTP_IERROR_NOMEM; + break; + } } + + if (!sctp_init_cause(*errp, SCTP_ERROR_UNKNOWN_PARAM, + ntohs(param.p->length))) + sctp_addto_chunk(*errp, ntohs(param.p->length), + param.v); break; default: break; @@ -2220,10 +2187,10 @@ static enum sctp_ierror sctp_verify_param(struct net *net, * MUST be aborted. The ABORT chunk SHOULD contain the error * cause 'Protocol Violation'. */ - if (SCTP_AUTH_RANDOM_LENGTH != - ntohs(param.p->length) - sizeof(struct sctp_paramhdr)) { + if (SCTP_AUTH_RANDOM_LENGTH != ntohs(param.p->length) - + sizeof(struct sctp_paramhdr)) { sctp_process_inv_paramlength(asoc, param.p, - chunk, err_chunk); + chunk, err_chunk); retval = SCTP_IERROR_ABORT; } break; diff --git a/net/sctp/socket.c b/net/sctp/socket.c index 80835ac26d2c..1b4593b842b0 100644 --- a/net/sctp/socket.c +++ b/net/sctp/socket.c @@ -644,16 +644,15 @@ static int sctp_send_asconf_add_ip(struct sock *sk, list_for_each_entry(trans, &asoc->peer.transport_addr_list, transports) { - /* Clear the source and route cache */ - sctp_transport_dst_release(trans); trans->cwnd = min(4*asoc->pathmtu, max_t(__u32, 2*asoc->pathmtu, 4380)); trans->ssthresh = asoc->peer.i.a_rwnd; trans->rto = asoc->rto_initial; sctp_max_rto(asoc, trans); trans->rtt = trans->srtt = trans->rttvar = 0; + /* Clear the source and route cache */ sctp_transport_route(trans, NULL, - sctp_sk(asoc->base.sk)); + sctp_sk(asoc->base.sk)); } } retval = sctp_send_asconf(asoc, chunk); @@ -896,7 +895,6 @@ skip_mkasconf: */ list_for_each_entry(transport, &asoc->peer.transport_addr_list, transports) { - sctp_transport_dst_release(transport); sctp_transport_route(transport, NULL, sctp_sk(asoc->base.sk)); } @@ -1895,6 +1893,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, struct sctp_sndrcvinfo *sinfo) { struct sock *sk = asoc->base.sk; + struct sctp_sock *sp = sctp_sk(sk); struct net *net = sock_net(sk); struct sctp_datamsg *datamsg; bool wait_connect = false; @@ -1913,13 +1912,16 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, goto err; } - if (sctp_sk(sk)->disable_fragments && msg_len > asoc->frag_point) { + if (sp->disable_fragments && msg_len > asoc->frag_point) { err = -EMSGSIZE; goto err; } - if (asoc->pmtu_pending) - sctp_assoc_pending_pmtu(asoc); + if (asoc->pmtu_pending) { + if (sp->param_flags & SPP_PMTUD_ENABLE) + sctp_assoc_sync_pmtu(asoc); + asoc->pmtu_pending = 0; + } if (sctp_wspace(asoc) < msg_len) sctp_prsctp_prune(asoc, sinfo, msg_len - sctp_wspace(asoc)); @@ -1936,7 +1938,7 @@ static int sctp_sendmsg_to_asoc(struct sctp_association *asoc, if (err) goto err; - if (sctp_sk(sk)->strm_interleave) { + if (sp->strm_interleave) { timeo = sock_sndtimeo(sk, 0); err = sctp_wait_for_connect(asoc, &timeo); if (err) @@ -2539,7 +2541,7 @@ static int sctp_apply_peer_addr_params(struct sctp_paddrparams *params, trans->pathmtu = params->spp_pathmtu; sctp_assoc_sync_pmtu(asoc); } else if (asoc) { - asoc->pathmtu = params->spp_pathmtu; + sctp_assoc_set_pmtu(asoc, params->spp_pathmtu); } else { sp->pathmtu = params->spp_pathmtu; } @@ -3209,7 +3211,6 @@ static int sctp_setsockopt_mappedv4(struct sock *sk, char __user *optval, unsign static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned int optlen) { struct sctp_sock *sp = sctp_sk(sk); - struct sctp_af *af = sp->pf->af; struct sctp_assoc_value params; struct sctp_association *asoc; int val; @@ -3231,30 +3232,24 @@ static int sctp_setsockopt_maxseg(struct sock *sk, char __user *optval, unsigned return -EINVAL; } + asoc = sctp_id2assoc(sk, params.assoc_id); + if (val) { int min_len, max_len; + __u16 datasize = asoc ? sctp_datachk_len(&asoc->stream) : + sizeof(struct sctp_data_chunk); - min_len = SCTP_DEFAULT_MINSEGMENT - af->net_header_len; - min_len -= af->ip_options_len(sk); - min_len -= sizeof(struct sctphdr) + - sizeof(struct sctp_data_chunk); - - max_len = SCTP_MAX_CHUNK_LEN - sizeof(struct sctp_data_chunk); + min_len = sctp_mtu_payload(sp, SCTP_DEFAULT_MINSEGMENT, + datasize); + max_len = SCTP_MAX_CHUNK_LEN - datasize; if (val < min_len || val > max_len) return -EINVAL; } - asoc = sctp_id2assoc(sk, params.assoc_id); if (asoc) { - if (val == 0) { - val = asoc->pathmtu - af->net_header_len; - val -= af->ip_options_len(sk); - val -= sizeof(struct sctphdr) + - sctp_datachk_len(&asoc->stream); - } asoc->user_frag = val; - asoc->frag_point = sctp_frag_point(asoc, asoc->pathmtu); + sctp_assoc_update_frag_point(asoc); } else { if (params.assoc_id && sctp_style(sk, UDP)) return -EINVAL; diff --git a/net/sctp/transport.c b/net/sctp/transport.c index 47f82bd794d9..4a95e260b674 100644 --- a/net/sctp/transport.c +++ b/net/sctp/transport.c @@ -242,9 +242,18 @@ void sctp_transport_pmtu(struct sctp_transport *transport, struct sock *sk) &transport->fl, sk); } - if (transport->dst) { - transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst)); - } else + if (transport->param_flags & SPP_PMTUD_DISABLE) { + struct sctp_association *asoc = transport->asoc; + + if (!transport->pathmtu && asoc && asoc->pathmtu) + transport->pathmtu = asoc->pathmtu; + if (transport->pathmtu) + return; + } + + if (transport->dst) + transport->pathmtu = sctp_dst_mtu(transport->dst); + else transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; } @@ -290,6 +299,7 @@ void sctp_transport_route(struct sctp_transport *transport, struct sctp_association *asoc = transport->asoc; struct sctp_af *af = transport->af_specific; + sctp_transport_dst_release(transport); af->get_dst(transport, saddr, &transport->fl, sctp_opt2sk(opt)); if (saddr) @@ -297,21 +307,14 @@ void sctp_transport_route(struct sctp_transport *transport, else af->get_saddr(opt, transport, &transport->fl); - if ((transport->param_flags & SPP_PMTUD_DISABLE) && transport->pathmtu) { - return; - } - if (transport->dst) { - transport->pathmtu = SCTP_TRUNC4(dst_mtu(transport->dst)); + sctp_transport_pmtu(transport, sctp_opt2sk(opt)); - /* Initialize sk->sk_rcv_saddr, if the transport is the - * association's active path for getsockname(). - */ - if (asoc && (!asoc->peer.primary_path || - (transport == asoc->peer.active_path))) - opt->pf->to_sk_saddr(&transport->saddr, - asoc->base.sk); - } else - transport->pathmtu = SCTP_DEFAULT_MAXSEGMENT; + /* Initialize sk->sk_rcv_saddr, if the transport is the + * association's active path for getsockname(). + */ + if (transport->dst && asoc && + (!asoc->peer.primary_path || transport == asoc->peer.active_path)) + opt->pf->to_sk_saddr(&transport->saddr, asoc->base.sk); } /* Hold a reference to a transport. */ diff --git a/net/smc/af_smc.c b/net/smc/af_smc.c index 544bab42f925..17688a02035b 100644 --- a/net/smc/af_smc.c +++ b/net/smc/af_smc.c @@ -29,6 +29,7 @@ #include <net/sock.h> #include <net/tcp.h> #include <net/smc.h> +#include <asm/ioctls.h> #include "smc.h" #include "smc_clc.h" @@ -305,6 +306,7 @@ static int smc_reg_rmb(struct smc_link *link, struct smc_buf_desc *rmb_desc) static int smc_clnt_conf_first_link(struct smc_sock *smc) { + struct net *net = sock_net(smc->clcsock->sk); struct smc_link_group *lgr = smc->conn.lgr; struct smc_link *link; int rest; @@ -362,7 +364,7 @@ static int smc_clnt_conf_first_link(struct smc_sock *smc) if (rc < 0) return SMC_CLC_DECL_TCL; - link->state = SMC_LNK_ACTIVE; + smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time); return 0; } @@ -400,6 +402,9 @@ static int smc_connect_rdma(struct smc_sock *smc) sock_hold(&smc->sk); /* sock put in passive closing */ + if (smc->use_fallback) + goto out_connected; + if (!tcp_sk(smc->clcsock->sk)->syn_smc) { /* peer has not signalled SMC-capability */ smc->use_fallback = true; @@ -716,6 +721,7 @@ void smc_close_non_accepted(struct sock *sk) static int smc_serv_conf_first_link(struct smc_sock *smc) { + struct net *net = sock_net(smc->clcsock->sk); struct smc_link_group *lgr = smc->conn.lgr; struct smc_link *link; int rest; @@ -768,7 +774,7 @@ static int smc_serv_conf_first_link(struct smc_sock *smc) return rc; } - link->state = SMC_LNK_ACTIVE; + smc_llc_link_active(link, net->ipv4.sysctl_tcp_keepalive_time); return 0; } @@ -792,6 +798,9 @@ static void smc_listen_work(struct work_struct *work) int rc = 0; u8 ibport; + if (new_smc->use_fallback) + goto out_connected; + /* check if peer is smc capable */ if (!tcp_sk(newclcsock->sk)->syn_smc) { new_smc->use_fallback = true; @@ -965,7 +974,7 @@ static void smc_tcp_listen_work(struct work_struct *work) continue; new_smc->listen_smc = lsmc; - new_smc->use_fallback = false; /* assume rdma capability first*/ + new_smc->use_fallback = lsmc->use_fallback; sock_hold(lsk); /* sock_put in smc_listen_work */ INIT_WORK(&new_smc->smc_listen_work, smc_listen_work); smc_copy_sock_settings_to_smc(new_smc); @@ -1001,7 +1010,8 @@ static int smc_listen(struct socket *sock, int backlog) * them to the clc socket -- copy smc socket options to clc socket */ smc_copy_sock_settings_to_clc(smc); - tcp_sk(smc->clcsock->sk)->syn_smc = 1; + if (!smc->use_fallback) + tcp_sk(smc->clcsock->sk)->syn_smc = 1; rc = kernel_listen(smc->clcsock, backlog); if (rc) @@ -1034,6 +1044,7 @@ static int smc_accept(struct socket *sock, struct socket *new_sock, if (lsmc->sk.sk_state != SMC_LISTEN) { rc = -EINVAL; + release_sock(sk); goto out; } @@ -1061,9 +1072,29 @@ static int smc_accept(struct socket *sock, struct socket *new_sock, if (!rc) rc = sock_error(nsk); + release_sock(sk); + if (rc) + goto out; + + if (lsmc->sockopt_defer_accept && !(flags & O_NONBLOCK)) { + /* wait till data arrives on the socket */ + timeo = msecs_to_jiffies(lsmc->sockopt_defer_accept * + MSEC_PER_SEC); + if (smc_sk(nsk)->use_fallback) { + struct sock *clcsk = smc_sk(nsk)->clcsock->sk; + + lock_sock(clcsk); + if (skb_queue_empty(&clcsk->sk_receive_queue)) + sk_wait_data(clcsk, &timeo, NULL); + release_sock(clcsk); + } else if (!atomic_read(&smc_sk(nsk)->conn.bytes_to_rcv)) { + lock_sock(nsk); + smc_rx_wait(smc_sk(nsk), &timeo, smc_rx_data_available); + release_sock(nsk); + } + } out: - release_sock(sk); sock_put(sk); /* sock_hold above */ return rc; } @@ -1094,6 +1125,16 @@ static int smc_sendmsg(struct socket *sock, struct msghdr *msg, size_t len) (sk->sk_state != SMC_APPCLOSEWAIT1) && (sk->sk_state != SMC_INIT)) goto out; + + if (msg->msg_flags & MSG_FASTOPEN) { + if (sk->sk_state == SMC_INIT) { + smc->use_fallback = true; + } else { + rc = -EINVAL; + goto out; + } + } + if (smc->use_fallback) rc = smc->clcsock->ops->sendmsg(smc->clcsock, msg, len); else @@ -1122,10 +1163,12 @@ static int smc_recvmsg(struct socket *sock, struct msghdr *msg, size_t len, goto out; } - if (smc->use_fallback) + if (smc->use_fallback) { rc = smc->clcsock->ops->recvmsg(smc->clcsock, msg, len, flags); - else - rc = smc_rx_recvmsg(smc, msg, len, flags); + } else { + msg->msg_namelen = 0; + rc = smc_rx_recvmsg(smc, msg, NULL, len, flags); + } out: release_sock(sk); @@ -1273,14 +1316,64 @@ static int smc_setsockopt(struct socket *sock, int level, int optname, { struct sock *sk = sock->sk; struct smc_sock *smc; + int val, rc; smc = smc_sk(sk); /* generic setsockopts reaching us here always apply to the * CLC socket */ - return smc->clcsock->ops->setsockopt(smc->clcsock, level, optname, - optval, optlen); + rc = smc->clcsock->ops->setsockopt(smc->clcsock, level, optname, + optval, optlen); + if (smc->clcsock->sk->sk_err) { + sk->sk_err = smc->clcsock->sk->sk_err; + sk->sk_error_report(sk); + } + if (rc) + return rc; + + if (optlen < sizeof(int)) + return rc; + get_user(val, (int __user *)optval); + + lock_sock(sk); + switch (optname) { + case TCP_ULP: + case TCP_FASTOPEN: + case TCP_FASTOPEN_CONNECT: + case TCP_FASTOPEN_KEY: + case TCP_FASTOPEN_NO_COOKIE: + /* option not supported by SMC */ + if (sk->sk_state == SMC_INIT) { + smc->use_fallback = true; + } else { + if (!smc->use_fallback) + rc = -EINVAL; + } + break; + case TCP_NODELAY: + if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (val) + mod_delayed_work(system_wq, &smc->conn.tx_work, + 0); + } + break; + case TCP_CORK: + if (sk->sk_state != SMC_INIT && sk->sk_state != SMC_LISTEN) { + if (!val) + mod_delayed_work(system_wq, &smc->conn.tx_work, + 0); + } + break; + case TCP_DEFER_ACCEPT: + smc->sockopt_defer_accept = val; + break; + default: + break; + } + release_sock(sk); + + return rc; } static int smc_getsockopt(struct socket *sock, int level, int optname, @@ -1298,12 +1391,38 @@ static int smc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { struct smc_sock *smc; + int answ; smc = smc_sk(sock->sk); - if (smc->use_fallback) + if (smc->use_fallback) { + if (!smc->clcsock) + return -EBADF; return smc->clcsock->ops->ioctl(smc->clcsock, cmd, arg); - else - return sock_no_ioctl(sock, cmd, arg); + } + switch (cmd) { + case SIOCINQ: /* same as FIONREAD */ + if (smc->sk.sk_state == SMC_LISTEN) + return -EINVAL; + answ = atomic_read(&smc->conn.bytes_to_rcv); + break; + case SIOCOUTQ: + /* output queue size (not send + not acked) */ + if (smc->sk.sk_state == SMC_LISTEN) + return -EINVAL; + answ = smc->conn.sndbuf_size - + atomic_read(&smc->conn.sndbuf_space); + break; + case SIOCOUTQNSD: + /* output queue size (not send only) */ + if (smc->sk.sk_state == SMC_LISTEN) + return -EINVAL; + answ = smc_tx_prepared_sends(&smc->conn); + break; + default: + return -ENOIOCTLCMD; + } + + return put_user(answ, (int __user *)arg); } static ssize_t smc_sendpage(struct socket *sock, struct page *page, @@ -1330,9 +1449,15 @@ out: return rc; } +/* Map the affected portions of the rmbe into an spd, note the number of bytes + * to splice in conn->splice_pending, and press 'go'. Delays consumer cursor + * updates till whenever a respective page has been fully processed. + * Note that subsequent recv() calls have to wait till all splice() processing + * completed. + */ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, struct pipe_inode_info *pipe, size_t len, - unsigned int flags) + unsigned int flags) { struct sock *sk = sock->sk; struct smc_sock *smc; @@ -1340,16 +1465,34 @@ static ssize_t smc_splice_read(struct socket *sock, loff_t *ppos, smc = smc_sk(sk); lock_sock(sk); - if ((sk->sk_state != SMC_ACTIVE) && (sk->sk_state != SMC_CLOSED)) + + if (sk->sk_state == SMC_INIT || + sk->sk_state == SMC_LISTEN || + sk->sk_state == SMC_CLOSED) goto out; + + if (sk->sk_state == SMC_PEERFINCLOSEWAIT) { + rc = 0; + goto out; + } + if (smc->use_fallback) { rc = smc->clcsock->ops->splice_read(smc->clcsock, ppos, pipe, len, flags); } else { - rc = -EOPNOTSUPP; + if (*ppos) { + rc = -ESPIPE; + goto out; + } + if (flags & SPLICE_F_NONBLOCK) + flags = MSG_DONTWAIT; + else + flags = 0; + rc = smc_rx_recvmsg(smc, NULL, pipe, len, flags); } out: release_sock(sk); + return rc; } diff --git a/net/smc/smc.h b/net/smc/smc.h index e4829a2f46ba..ec209cd48d42 100644 --- a/net/smc/smc.h +++ b/net/smc/smc.h @@ -164,6 +164,9 @@ struct smc_connection { atomic_t bytes_to_rcv; /* arrived data, * not yet received */ + atomic_t splice_pending; /* number of spliced bytes + * pending processing + */ #ifndef KERNEL_HAS_ATOMIC64 spinlock_t acurs_lock; /* protect cursors */ #endif @@ -180,6 +183,10 @@ struct smc_sock { /* smc sock container */ struct list_head accept_q; /* sockets to be accepted */ spinlock_t accept_q_lock; /* protects accept_q */ bool use_fallback; /* fallback to tcp */ + int sockopt_defer_accept; + /* sockopt TCP_DEFER_ACCEPT + * value + */ u8 wait_close_tx_prepared : 1; /* shutdown wr or close * started, waiting for unsent diff --git a/net/smc/smc_cdc.c b/net/smc/smc_cdc.c index b42395d24cba..42ad57365eca 100644 --- a/net/smc/smc_cdc.c +++ b/net/smc/smc_cdc.c @@ -82,7 +82,7 @@ static inline void smc_cdc_add_pending_send(struct smc_connection *conn, sizeof(struct smc_cdc_msg) > SMC_WR_BUF_SIZE, "must increase SMC_WR_BUF_SIZE to at least sizeof(struct smc_cdc_msg)"); BUILD_BUG_ON_MSG( - offsetof(struct smc_cdc_msg, reserved) > SMC_WR_TX_SIZE, + sizeof(struct smc_cdc_msg) != SMC_WR_TX_SIZE, "must adapt SMC_WR_TX_SIZE to sizeof(struct smc_cdc_msg); if not all smc_wr upper layer protocols use the same message size any more, must start to set link->wr_tx_sges[i].length on each individual smc_wr_tx_send()"); BUILD_BUG_ON_MSG( sizeof(struct smc_cdc_tx_pend) > SMC_WR_TX_PEND_PRIV_SIZE, diff --git a/net/smc/smc_cdc.h b/net/smc/smc_cdc.h index ab240b37ad11..d2012fd22100 100644 --- a/net/smc/smc_cdc.h +++ b/net/smc/smc_cdc.h @@ -48,7 +48,7 @@ struct smc_cdc_msg { struct smc_cdc_producer_flags prod_flags; struct smc_cdc_conn_state_flags conn_state_flags; u8 reserved[18]; -} __aligned(8); +} __packed; /* format defined in RFC7609 */ static inline bool smc_cdc_rxed_any_close(struct smc_connection *conn) { diff --git a/net/smc/smc_core.c b/net/smc/smc_core.c index d4bd01bb44e1..9c74844e2008 100644 --- a/net/smc/smc_core.c +++ b/net/smc/smc_core.c @@ -290,8 +290,8 @@ static void smc_buf_free(struct smc_buf_desc *buf_desc, struct smc_link *lnk, DMA_TO_DEVICE); } sg_free_table(&buf_desc->sgt[SMC_SINGLE_LINK]); - if (buf_desc->cpu_addr) - free_pages((unsigned long)buf_desc->cpu_addr, buf_desc->order); + if (buf_desc->pages) + __free_pages(buf_desc->pages, buf_desc->order); kfree(buf_desc); } @@ -326,6 +326,7 @@ static void smc_lgr_free_bufs(struct smc_link_group *lgr) /* remove a link group */ void smc_lgr_free(struct smc_link_group *lgr) { + smc_llc_link_flush(&lgr->lnk[SMC_SINGLE_LINK]); smc_lgr_free_bufs(lgr); smc_link_clear(&lgr->lnk[SMC_SINGLE_LINK]); kfree(lgr); @@ -348,6 +349,7 @@ void smc_lgr_terminate(struct smc_link_group *lgr) struct rb_node *node; smc_lgr_forget(lgr); + smc_llc_link_inactive(&lgr->lnk[SMC_SINGLE_LINK]); write_lock_bh(&lgr->conns_lock); node = rb_first(&lgr->conns_all); @@ -374,7 +376,8 @@ void smc_lgr_terminate(struct smc_link_group *lgr) static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id) { struct dst_entry *dst = sk_dst_get(clcsock->sk); - int rc = 0; + struct net_device *ndev; + int i, nest_lvl, rc = 0; *vlan_id = 0; if (!dst) { @@ -386,8 +389,27 @@ static int smc_vlan_by_tcpsk(struct socket *clcsock, unsigned short *vlan_id) goto out_rel; } - if (is_vlan_dev(dst->dev)) - *vlan_id = vlan_dev_vlan_id(dst->dev); + ndev = dst->dev; + if (is_vlan_dev(ndev)) { + *vlan_id = vlan_dev_vlan_id(ndev); + goto out_rel; + } + + rtnl_lock(); + nest_lvl = dev_get_nest_level(ndev); + for (i = 0; i < nest_lvl; i++) { + struct list_head *lower = &ndev->adj_list.lower; + + if (list_empty(lower)) + break; + lower = lower->next; + ndev = (struct net_device *)netdev_lower_get_next(ndev, &lower); + if (is_vlan_dev(ndev)) { + *vlan_id = vlan_dev_vlan_id(ndev); + break; + } + } + rtnl_unlock(); out_rel: dst_release(dst); @@ -544,16 +566,16 @@ static struct smc_buf_desc *smc_new_buf_create(struct smc_link_group *lgr, if (!buf_desc) return ERR_PTR(-ENOMEM); - buf_desc->cpu_addr = - (void *)__get_free_pages(GFP_KERNEL | __GFP_NOWARN | - __GFP_NOMEMALLOC | - __GFP_NORETRY | __GFP_ZERO, - get_order(bufsize)); - if (!buf_desc->cpu_addr) { + buf_desc->order = get_order(bufsize); + buf_desc->pages = alloc_pages(GFP_KERNEL | __GFP_NOWARN | + __GFP_NOMEMALLOC | __GFP_COMP | + __GFP_NORETRY | __GFP_ZERO, + buf_desc->order); + if (!buf_desc->pages) { kfree(buf_desc); return ERR_PTR(-EAGAIN); } - buf_desc->order = get_order(bufsize); + buf_desc->cpu_addr = (void *)page_address(buf_desc->pages); /* build the sg table from the pages */ lnk = &lgr->lnk[SMC_SINGLE_LINK]; diff --git a/net/smc/smc_core.h b/net/smc/smc_core.h index 5dfcb15d529f..fca8624e5e71 100644 --- a/net/smc/smc_core.h +++ b/net/smc/smc_core.h @@ -79,6 +79,7 @@ struct smc_link { dma_addr_t wr_rx_dma_addr; /* DMA address of wr_rx_bufs */ u64 wr_rx_id; /* seq # of last recv WR */ u32 wr_rx_cnt; /* number of WR recv buffers */ + unsigned long wr_rx_tstamp; /* jiffies when last buf rx */ struct ib_reg_wr wr_reg; /* WR register memory region */ wait_queue_head_t wr_reg_wait; /* wait for wr_reg result */ @@ -101,6 +102,9 @@ struct smc_link { int llc_confirm_resp_rc; /* rc from conf_resp msg */ struct completion llc_add; /* wait for rx of add link */ struct completion llc_add_resp; /* wait for rx of add link rsp*/ + struct delayed_work llc_testlink_wrk; /* testlink worker */ + struct completion llc_testlink_resp; /* wait for rx of testlink */ + int llc_testlink_time; /* testlink interval */ }; /* For now we just allow one parallel link per link group. The SMC protocol @@ -116,6 +120,7 @@ struct smc_link { struct smc_buf_desc { struct list_head list; void *cpu_addr; /* virtual address of buffer */ + struct page *pages; struct sg_table sgt[SMC_LINKS_PER_LGR_MAX];/* virtual buffer */ struct ib_mr *mr_rx[SMC_LINKS_PER_LGR_MAX]; /* for rmb only: memory region diff --git a/net/smc/smc_diag.c b/net/smc/smc_diag.c index 427b91c1c964..05dd7e6d314d 100644 --- a/net/smc/smc_diag.c +++ b/net/smc/smc_diag.c @@ -38,17 +38,27 @@ static void smc_diag_msg_common_fill(struct smc_diag_msg *r, struct sock *sk) { struct smc_sock *smc = smc_sk(sk); - r->diag_family = sk->sk_family; if (!smc->clcsock) return; r->id.idiag_sport = htons(smc->clcsock->sk->sk_num); r->id.idiag_dport = smc->clcsock->sk->sk_dport; r->id.idiag_if = smc->clcsock->sk->sk_bound_dev_if; sock_diag_save_cookie(sk, r->id.idiag_cookie); - memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); - memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); - r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; - r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; + if (sk->sk_protocol == SMCPROTO_SMC) { + r->diag_family = PF_INET; + memset(&r->id.idiag_src, 0, sizeof(r->id.idiag_src)); + memset(&r->id.idiag_dst, 0, sizeof(r->id.idiag_dst)); + r->id.idiag_src[0] = smc->clcsock->sk->sk_rcv_saddr; + r->id.idiag_dst[0] = smc->clcsock->sk->sk_daddr; +#if IS_ENABLED(CONFIG_IPV6) + } else if (sk->sk_protocol == SMCPROTO_SMC6) { + r->diag_family = PF_INET6; + memcpy(&r->id.idiag_src, &smc->clcsock->sk->sk_v6_rcv_saddr, + sizeof(smc->clcsock->sk->sk_v6_rcv_saddr)); + memcpy(&r->id.idiag_dst, &smc->clcsock->sk->sk_v6_daddr, + sizeof(smc->clcsock->sk->sk_v6_daddr)); +#endif + } } static int smc_diag_msg_attrs_fill(struct sock *sk, struct sk_buff *skb, @@ -153,7 +163,8 @@ errout: return -EMSGSIZE; } -static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +static int smc_diag_dump_proto(struct proto *prot, struct sk_buff *skb, + struct netlink_callback *cb) { struct net *net = sock_net(skb->sk); struct nlattr *bc = NULL; @@ -161,8 +172,8 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) struct sock *sk; int rc = 0; - read_lock(&smc_proto.h.smc_hash->lock); - head = &smc_proto.h.smc_hash->ht; + read_lock(&prot->h.smc_hash->lock); + head = &prot->h.smc_hash->ht; if (hlist_empty(head)) goto out; @@ -175,7 +186,17 @@ static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) } out: - read_unlock(&smc_proto.h.smc_hash->lock); + read_unlock(&prot->h.smc_hash->lock); + return rc; +} + +static int smc_diag_dump(struct sk_buff *skb, struct netlink_callback *cb) +{ + int rc = 0; + + rc = smc_diag_dump_proto(&smc_proto, skb, cb); + if (!rc) + rc = smc_diag_dump_proto(&smc_proto6, skb, cb); return rc; } diff --git a/net/smc/smc_llc.c b/net/smc/smc_llc.c index ea4b21981b4b..33b4d856f4c6 100644 --- a/net/smc/smc_llc.c +++ b/net/smc/smc_llc.c @@ -397,7 +397,8 @@ static void smc_llc_rx_test_link(struct smc_link *link, struct smc_llc_msg_test_link *llc) { if (llc->hd.flags & SMC_LLC_FLAG_RESP) { - /* unused as long as we don't send this type of msg */ + if (link->state == SMC_LNK_ACTIVE) + complete(&link->llc_testlink_resp); } else { smc_llc_send_test_link(link, llc->user_data, SMC_LLC_RESP); } @@ -502,6 +503,65 @@ static void smc_llc_rx_handler(struct ib_wc *wc, void *buf) } } +/***************************** worker ****************************************/ + +static void smc_llc_testlink_work(struct work_struct *work) +{ + struct smc_link *link = container_of(to_delayed_work(work), + struct smc_link, llc_testlink_wrk); + unsigned long next_interval; + struct smc_link_group *lgr; + unsigned long expire_time; + u8 user_data[16] = { 0 }; + int rc; + + lgr = container_of(link, struct smc_link_group, lnk[SMC_SINGLE_LINK]); + if (link->state != SMC_LNK_ACTIVE) + return; /* don't reschedule worker */ + expire_time = link->wr_rx_tstamp + link->llc_testlink_time; + if (time_is_after_jiffies(expire_time)) { + next_interval = expire_time - jiffies; + goto out; + } + reinit_completion(&link->llc_testlink_resp); + smc_llc_send_test_link(link, user_data, SMC_LLC_REQ); + /* receive TEST LINK response over RoCE fabric */ + rc = wait_for_completion_interruptible_timeout(&link->llc_testlink_resp, + SMC_LLC_WAIT_TIME); + if (rc <= 0) { + smc_lgr_terminate(lgr); + return; + } + next_interval = link->llc_testlink_time; +out: + schedule_delayed_work(&link->llc_testlink_wrk, next_interval); +} + +void smc_llc_link_active(struct smc_link *link, int testlink_time) +{ + init_completion(&link->llc_testlink_resp); + INIT_DELAYED_WORK(&link->llc_testlink_wrk, smc_llc_testlink_work); + link->state = SMC_LNK_ACTIVE; + if (testlink_time) { + link->llc_testlink_time = testlink_time * HZ; + schedule_delayed_work(&link->llc_testlink_wrk, + link->llc_testlink_time); + } +} + +/* called in tasklet context */ +void smc_llc_link_inactive(struct smc_link *link) +{ + link->state = SMC_LNK_INACTIVE; + cancel_delayed_work(&link->llc_testlink_wrk); +} + +/* called in worker context */ +void smc_llc_link_flush(struct smc_link *link) +{ + cancel_delayed_work_sync(&link->llc_testlink_wrk); +} + /***************************** init, exit, misc ******************************/ static struct smc_wr_rx_handler smc_llc_rx_handlers[] = { diff --git a/net/smc/smc_llc.h b/net/smc/smc_llc.h index e4a7d5e234d5..d6e42116485e 100644 --- a/net/smc/smc_llc.h +++ b/net/smc/smc_llc.h @@ -44,6 +44,9 @@ int smc_llc_send_delete_link(struct smc_link *link, enum smc_llc_reqresp reqresp); int smc_llc_send_test_link(struct smc_link *lnk, u8 user_data[16], enum smc_llc_reqresp reqresp); +void smc_llc_link_active(struct smc_link *link, int testlink_time); +void smc_llc_link_inactive(struct smc_link *link); +void smc_llc_link_flush(struct smc_link *link); int smc_llc_init(void) __init; #endif /* SMC_LLC_H */ diff --git a/net/smc/smc_rx.c b/net/smc/smc_rx.c index eff4e0d0bb31..ed45569289f5 100644 --- a/net/smc/smc_rx.c +++ b/net/smc/smc_rx.c @@ -22,11 +22,10 @@ #include "smc_tx.h" /* smc_tx_consumer_update() */ #include "smc_rx.h" -/* callback implementation for sk.sk_data_ready() - * to wakeup rcvbuf consumers that blocked with smc_rx_wait_data(). +/* callback implementation to wakeup consumers blocked with smc_rx_wait(). * indirectly called by smc_cdc_msg_recv_action(). */ -static void smc_rx_data_ready(struct sock *sk) +static void smc_rx_wake_up(struct sock *sk) { struct socket_wq *wq; @@ -44,28 +43,140 @@ static void smc_rx_data_ready(struct sock *sk) rcu_read_unlock(); } +/* Update consumer cursor + * @conn connection to update + * @cons consumer cursor + * @len number of Bytes consumed + */ +static void smc_rx_update_consumer(struct smc_connection *conn, + union smc_host_cursor cons, size_t len) +{ + smc_curs_add(conn->rmbe_size, &cons, len); + smc_curs_write(&conn->local_tx_ctrl.cons, smc_curs_read(&cons, conn), + conn); + /* send consumer cursor update if required */ + /* similar to advertising new TCP rcv_wnd if required */ + smc_tx_consumer_update(conn); +} + +struct smc_spd_priv { + struct smc_sock *smc; + size_t len; +}; + +static void smc_rx_pipe_buf_release(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + struct smc_spd_priv *priv = (struct smc_spd_priv *)buf->private; + struct smc_sock *smc = priv->smc; + struct smc_connection *conn; + union smc_host_cursor cons; + struct sock *sk = &smc->sk; + + if (sk->sk_state == SMC_CLOSED || + sk->sk_state == SMC_PEERFINCLOSEWAIT || + sk->sk_state == SMC_APPFINCLOSEWAIT) + goto out; + conn = &smc->conn; + lock_sock(sk); + smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn), + conn); + smc_rx_update_consumer(conn, cons, priv->len); + release_sock(sk); + if (atomic_sub_and_test(priv->len, &conn->splice_pending)) + smc_rx_wake_up(sk); +out: + kfree(priv); + put_page(buf->page); + sock_put(sk); +} + +static int smc_rx_pipe_buf_nosteal(struct pipe_inode_info *pipe, + struct pipe_buffer *buf) +{ + return 1; +} + +static const struct pipe_buf_operations smc_pipe_ops = { + .can_merge = 0, + .confirm = generic_pipe_buf_confirm, + .release = smc_rx_pipe_buf_release, + .steal = smc_rx_pipe_buf_nosteal, + .get = generic_pipe_buf_get +}; + +static void smc_rx_spd_release(struct splice_pipe_desc *spd, + unsigned int i) +{ + put_page(spd->pages[i]); +} + +static int smc_rx_splice(struct pipe_inode_info *pipe, char *src, size_t len, + struct smc_sock *smc) +{ + struct splice_pipe_desc spd; + struct partial_page partial; + struct smc_spd_priv *priv; + struct page *page; + int bytes; + + page = virt_to_page(smc->conn.rmb_desc->cpu_addr); + priv = kzalloc(sizeof(*priv), GFP_KERNEL); + if (!priv) + return -ENOMEM; + priv->len = len; + priv->smc = smc; + partial.offset = src - (char *)smc->conn.rmb_desc->cpu_addr; + partial.len = len; + partial.private = (unsigned long)priv; + + spd.nr_pages_max = 1; + spd.nr_pages = 1; + spd.pages = &page; + spd.partial = &partial; + spd.ops = &smc_pipe_ops; + spd.spd_release = smc_rx_spd_release; + + bytes = splice_to_pipe(pipe, &spd); + if (bytes > 0) { + sock_hold(&smc->sk); + get_page(smc->conn.rmb_desc->pages); + atomic_add(bytes, &smc->conn.splice_pending); + } + + return bytes; +} + +static int smc_rx_data_available_and_no_splice_pend(struct smc_connection *conn) +{ + return atomic_read(&conn->bytes_to_rcv) && + !atomic_read(&conn->splice_pending); +} + /* blocks rcvbuf consumer until >=len bytes available or timeout or interrupted * @smc smc socket * @timeo pointer to max seconds to wait, pointer to value 0 for no timeout + * @fcrit add'l criterion to evaluate as function pointer * Returns: * 1 if at least 1 byte available in rcvbuf or if socket error/shutdown. * 0 otherwise (nothing in rcvbuf nor timeout, e.g. interrupted). */ -static int smc_rx_wait_data(struct smc_sock *smc, long *timeo) +int smc_rx_wait(struct smc_sock *smc, long *timeo, + int (*fcrit)(struct smc_connection *conn)) { DEFINE_WAIT_FUNC(wait, woken_wake_function); struct smc_connection *conn = &smc->conn; struct sock *sk = &smc->sk; int rc; - if (atomic_read(&conn->bytes_to_rcv)) + if (fcrit(conn)) return 1; sk_set_bit(SOCKWQ_ASYNC_WAITDATA, sk); add_wait_queue(sk_sleep(sk), &wait); rc = sk_wait_event(sk, timeo, sk->sk_err || sk->sk_shutdown & RCV_SHUTDOWN || - atomic_read(&conn->bytes_to_rcv) || + fcrit(conn) || smc_cdc_rxed_any_close_or_senddone(conn), &wait); remove_wait_queue(sk_sleep(sk), &wait); @@ -73,19 +184,25 @@ static int smc_rx_wait_data(struct smc_sock *smc, long *timeo) return rc; } -/* rcvbuf consumer: main API called by socket layer. - * called under sk lock. +/* smc_rx_recvmsg - receive data from RMBE + * @msg: copy data to receive buffer + * @pipe: copy data to pipe if set - indicates splice() call + * + * rcvbuf consumer: main API called by socket layer. + * Called under sk lock. */ -int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, - int flags) +int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, + struct pipe_inode_info *pipe, size_t len, int flags) { size_t copylen, read_done = 0, read_remaining = len; size_t chunk_len, chunk_off, chunk_len_sum; struct smc_connection *conn = &smc->conn; + int (*func)(struct smc_connection *conn); union smc_host_cursor cons; int readable, chunk; char *rcvbuf_base; struct sock *sk; + int splbytes; long timeo; int target; /* Read at least these many bytes */ int rc; @@ -101,37 +218,32 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, timeo = sock_rcvtimeo(sk, flags & MSG_DONTWAIT); target = sock_rcvlowat(sk, flags & MSG_WAITALL, len); - msg->msg_namelen = 0; /* we currently use 1 RMBE per RMB, so RMBE == RMB base addr */ rcvbuf_base = conn->rmb_desc->cpu_addr; do { /* while (read_remaining) */ - if (read_done >= target) + if (read_done >= target || (pipe && read_done)) break; if (atomic_read(&conn->bytes_to_rcv)) goto copy; + if (sk->sk_shutdown & RCV_SHUTDOWN || + smc_cdc_rxed_any_close_or_senddone(conn) || + conn->local_tx_ctrl.conn_state_flags.peer_conn_abort) + break; + if (read_done) { if (sk->sk_err || sk->sk_state == SMC_CLOSED || - sk->sk_shutdown & RCV_SHUTDOWN || !timeo || - signal_pending(current) || - smc_cdc_rxed_any_close_or_senddone(conn) || - conn->local_tx_ctrl.conn_state_flags. - peer_conn_abort) + signal_pending(current)) break; } else { if (sk->sk_err) { read_done = sock_error(sk); break; } - if (sk->sk_shutdown & RCV_SHUTDOWN || - smc_cdc_rxed_any_close_or_senddone(conn) || - conn->local_tx_ctrl.conn_state_flags. - peer_conn_abort) - break; if (sk->sk_state == SMC_CLOSED) { if (!sock_flag(sk, SOCK_DONE)) { /* This occurs when user tries to read @@ -150,20 +262,33 @@ int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, return -EAGAIN; } - if (!atomic_read(&conn->bytes_to_rcv)) { - smc_rx_wait_data(smc, &timeo); + if (!smc_rx_data_available(conn)) { + smc_rx_wait(smc, &timeo, smc_rx_data_available); continue; } copy: /* initialize variables for 1st iteration of subsequent loop */ - /* could be just 1 byte, even after smc_rx_wait_data above */ + /* could be just 1 byte, even after waiting on data above */ readable = atomic_read(&conn->bytes_to_rcv); + splbytes = atomic_read(&conn->splice_pending); + if (!readable || (msg && splbytes)) { + if (splbytes) + func = smc_rx_data_available_and_no_splice_pend; + else + func = smc_rx_data_available; + smc_rx_wait(smc, &timeo, func); + continue; + } + /* not more than what user space asked for */ copylen = min_t(size_t, read_remaining, readable); smc_curs_write(&cons, smc_curs_read(&conn->local_tx_ctrl.cons, conn), conn); + /* subsequent splice() calls pick up where previous left */ + if (splbytes) + smc_curs_add(conn->rmbe_size, &cons, splbytes); /* determine chunks where to read from rcvbuf */ /* either unwrapped case, or 1st chunk of wrapped case */ chunk_len = min_t(size_t, @@ -173,9 +298,16 @@ copy: smc_rmb_sync_sg_for_cpu(conn); for (chunk = 0; chunk < 2; chunk++) { if (!(flags & MSG_TRUNC)) { - rc = memcpy_to_msg(msg, rcvbuf_base + chunk_off, - chunk_len); - if (rc) { + if (msg) { + rc = memcpy_to_msg(msg, rcvbuf_base + + chunk_off, + chunk_len); + } else { + rc = smc_rx_splice(pipe, rcvbuf_base + + chunk_off, chunk_len, + smc); + } + if (rc < 0) { if (!read_done) read_done = -EFAULT; smc_rmb_sync_sg_for_device(conn); @@ -196,18 +328,13 @@ copy: /* update cursors */ if (!(flags & MSG_PEEK)) { - smc_curs_add(conn->rmbe_size, &cons, copylen); /* increased in recv tasklet smc_cdc_msg_rcv() */ smp_mb__before_atomic(); atomic_sub(copylen, &conn->bytes_to_rcv); /* guarantee 0 <= bytes_to_rcv <= rmbe_size */ smp_mb__after_atomic(); - smc_curs_write(&conn->local_tx_ctrl.cons, - smc_curs_read(&cons, conn), - conn); - /* send consumer cursor update if required */ - /* similar to advertising new TCP rcv_wnd if required */ - smc_tx_consumer_update(conn); + if (msg) + smc_rx_update_consumer(conn, cons, copylen); } } while (read_remaining); out: @@ -217,5 +344,6 @@ out: /* Initialize receive properties on connection establishment. NB: not __init! */ void smc_rx_init(struct smc_sock *smc) { - smc->sk.sk_data_ready = smc_rx_data_ready; + smc->sk.sk_data_ready = smc_rx_wake_up; + atomic_set(&smc->conn.splice_pending, 0); } diff --git a/net/smc/smc_rx.h b/net/smc/smc_rx.h index 3a32b59bf06c..db823c97d824 100644 --- a/net/smc/smc_rx.h +++ b/net/smc/smc_rx.h @@ -18,7 +18,14 @@ #include "smc.h" void smc_rx_init(struct smc_sock *smc); -int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, size_t len, - int flags); + +int smc_rx_recvmsg(struct smc_sock *smc, struct msghdr *msg, + struct pipe_inode_info *pipe, size_t len, int flags); +int smc_rx_wait(struct smc_sock *smc, long *timeo, + int (*fcrit)(struct smc_connection *conn)); +static inline int smc_rx_data_available(struct smc_connection *conn) +{ + return atomic_read(&conn->bytes_to_rcv); +} #endif /* SMC_RX_H */ diff --git a/net/smc/smc_tx.c b/net/smc/smc_tx.c index 72f004c9c9b1..58dfe0bd9d60 100644 --- a/net/smc/smc_tx.c +++ b/net/smc/smc_tx.c @@ -19,6 +19,7 @@ #include <linux/sched/signal.h> #include <net/sock.h> +#include <net/tcp.h> #include "smc.h" #include "smc_wr.h" @@ -26,6 +27,7 @@ #include "smc_tx.h" #define SMC_TX_WORK_DELAY HZ +#define SMC_TX_CORK_DELAY (HZ >> 2) /* 250 ms */ /***************************** sndbuf producer *******************************/ @@ -115,6 +117,13 @@ static int smc_tx_wait_memory(struct smc_sock *smc, int flags) return rc; } +static bool smc_tx_is_corked(struct smc_sock *smc) +{ + struct tcp_sock *tp = tcp_sk(smc->clcsock->sk); + + return (tp->nonagle & TCP_NAGLE_CORK) ? true : false; +} + /* sndbuf producer: main API called by socket layer. * called under sock lock. */ @@ -209,7 +218,16 @@ int smc_tx_sendmsg(struct smc_sock *smc, struct msghdr *msg, size_t len) /* since we just produced more new data into sndbuf, * trigger sndbuf consumer: RDMA write into peer RMBE and CDC */ - smc_tx_sndbuf_nonempty(conn); + if ((msg->msg_flags & MSG_MORE || smc_tx_is_corked(smc)) && + (atomic_read(&conn->sndbuf_space) > + (conn->sndbuf_size >> 1))) + /* for a corked socket defer the RDMA writes if there + * is still sufficient sndbuf_space available + */ + schedule_delayed_work(&conn->tx_work, + SMC_TX_CORK_DELAY); + else + smc_tx_sndbuf_nonempty(conn); } /* while (msg_data_left(msg)) */ return send_done; @@ -409,8 +427,8 @@ int smc_tx_sndbuf_nonempty(struct smc_connection *conn) } rc = 0; if (conn->alert_token_local) /* connection healthy */ - schedule_delayed_work(&conn->tx_work, - SMC_TX_WORK_DELAY); + mod_delayed_work(system_wq, &conn->tx_work, + SMC_TX_WORK_DELAY); } goto out_unlock; } diff --git a/net/smc/smc_wr.c b/net/smc/smc_wr.c index 1b8af23e6e2b..cc7c1bb60fe8 100644 --- a/net/smc/smc_wr.c +++ b/net/smc/smc_wr.c @@ -376,6 +376,7 @@ static inline void smc_wr_rx_process_cqes(struct ib_wc wc[], int num) for (i = 0; i < num; i++) { link = wc[i].qp->qp_context; if (wc[i].status == IB_WC_SUCCESS) { + link->wr_rx_tstamp = jiffies; smc_wr_rx_demultiplex(&wc[i]); smc_wr_rx_post(link); /* refill WR RX */ } else { diff --git a/net/tipc/bearer.c b/net/tipc/bearer.c index f7d47c89d658..2dfb492a7c94 100644 --- a/net/tipc/bearer.c +++ b/net/tipc/bearer.c @@ -697,6 +697,9 @@ static int __tipc_nl_add_bearer(struct tipc_nl_msg *msg, goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, bearer->window)) goto prop_msg_full; + if (bearer->media->type_id == TIPC_MEDIA_TYPE_UDP) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, bearer->mtu)) + goto prop_msg_full; nla_nest_end(msg->skb, prop); @@ -979,12 +982,23 @@ int __tipc_nl_bearer_set(struct sk_buff *skb, struct genl_info *info) if (props[TIPC_NLA_PROP_TOL]) { b->tolerance = nla_get_u32(props[TIPC_NLA_PROP_TOL]); - tipc_node_apply_tolerance(net, b); + tipc_node_apply_property(net, b, TIPC_NLA_PROP_TOL); } if (props[TIPC_NLA_PROP_PRIO]) b->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) b->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + if (props[TIPC_NLA_PROP_MTU]) { + if (b->media->type_id != TIPC_MEDIA_TYPE_UDP) + return -EINVAL; +#ifdef CONFIG_TIPC_MEDIA_UDP + if (tipc_udp_mtu_bad(nla_get_u32 + (props[TIPC_NLA_PROP_MTU]))) + return -EINVAL; + b->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); + tipc_node_apply_property(net, b, TIPC_NLA_PROP_MTU); +#endif + } } return 0; @@ -1029,6 +1043,9 @@ static int __tipc_nl_add_media(struct tipc_nl_msg *msg, goto prop_msg_full; if (nla_put_u32(msg->skb, TIPC_NLA_PROP_WIN, media->window)) goto prop_msg_full; + if (media->type_id == TIPC_MEDIA_TYPE_UDP) + if (nla_put_u32(msg->skb, TIPC_NLA_PROP_MTU, media->mtu)) + goto prop_msg_full; nla_nest_end(msg->skb, prop); nla_nest_end(msg->skb, attrs); @@ -1158,6 +1175,16 @@ int __tipc_nl_media_set(struct sk_buff *skb, struct genl_info *info) m->priority = nla_get_u32(props[TIPC_NLA_PROP_PRIO]); if (props[TIPC_NLA_PROP_WIN]) m->window = nla_get_u32(props[TIPC_NLA_PROP_WIN]); + if (props[TIPC_NLA_PROP_MTU]) { + if (m->type_id != TIPC_MEDIA_TYPE_UDP) + return -EINVAL; +#ifdef CONFIG_TIPC_MEDIA_UDP + if (tipc_udp_mtu_bad(nla_get_u32 + (props[TIPC_NLA_PROP_MTU]))) + return -EINVAL; + m->mtu = nla_get_u32(props[TIPC_NLA_PROP_MTU]); +#endif + } } return 0; diff --git a/net/tipc/bearer.h b/net/tipc/bearer.h index 6efcee63a381..394290cbbb1d 100644 --- a/net/tipc/bearer.h +++ b/net/tipc/bearer.h @@ -94,6 +94,8 @@ struct tipc_bearer; * @priority: default link (and bearer) priority * @tolerance: default time (in ms) before declaring link failure * @window: default window (in packets) before declaring link congestion + * @mtu: max packet size bearer can support for media type not dependent on + * underlying device MTU * @type_id: TIPC media identifier * @hwaddr_len: TIPC media address len * @name: media name @@ -118,6 +120,7 @@ struct tipc_media { u32 priority; u32 tolerance; u32 window; + u32 mtu; u32 type_id; u32 hwaddr_len; char name[TIPC_MAX_MEDIA_NAME]; diff --git a/net/tipc/name_table.c b/net/tipc/name_table.c index dd1c4fa2eb78..bebe88cae07b 100644 --- a/net/tipc/name_table.c +++ b/net/tipc/name_table.c @@ -136,12 +136,12 @@ static struct tipc_service *tipc_service_create(u32 type, struct hlist_head *hd) } /** - * tipc_service_find_range - find service range matching a service instance + * tipc_service_first_range - find first service range in tree matching instance * * Very time-critical, so binary search through range rb tree */ -static struct service_range *tipc_service_find_range(struct tipc_service *sc, - u32 instance) +static struct service_range *tipc_service_first_range(struct tipc_service *sc, + u32 instance) { struct rb_node *n = sc->ranges.rb_node; struct service_range *sr; @@ -158,6 +158,30 @@ static struct service_range *tipc_service_find_range(struct tipc_service *sc, return NULL; } +/* tipc_service_find_range - find service range matching publication parameters + */ +static struct service_range *tipc_service_find_range(struct tipc_service *sc, + u32 lower, u32 upper) +{ + struct rb_node *n = sc->ranges.rb_node; + struct service_range *sr; + + sr = tipc_service_first_range(sc, lower); + if (!sr) + return NULL; + + /* Look for exact match */ + for (n = &sr->tree_node; n; n = rb_next(n)) { + sr = container_of(n, struct service_range, tree_node); + if (sr->upper == upper) + break; + } + if (!n || sr->lower != lower || sr->upper != upper) + return NULL; + + return sr; +} + static struct service_range *tipc_service_create_range(struct tipc_service *sc, u32 lower, u32 upper) { @@ -238,54 +262,19 @@ err: /** * tipc_service_remove_publ - remove a publication from a service */ -static struct publication *tipc_service_remove_publ(struct net *net, - struct tipc_service *sc, - u32 lower, u32 upper, - u32 node, u32 key, - struct service_range **rng) +static struct publication *tipc_service_remove_publ(struct service_range *sr, + u32 node, u32 key) { - struct tipc_subscription *sub, *tmp; - struct service_range *sr; struct publication *p; - bool found = false; - bool last = false; - struct rb_node *n; - - sr = tipc_service_find_range(sc, lower); - if (!sr) - return NULL; - /* Find exact matching service range */ - for (n = &sr->tree_node; n; n = rb_next(n)) { - sr = container_of(n, struct service_range, tree_node); - if (sr->upper == upper) - break; - } - if (!n || sr->lower != lower || sr->upper != upper) - return NULL; - - /* Find publication, if it exists */ list_for_each_entry(p, &sr->all_publ, all_publ) { if (p->key != key || (node && node != p->node)) continue; - found = true; - break; + list_del(&p->all_publ); + list_del(&p->local_publ); + return p; } - if (!found) - return NULL; - - list_del(&p->all_publ); - list_del(&p->local_publ); - if (list_empty(&sr->all_publ)) - last = true; - - /* Notify any waiting subscriptions */ - list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { - tipc_sub_report_overlap(sub, p->lower, p->upper, TIPC_WITHDRAWN, - p->port, p->node, p->scope, last); - } - *rng = sr; - return p; + return NULL; } /** @@ -376,17 +365,31 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, u32 node, u32 key) { struct tipc_service *sc = tipc_service_find(net, type); + struct tipc_subscription *sub, *tmp; struct service_range *sr = NULL; struct publication *p = NULL; + bool last; if (!sc) return NULL; spin_lock_bh(&sc->lock); - p = tipc_service_remove_publ(net, sc, lower, upper, node, key, &sr); + sr = tipc_service_find_range(sc, lower, upper); + if (!sr) + goto exit; + p = tipc_service_remove_publ(sr, node, key); + if (!p) + goto exit; + + /* Notify any waiting subscriptions */ + last = list_empty(&sr->all_publ); + list_for_each_entry_safe(sub, tmp, &sc->subscriptions, service_list) { + tipc_sub_report_overlap(sub, lower, upper, TIPC_WITHDRAWN, + p->port, node, p->scope, last); + } /* Remove service range item if this was its last publication */ - if (sr && list_empty(&sr->all_publ)) { + if (list_empty(&sr->all_publ)) { rb_erase(&sr->tree_node, &sc->ranges); kfree(sr); } @@ -396,6 +399,7 @@ struct publication *tipc_nametbl_remove_publ(struct net *net, u32 type, hlist_del_init_rcu(&sc->service_list); kfree_rcu(sc, rcu); } +exit: spin_unlock_bh(&sc->lock); return p; } @@ -437,7 +441,7 @@ u32 tipc_nametbl_translate(struct net *net, u32 type, u32 instance, u32 *dnode) goto not_found; spin_lock_bh(&sc->lock); - sr = tipc_service_find_range(sc, instance); + sr = tipc_service_first_range(sc, instance); if (unlikely(!sr)) goto no_match; @@ -484,7 +488,7 @@ bool tipc_nametbl_lookup(struct net *net, u32 type, u32 instance, u32 scope, spin_lock_bh(&sc->lock); - sr = tipc_service_find_range(sc, instance); + sr = tipc_service_first_range(sc, instance); if (!sr) goto no_match; @@ -756,8 +760,7 @@ static void tipc_service_delete(struct net *net, struct tipc_service *sc) spin_lock_bh(&sc->lock); rbtree_postorder_for_each_entry_safe(sr, tmpr, &sc->ranges, tree_node) { list_for_each_entry_safe(p, tmp, &sr->all_publ, all_publ) { - tipc_service_remove_publ(net, sc, p->lower, p->upper, - p->node, p->key, &sr); + tipc_service_remove_publ(sr, p->node, p->key); kfree_rcu(p, rcu); } rb_erase(&sr->tree_node, &sc->ranges); diff --git a/net/tipc/node.c b/net/tipc/node.c index f29549de9245..6a44eb812baf 100644 --- a/net/tipc/node.c +++ b/net/tipc/node.c @@ -195,6 +195,27 @@ int tipc_node_get_mtu(struct net *net, u32 addr, u32 sel) return mtu; } +bool tipc_node_get_id(struct net *net, u32 addr, u8 *id) +{ + u8 *own_id = tipc_own_id(net); + struct tipc_node *n; + + if (!own_id) + return true; + + if (addr == tipc_own_addr(net)) { + memcpy(id, own_id, TIPC_NODEID_LEN); + return true; + } + n = tipc_node_find(net, addr); + if (!n) + return false; + + memcpy(id, &n->peer_id, TIPC_NODEID_LEN); + tipc_node_put(n); + return true; +} + u16 tipc_node_get_capabilities(struct net *net, u32 addr) { struct tipc_node *n; @@ -1681,7 +1702,8 @@ discard: kfree_skb(skb); } -void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b) +void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, + int prop) { struct tipc_net *tn = tipc_net(net); int bearer_id = b->identity; @@ -1696,8 +1718,13 @@ void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b) list_for_each_entry_rcu(n, &tn->node_list, list) { tipc_node_write_lock(n); e = &n->links[bearer_id]; - if (e->link) - tipc_link_set_tolerance(e->link, b->tolerance, &xmitq); + if (e->link) { + if (prop == TIPC_NLA_PROP_TOL) + tipc_link_set_tolerance(e->link, b->tolerance, + &xmitq); + else if (prop == TIPC_NLA_PROP_MTU) + tipc_link_set_mtu(e->link, b->mtu); + } tipc_node_write_unlock(n); tipc_bearer_xmit(net, bearer_id, &xmitq, &e->maddr); } diff --git a/net/tipc/node.h b/net/tipc/node.h index f24b83500df1..846c8f240872 100644 --- a/net/tipc/node.h +++ b/net/tipc/node.h @@ -60,6 +60,7 @@ enum { #define INVALID_BEARER_ID -1 void tipc_node_stop(struct net *net); +bool tipc_node_get_id(struct net *net, u32 addr, u8 *id); u32 tipc_node_try_addr(struct net *net, u8 *id, u32 addr); void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128, struct tipc_bearer *bearer, @@ -67,7 +68,7 @@ void tipc_node_check_dest(struct net *net, u32 onode, u8 *peer_id128, struct tipc_media_addr *maddr, bool *respond, bool *dupl_addr); void tipc_node_delete_links(struct net *net, int bearer_id); -void tipc_node_apply_tolerance(struct net *net, struct tipc_bearer *b); +void tipc_node_apply_property(struct net *net, struct tipc_bearer *b, int prop); int tipc_node_get_linkname(struct net *net, u32 bearer_id, u32 node, char *linkname, size_t len); int tipc_node_xmit(struct net *net, struct sk_buff_head *list, u32 dnode, diff --git a/net/tipc/socket.c b/net/tipc/socket.c index 6be21575503a..930852c54d7a 100644 --- a/net/tipc/socket.c +++ b/net/tipc/socket.c @@ -2974,7 +2974,8 @@ static int tipc_getsockopt(struct socket *sock, int lvl, int opt, static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) { - struct sock *sk = sock->sk; + struct net *net = sock_net(sock->sk); + struct tipc_sioc_nodeid_req nr = {0}; struct tipc_sioc_ln_req lnr; void __user *argp = (void __user *)arg; @@ -2982,7 +2983,7 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) case SIOCGETLINKNAME: if (copy_from_user(&lnr, argp, sizeof(lnr))) return -EFAULT; - if (!tipc_node_get_linkname(sock_net(sk), + if (!tipc_node_get_linkname(net, lnr.bearer_id & 0xffff, lnr.peer, lnr.linkname, TIPC_MAX_LINK_NAME)) { if (copy_to_user(argp, &lnr, sizeof(lnr))) @@ -2990,6 +2991,14 @@ static int tipc_ioctl(struct socket *sock, unsigned int cmd, unsigned long arg) return 0; } return -EADDRNOTAVAIL; + case SIOCGETNODEID: + if (copy_from_user(&nr, argp, sizeof(nr))) + return -EFAULT; + if (!tipc_node_get_id(net, nr.peer, nr.node_id)) + return -EADDRNOTAVAIL; + if (copy_to_user(argp, &nr, sizeof(nr))) + return -EFAULT; + return 0; default: return -ENOIOCTLCMD; } diff --git a/net/tipc/udp_media.c b/net/tipc/udp_media.c index e7d91f5d5cae..9783101bc4a9 100644 --- a/net/tipc/udp_media.c +++ b/net/tipc/udp_media.c @@ -713,8 +713,7 @@ static int tipc_udp_enable(struct net *net, struct tipc_bearer *b, err = -EINVAL; goto err; } - b->mtu = dev->mtu - sizeof(struct iphdr) - - sizeof(struct udphdr); + b->mtu = b->media->mtu; #if IS_ENABLED(CONFIG_IPV6) } else if (local.proto == htons(ETH_P_IPV6)) { udp_conf.family = AF_INET6; @@ -803,6 +802,7 @@ struct tipc_media udp_media_info = { .priority = TIPC_DEF_LINK_PRI, .tolerance = TIPC_DEF_LINK_TOL, .window = TIPC_DEF_LINK_WIN, + .mtu = TIPC_DEF_LINK_UDP_MTU, .type_id = TIPC_MEDIA_TYPE_UDP, .hwaddr_len = 0, .name = "udp" diff --git a/net/tipc/udp_media.h b/net/tipc/udp_media.h index 281bbae87726..e7455cc73e16 100644 --- a/net/tipc/udp_media.h +++ b/net/tipc/udp_media.h @@ -38,9 +38,23 @@ #ifndef _TIPC_UDP_MEDIA_H #define _TIPC_UDP_MEDIA_H +#include <linux/ip.h> +#include <linux/udp.h> + int tipc_udp_nl_bearer_add(struct tipc_bearer *b, struct nlattr *attr); int tipc_udp_nl_add_bearer_data(struct tipc_nl_msg *msg, struct tipc_bearer *b); int tipc_udp_nl_dump_remoteip(struct sk_buff *skb, struct netlink_callback *cb); +/* check if configured MTU is too low for tipc headers */ +static inline bool tipc_udp_mtu_bad(u32 mtu) +{ + if (mtu >= (TIPC_MIN_BEARER_MTU + sizeof(struct iphdr) + + sizeof(struct udphdr))) + return false; + + pr_warn("MTU too low for tipc bearer\n"); + return true; +} + #endif #endif diff --git a/net/tls/Kconfig b/net/tls/Kconfig index 89b8745a986f..73f05ece53d0 100644 --- a/net/tls/Kconfig +++ b/net/tls/Kconfig @@ -14,3 +14,13 @@ config TLS encryption handling of the TLS protocol to be done in-kernel. If unsure, say N. + +config TLS_DEVICE + bool "Transport Layer Security HW offload" + depends on TLS + select SOCK_VALIDATE_XMIT + default n + help + Enable kernel support for HW offload of the TLS protocol. + + If unsure, say N. diff --git a/net/tls/Makefile b/net/tls/Makefile index a930fd1c4f7b..4d6b728a67d0 100644 --- a/net/tls/Makefile +++ b/net/tls/Makefile @@ -5,3 +5,5 @@ obj-$(CONFIG_TLS) += tls.o tls-y := tls_main.o tls_sw.o + +tls-$(CONFIG_TLS_DEVICE) += tls_device.o tls_device_fallback.o diff --git a/net/tls/tls_device.c b/net/tls/tls_device.c new file mode 100644 index 000000000000..a7a8f8e20ff3 --- /dev/null +++ b/net/tls/tls_device.c @@ -0,0 +1,766 @@ +/* Copyright (c) 2018, Mellanox Technologies All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <crypto/aead.h> +#include <linux/highmem.h> +#include <linux/module.h> +#include <linux/netdevice.h> +#include <net/dst.h> +#include <net/inet_connection_sock.h> +#include <net/tcp.h> +#include <net/tls.h> + +/* device_offload_lock is used to synchronize tls_dev_add + * against NETDEV_DOWN notifications. + */ +static DECLARE_RWSEM(device_offload_lock); + +static void tls_device_gc_task(struct work_struct *work); + +static DECLARE_WORK(tls_device_gc_work, tls_device_gc_task); +static LIST_HEAD(tls_device_gc_list); +static LIST_HEAD(tls_device_list); +static DEFINE_SPINLOCK(tls_device_lock); + +static void tls_device_free_ctx(struct tls_context *ctx) +{ + struct tls_offload_context *offload_ctx = tls_offload_ctx(ctx); + + kfree(offload_ctx); + kfree(ctx); +} + +static void tls_device_gc_task(struct work_struct *work) +{ + struct tls_context *ctx, *tmp; + unsigned long flags; + LIST_HEAD(gc_list); + + spin_lock_irqsave(&tls_device_lock, flags); + list_splice_init(&tls_device_gc_list, &gc_list); + spin_unlock_irqrestore(&tls_device_lock, flags); + + list_for_each_entry_safe(ctx, tmp, &gc_list, list) { + struct net_device *netdev = ctx->netdev; + + if (netdev) { + netdev->tlsdev_ops->tls_dev_del(netdev, ctx, + TLS_OFFLOAD_CTX_DIR_TX); + dev_put(netdev); + } + + list_del(&ctx->list); + tls_device_free_ctx(ctx); + } +} + +static void tls_device_queue_ctx_destruction(struct tls_context *ctx) +{ + unsigned long flags; + + spin_lock_irqsave(&tls_device_lock, flags); + list_move_tail(&ctx->list, &tls_device_gc_list); + + /* schedule_work inside the spinlock + * to make sure tls_device_down waits for that work. + */ + schedule_work(&tls_device_gc_work); + + spin_unlock_irqrestore(&tls_device_lock, flags); +} + +/* We assume that the socket is already connected */ +static struct net_device *get_netdev_for_sock(struct sock *sk) +{ + struct dst_entry *dst = sk_dst_get(sk); + struct net_device *netdev = NULL; + + if (likely(dst)) { + netdev = dst->dev; + dev_hold(netdev); + } + + dst_release(dst); + + return netdev; +} + +static void destroy_record(struct tls_record_info *record) +{ + int nr_frags = record->num_frags; + skb_frag_t *frag; + + while (nr_frags-- > 0) { + frag = &record->frags[nr_frags]; + __skb_frag_unref(frag); + } + kfree(record); +} + +static void delete_all_records(struct tls_offload_context *offload_ctx) +{ + struct tls_record_info *info, *temp; + + list_for_each_entry_safe(info, temp, &offload_ctx->records_list, list) { + list_del(&info->list); + destroy_record(info); + } + + offload_ctx->retransmit_hint = NULL; +} + +static void tls_icsk_clean_acked(struct sock *sk, u32 acked_seq) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_record_info *info, *temp; + struct tls_offload_context *ctx; + u64 deleted_records = 0; + unsigned long flags; + + if (!tls_ctx) + return; + + ctx = tls_offload_ctx(tls_ctx); + + spin_lock_irqsave(&ctx->lock, flags); + info = ctx->retransmit_hint; + if (info && !before(acked_seq, info->end_seq)) { + ctx->retransmit_hint = NULL; + list_del(&info->list); + destroy_record(info); + deleted_records++; + } + + list_for_each_entry_safe(info, temp, &ctx->records_list, list) { + if (before(acked_seq, info->end_seq)) + break; + list_del(&info->list); + + destroy_record(info); + deleted_records++; + } + + ctx->unacked_record_sn += deleted_records; + spin_unlock_irqrestore(&ctx->lock, flags); +} + +/* At this point, there should be no references on this + * socket and no in-flight SKBs associated with this + * socket, so it is safe to free all the resources. + */ +void tls_device_sk_destruct(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + + if (ctx->open_record) + destroy_record(ctx->open_record); + + delete_all_records(ctx); + crypto_free_aead(ctx->aead_send); + ctx->sk_destruct(sk); + clean_acked_data_disable(inet_csk(sk)); + + if (refcount_dec_and_test(&tls_ctx->refcount)) + tls_device_queue_ctx_destruction(tls_ctx); +} +EXPORT_SYMBOL(tls_device_sk_destruct); + +static void tls_append_frag(struct tls_record_info *record, + struct page_frag *pfrag, + int size) +{ + skb_frag_t *frag; + + frag = &record->frags[record->num_frags - 1]; + if (frag->page.p == pfrag->page && + frag->page_offset + frag->size == pfrag->offset) { + frag->size += size; + } else { + ++frag; + frag->page.p = pfrag->page; + frag->page_offset = pfrag->offset; + frag->size = size; + ++record->num_frags; + get_page(pfrag->page); + } + + pfrag->offset += size; + record->len += size; +} + +static int tls_push_record(struct sock *sk, + struct tls_context *ctx, + struct tls_offload_context *offload_ctx, + struct tls_record_info *record, + struct page_frag *pfrag, + int flags, + unsigned char record_type) +{ + struct tcp_sock *tp = tcp_sk(sk); + struct page_frag dummy_tag_frag; + skb_frag_t *frag; + int i; + + /* fill prepend */ + frag = &record->frags[0]; + tls_fill_prepend(ctx, + skb_frag_address(frag), + record->len - ctx->tx.prepend_size, + record_type); + + /* HW doesn't care about the data in the tag, because it fills it. */ + dummy_tag_frag.page = skb_frag_page(frag); + dummy_tag_frag.offset = 0; + + tls_append_frag(record, &dummy_tag_frag, ctx->tx.tag_size); + record->end_seq = tp->write_seq + record->len; + spin_lock_irq(&offload_ctx->lock); + list_add_tail(&record->list, &offload_ctx->records_list); + spin_unlock_irq(&offload_ctx->lock); + offload_ctx->open_record = NULL; + set_bit(TLS_PENDING_CLOSED_RECORD, &ctx->flags); + tls_advance_record_sn(sk, &ctx->tx); + + for (i = 0; i < record->num_frags; i++) { + frag = &record->frags[i]; + sg_unmark_end(&offload_ctx->sg_tx_data[i]); + sg_set_page(&offload_ctx->sg_tx_data[i], skb_frag_page(frag), + frag->size, frag->page_offset); + sk_mem_charge(sk, frag->size); + get_page(skb_frag_page(frag)); + } + sg_mark_end(&offload_ctx->sg_tx_data[record->num_frags - 1]); + + /* all ready, send */ + return tls_push_sg(sk, ctx, offload_ctx->sg_tx_data, 0, flags); +} + +static int tls_create_new_record(struct tls_offload_context *offload_ctx, + struct page_frag *pfrag, + size_t prepend_size) +{ + struct tls_record_info *record; + skb_frag_t *frag; + + record = kmalloc(sizeof(*record), GFP_KERNEL); + if (!record) + return -ENOMEM; + + frag = &record->frags[0]; + __skb_frag_set_page(frag, pfrag->page); + frag->page_offset = pfrag->offset; + skb_frag_size_set(frag, prepend_size); + + get_page(pfrag->page); + pfrag->offset += prepend_size; + + record->num_frags = 1; + record->len = prepend_size; + offload_ctx->open_record = record; + return 0; +} + +static int tls_do_allocation(struct sock *sk, + struct tls_offload_context *offload_ctx, + struct page_frag *pfrag, + size_t prepend_size) +{ + int ret; + + if (!offload_ctx->open_record) { + if (unlikely(!skb_page_frag_refill(prepend_size, pfrag, + sk->sk_allocation))) { + sk->sk_prot->enter_memory_pressure(sk); + sk_stream_moderate_sndbuf(sk); + return -ENOMEM; + } + + ret = tls_create_new_record(offload_ctx, pfrag, prepend_size); + if (ret) + return ret; + + if (pfrag->size > pfrag->offset) + return 0; + } + + if (!sk_page_frag_refill(sk, pfrag)) + return -ENOMEM; + + return 0; +} + +static int tls_push_data(struct sock *sk, + struct iov_iter *msg_iter, + size_t size, int flags, + unsigned char record_type) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + int tls_push_record_flags = flags | MSG_SENDPAGE_NOTLAST; + int more = flags & (MSG_SENDPAGE_NOTLAST | MSG_MORE); + struct tls_record_info *record = ctx->open_record; + struct page_frag *pfrag; + size_t orig_size = size; + u32 max_open_record_len; + int copy, rc = 0; + bool done = false; + long timeo; + + if (flags & + ~(MSG_MORE | MSG_DONTWAIT | MSG_NOSIGNAL | MSG_SENDPAGE_NOTLAST)) + return -ENOTSUPP; + + if (sk->sk_err) + return -sk->sk_err; + + timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); + rc = tls_complete_pending_work(sk, tls_ctx, flags, &timeo); + if (rc < 0) + return rc; + + pfrag = sk_page_frag(sk); + + /* TLS_HEADER_SIZE is not counted as part of the TLS record, and + * we need to leave room for an authentication tag. + */ + max_open_record_len = TLS_MAX_PAYLOAD_SIZE + + tls_ctx->tx.prepend_size; + do { + rc = tls_do_allocation(sk, ctx, pfrag, + tls_ctx->tx.prepend_size); + if (rc) { + rc = sk_stream_wait_memory(sk, &timeo); + if (!rc) + continue; + + record = ctx->open_record; + if (!record) + break; +handle_error: + if (record_type != TLS_RECORD_TYPE_DATA) { + /* avoid sending partial + * record with type != + * application_data + */ + size = orig_size; + destroy_record(record); + ctx->open_record = NULL; + } else if (record->len > tls_ctx->tx.prepend_size) { + goto last_record; + } + + break; + } + + record = ctx->open_record; + copy = min_t(size_t, size, (pfrag->size - pfrag->offset)); + copy = min_t(size_t, copy, (max_open_record_len - record->len)); + + if (copy_from_iter_nocache(page_address(pfrag->page) + + pfrag->offset, + copy, msg_iter) != copy) { + rc = -EFAULT; + goto handle_error; + } + tls_append_frag(record, pfrag, copy); + + size -= copy; + if (!size) { +last_record: + tls_push_record_flags = flags; + if (more) { + tls_ctx->pending_open_record_frags = + record->num_frags; + break; + } + + done = true; + } + + if (done || record->len >= max_open_record_len || + (record->num_frags >= MAX_SKB_FRAGS - 1)) { + rc = tls_push_record(sk, + tls_ctx, + ctx, + record, + pfrag, + tls_push_record_flags, + record_type); + if (rc < 0) + break; + } + } while (!done); + + if (orig_size - size > 0) + rc = orig_size - size; + + return rc; +} + +int tls_device_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) +{ + unsigned char record_type = TLS_RECORD_TYPE_DATA; + int rc; + + lock_sock(sk); + + if (unlikely(msg->msg_controllen)) { + rc = tls_proccess_cmsg(sk, msg, &record_type); + if (rc) + goto out; + } + + rc = tls_push_data(sk, &msg->msg_iter, size, + msg->msg_flags, record_type); + +out: + release_sock(sk); + return rc; +} + +int tls_device_sendpage(struct sock *sk, struct page *page, + int offset, size_t size, int flags) +{ + struct iov_iter msg_iter; + char *kaddr = kmap(page); + struct kvec iov; + int rc; + + if (flags & MSG_SENDPAGE_NOTLAST) + flags |= MSG_MORE; + + lock_sock(sk); + + if (flags & MSG_OOB) { + rc = -ENOTSUPP; + goto out; + } + + iov.iov_base = kaddr + offset; + iov.iov_len = size; + iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, &iov, 1, size); + rc = tls_push_data(sk, &msg_iter, size, + flags, TLS_RECORD_TYPE_DATA); + kunmap(page); + +out: + release_sock(sk); + return rc; +} + +struct tls_record_info *tls_get_record(struct tls_offload_context *context, + u32 seq, u64 *p_record_sn) +{ + u64 record_sn = context->hint_record_sn; + struct tls_record_info *info; + + info = context->retransmit_hint; + if (!info || + before(seq, info->end_seq - info->len)) { + /* if retransmit_hint is irrelevant start + * from the beggining of the list + */ + info = list_first_entry(&context->records_list, + struct tls_record_info, list); + record_sn = context->unacked_record_sn; + } + + list_for_each_entry_from(info, &context->records_list, list) { + if (before(seq, info->end_seq)) { + if (!context->retransmit_hint || + after(info->end_seq, + context->retransmit_hint->end_seq)) { + context->hint_record_sn = record_sn; + context->retransmit_hint = info; + } + *p_record_sn = record_sn; + return info; + } + record_sn++; + } + + return NULL; +} +EXPORT_SYMBOL(tls_get_record); + +static int tls_device_push_pending_record(struct sock *sk, int flags) +{ + struct iov_iter msg_iter; + + iov_iter_kvec(&msg_iter, WRITE | ITER_KVEC, NULL, 0, 0); + return tls_push_data(sk, &msg_iter, 0, flags, TLS_RECORD_TYPE_DATA); +} + +int tls_set_device_offload(struct sock *sk, struct tls_context *ctx) +{ + u16 nonce_size, tag_size, iv_size, rec_seq_size; + struct tls_record_info *start_marker_record; + struct tls_offload_context *offload_ctx; + struct tls_crypto_info *crypto_info; + struct net_device *netdev; + char *iv, *rec_seq; + struct sk_buff *skb; + int rc = -EINVAL; + __be64 rcd_sn; + + if (!ctx) + goto out; + + if (ctx->priv_ctx_tx) { + rc = -EEXIST; + goto out; + } + + start_marker_record = kmalloc(sizeof(*start_marker_record), GFP_KERNEL); + if (!start_marker_record) { + rc = -ENOMEM; + goto out; + } + + offload_ctx = kzalloc(TLS_OFFLOAD_CONTEXT_SIZE, GFP_KERNEL); + if (!offload_ctx) { + rc = -ENOMEM; + goto free_marker_record; + } + + crypto_info = &ctx->crypto_send; + switch (crypto_info->cipher_type) { + case TLS_CIPHER_AES_GCM_128: + nonce_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + tag_size = TLS_CIPHER_AES_GCM_128_TAG_SIZE; + iv_size = TLS_CIPHER_AES_GCM_128_IV_SIZE; + iv = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->iv; + rec_seq_size = TLS_CIPHER_AES_GCM_128_REC_SEQ_SIZE; + rec_seq = + ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->rec_seq; + break; + default: + rc = -EINVAL; + goto free_offload_ctx; + } + + ctx->tx.prepend_size = TLS_HEADER_SIZE + nonce_size; + ctx->tx.tag_size = tag_size; + ctx->tx.overhead_size = ctx->tx.prepend_size + ctx->tx.tag_size; + ctx->tx.iv_size = iv_size; + ctx->tx.iv = kmalloc(iv_size + TLS_CIPHER_AES_GCM_128_SALT_SIZE, + GFP_KERNEL); + if (!ctx->tx.iv) { + rc = -ENOMEM; + goto free_offload_ctx; + } + + memcpy(ctx->tx.iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, iv, iv_size); + + ctx->tx.rec_seq_size = rec_seq_size; + ctx->tx.rec_seq = kmalloc(rec_seq_size, GFP_KERNEL); + if (!ctx->tx.rec_seq) { + rc = -ENOMEM; + goto free_iv; + } + memcpy(ctx->tx.rec_seq, rec_seq, rec_seq_size); + + rc = tls_sw_fallback_init(sk, offload_ctx, crypto_info); + if (rc) + goto free_rec_seq; + + /* start at rec_seq - 1 to account for the start marker record */ + memcpy(&rcd_sn, ctx->tx.rec_seq, sizeof(rcd_sn)); + offload_ctx->unacked_record_sn = be64_to_cpu(rcd_sn) - 1; + + start_marker_record->end_seq = tcp_sk(sk)->write_seq; + start_marker_record->len = 0; + start_marker_record->num_frags = 0; + + INIT_LIST_HEAD(&offload_ctx->records_list); + list_add_tail(&start_marker_record->list, &offload_ctx->records_list); + spin_lock_init(&offload_ctx->lock); + sg_init_table(offload_ctx->sg_tx_data, + ARRAY_SIZE(offload_ctx->sg_tx_data)); + + clean_acked_data_enable(inet_csk(sk), &tls_icsk_clean_acked); + ctx->push_pending_record = tls_device_push_pending_record; + offload_ctx->sk_destruct = sk->sk_destruct; + + /* TLS offload is greatly simplified if we don't send + * SKBs where only part of the payload needs to be encrypted. + * So mark the last skb in the write queue as end of record. + */ + skb = tcp_write_queue_tail(sk); + if (skb) + TCP_SKB_CB(skb)->eor = 1; + + refcount_set(&ctx->refcount, 1); + + /* We support starting offload on multiple sockets + * concurrently, so we only need a read lock here. + * This lock must precede get_netdev_for_sock to prevent races between + * NETDEV_DOWN and setsockopt. + */ + down_read(&device_offload_lock); + netdev = get_netdev_for_sock(sk); + if (!netdev) { + pr_err_ratelimited("%s: netdev not found\n", __func__); + rc = -EINVAL; + goto release_lock; + } + + if (!(netdev->features & NETIF_F_HW_TLS_TX)) { + rc = -ENOTSUPP; + goto release_netdev; + } + + /* Avoid offloading if the device is down + * We don't want to offload new flows after + * the NETDEV_DOWN event + */ + if (!(netdev->flags & IFF_UP)) { + rc = -EINVAL; + goto release_netdev; + } + + ctx->priv_ctx_tx = offload_ctx; + rc = netdev->tlsdev_ops->tls_dev_add(netdev, sk, TLS_OFFLOAD_CTX_DIR_TX, + &ctx->crypto_send, + tcp_sk(sk)->write_seq); + if (rc) + goto release_netdev; + + ctx->netdev = netdev; + + spin_lock_irq(&tls_device_lock); + list_add_tail(&ctx->list, &tls_device_list); + spin_unlock_irq(&tls_device_lock); + + sk->sk_validate_xmit_skb = tls_validate_xmit_skb; + /* following this assignment tls_is_sk_tx_device_offloaded + * will return true and the context might be accessed + * by the netdev's xmit function. + */ + smp_store_release(&sk->sk_destruct, + &tls_device_sk_destruct); + up_read(&device_offload_lock); + goto out; + +release_netdev: + dev_put(netdev); +release_lock: + up_read(&device_offload_lock); + clean_acked_data_disable(inet_csk(sk)); + crypto_free_aead(offload_ctx->aead_send); +free_rec_seq: + kfree(ctx->tx.rec_seq); +free_iv: + kfree(ctx->tx.iv); +free_offload_ctx: + kfree(offload_ctx); + ctx->priv_ctx_tx = NULL; +free_marker_record: + kfree(start_marker_record); +out: + return rc; +} + +static int tls_device_down(struct net_device *netdev) +{ + struct tls_context *ctx, *tmp; + unsigned long flags; + LIST_HEAD(list); + + /* Request a write lock to block new offload attempts */ + down_write(&device_offload_lock); + + spin_lock_irqsave(&tls_device_lock, flags); + list_for_each_entry_safe(ctx, tmp, &tls_device_list, list) { + if (ctx->netdev != netdev || + !refcount_inc_not_zero(&ctx->refcount)) + continue; + + list_move(&ctx->list, &list); + } + spin_unlock_irqrestore(&tls_device_lock, flags); + + list_for_each_entry_safe(ctx, tmp, &list, list) { + netdev->tlsdev_ops->tls_dev_del(netdev, ctx, + TLS_OFFLOAD_CTX_DIR_TX); + ctx->netdev = NULL; + dev_put(netdev); + list_del_init(&ctx->list); + + if (refcount_dec_and_test(&ctx->refcount)) + tls_device_free_ctx(ctx); + } + + up_write(&device_offload_lock); + + flush_work(&tls_device_gc_work); + + return NOTIFY_DONE; +} + +static int tls_dev_event(struct notifier_block *this, unsigned long event, + void *ptr) +{ + struct net_device *dev = netdev_notifier_info_to_dev(ptr); + + if (!