- 03 Jul, 2017 25 commits
-
-
Daniel Borkmann authored
This work tries to make the semantics and code around the narrower ctx access a bit easier to follow. Right now everything is done inside the .is_valid_access(). Offset matching is done differently for read/write types, meaning writes don't support narrower access and thus matching only on offsetof(struct foo, bar) is enough whereas for read case that supports narrower access we must check for offsetof(struct foo, bar) + offsetof(struct foo, bar) + sizeof(<bar>) - 1 for each of the cases. For read cases of individual members that don't support narrower access (like packet pointers or skb->cb[] case which has its own narrow access logic), we check as usual only offsetof(struct foo, bar) like in write case. Then, for the case where narrower access is allowed, we also need to set the aux info for the access. Meaning, ctx_field_size and converted_op_size have to be set. First is the original field size e.g. sizeof(<bar>) as in above example from the user facing ctx, and latter one is the target size after actual rewrite happened, thus for the kernel facing ctx. Also here we need the range match and we need to keep track changing convert_ctx_access() and converted_op_size from is_valid_access() as both are not at the same location. We can simplify the code a bit: check_ctx_access() becomes simpler in that we only store ctx_field_size as a meta data and later in convert_ctx_accesses() we fetch the target_size right from the location where we do convert. Should the verifier be misconfigured we do reject for BPF_WRITE cases or target_size that are not provided. For the subsystems, we always work on ranges in is_valid_access() and add small helpers for ranges and narrow access, convert_ctx_accesses() sets target_size for the relevant instruction. Signed-off-by:
Daniel Borkmann <daniel@iogearbox.net> Acked-by:
John Fastabend <john.fastabend@gmail.com> Cc: Yonghong Song <yhs@fb.com> Signed-off-by:
David S. Miller <davem@davemloft.net>
-
Daniel Borkmann authored
This work adds a helper that can be used to adjust net room of an skb. The helper is generic and can be further extended in future. Main use case is for having a programmatic way to add/remove room to v4/v6 header options along with cls_bpf on egress and ingress hook of the data path. It reuses most of the infrastructure that we added for the bpf_skb_change_type() helper which can be used in nat64 translations. Similarly, the helper only takes care of adjusting the room so that related data is populated and csum adapted out of the BPF program using it. Signed-off-by:
Alexei Starovoitov <ast@kernel.org> Signed-off-by:
-
Daniel Borkmann authored
Add a small skb_mac_header_len() helper similarly as the skb_network_header_len() we have and replace open coded places in BPF's bpf_skb_change_proto() helper. Will also be used in upcoming work. Signed-off-by:
-
Tore Anderson authored
The HP lt4132 LTE/HSPA+ 4G Module (03f0:a31d) is a rebranded Huawei ME906s-158 device. It, like the ME906s-158, requires the "NDP to end" quirk for correct operation. Signed-off-by:
Tore Anderson <tore@fud.no> Signed-off-by:
-
Matteo Croce authored
In the IPVLAN documentation there is an example command line where the master and slave interface names are inverted. Fix the command line and also add the optional `name' keyword to better describe what the command is doing. v2: added commit message Signed-off-by:
Matteo Croce <mcroce@redhat.com> Signed-off-by:
-
Sabrina Dubroca authored
Commit a985343b ("vxlan: refactor verification and application of configuration") modified vxlan device creation, and replaced the assignment of vxlan->net to src_net with dev_net(netdev) in ->setup(). But dev_net(netdev) is not the same as src_net. At the time ->setup() is called, dev_net hasn't been set yet, so we end up creating the socket for the vxlan device in init_net. Fix this by bringing back the assignment of vxlan->net during device creation. Fixes: a985343b ("vxlan: refactor verification and application of configuration") Signed-off-by:
Sabrina Dubroca <sd@queasysnail.net> Reviewed-by:
Matthias Schiffer <mschiffer@universe-factory.net> Signed-off-by:
-
David S. Miller authored
Lin Yun Sheng says: ==================== Add loopback support in phy_driver and hns ethtool fix This Patch Set add set_loopback in phy_driver and use it to setup loopback when doing ethtool phy self_test. Patch V8: Respin the Patch based on net-next Patch V7: 1. Add comment why resume the phy in hns_nic_config_phy_loopback. 2. Fix a typo error in patch description. Patch V6: Fix Or'ing error code in __lb_setup. Patch V5: Removing non loopback related code change. Patch V4: 1. Remove c45 checking 2. Add -ENOTSUPP when function pointer is null, take mutex in phy_loopback. Patch V3: Calling phy_loopback enable and disable in pair in hns mac driver. Patch V2: 1. Add phy_loopback in phy_device.c. 2. Do error checking and do the read and write once in genphy_loopback. 3. Remove gen10g_loopback in phy_device.c. Patch V1: Initial Submit ==================== Signed-off-by: -
