From mboxrd@z Thu Jan 1 00:00:00 1970 Received: from mx0a-001b2d01.pphosted.com (mx0a-001b2d01.pphosted.com [148.163.156.1]) (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 20B6B44C4E2; Wed, 12 Aug 2026 15:37:17 +0000 (UTC) Authentication-Results: smtp.subspace.kernel.org; arc=none smtp.client-ip=148.163.156.1 ARC-Seal:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786549049; cv=none; b=KJeTsPvwhCvr6tVrfIkYoPumCLbWP9MTvbpHFRcY2evM/kt/el8YztFg9o3M6rIBQuoxImYrZVCLLc+tefnykPbunG4c2/z3t2TyEZE7MGGSbo1aKC8QUPx6+8omPcobzUALxKXP9qpmKvcDPsZltZ89N+XB86PJ77LuuEsst9o= ARC-Message-Signature:i=1; a=rsa-sha256; d=subspace.kernel.org; s=arc-20240116; t=1786549049; c=relaxed/simple; bh=uOcF1zD1XNDj2iXI9EzY9mfpPt/FXOE/SA6gY8bVyx8=; h=From:To:Cc:Subject:Date:Message-ID:In-Reply-To:References: MIME-Version:Content-Type; b=Ot1cdFRGpUq7i6fQh5Je4zBKL59B+nOLXAuRJlvv+eW1w3zUoUHtKgo3fA+VzXordCGJ5zXZnCIlU6QH3Yj8sA8W+P6XoK6T71FWwOokSceQfYDI8EtnOkZReNstoBZaZ6QjMsCbLVdXCUwpRkr8jrRx1aEK3HH1f6aQQJtiusg= 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=rR9egrau; arc=none smtp.client-ip=148.163.156.1 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="rR9egrau" Received: from pps.filterd (m0353729.ppops.net [127.0.0.1]) by mx0a-001b2d01.pphosted.com (8.18.1.11/8.18.1.11) with ESMTP id 67CE1UBZ1816396; Wed, 12 Aug 2026 15:36:38 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=/5NL9D O/LCOIeBJYhlzjg0RPSv1yXhjruJs23EtLbMw=; b=rR9egrauJDdTNZ4sBpxhgZ 6mRcA61jxuHt1yi0ni9FjsLR1xBVRz+DuxGaYph+IptMHB+AYkONqMPkIAMfF66M 7/y0Qy3gY6BxgXbPsMxpJzDQEuUK6f3PkdQImu3ikk6fmxyqxKxeykM7gMzcpEeo BBcBj3DWEMpl2wc+tM5qNgUfh+capnWvJ+utPO7k++9z8nGb+utYLKsDgNUdOkM7 aMWgFSXDQRTkniFlQu0ke9lvs1CeAZDAzqA/2rlCm83MI/b0epVZhv/DGUE3HUTn 9v5b/3O+zf1fuEVofC6EKVX4I8+UZZL5SxT+8q81g8T+ypW+GCbthoMbXzLA9pvA == Received: from ppma11.dal12v.mail.ibm.com (db.9e.1632.ip4.static.sl-reverse.com [50.22.158.219]) by mx0a-001b2d01.pphosted.com (PPS) with ESMTPS id 4fwvk0380c-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Wed, 12 Aug 2026 15:36:37 +0000 (GMT) Received: from pps.filterd (ppma11.dal12v.mail.ibm.com [127.0.0.1]) by ppma11.dal12v.mail.ibm.com (8.18.1.7/8.18.1.7) with ESMTP id 67CFQHOM021704; Wed, 12 Aug 2026 15:36:36 GMT Received: from smtprelay03.fra02v.mail.ibm.com ([9.218.2.224]) by ppma11.dal12v.mail.ibm.com (PPS) with ESMTPS id 4fxhfy6g3g-1 (version=TLSv1.2 cipher=ECDHE-RSA-AES256-GCM-SHA384 bits=256 verify=NOT); Wed, 12 Aug 2026 15:36:36 +0000 (GMT) Received: from smtpav06.fra02v.mail.ibm.com (smtpav06.fra02v.mail.ibm.com [10.20.54.105]) by smtprelay03.fra02v.mail.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id 67CFaWqT35717612 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-GCM-SHA384 bits=256 verify=OK); Wed, 12 Aug 2026 15:36:33 GMT Received: from smtpav06.fra02v.mail.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id CE8742004E; Wed, 12 Aug 2026 15:36:32 +0000 (GMT) Received: from smtpav06.fra02v.mail.ibm.com (unknown [127.0.0.1]) by IMSVA (Postfix) with ESMTP id 664A02004D; Wed, 12 Aug 2026 15:36:32 +0000 (GMT) Received: from tuxmaker.boeblingen.de.ibm.com (unknown [9.87.85.9]) by smtpav06.fra02v.mail.ibm.com (Postfix) with ESMTP; Wed, 12 Aug 2026 15:36:32 +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 v6 01/33] vfio: Use file-based reference counting for KVM Date: Wed, 12 Aug 2026 17:35:57 +0200 Message-ID: <20260812153631.3376090-2-seiden@linux.ibm.com> X-Mailer: git-send-email 2.53.0 In-Reply-To: <20260812153631.3376090-1-seiden@linux.ibm.com> References: <20260812153631.3376090-1-seiden@linux.ibm.com> Precedence: bulk X-Mailing-List: linux-kernel@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-Spam-Details-Enc: AW1haW4tMjYwODEyMDEyNiBTYWx0ZWRfXxAVS7HSTpWB9 g7fP50abyPZerqWSYDope405Egt8jTS08PYdST2faGhKQKlunIYX6JXMqhKNpVbxPUCEWBx5c1K arHrUZKC8tphL+fWm3xBoOtfgs5L7SrWhEpXhuQo+l/4U35HlUpqFngDqaOLUU64m72hgB2GGdo kb3aAEPnOnDa4jgWYJjOHxzsTDZRejCQE7PUyqso3LAiSMafgXSvN84W7xQSEEpMXD6FLlLMELj 1nC4DFmJ1fYLTa2zEkb6CY5PwoCzOkDcJu7zbfcqdAgY3rS8usENbbRZF2bPmZyVF2PLsGFHa9p sK8PkYhvxG5tGcK3GlstRfRpSllY9Zzw+h8NYRDsV/BAK7TIN3Zfap+XIkATPGgrhoZQKb0lg/b IFJNuwpBh7Sj7oCGFdxPxGuL/jFCEX42PWvSknkPYnDjimLj6G1Cj6tD4RBNnGWBmKGinlXRabo DO92A6mlANNDzMG+FmQ== X-Proofpoint-Spam-Info: AW1haW4tMjYwODEyMDEyNiBTYWx0ZWRfX/BXwSuGKiKj8 FFfhUFDTPx+D3wiQDz5AQBMfeDCTJX52pv7thdMnDBrkMF0/Cosm9pbFYvJs2AhHPMjqgf60hCt LrLJw/4gBNJQ4c6ioZQURG/pFB245Tc= X-Authority-Analysis: v=2.4 cv=RqD16imK c=1 sm=1 tr=0 ts=6a7c9306 cx=c_pps a=aDMHemPKRhS1OARIsFnwRA==:117 a=aDMHemPKRhS1OARIsFnwRA==:17 a=IkcTkHD0fZMA:10 a=Sv0fKeRqtYgA:10 a=VkNPw1HP01LnGYTKEx00:22 a=RnoormkPH1_aCDwRdu11:22 a=uAbxVGIbfxUO_5tXvNgY:22 a=Ikd4Dj_1AAAA:8 a=1XWaLZrsAAAA:8 a=VnNF1IyMAAAA:8 a=cFm4mksYcdg9GKIP9xkA:9 a=3ZKOabzyN94A:10 a=QEXdDO2ut3YA:10 X-Proofpoint-GUID: yBHl0QxAJqzQt7qjTPFFOCUdDnfVramG X-Proofpoint-ORIG-GUID: NbXaTicKfGWwKZQ_vNSULy1AMpFKRX7z 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=2026-08-12_04,2026-08-12_01,2025-10-01_01 X-Proofpoint-Spam-Details: rule=outbound_notspam policy=outbound score=0 phishscore=0 priorityscore=1501 suspectscore=0 lowpriorityscore=0 clxscore=1015 adultscore=0 bulkscore=0 malwarescore=0 impostorscore=0 spamscore=0 classifier=typeunknown authscore=0 authtc= authcc= route=outbound adjust=0 reason=mlx scancount=1 engine=8.22.0-2606150000 definitions=main-2608120126 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_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. 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 Signed-off-by: Steffen Eiden --- arch/x86/include/asm/kvm_page_track.h | 8 ++--- arch/x86/kvm/Makefile | 3 -- arch/x86/kvm/mmu/page_track.c | 16 +++++---- drivers/s390/crypto/vfio_ap_ops.c | 30 ++++++++++++---- drivers/s390/crypto/vfio_ap_private.h | 1 + drivers/vfio/device_cdev.c | 2 +- drivers/vfio/group.c | 4 +-- drivers/vfio/pci/vfio_pci_zdev.c | 7 +++- drivers/vfio/vfio.h | 10 +++--- drivers/vfio/vfio_main.c | 52 +++++++-------------------- include/linux/kvm_host.h | 7 ++++ include/linux/vfio.h | 5 ++- virt/kvm/kvm_main.c | 22 ++++++++++-- virt/kvm/vfio.c | 8 ++--- 14 files changed, 97 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..70645c2cd8ed 100644 --- a/arch/x86/kvm/Makefile +++ b/arch/x86/kvm/Makefile @@ -61,9 +61,6 @@ exports_grep_trailer := --include='*.