X-Git-Url: http://ftp.safe.ca/?a=blobdiff_plain;f=fs%2Fcompat.c;h=6d6f98fe64a086ae02c864d1e93ab3b597ef216e;hb=444528b3e614f7f2391488d9bca8e0b872db909b;hp=0ec70e3cee0a6113e24b9282250dbcb950e144f1;hpb=bbea9f69668a3d0cf9feba15a724cd02896f8675;p=safe%2Fjmp%2Flinux-2.6 diff --git a/fs/compat.c b/fs/compat.c index 0ec70e3..6d6f98f 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -15,6 +15,7 @@ * published by the Free Software Foundation. */ +#include #include #include #include @@ -23,16 +24,14 @@ #include #include #include +#include #include -#include #include #include -#include /* for SIOCDEVPRIVATE */ #include #include #include #include -#include #include #include #include @@ -45,11 +44,13 @@ #include #include #include +#include #include +#include #include #include - -#include /* siocdevprivate_ioctl */ +#include +#include #include #include @@ -78,30 +79,57 @@ int compat_printk(const char *fmt, ...) */ asmlinkage long compat_sys_utime(char __user *filename, struct compat_utimbuf __user *t) { - struct timeval tv[2]; + struct timespec tv[2]; if (t) { if (get_user(tv[0].tv_sec, &t->actime) || get_user(tv[1].tv_sec, &t->modtime)) return -EFAULT; - tv[0].tv_usec = 0; - tv[1].tv_usec = 0; + tv[0].tv_nsec = 0; + tv[1].tv_nsec = 0; + } + return do_utimes(AT_FDCWD, filename, t ? tv : NULL, 0); +} + +asmlinkage long compat_sys_utimensat(unsigned int dfd, char __user *filename, struct compat_timespec __user *t, int flags) +{ + struct timespec tv[2]; + + if (t) { + if (get_compat_timespec(&tv[0], &t[0]) || + get_compat_timespec(&tv[1], &t[1])) + return -EFAULT; + + if ((tv[0].tv_nsec == UTIME_OMIT || tv[0].tv_nsec == UTIME_NOW) + && tv[0].tv_sec != 0) + return -EINVAL; + if ((tv[1].tv_nsec == UTIME_OMIT || tv[1].tv_nsec == UTIME_NOW) + && tv[1].tv_sec != 0) + return -EINVAL; + + if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT) + return 0; } - return do_utimes(AT_FDCWD, filename, t ? tv : NULL); + return do_utimes(dfd, filename, t ? tv : NULL, flags); } asmlinkage long compat_sys_futimesat(unsigned int dfd, char __user *filename, struct compat_timeval __user *t) { - struct timeval tv[2]; + struct timespec tv[2]; if (t) { if (get_user(tv[0].tv_sec, &t[0].tv_sec) || - get_user(tv[0].tv_usec, &t[0].tv_usec) || + get_user(tv[0].tv_nsec, &t[0].tv_usec) || get_user(tv[1].tv_sec, &t[1].tv_sec) || - get_user(tv[1].tv_usec, &t[1].tv_usec)) + get_user(tv[1].tv_nsec, &t[1].tv_usec)) return -EFAULT; + if (tv[0].tv_nsec >= 1000000 || tv[0].tv_nsec < 0 || + tv[1].tv_nsec >= 1000000 || tv[1].tv_nsec < 0) + return -EINVAL; + tv[0].tv_nsec *= 1000; + tv[1].tv_nsec *= 1000; } - return do_utimes(dfd, filename, t ? tv : NULL); + return do_utimes(dfd, filename, t ? tv : NULL, 0); } asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval __user *t) @@ -109,26 +137,67 @@ asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval _ return compat_sys_futimesat(AT_FDCWD, filename, t); } +static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) +{ + compat_ino_t ino = stat->ino; + typeof(ubuf->st_uid) uid = 0; + typeof(ubuf->st_gid) gid = 0; + int err; + + SET_UID(uid, stat->uid); + SET_GID(gid, stat->gid); + + if ((u64) stat->size > MAX_NON_LFS || + !old_valid_dev(stat->dev) || + !old_valid_dev(stat->rdev)) + return -EOVERFLOW; + if (sizeof(ino) < sizeof(stat->ino) && ino != stat->ino) + return -EOVERFLOW; + + if (clear_user(ubuf, sizeof(*ubuf))) + return -EFAULT; + + err = __put_user(old_encode_dev(stat->dev), &ubuf->st_dev); + err |= __put_user(ino, &ubuf->st_ino); + err |= __put_user(stat->mode, &ubuf->st_mode); + err |= __put_user(stat->nlink, &ubuf->st_nlink); + err |= __put_user(uid, &ubuf->st_uid); + err |= __put_user(gid, &ubuf->st_gid); + err |= __put_user(old_encode_dev(stat->rdev), &ubuf->st_rdev); + err |= __put_user(stat->size, &ubuf->st_size); + err |= __put_user(stat->atime.tv_sec, &ubuf->st_atime); + err |= __put_user(stat->atime.tv_nsec, &ubuf->st_atime_nsec); + err |= __put_user(stat->mtime.tv_sec, &ubuf->st_mtime); + err |= __put_user(stat->mtime.tv_nsec, &ubuf->st_mtime_nsec); + err |= __put_user(stat->ctime.tv_sec, &ubuf->st_ctime); + err |= __put_user(stat->ctime.tv_nsec, &ubuf->st_ctime_nsec); + err |= __put_user(stat->blksize, &ubuf->st_blksize); + err |= __put_user(stat->blocks, &ubuf->st_blocks); + return err; +} + asmlinkage long compat_sys_newstat(char __user * filename, struct compat_stat __user *statbuf) { struct kstat stat; - int error = vfs_stat_fd(AT_FDCWD, filename, &stat); + int error; - if (!error) - error = cp_compat_stat(&stat, statbuf); - return error; + error = vfs_stat(filename, &stat); + if (error) + return error; + return cp_compat_stat(&stat, statbuf); } asmlinkage long compat_sys_newlstat(char __user * filename, struct compat_stat __user *statbuf) { struct kstat stat; - int error = vfs_lstat_fd(AT_FDCWD, filename, &stat); + int error; - if (!error) - error = cp_compat_stat(&stat, statbuf); - return error; + error = vfs_lstat(filename, &stat); + if (error) + return error; + return cp_compat_stat(&stat, statbuf); } #ifndef __ARCH_WANT_STAT64 @@ -136,21 +205,12 @@ asmlinkage long compat_sys_newfstatat(unsigned int dfd, char __user *filename, struct compat_stat __user *statbuf, int flag) { struct kstat stat; - int error = -EINVAL; - - if ((flag & ~AT_SYMLINK_NOFOLLOW) != 0) - goto out; - - if (flag & AT_SYMLINK_NOFOLLOW) - error = vfs_lstat_fd(dfd, filename, &stat); - else - error = vfs_stat_fd(dfd, filename, &stat); - - if (!error) - error = cp_compat_stat(&stat, statbuf); + int error; -out: - return error; + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_compat_stat(&stat, statbuf); } #endif @@ -169,8 +229,8 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs * { if (sizeof ubuf->f_blocks == 4) { - if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) & - 0xffffffff00000000ULL) + if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail | + kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) return -EOVERFLOW; /* f_files and f_ffree may be -1; it's okay * to stuff that into 32 bits */ @@ -206,18 +266,18 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs * * The following statfs calls are copies of code from fs/open.c and * should be checked against those from time to time */ -asmlinkage long compat_sys_statfs(const char __user *path, struct compat_statfs __user *buf) +asmlinkage long compat_sys_statfs(const char __user *pathname, struct compat_statfs __user *buf) { - struct nameidata nd; + struct path path; int error; - error = user_path_walk(path, &nd); + error = user_path(pathname, &path); if (!error) { struct kstatfs tmp; - error = vfs_statfs(nd.dentry, &tmp); + error = vfs_statfs(path.dentry, &tmp); if (!error) error = put_compat_statfs(buf, &tmp); - path_release(&nd); + path_put(&path); } return error; } @@ -243,8 +303,8 @@ out: static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstatfs *kbuf) { if (sizeof ubuf->f_blocks == 4) { - if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail) & - 0xffffffff00000000ULL) + if ((kbuf->f_blocks | kbuf->f_bfree | kbuf->f_bavail | + kbuf->f_bsize | kbuf->f_frsize) & 0xffffffff00000000ULL) return -EOVERFLOW; /* f_files and f_ffree may be -1; it's okay * to stuff that into 32 bits */ @@ -271,21 +331,21 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat return 0; } -asmlinkage long compat_sys_statfs64(const char __user *path, compat_size_t sz, struct compat_statfs64 __user *buf) +asmlinkage long compat_sys_statfs64(const char __user *pathname, compat_size_t sz, struct compat_statfs64 __user *buf) { - struct nameidata nd; + struct path path; int error; if (sz != sizeof(*buf)) return -EINVAL; - error = user_path_walk(path, &nd); + error = user_path(pathname, &path); if (!error) { struct kstatfs tmp; - error = vfs_statfs(nd.dentry, &tmp); + error = vfs_statfs(path.dentry, &tmp); if (!error) error = put_compat_statfs64(buf, &tmp); - path_release(&nd); + path_put(&path); } return error; } @@ -311,162 +371,34 @@ out: return error; } -/* ioctl32 stuff, used by sparc64, parisc, s390x, ppc64, x86_64, MIPS */ - -#define IOCTL_HASHSIZE 256 -static struct ioctl_trans *ioctl32_hash_table[IOCTL_HASHSIZE]; - -static inline unsigned long ioctl32_hash(unsigned long cmd) -{ - return (((cmd >> 6) ^ (cmd >> 4) ^ cmd)) % IOCTL_HASHSIZE; -} - -static void ioctl32_insert_translation(struct ioctl_trans *trans) -{ - unsigned long hash; - struct ioctl_trans *t; - - hash = ioctl32_hash (trans->cmd); - if (!ioctl32_hash_table[hash]) - ioctl32_hash_table[hash] = trans; - else { - t = ioctl32_hash_table[hash]; - while (t->next) - t = t->next; - trans->next = NULL; - t->next = trans; - } -} - -static int __init init_sys32_ioctl(void) +/* + * This is a copy of sys_ustat, just dealing with a structure layout. + * Given how simple this syscall is that apporach is more maintainable + * than the various conversion hacks. + */ +asmlinkage long compat_sys_ustat(unsigned dev, struct compat_ustat __user *u) { - int i; + struct super_block *sb; + struct compat_ustat tmp; + struct kstatfs sbuf; + int err; - for (i = 0; i < ioctl_table_size; i++) { - if (ioctl_start[i].next != 0) { - printk("ioctl translation %d bad\n",i); - return -1; - } + sb = user_get_super(new_decode_dev(dev)); + if (!sb) + return -EINVAL; + err = vfs_statfs(sb->s_root, &sbuf); + drop_super(sb); + if (err) + return err; - ioctl32_insert_translation(&ioctl_start[i]); - } + memset(&tmp, 0, sizeof(struct compat_ustat)); + tmp.f_tfree = sbuf.f_bfree; + tmp.f_tinode = sbuf.f_ffree; + if (copy_to_user(u, &tmp, sizeof(struct compat_ustat))) + return -EFAULT; return 0; } -__initcall(init_sys32_ioctl); - -static void compat_ioctl_error(struct file *filp, unsigned int fd, - unsigned int cmd, unsigned long arg) -{ - char buf[10]; - char *fn = "?"; - char *path; - - /* find the name of the device. */ - path = (char *)__get_free_page(GFP_KERNEL); - if (path) { - fn = d_path(filp->f_path.dentry, filp->f_path.mnt, path, PAGE_SIZE); - if (IS_ERR(fn)) - fn = "?"; - } - - sprintf(buf,"'%c'", (cmd>>24) & 0x3f); - if (!isprint(buf[1])) - sprintf(buf, "%02x", buf[1]); - compat_printk("ioctl32(%s:%d): Unknown cmd fd(%d) " - "cmd(%08x){%s} arg(%08x) on %s\n", - current->comm, current->pid, - (int)fd, (unsigned int)cmd, buf, - (unsigned int)arg, fn); - - if (path) - free_page((unsigned long)path); -} - -asmlinkage long compat_sys_ioctl(unsigned int fd, unsigned int cmd, - unsigned long arg) -{ - struct file *filp; - int error = -EBADF; - struct ioctl_trans *t; - int fput_needed; - - filp = fget_light(fd, &fput_needed); - if (!filp) - goto out; - - /* RED-PEN how should LSM module know it's handling 32bit? */ - error = security_file_ioctl(filp, cmd, arg); - if (error) - goto out_fput; - - /* - * To allow the compat_ioctl handlers to be self contained - * we need to check the common ioctls here first. - * Just handle them with the standard handlers below. - */ - switch (cmd) { - case FIOCLEX: - case FIONCLEX: - case FIONBIO: - case FIOASYNC: - case FIOQSIZE: - break; - - case FIBMAP: - case FIGETBSZ: - case FIONREAD: - if (S_ISREG(filp->f_path.dentry->d_inode->i_mode)) - break; - /*FALL THROUGH*/ - - default: - if (filp->f_op && filp->f_op->compat_ioctl) { - error = filp->f_op->compat_ioctl(filp, cmd, arg); - if (error != -ENOIOCTLCMD) - goto out_fput; - } - - if (!filp->f_op || - (!filp->f_op->ioctl && !filp->f_op->unlocked_ioctl)) - goto do_ioctl; - break; - } - - for (t = ioctl32_hash_table[ioctl32_hash(cmd)]; t; t = t->next) { - if (t->cmd == cmd) - goto found_handler; - } - - if (S_ISSOCK(filp->f_path.dentry->d_inode->i_mode) && - cmd >= SIOCDEVPRIVATE && cmd <= (SIOCDEVPRIVATE + 15)) { - error = siocdevprivate_ioctl(fd, cmd, arg); - } else { - static int count; - - if (++count <= 50) - compat_ioctl_error(filp, fd, cmd, arg); - error = -EINVAL; - } - - goto out_fput; - - found_handler: - if (t->handler) { - lock_kernel(); - error = t->handler(fd, cmd, arg, filp); - unlock_kernel(); - goto out_fput; - } - - do_ioctl: - error = vfs_ioctl(filp, fd, cmd, arg); - out_fput: - fput_light(filp, fput_needed); - out: - return error; -} - static int get_compat_flock(struct flock *kfl, struct compat_flock __user *ufl) { if (!access_ok(VERIFY_READ, ufl, sizeof(*ufl)) || @@ -538,7 +470,7 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, ret = sys_fcntl(fd, cmd, (unsigned long)&f); set_fs(old_fs); if (cmd == F_GETLK && ret == 0) { - /* GETLK was successfule and we need to return the data... + /* GETLK was successful and we need to return the data... * but it needs to fit in the compat structure. * l_start shouldn't be too big, unless the original * start + end is greater than COMPAT_OFF_T_MAX, in which @@ -831,9 +763,6 @@ static int do_nfs4_super_data_conv(void *raw_data) real->flags = raw->flags; real->version = raw->version; } - else { - return -EINVAL; - } return 0; } @@ -882,10 +811,8 @@ asmlinkage long compat_sys_mount(char __user * dev_name, char __user * dir_name, } } - lock_kernel(); retval = do_mount((char*)dev_page, dir_page, (char*)type_page, flags, (void*)data_page); - unlock_kernel(); out4: free_page(data_page); @@ -900,8 +827,6 @@ asmlinkage long compat_sys_mount(char __user * dev_name, char __user * dir_name, } #define NAME_OFFSET(de) ((int) ((de)->d_name - (char __user *) (de))) -#define COMPAT_ROUND_UP(x) (((x)+sizeof(compat_long_t)-1) & \ - ~(sizeof(compat_long_t)-1)) struct compat_old_linux_dirent { compat_ulong_t d_ino; @@ -925,8 +850,10 @@ static int compat_fillonedir(void *__buf, const char *name, int namlen, if (buf->result) return -EINVAL; d_ino = ino; - if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->result = -EOVERFLOW; return -EOVERFLOW; + } buf->result++; dirent = buf->dirent; if (!access_ok(VERIFY_WRITE, dirent, @@ -961,7 +888,7 @@ asmlinkage long compat_sys_old_readdir(unsigned int fd, buf.dirent = dirent; error = vfs_readdir(file, compat_fillonedir, &buf); - if (error >= 0) + if (buf.result) error = buf.result; fput(file); @@ -989,14 +916,16 @@ static int compat_filldir(void *__buf, const char *name, int namlen, struct compat_linux_dirent __user * dirent; struct compat_getdents_callback *buf = __buf; compat_ulong_t d_ino; - int reclen = COMPAT_ROUND_UP(NAME_OFFSET(dirent) + namlen + 2); + int reclen = ALIGN(NAME_OFFSET(dirent) + namlen + 2, sizeof(compat_long_t)); buf->error = -EINVAL; /* only used if we fail.. */ if (reclen > buf->count) return -EINVAL; d_ino = ino; - if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) + if (sizeof(d_ino) < sizeof(ino) && d_ino != ino) { + buf->error = -EOVERFLOW; return -EOVERFLOW; + } dirent = buf->previous; if (dirent) { if (__put_user(offset, &dirent->d_off)) @@ -1046,9 +975,8 @@ asmlinkage long compat_sys_getdents(unsigned int fd, buf.error = 0; error = vfs_readdir(file, compat_filldir, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { if (put_user(file->f_pos, &lastdirent->d_off)) @@ -1056,15 +984,12 @@ asmlinkage long compat_sys_getdents(unsigned int fd, else error = count - buf.count; } - -out_putf: fput(file); out: return error; } #ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64 -#define COMPAT_ROUND_UP64(x) (((x)+sizeof(u64)-1) & ~(sizeof(u64)-1)) struct compat_getdents_callback64 { struct linux_dirent64 __user *current_dir; @@ -1079,7 +1004,7 @@ static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t struct linux_dirent64 __user *dirent; struct compat_getdents_callback64 *buf = __buf; int jj = NAME_OFFSET(dirent); - int reclen = COMPAT_ROUND_UP64(jj + namlen + 1); + int reclen = ALIGN(jj + namlen + 1, sizeof(u64)); u64 off; buf->error = -EINVAL; /* only used if we fail.. */ @@ -1138,19 +1063,16 @@ asmlinkage long compat_sys_getdents64(unsigned int fd, buf.error = 0; error = vfs_readdir(file, compat_filldir64, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { typeof(lastdirent->d_off) d_off = file->f_pos; - error = -EFAULT; if (__put_user_unaligned(d_off, &lastdirent->d_off)) - goto out_putf; - error = count - buf.count; + error = -EFAULT; + else + error = count - buf.count; } - -out_putf: fput(file); out: return error; @@ -1236,10 +1158,6 @@ static ssize_t compat_do_readv_writev(int type, struct file *file, if (ret < 0) goto out; - ret = security_file_permission(file, type == READ ? MAY_READ:MAY_WRITE); - if (ret) - goto out; - fnv = NULL; if (type == READ) { fn = file->f_op->read; @@ -1268,16 +1186,12 @@ out: return ret; } -asmlinkage ssize_t -compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen) +static size_t compat_readv(struct file *file, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t *pos) { - struct file *file; ssize_t ret = -EBADF; - file = fget(fd); - if (!file) - return -EBADF; - if (!(file->f_mode & FMODE_READ)) goto out; @@ -1285,22 +1199,56 @@ compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsign if (!file->f_op || (!file->f_op->aio_read && !file->f_op->read)) goto out; - ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos); + ret = compat_do_readv_writev(READ, file, vec, vlen, pos); out: - fput(file); + if (ret > 0) + add_rchar(current, ret); + inc_syscr(current); return ret; } asmlinkage ssize_t -compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen) +compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen) { struct file *file; - ssize_t ret = -EBADF; + int fput_needed; + ssize_t ret; - file = fget(fd); + file = fget_light(fd, &fput_needed); if (!file) return -EBADF; + ret = compat_readv(file, vec, vlen, &file->f_pos); + fput_light(file, fput_needed); + return ret; +} + +asmlinkage ssize_t +compat_sys_preadv(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_low, u32 pos_high) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + int fput_needed; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget_light(fd, &fput_needed); + if (!file) + return -EBADF; + ret = compat_readv(file, vec, vlen, &pos); + fput_light(file, fput_needed); + return ret; +} + +static size_t compat_writev(struct file *file, + const struct compat_iovec __user *vec, + unsigned long vlen, loff_t *pos) +{ + ssize_t ret = -EBADF; + if (!