diff options
author | 2016-04-11 10:41:07 +0300 | |
---|---|---|
committer | 2016-04-13 08:17:18 +0300 | |
commit | e09b41010ba33a20a87472ee821fa407a5b8da36 (patch) | |
tree | d10dc367189862e7ca5c592f033dc3726e1df4e3 /kernel/arch/arm64/mm/dma-mapping.c | |
parent | f93b97fd65072de626c074dbe099a1fff05ce060 (diff) |
These changes are the raw update to linux-4.4.6-rt14. Kernel sources
are taken from kernel.org, and rt patch from the rt wiki download page.
During the rebasing, the following patch collided:
Force tick interrupt and get rid of softirq magic(I70131fb85).
Collisions have been removed because its logic was found on the
source already.
Change-Id: I7f57a4081d9deaa0d9ccfc41a6c8daccdee3b769
Signed-off-by: José Pekkarinen <jose.pekkarinen@nokia.com>
Diffstat (limited to 'kernel/arch/arm64/mm/dma-mapping.c')
-rw-r--r-- | kernel/arch/arm64/mm/dma-mapping.c | 605 |
1 files changed, 582 insertions, 23 deletions
diff --git a/kernel/arch/arm64/mm/dma-mapping.c b/kernel/arch/arm64/mm/dma-mapping.c index b0bd4e5fd..354144e33 100644 --- a/kernel/arch/arm64/mm/dma-mapping.c +++ b/kernel/arch/arm64/mm/dma-mapping.c @@ -18,6 +18,7 @@ */ #include <linux/gfp.h> +#include <linux/acpi.h> #include <linux/export.h> #include <linux/slab.h> #include <linux/genalloc.h> @@ -28,9 +29,6 @@ #include <asm/cacheflush.h> -struct dma_map_ops *dma_ops; -EXPORT_SYMBOL(dma_ops); - static pgprot_t __get_dma_pgprot(struct dma_attrs *attrs, pgprot_t prot, bool coherent) { @@ -100,7 +98,7 @@ static void *__dma_alloc_coherent(struct device *dev, size_t size, if (IS_ENABLED(CONFIG_ZONE_DMA) && dev->coherent_dma_mask <= DMA_BIT_MASK(32)) flags |= GFP_DMA; - if (IS_ENABLED(CONFIG_DMA_CMA) && (flags & __GFP_WAIT)) { + if (dev_get_cma_area(dev) && gfpflags_allow_blocking(flags)) { struct page *page; void *addr; @@ -144,10 +142,11 @@ static void *__dma_alloc(struct device *dev, size_t size, struct page *page; void *ptr, *coherent_ptr; bool coherent = is_device_dma_coherent(dev); + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, false); size = PAGE_ALIGN(size); - if (!coherent && !(flags & __GFP_WAIT)) { + if (!coherent && !gfpflags_allow_blocking(flags)) { struct page *page = NULL; void *addr = __alloc_from_pool(size, &page, flags); @@ -171,9 +170,7 @@ static void *__dma_alloc(struct device *dev, size_t size, /* create a coherent mapping */ page = virt_to_page(ptr); coherent_ptr = dma_common_contiguous_remap(page, size, VM_USERMAP, - __get_dma_pgprot(attrs, - __pgprot(PROT_NORMAL_NC), false), - NULL); + prot, NULL); if (!coherent_ptr) goto no_map; @@ -303,9 +300,10 @@ static void __swiotlb_sync_sg_for_device(struct device *dev, sg->length, dir); } -/* vma->vm_page_prot must be set appropriately before calling this function */ -static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size) +static int __swiotlb_mmap(struct device *dev, + struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) { int ret = -ENXIO; unsigned long nr_vma_pages = (vma->vm_end - vma->vm_start) >> @@ -314,6 +312,9 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma, unsigned long pfn = dma_to_phys(dev, dma_addr) >> PAGE_SHIFT; unsigned long off = vma->vm_pgoff; + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, + is_device_dma_coherent(dev)); + if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) return ret; @@ -327,20 +328,24 @@ static int __dma_common_mmap(struct device *dev, struct vm_area_struct *vma, return ret; } -static int __swiotlb_mmap(struct device *dev, - struct vm_area_struct *vma, - void *cpu_addr, dma_addr_t dma_addr, size_t size, - struct dma_attrs *attrs) +static int __swiotlb_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t handle, size_t size, + struct dma_attrs *attrs) { - vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, - is_device_dma_coherent(dev)); - return __dma_common_mmap(dev, vma, cpu_addr, dma_addr, size); + int ret = sg_alloc_table(sgt, 