From nobody Fri Oct 24 22:12:09 2025 Delivered-To: importer@patchew.org Received-SPF: pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) client-ip=208.118.235.17; envelope-from=qemu-devel-bounces+importer=patchew.org@nongnu.org; helo=lists.gnu.org; Authentication-Results: mx.zohomail.com; spf=pass (zoho.com: domain of gnu.org designates 208.118.235.17 as permitted sender) smtp.mailfrom=qemu-devel-bounces+importer=patchew.org@nongnu.org; dmarc=fail(p=none dis=none) header.from=redhat.com Return-Path: Received: from lists.gnu.org (208.118.235.17 [208.118.235.17]) by mx.zohomail.com with SMTPS id 15253844030020.1570431080255048; Thu, 3 May 2018 14:53:23 -0700 (PDT) Received: from localhost ([::1]:59277 helo=lists.gnu.org) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fEMA4-000796-Ro for importer@patchew.org; Thu, 03 May 2018 17:53:12 -0400 Received: from eggs.gnu.org ([2001:4830:134:3::10]:59760) by lists.gnu.org with esmtp (Exim 4.71) (envelope-from ) id 1fEM2R-0001bj-1K for qemu-devel@nongnu.org; Thu, 03 May 2018 17:45:22 -0400 Received: from Debian-exim by eggs.gnu.org with spam-scanned (Exim 4.71) (envelope-from ) id 1fEM2O-00045C-He for qemu-devel@nongnu.org; Thu, 03 May 2018 17:45:18 -0400 Received: from mx1.redhat.com ([209.132.183.28]:53132) by eggs.gnu.org with esmtps (TLS1.0:DHE_RSA_AES_256_CBC_SHA1:32) (Exim 4.71) (envelope-from ) id 1fEM2N-00042j-GN for qemu-devel@nongnu.org; Thu, 03 May 2018 17:45:16 -0400 Received: from smtp.corp.redhat.com (int-mx09.intmail.prod.int.phx2.redhat.com [10.5.11.24]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mx1.redhat.com (Postfix) with ESMTPS id 7A5D9356E6; Thu, 3 May 2018 21:45:14 +0000 (UTC) Received: from gimli.home (ovpn-116-103.phx2.redhat.com [10.3.116.103]) by smtp.corp.redhat.com (Postfix) with ESMTP id 1174F30012C9; Thu, 3 May 2018 21:45:14 +0000 (UTC) From: Alex Williamson To: qemu-devel@nongnu.org Date: Thu, 03 May 2018 15:45:13 -0600 Message-ID: <20180503214513.2749.30627.stgit@gimli.home> In-Reply-To: <20180503213458.2749.28566.stgit@gimli.home> References: <20180503213458.2749.28566.stgit@gimli.home> User-Agent: StGit/0.18-102-gdf9f MIME-Version: 1.0 Content-Type: text/plain; charset="utf-8" Content-Transfer-Encoding: quoted-printable X-Scanned-By: MIMEDefang 2.84 on 10.5.11.24 X-Greylist: Sender IP whitelisted, not delayed by milter-greylist-4.5.16 (mx1.redhat.com [10.5.110.30]); Thu, 03 May 2018 21:45:14 +0000 (UTC) X-detected-operating-system: by eggs.gnu.org: GNU/Linux 2.2.x-3.x [generic] [fuzzy] X-Received-From: 209.132.183.28 Subject: [Qemu-devel] [PATCH v3 6/6] vfio/quirks: Enable ioeventfd quirks to be handled by vfio directly X-BeenThere: qemu-devel@nongnu.org X-Mailman-Version: 2.1.21 Precedence: list List-Id: List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , Cc: eric.auger@redhat.com, peterx@redhat.com, kvm@vger.kernel.org Errors-To: qemu-devel-bounces+importer=patchew.org@nongnu.org Sender: "Qemu-devel" X-ZohoMail: RSF_0 Z_629925259 SPT_0 With vfio ioeventfd support, we can program vfio-pci to