summaryrefslogtreecommitdiffhomepage
AgeCommit message (Collapse)Author
2020-05-18Merge release-20200511.0-254-g99a18ec (automated)gVisor bot
2020-05-18Support TCP options for packetimpactZeling Feng
PiperOrigin-RevId: 312119730
2020-05-18Merge release-20200511.0-253-g32ab382 (automated)gVisor bot
2020-05-18Improve unsupported syscall messageFabricio Voznika
PiperOrigin-RevId: 312104899
2020-05-18Merge release-20200511.0-252-gc27e334 (automated)gVisor bot
2020-05-18Fix typo a => an.Adin Scannell
Always happens. PiperOrigin-RevId: 312097591
2020-05-16Merge release-20200511.0-251-g420b791 (automated)gVisor bot
2020-05-15Minor formatting updates for gvisor.dev.Adin Scannell
* Aggregate architecture Overview in "What is gVisor?" as it makes more sense in one place. * Drop "user-space kernel" and use "application kernel". The term "user-space kernel" is confusing when some platform implementation do not run in user-space (instead running in guest ring zero). * Clear up the relationship between the Platform page in the user guide and the Platform page in the architecture guide, and ensure they are cross-linked. * Restore the call-to-action quick start link in the main page, and drop the GitHub link (which also appears in the top-right). * Improve image formatting by centering all doc and blog images, and move the image captions to the alt text. PiperOrigin-RevId: 311845158
2020-05-15Merge release-20200511.0-250-g679fd25 (automated)gVisor bot
2020-05-15Remove debug log left behind by mistake.Bhasker Hariharan
PiperOrigin-RevId: 311808460
2020-05-15Merge release-20200422.0-311-gc5a939d (automated)gVisor bot
2020-05-15Update vm scripts to handle existing kbuilder user.Adin Scannell
PiperOrigin-RevId: 311751972
2020-05-15Merge release-20200422.0-310-g1847165 (automated)gVisor bot
2020-05-15Minor text updates and jquery ordering.Adin Scannell
PiperOrigin-RevId: 311744091
2020-05-15Merge release-20200422.0-309-g4502b73 (automated)gVisor bot
2020-05-14Update Kokoro images to include newer gcloud.Adin Scannell
PiperOrigin-RevId: 311658774
2020-05-15Merge release-20200422.0-308-gfb7e5f1 (automated)gVisor bot
2020-05-14Make utimes_test pass on VFS2.Jamie Liu
PiperOrigin-RevId: 311657502
2020-05-15Merge release-20200422.0-307-g326abf5 (automated)gVisor bot
2020-05-14Internal change.gVisor bot
PiperOrigin-RevId: 311645222
2020-05-14Merge release-20200422.0-306-gf589a85 (automated)gVisor bot
2020-05-14Run issue_reviver via GitHub.Adin Scannell
PiperOrigin-RevId: 311600872
2020-05-14Merge release-20200422.0-305-gbdf7bb7 (automated)gVisor bot
2020-05-14Merge pull request #2663 from lubinszARM:pr_sigfp_forkgVisor bot
PiperOrigin-RevId: 311573552
2020-05-14Merge release-20200422.0-303-g47dfba7 (automated)gVisor bot
2020-05-14Port memfd_create to vfs2 and finish implementation of file seals.Nicolas Lacasse
Closes #2612. PiperOrigin-RevId: 311548074
2020-05-14Merge release-20200422.0-302-gf1ad2d5 (automated)gVisor bot
2020-05-13Fix TCP segment retransmit timeout handling.Mithun Iyer
As per RFC 1122 and Linux retransmit timeout handling: - The segment retransmit timeout needs to exponentially increase and cap at a predefined value. - TCP connection needs to timeout after a predefined number of segment retransmissions. - TCP connection should not timeout when the retranmission timeout exceeds MaxRTO, predefined upper bound. Fixes #2673 PiperOrigin-RevId: 311463961
2020-05-14Merge release-20200422.0-301-g8b8774d (automated)gVisor bot
2020-05-13Stub support for TCP_SYNCNT and TCP_WINDOW_CLAMP.Bhasker Hariharan
This change adds support for TCP_SYNCNT and TCP_WINDOW_CLAMP options in GetSockOpt/SetSockOpt. This change does not really change any behaviour in Netstack and only stores/returns the stored value. Actual honoring of these options will be added as required. Fixes #2626, #2625 PiperOrigin-RevId: 311453777
