How to Write Kernel Space Memory (Physical Address) to a File Using O_Direct

How to access physical addresses from user space in Linux?

You can map a device file to a user process memory using mmap(2) system call. Usually, device files are mappings of physical memory to the file system.
Otherwise, you have to write a kernel module which creates such a file or provides a way to map the needed memory to a user process.

Another way is remapping parts of /dev/mem to a user memory.

Edit:
Example of mmaping /dev/mem (this program must have access to /dev/mem, e.g. have root rights):

#include <stdio.h>
#include <stdlib.h>
#include <fcntl.h>
#include <sys/mman.h>
#include <unistd.h>

int main(int argc, char *argv[]) {
    if (argc < 3) {
        printf("Usage: %s <phys_addr> <offset>\n", argv[0]);
        return 0;
    }

    off_t offset = strtoul(argv[1], NULL, 0);
    size_t len = strtoul(argv[2], NULL, 0);

    // Truncate offset to a multiple of the page size, or mmap will fail.
    size_t pagesize = sysconf(_SC_PAGE_SIZE);
    off_t page_base = (offset / pagesize) * pagesize;
    off_t page_offset = offset - page_base;

    int fd = open("/dev/mem", O_SYNC);
    unsigned char *mem = mmap(NULL, page_offset + len, PROT_READ | PROT_WRITE, MAP_PRIVATE, fd, page_base);
    if (mem == MAP_FAILED) {
        perror("Can't map memory");
        return -1;
    }

    size_t i;
    for (i = 0; i < len; ++i)
        printf("%02x ", (int)mem[page_offset + i]);

    return 0;
}

using O_DIRECT with IO memory

I think, that it all happens because of VM_PFNMAP flag ( http://elixir.free-electrons.com/linux/v4.11.7/source/include/linux/mm.h#L174 )

When you use io_remap_pfn_range, it sets VM_PFNMAP flag ( http://elixir.free-electrons.com/linux/v4.11.7/source/mm/memory.c#L1914 ), that tells "those pages aren't regular pages with usual struct page" ( see comment in the code above )

And __get_user_pages checks this flag and returns error ( http://elixir.free-electrons.com/linux/v4.11.7/source/mm/nommu.c#L136 )

P.S. There is VM_IO flag too in both io_remap_pfn_range and __get_user_pages, so there won't be any I/O on kernel pages, mapped to user-space, or anyone will rewrite kernel memory

Related Topics