diff options
Diffstat (limited to 'fs')
42 files changed, 568 insertions, 275 deletions
diff --git a/fs/9p/error.c b/fs/9p/error.c index ae91555c155..0d7fa4e0881 100644 --- a/fs/9p/error.c +++ b/fs/9p/error.c @@ -83,6 +83,7 @@ int v9fs_errstr2errno(char *errstr, int len) if (errno == 0) { /* TODO: if error isn't found, add it dynamically */ + errstr[len] = 0; printk(KERN_ERR "%s: errstr :%s: not found\n", __FUNCTION__, errstr); errno = 1; diff --git a/fs/9p/fid.c b/fs/9p/fid.c index 27507201f9e..a9b6301a04f 100644 --- a/fs/9p/fid.c +++ b/fs/9p/fid.c @@ -25,6 +25,7 @@ #include <linux/fs.h> #include <linux/sched.h> #include <linux/idr.h> +#include <asm/semaphore.h> #include "debug.h" #include "v9fs.h" @@ -84,6 +85,7 @@ struct v9fs_fid *v9fs_fid_create(struct v9fs_session_info *v9ses, int fid) new->iounit = 0; new->rdir_pos = 0; new->rdir_fcall = NULL; + init_MUTEX(&new->lock); INIT_LIST_HEAD(&new->list); return new; @@ -102,11 +104,11 @@ void v9fs_fid_destroy(struct v9fs_fid *fid) } /** - * v9fs_fid_lookup - retrieve the right fid from a particular dentry + * v9fs_fid_lookup - return a locked fid from a dentry * @dentry: dentry to look for fid in - * @type: intent of lookup (operation or traversal) * - * find a fid in the dentry + * find a fid in the dentry, obtain its semaphore and return a reference to it. + * code calling lookup is responsible for releasing lock * * TODO: only match fids that have the same uid as current user * @@ -124,7 +126,68 @@ struct v9fs_fid *v9fs_fid_lookup(struct dentry *dentry) if (!return_fid) { dprintk(DEBUG_ERROR, "Couldn't find a fid in dentry\n"); + return_fid = ERR_PTR(-EBADF); } + if(down_interruptible(&return_fid->lock)) + return ERR_PTR(-EINTR); + return return_fid; } + +/** + * v9fs_fid_clone - lookup the fid for a dentry, clone a private copy and release it + * @dentry: dentry to look for fid in + * + * find a fid in the dentry and then clone to a new private fid + * + * TODO: only match fids that have the same uid as current user + * + */ + +struct v9fs_fid *v9fs_fid_clone(struct dentry *dentry) +{ + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); + struct v9fs_fid *base_fid, *new_fid = ERR_PTR(-EBADF); + struct v9fs_fcall *fcall = NULL; + int fid, err; + + base_fid = v9fs_fid_lookup(dentry); + + if(IS_ERR(base_fid)) + return base_fid; + + if(base_fid) { /* clone fid */ + fid = v9fs_get_idpool(&v9ses->fidpool); + if (fid < 0) { + eprintk(KERN_WARNING, "newfid fails!\n"); + new_fid = ERR_PTR(-ENOSPC); + goto Release_Fid; + } + + err = v9fs_t_walk(v9ses, base_fid->fid, fid, NULL, &fcall); + if (err < 0) { + dprintk(DEBUG_ERROR, "clone walk didn't work\n"); + v9fs_put_idpool(fid, &v9ses->fidpool); + new_fid = ERR_PTR(err); + goto Free_Fcall; + } + new_fid = v9fs_fid_create(v9ses, fid); + if (new_fid == NULL) { + dprintk(DEBUG_ERROR, "out of memory\n"); + new_fid = ERR_PTR(-ENOMEM); + } +Free_Fcall: + kfree(fcall); + } + +Release_Fid: + up(&base_fid->lock); + return new_fid; +} + +void v9fs_fid_clunk(struct v9fs_session_info *v9ses, struct v9fs_fid *fid) +{ + v9fs_t_clunk(v9ses, fid->fid); + v9fs_fid_destroy(fid); +} diff --git a/fs/9p/fid.h b/fs/9p/fid.h index aa974d6875c..48fc170c26c 100644 --- a/fs/9p/fid.h +++ b/fs/9p/fid.h @@ -30,6 +30,8 @@ struct v9fs_fid { struct list_head list; /* list of fids associated with a dentry */ struct list_head active; /* XXX - debug */ + struct semaphore lock; + u32 fid; unsigned char fidopen; /* set when fid is opened */ unsigned char fidclunked; /* set when fid has already been clunked */ @@ -55,3 +57,6 @@ struct v9fs_fid *v9fs_fid_get_created(struct dentry *); void v9fs_fid_destroy(struct v9fs_fid *fid); struct v9fs_fid *v9fs_fid_create(struct v9fs_session_info *, int fid); int v9fs_fid_insert(struct v9fs_fid *fid, struct dentry *dentry); +struct v9fs_fid *v9fs_fid_clone(struct dentry *dentry); +void v9fs_fid_clunk(struct v9fs_session_info *v9ses, struct v9fs_fid *fid); + diff --git a/fs/9p/mux.c b/fs/9p/mux.c index 944273c3dbf..147ceef8e53 100644 --- a/fs/9p/mux.c +++ b/fs/9p/mux.c @@ -132,8 +132,10 @@ int v9fs_mux_global_init(void) v9fs_mux_poll_tasks[i].task = NULL; v9fs_mux_wq = create_workqueue("v9fs"); - if (!v9fs_mux_wq) + if (!v9fs_mux_wq) { + printk(KERN_WARNING "v9fs: mux: creating workqueue failed\n"); return -ENOMEM; + } return 0; } diff --git a/fs/9p/v9fs.c b/fs/9p/v9fs.c index 0b96fae8b47..d9b561ba5e5 100644 --- a/fs/9p/v9fs.c +++ b/fs/9p/v9fs.c @@ -457,14 +457,19 @@ static int __init init_v9fs(void) v9fs_error_init(); - printk(KERN_INFO "Installing v9fs 9P2000 file system support\n"); + printk(KERN_INFO "Installing v9fs 9p2000 file system support\n"); ret = v9fs_mux_global_init(); - if (!ret) + if (ret) { + printk(KERN_WARNING "v9fs: starting mux failed\n"); return ret; + } ret = register_filesystem(&v9fs_fs_type); - if (!ret) + if (ret) { + printk(KERN_WARNING "v9fs: registering file system failed\n"); v9fs_mux_global_exit(); + } + return ret; } diff --git a/fs/9p/vfs_file.c b/fs/9p/vfs_file.c index e86a0715128..9f17b0cacdd 100644 --- a/fs/9p/vfs_file.c +++ b/fs/9p/vfs_file.c @@ -55,53 +55,22 @@ int v9fs_file_open(struct inode *inode, struct file *file) struct v9fs_fid *vfid; struct v9fs_fcall *fcall = NULL; int omode; - int fid = V9FS_NOFID; int err; dprintk(DEBUG_VFS, "inode: %p file: %p \n", inode, file); - vfid = v9fs_fid_lookup(file->f_path.dentry); - if (!vfid) { - dprintk(DEBUG_ERROR, "Couldn't resolve fid from dentry\n"); - return -EBADF; - } - - fid = v9fs_get_idpool(&v9ses->fidpool); - if (fid < 0) { - eprintk(KERN_WARNING, "newfid fails!\n"); - return -ENOSPC; - } + vfid = v9fs_fid_clone(file->f_path.dentry); + if (IS_ERR(vfid)) + return PTR_ERR(vfid); - err = v9fs_t_walk(v9ses, vfid->fid, fid, NULL, &fcall); - if (err < 0) { - dprintk(DEBUG_ERROR, "rewalk didn't work\n"); - if (fcall && fcall->id == RWALK) - goto clunk_fid; - else { - v9fs_put_idpool(fid, &v9ses->fidpool); - goto free_fcall; - } - } - kfree(fcall); - - /* TODO: do special things for O_EXCL, O_NOFOLLOW, O_SYNC */ - /* translate open mode appropriately */ omode = v9fs_uflags2omode(file->f_flags); - err = v9fs_t_open(v9ses, fid, omode, &fcall); + err = v9fs_t_open(v9ses, vfid->fid, omode, &fcall); if (err < 0) { PRINT_FCALL_ERROR("open failed", fcall); - goto clunk_fid; - } - - vfid = kmalloc(sizeof(struct v9fs_fid), GFP_KERNEL); - if (vfid == NULL) { - dprintk(DEBUG_ERROR, "out of memory\n"); - err = -ENOMEM; - goto clunk_fid; + goto Clunk_Fid; } file->private_data = vfid; - vfid->fid = fid; vfid->fidopen = 1; vfid->fidclunked = 0; vfid->iounit = fcall->params.ropen.iounit; @@ -112,10 +81,8 @@ int v9fs_file_open(struct inode *inode, struct file *file) return 0; -clunk_fid: - v9fs_t_clunk(v9ses, fid); - -free_fcall: +Clunk_Fid: + v9fs_fid_clunk(v9ses, vfid); kfree(fcall); return err; diff --git a/fs/9p/vfs_inode.c b/fs/9p/vfs_inode.c index 18f26cdfd88..9109ba1d696 100644 --- a/fs/9p/vfs_inode.c +++ b/fs/9p/vfs_inode.c @@ -416,12 +416,8 