linux32.c

该文件是rt_linux

/*
 * Conversion between 32-bit and 64-bit native system calls.
 *
 * Copyright (C) 2000 Silicon Graphics, Inc.
 * Written by Ulf Carlsson ([e-mail])
 * sys32_execve from ia64/ia32 code, Feb 2000, Kanoj Sarcar ([e-mail])
 */
#include <linux/config.h>
#include <linux/mm.h>
#include <linux/errno.h>
#include <linux/file.h>
#include <linux/smp_lock.h>
#include <linux/highuid.h>
#include <linux/dirent.h>
#include <linux/resource.h>
#include <linux/filter.h>
#include <linux/highmem.h>
#include <linux/time.h>
#include <linux/poll.h>
#include <linux/slab.h>
#include <linux/skbuff.h>
#include <linux/filter.h>
#include <linux/shm.h>
#include <linux/sem.h>
#include <linux/msg.h>
#include <linux/icmpv6.h>
#include <linux/sysctl.h>
#include <linux/utime.h>
#include <linux/utsname.h>
#include <linux/personality.h>
#include <linux/timex.h>
#include <linux/dnotify.h>
#include <linux/module.h>
#include <net/sock.h>

#include <asm/uaccess.h>
#include <asm/mman.h>
#include <asm/ipc.h>

/* Use this to get at 32-bit user passed pointers. */
/* A() macro should be used for places where you e.g.
   have some internal variable u32 and just want to get
   rid of a compiler warning. AA() has to be used in
   places where you want to convert a function argument
   to 32bit pointer or when you e.g. access pt_regs
   structure and want to consider 32bit registers only.
 */
#define A(__x) ((unsigned long)(__x))
#define AA(__x) ((unsigned long)((int)__x))

#ifdef __MIPSEB__
#define merge_64(r1,r2)	((((r1) & 0xffffffffUL) << 32) + ((r2) & 0xffffffffUL))
#endif
#ifdef __MIPSEL__
#define merge_64(r1,r2)	((((r2) & 0xffffffffUL) << 32) + ((r1) & 0xffffffffUL))
#endif

/*
 * Revalidate the inode. This is required for proper NFS attribute caching.
 */
static __inline__ int
do_revalidate(struct dentry *dentry)
{
	struct inode * inode = dentry->d_inode;

	if (inode->i_op && inode->i_op->revalidate)
		return inode->i_op->revalidate(dentry);

	return 0;
}

static int cp_new_stat32(struct inode * inode, struct stat32 * statbuf)
{
	struct stat32 tmp;
	unsigned int blocks, indirect;

	memset(&tmp, 0, sizeof(tmp));
	tmp.st_dev = kdev_t_to_nr(inode->i_dev);
	tmp.st_ino = inode->i_ino;
	tmp.st_mode = inode->i_mode;
	tmp.st_nlink = inode->i_nlink;
	SET_STAT_UID(tmp, inode->i_uid);
	SET_STAT_GID(tmp, inode->i_gid);
	tmp.st_rdev = kdev_t_to_nr(inode->i_rdev);
	tmp.st_size = inode->i_size;
	tmp.st_atime = inode->i_atime;
	tmp.st_mtime = inode->i_mtime;
	tmp.st_ctime = inode->i_ctime;

	/*
	 * st_blocks and st_blksize are approximated with a simple algorithm if
	 * they aren't supported directly by the filesystem. The minix and msdos
	 * filesystems don't keep track of blocks, so they would either have to
	 * be counted explicitly (by delving into the file itself), or by using
	 * this simple algorithm to get a reasonable (although not 100%
	 * accurate) value.
	 */

