From patchwork Fri Jul 10 14:21:47 2015 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Andre Przywara X-Patchwork-Id: 6766401 Return-Path: X-Original-To: patchwork-kvm@patchwork.kernel.org Delivered-To: patchwork-parsemail@patchwork1.web.kernel.org Received: from mail.kernel.org (mail.kernel.org [198.145.29.136]) by patchwork1.web.kernel.org (Postfix) with ESMTP id 624EB9F2F0 for ; Fri, 10 Jul 2015 14:22:39 +0000 (UTC) Received: from mail.kernel.org (localhost [127.0.0.1]) by mail.kernel.org (Postfix) with ESMTP id 73C852069A for ; Fri, 10 Jul 2015 14:22:37 +0000 (UTC) Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by mail.kernel.org (Postfix) with ESMTP id 0327020681 for ; Fri, 10 Jul 2015 14:22:36 +0000 (UTC) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932899AbbGJOWb (ORCPT ); Fri, 10 Jul 2015 10:22:31 -0400 Received: from foss.arm.com ([217.140.101.70]:51241 "EHLO foss.arm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932863AbbGJOWQ (ORCPT ); Fri, 10 Jul 2015 10:22:16 -0400 Received: from usa-sjc-imap-foss1.foss.arm.com (unknown [10.72.51.249]) by usa-sjc-mx-foss1.foss.arm.com (Postfix) with ESMTP id 4F62B60A; Fri, 10 Jul 2015 07:22:40 -0700 (PDT) Received: from e104803-lin.lan (unknown [10.1.203.153]) by usa-sjc-imap-foss1.foss.arm.com (Postfix) with ESMTPSA id 2E5173F317; Fri, 10 Jul 2015 07:22:14 -0700 (PDT) From: Andre Przywara To: marc.zyngier@arm.com, christoffer.dall@linaro.org, kvmarm@lists.cs.columbia.edu Cc: eric.auger@linaro.org, Pavel Fedin , linux-arm-kernel@lists.infradead.org, kvm@vger.kernel.org Subject: [PATCH v2 11/15] KVM: arm64: handle pending bit for LPIs in ITS emulation Date: Fri, 10 Jul 2015 15:21:47 +0100 Message-Id: <1436538111-4294-12-git-send-email-andre.przywara@arm.com> X-Mailer: git-send-email 2.3.5 In-Reply-To: <1436538111-4294-1-git-send-email-andre.przywara@arm.com> References: <1436538111-4294-1-git-send-email-andre.przywara@arm.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org X-Spam-Status: No, score=-7.5 required=5.0 tests=BAYES_00, RCVD_IN_DNSWL_HI, RP_MATCHES_RCVD, UNPARSEABLE_RELAY autolearn=unavailable version=3.3.1 X-Spam-Checker-Version: SpamAssassin 3.3.1 (2010-03-16) on mail.kernel.org X-Virus-Scanned: ClamAV using ClamSMTP As the actual LPI number in a guest can be quite high, but is mostly assigned using a very sparse allocation scheme, bitmaps and arrays for storing the virtual interrupt status are a waste of memory. We use our equivalent of the "Interrupt Translation Table Entry" (ITTE) to hold this extra status information for a virtual LPI. As the normal VGIC code cannot use it's fancy bitmaps to manage pending interrupts, we provide a hook in the VGIC code to let the ITS emulation handle the list register queueing itself. LPIs are located in a separate number range (>=8192), so distinguishing them is easy. With LPIs being only edge-triggered, we get away with a less complex IRQ handling. Signed-off-by: Andre Przywara --- include/kvm/arm_vgic.h | 2 ++ virt/kvm/arm/its-emul.c | 71 ++++++++++++++++++++++++++++++++++++++++++++ virt/kvm/arm/its-emul.h | 3 ++ virt/kvm/arm/vgic-v3-emul.c | 2 ++ virt/kvm/arm/vgic.c | 72 ++++++++++++++++++++++++++++++++++----------- 5 files changed, 133 insertions(+), 17 deletions(-) diff --git a/include/kvm/arm_vgic.h b/include/kvm/arm_vgic.h index 1648668..2a67a10 100644 --- a/include/kvm/arm_vgic.h +++ b/include/kvm/arm_vgic.h @@ -147,6 +147,8 @@ struct vgic_vm_ops { int (*init_model)(struct kvm *); void (*destroy_model)(struct kvm *); int (*map_resources)(struct kvm *, const struct vgic_params *); + bool (*queue_lpis)(struct kvm_vcpu *); + void (*unqueue_lpi)(struct kvm_vcpu *, int irq); }; struct vgic_io_device { diff --git a/virt/kvm/arm/its-emul.c b/virt/kvm/arm/its-emul.c index 7f217fa..b9c40d7 100644 --- a/virt/kvm/arm/its-emul.c +++ b/virt/kvm/arm/its-emul.c @@ -50,8 +50,26 @@ struct its_itte { struct its_collection *collection; u32 lpi; u32 event_id; + bool enabled; + unsigned long *pending; }; +#define for_each_lpi(dev, itte, kvm) \ + list_for_each_entry(dev, &(kvm)->arch.vgic.its.device_list, dev_list) \ + list_for_each_entry(itte, &(dev)->itt, itte_list) + +static struct its_itte *find_itte_by_lpi(struct kvm *kvm, int lpi) +{ + struct its_device *device; + struct its_itte *itte; + + for_each_lpi(device, itte, kvm) { + if (itte->lpi == lpi) + return itte; + } + return NULL; +} + #define BASER_BASE_ADDRESS(x) ((x) & 0xfffffffff000ULL) /* The distributor lock is held by the VGIC MMIO handler. */ @@ -145,6 +163,59 @@ static bool handle_mmio_gits_idregs(struct kvm_vcpu *vcpu, return false; } +/* + * Find all enabled and pending LPIs and queue them into the list + * registers. + * The dist lock is held by the caller. + */ +bool vits_queue_lpis(struct kvm_vcpu *vcpu) +{ + struct vgic_its *its = &vcpu->kvm->arch.vgic.its; + struct its_device *device; + struct its_itte *itte; + bool ret = true; + + if (!vgic_has_its(vcpu->kvm)) + return true; + if (!its->enabled || !vcpu->kvm->arch.vgic.lpis_enabled) + return true; + + spin_lock(&its->lock); + for_each_lpi(device, itte, vcpu->kvm) { + if (!itte->enabled || !test_bit(vcpu->vcpu_id, itte->pending)) + continue; + + if (!itte->collection) + continue; + + if (itte->collection->target_addr != vcpu->vcpu_id) + continue; + + __clear_bit(vcpu->vcpu_id, itte->pending); + + ret &= vgic_queue_irq(vcpu, 0, itte->lpi); + } + + spin_unlock(&its->lock); + return ret; +} + +/* Called with the distributor lock held by the caller. */ +void vits_unqueue_lpi(struct kvm_vcpu *vcpu, int lpi) +{ + struct vgic_its *its = &vcpu->kvm->arch.vgic.its; + struct its_itte *itte; + + spin_lock(&its->lock); + + /* Find the right ITTE and put the pending state back in there */ + itte = find_itte_by_lpi(vcpu->kvm, lpi); + if (itte) + __set_bit(vcpu->vcpu_id, itte->pending); + + spin_unlock(&its->lock); +} + static int vits_handle_command(struct kvm_vcpu *vcpu, u64 *its_cmd) { return -ENODEV; diff --git a/virt/kvm/arm/its-emul.h b/virt/kvm/arm/its-emul.h index 472a6d0..cc5d5ff 100644 --- a/virt/kvm/arm/its-emul.h +++ b/virt/kvm/arm/its-emul.h @@ -33,4 +33,7 @@ void vgic_enable_lpis(struct kvm_vcpu *vcpu); int vits_init(struct kvm *kvm); void vits_destroy(struct kvm *kvm); +bool vits_queue_lpis(struct kvm_vcpu *vcpu); +void vits_unqueue_lpi(struct kvm_vcpu *vcpu, int irq); + #endif diff --git a/virt/kvm/arm/vgic-v3-emul.c b/virt/kvm/arm/vgic-v3-emul.c index 49be3c3..4132c26 100644 --- a/virt/kvm/arm/vgic-v3-emul.c +++ b/virt/kvm/arm/vgic-v3-emul.c @@ -948,6 +948,8 @@ void vgic_v3_init_emulation(struct kvm *kvm) dist->vm_ops.init_model = vgic_v3_init_model; dist->vm_ops.destroy_model = vgic_v3_destroy_model; dist->vm_ops.map_resources = vgic_v3_map_resources; + dist->vm_ops.queue_lpis = vits_queue_lpis; + dist->vm_ops.unqueue_lpi = vits_unqueue_lpi; dist->vgic_dist_base = VGIC_ADDR_UNDEF; dist->vgic_redist_base = VGIC_ADDR_UNDEF; diff --git a/virt/kvm/arm/vgic.c b/virt/kvm/arm/vgic.c index 49ee92b..9dfd094 100644 --- a/virt/kvm/arm/vgic.c +++ b/virt/kvm/arm/vgic.c @@ -95,6 +95,20 @@ static bool queue_sgi(struct kvm_vcpu *vcpu, int irq) return vcpu->kvm->arch.vgic.vm_ops.queue_sgi(vcpu, irq); } +static bool vgic_queue_lpis(struct kvm_vcpu *vcpu) +{ + if (vcpu->kvm->arch.vgic.vm_ops.queue_lpis) + return