From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: by dpdk.org (Postfix, from userid 33) id EC5024C99; Mon, 27 Aug 2018 07:43:49 +0200 (CEST) From: bugzilla@dpdk.org To: dev@dpdk.org Date: Mon, 27 Aug 2018 05:43:49 +0000 X-Bugzilla-Reason: AssignedTo X-Bugzilla-Type: new X-Bugzilla-Watch-Reason: None X-Bugzilla-Product: DPDK X-Bugzilla-Component: core X-Bugzilla-Version: 17.11 X-Bugzilla-Keywords: X-Bugzilla-Severity: major X-Bugzilla-Who: geoffrey.lv@gmail.com X-Bugzilla-Status: CONFIRMED X-Bugzilla-Resolution: X-Bugzilla-Priority: Normal X-Bugzilla-Assigned-To: dev@dpdk.org X-Bugzilla-Target-Milestone: --- X-Bugzilla-Flags: X-Bugzilla-Changed-Fields: bug_id short_desc product version rep_platform op_sys bug_status bug_severity priority component assigned_to reporter target_milestone Message-ID: Content-Type: text/plain; charset="UTF-8" Content-Transfer-Encoding: quoted-printable X-Bugzilla-URL: http://bugs.dpdk.org/ Auto-Submitted: auto-generated X-Auto-Response-Suppress: All MIME-Version: 1.0 Subject: [dpdk-dev] [Bug 85] pci_scan_one() issue 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: Mon, 27 Aug 2018 05:43:50 -0000 https://bugs.dpdk.org/show_bug.cgi?id=3D85 Bug ID: 85 Summary: pci_scan_one() issue Product: DPDK Version: 17.11 Hardware: All OS: Linux Status: CONFIRMED Severity: major Priority: Normal Component: core Assignee: dev@dpdk.org Reporter: geoffrey.lv@gmail.com Target Milestone: --- /* Scan one pci sysfs entry, and fill the devices list from it. */ static int pci_scan_one(const char *dirname, const struct rte_pci_addr *addr) This function is at drivers/bus/pci/linux/pci.c, and please refer to below code: } else { /* already registered */ dev2->kdrv =3D dev->kdrv; dev2->max_vfs =3D dev->max_vfs; pci_name_set(dev2); memmove(dev2->mem_resource, dev->mem_resour= ce, sizeof(dev->mem_resource)); free(dev); } If this device is already registered, this function will replace the mem_resource. But some devices need to map the PCI resource of a PCI device in virtual memory, which means dev2->mem_resource[i].addr is not 0, and it's overwritt= en here.=20 When we attach a new device, calling sequence is: rte_eth_dev_attach()->rte_eal_hotplug_add()->rte_pci_scan()->pci_scan_one() For already registered devices, mem_resource[i].addr is set to 0, and DPDK = will not invoke rte_pci_map_device() for these devices. --=20 You are receiving this mail because: You are the assignee for the bug.=