From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx0b-001b2d01.pphosted.com (mx0b-001b2d01.pphosted.com [148.163.158.5]) (using TLSv1.2 with cipher ECDHE-RSA-AES256-GCM-SHA384 (256/256 bits)) (No client certificate requested) by smtp.subspace.kernel.org (Postfix) with ESMTPS id CF087375F80; Mon, 31 Aug 2026 14:48:32 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=148.163.158.5 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788187716; cv=none; b=pEcxK0Gu2kTPRj/yhOUCZA1fLq79gpLZCV92DuknfgmFM3UsD1r0kiMJzFgV1X4u3cJH40oBSbwQ/QR/xX9q18jkhdzY2wAfw6Xf2Uu5H8K0Ghzs75v67i2ZJURDr7ZhQeHaTLSE42gwBHnd3ra8nAxFLy57yhZZegKvGAHQVbY= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1788187716; c=relaxed/simple; bh=26gziGi2HwmdVjE4u72mW6p0XNm/qrTyjMenzyhGxDk=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=P8H+x31GWCfHB6TDcmh5d/489wGAXHKhwYmWQDoQGX4q8rM8IzUbpPNgjB0iOucKZYqUbVBau/0ZEJORehufzLgkrSoyKXb6hUcjDcSGDSMdjqhcWrboR6rO6Puh3XRyOm44j3+aBAqh0xSfqsEYPCLrvAqk8YSKl05gl8kqME8= ARC-Authentication-Results:i=1; smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.ibm.com; spf=pass smtp.mailfrom=linux.ibm.com; dkim=pass (2048-bit key) header.d=ibm.com header.i=@ibm.com header.b=qeqsiQm2; arc=none smtp.client-ip=148.163.158.5 Authentication-Results: smtp.subspace.kernel.org; dmarc=pass (p=none dis=none) header.from=linux.ibm.com Authentication-Results: smtp.subspace.kernel.org; spf=pass smtp.mailfrom=linux.ibm.com Authentication-Results: smtp.subspace.kernel.org; dkim=pass (2048-bit key) header.d=ibm.com header.i=@ibm.com header.b="qeqsiQm2" Received: from pps.filterd (m0353725.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id 67VEZBOF1398288; Mon, 31 Aug 2026 14:48:09 GMT DKIM-Signature: v=1; a=rsa-sha256; c=relaxed/relaxed; d=ibm.com; h=cc :content-transfer-encoding:content-type:date:from:in-reply-to :message-id:mime-version:references:subject:to; s=pp1; bh=7kaI+/ UPeDpXa5Qci0g2WEyi5wxbt+xukphIht2Cyqk=; b=qeqsiQm2MnrroSczHORote /gs0e9Kyc29tvSatf3pJeD5p+VhwUf+sM32z8+BEnQAPtMVpcEA6hVM7uML00eCo i8oTMXB52LY9GmC+yOpgPeCds4gQPKHoOVQ01bsG7nq5iJLkrXhAbSW65osLkV5H 8Ujw38wxIkjEyeqtT5f7tpiQOajNLPaWxPyOX19Xj7GBim7HPoqemsIsxGoIwsN5 ClwWa5GPwTwc7k44UfhWgqPlMGxllsqxsk/uxk7ZpoFtYuLarKjrVaX8OlopSt7p P9K3OWpMm959dP5tQDVCFo3qBjau1UNt3Sh+/h22yez2FIlbjHA/luyw8+oF/0bg == Received: from ppma12.dal12v.mail.ibm.com (dc.9e.1632.ip4.static.sl-reverse.com [50.22.158.220]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 4gbnudhyrq-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Mon, 31 Aug 2026 14:48:08 +0000 (GMT) Received: from pps.filterd (ppma12.dal12v.mail.ibm.com [127.0.0.1]) by ppma12.dal12v.mail.ibm.com (8.18.1.7/8.18.1.7) with ESMTP id 67VEfbQD015523; Mon, 31 Aug 2026 14:48:07 GMT Received: from smtprelay01.fra02v.mail.ibm.com ([9.218.2.227]) by ppma12.dal12v.mail.ibm.com (PPS) with ESMTPS id 4gc9rq6m63-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Mon, 31 Aug 2026 14:48:07 +0000 (GMT) Received: from smtpav02.fra02v.mail.ibm.com (smtpav02.fra02v.mail.ibm.com [10.20.54.101]) by smtprelay01.fra02v.mail.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 67VEm3Is43188718 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Mon, 31 Aug 2026 14:48:03 GMT Received: from smtpav02.fra02v.mail.