October 2024 - dev

[PATCH v8 0/8] Add vhost-user support to passt. (part 3)
by Laurent Vivier 15 Nov '24

15 Nov '24

This series of patches adds vhost-user support to passt and then allows passt to connect to QEMU network backend using virtqueue rather than a socket. With QEMU, rather than using to connect: -netdev stream,id=s,server=off,addr.type=unix,addr.path=/tmp/passt_1.socket we will use: -chardev socket,id=chr0,path=/tmp/passt_1.socket -netdev vhost-user,id=netdev0,chardev=chr0 -device virtio-net,netdev=netdev0 -object memory-backend-memfd,id=memfd0,share=on,size=$RAMSIZE -numa node,memdev=memfd0 The memory backend is needed to share data between passt and QEMU. Performance comparison between "-netdev stream" and "-netdev vhost-user": $ iperf3 -c localhost -p 10001 -t 60 -6 -u -b 50G socket: [ 5] 0.00-60.05 sec 95.6 GBytes 13.7 Gbits/sec 0.017 ms 6998988/10132413 (69%) receiver vhost-user: [ 5] 0.00-60.04 sec 237 GBytes 33.9 Gbits/sec 0.006 ms 53673/7813770 (0.69%) receiver $ iperf3 -c localhost -p 10001 -t 60 -4 -u -b 50G socket: [ 5] 0.00-60.05 sec 98.9 GBytes 14.1 Gbits/sec 0.018 ms 6260735/9501832 (66%) receiver vhost-user: [ 5] 0.00-60.05 sec 235 GBytes 33.7 Gbits/sec 0.008 ms 37581/7752699 (0.48%) receiver $ iperf3 -c localhost -p 10001 -t 60 -6 socket: [ 5] 0.00-60.00 sec 17.3 GBytes 2.48 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 17.3 GBytes 2.48 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 191 GBytes 27.4 Gbits/sec 0 sender [ 5] 0.00-60.05 sec 191 GBytes 27.3 Gbits/sec receiver $ iperf3 -c localhost -p 10001 -t 60 -4 socket: [ 5] 0.00-60.00 sec 15.6 GBytes 2.24 Gbits/sec 0 sender [ 5] 0.00-60.06 sec 15.6 GBytes 2.24 Gbits/sec receiver vhost-user: [ 5] 0.00-60.00 sec 189 GBytes 27.1 Gbits/sec 0 sender [ 5] 0.00-60.04 sec 189 GBytes 27.0 Gbits/sec receiver v8: - remove iov_size() from vu_collect_one_frame() - move vu_packet_check_range() to vu_common.c - fix UDP when dlen is 0. v7: - rebase - use vu_collect_one_frame() to do vu_collect() (collect multiple frame) - add vhost-user tests from Stefano v6: - rebase - extract 3 patches from "vhost-user: add vhost-user": passt: rename tap_sock_init() to tap_backend_init() tcp: Export headers functions udp: Prepare udp.c to be shared with vhost-user - introduce new functions vu_collect_one_frame(), vu_collect(), vu_set_vnethdr(), vu_flush(), vu_send_single() to be called from tcp_vu.c, udp_vu.c and ICMP/DHCP where vhost-user code was duplicated. v5: - rebase on top of 2024_09_06.6b38f07 - rework udp_vu.c as ref.udp.v6 has been removed and we need to know if we receive IPv4 or IPv6 frame when we prepare the guest buffers for recvmsg() - remove vnet->hdrlen as the size is always the same with virtio-net v1 - address comments from David and Stefano v4: - rebase on top of 2024_08_21.1d6142f (rebasing on top of 620e19a1b48a ("udp: Merge udp[46]_mh_recv arrays") introduces a regression in the measure of the latency with UDP because I think I don't replace correctly ref.udp.v6 that is removed by this commit) - Addressed most of the comments from David and Stefano (I didn't want to postpone this version to next week, so I'll address the remaining comments in the next version). v3: - rebase on top of flow table - update tcp_vu.c to look like udp_vu.c (recv()/prepare()/send_frame()) - address comments from Stefano and David on version 2 v2: - remove PATCH 4 - rewrite PATCH 2 and 3 to follow passt coding style - move some code from PATCH 3 to PATCH 4 (previously PATCH 5) - partially addressed David's comment on PATCH 5 Laurent Vivier (7): packet: replace struct desc by struct iovec vhost-user: introduce virtio API vhost-user: introduce vhost-user API udp: Prepare udp.c to be shared with vhost-user tcp: Export headers functions passt: rename tap_sock_init() to tap_backend_init() vhost-user: add vhost-user Stefano Brivio (1): test: Add tests for passt in vhost-user mode Makefile | 9 +- conf.c | 21 +- epoll_type.h | 4 + iov.c | 1 - isolation.c | 15 +- packet.c | 91 ++-- packet.h | 22 +- passt.1 | 10 +- passt.c | 11 +- passt.h | 6 + pcap.c | 1 - tap.c | 128 ++++-- tap.h | 7 +- tcp.c | 37 +- tcp_internal.h | 15 + tcp_vu.c | 476 ++++++++++++++++++++ tcp_vu.h | 12 + test/lib/perf_report | 15 + test/lib/setup | 77 +++- test/lib/setup_ugly | 2 +- test/passt_vu | 1 + test/passt_vu_in_ns | 1 + test/perf/passt_vu_tcp | 211 +++++++++ test/perf/passt_vu_udp | 159 +++++++ test/run | 25 ++ test/two_guests_vu | 1 + udp.c | 84 ++-- udp_internal.h | 34 ++ udp_vu.c | 336 ++++++++++++++ udp_vu.h | 13 + util.h | 8 + vhost_user.c | 977 +++++++++++++++++++++++++++++++++++++++++ vhost_user.h | 206 +++++++++ virtio.c | 660 ++++++++++++++++++++++++++++ virtio.h | 184 ++++++++ vu_common.c | 385 ++++++++++++++++ vu_common.h | 47 ++ 37 files changed, 4138 insertions(+), 154 deletions(-) create mode 100644 tcp_vu.c create mode 100644 tcp_vu.h create mode 120000 test/passt_vu create mode 120000 test/passt_vu_in_ns create mode 100644 test/perf/passt_vu_tcp create mode 100644 test/perf/passt_vu_udp create mode 120000 test/two_guests_vu create mode 100644 udp_internal.h create mode 100644 udp_vu.c create mode 100644 udp_vu.h create mode 100644 vhost_user.c create mode 100644 vhost_user.h create mode 100644 virtio.c create mode 100644 virtio.h create mode 100644 vu_common.c create mode 100644 vu_common.h -- 2.46.2

