summaryrefslogtreecommitdiffhomepage
path: root/pkg
AgeCommit message (Collapse)Author
2019-10-22netstack/tcp: software segmentation offloadAndrei Vagin
Right now, we send each tcp packet separately, we call one system call per-packet. This patch allows to generate multiple tcp packets and send them by sendmmsg. The arguable part of this CL is a way how to handle multiple headers. This CL adds the next field to the Prepandable buffer. Nginx test results: Server Software: nginx/1.15.9 Server Hostname: 10.138.0.2 Server Port: 8080 Document Path: /10m.txt Document Length: 10485760 bytes w/o gso: Concurrency Level: 5 Time taken for tests: 5.491 seconds Complete requests: 100 Failed requests: 0 Total transferred: 1048600200 bytes HTML transferred: 1048576000 bytes Requests per second: 18.21 [#/sec] (mean) Time per request: 274.525 [ms] (mean) Time per request: 54.905 [ms] (mean, across all concurrent requests) Transfer rate: 186508.03 [Kbytes/sec] received sw-gso: Concurrency Level: 5 Time taken for tests: 3.852 seconds Complete requests: 100 Failed requests: 0 Total transferred: 1048600200 bytes HTML transferred: 1048576000 bytes Requests per second: 25.96 [#/sec] (mean) Time per request: 192.576 [ms] (mean) Time per request: 38.515 [ms] (mean, across all concurrent requests) Transfer rate: 265874.92 [Kbytes/sec] received w/o gso: $ ./tcp_benchmark --client --duration 15 --ideal [SUM] 0.0-15.1 sec 2.20 GBytes 1.25 Gbits/sec software gso: $ tcp_benchmark --client --duration 15 --ideal --gso $((1<<16)) --swgso [SUM] 0.0-15.1 sec 3.99 GBytes 2.26 Gbits/sec PiperOrigin-RevId: 276112677
2019-10-22Auto-generate an IPv6 link-local address based on the NIC's MAC Address.Ghanan Gowripalan
This change adds support for optionally auto-generating an IPv6 link-local address based on the NIC's MAC Address on NIC enable. Note, this change will not break existing uses of netstack as the default configuration for the stack options is set in such a way that a link-local address will not be auto-generated unless the stack is explicitly configured. See `stack.Options` for more details. Specifically, see `stack.Options.AutoGenIPv6LinkLocal`. Tests: Tests to make sure that the IPb6 link-local address is only auto-generated if the stack is specifically configured to do so. Also tests to make sure that an auto-generated address goes through the DAD process. PiperOrigin-RevId: 276059813
2019-10-21Remove old TODO.Nicolas Lacasse
PiperOrigin-RevId: 275956240
2019-10-21Add basic implementation of execveat syscall and associated tests.Dean Deng
Allow file descriptors of directories as well as AT_FDCWD. PiperOrigin-RevId: 275929668
2019-10-21AF_PACKET support for netstack (aka epsocket).Kevin Krakauer
Like (AF_INET, SOCK_RAW) sockets, AF_PACKET sockets require CAP_NET_RAW. With runsc, you'll need to pass `--net-raw=true` to enable them. Binding isn't supported yet. PiperOrigin-RevId: 275909366
2019-10-19Add support for pipes in VFS2.Kevin Krakauer
PiperOrigin-RevId: 275650307
2019-10-18Store primary endpoints in a sliceTamir Duberstein
There's no need for a linked list here. PiperOrigin-RevId: 275565920
2019-10-18Fix typo while initializing protocol for UDP endpoints.Mithun Iyer
Fixes #763 PiperOrigin-RevId: 275563222
2019-10-18Cleanup host UDS supportMichael Pratt
This change fixes several issues with the fsgofer host UDS support. Notably, it adds support for SOCK_SEQPACKET and SOCK_DGRAM sockets [1]. It also fixes unsafe use of unet.Socket, which could cause a panic if Socket.FD is called when err != nil, and calls to Socket.FD with nothing to prevent the garbage collector from destroying and closing the socket. A set of tests is added to exercise host UDS access. This required extracting most of the syscall test runner into a library that can be used by custom tests. Updates #235 Updates #1003 [1] N.B. SOCK_DGRAM sockets are likely not particularly useful, as a server can only reply to a client that binds first. We don't allow bind, so these are unlikely to be used. PiperOrigin-RevId: 275558502
