diff options
Diffstat (limited to 'drivers/char/mem.c')
| -rw-r--r-- | drivers/char/mem.c | 392 |
1 files changed, 196 insertions, 196 deletions
diff --git a/drivers/char/mem.c b/drivers/char/mem.c index be832b6f827..917403fe10d 100644 --- a/drivers/char/mem.c +++ b/drivers/char/mem.c @@ -3,7 +3,7 @@ * * Copyright (C) 1991, 1992 Linus Torvalds * - * Added devfs support. + * Added devfs support. * Jan-11-1998, C. Scott Ananian <cananian@alumni.princeton.edu> * Shared /dev/zero mmapping support, Feb 2000, Kanoj Sarcar <kanoj@sgi.com> */ @@ -21,19 +21,21 @@ #include <linux/ptrace.h> #include <linux/device.h> #include <linux/highmem.h> -#include <linux/crash_dump.h> #include <linux/backing-dev.h> -#include <linux/bootmem.h> #include <linux/splice.h> #include <linux/pfn.h> +#include <linux/export.h> +#include <linux/io.h> +#include <linux/aio.h> #include <asm/uaccess.h> -#include <asm/io.h> #ifdef CONFIG_IA64 # include <linux/efi.h> #endif +#define DEVPORT_MINOR 4 + static inline unsigned long size_inside_page(unsigned long start, unsigned long size) { @@ -44,43 +46,10 @@ static inline unsigned long size_inside_page(unsigned long start, return min(sz, size); } -/* - * Architectures vary in how they handle caching for addresses - * outside of main memory. - * - */ -static inline int uncached_access(struct file *file, unsigned long 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); -#elif defined(CONFIG_MIPS) - { - extern int __uncached_access(struct file *file, - unsigned long addr); - - return __uncached_access(file, addr); - } -#else - /* - * Accessing memory above the top the kernel knows about or through a file pointer - * that was marked O_DSYNC will be done non-cached. - */ - if (file->f_flags & O_DSYNC) - return 1; - return addr >= __pa(high_memory); -#endif -} - #ifndef ARCH_HAS_VALID_PHYS_ADDR_RANGE -static inline int valid_phys_addr_range(unsigned long addr, size_t count) +static inline int valid_phys_addr_range(phys_addr_t addr, size_t count) { - if (addr + count > __pa(high_memory)) - return 0; - - return 1; + return addr + count <= __pa(high_memory); } static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size) @@ -115,21 +84,24 @@ static inline int range_is_allowed(unsigned long pfn, unsigned long size) } #endif -void __attribute__((weak)) unxlate_dev_mem_ptr(unsigned long phys, void *addr) +void __weak unxlate_dev_mem_ptr(unsigned long phys, void *addr) { } /* - * This funcion reads the *physical* memory. The f_pos points directly to the - * memory location. + * This funcion reads the *physical* memory. The f_pos points directly to the + * memory location. */ -static ssize_t read_mem(struct file * file, char __user * buf, +static ssize_t read_mem(struct file *file, char __user *buf, size_t count, loff_t *ppos) { - unsigned long p = *ppos; + phys_addr_t p = *ppos; ssize_t read, sz; char *ptr; + if (p != *ppos) + return 0; + if (!valid_phys_addr_range(p, count)) return -EFAULT; read = 0; @@ -140,10 +112,10 @@ static ssize_t read_mem(struct file * file, char __user * buf, if (sz > 0) { if (clear_user(buf, sz)) return -EFAULT; - buf += sz; - p += sz; - count -= sz; - read += sz; + buf += sz; + p += sz; + count -= sz; + read += sz; } } #endif @@ -157,9 +129,9 @@ static ssize_t read_mem(struct file * file, char __user * buf, return -EPERM; /* - * On ia64 if a page has been mapped somewhere as - * uncached, then it must also be accessed uncached - * by the kernel or data corruption may occur + * On ia64 if a page has been mapped somewhere as uncached, then + * it must also be accessed uncached by the kernel or data + * corruption may occur. */ ptr = xlate_dev_mem_ptr(p); if (!ptr) @@ -180,14 +152,17 @@ static ssize_t read_mem(struct file * file, char __user * buf, return read; } -static ssize_t write_mem(struct file * file, const char __user * buf, +static ssize_t write_mem(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { - unsigned long p = *ppos; + phys_addr_t p = *ppos; ssize_t written, sz; unsigned long