From patchwork Tue May 22 05:05:36 2012 Content-Type: text/plain; charset="utf-8" MIME-Version: 1.0 Content-Transfer-Encoding: 7bit X-Patchwork-Submitter: Alex Williamson X-Patchwork-Id: 160533 Return-Path: X-Original-To: incoming@patchwork.ozlabs.org Delivered-To: patchwork-incoming@bilbo.ozlabs.org Received: from vger.kernel.org (vger.kernel.org [209.132.180.67]) by ozlabs.org (Postfix) with ESMTP id 6540CB6FA2 for ; Tue, 22 May 2012 15:08:54 +1000 (EST) Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S932839Ab2EVFHz (ORCPT ); Tue, 22 May 2012 01:07:55 -0400 Received: from mx1.redhat.com ([209.132.183.28]:35732 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S932861Ab2EVFGA (ORCPT ); Tue, 22 May 2012 01:06:00 -0400 Received: from int-mx10.intmail.prod.int.phx2.redhat.com (int-mx10.intmail.prod.int.phx2.redhat.com [10.5.11.23]) by mx1.redhat.com (8.14.4/8.14.4) with ESMTP id q4M55caX029518 (version=TLSv1/SSLv3 cipher=DHE-RSA-AES256-SHA bits=256 verify=OK); Tue, 22 May 2012 01:05:38 -0400 Received: from bling.home (ovpn-113-40.phx2.redhat.com [10.3.113.40]) by int-mx10.intmail.prod.int.phx2.redhat.com (8.14.4/8.14.4) with ESMTP id q4M55anm028824; Tue, 22 May 2012 01:05:37 -0400 From: Alex Williamson Subject: [PATCH v2 09/13] vfio: x86 IOMMU implementation To: benh@kernel.crashing.org, aik@ozlabs.ru, david@gibson.dropbear.id.au, joerg.roedel@amd.com, dwmw2@infradead.org Cc: chrisw@sous-sol.org, agraf@suse.de, benve@cisco.com, aafabbri@cisco.com, B08248@freescale.com, B07421@freescale.com, avi@redhat.com, konrad.wilk@oracle.com, kvm@vger.kernel.org, qemu-devel@nongnu.org, iommu@lists.linux-foundation.org, linux-pci@vger.kernel.org, linux-kernel@vger.kernel.org, gregkh@linuxfoundation.org, bhelgaas@google.com, ddutile@redhat.com, alex.williamson@redhat.com Date: Mon, 21 May 2012 23:05:36 -0600 Message-ID: <20120522050536.5871.65171.stgit@bling.home> In-Reply-To: <20120522043607.5871.11340.stgit@bling.home> References: <20120522043607.5871.11340.stgit@bling.home> User-Agent: StGIT/0.14.3 MIME-Version: 1.0 X-Scanned-By: MIMEDefang 2.68 on 10.5.11.23 Sender: linux-pci-owner@vger.kernel.org Precedence: bulk List-ID: X-Mailing-List: linux-pci@vger.kernel.org x86 is probably the wrong name for this VFIO IOMMU driver, but x86 is the primary target for it. This driver support a very simple usage model using the existing IOMMU API. The IOMMU is expected to support the full host address space with no special IOVA windows, number of mappings restrictions, or unique processor target options. Signed-off-by: Alex Williamson --- Documentation/ioctl/ioctl-number.txt | 2 drivers/vfio/Kconfig | 6 drivers/vfio/Makefile | 2 drivers/vfio/vfio.c | 7 drivers/vfio/vfio_iommu_x86.c | 743 ++++++++++++++++++++++++++++++++++ include/linux/vfio.h | 52 ++ 6 files changed, 811 insertions(+), 1 deletions(-) create mode 100644 drivers/vfio/vfio_iommu_x86.c -- To unsubscribe from this list: send the line "unsubscribe linux-pci" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html diff --git a/Documentation/ioctl/ioctl-number.txt b/Documentation/ioctl/ioctl-number.txt index 111e30a..9d1694e 100644 --- a/Documentation/ioctl/ioctl-number.txt +++ b/Documentation/ioctl/ioctl-number.txt @@ -88,7 +88,7 @@ Code Seq#(hex) Include File Comments and kernel/power/user.c '8' all SNP8023 advanced NIC card -';' 64-6F linux/vfio.h +';' 64-72 linux/vfio.h '@' 00-0F linux/radeonfb.h conflict! '@' 00-0F drivers/video/aty/aty128fb.c conflict! 