2019-10-18Remove restrictions on the sending addressTamir Duberstein
It is quite legal to send from the ANY address (it is required for DHCP). I can't figure out why the broadcast address was included here, so removing that as well. PiperOrigin-RevId: 275541954
2019-10-17Refactor pipe to support VFS2.Kevin Krakauer
* Pulls common functionality (IO and locking on open) into pipe_util.go. * Adds pipe/vfs.go, which implements a subset of vfs.FileDescriptionImpl. A subsequent change will add support for pipes in memfs. PiperOrigin-RevId: 275322385
2019-10-17NDP Neighbor Solicitations sent during DAD must have an IP hop limit of 255Ghanan Gowripalan
NDP Neighbor Solicitations sent during Duplicate Address Detection must have an IP hop limit of 255, as all NDP Neighbor Solicitations should have. Test: Test that DAD messages have the IPv6 hop limit field set to 255. PiperOrigin-RevId: 275321680
2019-10-16Do Duplicate Address Detection on permanent IPv6 addresses.Ghanan Gowripalan
This change adds support for Duplicate Address Detection on IPv6 addresses as defined by RFC 4862 section 5.4. Note, this change will not break existing uses of netstack as the default configuration for the stack options is set in such a way that DAD will not be performed. See `stack.Options` and `stack.NDPConfigurations` for more details. Tests: Tests to make sure that the DAD process properly resolves or fails. That is, tests make sure that DAD resolves only if: - No other node is performing DAD for the same address - No other node owns the same address PiperOrigin-RevId: 275189471
2019-10-16Reorder BUILD license and load functions in gvisor.Kevin Krakauer
PiperOrigin-RevId: 275139066
2019-10-16Add sublevel to kernel versionMichael Pratt
Standard Linux kernel versions are VERSION.PATCHLEVEL.SUBLEVEL. e.g., 4.4.0, even when the sublevel is 0. Match this standard. PiperOrigin-RevId: 275125715
2019-10-16Fix problem with open FD when copy up is triggered in overlayfsFabricio Voznika
Linux kernel before 4.19 doesn't implement a feature that updates open FD after a file is open for write (and is copied to the upper layer). Already open FD will continue to read the old file content until they are reopened. This is especially problematic for gVisor because it caches open files. Flag was added to force readonly files to be reopenned when the same file is open for write. This is only needed if using kernels prior to 4.19. Closes #1006 It's difficult to really test this because we never run on tests on older kernels. I'm adding a test in GKE which uses kernels with the overlayfs problem for 1.14 and lower. PiperOrigin-RevId: 275115289
2019-10-16Support O_SYNC and O_DSYNC flags.Nicolas Lacasse
When any of these flags are set, all writes will trigger a subsequent fsync call. This behavior already existed for "write-through" mounts. O_DIRECT is treated as an alias for O_SYNC. Better support coming soon. PiperOrigin-RevId: 275114392
2019-10-16Fix syscall changes lost in rebaseMichael Pratt
These syscalls were changed in the amd64 file around the time the arm64 PR was sent out, so their changes got lost. Updates #63 PiperOrigin-RevId: 275114194
2019-10-16Merge pull request #736 from tanjianfeng:fix-unixgVisor bot
PiperOrigin-RevId: 275114157
2019-10-15Minor vfs.FileDescriptionImpl fixes.Jamie Liu
- Pass context.Context to OnClose(). - Pass memmap.MMapOpts to ConfigureMMap() by pointer so that implementations can actually mutate it as required. PiperOrigin-RevId: 274934967
2019-10-15Remove panic when reassembly fails.Bhasker Hariharan
