From patchwork Wed May 6 09:49:32 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530891 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id C25D081 for ; Wed, 6 May 2020 09:50:10 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 9AF652070B for ; Wed, 6 May 2020 09:50:10 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="PEybXLPz" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729051AbgEFJuJ (ORCPT ); Wed, 6 May 2020 05:50:09 -0400 Received: from us-smtp-delivery-1.mimecast.com ([207.211.31.120]:41292 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1726935AbgEFJuJ (ORCPT ); Wed, 6 May 2020 05:50:09 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758608; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=1b7WzEdOr0opnS44tYvGmSayhyE3oXt+X3RgB8uyQ/4=; b=PEybXLPzyCAXbc0VPHNSmX4nyPKA9AIDQDyvs+FYMXf8oLwjU3hmQ5nnxuzlHYhMfjGnUo oPIFlxXn12O2P5lQ7GvMxly7eJEVKGhNSfc0P0hcn0nOb3H5wnzB0cz6gTdNTTPdUz7lOu RPZ8MxhsWZN4BLOVyY67FFmvgxAw6UU= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-287-tQp4UaSBNF61XvzTMO_hOA-1; Wed, 06 May 2020 05:50:06 -0400 X-MC-Unique: tQp4UaSBNF61XvzTMO_hOA-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 99C2C835B44; Wed, 6 May 2020 09:50:05 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id D68BA5C1D4; Wed, 6 May 2020 09:50:01 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand Subject: [PATCH v1 01/17] exec: Introduce ram_block_discard_set_(unreliable|required)() Date: Wed, 6 May 2020 11:49:32 +0200 Message-Id: <20200506094948.76388-2-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org We want to replace qemu_balloon_inhibit() by something more generic. Especially, we want to make sure that technologies that really rely on RAM block discards to work reliably to run mutual exclusive with technologies that break it. E.g., vfio will usually pin all guest memory, turning the virtio-balloon basically useless and make the VM consume more memory than reported via the balloon. While the balloon is special already (=> no guarantees, same behavior possible afer reboots and with huge pages), this will be different, especially, with virtio-mem. Let's implement a way such that we can make both types of technology run mutually exclusive. We'll convert existing balloon inhibitors in successive patches and add some new ones. Add the check to qemu_balloon_is_inhibited() for now. We might want to make virtio-balloon an acutal inhibitor in the future - however, that requires more thought to not break existing setups. Cc: "Michael S. Tsirkin" Cc: Richard Henderson Cc: Paolo Bonzini Signed-off-by: David Hildenbrand Reviewed-by: Dr. David Alan Gilbert --- balloon.c | 3 ++- exec.c | 48 +++++++++++++++++++++++++++++++++++++++++++ include/exec/memory.h | 41 ++++++++++++++++++++++++++++++++++++ 3 files changed, 91 insertions(+), 1 deletion(-) diff --git a/balloon.c b/balloon.c index f104b42961..c49f57c27b 100644 --- a/balloon.c +++ b/balloon.c @@ -40,7 +40,8 @@ static int balloon_inhibit_count; bool qemu_balloon_is_inhibited(void) { - return atomic_read(&balloon_inhibit_count) > 0; + return atomic_read(&balloon_inhibit_count) > 0 || + ram_block_discard_is_broken(); } void qemu_balloon_inhibit(bool state) diff --git a/exec.c b/exec.c index 2874bb5088..52a6e40e99 100644 --- a/exec.c +++ b/exec.c @@ -4049,4 +4049,52 @@ void mtree_print_dispatch(AddressSpaceDispatch *d, MemoryRegion *root) } } +static int ram_block_discard_broken; + +int ram_block_discard_set_broken(bool state) +{ + int old; + + if (!state) { + atomic_dec(&ram_block_discard_broken); + return 0; + } + + do { + old = atomic_read(&ram_block_discard_broken); + if (old < 0) { + return -EBUSY; + } + } while (atomic_cmpxchg(&ram_block_discard_broken, old, old + 1) != old); + return 0; +} + +int ram_block_discard_set_required(bool state) +{ + int old; + + if (!state) { + atomic_inc(&ram_block_discard_broken); + return 0; + } + + do { + old = atomic_read(&ram_block_discard_broken); + if (old > 0) { + return -EBUSY; + } + } while (atomic_cmpxchg(&ram_block_discard_broken, old, old - 1) != old); + return 0; +} + +bool ram_block_discard_is_broken(void) +{ + return atomic_read(&ram_block_discard_broken) > 0; +} + +bool ram_block_discard_is_required(void) +{ + return atomic_read(&ram_block_discard_broken) < 0; +} + #endif diff --git a/include/exec/memory.h b/include/exec/memory.h index e000bd2f97..9bb5ced38d 100644 --- a/include/exec/memory.h +++ b/include/exec/memory.h @@ -2463,6 +2463,47 @@ static inline MemOp devend_memop(enum device_endian end) } #endif +/* + * Inhibit technologies that rely on discarding of parts of RAM blocks to work + * reliably, e.g., to manage the actual amount of memory consumed by the VM + * (then, the memory provided by RAM blocks might be bigger than the desired + * memory consumption). This *must* be set if: + * - Discarding parts of a RAM blocks does not result in the change being + * reflected in the VM and the pages getting freed. + * - All memory in RAM blocks is pinned or duplicated, invaldiating any previous + * discards blindly. + * - Discarding parts of a RAM blocks will result in integrity issues (e.g., + * encrypted VMs). + * Technologies that only temporarily pin the current working set of a + * driver are fine, because we don't expect such pages to be discarded + * (esp. based on guest action like balloon inflation). + * + * This is *not* to be used to protect from concurrent discards (esp., + * postcopy). + * + * Returns 0 if successful. Returns -EBUSY if a technology that relies on + * discards to work reliably is active. + */ +int ram_block_discard_set_broken(bool state); + +/* + * Inhibit technologies that will break discarding of pages in RAM blocks. + * + * Returns 0 if successful. Returns -EBUSY if discards are already set to + * broken. + */ +int ram_block_discard_set_required(bool state); + +/* + * Test if discarding of memory in ram blocks is broken. + */ +bool ram_block_discard_is_broken(void); + +/* + * Test if discarding of memory in ram blocks is required to work reliably. + */ +bool ram_block_discard_is_required(void); + #endif #endif From patchwork Wed May 6 09:49:33 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530897 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 1206E81 for ; Wed, 6 May 2020 09:50:30 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id EADE320714 for ; Wed, 6 May 2020 09:50:29 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="jJY0Sinq" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729141AbgEFJu3 (ORCPT ); Wed, 6 May 2020 05:50:29 -0400 Received: from us-smtp-1.mimecast.com ([207.211.31.81]:49823 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728640AbgEFJu2 (ORCPT ); Wed, 6 May 2020 05:50:28 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758626; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=ZyQ2/G78uwjrsXG8DyLn++e8ECjOAjS5JkIsUcFHqRc=; b=jJY0SinqGTKGgyeVMHy3f0+bMljepKLmCS2/dVMHlCA+/mgUOxXDKUtBecjtgsqomURmgk CwMpbmkFNWoI6vvGCKQfi6Pp//h97JWtczup/6Gf2mImLe682m8TRt1GUkMuwOF1nHtEvX CtCcPv2knrODgnoQ6G/PbR7a4pKQdWc= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-51-3cLgPt92PAStbX38m3BNuw-1; Wed, 06 May 2020 05:50:20 -0400 X-MC-Unique: 3cLgPt92PAStbX38m3BNuw-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 930921800D4A; Wed, 6 May 2020 09:50:18 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id E5EF75C1D4; Wed, 6 May 2020 09:50:05 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Cornelia Huck , Alex Williamson , Christian Borntraeger , Tony Krowiak , Halil Pasic , Pierre Morel , Eric Farman Subject: [PATCH v1 02/17] vfio: Convert to ram_block_discard_set_broken() Date: Wed, 6 May 2020 11:49:33 +0200 Message-Id: <20200506094948.76388-3-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org VFIO is (except devices without a physical IOMMU or some mediated devices) incompatible ram_block_discard_set_broken. The kernel will pin basically all VM memory. Let's convert to ram_block_discard_set_broke(), which can now fail, in contrast to qemu_balloon_inhibit(). Leave "x-balloon-allowed" named as it is for now. Cc: Cornelia Huck Cc: Alex Williamson Cc: Christian Borntraeger Cc: Tony Krowiak Cc: Halil Pasic Cc: Pierre Morel Cc: Eric Farman Signed-off-by: David Hildenbrand --- hw/vfio/ap.c | 10 +++---- hw/vfio/ccw.c | 11 ++++---- hw/vfio/common.c | 53 +++++++++++++++++++---------------- hw/vfio/pci.c | 6 ++-- include/hw/vfio/vfio-common.h | 4 +-- 5 files changed, 45 insertions(+), 39 deletions(-) diff --git a/hw/vfio/ap.c b/hw/vfio/ap.c index 8649ac15f9..b51546d67a 100644 --- a/hw/vfio/ap.c +++ b/hw/vfio/ap.c @@ -105,12 +105,12 @@ static void vfio_ap_realize(DeviceState *dev, Error **errp) vapdev->vdev.dev = dev; /* - * vfio-ap devices operate in a way compatible with - * memory ballooning, as no pages are pinned in the host. - * This needs to be set before vfio_get_device() for vfio common to - * handle the balloon inhibitor. + * vfio-ap devices operate in a way compatible discarding of memory in + * RAM blocks, as no pages are pinned in the host. This needs to be + * set before vfio_get_device() for vfio common to handle + * ram_block_discard_set_broken(). */ - vapdev->vdev.balloon_allowed = true; + vapdev->vdev.ram_block_discard_allowed = true; ret = vfio_get_device(vfio_group, mdevid, &vapdev->vdev, errp); if (ret) { diff --git a/hw/vfio/ccw.c b/hw/vfio/ccw.c index 50cc2ec75c..0dd6c3f2ab 100644 --- a/hw/vfio/ccw.c +++ b/hw/vfio/ccw.c @@ -425,12 +425,13 @@ static void vfio_ccw_get_device(VFIOGroup *group, VFIOCCWDevice *vcdev, /* * All vfio-ccw devices are believed to operate in a way compatible with - * memory ballooning, ie. pages pinned in the host are in the current - * working set of the guest driver and therefore never overlap with pages - * available to the guest balloon driver. This needs to be set before - * vfio_get_device() for vfio common to handle the balloon inhibitor. + * discarding of memory in RAM blocks, ie. pages pinned in the host are + * in the current working set of the guest driver and therefore never + * overlap e.g., with pages available to the guest balloon driver. This + * needs to be set before vfio_get_device() for vfio common to handle + * ram_block_discard_set_broken(). */ - vcdev->vdev.balloon_allowed = true; + vcdev->vdev.ram_block_discard_allowed = true; if (vfio_get_device(group, vcdev->cdev.mdevid, &vcdev->vdev, errp)) { goto out_err; diff --git a/hw/vfio/common.c b/hw/vfio/common.c index 0b3593b3c0..98b2573ae6 100644 --- a/hw/vfio/common.c +++ b/hw/vfio/common.c @@ -33,7 +33,6 @@ #include "qemu/error-report.h" #include "qemu/main-loop.h" #include "qemu/range.h" -#include "sysemu/balloon.h" #include "sysemu/kvm.h" #include "sysemu/reset.h" #include "trace.h" @@ -1215,31 +1214,36 @@ static int vfio_connect_container(VFIOGroup *group, AddressSpace *as, space = vfio_get_address_space(as); /* - * VFIO is currently incompatible with memory ballooning insofar as the + * VFIO is currently incompatible with discarding of RAM insofar as the * madvise to purge (zap) the page from QEMU's address space does not * interact with the memory API and therefore leaves stale virtual to * physical mappings in the IOMMU if the page was previously pinned. We - * therefore add a balloon inhibit for each group added to a container, + * therefore set discarding broken for each group added to a container, * whether the container is used individually or shared. This provides * us with options to allow devices within a group to opt-in and allow - * ballooning, so long as it is done consistently for a group (for instance + * discarding, so long as it is done consistently for a group (for instance * if the device is an mdev device where it is known that the host vendor * driver will never pin pages outside of the working set of the guest - * driver, which would thus not be ballooning candidates). + * driver, which would thus not be discarding candidates). * * The first opportunity to induce pinning occurs here where we attempt to * attach the group to existing containers within the AddressSpace. If any - * pages are already zapped from the virtual address space, such as from a - * previous ballooning opt-in, new pinning will cause valid mappings to be + * pages are already zapped from the virtual address space, such as from + * previous discards, new pinning will cause valid mappings to be * re-established. Likewise, when the overall MemoryListener for a new * container is registered, a replay of mappings within the AddressSpace * will occur, re-establishing any previously zapped pages as well. * - * NB. Balloon inhibiting does not currently block operation of the - * balloon driver or revoke previously pinned pages, it only prevents - * calling madvise to modify the virtual mapping of ballooned pages. + * Especially virtio-balloon is currently only prevented from discarding + * new memory, it will not yet set ram_block_discard_set_required() and + * therefore, neither stops us here or deals with the sudden memory + * consumption of inflated memory. */ - qemu_balloon_inhibit(true); + ret = ram_block_discard_set_broken(true); + if (ret) { + error_setg_errno(errp, -ret, "Cannot set discarding of RAM broken"); + return ret; + } QLIST_FOREACH(container, &space->containers, next) { if (!ioctl(group->fd, VFIO_GROUP_SET_CONTAINER, &container->fd)) { @@ -1405,7 +1409,7 @@ close_fd_exit: close(fd); put_space_exit: - qemu_balloon_inhibit(false); + ram_block_discard_set_broken(false); vfio_put_address_space(space); return ret; @@ -1526,8 +1530,8 @@ void vfio_put_group(VFIOGroup *group) return; } - if (!group->balloon_allowed) { - qemu_balloon_inhibit(false); + if (!group->ram_block_discard_allowed) { + ram_block_discard_set_broken(false); } vfio_kvm_device_del_group(group); vfio_disconnect_container(group); @@ -1565,22 +1569,23 @@ int vfio_get_device(VFIOGroup *group, const char *name, } /* - * Clear the balloon inhibitor for this group if the driver knows the - * device operates compatibly with ballooning. Setting must be consistent - * per group, but since compatibility is really only possible with mdev - * currently, we expect singleton groups. + * Set discarding of RAM as not broken for this group if the driver knows + * the device operates compatibly with discarding. Setting must be + * consistent per group, but since compatibility is really only possible + * with mdev currently, we expect singleton