From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mail-yx2-f41.google.com (mail-yx2-f41.google.com [74.125.224.169]) (using TLSv1.2 with cipher ECDHE-RSA-AES128-GCM-SHA256 (128/128 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 54FF24A8FD9 for ; Thu, 24 Sep 2026 16:30:22 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=74.125.224.169 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790267423; cv=none; b=fpLuDA2YBbedmZC/5FcFmwycNt7ubMlZhJz+25zohSwpIJ5ynAh9+33GdQwZJN774A4NVIKoB8BnJztLeJL+FjMo3A/TVmRKdRzZoN2K3ptnmzf9fDjXcJ/v9HimBrW9sT5xu0amIAJew44AZ62hZfpu/js396rlLxCudfscaQc= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1790267423; c=relaxed/simple; bh=73k6FJTz+3Iw7WPeGZfV2lzEAXI++hDZctysXJS34no=; h=Content-Type:Date:Message-Id:Cc:Subject:From:To:In-Reply-To: References:MIME-Version; b=VQXDM8FGoqae8eSdj5Y0Y1HqfnihcgR3loMnO0W5d2kh5TdrGv6w9/EJtR1cIvpVTeoJNxv/lSz7JLkpoImlrM/FWfYN073blKVBy1+TkP9zCVnQUsq6NsGqlCXU3XGdRhqX+Dhz73reFlWqeD1A9umYilV5e3TvScXannYGZkI= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com; spf=pass smtp.mailfrom=gmail.com; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b=ZqUHkwNH; arc=none smtp.client-ip=74.125.224.169 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=gmail.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=gmail.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=gmail.com header.i=@gmail.com header.b="ZqUHkwNH" Received: by mail-yx2-f41.google.com with SMTP id 00721157ae682-8a8288165fbso187707b3.0 for ; Thu, 24 Sep 2026 09:30:22 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=gmail.com; s=20251104; t=1790267421; x=1790872221; darn=lists.linux.dev; h=mime-version:content-transfer-encoding:references:in-reply-to:to :from:subject:cc:message-id:date:content-type:from:to:cc:subject :date:message-id:reply-to:content-type; bh=73k6FJTz+3Iw7WPeGZfV2lzEAXI++hDZctysXJS34no=; b=ZqUHkwNHXIgDJPtIF0rJmVFQ1TZ948Bbh4OrzILwf2C7k+szzmrstSx8ITWh3nhT92 aYNvin7RSmR3sOrzCYau92bEOR8DzfaRQrESL4fb8JCU/bEISWy4IOm55SQtiDi7pwN9 IGnmAyyfayTR1x1YKh/r8kxq0uQGVlGrzqFV4nrZR0/Em8ytR2T+pQNywK286fgB30S6 L83xeDjyfslYSY9G17hXT6wQbTTdt/zCZXOdkrh8nKxRMG2BepmKl4tKAkD/n6pYgdyf vUjNwG6fbA46dwDlp5RFs75b8KiwjAuYkN31ws4SYFHd4fadQB/DfjOyGpcWJ3/FbuTF 1ppw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20260707; t=1790267421; x=1790872221; h=mime-version:content-transfer-encoding:references:in-reply-to:to :from:subject:cc:message-id:date:content-type:x-gm-gg :x-gm-message-state:from:to:cc:subject:date:message-id:reply-to :content-type; bh=73k6FJTz+3Iw7WPeGZfV2lzEAXI++hDZctysXJS34no=; b=i6xNs8fgaGunPBX5dEeaMvxh9ZDOgWuW0F8nBwP+MopTXYBOLxsW9k9X6VF5epUU2D 1OIWgS2A8+tnAJSdL6nf47cX6T0DpJZ1ychamSdr6d56YFaju3//oIGglAxcqFDNjLgv Na3WN6Tcr+3dDVMCFJ7Tjq2vvzv0VgSwC25k2ZR6HOHL//mVGFJovVf06bpjzZFhQJBm 01cugn1sTBgfx1Zi3E5Xwsgk3IGnj3giy2cHnQsX2C/DopjgDTX7PjnQAMPgTGS5qL3z F8NOYVXeump2+sVFbormaAQEaGBL2Zhi51vom0qmdkFdU47/itMt9rn6gZ44zdEuRHpc W1LA== X-Forwarded-Encrypted: i=1; AKwUvBxaUG10uAh8xUVDuD8r/Ttu3kE+JMh/gjCf60wlW0I/DS1UsjdROcN/RJ6bhPz+zZP5LhGDtWqu2gQ=@lists.linux.dev