diff options
Diffstat (limited to 'fs/compat.c')
| -rw-r--r-- | fs/compat.c | 1743 |
1 files changed, 635 insertions, 1108 deletions
diff --git a/fs/compat.c b/fs/compat.c index 8e71cdbecc7..66d3d3c6b4b 100644 --- a/fs/compat.c +++ b/fs/compat.c @@ -8,13 +8,15 @@ * Copyright (C) 1997-2000 Jakub Jelinek (jakub@redhat.com) * Copyright (C) 1998 Eddie C. Dost (ecd@skynet.be) * Copyright (C) 2001,2002 Andi Kleen, SuSE Labs - * Copyright (C) 2003 Pavel Machek (pavel@suse.cz) + * Copyright (C) 2003 Pavel Machek (pavel@ucw.cz) * * This program is free software; you can redistribute it and/or modify * it under the terms of the GNU General Public License version 2 as * published by the Free Software Foundation. */ +#include <linux/stddef.h> +#include <linux/kernel.h> #include <linux/linkage.h> #include <linux/compat.h> #include <linux/errno.h> @@ -23,92 +25,181 @@ #include <linux/fcntl.h> #include <linux/namei.h> #include <linux/file.h> +#include <linux/fdtable.h> #include <linux/vfs.h> -#include <linux/ioctl32.h> #include <linux/ioctl.h> #include <linux/init.h> -#include <linux/sockios.h> /* for SIOCDEVPRIVATE */ -#include <linux/smb.h> -#include <linux/smb_mount.h> #include <linux/ncp_mount.h> #include <linux/nfs4_mount.h> -#include <linux/smp_lock.h> #include <linux/syscalls.h> #include <linux/ctype.h> -#include <linux/module.h> #include <linux/dirent.h> #include <linux/fsnotify.h> #include <linux/highuid.h> -#include <linux/sunrpc/svc.h> -#include <linux/nfsd/nfsd.h> -#include <linux/nfsd/syscall.h> #include <linux/personality.h> #include <linux/rwsem.h> -#include <linux/acct.h> +#include <linux/tsacct_kern.h> +#include <linux/security.h> +#include <linux/highmem.h> +#include <linux/signal.h> +#include <linux/poll.h> #include <linux/mm.h> - -#include <net/sock.h> /* siocdevprivate_ioctl */ +#include <linux/fs_struct.h> +#include <linux/slab.h> +#include <linux/pagemap.h> +#include <linux/aio.h> #include <asm/uaccess.h> #include <asm/mmu_context.h> #include <asm/ioctls.h> +#include "internal.h" + +int compat_log = 1; + +int compat_printk(const char *fmt, ...) +{ + va_list ap; + int ret; + if (!compat_log) + return 0; + va_start(ap, fmt); + ret = vprintk(fmt, ap); + va_end(ap); + return ret; +} /* * Not all architectures have sys_utime, so implement this in terms * of sys_utimes. */ -asmlinkage long compat_sys_utime(char __user *filename, struct compat_utimbuf __user *t) +COMPAT_SYSCALL_DEFINE2(utime, const 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); +} + +COMPAT_SYSCALL_DEFINE4(utimensat, unsigned int, dfd, const char __user *, filename, struct compat_timespec __user *, t, int, flags) +{ + struct timespec tv[2]; + + if (t) { + if (compat_get_timespec(&tv[0], &t[0]) || + compat_get_timespec(&tv[1], &t[1])) + return -EFAULT; + + if (tv[0].tv_nsec == UTIME_OMIT && tv[1].tv_nsec == UTIME_OMIT) + return 0; } - return do_utimes(filename, t ? tv : NULL); + return do_utimes(dfd, filename, t ? tv : NULL, flags); } -asmlinkage long compat_sys_utimes(char __user *filename, struct compat_timeval __user *t) +COMPAT_SYSCALL_DEFINE3(futimesat, unsigned int, dfd, const char __user *, filename, struct compat_timeval __user *, t) { - struct timeval tv[2]; + struct timespec tv[2]; - if (t) { + 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)) - return -EFAULT; - } - return do_utimes(filename, t ? tv : NULL); + 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, 0); +} + +COMPAT_SYSCALL_DEFINE2(utimes, const char __user *, filename, struct compat_timeval __user *, t) +{ + return compat_sys_futimesat(AT_FDCWD, filename, t); +} + +static int cp_compat_stat(struct kstat *stat, struct compat_stat __user *ubuf) +{ + struct compat_stat tmp; + + if (!old_valid_dev(stat->dev) || !old_valid_dev(stat->rdev)) + return -EOVERFLOW; + + memset(&tmp, 0, sizeof(tmp)); + tmp.st_dev = old_encode_dev(stat->dev); + tmp.st_ino = stat->ino; + if (sizeof(tmp.st_ino) < sizeof(stat->ino) && tmp.st_ino != stat->ino) + return -EOVERFLOW; + tmp.st_mode = stat->mode; + tmp.st_nlink = stat->nlink; + if (tmp.st_nlink != stat->nlink) + return -EOVERFLOW; + SET_UID(tmp.st_uid, from_kuid_munged(current_user_ns(), stat->uid)); + SET_GID(tmp.st_gid, from_kgid_munged(current_user_ns(), stat->gid)); + tmp.st_rdev = old_encode_dev(stat->rdev); + if ((u64) stat->size > MAX_NON_LFS) + return -EOVERFLOW; + tmp.st_size = stat->size; + tmp.st_atime = stat->atime.tv_sec; + tmp.st_atime_nsec = stat->atime.tv_nsec; + tmp.st_mtime = stat->mtime.tv_sec; + tmp.st_mtime_nsec = stat->mtime.tv_nsec; + tmp.st_ctime = stat->ctime.tv_sec; + tmp.st_ctime_nsec = stat->ctime.tv_nsec; + tmp.st_blocks = stat->blocks; + tmp.st_blksize = stat->blksize; + return copy_to_user(ubuf, &tmp, sizeof(tmp)) ? -EFAULT : 0; } -asmlinkage long compat_sys_newstat(char __user * filename, - struct compat_stat __user *statbuf) +COMPAT_SYSCALL_DEFINE2(newstat, const char __user *, filename, + struct compat_stat __user *, statbuf) { struct kstat stat; - int error = vfs_stat(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) +COMPAT_SYSCALL_DEFINE2(newlstat, const char __user *, filename, + struct compat_stat __user *, statbuf) { struct kstat stat; - int error = vfs_lstat(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); } -asmlinkage long compat_sys_newfstat(unsigned int fd, - struct compat_stat __user * statbuf) +#ifndef __ARCH_WANT_STAT64 +COMPAT_SYSCALL_DEFINE4(newfstatat, unsigned int, dfd, + const char __user *, filename, + struct compat_stat __user *, statbuf, int, flag) +{ + struct kstat stat; + int error; + + error = vfs_fstatat(dfd, filename, &stat, flag); + if (error) + return error; + return cp_compat_stat(&stat, statbuf); +} +#endif + +COMPAT_SYSCALL_DEFINE2(newfstat, unsigned int, fd, + struct compat_stat __user *, statbuf) { struct kstat stat; int error = vfs_fstat(fd, &stat); @@ -122,8 +213,8 @@ 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 */ @@ -146,58 +237,39 @@ static int put_compat_statfs(struct compat_statfs __user *ubuf, struct kstatfs * __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || __put_user(kbuf->f_frsize, &ubuf->f_frsize) || - __put_user(0, &ubuf->f_spare[0]) || - __put_user(0, &ubuf->f_spare[1]) || - __put_user(0, &ubuf->f_spare[2]) || - __put_user(0, &ubuf->f_spare[3]) || - __put_user(0, &ubuf->f_spare[4])) + __put_user(kbuf->f_flags, &ubuf->f_flags) || + __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) return -EFAULT; return 0; } /* - * The following statfs calls are copies of code from fs/open.c and + * The following statfs calls are copies of code from fs/statfs.