From 12ea6cad1c7d046e21decc18b0e2170c6794dc51 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 11 Jun 2012 05:26:55 +0000 Subject: PCI: add PCI DMA source ID quirk DMA transactions are tagged with the source ID of the device making the request. Occasionally hardware screws this up and uses the source ID of a different device (often the wrong function number of a multifunction device). A specific Ricoh multifunction device is a prime example of this problem and included in this patch. Given a pci_dev, this function returns the pci_dev to use as the source ID for DMA. When hardware works correctly, this returns the input device. For the components of the Ricoh multifunction device, it returns the pci_dev for function 0. This will be used by IOMMU drivers for determining the boundaries of IOMMU groups as multiple devices using the same source ID must be contained within the same group. This can also be used by existing streaming DMA paths for the same purpose. [bhelgaas: fold in pci_dev_get() for !CONFIG_PCI] Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 8 ++++++++ 1 file changed, 8 insertions(+) (limited to 'include') diff --git a/include/linux/pci.h b/include/linux/pci.h index d8c379dba6ad..39983be7b25b 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1332,6 +1332,9 @@ static inline struct pci_dev *pci_get_bus_and_slot(unsigned int bus, static inline int pci_domain_nr(struct pci_bus *bus) { return 0; } +static inline struct pci_dev *pci_dev_get(struct pci_dev *dev) +{ return NULL; } + #define dev_is_pci(d) (false) #define dev_is_pf(d) (false) #define dev_num_vf(d) (0) @@ -1486,9 +1489,14 @@ 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); #else static inline void pci_fixup_device(enum pci_fixup_pass pass, struct pci_dev *dev) {} +static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev) +{ + return pci_dev_get(dev); +} #endif void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); -- cgit v1.2.3 From ad805758c0eb25bce7b2e3b298d63dc62a1bc71c Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 11 Jun 2012 05:27:07 +0000 Subject: PCI: add ACS validation utility In a PCI environment, transactions aren't always required to reach the root bus before being re-routed. Intermediate switches between an endpoint and the root bus can redirect DMA back downstream before things like IOMMUs have a chance to intervene. Legacy PCI is always susceptible to this as it operates on a shared bus. PCIe added a new capability to describe and control this behavior, Access Control Services, or ACS. The utility function pci_acs_enabled() allows us to test the ACS capabilities of an individual devices against a set of flags while pci_acs_path_enabled() tests a complete path from a given downstream device up to the specified upstream device. We also include the ability to add device specific tests as it's likely we'll see devices that do not implement ACS, but want to indicate support for various capabilities in this space. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 69 ++++++++++++++++++++++++++++++++++++++++++++++++++++ drivers/pci/quirks.c | 33 +++++++++++++++++++++++++ include/linux/pci.h | 10 +++++++- 3 files changed, 111 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 447e83472c01..1ccf7d49f522 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -2359,6 +2359,75 @@ void pci_enable_acs(struct pci_dev *dev) pci_write_config_word(dev, pos + PCI_ACS_CTRL, ctrl); } +/** + * pci_acs_enabled - test ACS against required flags for a given device + * @pdev: device to test + * @acs_flags: required PCI ACS flags + * + * Return true if the device supports the provided flags. Automatically + * filters out flags that are not implemented on multifunction devices. + */ +bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags) +{ + int pos, ret; + u16 ctrl; + + ret = pci_dev_specific_acs_enabled(pdev, acs_flags); + if (ret >= 0) + return ret > 0; + + if (!pci_is_pcie(pdev)) + return false; + + /* Filter out flags not applicable to multifunction */ + if (pdev->multifunction) + acs_flags &= (PCI_ACS_RR | PCI_ACS_CR | + PCI_ACS_EC | PCI_ACS_DT); + + if (pdev->pcie_type == PCI_EXP_TYPE_DOWNSTREAM || + pdev->pcie_type == PCI_EXP_TYPE_ROOT_PORT || + pdev->multifunction) { + pos = pci_find_ext_capability(pdev, PCI_EXT_CAP_ID_ACS); + if (!pos) + return false; + + pci_read_config_word(pdev, pos + PCI_ACS_CTRL, &ctrl); + if ((ctrl & acs_flags) != acs_flags) + return false; + } + + return true; +} + +/** + * pci_acs_path_enable - test ACS flags from start to end in a hierarchy + * @start: starting downstream device + * @end: ending upstream device or NULL to search to the root bus + * @acs_flags: required flags + * + * Walk up a device tree from start to end testing PCI ACS support. If + * any step along the way does not support the required flags, return false. + */ +bool pci_acs_path_enabled(struct pci_dev *start, + struct pci_dev *end, u16 acs_flags) +{ + struct pci_dev *pdev, *parent = start; + + do { + pdev = parent; + + if (!pci_acs_enabled(pdev, acs_flags)) + return false; + + if (pci_is_root_bus(pdev->bus)) + return (end == NULL); + + parent = pdev->bus->self; + } while (pdev != end); + + return true; +} + /** * pci_swizzle_interrupt_pin - swizzle INTx for device behind bridge * @dev: the PCI device diff --git a/drivers/pci/quirks.c b/drivers/pci/quirks.c index acd3956b44bd..27e2c8f4ec73 100644 --- a/drivers/pci/quirks.c +++ b/drivers/pci/quirks.c @@ -3230,3 +3230,36 @@ struct pci_dev *pci_get_dma_source(struct pci_dev *dev) return pci_dev_get(dev); } + +static const struct pci_dev_acs_enabled { + u16 vendor; + u16 device; + int (*acs_enabled)(struct pci_dev *dev, u16 acs_flags); +} pci_dev_acs_enabled[] = { + { 0 } +}; + +int pci_dev_specific_acs_enabled(struct pci_dev *dev, u16 acs_flags) +{ + const struct pci_dev_acs_enabled *i; + int ret; + + /* + * Allow devices that do not expose standard PCIe ACS capabilities + * or control to indicate their support here. Multi-function express + * devices which do not allow internal peer-to-peer between functions, + * but do not implement PCIe ACS may wish to return true here. + */ + for (i = pci_dev_acs_enabled; i->acs_enabled; i++) { + if ((i->vendor == dev->vendor || + i->vendor == (u16)PCI_ANY_ID) && + (i->device == dev->device || + i->device == (u16)PCI_ANY_ID)) { + ret = i->acs_enabled(dev, acs_flags); + if (ret >= 0) + return ret; + } + } + + return -ENOTTY; +} diff --git a/include/linux/pci.h b/include/linux/pci.h index 39983be7b25b..dd7af0f37b3a 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1490,6 +1490,7 @@ 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); +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, struct pci_dev *dev) {} @@ -1497,6 +1498,11 @@ static inline struct pci_dev *pci_get_dma_source(struct pci_dev *dev) { return pci_dev_get(dev); } +static inline int pci_dev_specific_acs_enabled(struct pci_dev *dev, + u16 acs_flags) +{ + return -ENOTTY; +} #endif void __iomem *pcim_iomap(struct pci_dev *pdev, int bar, unsigned long maxlen); @@ -1599,7 +1605,9 @@ static inline bool pci_is_pcie(struct pci_dev *dev) } void pci_request_acs(void); - +bool pci_acs_enabled(struct pci_dev *pdev, u16 acs_flags); +bool pci_acs_path_enabled(struct pci_dev *start, + struct pci_dev *end, u16 acs_flags); #define PCI_VPD_LRDT 0x80 /* Large Resource Data Type */ #define PCI_VPD_LRDT_ID(x) (x | PCI_VPD_LRDT) -- cgit v1.2.3 From c63587d7f5b9db84e71daf5962dc0394eb657da2 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 11 Jun 2012 05:27:19 +0000 Subject: PCI: export pci_user functions for use by other drivers VFIO PCI support will make use of these for user-initiated PCI config accesses. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/pci/access.c | 6 ++++-- drivers/pci/pci.h | 7 ------- include/linux/pci.h | 8 ++++++++ 3 files changed, 12 insertions(+), 9 deletions(-) (limited to 'include') diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 2a581642c237..ba91a7e17519 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -162,7 +162,8 @@ int pci_user_read_config_##size \ if (ret > 0) \ ret = -EINVAL; \ return ret; \ -} +} \ +EXPORT_SYMBOL_GPL(pci_user_read_config_##size); /* Returns 0 on success, negative values indicate error. */ #define PCI_USER_WRITE_CONFIG(size,type) \ @@ -181,7 +182,8 @@ int pci_user_write_config_##size \ if (ret > 0) \ ret = -EINVAL; \ return ret; \ -} +} \ +EXPORT_SYMBOL_GPL(pci_user_write_config_##size); PCI_USER_READ_CONFIG(byte, u8) PCI_USER_READ_CONFIG(word, u16) diff --git a/drivers/pci/pci.h b/drivers/pci/pci.h index e4943479b234..f2dcc46bdece 100644 --- a/drivers/pci/pci.h +++ b/drivers/pci/pci.h @@ -86,13 +86,6 @@ static inline bool pci_is_bridge(struct pci_dev *pci_dev) return !!