From 7ee4910ab31c4b1fafb7e4f273cbe9340ac953aa Mon Sep 17 00:00:00 2001 From: Jean Delvare Date: Mon, 31 Mar 2014 15:19:29 +0200 Subject: PCI: Remove old serial device IDs These IDs are no longer referenced since kernel 3.1 so I suppose we can remove them from pci_ids.h. Signed-off-by: Jean Delvare Signed-off-by: Bjorn Helgaas Acked-by: Greg Kroah-Hartman --- include/linux/pci_ids.h | 3 --- 1 file changed, 3 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci_ids.h b/include/linux/pci_ids.h index d4de24b4d4c6..7fa31731c854 100644 --- a/include/linux/pci_ids.h +++ b/include/linux/pci_ids.h @@ -1631,8 +1631,6 @@ #define PCI_DEVICE_ID_ATT_VENUS_MODEM 0x480 #define PCI_VENDOR_ID_SPECIALIX 0x11cb -#define PCI_DEVICE_ID_SPECIALIX_IO8 0x2000 -#define PCI_DEVICE_ID_SPECIALIX_RIO 0x8000 #define PCI_SUBDEVICE_ID_SPECIALIX_SPEED4 0xa004 #define PCI_VENDOR_ID_ANALOG_DEVICES 0x11d4 @@ -2874,7 +2872,6 @@ #define PCI_DEVICE_ID_SCALEMP_VSMP_CTL 0x1010 #define PCI_VENDOR_ID_COMPUTONE 0x8e0e -#define PCI_DEVICE_ID_COMPUTONE_IP2EX 0x0291 #define PCI_DEVICE_ID_COMPUTONE_PG 0x0302 #define PCI_SUBVENDOR_ID_COMPUTONE 0x8e0e #define PCI_SUBDEVICE_ID_COMPUTONE_PG4 0x0001 -- cgit From c1309040967e200d3ea6415ae54cf6a69d7ad996 Mon Sep 17 00:00:00 2001 From: Mark Rustad Date: Mon, 31 Mar 2014 14:58:39 -0700 Subject: PCI: Use designated initialization in PCI_VDEVICE By using designated initialization in PCI_VDEVICE, like other similar macros, many "missing initializer" warnings that appear when compiling with W=2 can be silenced. Tested-by: Phil Schmitt Tested-by: Aaron Brown Tested-by: Kavindya Deegala Signed-off-by: Mark Rustad Signed-off-by: Jeff Kirsher Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 10 +++++----- 1 file changed, 5 insertions(+), 5 deletions(-) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index aab57b4abe7f..a95aac7ad37f 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -680,8 +680,8 @@ struct pci_driver { /** * PCI_VDEVICE - macro used to describe a specific pci device in short form - * @vendor: the vendor name - * @device: the 16 bit PCI Device ID + * @vend: the vendor name + * @dev: the 16 bit PCI Device ID * * This macro is used to create a struct pci_device_id that matches a * specific PCI device. The subvendor, and subdevice fields will be set @@ -689,9 +689,9 @@ struct pci_driver { * private data. */ -#define PCI_VDEVICE(vendor, device) \ - PCI_VENDOR_ID_##vendor, (device), \ - PCI_ANY_ID, PCI_ANY_ID, 0, 0 +#define PCI_VDEVICE(vend, dev) \ + .vendor = PCI_VENDOR_ID_##vend, .device = (dev), \ + .subvendor = PCI_ANY_ID, .subdevice = PCI_ANY_ID, 0, 0 /* these external functions are only available when PCI support is enabled */ #ifdef CONFIG_PCI -- cgit From 034cd97ebda4062eb4402a6cf963ccd262caa86a Mon Sep 17 00:00:00 2001 From: Alexander Gordeev Date: Mon, 14 Apr 2014 15:28:35 +0200 Subject: PCI/MSI: Remove pci_enable_msi_block() There are no users of pci_enable_msi_block() function left. Obsolete it in favor of pci_enable_msi_range() and pci_enable_msi_exact() functions. Previously, we called arch_setup_msi_irqs() once, requesting the same vector count we passed to arch_msi_check_device(). Now we may call it several times: if it returns failure, we may retry and request fewer vectors. We don't keep track of the vector count we initially passed to arch_msi_check_device(). We only keep track of the number of vectors successfully set up by arch_setup_msi_irqs(), and this is what we use to clean things up when disabling MSI. Therefore, we assume that arch_msi_check_device() does nothing that will have to be cleaned up later. [bhelgaas: changelog] Signed-off-by: Alexander Gordeev Signed-off-by: Bjorn Helgaas --- drivers/pci/msi.c | 79 ++++++++++++++++++++++------------------------------- include/linux/pci.h | 5 +--- 2 files changed, 34 insertions(+), 50 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/msi.c b/drivers/pci/msi.c index 04130c3f9cf6..36dd0caa1759 100644 --- a/drivers/pci/msi.c +++ b/drivers/pci/msi.c @@ -879,50 +879,6 @@ int pci_msi_vec_count(struct pci_dev *dev) } EXPORT_SYMBOL(pci_msi_vec_count); -/** - * pci_enable_msi_block - configure device's MSI capability structure - * @dev: device to configure - * @nvec: number of interrupts to configure - * - * Allocate IRQs for a device with the MSI capability. - * This function returns a negative errno if an error occurs. If it - * is unable to allocate the number of interrupts requested, it returns - * the number of interrupts it might be able to allocate. If it successfully - * allocates at least the number of interrupts requested, it returns 0 and - * updates the @dev's irq member to the lowest new interrupt number; the - * other interrupt numbers allocated to this device are consecutive. - */ -int pci_enable_msi_block(struct pci_dev *dev, int nvec) -{ - int status, maxvec; - - if (dev->current_state != PCI_D0) - return -EINVAL; - - maxvec = pci_msi_vec_count(dev); - if (maxvec < 0) - return maxvec; - if (nvec > maxvec) - return maxvec; - - status = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI); - if (status) - return status; - - WARN_ON(!!dev->msi_enabled); - - /* Check whether driver already requested MSI-X irqs */ - if (dev->msix_enabled) { - dev_info(&dev->dev, "can't enable MSI " - "(MSI-X already enabled)\n"); - return -EINVAL; - } - - status = msi_capability_init(dev, nvec); - return status; -} -EXPORT_SYMBOL(pci_enable_msi_block); - void pci_msi_shutdown(struct pci_dev *dev) { struct msi_desc *desc; @@ -1128,14 +1084,45 @@ void pci_msi_init_pci_dev(struct pci_dev *dev) **/ int pci_enable_msi_range(struct pci_dev *dev, int minvec, int maxvec) { - int nvec = maxvec; + int nvec; int rc; + if (dev->current_state != PCI_D0) + return -EINVAL; + + WARN_ON(!!dev->msi_enabled); + + /* Check whether driver already requested MSI-X irqs */ + if (dev->msix_enabled) { + dev_info(&dev->dev, + "can't enable MSI (MSI-X already enabled)\n"); + return -EINVAL; + } + if (maxvec < minvec) return -ERANGE; + nvec = pci_msi_vec_count(dev); + if (nvec < 0) + return nvec; + else if (nvec < minvec) + return -EINVAL; + else if (nvec > maxvec) + nvec = maxvec; + + do { + rc = pci_msi_check_device(dev, nvec, PCI_CAP_ID_MSI); + if (rc < 0) { + return rc; + } else if (rc > 0) { + if (rc < minvec) + return -ENOSPC; + nvec = rc; + } + } while (rc); + do { - rc = pci_enable_msi_block(dev, nvec); + rc = msi_capability_init(dev, nvec); if (rc < 0) { return rc; } else if (rc > 0) { diff --git a/include/linux/pci.h b/include/linux/pci.h index aab57b4abe7f..499755e6dab5 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1158,7 +1158,6 @@ struct msix_entry { #ifdef CONFIG_PCI_MSI int pci_msi_vec_count(struct pci_dev *dev); -int pci_enable_msi_block(struct pci_dev *dev, int nvec); void pci_msi_shutdown(struct pci_dev *dev); void pci_disable_msi(struct pci_dev *dev); int pci_msix_vec_count(struct pci_dev *dev); @@ -1188,8 +1187,6 @@ static inline int pci_enable_msix_exact(struct pci_dev *dev, } #else static inline int pci_msi_vec_count(struct pci_dev *dev) { return -ENOSYS; } -static inline int pci_enable_msi_block(struct pci_dev *dev, int nvec) -{ return -ENOSYS; } static inline void pci_msi_shutdown(struct pci_dev *dev) { } static inline void pci_disable_msi(struct pci_dev *dev) { } static inline int pci_msix_vec_count(struct pci_dev *dev) { return -ENOSYS; } @@ -1244,7 +1241,7 @@ static inline void pcie_set_ecrc_checking(struct pci_dev *dev) { } static inline void pcie_ecrc_get_policy(char *str) { } #endif -#define pci_enable_msi(pdev) pci_enable_msi_block(pdev, 1) +#define pci_enable_msi(pdev) pci_enable_msi_exact(pdev, 1) #ifdef CONFIG_HT_IRQ /* The functions a driver should call */ -- cgit From 77f2ea2f8d0833f9e976368481fb9a0775acf9e7 Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Wed, 30 Apr 2014 11:20:53 -0600 Subject: DMA-API: Clarify physical/bus address distinction The DMA-API documentation sometimes refers to "physical addresses" when it really means "bus addresses." Sometimes these are identical, but they may be different if the bridge leading to the bus performs address translation. Update the documentation to use "bus address" when appropriate. Also, consistently capitalize "DMA", use parens with function names, use dev_printk() in examples, and reword a few sections for clarity. No functional change; documentation changes only. Signed-off-by: Bjorn Helgaas Acked-by: Greg Kroah-Hartman Acked-by: Arnd Bergmann Acked-by: James Bottomley Acked-by: Randy Dunlap --- Documentation/DMA-API-HOWTO.txt | 192 +++++++++++++++++++++++++--------------- Documentation/DMA-API.txt | 139 +++++++++++++++-------------- Documentation/DMA-ISA-LPC.txt | 4 +- include/linux/dma-mapping.h | 6 ++ include/linux/types.h | 1 + 5 files changed, 204 insertions(+), 138 deletions(-) (limited to 'include/linux') diff --git a/Documentation/DMA-API-HOWTO.txt b/Documentation/DMA-API-HOWTO.txt index 5e983031cc11..fd3727b94ac2 100644 --- a/Documentation/DMA-API-HOWTO.txt +++ b/Documentation/DMA-API-HOWTO.txt @@ -9,16 +9,76 @@ This is a guide to device driver writers on how to use the DMA API with example pseudo-code. For a concise description of the API, see DMA-API.txt. -Most of the 64bit platforms have special hardware that translates bus -addresses (DMA addresses) into physical addresses. This is similar to -how page tables and/or a TLB translates virtual addresses to physical -addresses on a CPU. This is needed so that e.g. PCI devices can -access with a Single Address Cycle (32bit DMA address) any page in the -64bit physical address space. Previously in Linux those 64bit -platforms had to set artificial limits on the maximum RAM size in the -system, so that the virt_to_bus() static scheme works (the DMA address -translation tables were simply filled on bootup to map each bus -address to the physical page __pa(bus_to_virt())). + CPU and DMA addresses + +There are several kinds of addresses involved in the DMA API, and it's +important to understand the differences. + +The kernel normally uses virtual addresses. Any address returned by +kmalloc(), vmalloc(), and similar interfaces is a virtual address and can +be stored in a "void *". + +The virtual memory system (TLB, page tables, etc.) translates virtual +addresses to CPU physical addresses, which are stored as "phys_addr_t" or +"resource_size_t". The kernel manages device resources like registers as +physical addresses. These are the addresses in /proc/iomem. The physical +address is not directly useful