3 49

[PATCH v2] tcp: Fix build against musl, __sum16 comes from linux/types.h
by Stefano Brivio 02 Nov '24

02 Nov '24

Use a plain uint16_t instead and avoid including one extra header: the 'bitwise' attribute of __sum16 is just used by sparse(1). Reported-by: omni <omni+alpine(a)hack.org> Fixes: 3d484aa37090 ("tcp: Update TCP checksum using an iovec array") Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- v2: Use uint16_t instead of including linux/types.h tcp.c | 8 ++++---- 1 file changed, 4 insertions(+), 4 deletions(-) diff --git a/tcp.c b/tcp.c index 4e0a17e..56ceba6 100644 --- a/tcp.c +++ b/tcp.c @@ -766,7 +766,7 @@ static void tcp_update_check_tcp4(const struct iphdr *iph, struct in_addr saddr = { .s_addr = iph->saddr }; struct in_addr daddr = { .s_addr = iph->daddr }; size_t check_ofs; - __sum16 *check; + uint16_t *check; int check_idx; uint32_t sum; char *ptr; @@ -797,7 +797,7 @@ static void tcp_update_check_tcp4(const struct iphdr *iph, return; } - check = (__sum16 *)ptr; + check = (uint16_t *)ptr; *check = 0; *check = csum_iov(iov, iov_cnt, l4offset, sum); @@ -816,7 +816,7 @@ static void tcp_update_check_tcp6(const struct ipv6hdr *ip6h, { uint16_t l4len = ntohs(ip6h->payload_len); size_t check_ofs; - __sum16 *check; + uint16_t *check; int check_idx; uint32_t sum; char *ptr; @@ -848,7 +848,7 @@ static void tcp_update_check_tcp6(const struct ipv6hdr *ip6h, return; } - check = (__sum16 *)ptr; + check = (uint16_t *)ptr; *check = 0; *check = csum_iov(iov, iov_cnt, l4offset, sum); -- 2.43.0

2 1

[PATCH] tcp: Fix build against musl, __sum16 comes from linux/types.h
by Stefano Brivio 31 Oct '24

