From patchwork Thu Mar 12 13:36:52 2009 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Sheng Yang X-Patchwork-Id: 11375 Received: from vger.kernel.org (vger.kernel.org [209.132.176.167]) by demeter.kernel.org (8.14.2/8.14.2) with ESMTP id n2CDc9BA026123 for ; Thu, 12 Mar 2009 13:38:13 GMT Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1756795AbZCLNhj (ORCPT ); Thu, 12 Mar 2009 09:37:39 -0400 Received: (majordomo@vger.kernel.org) by vger.kernel.org id S1756062AbZCLNhi (ORCPT ); Thu, 12 Mar 2009 09:37:38 -0400 Received: from mga09.intel.com ([134.134.136.24]:13471 "EHLO mga09.intel.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1756548AbZCLNhG (ORCPT ); Thu, 12 Mar 2009 09:37:06 -0400 Received: from orsmga001.jf.intel.com ([10.7.209.18]) by orsmga102.jf.intel.com with ESMTP; 12 Mar 2009 06:29:14 -0700 X-ExtLoop1: 1 X-IronPort-AV: E=Sophos;i="4.38,350,1233561600"; d="scan'208";a="497229646" Received: from syang10-desktop.sh.intel.com (HELO syang10-desktop) ([10.239.13.189]) by orsmga001.jf.intel.com with ESMTP; 12 Mar 2009 06:36:39 -0700 Received: from yasker by syang10-desktop with local (Exim 4.69) (envelope-from ) id 1Lhl5o-0007tp-CI; Thu, 12 Mar 2009 21:37:00 +0800 From: Sheng Yang To: Avi Kivity , Marcelo Tosatti , Anthony Liguori Cc: kvm@vger.kernel.org, Sheng Yang , Alexander Duyck Subject: [PATCH 09/16] kvm: expose MSI capability to guest Date: Thu, 12 Mar 2009 21:36:52 +0800 Message-Id: <1236865019-30321-10-git-send-email-sheng@linux.intel.com> X-Mailer: git-send-email 1.5.6.3 In-Reply-To: <1236865019-30321-1-git-send-email-sheng@linux.intel.com> References: <1236865019-30321-1-git-send-email-sheng@linux.intel.com> Sender: kvm-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: kvm@vger.kernel.org (Alex: correct libpci usage) Signed-off-by: Sheng Yang Signed-off-by: Alexander Duyck --- qemu/hw/device-assignment.c | 140 ++++++++++++++++++++++++++++++++++++++++-- qemu/hw/device-assignment.h | 9 +++ 2 files changed, 142 insertions(+), 7 deletions(-) diff --git a/qemu/hw/device-assignment.c b/qemu/hw/device-assignment.c index a354681..bda0e95 100644 --- a/qemu/hw/device-assignment.c +++ b/qemu/hw/device-assignment.c @@ -265,7 +265,8 @@ static void assigned_dev_pci_write_config(PCIDevice *d, uint32_t address, } if ((address >= 0x10 && address <= 0x24) || address == 0x34 || - address == 0x3c || address == 0x3d) { + address == 0x3c || address == 0x3d || + pci_access_cap_config(d, address, len)) { /* used for update-mappings (BAR emulation) */ pci_default_write_config(d, address, val, len); return; @@ -299,7 +300,8 @@ static uint32_t assigned_dev_pci_read_config(PCIDevice *d, uint32_t address, AssignedDevice *pci_dev = container_of(d, AssignedDevice, dev); if ((address >= 0x10 && address <= 0x24) || address == 0x34 || - address == 0x3c || address == 0x3d) { + address == 0x3c || address == 0x3d || + pci_access_cap_config(d, address, len)) { val = pci_default_read_config(d, address, len); DEBUG("(%x.