	/*
	 * Use minix fs values for the number of direct and indirect blocks.
	 * The count is now exact for the minix fs except that it counts zero
	 * blocks.  Everything is in units of BLOCK_SIZE until the assignment
	 * to tmp.st_blksize.
	 */
#define D_B   7
#define I_B   (BLOCK_SIZE / sizeof(unsigned short))

	if (!inode->i_blksize) {
		blocks = (tmp.st_size + BLOCK_SIZE - 1) / BLOCK_SIZE;
		if (blocks > D_B) {
			indirect = (blocks - D_B + I_B - 1) / I_B;
			blocks += indirect;
			if (indirect > 1) {
				indirect = (indirect - 1 + I_B - 1) / I_B;
				blocks += indirect;
				if (indirect > 1)
					blocks++;
			}
		}
		tmp.st_blocks = (BLOCK_SIZE / 512) * blocks;
		tmp.st_blksize = BLOCK_SIZE;
	} else {
		tmp.st_blocks = inode->i_blocks;
		tmp.st_blksize = inode->i_blksize;
	}

	return copy_to_user(statbuf,&tmp,sizeof(tmp)) ? -EFAULT : 0;
}

asmlinkage int sys32_newstat(char * filename, struct stat32 *statbuf)
{
	struct nameidata nd;
	int error;

	error = user_path_walk(filename, &nd);
	if (!error) {
		error = do_revalidate(nd.dentry);
		if (!error)
			error = cp_new_stat32(nd.dentry->d_inode, statbuf);

		path_release(&nd);
	}

	return error;
}

asmlinkage int sys32_newlstat(char * filename, struct stat32 *statbuf)
{
	struct nameidata nd;
	int error;

	error = user_path_walk_link(filename, &nd);
	if (!error) {
		error = do_revalidate(nd.dentry);
		if (!error)
			error = cp_new_stat32(nd.dentry->d_inode, statbuf);

		path_release(&nd);
	}

	return error;
}

asmlinkage long sys32_newfstat(unsigned int fd, struct stat32 * statbuf)
{
	struct file * f;
	int err = -EBADF;

	f = fget(fd);
	if (f) {
		struct dentry * dentry = f->f_dentry;

		err = do_revalidate(dentry);
		if (!err)
			err = cp_new_stat32(dentry->d_inode, statbuf);
		fput(f);
	}

	return err;
}

asmlinkage int sys_mmap2(void) {return 0;}

asmlinkage long sys_truncate(const char * path, unsigned long length);

asmlinkage int sys_truncate64(const char *path, unsigned int high,
			      unsigned int low)
{
	if ((int)high < 0)
		return -EINVAL;
	return sys_truncate(path, ((long) high << 32) | low);
}

asmlinkage long sys_ftruncate(unsigned int fd, unsigned long length);

asmlinkage int sys_ftruncate64(unsigned int fd, unsigned int high,
			       unsigned int low)
{
	if ((int)high < 0)
		return -EINVAL;
	return sys_ftruncate(fd, ((long) high << 32) | low);
}

extern asmlinkage int sys_utime(char * filename, struct utimbuf * times);

struct utimbuf32 {
	__kernel_time_t32 actime, modtime;
};

asmlinkage int sys32_utime(char * filename, struct utimbuf32 *times)
{
	struct utimbuf t;
	mm_segment_t old_fs;
	int ret;
	char *filenam;

	if (!times)
		return sys_utime(filename, NULL);
	if (get_user (t.actime, &times->actime) ||
	    __get_user (t.modtime, &times->modtime))
		return -EFAULT;
	filenam = getname (filename);
	ret = PTR_ERR(filenam);
	if (!IS_ERR(filenam)) {
		old_fs = get_fs();
		set_fs (KERNEL_DS);
		ret = sys_utime(filenam, &t);
		set_fs (old_fs);
		putname (filenam);
	}
	return ret;
}

#if 0
/*
 * count32() counts the number of arguments/envelopes
 */
static int count32(u32 * argv, int max)
{
	int i = 0;

	if (argv != NULL) {
		for (;;) {
			u32 p;
			/* egcs is stupid */
			if (!access_ok(VERIFY_READ, argv, sizeof (u32)))
				return -EFAULT;
			__get_user(p,argv);
			if (!p)
				break;
			argv++;
			if(++i > max)
				return -E2BIG;
		}
	}
	return i;
}


