From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755490AbbDJGgq (ORCPT ); Fri, 10 Apr 2015 02:36:46 -0400 Received: from e23smtp03.au.ibm.com ([202.81.31.145]:41949 "EHLO e23smtp03.au.ibm.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1754341AbbDJGcs (ORCPT ); Fri, 10 Apr 2015 02:32:48 -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 14/31] vfio: powerpc/spapr: powerpc/powernv/ioda2: Rework IOMMU ownership control Date: Fri, 10 Apr 2015 16:30:56 +1000 Message-Id: <1428647473-11738-15-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: 15041006-0009-0000-0000-000001332E3F Sender: linux-kernel-owner@vger.kernel.org List-ID: X-Mailing-List: linux-kernel@vger.kernel.org At the moment the iommu_table struct has a set_bypass() which enables/ disables DMA bypass on IODA2 PHB. This is exposed to POWERPC IOMMU code which calls this callback when external IOMMU users such as VFIO are about to get over a PHB. The set_bypass() callback is not really an iommu_table function but IOMMU/PE function. This introduces a iommu_table_group_ops struct and adds a set_ownership() callback to it which is called when an external user takes control over the IOMMU. This renames set_bypass() to set_ownership() as it is not necessarily just enabling bypassing, it can be something else/more so let's give it more generic name. The bool parameter is inverted. The callback is implemented for IODA2 only. Other platforms (P5IOC2, IODA1) will use the old iommu_take_ownership/iommu_release_ownership API. Signed-off-by: Alexey Kardashevskiy --- arch/powerpc/include/asm/iommu.h | 14 +++++++++++++- arch/powerpc/platforms/powernv/pci-ioda.c | 30 ++++++++++++++++++++++-------- drivers/vfio/vfio_iommu_spapr_tce.c | 25 +++++++++++++++++++++---- 3 files changed, 56 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index b9e50d3..d1f8c6c 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -92,7 +92,6 @@ struct iommu_table { unsigned long it_page_shift;/* table iommu page size */ struct iommu_table_group *it_group; struct iommu_table_ops *it_ops; - void (*set_bypass)(struct iommu_table *tbl, bool enable); }; /* Pure 2^n version of get_order */ @@ -127,11 +126,24 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, #define IOMMU_TABLE_GROUP_MAX_TABLES 1 +struct iommu_table_group; + +struct iommu_table_group_ops { + /* + * Switches ownership from the kernel itself to an external + * user. While onwership is enabled, the kernel cannot use IOMMU + * for itself. + */ + void (*set_ownership)(struct iommu_table_group *table_group, + bool enable); +}; + struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; + struct iommu_table_group_ops *ops; }; #ifdef CONFIG_IOMMU_API diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index a964c50..9687731 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1255,10 +1255,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } -static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) +static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable) { - struct pnv_ioda_pe *pe = container_of(tbl->it_group, struct pnv_ioda_pe, - table_group); uint16_t window_id = (pe->pe_number << 1 ) + 1; int64_t rc; @@ -1286,7 +1284,8 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) * host side. */ if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); + set_iommu_table_base(&pe->pdev->dev, + &pe->table_group.tables[0]); else pnv_ioda_setup_bus_dma(pe, pe->pbus, false); } @@ -1302,13 +1301,27 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, /* TVE #1 is selected by PCI address bit 59 */ pe->tce_bypass_base = 1ull << 59; - /* Install set_bypass callback for VFIO */ - pe->table_group.tables[0].set_bypass = pnv_pci_ioda2_set_bypass; - /* Enable bypass by default */ - pnv_pci_ioda2_set_bypass(&pe->table_group.tables[0], true); + pnv_pci_ioda2_set_bypass(pe, true); } +static void pnv_ioda2_set_ownership(struct iommu_table_group *table_group, + bool enable) +{ + struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, + table_group); + if (enable) + iommu_take_ownership(table_group); + else + iommu_release_ownership(table_group); + + pnv_pci_ioda2_set_bypass(pe, !enable); +} + +static struct iommu_table_group_ops pnv_pci_ioda2_ops = { + .set_ownership = pnv_ioda2_set_ownership, +}; + static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { @@ -1376,6 +1389,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, } tbl->it_ops = &pnv_iommu_ops; iommu_init_table(tbl, phb->hose->node); + pe->table_group.ops = &pnv_pci_ioda2_ops; iommu_register_group(&pe->table_group, phb->hose->global_number, pe->pe_number); diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 9f38351..d5d8c50 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -535,9 +535,22 @@ static int tce_iommu_attach_group(void *iommu_data, goto unlock_exit; } - ret = iommu_take_ownership(table_group); - if (!ret) - container->grp = iommu_group; + if (!table_group->ops || !table_group->ops->set_ownership) { + ret = iommu_take_ownership(table_group); + } else { + /* + * Disable iommu bypass, otherwise the user can DMA to all of + * our physical memory via the bypass window instead of just + * the pages that has been explicitly mapped into the iommu + */ + table_group->ops->set_ownership(table_group, true); + ret = 0; + } + + if (ret) + goto unlock_exit; + + container->grp = iommu_group; unlock_exit: mutex_unlock(&container->lock); @@ -572,7 +585,11 @@ static void tce_iommu_detach_group(void *iommu_data, table_group = iommu_group_get_iommudata(iommu_group); BUG_ON(!table_group); - iommu_release_ownership(table_group); + /* Kernel owns the device now, we can restore bypass */ + if (!table_group->ops || !table_group->ops->set_ownership) + iommu_release_ownership(table_group); + else + table_group->ops->set_ownership(table_group, false); unlock_exit: mutex_unlock(&container->lock); -- 2.0.0 From mboxrd@z Thu Jan 1 00:00:00 1970 Return-Path: Received: from e23smtp02.au.ibm.com (e23smtp02.au.ibm.com [202.81.31.144]) (using TLSv1 with cipher DHE-RSA-AES256-SHA (256/256 bits)) (No client certificate requested) by lists.ozlabs.org (Postfix) with ESMTPS id 6AD251A09EC for ; Fri, 10 Apr 2015 16:32:46 +1000 (AEST) Received: from /spool/local by e23smtp02.au.ibm.com with IBM ESMTP SMTP Gateway: Authorized Use Only! Violators will be prosecuted for from ; Fri, 10 Apr 2015 16:32:45 +1000 Received: from d23relay06.au.ibm.com (d23relay06.au.ibm.com [9.185.63.219]) by d23dlp03.au.ibm.com (Postfix) with ESMTP id 92B353578056 for ; Fri, 10 Apr 2015 16:32:44 +1000 (EST) Received: from d23av03.au.ibm.com (d23av03.au.ibm.com [9.190.234.97]) by d23relay06.au.ibm.com (8.14.9/8.14.9/NCO v10.0) with ESMTP id t3A6Wa7240042504 for ; Fri, 10 Apr 2015 16:32:44 +1000 Received: from d23av03.au.ibm.com (localhost [127.0.0.1]) by d23av03.au.ibm.com (8.14.4/8.14.4/NCO v10.0 AVout) with ESMTP id t3A6WBam004949 for ; Fri, 10 Apr 2015 16:32:11 +1000 From: Alexey Kardashevskiy To: linuxppc-dev@lists.ozlabs.org Subject: [PATCH kernel v8 14/31] vfio: powerpc/spapr: powerpc/powernv/ioda2: Rework IOMMU ownership control Date: Fri, 10 Apr 2015 16:30:56 +1000 Message-Id: <1428647473-11738-15-git-send-email-aik@ozlabs.ru> In-Reply-To: <1428647473-11738-1-git-send-email-aik@ozlabs.ru> References: <1428647473-11738-1-git-send-email-aik@ozlabs.ru> Cc: Alexey Kardashevskiy , Alex Williamson , Paul Mackerras , linux-kernel@vger.kernel.org List-Id: Linux on PowerPC Developers Mail List List-Unsubscribe: , List-Archive: List-Post: List-Help: List-Subscribe: , At the moment the iommu_table struct has a set_bypass() which enables/ disables DMA bypass on IODA2 PHB. This is exposed to POWERPC IOMMU code which calls this callback when external IOMMU users such as VFIO are about to get over a PHB. The set_bypass() callback is not really an iommu_table function but IOMMU/PE function. This introduces a iommu_table_group_ops struct and adds a set_ownership() callback to it which is called when an external user takes control over the IOMMU. This renames set_bypass() to set_ownership() as it is not necessarily just enabling bypassing, it can be something else/more so let's give it more generic name. The bool parameter is inverted. The callback is implemented for IODA2 only. Other platforms (P5IOC2, IODA1) will use the old iommu_take_ownership/iommu_release_ownership API. Signed-off-by: Alexey Kardashevskiy --- arch/powerpc/include/asm/iommu.h | 14 +++++++++++++- arch/powerpc/platforms/powernv/pci-ioda.c | 30 ++++++++++++++++++++++-------- drivers/vfio/vfio_iommu_spapr_tce.c | 25 +++++++++++++++++++++---- 3 files changed, 56 insertions(+), 13 deletions(-) diff --git a/arch/powerpc/include/asm/iommu.h b/arch/powerpc/include/asm/iommu.h index b9e50d3..d1f8c6c 100644 --- a/arch/powerpc/include/asm/iommu.h +++ b/arch/powerpc/include/asm/iommu.h @@ -92,7 +92,6 @@ struct iommu_table { unsigned long it_page_shift;/* table iommu page size */ struct iommu_table_group *it_group; struct iommu_table_ops *it_ops; - void (*set_bypass)(struct iommu_table *tbl, bool enable); }; /* Pure 2^n version of get_order */ @@ -127,11 +126,24 @@ extern struct iommu_table *iommu_init_table(struct iommu_table * tbl, #define IOMMU_TABLE_GROUP_MAX_TABLES 1 +struct iommu_table_group; + +struct iommu_table_group_ops { + /* + * Switches ownership from the kernel itself to an external + * user. While onwership is enabled, the kernel cannot use IOMMU + * for itself. + */ + void (*set_ownership)(struct iommu_table_group *table_group, + bool enable); +}; + struct iommu_table_group { #ifdef CONFIG_IOMMU_API struct iommu_group *group; #endif struct iommu_table tables[IOMMU_TABLE_GROUP_MAX_TABLES]; + struct iommu_table_group_ops *ops; }; #ifdef CONFIG_IOMMU_API diff --git a/arch/powerpc/platforms/powernv/pci-ioda.c b/arch/powerpc/platforms/powernv/pci-ioda.c index a964c50..9687731 100644 --- a/arch/powerpc/platforms/powernv/pci-ioda.c +++ b/arch/powerpc/platforms/powernv/pci-ioda.c @@ -1255,10 +1255,8 @@ static void pnv_pci_ioda_setup_dma_pe(struct pnv_phb *phb, __free_pages(tce_mem, get_order(TCE32_TABLE_SIZE * segs)); } -static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) +static void pnv_pci_ioda2_set_bypass(struct pnv_ioda_pe *pe, bool enable) { - struct pnv_ioda_pe *pe = container_of(tbl->it_group, struct pnv_ioda_pe, - table_group); uint16_t window_id = (pe->pe_number << 1 ) + 1; int64_t rc; @@ -1286,7 +1284,8 @@ static void pnv_pci_ioda2_set_bypass(struct iommu_table *tbl, bool enable) * host side. */ if (pe->pdev) - set_iommu_table_base(&pe->pdev->dev, tbl); + set_iommu_table_base(&pe->pdev->dev, + &pe->table_group.tables[0]); else pnv_ioda_setup_bus_dma(pe, pe->pbus, false); } @@ -1302,13 +1301,27 @@ static void pnv_pci_ioda2_setup_bypass_pe(struct pnv_phb *phb, /* TVE #1 is selected by PCI address bit 59 */ pe->tce_bypass_base = 1ull << 59; - /* Install set_bypass callback for VFIO */ - pe->table_group.tables[0].set_bypass = pnv_pci_ioda2_set_bypass; - /* Enable bypass by default */ - pnv_pci_ioda2_set_bypass(&pe->table_group.tables[0], true); + pnv_pci_ioda2_set_bypass(pe, true); } +static void pnv_ioda2_set_ownership(struct iommu_table_group *table_group, + bool enable) +{ + struct pnv_ioda_pe *pe = container_of(table_group, struct pnv_ioda_pe, + table_group); + if (enable) + iommu_take_ownership(table_group); + else + iommu_release_ownership(table_group); + + pnv_pci_ioda2_set_bypass(pe, !enable); +} + +static struct iommu_table_group_ops pnv_pci_ioda2_ops = { + .set_ownership = pnv_ioda2_set_ownership, +}; + static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, struct pnv_ioda_pe *pe) { @@ -1376,6 +1389,7 @@ static void pnv_pci_ioda2_setup_dma_pe(struct pnv_phb *phb, } tbl->it_ops = &pnv_iommu_ops; iommu_init_table(tbl, phb->hose->node); + pe->table_group.ops = &pnv_pci_ioda2_ops; iommu_register_group(&pe->table_group, phb->hose->global_number, pe->pe_number); diff --git a/drivers/vfio/vfio_iommu_spapr_tce.c b/drivers/vfio/vfio_iommu_spapr_tce.c index 9f38351..d5d8c50 100644 --- a/drivers/vfio/vfio_iommu_spapr_tce.c +++ b/drivers/vfio/vfio_iommu_spapr_tce.c @@ -535,9 +535,22 @@ static int tce_iommu_attach_group(void *iommu_data, goto unlock_exit; } - ret = iommu_take_ownership(table_group); - if (!ret) - container->grp = iommu_group; + if (!table_group->ops || !table_group->ops->set_ownership) { + ret = iommu_take_ownership(table_group); + } else { + /* + * Disable iommu bypass, otherwise the user can DMA to all of + * our physical memory via the bypass window instead of just + * the pages that has been explicitly mapped into the iommu + */ + table_group->ops->set_ownership(table_group, true); + ret = 0; + } + + if (ret) + goto unlock_exit; + + container->grp = iommu_group; unlock_exit: mutex_unlock(&container->lock); @@ -572,7 +585,11 @@ static void tce_iommu_detach_group(void *iommu_data, table_group = iommu_group_get_iommudata(iommu_group); BUG_ON(!table_group); - iommu_release_ownership(table_group); + /* Kernel owns the device now, we can restore bypass */ + if (!table_group->ops || !table_group->ops->set_ownership) + iommu_release_ownership(table_group); + else + table_group->ops->set_ownership(table_group, false); unlock_exit: mutex_unlock(&container->lock); -- 2.0.0