linux下的/dev/mem设备认识和使用

最近在为了读取一个寄存器的值动心思时,突然发现,一个好用的工具”r”,源码附上:

#include <fcntl.h>
#include <inttypes.h>
#include <stdbool.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/mman.h>

#if __LP64__
#define strtoptr strtoull
#else
#define strtoptr strtoul
#endif

static int usage()
{
    fprintf(stderr,"r [-b|-s] <address> [<value>]\n");
    return -1;
}

int r_main(int argc, char *argv[])
{
    if(argc < 2) return usage();

    int width = 4;
    if(!strcmp(argv[1], "-b")) {
        width = 1;
        argc--;
        argv++;
    } else if(!strcmp(argv[1], "-s")) {
        width = 2;
        argc--;
        argv++;
    }

    if(argc < 2) return usage();
    uintptr_t addr = strtoptr(argv[1], 0, 16);

    uintptr_t endaddr = 0;
    char* end = strchr(argv[1], '-');
    if (end)
        endaddr = strtoptr(end + 1, 0, 16);

    if (!endaddr)
        endaddr = addr + width - 1;

    if (endaddr <= addr) {
        fprintf(stderr, "end address <= start address\n");
        return -1;
    }

    bool set = false;
    uint32_t value = 0;
    if(argc > 2) {
        set = true;
        value = strtoul(argv[2], 0, 16);
    }

    int fd = open("/dev/mem", O_RDWR | O_SYNC);
    if(fd < 0) {
        fprintf(stderr,"cannot open /dev/mem\n");
        return -1;
    }

    off64_t mmap_start = addr & ~(PAGE_SIZE - 1);
    size_t mmap_size = endaddr - mmap_start + 1;
    mmap_size = (mmap_size + PAGE_SIZE - 1) & ~(PAGE_SIZE - 1);

    void* page = mmap64(0, mmap_size, PROT_READ | PROT_WRITE,
                        MAP_SHARED, fd, mmap_start);

    if(page == MAP_FAILED){
        fprintf(stderr,"cannot mmap region\n");
        return -1;
    }

    while (addr <= endaddr) {
        switch(width){
        case 4: {
            uint32_t* x = (uint32_t*) (((uintptr_t) page) + (addr & 4095));
            if(set) *x = value;
            fprintf(stderr,"%08"PRIxPTR": %08x\n", addr, *x);
            break;
        }
        case 2: {
            uint16_t* x = (uint16_t*) (((uintptr_t) page) + (addr & 4095));
            if(set) *x = value;
            fprintf(stderr,"%08"PRIxPTR": %04x\n", addr, *x);
            break;
        }
        case 1: {
            uint8_t* x = (uint8_t*) (((uintptr_t) page) + (addr & 4095));
            if(set) *x = value;
            fprintf(stderr,"%08"PRIxPTR": %02x\n", addr, *x);
            break;
        }
        }
        addr += width;
    }
    return 0;
}

简单好用不是!
秉承研究一下的思想,看了一下/dev/mem和mmap读写linux内存的通用C代码及原理。
附上一个mem这个字符驱动的源码:

/*
 *  linux/drivers/char/mem.c
 *
 *  Copyright (C) 1991, 1992  Linus Torvalds
 *
 *  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>
 */

#include <linux/mm.h>
#include <linux/miscdevice.h>
#include <linux/slab.h>
#include <linux/vmalloc.h>
#include <linux/mman.h>
#include <linux/random.h>
#include <linux/init.h>
#include <linux/raw.h>
#include <linux/tty.h>
#include <linux/capability.h>
#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 <asm/uaccess.h>
#include <asm/io.h>

#ifdef CONFIG_IA64
# include <linux/efi.h>
#endif

static inline unsigned long size_inside_page(unsigned long start,
                         unsigned long size)
{
    unsigned long sz;

    sz = PAGE_SIZE - (start & (PAGE_SIZE - 1));

    return min(sz, size);
}

#ifndef ARCH_HAS_VALID_PHYS_ADDR_RANGE
static inline int valid_phys_addr_range(unsigned long addr, size_t count)
{
    return addr + count <= __pa(high_memory);
}

static inline int valid_mmap_phys_addr_range(unsigned long pfn, size_t size)
{
    return 1;
}
#endif

#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM)
#ifdef CONFIG_STRICT_DEVMEM
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)) {
            printk(KERN_INFO
        "Program %s tried to access /dev/mem between %Lx->%Lx.\n",
                current->comm, from, to);
            return 0;
        }
        cursor += PAGE_SIZE;
        pfn++;
    }
    return 1;
}
#else
static inline int range_is_allowed(unsigned long pfn, unsigned long size)
{
    return 1;
}
#endif
#endif