to a driver; it must use ioremap() to map +the space and produce a virtual address. + +I/O devices use a third kind of address: a "bus address" or "DMA address". +If a device has registers at an MMIO address, or if it performs DMA to read +or write system memory, the addresses used by the device are bus addresses. +In some systems, bus addresses are identical to CPU physical addresses, but +in general they are not. IOMMUs and host bridges can produce arbitrary +mappings between physical and bus addresses. + +Here's a picture and some examples: + + CPU CPU Bus + Virtual Physical Address + Address Address Space + Space Space + + +-------+ +------+ +------+ + | | |MMIO | Offset | | + | | Virtual |Space | applied | | + C +-------+ --------> B +------+ ----------> +------+ A + | | mapping | | by host | | + +-----+ | | | | bridge | | +--------+ + | | | | +------+ | | | | + | CPU | | | | RAM | | | | Device | + | | | | | | | | | | + +-----+ +-------+ +------+ +------+ +--------+ + | | Virtual |Buffer| Mapping | | + X +-------+ --------> Y +------+ <---------- +------+ Z + | | mapping | RAM | by IOMMU + | | | | + | | | | + +-------+ +------+ + +During the enumeration process, the kernel learns about I/O devices and +their MMIO space and the host bridges that connect them to the system. For +example, if a PCI device has a BAR, the kernel reads the bus address (A) +from the BAR and converts it to a CPU physical address (B). The address B +is stored in a struct resource and usually exposed via /proc/iomem. When a +driver claims a device, it typically uses ioremap() to map physical address +B at a virtual address (C). It can then use, e.g., ioread32(C), to access +the device registers at bus address A. + +If the device supports DMA, the driver sets up a buffer using kmalloc() or +a similar interface, which returns a virtual address (X). The virtual +memory system maps X to a physical address (Y) in system RAM. The driver +can use virtual address X to access the buffer, but the device itself +cannot because DMA doesn't go through the CPU virtual memory system. + +In some simple systems, the device can do DMA directly to physical address +Y. But in many others, there is IOMMU hardware that translates bus +addresses to physical addresses, e.g., it translates Z to Y. This is part +of the reason for the DMA API: the driver can give a virtual address X to +an interface like dma_map_single(), which sets up any required IOMMU +mapping and returns the bus address Z. The driver then tells the device to +do DMA to Z, and the IOMMU maps it to the buffer at address Y in system +RAM. So that Linux can use the dynamic DMA mapping, it needs some help from the drivers, namely it has to take into account that DMA addresses should be @@ -29,17 +89,17 @@ The following API will work of course even on platforms where no such hardware exists. Note that the DMA API works with any bus independent of the underlying -microprocessor architecture. You should use the DMA API rather than -the bus specific DMA API (e.g. pci_dma_*). +microprocessor architecture. You should use the DMA API rather than the +bus-specific DMA API, i.e., use the dma_map_*() interfaces rather than the +pci_map_*() interfaces. First of all, you should make sure #include -is in your driver. This file will obtain for you the definition of the -dma_addr_t (which can hold any valid DMA address for the platform) -type which should be used everywhere you hold a DMA (bus) address -returned from the DMA mapping functions. +is in your driver, which provides the definition of dma_addr_t. This type +can hold any valid DMA or bus address for the platform and should be used +everywhere you hold a DMA address returned from the DMA mapping functions. What memory is DMA'able? @@ -123,9 +183,9 @@ Here, dev is a pointer to the device struct of your device, and mask is a bit mask describing which bits of an address your device supports. It returns zero if your card can perform DMA properly on the machine given the address mask you provided. In general, the -device struct of your device is embedded in the bus specific device -struct of your device. For example, a pointer to the device struct of -your PCI device is pdev->dev (pdev is a pointer to the PCI device +device struct of your device is embedded in the bus-specific device +struct of your device. For example, &pdev->dev is a pointer to the +device struct of a PCI device (pdev is a pointer to the PCI device struct of your device). If it returns non-zero, your device cannot perform DMA properly on @@ -147,8 +207,7 @@ exactly why. The standard 32-bit addressing device would do something like this: if (dma_set_mask_and_coherent(dev, DMA_BIT_MASK(32))) { - printk(KERN_WARNING - "mydev: No suitable DMA available.\n"); + dev_warn(dev, "mydev: No suitable DMA available\n"); goto ignore_this_device; } @@ -170,8 +229,7 @@ all 64-bits when accessing streaming DMA: } else if (!dma_set_mask(dev, DMA_BIT_MASK(32))) { using_dac = 0; } else { - printk(KERN_WARNING - "mydev: No suitable DMA available.\n"); + dev_warn(dev, "mydev: No suitable DMA available\n"); goto ignore_this_device; } @@ -187,8 +245,7 @@ the case would look like this: using_dac = 0; consistent_using_dac = 0; } else { - printk(KERN_WARNING - "mydev: No suitable DMA available.\n"); + dev_warn(dev, "mydev: No suitable DMA available\n"); goto ignore_this_device; } @@ -201,8 +258,7 @@ Finally, if your device can only drive the low 24-bits of address you might do something like: if (dma_set_mask(dev, DMA_BIT_MASK(24))) { - printk(KERN_WARNING - "mydev: 24-bit DMA addressing not available.\n"); + dev_warn(dev, "mydev: 24-bit DMA addressing not available\n"); goto ignore_this_device; } @@ -232,14 +288,14 @@ Here is pseudo-code showing how this might be done: card->playback_enabled = 1; } else { card->playback_enabled = 0; - printk(KERN_WARNING "%s: Playback disabled due to DMA limitations.\n", + dev_warn(dev, "%s: Playback disabled due to DMA limitations\n", card->name); } if (!dma_set_mask(dev, RECORD_ADDRESS_BITS)) { card->record_enabled = 1; } else { card->record_enabled = 0; - printk(KERN_WARNING "%s: Record disabled due to DMA limitations.\n", + dev_warn(dev, "%s: Record disabled due to DMA limitations\n", card->name); } @@ -331,7 +387,7 @@ context with the GFP_ATOMIC flag. Size is the length of the region you want to allocate, in bytes. This routine will allocate RAM for that region, so it acts similarly to -__get_free_pages (but takes size instead of a page order). If your +__get_free_pages() (but takes size instead of a page order). If your driver needs regions sized smaller than a page, you may prefer using the dma_pool interface, described below. @@ -343,11 +399,11 @@ the consistent DMA mask has been explicitly changed via dma_set_coherent_mask(). This is true of the dma_pool interface as well. -dma_alloc_coherent returns two values: the virtual address which you +dma_alloc_coherent() returns two values: the virtual address which you can use to access it from the CPU and dma_handle which you pass to the card. -The cpu return address and the DMA bus master address are both +The CPU virtual address and the DMA bus address are both guaranteed to be aligned to the smallest PAGE_SIZE order which is greater than or equal to the requested size. This invariant exists (for example) to guarantee that if you allocate a chunk @@ -359,13 +415,13 @@ To unmap and free such a DMA region, you call: dma_free_coherent(dev, size, cpu_addr, dma_handle); where dev, size are the same as in the above call and cpu_addr and -dma_handle are the values dma_alloc_coherent returned to you. +dma_handle are the values dma_alloc_coherent() returned to you. This function may not be called in interrupt context. If your driver needs lots of smaller memory regions, you can write -custom code to subdivide pages returned by dma_alloc_coherent, +custom code to subdivide pages returned by dma_alloc_coherent(), or you can use the dma_pool API to do that. A dma_pool is like -a kmem_cache, but it uses dma_alloc_coherent not __get_free_pages. +a kmem_cache, but it uses dma_alloc_coherent(), not __get_free_pages(). Also, it understands common hardware constraints for alignment, like queue heads needing to be aligned on N byte boundaries. @@ -381,29 +437,29 @@ type of data is "align" (which is expressed in bytes, and must be a power of two). If your device has no boundary crossing restrictions, pass 0 for alloc; passing 4096 says memory allocated from this pool must not cross 4KByte boundaries (but at that time it may be better to -go for dma_alloc_coherent directly instead). +use dma_alloc_coherent() directly instead). -Allocate memory from a dma pool like this: +Allocate memory from a DMA pool like this: cpu_addr = dma_pool_alloc(pool, flags, &dma_handle); flags are SLAB_KERNEL if blocking is permitted (not in_interrupt nor -holding SMP locks), SLAB_ATOMIC otherwise. Like dma_alloc_coherent, +holding SMP locks), SLAB_ATOMIC otherwise. Like dma_alloc_coherent(), this returns two values, cpu_addr and dma_handle. Free memory that was allocated from a dma_pool like this: dma_pool_free(pool, cpu_addr, dma_handle); -where pool is what you passed to dma_pool_alloc, and cpu_addr and -dma_handle are the values dma_pool_alloc returned. This function +where pool is what you passed to dma_pool_alloc(), and cpu_addr and +dma_handle are the values dma_pool_alloc() returned. This function may be called in interrupt context. Destroy a dma_pool by calling: dma_pool_destroy(pool); -Make sure you've called dma_pool_free for all memory allocated +Make sure you've called dma_pool_free() for all memory allocated from a pool before you destroy the pool. This function may not be called in interrupt context. @@ -418,7 +474,7 @@ one of the following values: DMA_FROM_DEVICE DMA_NONE -One should provide the exact DMA direction if you know it. +You should provide the exact DMA direction if you know it. DMA_TO_DEVICE means "from main memory to the device" DMA_FROM_DEVICE means "from the device to main memory" @@ -489,14 +545,14 @@ and to unmap it: dma_unmap_single(dev, dma_handle, size, direction); You should call dma_mapping_error() as dma_map_single() could fail and return -error. Not all dma implementations support dma_mapping_error() interface. +error. Not all DMA implementations support the dma_mapping_error() interface. However, it is a good practice to call dma_mapping_error() interface, which will invoke the generic mapping error check