groups. */ - if (vbasedev->balloon_allowed != group->balloon_allowed) { + if (vbasedev->ram_block_discard_allowed != + group->ram_block_discard_allowed) { if (!QLIST_EMPTY(&group->device_list)) { - error_setg(errp, - "Inconsistent device balloon setting within group"); + error_setg(errp, "Inconsistent setting of support for discarding " + "RAM (e.g., balloon) within group"); close(fd); return -1; } - if (!group->balloon_allowed) { - group->balloon_allowed = true; - qemu_balloon_inhibit(false); + if (!group->ram_block_discard_allowed) { + group->ram_block_discard_allowed = true; + ram_block_discard_set_broken(false); } } diff --git a/hw/vfio/pci.c b/hw/vfio/pci.c index 5e75a95129..88c630c21c 100644 --- a/hw/vfio/pci.c +++ b/hw/vfio/pci.c @@ -2796,7 +2796,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) } /* - * Mediated devices *might* operate compatibly with memory ballooning, but + * Mediated devices *might* operate compatibly with discarding of RAM, but * we cannot know for certain, it depends on whether the mdev vendor driver * stays in sync with the active working set of the guest driver. Prevent * the x-balloon-allowed option unless this is minimally an mdev device. @@ -2809,7 +2809,7 @@ static void vfio_realize(PCIDevice *pdev, Error **errp) trace_vfio_mdev(vdev->vbasedev.name, is_mdev); - if (vdev->vbasedev.balloon_allowed && !is_mdev) { + if (vdev->vbasedev.ram_block_discard_allowed && !is_mdev) { error_setg(errp, "x-balloon-allowed only potentially compatible " "with mdev devices"); vfio_put_group(group); @@ -3163,7 +3163,7 @@ static Property vfio_pci_dev_properties[] = { VFIO_FEATURE_ENABLE_IGD_OPREGION_BIT, false), DEFINE_PROP_BOOL("x-no-mmap", VFIOPCIDevice, vbasedev.no_mmap, false), DEFINE_PROP_BOOL("x-balloon-allowed", VFIOPCIDevice, - vbasedev.balloon_allowed, false), + vbasedev.ram_block_discard_allowed, false), DEFINE_PROP_BOOL("x-no-kvm-intx", VFIOPCIDevice, no_kvm_intx, false), DEFINE_PROP_BOOL("x-no-kvm-msi", VFIOPCIDevice, no_kvm_msi, false), DEFINE_PROP_BOOL("x-no-kvm-msix", VFIOPCIDevice, no_kvm_msix, false), diff --git a/include/hw/vfio/vfio-common.h b/include/hw/vfio/vfio-common.h index fd564209ac..c78f3ff559 100644 --- a/include/hw/vfio/vfio-common.h +++ b/include/hw/vfio/vfio-common.h @@ -108,7 +108,7 @@ typedef struct VFIODevice { bool reset_works; bool needs_reset; bool no_mmap; - bool balloon_allowed; + bool ram_block_discard_allowed; VFIODeviceOps *ops; unsigned int num_irqs; unsigned int num_regions; @@ -128,7 +128,7 @@ typedef struct VFIOGroup { QLIST_HEAD(, VFIODevice) device_list; QLIST_ENTRY(VFIOGroup) next; QLIST_ENTRY(VFIOGroup) container_next; - bool balloon_allowed; + bool ram_block_discard_allowed; } VFIOGroup; typedef struct VFIODMABuf { From patchwork Wed May 6 09:49:34 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530895 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 138C1139F for ; Wed, 6 May 2020 09:50:26 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E69982073A for ; Wed, 6 May 2020 09:50:25 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="XcgkJg4H" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729129AbgEFJuZ (ORCPT ); Wed, 6 May 2020 05:50:25 -0400 Received: from us-smtp-2.mimecast.com ([207.211.31.81]:58682 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728640AbgEFJuY (ORCPT ); Wed, 6 May 2020 05:50:24 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758623; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=ePQAGUxkbDh1KstjsNvoLvmQ61QNRVAAmm68r4w7K/A=; b=XcgkJg4Hi3SM90RjgDl1whalxwQ945p6WBJBEY6vfm3JLN5SAVhZBIYHaR/67xrnkUIQDu wWPUoU/5mooeUHxi+c77nDGtrZLp0NujVWWlp0YOJ/KaqRpglP7ZTw7ZK9yuCbxytolpmt 4noph6jcvCHfkzt5SDbbtHDGHthUsUM= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-445-WBZ3s7CHPq61jgOylngiQw-1; Wed, 06 May 2020 05:50:22 -0400 X-MC-Unique: WBZ3s7CHPq61jgOylngiQw-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id BDF488018AB; Wed, 6 May 2020 09:50:20 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id E0A415C1BD; Wed, 6 May 2020 09:50:18 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand Subject: [PATCH v1 03/17] accel/kvm: Convert to ram_block_discard_set_broken() Date: Wed, 6 May 2020 11:49:34 +0200 Message-Id: <20200506094948.76388-4-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Discarding memory does not work as expected. At the time this is called, we cannot have anyone active that relies on discards to work properly. Cc: Paolo Bonzini Signed-off-by: David Hildenbrand Reviewed-by: Dr. David Alan Gilbert --- accel/kvm/kvm-all.c | 3 +-- 1 file changed, 1 insertion(+), 2 deletions(-) diff --git a/accel/kvm/kvm-all.c b/accel/kvm/kvm-all.c index 439a4efe52..33421184ac 100644 --- a/accel/kvm/kvm-all.c +++ b/accel/kvm/kvm-all.c @@ -40,7 +40,6 @@ #include "trace.h" #include "hw/irq.h" #include "sysemu/sev.h" -#include "sysemu/balloon.h" #include "qapi/visitor.h" #include "qapi/qapi-types-common.h" #include "qapi/qapi-visit-common.h" @@ -2107,7 +2106,7 @@ static int kvm_init(MachineState *ms) s->sync_mmu = !!kvm_vm_check_extension(kvm_state, KVM_CAP_SYNC_MMU); if (!s->sync_mmu) { - qemu_balloon_inhibit(true); + g_assert(ram_block_discard_set_broken(true)); } return 0; From patchwork Wed May 6 09:49:35 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530899 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0F58381 for ; Wed, 6 May 2020 09:50:34 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id EB2382070B for ; Wed, 6 May 2020 09:50:33 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="PUu0u2TD" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729165AbgEFJud (ORCPT ); Wed, 6 May 2020 05:50:33 -0400 Received: from us-smtp-delivery-1.mimecast.com ([207.211.31.120]:24740 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1728640AbgEFJuc (ORCPT ); Wed, 6 May 2020 05:50:32 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758631; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=/GY4oovHxhg2sMHqPCFokb23HWuBbkQyiVf4WFIihCM=; b=PUu0u2TD+mAT4EQYygci9ZdmYZrTfWCDo5Z2li4AhM+xRHI00+x0QdTbwtkHquwhskmvry jNuoWgLe1eXmnlAy1ImZrrq+oJCR7P1u5OVYClco4SULInoolb5CJehyYTfnFx5xzuSOiR W7H1VJaQgB/MGFJdUB8OAiQR2dOI9lE= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-225-4o0BOl6hPdGs_kJ-OebmNg-1; Wed, 06 May 2020 05:50:25 -0400 X-MC-Unique: 4o0BOl6hPdGs_kJ-OebmNg-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 938C1835B41; Wed, 6 May 2020 09:50:23 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 177A65C1BD; Wed, 6 May 2020 09:50:20 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Cornelia Huck , Halil Pasic , Christian Borntraeger , Janosch Frank Subject: [PATCH v1 04/17] s390x/pv: Convert to ram_block_discard_set_broken() Date: Wed, 6 May 2020 11:49:35 +0200 Message-Id: <20200506094948.76388-5-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Discarding RAM does not work as expected with protected VMs. Let's switch to ram_block_discard_set_broken() for now, as we want to get rid of qemu_balloon_inhibit(). Note that it will currently never fail, but might fail in the future with new technologies (e.g., virtio-mem). Cc: Richard Henderson Cc: Cornelia Huck Cc: Halil Pasic Cc: Christian Borntraeger Cc: Janosch Frank Signed-off-by: David Hildenbrand --- hw/s390x/s390-virtio-ccw.c | 22 +++++++++++++--------- 1 file changed, 13 insertions(+), 9 deletions(-) diff --git a/hw/s390x/s390-virtio-ccw.c b/hw/s390x/s390-virtio-ccw.c index 45292fb5a8..883ea392bc 100644 --- a/hw/s390x/s390-virtio-ccw.c +++ b/hw/s390x/s390-virtio-ccw.c @@ -43,7 +43,6 @@ #include "hw/qdev-properties.h" #include "hw/s390x/tod.h" #include "sysemu/sysemu.h" -#include "sysemu/balloon.h" #include "hw/s390x/pv.h" #include "migration/blocker.h" @@ -329,7 +328,7 @@ static void s390_machine_unprotect(S390CcwMachineState *ms) ms->pv = false; migrate_del_blocker(pv_mig_blocker); error_free_or_abort(&pv_mig_blocker); - qemu_balloon_inhibit(false); + ram_block_discard_set_broken(false); } static int s390_machine_protect(S390CcwMachineState *ms) @@ -338,17 +337,22 @@ static int s390_machine_protect(S390CcwMachineState *ms) int rc; /* - * Ballooning on protected VMs needs support in the guest for - * sharing and unsharing balloon pages. Block ballooning for - * now, until we have a solution to make at least Linux guests - * either support it or fail gracefully. + * Discarding of memory in RAM blocks does not work as expected with + * protected VMs. Sharing and unsharing pages would be required. Mark it as + * broken for now, until until we have a solution to make at least Linux + * guests either support it (e.g., virtio-balloon) or fail gracefully. */ - qemu_balloon_inhibit(true); + rc = ram_block_discard_set_broken(true); + if (rc) { + error_report("protected VMs: cannot set discarding of RAM broken"); + return rc; + } + error_setg(&pv_mig_blocker, "protected VMs are currently not migrateable."); rc = migrate_add_blocker(pv_mig_blocker, &local_err); if (rc) { - qemu_balloon_inhibit(false); + ram_block_discard_set_broken(false); error_report_err(local_err); error_free_or_abort(&pv_mig_blocker); return rc; @@ -357,7 +361,7 @@ static int s390_machine_protect(S390CcwMachineState *ms) /* Create SE VM */ rc = s390_pv_vm_enable(); if (rc) { - qemu_balloon_inhibit(false); + ram_block_discard_set_broken(false); migrate_del_blocker(pv_mig_blocker); error_free_or_abort(&pv_mig_blocker); return rc; From patchwork Wed May 6 09:49:36 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530901 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 510DE139F for ; Wed, 6 May 2020 09:50:35 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 3ABB220714 for ; Wed, 6 May 2020 09:50:35 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="Y1Ax3kqX" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729173AbgEFJue (ORCPT ); Wed, 6 May 2020 05:50:34 -0400 Received: from us-smtp-2.mimecast.com ([207.211.31.81]:33943 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729146AbgEFJud (ORCPT ); Wed, 6 May 2020 05:50:33 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758632; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=VLvhweL9MM4fO8C2USx4CrswD98agNtloG3GZKunYNo=; b=Y1Ax3kqX0lWncYYOpYA1TFgwjgu3f7yjV+1Jaz0VblmjNX1XMERhcAM8IAkv43wMIkSEs6 1KczJ8R4LL7QcJClmOCTLtQDu/Wnx5t/9P9RVaIdJO4VFk1YiFpcItaoshlmioZXXl1WuX 5El3LEBMwLvSBRQHEW2CvowJS0txHHw= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-193-xu27MMluPju_Nh_onFEfNA-1; Wed, 06 May 2020 05:50:27 -0400 X-MC-Unique: xu27MMluPju_Nh_onFEfNA-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id E78CC461; Wed, 6 May 2020 09:50:25 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id E4A305C1BD; Wed, 6 May 2020 09:50:23 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Juan Quintela Subject: [PATCH v1 05/17] virtio-balloon: Rip out qemu_balloon_inhibit() Date: Wed, 6 May 2020 11:49:36 +0200 Message-Id: <20200506094948.76388-6-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org The only remaining special case is postcopy. It cannot handle concurrent discards yet, which would result in requesting already sent pages from the source. Special-case it in virtio-balloon instead. Cc: "Michael S. Tsirkin" Cc: Juan Quintela Cc: "Dr. David Alan Gilbert" Signed-off-by: David Hildenbrand --- balloon.c | 18 ------------------ hw/virtio/virtio-balloon.c | 12 +++++++++++- include/sysemu/balloon.h | 2 -- migration/postcopy-ram.c | 23 ----------------------- 4 files changed, 11 insertions(+), 44 deletions(-) diff --git a/balloon.c b/balloon.c index c49f57c27b..354408c6ea 100644 --- a/balloon.c +++ b/balloon.c @@ -36,24 +36,6 @@ static QEMUBalloonEvent *balloon_event_fn; static QEMUBalloonStatus *balloon_stat_fn; static void *balloon_opaque; -static int balloon_inhibit_count; - -bool qemu_balloon_is_inhibited(void) -{ - return atomic_read(&balloon_inhibit_count) > 0 || - ram_block_discard_is_broken(); -} - -void qemu_balloon_inhibit(bool state) -{ - if (state) { - atomic_inc(&balloon_inhibit_count); - } else { - atomic_dec(&balloon_inhibit_count); - } - - assert(atomic_read(&balloon_inhibit_count) >= 0); -} static bool have_balloon(Error **errp) { diff --git a/hw/virtio/virtio-balloon.c b/hw/virtio/virtio-balloon.c index a4729f7fc9..aa5b89fb47 100644 --- a/hw/virtio/virtio-balloon.c +++ b/hw/virtio/virtio-balloon.c @@ -29,6 +29,7 @@ #include "trace.h" #include "qemu/error-report.h" #include "migration/misc.h" +#include "migration/postcopy-ram.h" #include "hw/virtio/virtio-bus.h" #include "hw/virtio/virtio-access.h" @@ -63,6 +64,15 @@ static bool virtio_balloon_pbp_matches(PartiallyBalloonedPage *pbp, return pbp->base_gpa == base_gpa; } +static bool virtio_balloon_inhibited(void) +{ + PostcopyState ps = postcopy_state_get(); + + /* Postcopy cannot deal with concurrent discards (yet), so it's special. */ + return ram_block_discard_is_broken() || + (ps >= POSTCOPY_INCOMING_DISCARD && ps < POSTCOPY_INCOMING_END); +} + static void balloon_inflate_page(VirtIOBalloon *balloon, MemoryRegion *mr, hwaddr mr_offset, PartiallyBalloonedPage *pbp) @@ -360,7 +370,7 @@ static void virtio_balloon_handle_output(VirtIODevice *vdev, VirtQueue *vq) trace_virtio_balloon_handle_output(memory_region_name(section.mr), pa); - if (!qemu_balloon_is_inhibited()) { + if (!virtio_balloon_inhibited()) { if (vq == s->ivq) { balloon_inflate_page(s, section.mr, section.offset_within_region, &pbp); diff --git a/include/sysemu/balloon.h b/include/sysemu/balloon.h index aea0c44985..20a2defe3a 100644 --- a/include/sysemu/balloon.h +++ b/include/sysemu/balloon.h @@ -23,7 +23,5 @@ typedef void (QEMUBalloonStatus)(void *opaque, BalloonInfo *info); int qemu_add_balloon_handler(QEMUBalloonEvent *event_func, QEMUBalloonStatus *stat_func, void *opaque); void qemu_remove_balloon_handler(void *opaque); -bool qemu_balloon_is_inhibited(void); -void qemu_balloon_inhibit(bool state); #endif diff --git a/migration/postcopy-ram.c b/migration/postcopy-ram.c index a36402722b..b41a9fe2fd 100644 --- a/migration/postcopy-ram.c +++ b/migration/postcopy-ram.c @@ -27,7 +27,6 @@ #include "qemu/notify.h" #include "qemu/rcu.h" #include "sysemu/sysemu.h" -#include "sysemu/balloon.h" #include "qemu/error-report.h" #include "trace.h" #include "hw/boards.h" @@ -520,20 +519,6 @@ int postcopy_ram_incoming_init(MigrationIncomingState *mis) return 0; } -/* - * Manage a single vote to the QEMU balloon inhibitor for all postcopy usage, - * last caller wins. - */ -static void