From f0af9593372abfde34460aa1250e670cc535a7d8 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 24 Feb 2016 13:43:45 -0600 Subject: PCI: Add pci_add_dma_alias() to abstract implementation Add a pci_add_dma_alias() interface to encapsulate the details of adding an alias. No functional change intended. Signed-off-by: Bjorn Helgaas Reviewed-by: Alex Williamson --- include/linux/pci.h | 1 + 1 file changed, 1 insertion(+) (limited to 'include/linux/pci.h') diff --git a/include/linux/pci.h b/include/linux/pci.h index 004b8133417d..7e7019064437 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1988,6 +1988,7 @@ static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev) } #endif +void pci_add_dma_alias(struct pci_dev *dev, u8 devfn); int pci_for_each_dma_alias(struct pci_dev *pdev, int (*fn)(struct pci_dev *pdev, u16 alias, void *data), void *data); -- cgit v1.2.3 From 338c3149a221527e202ee26b1e35f76c965bb6c0 Mon Sep 17 00:00:00 2001 From: Jacek Lawrynowicz Date: Thu, 3 Mar 2016 15:38:02 +0100 Subject: PCI: Add support for multiple DMA aliases Solve IOMMU support issues with PCIe non-transparent bridges that use Requester ID look-up tables (RID-LUT), e.g., the PEX8733. The NTB connects devices in two independent PCI domains. Devices separated by the NTB are not able to discover each other. A PCI packet being forwared from one domain to another has to have its RID modified so it appears on correct bus and completions are forwarded back to the original domain through the NTB. The RID is translated using a preprogrammed table (LUT) and the PCI packet propagates upstream away from the NTB. If the destination system has IOMMU enabled, the packet will be discarded because the new RID is unknown to the IOMMU. Adding a DMA alias for the new RID allows IOMMU to properly recognize the packet. Each device behind the NTB has a unique RID assigned in the RID-LUT. The current DMA alias implementation supports only a single alias, so it's not possible to support mutiple devices behind the NTB when IOMMU is enabled. Enable all possible aliases on a given bus (256) that are stored in a bitset. Alias devfn is directly translated to a bit number. The bitset is not allocated for devices that have no need for DMA aliases. More details can be found in the following article: http://www.plxtech.com/files/pdf/technical/expresslane/RTC_Enabling%20MulitHostSystemDesigns.pdf Signed-off-by: Jacek Lawrynowicz Signed-off-by: Bjorn Helgaas Reviewed-by: Alex Williamson Acked-by: David Woodhouse Acked-by: Joerg Roedel --- drivers/iommu/iommu.c | 10 +++------- drivers/pci/pci.c | 19 +++++++++++++++++-- drivers/pci/probe.c | 1 + drivers/pci/search.c | 14 +++++++++----- include/linux/pci.h | 5 ++--- 5 files changed, 32 insertions(+), 17 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index bfd4f7c3b1d8..1b49e940a318 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -660,8 +660,8 @@ static struct iommu_group *get_pci_function_alias_group(struct pci_dev *pdev, } /* - * Look for aliases to or from the given device for exisiting groups. The - * dma_alias_devfn only supports aliases on the same bus, therefore the search + * Look for aliases to or from the given device for existing groups. DMA + * aliases are only supported on the same bus, therefore the search * space is quite small (especially since we're really only looking at pcie * device, and therefore only expect multiple slots on the root complex or * downstream switch ports). It's conceivable though that a pair of @@ -686,11 +686,7 @@ static struct iommu_group *get_pci_alias_group(struct pci_dev *pdev, continue; /* We alias them or they alias us */ - if (((pdev->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) && - pdev->dma_alias_devfn == tmp->devfn) || - ((tmp->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN) && - tmp->dma_alias_devfn == pdev->devfn)) { - + if (pci_devs_are_dma_aliases(pdev, tmp)) { group = get_pci_alias_group(tmp, devfns); if (group) { pci_dev_put(tmp); diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index c82ebd0f6982..0b90c2186f1c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -4588,12 +4588,27 @@ int pci_set_vga_state(struct pci_dev *dev, bool decode, */ void pci_add_dma_alias(struct pci_dev *dev, u8 devfn) { - dev->dma_alias_devfn = devfn; - dev->dev_flags |= PCI_DEV_FLAGS_DMA_ALIAS_DEVFN; + if (!dev->dma_alias_mask) + dev->dma_alias_mask = kcalloc(BITS_TO_LONGS(U8_MAX), + sizeof(long), GFP_KERNEL); + if (!dev->dma_alias_mask) { + dev_warn(&dev->dev, "Unable to allocate DMA alias mask\n"); + return; + } + + set_bit(devfn, dev->dma_alias_mask); dev_info(&dev->dev, "Enabling fixed DMA alias to %02x.%d\n", PCI_SLOT(devfn), PCI_FUNC(devfn)); } +bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2) +{ + return (dev1->dma_alias_mask && + test_bit(dev2->devfn, dev1->dma_alias_mask)) || + (dev2->dma_alias_mask && + test_bit(dev1->devfn, dev2->dma_alias_mask)); +} + bool pci_device_is_present(struct pci_dev *pdev) { u32 v; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index 8004f67c57ec..ae7daeb83e21 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1537,6 +1537,7 @@ static void pci_release_dev(struct device *dev) pcibios_release_device(pci_dev); pci_bus_put(pci_dev->bus); kfree(pci_dev->driver_override); + kfree(pci_dev->dma_alias_mask); kfree(pci_dev); } diff --git a/drivers/pci/search.c b/drivers/pci/search.c index a20ce7d5e2a7..33e0f033a48e 100644 --- a/drivers/pci/search.c +++ b/drivers/pci/search.c @@ -40,11 +40,15 @@ int pci_for_each_dma_alias(struct pci_dev *pdev, * If the device is broken and uses an alias requester ID for * DMA, iterate over that too. */ - if (unlikely(pdev->dev_flags & PCI_DEV_FLAGS_DMA_ALIAS_DEVFN)) { - ret = fn(pdev, PCI_DEVID(pdev->bus->number, - pdev->dma_alias_devfn), data); - if (ret) - return ret; + if (unlikely(pdev->dma_alias_mask)) { + u8 devfn; + + for_each_set_bit(devfn, pdev->dma_alias_mask, U8_MAX) { + ret = fn(pdev, PCI_DEVID(pdev->bus->number, devfn), + data); + if (ret) + return ret; + } } for (bus = pdev->bus; !pci_is_root_bus(bus); bus = bus->parent) { diff --git a/include/linux/pci.h b/include/linux/pci.h index 7e7019064437..5581d05f7833 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -166,8 +166,6 @@ enum pci_dev_flags { PCI_DEV_FLAGS_ASSIGNED = (__force pci_dev_flags_t) (1 << 2), /* Flag for quirk use to store if quirk-specific ACS is enabled */ PCI_DEV_FLAGS_ACS_ENABLED_QUIRK = (__force pci_dev_flags_t) (1 << 3), - /* Flag to indicate the device uses dma_alias_devfn */ - PCI_DEV_FLAGS_DMA_ALIAS_DEVFN = (__force pci_dev_flags_t) (1 << 4), /* Use a PCIe-to-PCI bridge alias even if !pci_is_pcie */ PCI_DEV_FLAG_PCIE_BRIDGE_ALIAS = (__force pci_dev_flags_t) (1 << 5), /* Do not use bus resets for device */ @@ -273,7 +271,7 @@ struct pci_dev { u8 rom_base_reg; /* which config register controls the ROM */ u8 pin; /* which interrupt pin this device uses */ u16 pcie_flags_reg; /* cached PCIe Capabilities Register */ - u8 dma_alias_devfn;/* devfn of DMA alias, if any */ + unsigned long *dma_alias_mask;/* mask of enabled devfn aliases */ struct pci_driver *driver; /* which driver has allocated this device */ u64 dma_mask; /* Mask of the bits of bus address this @@ -1989,6 +1987,7 @@ static inline struct eeh_dev *pci_dev_to_eeh_dev(struct pci_dev *pdev) #endif void pci_add_dma_alias(struct pci_dev *dev, u8 devfn); +bool pci_devs_are_dma_aliases(struct pci_dev *dev1, struct pci_dev *dev2); int pci_for_each_dma_alias(struct pci_dev *pdev, int (*fn)(struct pci_dev *pdev, u16 alias, void *data), void *data); -- cgit v1.2.3 From c1d61c9bb163e696bf06850bcabbd26386554489 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Thu, 31 Mar 2016 16:34:32 -0600 Subject: PCI: Reverse standard ACS vs device-specific ACS enabling The original thought was that if a device implemented ACS, then surely we want to use that... well, it turns out that devices can make an ACS capability so broken that we still need to fall back to quirks. Reverse the order of ACS enabling to give quirks first shot at it. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 10 ++++------ drivers/pci/quirks.c | 6 ++++-- include/linux/pci.h | 7 +++++-- 3 files changed, 13 insertions(+), 10 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 25e0327d4429..c98c4e2aed3c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2547,7 +2547,7 @@ void pci_request_acs(void) * pci_std_enable_acs - enable ACS on devices using standard ACS capabilites * @dev: the PCI device */ -static int pci_std_enable_acs(struct pci_dev *dev) +static void pci_std_enable_acs(struct pci_dev *dev) { int pos; u16 cap; @@ -2555,7 +2555,7 @@ static int pci_std_enable_acs(struct pci_dev *dev) pos = pci_find_ext_capability(dev, PCI_EXT_CAP_ID_ACS); if (!pos) - return -ENODEV; + return; pci_read_config_word(dev, pos + PCI_ACS_CAP, &cap); pci_read_config_word(dev, pos + PCI_ACS_CTRL, &ctrl); @@ -2573,8 +2573,6 @@ static int pci_std_enable_acs(struct pci_dev *dev) ctrl |= (cap & PCI_ACS_UF); pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); - - return 0; } /** @@ -2586,10 +2584,10 @@ void pci_enable_acs(struct pci_dev *dev) if (!pci_acs_enable) return; - if (!pci_std_enable_acs(dev)) + if (!pci_dev_specific_enable_acs(dev)) return; - pci_dev_specific_enable_acs(dev); + pci_std_enable_acs(dev); } static bool pci_acs_flags_enabled(struct pci_dev *pdev, u16 acs_flags) diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index e248c2aad000..1f5c7898a246 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -4201,7 +4201,7 @@ static const struct pci_dev_enable_acs { { 0 } }; -void pci_dev_specific_enable_acs(struct pci_dev *dev) +int pci_dev_specific_enable_acs(struct pci_dev *dev) { const struct pci_dev_enable_acs *i; int ret; @@ -4213,9 +4213,11 @@ void pci_dev_specific_enable_acs(struct pci_dev *dev) i->device == (u16)PCI_ANY_ID)) { ret = i->enable_acs(dev); if (ret >= 0) - return; + return ret; } } + + return -ENOTTY; } /* diff --git a/include/linux/pci.h b/include/linux/pci.h index 004b8133417d..aaec79aee805 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1663,7 +1663,7 @@ enum pci_fixup_pass { #ifdef CONFIG_PCI_QUIRKS void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev); int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags); -void pci_dev_specific_enable_acs(struct pci_dev *dev); +int pci_dev_specific_enable_acs(struct pci_dev *dev); #else static inline void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) { } @@ -1672,7 +1672,10 @@ static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, { return -ENOTTY; } -static inline void pci_dev_specific_enable_acs(struct pci_dev *dev) { } +static inline int pci_dev_specific_enable_acs(struct pci_dev *dev) +{ + return -ENOTTY; +} #endif void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); -- cgit v1.2.3 From c5076cfe768998e9d395bc8486b29b18b0f99fd9 Mon Sep 17 00:00:00 2001 From: Tomasz Nowicki Date: Wed, 11 May 2016 17:34:51 -0500 Subject: PCI, of: Move PCI I/O space management to PCI core code No functional changes in this patch. PCI I/O space mapping code does not depend on OF; therefore it can be moved to PCI core code. This way we will be able to use it, e.g., in ACPI PCI code. Suggested-by: Lorenzo Pieralisi Signed-off-by: Tomasz Nowicki Signed-off-by: Bjorn Helgaas CC: Arnd Bergmann CC: Liviu Dudau --- drivers/of/address.c | 116 +-------------------------------------------- drivers/pci/pci.c | 115 ++++++++++++++++++++++++++++++++++++++++++++ include/linux/of_address.h | 9 ---- include/linux/pci.h | 5 ++ 4 files changed, 121 insertions(+), 124 deletions(-) (limited to 'include/linux/pci.h') diff --git a/drivers/of/address.c b/drivers/of/address.c index 91a469d55b8f..0a553c084a81 100644 --- a/drivers/of/address.c +++ b/drivers/of/address.c @@ -4,6 +4,7 @@ #include #include #include +#include #include #include #include @@ -673,121 +674,6 @@ const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, } EXPORT_SYMBOL(of_get_address); -#ifdef PCI_IOBASE -struct io_range { - struct list_head list; - phys_addr_t start; - resource_size_t size; -}; - -static LIST_HEAD(io_range_list); -static DEFINE_SPINLOCK(io_range_lock); -#endif - -/* - * Record the PCI IO range (expressed as CPU physical address + size). - * Return a negative value if an error has occured, zero otherwise - */ -int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size) -{ - int err = 0; - -#ifdef PCI_IOBASE - struct io_range *range; - resource_size_t allocated_size = 0; - - /* check if the range hasn't been previously recorded */ - spin_lock(&io_range_lock); - list_for_each_entry(range, &io_range_list, list) { - if (addr >= range->start && addr + size <= range->start + size) { - /* range already registered, bail out */ - goto end_register; - } - allocated_size += range->size; - } - - /* range not registed yet, check for available space */ - if (allocated_size + size - 1 > IO_SPACE_LIMIT) { - /* if it's too big check if 64K space can be reserved */ - if (allocated_size + SZ_64K - 1 > IO_SPACE_LIMIT) { - err = -E2BIG; - goto end_register; - } - - size = SZ_64K; - pr_warn("Requested IO range too big, new size set to 64K\n"); - } - - /* add the range to the list */ - range = kzalloc(sizeof(*range), GFP_ATOMIC); - if (!range) { - err = -ENOMEM; - goto end_register; - } - - range->start = addr; - range->size = size; - - list_add_tail(&range->list, &io_range_list); - -end_register: - spin_unlock(&io_range_lock); -#endif - - return err; -} - -phys_addr_t pci_pio_to_address(unsigned long pio) -{ - phys_addr_t address = (phys_addr_t)OF_BAD_ADDR; - -#ifdef PCI_IOBASE - struct io_range *range; - resource_size_t allocated_size = 0; - - if (pio > IO_SPACE_LIMIT) - return address; - - spin_lock(&io_range_lock); - list_for_each_entry(range, &io_range_list, list) { - if (pio >= allocated_size && pio < allocated_size + range->size) { - address = range->start + pio - allocated_size; - break; - } - allocated_size += range->size; - } - spin_unlock(&io_range_lock); -#endif - - return address; -} - -unsigned long __weak pci_address_to_pio(phys_addr_t address) -{ -#ifdef PCI_IOBASE - struct io_range *res; - resource_size_t offset = 0; - unsigned long addr = -1; - - spin_lock(&io_range_lock); - list_for_each_entry(res, &io_range_list, list) { - if (address >= res->start && address < res->start + res->size) { - addr = address - res->start + offset; - break; - } - offset += res->size; - } - spin_unlock(&io_range_lock); - - return addr; -#else - if (address > IO_SPACE_LIMIT) - return (unsigned long)-1; - - return (unsigned long) address; -#endif -} - static int __of_address_to_resource(struct device_node *dev, const __be32 *addrp, u64 size, unsigned int flags, const char *name, struct resource *r) diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 25e0327d4429..bc0c914b8afc 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3021,6 +3021,121 @@ int pci_request_regions_exclusive(struct pci_dev *pdev, const char *res_name) } EXPORT_SYMBOL(pci_request_regions_exclusive); +#ifdef PCI_IOBASE +struct io_range { + struct list_head list; + phys_addr_t start; + resource_size_t size; +}; + +static LIST_HEAD(io_range_list); +static DEFINE_SPINLOCK(io_range_lock); +#endif + +/* + * Record the PCI IO range (expressed as CPU physical address + size). + * Return a negative value if an error has occured, zero otherwise + */ +int __weak pci_register_io_range(phys_addr_t addr, resource_size_t size) +{ + int err = 0; + +#ifdef PCI_IOBASE + struct io_range *range; + resource_size_t allocated_size = 0; + + /* check if the range hasn't been previously recorded */ + spin_lock(&io_range_lock); + list_for_each_entry(range, &io_range_list, list) { + if (addr >= range->start && addr + size <= range->start + size) { + /* range already