Lin Yun Sheng authored
Use function set_loopback in phy_driver to setup phy loopback when doing ethtool self test. Signed-off-by:
Lin Yun Sheng <linyunsheng@huawei.com> Signed-off-by:
-
Lin Yun Sheng authored
This patch add set_loopback in phy_driver, which is used by MAC driver to enable or disable phy loopback. it also add a generic genphy_loopback function, which use BMCR loopback bit to enable or disable loopback. Signed-off-by:
Andrew Lunn <andrew@lunn.ch> Reviewed-by:
Florian Fainelli <f.fainelli@gmail.com> Signed-off-by:
-
Stephen Rothwell authored
Signed-off-by:
Stephen Rothwell <sfr@canb.auug.org.au> Signed-off-by:
-
Sabrina Dubroca authored
Currently, when the link for $DEV is down, this command succeeds but the address is removed immediately by DAD (1): ip addr add 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800 In the same situation, this will succeed and not remove the address (2): ip addr add 1111::12/64 dev $DEV ip addr change 1111::12/64 dev $DEV valid_lft 3600 preferred_lft 1800 The comment in addrconf_dad_begin() when !IF_READY makes it look like this is the intended behavior, but doesn't explain why: * If the device is not ready: * - keep it tentative if it is a permanent address. * - otherwise, kill it. We clearly cannot prevent userspace from doing (2), but we can make (1) work consistently with (2). addrconf_dad_stop() is only called in two cases: if DAD failed, or to skip DAD when the link is down. In that second case, the fix is to avoid deleting the address, like we already do for permanent addresses. Fixes: 3c21edbd ("[IPV6]: Defer IPv6 device initialization until the link becomes ready.") Signed-off-by: -
Jim Baxter authored
The CDC-NCM driver can require large amounts of memory to create skb's and this can be a problem when the memory becomes fragmented. This especially affects embedded systems that have constrained resources but wish to maximise the throughput of CDC-NCM with 16KiB NTB's. The issue is after running for a while the kernel memory can become fragmented and it needs compacting. If the NTB allocation is needed before the memory has been compacted the atomic allocation can fail which can cause increased latency, large re-transmissions or disconnections depending upon the data being transmitted at the time. This situation occurs for less than a second until the kernel has compacted the memory but the failed devices can take a lot longer to recover from the failed TX packets. To ease this temporary situation I modified the CDC-NCM TX path to temporarily switch into a reduced memory mode which allocates an NTB that will fit into a USB_CDC_NCM_NTB_MIN_OUT_SIZE (default 2048 Bytes) sized memory block and only transmit NTB's with a single network frame until the memory situation is resolved. Each time this issue occurs we wait for an increasing number of reduced size allocations before requesting a full size one to not put additional pressure on a low memory system. Once the memory is compacted the CDC-NCM data can resume transmitting at the normal tx_max rate once again. Signed-off-by:
Jim Baxter <jim_baxter@mentor.com> Reviewed-by:
Bjørn Mork <bjorn@mork.no> Signed-off-by:
-
David S. Miller authored
Michal Kalderon says: ==================== qed: Add iWARP support for QL4xxxx This patch series adds iWARP support to our QL4xxxx networking adapters. The code changes span across qed and qedr drivers, but this series contains changes to qed only. Once the series is accepted, the qedr series will be submitted to the rdma tree. There is one additional qed patch which enables the iWARP, this patch is delayed until the qedr series will be accepted. The patches were previously sent as an RFC, and these are the first 12 patches in the RFC series: https://www.spinics.net/lists/linux-rdma/msg51416.html This series was tested and built against net-next. MAINTAINERS file is not updated in this PATCH as there is a pending patch for qedr driver update https://patchwork.kernel.org/patch/9752761. ==================== Signed-off-by:
-
Kalderon, Michal authored
iWARP has different physical queue requirements than RoCE Signed-off-by:
Michal Kalderon <Michal.Kalderon@cavium.com> Signed-off-by:
Yuval Mintz <Yuval.Mintz@cavium.com> Signed-off-by:
Ariel Elior <Ariel.Elior@cavium.com> Signed-off-by:
-
Kalderon, Michal authored
When computing how much memory is required for the different hw clients iWARP protocol should be taken into account Signed-off-by:
-
Kalderon, Michal authored
This patch introduces error handling for errors that occurred during connection establishment. Signed-off-by:
-
Kalderon, Michal authored
