From nobody Thu Nov 14 06:24:25 2024 Return-Path: X-Spam-Checker-Version: SpamAssassin 3.4.0 (2014-02-07) on aws-us-west-2-korg-lkml-1.web.codeaurora.org Received: from vger.kernel.org (vger.kernel.org [23.128.96.18]) by smtp.lore.kernel.org (Postfix) with ESMTP id 9C224C7EE37 for ; Fri, 9 Jun 2023 08:54:00 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S239458AbjFIIxb (ORCPT ); Fri, 9 Jun 2023 04:53:31 -0400 Received: from lindbergh.monkeyblade.net ([23.128.96.19]:52894 "EHLO lindbergh.monkeyblade.net" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S240362AbjFIIwc (ORCPT ); Fri, 9 Jun 2023 04:52:32 -0400 Received: from mailgw01.mediatek.com (unknown [60.244.123.138]) by lindbergh.monkeyblade.net (Postfix) with ESMTPS id 513001725; Fri, 9 Jun 2023 01:52:25 -0700 (PDT) X-UUID: efed138a06a211ee9cb5633481061a41-20230609 DKIM-Signature: v=1; a=rsa-sha256; q=dns/txt; c=relaxed/relaxed; d=mediatek.com; s=dk; h=Content-Type:MIME-Version:References:In-Reply-To:Message-ID:Date:Subject:CC:To:From; bh=MXXV9yY2g0nzhs+jXk0gIg2/hxo8rfBCZS2E1IQueTA=; b=Iy6qbfgH8vdUYYsy8Dw/t2BOFefk4V73Gq+CL7dpbuqywSO+aqYrbEAYiN5bpXrOVJu1Ulh0ztUWSIvhTV420ugj5UgoVRZX7QFrw7QxBCIMWdv1hj2clQ4lXhYoJvzcFz3AtUTrtFX5rLFHwb3ZY843DUrVh7pmxtQ18ndCE54=; X-CID-P-RULE: Release_Ham X-CID-O-INFO: VERSION:1.1.26,REQID:12266ae3-a771-47c6-a73b-bc0f2faf2319,IP:0,U RL:0,TC:0,Content:-25,EDM:0,RT:0,SF:0,FILE:0,BULK:0,RULE:Release_Ham,ACTIO N:release,TS:-25 X-CID-META: VersionHash:cb9a4e1,CLOUDID:01ce1b3e-7aa7-41f3-a6bd-0433bee822f3,B ulkID:nil,BulkQuantity:0,Recheck:0,SF:102,TC:nil,Content:0,EDM:-3,IP:nil,U RL:0,File:nil,Bulk:nil,QS:nil,BEC:nil,COL:0,OSI:0,OSA:0,AV:0,LES:1,SPR:NO X-CID-BVR: 0 X-CID-BAS: 0,_,0,_ X-CID-FACTOR: TF_CID_SPAM_SNR X-UUID: efed138a06a211ee9cb5633481061a41-20230609 Received: from mtkmbs11n1.mediatek.inc [(172.21.101.185)] by mailgw01.mediatek.com (envelope-from ) (Generic MTA with TLSv1.2 ECDHE-RSA-AES256-GCM-SHA384 256/256) with ESMTP id 2083432242; Fri, 09 Jun 2023 16:52:17 +0800 Received: from mtkmbs13n1.mediatek.inc (172.21.101.193) by mtkmbs13n1.mediatek.inc (172.21.101.193) with Microsoft SMTP Server (version=TLS1_2, cipher=TLS_ECDHE_RSA_WITH_AES_256_GCM_SHA384) id 15.2.1118.26; Fri, 9 Jun 2023 16:52:16 +0800 Received: from mtksdccf07.mediatek.inc (172.21.84.99) by mtkmbs13n1.mediatek.inc (172.21.101.73) with Microsoft SMTP Server id 15.2.1118.26 via Frontend Transport; Fri, 9 Jun 2023 16:52:16 +0800 From: Yi-De Wu To: Yingshiuan Pan , Ze-Yu Wang , Yi-De Wu , Jonathan Corbet , Catalin Marinas , Will Deacon , Arnd Bergmann , Matthias Brugger , AngeloGioacchino Del Regno CC: , , , , , Krzysztof Kozlowski , Rob Herring , Conor Dooley , Conor Dooley , Trilok Soni , David Bradil , Jade Shih , Miles Chen , Ivan Tseng , My Chuang , Shawn Hsiao , PeiLun Suei , Liju Chen , Willix Yeh Subject: [PATCH v4 5/9] virt: geniezone: Add irqfd support Date: Fri, 9 Jun 2023 16:52:10 +0800 Message-ID: <20230609085214.31071-6-yi-de.wu@mediatek.com> X-Mailer: git-send-email 2.18.0 In-Reply-To: <20230609085214.31071-1-yi-de.wu@mediatek.com> References: <20230609085214.31071-1-yi-de.wu@mediatek.com> MIME-Version: 1.0 X-MTK: N Precedence: bulk List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Transfer-Encoding: quoted-printable Content-Type: text/plain; charset="utf-8" From: "Yingshiuan Pan" irqfd enables other threads than vcpu threads to inject virtual interrupt through irqfd asynchronously rather through ioctl interface. This interface is necessary for VMM which creates separated thread for IO handling or uses vhost devices. Signed-off-by: Yingshiuan Pan Signed-off-by: Liju Chen Signed-off-by: Yi-De Wu --- arch/arm64/geniezone/gzvm_arch_common.h | 6 + drivers/virt/geniezone/Makefile | 4 +- drivers/virt/geniezone/gzvm_irqfd.c | 537 ++++++++++++++++++++++++ drivers/virt/geniezone/gzvm_main.c | 3 +- drivers/virt/geniezone/gzvm_vcpu.c | 1 + drivers/virt/geniezone/gzvm_vm.c | 18 + include/linux/gzvm_drv.h | 27 ++ include/uapi/linux/gzvm.h | 18 + 8 files changed, 611 insertions(+), 3 deletions(-) create mode 100644 drivers/virt/geniezone/gzvm_irqfd.c diff --git a/arch/arm64/geniezone/gzvm_arch_common.h b/arch/arm64/geniezone= /gzvm_arch_common.h index 1b315264bf24..5affa28b935a 100644 --- a/arch/arm64/geniezone/gzvm_arch_common.h +++ b/arch/arm64/geniezone/gzvm_arch_common.h @@ -46,6 +46,7 @@ enum { #define MT_HVC_GZVM_CREATE_DEVICE GZVM_HCALL_ID(GZVM_FUNC_CREATE_DEVICE) #define MT_HVC_GZVM_PROBE GZVM_HCALL_ID(GZVM_FUNC_PROBE) #define MT_HVC_GZVM_ENABLE_CAP GZVM_HCALL_ID(GZVM_FUNC_ENABLE_CAP) +#define GIC_V3_NR_LRS 16 =20 /** * gzvm_hypercall_wrapper() @@ -72,6 +73,11 @@ static inline gzvm_vcpu_id_t get_vcpuid_from_tuple(unsig= ned int tuple) return (gzvm_vcpu_id_t)(tuple & 0xffff); } =20 +struct gzvm_vcpu_hwstate { + __u32 nr_lrs; + __u64 lr[GIC_V3_NR_LRS]; +}; + static inline unsigned int assemble_vm_vcpu_tuple(gzvm_id_t vmid, gzvm_vcpu_id_t vcpuid) { diff --git a/drivers/virt/geniezone/Makefile b/drivers/virt/geniezone/Makef= ile index 67ba3ed76ea7..aa52cee3ca8e 100644 --- a/drivers/virt/geniezone/Makefile +++ b/drivers/virt/geniezone/Makefile @@ -7,5 +7,5 @@ GZVM_DIR ?=3D ../../../drivers/virt/geniezone =20 gzvm-y :=3D $(GZVM_DIR)/gzvm_main.o $(GZVM_DIR)/gzvm_vm.o \ - $(GZVM_DIR)/gzvm_vcpu.o $(GZVM_DIR)/gzvm_irqchip.o - + $(GZVM_DIR)/gzvm_vcpu.o $(GZVM_DIR)/gzvm_irqchip.o \ + $(GZVM_DIR)/gzvm_irqfd.o diff --git a/drivers/virt/geniezone/gzvm_irqfd.c b/drivers/virt/geniezone/g= zvm_irqfd.c new file mode 100644 index 000000000000..3a395b972fdf --- /dev/null +++ b/drivers/virt/geniezone/gzvm_irqfd.c @@ -0,0 +1,537 @@ +// SPDX-License-Identifier: GPL-2.0 +/* + * Copyright (c) 2023 MediaTek Inc. + */ + +#include +#include +#include +#include "gzvm_common.h" + +struct gzvm_irq_ack_notifier { + struct hlist_node link; + unsigned int gsi; + void (*irq_acked)(struct gzvm_irq_ack_notifier *ian); +}; + +/** + * struct gzvm_kernel_irqfd_resampler - irqfd resampler descriptor. + * @gzvm: Poiner to gzvm. + * @list_head list: List of resampling struct _irqfd objects sharing this = gsi. + * RCU list modified under gzvm->irqfds.resampler_lock. + * @notifier: gzvm irq ack notifier. + * @list_head