perform a specified BAR write when an eventfd is triggered. This allows the KVM ioeventfd to be wired directly to vfio-pci, entirely avoiding userspace handling for these events. On the same micro-benchmark where the ioeventfd got us to almost 90% of performance versus disabling the GeForce quirks, this gets us to within 95%. Signed-off-by: Alex Williamson Reviewed-by: Eric Auger Reviewed-by: Peter Xu --- hw/vfio/pci-quirks.c | 53 +++++++++++++++++++++++++++++++++++++++++++---= ---- hw/vfio/pci.c | 2 ++ hw/vfio/pci.h | 2 ++ hw/vfio/trace-events | 2 +- 4 files changed, 51 insertions(+), 8 deletions(-) diff --git a/hw/vfio/pci-quirks.c b/hw/vfio/pci-quirks.c index f7886487744e..061259b86b71 100644 --- a/hw/vfio/pci-quirks.c +++ b/hw/vfio/pci-quirks.c @@ -16,6 +16,7 @@ #include "qemu/range.h" #include "qapi/error.h" #include "qapi/visitor.h" +#include #include "hw/nvram/fw_cfg.h" #include "pci.h" #include "trace.h" @@ -287,12 +288,33 @@ static VFIOQuirk *vfio_quirk_alloc(int nr_mem) return quirk; } =20 -static void vfio_ioeventfd_exit(VFIOIOEventFD *ioeventfd) +static void vfio_ioeventfd_exit(VFIOPCIDevice *vdev, VFIOIOEventFD *ioeven= tfd) { QLIST_REMOVE(ioeventfd, next); memory_region_del_eventfd(ioeventfd->mr, ioeventfd->addr, ioeventfd->s= ize, true, ioeventfd->data, &ioeventfd->e); - qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), NULL, NULL, = NULL); + + if (ioeventfd->vfio) { + struct vfio_device_ioeventfd vfio_ioeventfd; + + vfio_ioeventfd.argsz =3D sizeof(vfio_ioeventfd); + vfio_ioeventfd.flags =3D ioeventfd->size; + vfio_ioeventfd.data =3D ioeventfd->data; + vfio_ioeventfd.offset =3D ioeventfd->region->fd_offset + + ioeventfd->region_addr; + vfio_ioeventfd.fd =3D -1; + + if (ioctl(vdev->vbasedev.fd, VFIO_DEVICE_IOEVENTFD, &vfio_ioeventf= d)) { + error_report("Failed to remove vfio ioeventfd for %s+0x%" + HWADDR_PRIx"[%d]:0x%"PRIx64" (%m)", + memory_region_name(ioeventfd->mr), ioeventfd->add= r, + ioeventfd->size, ioeventfd->data); + } + } else { + qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), + NULL, NULL, NULL); + } + event_notifier_cleanup(&ioeventfd->e); trace_vfio_ioeventfd_exit(memory_region_name(ioeventfd->mr), (uint64_t)ioeventfd->addr, ioeventfd->size, @@ -306,7 +328,7 @@ static void vfio_drop_dynamic_eventfds(VFIOPCIDevice *v= dev, VFIOQuirk *quirk) =20 QLIST_FOREACH_SAFE(ioeventfd, &quirk->ioeventfds, next, tmp) { if (ioeventfd->dynamic) { - vfio_ioeventfd_exit(ioeventfd); + vfio_ioeventfd_exit(vdev, ioeventfd); } } } @@ -359,12 +381,29 @@ static VFIOIOEventFD *vfio_ioeventfd_init(VFIOPCIDevi= ce *vdev, ioeventfd->region =3D region; ioeventfd->region_addr =3D region_addr; =20 - qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), - vfio_ioeventfd_handler, NULL, ioeventfd); + if (!vdev->no_vfio_ioeventfd) { + struct vfio_device_ioeventfd vfio_ioeventfd; + + vfio_ioeventfd.argsz =3D sizeof(vfio_ioeventfd); + vfio_ioeventfd.flags =3D ioeventfd->size; + vfio_ioeventfd.data =3D ioeventfd->data; + vfio_ioeventfd.offset =3D ioeventfd->region->fd_offset + + ioeventfd->region_addr; + vfio_ioeventfd.fd =3D event_notifier_get_fd(&ioeventfd->e); + + ioeventfd->vfio =3D !ioctl(vdev->vbasedev.fd, + VFIO_DEVICE_IOEVENTFD, &vfio_ioeventfd); + } + + if (!ioeventfd->vfio) { + qemu_set_fd_handler(event_notifier_get_fd(&ioeventfd->e), + vfio_ioeventfd_handler, NULL, ioeventfd); + } + memory_region_add_eventfd(ioeventfd->mr, ioeventfd->addr, ioeventfd->s= ize, true, ioeventfd->data, &ioeventfd->e); trace_vfio_ioeventfd_init(memory_region_name(mr), (uint64_t)addr, - size, data); + size, data, ioeventfd->vfio); =20 return ioeventfd; } @@ -1827,7 +1866,7 @@ void vfio_bar_quirk_exit(VFIOPCIDevice *vdev, int nr) =20 QLIST_FOREACH(quirk, &bar->quirks, next) { while (!QLIST_EMPTY(&quirk->ioeventfds)) { - vfio_ioeventfd_exit(QLIST_FIRST(&quirk->ioeventfds)); + vfio_ioeventfd_exit(vdev, QLIST_FIRST(&quirk->ioeventfds)); } =20 for (i =3D 0; i < quirk->nr_mem; i++) { diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index ba1239551115..84e27c7bb2d1 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -3177,6 +3177,8 @@ static Property vfio_pci_dev_properties[] =3D { no_geforce_quirks, false), DEFINE_PROP_BOOL("x-no-kvm-ioeventfd", VFIOPCIDevice, no_kvm_ioeventfd, false), + DEFINE_PROP_BOOL("x-no-vfio-ioeventfd", VFIOPCIDevice, no_vfio_ioevent= fd, + false), DEFINE_PROP_UINT32("x-pci-vendor-id", VFIOPCIDevice, vendor_id, PCI_AN= Y_ID), DEFINE_PROP_UINT32("x-pci-device-id", VFIOPCIDevice, device_id, PCI_AN= Y_ID), DEFINE_PROP_UINT32("x-pci-sub-vendor-id", VFIOPCIDevice, diff --git a/hw/vfio/pci.h b/hw/vfio/pci.h index a4ac583fbd6e..52b065421a68 100644 --- a/hw/vfio/pci.h +++ b/hw/vfio/pci.h @@ -34,6 +34,7 @@ typedef struct VFIOIOEventFD { VFIORegion *region; hwaddr region_addr; bool dynamic; /* Added runtime, removed on device reset */ + bool vfio; } VFIOIOEventFD; =20 typedef struct VFIOQuirk { @@ -163,6 +164,7 @@ typedef struct VFIOPCIDevice { bool no_kvm_msix; bool no_geforce_quirks; bool no_kvm_ioeventfd; + bool no_vfio_ioeventfd; VFIODisplay *dpy; } VFIOPCIDevice; =20 diff --git a/hw/vfio/trace-events b/hw/vfio/trace-events index f8f97d1ff90c..d2a74952e389 100644 --- a/hw/vfio/trace-events +++ b/hw/vfio/trace-events @@ -79,7 +79,7 @@ vfio_quirk_ati_bonaire_reset_done(const char *name) "%s" vfio_quirk_ati_bonaire_reset(const char *name) "%s" vfio_ioeventfd_exit(const char *name, uint64_t addr, unsigned size, uint64= _t data) "%s+0x%"PRIx64"[%d]:0x%"PRIx64 vfio_ioeventfd_handler(const char *name, uint64_t addr, unsigned size, uin= t64_t data) "%s+0x%"PRIx64"[%d] -> 0x%"PRIx64 -vfio_ioeventfd_init(const char *name, uint64_t addr, unsigned size, uint64= _t data) "%s+0x%"PRIx64"[%d]:0x%"PRIx64 +vfio_ioeventfd_init(const char *name, uint64_t addr, unsigned size, uint64= _t data, bool vfio) "%s+0x%"PRIx64"[%d]:0x%"PRIx64" vfio:%d" vfio_pci_igd_bar4_write(const char *name, uint32_t index, uint32_t data, u= int32_t base) "%s [0x%03x] 0x%08x -> 0x%08x" vfio_pci_igd_bdsm_enabled(const char *name, int size) "%s %dMB" vfio_pci_igd_opregion_enabled(const char *name) "%s"