diff options
Diffstat (limited to 'arch/arm64')
-rw-r--r-- | arch/arm64/Kconfig | 1 | ||||
-rw-r--r-- | arch/arm64/Makefile | 2 | ||||
-rw-r--r-- | arch/arm64/boot/dts/arm/juno-motherboard.dtsi | 12 | ||||
-rw-r--r-- | arch/arm64/include/asm/dma-mapping.h | 15 | ||||
-rw-r--r-- | arch/arm64/include/asm/unistd.h | 2 | ||||
-rw-r--r-- | arch/arm64/include/asm/unistd32.h | 9 | ||||
-rw-r--r-- | arch/arm64/include/uapi/asm/signal.h | 3 | ||||
-rw-r--r-- | arch/arm64/kernel/armv8_deprecated.c | 16 | ||||
-rw-r--r-- | arch/arm64/kernel/efi-stub.c | 14 | ||||
-rw-r--r-- | arch/arm64/kernel/stacktrace.c | 6 | ||||
-rw-r--r-- | arch/arm64/kernel/suspend.c | 22 | ||||
-rw-r--r-- | arch/arm64/mm/dma-mapping.c | 457 |
12 files changed, 520 insertions, 39 deletions
diff --git a/arch/arm64/Kconfig b/arch/arm64/Kconfig index 07d1811..1f823d1 100644 --- a/arch/arm64/Kconfig +++ b/arch/arm64/Kconfig @@ -75,6 +75,7 @@ config ARM64 select HAVE_PERF_USER_STACK_DUMP select HAVE_RCU_TABLE_FREE select HAVE_SYSCALL_TRACEPOINTS + select IOMMU_DMA if IOMMU_SUPPORT select IRQ_DOMAIN select IRQ_FORCED_THREADING select MODULES_USE_ELF_RELA diff --git a/arch/arm64/Makefile b/arch/arm64/Makefile index f9914d7..d10b5d4 100644 --- a/arch/arm64/Makefile +++ b/arch/arm64/Makefile @@ -42,7 +42,7 @@ endif CHECKFLAGS += -D__aarch64__ ifeq ($(CONFIG_ARM64_ERRATUM_843419), y) -CFLAGS_MODULE += -mcmodel=large +KBUILD_CFLAGS_MODULE += -mcmodel=large endif # Default value diff --git a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi index 637e046..3c38668 100644 --- a/arch/arm64/boot/dts/arm/juno-motherboard.dtsi +++ b/arch/arm64/boot/dts/arm/juno-motherboard.dtsi @@ -61,42 +61,42 @@ button@1 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <116>; label = "POWER"; gpios = <&iofpga_gpio0 0 0x4>; }; button@2 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <102>; label = "HOME"; gpios = <&iofpga_gpio0 1 0x4>; }; button@3 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <152>; label = "RLOCK"; gpios = <&iofpga_gpio0 2 0x4>; }; button@4 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <115>; label = "VOL+"; gpios = <&iofpga_gpio0 3 0x4>; }; button@5 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <114>; label = "VOL-"; gpios = <&iofpga_gpio0 4 0x4>; }; button@6 { debounce_interval = <50>; - wakeup = <1>; + wakeup-source; linux,code = <99>; label = "NMI"; gpios = <&iofpga_gpio0 5 0x4>; diff --git a/arch/arm64/include/asm/dma-mapping.h b/arch/arm64/include/asm/dma-mapping.h index cfdb34b..54d0ead 100644 --- a/arch/arm64/include/asm/dma-mapping.h +++ b/arch/arm64/include/asm/dma-mapping.h @@ -54,16 +54,15 @@ static inline struct dma_map_ops *get_dma_ops(struct device *dev) return __generic_dma_ops(dev); } -static inline void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, - struct iommu_ops *iommu, bool coherent) -{ - if (!acpi_disabled && !dev->archdata.dma_ops) - dev->archdata.dma_ops = dma_ops; - - dev->archdata.dma_coherent = coherent; -} +void arch_setup_dma_ops(struct device *dev, u64 dma_base, u64 size, + struct iommu_ops *iommu, bool coherent); #define arch_setup_dma_ops arch_setup_dma_ops +#ifdef CONFIG_IOMMU_DMA +void arch_teardown_dma_ops(struct device *dev); +#define arch_teardown_dma_ops arch_teardown_dma_ops +#endif + /* do not use this function in a driver */ static inline bool is_device_dma_coherent(struct device *dev) { diff --git a/arch/arm64/include/asm/unistd.h