From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=91.218.175.203 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1794374288; b=Q8VL2i2nDrV5DEo1EdDelOSDccz+Md/2U4tilcnNjESl+nJ+bfS+DOi4WaSScnWAp93d jTl7Cfho4vAyNToDgU8b/ODOPAKq/IuUWyzsfhdER5SojueqeBfZNaOuailHzcds2qZT/ fk8xtikzvidcnFMYJZBZh6QN0FC2M2eImhs4bra2gH7MuKiN09o5tDCch+yTtvcNn2hCl 4dL1TdcPrTboDgFaAApLAwKJJMmrz1xwzz+TlGhy5NewGjlSp0NYwT+MPCWRJ9IN8aWMF FubtPZ7kMFSTAPuuCDR0f/YHf5tbE0/GwIxgvECKaGxzEdU3iMDGxLdH7o5naWhu+4g== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1794374288; h=DMARC-Filter:X-Envelope-To:DKIM-Signature:X-Envelope-To:Received: X-Mizu-Trace-ID:X-Migadu-Flow:Message-ID:Date:MIME-Version:User-Agent: Cc:Subject:To:References:From:In-Reply-To:Content-Type: Content-Transfer-Encoding; bh=4E6KxAhNlFzENhgeIInuOXhEw9H++Tb+DYqZlBVUXzc=; b=h3M941qCSvdMUl9DIaKT6cf9mveIEcZwSC4ZXbRQji+01d3uTpkzRvqrrzFQB8KShTZs KTfK9ptnbG5iW3QWTMeiNwRAgoqTXe17ZXu7z7UjwlIk5E1W5Wg+DRlQGO7HYXSLi7IKU hub1h/fe63iHiNtqRpZ+5ChmBDdzZAPEgOAJuQqQvB8FCTB9RHDbbxUlBfieT8MAq+JMA NShZldS979iBl1mf8x+B5CJsP6gl82VL74KKP/Po8NM/OrkigB/foMw+eU0WvVbydoGOj BSyHd91ZasQ4SsABHHXj3ZgjGfR+IFdy96Y4tCdxJc6VgpzxDK1bINL1UBIRxkMr2gg== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=linux.dev; spf=pass smtp.mailfrom=linux.dev; dkim=pass header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b=XZHfbLZI; arc=none smtp.remote-ip=91.218.175.203 Received: from mta0.migadu.com (out-203.mta0.migadu.com [91.218.175.203]) (using TLSv1.3 with cipher TLS_AES_128_GCM_SHA256 (128/128 bits) key-exchange X25519 server-signature ECDSA (prime256v1) server-digest SHA256) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 16BC8606A320 for ; Wed, 11 Nov 2026 05:18:04 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 16BC8606A320 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.dev Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.dev Authentication-Results: smtp.subspace.kernel.org; dkim=pass (1024-bit key, unprotected) header.d=linux.dev header.i=@linux.dev header.a=rsa-sha256 header.s=key1 header.b=XZHfbLZI X-Envelope-To: bpf@vger.kernel.org DKIM-Signature: a=rsa-sha256; bh=YWujpAd2POSHBZxj/UGItw4ULXL9YbFbrRMqy5m6l6A=; c=simple/simple; d=linux.dev; h=from:to:subject:date:message-id:mime-version:content-type; s=key1; t=1794374282; v=1; x=1794979082; b=XZHfbLZI6xJ67cIrTmKahjhqrj9RX/I53nXXBC+DUHGpmm8/ix3WA02/xL2TsJAe3cDhnRmZ dCtUub/o5p6vPPlTI6QXEUnryTFfxKwh3blSvZiUa2tV+GewXSY0lXACzW9ra7S1sGPYvUZ7uVE WDeB564PSsvk5qEEOC0lrm+M= X-Envelope-To: bpf@vger.kernel.org Received: by smtp.migadu.com with ESMTPS id 42174d712a9758ba; Wed, 11 Nov 2026 05:18:02 +0000 X-Mizu-Trace-ID: 42174d712a9758ba X-Migadu-Flow: FLOW_OUT Message-ID: Date: Wed, 11 Nov 2026 13:17:52 +0800 X-Mailing-List: bpf@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 User-Agent: Mozilla Thunderbird Cc: cui.tao@linux.dev, tj@kernel.org, void@manifault.com, arighi@nvidia.com, changwoo@igalia.com, liwanwu@kylinos.cn, zhaomengmeng@kylinos.cn, emil@etsalapatis.com, yphbchou0911@gmail.com, mingo@redhat.com, sched-ext@lists.linux.dev, linux-kernel@vger.kernel.org, bpf@vger.kernel.org, Tao Cui Subject: Re: [PATCH 0/9] tools/sched_ext: robustness fixes from cold review To: David CARLIER References: <20261110125001.4167503-1-cui.tao@linux.dev> From: Tao Cui In-Reply-To: Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit Hello, David, 在 2026/11/10 21:03, David CARLIER 写道: > Hi Tao > > On Tue, 10 Nov 2026 at 12:50, Tao Cui > wrote: > > From: Tao Cui > > > Hello, > > This series fixes nine robustness issues in the example schedulers > scx_pair, scx_flatcg, scx_qmap and scx_userland. > > scx_flatcg resets its stats baseline on restart (stale counters print > as u64 underflow garbage) and rejects a stats interval