1, GFP_KERNEL); + + if (!ret) + sg_set_page(sgt->sgl, phys_to_page(dma_to_phys(dev, handle)), + PAGE_ALIGN(size), 0); + + return ret; } static struct dma_map_ops swiotlb_dma_ops = { .alloc = __dma_alloc, .free = __dma_free, .mmap = __swiotlb_mmap, + .get_sgtable = __swiotlb_get_sgtable, .map_page = __swiotlb_map_page, .unmap_page = __swiotlb_unmap_page, .map_sg = __swiotlb_map_sg_attrs, @@ -414,15 +419,101 @@ out: return -ENOMEM; } -static int __init arm64_dma_init(void) +/******************************************** + * The following APIs are for dummy DMA ops * + ********************************************/ + +static void *__dummy_alloc(struct device *dev, size_t size, + dma_addr_t *dma_handle, gfp_t flags, + struct dma_attrs *attrs) { - int ret; + return NULL; +} - dma_ops = &swiotlb_dma_ops; +static void __dummy_free(struct device *dev, size_t size, + void *vaddr, dma_addr_t dma_handle, + struct dma_attrs *attrs) +{ +} - ret = atomic_pool_init(); +static int __dummy_mmap(struct device *dev, + struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) +{ + return -ENXIO; +} - return ret; +static dma_addr_t __dummy_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return DMA_ERROR_CODE; +} + +static void __dummy_unmap_page(struct device *dev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ +} + +static int __dummy_map_sg(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + return 0; +} + +static void __dummy_unmap_sg(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ +} + +static void __dummy_sync_single(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ +} + +static void __dummy_sync_sg(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ +} + +static int __dummy_mapping_error(struct device *hwdev, dma_addr_t dma_addr) +{ + return 1; +} + +static int __dummy_dma_supported(struct device *hwdev, u64 mask) +{ + return 0; +} + +struct dma_map_ops dummy_dma_ops = { + .alloc = __dummy_alloc, + .free = __dummy_free, + .mmap = __dummy_mmap, + .map_page = __dummy_map_page, + .unmap_page = __dummy_unmap_page, + .map_sg = __dummy_map_sg, + .unmap_sg = __dummy_unmap_sg, + .sync_single_for_cpu = __dummy_sync_single, + .sync_single_for_device = __dummy_sync_single, + .sync_sg_for_cpu = __dummy_sync_sg, + .sync_sg_for_device = __dummy_sync_sg, + .mapping_error = __dummy_mapping_error, + .dma_supported = __dummy_dma_supported, +}; +EXPORT_SYMBOL(dummy_dma_ops); + +static int __init arm64_dma_init(void) +{ + return atomic_pool_init(); } arch_initcall(arm64_dma_init); @@ -434,3 +525,471 @@ static int __init dma_debug_do_init(void) return 0; } fs_initcall(dma_debug_do_init); + + +#ifdef CONFIG_IOMMU_DMA +#include <linux/dma-iommu.h> +#include <linux/platform_device.h> +#include <linux/amba/bus.h> + +/* Thankfully, all cache ops are by VA so we can ignore phys here */ +static void flush_page(struct device *dev, const void *virt, phys_addr_t phys) +{ + __dma_flush_range(virt, virt + PAGE_SIZE); +} + +static void *__iommu_alloc_attrs(struct device *dev, size_t size, + dma_addr_t *handle, gfp_t gfp, + struct dma_attrs *attrs) +{ + bool coherent = is_device_dma_coherent(dev); + int ioprot = dma_direction_to_prot(DMA_BIDIRECTIONAL, coherent); + size_t iosize = size; + void *addr; + + if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) + return NULL; + + size = PAGE_ALIGN(size); + + /* + * Some drivers rely on this, and we probably don't want the + * possibility of stale kernel data being read by devices anyway. + */ + gfp |= __GFP_ZERO; + + if (gfpflags_allow_blocking(gfp)) { + struct page **pages; + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); + + pages = iommu_dma_alloc(dev, iosize, gfp, ioprot, handle, + flush_page); + if (!pages) + return NULL; + + addr = dma_common_pages_remap(pages, size, VM_USERMAP, prot, + __builtin_return_address(0)); + if (!addr) + iommu_dma_free(dev, pages, iosize, handle); + } else { + struct