From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mails.dpdk.org (mails.dpdk.org [217.70.189.124]) by inbox.dpdk.org (Postfix) with ESMTP id 8EE6546DF8; Thu, 28 Aug 2025 16:45:48 +0200 (CEST) Received: from mails.dpdk.org (localhost [127.0.0.1]) by mails.dpdk.org (Postfix) with ESMTP id 2ADF84025A; Thu, 28 Aug 2025 16:45:48 +0200 (CEST) Received: from mail-wr1-f46.google.com (mail-wr1-f46.google.com [209.85.221.46]) by mails.dpdk.org (Postfix) with ESMTP id 61F81400D6 for ; Thu, 28 Aug 2025 16:45:46 +0200 (CEST) Received: by mail-wr1-f46.google.com with SMTP id ffacd0b85a97d-3cd59c5a953so676502f8f.0 for ; Thu, 28 Aug 2025 07:45:46 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=networkplumber-org.20230601.gappssmtp.com; s=20230601; t=1756392346; x=1756997146; darn=dpdk.org; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:from:to:cc:subject:date :message-id:reply-to; bh=WtM0ITmssz6BdTVgVZI1gj+gpm7ZUb9hQQJd9+G6j9Y=; b=Oy3r9NzKpH1Q9HPmjLCAlY6bPJS6/kgdPbMAGJ3XybSBPAp54NODZ2rZvuEQ8M7dY3 7raj24McaCjh3nACqzR6/Vrmq+/05bPZ3H3THa9wthTkSnI9UBfbexwSAE2t0WrdI0EY lGuX4Y8PDtED4C4Aa7LBJCiUUT76tHNh3r+w5oanIjeqR3uDr5HMrxc/e/n6lfWwMyXl mxxejhcXyyMDRIbRJ+ayURs9uK829gjVzV6h7QmQLiClxZL5U84w6OWkdgu433VhMxdx KVZW90ZNiP37r9xUCCK1fvKE8k0YJFxdP1c4AAEjiFvutVIFSQ+z2jvXYTov/pvo7kQK fqeQ== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20230601; t=1756392346; x=1756997146; h=content-transfer-encoding:mime-version:references:in-reply-to :message-id:subject:cc:to:from:date:x-gm-message-state:from:to:cc :subject:date:message-id:reply-to; bh=WtM0ITmssz6BdTVgVZI1gj+gpm7ZUb9hQQJd9+G6j9Y=; b=RxJQbP4gClu1W7zkUtlIJb0Ciw6nZIICAn/cqLPzaJm1A4o+xzQr1nEGVV3OgX+OC7 xtf16Iwdyorsm+40tt36AkASTbm2tIkM8oOCF5ZxSzg0Z90DDAvbm51adNejlDL34fCr 8GgautY3MqA/m+jcFXyN7KiWjyuBrwbRcp/feCjeIHZbrIxxLHyo3sda7Jjdo3hHscz/ w2Wg1qNVE+MW4o/awpEDa+1/1rH7Epm/mVmkyKScElEPuRwEhdvA1nGHCMDV1YJZkeC4 aUk6RZg63mHyuxqq3Nkwo7gmjIkOT30SXR8LHHZrna+qEsWCle2/UkBbMEzFaBwB9ixh GPYA== X-Gm-Message-State: AOJu0YwztKWE8oiHmrpNR/uaJCZJhtC83INVC9UXKJ9OyHQrd+cGkFFV ZFMj9jOzXng+FkG7+pX8K4aR4mVc4YLXMGU6EgnfkHFnOzry4vqKOhB9qA1rFyXDf14= X-Gm-Gg: ASbGncsjqR8kHepB2Q2ML0lEdhRDSmN+USVxWIt5k5ESme/oT4/jW+OcXg3tE5YIH65 cqAQaZBxt3j1s3+Pn8VNcfFxQYRedtEsHxAeNJevt8AmArNaAia2wcpePQK379xX/gzz/uvlp7e rulET+rFBg2W0lQ982MU8pkh15qRlqRYIOv8KeccO90oioUNmZZEEM3lAdoeXE+ZEBMo+0l2Dhl CCe7WvPzJ3aGtGf1lxnzbye0bDUnLUxh/QYdDLGFFqGJHBrw4TRgxwfrIaAUlAut4qfFm/rE+6Y e29gtSyxUAFkVPs7Xx564KiBDfIk6fzJA0Jo33wLFw2I5pbu29fmLNPOtNeWxqxoy4W4c9F4SBI PYsJN9I+iFDV2ex8ZNv8dioIJEhIIXNmomOkHQ5l+Z85J3Lyo4tSKEeKpF1hjju0M8LfSiqzL3Z Ab84kxSAULfQ== X-Google-Smtp-Source: AGHT+IHVfebYNXpRx3Gw8StUyWmM7PmEN8eqjOPyp7546bfjcp1ILRD7ikZu3T/0PwMCL87z8J6LHA== X-Received: by 2002:a05:6000:40df:b0:3c7:5844:333d with SMTP id ffacd0b85a97d-3c758443855mr15309070f8f.45.1756392345629; Thu, 28 Aug 2025 07:45:45 -0700 (PDT) Received: from hermes.local (204-195-96-226.wavecable.com. [204.195.96.226]) by smtp.gmail.com with ESMTPSA id 5b1f17b1804b1-45b73c52735sm57472345e9.22.2025.08.28.07.45.44 (version=TLS1_3 cipher=TLS_AES_256_GCM_SHA384 bits=256/256); Thu, 28 Aug 2025 07:45:45 -0700 (PDT) Date: Thu, 28 Aug 2025 07:45:41 -0700 From: Stephen Hemminger To: "Doraemon" Cc: "dev" Subject: Re: [Help needed] net_ice: MDD event (Malicious Driver Detection) on TX queue when using rte_eth_tx_prepare / rte_eth_tx_burst Message-ID: <20250828074541.2996da5a@hermes.local> In-Reply-To: References: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: quoted-printable X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.29 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: dev-bounces@dpdk.org On Wed, 27 Aug 2025 08:52:26 +0800 "Doraemon" wrote: > Hello DPDK / net_ice maintainers, >=20 >=20 > We are seeing a reproducible and concerning issue when