#ifdef CONFIG_DEVMEM
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.
 */
static ssize_t read_mem(struct file *file, char __user *buf,
            size_t count, loff_t *ppos)
{
    unsigned long p = *ppos;
    ssize_t read, sz;
    char *ptr;

    if (!valid_phys_addr_range(p, count))
        return -EFAULT;
    read = 0;
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
    /* we don't have page 0 mapped on sparc and m68k.. */
    if (p < PAGE_SIZE) {
        sz = size_inside_page(p, count);
        if (sz > 0) {
            if (clear_user(buf, sz))
                return -EFAULT;
            buf += sz;
            p += sz;
            count -= sz;
            read += sz;
        }
    }
#endif

    while (count > 0) {
        unsigned long remaining;

        sz = size_inside_page(p, count);

        if (!range_is_allowed(p >> PAGE_SHIFT, count))
            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.
         */
        ptr = xlate_dev_mem_ptr(p);
        if (!ptr)
            return -EFAULT;

        remaining = copy_to_user(buf, ptr, sz);
        unxlate_dev_mem_ptr(p, ptr);
        if (remaining)
            return -EFAULT;

        buf += sz;
        p += sz;
        count -= sz;
        read += sz;
    }

    *ppos += read;
    return read;
}

static ssize_t write_mem(struct file *file, const char __user *buf,
             size_t count, loff_t *ppos)
{
    unsigned long p = *ppos;
    ssize_t written, sz;
    unsigned long copied;
    void *ptr;

    if (!valid_phys_addr_range(p, count))
        return -EFAULT;

    written = 0;

#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
    /* we don't have page 0 mapped on sparc and m68k.. */
    if (p < PAGE_SIZE) {
        sz = size_inside_page(p, count);
        /* Hmm. Do something? */
        buf += sz;
        p += sz;
        count -= sz;
        written += sz;
    }
#endif

    while (count > 0) {
        sz = size_inside_page(p, count);

        if (!range_is_allowed(p >> PAGE_SHIFT, sz))
            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.
         */
        ptr = xlate_dev_mem_ptr(p);
        if (!ptr) {
            if (written)
                break;
            return -EFAULT;
        }

        copied = copy_from_user(ptr, buf, sz);
        unxlate_dev_mem_ptr(p, ptr);
        if (copied) {
            written += sz - copied;
            if (written)
                break;
            return -EFAULT;
        }

        buf += sz;
        p += sz;
        count -= sz;
        written += sz;
    }

    *ppos += written;
    return written;
}
#endif  /* CONFIG_DEVMEM */

#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM)

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, 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
}
#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;

    if (uncached_access(file, offset))
        return pgprot_noncached(vma_prot);
#endif
    return vma_prot;
}
#endif

#ifndef CONFIG_MMU
static unsigned long get_unmapped_area_mem(struct file *file,
                       unsigned long addr,
                       unsigned long len,
                       unsigned long pgoff,
                       unsigned long flags)
{
    if (!valid_mmap_phys_addr_range(pgoff, len))
        return (unsigned long) -EINVAL;
    return pgoff << PAGE_SHIFT;
}

/* can't do an in-place private mapping if there's no MMU */
static inline int private_mapping_ok(struct vm_area_struct *vma)
{
    return vma->vm_flags & VM_MAYSHARE;
}
#else
#define get_unmapped_area_mem   NULL

static inline int private_mapping_ok(struct vm_area_struct *vma)
{
    return 1;
}
#endif

static const struct vm_operations_struct mmap_mem_ops = {
#ifdef CONFIG_HAVE_IOREMAP_PROT
    .access = generic_access_phys
#endif
};

static int mmap_mem(struct file *file, struct vm_area_struct *vma)
{
    size_t size = vma->vm_end - vma->vm_start;

    if (!valid_mmap_phys_addr_range(vma->vm_pgoff, size))
        return -EINVAL;

    if (!private_mapping_ok(vma))
        return -ENOSYS;

    if (!range_is_allowed(vma->vm_pgoff, size))
        return -EPERM;

    if (!phys_mem_access_prot_allowed(file, vma->vm_pgoff, size,
                        &vma->vm_page_prot))
        return -EINVAL;

    vma->vm_page_prot = phys_mem_access_prot(file, vma->vm_pgoff,
                         size,
                         vma->vm_page_prot);

    vma->vm_ops = &mmap_mem_ops;

    /* Remap-pfn-range will mark the range VM_IO and VM_RESERVED */
    if (remap_pfn_range(vma,
                vma->vm_start,
                vma->vm_pgoff,
                size,
                vma->vm_page_prot)) {
        return -EAGAIN;
    }
    return 0;
}
#endif  /* CONFIG_DEVMEM */