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id A4A7020043; Mon, 31 Aug 2026 14:48:03 +0000 (GMT) Received: from smtpav02.fra02v.mail.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 2FE082004F; Mon, 31 Aug 2026 14:48:03 +0000 (GMT) Received: from tuxmaker.boeblingen.de.ibm.com (unknown [9.87.85.9]) by smtpav02.fra02v.mail.ibm.com (Postfix) with ESMTP; Mon, 31 Aug 2026 14:48:03 +0000 (GMT) From: Steffen Eiden To: kvm@vger.kernel.org, kvmarm@lists.linux.dev, linux-arm-kernel@lists.infradead.org, linux-kernel@vger.kernel.org, linux-s390@vger.kernel.org Cc: Alexander Gordeev , Andreas Grapentin , Arnd Bergmann , Catalin Marinas , Christian Borntraeger , Claudio Imbrenda , David Hildenbrand , Friedrich Welter , Fuad Tabba , Gautam Gala , Hariharan Mari , Heiko Carstens , Hendrik Brueckner , Ilya Leoshkevich , Janosch Frank , Joey Gouly , Marc Zyngier , Nico Boehr , Nina Schoetterl-Glausch , Oliver Upton , Paolo Bonzini , Sean Christopherson , Suzuki K Poulose , Sven Schnelle , Ulrich Weigand , Vasily Gorbik , Will Deacon , Zenghui Yu Subject: [PATCH v7 01/23] vfio: Use file-based reference counting for KVM Date: Mon, 31 Aug 2026 16:47:38 +0200 Message-ID: <20260831144802.834315-2-seiden@linux.ibm.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260831144802.834315-1-seiden@linux.ibm.com> References: <20260831144802.834315-1-seiden@linux.ibm.com> Precedence: bulk X-Mailing-List: kvm@vger.kernel.org List-Id: List-Subscribe: List-Unsubscribe: MIME-Version: 1.0 Content-Type: text/plain; charset=UTF-8 Content-Transfer-Encoding: 8bit X-TM-AS-GCONF: 00 X-Proofpoint-Reinject: loops=2 maxloops=12 X-Proofpoint-GUID: grjCtHBEg3MoNxpQpoi92VvbIRSBtAbZ X-Proofpoint-Spam-Details-Enc: AW1haW4tMjYwODMxMDEyNSBTYWx0ZWRfXziSPzJVeJWat Zudf8a1OU4z9vSKbQH2cyvFiHIKqqWifNLuePh+ZVKk0YdUZgcq2743i7mxj4H14uIIqSPfAFRH DhdFO+N4LjpcDCzATxLLKuaixRGpPikWgabROpfnidn0iz7FhirsHbALLC8U6cCvL3v09Hh2R6z 6ppskZPd6KaCVXlM5PcZH8dDKwsqbzIr+vzT4fnicEa9kUuOvmVZ+0+earoMVZ18R8c7l1pr7kV d+qQrCf4aPOxaV8knURHRPjt4/9f6CXfoMbytNTG4IWHHVD4rFCcSyeSb/yiEhrik0eh/lk4/Mu AwmRpf3RaVhMwg8shU4IQx8+rwYoPSeqduXnPdBIQ0ODjffoJgLVrJRCtVYsBQSXeGeAtd5o2YW Ethp8GjCtsQROuib+8AS7G5OO+faqy+BUOnd+XH11P0vakb/xQcXhYAkqxKQVyItp7RJxgr1aYF BaPNwNlqPa025ZTHCdQ== X-Proofpoint-ORIG-GUID: Eeush9WWXkx4w75GgqXJx8Uzs6k8IDcQ X-Proofpoint-Spam-Info: AW1haW4tMjYwODMxMDEyNSBTYWx0ZWRfX/IVBGuAyAvXE yZ/2SZUYCbKc1ZPZE8zf1UWIXioD2oPdQPtSYUt8vQOTlvELprsBh2sAUmIMCnQqh7JUuvAIGx1 a9MQNH0p09cwx4C3M08n2RhIngxZ83k= X-Authority-Analysis: v=2.4 cv=B92JFutM c=1 sm=1 tr=0 ts=6a959428 cx=c_pps a=bLidbwmWQ0KltjZqbj+ezA==:117 a=bLidbwmWQ0KltjZqbj+ezA==:17 a=IkcTkHD0fZMA:10 a=Sv0fKeRqtYgA:10 a=VkNPw1HP01LnGYTKEx00:22 a=RnoormkPH1_aCDwRdu11:22 a=V8glGbnc2Ofi9Qvn3v5h:22 a=Ikd4Dj_1AAAA:8 a=1XWaLZrsAAAA:8 a=VnNF1IyMAAAA:8 a=cFm4mksYcdg9GKIP9xkA:9 a=3ZKOabzyN94A:10 a=QEXdDO2ut3YA:10 X-Proofpoint-Virus-Version: vendor=baseguard engine=ICAP:2.0.293,Aquarius:18.0.1176,Hydra:6.1.134,FMLib:17.12.100.49 definitions=2026-08-31_05,2026-08-27_02,2025-10-01_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 adultscore=0 spamscore=0 clxscore=1015 suspectscore=0 