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) +COMPAT_SYSCALL_DEFINE2(statfs, const char __user *, pathname, struct compat_statfs __user *, buf) { - struct nameidata nd; - int error; - - error = user_path_walk(path, &nd); - if (!error) { - struct kstatfs tmp; - error = vfs_statfs(nd.dentry->d_inode->i_sb, &tmp); - if (!error && put_compat_statfs(buf, &tmp)) - error = -EFAULT; - path_release(&nd); - } + struct kstatfs tmp; + int error = user_statfs(pathname, &tmp); + if (!error) + error = put_compat_statfs(buf, &tmp); return error; } -asmlinkage long compat_sys_fstatfs(unsigned int fd, struct compat_statfs __user *buf) +COMPAT_SYSCALL_DEFINE2(fstatfs, unsigned int, fd, struct compat_statfs __user *, buf) { - struct file * file; struct kstatfs tmp; - int error; - - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - error = vfs_statfs(file->f_dentry->d_inode->i_sb, &tmp); - if (!error && put_compat_statfs(buf, &tmp)) - error = -EFAULT; - fput(file); -out: + int error = fd_statfs(fd, &tmp); + if (!error) + error = put_compat_statfs(buf, &tmp); return error; } 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 */ @@ -219,217 +291,62 @@ static int put_compat_statfs64(struct compat_statfs64 __user *ubuf, struct kstat __put_user(kbuf->f_namelen, &ubuf->f_namelen) || __put_user(kbuf->f_fsid.val[0], &ubuf->f_fsid.val[0]) || __put_user(kbuf->f_fsid.val[1], &ubuf->f_fsid.val[1]) || - __put_user(kbuf->f_frsize, &ubuf->f_frsize)) + __put_user(kbuf->f_frsize, &ubuf->f_frsize) || + __put_user(kbuf->f_flags, &ubuf->f_flags) || + __clear_user(ubuf->f_spare, sizeof(ubuf->f_spare))) return -EFAULT; return 0; } -asmlinkage long compat_sys_statfs64(const char __user *path, compat_size_t sz, struct compat_statfs64 __user *buf) +COMPAT_SYSCALL_DEFINE3(statfs64, const char __user *, pathname, compat_size_t, sz, struct compat_statfs64 __user *, buf) { - struct nameidata nd; + struct kstatfs tmp; int error; if (sz != sizeof(*buf)) return -EINVAL; - error = user_path_walk(path, &nd); - if (!error) { - struct kstatfs tmp; - error = vfs_statfs(nd.dentry->d_inode->i_sb, &tmp); - if (!error && put_compat_statfs64(buf, &tmp)) - error = -EFAULT; - path_release(&nd); - } + error = user_statfs(pathname, &tmp); + if (!error) + error = put_compat_statfs64(buf, &tmp); return error; } -asmlinkage long compat_sys_fstatfs64(unsigned int fd, compat_size_t sz, struct compat_statfs64 __user *buf) +COMPAT_SYSCALL_DEFINE3(fstatfs64, unsigned int, fd, compat_size_t, sz, struct compat_statfs64 __user *, buf) { - struct file * file; struct kstatfs tmp; int error; if (sz != sizeof(*buf)) return -EINVAL; - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - error = vfs_statfs(file->f_dentry->d_inode->i_sb, &tmp); - if (!error && put_compat_statfs64(buf, &tmp)) - error = -EFAULT; - fput(file); -out: + error = fd_statfs(fd, &tmp); + if (!error) + error = put_compat_statfs64(buf, &tmp); 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 DECLARE_RWSEM(ioctl32_sem); - -extern struct ioctl_trans ioctl_start[]; -extern int ioctl_table_size; - -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. + */ +COMPAT_SYSCALL_DEFINE2(ustat, unsigned, dev, struct compat_ustat __user *, u) { - int i; - - for (i = 0; i < ioctl_table_size; i++) { - if (ioctl_start[i].next != 0) { - printk("ioctl translation %d bad\n",i); - return -1; - } + struct compat_ustat tmp; + struct kstatfs sbuf; + int err = vfs_ustat(new_decode_dev(dev), &sbuf); + 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_dentry, filp->f_vfsmnt, path, PAGE_SIZE); - if (IS_ERR(fn)) - fn = "?"; - } - - sprintf(buf,"'%c'", (cmd>>24) & 0x3f); - if (!isprint(buf[1])) - sprintf(buf, "%02x", buf[1]); - 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_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; - } - - /* When register_ioctl32_conversion is finally gone remove - this lock! -AK */ - down_read(&ioctl32_sem); - for (t = ioctl32_hash_table[ioctl32_hash(cmd)]; t; t = t->next) { - if (t->cmd == cmd) - goto found_handler; - } - up_read(&ioctl32_sem); - - if (S_ISSOCK(filp->f_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(); - up_read(&ioctl32_sem); - goto out_fput; - } - - up_read(&ioctl32_sem); - 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)) || @@ -482,12 +399,28 @@ static int put_compat_flock64(struct flock *kfl, struct compat_flock64 __user *u } #endif -asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, - unsigned long arg) +static unsigned int +convert_fcntl_cmd(unsigned int cmd) +{ + switch (cmd) { + case F_GETLK64: + return F_GETLK; + case F_SETLK64: + return F_SETLK; + case F_SETLKW64: + return F_SETLKW; + } + + return cmd; +} + +COMPAT_SYSCALL_DEFINE3(fcntl64, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg) { mm_segment_t old_fs; struct flock f; long ret; + unsigned int conv_cmd; switch (cmd) { case F_GETLK: @@ -501,9 +434,21 @@ 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) { - if ((f.l_start >= COMPAT_OFF_T_MAX) || - ((f.l_start + f.l_len) > COMPAT_OFF_T_MAX)) + /* 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 + * case the app was asking for trouble, so we return + * -EOVERFLOW in that case. + * l_len could be too big, in which case we just truncate it, + * and only allow the app to see that part of the conflicting + * lock that might make sense to it anyway + */ + + if (f.l_start > COMPAT_OFF_T_MAX) ret = -EOVERFLOW; + if (f.l_len > COMPAT_OFF_T_MAX) + f.l_len = COMPAT_OFF_T_MAX; if (ret == 0) ret = put_compat_flock(&f, compat_ptr(arg)); } @@ -512,19 +457,23 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, case F_GETLK64: case F_SETLK64: case F_SETLKW64: + case F_OFD_GETLK: + case F_OFD_SETLK: + case F_OFD_SETLKW: ret = get_compat_flock64(&f, compat_ptr(arg)); if (ret != 0) break; old_fs = get_fs(); set_fs(KERNEL_DS); - ret = sys_fcntl(fd, (cmd == F_GETLK64) ? F_GETLK : - ((cmd == F_SETLK64) ? F_SETLK : F_SETLKW), - (unsigned long)&f); + conv_cmd = convert_fcntl_cmd(cmd); + ret = sys_fcntl(fd, conv_cmd, (unsigned