(file->f_mode & FMODE_WRITE)) goto out; @@ -1308,10 +1256,47 @@ compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsig if (!file->f_op || (!file->f_op->aio_write && !file->f_op->write)) goto out; - ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos); + ret = compat_do_readv_writev(WRITE, file, vec, vlen, pos); out: - fput(file); + if (ret > 0) + add_wchar(current, ret); + inc_syscw(current); + return ret; +} + +asmlinkage ssize_t +compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen) +{ + struct file *file; + int fput_needed; + ssize_t ret; + + file = fget_light(fd, &fput_needed); + if (!file) + return -EBADF; + ret = compat_writev(file, vec, vlen, &file->f_pos); + fput_light(file, fput_needed); + return ret; +} + +asmlinkage ssize_t +compat_sys_pwritev(unsigned long fd, const struct compat_iovec __user *vec, + unsigned long vlen, u32 pos_low, u32 pos_high) +{ + loff_t pos = ((loff_t)pos_high << 32) | pos_low; + struct file *file; + int fput_needed; + ssize_t ret; + + if (pos < 0) + return -EINVAL; + file = fget_light(fd, &fput_needed); + if (!file) + return -EBADF; + ret = compat_writev(file, vec, vlen, &pos); + fput_light(file, fput_needed); return ret; } @@ -1373,7 +1358,7 @@ static int compat_count(compat_uptr_t __user *argv, int max) if (!p) break; argv++; - if(++i > max) + if (i++ >= max) return -E2BIG; } } @@ -1389,6 +1374,7 @@ static int compat_copy_strings(int argc, compat_uptr_t __user *argv, { struct page *kmapped_page = NULL; char *kaddr = NULL; + unsigned long kpos = 0; int ret; while (argc-- > 0) { @@ -1397,92 +1383,84 @@ static int compat_copy_strings(int argc, compat_uptr_t __user *argv, unsigned long pos; if (get_user(str, argv+argc) || - !(len = strnlen_user(compat_ptr(str), bprm->p))) { + !(len = strnlen_user(compat_ptr(str), MAX_ARG_STRLEN))) { ret = -EFAULT; goto out; } - if (bprm->p < len) { + if (len > MAX_ARG_STRLEN) { ret = -E2BIG; goto out; } - bprm->p -= len; - /* XXX: add architecture specific overflow check here. */ + /* We're going to work our way backwords. */ pos = bprm->p; + str += len; + bprm->p -= len; while (len > 0) { - int i, new, err; int offset, bytes_to_copy; - struct page *page; 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) { - ret = -ENOMEM; + if (offset == 0) + offset = PAGE_SIZE; + + bytes_to_copy = offset; + if (bytes_to_copy > len) + bytes_to_copy = len; + + offset -= bytes_to_copy; + pos -= bytes_to_copy; + str -= bytes_to_copy; + len -= bytes_to_copy; + + if (!kmapped_page || kpos != (pos & PAGE_MASK)) { + struct page *page; + +#ifdef CONFIG_STACK_GROWSUP + ret = expand_stack_downwards(bprm->vma, pos); + if (ret < 0) { + /* We've exceed the stack rlimit. */ + ret = -E2BIG; + goto out; + } +#endif + ret = get_user_pages(current, bprm->mm, pos, + 1, 1, 1, &page, NULL); + if (ret <= 0) { + /* We've exceed the stack rlimit. */ + ret = -E2BIG; goto out; } - new = 1; - } - if (page != kmapped_page) { - if (kmapped_page) + if (kmapped_page) { + flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); + put_page(kmapped_page); + } kmapped_page = page; kaddr = kmap(kmapped_page); + kpos = pos & PAGE_MASK; + flush_cache_page(bprm->vma, kpos, + page_to_pfn(kmapped_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, compat_ptr(str), - bytes_to_copy); - if (err) { + if (copy_from_user(kaddr+offset, compat_ptr(str), + bytes_to_copy)) { ret = -EFAULT; goto out; } - - pos += bytes_to_copy; - str += bytes_to_copy; - len -= bytes_to_copy; } } ret = 0; out: - if (kmapped_page) + if (kmapped_page) { + flush_kernel_dcache_page(kmapped_page); kunmap(kmapped_page); - return ret; -} - -#ifdef CONFIG_MMU - -#define free_arg_pages(bprm) do { } while (0) - -#else - -static inline void free_arg_pages(struct linux_binprm *bprm) -{ - int i; - - for (i = 0; i < MAX_ARG_PAGES; i++) { - if (bprm->page[i]) - __free_page(bprm->page[i]); - bprm->page[i] = NULL; + put_page(kmapped_page); } + return ret; } -#endif /* CONFIG_MMU */ - /* * compat_do_execve() is mostly a copy of do_execve(), with the exception * that it processes 32 bit argv and envp pointers. @@ -1494,44 +1472,50 @@ int compat_do_execve(char * filename, { struct linux_binprm *bprm; struct file *file; + struct files_struct *displaced; + bool clear_in_exec; int retval; - int i; + + retval = unshare_files(&displaced); + if (retval) + goto out_ret; retval = -ENOMEM; bprm = kzalloc(sizeof(*bprm), GFP_KERNEL); if (!bprm) - goto out_ret; + goto out_files; + + retval = prepare_bprm_creds(bprm); + if (retval) + goto out_free; + + retval = check_unsafe_exec(bprm); + if (retval < 0) + goto out_free; + clear_in_exec = retval; + current->in_execve = 1; file = open_exec(filename); retval = PTR_ERR(file); if (IS_ERR(file)) - goto out_kfree; + goto out_unmark; sched_exec(); - bprm->p = PAGE_SIZE*MAX_ARG_PAGES-sizeof(void *); bprm->file = file; bprm->filename = filename; bprm->interp = filename; - bprm->mm = mm_alloc(); - retval = -ENOMEM; - if (!bprm->mm) - goto out_file; - retval = init_new_context(current, bprm->mm); - if (retval < 0) - goto out_mm; + retval = bprm_mm_init(bprm); + if (retval) + goto out_file; - bprm->argc = compat_count(argv, bprm->p / sizeof(compat_uptr_t)); + bprm->argc = compat_count(argv, MAX_ARG_STRINGS); if ((retval = bprm->argc) < 0) - goto out_mm; + goto out; - bprm->envc = compat_count(envp, bprm->p / sizeof(compat_uptr_t)); + bprm->envc = compat_count(envp, MAX_ARG_STRINGS); if ((retval = bprm->envc) < 0) - goto out_mm; - - retval = security_bprm_alloc(bprm); - if (retval) goto out; retval = prepare_binprm(bprm); @@ -1552,30 +1536,21 @@ int compat_do_execve(char * filename, goto out; retval = search_binary_handler(bprm, regs); - if (retval >= 0) { - free_arg_pages(bprm); - - /* execve success */ - security_bprm_free(bprm); - acct_update_integrals(current); - kfree(bprm); - return retval; - } - -out: - /* Something went wrong, return the inode and free the argument pages*/ - for (i = 0 ; i < MAX_ARG_PAGES ; i++) { - struct page * page = bprm->page[i]; - if (page) - __free_page(page); - } + if (retval < 0) + goto out; - if (bprm->security) - security_bprm_free(bprm); + /* execve succeeded */ + current->fs->in_exec = 0; + current->in_execve = 0; + acct_update_integrals(current); + free_bprm(bprm); + if (displaced) + put_files_struct(displaced); + return retval; -out_mm: +out: if (bprm->mm) - mmdrop(bprm->mm); + mmput(bprm->mm); out_file: if (bprm->file) { @@ -1583,16 +1558,73 @@ out_file: fput(bprm->file); } -out_kfree: - kfree(bprm); +out_unmark: + if (clear_in_exec) + current->fs->in_exec = 0; + current->in_execve = 0; +out_free: + free_bprm(bprm); + +out_files: + if (displaced) + reset_files_struct(displaced); out_ret: return retval; } #define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) -#define ROUND_UP(x,y) (((x)+(y)-1)/(y)) +static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, + int timeval, int ret) +{ + struct timespec ts; + + if (!p) + return ret; + + if (current->personality & STICKY_TIMEOUTS) + goto sticky; + + /* No update for zero timeout */ + if (!end_time->tv_sec && !end_time->tv_nsec) + return ret; + + ktime_get_ts(&ts); + ts = timespec_sub(*end_time, ts); + if (ts.tv_sec < 0) + ts.tv_sec = ts.tv_nsec = 0; + + if (timeval) { + struct compat_timeval rtv; + + rtv.tv_sec = ts.tv_sec; + rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; + + if (!copy_to_user(p, &rtv, sizeof(rtv))) + return ret; + } else { + struct compat_timespec rts; + + rts.tv_sec = ts.tv_sec; + rts.tv_nsec = ts.tv_nsec; + + if (!copy_to_user(p, &rts, sizeof(rts))) + return ret; + } + /* + * If an application puts its timeval in read-only memory, we + * don't want the Linux-specific update to the timeval to + * cause a fault after the select has completed + * successfully. However, because we're not updating the + * timeval, we can't restart the system call. + */ + +sticky: + if (ret == -ERESTARTNOHAND) + ret = -EINTR; + return ret; +} /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to @@ -1602,7 +1634,7 @@ static int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { - nr = ROUND_UP(nr, __COMPAT_NFDBITS); + nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); if (ufdset) { unsigned long odd; @@ -1636,7 +1668,7 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long *fdset) { unsigned long odd; - nr = ROUND_UP(nr, __COMPAT_NFDBITS); + nr = DIV_ROUND_UP(nr, __COMPAT_NFDBITS); if (!ufdset) return 0; @@ -1675,12 +1707,14 @@ int compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1) int compat_core_sys_select(int n, compat_ulong_t __user *inp, - compat_ulong_t __user *outp, compat_ulong_t __user *exp, s64 *timeout) + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct timespec *end_time) { fd_set_bits fds; - char *bits; + void *bits; int size, max_fds, ret = -EINVAL; struct fdtable *fdt; + long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; @@ -1698,11 +1732,14 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, * since we used fdset we need to allocate memory in units of * long-words. */ - ret = -ENOMEM; size = FDS_BYTES(n); - bits = kmalloc(6 * size, GFP_KERNEL); - if (!bits) - goto out_nofds; + bits = stack_fds; + if (size > sizeof(stack_fds) / 6) { + bits = kmalloc(6 * size, GFP_KERNEL); + ret = -ENOMEM; + if (!bits) + goto out_nofds; + } fds.in = (unsigned long *) bits; fds.out = (unsigned long *) (bits + size); fds.ex = (unsigned long *) (bits + 2*size); @@ -1718,7 +1755,7 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); - ret = do_select(n, &fds, timeout); + ret = do_select(n, &fds, end_time); if (ret < 0) goto out; @@ -1734,7 +1771,8 @@ int compat_core_sys_select(int n, compat_ulong_t __user *inp, compat_set_fd_set(n, exp, fds.res_ex)) ret = -EFAULT; out: - kfree(bits); + if (bits != stack_fds) + kfree(bits); out_nofds: return ret; } @@ -1743,7 +1781,7 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct compat_timeval __user *tvp) { - s64 timeout = -1; + struct timespec end_time, *to = NULL; struct compat_timeval tv; int ret; @@ -1751,64 +1789,37 @@ asmlinkage long compat_sys_select(int n, compat_ulong_t __user *inp, if (copy_from_user(&tv, tvp, sizeof(tv))) return -EFAULT; - if (tv.tv_sec < 0 || tv.tv_usec < 0) + to = &end_time; + if (poll_select_set_timeout(to, + tv.tv_sec + (tv.tv_usec / USEC_PER_SEC), + (tv.tv_usec % USEC_PER_SEC) * NSEC_PER_USEC)) return -EINVAL; - - /* Cast to u64 to make GCC stop complaining */ - if ((u64)tv.tv_sec >= (u64)MAX_INT64_SECONDS) - timeout = -1; /* infinite */ - else { - timeout = ROUND_UP(tv.tv_usec, 1000000/HZ); - timeout += tv.tv_sec * HZ; - } } - ret = compat_core_sys_select(n, inp, outp, exp, &timeout); - - if (tvp) { - struct compat_timeval rtv; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - rtv.tv_usec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)); - rtv.tv_sec = timeout; - if (compat_timeval_compare(&rtv, &tv) >= 0) - rtv = tv; - if (copy_to_user(tvp, &rtv, sizeof(rtv))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); return ret; } -#ifdef TIF_RESTORE_SIGMASK -asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, +#ifdef HAVE_SET_RESTORE_SIGMASK +static long do_compat_pselect(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp, compat_ulong_t __user *exp, struct compat_timespec __user *tsp, compat_sigset_t __user *sigmask, compat_size_t sigsetsize) { compat_sigset_t ss32; sigset_t ksigmask, sigsaved; - s64 timeout = MAX_SCHEDULE_TIMEOUT; struct compat_timespec ts; + struct timespec end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - if (ts.tv_sec < 0 || ts.tv_nsec < 0) + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) return -EINVAL; } @@ -1823,51 +1834,8 @@ asmlinkage long compat_sys_pselect7(int n, compat_ulong_t __user *inp, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - do { - if (tsp) { - if ((unsigned long)ts.tv_sec < MAX_SELECT_SECONDS) { - timeout = ROUND_UP(ts.tv_nsec, 1000000000/HZ); - timeout += ts.tv_sec * (unsigned long)HZ; - ts.tv_sec = 0; - ts.tv_nsec = 0; - } else { - ts.tv_sec -= MAX_SELECT_SECONDS; - timeout = MAX_SELECT_SECONDS * HZ; - } - } - - ret = compat_core_sys_select(n, inp, outp, exp, &timeout); - - } while (!ret && !timeout && tsp && (ts.tv_sec || ts.tv_nsec)); - - if (tsp) { - struct compat_timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - - rts.tv_sec = timeout / HZ; - rts.tv_nsec = (timeout % HZ) * (NSEC_PER_SEC/HZ); - if (rts.tv_nsec >= NSEC_PER_SEC) { - rts.tv_sec++; - rts.tv_nsec -= NSEC_PER_SEC; - } - if (compat_timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND) - ret = -EINTR; - } - } + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); if (ret == -ERESTARTNOHAND) { /* @@ -1878,7 +1846,7 @@ sticky: if (sigmask) { memcpy(¤t->saved_sigmask, &sigsaved, sizeof(sigsaved)); - set_thread_flag(TIF_RESTORE_SIGMASK); + set_restore_sigmask(); } } else if (sigmask) sigprocmask(SIG_SETMASK, &sigsaved, NULL); @@ -1901,8 +1869,8 @@ asmlinkage long compat_sys_pselect6(int n, compat_ulong_t __user *inp, (compat_size_t __user *)(sig+sizeof(up)))) return -EFAULT; } - return compat_sys_pselect7(n, inp, outp, exp, tsp, compat_ptr(up), - sigsetsize); + return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up), + sigsetsize); } asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, @@ -1912,18 +1880,16 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, compat_sigset_t ss32; sigset_t ksigmask, sigsaved; struct compat_timespec ts; - s64 timeout = -1; + struct timespec end_time, *to = NULL; int ret; if (tsp) { if (copy_from_user(&ts, tsp, sizeof(ts))) return -EFAULT; - /* We assume that ts.tv_sec is always lower than - the number of seconds that can be expressed in - an s64. Otherwise the compiler bitches at us */ - timeout = ROUND_UP(ts.tv_nsec, 1000000000/HZ); - timeout += ts.tv_sec * HZ; + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; } if (sigmask) { @@ -1937,7 +1903,7 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - ret = do_sys_poll(ufds, nfds, &timeout); + ret = do_sys_poll(ufds, nfds, to); /* We can restart this syscall, usually */ if (ret == -EINTR) { @@ -1949,41 +1915,17 @@ asmlinkage long compat_sys_ppoll(struct pollfd __user *ufds, if (sigmask) { memcpy(¤t->saved_sigmask, &sigsaved, sizeof(sigsaved)); - set_thread_flag(TIF_RESTORE_SIGMASK); + set_restore_sigmask(); } ret = -ERESTARTNOHAND; } else if (sigmask) sigprocmask(SIG_SETMASK, &sigsaved, NULL); - if (tsp && timeout >= 0) { - struct compat_timespec rts; - - if (current->personality & STICKY_TIMEOUTS) - goto sticky; - /* Yes, we know it's actually an s64, but it's also positive. */ - rts.tv_nsec = jiffies_to_usecs(do_div((*(u64*)&timeout), HZ)) * - 1000; - rts.tv_sec = timeout; - if (compat_timespec_compare(&rts, &ts) >= 0) - rts = ts; - if (copy_to_user(tsp, &rts, sizeof(rts))) { -sticky: - /* - * If an application puts its timeval in read-only - * memory, we don't want the Linux-specific update to - * the timeval to cause a fault after the select has - * completed successfully. However, because we're not - * updating the timeval, we can't restart the system - * call. - */ - if (ret == -ERESTARTNOHAND && timeout >= 0) - ret = -EINTR; - } - } + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); return ret; } -#endif /* TIF_RESTORE_SIGMASK */ +#endif /* HAVE_SET_RESTORE_SIGMASK */ #if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE) /* Stuff for NFS server syscalls... */ @@ -2235,3 +2177,124 @@ long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2) return sys_ni_syscall(); } #endif + +#ifdef CONFIG_EPOLL + +#ifdef HAVE_SET_RESTORE_SIGMASK +asmlinkage long compat_sys_epoll_pwait(int epfd, + struct compat_epoll_event __user *events, + int maxevents, int timeout, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) +{ + long err; + compat_sigset_t csigmask; + sigset_t ksigmask, sigsaved; + + /* + * If the caller wants a certain signal mask to be set during the wait, + * we apply it here. + */ + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&csigmask, sigmask, sizeof(csigmask))) + return -EFAULT; + sigset_from_compat(&ksigmask, &csigmask); + sigdelsetmask(&ksigmask, sigmask(SIGKILL) | sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } + + err = sys_epoll_wait(epfd, events, maxevents, timeout); + + /* + * If we changed the signal mask, we need to restore the original one. + * In case we've got a signal while waiting, we do not restore the + * signal mask yet, and we allow do_signal() to deliver the signal on + * the way back to userspace, before the signal mask is restored. + */ + if (sigmask) { + if (err == -EINTR) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } else + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + } + + return err; +} +#endif /* HAVE_SET_RESTORE_SIGMASK */ + +#endif /* CONFIG_EPOLL */ + +#ifdef CONFIG_SIGNALFD + +asmlinkage long compat_sys_signalfd4(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize, int flags) +{ + compat_sigset_t ss32; + sigset_t tmp; + sigset_t __user *ksigmask; + + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&tmp, &ss32); + ksigmask = compat_alloc_user_space(sizeof(sigset_t)); + if (copy_to_user(ksigmask, &tmp, sizeof(sigset_t))) + return -EFAULT; + + return sys_signalfd4(ufd, ksigmask, sizeof(sigset_t), flags); +} + +asmlinkage long compat_sys_signalfd(int ufd, + const compat_sigset_t __user *sigmask, + compat_size_t sigsetsize) +{ + return compat_sys_signalfd4(ufd, sigmask, sigsetsize, 0); +} +#endif /* CONFIG_SIGNALFD */ + +#ifdef CONFIG_TIMERFD + +asmlinkage long compat_sys_timerfd_settime(int ufd, int flags, + const struct compat_itimerspec __user *utmr, + struct compat_itimerspec __user *otmr) +{ + int error; + struct itimerspec t; + struct itimerspec __user *ut; + + if (get_compat_itimerspec(&t, utmr)) + return -EFAULT; + ut = compat_alloc_user_space(2 * sizeof(struct itimerspec)); + if (copy_to_user(&ut[0], &t, sizeof(t))) + return -EFAULT; + error = sys_timerfd_settime(ufd, flags, &ut[0], &ut[1]); + if (!error && otmr) + error = (copy_from_user(&t, &ut[1], sizeof(struct itimerspec)) || + put_compat_itimerspec(otmr, &t)) ? -EFAULT: 0; + + return error; +} + +asmlinkage long compat_sys_timerfd_gettime(int ufd, + struct compat_itimerspec __user *otmr) +{ + int error; + struct itimerspec t; + struct itimerspec __user *ut; + + ut = compat_alloc_user_space(sizeof(struct itimerspec)); + error = sys_timerfd_gettime(ufd, ut); + if (!error) + error = (copy_from_user(&t, ut, sizeof(struct itimerspec)) || + put_compat_itimerspec(otmr, &t)) ? -EFAULT: 0; + + return error; +} + +#endif /* CONFIG_TIMERFD */