diff options
Diffstat (limited to 'drivers/char/mem.c')
| -rw-r--r-- | drivers/char/mem.c | 186 |
1 files changed, 95 insertions, 91 deletions
diff --git a/drivers/char/mem.c b/drivers/char/mem.c index 83bf2a4dcb57..52039fae1594 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -31,10 +31,6 @@ #include <linux/uaccess.h> #include <linux/security.h> -#ifdef CONFIG_IA64 -# include <linux/efi.h> -#endif - #define DEVMEM_MINOR 1 #define DEVPORT_MINOR 4 @@ -65,36 +61,11 @@ static inline int page_is_allowed(unsigned long pfn) { return devmem_is_allowed(pfn); } -static inline int range_is_allowed(unsigned long pfn, unsigned long size) -{ - u64 from = ((u64)pfn) << PAGE_SHIFT; - u64 to = from + size; - u64 cursor = from; - - while (cursor < to) { - if (!devmem_is_allowed(pfn)) - return 0; - cursor += PAGE_SIZE; - pfn++; - } - return 1; -} #else static inline int page_is_allowed(unsigned long pfn) { return 1; } -static inline int range_is_allowed(unsigned long pfn, unsigned long size) -{ - return 1; -} -#endif - -#ifndef unxlate_dev_mem_ptr -#define unxlate_dev_mem_ptr unxlate_dev_mem_ptr -void __weak unxlate_dev_mem_ptr(phys_addr_t phys, void *addr) -{ -} #endif static inline bool should_stop_iteration(void) @@ -284,13 +255,6 @@ int __weak phys_mem_access_prot_allowed(struct file *file, #ifdef pgprot_noncached static int uncached_access(struct file *file, phys_addr_t addr) { -#if defined(CONFIG_IA64) - /* - * On ia64, we ignore O_DSYNC because we cannot tolerate memory - * attribute aliases. - */ - return !(efi_mem_attributes(addr) & EFI_MEMORY_WB); -#else /* * Accessing memory above the top the kernel knows about or through a * file pointer @@ -299,7 +263,6 @@ static int uncached_access(struct file *file, phys_addr_t addr) if (file->f_flags & O_DSYNC) return 1; return addr >= __pa(high_memory); -#endif } #endif @@ -341,13 +304,13 @@ static unsigned zero_mmap_capabilities(struct file *file) } /* can't do an in-place private mapping if there's no MMU */ -static inline int private_mapping_ok(struct vm_area_struct *vma) +static inline int private_mapping_ok(struct vm_area_desc *desc) { - return vma->vm_flags & VM_MAYSHARE; + return is_nommu_shared_mapping(desc->vm_flags); } #else -static inline int private_mapping_ok(struct vm_area_struct *vma) +static inline int private_mapping_ok(struct vm_area_desc *desc) { return 1; } @@ -359,49 +322,53 @@ static const struct vm_operations_struct mmap_mem_ops = { #endif }; -static int mmap_mem(struct file *file, struct vm_area_struct *vma) +static int mmap_filter_error(int err) +{ + return -EAGAIN; +} + +static int mmap_mem_prepare(struct vm_area_desc *desc) { - size_t size = vma->vm_end - vma->vm_start; - phys_addr_t offset = (phys_addr_t)vma->vm_pgoff << PAGE_SHIFT; + struct file *file = desc->file; + const size_t size = vma_desc_size(desc); + const phys_addr_t offset = (phys_addr_t)desc->pgoff << PAGE_SHIFT; /* Does it even fit in phys_addr_t? */ - if (offset >> PAGE_SHIFT != vma->vm_pgoff) + if (offset >> PAGE_SHIFT != desc->pgoff) return -EINVAL; /* It's illegal to wrap around the end of the physical address space. */ if (offset + (phys_addr_t)size - 1 < offset) return -EINVAL; - if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size)) + if (!valid_mmap_phys_addr_range(desc->pgoff, size)) return -EINVAL; - if (!private_mapping_ok(vma)) + if (!private_mapping_ok(desc)) return -ENOSYS; - if (!range_is_allowed(vma->vm_pgoff, size)) + if (!range_is_allowed(desc->pgoff, size)) return -EPERM; - if (!phys_mem_access_prot_allowed(file, vma->vm_pgoff, size, - &vma->vm_page_prot)) + if (!phys_mem_access_prot_allowed(file, desc->pgoff, size, + &desc->page_prot)) return -EINVAL; - vma->vm_page_prot = phys_mem_access_prot(file, vma->vm_pgoff, - size, - vma->vm_page_prot); + desc->page_prot = phys_mem_access_prot(file, desc->pgoff, + size, + desc->page_prot); - vma->vm_ops = &mmap_mem_ops; + desc->vm_ops = &mmap_mem_ops; + + /* Remap-pfn-range will mark the range VM_IO. */ + mmap_action_remap_full(desc, desc->pgoff); + /* We filter remap errors to -EAGAIN. */ + desc->action.error_hook = mmap_filter_error; - /* Remap-pfn-range will mark the range VM_IO */ - if (remap_pfn_range(vma, - vma->vm_start, - vma->vm_pgoff, - size, - vma->vm_page_prot)) { - return -EAGAIN; - } return 0; } +#ifdef CONFIG_DEVPORT static ssize_t read_port(struct file *file, char __user *buf, size_t count, loff_t *ppos) { @@ -443,6 +410,7 @@ static ssize_t write_port(struct file *file, const char __user *buf, *ppos = i; return tmp-buf; } +#endif static ssize_t read_null(struct file *file, char __user *buf, size_t count, loff_t *ppos) @@ -536,38 +504,64 @@ static ssize_t read_zero(struct file *file, char __user *buf, return cleared; } -static int mmap_zero(struct file *file, struct vm_area_struct *vma) +static int mmap_zero_private_success(const struct vm_area_struct *vma) +{ + /* + * This is a highly unique situation where we mark a MAP_PRIVATE mapping + * of /dev/zero anonymous, despite it not being. + */ + vma_set_anonymous((struct vm_area_struct *)vma); + + return 0; +} + +static int mmap_zero_prepare(struct vm_area_desc *desc) { #ifndef CONFIG_MMU return -ENOSYS; #endif - if (vma->vm_flags & VM_SHARED) - return shmem_zero_setup(vma); - vma_set_anonymous(vma); + if (desc->vm_flags & VM_SHARED) + return shmem_zero_setup_desc(desc); + + desc->action.success_hook = mmap_zero_private_success; return 0; } +#ifndef CONFIG_MMU +static unsigned long get_unmapped_area_zero(struct file *file, + unsigned long addr, unsigned long len, + unsigned long pgoff, unsigned long flags) +{ + return -ENOSYS; +} +#else static unsigned long get_unmapped_area_zero(struct file *file, unsigned long addr, unsigned long len, unsigned long pgoff, unsigned long flags) { -#ifdef CONFIG_MMU if (flags & MAP_SHARED) { /* - * mmap_zero() will call shmem_zero_setup() to create a file, - * so use shmem's get_unmapped_area in case it can be huge; - * and pass NULL for file as in mmap.c's get_unmapped_area(), - * so as not to confuse shmem with our handle on "/dev/zero". + * mmap_zero_prepare() will call shmem_zero_setup() to create a + * file, so use shmem's get_unmapped_area in case it can be + * huge; and pass NULL for file as in mmap.c's + * get_unmapped_area(), so as not to confuse shmem with our + * handle on "/dev/zero". */ return shmem_get_unmapped_area(NULL, addr, len, pgoff, flags); } - /* Otherwise flags & MAP_PRIVATE: with no shmem object beneath it */ - return current->mm->get_unmapped_area(file, addr, len, pgoff, flags); + /* + * Otherwise flags & MAP_PRIVATE: with no shmem object beneath it, + * attempt to map aligned to huge page size if possible, otherwise we + * fall back to system page size mappings. + */ +#ifdef CONFIG_TRANSPARENT_HUGEPAGE + return thp_get_unmapped_area(file, addr, len, pgoff, flags); #else - return -ENOSYS; + return mm_get_unmapped_area(file, addr, len, pgoff, flags); #endif } +#endif /* CONFIG_MMU */ static ssize_t write_full(struct file *file, const char __user *buf, size_t count, loff_t *ppos) @@ -647,18 +641,20 @@ static int open_port(struct inode *inode, struct file *filp) #define