(dev->features & NETIF_F_HW_TLS_TX)) + return NOTIFY_DONE; + + switch (event) { + case NETDEV_REGISTER: + case NETDEV_FEAT_CHANGE: + if (dev->tlsdev_ops && + dev->tlsdev_ops->tls_dev_add && + dev->tlsdev_ops->tls_dev_del) + return NOTIFY_DONE; + else + return NOTIFY_BAD; + case NETDEV_DOWN: + return tls_device_down(dev); + } + return NOTIFY_DONE; +} + +static struct notifier_block tls_dev_notifier = { + .notifier_call = tls_dev_event, +}; + +void __init tls_device_init(void) +{ + register_netdevice_notifier(&tls_dev_notifier); +} + +void __exit tls_device_cleanup(void) +{ + unregister_netdevice_notifier(&tls_dev_notifier); + flush_work(&tls_device_gc_work); +} diff --git a/net/tls/tls_device_fallback.c b/net/tls/tls_device_fallback.c new file mode 100644 index 000000000000..748914abdb60 --- /dev/null +++ b/net/tls/tls_device_fallback.c @@ -0,0 +1,450 @@ +/* Copyright (c) 2018, Mellanox Technologies All rights reserved. + * + * This software is available to you under a choice of one of two + * licenses. You may choose to be licensed under the terms of the GNU + * General Public License (GPL) Version 2, available from the file + * COPYING in the main directory of this source tree, or the + * OpenIB.org BSD license below: + * + * Redistribution and use in source and binary forms, with or + * without modification, are permitted provided that the following + * conditions are met: + * + * - Redistributions of source code must retain the above + * copyright notice, this list of conditions and the following + * disclaimer. + * + * - Redistributions in binary form must reproduce the above + * copyright notice, this list of conditions and the following + * disclaimer in the documentation and/or other materials + * provided with the distribution. + * + * THE SOFTWARE IS PROVIDED "AS IS", WITHOUT WARRANTY OF ANY KIND, + * EXPRESS OR IMPLIED, INCLUDING BUT NOT LIMITED TO THE WARRANTIES OF + * MERCHANTABILITY, FITNESS FOR A PARTICULAR PURPOSE AND + * NONINFRINGEMENT. IN NO EVENT SHALL THE AUTHORS OR COPYRIGHT HOLDERS + * BE LIABLE FOR ANY CLAIM, DAMAGES OR OTHER LIABILITY, WHETHER IN AN + * ACTION OF CONTRACT, TORT OR OTHERWISE, ARISING FROM, OUT OF OR IN + * CONNECTION WITH THE SOFTWARE OR THE USE OR OTHER DEALINGS IN THE + * SOFTWARE. + */ + +#include <net/tls.h> +#include <crypto/aead.h> +#include <crypto/scatterwalk.h> +#include <net/ip6_checksum.h> + +static void chain_to_walk(struct scatterlist *sg, struct scatter_walk *walk) +{ + struct scatterlist *src = walk->sg; + int diff = walk->offset - src->offset; + + sg_set_page(sg, sg_page(src), + src->length - diff, walk->offset); + + scatterwalk_crypto_chain(sg, sg_next(src), 0, 2); +} + +static int tls_enc_record(struct aead_request *aead_req, + struct crypto_aead *aead, char *aad, + char *iv, __be64 rcd_sn, + struct scatter_walk *in, + struct scatter_walk *out, int *in_len) +{ + unsigned char buf[TLS_HEADER_SIZE + TLS_CIPHER_AES_GCM_128_IV_SIZE]; + struct scatterlist sg_in[3]; + struct scatterlist sg_out[3]; + u16 len; + int rc; + + len = min_t(int, *in_len, ARRAY_SIZE(buf)); + + scatterwalk_copychunks(buf, in, len, 0); + scatterwalk_copychunks(buf, out, len, 1); + + *in_len -= len; + if (!*in_len) + return 0; + + scatterwalk_pagedone(in, 0, 1); + scatterwalk_pagedone(out, 1, 1); + + len = buf[4] | (buf[3] << 8); + len -= TLS_CIPHER_AES_GCM_128_IV_SIZE; + + tls_make_aad(aad, len - TLS_CIPHER_AES_GCM_128_TAG_SIZE, + (char *)&rcd_sn, sizeof(rcd_sn), buf[0]); + + memcpy(iv + TLS_CIPHER_AES_GCM_128_SALT_SIZE, buf + TLS_HEADER_SIZE, + TLS_CIPHER_AES_GCM_128_IV_SIZE); + + sg_init_table(sg_in, ARRAY_SIZE(sg_in)); + sg_init_table(sg_out, ARRAY_SIZE(sg_out)); + sg_set_buf(sg_in, aad, TLS_AAD_SPACE_SIZE); + sg_set_buf(sg_out, aad, TLS_AAD_SPACE_SIZE); + chain_to_walk(sg_in + 1, in); + chain_to_walk(sg_out + 1, out); + + *in_len -= len; + if (*in_len < 0) { + *in_len += TLS_CIPHER_AES_GCM_128_TAG_SIZE; + /* the input buffer doesn't contain the entire record. + * trim len accordingly. The resulting authentication tag + * will contain garbage, but we don't care, so we won't + * include any of it in the output skb + * Note that we assume the output buffer length + * is larger then input buffer length + tag size + */ + if (*in_len < 0) + len += *in_len; + + *in_len = 0; + } + + if (*in_len) { + scatterwalk_copychunks(NULL, in, len, 2); + scatterwalk_pagedone(in, 0, 1); + scatterwalk_copychunks(NULL, out, len, 2); + scatterwalk_pagedone(out, 1, 1); + } + + len -= TLS_CIPHER_AES_GCM_128_TAG_SIZE; + aead_request_set_crypt(aead_req, sg_in, sg_out, len, iv); + + rc = crypto_aead_encrypt(aead_req); + + return rc; +} + +static void tls_init_aead_request(struct aead_request *aead_req, + struct crypto_aead *aead) +{ + aead_request_set_tfm(aead_req, aead); + aead_request_set_ad(aead_req, TLS_AAD_SPACE_SIZE); +} + +static struct aead_request *tls_alloc_aead_request(struct crypto_aead *aead, + gfp_t flags) +{ + unsigned int req_size = sizeof(struct aead_request) + + crypto_aead_reqsize(aead); + struct aead_request *aead_req; + + aead_req = kzalloc(req_size, flags); + if (aead_req) + tls_init_aead_request(aead_req, aead); + return aead_req; +} + +static int tls_enc_records(struct aead_request *aead_req, + struct crypto_aead *aead, struct scatterlist *sg_in, + struct scatterlist *sg_out, char *aad, char *iv, + u64 rcd_sn, int len) +{ + struct scatter_walk out, in; + int rc; + + scatterwalk_start(&in, sg_in); + scatterwalk_start(&out, sg_out); + + do { + rc = tls_enc_record(aead_req, aead, aad, iv, + cpu_to_be64(rcd_sn), &in, &out, &len); + rcd_sn++; + + } while (rc == 0 && len); + + scatterwalk_done(&in, 0, 0); + scatterwalk_done(&out, 1, 0); + + return rc; +} + +/* Can't use icsk->icsk_af_ops->send_check here because the ip addresses + * might have been changed by NAT. + */ +static void update_chksum(struct sk_buff *skb, int headln) +{ + struct tcphdr *th = tcp_hdr(skb); + int datalen = skb->len - headln; + const struct ipv6hdr *ipv6h; + const struct iphdr *iph; + + /* We only changed the payload so if we are using partial we don't + * need to update anything. + */ + if (likely(skb->ip_summed == CHECKSUM_PARTIAL)) + return; + + skb->ip_summed = CHECKSUM_PARTIAL; + skb->csum_start = skb_transport_header(skb) - skb->head; + skb->csum_offset = offsetof(struct tcphdr, check); + + if (skb->sk->sk_family == AF_INET6) { + ipv6h = ipv6_hdr(skb); + th->check = ~csum_ipv6_magic(&ipv6h->saddr, &ipv6h->daddr, + datalen, IPPROTO_TCP, 0); + } else { + iph = ip_hdr(skb); + th->check = ~csum_tcpudp_magic(iph->saddr, iph->daddr, datalen, + IPPROTO_TCP, 0); + } +} + +static void complete_skb(struct sk_buff *nskb, struct sk_buff *skb, int headln) +{ + skb_copy_header(nskb, skb); + + skb_put(nskb, skb->len); + memcpy(nskb->data, skb->data, headln); + update_chksum(nskb, headln); + + nskb->destructor = skb->destructor; + nskb->sk = skb->sk; + skb->destructor = NULL; + skb->sk = NULL; + refcount_add(nskb->truesize - skb->truesize, + &nskb->sk->sk_wmem_alloc); +} + +/* This function may be called after the user socket is already + * closed so make sure we don't use anything freed during + * tls_sk_proto_close here + */ + +static int fill_sg_in(struct scatterlist *sg_in, + struct sk_buff *skb, + struct tls_offload_context *ctx, + u64 *rcd_sn, + s32 *sync_size, + int *resync_sgs) +{ + int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + int payload_len = skb->len - tcp_payload_offset; + u32 tcp_seq = ntohl(tcp_hdr(skb)->seq); + struct tls_record_info *record; + unsigned long flags; + int remaining; + int i; + + spin_lock_irqsave(&ctx->lock, flags); + record = tls_get_record(ctx, tcp_seq, rcd_sn); + if (!record) { + spin_unlock_irqrestore(&ctx->lock, flags); + WARN(1, "Record not found for seq %u\n", tcp_seq); + return -EINVAL; + } + + *sync_size = tcp_seq - tls_record_start_seq(record); + if (*sync_size < 0) { + int is_start_marker = tls_record_is_start_marker(record); + + spin_unlock_irqrestore(&ctx->lock, flags); + /* This should only occur if the relevant record was + * already acked. In that case it should be ok + * to drop the packet and avoid retransmission. + * + * There is a corner case where the packet contains + * both an acked and a non-acked record. + * We currently don't handle that case and rely + * on TCP to retranmit a packet that doesn't contain + * already acked payload. + */ + if (!is_start_marker) + *sync_size = 0; + return -EINVAL; + } + + remaining = *sync_size; + for (i = 0; remaining > 0; i++) { + skb_frag_t *frag = &record->frags[i]; + + __skb_frag_ref(frag); + sg_set_page(sg_in + i, skb_frag_page(frag), + skb_frag_size(frag), frag->page_offset); + + remaining -= skb_frag_size(frag); + + if (remaining < 0) + sg_in[i].length += remaining; + } + *resync_sgs = i; + + spin_unlock_irqrestore(&ctx->lock, flags); + if (skb_to_sgvec(skb, &sg_in[i], tcp_payload_offset, payload_len) < 0) + return -EINVAL; + + return 0; +} + +static void fill_sg_out(struct scatterlist sg_out[3], void *buf, + struct tls_context *tls_ctx, + struct sk_buff *nskb, + int tcp_payload_offset, + int payload_len, + int sync_size, + void *dummy_buf) +{ + sg_set_buf(&sg_out[0], dummy_buf, sync_size); + sg_set_buf(&sg_out[1], nskb->data + tcp_payload_offset, payload_len); + /* Add room for authentication tag produced by crypto */ + dummy_buf += sync_size; + sg_set_buf(&sg_out[2], dummy_buf, TLS_CIPHER_AES_GCM_128_TAG_SIZE); +} + +static struct sk_buff *tls_enc_skb(struct tls_context *tls_ctx, + struct scatterlist sg_out[3], + struct scatterlist *sg_in, + struct sk_buff *skb, + s32 sync_size, u64 rcd_sn) +{ + int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + int payload_len = skb->len - tcp_payload_offset; + void *buf, *iv, *aad, *dummy_buf; + struct aead_request *aead_req; + struct sk_buff *nskb = NULL; + int buf_len; + + aead_req = tls_alloc_aead_request(ctx->aead_send, GFP_ATOMIC); + if (!aead_req) + return NULL; + + buf_len = TLS_CIPHER_AES_GCM_128_SALT_SIZE + + TLS_CIPHER_AES_GCM_128_IV_SIZE + + TLS_AAD_SPACE_SIZE + + sync_size + + TLS_CIPHER_AES_GCM_128_TAG_SIZE; + buf = kmalloc(buf_len, GFP_ATOMIC); + if (!buf) + goto free_req; + + iv = buf; + memcpy(iv, tls_ctx->crypto_send_aes_gcm_128.salt, + TLS_CIPHER_AES_GCM_128_SALT_SIZE); + aad = buf + TLS_CIPHER_AES_GCM_128_SALT_SIZE + + TLS_CIPHER_AES_GCM_128_IV_SIZE; + dummy_buf = aad + TLS_AAD_SPACE_SIZE; + + nskb = alloc_skb(skb_headroom(skb) + skb->len, GFP_ATOMIC); + if (!nskb) + goto free_buf; + + skb_reserve(nskb, skb_headroom(skb)); + + fill_sg_out(sg_out, buf, tls_ctx, nskb, tcp_payload_offset, + payload_len, sync_size, dummy_buf); + + if (tls_enc_records(aead_req, ctx->aead_send, sg_in, sg_out, aad, iv, + rcd_sn, sync_size + payload_len) < 0) + goto free_nskb; + + complete_skb(nskb, skb, tcp_payload_offset); + + /* validate_xmit_skb_list assumes that if the skb wasn't segmented + * nskb->prev will point to the skb itself + */ + nskb->prev = nskb; + +free_buf: + kfree(buf); +free_req: + kfree(aead_req); + return nskb; +free_nskb: + kfree_skb(nskb); + nskb = NULL; + goto free_buf; +} + +static struct sk_buff *tls_sw_fallback(struct sock *sk, struct sk_buff *skb) +{ + int tcp_payload_offset = skb_transport_offset(skb) + tcp_hdrlen(skb); + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_offload_context *ctx = tls_offload_ctx(tls_ctx); + int payload_len = skb->len - tcp_payload_offset; + struct scatterlist *sg_in, sg_out[3]; + struct sk_buff *nskb = NULL; + int sg_in_max_elements; + int resync_sgs = 0; + s32 sync_size = 0; + u64 rcd_sn; + + /* worst case is: + * MAX_SKB_FRAGS in tls_record_info + * MAX_SKB_FRAGS + 1 in SKB head and frags. + */ + sg_in_max_elements = 2 * MAX_SKB_FRAGS + 1; + + if (!payload_len) + return skb; + + sg_in = kmalloc_array(sg_in_max_elements, sizeof(*sg_in), GFP_ATOMIC); + if (!sg_in) + goto free_orig; + + sg_init_table(sg_in, sg_in_max_elements); + sg_init_table(sg_out, ARRAY_SIZE(sg_out)); + + if (fill_sg_in(sg_in, skb, ctx, &rcd_sn, &sync_size, &resync_sgs)) { + /* bypass packets before kernel TLS socket option was set */ + if (sync_size < 0 && payload_len <= -sync_size) + nskb = skb_get(skb); + goto put_sg; + } + + nskb = tls_enc_skb(tls_ctx, sg_out, sg_in, skb, sync_size, rcd_sn); + +put_sg: + while (resync_sgs) + put_page(sg_page(&sg_in[--resync_sgs])); + kfree(sg_in); +free_orig: + kfree_skb(skb); + return nskb; +} + +struct sk_buff *tls_validate_xmit_skb(struct sock *sk, + struct net_device *dev, + struct sk_buff *skb) +{ + if (dev == tls_get_ctx(sk)->netdev) + return skb; + + return tls_sw_fallback(sk, skb); +} + +int tls_sw_fallback_init(struct sock *sk, + struct tls_offload_context *offload_ctx, + struct tls_crypto_info *crypto_info) +{ + const u8 *key; + int rc; + + offload_ctx->aead_send = + crypto_alloc_aead("gcm(aes)", 0, CRYPTO_ALG_ASYNC); + if (IS_ERR(offload_ctx->aead_send)) { + rc = PTR_ERR(offload_ctx->aead_send); + pr_err_ratelimited("crypto_alloc_aead failed rc=%d\n", rc); + offload_ctx->aead_send = NULL; + goto err_out; + } + + key = ((struct tls12_crypto_info_aes_gcm_128 *)crypto_info)->key; + + rc = crypto_aead_setkey(offload_ctx->aead_send, key, + TLS_CIPHER_AES_GCM_128_KEY_SIZE); + if (rc) + goto free_aead; + + rc = crypto_aead_setauthsize(offload_ctx->aead_send, + TLS_CIPHER_AES_GCM_128_TAG_SIZE); + if (rc) + goto free_aead; + + return 0; +free_aead: + crypto_free_aead(offload_ctx->aead_send); +err_out: + return rc; +} diff --git a/net/tls/tls_main.c b/net/tls/tls_main.c index 20cd93be6236..301f22430469 100644 --- a/net/tls/tls_main.c +++ b/net/tls/tls_main.c @@ -51,12 +51,12 @@ enum { TLSV6, TLS_NUM_PROTS, }; - enum { TLS_BASE, - TLS_SW_TX, - TLS_SW_RX, - TLS_SW_RXTX, + TLS_SW, +#ifdef CONFIG_TLS_DEVICE + TLS_HW, +#endif TLS_HW_RECORD, TLS_NUM_CONFIG, }; @@ -65,14 +65,14 @@ static struct proto *saved_tcpv6_prot; static DEFINE_MUTEX(tcpv6_prot_mutex); static LIST_HEAD(device_list); static DEFINE_MUTEX(device_mutex); -static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG]; +static struct proto tls_prots[TLS_NUM_PROTS][TLS_NUM_CONFIG][TLS_NUM_CONFIG]; static struct proto_ops tls_sw_proto_ops; -static inline void update_sk_prot(struct sock *sk, struct tls_context *ctx) +static void update_sk_prot(struct sock *sk, struct tls_context *ctx) { int ip_ver = sk->sk_family == AF_INET6 ? TLSV6 : TLSV4; - sk->sk_prot = &tls_prots[ip_ver][ctx->conf]; + sk->sk_prot = &tls_prots[ip_ver][ctx->tx_conf][ctx->rx_conf]; } int wait_on_pending_writer(struct sock *sk, long *timeo) @@ -254,7 +254,8 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) lock_sock(sk); sk_proto_close = ctx->sk_proto_close; - if (ctx->conf == TLS_BASE || ctx->conf == TLS_HW_RECORD) { + if ((ctx->tx_conf == TLS_HW_RECORD && ctx->rx_conf == TLS_HW_RECORD) || + (ctx->tx_conf == TLS_BASE && ctx->rx_conf == TLS_BASE)) { free_ctx = true; goto skip_tx_cleanup; } @@ -275,15 +276,26 @@ static void tls_sk_proto_close(struct sock *sk, long timeout) } } - kfree(ctx->tx.rec_seq); - kfree(ctx->tx.iv); - kfree(ctx->rx.rec_seq); - kfree(ctx->rx.iv); + /* We need these for tls_sw_fallback handling of other packets */ + if (ctx->tx_conf == TLS_SW) { + kfree(ctx->tx.rec_seq); + kfree(ctx->tx.iv); + tls_sw_free_resources_tx(sk); + } - if (ctx->conf == TLS_SW_TX || - ctx->conf == TLS_SW_RX || - ctx->conf == TLS_SW_RXTX) { - tls_sw_free_resources(sk); + if (ctx->rx_conf == TLS_SW) { + kfree(ctx->rx.rec_seq); + kfree(ctx->rx.iv); + tls_sw_free_resources_rx(sk); + } + +#ifdef CONFIG_TLS_DEVICE + if (ctx->tx_conf != TLS_HW) { +#else + { +#endif + kfree(ctx); + ctx = NULL; } skip_tx_cleanup: @@ -446,25 +458,29 @@ static int do_tls_setsockopt_conf(struct sock *sk, char __user *optval, goto err_crypto_info; } - /* currently SW is default, we will have ethtool in future */ if (tx) { - rc = tls_set_sw_offload(sk, ctx, 1); - if (ctx->conf == TLS_SW_RX) - conf = TLS_SW_RXTX; - else - conf = TLS_SW_TX; +#ifdef CONFIG_TLS_DEVICE + rc = tls_set_device_offload(sk, ctx); + conf = TLS_HW; + if (rc) { +#else + { +#endif + rc = tls_set_sw_offload(sk, ctx, 1); + conf = TLS_SW; + } } else { rc = tls_set_sw_offload(sk, ctx, 0); - if (ctx->conf == TLS_SW_TX) - conf = TLS_SW_RXTX; - else - conf = TLS_SW_RX; + conf = TLS_SW; } if (rc) goto err_crypto_info; - ctx->conf = conf; + if (tx) + ctx->tx_conf = conf; + else + ctx->rx_conf = conf; update_sk_prot(sk, ctx); if (tx) { ctx->sk_write_space = sk->sk_write_space; @@ -540,7 +556,8 @@ static int tls_hw_prot(struct sock *sk) ctx->hash = sk->sk_prot->hash; ctx->unhash = sk->sk_prot->unhash; ctx->sk_proto_close = sk->sk_prot->close; - ctx->conf = TLS_HW_RECORD; + ctx->rx_conf = TLS_HW_RECORD; + ctx->tx_conf = TLS_HW_RECORD; update_sk_prot(sk, ctx); rc = 1; break; @@ -584,29 +601,40 @@ static int tls_hw_hash(struct sock *sk) return err; } -static void build_protos(struct proto *prot, struct proto *base) +static void build_protos(struct proto prot[TLS_NUM_CONFIG][TLS_NUM_CONFIG], + struct proto *base) { - prot[TLS_BASE] = *base; - prot[TLS_BASE].setsockopt = tls_setsockopt; - prot[TLS_BASE].getsockopt = tls_getsockopt; - prot[TLS_BASE].close = tls_sk_proto_close; - - prot[TLS_SW_TX] = prot[TLS_BASE]; - prot[TLS_SW_TX].sendmsg = tls_sw_sendmsg; - prot[TLS_SW_TX].sendpage = tls_sw_sendpage; - - prot[TLS_SW_RX] = prot[TLS_BASE]; - prot[TLS_SW_RX].recvmsg = tls_sw_recvmsg; - prot[TLS_SW_RX].close = tls_sk_proto_close; - - prot[TLS_SW_RXTX] = prot[TLS_SW_TX]; - prot[TLS_SW_RXTX].recvmsg = tls_sw_recvmsg; - prot[TLS_SW_RXTX].close = tls_sk_proto_close; - - prot[TLS_HW_RECORD] = *base; - prot[TLS_HW_RECORD].hash = tls_hw_hash; - prot[TLS_HW_RECORD].unhash = tls_hw_unhash; - prot[TLS_HW_RECORD].close = tls_sk_proto_close; + prot[TLS_BASE][TLS_BASE] = *base; + prot[TLS_BASE][TLS_BASE].setsockopt = tls_setsockopt; + prot[TLS_BASE][TLS_BASE].getsockopt = tls_getsockopt; + prot[TLS_BASE][TLS_BASE].close = tls_sk_proto_close; + + prot[TLS_SW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; + prot[TLS_SW][TLS_BASE].sendmsg = tls_sw_sendmsg; + prot[TLS_SW][TLS_BASE].sendpage = tls_sw_sendpage; + + prot[TLS_BASE][TLS_SW] = prot[TLS_BASE][TLS_BASE]; + prot[TLS_BASE][TLS_SW].recvmsg = tls_sw_recvmsg; + prot[TLS_BASE][TLS_SW].close = tls_sk_proto_close; + + prot[TLS_SW][TLS_SW] = prot[TLS_SW][TLS_BASE]; + prot[TLS_SW][TLS_SW].recvmsg = tls_sw_recvmsg; + prot[TLS_SW][TLS_SW].close = tls_sk_proto_close; + +#ifdef CONFIG_TLS_DEVICE + prot[TLS_HW][TLS_BASE] = prot[TLS_BASE][TLS_BASE]; + prot[TLS_HW][TLS_BASE].sendmsg = tls_device_sendmsg; + prot[TLS_HW][TLS_BASE].sendpage = tls_device_sendpage; + + prot[TLS_HW][TLS_SW] = prot[TLS_BASE][TLS_SW]; + prot[TLS_HW][TLS_SW].sendmsg = tls_device_sendmsg; + prot[TLS_HW][TLS_SW].sendpage = tls_device_sendpage; +#endif + + prot[TLS_HW_RECORD][TLS_HW_RECORD] = *base; + prot[TLS_HW_RECORD][TLS_HW_RECORD].hash = tls_hw_hash; + prot[TLS_HW_RECORD][TLS_HW_RECORD].unhash = tls_hw_unhash; + prot[TLS_HW_RECORD][TLS_HW_RECORD].close = tls_sk_proto_close; } static int tls_init(struct sock *sk) @@ -637,7 +665,7 @@ static int tls_init(struct sock *sk) ctx->getsockopt = sk->sk_prot->getsockopt; ctx->sk_proto_close = sk->sk_prot->close; - /* Build IPv6 TLS whenever the address of tcpv6_prot changes */ + /* Build IPv6 TLS whenever the address of tcpv6 _prot changes */ if (ip_ver == TLSV6 && unlikely(sk->sk_prot != smp_load_acquire(&saved_tcpv6_prot))) { mutex_lock(&tcpv6_prot_mutex); @@ -648,7 +676,8 @@ static int tls_init(struct sock *sk) mutex_unlock(&tcpv6_prot_mutex); } - ctx->conf = TLS_BASE; + ctx->tx_conf = TLS_BASE; + ctx->rx_conf = TLS_BASE; update_sk_prot(sk, ctx); out: return rc; @@ -686,6 +715,9 @@ static int __init tls_register(void) tls_sw_proto_ops.poll = tls_sw_poll; tls_sw_proto_ops.splice_read = tls_sw_splice_read; +#ifdef CONFIG_TLS_DEVICE + tls_device_init(); +#endif tcp_register_ulp(&tcp_tls_ulp_ops); return 0; @@ -694,6 +726,9 @@ static int __init tls_register(void) static void __exit tls_unregister(void) { tcp_unregister_ulp(&tcp_tls_ulp_ops); +#ifdef CONFIG_TLS_DEVICE + tls_device_cleanup(); +#endif } module_init(tls_register); diff --git a/net/tls/tls_sw.c b/net/tls/tls_sw.c index 71e79597f940..5c3909c311f1 100644 --- a/net/tls/tls_sw.c +++ b/net/tls/tls_sw.c @@ -52,7 +52,7 @@ static int tls_do_decryption(struct sock *sk, gfp_t flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm = strp_msg(skb); struct aead_request *aead_req; @@ -122,7 +122,7 @@ out: static void trim_both_sgl(struct sock *sk, int target_size) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); trim_sg(sk, ctx->sg_plaintext_data, &ctx->sg_plaintext_num_elem, @@ -141,7 +141,7 @@ static void trim_both_sgl(struct sock *sk, int target_size) static int alloc_encrypted_sg(struct sock *sk, int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int rc = 0; rc = sk_alloc_sg(sk, len, @@ -155,7 +155,7 @@ static int alloc_encrypted_sg(struct sock *sk, int len) static int alloc_plaintext_sg(struct sock *sk, int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int rc = 0; rc = sk_alloc_sg(sk, len, ctx->sg_plaintext_data, 0, @@ -181,7 +181,7 @@ static void free_sg(struct sock *sk, struct scatterlist *sg, static void tls_free_both_sg(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); free_sg(sk, ctx->sg_encrypted_data, &ctx->sg_encrypted_num_elem, &ctx->sg_encrypted_size); @@ -191,7 +191,7 @@ static void tls_free_both_sg(struct sock *sk) } static int tls_do_encryption(struct tls_context *tls_ctx, - struct tls_sw_context *ctx, size_t data_len, + struct tls_sw_context_tx *ctx, size_t data_len, gfp_t flags) { unsigned int req_size = sizeof(struct aead_request) + @@ -227,7 +227,7 @@ static int tls_push_record(struct sock *sk, int flags, unsigned char record_type) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int rc; sg_mark_end(ctx->sg_plaintext_data + ctx->sg_plaintext_num_elem - 1); @@ -339,7 +339,7 @@ static int memcopy_from_iter(struct sock *sk, struct iov_iter *from, int bytes) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); struct scatterlist *sg = ctx->sg_plaintext_data; int copy, i, rc = 0; @@ -367,7 +367,7 @@ out: int tls_sw_sendmsg(struct sock *sk, struct msghdr *msg, size_t size) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int ret = 0; int required_size; long timeo = sock_sndtimeo(sk, msg->msg_flags & MSG_DONTWAIT); @@ -522,7 +522,7 @@ int tls_sw_sendpage(struct sock *sk, struct page *page, int offset, size_t size, int flags) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); int ret = 0; long timeo = sock_sndtimeo(sk, flags & MSG_DONTWAIT); bool eor; @@ -636,7 +636,7 @@ static struct sk_buff *tls_wait_data(struct sock *sk, int flags, long timeo, int *err) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct sk_buff *skb; DEFINE_WAIT_FUNC(wait, woken_wake_function); @@ -674,7 +674,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, struct scatterlist *sgout) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); char iv[TLS_CIPHER_AES_GCM_128_SALT_SIZE + MAX_IV_SIZE]; struct scatterlist sgin_arr[MAX_SKB_FRAGS + 2]; struct scatterlist *sgin = &sgin_arr[0]; @@ -693,8 +693,7 @@ static int decrypt_skb(struct sock *sk, struct sk_buff *skb, if (!sgout) { nsg = skb_cow_data(skb, 0, &unused) + 1; sgin = kmalloc_array(nsg, sizeof(*sgin), sk->sk_allocation); - if (!sgout) - sgout = sgin; + sgout = sgin; } sg_init_table(sgin, nsg); @@ -724,7 +723,7 @@ static bool tls_sw_advance_skb(struct sock *sk, struct sk_buff *skb, unsigned int len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm = strp_msg(skb); if (len < rxm->full_len) { @@ -750,7 +749,7 @@ int tls_sw_recvmsg(struct sock *sk, int *addr_len) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); unsigned char control; struct strp_msg *rxm; struct sk_buff *skb; @@ -870,7 +869,7 @@ ssize_t tls_sw_splice_read(struct socket *sock, loff_t *ppos, size_t len, unsigned int flags) { struct tls_context *tls_ctx = tls_get_ctx(sock->sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm = NULL; struct sock *sk = sock->sk; struct sk_buff *skb; @@ -923,7 +922,7 @@ unsigned int tls_sw_poll(struct file *file, struct socket *sock, unsigned int ret; struct sock *sk = sock->sk; struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); /* Grab POLLOUT and POLLHUP from the underlying socket */ ret = ctx->sk_poll(file, sock, wait); @@ -939,7 +938,7 @@ unsigned int tls_sw_poll(struct file *file, struct socket *sock, static int tls_read_size(struct strparser *strp, struct sk_buff *skb) { struct tls_context *tls_ctx = tls_get_ctx(strp->sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); char header[tls_ctx->rx.prepend_size]; struct strp_msg *rxm = strp_msg(skb); size_t cipher_overhead; @@ -988,7 +987,7 @@ read_failure: static void tls_queue(struct strparser *strp, struct sk_buff *skb) { struct tls_context *tls_ctx = tls_get_ctx(strp->sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); struct strp_msg *rxm; rxm = strp_msg(skb); @@ -1004,18 +1003,28 @@ static void tls_queue(struct strparser *strp, struct sk_buff *skb) static void tls_data_ready(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); strp_data_ready(&ctx->strp); } -void tls_sw_free_resources(struct sock *sk) +void tls_sw_free_resources_tx(struct sock *sk) { struct tls_context *tls_ctx = tls_get_ctx(sk); - struct tls_sw_context *ctx = tls_sw_ctx(tls_ctx); + struct tls_sw_context_tx *ctx = tls_sw_ctx_tx(tls_ctx); if (ctx->aead_send) crypto_free_aead(ctx->aead_send); + tls_free_both_sg(sk); + + kfree(ctx); +} + +void tls_sw_free_resources_rx(struct sock *sk) +{ + struct tls_context *tls_ctx = tls_get_ctx(sk); + struct tls_sw_context_rx *ctx = tls_sw_ctx_rx(tls_ctx); + if (ctx->aead_recv) { if (ctx->recv_pkt) { kfree_skb(ctx->recv_pkt); @@ -1031,10 +1040,7 @@ void tls_sw_free_resources(struct sock *sk) lock_sock(sk); } - tls_free_both_sg(sk); - kfree(ctx); - kfree(tls_ctx); } int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) @@ -1042,7 +1048,8 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) char keyval[TLS_CIPHER_AES_GCM_128_KEY_SIZE]; struct tls_crypto_info *crypto_info; struct tls12_crypto_info_aes_gcm_128 *gcm_128_info; - struct tls_sw_context *sw_ctx; + struct tls_sw_context_tx *sw_ctx_tx = NULL; + struct tls_sw_context_rx *sw_ctx_rx = NULL; struct cipher_context *cctx; struct crypto_aead **aead; struct strp_callbacks cb; @@ -1055,27 +1062,32 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) goto out; } - if (!ctx->priv_ctx) { - sw_ctx = kzalloc(sizeof(*sw_ctx), GFP_KERNEL); - if (!sw_ctx) { + if (tx) { + sw_ctx_tx = kzalloc(sizeof(*sw_ctx_tx), GFP_KERNEL); + if (!sw_ctx_tx) { rc = -ENOMEM; goto out; } - crypto_init_wait(&sw_ctx->async_wait); + crypto_init_wait(&sw_ctx_tx->async_wait); + ctx->priv_ctx_tx = sw_ctx_tx; } else { - sw_ctx = ctx->priv_ctx; + sw_ctx_rx = kzalloc(sizeof(*sw_ctx_rx), GFP_KERNEL); + if (!sw_ctx_rx) { + rc = -ENOMEM; + goto out; + } + crypto_init_wait(&sw_ctx_rx->async_wait); + ctx->priv_ctx_rx = sw_ctx_rx; } - ctx->priv_ctx = (struct tls_offload_context *)sw_ctx; - if (tx) { crypto_info = &ctx->crypto_send; cctx = &ctx->tx; - aead = &sw_ctx->aead_send; + aead = &sw_ctx_tx->aead_send; } else { crypto_info = &ctx->crypto_recv; cctx = &ctx->rx; - aead = &sw_ctx->aead_recv; + aead = &sw_ctx_rx->aead_recv; } switch (crypto_info->cipher_type) { @@ -1122,22 +1134,24 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) } memcpy(cctx->rec_seq, rec_seq, rec_seq_size); - if (tx) { - sg_init_table(sw_ctx->sg_encrypted_data, - ARRAY_SIZE(sw_ctx->sg_encrypted_data)); - sg_init_table(sw_ctx->sg_plaintext_data, - ARRAY_SIZE(sw_ctx->sg_plaintext_data)); - - sg_init_table(sw_ctx->sg_aead_in, 2); - sg_set_buf(&sw_ctx->sg_aead_in[0], sw_ctx->aad_space, - sizeof(sw_ctx->aad_space)); - sg_unmark_end(&sw_ctx->sg_aead_in[1]); - sg_chain(sw_ctx->sg_aead_in, 2, sw_ctx->sg_plaintext_data); - sg_init_table(sw_ctx->sg_aead_out, 2); - sg_set_buf(&sw_ctx->sg_aead_out[0], sw_ctx->aad_space, - sizeof(sw_ctx->aad_space)); - sg_unmark_end(&sw_ctx->sg_aead_out[1]); - sg_chain(sw_ctx->sg_aead_out, 2, sw_ctx->sg_encrypted_data); + if (sw_ctx_tx) { + sg_init_table(sw_ctx_tx->sg_encrypted_data, + ARRAY_SIZE(sw_ctx_tx->sg_encrypted_data)); + sg_init_table(sw_ctx_tx->sg_plaintext_data, + ARRAY_SIZE(sw_ctx_tx->sg_plaintext_data)); + + sg_init_table(sw_ctx_tx->sg_aead_in, 2); + sg_set_buf(&sw_ctx_tx->sg_aead_in[0], sw_ctx_tx->aad_space, + sizeof(sw_ctx_tx->aad_space)); + sg_unmark_end(&sw_ctx_tx->sg_aead_in[1]); + sg_chain(sw_ctx_tx->sg_aead_in, 2, + sw_ctx_tx->sg_plaintext_data); + sg_init_table(sw_ctx_tx->sg_aead_out, 2); + sg_set_buf(&sw_ctx_tx->sg_aead_out[0], sw_ctx_tx->aad_space, + sizeof(sw_ctx_tx->aad_space)); + sg_unmark_end(&sw_ctx_tx->sg_aead_out[1]); + sg_chain(sw_ctx_tx->sg_aead_out, 2, + sw_ctx_tx->sg_encrypted_data); } if (!*aead) { @@ -1162,22 +1176,22 @@ int tls_set_sw_offload(struct sock *sk, struct tls_context *ctx, int tx) if (rc) goto free_aead; - if (!tx) { + if (sw_ctx_rx) { /* Set up strparser */ memset(&cb, 0, sizeof(cb)); cb.rcv_msg = tls_queue; cb.parse_msg = tls_read_size; - strp_init(&sw_ctx->strp, sk, &cb); + strp_init(&sw_ctx_rx->strp, sk, &cb); write_lock_bh(&sk->sk_callback_lock); - sw_ctx->saved_data_ready = sk->sk_data_ready; + sw_ctx_rx->saved_data_ready = sk->sk_data_ready; sk->sk_data_ready = tls_data_ready; write_unlock_bh(&sk->sk_callback_lock); - sw_ctx->sk_poll = sk->sk_socket->ops->poll; + sw_ctx_rx->sk_poll = sk->sk_socket->ops->poll; - strp_check_rcv(&sw_ctx->strp); + strp_check_rcv(&sw_ctx_rx->strp); } goto out; @@ -1189,11 +1203,16 @@ free_rec_seq: kfree(cctx->rec_seq); cctx->rec_seq = NULL; free_iv: - kfree(ctx->tx.iv); - ctx->tx.iv = NULL; + kfree(cctx->iv); + cctx->iv = NULL; free_priv: - kfree(ctx->priv_ctx); - ctx->priv_ctx = NULL; + if (tx) { + kfree(ctx->priv_ctx_tx); + ctx->priv_ctx_tx = NULL; + } else { + kfree(ctx->priv_ctx_rx); + ctx->priv_ctx_rx = NULL; + } out: return rc; } diff --git a/net/xdp/Kconfig b/net/xdp/Kconfig new file mode 100644 index 000000000000..90e4a7152854 --- /dev/null +++ b/net/xdp/Kconfig @@ -0,0 +1,7 @@ +config XDP_SOCKETS + bool "XDP sockets" + depends on BPF_SYSCALL + default n + help + XDP sockets allows a channel between XDP programs and + userspace applications. diff --git a/net/xdp/Makefile b/net/xdp/Makefile new file mode 100644 index 000000000000..074fb2b2d51c --- /dev/null +++ b/net/xdp/Makefile @@ -0,0 +1,2 @@ +obj-$(CONFIG_XDP_SOCKETS) += xsk.o xdp_umem.o xsk_queue.o + diff --git a/net/xdp/xdp_umem.c b/net/xdp/xdp_umem.c new file mode 100644 index 000000000000..881dfdefe235 --- /dev/null +++ b/net/xdp/xdp_umem.c @@ -0,0 +1,260 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP user-space packet buffer + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/init.h> +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/uaccess.h> +#include <linux/slab.h> +#include <linux/bpf.h> +#include <linux/mm.h> + +#include "xdp_umem.h" + +#define XDP_UMEM_MIN_FRAME_SIZE 2048 + +int xdp_umem_create(struct xdp_umem **umem) +{ + *umem = kzalloc(sizeof(**umem), GFP_KERNEL); + + if (!(*umem)) + return -ENOMEM; + + return 0; +} + +static void xdp_umem_unpin_pages(struct xdp_umem *umem) +{ + unsigned int i; + + if (umem->pgs) { + for (i = 0; i < umem->npgs; i++) { + struct page *page = umem->pgs[i]; + + set_page_dirty_lock(page); + put_page(page); + } + + kfree(umem->pgs); + umem->pgs = NULL; + } +} + +static void xdp_umem_unaccount_pages(struct xdp_umem *umem) +{ + if (umem->user) { + atomic_long_sub(umem->npgs, &umem->user->locked_vm); + free_uid(umem->user); + } +} + +static void xdp_umem_release(struct xdp_umem *umem) +{ + struct task_struct *task; + struct mm_struct *mm; + + if (umem->fq) { + xskq_destroy(umem->fq); + umem->fq = NULL; + } + + if (umem->cq) { + xskq_destroy(umem->cq); + umem->cq = NULL; + } + + if (umem->pgs) { + xdp_umem_unpin_pages(umem); + + task = get_pid_task(umem->pid, PIDTYPE_PID); + put_pid(umem->pid); + if (!task) + goto out; + mm = get_task_mm(task); + put_task_struct(task); + if (!mm) + goto out; + + mmput(mm); + umem->pgs = NULL; + } + + xdp_umem_unaccount_pages(umem); +out: + kfree(umem); +} + +static void xdp_umem_release_deferred(struct work_struct *work) +{ + struct xdp_umem *umem = container_of(work, struct xdp_umem, work); + + xdp_umem_release(umem); +} + +void xdp_get_umem(struct xdp_umem *umem) +{ + atomic_inc(&umem->users); +} + +void xdp_put_umem(struct xdp_umem *umem) +{ + if (!umem) + return; + + if (atomic_dec_and_test(&umem->users)) { + INIT_WORK(&umem->work, xdp_umem_release_deferred); + schedule_work(&umem->work); + } +} + +static int xdp_umem_pin_pages(struct xdp_umem *umem) +{ + unsigned int gup_flags = FOLL_WRITE; + long npgs; + int err; + + umem->pgs = kcalloc(umem->npgs, sizeof(*umem->pgs), GFP_KERNEL); + if (!umem->pgs) + return -ENOMEM; + + down_write(¤t->mm->mmap_sem); + npgs = get_user_pages(umem->address, umem->npgs, + gup_flags, &umem->pgs[0], NULL); + up_write(¤t->mm->mmap_sem); + + if (npgs != umem->npgs) { + if (npgs >= 0) { + umem->npgs = npgs; + err = -ENOMEM; + goto out_pin; + } + err = npgs; + goto out_pgs; + } + return 0; + +out_pin: + xdp_umem_unpin_pages(umem); +out_pgs: + kfree(umem->pgs); + umem->pgs = NULL; + return err; +} + +static int xdp_umem_account_pages(struct xdp_umem *umem) +{ + unsigned long lock_limit, new_npgs, old_npgs; + + if (capable(CAP_IPC_LOCK)) + return 0; + + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + umem->user = get_uid(current_user()); + + do { + old_npgs = atomic_long_read(&umem->user->locked_vm); + new_npgs = old_npgs + umem->npgs; + if (new_npgs > lock_limit) { + free_uid(umem->user); + umem->user = NULL; + return -ENOBUFS; + } + } while (atomic_long_cmpxchg(&umem->user->locked_vm, old_npgs, + new_npgs) != old_npgs); + return 0; +} + +int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr) +{ + u32 frame_size = mr->frame_size, frame_headroom = mr->frame_headroom; + u64 addr = mr->addr, size = mr->len; + unsigned int nframes, nfpp; + int size_chk, err; + + if (!umem) + return -EINVAL; + + if (frame_size < XDP_UMEM_MIN_FRAME_SIZE || frame_size > PAGE_SIZE) { + /* Strictly speaking we could support this, if: + * - huge pages, or* + * - using an IOMMU, or + * - making sure the memory area is consecutive + * but for now, we simply say "computer says no". + */ + return -EINVAL; + } + + if (!is_power_of_2(frame_size)) + return -EINVAL; + + if (!PAGE_ALIGNED(addr)) { + /* Memory area has to be page size aligned. For + * simplicity, this might change. + */ + return -EINVAL; + } + + if ((addr + size) < addr) + return -EINVAL; + + nframes = size / frame_size; + if (nframes == 0 || nframes > UINT_MAX) + return -EINVAL; + + nfpp = PAGE_SIZE / frame_size; + if (nframes < nfpp || nframes % nfpp) + return -EINVAL; + + frame_headroom = ALIGN(frame_headroom, 64); + + size_chk = frame_size - frame_headroom - XDP_PACKET_HEADROOM; + if (size_chk < 0) + return -EINVAL; + + umem->pid = get_task_pid(current, PIDTYPE_PID); + umem->size = (size_t)size; + umem->address = (unsigned long)addr; + umem->props.frame_size = frame_size; + umem->props.nframes = nframes; + umem->frame_headroom = frame_headroom; + umem->npgs = size / PAGE_SIZE; + umem->pgs = NULL; + umem->user = NULL; + + umem->frame_size_log2 = ilog2(frame_size); + umem->nfpp_mask = nfpp - 1; + umem->nfpplog2 = ilog2(nfpp); + atomic_set(&umem->users, 1); + + err = xdp_umem_account_pages(umem); + if (err) + goto out; + + err = xdp_umem_pin_pages(umem); + if (err) + goto out_account; + return 0; + +out_account: + xdp_umem_unaccount_pages(umem); +out: + put_pid(umem->pid); + return err; +} + +bool xdp_umem_validate_queues(struct xdp_umem *umem) +{ + return (umem->fq && umem->cq); +} diff --git a/net/xdp/xdp_umem.h b/net/xdp/xdp_umem.h new file mode 100644 index 000000000000..7e0b2fab8522 --- /dev/null +++ b/net/xdp/xdp_umem.h @@ -0,0 +1,67 @@ +/* SPDX-License-Identifier: GPL-2.0 + * XDP user-space packet buffer + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef XDP_UMEM_H_ +#define XDP_UMEM_H_ + +#include <linux/mm.h> +#include <linux/if_xdp.h> +#include <linux/workqueue.h> + +#include "xsk_queue.h" +#include "xdp_umem_props.h" + +struct xdp_umem { + struct xsk_queue *fq; + struct xsk_queue *cq; + struct page **pgs; + struct xdp_umem_props props; + u32 npgs; + u32 frame_headroom; + u32 nfpp_mask; + u32 nfpplog2; + u32 frame_size_log2; + struct user_struct *user; + struct pid *pid; + unsigned long address; + size_t size; + atomic_t users; + struct work_struct work; +}; + +static inline char *xdp_umem_get_data(struct xdp_umem *umem, u32 idx) +{ + u64 pg, off; + char *data; + + pg = idx >> umem->nfpplog2; + off = (idx & umem->nfpp_mask) << umem->frame_size_log2; + + data = page_address(umem->pgs[pg]); + return data + off; +} + +static inline char *xdp_umem_get_data_with_headroom(struct xdp_umem *umem, + u32 idx) +{ + return xdp_umem_get_data(umem, idx) + umem->frame_headroom; +} + +bool xdp_umem_validate_queues(struct xdp_umem *umem); +int xdp_umem_reg(struct xdp_umem *umem, struct xdp_umem_reg *mr); +void xdp_get_umem(struct xdp_umem *umem); +void xdp_put_umem(struct xdp_umem *umem); +int xdp_umem_create(struct xdp_umem **umem); + +#endif /* XDP_UMEM_H_ */ diff --git a/net/xdp/xdp_umem_props.h b/net/xdp/xdp_umem_props.h new file mode 100644 index 000000000000..77fb5daf29f3 --- /dev/null +++ b/net/xdp/xdp_umem_props.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 + * XDP user-space packet buffer + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef XDP_UMEM_PROPS_H_ +#define XDP_UMEM_PROPS_H_ + +struct xdp_umem_props { + u32 frame_size; + u32 nframes; +}; + +#endif /* XDP_UMEM_PROPS_H_ */ diff --git a/net/xdp/xsk.c b/net/xdp/xsk.c new file mode 100644 index 000000000000..009c5af5bba5 --- /dev/null +++ b/net/xdp/xsk.c @@ -0,0 +1,656 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP sockets + * + * AF_XDP sockets allows a channel between XDP programs and userspace + * applications. + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * Author(s): Björn Töpel <bjorn.topel@intel.com> + * Magnus Karlsson <magnus.karlsson@intel.com> + */ + +#define pr_fmt(fmt) "AF_XDP: %s: " fmt, __func__ + +#include <linux/if_xdp.h> +#include <linux/init.h> +#include <linux/sched/mm.h> +#include <linux/sched/signal.h> +#include <linux/sched/task.h> +#include <linux/socket.h> +#include <linux/file.h> +#include <linux/uaccess.h> +#include <linux/net.h> +#include <linux/netdevice.h> +#include <net/xdp_sock.h> +#include <net/xdp.h> + +#include "xsk_queue.h" +#include "xdp_umem.h" + +#define TX_BATCH_SIZE 16 + +static struct xdp_sock *xdp_sk(struct sock *sk) +{ + return (struct xdp_sock *)sk; +} + +bool xsk_is_setup_for_bpf_map(struct xdp_sock *xs) +{ + return !!xs->rx; +} + +static int __xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + u32 *id, len = xdp->data_end - xdp->data; + void *buffer; + int err = 0; + + if (xs->dev != xdp->rxq->dev || xs->queue_id != xdp->rxq->queue_index) + return -EINVAL; + + id = xskq_peek_id(xs->umem->fq); + if (!id) + return -ENOSPC; + + buffer = xdp_umem_get_data_with_headroom(xs->umem, *id); + memcpy(buffer, xdp->data, len); + err = xskq_produce_batch_desc(xs->rx, *id, len, + xs->umem->frame_headroom); + if (!err) + xskq_discard_id(xs->umem->fq); + + return err; +} + +int xsk_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + int err; + + err = __xsk_rcv(xs, xdp); + if (likely(!err)) + xdp_return_buff(xdp); + else + xs->rx_dropped++; + + return err; +} + +void xsk_flush(struct xdp_sock *xs) +{ + xskq_produce_flush_desc(xs->rx); + xs->sk.sk_data_ready(&xs->sk); +} + +int xsk_generic_rcv(struct xdp_sock *xs, struct xdp_buff *xdp) +{ + int err; + + err = __xsk_rcv(xs, xdp); + if (!err) + xsk_flush(xs); + else + xs->rx_dropped++; + + return err; +} + +static void xsk_destruct_skb(struct sk_buff *skb) +{ + u32 id = (u32)(long)skb_shinfo(skb)->destructor_arg; + struct xdp_sock *xs = xdp_sk(skb->sk); + + WARN_ON_ONCE(xskq_produce_id(xs->umem->cq, id)); + + sock_wfree(skb); +} + +static int xsk_generic_xmit(struct sock *sk, struct msghdr *m, + size_t total_len) +{ + bool need_wait = !(m->msg_flags & MSG_DONTWAIT); + u32 max_batch = TX_BATCH_SIZE; + struct xdp_sock *xs = xdp_sk(sk); + bool sent_frame = false; + struct xdp_desc desc; + struct sk_buff *skb; + int err = 0; + + if (unlikely(!xs->tx)) + return -ENOBUFS; + if (need_wait) + return -EOPNOTSUPP; + + mutex_lock(&xs->mutex); + + while (xskq_peek_desc(xs->tx, &desc)) { + char *buffer; + u32 id, len; + + if (max_batch-- == 0) { + err = -EAGAIN; + goto out; + } + + if (xskq_reserve_id(xs->umem->cq)) { + err = -EAGAIN; + goto out; + } + + len = desc.len; + if (unlikely(len > xs->dev->mtu)) { + err = -EMSGSIZE; + goto out; + } + + skb = sock_alloc_send_skb(sk, len, !need_wait, &err); + if (unlikely(!skb)) { + err = -EAGAIN; + goto out; + } + + skb_put(skb, len); + id = desc.idx; + buffer = xdp_umem_get_data(xs->umem, id) + desc.offset; + err = skb_store_bits(skb, 0, buffer, len); + if (unlikely(err)) { + kfree_skb(skb); + goto out; + } + + skb->dev = xs->dev; + skb->priority = sk->sk_priority; + skb->mark = sk->sk_mark; + skb_shinfo(skb)->destructor_arg = (void *)(long)id; + skb->destructor = xsk_destruct_skb; + + err = dev_direct_xmit(skb, xs->queue_id); + /* Ignore NET_XMIT_CN as packet might have been sent */ + if (err == NET_XMIT_DROP || err == NETDEV_TX_BUSY) { + err = -EAGAIN; + /* SKB consumed by dev_direct_xmit() */ + goto out; + } + + sent_frame = true; + xskq_discard_desc(xs->tx); + } + +out: + if (sent_frame) + sk->sk_write_space(sk); + + mutex_unlock(&xs->mutex); + return err; +} + +static int xsk_sendmsg(struct socket *sock, struct msghdr *m, size_t total_len) +{ + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + + if (unlikely(!xs->dev)) + return -ENXIO; + if (unlikely(!(xs->dev->flags & IFF_UP))) + return -ENETDOWN; + + return xsk_generic_xmit(sk, m, total_len); +} + +static unsigned int xsk_poll(struct file *file, struct socket *sock, + struct poll_table_struct *wait) +{ + unsigned int mask = datagram_poll(file, sock, wait); + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + + if (xs->rx && !xskq_empty_desc(xs->rx)) + mask |= POLLIN | POLLRDNORM; + if (xs->tx && !xskq_full_desc(xs->tx)) + mask |= POLLOUT | POLLWRNORM; + + return mask; +} + +static int xsk_init_queue(u32 entries, struct xsk_queue **queue, + bool umem_queue) +{ + struct xsk_queue *q; + + if (entries == 0 || *queue || !is_power_of_2(entries)) + return -EINVAL; + + q = xskq_create(entries, umem_queue); + if (!q) + return -ENOMEM; + + *queue = q; + return 0; +} + +static void __xsk_release(struct xdp_sock *xs) +{ + /* Wait for driver to stop using the xdp socket. */ + synchronize_net(); + + dev_put(xs->dev); +} + +static int xsk_release(struct socket *sock) +{ + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + struct net *net; + + if (!sk) + return 0; + + net = sock_net(sk); + + local_bh_disable(); + sock_prot_inuse_add(net, sk->sk_prot, -1); + local_bh_enable(); + + if (xs->dev) { + __xsk_release(xs); + xs->dev = NULL; + } + + sock_orphan(sk); + sock->sk = NULL; + + sk_refcnt_debug_release(sk); + sock_put(sk); + + return 0; +} + +static struct socket *xsk_lookup_xsk_from_fd(int fd) +{ + struct socket *sock; + int err; + + sock = sockfd_lookup(fd, &err); + if (!sock) + return ERR_PTR(-ENOTSOCK); + + if (sock->sk->sk_family != PF_XDP) { + sockfd_put(sock); + return ERR_PTR(-ENOPROTOOPT); + } + + return sock; +} + +static int xsk_bind(struct socket *sock, struct sockaddr *addr, int addr_len) +{ + struct sockaddr_xdp *sxdp = (struct sockaddr_xdp *)addr; + struct sock *sk = sock->sk; + struct net_device *dev, *dev_curr; + struct xdp_sock *xs = xdp_sk(sk); + struct xdp_umem *old_umem = NULL; + int err = 0; + + if (addr_len < sizeof(struct sockaddr_xdp)) + return -EINVAL; + if (sxdp->sxdp_family != AF_XDP) + return -EINVAL; + + mutex_lock(&xs->mutex); + dev_curr = xs->dev; + dev = dev_get_by_index(sock_net(sk), sxdp->sxdp_ifindex); + if (!dev) { + err = -ENODEV; + goto out_release; + } + + if (!xs->rx && !xs->tx) { + err = -EINVAL; + goto out_unlock; + } + + if (sxdp->sxdp_queue_id >= dev->num_rx_queues) { + err = -EINVAL; + goto out_unlock; + } + + if (sxdp->sxdp_flags & XDP_SHARED_UMEM) { + struct xdp_sock *umem_xs; + struct socket *sock; + + if (xs->umem) { + /* We have already our own. */ + err = -EINVAL; + goto out_unlock; + } + + sock = xsk_lookup_xsk_from_fd(sxdp->sxdp_shared_umem_fd); + if (IS_ERR(sock)) { + err = PTR_ERR(sock); + goto out_unlock; + } + + umem_xs = xdp_sk(sock->sk); + if (!umem_xs->umem) { + /* No umem to inherit. */ + err = -EBADF; + sockfd_put(sock); + goto out_unlock; + } else if (umem_xs->dev != dev || + umem_xs->queue_id != sxdp->sxdp_queue_id) { + err = -EINVAL; + sockfd_put(sock); + goto out_unlock; + } + + xdp_get_umem(umem_xs->umem); + old_umem = xs->umem; + xs->umem = umem_xs->umem; + sockfd_put(sock); + } else if (!xs->umem || !xdp_umem_validate_queues(xs->umem)) { + err = -EINVAL; + goto out_unlock; + } else { + /* This xsk has its own umem. */ + xskq_set_umem(xs->umem->fq, &xs->umem->props); + xskq_set_umem(xs->umem->cq, &xs->umem->props); + } + + /* Rebind? */ + if (dev_curr && (dev_curr != dev || + xs->queue_id != sxdp->sxdp_queue_id)) { + __xsk_release(xs); + if (old_umem) + xdp_put_umem(old_umem); + } + + xs->dev = dev; + xs->queue_id = sxdp->sxdp_queue_id; + + xskq_set_umem(xs->rx, &xs->umem->props); + xskq_set_umem(xs->tx, &xs->umem->props); + +out_unlock: + if (err) + dev_put(dev); +out_release: + mutex_unlock(&xs->mutex); + return err; +} + +static int xsk_setsockopt(struct socket *sock, int level, int optname, + char __user *optval, unsigned int optlen) +{ + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + int err; + + if (level != SOL_XDP) + return -ENOPROTOOPT; + + switch (optname) { + case XDP_RX_RING: + case XDP_TX_RING: + { + struct xsk_queue **q; + int entries; + + if (optlen < sizeof(entries)) + return -EINVAL; + if (copy_from_user(&entries, optval, sizeof(entries))) + return -EFAULT; + + mutex_lock(&xs->mutex); + q = (optname == XDP_TX_RING) ? &xs->tx : &xs->rx; + err = xsk_init_queue(entries, q, false); + mutex_unlock(&xs->mutex); + return err; + } + case XDP_UMEM_REG: + { + struct xdp_umem_reg mr; + struct xdp_umem *umem; + + if (xs->umem) + return -EBUSY; + + if (copy_from_user(&mr, optval, sizeof(mr))) + return -EFAULT; + + mutex_lock(&xs->mutex); + err = xdp_umem_create(&umem); + + err = xdp_umem_reg(umem, &mr); + if (err) { + kfree(umem); + mutex_unlock(&xs->mutex); + return err; + } + + /* Make sure umem is ready before it can be seen by others */ + smp_wmb(); + + xs->umem = umem; + mutex_unlock(&xs->mutex); + return 0; + } + case XDP_UMEM_FILL_RING: + case XDP_UMEM_COMPLETION_RING: + { + struct xsk_queue **q; + int entries; + + if (!xs->umem) + return -EINVAL; + + if (copy_from_user(&entries, optval, sizeof(entries))) + return -EFAULT; + + mutex_lock(&xs->mutex); + q = (optname == XDP_UMEM_FILL_RING) ? &xs->umem->fq : + &xs->umem->cq; + err = xsk_init_queue(entries, q, true); + mutex_unlock(&xs->mutex); + return err; + } + default: + break; + } + + return -ENOPROTOOPT; +} + +static int xsk_getsockopt(struct socket *sock, int level, int optname, + char __user *optval, int __user *optlen) +{ + struct sock *sk = sock->sk; + struct xdp_sock *xs = xdp_sk(sk); + int len; + + if (level != SOL_XDP) + return -ENOPROTOOPT; + + if (get_user(len, optlen)) + return -EFAULT; + if (len < 0) + return -EINVAL; + + switch (optname) { + case XDP_STATISTICS: + { + struct xdp_statistics stats; + + if (len < sizeof(stats)) + return -EINVAL; + + mutex_lock(&xs->mutex); + stats.rx_dropped = xs->rx_dropped; + stats.rx_invalid_descs = xskq_nb_invalid_descs(xs->rx); + stats.tx_invalid_descs = xskq_nb_invalid_descs(xs->tx); + mutex_unlock(&xs->mutex); + + if (copy_to_user(optval, &stats, sizeof(stats))) + return -EFAULT; + if (put_user(sizeof(stats), optlen)) + return -EFAULT; + + return 0; + } + default: + break; + } + + return -EOPNOTSUPP; +} + +static int xsk_mmap(struct file *file, struct socket *sock, + struct vm_area_struct *vma) +{ + unsigned long offset = vma->vm_pgoff << PAGE_SHIFT; + unsigned long size = vma->vm_end - vma->vm_start; + struct xdp_sock *xs = xdp_sk(sock->sk); + struct xsk_queue *q = NULL; + unsigned long pfn; + struct page *qpg; + + if (offset == XDP_PGOFF_RX_RING) { + q = xs->rx; + } else if (offset == XDP_PGOFF_TX_RING) { + q = xs->tx; + } else { + if (!xs->umem) + return -EINVAL; + + if (offset == XDP_UMEM_PGOFF_FILL_RING) + q = xs->umem->fq; + else if (offset == XDP_UMEM_PGOFF_COMPLETION_RING) + q = xs->umem->cq; + } + + if (!q) + return -EINVAL; + + qpg = virt_to_head_page(q->ring); + if (size > (PAGE_SIZE << compound_order(qpg))) + return -EINVAL; + + pfn = virt_to_phys(q->ring) >> PAGE_SHIFT; + return remap_pfn_range(vma, vma->vm_start, pfn, + size, vma->vm_page_prot); +} + +static struct proto xsk_proto = { + .name = "XDP", + .owner = THIS_MODULE, + .obj_size = sizeof(struct xdp_sock), +}; + +static const struct proto_ops xsk_proto_ops = { + .family = PF_XDP, + .owner = THIS_MODULE, + .release = xsk_release, + .bind = xsk_bind, + .connect = sock_no_connect, + .socketpair = sock_no_socketpair, + .accept = sock_no_accept, + .getname = sock_no_getname, + .poll = xsk_poll, + .ioctl = sock_no_ioctl, + .listen = sock_no_listen, + .shutdown = sock_no_shutdown, + .setsockopt = xsk_setsockopt, + .getsockopt = xsk_getsockopt, + .sendmsg = xsk_sendmsg, + .recvmsg = sock_no_recvmsg, + .mmap = xsk_mmap, + .sendpage = sock_no_sendpage, +}; + +static void xsk_destruct(struct sock *sk) +{ + struct xdp_sock *xs = xdp_sk(sk); + + if (!sock_flag(sk, SOCK_DEAD)) + return; + + xskq_destroy(xs->rx); + xskq_destroy(xs->tx); + xdp_put_umem(xs->umem); + + sk_refcnt_debug_dec(sk); +} + +static int xsk_create(struct net *net, struct socket *sock, int protocol, + int kern) +{ + struct sock *sk; + struct xdp_sock *xs; + + if (!ns_capable(net->user_ns, CAP_NET_RAW)) + return -EPERM; + if (sock->type != SOCK_RAW) + return -ESOCKTNOSUPPORT; + + if (protocol) + return -EPROTONOSUPPORT; + + sock->state = SS_UNCONNECTED; + + sk = sk_alloc(net, PF_XDP, GFP_KERNEL, &xsk_proto, kern); + if (!sk) + return -ENOBUFS; + + sock->ops = &xsk_proto_ops; + + sock_init_data(sock, sk); + + sk->sk_family = PF_XDP; + + sk->sk_destruct = xsk_destruct; + sk_refcnt_debug_inc(sk); + + xs = xdp_sk(sk); + mutex_init(&xs->mutex); + + local_bh_disable(); + sock_prot_inuse_add(net, &xsk_proto, 1); + local_bh_enable(); + + return 0; +} + +static const struct net_proto_family xsk_family_ops = { + .family = PF_XDP, + .create = xsk_create, + .owner = THIS_MODULE, +}; + +static int __init xsk_init(void) +{ + int err; + + err = proto_register(&xsk_proto, 0 /* no slab */); + if (err) + goto out; + + err = sock_register(&xsk_family_ops); + if (err) + goto out_proto; + + return 0; + +out_proto: + proto_unregister(&xsk_proto); +out: + return err; +} + +fs_initcall(xsk_init); diff --git a/net/xdp/xsk_queue.c b/net/xdp/xsk_queue.c new file mode 100644 index 000000000000..d012e5e23591 --- /dev/null +++ b/net/xdp/xsk_queue.c @@ -0,0 +1,73 @@ +// SPDX-License-Identifier: GPL-2.0 +/* XDP user-space ring structure + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <linux/slab.h> + +#include "xsk_queue.h" + +void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props) +{ + if (!q) + return; + + q->umem_props = *umem_props; +} + +static u32 xskq_umem_get_ring_size(struct xsk_queue *q) +{ + return sizeof(struct xdp_umem_ring) + q->nentries * sizeof(u32); +} + +static u32 xskq_rxtx_get_ring_size(struct xsk_queue *q) +{ + return (sizeof(struct xdp_ring) + + q->nentries * sizeof(struct xdp_desc)); +} + +struct xsk_queue *xskq_create(u32 nentries, bool umem_queue) +{ + struct xsk_queue *q; + gfp_t gfp_flags; + size_t size; + + q = kzalloc(sizeof(*q), GFP_KERNEL); + if (!q) + return NULL; + + q->nentries = nentries; + q->ring_mask = nentries - 1; + + gfp_flags = GFP_KERNEL | __GFP_ZERO | __GFP_NOWARN | + __GFP_COMP | __GFP_NORETRY; + size = umem_queue ? xskq_umem_get_ring_size(q) : + xskq_rxtx_get_ring_size(q); + + q->ring = (struct xdp_ring *)__get_free_pages(gfp_flags, + get_order(size)); + if (!q->ring) { + kfree(q); + return NULL; + } + + return q; +} + +void xskq_destroy(struct xsk_queue *q) +{ + if (!q) + return; + + page_frag_free(q->ring); + kfree(q); +} diff --git a/net/xdp/xsk_queue.h b/net/xdp/xsk_queue.h new file mode 100644 index 000000000000..7aa9a535db0e --- /dev/null +++ b/net/xdp/xsk_queue.h @@ -0,0 +1,247 @@ +/* SPDX-License-Identifier: GPL-2.0 + * XDP user-space ring structure + * Copyright(c) 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#ifndef _LINUX_XSK_QUEUE_H +#define _LINUX_XSK_QUEUE_H + +#include <linux/types.h> +#include <linux/if_xdp.h> + +#include "xdp_umem_props.h" + +#define RX_BATCH_SIZE 16 + +struct xsk_queue { + struct xdp_umem_props umem_props; + u32 ring_mask; + u32 nentries; + u32 prod_head; + u32 prod_tail; + u32 cons_head; + u32 cons_tail; + struct xdp_ring *ring; + u64 invalid_descs; +}; + +/* Common functions operating for both RXTX and umem queues */ + +static inline u64 xskq_nb_invalid_descs(struct xsk_queue *q) +{ + return q ? q->invalid_descs : 0; +} + +static inline u32 xskq_nb_avail(struct xsk_queue *q, u32 dcnt) +{ + u32 entries = q->prod_tail - q->cons_tail; + + if (entries == 0) { + /* Refresh the local pointer */ + q->prod_tail = READ_ONCE(q->ring->producer); + entries = q->prod_tail - q->cons_tail; + } + + return (entries > dcnt) ? dcnt : entries; +} + +static inline u32 xskq_nb_free(struct xsk_queue *q, u32 producer, u32 dcnt) +{ + u32 free_entries = q->nentries - (producer - q->cons_tail); + + if (free_entries >= dcnt) + return free_entries; + + /* Refresh the local tail pointer */ + q->cons_tail = READ_ONCE(q->ring->consumer); + return q->nentries - (producer - q->cons_tail); +} + +/* UMEM queue */ + +static inline bool xskq_is_valid_id(struct xsk_queue *q, u32 idx) +{ + if (unlikely(idx >= q->umem_props.nframes)) { + q->invalid_descs++; + return false; + } + return true; +} + +static inline u32 *xskq_validate_id(struct xsk_queue *q) +{ + while (q->cons_tail != q->cons_head) { + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + unsigned int idx = q->cons_tail & q->ring_mask; + + if (xskq_is_valid_id(q, ring->desc[idx])) + return &ring->desc[idx]; + + q->cons_tail++; + } + + return NULL; +} + +static inline u32 *xskq_peek_id(struct xsk_queue *q) +{ + struct xdp_umem_ring *ring; + + if (q->cons_tail == q->cons_head) { + WRITE_ONCE(q->ring->consumer, q->cons_tail); + q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE); + + /* Order consumer and data */ + smp_rmb(); + + return xskq_validate_id(q); + } + + ring = (struct xdp_umem_ring *)q->ring; + return &ring->desc[q->cons_tail & q->ring_mask]; +} + +static inline void xskq_discard_id(struct xsk_queue *q) +{ + q->cons_tail++; + (void)xskq_validate_id(q); +} + +static inline int xskq_produce_id(struct xsk_queue *q, u32 id) +{ + struct xdp_umem_ring *ring = (struct xdp_umem_ring *)q->ring; + + ring->desc[q->prod_tail++ & q->ring_mask] = id; + + /* Order producer and data */ + smp_wmb(); + + WRITE_ONCE(q->ring->producer, q->prod_tail); + return 0; +} + +static inline int xskq_reserve_id(struct xsk_queue *q) +{ + if (xskq_nb_free(q, q->prod_head, 1) == 0) + return -ENOSPC; + + q->prod_head++; + return 0; +} + +/* Rx/Tx queue */ + +static inline bool xskq_is_valid_desc(struct xsk_queue *q, struct xdp_desc *d) +{ + u32 buff_len; + + if (unlikely(d->idx >= q->umem_props.nframes)) { + q->invalid_descs++; + return false; + } + + buff_len = q->umem_props.frame_size; + if (unlikely(d->len > buff_len || d->len == 0 || + d->offset > buff_len || d->offset + d->len > buff_len)) { + q->invalid_descs++; + return false; + } + + return true; +} + +static inline struct xdp_desc *xskq_validate_desc(struct xsk_queue *q, + struct xdp_desc *desc) +{ + while (q->cons_tail != q->cons_head) { + struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; + unsigned int idx = q->cons_tail & q->ring_mask; + + if (xskq_is_valid_desc(q, &ring->desc[idx])) { + if (desc) + *desc = ring->desc[idx]; + return desc; + } + + q->cons_tail++; + } + + return NULL; +} + +static inline struct xdp_desc *xskq_peek_desc(struct xsk_queue *q, + struct xdp_desc *desc) +{ + struct xdp_rxtx_ring *ring; + + if (q->cons_tail == q->cons_head) { + WRITE_ONCE(q->ring->consumer, q->cons_tail); + q->cons_head = q->cons_tail + xskq_nb_avail(q, RX_BATCH_SIZE); + + /* Order consumer and data */ + smp_rmb(); + + return xskq_validate_desc(q, desc); + } + + ring = (struct xdp_rxtx_ring *)q->ring; + *desc = ring->desc[q->cons_tail & q->ring_mask]; + return desc; +} + +static inline void xskq_discard_desc(struct xsk_queue *q) +{ + q->cons_tail++; + (void)xskq_validate_desc(q, NULL); +} + +static inline int xskq_produce_batch_desc(struct xsk_queue *q, + u32 id, u32 len, u16 offset) +{ + struct xdp_rxtx_ring *ring = (struct xdp_rxtx_ring *)q->ring; + unsigned int idx; + + if (xskq_nb_free(q, q->prod_head, 1) == 0) + return -ENOSPC; + + idx = (q->prod_head++) & q->ring_mask; + ring->desc[idx].idx = id; + ring->desc[idx].len = len; + ring->desc[idx].offset = offset; + + return 0; +} + +static inline void xskq_produce_flush_desc(struct xsk_queue *q) +{ + /* Order producer and data */ + smp_wmb(); + + q->prod_tail = q->prod_head, + WRITE_ONCE(q->ring->producer, q->prod_tail); +} + +static inline bool xskq_full_desc(struct xsk_queue *q) +{ + return (xskq_nb_avail(q, q->nentries) == q->nentries); +} + +static inline bool xskq_empty_desc(struct xsk_queue *q) +{ + return (xskq_nb_free(q, q->prod_tail, 1) == q->nentries); +} + +void xskq_set_umem(struct xsk_queue *q, struct xdp_umem_props *umem_props); +struct xsk_queue *xskq_create(u32 nentries, bool umem_queue); +void xskq_destroy(struct xsk_queue *q_ops); + +#endif /* _LINUX_XSK_QUEUE_H */ diff --git a/net/xfrm/xfrm_state.c b/net/xfrm/xfrm_state.c index 6c177ae7a6d9..8308281f3253 100644 --- a/net/xfrm/xfrm_state.c +++ b/net/xfrm/xfrm_state.c @@ -42,6 +42,7 @@ static void xfrm_state_gc_task(struct work_struct *work); static unsigned int xfrm_state_hashmax __read_mostly = 1 * 1024 * 1024; static __read_mostly seqcount_t xfrm_state_hash_generation = SEQCNT_ZERO(xfrm_state_hash_generation); +static struct kmem_cache *xfrm_state_cache __ro_after_init; static DECLARE_WORK(xfrm_state_gc_work, xfrm_state_gc_task); static HLIST_HEAD(xfrm_state_gc_list); @@ -451,7 +452,7 @@ static void xfrm_state_gc_destroy(struct xfrm_state *x) } xfrm_dev_state_free(x); security_xfrm_state_free(x); - kfree(x); + kmem_cache_free(xfrm_state_cache, x); } static void xfrm_state_gc_task(struct work_struct *work) @@ -563,7 +564,7 @@ struct xfrm_state *xfrm_state_alloc(struct net *net) { struct xfrm_state *x; - x = kzalloc(sizeof(struct xfrm_state), GFP_ATOMIC); + x = kmem_cache_alloc(xfrm_state_cache, GFP_ATOMIC | __GFP_ZERO); if (x) { write_pnet(&x->xs_net, net); @@ -2313,6 +2314,10 @@ int __net_init xfrm_state_init(struct net *net) { unsigned int sz; + if (net_eq(net, &init_net)) + xfrm_state_cache = KMEM_CACHE(xfrm_state, + SLAB_HWCACHE_ALIGN | SLAB_PANIC); + INIT_LIST_HEAD(&net->xfrm.state_all); sz = sizeof(struct hlist_head) * 8; diff --git a/samples/bpf/Makefile b/samples/bpf/Makefile index 4d6a6edd4bf6..8e0c7fb6d7cc 100644 --- a/samples/bpf/Makefile +++ b/samples/bpf/Makefile @@ -44,10 +44,13 @@ hostprogs-y += xdp_monitor hostprogs-y += xdp_rxq_info hostprogs-y += syscall_tp hostprogs-y += cpustat +hostprogs-y += xdp_adjust_tail +hostprogs-y += xdpsock # Libbpf dependencies LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o CGROUP_HELPERS := ../../tools/testing/selftests/bpf/cgroup_helpers.o +TRACE_HELPERS := ../../tools/testing/selftests/bpf/trace_helpers.o test_lru_dist-objs := test_lru_dist.o $(LIBBPF) sock_example-objs := sock_example.o $(LIBBPF) @@ -64,10 +67,10 @@ tracex6-objs := bpf_load.o $(LIBBPF) tracex6_user.o tracex7-objs := bpf_load.o $(LIBBPF) tracex7_user.o load_sock_ops-objs := bpf_load.o $(LIBBPF) load_sock_ops.o test_probe_write_user-objs := bpf_load.o $(LIBBPF) test_probe_write_user_user.o -trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o +trace_output-objs := bpf_load.o $(LIBBPF) trace_output_user.o $(TRACE_HELPERS) lathist-objs := bpf_load.o $(LIBBPF) lathist_user.o -offwaketime-objs := bpf_load.o $(LIBBPF) offwaketime_user.o -spintest-objs := bpf_load.o $(LIBBPF) spintest_user.o +offwaketime-objs := bpf_load.o $(LIBBPF) offwaketime_user.o $(TRACE_HELPERS) +spintest-objs := bpf_load.o $(LIBBPF) spintest_user.o $(TRACE_HELPERS) map_perf_test-objs := bpf_load.o $(LIBBPF) map_perf_test_user.o test_overhead-objs := bpf_load.o $(LIBBPF) test_overhead_user.o test_cgrp2_array_pin-objs := $(LIBBPF) test_cgrp2_array_pin.o @@ -81,8 +84,8 @@ xdp2-objs := bpf_load.o $(LIBBPF) xdp1_user.o xdp_router_ipv4-objs := bpf_load.o $(LIBBPF) xdp_router_ipv4_user.o test_current_task_under_cgroup-objs := bpf_load.o $(LIBBPF) $(CGROUP_HELPERS) \ test_current_task_under_cgroup_user.o -trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o -sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o +trace_event-objs := bpf_load.o $(LIBBPF) trace_event_user.o $(TRACE_HELPERS) +sampleip-objs := bpf_load.o $(LIBBPF) sampleip_user.o $(TRACE_HELPERS) tc_l2_redirect-objs := bpf_load.o $(LIBBPF) tc_l2_redirect_user.o lwt_len_hist-objs := bpf_load.o $(LIBBPF) lwt_len_hist_user.o xdp_tx_iptunnel-objs := bpf_load.o $(LIBBPF) xdp_tx_iptunnel_user.o @@ -95,6 +98,8 @@ xdp_monitor-objs := bpf_load.o $(LIBBPF) xdp_monitor_user.o xdp_rxq_info-objs := bpf_load.o $(LIBBPF) xdp_rxq_info_user.o syscall_tp-objs := bpf_load.o $(LIBBPF) syscall_tp_user.o cpustat-objs := bpf_load.o $(LIBBPF) cpustat_user.o +xdp_adjust_tail-objs := bpf_load.o $(LIBBPF) xdp_adjust_tail_user.o +xdpsock-objs := bpf_load.o $(LIBBPF) xdpsock_user.o # Tell kbuild to always build the programs always := $(hostprogs-y) @@ -112,7 +117,6 @@ always += sock_flags_kern.o always += test_probe_write_user_kern.o always += trace_output_kern.o always += tcbpf1_kern.o -always += tcbpf2_kern.o always += tc_l2_redirect_kern.o always += lathist_kern.o always += offwaketime_kern.o @@ -148,6 +152,8 @@ always += xdp_rxq_info_kern.o always += xdp2skb_meta_kern.o always += syscall_tp_kern.o always += cpustat_kern.o +always += xdp_adjust_tail_kern.o +always += xdpsock_kern.o HOSTCFLAGS += -I$(objtree)/usr/include HOSTCFLAGS += -I$(srctree)/tools/lib/ @@ -193,6 +199,8 @@ HOSTLOADLIBES_xdp_monitor += -lelf HOSTLOADLIBES_xdp_rxq_info += -lelf HOSTLOADLIBES_syscall_tp += -lelf HOSTLOADLIBES_cpustat += -lelf +HOSTLOADLIBES_xdp_adjust_tail += -lelf +HOSTLOADLIBES_xdpsock += -lelf -pthread # Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: # make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang diff --git a/samples/bpf/bpf_load.c b/samples/bpf/bpf_load.c index bebe4188b4b3..da9bccfaf391 100644 --- a/samples/bpf/bpf_load.c +++ b/samples/bpf/bpf_load.c @@ -145,6 +145,9 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) } if (is_kprobe || is_kretprobe) { + bool need_normal_check = true; + const char *event_prefix = ""; + if (is_kprobe) event += 7; else @@ -158,18 +161,33 @@ static int load_and_attach(const char *event, struct bpf_insn *prog, int size) if (isdigit(*event)) return populate_prog_array(event, fd); - snprintf(buf, sizeof(buf), - "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events", - is_kprobe ? 'p' : 'r', event, event); - err = system(buf); - if (err < 0) { - printf("failed to create kprobe '%s' error '%s'\n", - event, strerror(errno)); - return -1; +#ifdef __x86_64__ + if (strncmp(event, "sys_", 4) == 0) { + snprintf(buf, sizeof(buf), + "echo '%c:__x64_%s __x64_%s' >> /sys/kernel/debug/tracing/kprobe_events", + is_kprobe ? 'p' : 'r', event, event); + err = system(buf); + if (err >= 0) { + need_normal_check = false; + event_prefix = "__x64_"; + } + } +#endif + if (need_normal_check) { + snprintf(buf, sizeof(buf), + "echo '%c:%s %s' >> /sys/kernel/debug/tracing/kprobe_events", + is_kprobe ? 'p' : 'r', event, event); + err = system(buf); + if (err < 0) { + printf("failed to create kprobe '%s' error '%s'\n", + event, strerror(errno)); + return -1; + } } strcpy(buf, DEBUGFS); strcat(buf, "events/kprobes/"); + strcat(buf, event_prefix); strcat(buf, event); strcat(buf, "/id"); } else if (is_tracepoint) { @@ -549,7 +567,6 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) if (nr_maps < 0) { printf("Error: Failed loading ELF maps (errno:%d):%s\n", nr_maps, strerror(-nr_maps)); - ret = 1; goto done; } if (load_maps(map_data, nr_maps, fixup_map)) @@ -615,7 +632,6 @@ static int do_load_bpf_file(const char *path, fixup_map_cb fixup_map) } } - ret = 0; done: close(fd); return ret; @@ -650,66 +666,3 @@ void read_trace_pipe(void) } } } - -#define MAX_SYMS 300000 -static struct ksym syms[MAX_SYMS]; -static int sym_cnt; - -static int ksym_cmp(const void *p1, const void *p2) -{ - return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; -} - -int load_kallsyms(void) -{ - FILE *f = fopen("/proc/kallsyms", "r"); - char func[256], buf[256]; - char symbol; - void *addr; - int i = 0; - - if (!f) - return -ENOENT; - - while (!feof(f)) { - if (!fgets(buf, sizeof(buf), f)) - break; - if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) - break; - if (!addr) - continue; - syms[i].addr = (long) addr; - syms[i].name = strdup(func); - i++; - } - sym_cnt = i; - qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); - return 0; -} - -struct ksym *ksym_search(long key) -{ - int start = 0, end = sym_cnt; - int result; - - while (start < end) { - size_t mid = start + (end - start) / 2; - - result = key - syms[mid].addr; - if (result < 0) - end = mid; - else if (result > 0) - start = mid + 1; - else - return &syms[mid]; - } - - if (start >= 1 && syms[start - 1].addr < key && - key < syms[start].addr) - /* valid ksym */ - return &syms[start - 1]; - - /* out of range. return _stext */ - return &syms[0]; -} - diff --git a/samples/bpf/bpf_load.h b/samples/bpf/bpf_load.h index 453c200b389b..2c3d0b448632 100644 --- a/samples/bpf/bpf_load.h +++ b/samples/bpf/bpf_load.h @@ -54,12 +54,5 @@ int load_bpf_file(char *path); int load_bpf_file_fixup_map(const char *path, fixup_map_cb fixup_map); void read_trace_pipe(void); -struct ksym { - long addr; - char *name; -}; - -int load_kallsyms(void); -struct ksym *ksym_search(long key); int bpf_set_link_xdp_fd(int ifindex, int fd, __u32 flags); #endif diff --git a/samples/bpf/offwaketime_user.c b/samples/bpf/offwaketime_user.c index 512f87a5fd20..f06063af9fcb 100644 --- a/samples/bpf/offwaketime_user.c +++ b/samples/bpf/offwaketime_user.c @@ -17,6 +17,7 @@ #include <sys/resource.h> #include "libbpf.h" #include "bpf_load.h" +#include "trace_helpers.h" #define PRINT_RAW_ADDR 0 diff --git a/samples/bpf/sampleip_user.c b/samples/bpf/sampleip_user.c index 4ed690b907ff..60c2b73d1b4d 100644 --- a/samples/bpf/sampleip_user.c +++ b/samples/bpf/sampleip_user.c @@ -22,6 +22,7 @@ #include "libbpf.h" #include "bpf_load.h" #include "perf-sys.h" +#include "trace_helpers.h" #define DEFAULT_FREQ 99 #define DEFAULT_SECS 5 diff --git a/samples/bpf/sock_example.c b/samples/bpf/sock_example.c index 6fc6e193ef1b..33a637507c00 100644 --- a/samples/bpf/sock_example.c +++ b/samples/bpf/sock_example.c @@ -9,10 +9,10 @@ * if (value) * (*(u64*)value) += 1; * - * - attaches this program to eth0 raw socket + * - attaches this program to loopback interface "lo" raw socket * * - every second user space reads map[tcp], map[udp], map[icmp] to see - * how many packets of given protocol were seen on eth0 + * how many packets of given protocol were seen on "lo" */ #include <stdio.h> #include <unistd.h> diff --git a/samples/bpf/spintest_user.c b/samples/bpf/spintest_user.c index 3d736219a31c..8d3e9cfa1909 100644 --- a/samples/bpf/spintest_user.c +++ b/samples/bpf/spintest_user.c @@ -7,6 +7,7 @@ #include <sys/resource.h> #include "libbpf.h" #include "bpf_load.h" +#include "trace_helpers.h" int main(int ac, char **argv) { diff --git a/samples/bpf/test_tunnel_bpf.sh b/samples/bpf/test_tunnel_bpf.sh deleted file mode 100755 index c265863ccdf9..000000000000 --- a/samples/bpf/test_tunnel_bpf.sh +++ /dev/null @@ -1,319 +0,0 @@ -#!