link: Entry in list of gzvm->irqfd.resampler_list. + * Use for sharing esamplers among irqfds on the same gsi. + * Accessed and modified under gzvm->irqfds.resampler_lock. + * + * Resampling irqfds are a special variety of irqfds used to emulate + * level triggered interrupts. The interrupt is asserted on eventfd + * trigger. On acknowledgment through the irq ack notifier, the + * interrupt is de-asserted and userspace is notified through the + * resamplefd. All resamplers on the same gsi are de-asserted + * together, so we don't need to track the state of each individual + * user. We can also therefore share the same irq source ID. + */ +struct gzvm_kernel_irqfd_resampler { + struct gzvm *gzvm; + + struct list_head list; + struct gzvm_irq_ack_notifier notifier; + + struct list_head link; +}; + +/** + * struct gzvm_kernel_irqfd: gzvm kernel irqfd descriptor. + * @gzvm: Pointer to gzvm. + * @wait: Wait queue entry. + * @gsi: Used for level IRQ fast-path. + * @resampler: The resampler used by this irqfd (resampler-only). + * @resamplefd: Eventfd notified on resample (resampler-only). + * @resampler_link: Entry in list of irqfds for a resampler (resampler-onl= y). + * @eventfd: Used for setup/shutdown. + */ +struct gzvm_kernel_irqfd { + struct gzvm *gzvm; + wait_queue_entry_t wait; + + int gsi; + + struct gzvm_kernel_irqfd_resampler *resampler; + + struct eventfd_ctx *resamplefd; + + struct list_head resampler_link; + + struct eventfd_ctx *eventfd; + struct list_head list; + poll_table pt; + struct work_struct shutdown; +}; + +static struct workqueue_struct *irqfd_cleanup_wq; + +/** + * irqfd_set_spi(): irqfd to inject virtual interrupt. + * @gzvm: Pointer to gzvm. + * @irq_source_id: irq source id. + * @irq: This is spi interrupt number (starts from 0 instead of 32). + * @level: irq triggered level. + * @line_status: irq status. + */ +static void irqfd_set_spi(struct gzvm *gzvm, int irq_source_id, u32 irq, + int level, bool line_status) +{ + if (level) + gzvm_irqchip_inject_irq(gzvm, irq_source_id, 0, irq, level); +} + +/** + * irqfd_resampler_ack() - Notify all of the resampler irqfds using this G= SI + * when IRQ de-assert once. + * @ian: Pointer to gzvm_irq_ack_notifier. + * + * Since resampler irqfds share an IRQ source ID, we de-assert once + * then notify all of the resampler irqfds using this GSI. We can't + * do multiple de-asserts or we risk racing with incoming re-asserts. + */ +static void irqfd_resampler_ack(struct gzvm_irq_ack_notifier *ian) +{ + struct gzvm_kernel_irqfd_resampler *resampler; + struct gzvm *gzvm; + struct gzvm_kernel_irqfd *irqfd; + int idx; + + resampler =3D container_of(ian, + struct gzvm_kernel_irqfd_resampler, notifier); + gzvm =3D resampler->gzvm; + + irqfd_set_spi(gzvm, GZVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + resampler->notifier.gsi, 0, false); + + idx =3D srcu_read_lock(&gzvm->irq_srcu); + + list_for_each_entry_srcu(irqfd, &resampler->list, resampler_link, + srcu_read_lock_held(&gzvm->irq_srcu)) { + eventfd_signal(irqfd->resamplefd, 1); + } + + srcu_read_unlock(&gzvm->irq_srcu, idx); +} + +static