aboutgitcodebugslistschat
Commit message (Expand)AuthorAgeFilesLines
* pasta: correctly exit when execvp() failsPaul Holzinger2023-02-121-1/+1
* pasta: do not leak netlink sock into childPaul Holzinger2023-02-121-2/+2
* Make assertions actually usefulDavid Gibson2023-02-127-20/+32
* tcp: Reset ACK_FROM_TAP_DUE flag only as needed, update timerStefano Brivio2023-02-121-14/+38
* tap: Send frames after the first one in tap_send_frames_pasta()Stefano Brivio2023-02-121-1/+2
* pasta: Wait for tap to be set up before spawning commandStefano Brivio2023-02-123-1/+18
* udp: Use tap_send_frames()David Gibson2023-01-234-166/+8
* tap: Improve handling of partial frame sendsDavid Gibson2023-01-231-13/+36
* udp: Use abstracted tap headerDavid Gibson2023-01-232-62/+24
* tap: Use different io vector bases depending on tap typeDavid Gibson2023-01-232-5/+6
* tcp: Use abstracted tap headerDavid Gibson2023-01-231-55/+30
* tap: Add "tap headers" abstractionDavid Gibson2023-01-232-0/+66
* tcp: Consolidate calculation of total frame sizeDavid Gibson2023-01-231-19/+16
* tcp: Remove redundant and incorrect initialization from *_iov_init()David Gibson2023-01-231-6/+2
* util: Parameterize ethernet header initializer macroDavid Gibson2023-01-233-15/+8
* tcp, udp: Use named field initializers in iov_init functionsDavid Gibson2023-01-232-23/+16
* util: Introduce hton*_constant() in place of #ifdefsDavid Gibson2023-01-232-63/+24
* tap, tcp: Move tap send path to tap.cDavid Gibson2023-01-233-81/+89
* tcp: Combine two parts of pasta tap send path togetherDavid Gibson2023-01-231-22/+18
* tcp: Improve interface to tcp_l2_buf_flush()David Gibson2023-01-231-37/+26
* tcp: Don't compute total bytes in a message until we need itDavid Gibson2023-01-231-35/+18
* tcp: Combine two parts of passt tap send path togetherDavid Gibson2023-01-231-8/+12
* pcap: Replace pcapm() with pcap_multiple()David Gibson2023-01-233-11/+12
* pcap: Introduce pcap_frame() helperDavid Gibson2023-01-231-38/+38
* udp: Don't use separate sockets to listen for spliced packetsDavid Gibson2023-01-131-40/+13
* udp: Decide whether to "splice" per datagram rather than per socketDavid Gibson2023-01-132-20/+34
* udp: Unify udp_sock_handler_splice() with udp_sock_handler()David Gibson2023-01-131-60/+34
* udp: Pre-populate msg_names with local addressDavid Gibson2023-01-132-22/+25
* udp: Don't handle tap receive batch size calculation within a #defineDavid Gibson2023-01-131-3/+6
* udp: Split receive from preparation and send in udp_sock_handler()David Gibson2023-01-131-27/+52
* udp: Split sending to passt tap interface into separate functionDavid Gibson2023-01-131-58/+72
* udp: Move sending pasta tap frames to the end of udp_sock_handler()David Gibson2023-01-131-19/+42
* test/perf/pasta_tcp: Add host to namespace cases for traffic via tapStefano Brivio2023-01-051-0/+57
* tcp: Explicitly check option length field values in tcp_opt_get()Stefano Brivio2023-01-051-0/+4
* test/perf/pasta_udp: Add host to namespace cases for traffic via tapStefano Brivio2023-01-051-0/+37
* udp: Factor out control structure management from udp_sock_fill_data_v[46]David Gibson2022-12-061-68/+50
* udp: Preadjust udp[46]_l2_iov_tap[].iov_base for pasta modeDavid Gibson2022-12-061-18/+18
* udp: Better factor IPv4 and IPv6 paths in udp_sock_handler()David Gibson2022-12-061-22/+18
* udp: Fix incorrect use of IPv6 mh buffers in IPv4 pathDavid Gibson2022-12-061-4/+4
* udp: Correct splice forwarding when receiving from multiple sourcesDavid Gibson2022-12-061-5/+14
* udp: Split send half of udp_sock_handler_splice() from the receive halfDavid Gibson2022-12-061-23/+53
* udp: Unify buffers for tap and splice pathsDavid Gibson2022-12-061-40/+31
* udp: Add helper to extract port from a sockaddr_in or sockaddr_in6David Gibson2022-12-061-12/+14
* udp: Make UDP_SPLICE_FRAMES and UDP_TAP_FRAMES_MEM the same thingDavid Gibson2022-12-061-28/+27
* udp: Simplify udp_sock_handler_spliceDavid Gibson2022-12-061-32/+15
* udp: Update UDP "connection" timestamps in both directionsDavid Gibson2022-12-061-2/+17
* udp: Don't explicitly track originating socket for spliced "connections"David Gibson2022-12-061-61/+52
* udp: Re-use fixed bound sockets for packet forwarding when possibleDavid Gibson2022-12-061-9/+13
* udp: Don't create double sockets for -U portDavid Gibson2022-12-061-18/+14
* udp: Split splice field in udp_epoll_ref into (mostly) independent bitsDavid Gibson2022-12-063-35/+35