full_lseek null_lseek #define write_zero write_null #define write_iter_zero write_iter_null +#define splice_write_zero splice_write_null #define open_mem open_port static const struct file_operations __maybe_unused mem_fops = { .llseek = memory_lseek, .read = read_mem, .write = write_mem, - .mmap = mmap_mem, + .mmap_prepare = mmap_mem_prepare, .open = open_mem, #ifndef CONFIG_MMU .get_unmapped_area = get_unmapped_area_mem, .mmap_capabilities = memory_mmap_capabilities, #endif + .fop_flags = FOP_UNSIGNED_OFFSET, }; static const struct file_operations null_fops = { @@ -671,12 +667,14 @@ static const struct file_operations null_fops = { .uring_cmd = uring_cmd_null, }; -static const struct file_operations __maybe_unused port_fops = { +#ifdef CONFIG_DEVPORT +static const struct file_operations port_fops = { .llseek = memory_lseek, .read = read_port, .write = write_port, .open = open_port, }; +#endif static const struct file_operations zero_fops = { .llseek = zero_lseek, @@ -684,7 +682,9 @@ static const struct file_operations zero_fops = { .read_iter = read_iter_zero, .read = read_zero, .write_iter = write_iter_zero, - .mmap = mmap_zero, + .splice_read = copy_splice_read, + .splice_write = splice_write_zero, + .mmap_prepare = mmap_zero_prepare, .get_unmapped_area = get_unmapped_area_zero, #ifndef CONFIG_MMU .mmap_capabilities = zero_mmap_capabilities, @@ -695,27 +695,28 @@ static const struct file_operations full_fops = { .llseek = full_lseek, .read_iter = read_iter_zero, .write = write_full, + .splice_read = copy_splice_read, }; static const struct memdev { const char *name; - umode_t mode; const struct file_operations *fops; fmode_t fmode; + umode_t mode; } devlist[] = { #ifdef CONFIG_DEVMEM - [DEVMEM_MINOR] = { "mem", 0, &mem_fops, FMODE_UNSIGNED_OFFSET }, + [DEVMEM_MINOR] = { "mem", &mem_fops, 0, 0 }, #endif - [3] = { "null", 0666, &null_fops, FMODE_NOWAIT }, + [3] = { "null", &null_fops, FMODE_NOWAIT, 0666 }, #ifdef CONFIG_DEVPORT - [4] = { "port", 0, &port_fops, 0 }, + [4] = { "port", &port_fops, 0, 0 }, #endif - [5] = { "zero", 0666, &zero_fops, FMODE_NOWAIT }, - [7] = { "full", 0666, &full_fops, 0 }, - [8] = { "random", 0666, &random_fops, FMODE_NOWAIT }, - [9] = { "urandom", 0666, &urandom_fops, FMODE_NOWAIT }, + [5] = { "zero", &zero_fops, FMODE_NOWAIT, 0666 }, + [7] = { "full", &full_fops, 0, 0666 }, + [8] = { "random", &random_fops, FMODE_NOWAIT, 0666 }, + [9] = { "urandom", &urandom_fops, FMODE_NOWAIT, 0666 }, #ifdef CONFIG_PRINTK - [11] = { "kmsg", 0644, &kmsg_fops, 0 }, + [11] = { "kmsg", &kmsg_fops, 0, 0644 }, #endif }; @@ -753,20 +754,23 @@ static char *mem_devnode(const struct device *dev, umode_t *mode) return NULL; } -static struct class *mem_class; +static const struct class mem_class = { + .name = "mem", + .devnode = mem_devnode, +}; static int __init chr_dev_init(void) { + int retval; int minor; if (register_chrdev(MEM_MAJOR, "mem", &memory_fops)) printk("unable to get major %d for memory devs\n", MEM_MAJOR); - mem_class = class_create(THIS_MODULE, "mem"); - if (IS_ERR(mem_class)) - return PTR_ERR(mem_class); + retval = class_register(&mem_class); + if (retval) + return retval; - mem_class->devnode = mem_devnode; for (minor = 1; minor < ARRAY_SIZE(devlist); minor++) { if (!devlist[minor].name) continue; @@ -777,7 +781,7 @@ static int __init chr_dev_init(void) if ((minor == DEVPORT_MINOR) && !arch_has_dev_port()) continue; - device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor), + device_create(&mem_class, NULL, MKDEV(MEM_MAJOR, minor), NULL, devlist[minor].name); } |