31 Oct '24

...so we need to include that header explicitly. For some reason, it works without it when building against glibc. Reported-by: omni <omni+alpine(a)hack.org> Fixes: 3d484aa37090 ("tcp: Update TCP checksum using an iovec array") Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- tcp.c | 2 ++ 1 file changed, 2 insertions(+) diff --git a/tcp.c b/tcp.c index 4e0a17e..429634a 100644 --- a/tcp.c +++ b/tcp.c @@ -287,6 +287,8 @@ #include <time.h> #include <arpa/inet.h> +#include <linux/types.h> /* For __sum16 */ + #include "checksum.h" #include "util.h" #include "iov.h" -- 2.43.0

2 2

[PATCH v3 0/9] Take care of clang-tidy warnings with LLVM >= 16
by Stefano Brivio 31 Oct '24

31 Oct '24

So I started hitting some clang-tidy warnings with LLVM 16, some looked bogus, so I upgraded to LLVM 19, and... I got even more. This series takes care of them in different ways. v3: - split 5/8 into 5/9 and 6/9: in the first, drop O_APPEND so that we can have a helper to open any output file we need, and in the second one, always use O_CLOEXEC for pcap file (and use the new helper, now that we can) v2: - make snprintf_check() return and set errno on failure, in 2/8 - add missing err_perror() calls on clock_gettime() failures in 6/8 - drop all explicit integer assignments in enum udp_iov_idx in 7/8 Stefano Brivio (9): Makefile: Exclude qrap.c from clang-tidy checks treewide: Comply with CERT C rule ERR33-C for snprintf() treewide: Silence cert-err33-c clang-tidy warnings for fprintf() Makefile: Disable readability-math-missing-parentheses clang-tidy check log: Don't use O_APPEND at all treewide: Suppress clang-tidy warning if we already use O_CLOEXEC or if we can't treewide: Address cert-err33-c clang-tidy warnings for clock and timer functions udp: Take care of cert-int09-c clang-tidy warning for enum udp_iov_idx util: Don't use errno after a successful call in __daemon() Makefile | 13 ++++++++--- arch.c | 6 ++++- conf.c | 62 +++++++++++++++++++++++++++---------------------- log.c | 15 ++++-------- passt.c | 9 ++++--- pasta.c | 11 ++++++--- pcap.c | 24 ++++++++++--------- tap.c | 5 ++-- tcp.c | 12 +++++++--- udp.c | 10 ++++---- util.c | 71 +++++++++++++++++++++++++++++++++++--------------------- util.h | 7 +++++- 12 files changed, 148 insertions(+), 97 deletions(-) -- 2.43.0

2 18

[PATCH] tap: Explicitly cast TUNSETIFF to fix build warning with musl on ppc64le
by Stefano Brivio 31 Oct '24

31 Oct '24

On ppc64le, TUNSETIFF happens to be 2147767498, which is bigger than INT_MAX (2^31 - 1), and musl declares the second argument of ioctl() as 'int', not 'unsigned long' like glibc does, probably because of how POSIX specifies the equivalent argument, int dcmd, in posix_devctl(), so gcc reports a warning: tap.c: In function 'tap_ns_tun': tap.c:1291:24: warning: overflow in conversion from 'long unsigned int' to 'int' changes value from '2147767498' to '-2147199798' [-Woverflow] 1291 | rc = ioctl(fd, TUNSETIFF, &ifr); | ^~~~~~~~~ We don't care about that overflow, so explicitly cast TUNSETIFF to int. Signed-off-by: Stefano Brivio <sbrivio(a)redhat.com> --- tap.c | 2 +- 1 file changed, 1 insertion(+), 1 deletion(-) diff --git a/tap.c b/tap.c index cfb82e9..f638f2c 100644 --- a/tap.c +++ b/tap.c @@ -1288,7 +1288,7 @@ static int tap_ns_tun(void *arg) if (fd < 0) die_perror("Failed to open() /dev/net/tun"); - rc = ioctl(fd, TUNSETIFF, &ifr); + rc = ioctl(fd, (int)TUNSETIFF, &ifr); if (rc < 0) die_perror("TUNSETIFF ioctl on /dev/net/tun failed"); -- 2.43.0