%x): address=%04x val=0x%08x len=%d\n", (d->devfn >> 3) & 0x1F, (d->devfn & 0x7), address, val, len); @@ -328,11 +330,13 @@ do_log: DEBUG("(%x.%x): address=%04x val=0x%08x len=%d\n", (d->devfn >> 3) & 0x1F, (d->devfn & 0x7), address, val, len); - /* kill the special capabilities */ - if (address == 4 && len == 4) - val &= ~0x100000; - else if (address == 6) - val &= ~0x10; + if (!pci_dev->cap.available) { + /* kill the special capabilities */ + if (address == 4 && len == 4) + val &= ~0x100000; + else if (address == 6) + val &= ~0x10; + } return val; } @@ -474,6 +478,19 @@ again: static LIST_HEAD(, AssignedDevInfo) adev_head; +#ifdef KVM_CAP_IRQ_ROUTING +static void free_dev_irq_entries(AssignedDevice *dev) +{ + int i; + + for (i = 0; i < dev->irq_entries_nr; i++) + kvm_del_routing_entry(kvm_context, &dev->entry[i]); + free(dev->entry); + dev->entry = NULL; + dev->irq_entries_nr = 0; +} +#endif + static void free_assigned_device(AssignedDevInfo *adev) { AssignedDevice *dev = adev->assigned_dev; @@ -506,6 +523,9 @@ static void free_assigned_device(AssignedDevInfo *adev) } pci_unregister_device(&dev->dev); +#ifdef KVM_CAP_IRQ_ROUTING + free_dev_irq_entries(dev); +#endif adev->assigned_dev = dev = NULL; } @@ -645,11 +665,108 @@ void assigned_dev_update_irqs() } } +#if defined(KVM_CAP_DEVICE_MSI) && defined (KVM_CAP_IRQ_ROUTING) +static void assigned_dev_update_msi(PCIDevice *pci_dev, unsigned int ctrl_pos) +{ + struct kvm_assigned_irq assigned_irq_data; + AssignedDevice *assigned_dev = container_of(pci_dev, AssignedDevice, dev); + uint8_t ctrl_byte = pci_dev->config[ctrl_pos]; + int r; + + memset(&assigned_irq_data, 0, sizeof assigned_irq_data); + assigned_irq_data.assigned_dev_id = + calc_assigned_dev_id(assigned_dev->h_busnr, + (uint8_t)assigned_dev->h_devfn); + + assigned_irq_data.flags = KVM_DEV_IRQ_HOST_MSI | KVM_DEV_IRQ_GUEST_MSI; + + free_dev_irq_entries(assigned_dev); + r = kvm_deassign_irq(kvm_context, &assigned_irq_data); + /* -ENXIO means no assigned irq */ + if (r && r != -ENXIO) + perror("assigned_dev_update_msi: deassign irq"); + + if (ctrl_byte & PCI_MSI_FLAGS_ENABLE) { + assigned_dev->entry = calloc(1, sizeof(struct kvm_irq_routing_entry)); + if (!assigned_dev->entry) { + perror("assigned_dev_update_msi: "); + return; + } + assigned_dev->entry->u.msi.address_lo = + *(uint32_t *)(pci_dev->config + pci_dev->cap.start + + PCI_MSI_ADDRESS_LO); + assigned_dev->entry->u.msi.address_hi = 0; + assigned_dev->entry->u.msi.data = *(uint16_t *)(pci_dev->config + + pci_dev->cap.start + PCI_MSI_DATA_32); + assigned_dev->entry->type = KVM_IRQ_ROUTING_MSI; + assigned_dev->entry->gsi = kvm_get_irq_route_gsi(kvm_context); + if (assigned_dev->entry->gsi < 0) { + perror("assigned_dev_update_msi: kvm_get_irq_route_gsi"); + return; + } + + kvm_add_routing_entry(kvm_context, assigned_dev->entry); + if (kvm_commit_irq_routes(kvm_context) < 0) { + perror("assigned_dev_update_msi: kvm_commit_irq_routes"); + assigned_dev->cap.state &= ~ASSIGNED_DEVICE_MSI_ENABLED; + return; + } + assigned_irq_data.guest_irq = assigned_dev->entry->gsi; + } + + if (ctrl_byte & PCI_MSI_FLAGS_ENABLE) + if (kvm_assign_irq(kvm_context, &assigned_irq_data) < 0) + perror("assigned_dev_enable_msi: assign irq"); +} +#endif + +static void assigned_device_pci_cap_write_config(PCIDevice *pci_dev, uint32_t address, + uint32_t val, int len) +{ + AssignedDevice *assigned_dev = container_of(pci_dev, AssignedDevice, dev); + unsigned int pos = pci_dev->cap.start, ctrl_pos; + + pci_default_cap_write_config(pci_dev, address, val, len); +#if defined(KVM_CAP_DEVICE_MSI) && defined (KVM_CAP_IRQ_ROUTING) + if (assigned_dev->cap.available & ASSIGNED_DEVICE_CAP_MSI) { + ctrl_pos = pos + PCI_MSI_FLAGS; + if (address <= ctrl_pos && address + len > ctrl_pos) + assigned_dev_update_msi(pci_dev, ctrl_pos); + pos += PCI_CAPABILITY_CONFIG_MSI_LENGTH; + } +#endif + return; +} + +static int assigned_device_pci_cap_init(PCIDevice *pci_dev) +{ + AssignedDevice *dev = container_of(pci_dev, AssignedDevice, dev); + int next_cap_pt = 0; + + pci_dev->cap.length = 0; +#if defined(KVM_CAP_DEVICE_MSI) && defined (KVM_CAP_IRQ_ROUTING) + /* Expose MSI capability + * MSI capability is the 1st capability in capability config */ + if (pci_find_cap_offset(dev->pdev, PCI_CAP_ID_MSI)) { + dev->cap.available |= ASSIGNED_DEVICE_CAP_MSI; + memset(&pci_dev->config[pci_dev->cap.start + pci_dev->cap.length], + 0, PCI_CAPABILITY_CONFIG_MSI_LENGTH); + pci_dev->config[pci_dev->cap.start + pci_dev->cap.length] = + PCI_CAP_ID_MSI; + pci_dev->cap.length += PCI_CAPABILITY_CONFIG_MSI_LENGTH; + next_cap_pt = 1; + } +#endif + + return 0; +} + struct PCIDevice *init_assigned_device(AssignedDevInfo *adev, PCIBus *bus) { int r; AssignedDevice *dev; PCIDevice *pci_dev; + struct pci_access *pacc; uint8_t e_device, e_intx; DEBUG("Registering real physical device %s (bus=%x dev=%x func=%x)\n", @@ -689,6 +806,10 @@ struct PCIDevice *init_assigned_device(AssignedDevInfo *adev, PCIBus *bus) dev->h_busnr = adev->bus; dev->h_devfn = PCI_DEVFN(adev->dev, adev->func); + pacc = pci_alloc(); + pci_init(pacc); + dev->pdev = pci_get_dev(pacc, 0, adev->bus, adev->dev, adev->func); + /* assign device to guest */ r = assign_device(adev); if (r < 0) @@ -699,6 +820,11 @@ struct PCIDevice *init_assigned_device(AssignedDevInfo *adev, PCIBus *bus) if (r < 0) goto assigned_out; + if (pci_enable_capability_support(pci_dev, 0, NULL, + assigned_device_pci_cap_write_config, + assigned_device_pci_cap_init) < 0) + goto assigned_out; + return &dev->dev; assigned_out: diff --git a/qemu/hw/device-assignment.h b/qemu/hw/device-assignment.h index 0fd78de..b1f2156 100644 --- a/qemu/hw/device-assignment.h +++ b/qemu/hw/device-assignment.h @@ -81,6 +81,15 @@ typedef struct { unsigned char h_busnr; unsigned int h_devfn; int bound; + struct pci_dev *pdev; + struct { +#define ASSIGNED_DEVICE_CAP_MSI (1 << 0) + uint32_t available; +#define ASSIGNED_DEVICE_MSI_ENABLED (1 << 0) + uint32_t state; + } cap; + int irq_entries_nr; + struct kvm_irq_routing_entry *entry; } AssignedDevice; typedef struct AssignedDevInfo AssignedDevInfo;