postcopy_balloon_inhibit(bool state) -{ - static bool cur_state = false; - - if (state != cur_state) { - qemu_balloon_inhibit(state); - cur_state = state; - } -} - /* * At the end of a migration where postcopy_ram_incoming_init was called. */ @@ -565,8 +550,6 @@ int postcopy_ram_incoming_cleanup(MigrationIncomingState *mis) mis->have_fault_thread = false; } - postcopy_balloon_inhibit(false); - if (enable_mlock) { if (os_mlock() < 0) { error_report("mlock: %s", strerror(errno)); @@ -1160,12 +1143,6 @@ int postcopy_ram_incoming_setup(MigrationIncomingState *mis) } memset(mis->postcopy_tmp_zero_page, '\0', mis->largest_page_size); - /* - * Ballooning can mark pages as absent while we're postcopying - * that would cause false userfaults. - */ - postcopy_balloon_inhibit(true); - trace_postcopy_ram_enable_notify(); return 0; From patchwork Wed May 6 09:49:37 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530903 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id F169C139F for ; Wed, 6 May 2020 09:50:38 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id CFBA62073A for ; Wed, 6 May 2020 09:50:38 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="i5L9wF88" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729184AbgEFJuh (ORCPT ); Wed, 6 May 2020 05:50:37 -0400 Received: from us-smtp-1.mimecast.com ([207.211.31.81]:44754 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729153AbgEFJuh (ORCPT ); Wed, 6 May 2020 05:50:37 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758636; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=ZENkbpOQATs9T0Mx8ZvJbUDiOPi/mRt38fEpR3MkuxY=; b=i5L9wF88seGVdDzccMWT2oXGFVf3Ro49UN3LJZ7oHHsVaO2gLZ1ko/DGD5cOLtHxTwfKBw ofoUnDYgHhvUccvc4Cm8mX4eUK2mn7WdK2+SGaz8gF99mnsGQzy/IPxFSX6ifWCt28eVp3 L2FWse4+HN76fWw5DwYk43Y6q1ZsGkQ= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-193-YleYrMkWOMubZD7E1CkN7A-1; Wed, 06 May 2020 05:50:34 -0400 X-MC-Unique: YleYrMkWOMubZD7E1CkN7A-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id A54FB100CCC5; Wed, 6 May 2020 09:50:33 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 402C15C1BD; Wed, 6 May 2020 09:50:26 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand Subject: [PATCH v1 06/17] target/i386: sev: Use ram_block_discard_set_broken() Date: Wed, 6 May 2020 11:49:37 +0200 Message-Id: <20200506094948.76388-7-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org AMD SEV will pin all guest memory, mark discarding of RAM broken. At the time this is called, we cannot have anyone active that relies on discards to work properly. Cc: "Michael S. Tsirkin" Cc: Paolo Bonzini Cc: Richard Henderson Cc: Eduardo Habkost Signed-off-by: David Hildenbrand Reviewed-by: Dr. David Alan Gilbert --- target/i386/sev.c | 1 + 1 file changed, 1 insertion(+) diff --git a/target/i386/sev.c b/target/i386/sev.c index 846018a12d..608225f9ba 100644 --- a/target/i386/sev.c +++ b/target/i386/sev.c @@ -722,6 +722,7 @@ sev_guest_init(const char *id) ram_block_notifier_add(&sev_ram_notifier); qemu_add_machine_init_done_notifier(&sev_machine_done_notify); qemu_add_vm_change_state_handler(sev_vm_state_change, s); + g_assert(!ram_block_discard_set_broken(true)); return s; err: From patchwork Wed May 6 09:49:38 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530905 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 14BC3139F for ; Wed, 6 May 2020 09:50:42 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id F151C2073A for ; Wed, 6 May 2020 09:50:41 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="Y0Xk9b8b" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729227AbgEFJul (ORCPT ); Wed, 6 May 2020 05:50:41 -0400 Received: from us-smtp-delivery-1.mimecast.com ([207.211.31.120]:44581 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729206AbgEFJuk (ORCPT ); Wed, 6 May 2020 05:50:40 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758638; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=O10BhkYK4SLEDgxOR3AeYFqIdU21u3W3cDnwDc7jdOs=; b=Y0Xk9b8bYdPuxHX5GylAE2gwqu/ZFrIUGAQvqE/8d5XE6eBAuf+lUjCwf7xMsHKxW1CEtl E+VIYqKdi+GUBXbduaKaYHRdRwiob06g+Y+CYRC1jitnQGn0GmHU2/aiiwPh7Q6yL8Zkjo F0vW7ZHKMtR+WlDqz9sAvefNyZDc7ZU= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-499-EJvB0YQXPxi4wNhYZd1E4g-1; Wed, 06 May 2020 05:50:37 -0400 X-MC-Unique: EJvB0YQXPxi4wNhYZd1E4g-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 01E92107ACF2; Wed, 6 May 2020 09:50:36 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id F02245C1BD; Wed, 6 May 2020 09:50:33 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Juan Quintela Subject: [PATCH v1 07/17] migration/rdma: Use ram_block_discard_set_broken() Date: Wed, 6 May 2020 11:49:38 +0200 Message-Id: <20200506094948.76388-8-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org RDMA will pin all guest memory (as documented in docs/rdma.txt). We want to mark RAM block discards to be broken - however, to keep it simple use ram_block_discard_is_required() instead of inhibiting. Cc: "Michael S. Tsirkin" Cc: Juan Quintela Cc: "Dr. David Alan Gilbert" Signed-off-by: David Hildenbrand --- migration/rdma.c | 18 ++++++++++++++++-- 1 file changed, 16 insertions(+), 2 deletions(-) diff --git a/migration/rdma.c b/migration/rdma.c index f61587891b..029adbb950 100644 --- a/migration/rdma.c +++ b/migration/rdma.c @@ -29,6 +29,7 @@ #include "qemu/sockets.h" #include "qemu/bitmap.h" #include "qemu/coroutine.h" +#include "exec/memory.h" #include #include #include @@ -4017,8 +4018,14 @@ void rdma_start_incoming_migration(const char *host_port, Error **errp) Error *local_err = NULL; trace_rdma_start_incoming_migration(); - rdma = qemu_rdma_data_init(host_port, &local_err); + /* Avoid ram_block_discard_set_broken(), cannot change during migration. */ + if (ram_block_discard_is_required()) { + error_setg(errp, "RDMA: cannot set discarding of RAM broken"); + return; + } + + rdma = qemu_rdma_data_init(host_port, &local_err); if (rdma == NULL) { goto err; } @@ -4064,10 +4071,17 @@ void rdma_start_outgoing_migration(void *opaque, const char *host_port, Error **errp) { MigrationState *s = opaque; - RDMAContext *rdma = qemu_rdma_data_init(host_port, errp); RDMAContext *rdma_return_path = NULL; + RDMAContext *rdma; int ret = 0; + /* Avoid ram_block_discard_set_broken(), cannot change during migration. */ + if (ram_block_discard_is_required()) { + error_setg(errp, "RDMA: cannot set discarding of RAM broken"); + return; + } + + rdma = qemu_rdma_data_init(host_port, errp); if (rdma == NULL) { goto err; } From patchwork Wed May 6 09:49:39 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530907 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id D8E6D81 for ; Wed, 6 May 2020 09:50:46 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id BF31D2070B for ; Wed, 6 May 2020 09:50:46 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="OJ5WO+hX" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729234AbgEFJup (ORCPT ); Wed, 6 May 2020 05:50:45 -0400 Received: from us-smtp-1.mimecast.com ([205.139.110.61]:55594 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729176AbgEFJuo (ORCPT ); Wed, 6 May 2020 05:50:44 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758643; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=HiYZK5Z/1tdBn0MeeAphcfReGNPxF8BUMmE6+8UMB8Y=; b=OJ5WO+hXQOHrnk/CPhe48MGsd2B379we6FP1s6VDOasZVSBSt47aTI3qWD0kEP6v2ng9Ni dpL+e0WlFRxqvvGDy9PSfSAv/EKkHmWKEtn/XdWynHCgIsszlcxWXEQghQmcgTrNMxOTAc xNUuAzNg87mFs8JRQwkXzJx/CFzGzjA= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-250-fjvezdvuOE2bJ1-EzJwocQ-1; Wed, 06 May 2020 05:50:39 -0400 X-MC-Unique: fjvezdvuOE2bJ1-EzJwocQ-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 7C9211895A2B; Wed, 6 May 2020 09:50:38 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 52AF15C1BD; Wed, 6 May 2020 09:50:36 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Hailiang Zhang , Juan Quintela Subject: [PATCH v1 08/17] migration/colo: Use ram_block_discard_set_broken() Date: Wed, 6 May 2020 11:49:39 +0200 Message-Id: <20200506094948.76388-9-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org COLO will copy all memory in a RAM block, mark discarding of RAM broken. Cc: "Michael S. Tsirkin" Cc: Hailiang Zhang Cc: Juan Quintela Cc: "Dr. David Alan Gilbert" Signed-off-by: David Hildenbrand Reviewed-by: Dr. David Alan Gilbert --- include/migration/colo.h | 2 +- migration/migration.c | 8 +++++++- migration/savevm.c | 11 +++++++++-- 3 files changed, 17 insertions(+), 4 deletions(-) diff --git a/include/migration/colo.h b/include/migration/colo.h index 1636e6f907..768e1f04c3 100644 --- a/include/migration/colo.h +++ b/include/migration/colo.h @@ -25,7 +25,7 @@ void migrate_start_colo_process(MigrationState *s); bool migration_in_colo_state(void); /* loadvm */ -void migration_incoming_enable_colo(void); +int migration_incoming_enable_colo(void); void migration_incoming_disable_colo(void); bool migration_incoming_colo_enabled(void); void *colo_process_incoming_thread(void *opaque); diff --git a/migration/migration.c b/migration/migration.c index 177cce9e95..f6830e4620 100644 --- a/migration/migration.c +++ b/migration/migration.c @@ -338,12 +338,18 @@ bool migration_incoming_colo_enabled(void) void migration_incoming_disable_colo(void) { + ram_block_discard_set_broken(false); migration_colo_enabled = false; } -void migration_incoming_enable_colo(void) +int migration_incoming_enable_colo(void) { + if (ram_block_discard_set_broken(true)) { + error_report("COLO: cannot set discarding of RAM broken"); + return -EBUSY; + } migration_colo_enabled = true; + return 0; } void migrate_add_address(SocketAddress *address) diff --git a/migration/savevm.c b/migration/savevm.c index c00a6807d9..19b4f9600d 100644 --- a/migration/savevm.c +++ b/migration/savevm.c @@ -2111,8 +2111,15 @@ static int loadvm_handle_recv_bitmap(MigrationIncomingState *mis, static int loadvm_process_enable_colo(MigrationIncomingState *mis) { - migration_incoming_enable_colo(); - return colo_init_ram_cache(); + int ret = migration_incoming_enable_colo(); + + if (!ret) { + ret = colo_init_ram_cache(); + if (ret) { + migration_incoming_disable_colo(); + } + } + return ret; } /* From patchwork Wed May 6 09:49:40 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530909 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id E67E817EF for ; Wed, 6 May 2020 09:50:47 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id CA9F920747 for ; Wed, 6 May 2020 09:50:47 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="CLw5Idfz" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729230AbgEFJuq (ORCPT ); Wed, 6 May 2020 05:50:46 -0400 Received: from us-smtp-delivery-1.mimecast.com ([207.211.31.120]:59590 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729191AbgEFJup (ORCPT ); Wed, 6 May 2020 05:50:45 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758643; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=MnXnpMO0UqQKX2axyRI3RCRoe8bEB4edcKGCT4TrFx8=; b=CLw5IdfzBU6NVHdEJc4neyNOjP6idqtMEVQztpnc4DPMrD0V1b25+cUMjjXLl0IBqsx06a ZT/sC6oxF+NzNqXMn9YxZkJXBzYJVBkl/MKZN3SIT/9SCRodg5Xib5dkHC+YmzcveFn4pL +Zcdw+J5Tz605tn9TaVYqAPh9cenG+Y= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-423-Vdl480bjOgiZeNrnOZA-eg-1; Wed, 06 May 2020 05:50:41 -0400 X-MC-Unique: Vdl480bjOgiZeNrnOZA-eg-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id A6FF21800D4A; Wed, 6 May 2020 09:50:40 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id CB2FF5C1BD; Wed, 6 May 2020 09:50:38 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand Subject: [PATCH v1 09/17] linux-headers: update to contain virtio-mem Date: Wed, 6 May 2020 11:49:40 +0200 Message-Id: <20200506094948.76388-10-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org To be merged hopefully soon. Then, we can replace this by a proper header sync. Cc: "Michael S. Tsirkin" Signed-off-by: David Hildenbrand --- include/standard-headers/linux/virtio_ids.h | 1 + include/standard-headers/linux/virtio_mem.h | 208 ++++++++++++++++++++ 2 files changed, 209 insertions(+) create mode 100644 include/standard-headers/linux/virtio_mem.h diff --git a/include/standard-headers/linux/virtio_ids.h b/include/standard-headers/linux/virtio_ids.h index ecc27a1740..b052355ac7 100644 --- a/include/standard-headers/linux/virtio_ids.h +++ b/include/standard-headers/linux/virtio_ids.h @@ -44,6 +44,7 @@ #define VIRTIO_ID_VSOCK 19 /* virtio vsock transport */ #define VIRTIO_ID_CRYPTO 20 /* virtio crypto */ #define VIRTIO_ID_IOMMU 23 /* virtio IOMMU */ +#define VIRTIO_ID_MEM 24 /* virtio mem */ #define VIRTIO_ID_FS 26 /* virtio filesystem */ #define VIRTIO_ID_PMEM 27 /* virtio pmem */ #define VIRTIO_ID_MAC80211_HWSIM 29 /* virtio mac80211-hwsim */ diff --git a/include/standard-headers/linux/virtio_mem.h b/include/standard-headers/linux/virtio_mem.h new file mode 100644 index 0000000000..c28dd40870 --- /dev/null +++ b/include/standard-headers/linux/virtio_mem.h @@ -0,0 +1,208 @@ +/* SPDX-License-Identifier: BSD-3-Clause */ +/* + * Virtio Mem Device + * + * Copyright Red Hat, Inc. 2020 + * + * Authors: + * David Hildenbrand + * + * This header is BSD licensed so anyone can use the definitions + * to implement compatible drivers/servers: + * + * Redistribution and use in source and binary forms, with or without + * modification, are permitted provided that the following conditions + * are met: + * 1. Redistributions of source code must retain the above copyright + * notice, this list of conditions and the following disclaimer. + * 2. Redistributions in binary form must reproduce the above copyright + * notice, this list of conditions and the following disclaimer in the + * documentation and/or other materials provided with the distribution. + * 3. Neither the name of IBM nor the names of its contributors + * may be used to endorse or promote products derived from this software + * without specific prior written permission. + * THIS SOFTWARE IS PROVIDED BY THE COPYRIGHT HOLDERS AND CONTRIBUTORS + * ``AS IS'' AND ANY EXPRESS OR IMPLIED WARRANTIES, INCLUDING, BUT NOT + * LIMITED TO, THE IMPLIED WARRANTIES OF MERCHANTABILITY AND FITNESS + * FOR A PARTICULAR PURPOSE ARE DISCLAIMED. IN NO EVENT SHALL IBM OR + * CONTRIBUTORS BE LIABLE FOR ANY DIRECT, INDIRECT, INCIDENTAL, + * SPECIAL, EXEMPLARY, OR CONSEQUENTIAL DAMAGES (INCLUDING, BUT NOT + * LIMITED TO, PROCUREMENT OF SUBSTITUTE GOODS OR SERVICES; LOSS OF + * USE, DATA, OR