Reassembly can fail due to an invalid sequence of fragments being received. eg. Multiple fragments with same id which claim to be the last one by setting the more flag to 0 etc. It's safer to just drop the reassembler and increment a metric than to panic when reassembly fails. PiperOrigin-RevId: 274920901
2019-10-15Set NDP hop limit in accordance with RFC 4861Tamir Duberstein
...and do not populate link address cache at dispatch. This partially reverts 313c767b0001bf6271405f1b765b60a334d6e911, which caused malformed packets (e.g. NDP Neighbor Adverts with incorrect hop limit values) to populate the address cache. In particular, this masked a bug that was introduced to the Neighbor Advert generation code in 7c1587e3401a010d1865df61dbaf117c77dd062e. PiperOrigin-RevId: 274865182
2019-10-14Internal change.gVisor bot
PiperOrigin-RevId: 274700093
2019-10-14Reorder BUILD license and load functions in netstack.Kevin Krakauer
PiperOrigin-RevId: 274672346
2019-10-14Use a different fanoutID for each new fdbased endpoint.Bhasker Hariharan
PiperOrigin-RevId: 274638272
2019-10-10Allow for zero byte iovec with MSG_PEEK | MSG_TRUNC in recvmsg.Ian Lewis
This allows for peeking at the length of the next message on a netlink socket without pulling it off the socket's buffer/queue, allowing tools like 'ip' to work. This CL also fixes an issue where dump_done_errno was not included in the NLMSG_DONE messages payload. Issue #769 PiperOrigin-RevId: 274068637
2019-10-10Fix bugs in fragment handling.Bhasker Hariharan
Strengthen the header.IPv4.IsValid check to correctly check for IHL/TotalLength fields. Also add a check to make sure fragmentOffsets + size of the fragment do not cause a wrap around for the end of the fragment. PiperOrigin-RevId: 274049313
2019-10-10Fix signalfd polling.Adin Scannell
The signalfd descriptors otherwise always show as available. This can lead programs to spin, assuming they are looking to see what signals are pending. Updates #139 PiperOrigin-RevId: 274017890
2019-10-10Merge pull request #909 from xiaobo55x:atomic_bitsopsgVisor bot
PiperOrigin-RevId: 274011064
2019-10-09Internal change.gVisor bot
PiperOrigin-RevId: 273861936
2019-10-09Merge pull request #811 from lubinszARM:pr_testutilgVisor bot
PiperOrigin-RevId: 273781641
2019-10-09Merge pull request #813 from xiaobo55x:pkg_sleepgVisor bot
PiperOrigin-RevId: 273668431
2019-10-09Enable pkg/atomicbitops support on arm64.Haibo Xu
Signed-off-by: Haibo Xu <haibo.xu@arm.com> Change-Id: I1646aaa6f07b5ec31c39c318b70f48693fe59a7c
2019-10-07Implement IP_TTL.Ian Gudger
Also change the default TTL to 64 to match Linux. PiperOrigin-RevId: 273430341
2019-10-07Remove unnecessary context parameter for new pipes.Kevin Krakauer
PiperOrigin-RevId: 273421634
2019-10-07Rename epsocket to netstack.Kevin Krakauer
PiperOrigin-RevId: 273365058
2019-10-07Merge pull request #753 from lubinszARM:pr_syscall_linuxgVisor bot
PiperOrigin-RevId: 273364848
2019-10-04Add sanity check that overlayCreate is called with an overlay parent inode.Nicolas Lacasse
PiperOrigin-RevId: 272987037
2019-10-04Return EIO from p9 if flipcall.Endpoint.Connect() fails.Jamie Liu
Also ensure that all flipcall transport errors not returned by p9 (converted to EIO by the client, or dropped on the floor by channel server goroutines) are logged. PiperOrigin-RevId: 272963663
2019-10-04Change linux.FileMode from uint to uint16, and update VFS to use FileMode.Kevin Krakauer
In Linux (include/linux/types.h), mode_t is an unsigned short. PiperOrigin-RevId: 272956350
2019-10-03Implement proper local broadcast behaviorChris Kuiper