2 1

passt: new version 2024_10_30.ee7d0b6 available
by Stefano Brivio 30 Oct '24

30 Oct '24

The new version with tag 2024_10_30.ee7d0b6 includes the following changes: ee7d0b6 util: Don't use errno after a successful call in __daemon() b1a607f udp: Take care of cert-int09-c clang-tidy warning for enum udp_iov_idx 099ace6 treewide: Address cert-err33-c clang-tidy warnings for clock and timer functions 59fe34e treewide: Suppress clang-tidy warning if we already use O_CLOEXEC 134b4d5 Makefile: Disable readability-math-missing-parentheses clang-tidy check 7442478 treewide: Silence cert-err33-c clang-tidy warnings for fprintf() 98efe7c treewide: Comply with CERT C rule ERR33-C for snprintf() 988a4d7 Makefile: Exclude qrap.c from clang-tidy checks ba38e67 tcp: unify l2 TCPv4 and TCPv6 queues and structures 2053c36 tcp: set ip and eth headers in l2 tap queues on the fly 5563d5f test: remove obsolete images f43f7d5 tcp: cleanup tcp_buf_data_from_sock() e7fcd0c tcp: Use runtime tests for TCP_INFO fields 8114381 tcp: Generalise probing for tcpi_snd_wnd field 13f0291 tcp: Remove compile-time dependency on struct tcp_info version 9e4615b tcp_splice: fcntl(2) returns the size of the pipe, if F_SETPIPE_SZ succeeds 149f457 tcp_splice: splice() all we have to the writing side, not what we just read 9e5df35 tcp: Use structures to construct initial TCP options b4dace8 fwd: Direct inbound spliced forwards to the guest's external address 58e6d68 test: Clarify test for spliced inbound transfers 1fa4211 passt.1: Clarify and update "Handling of local addresses" section ef8a516 passt.1: Mark --stderr as deprecated more prominently 53176ca test: Wait for DAD on DHCPv6 addresses 75b9c0f test: Explicitly wait for DAD to complete on SLAAC addresses f9d677b arp: Fix a handful of small warts 2d7f734 tcp: Send "empty" handshake ACK before first data segment 7612cb8 test: Pass TRACE from run_term() into ./run from_term b40880c test/lib/term: Always use printf for messages with escape sequences ff63ac9 conf: Add --dns-host option to configure host side nameserver 9d66df9 conf: Add command line switch to enable IP_FREEBIND socket option 151dbe0 udp: Update UDP checksum using an iovec array 3d484aa tcp: Update TCP checksum using an iovec array e6548c6 checksum: Add an offset argument in csum_iov() fd8334b pcap: Add an offset argument in pcap_iov() 72e7d30 tcp: Use tcp_payload_t rather than tcphdr def8acd test: Kernel binary can now be passed via the KERNEL environmental variable b55013b inany: Add inany_pton() helper cbde419 tcp, udp: Make {tcp,udp}_sock_init() take an inany address b8d4fac util, pif: Replace sock_l4() with pif_sock_l4() 204e77c udp: Don't attempt to get dual-stack sockets in nonsensical cases 8f8c4d2 tcp: Allow checksum to be disabled 4fe5f4e udp: Allow checksum to be disabled d836d9e util: Remove possible quadratic behaviour from write_remainder() bfc294b util: Add helper to write() all of a buffer bb41901 tcp: Make tcp_update_seqack_wnd()s force_seq parameter explicitly boolean 265b209 tcp: Simplify ifdef logic in tcp_update_seqack_wnd() 4aff6f9 tcp: Clean up tcpi_snd_wnd probing 7d8804b tcp: Make some extra functions private 5ff5d55 tcp: Avoid overlapping memcpy() in DUP_ACK handling 1f414ed tcp: Remove redundant initialisation of iov[TCP_IOV_ETH].iov_base https://passt.top/passt/log/?qt=range&q=2024_09_06.6b38f07..2024_10_30.ee7d… Packages: - Alpine Linux: https://pkgs.alpinelinux.org/packages?name=passt - Arch Linux: https://www.archlinux.org/packages/extra/x86_64/passt/ https://archlinuxarm.org/packages/aarch64/passt https://archlinuxarm.org/packages/armv7h/passt - Chimera: https://pkgs.chimera-linux.org/packages?name=passt - Clear Linux: https://github.com/clearlinux-pkgs/passt/ - Debian tracker: https://tracker.debian.org/pkg/passt - Copr (CentOS Stream, EPEL, Fedora, Mageia): https://copr.fedorainfracloud.org/coprs/sbrivio/passt/build/8189610/ permanent mirror: https://passt.top/builds/copr/0^20241030.gee7d0b6/ - Fedora updates: https://bodhi.fedoraproject.org/updates/?packages=passt - Gentoo versions: https://packages.gentoo.org/packages/net-misc/passt - GNU Guix: https://packages.guix.gnu.org/packages/passt/ - Homebrew: https://formulae.brew.sh/formula/passt - NixOS: https://github.com/NixOS/nixpkgs/tree/nixos-unstable/pkgs/by-name/pa/passt - openSUSE: https://software.opensuse.org/package/passt - PLD Linux: https://git.pld-linux.org/cgi-bin/gitweb.cgi?p=packages/passt.git - Solus: https://github.com/getsolus/packages/tree/main/packages/p/passt - Ubuntu tracker: https://launchpad.net/ubuntu/+source/passt - Void Linux: https://voidlinux.org/packages/?q=passt - Static builds: - Package for other RPM-based distributions, x86_64 only: https://passt.top/builds/latest/x86_64/passt-gee7d0b6-1.x86_64.rpm - x86_64 static binaries: https://passt.top/builds/latest/x86_64/ - Debian package, from x86_64 static build: https://passt.top/builds/latest/x86_64/passt_0ee7d0b6-1_all.deb -- Stefano

