Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1754102AbbDJGck (ORCPT ); Fri, 10 Apr 2015 02:32:40 -0400 Received: from e23smtp09.au.ibm.com ([202.81.31.142]:50644 "EHLO e23smtp09.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1752156AbbDJGc0 (ORCPT ); Fri, 10 Apr 2015 02:32:26 -0400 From: Alexey Kardashevskiy To: linuxppc-dev@lists.ozlabs.org Cc: Alexey Kardashevskiy , Benjamin Herrenschmidt , Paul Mackerras , Alex Williamson , linux-kernel@vger.kernel.org Subject: [PATCH kernel v8 01/31] vfio: powerpc/spapr: Move page pinning from arch code to VFIO IOMMU driver Date: Fri, 10 Apr 2015 16:30:43 +1000 Message-Id: <1428647473-11738-2-git-send-email-aik@ozlabs.ru> X-Mailer: git-send-email 2.0.0 In-Reply-To: <1428647473-11738-1-git-send-email-aik@ozlabs.ru> References: <1428647473-11738-1-git-send-email-aik@ozlabs.ru> X-TM-AS-MML: disable X-Content-Scanned: Fidelis XPS MAILER x-cbid: 15041006-0033-0000-0000-0000014E69C5 Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org Content-Length: 7411 Lines: 244 This moves page pinning (get_user_pages_fast()/put_page()) code out of the platform IOMMU code and puts it to VFIO IOMMU driver where it belongs to as the platform code does not deal with page pinning. This makes iommu_take_ownership()/iommu_release_ownership() deal with the IOMMU table bitmap only. This removes page unpinning from iommu_take_ownership() as the actual TCE table might contain garbage and doing put_page() on it is undefined behaviour. Besides the last part, the rest of the patch is mechanical. Signed-off-by: Alexey Kardashevskiy --- Changes: v4: * s/iommu_tce_build(tbl, entry + 1/iommu_tce_build(tbl, entry + i/ --- arch/powerpc/include/asm/iommu.h | 4 -- arch/powerpc/kernel/iommu.c | 55 -------------------------- drivers/vfio/vfio_iommu_spapr_tce.c | 78 ++++++++++++++++++++++++++++++------- 3 files changed, 65 insertions(+), 72 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index f1ea597..ed69b7d 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -197,10 +197,6 @@ extern int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, unsigned long hwaddr, enum dma_data_direction direction); extern unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry); -extern int iommu_clear_tces_and_put_pages(struct iommu_table *tbl, - unsigned long entry, unsigned long pages); -extern int iommu_put_tce_user_mode(struct iommu_table *tbl, - unsigned long entry, unsigned long tce); extern void iommu_flush_tce(struct iommu_table *tbl); extern int iommu_take_ownership(struct iommu_table *tbl); diff --git a/arch/powerpc/kernel/iommu.c b/arch/powerpc/kernel/iommu.c index b054f33..1b4a178 100644 --- a/arch/powerpc/kernel/iommu.c +++ b/arch/powerpc/kernel/iommu.c @@ -991,30 +991,6 @@ unsigned long iommu_clear_tce(struct iommu_table *tbl, unsigned long entry) } EXPORT_SYMBOL_GPL(iommu_clear_tce); -int iommu_clear_tces_and_put_pages(struct iommu_table *tbl, - unsigned long entry, unsigned long pages) -{ - unsigned long oldtce; - struct page *page; - - for ( ; pages; --pages, ++entry) { - oldtce = iommu_clear_tce(tbl, entry); - if (!oldtce) - continue; - - page = pfn_to_page(oldtce >> PAGE_SHIFT); - WARN_ON(!page); - if (page) { - if (oldtce & TCE_PCI_WRITE) - SetPageDirty(page); - put_page(page); - } - } - - return 0; -} -EXPORT_SYMBOL_GPL(iommu_clear_tces_and_put_pages); - /* * hwaddr is a kernel virtual address here (0xc... bazillion), * tce_build converts it to a physical address. @@ -1044,35 +1020,6 @@ int iommu_tce_build(struct iommu_table *tbl, unsigned long entry, } EXPORT_SYMBOL_GPL(iommu_tce_build); -int iommu_put_tce_user_mode(struct iommu_table *tbl, unsigned long entry, - unsigned long tce) -{ - int ret; - struct page *page = NULL; - unsigned long hwaddr, offset = tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK; - enum dma_data_direction direction = iommu_tce_direction(tce); - - ret = get_user_pages_fast(tce & PAGE_MASK, 1, - direction != DMA_TO_DEVICE, &page); - if (unlikely(ret != 1)) { - /* pr_err("iommu_tce: get_user_pages_fast failed tce=%lx ioba=%lx ret=%d\n", - tce, entry << tbl->it_page_shift, ret); */ - return -EFAULT; - } - hwaddr = (unsigned long) page_address(page) + offset; - - ret = iommu_tce_build(tbl, entry, hwaddr, direction); - if (ret) - put_page(page); - - if (ret < 0) - pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%d\n", - __func__, entry << tbl->it_page_shift, tce, ret); - - return ret; -} -EXPORT_SYMBOL_GPL(iommu_put_tce_user_mode); - int iommu_take_ownership(struct iommu_table *tbl) { unsigned long sz = (tbl->it_size + 7) >> 3; @@ -1086,7 +1033,6 @@ int iommu_take_ownership(struct iommu_table *tbl) } memset(tbl->it_map, 0xff, sz); - iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size); /* * Disable iommu bypass, otherwise the user can DMA to all of @@ -1104,7 +1050,6 @@ void iommu_release_ownership(struct iommu_table *tbl) { unsigned long sz = (tbl->it_size + 7) >> 3; - iommu_clear_tces_and_put_pages(tbl, tbl->it_offset, tbl->it_size); memset(tbl->it_map, 0, sz); /* Restore bit#0 set by iommu_init_table() */ diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 730b4ef..cefaf05 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -147,6 +147,66 @@ static void tce_iommu_release(void *iommu_data) kfree(container); } +static int tce_iommu_clear(struct tce_container *container, + struct iommu_table *tbl, + unsigned long entry, unsigned long pages) +{ + unsigned long oldtce; + struct page *page; + + for ( ; pages; --pages, ++entry) { + oldtce = iommu_clear_tce(tbl, entry); + if (!oldtce) + continue; + + page = pfn_to_page(oldtce >> PAGE_SHIFT); + WARN_ON(!page); + if (page) { + if (oldtce & TCE_PCI_WRITE) + SetPageDirty(page); + put_page(page); + } + } + + return 0; +} + +static long tce_iommu_build(struct tce_container *container, + struct iommu_table *tbl, + unsigned long entry, unsigned long tce, unsigned long pages) +{ + long i, ret = 0; + struct page *page = NULL; + unsigned long hva; + enum dma_data_direction direction = iommu_tce_direction(tce); + + for (i = 0; i < pages; ++i) { + ret = get_user_pages_fast(tce & PAGE_MASK, 1, + direction != DMA_TO_DEVICE, &page); + if (unlikely(ret != 1)) { + ret = -EFAULT; + break; + } + hva = (unsigned long) page_address(page) + + (tce & IOMMU_PAGE_MASK(tbl) & ~PAGE_MASK); + + ret = iommu_tce_build(tbl, entry + i, hva, direction); + if (ret) { + put_page(page); + pr_err("iommu_tce: %s failed ioba=%lx, tce=%lx, ret=%ld\n", + __func__, entry << tbl->it_page_shift, + tce, ret); + break; + } + tce += IOMMU_PAGE_SIZE_4K; + } + + if (ret) + tce_iommu_clear(container, tbl, entry, i); + + return ret; +} + static long tce_iommu_ioctl(void *iommu_data, unsigned int cmd, unsigned long arg) { @@ -195,7 +255,7 @@ static long tce_iommu_ioctl(void *iommu_data, case VFIO_IOMMU_MAP_DMA: { struct vfio_iommu_type1_dma_map param; struct iommu_table *tbl = container->tbl; - unsigned long tce, i; + unsigned long tce; if (!tbl) return -ENXIO; @@ -229,17 +289,9 @@ static long tce_iommu_ioctl(void *iommu_data, if (ret) return ret; - for (i = 0; i < (param.size >> IOMMU_PAGE_SHIFT_4K); ++i) { - ret = iommu_put_tce_user_mode(tbl, - (param.iova >> IOMMU_PAGE_SHIFT_4K) + i, - tce); - if (ret) - break; - tce += IOMMU_PAGE_SIZE_4K; - } - if (ret) - iommu_clear_tces_and_put_pages(tbl, - param.iova >> IOMMU_PAGE_SHIFT_4K, i); + ret = tce_iommu_build(container, tbl, + param.iova >> IOMMU_PAGE_SHIFT_4K, + tce, param.size >> IOMMU_PAGE_SHIFT_4K); iommu_flush_tce(tbl); @@ -273,7 +325,7 @@ static long tce_iommu_ioctl(void *iommu_data, if (ret) return ret; - ret = iommu_clear_tces_and_put_pages(tbl, + ret = tce_iommu_clear(container, tbl, param.iova >> IOMMU_PAGE_SHIFT_4K, param.size >> IOMMU_PAGE_SHIFT_4K); iommu_flush_tce(tbl); -- 2.0.0 -- 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/