From patchwork Mon Jul 6 18:35:29 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Alex Williamson X-Patchwork-Id: 491759 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from lists.gnu.org (lists.gnu.org [IPv6:2001:4830:134:3::11]) (using TLSv1 with cipher AES256-SHA (256/256 bits)) (No client certificate requested) by ozlabs.org (Postfix) with ESMTPS id F3BFA140DBC for ; Tue, 7 Jul 2015 04:38:38 +1000 (AEST) Received: from localhost ([::1]:52453 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZCBHp-0001IE-6Y for incoming@patchwork.ozlabs.org; Mon, 06 Jul 2015 14:38:37 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:36621) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZCBEq-0004aE-31 for qemu-devel@nongnu.org; Mon, 06 Jul 2015 14:35:34 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1ZCBEo-0003Hg-Fl for qemu-devel@nongnu.org; Mon, 06 Jul 2015 14:35:32 -0400 Received: from mx1.redhat.com ([209.132.183.28]:38111) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1ZCBEo-0003HT-8l for qemu-devel@nongnu.org; Mon, 06 Jul 2015 14:35:30 -0400 Received: from int-mx13.intmail.prod.int.phx2.redhat.com (int-mx13.intmail.prod.int.phx2.redhat.com [10.5.11.26]) by mx1.redhat.com (Postfix) with ESMTPS id E4C7E373BF4 for ; Mon, 6 Jul 2015 18:35:29 +0000 (UTC) Received: from gimli.home (ovpn-113-190.phx2.redhat.com [10.3.113.190]) by int-mx13.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id t66IZTxb003701; Mon, 6 Jul 2015 14:35:29 -0400 From: Alex Williamson To: qemu-devel@nongnu.org Date: Mon, 06 Jul 2015 12:35:29 -0600 Message-ID: <20150706183529.15635.36463.stgit@gimli.home> In-Reply-To: <20150706183311.15635.76314.stgit@gimli.home> References: <20150706183311.15635.76314.stgit@gimli.home> User-Agent: StGit/0.17.1-dirty MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.68 on 10.5.11.26 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 3.x X-Received-From: 209.132.183.28 Subject: [Qemu-devel] [PULL 09/11] hw/vfio/platform: add irqfd support X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.14 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Errors-To: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org Sender: qemu-devel-bounces+incoming=patchwork.ozlabs.org@nongnu.org From: Eric Auger This patch aims at optimizing IRQ handling using irqfd framework. Instead of handling the eventfds on user-side they are handled on kernel side using - the KVM irqfd framework, - the VFIO driver virqfd framework. the virtual IRQ completion is trapped at interrupt controller This removes the need for fast/slow path swap. Overall this brings significant performance improvements. Signed-off-by: Alvise Rigo Signed-off-by: Eric Auger Reviewed-by: Alex Bennée Tested-by: Vikram Sethi Acked-by: Peter Maydell Signed-off-by: Alex Williamson --- hw/vfio/platform.c | 100 +++++++++++++++++++++++++++++++++++++++ include/hw/vfio/vfio-platform.h | 2 + trace-events | 1 3 files changed, 103 insertions(+) diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index 5c678b9..60365d1 100644 --- a/hw/vfio/platform.c +++ b/hw/vfio/platform.c @@ -26,6 +26,7 @@ #include "hw/sysbus.h" #include "trace.h" #include "hw/platform-bus.h" +#include "sysemu/kvm.h" /* * Functions used whatever the injection method @@ -51,6 +52,7 @@ static VFIOINTp *vfio_init_intp(VFIODevice *vbasedev, intp->pin = info.index; intp->flags = info.flags; intp->state = VFIO_IRQ_INACTIVE; + intp->kvm_accel = false; sysbus_init_irq(sbdev, &intp->qemuirq); @@ -61,6 +63,13 @@ static VFIOINTp *vfio_init_intp(VFIODevice *vbasedev, error_report("vfio: Error: trigger event_notifier_init failed "); return NULL; } + /* Get an eventfd for resample/unmask */ + ret = event_notifier_init(&intp->unmask, 0); + if (ret) { + g_free(intp); + error_report("vfio: Error: resamplefd event_notifier_init failed"); + return NULL; + } QLIST_INSERT_HEAD(&vdev->intp_list, intp, next); return intp; @@ -315,6 +324,94 @@ static int vfio_start_eventfd_injection(VFIOINTp *intp) return ret; } +/* + * Functions used for irqfd + */ + +/** + * vfio_set_resample_eventfd - sets the resamplefd for an IRQ + * @intp: the IRQ struct handle + * programs the VFIO driver to unmask this IRQ when the + * intp->unmask eventfd is triggered + */ +static int