registered, bail out */ + goto end_register; + } + allocated_size += range->size; + } + + /* range not registed yet, check for available space */ + if (allocated_size + size - 1 > IO_SPACE_LIMIT) { + /* if it's too big check if 64K space can be reserved */ + if (allocated_size + SZ_64K - 1 > IO_SPACE_LIMIT) { + err = -E2BIG; + goto end_register; + } + + size = SZ_64K; + pr_warn("Requested IO range too big, new size set to 64K\n"); + } + + /* add the range to the list */ + range = kzalloc(sizeof(*range), GFP_ATOMIC); + if (!range) { + err = -ENOMEM; + goto end_register; + } + + range->start = addr; + range->size = size; + + list_add_tail(&range->list, &io_range_list); + +end_register: + spin_unlock(&io_range_lock); +#endif + + return err; +} + +phys_addr_t pci_pio_to_address(unsigned long pio) +{ + phys_addr_t address = (phys_addr_t)OF_BAD_ADDR; + +#ifdef PCI_IOBASE + struct io_range *range; + resource_size_t allocated_size = 0; + + if (pio > IO_SPACE_LIMIT) + return address; + + spin_lock(&io_range_lock); + list_for_each_entry(range, &io_range_list, list) { + if (pio >= allocated_size && pio < allocated_size + range->size) { + address = range->start + pio - allocated_size; + break; + } + allocated_size += range->size; + } + spin_unlock(&io_range_lock); +#endif + + return address; +} + +unsigned long __weak pci_address_to_pio(phys_addr_t address) +{ +#ifdef PCI_IOBASE + struct io_range *res; + resource_size_t offset = 0; + unsigned long addr = -1; + + spin_lock(&io_range_lock); + list_for_each_entry(res, &io_range_list, list) { + if (address >= res->start && address < res->start + res->size) { + addr = address - res->start + offset; + break; + } + offset += res->size; + } + spin_unlock(&io_range_lock); + + return addr; +#else + if (address > IO_SPACE_LIMIT) + return (unsigned long)-1; + + return (unsigned long) address; +#endif +} + /** * pci_remap_iospace - Remap the memory mapped I/O space * @res: Resource describing the I/O space diff --git a/include/linux/of_address.h b/include/linux/of_address.h index 01c0a556448b..37864734ca50 100644 --- a/include/linux/of_address.h +++ b/include/linux/of_address.h @@ -47,10 +47,6 @@ void __iomem *of_io_request_and_map(struct device_node *device, extern const __be32 *of_get_address(struct device_node *dev, int index, u64 *size, unsigned int *flags); -extern int pci_register_io_range(phys_addr_t addr, resource_size_t size); -extern unsigned long pci_address_to_pio(phys_addr_t addr); -extern phys_addr_t pci_pio_to_address(unsigned long pio); - extern int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node); extern struct of_pci_range *of_pci_range_parser_one( @@ -86,11 +82,6 @@ static inline const __be32 *of_get_address(struct device_node *dev, int index, return NULL; } -static inline phys_addr_t pci_pio_to_address(unsigned long pio) -{ - return 0; -} - static inline int of_pci_range_parser_init(struct of_pci_range_parser *parser, struct device_node *node) { diff --git a/include/linux/pci.h b/include/linux/pci.h index 004b8133417d..1824ef80e10d 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1164,6 +1164,9 @@ int __must_check pci_bus_alloc_resource(struct pci_bus *bus, void *alignf_data); +int pci_register_io_range(phys_addr_t addr, resource_size_t size); +unsigned long pci_address_to_pio(phys_addr_t addr); +phys_addr_t pci_pio_to_address(unsigned long pio); int pci_remap_iospace(const struct resource *res, phys_addr_t phys_addr); static inline pci_bus_addr_t pci_bus_address(struct pci_dev *pdev, int bar) @@ -1480,6 +1483,8 @@ static inline int pci_request_regions(struct pci_dev *dev, const char *res_name) { return -EIO; } static inline void pci_release_regions(struct pci_dev *dev) { } +static inline unsigned long pci_address_to_pio(phys_addr_t addr) { return -1; } + static inline void pci_block_cfg_access(struct pci_dev *dev) { } static inline int pci_block_cfg_access_in_atomic(struct pci_dev *dev) { return 0; } -- cgit v1.2.3