'A' 00-1F linux/apm_bios.h conflict! diff --git a/drivers/vfio/Kconfig b/drivers/vfio/Kconfig index 9acb1e7..bd88a30 100644 --- a/drivers/vfio/Kconfig +++ b/drivers/vfio/Kconfig @@ -1,6 +1,12 @@ +config VFIO_IOMMU_X86 + tristate + depends on VFIO && X86 + default n + menuconfig VFIO tristate "VFIO Non-Privileged userspace driver framework" depends on IOMMU_API + select VFIO_IOMMU_X86 if X86 help VFIO provides a framework for secure userspace device drivers. See Documentation/vfio.txt for more details. diff --git a/drivers/vfio/Makefile b/drivers/vfio/Makefile index 7500a67..1f1abee 100644 --- a/drivers/vfio/Makefile +++ b/drivers/vfio/Makefile @@ -1 +1,3 @@ obj-$(CONFIG_VFIO) += vfio.o +obj-$(CONFIG_VFIO_IOMMU_X86) += vfio_iommu_x86.o +obj-$(CONFIG_VFIO_PCI) += pci/ diff --git a/drivers/vfio/vfio.c b/drivers/vfio/vfio.c index 6558eef..89899a8 100644 --- a/drivers/vfio/vfio.c +++ b/drivers/vfio/vfio.c @@ -1369,6 +1369,13 @@ static int __init vfio_init(void) pr_info(DRIVER_DESC " version: " DRIVER_VERSION "\n"); + /* + * Attempt to load known iommu-drivers. This gives us a working + * environment without the user needing to explicitly load iommu + * drivers. + */ + request_module_nowait("vfio_iommu_x86"); + return 0; err_groups_cdev: diff --git a/drivers/vfio/vfio_iommu_x86.c b/drivers/vfio/vfio_iommu_x86.c new file mode 100644 index 0000000..a52391d --- /dev/null +++ b/drivers/vfio/vfio_iommu_x86.c @@ -0,0 +1,743 @@ +/* + * VFIO: IOMMU DMA mapping support for x86 (Intel VT-d & AMD-Vi) + * + * Copyright (C) 2012 Red Hat, Inc. All rights reserved. + * Author: Alex Williamson + * + * This program is free software; you can redistribute it and/or modify + * it under the terms of the GNU General Public License version 2 as + * published by the Free Software Foundation. + * + * Derived from original vfio: + * Copyright 2010 Cisco Systems, Inc. All rights reserved. + * Author: Tom Lyon, pugs@cisco.com + */ + +#include +#include +#include +#include +#include +#include +#include /* pci_bus_type */ +#include +#include +#include +#include +#include + +#define DRIVER_VERSION "0.2" +#define DRIVER_AUTHOR "Alex Williamson " +#define DRIVER_DESC "x86 IOMMU driver for VFIO" + +static bool allow_unsafe_interrupts; +module_param_named(allow_unsafe_interrupts, + allow_unsafe_interrupts, bool, S_IRUGO | S_IWUSR); +MODULE_PARM_DESC(allow_unsafe_interrupts, + "Enable VFIO IOMMU support for on platforms without interrupt remapping support."); + +struct vfio_iommu { + struct iommu_domain *domain; + struct mutex lock; + struct list_head dma_list; + struct list_head group_list; + bool cache; +}; + +struct vfio_dma { + struct list_head next; + dma_addr_t iova; /* Device address */ + unsigned long vaddr; /* Process virtual addr */ + long npage; /* Number of pages */ + int