/bin/bash -# SPDX-License-Identifier: GPL-2.0 -# In Namespace 0 (at_ns0) using native tunnel -# Overlay IP: 10.1.1.100 -# local 192.16.1.100 remote 192.16.1.200 -# veth0 IP: 172.16.1.100, tunnel dev <type>00 - -# Out of Namespace using BPF set/get on lwtunnel -# Overlay IP: 10.1.1.200 -# local 172.16.1.200 remote 172.16.1.100 -# veth1 IP: 172.16.1.200, tunnel dev <type>11 - -function config_device { - ip netns add at_ns0 - ip link add veth0 type veth peer name veth1 - ip link set veth0 netns at_ns0 - ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip link set dev veth1 up mtu 1500 - ip addr add dev veth1 172.16.1.200/24 -} - -function add_gre_tunnel { - # in namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local 172.16.1.100 remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # out of namespace - ip link add dev $DEV type $TYPE key 2 external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -function add_ip6gretap_tunnel { - - # assign ipv6 address - ip netns exec at_ns0 ip addr add ::11/96 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip addr add dev veth1 ::22/96 - ip link set dev veth1 up - - # in namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \ - local ::11 remote ::22 - - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96 - ip netns exec at_ns0 ip link set dev $DEV_NS up - - # out of namespace - ip link add dev $DEV type $TYPE external - ip addr add dev $DEV 10.1.1.200/24 - ip addr add dev $DEV fc80::200/24 - ip link set dev $DEV up -} - -function add_erspan_tunnel { - # in namespace - if [ "$1" == "v1" ]; then - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local 172.16.1.100 remote 172.16.1.200 \ - erspan_ver 1 erspan 123 - else - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local 172.16.1.100 remote 172.16.1.200 \ - erspan_ver 2 erspan_dir egress erspan_hwid 3 - fi - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # out of namespace - ip link add dev $DEV type $TYPE external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -function add_ip6erspan_tunnel { - - # assign ipv6 address - ip netns exec at_ns0 ip addr add ::11/96 dev veth0 - ip netns exec at_ns0 ip link set dev veth0 up - ip addr add dev veth1 ::22/96 - ip link set dev veth1 up - - # in namespace - if [ "$1" == "v1" ]; then - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local ::11 remote ::22 \ - erspan_ver 1 erspan 123 - else - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE seq key 2 \ - local ::11 remote ::22 \ - erspan_ver 2 erspan_dir egress erspan_hwid 7 - fi - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 ip link set dev $DEV_NS up - - # out of namespace - ip link add dev $DEV type $TYPE external - ip addr add dev $DEV 10.1.1.200/24 - ip link set dev $DEV up -} - -function add_vxlan_tunnel { - # Set static ARP entry here because iptables set-mark works - # on L3 packet, as a result not applying to ARP packets, - # causing errors at get_tunnel_{key/opt}. - - # in namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE id 2 dstport 4789 gbp remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS address 52:54:00:d9:01:00 up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 - ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF - - # out of namespace - ip link add dev $DEV type $TYPE external gbp dstport 4789 - ip link set dev $DEV address 52:54:00:d9:02:00 up - ip addr add dev $DEV 10.1.1.200/24 - arp -s 10.1.1.100 52:54:00:d9:01:00 -} - -function add_geneve_tunnel { - # in namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE id 2 dstport 6081 remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # out of namespace - ip link add dev $DEV type $TYPE dstport 6081 external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -function add_ipip_tunnel { - # in namespace - ip netns exec at_ns0 \ - ip link add dev $DEV_NS type $TYPE local 172.16.1.100 remote 172.16.1.200 - ip netns exec at_ns0 ip link set dev $DEV_NS up - ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 - - # out of namespace - ip link add dev $DEV type $TYPE external - ip link set dev $DEV up - ip addr add dev $DEV 10.1.1.200/24 -} - -function attach_bpf { - DEV=$1 - SET_TUNNEL=$2 - GET_TUNNEL=$3 - tc qdisc add dev $DEV clsact - tc filter add dev $DEV egress bpf da obj tcbpf2_kern.o sec $SET_TUNNEL - tc filter add dev $DEV ingress bpf da obj tcbpf2_kern.o sec $GET_TUNNEL -} - -function test_gre { - TYPE=gretap - DEV_NS=gretap00 - DEV=gretap11 - config_device - add_gre_tunnel - attach_bpf $DEV gre_set_tunnel gre_get_tunnel - ping -c 1 10.1.1.100 - ip netns exec at_ns0 ping -c 1 10.1.1.200 - cleanup -} - -function test_ip6gre { - TYPE=ip6gre - DEV_NS=ip6gre00 - DEV=ip6gre11 - config_device - # reuse the ip6gretap function - add_ip6gretap_tunnel - attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel - # underlay - ping6 -c 4 ::11 - # overlay: ipv4 over ipv6 - ip netns exec at_ns0 ping -c 1 10.1.1.200 - ping -c 1 10.1.1.100 - # overlay: ipv6 over ipv6 - ip netns exec at_ns0 ping6 -c 1 fc80::200 - cleanup -} - -function test_ip6gretap { - TYPE=ip6gretap - DEV_NS=ip6gretap00 - DEV=ip6gretap11 - config_device - add_ip6gretap_tunnel - attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel - # underlay - ping6 -c 4 ::11 - # overlay: ipv4 over ipv6 - ip netns exec at_ns0 ping -i .2 -c 1 10.1.1.200 - ping -c 1 10.1.1.100 - # overlay: ipv6 over ipv6 - ip netns exec at_ns0 ping6 -c 1 fc80::200 - cleanup -} - -function test_erspan { - TYPE=erspan - DEV_NS=erspan00 - DEV=erspan11 - config_device - add_erspan_tunnel $1 - attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel - ping -c 1 10.1.1.100 - ip netns exec at_ns0 ping -c 1 10.1.1.200 - cleanup -} - -function test_ip6erspan { - TYPE=ip6erspan - DEV_NS=ip6erspan00 - DEV=ip6erspan11 - config_device - add_ip6erspan_tunnel $1 - attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel - ping6 -c 3 ::11 - ip netns exec at_ns0 ping -c 1 10.1.1.200 - cleanup -} - -function test_vxlan { - TYPE=vxlan - DEV_NS=vxlan00 - DEV=vxlan11 - config_device - add_vxlan_tunnel - attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel - ping -c 1 10.1.1.100 - ip netns exec at_ns0 ping -c 1 10.1.1.200 - cleanup -} - -function test_geneve { - TYPE=geneve - DEV_NS=geneve00 - DEV=geneve11 - config_device - add_geneve_tunnel - attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel - ping -c 1 10.1.1.100 - ip netns exec at_ns0 ping -c 1 10.1.1.200 - cleanup -} - -function test_ipip { - TYPE=ipip - DEV_NS=ipip00 - DEV=ipip11 - config_device - tcpdump -nei veth1 & - cat /sys/kernel/debug/tracing/trace_pipe & - add_ipip_tunnel - ethtool -K veth1 gso off gro off rx off tx off - ip link set dev veth1 mtu 1500 - attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel - ping -c 1 10.1.1.100 - ip netns exec at_ns0 ping -c 1 10.1.1.200 - ip netns exec at_ns0 iperf -sD -p 5200 > /dev/null - sleep 0.2 - iperf -c 10.1.1.100 -n 5k -p 5200 - cleanup -} - -function cleanup { - set +ex - pkill iperf - ip netns delete at_ns0 - ip link del veth1 - ip link del ipip11 - ip link del gretap11 - ip link del ip6gre11 - ip link del ip6gretap11 - ip link del vxlan11 - ip link del geneve11 - ip link del erspan11 - ip link del ip6erspan11 - pkill tcpdump - pkill cat - set -ex -} - -trap cleanup 0 2 3 6 9 -cleanup -echo "Testing GRE tunnel..." -test_gre -echo "Testing IP6GRE tunnel..." -test_ip6gre -echo "Testing IP6GRETAP tunnel..." -test_ip6gretap -echo "Testing ERSPAN tunnel..." -test_erspan v1 -test_erspan v2 -echo "Testing IP6ERSPAN tunnel..." -test_ip6erspan v1 -test_ip6erspan v2 -echo "Testing VXLAN tunnel..." -test_vxlan -echo "Testing GENEVE tunnel..." -test_geneve -echo "Testing IPIP tunnel..." -test_ipip -echo "*** PASS ***" diff --git a/samples/bpf/trace_event_user.c b/samples/bpf/trace_event_user.c index 56f7a259a7c9..1fa1becfa641 100644 --- a/samples/bpf/trace_event_user.c +++ b/samples/bpf/trace_event_user.c @@ -21,6 +21,7 @@ #include "libbpf.h" #include "bpf_load.h" #include "perf-sys.h" +#include "trace_helpers.h" #define SAMPLE_FREQ 50 diff --git a/samples/bpf/trace_output_user.c b/samples/bpf/trace_output_user.c index ccca1e348017..5e78c2ecd08d 100644 --- a/samples/bpf/trace_output_user.c +++ b/samples/bpf/trace_output_user.c @@ -21,100 +21,10 @@ #include "libbpf.h" #include "bpf_load.h" #include "perf-sys.h" +#include "trace_helpers.h" static int pmu_fd; -int page_size; -int page_cnt = 8; -volatile struct perf_event_mmap_page *header; - -typedef void (*print_fn)(void *data, int size); - -static int perf_event_mmap(int fd) -{ - void *base; - int mmap_size; - - page_size = getpagesize(); - mmap_size = page_size * (page_cnt + 1); - - base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); - if (base == MAP_FAILED) { - printf("mmap err\n"); - return -1; - } - - header = base; - return 0; -} - -static int perf_event_poll(int fd) -{ - struct pollfd pfd = { .fd = fd, .events = POLLIN }; - - return poll(&pfd, 1, 1000); -} - -struct perf_event_sample { - struct perf_event_header header; - __u32 size; - char data[]; -}; - -static void perf_event_read(print_fn fn) -{ - __u64 data_tail = header->data_tail; - __u64 data_head = header->data_head; - __u64 buffer_size = page_cnt * page_size; - void *base, *begin, *end; - char buf[256]; - - asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ - if (data_head == data_tail) - return; - - base = ((char *)header) + page_size; - - begin = base + data_tail % buffer_size; - end = base + data_head % buffer_size; - - while (begin != end) { - struct perf_event_sample *e; - - e = begin; - if (begin + e->header.size > base + buffer_size) { - long len = base + buffer_size - begin; - - assert(len < e->header.size); - memcpy(buf, begin, len); - memcpy(buf + len, base, e->header.size - len); - e = (void *) buf; - begin = base + e->header.size - len; - } else if (begin + e->header.size == base + buffer_size) { - begin = base; - } else { - begin += e->header.size; - } - - if (e->header.type == PERF_RECORD_SAMPLE) { - fn(e->data, e->size); - } else if (e->header.type == PERF_RECORD_LOST) { - struct { - struct perf_event_header header; - __u64 id; - __u64 lost; - } *lost = (void *) e; - printf("lost %lld events\n", lost->lost); - } else { - printf("unknown event type=%d size=%d\n", - e->header.type, e->header.size); - } - } - - __sync_synchronize(); /* smp_mb() */ - header->data_tail = data_head; -} - static __u64 time_get_ns(void) { struct timespec ts; @@ -127,7 +37,7 @@ static __u64 start_time; #define MAX_CNT 100000ll -static void print_bpf_output(void *data, int size) +static int print_bpf_output(void *data, int size) { static __u64 cnt; struct { @@ -138,7 +48,7 @@ static void print_bpf_output(void *data, int size) if (e->cookie != 0x12345678) { printf("BUG pid %llx cookie %llx sized %d\n", e->pid, e->cookie, size); - kill(0, SIGINT); + return PERF_EVENT_ERROR; } cnt++; @@ -146,8 +56,10 @@ static void print_bpf_output(void *data, int size) if (cnt == MAX_CNT) { printf("recv %lld events per sec\n", MAX_CNT * 1000000000ll / (time_get_ns() - start_time)); - kill(0, SIGINT); + return PERF_EVENT_DONE; } + + return PERF_EVENT_CONT; } static void test_bpf_perf_event(void) @@ -170,6 +82,7 @@ int main(int argc, char **argv) { char filename[256]; FILE *f; + int ret; snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); @@ -187,10 +100,7 @@ int main(int argc, char **argv) (void) f; start_time = time_get_ns(); - for (;;) { - perf_event_poll(pmu_fd); - perf_event_read(print_bpf_output); - } - - return 0; + ret = perf_event_poller(pmu_fd, print_bpf_output); + kill(0, SIGINT); + return ret; } diff --git a/samples/bpf/xdp_adjust_tail_kern.c b/samples/bpf/xdp_adjust_tail_kern.c new file mode 100644 index 000000000000..411fdb21f8bc --- /dev/null +++ b/samples/bpf/xdp_adjust_tail_kern.c @@ -0,0 +1,152 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + * + * This program shows how to use bpf_xdp_adjust_tail() by + * generating ICMPv4 "packet to big" (unreachable/ df bit set frag needed + * to be more preice in case of v4)" where receiving packets bigger then + * 600 bytes. + */ +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include <linux/in.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/if_vlan.h> +#include <linux/ip.h> +#include <linux/icmp.h> +#include "bpf_helpers.h" + +#define DEFAULT_TTL 64 +#define MAX_PCKT_SIZE 600 +#define ICMP_TOOBIG_SIZE 98 +#define ICMP_TOOBIG_PAYLOAD_SIZE 92 + +struct bpf_map_def SEC("maps") icmpcnt = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64), + .max_entries = 1, +}; + +static __always_inline void count_icmp(void) +{ + u64 key = 0; + u64 *icmp_count; + + icmp_count = bpf_map_lookup_elem(&icmpcnt, &key); + if (icmp_count) + *icmp_count += 1; +} + +static __always_inline void swap_mac(void *data, struct ethhdr *orig_eth) +{ + struct ethhdr *eth; + + eth = data; + memcpy(eth->h_source, orig_eth->h_dest, ETH_ALEN); + memcpy(eth->h_dest, orig_eth->h_source, ETH_ALEN); + eth->h_proto = orig_eth->h_proto; +} + +static __always_inline __u16 csum_fold_helper(__u32 csum) +{ + return ~((csum & 0xffff) + (csum >> 16)); +} + +static __always_inline void ipv4_csum(void *data_start, int data_size, + __u32 *csum) +{ + *csum = bpf_csum_diff(0, 0, data_start, data_size, *csum); + *csum = csum_fold_helper(*csum); +} + +static __always_inline int send_icmp4_too_big(struct xdp_md *xdp) +{ + int headroom = (int)sizeof(struct iphdr) + (int)sizeof(struct icmphdr); + + if (bpf_xdp_adjust_head(xdp, 0 - headroom)) + return XDP_DROP; + void *data = (void *)(long)xdp->data; + void *data_end = (void *)(long)xdp->data_end; + + if (data + (ICMP_TOOBIG_SIZE + headroom) > data_end) + return XDP_DROP; + + struct iphdr *iph, *orig_iph; + struct icmphdr *icmp_hdr; + struct ethhdr *orig_eth; + __u32 csum = 0; + __u64 off = 0; + + orig_eth = data + headroom; + swap_mac(data, orig_eth); + off += sizeof(struct ethhdr); + iph = data + off; + off += sizeof(struct iphdr); + icmp_hdr = data + off; + off += sizeof(struct icmphdr); + orig_iph = data + off; + icmp_hdr->type = ICMP_DEST_UNREACH; + icmp_hdr->code = ICMP_FRAG_NEEDED; + icmp_hdr->un.frag.mtu = htons(MAX_PCKT_SIZE-sizeof(struct ethhdr)); + icmp_hdr->checksum = 0; + ipv4_csum(icmp_hdr, ICMP_TOOBIG_PAYLOAD_SIZE, &csum); + icmp_hdr->checksum = csum; + iph->ttl = DEFAULT_TTL; + iph->daddr = orig_iph->saddr; + iph->saddr = orig_iph->daddr; + iph->version = 4; + iph->ihl = 5; + iph->protocol = IPPROTO_ICMP; + iph->tos = 0; + iph->tot_len = htons( + ICMP_TOOBIG_SIZE + headroom - sizeof(struct ethhdr)); + iph->check = 0; + csum = 0; + ipv4_csum(iph, sizeof(struct iphdr), &csum); + iph->check = csum; + count_icmp(); + return XDP_TX; +} + + +static __always_inline int handle_ipv4(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + int pckt_size = data_end - data; + int offset; + + if (pckt_size > MAX_PCKT_SIZE) { + offset = pckt_size - ICMP_TOOBIG_SIZE; + if (bpf_xdp_adjust_tail(xdp, 0 - offset)) + return XDP_PASS; + return send_icmp4_too_big(xdp); + } + return XDP_PASS; +} + +SEC("xdp_icmp") +int _xdp_icmp(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + struct ethhdr *eth = data; + __u16 h_proto; + + if (eth + 1 > data_end) + return XDP_DROP; + + h_proto = eth->h_proto; + + if (h_proto == htons(ETH_P_IP)) + return handle_ipv4(xdp); + else + return XDP_PASS; +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdp_adjust_tail_user.c b/samples/bpf/xdp_adjust_tail_user.c new file mode 100644 index 000000000000..f621a541b574 --- /dev/null +++ b/samples/bpf/xdp_adjust_tail_user.c @@ -0,0 +1,142 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <assert.h> +#include <errno.h> +#include <signal.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/resource.h> +#include <arpa/inet.h> +#include <netinet/ether.h> +#include <unistd.h> +#include <time.h> +#include "bpf_load.h" +#include "libbpf.h" +#include "bpf_util.h" + +#define STATS_INTERVAL_S 2U + +static int ifindex = -1; +static __u32 xdp_flags; + +static void int_exit(int sig) +{ + if (ifindex > -1) + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + exit(0); +} + +/* simple "icmp packet too big sent" counter + */ +static void poll_stats(unsigned int kill_after_s) +{ + time_t started_at = time(NULL); + __u64 value = 0; + int key = 0; + + + while (!kill_after_s || time(NULL) - started_at <= kill_after_s) { + sleep(STATS_INTERVAL_S); + + assert(bpf_map_lookup_elem(map_fd[0], &key, &value) == 0); + + printf("icmp \"packet too big\" sent: %10llu pkts\n", value); + } +} + +static void usage(const char *cmd) +{ + printf("Start a XDP prog which send ICMP \"packet too big\" \n" + "messages if ingress packet is bigger then MAX_SIZE bytes\n"); + printf("Usage: %s [...]\n", cmd); + printf(" -i <ifindex> Interface Index\n"); + printf(" -T <stop-after-X-seconds> Default: 0 (forever)\n"); + printf(" -S use skb-mode\n"); + printf(" -N enforce native mode\n"); + printf(" -h Display this help\n"); +} + +int main(int argc, char **argv) +{ + unsigned char opt_flags[256] = {}; + unsigned int kill_after_s = 0; + const char *optstr = "i:T:SNh"; + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char filename[256]; + int opt; + int i; + + + for (i = 0; i < strlen(optstr); i++) + if (optstr[i] != 'h' && 'a' <= optstr[i] && optstr[i] <= 'z') + opt_flags[(unsigned char)optstr[i]] = 1; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + + switch (opt) { + case 'i': + ifindex = atoi(optarg); + break; + case 'T': + kill_after_s = atoi(optarg); + break; + case 'S': + xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + xdp_flags |= XDP_FLAGS_DRV_MODE; + break; + default: + usage(argv[0]); + return 1; + } + opt_flags[opt] = 0; + } + + for (i = 0; i < strlen(optstr); i++) { + if (opt_flags[(unsigned int)optstr[i]]) { + fprintf(stderr, "Missing argument -%c\n", optstr[i]); + usage(argv[0]); + return 1; + } + } + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK, RLIM_INFINITY)"); + return 1; + } + + snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); + + if (load_bpf_file(filename)) { + printf("%s", bpf_log_buf); + return 1; + } + + if (!prog_fd[0]) { + printf("load_bpf_file: %s\n", strerror(errno)); + return 1; + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + + if (bpf_set_link_xdp_fd(ifindex, prog_fd[0], xdp_flags) < 0) { + printf("link set xdp fd failed\n"); + return 1; + } + + poll_stats(kill_after_s); + + bpf_set_link_xdp_fd(ifindex, -1, xdp_flags); + + return 0; +} diff --git a/samples/bpf/xdp_monitor_user.c b/samples/bpf/xdp_monitor_user.c index eec14520d513..894bc64c2cac 100644 --- a/samples/bpf/xdp_monitor_user.c +++ b/samples/bpf/xdp_monitor_user.c @@ -330,7 +330,7 @@ static void stats_print(struct stats_record *stats_rec, pps = calc_pps_u64(r, p, t); if (pps > 0) printf(fmt1, "Exception", i, - 0.0, pps, err2str(rec_i)); + 0.0, pps, action2str(rec_i)); } pps = calc_pps_u64(&rec->total, &prev->total, t); if (pps > 0) diff --git a/samples/bpf/xdpsock.h b/samples/bpf/xdpsock.h new file mode 100644 index 000000000000..533ab81adfa1 --- /dev/null +++ b/samples/bpf/xdpsock.h @@ -0,0 +1,11 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef XDPSOCK_H_ +#define XDPSOCK_H_ + +/* Power-of-2 number of sockets */ +#define MAX_SOCKS 4 + +/* Round-robin receive */ +#define RR_LB 0 + +#endif /* XDPSOCK_H_ */ diff --git a/samples/bpf/xdpsock_kern.c b/samples/bpf/xdpsock_kern.c new file mode 100644 index 000000000000..d8806c41362e --- /dev/null +++ b/samples/bpf/xdpsock_kern.c @@ -0,0 +1,56 @@ +// SPDX-License-Identifier: GPL-2.0 +#define KBUILD_MODNAME "foo" +#include <uapi/linux/bpf.h> +#include "bpf_helpers.h" + +#include "xdpsock.h" + +struct bpf_map_def SEC("maps") qidconf_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 1, +}; + +struct bpf_map_def SEC("maps") xsks_map = { + .type = BPF_MAP_TYPE_XSKMAP, + .key_size = sizeof(int), + .value_size = sizeof(int), + .max_entries = 4, +}; + +struct bpf_map_def SEC("maps") rr_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(unsigned int), + .max_entries = 1, +}; + +SEC("xdp_sock") +int xdp_sock_prog(struct xdp_md *ctx) +{ + int *qidconf, key = 0, idx; + unsigned int *rr; + + qidconf = bpf_map_lookup_elem(&qidconf_map, &key); + if (!qidconf) + return XDP_ABORTED; + + if (*qidconf != ctx->rx_queue_index) + return XDP_PASS; + +#if RR_LB /* NB! RR_LB is configured in xdpsock.h */ + rr = bpf_map_lookup_elem(&rr_map, &key); + if (!rr) + return XDP_ABORTED; + + *rr = (*rr + 1) & (MAX_SOCKS - 1); + idx = *rr; +#else + idx = 0; +#endif + + return bpf_redirect_map(&xsks_map, idx, 0); +} + +char _license[] SEC("license") = "GPL"; diff --git a/samples/bpf/xdpsock_user.c b/samples/bpf/xdpsock_user.c new file mode 100644 index 000000000000..4b8a7cf3e63b --- /dev/null +++ b/samples/bpf/xdpsock_user.c @@ -0,0 +1,948 @@ +// SPDX-License-Identifier: GPL-2.0 +/* Copyright(c) 2017 - 2018 Intel Corporation. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + */ + +#include <assert.h> +#include <errno.h> +#include <getopt.h> +#include <libgen.h> +#include <linux/bpf.h> +#include <linux/if_link.h> +#include <linux/if_xdp.h> +#include <linux/if_ether.h> +#include <net/if.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <net/ethernet.h> +#include <sys/resource.h> +#include <sys/socket.h> +#include <sys/mman.h> +#include <time.h> +#include <unistd.h> +#include <pthread.h> +#include <locale.h> +#include <sys/types.h> +#include <poll.h> + +#include "bpf_load.h" +#include "bpf_util.h" +#include "libbpf.h" + +#include "xdpsock.h" + +#ifndef SOL_XDP +#define SOL_XDP 283 +#endif + +#ifndef AF_XDP +#define AF_XDP 44 +#endif + +#ifndef PF_XDP +#define PF_XDP AF_XDP +#endif + +#define NUM_FRAMES 131072 +#define FRAME_HEADROOM 0 +#define FRAME_SIZE 2048 +#define NUM_DESCS 1024 +#define BATCH_SIZE 16 + +#define FQ_NUM_DESCS 1024 +#define CQ_NUM_DESCS 1024 + +#define DEBUG_HEXDUMP 0 + +typedef __u32 u32; + +static unsigned long prev_time; + +enum benchmark_type { + BENCH_RXDROP = 0, + BENCH_TXONLY = 1, + BENCH_L2FWD = 2, +}; + +static enum benchmark_type opt_bench = BENCH_RXDROP; +static u32 opt_xdp_flags; +static const char *opt_if = ""; +static int opt_ifindex; +static int opt_queue; +static int opt_poll; +static int opt_shared_packet_buffer; +static int opt_interval = 1; + +struct xdp_umem_uqueue { + u32 cached_prod; + u32 cached_cons; + u32 mask; + u32 size; + struct xdp_umem_ring *ring; +}; + +struct xdp_umem { + char (*frames)[FRAME_SIZE]; + struct xdp_umem_uqueue fq; + struct xdp_umem_uqueue cq; + int fd; +}; + +struct xdp_uqueue { + u32 cached_prod; + u32 cached_cons; + u32 mask; + u32 size; + struct xdp_rxtx_ring *ring; +}; + +struct xdpsock { + struct xdp_uqueue rx; + struct xdp_uqueue tx; + int sfd; + struct xdp_umem *umem; + u32 outstanding_tx; + unsigned long rx_npkts; + unsigned long tx_npkts; + unsigned long prev_rx_npkts; + unsigned long prev_tx_npkts; +}; + +#define MAX_SOCKS 4 +static int num_socks; +struct xdpsock *xsks[MAX_SOCKS]; + +static unsigned long get_nsecs(void) +{ + struct timespec ts; + + clock_gettime(CLOCK_MONOTONIC, &ts); + return ts.tv_sec * 1000000000UL + ts.tv_nsec; +} + +static void dump_stats(void); + +#define lassert(expr) \ + do { \ + if (!(expr)) { \ + fprintf(stderr, "%s:%s:%i: Assertion failed: " \ + #expr ": errno: %d/\"%s\"\n", \ + __FILE__, __func__, __LINE__, \ + errno, strerror(errno)); \ + dump_stats(); \ + exit(EXIT_FAILURE); \ + } \ + } while (0) + +#define barrier() __asm__ __volatile__("": : :"memory") +#define u_smp_rmb() barrier() +#define u_smp_wmb() barrier() +#define likely(x) __builtin_expect(!!(x), 1) +#define unlikely(x) __builtin_expect(!!(x), 0) + +static const char pkt_data[] = + "\x3c\xfd\xfe\x9e\x7f\x71\xec\xb1\xd7\x98\x3a\xc0\x08\x00\x45\x00" + "\x00\x2e\x00\x00\x00\x00\x40\x11\x88\x97\x05\x08\x07\x08\xc8\x14" + "\x1e\x04\x10\x92\x10\x92\x00\x1a\x6d\xa3\x34\x33\x1f\x69\x40\x6b" + "\x54\x59\xb6\x14\x2d\x11\x44\xbf\xaf\xd9\xbe\xaa"; + +static inline u32 umem_nb_free(struct xdp_umem_uqueue *q, u32 nb) +{ + u32 free_entries = q->size - (q->cached_prod - q->cached_cons); + + if (free_entries >= nb) + return free_entries; + + /* Refresh the local tail pointer */ + q->cached_cons = q->ring->ptrs.consumer; + + return q->size - (q->cached_prod - q->cached_cons); +} + +static inline u32 xq_nb_free(struct xdp_uqueue *q, u32 ndescs) +{ + u32 free_entries = q->cached_cons - q->cached_prod; + + if (free_entries >= ndescs) + return free_entries; + + /* Refresh the local tail pointer */ + q->cached_cons = q->ring->ptrs.consumer + q->size; + return q->cached_cons - q->cached_prod; +} + +static inline u32 umem_nb_avail(struct xdp_umem_uqueue *q, u32 nb) +{ + u32 entries = q->cached_prod - q->cached_cons; + + if (entries == 0) { + q->cached_prod = q->ring->ptrs.producer; + entries = q->cached_prod - q->cached_cons; + } + + return (entries > nb) ? nb : entries; +} + +static inline u32 xq_nb_avail(struct xdp_uqueue *q, u32 ndescs) +{ + u32 entries = q->cached_prod - q->cached_cons; + + if (entries == 0) { + q->cached_prod = q->ring->ptrs.producer; + entries = q->cached_prod - q->cached_cons; + } + + return (entries > ndescs) ? ndescs : entries; +} + +static inline int umem_fill_to_kernel_ex(struct xdp_umem_uqueue *fq, + struct xdp_desc *d, + size_t nb) +{ + u32 i; + + if (umem_nb_free(fq, nb) < nb) + return -ENOSPC; + + for (i = 0; i < nb; i++) { + u32 idx = fq->cached_prod++ & fq->mask; + + fq->ring->desc[idx] = d[i].idx; + } + + u_smp_wmb(); + + fq->ring->ptrs.producer = fq->cached_prod; + + return 0; +} + +static inline int umem_fill_to_kernel(struct xdp_umem_uqueue *fq, u32 *d, + size_t nb) +{ + u32 i; + + if (umem_nb_free(fq, nb) < nb) + return -ENOSPC; + + for (i = 0; i < nb; i++) { + u32 idx = fq->cached_prod++ & fq->mask; + + fq->ring->desc[idx] = d[i]; + } + + u_smp_wmb(); + + fq->ring->ptrs.producer = fq->cached_prod; + + return 0; +} + +static inline size_t umem_complete_from_kernel(struct xdp_umem_uqueue *cq, + u32 *d, size_t nb) +{ + u32 idx, i, entries = umem_nb_avail(cq, nb); + + u_smp_rmb(); + + for (i = 0; i < entries; i++) { + idx = cq->cached_cons++ & cq->mask; + d[i] = cq->ring->desc[idx]; + } + + if (entries > 0) { + u_smp_wmb(); + + cq->ring->ptrs.consumer = cq->cached_cons; + } + + return entries; +} + +static inline void *xq_get_data(struct xdpsock *xsk, __u32 idx, __u32 off) +{ + lassert(idx < NUM_FRAMES); + return &xsk->umem->frames[idx][off]; +} + +static inline int xq_enq(struct xdp_uqueue *uq, + const struct xdp_desc *descs, + unsigned int ndescs) +{ + struct xdp_rxtx_ring *r = uq->ring; + unsigned int i; + + if (xq_nb_free(uq, ndescs) < ndescs) + return -ENOSPC; + + for (i = 0; i < ndescs; i++) { + u32 idx = uq->cached_prod++ & uq->mask; + + r->desc[idx].idx = descs[i].idx; + r->desc[idx].len = descs[i].len; + r->desc[idx].offset = descs[i].offset; + } + + u_smp_wmb(); + + r->ptrs.producer = uq->cached_prod; + return 0; +} + +static inline int xq_enq_tx_only(struct xdp_uqueue *uq, + __u32 idx, unsigned int ndescs) +{ + struct xdp_rxtx_ring *q = uq->ring; + unsigned int i; + + if (xq_nb_free(uq, ndescs) < ndescs) + return -ENOSPC; + + for (i = 0; i < ndescs; i++) { + u32 idx = uq->cached_prod++ & uq->mask; + + q->desc[idx].idx = idx + i; + q->desc[idx].len = sizeof(pkt_data) - 1; + q->desc[idx].offset = 0; + } + + u_smp_wmb(); + + q->ptrs.producer = uq->cached_prod; + return 0; +} + +static inline int xq_deq(struct xdp_uqueue *uq, + struct xdp_desc *descs, + int ndescs) +{ + struct xdp_rxtx_ring *r = uq->ring; + unsigned int idx; + int i, entries; + + entries = xq_nb_avail(uq, ndescs); + + u_smp_rmb(); + + for (i = 0; i < entries; i++) { + idx = uq->cached_cons++ & uq->mask; + descs[i] = r->desc[idx]; + } + + if (entries > 0) { + u_smp_wmb(); + + r->ptrs.consumer = uq->cached_cons; + } + + return entries; +} + +static void swap_mac_addresses(void *data) +{ + struct ether_header *eth = (struct ether_header *)data; + struct ether_addr *src_addr = (struct ether_addr *)ð->ether_shost; + struct ether_addr *dst_addr = (struct ether_addr *)ð->ether_dhost; + struct ether_addr tmp; + + tmp = *src_addr; + *src_addr = *dst_addr; + *dst_addr = tmp; +} + +#if DEBUG_HEXDUMP +static void hex_dump(void *pkt, size_t length, const char *prefix) +{ + int i = 0; + const unsigned char *address = (unsigned char *)pkt; + const unsigned char *line = address; + size_t line_size = 32; + unsigned char c; + + printf("length = %zu\n", length); + printf("%s | ", prefix); + while (length-- > 0) { + printf("%02X ", *address++); + if (!(++i % line_size) || (length == 0 && i % line_size)) { + if (length == 0) { + while (i++ % line_size) + printf("__ "); + } + printf(" | "); /* right close */ + while (line < address) { + c = *line++; + printf("%c", (c < 33 || c == 255) ? 0x2E : c); + } + printf("\n"); + if (length > 0) + printf("%s | ", prefix); + } + } + printf("\n"); +} +#endif + +static size_t gen_eth_frame(char *frame) +{ + memcpy(frame, pkt_data, sizeof(pkt_data) - 1); + return sizeof(pkt_data) - 1; +} + +static struct xdp_umem *xdp_umem_configure(int sfd) +{ + int fq_size = FQ_NUM_DESCS, cq_size = CQ_NUM_DESCS; + struct xdp_umem_reg mr; + struct xdp_umem *umem; + void *bufs; + + umem = calloc(1, sizeof(*umem)); + lassert(umem); + + lassert(posix_memalign(&bufs, getpagesize(), /* PAGE_SIZE aligned */ + NUM_FRAMES * FRAME_SIZE) == 0); + + mr.addr = (__u64)bufs; + mr.len = NUM_FRAMES * FRAME_SIZE; + mr.frame_size = FRAME_SIZE; + mr.frame_headroom = FRAME_HEADROOM; + + lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_REG, &mr, sizeof(mr)) == 0); + lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_FILL_RING, &fq_size, + sizeof(int)) == 0); + lassert(setsockopt(sfd, SOL_XDP, XDP_UMEM_COMPLETION_RING, &cq_size, + sizeof(int)) == 0); + + umem->fq.ring = mmap(0, sizeof(struct xdp_umem_ring) + + FQ_NUM_DESCS * sizeof(u32), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, sfd, + XDP_UMEM_PGOFF_FILL_RING); + lassert(umem->fq.ring != MAP_FAILED); + + umem->fq.mask = FQ_NUM_DESCS - 1; + umem->fq.size = FQ_NUM_DESCS; + + umem->cq.ring = mmap(0, sizeof(struct xdp_umem_ring) + + CQ_NUM_DESCS * sizeof(u32), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, sfd, + XDP_UMEM_PGOFF_COMPLETION_RING); + lassert(umem->cq.ring != MAP_FAILED); + + umem->cq.mask = CQ_NUM_DESCS - 1; + umem->cq.size = CQ_NUM_DESCS; + + umem->frames = (char (*)[FRAME_SIZE])bufs; + umem->fd = sfd; + + if (opt_bench == BENCH_TXONLY) { + int i; + + for (i = 0; i < NUM_FRAMES; i++) + (void)gen_eth_frame(&umem->frames[i][0]); + } + + return umem; +} + +static struct xdpsock *xsk_configure(struct xdp_umem *umem) +{ + struct sockaddr_xdp sxdp = {}; + int sfd, ndescs = NUM_DESCS; + struct xdpsock *xsk; + bool shared = true; + u32 i; + + sfd = socket(PF_XDP, SOCK_RAW, 0); + lassert(sfd >= 0); + + xsk = calloc(1, sizeof(*xsk)); + lassert(xsk); + + xsk->sfd = sfd; + xsk->outstanding_tx = 0; + + if (!umem) { + shared = false; + xsk->umem = xdp_umem_configure(sfd); + } else { + xsk->umem = umem; + } + + lassert(setsockopt(sfd, SOL_XDP, XDP_RX_RING, + &ndescs, sizeof(int)) == 0); + lassert(setsockopt(sfd, SOL_XDP, XDP_TX_RING, + &ndescs, sizeof(int)) == 0); + + /* Rx */ + xsk->rx.ring = mmap(NULL, + sizeof(struct xdp_ring) + + NUM_DESCS * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, sfd, + XDP_PGOFF_RX_RING); + lassert(xsk->rx.ring != MAP_FAILED); + + if (!shared) { + for (i = 0; i < NUM_DESCS / 2; i++) + lassert(umem_fill_to_kernel(&xsk->umem->fq, &i, 1) + == 0); + } + + /* Tx */ + xsk->tx.ring = mmap(NULL, + sizeof(struct xdp_ring) + + NUM_DESCS * sizeof(struct xdp_desc), + PROT_READ | PROT_WRITE, + MAP_SHARED | MAP_POPULATE, sfd, + XDP_PGOFF_TX_RING); + lassert(xsk->tx.ring != MAP_FAILED); + + xsk->rx.mask = NUM_DESCS - 1; + xsk->rx.size = NUM_DESCS; + + xsk->tx.mask = NUM_DESCS - 1; + xsk->tx.size = NUM_DESCS; + + sxdp.sxdp_family = PF_XDP; + sxdp.sxdp_ifindex = opt_ifindex; + sxdp.sxdp_queue_id = opt_queue; + if (shared) { + sxdp.sxdp_flags = XDP_SHARED_UMEM; + sxdp.sxdp_shared_umem_fd = umem->fd; + } + + lassert(bind(sfd, (struct sockaddr *)&sxdp, sizeof(sxdp)) == 0); + + return xsk; +} + +static void print_benchmark(bool running) +{ + const char *bench_str = "INVALID"; + + if (opt_bench == BENCH_RXDROP) + bench_str = "rxdrop"; + else if (opt_bench == BENCH_TXONLY) + bench_str = "txonly"; + else if (opt_bench == BENCH_L2FWD) + bench_str = "l2fwd"; + + printf("%s:%d %s ", opt_if, opt_queue, bench_str); + if (opt_xdp_flags & XDP_FLAGS_SKB_MODE) + printf("xdp-skb "); + else if (opt_xdp_flags & XDP_FLAGS_DRV_MODE) + printf("xdp-drv "); + else + printf(" "); + + if (opt_poll) + printf("poll() "); + + if (running) { + printf("running..."); + fflush(stdout); + } +} + +static void dump_stats(void) +{ + unsigned long now = get_nsecs(); + long dt = now - prev_time; + int i; + + prev_time = now; + + for (i = 0; i < num_socks; i++) { + char *fmt = "%-15s %'-11.0f %'-11lu\n"; + double rx_pps, tx_pps; + + rx_pps = (xsks[i]->rx_npkts - xsks[i]->prev_rx_npkts) * + 1000000000. / dt; + tx_pps = (xsks[i]->tx_npkts - xsks[i]->prev_tx_npkts) * + 1000000000. / dt; + + printf("\n sock%d@", i); + print_benchmark(false); + printf("\n"); + + printf("%-15s %-11s %-11s %-11.2f\n", "", "pps", "pkts", + dt / 1000000000.); + printf(fmt, "rx", rx_pps, xsks[i]->rx_npkts); + printf(fmt, "tx", tx_pps, xsks[i]->tx_npkts); + + xsks[i]->prev_rx_npkts = xsks[i]->rx_npkts; + xsks[i]->prev_tx_npkts = xsks[i]->tx_npkts; + } +} + +static void *poller(void *arg) +{ + (void)arg; + for (;;) { + sleep(opt_interval); + dump_stats(); + } + + return NULL; +} + +static void int_exit(int sig) +{ + (void)sig; + dump_stats(); + bpf_set_link_xdp_fd(opt_ifindex, -1, opt_xdp_flags); + exit(EXIT_SUCCESS); +} + +static struct option long_options[] = { + {"rxdrop", no_argument, 0, 'r'}, + {"txonly", no_argument, 0, 't'}, + {"l2fwd", no_argument, 0, 'l'}, + {"interface", required_argument, 0, 'i'}, + {"queue", required_argument, 0, 'q'}, + {"poll", no_argument, 0, 'p'}, + {"shared-buffer", no_argument, 0, 's'}, + {"xdp-skb", no_argument, 0, 'S'}, + {"xdp-native", no_argument, 0, 'N'}, + {"interval", required_argument, 0, 'n'}, + {0, 0, 0, 0} +}; + +static void usage(const char *prog) +{ + const char *str = + " Usage: %s [OPTIONS]\n" + " Options:\n" + " -r, --rxdrop Discard all incoming packets (default)\n" + " -t, --txonly Only send packets\n" + " -l, --l2fwd MAC swap L2 forwarding\n" + " -i, --interface=n Run on interface n\n" + " -q, --queue=n Use queue n (default 0)\n" + " -p, --poll Use poll syscall\n" + " -s, --shared-buffer Use shared packet buffer\n" + " -S, --xdp-skb=n Use XDP skb-mod\n" + " -N, --xdp-native=n Enfore XDP native mode\n" + " -n, --interval=n Specify statistics update interval (default 1 sec).\n" + "\n"; + fprintf(stderr, str, prog); + exit(EXIT_FAILURE); +} + +static void parse_command_line(int argc, char **argv) +{ + int option_index, c; + + opterr = 0; + + for (;;) { + c = getopt_long(argc, argv, "rtli:q:psSNn:", long_options, + &option_index); + if (c == -1) + break; + + switch (c) { + case 'r': + opt_bench = BENCH_RXDROP; + break; + case 't': + opt_bench = BENCH_TXONLY; + break; + case 'l': + opt_bench = BENCH_L2FWD; + break; + case 'i': + opt_if = optarg; + break; + case 'q': + opt_queue = atoi(optarg); + break; + case 's': + opt_shared_packet_buffer = 1; + break; + case 'p': + opt_poll = 1; + break; + case 'S': + opt_xdp_flags |= XDP_FLAGS_SKB_MODE; + break; + case 'N': + opt_xdp_flags |= XDP_FLAGS_DRV_MODE; + break; + case 'n': + opt_interval = atoi(optarg); + break; + default: + usage(basename(argv[0])); + } + } + + opt_ifindex = if_nametoindex(opt_if); + if (!opt_ifindex) { + fprintf(stderr, "ERROR: interface \"%s\" does not exist\n", + opt_if); + usage(basename(argv[0])); + } +} + +static void kick_tx(int fd) +{ + int ret; + + ret = sendto(fd, NULL, 0, MSG_DONTWAIT, NULL, 0); + if (ret >= 0 || errno == ENOBUFS || errno == EAGAIN) + return; + lassert(0); +} + +static inline void complete_tx_l2fwd(struct xdpsock *xsk) +{ + u32 descs[BATCH_SIZE]; + unsigned int rcvd; + size_t ndescs; + + if (!xsk->outstanding_tx) + return; + + kick_tx(xsk->sfd); + ndescs = (xsk->outstanding_tx > BATCH_SIZE) ? BATCH_SIZE : + xsk->outstanding_tx; + + /* re-add completed Tx buffers */ + rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, ndescs); + if (rcvd > 0) { + umem_fill_to_kernel(&xsk->umem->fq, descs, rcvd); + xsk->outstanding_tx -= rcvd; + xsk->tx_npkts += rcvd; + } +} + +static inline void complete_tx_only(struct xdpsock *xsk) +{ + u32 descs[BATCH_SIZE]; + unsigned int rcvd; + + if (!xsk->outstanding_tx) + return; + + kick_tx(xsk->sfd); + + rcvd = umem_complete_from_kernel(&xsk->umem->cq, descs, BATCH_SIZE); + if (rcvd > 0) { + xsk->outstanding_tx -= rcvd; + xsk->tx_npkts += rcvd; + } +} + +static void rx_drop(struct xdpsock *xsk) +{ + struct xdp_desc descs[BATCH_SIZE]; + unsigned int rcvd, i; + + rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE); + if (!rcvd) + return; + + for (i = 0; i < rcvd; i++) { + u32 idx = descs[i].idx; + + lassert(idx < NUM_FRAMES); +#if DEBUG_HEXDUMP + char *pkt; + char buf[32]; + + pkt = xq_get_data(xsk, idx, descs[i].offset); + sprintf(buf, "idx=%d", idx); + hex_dump(pkt, descs[i].len, buf); +#endif + } + + xsk->rx_npkts += rcvd; + + umem_fill_to_kernel_ex(&xsk->umem->fq, descs, rcvd); +} + +static void rx_drop_all(void) +{ + struct pollfd fds[MAX_SOCKS + 1]; + int i, ret, timeout, nfds = 1; + + memset(fds, 0, sizeof(fds)); + + for (i = 0; i < num_socks; i++) { + fds[i].fd = xsks[i]->sfd; + fds[i].events = POLLIN; + timeout = 1000; /* 1sn */ + } + + for (;;) { + if (opt_poll) { + ret = poll(fds, nfds, timeout); + if (ret <= 0) + continue; + } + + for (i = 0; i < num_socks; i++) + rx_drop(xsks[i]); + } +} + +static void tx_only(struct xdpsock *xsk) +{ + int timeout, ret, nfds = 1; + struct pollfd fds[nfds + 1]; + unsigned int idx = 0; + + memset(fds, 0, sizeof(fds)); + fds[0].fd = xsk->sfd; + fds[0].events = POLLOUT; + timeout = 1000; /* 1sn */ + + for (;;) { + if (opt_poll) { + ret = poll(fds, nfds, timeout); + if (ret <= 0) + continue; + + if (fds[0].fd != xsk->sfd || + !(fds[0].revents & POLLOUT)) + continue; + } + + if (xq_nb_free(&xsk->tx, BATCH_SIZE) >= BATCH_SIZE) { + lassert(xq_enq_tx_only(&xsk->tx, idx, BATCH_SIZE) == 0); + + xsk->outstanding_tx += BATCH_SIZE; + idx += BATCH_SIZE; + idx %= NUM_FRAMES; + } + + complete_tx_only(xsk); + } +} + +static void l2fwd(struct xdpsock *xsk) +{ + for (;;) { + struct xdp_desc descs[BATCH_SIZE]; + unsigned int rcvd, i; + int ret; + + for (;;) { + complete_tx_l2fwd(xsk); + + rcvd = xq_deq(&xsk->rx, descs, BATCH_SIZE); + if (rcvd > 0) + break; + } + + for (i = 0; i < rcvd; i++) { + char *pkt = xq_get_data(xsk, descs[i].idx, + descs[i].offset); + + swap_mac_addresses(pkt); +#if DEBUG_HEXDUMP + char buf[32]; + u32 idx = descs[i].idx; + + sprintf(buf, "idx=%d", idx); + hex_dump(pkt, descs[i].len, buf); +#endif + } + + xsk->rx_npkts += rcvd; + + ret = xq_enq(&xsk->tx, descs, rcvd); + lassert(ret == 0); + xsk->outstanding_tx += rcvd; + } +} + +int main(int argc, char **argv) +{ + struct rlimit r = {RLIM_INFINITY, RLIM_INFINITY}; + char xdp_filename[256]; + int i, ret, key = 0; + pthread_t pt; + + parse_command_line(argc, argv); + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + fprintf(stderr, "ERROR: setrlimit(RLIMIT_MEMLOCK) \"%s\"\n", + strerror(errno)); + exit(EXIT_FAILURE); + } + + snprintf(xdp_filename, sizeof(xdp_filename), "%s_kern.o", argv[0]); + + if (load_bpf_file(xdp_filename)) { + fprintf(stderr, "ERROR: load_bpf_file %s\n", bpf_log_buf); + exit(EXIT_FAILURE); + } + + if (!prog_fd[0]) { + fprintf(stderr, "ERROR: load_bpf_file: \"%s\"\n", + strerror(errno)); + exit(EXIT_FAILURE); + } + + if (bpf_set_link_xdp_fd(opt_ifindex, prog_fd[0], opt_xdp_flags) < 0) { + fprintf(stderr, "ERROR: link set xdp fd failed\n"); + exit(EXIT_FAILURE); + } + + ret = bpf_map_update_elem(map_fd[0], &key, &opt_queue, 0); + if (ret) { + fprintf(stderr, "ERROR: bpf_map_update_elem qidconf\n"); + exit(EXIT_FAILURE); + } + + /* Create sockets... */ + xsks[num_socks++] = xsk_configure(NULL); + +#if RR_LB + for (i = 0; i < MAX_SOCKS - 1; i++) + xsks[num_socks++] = xsk_configure(xsks[0]->umem); +#endif + + /* ...and insert them into the map. */ + for (i = 0; i < num_socks; i++) { + key = i; + ret = bpf_map_update_elem(map_fd[1], &key, &xsks[i]->sfd, 0); + if (ret) { + fprintf(stderr, "ERROR: bpf_map_update_elem %d\n", i); + exit(EXIT_FAILURE); + } + } + + signal(SIGINT, int_exit); + signal(SIGTERM, int_exit); + signal(SIGABRT, int_exit); + + setlocale(LC_ALL, ""); + + ret = pthread_create(&pt, NULL, poller, NULL); + lassert(ret == 0); + + prev_time = get_nsecs(); + + if (opt_bench == BENCH_RXDROP) + rx_drop_all(); + else if (opt_bench == BENCH_TXONLY) + tx_only(xsks[0]); + else + l2fwd(xsks[0]); + + return 0; +} diff --git a/samples/sockmap/Makefile b/samples/sockmap/Makefile deleted file mode 100644 index fa53f4d77834..000000000000 --- a/samples/sockmap/Makefile +++ /dev/null @@ -1,78 +0,0 @@ -# List of programs to build -hostprogs-y := sockmap - -# Libbpf dependencies -LIBBPF := ../../tools/lib/bpf/bpf.o ../../tools/lib/bpf/nlattr.o - -HOSTCFLAGS += -I$(objtree)/usr/include -HOSTCFLAGS += -I$(srctree)/tools/lib/ -HOSTCFLAGS += -I$(srctree)/tools/testing/selftests/bpf/ -HOSTCFLAGS += -I$(srctree)/tools/lib/ -I$(srctree)/tools/include -HOSTCFLAGS += -I$(srctree)/tools/perf - -sockmap-objs := ../bpf/bpf_load.o $(LIBBPF) sockmap_user.o - -# Tell kbuild to always build the programs -always := $(hostprogs-y) -always += sockmap_kern.o - -HOSTLOADLIBES_sockmap += -lelf -lpthread - -# Allows pointing LLC/CLANG to a LLVM backend with bpf support, redefine on cmdline: -# make samples/bpf/ LLC=~/git/llvm/build/bin/llc CLANG=~/git/llvm/build/bin/clang -LLC ?= llc -CLANG ?= clang - -# Trick to allow make to be run from this directory -all: - $(MAKE) -C ../../ $(CURDIR)/ - -clean: - $(MAKE) -C ../../ M=$(CURDIR) clean - @rm -f *~ - -$(obj)/syscall_nrs.s: $(src)/syscall_nrs.c - $(call if_changed_dep,cc_s_c) - -$(obj)/syscall_nrs.h: $(obj)/syscall_nrs.s FORCE - $(call filechk,offsets,__SYSCALL_NRS_H__) - -clean-files += syscall_nrs.h - -FORCE: - - -# Verify LLVM compiler tools are available and bpf target is supported by llc -.PHONY: verify_cmds verify_target_bpf $(CLANG) $(LLC) - -verify_cmds: $(CLANG) $(LLC) - @for TOOL in $^ ; do \ - if ! (which -- "$${TOOL}" > /dev/null 2>&1); then \ - echo "*** ERROR: Cannot find LLVM tool $${TOOL}" ;\ - exit 1; \ - else true; fi; \ - done - -verify_target_bpf: verify_cmds - @if ! (${LLC} -march=bpf -mattr=help > /dev/null 2>&1); then \ - echo "*** ERROR: LLVM (${LLC}) does not support 'bpf' target" ;\ - echo " NOTICE: LLVM version >= 3.7.1 required" ;\ - exit 2; \ - else true; fi - -$(src)/*.c: verify_target_bpf - -# asm/sysreg.h - inline assembly used by it is incompatible with llvm. -# But, there is no easy way to fix it, so just exclude it since it is -# useless for BPF samples. -# -# -target bpf option required with SK_MSG programs, this is to ensure -# reading 'void *' data types for data and data_end are __u64 reads. -$(obj)/%.o: $(src)/%.c - $(CLANG) $(NOSTDINC_FLAGS) $(LINUXINCLUDE) $(EXTRA_CFLAGS) -I$(obj) \ - -D__KERNEL__ -D__ASM_SYSREG_H -Wno-unused-value -Wno-pointer-sign \ - -Wno-compare-distinct-pointer-types \ - -Wno-gnu-variable-sized-type-not-at-end \ - -Wno-address-of-packed-member -Wno-tautological-compare \ - -Wno-unknown-warning-option -O2 -target bpf \ - -emit-llvm -c $< -o -| $(LLC) -march=bpf -filetype=obj -o $@ diff --git a/samples/sockmap/sockmap_test.sh b/samples/sockmap/sockmap_test.sh deleted file mode 100755 index ace75f070eb8..000000000000 --- a/samples/sockmap/sockmap_test.sh +++ /dev/null @@ -1,488 +0,0 @@ -#Test a bunch of positive cases to verify basic functionality -for prog in "--txmsg_redir --txmsg_skb" "--txmsg_redir --txmsg_ingress" "--txmsg" "--txmsg_redir" "--txmsg_redir --txmsg_ingress" "--txmsg_drop"; do -for t in "sendmsg" "sendpage"; do -for r in 1 10 100; do - for i in 1 10 100; do - for l in 1 10 100; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 - done - done -done -done -done - -#Test max iov -t="sendmsg" -r=1 -i=1024 -l=1 -prog="--txmsg" - -TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" -echo $TEST -$TEST -sleep 2 -prog="--txmsg_redir" -TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" -echo $TEST -$TEST - -# Test max iov with 1k send - -t="sendmsg" -r=1 -i=1024 -l=1024 -prog="--txmsg" - -TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" -echo $TEST -$TEST -sleep 2 -prog="--txmsg_redir" -TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" -echo $TEST -$TEST -sleep 2 - -# Test apply with 1B -r=1 -i=1024 -l=1024 -prog="--txmsg_apply 1" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test apply with larger value than send -r=1 -i=8 -l=1024 -prog="--txmsg_apply 2048" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test apply with apply that never reaches limit -r=1024 -i=1 -l=1 -prog="--txmsg_apply 2048" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test apply and redirect with 1B -r=1 -i=1024 -l=1024 -prog="--txmsg_redir --txmsg_apply 1" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -prog="--txmsg_redir --txmsg_apply 1 --txmsg_ingress" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -prog="--txmsg_redir --txmsg_apply 1 --txmsg_skb" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - - -# Test apply and redirect with larger value than send -r=1 -i=8 -l=1024 -prog="--txmsg_redir --txmsg_apply 2048" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -prog="--txmsg_redir --txmsg_apply 2048 --txmsg_ingress" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -prog="--txmsg_redir --txmsg_apply 2048 --txmsg_skb" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - - -# Test apply and redirect with apply that never reaches limit -r=1024 -i=1 -l=1 -prog="--txmsg_apply 2048" - -for t in "sendmsg" "sendpage"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test cork with 1B not really useful but test it anyways -r=1 -i=1024 -l=1024 -prog="--txmsg_cork 1" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test cork with a more reasonable 100B -r=1 -i=1000 -l=1000 -prog="--txmsg_cork 100" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test cork with larger value than send -r=1 -i=8 -l=1024 -prog="--txmsg_cork 2048" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test cork with cork that never reaches limit -r=1024 -i=1 -l=1 -prog="--txmsg_cork 2048" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -r=1 -i=1024 -l=1024 -prog="--txmsg_redir --txmsg_cork 1" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test cork with a more reasonable 100B -r=1 -i=1000 -l=1000 -prog="--txmsg_redir --txmsg_cork 100" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test cork with larger value than send -r=1 -i=8 -l=1024 -prog="--txmsg_redir --txmsg_cork 2048" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test cork with cork that never reaches limit -r=1024 -i=1 -l=1 -prog="--txmsg_cork 2048" - -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - - -# mix and match cork and apply not really useful but valid programs - -# Test apply < cork -r=100 -i=1 -l=5 -prog="--txmsg_apply 10 --txmsg_cork 100" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Try again with larger sizes so we hit overflow case -r=100 -i=1000 -l=2048 -prog="--txmsg_apply 4096 --txmsg_cork 8096" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test apply > cork -r=100 -i=1 -l=5 -prog="--txmsg_apply 100 --txmsg_cork 10" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Again with larger sizes so we hit overflow cases -r=100 -i=1000 -l=2048 -prog="--txmsg_apply 8096 --txmsg_cork 4096" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - - -# Test apply = cork -r=100 -i=1 -l=5 -prog="--txmsg_apply 10 --txmsg_cork 10" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -r=100 -i=1000 -l=2048 -prog="--txmsg_apply 4096 --txmsg_cork 4096" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test apply < cork -r=100 -i=1 -l=5 -prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 100" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Try again with larger sizes so we hit overflow case -r=100 -i=1000 -l=2048 -prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 8096" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Test apply > cork -r=100 -i=1 -l=5 -prog="--txmsg_redir --txmsg_apply 100 --txmsg_cork 10" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Again with larger sizes so we hit overflow cases -r=100 -i=1000 -l=2048 -prog="--txmsg_redir --txmsg_apply 8096 --txmsg_cork 4096" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - - -# Test apply = cork -r=100 -i=1 -l=5 -prog="--txmsg_redir --txmsg_apply 10 --txmsg_cork 10" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -r=100 -i=1000 -l=2048 -prog="--txmsg_redir --txmsg_apply 4096 --txmsg_cork 4096" -for t in "sendpage" "sendmsg"; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog" - echo $TEST - $TEST - sleep 2 -done - -# Tests for bpf_msg_pull_data() -for i in `seq 99 100 1600`; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ - --txmsg --txmsg_start 0 --txmsg_end $i --txmsg_cork 1600" - echo $TEST - $TEST - sleep 2 -done - -for i in `seq 199 100 1600`; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ - --txmsg --txmsg_start 100 --txmsg_end $i --txmsg_cork 1600" - echo $TEST - $TEST - sleep 2 -done - -TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ - --txmsg --txmsg_start 1500 --txmsg_end 1600 --txmsg_cork 1600" -echo $TEST -$TEST -sleep 2 - -TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ - --txmsg --txmsg_start 1111 --txmsg_end 1112 --txmsg_cork 1600" -echo $TEST -$TEST -sleep 2 - -TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ - --txmsg --txmsg_start 1111 --txmsg_end 0 --txmsg_cork 1600" -echo $TEST -$TEST -sleep 2 - -TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ - --txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1600" -echo $TEST -$TEST -sleep 2 - -TEST="./sockmap --cgroup /mnt/cgroup2/ -t sendpage -r 16 -i 1 -l 100 \ - --txmsg --txmsg_start 0 --txmsg_end 1601 --txmsg_cork 1602" -echo $TEST -$TEST -sleep 2 - -# Run through gamut again with start and end -for prog in "--txmsg" "--txmsg_redir" "--txmsg_drop"; do -for t in "sendmsg" "sendpage"; do -for r in 1 10 100; do - for i in 1 10 100; do - for l in 1 10 100; do - TEST="./sockmap --cgroup /mnt/cgroup2/ -t $t -r $r -i $i -l $l $prog --txmsg_start 1 --txmsg_end 2" - echo $TEST - $TEST - sleep 2 - done - done -done -done -done - -# Some specific tests to cover specific code paths -./sockmap --cgroup /mnt/cgroup2/ -t sendpage \ - -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3 -./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \ - -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 3 -./sockmap --cgroup /mnt/cgroup2/ -t sendpage \ - -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5 -./sockmap --cgroup /mnt/cgroup2/ -t sendmsg \ - -r 5 -i 1 -l 1 --txmsg_redir --txmsg_cork 5 --txmsg_apply 5 diff --git a/scripts/bpf_helpers_doc.py b/scripts/bpf_helpers_doc.py new file mode 100755 index 000000000000..8f59897fbda1 --- /dev/null +++ b/scripts/bpf_helpers_doc.py @@ -0,0 +1,421 @@ +#!/usr/bin/python3 +# SPDX-License-Identifier: GPL-2.0-only +# +# Copyright (C) 2018 Netronome Systems, Inc. + +# In case user attempts to run with Python 2. +from __future__ import print_function + +import argparse +import re +import sys, os + +class NoHelperFound(BaseException): + pass + +class ParsingError(BaseException): + def __init__(self, line='<line not provided>', reader=None): + if reader: + BaseException.__init__(self, + 'Error at file offset %d, parsing line: %s' % + (reader.tell(), line)) + else: + BaseException.__init__(self, 'Error parsing line: %s' % line) + +class Helper(object): + """ + An object representing the description of an eBPF helper function. + @proto: function prototype of the helper function + @desc: textual description of the helper function + @ret: description of the return value of the helper function + """ + def __init__(self, proto='', desc='', ret=''): + self.proto = proto + self.desc = desc + self.ret = ret + + def proto_break_down(self): + """ + Break down helper function protocol into smaller chunks: return type, + name, distincts arguments. + """ + arg_re = re.compile('((const )?(struct )?(\w+|...))( (\**)(\w+))?$') + res = {} + proto_re = re.compile('(.+) (\**)(\w+)\(((([^,]+)(, )?){1,5})\)$') + + capture = proto_re.match(self.proto) + res['ret_type'] = capture.group(1) + res['ret_star'] = capture.group(2) + res['name'] = capture.group(3) + res['args'] = [] + + args = capture.group(4).split(', ') + for a in args: + capture = arg_re.match(a) + res['args'].append({ + 'type' : capture.group(1), + 'star' : capture.group(6), + 'name' : capture.group(7) + }) + + return res + +class HeaderParser(object): + """ + An object used to parse a file in order to extract the documentation of a + list of eBPF helper functions. All the helpers that can be retrieved are + stored as Helper object, in the self.helpers() array. + @filename: name of file to parse, usually include/uapi/linux/bpf.h in the + kernel tree + """ + def __init__(self, filename): + self.reader = open(filename, 'r') + self.line = '' + self.helpers = [] + + def parse_helper(self): + proto = self.parse_proto() + desc = self.parse_desc() + ret = self.parse_ret() + return Helper(proto=proto, desc=desc, ret=ret) + + def parse_proto(self): + # Argument can be of shape: + # - "void" + # - "type name" + # - "type *name" + # - Same as above, with "const" and/or "struct" in front of type + # - "..." (undefined number of arguments, for bpf_trace_printk()) + # There is at least one term ("void"), and at most five arguments. + p = re.compile(' \* ?((.+) \**\w+\((((const )?(struct )?(\w+|\.\.\.)( \**\w+)?)(, )?){1,5}\))$') + capture = p.match(self.line) + if not capture: + raise NoHelperFound + self.line = self.reader.readline() + return capture.group(1) + + def parse_desc(self): + p = re.compile(' \* ?(?:\t| {6,8})Description$') + capture = p.match(self.line) + if not capture: + # Helper can have empty description and we might be parsing another + # attribute: return but do not consume. + return '' + # Description can be several lines, some of them possibly empty, and it + # stops when another subsection title is met. + desc = '' + while True: + self.line = self.reader.readline() + if self.line == ' *\n': + desc += '\n' + else: + p = re.compile(' \* ?(?:\t| {6,8})(?:\t| {8})(.*)') + capture = p.match(self.line) + if capture: + desc += capture.group(1) + '\n' + else: + break + return desc + + def parse_ret(self): + p = re.compile(' \* ?(?:\t| {6,8})Return$') + capture = p.match(self.line) + if not capture: + # Helper can have empty retval and we might be parsing another + # attribute: return but do not consume. + return '' + # Return value description can be several lines, some of them possibly + # empty, and it stops when another subsection title is met. + ret = '' + while True: + self.line = self.reader.readline() + if self.line == ' *\n': + ret += '\n' + else: + p = re.compile(' \* ?(?:\t| {6,8})(?:\t| {8})(.*)') + capture = p.match(self.line) + if capture: + ret += capture.group(1) + '\n' + else: + break + return ret + + def run(self): + # Advance to start of helper function descriptions. + offset = self.reader.read().find('* Start of BPF helper function descriptions:') + if offset == -1: + raise Exception('Could not find start of eBPF helper descriptions list') + self.reader.seek(offset) + self.reader.readline() + self.reader.readline() + self.line = self.reader.readline() + + while True: + try: + helper = self.parse_helper() + self.helpers.append(helper) + except NoHelperFound: + break + + self.reader.close() + print('Parsed description of %d helper function(s)' % len(self.helpers), + file=sys.stderr) + +############################################################################### + +class Printer(object): + """ + A generic class for printers. Printers should be created with an array of + Helper objects, and implement a way to print them in the desired fashion. + @helpers: array of Helper objects to print to standard output + """ + def __init__(self, helpers): + self.helpers = helpers + + def print_header(self): + pass + + def print_footer(self): + pass + + def print_one(self, helper): + pass + + def print_all(self): + self.print_header() + for helper in self.helpers: + self.print_one(helper) + self.print_footer() + +class PrinterRST(Printer): + """ + A printer for dumping collected information about helpers as a ReStructured + Text page compatible with the rst2man program, which can be used to + generate a manual page for the helpers. + @helpers: array of Helper objects to print to standard output + """ + def print_header(self): + header = '''\ +.. Copyright (C) All BPF authors and contributors from 2014 to present. +.. See git log include/uapi/linux/bpf.h in kernel tree for details. +.. +.. %%%LICENSE_START(VERBATIM) +.. Permission is granted to make and distribute verbatim copies of this +.. manual provided the copyright notice and this permission notice are +.. preserved on all copies. +.. +.. Permission is granted to copy and distribute modified versions of this +.. manual under the conditions for verbatim copying, provided that the +.. entire resulting derived work is distributed under the terms of a +.. permission notice identical to this one. +.. +.. Since the Linux kernel and libraries are constantly changing, this +.. manual page may be incorrect or out-of-date. The author(s) assume no +.. responsibility for errors or omissions, or for damages resulting from +.. the use of the information contained herein. The author(s) may not +.. have taken the same level of care in the production of this manual, +.. which is licensed free of charge, as they might when working +.. professionally. +.. +.. Formatted or processed versions of this manual, if unaccompanied by +.. the source, must acknowledge the copyright and authors of this work. +.. %%%LICENSE_END +.. +.. Please do not edit this file. It was generated from the documentation +.. located in file include/uapi/linux/bpf.h of the Linux kernel sources +.. (helpers description), and from scripts/bpf_helpers_doc.py in the same +.. repository (header and footer). + +=========== +BPF-HELPERS +=========== +------------------------------------------------------------------------------- +list of eBPF helper functions +------------------------------------------------------------------------------- + +:Manual section: 7 + +DESCRIPTION +=========== + +The extended Berkeley Packet Filter (eBPF) subsystem consists in programs +written in a pseudo-assembly language, then attached to one of the several +kernel hooks and run in reaction of specific events. This framework differs +from the older, "classic" BPF (or "cBPF") in several aspects, one of them being +the ability to call special functions (or "helpers") from within a program. +These functions are restricted to a white-list of helpers defined in the +kernel. + +These helpers are used by eBPF programs to interact with the system, or with +the context in which they work. For instance, they can be used to print +debugging messages, to get the time since the system was booted, to interact +with eBPF maps, or to manipulate network packets. Since there are several eBPF +program types, and that they do not run in the same context, each program type +can only call a subset of those helpers. + +Due to eBPF conventions, a helper can not have more than five arguments. + +Internally, eBPF programs call directly into the compiled helper functions +without requiring any foreign-function interface. As a result, calling helpers +introduces no overhead, thus offering excellent performance. + +This document is an attempt to list and document the helpers available to eBPF +developers. They are sorted by chronological order (the oldest helpers in the +kernel at the top). + +HELPERS +======= +''' + print(header) + + def print_footer(self): + footer = ''' +EXAMPLES +======== + +Example usage for most of the eBPF helpers listed in this manual page are +available within the Linux kernel sources, at the following locations: + +* *samples/bpf/* +* *tools/testing/selftests/bpf/* + +LICENSE +======= + +eBPF programs can have an associated license, passed along with the bytecode +instructions to the kernel when the programs are loaded. The format for that +string is identical to the one in use for kernel modules (Dual licenses, such +as "Dual BSD/GPL", may be used). Some helper functions are only accessible to +programs that are compatible with the GNU Privacy License (GPL). + +In order to use such helpers, the eBPF program must be loaded with the correct +license string passed (via **attr**) to the **bpf**\ () system call, and this +generally translates into the C source code of the program containing a line +similar to the following: + +:: + + char ____license[] __attribute__((section("license"), used)) = "GPL"; + +IMPLEMENTATION +============== + +This manual page is an effort to document the existing eBPF helper functions. +But as of this writing, the BPF sub-system is under heavy development. New eBPF +program or map types are added, along with new helper functions. Some helpers +are occasionally made available for additional program types. So in spite of +the efforts of the community, this page might not be up-to-date. If you want to +check by yourself what helper functions exist in your kernel, or what types of +programs they can support, here are some files among the kernel tree that you +may be interested in: + +* *include/uapi/linux/bpf.h* is the main BPF header. It contains the full list + of all helper functions, as well as many other BPF definitions including most + of the flags, structs or constants used by the helpers. +* *net/core/filter.c* contains the definition of most network-related helper + functions, and the list of program types from which they can be used. +* *kernel/trace/bpf_trace.c* is the equivalent for most tracing program-related + helpers. +* *kernel/bpf/verifier.c* contains the functions used to check that valid types + of eBPF maps are used with a given helper function. +* *kernel/bpf/* directory contains other files in which additional helpers are + defined (for cgroups, sockmaps, etc.). + +Compatibility between helper functions and program types can generally be found +in the files where helper functions are defined. Look for the **struct +bpf_func_proto** objects and for functions returning them: these functions +contain a list of helpers that a given program type can call. Note that the +**default:** label of the **switch ... case** used to filter helpers can call +other functions, themselves allowing access to additional helpers. The +requirement for GPL license is also in those **struct bpf_func_proto**. + +Compatibility between helper functions and map types can be found in the +**check_map_func_compatibility**\ () function in file *kernel/bpf/verifier.c*. + +Helper functions that invalidate the checks on **data** and **data_end** +pointers for network processing are listed in function +**bpf_helper_changes_pkt_data**\ () in file *net/core/filter.c*. + +SEE ALSO +======== + +**bpf**\ (2), +**cgroups**\ (7), +**ip**\ (8), +**perf_event_open**\ (2), +**sendmsg**\ (2), +**socket**\ (7), +**tc-bpf**\ (8)''' + print(footer) + + def print_proto(self, helper): + """ + Format function protocol with bold and italics markers. This makes RST + file less readable, but gives nice results in the manual page. + """ + proto = helper.proto_break_down() + + print('**%s %s%s(' % (proto['ret_type'], + proto['ret_star'].replace('*', '\\*'), + proto['name']), + end='') + + comma = '' + for a in proto['args']: + one_arg = '{}{}'.format(comma, a['type']) + if a['name']: + if a['star']: + one_arg += ' {}**\ '.format(a['star'].replace('*', '\\*')) + else: + one_arg += '** ' + one_arg += '*{}*\\ **'.format(a['name']) + comma = ', ' + print(one_arg, end='') + + print(')**') + + def print_one(self, helper): + self.print_proto(helper) + + if (helper.desc): + print('\tDescription') + # Do not strip all newline characters: formatted code at the end of + # a section must be followed by a blank line. + for line in re.sub('\n$', '', helper.desc, count=1).split('\n'): + print('{}{}'.format('\t\t' if line else '', line)) + + if (helper.ret): + print('\tReturn') + for line in helper.ret.rstrip().split('\n'): + print('{}{}'.format('\t\t' if line else '', line)) + + print('') + +############################################################################### + +# If script is launched from scripts/ from kernel tree and can access +# ../include/uapi/linux/bpf.h, use it as a default name for the file to parse, +# otherwise the --filename argument will be required from the command line. +script = os.path.abspath(sys.argv[0]) +linuxRoot = os.path.dirname(os.path.dirname(script)) +bpfh = os.path.join(linuxRoot, 'include/uapi/linux/bpf.h') + +argParser = argparse.ArgumentParser(description=""" +Parse eBPF header file and generate documentation for eBPF helper functions. +The RST-formatted output produced can be turned into a manual page with the +rst2man utility. +""") +if (os.path.isfile(bpfh)): + argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h', + default=bpfh) +else: + argParser.add_argument('--filename', help='path to include/uapi/linux/bpf.h') +args = argParser.parse_args() + +# Parse file. +headerParser = HeaderParser(args.filename) +headerParser.run() + +# Print formatted output to standard output. +printer = PrinterRST(headerParser.helpers) +printer.print_all() diff --git a/security/selinux/hooks.c b/security/selinux/hooks.c index 4cafe6a19167..5c508d26b367 100644 --- a/security/selinux/hooks.c +++ b/security/selinux/hooks.c @@ -1471,7 +1471,9 @@ static inline u16 socket_type_to_security_class(int family, int type, int protoc return SECCLASS_QIPCRTR_SOCKET; case PF_SMC: return SECCLASS_SMC_SOCKET; -#if PF_MAX > 44 + case PF_XDP: + return SECCLASS_XDP_SOCKET; +#if PF_MAX > 45 #error New address family defined, please update this function. #endif } diff --git a/security/selinux/include/classmap.h b/security/selinux/include/classmap.h index 7f0372426494..bd5fe0d3204a 100644 --- a/security/selinux/include/classmap.h +++ b/security/selinux/include/classmap.h @@ -240,9 +240,11 @@ struct security_class_mapping secclass_map[] = { { "manage_subnet", NULL } }, { "bpf", {"map_create", "map_read", "map_write", "prog_load", "prog_run"} }, + { "xdp_socket", + { COMMON_SOCK_PERMS, NULL } }, { NULL } }; -#if PF_MAX > 44 +#if PF_MAX > 45 #error New address family defined, please update secclass_map. #endif diff --git a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst index 0e4e923235b6..d004f6382dab 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-cgroup.rst @@ -26,7 +26,8 @@ MAP COMMANDS | **bpftool** **cgroup help** | | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** } +| *ATTACH_TYPE* := { **ingress** | **egress** | **sock_create** | **sock_ops** | **device** | +| **bind4** | **bind6** | **post_bind4** | **post_bind6** | **connect4** | **connect6** } | *ATTACH_FLAGS* := { **multi** | **override** } DESCRIPTION @@ -63,7 +64,13 @@ DESCRIPTION **egress** egress path of the inet socket (since 4.10); **sock_create** opening of an inet socket (since 4.10); **sock_ops** various socket operations (since 4.12); - **device** device access (since 4.15). + **device** device access (since 4.15); + **bind4** call to bind(2) for an inet4 socket (since 4.17); + **bind6** call to bind(2) for an inet6 socket (since 4.17); + **post_bind4** return from bind(2) for an inet4 socket (since 4.17); + **post_bind6** return from bind(2) for an inet6 socket (since 4.17); + **connect4** call to connect(2) for an inet4 socket (since 4.17); + **connect6** call to connect(2) for an inet6 socket (since 4.17). **bpftool cgroup detach** *CGROUP* *ATTACH_TYPE* *PROG* Detach *PROG* from the cgroup *CGROUP* and attach type diff --git a/tools/bpf/bpftool/Documentation/bpftool-map.rst b/tools/bpf/bpftool/Documentation/bpftool-map.rst index 457e868bd32f..a6258bc8ec4f 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-map.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-map.rst @@ -22,17 +22,19 @@ MAP COMMANDS ============= | **bpftool** **map { show | list }** [*MAP*] -| **bpftool** **map dump** *MAP* -| **bpftool** **map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] -| **bpftool** **map lookup** *MAP* **key** *BYTES* -| **bpftool** **map getnext** *MAP* [**key** *BYTES*] -| **bpftool** **map delete** *MAP* **key** *BYTES* -| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map dump** *MAP* +| **bpftool** **map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*] +| **bpftool** **map lookup** *MAP* **key** *DATA* +| **bpftool** **map getnext** *MAP* [**key** *DATA*] +| **bpftool** **map delete** *MAP* **key** *DATA* +| **bpftool** **map pin** *MAP* *FILE* +| **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] | **bpftool** **map help** | | *MAP* := { **id** *MAP_ID* | **pinned** *FILE* } +| *DATA* := { [**hex**] *BYTES* } | *PROG* := { **id** *PROG_ID* | **pinned** *FILE* | **tag** *PROG_TAG* } -| *VALUE* := { *BYTES* | *MAP* | *PROG* } +| *VALUE* := { *DATA* | *MAP* | *PROG* } | *UPDATE_FLAGS* := { **any** | **exist** | **noexist** } DESCRIPTION @@ -48,20 +50,26 @@ DESCRIPTION **bpftool map dump** *MAP* Dump all entries in a given *MAP*. - **bpftool map update** *MAP* **key** *BYTES* **value** *VALUE* [*UPDATE_FLAGS*] + **bpftool map update** *MAP* **key** *DATA* **value** *VALUE* [*UPDATE_FLAGS*] Update map entry for a given *KEY*. *UPDATE_FLAGS* can be one of: **any** update existing entry or add if doesn't exit; **exist** update only if entry already exists; **noexist** update only if entry doesn't exist. - **bpftool map lookup** *MAP* **key** *BYTES* + If the **hex** keyword is provided in front of the bytes + sequence, the bytes are parsed as hexadeximal values, even if + no "0x" prefix is added. If the keyword is not provided, then + the bytes are parsed as decimal values, unless a "0x" prefix + (for hexadecimal) or a "0" prefix (for octal) is provided. + + **bpftool map lookup** *MAP* **key** *DATA* Lookup **key** in the map. - **bpftool map getnext** *MAP* [**key** *BYTES*] + **bpftool map getnext** *MAP* [**key** *DATA*] Get next key. If *key* is not specified, get first key. - **bpftool map delete** *MAP* **key** *BYTES* + **bpftool map delete** *MAP* **key** *DATA* Remove entry from the map. **bpftool map pin** *MAP* *FILE* @@ -69,6 +77,22 @@ DESCRIPTION Note: *FILE* must be located in *bpffs* mount. + **bpftool** **map event_pipe** *MAP* [**cpu** *N* **index** *M*] + Read events from a BPF_MAP_TYPE_PERF_EVENT_ARRAY map. + + Install perf rings into a perf event array map and dump + output of any bpf_perf_event_output() call in the kernel. + By default read the number of CPUs on the system and + install perf ring for each CPU in the corresponding index + in the array. + + If **cpu** and **index** are specified, install perf ring + for given **cpu** at **index** in the array (single ring). + + Note that installing a perf ring into an array will silently + replace any existing ring. Any other application will stop + receiving events if it installed its rings earlier. + **bpftool map help** Print short help message. @@ -98,7 +122,12 @@ EXAMPLES 10: hash name some_map flags 0x0 key 4B value 8B max_entries 2048 memlock 167936B -**# bpftool map update id 10 key 13 00 07 00 value 02 00 00 00 01 02 03 04** +The following three commands are equivalent: + +| +| **# bpftool map update id 10 key hex 20 c4 b7 00 value hex 0f ff ff ab 01 02 03 4c** +| **# bpftool map update id 10 key 0x20 0xc4 0xb7 0x00 value 0x0f 0xff 0xff 0xab 0x01 0x02 0x03 0x4c** +| **# bpftool map update id 10 key 32 196 183 0 value 15 255 255 171 1 2 3 76** **# bpftool map lookup id 10 key 0 1 2 3** diff --git a/tools/bpf/bpftool/Documentation/bpftool-prog.rst b/tools/bpf/bpftool/Documentation/bpftool-prog.rst index 67ca6c69376c..43d34a5c3ec5 100644 --- a/tools/bpf/bpftool/Documentation/bpftool-prog.rst +++ b/tools/bpf/bpftool/Documentation/bpftool-prog.rst @@ -95,7 +95,7 @@ EXAMPLES **# bpftool prog show** :: - 10: xdp name some_prog tag 005a3d2123620c8b + 10: xdp name some_prog tag 005a3d2123620c8b gpl loaded_at Sep 29/20:11 uid 0 xlated 528B jited 370B memlock 4096B map_ids 10 @@ -108,6 +108,7 @@ EXAMPLES "id": 10, "type": "xdp", "tag": "005a3d2123620c8b", + "gpl_compatible": true, "loaded_at": "Sep 29/20:11", "uid": 0, "bytes_xlated": 528, diff --git a/tools/bpf/bpftool/Documentation/bpftool.rst b/tools/bpf/bpftool/Documentation/bpftool.rst index 20689a321ffe..564cb0d9692b 100644 --- a/tools/bpf/bpftool/Documentation/bpftool.rst +++ b/tools/bpf/bpftool/Documentation/bpftool.rst @@ -23,7 +23,7 @@ SYNOPSIS *MAP-COMMANDS* := { **show** | **list** | **dump** | **update** | **lookup** | **getnext** | **delete** - | **pin** | **help** } + | **pin** | **event_pipe** | **help** } *PROG-COMMANDS* := { **show** | **list** | **dump jited** | **dump xlated** | **pin** | **load** | **help** } diff --git a/tools/bpf/bpftool/Makefile b/tools/bpf/bpftool/Makefile index 4e69782c4a79..892dbf095bff 100644 --- a/tools/bpf/bpftool/Makefile +++ b/tools/bpf/bpftool/Makefile @@ -39,7 +39,12 @@ CC = gcc CFLAGS += -O2 CFLAGS += -W -Wall -Wextra -Wno-unused-parameter -Wshadow -Wno-missing-field-initializers -CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ -I$(srctree)/tools/include/uapi -I$(srctree)/tools/include -I$(srctree)/tools/lib/bpf -I$(srctree)/kernel/bpf/ +CFLAGS += -DPACKAGE='"bpftool"' -D__EXPORTED_HEADERS__ \ + -I$(srctree)/kernel/bpf/ \ + -I$(srctree)/tools/include \ + -I$(srctree)/tools/include/uapi \ + -I$(srctree)/tools/lib/bpf \ + -I$(srctree)/tools/perf CFLAGS += -DBPFTOOL_VERSION='"$(BPFTOOL_VERSION)"' LIBS = -lelf -lbfd -lopcodes $(LIBBPF) diff --git a/tools/bpf/bpftool/bash-completion/bpftool b/tools/bpf/bpftool/bash-completion/bpftool index 490811b45fa7..b301c9b315f1 100644 --- a/tools/bpf/bpftool/bash-completion/bpftool +++ b/tools/bpf/bpftool/bash-completion/bpftool @@ -1,6 +1,6 @@ # bpftool(8) bash completion -*- shell-script -*- # -# Copyright (C) 2017 Netronome Systems, Inc. +# Copyright (C) 2017-2018 Netronome Systems, Inc. # # This software is dual licensed under the GNU General License # Version 2, June 1991 as shown in the file COPYING in the top-level @@ -79,6 +79,14 @@ _bpftool_get_map_ids() command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) } +_bpftool_get_perf_map_ids() +{ + COMPREPLY+=( $( compgen -W "$( bpftool -jp map 2>&1 | \ + command grep -C2 perf_event_array | \ + command sed -n 's/.