phishscore=0 lowpriorityscore=0 bulkscore=0 priorityscore=1501 impostorscore=0 malwarescore=0 classifier=typeunknown authscore=0 authtc= authcc= route=outbound adjust=0 reason=mlx scancount=1 engine=8.22.0-2606150000 definitions=main-2608310125 Replace manual module reference counting with file-based reference counting for KVM integration. Previously, VFIO used symbol_get() to obtain function pointers for kvm_get_kvm_safe() and kvm_put_kvm(), then manually tracked module references through these symbols. This approach required storing the put_kvm function pointer in each device and carefully managing symbol references. Remove the put_kvm field in struct vfio_device as is it no longer used. Pass struct file pointers instead of struct kvm pointers throughout the VFIO-KVM interface. This leverages the kernel's existing file reference counting mechanism via get_file()/get_file_active() and fput(), eliminating the need for manual module reference tracking. The file->private_data field provides access to the underlying struct kvm when needed. group->kvm and df->kvm hold a reference of their own, taken when the pointer is stored and dropped when it is overwritten or cleared. They have to: the kvm-vfio device fd holds a VM reference of its own, so the VM file can be closed and released while the kvm-vfio device is still alive and still pointing at it. filp_cachep is SLAB_TYPESAFE_BY_RCU, so a stale pointer left in those slots could be made to reference a recycled, unrelated file. kvm->file itself carries no reference, so that it does not pin the VM. It is only ever read with get_file_active(), which is safe because kvm_vm_release() clears it, i.e. before the struct file is freed. This simplifies the code and removes all remaining externally exported symbols for KVM, paving the path for a second concurrent KVM module. Suggested-by: Jason Gunthorpe Co-developed-by: Sean Christopherson Signed-off-by: Sean Christopherson Reviewed-by: Jason J. Herne Signed-off-by: Steffen Eiden --- arch/x86/include/asm/kvm_page_track.h | 8 ++-- arch/x86/kvm/Makefile | 5 +-- arch/x86/kvm/mmu/page_track.c | 20 ++++++---- drivers/s390/crypto/vfio_ap_ops.c | 20 +++++++--- drivers/vfio/group.c | 11 +++++- drivers/vfio/pci/vfio_pci_zdev.c | 8 +++- drivers/vfio/vfio.h | 10 ++--- drivers/vfio/vfio_main.c | 57 +++++++++------------------ include/linux/kvm_host.h | 8 ++++ include/linux/vfio.h | 5 +-- virt/kvm/kvm_main.c | 20 ++++++++-- virt/kvm/vfio.c | 13 ++++-- 12 files changed, 107 insertions(+), 78 deletions(-) diff --git a/arch/x86/include/asm/kvm_page_track.h b/arch/x86/include/asm/kvm_page_track.h index 3d040741044b..046a25c8fe4f 100644 --- a/arch/x86/include/asm/kvm_page_track.h +++ b/arch/x86/include/asm/kvm_page_track.h @@ -44,13 +44,13 @@ struct kvm_page_track_notifier_node { struct kvm_page_track_notifier_node *node); }; -int kvm_page_track_register_notifier(struct kvm *kvm, +int kvm_page_track_register_notifier(struct file *file, struct kvm_page_track_notifier_node *n); -void kvm_page_track_unregister_notifier(struct kvm *kvm, +void kvm_page_track_unregister_notifier(struct file *file, struct kvm_page_track_notifier_node *n); -int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn); -int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn); +int kvm_write_track_add_gfn(struct file *file, gfn_t gfn); +int kvm_write_track_remove_gfn(struct file *file, gfn_t gfn); #else /* * Allow defining a node in a structure even if page tracking is disabled, e.g. diff --git a/arch/x86/kvm/Makefile b/arch/x86/kvm/Makefile index 0474604ab8a1..96f89d6f7e6a 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -60,10 +60,7 @@ exports_grep_trailer := --include='*.[ch]' -nrw $(srctree)/virt/kvm $(srctree)/a grep -v -e kvm_page_track_register_notifier \ -e kvm_page_track_unregister_notifier \ -e kvm_write_track_add_gfn \ - -e kvm_write_track_remove_gfn \ - -e kvm_get_kvm \ - -e kvm_get_kvm_safe \ - -e kvm_put_kvm + -e kvm_write_track_remove_gfn # Force grep to emit a goofy group separator that can in turn be replaced with # the above newline macro (newlines in Make are a nightmare). Note, grep only diff --git a/arch/x86/kvm/mmu/page_track.c b/arch/x86/kvm/mmu/page_track.c index 7e8195a311bb..98f133e4f0b3 100644 --- a/arch/x86/kvm/mmu/page_track.c +++ b/arch/x86/kvm/mmu/page_track.c @@ -237,10 +237,11 @@ static int kvm_enable_external_write_tracking(struct kvm *kvm) * register the notifier so that event interception for the tracked guest * pages can be received. */ -int kvm_page_track_register_notifier(struct kvm *kvm, +int kvm_page_track_register_notifier(struct file *file, struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; + struct kvm *kvm = file_to_kvm(file); int r; if (!kvm || kvm->mm != current->mm) @@ -252,7 +253,7 @@ int kvm_page_track_register_notifier(struct kvm *kvm, return r; } - kvm_get_kvm(kvm); + get_file(file); head = &kvm->arch.track_notifier_head; @@ -267,10 +268,11 @@ EXPORT_SYMBOL_GPL(kvm_page_track_register_notifier); * stop receiving the event interception. It is the opposed operation of * kvm_page_track_register_notifier(). */ -void kvm_page_track_unregister_notifier(struct kvm *kvm, +void kvm_page_track_unregister_notifier(struct file *file, struct kvm_page_track_notifier_node *n) { struct kvm_page_track_notifier_head *head; + struct kvm *kvm = file_to_kvm(file); head = &kvm->arch.track_notifier_head; @@ -279,7 +281,7 @@ void kvm_page_track_unregister_notifier(struct kvm *kvm, write_unlock(&kvm->mmu_lock); synchronize_srcu(&head->track_srcu); - kvm_put_kvm(kvm); + fput(file); } EXPORT_SYMBOL_GPL(kvm_page_track_unregister_notifier); @@ -336,11 +338,12 @@ void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot) * add guest page to the tracking pool so that corresponding access on that * page will be intercepted. * - * @kvm: the guest instance we are interested in. + * @file: the VM file of the guest instance we are interested in. * @gfn: the guest page. */ -int kvm_write_track_add_gfn(struct kvm *kvm, gfn_t gfn) +int kvm_write_track_add_gfn(struct file *file, gfn_t gfn) { + struct kvm *kvm = file_to_kvm(file); struct kvm_memory_slot *slot; int idx; @@ -366,11 +369,12 @@ EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn); * remove the guest page from the tracking pool which stops the interception * of corresponding access on that page. * - * @kvm: the guest