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir) sb = file_inode->i_sb; v9ses = v9fs_inode2v9ses(file_inode); v9fid = v9fs_fid_lookup(file); - - if (!v9fid) { - dprintk(DEBUG_ERROR, - "no v9fs_fid\n"); - return -EBADF; - } + if(IS_ERR(v9fid)) + return PTR_ERR(v9fid); fid = v9fid->fid; if (fid < 0) { @@ -433,11 +429,13 @@ static int v9fs_remove(struct inode *dir, struct dentry *file, int rmdir) result = v9fs_t_remove(v9ses, fid, &fcall); if (result < 0) { PRINT_FCALL_ERROR("remove fails", fcall); + goto Error; } v9fs_put_idpool(fid, &v9ses->fidpool); v9fs_fid_destroy(v9fid); +Error: kfree(fcall); return result; } @@ -473,9 +471,13 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, inode = NULL; vfid = NULL; v9ses = v9fs_inode2v9ses(dir); - dfid = v9fs_fid_lookup(dentry->d_parent); - perm = unixmode2p9mode(v9ses, mode); + dfid = v9fs_fid_clone(dentry->d_parent); + if(IS_ERR(dfid)) { + err = PTR_ERR(dfid); + goto error; + } + perm = unixmode2p9mode(v9ses, mode); if (nd && nd->flags & LOOKUP_OPEN) flags = nd->intent.open.flags - 1; else @@ -485,9 +487,10 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, perm, v9fs_uflags2omode(flags), NULL, &fid, &qid, &iounit); if (err) - goto error; + goto clunk_dfid; vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry); + v9fs_fid_clunk(v9ses, dfid); if (IS_ERR(vfid)) { err = PTR_ERR(vfid); vfid = NULL; @@ -525,6 +528,9 @@ v9fs_vfs_create(struct inode *dir, struct dentry *dentry, int mode, return 0; +clunk_dfid: + v9fs_fid_clunk(v9ses, dfid); + error: if (vfid) v9fs_fid_destroy(vfid); @@ -551,7 +557,12 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) inode = NULL; vfid = NULL; v9ses = v9fs_inode2v9ses(dir); - dfid = v9fs_fid_lookup(dentry->d_parent); + dfid = v9fs_fid_clone(dentry->d_parent); + if(IS_ERR(dfid)) { + err = PTR_ERR(dfid); + goto error; + } + perm = unixmode2p9mode(v9ses, mode | S_IFDIR); err = v9fs_create(v9ses, dfid->fid, (char *) dentry->d_name.name, @@ -559,37 +570,36 @@ static int v9fs_vfs_mkdir(struct inode *dir, struct dentry *dentry, int mode) if (err) { dprintk(DEBUG_ERROR, "create error %d\n", err); - goto error; - } - - err = v9fs_t_clunk(v9ses, fid); - if (err) { - dprintk(DEBUG_ERROR, "clunk error %d\n", err); - goto error; + goto clean_up_dfid; } vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry); if (IS_ERR(vfid)) { err = PTR_ERR(vfid); vfid = NULL; - goto error; + goto clean_up_dfid; } + v9fs_fid_clunk(v9ses, dfid); inode = v9fs_inode_from_fid(v9ses, vfid->fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); inode = NULL; - goto error; + goto clean_up_fids; } dentry->d_op = &v9fs_dentry_operations; d_instantiate(dentry, inode); return 0; -error: +clean_up_fids: if (vfid) v9fs_fid_destroy(vfid); +clean_up_dfid: + v9fs_fid_clunk(v9ses, dfid); + +error: return err; } @@ -622,28 +632,23 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, dentry->d_op = &v9fs_dentry_operations; dirfid = v9fs_fid_lookup(dentry->d_parent); - if (!dirfid) { - dprintk(DEBUG_ERROR, "no dirfid\n"); - return ERR_PTR(-EINVAL); - } + if(IS_ERR(dirfid)) + return ERR_PTR(PTR_ERR(dirfid)); dirfidnum = dirfid->fid; - if (dirfidnum < 0) { - dprintk(DEBUG_ERROR, "no dirfid for inode %p, #%lu\n", - dir, dir->i_ino); - return ERR_PTR(-EBADF); - } - newfid = v9fs_get_idpool(&v9ses->fidpool); if (newfid < 0) { eprintk(KERN_WARNING, "newfid fails!\n"); - return ERR_PTR(-ENOSPC); + result = -ENOSPC; + goto Release_Dirfid; } result = v9fs_t_walk(v9ses, dirfidnum, newfid, (char *)dentry->d_name.name, &fcall); + up(&dirfid->lock); + if (result < 0) { if (fcall && fcall->id == RWALK) v9fs_t_clunk(v9ses, newfid); @@ -701,8 +706,12 @@ static struct dentry *v9fs_vfs_lookup(struct inode *dir, struct dentry *dentry, return NULL; - FreeFcall: +Release_Dirfid: + up(&dirfid->lock); + +FreeFcall: kfree(fcall); + return ERR_PTR(result); } @@ -746,10 +755,8 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, struct inode *old_inode = old_dentry->d_inode; struct v9fs_session_info *v9ses = v9fs_inode2v9ses(old_inode); struct v9fs_fid *oldfid = v9fs_fid_lookup(old_dentry); - struct v9fs_fid *olddirfid = - v9fs_fid_lookup(old_dentry->d_parent); - struct v9fs_fid *newdirfid = - v9fs_fid_lookup(new_dentry->d_parent); + struct v9fs_fid *olddirfid; + struct v9fs_fid *newdirfid; struct v9fs_wstat wstat; struct v9fs_fcall *fcall = NULL; int fid = -1; @@ -759,16 +766,26 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, dprintk(DEBUG_VFS, "\n"); - if ((!oldfid) || (!olddirfid) || (!newdirfid)) { - dprintk(DEBUG_ERROR, "problem with arguments\n"); - return -EBADF; + if(IS_ERR(oldfid)) + return PTR_ERR(oldfid); + + olddirfid = v9fs_fid_clone(old_dentry->d_parent); + if(IS_ERR(olddirfid)) { + retval = PTR_ERR(olddirfid); + goto Release_lock; + } + + newdirfid = v9fs_fid_clone(new_dentry->d_parent); + if(IS_ERR(newdirfid)) { + retval = PTR_ERR(newdirfid); + goto Clunk_olddir; } /* 9P can only handle file rename in the same directory */ if (memcmp(&olddirfid->qid, &newdirfid->qid, sizeof(newdirfid->qid))) { dprintk(DEBUG_ERROR, "old dir and new dir are different\n"); - retval = -EPERM; - goto FreeFcallnBail; + retval = -EXDEV; + goto Clunk_newdir; } fid = oldfid->fid; @@ -779,7 +796,7 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, dprintk(DEBUG_ERROR, "no fid for old file #%lu\n", old_inode->i_ino); retval = -EBADF; - goto FreeFcallnBail; + goto Clunk_newdir; } v9fs_blank_wstat(&wstat); @@ -788,11 +805,20 @@ v9fs_vfs_rename(struct inode *old_dir, struct dentry *old_dentry, retval = v9fs_t_wstat(v9ses, fid, &wstat, &fcall); - FreeFcallnBail: if (retval < 0) PRINT_FCALL_ERROR("wstat error", fcall); kfree(fcall); + +Clunk_newdir: + v9fs_fid_clunk(v9ses, newdirfid); + +Clunk_olddir: + v9fs_fid_clunk(v9ses, olddirfid); + +Release_lock: + up(&oldfid->lock); + return retval; } @@ -810,15 +836,12 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, { struct v9fs_fcall *fcall = NULL; struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); - struct v9fs_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_fid *fid = v9fs_fid_clone(dentry); int err = -EPERM; dprintk(DEBUG_VFS, "dentry: %p\n", dentry); - if (!fid) { - dprintk(DEBUG_ERROR, - "couldn't find fid associated with dentry\n"); - return -EBADF; - } + if(IS_ERR(fid)) + return PTR_ERR(fid); err = v9fs_t_stat(v9ses, fid->fid, &fcall); @@ -831,6 +854,7 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, } kfree(fcall); + v9fs_fid_clunk(v9ses, fid); return err; } @@ -844,18 +868,14 @@ v9fs_vfs_getattr(struct vfsmount *mnt, struct dentry *dentry, static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) { struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); - struct v9fs_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_fid *fid = v9fs_fid_clone(dentry); struct v9fs_fcall *fcall = NULL; struct v9fs_wstat wstat; int res = -EPERM; dprintk(DEBUG_VFS, "\n"); - - if (!fid) { - dprintk(DEBUG_ERROR, - "Couldn't find fid associated with dentry\n"); - return -EBADF; - } + if(IS_ERR(fid)) + return PTR_ERR(fid); v9fs_blank_wstat(&wstat); if (iattr->ia_valid & ATTR_MODE) @@ -887,6 +907,7 @@ static int v9fs_vfs_setattr(struct dentry *dentry, struct iattr *iattr) if (res >= 0) res = inode_setattr(dentry->d_inode, iattr); + v9fs_fid_clunk(v9ses, fid); return res; } @@ -987,18 +1008,15 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) struct v9fs_fcall *fcall = NULL; struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dentry->d_inode); - struct v9fs_fid *fid = v9fs_fid_lookup(dentry); + struct v9fs_fid *fid = v9fs_fid_clone(dentry); - if (!fid) { - dprintk(DEBUG_ERROR, "could not resolve fid from dentry\n"); - retval = -EBADF; - goto FreeFcall; - } + if(IS_ERR(fid)) + return PTR_ERR(fid); if (!v9ses->extended) { retval = -EBADF; dprintk(DEBUG_ERROR, "not extended\n"); - goto FreeFcall; + goto ClunkFid; } dprintk(DEBUG_VFS, " %s\n", dentry->d_name.name); @@ -1009,8 +1027,10 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) goto FreeFcall; } - if (!fcall) - return -EIO; + if (!fcall) { + retval = -EIO; + goto ClunkFid; + } if (!(fcall->params.rstat.stat.mode & V9FS_DMSYMLINK)) { retval = -EINVAL; @@ -1028,9 +1048,12 @@ static int v9fs_readlink(struct dentry *dentry, char *buffer, int buflen) fcall->params.rstat.stat.extension.str, buffer); retval = buflen; - FreeFcall: +FreeFcall: kfree(fcall); +ClunkFid: + v9fs_fid_clunk(v9ses, fid); + return retval; } @@ -1123,52 +1146,58 @@ static int v9fs_vfs_mkspecial(struct inode *dir, struct dentry *dentry, int err; u32 fid, perm; struct v9fs_session_info *v9ses; - struct v9fs_fid *dfid, *vfid; - struct inode *inode; + struct v9fs_fid *dfid, *vfid = NULL; + struct inode *inode = NULL; - inode = NULL; - vfid = NULL; v9ses = v9fs_inode2v9ses(dir); - dfid = v9fs_fid_lookup(dentry->d_parent); - perm = unixmode2p9mode(v9ses, mode); - if (!v9ses->extended) { dprintk(DEBUG_ERROR, "not extended\n"); return -EPERM; } + dfid = v9fs_fid_clone(dentry->d_parent); + if(IS_ERR(dfid)) { + err = PTR_ERR(dfid); + goto error; + } + + perm = unixmode2p9mode(v9ses, mode); + err = v9fs_create(v9ses, dfid->fid, (char *) dentry->d_name.name, perm, V9FS_OREAD, (char *) extension, &fid, NULL, NULL); if (err) - goto error; + goto clunk_dfid; err = v9fs_t_clunk(v9ses, fid); if (err) - goto error; + goto clunk_dfid; vfid = v9fs_clone_walk(v9ses, dfid->fid, dentry); if (IS_ERR(vfid)) { err = PTR_ERR(vfid); vfid = NULL; - goto error; + goto clunk_dfid; } inode = v9fs_inode_from_fid(v9ses, vfid->fid, dir->i_sb); if (IS_ERR(inode)) { err = PTR_ERR(inode); inode = NULL; - goto error; + goto free_vfid; } dentry->d_op = &v9fs_dentry_operations; d_instantiate(dentry, inode); return 0; -error: - if (vfid) - v9fs_fid_destroy(vfid); +free_vfid: + v9fs_fid_destroy(vfid); + +clunk_dfid: + v9fs_fid_clunk(v9ses, dfid); +error: return err; } @@ -1209,26 +1238,29 @@ v9fs_vfs_link(struct dentry *old_dentry, struct inode *dir, struct dentry *dentry) { int retval; + struct v9fs_session_info *v9ses = v9fs_inode2v9ses(dir); struct v9fs_fid *oldfid; char *name; dprintk(DEBUG_VFS, " %lu,%s,%s\n", dir->i_ino, dentry->d_name.name, old_dentry->d_name.name); - oldfid = v9fs_fid_lookup(old_dentry); - if (!oldfid) { - dprintk(DEBUG_ERROR, "can't find oldfid\n"); - return -EPERM; - } + oldfid = v9fs_fid_clone(old_dentry); + if(IS_ERR(oldfid)) + return PTR_ERR(oldfid); name = __getname(); - if (unlikely(!name)) - return -ENOMEM; + if (unlikely(!name)) { + retval = -ENOMEM; + goto clunk_fid; + } sprintf(name, "%d\n", oldfid->fid); retval = v9fs_vfs_mkspecial(dir, dentry, V9FS_DMLINK, name); __putname(name); +clunk_fid: + v9fs_fid_clunk(v9ses, oldfid); return retval; } @@ -298,17 +298,23 @@ static void wait_for_all_aios(struct kioctx *ctx) struct task_struct *tsk = current; DECLARE_WAITQUEUE(wait, tsk); + spin_lock_irq(&ctx->ctx_lock); if (!ctx->reqs_active) - return; + goto out; add_wait_queue(&ctx->wait, &wait); set_task_state(tsk, TASK_UNINTERRUPTIBLE); while (ctx->reqs_active) { + spin_unlock_irq(&ctx->ctx_lock); schedule(); set_task_state(tsk, TASK_UNINTERRUPTIBLE); + spin_lock_irq(&ctx->ctx_lock); } __set_task_state(tsk, TASK_RUNNING); remove_wait_queue(&ctx->wait, &wait); + +out: + spin_unlock_irq(&ctx->ctx_lock); } /* wait_on_sync_kiocb: @@ -424,7 +430,6 @@ static struct kiocb fastcall *__aio_get_req(struct kioctx *ctx) ring = kmap_atomic(ctx->ring_info.ring_pages[0], KM_USER0); if (ctx->reqs_active < aio_ring_avail(&ctx->ring_info, ring)) { list_add(&req->ki_list, &ctx->active_reqs); - get_ioctx(ctx); ctx->reqs_active++; okay = 1; } @@ -536,8 +541,6 @@ int fastcall aio_put_req(struct kiocb *req) spin_lock_irq(&ctx->ctx_lock); ret = __aio_put_req(ctx, req); spin_unlock_irq(&ctx->ctx_lock); - if (ret) - put_ioctx(ctx); return ret; } @@ -779,8 +782,7 @@ static int __aio_run_iocbs(struct kioctx *ctx) */ iocb->ki_users++; /* grab extra reference */ aio_run_iocb(iocb); - if (__aio_put_req(ctx, iocb)) /* drop extra ref */ - put_ioctx(ctx); + __aio_put_req(ctx, iocb); } if (!list_empty(&ctx->run_list)) return 1; @@ -997,14 +999,10 @@ put_rq: /* everything turned out well, dispose of the aiocb. */ ret = __aio_put_req(ctx, iocb); - spin_unlock_irqrestore(&ctx->ctx_lock, flags); - if (waitqueue_active(&ctx->wait)) wake_up(&ctx->wait); - if (ret) - put_ioctx(ctx); - + spin_unlock_irqrestore(&ctx->ctx_lock, flags); return ret; } diff --git a/fs/binfmt_elf.c b/fs/binfmt_elf.c index 7cb28720f90..669dbe5b031 100644 --- a/fs/binfmt_elf.c +++ b/fs/binfmt_elf.c @@ -682,6 +682,15 @@ static int load_elf_binary(struct linux_binprm *bprm, struct pt_regs *regs) retval = PTR_ERR(interpreter); if (IS_ERR(interpreter)) goto out_free_interp; + + /* + * If the binary is not readable then enforce + * mm->dumpable = 0 regardless of the interpreter's + * permissions. + */ + if (file_permission(interpreter, MAY_READ) < 0) + bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; + retval = kernel_read(interpreter, 0, bprm->buf, BINPRM_BUF_SIZE); if (retval != BINPRM_BUF_SIZE) { @@ -1178,6 +1187,10 @@ static int dump_seek(struct file *file, loff_t off) */ static int maydump(struct vm_area_struct *vma) { + /* The vma can be set up to tell us the answer directly. */ + if (vma->vm_flags & VM_ALWAYSDUMP) + return 1; + /* Do not dump I/O mapped devices or special mappings */ if (vma->vm_flags & (VM_IO | VM_RESERVED)) return 0; @@ -1424,6 +1437,32 @@ static int elf_dump_thread_status(long signr, struct elf_thread_status *t) return sz; } +static struct vm_area_struct *first_vma(struct task_struct *tsk, + struct vm_area_struct *gate_vma) +{ + struct vm_area_struct *ret = tsk->mm->mmap; + + if (ret) + return ret; + return gate_vma; +} +/* + * Helper function for iterating across a vma list. It ensures that the caller + * will visit `gate_vma' prior to terminating the search. + */ +static struct vm_area_struct *next_vma(struct vm_area_struct *this_vma, + struct vm_area_struct *gate_vma) +{ + struct vm_area_struct *ret; + + ret = this_vma->vm_next; + if (ret) + return ret; + if (this_vma == gate_vma) + return NULL; + return gate_vma; +} + /* * Actual dumper * @@ -1439,7 +1478,7 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) int segs; size_t size = 0; int i; - struct vm_area_struct *vma; + struct vm_area_struct *vma, *gate_vma; struct elfhdr *elf = NULL; loff_t offset = 0, dataoff, foffset; unsigned long limit = current->signal->rlim[RLIMIT_CORE].rlim_cur; @@ -1525,6 +1564,10 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) segs += ELF_CORE_EXTRA_PHDRS; #endif + gate_vma = get_gate_vma(current); + if (gate_vma != NULL) + segs++; + /* Set up header */ fill_elf_header(elf, segs + 1); /* including notes section */ @@ -1592,7 +1635,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) dataoff = offset = roundup(offset, ELF_EXEC_PAGESIZE); /* Write program headers for segments dump */ - for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) { + for (vma = first_vma(current, gate_vma); vma != NULL; + vma = next_vma(vma, gate_vma)) { struct elf_phdr phdr; size_t sz; @@ -1641,7 +1685,8 @@ static int elf_core_dump(long signr, struct pt_regs *regs, struct file *file) /* Align to page */ DUMP_SEEK(dataoff - foffset); - for (vma = current->mm->mmap; vma != NULL; vma = vma->vm_next) { + for (vma = first_vma(current, gate_vma); vma != NULL; + vma = next_vma(vma, gate_vma)) { unsigned long addr; if (!maydump(vma)) diff --git a/fs/binfmt_elf_fdpic.c b/fs/binfmt_elf_fdpic.c index 6e6d4568d54..a4d933a5120 100644 --- a/fs/binfmt_elf_fdpic.c +++ b/fs/binfmt_elf_fdpic.c @@ -234,6 +234,14 @@ static int load_elf_fdpic_binary(struct linux_binprm *bprm, goto error; } + /* + * If the binary is not readable then enforce + * mm->dumpable = 0 regardless of the interpreter's + * permissions. + */ + if (file_permission(interpreter, MAY_READ) < 0) + bprm->interp_flags |= BINPRM_FLAGS_ENFORCE_NONDUMP; + retval = kernel_read(interpreter, 0, bprm->buf, BINPRM_BUF_SIZE); if (retval < 0) diff --git a/fs/block_dev.c b/fs/block_dev.c index 8b18e43b82f..fc7028b685f 100644 --- a/fs/block_dev.c +++ b/fs/block_dev.c @@ -129,6 +129,46 @@ blkdev_get_block(struct inode *inode, sector_t iblock, return 0; } +static int +blkdev_get_blocks(struct inode *inode, sector_t iblock, + struct buffer_head *bh, int create) +{ + sector_t end_block = max_block(I_BDEV(inode)); + unsigned long max_blocks = bh->b_size >> inode->i_blkbits; + + if ((iblock + max_blocks) > end_block) { + max_blocks = end_block - iblock; + if ((long)max_blocks <= 0) { + if (create) + return -EIO; /* write fully beyond EOF */ + /* + * It is a read which is fully beyond EOF. We return + * a !buffer_mapped buffer + */ + max_blocks = 0; + } + } + + bh->b_bdev = I_BDEV(inode); + bh->b_blocknr = iblock; + bh->b_size = max_blocks << inode->i_blkbits; + if (max_blocks) + set_buffer_mapped(bh); + return 0; +} + +static ssize_t +blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, + loff_t offset, unsigned long nr_segs) +{ + struct file *file = iocb->ki_filp; + struct inode *inode = file->f_mapping->host; + + return blockdev_direct_IO_no_locking(rw, iocb, inode, I_BDEV(inode), + iov, offset, nr_segs, blkdev_get_blocks, NULL); +} + +#if 0 static int blk_end_aio(struct bio *bio, unsigned int bytes_done, int error) { struct kiocb *iocb = bio->bi_private; @@ -146,7 +186,7 @@ static int blk_end_aio(struct bio *bio, unsigned int bytes_done, int error) iocb->ki_nbytes = -EIO; if (atomic_dec_and_test(bio_count)) { - if (iocb->ki_nbytes < 0) + if ((long)iocb->ki_nbytes < 0) aio_complete(iocb, iocb->ki_nbytes, 0); else aio_complete(iocb, iocb->ki_left, 0); @@ -190,6 +230,12 @@ static struct page *blk_get_page(unsigned long addr, size_t count, int rw, return pvec->page[pvec->idx++]; } +/* return a page back to pvec array */ +static void blk_unget_page(struct page *page, struct pvec *pvec) +{ + pvec->page[--pvec->idx] = page; +} + static ssize_t blkdev_direct_IO(int rw, struct kiocb *iocb, const struct iovec *iov, loff_t pos, unsigned long nr_segs) @@ -278,6 +324,8 @@ same_bio: count = min(count, nbytes); goto same_bio; } + } else { + blk_unget_page(page, &pvec); } /* bio is ready, submit it */ @@ -315,6 +363,7 @@ backout: return PTR_ERR(page); goto completion; } +#endif static int blkdev_writepage(struct page *page, struct writeback_control *wbc) { diff --git a/fs/buffer.c b/fs/buffer.c index 3b116078b4c..1ad674fd348 100644 --- a/fs/buffer.c +++ b/fs/buffer.c @@ -2834,7 +2834,7 @@ int try_to_free_buffers(struct page *page) int ret = 0; BUG_ON(!PageLocked(page)); - if (PageDirty(page) || PageWriteback(page)) + if (PageWriteback(page)) return 0; if (mapping == NULL) { /* can this still happen? */ @@ -2844,6 +2844,23 @@ int try_to_free_buffers(struct page *page) spin_lock(&mapping->private_lock); ret = drop_buffers(page, &buffers_to_free); + + /* + * If the filesystem writes its buffers by hand (eg ext3) + * then we can have clean buffers against a dirty page. We + * clean the page here; otherwise the VM will never notice + * that the filesystem did any IO at all. + * + * Also, during truncate, discard_buffer will have marked all + * the page's buffers clean. We discover that here and clean + * the page also. + * + * private_lock must be held over this entire operation in order + * to synchronise against __set_page_dirty_buffers and prevent the + * dirty bit from being lost. + */ + if (ret) + cancel_dirty_page(page, PAGE_CACHE_SIZE); spin_unlock(&mapping->private_lock); out: if (buffers_to_free) { diff --git a/fs/cifs/CHANGES b/fs/cifs/CHANGES index 3539d6ef961..d04d2f7448d 100644 --- a/fs/cifs/CHANGES +++ b/fs/cifs/CHANGES @@ -1,3 +1,7 @@ +Version 1.47 +------------ +Fix oops in list_del during mount caused by unaligned string. + Version 1.46 ------------ Support deep tree mounts. Better support OS/2, Win9x (DOS) time stamps. diff --git a/fs/cifs/cifs_debug.c b/fs/cifs/cifs_debug.c index 96abeb73897..6017c465440 100644 --- a/fs/cifs/cifs_debug.c +++ b/fs/cifs/cifs_debug.c @@ -143,8 +143,8 @@ cifs_debug_data_read(char *buf, char **beginBuffer, off_t offset, ses = list_entry(tmp, struct cifsSesInfo, cifsSessionList); if((ses->serverDomain == NULL) || (ses->serverOS == NULL) || (ses->serverNOS == NULL)) { - buf += sprintf("\nentry for %s not fully displayed\n\t", - ses->serverName); + buf += sprintf(buf, "\nentry for %s not fully " + "displayed\n\t", ses->serverName); } else { length = diff --git a/fs/cifs/cifsfs.h b/fs/cifs/cifsfs.h index a243f779b36..8aa66dcf13b 100644 --- a/fs/cifs/cifsfs.h +++ b/fs/cifs/cifsfs.h @@ -100,5 +100,5 @@ extern ssize_t cifs_getxattr(struct dentry *, const char *, void *, size_t); extern ssize_t cifs_listxattr(struct dentry *, char *, size_t); extern int cifs_ioctl (struct inode * inode, struct file * filep, unsigned int command, unsigned long arg); -#define CIFS_VERSION "1.46" +#define CIFS_VERSION "1.47" #endif /* _CIFSFS_H */ diff --git a/fs/cifs/misc.c b/fs/cifs/misc.c index aedf683f011..19cc294c7c7 100644 --- a/fs/cifs/misc.c +++ b/fs/cifs/misc.c @@ -71,9 +71,7 @@ sesInfoAlloc(void) { struct cifsSesInfo *ret_buf; - ret_buf = - (struct cifsSesInfo *) kzalloc(sizeof (struct cifsSesInfo), - GFP_KERNEL); + ret_buf = kzalloc(sizeof (struct cifsSesInfo), GFP_KERNEL); if (ret_buf) { write_lock(&GlobalSMBSeslock); atomic_inc(&sesInfoAllocCount); @@ -109,9 +107,7 @@ struct cifsTconInfo * tconInfoAlloc(void) { struct cifsTconInfo *ret_buf; - ret_buf = - (struct cifsTconInfo *) kzalloc(sizeof (struct cifsTconInfo), - GFP_KERNEL); + ret_buf = kzalloc(sizeof (struct cifsTconInfo), GFP_KERNEL); if (ret_buf) { write_lock(&GlobalSMBSeslock); atomic_inc(&tconInfoAllocCount); diff --git a/fs/cifs/sess.c b/fs/cifs/sess.c index bbdda99dce6..75846463089 100644 --- a/fs/cifs/sess.c +++ b/fs/cifs/sess.c @@ -182,11 +182,14 @@ static int decode_unicode_ssetup(char ** pbcc_area, int bleft, struct cifsSesInf cFYI(1,("bleft %d",bleft)); - /* word align, if bytes remaining is not even */ - if(bleft % 2) { - bleft--; - data++; - } + /* SMB header is unaligned, so cifs servers word align start of + Unicode strings */ + data++; + bleft--; /* Windows servers do not always double null terminate + their final Unicode string - in which case we + now will not attempt to decode the byte of junk + which follows it */ + words_left = bleft / 2; /* save off server operating system */ diff --git a/fs/fs-writeback.c b/fs/fs-writeback.c index c403b66ec83..a4b142a6a2c 100644 --- a/fs/fs-writeback.c +++ b/fs/fs-writeback.c @@ -251,8 +251,19 @@ __writeback_single_inode(struct inode *inode, struct writeback_control *wbc) WARN_ON(inode->i_state & I_WILL_FREE); if ((wbc->sync_mode != WB_SYNC_ALL) && (inode->i_state & I_LOCK)) { + struct address_space *mapping = inode->i_mapping; + int ret; + list_move(&inode->i_list, &inode->i_sb->s_dirty); - return 0; + + /* + * Even if we don't actually write the inode itself here, + * we can at least start some of the data writeout.. + */ + spin_unlock(&inode_lock); + ret = do_writepages(mapping, wbc); + spin_lock(&inode_lock); + return ret; } /* diff --git a/fs/fuse/control.c b/fs/fuse/control.c index 8c58bd45399..1794305f9ed 100644 --- a/fs/fuse/control.c +++ b/fs/fuse/control.c @@ -193,8 +193,12 @@ static int fuse_ctl_get_sb(struct file_system_type *fs_type, int flags, static void fuse_ctl_kill_sb(struct super_block *sb) { + struct fuse_conn *fc; + mutex_lock(&fuse_mutex); fuse_control_sb = NULL; + list_for_each_entry(fc, &fuse_conn_list, entry) + fc->ctl_ndents = 0; mutex_unlock(&fuse_mutex); kill_litter_super(sb); diff --git a/fs/hostfs/hostfs.h b/fs/hostfs/hostfs.h index cca3fb693f9..70543b17e4c 100644 --- a/fs/hostfs/hostfs.h +++ b/fs/hostfs/hostfs.h @@ -76,7 +76,7 @@ extern int make_symlink(const char *from, const char *to); extern int unlink_file(const char *file); extern int do_mkdir(const char *file, int mode); extern int do_rmdir(const char *file); -extern int do_mknod(const char *file, int mode, int dev); +extern int do_mknod(const char *file, int mode, unsigned int major, unsigned int minor); extern int link_file(const char *from, const char *to); extern int do_readlink(char *file, char *buf, int size); extern int rename_file(char *from, char *to); diff --git a/fs/hostfs/hostfs_kern.c b/fs/hostfs/hostfs_kern.c index 1e6fc379987..69a376f35a6 100644 --- a/fs/hostfs/hostfs_kern.c +++ b/fs/hostfs/hostfs_kern.c @@ -755,7 +755,7 @@ int hostfs_mknod(struct inode *dir, struct dentry *dentry, int mode, dev_t dev) goto out_put; init_special_inode(inode, mode, dev); - err = do_mknod(name, mode, dev); + err = do_mknod(name, mode, MAJOR(dev), MINOR(dev)); if(err) goto out_free; diff --git a/fs/hostfs/hostfs_user.c b/fs/hostfs/hostfs_user.c index 23b7cee7212..1ed5ea389f1 100644 --- a/fs/hostfs/hostfs_user.c +++ b/fs/hostfs/hostfs_user.c @@ -295,11 +295,11 @@ int do_rmdir(const char *file) return(0); } -int do_mknod(const char *file, int mode, int dev) +int do_mknod(const char *file, int mode, unsigned int major, unsigned int minor) { int err; - err = mknod(file, mode, dev); + err = mknod(file, mode, makedev(major, minor)); if(err) return(-errno); return(0); } diff --git a/fs/lockd/clntlock.c b/fs/lockd/clntlock.c index 06270774516..f4d45d4d835 100644 --- a/fs/lockd/clntlock.c +++ b/fs/lockd/clntlock.c @@ -176,7 +176,7 @@ reclaimer(void *ptr) lock_kernel(); lockd_up(0); /* note: this cannot fail as lockd is already running */ - dprintk("lockd: reclaiming locks for host %s", host->h_name); + dprintk("lockd: reclaiming locks for host %s\n", host->h_name); restart: nsmstate = host->h_nsmstate; @@ -206,7 +206,7 @@ restart: host->h_reclaiming = 0; up_write(&host->h_rwsem); - dprintk("NLM: done reclaiming locks for host %s", host->h_name); + dprintk("NLM: done reclaiming locks for host %s\n", host->h_name); /* Now, wake up all processes that sleep on a blocked lock */ list_for_each_entry(block, &nlm_blocked, b_list) { diff --git a/fs/nfs/dir.c b/fs/nfs/dir.c index dee3d6c0f19..d9ba8cb0ee7 100644 --- a/fs/nfs/dir.c +++ b/fs/nfs/dir.c @@ -532,7 +532,7 @@ static int nfs_readdir(struct file *filp, void *dirent, filldir_t filldir) lock_kernel(); - res = nfs_revalidate_mapping(inode, filp->f_mapping); + res = nfs_revalidate_mapping_nolock(inode, filp->f_mapping); if (res < 0) { unlock_kernel(); return res; diff --git a/fs/nfs/file.c b/fs/nfs/file.c index fab20d06d93..9e4a2b70995 100644 --- a/fs/nfs/file.c +++ b/fs/nfs/file.c @@ -434,8 +434,9 @@ static int do_vfs_lock(struct file *file, struct file_lock *fl) BUG(); } if (res < 0) - printk(KERN_WARNING "%s: VFS is out of sync with lock manager!\n", - __FUNCTION__); + dprintk(KERN_WARNING "%s: VFS is out of sync with lock manager" + " - error %d!\n", + __FUNCTION__, res); return res; } diff --git a/fs/nfs/inode.c b/fs/nfs/inode.c index 63e47027930..d8349828283 100644 --- a/fs/nfs/inode.c +++ b/fs/nfs/inode.c @@ -665,49 +665,86 @@ int nfs_revalidate_inode(struct nfs_server *server, struct inode *inode) return __nfs_revalidate_inode(server, inode); } +static int nfs_invalidate_mapping_nolock(struct inode *inode, struct address_space *mapping) +{ + struct nfs_inode *nfsi = NFS_I(inode); + + if (mapping->nrpages != 0) { + int ret = invalidate_inode_pages2(mapping); + if (ret < 0) + return ret; + } + spin_lock(&inode->i_lock); + nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; + if (S_ISDIR(inode->i_mode)) { + memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); + /* This ensures we revalidate child dentries */ + nfsi->cache_change_attribute = jiffies; + } + spin_unlock(&inode->i_lock); + nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); + dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n", + inode->i_sb->s_id, (long long)NFS_FILEID(inode)); + return 0; +} + +static int nfs_invalidate_mapping(struct inode *inode, struct address_space *mapping) +{ + int ret = 0; + + mutex_lock(&inode->i_mutex); + if (NFS_I(inode)->cache_validity & NFS_INO_INVALID_DATA) { + ret = nfs_sync_mapping(mapping); + if (ret == 0) + ret = nfs_invalidate_mapping_nolock(inode, mapping); + } + mutex_unlock(&inode->i_mutex); + return ret; +} + /** - * nfs_revalidate_mapping - Revalidate the pagecache + * nfs_revalidate_mapping_nolock - Revalidate the pagecache * @inode - pointer to host inode * @mapping - pointer to mapping */ -int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) +int nfs_revalidate_mapping_nolock(struct inode *inode, struct address_space *mapping) { struct nfs_inode *nfsi = NFS_I(inode); int ret = 0; - if (NFS_STALE(inode)) - ret = -ESTALE; if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) - || nfs_attribute_timeout(inode)) + || nfs_attribute_timeout(inode) || NFS_STALE(inode)) { ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); - if (ret < 0) - goto out; + if (ret < 0) + goto out; + } + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + ret = nfs_invalidate_mapping_nolock(inode, mapping); +out: + return ret; +} - if (nfsi->cache_validity & NFS_INO_INVALID_DATA) { - if (mapping->nrpages != 0) { - if (S_ISREG(inode->i_mode)) { - ret = nfs_sync_mapping(mapping); - if (ret < 0) - goto out; - } - ret = invalidate_inode_pages2(mapping); - if (ret < 0) - goto out; - } - spin_lock(&inode->i_lock); - nfsi->cache_validity &= ~NFS_INO_INVALID_DATA; - if (S_ISDIR(inode->i_mode)) { - memset(nfsi->cookieverf, 0, sizeof(nfsi->cookieverf)); - /* This ensures we revalidate child dentries */ - nfsi->cache_change_attribute = jiffies; - } - spin_unlock(&inode->i_lock); +/** + * nfs_revalidate_mapping - Revalidate the pagecache + * @inode - pointer to host inode + * @mapping - pointer to mapping + * + * This version of the function will take the inode->i_mutex and attempt to + * flush out all dirty data if it needs to invalidate the page cache. + */ +int nfs_revalidate_mapping(struct inode *inode, struct address_space *mapping) +{ + struct nfs_inode *nfsi = NFS_I(inode); + int ret = 0; - nfs_inc_stats(inode, NFSIOS_DATAINVALIDATE); - dfprintk(PAGECACHE, "NFS: (%s/%Ld) data cache invalidated\n", - inode->i_sb->s_id, - (long long)NFS_FILEID(inode)); + if ((nfsi->cache_validity & NFS_INO_REVAL_PAGECACHE) + || nfs_attribute_timeout(inode) || NFS_STALE(inode)) { + ret = __nfs_revalidate_inode(NFS_SERVER(inode), inode); + if (ret < 0) + goto out; } + if (nfsi->cache_validity & NFS_INO_INVALID_DATA) + ret = nfs_invalidate_mapping(inode, mapping); out: return ret; } diff --git a/fs/nfs/symlink.c b/fs/nfs/symlink.c index 6c686112cc0..525c136c7d8 100644 --- a/fs/nfs/symlink.c +++ b/fs/nfs/symlink.c @@ -50,7 +50,9 @@ static void *nfs_follow_link(struct dentry *dentry, struct nameidata *nd) { struct inode *inode = dentry->d_inode; struct page *page; - void *err = ERR_PTR(nfs_revalidate_mapping(inode, inode->i_mapping)); + void *err; + + err = ERR_PTR(nfs_revalidate_mapping_nolock(inode, inode->i_mapping)); if (err) goto read_failed; page = read_cache_page(&inode->i_data, 0, diff --git a/fs/nfsd/export.c b/fs/nfsd/export.c index 248dd92e6a5..49c310b8492 100644 --- a/fs/nfsd/export.c +++ b/fs/nfsd/export.c @@ -35,7 +35,6 @@ #include <linux/lockd/bind.h> #define NFSDDBG_FACILITY NFSDDBG_EXPORT -#define NFSD_PARANOIA 1 typedef struct auth_domain svc_client; typedef struct svc_export svc_export; diff --git a/fs/nfsd/nfs3xdr.c b/fs/nfsd/nfs3xdr.c index 277df40f098..e695660921e 100644 --- a/fs/nfsd/nfs3xdr.c +++ b/fs/nfsd/nfs3xdr.c @@ -990,15 +990,16 @@ encode_entry(struct readdir_cd *ccd, const char *name, } int -nfs3svc_encode_entry(struct readdir_cd *cd, const char *name, - int namlen, loff_t offset, ino_t ino, unsigned int d_type) +nfs3svc_encode_entry(void *cd, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int d_type) { return encode_entry(cd, name, namlen, offset, ino, d_type, 0); } int -nfs3svc_encode_entry_plus(struct readdir_cd *cd, const char *name, - int namlen, loff_t offset, ino_t ino, unsigned int d_type) +nfs3svc_encode_entry_plus(void *cd, const char *name, + int namlen, loff_t offset, u64 ino, + unsigned int d_type) { return encode_entry(cd, name, namlen, offset, ino, d_type, 1); } diff --git a/fs/nfsd/nfs4xdr.c b/fs/nfsd/nfs4xdr.c index fea46368afb..18aa9440df1 100644 --- a/fs/nfsd/nfs4xdr.c +++ b/fs/nfsd/nfs4xdr.c @@ -1880,9 +1880,10 @@ nfsd4_encode_rdattr_error(__be32 *p, int buflen, __be32 nfserr) } static int -nfsd4_encode_dirent(struct readdir_cd *ccd, const char *name, int namlen, - loff_t offset, ino_t ino, unsigned int d_type) +nfsd4_encode_dirent(void *ccdv, const char *name, int namlen, + loff_t offset, u64 ino, unsigned int d_type) { + struct readdir_cd *ccd = ccdv; struct nfsd4_readdir *cd = container_of(ccd, struct nfsd4_readdir, common); int buflen; __be32 *p = cd->buffer; diff --git a/fs/nfsd/nfsfh.c b/fs/nfsd/nfsfh.c index b06bf9f70ef..c59d6fbb7a6 100644 --- a/fs/nfsd/nfsfh.c +++ b/fs/nfsd/nfsfh.c @@ -24,8 +24,6 @@ #include <linux/nfsd/nfsd.h> #define NFSDDBG_FACILITY NFSDDBG_FH -#define NFSD_PARANOIA 1 -/* #define NFSD_DEBUG_VERBOSE 1 */ static int nfsd_nr_verified; @@ -230,13 +228,12 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) error = nfserrno(PTR_ERR(dentry)); goto out; } -#ifdef NFSD_PARANOIA + if (S_ISDIR(dentry->d_inode->i_mode) && (dentry->d_flags & DCACHE_DISCONNECTED)) { printk("nfsd: find_fh_dentry returned a DISCONNECTED directory: %s/%s\n", dentry->d_parent->d_name.name, dentry->d_name.name); } -#endif fhp->fh_dentry = dentry; fhp->fh_export = exp; @@ -267,12 +264,13 @@ fh_verify(struct svc_rqst *rqstp, struct svc_fh *fhp, int type, int access) /* Finally, check access permissions. */ error = nfsd_permission(exp, dentry, access); -#ifdef NFSD_PARANOIA_EXTREME if (error) { - printk("fh_verify: %s/%s permission failure, acc=%x, error=%d\n", - dentry->d_parent->d_name.name, dentry->d_name.name, access, (error >> 24)); + dprintk("fh_verify: %s/%s permission failure, " + "acc=%x, error=%d\n", + dentry->d_parent->d_name.name, + dentry->d_name.name, + access, ntohl(error)); } -#endif out: if (exp && !IS_ERR(exp)) exp_put(exp); diff --git a/fs/nfsd/nfssvc.c b/fs/nfsd/nfssvc.c index 0aaccb03bf7..fbf5d51947e 100644 --- a/fs/nfsd/nfssvc.c +++ b/fs/nfsd/nfssvc.c @@ -72,7 +72,7 @@ static struct svc_program nfsd_acl_program = { .pg_prog = NFS_ACL_PROGRAM, .pg_nvers = NFSD_ACL_NRVERS, .pg_vers = nfsd_acl_versions, - .pg_name = "nfsd", + .pg_name = "nfsacl", .pg_class = "nfsd", .pg_stats = &nfsd_acl_svcstats, .pg_authenticate = &svc_set_client, @@ -118,16 +118,16 @@ int nfsd_vers(int vers, enum vers_op change) switch(change) { case NFSD_SET: nfsd_versions[vers] = nfsd_version[vers]; - break; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) if (vers < NFSD_ACL_NRVERS) - nfsd_acl_version[vers] = nfsd_acl_version[vers]; + nfsd_acl_versions[vers] = nfsd_acl_version[vers]; #endif + break; case NFSD_CLEAR: nfsd_versions[vers] = NULL; #if defined(CONFIG_NFSD_V2_ACL) || defined(CONFIG_NFSD_V3_ACL) if (vers < NFSD_ACL_NRVERS) - nfsd_acl_version[vers] = NULL; + nfsd_acl_versions[vers] = NULL; #endif break; case NFSD_TEST: diff --git