prot; /* IOMMU_READ/WRITE */ +}; + +struct vfio_group { + struct iommu_group *iommu_group; + struct list_head next; +}; + +/* + * This code handles mapping and unmapping of user data buffers + * into DMA'ble space using the IOMMU + */ + +#define NPAGE_TO_SIZE(npage) ((size_t)(npage) << PAGE_SHIFT) + +struct vwork { + struct mm_struct *mm; + long npage; + struct work_struct work; +}; + +/* delayed decrement/increment for locked_vm */ +static void vfio_lock_acct_bg(struct work_struct *work) +{ + struct vwork *vwork = container_of(work, struct vwork, work); + struct mm_struct *mm; + + mm = vwork->mm; + down_write(&mm->mmap_sem); + mm->locked_vm += vwork->npage; + up_write(&mm->mmap_sem); + mmput(mm); + kfree(vwork); +} + +static void vfio_lock_acct(long npage) +{ + struct vwork *vwork; + struct mm_struct *mm; + + if (!current->mm) + return; /* process exited */ + + if (down_write_trylock(¤t->mm->mmap_sem)) { + current->mm->locked_vm += npage; + up_write(¤t->mm->mmap_sem); + return; + } + + /* + * Couldn't get mmap_sem lock, so must setup to update + * mm->locked_vm later. If locked_vm were atomic, we + * wouldn't need this silliness + */ + vwork = kmalloc(sizeof(struct vwork), GFP_KERNEL); + if (!vwork) + return; + mm = get_task_mm(current); + if (!mm) { + kfree(vwork); + return; + } + INIT_WORK(&vwork->work, vfio_lock_acct_bg); + vwork->mm = mm; + vwork->npage = npage; + schedule_work(&vwork->work); +} + +/* + * Some mappings aren't backed by a struct page, for example an mmap'd + * MMIO range for our own or another device. These use a different + * pfn conversion and shouldn't be tracked as locked pages. + */ +static bool is_invalid_reserved_pfn(unsigned long pfn) +{ + if (pfn_valid(pfn)) { + bool reserved; + struct page *tail = pfn_to_page(pfn); + struct page *head = compound_trans_head(tail); + reserved = !!(PageReserved(head)); + if (head != tail) { + /* + * "head" is not a dangling pointer + * (compound_trans_head takes care of that) + * but the hugepage may have been split + * from under us (and we may not hold a + * reference count on the head page so it can + * be reused before we run PageReferenced), so + * we've to check PageTail before returning + * what we just read. + */ + smp_rmb(); + if (PageTail(tail)) + return reserved; + } + return PageReserved(tail); + } + + return true; +} + +static int put_pfn(unsigned long pfn, int prot) +{ + if (!is_invalid_reserved_pfn(pfn)) { + struct page *page = pfn_to_page(pfn); + if (prot & IOMMU_WRITE) + SetPageDirty(page); + put_page(page); + return 1; + } + return 0; +} + +/* Unmap DMA region */ +static long __vfio_dma_do_unmap(struct vfio_iommu *iommu, dma_addr_t iova, + long npage, int prot) +{ + long i, unlocked = 0; + + for (i = 0; i < npage; i++, iova += PAGE_SIZE) { + unsigned long pfn; + + pfn = iommu_iova_to_phys(iommu->domain, iova) >> PAGE_SHIFT; + if (pfn) { + iommu_unmap(iommu->domain, iova, PAGE_SIZE); + unlocked += put_pfn(pfn, prot); + } + } + return unlocked; +} + +static void vfio_dma_unmap(struct vfio_iommu *iommu, dma_addr_t iova, + long npage, int prot) +{ + long unlocked; + + unlocked = __vfio_dma_do_unmap(iommu, iova, npage, prot); + vfio_lock_acct(-unlocked); +} + +static int vaddr_get_pfn(unsigned long vaddr, int prot, unsigned long *pfn) +{ + struct page *page[1]; + struct vm_area_struct *vma; + int ret = -EFAULT; + + if (get_user_pages_fast(vaddr, 1, !!