instance we are interested in. + * @file: the VM file of the guest instance we are interested in. * @gfn: the guest page. */ -int kvm_write_track_remove_gfn(struct kvm *kvm, gfn_t gfn) +int kvm_write_track_remove_gfn(struct file *file, gfn_t gfn) { + struct kvm *kvm = file_to_kvm(file); struct kvm_memory_slot *slot; int idx; diff --git a/drivers/s390/crypto/vfio_ap_ops.c b/drivers/s390/crypto/vfio_ap_ops.c index 940c0ff668be..f160e1945fbc 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -1822,17 +1822,27 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = { /** * vfio_ap_mdev_set_kvm - sets all data for @matrix_mdev that are needed - * to manage AP resources for the guest whose state is represented by @kvm + * to manage AP resources for the guest whose state is represented by + * @kvm_file * * @matrix_mdev: a mediated matrix device - * @kvm: reference to KVM instance + * @kvm_file: the KVM VM file this vfio device is associated with * - * Return: 0 if no other mediated matrix device has a reference to @kvm; + * Return: 0 if no other mediated matrix device has a reference to the VM; * otherwise, returns an -EPERM. */ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, - struct kvm *kvm) + struct file *kvm_file) { + struct kvm *kvm; + + if (!kvm_file) + return -ENOENT; + + kvm = kvm_file->private_data; + if (!kvm) + return -ENOENT; + if (kvm->arch.crypto.crycbd) { get_update_locks_for_kvm(kvm); if (kvm->arch.crypto.pqap_hook) { @@ -1841,7 +1851,6 @@ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, } kvm->arch.crypto.pqap_hook = &matrix_mdev->pqap_hook; - kvm_get_kvm(kvm); matrix_mdev->kvm = kvm; vfio_ap_mdev_update_guest_apcb(matrix_mdev); release_update_locks_for_kvm(kvm); @@ -1894,7 +1903,6 @@ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) matrix_mdev->kvm = NULL; release_update_locks_for_kvm(kvm); - kvm_put_kvm(kvm); } } diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index b2299e5bc6df..5bf8cbdff377 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -860,11 +860,20 @@ bool vfio_group_enforced_coherent(struct vfio_group *group) return ret; } -void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm) +void vfio_group_set_kvm(struct vfio_group *group, struct file *kvm) { + struct file *old; + + if (kvm) + get_file(kvm); + spin_lock(&group->kvm_ref_lock); + old = group->kvm; group->kvm = kvm; spin_unlock(&group->kvm_ref_lock); + + if (old) + fput(old); } /** diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index f47f36314a1c..3dc302062a67 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -184,6 +184,7 @@ int vfio_pci_zdev_feature_err(struct vfio_device *device, u32 flags, int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) { struct zpci_dev *zdev = to_zpci(vdev->pdev); + struct kvm *kvm; int ret; if (!zdev) @@ -195,8 +196,13 @@ int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) return 0; ret = -ENOENT; + + kvm = vdev->vdev.kvm->private_data; + if (!kvm) + return ret; + if (zpci_kvm_hook.kvm_register) - ret = zpci_kvm_hook.kvm_register(zdev, vdev->vdev.kvm); + ret = zpci_kvm_hook.kvm_register(zdev, kvm); if (ret) zpci_stop_mediated_recovery(zdev); diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 