page *page; + /* + * In atomic context we can't remap anything, so we'll only + * get the virtually contiguous buffer we need by way of a + * physically contiguous allocation. + */ + if (coherent) { + page = alloc_pages(gfp, get_order(size)); + addr = page ? page_address(page) : NULL; + } else { + addr = __alloc_from_pool(size, &page, gfp); + } + if (!addr) + return NULL; + + *handle = iommu_dma_map_page(dev, page, 0, iosize, ioprot); + if (iommu_dma_mapping_error(dev, *handle)) { + if (coherent) + __free_pages(page, get_order(size)); + else + __free_from_pool(addr, size); + addr = NULL; + } + } + return addr; +} + +static void __iommu_free_attrs(struct device *dev, size_t size, void *cpu_addr, + dma_addr_t handle, struct dma_attrs *attrs) +{ + size_t iosize = size; + + size = PAGE_ALIGN(size); + /* + * @cpu_addr will be one of 3 things depending on how it was allocated: + * - A remapped array of pages from iommu_dma_alloc(), for all + * non-atomic allocations. + * - A non-cacheable alias from the atomic pool, for atomic + * allocations by non-coherent devices. + * - A normal lowmem address, for atomic allocations by + * coherent devices. + * Hence how dodgy the below logic looks... + */ + if (__in_atomic_pool(cpu_addr, size)) { + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); + __free_from_pool(cpu_addr, size); + } else if (is_vmalloc_addr(cpu_addr)){ + struct vm_struct *area = find_vm_area(cpu_addr); + + if (WARN_ON(!area || !area->pages)) + return; + iommu_dma_free(dev, area->pages, iosize, &handle); + dma_common_free_remap(cpu_addr, size, VM_USERMAP); + } else { + iommu_dma_unmap_page(dev, handle, iosize, 0, NULL); + __free_pages(virt_to_page(cpu_addr), get_order(size)); + } +} + +static int __iommu_mmap_attrs(struct device *dev, struct vm_area_struct *vma, + void *cpu_addr, dma_addr_t dma_addr, size_t size, + struct dma_attrs *attrs) +{ + struct vm_struct *area; + int ret; + + vma->vm_page_prot = __get_dma_pgprot(attrs, vma->vm_page_prot, + is_device_dma_coherent(dev)); + + if (dma_mmap_from_coherent(dev, vma, cpu_addr, size, &ret)) + return ret; + + area = find_vm_area(cpu_addr); + if (WARN_ON(!area || !area->pages)) + return -ENXIO; + + return iommu_dma_mmap(area->pages, size, vma); +} + +static int __iommu_get_sgtable(struct device *dev, struct sg_table *sgt, + void *cpu_addr, dma_addr_t dma_addr, + size_t size, struct dma_attrs *attrs) +{ + unsigned int count = PAGE_ALIGN(size) >> PAGE_SHIFT; + struct vm_struct *area = find_vm_area(cpu_addr); + + if (WARN_ON(!area || !area->pages)) + return -ENXIO; + + return sg_alloc_table_from_pages(sgt, area->pages, count, 0, size, + GFP_KERNEL); +} + +static void __iommu_sync_single_for_cpu(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ + phys_addr_t phys; + + if (is_device_dma_coherent(dev)) + return; + + phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr); + __dma_unmap_area(phys_to_virt(phys), size, dir); +} + +static void __iommu_sync_single_for_device(struct device *dev, + dma_addr_t dev_addr, size_t size, + enum dma_data_direction dir) +{ + phys_addr_t phys; + + if (is_device_dma_coherent(dev)) + return; + + phys = iommu_iova_to_phys(iommu_get_domain_for_dev(dev), dev_addr); + __dma_map_area(phys_to_virt(phys), size, dir); +} + +static dma_addr_t __iommu_map_page(struct device *dev, struct page *page, + unsigned long offset, size_t size, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + bool coherent = is_device_dma_coherent(dev); + int prot = dma_direction_to_prot(dir, coherent); + dma_addr_t dev_addr = iommu_dma_map_page(dev, page, offset, size, prot); + + if (!iommu_dma_mapping_error(dev, dev_addr) && + !dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_single_for_device(dev, dev_addr, size, dir); + + return dev_addr; +} + +static void __iommu_unmap_page(struct device *dev, dma_addr_t dev_addr, + size_t size, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_single_for_cpu(dev, dev_addr, size, dir); + + iommu_dma_unmap_page(dev, dev_addr, size, dir, attrs); +} + +static void __iommu_sync_sg_for_cpu(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + if (is_device_dma_coherent(dev)) + return; + + for_each_sg(sgl, sg, nelems, i) + __dma_unmap_area(sg_virt(sg), sg->length, dir); +} + +static void __iommu_sync_sg_for_device(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir) +{ + struct scatterlist *sg; + int i; + + if (is_device_dma_coherent(dev)) + return; + + for_each_sg(sgl, sg, nelems, i) + __dma_map_area(sg_virt(sg), sg->length, dir); +} + +static int __iommu_map_sg_attrs(struct device *dev, struct scatterlist *sgl, + int nelems, enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + bool coherent = is_device_dma_coherent(dev); + + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_sg_for_device(dev, sgl, nelems, dir); + + return iommu_dma_map_sg(dev, sgl, nelems, + dma_direction_to_prot(dir, coherent)); +} + +static void __iommu_unmap_sg_attrs(struct device *dev, + struct scatterlist *sgl, int nelems, + enum dma_data_direction dir, + struct dma_attrs *attrs) +{ + if (!dma_get_attr(DMA_ATTR_SKIP_CPU_SYNC, attrs)) + __iommu_sync_sg_for_cpu(dev, sgl, nelems, dir); + + iommu_dma_unmap_sg(dev, sgl, nelems, dir, attrs); +} + +static struct dma_map_ops iommu_dma_ops = { + .alloc = __iommu_alloc_attrs, + .free = __iommu_free_attrs, + .mmap = __iommu_mmap_attrs, + .get_sgtable = __iommu_get_sgtable, + .map_page = __iommu_map_page, + .unmap_page = __iommu_unmap_page, + .map_sg = __iommu_map_sg_attrs, + .unmap_sg = __iommu_unmap_sg_attrs, + .sync_single_for_cpu = __iommu_sync_single_for_cpu, + .sync_single_for_device = __iommu_sync_single_for_device, + .sync_sg_for_cpu = __iommu_sync_sg_for_cpu, + .sync_sg_for_device = __iommu_sync_sg_for_device, + .dma_supported = iommu_dma_supported, + .mapping_error = iommu_dma_mapping_error, +}; + +/* + * TODO: Right now __iommu_setup_dma_ops() gets called too early to do + * everything it needs to - the device is only partially created and the + * IOMMU driver hasn't seen it yet, so it can't have a group. Thus we + * need this delayed attachment dance. Once IOMMU probe ordering is sorted + * to move the arch_setup_dma_ops() call later, all the notifier bits below + * become unnecessary, and will go away. + */ +struct iommu_dma_notifier_data { + struct list_head list; + struct device *dev; + const struct iommu_ops *ops; + u64 dma_base; + u64 size; +}; +static LIST_HEAD(iommu_dma_masters); +static DEFINE_MUTEX(iommu_dma_notifier_lock); + +/* + * Temporarily "borrow" a domain feature flag to to tell if we had to resort + * to creating our own domain here, in case we need to clean it up again. + */ +#define __IOMMU_DOMAIN_FAKE_DEFAULT (1U << 31) + +static bool do_iommu_attach(struct device *dev, const struct iommu_ops *ops, + u64 dma_base, u64 size) +{ + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + + /* + * Best case: The device is either part of a group which was + * already attached to a domain in a previous call, or it's + * been put in a default DMA domain by the IOMMU core. + */ + if (!domain) { + /* + * Urgh. The IOMMU core isn't going to do default domains + * for non-PCI devices anyway, until it has some means of + * abstracting the entirely implementation-specific + * sideband data/SoC topology/unicorn dust that may or + * may not differentiate upstream masters. + * So until then, HORRIBLE HACKS! + */ + domain = ops->domain_alloc(IOMMU_DOMAIN_DMA); + if (!domain) + goto out_no_domain; + + domain->ops = ops; + domain->type = IOMMU_DOMAIN_DMA | __IOMMU_DOMAIN_FAKE_DEFAULT; + + if (iommu_attach_device(domain, dev)) + goto out_put_domain; + } + + if (iommu_dma_init_domain(domain, dma_base, size)) + goto out_detach; + + dev->archdata.dma_ops = &iommu_dma_ops; + return true; + +out_detach: + iommu_detach_device(domain, dev); +out_put_domain: + if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT) + iommu_domain_free(domain); +out_no_domain: + pr_warn("Failed to set up IOMMU for device %s; retaining platform DMA ops\n", + dev_name(dev)); + return false; +} + +static void queue_iommu_attach(struct device *dev, const struct iommu_ops *ops, + u64 dma_base, u64 size) +{ + struct iommu_dma_notifier_data *iommudata; + + iommudata = kzalloc(sizeof(*iommudata), GFP_KERNEL); + if (!iommudata) + return; + + iommudata->dev = dev; + iommudata->ops = ops; + iommudata->dma_base = dma_base; + iommudata->size = size; + + mutex_lock(&iommu_dma_notifier_lock); + list_add(&iommudata->list, &iommu_dma_masters); + mutex_unlock(&iommu_dma_notifier_lock); +} + +static int __iommu_attach_notifier(struct notifier_block *nb, + unsigned long action, void *data) +{ + struct iommu_dma_notifier_data *master, *tmp; + + if (action != BUS_NOTIFY_ADD_DEVICE) + return 0; + + mutex_lock(&iommu_dma_notifier_lock); + list_for_each_entry_safe(master, tmp, &iommu_dma_masters, list) { + if (do_iommu_attach(master->dev, master->ops, + master->dma_base, master->size)) { + list_del(&master->list); + kfree(master); + } + } + mutex_unlock(&iommu_dma_notifier_lock); + return 0; +} + +static int register_iommu_dma_ops_notifier(struct bus_type *bus) +{ + struct notifier_block *nb = kzalloc(sizeof(*nb), GFP_KERNEL); + int ret; + + if (!nb) + return -ENOMEM; + /* + * The device must be attached to a domain before the driver probe + * routine gets a chance to start allocating DMA buffers. However, + * the IOMMU driver also needs a chance to configure the iommu_group + * via its add_device callback first, so we need to make the attach + * happen between those two points. Since the IOMMU core uses a bus + * notifier with default priority for add_device, do the same but + * with a lower priority to ensure the appropriate ordering. + */ + nb->notifier_call = __iommu_attach_notifier; + nb->priority = -100; + + ret = bus_register_notifier(bus, nb); + if (ret) { + pr_warn("Failed to register DMA domain notifier; IOMMU DMA ops unavailable on bus '%s'\n", + bus->name); + kfree(nb); + } + return ret; +} + +static int __init __iommu_dma_init(void) +{ + int ret; + + ret = iommu_dma_init(); + if (!ret) + ret = register_iommu_dma_ops_notifier(&platform_bus_type); + if (!ret) + ret = register_iommu_dma_ops_notifier(&amba_bustype); + + /* handle devices queued before this arch_initcall */ + if (!ret) + __iommu_attach_notifier(NULL, BUS_NOTIFY_ADD_DEVICE, NULL); + return ret; +} +arch_initcall(__iommu_dma_init); + +static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + const struct iommu_ops *ops) +{ + struct iommu_group *group; + + if (!ops) + return; + /* + * TODO: As a concession to the future, we're ready to handle being + * called both early and late (i.e. after bus_add_device). Once all + * the platform bus code is reworked to call us late and the notifier + * junk above goes away, move the body of do_iommu_attach here. + */ + group = iommu_group_get(dev); + if (group) { + do_iommu_attach(dev, ops, dma_base, size); + iommu_group_put(group); + } else { + queue_iommu_attach(dev, ops, dma_base, size); + } +} + +void arch_teardown_dma_ops(struct device *dev) +{ + struct iommu_domain *domain = iommu_get_domain_for_dev(dev); + + if (domain) { + iommu_detach_device(domain, dev); + if (domain->type & __IOMMU_DOMAIN_FAKE_DEFAULT) + iommu_domain_free(domain); + } + + dev->archdata.dma_ops = NULL; +} + +#else + +static void __iommu_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + struct iommu_ops *iommu) +{ } + +#endif /* CONFIG_IOMMU_DMA */ + +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + struct iommu_ops *iommu, bool coherent) +{ + if (!dev->archdata.dma_ops) + dev->archdata.dma_ops = &swiotlb_dma_ops; + + dev->archdata.dma_coherent = coherent; + __iommu_setup_dma_ops(dev, dma_base, size, iommu); +} |