interface. Doing so will ensure -that the mapping code will work correctly on all dma implementations without +that the mapping code will work correctly on all DMA implementations without any dependency on the specifics of the underlying implementation. Using the returned address without checking for errors could result in failures ranging from panics to silent data corruption. A couple of examples of incorrect ways -to check for errors that make assumptions about the underlying dma +to check for errors that make assumptions about the underlying DMA implementation are as follows and these are applicable to dma_map_page() as well. @@ -516,12 +572,12 @@ Incorrect example 2: goto map_error; } -You should call dma_unmap_single when the DMA activity is finished, e.g. +You should call dma_unmap_single() when the DMA activity is finished, e.g., from the interrupt which told you that the DMA transfer is done. -Using cpu pointers like this for single mappings has a disadvantage, +Using cpu pointers like this for single mappings has a disadvantage: you cannot reference HIGHMEM memory in this way. Thus, there is a -map/unmap interface pair akin to dma_{map,unmap}_single. These +map/unmap interface pair akin to dma_{map,unmap}_single(). These interfaces deal with page/offset pairs instead of cpu pointers. Specifically: @@ -550,7 +606,7 @@ Here, "offset" means byte offset within the given page. You should call dma_mapping_error() as dma_map_page() could fail and return error as outlined under the dma_map_single() discussion. -You should call dma_unmap_page when the DMA activity is finished, e.g. +You should call dma_unmap_page() when the DMA activity is finished, e.g., from the interrupt which told you that the DMA transfer is done. With scatterlists, you map a region gathered from several regions by: @@ -588,18 +644,16 @@ PLEASE NOTE: The 'nents' argument to the dma_unmap_sg call must be it should _NOT_ be the 'count' value _returned_ from the dma_map_sg call. -Every dma_map_{single,sg} call should have its dma_unmap_{single,sg} -counterpart, because the bus address space is a shared resource (although -in some ports the mapping is per each BUS so less devices contend for the -same bus address space) and you could render the machine unusable by eating -all bus addresses. +Every dma_map_{single,sg}() call should have its dma_unmap_{single,sg}() +counterpart, because the bus address space is a shared resource and +you could render the machine unusable by consuming all bus addresses. If you need to use the same streaming DMA region multiple times and touch the data in between the DMA transfers, the buffer needs to be synced -properly in order for the cpu and device to see the most uptodate and +properly in order for the cpu and device to see the most up-to-date and correct copy of the DMA buffer. -So, firstly, just map it with dma_map_{single,sg}, and after each DMA +So, firstly, just map it with dma_map_{single,sg}(), and after each DMA transfer call either: dma_sync_single_for_cpu(dev, dma_handle, size, direction); @@ -623,9 +677,9 @@ or: as appropriate. After the last DMA transfer call one of the DMA unmap routines -dma_unmap_{single,sg}. If you don't touch the data from the first dma_map_* -call till dma_unmap_*, then you don't have to call the dma_sync_* -routines at all. +dma_unmap_{single,sg}(). If you don't touch the data from the first +dma_map_*() call till dma_unmap_*(), then you don't have to call the +dma_sync_*() routines at all. Here is pseudo code which shows a situation in which you would need to use the dma_sync_*() interfaces. @@ -690,12 +744,12 @@ to use the dma_sync_*() interfaces. } } -Drivers converted fully to this interface should not use virt_to_bus any -longer, nor should they use bus_to_virt. Some drivers have to be changed a -little bit, because there is no longer an equivalent to bus_to_virt in the +Drivers converted fully to this interface should not use virt_to_bus() any +longer, nor should they use bus_to_virt(). Some drivers have to be changed a +little bit, because there is no longer an equivalent to bus_to_virt() in the dynamic DMA mapping scheme - you have to always store the DMA addresses -returned by the dma_alloc_coherent, dma_pool_alloc, and dma_map_single -calls (dma_map_sg stores them in the scatterlist itself if the platform +returned by the dma_alloc_coherent(), dma_pool_alloc(), and dma_map_single() +calls (dma_map_sg() stores them in the scatterlist itself if the platform supports dynamic DMA mapping in hardware) in your driver structures and/or in the card registers. @@ -709,9 +763,9 @@ as it is impossible to correctly support them. DMA address space is limited on some architectures and an allocation failure can be determined by: -- checking if dma_alloc_coherent returns NULL or dma_map_sg returns 0 +- checking if dma_alloc_coherent() returns NULL or dma_map_sg returns 0 -- checking the returned dma_addr_t of dma_map_single and dma_map_page +- checking the dma_addr_t returned from dma_map_single() and dma_map_page() by using dma_mapping_error(): dma_addr_t dma_handle; @@ -794,7 +848,7 @@ Example 2: (if buffers are allocated in a loop, unmap all mapped buffers when dma_unmap_single(array[i].dma_addr); } -Networking drivers must call dev_kfree_skb to free the socket buffer +Networking drivers must call dev_kfree_skb() to free the socket buffer and return NETDEV_TX_OK if the DMA mapping fails on the transmit hook (ndo_start_xmit). This means that the socket buffer is just dropped in the failure case. @@ -831,7 +885,7 @@ transform some example code. DEFINE_DMA_UNMAP_LEN(len); }; -2) Use dma_unmap_{addr,len}_set to set these values. +2) Use dma_unmap_{addr,len}_set() to set these values. Example, before: ringp->mapping = FOO; @@ -842,7 +896,7 @@ transform some example code. dma_unmap_addr_set(ringp, mapping, FOO); dma_unmap_len_set(ringp, len, BAR); -3) Use dma_unmap_{addr,len} to access these values. +3) Use dma_unmap_{addr,len}() to access these values. Example, before: dma_unmap_single(dev, ringp->mapping, ringp->len, diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index e865279cec58..1147eba43128 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -4,22 +4,26 @@ James E.J. Bottomley This document describes the DMA API. For a more gentle introduction -of the API (and actual examples) see -Documentation/DMA-API-HOWTO.txt. +of the API (and actual examples), see Documentation/DMA-API-HOWTO.txt. -This API is split into two pieces. Part I describes the API. Part II -describes the extensions to the API for supporting non-consistent -memory machines. Unless you know that your driver absolutely has to -support non-consistent platforms (this is usually only legacy -platforms) you should only use the API described in part I. +This API is split into two pieces. Part I describes the basic API. +Part II describes extensions for supporting non-consistent memory +machines. Unless you know that your driver absolutely has to support +non-consistent platforms (this is usually only legacy platforms) you +should only use the API described in part I. Part I - dma_ API ------------------------------------- -To get the dma_ API, you must #include +To get the dma_ API, you must #include . This +provides dma_addr_t and the interfaces described below. +A dma_addr_t can hold any valid DMA or bus address for the platform. It +can be given to a device to use as a DMA source or target. A cpu cannot +reference a dma_addr_t directly because there may be translation between +its physical address space and the bus address space. -Part Ia - Using large dma-coherent buffers +Part Ia - Using large DMA-coherent buffers ------------------------------------------ void * @@ -33,20 +37,21 @@ to make sure to flush the processor's write buffers before telling devices to read that memory.) This routine allocates a region of bytes of consistent memory. -It also returns a which may be cast to an unsigned -integer the same width as the bus and used as the physical address -base of the region. -Returns: a pointer to the allocated region (in the processor's virtual +It returns a pointer to the allocated region (in the processor's virtual address space) or NULL if the allocation failed. +It also returns a which may be cast to an unsigned integer the +same width as the bus and given to the device as the bus address base of +the region. + Note: consistent memory can be expensive on some platforms, and the minimum allocation length may be as big as a page, so you should consolidate your requests for consistent memory as much as possible. The simplest way to do that is to use the dma_pool calls (see below). -The flag parameter (dma_alloc_coherent only) allows the caller to -specify the GFP_ flags (see kmalloc) for the allocation (the +The flag parameter (dma_alloc_coherent() only) allows the caller to +specify the GFP_ flags (see kmalloc()) for the allocation (the implementation may choose to ignore flags that affect the location of the returned memory, like GFP_DMA). @@ -61,24 +66,24 @@ void dma_free_coherent(struct device *dev, size_t size, void *cpu_addr, dma_addr_t dma_handle) -Free the region of consistent memory you previously allocated. dev, -size and dma_handle must all be the same as those passed into the -consistent allocate. cpu_addr must be the virtual address returned by -the consistent allocate. +Free a region of consistent memory you previously allocated. dev, +size and dma_handle must all be the same as those passed into +dma_alloc_coherent(). cpu_addr must be the virtual address returned by +the dma_alloc_coherent(). Note that unlike their sibling allocation calls, these routines may only be called with IRQs enabled. -Part Ib - Using small dma-coherent buffers +Part Ib - Using small DMA-coherent buffers ------------------------------------------ To get this part of the dma_ API, you must #include -Many drivers need lots of small dma-coherent memory regions for DMA +Many drivers need lots of small DMA-coherent memory regions for DMA descriptors or I/O buffers. Rather than allocating in units of a page or more using dma_alloc_coherent(), you can use DMA pools. These work -much like a struct kmem_cache, except that they use the dma-coherent allocator, +much like a struct kmem_cache, except that they use the DMA-coherent allocator, not __get_free_pages(). Also, they understand common hardware constraints for alignment, like queue heads needing to be aligned on N-byte boundaries. @@ -87,7 +92,7 @@ for alignment, like queue heads needing to be aligned on N-byte boundaries. dma_pool_create(const char *name, struct device *dev, size_t size, size_t align, size_t alloc); -The pool create() routines initialize a pool of dma-coherent buffers +dma_pool_create() initializes a pool of DMA-coherent buffers for use with a given device. It must be called in a context which can sleep. @@ -102,25 +107,26 @@ from this pool must not cross 4KByte boundaries. void *dma_pool_alloc(struct dma_pool *pool, gfp_t gfp_flags, dma_addr_t *dma_handle); -This allocates memory from the pool; the returned memory will meet the size -and alignment requirements specified at creation time. Pass GFP_ATOMIC to -prevent blocking, or if it's permitted (not in_interrupt, not holding SMP locks), -pass GFP_KERNEL to allow blocking. Like dma_alloc_coherent(), this returns -two values: an address usable by the cpu, and the dma address usable by the -pool's device. +This allocates memory from the pool; the returned memory will meet the +size and alignment requirements specified at creation time. Pass +GFP_ATOMIC to prevent blocking, or if it's permitted (not +in_interrupt, not holding SMP locks), pass GFP_KERNEL to allow +blocking. Like dma_alloc_coherent(), this returns two values: an +address usable by the cpu, and the DMA address usable by the pool's +device. void dma_pool_free(struct dma_pool *pool, void *vaddr, dma_addr_t addr); This puts memory back into the pool. The pool is what was passed to -the pool allocation routine; the cpu (vaddr) and dma addresses are what +dma_pool_alloc(); the cpu (vaddr) and DMA addresses are what were returned when that routine allocated the memory being freed. void dma_pool_destroy(struct dma_pool *pool); -The pool destroy() routines free the resources of the pool. They must be +dma_pool_destroy() frees the resources of the pool. It must be called in a context which can sleep. Make sure you've freed all allocated memory back to the pool before you destroy it. @@ -187,9 +193,9 @@ dma_map_single(struct device *dev, void *cpu_addr, size_t size, enum dma_data_direction direction) Maps a piece of processor virtual memory so it can be accessed by the -device and returns the physical handle of the memory. +device and returns the bus address of the memory. -The direction for both api's may be converted freely by casting. +The direction for both APIs may be converted freely by casting. However the dma_ API uses a strongly typed enumerator for its direction: @@ -198,31 +204,30 @@ DMA_TO_DEVICE data is going from the memory to the device DMA_FROM_DEVICE data is coming from the device to the memory DMA_BIDIRECTIONAL direction isn't known -Notes: Not all memory regions in a machine can be mapped by this -API. Further, regions that appear to be physically contiguous in -kernel virtual space may not be contiguous as physical memory. Since -this API does not provide any scatter/gather capability, it will fail -if the user tries to map a non-physically contiguous piece of memory. -For this reason, it is recommended that memory mapped by this API be -obtained only from sources which guarantee it to be physically contiguous -(like kmalloc). - -Further, the physical address of the memory must be within the -dma_mask of the device (the dma_mask represents a bit mask of the -addressable region for the device. I.e., if the physical address of -the memory anded with the dma_mask is still equal to the physical -address, then the device can perform DMA to the memory). In order to +Notes: Not all memory regions in a machine can be mapped by this API. +Further, contiguous kernel virtual space may not be contiguous as +physical memory. Since this API does not provide any scatter/gather +capability, it will fail if the user tries to map a non-physically +contiguous piece of memory. For this reason, memory to be mapped by +this API should be obtained from sources which guarantee it to be +physically contiguous (like kmalloc). + +Further, the bus address of the memory must be within the +dma_mask of the device (the dma_mask is a bit mask of the +addressable region for the device, i.e., if the bus address of +the memory ANDed with the dma_mask is still equal to the bus +address, then the device can perform DMA to the memory). To ensure that the memory allocated by kmalloc is within the dma_mask, the driver may specify various platform-dependent flags to restrict -the physical memory range of the allocation (e.g. on x86, GFP_DMA -guarantees to be within the first 16Mb of available physical memory, +the bus address range of the allocation (e.g., on x86, GFP_DMA +guarantees to be within the first 16MB of available bus addresses, as required by ISA devices). Note also that the above constraints on physical contiguity and dma_mask may not apply if the platform has an IOMMU (a device which -supplies a physical to virtual mapping between the I/O memory bus and -the device). However, to be portable, device driver writers may *not* -assume that such an IOMMU exists. +maps an I/O bus address to a physical memory address). However, to be +portable, device driver writers may *not* assume that such an IOMMU +exists. Warnings: Memory coherency operates at a granularity called the cache line width. In order for memory mapped by this API to operate @@ -281,9 +286,9 @@ cache width is. int dma_mapping_error(struct device *dev, dma_addr_t dma_addr) -In some circumstances dma_map_single and dma_map_page will fail to create +In some circumstances dma_map_single() and dma_map_page() will fail to create a mapping. A driver can check for these errors by testing the returned -dma address with dma_mapping_error(). A non-zero return value means the mapping +DMA address with dma_mapping_error(). A non-zero return value means the mapping could not be created and the driver should take appropriate action (e.g. reduce current DMA mapping usage or delay and try again later). @@ -291,7 +296,7 @@ reduce current DMA mapping usage or delay and try again later). dma_map_sg(struct device *dev, struct scatterlist *sg, int nents, enum dma_data_direction direction) -Returns: the number of physical segments mapped (this may be shorter +Returns: the number of bus address segments mapped (this may be shorter than passed in if some elements of the scatter/gather list are physically or virtually adjacent and an IOMMU maps them with a single entry). @@ -299,7 +304,7 @@ entry). Please note that the sg cannot be mapped again if it has been mapped once. The mapping process is allowed to destroy information in the sg. -As with the other mapping interfaces, dma_map_sg can fail. When it +As with the other mapping interfaces, dma_map_sg() can fail. When it does, 0 is returned and a driver must take appropriate action. It is critical that the driver do something, in the case of a block driver aborting the request or even oopsing is better than doing nothing and @@ -335,7 +340,7 @@ must be the same as those and passed in to the scatter/gather mapping API. Note: must be the number you passed in, *not* the number of -physical entries returned. +bus address entries returned. void dma_sync_single_for_cpu(struct device *dev, dma_addr_t dma_handle, size_t size, @@ -391,10 +396,10 @@ The four functions above are just like the counterpart functions without the _attrs suffixes, except that they pass an optional struct dma_attrs*. -struct dma_attrs encapsulates a set of "dma attributes". For the +struct dma_attrs encapsulates a set of "DMA attributes". For the definition of struct dma_attrs see linux/dma-attrs.h. -The interpretation of dma attributes is architecture-specific, and +The interpretation of DMA attributes is architecture-specific, and each attribute should be documented in Documentation/DMA-attributes.txt. If struct dma_attrs* is NULL, the semantics of each of these @@ -458,7 +463,7 @@ Note: where the platform can return consistent memory, it will guarantee that the sync points become nops. Warning: Handling non-consistent memory is a real pain. You should -only ever use this API if you positively know your driver will be +only use this API if you positively know your driver will be required to work on one of the rare (usually non-PCI) architectures that simply cannot make consistent memory. @@ -496,26 +501,26 @@ dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, dma_addr_t device_addr, size_t size, int flags) -Declare region of memory to be handed out by dma_alloc_coherent when +Declare region of memory to be handed out by dma_alloc_coherent() when it's asked for coherent memory for this device. bus_addr is the physical address to which the memory is currently assigned in the bus responding region (this will be used by the platform to perform the mapping). -device_addr is the physical address the device needs to be programmed +device_addr is the bus address the device needs to be programmed with actually to address this memory (this will be handed out as the dma_addr_t in dma_alloc_coherent()). size is the size of the area (must be multiples of PAGE_SIZE). -flags can be or'd together and are: +flags can be ORed together and are: DMA_MEMORY_MAP - request that the memory returned from dma_alloc_coherent() be directly writable. DMA_MEMORY_IO - request that the memory returned from -dma_alloc_coherent() be addressable using read/write/memcpy_toio etc. +dma_alloc_coherent() be addressable using read()/write()/memcpy_toio() etc. One or both of these flags must be present. @@ -572,7 +577,7 @@ region is occupied. Part III - Debug drivers use of the DMA-API ------------------------------------------- -The DMA-API as described above as some constraints. DMA addresses must be +The DMA-API as described above has some constraints. DMA addresses must be released with the corresponding function with the same size for example. With the advent of hardware IOMMUs it becomes more and more important that drivers do not violate those constraints. In the worst case such a violation can @@ -690,11 +695,11 @@ architectural default. void debug_dmap_mapping_error(struct device *dev, dma_addr_t dma_addr); dma-debug interface debug_dma_mapping_error() to debug drivers that fail -to check dma mapping errors on addresses returned by dma_map_single() and +to check DMA mapping errors on addresses returned by dma_map_single() and dma_map_page() interfaces. This interface clears a flag set by debug_dma_map_page() to indicate that dma_mapping_error() has been called by the driver. When driver does