void gzvm_register_irq_ack_notifier(struct gzvm *gzvm, + struct gzvm_irq_ack_notifier *ian) +{ + mutex_lock(&gzvm->irq_lock); + hlist_add_head_rcu(&ian->link, &gzvm->irq_ack_notifier_list); + mutex_unlock(&gzvm->irq_lock); +} + +static void gzvm_unregister_irq_ack_notifier(struct gzvm *gzvm, + struct gzvm_irq_ack_notifier *ian) +{ + mutex_lock(&gzvm->irq_lock); + hlist_del_init_rcu(&ian->link); + mutex_unlock(&gzvm->irq_lock); + synchronize_srcu(&gzvm->irq_srcu); +} + +static void irqfd_resampler_shutdown(struct gzvm_kernel_irqfd *irqfd) +{ + struct gzvm_kernel_irqfd_resampler *resampler =3D irqfd->resampler; + struct gzvm *gzvm =3D resampler->gzvm; + + mutex_lock(&gzvm->irqfds.resampler_lock); + + list_del_rcu(&irqfd->resampler_link); + synchronize_srcu(&gzvm->irq_srcu); + + if (list_empty(&resampler->list)) { + list_del(&resampler->link); + gzvm_unregister_irq_ack_notifier(gzvm, &resampler->notifier); + irqfd_set_spi(gzvm, GZVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + resampler->notifier.gsi, 0, false); + kfree(resampler); + } + + mutex_unlock(&gzvm->irqfds.resampler_lock); +} + +/** + * irqfd_shutdown() - Race-free decouple logic (ordering is critical). + * @work: Pointer to work_struct. + */ +static void irqfd_shutdown(struct work_struct *work) +{ + struct gzvm_kernel_irqfd *irqfd =3D + container_of(work, struct gzvm_kernel_irqfd, shutdown); + struct gzvm *gzvm =3D irqfd->gzvm; + u64 cnt; + + /* Make sure irqfd has been initialized in assign path. */ + synchronize_srcu(&gzvm->irq_srcu); + + /* + * Synchronize with the wait-queue and unhook ourselves to prevent + * further events. + */ + eventfd_ctx_remove_wait_queue(irqfd->eventfd, &irqfd->wait, &cnt); + + if (irqfd->resampler) { + irqfd_resampler_shutdown(irqfd); + eventfd_ctx_put(irqfd->resamplefd); + } + + /* + * It is now safe to release the object's resources + */ + eventfd_ctx_put(irqfd->eventfd); + kfree(irqfd); +} + +/** + * irqfd_is_active() - Assumes gzvm->irqfds.lock is held. + * @irqfd: Pointer to gzvm_kernel_irqfd. + */ +static bool irqfd_is_active(struct gzvm_kernel_irqfd *irqfd) +{ + return list_empty(&irqfd->list) ? false : true; +} + +/** + * irqfd_deactivate() - Mark the irqfd as inactive and schedule it for rem= oval. + * assumes gzvm->irqfds.lock is held. + * @irqfd: Pointer to gzvm_kernel_irqfd. + */ +static void irqfd_deactivate(struct gzvm_kernel_irqfd *irqfd) +{ + if (!irqfd_is_active(irqfd)) + return; + + list_del_init(&irqfd->list); + + queue_work(irqfd_cleanup_wq, &irqfd->shutdown); +} + +/** + * irqfd_wakeup() - Wake up irqfd to do virtual interrupt injection. + * @wait: Pointer to wait_queue_entry_t. + * @mode: + * @sync: + * @key: + */ +static int irqfd_wakeup(wait_queue_entry_t *wait, unsigned int mode, int s= ync, + void *key) +{ + struct gzvm_kernel_irqfd *irqfd =3D + container_of(wait, struct gzvm_kernel_irqfd, wait); + __poll_t flags =3D key_to_poll(key); + struct gzvm *gzvm =3D irqfd->gzvm; + + if (flags & EPOLLIN) { + u64 cnt; + + eventfd_ctx_do_read(irqfd->eventfd, &cnt); + /* gzvm's irq