From patchwork Wed May 27 09:11:11 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 8bit X-Patchwork-Submitter: Eric Auger X-Patchwork-Id: 477007 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 0F99814029C for ; Wed, 27 May 2015 19:13:13 +1000 (AEST) Received: from localhost ([::1]:52656 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YxXOh-0004A1-50 for incoming@patchwork.ozlabs.org; Wed, 27 May 2015 05:13:11 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:43440) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YxXNE-0001Xj-6j for qemu-devel@nongnu.org; Wed, 27 May 2015 05:11:44 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1YxXNC-000080-9g for qemu-devel@nongnu.org; Wed, 27 May 2015 05:11:39 -0400 Received: from mail-wi0-f174.google.com ([209.85.212.174]:37291) by eggs.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1YxXNC-00007r-1U for qemu-devel@nongnu.org; Wed, 27 May 2015 05:11:38 -0400 Received: by wifw1 with SMTP id w1so14029305wif.0 for ; Wed, 27 May 2015 02:11:37 -0700 (PDT) X-Google-DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=1e100.net; s=20130820; h=x-gm-message-state:from:to:cc:subject:date:message-id:in-reply-to :references:mime-version:content-type:content-transfer-encoding; bh=qQwB28OhwFGFn9IaIZnmJgbH28TgfCwoYwmLrLDJKG8=; b=QHM6Ylej7PD4Lp6dJLoI4W9aSj71h2bI7WMVEAL3BCV8NEw4ds9yj+tKLSDuZ2rNbW XMW3V7dnc+4vNJop5V0OnFHSEYVQpTQMHr6iYrEAANVhW4DYnTbohPLXFn13qR2MpCJx /UCxYsqVYV2x7TPHEkiKw07EJGpxe/MpOVvjlmLRfpNXlvBoUQzP/zLxdr+eNjarY+IR HSag9MJrKg3ijSKGRw0fS8CNFheGmRbWU0DacB9lzMXdMRw8drrJcQcv+fZiD7NLx6Zz BBPfni8XtBRR2KE94XI8fmZ850khI+yZPHFtXBgjDvFEAQdFq8wJhKr5QIfjrT6X59Zh ootQ== X-Gm-Message-State: ALoCoQkljl6/0zHO0qTPoZthcCgDsqQXLeWjmUiOoZ8JwxaK22i5uWIhtG9peiSy1uYbvHFi90W2 X-Received: by 10.180.89.231 with SMTP id br7mr39630427wib.60.1432717897632; Wed, 27 May 2015 02:11:37 -0700 (PDT) Received: from midway01-04-00.lavalab ([81.128.185.50]) by mx.google.com with ESMTPSA id ej5sm25828061wjd.22.2015.05.27.02.11.36 (version=TLSv1.1 cipher=ECDHE-RSA-RC4-SHA bits=128/128); Wed, 27 May 2015 02:11:36 -0700 (PDT) From: Eric Auger To: eric.auger@st.com, eric.auger@linaro.org, qemu-devel@nongnu.org, alex.williamson@redhat.com Date: Wed, 27 May 2015 10:11:11 +0100 Message-Id: <1432717871-2393-10-git-send-email-eric.auger@linaro.org> X-Mailer: git-send-email 1.8.3.2 In-Reply-To: <1432717871-2393-1-git-send-email-eric.auger@linaro.org> References: <1432717871-2393-1-git-send-email-eric.auger@linaro.org> MIME-Version: 1.0 X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 209.85.212.174 Cc: peter.maydell@linaro.org, b.reynal@virtualopensystems.com, vikrams@codeaurora.org, patches@linaro.org, agraf@suse.de, Alvise Rigo , pbonzini@redhat.com, kvmarm@lists.cs.columbia.edu, christoffer.dall@linaro.org Subject: [Qemu-devel] [PATCH v16 9/9] 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 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 --- v15 -> v16: - add Vikram's T-b v13 -> v14: - use connect_irq_notifier - remove trace_vfio_platform_start_eventfd v12 -> v13: - setup the new mechanism for starting irqfd, based on LinkPropertySetter override - use kvm_irqchip_[add,remove]_irqfd_notifier new functions: no need to bother about gsi (hence virtualID could be removed with small change in trace-events) v10 -> v11: - Add Alex' Reviewed-by - introduce kvm_accel in this patch and initialize it v5 -> v6 - rely on kvm_irqfds_enabled() and kvm_resamplefds_enabled() - guard KVM code with #ifdef CONFIG_KVM v3 -> v4: [Alvise Rigo] Use of VFIO Platform driver v6 unmask/virqfd feature and removal of resamplefd handler. Physical IRQ unmasking is now done in VFIO driver. v3: [Eric Auger] initial support with resamplefd handled on QEMU side since the unmask was not supported on VFIO platform driver v5. --- hw/vfio/platform.c | 107 ++++++++++++++++++++++++++++++++++++++++ include/hw/vfio/vfio-platform.h | 2 + trace-events | 1 + 3 files changed, 110 insertions(+) diff --git a/hw/vfio/platform.c b/hw/vfio/platform.c index 35266a8..901b98e 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: resample event_notifier_init failed eoi"); + return NULL; + } QLIST_INSERT_HEAD(&vdev->intp_list, intp, next); return intp; @@ -315,6 +324,95 @@ static int vfio_start_eventfd_injection(VFIOINTp *intp) return ret; } +/* + * Functions used for irqfd + */ + +#ifdef CONFIG_KVM + +/** + * 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; + bool found = false; + + QLIST_FOREACH(intp, &vdev->intp_list, next) { + if (intp->qemuirq == irq) { + found = true; + break; + } + } + assert(found); + + /* 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'em rip */ + 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; +} + +#endif /* CONFIG_KVM */ + /* VFIO skeleton */ static void vfio_platform_compute_needs_reset(VFIODevice *vbasedev) @@ -549,6 +647,7 @@ static void vfio_platform_realize(DeviceState *dev, Error **errp) { VFIOPlatformDevice *vdev = VFIO_PLATFORM_DEVICE(dev); SysBusDevice *sbdev = SYS_BUS_DEVICE(dev); + SysBusDeviceClass *sbc = SYS_BUS_DEVICE_GET_CLASS(dev); VFIODevice *vbasedev = &vdev->vbasedev; VFIOINTp *intp; int i, ret; @@ -556,6 +655,13 @@ static void vfio_platform_realize(DeviceState *dev, Error **errp) vbasedev->type = VFIO_DEVICE_TYPE_PLATFORM; vbasedev->ops = &vfio_platform_ops; +#ifdef CONFIG_KVM + if (kvm_irqfds_enabled() && kvm_resamplefds_enabled() && + vdev->irqfd_allowed) { + sbc->connect_irq_notifier = vfio_start_irqfd_injection; + } +#endif + trace_vfio_platform_realize(vbasedev->name, vdev->compat); ret = vfio_base_device_init(vbasedev); @@ -585,6 +691,7 @@ 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(), }; 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 4b4e040..90f2e3b 100644 --- a/trace-events +++ b/trace-events @@ -1571,6 +1571,7 @@ 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