a/fs/nfsd/nfsxdr.c b/fs/nfsd/nfsxdr.c index f5243f94399..6555c50d900 100644 --- a/fs/nfsd/nfsxdr.c +++ b/fs/nfsd/nfsxdr.c @@ -462,9 +462,10 @@ nfssvc_encode_statfsres(struct svc_rqst *rqstp, __be32 *p, } int -nfssvc_encode_entry(struct readdir_cd *ccd, const char *name, - int namlen, loff_t offset, ino_t ino, unsigned int d_type) +nfssvc_encode_entry(void *ccdv, const char *name, + int namlen, loff_t offset, u64 ino, unsigned int d_type) { + struct readdir_cd *ccd = ccdv; struct nfsd_readdirres *cd = container_of(ccd, struct nfsd_readdirres, common); __be32 *p = cd->buffer; int buflen, slen; diff --git a/fs/nfsd/vfs.c b/fs/nfsd/vfs.c index 7a79c23aa6d..8283236c6a0 100644 --- a/fs/nfsd/vfs.c +++ b/fs/nfsd/vfs.c @@ -59,7 +59,6 @@ #include <asm/uaccess.h> #define NFSDDBG_FACILITY NFSDDBG_FILEOP -#define NFSD_PARANOIA /* We must ignore files (but only files) which might have mandatory @@ -822,7 +821,8 @@ nfsd_read_actor(read_descriptor_t *desc, struct page *page, unsigned long offset rqstp->rq_res.page_len = size; } else if (page != pp[-1]) { get_page(page); - put_page(*pp); + if (*pp) + put_page(*pp); *pp = page; rqstp->rq_resused++; rqstp->rq_res.page_len += size; @@ -1244,7 +1244,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, __be32 err; int host_err; __u32 v_mtime=0, v_atime=0; - int v_mode=0; err = nfserr_perm; if (!flen) @@ -1281,16 +1280,11 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, goto out; if (createmode == NFS3_CREATE_EXCLUSIVE) { - /* while the verifier would fit in mtime+atime, - * solaris7 gets confused (bugid 4218508) if these have - * the high bit set, so we use the mode as well + /* solaris7 gets confused (bugid 4218508) if these have + * the high bit set, so just clear the high bits. */ v_mtime = verifier[0]&0x7fffffff; v_atime = verifier[1]&0x7fffffff; - v_mode = S_IFREG - | ((verifier[0]&0x80000000) >> (32-7)) /* u+x */ - | ((verifier[1]&0x80000000) >> (32-9)) /* u+r */ - ; } if (dchild->d_inode) { @@ -1318,7 +1312,6 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, case NFS3_CREATE_EXCLUSIVE: if ( dchild->d_inode->i_mtime.tv_sec == v_mtime && dchild->d_inode->i_atime.tv_sec == v_atime - && dchild->d_inode->i_mode == v_mode && dchild->d_inode->i_size == 0 ) break; /* fallthru */ @@ -1340,26 +1333,22 @@ nfsd_create_v3(struct svc_rqst *rqstp, struct svc_fh *fhp, } if (createmode == NFS3_CREATE_EXCLUSIVE) { - /* Cram the verifier into atime/mtime/mode */ + /* Cram the verifier into atime/mtime */ iap->ia_valid = ATTR_MTIME|ATTR_ATIME - | ATTR_MTIME_SET|ATTR_ATIME_SET - | ATTR_MODE; + | ATTR_MTIME_SET|ATTR_ATIME_SET; /* XXX someone who knows this better please fix it for nsec */ iap->ia_mtime.tv_sec = v_mtime; iap->ia_atime.tv_sec = v_atime; iap->ia_mtime.tv_nsec = 0; iap->ia_atime.tv_nsec = 0; - iap->ia_mode = v_mode; } /* Set file attributes. - * Mode has already been set but we might need to reset it - * for CREATE_EXCLUSIVE * Irix appears to send along the gid when it tries to * implement setgid directories via NFS. Clear out all that cruft. */ set_attr: - if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID)) != 0) { + if ((iap->ia_valid &= ~(ATTR_UID|ATTR_GID|ATTR_MODE)) != 0) { __be32 err2 = nfsd_setattr(rqstp, resfhp, iap, 0, (time_t)0); if (err2) err = err2; @@ -1726,7 +1715,7 @@ out: */ __be32 nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, - struct readdir_cd *cdp, encode_dent_fn func) + struct readdir_cd *cdp, filldir_t func) { __be32 err; int host_err; @@ -1751,7 +1740,7 @@ nfsd_readdir(struct svc_rqst *rqstp, struct svc_fh *fhp, loff_t *offsetp, do { cdp->err = nfserr_eof; /* will be cleared on successful read */ - host_err = vfs_readdir(file, (filldir_t) func, cdp); + host_err = vfs_readdir(file, func, cdp); } while (host_err >=0 && cdp->err == nfs_ok); if (host_err) err = nfserrno(host_err); diff --git a/fs/ntfs/aops.c b/fs/ntfs/aops.c index 7b2c8f4f6a6..629e7abdd84 100644 --- a/fs/ntfs/aops.c +++ b/fs/ntfs/aops.c @@ -92,10 +92,12 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) ofs = 0; if (file_ofs < init_size) ofs = init_size - file_ofs; + local_irq_save(flags); kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ); memset(kaddr + bh_offset(bh) + ofs, 0, bh->b_size - ofs); kunmap_atomic(kaddr, KM_BIO_SRC_IRQ); + local_irq_restore(flags); flush_dcache_page(page); } } else { @@ -143,11 +145,13 @@ static void ntfs_end_buffer_async_read(struct buffer_head *bh, int uptodate) recs = PAGE_CACHE_SIZE / rec_size; /* Should have been verified before we got here... */ BUG_ON(!recs); + local_irq_save(flags); kaddr = kmap_atomic(page, KM_BIO_SRC_IRQ); for (i = 0; i < recs; i++) post_read_mst_fixup((NTFS_RECORD*)(kaddr + i * rec_size), rec_size); kunmap_atomic(kaddr, KM_BIO_SRC_IRQ); + local_irq_restore(flags); flush_dcache_page(page); if (likely(page_uptodate && !PageError(page))) SetPageUptodate(page); diff --git a/fs/ocfs2/ocfs2_fs.h b/fs/ocfs2/ocfs2_fs.h index c99e9058c19..e61e218f5e0 100644 --- a/fs/ocfs2/ocfs2_fs.h +++ b/fs/ocfs2/ocfs2_fs.h @@ -587,7 +587,7 @@ static inline u64 ocfs2_backup_super_blkno(struct super_block *sb, int index) if (index >= 0 && index < OCFS2_MAX_BACKUP_SUPERBLOCKS) { offset <<= (2 * index); - offset /= sb->s_blocksize; + offset >>= sb->s_blocksize_bits; return offset; } diff --git a/fs/proc/base.c b/fs/proc/base.c index 77a57b5799c..1a979ea3b37 100644 --- a/fs/proc/base.c +++ b/fs/proc/base.c @@ -371,9 +371,11 @@ static int mounts_open(struct inode *inode, struct file *file) if (task) { task_lock(task); - ns = task->nsproxy->mnt_ns; - if (ns) - get_mnt_ns(ns); + if (task->nsproxy) { + ns = task->nsproxy->mnt_ns; + if (ns) + get_mnt_ns(ns); + } task_unlock(task); put_task_struct(task); } @@ -2326,13 +2328,23 @@ static int proc_task_readdir(struct file * filp, void * dirent, filldir_t filldi { struct dentry *dentry = filp->f_path.dentry; struct inode *inode = dentry->d_inode; - struct task_struct *leader = get_proc_task(inode); + struct task_struct *leader = NULL; struct task_struct *task; int retval = -ENOENT; ino_t ino; int tid; unsigned long pos = filp->f_pos; /* avoiding "long long" filp->f_pos */ + task = get_proc_task(inode); + if (!task) + goto out_no_task; + rcu_read_lock(); + if (pid_alive(task)) { + leader = task->group_leader; + get_task_struct(leader); + } + rcu_read_unlock(); + put_task_struct(task); if (!leader) goto out_no_task; retval = 0; diff --git a/fs/reiserfs/file.c b/fs/reiserfs/file.c index 99b6f329ba2..5109f1d5e7f 100644 --- a/fs/reiserfs/file.c +++ b/fs/reiserfs/file.c @@ -48,6 +48,11 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp) } mutex_lock(&inode->i_mutex); + + mutex_lock(&(REISERFS_I(inode)->i_mmap)); + if (REISERFS_I(inode)->i_flags & i_ever_mapped) + REISERFS_I(inode)->i_flags &= ~i_pack_on_close_mask; + reiserfs_write_lock(inode->i_sb); /* freeing preallocation only involves relogging blocks that * are already in the current transaction. preallocation gets @@ -100,11 +105,24 @@ static int reiserfs_file_release(struct