[ch]' -nrw $(srctree)/virt/kvm $(srctree)/a -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 # 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..860049ed24ea 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); @@ -339,8 +341,9 @@ void kvm_page_track_delete_slot(struct kvm *kvm, struct kvm_memory_slot *slot) * @kvm: 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; @@ -369,8 +372,9 @@ EXPORT_SYMBOL_GPL(kvm_write_track_add_gfn); * @kvm: 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 99a0efd999ef..875e67063d8e 100644 --- a/drivers/s390/crypto/vfio_ap_ops.c +++ b/drivers/s390/crypto/vfio_ap_ops.c @@ -8,6 +8,7 @@ * Halil Pasic * Pierre Morel */ +#include "linux/cleanup.h" #include #include #include @@ -1822,12 +1823,25 @@ static const struct attribute_group *vfio_ap_mdev_attr_groups[] = { * @matrix_mdev: a mediated matrix device * @kvm: reference to KVM instance * - * Return: 0 if no other mediated matrix device has a reference to @kvm; - * otherwise, returns an -EPERM. + * Returns: 0 if the reference to kvm is successfully retrieved from @kvm_file + * and set into @matrix_mdev; otherwise, returns: + * -ENOENT if a reference to kvm could not be retrieved from @kvm_file + * -EPERM if another mediated matrix device already has a reference to the same kvm instance */ static int vfio_ap_mdev_set_kvm(struct ap_matrix_mdev *matrix_mdev, - struct kvm *kvm) + struct file **kvm_file) { + struct file *kvm_file_ref __free(fput) = NULL; + struct kvm *kvm; + + kvm_file_ref = get_file_active(kvm_file); + if (!kvm_file_ref) + return -ENOENT; + + kvm = kvm_file_ref->private_data; + if (!kvm) + return -ENOENT; + if (kvm->arch.crypto.crycbd) { get_update_locks_for_kvm(kvm); if (kvm->arch.crypto.pqap_hook) { @@ -1836,10 +1850,11 @@ 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); + + matrix_mdev->kvm_file = no_free_ptr(kvm_file_ref); } return 0; @@ -1878,9 +1893,10 @@ static void vfio_ap_mdev_dma_unmap(struct vfio_device *vdev, u64 iova, */ static void vfio_ap_mdev_unset_kvm(struct ap_matrix_mdev *matrix_mdev) { + struct file *kvm_file = matrix_mdev->kvm_file; struct kvm *kvm = matrix_mdev->kvm; - if (kvm && kvm->arch.crypto.crycbd) { + if (kvm_file && kvm && kvm->arch.crypto.crycbd) { get_update_locks_for_kvm(kvm); kvm->arch.crypto.pqap_hook = NULL; @@ -1889,7 +1905,7 @@ 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); + fput(kvm_file); } } @@ -2053,7 +2069,7 @@ static int vfio_ap_mdev_open_device(struct vfio_device *vdev) if (!vdev->kvm) return -EINVAL; - return vfio_ap_mdev_set_kvm(matrix_mdev, vdev->kvm); + return vfio_ap_mdev_set_kvm(matrix_mdev, &vdev->kvm); } static void vfio_ap_mdev_close_device(struct vfio_device *vdev) diff --git a/drivers/s390/crypto/vfio_ap_private.h b/drivers/s390/crypto/vfio_ap_private.h index 9bff666b0b35..4ec91c6827eb 100644 --- a/drivers/s390/crypto/vfio_ap_private.h +++ b/drivers/s390/crypto/vfio_ap_private.h @@ -117,6 +117,7 @@ struct ap_matrix_mdev { struct ap_matrix matrix; struct ap_matrix shadow_apcb; struct kvm *kvm; + struct file *kvm_file; crypto_hook pqap_hook; struct mdev_device *mdev; struct ap_queue_table qtable; diff --git a/drivers/vfio/device_cdev.c b/drivers/vfio/device_cdev.c index 1d9515c967b0..e32176a55c46 100644 --- a/drivers/vfio/device_cdev.c +++ b/drivers/vfio/device_cdev.c @@ -65,7 +65,7 @@ int vfio_device_fops_cdev_open(struct inode *inode, struct file *filep) static void vfio_df_get_kvm_safe(struct vfio_device_file *df) { spin_lock(&df->kvm_ref_lock); - vfio_device_get_kvm_safe(df->device, df->kvm); + vfio_device_get_kvm_safe(df->device, &df->kvm); spin_unlock(&df->kvm_ref_lock); } diff --git a/drivers/vfio/group.c b/drivers/vfio/group.c index b2299e5bc6df..197298ca0003 100644 --- a/drivers/vfio/group.c +++ b/drivers/vfio/group.c @@ -163,7 +163,7 @@ static int vfio_group_ioctl_set_container(struct vfio_group *group, static void