#ifdef CONFIG_DEVKMEM
static int mmap_kmem(struct file *file, struct vm_area_struct *vma)
{
    unsigned long pfn;

    /* Turn a kernel-virtual address into a physical page frame */
    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: vmalloc is not supported right now.
     */
    if (!pfn_valid(pfn))
        return -EIO;

    vma->vm_pgoff = pfn;
    return mmap_mem(file, 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,
             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 */
    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;

#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
        /* we don't have page 0 mapped on sparc and m68k.. */
        if (p < PAGE_SIZE && low_count > 0) {
            sz = size_inside_page(p, low_count);
            if (clear_user(buf, sz))
                return -EFAULT;
            buf += sz;
            p += sz;
            read += sz;
            low_count -= sz;
            count -= sz;
        }
#endif
        while (low_count > 0) {
            sz = size_inside_page(p, low_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
             */
            kbuf = xlate_dev_kmem_ptr((char *)p);

            if (copy_to_user(buf, kbuf, sz))
                return -EFAULT;
            buf += sz;
            p += sz;
            read += sz;
            low_count -= sz;
            count -= sz;
        }
    }

    if (count > 0) {
        kbuf = (char *)__get_free_page(GFP_KERNEL);
        if (!kbuf)
            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)) {
                err = -EFAULT;
                break;
            }
            count -= sz;
            buf += sz;
            read += sz;
            p += sz;
        }
        free_page((unsigned long)kbuf);
    }
    *ppos = p;
    return read ? read : err;
}


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;

    written = 0;
#ifdef __ARCH_HAS_NO_PAGE_ZERO_MAPPED
    /* we don't have page 0 mapped on sparc and m68k.. */
    if (p < PAGE_SIZE) {
        sz = size_inside_page(p, count);
        /* Hmm. Do something? */
        buf += sz;
        p += sz;
        count -= sz;
        written += sz;
    }
#endif

    while (count > 0) {
        char *ptr;

        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.
         */
        ptr = xlate_dev_kmem_ptr((char *)p);

        copied = copy_from_user(ptr, buf, sz);
        if (copied) {
            written += sz - copied;
            if (written)
                break;
            return -EFAULT;
        }
        buf += sz;
        p += sz;
        count -= sz;
        written += sz;
    }

    *ppos += written;
    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,
              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 */
    int err = 0;

    if (p < (unsigned long) high_memory) {
        unsigned long to_write = min_t(unsigned long, count,
                           (unsigned long)high_memory - p);
        wrote = do_write_kmem(p, buf, to_write, ppos);
        if (wrote != to_write)
            return wrote;
        p += wrote;
        buf += wrote;
        count -= wrote;
    }

    if (count > 0) {
        kbuf = (char *)__get_free_page(GFP_KERNEL);
        if (!kbuf)
            return wrote ? wrote : -ENOMEM;
        while (count > 0) {
            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) {
                err = -EFAULT;
                break;
            }
            vwrite(kbuf, (char *)p, sz);
            count -= sz;
            buf += sz;
            virtr += sz;
            p += sz;
        }
        free_page((unsigned long)kbuf);
    }

    *ppos = p;
    return virtr + wrote ? : err;
}
#endif

#ifdef CONFIG_DEVPORT
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;
    while (count-- > 0 && i < 65536) {
        if (__put_user(inb(i), tmp) < 0)
            return -EFAULT;
        i++;
        tmp++;
    }
    *ppos = i;
    return tmp-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;

    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;
        }
        outb(c, i);
        i++;
        tmp++;
    }
    *ppos = i;
    return tmp-buf;
}
#endif

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,
              size_t count, loff_t *ppos)
{
    return count;
}

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,
                 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,
             size_t count, loff_t *ppos)
{
    size_t written;

    if (!count)
        return 0;

    if (!access_ok(VERIFY_WRITE, buf, count))
        return -EFAULT;

    written = 0;
    while (count) {
        unsigned long unwritten;
        size_t chunk = count;

        if (chunk > PAGE_SIZE)
            chunk = PAGE_SIZE;  /* Just for latency reasons */
        unwritten = __clear_user(buf, chunk);
        written += chunk - unwritten;
        if (unwritten)
            break;
        if (signal_pending(current))
            return written ? written : -ERESTARTSYS;
        buf += chunk;
        count -= chunk;
        cond_resched();
    }
    return written ? written : -EFAULT;
}

static int mmap_zero(struct file *file, struct vm_area_struct *vma)
{
#ifndef CONFIG_MMU
    return -ENOSYS;
#endif
    if (vma->vm_flags & VM_SHARED)
        return shmem_zero_setup(vma);
    return 0;
}

static ssize_t write_full(struct file *file, const char __user *buf,
              size_t count, loff_t *ppos)
{
    return -ENOSPC;
}