copied; void *ptr; + if (p != *ppos) + return -EFBIG; + if (!valid_phys_addr_range(p, count)) return -EFAULT; @@ -212,9 +187,9 @@ static ssize_t write_mem(struct file * file, const char __user * buf, return -EPERM; /* - * On ia64 if a page has been mapped somewhere as - * uncached, then it must also be accessed uncached - * by the kernel or data corruption may occur + * On ia64 if a page has been mapped somewhere as uncached, then + * it must also be accessed uncached by the kernel or data + * corruption may occur. */ ptr = xlate_dev_mem_ptr(p); if (!ptr) { @@ -242,18 +217,53 @@ static ssize_t write_mem(struct file * file, const char __user * buf, return written; } -int __attribute__((weak)) phys_mem_access_prot_allowed(struct file *file, +int __weak phys_mem_access_prot_allowed(struct file *file, unsigned long pfn, unsigned long size, pgprot_t *vma_prot) { return 1; } #ifndef __HAVE_PHYS_MEM_ACCESS_PROT + +/* + * Architectures vary in how they handle caching for addresses + * outside of main memory. + * + */ +#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); +#elif defined(CONFIG_MIPS) + { + extern int __uncached_access(struct file *file, + unsigned long addr); + + return __uncached_access(file, addr); + } +#else + /* + * Accessing memory above the top the kernel knows about or through a + * file pointer + * that was marked O_DSYNC will be done non-cached. + */ + if (file->f_flags & O_DSYNC) + return 1; + return addr >= __pa(high_memory); +#endif +} +#endif + static pgprot_t phys_mem_access_prot(struct file *file, unsigned long pfn, unsigned long size, pgprot_t vma_prot) { #ifdef pgprot_noncached - unsigned long offset = pfn << PAGE_SHIFT; + phys_addr_t offset = pfn << PAGE_SHIFT; if (uncached_access(file, offset)) return pgprot_noncached(vma_prot); @@ -294,7 +304,7 @@ 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_mem(struct file *file, struct vm_area_struct *vma) { size_t size = vma->vm_end - vma->vm_start; @@ -317,7 +327,7 @@ static int mmap_mem(struct file * file, struct vm_area_struct * vma) vma->vm_ops = &mmap_mem_ops; - /* Remap-pfn-range will mark the range VM_IO and VM_RESERVED */ + /* Remap-pfn-range will mark the range VM_IO */ if (remap_pfn_range(vma, vma->vm_start, vma->vm_pgoff, @@ -329,7 +339,7 @@ static int mmap_mem(struct file * file, struct vm_area_struct * vma) } #ifdef CONFIG_DEVKMEM -static int mmap_kmem(struct file * file, struct vm_area_struct * vma) +static int mmap_kmem(struct file *file, struct vm_area_struct *vma) { unsigned long pfn; @@ -337,9 +347,9 @@ static int mmap_kmem(struct file * file, struct vm_area_struct * vma) pfn = __pa((u64)vma->vm_pgoff << PAGE_SHIFT) >> PAGE_SHIFT; /* - * RED-PEN: on some architectures there is more mapped memory - * than available in mem_map which pfn_valid checks - * for. Perhaps should add a new macro here. + * RED-PEN: on some architectures there is more mapped memory than + * available in mem_map which pfn_valid checks for. Perhaps should add a + * new macro here. * * RED-PEN: vmalloc is not supported right now. */ @@ -351,56 +361,23 @@ static int mmap_kmem(struct file * file, struct vm_area_struct * vma) } #endif -#ifdef CONFIG_CRASH_DUMP -/* - * Read memory corresponding to the old kernel. - */ -static ssize_t read_oldmem(struct file *file, char __user *buf, - size_t count, loff_t *ppos) -{ - unsigned long pfn, offset; - size_t read = 0, csize; - int rc = 0; - - while (count) { - pfn = *ppos / PAGE_SIZE; - if (pfn > saved_max_pfn) - return read; - - offset = (unsigned long)(*ppos % PAGE_SIZE); - if (count > PAGE_SIZE - offset) - csize = PAGE_SIZE - offset; - else - csize = count; - - rc = copy_oldmem_page(pfn, buf, csize, offset, 1); - if (rc < 0) - return rc; - buf += csize; - *ppos += csize; - read += csize; - count -= csize; - } - return read; -} -#endif - #ifdef CONFIG_DEVKMEM /* * This function reads the *virtual* memory as seen by the kernel. */ -static ssize_t read_kmem(struct file *file, char __user *buf, +static ssize_t