vfio_device_group_get_kvm_safe(struct vfio_device *device) { spin_lock(&device->group->kvm_ref_lock); - vfio_device_get_kvm_safe(device, device->group->kvm); + vfio_device_get_kvm_safe(device, &device->group->kvm); spin_unlock(&device->group->kvm_ref_lock); } @@ -860,7 +860,7 @@ 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) { spin_lock(&group->kvm_ref_lock); group->kvm = kvm; diff --git a/drivers/vfio/pci/vfio_pci_zdev.c b/drivers/vfio/pci/vfio_pci_zdev.c index 0990fdb146b7..d3a110101353 100644 --- a/drivers/vfio/pci/vfio_pci_zdev.c +++ b/drivers/vfio/pci/vfio_pci_zdev.c @@ -144,6 +144,7 @@ int vfio_pci_info_zdev_add_caps(struct vfio_pci_core_device *vdev, int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) { struct zpci_dev *zdev = to_zpci(vdev->pdev); + struct kvm *kvm; if (!zdev) return -ENODEV; @@ -151,8 +152,12 @@ int vfio_pci_zdev_open_device(struct vfio_pci_core_device *vdev) if (!vdev->vdev.kvm) return 0; + kvm = vdev->vdev.kvm->private_data; + if (!kvm) + return -ENOENT; + if (zpci_kvm_hook.kvm_register) - return zpci_kvm_hook.kvm_register(zdev, vdev->vdev.kvm); + return zpci_kvm_hook.kvm_register(zdev, kvm); return -ENOENT; } diff --git a/drivers/vfio/vfio.h b/drivers/vfio/vfio.h index 7728bc99b63d..7935c51ea1ac 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..b06d1a911605 100644 --- a/drivers/vfio/vfio_main.c +++ b/drivers/vfio/vfio_main.c @@ -472,36 +472,17 @@ 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; + struct file *kvm_file_ref __free(fput) = NULL; lockdep_assert_held(&device->dev_set->lock); - if (!kvm) + kvm_file_ref = get_file_active(kvm); + if (!kvm_file_ref) 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 = no_free_ptr(kvm_file_ref); } void vfio_device_put_kvm(struct vfio_device *device) @@ -511,14 +492,7 @@ 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 @@ -1544,7 +1518,7 @@ 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; @@ -1560,22 +1534,22 @@ static void vfio_device_file_set_kvm(struct file *file, struct kvm *kvm) /** * 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..1c5bf2801bf1 100644 --- a/include/linux/kvm_host.h +++ b/include/linux/kvm_host.h @@ -784,6 +784,12 @@ struct kvm { * kvm_swap_active_memslots(). */ struct mutex slots_arch_lock; + /* + * Back-reference to VM file descriptor without extra refcount held. + * Use get_file_active() to safely access the file without circular references. + * RCU-protected to ensure safe access even during file release. + */ + struct file __rcu *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 +1088,7 @@ 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..0d80730e8424 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 +1352,9 @@ static int kvm_vm_release(struct inode *inode, struct file *filp) kvm_irqfd_release(kvm); + rcu_assign_pointer(kvm->file, NULL); + synchronize_rcu(); + kvm_put_kvm(kvm); return 0; } @@ -5496,6 +5499,15 @@ 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 +5539,10 @@ 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). */ + + /* Store back-reference for VFIO and other subsystems */ + rcu_assign_pointer(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..0166cc4d39b3 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); } @@ -168,7 +168,7 @@ 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, dev->kvm->file); kvm_vfio_update_coherency(dev); return 0; -- 2.53.0