long)&f); set_fs(old_fs); - if (cmd == F_GETLK64 && ret == 0) { - if ((f.l_start >= COMPAT_LOFF_T_MAX) || - ((f.l_start + f.l_len) > COMPAT_LOFF_T_MAX)) + if ((conv_cmd == F_GETLK || conv_cmd == F_OFD_GETLK) && ret == 0) { + /* need to return lock information - see above for commentary */ + if (f.l_start > COMPAT_LOFF_T_MAX) ret = -EOVERFLOW; + if (f.l_len > COMPAT_LOFF_T_MAX) + f.l_len = COMPAT_LOFF_T_MAX; if (ret == 0) ret = put_compat_flock64(&f, compat_ptr(arg)); } @@ -537,16 +486,22 @@ asmlinkage long compat_sys_fcntl64(unsigned int fd, unsigned int cmd, return ret; } -asmlinkage long compat_sys_fcntl(unsigned int fd, unsigned int cmd, - unsigned long arg) +COMPAT_SYSCALL_DEFINE3(fcntl, unsigned int, fd, unsigned int, cmd, + compat_ulong_t, arg) { - if ((cmd == F_GETLK64) || (cmd == F_SETLK64) || (cmd == F_SETLKW64)) + switch (cmd) { + case F_GETLK64: + case F_SETLK64: + case F_SETLKW64: + case F_OFD_GETLK: + case F_OFD_SETLK: + case F_OFD_SETLKW: return -EINVAL; + } return compat_sys_fcntl64(fd, cmd, arg); } -asmlinkage long -compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p) +COMPAT_SYSCALL_DEFINE2(io_setup, unsigned, nr_reqs, u32 __user *, ctx32p) { long ret; aio_context_t ctx64; @@ -565,30 +520,98 @@ compat_sys_io_setup(unsigned nr_reqs, u32 __user *ctx32p) return ret; } -asmlinkage long -compat_sys_io_getevents(aio_context_t ctx_id, - unsigned long min_nr, - unsigned long nr, - struct io_event __user *events, - struct compat_timespec __user *timeout) +COMPAT_SYSCALL_DEFINE5(io_getevents, compat_aio_context_t, ctx_id, + compat_long_t, min_nr, + compat_long_t, nr, + struct io_event __user *, events, + struct compat_timespec __user *, timeout) { - long ret; struct timespec t; struct timespec __user *ut = NULL; - ret = -EFAULT; - if (unlikely(!access_ok(VERIFY_WRITE, events, - nr * sizeof(struct io_event)))) - goto out; if (timeout) { - if (get_compat_timespec(&t, timeout)) - goto out; + if (compat_get_timespec(&t, timeout)) + return -EFAULT; ut = compat_alloc_user_space(sizeof(*ut)); if (copy_to_user(ut, &t, sizeof(t)) ) - goto out; + return -EFAULT; } - ret = sys_io_getevents(ctx_id, min_nr, nr, events, ut); + return sys_io_getevents(ctx_id, min_nr, nr, events, ut); +} + +/* A write operation does a read from user space and vice versa */ +#define vrfy_dir(type) ((type) == READ ? VERIFY_WRITE : VERIFY_READ) + +ssize_t compat_rw_copy_check_uvector(int type, + const struct compat_iovec __user *uvector, unsigned long nr_segs, + unsigned long fast_segs, struct iovec *fast_pointer, + struct iovec **ret_pointer) +{ + compat_ssize_t tot_len; + struct iovec *iov = *ret_pointer = fast_pointer; + ssize_t ret = 0; + int seg; + + /* + * SuS says "The readv() function *may* fail if the iovcnt argument + * was less than or equal to 0, or greater than {IOV_MAX}. Linux has + * traditionally returned zero for zero segments, so... + */ + if (nr_segs == 0) + goto out; + + ret = -EINVAL; + if (nr_segs > UIO_MAXIOV || nr_segs < 0) + goto out; + if (nr_segs > fast_segs) { + ret = -ENOMEM; + iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); + if (iov == NULL) + goto out; + } + *ret_pointer = iov; + + ret = -EFAULT; + if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector))) + goto out; + + /* + * Single unix specification: + * We should -EINVAL if an element length is not >= 0 and fitting an + * ssize_t. + * + * In Linux, the total length is limited to MAX_RW_COUNT, there is + * no overflow possibility. + */ + tot_len = 0; + ret = -EINVAL; + for (seg = 0; seg < nr_segs; seg++) { + compat_uptr_t buf; + compat_ssize_t len; + + if (__get_user(len, &uvector->iov_len) || + __get_user(buf, &uvector->iov_base)) { + ret = -EFAULT; + goto out; + } + if (len < 0) /* size_t not fitting in compat_ssize_t .. */ + goto out; + if (type >= 0 && + !access_ok(vrfy_dir(type), compat_ptr(buf), len)) { + ret = -EFAULT; + goto out; + } + if (len > MAX_RW_COUNT - tot_len) + len = MAX_RW_COUNT - tot_len; + tot_len += len; + iov->iov_base = compat_ptr(buf); + iov->iov_len = (compat_size_t) len; + uvector++; + iov++; + } + ret = tot_len; + out: return ret; } @@ -610,8 +633,8 @@ copy_iocb(long nr, u32 __user *ptr32, struct iocb __user * __user *ptr64) #define MAX_AIO_SUBMITS (PAGE_SIZE/sizeof(struct iocb *)) -asmlinkage long -compat_sys_io_submit(aio_context_t ctx_id, int nr, u32 __user *iocb) +COMPAT_SYSCALL_DEFINE3(io_submit, compat_aio_context_t, ctx_id, + int, nr, u32 __user *, iocb) { struct iocb __user * __user *iocb64; long ret; @@ -625,7 +648,7 @@ compat_sys_io_submit(aio_context_t ctx_id, int nr, u32 __user *iocb) iocb64 = compat_alloc_user_space(nr * sizeof(*iocb64)); ret = copy_iocb(nr, iocb, iocb64); if (!ret) - ret = sys_io_submit(ctx_id, nr, iocb64); + ret = do_io_submit(ctx_id, nr, iocb64, 1); return ret; } @@ -694,30 +717,6 @@ static void *do_ncp_super_data_conv(void *raw_data) return raw_data; } -struct compat_smb_mount_data { - compat_int_t version; - __compat_uid_t mounted_uid; - __compat_uid_t uid; - __compat_gid_t gid; - compat_mode_t file_mode; - compat_mode_t dir_mode; -}; - -static void *do_smb_super_data_conv(void *raw_data) -{ - struct smb_mount_data *s = raw_data; - struct compat_smb_mount_data *c_s = raw_data; - - if (c_s->version != SMB_MOUNT_OLDVERSION) - goto out; - s->dir_mode = c_s->dir_mode; - s->file_mode = c_s->file_mode; - s->gid = c_s->gid; - s->uid = c_s->uid; - s->mounted_uid = c_s->mounted_uid; - out: - return raw_data; -} struct compat_nfs_string { compat_uint_t len; @@ -780,80 +779,67 @@ static int do_nfs4_super_data_conv(void *raw_data) real->flags = raw->flags; real->version = raw->version; } - else { - return -EINVAL; - } return 0; } -extern int copy_mount_options (const void __user *, unsigned long *); - -#define SMBFS_NAME "smbfs" #define NCPFS_NAME "ncpfs" #define NFS4_NAME "nfs4" -asmlinkage long compat_sys_mount(char __user * dev_name, char __user * dir_name, - char __user * type, unsigned long flags, - void __user * data) +COMPAT_SYSCALL_DEFINE5(mount, const char __user *, dev_name, + const char __user *, dir_name, + const char __user *, type, compat_ulong_t, flags, + const void __user *, data) { - unsigned long type_page; + char *kernel_type; unsigned long data_page; - unsigned long dev_page; - char *dir_page; + char *kernel_dev; + struct filename *dir; int retval; - retval = copy_mount_options (type, &type_page); + retval = copy_mount_string(type, &kernel_type); if (retval < 0) goto out; - dir_page = getname(dir_name); - retval = PTR_ERR(dir_page); - if (IS_ERR(dir_page)) + dir = getname(dir_name); + retval = PTR_ERR(dir); + if (IS_ERR(dir)) goto out1; - retval = copy_mount_options (dev_name, &dev_page); + retval = copy_mount_string(dev_name, &kernel_dev); if (retval < 0) goto out2; - retval = copy_mount_options (data, &data_page); + retval = copy_mount_options(data, &data_page); if (retval < 0) goto out3; retval = -EINVAL; - if (type_page) { - if (!strcmp((char *)type_page, SMBFS_NAME)) { - do_smb_super_data_conv((void *)data_page); - } else if (!strcmp((char *)type_page, NCPFS_NAME)) { + if (kernel_type && data_page) { + if (!strcmp(kernel_type, NCPFS_NAME)) { do_ncp_super_data_conv((void *)data_page); - } else if (!strcmp((char *)type_page, NFS4_NAME)) { + } else if (!strcmp(kernel_type, NFS4_NAME)) { if (do_nfs4_super_data_conv((void *) data_page)) goto out4; } } - lock_kernel(); - retval = do_mount((char*)dev_page, dir_page, (char*)type_page, + retval = do_mount(kernel_dev, dir->name, kernel_type, flags, (void*)data_page); - unlock_kernel(); out4: free_page(data_page); out3: - free_page(dev_page); + kfree(kernel_dev); out2: - putname(dir_page); + putname(dir); out1: - free_page(type_page); + kfree(kernel_type); out: return retval; } -#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; compat_ulong_t d_offset; @@ -862,25 +848,32 @@ struct compat_old_linux_dirent { }; struct compat_readdir_callback { + struct dir_context ctx; struct compat_old_linux_dirent __user *dirent; int result; }; static int compat_fillonedir(void *__buf, const char *name, int namlen, - loff_t offset, ino_t ino, unsigned int d_type) + loff_t offset, u64 ino, unsigned int d_type) { struct compat_readdir_callback *buf = __buf; struct compat_old_linux_dirent __user *dirent; + compat_ulong_t d_ino; if (buf->result) return -EINVAL; + 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, (unsigned long)(dirent->d_name + namlen + 1) - (unsigned long)dirent)) goto efault; - if ( __put_user(ino, &dirent->d_ino) || + if ( __put_user(d_ino, &dirent->d_ino) || __put_user(offset, &dirent->d_offset) || __put_user(namlen, &dirent->d_namlen) || __copy_to_user(dirent->d_name, name, namlen) || @@ -892,27 +885,24 @@ efault: return -EFAULT; } -asmlinkage long compat_sys_old_readdir(unsigned int fd, - struct compat_old_linux_dirent __user *dirent, unsigned int count) +COMPAT_SYSCALL_DEFINE3(old_readdir, unsigned int, fd, + struct compat_old_linux_dirent __user *, dirent, unsigned int, count) { int error; - struct file *file; - struct compat_readdir_callback buf; + struct fd f = fdget(fd); + struct compat_readdir_callback buf = { + .ctx.actor = compat_fillonedir, + .dirent = dirent + }; - error = -EBADF; - file = fget(fd); - if (!file) - goto out; - - buf.result = 0; - buf.dirent = dirent; + if (!f.file) + return -EBADF; - error = vfs_readdir(file, compat_fillonedir, &buf); - if (error >= 0) + error = iterate_dir(f.file, &buf.ctx); + if (buf.result) error = buf.result; - fput(file); -out: + fdput(f); return error; } @@ -924,6 +914,7 @@ struct compat_linux_dirent { }; struct compat_getdents_callback { + struct dir_context ctx; struct compat_linux_dirent __user *current_dir; struct compat_linux_dirent __user *previous; int count; @@ -931,22 +922,29 @@ struct compat_getdents_callback { }; static int compat_filldir(void *__buf, const char *name, int namlen, - loff_t offset, ino_t ino, unsigned int d_type) + loff_t offset, u64 ino, unsigned int d_type) { struct compat_linux_dirent __user * dirent; struct compat_getdents_callback *buf = __buf; - int reclen = COMPAT_ROUND_UP(NAME_OFFSET(dirent) + namlen + 2); + compat_ulong_t d_ino; + int reclen = ALIGN(offsetof(struct compat_linux_dirent, d_name) + + 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) { + buf->error = -EOVERFLOW; + return -EOVERFLOW; + } dirent = buf->previous; if (dirent) { if (__put_user(offset, &dirent->d_off)) goto efault; } dirent = buf->current_dir; - if (__put_user(ino, &dirent->d_ino)) + if (__put_user(d_ino, &dirent->d_ino)) goto efault; if (__put_user(reclen, &dirent->d_reclen)) goto efault; @@ -966,50 +964,43 @@ efault: return -EFAULT; } -asmlinkage long compat_sys_getdents(unsigned int fd, - struct compat_linux_dirent __user *dirent, unsigned int count) +COMPAT_SYSCALL_DEFINE3(getdents, unsigned int, fd, + struct compat_linux_dirent __user *, dirent, unsigned int, count) { - struct file * file; + struct fd f; struct compat_linux_dirent __user * lastdirent; - struct compat_getdents_callback buf; + struct compat_getdents_callback buf = { + .ctx.actor = compat_filldir, + .current_dir = dirent, + .count = count + }; int error; - error = -EFAULT; if (!access_ok(VERIFY_WRITE, dirent, count)) - goto out; - - error = -EBADF; - file = fget(fd); - if (!file) - goto out; + return -EFAULT; - buf.current_dir = dirent; - buf.previous = NULL; - buf.count = count; - buf.error = 0; + f = fdget(fd); + if (!f.file) + return -EBADF; - error = vfs_readdir(file, compat_filldir, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + error = iterate_dir(f.file, &buf.ctx); + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { - if (put_user(file->f_pos, &lastdirent->d_off)) + if (put_user(buf.ctx.pos, &lastdirent->d_off)) error = -EFAULT; else error = count - buf.count; } - -out_putf: - fput(file); -out: + fdput(f); return error; } -#ifndef __ARCH_OMIT_COMPAT_SYS_GETDENTS64 -#define COMPAT_ROUND_UP64(x) (((x)+sizeof(u64)-1) & ~(sizeof(u64)-1)) +#ifdef __ARCH_WANT_COMPAT_SYS_GETDENTS64 struct compat_getdents_callback64 { + struct dir_context ctx; struct linux_dirent64 __user *current_dir; struct linux_dirent64 __user *previous; int count; @@ -1017,12 +1008,12 @@ struct compat_getdents_callback64 { }; static int compat_filldir64(void * __buf, const char * name, int namlen, loff_t offset, - ino_t ino, unsigned int d_type) + u64 ino, unsigned int d_type) { 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(offsetof(struct linux_dirent64, d_name) + namlen + 1, + sizeof(u64)); u64 off; buf->error = -EINVAL; /* only used if we fail.. */ @@ -1058,483 +1049,121 @@ efault: return -EFAULT; } -asmlinkage long compat_sys_getdents64(unsigned int fd, - struct linux_dirent64 __user * dirent, unsigned int count) +COMPAT_SYSCALL_DEFINE3(getdents64, unsigned int, fd, + struct linux_dirent64 __user *, dirent, unsigned int, count) { - struct file * file; + struct fd f; struct linux_dirent64 __user * lastdirent; - struct compat_getdents_callback64 buf; + struct compat_getdents_callback64 buf = { + .ctx.actor = compat_filldir64, + .current_dir = dirent, + .count = count + }; int error; - error = -EFAULT; if (!access_ok(VERIFY_WRITE, dirent, count)) - goto out; - - error = -EBADF; - file = fget(fd); - if (!file) - goto out; + return -EFAULT; - buf.current_dir = dirent; - buf.previous = NULL; - buf.count = count; - buf.error = 0; + f = fdget(fd); + if (!f.file) + return -EBADF; - error = vfs_readdir(file, compat_filldir64, &buf); - if (error < 0) - goto out_putf; - error = buf.error; + error = iterate_dir(f.file, &buf.ctx); + if (error >= 0) + error = buf.error; lastdirent = buf.previous; if (lastdirent) { - typeof(lastdirent->d_off) d_off = file->f_pos; - __put_user_unaligned(d_off, &lastdirent->d_off); - error = count - buf.count; - } - -out_putf: - fput(file); -out: - return error; -} -#endif /* ! __ARCH_OMIT_COMPAT_SYS_GETDENTS64 */ - -static ssize_t compat_do_readv_writev(int type, struct file *file, - const struct compat_iovec __user *uvector, - unsigned long nr_segs, loff_t *pos) -{ - typedef ssize_t (*io_fn_t)(struct file *, char __user *, size_t, loff_t *); - typedef ssize_t (*iov_fn_t)(struct file *, const struct iovec *, unsigned long, loff_t *); - - compat_ssize_t tot_len; - struct iovec iovstack[UIO_FASTIOV]; - struct iovec *iov=iovstack, *vector; - ssize_t ret; - int seg; - io_fn_t fn; - iov_fn_t fnv; - - /* - * SuS says "The readv() function *may* fail if the iovcnt argument - * was less than or equal to 0, or greater than {IOV_MAX}. Linux has - * traditionally returned zero for zero segments, so... - */ - ret = 0; - if (nr_segs == 0) - goto out; - - /* - * First get the "struct iovec" from user memory and - * verify all the pointers - */ - ret = -EINVAL; - if ((nr_segs > UIO_MAXIOV) || (nr_segs <= 0)) - goto out; - if (!file->f_op) - goto out; - if (nr_segs > UIO_FASTIOV) { - ret = -ENOMEM; - iov = kmalloc(nr_segs*sizeof(struct iovec), GFP_KERNEL); - if (!iov) - goto out; - } - ret = -EFAULT; - if (!access_ok(VERIFY_READ, uvector, nr_segs*sizeof(*uvector))) - goto out; - - /* - * Single unix specification: - * We should -EINVAL if an element length is not >= 0 and fitting an - * ssize_t. The total length is fitting an ssize_t - * - * Be careful here because iov_len is a size_t not an ssize_t - */ - tot_len = 0; - vector = iov; - ret = -EINVAL; - for (seg = 0 ; seg < nr_segs; seg++) { - compat_ssize_t tmp = tot_len; - compat_ssize_t len; - compat_uptr_t buf; - - if (__get_user(len, &uvector->iov_len) || - __get_user(buf, &uvector->iov_base)) { - ret = -EFAULT; - goto out; - } - if (len < 0) /* size_t not fitting an compat_ssize_t .. */ - goto out; - tot_len += len; - if (tot_len < tmp) /* maths overflow on the compat_ssize_t */ - goto out; - vector->iov_base = compat_ptr(buf); - vector->iov_len = (compat_size_t) len; - uvector++; - vector++; - } - if (tot_len == 0) { - ret = 0; - goto out; - } - - ret = rw_verify_area(type, file, pos, tot_len); - if (ret) - goto out; - - fnv = NULL; - if (type == READ) { - fn = file->f_op->read; - fnv = file->f_op->readv; - } else { - fn = (io_fn_t)file->f_op->write; - fnv = file->f_op->writev; - } - if (fnv) { - ret = fnv(file, iov, nr_segs, pos); - goto out; - } - - /* Do it by hand, with file-ops */ - ret = 0; - vector = iov; - while (nr_segs > 0) { - void __user * base; - size_t len; - ssize_t nr; - - base = vector->iov_base; - len = vector->iov_len; - vector++; - nr_segs--; - - nr = fn(file, base, len, pos); - - if (nr < 0) { - if (!ret) ret = nr; - break; - } - ret += nr; - if (nr != len) - break; - } -out: - if (iov != iovstack) - kfree(iov); - if ((ret + (type == READ)) > 0) { - struct dentry *dentry = file->f_dentry; - if (type == READ) - fsnotify_access(dentry); + typeof(lastdirent->d_off) d_off = buf.ctx.pos; + if (__put_user_unaligned(d_off, &lastdirent->d_off)) + error = -EFAULT; else - fsnotify_modify(dentry); + error = count - buf.count; } - return ret; -} - -asmlinkage ssize_t -compat_sys_readv(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen) -{ - struct file *file; - ssize_t ret = -EBADF; - - file = fget(fd); - if (!file) - return -EBADF; - - if (!(file->f_mode & FMODE_READ)) - goto out; - - ret = -EINVAL; - if (!file->f_op || (!file->f_op->readv && !file->f_op->read)) - goto out; - - ret = compat_do_readv_writev(READ, file, vec, vlen, &file->f_pos); - -out: - fput(file); - return ret; -} - -asmlinkage ssize_t -compat_sys_writev(unsigned long fd, const struct compat_iovec __user *vec, unsigned long vlen) -{ - struct file *file; - ssize_t ret = -EBADF; - - file = fget(fd); - if (!file) - return -EBADF; - if (!(file->f_mode & FMODE_WRITE)) - goto out; - - ret = -EINVAL; - if (!file->f_op || (!file->f_op->writev && !file->f_op->write)) - goto out; - - ret = compat_do_readv_writev(WRITE, file, vec, vlen, &file->f_pos); - -out: - fput(file); - return ret; + fdput(f); + return error; } +#endif /* __ARCH_WANT_COMPAT_SYS_GETDENTS64 */ /* * Exactly like fs/open.c:sys_open(), except that it doesn't set the * O_LARGEFILE flag. */ -asmlinkage long -compat_sys_open(const char __user *filename, int flags, int mode) +COMPAT_SYSCALL_DEFINE3(open, const char __user *, filename, int, flags, umode_t, mode) { - return do_sys_open(filename, flags, mode); -} - -/* - * compat_count() counts the number of arguments/envelopes. It is basically - * a copy of count() from fs/exec.c, except that it works with 32 bit argv - * and envp pointers. - */ -static int compat_count(compat_uptr_t __user *argv, int max) -{ - int i = 0; - - if (argv != NULL) { - for (;;) { - compat_uptr_t p; - - if (get_user(p, argv)) - return -EFAULT; - if (!p) - break; - argv++; - if(++i > max) - return -E2BIG; - } - } - return i; + return do_sys_open(AT_FDCWD, filename, flags, mode); } /* - * compat_copy_strings() is basically a copy of copy_strings() from fs/exec.c - * except that it works with 32 bit argv and envp pointers. + * Exactly like fs/open.c:sys_openat(), except that it doesn't set the + * O_LARGEFILE flag. */ -static int compat_copy_strings(int argc, compat_uptr_t __user *argv, - struct linux_binprm *bprm) +COMPAT_SYSCALL_DEFINE4(openat, int, dfd, const char __user *, filename, int, flags, umode_t, mode) { - struct page *kmapped_page = NULL; - char *kaddr = NULL; - int ret; - - while (argc-- > 0) { - compat_uptr_t str; - int len; - unsigned long pos; - - if (get_user(str, argv+argc) || - !