*"id": \(.*\),$/\1/p' )" -- "$cur" ) ) +} + + _bpftool_get_prog_ids() { COMPREPLY+=( $( compgen -W "$( bpftool -jp prog 2>&1 | \ @@ -147,7 +155,7 @@ _bpftool() # Deal with simplest keywords case $prev in - help|key|opcodes|visual) + help|hex|opcodes|visual) return 0 ;; tag) @@ -283,7 +291,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; *) _bpftool_once_attr 'key' @@ -302,7 +310,7 @@ _bpftool() return 0 ;; key) - return 0 + COMPREPLY+=( $( compgen -W 'hex' -- "$cur" ) ) ;; value) # We can have bytes, or references to a prog or a @@ -321,6 +329,8 @@ _bpftool() return 0 ;; *) + COMPREPLY+=( $( compgen -W 'hex' \ + -- "$cur" ) ) return 0 ;; esac @@ -357,10 +367,34 @@ _bpftool() fi return 0 ;; + event_pipe) + case $prev in + $command) + COMPREPLY=( $( compgen -W "$MAP_TYPE" -- "$cur" ) ) + return 0 + ;; + id) + _bpftool_get_perf_map_ids + return 0 + ;; + cpu) + return 0 + ;; + index) + return 0 + ;; + *) + _bpftool_once_attr 'cpu' + _bpftool_once_attr 'index' + return 0 + ;; + esac + ;; *) [[ $prev == $object ]] && \ COMPREPLY=( $( compgen -W 'delete dump getnext help \ - lookup pin show list update' -- "$cur" ) ) + lookup pin event_pipe show list update' -- \ + "$cur" ) ) ;; esac ;; @@ -372,7 +406,8 @@ _bpftool() ;; attach|detach) local ATTACH_TYPES='ingress egress sock_create sock_ops \ - device' + device bind4 bind6 post_bind4 post_bind6 connect4 \ + connect6' local ATTACH_FLAGS='multi override' local PROG_TYPE='id pinned tag' case $prev in @@ -380,7 +415,8 @@ _bpftool() _filedir return 0 ;; - ingress|egress|sock_create|sock_ops|device) + ingress|egress|sock_create|sock_ops|device|bind4|bind6|\ + post_bind4|post_bind6|connect4|connect6) COMPREPLY=( $( compgen -W "$PROG_TYPE" -- \ "$cur" ) ) return 0 diff --git a/tools/bpf/bpftool/cgroup.c b/tools/bpf/bpftool/cgroup.c index cae32a61cb18..1351bd6b5aa7 100644 --- a/tools/bpf/bpftool/cgroup.c +++ b/tools/bpf/bpftool/cgroup.c @@ -16,8 +16,11 @@ #define HELP_SPEC_ATTACH_FLAGS \ "ATTACH_FLAGS := { multi | override }" -#define HELP_SPEC_ATTACH_TYPES \ - "ATTACH_TYPE := { ingress | egress | sock_create | sock_ops | device }" +#define HELP_SPEC_ATTACH_TYPES \ + " ATTACH_TYPE := { ingress | egress | sock_create |\n" \ + " sock_ops | device | bind4 | bind6 |\n" \ + " post_bind4 | post_bind6 | connect4 |\n" \ + " connect6 }" static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_INGRESS] = "ingress", @@ -25,6 +28,12 @@ static const char * const attach_type_strings[] = { [BPF_CGROUP_INET_SOCK_CREATE] = "sock_create", [BPF_CGROUP_SOCK_OPS] = "sock_ops", [BPF_CGROUP_DEVICE] = "device", + [BPF_CGROUP_INET4_BIND] = "bind4", + [BPF_CGROUP_INET6_BIND] = "bind6", + [BPF_CGROUP_INET4_CONNECT] = "connect4", + [BPF_CGROUP_INET6_CONNECT] = "connect6", + [BPF_CGROUP_INET4_POST_BIND] = "post_bind4", + [BPF_CGROUP_INET6_POST_BIND] = "post_bind6", [__MAX_BPF_ATTACH_TYPE] = NULL, }; @@ -282,7 +291,7 @@ static int do_help(int argc, char **argv) " %s %s detach CGROUP ATTACH_TYPE PROG\n" " %s %s help\n" "\n" - " " HELP_SPEC_ATTACH_TYPES "\n" + HELP_SPEC_ATTACH_TYPES "\n" " " HELP_SPEC_ATTACH_FLAGS "\n" " " HELP_SPEC_PROGRAM "\n" " " HELP_SPEC_OPTIONS "\n" diff --git a/tools/bpf/bpftool/common.c b/tools/bpf/bpftool/common.c index 465995281dcd..32f9e397a6c0 100644 --- a/tools/bpf/bpftool/common.c +++ b/tools/bpf/bpftool/common.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -33,6 +33,7 @@ /* Author: Jakub Kicinski <kubakici@wp.pl> */ +#include <ctype.h> #include <errno.h> #include <fcntl.h> #include <fts.h> @@ -330,6 +331,16 @@ char *get_fdinfo(int fd, const char *key) return NULL; } +void print_data_json(uint8_t *data, size_t len) +{ + unsigned int i; + + jsonw_start_array(json_wtr); + for (i = 0; i < len; i++) + jsonw_printf(json_wtr, "%d", data[i]); + jsonw_end_array(json_wtr); +} + void print_hex_data_json(uint8_t *data, size_t len) { unsigned int i; @@ -420,6 +431,70 @@ void delete_pinned_obj_table(struct pinned_obj_table *tab) } } +unsigned int get_page_size(void) +{ + static int result; + + if (!result) + result = getpagesize(); + return result; +} + +unsigned int get_possible_cpus(void) +{ + static unsigned int result; + char buf[128]; + long int n; + char *ptr; + int fd; + + if (result) + return result; + + fd = open("/sys/devices/system/cpu/possible", O_RDONLY); + if (fd < 0) { + p_err("can't open sysfs possible cpus"); + exit(-1); + } + + n = read(fd, buf, sizeof(buf)); + if (n < 2) { + p_err("can't read sysfs possible cpus"); + exit(-1); + } + close(fd); + + if (n == sizeof(buf)) { + p_err("read sysfs possible cpus overflow"); + exit(-1); + } + + ptr = buf; + n = 0; + while (*ptr && *ptr != '\n') { + unsigned int a, b; + + if (sscanf(ptr, "%u-%u", &a, &b) == 2) { + n += b - a + 1; + + ptr = strchr(ptr, '-') + 1; + } else if (sscanf(ptr, "%u", &a) == 1) { + n++; + } else { + assert(0); + } + + while (isdigit(*ptr)) + ptr++; + if (*ptr == ',') + ptr++; + } + + result = n; + + return result; +} + static char * ifindex_to_name_ns(__u32 ifindex, __u32 ns_dev, __u32 ns_ino, char *buf) { diff --git a/tools/bpf/bpftool/main.h b/tools/bpf/bpftool/main.h index b8e9584d6246..6173cd997e7a 100644 --- a/tools/bpf/bpftool/main.h +++ b/tools/bpf/bpftool/main.h @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -117,14 +117,19 @@ int do_pin_fd(int fd, const char *name); int do_prog(int argc, char **arg); int do_map(int argc, char **arg); +int do_event_pipe(int argc, char **argv); int do_cgroup(int argc, char **arg); int prog_parse_fd(int *argc, char ***argv); +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len); void disasm_print_insn(unsigned char *image, ssize_t len, int opcodes, const char *arch); +void print_data_json(uint8_t *data, size_t len); void print_hex_data_json(uint8_t *data, size_t len); +unsigned int get_page_size(void); +unsigned int get_possible_cpus(void); const char *ifindex_to_bfd_name_ns(__u32 ifindex, __u64 ns_dev, __u64 ns_ino); #endif diff --git a/tools/bpf/bpftool/map.c b/tools/bpf/bpftool/map.c index f509c86faede..af6766e956ba 100644 --- a/tools/bpf/bpftool/map.c +++ b/tools/bpf/bpftool/map.c @@ -1,5 +1,5 @@ /* - * Copyright (C) 2017 Netronome Systems, Inc. + * Copyright (C) 2017-2018 Netronome Systems, Inc. * * This software is dual licensed under the GNU General License Version 2, * June 1991 as shown in the file COPYING in the top-level directory of this @@ -34,7 +34,6 @@ /* Author: Jakub Kicinski <kubakici@wp.pl> */ #include <assert.h> -#include <ctype.h> #include <errno.h> #include <fcntl.h> #include <stdbool.h> @@ -69,61 +68,6 @@ static const char * const map_type_name[] = { [BPF_MAP_TYPE_CPUMAP] = "cpumap", }; -static unsigned int get_possible_cpus(void) -{ - static unsigned int result; - char buf[128]; - long int n; - char *ptr; - int fd; - - if (result) - return result; - - fd = open("/sys/devices/system/cpu/possible", O_RDONLY); - if (fd < 0) { - p_err("can't open sysfs possible cpus"); - exit(-1); - } - - n = read(fd, buf, sizeof(buf)); - if (n < 2) { - p_err("can't read sysfs possible cpus"); - exit(-1); - } - close(fd); - - if (n == sizeof(buf)) { - p_err("read sysfs possible cpus overflow"); - exit(-1); - } - - ptr = buf; - n = 0; - while (*ptr && *ptr != '\n') { - unsigned int a, b; - - if (sscanf(ptr, "%u-%u", &a, &b) == 2) { - n += b - a + 1; - - ptr = strchr(ptr, '-') + 1; - } else if (sscanf(ptr, "%u", &a) == 1) { - n++; - } else { - assert(0); - } - - while (isdigit(*ptr)) - ptr++; - if (*ptr == ',') - ptr++; - } - - result = n; - - return result; -} - static bool map_is_per_cpu(__u32 type) { return type == BPF_MAP_TYPE_PERCPU_HASH || @@ -186,8 +130,7 @@ static int map_parse_fd(int *argc, char ***argv) return -1; } -static int -map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) +int map_parse_fd_and_info(int *argc, char ***argv, void *info, __u32 *info_len) { int err; int fd; @@ -283,11 +226,16 @@ static void print_entry_plain(struct bpf_map_info *info, unsigned char *key, static char **parse_bytes(char **argv, const char *name, unsigned char *val, unsigned int n) { - unsigned int i = 0; + unsigned int i = 0, base = 0; char *endptr; + if (is_prefix(*argv, "hex")) { + base = 16; + argv++; + } + while (i < n && argv[i]) { - val[i] = strtoul(argv[i], &endptr, 0); + val[i] = strtoul(argv[i], &endptr, base); if (*endptr) { p_err("error parsing byte: %s", argv[i]); return NULL; @@ -868,23 +816,25 @@ static int do_help(int argc, char **argv) fprintf(stderr, "Usage: %s %s { show | list } [MAP]\n" - " %s %s dump MAP\n" - " %s %s update MAP key BYTES value VALUE [UPDATE_FLAGS]\n" - " %s %s lookup MAP key BYTES\n" - " %s %s getnext MAP [key BYTES]\n" - " %s %s delete MAP key BYTES\n" - " %s %s pin MAP FILE\n" + " %s %s dump MAP\n" + " %s %s update MAP key DATA value VALUE [UPDATE_FLAGS]\n" + " %s %s lookup MAP key DATA\n" + " %s %s getnext MAP [key DATA]\n" + " %s %s delete MAP key DATA\n" + " %s %s pin MAP FILE\n" + " %s %s event_pipe MAP [cpu N index M]\n" " %s %s help\n" "\n" " MAP := { id MAP_ID | pinned FILE }\n" + " DATA := { [hex] BYTES }\n" " " HELP_SPEC_PROGRAM "\n" - " VALUE := { BYTES | MAP | PROG }\n" + " VALUE := { DATA | MAP | PROG }\n" " UPDATE_FLAGS := { any | exist | noexist }\n" " " HELP_SPEC_OPTIONS "\n" "", bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2], - bin_name, argv[-2], bin_name, argv[-2]); + bin_name, argv[-2], bin_name, argv[-2], bin_name, argv[-2]); return 0; } @@ -899,6 +849,7 @@ static const struct cmd cmds[] = { { "getnext", do_getnext }, { "delete", do_delete }, { "pin", do_pin }, + { "event_pipe", do_event_pipe }, { 0 } }; diff --git a/tools/bpf/bpftool/map_perf_ring.c b/tools/bpf/bpftool/map_perf_ring.c new file mode 100644 index 000000000000..c5a2ced8552d --- /dev/null +++ b/tools/bpf/bpftool/map_perf_ring.c @@ -0,0 +1,347 @@ +// SPDX-License-Identifier: GPL-2.0-only +/* Copyright (C) 2018 Netronome Systems, Inc. */ +/* This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <errno.h> +#include <fcntl.h> +#include <libbpf.h> +#include <poll.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <time.h> +#include <unistd.h> +#include <linux/bpf.h> +#include <linux/perf_event.h> +#include <sys/ioctl.h> +#include <sys/mman.h> +#include <sys/syscall.h> + +#include <bpf.h> +#include <perf-sys.h> + +#include "main.h" + +#define MMAP_PAGE_CNT 16 + +static bool stop; + +struct event_ring_info { + int fd; + int key; + unsigned int cpu; + void *mem; +}; + +struct perf_event_sample { + struct perf_event_header header; + __u32 size; + unsigned char data[]; +}; + +static void int_exit(int signo) +{ + fprintf(stderr, "Stopping...\n"); + stop = true; +} + +static void +print_bpf_output(struct event_ring_info *ring, struct perf_event_sample *e) +{ + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = (void *)e; + struct timespec ts; + + if (clock_gettime(CLOCK_MONOTONIC, &ts)) { + perror("Can't read clock for timestamp"); + return; + } + + if (json_output) { + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "timestamp"); + jsonw_uint(json_wtr, ts.tv_sec * 1000000000ull + ts.tv_nsec); + jsonw_name(json_wtr, "type"); + jsonw_uint(json_wtr, e->header.type); + jsonw_name(json_wtr, "cpu"); + jsonw_uint(json_wtr, ring->cpu); + jsonw_name(json_wtr, "index"); + jsonw_uint(json_wtr, ring->key); + if (e->header.type == PERF_RECORD_SAMPLE) { + jsonw_name(json_wtr, "data"); + print_data_json(e->data, e->size); + } else if (e->header.type == PERF_RECORD_LOST) { + jsonw_name(json_wtr, "lost"); + jsonw_start_object(json_wtr); + jsonw_name(json_wtr, "id"); + jsonw_uint(json_wtr, lost->id); + jsonw_name(json_wtr, "count"); + jsonw_uint(json_wtr, lost->lost); + jsonw_end_object(json_wtr); + } + jsonw_end_object(json_wtr); + } else { + if (e->header.type == PERF_RECORD_SAMPLE) { + printf("== @%ld.%ld CPU: %d index: %d =====\n", + (long)ts.tv_sec, ts.tv_nsec, + ring->cpu, ring->key); + fprint_hex(stdout, e->data, e->size, " "); + printf("\n"); + } else if (e->header.type == PERF_RECORD_LOST) { + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + } +} + +static void +perf_event_read(struct event_ring_info *ring, void **buf, size_t *buf_len) +{ + volatile struct perf_event_mmap_page *header = ring->mem; + __u64 buffer_size = MMAP_PAGE_CNT * get_page_size(); + __u64 data_tail = header->data_tail; + __u64 data_head = header->data_head; + void *base, *begin, *end; + + asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ + if (data_head == data_tail) + return; + + base = ((char *)header) + get_page_size(); + + begin = base + data_tail % buffer_size; + end = base + data_head % buffer_size; + + while (begin != end) { + struct perf_event_sample *e; + + e = begin; + if (begin + e->header.size > base + buffer_size) { + long len = base + buffer_size - begin; + + if (*buf_len < e->header.size) { + free(*buf); + *buf = malloc(e->header.size); + if (!*buf) { + fprintf(stderr, + "can't allocate memory"); + stop = true; + return; + } + *buf_len = e->header.size; + } + + memcpy(*buf, begin, len); + memcpy(*buf + len, base, e->header.size - len); + e = (void *)*buf; + begin = base + e->header.size - len; + } else if (begin + e->header.size == base + buffer_size) { + begin = base; + } else { + begin += e->header.size; + } + + print_bpf_output(ring, e); + } + + __sync_synchronize(); /* smp_mb() */ + header->data_tail = data_head; +} + +static int perf_mmap_size(void) +{ + return get_page_size() * (MMAP_PAGE_CNT + 1); +} + +static void *perf_event_mmap(int fd) +{ + int mmap_size = perf_mmap_size(); + void *base; + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + p_err("event mmap failed: %s\n", strerror(errno)); + return NULL; + } + + return base; +} + +static void perf_event_unmap(void *mem) +{ + if (munmap(mem, perf_mmap_size())) + fprintf(stderr, "Can't unmap ring memory!\n"); +} + +static int bpf_perf_event_open(int map_fd, int key, int cpu) +{ + struct perf_event_attr attr = { + .sample_type = PERF_SAMPLE_RAW, + .type = PERF_TYPE_SOFTWARE, + .config = PERF_COUNT_SW_BPF_OUTPUT, + }; + int pmu_fd; + + pmu_fd = sys_perf_event_open(&attr, -1, cpu, -1, 0); + if (pmu_fd < 0) { + p_err("failed to open perf event %d for CPU %d", key, cpu); + return -1; + } + + if (bpf_map_update_elem(map_fd, &key, &pmu_fd, BPF_ANY)) { + p_err("failed to update map for event %d for CPU %d", key, cpu); + goto err_close; + } + if (ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0)) { + p_err("failed to enable event %d for CPU %d", key, cpu); + goto err_close; + } + + return pmu_fd; + +err_close: + close(pmu_fd); + return -1; +} + +int do_event_pipe(int argc, char **argv) +{ + int i, nfds, map_fd, index = -1, cpu = -1; + struct bpf_map_info map_info = {}; + struct event_ring_info *rings; + size_t tmp_buf_sz = 0; + void *tmp_buf = NULL; + struct pollfd *pfds; + __u32 map_info_len; + bool do_all = true; + + map_info_len = sizeof(map_info); + map_fd = map_parse_fd_and_info(&argc, &argv, &map_info, &map_info_len); + if (map_fd < 0) + return -1; + + if (map_info.type != BPF_MAP_TYPE_PERF_EVENT_ARRAY) { + p_err("map is not a perf event array"); + goto err_close_map; + } + + while (argc) { + if (argc < 2) + BAD_ARG(); + + if (is_prefix(*argv, "cpu")) { + char *endptr; + + NEXT_ARG(); + cpu = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as CPU ID", **argv); + goto err_close_map; + } + + NEXT_ARG(); + } else if (is_prefix(*argv, "index")) { + char *endptr; + + NEXT_ARG(); + index = strtoul(*argv, &endptr, 0); + if (*endptr) { + p_err("can't parse %s as index", **argv); + goto err_close_map; + } + + NEXT_ARG(); + } else { + BAD_ARG(); + } + + do_all = false; + } + + if (!do_all) { + if (index == -1 || cpu == -1) { + p_err("cpu and index must be specified together"); + goto err_close_map; + } + + nfds = 1; + } else { + nfds = min(get_possible_cpus(), map_info.max_entries); + cpu = 0; + index = 0; + } + + rings = calloc(nfds, sizeof(rings[0])); + if (!rings) + goto err_close_map; + + pfds = calloc(nfds, sizeof(pfds[0])); + if (!pfds) + goto err_free_rings; + + for (i = 0; i < nfds; i++) { + rings[i].cpu = cpu + i; + rings[i].key = index + i; + + rings[i].fd = bpf_perf_event_open(map_fd, rings[i].key, + rings[i].cpu); + if (rings[i].fd < 0) + goto err_close_fds_prev; + + rings[i].mem = perf_event_mmap(rings[i].fd); + if (!rings[i].mem) + goto err_close_fds_current; + + pfds[i].fd = rings[i].fd; + pfds[i].events = POLLIN; + } + + signal(SIGINT, int_exit); + signal(SIGHUP, int_exit); + signal(SIGTERM, int_exit); + + if (json_output) + jsonw_start_array(json_wtr); + + while (!stop) { + poll(pfds, nfds, 200); + for (i = 0; i < nfds; i++) + perf_event_read(&rings[i], &tmp_buf, &tmp_buf_sz); + } + free(tmp_buf); + + if (json_output) + jsonw_end_array(json_wtr); + + for (i = 0; i < nfds; i++) { + perf_event_unmap(rings[i].mem); + close(rings[i].fd); + } + free(pfds); + free(rings); + close(map_fd); + + return 0; + +err_close_fds_prev: + while (i--) { + perf_event_unmap(rings[i].mem); +err_close_fds_current: + close(rings[i].fd); + } + free(pfds); +err_free_rings: + free(rings); +err_close_map: + close(map_fd); + return -1; +} diff --git a/tools/bpf/bpftool/prog.c b/tools/bpf/bpftool/prog.c index f7a810897eac..9bdfdf2d3fbe 100644 --- a/tools/bpf/bpftool/prog.c +++ b/tools/bpf/bpftool/prog.c @@ -68,6 +68,9 @@ static const char * const prog_type_name[] = { [BPF_PROG_TYPE_SOCK_OPS] = "sock_ops", [BPF_PROG_TYPE_SK_SKB] = "sk_skb", [BPF_PROG_TYPE_CGROUP_DEVICE] = "cgroup_device", + [BPF_PROG_TYPE_SK_MSG] = "sk_msg", + [BPF_PROG_TYPE_RAW_TRACEPOINT] = "raw_tracepoint", + [BPF_PROG_TYPE_CGROUP_SOCK_ADDR] = "cgroup_sock_addr", }; static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) @@ -93,7 +96,10 @@ static void print_boot_time(__u64 nsecs, char *buf, unsigned int size) return; } - strftime(buf, size, "%b %d/%H:%M", &load_tm); + if (json_output) + strftime(buf, size, "%s", &load_tm); + else + strftime(buf, size, "%FT%T%z", &load_tm); } static int prog_fd_by_tag(unsigned char *tag) @@ -232,6 +238,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) info->tag[0], info->tag[1], info->tag[2], info->tag[3], info->tag[4], info->tag[5], info->tag[6], info->tag[7]); + jsonw_bool_field(json_wtr, "gpl_compatible", info->gpl_compatible); + print_dev_json(info->ifindex, info->netns_dev, info->netns_ino); if (info->load_time) { @@ -240,7 +248,8 @@ static void print_prog_json(struct bpf_prog_info *info, int fd) print_boot_time(info->load_time, buf, sizeof(buf)); /* Piggy back on load_time, since 0 uid is a valid one */ - jsonw_string_field(json_wtr, "loaded_at", buf); + jsonw_name(json_wtr, "loaded_at"); + jsonw_printf(json_wtr, "%s", buf); jsonw_uint_field(json_wtr, "uid", info->created_by_uid); } @@ -292,6 +301,7 @@ static void print_prog_plain(struct bpf_prog_info *info, int fd) printf("tag "); fprint_hex(stdout, info->tag, BPF_TAG_SIZE, ""); print_dev_plain(info->ifindex, info->netns_dev, info->netns_ino); + printf("%s", info->gpl_compatible ? " gpl" : ""); printf("\n"); if (info->load_time) { diff --git a/tools/include/uapi/linux/bpf.h b/tools/include/uapi/linux/bpf.h index c5ec89732a8d..83a95ae388dd 100644 --- a/tools/include/uapi/linux/bpf.h +++ b/tools/include/uapi/linux/bpf.h @@ -95,6 +95,7 @@ enum bpf_cmd { BPF_OBJ_GET_INFO_BY_FD, BPF_PROG_QUERY, BPF_RAW_TRACEPOINT_OPEN, + BPF_BTF_LOAD, }; enum bpf_map_type { @@ -279,6 +280,9 @@ union bpf_attr { */ char map_name[BPF_OBJ_NAME_LEN]; __u32 map_ifindex; /* ifindex of netdev to create on */ + __u32 btf_fd; /* fd pointing to a BTF type data */ + __u32 btf_key_id; /* BTF type_id of the key */ + __u32 btf_value_id; /* BTF type_id of the value */ }; struct { /* anonymous struct used by BPF_MAP_*_ELEM commands */ @@ -363,398 +367,1464 @@ union bpf_attr { __u64 name; __u32 prog_fd; } raw_tracepoint; + + struct { /* anonymous struct for BPF_BTF_LOAD */ + __aligned_u64 btf; + __aligned_u64 btf_log_buf; + __u32 btf_size; + __u32 btf_log_size; + __u32 btf_log_level; + }; } __attribute__((aligned(8))); -/* BPF helper function descriptions: - * - * void *bpf_map_lookup_elem(&map, &key) - * Return: Map value or NULL - * - * int bpf_map_update_elem(&map, &key, &value, flags) - * Return: 0 on success or negative error - * - * int bpf_map_delete_elem(&map, &key) - * Return: 0 on success or negative error - * - * int bpf_probe_read(void *dst, int size, void *src) - * Return: 0 on success or negative error +/* The description below is an attempt at providing documentation to eBPF + * developers about the multiple available eBPF helper functions. It can be + * parsed and used to produce a manual page. The workflow is the following, + * and requires the rst2man utility: + * + * $ ./scripts/bpf_helpers_doc.py \ + * --filename include/uapi/linux/bpf.h > /tmp/bpf-helpers.rst + * $ rst2man /tmp/bpf-helpers.rst > /tmp/bpf-helpers.7 + * $ man /tmp/bpf-helpers.7 + * + * Note that in order to produce this external documentation, some RST + * formatting is used in the descriptions to get "bold" and "italics" in + * manual pages. Also note that the few trailing white spaces are + * intentional, removing them would break paragraphs for rst2man. + * + * Start of BPF helper function descriptions: + * + * void *bpf_map_lookup_elem(struct bpf_map *map, const void *key) + * Description + * Perform a lookup in *map* for an entry associated to *key*. + * Return + * Map value associated to *key*, or **NULL** if no entry was + * found. + * + * int bpf_map_update_elem(struct bpf_map *map, const void *key, const void *value, u64 flags) + * Description + * Add or update the value of the entry associated to *key* in + * *map* with *value*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * Flag value **BPF_NOEXIST** cannot be used for maps of types + * **BPF_MAP_TYPE_ARRAY** or **BPF_MAP_TYPE_PERCPU_ARRAY** (all + * elements always exist), the helper would return an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_map_delete_elem(struct bpf_map *map, const void *key) + * Description + * Delete entry with *key* from *map*. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_probe_read(void *dst, u32 size, const void *src) + * Description + * For tracing programs, safely attempt to read *size* bytes from + * address *src* and store the data in *dst*. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_ktime_get_ns(void) - * Return: current ktime - * - * int bpf_trace_printk(const char *fmt, int fmt_size, ...) - * Return: length of buffer written or negative error - * - * u32 bpf_prandom_u32(void) - * Return: random value - * - * u32 bpf_raw_smp_processor_id(void) - * Return: SMP processor ID - * - * int bpf_skb_store_bytes(skb, offset, from, len, flags) - * store bytes into packet - * @skb: pointer to skb - * @offset: offset within packet from skb->mac_header - * @from: pointer where to copy bytes from - * @len: number of bytes to store into packet - * @flags: bit 0 - if true, recompute skb->csum - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l3_csum_replace(skb, offset, from, to, flags) - * recompute IP checksum - * @skb: pointer to skb - * @offset: offset within packet where IP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_l4_csum_replace(skb, offset, from, to, flags) - * recompute TCP/UDP checksum - * @skb: pointer to skb - * @offset: offset within packet where TCP/UDP checksum is located - * @from: old value of header field - * @to: new value of header field - * @flags: bits 0-3 - size of header field - * bit 4 - is pseudo header - * other bits - reserved - * Return: 0 on success or negative error - * - * int bpf_tail_call(ctx, prog_array_map, index) - * jump into another BPF program - * @ctx: context pointer passed to next program - * @prog_array_map: pointer to map which type is BPF_MAP_TYPE_PROG_ARRAY - * @index: 32-bit index inside array that selects specific program to run - * Return: 0 on success or negative error - * - * int bpf_clone_redirect(skb, ifindex, flags) - * redirect to another netdev - * @skb: pointer to skb - * @ifindex: ifindex of the net device - * @flags: bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * Return: 0 on success or negative error + * Description + * Return the time elapsed since system boot, in nanoseconds. + * Return + * Current *ktime*. + * + * int bpf_trace_printk(const char *fmt, u32 fmt_size, ...) + * Description + * This helper is a "printk()-like" facility for debugging. It + * prints a message defined by format *fmt* (of size *fmt_size*) + * to file *\/sys/kernel/debug/tracing/trace* from DebugFS, if + * available. It can take up to three additional **u64** + * arguments (as an eBPF helpers, the total number of arguments is + * limited to five). + * + * Each time the helper is called, it appends a line to the trace. + * The format of the trace is customizable, and the exact output + * one will get depends on the options set in + * *\/sys/kernel/debug/tracing/trace_options* (see also the + * *README* file under the same directory). However, it usually + * defaults to something like: + * + * :: + * + * telnet-470 [001] .N.. 419421.045894: 0x00000001: <formatted msg> + * + * In the above: + * + * * ``telnet`` is the name of the current task. + * * ``470`` is the PID of the current task. + * * ``001`` is the CPU number on which the task is + * running. + * * In ``.N..``, each character refers to a set of + * options (whether irqs are enabled, scheduling + * options, whether hard/softirqs are running, level of + * preempt_disabled respectively). **N** means that + * **TIF_NEED_RESCHED** and **PREEMPT_NEED_RESCHED** + * are set. + * * ``419421.045894`` is a timestamp. + * * ``0x00000001`` is a fake value used by BPF for the + * instruction pointer register. + * * ``<formatted msg>`` is the message formatted with + * *fmt*. + * + * The conversion specifiers supported by *fmt* are similar, but + * more limited than for printk(). They are **%d**, **%i**, + * **%u**, **%x**, **%ld**, **%li**, **%lu**, **%lx**, **%lld**, + * **%lli**, **%llu**, **%llx**, **%p**, **%s**. No modifier (size + * of field, padding with zeroes, etc.) is available, and the + * helper will return **-EINVAL** (but print nothing) if it + * encounters an unknown specifier. + * + * Also, note that **bpf_trace_printk**\ () is slow, and should + * only be used for debugging purposes. For this reason, a notice + * bloc (spanning several lines) is printed to kernel logs and + * states that the helper should not be used "for production use" + * the first time this helper is used (or more precisely, when + * **trace_printk**\ () buffers are allocated). For passing values + * to user space, perf events should be preferred. + * Return + * The number of bytes written to the buffer, or a negative error + * in case of failure. + * + * u32 bpf_get_prandom_u32(void) + * Description + * Get a pseudo-random number. + * + * From a security point of view, this helper uses its own + * pseudo-random internal state, and cannot be used to infer the + * seed of other random functions in the kernel. However, it is + * essential to note that the generator used by the helper is not + * cryptographically secure. + * Return + * A random 32-bit unsigned value. + * + * u32 bpf_get_smp_processor_id(void) + * Description + * Get the SMP (symmetric multiprocessing) processor id. Note that + * all programs run with preemption disabled, which means that the + * SMP processor id is stable during all the execution of the + * program. + * Return + * The SMP id of the processor running the program. + * + * int bpf_skb_store_bytes(struct sk_buff *skb, u32 offset, const void *from, u32 len, u64 flags) + * Description + * Store *len* bytes from address *from* into the packet + * associated to *skb*, at *offset*. *flags* are a combination of + * **BPF_F_RECOMPUTE_CSUM** (automatically recompute the + * checksum for the packet after storing the bytes) and + * **BPF_F_INVALIDATE_HASH** (set *skb*\ **->hash**, *skb*\ + * **->swhash** and *skb*\ **->l4hash** to 0). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l3_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 size) + * Description + * Recompute the layer 3 (e.g. IP) checksum for the packet + * associated to *skb*. Computation is incremental, so the helper + * must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored in *size*. + * Alternatively, it is possible to store the difference between + * the previous and the new values of the header field in *to*, by + * setting *from* and *size* to 0. For both methods, *offset* + * indicates the location of the IP checksum within the packet. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_l4_csum_replace(struct sk_buff *skb, u32 offset, u64 from, u64 to, u64 flags) + * Description + * Recompute the layer 4 (e.g. TCP, UDP or ICMP) checksum for the + * packet associated to *skb*. Computation is incremental, so the + * helper must know the former value of the header field that was + * modified (*from*), the new value of this field (*to*), and the + * number of bytes (2 or 4) for this field, stored on the lowest + * four bits of *flags*. Alternatively, it is possible to store + * the difference between the previous and the new values of the + * header field in *to*, by setting *from* and the four lowest + * bits of *flags* to 0. For both methods, *offset* indicates the + * location of the IP checksum within the packet. In addition to + * the size of the field, *flags* can be added (bitwise OR) actual + * flags. With **BPF_F_MARK_MANGLED_0**, a null checksum is left + * untouched (unless **BPF_F_MARK_ENFORCE** is added as well), and + * for updates resulting in a null checksum the value is set to + * **CSUM_MANGLED_0** instead. Flag **BPF_F_PSEUDO_HDR** indicates + * the checksum is to be computed against a pseudo-header. + * + * This helper works in combination with **bpf_csum_diff**\ (), + * which does not update the checksum in-place, but offers more + * flexibility and can handle sizes larger than 2 or 4 for the + * checksum to update. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_tail_call(void *ctx, struct bpf_map *prog_array_map, u32 index) + * Description + * This special helper is used to trigger a "tail call", or in + * other words, to jump into another eBPF program. The same stack + * frame is used (but values on stack and in registers for the + * caller are not accessible to the callee). This mechanism allows + * for program chaining, either for raising the maximum number of + * available eBPF instructions, or to execute given programs in + * conditional blocks. For security reasons, there is an upper + * limit to the number of successive tail calls that can be + * performed. + * + * Upon call of this helper, the program attempts to jump into a + * program referenced at index *index* in *prog_array_map*, a + * special map of type **BPF_MAP_TYPE_PROG_ARRAY**, and passes + * *ctx*, a pointer to the context. + * + * If the call succeeds, the kernel immediately runs the first + * instruction of the new program. This is not a function call, + * and it never returns to the previous program. If the call + * fails, then the helper has no effect, and the caller continues + * to run its subsequent instructions. A call can fail if the + * destination program for the jump does not exist (i.e. *index* + * is superior to the number of entries in *prog_array_map*), or + * if the maximum number of tail calls has been reached for this + * chain of programs. This limit is defined in the kernel by the + * macro **MAX_TAIL_CALL_CNT** (not accessible to user space), + * which is currently set to 32. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_clone_redirect(struct sk_buff *skb, u32 ifindex, u64 flags) + * Description + * Clone and redirect the packet associated to *skb* to another + * net device of index *ifindex*. Both ingress and egress + * interfaces can be used for redirection. The **BPF_F_INGRESS** + * value in *flags* is used to make the distinction (ingress path + * is selected if the flag is present, egress path otherwise). + * This is the only flag supported for now. + * + * In comparison with **bpf_redirect**\ () helper, + * **bpf_clone_redirect**\ () has the associated cost of + * duplicating the packet buffer, but this can be executed out of + * the eBPF program. Conversely, **bpf_redirect**\ () is more + * efficient, but it is handled through an action code where the + * redirection happens only after the eBPF program has returned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * u64 bpf_get_current_pid_tgid(void) - * Return: current->tgid << 32 | current->pid + * Return + * A 64-bit integer containing the current tgid and pid, and + * created as such: + * *current_task*\ **->tgid << 32 \|** + * *current_task*\ **->pid**. * * u64 bpf_get_current_uid_gid(void) - * Return: current_gid << 32 | current_uid - * - * int bpf_get_current_comm(char *buf, int size_of_buf) - * stores current->comm into buf - * Return: 0 on success or negative error - * - * u32 bpf_get_cgroup_classid(skb) - * retrieve a proc's classid - * @skb: pointer to skb - * Return: classid if != 0 - * - * int bpf_skb_vlan_push(skb, vlan_proto, vlan_tci) - * Return: 0 on success or negative error - * - * int bpf_skb_vlan_pop(skb) - * Return: 0 on success or negative error - * - * int bpf_skb_get_tunnel_key(skb, key, size, flags) - * int bpf_skb_set_tunnel_key(skb, key, size, flags) - * retrieve or populate tunnel metadata - * @skb: pointer to skb - * @key: pointer to 'struct bpf_tunnel_key' - * @size: size of 'struct bpf_tunnel_key' - * @flags: room for future extensions - * Return: 0 on success or negative error - * - * u64 bpf_perf_event_read(map, flags) - * read perf event counter value - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * Return: value of perf event counter read or error code - * - * int bpf_redirect(ifindex, flags) - * redirect to another netdev - * @ifindex: ifindex of the net device - * @flags: - * cls_bpf: - * bit 0 - if set, redirect to ingress instead of egress - * other bits - reserved - * xdp_bpf: - * all bits - reserved - * Return: cls_bpf: TC_ACT_REDIRECT on success or TC_ACT_SHOT on error - * xdp_bfp: XDP_REDIRECT on success or XDP_ABORT on error - * int bpf_redirect_map(map, key, flags) - * redirect to endpoint in map - * @map: pointer to dev map - * @key: index in map to lookup - * @flags: -- - * Return: XDP_REDIRECT on success or XDP_ABORT on error - * - * u32 bpf_get_route_realm(skb) - * retrieve a dst's tclassid - * @skb: pointer to skb - * Return: realm if != 0 - * - * int bpf_perf_event_output(ctx, map, flags, data, size) - * output perf raw sample - * @ctx: struct pt_regs* - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @data: data on stack to be output as raw data - * @size: size of data - * Return: 0 on success or negative error - * - * int bpf_get_stackid(ctx, map, flags) - * walk user or kernel stack and return id - * @ctx: struct pt_regs* - * @map: pointer to stack_trace map - * @flags: bits 0-7 - numer of stack frames to skip - * bit 8 - collect user stack instead of kernel - * bit 9 - compare stacks by hash only - * bit 10 - if two different stacks hash into the same stackid - * discard old - * other bits - reserved - * Return: >= 0 stackid on success or negative error - * - * s64 bpf_csum_diff(from, from_size, to, to_size, seed) - * calculate csum diff - * @from: raw from buffer - * @from_size: length of from buffer - * @to: raw to buffer - * @to_size: length of to buffer - * @seed: optional seed - * Return: csum result or negative error code - * - * int bpf_skb_get_tunnel_opt(skb, opt, size) - * retrieve tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: option size - * - * int bpf_skb_set_tunnel_opt(skb, opt, size) - * populate tunnel options metadata - * @skb: pointer to skb - * @opt: pointer to raw tunnel option data - * @size: size of @opt - * Return: 0 on success or negative error - * - * int bpf_skb_change_proto(skb, proto, flags) - * Change protocol of the skb. Currently supported is v4 -> v6, - * v6 -> v4 transitions. The helper will also resize the skb. eBPF - * program is expected to fill the new headers via skb_store_bytes - * and lX_csum_replace. - * @skb: pointer to skb - * @proto: new skb->protocol type - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_change_type(skb, type) - * Change packet type of skb. - * @skb: pointer to skb - * @type: new skb->pkt_type type - * Return: 0 on success or negative error - * - * int bpf_skb_under_cgroup(skb, map, index) - * Check cgroup2 membership of skb - * @skb: pointer to skb - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 skb failed the cgroup2 descendant test - * == 1 skb succeeded the cgroup2 descendant test - * < 0 error - * - * u32 bpf_get_hash_recalc(skb) - * Retrieve and possibly recalculate skb->hash. - * @skb: pointer to skb - * Return: hash + * Return + * A 64-bit integer containing the current GID and UID, and + * created as such: *current_gid* **<< 32 \|** *current_uid*. + * + * int bpf_get_current_comm(char *buf, u32 size_of_buf) + * Description + * Copy the **comm** attribute of the current task into *buf* of + * *size_of_buf*. The **comm** attribute contains the name of + * the executable (excluding the path) for the current task. The + * *size_of_buf* must be strictly positive. On success, the + * helper makes sure that the *buf* is NUL-terminated. On failure, + * it is filled with zeroes. + * Return + * 0 on success, or a negative error in case of failure. + * + * u32 bpf_get_cgroup_classid(struct sk_buff *skb) + * Description + * Retrieve the classid for the current task, i.e. for the net_cls + * cgroup to which *skb* belongs. + * + * This helper can be used on TC egress path, but not on ingress. + * + * The net_cls cgroup provides an interface to tag network packets + * based on a user-provided identifier for all traffic coming from + * the tasks belonging to the related cgroup. See also the related + * kernel documentation, available from the Linux sources in file + * *Documentation/cgroup-v1/net_cls.txt*. + * + * The Linux kernel has two versions for cgroups: there are + * cgroups v1 and cgroups v2. Both are available to users, who can + * use a mixture of them, but note that the net_cls cgroup is for + * cgroup v1 only. This makes it incompatible with BPF programs + * run on cgroups, which is a cgroup-v2-only feature (a socket can + * only hold data for one version of cgroups at a time). + * + * This helper is only available is the kernel was compiled with + * the **CONFIG_CGROUP_NET_CLASSID** configuration option set to + * "**y**" or to "**m**". + * Return + * The classid, or 0 for the default unconfigured classid. + * + * int bpf_skb_vlan_push(struct sk_buff *skb, __be16 vlan_proto, u16 vlan_tci) + * Description + * Push a *vlan_tci* (VLAN tag control information) of protocol + * *vlan_proto* to the packet associated to *skb*, then update + * the checksum. Note that if *vlan_proto* is different from + * **ETH_P_8021Q** and **ETH_P_8021AD**, it is considered to + * be **ETH_P_8021Q**. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_vlan_pop(struct sk_buff *skb) + * Description + * Pop a VLAN header from the packet associated to *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Get tunnel metadata. This helper takes a pointer *key* to an + * empty **struct bpf_tunnel_key** of **size**, that will be + * filled with tunnel metadata for the packet associated to *skb*. + * The *flags* can be set to **BPF_F_TUNINFO_IPV6**, which + * indicates that the tunnel is based on IPv6 protocol instead of + * IPv4. + * + * The **struct bpf_tunnel_key** is an object that generalizes the + * principal parameters used by various tunneling protocols into a + * single struct. This way, it can be used to easily make a + * decision based on the contents of the encapsulation header, + * "summarized" in this struct. In particular, it holds the IP + * address of the remote end (IPv4 or IPv6, depending on the case) + * in *key*\ **->remote_ipv4** or *key*\ **->remote_ipv6**. Also, + * this struct exposes the *key*\ **->tunnel_id**, which is + * generally mapped to a VNI (Virtual Network Identifier), making + * it programmable together with the **bpf_skb_set_tunnel_key**\ + * () helper. + * + * Let's imagine that the following code is part of a program + * attached to the TC ingress interface, on one end of a GRE + * tunnel, and is supposed to filter out all messages coming from + * remote ends with IPv4 address other than 10.0.0.1: + * + * :: + * + * int ret; + * struct bpf_tunnel_key key = {}; + * + * ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); + * if (ret < 0) + * return TC_ACT_SHOT; // drop packet + * + * if (key.remote_ipv4 != 0x0a000001) + * return TC_ACT_SHOT; // drop packet + * + * return TC_ACT_OK; // accept packet + * + * This interface can also be used with all encapsulation devices + * that can operate in "collect metadata" mode: instead of having + * one network device per specific configuration, the "collect + * metadata" mode only requires a single device where the + * configuration can be extracted from this helper. + * + * This can be used together with various tunnels such as VXLan, + * Geneve, GRE or IP in IP (IPIP). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_set_tunnel_key(struct sk_buff *skb, struct bpf_tunnel_key *key, u32 size, u64 flags) + * Description + * Populate tunnel metadata for packet associated to *skb.* The + * tunnel metadata is set to the contents of *key*, of *size*. The + * *flags* can be set to a combination of the following values: + * + * **BPF_F_TUNINFO_IPV6** + * Indicate that the tunnel is based on IPv6 protocol + * instead of IPv4. + * **BPF_F_ZERO_CSUM_TX** + * For IPv4 packets, add a flag to tunnel metadata + * indicating that checksum computation should be skipped + * and checksum set to zeroes. + * **BPF_F_DONT_FRAGMENT** + * Add a flag to tunnel metadata indicating that the + * packet should not be fragmented. + * **BPF_F_SEQ_NUMBER** + * Add a flag to tunnel metadata indicating that a + * sequence number should be added to tunnel header before + * sending the packet. This flag was added for GRE + * encapsulation, but might be used with other protocols + * as well in the future. + * + * Here is a typical usage on the transmit path: + * + * :: + * + * struct bpf_tunnel_key key; + * populate key ... + * bpf_skb_set_tunnel_key(skb, &key, sizeof(key), 0); + * bpf_clone_redirect(skb, vxlan_dev_ifindex, 0); + * + * See also the description of the **bpf_skb_get_tunnel_key**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * u64 bpf_perf_event_read(struct bpf_map *map, u64 flags) + * Description + * Read the value of a perf event counter. This helper relies on a + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of + * the perf event counter is selected when *map* is updated with + * perf event file descriptors. The *map* is an array whose size + * is the number of available CPUs, and each cell contains a value + * relative to one CPU. The value to retrieve is indicated by + * *flags*, that contains the index of the CPU to look up, masked + * with **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * Note that before Linux 4.13, only hardware perf event can be + * retrieved. + * + * Also, be aware that the newer helper + * **bpf_perf_event_read_value**\ () is recommended over + * **bpf_perf_event_read**\ () in general. The latter has some ABI + * quirks where error and counter value are used as a return code + * (which is wrong to do since ranges may overlap). This issue is + * fixed with **bpf_perf_event_read_value**\ (), which at the same + * time provides more features over the **bpf_perf_event_read**\ + * () interface. Please refer to the description of + * **bpf_perf_event_read_value**\ () for details. + * Return + * The value of the perf event counter read from the map, or a + * negative error code in case of failure. + * + * int bpf_redirect(u32 ifindex, u64 flags) + * Description + * Redirect the packet to another net device of index *ifindex*. + * This helper is somewhat similar to **bpf_clone_redirect**\ + * (), except that the packet is not cloned, which provides + * increased performance. + * + * Except for XDP, both ingress and egress interfaces can be used + * for redirection. The **BPF_F_INGRESS** value in *flags* is used + * to make the distinction (ingress path is selected if the flag + * is present, egress path otherwise). Currently, XDP only + * supports redirection to the egress interface, and accepts no + * flag at all. + * + * The same effect can be attained with the more generic + * **bpf_redirect_map**\ (), which requires specific maps to be + * used but offers better performance. + * Return + * For XDP, the helper returns **XDP_REDIRECT** on success or + * **XDP_ABORTED** on error. For other program types, the values + * are **TC_ACT_REDIRECT** on success or **TC_ACT_SHOT** on + * error. + * + * u32 bpf_get_route_realm(struct sk_buff *skb) + * Description + * Retrieve the realm or the route, that is to say the + * **tclassid** field of the destination for the *skb*. The + * indentifier retrieved is a user-provided tag, similar to the + * one used with the net_cls cgroup (see description for + * **bpf_get_cgroup_classid**\ () helper), but here this tag is + * held by a route (a destination entry), not by a task. + * + * Retrieving this identifier works with the clsact TC egress hook + * (see also **tc-bpf(8)**), or alternatively on conventional + * classful egress qdiscs, but not on TC ingress path. In case of + * clsact TC egress hook, this has the advantage that, internally, + * the destination entry has not been dropped yet in the transmit + * path. Therefore, the destination entry does not need to be + * artificially held via **netif_keep_dst**\ () for a classful + * qdisc until the *skb* is freed. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_IP_ROUTE_CLASSID** configuration option. + * Return + * The realm of the route for the packet associated to *skb*, or 0 + * if none was found. + * + * int bpf_perf_event_output(struct pt_reg *ctx, struct bpf_map *map, u64 flags, void *data, u64 size) + * Description + * Write raw *data* blob into a special BPF perf event held by + * *map* of type **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. This perf + * event must have the following attributes: **PERF_SAMPLE_RAW** + * as **sample_type**, **PERF_TYPE_SOFTWARE** as **type**, and + * **PERF_COUNT_SW_BPF_OUTPUT** as **config**. + * + * The *flags* are used to indicate the index in *map* for which + * the value must be put, masked with **BPF_F_INDEX_MASK**. + * Alternatively, *flags* can be set to **BPF_F_CURRENT_CPU** + * to indicate that the index of the current CPU core should be + * used. + * + * The value to write, of *size*, is passed through eBPF stack and + * pointed by *data*. + * + * The context of the program *ctx* needs also be passed to the + * helper. + * + * On user space, a program willing to read the values needs to + * call **perf_event_open**\ () on the perf event (either for + * one or for all CPUs) and to store the file descriptor into the + * *map*. This must be done before the eBPF program can send data + * into it. An example is available in file + * *samples/bpf/trace_output_user.c* in the Linux kernel source + * tree (the eBPF program counterpart is in + * *samples/bpf/trace_output_kern.c*). + * + * **bpf_perf_event_output**\ () achieves better performance + * than **bpf_trace_printk**\ () for sharing data with user + * space, and is much better suitable for streaming data from eBPF + * programs. + * + * Note that this helper is not restricted to tracing use cases + * and can be used with programs attached to TC or XDP as well, + * where it allows for passing data to user space listeners. Data + * can be: + * + * * Only custom structs, + * * Only the packet payload, or + * * A combination of both. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_load_bytes(const struct sk_buff *skb, u32 offset, void *to, u32 len) + * Description + * This helper was provided as an easy way to load data from a + * packet. It can be used to load *len* bytes from *offset* from + * the packet associated to *skb*, into the buffer pointed by + * *to*. + * + * Since Linux 4.7, usage of this helper has mostly been replaced + * by "direct packet access", enabling packet data to be + * manipulated with *skb*\ **->data** and *skb*\ **->data_end** + * pointing respectively to the first byte of packet data and to + * the byte after the last byte of packet data. However, it + * remains useful if one wishes to read large quantities of data + * at once from a packet into the eBPF stack. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stackid(struct pt_reg *ctx, struct bpf_map *map, u64 flags) + * Description + * Walk a user or a kernel stack and return its id. To achieve + * this, the helper needs *ctx*, which is a pointer to the context + * on which the tracing program is executed, and a pointer to a + * *map* of type **BPF_MAP_TYPE_STACK_TRACE**. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * a combination of the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_FAST_STACK_CMP** + * Compare stacks by hash only. + * **BPF_F_REUSE_STACKID** + * If two different stacks hash into the same *stackid*, + * discard the old one. + * + * The stack id retrieved is a 32 bit long integer handle which + * can be further combined with other data (including other stack + * ids) and used as a key into maps. This can be useful for + * generating a variety of graphs (such as flame graphs or off-cpu + * graphs). + * + * For walking a stack, this helper is an improvement over + * **bpf_probe_read**\ (), which can be used with unrolled loops + * but is not efficient and consumes a lot of eBPF instructions. + * Instead, **bpf_get_stackid**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * + * Return + * The positive or null stack id on success, or a negative error + * in case of failure. + * + * s64 bpf_csum_diff(__be32 *from, u32 from_size, __be32 *to, u32 to_size, __wsum seed) + * Description + * Compute a checksum difference, from the raw buffer pointed by + * *from*, of length *from_size* (that must be a multiple of 4), + * towards the raw buffer pointed by *to*, of size *to_size* + * (same remark). An optional *seed* can be added to the value + * (this can be cascaded, the seed may come from a previous call + * to the helper). + * + * This is flexible enough to be used in several ways: + * + * * With *from_size* == 0, *to_size* > 0 and *seed* set to + * checksum, it can be used when pushing new data. + * * With *from_size* > 0, *to_size* == 0 and *seed* set to + * checksum, it can be used when removing data from a packet. + * * With *from_size* > 0, *to_size* > 0 and *seed* set to 0, it + * can be used to compute a diff. Note that *from_size* and + * *to_size* do not need to be equal. + * + * This helper can be used in combination with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ (), to + * which one can feed in the difference computed with + * **bpf_csum_diff**\ (). + * Return + * The checksum result, or a negative error code in case of + * failure. + * + * int bpf_skb_get_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Retrieve tunnel options metadata for the packet associated to + * *skb*, and store the raw tunnel option data to the buffer *opt* + * of *size*. + * + * This helper can be used with encapsulation devices that can + * operate in "collect metadata" mode (please refer to the related + * note in the description of **bpf_skb_get_tunnel_key**\ () for + * more details). A particular example where this can be used is + * in combination with the Geneve encapsulation protocol, where it + * allows for pushing (with **bpf_skb_get_tunnel_opt**\ () helper) + * and retrieving arbitrary TLVs (Type-Length-Value headers) from + * the eBPF program. This allows for full customization of these + * headers. + * Return + * The size of the option data retrieved. + * + * int bpf_skb_set_tunnel_opt(struct sk_buff *skb, u8 *opt, u32 size) + * Description + * Set tunnel options metadata for the packet associated to *skb* + * to the option data contained in the raw buffer *opt* of *size*. + * + * See also the description of the **bpf_skb_get_tunnel_opt**\ () + * helper for additional information. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_proto(struct sk_buff *skb, __be16 proto, u64 flags) + * Description + * Change the protocol of the *skb* to *proto*. Currently + * supported are transition from IPv4 to IPv6, and from IPv6 to + * IPv4. The helper takes care of the groundwork for the + * transition, including resizing the socket buffer. The eBPF + * program is expected to fill the new headers, if any, via + * **skb_store_bytes**\ () and to recompute the checksums with + * **bpf_l3_csum_replace**\ () and **bpf_l4_csum_replace**\ + * (). The main case for this helper is to perform NAT64 + * operations out of an eBPF program. + * + * Internally, the GSO type is marked as dodgy so that headers are + * checked and segments are recalculated by the GSO/GRO engine. + * The size for GSO target is adapted as well. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_change_type(struct sk_buff *skb, u32 type) + * Description + * Change the packet type for the packet associated to *skb*. This + * comes down to setting *skb*\ **->pkt_type** to *type*, except + * the eBPF program does not have a write access to *skb*\ + * **->pkt_type** beside this helper. Using a helper here allows + * for graceful handling of errors. + * + * The major use case is to change incoming *skb*s to + * **PACKET_HOST** in a programmatic way instead of having to + * recirculate via **redirect**\ (..., **BPF_F_INGRESS**), for + * example. + * + * Note that *type* only allows certain values. At this time, they + * are: + * + * **PACKET_HOST** + * Packet is for us. + * **PACKET_BROADCAST** + * Send packet to all. + * **PACKET_MULTICAST** + * Send packet to group. + * **PACKET_OTHERHOST** + * Send packet to someone else. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_under_cgroup(struct sk_buff *skb, struct bpf_map *map, u32 index) + * Description + * Check whether *skb* is a descendant of the cgroup2 held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* failed the cgroup2 descendant test. + * * 1, if the *skb* succeeded the cgroup2 descendant test. + * * A negative error code, if an error occurred. + * + * u32 bpf_get_hash_recalc(struct sk_buff *skb) + * Description + * Retrieve the hash of the packet, *skb*\ **->hash**. If it is + * not set, in particular if the hash was cleared due to mangling, + * recompute this hash. Later accesses to the hash can be done + * directly with *skb*\ **->hash**. + * + * Calling **bpf_set_hash_invalid**\ (), changing a packet + * prototype with **bpf_skb_change_proto**\ (), or calling + * **bpf_skb_store_bytes**\ () with the + * **BPF_F_INVALIDATE_HASH** are actions susceptible to clear + * the hash and to trigger a new computation for the next call to + * **bpf_get_hash_recalc**\ (). + * Return + * The 32-bit hash. * * u64 bpf_get_current_task(void) - * Returns current task_struct - * Return: current - * - * int bpf_probe_write_user(void *dst, void *src, int len) - * safely attempt to write to a location - * @dst: destination address in userspace - * @src: source address on stack - * @len: number of bytes to copy - * Return: 0 on success or negative error - * - * int bpf_current_task_under_cgroup(map, index) - * Check cgroup2 membership of current task - * @map: pointer to bpf_map in BPF_MAP_TYPE_CGROUP_ARRAY type - * @index: index of the cgroup in the bpf_map - * Return: - * == 0 current failed the cgroup2 descendant test - * == 1 current succeeded the cgroup2 descendant test - * < 0 error - * - * int bpf_skb_change_tail(skb, len, flags) - * The helper will resize the skb to the given new size, to be used f.e. - * with control messages. - * @skb: pointer to skb - * @len: new skb length - * @flags: reserved - * Return: 0 on success or negative error - * - * int bpf_skb_pull_data(skb, len) - * The helper will pull in non-linear data in case the skb is non-linear - * and not all of len are part of the linear section. Only needed for - * read/write with direct packet access. - * @skb: pointer to skb - * @len: len to make read/writeable - * Return: 0 on success or negative error - * - * s64 bpf_csum_update(skb, csum) - * Adds csum into skb->csum in case of CHECKSUM_COMPLETE. - * @skb: pointer to skb - * @csum: csum to add - * Return: csum on success or negative error - * - * void bpf_set_hash_invalid(skb) - * Invalidate current skb->hash. - * @skb: pointer to skb - * - * int bpf_get_numa_node_id() - * Return: Id of current NUMA node. - * - * int bpf_skb_change_head() - * Grows headroom of skb and adjusts MAC header offset accordingly. - * Will extends/reallocae as required automatically. - * May change skb data pointer and will thus invalidate any check - * performed for direct packet access. - * @skb: pointer to skb - * @len: length of header to be pushed in front - * @flags: Flags (unused for now) - * Return: 0 on success or negative error - * - * int bpf_xdp_adjust_head(xdp_md, delta) - * Adjust the xdp_md.data by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data - * Return: 0 on success or negative on error + * Return + * A pointer to the current task struct. + * + * int bpf_probe_write_user(void *dst, const void *src, u32 len) + * Description + * Attempt in a safe way to write *len* bytes from the buffer + * *src* to *dst* in memory. It only works for threads that are in + * user context, and *dst* must be a valid user space address. + * + * This helper should not be used to implement any kind of + * security mechanism because of TOC-TOU attacks, but rather to + * debug, divert, and manipulate execution of semi-cooperative + * processes. + * + * Keep in mind that this feature is meant for experiments, and it + * has a risk of crashing the system and running programs. + * Therefore, when an eBPF program using this helper is attached, + * a warning including PID and process name is printed to kernel + * logs. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_current_task_under_cgroup(struct bpf_map *map, u32 index) + * Description + * Check whether the probe is being run is the context of a given + * subset of the cgroup2 hierarchy. The cgroup2 to test is held by + * *map* of type **BPF_MAP_TYPE_CGROUP_ARRAY**, at *index*. + * Return + * The return value depends on the result of the test, and can be: + * + * * 0, if the *skb* task belongs to the cgroup2. + * * 1, if the *skb* task does not belong to the cgroup2. + * * A negative error code, if an error occurred. + * + * int bpf_skb_change_tail(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Resize (trim or grow) the packet associated to *skb* to the + * new *len*. The *flags* are reserved for future usage, and must + * be left at zero. + * + * The basic idea is that the helper performs the needed work to + * change the size of the packet, then the eBPF program rewrites + * the rest via helpers like **bpf_skb_store_bytes**\ (), + * **bpf_l3_csum_replace**\ (), **bpf_l3_csum_replace**\ () + * and others. This helper is a slow path utility intended for + * replies with control messages. And because it is targeted for + * slow path, the helper itself can afford to be slow: it + * implicitly linearizes, unclones and drops offloads from the + * *skb*. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_pull_data(struct sk_buff *skb, u32 len) + * Description + * Pull in non-linear data in case the *skb* is non-linear and not + * all of *len* are part of the linear section. Make *len* bytes + * from *skb* readable and writable. If a zero value is passed for + * *len*, then the whole length of the *skb* is pulled. + * + * This helper is only needed for reading and writing with direct + * packet access. + * + * For direct packet access, testing that offsets to access + * are within packet boundaries (test on *skb*\ **->data_end**) is + * susceptible to fail if offsets are invalid, or if the requested + * data is in non-linear parts of the *skb*. On failure the + * program can just bail out, or in the case of a non-linear + * buffer, use a helper to make the data available. The + * **bpf_skb_load_bytes**\ () helper is a first solution to access + * the data. Another one consists in using **bpf_skb_pull_data** + * to pull in once the non-linear parts, then retesting and + * eventually access the data. + * + * At the same time, this also makes sure the *skb* is uncloned, + * which is a necessary condition for direct write. As this needs + * to be an invariant for the write part only, the verifier + * detects writes and adds a prologue that is calling + * **bpf_skb_pull_data()** to effectively unclone the *skb* from + * the very beginning in case it is indeed cloned. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * s64 bpf_csum_update(struct sk_buff *skb, __wsum csum) + * Description + * Add the checksum *csum* into *skb*\ **->csum** in case the + * driver has supplied a checksum for the entire packet into that + * field. Return an error otherwise. This helper is intended to be + * used in combination with **bpf_csum_diff**\ (), in particular + * when the checksum needs to be updated after data has been + * written into the packet through direct packet access. + * Return + * The checksum on success, or a negative error code in case of + * failure. + * + * void bpf_set_hash_invalid(struct sk_buff *skb) + * Description + * Invalidate the current *skb*\ **->hash**. It can be used after + * mangling on headers through direct packet access, in order to + * indicate that the hash is outdated and to trigger a + * recalculation the next time the kernel tries to access this + * hash or when the **bpf_get_hash_recalc**\ () helper is called. + * + * int bpf_get_numa_node_id(void) + * Description + * Return the id of the current NUMA node. The primary use case + * for this helper is the selection of sockets for the local NUMA + * node, when the program is attached to sockets using the + * **SO_ATTACH_REUSEPORT_EBPF** option (see also **socket(7)**), + * but the helper is also available to other eBPF program types, + * similarly to **bpf_get_smp_processor_id**\ (). + * Return + * The id of current NUMA node. + * + * int bpf_skb_change_head(struct sk_buff *skb, u32 len, u64 flags) + * Description + * Grows headroom of packet associated to *skb* and adjusts the + * offset of the MAC header accordingly, adding *len* bytes of + * space. It automatically extends and reallocates memory as + * required. + * + * This helper can be used on a layer 3 *skb* to push a MAC header + * for redirection into a layer 2 device. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_head(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data** by *delta* bytes. Note that + * it is possible to use a negative value for *delta*. This helper + * can be used to prepare the packet for pushing or popping + * headers. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. * * int bpf_probe_read_str(void *dst, int size, const void *unsafe_ptr) - * Copy a NUL terminated string from unsafe address. In case the string - * length is smaller than size, the target is not padded with further NUL - * bytes. In case the string length is larger than size, just count-1 - * bytes are copied and the last byte is set to NUL. - * @dst: destination address - * @size: maximum number of bytes to copy, including the trailing NUL - * @unsafe_ptr: unsafe address - * Return: - * > 0 length of the string including the trailing NUL on success - * < 0 error - * - * u64 bpf_get_socket_cookie(skb) - * Get the cookie for the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: 8 Bytes non-decreasing number on success or 0 if the socket - * field is missing inside sk_buff - * - * u32 bpf_get_socket_uid(skb) - * Get the owner uid of the socket stored inside sk_buff. - * @skb: pointer to skb - * Return: uid of the socket owner on success or overflowuid if failed. - * - * u32 bpf_set_hash(skb, hash) - * Set full skb->hash. - * @skb: pointer to skb - * @hash: hash to set - * - * int bpf_setsockopt(bpf_socket, level, optname, optval, optlen) - * Calls setsockopt. Not all opts are available, only those with - * integer optvals plus TCP_CONGESTION. - * Supported levels: SOL_SOCKET and IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: SOL_SOCKET or IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_getsockopt(bpf_socket, level, optname, optval, optlen) - * Calls getsockopt. Not all opts are available. - * Supported levels: IPPROTO_TCP - * @bpf_socket: pointer to bpf_socket - * @level: IPPROTO_TCP - * @optname: option name - * @optval: pointer to option value - * @optlen: length of optval in bytes - * Return: 0 or negative error - * - * int bpf_sock_ops_cb_flags_set(bpf_sock_ops, flags) - * Set callback flags for sock_ops - * @bpf_sock_ops: pointer to bpf_sock_ops_kern struct - * @flags: flags value - * Return: 0 for no error - * -EINVAL if there is no full tcp socket - * bits in flags that are not supported by current kernel - * - * int bpf_skb_adjust_room(skb, len_diff, mode, flags) - * Grow or shrink room in sk_buff. - * @skb: pointer to skb - * @len_diff: (signed) amount of room to grow/shrink - * @mode: operation mode (enum bpf_adj_room_mode) - * @flags: reserved for future use - * Return: 0 on success or negative error code - * - * int bpf_sk_redirect_map(map, key, flags) - * Redirect skb to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_sock_map_update(skops, map, key, flags) - * @skops: pointer to bpf_sock_ops - * @map: pointer to sockmap to update - * @key: key to insert/update sock in map - * @flags: same flags as map update elem - * - * int bpf_xdp_adjust_meta(xdp_md, delta) - * Adjust the xdp_md.data_meta by delta - * @xdp_md: pointer to xdp_md - * @delta: An positive/negative integer to be added to xdp_md.data_meta - * Return: 0 on success or negative on error - * - * int bpf_perf_event_read_value(map, flags, buf, buf_size) - * read perf event counter value and perf event enabled/running time - * @map: pointer to perf_event_array map - * @flags: index of event in the map or bitmask flags - * @buf: buf to fill - * @buf_size: size of the buf - * Return: 0 on success or negative error code - * - * int bpf_perf_prog_read_value(ctx, buf, buf_size) - * read perf prog attached perf event counter and enabled/running time - * @ctx: pointer to ctx - * @buf: buf to fill - * @buf_size: size of the buf - * Return : 0 on success or negative error code - * - * int bpf_override_return(pt_regs, rc) - * @pt_regs: pointer to struct pt_regs - * @rc: the return value to set - * - * int bpf_msg_redirect_map(map, key, flags) - * Redirect msg to a sock in map using key as a lookup key for the - * sock in map. - * @map: pointer to sockmap - * @key: key to lookup sock in map - * @flags: reserved for future use - * Return: SK_PASS - * - * int bpf_bind(ctx, addr, addr_len) - * Bind socket to address. Only binding to IP is supported, no port can be - * set in addr. - * @ctx: pointer to context of type bpf_sock_addr - * @addr: pointer to struct sockaddr to bind socket to - * @addr_len: length of sockaddr structure - * Return: 0 on success or negative error code + * Description + * Copy a NUL terminated string from an unsafe address + * *unsafe_ptr* to *dst*. The *size* should include the + * terminating NUL byte. In case the string length is smaller than + * *size*, the target is not padded with further NUL bytes. If the + * string length is larger than *size*, just *size*-1 bytes are + * copied and the last byte is set to NUL. + * + * On success, the length of the copied string is returned. This + * makes this helper useful in tracing programs for reading + * strings, and more importantly to get its length at runtime. See + * the following snippet: + * + * :: + * + * SEC("kprobe/sys_open") + * void bpf_sys_open(struct pt_regs *ctx) + * { + * char buf[PATHLEN]; // PATHLEN is defined to 256 + * int res = bpf_probe_read_str(buf, sizeof(buf), + * ctx->di); + * + * // Consume buf, for example push it to + * // userspace via bpf_perf_event_output(); we + * // can use res (the string length) as event + * // size, after checking its boundaries. + * } + * + * In comparison, using **bpf_probe_read()** helper here instead + * to read the string would require to estimate the length at + * compile time, and would often result in copying more memory + * than necessary. + * + * Another useful use case is when parsing individual process + * arguments or individual environment variables navigating + * *current*\ **->mm->arg_start** and *current*\ + * **->mm->env_start**: using this helper and the return value, + * one can quickly iterate at the right offset of the memory area. + * Return + * On success, the strictly positive length of the string, + * including the trailing NUL character. On error, a negative + * value. + * + * u64 bpf_get_socket_cookie(struct sk_buff *skb) + * Description + * If the **struct sk_buff** pointed by *skb* has a known socket, + * retrieve the cookie (generated by the kernel) of this socket. + * If no cookie has been set yet, generate a new cookie. Once + * generated, the socket cookie remains stable for the life of the + * socket. This helper can be useful for monitoring per socket + * networking traffic statistics as it provides a unique socket + * identifier per namespace. + * Return + * A 8-byte long non-decreasing number on success, or 0 if the + * socket field is missing inside *skb*. + * + * u32 bpf_get_socket_uid(struct sk_buff *skb) + * Return + * The owner UID of the socket associated to *skb*. If the socket + * is **NULL**, or if it is not a full socket (i.e. if it is a + * time-wait or a request socket instead), **overflowuid** value + * is returned (note that **overflowuid** might also be the actual + * UID value for the socket). + * + * u32 bpf_set_hash(struct sk_buff *skb, u32 hash) + * Description + * Set the full hash for *skb* (set the field *skb*\ **->hash**) + * to value *hash*. + * Return + * 0 + * + * int bpf_setsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **setsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **setsockopt(2)** for more information. + * The option value of length *optlen* is pointed by *optval*. + * + * This helper actually implements a subset of **setsockopt()**. + * It supports the following *level*\ s: + * + * * **SOL_SOCKET**, which supports the following *optname*\ s: + * **SO_RCVBUF**, **SO_SNDBUF**, **SO_MAX_PACING_RATE**, + * **SO_PRIORITY**, **SO_RCVLOWAT**, **SO_MARK**. + * * **IPPROTO_TCP**, which supports the following *optname*\ s: + * **TCP_CONGESTION**, **TCP_BPF_IW**, + * **TCP_BPF_SNDCWND_CLAMP**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_adjust_room(struct sk_buff *skb, u32 len_diff, u32 mode, u64 flags) + * Description + * Grow or shrink the room for data in the packet associated to + * *skb* by *len_diff*, and according to the selected *mode*. + * + * There is a single supported mode at this time: + * + * * **BPF_ADJ_ROOM_NET**: Adjust room at the network layer + * (room space is added or removed below the layer 3 header). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the endpoint referenced by *map* at + * index *key*. Depending on its type, this *map* can contain + * references to net devices (for forwarding packets through other + * ports), or to CPUs (for redirecting XDP frames to another CPU; + * but this is only implemented for native XDP (with driver + * support) as of this writing). + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * When used to redirect packets to net devices, this helper + * provides a high performance increase over **bpf_redirect**\ (). + * This is due to various implementation details of the underlying + * mechanisms, one of which is the fact that **bpf_redirect_map**\ + * () tries to send packet as a "bulk" to the device. + * Return + * **XDP_REDIRECT** on success, or **XDP_ABORTED** on error. + * + * int bpf_sk_redirect_map(struct bpf_map *map, u32 key, u64 flags) + * Description + * Redirect the packet to the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_sock_map_update(struct bpf_sock_ops *skops, struct bpf_map *map, void *key, u64 flags) + * Description + * Add an entry to, or update a *map* referencing sockets. The + * *skops* is used as a new value for the entry associated to + * *key*. *flags* is one of: + * + * **BPF_NOEXIST** + * The entry for *key* must not exist in the map. + * **BPF_EXIST** + * The entry for *key* must already exist in the map. + * **BPF_ANY** + * No condition on the existence of the entry for *key*. + * + * If the *map* has eBPF programs (parser and verdict), those will + * be inherited by the socket being added. If the socket is + * already attached to eBPF programs, this results in an error. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_meta(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust the address pointed by *xdp_md*\ **->data_meta** by + * *delta* (which can be positive or negative). Note that this + * operation modifies the address stored in *xdp_md*\ **->data**, + * so the latter must be loaded only after the helper has been + * called. + * + * The use of *xdp_md*\ **->data_meta** is optional and programs + * are not required to use it. The rationale is that when the + * packet is processed with XDP (e.g. as DoS filter), it is + * possible to push further meta data along with it before passing + * to the stack, and to give the guarantee that an ingress eBPF + * program attached as a TC classifier on the same device can pick + * this up for further post-processing. Since TC works with socket + * buffers, it remains possible to set from XDP the **mark** or + * **priority** pointers, or other pointers for the socket buffer. + * Having this scratch space generic and programmable allows for + * more flexibility as the user is free to store whatever meta + * data they need. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_event_read_value(struct bpf_map *map, u64 flags, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * Read the value of a perf event counter, and store it into *buf* + * of size *buf_size*. This helper relies on a *map* of type + * **BPF_MAP_TYPE_PERF_EVENT_ARRAY**. The nature of the perf event + * counter is selected when *map* is updated with perf event file + * descriptors. The *map* is an array whose size is the number of + * available CPUs, and each cell contains a value relative to one + * CPU. The value to retrieve is indicated by *flags*, that + * contains the index of the CPU to look up, masked with + * **BPF_F_INDEX_MASK**. Alternatively, *flags* can be set to + * **BPF_F_CURRENT_CPU** to indicate that the value for the + * current CPU should be retrieved. + * + * This helper behaves in a way close to + * **bpf_perf_event_read**\ () helper, save that instead of + * just returning the value observed, it fills the *buf* + * structure. This allows for additional data to be retrieved: in + * particular, the enabled and running times (in *buf*\ + * **->enabled** and *buf*\ **->running**, respectively) are + * copied. In general, **bpf_perf_event_read_value**\ () is + * recommended over **bpf_perf_event_read**\ (), which has some + * ABI issues and provides fewer functionalities. + * + * These values are interesting, because hardware PMU (Performance + * Monitoring Unit) counters are limited resources. When there are + * more PMU based perf events opened than available counters, + * kernel will multiplex these events so each event gets certain + * percentage (but not all) of the PMU time. In case that + * multiplexing happens, the number of samples or counter value + * will not reflect the case compared to when no multiplexing + * occurs. This makes comparison between different runs difficult. + * Typically, the counter value should be normalized before + * comparing to other experiments. The usual normalization is done + * as follows. + * + * :: + * + * normalized_counter = counter * t_enabled / t_running + * + * Where t_enabled is the time enabled for event and t_running is + * the time running for event since last normalization. The + * enabled and running times are accumulated since the perf event + * open. To achieve scaling factor between two invocations of an + * eBPF program, users can can use CPU id as the key (which is + * typical for perf array usage model) to remember the previous + * value and do the calculation inside the eBPF program. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_perf_prog_read_value(struct bpf_perf_event_data *ctx, struct bpf_perf_event_value *buf, u32 buf_size) + * Description + * For en eBPF program attached to a perf event, retrieve the + * value of the event counter associated to *ctx* and store it in + * the structure pointed by *buf* and of size *buf_size*. Enabled + * and running times are also stored in the structure (see + * description of helper **bpf_perf_event_read_value**\ () for + * more details). + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_getsockopt(struct bpf_sock_ops *bpf_socket, int level, int optname, char *optval, int optlen) + * Description + * Emulate a call to **getsockopt()** on the socket associated to + * *bpf_socket*, which must be a full socket. The *level* at + * which the option resides and the name *optname* of the option + * must be specified, see **getsockopt(2)** for more information. + * The retrieved value is stored in the structure pointed by + * *opval* and of length *optlen*. + * + * This helper actually implements a subset of **getsockopt()**. + * It supports the following *level*\ s: + * + * * **IPPROTO_TCP**, which supports *optname* + * **TCP_CONGESTION**. + * * **IPPROTO_IP**, which supports *optname* **IP_TOS**. + * * **IPPROTO_IPV6**, which supports *optname* **IPV6_TCLASS**. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_override_return(struct pt_reg *regs, u64 rc) + * Description + * Used for error injection, this helper uses kprobes to override + * the return value of the probed function, and to set it to *rc*. + * The first argument is the context *regs* on which the kprobe + * works. + * + * This helper works by setting setting the PC (program counter) + * to an override function which is run in place of the original + * probed function. This means the probed function is not run at + * all. The replacement function just returns with the required + * value. + * + * This helper has security implications, and thus is subject to + * restrictions. It is only available if the kernel was compiled + * with the **CONFIG_BPF_KPROBE_OVERRIDE** configuration + * option, and in this case it only works on functions tagged with + * **ALLOW_ERROR_INJECTION** in the kernel code. + * + * Also, the helper is only available for the architectures having + * the CONFIG_FUNCTION_ERROR_INJECTION option. As of this writing, + * x86 architecture is the only one to support this feature. + * Return + * 0 + * + * int bpf_sock_ops_cb_flags_set(struct bpf_sock_ops *bpf_sock, int argval) + * Description + * Attempt to set the value of the **bpf_sock_ops_cb_flags** field + * for the full TCP socket associated to *bpf_sock_ops* to + * *argval*. + * + * The primary use of this field is to determine if there should + * be calls to eBPF programs of type + * **BPF_PROG_TYPE_SOCK_OPS** at various points in the TCP + * code. A program of the same type can change its value, per + * connection and as necessary, when the connection is + * established. This field is directly accessible for reading, but + * this helper must be used for updates in order to return an + * error if an eBPF program tries to set a callback that is not + * supported in the current kernel. + * + * The supported callback values that *argval* can combine are: + * + * * **BPF_SOCK_OPS_RTO_CB_FLAG** (retransmission time out) + * * **BPF_SOCK_OPS_RETRANS_CB_FLAG** (retransmission) + * * **BPF_SOCK_OPS_STATE_CB_FLAG** (TCP state change) + * + * Here are some examples of where one could call such eBPF + * program: + * + * * When RTO fires. + * * When a packet is retransmitted. + * * When the connection terminates. + * * When a packet is sent. + * * When a packet is received. + * Return + * Code **-EINVAL** if the socket is not a full TCP socket; + * otherwise, a positive number containing the bits that could not + * be set is returned (which comes down to 0 if all bits were set + * as required). + * + * int bpf_msg_redirect_map(struct sk_msg_buff *msg, struct bpf_map *map, u32 key, u64 flags) + * Description + * This helper is used in programs implementing policies at the + * socket level. If the message *msg* is allowed to pass (i.e. if + * the verdict eBPF program returns **SK_PASS**), redirect it to + * the socket referenced by *map* (of type + * **BPF_MAP_TYPE_SOCKMAP**) at index *key*. Both ingress and + * egress interfaces can be used for redirection. The + * **BPF_F_INGRESS** value in *flags* is used to make the + * distinction (ingress path is selected if the flag is present, + * egress path otherwise). This is the only flag supported for now. + * Return + * **SK_PASS** on success, or **SK_DROP** on error. + * + * int bpf_msg_apply_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, apply the verdict of the eBPF program to + * the next *bytes* (number of bytes) of message *msg*. + * + * For example, this helper can be used in the following cases: + * + * * A single **sendmsg**\ () or **sendfile**\ () system call + * contains multiple logical messages that the eBPF program is + * supposed to read and for which it should apply a verdict. + * * An eBPF program only cares to read the first *bytes* of a + * *msg*. If the message has a large payload, then setting up + * and calling the eBPF program repeatedly for all bytes, even + * though the verdict is already known, would create unnecessary + * overhead. + * + * When called from within an eBPF program, the helper sets a + * counter internal to the BPF infrastructure, that is used to + * apply the last verdict to the next *bytes*. If *bytes* is + * smaller than the current data being processed from a + * **sendmsg**\ () or **sendfile**\ () system call, the first + * *bytes* will be sent and the eBPF program will be re-run with + * the pointer for start of data pointing to byte number *bytes* + * **+ 1**. If *bytes* is larger than the current data being + * processed, then the eBPF verdict will be applied to multiple + * **sendmsg**\ () or **sendfile**\ () calls until *bytes* are + * consumed. + * + * Note that if a socket closes with the internal counter holding + * a non-zero value, this is not a problem because data is not + * being buffered for *bytes* and is sent as it is received. + * Return + * 0 + * + * int bpf_msg_cork_bytes(struct sk_msg_buff *msg, u32 bytes) + * Description + * For socket policies, prevent the execution of the verdict eBPF + * program for message *msg* until *bytes* (byte number) have been + * accumulated. + * + * This can be used when one needs a specific number of bytes + * before a verdict can be assigned, even if the data spans + * multiple **sendmsg**\ () or **sendfile**\ () calls. The extreme + * case would be a user calling **sendmsg**\ () repeatedly with + * 1-byte long message segments. Obviously, this is bad for + * performance, but it is still valid. If the eBPF program needs + * *bytes* bytes to validate a header, this helper can be used to + * prevent the eBPF program to be called again until *bytes* have + * been accumulated. + * Return + * 0 + * + * int bpf_msg_pull_data(struct sk_msg_buff *msg, u32 start, u32 end, u64 flags) + * Description + * For socket policies, pull in non-linear data from user space + * for *msg* and set pointers *msg*\ **->data** and *msg*\ + * **->data_end** to *start* and *end* bytes offsets into *msg*, + * respectively. + * + * If a program of type **BPF_PROG_TYPE_SK_MSG** is run on a + * *msg* it can only parse data that the (**data**, **data_end**) + * pointers have already consumed. For **sendmsg**\ () hooks this + * is likely the first scatterlist element. But for calls relying + * on the **sendpage** handler (e.g. **sendfile**\ ()) this will + * be the range (**0**, **0**) because the data is shared with + * user space and by default the objective is to avoid allowing + * user space to modify data while (or after) eBPF verdict is + * being decided. This helper can be used to pull in data and to + * set the start and end pointer to given values. Data will be + * copied if necessary (i.e. if data was not linear and if start + * and end pointers do not point to the same chunk). + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_bind(struct bpf_sock_addr *ctx, struct sockaddr *addr, int addr_len) + * Description + * Bind the socket associated to *ctx* to the address pointed by + * *addr*, of length *addr_len*. This allows for making outgoing + * connection from the desired IP address, which can be useful for + * example when all processes inside a cgroup should use one + * single IP address on a host that has multiple IP configured. + * + * This helper works for IPv4 and IPv6, TCP and UDP sockets. The + * domain (*addr*\ **->sa_family**) must be **AF_INET** (or + * **AF_INET6**). Looking for a free port to bind to can be + * expensive, therefore binding to port is not permitted by the + * helper: *addr*\ **->sin_port** (or **sin6_port**, respectively) + * must be set to zero. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_xdp_adjust_tail(struct xdp_buff *xdp_md, int delta) + * Description + * Adjust (move) *xdp_md*\ **->data_end** by *delta* bytes. It is + * only possible to shrink the packet as of this writing, + * therefore *delta* must be a negative integer. + * + * A call to this helper is susceptible to change the underlaying + * packet buffer. Therefore, at load time, all checks on pointers + * previously done by the verifier are invalidated and must be + * performed again, if the helper is used in combination with + * direct packet access. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_skb_get_xfrm_state(struct sk_buff *skb, u32 index, struct bpf_xfrm_state *xfrm_state, u32 size, u64 flags) + * Description + * Retrieve the XFRM state (IP transform framework, see also + * **ip-xfrm(8)**) at *index* in XFRM "security path" for *skb*. + * + * The retrieved value is stored in the **struct bpf_xfrm_state** + * pointed by *xfrm_state* and of length *size*. + * + * All values for *flags* are reserved for future usage, and must + * be left at zero. + * + * This helper is available only if the kernel was compiled with + * **CONFIG_XFRM** configuration option. + * Return + * 0 on success, or a negative error in case of failure. + * + * int bpf_get_stack(struct pt_regs *regs, void *buf, u32 size, u64 flags) + * Description + * Return a user or a kernel stack in bpf program provided buffer. + * To achieve this, the helper needs *ctx*, which is a pointer + * to the context on which the tracing program is executed. + * To store the stacktrace, the bpf program provides *buf* with + * a nonnegative *size*. + * + * The last argument, *flags*, holds the number of stack frames to + * skip (from 0 to 255), masked with + * **BPF_F_SKIP_FIELD_MASK**. The next bits can be used to set + * the following flags: + * + * **BPF_F_USER_STACK** + * Collect a user space stack instead of a kernel stack. + * **BPF_F_USER_BUILD_ID** + * Collect buildid+offset instead of ips for user stack, + * only valid if **BPF_F_USER_STACK** is also specified. + * + * **bpf_get_stack**\ () can collect up to + * **PERF_MAX_STACK_DEPTH** both kernel and user frames, subject + * to sufficient large buffer size. Note that + * this limit can be controlled with the **sysctl** program, and + * that it should be manually increased in order to profile long + * user stacks (such as stacks for Java programs). To do so, use: + * + * :: + * + * # sysctl kernel.perf_event_max_stack=<new value> + * + * Return + * a non-negative value equal to or less than size on success, or + * a negative error in case of failure. + * + * int skb_load_bytes_relative(const struct sk_buff *skb, u32 offset, void *to, u32 len, u32 start_header) + * Description + * This helper is similar to **bpf_skb_load_bytes**\ () in that + * it provides an easy way to load *len* bytes from *offset* + * from the packet associated to *skb*, into the buffer pointed + * by *to*. The difference to **bpf_skb_load_bytes**\ () is that + * a fifth argument *start_header* exists in order to select a + * base offset to start from. *start_header* can be one of: + * + * **BPF_HDR_START_MAC** + * Base offset to load data from is *skb*'s mac header. + * **BPF_HDR_START_NET** + * Base offset to load data from is *skb*'s network header. + * + * In general, "direct packet access" is the preferred method to + * access packet data, however, this helper is in particular useful + * in socket filters where *skb*\ **->data** does not always point + * to the start of the mac header and where "direct packet access" + * is not available. + * + * Return + * 0 on success, or a negative error in case of failure. + * */ #define __BPF_FUNC_MAPPER(FN) \ FN(unspec), \ @@ -821,7 +1891,11 @@ union bpf_attr { FN(msg_apply_bytes), \ FN(msg_cork_bytes), \ FN(msg_pull_data), \ - FN(bind), + FN(bind), \ + FN(xdp_adjust_tail), \ + FN(skb_get_xfrm_state), \ + FN(get_stack), \ + FN(skb_load_bytes_relative), /* integer value in 'imm' field of BPF_CALL instruction selects which helper * function eBPF program intends to call @@ -855,11 +1929,14 @@ enum bpf_func_id { /* BPF_FUNC_skb_set_tunnel_key and BPF_FUNC_skb_get_tunnel_key flags. */ #define BPF_F_TUNINFO_IPV6 (1ULL << 0) -/* BPF_FUNC_get_stackid flags. */ +/* flags for both BPF_FUNC_get_stackid and BPF_FUNC_get_stack. */ #define BPF_F_SKIP_FIELD_MASK 0xffULL #define BPF_F_USER_STACK (1ULL << 8) +/* flags used by BPF_FUNC_get_stackid only. */ #define BPF_F_FAST_STACK_CMP (1ULL << 9) #define BPF_F_REUSE_STACKID (1ULL << 10) +/* flags used by BPF_FUNC_get_stack only. */ +#define BPF_F_USER_BUILD_ID (1ULL << 11) /* BPF_FUNC_skb_set_tunnel_key flags. */ #define BPF_F_ZERO_CSUM_TX (1ULL << 1) @@ -879,6 +1956,12 @@ enum bpf_adj_room_mode { BPF_ADJ_ROOM_NET, }; +/* Mode for BPF_FUNC_skb_load_bytes_relative helper. */ +enum bpf_hdr_start_off { + BPF_HDR_START_MAC, + BPF_HDR_START_NET, +}; + /* user accessible mirror of in-kernel sk_buff. * new fields can only be added to the end of this structure */ @@ -927,6 +2010,19 @@ struct bpf_tunnel_key { __u32 tunnel_label; }; +/* user accessible mirror of in-kernel xfrm_state. + * new fields can only be added to the end of this structure + */ +struct bpf_xfrm_state { + __u32 reqid; + __u32 spi; /* Stored in network byte order */ + __u16 family; + union { + __u32 remote_ipv4; /* Stored in network byte order */ + __u32 remote_ipv6[4]; /* Stored in network byte order */ + }; +}; + /* Generic BPF return codes which all BPF program types may support. * The values are binary compatible with their TC_ACT_* counter-part to * provide backwards compatibility with existing SCHED_CLS and SCHED_ACT @@ -1017,6 +2113,7 @@ struct bpf_prog_info { __aligned_u64 map_ids; char name[BPF_OBJ_NAME_LEN]; __u32 ifindex; + __u32 gpl_compatible:1; __u64 netns_dev; __u64 netns_ino; } __attribute__((aligned(8))); diff --git a/tools/include/uapi/linux/btf.h b/tools/include/uapi/linux/btf.h new file mode 100644 index 000000000000..bcb56ee47014 --- /dev/null +++ b/tools/include/uapi/linux/btf.h @@ -0,0 +1,128 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* Copyright (c) 2018 Facebook */ +#ifndef _UAPI__LINUX_BTF_H__ +#define _UAPI__LINUX_BTF_H__ + +#include <linux/types.h> + +#define BTF_MAGIC 0xeB9F +#define BTF_VERSION 1 + +struct btf_header { + __u16 magic; + __u8 version; + __u8 flags; + + __u32 parent_label; + __u32 parent_name; + + /* All offsets are in bytes relative to the end of this header */ + __u32 label_off; /* offset of label section */ + __u32 object_off; /* offset of data object section*/ + __u32 func_off; /* offset of function section */ + __u32 type_off; /* offset of type section */ + __u32 str_off; /* offset of string section */ + __u32 str_len; /* length of string section */ +}; + +/* Max # of type identifier */ +#define BTF_MAX_TYPE 0x7fffffff +/* Max offset into the string section */ +#define BTF_MAX_NAME_OFFSET 0x7fffffff +/* Max # of struct/union/enum members or func args */ +#define BTF_MAX_VLEN 0xffff + +/* The type id is referring to a parent BTF */ +#define BTF_TYPE_PARENT(id) (((id) >> 31) & 0x1) +#define BTF_TYPE_ID(id) ((id) & BTF_MAX_TYPE) + +/* String is in the ELF string section */ +#define BTF_STR_TBL_ELF_ID(ref) (((ref) >> 31) & 0x1) +#define BTF_STR_OFFSET(ref) ((ref) & BTF_MAX_NAME_OFFSET) + +struct btf_type { + __u32 name_off; + /* "info" bits arrangement + * bits 0-15: vlen (e.g. # of struct's members) + * bits 16-23: unused + * bits 24-28: kind (e.g. int, ptr, array...etc) + * bits 29-30: unused + * bits 31: root + */ + __u32 info; + /* "size" is used by INT, ENUM, STRUCT and UNION. + * "size" tells the size of the type it is describing. + * + * "type" is used by PTR, TYPEDEF, VOLATILE, CONST and RESTRICT. + * "type" is a type_id referring to another type. + */ + union { + __u32 size; + __u32 type; + }; +}; + +#define BTF_INFO_KIND(info) (((info) >> 24) & 0x1f) +#define BTF_INFO_ISROOT(info) (!!(((info) >> 24) & 0x80)) +#define BTF_INFO_VLEN(info) ((info) & 0xffff) + +#define BTF_KIND_UNKN 0 /* Unknown */ +#define BTF_KIND_INT 1 /* Integer */ +#define BTF_KIND_PTR 2 /* Pointer */ +#define BTF_KIND_ARRAY 3 /* Array */ +#define BTF_KIND_STRUCT 4 /* Struct */ +#define BTF_KIND_UNION 5 /* Union */ +#define BTF_KIND_ENUM 6 /* Enumeration */ +#define BTF_KIND_FWD 7 /* Forward */ +#define BTF_KIND_TYPEDEF 8 /* Typedef */ +#define BTF_KIND_VOLATILE 9 /* Volatile */ +#define BTF_KIND_CONST 10 /* Const */ +#define BTF_KIND_RESTRICT 11 /* Restrict */ +#define BTF_KIND_MAX 11 +#define NR_BTF_KINDS 12 + +/* For some specific BTF_KIND, "struct btf_type" is immediately + * followed by extra data. + */ + +/* BTF_KIND_INT is followed by a u32 and the following + * is the 32 bits arrangement: + */ +#define BTF_INT_ENCODING(VAL) (((VAL) & 0xff000000) >> 24) +#define BTF_INT_OFFSET(VAL) (((VAL & 0x00ff0000)) >> 16) +#define BTF_INT_BITS(VAL) ((VAL) & 0x0000ffff) + +/* Attributes stored in the BTF_INT_ENCODING */ +#define BTF_INT_SIGNED 0x1 +#define BTF_INT_CHAR 0x2 +#define BTF_INT_BOOL 0x4 +#define BTF_INT_VARARGS 0x8 + +/* BTF_KIND_ENUM is followed by multiple "struct btf_enum". + * The exact number of btf_enum is stored in the vlen (of the + * info in "struct btf_type"). + */ +struct btf_enum { + __u32 name_off; + __s32 val; +}; + +/* BTF_KIND_ARRAY is followed by one "struct btf_array" */ +struct btf_array { + __u32 type; + __u32 index_type; + __u32 nelems; +}; + +/* BTF_KIND_STRUCT and BTF_KIND_UNION are followed + * by multiple "struct btf_member". The exact number + * of btf_member is stored in the vlen (of the info in + * "struct btf_type"). + */ +struct btf_member { + __u32 name_off; + __u32 type; + __u32 offset; /* offset in bits */ +}; + +#endif /* _UAPI__LINUX_BTF_H__ */ diff --git a/tools/include/uapi/linux/erspan.h b/tools/include/uapi/linux/erspan.h new file mode 100644 index 000000000000..841573019ae1 --- /dev/null +++ b/tools/include/uapi/linux/erspan.h @@ -0,0 +1,52 @@ +/* SPDX-License-Identifier: GPL-2.0 WITH Linux-syscall-note */ +/* + * ERSPAN Tunnel Metadata + * + * Copyright (c) 2018 VMware + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 + * as published by the Free Software Foundation. + * + * Userspace API for metadata mode ERSPAN tunnel + */ +#ifndef _UAPI_ERSPAN_H +#define _UAPI_ERSPAN_H + +#include <linux/types.h> /* For __beXX in userspace */ +#include <asm/byteorder.h> + +/* ERSPAN version 2 metadata header */ +struct erspan_md2 { + __be32 timestamp; + __be16 sgt; /* security group tag */ +#if defined(__LITTLE_ENDIAN_BITFIELD) + __u8 hwid_upper:2, + ft:5, + p:1; + __u8 o:1, + gra:2, + dir:1, + hwid:4; +#elif defined(__BIG_ENDIAN_BITFIELD) + __u8 p:1, + ft:5, + hwid_upper:2; + __u8 hwid:4, + dir:1, + gra:2, + o:1; +#else +#error "Please fix <asm/byteorder.h>" +#endif +}; + +struct erspan_metadata { + int version; + union { + __be32 index; /* Version 1 (type II)*/ + struct erspan_md2 md2; /* Version 2 (type III) */ + } u; +}; + +#endif /* _UAPI_ERSPAN_H */ diff --git a/tools/lib/bpf/Build b/tools/lib/bpf/Build index 64c679d67109..6070e655042d 100644 --- a/tools/lib/bpf/Build +++ b/tools/lib/bpf/Build @@ -1 +1 @@ -libbpf-y := libbpf.o bpf.o nlattr.o +libbpf-y := libbpf.o bpf.o nlattr.o btf.o diff --git a/tools/lib/bpf/bpf.c b/tools/lib/bpf/bpf.c index acbb3f8b3bec..76b36cc16e7f 100644 --- a/tools/lib/bpf/bpf.c +++ b/tools/lib/bpf/bpf.c @@ -73,43 +73,76 @@ static inline int sys_bpf(enum bpf_cmd cmd, union bpf_attr *attr, return syscall(__NR_bpf, cmd, attr, size); } -int bpf_create_map_node(enum bpf_map_type map_type, const char *name, - int key_size, int value_size, int max_entries, - __u32 map_flags, int node) +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr) { - __u32 name_len = name ? strlen(name) : 0; + __u32 name_len = create_attr->name ? strlen(create_attr->name) : 0; union bpf_attr attr; memset(&attr, '\0', sizeof(attr)); - attr.map_type = map_type; - attr.key_size = key_size; - attr.value_size = value_size; - attr.max_entries = max_entries; - attr.map_flags = map_flags; - memcpy(attr.map_name, name, min(name_len, BPF_OBJ_NAME_LEN - 1)); + attr.map_type = create_attr->map_type; + attr.key_size = create_attr->key_size; + attr.value_size = create_attr->value_size; + attr.max_entries = create_attr->max_entries; + attr.map_flags = create_attr->map_flags; + memcpy(attr.map_name, create_attr->name, + min(name_len, BPF_OBJ_NAME_LEN - 1)); + attr.numa_node = create_attr->numa_node; + attr.btf_fd = create_attr->btf_fd; + attr.btf_key_id = create_attr->btf_key_id; + attr.btf_value_id = create_attr->btf_value_id; + + return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); +} +int bpf_create_map_node(enum bpf_map_type map_type, const char *name, + int key_size, int value_size, int max_entries, + __u32 map_flags, int node) +{ + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; if (node >= 0) { - attr.map_flags |= BPF_F_NUMA_NODE; - attr.numa_node = node; + map_attr.numa_node = node; + map_attr.map_flags |= BPF_F_NUMA_NODE; } - return sys_bpf(BPF_MAP_CREATE, &attr, sizeof(attr)); + return bpf_create_map_xattr(&map_attr); } int bpf_create_map(enum bpf_map_type map_type, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, NULL, key_size, value_size, - max_entries, map_flags, -1); + struct bpf_create_map_attr map_attr = {}; + + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); } int bpf_create_map_name(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags) { - return bpf_create_map_node(map_type, name, key_size, value_size, - max_entries, map_flags, -1); + struct bpf_create_map_attr map_attr = {}; + + map_attr.name = name; + map_attr.map_type = map_type; + map_attr.map_flags = map_flags; + map_attr.key_size = key_size; + map_attr.value_size = value_size; + map_attr.max_entries = max_entries; + + return bpf_create_map_xattr(&map_attr); } int bpf_create_map_in_map_node(enum bpf_map_type map_type, const char *name, @@ -573,3 +606,28 @@ cleanup: close(sock); return ret; } + +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log) +{ + union bpf_attr attr = {}; + int fd; + + attr.btf = ptr_to_u64(btf); + attr.btf_size = btf_size; + +retry: + if (do_log && log_buf && log_buf_size) { + attr.btf_log_level = 1; + attr.btf_log_size = log_buf_size; + attr.btf_log_buf = ptr_to_u64(log_buf); + } + + fd = sys_bpf(BPF_BTF_LOAD, &attr, sizeof(attr)); + if (fd == -1 && !do_log && log_buf && log_buf_size) { + do_log = true; + goto retry; + } + + return fd; +} diff --git a/tools/lib/bpf/bpf.h b/tools/lib/bpf/bpf.h index 39f6a0d64a3b..553b11ad52b3 100644 --- a/tools/lib/bpf/bpf.h +++ b/tools/lib/bpf/bpf.h @@ -24,8 +24,23 @@ #define __BPF_BPF_H #include <linux/bpf.h> +#include <stdbool.h> #include <stddef.h> +struct bpf_create_map_attr { + const char *name; + enum bpf_map_type map_type; + __u32 map_flags; + __u32 key_size; + __u32 value_size; + __u32 max_entries; + __u32 numa_node; + __u32 btf_fd; + __u32 btf_key_id; + __u32 btf_value_id; +}; + +int bpf_create_map_xattr(const struct bpf_create_map_attr *create_attr); int bpf_create_map_node(enum bpf_map_type map_type, const char *name, int key_size, int value_size, int max_entries, __u32 map_flags, int node); @@ -87,4 +102,6 @@ int bpf_obj_get_info_by_fd(int prog_fd, void *info, __u32 *info_len); int bpf_prog_query(int target_fd, enum bpf_attach_type type, __u32 query_flags, __u32 *attach_flags, __u32 *prog_ids, __u32 *prog_cnt); int bpf_raw_tracepoint_open(const char *name, int prog_fd); +int bpf_load_btf(void *btf, __u32 btf_size, char *log_buf, __u32 log_buf_size, + bool do_log); #endif diff --git a/tools/lib/bpf/btf.c b/tools/lib/bpf/btf.c new file mode 100644 index 000000000000..2bac710e3194 --- /dev/null +++ b/tools/lib/bpf/btf.c @@ -0,0 +1,374 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <stdlib.h> +#include <stdint.h> +#include <string.h> +#include <unistd.h> +#include <errno.h> +#include <linux/err.h> +#include <linux/btf.h> +#include "btf.h" +#include "bpf.h" + +#define elog(fmt, ...) { if (err_log) err_log(fmt, ##__VA_ARGS__); } +#define max(a, b) ((a) > (b) ? (a) : (b)) +#define min(a, b) ((a) < (b) ? (a) : (b)) + +#define BTF_MAX_NR_TYPES 65535 + +static struct btf_type btf_void; + +struct btf { + union { + struct btf_header *hdr; + void *data; + }; + struct btf_type **types; + const char *strings; + void *nohdr_data; + uint32_t nr_types; + uint32_t types_size; + uint32_t data_size; + int fd; +}; + +static const char *btf_name_by_offset(const struct btf *btf, uint32_t offset) +{ + if (!BTF_STR_TBL_ELF_ID(offset) && + BTF_STR_OFFSET(offset) < btf->hdr->str_len) + return &btf->strings[BTF_STR_OFFSET(offset)]; + else + return NULL; +} + +static int btf_add_type(struct btf *btf, struct btf_type *t) +{ + if (btf->types_size - btf->nr_types < 2) { + struct btf_type **new_types; + u32 expand_by, new_size; + + if (btf->types_size == BTF_MAX_NR_TYPES) + return -E2BIG; + + expand_by = max(btf->types_size >> 2, 16); + new_size = min(BTF_MAX_NR_TYPES, btf->types_size + expand_by); + + new_types = realloc(btf->types, sizeof(*new_types) * new_size); + if (!new_types) + return -ENOMEM; + + if (btf->nr_types == 0) + new_types[0] = &btf_void; + + btf->types = new_types; + btf->types_size = new_size; + } + + btf->types[++(btf->nr_types)] = t; + + return 0; +} + +static int btf_parse_hdr(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + u32 meta_left; + + if (btf->data_size < sizeof(struct btf_header)) { + elog("BTF header not found\n"); + return -EINVAL; + } + + if (hdr->magic != BTF_MAGIC) { + elog("Invalid BTF magic:%x\n", hdr->magic); + return -EINVAL; + } + + if (hdr->version != BTF_VERSION) { + elog("Unsupported BTF version:%u\n", hdr->version); + return -ENOTSUP; + } + + if (hdr->flags) { + elog("Unsupported BTF flags:%x\n", hdr->flags); + return -ENOTSUP; + } + + meta_left = btf->data_size - sizeof(*hdr); + if (!meta_left) { + elog("BTF has no data\n"); + return -EINVAL; + } + + if (meta_left < hdr->type_off) { + elog("Invalid BTF type section offset:%u\n", hdr->type_off); + return -EINVAL; + } + + if (meta_left < hdr->str_off) { + elog("Invalid BTF string section offset:%u\n", hdr->str_off); + return -EINVAL; + } + + if (hdr->type_off >= hdr->str_off) { + elog("BTF type section offset >= string section offset. No type?\n"); + return -EINVAL; + } + + if (hdr->type_off & 0x02) { + elog("BTF type section is not aligned to 4 bytes\n"); + return -EINVAL; + } + + btf->nohdr_data = btf->hdr + 1; + + return 0; +} + +static int btf_parse_str_sec(struct btf *btf, btf_print_fn_t err_log) +{ + const struct btf_header *hdr = btf->hdr; + const char *start = btf->nohdr_data + hdr->str_off; + const char *end = start + btf->hdr->str_len; + + if (!hdr->str_len || hdr->str_len - 1 > BTF_MAX_NAME_OFFSET || + start[0] || end[-1]) { + elog("Invalid BTF string section\n"); + return -EINVAL; + } + + btf->strings = start; + + return 0; +} + +static int btf_parse_type_sec(struct btf *btf, btf_print_fn_t err_log) +{ + struct btf_header *hdr = btf->hdr; + void *nohdr_data = btf->nohdr_data; + void *next_type = nohdr_data + hdr->type_off; + void *end_type = nohdr_data + hdr->str_off; + + while (next_type < end_type) { + struct btf_type *t = next_type; + uint16_t vlen = BTF_INFO_VLEN(t->info); + int err; + + next_type += sizeof(*t); + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + next_type += sizeof(int); + break; + case BTF_KIND_ARRAY: + next_type += sizeof(struct btf_array); + break; + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + next_type += vlen * sizeof(struct btf_member); + break; + case BTF_KIND_ENUM: + next_type += vlen * sizeof(struct btf_enum); + break; + case BTF_KIND_TYPEDEF: + case BTF_KIND_PTR: + case BTF_KIND_FWD: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + break; + default: + elog("Unsupported BTF_KIND:%u\n", + BTF_INFO_KIND(t->info)); + return -EINVAL; + } + + err = btf_add_type(btf, t); + if (err) + return err; + } + + return 0; +} + +static const struct btf_type *btf_type_by_id(const struct btf *btf, + uint32_t type_id) +{ + if (type_id > btf->nr_types) + return NULL; + + return btf->types[type_id]; +} + +static bool btf_type_is_void(const struct btf_type *t) +{ + return t == &btf_void || BTF_INFO_KIND(t->info) == BTF_KIND_FWD; +} + +static bool btf_type_is_void_or_null(const struct btf_type *t) +{ + return !t || btf_type_is_void(t); +} + +static int64_t btf_type_size(const struct btf_type *t) +{ + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_INT: + case BTF_KIND_STRUCT: + case BTF_KIND_UNION: + case BTF_KIND_ENUM: + return t->size; + case BTF_KIND_PTR: + return sizeof(void *); + default: + return -EINVAL; + } +} + +#define MAX_RESOLVE_DEPTH 32 + +int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id) +{ + const struct btf_array *array; + const struct btf_type *t; + uint32_t nelems = 1; + int64_t size = -1; + int i; + + t = btf_type_by_id(btf, type_id); + for (i = 0; i < MAX_RESOLVE_DEPTH && !btf_type_is_void_or_null(t); + i++) { + size = btf_type_size(t); + if (size >= 0) + break; + + switch (BTF_INFO_KIND(t->info)) { + case BTF_KIND_TYPEDEF: + case BTF_KIND_VOLATILE: + case BTF_KIND_CONST: + case BTF_KIND_RESTRICT: + type_id = t->type; + break; + case BTF_KIND_ARRAY: + array = (const struct btf_array *)(t + 1); + if (nelems && array->nelems > UINT32_MAX / nelems) + return -E2BIG; + nelems *= array->nelems; + type_id = array->type; + break; + default: + return -EINVAL; + } + + t = btf_type_by_id(btf, type_id); + } + + if (size < 0) + return -EINVAL; + + if (nelems && size > UINT32_MAX / nelems) + return -E2BIG; + + return nelems * size; +} + +int32_t btf__find_by_name(const struct btf *btf, const char *type_name) +{ + uint32_t i; + + if (!strcmp(type_name, "void")) + return 0; + + for (i = 1; i <= btf->nr_types; i++) { + const struct btf_type *t = btf->types[i]; + const char *name = btf_name_by_offset(btf, t->name_off); + + if (name && !strcmp(type_name, name)) + return i; + } + + return -ENOENT; +} + +void btf__free(struct btf *btf) +{ + if (!btf) + return; + + if (btf->fd != -1) + close(btf->fd); + + free(btf->data); + free(btf->types); + free(btf); +} + +struct btf *btf__new(uint8_t *data, uint32_t size, + btf_print_fn_t err_log) +{ + uint32_t log_buf_size = 0; + char *log_buf = NULL; + struct btf *btf; + int err; + + btf = calloc(1, sizeof(struct btf)); + if (!btf) + return ERR_PTR(-ENOMEM); + + btf->fd = -1; + + if (err_log) { + log_buf = malloc(BPF_LOG_BUF_SIZE); + if (!log_buf) { + err = -ENOMEM; + goto done; + } + *log_buf = 0; + log_buf_size = BPF_LOG_BUF_SIZE; + } + + btf->data = malloc(size); + if (!btf->data) { + err = -ENOMEM; + goto done; + } + + memcpy(btf->data, data, size); + btf->data_size = size; + + btf->fd = bpf_load_btf(btf->data, btf->data_size, + log_buf, log_buf_size, false); + + if (btf->fd == -1) { + err = -errno; + elog("Error loading BTF: %s(%d)\n", strerror(errno), errno); + if (log_buf && *log_buf) + elog("%s\n", log_buf); + goto done; + } + + err = btf_parse_hdr(btf, err_log); + if (err) + goto done; + + err = btf_parse_str_sec(btf, err_log); + if (err) + goto done; + + err = btf_parse_type_sec(btf, err_log); + +done: + free(log_buf); + + if (err) { + btf__free(btf); + return ERR_PTR(err); + } + + return btf; +} + +int btf__fd(const struct btf *btf) +{ + return btf->fd; +} diff --git a/tools/lib/bpf/btf.h b/tools/lib/bpf/btf.h new file mode 100644 index 000000000000..74bb344035bb --- /dev/null +++ b/tools/lib/bpf/btf.h @@ -0,0 +1,22 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#ifndef __BPF_BTF_H +#define __BPF_BTF_H + +#include <stdint.h> + +#define BTF_ELF_SEC ".BTF" + +struct btf; + +typedef int (*btf_print_fn_t)(const char *, ...) + __attribute__((format(printf, 1, 2))); + +void btf__free(struct btf *btf); +struct btf *btf__new(uint8_t *data, uint32_t size, btf_print_fn_t err_log); +int32_t btf__find_by_name(const struct btf *btf, const char *type_name); +int64_t btf__resolve_size(const struct btf *btf, uint32_t type_id); +int btf__fd(const struct btf *btf); + +#endif diff --git a/tools/lib/bpf/libbpf.c b/tools/lib/bpf/libbpf.c index 5922443063f0..7bcdca13083a 100644 --- a/tools/lib/bpf/libbpf.c +++ b/tools/lib/bpf/libbpf.c @@ -45,6 +45,7 @@ #include "libbpf.h" #include "bpf.h" +#include "btf.h" #ifndef EM_BPF #define EM_BPF 247 @@ -212,6 +213,8 @@ struct bpf_map { char *name; size_t offset; struct bpf_map_def def; + uint32_t btf_key_id; + uint32_t btf_value_id; void *priv; bpf_map_clear_priv_t clear_priv; }; @@ -256,6 +259,8 @@ struct bpf_object { */ struct list_head list; + struct btf *btf; + void *priv; bpf_object_clear_priv_t clear_priv; @@ -819,7 +824,15 @@ static int bpf_object__elf_collect(struct bpf_object *obj) data->d_size); else if (strcmp(name, "maps") == 0) obj->efile.maps_shndx = idx; - else if (sh.sh_type == SHT_SYMTAB) { + else if (strcmp(name, BTF_ELF_SEC) == 0) { + obj->btf = btf__new(data->d_buf, data->d_size, + __pr_debug); + if (IS_ERR(obj->btf)) { + pr_warning("Error loading ELF section %s: %ld. Ignored and continue.\n", + BTF_ELF_SEC, PTR_ERR(obj->btf)); + obj->btf = NULL; + } + } else if (sh.sh_type == SHT_SYMTAB) { if (obj->efile.symbols) { pr_warning("bpf: multiple SYMTAB in %s\n", obj->path); @@ -996,33 +1009,126 @@ bpf_program__collect_reloc(struct bpf_program *prog, GElf_Shdr *shdr, return 0; } +static int bpf_map_find_btf_info(struct bpf_map *map, const struct btf *btf) +{ + struct bpf_map_def *def = &map->def; + const size_t max_name = 256; + int64_t key_size, value_size; + int32_t key_id, value_id; + char name[max_name]; + + /* Find key type by name from BTF */ + if (snprintf(name, max_name, "%s_key", map->name) == max_name) { + pr_warning("map:%s length of BTF key_type:%s_key is too long\n", + map->name, map->name); + return -EINVAL; + } + + key_id = btf__find_by_name(btf, name); + if (key_id < 0) { + pr_debug("map:%s key_type:%s cannot be found in BTF\n", + map->name, name); + return key_id; + } + + key_size = btf__resolve_size(btf, key_id); + if (key_size < 0) { + pr_warning("map:%s key_type:%s cannot get the BTF type_size\n", + map->name, name); + return key_size; + } + + if (def->key_size != key_size) { + pr_warning("map:%s key_type:%s has BTF type_size:%ld != key_size:%u\n", + map->name, name, key_size, def->key_size); + return -EINVAL; + } + + /* Find value type from BTF */ + if (snprintf(name, max_name, "%s_value", map->name) == max_name) { + pr_warning("map:%s length of BTF value_type:%s_value is too long\n", + map->name, map->name); + return -EINVAL; + } + + value_id = btf__find_by_name(btf, name); + if (value_id < 0) { + pr_debug("map:%s value_type:%s cannot be found in BTF\n", + map->name, name); + return value_id; + } + + value_size = btf__resolve_size(btf, value_id); + if (value_size < 0) { + pr_warning("map:%s value_type:%s cannot get the BTF type_size\n", + map->name, name); + return value_size; + } + + if (def->value_size != value_size) { + pr_warning("map:%s value_type:%s has BTF type_size:%ld != value_size:%u\n", + map->name, name, value_size, def->value_size); + return -EINVAL; + } + + map->btf_key_id = key_id; + map->btf_value_id = value_id; + + return 0; +} + static int bpf_object__create_maps(struct bpf_object *obj) { + struct bpf_create_map_attr create_attr = {}; unsigned int i; + int err; for (i = 0; i < obj->nr_maps; i++) { - struct bpf_map_def *def = &obj->maps[i].def; - int *pfd = &obj->maps[i].fd; - - *pfd = bpf_create_map_name(def->type, - obj->maps[i].name, - def->key_size, - def->value_size, - def->max_entries, - def->map_flags); + struct bpf_map *map = &obj->maps[i]; + struct bpf_map_def *def = &map->def; + int *pfd = &map->fd; + + create_attr.name = map->name; + create_attr.map_type = def->type; + create_attr.map_flags = def->map_flags; + create_attr.key_size = def->key_size; + create_attr.value_size = def->value_size; + create_attr.max_entries = def->max_entries; + create_attr.btf_fd = 0; + create_attr.btf_key_id = 0; + create_attr.btf_value_id = 0; + + if (obj->btf && !bpf_map_find_btf_info(map, obj->btf)) { + create_attr.btf_fd = btf__fd(obj->btf); + create_attr.btf_key_id = map->btf_key_id; + create_attr.btf_value_id = map->btf_value_id; + } + + *pfd = bpf_create_map_xattr(&create_attr); + if (*pfd < 0 && create_attr.btf_key_id) { + pr_warning("Error in bpf_create_map_xattr(%s):%s(%d). Retrying without BTF.\n", + map->name, strerror(errno), errno); + create_attr.btf_fd = 0; + create_attr.btf_key_id = 0; + create_attr.btf_value_id = 0; + map->btf_key_id = 0; + map->btf_value_id = 0; + *pfd = bpf_create_map_xattr(&create_attr); + } + if (*pfd < 0) { size_t j; - int err = *pfd; + err = *pfd; pr_warning("failed to create map (name: '%s'): %s\n", - obj->maps[i].name, + map->name, strerror(errno)); for (j = 0; j < i; j++) zclose(obj->maps[j].fd); return err; } - pr_debug("create map %s: fd=%d\n", obj->maps[i].name, *pfd); + pr_debug("create map %s: fd=%d\n", map->name, *pfd); } return 0; @@ -1641,6 +1747,7 @@ void bpf_object__close(struct bpf_object *obj) bpf_object__elf_finish(obj); bpf_object__unload(obj); + btf__free(obj->btf); for (i = 0; i < obj->nr_maps; i++) { zfree(&obj->maps[i].name); @@ -1692,6 +1799,11 @@ unsigned int bpf_object__kversion(struct bpf_object *obj) return obj ? obj->kern_version : 0; } +int bpf_object__btf_fd(const struct bpf_object *obj) +{ + return obj->btf ? btf__fd(obj->btf) : -1; +} + int bpf_object__set_priv(struct bpf_object *obj, void *priv, bpf_object_clear_priv_t clear_priv) { @@ -1845,11 +1957,12 @@ BPF_PROG_TYPE_FNS(kprobe, BPF_PROG_TYPE_KPROBE); BPF_PROG_TYPE_FNS(sched_cls, BPF_PROG_TYPE_SCHED_CLS); BPF_PROG_TYPE_FNS(sched_act, BPF_PROG_TYPE_SCHED_ACT); BPF_PROG_TYPE_FNS(tracepoint, BPF_PROG_TYPE_TRACEPOINT); +BPF_PROG_TYPE_FNS(raw_tracepoint, BPF_PROG_TYPE_RAW_TRACEPOINT); BPF_PROG_TYPE_FNS(xdp, BPF_PROG_TYPE_XDP); BPF_PROG_TYPE_FNS(perf_event, BPF_PROG_TYPE_PERF_EVENT); -static void bpf_program__set_expected_attach_type(struct bpf_program *prog, - enum bpf_attach_type type) +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type) { prog->expected_attach_type = type; } @@ -1859,6 +1972,9 @@ static void bpf_program__set_expected_attach_type(struct bpf_program *prog, #define BPF_PROG_SEC(string, ptype) BPF_PROG_SEC_FULL(string, ptype, 0) +#define BPF_S_PROG_SEC(string, ptype) \ + BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK, ptype) + #define BPF_SA_PROG_SEC(string, ptype) \ BPF_PROG_SEC_FULL(string, BPF_PROG_TYPE_CGROUP_SOCK_ADDR, ptype) @@ -1874,6 +1990,7 @@ static const struct { BPF_PROG_SEC("classifier", BPF_PROG_TYPE_SCHED_CLS), BPF_PROG_SEC("action", BPF_PROG_TYPE_SCHED_ACT), BPF_PROG_SEC("tracepoint/", BPF_PROG_TYPE_TRACEPOINT), + BPF_PROG_SEC("raw_tracepoint/", BPF_PROG_TYPE_RAW_TRACEPOINT), BPF_PROG_SEC("xdp", BPF_PROG_TYPE_XDP), BPF_PROG_SEC("perf_event", BPF_PROG_TYPE_PERF_EVENT), BPF_PROG_SEC("cgroup/skb", BPF_PROG_TYPE_CGROUP_SKB), @@ -1889,10 +2006,13 @@ static const struct { BPF_SA_PROG_SEC("cgroup/bind6", BPF_CGROUP_INET6_BIND), BPF_SA_PROG_SEC("cgroup/connect4", BPF_CGROUP_INET4_CONNECT), BPF_SA_PROG_SEC("cgroup/connect6", BPF_CGROUP_INET6_CONNECT), + BPF_S_PROG_SEC("cgroup/post_bind4", BPF_CGROUP_INET4_POST_BIND), + BPF_S_PROG_SEC("cgroup/post_bind6", BPF_CGROUP_INET6_POST_BIND), }; #undef BPF_PROG_SEC #undef BPF_PROG_SEC_FULL +#undef BPF_S_PROG_SEC #undef BPF_SA_PROG_SEC static int bpf_program__identify_section(struct bpf_program *prog) @@ -1929,6 +2049,16 @@ const char *bpf_map__name(struct bpf_map *map) return map ? map->name : NULL; } +uint32_t bpf_map__btf_key_id(const struct bpf_map *map) +{ + return map ? map->btf_key_id : 0; +} + +uint32_t bpf_map__btf_value_id(const struct bpf_map *map) +{ + return map ? map->btf_value_id : 0; +} + int bpf_map__set_priv(struct bpf_map *map, void *priv, bpf_map_clear_priv_t clear_priv) { diff --git a/tools/lib/bpf/libbpf.h b/tools/lib/bpf/libbpf.h index a3a62a583f27..197f9ce2248c 100644 --- a/tools/lib/bpf/libbpf.h +++ b/tools/lib/bpf/libbpf.h @@ -78,6 +78,7 @@ int bpf_object__load(struct bpf_object *obj); int bpf_object__unload(struct bpf_object *obj); const char *bpf_object__name(struct bpf_object *obj); unsigned int bpf_object__kversion(struct bpf_object *obj); +int bpf_object__btf_fd(const struct bpf_object *obj); struct bpf_object *bpf_object__next(struct bpf_object *prev); #define bpf_object__for_each_safe(pos, tmp) \ @@ -185,15 +186,19 @@ int bpf_program__nth_fd(struct bpf_program *prog, int n); */ int bpf_program__set_socket_filter(struct bpf_program *prog); int bpf_program__set_tracepoint(struct bpf_program *prog); +int bpf_program__set_raw_tracepoint(struct bpf_program *prog); int bpf_program__set_kprobe(struct bpf_program *prog); int bpf_program__set_sched_cls(struct bpf_program *prog); int bpf_program__set_sched_act(struct bpf_program *prog); int bpf_program__set_xdp(struct bpf_program *prog); int bpf_program__set_perf_event(struct bpf_program *prog); void bpf_program__set_type(struct bpf_program *prog, enum bpf_prog_type type); +void bpf_program__set_expected_attach_type(struct bpf_program *prog, + enum bpf_attach_type type); bool bpf_program__is_socket_filter(struct bpf_program *prog); bool bpf_program__is_tracepoint(struct bpf_program *prog); +bool bpf_program__is_raw_tracepoint(struct bpf_program *prog); bool bpf_program__is_kprobe(struct bpf_program *prog); bool bpf_program__is_sched_cls(struct bpf_program *prog); bool bpf_program__is_sched_act(struct bpf_program *prog); @@ -239,6 +244,8 @@ bpf_map__next(struct bpf_map *map, struct bpf_object *obj); int bpf_map__fd(struct bpf_map *map); const struct bpf_map_def *bpf_map__def(struct bpf_map *map); const char *bpf_map__name(struct bpf_map *map); +uint32_t bpf_map__btf_key_id(const struct bpf_map *map); +uint32_t bpf_map__btf_value_id(const struct bpf_map *map); typedef void (*bpf_map_clear_priv_t)(struct bpf_map *, void *); int bpf_map__set_priv(struct bpf_map *map, void *priv, diff --git a/tools/testing/selftests/bpf/.gitignore b/tools/testing/selftests/bpf/.gitignore index 5e1ab2f0eb79..3e3b3ced3f7c 100644 --- a/tools/testing/selftests/bpf/.gitignore +++ b/tools/testing/selftests/bpf/.gitignore @@ -15,3 +15,4 @@ test_libbpf_open test_sock test_sock_addr urandom_read +test_btf diff --git a/tools/testing/selftests/bpf/Makefile b/tools/testing/selftests/bpf/Makefile index 0a315ddabbf4..9d762184b805 100644 --- a/tools/testing/selftests/bpf/Makefile +++ b/tools/testing/selftests/bpf/Makefile @@ -24,14 +24,16 @@ urandom_read: urandom_read.c # Order correspond to 'make run_tests' order TEST_GEN_PROGS = test_verifier test_tag test_maps test_lru_map test_lpm_map test_progs \ test_align test_verifier_log test_dev_cgroup test_tcpbpf_user \ - test_sock test_sock_addr + test_sock test_btf test_sockmap TEST_GEN_FILES = test_pkt_access.o test_xdp.o test_l4lb.o test_tcp_estats.o test_obj_id.o \ test_pkt_md_access.o test_xdp_redirect.o test_xdp_meta.o sockmap_parse_prog.o \ sockmap_verdict_prog.o dev_cgroup.o sample_ret0.o test_tracepoint.o \ test_l4lb_noinline.o test_xdp_noinline.o test_stacktrace_map.o \ sample_map_ret0.o test_tcpbpf_kern.o test_stacktrace_build_id.o \ - sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o + sockmap_tcp_msg_prog.o connect4_prog.o connect6_prog.o test_adjust_tail.o \ + test_btf_haskv.o test_btf_nokv.o test_sockmap_kern.o test_tunnel_kern.o \ + test_get_stack_rawtp.o # Order correspond to 'make run_tests' order TEST_PROGS := test_kmod.sh \ @@ -39,10 +41,11 @@ TEST_PROGS := test_kmod.sh \ test_xdp_redirect.sh \ test_xdp_meta.sh \ test_offload.py \ - test_sock_addr.sh + test_sock_addr.sh \ + test_tunnel.sh # Compile but not part of 'make run_tests' -TEST_GEN_PROGS_EXTENDED = test_libbpf_open +TEST_GEN_PROGS_EXTENDED = test_libbpf_open test_sock_addr include ../lib.mk @@ -55,6 +58,8 @@ $(TEST_GEN_PROGS_EXTENDED): $(OUTPUT)/libbpf.a $(OUTPUT)/test_dev_cgroup: cgroup_helpers.c $(OUTPUT)/test_sock: cgroup_helpers.c $(OUTPUT)/test_sock_addr: cgroup_helpers.c +$(OUTPUT)/test_sockmap: cgroup_helpers.c +$(OUTPUT)/test_progs: trace_helpers.c .PHONY: force @@ -66,6 +71,8 @@ $(BPFOBJ): force CLANG ?= clang LLC ?= llc +LLVM_OBJCOPY ?= llvm-objcopy +BTF_PAHOLE ?= pahole PROBE := $(shell $(LLC) -march=bpf -mcpu=probe -filetype=null /dev/null 2>&1) @@ -83,9 +90,26 @@ CLANG_FLAGS = -I. -I./include/uapi -I../../../include/uapi \ $(OUTPUT)/test_l4lb_noinline.o: CLANG_FLAGS += -fno-inline $(OUTPUT)/test_xdp_noinline.o: CLANG_FLAGS += -fno-inline +BTF_LLC_PROBE := $(shell $(LLC) -march=bpf -mattr=help |& grep dwarfris) +BTF_PAHOLE_PROBE := $(shell $(BTF_PAHOLE) --help |& grep BTF) +BTF_OBJCOPY_PROBE := $(shell $(LLVM_OBJCOPY) --version |& grep LLVM) + +ifneq ($(BTF_LLC_PROBE),) +ifneq ($(BTF_PAHOLE_PROBE),) +ifneq ($(BTF_OBJCOPY_PROBE),) + CLANG_FLAGS += -g + LLC_FLAGS += -mattr=dwarfris + DWARF2BTF = y +endif +endif +endif + $(OUTPUT)/%.o: %.c $(CLANG) $(CLANG_FLAGS) \ -O2 -target bpf -emit-llvm -c $< -o - | \ - $(LLC) -march=bpf -mcpu=$(CPU) -filetype=obj -o $@ + $(LLC) -march=bpf -mcpu=$(CPU) $(LLC_FLAGS) -filetype=obj -o $@ +ifeq ($(DWARF2BTF),y) + $(BTF_PAHOLE) -J $@ +endif EXTRA_CLEAN := $(TEST_CUSTOM_PROGS) diff --git a/tools/testing/selftests/bpf/bpf_helpers.h b/tools/testing/selftests/bpf/bpf_helpers.h index d8223d99f96d..265f8e0e8ada 100644 --- a/tools/testing/selftests/bpf/bpf_helpers.h +++ b/tools/testing/selftests/bpf/bpf_helpers.h @@ -96,6 +96,13 @@ static int (*bpf_msg_pull_data)(void *ctx, int start, int end, int flags) = (void *) BPF_FUNC_msg_pull_data; static int (*bpf_bind)(void *ctx, void *addr, int addr_len) = (void *) BPF_FUNC_bind; +static int (*bpf_xdp_adjust_tail)(void *ctx, int offset) = + (void *) BPF_FUNC_xdp_adjust_tail; +static int (*bpf_skb_get_xfrm_state)(void *ctx, int index, void *state, + int size, int flags) = + (void *) BPF_FUNC_skb_get_xfrm_state; +static int (*bpf_get_stack)(void *ctx, void *buf, int size, int flags) = + (void *) BPF_FUNC_get_stack; /* llvm builtin functions that eBPF C program may use to * emit BPF_LD_ABS and BPF_LD_IND instructions @@ -129,6 +136,8 @@ static int (*bpf_l3_csum_replace)(void *ctx, int off, int from, int to, int flag (void *) BPF_FUNC_l3_csum_replace; static int (*bpf_l4_csum_replace)(void *ctx, int off, int from, int to, int flags) = (void *) BPF_FUNC_l4_csum_replace; +static int (*bpf_csum_diff)(void *from, int from_size, void *to, int to_size, int seed) = + (void *) BPF_FUNC_csum_diff; static int (*bpf_skb_under_cgroup)(void *ctx, void *map, int index) = (void *) BPF_FUNC_skb_under_cgroup; static int (*bpf_skb_change_head)(void *, int len, int flags) = diff --git a/tools/testing/selftests/bpf/test_adjust_tail.c b/tools/testing/selftests/bpf/test_adjust_tail.c new file mode 100644 index 000000000000..4cd5e860c903 --- /dev/null +++ b/tools/testing/selftests/bpf/test_adjust_tail.c @@ -0,0 +1,30 @@ +/* SPDX-License-Identifier: GPL-2.0 + * Copyright (c) 2018 Facebook + * + * This program is free software; you can redistribute it and/or + * modify it under the terms of version 2 of the GNU General Public + * License as published by the Free Software Foundation. + */ +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +SEC("xdp_adjust_tail") +int _xdp_adjust_tail(struct xdp_md *xdp) +{ + void *data_end = (void *)(long)xdp->data_end; + void *data = (void *)(long)xdp->data; + int offset = 0; + + if (data_end - data == 54) + offset = 256; + else + offset = 20; + if (bpf_xdp_adjust_tail(xdp, 0 - offset)) + return XDP_DROP; + return XDP_TX; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf.c b/tools/testing/selftests/bpf/test_btf.c new file mode 100644 index 000000000000..7b39b1f712a1 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf.c @@ -0,0 +1,1669 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ + +#include <linux/bpf.h> +#include <linux/btf.h> +#include <linux/err.h> +#include <bpf/bpf.h> +#include <sys/resource.h> +#include <libelf.h> +#include <gelf.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdarg.h> +#include <unistd.h> +#include <fcntl.h> +#include <errno.h> +#include <bpf/libbpf.h> +#include <bpf/btf.h> + +#include "bpf_rlimit.h" + +#define min(a, b) ((a) < (b) ? (a) : (b)) +#define __printf(a, b) __attribute__((format(printf, a, b))) + +__printf(1, 2) +static int __base_pr(const char *format, ...) +{ + va_list args; + int err; + + va_start(args, format); + err = vfprintf(stderr, format, args); + va_end(args); + return err; +} + +#define BTF_INFO_ENC(kind, root, vlen) \ + ((!!(root) << 31) | ((kind) << 24) | ((vlen) & BTF_MAX_VLEN)) + +#define BTF_TYPE_ENC(name, info, size_or_type) \ + (name), (info), (size_or_type) + +#define BTF_INT_ENC(encoding, bits_offset, nr_bits) \ + ((encoding) << 24 | (bits_offset) << 16 | (nr_bits)) +#define BTF_TYPE_INT_ENC(name, encoding, bits_offset, bits, sz) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_INT, 0, 0), sz), \ + BTF_INT_ENC(encoding, bits_offset, bits) + +#define BTF_ARRAY_ENC(type, index_type, nr_elems) \ + (type), (index_type), (nr_elems) +#define BTF_TYPE_ARRAY_ENC(type, index_type, nr_elems) \ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ARRAY, 0, 0), 0), \ + BTF_ARRAY_ENC(type, index_type, nr_elems) + +#define BTF_MEMBER_ENC(name, type, bits_offset) \ + (name), (type), (bits_offset) +#define BTF_ENUM_ENC(name, val) (name), (val) + +#define BTF_TYPEDEF_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), type) + +#define BTF_PTR_ENC(name, type) \ + BTF_TYPE_ENC(name, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), type) + +#define BTF_END_RAW 0xdeadbeef +#define NAME_TBD 0xdeadb33f + +#define MAX_NR_RAW_TYPES 1024 +#define BTF_LOG_BUF_SIZE 65535 + +#ifndef ARRAY_SIZE +# define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) +#endif + +static struct args { + unsigned int raw_test_num; + unsigned int file_test_num; + unsigned int get_info_test_num; + bool raw_test; + bool file_test; + bool get_info_test; + bool pprint_test; + bool always_log; +} args; + +static char btf_log_buf[BTF_LOG_BUF_SIZE]; + +static struct btf_header hdr_tmpl = { + .magic = BTF_MAGIC, + .version = BTF_VERSION, +}; + +struct btf_raw_test { + const char *descr; + const char *str_sec; + const char *map_name; + __u32 raw_types[MAX_NR_RAW_TYPES]; + __u32 str_sec_size; + enum bpf_map_type map_type; + __u32 key_size; + __u32 value_size; + __u32 key_id; + __u32 value_id; + __u32 max_entries; + bool btf_load_err; + bool map_create_err; + int type_off_delta; + int str_off_delta; + int str_len_delta; +}; + +static struct btf_raw_test raw_tests[] = { +/* enum E { + * E0, + * E1, + * }; + * + * struct A { + * int m; + * unsigned long long n; + * char o; + * [3 bytes hole] + * int p[8]; + * int q[4][8]; + * enum E r; + * }; + */ +{ + .descr = "struct test #1", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* unsigned long long */ + BTF_TYPE_INT_ENC(0, 0, 0, 64, 8), /* [2] */ + /* char */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 8, 1), /* [3] */ + /* int[8] */ + BTF_TYPE_ARRAY_ENC(1, 1, 8), /* [4] */ + /* struct A { */ /* [5] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 6), 180), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* unsigned long long n;*/ + BTF_MEMBER_ENC(NAME_TBD, 3, 96),/* char o; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 128),/* int p[8] */ + BTF_MEMBER_ENC(NAME_TBD, 6, 384),/* int q[4][8] */ + BTF_MEMBER_ENC(NAME_TBD, 7, 1408), /* enum E r */ + /* } */ + /* int[4][8] */ + BTF_TYPE_ARRAY_ENC(4, 1, 4), /* [6] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1", + .str_sec_size = sizeof("\0A\0m\0n\0o\0p\0q\0r\0E\0E0\0E1"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test1_map", + .key_size = sizeof(int), + .value_size = 180, + .key_id = 1, + .value_id = 5, + .max_entries = 4, +}, + +/* typedef struct b Struct_B; + * + * struct A { + * int m; + * struct b n[4]; + * const Struct_B o[4]; + * }; + * + * struct B { + * int m; + * int n; + * }; + */ +{ + .descr = "struct test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct b [4] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(4, 1, 4), + + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 3), 68), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct B n[4] */ + BTF_MEMBER_ENC(NAME_TBD, 8, 288),/* const Struct_B o[4];*/ + /* } */ + + /* struct B { */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 1, 32),/* int n; */ + /* } */ + + /* const int */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 1), + /* typedef struct b Struct_B */ /* [6] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_TYPEDEF, 0, 0), 4), + /* const Struct_B */ /* [7] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 6), + /* const Struct_B [4] */ /* [8] */ + BTF_TYPE_ARRAY_ENC(7, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n\0o\0B\0m\0n\0Struct_B", + .str_sec_size = sizeof("\0A\0m\0n\0o\0B\0m\0n\0Struct_B"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "struct_test2_map", + .key_size = sizeof(int), + .value_size = 68, + .key_id = 1, + .value_id = 3, + .max_entries = 4, +}, + +/* Test member exceeds the size of struct. + * + * struct A { + * int m; + * int n; + * }; + */ +{ + .descr = "size check test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* int n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check1_map", + .key_size = sizeof(int), + .value_size = 1, + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +/* Test member exeeds the size of struct + * + * struct A { + * int m; + * int n[2]; + * }; + */ +{ + .descr = "size check test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* int[2] */ /* [2] */ + BTF_TYPE_ARRAY_ENC(1, 1, 2), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 3 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* int n[2]; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check2_map", + .key_size = sizeof(int), + .value_size = 1, + .key_id = 1, + .value_id = 3, + .max_entries = 4, + .btf_load_err = true, + +}, + +/* Test member exeeds the size of struct + * + * struct A { + * int m; + * void *n; + * }; + */ +{ + .descr = "size check test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* void* */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 0), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) + sizeof(void *) - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* void *n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0n", + .str_sec_size = sizeof("\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check3_map", + .key_size = sizeof(int), + .value_size = 1, + .key_id = 1, + .value_id = 3, + .max_entries = 4, + .btf_load_err = true, +}, + +/* Test member exceeds the size of struct + * + * enum E { + * E0, + * E1, + * }; + * + * struct A { + * int m; + * enum E n; + * }; + */ +{ + .descr = "size check test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, sizeof(int)), + /* enum E { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 2), sizeof(int)), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + /* } */ + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), sizeof(int) * 2 - 1), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* enum E n; */ + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0E\0E0\0E1\0A\0m\0n", + .str_sec_size = sizeof("\0E\0E0\0E1\0A\0m\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "size_check4_map", + .key_size = sizeof(int), + .value_size = 1, + .key_id = 1, + .value_id = 3, + .max_entries = 4, + .btf_load_err = true, +}, + +/* typedef const void * const_void_ptr; + * struct A { + * const_void_ptr m; + * }; + */ +{ + .descr = "void test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + /* typedef const void * const_void_ptr */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + /* struct A { */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const_void_ptr m; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 0), + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0const_void_ptr\0A\0m", + .str_sec_size = sizeof("\0const_void_ptr\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test1_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_id = 1, + .value_id = 4, + .max_entries = 4, +}, + +/* struct A { + * const void m; + * }; + */ +{ + .descr = "void test #2", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* struct A { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), 8), + /* const void m; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 0), + /* } */ + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test2_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_id = 1, + .value_id = 3, + .max_entries = 4, + .btf_load_err = true, +}, + +/* typedef const void * const_void_ptr; + * const_void_ptr[4] + */ +{ + .descr = "void test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void* */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 2), + /* typedef const void * const_void_ptr */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + /* const_void_ptr[4] */ /* [4] */ + BTF_TYPE_ARRAY_ENC(3, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0const_void_ptr", + .str_sec_size = sizeof("\0const_void_ptr"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test3_map", + .key_size = sizeof(int), + .value_size = sizeof(void *) * 4, + .key_id = 1, + .value_id = 4, + .max_entries = 4, +}, + +/* const void[4] */ +{ + .descr = "void test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* const void */ /* [2] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 0), + /* const void[4] */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "void_test4_map", + .key_size = sizeof(int), + .value_size = sizeof(void *) * 4, + .key_id = 1, + .value_id = 3, + .max_entries = 4, + .btf_load_err = true, +}, + +/* Array_A <------------------+ + * elem_type == Array_B | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array A --+ + */ +{ + .descr = "loop test #1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* Array_B */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test1_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +/* typedef is _before_ the BTF type of Array_A and Array_B + * + * typedef Array_B int_array; + * + * Array_A <------------------+ + * elem_type == int_array | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #2", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* typedef Array_B int_array */ + BTF_TYPEDEF_ENC(1, 4), /* [2] */ + /* Array_A */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), /* [3] */ + /* Array_B */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), /* [4] */ + + BTF_END_RAW, + }, + .str_sec = "\0int_array\0", + .str_sec_size = sizeof("\0int_array"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test2_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +/* Array_A <------------------+ + * elem_type == Array_B | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* Array_B */ /* [3] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test3_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +/* typedef is _between_ the BTF type of Array_A and Array_B + * + * typedef Array_B int_array; + * + * Array_A <------------------+ + * elem_type == int_array | + * | | + * | | + * Array_B <-------- + | + * elem_type == Array_A --+ + */ +{ + .descr = "loop test #4", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* Array_A */ /* [2] */ + BTF_TYPE_ARRAY_ENC(3, 1, 8), + /* typedef Array_B int_array */ /* [3] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), + /* Array_B */ /* [4] */ + BTF_TYPE_ARRAY_ENC(2, 1, 8), + BTF_END_RAW, + }, + .str_sec = "\0int_array\0", + .str_sec_size = sizeof("\0int_array"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test4_map", + .key_size = sizeof(int), + .value_size = sizeof(sizeof(int) * 8), + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +/* typedef struct B Struct_B + * + * struct A { + * int x; + * Struct_B y; + * }; + * + * struct B { + * int x; + * struct A y; + * }; + */ +{ + .descr = "loop test #5", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + /* struct A */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 32),/* Struct_B y; */ + /* typedef struct B Struct_B */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), /* [3] */ + /* struct B */ /* [4] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A y; */ + BTF_END_RAW, + }, + .str_sec = "\0A\0x\0y\0Struct_B\0B\0x\0y", + .str_sec_size = sizeof("\0A\0x\0y\0Struct_B\0B\0x\0y"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test5_map", + .key_size = sizeof(int), + .value_size = 8, + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +/* struct A { + * int x; + * struct A array_a[4]; + * }; + */ +{ + .descr = "loop test #6", + .raw_types = { + /* int */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), /* [1] */ + BTF_TYPE_ARRAY_ENC(3, 1, 4), /* [2] */ + /* struct A */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 1, 0), /* int x; */ + BTF_MEMBER_ENC(NAME_TBD, 2, 32),/* struct A array_a[4]; */ + BTF_END_RAW, + }, + .str_sec = "\0A\0x\0y", + .str_sec_size = sizeof("\0A\0x\0y"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test6_map", + .key_size = sizeof(int), + .value_size = 8, + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +{ + .descr = "loop test #7", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *m; */ + BTF_MEMBER_ENC(NAME_TBD, 3, 0), + /* CONST type_id=3 */ /* [3] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 4), + /* PTR type_id=2 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 3), + BTF_END_RAW, + }, + .str_sec = "\0A\0m", + .str_sec_size = sizeof("\0A\0m"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test7_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +{ + .descr = "loop test #8", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + /* struct A { */ /* [2] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *m; */ + BTF_MEMBER_ENC(NAME_TBD, 4, 0), + /* struct B { */ /* [3] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 1), sizeof(void *)), + /* const void *n; */ + BTF_MEMBER_ENC(NAME_TBD, 6, 0), + /* CONST type_id=5 */ /* [4] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 5), + /* PTR type_id=6 */ /* [5] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 6), + /* CONST type_id=7 */ /* [6] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_CONST, 0, 0), 7), + /* PTR type_id=4 */ /* [7] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_PTR, 0, 0), 4), + BTF_END_RAW, + }, + .str_sec = "\0A\0m\0B\0n", + .str_sec_size = sizeof("\0A\0m\0B\0n"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "loop_test8_map", + .key_size = sizeof(int), + .value_size = sizeof(void *), + .key_id = 1, + .value_id = 2, + .max_entries = 4, + .btf_load_err = true, +}, + +{ + .descr = "type_off == str_off", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_id = 1, + .value_id = 1, + .max_entries = 4, + .btf_load_err = true, + .type_off_delta = sizeof(struct btf_type) + sizeof(int) + sizeof("\0int"), +}, + +{ + .descr = "Unaligned type_off", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_id = 1, + .value_id = 1, + .max_entries = 4, + .btf_load_err = true, + .type_off_delta = 1, +}, + +{ + .descr = "str_off beyonds btf size", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_id = 1, + .value_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_off_delta = sizeof("\0int") + 1, +}, + +{ + .descr = "str_len beyonds btf size", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_id = 1, + .value_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_len_delta = 1, +}, + +{ + .descr = "String section does not end with null", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_id = 1, + .value_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_len_delta = -1, +}, + +{ + .descr = "Empty string section", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "\0int", + .str_sec_size = sizeof("\0int"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "hdr_test_map", + .key_size = sizeof(int), + .value_size = sizeof(int), + .key_id = 1, + .value_id = 1, + .max_entries = 4, + .btf_load_err = true, + .str_len_delta = 0 - (int)sizeof("\0int"), +}, + +}; /* struct btf_raw_test raw_tests[] */ + +static const char *get_next_str(const char *start, const char *end) +{ + return start < end - 1 ? start + 1 : NULL; +} + +static int get_type_sec_size(const __u32 *raw_types) +{ + int i; + + for (i = MAX_NR_RAW_TYPES - 1; + i >= 0 && raw_types[i] != BTF_END_RAW; + i--) + ; + + return i < 0 ? i : i * sizeof(raw_types[0]); +} + +static void *btf_raw_create(const struct btf_header *hdr, + const __u32 *raw_types, + const char *str, + unsigned int str_sec_size, + unsigned int *btf_size) +{ + const char *next_str = str, *end_str = str + str_sec_size; + unsigned int size_needed, offset; + struct btf_header *ret_hdr; + int i, type_sec_size; + uint32_t *ret_types; + void *raw_btf; + + type_sec_size = get_type_sec_size(raw_types); + if (type_sec_size < 0) { + fprintf(stderr, "Cannot get nr_raw_types\n"); + return NULL; + } + + size_needed = sizeof(*hdr) + type_sec_size + str_sec_size; + raw_btf = malloc(size_needed); + if (!raw_btf) { + fprintf(stderr, "Cannot allocate memory for raw_btf\n"); + return NULL; + } + + /* Copy header */ + memcpy(raw_btf, hdr, sizeof(*hdr)); + offset = sizeof(*hdr); + + /* Copy type section */ + ret_types = raw_btf + offset; + for (i = 0; i < type_sec_size / sizeof(raw_types[0]); i++) { + if (raw_types[i] == NAME_TBD) { + next_str = get_next_str(next_str, end_str); + if (!next_str) { + fprintf(stderr, "Error in getting next_str\n"); + free(raw_btf); + return NULL; + } + ret_types[i] = next_str - str; + next_str += strlen(next_str); + } else { + ret_types[i] = raw_types[i]; + } + } + offset += type_sec_size; + + /* Copy string section */ + memcpy(raw_btf + offset, str, str_sec_size); + + ret_hdr = (struct btf_header *)raw_btf; + ret_hdr->str_off = type_sec_size; + ret_hdr->str_len = str_sec_size; + + *btf_size = size_needed; + + return raw_btf; +} + +static int do_test_raw(unsigned int test_num) +{ + struct btf_raw_test *test = &raw_tests[test_num - 1]; + struct bpf_create_map_attr create_attr = {}; + int map_fd = -1, btf_fd = -1; + unsigned int raw_btf_size; + struct btf_header *hdr; + void *raw_btf; + int err; + + fprintf(stderr, "BTF raw test[%u] (%s): ", test_num, test->descr); + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + hdr = raw_btf; + + hdr->type_off = (int)hdr->type_off + test->type_off_delta; + hdr->str_off = (int)hdr->str_off + test->str_off_delta; + hdr->str_len = (int)hdr->str_len + test->str_len_delta; + + *btf_log_buf = '\0'; + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + free(raw_btf); + + err = ((btf_fd == -1) != test->btf_load_err); + if (err) + fprintf(stderr, "btf_load_err:%d btf_fd:%d\n", + test->btf_load_err, btf_fd); + + if (err || btf_fd == -1) + goto done; + + create_attr.name = test->map_name; + create_attr.map_type = test->map_type; + create_attr.key_size = test->key_size; + create_attr.value_size = test->value_size; + create_attr.max_entries = test->max_entries; + create_attr.btf_fd = btf_fd; + create_attr.btf_key_id = test->key_id; + create_attr.btf_value_id = test->value_id; + + map_fd = bpf_create_map_xattr(&create_attr); + + err = ((map_fd == -1) != test->map_create_err); + if (err) + fprintf(stderr, "map_create_err:%d map_fd:%d\n", + test->map_create_err, map_fd); + +done: + if (!err) + fprintf(stderr, "OK\n"); + + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "%s\n", btf_log_buf); + + if (btf_fd != -1) + close(btf_fd); + if (map_fd != -1) + close(map_fd); + + return err; +} + +static int test_raw(void) +{ + unsigned int i; + int err = 0; + + if (args.raw_test_num) + return do_test_raw(args.raw_test_num); + + for (i = 1; i <= ARRAY_SIZE(raw_tests); i++) + err |= do_test_raw(i); + + return err; +} + +struct btf_get_info_test { + const char *descr; + const char *str_sec; + __u32 raw_types[MAX_NR_RAW_TYPES]; + __u32 str_sec_size; + int info_size_delta; +}; + +const struct btf_get_info_test get_info_tests[] = { +{ + .descr = "== raw_btf_size+1", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .info_size_delta = 1, +}, +{ + .descr = "== raw_btf_size-3", + .raw_types = { + /* int */ /* [1] */ + BTF_TYPE_INT_ENC(0, BTF_INT_SIGNED, 0, 32, 4), + BTF_END_RAW, + }, + .str_sec = "", + .str_sec_size = sizeof(""), + .info_size_delta = -3, +}, +}; + +static int do_test_get_info(unsigned int test_num) +{ + const struct btf_get_info_test *test = &get_info_tests[test_num - 1]; + unsigned int raw_btf_size, user_btf_size, expected_nbytes; + uint8_t *raw_btf = NULL, *user_btf = NULL; + int btf_fd = -1, err; + + fprintf(stderr, "BTF GET_INFO_BY_ID test[%u] (%s): ", + test_num, test->descr); + + raw_btf = btf_raw_create(&hdr_tmpl, + test->raw_types, + test->str_sec, + test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + + user_btf = malloc(raw_btf_size); + if (!user_btf) { + fprintf(stderr, "Cannot allocate memory for user_btf\n"); + err = -1; + goto done; + } + + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + if (btf_fd == -1) { + fprintf(stderr, "bpf_load_btf:%s(%d)\n", + strerror(errno), errno); + err = -1; + goto done; + } + + user_btf_size = (int)raw_btf_size + test->info_size_delta; + expected_nbytes = min(raw_btf_size, user_btf_size); + if (raw_btf_size > expected_nbytes) + memset(user_btf + expected_nbytes, 0xff, + raw_btf_size - expected_nbytes); + + err = bpf_obj_get_info_by_fd(btf_fd, user_btf, &user_btf_size); + if (err || user_btf_size != raw_btf_size || + memcmp(raw_btf, user_btf, expected_nbytes)) { + fprintf(stderr, + "err:%d(errno:%d) raw_btf_size:%u user_btf_size:%u expected_nbytes:%u memcmp:%d\n", + err, errno, + raw_btf_size, user_btf_size, expected_nbytes, + memcmp(raw_btf, user_btf, expected_nbytes)); + err = -1; + goto done; + } + + while (expected_nbytes < raw_btf_size) { + fprintf(stderr, "%u...", expected_nbytes); + if (user_btf[expected_nbytes++] != 0xff) { + fprintf(stderr, "!