vfio_set_resample_eventfd(VFIOINTp *intp) +{ + VFIODevice *vbasedev = &intp->vdev->vbasedev; + struct vfio_irq_set *irq_set; + int argsz, ret; + int32_t *pfd; + + 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_UNMASK; + irq_set->index = intp->pin; + irq_set->start = 0; + irq_set->count = 1; + pfd = (int32_t *)&irq_set->data; + *pfd = event_notifier_get_fd(&intp->unmask); + qemu_set_fd_handler(*pfd, NULL, NULL, NULL); + ret = ioctl(vbasedev->fd, VFIO_DEVICE_SET_IRQS, irq_set); + g_free(irq_set); + if (ret < 0) { + error_report("vfio: Failed to set resample eventfd: %m"); + } + return ret; +} + +static void vfio_start_irqfd_injection(SysBusDevice *sbdev, qemu_irq irq) +{ + VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(sbdev); + VFIOINTp *intp; + + if (!kvm_irqfds_enabled() || !kvm_resamplefds_enabled() || + !vdev->irqfd_allowed) { + return; + } + + QLIST_FOREACH(intp, &vdev->intp_list, next) { + if (intp->qemuirq == irq) { + break; + } + } + assert(intp); + + /* Get to a known interrupt state */ + qemu_set_fd_handler(event_notifier_get_fd(&intp->interrupt), + NULL, NULL, vdev); + + vfio_mask_single_irqindex(&vdev->vbasedev, intp->pin); + qemu_set_irq(intp->qemuirq, 0); + + if (kvm_irqchip_add_irqfd_notifier(kvm_state, &intp->interrupt, + &intp->unmask, irq) < 0) { + goto fail_irqfd; + } + + if (vfio_set_trigger_eventfd(intp, NULL) < 0) { + goto fail_vfio; + } + if (vfio_set_resample_eventfd(intp) < 0) { + goto fail_vfio; + } + + /* Let's resume injection with irqfd setup */ + vfio_unmask_single_irqindex(&vdev->vbasedev, intp->pin); + + intp->kvm_accel = true; + + trace_vfio_platform_start_irqfd_injection(intp->pin, + event_notifier_get_fd(&intp->interrupt), + event_notifier_get_fd(&intp->unmask)); + return; +fail_vfio: + kvm_irqchip_remove_irqfd_notifier(kvm_state, &intp->interrupt, irq); +fail_irqfd: + vfio_start_eventfd_injection(intp); + vfio_unmask_single_irqindex(&vdev->vbasedev, intp->pin); + return; +} + /* VFIO skeleton */ static void vfio_platform_compute_needs_reset(VFIODevice *vbasedev) @@ -584,17 +681,20 @@ static Property vfio_platform_dev_properties[] = { DEFINE_PROP_BOOL("x-mmap", VFIOPlatformDevice, vbasedev.allow_mmap, true), DEFINE_PROP_UINT32("mmap-timeout-ms", VFIOPlatformDevice, mmap_timeout, 1100), + DEFINE_PROP_BOOL("x-irqfd", VFIOPlatformDevice, irqfd_allowed, true), DEFINE_PROP_END_OF_LIST(), }; static void vfio_platform_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); + SysBusDeviceClass *sbc = SYS_BUS_DEVICE_CLASS(klass); dc->realize = vfio_platform_realize; dc->props = vfio_platform_dev_properties; dc->vmsd = &vfio_platform_vmstate; dc->desc = "VFIO-based platform device assignment"; + sbc->connect_irq_notifier = vfio_start_irqfd_injection; set_bit(DEVICE_CATEGORY_MISC, dc->categories); } diff --git a/include/hw/vfio/vfio-platform.h b/include/hw/vfio/vfio-platform.h index 26b2ad6..c5cf1d7 100644 --- a/include/hw/vfio/vfio-platform.h +++ b/include/hw/vfio/vfio-platform.h @@ -41,6 +41,7 @@ typedef struct VFIOINTp { int state; /* inactive, pending, active */ uint8_t pin; /* index */ uint32_t flags; /* IRQ info flags */ + bool kvm_accel; /* set when QEMU bypass through KVM enabled */ } VFIOINTp; /* function type for user side eventfd handler */ @@ -57,6 +58,7 @@ typedef struct VFIOPlatformDevice { uint32_t mmap_timeout; /* delay to re-enable mmaps after interrupt */ QEMUTimer *mmap_timer; /* allows fast-path resume after IRQ hit */ QemuMutex intp_mutex; /* protect the intp_list IRQ state */ + bool irqfd_allowed; /* debug option to force irqfd on/off */ } VFIOPlatformDevice; typedef struct VFIOPlatformDeviceClass { diff --git a/trace-events b/trace-events index 52b7efa..d24d80a 100644 --- a/trace-events +++ b/trace-events @@ -1594,6 +1594,7 @@ vfio_platform_intp_interrupt(int pin, int fd) "Inject IRQ #%d (fd = %d)" vfio_platform_intp_inject_pending_lockheld(int pin, int fd) "Inject pending IRQ #%d (fd = %d)" vfio_platform_populate_interrupts(int pin, int count, int flags) "- IRQ index %d: count %d, flags=0x%x" vfio_intp_interrupt_set_pending(int index) "irq %d is set PENDING" +vfio_platform_start_irqfd_injection(int index, int fd, int resamplefd) "IRQ index=%d, fd = %d, resamplefd = %d" #hw/acpi/memory_hotplug.c mhp_acpi_invalid_slot_selected(uint32_t slot) "0x%"PRIx32