read_kmem(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long p = *ppos; ssize_t low_count, read, sz; - char * kbuf; /* k-addr because vread() takes vmlist_lock rwlock */ + char *kbuf; /* k-addr because vread() takes vmlist_lock rwlock */ + int err = 0; read = 0; if (p < (unsigned long) high_memory) { low_count = count; - if (count > (unsigned long) high_memory - p) - low_count = (unsigned long) high_memory - p; + if (count > (unsigned long)high_memory - p) + low_count = (unsigned long)high_memory - p; #ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED /* we don't have page 0 mapped on sparc and m68k.. */ @@ -441,12 +418,16 @@ static ssize_t read_kmem(struct file *file, char __user *buf, return -ENOMEM; while (count > 0) { sz = size_inside_page(p, count); + if (!is_vmalloc_or_module_addr((void *)p)) { + err = -ENXIO; + break; + } sz = vread(kbuf, (char *)p, sz); if (!sz) break; if (copy_to_user(buf, kbuf, sz)) { - free_page((unsigned long)kbuf); - return -EFAULT; + err = -EFAULT; + break; } count -= sz; buf += sz; @@ -455,14 +436,13 @@ static ssize_t read_kmem(struct file *file, char __user *buf, } free_page((unsigned long)kbuf); } - *ppos = p; - return read; + *ppos = p; + return read ? read : err; } -static inline ssize_t -do_write_kmem(unsigned long p, const char __user *buf, - size_t count, loff_t *ppos) +static ssize_t do_write_kmem(unsigned long p, const char __user *buf, + size_t count, loff_t *ppos) { ssize_t written, sz; unsigned long copied; @@ -486,9 +466,9 @@ do_write_kmem(unsigned long p, const char __user *buf, sz = size_inside_page(p, count); /* - * On ia64 if a page has been mapped somewhere as - * uncached, then it must also be accessed uncached - * by the kernel or data corruption may occur + * On ia64 if a page has been mapped somewhere as uncached, then + * it must also be accessed uncached by the kernel or data + * corruption may occur. */ ptr = xlate_dev_kmem_ptr((char *)p); @@ -509,17 +489,17 @@ do_write_kmem(unsigned long p, const char __user *buf, return written; } - /* * This function writes to the *virtual* memory as seen by the kernel. */ -static ssize_t write_kmem(struct file * file, const char __user * buf, +static ssize_t write_kmem(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { unsigned long p = *ppos; ssize_t wrote = 0; ssize_t virtr = 0; - char * kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */ + char *kbuf; /* k-addr because vwrite() takes vmlist_lock rwlock */ + int err = 0; if (p < (unsigned long) high_memory) { unsigned long to_write = min_t(unsigned long, count, @@ -540,14 +520,16 @@ static ssize_t write_kmem(struct file * file, const char __user * buf, unsigned long sz = size_inside_page(p, count); unsigned long n; + if (!is_vmalloc_or_module_addr((void *)p)) { + err = -ENXIO; + break; + } n = copy_from_user(kbuf, buf, sz); if (n) { - if (wrote + virtr) - break; - free_page((unsigned long)kbuf); - return -EFAULT; + err = -EFAULT; + break; } - sz = vwrite(kbuf, (char *)p, sz); + vwrite(kbuf, (char *)p, sz); count -= sz; buf += sz; virtr += sz; @@ -556,23 +538,23 @@ static ssize_t write_kmem(struct file * file, const char __user * buf, free_page((unsigned long)kbuf); } - *ppos = p; - return virtr + wrote; + *ppos = p; + return virtr + wrote ? : err; } #endif #ifdef CONFIG_DEVPORT -static ssize_t read_port(struct file * file, char __user * buf, +static ssize_t read_port(struct file *file, char __user *buf, size_t count, loff_t *ppos) { unsigned long i = *ppos; char __user *tmp = buf; if (!access_ok(VERIFY_WRITE, buf, count)) - return -EFAULT; + return -EFAULT; while (count-- > 0 && i < 65536) { - if (__put_user(inb(i),tmp) < 0) - return -EFAULT; + if (__put_user(inb(i), tmp) < 0) + return -EFAULT; i++; tmp++; } @@ -580,22 +562,22 @@ static ssize_t read_port(struct file * file, char __user * buf, return tmp-buf; } -static ssize_t write_port(struct file * file, const char __user * buf, +static ssize_t write_port(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { unsigned long