(pci_dev->subordinate); } -extern int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val); -extern int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val); -extern int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val); -extern int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val); -extern int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val); -extern int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val); - struct pci_vpd_ops { ssize_t (*read)(struct pci_dev *dev, loff_t pos, size_t count, void *buf); ssize_t (*write)(struct pci_dev *dev, loff_t pos, size_t count, const void *buf); diff --git a/include/linux/pci.h b/include/linux/pci.h index dd7af0f37b3a..9d04599c6bd9 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -777,6 +777,14 @@ static inline int pci_write_config_dword(const struct pci_dev *dev, int where, return pci_bus_write_config_dword(dev->bus, dev->devfn, where, val); } +/* user-space driven config access */ +int pci_user_read_config_byte(struct pci_dev *dev, int where, u8 *val); +int pci_user_read_config_word(struct pci_dev *dev, int where, u16 *val); +int pci_user_read_config_dword(struct pci_dev *dev, int where, u32 *val); +int pci_user_write_config_byte(struct pci_dev *dev, int where, u8 val); +int pci_user_write_config_word(struct pci_dev *dev, int where, u16 val); +int pci_user_write_config_dword(struct pci_dev *dev, int where, u32 val); + int __must_check pci_enable_device(struct pci_dev *dev); int __must_check pci_enable_device_io(struct pci_dev *dev); int __must_check pci_enable_device_mem(struct pci_dev *dev); -- cgit v1.2.3 From a6961651408afa9387d6df43c4a1dc4fd35dcb1b Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 11 Jun 2012 05:27:33 +0000 Subject: PCI: create common pcibios_err_to_errno For returning errors out to non-PCI code. Re-name xen's version. Acked-by: Konrad Rzeszutek Wilk Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- drivers/xen/xen-pciback/conf_space.c | 6 +++--- include/linux/pci.h | 26 ++++++++++++++++++++++++++ 2 files changed, 29 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/xen/xen-pciback/conf_space.c b/drivers/xen/xen-pciback/conf_space.c index 30d7be026c18..46ae0f9f02ad 100644 --- a/drivers/xen/xen-pciback/conf_space.c +++ b/drivers/xen/xen-pciback/conf_space.c @@ -124,7 +124,7 @@ static inline u32 merge_value(u32 val, u32 new_val, u32 new_val_mask, return val; } -static int pcibios_err_to_errno(int err) +static int xen_pcibios_err_to_errno(int err) { switch (err) { case PCIBIOS_SUCCESSFUL: @@ -202,7 +202,7 @@ out: pci_name(dev), size, offset, value); *ret_val = value; - return pcibios_err_to_errno(err); + return xen_pcibios_err_to_errno(err); } int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value) @@ -290,7 +290,7 @@ int xen_pcibk_config_write(struct pci_dev *dev, int offset, int size, u32 value) } } - return pcibios_err_to_errno(err); + return xen_pcibios_err_to_errno(err); } void xen_pcibk_config_free_dyn_fields(struct pci_dev *dev) diff --git a/include/linux/pci.h b/include/linux/pci.h index 9d04599c6bd9..a691f62bcf89 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -474,6 +474,32 @@ static inline bool pci_dev_msi_enabled(struct pci_dev *pci_dev) { return false; #define PCIBIOS_SET_FAILED 0x88 #define PCIBIOS_BUFFER_TOO_SMALL 0x89 +/* + * Translate above to generic errno for passing back through non-pci. + */ +static inline int pcibios_err_to_errno(int err) +{ + if (err <= PCIBIOS_SUCCESSFUL) + return err; /* Assume already errno */ + + switch (err) { + case PCIBIOS_FUNC_NOT_SUPPORTED: + return -ENOENT; + case PCIBIOS_BAD_VENDOR_ID: + return -EINVAL; + case PCIBIOS_DEVICE_NOT_FOUND: + return -ENODEV; + case PCIBIOS_BAD_REGISTER_NUMBER: + return -EFAULT; + case PCIBIOS_SET_FAILED: + return -EIO; + case PCIBIOS_BUFFER_TOO_SMALL: + return -ENOSPC; + } + + return -ENOTTY; +} + /* Low-level architecture-dependent routines */ struct pci_ops { -- cgit v1.2.3 From a0dee2ed0cdc666b5622f1fc74979355a6b36850 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Mon, 11 Jun 2012 05:27:45 +0000 Subject: PCI: misc pci_reg additions Fill in many missing definitions and add sizeof fields for many sections allowing for more extensive config parsing. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas --- include/linux/pci_regs.h | 113 ++++++++++++++++++++++++++++++++++++++++++----- 1 file changed, 101 insertions(+), 12 deletions(-) (limited to 'include') diff --git a/include/linux/pci_regs.h b/include/linux/pci_regs.h index 4b608f543412..526d2c4bc3a6 100644 --- a/include/linux/pci_regs.h +++ b/include/linux/pci_regs.h @@ -26,6 +26,7 @@ * Under PCI, each device has 256 bytes of configuration address space, * of which the first 64 bytes are standardized as follows: */ +#define PCI_STD_HEADER_SIZEOF 64 #define PCI_VENDOR_ID 0x00 /* 16 bits */ #define PCI_DEVICE_ID 0x02 /* 16 bits */ #define PCI_COMMAND 0x04 /* 16 bits */ @@ -209,9 +210,12 @@ #define PCI_CAP_ID_SHPC 0x0C /* PCI Standard Hot-Plug Controller */ #define PCI_CAP_ID_SSVID 0x0D /* Bridge subsystem vendor/device ID */ #define PCI_CAP_ID_AGP3 0x0E /* AGP Target PCI-PCI bridge */ +#define PCI_CAP_ID_SECDEV 0x0F /* Secure Device */ #define PCI_CAP_ID_EXP 0x10 /* PCI Express */ #define PCI_CAP_ID_MSIX 0x11 /* MSI-X */ +#define PCI_CAP_ID_SATA 0x12 /* SATA Data/Index Conf. */ #define PCI_CAP_ID_AF 0x13 /* PCI Advanced Features */ +#define PCI_CAP_ID_MAX PCI_CAP_ID_AF #define PCI_CAP_LIST_NEXT 1 /* Next capability in the list */ #define PCI_CAP_FLAGS 2 /* Capability defined flags (16 bits) */ #define PCI_CAP_SIZEOF 4 @@ -276,6 +280,7 @@ #define PCI_VPD_ADDR_MASK 0x7fff /* Address mask */ #define PCI_VPD_ADDR_F 0x8000 /* Write 0, 1 indicates completion */ #define PCI_VPD_DATA 4 /* 32-bits of data returned here */ +#define PCI_CAP_VPD_SIZEOF 8 /* Slot Identification */ @@ -297,8 +302,10 @@ #define PCI_MSI_ADDRESS_HI 8 /* Upper 32 bits (if PCI_MSI_FLAGS_64BIT set) */ #define PCI_MSI_DATA_32 8 /* 16 bits of data for 32-bit devices */ #define PCI_MSI_MASK_32 12 /* Mask bits register for 32-bit devices */ +#define PCI_MSI_PENDING_32 16 /* Pending intrs for 32-bit devices */ #define PCI_MSI_DATA_64 12 /* 16 bits of data for 64-bit devices */ #define PCI_MSI_MASK_64 16 /* Mask bits register for 64-bit devices */ +#define PCI_MSI_PENDING_64 20 /* Pending intrs for 64-bit devices */ /* MSI-X registers */ #define PCI_MSIX_FLAGS 2 @@ -308,6 +315,7 @@ #define PCI_MSIX_TABLE 4 #define PCI_MSIX_PBA 8 #define PCI_MSIX_FLAGS_BIRMASK (7 << 0) +#define PCI_CAP_MSIX_SIZEOF 12 /* size of MSIX registers */ /* MSI-X entry's format */ #define PCI_MSIX_ENTRY_SIZE 16 @@ -338,6 +346,7 @@ #define PCI_AF_CTRL_FLR 0x01 #define PCI_AF_STATUS 5 #define PCI_AF_STATUS_TP 0x01 +#define PCI_CAP_AF_SIZEOF 6 /* size of AF registers */ /* PCI-X registers */ @@ -374,6 +383,10 @@ #define PCI_X_STATUS_SPL_ERR 0x20000000 /* Rcvd Split Completion Error Msg */ #define PCI_X_STATUS_266MHZ 0x40000000 /* 266 MHz capable */ #define PCI_X_STATUS_533MHZ 0x80000000 /* 533 MHz capable */ +#define PCI_X_ECC_CSR 8 /* ECC control and status */ +#define PCI_CAP_PCIX_SIZEOF_V0 8 /* size of registers for Version 0 */ +#define PCI_CAP_PCIX_SIZEOF_V1 24 /* size for Version 1 */ +#define PCI_CAP_PCIX_SIZEOF_V2 PCI_CAP_PCIX_SIZEOF_V1 /* Same for v2 */ /* PCI Bridge Subsystem ID registers */ @@ -462,6 +475,7 @@ #define PCI_EXP_LNKSTA_DLLLA 0x2000 /* Data Link Layer Link Active */ #define PCI_EXP_LNKSTA_LBMS 0x4000 /* Link Bandwidth Management Status */ #define PCI_EXP_LNKSTA_LABS 0x8000 /* Link Autonomous Bandwidth Status */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V1 20 /* v1 endpoints end here */ #define PCI_EXP_SLTCAP 20 /* Slot Capabilities */ #define PCI_EXP_SLTCAP_ABP 0x00000001 /* Attention Button Present */ #define PCI_EXP_SLTCAP_PCP 0x00000002 /* Power Controller Present */ @@ -521,6 +535,7 @@ #define PCI_EXP_OBFF_MSGA_EN 0x2000 /* OBFF enable with Message type A */ #define PCI_EXP_OBFF_MSGB_EN 0x4000 /* OBFF enable with Message type B */ #define PCI_EXP_OBFF_WAKE_EN 0x6000 /* OBFF using WAKE# signaling */ +#define PCI_CAP_EXP_ENDPOINT_SIZEOF_V2 44 /* v2 endpoints end here */ #define PCI_EXP_LNKCTL2 48 /* Link Control 2 */ #define PCI_EXP_SLTCTL2 56 /* Slot Control 2 */ @@ -529,23 +544,43 @@ #define PCI_EXT_CAP_VER(header) ((header >> 16) & 0xf) #define PCI_EXT_CAP_NEXT(header) ((header >> 20) & 0xffc) -#define PCI_EXT_CAP_ID_ERR 1 -#define