unmap, debug_dma_unmap() checks the flag and if this flag is still set, prints warning message that includes call trace that leads up to the unmap. This interface can be called from dma_mapping_error() -routines to enable dma mapping error check debugging. +routines to enable DMA mapping error check debugging. diff --git a/Documentation/DMA-ISA-LPC.txt b/Documentation/DMA-ISA-LPC.txt index e767805b4182..b1a19835e907 100644 --- a/Documentation/DMA-ISA-LPC.txt +++ b/Documentation/DMA-ISA-LPC.txt @@ -16,7 +16,7 @@ To do ISA style DMA you need to include two headers: #include The first is the generic DMA API used to convert virtual addresses to -physical addresses (see Documentation/DMA-API.txt for details). +bus addresses (see Documentation/DMA-API.txt for details). The second contains the routines specific to ISA DMA transfers. Since this is not present on all platforms make sure you construct your @@ -50,7 +50,7 @@ early as possible and not release it until the driver is unloaded.) Part III - Address translation ------------------------------ -To translate the virtual address to a physical use the normal DMA +To translate the virtual address to a bus address, use the normal DMA API. Do _not_ use isa_virt_to_phys() even though it does the same thing. The reason for this is that the function isa_virt_to_phys() will require a Kconfig dependency to ISA, not just ISA_DMA_API which diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index fd4aee29ad10..b9aa2b97aab5 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -8,6 +8,12 @@ #include #include +/* + * A dma_addr_t can hold any valid DMA or bus address for the platform. + * It can be given to a device to use as a DMA source or target. A CPU cannot + * reference a dma_addr_t directly because there may be translation between + * its physical address space and the bus address space. + */ struct dma_map_ops { void* (*alloc)(struct device *dev, size_t size, dma_addr_t *dma_handle, gfp_t gfp, diff --git a/include/linux/types.h b/include/linux/types.h index 4d118ba11349..a0bb7048687f 100644 --- a/include/linux/types.h +++ b/include/linux/types.h @@ -142,6 +142,7 @@ typedef unsigned long blkcnt_t; #define pgoff_t unsigned long #endif +/* A dma_addr_t can hold any valid DMA or bus address for the platform */ #ifdef CONFIG_ARCH_DMA_ADDR_T_64BIT typedef u64 dma_addr_t; #else -- cgit From 88a984ba0795f14a3847edbd7fabe652289ea89b Mon Sep 17 00:00:00 2001 From: Bjorn Helgaas Date: Tue, 20 May 2014 16:54:22 -0600 Subject: DMA-API: Change dma_declare_coherent_memory() CPU address to phys_addr_t dma_declare_coherent_memory() takes two addresses for a region of memory: a "bus_addr" and a "device_addr". I think the intent is that "bus_addr" is the physical address a *CPU* would use to access the region, and "device_addr" is the bus address the *device* would use to address the region. Rename "bus_addr" to "phys_addr" and change its type to phys_addr_t. Most callers already supply a phys_addr_t for this argument. The others supply a 32-bit integer (a constant, unsigned int, or __u32) and need no change. Use "unsigned long", not phys_addr_t, to hold PFNs. No functional change (this could theoretically fix a truncation in a config with 32-bit dma_addr_t and 64-bit phys_addr_t, but I don't think there are any such cases involving this code). Signed-off-by: Bjorn Helgaas Acked-by: Arnd Bergmann Acked-by: Greg Kroah-Hartman Acked-by: James Bottomley Acked-by: Randy Dunlap --- Documentation/DMA-API.txt | 9 ++++----- drivers/base/dma-coherent.c | 10 +++++----- drivers/base/dma-mapping.c | 6 +++--- include/asm-generic/dma-coherent.h | 13 +++++-------- include/linux/dma-mapping.h | 7 ++++--- 5 files changed, 21 insertions(+), 24 deletions(-) (limited to 'include/linux') diff --git a/Documentation/DMA-API.txt b/Documentation/DMA-API.txt index 1147eba43128..4f1cdc5febd1 100644 --- a/Documentation/DMA-API.txt +++ b/Documentation/DMA-API.txt @@ -497,19 +497,18 @@ continuing on for size. Again, you *must* observe the cache line boundaries when doing this. int -dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, +dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags) Declare region of memory to be handed out by dma_alloc_coherent() when it's asked for coherent memory for this device. -bus_addr is the physical address to which the memory is currently -assigned in the bus responding region (this will be used by the -platform to perform the mapping). +phys_addr is the cpu physical address to which the memory is currently +assigned (this will be ioremapped so the cpu can access the region). device_addr is the bus address the device needs to be programmed -with actually to address this memory (this will be handed out as the +with to actually address this memory (this will be handed out as the dma_addr_t in dma_alloc_coherent()). size is the size of the area (must be multiples of PAGE_SIZE). diff --git a/drivers/base/dma-coherent.c b/drivers/base/dma-coherent.c index bc256b641027..7d6e84a51424 100644 --- a/drivers/base/dma-coherent.c +++ b/drivers/base/dma-coherent.c @@ -10,13 +10,13 @@ struct dma_coherent_mem { void *virt_base; dma_addr_t device_base; - phys_addr_t pfn_base; + unsigned long pfn_base; int size; int flags; unsigned long *bitmap; }; -int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, +int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags) { void __iomem *mem_base = NULL; @@ -32,7 +32,7 @@ int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, /* FIXME: this routine just ignores DMA_MEMORY_INCLUDES_CHILDREN */ - mem_base = ioremap(bus_addr, size); + mem_base = ioremap(phys_addr, size); if (!mem_base) goto out; @@ -45,7 +45,7 @@ int dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, dev->dma_mem->virt_base = mem_base; dev->dma_mem->device_base = device_addr; - dev->dma_mem->pfn_base = PFN_DOWN(bus_addr); + dev->dma_mem->pfn_base = PFN_DOWN(phys_addr); dev->dma_mem->size = pages; dev->dma_mem->flags = flags; @@ -208,7 +208,7 @@ int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, *ret = -ENXIO; if (off < count && user_count <= count - off) { - unsigned pfn = mem->pfn_base + start + off; + unsigned long pfn = mem->pfn_base + start + off; *ret = remap_pfn_range(vma, vma->vm_start, pfn, user_count << PAGE_SHIFT, vma->vm_page_prot); diff --git a/drivers/base/dma-mapping.c b/drivers/base/dma-mapping.c index 0ce39a33b3c2..6cd08e145bfa 100644 --- a/drivers/base/dma-mapping.c +++ b/drivers/base/dma-mapping.c @@ -175,7 +175,7 @@ static void dmam_coherent_decl_release(struct device *dev, void *res) /** * dmam_declare_coherent_memory - Managed dma_declare_coherent_memory() * @dev: Device to declare coherent memory for - * @bus_addr: Bus address of coherent memory to be declared + * @phys_addr: Physical address of coherent memory to be declared * @device_addr: Device address of coherent memory to be declared * @size: Size of coherent memory to be declared * @flags: Flags @@ -185,7 +185,7 @@ static void dmam_coherent_decl_release(struct device *dev, void *res) * RETURNS: * 0 on success, -errno on failure. */ -int dmam_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, +int dmam_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags) { void *res; @@ -195,7 +195,7 @@ int dmam_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, if (!res) return -ENOMEM; - rc = dma_declare_coherent_memory(dev, bus_addr, device_addr, size, + rc = dma_declare_coherent_memory(dev, phys_addr, device_addr, size, flags); if (rc == 0) devres_add(dev, res); diff --git a/include/asm-generic/dma-coherent.h b/include/asm-generic/dma-coherent.h index 2be8a2dbc868..0297e5875798 100644 --- a/include/asm-generic/dma-coherent.h +++ b/include/asm-generic/dma-coherent.h @@ -16,16 +16,13 @@ int dma_mmap_from_coherent(struct device *dev, struct vm_area_struct *vma, * Standard interface */ #define ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY -extern int -dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, - dma_addr_t device_addr, size_t size, int flags); +int dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, + dma_addr_t device_addr, size_t size, int flags); -extern void -dma_release_declared_memory(struct device *dev); +void dma_release_declared_memory(struct device *dev); -extern void * -dma_mark_declared_memory_occupied(struct device *dev, - dma_addr_t device_addr, size_t size); +void *dma_mark_declared_memory_occupied(struct device *dev, + dma_addr_t device_addr, size_t size); #else #define dma_alloc_from_coherent(dev, size, handle, ret) (0) #define dma_release_from_coherent(dev, order, vaddr) (0) diff --git a/include/linux/dma-mapping.h b/include/linux/dma-mapping.h index b9aa2b97aab5..0c3eab1e39ac 100644 --- a/include/linux/dma-mapping.h +++ b/include/linux/dma-mapping.h @@ -192,7 +192,7 @@ static inline int dma_get_cache_alignment(void) #ifndef ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY static inline int -dma_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, +dma_declare_coherent_memory(struct device *dev, phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags) { return 0; @@ -223,13 +223,14 @@ extern void *dmam_alloc_noncoherent(struct device *dev, size_t size, extern void dmam_free_noncoherent(struct device *dev, size_t size, void *vaddr, dma_addr_t dma_handle); #ifdef ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY -extern int dmam_declare_coherent_memory(struct device *dev, dma_addr_t bus_addr, +extern int dmam_declare_coherent_memory(struct device *dev, + phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, int flags); extern void dmam_release_declared_memory(struct device *dev); #else /* ARCH_HAS_DMA_DECLARE_COHERENT_MEMORY */ static inline int dmam_declare_coherent_memory(struct device *dev, - dma_addr_t bus_addr, dma_addr_t device_addr, + phys_addr_t phys_addr, dma_addr_t device_addr, size_t size, gfp_t gfp) { return 0; -- cgit From 9edbcd2252b5ef148177c9f2c11a56469cf5db52 Mon Sep 17 00:00:00 2001 From: Sebastian Ott Date: Thu, 17 Apr 2014 19:48:07 +0200 Subject: PCI: Remove pcibios_add_platform_entries() Remove pcibios_add_platform_entries(). Architecture-specific attributes can be achieved by setting pdev->dev.groups. Link: https://lkml.kernel.org/r/alpine.LFD.2.11.1404141101500.1529@denkbrett Signed-off-by: Sebastian Ott Signed-off-by: Bjorn Helgaas Acked-by: Greg Kroah-Hartman --- drivers/pci/pci-sysfs.c | 10 ---------- include/linux/pci.h | 1 - 2 files changed, 11 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 