i = *ppos; - const char __user * tmp = buf; + const char __user *tmp = buf; - if (!access_ok(VERIFY_READ,buf,count)) + if (!access_ok(VERIFY_READ, buf, count)) return -EFAULT; while (count-- > 0 && i < 65536) { char c; if (__get_user(c, tmp)) { if (tmp > buf) break; - return -EFAULT; + return -EFAULT; } - outb(c,i); + outb(c, i); i++; tmp++; } @@ -604,31 +586,43 @@ static ssize_t write_port(struct file * file, const char __user * buf, } #endif -static ssize_t read_null(struct file * file, char __user * buf, +static ssize_t read_null(struct file *file, char __user *buf, size_t count, loff_t *ppos) { return 0; } -static ssize_t write_null(struct file * file, const char __user * buf, +static ssize_t write_null(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return count; } +static ssize_t aio_read_null(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + return 0; +} + +static ssize_t aio_write_null(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + return iov_length(iov, nr_segs); +} + static int pipe_to_null(struct pipe_inode_info *info, struct pipe_buffer *buf, struct splice_desc *sd) { return sd->len; } -static ssize_t splice_write_null(struct pipe_inode_info *pipe,struct file *out, +static ssize_t splice_write_null(struct pipe_inode_info *pipe, struct file *out, loff_t *ppos, size_t len, unsigned int flags) { return splice_from_pipe(pipe, out, ppos, len, flags, pipe_to_null); } -static ssize_t read_zero(struct file * file, char __user * buf, +static ssize_t read_zero(struct file *file, char __user *buf, size_t count, loff_t *ppos) { size_t written; @@ -659,7 +653,25 @@ static ssize_t read_zero(struct file * file, char __user * buf, return written ? written : -EFAULT; } -static int mmap_zero(struct file * file, struct vm_area_struct * vma) +static ssize_t aio_read_zero(struct kiocb *iocb, const struct iovec *iov, + unsigned long nr_segs, loff_t pos) +{ + size_t written = 0; + unsigned long i; + ssize_t ret; + + for (i = 0; i < nr_segs; i++) { + ret = read_zero(iocb->ki_filp, iov[i].iov_base, iov[i].iov_len, + &pos); + if (ret < 0) + break; + written += ret; + } + + return written ? written : -EFAULT; +} + +static int mmap_zero(struct file *file, struct vm_area_struct *vma) { #ifndef CONFIG_MMU return -ENOSYS; @@ -669,7 +681,7 @@ static int mmap_zero(struct file * file, struct vm_area_struct * vma) return 0; } -static ssize_t write_full(struct file * file, const char __user * buf, +static ssize_t write_full(struct file *file, const char __user *buf, size_t count, loff_t *ppos) { return -ENOSPC; @@ -680,8 +692,7 @@ static ssize_t write_full(struct file * file, const char __user * buf, * can fopen() both devices with "a" now. This was previously impossible. * -- SRB. */ - -static loff_t null_lseek(struct file * file, loff_t offset, int orig) +static loff_t null_lseek(struct file *file, loff_t offset, int orig) { return file->f_pos = 0; } @@ -694,30 +705,32 @@ static loff_t null_lseek(struct file * file, loff_t offset, int orig) * also note that seeking relative to the "end of file" isn't supported: * it has no meaning, so it returns -EINVAL. */ -static loff_t memory_lseek(struct file * file, loff_t offset, int orig) +static loff_t memory_lseek(struct file *file, loff_t offset, int orig) { loff_t ret; - mutex_lock(&file->f_path.dentry->d_inode->i_mutex); + mutex_lock(&file_inode(file)->i_mutex); switch (orig) { - case 0: - file->f_pos = offset; - ret = file->f_pos; - force_successful_syscall_return(); - break; - case 1: - file->f_pos += offset; - ret = file->f_pos; - force_successful_syscall_return(); + case SEEK_CUR: + offset += file->f_pos; + case SEEK_SET: + /* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */ + if (IS_ERR_VALUE((unsigned long long)offset)) { + ret = -EOVERFLOW; break; - default: - ret = -EINVAL; + } + file->f_pos = offset; + ret = file->f_pos; + force_successful_syscall_return(); + break; + default: + ret = -EINVAL; } - mutex_unlock(&file->f_path.dentry->d_inode->i_mutex); + mutex_unlock(&file_inode(file)->i_mutex); return ret; } -static int open_port(struct inode * inode, struct file * filp) +static int open_port(struct inode *inode, struct file *filp) { return capable(CAP_SYS_RAWIO) ? 