PCI_EXT_CAP_ID_VC 2 -#define PCI_EXT_CAP_ID_DSN 3 -#define PCI_EXT_CAP_ID_PWR 4 -#define PCI_EXT_CAP_ID_VNDR 11 -#define PCI_EXT_CAP_ID_ACS 13 -#define PCI_EXT_CAP_ID_ARI 14 -#define PCI_EXT_CAP_ID_ATS 15 -#define PCI_EXT_CAP_ID_SRIOV 16 -#define PCI_EXT_CAP_ID_PRI 19 -#define PCI_EXT_CAP_ID_LTR 24 -#define PCI_EXT_CAP_ID_PASID 27 +#define PCI_EXT_CAP_ID_ERR 0x01 /* Advanced Error Reporting */ +#define PCI_EXT_CAP_ID_VC 0x02 /* Virtual Channel Capability */ +#define PCI_EXT_CAP_ID_DSN 0x03 /* Device Serial Number */ +#define PCI_EXT_CAP_ID_PWR 0x04 /* Power Budgeting */ +#define PCI_EXT_CAP_ID_RCLD 0x05 /* Root Complex Link Declaration */ +#define PCI_EXT_CAP_ID_RCILC 0x06 /* Root Complex Internal Link Control */ +#define PCI_EXT_CAP_ID_RCEC 0x07 /* Root Complex Event Collector */ +#define PCI_EXT_CAP_ID_MFVC 0x08 /* Multi-Function VC Capability */ +#define PCI_EXT_CAP_ID_VC9 0x09 /* same as _VC */ +#define PCI_EXT_CAP_ID_RCRB 0x0A /* Root Complex RB? */ +#define PCI_EXT_CAP_ID_VNDR 0x0B /* Vendor Specific */ +#define PCI_EXT_CAP_ID_CAC 0x0C /* Config Access - obsolete */ +#define PCI_EXT_CAP_ID_ACS 0x0D /* Access Control Services */ +#define PCI_EXT_CAP_ID_ARI 0x0E /* Alternate Routing ID */ +#define PCI_EXT_CAP_ID_ATS 0x0F /* Address Translation Services */ +#define PCI_EXT_CAP_ID_SRIOV 0x10 /* Single Root I/O Virtualization */ +#define PCI_EXT_CAP_ID_MRIOV 0x11 /* Multi Root I/O Virtualization */ +#define PCI_EXT_CAP_ID_MCAST 0x12 /* Multicast */ +#define PCI_EXT_CAP_ID_PRI 0x13 /* Page Request Interface */ +#define PCI_EXT_CAP_ID_AMD_XXX 0x14 /* reserved for AMD */ +#define PCI_EXT_CAP_ID_REBAR 0x15 /* resizable BAR */ +#define PCI_EXT_CAP_ID_DPA 0x16 /* dynamic power alloc */ +#define PCI_EXT_CAP_ID_TPH 0x17 /* TPH request */ +#define PCI_EXT_CAP_ID_LTR 0x18 /* latency tolerance reporting */ +#define PCI_EXT_CAP_ID_SECPCI 0x19 /* Secondary PCIe */ +#define PCI_EXT_CAP_ID_PMUX 0x1A /* Protocol Multiplexing */ +#define PCI_EXT_CAP_ID_PASID 0x1B /* Process Address Space ID */ +#define PCI_EXT_CAP_ID_MAX PCI_EXT_CAP_ID_PASID + +#define PCI_EXT_CAP_DSN_SIZEOF 12 +#define PCI_EXT_CAP_MCAST_ENDPOINT_SIZEOF 40 /* Advanced Error Reporting */ #define PCI_ERR_UNCOR_STATUS 4 /* Uncorrectable Error Status */ #define PCI_ERR_UNC_TRAIN 0x00000001 /* Training */ #define PCI_ERR_UNC_DLP 0x00000010 /* Data Link Protocol */ +#define PCI_ERR_UNC_SURPDN 0x00000020 /* Surprise Down */ #define PCI_ERR_UNC_POISON_TLP 0x00001000 /* Poisoned TLP */ #define PCI_ERR_UNC_FCP 0x00002000 /* Flow Control Protocol */ #define PCI_ERR_UNC_COMP_TIME 0x00004000 /* Completion Timeout */ @@ -555,6 +590,11 @@ #define PCI_ERR_UNC_MALF_TLP 0x00040000 /* Malformed TLP */ #define PCI_ERR_UNC_ECRC 0x00080000 /* ECRC Error Status */ #define PCI_ERR_UNC_UNSUP 0x00100000 /* Unsupported Request */ +#define PCI_ERR_UNC_ACSV 0x00200000 /* ACS Violation */ +#define PCI_ERR_UNC_INTN 0x00400000 /* internal error */ +#define PCI_ERR_UNC_MCBTLP 0x00800000 /* MC blocked TLP */ +#define PCI_ERR_UNC_ATOMEG 0x01000000 /* Atomic egress blocked */ +#define PCI_ERR_UNC_TLPPRE 0x02000000 /* TLP prefix blocked */ #define PCI_ERR_UNCOR_MASK 8 /* Uncorrectable Error Mask */ /* Same bits as above */ #define PCI_ERR_UNCOR_SEVER 12 /* Uncorrectable Error Severity */ @@ -565,6 +605,9 @@ #define PCI_ERR_COR_BAD_DLLP 0x00000080 /* Bad DLLP Status */ #define PCI_ERR_COR_REP_ROLL 0x00000100 /* REPLAY_NUM Rollover */ #define PCI_ERR_COR_REP_TIMER 0x00001000 /* Replay Timer Timeout */ +#define PCI_ERR_COR_ADV_NFAT 0x00002000 /* Advisory Non-Fatal */ +#define PCI_ERR_COR_INTERNAL 0x00004000 /* Corrected Internal */ +#define PCI_ERR_COR_LOG_OVER 0x00008000 /* Header Log Overflow */ #define PCI_ERR_COR_MASK 20 /* Correctable Error Mask */ /* Same bits as above */ #define PCI_ERR_CAP 24 /* Advanced Error Capabilities */ @@ -596,12 +639,18 @@ /* Virtual Channel */ #define PCI_VC_PORT_REG1 4 +#define PCI_VC_REG1_EVCC 0x7 /* extended vc count */ #define PCI_VC_PORT_REG2 8 +#define PCI_VC_REG2_32_PHASE 0x2 +#define PCI_VC_REG2_64_PHASE 0x4 +#define PCI_VC_REG2_128_PHASE 0x8 #define PCI_VC_PORT_CTRL 12 #define PCI_VC_PORT_STATUS 14 #define PCI_VC_RES_CAP 16 #define PCI_VC_RES_CTRL 20 #define PCI_VC_RES_STATUS 26 +#define PCI_CAP_VC_BASE_SIZEOF 0x10 +#define PCI_CAP_VC_PER_VC_SIZEOF 0x0C /* Power Budgeting */ #define PCI_PWR_DSR 4 /* Data Select Register */ @@ -614,6 +663,7 @@ #define PCI_PWR_DATA_RAIL(x) (((x) >> 18) & 7) /* Power Rail */ #define PCI_PWR_CAP 12 /* Capability */ #define PCI_PWR_CAP_BUDGET(x) ((x) & 1) /* Included in system budget */ +#define PCI_EXT_CAP_PWR_SIZEOF 16 /* * Hypertransport sub capability types @@ -646,6 +696,8 @@ #define HT_CAPTYPE_ERROR_RETRY 0xC0 /* Retry on error configuration */ #define HT_CAPTYPE_GEN3 0xD0 /* Generation 3 hypertransport configuration */ #define HT_CAPTYPE_PM 0xE0 /* Hypertransport powermanagement configuration */ +#define HT_CAP_SIZEOF_LONG 28 /* slave & primary */ +#define HT_CAP_SIZEOF_SHORT 24 /* host & secondary */ /* Alternative Routing-ID Interpretation */ #define PCI_ARI_CAP 0x04 /* ARI Capability Register */ @@ -656,6 +708,7 @@ #define PCI_ARI_CTRL_MFVC 0x0001 /* MFVC Function Groups Enable */ #define PCI_ARI_CTRL_ACS 0x0002 /* ACS Function Groups Enable */ #define PCI_ARI_CTRL_FG(x) (((x) >> 4) & 7) /* Function Group */ +#define PCI_EXT_CAP_ARI_SIZEOF 8 /* Address Translation Service */ #define PCI_ATS_CAP 0x04 /* ATS Capability Register */ @@ -665,6 +718,7 @@ #define PCI_ATS_CTRL_ENABLE 0x8000 /* ATS Enable */ #define PCI_ATS_CTRL_STU(x) ((x) & 0x1f) /* Smallest Translation Unit */ #define PCI_ATS_MIN_STU 12 /* shift of minimum STU block */ +#define PCI_EXT_CAP_ATS_SIZEOF 8 /* Page Request Interface */ #define PCI_PRI_CTRL 0x04 /* PRI control register */ @@ -676,6 +730,7 @@ #define PCI_PRI_STATUS_STOPPED 0x100 /* PRI Stopped */ #define PCI_PRI_MAX_REQ 0x08 /* PRI max reqs supported */ #define PCI_PRI_ALLOC_REQ 0x0c /* PRI max reqs allowed */ +#define PCI_EXT_CAP_PRI_SIZEOF 16 /* PASID capability */ #define PCI_PASID_CAP 0x04 /* PASID feature register */ @@ -685,6 +740,7 @@ #define PCI_PASID_CTRL_ENABLE 0x01 /* Enable bit */ #define PCI_PASID_CTRL_EXEC 0x02 /* Exec permissions Enable */ #define PCI_PASID_CTRL_PRIV 0x04 /* Priviledge Mode Enable */ +#define PCI_EXT_CAP_PASID_SIZEOF 8 /* Single Root I/O Virtualization */ #define PCI_SRIOV_CAP 0x04 /* SR-IOV Capabilities */ @@ -716,12 +772,14 @@ #define PCI_SRIOV_VFM_MI 0x1 /* Dormant.MigrateIn */ #define PCI_SRIOV_VFM_MO 0x2 /* Active.MigrateOut */ #define PCI_SRIOV_VFM_AV 0x3 /* Active.Available */ +#define PCI_EXT_CAP_SRIOV_SIZEOF 64 #define PCI_LTR_MAX_SNOOP_LAT 0x4 #define PCI_LTR_MAX_NOSNOOP_LAT 0x6 #define PCI_LTR_VALUE_MASK 0x000003ff #define PCI_LTR_SCALE_MASK 0x00001c00 #define PCI_LTR_SCALE_SHIFT 10 +#define PCI_EXT_CAP_LTR_SIZEOF 8 /* Access Control Service */ #define PCI_ACS_CAP 0x04 /* ACS Capability Register */ @@ -732,7 +790,38 @@ #define PCI_ACS_UF 0x10 /* Upstream Forwarding */ #define PCI_ACS_EC 0x20 /* P2P Egress Control */ #define PCI_ACS_DT 0x40 /* Direct Translated P2P */ +#define PCI_ACS_EGRESS_BITS 0x05 /* ACS Egress Control Vector Size */ #define PCI_ACS_CTRL 0x06 /* ACS Control Register */ #define PCI_ACS_EGRESS_CTL_V 0x08 /* ACS Egress Control Vector */ +#define PCI_VSEC_HDR 4 /* extended cap - vendor specific */ +#define PCI_VSEC_HDR_LEN_SHIFT 20 /* shift for length field */ + +/* sata capability */ +#define PCI_SATA_REGS 4 /* SATA REGs specifier */ +#define PCI_SATA_REGS_MASK 0xF /* location - BAR#/inline */ +#define PCI_SATA_REGS_INLINE 0xF /* REGS in config space */ +#define PCI_SATA_SIZEOF_SHORT 8 +#define PCI_SATA_SIZEOF_LONG 16 + +/* resizable BARs */ +#define PCI_REBAR_CTRL 8 /* control register */ +#define PCI_REBAR_CTRL_NBAR_MASK (7 << 5) /* mask for # bars */ +#define PCI_REBAR_CTRL_NBAR_SHIFT 5 /* shift for # bars */ + +/* dynamic power allocation */ +#define PCI_DPA_CAP 4 /* capability register */ +#define PCI_DPA_CAP_SUBSTATE_MASK 0x1F /* # substates - 1 */ +#define PCI_DPA_BASE_SIZEOF 16 /* size with 0 substates */ + +/* TPH Requester */ +#define PCI_TPH_CAP 4 /* capability register */ +#define PCI_TPH_CAP_LOC_MASK 0x600 /* location mask */ +#define PCI_TPH_LOC_NONE 0x000 /* no location */ +#define PCI_TPH_LOC_CAP 0x200 /* in capability */ +#define PCI_TPH_LOC_MSIX 0x400 /* in MSI-X */ +#define PCI_TPH_CAP_ST_MASK 0x07FF0000 /* st table mask */ +#define PCI_TPH_CAP_ST_SHIFT 16 /* st table shift */ +#define PCI_TPH_BASE_SIZEOF 12 /* size with no st table */ + #endif /* LINUX_PCI_REGS_H */ -- cgit v1.2.3 From 