Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1752667Ab2K2E1i (ORCPT ); Wed, 28 Nov 2012 23:27:38 -0500 Received: from mx1.redhat.com ([209.132.183.28]:43696 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752378Ab2K2E1h (ORCPT ); Wed, 28 Nov 2012 23:27:37 -0500 Message-ID: <1354162826.1809.241.camel@bling.home> Subject: Re: [PATCH] vfio powerpc: enabled on powernv platform From: Alex Williamson To: Alexey Kardashevskiy Cc: Benjamin Herrenschmidt , Paul Mackerras , linuxppc-dev@lists.ozlabs.org, linux-kernel@vger.kernel.org, David Gibson Date: Wed, 28 Nov 2012 21:20:26 -0700 In-Reply-To: <1354161225-23118-1-git-send-email-aik@ozlabs.ru> References: <1354138245.1809.226.camel@bling.home> <1354161225-23118-1-git-send-email-aik@ozlabs.ru> Content-Type: text/plain; charset="UTF-8" Mime-Version: 1.0 Content-Transfer-Encoding: 7bit Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 11682 Lines: 417 On Thu, 2012-11-29 at 14:53 +1100, Alexey Kardashevskiy wrote: > This patch initializes IOMMU groups based on the IOMMU > configuration discovered during the PCI scan on POWERNV > (POWER non virtualized) platform. The IOMMU groups are > to be used later by VFIO driver (PCI pass through). > > It also implements an API for mapping/unmapping pages for > guest PCI drivers and providing DMA window properties. > This API is going to be used later by QEMU-VFIO to handle > h_put_tce hypercalls from the KVM guest. > > Although this driver has been tested only on the POWERNV > platform, it should work on any platform which supports > TCE tables. > > To enable VFIO on POWER, enable SPAPR_TCE_IOMMU config > option and configure VFIO as required. > > Cc: David Gibson > Signed-off-by: Alexey Kardashevskiy > --- > arch/powerpc/include/asm/iommu.h | 9 ++ > arch/powerpc/kernel/iommu.c | 159 ++++++++++++++++++++++++++++++++++ > arch/powerpc/platforms/powernv/pci.c | 135 +++++++++++++++++++++++++++++ > drivers/iommu/Kconfig | 8 ++ > 4 files changed, 311 insertions(+) > > diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h > index cbfe678..5c7087a 100644 > --- a/arch/powerpc/include/asm/iommu.h > +++ b/arch/powerpc/include/asm/iommu.h > @@ -76,6 +76,9 @@ struct iommu_table { > struct iommu_pool large_pool; > struct iommu_pool pools[IOMMU_NR_POOLS]; > unsigned long *it_map; /* A simple allocation bitmap for now */ > +#ifdef CONFIG_IOMMU_API > + struct iommu_group *it_group; > +#endif > }; > > struct scatterlist; > @@ -147,5 +150,11 @@ static inline void iommu_restore(void) > } > #endif > > +extern long iommu_clear_tces(struct iommu_table *tbl, unsigned long entry, > + unsigned long pages); > +extern long iommu_put_tces(struct iommu_table *tbl, unsigned long entry, > + uint64_t tce, enum dma_data_direction direction, > + unsigned long pages); > + > #endif /* __KERNEL__ */ > #endif /* _ASM_IOMMU_H */ > diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c > index ff5a6ce..1225fbb 100644 > --- a/arch/powerpc/kernel/iommu.c > +++ b/arch/powerpc/kernel/iommu.c > @@ -44,6 +44,7 @@ > #include > #include > #include > +#include > > #define DBG(...) > > @@ -856,3 +857,161 @@ void iommu_free_coherent(struct iommu_table *tbl, size_t size, > free_pages((unsigned long)vaddr, get_order(size)); > } > } > + > +#ifdef CONFIG_IOMMU_API > +/* > + * SPAPR TCE API > + */ > +static void tce_flush(struct iommu_table *tbl) > +{ > + /* Flush/invalidate TLB caches if necessary */ > + if (ppc_md.tce_flush) > + ppc_md.tce_flush(tbl); > + > + /* Make sure updates are seen by hardware */ > + mb(); > +} > + > +/* > + * iommu_clear_tces clears tces and returned the number of pages > + * which it called put_page() on. > + */ > +static long clear_tces_nolock(struct iommu_table *tbl, unsigned long entry, > + unsigned long pages) > +{ > + int i, retpages = 0; > + unsigned long oldtce; > + struct page *page; > + > + for (i = 0; i < pages; ++i) { > + oldtce = ppc_md.tce_get(tbl, entry + i); > + ppc_md.tce_free(tbl, entry + i, 1); > + > + if (!