= 0xff\n"); + err = -1; + goto done; + } + } + + fprintf(stderr, "OK\n"); + +done: + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "%s\n", btf_log_buf); + + free(raw_btf); + free(user_btf); + + if (btf_fd != -1) + close(btf_fd); + + return err; +} + +static int test_get_info(void) +{ + unsigned int i; + int err = 0; + + if (args.get_info_test_num) + return do_test_get_info(args.get_info_test_num); + + for (i = 1; i <= ARRAY_SIZE(get_info_tests); i++) + err |= do_test_get_info(i); + + return err; +} + +struct btf_file_test { + const char *file; + bool btf_kv_notfound; +}; + +static struct btf_file_test file_tests[] = { +{ + .file = "test_btf_haskv.o", +}, +{ + .file = "test_btf_nokv.o", + .btf_kv_notfound = true, +}, +}; + +static int file_has_btf_elf(const char *fn) +{ + Elf_Scn *scn = NULL; + GElf_Ehdr ehdr; + int elf_fd; + Elf *elf; + int ret; + + if (elf_version(EV_CURRENT) == EV_NONE) { + fprintf(stderr, "Failed to init libelf\n"); + return -1; + } + + elf_fd = open(fn, O_RDONLY); + if (elf_fd == -1) { + fprintf(stderr, "Cannot open file %s: %s(%d)\n", + fn, strerror(errno), errno); + return -1; + } + + elf = elf_begin(elf_fd, ELF_C_READ, NULL); + if (!elf) { + fprintf(stderr, "Failed to read ELF from %s. %s\n", fn, + elf_errmsg(elf_errno())); + ret = -1; + goto done; + } + + if (!gelf_getehdr(elf, &ehdr)) { + fprintf(stderr, "Failed to get EHDR from %s\n", fn); + ret = -1; + goto done; + } + + while ((scn = elf_nextscn(elf, scn))) { + const char *sh_name; + GElf_Shdr sh; + + if (gelf_getshdr(scn, &sh) != &sh) { + fprintf(stderr, + "Failed to get section header from %s\n", fn); + ret = -1; + goto done; + } + + sh_name = elf_strptr(elf, ehdr.e_shstrndx, sh.sh_name); + if (!strcmp(sh_name, BTF_ELF_SEC)) { + ret = 1; + goto done; + } + } + + ret = 0; + +done: + close(elf_fd); + elf_end(elf); + return ret; +} + +static int do_test_file(unsigned int test_num) +{ + const struct btf_file_test *test = &file_tests[test_num - 1]; + struct bpf_object *obj = NULL; + struct bpf_program *prog; + struct bpf_map *map; + int err; + + fprintf(stderr, "BTF libbpf test[%u] (%s): ", test_num, + test->file); + + err = file_has_btf_elf(test->file); + if (err == -1) + return err; + + if (err == 0) { + fprintf(stderr, "SKIP. No ELF %s found\n", BTF_ELF_SEC); + return 0; + } + + obj = bpf_object__open(test->file); + if (IS_ERR(obj)) + return PTR_ERR(obj); + + err = bpf_object__btf_fd(obj); + if (err == -1) { + fprintf(stderr, "bpf_object__btf_fd: -1\n"); + goto done; + } + + prog = bpf_program__next(NULL, obj); + if (!prog) { + fprintf(stderr, "Cannot find bpf_prog\n"); + err = -1; + goto done; + } + + bpf_program__set_type(prog, BPF_PROG_TYPE_TRACEPOINT); + err = bpf_object__load(obj); + if (err < 0) { + fprintf(stderr, "bpf_object__load: %d\n", err); + goto done; + } + + map = bpf_object__find_map_by_name(obj, "btf_map"); + if (!map) { + fprintf(stderr, "btf_map not found\n"); + err = -1; + goto done; + } + + err = (bpf_map__btf_key_id(map) == 0 || bpf_map__btf_value_id(map) == 0) + != test->btf_kv_notfound; + if (err) { + fprintf(stderr, + "btf_kv_notfound:%u btf_key_id:%u btf_value_id:%u\n", + test->btf_kv_notfound, + bpf_map__btf_key_id(map), + bpf_map__btf_value_id(map)); + goto done; + } + + fprintf(stderr, "OK\n"); + +done: + bpf_object__close(obj); + return err; +} + +static int test_file(void) +{ + unsigned int i; + int err = 0; + + if (args.file_test_num) + return do_test_file(args.file_test_num); + + for (i = 1; i <= ARRAY_SIZE(file_tests); i++) + err |= do_test_file(i); + + return err; +} + +const char *pprint_enum_str[] = { + "ENUM_ZERO", + "ENUM_ONE", + "ENUM_TWO", + "ENUM_THREE", +}; + +struct pprint_mapv { + uint32_t ui32; + uint16_t ui16; + /* 2 bytes hole */ + int32_t si32; + uint32_t unused_bits2a:2, + bits28:28, + unused_bits2b:2; + union { + uint64_t ui64; + uint8_t ui8a[8]; + }; + enum { + ENUM_ZERO, + ENUM_ONE, + ENUM_TWO, + ENUM_THREE, + } aenum; +}; + +static struct btf_raw_test pprint_test = { + .descr = "BTF pretty print test #1", + .raw_types = { + /* unsighed char */ /* [1] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 8, 1), + /* unsigned short */ /* [2] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 16, 2), + /* unsigned int */ /* [3] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 32, 4), + /* int */ /* [4] */ + BTF_TYPE_INT_ENC(NAME_TBD, BTF_INT_SIGNED, 0, 32, 4), + /* unsigned long long */ /* [5] */ + BTF_TYPE_INT_ENC(NAME_TBD, 0, 0, 64, 8), + /* 2 bits */ /* [6] */ + BTF_TYPE_INT_ENC(0, 0, 0, 2, 2), + /* 28 bits */ /* [7] */ + BTF_TYPE_INT_ENC(0, 0, 0, 28, 4), + /* uint8_t[8] */ /* [8] */ + BTF_TYPE_ARRAY_ENC(9, 3, 8), + /* typedef unsigned char uint8_t */ /* [9] */ + BTF_TYPEDEF_ENC(NAME_TBD, 1), + /* typedef unsigned short uint16_t */ /* [10] */ + BTF_TYPEDEF_ENC(NAME_TBD, 2), + /* typedef unsigned int uint32_t */ /* [11] */ + BTF_TYPEDEF_ENC(NAME_TBD, 3), + /* typedef int int32_t */ /* [12] */ + BTF_TYPEDEF_ENC(NAME_TBD, 4), + /* typedef unsigned long long uint64_t *//* [13] */ + BTF_TYPEDEF_ENC(NAME_TBD, 5), + /* union (anon) */ /* [14] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_UNION, 0, 2), 8), + BTF_MEMBER_ENC(NAME_TBD, 13, 0),/* uint64_t ui64; */ + BTF_MEMBER_ENC(NAME_TBD, 8, 0), /* uint8_t ui8a[8]; */ + /* enum (anon) */ /* [15] */ + BTF_TYPE_ENC(0, BTF_INFO_ENC(BTF_KIND_ENUM, 0, 4), 4), + BTF_ENUM_ENC(NAME_TBD, 0), + BTF_ENUM_ENC(NAME_TBD, 1), + BTF_ENUM_ENC(NAME_TBD, 2), + BTF_ENUM_ENC(NAME_TBD, 3), + /* struct pprint_mapv */ /* [16] */ + BTF_TYPE_ENC(NAME_TBD, BTF_INFO_ENC(BTF_KIND_STRUCT, 0, 8), 28), + BTF_MEMBER_ENC(NAME_TBD, 11, 0), /* uint32_t ui32 */ + BTF_MEMBER_ENC(NAME_TBD, 10, 32), /* uint16_t ui16 */ + BTF_MEMBER_ENC(NAME_TBD, 12, 64), /* int32_t si32 */ + BTF_MEMBER_ENC(NAME_TBD, 6, 96), /* unused_bits2a */ + BTF_MEMBER_ENC(NAME_TBD, 7, 98), /* bits28 */ + BTF_MEMBER_ENC(NAME_TBD, 6, 126), /* unused_bits2b */ + BTF_MEMBER_ENC(0, 14, 128), /* union (anon) */ + BTF_MEMBER_ENC(NAME_TBD, 15, 192), /* aenum */ + BTF_END_RAW, + }, + .str_sec = "\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum", + .str_sec_size = sizeof("\0unsigned char\0unsigned short\0unsigned int\0int\0unsigned long long\0uint8_t\0uint16_t\0uint32_t\0int32_t\0uint64_t\0ui64\0ui8a\0ENUM_ZERO\0ENUM_ONE\0ENUM_TWO\0ENUM_THREE\0pprint_mapv\0ui32\0ui16\0si32\0unused_bits2a\0bits28\0unused_bits2b\0aenum"), + .map_type = BPF_MAP_TYPE_ARRAY, + .map_name = "pprint_test", + .key_size = sizeof(unsigned int), + .value_size = sizeof(struct pprint_mapv), + .key_id = 3, /* unsigned int */ + .value_id = 16, /* struct pprint_mapv */ + .max_entries = 128 * 1024, +}; + +static void set_pprint_mapv(struct pprint_mapv *v, uint32_t i) +{ + v->ui32 = i; + v->si32 = -i; + v->unused_bits2a = 3; + v->bits28 = i; + v->unused_bits2b = 3; + v->ui64 = i; + v->aenum = i & 0x03; +} + +static int test_pprint(void) +{ + const struct btf_raw_test *test = &pprint_test; + struct bpf_create_map_attr create_attr = {}; + int map_fd = -1, btf_fd = -1; + struct pprint_mapv mapv = {}; + unsigned int raw_btf_size; + char expected_line[255]; + FILE *pin_file = NULL; + char pin_path[255]; + size_t line_len = 0; + char *line = NULL; + unsigned int key; + uint8_t *raw_btf; + ssize_t nread; + int err; + + fprintf(stderr, "%s......", test->descr); + raw_btf = btf_raw_create(&hdr_tmpl, test->raw_types, + test->str_sec, test->str_sec_size, + &raw_btf_size); + + if (!raw_btf) + return -1; + + *btf_log_buf = '\0'; + btf_fd = bpf_load_btf(raw_btf, raw_btf_size, + btf_log_buf, BTF_LOG_BUF_SIZE, + args.always_log); + free(raw_btf); + + if (btf_fd == -1) { + err = -1; + fprintf(stderr, "bpf_load_btf: %s(%d)\n", + strerror(errno), errno); + goto done; + } + + create_attr.name = test->map_name; + create_attr.map_type = test->map_type; + create_attr.key_size = test->key_size; + create_attr.value_size = test->value_size; + create_attr.max_entries = test->max_entries; + create_attr.btf_fd = btf_fd; + create_attr.btf_key_id = test->key_id; + create_attr.btf_value_id = test->value_id; + + map_fd = bpf_create_map_xattr(&create_attr); + if (map_fd == -1) { + err = -1; + fprintf(stderr, "bpf_creat_map_btf: %s(%d)\n", + strerror(errno), errno); + goto done; + } + + if (snprintf(pin_path, sizeof(pin_path), "%s/%s", + "/sys/fs/bpf", test->map_name) == sizeof(pin_path)) { + err = -1; + fprintf(stderr, "pin_path is too long\n"); + goto done; + } + + err = bpf_obj_pin(map_fd, pin_path); + if (err) { + fprintf(stderr, "Cannot pin to %s. %s(%d).\n", pin_path, + strerror(errno), errno); + goto done; + } + + for (key = 0; key < test->max_entries; key++) { + set_pprint_mapv(&mapv, key); + bpf_map_update_elem(map_fd, &key, &mapv, 0); + } + + pin_file = fopen(pin_path, "r"); + if (!pin_file) { + err = -1; + fprintf(stderr, "fopen(%s): %s(%d)\n", pin_path, + strerror(errno), errno); + goto done; + } + + /* Skip lines start with '#' */ + while ((nread = getline(&line, &line_len, pin_file)) > 0 && + *line == '#') + ; + + if (nread <= 0) { + err = -1; + fprintf(stderr, "Unexpected EOF\n"); + goto done; + } + + key = 0; + do { + ssize_t nexpected_line; + + set_pprint_mapv(&mapv, key); + nexpected_line = snprintf(expected_line, sizeof(expected_line), + "%u: {%u,0,%d,0x%x,0x%x,0x%x,{%lu|[%u,%u,%u,%u,%u,%u,%u,%u]},%s}\n", + key, + mapv.ui32, mapv.si32, + mapv.unused_bits2a, mapv.bits28, mapv.unused_bits2b, + mapv.ui64, + mapv.ui8a[0], mapv.ui8a[1], mapv.ui8a[2], mapv.ui8a[3], + mapv.ui8a[4], mapv.ui8a[5], mapv.ui8a[6], mapv.ui8a[7], + pprint_enum_str[mapv.aenum]); + + if (nexpected_line == sizeof(expected_line)) { + err = -1; + fprintf(stderr, "expected_line is too long\n"); + goto done; + } + + if (strcmp(expected_line, line)) { + err = -1; + fprintf(stderr, "unexpected pprint output\n"); + fprintf(stderr, "expected: %s", expected_line); + fprintf(stderr, " read: %s", line); + goto done; + } + + nread = getline(&line, &line_len, pin_file); + } while (++key < test->max_entries && nread > 0); + + if (key < test->max_entries) { + err = -1; + fprintf(stderr, "Unexpected EOF\n"); + goto done; + } + + if (nread > 0) { + err = -1; + fprintf(stderr, "Unexpected extra pprint output: %s\n", line); + goto done; + } + + err = 0; + +done: + if (!err) + fprintf(stderr, "OK\n"); + if (*btf_log_buf && (err || args.always_log)) + fprintf(stderr, "%s\n", btf_log_buf); + if (btf_fd != -1) + close(btf_fd); + if (map_fd != -1) + close(map_fd); + if (pin_file) + fclose(pin_file); + unlink(pin_path); + free(line); + + return err; +} + +static void usage(const char *cmd) +{ + fprintf(stderr, "Usage: %s [-l] [[-r test_num (1 - %zu)] | [-g test_num (1 - %zu)] | [-f test_num (1 - %zu)] | [-p]]\n", + cmd, ARRAY_SIZE(raw_tests), ARRAY_SIZE(get_info_tests), + ARRAY_SIZE(file_tests)); +} + +static int parse_args(int argc, char **argv) +{ + const char *optstr = "lpf:r:g:"; + int opt; + + while ((opt = getopt(argc, argv, optstr)) != -1) { + switch (opt) { + case 'l': + args.always_log = true; + break; + case 'f': + args.file_test_num = atoi(optarg); + args.file_test = true; + break; + case 'r': + args.raw_test_num = atoi(optarg); + args.raw_test = true; + break; + case 'g': + args.get_info_test_num = atoi(optarg); + args.get_info_test = true; + break; + case 'p': + args.pprint_test = true; + break; + case 'h': + usage(argv[0]); + exit(0); + default: + usage(argv[0]); + return -1; + } + } + + if (args.raw_test_num && + (args.raw_test_num < 1 || + args.raw_test_num > ARRAY_SIZE(raw_tests))) { + fprintf(stderr, "BTF raw test number must be [1 - %zu]\n", + ARRAY_SIZE(raw_tests)); + return -1; + } + + if (args.file_test_num && + (args.file_test_num < 1 || + args.file_test_num > ARRAY_SIZE(file_tests))) { + fprintf(stderr, "BTF file test number must be [1 - %zu]\n", + ARRAY_SIZE(file_tests)); + return -1; + } + + if (args.get_info_test_num && + (args.get_info_test_num < 1 || + args.get_info_test_num > ARRAY_SIZE(get_info_tests))) { + fprintf(stderr, "BTF get info test number must be [1 - %zu]\n", + ARRAY_SIZE(get_info_tests)); + return -1; + } + + return 0; +} + +int main(int argc, char **argv) +{ + int err = 0; + + err = parse_args(argc, argv); + if (err) + return err; + + if (args.always_log) + libbpf_set_print(__base_pr, __base_pr, __base_pr); + + if (args.raw_test) + err |= test_raw(); + + if (args.get_info_test) + err |= test_get_info(); + + if (args.file_test) + err |= test_file(); + + if (args.pprint_test) + err |= test_pprint(); + + if (args.raw_test || args.get_info_test || args.file_test || + args.pprint_test) + return err; + + err |= test_raw(); + err |= test_get_info(); + err |= test_file(); + + return err; +} diff --git a/tools/testing/selftests/bpf/test_btf_haskv.c b/tools/testing/selftests/bpf/test_btf_haskv.c new file mode 100644 index 000000000000..8c7ca096ecf2 --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf_haskv.c @@ -0,0 +1,48 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +typedef int btf_map_key; +typedef struct ipv_counts btf_map_value; +btf_map_key dumm_key; +btf_map_value dummy_value; + +struct bpf_map_def SEC("maps") btf_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct ipv_counts), + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_btf_nokv.c b/tools/testing/selftests/bpf/test_btf_nokv.c new file mode 100644 index 000000000000..0ed8e088eebf --- /dev/null +++ b/tools/testing/selftests/bpf/test_btf_nokv.c @@ -0,0 +1,43 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +/* Copyright (c) 2018 Facebook */ +#include <linux/bpf.h> +#include "bpf_helpers.h" + +int _version SEC("version") = 1; + +struct ipv_counts { + unsigned int v4; + unsigned int v6; +}; + +struct bpf_map_def SEC("maps") btf_map = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(struct ipv_counts), + .max_entries = 4, +}; + +struct dummy_tracepoint_args { + unsigned long long pad; + struct sock *sock; +}; + +SEC("dummy_tracepoint") +int _dummy_tracepoint(struct dummy_tracepoint_args *arg) +{ + struct ipv_counts *counts; + int key = 0; + + if (!arg->sock) + return 0; + + counts = bpf_map_lookup_elem(&btf_map, &key); + if (!counts) + return 0; + + counts->v6++; + + return 0; +} + +char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_get_stack_rawtp.c b/tools/testing/selftests/bpf/test_get_stack_rawtp.c new file mode 100644 index 000000000000..f6d9f238e00a --- /dev/null +++ b/tools/testing/selftests/bpf/test_get_stack_rawtp.c @@ -0,0 +1,102 @@ +// SPDX-License-Identifier: GPL-2.0 + +#include <linux/bpf.h> +#include "bpf_helpers.h" + +/* Permit pretty deep stack traces */ +#define MAX_STACK_RAWTP 100 +struct stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +struct bpf_map_def SEC("maps") perfmap = { + .type = BPF_MAP_TYPE_PERF_EVENT_ARRAY, + .key_size = sizeof(int), + .value_size = sizeof(__u32), + .max_entries = 2, +}; + +struct bpf_map_def SEC("maps") stackdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct stack_trace_t), + .max_entries = 1, +}; + +/* Allocate per-cpu space twice the needed. For the code below + * usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + * if (usize < 0) + * return 0; + * ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + * + * If we have value_size = MAX_STACK_RAWTP * sizeof(__u64), + * verifier will complain that access "raw_data + usize" + * with size "max_len - usize" may be out of bound. + * The maximum "raw_data + usize" is "raw_data + max_len" + * and the maximum "max_len - usize" is "max_len", verifier + * concludes that the maximum buffer access range is + * "raw_data[0...max_len * 2 - 1]" and hence reject the program. + * + * Doubling the to-be-used max buffer size can fix this verifier + * issue and avoid complicated C programming massaging. + * This is an acceptable workaround since there is one entry here. + */ +struct bpf_map_def SEC("maps") rawdata_map = { + .type = BPF_MAP_TYPE_PERCPU_ARRAY, + .key_size = sizeof(__u32), + .value_size = MAX_STACK_RAWTP * sizeof(__u64) * 2, + .max_entries = 1, +}; + +SEC("tracepoint/raw_syscalls/sys_enter") +int bpf_prog1(void *ctx) +{ + int max_len, max_buildid_len, usize, ksize, total_size; + struct stack_trace_t *data; + void *raw_data; + __u32 key = 0; + + data = bpf_map_lookup_elem(&stackdata_map, &key); + if (!data) + return 0; + + max_len = MAX_STACK_RAWTP * sizeof(__u64); + max_buildid_len = MAX_STACK_RAWTP * sizeof(struct bpf_stack_build_id); + data->pid = bpf_get_current_pid_tgid(); + data->kern_stack_size = bpf_get_stack(ctx, data->kern_stack, + max_len, 0); + data->user_stack_size = bpf_get_stack(ctx, data->user_stack, max_len, + BPF_F_USER_STACK); + data->user_stack_buildid_size = bpf_get_stack( + ctx, data->user_stack_buildid, max_buildid_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + bpf_perf_event_output(ctx, &perfmap, 0, data, sizeof(*data)); + + /* write both kernel and user stacks to the same buffer */ + raw_data = bpf_map_lookup_elem(&rawdata_map, &key); + if (!raw_data) + return 0; + + usize = bpf_get_stack(ctx, raw_data, max_len, BPF_F_USER_STACK); + if (usize < 0) + return 0; + + ksize = bpf_get_stack(ctx, raw_data + usize, max_len - usize, 0); + if (ksize < 0) + return 0; + + total_size = usize + ksize; + if (total_size > 0 && total_size <= max_len) + bpf_perf_event_output(ctx, &perfmap, 0, raw_data, total_size); + + return 0; +} + +char _license[] SEC("license") = "GPL"; +__u32 _version SEC("version") = 1; /* ignored by tracepoints, required by libbpf.a */ diff --git a/tools/testing/selftests/bpf/test_progs.c b/tools/testing/selftests/bpf/test_progs.c index 4123d0ab90ba..ed197eef1cfc 100644 --- a/tools/testing/selftests/bpf/test_progs.c +++ b/tools/testing/selftests/bpf/test_progs.c @@ -38,8 +38,10 @@ typedef __u16 __sum16; #include "bpf_util.h" #include "bpf_endian.h" #include "bpf_rlimit.h" +#include "trace_helpers.h" static int error_cnt, pass_cnt; +static bool jit_enabled; #define MAGIC_BYTES 123 @@ -166,6 +168,37 @@ out: bpf_object__close(obj); } +static void test_xdp_adjust_tail(void) +{ + const char *file = "./test_adjust_tail.o"; + struct bpf_object *obj; + char buf[128]; + __u32 duration, retval, size; + int err, prog_fd; + + err = bpf_prog_load(file, BPF_PROG_TYPE_XDP, &obj, &prog_fd); + if (err) { + error_cnt++; + return; + } + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v4, sizeof(pkt_v4), + buf, &size, &retval, &duration); + + CHECK(err || errno || retval != XDP_DROP, + "ipv4", "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + + err = bpf_prog_test_run(prog_fd, 1, &pkt_v6, sizeof(pkt_v6), + buf, &size, &retval, &duration); + CHECK(err || errno || retval != XDP_TX || size != 54, + "ipv6", "err %d errno %d retval %d size %d\n", + err, errno, retval, size); + bpf_object__close(obj); +} + + + #define MAGIC_VAL 0x1234 #define NUM_ITER 100000 #define VIP_NUM 5 @@ -360,13 +393,30 @@ static inline __u64 ptr_to_u64(const void *ptr) return (__u64) (unsigned long) ptr; } +static bool is_jit_enabled(void) +{ + const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; + bool enabled = false; + int sysctl_fd; + + sysctl_fd = open(jit_sysctl, 0, O_RDONLY); + if (sysctl_fd != -1) { + char tmpc; + + if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) + enabled = (tmpc != '0'); + close(sysctl_fd); + } + + return enabled; +} + static void test_bpf_obj_id(void) { const __u64 array_magic_value = 0xfaceb00c; const __u32 array_key = 0; const int nr_iters = 2; const char *file = "./test_obj_id.o"; - const char *jit_sysctl = "/proc/sys/net/core/bpf_jit_enable"; const char *expected_prog_name = "test_obj_id"; const char *expected_map_name = "test_map_id"; const __u64 nsec_per_sec = 1000000000; @@ -383,20 +433,11 @@ static void test_bpf_obj_id(void) char jited_insns[128], xlated_insns[128], zeros[128]; __u32 i, next_id, info_len, nr_id_found, duration = 0; struct timespec real_time_ts, boot_time_ts; - int sysctl_fd, jit_enabled = 0, err = 0; + int err = 0; __u64 array_value; uid_t my_uid = getuid(); time_t now, load_time; - sysctl_fd = open(jit_sysctl, 0, O_RDONLY); - if (sysctl_fd != -1) { - char tmpc; - - if (read(sysctl_fd, &tmpc, sizeof(tmpc)) == 1) - jit_enabled = (tmpc != '0'); - close(sysctl_fd); - } - err = bpf_prog_get_fd_by_id(0); CHECK(err >= 0 || errno != ENOENT, "get-fd-by-notexist-prog-id", "err %d errno %d\n", err, errno); @@ -865,11 +906,47 @@ static int compare_map_keys(int map1_fd, int map2_fd) return 0; } +static int compare_stack_ips(int smap_fd, int amap_fd, int stack_trace_len) +{ + __u32 key, next_key, *cur_key_p, *next_key_p; + char *val_buf1, *val_buf2; + int i, err = 0; + + val_buf1 = malloc(stack_trace_len); + val_buf2 = malloc(stack_trace_len); + cur_key_p = NULL; + next_key_p = &key; + while (bpf_map_get_next_key(smap_fd, cur_key_p, next_key_p) == 0) { + err = bpf_map_lookup_elem(smap_fd, next_key_p, val_buf1); + if (err) + goto out; + err = bpf_map_lookup_elem(amap_fd, next_key_p, val_buf2); + if (err) + goto out; + for (i = 0; i < stack_trace_len; i++) { + if (val_buf1[i] != val_buf2[i]) { + err = -1; + goto out; + } + } + key = *next_key_p; + cur_key_p = &key; + next_key_p = &next_key; + } + if (errno != ENOENT) + err = -1; + +out: + free(val_buf1); + free(val_buf2); + return err; +} + static void test_stacktrace_map() { - int control_map_fd, stackid_hmap_fd, stackmap_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; const char *file = "./test_stacktrace_map.o"; - int bytes, efd, err, pmu_fd, prog_fd; + int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len; struct perf_event_attr attr = {}; __u32 key, val, duration = 0; struct bpf_object *obj; @@ -925,6 +1002,10 @@ static void test_stacktrace_map() if (stackmap_fd < 0) goto disable_pmu; + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (stack_amap_fd < 0) + goto disable_pmu; + /* give some time for bpf program run */ sleep(1); @@ -946,6 +1027,12 @@ static void test_stacktrace_map() "err %d errno %d\n", err, errno)) goto disable_pmu_noerr; + stack_trace_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + if (CHECK(err, "compare_stack_ips stackmap vs. stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu_noerr; + goto disable_pmu_noerr; disable_pmu: error_cnt++; @@ -1039,9 +1126,9 @@ err: static void test_stacktrace_build_id(void) { - int control_map_fd, stackid_hmap_fd, stackmap_fd; + int control_map_fd, stackid_hmap_fd, stackmap_fd, stack_amap_fd; const char *file = "./test_stacktrace_build_id.o"; - int bytes, efd, err, pmu_fd, prog_fd; + int bytes, efd, err, pmu_fd, prog_fd, stack_trace_len; struct perf_event_attr attr = {}; __u32 key, previous_key, val, duration = 0; struct bpf_object *obj; @@ -1106,6 +1193,11 @@ static void test_stacktrace_build_id(void) err, errno)) goto disable_pmu; + stack_amap_fd = bpf_find_map(__func__, obj, "stack_amap"); + if (CHECK(stack_amap_fd < 0, "bpf_find_map stack_amap", + "err %d errno %d\n", err, errno)) + goto disable_pmu; + assert(system("dd if=/dev/urandom of=/dev/zero count=4 2> /dev/null") == 0); assert(system("./urandom_read") == 0); @@ -1157,8 +1249,15 @@ static void test_stacktrace_build_id(void) previous_key = key; } while (bpf_map_get_next_key(stackmap_fd, &previous_key, &key) == 0); - CHECK(build_id_matches < 1, "build id match", - "Didn't find expected build ID from the map\n"); + if (CHECK(build_id_matches < 1, "build id match", + "Didn't find expected build ID from the map\n")) + goto disable_pmu; + + stack_trace_len = PERF_MAX_STACK_DEPTH + * sizeof(struct bpf_stack_build_id); + err = compare_stack_ips(stackmap_fd, stack_amap_fd, stack_trace_len); + CHECK(err, "compare_stack_ips stackmap vs. stack_amap", + "err %d errno %d\n", err, errno); disable_pmu: ioctl(pmu_fd, PERF_EVENT_IOC_DISABLE); @@ -1173,10 +1272,150 @@ out: return; } +#define MAX_CNT_RAWTP 10ull +#define MAX_STACK_RAWTP 100 +struct get_stack_trace_t { + int pid; + int kern_stack_size; + int user_stack_size; + int user_stack_buildid_size; + __u64 kern_stack[MAX_STACK_RAWTP]; + __u64 user_stack[MAX_STACK_RAWTP]; + struct bpf_stack_build_id user_stack_buildid[MAX_STACK_RAWTP]; +}; + +static int get_stack_print_output(void *data, int size) +{ + bool good_kern_stack = false, good_user_stack = false; + const char *nonjit_func = "___bpf_prog_run"; + struct get_stack_trace_t *e = data; + int i, num_stack; + static __u64 cnt; + struct ksym *ks; + + cnt++; + + if (size < sizeof(struct get_stack_trace_t)) { + __u64 *raw_data = data; + bool found = false; + + num_stack = size / sizeof(__u64); + /* If jit is enabled, we do not have a good way to + * verify the sanity of the kernel stack. So we + * just assume it is good if the stack is not empty. + * This could be improved in the future. + */ + if (jit_enabled) { + found = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(raw_data[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + found = true; + break; + } + } + } + if (found) { + good_kern_stack = true; + good_user_stack = true; + } + } else { + num_stack = e->kern_stack_size / sizeof(__u64); + if (jit_enabled) { + good_kern_stack = num_stack > 0; + } else { + for (i = 0; i < num_stack; i++) { + ks = ksym_search(e->kern_stack[i]); + if (strcmp(ks->name, nonjit_func) == 0) { + good_kern_stack = true; + break; + } + } + } + if (e->user_stack_size > 0 && e->user_stack_buildid_size > 0) + good_user_stack = true; + } + if (!good_kern_stack || !good_user_stack) + return PERF_EVENT_ERROR; + + if (cnt == MAX_CNT_RAWTP) + return PERF_EVENT_DONE; + + return PERF_EVENT_CONT; +} + +static void test_get_stack_raw_tp(void) +{ + const char *file = "./test_get_stack_rawtp.o"; + int i, efd, err, prog_fd, pmu_fd, perfmap_fd; + struct perf_event_attr attr = {}; + struct timespec tv = {0, 10}; + __u32 key = 0, duration = 0; + struct bpf_object *obj; + + err = bpf_prog_load(file, BPF_PROG_TYPE_RAW_TRACEPOINT, &obj, &prog_fd); + if (CHECK(err, "prog_load raw tp", "err %d errno %d\n", err, errno)) + return; + + efd = bpf_raw_tracepoint_open("sys_enter", prog_fd); + if (CHECK(efd < 0, "raw_tp_open", "err %d errno %d\n", efd, errno)) + goto close_prog; + + perfmap_fd = bpf_find_map(__func__, obj, "perfmap"); + if (CHECK(perfmap_fd < 0, "bpf_find_map", "err %d errno %d\n", + perfmap_fd, errno)) + goto close_prog; + + err = load_kallsyms(); + if (CHECK(err < 0, "load_kallsyms", "err %d errno %d\n", err, errno)) + goto close_prog; + + attr.sample_type = PERF_SAMPLE_RAW; + attr.type = PERF_TYPE_SOFTWARE; + attr.config = PERF_COUNT_SW_BPF_OUTPUT; + pmu_fd = syscall(__NR_perf_event_open, &attr, getpid()/*pid*/, -1/*cpu*/, + -1/*group_fd*/, 0); + if (CHECK(pmu_fd < 0, "perf_event_open", "err %d errno %d\n", pmu_fd, + errno)) + goto close_prog; + + err = bpf_map_update_elem(perfmap_fd, &key, &pmu_fd, BPF_ANY); + if (CHECK(err < 0, "bpf_map_update_elem", "err %d errno %d\n", err, + errno)) + goto close_prog; + + err = ioctl(pmu_fd, PERF_EVENT_IOC_ENABLE, 0); + if (CHECK(err < 0, "ioctl PERF_EVENT_IOC_ENABLE", "err %d errno %d\n", + err, errno)) + goto close_prog; + + err = perf_event_mmap(pmu_fd); + if (CHECK(err < 0, "perf_event_mmap", "err %d errno %d\n", err, errno)) + goto close_prog; + + /* trigger some syscall action */ + for (i = 0; i < MAX_CNT_RAWTP; i++) + nanosleep(&tv, NULL); + + err = perf_event_poller(pmu_fd, get_stack_print_output); + if (CHECK(err < 0, "perf_event_poller", "err %d errno %d\n", err, errno)) + goto close_prog; + + goto close_prog_noerr; +close_prog: + error_cnt++; +close_prog_noerr: + bpf_object__close(obj); +} + int main(void) { + jit_enabled = is_jit_enabled(); + test_pkt_access(); test_xdp(); + test_xdp_adjust_tail(); test_l4lb_all(); test_xdp_noinline(); test_tcp_estats(); @@ -1187,6 +1426,7 @@ int main(void) test_stacktrace_map(); test_stacktrace_build_id(); test_stacktrace_map_raw_tp(); + test_get_stack_raw_tp(); printf("Summary: %d PASSED, %d FAILED\n", pass_cnt, error_cnt); return error_cnt ? EXIT_FAILURE : EXIT_SUCCESS; diff --git a/samples/sockmap/sockmap_user.c b/tools/testing/selftests/bpf/test_sockmap.c index 6f2334912283..29c022d23f4e 100644 --- a/samples/sockmap/sockmap_user.c +++ b/tools/testing/selftests/bpf/test_sockmap.c @@ -1,14 +1,5 @@ -/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io #include <stdio.h> #include <stdlib.h> #include <sys/socket.h> @@ -25,6 +16,7 @@ #include <fcntl.h> #include <sys/wait.h> #include <time.h> +#include <sched.h> #include <sys/time.h> #include <sys/resource.h> @@ -41,19 +33,31 @@ #include <getopt.h> -#include "../bpf/bpf_load.h" -#include "../bpf/bpf_util.h" -#include "../bpf/libbpf.h" +#include <bpf/bpf.h> +#include <bpf/libbpf.h> + +#include "bpf_util.h" +#include "bpf_rlimit.h" +#include "cgroup_helpers.h" int running; -void running_handler(int a); +static void running_handler(int a); /* randomly selected ports for testing on lo */ #define S1_PORT 10000 #define S2_PORT 10001 +#define BPF_FILENAME "test_sockmap_kern.o" +#define CG_PATH "/sockmap" + /* global sockets */ int s1, s2, c1, c2, p1, p2; +int test_cnt; +int passed; +int failed; +int map_fd[8]; +struct bpf_map *maps[8]; +int prog_fd[11]; int txmsg_pass; int txmsg_noisy; @@ -107,7 +111,7 @@ static void usage(char *argv[]) printf("\n"); } -static int sockmap_init_sockets(void) +static int sockmap_init_sockets(int verbose) { int i, err, one = 1; struct sockaddr_in addr; @@ -207,9 +211,11 @@ static int sockmap_init_sockets(void) return errno; } - printf("connected sockets: c1 <-> p1, c2 <-> p2\n"); - printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n", - c1, s1, c2, s2); + if (verbose) { + printf("connected sockets: c1 <-> p1, c2 <-> p2\n"); + printf("cgroups binding: c1(%i) <-> s1(%i) - - - c2(%i) <-> s2(%i)\n", + c1, s1, c2, s2); + } return 0; } @@ -226,6 +232,9 @@ struct sockmap_options { bool sendpage; bool data_test; bool drop_expected; + int iov_count; + int iov_length; + int rate; }; static int msg_loop_sendpage(int fd, int iov_length, int cnt, @@ -324,17 +333,19 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, clock_gettime(CLOCK_MONOTONIC, &s->end); } else { int slct, recv, max_fd = fd; + int fd_flags = O_NONBLOCK; struct timeval timeout; float total_bytes; fd_set w; + fcntl(fd, fd_flags); total_bytes = (float)iov_count * (float)iov_length * (float)cnt; err = clock_gettime(CLOCK_MONOTONIC, &s->start); if (err < 0) perror("recv start time: "); while (s->bytes_recvd < total_bytes) { - timeout.tv_sec = 1; - timeout.tv_usec = 0; + timeout.tv_sec = 0; + timeout.tv_usec = 10; /* FD sets */ FD_ZERO(&w); @@ -346,7 +357,8 @@ static int msg_loop(int fd, int iov_count, int iov_length, int cnt, clock_gettime(CLOCK_MONOTONIC, &s->end); goto out_errno; } else if (!slct) { - fprintf(stderr, "unexpected timeout\n"); + if (opt->verbose) + fprintf(stderr, "unexpected timeout\n"); errno = -EIO; clock_gettime(CLOCK_MONOTONIC, &s->end); goto out_errno; @@ -409,12 +421,14 @@ static inline float recvdBps(struct msg_stats s) return s.bytes_recvd / (s.end.tv_sec - s.start.tv_sec); } -static int sendmsg_test(int iov_count, int iov_buf, int cnt, - struct sockmap_options *opt) +static int sendmsg_test(struct sockmap_options *opt) { float sent_Bps = 0, recvd_Bps = 0; int rx_fd, txpid, rxpid, err = 0; struct msg_stats s = {0}; + int iov_count = opt->iov_count; + int iov_buf = opt->iov_length; + int cnt = opt->rate; int status; errno = 0; @@ -433,7 +447,7 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt, iov_count = 1; err = msg_loop(rx_fd, iov_count, iov_buf, cnt, &s, false, opt); - if (err) + if (err && opt->verbose) fprintf(stderr, "msg_loop_rx: iov_count %i iov_buf %i cnt %i err %i\n", iov_count, iov_buf, cnt, err); @@ -443,10 +457,11 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt, sent_Bps = sentBps(s); recvd_Bps = recvdBps(s); } - fprintf(stdout, - "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n", - s.bytes_sent, sent_Bps, sent_Bps/giga, - s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + if (opt->verbose) + fprintf(stdout, + "rx_sendmsg: TX: %zuB %fB/s %fGB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); exit(1); } else if (rxpid == -1) { perror("msg_loop_rx: "); @@ -470,10 +485,11 @@ static int sendmsg_test(int iov_count, int iov_buf, int cnt, sent_Bps = sentBps(s); recvd_Bps = recvdBps(s); } - fprintf(stdout, - "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n", - s.bytes_sent, sent_Bps, sent_Bps/giga, - s.bytes_recvd, recvd_Bps, recvd_Bps/giga); + if (opt->verbose) + fprintf(stdout, + "tx_sendmsg: TX: %zuB %fB/s %f GB/s RX: %zuB %fB/s %fGB/s\n", + s.bytes_sent, sent_Bps, sent_Bps/giga, + s.bytes_recvd, recvd_Bps, recvd_Bps/giga); exit(1); } else if (txpid == -1) { perror("msg_loop_tx: "); @@ -568,102 +584,9 @@ enum { SENDPAGE, }; -int main(int argc, char **argv) +static int run_options(struct sockmap_options *options, int cg_fd, int test) { - int iov_count = 1, length = 1024, rate = 1, tx_prog_fd; - struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; - int opt, longindex, err, cg_fd = 0; - struct sockmap_options options = {0}; - int test = PING_PONG; - char filename[256]; - - while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", - long_options, &longindex)) != -1) { - switch (opt) { - case 's': - txmsg_start = atoi(optarg); - break; - case 'e': - txmsg_end = atoi(optarg); - break; - case 'a': - txmsg_apply = atoi(optarg); - break; - case 'k': - txmsg_cork = atoi(optarg); - break; - case 'c': - cg_fd = open(optarg, O_DIRECTORY, O_RDONLY); - if (cg_fd < 0) { - fprintf(stderr, - "ERROR: (%i) open cg path failed: %s\n", - cg_fd, optarg); - return cg_fd; - } - break; - case 'r': - rate = atoi(optarg); - break; - case 'v': - options.verbose = 1; - break; - case 'i': - iov_count = atoi(optarg); - break; - case 'l': - length = atoi(optarg); - break; - case 'd': - options.data_test = true; - break; - case 't': - if (strcmp(optarg, "ping") == 0) { - test = PING_PONG; - } else if (strcmp(optarg, "sendmsg") == 0) { - test = SENDMSG; - } else if (strcmp(optarg, "base") == 0) { - test = BASE; - } else if (strcmp(optarg, "base_sendpage") == 0) { - test = BASE_SENDPAGE; - } else if (strcmp(optarg, "sendpage") == 0) { - test = SENDPAGE; - } else { - usage(argv); - return -1; - } - break; - case 0: - break; - case 'h': - default: - usage(argv); - return -1; - } - } - - if (!cg_fd) { - fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n", - argv[0]); - return -1; - } - - if (setrlimit(RLIMIT_MEMLOCK, &r)) { - perror("setrlimit(RLIMIT_MEMLOCK)"); - return 1; - } - - snprintf(filename, sizeof(filename), "%s_kern.o", argv[0]); - - running = 1; - - /* catch SIGINT */ - signal(SIGINT, running_handler); - - if (load_bpf_file(filename)) { - fprintf(stderr, "load_bpf_file: (%s) %s\n", - filename, strerror(errno)); - return 1; - } + int i, key, next_key, err, tx_prog_fd = -1, zero = 0; /* If base test skip BPF setup */ if (test == BASE || test == BASE_SENDPAGE) @@ -673,8 +596,9 @@ int main(int argc, char **argv) err = bpf_prog_attach(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER, 0); if (err) { - fprintf(stderr, "ERROR: bpf_prog_attach (sockmap): %d (%s)\n", - err, strerror(errno)); + fprintf(stderr, + "ERROR: bpf_prog_attach (sockmap %i->%i): %d (%s)\n", + prog_fd[0], map_fd[0], err, strerror(errno)); return err; } @@ -695,7 +619,7 @@ int main(int argc, char **argv) } run: - err = sockmap_init_sockets(); + err = sockmap_init_sockets(options->verbose); if (err) { fprintf(stderr, "ERROR: test socket failed: %d\n", err); goto out; @@ -729,7 +653,7 @@ run: fprintf(stderr, "ERROR: bpf_prog_attach (txmsg): %d (%s)\n", err, strerror(errno)); - return err; + goto out; } err = bpf_map_update_elem(map_fd[1], &i, &c1, BPF_ANY); @@ -737,7 +661,7 @@ run: fprintf(stderr, "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", err, strerror(errno)); - return err; + goto out; } if (txmsg_redir || txmsg_redir_noisy) @@ -750,7 +674,7 @@ run: fprintf(stderr, "ERROR: bpf_map_update_elem (txmsg): %d (%s\n", err, strerror(errno)); - return err; + goto out; } if (txmsg_apply) { @@ -760,7 +684,7 @@ run: fprintf(stderr, "ERROR: bpf_map_update_elem (apply_bytes): %d (%s\n", err, strerror(errno)); - return err; + goto out; } } @@ -771,7 +695,7 @@ run: fprintf(stderr, "ERROR: bpf_map_update_elem (cork_bytes): %d (%s\n", err, strerror(errno)); - return err; + goto out; } } @@ -782,7 +706,7 @@ run: fprintf(stderr, "ERROR: bpf_map_update_elem (txmsg_start): %d (%s)\n", err, strerror(errno)); - return err; + goto out; } } @@ -794,7 +718,7 @@ run: fprintf(stderr, "ERROR: bpf_map_update_elem (txmsg_end): %d (%s)\n", err, strerror(errno)); - return err; + goto out; } } @@ -832,11 +756,13 @@ run: } if (txmsg_skb) { - int skb_fd = (test == SENDMSG || test == SENDPAGE) ? p2 : p1; + int skb_fd = (test == SENDMSG || test == SENDPAGE) ? + p2 : p1; int ingress = BPF_F_INGRESS; i = 0; - err = bpf_map_update_elem(map_fd[7], &i, &ingress, BPF_ANY); + err = bpf_map_update_elem(map_fd[7], + &i, &ingress, BPF_ANY); if (err) { fprintf(stderr, "ERROR: bpf_map_update_elem (txmsg_ingress): %d (%s)\n", @@ -844,7 +770,8 @@ run: } i = 3; - err = bpf_map_update_elem(map_fd[0], &i, &skb_fd, BPF_ANY); + err = bpf_map_update_elem(map_fd[0], + &i, &skb_fd, BPF_ANY); if (err) { fprintf(stderr, "ERROR: bpf_map_update_elem (c1 sockmap): %d (%s)\n", @@ -854,36 +781,679 @@ run: } if (txmsg_drop) - options.drop_expected = true; + options->drop_expected = true; if (test == PING_PONG) - err = forever_ping_pong(rate, &options); + err = forever_ping_pong(options->rate, options); else if (test == SENDMSG) { - options.base = false; - options.sendpage = false; - err = sendmsg_test(iov_count, length, rate, &options); + options->base = false; + options->sendpage = false; + err = sendmsg_test(options); } else if (test == SENDPAGE) { - options.base = false; - options.sendpage = true; - err = sendmsg_test(iov_count, length, rate, &options); + options->base = false; + options->sendpage = true; + err = sendmsg_test(options); } else if (test == BASE) { - options.base = true; - options.sendpage = false; - err = sendmsg_test(iov_count, length, rate, &options); + options->base = true; + options->sendpage = false; + err = sendmsg_test(options); } else if (test == BASE_SENDPAGE) { - options.base = true; - options.sendpage = true; - err = sendmsg_test(iov_count, length, rate, &options); + options->base = true; + options->sendpage = true; + err = sendmsg_test(options); } else fprintf(stderr, "unknown test\n"); out: + /* Detatch and zero all the maps */ bpf_prog_detach2(prog_fd[2], cg_fd, BPF_CGROUP_SOCK_OPS); + bpf_prog_detach2(prog_fd[0], map_fd[0], BPF_SK_SKB_STREAM_PARSER); + bpf_prog_detach2(prog_fd[1], map_fd[0], BPF_SK_SKB_STREAM_VERDICT); + if (tx_prog_fd >= 0) + bpf_prog_detach2(tx_prog_fd, map_fd[1], BPF_SK_MSG_VERDICT); + + for (i = 0; i < 8; i++) { + key = next_key = 0; + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + while (bpf_map_get_next_key(map_fd[i], &key, &next_key) == 0) { + bpf_map_update_elem(map_fd[i], &key, &zero, BPF_ANY); + key = next_key; + } + } + close(s1); close(s2); close(p1); close(p2); close(c1); close(c2); + return err; +} + +static char *test_to_str(int test) +{ + switch (test) { + case SENDMSG: + return "sendmsg"; + case SENDPAGE: + return "sendpage"; + } + return "unknown"; +} + +#define OPTSTRING 60 +static void test_options(char *options) +{ + memset(options, 0, OPTSTRING); + + if (txmsg_pass) + strncat(options, "pass,", OPTSTRING); + if (txmsg_noisy) + strncat(options, "pass_noisy,", OPTSTRING); + if (txmsg_redir) + strncat(options, "redir,", OPTSTRING); + if (txmsg_redir_noisy) + strncat(options, "redir_noisy,", OPTSTRING); + if (txmsg_drop) + strncat(options, "drop,", OPTSTRING); + if (txmsg_apply) + strncat(options, "apply,", OPTSTRING); + if (txmsg_cork) + strncat(options, "cork,", OPTSTRING); + if (txmsg_start) + strncat(options, "start,", OPTSTRING); + if (txmsg_end) + strncat(options, "end,", OPTSTRING); + if (txmsg_ingress) + strncat(options, "ingress,", OPTSTRING); + if (txmsg_skb) + strncat(options, "skb,", OPTSTRING); +} + +static int __test_exec(int cgrp, int test, struct sockmap_options *opt) +{ + char *options = calloc(60, sizeof(char)); + int err; + + if (test == SENDPAGE) + opt->sendpage = true; + else + opt->sendpage = false; + + if (txmsg_drop) + opt->drop_expected = true; + else + opt->drop_expected = false; + + test_options(options); + + fprintf(stdout, + "[TEST %i]: (%i, %i, %i, %s, %s): ", + test_cnt, opt->rate, opt->iov_count, opt->iov_length, + test_to_str(test), options); + fflush(stdout); + err = run_options(opt, cgrp, test); + fprintf(stdout, "%s\n", !err ? "PASS" : "FAILED"); + test_cnt++; + !err ? passed++ : failed++; + free(options); + return err; +} + +static int test_exec(int cgrp, struct sockmap_options *opt) +{ + int err = __test_exec(cgrp, SENDMSG, opt); + + if (err) + goto out; + + err = __test_exec(cgrp, SENDPAGE, opt); +out: + return err; +} + +static int test_loop(int cgrp) +{ + struct sockmap_options opt; + + int err, i, l, r; + + opt.verbose = 0; + opt.base = false; + opt.sendpage = false; + opt.data_test = false; + opt.drop_expected = false; + opt.iov_count = 0; + opt.iov_length = 0; + opt.rate = 0; + + r = 1; + for (i = 1; i < 100; i += 33) { + for (l = 1; l < 100; l += 33) { + opt.rate = r; + opt.iov_count = i; + opt.iov_length = l; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + } + sched_yield(); +out: + return err; +} + +static int test_txmsg(int cgrp) +{ + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_ingress = txmsg_skb = 0; + + txmsg_pass = 1; + err = test_loop(cgrp); + txmsg_pass = 0; + if (err) + goto out; + + txmsg_redir = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + if (err) + goto out; + + txmsg_drop = 1; + err = test_loop(cgrp); + txmsg_drop = 0; + if (err) + goto out; + + txmsg_redir = 1; + txmsg_ingress = 1; + err = test_loop(cgrp); + txmsg_redir = 0; + txmsg_ingress = 0; + if (err) + goto out; +out: + txmsg_pass = 0; + txmsg_redir = 0; + txmsg_drop = 0; + return err; +} + +static int test_send(struct sockmap_options *opt, int cgrp) +{ + int err; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1024; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1024; + opt->iov_count = 1; + opt->rate = 1; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 1; + opt->iov_count = 1; + opt->rate = 1024; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->iov_length = 256; + opt->iov_count = 1024; + opt->rate = 10; + err = test_exec(cgrp, opt); + if (err) + goto out; + + opt->rate = 100; + opt->iov_count = 1; + opt->iov_length = 5; + err = test_exec(cgrp, opt); + if (err) + goto out; +out: + sched_yield(); + return err; +} + +static int test_mixed(int cgrp) +{ + struct sockmap_options opt = {0}; + int err; + + txmsg_pass = txmsg_noisy = txmsg_redir_noisy = txmsg_drop = 0; + txmsg_apply = txmsg_cork = 0; + txmsg_start = txmsg_end = 0; + /* Test small and large iov_count values with pass/redir/apply/cork */ + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 1; + txmsg_redir = 0; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 0; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 0; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_apply = 1024; + txmsg_cork = 1024; + err = test_send(&opt, cgrp); + if (err) + goto out; + + txmsg_pass = 0; + txmsg_redir = 1; + txmsg_cork = 4096; + txmsg_apply = 4096; + err = test_send(&opt, cgrp); + if (err) + goto out; +out: + return err; +} + +static int test_start_end(int cgrp) +{ + struct sockmap_options opt = {0}; + int err, i; + + /* Test basic start/end with lots of iov_count and iov_lengths */ + txmsg_start = 1; + txmsg_end = 2; + err = test_txmsg(cgrp); + if (err) + goto out; + + /* Test start/end with cork */ + opt.rate = 16; + opt.iov_count = 1; + opt.iov_length = 100; + txmsg_cork = 1600; + + for (i = 99; i <= 1600; i += 500) { + txmsg_start = 0; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork but pull data in middle */ + for (i = 199; i <= 1600; i += 500) { + txmsg_start = 100; + txmsg_end = i; + err = test_exec(cgrp, &opt); + if (err) + goto out; + } + + /* Test start/end with cork pulling last sg entry */ + txmsg_start = 1500; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end pull of single byte in last page */ + txmsg_start = 1111; + txmsg_end = 1112; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end < start */ + txmsg_start = 1111; + txmsg_end = 0; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with end > data */ + txmsg_start = 0; + txmsg_end = 1601; + err = test_exec(cgrp, &opt); + if (err) + goto out; + + /* Test start/end with start > data */ + txmsg_start = 1601; + txmsg_end = 1600; + err = test_exec(cgrp, &opt); + +out: + txmsg_start = 0; + txmsg_end = 0; + sched_yield(); + return err; +} + +char *map_names[] = { + "sock_map", + "sock_map_txmsg", + "sock_map_redir", + "sock_apply_bytes", + "sock_cork_bytes", + "sock_pull_bytes", + "sock_redir_flags", + "sock_skb_opts", +}; + +int prog_attach_type[] = { + BPF_SK_SKB_STREAM_PARSER, + BPF_SK_SKB_STREAM_VERDICT, + BPF_CGROUP_SOCK_OPS, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, + BPF_SK_MSG_VERDICT, +}; + +int prog_type[] = { + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SK_SKB, + BPF_PROG_TYPE_SOCK_OPS, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, + BPF_PROG_TYPE_SK_MSG, +}; + +static int populate_progs(void) +{ + char *bpf_file = BPF_FILENAME; + struct bpf_program *prog; + struct bpf_object *obj; + int i = 0; + long err; + + obj = bpf_object__open(bpf_file); + err = libbpf_get_error(obj); + if (err) { + char err_buf[256]; + + libbpf_strerror(err, err_buf, sizeof(err_buf)); + printf("Unable to load eBPF objects in file '%s' : %s\n", + bpf_file, err_buf); + return -1; + } + + bpf_object__for_each_program(prog, obj) { + bpf_program__set_type(prog, prog_type[i]); + bpf_program__set_expected_attach_type(prog, + prog_attach_type[i]); + i++; + } + + i = bpf_object__load(obj); + i = 0; + bpf_object__for_each_program(prog, obj) { + prog_fd[i] = bpf_program__fd(prog); + i++; + } + + for (i = 0; i < sizeof(map_fd)/sizeof(int); i++) { + maps[i] = bpf_object__find_map_by_name(obj, map_names[i]); + map_fd[i] = bpf_map__fd(maps[i]); + if (map_fd[i] < 0) { + fprintf(stderr, "load_bpf_file: (%i) %s\n", + map_fd[i], strerror(errno)); + return -1; + } + } + + return 0; +} + +static int test_suite(void) +{ + int cg_fd, err; + + err = populate_progs(); + if (err < 0) { + fprintf(stderr, "ERROR: (%i) load bpf failed\n", err); + return err; + } + + if (setup_cgroup_environment()) { + fprintf(stderr, "ERROR: cgroup env failed\n"); + return -EINVAL; + } + + cg_fd = create_and_get_cgroup(CG_PATH); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + + /* Tests basic commands and APIs with range of iov values */ + txmsg_start = txmsg_end = 0; + err = test_txmsg(cg_fd); + if (err) + goto out; + + /* Tests interesting combinations of APIs used together */ + err = test_mixed(cg_fd); + if (err) + goto out; + + /* Tests pull_data API using start/end API */ + err = test_start_end(cg_fd); + if (err) + goto out; + +out: + printf("Summary: %i PASSED %i FAILED\n", passed, failed); + close(cg_fd); + return err; +} + +int main(int argc, char **argv) +{ + struct rlimit r = {10 * 1024 * 1024, RLIM_INFINITY}; + int iov_count = 1, length = 1024, rate = 1; + struct sockmap_options options = {0}; + int opt, longindex, err, cg_fd = 0; + char *bpf_file = BPF_FILENAME; + int test = PING_PONG; + + if (setrlimit(RLIMIT_MEMLOCK, &r)) { + perror("setrlimit(RLIMIT_MEMLOCK)"); + return 1; + } + + if (argc < 2) + return test_suite(); + + while ((opt = getopt_long(argc, argv, ":dhvc:r:i:l:t:", + long_options, &longindex)) != -1) { + switch (opt) { + case 's': + txmsg_start = atoi(optarg); + break; + case 'e': + txmsg_end = atoi(optarg); + break; + case 'a': + txmsg_apply = atoi(optarg); + break; + case 'k': + txmsg_cork = atoi(optarg); + break; + case 'c': + cg_fd = open(optarg, O_DIRECTORY, O_RDONLY); + if (cg_fd < 0) { + fprintf(stderr, + "ERROR: (%i) open cg path failed: %s\n", + cg_fd, optarg); + return cg_fd; + } + break; + case 'r': + rate = atoi(optarg); + break; + case 'v': + options.verbose = 1; + break; + case 'i': + iov_count = atoi(optarg); + break; + case 'l': + length = atoi(optarg); + break; + case 'd': + options.data_test = true; + break; + case 't': + if (strcmp(optarg, "ping") == 0) { + test = PING_PONG; + } else if (strcmp(optarg, "sendmsg") == 0) { + test = SENDMSG; + } else if (strcmp(optarg, "base") == 0) { + test = BASE; + } else if (strcmp(optarg, "base_sendpage") == 0) { + test = BASE_SENDPAGE; + } else if (strcmp(optarg, "sendpage") == 0) { + test = SENDPAGE; + } else { + usage(argv); + return -1; + } + break; + case 0: + break; + case 'h': + default: + usage(argv); + return -1; + } + } + + if (!cg_fd) { + fprintf(stderr, "%s requires cgroup option: --cgroup <path>\n", + argv[0]); + return -1; + } + + err = populate_progs(); + if (err) { + fprintf(stderr, "populate program: (%s) %s\n", + bpf_file, strerror(errno)); + return 1; + } + running = 1; + + /* catch SIGINT */ + signal(SIGINT, running_handler); + + options.iov_count = iov_count; + options.iov_length = length; + options.rate = rate; + + err = run_options(&options, cg_fd, test); close(cg_fd); return err; } diff --git a/samples/sockmap/sockmap_kern.c b/tools/testing/selftests/bpf/test_sockmap_kern.c index 9ff8bc5dc206..33de97e2b6b6 100644 --- a/samples/sockmap/sockmap_kern.c +++ b/tools/testing/selftests/bpf/test_sockmap_kern.c @@ -1,20 +1,19 @@ -/* Copyright (c) 2017 Covalent IO, Inc. http://covalent.io - * - * This program is free software; you can redistribute it and/or - * modify it under the terms of version 2 of the GNU General Public - * License as published by the Free Software Foundation. - * - * This program is distributed in the hope that it will be useful, but - * WITHOUT ANY WARRANTY; without even the implied warranty of - * MERCHANTABILITY or FITNESS FOR A PARTICULAR PURPOSE. See the GNU - * General Public License for more details. - */ -#include <uapi/linux/bpf.h> -#include <uapi/linux/if_ether.h> -#include <uapi/linux/if_packet.h> -#include <uapi/linux/ip.h> -#include "../../tools/testing/selftests/bpf/bpf_helpers.h" -#include "../../tools/testing/selftests/bpf/bpf_endian.h" +// SPDX-License-Identifier: GPL-2.0 +// Copyright (c) 2017-2018 Covalent IO, Inc. http://covalent.io +#include <stddef.h> +#include <string.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/in.h> +#include <linux/udp.h> +#include <linux/tcp.h> +#include <linux/pkt_cls.h> +#include <sys/socket.h> +#include "bpf_helpers.h" +#include "bpf_endian.h" /* Sockmap sample program connects a client and a backend together * using cgroups. @@ -337,5 +336,5 @@ int bpf_prog10(struct sk_msg_md *msg) return SK_DROP; } - +int _version SEC("version") = 1; char _license[] SEC("license") = "GPL"; diff --git a/tools/testing/selftests/bpf/test_stacktrace_build_id.c b/tools/testing/selftests/bpf/test_stacktrace_build_id.c index b755bd783ce5..d86c281e957f 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_build_id.c +++ b/tools/testing/selftests/bpf/test_stacktrace_build_id.c @@ -19,7 +19,7 @@ struct bpf_map_def SEC("maps") stackid_hmap = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 10000, + .max_entries = 16384, }; struct bpf_map_def SEC("maps") stackmap = { @@ -31,6 +31,14 @@ struct bpf_map_def SEC("maps") stackmap = { .map_flags = BPF_F_STACK_BUILD_ID, }; +struct bpf_map_def SEC("maps") stack_amap = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(struct bpf_stack_build_id) + * PERF_MAX_STACK_DEPTH, + .max_entries = 128, +}; + /* taken from /sys/kernel/debug/tracing/events/random/urandom_read/format */ struct random_urandom_args { unsigned long long pad; @@ -42,7 +50,10 @@ struct random_urandom_args { SEC("tracepoint/random/urandom_read") int oncpu(struct random_urandom_args *args) { + __u32 max_len = sizeof(struct bpf_stack_build_id) + * PERF_MAX_STACK_DEPTH; __u32 key = 0, val = 0, *value_p; + void *stack_p; value_p = bpf_map_lookup_elem(&control_map, &key); if (value_p && *value_p) @@ -50,8 +61,13 @@ int oncpu(struct random_urandom_args *args) /* The size of stackmap and stackid_hmap should be the same */ key = bpf_get_stackid(args, &stackmap, BPF_F_USER_STACK); - if ((int)key >= 0) + if ((int)key >= 0) { bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(args, stack_p, max_len, + BPF_F_USER_STACK | BPF_F_USER_BUILD_ID); + } return 0; } diff --git a/tools/testing/selftests/bpf/test_stacktrace_map.c b/tools/testing/selftests/bpf/test_stacktrace_map.c index 76d85c5d08bd..af111af7ca1a 100644 --- a/tools/testing/selftests/bpf/test_stacktrace_map.c +++ b/tools/testing/selftests/bpf/test_stacktrace_map.c @@ -19,14 +19,21 @@ struct bpf_map_def SEC("maps") stackid_hmap = { .type = BPF_MAP_TYPE_HASH, .key_size = sizeof(__u32), .value_size = sizeof(__u32), - .max_entries = 10000, + .max_entries = 16384, }; struct bpf_map_def SEC("maps") stackmap = { .type = BPF_MAP_TYPE_STACK_TRACE, .key_size = sizeof(__u32), .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, - .max_entries = 10000, + .max_entries = 16384, +}; + +struct bpf_map_def SEC("maps") stack_amap = { + .type = BPF_MAP_TYPE_ARRAY, + .key_size = sizeof(__u32), + .value_size = sizeof(__u64) * PERF_MAX_STACK_DEPTH, + .max_entries = 16384, }; /* taken from /sys/kernel/debug/tracing/events/sched/sched_switch/format */ @@ -44,7 +51,9 @@ struct sched_switch_args { SEC("tracepoint/sched/sched_switch") int oncpu(struct sched_switch_args *ctx) { + __u32 max_len = PERF_MAX_STACK_DEPTH * sizeof(__u64); __u32 key = 0, val = 0, *value_p; + void *stack_p; value_p = bpf_map_lookup_elem(&control_map, &key); if (value_p && *value_p) @@ -52,8 +61,12 @@ int oncpu(struct sched_switch_args *ctx) /* The size of stackmap and stackid_hmap should be the same */ key = bpf_get_stackid(ctx, &stackmap, 0); - if ((int)key >= 0) + if ((int)key >= 0) { bpf_map_update_elem(&stackid_hmap, &key, &val, 0); + stack_p = bpf_map_lookup_elem(&stack_amap, &key); + if (stack_p) + bpf_get_stack(ctx, stack_p, max_len, 0); + } return 0; } diff --git a/tools/testing/selftests/bpf/test_tunnel.sh b/tools/testing/selftests/bpf/test_tunnel.sh new file mode 100755 index 000000000000..aeb2901f21f4 --- /dev/null +++ b/tools/testing/selftests/bpf/test_tunnel.sh @@ -0,0 +1,729 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# End-to-end eBPF tunnel test suite +# The script tests BPF network tunnel implementation. +# +# Topology: +# --------- +# root namespace | at_ns0 namespace +# | +# ----------- | ----------- +# | tnl dev | | | tnl dev | (overlay network) +# ----------- | ----------- +# metadata-mode | native-mode +# with bpf | +# | +# ---------- | ---------- +# | veth1 | --------- | veth0 | (underlay network) +# ---------- peer ---------- +# +# +# Device Configuration +# -------------------- +# Root namespace with metadata-mode tunnel + BPF +# Device names and addresses: +# veth1 IP: 172.16.1.200, IPv6: 00::22 (underlay) +# tunnel dev <type>11, ex: gre11, IPv4: 10.1.1.200 (overlay) +# +# Namespace at_ns0 with native tunnel +# Device names and addresses: +# veth0 IPv4: 172.16.1.100, IPv6: 00::11 (underlay) +# tunnel dev <type>00, ex: gre00, IPv4: 10.1.1.100 (overlay) +# +# +# End-to-end ping packet flow +# --------------------------- +# Most of the tests start by namespace creation, device configuration, +# then ping the underlay and overlay network. When doing 'ping 10.1.1.100' +# from root namespace, the following operations happen: +# 1) Route lookup shows 10.1.1.100/24 belongs to tnl dev, fwd to tnl dev. +# 2) Tnl device's egress BPF program is triggered and set the tunnel metadata, +# with remote_ip=172.16.1.200 and others. +# 3) Outer tunnel header is prepended and route the packet to veth1's egress +# 4) veth0's ingress queue receive the tunneled packet at namespace at_ns0 +# 5) Tunnel protocol handler, ex: vxlan_rcv, decap the packet +# 6) Forward the packet to the overlay tnl dev + +PING_ARG="-c 3 -w 10 -q" +ret=0 +GREEN='\033[0;92m' +RED='\033[0;31m' +NC='\033[0m' # No Color + +config_device() +{ + ip netns add at_ns0 + ip link add veth0 type veth peer name veth1 + ip link set veth0 netns at_ns0 + ip netns exec at_ns0 ip addr add 172.16.1.100/24 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip link set dev veth1 up mtu 1500 + ip addr add dev veth1 172.16.1.200/24 +} + +add_gre_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE key 2 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6gretap_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq flowlabel 0xbcdef key 2 \ + local ::11 remote ::22 + + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip addr add dev $DEV_NS fc80::100/96 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip addr add dev $DEV fc80::200/24 + ip link set dev $DEV up +} + +add_erspan_tunnel() +{ + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local 172.16.1.100 remote 172.16.1.200 \ + erspan_ver 2 erspan_dir egress erspan_hwid 3 + fi + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6erspan_tunnel() +{ + + # assign ipv6 address + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + if [ "$1" == "v1" ]; then + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 1 erspan 123 + else + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE seq key 2 \ + local ::11 remote ::22 \ + erspan_ver 2 erspan_dir egress erspan_hwid 7 + fi + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_vxlan_tunnel() +{ + # Set static ARP entry here because iptables set-mark works + # on L3 packet, as a result not applying to ARP packets, + # causing errors at get_tunnel_{key/opt}. + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 4789 gbp remote 172.16.1.200 + ip netns exec at_ns0 \ + ip link set dev $DEV_NS address 52:54:00:d9:01:00 up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 arp -s 10.1.1.200 52:54:00:d9:02:00 + ip netns exec at_ns0 iptables -A OUTPUT -j MARK --set-mark 0x800FF + + # root namespace + ip link add dev $DEV type $TYPE external gbp dstport 4789 + ip link set dev $DEV address 52:54:00:d9:02:00 up + ip addr add dev $DEV 10.1.1.200/24 + arp -s 10.1.1.100 52:54:00:d9:01:00 +} + +add_ip6vxlan_tunnel() +{ + #ip netns exec at_ns0 ip -4 addr del 172.16.1.100 dev veth0 + ip netns exec at_ns0 ip -6 addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + #ip -4 addr del 172.16.1.200 dev veth1 + ip -6 addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 dstport 4789 \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external dstport 4789 + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_geneve_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + id 2 dstport 6081 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE dstport 6081 external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ip6geneve_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE id 22 \ + remote ::22 # geneve has no local option + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +add_ipip_tunnel() +{ + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local 172.16.1.100 remote 172.16.1.200 + ip netns exec at_ns0 ip link set dev $DEV_NS up + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + + # root namespace + ip link add dev $DEV type $TYPE external + ip link set dev $DEV up + ip addr add dev $DEV 10.1.1.200/24 +} + +add_ipip6tnl_tunnel() +{ + ip netns exec at_ns0 ip addr add ::11/96 dev veth0 + ip netns exec at_ns0 ip link set dev veth0 up + ip addr add dev veth1 ::22/96 + ip link set dev veth1 up + + # at_ns0 namespace + ip netns exec at_ns0 \ + ip link add dev $DEV_NS type $TYPE \ + local ::11 remote ::22 + ip netns exec at_ns0 ip addr add dev $DEV_NS 10.1.1.100/24 + ip netns exec at_ns0 ip link set dev $DEV_NS up + + # root namespace + ip link add dev $DEV type $TYPE external + ip addr add dev $DEV 10.1.1.200/24 + ip link set dev $DEV up +} + +test_gre() +{ + TYPE=gretap + DEV_NS=gretap00 + DEV=gretap11 + ret=0 + + check $TYPE + config_device + add_gre_tunnel + attach_bpf $DEV gre_set_tunnel gre_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gre() +{ + TYPE=ip6gre + DEV_NS=ip6gre00 + DEV=ip6gre11 + ret=0 + + check $TYPE + config_device + # reuse the ip6gretap function + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6gretap() +{ + TYPE=ip6gretap + DEV_NS=ip6gretap00 + DEV=ip6gretap11 + ret=0 + + check $TYPE + config_device + add_ip6gretap_tunnel + attach_bpf $DEV ip6gretap_set_tunnel ip6gretap_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # overlay: ipv4 over ipv6 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + ping $PING_ARG 10.1.1.100 + check_err $? + # overlay: ipv6 over ipv6 + ip netns exec at_ns0 ping6 $PING_ARG fc80::200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_erspan() +{ + TYPE=erspan + DEV_NS=erspan00 + DEV=erspan11 + ret=0 + + check $TYPE + config_device + add_erspan_tunnel $1 + attach_bpf $DEV erspan_set_tunnel erspan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6erspan() +{ + TYPE=ip6erspan + DEV_NS=ip6erspan00 + DEV=ip6erspan11 + ret=0 + + check $TYPE + config_device + add_ip6erspan_tunnel $1 + attach_bpf $DEV ip4ip6erspan_set_tunnel ip4ip6erspan_get_tunnel + ping6 $PING_ARG ::11 + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_vxlan() +{ + TYPE=vxlan + DEV_NS=vxlan00 + DEV=vxlan11 + ret=0 + + check $TYPE + config_device + add_vxlan_tunnel + attach_bpf $DEV vxlan_set_tunnel vxlan_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6vxlan() +{ + TYPE=vxlan + DEV_NS=ip6vxlan00 + DEV=ip6vxlan11 + ret=0 + + check $TYPE + config_device + add_ip6vxlan_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ip6vxlan_set_tunnel ip6vxlan_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_geneve() +{ + TYPE=geneve + DEV_NS=geneve00 + DEV=geneve11 + ret=0 + + check $TYPE + config_device + add_geneve_tunnel + attach_bpf $DEV geneve_set_tunnel geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ip6geneve() +{ + TYPE=geneve + DEV_NS=ip6geneve00 + DEV=ip6geneve11 + ret=0 + + check $TYPE + config_device + add_ip6geneve_tunnel + attach_bpf $DEV ip6geneve_set_tunnel ip6geneve_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: ip6$TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: ip6$TYPE"${NC} +} + +test_ipip() +{ + TYPE=ipip + DEV_NS=ipip00 + DEV=ipip11 + ret=0 + + check $TYPE + config_device + add_ipip_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip_set_tunnel ipip_get_tunnel + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +test_ipip6() +{ + TYPE=ip6tnl + DEV_NS=ipip6tnl00 + DEV=ipip6tnl11 + ret=0 + + check $TYPE + config_device + add_ipip6tnl_tunnel + ip link set dev veth1 mtu 1500 + attach_bpf $DEV ipip6_set_tunnel ipip6_get_tunnel + # underlay + ping6 $PING_ARG ::11 + # ip4 over ip6 + ping $PING_ARG 10.1.1.100 + check_err $? + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: $TYPE"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: $TYPE"${NC} +} + +setup_xfrm_tunnel() +{ + auth=0x$(printf '1%.0s' {1..40}) + enc=0x$(printf '2%.0s' {1..32}) + spi_in_to_out=0x1 + spi_out_to_in=0x2 + # at_ns0 namespace + # at_ns0 -> root + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir out \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip netns exec at_ns0 \ + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip netns exec at_ns0 \ + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir in \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip netns exec at_ns0 \ + ip addr add dev veth0 10.1.1.100/32 + ip netns exec at_ns0 \ + ip route add 10.1.1.200 dev veth0 via 172.16.1.200 \ + src 10.1.1.100 + + # root namespace + # at_ns0 -> root + ip xfrm state add src 172.16.1.100 dst 172.16.1.200 proto esp \ + spi $spi_in_to_out reqid 1 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.100/32 dst 10.1.1.200/32 dir in \ + tmpl src 172.16.1.100 dst 172.16.1.200 proto esp reqid 1 \ + mode tunnel + # root -> at_ns0 + ip xfrm state add src 172.16.1.200 dst 172.16.1.100 proto esp \ + spi $spi_out_to_in reqid 2 mode tunnel \ + auth-trunc 'hmac(sha1)' $auth 96 enc 'cbc(aes)' $enc + ip xfrm policy add src 10.1.1.200/32 dst 10.1.1.100/32 dir out \ + tmpl src 172.16.1.200 dst 172.16.1.100 proto esp reqid 2 \ + mode tunnel + # address & route + ip addr add dev veth1 10.1.1.200/32 + ip route add 10.1.1.100 dev veth1 via 172.16.1.100 src 10.1.1.200 +} + +test_xfrm_tunnel() +{ + config_device + #tcpdump -nei veth1 ip & + output=$(mktemp) + cat /sys/kernel/debug/tracing/trace_pipe | tee $output & + setup_xfrm_tunnel + tc qdisc add dev veth1 clsact + tc filter add dev veth1 proto ip ingress bpf da obj test_tunnel_kern.o \ + sec xfrm_get_state + ip netns exec at_ns0 ping $PING_ARG 10.1.1.200 + sleep 1 + grep "reqid 1" $output + check_err $? + grep "spi 0x1" $output + check_err $? + grep "remote ip 0xac100164" $output + check_err $? + cleanup + + if [ $ret -ne 0 ]; then + echo -e ${RED}"FAIL: xfrm tunnel"${NC} + return 1 + fi + echo -e ${GREEN}"PASS: xfrm tunnel"${NC} +} + +attach_bpf() +{ + DEV=$1 + SET=$2 + GET=$3 + tc qdisc add dev $DEV clsact + tc filter add dev $DEV egress bpf da obj test_tunnel_kern.o sec $SET + tc filter add dev $DEV ingress bpf da obj test_tunnel_kern.o sec $GET +} + +cleanup() +{ + ip netns delete at_ns0 2> /dev/null + ip link del veth1 2> /dev/null + ip link del ipip11 2> /dev/null + ip link del ipip6tnl11 2> /dev/null + ip link del gretap11 2> /dev/null + ip link del ip6gre11 2> /dev/null + ip link del ip6gretap11 2> /dev/null + ip link del vxlan11 2> /dev/null + ip link del ip6vxlan11 2> /dev/null + ip link del geneve11 2> /dev/null + ip link del ip6geneve11 2> /dev/null + ip link del erspan11 2> /dev/null + ip link del ip6erspan11 2> /dev/null +} + +cleanup_exit() +{ + echo "CATCH SIGKILL or SIGINT, cleanup and exit" + cleanup + exit 0 +} + +check() +{ + ip link help $1 2>&1 | grep -q "^Usage:" + if [ $? -ne 0 ];then + echo "SKIP $1: iproute2 not support" + cleanup + return 1 + fi +} + +enable_debug() +{ + echo 'file ip_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ip6_gre.