74416e1e07660798379ce10a210bf4fd35b84f9f Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 30 May 2012 14:18:41 -0600 Subject: driver core: Add iommu_group tracking to struct device IOMMU groups allow IOMMU drivers to represent DMA visibility and isolation of devices. Multiple devices may be grouped together for the purposes of DMA. Placing a pointer on struct device enable easy access for things like streaming DMA programming and drivers like VFIO. Signed-off-by: Alex Williamson Acked-by: Greg Kroah-Hartman Acked-by: Benjamin Herrenschmidt Signed-off-by: Joerg Roedel --- include/linux/device.h | 2 ++ 1 file changed, 2 insertions(+) (limited to 'include') diff --git a/include/linux/device.h b/include/linux/device.h index 161d96241b1b..d0e4d99405ae 100644 --- a/include/linux/device.h +++ b/include/linux/device.h @@ -36,6 +36,7 @@ struct subsys_private; struct bus_type; struct device_node; struct iommu_ops; +struct iommu_group; struct bus_attribute { struct attribute attr; @@ -687,6 +688,7 @@ struct device { const struct attribute_group **groups; /* optional groups */ void (*release)(struct device *dev); + struct iommu_group *iommu_group; }; /* Get the wakeup routines, which depend on struct device */ -- cgit v1.2.3 From d72e31c9374627068df29da8085ca18c92ae35d3 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Wed, 30 May 2012 14:18:53 -0600 Subject: iommu: IOMMU Groups IOMMU device groups are currently a rather vague associative notion with assembly required by the user or user level driver provider to do anything useful. This patch intends to grow the IOMMU group concept into something a bit more consumable. To do this, we first create an object representing the group, struct iommu_group. This structure is allocated (iommu_group_alloc) and filled (iommu_group_add_device) by the iommu driver. The iommu driver is free to add devices to the group using it's own set of policies. This allows inclusion of devices based on physical hardware or topology limitations of the platform, as well as soft requirements, such as multi-function trust levels or peer-to-peer protection of the interconnects. Each device may only belong to a single iommu group, which is linked from struct device.iommu_group. IOMMU groups are maintained using kobject reference counting, allowing for automatic removal of empty, unreferenced groups. It is the responsibility of the iommu driver to remove devices from the group (iommu_group_remove_device). IOMMU groups also include a userspace representation in sysfs under /sys/kernel/iommu_groups. When allocated, each group is given a dynamically assign ID (int). The ID is managed by the core IOMMU group code to support multiple heterogeneous iommu drivers, which could potentially collide in group naming/numbering. This also keeps group IDs to small, easily managed values. A directory is created under /sys/kernel/iommu_groups for each group. A further subdirectory named "devices" contains links to each device within the group. The iommu_group file in the device's sysfs directory, which formerly contained a group number when read, is now a link to the iommu group. Example: $ ls -l /sys/kernel/iommu_groups/26/devices/ total 0 lrwxrwxrwx. 1 root root 0 Apr 17 12:57 0000:00:1e.0 -> ../../../../devices/pci0000:00/0000:00:1e.0 lrwxrwxrwx. 1 root root 0 Apr 17 12:57 0000:06:0d.0 -> ../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.0 lrwxrwxrwx. 1 root root 0 Apr 17 12:57 0000:06:0d.1 -> ../../../../devices/pci0000:00/0000:00:1e.0/0000:06:0d.1 $ ls -l /sys/kernel/iommu_groups/26/devices/*/iommu_group [truncating perms/owner/timestamp] /sys/kernel/iommu_groups/26/devices/0000:00:1e.0/iommu_group -> ../../../kernel/iommu_groups/26 /sys/kernel/iommu_groups/26/devices/0000:06:0d.0/iommu_group -> ../../../../kernel/iommu_groups/26 /sys/kernel/iommu_groups/26/devices/0000:06:0d.1/iommu_group -> ../../../../kernel/iommu_groups/26 Groups also include several exported functions for use by user level driver providers, for example VFIO. These include: iommu_group_get(): Acquires a reference to a group from a device iommu_group_put(): Releases reference iommu_group_for_each_dev(): Iterates over group devices using callback iommu_group_[un]register_notifier(): Allows notification of device add and remove operations relevant to the group iommu_group_id(): Return the group number This patch also extends the IOMMU API to allow attaching groups to domains. This is currently a simple wrapper for iterating through devices within a group, but it's expected that the IOMMU API may eventually make groups a more integral part of domains. Groups intentionally do not try to manage group ownership. A user level driver provider must independently acquire ownership for each device within a group before making use of the group as a whole. This may change in the future if group usage becomes more pervasive across both DMA and IOMMU ops. Groups intentionally do not provide a mechanism for driver locking or otherwise manipulating driver matching/probing of devices within the group. Such interfaces are generic to devices and beyond the scope of IOMMU groups. If implemented, user level providers have ready access via iommu_group_for_each_dev and group notifiers. iommu_device_group() is removed here as it has no users. The replacement is: group = iommu_group_get(dev); id = iommu_group_id(group); iommu_group_put(group); AMD-Vi & Intel VT-d support re-added in following patches. Signed-off-by: Alex Williamson Acked-by: Benjamin Herrenschmidt Signed-off-by: Joerg Roedel --- .../ABI/testing/sysfs-kernel-iommu_groups | 14 + drivers/iommu/amd_iommu.c | 21 - drivers/iommu/intel-iommu.c | 49 -- drivers/iommu/iommu.c | 578 +++++++++++++++++++-- include/linux/iommu.h | 104 +++- 5 files changed, 663 insertions(+), 103 deletions(-) create mode 100644 Documentation/ABI/testing/sysfs-kernel-iommu_groups (limited to 'include') diff --git a/Documentation/ABI/testing/sysfs-kernel-iommu_groups b/Documentation/ABI/testing/sysfs-kernel-iommu_groups new file mode 100644 index 000000000000..9b31556cfdda --- /dev/null +++ b/Documentation/ABI/testing/sysfs-kernel-iommu_groups @@ -0,0 +1,14 @@ +What: /sys/kernel/iommu_groups/ +Date: May 2012 +KernelVersion: v3.5 +Contact: Alex Williamson +Description: /sys/kernel/iommu_groups/ contains a number of sub- + directories, each representing an IOMMU group. The + name of the sub-directory matches the iommu_group_id() + for the group, which is an integer value. Within each + subdirectory is another directory named "devices" with + links to the sysfs devices contained in this group. + The group directory also optionally contains a "name" + file if the IOMMU driver has chosen to register a more + common name for the group. +Users: diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a2e418cba0ff..55283d6291c8 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3227,26 +3227,6 @@ static int amd_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } -static int amd_iommu_device_group(struct device *dev, unsigned int *groupid) -{ - struct iommu_dev_data *dev_data = dev->archdata.iommu; - struct pci_dev *pdev = to_pci_dev(dev); - u16 devid; - - if (!dev_data) - return -ENODEV; - - if (pdev->is_virtfn || !iommu_group_mf) - devid = dev_data->devid; - else - devid = calc_devid(pdev->bus->number, - PCI_DEVFN(PCI_SLOT(pdev->devfn), 0)); - - *groupid = amd_iommu_alias_table[devid]; - - return 0; -} - static struct iommu_ops amd_iommu_ops = { .domain_init = amd_iommu_domain_init, .domain_destroy = amd_iommu_domain_destroy, @@ -3256,7 +3236,6 @@ static struct iommu_ops amd_iommu_ops = { .unmap = amd_iommu_unmap, .iova_to_phys = amd_iommu_iova_to_phys, .domain_has_cap = amd_iommu_domain_has_cap, - .device_group = amd_iommu_device_group, .pgsize_bitmap = AMD_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/intel-iommu.c b/drivers/iommu/intel-iommu.c index b12af2ff8c54..c62f2df25221 100644 --- a/drivers/iommu/intel-iommu.c +++ b/drivers/iommu/intel-iommu.c @@ -4090,54 +4090,6 @@ static int intel_iommu_domain_has_cap(struct iommu_domain *domain, return 0; } -/* - * Group numbers are arbitrary. Device with the same group number - * indicate the iommu cannot differentiate between them. To avoid - * tracking used groups we just use the seg|bus|devfn of the lowest - * level we're able to differentiate devices - */ -static int intel_iommu_device_group(struct device *dev, unsigned int *groupid) -{ - struct pci_dev *pdev = to_pci_dev(dev); - struct pci_dev *bridge; - union { - struct { - u8 devfn; - u8 bus; - u16 segment; - } pci; - u32 group; - } id; - - if (iommu_no_mapping(dev)) - return -ENODEV; - - id.pci.segment = pci_domain_nr(pdev->bus); - id.pci.bus = pdev->bus->number; - id.pci.devfn = pdev->devfn; - - if (!device_to_iommu(id.pci.segment, id.pci.bus, id.pci.devfn)) - return -ENODEV; - - bridge = pci_find_upstream_pcie_bridge(pdev); - if (bridge) { - if (pci_is_pcie(bridge)) { - id.pci.bus = bridge->subordinate->number; - id.pci.devfn = 0; - } else { - id.pci.bus = bridge->bus->number; - id.pci.devfn = bridge->devfn; - } - } - - if (!pdev->is_virtfn && iommu_group_mf) - id.pci.devfn = PCI_DEVFN(PCI_SLOT(id.pci.devfn), 0); - - *groupid = id.group; - - return 0; -} - static struct iommu_ops intel_iommu_ops = { .domain_init = intel_iommu_domain_init, .domain_destroy = intel_iommu_domain_destroy, @@ -4147,7 +4099,6 @@ static struct iommu_ops intel_iommu_ops = { .unmap = intel_iommu_unmap, .iova_to_phys = intel_iommu_iova_to_phys, .domain_has_cap = intel_iommu_domain_has_cap, - .device_group = intel_iommu_device_group, .pgsize_bitmap = INTEL_IOMMU_PGSIZES, }; diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8b9ded88e6f5..0e928acd7dcf 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -26,60 +26,535 @@ #include #include #include +#include +#include +#include + +static struct kset *iommu_group_kset; +static struct ida iommu_group_ida; +static struct mutex iommu_group_mutex; + +struct iommu_group { + struct kobject kobj; + struct kobject *devices_kobj; + struct list_head devices; + struct mutex mutex; + struct blocking_notifier_head notifier; + void *iommu_data; + void (*iommu_data_release)(void *iommu_data); + char *name; + int id; +}; + +struct iommu_device { + struct list_head list; + struct device *dev; + char *name; +}; + +struct iommu_group_attribute { + struct attribute attr; + ssize_t (*show)(struct iommu_group *group, char *buf); + ssize_t (*store)(struct iommu_group *group, + const char *buf, size_t count); +}; + +#define IOMMU_GROUP_ATTR(_name, _mode, _show, _store) \ +struct iommu_group_attribute iommu_group_attr_##_name = \ + __ATTR(_name, _mode, _show, _store) -static ssize_t show_iommu_group(struct device *dev, - struct device_attribute *attr, char *buf) +#define to_iommu_group_attr(_attr) \ + container_of(_attr, struct iommu_group_attribute, attr) +#define to_iommu_group(_kobj) \ + container_of(_kobj, struct iommu_group, kobj) + +static ssize_t iommu_group_attr_show(struct kobject *kobj, + struct attribute *__attr, char *buf) { - unsigned int groupid; + struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); + struct iommu_group *group = to_iommu_group(kobj); + ssize_t ret = -EIO; - if (iommu_device_group(dev, &groupid)) - return 0; + if (attr->show) + ret = attr->show(group, buf); + return ret; +} + +static ssize_t iommu_group_attr_store(struct kobject *kobj, + struct attribute *__attr, + const char *buf, size_t count) +{ + struct iommu_group_attribute *attr = to_iommu_group_attr(__attr); + struct iommu_group *group = to_iommu_group(kobj); + ssize_t ret = -EIO; - return sprintf(buf, "%u", groupid); + if (attr->store) + ret = attr->store(group, buf, count); + return ret; } -static DEVICE_ATTR(iommu_group, S_IRUGO, show_iommu_group, NULL); -static int add_iommu_group(struct device *dev, void *data) +static const struct sysfs_ops iommu_group_sysfs_ops = { + .show = iommu_group_attr_show, + .store = iommu_group_attr_store, +}; + +static int iommu_group_create_file(struct iommu_group *group, + struct iommu_group_attribute *attr) +{ + return sysfs_create_file(&group->kobj, &attr->attr); +} + +static void iommu_group_remove_file(struct iommu_group *group, + struct iommu_group_attribute *attr) +{ + sysfs_remove_file(&group->kobj, &attr->attr); +} + +static ssize_t iommu_group_show_name(struct iommu_group *group, char *buf) +{ + return sprintf(buf, "%s\n", group->name); +} + +static IOMMU_GROUP_ATTR(name, S_IRUGO, iommu_group_show_name, NULL); + +static void iommu_group_release(struct kobject *kobj) +{ + struct iommu_group *group = to_iommu_group(kobj); + + if (group->iommu_data_release) + group->iommu_data_release(group->iommu_data); + + mutex_lock(&iommu_group_mutex); + ida_remove(&iommu_group_ida, group->id); + mutex_unlock(&iommu_group_mutex); + + kfree(group->name); + kfree(group); +} + +static struct kobj_type iommu_group_ktype = { + .sysfs_ops = &iommu_group_sysfs_ops, + .release = iommu_group_release, +}; + +/** + * iommu_group_alloc - Allocate a new group + * @name: Optional name to associate with group, visible in sysfs + * + * This function is called by an iommu driver to allocate a new iommu + * group. The iommu group represents the minimum granularity of the iommu. + * Upon successful return, the caller holds a reference to the supplied + * group in order to hold the group until devices are added. Use + * iommu_group_put() to release this extra reference count, allowing the + * group to be automatically reclaimed once it has no devices or external + * references. + */ +struct iommu_group *iommu_group_alloc(void) { - unsigned int groupid; + struct iommu_group *group; + int ret; + + group = kzalloc(sizeof(*group), GFP_KERNEL); + if (!group) + return ERR_PTR(-ENOMEM); + + group->kobj.kset = iommu_group_kset; + mutex_init(&group->mutex); + INIT_LIST_HEAD(&group->devices); + BLOCKING_INIT_NOTIFIER_HEAD(&group->notifier); + + mutex_lock(&iommu_group_mutex); + +again: + if (unlikely(0 == ida_pre_get(&iommu_group_ida, GFP_KERNEL))) { + kfree(group); + mutex_unlock(&iommu_group_mutex); + return ERR_PTR(-ENOMEM); + } + + if (-EAGAIN == ida_get_new(&iommu_group_ida, &group->id)) + goto again; + + mutex_unlock(&iommu_group_mutex); - if (iommu_device_group(dev, &groupid) == 0) - return device_create_file(dev, &dev_attr_iommu_group); + ret = kobject_init_and_add(&group->kobj, &iommu_group_ktype, + NULL, "%d", group->id); + if (ret) { + mutex_lock(&iommu_group_mutex); + ida_remove(&iommu_group_ida, group->id); + mutex_unlock(&iommu_group_mutex); + kfree(group); + return ERR_PTR(ret); + } + + group->devices_kobj = kobject_create_and_add("devices", &group->kobj); + if (!group->devices_kobj) { + kobject_put(&group->kobj); /* triggers .release & free */ + return ERR_PTR(-ENOMEM); + } + + /* + * The devices_kobj holds a reference on the group kobject, so + * as long as that exists so will the group. We can therefore + * use the devices_kobj for reference counting. + */ + kobject_put(&group->kobj); + + return group; +} +EXPORT_SYMBOL_GPL(iommu_group_alloc); + +/** + * iommu_group_get_iommudata - retrieve iommu_data registered for a group + * @group: the group + * + * iommu drivers can store data in the group for use when doing iommu + * operations. This function provides a way to retrieve it. Caller + * should hold a group reference. + */ +void *iommu_group_get_iommudata(struct iommu_group *group) +{ + return group->iommu_data; +} +EXPORT_SYMBOL_GPL(iommu_group_get_iommudata); + +/** + * iommu_group_set_iommudata - set iommu_data for a group + * @group: the group + * @iommu_data: new data + * @release: release function for iommu_data + * + * iommu drivers can store data in the group for use when doing iommu + * operations. This function provides a way to set the data after + * the group has been allocated. Caller should hold a group reference. + */ +void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data, + void (*release)(void *iommu_data)) +{ + group->iommu_data = iommu_data; + group->iommu_data_release = release; +} +EXPORT_SYMBOL_GPL(iommu_group_set_iommudata); + +/** + * iommu_group_set_name - set name for a group + * @group: the group + * @name: name + * + * Allow iommu driver to set a name for a group. When set it will + * appear in a name attribute file under the group in sysfs. + */ +int iommu_group_set_name(struct iommu_group *group, const char *name) +{ + int ret; + + if (group->name) { + iommu_group_remove_file(group, &iommu_group_attr_name); + kfree(group->name); + group->name = NULL; + if (!name) + return 0; + } + + group->name = kstrdup(name, GFP_KERNEL); + if (!group->name) + return -ENOMEM; + + ret = iommu_group_create_file(group, &iommu_group_attr_name); + if (ret) { + kfree(group->name); + group->name = NULL; + return ret; + } return 0; } +EXPORT_SYMBOL_GPL(iommu_group_set_name); -static int remove_iommu_group(struct device *dev) +/** + * iommu_group_add_device - add a device to an iommu group + * @group: the group into which to add the device (reference should be held) + * @dev: the device + * + * This function is called by an iommu driver to add a device into a + * group. Adding a device increments the group reference count. + */ +int iommu_group_add_device(struct iommu_group *group, struct device *dev) { - unsigned int groupid; + int ret, i = 0; + struct iommu_device *device; + + device = kzalloc(sizeof(*device), GFP_KERNEL); + if (!device) + return -ENOMEM; + + device->dev = dev; - if (iommu_device_group(dev, &groupid) == 0) - device_remove_file(dev, &dev_attr_iommu_group); + ret = sysfs_create_link(&dev->kobj, &group->kobj, "iommu_group"); + if (ret) { + kfree(device); + return ret; + } + + device->name = kasprintf(GFP_KERNEL, "%s", kobject_name(&dev->kobj)); +rename: + if (!device->name) { + sysfs_remove_link(&dev->kobj, "iommu_group"); + kfree(device); + return -ENOMEM; + } + ret = sysfs_create_link_nowarn(group->devices_kobj, + &dev->kobj, device->name); + if (ret) { + kfree(device->name); + if (ret == -EEXIST && i >= 0) { + /* + * Account for the slim chance of collision + * and append an instance to the name. + */ + device->name = kasprintf(GFP_KERNEL, "%s.