3db1c7ff5dd3..b7333fa5f80d 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -1273,11 +1273,6 @@ static struct bin_attribute pcie_config_attr = { .write = pci_write_config, }; -int __weak pcibios_add_platform_entries(struct pci_dev *dev) -{ - return 0; -} - static ssize_t reset_store(struct device *dev, struct device_attribute *attr, const char *buf, size_t count) @@ -1393,11 +1388,6 @@ int __must_check pci_create_sysfs_dev_files (struct pci_dev *pdev) pdev->rom_attr = attr; } - /* add platform-specific attributes */ - retval = pcibios_add_platform_entries(pdev); - if (retval) - goto err_rom_file; - /* add sysfs entries for various capabilities */ retval = pci_create_capabilities_sysfs(pdev); if (retval) diff --git a/include/linux/pci.h b/include/linux/pci.h index a95aac7ad37f..84182b153b21 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1572,7 +1572,6 @@ extern unsigned long pci_hotplug_io_size; extern unsigned long pci_hotplug_mem_size; /* Architecture-specific versions may override these (weak) */ -int pcibios_add_platform_entries(struct pci_dev *dev); void pcibios_disable_device(struct pci_dev *dev); void pcibios_set_master(struct pci_dev *dev); int pcibios_set_pcie_reset_state(struct pci_dev *dev, -- cgit From 3ebe7f9f7e4a4fd1f6461ecd01ff2961317a483a Mon Sep 17 00:00:00 2001 From: Keith Busch Date: Fri, 2 May 2014 10:40:42 -0600 Subject: PCI: Notify driver before and after device reset Notify a PCI device driver when its device's access is about to be disabled for an impending reset attempt, then after the attempt completes and device access is restored. The notification is via the pci_error_handlers interface. Signed-off-by: Keith Busch Signed-off-by: Bjorn Helgaas --- drivers/pci/pci.c | 21 +++++++++++++++++++++ include/linux/pci.h | 3 +++ 2 files changed, 24 insertions(+) (limited to 'include/linux') diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 7325d43bf030..43d87b26ec5b 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -3305,8 +3305,27 @@ static void pci_dev_unlock(struct pci_dev *dev) pci_cfg_access_unlock(dev); } +/** + * pci_reset_notify - notify device driver of reset + * @dev: device to be notified of reset + * @prepare: 'true' if device is about to be reset; 'false' if reset attempt + * completed + * + * Must be called prior to device access being disabled and after device + * access is restored. + */ +static void pci_reset_notify(struct pci_dev *dev, bool prepare) +{ + const struct pci_error_handlers *err_handler = + dev->driver ? dev->driver->err_handler : NULL; + if (err_handler && err_handler->reset_notify) + err_handler->reset_notify(dev, prepare); +} + static void pci_dev_save_and_disable(struct pci_dev *dev) { + pci_reset_notify(dev, true); + /* * Wake-up device prior to save. PM registers default to D0 after * reset and a simple register restore doesn't reliably return @@ -3328,6 +3347,7 @@ static void pci_dev_save_and_disable(struct pci_dev *dev) static void pci_dev_restore(struct pci_dev *dev) { pci_restore_state(dev); + pci_reset_notify(dev, false); } static int pci_dev_reset(struct pci_dev *dev, int probe) @@ -3344,6 +3364,7 @@ static int pci_dev_reset(struct pci_dev *dev, int probe) return rc; } + /** * __pci_reset_function - reset a PCI device function * @dev: PCI device to reset diff --git a/include/linux/pci.h b/include/linux/pci.h index aab57b4abe7f..31c43093e538 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -603,6 +603,9 @@ struct pci_error_handlers { /* PCI slot has been reset */ pci_ers_result_t (*slot_reset)(struct pci_dev *dev); + /* PCI function reset prepare or completed */ + void (*reset_notify)(struct pci_dev *dev, bool prepare); + /* Device driver may resume normal operations */ void (*resume)(struct pci_dev *dev); }; -- cgit From 1c86438c9423a26cc9f7f74a8950d9cf9c93bc23 Mon Sep 17 00:00:00 2001 From: Yijing Wang Date: Sun, 4 May 2014 12:23:37 +0800 Subject: PCI: Add new pci_is_bridge() interface Add a helper function to check a device's header type for PCI bridge or CardBus bridge. Requires: 326c1cdae741 PCI: Rename pci_is_bridge() to pci_has_subordinate() Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas --- include/linux/pci.h | 13 +++++++++++++ 1 file changed, 13 insertions(+) (limited to 'include/linux') diff --git a/include/linux/pci.h b/include/linux/pci.h index aab57b4abe7f..f2a5946ea0bf 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -477,6 +477,19 @@ static inline bool pci_is_root_bus(struct pci_bus *pbus) return !(pbus->parent); } +/** + * pci_is_bridge - check if the PCI device is a bridge + * @dev: PCI device + * + * Return true if the PCI device is bridge whether it has subordinate + * or not. + */ +static inline bool pci_is_bridge(struct pci_dev *dev) +{ + return dev->hdr_type == PCI_HEADER_TYPE_BRIDGE || + dev->hdr_type == PCI_HEADER_TYPE_CARDBUS; +} + static inline struct pci_dev *pci_upstream_bridge(struct pci_dev *dev) { dev = pci_physfn(dev); -- cgit From a43ae58c848cfbadaba81c8d63202b4487f922a0 Mon Sep 17 00:00:00 2001 From: Hanjun Guo Date: Tue, 6 May 2014 11:29:52 +0800 Subject: PCI: Turn pcibios_penalize_isa_irq() into a weak function pcibios_penalize_isa_irq() is only implemented by x86 now, and legacy ISA is not used by some architectures. Make pcibios_penalize_isa_irq() a __weak function to simplify the code. This removes the need for new platforms to add stub implementations of pcibios_penalize_isa_irq(). [bhelgaas: changelog, comments] Signed-off-by: Hanjun Guo Signed-off-by: Bjorn Helgaas Acked-by: Arnd Bergmann --- arch/alpha/include/asm/pci.h | 5 ----- arch/arm/include/asm/pci.h | 5 ----- arch/blackfin/include/asm/pci.h | 5 ----- arch/cris/include/asm/pci.h | 1 - arch/frv/include/asm/pci.h | 2 -- arch/frv/mb93090-mb00/pci-irq.c | 4 ---- arch/ia64/include/asm/pci.h | 6 ------ arch/microblaze/include/asm/pci.h | 5 ----- arch/mips/include/asm/pci.h | 5 ----- arch/mn10300/include/asm/pci.h | 1 - arch/mn10300/unit-asb2305/pci-irq.c | 4 ---- arch/parisc/include/asm/pci.h | 5 ----- arch/powerpc/include/asm/pci.h | 5 ----- arch/sh/include/asm/pci.h | 5 ----- arch/sparc/include/asm/pci_32.h | 5 ----- arch/sparc/include/asm/pci_64.h | 5 ----- arch/unicore32/include/asm/pci.h | 5 ----- arch/x86/include/asm/pci.h | 1 - arch/xtensa/include/asm/pci.h | 5 ----- drivers/pci/pci.c | 11 +++++++++++ include/linux/pci.h | 1 + 21 files changed, 12 insertions(+), 79 deletions(-) (limited to 'include/linux') diff --git a/arch/alpha/include/asm/pci.h b/arch/alpha/include/asm/pci.h index d01afb78919c..f7f680f7457d 100644 --- a/arch/alpha/include/asm/pci.h +++ b/arch/alpha/include/asm/pci.h @@ -59,11 +59,6 @@ struct pci_controller { extern void pcibios_set_master(struct pci_dev *dev); -extern inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - /* IOMMU controls. */ /* The PCI address space does not equal the physical memory address space. diff --git a/arch/arm/include/asm/pci.h b/arch/arm/include/asm/pci.h index 680a83e94467..7e95d8535e24 100644 --- a/arch/arm/include/asm/pci.h +++ b/arch/arm/include/asm/pci.h @@ -31,11 +31,6 @@ static inline int pci_proc_domain(struct pci_bus *bus) } #endif /* CONFIG_PCI_DOMAINS */ -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - /* * The PCI address space does equal the physical memory address space. * The networking and block device layers use this boolean for bounce diff --git a/arch/blackfin/include/asm/pci.h b/arch/blackfin/include/asm/pci.h index 74352c4597d9..c737909fba47 100644 --- a/arch/blackfin/include/asm/pci.h +++ b/arch/blackfin/include/asm/pci.h @@ -10,9 +10,4 @@ #define PCIBIOS_MIN_IO 0x00001000 #define PCIBIOS_MIN_MEM 0x10000000 -static inline void pcibios_penalize_isa_irq(int irq) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - #endif /* _ASM_BFIN_PCI_H */ diff --git a/arch/cris/include/asm/pci.h b/arch/cris/include/asm/pci.h index f666734926d5..cc2399c175e9 100644 --- a/arch/cris/include/asm/pci.h +++ b/arch/cris/include/asm/pci.h @@ -20,7 +20,6 @@ void pcibios_config_init(void); struct pci_bus * pcibios_scan_root(int bus); void pcibios_set_master(struct pci_dev *dev); -void pcibios_penalize_isa_irq(int irq); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); diff --git a/arch/frv/include/asm/pci.h b/arch/frv/include/asm/pci.h index ef03baf5d89d..2035a4d3f9b9 100644 --- a/arch/frv/include/asm/pci.h +++ b/arch/frv/include/asm/pci.h @@ -24,8 +24,6 @@ struct pci_dev; extern void pcibios_set_master(struct pci_dev *dev); -extern void pcibios_penalize_isa_irq(int irq); - #ifdef CONFIG_MMU extern void *consistent_alloc(gfp_t gfp, size_t size, dma_addr_t *dma_handle); extern void consistent_free(void *vaddr); diff --git a/arch/frv/mb93090-mb00/pci-irq.c b/arch/frv/mb93090-mb00/pci-irq.c index c677b9d81d30..1c35c93f942b 100644 --- a/arch/frv/mb93090-mb00/pci-irq.c +++ b/arch/frv/mb93090-mb00/pci-irq.c @@ -55,10 +55,6 @@ void __init pcibios_fixup_irqs(void) } } -void __init pcibios_penalize_isa_irq(int irq) -{ -} - void pcibios_enable_irq(struct pci_dev *dev) { pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq); diff --git a/arch/ia64/include/asm/pci.h b/arch/ia64/include/asm/pci.h index 7d41cc089822..52af5ed9f60b 100644 --- a/arch/ia64/include/asm/pci.h +++ b/arch/ia64/include/asm/pci.h @@ -50,12 +50,6 @@ struct pci_dev; extern unsigned long ia64_max_iommu_merge_mask; #define PCI_DMA_BUS_IS_PHYS (ia64_max_iommu_merge_mask == ~0UL) -static inline void -pcibios_penalize_isa_irq (int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - #include #ifdef CONFIG_PCI diff --git a/arch/microblaze/include/asm/pci.h b/arch/microblaze/include/asm/pci.h index 935f9bec414a..335524040fff 100644 --- a/arch/microblaze/include/asm/pci.h +++ b/arch/microblaze/include/asm/pci.h @@ -44,11 +44,6 @@ struct pci_dev; */ #define pcibios_assign_all_busses() 0 -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - #ifdef CONFIG_PCI extern void set_pci_dma_ops(struct dma_map_ops *dma_ops); extern struct dma_map_ops *get_pci_dma_ops(void); diff --git a/arch/mips/include/asm/pci.h b/arch/mips/include/asm/pci.h index 12d6842962be..974b0e308963 100644 --- a/arch/mips/include/asm/pci.h +++ b/arch/mips/include/asm/pci.h @@ -73,11 +73,6 @@ extern unsigned long PCIBIOS_MIN_MEM; extern void pcibios_set_master(struct pci_dev *dev); -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - #define HAVE_PCI_MMAP extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, diff --git a/arch/mn10300/include/asm/pci.h b/arch/mn10300/include/asm/pci.h index 166323824683..5f70af25c7d0 100644 --- a/arch/mn10300/include/asm/pci.h +++ b/arch/mn10300/include/asm/pci.h @@ -48,7 +48,6 @@ extern void unit_pci_init(void); #define PCIBIOS_MIN_MEM 0xB8000000 void pcibios_set_master(struct pci_dev *dev); -void pcibios_penalize_isa_irq(int irq); /* Dynamic DMA mapping stuff. * i386 has everything mapped statically. diff --git a/arch/mn10300/unit-asb2305/pci-irq.c b/arch/mn10300/unit-asb2305/pci-irq.c index 77439da04671..fcb28ceb824d 100644 --- a/arch/mn10300/unit-asb2305/pci-irq.c +++ b/arch/mn10300/unit-asb2305/pci-irq.c @@ -40,10 +40,6 @@ void __init pcibios_fixup_irqs(void) } } -void __init pcibios_penalize_isa_irq(int irq) -{ -} - void pcibios_enable_irq(struct pci_dev *dev) { pci_write_config_byte(dev, PCI_INTERRUPT_LINE, dev->irq); diff --git a/arch/parisc/include/asm/pci.h b/arch/parisc/include/asm/pci.h index 465154076d23..20df2b04fc09 100644 --- a/arch/parisc/include/asm/pci.h +++ b/arch/parisc/include/asm/pci.h @@ -215,11 +215,6 @@ static inline void pci_dma_burst_advice(struct pci_dev *pdev, } #endif -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't need to penalize isa irq's */ -} - static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) { return channel ? 