/*
 * Special lseek() function for /dev/null and /dev/zero.  Most notably, you
 * 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)
{
    return file->f_pos = 0;
}

#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM) || defined(CONFIG_DEVPORT)

/*
 * The memory devices use the full 32/64 bits of the offset, and so we cannot
 * check against negative addresses: they are ok. The return value is weird,
 * though, in that case (0).
 *
 * 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)
{
    loff_t ret;

    mutex_lock(&file->f_path.dentry->d_inode->i_mutex);
    switch (orig) {
    case SEEK_CUR:
        offset += file->f_pos;
    case SEEK_SET:
        /* to avoid userland mistaking f_pos=-9 as -EBADF=-9 */
        if ((unsigned long long)offset >= ~0xFFFULL) {
            ret = -EOVERFLOW;
            break;
        }
        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);
    return ret;
}

#endif

#if defined(CONFIG_DEVMEM) || defined(CONFIG_DEVKMEM) || defined(CONFIG_DEVPORT)
static int open_port(struct inode * inode, struct file * filp)
{
    return capable(CAP_SYS_RAWIO) ? 0 : -EPERM;
}
#endif

#define zero_lseek  null_lseek
#define full_lseek      null_lseek
#define write_zero  write_null
#define read_full       read_zero
#define open_mem    open_port
#define open_kmem   open_mem
#define open_oldmem open_mem

#ifdef CONFIG_DEVMEM
static const struct file_operations mem_fops = {
    .llseek     = memory_lseek,
    .read       = read_mem,
    .write      = write_mem,
    .mmap       = mmap_mem,
    .open       = open_mem,
    .get_unmapped_area = get_unmapped_area_mem,
};
#endif

#ifdef CONFIG_DEVKMEM
static const struct file_operations kmem_fops = {
    .llseek     = memory_lseek,
    .read       = read_kmem,
    .write      = write_kmem,
    .mmap       = mmap_kmem,
    .open       = open_kmem,
    .get_unmapped_area = get_unmapped_area_mem,
};
#endif

static const struct file_operations null_fops = {
    .llseek     = null_lseek,
    .read       = read_null,
    .write      = write_null,
    .splice_write   = splice_write_null,
};

#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,
    .read       = read_zero,
    .write      = 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 | BDI_CAP_NO_ACCT_AND_WRITEBACK,
};

static const struct file_operations full_fops = {
    .llseek     = full_lseek,
    .read       = read_full,
    .write      = write_full,
};

#ifdef CONFIG_CRASH_DUMP
static const struct file_operations oldmem_fops = {
    .read   = read_oldmem,
    .open   = open_oldmem,
    .llseek = default_llseek,
};
#endif

static ssize_t kmsg_writev(struct kiocb *iocb, const struct iovec *iv,
               unsigned long count, loff_t pos)
{
    char *line, *p;
    int i;
    ssize_t ret = -EFAULT;
    size_t len = iov_length(iv, count);

    line = kmalloc(len + 1, GFP_KERNEL);
    if (line == NULL)
        return -ENOMEM;

    /*
     * copy all vectors into a single string, to ensure we do
     * not interleave our log line with other printk calls
     */
    p = line;
    for (i = 0; i < count; i++) {
        if (copy_from_user(p, iv[i].iov_base, iv[i].iov_len))
            goto out;
        p += iv[i].iov_len;
    }
    p[0] = '\0';

    ret = printk("%s", line);
    /* printk can add a prefix */
    if (ret > len)
        ret = len;
out:
    kfree(line);
    return ret;
}

static const struct file_operations kmsg_fops = {
    .aio_write = kmsg_writev,
    .llseek = noop_llseek,
};

static const struct memdev {
    const char *name;
    umode_t mode;
    const struct file_operations *fops;
    struct backing_dev_info *dev_info;
} devlist[] = {
#ifdef CONFIG_DEVMEM
     [1] = { "mem", 0, &mem_fops, &directly_mappable_cdev_bdi },
#endif
#ifdef CONFIG_DEVKMEM
     [2] = { "kmem", 0, &kmem_fops, &directly_mappable_cdev_bdi },
#endif
     [3] = { "null", 0666, &null_fops, NULL },
#ifdef CONFIG_DEVPORT
     [4] = { "port", 0, &port_fops, NULL },
#endif
     [5] = { "zero", 0666, &zero_fops, &zero_bdi },
     [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 },
#endif
};

