From patchwork Sat Mar 2 07:16:59 2013 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: "Pandarathil, Vijaymohan R" X-Patchwork-Id: 224471 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 56A532C02F3 for ; Sat, 2 Mar 2013 18:18:11 +1100 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752240Ab3CBHRg (ORCPT ); Sat, 2 Mar 2013 02:17:36 -0500 Received: from g5t0007.atlanta.hp.com ([15.192.0.44]:20142 "EHLO g5t0007.atlanta.hp.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752081Ab3CBHRS (ORCPT ); Sat, 2 Mar 2013 02:17:18 -0500 Received: from g5t0030.atlanta.hp.com (g5t0030.atlanta.hp.com [16.228.8.142]) by g5t0007.atlanta.hp.com (Postfix) with ESMTP id DACF9141A2; Sat, 2 Mar 2013 07:17:17 +0000 (UTC) Received: from cumin.cce.hp.com (cumin.cce.hp.com [15.250.252.195]) by g5t0030.atlanta.hp.com (Postfix) with ESMTP id 8A8421405B; Sat, 2 Mar 2013 07:17:17 +0000 (UTC) From: Vijay Mohan Pandarathil To: alex.williamson@redhat.com, gleb@redhat.com, bhelgaas@google.com, blauwirbel@gmail.com, lance.oritz@hp.com, kvm@vger.kernel.org, qemu-devel@nongnu.org, linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org Cc: Vijay Mohan Pandarathil Subject: [PATCH v6 3/3] QEMU-AER: Qemu changes to support AER for VFIO-PCI devices Date: Sat, 2 Mar 2013 01:16:59 -0600 Message-Id: <1362208619-5028-4-git-send-email-vijaymohan.pandarathil@hp.com> X-Mailer: git-send-email 1.7.11.3 In-Reply-To: <1362208619-5028-1-git-send-email-vijaymohan.pandarathil@hp.com> References: <1362208619-5028-1-git-send-email-vijaymohan.pandarathil@hp.com> Sender: linux-pci-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-pci@vger.kernel.org - Create eventfd per vfio device assigned to a guest and register an event handler - This fd is passed to the vfio_pci driver through the SET_IRQ ioctl - When the device encounters an error, the eventfd is signalled and the qemu eventfd handler gets invoked. - In the handler decide what action to take. Current action taken is to stop the guest. Signed-off-by: Vijay Mohan Pandarathil --- hw/vfio_pci.c | 123 +++++++++++++++++++++++++++++++++++++++++++++ linux-headers/linux/vfio.h | 1 + 2 files changed, 124 insertions(+) diff --git a/hw/vfio_pci.c b/hw/vfio_pci.c index ad9ae36..3c78771 100644 --- a/hw/vfio_pci.c +++ b/hw/vfio_pci.c @@ -38,6 +38,7 @@ #include "qemu/error-report.h" #include "qemu/queue.h" #include "qemu/range.h" +#include "sysemu/sysemu.h" /* #define DEBUG_VFIO */ #ifdef DEBUG_VFIO @@ -129,7 +130,9 @@ typedef struct VFIODevice { PCIHostDeviceAddress host; QLIST_ENTRY(VFIODevice) next; struct VFIOGroup *group; + EventNotifier err_notifier; bool reset_works; + bool pci_aer; } VFIODevice; typedef struct VFIOGroup { @@ -1802,6 +1805,7 @@ static int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vdev) { struct vfio_device_info dev_info = { .argsz = sizeof(dev_info) }; struct vfio_region_info reg_info = { .argsz = sizeof(reg_info) }; + struct vfio_irq_info irq_info = { .argsz = sizeof(irq_info) }; int ret, i; ret = ioctl(group->fd, VFIO_GROUP_GET_DEVICE_FD, name); @@ -1904,6 +1908,18 @@ static int vfio_get_device(VFIOGroup *group, const char *name, VFIODevice *vdev) } vdev->config_offset = reg_info.offset; + irq_info.index = VFIO_PCI_ERR_IRQ_INDEX; + + ret = ioctl(vdev->fd, VFIO_DEVICE_GET_IRQ_INFO, &irq_info); + if (ret) { + /* This can fail for an old kernel or legacy PCI dev */ + DPRINTF("VFIO_DEVICE_GET_IRQ_INFO failure ret=%d\n", ret); + ret = 0; + } else if (irq_info.count == 1) { + vdev->pci_aer = true; + } else { + error_report("vfio: Warning: Could not enable error recovery for the device\n"); + } error: if (ret) { QLIST_REMOVE(vdev, next); @@ -1925,6 +1941,110 @@ static void vfio_put_device(VFIODevice *vdev) } } +static void vfio_err_notifier_handler(void *opaque) +{ + VFIODevice *vdev = opaque; + + if (!event_notifier_test_and_clear(&vdev->err_notifier)) { + return; + } + + /* + * TBD. Retrieve the error details and decide what action + * needs to be taken. One of the actions could be to pass + * the error to the guest and have the guest driver recover + * from the error. This requires that PCIe capabilities be + * exposed to the guest. For now, we just terminate the + * guest to contain the error. + */ + + error_report("%s (%04x:%02x:%02x.%x)" + "Unrecoverable error detected...\n" + "Please collect any data possible and then kill the guest", + __func__, vdev->host.domain, vdev->host.bus, + vdev->host.slot, vdev->host.function); + + vm_stop(RUN_STATE_IO_ERROR); +} + +/* + * Registers error notifier for devices supporting error recovery. + * If we encounter a failure in this function, we report an error + * and continue after disabling error recovery support for the + * device. + */ +static void vfio_register_err_notifier(VFIODevice *vdev) +{ + int ret; + int argsz; + struct vfio_irq_set *irq_set; + int32_t *pfd; + + if (!vdev->pci_aer) { + return; + } + + if (event_notifier_init(&vdev->err_notifier, 0)) { + error_report("vfio: Warning: Unable to init event notifier for error detection\n"); + vdev->pci_aer = false; + return; + } + + argsz = sizeof(*irq_set) + sizeof(*pfd); + + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_PCI_ERR_IRQ_INDEX; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *)&irq_set->data; + + *pfd = event_notifier_get_fd(&vdev->err_notifier); + qemu_set_fd_handler(*pfd, vfio_err_notifier_handler, NULL, vdev); + + ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + if (ret) { + error_report("vfio: Failed to set up error notification\n"); + qemu_set_fd_handler(*pfd, NULL, NULL, vdev); + event_notifier_cleanup(&vdev->err_notifier); + vdev->pci_aer = false; + } + g_free(irq_set); +} +static void vfio_unregister_err_notifier(VFIODevice *vdev) +{ + int argsz; + struct vfio_irq_set *irq_set; + int32_t *pfd; + int ret; + + if (!vdev->pci_aer) { + return; + } + + argsz = sizeof(*irq_set) + sizeof(*pfd); + + irq_set = g_malloc0(argsz); + irq_set->argsz = argsz; + irq_set->flags = VFIO_IRQ_SET_DATA_EVENTFD | + VFIO_IRQ_SET_ACTION_TRIGGER; + irq_set->index = VFIO_PCI_ERR_IRQ_INDEX; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *)&irq_set->data; + *pfd = -1; + + ret = ioctl(vdev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + if (ret) { + error_report("vfio: Failed to de-assign error fd: %d\n", ret); + } + g_free(irq_set); + qemu_set_fd_handler(event_notifier_get_fd(&vdev->err_notifier), + NULL, NULL, vdev); + event_notifier_cleanup(&vdev->err_notifier); +} static int vfio_initfn(PCIDevice *pdev) { VFIODevice *pvdev, *vdev = DO_UPCAST(VFIODevice, pdev, pdev); @@ -2035,6 +2155,8 @@ static int vfio_initfn(PCIDevice *pdev) } } + vfio_register_err_notifier(vdev); + return 0; out_teardown: @@ -2052,6 +2174,7 @@ static void vfio_exitfn(PCIDevice *pdev) VFIODevice *vdev = DO_UPCAST(VFIODevice, pdev, pdev); VFIOGroup *group = vdev->group; + vfio_unregister_err_notifier(vdev); pci_device_set_intx_routing_notifier(&vdev->pdev, NULL); vfio_disable_interrupts(vdev); if (vdev->intx.mmap_timer) { diff --git a/linux-headers/linux/vfio.h b/linux-headers/linux/vfio.h index f787b72..6b20849 100644 --- a/linux-headers/linux/vfio.h +++ b/linux-headers/linux/vfio.h @@ -310,6 +310,7 @@ enum { VFIO_PCI_INTX_IRQ_INDEX, VFIO_PCI_MSI_IRQ_INDEX, VFIO_PCI_MSIX_IRQ_INDEX, + VFIO_PCI_ERR_IRQ_INDEX, VFIO_PCI_NUM_IRQS };