using the net_ice = PMD with DPDK 22.11.2, and we would appreciate your help diagnosing it. >=20 >=20 > Summary > - Environment: > - DPDK: 22.11.2 > - net_ice PCI device: 8086:159b > - ice kernel driver: 1.12.7 > - NIC firmware: FW 7.3.6111681 (NVM 4.30) > - IOVA mode: PA, VFIO enabled > - Multi-process socket: /var/run/dpdk/PGW/mp_socket > - NUMA: 2, detected lcores: 112 > - Bonding: pmd_bond with bonded devices created (net_bonding0 on port 4, = net_bonding1 on port 5) > - Driver enabled AVX2 OFFLOAD Vector Tx (log shows "ice_set_tx_function()= : Using AVX2 OFFLOAD Vector Tx") >=20 >=20 > - Problem statement: > - Our application calls rte_eth_tx_prepare before calling rte_eth_tx_burs= t as part of the normal transmission path. > - After the application has been running for some time (not immediate), t= he kernel/driver emits the following messages repeatedly: > - ice_interrupt_handler(): OICR: MDD event > - ice_interrupt_handler(): Malicious Driver Detection event 3 by TCLAN on= TX queue 1025 PF# 1 > - We are using a single TX queue (application-level single queue) and are= sending only one packet per burst (burst size =3D 1). > - The sequence is: rte_eth_tx_prepare (returns) -> rte_eth_tx_burst -&= gt; MDD events occur later. > - The events affect stability and repeat over time. >=20 >=20 > Relevant startup logs (excerpt) > EAL: Detected CPU lcores: 112 > EAL: Detected NUMA nodes: 2 > EAL: Selected IOVA mode 'PA' > EAL: VFIO support initialized > EAL: Probe PCI driver: net_ice (8086:159b) device: 0000:3b:00.1 (socket 0) > ice_load_pkg_type(): Active package is: 1.3.45.0, ICE COMMS Package (doub= le VLAN mode) > ice_dev_init(): FW 7.3.6111681 API 1.7 > ... > bond_probe(3506) - Initializing pmd_bond for net_bonding0 > bond_probe(3592) - Create bonded device net_bonding0 on port 4 in mode 1 = on socket 0. > ... > ice_set_tx_function(): Using AVX2 OFFLOAD Vector Tx (port 0). > TELEMETRY: No legacy callbacks, legacy socket not created >=20 >=20 > What we have tried / preliminary observations > - Confirmed application calls rte_eth_tx_prepare prior to rte_eth_tx_burs= t. > - Confirmed single TX queue configuration and small bursts (size =3D 1) = =E2=80=94 not high-rate, not a typical high-burst/malicious pattern. > - The MDD log identifies "TX queue 1025";  unclear how that maps to = our DPDK queue numbering (we use queue 0 in the app). > - No obvious other DPDK errors at startup;  interface initializes no= rmally and vector TX is enabled. > - We suspect the driver's Malicious Driver Detection (MDD) is triggering = due to some descriptor/doorbell ordering or offload interaction, possibly r= elated to AVX2 Vector Tx offload. >=20 >=20 > Questions / requests to the maintainers > 1.  What specifically triggers "MDD event 3 by TCLAN" in net_ice?&nb= sp; Which driver check/threshold corresponds to event type 3? > 2.  How is the "TX queue 1025" value computed/mapped in the log?&nbs= p; (Is it queue id + offset, VF mapping, or an internal vector id?)  W= e need to map that log value to our DPDK queue index. > 3.  Can the rte_eth_tx_prepare + rte_eth_tx_burst call pattern cause= MDD detections under any circumstances?  If so, are there recommended= usage patterns or ordering constraints to avoid false positives? > 4.  Are there known firmware/driver/DPDK version combinations with s= imilar MDD behavior?  Do you recommend specific NIC firmware, kernel d= river, or DPDK versions as a workaround/fix? > 5.  Any suggested workarounds we can test quickly (e.g., disable vec= tor TX offload, disable specific HW offloads, change interrupt/queue bindin= gs, or adjust doorbell behavior)? >=20 >=20 >=20 >=20 > Best regards. Did you make sure that the source address of the packet matches the MAC add= ress of teh VF?