static int memory_open(struct inode *inode, struct file *filp)
{
    int minor;
    const struct memdev *dev;

    minor = iminor(inode);
    if (minor >= ARRAY_SIZE(devlist))
        return -ENXIO;

    dev = &devlist[minor];
    if (!dev->fops)
        return -ENXIO;

    filp->f_op = dev->fops;
    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);

    return 0;
}

static const struct file_operations memory_fops = {
    .open = memory_open,
    .llseek = noop_llseek,
};

static char *mem_devnode(struct device *dev, umode_t *mode)
{
    if (mode && devlist[MINOR(dev->devt)].mode)
        *mode = devlist[MINOR(dev->devt)].mode;
    return NULL;
}

static struct class *mem_class;

static int __init chr_dev_init(void)
{
    int minor;
    int err;

    err = bdi_init(&zero_bdi);
    if (err)
        return err;

    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;
        device_create(mem_class, NULL, MKDEV(MEM_MAJOR, minor),
                  NULL, devlist[minor].name);
    }

    return tty_init();
}

fs_initcall(chr_dev_init);

利用/dev/mem和mmap导出系统物理地址,免去了用户虚拟地址到内核逻辑地址的繁琐拷贝,提升效率。
注意:如果地址不是一个有效物理地址(处理器地址空间分布中该地址没用),mmap建立该物理地址与用户空间虚拟地址的映射,填TLB,CPU经过TLB翻译后去访问该不存在的物理地址访问就有可能导致CPU挂掉。
内核中定义了4个变量来表示内核一些基本的物理地址和虚拟地址,如下:
KERNELBASE 内核的起始虚拟地址,
PAGE_OFFSET 低端内存的起始虚拟地址,一般是0xc0000000
PHYSICAL_START 内核的起始物理地址,
MEMORY_START 低端内存的起始物理地址,

内核在启动过程中对于lowmem的静态映射,就是以上述的物理地址和虚拟地址的差值进行线性映射的。
所以__pa __va转换的是线性映射的内存部分,也就是lowmem。
所以kmem映射的是lowmem,如果cmdline参数中mem=512M,这就意味着通过kmem的mmap最多可以访问内核地址空间开始的512M内存。
对于超过lowmem范围,访问highmem,如果使用__pa访问,由于highmem是动态映射的,其映射关系不是线性的那么简单了,根据__pa获取的物理地址与我们想要的内核虚拟地址是不对应的。
一个简单GPIO的应用层驱动:

int main(int argc, char *argv[])
{
    int mfd;
    unsigned int val=0, last_val;
    void *base;
    char *sys_pinstaterd;
    time_t t_now, t_old;
    int flag_issued = 0;
#if 0
    // uncomment these to make the program a daemon.

    pid_t pid;
        int i;
        if ( (pid=fork())<0)
                return -1;
        else if (pid!=0)
                exit(0);
        setsid();
        chdir("/");
        umask(0);
        for (i=0;i<256;i++)
                close(i);
#endif

    // open the memery mapped file.
    mfd=open("/dev/mem", O_RDWR);
    if (mfd < 0){
        printf("Cannot open /dev/mem.\n");
        exit(-1);
    }

    // Initialize the map
    base = mmap( NULL, 0x130,  PROT_READ | PROT_WRITE, MAP_SHARED, mfd, 0x1fe00000);
    if ( base < 0){
        exit(-1);
    }
    sys_pinstaterd = base + 0x011c;
    // init the temperay variables
    t_now=t_old=time(NULL);
    last_val = 0;
    while(1)
    {
        val = *( (volatile unsigned int*)sys_pinstaterd );
        val = (val&0x4) ? 1:0;
        printf("\tgpio 7 stat=%x.\n", val);
        if (val){
            // the button is pressed down !!
            if ( last_val==0 ){
                // starting time of press, log the time
                t_old = time(NULL);
                last_val=1;
                printf("Button Down\n");
            }else {
                // already pressed down! let's count the time!
                t_now = time(NULL);
                if (t_now-t_old>=TIME_OUT && flag_issued==0){
                    // Pressed LONG ENOUGH, issue the handler script!!
                    flag_issued = 1;
                    longtu_timeout();
                }
            }
        }else{
            // No button pressed.
            if (flag_issued){
                flag_issued = 0;
                printf("Button UP.\n");
            }
        }

        last_val = val;
        usleep(100);
    }

    munmap(base, 0x000);
    close(mfd);   
    return 0;
}

写在应用层的物理地址操作。快速开发的一个方法。

没有更多推荐了,返回首页