Cover Detail
Show a cover letter.
GET /api/covers/83713/?format=api
{ "id": 83713, "url": "https://patches.dpdk.org/api/covers/83713/?format=api", "web_url": "https://patches.dpdk.org/project/dpdk/cover/20201105090423.11954-1-ndabilpuram@marvell.com/", "project": { "id": 1, "url": "https://patches.dpdk.org/api/projects/1/?format=api", "name": "DPDK", "link_name": "dpdk", "list_id": "dev.dpdk.org", "list_email": "dev@dpdk.org", "web_url": "http://core.dpdk.org", "scm_url": "git://dpdk.org/dpdk", "webscm_url": "http://git.dpdk.org/dpdk", "list_archive_url": "https://inbox.dpdk.org/dev", "list_archive_url_format": "https://inbox.dpdk.org/dev/{}", "commit_url_format": "" }, "msgid": "<20201105090423.11954-1-ndabilpuram@marvell.com>", "list_archive_url": "https://inbox.dpdk.org/dev/20201105090423.11954-1-ndabilpuram@marvell.com", "date": "2020-11-05T09:04:20", "name": "[v2,0/3] fix issue with partial DMA unmap", "submitter": { "id": 1202, "url": "https://patches.dpdk.org/api/people/1202/?format=api", "name": "Nithin Dabilpuram", "email": "ndabilpuram@marvell.com" }, "mbox": "https://patches.dpdk.org/project/dpdk/cover/20201105090423.11954-1-ndabilpuram@marvell.com/mbox/", "series": [ { "id": 13683, "url": "https://patches.dpdk.org/api/series/13683/?format=api", "web_url": "https://patches.dpdk.org/project/dpdk/list/?series=13683", "date": "2020-11-05T09:04:20", "name": "fix issue with partial DMA unmap", "version": 2, "mbox": "https://patches.dpdk.org/series/13683/mbox/" } ], "comments": "https://patches.dpdk.org/api/covers/83713/comments/", "headers": { "Return-Path": "<dev-bounces@dpdk.org>", "X-Original-To": "patchwork@inbox.dpdk.org", "Delivered-To": "patchwork@inbox.dpdk.org", "Received": [ "from dpdk.org (dpdk.org [92.243.14.124])\n\tby inbox.dpdk.org (Postfix) with ESMTP id 2795BA04B1;\n\tThu, 5 Nov 2020 10:04:34 +0100 (CET)", "from [92.243.14.124] (localhost [127.0.0.1])\n\tby dpdk.org (Postfix) with ESMTP id F1F757CAE;\n\tThu, 5 Nov 2020 10:04:32 +0100 (CET)", "from mx0b-0016f401.pphosted.com (mx0a-0016f401.pphosted.com\n [67.231.148.174]) by dpdk.org (Postfix) with ESMTP id 068CC6CAC\n for <dev@dpdk.org>; Thu, 5 Nov 2020 10:04:31 +0100 (CET)", "from pps.filterd (m0045849.ppops.net [127.0.0.1])\n by mx0a-0016f401.pphosted.com (8.16.0.42/8.16.0.42) with SMTP id\n 0A5900PS028629; Thu, 5 Nov 2020 01:04:30 -0800", "from sc-exch01.marvell.com ([199.233.58.181])\n by mx0a-0016f401.pphosted.com with ESMTP id 34mbfcrndg-2\n (version=TLSv1.2 cipher=ECDHE-RSA-AES256-SHA384 bits=256 verify=NOT);\n Thu, 05 Nov 2020 01:04:30 -0800", "from DC5-EXCH02.marvell.com (10.69.176.39) by SC-EXCH01.marvell.com\n (10.93.176.81) with Microsoft SMTP Server (TLS) id 15.0.1497.2;\n Thu, 5 Nov 2020 01:04:27 -0800", "from maili.marvell.com (10.69.176.80) by DC5-EXCH02.marvell.com\n (10.69.176.39) with Microsoft SMTP Server id 15.0.1497.2 via Frontend\n Transport; Thu, 5 Nov 2020 01:04:27 -0800", "from hyd1588t430.marvell.com (unknown [10.29.52.204])\n by maili.marvell.com (Postfix) with ESMTP id 1E6363F703F;\n Thu, 5 Nov 2020 01:04:25 -0800 (PST)" ], "DKIM-Signature": "v=1; a=rsa-sha256; c=relaxed/relaxed; d=marvell.com;\n h=from : to : cc :\n subject : date : message-id : in-reply-to : references : mime-version :\n content-type; s=pfpt0220; bh=mtJkplKQGMekQ4A0g0HtsqBm+Dnu2TMJXB3kqwJ0xj8=;\n b=a/2VwUxW92Cme2jB5xSXtYOIh87pE/9wIFxB+tbC2SrM8Vh4BAxEPb2Q3aHH+7xEv6np\n 1lSNI23oadWPD4BuxZ9WPP0andU9fvkv1zlOnTDXsGSX48RY8WUTw9lx5ouImnTRbMRm\n mrAC3U6JAtYuvJ2fOcF2wQJWl1HWnBKs/4Xgzm0S2tIE40/zqyZNG2OdXi46AIRrKxXo\n ipwgSura4/gKjbZ3J7LnXmkx9KpIH+OVcoc7CpctkWNXWK8Hl2lkBxFuzu5008VdEh5H\n omRI+lAUdCUa61P4gNqSNI+2ZxQXD7UqnPsx4uVq//YycOnCY14q/1TWXpjf/O8TEy2A Qg==", "From": "Nithin Dabilpuram <ndabilpuram@marvell.com>", "To": "<anatoly.burakov@intel.com>", "CC": "<jerinj@marvell.com>, <dev@dpdk.org>, Nithin Dabilpuram\n <ndabilpuram@marvell.com>", "Date": "Thu, 5 Nov 2020 14:34:20 +0530", "Message-ID": "<20201105090423.11954-1-ndabilpuram@marvell.com>", "X-Mailer": "git-send-email 2.8.4", "In-Reply-To": "<20201012081106.10610-1-ndabilpuram@marvell.com>", "References": "<20201012081106.10610-1-ndabilpuram@marvell.com>", "MIME-Version": "1.0", "Content-Type": "text/plain", "X-Proofpoint-Virus-Version": "vendor=fsecure engine=2.50.10434:6.0.312, 18.0.737\n definitions=2020-11-05_05:2020-11-05,\n 2020-11-05 signatures=0", "Subject": "[dpdk-dev] [PATCH v2 0/3] fix issue with partial DMA unmap", "X-BeenThere": "dev@dpdk.org", "X-Mailman-Version": "2.1.15", "Precedence": "list", "List-Id": "DPDK patches and discussions <dev.dpdk.org>", "List-Unsubscribe": "<https://mails.dpdk.org/options/dev>,\n <mailto:dev-request@dpdk.org?subject=unsubscribe>", "List-Archive": "<http://mails.dpdk.org/archives/dev/>", "List-Post": "<mailto:dev@dpdk.org>", "List-Help": "<mailto:dev-request@dpdk.org?subject=help>", "List-Subscribe": "<https://mails.dpdk.org/listinfo/dev>,\n <mailto:dev-request@dpdk.org?subject=subscribe>", "Errors-To": "dev-bounces@dpdk.org", "Sender": "\"dev\" <dev-bounces@dpdk.org>" }, "content": "Partial DMA unmap is not supported by VFIO type1 IOMMU\nin Linux. Though the return value is zero, the returned\nDMA unmap size is not same as expected size.\nSo add test case and fix to both heap triggered DMA\nmapping and user triggered DMA mapping/unmapping.\n\nRefer vfio_dma_do_unmap() in drivers/vfio/vfio_iommu_type1.c\nSnippet of comment is below.\n\n /*\n * vfio-iommu-type1 (v1) - User mappings were coalesced together to\n * avoid tracking individual mappings. This means that the granularity\n * of the original mapping was lost and the user was allowed to attempt\n * to unmap any range. Depending on the contiguousness of physical\n * memory and page sizes supported by the IOMMU, arbitrary unmaps may\n * or may not have worked. We only guaranteed unmap granularity\n * matching the original mapping; even though it was untracked here,\n * the original mappings are reflected in IOMMU mappings. This\n * resulted in a couple unusual behaviors. First, if a range is not\n * able to be unmapped, ex. a set of 4k pages that was mapped as a\n * 2M hugepage into the IOMMU, the unmap ioctl returns success but with\n * a zero sized unmap. Also, if an unmap request overlaps the first\n * address of a hugepage, the IOMMU will unmap the entire hugepage.\n * This also returns success and the returned unmap size reflects the\n * actual size unmapped.\n\n * We attempt to maintain compatibility with this \"v1\" interface, but \n * we take control out of the hands of the IOMMU. Therefore, an unmap \n * request offset from the beginning of the original mapping will \n * return success with zero sized unmap. And an unmap request covering\n * the first iova of mapping will unmap the entire range. \n\nThis behavior can be verified by using first patch and add return check for\ndma_unmap.size != len in vfio_type1_dma_mem_map()\n\nv2: \n- Reverted earlier commit that enables mergin contiguous mapping for\n IOVA as PA. (see 1/3)\n- Updated documentation about kernel dma mapping limits and vfio\n module parameter.\n- Moved vfio test to test_vfio.c and handled comments from\n Anatoly.\n\n\nNithin Dabilpuram (3):\n vfio: revert changes for map contiguous areas in one go\n vfio: fix DMA mapping granularity for type1 iova as va\n test: add test case to validate VFIO DMA map/unmap\n\n app/test/meson.build | 1 +\n app/test/test_vfio.c | 103 +++++++++++++++++++++++++++++++++\n doc/guides/linux_gsg/linux_drivers.rst | 10 ++++\n lib/librte_eal/linux/eal_vfio.c | 93 ++++++++++++-----------------\n lib/librte_eal/linux/eal_vfio.h | 1 +\n 5 files changed, 151 insertions(+), 57 deletions(-)\n create mode 100644 app/test/test_vfio.c" }