vcpu->kvm->arch.vgic.vm_ops.queue_lpis(vcpu); + else + return true; +} + +static void vgic_unqueue_lpi(struct kvm_vcpu *vcpu, int irq) +{ + if (vcpu->kvm->arch.vgic.vm_ops.unqueue_lpi) + vcpu->kvm->arch.vgic.vm_ops.unqueue_lpi(vcpu, irq); +} + int kvm_vgic_map_resources(struct kvm *kvm) { return kvm->arch.vgic.vm_ops.map_resources(kvm, vgic); @@ -1135,6 +1149,10 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu) for_each_clear_bit(lr, elrsr_ptr, vgic->nr_lr) { vlr = vgic_get_lr(vcpu, lr); + /* We don't care about LPIs here */ + if (vlr.irq >= 8192) + continue; + if (!vgic_irq_is_enabled(vcpu, vlr.irq)) { vlr.state = 0; vgic_set_lr(vcpu, lr, vlr); @@ -1147,25 +1165,33 @@ static void vgic_retire_disabled_irqs(struct kvm_vcpu *vcpu) static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, int lr_nr, int sgi_source_id) { + struct vgic_dist *dist = &vcpu->kvm->arch.vgic; struct vgic_lr vlr; vlr.state = 0; vlr.irq = irq; vlr.source = sgi_source_id; - if (vgic_irq_is_active(vcpu, irq)) { - vlr.state |= LR_STATE_ACTIVE; - kvm_debug("Set active, clear distributor: 0x%x\n", vlr.state); - vgic_irq_clear_active(vcpu, irq); - vgic_update_state(vcpu->kvm); - } else if (vgic_dist_irq_is_pending(vcpu, irq)) { - vlr.state |= LR_STATE_PENDING; - kvm_debug("Set pending: 0x%x\n", vlr.state); - } - - if (!vgic_irq_is_edge(vcpu, irq)) - vlr.state |= LR_EOI_INT; + /* We care only about state for SGIs/PPIs/SPIs, not for LPIs */ + if (irq < dist->nr_irqs) { + if (vgic_irq_is_active(vcpu, irq)) { + vlr.state |= LR_STATE_ACTIVE; + kvm_debug("Set active, clear distributor: 0x%x\n", + vlr.state); + vgic_irq_clear_active(vcpu, irq); + vgic_update_state(vcpu->kvm); + } else if (vgic_dist_irq_is_pending(vcpu, irq)) { + vlr.state |= LR_STATE_PENDING; + kvm_debug("Set pending: 0x%x\n", vlr.state); + } + if (!vgic_irq_is_edge(vcpu, irq)) + vlr.state |= LR_EOI_INT; + } else { + /* If this is an LPI, it can only be pending */ + if (irq >= 8192) + vlr.state |= LR_STATE_PENDING; + } vgic_set_lr(vcpu, lr_nr, vlr); vgic_sync_lr_elrsr(vcpu, lr_nr, vlr); } @@ -1177,7 +1203,6 @@ static void vgic_queue_irq_to_lr(struct kvm_vcpu *vcpu, int irq, */ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) { - struct vgic_dist *dist = &vcpu->kvm->arch.vgic; u64 elrsr = vgic_get_elrsr(vcpu); unsigned long *elrsr_ptr = u64_to_bitmask(&elrsr); int lr; @@ -1185,7 +1210,6 @@ bool vgic_queue_irq(struct kvm_vcpu *vcpu, u8 sgi_source_id, int irq) /* Sanitize the input... */ BUG_ON(sgi_source_id & ~7); BUG_ON(sgi_source_id && irq >= VGIC_NR_SGIS); - BUG_ON(irq >= dist->nr_irqs); kvm_debug("Queue IRQ%d\n", irq); @@ -1265,8 +1289,12 @@ static void __kvm_vgic_flush_hwstate(struct kvm_vcpu *vcpu) overflow = 1; } - - + /* + * LPIs are not mapped in our bitmaps, so we leave the iteration + * to the ITS emulation code. + */ + if (!vgic_queue_lpis(vcpu)) + overflow = 1; epilog: if (overflow) { @@ -1387,6 +1415,16 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) for_each_clear_bit(lr_nr, elrsr_ptr, vgic_cpu->nr_lr) { vlr = vgic_get_lr(vcpu, lr_nr); + /* LPIs are handled separately */ + if (vlr.irq >= 8192) { + /* We just need to take care about still pending LPIs */ + if (vlr.state & LR_STATE_PENDING) { + vgic_unqueue_lpi(vcpu, vlr.irq); + pending = true; + } + continue; + } + BUG_ON(!(vlr.state & LR_STATE_MASK)); pending = true; @@ -1411,7 +1449,7 @@ static void __kvm_vgic_sync_hwstate(struct kvm_vcpu *vcpu) } vgic_update_state(vcpu->kvm); - /* vgic_update_state would not cover only-active IRQs */ + /* vgic_update_state would not cover only-active IRQs or LPIs */ if (pending) set_bit(vcpu->vcpu_id, dist->irq_pending_on_cpu); }