2020-05-14Merge release-20200422.0-300-g64afaf0 (automated)gVisor bot
2020-05-13Fix runsc association of gofers and FDs on VFS2.Jamie Liu
Updates #1487 PiperOrigin-RevId: 311443628
2020-05-14Merge release-20200422.0-299-gdb655f0 (automated)gVisor bot
2020-05-13Resolve remaining TODOs for tmpfs.Nicolas Lacasse
Closes #1197 PiperOrigin-RevId: 311438223
2020-05-13Merge release-20200422.0-298-g8605c97 (automated)gVisor bot
2020-05-13Automated rollback of changelist 311285868Bhasker Hariharan
PiperOrigin-RevId: 311424257
2020-05-13Merge release-20200422.0-297-gd846077 (automated)gVisor bot
2020-05-13Enable overlayfs_stale_read by default for runsc.Jamie Liu
Linux 4.18 and later make reads and writes coherent between pre-copy-up and post-copy-up FDs representing the same file on an overlay filesystem. However, memory mappings remain incoherent: - Documentation/filesystems/overlayfs.rst, "Non-standard behavior": "If a file residing on a lower layer is opened for read-only and then memory mapped with MAP_SHARED, then subsequent changes to the file are not reflected in the memory mapping." - fs/overlay/file.c:ovl_mmap() passes through to the underlying FD without any management of coherence in the overlay. - Experimentally on Linux 5.2: ``` $ cat mmap_cat_page.c #include <err.h> #include <fcntl.h> #include <stdio.h> #include <string.h> #include <sys/mman.h> #include <unistd.h> int main(int argc, char **argv) { if (argc < 2) { errx(1, "syntax: %s [FILE]", argv[0]); } const int fd = open(argv[1], O_RDONLY); if (fd < 0) { err(1, "open(%s)", argv[1]); } const size_t page_size = sysconf(_SC_PAGE_SIZE); void* page = mmap(NULL, page_size, PROT_READ, MAP_SHARED, fd, 0); if (page == MAP_FAILED) { err(1, "mmap"); } for (;;) { write(1, page, strnlen(page, page_size)); if (getc(stdin) == EOF) { break; } } return 0; } $ gcc -O2 -o mmap_cat_page mmap_cat_page.c $ mkdir lowerdir upperdir workdir overlaydir $ echo old > lowerdir/file $ sudo mount -t overlay -o "lowerdir=lowerdir,upperdir=upperdir,workdir=workdir" none overlaydir $ ./mmap_cat_page overlaydir/file old ^Z [1]+ Stopped ./mmap_cat_page overlaydir/file $ echo new > overlaydir/file $ cat overlaydir/file new $ fg ./mmap_cat_page overlaydir/file old ``` Therefore, while the VFS1 gofer client's behavior of reopening read FDs is only necessary pre-4.18, replacing existing memory mappings (in both sentry and application address spaces) with mappings of the new FD is required regardless of kernel version, and this latter behavior is common to both VFS1 and VFS2. Re-document accordingly, and change the runsc flag to enabled by default. New test: - Before this CL: https://source.cloud.google.com/results/invocations/5b222d2c-e918-4bae-afc4-407f5bac509b - After this CL: https://source.cloud.google.com/results/invocations/f28c747e-d89c-4d8c-a461-602b33e71aab PiperOrigin-RevId: 311361267
2020-05-13Merge release-20200422.0-296-g18cb3d2 (automated)gVisor bot
2020-05-13Use VFS2 mount namesFabricio Voznika
Updates #1487 PiperOrigin-RevId: 311356385
2020-05-13Merge release-20200422.0-295-ge4058c0 (automated)gVisor bot
2020-05-13Replace test_runner.sh bash script with Go.Ian Gudger
PiperOrigin-RevId: 311285868
2020-05-13Merge release-20200422.0-294-g305f786 (automated)gVisor bot
2020-05-12Adjust a few log messagesFabricio Voznika
PiperOrigin-RevId: 311234146
2020-05-12Merge release-20200422.0-293-g725afc6 (automated)gVisor bot
2020-05-12Merge pull request #2678 from nybidari:iptablesgVisor bot
PiperOrigin-RevId: 311203776
2020-05-12Merge release-20200422.0-291-g7b691ab (automated)gVisor bot
2020-05-12Don't allow rename across different gofer or tmpfs mounts.Nicolas Lacasse
Fixes #2651. PiperOrigin-RevId: 311193661
2020-05-12Merge release-20200422.0-290-ga3f97a7 (automated)gVisor bot
2020-05-12Merge pull request #2513 from amscanne:website-integratedgVisor bot
PiperOrigin-RevId: 311184385