This patch takes care of active/passive disconnect flows. Disconnect flows can be initiated remotely, in which case a async event will arrive from peer and indicated to qedr driver. These are referred to as exceptions. When a QP is destroyed, it needs to check that it's associated ep has been closed. Signed-off-by:
-
Kalderon, Michal authored
This patch implements the active side connect. Offload a connection, process MPA reply and send RTR. In some of the common passive/active functions, the active side will work in blocking mode. Signed-off-by:
-
Kalderon, Michal authored
This patch implements the passive side connect. It addresses pre-allocating resources, creating a connection element upon valid SYN packet received. Calling upper layer and implementation of the accept/reject calls. Error handling is not part of this patch. Signed-off-by:
-
Kalderon, Michal authored
This patch adds the ability to add and remove listeners and identify whether the SYN packet received is intended for iWARP or not. If a listener is not found the SYN packet is posted back to the chip. Signed-off-by:
-
Kalderon, Michal authored
iWARP handles incoming SYN packets using the ll2 interface. This patch implements ll2 setup and teardown. Additional ll2 connections will be used in the future which are not part of this patch series. Signed-off-by:
-
Kalderon, Michal authored
Add a new connection type for iWARP ll2 connections for setting correct ll2 filters and connection type to FW. Signed-off-by:
-
Kalderon, Michal authored
Make some names more generic as they will be used by iWARP too. Signed-off-by:
-
Kalderon, Michal authored
This patch adds iWARP support for flows that have common code between RoCE and iWARP, such as initialization, teardown and qp setup verbs: create, destroy, modify, query. It introduces the iWARP specific files qed_iwarp.[ch] and iwarp_common.h Signed-off-by:
-
Kalderon, Michal authored
iWARP personality introduced the need for differentiating in several places in the code whether we are RoCE, iWARP or either. This leads to introducing new macros for querying the personality. Signed-off-by:
-
- 02 Jul, 2017 1 commit
-
-
Lawrence Brakmo authored
Fixed build error due to misplaced "#ifdef CONFIG_INET" (moved 1 statement up). Signed-off-by:
Lawrence Brakmo <brakmo@fb.com> Signed-off-by:
-
- 01 Jul, 2017 14 commits
-
-
David S. Miller authored
Lawrence Brakmo says: ==================== bpf: Add support for sock_ops Created a new BPF program type, BPF_PROG_TYPE_SOCK_OPS, and a corresponding struct that allows BPF programs of this type to access some of the socket's fields (such as IP addresses, ports, etc.) and setting connection parameters such as buffer sizes, initial window, SYN/SYN-ACK RTOs, etc. Unlike current BPF program types that expect to be called at a particular place in the network stack code, SOCK_OPS program can be called at different places and use an "op" field to indicate the context. There are currently two types of operations, those whose effect is through their return value and those whose effect is through the new bpf_setsocketop BPF helper function. Example operands of the first type are: BPF_SOCK_OPS_TIMEOUT_INIT BPF_SOCK_OPS_RWND_INIT BPF_SOCK_OPS_NEEDS_ECN Example operands of the secont type are: BPF_SOCK_OPS_TCP_CONNECT_CB BPF_SOCK_OPS_ACTIVE_ESTABLISHED_CB BPF_SOCK_OPS_PASSIVE_ESTABLISHED_CB Current operands are only called during connection establishment so there should not be any BPF overheads after connection establishment. The main idea is to use connection information form both hosts, such as IP addresses and ports to allow setting of per connection parameters to optimize the connection's peformance. Alghough there are already 3 mechanisms to set parameters (sysctls, route metrics and setsockopts), this new mechanism provides some disticnt advantages. Unlike sysctls, it can set parameters per connection. In contrast to route metrics, it can also use port numbers and information provided by a user level program. In addition, it could set parameters probabilistically for evaluation purposes (i.e. do something different on 10% of the flows and compare results with the other 90% of the flows). Also, in cases where IPv6 addresses contain geographic information, the rules to make changes based on the distance (or RTT) between the hosts are much easier than route metric rules and can be global. Finally, unlike setsockopt, it does not require application changes and it can be updated easily at any time. It uses the existing bpf cgroups infrastructure so the programs can be attached per cgroup with full inheritance support. Although the bpf cgroup framework already contains a sock related program type (BPF_PROG_TYPE_CGROUP_SOCK), I created the new type (BPF_PROG_TYPE_SOCK_OPS) beccause the existing type expects to be called only once during the connections's lifetime. In contrast, the new program type will be called multiple times from different places in the network stack code. For