X-Gm-Message-State: AFuF++nLaD3H1hBT22cMpG7WkIFHPj9+hshClUz+X5Vef+bjcvv8vh5N J+q3M53kxoX8UcSs1GlC3pTVX2ywSNR6Vm5xtCoPYw8Elw5yEA6vCq14 X-Gm-Gg: AYBFou3OlMDksS4NZyWdNcfzzUBaFT7YUlRSzHZ1gBX+fDKD60JL1EmyaQSPbklMQcL HP6EckANwX4wrzNN7prY92Y1HZrdW9XCN9hUiBGy94Fk52uCw0EHb9N3jGL9jjRuUCH+zqGmJok 32GK86415aVYkOzAjSKyycRErjkK4XqrZeqpmfnjpPetuoKdXQt1zp7p1EwTrC1G46CN2f5M03L vhLyvLBWCJNP+FrnqIKsOw8TtRdD6SUIi4tCc539tIvtFuABsYOav/c8SWnzPkoAvCFAwYwWs73 jjf2zXFkZEDFbq7ejLW1kGVS8HbM8I4ew/hjdWCWwKb6RE6ZcD5QLRg9fXypAkie7hcklWQFuxB ZEB4/f0+aV0AoeU5ykF39dIBu3JEz5z5MHymnpo9yRaKeKzwOohCXlqIYP0aiX6pHrKyqWsoFUB guiodJGs/ILCl0e+uSZme3NsqWh9FE8fFUNnC6PHZRRuig1J6O+BNN+UzCXCrvCnEectIIpWl30 E4eNC8lj5avEOJfPRolAroGvU+SjJHfaS0kCdFYQfsYUccvMFDsmG8MG3vtSw4c+BsGKPR99xPI rVKn X-Received: by 2002:a05:690c:e3cb:b0:8a0:9ec0:e13b with SMTP id 00721157ae682-8a648ec5183mr21164237b3.17.1790267419358; Thu, 24 Sep 2026 09:30:19 -0700 (PDT) Received: from localhost ([153.61.198.249]) by smtp.gmail.com with ESMTPSA id 00721157ae682-8a6525dc675sm10883477b3.34.2026.09.24.09.30.17 (version=TLS1_3 cipher=TLS_AES_128_GCM_SHA256 bits=128/128); Thu, 24 Sep 2026 09:30:18 -0700 (PDT) Content-Type: text/plain; charset=UTF-8 Date: Thu, 24 Sep 2026 16:30:16 +0000 Message-Id: Cc: "Daniel Borkmann" , "Andrii Nakryiko" , "Martin KaFai Lau" , "Eduard Zingerman" , "Kumar Kartikeya Dwivedi" , "Song Liu" , "Yonghong Song" , "Tejun Heo" , "David Vernet" , "Andrea Righi" , "Changwoo Min" , , Subject: Re: [PATCH bpf-next v2 3/3] sched_ext: Stop citing the x86 JIT for the cmask cmpxchg loop From: "Alexei Starovoitov" To: "Puranjay Mohan" , In-Reply-To: <20260924160354.531101-4-puranjay@kernel.org> References: <20260924160354.531101-1-puranjay@kernel.org> <20260924160354.531101-4-puranjay@kernel.org> X-Mailer: mkdraft (claude review draft; edit before sending) Content-Transfer-Encoding: 8bit Precedence: bulk X-Mailing-List: sched-ext@lists.linux.dev List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 On Thu, Sep 24, 2026 at 09:03 AM Puranjay Mohan wrote: > - * x86 BPF JIT rejects BPF_OR | BPF_FETCH and BPF_AND | BPF_FETCH on arena > - * pointers (see bpf_jit_supports_insn() in arch/x86/net/bpf_jit_comp.c). Only > - * BPF_CMPXCHG / BPF_XCHG / BPF_ADD with FETCH are allowed. Implement > - * test_and_{set,clear} and the atomic set/clear via a cmpxchg loop. > + * Not every BPF JIT accepts BPF_OR | BPF_FETCH and BPF_AND | BPF_FETCH on > + * arena pointers: arm64 without LSE rejects every arena read-modify-write > + * atomic. Implement test_and_{set,clear} and the atomic set/clear via a > + * cmpxchg loop so this works everywhere. arm64 without LSE rejects BPF_CMPXCHG in arena too. bpf_jit_supports_insn() there returns false for everything that is not load_acq/store_rel, so the loop doesn't load on such cpu either. riscv without Zacas is the other way around. It rejects arena cmpxchg and accepts fetching and/or. So the loop doesn't make it work everywhere. After patch 1 can cmask_set/clear/test_and_set/test_and_clear be __sync_fetch_and_or/and and CMASK_CAS_TRIES go away ? pw-bot: cr