1 0

[PATCH v5 0/8] Take care of clang-tidy warnings with LLVM >= 16
by Stefano Brivio 30 Oct '24

30 Oct '24

So I started hitting some clang-tidy warnings with LLVM 16, some looked bogus, so I upgraded to LLVM 19, and... I got even more. This series takes care of them in different ways. v5: - ouch, it looks like I didn't test with 2/8 while rebasing this thing back and forth... replace snprintf() with vsnprintf() there, otherwise nothing works v4: - drop 5/9 and keep O_APPEND for the log file, turned off around log rotation, so that a hypothetical log file with multiple writers would still be somewhat consistent v3: - split 5/8 into 5/9 and 6/9: in the first, drop O_APPEND so that we can have a helper to open any output file we need, and in the second one, always use O_CLOEXEC for pcap file (and use the new helper, now that we can) v2: - make snprintf_check() return and set errno on failure, in 2/8 - add missing err_perror() calls on clock_gettime() failures in 6/8 - drop all explicit integer assignments in enum udp_iov_idx in 7/8 Stefano Brivio (8): Makefile: Exclude qrap.c from clang-tidy checks treewide: Comply with CERT C rule ERR33-C for snprintf() treewide: Silence cert-err33-c clang-tidy warnings for fprintf() Makefile: Disable readability-math-missing-parentheses clang-tidy check treewide: Suppress clang-tidy warning if we already use O_CLOEXEC treewide: Address cert-err33-c clang-tidy warnings for clock and timer functions udp: Take care of cert-int09-c clang-tidy warning for enum udp_iov_idx util: Don't use errno after a successful call in __daemon() Makefile | 13 +++++++--- arch.c | 6 ++++- conf.c | 64 +++++++++++++++++++++++++++---------------------- log.c | 9 ++++--- passt.c | 9 ++++--- pasta.c | 11 ++++++--- pcap.c | 24 ++++++++++--------- tap.c | 5 ++-- tcp.c | 12 +++++++--- udp.c | 10 ++++---- util.c | 72 ++++++++++++++++++++++++++++++++++++-------------------- util.h | 7 +++++- 12 files changed, 151 insertions(+), 91 deletions(-) -- 2.43.0

2 9

[PATCH v6 0/8] Take care of clang-tidy warnings with LLVM >= 16
by Stefano Brivio 30 Oct '24