b/arch/arm64/include/asm/unistd.h index 3bc498c..41e58fe 100644 --- a/arch/arm64/include/asm/unistd.h +++ b/arch/arm64/include/asm/unistd.h @@ -44,7 +44,7 @@ #define __ARM_NR_compat_cacheflush (__ARM_NR_COMPAT_BASE+2) #define __ARM_NR_compat_set_tls (__ARM_NR_COMPAT_BASE+5) -#define __NR_compat_syscalls 388 +#define __NR_compat_syscalls 390 #endif #define __ARCH_WANT_SYS_CLONE diff --git a/arch/arm64/include/asm/unistd32.h b/arch/arm64/include/asm/unistd32.h index cef934a..5b925b7 100644 --- a/arch/arm64/include/asm/unistd32.h +++ b/arch/arm64/include/asm/unistd32.h @@ -797,3 +797,12 @@ __SYSCALL(__NR_memfd_create, sys_memfd_create) __SYSCALL(__NR_bpf, sys_bpf) #define __NR_execveat 387 __SYSCALL(__NR_execveat, compat_sys_execveat) +#define __NR_userfaultfd 388 +__SYSCALL(__NR_userfaultfd, sys_userfaultfd) +#define __NR_membarrier 389 +__SYSCALL(__NR_membarrier, sys_membarrier) + +/* + * Please add new compat syscalls above this comment and update + * __NR_compat_syscalls in asm/unistd.h. + */ diff --git a/arch/arm64/include/uapi/asm/signal.h b/arch/arm64/include/uapi/asm/signal.h index 8d1e723..991bf5d 100644 --- a/arch/arm64/include/uapi/asm/signal.h +++ b/arch/arm64/include/uapi/asm/signal.h @@ -19,6 +19,9 @@ /* Required for AArch32 compatibility. */ #define SA_RESTORER 0x04000000 +#define MINSIGSTKSZ 5120 +#define SIGSTKSZ 16384 + #include <asm-generic/signal.h> #endif diff --git a/arch/arm64/kernel/armv8_deprecated.c b/arch/arm64/kernel/armv8_deprecated.c index bcee7ab..937f5e5 100644 --- a/arch/arm64/kernel/armv8_deprecated.c +++ b/arch/arm64/kernel/armv8_deprecated.c @@ -284,21 +284,23 @@ static void register_insn_emulation_sysctl(struct ctl_table *table) __asm__ __volatile__( \ ALTERNATIVE("nop", SET_PSTATE_PAN(0), ARM64_HAS_PAN, \ CONFIG_ARM64_PAN) \ - " mov %w2, %w1\n" \ - "0: ldxr"B" %w1, [%3]\n" \ - "1: stxr"B" %w0, %w2, [%3]\n" \ + "0: ldxr"B" %w2, [%3]\n" \ + "1: stxr"B" %w0, %w1, [%3]\n" \ " cbz %w0, 2f\n" \ " mov %w0, %w4\n" \ + " b 3f\n" \ "2:\n" \ + " mov %w1, %w2\n" \ + "3:\n" \ " .pushsection .fixup,\"ax\"\n" \ " .align 2\n" \ - "3: mov %w0, %w5\n" \ - " b 2b\n" \ + "4: mov %w0, %w5\n" \ + " b 3b\n" \ " .popsection" \ " .pushsection __ex_table,\"a\"\n" \ " .align 3\n" \ - " .quad 0b, 3b\n" \ - " .quad 1b, 3b\n" \ + " .quad 0b, 4b\n" \ + " .quad 1b, 4b\n" \ " .popsection\n" \ ALTERNATIVE("nop", SET_PSTATE_PAN(1), ARM64_HAS_PAN, \ CONFIG_ARM64_PAN) \ diff --git a/arch/arm64/kernel/efi-stub.c b/arch/arm64/kernel/efi-stub.c index 816120e..78dfbd3 100644 --- a/arch/arm64/kernel/efi-stub.c +++ b/arch/arm64/kernel/efi-stub.c @@ -25,10 +25,20 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg, unsigned long kernel_size, kernel_memsize = 0; unsigned long nr_pages; void *old_image_addr = (void *)*image_addr; + unsigned long preferred_offset; + + /* + * The preferred offset of the kernel Image is TEXT_OFFSET bytes beyond + * a 2 MB aligned base, which itself may be lower than dram_base, as + * long as the resulting offset equals or exceeds it. + */ + preferred_offset = round_down(dram_base, SZ_2M) + TEXT_OFFSET; + if (preferred_offset < dram_base) + preferred_offset += SZ_2M; /* Relocate the image, if required. */ kernel_size = _edata - _text; - if (*image_addr != (dram_base + TEXT_OFFSET)) { + if (*image_addr != preferred_offset) { kernel_memsize = kernel_size + (_end - _edata); /* @@ -42,7 +52,7 @@ efi_status_t __init handle_kernel_image(efi_system_table_t *sys_table_arg, * Mustang), we can still place the kernel at the address * 'dram_base + TEXT_OFFSET'. */ - *image_addr = *reserve_addr = dram_base + TEXT_OFFSET; + *image_addr = *reserve_addr = preferred_offset; nr_pages = round_up(kernel_memsize, EFI_ALLOC_ALIGN) / EFI_PAGE_SIZE; status = efi_call_early(allocate_pages, EFI_ALLOCATE_ADDRESS, diff --git a/arch/arm64/kernel/stacktrace.c b/arch/arm64/kernel/stacktrace.c index 407991b..ccb6078 100644 --- a/arch/arm64/kernel/stacktrace.c +++ b/arch/arm64/kernel/stacktrace.c @@ -48,11 +48,7 @@ int notrace unwind_frame(struct stackframe *frame) frame->sp = fp + 0x10; frame->fp = *(unsigned long *)(fp); - /* - * -4 here because we care about the PC at time of bl, - * not where the return will go. - */ - frame->pc = *(unsigned long *)(fp + 8) - 4; + frame->pc = *(unsigned long *)(fp + 8); return 0; } diff --git a/arch/arm64/kernel/suspend.c b/arch/arm64/kernel/suspend.c index 8297d50..44ca414 100644 --- a/arch/arm64/kernel/suspend.c +++ b/arch/arm64/kernel/suspend.c @@ -80,17 +80,21 @@ int cpu_suspend(unsigned long arg, int (*fn)(unsigned long)) if (ret == 0) { /* * We are resuming from reset with TTBR0_EL1 set to the - * idmap to enable the MMU; restore the active_mm mappings in - * TTBR0_EL1 unless the active_mm == &init_mm, in which case - * the thread entered cpu_suspend with TTBR0_EL1 set to - * reserved TTBR0 page tables and should be restored as such. + * idmap to enable the MMU; set the TTBR0 to the reserved + * page tables to prevent speculative TLB allocations, flush + * the local tlb and set the default tcr_el1.t0sz so that + * the TTBR0 address space set-up is properly restored. + * If the current active_mm != &init_mm we entered cpu_suspend + * with mappings in TTBR0 that must be restored, so we switch + * them back to complete the address space configuration + * restoration before returning. */ - if (mm == &init_mm) - cpu_set_reserved_ttbr0(); - else - cpu_switch_mm(mm->pgd, mm); - + cpu_set_reserved_ttbr0(); flush_tlb_all(); + cpu_set_default_tcr_t0sz(); + + if (mm != &init_mm) + cpu_switch_mm(mm->pgd, mm); /* * Restore per-cpu offset before any kernel diff --git a/arch/arm64/mm/dma-mapping.c b/arch/arm64/mm/dma-mapping.c index 99224dc..6320361 100644 --- a/arch/arm64/mm/dma-mapping.c +++ b/arch/arm64/mm/dma-mapping.c @@ -533,3 +533,460 @@ 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); + void *addr; + + if (WARN(!dev, "cannot create IOMMU mapping for unknown device\n")) + return NULL; + /* + * 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 (gfp & __GFP_WAIT) { + struct page **pages; + pgprot_t prot = __get_dma_pgprot(attrs, PAGE_KERNEL, coherent); + + pages = iommu_dma_alloc(dev, size, 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, size, 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, size, 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) +{ + /* + * @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, size, 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, size, &handle); + dma_common_free_remap(cpu_addr, size, VM_USERMAP); + } else { + iommu_dma_unmap_page(dev, handle, size, 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); + 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 (!acpi_disabled && !dev->archdata.dma_ops) + dev->archdata.dma_ops = dma_ops; + + dev->archdata.dma_coherent = coherent; + __iommu_setup_dma_ops(dev, dma_base, size, iommu); +} |