/*
 * 'copy_strings32()' copies argument/envelope strings from user
 * memory to free pages in kernel mem. These are in a format ready
 * to be put directly into the top of new user memory.
 */
int copy_strings32(int argc, u32 * argv, struct linux_binprm *bprm)
{
	while (argc-- > 0) {
		u32 str;
		int len;
		unsigned long pos;

		if (get_user(str, argv+argc) || !str ||
		     !(len = strnlen_user((char *)A(str), bprm->p)))
			return -EFAULT;
		if (bprm->p < len)
			return -E2BIG;

		bprm->p -= len;
		/* XXX: add architecture specific overflow check here. */

		pos = bprm->p;
		while (len > 0) {
			char *kaddr;
			int i, new, err;
			struct page *page;
			int offset, bytes_to_copy;

			offset = pos % PAGE_SIZE;
			i = pos/PAGE_SIZE;
			page = bprm->page[i];
			new = 0;
			if (!page) {
				page = alloc_page(GFP_HIGHUSER);
				bprm->page[i] = page;
				if (!page)
					return -ENOMEM;
				new = 1;
			}
			kaddr = kmap(page);

			if (new && offset)
				memset(kaddr, 0, offset);
			bytes_to_copy = PAGE_SIZE - offset;
			if (bytes_to_copy > len) {
				bytes_to_copy = len;
				if (new)
					memset(kaddr+offset+len, 0,
					       PAGE_SIZE-offset-len);
			}
			err = copy_from_user(kaddr + offset, (char *)A(str),
			                     bytes_to_copy);
			flush_page_to_ram(page);
			kunmap(page);

			if (err)
				return -EFAULT;

			pos += bytes_to_copy;
			str += bytes_to_copy;
			len -= bytes_to_copy;
		}
	}
	return 0;
}


/*
 * sys_execve32() executes a new program.
 */
int do_execve32(char * filename, u32 * argv, u32 * envp, struct pt_regs * regs)
{
	struct linux_binprm bprm;
	struct dentry * dentry;
	int retval;
	int i;

	bprm.p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *);
	memset(bprm.page, 0, MAX_ARG_PAGES*sizeof(bprm.page[0]));

	dentry = open_namei(filename, 0, 0);
	retval = PTR_ERR(dentry);
	if (IS_ERR(dentry))
		return retval;

	bprm.dentry = dentry;
	bprm.filename = filename;
	bprm.sh_bang = 0;
	bprm.loader = 0;
	bprm.exec = 0;
	if ((bprm.argc = count32(argv, bprm.p / sizeof(u32))) < 0) {
		dput(dentry);
		return bprm.argc;
	}

	if ((bprm.envc = count32(envp, bprm.p / sizeof(u32))) < 0) {
		dput(dentry);
		return bprm.envc;
	}

	retval = prepare_binprm(&bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings_kernel(1, &bprm.filename, &bprm);
	if (retval < 0)
		goto out;

	bprm.exec = bprm.p;
	retval = copy_strings32(bprm.envc, envp, &bprm);
	if (retval < 0)
		goto out;

	retval = copy_strings32(bprm.argc, argv, &bprm);
	if (retval < 0)
		goto out;

	retval = search_binary_handler(&bprm,regs);
	if (retval >= 0)
		/* execve success */
		return retval;

out:
	/* Something went wrong, return the inode and free the argument pages*/
	if (bprm.dentry)
		dput(bprm.dentry);