(prot & IOMMU_WRITE), page) == 1) { + *pfn = page_to_pfn(page[0]); + return 0; + } + + down_read(¤t->mm->mmap_sem); + + vma = find_vma_intersection(current->mm, vaddr, vaddr + 1); + + if (vma && vma->vm_flags & VM_PFNMAP) { + *pfn = ((vaddr - vma->vm_start) >> PAGE_SHIFT) + vma->vm_pgoff; + if (is_invalid_reserved_pfn(*pfn)) + ret = 0; + } + + up_read(¤t->mm->mmap_sem); + + return ret; +} + +/* Map DMA region */ +static int __vfio_dma_map(struct vfio_iommu *iommu, dma_addr_t iova, + unsigned long vaddr, long npage, int prot) +{ + dma_addr_t start = iova; + long i, locked = 0; + int ret; + + /* Verify that pages are not already mapped */ + for (i = 0; i < npage; i++, iova += PAGE_SIZE) + if (iommu_iova_to_phys(iommu->domain, iova)) + return -EBUSY; + + iova = start; + + if (iommu->cache) + prot |= IOMMU_CACHE; + + /* + * XXX We break mappings into pages and use get_user_pages_fast to + * pin the pages in memory. It's been suggested that mlock might + * provide a more efficient mechanism, but nothing prevents the + * user from munlocking the pages, which could then allow the user + * access to random host memory. We also have no guarantee from the + * IOMMU API that the iommu driver can unmap sub-pages of previous + * mappings. This means we might lose an entire range if a single + * page within it is unmapped. Single page mappings are inefficient, + * but provide the most flexibility for now. + */ + for (i = 0; i < npage; i++, iova += PAGE_SIZE, vaddr += PAGE_SIZE) { + unsigned long pfn = 0; + + ret = vaddr_get_pfn(vaddr, prot, &pfn); + if (ret) { + __vfio_dma_do_unmap(iommu, start, i, prot); + return ret; + } + + /* + * Only add actual locked pages to accounting + * XXX We're effectively marking a page locked for every + * IOVA page even though it's possible the user could be + * backing multiple IOVAs with the same vaddr. This over- + * penalizes the user process, but we currently have no + * easy way to do this properly. + */ + if (!is_invalid_reserved_pfn(pfn)) + locked++; + + ret = iommu_map(iommu->domain, iova, + (phys_addr_t)pfn << PAGE_SHIFT, + PAGE_SIZE, prot); + if (ret) { + /* Back out mappings on error */ + put_pfn(pfn, prot); + __vfio_dma_do_unmap(iommu, start, i, prot); + return ret; + } + } + vfio_lock_acct(locked); + return 0; +} + +static inline bool ranges_overlap(dma_addr_t start1, size_t size1, + dma_addr_t start2, size_t size2) +{ + if (start1 < start2) + return (start2 - start1 < size1); + else if (start2 < start1) + return (start1 - start2 < size2); + return (size1 > 0 && size2 > 0); +} + +static struct vfio_dma *vfio_find_dma(struct vfio_iommu *iommu, + dma_addr_t start, size_t size) +{ + struct vfio_dma *dma; + + list_for_each_entry(dma, &iommu->dma_list, next) { + if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage), + start, size)) + return dma; + } + return NULL; +} + +static long