)]}'
{
  "commit": "bcc843bb0e7468de7f2de8bc2e3fa5a54dd1f3d0",
  "tree": "64bc4c5d5bba2bc7f17bd38e1edcaa4cfc789afa",
  "parents": [
    "f99c579211f5c77da6750b90c6bec9b264188120",
    "aa251c84636c326471ca9d53723816ba8fffe2bf"
  ],
  "author": {
    "name": "Jakub Kicinski",
    "email": "kuba@kernel.org",
    "time": "Wed Oct 29 17:30:45 2025 -0700"
  },
  "committer": {
    "name": "Jakub Kicinski",
    "email": "kuba@kernel.org",
    "time": "Wed Oct 29 17:30:45 2025 -0700"
  },
  "message": "Merge branch \u0027tcp-fix-receive-autotune-again\u0027\n\nMatthieu Baerts says:\n\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\ntcp: fix receive autotune again\n\nNeal Cardwell found that recent kernels were having RWIN limited\nissues, even when net.ipv4.tcp_rmem[2] was set to a very big value like\n512MB.\n\nHe suspected that tcp_stream default buffer size (64KB) was triggering\nheuristic added in ea33537d8292 (\"tcp: add receive queue awareness\nin tcp_rcv_space_adjust()\").\n\nAfter more testing, it turns out the bug was added earlier\nwith commit 65c5287892e9 (\"tcp: fix sk_rcvbuf overshoot\").\n\nI forgot once again that DRS has one RTT latency.\n\nMPTCP also got the same issue.\n\nThis series :\n - Prevents calling tcp_rcvbuf_grow() on some MPTCP subflows.\n - adds rcv_ssthresh, window_clamp and rcv_wnd to trace_tcp_rcvbuf_grow().\n - Refactors code in a patch with no functional changes.\n - Fixes the issue in the final patch.\n\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\u003d\n\nLink: https://patch.msgid.link/20251028-net-tcp-recv-autotune-v3-0-74b43ba4c84c@kernel.org\nSigned-off-by: Jakub Kicinski \u003ckuba@kernel.org\u003e\n",
  "tree_diff": []
}