(len = strnlen_user(compat_ptr(str), bprm->p))) { - ret = -EFAULT; - goto out; - } - - if (bprm->p < len) { - ret = -E2BIG; - goto out; - } - - bprm->p -= len; - /* XXX: add architecture specific overflow check here. */ - pos = bprm->p; - - 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; - goto out; - } - new = 1; - } - - if (page != kmapped_page) { - if (kmapped_page) - kunmap(kmapped_page); - kmapped_page = page; - kaddr = kmap(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) { - ret = -EFAULT; - goto out; - } - - pos += bytes_to_copy; - str += bytes_to_copy; - len -= bytes_to_copy; - } - } - ret = 0; -out: - if (kmapped_page) - kunmap(kmapped_page); - return ret; + return do_sys_open(dfd, filename, flags, mode); } -#ifdef CONFIG_MMU - -#define free_arg_pages(bprm) do { } while (0) - -#else +#define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) -static inline void free_arg_pages(struct linux_binprm *bprm) +static int poll_select_copy_remaining(struct timespec *end_time, void __user *p, + int timeval, int ret) { - int i; + struct timespec ts; - for (i = 0; i < MAX_ARG_PAGES; i++) { - if (bprm->page[i]) - __free_page(bprm->page[i]); - bprm->page[i] = NULL; - } -} + if (!p) + return ret; -#endif /* CONFIG_MMU */ + if (current->personality & STICKY_TIMEOUTS) + goto sticky; -/* - * compat_do_execve() is mostly a copy of do_execve(), with the exception - * that it processes 32 bit argv and envp pointers. - */ -int compat_do_execve(char * filename, - compat_uptr_t __user *argv, - compat_uptr_t __user *envp, - struct pt_regs * regs) -{ - struct linux_binprm *bprm; - struct file *file; - int retval; - int i; + /* No update for zero timeout */ + if (!end_time->tv_sec && !end_time->tv_nsec) + return ret; - retval = -ENOMEM; - bprm = kmalloc(sizeof(*bprm), GFP_KERNEL); - if (!bprm) - goto out_ret; - memset(bprm, 0, sizeof(*bprm)); - - file = open_exec(filename); - retval = PTR_ERR(file); - if (IS_ERR(file)) - goto out_kfree; - - 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; + ktime_get_ts(&ts); + ts = timespec_sub(*end_time, ts); + if (ts.tv_sec < 0) + ts.tv_sec = ts.tv_nsec = 0; - bprm->argc = compat_count(argv, bprm->p / sizeof(compat_uptr_t)); - if ((retval = bprm->argc) < 0) - goto out_mm; + if (timeval) { + struct compat_timeval rtv; - bprm->envc = compat_count(envp, bprm->p / sizeof(compat_uptr_t)); - if ((retval = bprm->envc) < 0) - goto out_mm; + rtv.tv_sec = ts.tv_sec; + rtv.tv_usec = ts.tv_nsec / NSEC_PER_USEC; - retval = security_bprm_alloc(bprm); - if (retval) - goto out; - - 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 = compat_copy_strings(bprm->envc, envp, bprm); - if (retval < 0) - goto out; - - retval = compat_copy_strings(bprm->argc, argv, bprm); - if (retval < 0) - 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 (bprm->security) - security_bprm_free(bprm); + if (!copy_to_user(p, &rtv, sizeof(rtv))) + return ret; + } else { + struct compat_timespec rts; -out_mm: - if (bprm->mm) - mmdrop(bprm->mm); + rts.tv_sec = ts.tv_sec; + rts.tv_nsec = ts.tv_nsec; -out_file: - if (bprm->file) { - allow_write_access(bprm->file); - fput(bprm->file); + 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. + */ -out_kfree: - kfree(bprm); - -out_ret: - return retval; +sticky: + if (ret == -ERESTARTNOHAND) + ret = -EINTR; + return ret; } -#define __COMPAT_NFDBITS (8 * sizeof(compat_ulong_t)) - -#define ROUND_UP(x,y) (((x)+(y)-1)/(y)) - /* * Ooo, nasty. We need here to frob 32-bit unsigned longs to * 64-bit unsigned longs. */ -static inline +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; @@ -1545,14 +1174,14 @@ int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, nr &= ~1UL; while (nr) { unsigned long h, l; - __get_user(l, ufdset); - __get_user(h, ufdset+1); + if (__get_user(l, ufdset) || __get_user(h, ufdset+1)) + return -EFAULT; ufdset += 2; *fdset++ = h << 32 | l; nr -= 2; } - if (odd) - __get_user(*fdset, ufdset); + if (odd && __get_user(*fdset, ufdset)) + return -EFAULT; } else { /* Tricky, must clear full unsigned long in the * kernel fdset at the end, this makes sure that @@ -1563,15 +1192,15 @@ int compat_get_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, return 0; } -static inline -void compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, - unsigned long *fdset) +static +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; + return 0; odd = nr & 1UL; nr &= ~1UL; @@ -1579,13 +1208,14 @@ void compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, unsigned long h, l; l = *fdset++; h = l >> 32; - __put_user(l, ufdset); - __put_user(h, ufdset+1); + if (__put_user(l, ufdset) || __put_user(h, ufdset+1)) + return -EFAULT; ufdset += 2; nr -= 2; } - if (odd) - __put_user(*fdset, ufdset); + if (odd && __put_user(*fdset, ufdset)) + return -EFAULT; + return 0; } @@ -1593,15 +1223,6 @@ void compat_set_fd_set(unsigned long nr, compat_ulong_t __user *ufdset, * This is a virtual copy of sys_select from fs/select.c and probably * should be compared to it from time to time */ -static void *select_bits_alloc(int size) -{ - return kmalloc(6 * size, GFP_KERNEL); -} - -static void select_bits_free(void *bits, int size) -{ - kfree(bits); -} /* * We can actually return ERESTARTSYS instead of EINTR, but I'd @@ -1611,60 +1232,40 @@ static void select_bits_free(void *bits, int size) * Update: ERESTARTSYS breaks at least the xview clock binary, so * I'm trying ERESTARTNOHAND which restart only when you want to. */ -#define MAX_SELECT_SECONDS \ - ((unsigned long) (MAX_SCHEDULE_TIMEOUT / HZ)-1) - -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) +int compat_core_sys_select(int n, compat_ulong_t __user *inp, + compat_ulong_t __user *outp, compat_ulong_t __user *exp, + struct timespec *end_time) { fd_set_bits fds; - char *bits; - long timeout; - int size, max_fdset, ret = -EINVAL; + void *bits; + int size, max_fds, ret = -EINVAL; struct fdtable *fdt; - - timeout = MAX_SCHEDULE_TIMEOUT; - if (tvp) { - time_t sec, usec; - - if (!access_ok(VERIFY_READ, tvp, sizeof(*tvp)) - || __get_user(sec, &tvp->tv_sec) - || __get_user(usec, &tvp->tv_usec)) { - ret = -EFAULT; - goto out_nofds; - } - - if (sec < 0 || usec < 0) - goto out_nofds; - - if ((unsigned long) sec < MAX_SELECT_SECONDS) { - timeout = ROUND_UP(usec, 1000000/HZ); - timeout += sec * (unsigned long) HZ; - } - } + long stack_fds[SELECT_STACK_ALLOC/sizeof(long)]; if (n < 0) goto out_nofds; - /* max_fdset can increase, so grab it once to avoid race */ + /* max_fds can increase, so grab it once to avoid race */ rcu_read_lock(); fdt = files_fdtable(current->files); - max_fdset = fdt->max_fdset; + max_fds = fdt->max_fds; rcu_read_unlock(); - if (n > max_fdset) - n = max_fdset; + if (n > max_fds) + n = max_fds; /* * We need 6 bitmaps (in/out/ex for both incoming and outgoing), * since we used fdset we need to allocate memory in units of * long-words. */ - ret = -ENOMEM; size = FDS_BYTES(n); - bits = select_bits_alloc(size); - 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); @@ -1680,19 +1281,7 @@ compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp zero_fd_set(n, fds.res_out); zero_fd_set(n, fds.res_ex); - ret = do_select(n, &fds, &timeout); - - if (tvp && !(current->personality & STICKY_TIMEOUTS)) { - time_t sec = 0, usec = 0; - if (timeout) { - sec = timeout / HZ; - usec = timeout % HZ; - usec *= (1000000/HZ); - } - if (put_user(sec, &tvp->tv_sec) || - put_user(usec, &tvp->tv_usec)) - ret = -EFAULT; - } + ret = do_select(n, &fds, end_time); if (ret < 0) goto out; @@ -1703,253 +1292,191 @@ compat_sys_select(int n, compat_ulong_t __user *inp, compat_ulong_t __user *outp ret = 0; } - compat_set_fd_set(n, inp, fds.res_in); - compat_set_fd_set(n, outp, fds.res_out); - compat_set_fd_set(n, exp, fds.res_ex); - + if (compat_set_fd_set(n, inp, fds.res_in) || + compat_set_fd_set(n, outp, fds.res_out) || + compat_set_fd_set(n, exp, fds.res_ex)) + ret = -EFAULT; out: - select_bits_free(bits, size); + if (bits != stack_fds) + kfree(bits); out_nofds: return ret; } -#if defined(CONFIG_NFSD) || defined(CONFIG_NFSD_MODULE) -/* Stuff for NFS server syscalls... */ -struct compat_nfsctl_svc { - u16 svc32_port; - s32 svc32_nthreads; -}; - -struct compat_nfsctl_client { - s8 cl32_ident[NFSCLNT_IDMAX+1]; - s32 cl32_naddr; - struct in_addr cl32_addrlist[NFSCLNT_ADDRMAX]; - s32 cl32_fhkeytype; - s32 cl32_fhkeylen; - u8 cl32_fhkey[NFSCLNT_KEYMAX]; -}; +COMPAT_SYSCALL_DEFINE5(select, int, n, compat_ulong_t __user *, inp, + compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, + struct compat_timeval __user *, tvp) +{ + struct timespec end_time, *to = NULL; + struct compat_timeval tv; + int ret; -struct compat_nfsctl_export { - char ex32_client[NFSCLNT_IDMAX+1]; - char ex32_path[NFS_MAXPATHLEN+1]; - compat_dev_t ex32_dev; - compat_ino_t ex32_ino; - compat_int_t ex32_flags; - __compat_uid_t ex32_anon_uid; - __compat_gid_t ex32_anon_gid; -}; + if (tvp) { + if (copy_from_user(&tv, tvp, sizeof(tv))) + return -EFAULT; -struct compat_nfsctl_fdparm { - struct sockaddr gd32_addr; - s8 gd32_path[NFS_MAXPATHLEN+1]; - compat_int_t gd32_version; -}; + 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; + } -struct compat_nfsctl_fsparm { - struct sockaddr gd32_addr; - s8 gd32_path[NFS_MAXPATHLEN+1]; - compat_int_t gd32_maxlen; -}; + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tvp, 1, ret); -struct compat_nfsctl_arg { - compat_int_t ca32_version; /* safeguard */ - union { - struct compat_nfsctl_svc u32_svc; - struct compat_nfsctl_client u32_client; - struct compat_nfsctl_export u32_export; - struct compat_nfsctl_fdparm u32_getfd; - struct compat_nfsctl_fsparm u32_getfs; - } u; -#define ca32_svc u.u32_svc -#define ca32_client u.u32_client -#define ca32_export u.u32_export -#define ca32_getfd u.u32_getfd -#define ca32_getfs u.u32_getfs -}; + return ret; +} -union compat_nfsctl_res { - __u8 cr32_getfh[NFS_FHSIZE]; - struct knfsd_fh cr32_getfs; +struct compat_sel_arg_struct { + compat_ulong_t n; + compat_uptr_t inp; + compat_uptr_t outp; + compat_uptr_t exp; + compat_uptr_t tvp; }; -static int compat_nfs_svc_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg) +COMPAT_SYSCALL_DEFINE1(old_select, struct compat_sel_arg_struct __user *, arg) { - int err; + struct compat_sel_arg_struct a; - err = access_ok(VERIFY_READ, &arg->ca32_svc, sizeof(arg->ca32_svc)); - err |= get_user(karg->ca_version, &arg->ca32_version); - err |= __get_user(karg->ca_svc.svc_port, &arg->ca32_svc.svc32_port); - err |= __get_user(karg->ca_svc.svc_nthreads, &arg->ca32_svc.svc32_nthreads); - return (err) ? -EFAULT : 0; + if (copy_from_user(&a, arg, sizeof(a))) + return -EFAULT; + return compat_sys_select(a.n, compat_ptr(a.inp), compat_ptr(a.outp), + compat_ptr(a.exp), compat_ptr(a.tvp)); } -static int compat_nfs_clnt_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg) +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) { - int err; - - err = access_ok(VERIFY_READ, &arg->ca32_client, sizeof(arg->ca32_client)); - err |= get_user(karg->ca_version, &arg->ca32_version); - err |= __copy_from_user(&karg->ca_client.cl_ident[0], - &arg->ca32_client.cl32_ident[0], - NFSCLNT_IDMAX); - err |= __get_user(karg->ca_client.cl_naddr, &arg->ca32_client.cl32_naddr); - err |= __copy_from_user(&karg->ca_client.cl_addrlist[0], - &arg->ca32_client.cl32_addrlist[0], - (sizeof(struct in_addr) * NFSCLNT_ADDRMAX)); - err |= __get_user(karg->ca_client.cl_fhkeytype, - &arg->ca32_client.cl32_fhkeytype); - err |= __get_user(karg->ca_client.cl_fhkeylen, - &arg->ca32_client.cl32_fhkeylen); - err |= __copy_from_user(&karg->ca_client.cl_fhkey[0], - &arg->ca32_client.cl32_fhkey[0], - NFSCLNT_KEYMAX); - - return (err) ? -EFAULT : 0; -} + compat_sigset_t ss32; + sigset_t ksigmask, sigsaved; + struct compat_timespec ts; + struct timespec end_time, *to = NULL; + int ret; -static int compat_nfs_exp_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg) -{ - int err; - - err = access_ok(VERIFY_READ, &arg->ca32_export, sizeof(arg->ca32_export)); - err |= get_user(karg->ca_version, &arg->ca32_version); - err |= __copy_from_user(&karg->ca_export.ex_client[0], - &arg->ca32_export.ex32_client[0], - NFSCLNT_IDMAX); - err |= __copy_from_user(&karg->ca_export.ex_path[0], - &arg->ca32_export.ex32_path[0], - NFS_MAXPATHLEN); - err |= __get_user(karg->ca_export.ex_dev, - &arg->ca32_export.ex32_dev); - err |= __get_user(karg->ca_export.ex_ino, - &arg->ca32_export.ex32_ino); - err |= __get_user(karg->ca_export.ex_flags, - &arg->ca32_export.ex32_flags); - err |= __get_user(karg->ca_export.ex_anon_uid, - &arg->ca32_export.ex32_anon_uid); - err |= __get_user(karg->ca_export.ex_anon_gid, - &arg->ca32_export.ex32_anon_gid); - SET_UID(karg->ca_export.ex_anon_uid, karg->ca_export.ex_anon_uid); - SET_GID(karg->ca_export.ex_anon_gid, karg->ca_export.ex_anon_gid); - - return (err) ? -EFAULT : 0; -} + if (tsp) { + if (copy_from_user(&ts, tsp, sizeof(ts))) + return -EFAULT; -static int compat_nfs_getfd_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg) -{ - int err; - - err = access_ok(VERIFY_READ, &arg->ca32_getfd, sizeof(arg->ca32_getfd)); - err |= get_user(karg->ca_version, &arg->ca32_version); - err |= __copy_from_user(&karg->ca_getfd.gd_addr, - &arg->ca32_getfd.gd32_addr, - (sizeof(struct sockaddr))); - err |= __copy_from_user(&karg->ca_getfd.gd_path, - &arg->ca32_getfd.gd32_path, - (NFS_MAXPATHLEN+1)); - err |= __get_user(karg->ca_getfd.gd_version, - &arg->ca32_getfd.gd32_version); - - return (err) ? -EFAULT : 0; -} + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } -static int compat_nfs_getfs_trans(struct nfsctl_arg *karg, struct compat_nfsctl_arg __user *arg) -{ - int err; - - err = access_ok(VERIFY_READ, &arg->ca32_getfs, sizeof(arg->ca32_getfs)); - err |= get_user(karg->ca_version, &arg->ca32_version); - err |= __copy_from_user(&karg->ca_getfs.gd_addr, - &arg->ca32_getfs.gd32_addr, - (sizeof(struct sockaddr))); - err |= __copy_from_user(&karg->ca_getfs.gd_path, - &arg->ca32_getfs.gd32_path, - (NFS_MAXPATHLEN+1)); - err |= __get_user(karg->ca_getfs.gd_maxlen, - &arg->ca32_getfs.gd32_maxlen); - - return (err) ? -EFAULT : 0; -} + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&ksigmask, &ss32); -/* This really doesn't need translations, we are only passing - * back a union which contains opaque nfs file handle data. - */ -static int compat_nfs_getfh_res_trans(union nfsctl_res *kres, union compat_nfsctl_res __user *res) -{ - int err; + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); + } - err = copy_to_user(res, kres, sizeof(*res)); + ret = compat_core_sys_select(n, inp, outp, exp, to); + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); - return (err) ? -EFAULT : 0; + if (ret == -ERESTARTNOHAND) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); + + return ret; } -asmlinkage long compat_sys_nfsservctl(int cmd, struct compat_nfsctl_arg __user *arg, - union compat_nfsctl_res __user *res) +COMPAT_SYSCALL_DEFINE6(pselect6, int, n, compat_ulong_t __user *, inp, + compat_ulong_t __user *, outp, compat_ulong_t __user *, exp, + struct compat_timespec __user *, tsp, void __user *, sig) { - struct nfsctl_arg *karg; - union nfsctl_res *kres; - mm_segment_t oldfs; - int err; - - karg = kmalloc(sizeof(*karg), GFP_USER); - kres = kmalloc(sizeof(*kres), GFP_USER); - if(!karg || !kres) { - err = -ENOMEM; - goto done; + compat_size_t sigsetsize = 0; + compat_uptr_t up = 0; + + if (sig) { + if (!access_ok(VERIFY_READ, sig, + sizeof(compat_uptr_t)+sizeof(compat_size_t)) || + __get_user(up, (compat_uptr_t __user *)sig) || + __get_user(sigsetsize, + (compat_size_t __user *)(sig+sizeof(up)))) + return -EFAULT; } + return do_compat_pselect(n, inp, outp, exp, tsp, compat_ptr(up), + sigsetsize); +} - switch(cmd) { - case NFSCTL_SVC: - err = compat_nfs_svc_trans(karg, arg); - break; - - case NFSCTL_ADDCLIENT: - err = compat_nfs_clnt_trans(karg, arg); - break; - - case NFSCTL_DELCLIENT: - err = compat_nfs_clnt_trans(karg, arg); - break; +COMPAT_SYSCALL_DEFINE5(ppoll, struct pollfd __user *, ufds, + unsigned int, nfds, struct compat_timespec __user *, tsp, + const compat_sigset_t __user *, sigmask, compat_size_t, sigsetsize) +{ + compat_sigset_t ss32; + sigset_t ksigmask, sigsaved; + struct compat_timespec ts; + struct timespec end_time, *to = NULL; + int ret; - case NFSCTL_EXPORT: - case NFSCTL_UNEXPORT: - err = compat_nfs_exp_trans(karg, arg); - break; + if (tsp) { + if (copy_from_user(&ts, tsp, sizeof(ts))) + return -EFAULT; - case NFSCTL_GETFD: - err = compat_nfs_getfd_trans(karg, arg); - break; + to = &end_time; + if (poll_select_set_timeout(to, ts.tv_sec, ts.tv_nsec)) + return -EINVAL; + } - case NFSCTL_GETFS: - err = compat_nfs_getfs_trans(karg, arg); - break; + if (sigmask) { + if (sigsetsize != sizeof(compat_sigset_t)) + return -EINVAL; + if (copy_from_user(&ss32, sigmask, sizeof(ss32))) + return -EFAULT; + sigset_from_compat(&ksigmask, &ss32); - default: - err = -EINVAL; - goto done; + sigdelsetmask(&ksigmask, sigmask(SIGKILL)|sigmask(SIGSTOP)); + sigprocmask(SIG_SETMASK, &ksigmask, &sigsaved); } - oldfs = get_fs(); - set_fs(KERNEL_DS); - /* The __user pointer casts are valid because of the set_fs() */ - err = sys_nfsservctl(cmd, (void __user *) karg, (void __user *) kres); - set_fs(oldfs); + ret = do_sys_poll(ufds, nfds, to); - if (err) - goto done; + /* We can restart this syscall, usually */ + if (ret == -EINTR) { + /* + * Don't restore the signal mask yet. Let do_signal() deliver + * the signal on the way back to userspace, before the signal + * mask is restored. + */ + if (sigmask) { + memcpy(¤t->saved_sigmask, &sigsaved, + sizeof(sigsaved)); + set_restore_sigmask(); + } + ret = -ERESTARTNOHAND; + } else if (sigmask) + sigprocmask(SIG_SETMASK, &sigsaved, NULL); - if((cmd == NFSCTL_GETFD) || - (cmd == NFSCTL_GETFS)) - err = compat_nfs_getfh_res_trans(kres, res); + ret = poll_select_copy_remaining(&end_time, tsp, 0, ret); -done: - kfree(karg); - kfree(kres); - return err; + return ret; } -#else /* !NFSD */ -long asmlinkage compat_sys_nfsservctl(int cmd, void *notused, void *notused2) + +#ifdef CONFIG_FHANDLE +/* + * Exactly like fs/open.c:sys_open_by_handle_at(), except that it + * doesn't set the O_LARGEFILE flag. + */ +COMPAT_SYSCALL_DEFINE3(open_by_handle_at, int, mountdirfd, + struct file_handle __user *, handle, int, flags) { - return sys_ni_syscall(); + return do_handle_open(mountdirfd, handle, flags); } #endif |