15 : 14; diff --git a/arch/powerpc/include/asm/pci.h b/arch/powerpc/include/asm/pci.h index 95145a15c708..1b0739bc14b5 100644 --- a/arch/powerpc/include/asm/pci.h +++ b/arch/powerpc/include/asm/pci.h @@ -46,11 +46,6 @@ struct pci_dev; #define pcibios_assign_all_busses() \ (pci_has_flag(PCI_REASSIGN_ALL_BUS)) -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - #define HAVE_ARCH_PCI_GET_LEGACY_IDE_IRQ static inline int pci_get_legacy_ide_irq(struct pci_dev *dev, int channel) { diff --git a/arch/sh/include/asm/pci.h b/arch/sh/include/asm/pci.h index bff96c2e7d25..5b4511552998 100644 --- a/arch/sh/include/asm/pci.h +++ b/arch/sh/include/asm/pci.h @@ -70,11 +70,6 @@ extern int pci_mmap_page_range(struct pci_dev *dev, struct vm_area_struct *vma, enum pci_mmap_state mmap_state, int write_combine); extern void pcibios_set_master(struct pci_dev *dev); -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - /* Dynamic DMA mapping stuff. * SuperH has everything mapped statically like x86. */ diff --git a/arch/sparc/include/asm/pci_32.h b/arch/sparc/include/asm/pci_32.h index dc503297481f..53e9b4987db0 100644 --- a/arch/sparc/include/asm/pci_32.h +++ b/arch/sparc/include/asm/pci_32.h @@ -16,11 +16,6 @@ #define PCI_IRQ_NONE 0xffffffff -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - /* Dynamic DMA mapping stuff. */ #define PCI_DMA_BUS_IS_PHYS (0) diff --git a/arch/sparc/include/asm/pci_64.h b/arch/sparc/include/asm/pci_64.h index 1633b718d3bc..c6c7396e7627 100644 --- a/arch/sparc/include/asm/pci_64.h +++ b/arch/sparc/include/asm/pci_64.h @@ -16,11 +16,6 @@ #define PCI_IRQ_NONE 0xffffffff -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - /* The PCI address space does not equal the physical memory * address space. The networking and block device layers use * this boolean for bounce buffer decisions. diff --git a/arch/unicore32/include/asm/pci.h b/arch/unicore32/include/asm/pci.h index f5e108f4a151..654407e98619 100644 --- a/arch/unicore32/include/asm/pci.h +++ b/arch/unicore32/include/asm/pci.h @@ -18,11 +18,6 @@ #include #include /* for PCIBIOS_MIN_* */ -static inline void pcibios_penalize_isa_irq(int irq, int active) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - #ifdef CONFIG_PCI static inline void pci_dma_burst_advice(struct pci_dev *pdev, enum pci_dma_burst_strategy *strat, diff --git a/arch/x86/include/asm/pci.h b/arch/x86/include/asm/pci.h index 96ae4f4040bb..0892ea0e683f 100644 --- a/arch/x86/include/asm/pci.h +++ b/arch/x86/include/asm/pci.h @@ -68,7 +68,6 @@ void pcibios_config_init(void); void pcibios_scan_root(int bus); void pcibios_set_master(struct pci_dev *dev); -void pcibios_penalize_isa_irq(int irq, int active); struct irq_routing_table *pcibios_get_irq_routing_table(void); int pcibios_set_irq_routing(struct pci_dev *dev, int pin, int irq); diff --git a/arch/xtensa/include/asm/pci.h b/arch/xtensa/include/asm/pci.h index 614be031a79a..5d52dc43dfe7 100644 --- a/arch/xtensa/include/asm/pci.h +++ b/arch/xtensa/include/asm/pci.h @@ -22,11 +22,6 @@ extern struct pci_controller* pcibios_alloc_controller(void); -static inline void pcibios_penalize_isa_irq(int irq) -{ - /* We don't do dynamic PCI IRQ allocation */ -} - /* Assume some values. (We should revise them, if necessary) */ #define PCIBIOS_MIN_IO 0x2000 diff --git a/drivers/pci/pci.c b/drivers/pci/pci.c index 39012831867e..11f24912523c 100644 --- a/drivers/pci/pci.c +++ b/drivers/pci/pci.c @@ -1468,6 +1468,17 @@ void __weak pcibios_release_device(struct pci_dev *dev) {} */ void __weak pcibios_disable_device (struct pci_dev *dev) {} +/** + * pcibios_penalize_isa_irq - penalize an ISA IRQ + * @irq: ISA IRQ to penalize + * @active: IRQ active or not + * + * Permits the platform to provide architecture-specific functionality when + * penalizing ISA IRQs. This is the default implementation. Architecture + * implementations can override this. + */ +void __weak pcibios_penalize_isa_irq(int irq, int active) {} + static void do_pci_disable_device(struct pci_dev *dev) { u16 pci_command; diff --git a/include/linux/pci.h b/include/linux/pci.h index 84182b153b21..018877b8b4e8 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -1578,6 +1578,7 @@ int pcibios_set_pcie_reset_state(struct pci_dev *dev, enum pcie_reset_state state); int pcibios_add_device(struct pci_dev *dev); void pcibios_release_device(struct pci_dev *dev); +void pcibios_penalize_isa_irq(int irq, int active); #ifdef CONFIG_HIBERNATE_CALLBACKS extern struct dev_pm_ops pcibios_pm_ops; -- cgit From d97ffe236894856d08146390ef3fbe6448a8ac2b Mon Sep 17 00:00:00 2001 From: Gavin Shan Date: Wed, 21 May 2014 15:23:30 +1000 Subject: PCI: Fix return value from pci_user_{read,write}_config_*() The PCI user-space config accessors pci_user_{read,write}_config_*() return negative error numbers, which were introduced by commit 34e3207205ef ("PCI: handle positive error codes"). That patch converted all positive error numbers from platform-specific PCI config accessors to -EINVAL, which means the callers don't know anything about the specific cause of the failure. The patch fixes the issue by converting the positive PCIBIOS_* error values to generic negative error numbers with pcibios_err_to_errno(). [bhelgaas: changelog] Signed-off-by: Gavin Shan Signed-off-by: Bjorn Helgaas Acked-by: Greg Thelen --- drivers/pci/access.c | 12 ++++-------- include/linux/pci.h | 4 ++-- 2 files changed, 6 insertions(+), 10 deletions(-) (limited to 'include/linux') diff --git a/drivers/pci/access.c b/drivers/pci/access.c index 7f8b78c08879..8c148f39e8d7 100644 --- a/drivers/pci/access.c +++ b/drivers/pci/access.c @@ -148,7 +148,7 @@ static noinline void pci_wait_cfg(struct pci_dev *dev) int pci_user_read_config_##size \ (struct pci_dev *dev, int pos, type *val) \ { \ - int ret = 0; \ + int ret = PCIBIOS_SUCCESSFUL; \ u32 data = -1; \ if (PCI_##size##_BAD) \ return -EINVAL; \ @@ -159,9 +159,7 @@ int pci_user_read_config_##size \ pos, sizeof(type), &data); \ raw_spin_unlock_irq(&pci_lock); \ *val = (type)data; \ - if (ret > 0) \ - ret = -EINVAL; \ - return ret; \ + return pcibios_err_to_errno(ret); \ } \ EXPORT_SYMBOL_GPL(pci_user_read_config_##size); @@ -170,7 +168,7 @@ EXPORT_SYMBOL_GPL(pci_user_read_config_##size); int pci_user_write_config_##size \ (struct pci_dev *dev, int pos, type val) \ { \ - int ret = -EIO; \ + int ret = PCIBIOS_SUCCESSFUL; \ if (PCI_##size##_BAD) \ return -EINVAL; \ raw_spin_lock_irq(&pci_lock); \ @@ -179,9 +177,7 @@ int pci_user_write_config_##size \ ret = dev->bus->ops->write(dev->bus, dev->devfn, \ pos, sizeof(type), val); \ raw_spin_unlock_irq(&pci_lock); \ - if (ret > 0) \ - ret = -EINVAL; \ - return ret; \ + return pcibios_err_to_errno(ret); \ } \ EXPORT_SYMBOL_GPL(pci_user_write_config_##size); diff --git a/include/linux/pci.h b/include/linux/pci.h index 018877b8b4e8..322335aaa7e1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -518,7 +518,7 @@ static inline int pcibios_err_to_errno(int err) case PCIBIOS_FUNC_NOT_SUPPORTED: return -ENOENT; case PCIBIOS_BAD_VENDOR_ID: - return -EINVAL; + return -ENOTTY; case PCIBIOS_DEVICE_NOT_FOUND: return -ENODEV; case PCIBIOS_BAD_REGISTER_NUMBER: @@ -529,7 +529,7 @@ static inline int pcibios_err_to_errno(int err) return -ENOSPC; } - return -ENOTTY; + return -ERANGE; } /* Low-level architecture-dependent routines */ -- cgit From 782a985d7af26db39e86070d28f987cad21313c0 Mon Sep 17 00:00:00 2001 From: Alex Williamson Date: Tue, 20 May 2014 08:53:21 -0600 Subject: PCI: Introduce new device binding path using pci_dev.driver_override The driver_override field allows us to specify the driver for a device rather than relying on the driver to provide a positive match of the device. This shortcuts the existing process of looking up the vendor and device ID, adding them to the driver new_id, binding the device, then removing the ID, but it also provides a couple advantages. First, the above existing process allows the driver to bind to any device matching the new_id for the window where it's enabled. This is often not desired, such as the case of trying to bind a single device to a meta driver like pci-stub or vfio-pci. Using driver_override we can do this deterministically using: echo pci-stub > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Previously we could not invoke drivers_probe after adding a device to new_id for a driver as we get non-deterministic behavior whether the driver we intend or the standard driver will claim the device. Now it becomes a deterministic process, only the driver matching driver_override will probe the device. To return the device to the standard driver, we simply clear the driver_override and reprobe the device: echo > /sys/bus/pci/devices/0000:03:00.0/driver_override echo 0000:03:00.0 > /sys/bus/pci/devices/0000:03:00.0/driver/unbind echo 0000:03:00.0 > /sys/bus/pci/drivers_probe Another advantage to this approach is that we can specify a driver override to force a specific binding or prevent any binding. For instance when an IOMMU group is exposed to userspace through VFIO we require that all devices within that group are owned by VFIO. However, devices can be hot-added into an IOMMU group, in which case we want to prevent the device from binding to any driver (override driver = "none") or perhaps have it automatically