The behavior for sending and receiving local broadcast (255.255.255.255) traffic is as follows: Outgoing -------- * A broadcast packet sent on a socket that is bound to an interface goes out that interface * A broadcast packet sent on an unbound socket follows the route table to select the outgoing interface + if an explicit route entry exists for 255.255.255.255/32, use that one + else use the default route * Broadcast packets are looped back and delivered following the rules for incoming packets (see next). This is the same behavior as for multicast packets, except that it cannot be disabled via sockopt. Incoming -------- * Sockets wishing to receive broadcast packets must bind to either INADDR_ANY (0.0.0.0) or INADDR_BROADCAST (255.255.255.255). No other socket receives broadcast packets. * Broadcast packets are multiplexed to all sockets matching it. This is the same behavior as for multicast packets. * A socket can bind to 255.255.255.255:<port> and then receive its own broadcast packets sent to 255.255.255.255:<port> In addition, this change implicitly fixes an issue with multicast reception. If two sockets want to receive a given multicast stream and one is bound to ANY while the other is bound to the multicast address, only one of them will receive the traffic. PiperOrigin-RevId: 272792377
2019-10-03Merge pull request #757 from xiaobo55x:pkg_bitsgVisor bot
PiperOrigin-RevId: 272760964
2019-10-03Don't report partialResult errors from sendfileAndrei Vagin
The input file descriptor is always a regular file, so sendfile can't lose any data if it will not be able to write them to the output file descriptor. Reported-by: syzbot+22d22330a35fa1c02155@syzkaller.appspotmail.com PiperOrigin-RevId: 272730357
2019-10-02Merge pull request #865 from tanjianfeng:fix-829gVisor bot
PiperOrigin-RevId: 272522508
2019-10-02fs/proc: report PID-s from a pid namespace of the proc mountAndrei Vagin
Right now, we can find more than one process with the 1 PID in /proc. $ for i in `seq 10`; do > unshare -fp sleep 1000 & > done $ ls /proc 1 1 1 1 12 18 24 29 6 loadavg net sys version 1 1 1 1 16 20 26 32 cpuinfo meminfo self thread-self 1 1 1 1 17 21 28 36 filesystems mounts stat uptime PiperOrigin-RevId: 272506593
2019-10-02Merge branch 'master' into pr_syscall_linuxAndrei Vagin
2019-10-01Include AT_SECURE in the aux vectorMichael Pratt
gVisor does not currently implement the functionality that would result in AT_SECURE = 1, but Linux includes AT_SECURE = 0 in the normal case, so we should do the same. PiperOrigin-RevId: 272311488
2019-10-01Disable cpuClockTicker when app is idleMichael Pratt
Kernel.cpuClockTicker increments kernel.cpuClock, which tasks use as a clock to track their CPU usage. This improves latency in the syscall path by avoid expensive monotonic clock calls on every syscall entry/exit. However, this timer fires every 10ms. Thus, when all tasks are idle (i.e., blocked or stopped), this forces a sentry wakeup every 10ms, when we may otherwise be able to sleep until the next app-relevant event. These wakeups cause the sentry to utilize approximately 2% CPU when the application is otherwise idle. Updates to clock are not strictly necessary when the app is idle, as there are no readers of cpuClock. This commit reduces idle CPU by disabling the timer when tasks are completely idle, and computing its effects at the next wakeup. Rather than disabling the timer as soon as the app goes idle, we wait until the next tick, which provides a window for short sleeps to sleep and wakeup without doing the (relatively) expensive work of disabling and enabling the timer. PiperOrigin-RevId: 272265822
2019-10-01Honor X bit on extra anon pages in PT_LOAD segmentsMichael Pratt
Linux changed this behavior in 16e72e9b30986ee15f17fbb68189ca842c32af58 (v4.11). Previously, extra pages were always mapped RW. Now, those pages will be executable if the segment specified PF_X. They still must be writeable. PiperOrigin-RevId: 272256280
2019-09-30splice: try another fallback option only if the previous one isn't supportedAndrei Vagin
Reported-by: syzbot+bb5ed342be51d39b0cbb@syzkaller.appspotmail.com PiperOrigin-RevId: 272110815
generated by cgit v1.2.3 (git 2.39.1) at 2024-11-02 05:25:42 +0000