	/* Assumes that free_page() can take a NULL argument. */
	/* I hope this is ok for all architectures */
	for (i = 0 ; i < MAX_ARG_PAGES ; i++)
		if (bprm.page[i])
			__free_page(bprm.page[i]);

	return retval;
}

/*
 * sys_execve() executes a new program.
 */
asmlinkage int sys32_execve(abi64_no_regargs, struct pt_regs regs)
{
	int error;
	char * filename;

	filename = getname((char *) (long)regs.regs[4]);
	printk("Executing: %s\n", filename);
	error = PTR_ERR(filename);
	if (IS_ERR(filename))
		goto out;
	error = do_execve32(filename, (u32 *) (long)regs.regs[5],
	                  (u32 *) (long)regs.regs[6], &regs);
	putname(filename);

out:
	return error;
}
#else
static int nargs(unsigned int arg, char **ap)
{
	char *ptr;
	int n, ret;

	if (!arg)
		return 0;

	n = 0;
	do {
		/* egcs is stupid */
		if (!access_ok(VERIFY_READ, arg, sizeof (unsigned int)))
			return -EFAULT;
		if (IS_ERR(ret = __get_user((long)ptr,(int *)A(arg))))
			return ret;
		if (ap)		/* no access_ok needed, we allocated */
			if (IS_ERR(ret = __put_user(ptr, ap++)))
				return ret;
		arg += sizeof(unsigned int);
		n++;
	} while (ptr);

	return n - 1;
}

asmlinkage int
sys32_execve(abi64_no_regargs, struct pt_regs regs)
{
	extern asmlinkage int sys_execve(abi64_no_regargs, struct pt_regs regs);
	extern asmlinkage long sys_munmap(unsigned long addr, size_t len);
	unsigned int argv = (unsigned int)regs.regs[5];
	unsigned int envp = (unsigned int)regs.regs[6];
	char **av, **ae;
	int na, ne, r, len;
	char * filename;

	na = nargs(argv, NULL);
	if (IS_ERR(na))
		return(na);
	ne = nargs(envp, NULL);
	if (IS_ERR(ne))
		return(ne);
	len = (na + ne + 2) * sizeof(*av);
	/*
	 *  kmalloc won't work because the `sys_exec' code will attempt
	 *  to do a `get_user' on the arg list and `get_user' will fail
	 *  on a kernel address (simplifies `get_user').  Instead we
	 *  do an mmap to get a user address.  Note that since a successful
	 *  `execve' frees all current memory we only have to do an
	 *  `munmap' if the `execve' failes.
	 */
	down_write(&current->mm->mmap_sem);
	av = (char **) do_mmap_pgoff(0, 0, len, PROT_READ | PROT_WRITE,
				     MAP_PRIVATE | MAP_ANONYMOUS, 0);
	up_write(&current->mm->mmap_sem);

	if (IS_ERR(av))
		return (long) av;
	ae = av + na + 1;
	if (IS_ERR(r = __put_user(0, (av + na))))
		goto out;
	if (IS_ERR(r = __put_user(0, (ae + ne))))
		goto out;
	if (IS_ERR(r = nargs(argv, av)))
		goto out;
	if (IS_ERR(r = nargs(envp, ae)))
		goto out;
	filename = getname((char *) (long)regs.regs[4]);
	r = PTR_ERR(filename);
	if (IS_ERR(filename))
		goto out;

	r = do_execve(filename, av, ae, &regs);
	putname(filename);
	if (IS_ERR(r))
out:
		sys_munmap((unsigned long)av, len);
	return(r);
}
#endif

struct dirent32 {
	unsigned int	d_ino;
	unsigned int	d_off;
	unsigned short	d_reclen;
	char		d_name[NAME_MAX + 1];
};

static void
xlate_dirent(void *dirent64, void *dirent32, long n)
{
	long off;
	struct dirent *dirp;
	struct dirent32 *dirp32;

	off = 0;
	while (off < n) {
		dirp = (struct dirent *)(dirent64 + off);
		dirp32 = (struct dirent32 *)(dirent32 + off);
		off += dirp->d_reclen;
		dirp32->d_ino = dirp->d_ino;
		dirp32->d_off = (unsigned int)dirp->d_off;
		dirp32->d_reclen = dirp->d_reclen;
		strncpy(dirp32->d_name, dirp->d_name, dirp->d_reclen - ((3 * 4) + 2));
	}
	return;
}

asmlinkage long sys_getdents(unsigned int fd, void * dirent, unsigned int count);