30 Oct '24

So I started hitting some clang-tidy warnings with LLVM 16, some looked bogus, so I upgraded to LLVM 19, and... I got even more. This series takes care of them in different ways. v6: - ...and I didn't test 5/8 either :( the log file needs O_RDWR, whereas O_WRONLY suffices for pcap and PID file v5: - ouch, it looks like I didn't test with 2/8 while rebasing this thing back and forth... replace snprintf() with vsnprintf() there, otherwise nothing works v4: - drop 5/9 and keep O_APPEND for the log file, turned off around log rotation, so that a hypothetical log file with multiple writers would still be somewhat consistent v3: - split 5/8 into 5/9 and 6/9: in the first, drop O_APPEND so that we can have a helper to open any output file we need, and in the second one, always use O_CLOEXEC for pcap file (and use the new helper, now that we can) v2: - make snprintf_check() return and set errno on failure, in 2/8 - add missing err_perror() calls on clock_gettime() failures in 6/8 - drop all explicit integer assignments in enum udp_iov_idx in 7/8 Stefano Brivio (8): Makefile: Exclude qrap.c from clang-tidy checks treewide: Comply with CERT C rule ERR33-C for snprintf() treewide: Silence cert-err33-c clang-tidy warnings for fprintf() Makefile: Disable readability-math-missing-parentheses clang-tidy check treewide: Suppress clang-tidy warning if we already use O_CLOEXEC treewide: Address cert-err33-c clang-tidy warnings for clock and timer functions udp: Take care of cert-int09-c clang-tidy warning for enum udp_iov_idx util: Don't use errno after a successful call in __daemon() Makefile | 13 +++++++--- arch.c | 6 ++++- conf.c | 65 ++++++++++++++++++++++++++++---------------------- log.c | 9 ++++--- passt.c | 9 ++++--- pasta.c | 11 ++++++--- pcap.c | 24 ++++++++++--------- tap.c | 5 ++-- tcp.c | 12 +++++++--- udp.c | 10 ++++---- util.c | 72 ++++++++++++++++++++++++++++++++++++-------------------- util.h | 7 +++++- 12 files changed, 152 insertions(+), 91 deletions(-) -- 2.43.0

1 8

[PATCH v4 0/8] Take care of clang-tidy warnings with LLVM >= 16
by Stefano Brivio 30 Oct '24

30 Oct '24

So I started hitting some clang-tidy warnings with LLVM 16, some looked bogus, so I upgraded to LLVM 19, and... I got even more. This series takes care of them in different ways. v4: - drop 5/9 and keep O_APPEND for the log file, turned off around log rotation, so that a hypothetical log file with multiple writers would still be somewhat consistent v3: - split 5/8 into 5/9 and 6/9: in the first, drop O_APPEND so that we can have a helper to open any output file we need, and in the second one, always use O_CLOEXEC for pcap file (and use the new helper, now that we can) v2: - make snprintf_check() return and set errno on failure, in 2/8 - add missing err_perror() calls on clock_gettime() failures in 6/8 - drop all explicit integer assignments in enum udp_iov_idx in 7/8 Stefano Brivio (8): Makefile: Exclude qrap.c from clang-tidy checks treewide: Comply with CERT C rule ERR33-C for snprintf() treewide: Silence cert-err33-c clang-tidy warnings for fprintf() Makefile: Disable readability-math-missing-parentheses clang-tidy check treewide: Suppress clang-tidy warning if we already use O_CLOEXEC or if we can't treewide: Address cert-err33-c clang-tidy warnings for clock and timer functions udp: Take care of cert-int09-c clang-tidy warning for enum udp_iov_idx util: Don't use errno after a successful call in __daemon() Makefile | 13 +++++++--- arch.c | 6 ++++- conf.c | 64 +++++++++++++++++++++++++++---------------------- log.c | 9 ++++--- passt.c | 9 ++++--- pasta.c | 11 ++++++--- pcap.c | 24 ++++++++++--------- tap.c | 5 ++-- tcp.c | 12 +++++++--- udp.c | 10 ++++---- util.c | 72 ++++++++++++++++++++++++++++++++++++-------------------- util.h | 7 +++++- 12 files changed, 151 insertions(+), 91 deletions(-) -- 2.43.0

2 9

[PATCH v5 0/2] tcp: unify IPv4 and IPv6 tap queues
by Jon Maloy 29 Oct '24

29 Oct '24

This should save us some memory and code. --- v2: - Setting pointers to pre-set IP and MAC headers on the fly instead of copying them. - Merged patch #2 and #3 from v1 v3: - Changes based on feedback from team v4: - Rebased v5: - Changes based on feedback from team and rebased Jon Maloy (2): tcp: set ip and eth headers in l2 tap queues on the fly tcp: unify l2 TCPv4 and TCPv6 queues and structures tcp.c | 6 +- tcp_buf.c | 272 ++++++++++++++++++------------------------------------ tcp_buf.h | 3 +- 3 files changed, 91 insertions(+), 190 deletions(-) -- 2.45.2

3 5