7728bc99b63d..f76504d707e1 100644 --- a/drivers/vfio/vfio.h +++ b/drivers/vfio/vfio.h @@ -23,7 +23,7 @@ struct vfio_device_file { u8 access_granted; u32 devid; /* only valid when iommufd is valid */ spinlock_t kvm_ref_lock; /* protect kvm field */ - struct kvm *kvm; + struct file *kvm; struct iommufd_ctx *iommufd; /* protected by struct vfio_device_set::lock */ }; @@ -88,7 +88,7 @@ struct vfio_group { #endif enum vfio_group_type type; struct mutex group_lock; - struct kvm *kvm; + struct file *kvm; struct file *opened_file; struct iommufd_ctx *iommufd; spinlock_t kvm_ref_lock; @@ -107,7 +107,7 @@ void vfio_device_group_unuse_iommu(struct vfio_device *device); void vfio_df_group_close(struct vfio_device_file *df); struct vfio_group *vfio_group_from_file(struct file *file); bool vfio_group_enforced_coherent(struct vfio_group *group); -void vfio_group_set_kvm(struct vfio_group *group, struct kvm *kvm); +void vfio_group_set_kvm(struct vfio_group *group, struct file *kvm); bool vfio_device_has_container(struct vfio_device *device); int __init vfio_group_init(void); void vfio_group_cleanup(void); @@ -429,11 +429,11 @@ static inline void vfio_virqfd_exit(void) #endif #if IS_ENABLED(CONFIG_KVM) -void vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm); +void vfio_device_get_kvm_safe(struct vfio_device *device, struct file *kvm); void vfio_device_put_kvm(struct vfio_device *device); #else static inline void vfio_device_get_kvm_safe(struct vfio_device *device, - struct kvm *kvm) + struct file *kvm) { } diff --git a/drivers/vfio/vfio_main.c b/drivers/vfio/vfio_main.c index 423ead48aafe..ed96acfa8635 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -472,36 +472,14 @@ void vfio_unregister_group_dev(struct vfio_device *device) EXPORT_SYMBOL_GPL(vfio_unregister_group_dev); #if IS_ENABLED(CONFIG_KVM) -void vfio_device_get_kvm_safe(struct vfio_device *device, struct kvm *kvm) +void vfio_device_get_kvm_safe(struct vfio_device *device, struct file *kvm) { - void (*pfn)(struct kvm *kvm); - bool (*fn)(struct kvm *kvm); - bool ret; - lockdep_assert_held(&device->dev_set->lock); if (!kvm) return; - pfn = symbol_get(kvm_put_kvm); - if (WARN_ON(!pfn)) - return; - - fn = symbol_get(kvm_get_kvm_safe); - if (WARN_ON(!fn)) { - symbol_put(kvm_put_kvm); - return; - } - - ret = fn(kvm); - symbol_put(kvm_get_kvm_safe); - if (!ret) { - symbol_put(kvm_put_kvm); - return; - } - - device->put_kvm = pfn; - device->kvm = kvm; + device->kvm = get_file(kvm); } void vfio_device_put_kvm(struct vfio_device *device) @@ -511,14 +489,7 @@ void vfio_device_put_kvm(struct vfio_device *device) if (!device->kvm) return; - if (WARN_ON(!device->put_kvm)) - goto clear; - - device->put_kvm(device->kvm); - device->put_kvm = NULL; - symbol_put(kvm_put_kvm); - -clear: + fput(device->kvm); device->kvm = NULL; } #endif @@ -1544,9 +1515,13 @@ bool vfio_file_enforced_coherent(struct file *file) } EXPORT_SYMBOL_GPL(vfio_file_enforced_coherent); -static void vfio_device_file_set_kvm(struct file *file, struct kvm *kvm) +static void vfio_device_file_set_kvm(struct file *file, struct file *kvm) { struct vfio_device_file *df = file->private_data; + struct file *old; + + if (kvm) + get_file(kvm); /* * The kvm is first recorded in the vfio_device_file, and will @@ -1554,28 +1529,32 @@ static void vfio_device_file_set_kvm(struct file *file, struct kvm *kvm) * iommufd successfully in the vfio device cdev path. */ spin_lock(&df->kvm_ref_lock); + old = df->kvm; df->kvm = kvm; spin_unlock(&df->kvm_ref_lock); + + if (old) + fput(old); } /** * vfio_file_set_kvm - Link a kvm with VFIO drivers - * @file: VFIO group file or VFIO device file - * @kvm: KVM to link + * @vfio_file: VFIO group file or VFIO device file + * @kvm: KVM file to link * * When a VFIO device is first opened the KVM will be available in * device->kvm if one was associated with the file. */ -void vfio_file_set_kvm(struct file *file, struct kvm *kvm) +void vfio_file_set_kvm(struct file *vfio_file, struct file *kvm) { struct vfio_group *group; - group = vfio_group_from_file(file); + group = vfio_group_from_file(vfio_file); if (group) vfio_group_set_kvm(group, kvm); - if (vfio_device_from_file(file)) - vfio_device_file_set_kvm(file, kvm); + if (vfio_device_from_file(vfio_file)) + vfio_device_file_set_kvm(vfio_file, kvm); } EXPORT_SYMBOL_GPL(vfio_file_set_kvm); diff --git a/include/linux/kvm_host.h b/include/linux/kvm_host.h index 03bfc92864b6..bfecce1b5955 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -784,6 +784,13 @@ struct kvm { * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; + /* + * Back-reference to the VM file for subsystems (e.g., VFIO). Holds no + * reference to avoid pinning the VM. Access via get_file_active(&kvm->file) + * only—safe because cleared in kvm_vm_release() before file freed. Callers + * storing the result must take their own reference via get_file() + */ + struct file *file; struct mm_struct *mm; /* userspace tied to this vm */ unsigned long nr_memslot_pages; /* The two memslot sets - active and inactive (per address space) */ @@ -1082,6 +1089,7 @@ void kvm_get_kvm(struct kvm *kvm); bool kvm_get_kvm_safe(struct kvm *kvm); void kvm_put_kvm(struct kvm *kvm); bool file_is_kvm(struct file *file); +struct kvm *file_to_kvm(struct file *file); void kvm_put_kvm_no_destroy(struct kvm *kvm); static inline struct kvm_memslots *__kvm_memslots(struct kvm *kvm, int as_id) diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 45f08986359e..0cc91c6f96d2 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -54,7 +54,7 @@ struct vfio_device { struct list_head dev_set_list; unsigned int migration_flags; u8 precopy_info_v2; - struct kvm *kvm; + struct file *kvm; /* Members below here are private, not for driver use */ unsigned int index; @@ -66,7 +66,6 @@ struct vfio_device { unsigned int open_count; struct completion comp; struct iommufd_access *iommufd_access; - void (*put_kvm)(struct kvm *kvm); struct inode *inode; #if IS_ENABLED(CONFIG_IOMMUFD) struct iommufd_device *iommufd_device; @@ -378,7 +377,7 @@ static inline bool vfio_file_has_dev(struct file *file, struct vfio_device *devi #endif bool vfio_file_is_valid(struct file *file); bool vfio_file_enforced_coherent(struct file *file); -void vfio_file_set_kvm(struct file *file, struct kvm *kvm); +void vfio_file_set_kvm(struct file *vfio_file, struct file *kvm); #define VFIO_PIN_PAGES_MAX_ENTRIES (PAGE_SIZE/sizeof(unsigned long)) diff --git a/virt/kvm/kvm_main.c b/virt/kvm/kvm_main.c index 65eb26a0520d..34b4c43908b3 100644 --- a/virt/kvm/kvm_main.c +++ b/virt/kvm/kvm_main.c @@ -1314,7 +1314,7 @@ void kvm_get_kvm(struct kvm *kvm) { refcount_inc(&kvm->users_count); } -EXPORT_SYMBOL_GPL(kvm_get_kvm); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_kvm); /* * Make sure the vm is not during destruction, which is a safe version of @@ -1324,14 +1324,14 @@ bool kvm_get_kvm_safe(struct kvm *kvm) { return refcount_inc_not_zero(&kvm->users_count); } -EXPORT_SYMBOL_GPL(kvm_get_kvm_safe); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_get_kvm_safe); void kvm_put_kvm(struct kvm *kvm) { if (refcount_dec_and_test(&kvm->users_count)) kvm_destroy_vm(kvm); } -EXPORT_SYMBOL_GPL(kvm_put_kvm); +EXPORT_SYMBOL_FOR_KVM_INTERNAL(kvm_put_kvm); /* * Used to put a reference that was taken on behalf of an object associated @@ -1352,6 +1352,8 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) kvm_irqfd_release(kvm); + WRITE_ONCE(kvm->file, NULL); + kvm_put_kvm(kvm); return 0; } @@ -5496,6 +5498,15 @@ bool file_is_kvm(struct file *file) } EXPORT_SYMBOL_FOR_KVM_INTERNAL(file_is_kvm); +struct kvm *file_to_kvm(struct file *file) +{ + if (!file_is_kvm(file)) + return NULL; + + return file->private_data; +} +EXPORT_SYMBOL_FOR_KVM_INTERNAL(file_to_kvm); + static int kvm_dev_ioctl_create_vm(unsigned long type) { char fdname[ITOA_MAX_LEN + 1]; @@ -5527,6 +5538,9 @@ static int kvm_dev_ioctl_create_vm(unsigned long type) * cases it will be called by the final fput(file) and will take * care of doing kvm_put_kvm(kvm). */ + + kvm->file = file; + kvm_uevent_notify_change(KVM_EVENT_CREATE_VM, kvm); fd_install(fd, file); diff --git a/virt/kvm/vfio.c b/virt/kvm/vfio.c index 6cdc4e9a333a..19548a430942 100644 --- a/virt/kvm/vfio.c +++ b/virt/kvm/vfio.c @@ -35,15 +35,15 @@ struct kvm_vfio { bool noncoherent; }; -static void kvm_vfio_file_set_kvm(struct file *file, struct kvm *kvm) +static void kvm_vfio_file_set_kvm(struct file *vfio_file, struct file *kvm) { - void (*fn)(struct file *file, struct kvm *kvm); + void (*fn)(struct file *vfio_file, struct file *kvm); fn = symbol_get(vfio_file_set_kvm); if (!fn) return; - fn(file, kvm); + fn(vfio_file, kvm); symbol_put(vfio_file_set_kvm); } @@ -144,6 +144,7 @@ static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) { struct kvm_vfio *kv = dev->private; struct kvm_vfio_file *kvf; + struct file *kvm_file __free(fput) = NULL; struct file *filp __free(fput) = NULL; filp = fget(fd); @@ -154,6 +155,10 @@ static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) if (!kvm_vfio_file_is_valid(filp)) return -EINVAL; + kvm_file = get_file_active(&dev->kvm->file); + if (!kvm_file) + return -ENOENT; + guard(mutex)(&kv->lock); list_for_each_entry(kvf, &kv->file_list, node) { @@ -168,7 +173,7 @@ static int kvm_vfio_file_add(struct kvm_device *dev, unsigned int fd) kvf->file = get_file(filp); list_add_tail(&kvf->node, &kv->file_list); - kvm_vfio_file_set_kvm(kvf->file, dev->kvm); + kvm_vfio_file_set_kvm(kvf->file, kvm_file); kvm_vfio_update_coherency(dev); return 0; -- 2.53.0