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file vxlan.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file geneve.c +p' > /sys/kernel/debug/dynamic_debug/control + echo 'file ipip.c +p' > /sys/kernel/debug/dynamic_debug/control +} + +check_err() +{ + if [ $ret -eq 0 ]; then + ret=$1 + fi +} + +bpf_tunnel_test() +{ + echo "Testing GRE tunnel..." + test_gre + echo "Testing IP6GRE tunnel..." + test_ip6gre + echo "Testing IP6GRETAP tunnel..." + test_ip6gretap + echo "Testing ERSPAN tunnel..." + test_erspan v2 + echo "Testing IP6ERSPAN tunnel..." + test_ip6erspan v2 + echo "Testing VXLAN tunnel..." + test_vxlan + echo "Testing IP6VXLAN tunnel..." + test_ip6vxlan + echo "Testing GENEVE tunnel..." + test_geneve + echo "Testing IP6GENEVE tunnel..." + test_ip6geneve + echo "Testing IPIP tunnel..." + test_ipip + echo "Testing IPIP6 tunnel..." + test_ipip6 + echo "Testing IPSec tunnel..." + test_xfrm_tunnel +} + +trap cleanup 0 3 6 +trap cleanup_exit 2 9 + +cleanup +bpf_tunnel_test + +exit 0 diff --git a/samples/bpf/tcbpf2_kern.c b/tools/testing/selftests/bpf/test_tunnel_kern.c index 9a8db7bd6db4..504df69c83df 100644 --- a/samples/bpf/tcbpf2_kern.c +++ b/tools/testing/selftests/bpf/test_tunnel_kern.c @@ -1,3 +1,4 @@ +// SPDX-License-Identifier: GPL-2.0 /* Copyright (c) 2016 VMware * Copyright (c) 2016 Facebook * @@ -5,39 +6,41 @@ * modify it under the terms of version 2 of the GNU General Public * License as published by the Free Software Foundation. */ -#define KBUILD_MODNAME "foo" -#include <uapi/linux/bpf.h> -#include <uapi/linux/if_ether.h> -#include <uapi/linux/if_packet.h> -#include <uapi/linux/ip.h> -#include <uapi/linux/ipv6.h> -#include <uapi/linux/in.h> -#include <uapi/linux/tcp.h> -#include <uapi/linux/filter.h> -#include <uapi/linux/pkt_cls.h> -#include <uapi/linux/erspan.h> -#include <net/ipv6.h> +#include <stddef.h> +#include <string.h> +#include <arpa/inet.h> +#include <linux/bpf.h> +#include <linux/if_ether.h> +#include <linux/if_packet.h> +#include <linux/ip.h> +#include <linux/ipv6.h> +#include <linux/types.h> +#include <linux/tcp.h> +#include <linux/socket.h> +#include <linux/pkt_cls.h> +#include <linux/erspan.h> #include "bpf_helpers.h" #include "bpf_endian.h" -#define _htonl __builtin_bswap32 #define ERROR(ret) do {\ char fmt[] = "ERROR line:%d ret:%d\n";\ bpf_trace_printk(fmt, sizeof(fmt), __LINE__, ret); \ - } while(0) + } while (0) + +int _version SEC("version") = 1; struct geneve_opt { __be16 opt_class; - u8 type; - u8 length:5; - u8 r3:1; - u8 r2:1; - u8 r1:1; - u8 opt_data[8]; /* hard-coded to 8 byte */ + __u8 type; + __u8 length:5; + __u8 r3:1; + __u8 r2:1; + __u8 r1:1; + __u8 opt_data[8]; /* hard-coded to 8 byte */ }; struct vxlan_metadata { - u32 gbp; + __u32 gbp; }; SEC("gre_set_tunnel") @@ -86,7 +89,7 @@ int _ip6gretap_set_tunnel(struct __sk_buff *skb) int ret; __builtin_memset(&key, 0x0, sizeof(key)); - key.remote_ipv6[3] = _htonl(0x11); /* ::11 */ + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ key.tunnel_id = 2; key.tunnel_tos = 0; key.tunnel_ttl = 64; @@ -136,7 +139,8 @@ int _erspan_set_tunnel(struct __sk_buff *skb) key.tunnel_tos = 0; key.tunnel_ttl = 64; - ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX); + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; @@ -147,8 +151,8 @@ int _erspan_set_tunnel(struct __sk_buff *skb) md.version = 1; md.u.index = bpf_htonl(123); #else - u8 direction = 1; - u8 hwid = 7; + __u8 direction = 1; + __u8 hwid = 7; md.version = 2; md.u.md2.dir = direction; @@ -171,7 +175,7 @@ int _erspan_get_tunnel(struct __sk_buff *skb) char fmt[] = "key %d remote ip 0x%x erspan version %d\n"; struct bpf_tunnel_key key; struct erspan_metadata md; - u32 index; + __u32 index; int ret; ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), 0); @@ -214,7 +218,7 @@ int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb) int ret; __builtin_memset(&key, 0x0, sizeof(key)); - key.remote_ipv6[3] = _htonl(0x11); + key.remote_ipv6[3] = bpf_htonl(0x11); key.tunnel_id = 2; key.tunnel_tos = 0; key.tunnel_ttl = 64; @@ -229,11 +233,11 @@ int _ip4ip6erspan_set_tunnel(struct __sk_buff *skb) __builtin_memset(&md, 0, sizeof(md)); #ifdef ERSPAN_V1 - md.u.index = htonl(123); + md.u.index = bpf_htonl(123); md.version = 1; #else - u8 direction = 0; - u8 hwid = 17; + __u8 direction = 0; + __u8 hwid = 17; md.version = 2; md.u.md2.dir = direction; @@ -256,10 +260,11 @@ int _ip4ip6erspan_get_tunnel(struct __sk_buff *skb) char fmt[] = "ip6erspan get key %d remote ip6 ::%x erspan version %d\n"; struct bpf_tunnel_key key; struct erspan_metadata md; - u32 index; + __u32 index; int ret; - ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6); + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; @@ -304,7 +309,8 @@ int _vxlan_set_tunnel(struct __sk_buff *skb) key.tunnel_tos = 0; key.tunnel_ttl = 64; - ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX); + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; @@ -346,6 +352,48 @@ int _vxlan_get_tunnel(struct __sk_buff *skb) return TC_ACT_OK; } +SEC("ip6vxlan_set_tunnel") +int _ip6vxlan_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6vxlan_get_tunnel") +int _ip6vxlan_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip6 ::%x label %x\n"; + struct bpf_tunnel_key key; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv6[3], key.tunnel_label); + + return TC_ACT_OK; +} + SEC("geneve_set_tunnel") int _geneve_set_tunnel(struct __sk_buff *skb) { @@ -360,15 +408,16 @@ int _geneve_set_tunnel(struct __sk_buff *skb) key.tunnel_ttl = 64; __builtin_memset(&gopt, 0x0, sizeof(gopt)); - gopt.opt_class = 0x102; /* Open Virtual Networking (OVN) */ + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ gopt.type = 0x08; gopt.r1 = 0; gopt.r2 = 0; gopt.r3 = 0; gopt.length = 2; /* 4-byte multiple */ - *(int *) &gopt.opt_data = 0xdeadbeef; + *(int *) &gopt.opt_data = bpf_htonl(0xdeadbeef); - ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_ZERO_CSUM_TX); + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_ZERO_CSUM_TX); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; @@ -408,6 +457,71 @@ int _geneve_get_tunnel(struct __sk_buff *skb) return TC_ACT_OK; } +SEC("ip6geneve_set_tunnel") +int _ip6geneve_set_tunnel(struct __sk_buff *skb) +{ + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ + key.tunnel_id = 22; + key.tunnel_tos = 0; + key.tunnel_ttl = 64; + + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + __builtin_memset(&gopt, 0x0, sizeof(gopt)); + gopt.opt_class = bpf_htons(0x102); /* Open Virtual Networking (OVN) */ + gopt.type = 0x08; + gopt.r1 = 0; + gopt.r2 = 0; + gopt.r3 = 0; + gopt.length = 2; /* 4-byte multiple */ + *(int *) &gopt.opt_data = bpf_htonl(0xfeedbeef); + + ret = bpf_skb_set_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + return TC_ACT_OK; +} + +SEC("ip6geneve_get_tunnel") +int _ip6geneve_get_tunnel(struct __sk_buff *skb) +{ + char fmt[] = "key %d remote ip 0x%x geneve class 0x%x\n"; + struct bpf_tunnel_key key; + struct geneve_opt gopt; + int ret; + + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + ret = bpf_skb_get_tunnel_opt(skb, &gopt, sizeof(gopt)); + if (ret < 0) { + ERROR(ret); + return TC_ACT_SHOT; + } + + bpf_trace_printk(fmt, sizeof(fmt), + key.tunnel_id, key.remote_ipv4, gopt.opt_class); + + return TC_ACT_OK; +} + SEC("ipip_set_tunnel") int _ipip_set_tunnel(struct __sk_buff *skb) { @@ -431,9 +545,9 @@ int _ipip_set_tunnel(struct __sk_buff *skb) if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) return TC_ACT_SHOT; - if (tcp->dest == htons(5200)) + if (tcp->dest == bpf_htons(5200)) key.remote_ipv4 = 0xac100164; /* 172.16.1.100 */ - else if (tcp->dest == htons(5201)) + else if (tcp->dest == bpf_htons(5201)) key.remote_ipv4 = 0xac100165; /* 172.16.1.101 */ else return TC_ACT_SHOT; @@ -481,28 +595,12 @@ int _ipip6_set_tunnel(struct __sk_buff *skb) return TC_ACT_SHOT; } - key.remote_ipv6[0] = _htonl(0x2401db00); + __builtin_memset(&key, 0x0, sizeof(key)); + key.remote_ipv6[3] = bpf_htonl(0x11); /* ::11 */ key.tunnel_ttl = 64; - if (iph->protocol == IPPROTO_ICMP) { - key.remote_ipv6[3] = _htonl(1); - } else { - if (iph->protocol != IPPROTO_TCP || iph->ihl != 5) { - ERROR(iph->protocol); - return TC_ACT_SHOT; - } - - if (tcp->dest == htons(5200)) { - key.remote_ipv6[3] = _htonl(1); - } else if (tcp->dest == htons(5201)) { - key.remote_ipv6[3] = _htonl(2); - } else { - ERROR(tcp->dest); - return TC_ACT_SHOT; - } - } - - ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6); + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; @@ -518,14 +616,15 @@ int _ipip6_get_tunnel(struct __sk_buff *skb) struct bpf_tunnel_key key; char fmt[] = "remote ip6 %x::%x\n"; - ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6); + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; } - bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]), - _htonl(key.remote_ipv6[3])); + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); return TC_ACT_OK; } @@ -545,28 +644,29 @@ int _ip6ip6_set_tunnel(struct __sk_buff *skb) return TC_ACT_SHOT; } - key.remote_ipv6[0] = _htonl(0x2401db00); + key.remote_ipv6[0] = bpf_htonl(0x2401db00); key.tunnel_ttl = 64; - if (iph->nexthdr == NEXTHDR_ICMP) { - key.remote_ipv6[3] = _htonl(1); + if (iph->nexthdr == 58 /* NEXTHDR_ICMP */) { + key.remote_ipv6[3] = bpf_htonl(1); } else { - if (iph->nexthdr != NEXTHDR_TCP) { + if (iph->nexthdr != 6 /* NEXTHDR_TCP */) { ERROR(iph->nexthdr); return TC_ACT_SHOT; } - if (tcp->dest == htons(5200)) { - key.remote_ipv6[3] = _htonl(1); - } else if (tcp->dest == htons(5201)) { - key.remote_ipv6[3] = _htonl(2); + if (tcp->dest == bpf_htons(5200)) { + key.remote_ipv6[3] = bpf_htonl(1); + } else if (tcp->dest == bpf_htons(5201)) { + key.remote_ipv6[3] = bpf_htonl(2); } else { ERROR(tcp->dest); return TC_ACT_SHOT; } } - ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6); + ret = bpf_skb_set_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; @@ -582,14 +682,31 @@ int _ip6ip6_get_tunnel(struct __sk_buff *skb) struct bpf_tunnel_key key; char fmt[] = "remote ip6 %x::%x\n"; - ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), BPF_F_TUNINFO_IPV6); + ret = bpf_skb_get_tunnel_key(skb, &key, sizeof(key), + BPF_F_TUNINFO_IPV6); if (ret < 0) { ERROR(ret); return TC_ACT_SHOT; } - bpf_trace_printk(fmt, sizeof(fmt), _htonl(key.remote_ipv6[0]), - _htonl(key.remote_ipv6[3])); + bpf_trace_printk(fmt, sizeof(fmt), bpf_htonl(key.remote_ipv6[0]), + bpf_htonl(key.remote_ipv6[3])); + return TC_ACT_OK; +} + +SEC("xfrm_get_state") +int _xfrm_get_state(struct __sk_buff *skb) +{ + struct bpf_xfrm_state x; + char fmt[] = "reqid %d spi 0x%x remote ip 0x%x\n"; + int ret; + + ret = bpf_skb_get_xfrm_state(skb, 0, &x, sizeof(x), 0); + if (ret < 0) + return TC_ACT_OK; + + bpf_trace_printk(fmt, sizeof(fmt), x.reqid, bpf_ntohl(x.spi), + bpf_ntohl(x.remote_ipv4)); return TC_ACT_OK; } diff --git a/tools/testing/selftests/bpf/test_verifier.c b/tools/testing/selftests/bpf/test_verifier.c index 3e7718b1a9ae..275b4570b5b8 100644 --- a/tools/testing/selftests/bpf/test_verifier.c +++ b/tools/testing/selftests/bpf/test_verifier.c @@ -47,7 +47,7 @@ # define ARRAY_SIZE(x) (sizeof(x) / sizeof((x)[0])) #endif -#define MAX_INSNS 512 +#define MAX_INSNS BPF_MAXINSNS #define MAX_FIXUPS 8 #define MAX_NR_MAPS 4 #define POINTER_VALUE 0xcafe4all @@ -64,6 +64,7 @@ struct bpf_test { struct bpf_insn insns[MAX_INSNS]; int fixup_map1[MAX_FIXUPS]; int fixup_map2[MAX_FIXUPS]; + int fixup_map3[MAX_FIXUPS]; int fixup_prog[MAX_FIXUPS]; int fixup_map_in_map[MAX_FIXUPS]; const char *errstr; @@ -76,6 +77,8 @@ struct bpf_test { } result, result_unpriv; enum bpf_prog_type prog_type; uint8_t flags; + __u8 data[TEST_DATA_LEN]; + void (*fill_helper)(struct bpf_test *self); }; /* Note we want this to be 64 bit aligned so that the end of our array is @@ -88,6 +91,67 @@ struct test_val { int foo[MAX_ENTRIES]; }; +struct other_val { + long long foo; + long long bar; +}; + +static void bpf_fill_ld_abs_vlan_push_pop(struct bpf_test *self) +{ + /* test: {skb->data[0], vlan_push} x 68 + {skb->data[0], vlan_pop} x 68 */ +#define PUSH_CNT 51 + unsigned int len = BPF_MAXINSNS; + struct bpf_insn *insn = self->insns; + int i = 0, j, k = 0; + + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); +loop: + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + insn[i++] = BPF_MOV64_IMM(BPF_REG_2, 1); + insn[i++] = BPF_MOV64_IMM(BPF_REG_3, 2); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2); + i++; + } + + for (j = 0; j < PUSH_CNT; j++) { + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x34, len - i - 2); + i++; + insn[i++] = BPF_MOV64_REG(BPF_REG_1, BPF_REG_6); + insn[i++] = BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_pop), + insn[i] = BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, len - i - 2); + i++; + } + if (++k < 5) + goto loop; + + for (; i < len - 1; i++) + insn[i] = BPF_ALU32_IMM(BPF_MOV, BPF_REG_0, 0xbef); + insn[len - 1] = BPF_EXIT_INSN(); +} + +static void bpf_fill_jump_around_ld_abs(struct bpf_test *self) +{ + struct bpf_insn *insn = self->insns; + unsigned int len = BPF_MAXINSNS; + int i = 0; + + insn[i++] = BPF_MOV64_REG(BPF_REG_6, BPF_REG_1); + insn[i++] = BPF_LD_ABS(BPF_B, 0); + insn[i] = BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 10, len - i - 2); + i++; + while (i < len - 1) + insn[i++] = BPF_LD_ABS(BPF_B, 1); + insn[i] = BPF_EXIT_INSN(); +} + static struct bpf_test tests[] = { { "add+sub+mul", @@ -5594,6 +5658,257 @@ static struct bpf_test tests[] = { .prog_type = BPF_PROG_TYPE_TRACEPOINT, }, { + "map lookup helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 4), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 8 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map update helper access to map: wrong size", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_update_elem), + BPF_EXIT_INSN(), + }, + .fixup_map1 = { 3 }, + .fixup_map3 = { 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=8 off=0 size=16", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + offsetof(struct other_val, bar)), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, + sizeof(struct other_val) - 4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const imm): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 5), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -4), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 9 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + offsetof(struct other_val, bar)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 1", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, + sizeof(struct other_val) - 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=12 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via const reg): out-of-bound 2", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_3, -4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=-4 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable)", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar), 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): no max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 10 }, + .result = REJECT, + .errstr = "R2 unbounded memory access, make sure to bounds check any array access into a map", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "map helper access to adjusted map (via variable): wrong max check", + .insns = { + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_ST_MEM(BPF_DW, BPF_REG_2, 0, 0), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 7), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_0), + BPF_LDX_MEM(BPF_W, BPF_REG_3, BPF_REG_0, 0), + BPF_JMP_IMM(BPF_JGT, BPF_REG_3, + offsetof(struct other_val, bar) + 1, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_3), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_EMIT_CALL(BPF_FUNC_map_lookup_elem), + BPF_EXIT_INSN(), + }, + .fixup_map3 = { 3, 11 }, + .result = REJECT, + .errstr = "invalid access to map value, value_size=16 off=9 size=8", + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { "map element value is preserved across register spilling", .insns = { BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), @@ -11423,6 +11738,242 @@ static struct bpf_test tests[] = { .errstr = "BPF_XADD stores into R2 packet", .prog_type = BPF_PROG_TYPE_XDP, }, + { + "bpf_get_stack return R0 within range", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_ST_MEM(BPF_DW, BPF_REG_10, -8, 0), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_10), + BPF_ALU64_IMM(BPF_ADD, BPF_REG_2, -8), + BPF_LD_MAP_FD(BPF_REG_1, 0), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_map_lookup_elem), + BPF_JMP_IMM(BPF_JEQ, BPF_REG_0, 0, 28), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_0), + BPF_MOV64_IMM(BPF_REG_9, sizeof(struct test_val)), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_3, sizeof(struct test_val)), + BPF_MOV64_IMM(BPF_REG_4, 256), + BPF_EMIT_CALL(BPF_FUNC_get_stack), + BPF_MOV64_IMM(BPF_REG_1, 0), + BPF_MOV64_REG(BPF_REG_8, BPF_REG_0), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_8, 32), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_8, 32), + BPF_JMP_REG(BPF_JSLT, BPF_REG_1, BPF_REG_8, 16), + BPF_ALU64_REG(BPF_SUB, BPF_REG_9, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_2, BPF_REG_7), + BPF_ALU64_REG(BPF_ADD, BPF_REG_2, BPF_REG_8), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_9), + BPF_ALU64_IMM(BPF_LSH, BPF_REG_1, 32), + BPF_ALU64_IMM(BPF_ARSH, BPF_REG_1, 32), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_2), + BPF_ALU64_REG(BPF_ADD, BPF_REG_3, BPF_REG_1), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_5, sizeof(struct test_val)), + BPF_ALU64_REG(BPF_ADD, BPF_REG_1, BPF_REG_5), + BPF_JMP_REG(BPF_JGE, BPF_REG_3, BPF_REG_1, 4), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_6), + BPF_MOV64_REG(BPF_REG_3, BPF_REG_9), + BPF_MOV64_IMM(BPF_REG_4, 0), + BPF_EMIT_CALL(BPF_FUNC_get_stack), + BPF_EXIT_INSN(), + }, + .fixup_map2 = { 4 }, + .result = ACCEPT, + .prog_type = BPF_PROG_TYPE_TRACEPOINT, + }, + { + "ld_abs: invalid op 1", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_DW, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "unknown opcode", + }, + { + "ld_abs: invalid op 2", + .insns = { + BPF_MOV32_IMM(BPF_REG_0, 256), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_IND(BPF_DW, BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = REJECT, + .errstr = "unknown opcode", + }, + { + "ld_abs: nmap reduced", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 28), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 26), + BPF_MOV32_IMM(BPF_REG_0, 18), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -64), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -64), + BPF_LD_IND(BPF_W, BPF_REG_7, 14), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -60), + BPF_MOV32_IMM(BPF_REG_0, 280971478), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -60), + BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 15), + BPF_LD_ABS(BPF_H, 12), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0x806, 13), + BPF_MOV32_IMM(BPF_REG_0, 22), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -56), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -56), + BPF_LD_IND(BPF_H, BPF_REG_7, 14), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -52), + BPF_MOV32_IMM(BPF_REG_0, 17366), + BPF_STX_MEM(BPF_W, BPF_REG_10, BPF_REG_0, -48), + BPF_LDX_MEM(BPF_W, BPF_REG_7, BPF_REG_10, -48), + BPF_LDX_MEM(BPF_W, BPF_REG_0, BPF_REG_10, -52), + BPF_ALU32_REG(BPF_SUB, BPF_REG_0, BPF_REG_7), + BPF_JMP_IMM(BPF_JNE, BPF_REG_0, 0, 2), + BPF_MOV32_IMM(BPF_REG_0, 256), + BPF_EXIT_INSN(), + BPF_MOV32_IMM(BPF_REG_0, 0), + BPF_EXIT_INSN(), + }, + .data = { + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0x08, 0x06, 0, + 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, 0, + 0x10, 0xbf, 0x48, 0xd6, 0x43, 0xd6, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 256, + }, + { + "ld_abs: div + abs, test 1", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0), + BPF_LD_ABS(BPF_B, 4), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0), + BPF_LD_IND(BPF_B, BPF_REG_8, -70), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 10, + }, + { + "ld_abs: div + abs, test 2", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_2, 2), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_2), + BPF_ALU64_REG(BPF_MOV, BPF_REG_8, BPF_REG_0), + BPF_LD_ABS(BPF_B, 128), + BPF_ALU64_REG(BPF_ADD, BPF_REG_8, BPF_REG_0), + BPF_LD_IND(BPF_B, BPF_REG_8, -70), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: div + abs, test 3", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_LD_ABS(BPF_B, 3), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: div + abs, test 4", + .insns = { + BPF_ALU64_REG(BPF_MOV, BPF_REG_6, BPF_REG_1), + BPF_ALU64_IMM(BPF_MOV, BPF_REG_7, 0), + BPF_LD_ABS(BPF_B, 256), + BPF_ALU32_REG(BPF_DIV, BPF_REG_0, BPF_REG_7), + BPF_EXIT_INSN(), + }, + .data = { + 10, 20, 30, 40, 50, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0, + }, + { + "ld_abs: vlan + abs, test 1", + .insns = { }, + .data = { + 0x34, + }, + .fill_helper = bpf_fill_ld_abs_vlan_push_pop, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 0xbef, + }, + { + "ld_abs: vlan + abs, test 2", + .insns = { + BPF_MOV64_REG(BPF_REG_6, BPF_REG_1), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_REG(BPF_REG_7, BPF_REG_6), + BPF_MOV64_IMM(BPF_REG_6, 0), + BPF_MOV64_REG(BPF_REG_1, BPF_REG_7), + BPF_MOV64_IMM(BPF_REG_2, 1), + BPF_MOV64_IMM(BPF_REG_3, 2), + BPF_RAW_INSN(BPF_JMP | BPF_CALL, 0, 0, 0, + BPF_FUNC_skb_vlan_push), + BPF_MOV64_REG(BPF_REG_6, BPF_REG_7), + BPF_LD_ABS(BPF_B, 0), + BPF_LD_ABS(BPF_H, 0), + BPF_LD_ABS(BPF_W, 0), + BPF_MOV64_IMM(BPF_REG_0, 42), + BPF_EXIT_INSN(), + }, + .data = { + 0x34, + }, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 42, + }, + { + "ld_abs: jump around ld_abs", + .insns = { }, + .data = { + 10, 11, + }, + .fill_helper = bpf_fill_jump_around_ld_abs, + .prog_type = BPF_PROG_TYPE_SCHED_CLS, + .result = ACCEPT, + .retval = 10, + }, }; static int probe_filter_length(const struct bpf_insn *fp) @@ -11526,16 +12077,20 @@ static int create_map_in_map(void) return outer_map_fd; } -static char bpf_vlog[32768]; +static char bpf_vlog[UINT_MAX >> 8]; static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, int *map_fds) { int *fixup_map1 = test->fixup_map1; int *fixup_map2 = test->fixup_map2; + int *fixup_map3 = test->fixup_map3; int *fixup_prog = test->fixup_prog; int *fixup_map_in_map = test->fixup_map_in_map; + if (test->fill_helper) + test->fill_helper(test); + /* Allocating HTs with 1 elem is fine here, since we only test * for verifier and not do a runtime lookup, so the only thing * that really matters is value size in this case. @@ -11556,6 +12111,14 @@ static void do_test_fixup(struct bpf_test *test, struct bpf_insn *prog, } while (*fixup_map2); } + if (*fixup_map3) { + map_fds[1] = create_map(sizeof(struct other_val), 1); + do { + prog[*fixup_map3].imm = map_fds[1]; + fixup_map3++; + } while (*fixup_map3); + } + if (*fixup_prog) { map_fds[2] = create_prog_array(); do { @@ -11577,10 +12140,8 @@ static void do_test_single(struct bpf_test *test, bool unpriv, int *passes, int *errors) { int fd_prog, expected_ret, reject_from_alignment; + int prog_len, prog_type = test->prog_type; struct bpf_insn *prog = test->insns; - int prog_len = probe_filter_length(prog); - char data_in[TEST_DATA_LEN] = {}; - int prog_type = test->prog_type; int map_fds[MAX_NR_MAPS]; const char *expected_err; uint32_t retval; @@ -11590,6 +12151,7 @@ static void do_test_single(struct bpf_test *test, bool unpriv, map_fds[i] = -1; do_test_fixup(test, prog, map_fds); + prog_len = probe_filter_length(prog); fd_prog = bpf_verify_program(prog_type ? : BPF_PROG_TYPE_SOCKET_FILTER, prog, prog_len, test->flags & F_LOAD_WITH_STRICT_ALIGNMENT, @@ -11629,8 +12191,9 @@ static void do_test_single(struct bpf_test *test, bool unpriv, } if (fd_prog >= 0) { - err = bpf_prog_test_run(fd_prog, 1, data_in, sizeof(data_in), - NULL, NULL, &retval, NULL); + err = bpf_prog_test_run(fd_prog, 1, test->data, + sizeof(test->data), NULL, NULL, + &retval, NULL); if (err && errno != 524/*ENOTSUPP*/ && errno != EPERM) { printf("Unexpected bpf_prog_test_run error\n"); goto fail_log; diff --git a/tools/testing/selftests/bpf/trace_helpers.c b/tools/testing/selftests/bpf/trace_helpers.c new file mode 100644 index 000000000000..ad025bd75f1c --- /dev/null +++ b/tools/testing/selftests/bpf/trace_helpers.c @@ -0,0 +1,180 @@ +// SPDX-License-Identifier: GPL-2.0 +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <assert.h> +#include <errno.h> +#include <poll.h> +#include <unistd.h> +#include <linux/perf_event.h> +#include <sys/mman.h> +#include "trace_helpers.h" + +#define MAX_SYMS 300000 +static struct ksym syms[MAX_SYMS]; +static int sym_cnt; + +static int ksym_cmp(const void *p1, const void *p2) +{ + return ((struct ksym *)p1)->addr - ((struct ksym *)p2)->addr; +} + +int load_kallsyms(void) +{ + FILE *f = fopen("/proc/kallsyms", "r"); + char func[256], buf[256]; + char symbol; + void *addr; + int i = 0; + + if (!f) + return -ENOENT; + + while (!feof(f)) { + if (!fgets(buf, sizeof(buf), f)) + break; + if (sscanf(buf, "%p %c %s", &addr, &symbol, func) != 3) + break; + if (!addr) + continue; + syms[i].addr = (long) addr; + syms[i].name = strdup(func); + i++; + } + sym_cnt = i; + qsort(syms, sym_cnt, sizeof(struct ksym), ksym_cmp); + return 0; +} + +struct ksym *ksym_search(long key) +{ + int start = 0, end = sym_cnt; + int result; + + while (start < end) { + size_t mid = start + (end - start) / 2; + + result = key - syms[mid].addr; + if (result < 0) + end = mid; + else if (result > 0) + start = mid + 1; + else + return &syms[mid]; + } + + if (start >= 1 && syms[start - 1].addr < key && + key < syms[start].addr) + /* valid ksym */ + return &syms[start - 1]; + + /* out of range. return _stext */ + return &syms[0]; +} + +static int page_size; +static int page_cnt = 8; +static volatile struct perf_event_mmap_page *header; + +int perf_event_mmap(int fd) +{ + void *base; + int mmap_size; + + page_size = getpagesize(); + mmap_size = page_size * (page_cnt + 1); + + base = mmap(NULL, mmap_size, PROT_READ | PROT_WRITE, MAP_SHARED, fd, 0); + if (base == MAP_FAILED) { + printf("mmap err\n"); + return -1; + } + + header = base; + return 0; +} + +static int perf_event_poll(int fd) +{ + struct pollfd pfd = { .fd = fd, .events = POLLIN }; + + return poll(&pfd, 1, 1000); +} + +struct perf_event_sample { + struct perf_event_header header; + __u32 size; + char data[]; +}; + +static int perf_event_read(perf_event_print_fn fn) +{ + __u64 data_tail = header->data_tail; + __u64 data_head = header->data_head; + __u64 buffer_size = page_cnt * page_size; + void *base, *begin, *end; + char buf[256]; + int ret; + + asm volatile("" ::: "memory"); /* in real code it should be smp_rmb() */ + if (data_head == data_tail) + return PERF_EVENT_CONT; + + base = ((char *)header) + page_size; + + begin = base + data_tail % buffer_size; + end = base + data_head % buffer_size; + + while (begin != end) { + struct perf_event_sample *e; + + e = begin; + if (begin + e->header.size > base + buffer_size) { + long len = base + buffer_size - begin; + + assert(len < e->header.size); + memcpy(buf, begin, len); + memcpy(buf + len, base, e->header.size - len); + e = (void *) buf; + begin = base + e->header.size - len; + } else if (begin + e->header.size == base + buffer_size) { + begin = base; + } else { + begin += e->header.size; + } + + if (e->header.type == PERF_RECORD_SAMPLE) { + ret = fn(e->data, e->size); + if (ret != PERF_EVENT_CONT) + return ret; + } else if (e->header.type == PERF_RECORD_LOST) { + struct { + struct perf_event_header header; + __u64 id; + __u64 lost; + } *lost = (void *) e; + printf("lost %lld events\n", lost->lost); + } else { + printf("unknown event type=%d size=%d\n", + e->header.type, e->header.size); + } + } + + __sync_synchronize(); /* smp_mb() */ + header->data_tail = data_head; + return PERF_EVENT_CONT; +} + +int perf_event_poller(int fd, perf_event_print_fn output_fn) +{ + int ret; + + for (;;) { + perf_event_poll(fd); + ret = perf_event_read(output_fn); + if (ret != PERF_EVENT_CONT) + return ret; + } + + return PERF_EVENT_DONE; +} diff --git a/tools/testing/selftests/bpf/trace_helpers.h b/tools/testing/selftests/bpf/trace_helpers.h new file mode 100644 index 000000000000..fe3eefd21e86 --- /dev/null +++ b/tools/testing/selftests/bpf/trace_helpers.h @@ -0,0 +1,23 @@ +/* SPDX-License-Identifier: GPL-2.0 */ +#ifndef __TRACE_HELPER_H +#define __TRACE_HELPER_H + +struct ksym { + long addr; + char *name; +}; + +int load_kallsyms(void); +struct ksym *ksym_search(long key); + +typedef int (*perf_event_print_fn)(void *data, int size); + +/* return code for perf_event_print_fn */ +#define PERF_EVENT_DONE 0 +#define PERF_EVENT_ERROR -1 +#define PERF_EVENT_CONT -2 + +int perf_event_mmap(int fd); +/* return PERF_EVENT_DONE or PERF_EVENT_ERROR */ +int perf_event_poller(int fd, perf_event_print_fn output_fn); +#endif diff --git a/tools/testing/selftests/net/.gitignore b/tools/testing/selftests/net/.gitignore index c612d6e38c62..f0e6c35a93ae 100644 --- a/tools/testing/selftests/net/.gitignore +++ b/tools/testing/selftests/net/.gitignore @@ -7,3 +7,7 @@ reuseport_bpf_cpu reuseport_bpf_numa reuseport_dualstack reuseaddr_conflict +tcp_mmap +udpgso +udpgso_bench_rx +udpgso_bench_tx diff --git a/tools/testing/selftests/net/Makefile b/tools/testing/selftests/net/Makefile index 3ff81a478dbe..e60dddbf963c 100644 --- a/tools/testing/selftests/net/Makefile +++ b/tools/testing/selftests/net/Makefile @@ -5,13 +5,18 @@ CFLAGS = -Wall -Wl,--no-as-needed -O2 -g CFLAGS += -I../../../../usr/include/ TEST_PROGS := run_netsocktests run_afpackettests test_bpf.sh netdevice.sh rtnetlink.sh -TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh +TEST_PROGS += fib_tests.sh fib-onlink-tests.sh pmtu.sh udpgso.sh +TEST_PROGS += udpgso_bench.sh TEST_PROGS_EXTENDED := in_netns.sh TEST_GEN_FILES = socket TEST_GEN_FILES += psock_fanout psock_tpacket msg_zerocopy +TEST_GEN_FILES += tcp_mmap tcp_inq +TEST_GEN_FILES += udpgso udpgso_bench_tx udpgso_bench_rx TEST_GEN_PROGS = reuseport_bpf reuseport_bpf_cpu reuseport_bpf_numa TEST_GEN_PROGS += reuseport_dualstack reuseaddr_conflict include ../lib.mk $(OUTPUT)/reuseport_bpf_numa: LDFLAGS += -lnuma +$(OUTPUT)/tcp_mmap: LDFLAGS += -lpthread +$(OUTPUT)/tcp_inq: LDFLAGS += -lpthread diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh index 75d922438bc9..d8313d0438b7 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_aware.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" NUM_NETIFS=4 CHECK_TC="yes" source lib.sh @@ -75,14 +76,31 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +learning() +{ + learning_test "br0" $swp1 $h1 $h2 +} + +flooding() +{ + flood_test $swp2 $h1 $h2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 192.0.2.2 -ping6_test $h1 2001:db8:1::2 -learning_test "br0" $swp1 $h1 $h2 -flood_test $swp2 $h1 $h2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh index 1cddf06f691d..c15c6c85c984 100755 --- a/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh +++ b/tools/testing/selftests/net/forwarding/bridge_vlan_unaware.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 learning flooding" NUM_NETIFS=4 source lib.sh @@ -73,14 +74,31 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 192.0.2.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:1::2 +} + +learning() +{ + learning_test "br0" $swp1 $h1 $h2 +} + +flooding() +{ + flood_test $swp2 $h1 $h2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 192.0.2.2 -ping6_test $h1 2001:db8:1::2 -learning_test "br0" $swp1 $h1 $h2 -flood_test $swp2 $h1 $h2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/lib.sh b/tools/testing/selftests/net/forwarding/lib.sh index 1ac6c62271f3..91041c49655b 100644 --- a/tools/testing/selftests/net/forwarding/lib.sh +++ b/tools/testing/selftests/net/forwarding/lib.sh @@ -321,6 +321,25 @@ simple_if_fini() vrf_destroy $vrf_name } +tunnel_create() +{ + local name=$1; shift + local type=$1; shift + local local=$1; shift + local remote=$1; shift + + ip link add name $name type $type \ + local $local remote $remote "$@" + ip link set dev $name up +} + +tunnel_destroy() +{ + local name=$1; shift + + ip link del dev $name +} + master_name_get() { local if_name=$1 @@ -335,6 +354,15 @@ link_stats_tx_packets_get() ip -j -s link show dev $if_name | jq '.[]["stats64"]["tx"]["packets"]' } +tc_rule_stats_get() +{ + local dev=$1; shift + local pref=$1; shift + + tc -j -s filter show dev $dev ingress pref $pref | + jq '.[1].options.actions[].stats.packets' +} + mac_get() { local if_name=$1 @@ -353,19 +381,33 @@ bridge_ageing_time_get() echo $((ageing_time / 100)) } -forwarding_enable() +declare -A SYSCTL_ORIG +sysctl_set() +{ + local key=$1; shift + local value=$1; shift + + SYSCTL_ORIG[$key]=$(sysctl -n $key) + sysctl -qw $key=$value +} + +sysctl_restore() { - ipv4_fwd=$(sysctl -n net.ipv4.conf.all.forwarding) - ipv6_fwd=$(sysctl -n net.ipv6.conf.all.forwarding) + local key=$1; shift - sysctl -q -w net.ipv4.conf.all.forwarding=1 - sysctl -q -w net.ipv6.conf.all.forwarding=1 + sysctl -qw $key=${SYSCTL_ORIG["$key"]} +} + +forwarding_enable() +{ + sysctl_set net.ipv4.conf.all.forwarding 1 + sysctl_set net.ipv6.conf.all.forwarding 1 } forwarding_restore() { - sysctl -q -w net.ipv6.conf.all.forwarding=$ipv6_fwd - sysctl -q -w net.ipv4.conf.all.forwarding=$ipv4_fwd + sysctl_restore net.ipv6.conf.all.forwarding + sysctl_restore net.ipv4.conf.all.forwarding } tc_offload_check() @@ -381,6 +423,83 @@ tc_offload_check() return 0 } +slow_path_trap_install() +{ + local dev=$1; shift + local direction=$1; shift + + if [ "${tcflags/skip_hw}" != "$tcflags" ]; then + # For slow-path testing, we need to install a trap to get to + # slow path the packets that would otherwise be switched in HW. + tc filter add dev $dev $direction pref 1 \ + flower skip_sw action trap + fi +} + +slow_path_trap_uninstall() +{ + local dev=$1; shift + local direction=$1; shift + + if [ "${tcflags/skip_hw}" != "$tcflags" ]; then + tc filter del dev $dev $direction pref 1 flower skip_sw + fi +} + +__icmp_capture_add_del() +{ + local add_del=$1; shift + local pref=$1; shift + local vsuf=$1; shift + local tundev=$1; shift + local filter=$1; shift + + tc filter $add_del dev "$tundev" ingress \ + proto ip$vsuf pref $pref \ + flower ip_proto icmp$vsuf $filter \ + action pass +} + +icmp_capture_install() +{ + __icmp_capture_add_del add 100 "" "$@" +} + +icmp_capture_uninstall() +{ + __icmp_capture_add_del del 100 "" "$@" +} + +icmp6_capture_install() +{ + __icmp_capture_add_del add 100 v6 "$@" +} + +icmp6_capture_uninstall() +{ + __icmp_capture_add_del del 100 v6 "$@" +} + +matchall_sink_create() +{ + local dev=$1; shift + + tc qdisc add dev $dev clsact + tc filter add dev $dev ingress \ + pref 10000 \ + matchall \ + action drop +} + +tests_run() +{ + local current_test + + for current_test in ${TESTS:-$ALL_TESTS}; do + $current_test + done +} + ############################################################################## # Tests diff --git a/tools/testing/selftests/net/forwarding/mirror_gre.sh b/tools/testing/selftests/net/forwarding/mirror_gre.sh new file mode 100755 index 000000000000..c6786d1b2b96 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre.sh @@ -0,0 +1,161 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for "tc action mirred egress mirror" when the device to mirror to is a +# gretap or ip6gretap netdevice. Expect that the packets come out encapsulated, +# and another gretap / ip6gretap netdevice is then capable of decapsulating the +# traffic. Test that the payload is what is expected (ICMP ping request or +# reply, depending on test). + +ALL_TESTS=" + test_gretap + test_ip6gretap + test_gretap_mac + test_ip6gretap_mac + test_two_spans +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_mac() +{ + local tundev=$1; shift + local direction=$1; shift + local prot=$1; shift + local what=$1; shift + + local swp3mac=$(mac_get $swp3) + local h3mac=$(mac_get $h3) + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + tc qdisc add dev $h3 clsact + tc filter add dev $h3 ingress pref 77 prot $prot \ + flower ip_proto 0x2f src_mac $swp3mac dst_mac $h3mac \ + action pass + + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + + tc filter del dev $h3 ingress pref 77 + tc qdisc del dev $h3 clsact + mirror_uninstall $swp1 $direction + + log_test "$direction $what: envelope MAC ($tcflags)" +} + +test_two_spans() +{ + RET=0 + + mirror_install $swp1 ingress gt4 "matchall $tcflags" + mirror_install $swp1 egress gt6 "matchall $tcflags" + quick_test_span_gre_dir gt4 ingress + quick_test_span_gre_dir gt6 egress + + mirror_uninstall $swp1 ingress + fail_test_span_gre_dir gt4 ingress + quick_test_span_gre_dir gt6 egress + + mirror_install $swp1 ingress gt4 "matchall $tcflags" + mirror_uninstall $swp1 egress + quick_test_span_gre_dir gt4 ingress + fail_test_span_gre_dir gt6 egress + + mirror_uninstall $swp1 ingress + log_test "two simultaneously configured mirrors ($tcflags)" +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap" +} + +test_gretap_mac() +{ + test_span_gre_mac gt4 ingress ip "mirror to gretap" + test_span_gre_mac gt4 egress ip "mirror to gretap" +} + +test_ip6gretap_mac() +{ + test_span_gre_mac gt6 ingress ipv6 "mirror to ip6gretap" + test_span_gre_mac gt6 egress ipv6 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh new file mode 100755 index 000000000000..360ca133bead --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_bound.sh @@ -0,0 +1,226 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | +---------------------------------------------------------------------+ | +# | | OL + gt6 (ip6gretap) + gt4 (gretap) | | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | | +# | | : ttl=100 : ttl=100 | | +# | | : tos=inherit : tos=inherit | | +# | +-------------------------:--|-------------------:--|-----------------+ | +# | : | : | | +# | +-------------------------:--|-------------------:--|-----------------+ | +# | | UL : |,---------------------' | | +# | | + $swp3 : || : | | +# | | | 192.0.2.129/28 : vv : | | +# | | | 2001:db8:2::1/64 : + ul (dummy) : | | +# | +---|---------------------:----------------------:--------------------+ | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | 192.0.2.130/28 loc=2001:db8:2::2 loc=192.0.2.130 | +# | 2001:db8:2::2/64 rem=2001:db8:2::1 rem=192.0.2.129 | +# | ttl=100 ttl=100 | +# | tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ +# +# This tests mirroring to gretap and ip6gretap configured in an overlay / +# underlay manner, i.e. with a bound dummy device that marks underlay VRF where +# the encapsulated packed should be routed. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh + +h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +h2_create() +{ + simple_if_init $h2 192.0.2.2/28 +} + +h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 +} + +h3_create() +{ + simple_if_init $h3 192.0.2.130/28 2001:db8:2::2/64 + + tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129 + ip link set h3-gt4 vrf v$h3 + matchall_sink_create h3-gt4 + + tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1 + ip link set h3-gt6 vrf v$h3 + matchall_sink_create h3-gt6 +} + +h3_destroy() +{ + tunnel_destroy h3-gt6 + tunnel_destroy h3-gt4 + + simple_if_fini $h3 192.0.2.130/28 2001:db8:2::2/64 +} + +switch_create() +{ + # Bridge between H1 and H2. + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tc qdisc add dev $swp1 clsact + + # Underlay. + + simple_if_init $swp3 192.0.2.129/28 2001:db8:2::1/64 + + ip link add name ul type dummy + ip link set dev ul master v$swp3 + ip link set dev ul up + + # Overlay. + + vrf_create vrf-ol + ip link set dev vrf-ol up + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit dev ul + ip link set dev gt4 master vrf-ol + ip link set dev gt4 up + + tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \ + ttl 100 tos inherit dev ul allow-localremote + ip link set dev gt6 master vrf-ol + ip link set dev gt6 up +} + +switch_destroy() +{ + vrf_destroy vrf-ol + + tunnel_destroy gt6 + tunnel_destroy gt4 + + simple_if_fini $swp3 192.0.2.129/28 2001:db8:2::1/64 + + ip link del dev ul + + tc qdisc del dev $swp1 clsact + + ip link set dev $swp1 down + ip link set dev $swp2 down + ip link del dev br1 +} + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + + h1_create + h2_create + h3_create + + switch_create +} + +cleanup() +{ + pre_cleanup + + switch_destroy + + h3_destroy + h2_destroy + h1_destroy + + vrf_cleanup +} + +test_gretap() +{ + full_test_span_gre_dir gt4 ingress 8 0 "mirror to gretap w/ UL" + full_test_span_gre_dir gt4 egress 0 8 "mirror to gretap w/ UL" +} + +test_ip6gretap() +{ + full_test_span_gre_dir gt6 ingress 8 0 "mirror to ip6gretap w/ UL" + full_test_span_gre_dir gt6 egress 0 8 "mirror to ip6gretap w/ UL" +} + +test_all() +{ + RET=0 + + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh new file mode 100755 index 000000000000..50ab3462af0c --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_changes.sh @@ -0,0 +1,212 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test how mirrors to gretap and ip6gretap react to changes to relevant +# configuration. + +ALL_TESTS=" + test_ttl + test_tun_up + test_egress_up + test_remote_ip +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + # This test downs $swp3, which deletes the configured IPv6 address + # unless this sysctl is set. + sysctl_set net.ipv6.conf.$swp3.keep_addr_on_down 1 + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + sysctl_restore net.ipv6.conf.$swp3.keep_addr_on_down + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_ttl() +{ + local tundev=$1; shift + local type=$1; shift + local prot=$1; shift + local what=$1; shift + + RET=0 + + mirror_install $swp1 ingress $tundev "matchall $tcflags" + tc qdisc add dev $h3 clsact + tc filter add dev $h3 ingress pref 77 prot $prot \ + flower ip_ttl 50 action pass + + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 0 + + ip link set dev $tundev type $type ttl 50 + mirror_test v$h1 192.0.2.1 192.0.2.2 $h3 77 10 + + ip link set dev $tundev type $type ttl 100 + tc filter del dev $h3 ingress pref 77 + tc qdisc del dev $h3 clsact + mirror_uninstall $swp1 ingress + + log_test "$what: TTL change ($tcflags)" +} + +test_span_gre_tun_up() +{ + local tundev=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $tundev down + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + ip link set dev $tundev up + + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: tunnel down/up ($tcflags)" +} + +test_span_gre_egress_up() +{ + local tundev=$1; shift + local remote_ip=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $swp3 down + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + # After setting the device up, wait for neighbor to get resolved so that + # we can expect mirroring to work. + ip link set dev $swp3 up + while true; do + ip neigh sh dev $swp3 $remote_ip nud reachable | + grep -q ^ + if [[ $? -ne 0 ]]; then + sleep 1 + else + break + fi + done + + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: egress down/up ($tcflags)" +} + +test_span_gre_remote_ip() +{ + local tundev=$1; shift + local type=$1; shift + local correct_ip=$1; shift + local wrong_ip=$1; shift + local what=$1; shift + + RET=0 + + ip link set dev $tundev type $type remote $wrong_ip + mirror_install $swp1 ingress $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + + ip link set dev $tundev type $type remote $correct_ip + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 ingress + + log_test "$what: remote address change ($tcflags)" +} + +test_ttl() +{ + test_span_gre_ttl gt4 gretap ip "mirror to gretap" + test_span_gre_ttl gt6 ip6gretap ipv6 "mirror to ip6gretap" +} + +test_tun_up() +{ + test_span_gre_tun_up gt4 "mirror to gretap" + test_span_gre_tun_up gt6 "mirror to ip6gretap" +} + +test_egress_up() +{ + test_span_gre_egress_up gt4 192.0.2.130 "mirror to gretap" + test_span_gre_egress_up gt6 2001:db8:2::2 "mirror to ip6gretap" +} + +test_remote_ip() +{ + test_span_gre_remote_ip gt4 gretap 192.0.2.130 192.0.2.132 "mirror to gretap" + test_span_gre_remote_ip gt6 ip6gretap 2001:db8:2::2 2001:db8:2::4 "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh new file mode 100755 index 000000000000..2e54407d8954 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_flower.sh @@ -0,0 +1,129 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# This tests flower-triggered mirroring to gretap and ip6gretap netdevices. The +# interfaces on H1 and H2 have two addresses each. Flower match on one of the +# addresses is configured with mirror action. It is expected that when pinging +# this address, mirroring takes place, whereas when pinging the other one, +# there's no mirroring. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 + + ip address add dev $h1 192.0.2.3/28 + ip address add dev $h2 192.0.2.4/28 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h2 192.0.2.4/28 + ip address del dev $h1 192.0.2.3/28 + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_dir_acl() +{ + test_span_gre_dir_ips "$@" 192.0.2.3 192.0.2.4 +} + +full_test_span_gre_dir_acl() +{ + local tundev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local match_dip=$1; shift + local what=$1; shift + + mirror_install $swp1 $direction $tundev \ + "protocol ip flower $tcflags dst_ip $match_dip" + fail_test_span_gre_dir $tundev $direction + test_span_gre_dir_acl "$tundev" "$direction" \ + "$forward_type" "$backward_type" + mirror_uninstall $swp1 $direction + + log_test "$direction $what ($tcflags)" +} + +test_gretap() +{ + full_test_span_gre_dir_acl gt4 ingress 8 0 192.0.2.4 "ACL mirror to gretap" + full_test_span_gre_dir_acl gt4 egress 0 8 192.0.2.3 "ACL mirror to gretap" +} + +test_ip6gretap() +{ + full_test_span_gre_dir_acl gt6 ingress 8 0 192.0.2.4 "ACL mirror to ip6gretap" + full_test_span_gre_dir_acl gt6 egress 0 8 192.0.2.3 "ACL mirror to ip6gretap" +} + +test_all() +{ + RET=0 + + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh new file mode 100644 index 000000000000..207ffd167dba --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_lib.sh @@ -0,0 +1,85 @@ +# SPDX-License-Identifier: GPL-2.0 + +do_test_span_gre_dir_ips() +{ + local expect=$1; shift + local tundev=$1; shift + local direction=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + icmp_capture_install h3-$tundev + mirror_test v$h1 $ip1 $ip2 h3-$tundev 100 $expect + mirror_test v$h2 $ip2 $ip1 h3-$tundev 100 $expect + icmp_capture_uninstall h3-$tundev +} + +quick_test_span_gre_dir_ips() +{ + do_test_span_gre_dir_ips 10 "$@" +} + +fail_test_span_gre_dir_ips() +{ + do_test_span_gre_dir_ips 0 "$@" +} + +test_span_gre_dir_ips() +{ + local tundev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + quick_test_span_gre_dir_ips "$tundev" "$direction" "$ip1" "$ip2" + + icmp_capture_install h3-$tundev "type $forward_type" + mirror_test v$h1 $ip1 $ip2 h3-$tundev 100 10 + icmp_capture_uninstall h3-$tundev + + icmp_capture_install h3-$tundev "type $backward_type" + mirror_test v$h2 $ip2 $ip1 h3-$tundev 100 10 + icmp_capture_uninstall h3-$tundev +} + +full_test_span_gre_dir_ips() +{ + local tundev=$1; shift + local direction=$1; shift + local forward_type=$1; shift + local backward_type=$1; shift + local what=$1; shift + local ip1=$1; shift + local ip2=$1; shift + + RET=0 + + mirror_install $swp1 $direction $tundev "matchall $tcflags" + test_span_gre_dir_ips "$tundev" "$direction" "$forward_type" \ + "$backward_type" "$ip1" "$ip2" + mirror_uninstall $swp1 $direction + + log_test "$direction $what ($tcflags)" +} + +quick_test_span_gre_dir() +{ + quick_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +fail_test_span_gre_dir() +{ + fail_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +test_span_gre_dir() +{ + test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} + +full_test_span_gre_dir() +{ + full_test_span_gre_dir_ips "$@" 192.0.2.1 192.0.2.2 +} diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh new file mode 100755 index 000000000000..fc0508e40fca --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_neigh.sh @@ -0,0 +1,115 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test for mirroring to gretap and ip6gretap, such that the neighbor entry for +# the tunnel remote address has invalid address at the time that the mirroring +# is set up. Later on, the neighbor is deleted and it is expected to be +# reinitialized using the usual ARP process, and the mirroring offload updated. + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.129/28 + ip address add dev $h3 192.0.2.130/28 + + ip address add dev $swp3 2001:db8:2::1/64 + ip address add dev $h3 2001:db8:2::2/64 +} + +cleanup() +{ + pre_cleanup + + ip address del dev $h3 2001:db8:2::2/64 + ip address del dev $swp3 2001:db8:2::1/64 + + ip address del dev $h3 192.0.2.130/28 + ip address del dev $swp3 192.0.2.129/28 + + mirror_gre_topo_destroy + vrf_cleanup +} + +test_span_gre_neigh() +{ + local addr=$1; shift + local tundev=$1; shift + local direction=$1; shift + local what=$1; shift + + RET=0 + + ip neigh replace dev $swp3 $addr lladdr 00:11:22:33:44:55 + mirror_install $swp1 $direction $tundev "matchall $tcflags" + fail_test_span_gre_dir $tundev ingress + ip neigh del dev $swp3 $addr + quick_test_span_gre_dir $tundev ingress + mirror_uninstall $swp1 $direction + + log_test "$direction $what: neighbor change ($tcflags)" +} + +test_gretap() +{ + test_span_gre_neigh 192.0.2.130 gt4 ingress "mirror to gretap" + test_span_gre_neigh 192.0.2.130 gt4 egress "mirror to gretap" +} + +test_ip6gretap() +{ + test_span_gre_neigh 2001:db8:2::2 gt6 ingress "mirror to ip6gretap" + test_span_gre_neigh 2001:db8:2::2 gt6 egress "mirror to ip6gretap" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh new file mode 100755 index 000000000000..8fa681eb90e7 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_nh.sh @@ -0,0 +1,127 @@ +#!/bin/bash +# SPDX-License-Identifier: GPL-2.0 + +# This test uses standard topology for testing gretap. See +# mirror_gre_topo_lib.sh for more details. +# +# Test that gretap and ip6gretap mirroring works when the other tunnel endpoint +# is reachable through a next-hop route (as opposed to directly-attached route). + +ALL_TESTS=" + test_gretap + test_ip6gretap +" + +NUM_NETIFS=6 +source lib.sh +source mirror_lib.sh +source mirror_gre_lib.sh +source mirror_gre_topo_lib.sh + +setup_prepare() +{ + h1=${NETIFS[p1]} + swp1=${NETIFS[p2]} + + swp2=${NETIFS[p3]} + h2=${NETIFS[p4]} + + swp3=${NETIFS[p5]} + h3=${NETIFS[p6]} + + sysctl_set net.ipv4.conf.all.rp_filter 0 + sysctl_set net.ipv4.conf.$h3.rp_filter 0 + + vrf_prepare + mirror_gre_topo_create + + ip address add dev $swp3 192.0.2.161/28 + ip address add dev $h3 192.0.2.162/28 + ip address add dev gt4 192.0.2.129/32 + ip address add dev h3-gt4 192.0.2.130/32 + + # IPv6 route can't be added after address. Such routes are rejected due + # to the gateway address having been configured on the local system. It + # works the other way around though. + ip address add dev $swp3 2001:db8:4::1/64 + ip -6 route add 2001:db8:2::2/128 via 2001:db8:4::2 + ip address add dev $h3 2001:db8:4::2/64 + ip address add dev gt6 2001:db8:2::1 + ip address add dev h3-gt6 2001:db8:2::2 +} + +cleanup() +{ + pre_cleanup + + ip -6 route del 2001:db8:2::2/128 via 2001:db8:4::2 + ip address del dev $h3 2001:db8:4::2/64 + ip address del dev $swp3 2001:db8:4::1/64 + + ip address del dev $h3 192.0.2.162/28 + ip address del dev $swp3 192.0.2.161/28 + + mirror_gre_topo_destroy + vrf_cleanup + + sysctl_restore net.ipv4.conf.$h3.rp_filter + sysctl_restore net.ipv4.conf.all.rp_filter +} + +test_gretap() +{ + RET=0 + mirror_install $swp1 ingress gt4 "matchall $tcflags" + + # For IPv4, test that there's no mirroring without the route directing + # the traffic to tunnel remote address. Then add it and test that + # mirroring starts. For IPv6 we can't test this due to the limitation + # that routes for locally-specified IPv6 addresses can't be added. + fail_test_span_gre_dir gt4 ingress + + ip route add 192.0.2.130/32 via 192.0.2.162 + quick_test_span_gre_dir gt4 ingress + ip route del 192.0.2.130/32 via 192.0.2.162 + + mirror_uninstall $swp1 ingress + log_test "mirror to gre with next-hop remote ($tcflags)" +} + +test_ip6gretap() +{ + RET=0 + + mirror_install $swp1 ingress gt6 "matchall $tcflags" + quick_test_span_gre_dir gt6 ingress + mirror_uninstall $swp1 ingress + + log_test "mirror to ip6gre with next-hop remote ($tcflags)" +} + +test_all() +{ + slow_path_trap_install $swp1 ingress + slow_path_trap_install $swp1 egress + + tests_run + + slow_path_trap_uninstall $swp1 egress + slow_path_trap_uninstall $swp1 ingress +} + +trap cleanup EXIT + +setup_prepare +setup_wait + +tcflags="skip_hw" +test_all + +if ! tc_offload_check; then + echo "WARN: Could not test offloaded functionality" +else + tcflags="skip_sw" + test_all +fi + +exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh new file mode 100644 index 000000000000..b3ceda2b4197 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_gre_topo_lib.sh @@ -0,0 +1,129 @@ +# SPDX-License-Identifier: GPL-2.0 + +# This is the standard topology for testing mirroring to gretap and ip6gretap +# netdevices. The tests that use it tweak it in one way or another--importantly, +# $swp3 and $h3 need to have addresses set up. +# +# +---------------------+ +---------------------+ +# | H1 | | H2 | +# | + $h1 | | $h2 + | +# | | 192.0.2.1/28 | | 192.0.2.2/28 | | +# +-----|---------------+ +---------------|-----+ +# | | +# +-----|-------------------------------------------------------------|-----+ +# | SW o--> mirror | | +# | +---|-------------------------------------------------------------|---+ | +# | | + $swp1 BR $swp2 + | | +# | +---------------------------------------------------------------------+ | +# | | +# | + $swp3 + gt6 (ip6gretap) + gt4 (gretap) | +# | | : loc=2001:db8:2::1 : loc=192.0.2.129 | +# | | : rem=2001:db8:2::2 : rem=192.0.2.130 | +# | | : ttl=100 : ttl=100 | +# | | : tos=inherit : tos=inherit | +# | | : : | +# +-----|---------------------:----------------------:----------------------+ +# | : : +# +-----|---------------------:----------------------:----------------------+ +# | H3 + $h3 + h3-gt6 (ip6gretap) + h3-gt4 (gretap) | +# | loc=2001:db8:2::2 loc=192.0.2.130 | +# | rem=2001:db8:2::1 rem=192.0.2.129 | +# | ttl=100 ttl=100 | +# | tos=inherit tos=inherit | +# | | +# +-------------------------------------------------------------------------+ + +mirror_gre_topo_h1_create() +{ + simple_if_init $h1 192.0.2.1/28 +} + +mirror_gre_topo_h1_destroy() +{ + simple_if_fini $h1 192.0.2.1/28 +} + +mirror_gre_topo_h2_create() +{ + simple_if_init $h2 192.0.2.2/28 +} + +mirror_gre_topo_h2_destroy() +{ + simple_if_fini $h2 192.0.2.2/28 +} + +mirror_gre_topo_h3_create() +{ + simple_if_init $h3 + + tunnel_create h3-gt4 gretap 192.0.2.130 192.0.2.129 + ip link set h3-gt4 vrf v$h3 + matchall_sink_create h3-gt4 + + tunnel_create h3-gt6 ip6gretap 2001:db8:2::2 2001:db8:2::1 + ip link set h3-gt6 vrf v$h3 + matchall_sink_create h3-gt6 +} + +mirror_gre_topo_h3_destroy() +{ + tunnel_destroy h3-gt6 + tunnel_destroy h3-gt4 + + simple_if_fini $h3 +} + +mirror_gre_topo_switch_create() +{ + ip link set dev $swp3 up + + ip link add name br1 type bridge vlan_filtering 1 + ip link set dev br1 up + + ip link set dev $swp1 master br1 + ip link set dev $swp1 up + + ip link set dev $swp2 master br1 + ip link set dev $swp2 up + + tunnel_create gt4 gretap 192.0.2.129 192.0.2.130 \ + ttl 100 tos inherit + + tunnel_create gt6 ip6gretap 2001:db8:2::1 2001:db8:2::2 \ + ttl 100 tos inherit allow-localremote + + tc qdisc add dev $swp1 clsact +} + +mirror_gre_topo_switch_destroy() +{ + tc qdisc del dev $swp1 clsact + + tunnel_destroy gt6 + tunnel_destroy gt4 + + ip link set dev $swp1 down + ip link set dev $swp2 down + ip link del dev br1 + + ip link set dev $swp3 down +} + +mirror_gre_topo_create() +{ + mirror_gre_topo_h1_create + mirror_gre_topo_h2_create + mirror_gre_topo_h3_create + + mirror_gre_topo_switch_create +} + +mirror_gre_topo_destroy() +{ + mirror_gre_topo_switch_destroy + + mirror_gre_topo_h3_destroy + mirror_gre_topo_h2_destroy + mirror_gre_topo_h1_destroy +} diff --git a/tools/testing/selftests/net/forwarding/mirror_lib.sh b/tools/testing/selftests/net/forwarding/mirror_lib.sh new file mode 100644 index 000000000000..e5028a5725e3 --- /dev/null +++ b/tools/testing/selftests/net/forwarding/mirror_lib.sh @@ -0,0 +1,40 @@ +# SPDX-License-Identifier: GPL-2.0 + +mirror_install() +{ + local from_dev=$1; shift + local direction=$1; shift + local to_dev=$1; shift + local filter=$1; shift + + tc filter add dev $from_dev $direction \ + pref 1000 $filter \ + action mirred egress mirror dev $to_dev +} + +mirror_uninstall() +{ + local from_dev=$1; shift + local direction=$1; shift + + tc filter del dev $swp1 $direction pref 1000 +} + +mirror_test() +{ + local vrf_name=$1; shift + local sip=$1; shift + local dip=$1; shift + local dev=$1; shift + local pref=$1; shift + local expect=$1; shift + + local t0=$(tc_rule_stats_get $dev $pref) + ip vrf exec $vrf_name \ + ${PING} ${sip:+-I $sip} $dip -c 10 -i 0.1 -w 2 &> /dev/null + local t1=$(tc_rule_stats_get $dev $pref) + local delta=$((t1 - t0)) + # Tolerate a couple stray extra packets. + ((expect <= delta && delta <= expect + 2)) + check_err $? "Expected to capture $expect packets, got $delta." +} diff --git a/tools/testing/selftests/net/forwarding/router.sh b/tools/testing/selftests/net/forwarding/router.sh index cc6a14abfa87..a75cb51cc5bd 100755 --- a/tools/testing/selftests/net/forwarding/router.sh +++ b/tools/testing/selftests/net/forwarding/router.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6" NUM_NETIFS=4 source lib.sh @@ -114,12 +115,21 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 198.51.100.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 198.51.100.2 -ping6_test $h1 2001:db8:2::2 +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/router_multipath.sh b/tools/testing/selftests/net/forwarding/router_multipath.sh index 3bc351008db6..8b6d0fb6d604 100755 --- a/tools/testing/selftests/net/forwarding/router_multipath.sh +++ b/tools/testing/selftests/net/forwarding/router_multipath.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="ping_ipv4 ping_ipv6 multipath_test" NUM_NETIFS=8 source lib.sh @@ -191,7 +192,7 @@ multipath_eval() diff=$(echo $weights_ratio - $packets_ratio | bc -l) diff=${diff#-} - test "$(echo "$diff / $weights_ratio > 0.1" | bc -l)" -eq 0 + test "$(echo "$diff / $weights_ratio > 0.15" | bc -l)" -eq 0 check_err $? "Too large discrepancy between expected and measured ratios" log_test "$desc" log_info "Expected ratio $weights_ratio Measured ratio $packets_ratio" @@ -204,13 +205,11 @@ multipath4_test() local weight_rp13=$3 local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 - local hash_policy # Transmit multiple flows from h1 to h2 and make sure they are # distributed between both multipath links (rp12 and rp13) # according to the configured weights. - hash_policy=$(sysctl -n net.ipv4.fib_multipath_hash_policy) - sysctl -q -w net.ipv4.fib_multipath_hash_policy=1 + sysctl_set net.ipv4.fib_multipath_hash_policy 1 ip route replace 198.51.100.0/24 vrf vrf-r1 \ nexthop via 169.254.2.22 dev $rp12 weight $weight_rp12 \ nexthop via 169.254.3.23 dev $rp13 weight $weight_rp13 @@ -232,7 +231,7 @@ multipath4_test() ip route replace 198.51.100.0/24 vrf vrf-r1 \ nexthop via 169.254.2.22 dev $rp12 \ nexthop via 169.254.3.23 dev $rp13 - sysctl -q -w net.ipv4.fib_multipath_hash_policy=$hash_policy + sysctl_restore net.ipv4.fib_multipath_hash_policy } multipath6_l4_test() @@ -242,13 +241,11 @@ multipath6_l4_test() local weight_rp13=$3 local t0_rp12 t0_rp13 t1_rp12 t1_rp13 local packets_rp12 packets_rp13 - local hash_policy # Transmit multiple flows from h1 to h2 and make sure they are # distributed between both multipath links (rp12 and rp13) # according to the configured weights. - hash_policy=$(sysctl -n net.ipv6.fib_multipath_hash_policy) - sysctl -q -w net.ipv6.fib_multipath_hash_policy=1 + sysctl_set net.ipv6.fib_multipath_hash_policy 1 ip route replace 2001:db8:2::/64 vrf vrf-r1 \ nexthop via fe80:2::22 dev $rp12 weight $weight_rp12 \ @@ -271,7 +268,7 @@ multipath6_l4_test() nexthop via fe80:2::22 dev $rp12 \ nexthop via fe80:3::23 dev $rp13 - sysctl -q -w net.ipv6.fib_multipath_hash_policy=$hash_policy + sysctl_restore net.ipv6.fib_multipath_hash_policy } multipath6_test() @@ -364,13 +361,21 @@ cleanup() vrf_cleanup } +ping_ipv4() +{ + ping_test $h1 198.51.100.2 +} + +ping_ipv6() +{ + ping6_test $h1 2001:db8:2::2 +} + trap cleanup EXIT setup_prepare setup_wait -ping_test $h1 198.51.100.2 -ping6_test $h1 2001:db8:2::2 -multipath_test +tests_run exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_actions.sh b/tools/testing/selftests/net/forwarding/tc_actions.sh index 3a6385ebd5d0..813d02d1939d 100755 --- a/tools/testing/selftests/net/forwarding/tc_actions.sh +++ b/tools/testing/selftests/net/forwarding/tc_actions.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="gact_drop_and_ok_test mirred_egress_redirect_test \ + mirred_egress_mirror_test gact_trap_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -111,6 +113,10 @@ gact_trap_test() { RET=0 + if [[ "$tcflags" != "skip_sw" ]]; then + return 0; + fi + tc filter add dev $swp1 ingress protocol ip pref 1 handle 101 flower \ skip_hw dst_ip 192.0.2.2 action drop tc filter add dev $swp1 ingress protocol ip pref 3 handle 103 flower \ @@ -179,24 +185,29 @@ cleanup() ip link set $swp1 address $swp1origmac } +mirred_egress_redirect_test() +{ + mirred_egress_test "redirect" +} + +mirred_egress_mirror_test() +{ + mirred_egress_test "mirror" +} + trap cleanup EXIT setup_prepare setup_wait -gact_drop_and_ok_test -mirred_egress_test "redirect" -mirred_egress_test "mirror" +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - gact_drop_and_ok_test - mirred_egress_test "redirect" - mirred_egress_test "mirror" - gact_trap_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_chains.sh b/tools/testing/selftests/net/forwarding/tc_chains.sh index 2fd15226974b..d2c783e94df3 100755 --- a/tools/testing/selftests/net/forwarding/tc_chains.sh +++ b/tools/testing/selftests/net/forwarding/tc_chains.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="unreachable_chain_test gact_goto_chain_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -107,16 +108,14 @@ trap cleanup EXIT setup_prepare setup_wait -unreachable_chain_test -gact_goto_chain_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - unreachable_chain_test - gact_goto_chain_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_flower.sh b/tools/testing/selftests/net/forwarding/tc_flower.sh index 032b882adfc0..20d1077e5a3d 100755 --- a/tools/testing/selftests/net/forwarding/tc_flower.sh +++ b/tools/testing/selftests/net/forwarding/tc_flower.sh @@ -1,6 +1,8 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="match_dst_mac_test match_src_mac_test match_dst_ip_test \ + match_src_ip_test match_ip_flags_test" NUM_NETIFS=2 source tc_common.sh source lib.sh @@ -149,6 +151,74 @@ match_src_ip_test() log_test "src_ip match ($tcflags)" } +match_ip_flags_test() +{ + RET=0 + + tc filter add dev $h2 ingress protocol ip pref 1 handle 101 flower \ + $tcflags ip_flags frag action continue + tc filter add dev $h2 ingress protocol ip pref 2 handle 102 flower \ + $tcflags ip_flags firstfrag action continue + tc filter add dev $h2 ingress protocol ip pref 3 handle 103 flower \ + $tcflags ip_flags nofirstfrag action continue + tc filter add dev $h2 ingress protocol ip pref 4 handle 104 flower \ + $tcflags ip_flags nofrag action drop + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=0" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_fail $? "Matched on wrong frag filter (nofrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_fail $? "Matched on wrong firstfrag filter (nofrag)" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Did not match on nofirstfrag filter (nofrag) " + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Did not match on nofrag filter (nofrag)" + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=0,mf" -q + + tc_check_packets "dev $h2 ingress" 101 1 + check_err $? "Did not match on frag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Did not match fistfrag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 103 1 + check_err $? "Matched on wrong nofirstfrag filter (1stfrag)" + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Match on wrong nofrag filter (1stfrag)" + + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=256,mf" -q + $MZ $h1 -c 1 -p 1000 -a $h1mac -b $h2mac -A 192.0.2.1 -B 192.0.2.2 \ + -t ip "frag=256" -q + + tc_check_packets "dev $h2 ingress" 101 3 + check_err $? "Did not match on frag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 102 1 + check_err $? "Matched on wrong firstfrag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 103 3 + check_err $? "Did not match on nofirstfrag filter (no1stfrag)" + + tc_check_packets "dev $h2 ingress" 104 1 + check_err $? "Matched on nofrag filter (no1stfrag)" + + tc filter del dev $h2 ingress protocol ip pref 1 handle 101 flower + tc filter del dev $h2 ingress protocol ip pref 2 handle 102 flower + tc filter del dev $h2 ingress protocol ip pref 3 handle 103 flower + tc filter del dev $h2 ingress protocol ip pref 4 handle 104 flower + + log_test "ip_flags match ($tcflags)" +} + setup_prepare() { h1=${NETIFS[p1]} @@ -177,20 +247,14 @@ trap cleanup EXIT setup_prepare setup_wait -match_dst_mac_test -match_src_mac_test -match_dst_ip_test -match_src_ip_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - match_dst_mac_test - match_src_mac_test - match_dst_ip_test - match_src_ip_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/forwarding/tc_shblocks.sh b/tools/testing/selftests/net/forwarding/tc_shblocks.sh index 077b98048ef4..b5b917203815 100755 --- a/tools/testing/selftests/net/forwarding/tc_shblocks.sh +++ b/tools/testing/selftests/net/forwarding/tc_shblocks.sh @@ -1,6 +1,7 @@ #!/bin/bash # SPDX-License-Identifier: GPL-2.0 +ALL_TESTS="shared_block_test" NUM_NETIFS=4 source tc_common.sh source lib.sh @@ -109,14 +110,14 @@ trap cleanup EXIT setup_prepare setup_wait -shared_block_test +tests_run tc_offload_check if [[ $? -ne 0 ]]; then log_info "Could not test offloaded functionality" else tcflags="skip_sw" - shared_block_test + tests_run fi exit $EXIT_STATUS diff --git a/tools/testing/selftests/net/pmtu.sh b/tools/testing/selftests/net/pmtu.sh index 1e428781a625..7651fd4d86fe 100755 --- a/tools/testing/selftests/net/pmtu.sh +++ b/tools/testing/selftests/net/pmtu.sh @@ -368,7 +368,7 @@ test_pmtu_vti6_link_add_mtu() { fail=0 - min=1280 + min=68 # vti6 can carry IPv4 packets too max=$((65535 - 40)) # Check invalid values first for v in $((min - 1)) $((max + 1)); do @@ -384,7 +384,7 @@ test_pmtu_vti6_link_add_mtu() { done # Now check valid values - for v in 1280 1300 $((65535 - 40)); do + for v in 68 1280 1300 $((65535 - 40)); do ${ns_a} ip link add vti6_a mtu ${v} type vti6 local ${veth6_a_addr} remote ${veth6_b_addr} key 10 mtu="$(link_get_mtu "${ns_a}" vti6_a)" ${ns_a} ip link del vti6_a diff --git a/tools/testing/selftests/net/rtnetlink.sh b/tools/testing/selftests/net/rtnetlink.sh index e6f485235435..760faef2e12e 100755 --- a/tools/testing/selftests/net/rtnetlink.sh +++ b/tools/testing/selftests/net/rtnetlink.sh @@ -502,6 +502,108 @@ kci_test_macsec() echo "PASS: macsec" } +#------------------------------------------------------------------- +# Example commands +# ip x s add proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 replay-window 32 \ +# aead 'rfc4106(gcm(aes))' 1234567890123456dcba 128 \ +# sel src 14.0.0.52/24 dst 14.0.0.70/24 +# ip x p add dir out src 14.0.0.52/24 dst 14.0.0.70/24 \ +# tmpl proto esp src 14.0.0.52 dst 14.0.0.70 \ +# spi 0x07 mode transport reqid 0x07 +# +# Subcommands not tested +# ip x s update +# ip x s allocspi +# ip x s deleteall +# ip x p update +# ip x p deleteall +# ip x p set +#------------------------------------------------------------------- +kci_test_ipsec() +{ + srcip="14.0.0.52" + dstip="14.0.0.70" + algo="aead rfc4106(gcm(aes)) 0x3132333435363738393031323334353664636261 128" + + # flush to be sure there's nothing configured + ip x s flush ; ip x p flush + check_err $? + + # start the monitor in the background + tmpfile=`mktemp ipsectestXXX` + ip x m > $tmpfile & + mpid=$! + sleep 0.2 + + ipsecid="proto esp src $srcip dst $dstip spi 0x07" + ip x s add $ipsecid \ + mode transport reqid 0x07 replay-window 32 \ + $algo sel src $srcip/24 dst $dstip/24 + check_err $? + + lines=`ip x s list | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x s count | grep -q "SAD count 1" + check_err $? + + lines=`ip x s get $ipsecid | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x s delete $ipsecid + check_err $? + + lines=`ip x s list | wc -l` + test $lines -eq 0 + check_err $? + + ipsecsel="dir out src $srcip/24 dst $dstip/24" + ip x p add $ipsecsel \ + tmpl proto esp src $srcip dst $dstip \ + spi 0x07 mode transport reqid 0x07 + check_err $? + + lines=`ip x p list | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x p count | grep -q "SPD IN 0 OUT 1 FWD 0" + check_err $? + + lines=`ip x p get $ipsecsel | grep $srcip | grep $dstip | wc -l` + test $lines -eq 2 + check_err $? + + ip x p delete $ipsecsel + check_err $? + + lines=`ip x p list | wc -l` + test $lines -eq 0 + check_err $? + + # check the monitor results + kill $mpid + lines=`wc -l $tmpfile | cut "-d " -f1` + test $lines -eq 20 + check_err $? + rm -rf $tmpfile + + # clean up any leftovers + ip x s flush + check_err $? + ip x p flush + check_err $? + + if [ $ret -ne 0 ]; then + echo "FAIL: ipsec" + return 1 + fi + echo "PASS: ipsec" +} + kci_test_gretap() { testns="testns" @@ -755,6 +857,7 @@ kci_test_rtnl() kci_test_vrf kci_test_encap kci_test_macsec + kci_test_ipsec kci_del_dummy } diff --git a/tools/testing/selftests/net/tcp_inq.c b/tools/testing/selftests/net/tcp_inq.c new file mode 100644 index 000000000000..d044b29ddabc --- /dev/null +++ b/tools/testing/selftests/net/tcp_inq.c @@ -0,0 +1,189 @@ +/* + * Copyright 2018 Google Inc. + * Author: Soheil Hassas Yeganeh (soheil@google.com) + * + * Simple example on how to use TCP_INQ and TCP_CM_INQ. + * + * License (GPLv2): + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + */ +#define _GNU_SOURCE + +#include <error.h> +#include <netinet/in.h> +#include <netinet/tcp.h> +#include <pthread.h> +#include <stdio.h> +#include <errno.