inode *inode, struct file *filp) err = reiserfs_truncate_file(inode, 0); } out: + mutex_unlock(&(REISERFS_I(inode)->i_mmap)); mutex_unlock(&inode->i_mutex); reiserfs_write_unlock(inode->i_sb); return err; } +static int reiserfs_file_mmap(struct file *file, struct vm_area_struct *vma) +{ + struct inode *inode; + + inode = file->f_path.dentry->d_inode; + mutex_lock(&(REISERFS_I(inode)->i_mmap)); + REISERFS_I(inode)->i_flags |= i_ever_mapped; + mutex_unlock(&(REISERFS_I(inode)->i_mmap)); + + return generic_file_mmap(file, vma); +} + static void reiserfs_vfs_truncate_file(struct inode *inode) { reiserfs_truncate_file(inode, 1); @@ -1527,7 +1545,7 @@ const struct file_operations reiserfs_file_operations = { #ifdef CONFIG_COMPAT .compat_ioctl = reiserfs_compat_ioctl, #endif - .mmap = generic_file_mmap, + .mmap = reiserfs_file_mmap, .open = generic_file_open, .release = reiserfs_file_release, .fsync = reiserfs_sync_file, diff --git a/fs/reiserfs/inode.c b/fs/reiserfs/inode.c index f3d1c4a7797..9fcbfe31697 100644 --- a/fs/reiserfs/inode.c +++ b/fs/reiserfs/inode.c @@ -1125,6 +1125,7 @@ static void init_inode(struct inode *inode, struct treepath *path) REISERFS_I(inode)->i_prealloc_count = 0; REISERFS_I(inode)->i_trans_id = 0; REISERFS_I(inode)->i_jl = NULL; + mutex_init(&(REISERFS_I(inode)->i_mmap)); reiserfs_init_acl_access(inode); reiserfs_init_acl_default(inode); reiserfs_init_xattr_rwsem(inode); @@ -1832,6 +1833,7 @@ int reiserfs_new_inode(struct reiserfs_transaction_handle *th, REISERFS_I(inode)->i_attrs = REISERFS_I(dir)->i_attrs & REISERFS_INHERIT_MASK; sd_attrs_to_i_attrs(REISERFS_I(inode)->i_attrs, inode); + mutex_init(&(REISERFS_I(inode)->i_mmap)); reiserfs_init_acl_access(inode); reiserfs_init_acl_default(inode); reiserfs_init_xattr_rwsem(inode); diff --git a/fs/ufs/balloc.c b/fs/ufs/balloc.c index 2e0021e8f36..638f4c585e8 100644 --- a/fs/ufs/balloc.c +++ b/fs/ufs/balloc.c @@ -227,24 +227,27 @@ failed: * We can come here from ufs_writepage or ufs_prepare_write, * locked_page is argument of these functions, so we already lock it. */ -static void ufs_change_blocknr(struct inode *inode, unsigned int baseblk, +static void ufs_change_blocknr(struct inode *inode, unsigned int beg, unsigned int count, unsigned int oldb, unsigned int newb, struct page *locked_page) { - unsigned int blk_per_page = 1 << (PAGE_CACHE_SHIFT - inode->i_blkbits); - struct address_space *mapping = inode->i_mapping; - pgoff_t index, cur_index = locked_page->index; - unsigned int i, j; + const unsigned mask = (1 << (PAGE_CACHE_SHIFT - inode->i_blkbits)) - 1; + struct address_space * const mapping = inode->i_mapping; + pgoff_t index, cur_index; + unsigned end, pos, j; struct page *page; struct buffer_head *head, *bh; UFSD("ENTER, ino %lu, count %u, oldb %u, newb %u\n", inode->i_ino, count, oldb, newb); + BUG_ON(!locked_page); BUG_ON(!PageLocked(locked_page)); - for (i = 0; i < count; i += blk_per_page) { - index = (baseblk+i) >> (PAGE_CACHE_SHIFT - inode->i_blkbits); + cur_index = locked_page->index; + + for (end = count + beg; beg < end; beg = (beg | mask) + 1) { + index = beg >> (PAGE_CACHE_SHIFT - inode->i_blkbits); if (likely(cur_index != index)) { page = ufs_get_locked_page(mapping, index); @@ -253,21 +256,32 @@ static void ufs_change_blocknr(struct inode *inode, unsigned int baseblk, } else page = locked_page; - j = i; head = page_buffers(page); bh = head; + pos = beg & mask; + for (j = 0; j < pos; ++j) + bh = bh->b_this_page; + j = 0; do { - if (likely(bh->b_blocknr == j + oldb && j < count)) { - unmap_underlying_metadata(bh->b_bdev, - bh->b_blocknr); - bh->b_blocknr = newb + j++; - mark_buffer_dirty(bh); + if (buffer_mapped(bh)) { + pos = bh->b_blocknr - oldb; + if (pos < count) { + UFSD(" change from %llu to %llu\n", + (unsigned long long)pos + oldb, + (unsigned long long)pos + newb); + bh->b_blocknr = newb + pos; + unmap_underlying_metadata(bh->b_bdev, + bh->b_blocknr); + mark_buffer_dirty(bh); + ++j; + } } bh = bh->b_this_page; } while (bh != head); - set_page_dirty(page); + if (j) + set_page_dirty(page); if (likely(cur_index != index)) ufs_put_locked_page(page); @@ -415,14 +429,14 @@ unsigned ufs_new_fragments(struct inode * inode, __fs32 * p, unsigned fragment, } result = ufs_alloc_fragments (inode, cgno, goal, request, err); if (result) { + ufs_clear_frags(inode, result + oldcount, newcount - oldcount, + locked_page != NULL); ufs_change_blocknr(inode, fragment - oldcount, oldcount, tmp, result, locked_page); *p = cpu_to_fs32(sb, result); *err = 0; UFS_I(inode)->i_lastfrag = max_t(u32, UFS_I(inode)->i_lastfrag, fragment + count); - ufs_clear_frags(inode, result + oldcount, newcount - oldcount, - locked_page != NULL); unlock_super(sb); if (newcount < request) ufs_free_fragments (inode, result + newcount, request - newcount); diff --git a/fs/ufs/inode.c b/fs/ufs/inode.c index 2fbab0aab68..4295ca91cf8 100644 --- a/fs/ufs/inode.c +++ b/fs/ufs/inode.c @@ -242,7 +242,8 @@ repeat: goal = tmp + uspi->s_fpb; tmp = ufs_new_fragments (inode, p, fragment - blockoff, goal, required + blockoff, - err, locked_page); + err, + phys != NULL ? locked_page : NULL); } /* * We will extend last allocated block @@ -250,7 +251,7 @@ repeat: else if (lastblock == block) { tmp = ufs_new_fragments(inode, p, fragment - (blockoff - lastblockoff), fs32_to_cpu(sb, *p), required + (blockoff - lastblockoff), - err, locked_page); + err, phys != NULL ? locked_page : NULL); } else /* (lastblock > block) */ { /* * We will allocate new block before last allocated block @@ -261,7 +262,8 @@ repeat: goal = tmp + uspi->s_fpb; } tmp = ufs_new_fragments(inode, p, fragment - blockoff, - goal, uspi->s_fpb, err, locked_page); + goal, uspi->s_fpb, err, + phys != NULL ? locked_page : NULL); } if (!tmp) { if ((!blockoff && *p) || @@ -438,9 +440,11 @@ int ufs_getfrag_block(struct inode *inode, sector_t fragment, struct buffer_head * it much more readable: */ #define GET_INODE_DATABLOCK(x) \ - ufs_inode_getfrag(inode, x, fragment, 1, &err, &phys, &new, bh_result->b_page) + ufs_inode_getfrag(inode, x, fragment, 1, &err, &phys, &new,\ + bh_result->b_page) #define GET_INODE_PTR(x) \ - ufs_inode_getfrag(inode, x, fragment, uspi->s_fpb, &err, NULL, NULL, NULL) + ufs_inode_getfrag(inode, x, fragment, uspi->s_fpb, &err, NULL, NULL,\ + bh_result->b_page) #define GET_INDIRECT_DATABLOCK(x) \ ufs_inode_getblock(inode, bh, x, fragment, \ &err, &phys, &new, bh_result->b_page) diff --git a/fs/ufs/truncate.c b/fs/ufs/truncate.c index ea11d04c41a..0437b0a6fe9 100644 --- a/fs/ufs/truncate.c +++ b/fs/ufs/truncate.c @@ -109,10 +109,10 @@ static int ufs_trunc_direct (struct inode * inode) tmp = fs32_to_cpu(sb, *p); if (!tmp ) ufs_panic (sb, "ufs_trunc_direct", "internal error"); + frag2 -= frag1; frag1 = ufs_fragnum (frag1); - frag2 = ufs_fragnum (frag2); - ufs_free_fragments (inode, tmp + frag1, frag2 - frag1); + ufs_free_fragments(inode, tmp + frag1, frag2); mark_inode_dirty(inode); frag_to_free = tmp + frag1; |