0 : -EPERM; } @@ -726,9 +739,9 @@ static int open_port(struct inode * inode, struct file * filp) #define full_lseek null_lseek #define write_zero write_null #define read_full read_zero +#define aio_write_zero aio_write_null #define open_mem open_port #define open_kmem open_mem -#define open_oldmem open_mem static const struct file_operations mem_fops = { .llseek = memory_lseek, @@ -754,6 +767,8 @@ static const struct file_operations null_fops = { .llseek = null_lseek, .read = read_null, .write = write_null, + .aio_read = aio_read_null, + .aio_write = aio_write_null, .splice_write = splice_write_null, }; @@ -770,16 +785,19 @@ static const struct file_operations zero_fops = { .llseek = zero_lseek, .read = read_zero, .write = write_zero, + .aio_read = aio_read_zero, + .aio_write = aio_write_zero, .mmap = mmap_zero, }; /* * capabilities for /dev/zero * - permits private mappings, "copies" are taken of the source of zeros + * - no writeback happens */ static struct backing_dev_info zero_bdi = { .name = "char/mem", - .capabilities = BDI_CAP_MAP_COPY, + .capabilities = BDI_CAP_MAP_COPY | BDI_CAP_NO_ACCT_AND_WRITEBACK, }; static const struct file_operations full_fops = { @@ -788,41 +806,9 @@ static const struct file_operations full_fops = { .write = write_full, }; -#ifdef CONFIG_CRASH_DUMP -static const struct file_operations oldmem_fops = { - .read = read_oldmem, - .open = open_oldmem, -}; -#endif - -static ssize_t kmsg_write(struct file * file, const char __user * buf, - size_t count, loff_t *ppos) -{ - char *tmp; - ssize_t ret; - - tmp = kmalloc(count + 1, GFP_KERNEL); - if (tmp == NULL) - return -ENOMEM; - ret = -EFAULT; - if (!copy_from_user(tmp, buf, count)) { - tmp[count] = 0; - ret = printk("%s", tmp); - if (ret > count) - /* printk can add a prefix */ - ret = count; - } - kfree(tmp); - return ret; -} - -static const struct file_operations kmsg_fops = { - .write = kmsg_write, -}; - static const struct memdev { const char *name; - mode_t mode; + umode_t mode; const struct file_operations *fops; struct backing_dev_info *dev_info; } devlist[] = { @@ -838,9 +824,8 @@ static const struct memdev { [7] = { "full", 0666, &full_fops, NULL }, [8] = { "random", 0666, &random_fops, NULL }, [9] = { "urandom", 0666, &urandom_fops, NULL }, - [11] = { "kmsg", 0, &kmsg_fops, NULL }, -#ifdef CONFIG_CRASH_DUMP - [12] = { "oldmem", 0, &oldmem_fops, NULL }, +#ifdef CONFIG_PRINTK + [11] = { "kmsg", 0644, &kmsg_fops, NULL }, #endif }; @@ -861,6 +846,10 @@ static int memory_open(struct inode *inode, struct file *filp) if (dev->dev_info) filp->f_mapping->backing_dev_info = dev->dev_info; + /* Is /dev/mem or /dev/kmem ? */ + if (dev->dev_info == &directly_mappable_cdev_bdi) + filp->f_mode |= FMODE_UNSIGNED_OFFSET; + if (dev->fops->open) return dev->fops->open(inode, filp); @@ -868,10 +857,11 @@ static int memory_open(struct inode *inode, struct file *filp) } static const struct file_operations memory_fops = { - .open = memory_open, + .open = memory_open, + .llseek = noop_llseek, }; -static char *mem_devnode(struct device *dev, mode_t *mode) +static char *mem_devnode(struct device *dev, umode_t *mode) { if (mode && devlist[MINOR(dev->devt)].mode) *mode = devlist[MINOR(dev->devt)].mode; @@ -889,19 +879,29 @@ static int __init chr_dev_init(void) if (err) return err; - if (register_chrdev(MEM_MAJOR,"mem",&memory_fops)) + 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); + mem_class->devnode = mem_devnode; for (minor = 1; minor < ARRAY_SIZE(devlist); minor++) { if (!devlist[minor].name) continue; + + /* + * Create /dev/port? + */ + if ((minor == DEVPORT_MINOR) && !arch_has_dev_port()) + continue; + device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor), NULL, devlist[minor].name); } - return 0; + return tty_init(); } fs_initcall(chr_dev_init); |