bind to vfio-pci. With driver_override it's a simple matter for this field to be set internally when the device is first discovered to prevent driver matches. Signed-off-by: Alex Williamson Signed-off-by: Bjorn Helgaas Reviewed-by: Konrad Rzeszutek Wilk Reviewed-by: Alexander Graf Acked-by: Greg Kroah-Hartman --- Documentation/ABI/testing/sysfs-bus-pci | 21 +++++++++++++++++ drivers/pci/pci-driver.c | 25 ++++++++++++++++++--- drivers/pci/pci-sysfs.c | 40 +++++++++++++++++++++++++++++++++ drivers/pci/probe.c | 1 + include/linux/pci.h | 1 + 5 files changed, 85 insertions(+), 3 deletions(-) (limited to 'include/linux') diff --git a/Documentation/ABI/testing/sysfs-bus-pci b/Documentation/ABI/testing/sysfs-bus-pci index a3c5a6685036..898ddc4440e6 100644 --- a/Documentation/ABI/testing/sysfs-bus-pci +++ b/Documentation/ABI/testing/sysfs-bus-pci @@ -250,3 +250,24 @@ Description: valid. For example, writing a 2 to this file when sriov_numvfs is not 0 and not 2 already will return an error. Writing a 10 when the value of sriov_totalvfs is 8 will return an error. + +What: /sys/bus/pci/devices/.../driver_override +Date: April 2014 +Contact: Alex Williamson +Description: + This file allows the driver for a device to be specified which + will override standard static and dynamic ID matching. When + specified, only a driver with a name matching the value written + to driver_override will have an opportunity to bind to the + device. The override is specified by writing a string to the + driver_override file (echo pci-stub > driver_override) and + may be cleared with an empty string (echo > driver_override). + This returns the device to standard matching rules binding. + Writing to driver_override does not automatically unbind the + device from its current driver or make any attempt to + automatically load the specified driver. If no driver with a + matching name is currently loaded in the kernel, the device + will not bind to any driver. This also allows devices to + opt-out of driver binding using a driver_override name such as + "none". Only a single driver may be specified in the override, + there is no support for parsing delimiters. diff --git a/drivers/pci/pci-driver.c b/drivers/pci/pci-driver.c index d911e0c1f359..4393c12e9135 100644 --- a/drivers/pci/pci-driver.c +++ b/drivers/pci/pci-driver.c @@ -216,6 +216,13 @@ const struct pci_device_id *pci_match_id(const struct pci_device_id *ids, return NULL; } +static const struct pci_device_id pci_device_id_any = { + .vendor = PCI_ANY_ID, + .device = PCI_ANY_ID, + .subvendor = PCI_ANY_ID, + .subdevice = PCI_ANY_ID, +}; + /** * pci_match_device - Tell if a PCI device structure has a matching PCI device id structure * @drv: the PCI driver to match against @@ -229,18 +236,30 @@ static const struct pci_device_id *pci_match_device(struct pci_driver *drv, struct pci_dev *dev) { struct pci_dynid *dynid; + const struct pci_device_id *found_id = NULL; + + /* When driver_override is set, only bind to the matching driver */ + if (dev->driver_override && strcmp(dev->driver_override, drv->name)) + return NULL; /* Look at the dynamic ids first, before the static ones */ spin_lock(&drv->dynids.lock); list_for_each_entry(dynid, &drv->dynids.list, node) { if (pci_match_one_device(&dynid->id, dev)) { - spin_unlock(&drv->dynids.lock); - return &dynid->id; + found_id = &dynid->id; + break; } } spin_unlock(&drv->dynids.lock); - return pci_match_id(drv->id_table, dev); + if (!found_id) + found_id = pci_match_id(drv->id_table, dev); + + /* driver_override will always match, send a dummy id */ + if (!found_id && dev->driver_override) + found_id = &pci_device_id_any; + + return found_id; } struct drv_dev_and_id { diff --git a/drivers/pci/pci-sysfs.c b/drivers/pci/pci-sysfs.c index 4e0acefb7565..faa4ab554d68 100644 --- a/drivers/pci/pci-sysfs.c +++ b/drivers/pci/pci-sysfs.c @@ -499,6 +499,45 @@ static struct device_attribute sriov_numvfs_attr = sriov_numvfs_show, sriov_numvfs_store); #endif /* CONFIG_PCI_IOV */ +static ssize_t driver_override_store(struct device *dev, + struct device_attribute *attr, + const char *buf, size_t count) +{ + struct pci_dev *pdev = to_pci_dev(dev); + char *driver_override, *old = pdev->driver_override, *cp; + + if (count > PATH_MAX) + return -EINVAL; + + driver_override = kstrndup(buf, count, GFP_KERNEL); + if (!driver_override) + return -ENOMEM; + + cp = strchr(driver_override, '\n'); + if (cp) + *cp = '\0'; + + if (strlen(driver_override)) { + pdev->driver_override = driver_override; + } else { + kfree(driver_override); + pdev->driver_override = NULL; + } + + kfree(old); + + return count; +} + +static ssize_t driver_override_show(struct device *dev, + struct device_attribute *attr, char *buf) +{ + struct pci_dev *pdev = to_pci_dev(dev); + + return sprintf(buf, "%s\n", pdev->driver_override); +} +static DEVICE_ATTR_RW(driver_override); + static struct attribute *pci_dev_attrs[] = { &dev_attr_resource.attr, &dev_attr_vendor.attr, @@ -521,6 +560,7 @@ static struct attribute *pci_dev_attrs[] = { #if defined(CONFIG_PM_RUNTIME) && defined(CONFIG_ACPI) &dev_attr_d3cold_allowed.attr, #endif + &dev_attr_driver_override.attr, NULL, }; diff --git a/drivers/pci/probe.c b/drivers/pci/probe.c index ef09f5f2fe6c..54268de45f59 100644 --- a/drivers/pci/probe.c +++ b/drivers/pci/probe.c @@ -1215,6 +1215,7 @@ static void pci_release_dev(struct device *dev) pci_release_of_node(pci_dev); pcibios_release_device(pci_dev); pci_bus_put(pci_dev->bus); + kfree(pci_dev->driver_override); kfree(pci_dev); } diff --git a/include/linux/pci.h b/include/linux/pci.h index aab57b4abe7f..b72af276f591 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -365,6 +365,7 @@ struct pci_dev { #endif phys_addr_t rom; /* Physical address of ROM if it's not from the BAR */ size_t romlen; /* Length of ROM if it's not from the BAR */ + char *driver_override; /* Driver name to force a match */ }; static inline struct pci_dev *pci_physfn(struct pci_dev *dev) -- cgit From c893d133eaccdda2516a3e71cd05a7dac2e14b00 Mon Sep 17 00:00:00 2001 From: Yijing Wang Date: Fri, 30 May 2014 11:01:03 +0800 Subject: PCI: Make pci_bus_add_device() void pci_bus_add_device() always returns 0, so there's no point in returning anything at all. Make it a void function and remove the tests of the return value from the callers. [bhelgaas: changelog, remove unused "err" from i82875p_setup_overfl_dev()] Signed-off-by: Yijing Wang Signed-off-by: Bjorn Helgaas --- drivers/edac/i82875p_edac.c | 8 +------- drivers/pci/bus.c | 10 ++-------- drivers/pci/iov.c | 2 +- drivers/platform/x86/asus-wmi.c | 3 +-- drivers/platform/x86/eeepc-laptop.c | 3 +-- include/linux/pci.h | 2 +- 6 files changed, 7 insertions(+), 21 deletions(-) (limited to 'include/linux') diff --git a/drivers/edac/i82875p_edac.c b/drivers/edac/i82875p_edac.c index 8d0450b9b9af..4009077c8839 100644 --- a/drivers/edac/i82875p_edac.c +++ b/drivers/edac/i82875p_edac.c @@ -275,7 +275,6 @@ static int i82875p_setup_overfl_dev(struct pci_dev *pdev, { struct pci_dev *dev; void __iomem *window; - int err; *ovrfl_pdev = NULL; *ovrfl_window = NULL; @@ -293,12 +292,7 @@ static int i82875p_setup_overfl_dev(struct pci_dev *pdev, if (dev == NULL) return 1; - err = pci_bus_add_device(dev); - if (err) { - i82875p_printk(KERN_ERR, - "%s(): pci_bus_add_device() Failed\n", - __func__); - } + pci_bus_add_device(dev); pci_bus_assign_resources(dev->bus); } diff --git a/drivers/pci/bus.c b/drivers/pci/bus.c index ba2bf55a38df..447d393725e1 100644 --- a/drivers/pci/bus.c +++ b/drivers/pci/bus.c @@ -235,7 +235,7 @@ void __weak pcibios_resource_survey_bus(struct pci_bus *bus) { } * * This adds add sysfs entries and start device drivers */ -int pci_bus_add_device(struct pci_dev *dev) +void pci_bus_add_device(struct pci_dev *dev) { int retval; @@ -252,8 +252,6 @@ int pci_bus_add_device(struct pci_dev *dev) WARN_ON(retval < 0); dev->is_added = 1; - - return 0; } /** @@ -266,16 +264,12 @@ void pci_bus_add_devices(const struct pci_bus *bus) { struct pci_dev *dev; struct pci_bus *child; - int retval; list_for_each_entry(dev, &bus->devices, bus_list) { /* Skip already-added devices */ if (dev->is_added) continue; - retval = pci_bus_add_device(dev); - if (retval) - dev_err(&dev->dev, "Error adding device (%d)\n", - retval); + pci_bus_add_device(dev); } list_for_each_entry(dev, &bus->devices, bus_list) { diff --git a/drivers/pci/iov.c b/drivers/pci/iov.c index de7a74782f92..cb6f24740ee3 100644 --- a/drivers/pci/iov.c +++ b/drivers/pci/iov.c @@ -106,7 +106,7 @@ static int virtfn_add(struct pci_dev *dev, int id, int reset) pci_device_add(virtfn, virtfn->bus); mutex_unlock(&iov->dev->sriov->lock); - rc = pci_bus_add_device(virtfn); + pci_bus_add_device(virtfn); sprintf(buf, "virtfn%u", id); rc = sysfs_create_link(&dev->dev.kobj, &virtfn->dev.kobj, buf); if (rc) diff --git a/drivers/platform/x86/asus-wmi.c b/drivers/platform/x86/asus-wmi.c index c5e082fb82fa..91ef69a52263 100644 --- a/drivers/platform/x86/asus-wmi.c +++ b/drivers/platform/x86/asus-wmi.c @@ -642,8 +642,7 @@ static void asus_rfkill_hotplug(struct asus_wmi *asus) dev = pci_scan_single_device(bus, 0); if (dev) { pci_bus_assign_resources(bus); - if (pci_bus_add_device(dev)) - pr_err("Unable to hotplug wifi\n"); + pci_bus_add_device(dev); } } else { dev = pci_get_slot(bus, 0); diff --git a/drivers/platform/x86/eeepc-laptop.c b/drivers/platform/x86/eeepc-laptop.c index 399e8c562192..9b0c57cd1d4a 100644 --- a/drivers/platform/x86/eeepc-laptop.c +++ b/drivers/platform/x86/eeepc-laptop.c @@ -633,8 +633,7 @@ static void eeepc_rfkill_hotplug(struct eeepc_laptop *eeepc, acpi_handle handle) dev = pci_scan_single_device(bus, 0); if (dev) { pci_bus_assign_resources(bus); - if (pci_bus_add_device(dev)) - pr_err("Unable to hotplug wifi\n"); + pci_bus_add_device(dev); } } else { dev = pci_get_slot(bus, 0); diff --git a/include/linux/pci.h b/include/linux/pci.h index 322335aaa7e1..785149a6aec1 100644 --- a/include/linux/pci.h +++ b/include/linux/pci.h @@ -764,7 +764,7 @@ int pci_scan_slot(struct pci_bus *bus, int devfn); struct pci_dev *pci_scan_single_device(struct pci_bus *bus, int devfn); void pci_device_add(struct pci_dev *dev, struct pci_bus *bus); unsigned int pci_scan_child_bus(struct pci_bus *bus); -int __must_check pci_bus_add_device(struct pci_dev *dev); +void pci_bus_add_device(struct pci_dev *dev); void pci_read_bridge_bases(struct pci_bus *child); struct resource *pci_find_parent_resource(const struct pci_dev *dev, struct resource *res); -- cgit