Patch Detail
get:
Show a patch.
patch:
Update a patch.
put:
Update a patch.
GET /api/patches/1187/?format=api
{ "id": 1187, "url": "https://patches.dpdk.org/api/patches/1187/?format=api", "web_url": "https://patches.dpdk.org/project/dpdk/patch/C6ECDF3AB251BE4894318F4E4512369780C07848@IRSMSX109.ger.corp.intel.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": "<C6ECDF3AB251BE4894318F4E4512369780C07848@IRSMSX109.ger.corp.intel.com>", "list_archive_url": "https://inbox.dpdk.org/dev/C6ECDF3AB251BE4894318F4E4512369780C07848@IRSMSX109.ger.corp.intel.com", "date": "2014-11-07T10:00:57", "name": "[dpdk-dev,v6] eal: map uio resources after hugepages when the base_virtaddr is configured.", "commit_ref": null, "pull_url": null, "state": "not-applicable", "archived": true, "hash": "c144a882466da9eaf9637fec9fe7f69031719676", "submitter": { "id": 4, "url": "https://patches.dpdk.org/api/people/4/?format=api", "name": "Burakov, Anatoly", "email": "anatoly.burakov@intel.com" }, "delegate": null, "mbox": "https://patches.dpdk.org/project/dpdk/patch/C6ECDF3AB251BE4894318F4E4512369780C07848@IRSMSX109.ger.corp.intel.com/mbox/", "series": [], "comments": "https://patches.dpdk.org/api/patches/1187/comments/", "check": "pending", "checks": "https://patches.dpdk.org/api/patches/1187/checks/", "tags": {}, "related": [], "headers": { "Return-Path": "<dev-bounces@dpdk.org>", "X-Original-To": "patchwork@dpdk.org", "Delivered-To": "patchwork@dpdk.org", "Received": [ "from [92.243.14.124] (localhost [IPv6:::1])\n\tby dpdk.org (Postfix) with ESMTP id 3F70C7F2C;\n\tFri, 7 Nov 2014 10:53:53 +0100 (CET)", "from mga01.intel.com (mga01.intel.com [192.55.52.88])\n\tby dpdk.org (Postfix) with ESMTP id 2EF227EC4\n\tfor <dev@dpdk.org>; Fri, 7 Nov 2014 10:53:45 +0100 (CET)", "from fmsmga002.fm.intel.com ([10.253.24.26])\n\tby fmsmga101.fm.intel.com with ESMTP; 07 Nov 2014 02:02:55 -0800", "from irsmsx104.ger.corp.intel.com ([163.33.3.159])\n\tby fmsmga002.fm.intel.com with ESMTP; 07 Nov 2014 02:02:40 -0800", "from irsmsx107.ger.corp.intel.com (163.33.3.99) by\n\tIRSMSX104.ger.corp.intel.com (163.33.3.159) with Microsoft SMTP\n\tServer (TLS) id 14.3.195.1; Fri, 7 Nov 2014 10:00:58 +0000", "from irsmsx109.ger.corp.intel.com ([169.254.13.101]) by\n\tIRSMSX107.ger.corp.intel.com ([169.254.10.154]) with mapi id\n\t14.03.0195.001; Fri, 7 Nov 2014 10:00:57 +0000" ], "X-ExtLoop1": "1", "X-IronPort-AV": "E=Sophos;i=\"5.07,331,1413270000\"; \n\td=\"scan'208,217\";a=\"628228403\"", "From": "\"Burakov, Anatoly\" <anatoly.burakov@intel.com>", "To": "XU Liang <liang.xu@cinfotech.cn>, \"dev@dpdk.org\" <dev@dpdk.org>", "Thread-Topic": "[PATCH v6] eal: map uio resources after hugepages when the\n\tbase_virtaddr is configured.", "Thread-Index": "AQHP+mEdCoJJM6uhEkSpotX1GZcOhJxU7g3YgAAALIA=", "Date": "Fri, 7 Nov 2014 10:00:57 +0000", "Message-ID": "<C6ECDF3AB251BE4894318F4E4512369780C07848@IRSMSX109.ger.corp.intel.com>", "References": "<1415193919-17361-1-git-send-email-liang.xu@cinfotech.cn>\n\t<1415347284-15468-1-git-send-email-liang.xu@cinfotech.cn>,\n\tC6ECDF3AB251BE4894318F4E4512369780C07822@IRSMSX109.ger.corp.intel.com\n\t<2c2ad9a4-1c04-4641-9667-249617ae2c56@cinfotech.cn>", "In-Reply-To": "<2c2ad9a4-1c04-4641-9667-249617ae2c56@cinfotech.cn>", "Accept-Language": "en-US", "Content-Language": "en-US", "X-MS-Has-Attach": "", "X-MS-TNEF-Correlator": "", "x-originating-ip": "[163.33.239.180]", "MIME-Version": "1.0", "Content-Type": "text/plain; charset=\"utf-8\"", "Content-Transfer-Encoding": "base64", "X-Content-Filtered-By": "Mailman/MimeDel 