X-Git-Url: http://git.onelab.eu/?a=blobdiff_plain;f=fs%2Ffcntl.c;h=13b97ae9ec3ecf69ee2449073e034351ed88c52c;hb=97bf2856c6014879bd04983a3e9dfcdac1e7fe85;hp=3fe5cdae376ff88c42328030fbfd6433566a68d2;hpb=9213980e6a70d8473e0ffd4b39ab5b6caaba9ff5;p=linux-2.6.git diff --git a/fs/fcntl.c b/fs/fcntl.c index 3fe5cdae3..13b97ae9e 100644 --- a/fs/fcntl.c +++ b/fs/fcntl.c @@ -4,16 +4,20 @@ * Copyright (C) 1991, 1992 Linus Torvalds */ +#include #include #include #include #include +#include #include #include #include #include #include #include +#include +#include #include #include @@ -23,56 +27,28 @@ void fastcall set_close_on_exec(unsigned int fd, int flag) { struct files_struct *files = current->files; + struct fdtable *fdt; spin_lock(&files->file_lock); + fdt = files_fdtable(files); if (flag) - FD_SET(fd, files->close_on_exec); + FD_SET(fd, fdt->close_on_exec); else - FD_CLR(fd, files->close_on_exec); + FD_CLR(fd, fdt->close_on_exec); spin_unlock(&files->file_lock); } -static inline int get_close_on_exec(unsigned int fd) +static int get_close_on_exec(unsigned int fd) { struct files_struct *files = current->files; + struct fdtable *fdt; int res; - spin_lock(&files->file_lock); - res = FD_ISSET(fd, files->close_on_exec); - spin_unlock(&files->file_lock); + rcu_read_lock(); + fdt = files_fdtable(files); + res = FD_ISSET(fd, fdt->close_on_exec); + rcu_read_unlock(); return res; } - -/* Expand files. Return <0 on error; 0 nothing done; 1 files expanded, - * we may have blocked. - * - * Should be called with the files->file_lock spinlock held for write. - */ -static int expand_files(struct files_struct *files, int nr) -{ - int err, expand = 0; -#ifdef FDSET_DEBUG - printk (KERN_ERR "%s %d: nr = %d\n", __FUNCTION__, current->pid, nr); -#endif - - if (nr >= files->max_fdset) { - expand = 1; - if ((err = expand_fdset(files, nr))) - goto out; - } - if (nr >= files->max_fds) { - expand = 1; - if ((err = expand_fd_array(files, nr))) - goto out; - } - err = expand; - out: -#ifdef FDSET_DEBUG - if (err) - printk (KERN_ERR "%s %d: return %d\n", __FUNCTION__, current->pid, err); -#endif - return err; -} - /* * locate_fd finds a free file descriptor in the open_fds fdset, * expanding the fd arrays if necessary. Must be called with the @@ -85,28 +61,29 @@ static int locate_fd(struct files_struct *files, unsigned int newfd; unsigned int start; int error; + struct fdtable *fdt; error = -EINVAL; - if (orig_start >= current->rlim[RLIMIT_NOFILE].rlim_cur) + if (orig_start >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur) goto out; repeat: + fdt = files_fdtable(files); /* * Someone might have closed fd's in the range - * orig_start..files->next_fd + * orig_start..fdt->next_fd */ start = orig_start; if (start < files->next_fd) start = files->next_fd; newfd = start; - if (start < files->max_fdset) { - newfd = find_next_zero_bit(files->open_fds->fds_bits, - files->max_fdset, start); - } + if (start < fdt->max_fds) + newfd = find_next_zero_bit(fdt->open_fds->fds_bits, + fdt->max_fds, start); error = -EMFILE; - if (newfd >= current->rlim[RLIMIT_NOFILE].rlim_cur) + if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur) goto out; if (!vx_files_avail(1)) goto out; @@ -122,9 +99,14 @@ repeat: if (error) goto repeat; + /* + * We reacquired files_lock, so we are safe as long as + * we reacquire the fdtable pointer and use it while holding + * the lock, no one can free it during that time. + */ if (start <= files->next_fd) files->next_fd = newfd + 1; - + error = newfd; out: @@ -134,13 +116,16 @@ out: static int dupfd(struct file *file, unsigned int start) { struct