From mboxrd@z Thu Jan 1 00:00:00 1970 Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.remote-ip=74.208.142.49 ARC-Seal: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; cv=none; t=1793609223; b=FPSt6cRMtxmBjiSq8pysdZFN4mTBKhBpRDtDBPsFtJFA+u034v77F8Vomy0AQ+FtUlwg jN4Q0jD8ifDq7NQEmu4XhM9Cnn39tpDaqO6m6nZzSZ6g8DjgfMtqk9/ajUP9gp4vegadt 5dFUkc7ZFha5weVpIjc7IN4s4S0VPZppqFEovg11JBLULOhnK9rRwjeOzuok3DOIB+pjF 3HhC7dBE23NAi66ToCDiOXvH7bgYWhtfFaZNMhcTFsiV/xUjMliwqsRxZdy6Mcn8Pg+Sv 73ahRNh9/67GII4XAIUP2mxxGauNLNihRhGNewyMhfnz3iw99yM9mq/1H2e191Z6f1A== ARC-Message-Signature: i=1; d=subspace.kernel.org; s=arc20261015; a=rsa-sha256; c=relaxed/relaxed; t=1793609223; h=DMARC-Filter:DKIM-Signature:Received:From:To:Cc:Subject:Date: Message-ID:X-Mailer:In-Reply-To:References:MIME-Version: Content-Transfer-Encoding; bh=yuiWaWQDrq0Vg9DrcjhhGqt3JHN8TGxGS0CrvgppQHM=; b=h3d6LY7sW6/fUyC99LihgX5IhUvkFNooFa+l2cLjt3Mmz0r26DTIT2iulAjcHass9T7m yHMLXYUKUXEguu/XuuKc7sNJ2LNCcdjmjyS3GuG05YtE8+hn19+NnQiOkKUzrA8QxqF8v Lv53qoHYWHtYSLAqgtOJ/TUPaFzdWXTAhrF1+CKMJv/6IcEJSqnZw8wSE9jC+CAzlp5WP TKuCgm6nKvd7mXOCTqskQ0EsTsXAwi/dWB4S9O0LgE6mvGXopUBPH7D6vjkKz1s6ELaIg 0wvG2NVOm3l8UcK6XfNlXnkXELeLlPODucEyZ+xsUGQ1PNRh5ydBXqeMKqrisO6xdqw== ARC-Authentication-Results: i=1; smtp.subspace.kernel.org; dmarc=pass header.from=kernelriot.com; spf=pass smtp.mailfrom=kernelriot.com; dkim=pass header.d=kernelriot.com header.i=@kernelriot.com header.a=rsa-sha256 header.s=kr2026 header.b=Z1HGC3Hk; arc=none smtp.remote-ip=74.208.142.49 Received: from mail.kernelriot.com (mail.kernelriot.com [74.208.142.49]) (using TLSv1.3 with cipher TLS_AES_256_GCM_SHA384 (256/256 bits) key-exchange X25519 server-signature ECDSA (prime256v1)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id 5C243606A324; Mon, 2 Nov 2026 08:47:03 +0000 (UTC) DMARC-Filter: OpenDMARC Filter v1.4.2 smtp.subspace.kernel.org 5C243606A324 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=kernelriot.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=kernelriot.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key, unprotected) header.d=kernelriot.com header.i=@kernelriot.com header.a=rsa-sha256 header.s=kr2026 header.b=Z1HGC3Hk DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/simple; d=kernelriot.com; s=kr2026; t=1793609222; bh=yuiWaWQDrq0Vg9DrcjhhGqt3JHN8TGxGS0CrvgppQHM=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Transfer-Encoding:From; b=Z1HGC3HkR8D00Uh0FiLWurch+GQd10bwl2o2HDqhQXQmKVZsWi2pnIo94j6nTnyWI TePKg9UI0on9soMqJYZ2ICUTB36Ii7//aTV+5o5DRK54lTOlYvhqAfbIgo9+RlVUUh vXMW9ff3cdv1Jb8B1C8oAJw0+AFj+IvCiYR6Zra9xCqFH+Im3iei2uXeYIlafn+hz5 7/xaJcTPgVCNaaUzNFGJxOQL540GjMq2Xol/1KYHRCGo4Z6ovG5ogoLfPVpTQArYAg tSDTMGktKaG+xIgwD+RxTVMYCExwE6jmkcCKDjFhRBN3r0PjsfvpyY0xO+mXfMnIvX 5lWwKAUA9c+OA== Received: by mail.kernelriot.com (Postfix, from userid 995) id 22D0F81455; Mon, 2 Nov 2026 08:47:02 +0000 (UTC) From: Magnus Leatti To: Maxime Chevallier Cc: Andrew Lunn , Jakub Kicinski , davem@davemloft.net, Eric Dumazet , Paolo Abeni , Simon Horman , Maxime Coquelin , Alexandre Torgue , Russell King , Lorenzo Bianconi , Ovidiu Panait , Nicolai Buchwitz , thomas.petazzoni@bootlin.com, alexis.lothore@bootlin.com, netdev@vger.kernel.org, linux-kernel@vger.kernel.org, linux-arm-kernel@lists.infradead.org Subject: Re: [PATCH net] net: stmmac: Clear DMA errors for multi-channel interrupts Date: Mon, 2 Nov 2026 05:45:58 -0300 Message-ID: <20261102084558.5105-1-magnusleatti@kernelriot.com> X-Mailer: git-send-email 2.56.0 In-Reply-To: <20261030102251.208929-1-maxime.chevallier@bootlin.com> References: <20261030102251.208929-1-maxime.chevallier@bootlin.com> X-Mailing-List: netdev@vger.kernel.org List-Id: List-Post: List-Help: List-Subscribe: List-Unsubscribe: List-Owner: Precedence: list MIME-Version: 1.0 Content-Transfer-Encoding: 8bit On 10/30/26 11:22, Maxime Chevallier wrote: > The Multi-MSI interrupt handler doesn't clear the DMA error interrupts, > and this leads to interrupt storms when one of these interrupts starts > firing : Tested on a YT6801 (dwmac-motorcomm) with net at cb284914e749 and the glue unmodified. Without this patch, a 64-byte UDP flood (iperf3 -u -b 0 -l 64 -R -P 4) hangs the machine. On this board the stuck RBU also keeps the MISC bit in MGMT_INT_CTRL0 set, so vector 5 fires about 120k times per second. With the patch, the MAC interrupt only fires while the flood runs, about 1k/s, and stops afterwards; same with eight streams plus a TX flood for 30 s. Throughput is the same. Tested-by: Magnus Leatti nit: "YT8601" in the commit message should be YT6801.