vfio_remove_dma_overlap(struct vfio_iommu *iommu, dma_addr_t start, + size_t size, struct vfio_dma *dma) +{ + struct vfio_dma *split; + long npage_lo, npage_hi; + + /* Existing dma region is completely covered, unmap all */ + if (start <= dma->iova && + start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) { + vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot); + list_del(&dma->next); + npage_lo = dma->npage; + kfree(dma); + return npage_lo; + } + + /* Overlap low address of existing range */ + if (start <= dma->iova) { + size_t overlap; + + overlap = start + size - dma->iova; + npage_lo = overlap >> PAGE_SHIFT; + + vfio_dma_unmap(iommu, dma->iova, npage_lo, dma->prot); + dma->iova += overlap; + dma->vaddr += overlap; + dma->npage -= npage_lo; + return npage_lo; + } + + /* Overlap high address of existing range */ + if (start + size >= dma->iova + NPAGE_TO_SIZE(dma->npage)) { + size_t overlap; + + overlap = dma->iova + NPAGE_TO_SIZE(dma->npage) - start; + npage_hi = overlap >> PAGE_SHIFT; + + vfio_dma_unmap(iommu, start, npage_hi, dma->prot); + dma->npage -= npage_hi; + return npage_hi; + } + + /* Split existing */ + npage_lo = (start - dma->iova) >> PAGE_SHIFT; + npage_hi = dma->npage - (size >> PAGE_SHIFT) - npage_lo; + + split = kzalloc(sizeof *split, GFP_KERNEL); + if (!split) + return -ENOMEM; + + vfio_dma_unmap(iommu, start, size >> PAGE_SHIFT, dma->prot); + + dma->npage = npage_lo; + + split->npage = npage_hi; + split->iova = start + size; + split->vaddr = dma->vaddr + NPAGE_TO_SIZE(npage_lo) + size; + split->prot = dma->prot; + list_add(&split->next, &iommu->dma_list); + return size >> PAGE_SHIFT; +} + +static int vfio_dma_do_unmap(struct vfio_iommu *iommu, + struct vfio_iommu_x86_dma_unmap *unmap) +{ + long ret = 0, npage = unmap->size >> PAGE_SHIFT; + struct vfio_dma *dma, *tmp; + uint64_t mask; + + mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1; + + if (unmap->iova & mask) + return -EINVAL; + if (unmap->size & mask) + return -EINVAL; + + /* XXX We still break these down into PAGE_SIZE */ + WARN_ON(mask & PAGE_MASK); + + mutex_lock(&iommu->lock); + + list_for_each_entry_safe(dma, tmp, &iommu->dma_list, next) { + if (ranges_overlap(dma->iova, NPAGE_TO_SIZE(dma->npage), + unmap->iova, unmap->size)) { + ret = vfio_remove_dma_overlap(iommu, unmap->iova, + unmap->size, dma); + if (ret > 0) + npage -= ret; + if (ret < 0 || npage == 0) + break; + } + } + mutex_unlock(&iommu->lock); + return ret > 0 ? 0 : (int)ret; +} + +static int vfio_dma_do_map(struct vfio_iommu *iommu, + struct vfio_iommu_x86_dma_map *map) +{ + struct vfio_dma *dma, *pdma = NULL; + dma_addr_t iova = map->iova; + unsigned long locked, lock_limit, vaddr = map->vaddr; + size_t size = map->size; + int ret = 0, prot = 0; + uint64_t mask; + long npage; + + mask = ((uint64_t)1 << __ffs(iommu->domain->ops->pgsize_bitmap)) - 1; + + /* READ/WRITE from device perspective */ + if (map->flags & VFIO_DMA_MAP_FLAG_WRITE) + prot |= IOMMU_WRITE; + if (map->flags & VFIO_DMA_MAP_FLAG_READ) + prot |= IOMMU_READ; + + if (!prot) + return -EINVAL; /* No READ/WRITE? */ + + if (vaddr & mask) + return -EINVAL; + if (iova & mask) + return -EINVAL; + if (size & mask) + return -EINVAL; + + /* XXX We still break these down into PAGE_SIZE */ + WARN_ON(mask & PAGE_MASK); + + /* Don't allow IOVA wrap */ + if (iova + size && iova + size < iova) + return -EINVAL; + + /* Don't allow virtual address wrap */ + if (vaddr + size && vaddr + size < vaddr) + return -EINVAL; + + npage = size >> PAGE_SHIFT; + if (!npage) + return -EINVAL; + + mutex_lock(&iommu->lock); + + if (vfio_find_dma(iommu, iova, size)) { + ret = -EBUSY; + goto out_lock; + } + + /* account for locked pages */ + locked = current->mm->locked_vm + npage; + lock_limit = rlimit(RLIMIT_MEMLOCK) >> PAGE_SHIFT; + if (locked > lock_limit && !capable(CAP_IPC_LOCK)) { + printk(KERN_WARNING "%s: RLIMIT_MEMLOCK (%ld) exceeded\n", + __func__, rlimit(RLIMIT_MEMLOCK)); + ret = -ENOMEM; + goto out_lock; + } + + ret = __vfio_dma_map(iommu, iova, vaddr, npage, prot); + if (ret) + goto out_lock; + + /* Check if we abut a region below - nothing below 0 */ + if (iova) { + dma = vfio_find_dma(iommu, iova - 1, 1); + if (dma && dma->prot == prot && + dma->vaddr + NPAGE_TO_SIZE(dma->npage) == vaddr) { + + dma->npage += npage; + iova = dma->iova; + vaddr = dma->vaddr; + npage = dma->npage; + size = NPAGE_TO_SIZE(npage); + + pdma = dma; + } + } + + /* Check if we abut a region above - nothing above ~0 + 1 */ + if (iova + size) { + dma = vfio_find_dma(iommu, iova + size, 1); + if (dma && dma->prot == prot && + dma->vaddr == vaddr + size) { + + dma->npage += npage; + dma->iova = iova; + dma->vaddr = vaddr; + + /* + * If merged above and below, remove previously + * merged entry. New entry covers it. + */ + if (pdma) { + list_del(&pdma->next); + kfree(pdma); + } + pdma = dma; + } + } + + /* Isolated, new region */ + if (!pdma) { + dma = kzalloc(sizeof *dma, GFP_KERNEL); + if (!dma) { + ret = -ENOMEM; + vfio_dma_unmap(iommu, iova, npage, prot); + goto out_lock; + } + + dma->npage = npage; + dma->iova = iova; + dma->vaddr = vaddr; + dma->prot = prot; + list_add(&dma->next, &iommu->dma_list); + } + +out_lock: + mutex_unlock(&iommu->lock); + return ret; +} + +static int vfio_iommu_x86_attach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + struct vfio_iommu *iommu = iommu_data; + struct vfio_group *group, *tmp; + int ret; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return -ENOMEM; + + mutex_lock(&iommu->lock); + + list_for_each_entry(tmp, &iommu->group_list, next) { + if (tmp->iommu_group == iommu_group) { + mutex_unlock(&iommu->lock); + kfree(group); + return -EINVAL; + } + } + + /* + * TODO: Domain have capabilities that might change as we add + * groups (see iommu->cache, currently never set). Check for + * them and potentially disallow groups to be attached when it + * would change capabilities (ugh). + */ + ret = iommu_attach_group(iommu->domain, iommu_group); + if (ret) { + mutex_unlock(&iommu->lock); + kfree(group); + return ret; + } + + group->iommu_group = iommu_group; + list_add(&group->next, &iommu->group_list); + + mutex_unlock(&iommu->lock); + + return 0; +} + +static void vfio_iommu_x86_detach_group(void *iommu_data, + struct