that puts > nanosleep in an error loop (a negative or non-finite -i busy-spins at > 100% CPU). scx_pair stops aborting the scheduler when the dispatching > cgroup goes away mid-dispatch, gates attach on an interrupted > initialization instead of running with a half-built cgrp_q_arr, resets > pair_id on restart, and cleans up a dead busy-check whose fall-through > clears another cgroup's busy marker. scx_qmap documents the options it > actually accepts and resets its hier stats baseline on restart. > scx_userland bounds the batch against the dispatch buffer instead of > overflowing it 13ms in, and rejects batch size 0, which livelocks the > machine until the stall watchdog fires. > > Verified in qemu on tj/sched_ext for-next (5b740a72b55c), same > kernel and config with and without each patch, comparing stock and > patched binaries: a scx_flatcg restart prints six > u64-underflow garbage counters on stock and zeros with patch 1; a > non-finite -i busy-spins ~17k EINVAL lines in 3s on stock and is > rejected at parse time with patch 2; SIGINT storms abort 20/30 > interrupted inits on stock with the scheduler never loading and exit > 30/30 clean with patch 4; a scx_pair restart aborts 7ms in with a > stale pair_id on stock and runs clean for its full window with patch > 5; an oversized scx_userland batch aborts 13ms in with "dispatch > buffer overflow" on stock and survives 25s with patch 9; and batch > size 0, which livelocks the machine until the stall watchdog fires > (spinner progress collapses to ~1%), is rejected immediately with > patch 8. Beyond the A/B pairs: the scx_pair cgid-cache churn window > is too narrow to drive (40 rounds clean on both binaries; patch 3 is > graded by inspection), the qmap synopsis diff shows exactly the three > added options (patch 6), and the hier stats baseline was verified with > a clang-23.1.5-built scx_qmap run through restart cycles (patch 7, > hier stats clean throughout). > > Based on sched_ext/for-next (5b740a72b55c). > > Tao Cui (9): >   tools/sched_ext: scx_flatcg: Reset the stats baseline on restart >   tools/sched_ext: scx_flatcg: Validate the stats interval >   tools/sched_ext: scx_pair: Don't abort when the dispatching cgroup >     goes away >   tools/sched_ext: scx_pair: Don't attach after an interrupted >     initialization >   tools/sched_ext: scx_pair: Reset pair_id on restart >   tools/sched_ext: scx_qmap: Add the missing options to the usage >     synopsis >   tools/sched_ext: scx_qmap: Reset the hier stats baseline on restart >   tools/sched_ext: scx_userland: Check dispatch buffer slots before >     inserting >   tools/sched_ext: scx_userland: Reject batch size 0 > >  tools/sched_ext/scx_flatcg.c       |  7 ++++++- >  tools/sched_ext/scx_pair.bpf.c     | 12 ++++++++++-- >  tools/sched_ext/scx_pair.c         | 14 ++++++++++++-- >  tools/sched_ext/scx_qmap.c         |  3 ++- >  tools/sched_ext/scx_userland.bpf.c |  8 ++++++++ >  tools/sched_ext/scx_userland.c     |  5 +++++ >  6 files changed, 43 insertions(+), 6 deletions(-) > > -- > 2.53.0 > > > I might be missing something, but the cover letter mentions a scx_pair busy-check cleanup that isn't > in the series, and the verification paragraph swaps patches 8 and 9 it seems. > > hope it helps.  You're right on both counts. Thanks for the careful read. The busy-check sentence is a leftover. The series originally included that cleanup, but I dropped it before posting because it became clear the path it removed has no observable behavioral difference (the would-be hijacking update always fails with -EBUSY anyway). I neglected to update the cover letter accordingly. The patch 8/9 swap is also just an editing mistake from the same late rewrite of the verification paragraph. Thanks, Tao