example, before sending SYN and SYN-ACKs to set an appropriate timeout, when the connection is established to set congestion control, etc. As a result it has "op" field to specify the type of operation requested. This patch set also includes sample BPF programs to demostrate the differnet features. v2: Formatting changes, rebased to latest net-next v3: Fixed build issues, changed socket_ops to sock_ops throught, fixed formatting issues, removed the syscall to load sock_ops program and added functionality to use existing bpf attach and bpf detach system calls, removed reader/writer locks in sock_bpfops.c (used when saving sock_ops global program) and fixed missing module refcount increment. v4: Removed global sock_ops program and instead used existing cgroup bpf infrastructure to support a new BPF_CGROUP_ATTCH type. v5: fixed kbuild warning happening in bpf-cgroup.h removed automatic converstion to host byte order from some sock_ops fields (ipv4 and ipv6 addresses, remote port) Added conversion to host byte order in some of the sample programs Added to sample BPF program comments about using load_sock_ops to load Removed is_req_sock field from bpf_sock_ops_kern and related places, using sk_fullsock() instead. v6: fixes to BPF helper function setsockopt (possible NULL deferencing, etc.) ==================== Signed-off-by: -
Lawrence Brakmo authored
Update tools/include/uapi/linux/bpf.h to include changes related to new bpf sock_ops program type. Signed-off-by:
-
Lawrence Brakmo authored
Sample BPF program, tcp_clamp_kern.c, to demostrate the use of setting the sndcwnd clamp. This program assumes that if the first 5.5 bytes of the host's IPv6 addresses are the same, then the hosts are in the same datacenter and sets sndcwnd clamp to 100 packets, SYN and SYN-ACK RTOs to 10ms and send/receive buffer sizes to 150KB. Signed-off-by:
-
Lawrence Brakmo authored
Adds a new bpf_setsockopt for TCP sockets, TCP_BPF_SNDCWND_CLAMP, which sets the initial congestion window. It is useful to limit the sndcwnd when the host are close to each other (small RTT). Signed-off-by:
-
Lawrence Brakmo authored
Sample BPF program that assumes hosts are far away (i.e. large RTTs) and sets initial cwnd and initial receive window to 40 packets, send and receive buffers to 1.5MB. In practice there would be a test to insure the hosts are actually far enough away. Signed-off-by:
-
Lawrence Brakmo authored
Adds a new bpf_setsockopt for TCP sockets, TCP_BPF_IW, which sets the initial congestion window. This can be used when the hosts are far apart (large RTTs) and it is safe to start with a large inital cwnd. Signed-off-by:
-
Lawrence Brakmo authored
Sample BPF program that sets congestion control to dctcp when both hosts are within the same datacenter. In this example that is assumed to be when they have the first 5.5 bytes of their IPv6 address are the same. Signed-off-by:
-
Lawrence Brakmo authored
Added support for changing congestion control for SOCK_OPS bpf programs through the setsockopt bpf helper function. It also adds a new SOCK_OPS op, BPF_SOCK_OPS_NEEDS_ECN, that is needed for congestion controls, like dctcp, that need to enable ECN in the SYN packets. Signed-off-by:
-
Lawrence Brakmo authored
This patch contains a BPF program to set initial receive window to 40 packets and send and receive buffers to 1.5MB. This would usually be done after doing appropriate checks that indicate the hosts are far enough away (i.e. large RTT). Signed-off-by:
-
Lawrence Brakmo authored
Added callbacks to BPF SOCK_OPS type program before an active connection is intialized and after a passive or active connection is established. The following patch demostrates how they can be used to set send and receive buffer sizes. Signed-off-by:
-
Lawrence Brakmo authored
Added support for calling a subset of socket setsockopts from BPF_PROG_TYPE_SOCK_OPS programs. The code was duplicated rather than making the changes to call the socket setsockopt function because the changes required would have been larger. The ops supported are: SO_RCVBUF SO_SNDBUF SO_MAX_PACING_RATE SO_PRIORITY SO_RCVLOWAT SO_MARK Signed-off-by:
-
Lawrence Brakmo authored
The sample bpf program, tcp_rwnd_kern.c, sets the initial advertized window to 40 packets in an environment where distinct IPv6 prefixes indicate that both hosts are not in the same data center. Signed-off-by:
-
Lawrence Brakmo authored
This patch adds suppport for setting the initial advertized window from within a BPF_SOCK_OPS program. This can be used to support larger initial cwnd values in environments where it is known to be safe. Signed-off-by:
-
Lawrence Brakmo authored
The sample BPF program, tcp_synrto_kern.c, sets the SYN and SYN-ACK RTOs to 10ms when both hosts are within the same datacenter (i.e. small RTTs) in an environment where common IPv6 prefixes indicate both hosts are in the same data center. Signed-off-by:
-