PROFITS; OR BUSINESS INTERRUPTION) HOWEVER CAUSED AND + * ON ANY THEORY OF LIABILITY, WHETHER IN CONTRACT, STRICT LIABILITY, + * OR TORT (INCLUDING NEGLIGENCE OR OTHERWISE) ARISING IN ANY WAY OUT + * OF THE USE OF THIS SOFTWARE, EVEN IF ADVISED OF THE POSSIBILITY OF + * SUCH DAMAGE. + */ + +#ifndef _LINUX_VIRTIO_MEM_H +#define _LINUX_VIRTIO_MEM_H + +#include "standard-headers/linux/types.h" +#include "standard-headers/linux/virtio_types.h" +#include "standard-headers/linux/virtio_ids.h" +#include "standard-headers/linux/virtio_config.h" + +/* + * Each virtio-mem device manages a dedicated region in physical address + * space. Each device can belong to a single NUMA node, multiple devices + * for a single NUMA node are possible. A virtio-mem device is like a + * "resizable DIMM" consisting of small memory blocks that can be plugged + * or unplugged. The device driver is responsible for (un)plugging memory + * blocks on demand. + * + * Virtio-mem devices can only operate on their assigned memory region in + * order to (un)plug memory. A device cannot (un)plug memory belonging to + * other devices. + * + * The "region_size" corresponds to the maximum amount of memory that can + * be provided by a device. The "size" corresponds to the amount of memory + * that is currently plugged. "requested_size" corresponds to a request + * from the device to the device driver to (un)plug blocks. The + * device driver should try to (un)plug blocks in order to reach the + * "requested_size". It is impossible to plug more memory than requested. + * + * The "usable_region_size" represents the memory region that can actually + * be used to (un)plug memory. It is always at least as big as the + * "requested_size" and will grow dynamically. It will only shrink when + * explicitly triggered (VIRTIO_MEM_REQ_UNPLUG). + * + * There are no guarantees what will happen if unplugged memory is + * read/written. Such memory should, in general, not be touched. E.g., + * even writing might succeed, but the values will simply be discarded at + * random points in time. + * + * It can happen that the device cannot process a request, because it is + * busy. The device driver has to retry later. + * + * Usually, during system resets all memory will get unplugged, so the + * device driver can start with a clean state. However, in specific + * scenarios (if the device is busy) it can happen that the device still + * has memory plugged. The device driver can request to unplug all memory + * (VIRTIO_MEM_REQ_UNPLUG) - which might take a while to succeed if the + * device is busy. + */ + +/* --- virtio-mem: feature bits --- */ + +/* node_id is an ACPI PXM and is valid */ +#define VIRTIO_MEM_F_ACPI_PXM 0 + + +/* --- virtio-mem: guest -> host requests --- */ + +/* request to plug memory blocks */ +#define VIRTIO_MEM_REQ_PLUG 0 +/* request to unplug memory blocks */ +#define VIRTIO_MEM_REQ_UNPLUG 1 +/* request to unplug all blocks and shrink the usable size */ +#define VIRTIO_MEM_REQ_UNPLUG_ALL 2 +/* request information about the plugged state of memory blocks */ +#define VIRTIO_MEM_REQ_STATE 3 + +struct virtio_mem_req_plug { + __virtio64 addr; + __virtio16 nb_blocks; +}; + +struct virtio_mem_req_unplug { + __virtio64 addr; + __virtio16 nb_blocks; +}; + +struct virtio_mem_req_state { + __virtio64 addr; + __virtio16 nb_blocks; +}; + +struct virtio_mem_req { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_req_plug plug; + struct virtio_mem_req_unplug unplug; + struct virtio_mem_req_state state; + } u; +}; + + +/* --- virtio-mem: host -> guest response --- */ + +/* + * Request processed successfully, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ACK 0 +/* + * Request denied - e.g. trying to plug more than requested, applicable for + * - VIRTIO_MEM_REQ_PLUG + */ +#define VIRTIO_MEM_RESP_NACK 1 +/* + * Request cannot be processed right now, try again later, applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_UNPLUG_ALL + */ +#define VIRTIO_MEM_RESP_BUSY 2 +/* + * Error in request (e.g. addresses/alignment), applicable for + * - VIRTIO_MEM_REQ_PLUG + * - VIRTIO_MEM_REQ_UNPLUG + * - VIRTIO_MEM_REQ_STATE + */ +#define VIRTIO_MEM_RESP_ERROR 3 + + +/* State of memory blocks is "plugged" */ +#define VIRTIO_MEM_STATE_PLUGGED 0 +/* State of memory blocks is "unplugged" */ +#define VIRTIO_MEM_STATE_UNPLUGGED 1 +/* State of memory blocks is "mixed" */ +#define VIRTIO_MEM_STATE_MIXED 2 + +struct virtio_mem_resp_state { + __virtio16 state; +}; + +struct virtio_mem_resp { + __virtio16 type; + __virtio16 padding[3]; + + union { + struct virtio_mem_resp_state state; + } u; +}; + +/* --- virtio-mem: configuration --- */ + +struct virtio_mem_config { + /* Block size and alignment. Cannot change. */ + uint32_t block_size; + /* Valid with VIRTIO_MEM_F_ACPI_PXM. Cannot change. */ + uint16_t node_id; + uint16_t padding; + /* Start address of the memory region. Cannot change. */ + uint64_t addr; + /* Region size (maximum). Cannot change. */ + uint64_t region_size; + /* + * Currently usable region size. Can grow up to region_size. Can + * shrink due to VIRTIO_MEM_REQ_UNPLUG_ALL (in which case no config + * update will be sent). + */ + uint64_t usable_region_size; + /* + * Currently used size. Changes due to plug/unplug requests, but no + * config updates will be sent. + */ + uint64_t plugged_size; + /* Requested size. New plug requests cannot exceed it. Can change. */ + uint64_t requested_size; +}; + +#endif /* _LINUX_VIRTIO_MEM_H */ From patchwork Wed May 6 09:49:41 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530913 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id CE1A417EF for ; Wed, 6 May 2020 09:50:53 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id A7B002073A for ; Wed, 6 May 2020 09:50:53 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="aCl6/6fj" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729252AbgEFJux (ORCPT ); Wed, 6 May 2020 05:50:53 -0400 Received: from us-smtp-1.mimecast.com ([207.211.31.81]:31807 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729236AbgEFJuw (ORCPT ); Wed, 6 May 2020 05:50:52 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758648; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=Neb3XNqN8GnA6E+Qn0tinD/A0QhWu5ZHKEpLUQAT+yU=; b=aCl6/6fjpLVwmpa3ExZaiu38o+J24dSS0yuvtkzAUMt1HAZYmD+ckDhrrO+xGLCZM01qlA UwyUcKJ5Ch0Il1qMW+pNTrlCuKXSQdmOcjD54+PVMoW5BTNQuoMsm7IoP9ybTAShaKMKlE 7L4N0pI6qOiL/p4FU/UBm2UeiqTdtJ4= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-75-v2VmSf4BNYeGMrlSAQM-dA-1; Wed, 06 May 2020 05:50:44 -0400 X-MC-Unique: v2VmSf4BNYeGMrlSAQM-dA-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 82A961800D4A; Wed, 6 May 2020 09:50:43 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 0361C5C1BD; Wed, 6 May 2020 09:50:40 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Eric Blake , Markus Armbruster , Igor Mammedov Subject: [PATCH v1 10/17] virtio-mem: Paravirtualized memory hot(un)plug Date: Wed, 6 May 2020 11:49:41 +0200 Message-Id: <20200506094948.76388-11-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org This is the very basic/initial version of virtio-mem. An introduction to virtio-mem can be found in the Linux kernel driver [1]. While it can be used in the current state for hotplug of a smaller amount of memory, it will heavily benefit from resizeable memory regions in the future. Each virtio-mem device manages a memory region (provided via a memory backend). After requested by the hypervisor ("requested-size"), the guest can try to plug/unplug blocks of memory within that region, in order to reach the requested size. Initially, and after a reboot, all memory is unplugged (except in special cases - reboot during postcopy). The guest may only try to plug/unplug blocks of memory within the usable region size. The usable region size is a little bigger than the requested size, to give the device driver some flexibility. The usable region size will only grow, except on reboots or when all memory is requested to get unplugged. The guest can never plug more memory than requested. Unplugged memory will get zapped/discarded, similar to in a balloon device. The block size is variable, however, it is always chosen in a way such that THP splits are avoided (e.g., 2MB). The state of each block (plugged/unplugged) is tracked in a bitmap. As virtio-mem devices (e.g., virtio-mem-pci) will be memory devices, we now expose "VirtioMEMDeviceInfo" via "query-memory-devices". -------------------------------------------------------------------------- There are two important follow-up items that are in the works: 1. Resizeable memory regions: Use resizeable allocations/RAM blocks to grow/shrink along with the usable region size. This avoids creating initially very big VMAs, RAM blocks, and KVM slots. 2. Protection of unplugged memory: Make sure the gust cannot actually make use of unplugged memory. Other follow-up items that are in the works: 1. Exclude unplugged memory during migration (via precopy notifier). 2. Handle remapping of memory. 3. Support for other architectures. -------------------------------------------------------------------------- Example usage (virtio-mem-pci is introduced in follow-up patches): Start QEMU with two virtio-mem devices (one per NUMA node): $ qemu-system-x86_64 -m 4G,maxmem=20G \ -smp sockets=2,cores=2 \ -numa node,nodeid=0,cpus=0-1 -numa node,nodeid=1,cpus=2-3 \ [...] -object memory-backend-ram,id=mem0,size=8G \ -device virtio-mem-pci,id=vm0,memdev=mem0,node=0,requested-size=0M \ -object memory-backend-ram,id=mem1,size=8G \ -device virtio-mem-pci,id=vm1,memdev=mem1,node=1,requested-size=1G Query the configuration: (qemu) info memory-devices Memory device [virtio-mem]: "vm0" memaddr: 0x140000000 node: 0 requested-size: 0 size: 0 max-size: 8589934592 block-size: 2097152 memdev: /objects/mem0 Memory device [virtio-mem]: "vm1" memaddr: 0x340000000 node: 1 requested-size: 1073741824 size: 1073741824 max-size: 8589934592 block-size: 2097152 memdev: /objects/mem1 Add some memory to node 0: (qemu) qom-set vm0 requested-size 500M Remove some memory from node 1: (qemu) qom-set vm1 requested-size 200M Query the configuration again: (qemu) info memory-devices Memory device [virtio-mem]: "vm0" memaddr: 0x140000000 node: 0 requested-size: 524288000 size: 524288000 max-size: 8589934592 block-size: 2097152 memdev: /objects/mem0 Memory device [virtio-mem]: "vm1" memaddr: 0x340000000 node: 1 requested-size: 209715200 size: 209715200 max-size: 8589934592 block-size: 2097152 memdev: /objects/mem1 [1] https://lkml.kernel.org/r/20200311171422.10484-1-david@redhat.com Cc: "Michael S. Tsirkin" Cc: Eric Blake Cc: Markus Armbruster Cc: "Dr. David Alan Gilbert" Cc: Igor Mammedov Signed-off-by: David Hildenbrand --- hw/virtio/Kconfig | 11 + hw/virtio/Makefile.objs | 1 + hw/virtio/virtio-mem.c | 762 +++++++++++++++++++++++++++++++++ include/hw/virtio/virtio-mem.h | 80 ++++ qapi/misc.json | 39 +- 5 files changed, 892 insertions(+), 1 deletion(-) create mode 100644 hw/virtio/virtio-mem.c create mode 100644 include/hw/virtio/virtio-mem.h diff --git a/hw/virtio/Kconfig b/hw/virtio/Kconfig index 83122424fa..0eda25c4e1 100644 --- a/hw/virtio/Kconfig +++ b/hw/virtio/Kconfig @@ -47,3 +47,14 @@ config VIRTIO_PMEM depends on VIRTIO depends on VIRTIO_PMEM_SUPPORTED select MEM_DEVICE + +config VIRTIO_MEM_SUPPORTED + bool + +config VIRTIO_MEM + bool + default y + depends on VIRTIO + depends on LINUX + depends on VIRTIO_MEM_SUPPORTED + select MEM_DEVICE diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 4e4d39a0a4..7df70e977e 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -18,6 +18,7 @@ common-obj-$(call land,$(CONFIG_VIRTIO_PMEM),$(CONFIG_VIRTIO_PCI)) += virtio-pme obj-$(call land,$(CONFIG_VHOST_USER_FS),$(CONFIG_VIRTIO_PCI)) += vhost-user-fs-pci.o obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o +obj-$(CONFIG_VIRTIO_MEM) += virtio-mem.o ifeq ($(CONFIG_VIRTIO_PCI),y) obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c new file mode 100644 index 0000000000..e25b2c74f2 --- /dev/null +++ b/hw/virtio/virtio-mem.c @@ -0,0 +1,762 @@ +/* + * Virtio MEM device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" +#include "qemu-common.h" +#include "qemu/iov.h" +#include "qemu/cutils.h" +#include "qemu/error-report.h" +#include "qemu/units.h" +#include "sysemu/numa.h" +#include "sysemu/sysemu.h" +#include "sysemu/reset.h" +#include "hw/virtio/virtio.h" +#include "hw/virtio/virtio-bus.h" +#include "hw/virtio/virtio-access.h" +#include "hw/virtio/virtio-mem.h" +#include "qapi/error.h" +#include "qapi/visitor.h" +#include "exec/ram_addr.h" +#include "migration/misc.h" +#include "migration/postcopy-ram.h" +#include "hw/boards.h" +#include "hw/qdev-properties.h" +#include "config-devices.h" + +/* + * Use QEMU_VMALLOC_ALIGN, so no THP will have to be split when unplugging + * memory (e.g., 2MB on x86_64). + */ +#define VIRTIO_MEM_MIN_BLOCK_SIZE QEMU_VMALLOC_ALIGN +/* + * Size the usable region bigger than the requested size if possible. Esp. + * Linux guests will only add (aligned) memory blocks in case they fully + * fit into the usable region, but plug+online only a subset of the pages. + * The memory block size corresponds mostly to the section size. + * + * This allows e.g., to add 20MB with a section size of 128MB on x86_64, and + * a section size of 1GB on arm64 (as long as the start address is properly + * aligned, similar to ordinary DIMMs). + * + * We can change this at any time and maybe even make it configurable if + * necessary (as the section size can change). But it's more likely that the + * section size will rather get smaller and not bigger over time. + */ +#if defined(__x86_64__) +#define VIRTIO_MEM_USABLE_EXTENT (2 * (128 * MiB)) +#else +#error VIRTIO_MEM_USABLE_EXTENT not defined +#endif + +static bool virtio_mem_discard_inhibited(void) +{ + PostcopyState ps = postcopy_state_get(); + + /* Postcopy cannot deal with concurrent discards (yet), so it's special. */ + return ps >= POSTCOPY_INCOMING_DISCARD && ps < POSTCOPY_INCOMING_END; +} + +static bool virtio_mem_test_bitmap(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plug) +{ + uint64_t bit = (start_gpa - vmem->addr) / vmem->block_size; + + g_assert(QEMU_IS_ALIGNED(start_gpa, vmem->block_size)); + g_assert(QEMU_IS_ALIGNED(size, vmem->block_size)); + g_assert(vmem->bitmap); + + while (size) { + g_assert((bit / BITS_PER_BYTE) <= vmem->bitmap_size); + + if (plug && !test_bit(bit, vmem->bitmap)) { + return false; + } else if (!plug && test_bit(bit, vmem->bitmap)) { + return false; + } + size -= vmem->block_size; + bit++; + } + return true; +} + +static void virtio_mem_set_bitmap(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plug) +{ + const uint64_t bit = (start_gpa - vmem->addr) / vmem->block_size; + const uint64_t nbits = size / vmem->block_size; + + g_assert(QEMU_IS_ALIGNED(start_gpa, vmem->block_size)); + g_assert(QEMU_IS_ALIGNED(size, vmem->block_size)); + g_assert(vmem->bitmap); + + if (plug) { + bitmap_set(vmem->bitmap, bit, nbits); + } else { + bitmap_clear(vmem->bitmap, bit, nbits); + } +} + +static void virtio_mem_send_response(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_resp *resp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(vmem); + VirtQueue *vq = vmem->vq; + + iov_from_buf(elem->in_sg, elem->in_num, 0, resp, sizeof(*resp)); + + virtqueue_push(vq, elem, sizeof(*resp)); + virtio_notify(vdev, vq); +} + +static void virtio_mem_send_response_simple(VirtIOMEM *vmem, + VirtQueueElement *elem, + uint16_t type) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(vmem); + struct virtio_mem_resp resp = {}; + + virtio_stw_p(vdev, &resp.type, type); + virtio_mem_send_response(vmem, elem, &resp); +} + +static void virtio_mem_bad_request(VirtIOMEM *vmem, const char *msg) +{ + virtio_error(VIRTIO_DEVICE(vmem), "virtio-mem protocol violation: %s", msg); +} + +static bool virtio_mem_valid_range(VirtIOMEM *vmem, uint64_t gpa, uint64_t size) +{ + if (!QEMU_IS_ALIGNED(gpa, vmem->block_size)) { + return false; + } + if (gpa + size < gpa || size == 0) { + return false; + } + if (gpa < vmem->addr || gpa >= vmem->addr + vmem->usable_region_size) { + return false; + } + if (gpa + size > vmem->addr + vmem->usable_region_size) { + return false; + } + return true; +} + +static int virtio_mem_set_block_state(VirtIOMEM *vmem, uint64_t start_gpa, + uint64_t size, bool plug) +{ + const uint64_t offset = start_gpa - vmem->addr; + int ret; + + if (!plug) { + if (virtio_mem_discard_inhibited()) { + return -EBUSY; + } + /* Note: Discarding should never fail at this point. */ + ret = ram_block_discard_range(vmem->memdev->mr.ram_block, offset, size); + if (ret) { + return -EBUSY; + } + } + virtio_mem_set_bitmap(vmem, start_gpa, size, plug); + return 0; +} + +static int virtio_mem_state_change_request(VirtIOMEM *vmem, uint64_t gpa, + uint16_t nb_blocks, bool plug) +{ + const uint64_t size = nb_blocks * vmem->block_size; + int ret; + + if (!virtio_mem_valid_range(vmem, gpa, size)) { + return VIRTIO_MEM_RESP_ERROR; + } + + if (plug && (vmem->size + size > vmem->requested_size)) { + return VIRTIO_MEM_RESP_NACK; + } + + /* test if really all blocks are in the opposite state */ + if (!virtio_mem_test_bitmap(vmem, gpa, size, !plug)) { + return VIRTIO_MEM_RESP_ERROR; + } + + ret = virtio_mem_set_block_state(vmem, gpa, size, plug); + if (ret) { + return VIRTIO_MEM_RESP_BUSY; + } + if (plug) { + vmem->size += size; + } else { + vmem->size -= size; + } + return VIRTIO_MEM_RESP_ACK; +} + +static void virtio_mem_plug_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint64_t gpa = le64_to_cpu(req->u.plug.addr); + const uint16_t nb_blocks = le16_to_cpu(req->u.plug.nb_blocks); + uint16_t type; + + type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, true); + virtio_mem_send_response_simple(vmem, elem, type); +} + +static void virtio_mem_unplug_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint64_t gpa = le64_to_cpu(req->u.unplug.addr); + const uint16_t nb_blocks = le16_to_cpu(req->u.unplug.nb_blocks); + uint16_t type; + + type = virtio_mem_state_change_request(vmem, gpa, nb_blocks, false); + virtio_mem_send_response_simple(vmem, elem, type); +} + +static void virtio_mem_resize_usable_region(VirtIOMEM *vmem, + uint64_t requested_size, + bool can_shrink) +{ + uint64_t newsize = MIN(memory_region_size(&vmem->memdev->mr), + requested_size + VIRTIO_MEM_USABLE_EXTENT); + + /* We must only grow while the guest is running. */ + if (newsize < vmem->usable_region_size && !can_shrink) { + return; + } + + vmem->usable_region_size = newsize; +} + +static int virtio_mem_unplug_all(VirtIOMEM *vmem) +{ + RAMBlock *rb = vmem->memdev->mr.ram_block; + int ret; + + if (virtio_mem_discard_inhibited()) { + return -EBUSY; + } + + ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); + if (ret) { + /* Note: Discarding should never fail at this point. */ + return -EBUSY; + } + bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size); + vmem->size = 0; + + virtio_mem_resize_usable_region(vmem, vmem->requested_size, true); + return 0; +} + +static void virtio_mem_unplug_all_request(VirtIOMEM *vmem, + VirtQueueElement *elem) +{ + + if (virtio_mem_unplug_all(vmem)) { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_BUSY); + } else { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_ACK); + } +} + +static void virtio_mem_state_request(VirtIOMEM *vmem, VirtQueueElement *elem, + struct virtio_mem_req *req) +{ + const uint64_t gpa = le64_to_cpu(req->u.state.addr); + const uint16_t nb_blocks = le16_to_cpu(req->u.state.nb_blocks); + const uint64_t size = nb_blocks * vmem->block_size; + VirtIODevice *vdev = VIRTIO_DEVICE(vmem); + struct virtio_mem_resp resp = {}; + + if (!virtio_mem_valid_range(vmem, gpa, size)) { + virtio_mem_send_response_simple(vmem, elem, VIRTIO_MEM_RESP_ERROR); + return; + } + + virtio_stw_p(vdev, &resp.type, VIRTIO_MEM_RESP_ACK); + if (virtio_mem_test_bitmap(vmem, gpa, size, true)) { + virtio_stw_p(vdev, &resp.u.state.state, VIRTIO_MEM_STATE_PLUGGED); + } else if (virtio_mem_test_bitmap(vmem, gpa, size, false)) { + virtio_stw_p(vdev, &resp.u.state.state, VIRTIO_MEM_STATE_UNPLUGGED); + } else { + virtio_stw_p(vdev, &resp.u.state.state, VIRTIO_MEM_STATE_MIXED); + } + virtio_mem_send_response(vmem, elem, &resp); +} + +static void virtio_mem_handle_request(VirtIODevice *vdev, VirtQueue *vq) +{ + const int len = sizeof(struct virtio_mem_req); + VirtIOMEM *vmem = VIRTIO_MEM(vdev); + VirtQueueElement *elem; + struct virtio_mem_req req; + uint64_t type; + + while (true) { + elem = virtqueue_pop(vq, sizeof(VirtQueueElement)); + if (!elem) { + return; + } + + if (iov_to_buf(elem->out_sg, elem->out_num, 0, &req, len) < len) { + virtio_mem_bad_request(vmem, "invalid request size"); + g_free(elem); + return; + } + + if (iov_size(elem->in_sg, elem->in_num) < + sizeof(struct virtio_mem_resp)) { + virtio_mem_bad_request(vmem, "not enough space for response"); + g_free(elem); + return; + } + + type = le16_to_cpu(req.type); + switch (type) { + case VIRTIO_MEM_REQ_PLUG: + virtio_mem_plug_request(vmem, elem, &req); + break; + case VIRTIO_MEM_REQ_UNPLUG: + virtio_mem_unplug_request(vmem, elem, &req); + break; + case VIRTIO_MEM_REQ_UNPLUG_ALL: + virtio_mem_unplug_all_request(vmem, elem); + break; + case VIRTIO_MEM_REQ_STATE: + virtio_mem_state_request(vmem, elem, &req); + break; + default: + virtio_mem_bad_request(vmem, "unknown request type"); + g_free(elem); + return; + } + + g_free(elem); + } +} + +static void virtio_mem_get_config(VirtIODevice *vdev, uint8_t *config_data) +{ + VirtIOMEM *vmem = VIRTIO_MEM(vdev); + struct virtio_mem_config *config = (void *) config_data; + + config->block_size = cpu_to_le32(vmem->block_size); + config->node_id = cpu_to_le16(vmem->node); + config->requested_size = cpu_to_le64(vmem->requested_size); + config->plugged_size = cpu_to_le64(vmem->size); + config->addr = cpu_to_le64(vmem->addr); + config->region_size = cpu_to_le64(memory_region_size(&vmem->memdev->mr)); + config->usable_region_size = cpu_to_le64(vmem->usable_region_size); +} + +static uint64_t virtio_mem_get_features(VirtIODevice *vdev, uint64_t features, + Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + + if (ms->numa_state) { +#if defined(CONFIG_ACPI) + virtio_add_feature(&features, VIRTIO_MEM_F_ACPI_PXM); +#endif + } + return features; +} + +static void virtio_mem_system_reset(void *opaque) +{ + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + + /* + * During usual resets, we will unplug all memory and shrink the usable + * region size. This is, however, not possible in all scenarios. Then, + * the guest has to deal with this manually (VIRTIO_MEM_REQ_UNPLUG_ALL). + */ + virtio_mem_unplug_all(vmem); +} + +static void virtio_mem_device_realize(DeviceState *dev, Error **errp) +{ + MachineState *ms = MACHINE(qdev_get_machine()); + int nb_numa_nodes = ms->numa_state ? ms->numa_state->num_nodes : 0; + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VirtIOMEM *vmem = VIRTIO_MEM(dev); + uint64_t page_size; + RAMBlock *rb; + int ret; + + if (!vmem->memdev) { + error_setg(errp, "'%s' property must be set", VIRTIO_MEM_MEMDEV_PROP); + return; + } else if (host_memory_backend_is_mapped(vmem->memdev)) { + char *path = object_get_canonical_path_component(OBJECT(vmem->memdev)); + + error_setg(errp, "can't use already busy memdev: %s", path); + g_free(path); + return; + } + + if ((nb_numa_nodes && vmem->node >= nb_numa_nodes) || + (!nb_numa_nodes && vmem->node)) { + error_setg(errp, "Property '%s' has value '%" PRIu32 + "', which exceeds the number of numa nodes: %d", + VIRTIO_MEM_NODE_PROP, vmem->node, + nb_numa_nodes ? nb_numa_nodes : 1); + return; + } + + if (enable_mlock) { + error_setg(errp, "not compatible with mlock yet"); + return; + } + + if (!memory_region_is_ram(&vmem->memdev->mr) || + memory_region_is_rom(&vmem->memdev->mr) || + !vmem->memdev->mr.ram_block) { + error_setg(errp, "unsupported memdev"); + return; + } + + rb = vmem->memdev->mr.ram_block; + page_size = qemu_ram_pagesize(rb); + + if (vmem->block_size < page_size) { + error_setg(errp, "'%s' has to be at least the page size (0x%" + PRIx64 ")", VIRTIO_MEM_BLOCK_SIZE_PROP, page_size); + return; + } else if (!QEMU_IS_ALIGNED(vmem->requested_size, vmem->block_size)) { + error_setg(errp, "'%s' has to be multiples of '%s' (0x%" PRIx32 + ")", VIRTIO_MEM_REQUESTED_SIZE_PROP, + VIRTIO_MEM_BLOCK_SIZE_PROP, vmem->block_size); + return; + } else if (!QEMU_IS_ALIGNED(memory_region_size(&vmem->memdev->mr), + vmem->block_size)) { + error_setg(errp, "'%s' backend size has to be multiples of '%s' (0x%" + PRIx32 ")", VIRTIO_MEM_MEMDEV_PROP, + VIRTIO_MEM_BLOCK_SIZE_PROP, vmem->block_size); + return; + } + + if (ram_block_discard_set_required(true)) { + error_setg(errp, "Discarding RAM is marked broken."); + return; + } + + ret = ram_block_discard_range(rb, 0, qemu_ram_get_used_length(rb)); + if (ret) { + /* Note: Discarding should never fail at this point. */ + error_setg_errno(errp, -ret, "Discarding RAM failed."); + ram_block_discard_set_required(false); + return; + } + + virtio_mem_resize_usable_region(vmem, vmem->requested_size, true); + + vmem->bitmap_size = memory_region_size(&vmem->memdev->mr) / + vmem->block_size; + vmem->bitmap = bitmap_new(vmem->bitmap_size); + + virtio_init(vdev, TYPE_VIRTIO_MEM, VIRTIO_ID_MEM, + sizeof(struct virtio_mem_config)); + vmem->vq = virtio_add_queue(vdev, 128, virtio_mem_handle_request); + + host_memory_backend_set_mapped(vmem->memdev, true); + vmstate_register_ram(&vmem->memdev->mr, DEVICE(vmem)); + qemu_register_reset(virtio_mem_system_reset, vmem); + return; +} + +static void virtio_mem_device_unrealize(DeviceState *dev, Error **errp) +{ + VirtIODevice *vdev = VIRTIO_DEVICE(dev); + VirtIOMEM *vmem = VIRTIO_MEM(dev); + + qemu_unregister_reset(virtio_mem_system_reset, vmem); + vmstate_unregister_ram(&vmem->memdev->mr, DEVICE(vmem)); + host_memory_backend_set_mapped(vmem->memdev, false); + virtio_del_queue(vdev, 0); + virtio_cleanup(vdev); + g_free(vmem->bitmap); + ramblock_discard_set_required(false); +} + +static int virtio_mem_pre_save(void *opaque) +{ + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + + vmem->migration_addr = vmem->addr; + vmem->migration_block_size = vmem->block_size; + + return 0; +} + +static int virtio_mem_restore_unplugged(VirtIOMEM *vmem) +{ + unsigned long bit; + uint64_t offset; + int ret; + + /* TODO: Better postcopy handling - defer to postcopy end. */ + if (virtio_mem_discard_inhibited()) { + return 0; + } + + bit = find_first_zero_bit(vmem->bitmap, vmem->bitmap_size); + while (bit < vmem->bitmap_size) { + offset = bit * vmem->block_size; + + if (offset + vmem->block_size >= + memory_region_size(&vmem->memdev->mr)) { + break; + } + /* Note: Discarding should never fail at this point. */ + ret = ram_block_discard_range(vmem->memdev->mr.ram_block, offset, + vmem->block_size); + if (ret) { + return -EINVAL; + } + bit = find_next_zero_bit(vmem->bitmap, vmem->bitmap_size, bit + 1); + } + return 0; +} + +static int virtio_mem_post_load(void *opaque, int version_id) +{ + VirtIOMEM *vmem = VIRTIO_MEM(opaque); + + if (vmem->migration_block_size != vmem->block_size) { + error_report("'%s' doesn't match", VIRTIO_MEM_BLOCK_SIZE_PROP); + return -EINVAL; + } + if (vmem->migration_addr != vmem->addr) { + error_report("'%s' doesn't match", VIRTIO_MEM_ADDR_PROP); + return -EINVAL; + } + return virtio_mem_restore_unplugged(vmem); +} + +static const VMStateDescription vmstate_virtio_mem_device = { + .name = "virtio-mem-device", + .minimum_version_id = 1, + .version_id = 1, + .pre_save = virtio_mem_pre_save, + .post_load = virtio_mem_post_load, + .fields = (VMStateField[]) { + VMSTATE_UINT64(usable_region_size, VirtIOMEM), + VMSTATE_UINT64(size, VirtIOMEM), + VMSTATE_UINT64(requested_size, VirtIOMEM), + VMSTATE_UINT64(migration_addr, VirtIOMEM), + VMSTATE_UINT32(migration_block_size, VirtIOMEM), + VMSTATE_BITMAP(bitmap, VirtIOMEM, 0, bitmap_size), + VMSTATE_END_OF_LIST() + }, +}; + +static const VMStateDescription vmstate_virtio_mem = { + .name = "virtio-mem", + .minimum_version_id = 1, + .version_id = 1, + .fields = (VMStateField[]) { + VMSTATE_VIRTIO_DEVICE, + VMSTATE_END_OF_LIST() + }, +}; + +static void virtio_mem_fill_device_info(const VirtIOMEM *vmem, + VirtioMEMDeviceInfo *vi) +{ + vi->memaddr = vmem->addr; + vi->node = vmem->node; + vi->requested_size = vmem->requested_size; + vi->size = vmem->size; + vi->max_size = memory_region_size(&vmem->memdev->mr); + vi->block_size = vmem->block_size; + vi->memdev = object_get_canonical_path(OBJECT(vmem->memdev)); +} + +static MemoryRegion *virtio_mem_get_memory_region(VirtIOMEM *vmem, Error **errp) +{ + if (!vmem->memdev) { + error_setg(errp, "'%s' property must be set", VIRTIO_MEM_MEMDEV_PROP); + return NULL; + } + + return &vmem->memdev->mr; +} + +static void virtio_mem_get_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_get_requested_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->requested_size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_set_requested_size(Object *obj, Visitor *v, + const char *name, void *opaque, + Error **errp) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + Error *err = NULL; + uint64_t value; + + visit_type_size(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + /* + * The block size and memory backend are not fixed until the device was + * realized. realize() will verify these properties then. + */ + if (DEVICE(obj)->realized) { + if (!QEMU_IS_ALIGNED(value, vmem->block_size)) { + error_setg(errp, "'%s' has to be multiples of '%s' (0x%" PRIx32 + ")", name, VIRTIO_MEM_BLOCK_SIZE_PROP, + vmem->block_size); + return; + } else if (value > memory_region_size(&vmem->memdev->mr)) { + error_setg(errp, "'%s' cannot exceed the memory backend size" + "(0x%" PRIx64 ")", name, + memory_region_size(&vmem->memdev->mr)); + return; + } + + if (value != vmem->requested_size) { + virtio_mem_resize_usable_region(vmem, value, false); + vmem->requested_size = value; + } + /* + * Trigger a config update so the guest gets notified. We trigger + * even if the size didn't change (especially helpful for debugging). + */ + virtio_notify_config(VIRTIO_DEVICE(vmem)); + } else { + vmem->requested_size = value; + } +} + +static void virtio_mem_get_block_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + const VirtIOMEM *vmem = VIRTIO_MEM(obj); + uint64_t value = vmem->block_size; + + visit_type_size(v, name, &value, errp); +} + +static void virtio_mem_set_block_size(Object *obj, Visitor *v, const char *name, + void *opaque, Error **errp) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + Error *err = NULL; + uint64_t value; + + if (DEVICE(obj)->realized) { + error_setg(errp, "'%s' cannot be changed", name); + return; + } + + visit_type_size(v, name, &value, &err); + if (err) { + error_propagate(errp, err); + return; + } + + if (value > UINT32_MAX) { + error_setg(errp, "'%s' has to be smaller than 0x%" PRIx32, name, + UINT32_MAX); + return; + } else if (value < VIRTIO_MEM_MIN_BLOCK_SIZE) { + error_setg(errp, "'%s' has to be at least 0x%" PRIx32, name, + VIRTIO_MEM_MIN_BLOCK_SIZE); + return; + } else if (!is_power_of_2(value)) { + error_setg(errp, "'%s' has to be a power of two", name); + return; + } + vmem->block_size = value; +} + +static void virtio_mem_instance_init(Object *obj) +{ + VirtIOMEM *vmem = VIRTIO_MEM(obj); + + vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE; + + object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size, + NULL, NULL, NULL, &error_abort); + object_property_add(obj, VIRTIO_MEM_REQUESTED_SIZE_PROP, "size", + virtio_mem_get_requested_size, + virtio_mem_set_requested_size, NULL, NULL, + &error_abort); + object_property_add(obj, VIRTIO_MEM_BLOCK_SIZE_PROP, "size", + virtio_mem_get_block_size, virtio_mem_set_block_size, + NULL, NULL, &error_abort); +} + +static Property virtio_mem_properties[] = { + DEFINE_PROP_UINT64(VIRTIO_MEM_ADDR_PROP, VirtIOMEM, addr, 0), + DEFINE_PROP_UINT32(VIRTIO_MEM_NODE_PROP, VirtIOMEM, node, 0), + DEFINE_PROP_LINK(VIRTIO_MEM_MEMDEV_PROP, VirtIOMEM, memdev, + TYPE_MEMORY_BACKEND, HostMemoryBackend *), + DEFINE_PROP_END_OF_LIST(), +}; + +static void virtio_mem_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioDeviceClass *vdc = VIRTIO_DEVICE_CLASS(klass); + VirtIOMEMClass *vmc = VIRTIO_MEM_CLASS(klass); + + device_class_set_props(dc, virtio_mem_properties); + dc->vmsd = &vmstate_virtio_mem; + + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + vdc->realize = virtio_mem_device_realize; + vdc->unrealize = virtio_mem_device_unrealize; + vdc->get_config = virtio_mem_get_config; + vdc->get_features = virtio_mem_get_features; + vdc->vmsd = &vmstate_virtio_mem_device; + + vmc->fill_device_info = virtio_mem_fill_device_info; + vmc->get_memory_region = virtio_mem_get_memory_region; +} + +static const TypeInfo virtio_mem_info = { + .name = TYPE_VIRTIO_MEM, + .parent = TYPE_VIRTIO_DEVICE, + .instance_size = sizeof(VirtIOMEM), + .instance_init = virtio_mem_instance_init, + .class_init = virtio_mem_class_init, + .class_size = sizeof(VirtIOMEMClass), +}; + +static void virtio_register_types(void) +{ + type_register_static(&virtio_mem_info); +} + +type_init(virtio_register_types) diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h new file mode 100644 index 0000000000..27158cb611 --- /dev/null +++ b/include/hw/virtio/virtio-mem.h @@ -0,0 +1,80 @@ +/* + * Virtio MEM device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#ifndef HW_VIRTIO_MEM_H +#define HW_VIRTIO_MEM_H + +#include "standard-headers/linux/virtio_mem.h" +#include "hw/virtio/virtio.h" +#include "qapi/qapi-types-misc.h" +#include "sysemu/hostmem.h" + +#define TYPE_VIRTIO_MEM "virtio-mem" + +#define VIRTIO_MEM(obj) \ + OBJECT_CHECK(VirtIOMEM, (obj), TYPE_VIRTIO_MEM) +#define VIRTIO_MEM_CLASS(oc) \ + OBJECT_CLASS_CHECK(VirtIOMEMClass, (oc), TYPE_VIRTIO_MEM) +#define VIRTIO_MEM_GET_CLASS(obj) \ + OBJECT_GET_CLASS(VirtIOMEMClass, (obj), TYPE_VIRTIO_MEM) + +#define VIRTIO_MEM_MEMDEV_PROP "memdev" +#define VIRTIO_MEM_NODE_PROP "node" +#define VIRTIO_MEM_SIZE_PROP "size" +#define VIRTIO_MEM_REQUESTED_SIZE_PROP "requested-size" +#define VIRTIO_MEM_BLOCK_SIZE_PROP "block-size" +#define VIRTIO_MEM_ADDR_PROP "memaddr" + +typedef struct VirtIOMEM { + VirtIODevice parent_obj; + + /* guest -> host request queue */ + VirtQueue *vq; + + /* bitmap used to track unplugged memory */ + int32_t bitmap_size; + unsigned long *bitmap; + + /* assigned memory backend and memory region */ + HostMemoryBackend *memdev; + + /* NUMA node */ + uint32_t node; + + /* assigned address of the region in guest physical memory */ + uint64_t addr; + uint64_t migration_addr; + + /* usable region size (<= region_size) */ + uint64_t usable_region_size; + + /* actual size (how much the guest plugged) */ + uint64_t size; + + /* requested size */ + uint64_t requested_size; + + /* block size and alignment */ + uint32_t block_size; + uint32_t migration_block_size; +} VirtIOMEM; + +typedef struct VirtIOMEMClass { + /* private */ + VirtIODevice parent; + + /* public */ + void (*fill_device_info)(const VirtIOMEM *vmen, VirtioMEMDeviceInfo *vi); + MemoryRegion *(*get_memory_region)(VirtIOMEM *vmem, Error **errp); +} VirtIOMEMClass; + +#endif diff --git a/qapi/misc.json b/qapi/misc.json index 99b90ac80b..feaeacec22 100644 --- a/qapi/misc.json +++ b/qapi/misc.json @@ -1354,19 +1354,56 @@ } } +## +# @VirtioMEMDeviceInfo: +# +# VirtioMEMDevice state information +# +# @id: device's ID +# +# @memaddr: physical address in memory, where device is mapped +# +# @requested-size: the user requested size of the device +# +# @size: the (current) size of memory that the device provides +# +# @max-size: the maximum size of memory that the device can provide +# +# @block-size: the block size of memory that the device provides +# +# @node: NUMA node number where device is assigned to +# +# @memdev: memory backend linked with the region +# +# Since: 5.1 +## +{ 'struct': 'VirtioMEMDeviceInfo', + 'data': { '*id': 'str', + 'memaddr': 'size', + 'requested-size': 'size', + 'size': 'size', + 'max-size': 'size', + 'block-size': 'size', + 'node': 'int', + 'memdev': 'str' + } +} + ## # @MemoryDeviceInfo: # # Union containing information about a memory device # # nvdimm is included since 2.12. virtio-pmem is included since 4.1. +# virtio-mem is included since 5.2. # # Since: 2.1 ## { 'union': 'MemoryDeviceInfo', 'data': { 'dimm': 'PCDIMMDeviceInfo', 'nvdimm': 'PCDIMMDeviceInfo', - 'virtio-pmem': 'VirtioPMEMDeviceInfo' + 'virtio-pmem': 'VirtioPMEMDeviceInfo', + 'virtio-mem': 'VirtioMEMDeviceInfo' } } From patchwork Wed May 6 09:49:42 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530911 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 478BA81 for ; Wed, 6 May 2020 09:50:53 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 27B6720714 for ; Wed, 6 May 2020 09:50:53 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="MMOKaLdd" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729238AbgEFJuw (ORCPT ); Wed, 6 May 2020 05:50:52 -0400 Received: from us-smtp-2.mimecast.com ([205.139.110.61]:38101 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729243AbgEFJuv (ORCPT ); Wed, 6 May 2020 05:50:51 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758649; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=MsLyeZhBmtaI3y14ev+wnqkHN5tBcDSVj+6Qghyl2/M=; b=MMOKaLddODQ0dfMsEPRwyCgslehd2d15+/iTB81DJuF/ZuxXF1htKm1qpV1DJHfCKO52Nr FvOZBVm7nv8IK2AJE8lFqF3iGQAymqUFU4zKZISvdem+WDuhYgEKH+cd189uIYMbHl4ld2 IR3YD3gsaWLMcs9ZVkoEikvFsUYgSw8= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-506-VsmSJsduPeeWnxO87wqI0Q-1; Wed, 06 May 2020 05:50:47 -0400 X-MC-Unique: VsmSJsduPeeWnxO87wqI0Q-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 0B424460; Wed, 6 May 2020 09:50:46 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id D154F5C1BD; Wed, 6 May 2020 09:50:43 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Marcel Apfelbaum , Igor Mammedov Subject: [PATCH v1 11/17] virtio-pci: Proxy for virtio-mem Date: Wed, 6 May 2020 11:49:42 +0200 Message-Id: <20200506094948.76388-12-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Let's add a proxy for virtio-mem, make it a memory device, and pass-through the properties. Cc: "Michael S. Tsirkin" Cc: Marcel Apfelbaum Cc: "Dr. David Alan Gilbert" Cc: Igor Mammedov Signed-off-by: David Hildenbrand Reviewed-by: Pankaj Gupta --- hw/virtio/Makefile.objs | 1 + hw/virtio/virtio-mem-pci.c | 131 +++++++++++++++++++++++++++++++++++++ hw/virtio/virtio-mem-pci.h | 33 ++++++++++ include/hw/pci/pci.h | 1 + 4 files changed, 166 insertions(+) create mode 100644 hw/virtio/virtio-mem-pci.c create mode 100644 hw/virtio/virtio-mem-pci.h diff --git a/hw/virtio/Makefile.objs b/hw/virtio/Makefile.objs index 7df70e977e..b9661f9c01 100644 --- a/hw/virtio/Makefile.objs +++ b/hw/virtio/Makefile.objs @@ -19,6 +19,7 @@ obj-$(call land,$(CONFIG_VHOST_USER_FS),$(CONFIG_VIRTIO_PCI)) += vhost-user-fs-p obj-$(CONFIG_VIRTIO_IOMMU) += virtio-iommu.o obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock.o obj-$(CONFIG_VIRTIO_MEM) += virtio-mem.o +common-obj-$(call land,$(CONFIG_VIRTIO_MEM),$(CONFIG_VIRTIO_PCI)) += virtio-mem-pci.o ifeq ($(CONFIG_VIRTIO_PCI),y) obj-$(CONFIG_VHOST_VSOCK) += vhost-vsock-pci.o diff --git a/hw/virtio/virtio-mem-pci.c b/hw/virtio/virtio-mem-pci.c new file mode 100644 index 0000000000..a47d21c81f --- /dev/null +++ b/hw/virtio/virtio-mem-pci.c @@ -0,0 +1,131 @@ +/* + * Virtio MEM PCI device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#include "qemu/osdep.h" + +#include "virtio-mem-pci.h" +#include "hw/mem/memory-device.h" +#include "qapi/error.h" + +static void virtio_mem_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) +{ + VirtIOMEMPCI *mem_pci = VIRTIO_MEM_PCI(vpci_dev); + DeviceState *vdev = DEVICE(&mem_pci->vdev); + + qdev_set_parent_bus(vdev, BUS(&vpci_dev->bus)); + object_property_set_bool(OBJECT(vdev), true, "realized", errp); +} + +static void virtio_mem_pci_set_addr(MemoryDeviceState *md, uint64_t addr, + Error **errp) +{ + object_property_set_uint(OBJECT(md), addr, VIRTIO_MEM_ADDR_PROP, errp); +} + +static uint64_t virtio_mem_pci_get_addr(const MemoryDeviceState *md) +{ + return object_property_get_uint(OBJECT(md), VIRTIO_MEM_ADDR_PROP, + &error_abort); +} + +static MemoryRegion *virtio_mem_pci_get_memory_region(MemoryDeviceState *md, + Error **errp) +{ + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vmc = VIRTIO_MEM_GET_CLASS(vmem); + + return vmc->get_memory_region(vmem, errp); +} + +static uint64_t virtio_mem_pci_get_plugged_size(const MemoryDeviceState *md, + Error **errp) +{ + return object_property_get_uint(OBJECT(md), VIRTIO_MEM_SIZE_PROP, + errp); +} + +static void virtio_mem_pci_fill_device_info(const MemoryDeviceState *md, + MemoryDeviceInfo *info) +{ + VirtioMEMDeviceInfo *vi = g_new0(VirtioMEMDeviceInfo, 1); + VirtIOMEMPCI *pci_mem = VIRTIO_MEM_PCI(md); + VirtIOMEM *vmem = VIRTIO_MEM(&pci_mem->vdev); + VirtIOMEMClass *vpc = VIRTIO_MEM_GET_CLASS(vmem); + DeviceState *dev = DEVICE(md); + + if (dev->id) { + vi->has_id = true; + vi->id = g_strdup(dev->id); + } + + /* let the real device handle everything else */ + vpc->fill_device_info(vmem, vi); + + info->u.virtio_mem.data = vi; + info->type = MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM; +} + +static void virtio_mem_pci_class_init(ObjectClass *klass, void *data) +{ + DeviceClass *dc = DEVICE_CLASS(klass); + VirtioPCIClass *k = VIRTIO_PCI_CLASS(klass); + PCIDeviceClass *pcidev_k = PCI_DEVICE_CLASS(klass); + MemoryDeviceClass *mdc = MEMORY_DEVICE_CLASS(klass); + + k->realize = virtio_mem_pci_realize; + set_bit(DEVICE_CATEGORY_MISC, dc->categories); + pcidev_k->vendor_id = PCI_VENDOR_ID_REDHAT_QUMRANET; + pcidev_k->device_id = PCI_DEVICE_ID_VIRTIO_MEM; + pcidev_k->revision = VIRTIO_PCI_ABI_VERSION; + pcidev_k->class_id = PCI_CLASS_OTHERS; + + mdc->get_addr = virtio_mem_pci_get_addr; + mdc->set_addr = virtio_mem_pci_set_addr; + mdc->get_plugged_size = virtio_mem_pci_get_plugged_size; + mdc->get_memory_region = virtio_mem_pci_get_memory_region; + mdc->fill_device_info = virtio_mem_pci_fill_device_info; +} + +static void virtio_mem_pci_instance_init(Object *obj) +{ + VirtIOMEMPCI *dev = VIRTIO_MEM_PCI(obj); + + virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), + TYPE_VIRTIO_MEM); + object_property_add_alias(obj, VIRTIO_MEM_BLOCK_SIZE_PROP, + OBJECT(&dev->vdev), + VIRTIO_MEM_BLOCK_SIZE_PROP, &error_abort); + object_property_add_alias(obj, VIRTIO_MEM_SIZE_PROP, OBJECT(&dev->vdev), + VIRTIO_MEM_SIZE_PROP, &error_abort); + object_property_add_alias(obj, VIRTIO_MEM_REQUESTED_SIZE_PROP, + OBJECT(&dev->vdev), + VIRTIO_MEM_REQUESTED_SIZE_PROP, &error_abort); +} + +static const VirtioPCIDeviceTypeInfo virtio_mem_pci_info = { + .base_name = TYPE_VIRTIO_MEM_PCI, + .generic_name = "virtio-mem-pci", + .instance_size = sizeof(VirtIOMEMPCI), + .instance_init = virtio_mem_pci_instance_init, + .class_init = virtio_mem_pci_class_init, + .interfaces = (InterfaceInfo[]) { + { TYPE_MEMORY_DEVICE }, + { } + }, +}; + +static void virtio_mem_pci_register_types(void) +{ + virtio_pci_types_register(&virtio_mem_pci_info); +} +type_init(virtio_mem_pci_register_types) diff --git a/hw/virtio/virtio-mem-pci.h b/hw/virtio/virtio-mem-pci.h new file mode 100644 index 0000000000..8820cd6628 --- /dev/null +++ b/hw/virtio/virtio-mem-pci.h @@ -0,0 +1,33 @@ +/* + * Virtio MEM PCI device + * + * Copyright (C) 2020 Red Hat, Inc. + * + * Authors: + * David Hildenbrand + * + * This work is licensed under the terms of the GNU GPL, version 2. + * See the COPYING file in the top-level directory. + */ + +#ifndef QEMU_VIRTIO_MEM_PCI_H +#define QEMU_VIRTIO_MEM_PCI_H + +#include "hw/virtio/virtio-pci.h" +#include "hw/virtio/virtio-mem.h" + +typedef struct VirtIOMEMPCI VirtIOMEMPCI; + +/* + * virtio-mem-pci: This extends VirtioPCIProxy. + */ +#define TYPE_VIRTIO_MEM_PCI "virtio-mem-pci-base" +#define VIRTIO_MEM_PCI(obj) \ + OBJECT_CHECK(VirtIOMEMPCI, (obj), TYPE_VIRTIO_MEM_PCI) + +struct VirtIOMEMPCI { + VirtIOPCIProxy parent_obj; + VirtIOMEM vdev; +}; + +#endif /* QEMU_VIRTIO_MEM_PCI_H */ diff --git a/include/hw/pci/pci.h b/include/hw/pci/pci.h index cfedf5a995..fec72d5a31 100644 --- a/include/hw/pci/pci.h +++ b/include/hw/pci/pci.h @@ -87,6 +87,7 @@ extern bool pci_available; #define PCI_DEVICE_ID_VIRTIO_VSOCK 0x1012 #define PCI_DEVICE_ID_VIRTIO_PMEM 0x1013 #define PCI_DEVICE_ID_VIRTIO_IOMMU 0x1014 +#define PCI_DEVICE_ID_VIRTIO_MEM 0x1015 #define PCI_VENDOR_ID_REDHAT 0x1b36 #define PCI_DEVICE_ID_REDHAT_BRIDGE 0x0001 From patchwork Wed May 6 09:49:43 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530915 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id E075F139F for ; Wed, 6 May 2020 09:50:58 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id BE0FC20747 for ; Wed, 6 May 2020 09:50:58 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="WTk60kHG" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729259AbgEFJu6 (ORCPT ); Wed, 6 May 2020 05:50:58 -0400 Received: from us-smtp-2.mimecast.com ([207.211.31.81]:45164 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729255AbgEFJu5 (ORCPT ); Wed, 6 May 2020 05:50:57 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758656; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=wNnV1o2sGn2mnkPQHzSb908sWqnev3kAZicrjpV0Uu4=; b=WTk60kHGKVpyG7EaWFIZbvet5rcGXT+bMSGxc/19lCACQGsaGxr+KPCeiwcstJY7putYv5 JyoP59ek7mxI9betM/bZUF1RivquVze//GveHUYH7DgCs/tQMpfgt8ykc+fi4pBxAaABdP 1R7vpWb+99MRi1aHyFefHKhbRKSBMmU= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-347-k6OBLxMJN6aj_s6dkKEgGQ-1; Wed, 06 May 2020 05:50:55 -0400 X-MC-Unique: k6OBLxMJN6aj_s6dkKEgGQ-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id D4280107ACCA; Wed, 6 May 2020 09:50:53 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 591515C1BD; Wed, 6 May 2020 09:50:46 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Peter Maydell , Markus Armbruster Subject: [PATCH v1 12/17] MAINTAINERS: Add myself as virtio-mem maintainer Date: Wed, 6 May 2020 11:49:43 +0200 Message-Id: <20200506094948.76388-13-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Let's make sure patches/bug reports find the right person. Cc: "Michael S. Tsirkin" Cc: Peter Maydell Cc: Markus Armbruster Signed-off-by: David Hildenbrand Reviewed-by: Dr. David Alan Gilbert --- MAINTAINERS | 8 ++++++++ 1 file changed, 8 insertions(+) diff --git a/MAINTAINERS b/MAINTAINERS index 1f84e3ae2c..09fff9e1bd 100644 --- a/MAINTAINERS +++ b/MAINTAINERS @@ -1734,6 +1734,14 @@ F: hw/virtio/virtio-crypto.c F: hw/virtio/virtio-crypto-pci.c F: include/hw/virtio/virtio-crypto.h +virtio-mem +M: David Hildenbrand +S: Supported +F: hw/virtio/virtio-mem.c +F: hw/virtio/virtio-mem-pci.h +F: hw/virtio/virtio-mem-pci.c +F: include/hw/virtio/virtio-mem.h + nvme M: Keith Busch L: qemu-block@nongnu.org From patchwork Wed May 6 09:49:44 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530917 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 13714139F for ; Wed, 6 May 2020 09:51:01 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id F08DE2073A for ; Wed, 6 May 2020 09:51:00 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="JFlDe55u" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729260AbgEFJvA (ORCPT ); Wed, 6 May 2020 05:51:00 -0400 Received: from us-smtp-delivery-1.mimecast.com ([207.211.31.120]:41203 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729261AbgEFJu7 (ORCPT ); Wed, 6 May 2020 05:50:59 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758658; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=ko1It9mCGjyIjOIhDtbfixtHC6gx4a3dweLY3ADWVjI=; b=JFlDe55u8NUsU6slyxGZH9Imsga/CFuaHvx/IoGeX/qVm4awkMXBu916U0BxtwUYnk6/NU ubQtM1x+xiuJn4cp6OtaNg19TWj6oz8Ae+1/z5fOetZVXvK+Jh31WBP4UYlsZ5BACO7Rx6 zeO7pu58g4zsVBlnOZgppVMzcjZp2xM= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-507-En2Gr8pMNr2BK5wn2n0xlA-1; Wed, 06 May 2020 05:50:57 -0400 X-MC-Unique: En2Gr8pMNr2BK5wn2n0xlA-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 0AAA280058A; Wed, 6 May 2020 09:50:56 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 2FB675C1BD; Wed, 6 May 2020 09:50:54 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand Subject: [PATCH v1 13/17] hmp: Handle virtio-mem when printing memory device info Date: Wed, 6 May 2020 11:49:44 +0200 Message-Id: <20200506094948.76388-14-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Print the memory device info just like for other memory devices. Cc: "Dr. David Alan Gilbert" Cc: "Michael S. Tsirkin" Signed-off-by: David Hildenbrand Reviewed-by: Pankaj Gupta --- monitor/hmp-cmds.c | 16 ++++++++++++++++ 1 file changed, 16 insertions(+) diff --git a/monitor/hmp-cmds.c b/monitor/hmp-cmds.c index 7f6e982dc8..4b3638a2a6 100644 --- a/monitor/hmp-cmds.c +++ b/monitor/hmp-cmds.c @@ -1805,6 +1805,7 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict) MemoryDeviceInfoList *info_list = qmp_query_memory_devices(&err); MemoryDeviceInfoList *info; VirtioPMEMDeviceInfo *vpi; + VirtioMEMDeviceInfo *vmi; MemoryDeviceInfo *value; PCDIMMDeviceInfo *di; @@ -1839,6 +1840,21 @@ void hmp_info_memory_devices(Monitor *mon, const QDict *qdict) monitor_printf(mon, " size: %" PRIu64 "\n", vpi->size); monitor_printf(mon, " memdev: %s\n", vpi->memdev); break; + case MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM: + vmi = value->u.virtio_mem.data; + monitor_printf(mon, "Memory device [%s]: \"%s\"\n", + MemoryDeviceInfoKind_str(value->type), + vmi->id ? vmi->id : ""); + monitor_printf(mon, " memaddr: 0x%" PRIx64 "\n", vmi->memaddr); + monitor_printf(mon, " node: %" PRId64 "\n", vmi->node); + monitor_printf(mon, " requested-size: %" PRIu64 "\n", + vmi->requested_size); + monitor_printf(mon, " size: %" PRIu64 "\n", vmi->size); + monitor_printf(mon, " max-size: %" PRIu64 "\n", vmi->max_size); + monitor_printf(mon, " block-size: %" PRIu64 "\n", + vmi->block_size); + monitor_printf(mon, " memdev: %s\n", vmi->memdev); + break; default: g_assert_not_reached(); } From patchwork Wed May 6 09:49:45 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530919 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 7433A81 for ; Wed, 6 May 2020 09:51:05 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 5CD6620714 for ; Wed, 6 May 2020 09:51:05 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="K32mckEC" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729265AbgEFJvE (ORCPT ); Wed, 6 May 2020 05:51:04 -0400 Received: from us-smtp-2.mimecast.com ([207.211.31.81]:39206 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729268AbgEFJvE (ORCPT ); Wed, 6 May 2020 05:51:04 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758663; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=gPYy5xjngtAqGsyw4OWH5Hdfo7Ahip1m9nldPmeLgtA=; b=K32mckECEvZa3R7CdL5EN+oq1noP9tShMvgV0MN9tbFSddmUkY/BMvmZxixFc7XTsNQRzK nyGHpH8HRFHwDhaPdWosBX8koUIg+TvNdbvVg3KqNXJdC+qSdJFyuG/pSftDUbFdQGvW6n g6QwaOGsKanwrACL1P2pJ3KybFV0+vI= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-49-4NIsTY3ePFGNQHX65Cxkwg-1; Wed, 06 May 2020 05:50:59 -0400 X-MC-Unique: 4NIsTY3ePFGNQHX65Cxkwg-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 5CD4B1800D4A; Wed, 6 May 2020 09:50:58 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 58E345C1BD; Wed, 6 May 2020 09:50:56 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Marcel Apfelbaum Subject: [PATCH v1 14/17] numa: Handle virtio-mem in NUMA stats Date: Wed, 6 May 2020 11:49:45 +0200 Message-Id: <20200506094948.76388-15-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Account the memory to the configured nid. Cc: Eduardo Habkost Cc: Marcel Apfelbaum Cc: "Michael S. Tsirkin" Signed-off-by: David Hildenbrand --- hw/core/numa.c | 6 ++++++ 1 file changed, 6 insertions(+) diff --git a/hw/core/numa.c b/hw/core/numa.c index 316bc50d75..06960918e7 100644 --- a/hw/core/numa.c +++ b/hw/core/numa.c @@ -812,6 +812,7 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[]) MemoryDeviceInfoList *info; PCDIMMDeviceInfo *pcdimm_info; VirtioPMEMDeviceInfo *vpi; + VirtioMEMDeviceInfo *vmi; for (info = info_list; info; info = info->next) { MemoryDeviceInfo *value = info->value; @@ -832,6 +833,11 @@ static void numa_stat_memory_devices(NumaNodeMem node_mem[]) node_mem[0].node_mem += vpi->size; node_mem[0].node_plugged_mem += vpi->size; break; + case MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM: + vmi = value->u.virtio_mem.data; + node_mem[vmi->node].node_mem += vmi->size; + node_mem[vmi->node].node_plugged_mem += vmi->size; + break; default: g_assert_not_reached(); } From patchwork Wed May 6 09:49:46 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530921 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 0FEA0139F for ; Wed, 6 May 2020 09:51:07 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id E2FA920714 for ; Wed, 6 May 2020 09:51:06 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="KWpERWt3" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729218AbgEFJvG (ORCPT ); Wed, 6 May 2020 05:51:06 -0400 Received: from us-smtp-delivery-1.mimecast.com ([207.211.31.120]:23478 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729267AbgEFJvF (ORCPT ); Wed, 6 May 2020 05:51:05 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758663; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=W2SInkhAIawUVaThIi/q7IY8VTE4Y+kHdMQ9prL2k5E=; b=KWpERWt3t26oX1+f9ldPBcVIpZnv0ZvMUcDIWDcR5NjeX+DKMRkWWa0V73vlSLfSuiNpm7 srFPdJfCQ9GSjaM3oIC+kQBDvMqHjbJEwoQNkva2kKbWkItpA6r4fOznfl8LIfjfHlypLd 7f+p3OhautdJqjF+kGDhR1KYLWDwWqQ= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-263-Ah1xG7R5OV-pXh4BYC61wg-1; Wed, 06 May 2020 05:51:02 -0400 X-MC-Unique: Ah1xG7R5OV-pXh4BYC61wg-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 13A6D835B41; Wed, 6 May 2020 09:51:01 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id AD9265C1BD; Wed, 6 May 2020 09:50:58 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Marcel Apfelbaum , Eric Blake , Markus Armbruster Subject: [PATCH v1 15/17] pc: Support for virtio-mem-pci Date: Wed, 6 May 2020 11:49:46 +0200 Message-Id: <20200506094948.76388-16-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Let's wire it up similar to virtio-pmem. Also disallow unplug, so it's harder for users to shoot themselves into the foot. Cc: "Michael S. Tsirkin" Cc: Marcel Apfelbaum Cc: Paolo Bonzini Cc: Richard Henderson Cc: Eduardo Habkost Cc: Eric Blake Cc: Markus Armbruster Signed-off-by: David Hildenbrand Reviewed-by: Pankaj Gupta --- hw/i386/Kconfig | 1 + hw/i386/pc.c | 49 ++++++++++++++++++++++++++++--------------------- 2 files changed, 29 insertions(+), 21 deletions(-) diff --git a/hw/i386/Kconfig b/hw/i386/Kconfig index c93f32f657..03e347b207 100644 --- a/hw/i386/Kconfig +++ b/hw/i386/Kconfig @@ -35,6 +35,7 @@ config PC select ACPI_PCI select ACPI_VMGENID select VIRTIO_PMEM_SUPPORTED + select VIRTIO_MEM_SUPPORTED config PC_PCI bool diff --git a/hw/i386/pc.c b/hw/i386/pc.c index f6b8431c8b..588804f895 100644 --- a/hw/i386/pc.c +++ b/hw/i386/pc.c @@ -86,6 +86,7 @@ #include "hw/net/ne2000-isa.h" #include "standard-headers/asm-x86/bootparam.h" #include "hw/virtio/virtio-pmem-pci.h" +#include "hw/virtio/virtio-mem-pci.h" #include "hw/mem/memory-device.h" #include "sysemu/replay.h" #include "qapi/qmp/qerror.h" @@ -1654,8 +1655,8 @@ static void pc_cpu_pre_plug(HotplugHandler *hotplug_dev, numa_cpu_pre_plug(cpu_slot, dev, errp); } -static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_pre_plug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { HotplugHandler *hotplug_dev2 = qdev_get_bus_hotplug_handler(dev); Error *local_err = NULL; @@ -1666,7 +1667,8 @@ static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev, * order. This should never be the case on x86, however better add * a safety net. */ - error_setg(errp, "virtio-pmem-pci not supported on this bus."); + error_setg(errp, + "virtio based memory devices not supported on this bus."); return; } /* @@ -1681,8 +1683,8 @@ static void pc_virtio_pmem_pci_pre_plug(HotplugHandler *hotplug_dev, error_propagate(errp, local_err); } -static void pc_virtio_pmem_pci_plug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_plug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { HotplugHandler *hotplug_dev2 = qdev_get_bus_hotplug_handler(dev); Error *local_err = NULL; @@ -1700,17 +1702,17 @@ static void pc_virtio_pmem_pci_plug(HotplugHandler *hotplug_dev, error_propagate(errp, local_err); } -static void pc_virtio_pmem_pci_unplug_request(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_unplug_request(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { - /* We don't support virtio pmem hot unplug */ - error_setg(errp, "virtio pmem device unplug not supported."); + /* We don't support hot unplug of virtio based memory devices */ + error_setg(errp, "virtio based memory devices cannot be unplugged."); } -static void pc_virtio_pmem_pci_unplug(HotplugHandler *hotplug_dev, - DeviceState *dev, Error **errp) +static void pc_virtio_md_pci_unplug(HotplugHandler *hotplug_dev, + DeviceState *dev, Error **errp) { - /* We don't support virtio pmem hot unplug */ + /* We don't support hot unplug of virtio based memory devices */ } static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, @@ -1720,8 +1722,9 @@ static void pc_machine_device_pre_plug_cb(HotplugHandler *hotplug_dev, pc_memory_pre_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_pre_plug(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_pre_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_pre_plug(hotplug_dev, dev, errp); } } @@ -1732,8 +1735,9 @@ static void pc_machine_device_plug_cb(HotplugHandler *hotplug_dev, pc_memory_plug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_plug(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_plug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_plug(hotplug_dev, dev, errp); } } @@ -1744,8 +1748,9 @@ static void pc_machine_device_unplug_request_cb(HotplugHandler *hotplug_dev, pc_memory_unplug_request(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_unplug_request_cb(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_unplug_request(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_unplug_request(hotplug_dev, dev, errp); } else { error_setg(errp, "acpi: device unplug request for not supported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -1759,8 +1764,9 @@ static void pc_machine_device_unplug_cb(HotplugHandler *hotplug_dev, pc_memory_unplug(hotplug_dev, dev, errp); } else if (object_dynamic_cast(OBJECT(dev), TYPE_CPU)) { pc_cpu_unplug_cb(hotplug_dev, dev, errp); - } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { - pc_virtio_pmem_pci_unplug(hotplug_dev, dev, errp); + } else if (object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { + pc_virtio_md_pci_unplug(hotplug_dev, dev, errp); } else { error_setg(errp, "acpi: device unplug for not supported device" " type: %s", object_get_typename(OBJECT(dev))); @@ -1772,7 +1778,8 @@ static HotplugHandler *pc_get_hotplug_handler(MachineState *machine, { if (object_dynamic_cast(OBJECT(dev), TYPE_PC_DIMM) || object_dynamic_cast(OBJECT(dev), TYPE_CPU) || - object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI)) { + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_PMEM_PCI) || + object_dynamic_cast(OBJECT(dev), TYPE_VIRTIO_MEM_PCI)) { return HOTPLUG_HANDLER(machine); } From patchwork Wed May 6 09:49:47 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530923 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 9242B81 for ; Wed, 6 May 2020 09:51:11 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id 755812073A for ; Wed, 6 May 2020 09:51:11 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="UpIXEMwG" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729270AbgEFJvK (ORCPT ); Wed, 6 May 2020 05:51:10 -0400 Received: from us-smtp-delivery-1.mimecast.com ([205.139.110.120]:56427 "EHLO us-smtp-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729279AbgEFJvJ (ORCPT ); Wed, 6 May 2020 05:51:09 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758668; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=wV4EATbXKx0yfoicp1MyNawAoP7R4yGLGPwFlFlYLgg=; b=UpIXEMwGjvtYyS2mQvr/cCoCimBuzqgOdsHkDhwiRxlBDY2x7y3Xo1Xse2afT1oQLFYSGf gS8/Io5naoPhMFFt4KmT43gwS8cZkLcBbUVtCtcU13v22VeBKyryMfma3ICrDRXe5ylV9J KRW7ihdWpp2fEmkLTjerDjWisb0JUE8= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-150-9weV7qJ5NwavGmfRKWAGNA-1; Wed, 06 May 2020 05:51:04 -0400 X-MC-Unique: 9weV7qJ5NwavGmfRKWAGNA-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 66226835B43; Wed, 6 May 2020 09:51:03 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id 5F6285C1BD; Wed, 6 May 2020 09:51:01 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Igor Mammedov Subject: [PATCH v1 16/17] virtio-mem: Allow notifiers for size changes Date: Wed, 6 May 2020 11:49:47 +0200 Message-Id: <20200506094948.76388-17-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org We want to send qapi events in case the size of a virtio-mem device changes. This allows upper layers to always know how much memory is actually currently consumed via a virtio-mem device. Unfortuantely, we have to report the id of our proxy device. Let's provide an easy way for our proxy device to register, so it can send the qapi events. Piggy-backing on the notifier infrastructure (although we'll only ever have one notifier registered) seems to be an easy way. Cc: "Michael S. Tsirkin" Cc: "Dr. David Alan Gilbert" Cc: Igor Mammedov Signed-off-by: David Hildenbrand Reviewed-by: Dr. David Alan Gilbert --- hw/virtio/virtio-mem.c | 21 ++++++++++++++++++++- include/hw/virtio/virtio-mem.h | 5 +++++ 2 files changed, 25 insertions(+), 1 deletion(-) diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index e25b2c74f2..88a99a0d90 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -198,6 +198,7 @@ static int virtio_mem_state_change_request(VirtIOMEM *vmem, uint64_t gpa, } else { vmem->size -= size; } + notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); return VIRTIO_MEM_RESP_ACK; } @@ -253,7 +254,10 @@ static int virtio_mem_unplug_all(VirtIOMEM *vmem) return -EBUSY; } bitmap_clear(vmem->bitmap, 0, vmem->bitmap_size); - vmem->size = 0; + if (vmem->size != 0) { + vmem->size = 0; + notifier_list_notify(&vmem->size_change_notifiers, &vmem->size); + } virtio_mem_resize_usable_region(vmem, vmem->requested_size, true); return 0; @@ -594,6 +598,18 @@ static MemoryRegion *virtio_mem_get_memory_region(VirtIOMEM *vmem, Error **errp) return &vmem->memdev->mr; } +static void virtio_mem_add_size_change_notifier(VirtIOMEM *vmem, + Notifier *notifier) +{ + notifier_list_add(&vmem->size_change_notifiers, notifier); +} + +static void virtio_mem_remove_size_change_notifier(VirtIOMEM *vmem, + Notifier *notifier) +{ + notifier_remove(notifier); +} + static void virtio_mem_get_size(Object *obj, Visitor *v, const char *name, void *opaque, Error **errp) { @@ -705,6 +721,7 @@ static void virtio_mem_instance_init(Object *obj) VirtIOMEM *vmem = VIRTIO_MEM(obj); vmem->block_size = VIRTIO_MEM_MIN_BLOCK_SIZE; + notifier_list_init(&vmem->size_change_notifiers); object_property_add(obj, VIRTIO_MEM_SIZE_PROP, "size", virtio_mem_get_size, NULL, NULL, NULL, &error_abort); @@ -743,6 +760,8 @@ static void virtio_mem_class_init(ObjectClass *klass, void *data) vmc->fill_device_info = virtio_mem_fill_device_info; vmc->get_memory_region = virtio_mem_get_memory_region; + vmc->add_size_change_notifier = virtio_mem_add_size_change_notifier; + vmc->remove_size_change_notifier = virtio_mem_remove_size_change_notifier; } static const TypeInfo virtio_mem_info = { diff --git a/include/hw/virtio/virtio-mem.h b/include/hw/virtio/virtio-mem.h index 27158cb611..5820b5c23e 100644 --- a/include/hw/virtio/virtio-mem.h +++ b/include/hw/virtio/virtio-mem.h @@ -66,6 +66,9 @@ typedef struct VirtIOMEM { /* block size and alignment */ uint32_t block_size; uint32_t migration_block_size; + + /* notifiers to notify when "size" changes */ + NotifierList size_change_notifiers; } VirtIOMEM; typedef struct VirtIOMEMClass { @@ -75,6 +78,8 @@ typedef struct VirtIOMEMClass { /* public */ void (*fill_device_info)(const VirtIOMEM *vmen, VirtioMEMDeviceInfo *vi); MemoryRegion *(*get_memory_region)(VirtIOMEM *vmem, Error **errp); + void (*add_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier); + void (*remove_size_change_notifier)(VirtIOMEM *vmem, Notifier *notifier); } VirtIOMEMClass; #endif From patchwork Wed May 6 09:49:48 2020 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: David Hildenbrand X-Patchwork-Id: 11530925 Return-Path: Received: from mail.kernel.org (pdx-korg-mail-1.web.codeaurora.org [172.30.200.123]) by pdx-korg-patchwork-2.web.codeaurora.org (Postfix) with ESMTP id 106EB81 for ; Wed, 6 May 2020 09:51:13 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by mail.kernel.org (Postfix) with ESMTP id ED89E20747 for ; Wed, 6 May 2020 09:51:12 +0000 (UTC) Authentication-Results: mail.kernel.org; dkim=pass (1024-bit key) header.d=redhat.com header.i=@redhat.com header.b="OhL/LYtP" Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1729276AbgEFJvL (ORCPT ); Wed, 6 May 2020 05:51:11 -0400 Received: from us-smtp-2.mimecast.com ([207.211.31.81]:60104 "EHLO us-smtp-delivery-1.mimecast.com" rhost-flags-OK-OK-OK-FAIL) by vger.kernel.org with ESMTP id S1729280AbgEFJvK (ORCPT ); Wed, 6 May 2020 05:51:10 -0400 DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=redhat.com; s=mimecast20190719; t=1588758668; h=from:from:reply-to:subject:subject:date:date:message-id:message-id: to:to:cc:cc:mime-version:mime-version: content-transfer-encoding:content-transfer-encoding: in-reply-to:in-reply-to:references:references; bh=rWys4epAU2XbucOUD2NVIBpXUWNVgzGVlwwLM5nrzXo=; b=OhL/LYtP/L2en4Zo2fYK5EMRL5yknDpkBBaauKFn5ptyo1ga/DoeLwNvSc5ODY2jkMxunc qdCETX5zSU6F/tmKeWTzMTQe3Jd7WRcvPXoU/kax7ktw7KAS4ayCgsNRiu5wqJIRw9PazH 2HYHInwrQMzonZqQApRcWvQDDiVoFmU= Received: from mimecast-mx01.redhat.com (mimecast-mx01.redhat.com [209.132.183.4]) (Using TLS) by relay.mimecast.com with ESMTP id us-mta-25-Xl0oQs4VM6OnDDsJytsSUg-1; Wed, 06 May 2020 05:51:07 -0400 X-MC-Unique: Xl0oQs4VM6OnDDsJytsSUg-1 Received: from smtp.corp.redhat.com (int-mx06.intmail.prod.int.phx2.redhat.com [10.5.11.16]) (using TLSv1.2 with cipher AECDH-AES256-SHA (256/256 bits)) (No client certificate requested) by mimecast-mx01.redhat.com (Postfix) with ESMTPS id 148DC80058A; Wed, 6 May 2020 09:51:06 +0000 (UTC) Received: from t480s.redhat.com (ovpn-113-17.ams2.redhat.com [10.36.113.17]) by smtp.corp.redhat.com (Postfix) with ESMTP id B4A7D5C1BD; Wed, 6 May 2020 09:51:03 +0000 (UTC) From: David Hildenbrand To: qemu-devel@nongnu.org Cc: kvm@vger.kernel.org, qemu-s390x@nongnu.org, Richard Henderson , Paolo Bonzini , "Dr . David Alan Gilbert" , Eduardo Habkost , "Michael S . Tsirkin" , David Hildenbrand , Markus Armbruster , Eric Blake , Igor Mammedov Subject: [PATCH v1 17/17] virtio-pci: Send qapi events when the virtio-mem size changes Date: Wed, 6 May 2020 11:49:48 +0200 Message-Id: <20200506094948.76388-18-david@redhat.com> In-Reply-To: <20200506094948.76388-1-david@redhat.com> References: <20200506094948.76388-1-david@redhat.com> MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.79 on 10.5.11.16 Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org Let's register the notifier and trigger the qapi event with the right device id. MEMORY_DEVICE_SIZE_CHANGE is similar to BALLOON_CHANGE, however on a memory device level. Don't unregister the notifier (we neither have finalize() nor unrealize() for VirtIOPCIProxy, so it's not that simple to do it) - both devices are expected to vanish at the same time. Cc: "Michael S. Tsirkin" Cc: Markus Armbruster Cc: "Dr. David Alan Gilbert" Cc: Eric Blake Cc: Igor Mammedov Signed-off-by: David Hildenbrand --- hw/virtio/virtio-mem-pci.c | 28 ++++++++++++++++++++++++++++ hw/virtio/virtio-mem-pci.h | 1 + hw/virtio/virtio-mem.c | 2 +- monitor/monitor.c | 1 + qapi/misc.json | 25 +++++++++++++++++++++++++ 5 files changed, 56 insertions(+), 1 deletion(-) diff --git a/hw/virtio/virtio-mem-pci.c b/hw/virtio/virtio-mem-pci.c index a47d21c81f..780d7b4af7 100644 --- a/hw/virtio/virtio-mem-pci.c +++ b/hw/virtio/virtio-mem-pci.c @@ -15,6 +15,7 @@ #include "virtio-mem-pci.h" #include "hw/mem/memory-device.h" #include "qapi/error.h" +#include "qapi/qapi-events-misc.h" static void virtio_mem_pci_realize(VirtIOPCIProxy *vpci_dev, Error **errp) { @@ -75,6 +76,21 @@ static void virtio_mem_pci_fill_device_info(const MemoryDeviceState *md, info->type = MEMORY_DEVICE_INFO_KIND_VIRTIO_MEM; } +static void virtio_mem_pci_size_change_notify(Notifier *notifier, void *data) +{ + VirtIOMEMPCI *pci_mem = container_of(notifier, VirtIOMEMPCI, + size_change_notifier); + DeviceState *dev = DEVICE(pci_mem); + const uint64_t * const size_p = data; + const char *id = NULL; + + if (dev->id) { + id = g_strdup(dev->id); + } + + qapi_event_send_memory_device_size_change(!!id, id, *size_p); +} + static void virtio_mem_pci_class_init(ObjectClass *klass, void *data) { DeviceClass *dc = DEVICE_CLASS(klass); @@ -99,9 +115,21 @@ static void virtio_mem_pci_class_init(ObjectClass *klass, void *data) static void virtio_mem_pci_instance_init(Object *obj) { VirtIOMEMPCI *dev = VIRTIO_MEM_PCI(obj); + VirtIOMEMClass *vmc; + VirtIOMEM *vmem; virtio_instance_init_common(obj, &dev->vdev, sizeof(dev->vdev), TYPE_VIRTIO_MEM); + + dev->size_change_notifier.notify = virtio_mem_pci_size_change_notify; + vmem = VIRTIO_MEM(&dev->vdev); + vmc = VIRTIO_MEM_GET_CLASS(vmem); + /* + * We never remove the notifier again, as we expect both devices to + * disappear at the same time. + */ + vmc->add_size_change_notifier(vmem, &dev->size_change_notifier); + object_property_add_alias(obj, VIRTIO_MEM_BLOCK_SIZE_PROP, OBJECT(&dev->vdev), VIRTIO_MEM_BLOCK_SIZE_PROP, &error_abort); diff --git a/hw/virtio/virtio-mem-pci.h b/hw/virtio/virtio-mem-pci.h index 8820cd6628..b51a28b275 100644 --- a/hw/virtio/virtio-mem-pci.h +++ b/hw/virtio/virtio-mem-pci.h @@ -28,6 +28,7 @@ typedef struct VirtIOMEMPCI VirtIOMEMPCI; struct VirtIOMEMPCI { VirtIOPCIProxy parent_obj; VirtIOMEM vdev; + Notifier size_change_notifier; }; #endif /* QEMU_VIRTIO_MEM_PCI_H */ diff --git a/hw/virtio/virtio-mem.c b/hw/virtio/virtio-mem.c index 88a99a0d90..eb5cf66855 100644 --- a/hw/virtio/virtio-mem.c +++ b/hw/virtio/virtio-mem.c @@ -491,7 +491,7 @@ static void virtio_mem_device_unrealize(DeviceState *dev, Error **errp) virtio_del_queue(vdev, 0); virtio_cleanup(vdev); g_free(vmem->bitmap); - ramblock_discard_set_required(false); + ram_block_discard_set_required(false); } static int virtio_mem_pre_save(void *opaque) diff --git a/monitor/monitor.c b/monitor/monitor.c index 125494410a..19dcb8fbe3 100644 --- a/monitor/monitor.c +++ b/monitor/monitor.c @@ -235,6 +235,7 @@ static MonitorQAPIEventConf monitor_qapi_event_conf[QAPI_EVENT__MAX] = { [QAPI_EVENT_QUORUM_REPORT_BAD] = { 1000 * SCALE_MS }, [QAPI_EVENT_QUORUM_FAILURE] = { 1000 * SCALE_MS }, [QAPI_EVENT_VSERPORT_CHANGE] = { 1000 * SCALE_MS }, + [QAPI_EVENT_MEMORY_DEVICE_SIZE_CHANGE] = { 1000 * SCALE_MS }, }; /* diff --git a/qapi/misc.json b/qapi/misc.json index feaeacec22..58b073562b 100644 --- a/qapi/misc.json +++ b/qapi/misc.json @@ -1432,6 +1432,31 @@ ## { 'command': 'query-memory-devices', 'returns': ['MemoryDeviceInfo'] } +## +# @MEMORY_DEVICE_SIZE_CHANGE: +# +# Emitted when the size of a memory device changes. Only emitted for memory +# devices that can actually change the size (e.g., virtio-mem due to guest +# action). +# +# @id: device's ID +# @size: the new size of memory that the device provides +# +# Note: this event is rate-limited. +# +# Since: 5.1 +# +# Example: +# +# <- { "event": "MEMORY_DEVICE_SIZE_CHANGE", +# "data": { "id": "vm0", "size": 1073741824}, +# "timestamp": { "seconds": 1588168529, "microseconds": 201316 } } +# +## +{ 'event': 'MEMORY_DEVICE_SIZE_CHANGE', + 'data': { '*id': 'str', 'size': 'size' } } + + ## # @MEM_UNPLUG_ERROR: #