Date: Sat, 08 Aug 2026 23:06:51 +0000 From: bugzilla-noreply@freebsd.org To: net@FreeBSD.org Subject: [Bug 265714] igc(4) drops link under high traffic Message-ID: <bug-265714-7501-9HT5z9vn33@https.bugs.freebsd.org/bugzilla/> In-Reply-To: <bug-265714-7501@https.bugs.freebsd.org/bugzilla/>
index | next in thread | previous in thread | raw e-mail
https://bugs.freebsd.org/bugzilla/show_bug.cgi?id=265714 --- Comment #75 from Kevin Bowling <kbowling@freebsd.org> --- (In reply to Tomasz "CeDeROM" CEDRO from comment #74) That dump is helpful, we "caught" it insofar as EIMS=0x1e during the stall and 0x1f after restart so it lost a rearm somehow. The L1.2 workaround is confirmed active. There is an oddity on your particular system, in several of the pastes/dumps after the stall there is a PCIe AER "Unsupported Request". I'm not sure what to make of that (it could be a platform or physical issue) but it is concerning. You could also try disabling AER temporarily in the firmware to see if we are mishandling an event. Next steps after another stall... Manually kick q0 back into action: pciconf -W igc0 0x10 0x1524 0x00000001 If that doesn't work then generate an interrupt: pciconf -W igc0 0x10 0x1520 0x00000001 Run the read4 script after so we can see EIMS, does this recover it? If so the issue is a lost interrupt. Main e2aff50727cbe4cb5e99f825c2c6bd8a4915de67 is possibly relevant, more of a correctness thing but worth cherry-picking into your branch as I saw a similar issue with an I219 recently. -- You are receiving this mail because: You are the assignee for the bug.home | help
Want to link to this message? Use this
URL: <https://mail-archive.FreeBSD.org/cgi/mid.cgi?bug-265714-7501-9HT5z9vn33>