injection is not blocked, don't need workq */ + irqfd_set_spi(gzvm, GZVM_USERSPACE_IRQ_SOURCE_ID, irqfd->gsi, + 1, false); + } + + if (flags & EPOLLHUP) { + /* The eventfd is closing, detach from GZVM */ + unsigned long iflags; + + spin_lock_irqsave(&gzvm->irqfds.lock, iflags); + + /* + * Do more check if someone deactivated the irqfd before + * we could acquire the irqfds.lock. + */ + if (irqfd_is_active(irqfd)) + irqfd_deactivate(irqfd); + + spin_unlock_irqrestore(&gzvm->irqfds.lock, iflags); + } + + return 0; +} + +static void irqfd_ptable_queue_proc(struct file *file, wait_queue_head_t *= wqh, + poll_table *pt) +{ + struct gzvm_kernel_irqfd *irqfd =3D + container_of(pt, struct gzvm_kernel_irqfd, pt); + add_wait_queue_priority(wqh, &irqfd->wait); +} + +static int gzvm_irqfd_assign(struct gzvm *gzvm, struct gzvm_irqfd *args) +{ + struct gzvm_kernel_irqfd *irqfd, *tmp; + struct fd f; + struct eventfd_ctx *eventfd =3D NULL, *resamplefd =3D NULL; + int ret; + __poll_t events; + int idx; + + irqfd =3D kzalloc(sizeof(*irqfd), GFP_KERNEL_ACCOUNT); + if (!irqfd) + return -ENOMEM; + + irqfd->gzvm =3D gzvm; + irqfd->gsi =3D args->gsi; + irqfd->resampler =3D NULL; + + INIT_LIST_HEAD(&irqfd->list); + INIT_WORK(&irqfd->shutdown, irqfd_shutdown); + + f =3D fdget(args->fd); + if (!f.file) { + ret =3D -EBADF; + goto out; + } + + eventfd =3D eventfd_ctx_fileget(f.file); + if (IS_ERR(eventfd)) { + ret =3D PTR_ERR(eventfd); + goto fail; + } + + irqfd->eventfd =3D eventfd; + + if (args->flags & GZVM_IRQFD_FLAG_RESAMPLE) { + struct gzvm_kernel_irqfd_resampler *resampler; + + resamplefd =3D eventfd_ctx_fdget(args->resamplefd); + if (IS_ERR(resamplefd)) { + ret =3D PTR_ERR(resamplefd); + goto fail; + } + + irqfd->resamplefd =3D resamplefd; + INIT_LIST_HEAD(&irqfd->resampler_link); + + mutex_lock(&gzvm->irqfds.resampler_lock); + + list_for_each_entry(resampler, + &gzvm->irqfds.resampler_list, link) { + if (resampler->notifier.gsi =3D=3D irqfd->gsi) { + irqfd->resampler =3D resampler; + break; + } + } + + if (!irqfd->resampler) { + resampler =3D kzalloc(sizeof(*resampler), + GFP_KERNEL_ACCOUNT); + if (!resampler) { + ret =3D -ENOMEM; + mutex_unlock(&gzvm->irqfds.resampler_lock); + goto fail; + } + + resampler->gzvm =3D gzvm; + INIT_LIST_HEAD(&resampler->list); + resampler->notifier.gsi =3D irqfd->gsi; + resampler->notifier.irq_acked =3D irqfd_resampler_ack; + INIT_LIST_HEAD(&resampler->link); + + list_add(&resampler->link, &gzvm->irqfds.resampler_list); + gzvm_register_irq_ack_notifier(gzvm, + &resampler->notifier); + irqfd->resampler =3D resampler; + } + + list_add_rcu(&irqfd->resampler_link, &irqfd->resampler->list); + synchronize_srcu(&gzvm->irq_srcu); + + mutex_unlock(&gzvm->irqfds.resampler_lock); + } + + /* + * Install our own custom wake-up handling so we are notified via + * a callback whenever someone signals the underlying eventfd + */ + init_waitqueue_func_entry(&irqfd->wait, irqfd_wakeup); + init_poll_funcptr(&irqfd->pt, irqfd_ptable_queue_proc); + + spin_lock_irq(&gzvm->irqfds.lock); + + ret =3D 0; + list_for_each_entry(tmp, &gzvm->irqfds.items, list) { + if (irqfd->eventfd !