2.1.15", "Subject": "Re: [dpdk-dev] [PATCH v6] eal: map uio resources after hugepages\n\twhen the base_virtaddr is configured.", "X-BeenThere": "dev@dpdk.org", "X-Mailman-Version": "2.1.15", "Precedence": "list", "List-Id": "patches and discussions about DPDK <dev.dpdk.org>", "List-Unsubscribe": "<http://dpdk.org/ml/options/dev>,\n\t<mailto:dev-request@dpdk.org?subject=unsubscribe>", "List-Archive": "<http://dpdk.org/ml/archives/dev/>", "List-Post": "<mailto:dev@dpdk.org>", "List-Help": "<mailto:dev-request@dpdk.org?subject=help>", "List-Subscribe": "<http://dpdk.org/ml/listinfo/dev>,\n\t<mailto:dev-request@dpdk.org?subject=subscribe>", "Errors-To": "dev-bounces@dpdk.org", "Sender": "\"dev\" <dev-bounces@dpdk.org>" }, "content": "Ah, yes, sorry about that, haven’t quite woke up yet ☹ You’re right. So it’s removing the dependency on --base-virtaddr, moving the function to eal_pci.c and adding similar VFIO code that’s left then.\r\n\r\nThanks,\r\nAnatoly\r\n\r\nFrom: XU Liang [mailto:liang.xu@cinfotech.cn]\r\nSent: Friday, November 7, 2014 9:57 AM\r\nTo: Burakov, Anatoly; dev@dpdk.org\r\nCc: thomas.monjalon@6wind.com; De Lara Guarch, Pablo\r\nSubject: Re: [PATCH v6] eal: map uio resources after hugepages when the base_virtaddr is configured.\r\n\r\nHow to find the maximum end virtual address ? I'm not the DPDK expert, but I will try to do my best.\r\n\r\nIf the segments isn't overlap, \"if(seg->addr > last->addr) last = seg;\" already find the segment with maximum end virtual address.\r\n\r\n------------------------------------------------------------------\r\nFrom:Burakov, Anatoly <anatoly.burakov@intel.com<mailto:anatoly.burakov@intel.com>>\r\nTime:2014 Nov 7 (Fri) 17 : 47\r\nTo:徐亮 <liang.xu@cinfotech.cn<mailto:liang.xu@cinfotech.cn>>, dev@dpdk.org<mailto:dev@dpdk.org> <dev@dpdk.org<mailto:dev@dpdk.org>>\r\nCc:thomas.monjalon@6wind.com <thomas.monjalon@6wind.com<mailto:thomas.monjalon@6wind.com>>, De Lara Guarch, Pablo <pablo.de.lara.guarch@intel.com<mailto:pablo.de.lara.guarch@intel.com>>\r\nSubject:RE: [PATCH v6] eal: map uio resources after hugepages when the base_virtaddr is configured.\r\n\r\nThe commit message looks fine to me, but VFIO code needs to be adjusted the same way.\r\n\r\nAlso, now that I think of it, you can't simply assume that whatever last memseg you have has the latest virtual address. When IVSHMEM is initialized, it too reserves some space in the virtual memory, which can be higher than the last hugepage, but not be the last hugepage (because IVSHMEM memory is first to be reserved, before the main memory).\r\n\r\nMy advice would be to rewrite the function to return the maximum end virtual address (instead of a last segment) and move it to eal_pci.c (and include declaration for it in include/eal_pci_init.h).