iommu_group *iommu_group) +{ + struct vfio_iommu *iommu = iommu_data; + struct vfio_group *group; + + mutex_lock(&iommu->lock); + + list_for_each_entry(group, &iommu->group_list, next) { + if (group->iommu_group == iommu_group) { + iommu_detach_group(iommu->domain, iommu_group); + list_del(&group->next); + kfree(group); + break; + } + } + + mutex_unlock(&iommu->lock); +} + +static void *vfio_iommu_x86_open(unsigned long arg) +{ + struct vfio_iommu *iommu; + + if (arg != VFIO_X86_IOMMU) + return ERR_PTR(-EINVAL); + + iommu = kzalloc(sizeof(*iommu), GFP_KERNEL); + if (!iommu) + return ERR_PTR(-ENOMEM); + + INIT_LIST_HEAD(&iommu->group_list); + INIT_LIST_HEAD(&iommu->dma_list); + mutex_init(&iommu->lock); + + /* + * Wish we didn't have to know about bus_type here. + */ + iommu->domain = iommu_domain_alloc(&pci_bus_type); + if (!iommu->domain) { + kfree(iommu); + return ERR_PTR(-EIO); + } + + /* + * Wish we could specify required capabilities rather than create + * a domain, see what comes out and hope it doesn't change along + * the way. Fortunately we know interrupt remapping is global for + * our iommus. + */ + if (!allow_unsafe_interrupts && + !iommu_domain_has_cap(iommu->domain, IOMMU_CAP_INTR_REMAP)) { + printk(KERN_WARNING + "%s: No interrupt remapping support. Use the module param \"allow_unsafe_interrupts\" to enable VFIO IOMMU support on this platform\n", + __func__); + iommu_domain_free(iommu->domain); + kfree(iommu); + return ERR_PTR(-EPERM); + } + + return iommu; +} + +static void vfio_iommu_x86_release(void *iommu_data) +{ + struct vfio_iommu *iommu = iommu_data; + struct vfio_group *group, *group_tmp; + struct vfio_dma *dma, *dma_tmp; + + list_for_each_entry_safe(group, group_tmp, &iommu->group_list, next) { + iommu_detach_group(iommu->domain, group->iommu_group); + list_del(&group->next); + kfree(group); + } + + list_for_each_entry_safe(dma, dma_tmp, &iommu->dma_list, next) { + vfio_dma_unmap(iommu, dma->iova, dma->npage, dma->prot); + list_del(&dma->next); + kfree(dma); + } + + iommu_domain_free(iommu->domain); + iommu->domain = NULL; + kfree(iommu); +} + +static long vfio_iommu_x86_ioctl(void *iommu_data, + unsigned int cmd, unsigned long arg) +{ + struct vfio_iommu *iommu = iommu_data; + unsigned long minsz; + + if (cmd == VFIO_CHECK_EXTENSION) { + switch (arg) { + case VFIO_X86_IOMMU: + return 1; + default: + return 0; + } + } else if (cmd == VFIO_IOMMU_GET_INFO) { + struct vfio_iommu_x86_info info; + + minsz = offsetofend(struct vfio_iommu_x86_info, iova_pgsizes); + + if (copy_from_user(&info, (void __user *)arg, minsz)) + return -EFAULT; + + if (info.argsz < minsz) + return -EINVAL; + + info.flags = 0; + + info.iova_pgsizes = iommu->domain->ops->pgsize_bitmap; + + return copy_to_user((void __user *)arg, &info, minsz); + + } else if (cmd == VFIO_IOMMU_MAP_DMA) { + struct vfio_iommu_x86_dma_map map; + uint32_t mask = VFIO_DMA_MAP_FLAG_READ | + VFIO_DMA_MAP_FLAG_WRITE; + + minsz = offsetofend(struct vfio_iommu_x86_dma_map, size); + + if (copy_from_user(&map, (void __user *)arg, minsz)) + return -EFAULT; + + if (map.argsz < minsz || map.flags & ~mask) + return -EINVAL; + + return vfio_dma_do_map(iommu, &map); + + } else if (cmd == VFIO_IOMMU_UNMAP_DMA) { + struct vfio_iommu_x86_dma_unmap unmap; + + minsz = offsetofend(struct vfio_iommu_x86_dma_unmap, size); + + if (copy_from_user(&unmap, (void __user *)arg, minsz)) + return -EFAULT; + + if (unmap.argsz < minsz || unmap.flags) + return -EINVAL; + + return vfio_dma_do_unmap(iommu, &unmap); + } + + return -ENOTTY; +} + +const struct vfio_iommu_driver_ops vfio_iommu_driver_ops_x86 = { + .name = "vfio-iommu-x86", + .owner = THIS_MODULE, + .open = vfio_iommu_x86_open, + .release = vfio_iommu_x86_release, + .ioctl = vfio_iommu_x86_ioctl, + .attach_group = vfio_iommu_x86_attach_group, + .detach_group = vfio_iommu_x86_detach_group, +}; + +static int __init vfio_iommu_x86_init(void) +{ + if (!iommu_present(&pci_bus_type)) + return -ENODEV; + + return vfio_register_iommu_driver(&vfio_iommu_driver_ops_x86); +} + +static void __exit vfio_iommu_x86_cleanup(void) +{ + vfio_unregister_iommu_driver(&vfio_iommu_driver_ops_x86); +} + +module_init(vfio_iommu_x86_init); +module_exit(vfio_iommu_x86_cleanup); + +MODULE_VERSION(DRIVER_VERSION); +MODULE_LICENSE("GPL v2"); +MODULE_AUTHOR(DRIVER_AUTHOR); +MODULE_DESCRIPTION(DRIVER_DESC); diff --git a/include/linux/vfio.h b/include/linux/vfio.h index 76a8f97..b3e4583 100644 --- a/include/linux/vfio.h +++ b/include/linux/vfio.h @@ -363,4 +363,56 @@ struct vfio_irq_set { */ #define VFIO_DEVICE_RESET _IO(VFIO_TYPE, VFIO_BASE + 11) +/* -------- API for x86 VFIO IOMMU -------- */ + +/** + * VFIO_IOMMU_GET_INFO - _IOR(VFIO_TYPE, VFIO_BASE + 12, struct vfio_iommu_info) + * + * Retrieve information about the IOMMU object. Fills in provided + * struct vfio_iommu_info. Caller sets argsz. + * + * XXX Should we do these by CHECK_EXTENSION too? + */ +struct vfio_iommu_x86_info { + __u32 argsz; + __u32 flags; +#define VFIO_IOMMU_INFO_PGSIZES (1 << 0) /* supported page sizes info */ + __u64 iova_pgsizes; /* Bitmap of supported page sizes */ +}; + +#define VFIO_IOMMU_GET_INFO _IO(VFIO_TYPE, VFIO_BASE + 12) + +/** + * VFIO_IOMMU_MAP_DMA - _IOW(VFIO_TYPE, VFIO_BASE + 13, struct vfio_dma_map) + * + * Map process virtual addresses to IO virtual addresses using the + * provided struct vfio_dma_map. Caller sets argsz. READ &/ WRITE required. + */ +struct vfio_iommu_x86_dma_map { + __u32 argsz; + __u32 flags; +#define VFIO_DMA_MAP_FLAG_READ (1 << 0) /* readable from device */ +#define VFIO_DMA_MAP_FLAG_WRITE (1 << 1) /* writable from device */ + __u64 vaddr; /* Process virtual address */ + __u64 iova; /* IO virtual address */ + __u64 size; /* Size of mapping (bytes) */ +}; + +#define VFIO_IOMMU_MAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 13) + +/** + * VFIO_IOMMU_UNMAP_DMA - _IOW(VFIO_TYPE, VFIO_BASE + 14, struct vfio_dma_unmap) + * + * Unmap IO virtual addresses using the provided struct vfio_dma_unmap. + * Caller sets argsz. + */ +struct vfio_iommu_x86_dma_unmap { + __u32 argsz; + __u32 flags; + __u64 iova; /* IO virtual address */ + __u64 size; /* Size of mapping (bytes) */ +}; + +#define VFIO_IOMMU_UNMAP_DMA _IO(VFIO_TYPE, VFIO_BASE + 14) + #endif /* VFIO_H */