(oldtce & (TCE_PCI_WRITE | TCE_PCI_READ))) > + continue; > + > + page = pfn_to_page(oldtce >> PAGE_SHIFT); > + > + WARN_ON(!page); > + if (!page) > + continue; > + > + if (oldtce & TCE_PCI_WRITE) > + SetPageDirty(page); > + > + if (!(oldtce & ~PAGE_MASK)) > + ++retpages; I'm confused, it looks like you're trying to only increment the counter for tce pages aligned at the start of a page, but don't we need to mask out the read/write and valid bits? Trickiness like this demands a comment. > + > + put_page(page); > + } > + > + return retpages; > +} > + > +/* > + * iommu_clear_tces clears tces and returned the number of released pages > + */ > +long iommu_clear_tces(struct iommu_table *tbl, unsigned long entry, > + unsigned long pages) > +{ > + int ret; > + struct iommu_pool *pool = get_pool(tbl, entry); > + > + spin_lock(&(pool->lock)); > + ret = clear_tces_nolock(tbl, entry, pages); > + tce_flush(tbl); > + spin_unlock(&(pool->lock)); > + > + return ret; > +} > +EXPORT_SYMBOL_GPL(iommu_clear_tces); > + > +static int put_tce(struct iommu_table *tbl, unsigned long entry, > + uint64_t tce, enum dma_data_direction direction) > +{ > + int ret; > + struct page *page = NULL; > + unsigned long kva, offset; > + > + /* Map new TCE */ > + offset = (tce & IOMMU_PAGE_MASK) - (tce & PAGE_MASK); > + > + ret = get_user_pages_fast(tce & PAGE_MASK, 1, > + direction != DMA_TO_DEVICE, &page); > + if (ret < 1) { > + printk(KERN_ERR "tce_vfio: get_user_pages_fast failed tce=%llx ioba=%lx ret=%d\n", > + tce, entry << IOMMU_PAGE_SHIFT, ret); > + if (!ret) > + ret = -EFAULT; > + return ret; > + } > + > + kva = (unsigned long) page_address(page); > + kva += offset; > + > + /* tce_build receives a virtual address */ > + entry += tbl->it_offset; /* Offset into real TCE table */ > + ret = ppc_md.tce_build(tbl, entry, 1, kva, direction, NULL); > + > + /* tce_build() only returns non-zero for transient errors */ > + if (unlikely(ret)) { > + printk(KERN_ERR "tce_vfio: tce_put failed on tce=%llx ioba=%lx kva=%lx ret=%d\n", > + tce, entry << IOMMU_PAGE_SHIFT, kva, ret); > + put_page(page); > + return -EIO; > + } > + > + return 0; > +} > + > +/* > + * iommu_put_tces builds tces and returned the number of actually > + * locked system pages > + */ > +long iommu_put_tces(struct iommu_table *tbl, unsigned long entry, > + uint64_t tce, enum dma_data_direction direction, > + unsigned long pages) > +{ > + int i, ret = 0, retpages = 0; > + struct iommu_pool *pool = get_pool(tbl, entry); > + > + BUILD_BUG_ON(PAGE_SIZE < IOMMU_PAGE_SIZE); > + BUG_ON(direction == DMA_NONE); > + > + spin_lock(&(pool->lock)); > + > + /* Check if any is in use */ > + for (i = 0; i < pages; ++i) { > + unsigned long oldtce = ppc_md.tce_get(tbl, entry + i); > + if (oldtce & (TCE_PCI_WRITE | TCE_PCI_READ)) { > + spin_unlock(&(pool->lock)); > + return -EBUSY; > + } > + } > + > + /* Put tces to the table */ > + for (i = 0; (i < pages) && !ret; ++i, tce += IOMMU_PAGE_SIZE) { > + ret = put_tce(tbl, entry + i, tce, direction); > + /* > + * As IOMMU page size is always 4K, the system page size > + * can be 64K and there is no special tracking for IOMMU pages, > + * we only do rlimit check/update for the very first > + * 4K IOMMUpage within 64K system page. > + */ > + if (!(tce & ~PAGE_MASK)) > + ++retpages; Ah, here's the comment I was looking for, though I'm still not sure about the read/write bits. Isn't there an exploit here that a user can lock pages beyond their limits if they just skip mapping the first 4k of each page? Thanks, Alex > + } > + > + /* If failed, release locked pages, otherwise return the number of pages */ > + if (ret) > + clear_tces_nolock(tbl, entry, i); > + else > + ret = retpages; > + > + tce_flush(tbl); > + spin_unlock(&(pool->lock)); > + > + return ret; > +} > +EXPORT_SYMBOL_GPL(iommu_put_tces); > +#endif /* CONFIG_IOMMU_API */ > diff --git a/arch/powerpc/platforms/powernv/pci.c b/arch/powerpc/platforms/powernv/pci.c > index 05205cf..21250ef 100644 > --- a/arch/powerpc/platforms/powernv/pci.c > +++ b/arch/powerpc/platforms/powernv/pci.c > @@ -20,6 +20,7 @@ > #include > #include > #include > +#include > > #include > #include > @@ -613,3 +614,137 @@ void __init pnv_pci_init(void) > ppc_md.teardown_msi_irqs = pnv_teardown_msi_irqs; > #endif > } > + > +#ifdef CONFIG_IOMMU_API > +/* > + * IOMMU groups support required by VFIO > + */ > +static int add_device(struct device *dev) > +{ > + struct iommu_table *tbl; > + int ret = 0; > + > + if (WARN_ON(dev->iommu_group)) { > + printk(KERN_WARNING "tce_vfio: device %s is already in iommu group %d, skipping\n", > + dev_name(dev), > + iommu_group_id(dev->iommu_group)); > + return -EBUSY; > + } > + > + tbl = get_iommu_table_base(dev); > + if (!tbl) { > + pr_debug("tce_vfio: skipping device %s with no tbl\n", > + dev_name(dev)); > + return 0; > + } > + > + pr_debug("tce_vfio: adding %s to iommu group %d\n", > + dev_name(dev), iommu_group_id(tbl->it_group)); > + > + ret = iommu_group_add_device(tbl->it_group, dev); > + if (ret < 0) > + printk(KERN_ERR "tce_vfio: %s has not been added, ret=%d\n", > + dev_name(dev), ret); > + > + return ret; > +} > + > +static void del_device(struct device *dev) > +{ > + iommu_group_remove_device(dev); > +} > + > +static int iommu_bus_notifier(struct notifier_block *nb, > + unsigned long action, void *data) > +{ > + struct device *dev = data; > + > + switch (action) { > + case BUS_NOTIFY_ADD_DEVICE: > + return add_device(dev); > + case BUS_NOTIFY_DEL_DEVICE: > + del_device(dev); > + return 0; > + default: > + return 0; > + } > +} > + > +static struct notifier_block tce_iommu_bus_nb = { > + .notifier_call = iommu_bus_notifier, > +}; > + > +static void group_release(void *iommu_data) > +{ > + struct iommu_table *tbl = iommu_data; > + tbl->it_group = NULL; > +} > + > +static int __init tce_iommu_init(void) > +{ > + struct pci_dev *pdev = NULL; > + struct iommu_table *tbl; > + struct iommu_group *grp; > + > + /* Allocate and initialize IOMMU groups */ > + for_each_pci_dev(pdev) { > + tbl = get_iommu_table_base(&pdev->dev); > + if (!tbl) > + continue; > + > + /* Skip already initialized */ > + if (tbl->it_group) > + continue; > + > + grp = iommu_group_alloc(); > + if (IS_ERR(grp)) { > + printk(KERN_INFO "tce_vfio: cannot create " > + "new IOMMU group, ret=%ld\n", > + PTR_ERR(grp)); > + return PTR_ERR(grp); > + } > + tbl->it_group = grp; > + iommu_group_set_iommudata(grp, tbl, group_release); > + } > + > + bus_register_notifier(&pci_bus_type, &tce_iommu_bus_nb); > + > + /* Add PCI devices to VFIO groups */ > + for_each_pci_dev(pdev) > + add_device(&pdev->dev); > + > + return 0; > +} > + > +static void __exit tce_iommu_cleanup(void) > +{ > + struct pci_dev *pdev = NULL; > + struct iommu_table *tbl; > + struct iommu_group *grp = NULL; > + > + bus_unregister_notifier(&pci_bus_type, &tce_iommu_bus_nb); > + > + /* Delete PCI devices from VFIO groups */ > + for_each_pci_dev(pdev) > + del_device(&pdev->dev); > + > + /* Release VFIO groups */ > + for_each_pci_dev(pdev) { > + tbl = get_iommu_table_base(&pdev->dev); > + if (!tbl) > + continue; > + grp = tbl->it_group; > + > + /* Skip (already) uninitialized */ > + if (!grp) > + continue; > + > + /* Do actual release, group_release() is expected to work */ > + iommu_group_put(grp); > + BUG_ON(tbl->it_group); > + } > +} > + > +module_init(tce_iommu_init); > +module_exit(tce_iommu_cleanup); > +#endif /* CONFIG_IOMMU_API */ > diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig > index 9f69b56..29d11dc 100644 > --- a/drivers/iommu/Kconfig > +++ b/drivers/iommu/Kconfig > @@ -187,4 +187,12 @@ config EXYNOS_IOMMU_DEBUG > > Say N unless you need kernel log message for IOMMU debugging > > +config SPAPR_TCE_IOMMU > + bool "sPAPR TCE IOMMU Support" > + depends on PPC_POWERNV > + select IOMMU_API > + help > + Enables bits of IOMMU API required by VFIO. The iommu_ops is > + still not implemented. > + > endif # IOMMU_SUPPORT -- To unsubscribe from this list: send the line "unsubscribe linux-kernel" in the body of a message to majordomo@vger.kernel.org More majordomo info at http://vger.kernel.org/majordomo-info.html Please read the FAQ at http://www.tux.org/lkml/