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <unistd.h> + +#ifndef TCP_INQ +#define TCP_INQ 36 +#endif + +#ifndef TCP_CM_INQ +#define TCP_CM_INQ TCP_INQ +#endif + +#define BUF_SIZE 8192 +#define CMSG_SIZE 32 + +static int family = AF_INET6; +static socklen_t addr_len = sizeof(struct sockaddr_in6); +static int port = 4974; + +static void setup_loopback_addr(int family, struct sockaddr_storage *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (family) { + case PF_INET: + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = AF_INET; + addr4->sin_addr.s_addr = htonl(INADDR_LOOPBACK); + addr4->sin_port = htons(port); + break; + case PF_INET6: + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = AF_INET6; + addr6->sin6_addr = in6addr_loopback; + addr6->sin6_port = htons(port); + break; + default: + error(1, 0, "illegal family"); + } +} + +void *start_server(void *arg) +{ + int server_fd = (int)(unsigned long)arg; + struct sockaddr_in addr; + socklen_t addrlen = sizeof(addr); + char *buf; + int fd; + int r; + + buf = malloc(BUF_SIZE); + + for (;;) { + fd = accept(server_fd, (struct sockaddr *)&addr, &addrlen); + if (fd == -1) { + perror("accept"); + break; + } + do { + r = send(fd, buf, BUF_SIZE, 0); + } while (r < 0 && errno == EINTR); + if (r < 0) + perror("send"); + if (r != BUF_SIZE) + fprintf(stderr, "can only send %d bytes\n", r); + /* TCP_INQ can overestimate in-queue by one byte if we send + * the FIN packet. Sleep for 1 second, so that the client + * likely invoked recvmsg(). + */ + sleep(1); + close(fd); + } + + free(buf); + close(server_fd); + pthread_exit(0); +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_storage listen_addr, addr; + int c, one = 1, inq = -1; + pthread_t server_thread; + char cmsgbuf[CMSG_SIZE]; + struct iovec iov[1]; + struct cmsghdr *cm; + struct msghdr msg; + int server_fd, fd; + char *buf; + + while ((c = getopt(argc, argv, "46p:")) != -1) { + switch (c) { + case '4': + family = PF_INET; + addr_len = sizeof(struct sockaddr_in); + break; + case '6': + family = PF_INET6; + addr_len = sizeof(struct sockaddr_in6); + break; + case 'p': + port = atoi(optarg); + break; + } + } + + server_fd = socket(family, SOCK_STREAM, 0); + if (server_fd < 0) + error(1, errno, "server socket"); + setup_loopback_addr(family, &listen_addr); + if (setsockopt(server_fd, SOL_SOCKET, SO_REUSEADDR, + &one, sizeof(one)) != 0) + error(1, errno, "setsockopt(SO_REUSEADDR)"); + if (bind(server_fd, (const struct sockaddr *)&listen_addr, + addr_len) == -1) + error(1, errno, "bind"); + if (listen(server_fd, 128) == -1) + error(1, errno, "listen"); + if (pthread_create(&server_thread, NULL, start_server, + (void *)(unsigned long)server_fd) != 0) + error(1, errno, "pthread_create"); + + fd = socket(family, SOCK_STREAM, 0); + if (fd < 0) + error(1, errno, "client socket"); + setup_loopback_addr(family, &addr); + if (connect(fd, (const struct sockaddr *)&addr, addr_len) == -1) + error(1, errno, "connect"); + if (setsockopt(fd, SOL_TCP, TCP_INQ, &one, sizeof(one)) != 0) + error(1, errno, "setsockopt(TCP_INQ)"); + + msg.msg_name = NULL; + msg.msg_namelen = 0; + msg.msg_iov = iov; + msg.msg_iovlen = 1; + msg.msg_control = cmsgbuf; + msg.msg_controllen = sizeof(cmsgbuf); + msg.msg_flags = 0; + + buf = malloc(BUF_SIZE); + iov[0].iov_base = buf; + iov[0].iov_len = BUF_SIZE / 2; + + if (recvmsg(fd, &msg, 0) != iov[0].iov_len) + error(1, errno, "recvmsg"); + if (msg.msg_flags & MSG_CTRUNC) + error(1, 0, "control message is truncated"); + + for (cm = CMSG_FIRSTHDR(&msg); cm; cm = CMSG_NXTHDR(&msg, cm)) + if (cm->cmsg_level == SOL_TCP && cm->cmsg_type == TCP_CM_INQ) + inq = *((int *) CMSG_DATA(cm)); + + if (inq != BUF_SIZE - iov[0].iov_len) { + fprintf(stderr, "unexpected inq: %d\n", inq); + exit(1); + } + + printf("PASSED\n"); + free(buf); + close(fd); + return 0; +} diff --git a/tools/testing/selftests/net/tcp_mmap.c b/tools/testing/selftests/net/tcp_mmap.c new file mode 100644 index 000000000000..77f762780199 --- /dev/null +++ b/tools/testing/selftests/net/tcp_mmap.c @@ -0,0 +1,447 @@ +/* + * Copyright 2018 Google Inc. + * Author: Eric Dumazet (edumazet@google.com) + * + * Reference program demonstrating tcp mmap() usage, + * and SO_RCVLOWAT hints for receiver. + * + * Note : NIC with header split is needed to use mmap() on TCP : + * Each incoming frame must be a multiple of PAGE_SIZE bytes of TCP payload. + * + * How to use on loopback interface : + * + * ifconfig lo mtu 61512 # 15*4096 + 40 (ipv6 header) + 32 (TCP with TS option header) + * tcp_mmap -s -z & + * tcp_mmap -H ::1 -z + * + * Or leave default lo mtu, but use -M option to set TCP_MAXSEG option to (4096 + 12) + * (4096 : page size on x86, 12: TCP TS option length) + * tcp_mmap -s -z -M $((4096+12)) & + * tcp_mmap -H ::1 -z -M $((4096+12)) + * + * Note: -z option on sender uses MSG_ZEROCOPY, which forces a copy when packets go through loopback interface. + * We might use sendfile() instead, but really this test program is about mmap(), for receivers ;) + * + * $ ./tcp_mmap -s & # Without mmap() + * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done + * received 32768 MB (0 % mmap'ed) in 14.1157 s, 19.4732 Gbit + * cpu usage user:0.057 sys:7.815, 240.234 usec per MB, 65531 c-switches + * received 32768 MB (0 % mmap'ed) in 14.6833 s, 18.7204 Gbit + * cpu usage user:0.043 sys:8.103, 248.596 usec per MB, 65524 c-switches + * received 32768 MB (0 % mmap'ed) in 11.143 s, 24.6682 Gbit + * cpu usage user:0.044 sys:6.576, 202.026 usec per MB, 65519 c-switches + * received 32768 MB (0 % mmap'ed) in 14.9056 s, 18.4413 Gbit + * cpu usage user:0.036 sys:8.193, 251.129 usec per MB, 65530 c-switches + * $ kill %1 # kill tcp_mmap server + * + * $ ./tcp_mmap -s -z & # With mmap() + * $ for i in {1..4}; do ./tcp_mmap -H ::1 -z ; done + * received 32768 MB (99.9939 % mmap'ed) in 6.73792 s, 40.7956 Gbit + * cpu usage user:0.045 sys:2.827, 87.6465 usec per MB, 65532 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.26732 s, 37.8238 Gbit + * cpu usage user:0.037 sys:3.087, 95.3369 usec per MB, 65532 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.61661 s, 36.0893 Gbit + * cpu usage user:0.046 sys:3.559, 110.016 usec per MB, 65529 c-switches + * received 32768 MB (99.9939 % mmap'ed) in 7.43764 s, 36.9577 Gbit + * cpu usage user:0.035 sys:3.467, 106.873 usec per MB, 65530 c-switches + * + * License (GPLv2): + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. * See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ +#define _GNU_SOURCE +#include <pthread.h> +#include <sys/types.h> +#include <fcntl.h> +#include <error.h> +#include <sys/socket.h> +#include <sys/mman.h> +#include <sys/resource.h> +#include <unistd.h> +#include <string.h> +#include <stdlib.h> +#include <stdio.h> +#include <errno.h> +#include <time.h> +#include <sys/time.h> +#include <netinet/in.h> +#include <arpa/inet.h> +#include <poll.h> +#include <linux/tcp.h> +#include <assert.h> + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +#define FILE_SZ (1UL << 35) +static int cfg_family = AF_INET6; +static socklen_t cfg_alen = sizeof(struct sockaddr_in6); +static int cfg_port = 8787; + +static int rcvbuf; /* Default: autotuning. Can be set with -r <integer> option */ +static int sndbuf; /* Default: autotuning. Can be set with -w <integer> option */ +static int zflg; /* zero copy option. (MSG_ZEROCOPY for sender, mmap() for receiver */ +static int xflg; /* hash received data (simple xor) (-h option) */ +static int keepflag; /* -k option: receiver shall keep all received file in memory (no munmap() calls) */ + +static int chunk_size = 512*1024; + +unsigned long htotal; + +static inline void prefetch(const void *x) +{ +#if defined(__x86_64__) + asm volatile("prefetcht0 %P0" : : "m" (*(const char *)x)); +#endif +} + +void hash_zone(void *zone, unsigned int length) +{ + unsigned long temp = htotal; + + while (length >= 8*sizeof(long)) { + prefetch(zone + 384); + temp ^= *(unsigned long *)zone; + temp ^= *(unsigned long *)(zone + sizeof(long)); + temp ^= *(unsigned long *)(zone + 2*sizeof(long)); + temp ^= *(unsigned long *)(zone + 3*sizeof(long)); + temp ^= *(unsigned long *)(zone + 4*sizeof(long)); + temp ^= *(unsigned long *)(zone + 5*sizeof(long)); + temp ^= *(unsigned long *)(zone + 6*sizeof(long)); + temp ^= *(unsigned long *)(zone + 7*sizeof(long)); + zone += 8*sizeof(long); + length -= 8*sizeof(long); + } + while (length >= 1) { + temp ^= *(unsigned char *)zone; + zone += 1; + length--; + } + htotal = temp; +} + +void *child_thread(void *arg) +{ + unsigned long total_mmap = 0, total = 0; + struct tcp_zerocopy_receive zc; + unsigned long delta_usec; + int flags = MAP_SHARED; + struct timeval t0, t1; + char *buffer = NULL; + void *addr = NULL; + double throughput; + struct rusage ru; + int lu, fd; + + fd = (int)(unsigned long)arg; + + gettimeofday(&t0, NULL); + + fcntl(fd, F_SETFL, O_NDELAY); + buffer = malloc(chunk_size); + if (!buffer) { + perror("malloc"); + goto error; + } + if (zflg) { + addr = mmap(NULL, chunk_size, PROT_READ, flags, fd, 0); + if (addr == (void *)-1) + zflg = 0; + } + while (1) { + struct pollfd pfd = { .fd = fd, .events = POLLIN, }; + int sub; + + poll(&pfd, 1, 10000); + if (zflg) { + socklen_t zc_len = sizeof(zc); + int res; + + zc.address = (__u64)addr; + zc.length = chunk_size; + zc.recv_skip_hint = 0; + res = getsockopt(fd, IPPROTO_TCP, TCP_ZEROCOPY_RECEIVE, + &zc, &zc_len); + if (res == -1) + break; + + if (zc.length) { + assert(zc.length <= chunk_size); + total_mmap += zc.length; + if (xflg) + hash_zone(addr, zc.length); + total += zc.length; + } + if (zc.recv_skip_hint) { + assert(zc.recv_skip_hint <= chunk_size); + lu = read(fd, buffer, zc.recv_skip_hint); + if (lu > 0) { + if (xflg) + hash_zone(buffer, lu); + total += lu; + } + } + continue; + } + sub = 0; + while (sub < chunk_size) { + lu = read(fd, buffer + sub, chunk_size - sub); + if (lu == 0) + goto end; + if (lu < 0) + break; + if (xflg) + hash_zone(buffer + sub, lu); + total += lu; + sub += lu; + } + } +end: + gettimeofday(&t1, NULL); + delta_usec = (t1.tv_sec - t0.tv_sec) * 1000000 + t1.tv_usec - t0.tv_usec; + + throughput = 0; + if (delta_usec) + throughput = total * 8.0 / (double)delta_usec / 1000.0; + getrusage(RUSAGE_THREAD, &ru); + if (total > 1024*1024) { + unsigned long total_usec; + unsigned long mb = total >> 20; + total_usec = 1000000*ru.ru_utime.tv_sec + ru.ru_utime.tv_usec + + 1000000*ru.ru_stime.tv_sec + ru.ru_stime.tv_usec; + printf("received %lg MB (%lg %% mmap'ed) in %lg s, %lg Gbit\n" + " cpu usage user:%lg sys:%lg, %lg usec per MB, %lu c-switches\n", + total / (1024.0 * 1024.0), + 100.0*total_mmap/total, + (double)delta_usec / 1000000.0, + throughput, + (double)ru.ru_utime.tv_sec + (double)ru.ru_utime.tv_usec / 1000000.0, + (double)ru.ru_stime.tv_sec + (double)ru.ru_stime.tv_usec / 1000000.0, + (double)total_usec/mb, + ru.ru_nvcsw); + } +error: + free(buffer); + close(fd); + if (zflg) + munmap(addr, chunk_size); + pthread_exit(0); +} + +static void apply_rcvsnd_buf(int fd) +{ + if (rcvbuf && setsockopt(fd, SOL_SOCKET, + SO_RCVBUF, &rcvbuf, sizeof(rcvbuf)) == -1) { + perror("setsockopt SO_RCVBUF"); + } + + if (sndbuf && setsockopt(fd, SOL_SOCKET, + SO_SNDBUF, &sndbuf, sizeof(sndbuf)) == -1) { + perror("setsockopt SO_SNDBUF"); + } +} + + +static void setup_sockaddr(int domain, const char *str_addr, + struct sockaddr_storage *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + memset(addr4, 0, sizeof(*addr4)); + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (str_addr && + inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + memset(addr6, 0, sizeof(*addr6)); + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (str_addr && + inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static void do_accept(int fdlisten) +{ + if (setsockopt(fdlisten, SOL_SOCKET, SO_RCVLOWAT, + &chunk_size, sizeof(chunk_size)) == -1) { + perror("setsockopt SO_RCVLOWAT"); + } + + apply_rcvsnd_buf(fdlisten); + + while (1) { + struct sockaddr_in addr; + socklen_t addrlen = sizeof(addr); + pthread_t th; + int fd, res; + + fd = accept(fdlisten, (struct sockaddr *)&addr, &addrlen); + if (fd == -1) { + perror("accept"); + continue; + } + res = pthread_create(&th, NULL, child_thread, + (void *)(unsigned long)fd); + if (res) { + errno = res; + perror("pthread_create"); + close(fd); + } + } +} + +int main(int argc, char *argv[]) +{ + struct sockaddr_storage listenaddr, addr; + unsigned int max_pacing_rate = 0; + unsigned long total = 0; + char *host = NULL; + int fd, c, on = 1; + char *buffer; + int sflg = 0; + int mss = 0; + + while ((c = getopt(argc, argv, "46p:svr:w:H:zxkP:M:")) != -1) { + switch (c) { + case '4': + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'p': + cfg_port = atoi(optarg); + break; + case 'H': + host = optarg; + break; + case 's': /* server : listen for incoming connections */ + sflg++; + break; + case 'r': + rcvbuf = atoi(optarg); + break; + case 'w': + sndbuf = atoi(optarg); + break; + case 'z': + zflg = 1; + break; + case 'M': + mss = atoi(optarg); + break; + case 'x': + xflg = 1; + break; + case 'k': + keepflag = 1; + break; + case 'P': + max_pacing_rate = atoi(optarg) ; + break; + default: + exit(1); + } + } + if (sflg) { + int fdlisten = socket(cfg_family, SOCK_STREAM, 0); + + if (fdlisten == -1) { + perror("socket"); + exit(1); + } + apply_rcvsnd_buf(fdlisten); + setsockopt(fdlisten, SOL_SOCKET, SO_REUSEADDR, &on, sizeof(on)); + + setup_sockaddr(cfg_family, host, &listenaddr); + + if (mss && + setsockopt(fdlisten, IPPROTO_TCP, TCP_MAXSEG, + &mss, sizeof(mss)) == -1) { + perror("setsockopt TCP_MAXSEG"); + exit(1); + } + if (bind(fdlisten, (const struct sockaddr *)&listenaddr, cfg_alen) == -1) { + perror("bind"); + exit(1); + } + if (listen(fdlisten, 128) == -1) { + perror("listen"); + exit(1); + } + do_accept(fdlisten); + } + buffer = mmap(NULL, chunk_size, PROT_READ | PROT_WRITE, + MAP_PRIVATE | MAP_ANONYMOUS, -1, 0); + if (buffer == (char *)-1) { + perror("mmap"); + exit(1); + } + + fd = socket(AF_INET6, SOCK_STREAM, 0); + if (fd == -1) { + perror("socket"); + exit(1); + } + apply_rcvsnd_buf(fd); + + setup_sockaddr(cfg_family, host, &addr); + + if (mss && + setsockopt(fd, IPPROTO_TCP, TCP_MAXSEG, &mss, sizeof(mss)) == -1) { + perror("setsockopt TCP_MAXSEG"); + exit(1); + } + if (connect(fd, (const struct sockaddr *)&addr, cfg_alen) == -1) { + perror("connect"); + exit(1); + } + if (max_pacing_rate && + setsockopt(fd, SOL_SOCKET, SO_MAX_PACING_RATE, + &max_pacing_rate, sizeof(max_pacing_rate)) == -1) + perror("setsockopt SO_MAX_PACING_RATE"); + + if (zflg && setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, + &on, sizeof(on)) == -1) { + perror("setsockopt SO_ZEROCOPY, (-z option disabled)"); + zflg = 0; + } + while (total < FILE_SZ) { + long wr = FILE_SZ - total; + + if (wr > chunk_size) + wr = chunk_size; + /* Note : we just want to fill the pipe with 0 bytes */ + wr = send(fd, buffer, wr, zflg ? MSG_ZEROCOPY : 0); + if (wr <= 0) + break; + total += wr; + } + close(fd); + munmap(buffer, chunk_size); + return 0; +} diff --git a/tools/testing/selftests/net/udpgso.c b/tools/testing/selftests/net/udpgso.c new file mode 100644 index 000000000000..48a0592db938 --- /dev/null +++ b/tools/testing/selftests/net/udpgso.c @@ -0,0 +1,620 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <stddef.h> +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <net/if.h> +#include <linux/in.h> +#include <linux/netlink.h> +#include <linux/rtnetlink.h> +#include <netinet/if_ether.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <stdbool.h> +#include <stdlib.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef ETH_MAX_MTU +#define ETH_MAX_MTU 0xFFFFU +#endif + +#ifndef UDP_SEGMENT +#define UDP_SEGMENT 103 +#endif + +#define CONST_MTU_TEST 1500 + +#define CONST_HDRLEN_V4 (sizeof(struct iphdr) + sizeof(struct udphdr)) +#define CONST_HDRLEN_V6 (sizeof(struct ip6_hdr) + sizeof(struct udphdr)) + +#define CONST_MSS_V4 (CONST_MTU_TEST - CONST_HDRLEN_V4) +#define CONST_MSS_V6 (CONST_MTU_TEST - CONST_HDRLEN_V6) + +#define CONST_MAX_SEGS_V4 (ETH_MAX_MTU / CONST_MSS_V4) +#define CONST_MAX_SEGS_V6 (ETH_MAX_MTU / CONST_MSS_V6) + +static bool cfg_do_ipv4; +static bool cfg_do_ipv6; +static bool cfg_do_connected; +static bool cfg_do_connectionless; +static bool cfg_do_msgmore; +static bool cfg_do_setsockopt; +static int cfg_specific_test_id = -1; + +static const char cfg_ifname[] = "lo"; +static unsigned short cfg_port = 9000; + +static char buf[ETH_MAX_MTU]; + +struct testcase { + int tlen; /* send() buffer size, may exceed mss */ + bool tfail; /* send() call is expected to fail */ + int gso_len; /* mss after applying gso */ + int r_num_mss; /* recv(): number of calls of full mss */ + int r_len_last; /* recv(): size of last non-mss dgram, if any */ +}; + +const struct in6_addr addr6 = IN6ADDR_LOOPBACK_INIT; +const struct in_addr addr4 = { .s_addr = __constant_htonl(INADDR_LOOPBACK + 2) }; + +struct testcase testcases_v4[] = { + { + /* no GSO: send a single byte */ + .tlen = 1, + .r_len_last = 1, + }, + { + /* no GSO: send a single MSS */ + .tlen = CONST_MSS_V4, + .r_num_mss = 1, + }, + { + /* no GSO: send a single MSS + 1B: fail */ + .tlen = CONST_MSS_V4 + 1, + .tfail = true, + }, + { + /* send a single MSS: will fail with GSO, because the segment + * logic in udp4_ufo_fragment demands a gso skb to be > MTU + */ + .tlen = CONST_MSS_V4, + .gso_len = CONST_MSS_V4, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send a single MSS + 1B */ + .tlen = CONST_MSS_V4 + 1, + .gso_len = CONST_MSS_V4, + .r_num_mss = 1, + .r_len_last = 1, + }, + { + /* send exactly 2 MSS */ + .tlen = CONST_MSS_V4 * 2, + .gso_len = CONST_MSS_V4, + .r_num_mss = 2, + }, + { + /* send 2 MSS + 1B */ + .tlen = (CONST_MSS_V4 * 2) + 1, + .gso_len = CONST_MSS_V4, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send MAX segs */ + .tlen = (ETH_MAX_MTU / CONST_MSS_V4) * CONST_MSS_V4, + .gso_len = CONST_MSS_V4, + .r_num_mss = (ETH_MAX_MTU / CONST_MSS_V4), + }, + + { + /* send MAX bytes */ + .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4, + .gso_len = CONST_MSS_V4, + .r_num_mss = CONST_MAX_SEGS_V4, + .r_len_last = ETH_MAX_MTU - CONST_HDRLEN_V4 - + (CONST_MAX_SEGS_V4 * CONST_MSS_V4), + }, + { + /* send MAX + 1: fail */ + .tlen = ETH_MAX_MTU - CONST_HDRLEN_V4 + 1, + .gso_len = CONST_MSS_V4, + .tfail = true, + }, + { + /* EOL */ + } +}; + +#ifndef IP6_MAX_MTU +#define IP6_MAX_MTU (ETH_MAX_MTU + sizeof(struct ip6_hdr)) +#endif + +struct testcase testcases_v6[] = { + { + /* no GSO: send a single byte */ + .tlen = 1, + .r_len_last = 1, + }, + { + /* no GSO: send a single MSS */ + .tlen = CONST_MSS_V6, + .r_num_mss = 1, + }, + { + /* no GSO: send a single MSS + 1B: fail */ + .tlen = CONST_MSS_V6 + 1, + .tfail = true, + }, + { + /* send a single MSS: will fail with GSO, because the segment + * logic in udp4_ufo_fragment demands a gso skb to be > MTU + */ + .tlen = CONST_MSS_V6, + .gso_len = CONST_MSS_V6, + .tfail = true, + .r_num_mss = 1, + }, + { + /* send a single MSS + 1B */ + .tlen = CONST_MSS_V6 + 1, + .gso_len = CONST_MSS_V6, + .r_num_mss = 1, + .r_len_last = 1, + }, + { + /* send exactly 2 MSS */ + .tlen = CONST_MSS_V6 * 2, + .gso_len = CONST_MSS_V6, + .r_num_mss = 2, + }, + { + /* send 2 MSS + 1B */ + .tlen = (CONST_MSS_V6 * 2) + 1, + .gso_len = CONST_MSS_V6, + .r_num_mss = 2, + .r_len_last = 1, + }, + { + /* send MAX segs */ + .tlen = (IP6_MAX_MTU / CONST_MSS_V6) * CONST_MSS_V6, + .gso_len = CONST_MSS_V6, + .r_num_mss = (IP6_MAX_MTU / CONST_MSS_V6), + }, + + { + /* send MAX bytes */ + .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6, + .gso_len = CONST_MSS_V6, + .r_num_mss = CONST_MAX_SEGS_V6, + .r_len_last = IP6_MAX_MTU - CONST_HDRLEN_V6 - + (CONST_MAX_SEGS_V6 * CONST_MSS_V6), + }, + { + /* send MAX + 1: fail */ + .tlen = IP6_MAX_MTU - CONST_HDRLEN_V6 + 1, + .gso_len = CONST_MSS_V6, + .tfail = true, + }, + { + /* EOL */ + } +}; + +static unsigned int get_device_mtu(int fd, const char *ifname) +{ + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCGIFMTU, &ifr)) + error(1, errno, "ioctl get mtu"); + + return ifr.ifr_mtu; +} + +static void __set_device_mtu(int fd, const char *ifname, unsigned int mtu) +{ + struct ifreq ifr; + + memset(&ifr, 0, sizeof(ifr)); + + ifr.ifr_mtu = mtu; + strcpy(ifr.ifr_name, ifname); + + if (ioctl(fd, SIOCSIFMTU, &ifr)) + error(1, errno, "ioctl set mtu"); +} + +static void set_device_mtu(int fd, int mtu) +{ + int val; + + val = get_device_mtu(fd, cfg_ifname); + fprintf(stderr, "device mtu (orig): %u\n", val); + + __set_device_mtu(fd, cfg_ifname, mtu); + val = get_device_mtu(fd, cfg_ifname); + if (val != mtu) + error(1, 0, "unable to set device mtu to %u\n", val); + + fprintf(stderr, "device mtu (test): %u\n", val); +} + +static void set_pmtu_discover(int fd, bool is_ipv4) +{ + int level, name, val; + + if (is_ipv4) { + level = SOL_IP; + name = IP_MTU_DISCOVER; + val = IP_PMTUDISC_DO; + } else { + level = SOL_IPV6; + name = IPV6_MTU_DISCOVER; + val = IPV6_PMTUDISC_DO; + } + + if (setsockopt(fd, level, name, &val, sizeof(val))) + error(1, errno, "setsockopt path mtu"); +} + +static unsigned int get_path_mtu(int fd, bool is_ipv4) +{ + socklen_t vallen; + unsigned int mtu; + int ret; + + vallen = sizeof(mtu); + if (is_ipv4) + ret = getsockopt(fd, SOL_IP, IP_MTU, &mtu, &vallen); + else + ret = getsockopt(fd, SOL_IPV6, IPV6_MTU, &mtu, &vallen); + + if (ret) + error(1, errno, "getsockopt mtu"); + + + fprintf(stderr, "path mtu (read): %u\n", mtu); + return mtu; +} + +/* very wordy version of system("ip route add dev lo mtu 1500 127.0.0.3/32") */ +static void set_route_mtu(int mtu, bool is_ipv4) +{ + struct sockaddr_nl nladdr = { .nl_family = AF_NETLINK }; + struct nlmsghdr *nh; + struct rtattr *rta; + struct rtmsg *rt; + char data[NLMSG_ALIGN(sizeof(*nh)) + + NLMSG_ALIGN(sizeof(*rt)) + + NLMSG_ALIGN(RTA_LENGTH(sizeof(addr6))) + + NLMSG_ALIGN(RTA_LENGTH(sizeof(int))) + + NLMSG_ALIGN(RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)))]; + int fd, ret, alen, off = 0; + + alen = is_ipv4 ? sizeof(addr4) : sizeof(addr6); + + fd = socket(AF_NETLINK, SOCK_RAW, NETLINK_ROUTE); + if (fd == -1) + error(1, errno, "socket netlink"); + + memset(data, 0, sizeof(data)); + + nh = (void *)data; + nh->nlmsg_type = RTM_NEWROUTE; + nh->nlmsg_flags = NLM_F_REQUEST | NLM_F_CREATE; + off += NLMSG_ALIGN(sizeof(*nh)); + + rt = (void *)(data + off); + rt->rtm_family = is_ipv4 ? AF_INET : AF_INET6; + rt->rtm_table = RT_TABLE_MAIN; + rt->rtm_dst_len = alen << 3; + rt->rtm_protocol = RTPROT_BOOT; + rt->rtm_scope = RT_SCOPE_UNIVERSE; + rt->rtm_type = RTN_UNICAST; + off += NLMSG_ALIGN(sizeof(*rt)); + + rta = (void *)(data + off); + rta->rta_type = RTA_DST; + rta->rta_len = RTA_LENGTH(alen); + if (is_ipv4) + memcpy(RTA_DATA(rta), &addr4, alen); + else + memcpy(RTA_DATA(rta), &addr6, alen); + off += NLMSG_ALIGN(rta->rta_len); + + rta = (void *)(data + off); + rta->rta_type = RTA_OIF; + rta->rta_len = RTA_LENGTH(sizeof(int)); + *((int *)(RTA_DATA(rta))) = 1; //if_nametoindex("lo"); + off += NLMSG_ALIGN(rta->rta_len); + + /* MTU is a subtype in a metrics type */ + rta = (void *)(data + off); + rta->rta_type = RTA_METRICS; + rta->rta_len = RTA_LENGTH(0) + RTA_LENGTH(sizeof(int)); + off += NLMSG_ALIGN(rta->rta_len); + + /* now fill MTU subtype. Note that it fits within above rta_len */ + rta = (void *)(((char *) rta) + RTA_LENGTH(0)); + rta->rta_type = RTAX_MTU; + rta->rta_len = RTA_LENGTH(sizeof(int)); + *((int *)(RTA_DATA(rta))) = mtu; + + nh->nlmsg_len = off; + + ret = sendto(fd, data, off, 0, (void *)&nladdr, sizeof(nladdr)); + if (ret != off) + error(1, errno, "send netlink: %uB != %uB\n", ret, off); + + if (close(fd)) + error(1, errno, "close netlink"); + + fprintf(stderr, "route mtu (test): %u\n", mtu); +} + +static bool __send_one(int fd, struct msghdr *msg, int flags) +{ + int ret; + + ret = sendmsg(fd, msg, flags); + if (ret == -1 && (errno == EMSGSIZE || errno == ENOMEM)) + return false; + if (ret == -1) + error(1, errno, "sendmsg"); + if (ret != msg->msg_iov->iov_len) + error(1, 0, "sendto: %d != %lu", ret, msg->msg_iov->iov_len); + if (msg->msg_flags) + error(1, 0, "sendmsg: return flags 0x%x\n", msg->msg_flags); + + return true; +} + +static bool send_one(int fd, int len, int gso_len, + struct sockaddr *addr, socklen_t alen) +{ + char control[CMSG_SPACE(sizeof(uint16_t))] = {0}; + struct msghdr msg = {0}; + struct iovec iov = {0}; + struct cmsghdr *cm; + + iov.iov_base = buf; + iov.iov_len = len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_name = addr; + msg.msg_namelen = alen; + + if (gso_len && !cfg_do_setsockopt) { + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + + cm = CMSG_FIRSTHDR(&msg); + cm->cmsg_level = SOL_UDP; + cm->cmsg_type = UDP_SEGMENT; + cm->cmsg_len = CMSG_LEN(sizeof(uint16_t)); + *((uint16_t *) CMSG_DATA(cm)) = gso_len; + } + + /* If MSG_MORE, send 1 byte followed by remainder */ + if (cfg_do_msgmore && len > 1) { + iov.iov_len = 1; + if (!__send_one(fd, &msg, MSG_MORE)) + error(1, 0, "send 1B failed"); + + iov.iov_base++; + iov.iov_len = len - 1; + } + + return __send_one(fd, &msg, 0); +} + +static int recv_one(int fd, int flags) +{ + int ret; + + ret = recv(fd, buf, sizeof(buf), flags); + if (ret == -1 && errno == EAGAIN && (flags & MSG_DONTWAIT)) + return 0; + if (ret == -1) + error(1, errno, "recv"); + + return ret; +} + +static void run_one(struct testcase *test, int fdt, int fdr, + struct sockaddr *addr, socklen_t alen) +{ + int i, ret, val, mss; + bool sent; + + fprintf(stderr, "ipv%d tx:%d gso:%d %s\n", + addr->sa_family == AF_INET ? 4 : 6, + test->tlen, test->gso_len, + test->tfail ? "(fail)" : ""); + + val = test->gso_len; + if (cfg_do_setsockopt) { + if (setsockopt(fdt, SOL_UDP, UDP_SEGMENT, &val, sizeof(val))) + error(1, errno, "setsockopt udp segment"); + } + + sent = send_one(fdt, test->tlen, test->gso_len, addr, alen); + if (sent && test->tfail) + error(1, 0, "send succeeded while expecting failure"); + if (!sent && !test->tfail) + error(1, 0, "send failed while expecting success"); + if (!sent) + return; + + mss = addr->sa_family == AF_INET ? CONST_MSS_V4 : CONST_MSS_V6; + + /* Recv all full MSS datagrams */ + for (i = 0; i < test->r_num_mss; i++) { + ret = recv_one(fdr, 0); + if (ret != mss) + error(1, 0, "recv.%d: %d != %d", i, ret, mss); + } + + /* Recv the non-full last datagram, if tlen was not a multiple of mss */ + if (test->r_len_last) { + ret = recv_one(fdr, 0); + if (ret != test->r_len_last) + error(1, 0, "recv.%d: %d != %d (last)", + i, ret, test->r_len_last); + } + + /* Verify received all data */ + ret = recv_one(fdr, MSG_DONTWAIT); + if (ret) + error(1, 0, "recv: unexpected datagram"); +} + +static void run_all(int fdt, int fdr, struct sockaddr *addr, socklen_t alen) +{ + struct testcase *tests, *test; + + tests = addr->sa_family == AF_INET ? testcases_v4 : testcases_v6; + + for (test = tests; test->tlen; test++) { + /* if a specific test is given, then skip all others */ + if (cfg_specific_test_id == -1 || + cfg_specific_test_id == test - tests) + run_one(test, fdt, fdr, addr, alen); + } +} + +static void run_test(struct sockaddr *addr, socklen_t alen) +{ + struct timeval tv = { .tv_usec = 100 * 1000 }; + int fdr, fdt, val; + + fdr = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fdr == -1) + error(1, errno, "socket r"); + + if (bind(fdr, addr, alen)) + error(1, errno, "bind"); + + /* Have tests fail quickly instead of hang */ + if (setsockopt(fdr, SOL_SOCKET, SO_RCVTIMEO, &tv, sizeof(tv))) + error(1, errno, "setsockopt rcv timeout"); + + fdt = socket(addr->sa_family, SOCK_DGRAM, 0); + if (fdt == -1) + error(1, errno, "socket t"); + + /* Do not fragment these datagrams: only succeed if GSO works */ + set_pmtu_discover(fdt, addr->sa_family == AF_INET); + + if (cfg_do_connectionless) { + set_device_mtu(fdt, CONST_MTU_TEST); + run_all(fdt, fdr, addr, alen); + } + + if (cfg_do_connected) { + set_device_mtu(fdt, CONST_MTU_TEST + 100); + set_route_mtu(CONST_MTU_TEST, addr->sa_family == AF_INET); + + if (connect(fdt, addr, alen)) + error(1, errno, "connect"); + + val = get_path_mtu(fdt, addr->sa_family == AF_INET); + if (val != CONST_MTU_TEST) + error(1, 0, "bad path mtu %u\n", val); + + run_all(fdt, fdr, addr, 0 /* use connected addr */); + } + + if (close(fdt)) + error(1, errno, "close t"); + if (close(fdr)) + error(1, errno, "close r"); +} + +static void run_test_v4(void) +{ + struct sockaddr_in addr = {0}; + + addr.sin_family = AF_INET; + addr.sin_port = htons(cfg_port); + addr.sin_addr = addr4; + + run_test((void *)&addr, sizeof(addr)); +} + +static void run_test_v6(void) +{ + struct sockaddr_in6 addr = {0}; + + addr.sin6_family = AF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = addr6; + + run_test((void *)&addr, sizeof(addr)); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "46cCmst:")) != -1) { + switch (c) { + case '4': + cfg_do_ipv4 = true; + break; + case '6': + cfg_do_ipv6 = true; + break; + case 'c': + cfg_do_connected = true; + break; + case 'C': + cfg_do_connectionless = true; + break; + case 'm': + cfg_do_msgmore = true; + break; + case 's': + cfg_do_setsockopt = true; + break; + case 't': + cfg_specific_test_id = strtoul(optarg, NULL, 0); + break; + default: + error(1, 0, "%s: parse error", argv[0]); + } + } +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + if (cfg_do_ipv4) + run_test_v4(); + if (cfg_do_ipv6) + run_test_v6(); + + fprintf(stderr, "OK\n"); + return 0; +} diff --git a/tools/testing/selftests/net/udpgso.sh b/tools/testing/selftests/net/udpgso.sh new file mode 100755 index 000000000000..fec24f584fe9 --- /dev/null +++ b/tools/testing/selftests/net/udpgso.sh @@ -0,0 +1,29 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgso regression tests + +echo "ipv4 cmsg" +./in_netns.sh ./udpgso -4 -C + +echo "ipv4 setsockopt" +./in_netns.sh ./udpgso -4 -C -s + +echo "ipv6 cmsg" +./in_netns.sh ./udpgso -6 -C + +echo "ipv6 setsockopt" +./in_netns.sh ./udpgso -6 -C -s + +echo "ipv4 connected" +./in_netns.sh ./udpgso -4 -c + +# blocked on 2nd loopback address +# echo "ipv6 connected" +# ./in_netns.sh ./udpgso -6 -c + +echo "ipv4 msg_more" +./in_netns.sh ./udpgso -4 -C -m + +echo "ipv6 msg_more" +./in_netns.sh ./udpgso -6 -C -m diff --git a/tools/testing/selftests/net/udpgso_bench.sh b/tools/testing/selftests/net/udpgso_bench.sh new file mode 100755 index 000000000000..792fa4d0285e --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench.sh @@ -0,0 +1,74 @@ +#!/bin/sh +# SPDX-License-Identifier: GPL-2.0 +# +# Run a series of udpgso benchmarks + +wake_children() { + local -r jobs="$(jobs -p)" + + if [[ "${jobs}" != "" ]]; then + kill -1 ${jobs} 2>/dev/null + fi +} +trap wake_children EXIT + +run_one() { + local -r args=$@ + + ./udpgso_bench_rx & + ./udpgso_bench_rx -t & + + ./udpgso_bench_tx ${args} +} + +run_in_netns() { + local -r args=$@ + + ./in_netns.sh $0 __subprocess ${args} +} + +run_udp() { + local -r args=$@ + + echo "udp" + run_in_netns ${args} + + echo "udp gso" + run_in_netns ${args} -S + + echo "udp gso zerocopy" + run_in_netns ${args} -S -z +} + +run_tcp() { + local -r args=$@ + + echo "tcp" + run_in_netns ${args} -t + + echo "tcp zerocopy" + run_in_netns ${args} -t -z +} + +run_all() { + local -r core_args="-l 4" + local -r ipv4_args="${core_args} -4 -D 127.0.0.1" + local -r ipv6_args="${core_args} -6 -D ::1" + + echo "ipv4" + run_tcp "${ipv4_args}" + run_udp "${ipv4_args}" + + echo "ipv6" + run_tcp "${ipv4_args}" + run_udp "${ipv6_args}" +} + +if [[ $# -eq 0 ]]; then + run_all +elif [[ $1 == "__subprocess" ]]; then + shift + run_one $@ +else + run_in_netns $@ +fi diff --git a/tools/testing/selftests/net/udpgso_bench_rx.c b/tools/testing/selftests/net/udpgso_bench_rx.c new file mode 100644 index 000000000000..727cf67a3f75 --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench_rx.c @@ -0,0 +1,265 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <error.h> +#include <errno.h> +#include <limits.h> +#include <linux/errqueue.h> +#include <linux/if_packet.h> +#include <linux/socket.h> +#include <linux/sockios.h> +#include <net/ethernet.h> +#include <net/if.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/tcp.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdint.h> +#include <stdlib.h> +#include <string.h> +#include <sys/ioctl.h> +#include <sys/socket.h> +#include <sys/stat.h> +#include <sys/time.h> +#include <sys/types.h> +#include <sys/wait.h> +#include <unistd.h> + +static int cfg_port = 8000; +static bool cfg_tcp; +static bool cfg_verify; + +static bool interrupted; +static unsigned long packets, bytes; + +static void sigint_handler(int signum) +{ + if (signum == SIGINT) + interrupted = true; +} + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static void do_poll(int fd) +{ + struct pollfd pfd; + int ret; + + pfd.events = POLLIN; + pfd.revents = 0; + pfd.fd = fd; + + do { + ret = poll(&pfd, 1, 10); + if (ret == -1) + error(1, errno, "poll"); + if (ret == 0) + continue; + if (pfd.revents != POLLIN) + error(1, errno, "poll: 0x%x expected 0x%x\n", + pfd.revents, POLLIN); + } while (!ret && !interrupted); +} + +static int do_socket(bool do_tcp) +{ + struct sockaddr_in6 addr = {0}; + int fd, val; + + fd = socket(PF_INET6, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket"); + + val = 1 << 21; + if (setsockopt(fd, SOL_SOCKET, SO_RCVBUF, &val, sizeof(val))) + error(1, errno, "setsockopt rcvbuf"); + val = 1; + if (setsockopt(fd, SOL_SOCKET, SO_REUSEPORT, &val, sizeof(val))) + error(1, errno, "setsockopt reuseport"); + + addr.sin6_family = PF_INET6; + addr.sin6_port = htons(cfg_port); + addr.sin6_addr = in6addr_any; + if (bind(fd, (void *) &addr, sizeof(addr))) + error(1, errno, "bind"); + + if (do_tcp) { + int accept_fd = fd; + + if (listen(accept_fd, 1)) + error(1, errno, "listen"); + + do_poll(accept_fd); + + fd = accept(accept_fd, NULL, NULL); + if (fd == -1) + error(1, errno, "accept"); + if (close(accept_fd)) + error(1, errno, "close accept fd"); + } + + return fd; +} + +/* Flush all outstanding bytes for the tcp receive queue */ +static void do_flush_tcp(int fd) +{ + int ret; + + while (true) { + /* MSG_TRUNC flushes up to len bytes */ + ret = recv(fd, NULL, 1 << 21, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "flush"); + if (ret == 0) { + /* client detached */ + exit(0); + } + + packets++; + bytes += ret; + } + +} + +static char sanitized_char(char val) +{ + return (val >= 'a' && val <= 'z') ? val : '.'; +} + +static void do_verify_udp(const char *data, int len) +{ + char cur = data[0]; + int i; + + /* verify contents */ + if (cur < 'a' || cur > 'z') + error(1, 0, "data initial byte out of range"); + + for (i = 1; i < len; i++) { + if (cur == 'z') + cur = 'a'; + else + cur++; + + if (data[i] != cur) + error(1, 0, "data[%d]: len %d, %c(%hhu) != %c(%hhu)\n", + i, len, + sanitized_char(data[i]), data[i], + sanitized_char(cur), cur); + } +} + +/* Flush all outstanding datagrams. Verify first few bytes of each. */ +static void do_flush_udp(int fd) +{ + static char rbuf[ETH_DATA_LEN]; + int ret, len, budget = 256; + + len = cfg_verify ? sizeof(rbuf) : 0; + while (budget--) { + /* MSG_TRUNC will make return value full datagram length */ + ret = recv(fd, rbuf, len, MSG_TRUNC | MSG_DONTWAIT); + if (ret == -1 && errno == EAGAIN) + return; + if (ret == -1) + error(1, errno, "recv"); + if (len) { + if (ret == 0) + error(1, errno, "recv: 0 byte datagram\n"); + + do_verify_udp(rbuf, ret); + } + + packets++; + bytes += ret; + } +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [-tv] [-p port]", filepath); +} + +static void parse_opts(int argc, char **argv) +{ + int c; + + while ((c = getopt(argc, argv, "ptv")) != -1) { + switch (c) { + case 'p': + cfg_port = htons(strtoul(optarg, NULL, 0)); + break; + case 't': + cfg_tcp = true; + break; + case 'v': + cfg_verify = true; + break; + } + } + + if (optind != argc) + usage(argv[0]); + + if (cfg_tcp && cfg_verify) + error(1, 0, "TODO: implement verify mode for tcp"); +} + +static void do_recv(void) +{ + unsigned long tnow, treport; + int fd; + + fd = do_socket(cfg_tcp); + + treport = gettimeofday_ms() + 1000; + do { + do_poll(fd); + + if (cfg_tcp) + do_flush_tcp(fd); + else + do_flush_udp(fd); + + tnow = gettimeofday_ms(); + if (tnow > treport) { + if (packets) + fprintf(stderr, + "%s rx: %6lu MB/s %8lu calls/s\n", + cfg_tcp ? "tcp" : "udp", + bytes >> 20, packets); + bytes = packets = 0; + treport = tnow + 1000; + } + + } while (!interrupted); + + if (close(fd)) + error(1, errno, "close"); +} + +int main(int argc, char **argv) +{ + parse_opts(argc, argv); + + signal(SIGINT, sigint_handler); + + do_recv(); + + return 0; +} diff --git a/tools/testing/selftests/net/udpgso_bench_tx.c b/tools/testing/selftests/net/udpgso_bench_tx.c new file mode 100644 index 000000000000..e821564053cf --- /dev/null +++ b/tools/testing/selftests/net/udpgso_bench_tx.c @@ -0,0 +1,420 @@ +// SPDX-License-Identifier: GPL-2.0 + +#define _GNU_SOURCE + +#include <arpa/inet.h> +#include <errno.h> +#include <error.h> +#include <netinet/if_ether.h> +#include <netinet/in.h> +#include <netinet/ip.h> +#include <netinet/ip6.h> +#include <netinet/udp.h> +#include <poll.h> +#include <sched.h> +#include <signal.h> +#include <stdbool.h> +#include <stdio.h> +#include <stdlib.h> +#include <string.h> +#include <sys/socket.h> +#include <sys/time.h> +#include <sys/types.h> +#include <unistd.h> + +#ifndef ETH_MAX_MTU +#define ETH_MAX_MTU 0xFFFFU +#endif + +#ifndef UDP_SEGMENT +#define UDP_SEGMENT 103 +#endif + +#ifndef SO_ZEROCOPY +#define SO_ZEROCOPY 60 +#endif + +#ifndef MSG_ZEROCOPY +#define MSG_ZEROCOPY 0x4000000 +#endif + +#define NUM_PKT 100 + +static bool cfg_cache_trash; +static int cfg_cpu = -1; +static int cfg_connected = true; +static int cfg_family = PF_UNSPEC; +static uint16_t cfg_mss; +static int cfg_payload_len = (1472 * 42); +static int cfg_port = 8000; +static int cfg_runtime_ms = -1; +static bool cfg_segment; +static bool cfg_sendmmsg; +static bool cfg_tcp; +static bool cfg_zerocopy; + +static socklen_t cfg_alen; +static struct sockaddr_storage cfg_dst_addr; + +static bool interrupted; +static char buf[NUM_PKT][ETH_MAX_MTU]; + +static void sigint_handler(int signum) +{ + if (signum == SIGINT) + interrupted = true; +} + +static unsigned long gettimeofday_ms(void) +{ + struct timeval tv; + + gettimeofday(&tv, NULL); + return (tv.tv_sec * 1000) + (tv.tv_usec / 1000); +} + +static int set_cpu(int cpu) +{ + cpu_set_t mask; + + CPU_ZERO(&mask); + CPU_SET(cpu, &mask); + if (sched_setaffinity(0, sizeof(mask), &mask)) + error(1, 0, "setaffinity %d", cpu); + + return 0; +} + +static void setup_sockaddr(int domain, const char *str_addr, void *sockaddr) +{ + struct sockaddr_in6 *addr6 = (void *) sockaddr; + struct sockaddr_in *addr4 = (void *) sockaddr; + + switch (domain) { + case PF_INET: + addr4->sin_family = AF_INET; + addr4->sin_port = htons(cfg_port); + if (inet_pton(AF_INET, str_addr, &(addr4->sin_addr)) != 1) + error(1, 0, "ipv4 parse error: %s", str_addr); + break; + case PF_INET6: + addr6->sin6_family = AF_INET6; + addr6->sin6_port = htons(cfg_port); + if (inet_pton(AF_INET6, str_addr, &(addr6->sin6_addr)) != 1) + error(1, 0, "ipv6 parse error: %s", str_addr); + break; + default: + error(1, 0, "illegal domain"); + } +} + +static void flush_zerocopy(int fd) +{ + struct msghdr msg = {0}; /* flush */ + int ret; + + while (1) { + ret = recvmsg(fd, &msg, MSG_ERRQUEUE); + if (ret == -1 && errno == EAGAIN) + break; + if (ret == -1) + error(1, errno, "errqueue"); + if (msg.msg_flags != (MSG_ERRQUEUE | MSG_CTRUNC)) + error(1, 0, "errqueue: flags 0x%x\n", msg.msg_flags); + msg.msg_flags = 0; + } +} + +static int send_tcp(int fd, char *data) +{ + int ret, done = 0, count = 0; + + while (done < cfg_payload_len) { + ret = send(fd, data + done, cfg_payload_len - done, + cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "write"); + + done += ret; + count++; + } + + return count; +} + +static int send_udp(int fd, char *data) +{ + int ret, total_len, len, count = 0; + + total_len = cfg_payload_len; + + while (total_len) { + len = total_len < cfg_mss ? total_len : cfg_mss; + + ret = sendto(fd, data, len, cfg_zerocopy ? MSG_ZEROCOPY : 0, + cfg_connected ? NULL : (void *)&cfg_dst_addr, + cfg_connected ? 0 : cfg_alen); + if (ret == -1) + error(1, errno, "write"); + if (ret != len) + error(1, errno, "write: %uB != %uB\n", ret, len); + + total_len -= len; + count++; + } + + return count; +} + +static int send_udp_sendmmsg(int fd, char *data) +{ + const int max_nr_msg = ETH_MAX_MTU / ETH_DATA_LEN; + struct mmsghdr mmsgs[max_nr_msg]; + struct iovec iov[max_nr_msg]; + unsigned int off = 0, left; + int i = 0, ret; + + memset(mmsgs, 0, sizeof(mmsgs)); + + left = cfg_payload_len; + while (left) { + if (i == max_nr_msg) + error(1, 0, "sendmmsg: exceeds max_nr_msg"); + + iov[i].iov_base = data + off; + iov[i].iov_len = cfg_mss < left ? cfg_mss : left; + + mmsgs[i].msg_hdr.msg_iov = iov + i; + mmsgs[i].msg_hdr.msg_iovlen = 1; + + off += iov[i].iov_len; + left -= iov[i].iov_len; + i++; + } + + ret = sendmmsg(fd, mmsgs, i, cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "sendmmsg"); + + return ret; +} + +static void send_udp_segment_cmsg(struct cmsghdr *cm) +{ + uint16_t *valp; + + cm->cmsg_level = SOL_UDP; + cm->cmsg_type = UDP_SEGMENT; + cm->cmsg_len = CMSG_LEN(sizeof(cfg_mss)); + valp = (void *)CMSG_DATA(cm); + *valp = cfg_mss; +} + +static int send_udp_segment(int fd, char *data) +{ + char control[CMSG_SPACE(sizeof(cfg_mss))] = {0}; + struct msghdr msg = {0}; + struct iovec iov = {0}; + int ret; + + iov.iov_base = data; + iov.iov_len = cfg_payload_len; + + msg.msg_iov = &iov; + msg.msg_iovlen = 1; + + msg.msg_control = control; + msg.msg_controllen = sizeof(control); + send_udp_segment_cmsg(CMSG_FIRSTHDR(&msg)); + + msg.msg_name = (void *)&cfg_dst_addr; + msg.msg_namelen = cfg_alen; + + ret = sendmsg(fd, &msg, cfg_zerocopy ? MSG_ZEROCOPY : 0); + if (ret == -1) + error(1, errno, "sendmsg"); + if (ret != iov.iov_len) + error(1, 0, "sendmsg: %u != %lu\n", ret, iov.iov_len); + + return 1; +} + +static void usage(const char *filepath) +{ + error(1, 0, "Usage: %s [-46cmStuz] [-C cpu] [-D dst ip] [-l secs] [-p port] [-s sendsize]", + filepath); +} + +static void parse_opts(int argc, char **argv) +{ + int max_len, hdrlen; + int c; + + while ((c = getopt(argc, argv, "46cC:D:l:mp:s:Stuz")) != -1) { + switch (c) { + case '4': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET; + cfg_alen = sizeof(struct sockaddr_in); + break; + case '6': + if (cfg_family != PF_UNSPEC) + error(1, 0, "Pass one of -4 or -6"); + cfg_family = PF_INET6; + cfg_alen = sizeof(struct sockaddr_in6); + break; + case 'c': + cfg_cache_trash = true; + break; + case 'C': + cfg_cpu = strtol(optarg, NULL, 0); + break; + case 'D': + setup_sockaddr(cfg_family, optarg, &cfg_dst_addr); + break; + case 'l': + cfg_runtime_ms = strtoul(optarg, NULL, 10) * 1000; + break; + case 'm': + cfg_sendmmsg = true; + break; + case 'p': + cfg_port = strtoul(optarg, NULL, 0); + break; + case 's': + cfg_payload_len = strtoul(optarg, NULL, 0); + break; + case 'S': + cfg_segment = true; + break; + case 't': + cfg_tcp = true; + break; + case 'u': + cfg_connected = false; + break; + case 'z': + cfg_zerocopy = true; + break; + } + } + + if (optind != argc) + usage(argv[0]); + + if (cfg_family == PF_UNSPEC) + error(1, 0, "must pass one of -4 or -6"); + if (cfg_tcp && !cfg_connected) + error(1, 0, "connectionless tcp makes no sense"); + if (cfg_segment && cfg_sendmmsg) + error(1, 0, "cannot combine segment offload and sendmmsg"); + + if (cfg_family == PF_INET) + hdrlen = sizeof(struct iphdr) + sizeof(struct udphdr); + else + hdrlen = sizeof(struct ip6_hdr) + sizeof(struct udphdr); + + cfg_mss = ETH_DATA_LEN - hdrlen; + max_len = ETH_MAX_MTU - hdrlen; + + if (cfg_payload_len > max_len) + error(1, 0, "payload length %u exceeds max %u", + cfg_payload_len, max_len); +} + +static void set_pmtu_discover(int fd, bool is_ipv4) +{ + int level, name, val; + + if (is_ipv4) { + level = SOL_IP; + name = IP_MTU_DISCOVER; + val = IP_PMTUDISC_DO; + } else { + level = SOL_IPV6; + name = IPV6_MTU_DISCOVER; + val = IPV6_PMTUDISC_DO; + } + + if (setsockopt(fd, level, name, &val, sizeof(val))) + error(1, errno, "setsockopt path mtu"); +} + +int main(int argc, char **argv) +{ + unsigned long num_msgs, num_sends; + unsigned long tnow, treport, tstop; + int fd, i, val; + + parse_opts(argc, argv); + + if (cfg_cpu > 0) + set_cpu(cfg_cpu); + + for (i = 0; i < sizeof(buf[0]); i++) + buf[0][i] = 'a' + (i % 26); + for (i = 1; i < NUM_PKT; i++) + memcpy(buf[i], buf[0], sizeof(buf[0])); + + signal(SIGINT, sigint_handler); + + fd = socket(cfg_family, cfg_tcp ? SOCK_STREAM : SOCK_DGRAM, 0); + if (fd == -1) + error(1, errno, "socket"); + + if (cfg_zerocopy) { + val = 1; + if (setsockopt(fd, SOL_SOCKET, SO_ZEROCOPY, &val, sizeof(val))) + error(1, errno, "setsockopt zerocopy"); + } + + if (cfg_connected && + connect(fd, (void *)&cfg_dst_addr, cfg_alen)) + error(1, errno, "connect"); + + if (cfg_segment) + set_pmtu_discover(fd, cfg_family == PF_INET); + + num_msgs = num_sends = 0; + tnow = gettimeofday_ms(); + tstop = tnow + cfg_runtime_ms; + treport = tnow + 1000; + + i = 0; + do { + if (cfg_tcp) + num_sends += send_tcp(fd, buf[i]); + else if (cfg_segment) + num_sends += send_udp_segment(fd, buf[i]); + else if (cfg_sendmmsg) + num_sends += send_udp_sendmmsg(fd, buf[i]); + else + num_sends += send_udp(fd, buf[i]); + num_msgs++; + + if (cfg_zerocopy && ((num_msgs & 0xF) == 0)) + flush_zerocopy(fd); + + tnow = gettimeofday_ms(); + if (tnow > treport) { + fprintf(stderr, + "%s tx: %6lu MB/s %8lu calls/s %6lu msg/s\n", + cfg_tcp ? "tcp" : "udp", + (num_msgs * cfg_payload_len) >> 20, + num_sends, num_msgs); + num_msgs = num_sends = 0; + treport = tnow + 1000; + } + + /* cold cache when writing buffer */ + if (cfg_cache_trash) + i = ++i < NUM_PKT ? i : 0; + + } while (!interrupted && (cfg_runtime_ms == -1 || tnow < tstop)); + + if (close(fd)) + error(1, errno, "close"); + + return 0; +} diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json index 93cf8fea8ae7..3a2f51fc7fd4 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/csum.json @@ -398,13 +398,83 @@ 255 ] ], - "cmdUnderTest": "for i in `seq 1 32`; do cmd=\"action csum tcp continue index $i \"; args=\"$args$cmd\"; done && $TC actions add $args", - "expExitCode": "255", + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", "verifyCmd": "$TC actions ls action csum", "matchPattern": "^[ \t]+index [0-9]* ref", "matchCount": "32", "teardown": [ "$TC actions flush action csum" ] + }, + { + "id": "b4e9", + "name": "Delete batch of 32 csum actions", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action csum", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "0015", + "name": "Add batch of 32 csum tcp actions with large cookies", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions ls action csum", + "matchPattern": "^[ \t]+index [0-9]* ref", + "matchCount": "32", + "teardown": [ + "$TC actions flush action csum" + ] + }, + { + "id": "989e", + "name": "Delete batch of 32 csum actions with large cookies", + "category": [ + "actions", + "csum" + ], + "setup": [ + [ + "$TC actions flush action csum", + 0, + 1, + 255 + ], + "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum tcp continue index \\$i cookie aaabbbcccdddeee \\\"; args=\"\\$args\\$cmd\"; done && $TC actions add \\$args\"" + ], + "cmdUnderTest": "bash -c \"for i in \\`seq 1 32\\`; do cmd=\\\"action csum index \\$i \\\"; args=\"\\$args\\$cmd\"; done && $TC actions del \\$args\"", + "expExitCode": "0", + "verifyCmd": "$TC actions list action csum", + "matchPattern": "^[ \t]+index [0-9]+ ref", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json index 9f34f0753969..03777730ef29 100644 --- a/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/ife.json @@ -1,7 +1,7 @@ [ { - "id": "a568", - "name": "Add action with ife type", + "id": "7682", + "name": "Create valid ife encode action with mark and pass control", "category": [ "actions", "ife" @@ -12,21 +12,710 @@ 0, 1, 255 - ], - "$TC actions add action ife encode type 0xDEAD index 1" + ] ], - "cmdUnderTest": "$TC actions get action ife index 1", + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "ef47", + "name": "Create valid ife encode action with mark and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 10 pipe index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "df43", + "name": "Create valid ife encode action with mark and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark continue index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*allow mark.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "e4cf", + "name": "Create valid ife encode action with mark and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 789 drop index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*use mark 789.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "ccba", + "name": "Create valid ife encode action with mark and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 656768 reclassify index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 656768.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "a1cf", + "name": "Create valid ife encode action with mark and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 65 jump 1 index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 2", + "matchPattern": "action order [0-9]*: ife encode action jump 1.*type 0xED3E.*use mark 65.*index 2", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "cb3d", + "name": "Create valid ife encode action with mark value at 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295 reclassify index 90", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use mark 4294967295.*index 90", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "1efb", + "name": "Create ife encode action with mark value exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 4294967295999 pipe index 90", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 90", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use mark 4294967295999.*index 90", + "matchCount": "0", + "teardown": [] + }, + { + "id": "95ed", + "name": "Create valid ife encode action with prio and pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio pass index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow prio.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "aa17", + "name": "Create valid ife encode action with prio and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 7 pipe index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 7.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "74c7", + "name": "Create valid ife encode action with prio and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 3 continue index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use prio 3.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "7a97", + "name": "Create valid ife encode action with prio and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio drop index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow prio.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "f66b", + "name": "Create valid ife encode action with prio and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 998877 reclassify index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 998877.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "3056", + "name": "Create valid ife encode action with prio and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 998877 jump 10 index 9", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 9", + "matchPattern": "action order [0-9]*: ife encode action jump 10.*type 0xED3E.*use prio 998877.*index 9", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "7dd3", + "name": "Create valid ife encode action with prio value at 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 4294967295 reclassify index 99", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 99", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 4294967295.*index 99", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "2ca1", + "name": "Create ife encode action with prio value exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 4294967298 pipe index 99", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 99", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use prio 4294967298.*index 99", + "matchCount": "0", + "teardown": [] + }, + { + "id": "05bb", + "name": "Create valid ife encode action with tcindex and pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "ce65", + "name": "Create valid ife encode action with tcindex and pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 111 pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 111.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "09cd", + "name": "Create valid ife encode action with tcindex and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "8eb5", + "name": "Create valid ife encode action with tcindex and continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 1 continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action continue.*type 0xED3E.*use tcindex 1.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "451a", + "name": "Create valid ife encode action with tcindex and drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex drop index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action drop.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d76c", + "name": "Create valid ife encode action with tcindex and reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex reclassify index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "e731", + "name": "Create valid ife encode action with tcindex and jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex jump 999 index 77", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 77", + "matchPattern": "action order [0-9]*: ife encode action jump 999.*type 0xED3E.*allow tcindex.*index 77", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "b7b8", + "name": "Create valid ife encode action with tcindex value at 16-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 65535 pass index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*use tcindex 65535.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action skbedit" + ] + }, + { + "id": "d0d8", + "name": "Create ife encode action with tcindex value exceeding 16-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use tcindex 65539 pipe index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*use tcindex 65539.*index 1", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2a9c", + "name": "Create valid ife encode action with mac src parameter", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark src 00:11:22:33:44:55 pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow mark src 00:11:22:33:44:55.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "cf5c", + "name": "Create valid ife encode action with mac dst parameter", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 9876 dst 00:11:22:33:44:55 reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xED3E.*use prio 9876 dst 00:11:22:33:44:55.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "2353", + "name": "Create valid ife encode action with mac src and mac dst parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow tcindex src 00:aa:bb:cc:dd:ee dst 00:11:22:33:44:55 pass index 11", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 11", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow tcindex dst 00:11:22:33:44:55 src 00:aa:bb:cc:dd:ee .*index 11", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "552c", + "name": "Create valid ife encode action with mark and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use mark 7 type 0xfefe pass index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xDEAD", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xFEFE.*use mark 7.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "0421", + "name": "Create valid ife encode action with prio and type parameters", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode use prio 444 type 0xabba pipe index 21", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 21", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xABBA.*use prio 444.*index 21", "matchCount": "1", "teardown": [ "$TC actions flush action ife" ] }, { - "id": "b983", - "name": "Add action without ife type", + "id": "4017", + "name": "Create valid ife encode action with tcindex and type parameters", "category": [ "actions", "ife" @@ -37,16 +726,339 @@ 0, 1, 255 - ], - "$TC actions add action ife encode index 1" + ] ], - "cmdUnderTest": "$TC actions get action ife index 1", + "cmdUnderTest": "$TC actions add action ife encode use tcindex 5000 type 0xabcd reclassify index 21", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 21", + "matchPattern": "action order [0-9]*: ife encode action reclassify.*type 0xABCD.*use tcindex 5000.*index 21", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "fac3", + "name": "Create valid ife encode action with index at 32-bit maximnum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 4294967295", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7c25", + "name": "Create valid ife decode action with pass control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode pass index 1", "expExitCode": "0", "verifyCmd": "$TC actions get action ife index 1", - "matchPattern": "type 0xED3E", + "matchPattern": "action order [0-9]*: ife decode action pass.*type 0x0.*allow mark allow tcindex allow prio.*index 1", "matchCount": "1", "teardown": [ "$TC actions flush action ife" ] + }, + { + "id": "dccb", + "name": "Create valid ife decode action with pipe control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode pipe index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action pipe.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "7bb9", + "name": "Create valid ife decode action with continue control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode continue index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action continue.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "d9ad", + "name": "Create valid ife decode action with drop control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode drop index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action drop.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "219f", + "name": "Create valid ife decode action with reclassify control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode reclassify index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action reclassify.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "8f44", + "name": "Create valid ife decode action with jump control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife decode jump 10 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 1", + "matchPattern": "action order [0-9]*: ife decode action jump 10.*type 0x0.*allow mark allow tcindex allow prio.*index 1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "56cf", + "name": "Create ife encode action with index exceeding 32-bit maximum", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark pass index 4294967295999", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4294967295999", + "matchPattern": "action order [0-9]*: ife encode action pass.*type 0xED3E.*allow mark.*index 4294967295999", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ee94", + "name": "Create ife encode action with invalid control", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow mark kuka index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action kuka.*type 0xED3E.*allow mark.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "b330", + "name": "Create ife encode action with cookie", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio pipe index 4 cookie aabbccddeeff112233445566778800a1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow prio.*index 4.*cookie aabbccddeeff112233445566778800a1", + "matchCount": "1", + "teardown": [ + "$TC actions flush action ife" + ] + }, + { + "id": "bbc0", + "name": "Create ife encode action with invalid argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow foo pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0xED3E.*allow foo.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "d54a", + "name": "Create ife encode action with invalid type argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio type 70000 pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*type 0x11170.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "7ee0", + "name": "Create ife encode action with invalid mac src argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio src 00:11:22:33:44:pp pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] + }, + { + "id": "0a7d", + "name": "Create ife encode action with invalid mac dst argument", + "category": [ + "actions", + "ife" + ], + "setup": [ + [ + "$TC actions flush action ife", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action ife encode allow prio dst 00.111-22:33:44:aa pipe index 4", + "expExitCode": "255", + "verifyCmd": "$TC actions get action ife index 4", + "matchPattern": "action order [0-9]*: ife encode action pipe.*allow prio.*index 4", + "matchCount": "0", + "teardown": [] } ] diff --git a/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json new file mode 100644 index 000000000000..3aca33c00039 --- /dev/null +++ b/tools/testing/selftests/tc-testing/tc-tests/actions/sample.json @@ -0,0 +1,588 @@ +[ + { + "id": "9784", + "name": "Add valid sample action with mandatory arguments", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 10 group 1 index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/10 group 1.*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "5c91", + "name": "Add valid sample action with mandatory arguments and continue control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 700 group 2 continue index 2", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 2", + "matchPattern": "action order [0-9]+: sample rate 1/700 group 2 continue.*index 2 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "334b", + "name": "Add valid sample action with mandatory arguments and drop control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 10000 group 11 drop index 22", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/10000 group 11 drop.*index 22 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "da69", + "name": "Add valid sample action with mandatory arguments and reclassify control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 20000 group 72 reclassify index 100", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/20000 group 72 reclassify.*index 100 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "13ce", + "name": "Add valid sample action with mandatory arguments and pipe control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 20 group 2 pipe index 100", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/20 group 2 pipe.*index 100 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "1886", + "name": "Add valid sample action with mandatory arguments and jump control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 700 group 25 jump 4 index 200", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 200", + "matchPattern": "action order [0-9]+: sample rate 1/700 group 25 jump 4.*index 200 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "b6d4", + "name": "Add sample action with mandatory arguments and invalid control action", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 200000 group 52 foo index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/200000 group 52 foo.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "a874", + "name": "Add invalid sample action without mandatory arguments", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "ac01", + "name": "Add invalid sample action without mandatory argument rate", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample group 10 index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample.*group 10.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "4203", + "name": "Add invalid sample action without mandatory argument group", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 100 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "14a7", + "name": "Add invalid sample action without mandatory argument group", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 100 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/100.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "8f2e", + "name": "Add valid sample action with trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 1024 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 1024 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "45f8", + "name": "Add sample action with maximum rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294967295 group 4 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/4294967295 group 4 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "ad0c", + "name": "Add sample action with maximum trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 16000 group 4 trunc 4294967295 index 10", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/16000 group 4 trunc_size 4294967295 pipe.*index 10 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "83a9", + "name": "Add sample action with maximum group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294 group 4294967295 index 1", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 1", + "matchPattern": "action order [0-9]+: sample rate 1/4294 group 4294967295 pipe.*index 1 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "ed27", + "name": "Add sample action with invalid rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4294967296 group 4 index 10", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 10", + "matchPattern": "action order [0-9]+: sample rate 1/4294967296 group 4 pipe.*index 10 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2eae", + "name": "Add sample action with invalid group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 4098 group 5294967299 continue index 1", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 1", + "matchPattern": "action order [0-9]+: sample rate 1/4098 group 5294967299 continue.*index 1 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "6ff3", + "name": "Add sample action with invalid trunc size", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 trunc 112233445566 index 11", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 11", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 trunc_size 112233445566.*index 11 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "2b2a", + "name": "Add sample action with invalid index", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 5294967299", + "expExitCode": "255", + "verifyCmd": "$TC actions get action sample index 5294967299", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 5294967299 ref", + "matchCount": "0", + "teardown": [] + }, + { + "id": "dee2", + "name": "Add sample action with maximum allowed index", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 4294967295", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 4294967295", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 4294967295 ref", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "560e", + "name": "Add sample action with cookie", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ] + ], + "cmdUnderTest": "$TC actions add action sample rate 1024 group 4 index 45 cookie aabbccdd", + "expExitCode": "0", + "verifyCmd": "$TC actions get action sample index 45", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 4 pipe.*index 45.*cookie aabbccdd", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "704a", + "name": "Replace existing sample action with new rate argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 2048 group 4 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/2048 group 4 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "60eb", + "name": "Replace existing sample action with new group argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "2cce", + "name": "Replace existing sample action with new trunc argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 trunc 48 index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 trunc 64 index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 trunc_size 64 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + }, + { + "id": "59d1", + "name": "Replace existing sample action with new control argument", + "category": [ + "actions", + "sample" + ], + "setup": [ + [ + "$TC actions flush action sample", + 0, + 1, + 255 + ], + "$TC actions add action sample rate 1024 group 4 reclassify index 4" + ], + "cmdUnderTest": "$TC actions replace action sample rate 1024 group 7 pipe index 4", + "expExitCode": "0", + "verifyCmd": "$TC actions list action sample", + "matchPattern": "action order [0-9]+: sample rate 1/1024 group 7 pipe.*index 4", + "matchCount": "1", + "teardown": [ + "$TC actions flush action sample" + ] + } +] |