%d", + kobject_name(&dev->kobj), i++); + goto rename; + } + + sysfs_remove_link(&dev->kobj, "iommu_group"); + kfree(device); + return ret; + } + + kobject_get(group->devices_kobj); + + dev->iommu_group = group; + + mutex_lock(&group->mutex); + list_add_tail(&device->list, &group->devices); + mutex_unlock(&group->mutex); + + /* Notify any listeners about change to group. */ + blocking_notifier_call_chain(&group->notifier, + IOMMU_GROUP_NOTIFY_ADD_DEVICE, dev); return 0; } +EXPORT_SYMBOL_GPL(iommu_group_add_device); -static int iommu_device_notifier(struct notifier_block *nb, - unsigned long action, void *data) +/** + * iommu_group_remove_device - remove a device from it's current group + * @dev: device to be removed + * + * This function is called by an iommu driver to remove the device from + * it's current group. This decrements the iommu group reference count. + */ +void iommu_group_remove_device(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + struct iommu_device *tmp_device, *device = NULL; + + /* Pre-notify listeners that a device is being removed. */ + blocking_notifier_call_chain(&group->notifier, + IOMMU_GROUP_NOTIFY_DEL_DEVICE, dev); + + mutex_lock(&group->mutex); + list_for_each_entry(tmp_device, &group->devices, list) { + if (tmp_device->dev == dev) { + device = tmp_device; + list_del(&device->list); + break; + } + } + mutex_unlock(&group->mutex); + + if (!device) + return; + + sysfs_remove_link(group->devices_kobj, device->name); + sysfs_remove_link(&dev->kobj, "iommu_group"); + + kfree(device->name); + kfree(device); + dev->iommu_group = NULL; + kobject_put(group->devices_kobj); +} +EXPORT_SYMBOL_GPL(iommu_group_remove_device); + +/** + * iommu_group_for_each_dev - iterate over each device in the group + * @group: the group + * @data: caller opaque data to be passed to callback function + * @fn: caller supplied callback function + * + * This function is called by group users to iterate over group devices. + * Callers should hold a reference count to the group during callback. + * The group->mutex is held across callbacks, which will block calls to + * iommu_group_add/remove_device. + */ +int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)) +{ + struct iommu_device *device; + int ret = 0; + + mutex_lock(&group->mutex); + list_for_each_entry(device, &group->devices, list) { + ret = fn(device->dev, data); + if (ret) + break; + } + mutex_unlock(&group->mutex); + return ret; +} +EXPORT_SYMBOL_GPL(iommu_group_for_each_dev); + +/** + * iommu_group_get - Return the group for a device and increment reference + * @dev: get the group that this device belongs to + * + * This function is called by iommu drivers and users to get the group + * for the specified device. If found, the group is returned and the group + * reference in incremented, else NULL. + */ +struct iommu_group *iommu_group_get(struct device *dev) +{ + struct iommu_group *group = dev->iommu_group; + + if (group) + kobject_get(group->devices_kobj); + + return group; +} +EXPORT_SYMBOL_GPL(iommu_group_get); + +/** + * iommu_group_put - Decrement group reference + * @group: the group to use + * + * This function is called by iommu drivers and users to release the + * iommu group. Once the reference count is zero, the group is released. + */ +void iommu_group_put(struct iommu_group *group) +{ + if (group) + kobject_put(group->devices_kobj); +} +EXPORT_SYMBOL_GPL(iommu_group_put); + +/** + * iommu_group_register_notifier - Register a notifier for group changes + * @group: the group to watch + * @nb: notifier block to signal + * + * This function allows iommu group users to track changes in a group. + * See include/linux/iommu.h for actions sent via this notifier. Caller + * should hold a reference to the group throughout notifier registration. + */ +int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return blocking_notifier_chain_register(&group->notifier, nb); +} +EXPORT_SYMBOL_GPL(iommu_group_register_notifier); + +/** + * iommu_group_unregister_notifier - Unregister a notifier + * @group: the group to watch + * @nb: notifier block to signal + * + * Unregister a previously registered group notifier block. + */ +int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return blocking_notifier_chain_unregister(&group->notifier, nb); +} +EXPORT_SYMBOL_GPL(iommu_group_unregister_notifier); + +/** + * iommu_group_id - Return ID for a group + * @group: the group to ID + * + * Return the unique ID for the group matching the sysfs group number. + */ +int iommu_group_id(struct iommu_group *group) +{ + return group->id; +} +EXPORT_SYMBOL_GPL(iommu_group_id); + +static int add_iommu_group(struct device *dev, void *data) +{ + struct iommu_ops *ops = data; + + if (!ops->add_device) + return -ENODEV; + + WARN_ON(dev->iommu_group); + + ops->add_device(dev); + + return 0; +} + +static int iommu_bus_notifier(struct notifier_block *nb, + unsigned long action, void *data) { struct device *dev = data; + struct iommu_ops *ops = dev->bus->iommu_ops; + struct iommu_group *group; + unsigned long group_action = 0; + + /* + * ADD/DEL call into iommu driver ops if provided, which may + * result in ADD/DEL notifiers to group->notifier + */ + if (action == BUS_NOTIFY_ADD_DEVICE) { + if (ops->add_device) + return ops->add_device(dev); + } else if (action == BUS_NOTIFY_DEL_DEVICE) { + if (ops->remove_device && dev->iommu_group) { + ops->remove_device(dev); + return 0; + } + } - if (action == BUS_NOTIFY_ADD_DEVICE) - return add_iommu_group(dev, NULL); - else if (action == BUS_NOTIFY_DEL_DEVICE) - return remove_iommu_group(dev); + /* + * Remaining BUS_NOTIFYs get filtered and republished to the + * group, if anyone is listening + */ + group = iommu_group_get(dev); + if (!group) + return 0; + switch (action) { + case BUS_NOTIFY_BIND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_BIND_DRIVER; + break; + case BUS_NOTIFY_BOUND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_BOUND_DRIVER; + break; + case BUS_NOTIFY_UNBIND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_UNBIND_DRIVER; + break; + case BUS_NOTIFY_UNBOUND_DRIVER: + group_action = IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER; + break; + } + + if (group_action) + blocking_notifier_call_chain(&group->notifier, + group_action, dev); + + iommu_group_put(group); return 0; } -static struct notifier_block iommu_device_nb = { - .notifier_call = iommu_device_notifier, +static struct notifier_block iommu_bus_nb = { + .notifier_call = iommu_bus_notifier, }; static void iommu_bus_init(struct bus_type *bus, struct iommu_ops *ops) { - bus_register_notifier(bus, &iommu_device_nb); - bus_for_each_dev(bus, NULL, NULL, add_iommu_group); + bus_register_notifier(bus, &iommu_bus_nb); + bus_for_each_dev(bus, NULL, ops, add_iommu_group); } /** @@ -192,6 +667,45 @@ void iommu_detach_device(struct iommu_domain *domain, struct device *dev) } EXPORT_SYMBOL_GPL(iommu_detach_device); +/* + * IOMMU groups are really the natrual working unit of the IOMMU, but + * the IOMMU API works on domains and devices. Bridge that gap by + * iterating over the devices in a group. Ideally we'd have a single + * device which represents the requestor ID of the group, but we also + * allow IOMMU drivers to create policy defined minimum sets, where + * the physical hardware may be able to distiguish members, but we + * wish to group them at a higher level (ex. untrusted multi-function + * PCI devices). Thus we attach each device. + */ +static int iommu_group_do_attach_device(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + return iommu_attach_device(domain, dev); +} + +int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + return iommu_group_for_each_dev(group, domain, + iommu_group_do_attach_device); +} +EXPORT_SYMBOL_GPL(iommu_attach_group); + +static int iommu_group_do_detach_device(struct device *dev, void *data) +{ + struct iommu_domain *domain = data; + + iommu_detach_device(domain, dev); + + return 0; +} + +void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + iommu_group_for_each_dev(group, domain, iommu_group_do_detach_device); +} +EXPORT_SYMBOL_GPL(iommu_detach_group); + phys_addr_t iommu_iova_to_phys(struct iommu_domain *domain, unsigned long iova) { @@ -336,11 +850,15 @@ size_t iommu_unmap(struct iommu_domain *domain, unsigned long iova, size_t size) } EXPORT_SYMBOL_GPL(iommu_unmap); -int iommu_device_group(struct device *dev, unsigned int *groupid) +static int __init iommu_init(void) { - if (iommu_present(dev->bus) && dev->bus->iommu_ops->device_group) - return dev->bus->iommu_ops->device_group(dev, groupid); + iommu_group_kset = kset_create_and_add("iommu_groups", + NULL, kernel_kobj); + ida_init(&iommu_group_ida); + mutex_init(&iommu_group_mutex); - return -ENODEV; + BUG_ON(!iommu_group_kset); + + return 0; } -EXPORT_SYMBOL_GPL(iommu_device_group); +subsys_initcall(iommu_init); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 450293f6d68b..a71df92be992 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -26,6 +26,7 @@ #define IOMMU_CACHE (4) /* DMA cache coherency */ struct iommu_ops; +struct iommu_group; struct bus_type; struct device; struct iommu_domain; @@ -60,6 +61,8 @@ struct iommu_domain { * @iova_to_phys: translate iova to physical address * @domain_has_cap: domain capabilities query * @commit: commit iommu domain + * @add_device: add device to iommu grouping + * @remove_device: remove device from iommu grouping * @pgsize_bitmap: bitmap of supported page sizes */ struct iommu_ops { @@ -75,10 +78,18 @@ struct iommu_ops { unsigned long iova); int (*domain_has_cap)(struct iommu_domain *domain, unsigned long cap); - int (*device_group)(struct device *dev, unsigned int *groupid); + int (*add_device)(struct device *dev); + void (*remove_device)(struct device *dev); unsigned long pgsize_bitmap; }; +#define IOMMU_GROUP_NOTIFY_ADD_DEVICE 1 /* Device added */ +#define IOMMU_GROUP_NOTIFY_DEL_DEVICE 2 /* Pre Device removed */ +#define IOMMU_GROUP_NOTIFY_BIND_DRIVER 3 /* Pre Driver bind */ +#define IOMMU_GROUP_NOTIFY_BOUND_DRIVER 4 /* Post Driver bind */ +#define IOMMU_GROUP_NOTIFY_UNBIND_DRIVER 5 /* Pre Driver unbind */ +#define IOMMU_GROUP_NOTIFY_UNBOUND_DRIVER 6 /* Post Driver unbind */ + extern int bus_set_iommu(struct bus_type *bus, struct iommu_ops *ops); extern bool iommu_present(struct bus_type *bus); extern struct iommu_domain *iommu_domain_alloc(struct bus_type *bus); @@ -97,7 +108,29 @@ extern int iommu_domain_has_cap(struct iommu_domain *domain, unsigned long cap); extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); -extern int iommu_device_group(struct device *dev, unsigned int *groupid); + +extern int iommu_attach_group(struct iommu_domain *domain, + struct iommu_group *group); +extern void iommu_detach_group(struct iommu_domain *domain, + struct iommu_group *group); +extern struct iommu_group *iommu_group_alloc(void); +extern void *iommu_group_get_iommudata(struct iommu_group *group); +extern void iommu_group_set_iommudata(struct iommu_group *group, + void *iommu_data, + void (*release)(void *iommu_data)); +extern int iommu_group_set_name(struct iommu_group *group, const char *name); +extern int iommu_group_add_device(struct iommu_group *group, + struct device *dev); +extern void iommu_group_remove_device(struct device *dev); +extern int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)); +extern struct iommu_group *iommu_group_get(struct device *dev); +extern void iommu_group_put(struct iommu_group *group); +extern int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb); +extern int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb); +extern int iommu_group_id(struct iommu_group *group); /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework @@ -142,6 +175,7 @@ static inline int report_iommu_fault(struct iommu_domain *domain, #else /* CONFIG_IOMMU_API */ struct iommu_ops {}; +struct iommu_group {}; static inline bool iommu_present(struct bus_type *bus) { @@ -197,11 +231,75 @@ static inline void iommu_set_fault_handler(struct iommu_domain *domain, { } -static inline int iommu_device_group(struct device *dev, unsigned int *groupid) +int iommu_attach_group(struct iommu_domain *domain, struct iommu_group *group) +{ + return -ENODEV; +} + +void iommu_detach_group(struct iommu_domain *domain, struct iommu_group *group) +{ +} + +struct iommu_group *iommu_group_alloc(void) +{ + return ERR_PTR(-ENODEV); +} + +void *iommu_group_get_iommudata(struct iommu_group *group) +{ + return NULL; +} + +void iommu_group_set_iommudata(struct iommu_group *group, void *iommu_data, + void (*release)(void *iommu_data)) +{ +} + +int iommu_group_set_name(struct iommu_group *group, const char *name) +{ + return -ENODEV; +} + +int iommu_group_add_device(struct iommu_group *group, struct device *dev) +{ + return -ENODEV; +} + +void iommu_group_remove_device(struct device *dev) +{ +} + +int iommu_group_for_each_dev(struct iommu_group *group, void *data, + int (*fn)(struct device *, void *)) +{ + return -ENODEV; +} + +struct iommu_group *iommu_group_get(struct device *dev) +{ + return NULL; +} + +void iommu_group_put(struct iommu_group *group) +{ +} + +int iommu_group_register_notifier(struct iommu_group *group, + struct notifier_block *nb) { return -ENODEV; } +int iommu_group_unregister_notifier(struct iommu_group *group, + struct notifier_block *nb) +{ + return 0; +} + +int iommu_group_id(struct iommu_group *group) +{ + return -ENODEV; +} #endif /* CONFIG_IOMMU_API */ #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From 4e0ee78f2af96676c9dca898c13250f62c513058 Mon Sep 17 00:00:00 2001 From: Hiroshi Doyu Date: Mon, 25 Jun 2012 14:23:54 +0300 Subject: iommu: Add DMA window parser, of_get_dma_window() This code was based on: "arch/microblaze/kernel/prom_parse.c" "arch/powerpc/kernel/prom_parse.c" Can replace "of_parse_dma_window()" in the above. This supports different formats flexibly. "prefix" can be configured if any. "busno" and "index" are optionally specified. Set NULL and 0 if not used. Signed-off-by: Hiroshi DOYU Acked-by: Stephen Warren Signed-off-by: Joerg Roedel --- drivers/iommu/Kconfig | 4 +++ drivers/iommu/Makefile | 1 + drivers/iommu/of_iommu.c | 90 ++++++++++++++++++++++++++++++++++++++++++++++++ include/linux/of_iommu.h | 21 +++++++++++ 4 files changed, 116 insertions(+) create mode 100644 drivers/iommu/of_iommu.c create mode 100644 include/linux/of_iommu.h (limited to 'include') diff --git a/drivers/iommu/Kconfig b/drivers/iommu/Kconfig index 340893727538..4826af62a9de 100644 --- a/drivers/iommu/Kconfig +++ b/drivers/iommu/Kconfig @@ -13,6 +13,10 @@ menuconfig IOMMU_SUPPORT if IOMMU_SUPPORT +config OF_IOMMU + def_bool y + depends on OF + # MSM IOMMU support config MSM_IOMMU bool "MSM IOMMU Support" diff --git a/drivers/iommu/Makefile b/drivers/iommu/Makefile index 76e54ef796de..14a4d5fc94fa 100644 --- a/drivers/iommu/Makefile +++ b/drivers/iommu/Makefile @@ -1,4 +1,5 @@ obj-$(CONFIG_IOMMU_API) += iommu.o +obj-$(CONFIG_OF_IOMMU) += of_iommu.o obj-$(CONFIG_MSM_IOMMU) += msm_iommu.o msm_iommu_dev.o obj-$(CONFIG_AMD_IOMMU) += amd_iommu.o amd_iommu_init.o obj-$(CONFIG_AMD_IOMMU_V2) += amd_iommu_v2.o diff --git a/drivers/iommu/of_iommu.c b/drivers/iommu/of_iommu.c new file mode 100644 index 000000000000..ee249bc959f8 --- /dev/null +++ b/drivers/iommu/of_iommu.c @@ -0,0 +1,90 @@ +/* + * OF helpers for IOMMU + * + * Copyright (c) 2012, NVIDIA CORPORATION. All rights reserved. + * + * This program is free software; you can redistribute it and/or modify it + * under the terms and conditions of the GNU General Public License, + * version 2, as published by the Free Software Foundation. + * + * This program is distributed in the hope it will be useful, but WITHOUT + * ANY WARRANTY; without even the implied warranty of MERCHANTABILITY or + * FITNESS FOR A PARTICULAR PURPOSE. See the GNU General Public License for + * more details. + * + * You should have received a copy of the GNU General Public License along with + * this program; if not, write to the Free Software Foundation, Inc., + * 51 Franklin St - Fifth Floor, Boston, MA 02110-1301 USA. + */ + +#include +#include +#include + +/** + * of_get_dma_window - Parse *dma-window property and returns 0 if found. + * + * @dn: device node + * @prefix: prefix for property name if any + * @index: index to start to parse + * @busno: Returns busno if supported. Otherwise pass NULL + * @addr: Returns address that DMA starts + * @size: Returns the range that DMA can handle + * + * This supports different formats flexibly. "prefix" can be + * configured if any. "busno" and "index" are optionally + * specified. Set 0(or NULL) if not used. + */ +int of_get_dma_window(struct device_node *dn, const char *prefix, int index, + unsigned long *busno, dma_addr_t *addr, size_t *size) +{ + const __be32 *dma_window, *end; + int bytes, cur_index = 0; + char propname[NAME_MAX], addrname[NAME_MAX], sizename[NAME_MAX]; + + if (!dn || !addr || !size) + return -EINVAL; + + if (!prefix) + prefix = ""; + + snprintf(propname, sizeof(propname), "%sdma-window", prefix); + snprintf(addrname, sizeof(addrname), "%s#dma-address-cells", prefix); + snprintf(sizename, sizeof(sizename), "%s#dma-size-cells", prefix); + + dma_window = of_get_property(dn, propname, &bytes); + if (!dma_window) + return -ENODEV; + end = dma_window + bytes / sizeof(*dma_window); + + while (dma_window < end) { + u32 cells; + const void *prop; + + /* busno is one cell if supported */ + if (busno) + *busno = be32_to_cpup(dma_window++); + + prop = of_get_property(dn, addrname, NULL); + if (!prop) + prop = of_get_property(dn, "#address-cells", NULL); + + cells = prop ? be32_to_cpup(prop) : of_n_addr_cells(dn); + if (!cells) + return -EINVAL; + *addr = of_read_number(dma_window, cells); + dma_window += cells; + + prop = of_get_property(dn, sizename, NULL); + cells = prop ? be32_to_cpup(prop) : of_n_size_cells(dn); + if (!cells) + return -EINVAL; + *size = of_read_number(dma_window, cells); + dma_window += cells; + + if (cur_index++ == index) + break; + } + return 0; +} +EXPORT_SYMBOL_GPL(of_get_dma_window); diff --git a/include/linux/of_iommu.h b/include/linux/of_iommu.h new file mode 100644 index 000000000000..51a560f34bca --- /dev/null +++ b/include/linux/of_iommu.h @@ -0,0 +1,21 @@ +#ifndef __OF_IOMMU_H +#define __OF_IOMMU_H + +#ifdef CONFIG_OF_IOMMU + +extern int of_get_dma_window(struct device_node *dn, const char *prefix, + int index, unsigned long *busno, dma_addr_t *addr, + size_t *size); + +#else + +static inline int of_get_dma_window(struct device_node *dn, const char *prefix, + int index, unsigned long *busno, dma_addr_t *addr, + size_t *size) +{ + return -EINVAL; +} + +#endif /* CONFIG_OF_IOMMU */ + +#endif /* __OF_IOMMU_H */ -- cgit v1.2.3 From 0cd76dd13bdd2f7f02a2dc931e808e92b191082f Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 26 Jan 2012 19:40:52 +0100 Subject: iommu: Add domain-attribute handlers This patch introduces an extension to the iommu-api to get and set attributes for an iommu_domain. Two functions are introduced for this: * iommu_domain_get_attr() * iommu_domain_set_attr() These functions will be used to make the iommu-api suitable for GART-like IOMMUs and to implement hardware-specifc api-extensions. Signed-off-by: Joerg Roedel --- drivers/iommu/iommu.c | 20 ++++++++++++++++++++ include/linux/iommu.h | 28 +++++++++++++++++++++++++++- 2 files changed, 47 insertions(+), 1 deletion(-) (limited to 'include') diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index 8b9ded88e6f5..c39972d8ded3 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -344,3 +344,23 @@ int iommu_device_group(struct device *dev, unsigned int *groupid) return -ENODEV; } EXPORT_SYMBOL_GPL(iommu_device_group); + +int iommu_domain_get_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + if (!domain->ops->domain_get_attr) + return -EINVAL; + + return domain->ops->domain_get_attr(domain, attr, data); +} +EXPORT_SYMBOL_GPL(iommu_domain_get_attr); + +int iommu_domain_set_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + if (!domain->ops->domain_set_attr) + return -EINVAL; + + return domain->ops->domain_set_attr(domain, attr, data); +} +EXPORT_SYMBOL_GPL(iommu_domain_set_attr); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 450293f6d68b..0eef096183e8 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -47,6 +47,10 @@ struct iommu_domain { #define IOMMU_CAP_CACHE_COHERENCY 0x1 #define IOMMU_CAP_INTR_REMAP 0x2 /* isolates device intrs */ +enum iommu_attr { + DOMAIN_ATTR_MAX, +}; + #ifdef CONFIG_IOMMU_API /** @@ -59,7 +63,8 @@ struct iommu_domain { * @unmap: unmap a physically contiguous memory region from an iommu domain * @iova_to_phys: translate iova to physical address * @domain_has_cap: domain capabilities query - * @commit: commit iommu domain + * @domain_get_attr: Query domain attributes + * @domain_set_attr: Change domain attributes * @pgsize_bitmap: bitmap of supported page sizes */ struct iommu_ops { @@ -76,6 +81,10 @@ struct iommu_ops { int (*domain_has_cap)(struct iommu_domain *domain, unsigned long cap); int (*device_group)(struct device *dev, unsigned int *groupid); + int (*domain_get_attr)(struct iommu_domain *domain, + enum iommu_attr attr, void *data); + int (*domain_set_attr)(struct iommu_domain *domain, + enum iommu_attr attr, void *data); unsigned long pgsize_bitmap; }; @@ -99,6 +108,11 @@ extern void iommu_set_fault_handler(struct iommu_domain *domain, iommu_fault_handler_t handler, void *token); extern int iommu_device_group(struct device *dev, unsigned int *groupid); +extern int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr, + void *data); +extern int iommu_domain_set_attr(struct iommu_domain *domain, enum iommu_attr, + void *data); + /** * report_iommu_fault() - report about an IOMMU fault to the IOMMU framework * @domain: the iommu domain where the fault has happened @@ -202,6 +216,18 @@ static inline int iommu_device_group(struct device *dev, unsigned int *groupid) return -ENODEV; } +static inline int iommu_domain_get_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + return -EINVAL; +} + +static inline int iommu_domain_set_attr(struct iommu_domain *domain, + enum iommu_attr attr, void *data) +{ + return -EINVAL; +} + #endif /* CONFIG_IOMMU_API */ #endif /* __LINUX_IOMMU_H */ -- cgit v1.2.3 From 0ff64f80e075ae036a4c80c7d7752b1e07fed792 Mon Sep 17 00:00:00 2001 From: Joerg Roedel Date: Thu, 26 Jan 2012 19:40:53 +0100 Subject: iommu/amd: Implement DOMAIN_ATTR_GEOMETRY attribute Implement the attribute itself and add the code for the AMD IOMMU driver. Signed-off-by: Joerg Roedel --- drivers/iommu/amd_iommu.c | 4 ++++ drivers/iommu/iommu.c | 19 ++++++++++++++++--- include/linux/iommu.h | 8 ++++++++ 3 files changed, 28 insertions(+), 3 deletions(-) (limited to 'include') diff --git a/drivers/iommu/amd_iommu.c b/drivers/iommu/amd_iommu.c index a2e418cba0ff..259a6beddece 100644 --- a/drivers/iommu/amd_iommu.c +++ b/drivers/iommu/amd_iommu.c @@ -3069,6 +3069,10 @@ static int amd_iommu_domain_init(struct iommu_domain *dom) dom->priv = domain; + dom->geometry.aperture_start = 0; + dom->geometry.aperture_end = ~0ULL; + dom->geometry.force_aperture = true; + return 0; out_free: diff --git a/drivers/iommu/iommu.c b/drivers/iommu/iommu.c index c39972d8ded3..ed5e0a553ca7 100644 --- a/drivers/iommu/iommu.c +++ b/drivers/iommu/iommu.c @@ -348,10 +348,23 @@ EXPORT_SYMBOL_GPL(iommu_device_group); int iommu_domain_get_attr(struct iommu_domain *domain, enum iommu_attr attr, void *data) { - if (!domain->ops->domain_get_attr) - return -EINVAL; + struct iommu_domain_geometry *geometry; + int ret = 0; + + switch (attr) { + case DOMAIN_ATTR_GEOMETRY: + geometry = data; + *geometry = domain->geometry; + + break; + default: + if (!domain->ops->domain_get_attr) + return -EINVAL; - return domain->ops->domain_get_attr(domain, attr, data); + ret = domain->ops->domain_get_attr(domain, attr, data); + } + + return ret; } EXPORT_SYMBOL_GPL(iommu_domain_get_attr); diff --git a/include/linux/iommu.h b/include/linux/iommu.h index 0eef096183e8..f7df4aa527f3 100644 --- a/include/linux/iommu.h +++ b/include/linux/iommu.h @@ -37,11 +37,18 @@ struct iommu_domain; typedef int (*iommu_fault_handler_t)(struct iommu_domain *, struct device *, unsigned long, int, void *); +struct iommu_domain_geometry { + dma_addr_t aperture_start; /* First address that can be mapped */ + dma_addr_t aperture_end; /* Last address that can be mapped */ + bool force_aperture; /* DMA only allowed in mappable range? */ +}; + struct iommu_domain { struct iommu_ops *ops; void *priv; iommu_fault_handler_t handler; void *handler_token; + struct iommu_domain_geometry geometry; }; #define IOMMU_CAP_CACHE_COHERENCY 0x1 @@ -49,6 +56,7 @@ struct iommu_domain { enum iommu_attr { DOMAIN_ATTR_MAX, + DOMAIN_ATTR_GEOMETRY, }; #ifdef CONFIG_IOMMU_API -- cgit v1.2.3