\r\n\r\nMy apologies for not thinking about any of this during the first 6 iterations of the patch :(\r\n\r\nThanks,\r\nAnatoly\r\n\r\n-----Original Message-----\r\nFrom: lxu [mailto:liang.xu@cinfotech.cn]\r\nSent: Friday, November 7, 2014 8:01 AM\r\nTo: dev@dpdk.org<mailto:dev@dpdk.org>\r\nCc: Burakov, Anatoly; thomas.monjalon@6wind.com<mailto:thomas.monjalon@6wind.com>; De Lara Guarch, Pablo\r\nSubject: [PATCH v6] eal: map uio resources after hugepages when the base_virtaddr is configured.\r\n\r\nA multiple process DPDK application must mmap hugepages and pci resource into same virtual addresses. By default the virtual addresses chosen by the primary process automatically when calling the mmap. But sometime the virtual addresses chosen by the primary process isn't usable at secondary process. Such as the secondary process linked with more libraries than primary process. The library has been mapped into this virtual address. The command line parameter 'base-virtaddr' has been added for this situation. If it's configured, the hugepages will be mapped into this base address. But the virtual address of uio resource mapped still does not refer to the parameter. In that case it would still fail.\r\n\r\nThis patch try to map uio resources after hugepages when the base_virtaddr is configured. So the error of \"EAL: pci_map_resource(): cannot mmap\" can be resolved by set base-virtaddr into free virtual address space.\r\n\r\nSigned-off-by: lxu <liang.xu@cinfotech.cn<mailto:liang.xu@cinfotech.cn>>\r\n---\r\nlib/librte_eal/linuxapp/eal/eal_pci_uio.c | 29 ++++++++++++++++++++++++++++-\r\n1 file changed, 28 insertions(+), 1 deletion(-)\r\n\r\n\r\n+ /* map uio resource into user required virtual address */\r\n+ static void * requested_addr;\r\n+ if (internal_config.base_virtaddr && NULL == requested_addr) {\r\n+ const struct rte_memseg * last = get_physmem_last();\r\n+ requested_addr = RTE_PTR_ADD(last->addr, last->len);\r\n+ }\r\n+\r\ndev->intr_handle.fd = -1;\r\ndev->intr_handle.type = RTE_INTR_HANDLE_UNKNOWN;\r\n\r\n@@ -371,10 +396,12 @@ pci_uio_map_resource(struct rte_pci_device *dev)\r\nif (maps[j].addr != NULL)\r\nfail = 1;\r\nelse {\r\n- mapaddr = pci_map_resource(NULL, fd, (off_t)offset,\r\n+ mapaddr = pci_map_resource(requested_addr, fd, (off_t)offset,\r\n(size_t)maps[j].size);\r\nif (mapaddr == NULL)\r\nfail = 1;\r\n+ else if (NULL != requested_addr)\r\n+ requested_addr = RTE_PTR_ADD(mapaddr, maps[j].size);\r\n}\r\n\r\nif (fail) {\r\n--\r\n1.9.1", "diff": "diff --git a/lib/librte_eal/linuxapp/eal/eal_pci_uio.c b/lib/librte_eal/linuxapp/eal/eal_pci_uio.c\r\nindex 7e62266..a2c9ab6 100644\r\n--- a/lib/librte_eal/linuxapp/eal/eal_pci_uio.c\r\n+++ b/lib/librte_eal/linuxapp/eal/eal_pci_uio.c\r\n@@ -273,6 +273,24 @@ pci_get_uio_dev(struct rte_pci_device *dev, char *dstbuf,\r\nreturn uio_num;\r\n}\r\n\r\n+static inline const struct rte_memseg *\r\n+get_physmem_last(void)\r\n+{\r\n+ const struct rte_memseg * seg = rte_eal_get_physmem_layout();\r\n+ const struct rte_memseg * last = seg;\r\n+ unsigned i = 0;\r\n+\r\n+ for (i=0; i<RTE_MAX_MEMSEG; i++, seg++) {\r\n+ if (seg->addr == NULL)\r\n+ break;\r\n+\r\n+ if(seg->addr > last->addr)\r\n+ last = seg;\r\n+\r\n+ }\r\n+ return last;\r\n+}\r\n+\r\n/* map the PCI resource of a PCI device in virtual memory */ int pci_uio_map_resource(struct rte_pci_device *dev) @@ -290,6 +308,13 @@ pci_uio_map_resource(struct rte_pci_device *dev)\r\nstruct mapped_pci_resource *uio_res;\r\nstruct pci_map *maps;\r\n", "prefixes": [ "dpdk-dev", "v6" ] }