From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from mail-ed1-f66.google.com (mail-ed1-f66.google.com [209.85.208.66]) by dpdk.org (Postfix) with ESMTP id F3515F94 for ; Wed, 31 Oct 2018 18:47:51 +0100 (CET) Received: by mail-ed1-f66.google.com with SMTP id f8-v6so2034160edt.13 for ; Wed, 31 Oct 2018 10:47:51 -0700 (PDT) DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=netronome-com.20150623.gappssmtp.com; s=20150623; h=mime-version:references:in-reply-to:from:date:message-id:subject:to; bh=ay4atM6cQblZMoUuELizvDVS80uUcpVwwhC+yWbA3rs=; b=mE3eLQIS1Wyw1Z2HcWnZtV7MoEoE5qfhQREwXECXoTE3ASmIzD6tksVn9KPE1Rz5b8 I4kqKvL5sdVhUnHqK8KfLFZRWRZC7OIXzxnU52SAc8XXWn6Oau8/Wt9apFQniIHovJAx JSkULUjDUyju5KX/jbNsQgz+0LiUiXa0s3UOzuCH/3qcs6ricAdwM64yaOSkDOFNzQX8 XvR3d1ZNMV9mpCyh3E6hCBEwr9+Cw7NBDCArBY5/mjRkRFCK+F9Ymt98UROcHQlUGzEV Vq58E+lydbsol/ziwaO+mkkbGKY/RIHIXfFPtQ6DCLp8xdA1a9gB0z2xw8iSwJOWvjq7 BEKw== X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20161025; h=x-gm-message-state:mime-version:references:in-reply-to:from:date :message-id:subject:to; bh=ay4atM6cQblZMoUuELizvDVS80uUcpVwwhC+yWbA3rs=; b=jq60YHJx7i4N0rmL8CTjMkGEapDHeyx/bJ/a9aIOrfshK1Tj9wPP4vULg0g1/qrXsg Jbeai2Ly/kaxbcz9410zQxHIH2yOHLGXd4pxHnWS+/7uGeYJGfeEKI37Hd/IlMGGBlFX xzdhhU5cNAe5jsGJyDhl1C0tzdWzEbef1JSUecSFQGDXVjA8lE2dR15k5F7mp+oAt6kP HoedmTDqREmXFYfkTdMWGZPWk/W2vlQpMaAdj2emRFa9Cr3+f6+Zdlv5FTorMK7I8dKB koEkss4b2Bv6AbnMnoh0InaPvJBJx4AZTIKfwvl/0u2/k+b/reCiYewfu0nhZl8lxaVj 0K9g== X-Gm-Message-State: AGRZ1gKr3MIffiz+ZRjBotMAvJShKtHLgsSdCJvzqv9KUvz+BbXT9iFe 8vGQptDDB2xTqZ1PfvoM9nFYnMnLg9dlp8G3o4M3a8WM X-Google-Smtp-Source: AJdET5fRkTA75Z4k7aPrOCzZVsvcDYDNwEPjhWosDSb8cqa4OyVjtUpA9vNqOdRT1VoIJ9NGRDONqXQGjuQpgNG2GbA= X-Received: by 2002:a17:906:31db:: with SMTP id f27-v6mr2176389ejf.186.1541008071400; Wed, 31 Oct 2018 10:47:51 -0700 (PDT) MIME-Version: 1.0 References: <20181031172931.11894-1-alejandro.lucero@netronome.com> In-Reply-To: <20181031172931.11894-1-alejandro.lucero@netronome.com> From: Alejandro Lucero Date: Wed, 31 Oct 2018 17:47:40 +0000 Message-ID: To: dev Content-Type: text/plain; charset="UTF-8" X-Content-Filtered-By: Mailman/MimeDel 2.1.15 Subject: Re: [dpdk-dev] [PATCH 0/7] fix DMA mask check X-BeenThere: dev@dpdk.org X-Mailman-Version: 2.1.15 Precedence: list List-Id: DPDK patches and discussions List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , X-List-Received-Date: Wed, 31 Oct 2018 17:47:52 -0000 On Wed, Oct 31, 2018 at 5:29 PM Alejandro Lucero < alejandro.lucero@netronome.com> wrote: > A patchset sent introducing DMA mask checks has several critical > issues precluding apps to execute. The patchset was reviewed and > finally accepted after three versions. Obviously it did not go > through the proper testing what can be explained, at least from my > side, due to the big changes to the memory initialization code these > last months. It turns out the patchset did work with legacy memory > and I'm afraid that was mainly my testing. > > This patchset should solve the main problems reported: > > - deadlock duriing initialization > - segmentation fault with secondary processes > > For solving the deadlock, a new API is introduced: > > rte_mem_check_dma_mask_safe/unsafe > > making the previous rte_mem_check_dma_mask the one those new functions > end calling. A boolean param is used for calling rte_memseg_walk thread > safe or thread unsafe. This second option is needed for avoiding the > deadlock. > > For the secondary processes problem, the call to check the dma mask is > avoided from code being executed before the memory initialization. > Instead, a new API function, rte_mem_set_dma_mask is introduced, which > will be used in those cases. The dma mask check is done once the memory > initialization is completed. > > This last change implies the IOVA mode can not be set depending on IOMMU > hardware limitations, and it is assumed IOVA VA is possible. If the dma > mask check reports a problem after memory initilization, the error > message includes now advice for trying with --iova-mode option set to > pa. > > The patchet also includes the dma mask check for legacy memory and the > no hugepage option. > > Finally, all the DMA mask API has been updated for using the same prefix > than other EAL memory code. > > An initial version of this patchset has been tested by Intel DPDK > Validation team and it seems it solves all the problems reported. This > final patchset has the same functionality with minor changes. I have > successfully tested the patchset with my limited testbench. > > Alejandro Lucero (7): > mem: fix call to DMA mask check > mem: use proper prefix > mem: add function for setting DMA mask > bus/pci: avoid call to DMA mask check > mem: modify error message for DMA mask check > mem: add safe and unsafe versions for checking DMA mask > eal/mem: use DMA mask check for legacy memory > > doc/guides/rel_notes/release_18_11.rst | 2 +- > drivers/bus/pci/linux/pci.c | 11 ++++++- > drivers/net/nfp/nfp_net.c | 2 +- > lib/librte_eal/common/eal_common_memory.c | 36 +++++++++++++++++--- > lib/librte_eal/common/include/rte_memory.h | 37 +++++++++++++++++++-- > lib/librte_eal/common/malloc_heap.c | 38 ++++++++++++++++++---- > lib/librte_eal/linuxapp/eal/eal_memory.c | 17 ++++++++++ > lib/librte_eal/rte_eal_version.map | 4 ++- > 8 files changed, 131 insertions(+), 16 deletions(-) > > -- > 2.17.1 > > I have just realized that there is a minor problem with compiling one patch at a time, but it does compile when all applied. I will fix this in another version but I will wait until review and testing has been reported.