=3D tmp->eventfd) + continue; + /* This fd is used for another irq already. */ + pr_err("already used: gsi=3D%d fd=3D%d\n", args->gsi, args->fd); + ret =3D -EBUSY; + spin_unlock_irq(&gzvm->irqfds.lock); + goto fail; + } + + idx =3D srcu_read_lock(&gzvm->irq_srcu); + + list_add_tail(&irqfd->list, &gzvm->irqfds.items); + + spin_unlock_irq(&gzvm->irqfds.lock); + + /* + * Check if there was an event already pending on the eventfd + * before we registered, and trigger it as if we didn't miss it. + */ + events =3D vfs_poll(f.file, &irqfd->pt); + + /* In case there is already a pending event */ + if (events & EPOLLIN) + irqfd_set_spi(gzvm, GZVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID, + irqfd->gsi, 1, false); + + srcu_read_unlock(&gzvm->irq_srcu, idx); + + /* + * do not drop the file until the irqfd is fully initialized, otherwise + * we might race against the EPOLLHUP + */ + fdput(f); + return 0; + +fail: + if (irqfd->resampler) + irqfd_resampler_shutdown(irqfd); + + if (resamplefd && !IS_ERR(resamplefd)) + eventfd_ctx_put(resamplefd); + + if (eventfd && !IS_ERR(eventfd)) + eventfd_ctx_put(eventfd); + + fdput(f); + +out: + kfree(irqfd); + return ret; +} + +static void gzvm_notify_acked_gsi(struct gzvm *gzvm, int gsi) +{ + struct gzvm_irq_ack_notifier *gian; + + hlist_for_each_entry_srcu(gian, &gzvm->irq_ack_notifier_list, + link, srcu_read_lock_held(&gzvm->irq_srcu)) + if (gian->gsi =3D=3D gsi) + gian->irq_acked(gian); +} + +void gzvm_notify_acked_irq(struct gzvm *gzvm, unsigned int gsi) +{ + int idx; + + idx =3D srcu_read_lock(&gzvm->irq_srcu); + gzvm_notify_acked_gsi(gzvm, gsi); + srcu_read_unlock(&gzvm->irq_srcu, idx); +} + +/** + * gzvm_irqfd_deassign() - Shutdown any irqfd's that match fd+gsi. + * @gzvm: Pointer to gzvm. + * @args: Pointer to gzvm_irqfd. + */ +static int gzvm_irqfd_deassign(struct gzvm *gzvm, struct gzvm_irqfd *args) +{ + struct gzvm_kernel_irqfd *irqfd, *tmp; + struct eventfd_ctx *eventfd; + + eventfd =3D eventfd_ctx_fdget(args->fd); + if (IS_ERR(eventfd)) + return PTR_ERR(eventfd); + + spin_lock_irq(&gzvm->irqfds.lock); + + list_for_each_entry_safe(irqfd, tmp, &gzvm->irqfds.items, list) { + if (irqfd->eventfd =3D=3D eventfd && irqfd->gsi =3D=3D args->gsi) + irqfd_deactivate(irqfd); + } + + spin_unlock_irq(&gzvm->irqfds.lock); + eventfd_ctx_put(eventfd); + + /* + * Block until we know all outstanding shutdown jobs have completed + * so that we guarantee there will not be any more interrupts on this + * gsi once this deassign function returns. + */ + flush_workqueue(irqfd_cleanup_wq); + + return 0; +} + +int gzvm_irqfd(struct gzvm *gzvm, struct gzvm_irqfd *args) +{ + if (args->flags & + ~(GZVM_IRQFD_FLAG_DEASSIGN | GZVM_IRQFD_FLAG_RESAMPLE)) + return -EINVAL; + + if (args->flags & GZVM_IRQFD_FLAG_DEASSIGN) + return gzvm_irqfd_deassign(gzvm, args); + + return gzvm_irqfd_assign(gzvm, args); +} + +/** + * gzvm_vm_irqfd_init() - Initialize irqfd data structure per VM + */ +int gzvm_vm_irqfd_init(struct gzvm *gzvm) +{ + mutex_init(&gzvm->irq_lock); + + spin_lock_init(&gzvm->irqfds.lock); + INIT_LIST_HEAD(&gzvm->irqfds.items); + INIT_LIST_HEAD(&gzvm->irqfds.resampler_list); + if (init_srcu_struct(&gzvm->irq_srcu)) + return -EINVAL; + INIT_HLIST_HEAD(&gzvm->irq_ack_notifier_list); + mutex_init(&gzvm->irqfds.resampler_lock); + + return 0; +} + +/** + * gzvm_vm_irqfd_release() - This function is called as the gzvm VM fd is = being + * released. Shutdown all irqfds that still remain open. + * @gzvm: Pointer to gzvm. + */ +void gzvm_vm_irqfd_release(struct gzvm *gzvm) +{ + struct gzvm_kernel_irqfd *irqfd, *tmp; + + spin_lock_irq(&gzvm->irqfds.lock); + + list_for_each_entry_safe(irqfd, tmp, &gzvm->irqfds.items, list) + irqfd_deactivate(irqfd); + + spin_unlock_irq(&gzvm->irqfds.lock); + + /* + * Block until we know all outstanding shutdown jobs have completed. + */ + flush_workqueue(irqfd_cleanup_wq); +} + +/** + * gzvm_drv_irqfd_init() - Erase flushing work items when a VM exits. + * + * Create a host-wide workqueue for issuing deferred shutdown requests + * aggregated from all vm* instances. We need our own isolated + * queue to ease flushing work items when a VM exits. + */ +int gzvm_drv_irqfd_init(void) +{ + irqfd_cleanup_wq =3D alloc_workqueue("gzvm-irqfd-cleanup", 0, 0); + if (!irqfd_cleanup_wq) + return -ENOMEM; + + return 0; +} + +void gzvm_drv_irqfd_exit(void) +{ + destroy_workqueue(irqfd_cleanup_wq); +} diff --git a/drivers/virt/geniezone/gzvm_main.c b/drivers/virt/geniezone/gz= vm_main.c index 230970cb0953..e62c046d76b3 100644 --- a/drivers/virt/geniezone/gzvm_main.c +++ b/drivers/virt/geniezone/gzvm_main.c @@ -113,11 +113,12 @@ static int gzvm_drv_probe(void) return ret; gzvm_debug_dev =3D &gzvm_dev; =20 - return 0; + return gzvm_drv_irqfd_init(); } =20 static int gzvm_drv_remove(void) { + gzvm_drv_irqfd_exit(); destroy_all_vm(); misc_deregister(&gzvm_dev); return 0; diff --git a/drivers/virt/geniezone/gzvm_vcpu.c b/drivers/virt/geniezone/gz= vm_vcpu.c index 5e9d34fcc1ea..94ead15fea3f 100644 --- a/drivers/virt/geniezone/gzvm_vcpu.c +++ b/drivers/virt/geniezone/gzvm_vcpu.c @@ -211,6 +211,7 @@ int gzvm_vm_ioctl_create_vcpu(struct gzvm *gzvm, u32 cp= uid) ret =3D -ENOMEM; goto free_vcpu; } + vcpu->hwstate =3D (void *)vcpu->run + PAGE_SIZE; vcpu->vcpuid =3D cpuid; vcpu->gzvm =3D gzvm; mutex_init(&vcpu->lock); diff --git a/drivers/virt/geniezone/gzvm_vm.c b/drivers/virt/geniezone/gzvm= _vm.c index 0cab67b0bdf8..eedc2d5c24ad 100644 --- a/drivers/virt/geniezone/gzvm_vm.c +++ b/drivers/virt/geniezone/gzvm_vm.c @@ -361,6 +361,15 @@ static long gzvm_vm_ioctl(struct file *filp, unsigned = int ioctl, ret =3D gzvm_vm_ioctl_create_device(gzvm, argp); break; } + case GZVM_IRQFD: { + struct gzvm_irqfd data; + + ret =3D -EFAULT; + if (copy_from_user(&data, argp, sizeof(data))) + goto out; + ret =3D gzvm_irqfd(gzvm, &data); + break; + } case GZVM_ENABLE_CAP: { struct gzvm_enable_cap cap; =20 @@ -385,6 +394,7 @@ static void gzvm_destroy_vm(struct gzvm *gzvm) =20 mutex_lock(&gzvm->lock); =20 + gzvm_vm_irqfd_release(gzvm); gzvm_destroy_vcpus(gzvm); gzvm_arch_destroy_vm(gzvm->vm_id); =20 @@ -430,6 +440,14 @@ static struct gzvm *gzvm_create_vm(unsigned long vm_ty= pe) gzvm->mm =3D current->mm; mutex_init(&gzvm->lock); =20 + ret =3D gzvm_vm_irqfd_init(gzvm); + if (ret) { + dev_err(gzvm_debug_dev->this_device, + "Failed to initialize irqfd\n"); + kfree(gzvm); + return ERR_PTR(ret); + } + mutex_lock(&gzvm_list_lock); list_add(&gzvm->vm_list, &gzvm_list); mutex_unlock(&gzvm_list_lock); diff --git a/include/linux/gzvm_drv.h b/include/linux/gzvm_drv.h index 842a026df9f3..54b0a3d443c5 100644 --- a/include/linux/gzvm_drv.h +++ b/include/linux/gzvm_drv.h @@ -11,6 +11,7 @@ #include #include #include +#include =20 #define MODULE_NAME "gzvm" #define GZVM_VCPU_MMAP_SIZE PAGE_SIZE @@ -26,6 +27,8 @@ #define ERR_NOT_SUPPORTED (-24) #define ERR_NOT_IMPLEMENTED (-27) #define ERR_FAULT (-40) +#define GZVM_USERSPACE_IRQ_SOURCE_ID 0 +#define GZVM_IRQFD_RESAMPLE_IRQ_SOURCE_ID 1 =20 /** * The following data structures are for data transferring between driver = and @@ -69,6 +72,7 @@ struct gzvm_vcpu { /* lock of vcpu*/ struct mutex lock; struct gzvm_vcpu_run *run; + struct gzvm_vcpu_hwstate *hwstate; }; =20 struct gzvm { @@ -78,8 +82,23 @@ struct gzvm { struct gzvm_memslot memslot[GZVM_MAX_MEM_REGION]; /* lock for list_add*/ struct mutex lock; + + struct { + /* lock for irqfds list operation */ + spinlock_t lock; + struct list_head items; + struct list_head resampler_list; + /* lock for irqfds resampler */ + struct mutex resampler_lock; + } irqfds; + struct list_head vm_list; gzvm_id_t vm_id; + + struct hlist_head irq_ack_notifier_list; + struct srcu_struct irq_srcu; + /* lock for irq injection */ + struct mutex irq_lock; }; =20 long gzvm_dev_ioctl_check_extension(struct gzvm *gzvm, unsigned long args); @@ -113,6 +132,14 @@ int gzvm_arch_create_device(gzvm_id_t vm_id, struct gz= vm_create_device *gzvm_dev int gzvm_arch_inject_irq(struct gzvm *gzvm, unsigned int vcpu_idx, u32 irq= _type, u32 irq, bool level); =20 +void gzvm_notify_acked_irq(struct gzvm *gzvm, unsigned int gsi); +int gzvm_irqfd(struct gzvm *gzvm, struct gzvm_irqfd *args); +int gzvm_drv_irqfd_init(void); +void gzvm_drv_irqfd_exit(void); +int gzvm_vm_irqfd_init(struct gzvm *gzvm); +void gzvm_vm_irqfd_release(struct gzvm *gzvm); +void gzvm_sync_hwstate(struct gzvm_vcpu *vcpu); + extern struct miscdevice *gzvm_debug_dev; =20 #endif /* __GZVM_DRV_H__ */ diff --git a/include/uapi/linux/gzvm.h b/include/uapi/linux/gzvm.h index 279b52192366..3f1e829f855d 100644 --- a/include/uapi/linux/gzvm.h +++ b/include/uapi/linux/gzvm.h @@ -224,4 +224,22 @@ struct gzvm_one_reg { =20 #define GZVM_REG_GENERIC 0x0000000000000000ULL =20 +#define GZVM_IRQFD_FLAG_DEASSIGN (1 << 0) +/** + * GZVM_IRQFD_FLAG_RESAMPLE indicates resamplefd is valid and specifies + * the irqfd to operate in resampling mode for level triggered interrupt + * emulation. + */ +#define GZVM_IRQFD_FLAG_RESAMPLE (1 << 1) + +struct gzvm_irqfd { + __u32 fd; + __u32 gsi; + __u32 flags; + __u32 resamplefd; + __u8 pad[16]; +}; + +#define GZVM_IRQFD _IOW(GZVM_IOC_MAGIC, 0x76, struct gzvm_irqfd) + #endif /* __GZVM_H__ */ --=20 2.18.0