files_struct * files = current->files; + struct fdtable *fdt; int fd; spin_lock(&files->file_lock); fd = locate_fd(files, file, start); if (fd >= 0) { - FD_SET(fd, files->open_fds); - FD_CLR(fd, files->close_on_exec); + /* locate_fd() may have expanded fdtable, load the ptr */ + fdt = files_fdtable(files); + FD_SET(fd, fdt->open_fds); + FD_CLR(fd, fdt->close_on_exec); spin_unlock(&files->file_lock); vx_openfd_inc(fd); fd_install(fd, file); @@ -157,6 +142,7 @@ asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) int err = -EBADF; struct file * file, *tofree; struct files_struct * files = current->files; + struct fdtable *fdt; spin_lock(&files->file_lock); if (!(file = fcheck(oldfd))) @@ -165,7 +151,7 @@ asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) if (newfd == oldfd) goto out_unlock; err = -EBADF; - if (newfd >= current->rlim[RLIMIT_NOFILE].rlim_cur) + if (newfd >= current->signal->rlim[RLIMIT_NOFILE].rlim_cur) goto out_unlock; get_file(file); /* We are now finished with oldfd */ @@ -182,18 +168,21 @@ asmlinkage long sys_dup2(unsigned int oldfd, unsigned int newfd) /* Yes. It's a race. In user space. Nothing sane to do */ err = -EBUSY; - tofree = files->fd[newfd]; - if (!tofree && FD_ISSET(newfd, files->open_fds)) + fdt = files_fdtable(files); + tofree = fdt->fd[newfd]; + if (!tofree && FD_ISSET(newfd, fdt->open_fds)) goto out_fput; - files->fd[newfd] = file; - FD_SET(newfd, files->open_fds); - FD_CLR(newfd, files->close_on_exec); + rcu_assign_pointer(fdt->fd[newfd], file); + FD_SET(newfd, fdt->open_fds); + FD_CLR(newfd, fdt->close_on_exec); spin_unlock(&files->file_lock); - vx_openfd_inc(newfd); if (tofree) filp_close(tofree, files); + else + vx_openfd_inc(newfd); /* fd was unused */ + err = newfd; out: return err; @@ -217,17 +206,25 @@ asmlinkage long sys_dup(unsigned int fildes) return ret; } -#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | FASYNC | O_DIRECT) +#define SETFL_MASK (O_APPEND | O_NONBLOCK | O_NDELAY | FASYNC | O_DIRECT | O_NOATIME) static int setfl(int fd, struct file * filp, unsigned long arg) { - struct inode * inode = filp->f_dentry->d_inode; + struct inode * inode = filp->f_path.dentry->d_inode; int error = 0; - /* O_APPEND cannot be cleared if the file is marked as append-only */ - if (!(arg & O_APPEND) && IS_APPEND(inode)) + /* + * O_APPEND cannot be cleared if the file is marked as append-only + * and the file is open for write. + */ + if (((arg ^ filp->f_flags) & O_APPEND) && IS_APPEND(inode)) return -EPERM; + /* O_NOATIME can only be set by the owner or superuser */ + if ((arg & O_NOATIME) && !(filp->f_flags & O_NOATIME)) + if (current->fsuid != inode->i_uid && !capable(CAP_FOWNER)) + return -EPERM; + /* required for strict SunOS emulation */ if (O_NONBLOCK != O_NDELAY) if (arg & O_NDELAY) @@ -239,6 +236,11 @@ static int setfl(int fd, struct file * filp, unsigned long arg) return -EINVAL; } + if (filp->f_op && filp->f_op->check_flags) + error = filp->f_op->check_flags(arg); + if (error) + return error; + lock_kernel(); if ((arg ^ filp->f_flags) & FASYNC) { if (filp->f_op && filp->f_op->fasync) { @@ -254,19 +256,22 @@ static int setfl(int fd, struct file * filp, unsigned long arg) return error; } -static void f_modown(struct file *filp, unsigned long pid, +static void f_modown(struct file *filp, struct pid *pid, enum pid_type type, uid_t uid, uid_t euid, int force) { write_lock_irq(&filp->f_owner.lock); if (force || !filp->f_owner.pid) { - filp->f_owner.pid = pid; + put_pid(filp->f_owner.pid); + filp->f_owner.pid = get_pid(pid); + filp->f_owner.pid_type = type; filp->f_owner.uid = uid; filp->f_owner.euid = euid; } write_unlock_irq(&filp->f_owner.lock); } -int f_setown(struct file *filp, unsigned long arg, int force) +int __f_setown(struct file *filp, struct pid *pid, enum pid_type type, + int force) { int err; @@ -274,21 +279,48 @@ int f_setown(struct file *filp, unsigned long arg, int force) if (err) return err; - f_modown(filp, arg, current->uid, current->euid, force); + f_modown(filp, pid, type, current->uid, current->euid, force); return 0; } +EXPORT_SYMBOL(__f_setown); +int f_setown(struct file *filp, unsigned long arg, int force) +{ + enum pid_type type; + struct pid *pid; + int who = arg; + int result; + type = PIDTYPE_PID; + if (who < 0) { + type = PIDTYPE_PGID; + who = -who; + } + rcu_read_lock(); + pid = find_pid(who); + result = __f_setown(filp, pid, type, force); + rcu_read_unlock(); + return result; +} EXPORT_SYMBOL(f_setown); void f_delown(struct file *filp) { - f_modown(filp, 0, 0, 0, 1); + f_modown(filp, NULL, PIDTYPE_PID, 0, 0, 1); } -EXPORT_SYMBOL(f_delown); +pid_t f_getown(struct file *filp) +{ + pid_t pid; + read_lock(&filp->f_owner.lock); + pid = pid_nr(filp->f_owner.pid); + if (filp->f_owner.pid_type == PIDTYPE_PGID) + pid = -pid; + read_unlock(&filp->f_owner.lock); + return pid; +} -long generic_file_fcntl(int fd, unsigned int cmd, - unsigned long arg, struct file *filp) +static long do_fcntl(int fd, unsigned int cmd, unsigned long arg, + struct file *filp) { long err = -EINVAL; @@ -315,7 +347,7 @@ long generic_file_fcntl(int fd, unsigned int cmd, break; case F_SETLK: case F_SETLKW: - err = fcntl_setlk(filp, cmd, (struct flock __user *) arg); + err = fcntl_setlk(fd, filp, cmd, (struct flock __user *) arg); break; case F_GETOWN: /* @@ -325,7 +357,7 @@ long generic_file_fcntl(int fd, unsigned int cmd, * current syscall conventions, the only way * to fix this will be in libc. */ - err = filp->f_owner.pid; + err = f_getown(filp); force_successful_syscall_return(); break; case F_SETOWN: @@ -336,7 +368,7 @@ long generic_file_fcntl(int fd, unsigned int cmd, break; case F_SETSIG: /* arg == 0 restores default behaviour. */ - if (arg < 0 || arg > _NSIG) { + if (!valid_signal(arg)) { break; } err = 0; @@ -356,17 +388,8 @@ long generic_file_fcntl(int fd, unsigned int cmd, } return err; } -EXPORT_SYMBOL(generic_file_fcntl); - -static long do_fcntl(int fd, unsigned int cmd, - unsigned long arg, struct file *filp) -{ - if (filp->f_op && filp->f_op->fcntl) - return filp->f_op->fcntl(fd, cmd, arg, filp); - return generic_file_fcntl(fd, cmd, arg, filp); -} -asmlinkage long sys_fcntl(int fd, unsigned int cmd, unsigned long arg) +asmlinkage long sys_fcntl(unsigned int fd, unsigned int cmd, unsigned long arg) { struct file *filp; long err = -EBADF; @@ -412,7 +435,8 @@ asmlinkage long sys_fcntl64(unsigned int fd, unsigned int cmd, unsigned long arg break; case F_SETLK64: case F_SETLKW64: - err = fcntl_setlk64(filp, cmd, (struct flock64 __user *) arg); + err = fcntl_setlk64(fd, filp, cmd, + (struct flock64 __user *) arg); break; default: err = do_fcntl(fd, cmd, arg, filp); @@ -426,7 +450,7 @@ out: /* Table to convert sigio signal codes into poll band bitmaps */ -static long band_table[NSIGPOLL] = { +static const long band_table[NSIGPOLL] = { POLLIN | POLLRDNORM, /* POLL_IN */ POLLOUT | POLLWRNORM | POLLWRBAND, /* POLL_OUT */ POLLIN | POLLRDNORM | POLLMSG, /* POLL_MSG */ @@ -436,11 +460,12 @@ static long band_table[NSIGPOLL] = { }; static inline int sigio_perm(struct task_struct *p, - struct fown_struct *fown) + struct fown_struct *fown, int sig) { - return ((fown->euid == 0) || - (fown->euid == p->suid) || (fown->euid == p->uid) || - (fown->uid == p->suid) || (fown->uid == p->uid)); + return (((fown->euid == 0) || + (fown->euid == p->suid) || (fown->euid == p->uid) || + (fown->uid == p->suid) || (fown->uid == p->uid)) && + !security_file_send_sigiotask(p, fown, sig)); } static void send_sigio_to_task(struct task_struct *p, @@ -448,10 +473,7 @@ static void send_sigio_to_task(struct task_struct *p, int fd, int reason) { - if (!sigio_perm(p, fown)) - return; - - if (security_file_send_sigiotask(p, fown, fd, reason)) + if (!sigio_perm(p, fown, fown->signum)) return; switch (fown->signum) { @@ -469,44 +491,36 @@ static void send_sigio_to_task(struct task_struct *p, /* Make sure we are called with one of the POLL_* reasons, otherwise we could leak kernel stack into userspace. */ - if ((reason & __SI_MASK) != __SI_POLL) - BUG(); + BUG_ON((reason & __SI_MASK) != __SI_POLL); if (reason - POLL_IN >= NSIGPOLL) si.si_band = ~0L; else si.si_band = band_table[reason - POLL_IN]; si.si_fd = fd; - if (!send_sig_info(fown->signum, &si, p)) + if (!group_send_sig_info(fown->signum, &si, p)) break; /* fall-through: fall back on the old plain SIGIO signal */ case 0: - send_group_sig_info(SIGIO, SEND_SIG_PRIV, p); + group_send_sig_info(SIGIO, SEND_SIG_PRIV, p); } } void send_sigio(struct fown_struct *fown, int fd, int band) { struct task_struct *p; - int pid; + enum pid_type type; + struct pid *pid; read_lock(&fown->lock); + type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; read_lock(&tasklist_lock); - if (pid > 0) { - p = find_task_by_pid(pid); - if (p) { - send_sigio_to_task(p, fown, fd, band); - } - } else { - struct list_head *l; - struct pid *pidptr; - for_each_task_pid(-pid, PIDTYPE_PGID, p, l, pidptr) { - send_sigio_to_task(p, fown, fd, band); - } - } + do_each_pid_task(pid, type, p) { + send_sigio_to_task(p, fown, fd, band); + } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); out_unlock_fown: read_unlock(&fown->lock); @@ -515,16 +529,19 @@ void send_sigio(struct fown_struct *fown, int fd, int band) static void send_sigurg_to_task(struct task_struct *p, struct fown_struct *fown) { - if (sigio_perm(p, fown)) - send_group_sig_info(SIGURG, SEND_SIG_PRIV, p); + if (sigio_perm(p, fown, SIGURG)) + group_send_sig_info(SIGURG, SEND_SIG_PRIV, p); } int send_sigurg(struct fown_struct *fown) { struct task_struct *p; - int pid, ret = 0; + enum pid_type type; + struct pid *pid; + int ret = 0; read_lock(&fown->lock); + type = fown->pid_type; pid = fown->pid; if (!pid) goto out_unlock_fown; @@ -532,26 +549,19 @@ int send_sigurg(struct fown_struct *fown) ret = 1; read_lock(&tasklist_lock); - if (pid > 0) { - p = find_task_by_pid(pid); - if (p) { - send_sigurg_to_task(p, fown); - } - } else { - struct list_head *l; - struct pid *pidptr; - for_each_task_pid(-pid, PIDTYPE_PGID, p, l, pidptr) { - send_sigurg_to_task(p, fown); - } - } + do_each_pid_task(pid, type, p) { + send_sigurg_to_task(p, fown); + } while_each_pid_task(pid, type, p); read_unlock(&tasklist_lock); out_unlock_fown: read_unlock(&fown->lock); return ret; } -static rwlock_t fasync_lock = RW_LOCK_UNLOCKED; -static kmem_cache_t *fasync_cache; +EXPORT_SYMBOL(send_sigurg); + +static DEFINE_RWLOCK(fasync_lock); +static struct kmem_cache *fasync_cache __read_mostly; /* * fasync_helper() is used by some character device drivers (mainly mice) @@ -565,7 +575,7 @@ int fasync_helper(int fd, struct file * filp, int on, struct fasync_struct **fap int result = 0; if (on) { - new = kmem_cache_alloc(fasync_cache, SLAB_KERNEL); + new = kmem_cache_alloc(fasync_cache, GFP_KERNEL); if (!new) return -ENOMEM; }