Return-Path: Received: (majordomo@vger.kernel.org) by vger.kernel.org via listexpand id S1755130Ab3CFEEw (ORCPT ); Tue, 5 Mar 2013 23:04:52 -0500 Received: from mx1.redhat.com ([209.132.183.28]:16971 "EHLO mx1.redhat.com" rhost-flags-OK-OK-OK-OK) by vger.kernel.org with ESMTP id S1753041Ab3CFEEt (ORCPT ); Tue, 5 Mar 2013 23:04:49 -0500 Message-ID: <1362542675.22132.86.camel@bling.home> Subject: Re: [PATCH] Quirk to support Marvell 88SE91xx SATA controllers with Intel IOMMU. From: Alex Williamson To: Andrew Cooks Cc: joro@8bytes.org, xjtuychu@hotmail.com, gm.ychu@gmail.com, bhelgaas@google.com, jpiszcz@lucidpixels.com, dwmw2@infradead.org, "open list:INTEL IOMMU (VT-d)" , open list , "open list:PCI SUBSYSTEM" Date: Tue, 05 Mar 2013 21:04:35 -0700 In-Reply-To: <1362126373-32318-1-git-send-email-acooks@gmail.com> References: <1354533387-4110-1-git-send-email-acooks@gmail.com> , <1355914703-28576-1-git-send-email-acooks@gmail.com> <1362126373-32318-1-git-send-email-acooks@gmail.com> 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: 8737 Lines: 248 On Fri, 2013-03-01 at 16:26 +0800, Andrew Cooks wrote: > This is my third submitted patch to make Marvell 88SE91xx SATA controllers work when IOMMU is enabled.[1][2] > > What's changed: > * Adopt David Woodhouse's terminology by referring to the quirky functions as 'ghost' functions. > * Unmap ghost functions when device is detached from IOMMU. > * Stub function for when CONFIG_PCI_QUIRKS is not enabled. > > The bad: > * Still no AMD support. > * The table of affected chip IDs is as complete as I can make it by googling for bug reports. > > This patch was generated against commit b0af9cd9aab60ceb17d3ebabb9fdf4ff0a99cf50, but will also apply cleanly to 3.7.10. > > Bug reports: > 1. https://bugzilla.redhat.com/show_bug.cgi?id=757166 > 2. https://bugzilla.kernel.org/show_bug.cgi?id=42679 > > Signed-off-by: Andrew Cooks > --- > drivers/iommu/intel-iommu.c | 50 +++++++++++++++++++++++++++++++++++++++++++ > drivers/pci/quirks.c | 47 +++++++++++++++++++++++++++++++++++++++- > include/linux/pci.h | 5 ++++ > include/linux/pci_ids.h | 1 + > 4 files changed, 102 insertions(+), 1 deletions(-) > > diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c > index 0099667..13323f2 100644 > --- a/drivers/iommu/intel-iommu.c > +++ b/drivers/iommu/intel-iommu.c > @@ -1674,6 +1674,50 @@ static int domain_context_mapping_one(struct dmar_domain *domain, int segment, > return 0; > } > > +/* For quirky devices like Marvell 88SE91xx chips that use ghost functions. */ > +static int map_ghost_dma_fn(struct dmar_domain *domain, > + struct pci_dev *pdev, > + int translation) > +{ > + u8 fn, fn_map; > + int err = 0; > + > + fn_map = pci_get_dma_source_map(pdev); if (!fn_map) return 0; > + > + for (fn = 1; fn < 8; fn++) { Wouldn't you want to do 0 to 7, then add: if (fn == PCI_FUNC(pdev->devfn)) continue; You could also get more creative with the loop using shifts and exit when the remaining map is 0. > + if (fn_map & (1 << fn)) { > + err = domain_context_mapping_one(domain, > + pci_domain_nr(pdev->bus), > + pdev->bus->number, > + PCI_DEVFN(PCI_SLOT(pdev->devfn), fn), > + translation); > + if (err) > + return err; I'd be worried that there's missing cleanup here, what if you were mapping multiple ghost functions and the 2nd one failed, leaving one attached? > + dev_dbg(&pdev->dev, "dma quirk; func %d mapped", fn); > + } > + } > + return 0; > +} > + > +static void iommu_detach_dev(struct intel_iommu *iommu, u8 bus, u8 devfn); > + > +static void unmap_ghost_dma_fn(struct intel_iommu *iommu, > + struct pci_dev *pdev) > +{ > + u8 fn, fn_map; > + > + fn_map = pci_get_dma_source_map(pdev); > + > + for (fn = 1; fn < 8; fn++) { Same early exit and loop comments as above. > + if (fn_map & (1 << fn)) { > + iommu_detach_dev(iommu, > + pdev->bus->number, > + PCI_DEVFN(PCI_SLOT(pdev->devfn), fn)); > + dev_dbg(&pdev->dev, "dma quirk; func %d unmapped", fn); > + } > + } > +} > + > static int > domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev, > int translation) > @@ -1687,6 +1731,11 @@ domain_context_mapping(struct dmar_domain *domain, struct pci_dev *pdev, > if (ret) > return ret; > > + /* quirk for undeclared/ghost pci functions */ > + ret = map_ghost_dma_fn(domain, pdev, translation); > + if (ret) > + return ret; > + > /* dependent device mapping */ > tmp = pci_find_upstream_pcie_bridge(pdev); > if (!tmp) > @@ -3786,6 +3835,7 @@ static void domain_remove_one_dev_info(struct dmar_domain *domain, > iommu_disable_dev_iotlb(info); > iommu_detach_dev(iommu, info->bus, info->devfn); > iommu_detach_dependent_devices(iommu, pdev); > + unmap_ghost_dma_fn(iommu, pdev); > free_devinfo_mem(info); > > spin_lock_irqsave(&device_domain_lock, flags); > diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c > index 0369fb6..d311100 100644 > --- a/drivers/pci/quirks.c > +++ b/drivers/pci/quirks.c > @@ -3249,6 +3249,10 @@ static struct pci_dev *pci_func_0_dma_source(struct pci_dev *dev) > return pci_get_slot(dev->bus, PCI_DEVFN(PCI_SLOT(dev->devfn), 0)); > } > > +/* Table of source functions for real devices. The DMA requests for the > + * device are tagged with a different real function as source. This is > + * relevant to multifunction devices. > + */ > static const struct pci_dev_dma_source { > u16 vendor; > u16 device; > @@ -3275,7 +3279,8 @@ static const struct pci_dev_dma_source { > * the device doing the DMA, but sometimes hardware is broken and will > * tag the DMA as being sourced from a different device. This function > * allows that translation. Note that the reference count of the > - * returned device is incremented on all paths. > + * returned device is incremented on all paths. Translation is done when > + * the device is added to an IOMMU group. > */ > struct pci_dev *pci_get_dma_source(struct pci_dev *dev) > { > @@ -3292,6 +3297,46 @@ struct pci_dev *pci_get_dma_source(struct pci_dev *dev) > return pci_dev_get(dev); > } > > +/* Table of multiple (ghost) source functions. This is similar to the > + * translated sources above, but with the following differences: > + * 1. the device may use multiple functions as DMA sources, > + * 2. these functions cannot be assumed to be actual devices, > + * 3. the specific ghost function for a request can not be exactly predicted. > + * The bitmap only contains the additional quirk functions. > + */ > +static const struct pci_dev_dma_multi_func_sources { > + u16 vendor; > + u16 device; > + u8 func_map; /* bit map. lsb is fn 0. */ > +} pci_dev_dma_multi_func_sources[] = { > + { PCI_VENDOR_ID_MARVELL_2, 0x9123, (1<<0)|(1<<1)}, > + { PCI_VENDOR_ID_MARVELL_2, 0x9125, (1<<0)|(1<<1)}, > + { PCI_VENDOR_ID_MARVELL_2, 0x9128, (1<<0)|(1<<1)}, > + { PCI_VENDOR_ID_MARVELL_2, 0x9130, (1<<0)|(1<<1)}, > + { PCI_VENDOR_ID_MARVELL_2, 0x9172, (1<<0)|(1<<1)}, Links to bug reports in the comments might be useful for future workarounds. I'm also not sure what you mean in the 3rd bullet, the non-ghost function of some of these is sometimes 0, sometimes 1? And the ghost function is the other? Skipping fn 0 above, I assume all cases are fn 0 exists and fn 1 is the ghost function, right? If so, then we probably only want bit 1 set. I'm afraid to ask whether there are configurations of this vendor/device that have a fn 1. Thanks, Alex > + { 0 } > +}; > + > +/* > + * The mapping of fake/ghost functions is used when the real device is > + * attached to an IOMMU domain. IOMMU groups are not aware of these > + * functions, because they're not real devices. > + */ > +u8 pci_get_dma_source_map(struct pci_dev *dev) > +{ > + const struct pci_dev_dma_multi_func_sources *i; > + > + for (i = pci_dev_dma_multi_func_sources; i->func_map; i++) { > + if ((i->vendor == dev->vendor || > + i->vendor == (u16)PCI_ANY_ID) && > + (i->device == dev->device || > + i->device == (u16)PCI_ANY_ID)) { > + return i->func_map; > + } > + } > + return 0; > +} > + > static const struct pci_dev_acs_enabled { > u16 vendor; > u16 device; > diff --git a/include/linux/pci.h b/include/linux/pci.h > index 2461033..5ad3822 100644 > --- a/include/linux/pci.h > +++ b/include/linux/pci.h > @@ -1578,6 +1578,7 @@ enum pci_fixup_pass { > #ifdef CONFIG_PCI_QUIRKS > void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); > struct pci_dev *pci_get_dma_source(struct pci_dev *dev); > +u8 pci_get_dma_source_map(struct pci_dev *dev); > int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); > #else > static inline void pci_fixup_device(enum pci_fixup_pass pass, > @@ -1586,6 +1587,10 @@ static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev) > { > return pci_dev_get(dev); > } > +u8 pci_get_dma_source_map(struct pci_dev *dev) > +{ > + return 0; > +} > static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, > u16 acs_flags) > { > diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h > index f11c1c2..df57496 100644 > --- a/include/linux/pci_ids.h > +++ b/include/linux/pci_ids.h > @@ -1604,6 +1604,7 @@ > #define PCI_SUBDEVICE_ID_KEYSPAN_SX2 0x5334 > > #define PCI_VENDOR_ID_MARVELL 0x11ab > +#define PCI_VENDOR_ID_MARVELL_2 0x1b4b > #define PCI_DEVICE_ID_MARVELL_GT64111 0x4146 > #define PCI_DEVICE_ID_MARVELL_GT64260 0x6430 > #define PCI_DEVICE_ID_MARVELL_MV64360 0x6460 -- 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/