asmlinkage long
sys32_getdents(unsigned int fd, void * dirent32, unsigned int count)
{
	long n;
	void *dirent64;

	dirent64 = (void *)((unsigned long)(dirent32 + (sizeof(long) - 1)) & ~(sizeof(long) - 1));
	if ((n = sys_getdents(fd, dirent64, count - (dirent64 - dirent32))) < 0)
		return(n);
	xlate_dirent(dirent64, dirent32, n);
	return(n);
}

asmlinkage int old_readdir(unsigned int fd, void * dirent, unsigned int count);

asmlinkage int
sys32_readdir(unsigned int fd, void * dirent32, unsigned int count)
{
	int n;
	struct dirent dirent64;

	if ((n = old_readdir(fd, &dirent64, count)) < 0)
		return(n);
	xlate_dirent(&dirent64, dirent32, dirent64.d_reclen);
	return(n);
}

struct timeval32
{
    int tv_sec, tv_usec;
};

struct itimerval32
{
    struct timeval32 it_interval;
    struct timeval32 it_value;
};

struct rusage32 {
        struct timeval32 ru_utime;
        struct timeval32 ru_stime;
        int    ru_maxrss;
        int    ru_ixrss;
        int    ru_idrss;
        int    ru_isrss;
        int    ru_minflt;
        int    ru_majflt;
        int    ru_nswap;
        int    ru_inblock;
        int    ru_oublock;
        int    ru_msgsnd;
        int    ru_msgrcv;
        int    ru_nsignals;
        int    ru_nvcsw;
        int    ru_nivcsw;
};

static int
put_rusage (struct rusage32 *ru, struct rusage *r)
{
	int err;

	err = put_user (r->ru_utime.tv_sec, &ru->ru_utime.tv_sec);
	err |= __put_user (r->ru_utime.tv_usec, &ru->ru_utime.tv_usec);
	err |= __put_user (r->ru_stime.tv_sec, &ru->ru_stime.tv_sec);
	err |= __put_user (r->ru_stime.tv_usec, &ru->ru_stime.tv_usec);
	err |= __put_user (r->ru_maxrss, &ru->ru_maxrss);
	err |= __put_user (r->ru_ixrss, &ru->ru_ixrss);
	err |= __put_user (r->ru_idrss, &ru->ru_idrss);
	err |= __put_user (r->ru_isrss, &ru->ru_isrss);
	err |= __put_user (r->ru_minflt, &ru->ru_minflt);
	err |= __put_user (r->ru_majflt, &ru->ru_majflt);
	err |= __put_user (r->ru_nswap, &ru->ru_nswap);
	err |= __put_user (r->ru_inblock, &ru->ru_inblock);
	err |= __put_user (r->ru_oublock, &ru->ru_oublock);
	err |= __put_user (r->ru_msgsnd, &ru->ru_msgsnd);
	err |= __put_user (r->ru_msgrcv, &ru->ru_msgrcv);
	err |= __put_user (r->ru_nsignals, &ru->ru_nsignals);
	err |= __put_user (r->ru_nvcsw, &ru->ru_nvcsw);
	err |= __put_user (r->ru_nivcsw, &ru->ru_nivcsw);
	return err;
}

asmlinkage int
sys32_wait4(__kernel_pid_t32 pid, unsigned int * stat_addr, int options,
	    struct rusage32 * ru)
{
	if (!ru)
		return sys_wait4(pid, stat_addr, options, NULL);
	else {
		struct rusage r;
		int ret;
		unsigned int status;
		mm_segment_t old_fs = get_fs();

		set_fs(KERNEL_DS);
		ret = sys_wait4(pid, stat_addr ? &status : NULL, options, &r);
		set_fs(old_fs);
		if (put_rusage (ru, &r)) return -EFAULT;
		if (stat_addr && put_user (status, stat_addr))
			return -EFAULT;
		return ret;
	}
}

asmlinkage int
sys32_waitpid(__kernel_pid_t32 pid, unsigned int *stat_addr, int options)